Signal Processing for Automated EEG QualityAssessment
by
Sherif Haggag
Submitted in fulfilment of the requirements for the degree ofDoctor of Philosophy
Deakin UniversityFebruary 2016
To My Family
ii
Table of Contents
Table of Contents iii
List of Tables vi
List of Figures vii
Research Publications xi
Abstract xiii
1 Introduction 11.1 Background and Motivation . . . . . . . . . . . . . . . . . . . . 11.2 Aims and Objectives . . . . . . . . . . . . . . . . . . . . . . . . 21.3 Thesis Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2 Literature Review 62.1 What is meant by a Neuron? . . . . . . . . . . . . . . . . . . . . 62.2 Neural Signal in the brain . . . . . . . . . . . . . . . . . . . . . 102.3 Signal Acquisition . . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.3.1 Invasive and Partially Invasive acquisition . . . . . . . . 142.3.2 Non-Invasive acquisition . . . . . . . . . . . . . . . . . . 15
2.4 EEG: an electrical activity recording . . . . . . . . . . . . . . . 162.4.1 EEG Bands . . . . . . . . . . . . . . . . . . . . . . . . . 192.4.2 Recording of EEG . . . . . . . . . . . . . . . . . . . . . 22
2.5 EEG Applications . . . . . . . . . . . . . . . . . . . . . . . . . . 252.5.1 Evoked Related Potentials . . . . . . . . . . . . . . . . . 282.5.2 Quantitative EEG . . . . . . . . . . . . . . . . . . . . . 292.5.3 EEG Biofeedback . . . . . . . . . . . . . . . . . . . . . . 292.5.4 Brain Computer Interface . . . . . . . . . . . . . . . . . 30
3 Critical Review on Feature Extraction, Spike Sorting and Qual-ity Assessment Measures 363.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
iii
3.2 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . 373.3 Spike Sorting . . . . . . . . . . . . . . . . . . . . . . . . . . . . 463.4 Noise level Estimation and Quality Assessment Measure . . . . 543.5 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59
4 Feature Extraction and Spike Sorting 604.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 604.2 Feature Extraction Methods . . . . . . . . . . . . . . . . . . . . 61
4.2.1 Diffusion Maps . . . . . . . . . . . . . . . . . . . . . . . 624.2.2 Cepstrum Coefficients . . . . . . . . . . . . . . . . . . . 634.2.3 Mel-Frequency Cepstral Coefficients . . . . . . . . . . . 73
4.3 Spike Sorting . . . . . . . . . . . . . . . . . . . . . . . . . . . . 764.4 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 85
5 Noise Level Estimation 875.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 875.2 Noise Estimation Methodology . . . . . . . . . . . . . . . . . . . 885.3 Noise Level Estimation Results . . . . . . . . . . . . . . . . . . 91
5.3.1 Matlab SNR function . . . . . . . . . . . . . . . . . . . . 915.3.2 Neural signal recorded by Multichannel systems . . . . . 935.3.3 EEG signal recorded by Neurofax EEG system . . . . . . 97
5.4 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 99
6 Automated Quality Assessment Scores 1016.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1026.2 Recording EEG data . . . . . . . . . . . . . . . . . . . . . . . . 1066.3 Splitting EEG data frequency bands . . . . . . . . . . . . . . . 1076.4 Score 1: Analysing the amplitude of each channel . . . . . . . . 1096.5 Score 2: Highest Amplitude Score . . . . . . . . . . . . . . . . . 1116.6 Score 3: Dominant Frequency Score . . . . . . . . . . . . . . . . 1156.7 Score 4: Beta Amplitude Score . . . . . . . . . . . . . . . . . . 1186.8 Score 5: Beta Sinusoidal Score . . . . . . . . . . . . . . . . . . . 1206.9 Score 6: Theta Amplitude Score . . . . . . . . . . . . . . . . . . 1236.10 Score 7: Symmetry Analysis Score . . . . . . . . . . . . . . . . . 1256.11 Score 8: Morphology Score . . . . . . . . . . . . . . . . . . . . . 1276.12 Score 9: Eye movement Analysis Score . . . . . . . . . . . . . . 1286.13 Amplitude and Frequency Analysis Scores (10, 11, 12) . . . . . . 1316.14 General Summary Score (GSS) . . . . . . . . . . . . . . . . . . 1356.15 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 138
7 Quality Assessment Scores and BCI 1397.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1397.2 BCI Input, Importance and Applications . . . . . . . . . . . . . 1417.3 BCI Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . 142
iv
7.3.1 BioSig . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1427.3.2 BCI2000 . . . . . . . . . . . . . . . . . . . . . . . . . . . 1437.3.3 OpenViBE . . . . . . . . . . . . . . . . . . . . . . . . . . 1437.3.4 BCILAB . . . . . . . . . . . . . . . . . . . . . . . . . . . 143
7.4 Applying Scores to BCI applications . . . . . . . . . . . . . . . 1447.5 Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1477.6 BCILAB plugin . . . . . . . . . . . . . . . . . . . . . . . . . . . 1497.7 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 154
8 Conclusions and Future Work 1558.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1558.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 159
References 161
v
List of Tables
3.1 Comparison between the common Spike Sorting techniques. . . . 53
4.1 Number of spikes in each cluster using Haar and Cepstrum rep-resentation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 70
4.2 Number of correctly assigned spikes in each cluster using Cep-strum representation . . . . . . . . . . . . . . . . . . . . . . . . 71
4.3 Number of correctly assigned spikes in each cluster using Haarrepresentation. . . . . . . . . . . . . . . . . . . . . . . . . . . . 72
4.4 Haar’s Confusion Matrix. . . . . . . . . . . . . . . . . . . . . . . 724.5 Cepstrum’s Confusion Matrix. . . . . . . . . . . . . . . . . . . . 724.6 Clustering accuracy comparison using different noise levels. . . . 83
6.1 Percentage of each score in the General Summary Score. . . . . 137
7.1 The relationship between trials, scores and sorting accuracy isshown. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 146
7.2 Relation between quality assessment scores and sorting accuracyunder different noise levels. . . . . . . . . . . . . . . . . . . . . 149
7.3 Relationship between the proposed quality scores and noise. . . 153
vi
List of Figures
2.1 Neurons are the building blocks of the nervous system [14] . . . 72.2 Neuron’s most important parts [14] . . . . . . . . . . . . . . . . 82.3 Chemical signals pass between neurons through a site called
Synapse [34]. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 112.4 The negativity of the resting neuron’s cell membrane. . . . . . . 122.5 Invasive Brain signal acquisition [43]. . . . . . . . . . . . . . . . 152.6 Partially Invasive Brain signal acquisition [44]. . . . . . . . . . . 162.7 Invasive and non-Invasive Brain signal acquisition [46]. . . . . . 172.8 Different EEG bands [61]. . . . . . . . . . . . . . . . . . . . . . 202.9 EEG cables which has the sensitive electrodes at the end . . . . 232.10 10-20 International System details. . . . . . . . . . . . . . . . . 242.11 SynAmps 2/RT is the latest EEG amplifier from Compumedics
Neuroscan. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 252.12 Curry Software and Impedance test. . . . . . . . . . . . . . . . . 262.13 Quik-Cap Electrode Placement System. . . . . . . . . . . . . . . 262.14 Common steps of any BCI application [97]. . . . . . . . . . . . . 312.15 BCI Functional components and feedback loops [99]. . . . . . . 32
3.1 The signal processing steps used to obtain single unit activity. . 373.2 K-means calculation steps. . . . . . . . . . . . . . . . . . . . . . 483.3 Steps of the Valley Seeking clustering algorithm. . . . . . . . . 49
4.1 Sample signal representation. . . . . . . . . . . . . . . . . . . . 654.2 DFT of the signal. . . . . . . . . . . . . . . . . . . . . . . . . . 654.3 Log magnitude of the DFT of the signal. . . . . . . . . . . . . 664.4 Cepstrum representation of the signal. . . . . . . . . . . . . . . 66
vii
4.5 Haar representation of signal in Fig. 4.1. . . . . . . . . . . . . . 664.6 Cepstrum representation. . . . . . . . . . . . . . . . . . . . . . . 674.7 Haar and Cepstrum output in terms of number of clusters and
number of spikes per cluster. . . . . . . . . . . . . . . . . . . . . 714.8 The main steps of Spike Sorting. . . . . . . . . . . . . . . . . . . 784.9 Observable and hidden states of the Hidden Markov Model. . . 794.10 The HMM states applied on the spikes. . . . . . . . . . . . . . . 794.11 HMM states and the transitions from one state to another. . . 804.12 Clustering accuracy comparison using different levels of noise . . 84
5.1 MFCC calculation steps . . . . . . . . . . . . . . . . . . . . . . 895.2 Noise Estimation Accuracy using different signals with different
Signal to Noise Ratio (SNR). . . . . . . . . . . . . . . . . . . . . 925.3 Relationship between the number of iterations used in HMM
and the accuracy of classification . . . . . . . . . . . . . . . . . 945.4 Classification Accuracy using different signals with different Sig-
nal to Noise Ratio (SNR). . . . . . . . . . . . . . . . . . . . . . 955.5 Relationship between the number of samples used in HMM and
the accuracy of classification . . . . . . . . . . . . . . . . . . . . 955.6 Relationship between the number of states used in HMM and
the accuracy of classification . . . . . . . . . . . . . . . . . . . . 965.7 Classification Accuracy using different Signal to Noise Ratio
(SNR) applied to EEG signal which is recorded by the 10-20international system. . . . . . . . . . . . . . . . . . . . . . . . . 97
5.8 Relationship between the number of iterations used in HMM forthe EEG signal and the accuracy of classification . . . . . . . . 98
5.9 Relationship between the number of EEG signals used by HMMfor training and the accuracy of classification . . . . . . . . . . . 98
5.10 Relationship between the number of states used in HMM forthe EEG signal and the accuracy of classification . . . . . . . . 99
5.11 Relationship between the number of noise levels and the accu-racy of classification using two clusters error tolerance . . . . . . 99
6.1 Eye blinking/movement effect on the EEG signal. . . . . . . . . 103
viii
6.2 EEG raw data and the main frequency bands. . . . . . . . . . . 1056.3 International 10-20 system. . . . . . . . . . . . . . . . . . . . . . 1086.4 Relation between General Amplitude Score and SNR. . . . . . . 1116.5 Histogram of the amplitude of the EEG data. . . . . . . . . . . 1126.6 Relation between Highest Amplitude Score and SNR. . . . . . . 1146.7 Relation between Dominant Frequency Score and SNR. . . . . . 1176.8 Beta Amplitude score calculation steps. . . . . . . . . . . . . . . 1196.9 Relation between Beta Amplitude Score and SNR. . . . . . . . . 1206.10 Steps for calculating the Sinusoidal Score. . . . . . . . . . . . . 1226.11 Relationship between Beta Sinusoidal Score and SNR. . . . . . . 1246.12 Relation between Beta Amplitude Score and SNR. . . . . . . . . 1256.13 Relation between Symmetry Analysis Score and SNR. . . . . . . 1286.14 Relation between Morphology Score and SNR. . . . . . . . . . 1306.15 The effect of eye movement on F7 and F8 EEG channels. . . . . 1306.16 Relationship between Eye Movement Analysis score and the in-
put signals. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1326.17 Increasing in amplitude and frequency over time at C3-CZ, CZ-
C4 and C4-T4 channels. . . . . . . . . . . . . . . . . . . . . . . 1336.18 The percentage of each score group in the General Summary
Score. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 136
7.1 BCI input output interface. . . . . . . . . . . . . . . . . . . . . 1407.2 Recording EEG signals while doing different activities. . . . . . 1457.3 Relation between General Summary Score and BCI Accuracy. . 1477.4 Relation between noise, General Summary Score and BCI Ac-
curacy. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1487.5 The developed plugin which assess the input signal in BCILAB. 1497.6 Comparison between a normal signal and the same signal after
applying different types of noise. . . . . . . . . . . . . . . . . . . 1517.7 Classification accuracy after applying two different models on
two datasets. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 153
ix
8.1 This figure shows the whole connection between neural signaland BCI application, beginning by recording the signal thenprocess and assess the signal, finally connecting to BCI appli-cations and providing feedback to the user using Haptic device.Average accuracy using different feature extraction and sortingmethods is shown in sub-figure (a), while sub-figure (b) showsthe automated assessment scores for an input signal. . . . . . . 157
8.2 Combining Haptic, visual feedback with BCI application. . . . . 159
x
Research Publications
1. Shady Mohamed, Sherif Haggag, Hussein Haggag, Saeid Nahavandi "To-wards Automated Quality Assessment Measure for EEG signals" Neuro-computing journal (under review).
2. Sherif Haggag, Shady Mohamed, Hussein Haggag, Saeid Nahavandi "Au-tomated Quality Assessment for EEG Signals Based On Extracted Fea-tures" Neurocomputing journal (under review).
3. T. Nguyen, A. Bhatti, A. Khosravi, S. Haggag, D. Creighton and S.Nahavandi "Automatic Spike Sorting by Unsupervised Clustering withDiffusion Maps and Silhouettes" Neurocomputing journal, Volume 153,04 April 2015, Pages 199-210.
4. Sherif Haggag, Shady Mohamed, Omar Haggag and Saeid Nahavandi "Prosthetic Motor Imaginary Task Classification Based on EEG QualityAssessment Features" in the 22nd International Conference on Neural In-formation Processing (ICONIP), Istanbul, Turkey, 09-12 November 2015.
5. Sherif Haggag, Shady Mohamed, Hussein Haggag, Saeid Nahavandi "Pros-thetic Motor Imaginary Task Classification using Single Channel of Elec-troencephalography" in SMC IEEE International Conference, Hong Kong,09-13 October 2015.
6. Sherif Haggag, Shady Mohamed, Asim Bhatti, Hussein Haggag and SaeidNahavandi "Noise Level Classification for EEG using Hidden MarkovModels" in IEEE 10th International Conference on System of SystemsEngineering (SoSE), San Antonio, TX, USA, 17-20 May 2015.
xi
xii
7. Sherif Haggag, Shady Mohamed, Asim Bhatti, Hussein Haggag andSaeid Nahavandi "Neuron’s Spikes Noise Level Classification using Hid-den Markov Models" in 21st International Conference on Neural Infor-mation Processing (ICONIP), Malaysia, 03-06 November 2015.
8. Sherif Haggag, Shady Mohamed, Hussein Haggag, Saeid Nahavandi "Neu-ral Hidden Markov Model Neurons Classification based on Mel-frequencyCepstral Coefficients" in IEEE 9th International Conference on Systemof Systems Engineering (SoSE), Glenelg, Australia, 09-13 June 2014.
9. Sherif Haggag, Shady Mohamed, Asim Bhatti, Hussein Haggag and SaeidNahavandi "Neural Spike Representation Using Cepstrum " in IEEE9th International Conference on System of Systems Engineering (SoSE),Glenelg, Australia, 09-13 June 2014.
10. Hailing Zhou, Shady Mohamed, Asim Bhatti,Chee Peng Lim, Nong Gu,Sherif Haggag and Saeid Nahavandi, "Neural spikes sorting using Hid-den Markov models" in International Conference on Neural InformationProcessing, Korea, 03-07 November 2013.
11. Sherif Haggag, Shady Mohamed, Asim Bhatti, Nong Gu, Hailing Zhou,Saeid Nahavandi "Cepstrum Based Unsupervised Spike Classification" inSMC IEEE International Conference, Manchester, United Kingdom, 13- 16 October 2013.
Abstract
Humans have long imagined a world in which they could control, interactand command different types of machines using only their thoughts. Excit-ing advances in Neuroscientific research mean that this seemingly impossibledream is fast becoming a remarkable reality. Researchers have opened a newwindow through which brain signals can be translated into commands using aBrain Computer Interface (BCI).
At its present stage of development, BCI applications allow users to com-mand simple tasks, but research stage, such as the following, is pushing itscapabilities ever closer to the ultimate objective of fully thought operatedmachines. The liberating possibilities of mind operated wheelchairs and pros-thetic limbs represent BCI’s most immediate and pressing application, buttheir potential is boundless. This will help disabled people to communicateand connect with the wider world during their daily lives. For example, peo-ple who suffer from spinal cord injuries, such as paralysis, are figuratively‘locked-in’ their bodies, as they cannot control any motor activity. However,brain signals have potential to play an important role in allowing people withspinal cord injuries to communicate effectively and gain control of their bodies.Non-invasive electroencephalogram (EEG) is perhaps the best known means ofneural signal recording and the current research is heading towards the use ofEEG to help those people find a way out and thereby improving their qualityof life.
EEG signals provide means to understand how the brain works. SpikeSorting is the first step in decoding brain signals. First, brain short and sharpelectronic pulses in the brain, or ‘spikes’ are detected, then the importantfeatures are extracted from which the spikes can be ordered into groups. If
xiii
xiv
these steps are performed efficiently, it is possible to know the timing and theorigin of the spikes, then it is possible to ascertain abnormal behaviour andits location in the brain. The performance of BCI applications is contingentupon the accuracy of the Spike Sorting process.
The quality of the recorded EEG signal, furthermore, has a direct bearingon the performance of BCI applications. Noise produced during the record-ing of the EEG signal has a direct impact upon the quality of the acquiredneural signal, and therefore, the efficiency of BCI application’s performance.Most BCI research focuses only on the effectiveness of the selected featuresand classifiers; however, the quality of the input EEG signals is determinedmanually.
The accuracy of the current methods for analysing the brain signals isinadequate to current and future requirements. This research incorporates thedevelopment of novel feature extraction technique to extract more meaningfulfeatures and a new clustering algorithm, to more efficiently classify the spikesduring the Spike Sorting process. Moreover, in this research, an automatedsignal quality assessment method was proposed for the EEG signals. Theproposed method generates an automated quality measure for each windowin the EEG signal based on their characteristics as well as their noise levels.This EEG quality assessment measure will give researchers early indicationof the quality of the signal, which will help in testing new BCI algorithmsso that the testing can be made on high quality signals only. It will alsohelp BCI applications to react to high quality signals and to ignore lowerquality ones without the need for manual interference. The results of EEGdata acquisition experiments that were conducted with different levels of noiseshow the consistency of these algorithms in estimating the accurate signalquality measure.
Chapter 1
Introduction
1.1 Background and Motivation
Brain signals are now widely used in scientific investigation and particularly
for patient diagnoses. Surgery can be an option for patients with problems of
the brain, which have not responded to medications. To ensure the best out-
comes, it is critical that regions of the brain that produce abnormal activities
are clearly identified. To achieve this, patients undergo brain signals moni-
toring that allows neurophysiologists to determine areas that show abnormal
activities or spikes [1, 2].
It can take many days to comprehensively audit the EEG signals of a
specific person as a huge bulk of data is recorded in this period. The pathway
for analysing the data begins with visual analysis, followed by spike detection,
spike feature extraction and then Spike Sorting. This process is expensive, time
consuming and exhausting, and so in recent times, automatic spike detection,
feature extraction and Spike Sorting techniques have received a huge amount of
attention [3]. Automation significantly reduces review time but in comparison
to manual techniques, automation produces lower accuracy [4].
1
2
Recent research studies show that by removing frequent spike regions -
seizure onset regions - surgical success can be increased. However, it is not well
understood how spikes work, or how they are generated and propagated [5,6].
A recent study shows a correlation between certain genes and abnormal
parts of the human brain, as well as the frequency and shape of neural spikes.
Accordingly, analysis of both qualitative and quantitative spikes is very im-
portant for disease diagnosis and identifying regions of abnormality [7, 8].
The first step in qualitative and quantitative spike analysis is Spike Sorting.
The process begins with spike detection, and then the extraction of features
from the spikes and then finally, the clustering of the spikes into different
groups, each representing a certain source or neuron. A meaningful feature ex-
traction method is needed and this will be discussed later in details. Moreover,
an accurate clustering algorithm to gather the spikes is also necessary [9, 10].
Neural signals are also used in many applications including the assessment
of various brain disorders types. As an example, if a patient suffers from
epilepsy, the seizure activity usually appears as rapid spiking waves on the
EEG. However, no one has previously used to assess the neural signal itself,
or found a means by which to establish if it is recorded correctly. There is no
automated quality assessment for the EEG signal which is vitally necessary to
neurologist, physicians, technicians and BCI researchers [11,12].
1.2 Aims and Objectives
The aim of this research is to improve the process of understanding neural
signal by refining the Spike Sorting processes and signal processing assessment.
3
This research has three main aims: the first is to use mathematical methods to
refine the feature extraction process so as to extract only the most significant
features from the signal; the second is to improve the existing clustering algo-
rithm to cluster the data in a more meaningful and accurate way, and finally
to generate an automated biological and signal processing measure for EEG
assessment to be used in BCI applications.
1.3 Thesis Outline
This thesis is divided into eight chapters. In Chapter 2, the literature re-
view, a general introduction to neurons, where it shows how they communicate,
send information and function, and provides basic knowledge of brain compo-
nents, neural signals, EEG signals and applications. EEG signal characteris-
tics are explained, including, frequencies, voltages, morphology and synchrony.
Then, the relationship between EEG signal recording and BCI applications is
demonstrated. This chapter also explains the importance of the neural signal
quality and its effect on the performance of different applications, including
BCI.
Spike Sorting is the first step to decoding the brain. This is contingent on
the design of an automated quality measure since it can identify the behaviour
of the neurons. In order to undertake the Spike Sorting process, extracting the
spike features should be the commencement point, followed by the clustering
of the spikes according to those features. Chapter 3 presents a critical review
of feature extraction, Spike Sorting and Quality Assessment Measures. It
highlights the advantages and disadvantages of each method. This is followed
4
by the problem statement, which shows that the process needs a new feature
extraction and Spike Sorting methods based on the reasons mentioned in this
chapter. Moreover, the reasons for developing a quality measure for assessing
the recorded EEG signal are explained. The research methodology plan and
the steps followed during the development of the research are also shown.
Chapter 4 details the new feature extraction and Spike Sorting methods
used to represent the neural signal in a better way. Diffusion Maps, Cepstrum
Coefficients and Mel-Frequency Cepstral Coefficients are used as feature ex-
traction methods. Hidden Markov Models (HMM) are used as the sorting
method as it was noticed that neural spikes are represented precisely and con-
cisely using HMM state sequences. An HMM was built for neural spikes,
whereby HMM states could represent the neural spikes.
A noise level estimation method for neural signal is needed, to determine
the amount of noise recorded in the neural signal. Chapter 5 introduces a noise
level estimation method, in order to estimate the amount of noise before doing
any kind of processing on the recorded signal. Mel-Frequency Cepstral Coef-
ficients and HMM are used in the estimation process. The method generates
an automated measure to estimate the noise levels in neural signal. HMM was
used to build a classification model that classifies the neural spikes based on
the noise level.
Knowing the quality of the EEG signal is very important to estimating
the amount of noise in the signal. Hence, automated scores, which are used
to assess the brain signal, are discussed in Chapter 6. Twelve scores were
developed to assess the EEG signal based on biological and statistical features.
5
This represents the first online quality assessment measure for EEG signal.
Chapter 7 indicates how to practically connect the assessment measure,
developed in this research, with BCI applications. An online quality assess-
ment plugin is developed and linked to BCILAB, the best known MATLAB
toolbox for BCI applications available for anyone to use. This plugin can give
an assessment measure, which will help many people, such as neurologists,
physicians and technicians, in knowing the quality of the recorded signal. This
automated measure can provide benefit in many ways, such as ensuring that
the data is correctly recorded. Finally, Chapter 8 presents the conclusions and
points to future directions in using Haptics devices for this research.
Chapter 2
Literature Review
This chapter explains what is meant by neurons and shows how they com-
municate, send information and function. Moreover, this chapter will discuss
neural signals and especially the EEG signal, its bands, frequencies, voltages,
morphology and synchrony. Then, the process of recording EEG signal will
be explained and also how it is used in different applications, such as BCI
applications is determined.
2.1 What is meant by a Neuron?
A neuron is a nerve cell; it is considered the nervous system’s basic building
block as shown in Figure 2.1. Neurons and other cells in the human body have
many things in common, but there is a major difference between them in
that neurons have a specific functionality, not found in any other cells in the
human body: they can communicate with each other, and in addition, send
information to and from any organ in the human body [13].
Neurons have a very specific task. They are responsible for transporting
information between human organs either chemically or electrically. Neurons
can be classified into different categories, each category has its own task and
6
7
Figure 2.1 Neurons are the building blocks of the nervous system [14]
functionality in the body of a human [15].
As an example, a sensory neuron is a type of neuron, its job is to transfer in-
formation from the human body’s sensory receptor cells to the brain. Another
type is the Motor neurons, which is responsible for communication between the
human’s body muscles and the brain. Also there is a specific type of neurons
which transfers information between the neurons themselves. These neurons
are called Interneurons. Sometimes the information is prevented from moving
to its destination properly as a result of a bad signal, but it can be detected by
the quality assessment measure (discussed in the subsequent chapters) [16,17].
Neurons and other body cells have many structural commonalities. The
genetic information of the cell is stored in this nucleus. Organelles are found in
the body of both cell types, which help to keep the cell alive, along with Mito-
chondria, Golgi bodies, and Cytoplasm and in addition encircling membranes
protect both neurons and other body cells. [18].
There are, however, major differences between the neurons and the other
body cells. One of these differences is that the reproduction of neurons stops
within a small period after birth, so when any neuron dies, it will not be
8
Figure 2.2 Neuron’s most important parts [14]
replaced by a new one. This is why not all the brain parts have the same
number of neurons. Research shows that new communication channels and
paths are created when neurons die so that, depending on the neurons, living
neurons can communicate with those still living. Moreover, the membrane of
the neurons is created in a way that enables transmission of information to
another cell. Here, the Spike Sorting process is applied, to detect the areas of
the brain that behave abnormally. It can also detect the new communication
paths [19–21].
Neurons consist of four main parts as shown in Figure 2.2. The first part,
known as the Dendrites, is located at the beginning of neuron, looks like tree
branches and increase the cell’s surface area [22]. The role of Dendrites is to
send electrical signals to the Soma as soon as they receive any information
from the surrounding neurons. They cannot do their job if there is an external
electrical signal, as this will lead to the generation of an abnormal signal.
Synapses covers Dendrites as well [23]. The Soma is the next part of a neuron,
9
where signals from Dendrites are received and forwarded. The Soma and the
nucleus do not perform an important role in the transmission of the neural
signal; their main job is to make sure that the cell functions are working.
In addition, Mitochondria and Golgi apparatus play an important roles in
supporting the cell. Mitochondria are the source of energy for the cell and the
Golgi apparatus collects the cell production from outside the cell wall [24,25].
The third and very important part is the Axon Hillock. Its location is at
the end of the Soma. The main function of the Axon Hillock is neuron firing. A
signal (action potential) will fire if the its strength surpasses the Axon Hillock
threshold [26,27].
The Axon is a stretched fiber, which runs from the cell body to the terminal
endings. Its main function is sending the neural signal [28]. The speed of
sending information mainly depends on the size of the Axon [29]. When the
size increases the transition rate increases. Myelin is a greasy insulator that
covers some Axons, these greasy Axons sends the information faster than the
non-greasy ones [30,31].
Finally, at the end of each neuron are features known as Terminal Buttons.
These buttons transmit the neural signal to other neurons. Between two nerve
cells is a minute gap known as a Synapse, which is located at the edge of the
terminal button; this gap is used by Neurotransmitters to transmit the signal
to other neurons.
10
2.2 Neural Signal in the brain
Neurons have a unique shape compared to other human cells. Soma is the
name of this cell body. Soma contains the nucleus that carries the DNA. It
directs the cell to make different proteins. On one edge, the Soma sprouts
branch-like Dendrites for receiving signals. In the opposite direction, Axon
stretches away and acts as many Axon terminals for transmitting signals [32,
33].
The location of the Axon terminals is commonly adjacent to another neu-
ron’s Dendrites, however, this does not mean that the Axon terminals physi-
cally touch the other neuron’s Dendrites. They are very close but they do not
touch each other, and are separated, as mentioned above, by a space known as
a Synapse. Each neuron has about a thousand Synapses, which enables it to
connect with the nearby neurons. These Synapses link the cells and enables
them to transfer messages from its neuron to any adjacent neuron. The hu-
man brain contains a countless number of Synapses exceeding the number of
stars in the Milky Way galaxy. Abnormal signaling across these multitudinous
Synapses can lead to abnormal human behaviour [16].
The Synapses are empty space, and there is no immediate connection be-
tween the Axon terminals of one neuron and the Dendrites of another neuron.
This gap enables a cell to transfer chemical signals through, which is consid-
ered the message as shown in Figure 2.3. Each Axon terminal contains sacs
called Vesicles, which are replete with chemicals known as neurotransmitters.
Neurotransmitters can be any of 50 different chemicals. Each neurotransmitter
transmits various message type to the next neuron. This message is realised
11
Figure 2.3 Chemical signals pass between neurons through a site calledSynapse [34].
by specific receptors located on the exterior part of the Dendrites [35].
These specific receptors behave like locks; the ’key’ to these ’locks’ is a
specific neurotransmitter. Once its key opens the lock, the neurotransmitter
drifts back into the gap between neurons and is destroyed by enzymes or trans-
ported back to the original neuron’s Axon terminal at which point it may be
destroyed or reused by a vesicle. Each neurotransmitter has its own function
and their recycling processes differ from one to another [36].
When the receptors of the accepting neuron’s Dendrites are filled by the
neurotransmitters, excitatory neurotransmitters prompt the receiver to for-
ward the signal to other cells, whereas inhibitory neurotransmitters block the
receiver from sending the signal to other cells. Neuron’s Dendrites can ac-
cept more than a single neurotransmitter signal at the same time, the signal
will be fired to the next neuron if the excitatory signals are stronger than the
inhibitory signals and will be blocked otherwise [37].
Even though transmitting a messages from one neuron to another requires
12
Figure 2.4 The inside negativity of the resting neuron’s cell membraneis higher than the outside. Then the inside becomes more positive whenthe neuron is stimulated. This will leads to similar change in the adjoiningsegment of the neuron’s membrane that will cause the movement of theelectrical impulse along the neuron
chemicals, another medium is used to send that messages between the receiving
neuron’s Dendrites and its own Axon terminals. When neurotransmitter’s
trigger fires, the receiving neuron sends an electrical "action potential" along
its length similar to the electrical flow in a metal wire. An insulating coating
made of fatty myelin sheath surrounds the Axons to help in transmitting the
signal faster [38].
In the following section, the conduction of an electrical signal by a non-
metallic human cell will be explained. Usually, the neuron adjusts its own
charge in relation to the cell’s external space. To change its charge, a neuron
changes the charged ions, located inside and outside of the cell membrane.
When a neuron is not active and is not firing any signal, its internal ions
have more negative charges than the external ions. At this time, electrical
potential, known as resting membrane potential, is created side to side with the
cell membrane. The channels of sodium and potassium in the cell membrane
13
control the ingoing and outgoing movement of positive sodium and potassium
ions in the cell [39].
The makeup of the Axon’s cell membrane is affected when any neurotrans-
mitters enters the receptor areas. In the Axon’s structure nearest to the Soma,
the cell membrane’s absorptivity increases. Positive sodium ions find their way
into the cell and increase the Axon section’s positivity in comparison to the
external section as shown in Figure 2.4. The sodium ions provide energy to
push the newly added positive charges outside the neuron and return to the
original state, but the same effect has also been generated in the nearby section
of the cell. Ultimately, this positive charge reaches the Axon terminals and
the distance travelled is is about the length of the Axon inside the cell [40].
The electrical charge changes again when the axon terminals receive the
signal. Sometimes the signal is not received, or too many signals are received,
which leads to a corrupted signal resulting in abnormal human behaviour.
Positive calcium ions plays last role of the sodium ions, as it penetrates the
extra-permeable cell membrane. When the calcium ions reach the Axon termi-
nal, the vesicles with a full capacity of neurotransmitter are triggered, causing
it to drift to the cell membrane, merge with it, and then let the specific neu-
rotransmitters move outside the cell. Although this process seems protracted,
the action potential occurs with astonishing speed. So if the Axon is a soccer
field, one second is the time for an action potential to move through it [41].
This whole process will be repeated by the next neuron to generate and
transfer the neural signal. Some abnormal neurons transfer random signals or
prevent the transmission of normal signal corrupting the original signal, but
14
these abnormal behaviours can be detected by the Spike Sorting process that
will be discussed in the following chapters.
2.3 Signal Acquisition
The above section shows how neurons communicate with each other through
neural signals, which are mainly electrical activity generated by brain struc-
tures. These signals are acquired and processed by the signal acquisition and
processing techniques and devices. In general, there are three brain’s signal
acquisition techniques, which are invasive, partially invasive and non-invasive
acquisition.
2.3.1 Invasive and Partially Invasive acquisition
Both Invasive and Partially Invasive acquisition techniques require a surgery
to implant electrodes. In Invasive acquisition, electrodes are placed on the
brain as shown in Figure 2.5. These produce the highest quality signals, which
can be used by the BCI devices. However, this technique has two major draw-
backs. Firstly, it requires a surgery to open the skull and plant the electrodes.
Secondly, tissues build-up, which leads to weaker signals and after a while, the
body reacts to the presence of the foreign object and rejects it, resulting in no
signal at all [42].
On the other hand, Partially Invasive acquisition records the activity of the
brain inside the skull, but from the surface of the membranes that protect it
as shown in Figure 2.6. An electrode Grid is implanted by surgical incision,
but this has the same drawbacks of the Invasive acquisition techniques [45].
15
Figure 2.5 Invasive Brain signal acquisition [43].
2.3.2 Non-Invasive acquisition
This is the most useful neuron signal imaging method, applied to the out-
side of the skull, on the scalp. There are many types of non-Invasive acquisi-
tion technologies, such as EEG, functional magnetic resonance imaging (fMRI),
magneto-encephalogram (MEG), P-300 based BCI, etc. EEG is the most com-
mon technique among non-invasive Brain Computer Interfaces (BCIs). EEG
has many advantages such as simplicity and ease of use, which are considered
the main requirements for any BCI application. This is the reason behind
using EEG in most of the experiments in this research. The next section will
discuss EEG in more details. Figure 2.7 shows the difference between Invasive
and non-Invasive acquisition.
16
Figure 2.6 Partially Invasive Brain signal acquisition [44].
2.4 EEG: an electrical activity recording
Electroencephalography is a medical imaging technique that records these
signals from the scalp. The electroencephalogram (EEG) is defined as alter-
nating type electrical activity recorded from the scalp surface. This activity is
recorded using metal electrodes and conductive material [47].
The EEG can be measured by two ways. The first way is called electro-
cortiogram which records the signal directly from the cortical surface. The
second, electrogram, uses depth probes to record the data [48]. Electroen-
cephalographic reading is an entirely non-invasive process, which means it has
no risky side effects. It can be used safely on all normal adults and children
and there are no limitations on recording time [49,50].
Brain cells (neurons) does not trigger all the time, but it produces a re-
gional current flows. In the cerebral cortex, the Dendrites of many neurons
excite in a synaptic way, so the rule of EEG is to record the current flow
during the excitation process [51]. Electrical potentials differences are caused
17
Figure 2.7 Invasive and non-Invasive Brain signal acquisition [46].
by summed post-synaptic potentials cells, which causes the creation of electri-
cal dipoles. These dipoles occurs between Soma, the body of the neuron and
apical Dendrites, which are the neural branches. Na+, K+, Ca++, and Cl-
ions are the main components of the brain’s electrical current, which moves
in a specific direction inside the neural membrane channels. The membrane
potential is the one responsible for direction determination [52]. There are var-
ious types of synapses and neurotransmitters but they cannot be seen unless a
complex microscope is used. After placing the electrodes on the head surface,
the electrical activity is record for a huge population of active neurons [53].
The electrical signal passes through the skin, skull and various other layers,
after which reaching the electrode, and from which it is recorded.
Electrodes captures these electrical signals, which are then amplified and
can be shown on a screen or saved on any memory device [54]. EEG is a highly,
effective and capable tool in the fields of neurology and clinical neurophysiology
because it can record the brain’s normal and abnormal electrical activity. The
18
electric activity of the human brain begins when the baby is in the uterus
within 17-23 weeks. At birth, a baby will have about 1011 neural cells at a
mean density of 104 per cubic cm and connected by synapses to form neural
nets. When the brain is fully grown (adult brain), it has around 500 trillion
synapses.
The Synapses count per neuron is directly proportional to the age of the
person, which means that the number of synapses decrease with age. Similarly,
the brain’s neuron count is inversely proportional to age, because neurons do
not reproduce and are not replaced as they die [55].
Now the brain will be considered from an anatomical point of view. There
are main three sections in the brain; these sections are the cerebrum, cere-
bellum, and the brain stem [56]. The Cerebrum is the first and the most
important section, containing the right and the left hemispheres, the surfaces
of which, known as the cerebral cortex is very convoluted. The most superior
section of the central nervous system is the cortex [57]. Moreover, the cerebrum
has a center which is responsible for initiating movement, sensation conscious
attention, emotion expressions, analysis of complex matters and behaviour.
The second section is the Cerebellum, which controls the muscles move-
ments and maintains the balance of the body. The third and last section is the
brain stem, which manages the regularity of the heart, breathing, biological
clock, and hormone production and release. Due to its position, the electrical
activity of the cerebral cortex has the biggest influence on EEG [58]. All the
following subsections pave the way for the automated EEG quality assessment
19
measure as these sections contains many biological and statistical characteris-
tics for EEG signals. All the signals recorded from all brain sections will be
used in the quality assessment measure, which is developed in this research.
2.4.1 EEG Bands
The intensity of the EEG signal is quite low, measured in microvolts (μV)
and divided into four main frequencies as shown in Figure 2.8 [59]. All four
bands were used in the proposed automated EEG quality assessment measure.
The Delta wave is the first frequency; it represents any frequency below 3 Hz.
It is known for being the slowest of the waves and with the highest amplitude.
The Delta wave appears normally in the EEG of babies less than 12 months
of age, also in the third and the fourth sleeping stages of older humans, or it
can be present in association with sub-cortical, deep and widespread injuries.
It is a dominant frequency in the frontal part of the adults brain (e.g. Frontal
Intermittent Rhythmic Delta "FIRDA") and also in the children posterior part
( e.g. Occipital Intermittent Rhythmic Delta "OIRDA") [60].
The second frequency is the Theta wave; a slow wave ranging between 3.5
Hz and 7.5 Hz. It is a slow wave. It usually appears in children of less than
13 years of age. In addition, it appears normally while sleeping but it will be
abnormal if it appease while a person is awake. It may happen during a focal
sub-cortical injury and in general diffuse disorders spreading like metabolic
encephalopathy and from a few hydrocephalus cases [62].
The third wave is called the Alpha wave. It is from 7.5 Hz to 13 Hz. It
mainly occurs in the posterior head areas in both hemispheres. It always has
high amplitude in the dominant side. It occurs when the person closes his or
20
Figure 2.8 Different EEG bands [61].
her eyes and is calm, and vanishes when the eyes are open or when the brain
is contemplating, manipulating or is interrupted by any mechanism. It occurs
most frequently in normal relaxed adults. It usually occurs when the person
is older than the thirteenth year [63].
The activity which has frequency more than or equal 14 Hz is called Beta
wave activity. It occurs frequently on both sides of the hemisphere especially
the frontal area. It is mainly affected by anodyne drugs. A very limited
amount of this band appears - or even it totally disappears - sometimes in
relation to cortical damage areas. It usually appears when normal adults are
alert or worried or while opening their eyes [63]. All these bands will be used
in assessing the quality of the EEG signal in the following chapters.
21
There are different properties for the EEG signal, such as:
• EEG frequencies The meaning of Frequency here is the rhythmic monotonous
activity, measured in Hz. There are different features for the EEG fre-
quency. The first feature is the Rhythmic wave which means that the
waves of the EEG activity are firing with a constant frequency. The sec-
ond feature is called the Arrhythmic wave which means that the EEG
activity has no specific rhythms or frequency. This means that the fre-
quency changes over time. The last feature is the Dysrhythmic wave,
which rarely appears in normal healthy people [64].
• EEG voltage The electrical activity in the brain has a low voltage, which
can be measured in micro-volts(μV). Its value varies, depending upon
the technique used for recording. It is known that the word amplitude
in EEG means the voltage in microvolts and it is the distance between
the peak of the wave and the trough of the wave. It ranges between
± 10 to ±100 μV and the average normal amplitude ranges from ±20 to
±50 μV [65] but it can reach ±1000μV in abnormal cases which will be
detected by the quality assessment measure.
• EEG morphology The shape of a waveform is known as its morphology.
The EEG pattern (wave) is determined by the mixture of frequencies
and the relationship between the phase and voltage of the wave. The
waves can be classified into several patterns. The first pattern is called
Monomorphic, in which one dominant activity creates the recorded EEG
activity. The second, known as the polymorphic pattern, is a complex
22
waveform resulting from the mixing of multiple frequencies. Sinusoidal
is the name of the third pattern, in which the pattern looks like a sine
wave. Finally, the transient pattern where the wave appears isolated
and in which the background activity shape and the pattern are clearly
dissimilar [66].
The pointed peak in the wave is called spike if its width (duration) ranges
between 20 and 70 msec. It is called a Sharp wave if its width exceeds
70 msec up to 200 msec [67].
• EEG synchrony Some rhythmically distinct patterns appears simultane-
ously over various regions of the brain, which can have a unilateral ap-
pearance, meaning that it appears on the same side or it can have a
bilateral appearance, appearing on both sides [68, 69].
• EEG Periodicity Periodicity points to the brain patterns distribution
over time, whether or not a specific EEG activity pattern shows reg-
ularly. This activity can be general, focal or lateral [70].
2.4.2 Recording of EEG
Metal electrodes are used to record the EEG data [49] as shown in Fig-
ure 2.9. These electrodes are tiny metal discs, which are manufactured from
tin, stainless steel, silver or even gold and provided with a silver chloride cover.
They have specific positions on the scalp determined by the method used [50].
The best known method for electrode placement is the International 10/20
system, by which a number and a letter is assigned to each electrode. The
letter represents the implicit brain area where the electrode is placed, e.g., C-
23
Figure 2.9 EEG cables which has the sensitive electrodes at the end. Aspecific gel is added on each electrode before putting the electrode in aspecific position on the human’s scalp.
central lobe and P - parietal lobe. The right side of the brain is represented
by even numbers and odd numbers represent the left side [71].
The 10/20 international system is now the standard method for scalp elec-
trode organisation. The system core is the percentage in distance, this percent-
age is 10/20 and it is measured from nasion-inion to specific points as shown in
Figure 2.10. These specific points are located in precise positions, the points
which are located in the Frontal pole begins with FP, the points located in
the center beginning with the letter C, similarly parietal points begins with
P, occipital begins with O and finally the temporal region begins with T. The
mid-line electrodes begins with the letter z, which means zero. The electrodes
which are located in the left hemisphere are assigned odd numbers and right
hemisphere even numbers [71].
The Neuroscan device was used for recording EEG signals in most of the
experiments, which are done in this research. A SynAmps 2/RT amplifier was
24
(a) (b)
Figure 2.10 Each location is defined by alphabets F, T, C, P and O. Eachalphabet denotes frontal, temporal, central, parietal, and occipital lobes.Even numbers 2, 4, 6 and 8 represents right hemisphere and Odd number1, 3, 5 and 7 for left hemisphere as shown in Figure (a). Also the locationof each electrode is shown in Figure (b) [72].
used as shown in Figure 2.11. Designed with specific engineering considerations
to provide the best possible recordings, the SynAmps 2/RT amplifier is one
of the most advanced and versatile amplifiers, capable of recording true DC
potentials contained in cognitive potentials to the fastest ABRs.
Curry 7 Neuroimaging Suite software was used to record the data in the
experiments. Acquisition in Curry is enhanced with easy, more flexible, and
advanced tools for online data processing. The impedance can be tested for
each electrode without interrupting the data acquisition process, and is pro-
vided in a simple visual display with values for each electrode as shown in
Figure 2.12.
Quik-Cap EEG, shown in Figure 2.13, was used in experiments while
recording the data, because it can be quickly placed using easily identified
25
Figure 2.11 SynAmps 2/RT is the latest EEG amplifier from Com-pumedics Neuroscan.
landmarks, and it requires no marking while recording.
2.5 EEG Applications
Speed is the biggest advantage of EEG [73]. Any stimulus received or un-
dertaken by humans produces neural activity; the more complex the stimulus,
the more complex the activity [74, 75]. EEG can record this activity within
fractions of a second after being triggered. MRI and PET scans gives more
spatial resolution compared to EEG. In order to understand the brain, EEG
images and MRI scans are used together. Brain electrical activity can be lo-
cated using EEG and can determine the source (brain location) of this electrical
activity. EEG is used in many research and clinical applications including:
1. Auditing of deep unconsciousness, watchfulness or the death of the brain
26
(a) (b)
Figure 2.12 Figure (a) shows a screen shot from the Curry software. Also,the impedance test of each electrode is shown in Figure (b).
Figure 2.13 Quik-Cap Electrode Placement System.
[76].
2. Identifying the damaged areas after having a head injury, stroke or cancer
[77].
3. Sensory pathways testing [78].
4. Monitoring psychological relations [79].
5. Generating biological feedback [80].
27
6. Managing numbness depth [81].
7. Learning more about epilepsy and finding the core of the seizure [82].
8. Testing the drugs effect on epilepsy [83].
9. Helping in epileptic research experiments [84].
10. Auditing the brain development of humans and animals [85].
11. Drug analysis for jerky effects [86].
12. Sleeping disorder and physiology investigation [87].
If a person has lesions from, for example, tumor, hemorrhage, or throm-
bosis, the cortex produces lower frequencies. Understanding this is useful in
identifying some lesions. EEG signal can offer information about the person
based on the amplitude and the frequency of the signal, also spike production
and the pattern of the wave [88]. EEG can identify brain problems if there is
any distortion in amplitude, frequency, spike production or in wave patterns.
For example, the brains of patients who have epilepsy releases very high volt-
age waves from the cortex region. There are a lot of factors that can change
the EEG patterns including behavioural, hormonal, circulatory, neuroelectric,
metabolic and biochemical factors. Variation of electric activity can be tracked
before, during and after taking medication, and its effect on the brain regions
can be monitored [89].
The procedure for recording EEG is non-invasive and painless, which is
why it is commonly used in brain research in many fields, including those of
28
memory, perception, concentration, communication, and mental state in adults
and children. EEG has many applications in real life such as:
2.5.1 Evoked Related Potentials
Event Related Potential (ERP), which is the abbreviation of event related
potential, is one of the greatest beneficial applications for EEG recording.
Evoked potentials, also called event related potentials, are big fluctuations in
amplitude (voltage) due to the evoked neural activity. Mainly, any internal
or external stimulus triggers the evoked potential. ERPs are perfect methods
to investigate aspects of cognitive processes; the nature of which could be
normal or abnormal. They are used in many research fields such as psychiatric
and neurological disorders, mental operations such as understanding, alertness,
language processing and memorisation. ERPs can help PET and MRI scans in
finding the local activation regions, while performing a specific cerebral task.
Also the time course of these activities can be identified by ERPs [90].
ERPs cannot be identified from raw EEG data because the amplitude is
very small compared to other EEG components. On the other hand, ERPs
can be extracted by calculating the average of the EEG time-locked recording
periods (epochs) and this can show the frequency of the sensory, motor and
cognitive events. In order to obtain the ERP when a stimulus occurs, the
background EEG fluctuations are averaged out and the remaining will be the
event related brain potentials. Only these remaining electrical signals reflect
the activity, which is always related to the stimulus in a time-locked way.
Therefore, when a stimulus evokes a neural activity pattern, the ERP reflects
it with a high temporal resolution.
29
2.5.2 Quantitative EEG
Technological approaches are used in conjunction with EEG to monitor si-
multaneous brain activity data from the whole head. Multi-channel measure-
ments are applied in quantitative EEG (QEEG), which helps in locating brain
regions presenting abnormal behaviour. From the output, two and three di-
mensional colour maps can be produced using topographic brain mapping [91].
2.5.3 EEG Biofeedback
EEG Biofeedback (Neurofeedback) is mainly used as a means of brain func-
tion training, by which the brain consciously acquires information to perform
more efficiently. Brain action is monitored from moment to moment and the
recorded information is shown back to the person, so the brain is pushed to
change its own activity to more patterns that are more appropriate. This
process requires a gradual learning process. In addition, it can be applied to
measurable brain function. It is called Biofeedback as it mainly depends on
electrical brain activity (electroencephalogram), or EEG.
Neurofeedback is considered as a self-regulatory training method and it is
applied directly to the brain. Good brain function should be self-regulated.
The central nervous system is helped to function better by the self-regulation
training. Frequency following response is one of the neurofeedback training
methods. It adjusts the brain functions in desired ways, such as increasing
the Alpha activity, which leads to better touch, sight and auditory response.
Thus, a person can know the optimal training route [92].
Some researchers say that subjects can enhance the performance of the
30
brain [93,94], regulate behaviour and change the mood to a stable state using
the positive or negative feedback loop. On the other hand, some researches see
that it increases the brain’s unsuitability. However, it is generally applicable
for specific patients who suffer from certain mental disorders including epilepsy,
alcoholism and depression [95].
2.5.4 Brain Computer Interface
BCI also called mind-machine interface is a direct communication system
that reacts based on the user’s commands, extracted from the brainwaves of
the user. This system needs a significant amount of training from the specific
user’s brain waves in order to accurately understand the brain command.
At the beginning, the subject might be asked to perform a simple task,
such as imagining moving his or her arm based on an arrow on the screen. If
the arrow is pointing right, the user should imagine moving his or her right
arm and vice versa. The system then tries to understand and recognise the
command of the brain wave based on its characteristics. But now it is used
in recognising a more complex commands [96]. The common steps of any
BCI application are shown in Figure 2.14. The first step is to acquire the
brain signals. These signals are then analysed in order to convert them into
commands; these commands order an external device so as to perform a specific
action.
Components of a BCI system
It is very important to understand the entire BCI system in order to con-
duct any basic research in BCI. The main target of a BCI system is enabling
31
Figure 2.14 Common steps of any BCI application [97].
the user to control other devices using the user’s brain signals. This control
task is done through different components, signals and feedback loops as shown
in Figure 2.15. Detailed steps for any BCI application are shown below.
• Electrodes Record the human brain activity.
• Amplifier Amplify the recorded signal.
• Feature Extractor Extract significant features from amplified version of
the recorded signals.
• Feature Translator Classify the extracted features into logical controls.
• Control Interface Logical controls are converted to semantic controls by
the control interface in order to be used as an input for the device con-
troller.
• Device Controller Semantic controls are converted by the device con-
troller to specific physical commands for the controlled device.
• Controlled Device Executes specific physical commands once received.
32
Figure 2.15 BCI Functional components and feedback loops [99].
By following the above steps, the BCI system can translate brain signals to
device action. [98].
There are different types of BCI applications such as:
- Direct Control Applications
In this type of BCI applications, the main focus is using brain signals to
control devices directly. These devices are mainly used for clinical applications
such as prosthetic limbs, wheelchairs and communication devices. They can
also be used in gaming, entertainment and quality of life applications. BCI
does not yet have a full control over these devices, but researchers are now
working towards this objective. Valuable clinical applications for this tech-
nology include enabling disabled people to control their own movements, to
operate wheelchairs or prosthetic limbs, or to gain direct control of devices
33
such as computers, telephones, radios, lights, televisions, washing machines
and so on. The quality of the signals plays an important role is the accuracy
of any BCI application and the quality assessment measure will be discussed
in the following chapters.
- Indirect Control Applications
This type of BCI applications depends upon special brain error signals,
such as Error Related Negativity. It can be a group of signals associated with
errors, such as attention/engagement, frustration/anger, or comprehension.
The application user does not engage directly in the control task. For example,
the user can be watching a robotic arm extending to a door handle and the
user can determine if the arm is in the right position or not and the brain will
trigger that reaction, which will be translated by the algorithms that controls
the arm in order to move the arm in the correct position. This example shows
the indirect control BCI application where the user’s error helped the robotic
arm to make the right choice, however, it does not directly control the arm
task.
In the last few years, a few BCI products have become available for normal
people to use and try. These products are not yet commonplace due to their
signal’s low accuracy and their high cost. A few BCI products are shown
below.
∗ Neural Impulse Actuator Mainly a brain BCI mouse which enables users
to control games using their thoughts, considered a game playing prod-
uct.
34
∗ Deep Brain Stimulator Used to treat Depression, Epilepsy, Dystonia,
etc.
∗ Mindset Developed by NeuroSky, a Bluetooth BCI headset which can be
used in many BCI applications, especially games.
∗ Robotic Foot An example of a BCI products that can help disabled peo-
ple.
∗ Honda Asimo Control Robots which are designed and implemented in
Japan. These robots can work in receptions, in hospitals and many
other places. They also can also perform tasks, which are too difficult or
dangerous for humans.
∗ Artificial Arm Developed by DEKA and Development Corporation, is
good for paralysed patients.
∗ Mind Reader Google Glass Integrates Google Glass with BCI headsets
to produce a mind reader glass.
Generally, the success of these types of applications will largely depend on
the quality, specificity, robustness, and timeliness of the input brain signals.
This is the reason behind focusing on the quality of the brain signal in the
following chapters.
In this chapter, a general introduction to neurons has been given, EEG
signal recording, BCI and the applications, which use EEG signals. The im-
portance of the neural signal quality has been shown and how it affects the
performance of BCI applications. In the next chapter, a critical review of the
35
current feature extraction, Spike Sorting, noise level detection and the quality
assessment for neural signals will be given.
Chapter 3
Critical Review on FeatureExtraction, Spike Sorting andQuality Assessment Measures
3.1 Introduction
A general introduction to EEG signal and BCI application was given in
the previous chapter. This chapter will undertake a critical review of the
main sections. These sections are feature extraction methods, Spike Sorting
techniques, neural signal noise estimation and quality assessment measures,
highlighting the main advantages and disadvantages of each.
Spike Sorting is very important as it is considered to be the first step in
decoding the brain. Figure 3.1 shows the steps to sorting the neural spikes [10].
The first step is feature detection using different types of thresholds [100], then
extraction of the spike features, where each spike is represented by a set of
features which can differentiate between spikes from different neurons [101].
Some dimensionality reductions are applied to the features so that the feature
coefficients, which are highly differentiated between spikes, can be determined
and saved for processing, and the rest can be discarded [102]. Finally is the
36
37
Figure 3.1 The signal processing steps used to obtain single unit activity.
process referred to as clustering or sorting in which spikes are divided into
different groups, corresponding to different neurons and based on the extracted
feature coefficients [9].
As mentioned earlier, BCIs can help disabled people to restore their motor
ability and Spiking-based BCI applications can help disabled people to control
robotic devices such as prosthetic limbs. Current Spike Sorting methods needs
to be further refined to provide faster BCI applications, as these applications
suffer from a lengthy Spike Sorting step. The Spike Sorting process needs fea-
ture extraction and clustering methods, which can decode information without
losing spike identity.
3.2 Feature Extraction
Extracting the features is crucial to Spike Sorting steps as the spikes are
convoluted with noise and it is not easy to extract distinguishable features.
Moreover, it is important to reduce the number of features to avoid flooding
38
the system with unnecessary data, creating computational burdens and real
time delays [10].
The brain is a supremely specialised organ comprised of millions of neurons,
which communicate with each other and the entirety of the human body by
firing a voltage called action potentials (spikes). A micro-electrode device
can be used to record the voltage of these action potentials within a specific
region, or they can be recorded as an EEG signal using a Neuroscan device.
In this instance, the objective of the neurophysiologist is to understand the
behaviour of the brain through the interpretation of these spikes, matching
them as accurately as possible to their respective neurons. The steps to sorting
the spikes begin with detection of spikes using different types of thresholding,
then extracting spike features, and then finally clustering the spikes according
to those features. Extracting the features is the most important part of this
process as the spikes are convoluted with noise data and it is not easy to extract
a distinguishable features.
The spike sample points can be identified in two ways: feature selection
and feature extraction. Feature selection trims down the dimensions of the
original data before applying sorting, while feature extraction converts the
sample point to a more representative data with the same dimensions. When
the spike data have a large number of features, it is useful to consolidate them
to enhance computations by reducing the calculation time and complexity.
There are many methods used to extract features. The most popular meth-
ods will be explained and the advantages and disadvantages of each method
will be highlighted.
39
In [103], Yang used the Point-to-Point (PP) comparison as a feature extrac-
tion method. It is a ‘brute force’ approach that directly uses the spike sample
points instead of extracting features (i.e. it does not reduce the dimensions).
It is considered to be one of the easiest feature extraction methods. However,
time shift sensitivity is one of the main problems with this method. Shifting
the spikes before comparing them can solve the problem but it can also causes
serious problems in more complex cases [104].
Discrete Derivative (DD) was introduced in [105,106]. This depends mainly
on calculating the signal derivative at each spike sample point as shown in
Equation (3.1).
ddδ(i) = S(i) − S(i − δ) (3.1)
where S is a spike, i is one sample point, and δ is the delay in time (sec). Usu-
ally the time delay is used with three values, which are 1, 3, and 7. This will
solve the time delay problem. However, the feature space dimension is tripled
in comparison to the spike sample’s real number, so the most effective DD
coefficients are used as features to reduce the added dimensions. The problem
here is that many coefficients have to be used as features, which will decrease
the performance of feature extraction step; hence, it cannot be used in online
applications.
In [106,107], First and Second Derivative extrema were used as feature extrac-
tion methods, the First Derivative (FD) method depends on the derivation
of the spike waveform in the discrete domain. First it calculates the first
derivative of the spike, then the negative and positive peak of the derivative in
addition to the peak of the spike itself, with the extracted features according
40
to Equation (3.2).
fd(n) = S(i) − S(i − 1) (3.2)
where S is a spike and i is the index of the sample point.
This method depends mainly on the derivative of the waveform. The first
derivative of a signal is defined as its rate of change. The second derivative is
defined as the rate of change of the slope that represents signal’s curvature.
Spikes have several structural characteristics, such as slope, amplitude and
curve. The First and Second Derivatives are used to detect those features.
The derivatives are calculated using the difference between each spike sam-
ple point and its previous sample point. The first and second derivatives are
calculated using Equations (3.2) and (3.3) respectively.
sd(i) = fd(i) − fd(i − 1) (3.3)
Then it uses the negative and positive peaks of the first derivative and the
negative and positive peaks of the second derivative as features for each spike.
Then these features can be used together to distinguish between different spikes
without any calibration.
A potential disadvantage of using the derivative is that the wavelength
modulation’s amplitude is smaller than the spectral line’s width, which helps
in distortion avoidance. This leads to a low signal amplitude compared to the
original signal. Since the noise level is still the same, this represents a loss in
signal to noise ratio and thus a compromise has to be reached.
Variable selection techniques were presented in [108,109] as feature extrac-
tion algorithms. They do not depend on the entire spike samples but only the
41
necessary information that can be obtained from a subset of samples to cluster
the data after that. These samples are very useful when a single outstanding
sample set is presented.
There are many examples for the variable selection techniques such as:
1) Chi-square approach that evaluates the spikes information based on mea-
suring their chi- squared statistic.
2) Correlation approach that evaluates the spikes information based on corre-
lation coefficient.
It is difficult to ascertain the subset of samples that contains the essential
information and it requires significant computational time. Nevertheless, it
will be used if these subset samples are clear enough.
Yang used Informative samples in [101,110], which depend on a theoretical
framework to extract the spikes’ feature. This framework includes neuronal
geometry signatures, noise shaping, and informative sample selection. It uses
the high frequency signal spectrum to differentiate between the neuronal geom-
etry signatures. In addition, it uses the noise-predefined properties to reduce
the SNR. It then uses the Variable Selection Techniques to identify informa-
tive samples to be subsequently used to sort spikes. Again, it is very complex
and challenging process to select the samples, which hold the most pertinent
information. The input data is the main performance controller.
In [111], Ghanbari used Graph Laplacian features to reduce the dimensions
of the data. The main M dimension data X = {xn}Nn=1 is reduced to a M ′
dimensional data using the transformation Y = AT X, where A = {am}Mm=1
and a is a vector with M dimension and projection A can be calculated from
42
this minimisation Equation:
minA
N∑i=1
N∑j=1
|yi − yj|2Wij (3.4)
It is eligible if the M dimension neighbouring points in the main data remain
close to each other after a projection to the low dimensional space [112].
The spike signal is modelled using an autoregressive (AR) model of pth
order in [106, 113]. Its coefficients are calculated using the Burg algorithm.
The features used are the coefficients of the AR model for each spike.
xt = c +p∑
i=1φixt−1 + εt (3.5)
where φ1, ..., φp are the parameters of the model, c is a constant and εt is white
noise.
AR model succeeded in separating the signal from background activity.
However, this method is time consuming, hardware intensive, and draws ex-
cessive amounts of processing power. For these reasons it is inefficient for
online applications.
Geometrical Shape was one of the earliest techniques to extract the spike
features and it was introduced in [114]. This technique depends on the shape
of the spike, which could be the width, the height or peak-to-peak amplitude.
This method was commonly used because the computer power and memory
was not so high, but it takes time to choose the features that can highly
differentiate between the spikes [115]. In this method, a long feature vector
should be used which causes a low speed for any online application.
Principal Component Analysis was used as a feature in [116,117]. The idea
43
behind principal component analysis (PCA) is finding an arranged set of rect-
angular basis vectors that capture the directions in the spikes of largest vari-
ation. This indicate the signal’s most significant components. Usually, due to
high variations in the visual aspect of neural spikes, the principal components
are then re-measured. Therefore, PCA-based algorithms are semi-automated,
as they need the user intercession to ensure that the detection accuracy is high.
PCA algorithm performs well if there is a high correlation between spikes.
However, recorded spikes are usually mixed with noise. Therefore, PCA fails
in noisy recordings.
Suppose that the given data X = {xn}Nn=1 with dimensional M . PCA
uses the linear transformation V T XC to reduce the dimension of the data to
M ′ where XC = xn − E[x]Nn=1 and V is the projection matrix that contains
the largest M ′ eigenvalues λ1 ≥ λ2 ≥... ≥λM ′ obtained from the covariance
matrix of XC [118].
Because there is no probability distribution specified for the observations,
PCA is not a statistical method, however PCA is an excellent mean by which
to process and concisely represent data. PCA will work better if standardised
data is used which changes the mean to zero. Most of the time the scales of
the original variables are not comparable and the first principal component is
dominated by those variables with a high absolute variance. Standardisation
will lead PCA results to come out with respect to standardised variables. This
makes the interpretation and further applications of PCA results even more
difficult. PCA can get rid of second order dependences; on the other hand, it
causes trouble with higher order dependencies.
44
Wavelet Transform (WT) is one of the most prominent and usable methods
for extracting features. It is a time-frequency representation of the signal, it
is defined as the convolution between a brain signal x(t) and wavelet function
Ψa,b(t) [100,119],
WΨX(a, b) = 〈x(t)|Ψa,b(t)〉 (3.6)
where Ψa,b(t) are expanded and shifted versions of a unique wavelet function
Ψ(t),
Ψa,b(t) = |a|− 12 Ψ
(t − b
a
)(3.7)
where a is the scale and b is the translation parameter.
There are different versions of the wavelet; low frequency components pro-
duce a contracted version and high frequency components produce a dilated
version. Hence, the signal’s detail can be identified at several scales using
different wavelet functions.
WT has many advantages. First, the localised shape differences are consid-
ered while extracting the features. Second, it extinguishes the signal station-
ary requirement. Third, the spike’s shape information is dispensed on many
wavelet coefficients, but in PCA the first three principal components repre-
sent most of the spike’s information that are not obligatory helps in cluster
identification. Moreover, wavelet coefficients are time focalised.
The most popular wavelet transform which are used is Haar wavelets, which
are rescaled square functions. Haar wavelets are the best wavelet transform
as it has heavyset support and orthogonality, also it can represent the spike
using small number of wavelet coefficients and it does not depend on any prior
knowledge (i.e. spike shape) [120].
45
Multi-modal wavelet coefficient (Multimodality pickup) was introduced
in [120]. It is commonly used if the spike components are distributed with
multiple peaks. These components are used to separate a large number of
clusters in the data. Multiple peaks wavelet coefficients are picked up then the
Kolmogorov-Smirnov (KS) [120] test for the normality is employed. KS test
evaluates the deviation from the normal distribution.
To reduce the outliers; mean and variance statistical assessment is calcu-
lated for the normalised data. When mPICK is used without wavelet trans-
form, the KS test is applied to the distribution of the values at each time point
of all the detected spike waveforms and pick up the time points that yield large
multi-modality. A problem here is that the redundancy can be generally large
in the features extracted by mPICK.
Using wavelets can cause other serious problems. Firstly, the WT is shift
sensitive because input signal shifts generate unpredictable changes in WT co-
efficients. Secondly, the WT suffers from poor directionality because WT co-
efficients reveal only three spatial orientations. Thirdly, WT analysis lacks the
phase information that accurately describes non-stationary signal behaviour.
Given these disadvantages, a feature extraction method is necessary. Two
logarithmic feature vectors will be used to represent the signal; these methods
are the Cepstrum Coefficients and Mel-Frequency Cepstral Coefficients. The
advantages of using these methods are stated in the following chapter.
46
3.3 Spike Sorting
This is the step where the neural spikes are grouped into different clusters
based on their sources. The clustering step is usually the most difficult and
complicated step in the Spike Sorting process. In early Spike Sorting, the
clustering method was performed manually, with the obtained features drawn
on a scatter plot and the boundaries of each cluster determined manually [114].
The best known Spike Sorting software packages enables the user to define
the cluster edges by drawing polygons in the feature space using the mouse
pointer. This method was not practical, however, as it mainly depends on
human judgement, which is not infallible [121, 122]. Moreover, they were ex-
tremely time consuming, so, researchers decided that they needed a semi-
automated approach. Semi-automated methods were implemented depending
on window discriminators, by which any spike that intersects with one or sev-
eral user-defined windows are marked and assigned to the same neuron. The
most common Spike Sorting methods will be investigated, and the main ad-
vantages and disadvantages of each method will be highlighted.
The first clustering algorithm is called K-means. It is a fully automated
method used to cluster the data and which is more sophisticated than manual
and semi-automated clustering methods. This method is called K-means and
it is now considered to be the benchmark for all other techniques [123]. The
K-means algorithm is based on a distance metric. The detailed algorithm is
described in the flowchart shown in Figure 3.2 at the end of this subsection.
Let us focus now on the main advantages and disadvantages of this method.
The major advantages of k-means are simplicity and speed. It is a very simple
47
algorithm and its computation time is very low. On the other hand, its main
disadvantage is that it is a supervised algorithm, which means it does not work
unless the user enters the number of clusters.
Most of the time, Spike Sorting is used by Brain Computer Interface (BCI)
applications. These are considered to be fully automated applications in which
the user cannot enter any data. In addition, it is immensely difficult for the
user to know the number of neurons. However, substantial amounts of research
has been performed to estimate the number of neurons and use this as an input
to covert the k-means to an unsupervised algorithm [124].
K-means training does not run in real time, which is a major drawback. So
it cannot be used for any online (real time) application. In addition, K-means
is parametric which means that each point (spike) is allocated to a specific
cluster depending on the distances from the cluster’s centroid. This will lead
to spherical clusters, which is not the case of many neural data distribution
such as electrode drifting, and the neural data distribution will form ellipsoidal
clusters. However, K-means will divide the ellipsoidal cluster into two spherical
clusters.
Another algorithm that is used in Spike Sorting is called Valley Seeking. It
is an unsupervised clustering algorithm [125]. Valley seeking is based on the
normalised density derivative (NDD), it measures the dissimilarity between
each observation pair in a local neighbourhood. The normalised density deriva-
tive is calculated first and the peaks of this function are detected as shown in
Figure 3.3. The regions between these peaks are known as the valleys and they
identify the cluster boundaries.
48
Figure 3.2 K-means calculation steps. The first step is to define thenumber of clusters that one needs to generate. Each cluster represents asingle neuron. Then, randomly select a random centroid for each cluster inthe k clusters. This will leads to k random centroids. Each data point willbe assigned to the cluster with the closest (usually by Euclidean distancemeasure) centroid. Then, recalculate the centroid of each cluster based onthe cluster’s mean value. Finally, steps 3 and 4 should be repeated untilthe centroid values do not change or until a specific number of loops isreached.
The major advantage of the valley seeking algorithm is that it is an unsuper-
vised algorithm, so the user does not enter the number of clusters. Moreover, it
is a non-parametric algorithm, which means that it can cluster different neural
data distribution with different shapes. On the other hand, it still has the same
running time problem as it does not run in real time, making it incompatible
with the real-time applications. From a hardware point of view, this algorithm
has a significant complexity as it performs operations and stores the data in at
least six n-by-n matrices where n represents the spike’s count. Valley seeking
cannot be used for large n as it will be difficult to implement on hardware.
49
Figure 3.3 Steps of the Valley Seeking clustering algorithm.
In [120], Superparamagnetic clustering (SPC) was introduced, which be-
came one of the most acclaimed clustering algorithm in Spike Sorting pro-
cess [126]. It is an unsupervised clustering algorithm. The spikes are rep-
resented as a granular magnet model, where each spike is assigned a spin.
The temperature of the model is increased gradually from low to high. The
ferromagnetic region appears at very low temperatures where all the spins
are aligned, and the paramagnetic region appears at high temperatures. The
system is unstable and all the spins are at random positions. The superparam-
agnetic region appears when the temperature of the model lies between these
two temperatures (the high and the low). In this region, the spins, which have
a similar high-density region, are grouped together while the spins of different
high-density regions are not grouped. At these points, the clusters appear. An
algorithm is also written at the end of this subsection.
SPC has some advantages, similar to Valley Seeking. Firstly, SPC is an
unsupervised clustering algorithm in which the number of clusters (neurons) is
not used as an input. Secondly, it is nonparametric so it can represent any neu-
ral data distribution. It does, however, contain some disadvantages, the first
being its huge complexity. It needs at least 9 n-by-n matrices for computation,
50
where n represents the spikes count and huge n must need many operations
and memory to be done. In addition, Monte Carlo simulation is needed for
SPC computation, making the computation time even more protracted. The
algorithm can be made simpler by replacing the Monte Carlo simulations with
mean-field approximation, which will decrease the running time, however the
complexity will increase. Moreover, SPC works offline, which means that it is
not a real time algorithm making it impractical for any BCI applications.
1. Estimate matrix D = (dij) which is basically based on Euclidean dis-
tance.
2. Get all neighbours’ points for point vi based on the K nearest neighbour-
ing algorithm. vi can be a neighbour for point vj if and only if vi and vj
are one of the K nearest neighbours for each other.
3. A random Potts spin is allocated to every point vi and is represented by
si = 1, 2, ..., q and si can have one as a default value. Also, q represents
the achievable number of spins which does not represent the number of
clusters at all. In [126] the value 20 is used for q.
4. Calculate Jij represents the interaction strength, and it is calculated for
two neighbouring points vi and vj, where
Jij =
⎧⎪⎨⎪⎩
1K
exp( d2ij
2a2 ), if vi and vj are neighbours.
0, otherwise.(3.8)
and a is the average of all dij‘s for all points which are neighbours.
5. Monte Carlo simulation is applied to all temperatures (such as T =
51
0:0.02:0.2), Monte Carlo simulation is shown from step (a) until (d) with
iterations m ranges from 1 to M.
(a) A frozen bond is applied on nearest neighbouring points which are
represented as vi and vj with probability pfij = 1 − exp(Jij
T.δsi,sj
)
when si = sj where δsi,sj= 1 and it is zero in any other cases.
(b) A number x is selected randomly from a uniform distribution ranges
between zero and one. If x < pfij, there is a which is the bond
between vi and vj.
(c) All the points which are connected by a bond form a cluster.
(d) Generate cm as:
cmij =
⎧⎪⎨⎪⎩
1, if vi and vj are in the same cluster.
0, otherwise.(3.9)
6. Two-point connectedness is calculated and is given the symbol Cij. It
can calculated from this Equation: Cij = 1M
∑Mm=1 cm
ij
7. Spin-spin correlation function is calculated from the Equation below:
Gij = (q−1)cij+1q
8. If Gij > θ, where θ is a predefined threshold, the same cluster contains
vi and vj.
9. Cluster labels are assigned to observations based on the value of G.
Osort is the only automatic and online clustering algorithm. It is basically
designed and implemented by researchers who need to extract each signal
neuron in their experiments [127]. This target needs huge amount of data
52
processing in real time. Their method is simple. They use the on-the-fly
technique to allocate each spike to a specific cluster. The algorithm is written
at the end of this chapter.
The Osort does not require either huge computations or memory and it is
considered the only algorithm that can be implemented in hardware. The
major disadvantage is that it clusters the data based on the distance, and
especially assumes that the data distribution is spherical. This means that it
works effectively with spherical data distribution but generates poor results
for any other distribution, such as ellipsoidal clusters, which usually happen
due to the multivariate noise.
The Osort algorithm is shown below.
1. The first data point is allocated to its own cluster as an initialisation
step.
2. Euclidean distance is calculated between the following data point and
the centroid of each cluster.
3. Calculate the smallest Euclidean distance and compare it with the merg-
ing threshold TM . The point is assigned to the nearest cluster if this dis-
tance is less than TM and the cluster’s mean should be calculated again
after adding the new point. The mean should use the most recent N
points. Otherwise, create a new cluster.
4. Check if any distance between any clusters is less than the sorting thresh-
old TS, if yes, those clusters should be combined together to create a new
big cluster with a new mean.
53
Steps 2 to 4 are then done again in an open-ended fashion. The simple
form of the Osort algorithm, TM = TS, which is equivalent to the data variance
calculated continuously on a long (∼ 1 min) sliding window. The most recent
N points in each cluster must be used to calculate the cluster’s centroid. This
assists in identifying the drift of any electrode, as it is possible for the clusters
to drift.
A comparison that shows the differences between K-means, Valley Seeking
clustering, SPC, and Osort is shown in Table below. SPC gives close results to
Valley seeking clustering, but Osort generates many clusters, which should not
be there, and this is called over-clustering, where it splits the original cluster
to one or more sub-clusters. A summary of various characteristics of each of
the algorithms described in this section is given in Table 3.1.
Table 3.1 Comparison between the common Spike Sorting techniques.K-means Valley Seeking SPC Osort
NonParametric No Yes Yes NoAutomatic/Unsupervised No Yes Yes YesReal-time/Online No No No YesAdaptive No No No YesAccuracy low 0.9 0.74 0.85 0.74Complexity Low High High Low
In the next chapter, HMM will be used in the Spike Sorting process. Briefly,
this identifies the signal as a set of states, which will lead to a better accuracy.
It is non parametric algorithm, unsupervised, online and it has low complexity.
54
3.4 Noise level Estimation and Quality As-sessment Measure
The input of the Spike Sorting process is a neural signal such as EEG signal.
EEG signal passes through several steps including feature extraction and Spike
Sorting. There is a very important step before applying any method, this step
is to establish the quality of the input signal and the amount of noise in the
signal. This aspect is paramount in this research.
Neural signal will be ideal if it does not contain any noise. Unfortunately,
it is impossible to record a neural signal without noise. Removing some noise
sources can be relatively easy; however, others are more challenging.
One of the main sources of noise is the external environmental noise, for
example computers, routers, displays, AC power lines and mobile telephones.
The easiest way to reduce the effect of the external environmental noise source
is to avoid having it in the first place, which can be done by turning off these
devices. However, this solution cannot be implemented in all cases, as one will
need to turn on at least one computer to record the data [128].
The external environmental noise source can be partially avoided by insu-
lating the recording room using a Faraday cage. This will reduce the external
environmental noise but it needs an advanced planning and costly materi-
als [129].
Physiological noise is another noise type, which can be generated from dif-
ferent sources such as cardiac signal (ECG), muscle movement artifacts (EMG)
and eye movement artifacts (EOG). The ECG signal effect cannot be avoided,
but it is considered to have the lowest effect on the recorded EEG signal.
55
EMG and EOG signals can have a huge effect on the EEG signal. They can
be avoided for a minor period by asking the participant to stay in a motionless
position, but this will not last for a long time. Other researchers have tried
to plan their experiments carefully in order to avoid any motion during the
critical task recording component, for example, by ensuring no eye blinking or
any limb motion during recording of the main critical part [130].
Signal averaging [87] is considered to be the easiest way to deal with noise
in the recorded EEG signal. It is based on the assumption that the noise
is random or it can happen with a random phase. However, the EEG signal
should be stable. Signal averaging has some limitations. One of these problems
is stability, signal averaging will work when a stable signal is recorded over a
big count of trials. Another problem is that signal averaging can only eliminate
stationary, zero mean random noise, which means that it will not work with
any non-random noise. Finally, signal averaging needs a quite large number of
trials to sufficiently increase the Signal-to-Noise ratio.
Visual inspection [131] is one of the most common ways to detect the noise
in the recorded EEG signal. It is a straightforward procedure. Most common
artifacts can be detected before applying any analysis on the recorded data.
However, it is not always an effective method especially when dealing with a
huge amount of data; it needs a vast amount of time to visually inspect these
data. Moreover, it is a difficult task to detect some types of noise, even for
expert EEG analysts.
The estimation of SNR has been used in numerous fields, such as speech
and image processing [132, 133], and has been an active field of research in
56
recent years. An accurate SNR estimation can improve the performance of
any algorithm, where the amount of noise is known prior to any processing.
Hence, it makes it easier to compensate for the effects of noise.
Different techniques have been developed for SNR estimation. These tech-
niques were used to estimate the amount of noise in a signal. One of those
techniques is called the Directive algorithm, which estimates the noise based
on spatial filtering. The original signal is detected and any other signal which
comes from other direction is considered as noise [134,135]. This technique is
successfully used in speech processing, however, it cannot be applied to brain
signal due to the countless number of sources (neurons), located in different
directions.
In [136–138], Noise Suppression algorithms were used to estimate the noise
level based on one channel only and without any spatial information. The
noise estimate is generated based on the signal pauses. In signal pauses, the
signal’s spectrum is calculated. This spectrum identifies the present noise floor.
It estimates the noise perfectly in speech applications; however, this will not
be the case if applied to brain signals. At anytime, different neurons must
fire action potentials as discussed in Chapter 2, hence, there are no pauses in
the neural signals, pauses upon which Noise Suppression algorithms mainly
depend on them.
Doblinger [139] divided the signal into bins based on frequency. Then, the
minimum of the noisy signal was tracked in each bin continuously. However, it
failed to detect any increase in the signal power as it is detected as an increase
in the noise floor.
57
Hirsch and Ehrlicher [140] and Martin [141] proposed algorithms that do not
depend on the signal pauses. These algorithms depend on the statistical anal-
ysis of the spectral energy envelope. Both algorithms are based mainly on
tracking the minimum of the noisy signal within a specific limited window.
Tracking is based on two energy histograms values, which are built using dif-
ferent frequency bands. The minimum value is less than the mean, therefore
the unbiased noise estimate is calculated using a bias factor, which is reliant
upon the minimum estimate statistics. The fact that both methods are very
time consuming represents a methodological shortcoming. If the noise floor
changes, further time will be consumed while updating the noise spectrum.
In [142, 143], Cohen introduced a minima controlled recursive algorithm,
which tracks the noisy regions only and update updates the noise estimate
accordingly. Regions tracking is done based on a predefined threshold. When
the noise spectrum increases, there is a time delay and lagging twice that
window length. Delay and thresholding are the drawbacks of this method.
Ris and Dupont [144] mixed some of the previous methods with narrow
band spectral analysis, by which valleys between the segments of the signal
enabled noise estimation. However, this method needs extended time windows
to accomplish the required spectral resolution. The major drawback of the
method is the lack of fast adaptation when the noise levels increases, so this
method cannot be used in real time applications and when the SNR is high.
Finally, Stahl introduced a quantile-based algorithm to estimate noise in
[136], the noise is estimated depending on the noisy power spectrum‘s qth
quantile. A wrong noise floor is generated when the noise is varying in the
58
signal, which is the case in neural signals. This leads to an incorrect noise
level estimation.
For all the reasons stated above, a noise estimation method, which depends
on principles of statistics and applied on the signal’s feature level in the loga-
rithmic spectral domain, is required. In brief, vectors holding the features of
a noisy signal could be modelled using a Gaussians mixture, and the recur-
sive EM algorithm to maximise the conditional likelihood function, which will
generates the noise feature vector.
An automated quality assessment measure is needed. This measure can
identify the quality of the recorded signal based on the amount of noise, and
the biological and statistical features of the signal. It can identify bad channels
and containing excessive noise [145]. This will be the first automated quality
assessment measure for the neural signal. There are various research and BCI
applications, which are based on neural signals such as EEG signals. All of
them use the EEG signals to control, give order and assess machines but the
assessment of the EEG signal itself has not yet been done. It is a compelling
topic of investigation to assess EEG signal and use this assessment measure to
improve the performance of the applications, such as BCI applications. It will
be used as an input for the BCI applications as well, hence, there will be two
inputs for BCI applications. The first input is the EEG signal itself and the
second is the quality of the EEG signal.
59
3.5 Conclusion
This chapter has provided a critical review of feature extraction methods,
Spike Sorting techniques, noise estimation and quality assessment measures
for the neural signal. The main advantages and disadvantages of each method
has been highlighted. New feature extraction and Spike Sorting methods are
needed based on the reasons mentioned in this chapter. Moreover, a quality
measure will be needed to assess the recorded EEG signal. In the next chapter,
the new methods of feature extraction and Spike Sorting will be introduced.
Feature extraction methods will extract meaningful features which will improve
the accuracy of the Spike Sorting process. Moreover, new clustering algorithm
will be used to increase the speed and performance of the Spike Sorting process.
Then, the noise level estimation will be addressed in Chapter 5 followed by
the automated scores chapter.
Chapter 4
Feature Extraction and SpikeSorting
4.1 Introduction
A critical review on feature extraction methods, Spike Sorting techniques,
noise estimation and quality assessment measures for the neural signal were
provided in the previous chapter, where advantages and disadvantages of each
method were highlighted. In this chapter, the new feature extraction and Spike
Sorting methods are introduced. This is the first step to decoding the brain
and helps designing an automated quality measure since it can identify the
behaviour of the neurons. In order to undertake the Spike Sorting process,
, first the spike features should be extracted, and then clustering the spikes
according to those features [114]. Extracting the features is the most important
part in these steps as the spikes are convoluted with noise and it is not an
easy task to extract distinguishable features. Moreover, it is important to
consolidate the number of features in case of extracting too many unnecessary
features, to reduce computational burdens for real-time applications.
60
61
Three different feature extraction methods were mainly used, which are Dif-
fusion Maps, Cepstrum Coefficients and Mel-Frequency Cepstral Coefficients.
Then, Hidden Markov Models (HMM) were applied for spike classification.
In the beginning of this research, the Diffusion Maps were used to represent
spikes in a meaningful feature vector, then trying to improve the performance
of extracting features, the Cepstrum and Mel-Frequency Cepstral Coefficients
were used.
The next step was focusing on the Spike Sorting process itself. HMM was
used for Spike Sorting. It was noticed that neural spikes have been represented
precisely and concisely using HMM state sequences. A HMM was built for neu-
ral spikes, where HMM states can represent the neural spike. The neural spike
can be represented by four states: it could be ascending, descending, silence or
peak. Each spike was constituted with an underlying probabilistic dependence
modelled by HMM. Based on this representation, spikes sorting became a clas-
sification problem of compact HMM state sequences. In addition, the method
was enhanced by defining HMM on extracted Cepstrum features, which im-
proved the accuracy of Spike Sorting. In addition, Mel-Frequency Cepstral
Coefficients (MFCC) were applied to improve the classification results. Sim-
ulation results demonstrated the effectiveness of the proposed method as well
as the efficiency.
4.2 Feature Extraction Methods
Feature extraction is one of the most important steps in which the salient
features of the spikes are derived based on spike wave-shapes. The features
62
should be able to differentiate spikes of different neurons and preferably low di-
mensional well. Peak-to-peak amplitude, maximum spike amplitude and spike
width are simple features, which may be used [114]. These approaches however
are sensitive to noise and intrinsic variations in spike shapes. As shown in the
literature review, principal component analysis (PCA) is one of the popular
methods used for feature extraction in Spike Sorting [146,147]. Wavelet Trans-
form [148] has emerged as a competitive feature extraction method for Spike
Sorting [149–151].
4.2.1 Diffusion Maps
In the diffusion maps (DM) framework, one needs to construct a graph of
the data [152]. The weights of the edges of the graph are computed by the
Gaussian kernel function. This process results in a matrix w with elements
defined as :
wi,j = e− ||xi−xj ||22σ2 (4.1)
where σ is the variance of the Gaussian variables, xi and xj are nodes of the
graph. The matrix w afterwards is normalised to have the summation of its
rows elements equals to 1. The following matrix, denoted as p(1), is then
constructed:
p(1)i,j = wij∑
k wik
(4.2)
The matrix p(1) is considered as a Markov matrix as the DM originates from
dynamical systems theory. The matrix p(1) represents the probability of a
transition among data points in a single time step. The forward probability
matrix for t time steps p(t) is accordingly defined by (p(1))t. The diffusion
63
distance is calculated based on the random walk forward probabilities p(t)ij as
follows:
D(t)(xi, xj) =
√√√√√∑k
(p(t)ik − p
(t)jk )2
ψ(xk)0 (4.3)
where ψ(xk)0 = mk∑j
mjwith mk = ∑
j pkj the degree of node xk. It is obvious
that pairs of data points with a small diffusion distance correspond to a high
forward transition probability. The low-dimensional representation O is then
represented by the d non trivial principal eigenvectors of the eigenproblem
using spectral theory on the random walk p(t)ν = λν. The largest eigenvalue
is trivial because the graph is fully connected, and thus its eigenvectors ν1 is
discarded. Then the low-dimensional data representation is expressed by
Y = (λ2ν2, λ3ν3, ..., λd+1νd+1) (4.4)
The results are shown in the next section, the accuracy of the most common
algorithms were compared and diffusion maps showed high accuracy despite
using less number of features, this reduced the computation cost as well. How-
ever, using Cepstrum coefficients and Mel-Frequency Cepstral Coefficients gave
the highest accuracy; the results will be discussed in the following sections.
4.2.2 Cepstrum Coefficients
The proposed method used Cepstrum to represent spikes of a noisy signal.
Cepstrum is the Inverse Fourier transform (IFT) of the logarithm of the es-
timated spectrum of a signal as shown in Figures 4.1, 4.2, 4.3 and 4.4. The
idea behind representing the spikes using Cepstrum is that not only does Cep-
strum hold information about magnitude, but also it selects more meaningful
features from noisy signals. Moreover, the number of the extracted features
64
is very small compared to other methods, which leads to less computation.
Hence, Cepstrum gives better performance, more efficient Spike Sorting and
requires less computation time.
In this section, the proposed feature extraction method was compared with
the most common extraction method, the Haar wavelet transform. In order to
compare the feature extraction methods, Superparamagnetic Clustering (SPC)
algorithm was applied to both methods. SPC is considered the most common
clustering algorithm used for Spike Sorting.
A multielectrode array system was used to record the neural spikes and
after that, thresholding was applied to recorded data to detect the spikes.
There are abundant methods used to select a threshold for the data [153], but
the most accurate method is the dynamic thresholding as shown in Equations
(4.5) and (4.6) [119].
Thr = 4σn (4.5)
σn = median( |x|
0.6745
)(4.6)
where σn is the background noise standard deviation and x is the bandpass
filtered signal.
The next step was to extract the spike features. This is the most important
step because clustering the spikes depends on the accuracy of the extracted
features. Extracting the most dominant and invariant features that are insen-
sitive to noise will improve the performance of neural spikes classification.
Cepstrum is computed as in Equation ((4.7)):
65
Figure 4.1 Sample signal representation.
Figure 4.2 DFT of the signal in Fig. 4.1. (F{x[n]})
c[n] = IDFT{log|DFT{x[n]}|} (4.7)
Cepstrum feature vector of a signal is computed as in Equation (4.8):
c[n] =N−1∑n=0
log
(∣∣∣∣∣N−1∑n=0
x[n]e−j 2πN
kn
∣∣∣∣∣)
e−j 2πN
kn (4.8)
where c is the Cepstrum feature vector of signal x, N is the number of samples
in the signal, j is√−1 and 0 ≤ k ≤ N − 1.
The last step was clustering the spikes based on the extracted features,
Superparamagnetic Clustering was used to cluster the spikes. It is the most
66
Figure 4.3 Log magnitude of the DFT of the signal in Fig. 4.2.(log|F{x[n]}|)
Figure 4.4 The Cepstrum representation of the signal shown in Fig. 4.1and it is called as the inverse DFT of the of the signal in Fig. 4.3(F−1{log |F{x[n]}|}).
Figure 4.5 Haar representation of signal in Fig. 4.1.
67
Figure 4.6 Cepstrum representation.
commonly used, unsupervised clustering algorithm, and is explained in [154].
It will be replaced by an improved clustering method in the following chapter.
Two algorithms were developed to measure the clustering accuracy between
Haar and Cepstrum’s spike representation. Algorithm 1 was developed to mea-
sure the clustering accuracy in terms of spikes correct assignment. The inputs
of the algorithm were the real spikes (RealS) and the real clusters (RealC) of
the used data. Also the generated spikes and clusters were marked as GenS
and GenC and the generated spikes were mapped to the real ones based on
the detection time (DTime).
Then the spike’s real cluster (RealClass) and the generated cluster (Class)
are known. For each generated cluster, the number of spikes were counted from
real cluster 1, 2 and 3 (SpkRealC1, SpkRealC2 and SpkRealC3) and max of
them will map the real cluster to the generated one (MappedRealtoGenClass),
then that max number was divided by the total number of spikes of the real
class to get the mapping ratio (MappedRealtoGenClassRatio).
Also Algorithm 2 was developed to measure the accuracy of the clustering
results using the confusion matrix [155]. First, Superparamagnitic clustering
algorithm was applied to 70% of the spikes (training data) and the remaining
30% was used for testing. Secondly, the mean for each generated cluster was
68
Algorithm 1 Calculate spike and cluster matching correctness.Require: RealS and RealC are known.
Also GenS and GenC are calculated.Ensure: MappedRealtoGenClassRatio.
i = 0while GenS[i] = null do
MinDiff = 1000j = 0while RealS[j] = null do
TimeDiff = |RealS[i].DTime − GenS[i].DTime|if TimeDiff < MinDiff then
MinDiff = TimeDiffGenS[i].RealClass = RealS[j].Class
end ifj++
end whilei++
end whilewhile GenC[i] = null do
SpkRealC1 = GetSpikesInfo(GenC[i], RealC[1])SpkRealC2 = GetSpikesInfo(GenC[i], RealC[2])SpkRealC3 = GetSpikesInfo(GenC[i], RealC[3])MappedRealtoGenClass[i] =
MaxSpikeNo(SpkRealC1, SpkRealC2, SpkRealC3)MappedRealtoGenClassRatio[i] =MappedRealtoGenClass[i]/SpikesCount(GenC[i])
end while
calculated. Thirdly, the cluster that has the minimum Euclidean distance
between its mean and the testing spike was assigned to the testing spike.
Fourthly, the class that has the maximum number of spikes in that generated
cluster was assigned to the testing spike. Finally, the index of the detected
class and real class of the tested spike was incremented in the confusion matrix.
The accuracy can be calculated by adding the diagonal values then divide it
by the sum of the matrix values.
69
Algorithm 2 Calculate Confusion Matrix for clustering results.Require: Cluster 70% of the detected spikes.
The remaining 30% will be used for testing.while GenC = null do
spikes = GetAllSpikesBelongtoCluster(GenC)ClusterMean[GenC] = Mean(spikes)GenC = nextCluster
end whilewhile TestingSpike = null do
GenCluster = minEucDis(TesingSpike,ClusterMean)MajorityClass = ClassMajoritySpikes(GenCluster)RealClass = getRealClass(TestingSpike)ConfusionMatrix[MajorityClass][RealClass]++TestingSpike = nextSpike
end while
For the performance comparison of classification using different feature vec-
tors, a synthetic time series signal representing the neural spikes, with varying
degree of noise levels, was adopted. This dataset is commonly used for per-
formance analysis [119]. The results were accumulated over 50 repetitions
to avoid any bias. Spikes embedded into the synthetic signal are from three
distinct classes; class 1, 2 and 3 contain 784, 776, 794 spikes respectively. Cep-
strum transformation gave better clustering results as compared with that of
the Haar wavelet (HW) features in terms of the computational cost, number of
generated clusters, number of spikes per cluster, number of unclustered spikes,
percentage of correctly assigned spikes and confusion matrix accuracy.
Unclassified spikes can be defined as the spikes that could not be assigned to
any cluster during classification. This factor was highlighted as one of the key
parameters in validating the performance of the proposed algorithm. Compar-
isons performed are shown in Table 4.1 where unclassified spikes were assigned
to cluster zero. A clear distinction can be seen between Haar and Cepstrum
70
Table 4.1 Number of spikes in each cluster using Haar and Cepstrumrepresentation.
Generated Haar’s Spike Cepstrum’s SpikeCluster Count Count0 1032 1291 316 6722 273 6433 261 5074 94 845 65 306 24 -
based algorithms. The Haar method managed to classify around 40% spikes
whereas the classification done by Cepstrum method managed to cluster above
95% of the spikes. In reference to three classes of the synthetic data used for
this validation, Haar method classified all the remaining spikes into six clusters
whereas the Cepstrum method divided the spikes into five clusters with three
very dominant ones, as shown in Figure 4.7. Average correlation coefficient
calculated for spikes within the same cluster was around 93% and 95.5% for
Haar and Cepstrum, respectively. The number of spikes that are assigned to
the first three clusters (1, 2 and 3) using Cepstrum is approximately twice
the number assigned using Haar. This means that the Cepstrum succeeded to
represent the spikes in a better way leading to more meaningful clusters.
Haar represented the spike in a 64-sample point. After some processing
steps, the best 10 sample points were selected for clustering. However, for the
Cepstrum approach, only 20 sample points were used. This implied that less
computation time could be used.
Also, Tables 4.2 and 4.3 show the output of Algorithm 1. The number
71
(a) (b)
Figure 4.7 Haar and Cepstrum output in terms of number of clusters andnumber of spikes per cluster.
of spikes, which were correctly assigned inside each cluster by the Haar repre-
sentation, was about 50% fewer than those by the Cepstrum representation.
Besides that, percentages of the correctly mapped spikes using the Cep- strum
representation were higher than those of the Haar representation.
Table 4.2 Number of correctly assigned spikes in each cluster using Cep-strum representation
GeneratedClass 1 Class 2 Class 3 HighlyMapped
Correctly Wrongly Not
Cluster Class assigned assigned assigned
1 633 24 15 1 80% 4.9 % 15.1%2 10 608 25 2 78% 4.5% 17.5%3 11 13 483 3 60% 3% 37%4 3 4 77 3 - - -5 1 3 26 3 - - -
Algorithm 2 was applied to the results to compare the accuracy between
Haar and Cepstrum representation in terms of classification. A percentage
of 70% of the spikes were used as training data and the remaining 30% is
used for testing. In this experiment, synthetic data were used, so the correct
class assignment were checked using the testing spikes and filling the confusion
72
Table 4.3 Number of correctly assigned spikes in each cluster using Haarrepresentation.
GeneratedClass 1 Class 2 Class 3 HighlyMapped
Correctly Wrongly Not
Cluster Class assigned assigned assigned
1 6 302 8 2 38% 2% 60%2 263 8 2 1 33% 2% 65%3 2 8 251 3 31% 2% 67%4 1 89 4 2 - - -5 62 1 3 1 - - -6 2 20 2 2 - - -
Table 4.4 Haar’s Confusion Matrix.Class 1 Class 2 Class 3
Class 1 242 28 22Class 2 7 272 14Class 3 2 21 276
matrix. For example, if a testing spike belonged to class 1 and was assigned
to class 2 the cell [1][2] in the confusion matrix was incremented. The bigger
numbers in the diagonals the more accurate classification could be achieve.
The accuracy was calculated by dividing the sum of the diagonal number to
the total matrix sum. The confusion matrix of Haar shown in Table 4.4 gave
89% accuracy but when Cepstrum was used it gave 94% accuracy as shown in
Table 4.5.
Table 4.5 Cepstrum’s Confusion Matrix.Class 1 Class 2 Class 3
Class 1 282 8 2Class 2 10 279 4Class 3 9 13 277
73
4.2.3 Mel-Frequency Cepstral Coefficients
The most informative directions; those with lower entropy and with no
statistical model or orthonormal constraints, for example PCA or WT, are
linearly pursued MFCC. In addition, it will be shown here that PCA and
WT do not provide the highest clustering accuracy amongst the compared
linear feature extractors. On the other hand, the Mel-Frequency Cepstral Co-
efficients (MFCC) was proposed [156] for this step. The proposed method
provided higher clustering accuracy amongst the compared methods using dif-
ferent classifiers.
The use of MFCC as features for neural spikes has many advantages:
(a) MFCC can represent signals in a compact and meaningful way as they
allow focusing on specific frequencies by giving them more weight.
(b) Classifiers with MFCC features can achieve a good accuracy without the
need to build complex classification models.
Although MFCCs have been successfully used in many applications such as
speech recognition, music modelling, or emotion recognition, to the best of our
knowledge, they were not previously explored as features for identifying neural
spikes. After extracting the features, HMM [157] was applied in the clustering
step which gave better clustering results than the existing methods such as
K-means [158–161] and Superparamagnitic clustering (SPC) [119]. The main
problem in those clustering algorithms is that they rely on shape measurement
such as comparing width, height and spikes peak-to-peak amplitude.
This model is a novel introduction of HMM to analyse shapes of different
74
spikes. For each spike, the proposed method observed that it contained four
significant shape variations: silence, ascending, peak and descending. Each
spike was partitioned into several segments and define observations of HMM
as these spike segments. The states of HMM corresponded to the four shape
variations. HMM with mixture of Gaussians was applied in this method. An
expectation maximisation (EM) algorithm is used to compute optimal HMM
parameters. The Viterbi algorithm [162] was then used to find the most likely
state sequence to represent each spike. After that, the sorting of spikes was
undertaken to classify the state sequences obtained. Experiments demonstrate
the effectiveness and efficiency of the proposed method.
First of all, the neural signal was recorded, then the MFCC of the signal
was calculated using the following steps:
1. Each spike had its own data file that can be read into an array S(n), where
n ranges from 0, 1, ... N-1 with N being the number of samples.
2. Spikes were split into distinct frames, each frame is 20-40 ms (25ms is
standard). This means the frame length for a 16kHz signal was 0.025*16000
= 400 samples. Frame step was usually something like 10ms (160 samples),
which allows some overlap to the frames. The first 400 sample frame started
at sample 0, the next 400 sample frame starts at sample 160 and so on until
the end of the file was reached. If the file did not divide into an even number
of frames, it was padded with zeros until it did.
3. Once it is framed Si(n) was obtained where n ranges over 1-frame size and
i ranges over the number of frames. This is a form of quantisation.
4. When the complex DFT was calculated, Si(k) was gotten - where i denotes
75
the frame number corresponding to the time-domain frame. To take the Dis-
crete Fourier Transform of the frame, the following equation was performed:
Si(k) =N∑
n=1si(n)h(n)e−j 2π
Nkn, 1 < k < K (4.9)
where h(n) is an N sample long analysis window, and K is the length of the
DFT.
5. Then Pi(k) was calculated which is the periodogram based power spectral
of frame i is given by:
Pi(k) = 1N
|Si(n)|2 (4.10)
This is called the Periodogram estimate of the power spectrum. The absolute
value of the complex fourier transform was taken, and square the result. It
would generally perform the FFT. 6. The Mel-spaced filterbank was computed.
It is a group of 20-40 (the standard value is 26) triangular filters that is prac-
ticed to the periodogram power spectral estimate from step number five. The
filterbank was represented in 26 vectors. Most values in each vector were zeros
except for a particular section of the spectrum. Each filterbank was multiplied
with the power spectrum to calculate filterbank energies, and then coefficients
were added up. The output from this step was 26 numbers that indicated the
amount of energy found in each filterbank.
7. The log magnitude was calculated for the 26 energies, calculated from step
six. This gave 26 log filterbank energies.
8. Discrete Cosine Transform (DCT) was taken to the log magnitude (calcu-
lated in step seven) to give 26 cepstral coefficients.
The least 13 cepstral coefficients were used and the rest neglected, as only the
most significant features were needed. These values are called Mel-Frequency
76
Cepstral Coefficients.
After that, 10 spikes were used from each cluster to build an HMM, this
model was used to classify the testing data which has more than 500 spikes per
cluster. HMM details are explained in the section below as well as the results
of using both MFCC and HMM.
4.3 Spike Sorting
Millions of neurons’ activities reflect the complex processes of the brain.
It is very important to understand neuron actions, as this will leads to un-
derstanding brain behaviour. Neurons communicate with each other through
action potentials. These action potentials are called spikes, which appears
in any neural signal, and each neuron has a unique spike shape. Assigning
each spike to its own neuron is very challenging and it is called Spike Sort-
ing. The main goal of Spike Sorting is to find the correlation between specific
spikes and neurons. This research shows an improvement in the accuracy of
the Spike Sorting process, which will help in many brain computer interface
applications.
Many Spike Sorting techniques have been developed as shown in Chapter
3 (sections 1 and 2). The unknown number of neurons is one of the main
challenges of Spike Sorting. Distinguishing spikes in the local area is a difficult
task especially when there is physical and biological noise [114, 119]. Most of
the common Spike Sorting methods depend on shape measurement such as
comparing height, width, and peak-to-peak amplitude of spikes [163, 164] but
their main problem is that they are not efficient when signal to noise ratio is
77
low.
In this section, HMM was used for Spike Sorting, which showed an effective
and efficient result. There were three main steps as shown in Figure 4.8, these
steps are spike detection and feature extraction [119] and spike clustering.
Using HMM and MFCC in Spike Sorting is the main contribution in this
chapter. HMM can easily represent any spike, as each spike can be represented
by four different significant shapes, either ascending or descending, reaching
its peak or remaining unchanged (silence) and the HMM states were based
on these four different spike states. HMM parameters were computed using
expectation maximisation (EM) algorithm and the spikes’ state sequences were
generated using the Viterbi algorithm, then the spikes were sorted based on
their states. The results showed that the proposed method is effective and
efficient.
HMM is a statistical tool to model sequences, and it describes the prob-
ability distribution over a set of observations. It has been successfully used
for speech recognition. HMM consists of a set of states {S1, S2, ... Sn} as
shown in Figure 4.9. The Process moved from one state to another generating
a sequence of states: {Si1, Si2, ..., Sik, ...} and the Markov chain property of
each subsequent state depended only on what was the previous state, defined
as: P (Sik|Si1, Si2, ...Sik−1) = P (Sik|Sik−1). In addition, there are states that
are not visible, but each state randomly generates one of M observations (or
visible states) {V1, V2, ... Vn}.
HMM was utilized to model spikes in order to understand its underlying
states over a sequence of observations. For a spike, the significant shape states
78
(a)
(b)
(c) (d) (e)
Figure 4.8 The main steps of Spike Sorting.The Raw data are shown insub-figure(a). The spikes are detected as shown in sub-figure(b), then thespikes are divided into three groups as shown in sub-figures(c, d and e),based on the extracted features.
79
Figure 4.9 Observable and hidden states of the Hidden Markov Model.
are silence, ascending, peak and descending. Each of them was assigned to a
state (from s1 to s4) of the HMM as shown in Figure 4.10.
(a) (b)
Figure 4.10 The HMM states applied on the spikes.
HMM has five main elements, N is the number of states, M is the number of
observations, A and B are the state transition, observation probability matrix
B respectively and finally the initial state distribution Π.
Spikes were modelled using HMM. This modelling helps in finding the hid-
den spike’s states through observations. Any spike can be represented by these
states: silence, ascending, descending and peak (states from 1 to 4 respectively)
80
Figure 4.11 HMM states and the transitions from one state to another.
as shown in Figure 4.10. HMM states were built according to the spike states.
Figure 4.11 shows the possible transitions between states in any spike. Any
spike begins and ends with a silence state, also any state can move on to any
other state except moving from up state to the down state or from silence to
peak or vice versa. The state transition matrix is shown below.
A =
⎛⎜⎜⎜⎜⎜⎜⎝
0.3 0.4 0.3 0.00.4 0.3 0.0 0.30.3 0.0 0.4 0.30.0 0.3 0.3 0.4
⎞⎟⎟⎟⎟⎟⎟⎠
(4.11)
Spike detection is the first step in Spike Sorting. The most commonly used
method for a dynamic amplitude thresholding is introduced in [119], where
spikes are accurately detected. First the signal S is filtered by a bandpass
filter bf , then the standard deviation σ is calculated by
median{|Sbf |/0.6745}. (4.12)
Then the dynamic threshold will be 4σ.
Spikes were saved in L number of samples after being detected by the dy-
namic threshold. L was set to 64 based on the literature review. Using raw
81
data as HMM observation vectors is not a good idea due to noise sensitivity.
Cepstrum coefficients were used as a feature extraction method as mentioned
before in section 4.1.2, Cepstrum coefficients were extracted to help in noise re-
duction. Cepstrum features can capture both the amplitude property of spikes
and the phase of the initial spectrum. This helps in extracting meaningful
features from the data regardless of the noise level. Cepstrum was used to
represent spikes of a noisy signal. Cepstrum is the Inverse Fourier transform
(IFT) of the logarithm of the estimated spectrum of a signal as mentioned
previously.
Datasets used for experiments are the same as that used in [119]. Each
dataset contains a recording from three neurons with different noise levels. It
is difficult to differentiate between spikes, as they are very similar in shape.
In order to cluster them one must extract the features which can differentiate
them properly.
For the performance comparison of classification using different feature vec-
tors, a synthetic time series signal representing the neural spikes with varying
degree of noise levels, was adopted. The results were accumulated over 50
repetitions to avoid any bias.
Table 4.6 shows the clustering accuracy using different methods for feature
extraction and clustering algorithms. Spikes were represented in the first four
experiments by wavelet transformation. The most significant features were
selected using Kolmogorov-Smirnov (KS) test [165] [166] and then the data
were clustered using Superparamagnetic Clustering (SPC) [119]. It gave about
52% clustering accuracy on average. This accuracy was very low as very similar
82
spike shapes were used, which make differentiation difficult.
The same feature extraction algorithm was used in the second experiment
but Gap statistics (GS [167]) merged with K-means clustering algorithm was
used instead of SPC. The result of clustering became 66% on average as K-
means is more stable clustering algorithm. Gap statistics were replaced by Sil-
houette statistics (SH) [168] in experiment number three. Statistics were used
to estimate the number of clusters before applying any clustering algorithm,
so this converted K-means from a supervised to an unsupervised algorithm.
The clustering accuracy was 69% when Silhouette statistics were used. It gave
slightly better accuracy than Silhouette statistics as it could better identify the
number of clusters. Mean shift was used in clustering in experiment number
four. Mean shift gave 69% accuracy.
The same experiments were repeated using the same clustering algorithm
but with different feature extraction algorithm. Diffusion Map [169] was used
for feature extraction and it gave better clustering results compared to wavelet
transform as shown in Table 4.6. In experiment 5, 6, 7 and 8 the clustering
accuracy was improved and this means that using the Diffusion Map represents
the spike in a more meaningful way.
In the last experiment, MFCC was used as a feature extraction method.
The proposed algorithm gave better results in terms of clustering accuracy.
The bar chart shown in Figure 4.12 compares between all common techniques
in terms of clustering accuracy and shows the result using different noise levels.
It was found that using MFCC as a feature extraction method gave the best
results among all other feature extraction methods.
83
Tab
le4.
6C
lust
erin
gac
cura
cyco
mpa
rison
usin
gdi
ffere
ntno
isele
vels.
Fea
ture
Sel
ecti
onW
TW
TW
TW
TD
MD
MD
MD
MM
FC
C
Clu
ster
ing
Noi
seL
evel
No
ofsp
ikes
SP
CM
ean
GS
+S
H+
SP
CM
ean
shif
tG
S+
SH
+H
MM
Alg
orit
hm
shif
tK
-mea
ns
K-m
ean
sK
-mea
ns
K-m
ean
s
Exa
mp
le1
0.05
2729
42.1
479
.08
78.9
780
.249
.69
80.5
983
.09
84.1
995
.93
0.1
2753
44.1
184
.55
77.5
781
.451
.47
91.9
791
.02
92.2
493
.98
0.15
2693
40.3
385
.57
74.5
279
.290
.31
74.6
889
.98
87.8
93.0
7
0.2
2678
51.4
587
.69
71.8
181
.58
77.1
693
.74
95.5
492
.42
95.7
3
0.25
2586
56.6
682
.72
75.3
799
.96
58.2
173
.56
72.9
173
.12
95.8
0.3
2629
29.4
466
.87
83.6
166
.98
30.6
972
.17
71.6
274
.73
94.8
7
0.35
2702
8094
.565
.96
99.4
227
.17
66.1
475
.65
75.8
391
.2
0.4
2645
74.8
893
.51
69.8
197
.95
19.8
578
.11
87.8
89.3
890
.47
Exa
mp
le2
0.05
2619
5367
.32
74.9
967
.32
89.3
99.9
388
.53
88.0
393
.27
0.1
2694
75.4
267
.85
63.1
867
.85
63.6
794
.91
91.8
193
.34
92.8
7
0.15
2648
66.0
567
.49
58.1
367
.49
32.3
577
.11
90.9
191
.31
91.9
3
0.2
2715
43.2
66.1
551
.84
66.4
849
.85
63.3
882
.94
84.8
990
.79
Exa
mp
le3
0.05
2616
60.1
867
.277
.39
33.9
566
.52
82.0
792
92.4
592
.07
0.1
2638
49.1
62.3
642
.23
34.2
728
.23
86.6
188
.89
89.2
491
.67
0.15
2660
51.1
42.2
246
.97
34.2
928
.91
90.2
790
.28
90.4
591
0.2
2624
29.7
748
.63
48.6
434
.79
19.9
476
.96
78.5
981
.15
89.2
Exa
mp
le4
0.05
2535
38.4
666
.51
75.8
866
.51
74.4
998
.35
96.6
894
.23
94.3
0.1
2742
28.1
767
.65
73.1
967
.65
98.9
191
.91
91.8
791
.45
93.8
0.15
2631
54.0
867
.39
87.8
567
.39
85.1
110
098
.39
97.9
292
.93
0.2
2716
7467
.16
74.0
967
.17
48.2
699
.26
99.2
696
.63
90.8
7
Ave
rage
2663
5266
6869
5484
8788
92
84
Fig
ure
4.12
Clu
ster
ing
accu
racy
com
paris
onus
ing
diffe
rent
leve
lsof
noise
85
4.4 Conclusion
A robust feature extraction method and a robust classifier are needed to
extract and classify features of a noisy signal as noise will affect the accuracy
of any method. However, using a robust feature extraction method and clas-
sifier in conjunction with a noise estimation measure will help in identifying
the quality of the recorded signal as well as the quality of the methods used.
Hence, this chapter has introduced robust methods for extracting and classi-
fying signals and the noise estimation. Quality assessment methods will be
introduced in the next chapters.
In this chapter, the new feature extraction methods were explained. Fea-
ture extraction is very important step in Spike Sorting especially when dealing
with signals, which are convoluted with noise. Three different feature ex-
traction methods were used: Diffusion Maps, Cepstrum Coefficients and Mel-
Frequency Cepstral Coefficients. Based on the results shown in this chapter,
neural spikes were represented in a meaningful way, which helped in getting
better Spike Sorting accuracy compared to other common methods.
HMM were also used for Spike Sorting in this chapter. It was noticed
that neural spikes were represented precisely and concisely using HMM state
sequences. An HMM was built for neural spikes, where HMM states could
represent the neural spikes. The neural spikes can be represented by four
states; it could be ascending, descending, silence or peak. They imbue every
spike with an underlying probabilistic dependence that is modelled by HMM.
Based on this representation, spikes sorting became a classification problem
of compact HMM state sequences. In addition, the method was enhanced by
86
defining HMM on extracted Cepstrum features, which improves the accuracy of
Spike Sorting. Simulation results demonstrate the effectiveness of the proposed
method as well as the efficiency. Also in this chapter, Mel-frequency Cepstral
Coefficients (MFCC) were used to improve the classification results.
In the next chapter, the research is going to show how to estimate the
noise level in the neural signal. Estimating the noise level will be based on the
extracted features and the classification algorithms introduced in this chapter,
which will help ascertain the noise level in an accurate way.
Chapter 5
Noise Level Estimation
A robust feature extraction method and a robust classifier were introduced
in the previous chapter. However, considering the uncertainty produced by
noise and the subsequent decline in the quality of collected neural signal, this
chapter proposes a quality assessment method for neural signal. The method
makes an automated measure to estimate the noise levels in the neural signal.
Hidden Markov Models (HMM) were used to build a classification model that
classifies the neural spikes based on the noise level associated with the signal.
This neural quality assessment measure will help physicians and researchers
to focus on the patterns in the signal that have a high Signal-to-Noise ratio
(SNR) and carry more information.
5.1 Introduction
Noise is the main problem that occurs while recoding any kind of neural
signals. Noise is undesired signal which is implicated with the main recording
[147]. Noise affects the recording and it is difficult to use the data in the
presence of large amounts of noise [170]. It is arduous process to estimate the
SNR in a neural signal [171].
87
88
Noise can be divided into two categories. First, there is biological noise,
which is commonly produced by limbs, eyes or head activities. The second
category of noise is external noise, generated by technological factors [106].
Principally, the electrodes record the signal which is generated by a specific
number of neurons but the problem here is that one cannot control the number
of neurons, so unneeded spikes were recorded, which decreases the SNR [101].
It is not possible to record the neural signals without the biological noise but it
is a relatively easy to detect them and remove it after recording and analysing
the neural signal. The effect of technological interference can be minimised by
knowing the amount of SNR [106,155,171–173].
The most challenging aspect of removing any type of noise is to differentiate
between the noise and the signal, as removing the noise may leads to distortion
of the signal. One of the ways to remove the noise is using the Wavelet Trans-
form proposed in [172] and [119]. The main problem in this method is that it
largely depends on the assumption that the signal magnitudes dominate the
magnitudes of the noise in a Wavelet representation. The main objective in
this chapter is to give a more accurate measure for noise in a neural signal.
5.2 Noise Estimation Methodology
The main idea was to extract the most significant features of a pure signal
and the noise from a noisy signal, then each signal was classified to a group
based on the extracted features. The features were extracted using MFCC
which was explained in details in Chapter 4. First, a neural signal was recorded
and each spike was saved in a separate file. Then, the MFCC of the spikes was
89
Figure 5.1 MFCC calculation steps
calculated using the steps shown in Figure 5.1.
Each spike contained N samples which were stored in an array S(N). The
array was then split into distinct number of frames (i) and a small number of
samples overlapping between each frame. Then, the DFT of each frame Si(k)
was calculated using Equation (5.1).
Si(k) =N∑
n=1si(n)h(n)e−j 2π
Nkn, 1 < k < K (5.1)
where h(n) is an N sample long analysis window, and K is the length of the
DFT.
Then, the periodogram based power spectral of frame i(Pi(k)) was calcu-
lated using Equation (5.2).
Pi(k) = 1N
|Si(n)|2 (5.2)
The Mel-spaced filterbank, consisting of a group of 26 triangular filters, was
then applied. Then, the log magnitude of the output was taken giving 26 log
filterbank energies. Finally, DCT was taken for the output, which gave 26
90
cepstral coefficients. The least 12 cepstral coefficients were used as only the
most significant features are needed. These values are called Mel-Frequency
Cepstral Coefficients.
The next step was to build a classification model using HMM [157, 174].
HMM is a statistical tool to model sequences and describe the probability
distribution over a set of observations. HMM has been successfully used for
speech recognition. HMM consists of a set of states {S1, S2, ... Sn}.
The process moves from one state to another generating a sequence of
states: {Si1, Si2, ..., Sik, ...} and the Markov chain property of each subsequent
state depends only on what was the previous state and can be defined as:
P (Sik|Si1, Si2, ...Sik−1) = P (Sik|Sik−1). Also there are states which are not
visible, but each state randomly generates one of M observations (or visible
states) {V1, V2, ... Vn}.
HMM was utilized to model spikes in order to understand its underlying states
over a sequence of observations. For a spike, the significant shape states are
silence, ascending, peak and descending. Each of them was assigned to a state
(from s1 to s4) of the HMM. The main problem in other classification algo-
rithms is that they rely on shape and distance measurement such as comparing
height, width, and peak-to-peak amplitudes of spikes.
These HMM models were used to classify the testing data which is more
than 500 spikes per group. The HMM which was developed contains four
states for the spike. It iterated five times, frame size was 0.025, frame shift
was 0.01, forward backward direction and matrices were set to identity matrix.
In addition, the data, used in the experiments, was neural signals recorded from
91
three different neurons each with its unique shape, the same signal was used
but with different noise levels and the HMM model classification of the same
signal to one of different groups based on the noise level.
5.3 Noise Level Estimation Results
Three different experiments were conducted in this section, the first exper-
iment is based on comparing the estimation results of the proposed method to
a well known method. Then, two different devices were used in the second and
third experiments to prove that the proposed method can estimate the noise
level on different signals recorded by different devices. Multichannel systems
was used to record the neural signal data in the second experiment. While
in the third experiment, Neurofax EEG system was used to record the EEG
signal.
5.3.1 Matlab SNR function
First, the developed system was compared to one of the noise estimation’s
well-known functions; this function is created by the Mathworks team for use
in different domains, such as speech processing. When given time-domain in-
put, SNR performed a periodogram using a Kaiser window with large sidelobe
attenuation. To find the fundamental frequency, the algorithm searched the
periodogram for the largest nonzero spectral component. It then computed
the central moment of all adjacent bins that decreased monotonically away
from the maximum. To be detectable, the fundamental should be at least in
the second frequency bin. Higher harmonics are at integer multiples of the
fundamental frequency. If a harmonic fell within the monotonically decreasing
92
region in the neighbourhood of another, its power was considered to belong to
the larger harmonic, which may or may not be the fundamental.
The function estimated a noise level using the median power in the regions
containing only noise. The DC component was excluded from the calculation.
The noise at each point was the estimated level or the ordinate of the point,
whichever was smaller. The noise was then subtracted from the values of the
signal and the harmonics.
Figure 5.2 Noise Estimation Accuracy using different signals with differ-ent Signal to Noise Ratio (SNR).
A needed comparison was done between the proposed method and one
of the most common methods, which is developed by Mathworks team. Both
methods were applied to 500 different signals with different noise levels (SNR),
which are 0.1, 1, 10, 100, 1000, 10000. As shown in Figure 5.2, the proposed
method showed better accuracy in terms of noise estimation as the median
power fails if the fundamental is not the highest spectral component in the
signal which occurs in low SNR values.
93
5.3.2 Neural signal recorded by Multichannel systems
In this experiment, the effectiveness of using MFCC and HMM in estimat-
ing the amount of noise in the neural signal will be shown. A new device was
used, which can record a specific number of neurons using specific chips. This
device is called Multielectrode Array (Multichannel systems) [175]. A signal
was used with different SNR. HMM was trained using 20 spikes and 500 spikes
were used for testing. The neural signal, which was used in the experiments,
was the same, but with different noise levels, the original signal was considered
the cleanest signal as it was recorded very carefully and then the noise was
added based on the needed SNR using MATLAB. HMM was used to classify
the same signal to one of different groups based on the noise level.
HMM was built using 3 iterations, the more iterations used, the more com-
plex the system, and complexity affects the time for running the program.
On the other hand, the accuracy of the classification increases to a certain
limit when the number of iterations increases. Figure 5.3 explains the rela-
tionship between the number of iterations used in HMM and the accuracy of
classification. When only two iterations were used, the complexity was very
low.
The proposed model was able to differentiate between different noise levels
with accuracy of 95% and these noise levels (SNR) are 0.1, 1, 10, 100, 1000,
10000. Also the noise levels were meant to be very close to each other and our
model was able to differentiate between them to an accuracy of 89% and these
noise levels (SNR) are 0.5, 1, 5, 25, 125, 625.
Figure 5.4 shows the accuracy of classification of the spikes when the SNR
94
Figure 5.3 Relationship between the number of iterations used in HMMand the accuracy of classification
is 0.1, 1, 10, 100, 1000, 10000 using three different signals. The accuracy of
SNR estimation was about 95 % which will help later to estimate the amount
of information in the signal. Also in Figure 5.4 the level of SNR used in the
signals was very close to proving how accurate the proposed model is and the
results shows that accuracy of classification of the spikes when the SNR is 0.5,
1, 5, 25, 125, 625 is about 89%.
When the number of iterations was increased to 3 the accuracy was in-
creased by about 25 % to be 92.1%. When the number of iterations was
increased to 4 and 5, the accuracy increased to 95.6 % and 95.7% respec-
tively. Evidently, the number of iterations should not exceed 5 iterations as
the accuracy does not significantly change. Therefore, the HMM was built
using 3 iterations to reduce the complexity and increase the accuracy of the
classification method.
One major advantage in the proposed model is the low number of training
95
Figure 5.4 Classification Accuracy using different signals with differentSignal to Noise Ratio (SNR).
Figure 5.5 Relationship between the number of samples used in HMMand the accuracy of classification
96
Figure 5.6 Relationship between the number of states used in HMM andthe accuracy of classification
samples. This model uses only 20 spikes for training and tests the noise levels
for 500 spikes. This reduces the complexity of the model and makes it unnec-
essary to use more samples to train, as the model was built using a specific
number of iterations and states. Figure 5.5 shows the relationship between the
number of training samples and classification accuracy. Using only 5 samples
will give about 90% accuracy, a high value, particularly when considering the
low number of training samples.. The accuracy remains nearly the same as
shown when the number of training samples exceeds 20 samples, so the best
number of samples to use with respect to efficiency and accuracy is 20.
The number of states used in the HMM was four, which closely correlated
to the spikes. These states are: silence, ascending, peak and descending. And
if the number of states was changed as shown in Figure 5.6 the accuracy of the
classification will be changed markedly due to the fact that the spike shape
can be represented in 3 or 4 states maximum.
97
Figure 5.7 Classification Accuracy using different Signal to Noise Ratio(SNR) applied to EEG signal which is recorded by the 10-20 internationalsystem.
5.3.3 EEG signal recorded by Neurofax EEG system
The proposed model was applied to a recorded EEG signal with different
noise levels and it differentiated between these noise levels with accuracy of
91%. These noise levels (SNR) were 0.1, 1, 10, 100, 1000 and 10000. This
model was also able to differentiate between close noise levels with accuracy
83% and these noise levels (SNR) were 0.5, 1, 5, 25, 125 and 625 as shown in
Figure 5.7.
Figure 5.8 shows that the HMM models needed only three iterations to train
and test the data, these three iterations gave the best classification results.
Figure 5.9 confirms that 20 signals were enough to train the system and get
the highest possible classification accuracy. As mentioned before, the EEG
signal has only four states so the HMM used only four states giving the highest
98
Figure 5.8 Relationship between the number of iterations used in HMMfor the EEG signal and the accuracy of classification
accuracy, as shown in Figure 5.10.
Figure 5.9 Relationship between the number of EEG signals used byHMM for training and the accuracy of classification
The number of training samples was small. The proposed model only uses
20 signals for training and tests the noise level for 200 signal, which reduced
the complexity of the model.
An n error tolerance could also be used when SNR levels were very close to
each other, where the n adjacent clusters were considered as the same cluster
as they have a very close SNR values. For example, if the error tolerance
was two, this means that any two adjacent clusters were considered to be the
99
Figure 5.10 Relationship between the number of states used in HMM forthe EEG signal and the accuracy of classification
Figure 5.11 Relationship between the number of noise levels and theaccuracy of classification using two clusters error tolerance
same cluster. Figure 5.11 shows the relationship between the number of noise
levels and the classification accuracy. When the error tolerance is two, the
classification accuracy was more than 94% even if the signal have 20 noise
levels.
5.4 Conclusion
This chapter proposed an SNR quality assessment method for neural signal.
The method generates an automated measure to estimate the noise levels in
neural signal. HMM was used to build a classification model that classifies
100
the neural spikes based on the noise level. This model works better with the
controlled environment than the uncontrolled environment as the EEG data is
generated based on an enormous number of neurons. On the other hand, the
neural signal, which is recorded by the multichannel device, observed a limited
number of neurons.
This is considered to be the first quality assessment measure of neural
signal, which can be used as a flag beside other flags, discussed in the following
chapter to achieve a complete quality measure for neural signal.
Chapter 6
Automated Quality AssessmentScores
EEG signals allows people to understand how the brain works and BCI
is one of the most popular EEG applications. Capturing high quality EEG
signal is one of central challenges in BCI applications. The EEG signal noise
affects the quality of the captured neural signal, which will subsequently affect
the performance of the BCI applications. Although most of the BCI research
focuses on the effectiveness of the selected features and classifiers, the quality
of the input EEG signal is manually set. A noise estimation method was
introduced in the previous chapter, but in this chapter, a full automated quality
assessment method for the EEG signal is proposed.
The proposed method generates an automated quality measure for each
EEG frequency window based on the EEG signal bands characteristics as well
as their noise levels. In this research, twelve scores were developed to postulate
EEG signals. This EEG quality assessment measure gives researchers an early
indication of the signal’s quality. This is useful in applying new BCI algo-
rithms to test on only high quality signals. It also helps BCI applications to
automatically react to high quality signals and ignore lower quality ones. EEG
101
102
data acquisition experiments were conducted with different noise levels and the
results showed the consistency of the proposed algorithms in estimating the
accurate signal quality measure.
6.1 Introduction
Neurons communicate with each other using electrical spikes that carry
the information required for a specific activity. Electroencephalogram (EEG)
is the standard means by which to record neural signals that includes different
waves and spikes with varying amplitudes and frequencies [1, 157, 176–178].
These signals are recorded by placing a set number of electrodes on the human
scalp [179]. Billions of neurons communicate together with electrical pulses,
forming a huge complicated neural network [180,181].
There are many challenges in recording the EEG signal [182, 183]. Some
sources other than the brain produce unwanted electrical interference, which
is recorded with the cerebral activity and increases the noise in the recorded
EEG [184]. Sometimes the signal can be fully corrupted and needs to be
reacquired [185].
The noise affecting the quality of the EEG signals originates mainly from
the non-cerebral activities taking place at the time of recording. Non-cerebral
activities can be divided into two categories. The first category is the Physi-
ological activity, which is generated by organs in the human body, other than
the brain, such as muscles and limbs. The second category is external envi-
ronmental factors. Figure 6.1 shows the effect of an eye blink on the quality
of the acquired EEG signal.
103
Figure 6.1 Eye blinking/movement effect on the EEG signal.
Many feature extraction and classification techniques have been developed
in the past few years to improve the performance of the BCI applications
[186, 187]. However, the EEG data recording process has a significant impact
on the resulting performance of the BCI algorithms. The traditional method
is to observe the recorded signal and discard the highly corrupted parts that
are clearly contaminated with noise. However, there are some inherent noise
features within the signal that cannot be clearly observed. Having means of
measuring the quality of the recorded EEG signal will be of a great importance
to detect these features and highlight only the reliable parts of the signal
[188–190].
The main objective of this chapter is to generate an automated quality
assessment measure for an input EEG signal through generating automated
scores that evaluate the quality of the signal while recording. These scores
are based on biological and mathematical features where signal processing
techniques are needed. This idea has many benefits such as:
104
• Online Quality Assessment While the EEG signal is recorded using the
proposed system, an online alert is given when any channel has abnormal
behaviour. This will assist researchers to determine to stop recording to
resolve the noise-generating issues, or continue recording.
• Important factor in BCI applications The proposed scores can be used
as input to BCI applications. This will increase the accuracy of BCI
applications, as the brain commands will be handled with different levels
of confidence based on the quality of the signal.
During the EEG acquisition process, the electrodes sense the signals of a
specific number of neurons. Controlling the number of neurons captured is
challenging, so any unwanted number of spikes will decrease SNR [101, 106].
It is not feasible to record the neural signals without the biological noise, but
detecting and removing it is a relatively easy task [106, 155, 171, 173]. The
effect of the technical factors can be minimised by establishing the SNR. To
evaluate the accuracy, a normal signal was recorded carefully and then added
noise to it. The percentage of noise was controlled based on the SNR value as
the original clean signal is already recorded.
Although detecting the occurrence of biological noise is difficult, it is more
challenging to remove the noise when the level and type of noise is unknown
[191]. For example, eye blinking artifact detection is easy while recording the
EEG signal as most EEG recording software has an eye blinking detection
algorithms [131]. On the other hand, many factors affect - and sometimes
destroy - the viability of the recording, such as electromagnetic signals, high
power cables under buildings and mobile phone signals. These factors are more
105
Figure 6.2 EEG raw data is shown in the top figure, and then the mainfrequency bands are shown in the rest of the figures. The main EEGfrequency bands are Delta, Theta, Alpha and Beta as shown respectively.
difficult to isolate [192,193].
Clear differentiation between noise and signal is needed to avoid having
to minimise environmental noise and potentially compromising signal quality
when removing it. Wavelet transform [119, 172] can be used to remove the
noise. The major challenge with this method is the assumption that the signal’s
magnitude dominates the noise’s magnitude in any wavelet representation, and
this assumption may not hold for many neural signal recordings. The aim of
this chapter is not to minimise the noise in an EEG signal but to identify the
quality of the EEG signal.
Specific features in EEG signals can provide more information about the
quality of a signal’s recording. These features are the biometric features of the
signal bands, which are used in this chapter. Each EEG signal consists of a
range of signals within different frequency bands [178]. These bands are the
106
Alpha, Beta, Theta and Delta as shown in the Figure 6.2 [194]. These bands
are used to differentiate between quality scores that can be used to determine
whether or not the recorded EEG signal is reliable. This is the first automated
measure that assesses the EEG signal from a biological and statistical point of
view. The rest of the chapter is organised as follows: section 2 is the aim of this
chapter, followed by two sections for setting up the data. Each score is then
separated and independently analysed. This is followed by the conclusion.
The main idea for this chapter is to generate an automated quality assess-
ment measure for an input EEG signal. This model generates twelve scores,
which indicate the quality of the signal. The first score is calculated from the
general amplitude of the EEG channels. The second score is calculated based
on which channel have the highest amplitude. The third score is based on
calculating the dominant frequency for the channels. Followed by two scores
for analysing the Beta band and another one score for the assessment of the
Theta band amplitude. Then, another three scores are calculated, depending
upon the geometrical shape of the signals in each channel. Finally, the last
three scores are based on amplitude and frequency analysis. The following
sections describe the overall methodology of the research, with an emphasis on
how the twelve scores are used to assess EEG quality.
6.2 Recording EEG data
Prerecorded EEG signal database was used to test the effectiveness of the
proposed scores [195]. The EEG data were recorded using the Neurofax EEG
107
system and the electrodes were placed based on the International 10-20 sys-
tem, as shown in Figure 6.3. The participants sat on a reclining chair facing
a video screen, and they were asked to remain motionless during the perfor-
mance. Data were collected from three subjects with ten daily sessions for
each subject. Each session consisted of six runs. These 180 runs were used
in the experiments. The recording was done at 160Hz, while the AC lines in
the host country operate at 50 Hz. The data were exported with a common
reference using Eemagine EEG.
There were 12 scores that are produced by the proposed system to evaluate
the input EEG signal. Different noise levels were added to the EEG signal after
recording it to validate this system. Close noise levels were used in the first
experiment, which are 0.1, 0.5, 1 and 2. In the second experiment, noise levels
difference was increased to 0.1, 1, 5 and 10 and at the last experiment it was
increased to 0.1, 1, 10 and 100.
6.3 Splitting EEG data frequency bands
Figure 6.2 shows the frequency bands of the EEG signal. Delta waves,
which always appear during deep sleeping and have a frequency ranging from
0Hz till 4Hz. A sample of the Theta waves, which appears during normal sleep,
is shown in the second graph. Its frequency ranges between 4Hz and 8Hz. The
Third graph shows a sample of the Alpha wave, which usually appears when
the person is awake and resting, and its frequency ranges between 8Hz and
12Hz. The standard properties of the low gamma wave are not well known so
it is difficult to use them as a baseline. A sample of the Beta wave is shown
108
Figure 6.3 International 10-20 system is a way to describe the location ofscalp electrodes. These scalp electrodes are used to record the EEG signal.
in the last graph, and it appears when the person is awake doing a mental
activity and its frequency ranges between 12Hz and 40Hz.
The recorded EEG data were split to four different frequency bands, Delta,
Theta, Alpha and Beta. Butterworth filter was used successfully in splitting
the bands [196,197].
The Fourth Order Butterworth filter was used to split the EEG bands as
it is designed as an Nth order lowpass digital filter and it is commonly used to
split the bands, as described in Equation (6.1).
H(z) = b(1) + b(2)z−2 + ... + b(n + 1)z−n
1 + a(2)z−1 + ... + a(n + 1)z−n(6.1)
where n = 4 and H is the filter coefficient in length n + 1, row vectors a
and b are the transfer function coefficients of the filter, with coefficients in
descending powers of z. The main advantage of Butterworth filters is their
smooth, monotonically decreasing frequency response.
109
6.4 Score 1: Analysing the amplitude of eachchannel
Normal EEG waveforms, like many other waveforms, can be defined and
assessed using some properties, such as the amplitude measure. The EEG
is in essence a layout between voltage and time. The voltage of the EEG
determines the amplitude. The cortical EEG signal passes through the scalp,
which strongly affects the original signal strongly. EEG normal amplitudes
can range between -100 and 100 μV and they were measured from peak to
peak [198].
The EEG amplitude (voltage) was analysed for each channel. A histogram
of the count of each amplitude value was created. The histogram shape will be
perfect if the values are increasing to a maximum value and then decreasing
only once. There will be a problem in the quality of the data if this pattern
is inconsistent and appears more than once in the histogram. The larger the
number of peak changeover from increasing to decreasing amplitude scores in
the overall signal, the lower the quality of the signal.
As shown below, Algorithm 3 was developed to calculate Score 1. It
mainly counts the repetition of each amplitude value, and then it divides the
amplitudes into small bins, each bin carries a specific amplitude range between
-1000 and 1000μV and the width of each bin is 10μV. The reason for selecting
-1000 and 1000μV is that it is highly unlikely for EEG to fall outside of these
values under normal conditions. EEG signal distortion can be manifested by a
reduction in amplitude; a decrease of dominant frequencies beyond the normal
110
limit and production of spikes or special patterns. Epileptic conditions pro-
duce stimulation of the cortex and the appearance of high-voltage waves (up
to 1000 μV) [63]. High amplitude is a very important factor in assessing the
EEG signal. A histogram was plotted to show the amplitude’s count in each
bin. After which, a percentage was calculated based on the count of normal
bins between -100 and 100 μV, and the count of all other bins.
Algorithm 3 Calculating General Amplitude Scoreprocedure CheckGeneralamplitude
NormalValuesSum1 ← sum(bincounts(91:111))TotalSum1 ← sum(bincounts)s1 ← NormalValuesSum1/TotalSum1NormalValuesSum2 ← length(find(p(91:111) >0))TotalSum2 ← length(find(p >0))s2 ← NormalValuesSum2/TotalSum2Score 1 ← ((s1+s2)/2)*100
end procedure
The first experiment used a clean EEG signal with the addition of some
close noise levels (SNR = 0.1, 0.5, 1, 2). The same experiment was repeated
two more times but with different noise levels. Noise levels 0.1, 1, 5 and 10
were used for the second experiment and 0.1, 1, 10 and 100 were used in the
third experiment. The developed score system was able to generate a low score
for the high noise level and a high score for the low noise level as shown in
Figure 6.4.
Figure 6.5 shows the effect of noise on General Amplitude Score using
each individual channel. The incorrect amplitude is shown in red and the
correct amplitude is shown in blue. Kurtosis measure was used to support
this score. It is a measure of whether the data are peaked or flat relative to
111
(a) (b) (c)
Figure 6.4 Relation between General Amplitude Score and SNR. GeneralAmplitude score ranges between 0 and 100. The signal is noisier when thescore value decrease. Sub-figure a, b and c show the output of the GeneralAmplitude score but the difference between each sub-figure is the noiselevels being used. Sub-figure a shows the score when noise level 0.1, 0.5, 1and 2 were applied, then the noise level range was increased to be 0.1, 1, 5and 10 in sub-figure b and the score increased while increasing the SNR asshown. The noise level range was increased again to be 0.1, 1, 10 and 100in sub-figure c. As shown in all sub-figures, the General amplitude scoreis directly proportional to the SNR.
a normal distribution [199]. It was used to reveal the peakedness or flatness
of the bins distribution as shown in Figure 6.5. It showed that flatness of the
distribution increased when the noise increased. In the first experiment, the
Kurtosis values were 4.0849, 21.7938, 38.0479 and 55.8012 when the noise levels
were 0.1, 0.5, 1 and 2 respectively. Then the Kurtosis values were increased to
4.1021, 37.9853, 68.2545 and 70.7982 in the second experiment. Finally, the
Kurtosis values became 4.0910, 38.0452, 70.8802 and 71.8349, respectively in
the last experiment.
6.5 Score 2: Highest Amplitude Score
Alpha brainwaves always appear for an adults experiencing quietly flowing
thoughts, awake but relaxed (eyes closed) and in some meditative states. Alpha
is known as the brain’s resting state. Alpha waves have the highest amplitude
112
FP1 FP1 FP1 FP1 FP1
F3 F3 F3 F3 F3
C3 C3 C3 C3 C3
C4 C4 C4 C4 C4
Figure 6.5 The histogram of the amplitude of the EEG data was drawn.The normal EEG data ranges between -100 and 100μV which is shownin blue and the abnormal range was drawn in red. Each row shows thehistogram of a certain channel, and each column shows different noise level(the SNR increase while moving from left to right). As shown, the red barsdecreases gradually while moving from left to right as the noise decreasesand the amplitude returns to the normal range.
in the occipital and parietal regions of the cerebral cortex [200].
Alpha rhythm amplitudes change considerably from one individual to an-
other and can even change within the recording of the same person from time
to time. Sometimes, a referential ear montage can be used to determine the
alpha rhythm amplitude. In 1929, Berger found that the voltage of the alpha
rhythm ranges between 15μ and 20 μV [201], the small range explained by
113
instrument limitations. However in 1963, William Cobb found that the al-
pha amplitude ranges between 40μ and 50 μV. Until now, there has been no
specific range for the Alpha amplitude, which could be used as a score. How-
ever, electroencephalographers agree that values above 100μV are abnormal
and uncommon in clean EEG signal, which supports Score 1.
The maximum alpha voltage is always over the occipital region. Hence,
all the electrodes, which recorded the signal on the occipital region, should
have the highest amplitude such as O1 and O2 channels [198]. There were
two scores calculated through analyzing the Alpha band, the second score
will be discussed in the next section. The first score (Score 2) requires that
the highest amplitude should occur in O1, O2, P3, P4, T5, T6, C3, C4, A1,
A2, T3 and T4 channels, based on the biological description of a normal and
clean EEG [3, 63, 178, 202–204]. Therefore, the proposed system checks the
highest amplitude depending on Algorithm 4. In order to not be affected by
any outliers, the highest 1% of the amplitude values is considered the highest
amplitude in each window, which will resolve any outliers’ misguidance.
Alpha band characteristics of normal EEG are described in [202] beside the
Theta and Beta characteristics. It will be difficult for a person who experiences
seizure to control his or her body during the seizure, and so accordingly, the
proposed system considers epileptic or paroxysmal segments representative of
abnormality. The scores will warn the BCI application of abnormal behaviour.
For example, this system will show low scores if a person is using a BCI
application to control a wheelchair while having a seizure.
Different noise levels were applied as in the previous section. Figure 6.6
114
Algorithm 4 Calculating Highest Amplitude Score1: procedure CheckHighestamplitude2: Foreach Channel C in All Channels3: HighestAmplitudes(C) ← Get Maximum Values in each channel4: End Foreach5: Sort HighestAmplitudes6: Foreach Channel C in Channels O1,2 P3,4 T5,6 C3,4 A1,2 T3,47: index ← Find Index of C in HighestAmplitudes8: IF index > NumberOfElectrodes/29: score += 1
10: ELSIFindex > NumberOfElectrodes/411: score += 0.512: ENDIF13: End Foreach14: Score 2 = (score/10)*10015: end procedure
shows the accuracy of the score based on the noise level. The SNR is directly
proportional to the score. In the second series of experiments, the SNR was
increased to be 0.1, 1, 5 and 10 and then in the third series of experiments,
the SNR it was increased to be 0.1, 1, 10 and 100. The score increased with
the increasing SNR, as shown in Figure 6.6 which indicates that this score is
accurate.
(a) (b) (c)
Figure 6.6 Highest Amplitude Score and SNR values are directly pro-portional as shown in subfigures a, b and c. Subfigure (a) shows that thescore was less than 20% when SNR was 0.1. Then the score was around80% when SNR value became 10 as shown in subfigures b and c.
115
6.6 Score 3: Dominant Frequency Score
Through daily life, the brain’s activities range constantly through cogni-
tive, sensory, and motor activities, meaning that brain’s waves will also vary
constantly. However, the brain become slower while relaxing, meditating or
when participating in biofeedback; the amplitude increases and the signals
become more synchronised. In this case, the Alpha waves become the domi-
nant signal. The frequency of the Alpha waves is spread through both hemi-
spheres [205,206].
The second score within the alpha waves checks the dominant frequency
in each channel, as the dominant frequency should be similar in each hemi-
sphere in normal relaxing conditions. Figure 6.3 shows the left and the right
hemispheres in different colours and the correlation between adjacent chan-
nels in each hemisphere should provide a measure of the quality of the signal
recording. For example, the dominant frequency as calculated for FP1 channel
should be similar to the same channel in the other hemisphere, which is FP2.
This measure should be applied to all channels. The symmetry percentage is
calculated between both hemispheres and it ranges between 0, which means no
symmetry at all, and 100, which means they are identical. The score threshold
is based on the actions of the participant and the BCI application used for it.
For this reason the score has a threshold, which is set by the user. If there is
no action needed from the participant the score threshold will be high.
On the other hand, the threshold will drop if there is an action is performed
by the user, and this will lead to asymmetry. Therefore, this score is indicative
of a good quality signal, but not necessarily indicative of a bad signal. As an
116
example, the occipital lobe is one of the four major lobes of the cerebral cortex
in the human brain. The occipital lobe is the visual processing center of the
brain containing most of the anatomical regions of the visual cortex. Damage
to one side of the occipital lobe causes homonymous loss of vision with exactly
the same "field cut" in both eyes. Therefore, if the action is based on watching
visual images, there will be a common vision area between the two eyes, which
leads to having a similarity between the two signals reaching the occipital lobe.
This will lead to symmetry between the signals recorded for the occipital lobe
on both hemispheres; hence, the score threshold is expected to be high.
Algorithm 5 Calculating Dominant Frequency Scoreprocedure CheckDominantFrequency
2: Channels: FP1, FP2, F3, F4, C3, C4, P3, P4,O1, O2, F7, F8, T3, T4, T5, T6
4: Foreach Channel C in ChannelsdomFreqC ← CalculateDominantFrequency(C)
6: End Foreachleft ← [domFreqFP 1, domFreqF 3, domFreqC3, domFreqP 3,
8: domFreqO1, domFreqF 7, domFreqT 3, domFreqT 5]right ← [domFreqFP 2, domFreqF 4, domFreqC4, domFreqP 4,
10: domFreqO2, domFreqF 8, domFreqT 4, domFreqT 6]score3 = correlationbetweenleftandright
12: end procedureprocedure CheckDominantFrequency(signal)
14: fftLength ← length(signal)xdft ← fft(signal,fftLength)
16: FrequencySpectrum ← 200freq ← [0:fftLength-1].*(FrequencySpectrum/fftLength)
18: freqsCareAbout ← freq(freq <Fs/2)xdftYouCareAbout ← abs(xdft(1:round(fftLength/2)))
20: [maxVal, index] ← max(xdftYouCareAbout)maxFreq ← freqsCareAbout(index)
22: end procedure
117
The algorithm for calculating the Alpha Band’s second score is shown be-
low, as Algorithm 5. The Fast Fourier transform is calculated for the signal,
then the total frequency axis is calculated so the frequencies can be selected
which are pertinent (either the positive or negative frequencies), since they are
redundant for a real signal. The dominant frequency will be the unnormalised
maximum amplitude of the frequency rage after taking into consideration the
absolute magnitude.
The same noise levels were introduced, as with previous experiments. The
results indicated an increasing score as the SNR increased. The Dominant
Frequency score was of such a low percentage accuracy because the SNR was
very low, but it lifted in the subsequent experiments as the SNR was increased
to 0.1, 1, 5 and 10 for the second experiment and to 0.1, 1, 10 and 100 in the
third one. Figures 6.7a, 6.7b and 6.7c show that the score is affected signifi-
cantly by the noise level and this indicates that the score is very meaningful.
(a) (b) (c)
Figure 6.7 This Figure shows the relationship between Dominant Fre-quency Score and SNR. Subfigure a shows the score values when the SNRwas very low, the score values were low as well which indicates that thescore and the SNR values are directly proportional. Then SNR valueswere increased which led to an increase in the score values as shown insubfigures b and c.
118
6.7 Score 4: Beta Amplitude Score
Beta brainwaves manage the ordinary waking consciousness state during
which the brain undertakes cognitive tasks and monitors a person’s environ-
ment [207]. Beta represents a fast activity, when the person is in an alert and
attentive mode. Also it appears while making decisions and solving problems.
There are two scores to indicate the accuracy of the Beta wave. The first
score (Score 4) is calculated based on the amplitude of the Beta wave of each
channel. The amplitude should not exceed 20 μV in any of the channels [202].
This score checks all the values, which exceed the known maximum amplitude.
This step is calculated for each window frame and the score will not be affected
if one, two or three outliers were obtained but it will be affected if tens or
hundreds of outliers were obtained as the normal clean signal should not have
this many outliers. Score 4 is calculated based on the percentage of samples
exceeding the maximum amplitude. The algorithm for calculating score 4 is
shown below in the Flowcharts 6.8.a and 6.8.b and its pseudocode is shown
in Algorithm 6.
Algorithm 6 Calculating Beta Amplitude Score1: procedure CheckBetaamplitude2: Betawaves: BetaFP1, BetaFP2, BetaF3, BetaF4, BetaC3, BetaC4,3: BetaP3, BetaP4, BetaO1, BetaO2, BetaF7, BetaF8, BetaT3,4: BetaT4, BetaT5, BetaT6, BetaFZ, BetaCZ,BetaPZ5: Foreach Betawave B in Betawaves6: i ← find(absolute(B) < maxamp)7: n ← length(i)8: scores(B) ← n/length(B)9: End Foreach
10: score4 ← Average(scores)11: end procedure
119
(a) (b)
Figure 6.8 Figure (a) shows the steps of calculating the overall BetaAmplitude score while Figure (b) shows the steps of calculating the BetaAmplitude score for a channel.
This score depends mainly on the Beta band. It is calculated from the
amplitude of the Beta wave of each channel. It checks the amplitude which
should not exceed 20 μV in all the channels. The more samples exceeding
the maximum amplitude, the more noise is included in the signal. The Beta
Amplitude Score is the percentage of the samples exceeding the maximum
amplitude over the total number of samples in the signal window.
Figure 6.9 shows how the quality of the signal affects Beta Amplitude Score,
the score is low if the noise in the signal is high.
120
(a) (b) (c)
Figure 6.9 Relation between Beta Amplitude Score and SNR. Beta Am-plitude Score ranges between 0 and 100. This score will have a large valueif the entered EEG data is clean, otherwise it will give a small value. BetaAmplitude Score output is shown in sub-figures a, b and c. Sub-figure ashows the score when noise level 0.1, 0.5, 1 and 2 were applied,then thenoise level range was increased to be 0.1, 1, 5 and 10 in sub-figure b andthe score increased while increasing the SNR as shown. The noise levelrange was increased again to be 0.1, 1, 10 and 100 in sub-figure c. Asshown in all sub-figures, the score was very low when the SNR is low andbegan increasing while increasing SNR, which shows that the score andthe SNR are directly, proportional.
6.8 Score 5: Beta Sinusoidal Score
Sinusoidal waves are common in nature, they can be observed in many
different signals. In 1830, Joseph Fourier proved that any complex wave could
be analysed into set of sine waves. Brain patterns form wave shapes that are
commonly sinusoidal. EEG signal consists of a mixture of rhythmic waves;
therefore, EEG can be transformed into different set of continuous rhythmic
sinusoidal EEG waves, which are called bands. Four major bands have been
identified which are alpha, beta, delta and theta band. Beta waves are the
most likely to be encountered in research as it is considered the most common
band, it consists of a small number of sine components in case of there is no
external noise [208–210].
The second score (Score 5), which is generated from the beta wave analysis,
121
confirms the presence or absence of a sinusoidal-like wave. The closer the
beta waves to a sinusoidal pattern, the higher the quality it represents. The
signal is divided into windows, in which each window has a specific number
of samples. The signal has to be transformed from the time domain to the
frequency domain, based on the Discrete Cosine Transform (DCT). DCT is
used to represent the amount of energy stored in the signal. Then the number
of DCT components, which are needed to represent 99% of the energy in the
same signal, were counted. Next, the signal was reconstruct using the extracted
components and check the correlation between the generated signal and the
original signal.
The equation below, Equation (6.2), is utilised to compute the DCT, where
N is the number of samples in each window. This is represented as:
y(k) = w(k)N∑
n=1x(n)cos( π
2N(2n − 1)(k − 1)) k = 1, 2, 3.., N
where :
w(k) =
⎧⎪⎨⎪⎩
1√N
, if k = 1√2N
, 2 ≤ k ≤ N
(6.2)
Then the DCT components are sorted in a descending order. The original
signal is reconstructed using the least number of DCT components based on
flowchart shown below in Figure 4.6. The inverse DCT is used to return the
signal back to the time domain. The equation below, Equation (6.3), details
the formulation of the Inverse Discrete Cosine Transform where y is the DCT
122
Figure 6.10 Steps for calculating the Sinusoidal Score.
of the signal x.
x(n) =N∑
k=1w(k)y(k)cos(π(2n − 1)(k − 1)
2N) n = 1, 2, 3.., N
where :
w(k) =
⎧⎪⎨⎪⎩
1√N
, if k = 1√2N
, 2 ≤ k ≤ N
(6.3)
Figure 6.10 shows the steps for calculating the Sinusoidal Score. The algo-
rithm pseudocode is shown in Algorithm 7.
123
Algorithm 7 Calculating Sinusoidal Score1: procedure CheckSinusoidal2: Betawaves: BetaFP1, BetaFP2, BetaF3, BetaF4, BetaC3, BetaC4,3: BetaP3, BetaP4, BetaO1, BetaO2, BetaF7, BetaF8, BetaT3,4: BetaT4, BetaT5, BetaT6, BetaFZ, BetaCZ,BetaPZ5: Foreach Betawave B in Betawaves6: dct(B) ← dctcomparison(B)7: score5 = Average(dct)8: end procedure9: procedure dctcomparison(signal)
10: Signaldct ← CalculateDCT (signal)11: AbsSignaldct ← CalculateAbsoluteV alue(Signaldct)12: [SortAbsSdct, indices] ← sort(AbsSignaldct,′ descend′)13: i ← 114: while norm(SortAbsSdct(indices(1 : i)))/norm(Signaldct) < 0.99 do15: i ← i + 116: end while17: Sinusoidalpercentage ← i/totalcount18: end procedure
A signal is nearly sinusoidal if the same signal was managed to be generated
with a small number of DCT components and possessing a high correlation
to the original signal. The relation between the norm vector of the selected
DCT components and the norm vector of the whole DCT components should
be more than 99 % as reaching 100% will need a huge number of components.
Figure 6.11 represents score five which shows the inverse of the number of
DCT components used to generate the same signal. As shown, the number of
components decreases (the inverse increases) when SNR was increased.
6.9 Score 6: Theta Amplitude Score
Theta brainwaves always appear in the brain of a person sleeping or in
deep meditation. It is the learning and memory entrance [211]. Theta waves
indicate dreaming, imagining and anything occurs behind the normal conscious
124
(a) (b) (c)
Figure 6.11 Relation between Beta Sinusoidal Score and SNR. Beta Si-nusoidal Score is mainly based on calculating the percentage between twonorm vectors. The signal will not be in a sinusoidal shape when it is mixedwith noise, which means that it needs a lot of DCT components to generatethe original signal. Subfigures a, b and c shows the relationship betweenBeta Sinusoidal Score and SNR. Different noise levels were applied and thescore increased when the noise decreased.
awareness. Theta band ranges between 4Hz to 7 Hz and its amplitude should
not exceed 30μV [202].
A score is calculated from the amplitude of the Theta wave of each channel.
The amplitude should not exceed 30 μV in all the channels. This score is
calculated from the percentage of samples exceeding the maximum amplitude.
The algorithm used is the same as utilised when analysing the Beta wave,
using the details in Algorithm 6. More sample points extending the maximum
amplitude in noisy signals compared to the normal signal. Theta Amplitude
Score is the percentage value of the samples exceeding the maximum amplitude
over the total number of samples in the signal window.
The quality of the signal affects Theta Amplitude Score as shown in Fig-
ure 6.12, the score is low if the noise in the signal is high.
125
(a) (b) (c)
Figure 6.12 Relation between Beta Amplitude Score and SNR. Beta Am-plitude Score ranges between 0 and 100. This score will have a large valueif the entered EEG data is clean, otherwise it will give a small value. BetaAmplitude Score output is shown in sub-figures a, b and c. Sub-figure ashows the score when noise level 0.1, 0.5, 1 and 2 were applied,then thenoise level range was increased to be 0.1, 1, 5 and 10 in sub-figure b andthe score increased while increasing the SNR as shown. The noise levelrange was increased again to be 0.1, 1, 10 and 100 in sub-figure c. Asshown in all sub-figures, the score was very low when the SNR is low andbegan increasing while increasing SNR, which shows that the score andthe SNR are directly, proportional.
6.10 Score 7: Symmetry Analysis Score
Symmetry between homologous electrode pairs is considered a basic prin-
ciple of normal EEG activity, this symmetry is found during both waking and
sleeping states. The symmetry should be in amplitude and frequency of two
homologous derivations, however, exact symmetry is not expected. [212].
The occipital lobe is one of the four major lobes of the cerebral cortex in
the human brain. It forms the brain’s visual processing center and contains
most of the anatomical region of the visual cortex [213]. The occipital lobes
are involved in several body functions including visual perception and colour
recognition. Damage to one side of the occipital lobe causes homonymous loss
of vision with exactly the same "field cut" in both eyes. They are not partic-
ularly vulnerable to injury because of their location at the back of the brain,
126
although any significant trauma to the brain could can produce subtle changes
to the visual-perceptual system, such as visual field defects and scotomas.
This score is based on the symmetry between the left and the right occipital
lobes. The symmetry is based on the spikes amplitude and timing. The first
step is detecting the spikes in the EEG signal using the local maxima method,
then each spike is compared with any spike appears at the same time frame
but in the other side. The comparison is based on the amplitude of the spike.
Symmetry should be at least 50% between both sides [214].
As shown below, Algorithm 8 was developed to calculate Score 7. Mainly,
it checks the symmetry between the occipital lobes. The occipital lobes in
the EEG channels are known as O1 and O2. First, the channel reference
is generated based on the average of four different channels. Then the DC
component is adjusted in both channels O1 and O2 by normalisation. The
spikes are extracted based on the local peaks, defined as a data sample which
is either larger than the two neighbouring samples or is equal to infinity. Each
spike in one hemisphere is compared with the same spike occurs at the same
period in the other hemisphere (O1 and O2). The symmetry of the spikes
occurs on the both hemisphere represents the score.
Three experiments were undertaken using different noise levels as men-
tioned in the beginning of section 6.3. The score system developed was able
to generate low scores for high noise levels and high scores for low noise levels,
as shown in Figure 6.13.
127
Algorithm 8 Calculating Occipital Symmetry Scoreprocedure CheckOccipitalSymmetry
car ← average(T3,T4,T5,T6)O1 CAR ← O1 - carO2 CAR ← O2 - carO1 CAR ← normalize(O1 CAR)O2 CAR ← normalize(O2 CAR)O1 spikes,O1 times ← findpeaks(O1 CAR)O2 spikes,O2 times ← findpeaks(O2 CAR)Score 7 ← checksimilarity(O1 spikes,O1 times,O2 spikes,O2 times)
end procedure
6.11 Score 8: Morphology Score
This score is based on the morphology of the signals in the left and right
hemisphere. In a resting state, the morphology of the spikes on both hemi-
spheres should be similar, otherwise there is likely a problem in the recording
signal [104, 215]. The channels, which are used, are FP1-F3, F3-C3, C3-P3,
P3-O1, FP1-F7, F7-T3, T3-T5, T5-O1 and their corresponding electrodes in
the opposite hemisphere are FP2-F4, F4-C4, C4-P4, P4-O2, FP2-F8, F8-T4,
T4-T6 and T6-O2. The spikes’ morphology at FP1-F3 channel is compared
with FP2-F4 channel and so on.
The morphology similarity is calculated based on Algorithm 9. First of
all, not all spikes have the same number of samples therefore all the spikes
are resampled in order to have the same number of samples. This will help in
calculating the correlation between the spikes shape.
Score 8 depends mainly on the morphology of the signal in each channel,
as the morphology of corresponding channels in each hemisphere should be
similar. The signals of each corresponding electrodes are recorded for each
channel, and then the correlation of corresponding channels in each hemisphere
128
(a) (b) (c)
Figure 6.13 Relation between Symmetry Analysis Score and SNR. Sym-metry Analysis Score ranges between 0 and 100. The signal is noisierwhen the score value decrease. Subfigures a, b and c show the output ofthe Symmetry Analysis score but the difference between each sub-figureis the noise levels being used. Subfigure a shows the scores after applyingnoise levels 0.1, 0.5, 1 and 2 were applied, then the noise level range wasincreased to be 0.1, 1, 5 and 10 in subfigure b and the score increased whileincreasing the SNR as shown. The noise level range was increased againto be 0.1, 1, 10 and 100 in subfigure c. As shown in all subfigures, thesymmetry analysis score is directly proportional to the SNR.
is calculated.
Different noise levels were applied in three experiments as mentioned in
section 6.3. The morphology score has a low percentage accuracy because the
SNR was very low, but it increased in subsequent experiments as the SNR
was raised to 0.1, 1, 5 and 10 for the second experiment and to 0.1, 1, 10
and 100 in the third one. Figures 6.14a, 6.14b and 6.14c shows that the
score was significantly affected by noise levels indicating that the score is very
meaningful.
6.12 Score 9: Eye movement Analysis Score
The appearance of eye movements potentials appearance in the EEG sig-
nal is a well-known phenomenon, which is relatively easy to recognise by the
experienced electroencephalographer. Essentially, the eye plays the role of an
129
Algorithm 9 Calculating Morphology Similarity Score between channel Aand B
1: procedure CheckMorphologySimilarity2: MaxRow = min(size(A,1),size(B,1))3: MaxCol = max(size(A,2),size(B,2))4: NewA = resample(A,MaxRow,size(A,1))5: NewB = resample(B,MaxRow,size(B,1))6: NewA = resample(NewA’,MaxCol,size(A,2))’7: NewB = resample(NewB’,MaxCol,size(B,2))’8: for s = 1 : MaxRow do9: a = NewA(s,:)
10: b = NewB(s,:)11: c(s)=real(corr(a’,b’))12: end for13: Score 8 = average(c)14: end procedure
electric dipole, the cornea becoming positive compared to the retina. During
eye movement, the potential near to the eye is changed by the corneo-retinal.
These potentials are sent through the whole head, and affect the EEG sig-
nals [216].
Eye movement potentials are considered to be a problem that faces both
clinical and experimental EEG recording techniques. The magnitude of the
eye movements signals can be larger than the magnitude of the EEG signals,
which is why they represent one of the main sources of artifacts in EEG data.
Some methods were used to remove eye movement signals from EEG data,
however, the target was not to remove any artifacts but to assess the quality
of the EEG data [217].
Sometimes, eyes move normally while recording the EEG signal, in which
case the EEG data will need to be discarded. It will be deemed abnormal if
eyes movement dominates the whole recording [218]. This score checks the
130
(a) (b) (c)
Figure 6.14 Relation between Morphology Score and SNR is shown insubfigures a, b and c. Different noise levels where applied, the score wasvery low when the SNR is low and began increasing while increasing SNRwhich shows that the score and the SNR are directly proportional.
Figure 6.15 The effect of eye movement on F7 and F8 EEG channels.
percentage of eye movement in the recorded EEG data. Eyes movement can
be easily detected by checking the amplitudes of F7 and F8 channels as shown
in Figure 6.15 [131, 219]. The spikes at both channels should have the same
amplitude polarity. When eyes move, the polarity of F7 and F8 channels
should be opposite to each other. Algorithm 10 shows the steps of calculating
the eyes movement score.
Figure 6.16 shows the effect of the signal’s quality on the Eye Movement
Score. The score was low when the signal contained eyes movement windows,
otherwise, the score was relatively high.
131
Algorithm 10 Calculating Eye Movement Analysis Scoreprocedure EyeMovCalculation
2: [xv,xt] = findpeaks(x)[yv, yt] = findpeaks(-y)
4: for i = 1 : length(xv) docurTime = abs(yt - xt(i))
6: v = min(curTime)IF v < 3
8: opSpikes = opSpikes + 1ENDIF
10: end forres1 = 1 - (opSpikes /length(xv))
12: opSpikes = 0[xv,xt] = findpeaks(y)
14: [yv, yt] = findpeaks(-x)for i = 1 : length(xv) do
16: curTime = abs(yt - xt(i))v = min(curTime)
18: IF v < 3opSpikes = opSpikes + 1
20: ENDIFend for
22: res2 = 1 - (opSpikes /length(xv))score = (res1+res2)/2
24: end procedure
6.13 Amplitude and Frequency Analysis Scores(10, 11, 12)
EEG signals have specific features in relation to their amplitudes and fre-
quencies. One of the characteristics of the amplitude is variation via a wide
range, this range begins from a few micro-volts and extends to hundreds of
micro-volts. In general, normal adults EEG signals are less than 100μV. Am-
plitude can reach 200μV in normal children. On the other hand, abnormal
activities and noise can change increase the amplitude to reach 1000μV such
132
(a) (b)
Figure 6.16 Relationship between Eye Movement Analysis score and theinput signals. Figure a shows the score output when a normal signal wasused as an input, it shows high score which means that the signal is clean.On the other hand, Figure b shows low score when a signal full of eyesmovement was used as an input. The score and the percentage of eyemovements in the signal are directly proportional.
as Hypsarrhythmia, where extremely high amplitude is one of it’s main char-
acteristics [63].
Frequency is also a very important factor in assessing the quality of EEG
signal. Frequency of EEG activity is classified into four main waves, which are
delta , theta, alpha and beta waves. If the same frequency appears repeat-
edly, counting the number of waves occurring within 1 second can measure
(estimate) the frequency of the EEG signal. Otherwise, the frequency must be
estimated by measuring the duration [220].
Constant, continuously increasing or decreasing amplitudes or frequencies,
for a long time period or regularly happening, always occur due to technical
and noise problems. Such technical problems affect the quality of the recorded
signal. There are ways in which these problems can occur, such as erroneously
short inter-electrode distance, excessive electrode paste, leading to shorting of
electrodes, or mistakenly recorded sensitivity or filter setting parameters [212].
Three scores will be introduced to assess the quality of the EEG signal. EEG
signal will be assessed based on the amplitude and the frequency characteristics
133
mentioned above.
Score 10 is based on the Amplitude and Frequency of the EEG signal,
the signal’s amplitude and the frequency in each electrode are very important
quality factors. The normal EEG signal should have different amplitude and
frequency over time [221] which means that there will be a significant problem
in the signal if its amplitude and frequency is continuously increasing over time
in C3-CZ, CZ-C4 and C4-T4 channels [87], as shown in Figure 6.17.
Figure 6.17 Increasing in amplitude and frequency over time at C3-CZ,CZ-C4 and C4-T4 channels.
Algorithm 11 checks if the amplitude and frequency of the signal are
increasing over time or not. It returns a zero-one score, which means that it
returns one if both amplitude and frequency are increasing overtime, and are
otherwise zero. This score is calculated for each window and the average score
is calculated and converted to percentage at the end.
On the other hand, the amplitude of normal spikes should not be increasing
over time and neither should their frequency be decreasing over time [221]. In
abnormal cases, the amplitude of the signal in any channel increases and the
frequency decreases over time [87]. Hence, this score checks the amplitude and
frequency of each window and returns one if the amplitude is increasing and
frequency is decreasing over time, It otherwise returns zero. Algorithm 12
shows how Score 11 is calculated for each channel window, and the total score
is the average score of all channels.
134
Algorithm 11 Calculating Increasing Amplitude and Frequency Scoreprocedure CheckIncreasingAmpFreq
2: for i = 1:length(signal)-51 dowindow = signal(i:i+50)
4: maxamp(i) =max(window)[maxValue,indexMax] = max(abs(fft(window-mean(window))))
6: maxfreq(i) = indexMax * 500 / length(window)end for
8: n = 5maxamp(1+find(diff(maxamp)==0)) = []
10: AmpSorted = any(conv(double(diff(maxamp) >0), ones(1,n), ’valid’)==n)maxfreq(1+find(diff(maxfreq)==0)) = []
12: maxfreq = real(maxfreq)IF length(maxfreq) > 1
14: FreqSorted = any(conv(double(diff(maxfreq) >0), ones(1,n), ’valid’)==n)ELSE
16: FreqSorted =0ENDIF
18: return AmpSorted && FreqSortedend procedure
Indications of constant frequency or amplitude contradicts with the main
characteristics of the EEG signal. This only occurs if there is an error in the
recording such as a loose electrode, which will lead to a constant frequency.
Score 12 is calculated using Algorithm 13, which detects whether or not the
amplitude or the frequency is constant.
In the dataset used, five windows had increasing amplitude and frequency,
four windows had increasing amplitude, but decreasing frequency and there
were no windows indicating constant amplitudes or frequencies. Score 10 gave
91% as a quality measure which indicates that there is a small number of
windows with increasing amplitude and frequency. On the other hand, Score
11 gave 94% as a quality measure, this shows that the signal has some windows
with increasing amplitude and decreasing frequency. Finally, Score 12 gave
135
Algorithm 12 Calculating Increasing Amplitude and Decreasing FrequencyScore
procedure CheckIncAmpDecFreq2: for i = 1:length(signal)-51 do
window = signal(i:i+50)4: maxamp(i) =max(window)
[maxValue,indexMax] = max(abs(fft(window-mean(window))))6: maxfreq(i) = indexMax * 500 / length(window)
end for8: n = 5
maxamp(1+find(diff(maxamp)==0)) = []10: AmpSorted = any(conv(double(diff(maxamp) >0), ones(1,n), ’valid’)==n)
fliplr(maxfreq)12: maxfreq(1+find(diff(maxfreq)==0)) = []
maxfreq = real(maxfreq)14: IF length(maxfreq) > 1
FreqSorted = any(conv(double(diff(maxfreq)<0), ones(1,n), ’valid’)==n)16: ELSE
FreqSorted =018: ENDIF
return AmpSorted && FreqSorted20: end procedure
100% as this dataset does not have any windows in the signal, with constant
amplitude or frequency.
6.14 General Summary Score (GSS)
The proposed quality assessment scores were introduced in the previous
sections. These scores were arranged into different groups in order to combine
Algorithm 13 Checking Constant Amplitude and Frequencyprocedure CheckConstantAmpFreq
2: [xv,xt] = findpeaks(x)value diff = length(diff(xv) >10) >0
4: time diff = length(diff(xt) >2) >0res = value diff OR time diff
6: end procedure
136
them into one score. The General Summary Score shows a general quality
percentage of the input signal and examining each individual score will pro-
vide more detailed information about the quality of the signal. Each score
will contribute with a specific percentage based on how often does it happen.
Some scores were based on the amplitude of the signal and they were grouped
together into “A” group. Other scores depended on the frequency of the signal
and the letter “F” was assigned to them. Some scores were grouped into oth-
ers, where they were calculated based on different inputs. One the other hand,
it was recognised that some scores would show repeatedly low scores when the
task required movement during the recording of the data. These were given
the letter “R”. Scores 1, 2, 4 and 6 depended mainly on the signal’s amplitude,
Figure 6.18 The percentage of each score group in the General SummaryScore.
hence, they were grouped under group “A”. Score 3 was calculated based on
the frequency of the signal as is marked as “F”. The others “O” group included
scores 5. However, there were scores that were marked as “O & R” at the same
137
time, such as Score 7 and 8, because they would show repeatedly low scores if
there was movement involved in the recording. Score 9 was marked as “A &
R” as it was affected by movement and was based on amplitude at the same
time. The last three scores (Score 10, 11 and 12) were marked as “A & F” as
they depended on amplitude and frequency.
Table 6.1 Percentage of each score in the General Summary Score.Score Percentage (%)
1 102 103 104 105 56 107 58 59 510 1011 1012 10
Any score that was marked as “A” only represented a 10% of the general
summary score. Moreover, any score that was marked as “F” only or “A & F”
represented 10% of the total score. Any other score represented only 5% if it
was marked as “O”, “O & R” or “A & R”, as some of these scores were affected
by movements and were preferred to be calculated when the participant was
in this motionless resting state. Table 6.1 shows the percentage of each score
in the general summary score. Four “A”, one “F”, one “O”, two “O & R”, one
“A & R” and three “ A & F” scores represent 40%, 10%, 5%, 10%, 5% and
30% of the General Summary Score respectively as shown in Figure 6.18. If
any score showed a zero value, this means that the whole general score will be
138
reduced by 50%. In this case, each score is checked individually to know what
is the problem that cause this very low score value.
6.15 Conclusion
This chapter proposed quality assessment methods for EEG signal. These
methods generate an automated measure to detect the quality of the signal
based on its biological and statistical properties. Twelve scores were introduced
and each score was based on a specific property in the EEG signal. This is
considered to be the first quality assessment measure for EEG signals.
This research has many advantages. The whole process is undertaken on-
line, which means an online quality assessment framework was developed. In
case of data abnormality, an online alert will appear as an indicator of data
corruption. Furthermore, this measure can be considered a very important in-
put for BCI applications because it will help in identifying the degree of data
reliability. The next chapter will show that this measure can be used as an
additional input for BCI applications; this will increase the accuracy of BCI
applications.
Chapter 7
Quality Assessment Scores andBCI
7.1 Introduction
The main difficulty with BCI applications is that the signal processing is
always person and task specific. Non-stationary brain dynamics lead to a dif-
ferent brain function map for each person. This makes it harder to deploy
the BCI applications for general use. SNR plays an important role in the BCI
application’s accuracy, as sometimes the noise is substantial compared to the
brain activity. This is the reason for developing the proposed quality assess-
ment scores in the previous chapter and to merge them with BCI applications
in this chapter.
The goal of BCI technology, as defined by the Wadsworth Center is “to give
severely paralysed people another way to communicate, a way that does not
depend on muscle control” [222]. BCI is a system that takes a human neural
signal, such as the EEG signal, as an input as shown in Figure 7.1. It can
then predict an abstract aspect of the person’s cognitive state. Three different
cognitive states are measured: the Tonic state, which indicates the degree of
139
140
Figure 7.1 BCI input output interface.
relaxation and cognitive load; the Phasic state, which indicates movement and
switching attention, and the Event-related state, which indicates event firing
or external factors. Most successful BCI applications run online, in real time
and depend on a single-trial basis.
BCI applications are not restricted to using brain activity as the only source
of information. Instead, BCI applications use context parameters for improv-
ing the predictions accuracy. Context parameters have a great potential for
real world applications, which are different to controlled laboratory condi-
tions. One of their main functions is to help factoring out variations in brain
activity. These parameters are the application, environmental and user state.
Brain signal plays a major role in BCI, to transfer information from the user
to the application. These measures would be added as an extra parameter to
determine the data state.
There are three types of BCIs :
Active BCI: Outputs are extracted from the brain activity of the user. The
user controls it in a direct and deliberate way, and it does not depend
on any external events to control an application.
Reactive BCI: Acquires outputs from brain activity, mainly depending on
141
external stimulation, which indirectly affects the user’s brain in order to
control an application.
Passive BCI: Derives its outputs from arbitrary brain activity without vol-
untary control, for enriching a human computer interaction with implicit
information.
Active and reactive BCIs are considered “classical” BCIs, and introduced
in Chapter 3 as direct and indirect control. These subtypes cover all BCIs
spaces, from independent conscious control to rendering external events and
reaching the passive BCIs, which are complementary. These categories have
a smooth boundary, as the conscious control and rendering of external events
are not binary properties of brain activity. Any category requires a complex
signal processing and user calibration.
7.2 BCI Input, Importance and Applications
Brain signals are the main inputs of BCI applications. These can be derived
through non-invasive means, such as Electroencephalogram (EEG), explained
in details in Chapter 3, or Functional Near-Infrared Spectroscopy (fNIRS).
Alternatively, the input signal can be derived through invasive means using
different methods, such as Microarrays, Neurochips or ECoG. There are some
other inputs which can be used beside the brain signals such as motion capture
and eye-tracking techniques. Some other body signals can be used as an addi-
tional input for BCI, such as Electromyography (EMG), Electrocardiography
(ECG) and Electrooculography (EOG).
BCI is mainly used for severely disabled or injured people, such as those
142
with Tetraplegia or Locked-in syndrome. It can enhance communication and
bodily control. P300 Speller and Hex-o-Spell are example BCI Speller Pro-
grams, which helps disabled people to to spell words and even speak. More-
over, paralysed people require assistance on daily basis. Brain2Robot project
was developed to help those people with a robotic control system, which is
controlled by EEG signals. The user’s thoughts are the main controller of the
robot. There are many other BCI projects that helps in prosthetic control and
home automation, such as brain project and IGUI.
Recently, BCI has been used in many different fields. It has been used in
monitoring the actions of car drivers, such as alertness monitoring, braking
intent, workload and intent of changing lanes. Forensics is another field where
BCI is widely used, in Lie Detector applications, brain fingerprinting and trust
assessment. BCI is also now used in the gaming industry and entertainment,
using the Neurosky Mindset.
7.3 BCI Systems
In this section, the most common BCI systems will be discussed, highlight
the main reasons for using BCILAB in the following experiments.
7.3.1 BioSig
Open-source and developed using MATLAB/Octave (cross-platform), BioSig
is one of the oldest BCI toolboxes. It was developed in 2002 at Graz Univer-
sity of Technology and contains a vast quantity of statistical and analytical
functions, including Blind Source Separation (BSS) and LDA Classifier. Its
major shortcoming is that it can only analysis the data offline. Moreover, it
143
is not user friendly as there is no graphical user interface and it employs very
complicated code [223].
7.3.2 BCI2000
In 1999 the Wadsworth Center produced BCI2000. It was developed by
C++ and it includes an online acquisition technique for a wide range of ac-
quisition hardware devices and some signal processing methods. It comes
complete with a very good documentation and excellent user guidance, but it
lacks most of the advanced signal processing and machine learning algorithms
now available [224].
7.3.3 OpenViBE
This was initially made by Inria Rennes, and it was developed using C++
and runs on Windows and Linux. It concentrates on visual programming. It
has a friendly graphical user interface, it is well documented, and compatible
with a range of acquisition hardware devices. However, it has a complex build-
ing block design, which make it difficult to implement one’s own code in it. It
also suffers from having only rudimentary signal processing algorithms [225].
7.3.4 BCILAB
This is the best-known BCI toolbox for MATLAB. It was developed using
MATLAB at Swartz Center for Computational Neuroscience (UCSD) in 2010.
Online analysis can be done which gives BCILAB a huge advantage. It has
the largest collection of signal processing, machine learning methods, which
are BCI based methods. It needs a code expert to add, modify and extend as
144
it has a complex internal framework and it only supports only five acquisition
systems; however, it can be linked to any of the other previous frameworks.
For these reasons, BCILAB was used in the experiments. This research also
managed to add a plugin (code) to the toolbox, which will be discussed later
in this chapter [226].
7.4 Applying Scores to BCI applications
Quality assessment scores were developed in the previous chapter, and these
scores will be applied to real BCI applications using real data. These data
were recorded using the Compumedics Neuroscan device. Curry NeuroImag-
ing Suite 7 software was used to record the data, also Synamps 2/RT amplifier
was used while recording the data. Quik-Caps were used to provide speedy,
consistent application of 32 electrodes. Quick-Caps are fabricated from a flex-
ible breathable Lycra material with soft neoprene electrode gel reservoirs for
enhanced participant comfort. All electrodes within the Quik-Caps were placed
based on the International 10-20 electrode placement standard. The data were
recorded with sampling rate of 1000Hz. The recorded EEG, after an ethical
approval was taken, was for a twenty-three years old male, right handed and
with no known medical condition.
Two experiments were performed. In the first experiment, an arrow was
shown on the screen, the arrow pointing randomly in one of four different
directions. The arrow could point up, down, right or left. Twenty random
arrow directions appeared in each trial, each arrow appeared for 8 seconds
and there was a 5 seconds break between any arrow appearances. Showing a
145
Figure 7.2 Recording EEG signals while doing different activities.
black cross instead of the arrows indicated the break. The second experiment
showed the same arrows, but each arrow flashed with different frequency.
In both experiments, the participant was asked to imagine moving the com-
puter’s mouse on the screen towards the direction indicated. Different trials
were recorded under the effect of different noise levels. In the first trial, the
participant was asked to sit motionless and stay focused on the imagination
task. In the second trial the participant was asked to walk while watching the
screen and focusing on the main task. Running was the activity undertaken by
the participant while recording took place in the third trial. The participant
was asked to listen to music while recording the fourth trial. The next trial in-
cluded talking on the phone while recording the data. For the second last trial,
the participant was asked to touch the desk surface while data was recorded.
Finally, the participant was asked to blink his eyes continuously while the data
was recorded. All of these activities were performed in conjunction with the
main task, which was to move the computer’s mouse based on the direction
of the apparent arrow. Then the data were sorted using Kmeans, which is
considered a simple sorting algorithm in BCILAB.
Table 7.1 shows the average relationship between the scores and the recorded
EEG signals. In addition, it shows the average relationship between the scores
146
Table 7.1 The relationship between trials, scores and sorting accuracy isshown.
Score/Trail 1 2 3 4 5 6 7
1 72.87472 52.63158 20.49257 100 96.26541 100 1002 98.38261 96.34585 85.33534 94.53569 100 100 1003 29.24772 32.1591 25.72884 53.14691 56.18117 21.63943 83.13194 84.66595 81.53843 54.50289 84.6673 77.26333 83.61863 81.813375 20.90537 14.84569 19.98254 10.18209 15.24071 22.9546 25.328016 54.68769 48.18274 33.90985 51.02741 48.46199 57.7906 50.148777 96.8837 87.89941 0 100 4.140432 0 08 72.10744 69.36311 69.40994 69.60825 69.60675 67.2682 70.310569 67.77412 67.98066 54.99066 52.38999 100 56.86192 77.61457
10 97.3236 72.9927 23.69668 71.09005 47.39336 47.39336 47.3933611 99.83273 99.89355 99.70379 98.96327 96.96386 97.734 96.9934812 100 100 100 99.05213 97.1564 97.8673 97.1564
General Summary Score 76.2331455 72.4776195 54.601386 38.42864625 71.4179466 33.979284 37.1631925Sorting Accuracy 94.4444 80.1254 71.8549 69.0476 82.1667 62.5 20.7407
and sorting accuracy. The Relation between the General Summary Score and
the BCI Accuracy is shown in Figure 7.3. The General Summary Score is
directly proportional to the BCI accuracy. The scores are independent, which
means that each score focuses on specific criteria in the input signal. The
noisiest signal was recorded when the participant was running and that is the
reason of getting low scores for that trial.
On the other hand, the cleanest signal was recorded when the participant
was staying motionless and the proposed system showed high scores from that
trial. The Symmetry Analysis Score showed very low values especially in the
running, touching surface, talking on the phone and eyes blinking trials, also
it showed high values while sitting and listening to music. However, the Spikes
Count Score was very high while relaxing and decreased when noisy actions
were done. As shown in Table 7.1, the Increasing Amplitude and Frequency
Score was directly proportional to the noise in each trial. Increasing Amplitude
and Decreasing Frequency Score was nearly the same in all trials because
the data contains one window only with increasing amplitude and decreasing
147
Figure 7.3 Relation between General Summary Score and BCI Accuracy.
frequency, but other results were shown before in the results section. All trials
contained eye movement, so the Eye Movement Analysis Score was low in all
scores especially the running trial. Sorting was then applied to classify the
data based on the displayed arrows. In the first trial, the participant was
asked to remain motionless and this produced the highest accuracy. On the
other hand, walking, running and other actions showed lower accuracy. This
means that the sorting accuracy was very high in the motionless trials and
getting lower when the noise increased and the quality of the signal decreased.
7.5 Applications
The proposed system can be applied to many different applications. It can
be used in many BCI applications where the scores are treated as an input in
conjunction with the main signal. This system was applied to one of the BCI
applications, using prerecorded data [195] in which subjects were asked to sit
on a reclining chair facing a video screen and to remain motionless during the
recording. Some EEG channels were used to control the movement of the cur-
sor on the screen online. The EEG signal bands was the main controller of the
148
Figure 7.4 Relation between noise, General Summary Score and BCIAccuracy.
cursor movement, by which the cursor moved vertically towards the position of
a target located at the right edge of the video screen. A black screen appeared
for one second at the beginning of each trial. Then, a target was shown on
the right in four attainable locations. After one second, a cursor appeared at
the left edge center and moved all the way right with a fixed speed. The sub-
ject’s EEG controlled its vertical position. The main goal was to change the
cursor location to match the height of the target. Then the screen went black
when the cursor arrived at the right edge and this indicated the end of the trial.
As shown in Table 7.2 the input EEG signal was evaluated using the pro-
posed system as the scores were generated. Then the target sorting was applied
to the input EEG signal. Table 7.2 shows the relationship between the system’s
scores, SNR and the sorting accuracy. This system generated low scores when
SNR was low, then the sorting process was applied and the sorting accuracy
was directly proportional to both the generated scores and the SNR values.
Figure 7.4 shows that the General Summary Score is directly proportional to
the SNR and also it is directly proportional to the sorting accuracy.
149
Table 7.2 Relation between quality assessment scores and sorting accu-racy under different noise levels.
SNR/Score 1 2 3 4 5 6 7 8 9 10 11 12 GSS Sorting accuracy
0.1 10.9286 1.9072 29.48 2.21 17.4 14.92 2.11 43.06 69 88.89 88.89 10 31.30108 96.061 30.3575 18.7262 30.58 20.24 17.7 77.26 21.24 69.44 71.6 88.89 88.89 16 46.09337 97.64
100 50.3833 72.4002 35.32 78.16 47.73 98.63 50.38 84.32 72.7 88.89 88.89 63 70.32385 99.21
Figure 7.5 The developed plugin which assess the input signal inBCILAB.
7.6 BCILAB plugin
In the last experiment, a plugin was created that anyone can use it within
BCILAB code. The proposed quality assessment measure was imported and
two different datasets were used, two different models and four different types
of noise. This quality assessment plugin is very easy to use and can be added
as a menu item, as shown in Figure 7.5. The two different datasets for differ-
ent subjects where used in this experiment, these datasets are recorded and
prepared by BCILAB developers and are commonly used in testing.
The data sets which were used are the ones which are packaged with the
toolbox. The datasets are just for imagined movements. The participants were
asked to imagine moving their left-hand and their right-hand. Each dataset
holds the EEG data of a person imagining the two hand movements for 20
150
minutes. A stimulus is shown on the computer screen every 7.5 seconds. The
participant was asked to imagine moving the left arm when the letter “L” is
shown on the screen or imagine moving the right arm if the letter “R” is shown
on the computer screen. Data analysis and learning is the main target needed
when doing these experiments, so as to estimate which hand the user imagined
to moving using the users’ raw EEG data. Hence, it will lead to a predictive
model, which can be used in real time, such moving a wheel chair or controlling
a cursor.
Four different types of noise were applied on the datasets as shown in Fig-
ure 7.6. White noise is the first type, it was generated randomly and its power
over the frequency range was equal. Its name is derived from the white light,
where in the visible region, all its wavelengths have equal brightness. More-
over, white noise is fairly common. The second type was the Pink noise, which
has a lower frequency weighted character, meaning it is more powerful in low
frequency. 1/f noise is regarded as a pink noise subtype, where the frequency
is inversely proportional to noise power. Noise that is more powerful at high
frequencies is known as Blue noise, which is commonly used in experimental
work. Finally, the Square root noise was applied, which is a random noise
and the signal’s amplitude square root is proportional to the amplitude of the
noise, and it has a white power spectrum.
One of the main advantages of using BCILAB is having a huge variety of
signal processing models and machine learning functions. Hence, two different
models were applied to two datasets. Each model has its own feature extraction
151
(a) (b)
(c) (d)
(e)
Figure 7.6 This Figure shows the normal signal compared to the samesignal after applying different types of noise. Figure (a) shows the normalsignal, Figures (b), (c), (d) and (e) show the signal after applying the blue,pink, white and square root noise respectively.
152
and classification (machine learning) techniques.
The first model is called Logarithmic Bandpower (LBP). It is a basic model
for oscillatory processes. The logarithmic Bandpower is based on the design
of the original Graz Brain-Computer Interface, which used literalised motor
imagery for control. The features were extracted using the logarithmic variance
of each channel. The data were then filtered using the surface Laplacian;
that is a non-adaptive spatial filter. Then, the learner component processed
the resulting feature vectors. The learner model in this model is the Linear
discriminant analysis (LDA). The windowed means (WM) is the second model.
It captured the slow changing potentials, the multi-window signal average in
each channel is used as the feature vector and it used the Support Vector
Machines (SVM) as a classifier.
Blue, Pink, Square Root and White noise were applied on the two datasets
as an initial step. Then, the developed scores were applied, which are men-
tioned in Chapter 6, to these datasets. These scores gave a quality indication,
which can help in identifying whether to apply the signal processing techniques
to the data or not. It was expected that the dataset, that had low scores would
give low classification accuracy. After applying the two models to the data,
the classification accuracy was found to be low when the scores were low.
The quality scores were applied to two datasets, the average scores are
shown in Table 7.3. Signal 1 had the least amount of noise as different noise
types were applied on signals 2, 3, 4 and 5. The scoring system gave signal 1
the highest scoring values compared to the other signals, which indicates the
high accuracy of the proposed system.
153
Table 7.3 Relationship between the proposed quality scores and noise.Different noise types were applied to all the signals except signal 1. Blue,Pink, Square Root and White noise were applied to Signals 2, 3, 4 and 5respectively. These quality scores are shown in the first row, they have thehighest values compared to the other signals. Scores 10, 11 and 12 were notchanged as the data do not have any continuously increasing, decreasingor constant amplitudes and frequencies.
Signal\Score 1 2 3 4 5 6 7 8 9 10 11 12
1 32.31451 49.16605 38.08838 91 54.89063 96.08076 84.08477 70.17037 61.78387 100 100 1002 20.02751 49.23535 32.32885 88.67056 48.83882 96.08553 24.04292 69.76608 61.54034 100 99.90234 1003 19.04506 28.07739 24.04083 38.80683 45.00288 81.44688 24.0108 70.0476 61.67826 100 99.90234 1004 25.8472 32.42748 31.40555 43.55905 43.35115 93.75288 52.95945 65.25099 1.521668 100 100 1005 25.97907 24.83562 32.502 28.12952 42.46834 86.27574 29.76674 65.13548 1.387632 100 100 100
(a) (b)
Figure 7.7 Classification accuracy after applying two different models onthe two datasets. Different noise types were applied to datasets 1 and 2.None of the noise types were applied to signal 1. Hence, it had the highestaccuracy. Signals 2, 3, 4 and 5 had lower accuracy because Blue, Pink,Square Root and White noises were applied to them respectively.
154
Figure 7.7 shows the relationship between the classification accuracy and
the noise types. First, the normal datasets were classified without applying
any noise. Then, the noise types were applied which were mentioned earlier
and classified the same datasets. The classification accuracy in both models
decreased after applying the noise. These results match with the quality scores,
where the scores gave low values for the noisy datasets.
7.7 Conclusion
In this chapter, this research managed to practically connect this research
work with one of the renowned BCI toolboxes. The quality assessment measure
was linked to BCILAB and a plugin was created and will be available for
anyone to use. This plugin can give an assessment measure, which will help
many people, such as neurologists, doctors and technicians in knowing the
quality of the recorded signal. This measure can give help in many ways, such
as knowing if the data is correctly recorded. The main conclusions and future
work will be discussed in the following chapter.
Chapter 8
Conclusions and Future Work
8.1 Conclusions
Brain signals are now widely used in different aspects of life, such as patient
diagnoses and helping disabled people. Recent studies show a genetic basis for
some abnormalities of the brain, abnormalities with likely psychological con-
sequences and are strongly indicated by the frequency and shape of the neural
spikes. People with physical impairments may also gain improved quality of
life from highly controllable prosthetic limbs. Accordingly, both qualitative
and quantitative spikes analysis are very important for the disease diagnosis
and identifying the regions of abnormality.
The aim in this research was to improve the process of understanding neural
signal. The first part was to improve the feature extraction process by trying
to extract the most meaningful features from the signal using mathematical
methods. Secondly, the proposed methods sought to improve the existing
classification algorithm in order to classify the data in a more meaningful and
accurate way. Finally, the proposed methods looked to generate an automated
measure for EEG assessment based on biological and signal processing.
155
156
The first step in the qualitative and quantitative spike analysis was Spike
Sorting. The process began with spike detection, then extracting features
from the spikes and finally classification of the spikes into different groups,
each represent a certain source or neuron. In this research, a critical review
of feature extraction methods, Spike Sorting techniques, neural signal noise
estimation and quality assessment measures was undertaken and the main
advantages and disadvantages of each method were highlighted.
The next stage in this research was to show the new feature extraction
methods. Feature extraction is very important step in Spike Sorting especially
when dealing with signals, which are convoluted with noise. Three different
feature extraction methods were developed: Diffusion Maps, Cepstrum Coef-
ficients and Mel-Frequency Cepstral Coefficients. At the beginning Diffusion
Maps were used to extract the features from the neural signal. The average
accuracy of the most common algorithms were compared as shown in Figure
8.1. The first four methods used Wavelet Transform as a feature extraction
method, then the next four showed the results of using Diffusion Maps followed
by the Mel-Frequency Cepstral Coefficients as the last method. The proposed
methods showed high accuracy despite using less number of features and less
computation time. Based on the results shown in the previous chapters, neu-
ral signals were represented in a meaningful way, which helped in achieving
improved Spike Sorting accuracy, in comparison to other common methods.
Hidden Markov Models (HMM) was used in this research for Spike Sorting.
It was observed that neural spikes were represented precisely and concisely
using HMM state sequences. An HMM was built for neural spikes, where HMM
157
Figure 8.1 This figure shows the whole connection between neural signaland BCI application, beginning by recording the signal then process andassess the signal, finally connecting to BCI applications and providingfeedback to the user using Haptic device. Average accuracy using differentfeature extraction and sorting methods is shown in sub-figure (a), whilesub-figure (b) shows the automated assessment scores for an input signal.
states can represent the neural spike. The neural spike can be represented by
four states: ascending, descending, silence or peak. They constitute every
spike with an underlying probabilistic dependence that is modelled by HMM.
Based on this representation, Spike Sorting become a classification problem
of compact HMM state sequences. In addition, the method was enhanced
by applying HMM on the extracted Cepstrum features, which improved the
accuracy of Spike Sorting. Simulation results demonstrated the effectiveness
of the proposed method as well as the efficiency. In addition, Mel-frequency
Cepstral Coefficients (MFCC) were used to improve the classification results.
Nevertheless, no one had automatically assessed the input neural signal
itself, or established whether or not it had been correctly recorded. There
158
was no automated quality assessment for the EEG signal, which is really im-
portant and is needed by many people including neurologist, physicians and
technicians. The next stage of this research was to propose a quality assess-
ment method for neural signal. Neural signal is used in many applications and
it is used to assess various brain disorders types. As an example, if the patient
suffers from epilepsy, a seizure activity usually appears as rapid spiking waves
on the EEG. The method generated an automated measure to detect the noise
levels in neural signal. HMM was used to build a classification model that
classified the neural spikes based on the spike noise level. This is the first
quality assessment measure of neural signal, which can be used as a flag beside
other scores to achieve a complete quality measure for neural signal.
Twelve scores have been introduced in this research to detect the quality of
the signal based on biological and statistical properties; each score is based on
a specific property in the signal or its bands as shown in Figure 8.1. General
amplitude of the EEG channels was used to calculate the first score. The sec-
ond score was calculated based on which channel had the highest amplitude.
The dominant frequency for the channels was used to calculate the third score.
The Beta band was analysed using two scores and another one score for the
assessment of the Theta band amplitude. Then, another three scores were cal-
culated, depending upon the geometrical shape of the signals in each channel.
Finally, the last three scores were based on amplitude and frequency analysis.
This research has introduced valuable innovations: the whole process was
performed online, meaning an online quality assessment framework was ob-
tained. So the EEG signal was recorded, the proposed system gave an online
159
Figure 8.2 Combining Haptic, visual feedback with BCI application.
alerts when any channel had any abnormal or wrong behaviour, which is very
important for BCI applications. This measure was used as an input for BCI
and increased the accuracy of BCI applications. Increased credibility of data
is another advantage; this measure gave more credit for the clean signal and
gave less credit for the abnormal and noisy signal. This helped BCI applica-
tions, which used EEG signal to know how to deal with noisy data when they
received it at anytime.
8.2 Future Work
In order to get the full benefit of any BCI application, any BCI user,
especially patients, have to understand how BCI application works and also
160
how to use them. Well designed feedback provides a better understanding for
any BCI application. Haptic devices enrich the digital world by the sense of
touch. These devices enable users to have a real three dimensional navigation
and a force feedback, which can be used in different applications. Using a
Multi-feedback BCI system, which will depend on visual feedback combined
with Haptic feedback, will help to improve the accuracy of BCI applications.
Moreover, it will make it easier to be used and trained.
BCI applications can be combined with visual feedback and Haptic feed-
back as shown in Figure 8.2. Using the quality assessment measure as an input
to the BCI applications will help in improving and identifying the accuracy
of these applications. The future work of this research will involve extensive
research and experiments on merging BCI applications with Haptic devices to
provide feedback for disabled people. It can be used in many other disciplines,
such as gaming.
References
[1] S. Haggag, S. Mohamed, A. Bhatti, H. Haggag, and S. Nahavandi, “Neu-
ral spike representation using cepstrum,” in System of Systems Engineer-
ing (SOSE), 2014 9th International Conference on, pp. 97–100, IEEE,
2014.
[2] G. Buzsaki, Rhythms of the Brain. Oxford University Press, 2006.
[3] E. Hulata, R. Segev, Y. Shapira, M. Benveniste, and E. Ben-Jacob, “De-
tection and sorting of neural spikes using wavelet packets,” Physical re-
view letters, vol. 85, no. 21, pp. 4637–4640, 2000.
[4] Y. Yuan, C. Yang, and J. Si, “An advanced spike detection and sorting
system,” in Neural Networks, 2009. IJCNN 2009. International Joint
Conference on, pp. 3477–3484, IEEE, 2009.
[5] S. Demont-Guignard, P. Benquet, U. Gerber, and F. Wendling, “Analysis
of intracerebral eeg recordings of epileptic spikes: insights from a neural
network model,” Biomedical Engineering, IEEE Transactions on, vol. 56,
no. 12, pp. 2782–2795, 2009.
[6] C. E. Stafstrom, “Sites of interictal spike generation in neocortex,”
Epilepsy Currents, vol. 4, no. 3, p. 96, 2004.
161
162
[7] A. Holley, A. Duchamp, M.-F. Revial, A. Juge, and P. MacLeod,
“Qualitative and quantitative discrimination in the frog olfactory recep-
tors: analysis from electrophysiological data,” Annals of the New York
Academy of Sciences, vol. 237, no. 1, pp. 102–114, 1974.
[8] T. M. Itil, “Qualitative and quantitative eeg findings in schizophrenia.,”
Schizophrenia bulletin, vol. 3, no. 1, p. 61, 1977.
[9] R. Q. Quiroga, “Spike sorting,” Scholarpedia, vol. 2, no. 12, p. 3583,
2007.
[10] S. Gibson, J. Judy, and D. Markovic, “Spike sorting: The first step
in decoding the brain: The first step in decoding the brain,” Signal
Processing Magazine, IEEE, vol. 29, pp. 124–143, Jan 2012.
[11] E. Cohen and Y. Gross, “Treatment of disorders by unidirectional nerve
stimulation,” Jan. 27 2004. US Patent 6,684,105.
[12] L. Sornmo and P. Laguna, Bioelectrical signal processing in cardiac and
neurological applications. Academic Press, 2005.
[13] B. A. Simms and G. W. Zamponi, “Neuronal voltage-gated calcium
channels: structure, function, and dysfunction,” Neuron, vol. 82, no. 1,
pp. 24–45, 2014.
[14] “What is a neuron?.” http://psychology.about.com/od/
biopsychology/f/neuron01.htm. Accessed: 2015-09-30.
[15] Z. S. Lodish H, Berk A, Overview of Neuron Structure and Function. et
al. Molecular Cell Biology. 4th edition. New York, 2000.
163
[16] E. R. Kandel, J. H. Schwartz, T. M. Jessell, et al., Principles of neural
science, vol. 4. McGraw-Hill New York, 2000.
[17] E. Adrian, “Croonian lecture: the messages in sensory nerve fibres and
their interpretation,” Proceedings of the Royal Society of London. Series
B, Containing Papers of a Biological Character, pp. 1–18, 1931.
[18] L. Cohen, “Changes in neuron structure during action potential propa-
gation and synaptic transmission.,” Physiological Reviews, vol. 53, no. 2,
pp. 373–418, 1973.
[19] S. Krantic, N. Mechawar, S. Reix, and R. Quirion, “Apoptosis-inducing
factor: a matter of neuron life and death,” Progress in neurobiology,
vol. 81, no. 3, pp. 179–196, 2007.
[20] A. S. Tsvetkov, S. Mitra, and S. Finkbeiner, “Protein turnover differences
between neurons and other cells,” Autophagy, vol. 5, no. 7, p. 1037, 2009.
[21] G. Fiskum, A. Starkov, B. M. Polster, and C. Chinopoulos, “Mitochon-
drial mechanisms of neural cell death and neuroprotective interventions
in parkinson’s disease,” Annals of the New York Academy of Sciences,
vol. 991, no. 1, pp. 111–119, 2003.
[22] F.-B. Gao, J. E. Brenman, L. Y. Jan, and Y. N. Jan, “Genes regulating
dendritic outgrowth, branching, and routing in drosophila,” Genes and
development, vol. 13, no. 19, pp. 2549–2561, 1999.
[23] L. Eliot, “WhatÕs going on in there,” How the brain and mind develop
in the first five years of life, pp. 237–239, 1999.
164
[24] A. Peters, S. L. Palay, et al., The fine structure of the nervous system:
the cells and their processes. Hoeber Medical Division, Harper & Row,
1970.
[25] S. J. Baloyannis, V. Costa, and D. Michmizos, “Mitochondrial alterations
alzheimer’s disease,” American journal of Alzheimer’s disease and other
dementias, vol. 19, no. 2, pp. 89–93, 2004.
[26] Z. F. Mainen, J. Joerges, J. R. Huguenard, and T. J. Sejnowski, “A model
of spike initiation in neocortical pyramidal neurons,” Neuron, vol. 15,
no. 6, pp. 1427–1439, 1995.
[27] S. L. Palay, C. Sotelo, A. Peters, and P. M. Orkand, “The axon hillock
and the initial segment,” The Journal of Cell Biology, vol. 38, no. 1,
pp. 193–201, 1968.
[28] M. H. Kole and G. J. Stuart, “Signal processing in the axon initial seg-
ment,” Neuron, vol. 73, no. 2, pp. 235–247, 2012.
[29] M. R. Raffe, “Principles of peripheral nerve repair,” Newton CD and
Nunam, 1985.
[30] M. Adachi, A. Hirano, and S. M. Aronson, The pathology of the myeli-
nated axon. Igaku-Shoin Medical Pub, 1985.
[31] J. Brown and J. L. Opitz, “Treatment of neuropathies,” Handbook of
clinical neurology, vol. 7, 1970.
[32] A. R. Palmer, “Neural signal processing.,” 1995.
165
[33] J. A. Hoffer, R. B. Stein, M. K. Haugland, T. Sinkjaer, W. K. Durfee,
A. B. Schwartz, G. E. Loeb, C. Kantor, et al., “Neural signals for com-
mand control and feedback in functional neuromuscular stimulation: a
review,” J Rehabil Res Dev, vol. 33, no. 2, pp. 145–157, 1996.
[34] J. E. Lisman, S. Raghavachari, and R. W. Tsien, “The sequence of events
that underlie quantal transmission at central glutamatergic synapses,”
Nature Reviews Neuroscience, vol. 8, no. 8, pp. 597–609, 2007.
[35] D. D. Ginty and R. A. Segal, “Retrograde neurotrophin signaling: Trk-
ing along the axon,” Current opinion in neurobiology, vol. 12, no. 3,
pp. 268–274, 2002.
[36] T. L. O’Donohue, W. R. Millington, G. E. Handelmann, P. C. Contreras,
and B. M. Chronwall, “On the 50th anniversary of dale’s law: multiple
neurotransmitter neurons,” Trends in Pharmacological Sciences, vol. 6,
pp. 305–308, 1985.
[37] M. Urbanska, M. Blazejczyk, and J. Jaworski, “Molecular basis of den-
dritic arborization,” Acta neurobiologiae experimentalis, vol. 68, no. 2,
p. 264, 2008.
[38] K.-W. Yau, “Receptive fields, geometry and conduction block of sensory
neurones in the central nervous system of the leech.,” The Journal of
Physiology, vol. 263, no. 3, pp. 513–538, 1976.
[39] S. Meng, M. Rouabhia, and Z. Zhang, Electrical stimulation in tissue
regeneration. INTECH Open Access Publisher, 2011.
166
[40] H. Y. Frank and W. A. Catterall, “Overview of the voltage-gated sodium
channel family,” Genome Biol, vol. 4, no. 207, pp. 10–1186, 2003.
[41] A. Ghosh and M. E. Greenberg, “Calcium signaling in neurons: molec-
ular mechanisms and cellular consequences,” Science, vol. 268, no. 5208,
pp. 239–247, 1995.
[42] G. Moruzzi and H. W. Magoun, “Brain stem reticular formation and ac-
tivation of the eeg,” Electroencephalography and clinical neurophysiology,
vol. 1, no. 1, pp. 455–473, 1949.
[43] V. A. Zerris, J. D. Donoghue, L. R. Hochberg, D. K. OÕRourke, and
E. A. Chiocca, “Braingate: Turning thought into actionÑfirst experience
with a human neuromotor prosthesis: 885,” Neurosurgery, vol. 57, no. 2,
p. 425, 2005.
[44] “g.tec medical engineering.” https://gtecmedical.wordpress.com/.
Accessed: 2015-10-30.
[45] R. Mathur and N. Douglas, “Frequency of eeg arousals from nocturnal
sleep in normal subjects.,” Sleep, vol. 18, no. 5, pp. 330–333, 1995.
[46] N. C. on Bioethics, “Novel neurotechnologies: intervening in the brain,”
2013.
[47] P. Ferenci, A. Lockwood, K. Mullen, R. Tarter, K. Weissenborn, and
A. T. Blei, “Hepatic encephalopathyÑdefinition, nomenclature, diagno-
sis, and quantification: final report of the working party at the 11th
167
world congresses of gastroenterology, vienna, 1998,” Hepatology, vol. 35,
no. 3, pp. 716–721, 2002.
[48] S. S. Spencer, “Depth electroencephalography in selection of refractory
epilepsy for surgery,” Annals of neurology, vol. 9, no. 3, pp. 207–214,
1981.
[49] E. L. Reilly, “Eeg recording and operation of the apparatus,” Electroen-
cephalography: basic principles, clinical applications and related fields,
pp. 122–142, 1999.
[50] R. Katznelson, “Eeg recording, electrode placement, and aspects of gen-
erator localization,” Electric fields of the brain, pp. 176–213, 1981.
[51] L. I. Zhang and M.-m. Poo, “Electrical activity and development of neu-
ral circuits,” Nature Neuroscience, vol. 4, pp. 1207–1214, 2001.
[52] E. Callaway, Brain electrical potentials and individual psychological dif-
ferences. Grune & Stratton, 1975.
[53] D. B. Lindsley, “Electrical potentials of the brain in children and adults,”
The Journal of General Psychology, vol. 19, no. 2, pp. 285–306, 1938.
[54] A. L. Loomis, E. N. Harvey, and G. Hobart, “Electrical potentials of
the human brain.,” Journal of experimental Psychology, vol. 19, no. 3,
p. 249, 1936.
[55] C. Shagass, “Electrical activity of the brain,” Handbook of psychophysi-
ology, pp. 263–328, 1972.
168
[56] J. K. Mai, J. Assheuer, and G. Paxinos, Atlas of the human brain. Aca-
demic Press San Diego:, 1997.
[57] H. Damasio, Human brain anatomy in computerized images. Oxford
university press, 1995.
[58] G. Salamon and Y. P. Huang, Radiologic anatomy of the brain. Springer,
1976.
[59] S. Blanco, R. Q. Quiroga, O. Rosso, and S. Kochen, “Time-frequency
analysis of electroencephalogram series,” Physical Review E, vol. 51,
no. 3, p. 2624, 1995.
[60] D. B. Lindsley, “Emotions and the electroencephalogram.,” 1950.
[61] M. Ortiz, “A brief history of biosignal-driven art,”
[62] D. L. Schacter, “Eeg theta waves and psychological phenomena: A review
and analysis,” Biological Psychology, vol. 5, no. 1, pp. 47–82, 1977.
[63] M. Teplan, “Fundamentals of eeg measurement,” Measurement science
review, vol. 2, no. 2, pp. 1–11, 2002.
[64] H. Adeli, S. Ghosh-Dastidar, and N. Dadmehr, “A wavelet-chaos
methodology for analysis of eegs and eeg subbands to detect seizure
and epilepsy,” Biomedical Engineering, IEEE Transactions on, vol. 54,
no. 2, pp. 205–211, 2007.
[65] P. Olejniczak, “Neurophysiologic basis of eeg,” Journal of clinical neu-
rophysiology, vol. 23, no. 3, pp. 186–189, 2006.
169
[66] W. T. Blume, G. B. Young, and J. F. Lemieux, “Eeg morphology of par-
tial epileptic seizures,” Electroencephalography and clinical neurophysi-
ology, vol. 57, no. 4, pp. 295–302, 1984.
[67] C.-W. Ko and H.-W. Chung, “Automatic spike detection via an artificial
neural network using raw eeg data: effects of data preparation and impli-
cations in the limitations of online recognition,” Clinical neurophysiology,
vol. 111, no. 3, pp. 477–481, 2000.
[68] J. Dauwels, F. Vialatte, C. Latchoumane, J. Jeong, and A. Cichocki,
“Eeg synchrony analysis for early diagnosis of alzheimer’s disease: a
study with several synchrony measures and eeg data sets,” in Engineer-
ing in Medicine and Biology Society, 2009. EMBC 2009. Annual Inter-
national Conference of the IEEE, pp. 2224–2227, IEEE, 2009.
[69] C. Schevon, J. Cappell, R. Emerson, J. Isler, P. Grieve, R. Goodman,
G. McKhann, H. Weiner, W. Doyle, R. Kuzniecky, et al., “Cortical ab-
normalities in epilepsy revealed by local eeg synchrony,” Neuroimage,
vol. 35, no. 1, pp. 140–148, 2007.
[70] R. P. Brenner and N. Schaul, “Periodic eeg patterns: classification, clin-
ical correlation, and pathophysiology.,” Journal of Clinical Neurophysi-
ology, vol. 7, no. 2, pp. 249–268, 1990.
[71] R. W. Homan, J. Herman, and P. Purdy, “Cerebral location of interna-
tional 10–20 system electrode placement,” Electroencephalography and
clinical neurophysiology, vol. 66, no. 4, pp. 376–382, 1987.
170
[72] G. H. Klem, H. O. Lüders, H. Jasper, and C. Elger, “The ten-twenty
electrode system of the international federation,” Electroencephalogr Clin
Neurophysiol, vol. 52, no. suppl., p. 3, 1999.
[73] B. Blankertz, G. Dornhege, M. Krauledat, K. Muller, V. Kunzmann,
F. Losch, and G. Curio, “The berlin brain-computer interface: Eeg-based
communication without subject training,” Neural Systems and Rehabil-
itation Engineering, IEEE Transactions on, vol. 14, no. 2, pp. 147–152,
2006.
[74] T. Thompson, T. Steffert, T. Ros, J. Leach, and J. Gruzelier, “Eeg
applications for sport and performance,” Methods, vol. 45, no. 4, pp. 279–
288, 2008.
[75] T. Ning and J. Bronzino, “Autoregressive and bispectral analysis tech-
niques: Eeg applications,” Engineering in Medicine and Biology Maga-
zine, IEEE, vol. 9, no. 1, pp. 47–50, 1990.
[76] K. Bauerle, C.-A. Greim, M. Schroth, M. Geisselbrecht, A. Köbler, and
N. Roewer, “Prediction of depth of sedation and anaesthesia by the nar-
cotrendtm eeg monitor,” British journal of anaesthesia, vol. 92, no. 6,
pp. 841–845, 2004.
[77] S. M. Kosslyn, Image and brain: The resolution of the imagery debate.
MIT press, 1996.
171
[78] M. B. Sterman, “Physiological origins and functional correlates of eeg
rhythmic activities: implications for self-regulation,” Biofeedback and
self-regulation, vol. 21, no. 1, pp. 3–33, 1996.
[79] D. G. Gilbert, F. J. McClernon, N. E. Rabinovich, W. D. Dibb, L. C.
Plath, S. Hiyane, R. A. Jensen, C. J. Meliska, S. L. Estes, and B. A.
Gehlbach, “Eeg, physiology, and task-related mood fail to resolve across
31 days of smoking abstinence: relations to depressive traits, nicotine
exposure, and dependence.,” Experimental and Clinical Psychopharma-
cology, vol. 7, no. 4, p. 427, 1999.
[80] K. K. Ang, C. Guan, K. Sui Geok Chua, B. T. Ang, C. Kuah, C. Wang,
K. S. Phua, Z. Y. Chin, and H. Zhang, “Clinical study of neurorehabili-
tation in stroke using eeg-based motor imagery brain-computer interface
with robotic feedback,” in Engineering in Medicine and Biology Society
(EMBC), 2010 Annual International Conference of the IEEE, pp. 5549–
5552, IEEE, 2010.
[81] A. P. Bagshaw, J. Jacobs, P. LeVan, F. Dubeau, and J. Gotman, “Ef-
fect of sleep stage on interictal high-frequency oscillations recorded from
depth macroelectrodes in patients with focal epilepsy,” Epilepsia, vol. 50,
no. 4, pp. 617–628, 2009.
[82] R. B. Pachori and V. Bajaj, “Analysis of normal and epileptic seizure
eeg signals using empirical mode decomposition,” Computer methods and
programs in biomedicine, vol. 104, no. 3, pp. 373–381, 2011.
172
[83] J. R. Cho, D. L. Koo, E. Y. Joo, S. M. Yoon, E. Ju, J. Lee, D. Y. Kim,
and S. B. Hong, “Effect of levetiracetam monotherapy on background
eeg activity and cognition in drug-naïve epilepsy patients,” Clinical neu-
rophysiology, vol. 123, no. 5, pp. 883–891, 2012.
[84] U. R. Acharya, F. Molinari, S. V. Sree, S. Chattopadhyay, K.-H. Ng,
and J. S. Suri, “Automated diagnosis of epileptic eeg using entropies,”
Biomedical Signal Processing and Control, vol. 7, no. 4, pp. 401–408,
2012.
[85] P. J. Marshall, J. N. Saby, and A. N. Meltzoff, “Imitation and the de-
veloping social brain: infantsÕ somatotopic eeg patterns for acts of self
and other,” Int. J. Psychol. Res., vol. 6, pp. 22–29, 2013.
[86] P. A. Davis, “Comparative study of the eegs of schizophrenic and manic-
depressive patients,” 2014.
[87] S. Sanei and J. A. Chambers, EEG signal processing. John Wiley &
Sons, 2013.
[88] J. Claassen, S. Mayer, R. Kowalski, R. Emerson, and L. Hirsch, “Detec-
tion of electrographic seizures with continuous eeg monitoring in criti-
cally ill patients,” Neurology, vol. 62, no. 10, pp. 1743–1748, 2004.
[89] D. R. Simkin, R. W. Thatcher, and J. Lubar, “Quantitative eeg and
neurofeedback in children and adolescents: Anxiety disorders, depressive
173
disorders, comorbid addiction and attention-deficit/hyperactivity disor-
der, and brain injury,” Child and adolescent psychiatric clinics of North
America, vol. 23, no. 3, pp. 427–464, 2014.
[90] Y. Tu, Y. S. Hung, L. Hu, G. Huang, Y. Hu, and Z. Zhang, “An auto-
mated and fast approach to detect single-trial visual evoked potentials
with application to brain–computer interface,” Clinical Neurophysiology,
vol. 125, no. 12, pp. 2372–2383, 2014.
[91] D. C. Hammond, “Book review: Handbook of quantitative electroen-
cephalography and eeg biofeedback: Scientific foundations and practical
applications,” Clinical EEG and neuroscience, vol. 45, no. 1, pp. 59–60,
2014.
[92] E. V. Friedrich, N. Suttie, A. Sivanathan, T. Lim, S. Louchart, and J. A.
Pineda, “Brain–computer interface game applications for combined neu-
rofeedback and biofeedback treatment for children on the autism spec-
trum,” Frontiers in neuroengineering, vol. 7, 2014.
[93] N. C. Moore, “A review of eeg biofeedback treatment of anxiety disor-
ders,” Clinical EEG and Neuroscience, vol. 31, no. 1, pp. 1–6, 2000.
[94] G. E. Schwartz, “Biofeedback, self-regulation, and the patterning of
physiological processes: By training subjects to control voluntarily com-
binations of visceral, neural, and motor responses, it is possible to assess
linkages between physiological responses and their relationship to human
consciousness,” American Scientist, pp. 314–324, 1975.
174
[95] D. A. Hoffman, J. F. Lubar, R. W. Thatcher, M. B. Sterman, P. J.
Rosenfeld, S. Striefel, D. Trudeau, and S. Stockdale, “Limitations of the
american academy of neurology and american clinical neurophysiology
society paper on qeeg,” 2014.
[96] R. Xu, N. Jiang, C. Lin, N. Mrachacz-Kersting, K. Dremstrup, and
D. Farina, “Enhanced low-latency detection of motor intention from eeg
for closed-loop brain-computer interface applications,” Biomedical Engi-
neering, IEEE Transactions on, vol. 61, no. 2, pp. 288–296, 2014.
[97] A. Ortiz-Rosario and H. Adeli, “Brain-computer interface technologies:
from signal to action,” Reviews in the Neurosciences, vol. 24, no. 5,
pp. 537–552, 2013.
[98] V. Kaiser, G. Bauernfeind, A. Kreilinger, T. Kaufmann, A. Kübler,
C. Neuper, and G. R. Müller-Putz, “Cortical effects of user training
in a motor imagery based brain–computer interface measured by fnirs
and eeg,” Neuroimage, vol. 85, pp. 432–444, 2014.
[99] R. Raj, R. Singal, and A. Gagneja, “A technical analysis of brain com-
puter interface and its real world applications,”
[100] Z. Nenadic and J. W. Burdick, “Spike detection using the continu-
ous wavelet transform,” Biomedical Engineering, IEEE Transactions on,
vol. 52, no. 1, pp. 74–87, 2005.
175
[101] Z. Yang, Q. Zhao, and W. Liu, “Spike feature extraction using infor-
mative samples,” Advances in Neural Information Processing Systems,
vol. 21, pp. 1865–1872, 2009.
[102] J. P. Cunningham and M. Y. Byron, “Dimensionality reduction for large-
scale neural recordings,” Nature neuroscience, 2014.
[103] X. Yang and S. A. Shamma, “A totally automated system for the detec-
tion and classification of neural spikes,” Biomedical Engineering, IEEE
Transactions on, vol. 35, no. 10, pp. 806–816, 1988.
[104] D. McFarland, A. Lefkowicz, and J. Wolpaw, “Design and operation
of an eeg-based brain-computer interface with digital signal processing
technology,” Behavior Research Methods, Instruments, & Computers,
vol. 29, no. 3, pp. 337–345, 1997.
[105] S. Gibson, J. W. Judy, and D. Markovic, “Comparison of spike-sorting
algorithms for future hardware implementation,” in Engineering in
Medicine and Biology Society, 2008. EMBS 2008. 30th Annual Inter-
national Conference of the IEEE, pp. 5015–5020, IEEE, 2008.
[106] S. E. Paraskevopoulou, D. Y. Barsakcioglu, M. R. Saberi, A. Eftekhar,
and T. G. Constandinou, “Feature extraction using first and second
derivative extrema (fsde) for real-time and hardware-efficient spike sort-
ing,” Journal of neuroscience methods, vol. 215, no. 1, pp. 29–37, 2013.
[107] T. I. Aksenova, O. K. Chibirova, O. A. Dryga, I. V. Tetko, A.-L. Benabid,
and A. E. Villa, “An unsupervised automatic method for sorting neuronal
176
spike waveforms in awake and freely moving animals,” Methods, vol. 30,
no. 2, pp. 178–187, 2003.
[108] T. Takekawa, Y. Isomura, and T. Fukai, “Accurate spike sorting for
multi-unit recordings,” European Journal of Neuroscience, vol. 31, no. 2,
pp. 263–272, 2010.
[109] S. P. Rebrik, B. D. Wright, A. A. Emondi, and K. D. Miller, “Cross-
channel correlations in tetrode recordings: implications for spike-
sorting,” Neurocomputing, vol. 26, pp. 1033–1038, 1999.
[110] Z. Yang, L. Hoang, Q. Zhao, E. Keefer, and W. Liu, “1/f neural noise
reduction and spike feature extraction using a subset of informative sam-
ples,” Annals of biomedical engineering, vol. 39, no. 4, pp. 1264–1277,
2011.
[111] Y. Ghanbari, P. E. Papamichalis, and L. Spence, “Graph-laplacian fea-
tures for neural waveform classification,” Biomedical Engineering, IEEE
Transactions on, vol. 58, no. 5, pp. 1365–1372, 2011.
[112] X. He, D. Cai, and P. Niyogi, “Laplacian score for feature selection,” in
Advances in neural information processing systems, pp. 507–514, 2005.
[113] S. Shoham, L. M. Paninski, M. R. Fellows, N. G. Hatsopoulos, J. P.
Donoghue, R. Normann, et al., “Statistical encoding model for a primary
motor cortical brain-machine interface,” Biomedical Engineering, IEEE
Transactions on, vol. 52, no. 7, pp. 1312–1322, 2005.
177
[114] M. S. Lewicki, “A review of methods for spike sorting: the detection
and classification of neural action potentials,” Network: Computation in
Neural Systems, vol. 9, no. 4, pp. R53–R78, 1998.
[115] P. Horton, A. Nicol, K. Kendrick, and J. Feng, “Spike sorting based upon
machine learning algorithms (soma),” Journal of neuroscience methods,
vol. 160, no. 1, pp. 52–68, 2007.
[116] D. A. Adamos, E. K. Kosmidis, and G. Theophilidis, “Performance eval-
uation of pca-based spike sorting algorithms,” Computer methods and
programs in biomedicine, vol. 91, no. 3, pp. 232–244, 2008.
[117] A. Pavlov, V. A. Makarov, I. Makarova, and F. Panetsos, “Sorting of
neural spikes: when wavelet based methods outperform principal com-
ponent analysis,” Natural Computing, vol. 6, no. 3, pp. 269–281, 2007.
[118] T. Takekawa, Y. Isomura, and T. Fukai, “Spike sorting of heterogeneous
neuron types by multimodality-weighted pca and explicit robust varia-
tional bayes,” Frontiers in neuroinformatics, vol. 6, 2012.
[119] R. Quian Quiroga, Z. Nadasdy, and Y. Ben-Shaul, “Unsupervised spike
detection and sorting with wavelets and superparamagnetic clustering,”
2004.
[120] R. Quiroga, Z. Nadasdy, and Y. Ben-Shaul, “Unsupervised spike de-
tection and sorting with wavelets and superparamagnetic clustering,”
Neural computation, vol. 16, no. 8, pp. 1661–1687, 2004.
178
[121] F. Wood, M. J. Black, C. Vargas-Irwin, M. Fellows, and J. P. Donoghue,
“On the variability of manual spike sorting,” Biomedical Engineering,
IEEE Transactions on, vol. 51, no. 6, pp. 912–918, 2004.
[122] K. D. Harris, D. A. Henze, J. Csicsvari, H. Hirase, and G. Buzsáki,
“Accuracy of tetrode spike separation as determined by simultaneous in-
tracellular and extracellular measurements,” Journal of neurophysiology,
vol. 84, no. 1, pp. 401–414, 2000.
[123] J. MacQueen et al., “Some methods for classification and analysis of mul-
tivariate observations,” in Proceedings of the fifth Berkeley symposium
on mathematical statistics and probability, vol. 1, pp. 281–297, Oakland,
CA, USA., 1967.
[124] D. Novak, J. Wild, T. Sieger, and R. Jech, “Identifying number of neu-
rons in extracellular recording,” in Neural Engineering, 2009. NER’09.
4th International IEEE/EMBS Conference on, pp. 742–745, IEEE, 2009.
[125] C. Zhang, X. Zhang, M. Q. Zhang, and Y. Li, “Neighbor number, val-
ley seeking and clustering,” Pattern Recognition Letters, vol. 28, no. 2,
pp. 173–180, 2007.
[126] M. Blatt, S. Wiseman, and E. Domany, “Data clustering using a model
granular magnet,” Neural Computation, vol. 9, no. 8, pp. 1805–1842,
1997.
[127] U. Rutishauser, E. M. Schuman, and A. N. Mamelak, “Online detection
and sorting of extracellularly recorded action potentials in human medial
179
temporal lobe recordings, in vivo,” Journal of neuroscience methods,
vol. 154, no. 1, pp. 204–224, 2006.
[128] T. M. Vaughan, J. R. Wolpaw, and E. Donchin, “Eeg-based commu-
nication: prospects and problems,” Rehabilitation Engineering, IEEE
Transactions on, vol. 4, no. 4, pp. 425–430, 1996.
[129] A. S. Zandi, G. A. Dumont, M. J. Yedlin, P. Lapeyrie, C. Sudre, and
S. Gaffet, “Scalp eeg acquisition in a low-noise environment: A quan-
titative assessment,” Biomedical Engineering, IEEE Transactions on,
vol. 58, no. 8, pp. 2407–2417, 2011.
[130] R. T. Wilkinson and K. B. Campbell, “Effects of traffic noise on quality
of sleep: assessment by eeg, subjective report, or performance the next
day,” The Journal of the Acoustical Society of America, vol. 75, no. 2,
pp. 468–475, 1984.
[131] A. Delorme, T. Sejnowski, and S. Makeig, “Enhanced detection of arti-
facts in eeg data using higher-order statistics and independent compo-
nent analysis,” Neuroimage, vol. 34, no. 4, pp. 1443–1449, 2007.
[132] P. Scalart et al., “Speech enhancement based on a priori signal to noise
estimation,” in Acoustics, Speech, and Signal Processing, 1996. ICASSP-
96. Conference Proceedings., 1996 IEEE International Conference on,
vol. 2, pp. 629–632, IEEE, 1996.
180
[133] C. Plapous, C. Marro, and P. Scalart, “Improved signal-to-noise ratio
estimation for speech enhancement,” Audio, Speech, and Language Pro-
cessing, IEEE Transactions on, vol. 14, no. 6, pp. 2098–2108, 2006.
[134] Y. Xu, J. B. Weaver, D. M. Healy Jr, and J. Lu, “Wavelet transform
domain filters: a spatially selective noise filtration technique,” Image
Processing, IEEE Transactions on, vol. 3, no. 6, pp. 747–758, 1994.
[135] T. Wittkop, V. Hohmann, and B. Kollmeier, “Noise reduction strategies
employing interaural parameters,” The Journal of the Acoustical Society
of America, vol. 105, no. 2, pp. 1211–1211, 1999.
[136] V. Stahl, A. Fischer, and R. Bippus, “Quantile based noise estimation for
spectral subtraction and wiener filtering,” in Acoustics, Speech, and Sig-
nal Processing, 2000. ICASSP’00. Proceedings. 2000 IEEE International
Conference on, vol. 3, pp. 1875–1878, IEEE, 2000.
[137] R. Martin, “Spectral subtraction based on minimum statistics,” power,
vol. 6, p. 8, 1994.
[138] S. F. Boll, “Suppression of acoustic noise in speech using spectral sub-
traction,” Acoustics, Speech and Signal Processing, IEEE Transactions
on, vol. 27, no. 2, pp. 113–120, 1979.
[139] G. Doblinger, “Computationally efficient speech enhancement by spec-
tral minima tracking in subbands,” Power, vol. 1, p. 2, 1995.
[140] H. Hirsch and C. Ehrlicher, “Noise estimation techniques for robust
speech recognition,” in Acoustics, Speech, and Signal Processing, 1995.
181
ICASSP-95., 1995 International Conference on, vol. 1, pp. 153–156,
IEEE, 1995.
[141] R. Martin, “An efficient algorithm to estimate the instantaneous snr of
speech signals.,” in Eurospeech, vol. 93, pp. 1093–1096, 1993.
[142] I. Cohen and B. Berdugo, “Noise estimation by minima controlled recur-
sive averaging for robust speech enhancement,” Signal Processing Let-
ters, IEEE, vol. 9, no. 1, pp. 12–15, 2002.
[143] I. Cohen, “Noise spectrum estimation in adverse environments: Im-
proved minima controlled recursive averaging,” Speech and Audio Pro-
cessing, IEEE Transactions on, vol. 11, no. 5, pp. 466–475, 2003.
[144] C. Ris and S. Dupont, “Assessing local noise level estimation methods:
Application to noise robust asr,” Speech Communication, vol. 34, no. 1,
pp. 141–158, 2001.
[145] A. Anier, T. Lipping, R. Ferenets, P. Puumala, E. Sonkajärvi, I. Rätsep,
and V. Jäntti, “Relationship between approximate entropy and visual
inspection of irregularity in the eeg signal, a comparison with spectral
entropy,” British journal of anaesthesia, p. aes312, 2012.
[146] H. K. Jung, J. H. Choi, and T. Kim, “Solving alignment problems in neu-
ral spike sorting using frequency domain pca,” Neurocomputing, vol. 69,
no. 7, pp. 975–978, 2006.
[147] J. Wild, Z. Prekopcsak, T. Sieger, D. Novak, and R. Jech, “Performance
comparison of extracellular spike sorting algorithms for single-channel
182
recordings,” Journal of Neuroscience Methods, vol. 203, no. 2, pp. 369–
376, 2012.
[148] R. A. DeVore and B. J. Lucier, “Wavelets,” Acta numerica, vol. 1, pp. 1–
56, 1992.
[149] C. Yang, B. Olson, and J. Si, “A multiscale correlation of wavelet coeffi-
cients approach to spike detection,” Neural computation, vol. 23, no. 1,
pp. 215–250, 2011.
[150] H.-Y. Lai, Y.-Y. Chen, S.-H. Lin, Y.-C. Lo, S. Tsang, S.-Y. Chen, W.-T.
Zhao, W.-H. Chao, Y.-C. Chang, R. Wu, et al., “Automatic spike sorting
for extracellular electrophysiological recording using unsupervised single
linkage clustering based on grey relational analysis,” Journal of neural
engineering, vol. 8, no. 3, p. 036003, 2011.
[151] Y. Yuan, C. Yang, and J. Si, “The m-sorter: An automatic and ro-
bust spike detection and classification system,” Journal of neuroscience
methods, vol. 210, no. 2, pp. 281–290, 2012.
[152] R. R. Coifman and S. Lafon, “Diffusion maps,” Applied and computa-
tional harmonic analysis, vol. 21, no. 1, pp. 5–30, 2006.
[153] P.-M. Zhang, J.-Y. Wu, Y. Zhou, P.-J. Liang, and J.-Q. Yuan, “Spike
sorting based on automatic template reconstruction with a partial so-
lution to the overlapping problem,” Journal of neuroscience methods,
vol. 135, no. 1, pp. 55–65, 2004.
183
[154] M. Blatt, S. Wiseman, and E. Domany, “Superparamagnetic clustering
of data,” Physical review letters, vol. 76, no. 18, pp. 3251–3254, 1996.
[155] P. Machart and L. Ralaivola, “Confusion matrix stability bounds for
multiclass classification,” arXiv preprint arXiv:1202.6221, 2012.
[156] N. V. Cuong, V. Dinh, and L. S. T. Ho, “Mel-frequency cepstral coef-
ficients for eye movement identification,” in Tools with Artificial Intel-
ligence (ICTAI), 2012 IEEE 24th International Conference on, vol. 1,
pp. 253–260, IEEE, 2012.
[157] H. Zhou, S. Mohamed, A. Bhatti, C. P. Lim, N. Gu, S. Haggag, and
S. Nahavandi, “Spike sorting using hidden markov models,” in Neural
Information Processing, pp. 553–560, Springer, 2013.
[158] E. Hulata, R. Segev, and E. Ben-Jacob, “A method for spike sorting and
detection based on wavelet packets and shannon’s mutual information,”
Journal of Neuroscience methods, vol. 117, no. 1, pp. 1–12, 2002.
[159] E. De Benedetti, S. Lew, and B. Zanutto, “A wavelet approach for on-
line spike sorting in tetrode recordings,” in Engineering in Medicine and
Biology Society (EMBC), 2010 Annual International Conference of the
IEEE, pp. 6662–6665, IEEE, 2010.
[160] S. Takahashi, Y. Anzai, and Y. Sakurai, “Automatic sorting for multi-
neuronal activity recorded with tetrodes in the presence of overlapping
spikes,” Journal of neurophysiology, vol. 89, no. 4, pp. 2245–2258, 2003.
184
[161] S. Takahashi, Y. Anzai, and Y. Sakurai, “A new approach to spike sort-
ing for multi-neuronal activities recorded with a tetrode how ica can be
practical,” Neuroscience research, vol. 46, no. 3, pp. 265–272, 2003.
[162] L. H. Ang, M. Kamuf, and W. G. Lim, “Soft output viterbi algorithm
method and decoder,” Mar. 27 2013. EP Patent 2,302,811.
[163] G. J. Dinning and A. C. Sanderson, “Real-time classification of multiunit
neural signals using reduced feature sets,” Biomedical Engineering, IEEE
Transactions on, no. 12, pp. 804–812, 1981.
[164] E. M. Schmidt, “Computer separation of multi-unit neuroelectric data:
a review,” Journal of neuroscience methods, vol. 12, no. 2, pp. 95–111,
1984.
[165] G. Tauchen and V. Todorov, “Kolmogorov-smirnov type tests for local
gaussianity in high-frequency data,” 2012.
[166] H. W. Lilliefors, “On the kolmogorov-smirnov test for normality with
mean and variance unknown,” Journal of the American Statistical Asso-
ciation, vol. 62, no. 318, pp. 399–402, 1967.
[167] A. K. Jain, “Data clustering: 50 years beyond k-means,” Pattern Recog-
nition Letters, vol. 31, no. 8, pp. 651–666, 2010.
[168] P. J. Lisboa, T. A. Etchells, I. H. Jarman, and S. J. Chambers, “Finding
reproducible cluster partitions for the k-means algorithm,” BMC bioin-
formatics, vol. 14, no. Suppl 1, p. S8, 2013.
185
[169] A. Singer and H.-t. Wu, “Orientability and diffusion maps,” Applied and
computational harmonic analysis, vol. 31, no. 1, pp. 44–58, 2011.
[170] T. Lapainis, C. Scanlan, S. Rubakhin, and J. Sweedler, “A multichannel
native fluorescence detection system for capillary electrophoretic analy-
sis of neurotransmitters in single neurons,” Analytical and bioanalytical
chemistry, vol. 387, no. 1, pp. 97–105, 2007.
[171] F. Briggs, G. R. Mangun, and W. M. Usrey, “Attention enhances synap-
tic efficacy and the signal-to-noise ratio in neural circuits,” Nature, 2013.
[172] N. Ramachandran and A. Chellappa, “Feature extraction from eeg using
wavelets: Spike detection algorithm,” in International Symposium on
Modern Computing (JVA 2006), pp. 120–124, 2006.
[173] V. E. Bielat and A. Levi, “Open access textbookÑaccess, quality, use,”
2012.
[174] Y. Ephraim, “Hidden markov models,” Encyclopedia of Operations Re-
search and Management Science, pp. 704–708, 2013.
[175] Y. Perelman and R. Ginosar, “An integrated system for multichannel
neuronal recording with spike/lfp separation, integrated a/d conversion
and threshold detection,” Biomedical Engineering, IEEE Transactions
on, vol. 54, no. 1, pp. 130–137, 2007.
[176] H. Moravec, “When will computer hardware match the human brain,”
Journal of evolution and technology, vol. 1, no. 1, p. 10, 1998.
186
[177] S. Haggag, S. Mohamed, A. Bhatti, N. Gu, H. Zhou, and S. Naha-
vandi, “Cepstrum based unsupervised spike classification,” in Systems,
Man, and Cybernetics (SMC), 2013 IEEE International Conference on,
pp. 3716–3720, IEEE, 2013.
[178] S. Sanei and J. A. Chambers, EEG signal processing. John Wiley &
Sons, 2008.
[179] M. Seeck, C. M. Michel, N. Mainwaring, R. Cosgrove, H. Blume, J. Ives,
T. Landis, and D. L. Schomer, “Evidence for rapid face recognition from
human scalp and intracranial electrodes,” Neuroreport, vol. 8, no. 12,
pp. 2749–2754, 1997.
[180] S. Haggag, S. Mohamed, H. Haggag, and S. Nahavandi, “Hidden markov
model neurons classification based on mel-frequency cepstral coeffi-
cients,” in System of Systems Engineering (SOSE), 2014 9th Interna-
tional Conference on, pp. 166–170, IEEE, 2014.
[181] T. Nguyen, A. Bhatti, A. Khosravi, S. Haggag, D. Creighton, and S. Na-
havandi, “Automatic spike sorting by unsupervised clustering with dif-
fusion maps and silhouettes,” Neurocomputing, 2014.
[182] H. J. Hermens, B. Freriks, R. Merletti, D. Stegeman, J. Blok, G. Rau,
C. Disselhorst-Klug, and G. Hägg, European recommendations for sur-
face electromyography. Roessingh Research and Development The
Netherlands, 1999.
187
[183] C. J. De Luca, “The use of surface electromyography in biomechanics,”
Journal of applied biomechanics, vol. 13, pp. 135–163, 1997.
[184] I. Hettiarachchi, S. Mohamed, and S. Nahavandi, “A marginalised
markov chain monte carlo approach for model based analysis of eeg
data,” in Biomedical Imaging (ISBI), 2012 9th IEEE International Sym-
posium on, pp. 1539–1542, IEEE, 2012.
[185] C. L. Philips, J. M. Parr, and E. Riskin, Signals, systems, and trans-
forms. Prentice Hall, 1995.
[186] B. Yang, Q. Wang, Z. Han, H. Wang, and L. He, “Development of a bci
simulated application system based on directx,” in Practical Applications
of Intelligent Systems, pp. 813–822, Springer, 2014.
[187] I. T. Hettiarachchi, T. T. Nguyen, and S. Nahavandi, “Motor imagery
data classification for bci application using wavelet packet feature extrac-
tion,” in Neural Information Processing, pp. 519–526, Springer, 2014.
[188] Y. Zhang, G. Zhou, Q. Zhao, J. Jin, X. Wang, and A. Cichocki, “Spatial-
temporal discriminant analysis for erp-based brain-computer interface,”
Neural Systems and Rehabilitation Engineering, IEEE Transactions on,
vol. 21, no. 2, pp. 233–243, 2013.
[189] Y. Zhang, G. Zhou, J. Jin, X. Wang, and A. Cichocki, “Frequency recog-
nition in ssvep-based bci using multiset canonical correlation analysis,”
International journal of neural systems, vol. 24, no. 04, p. 1450013, 2014.
188
[190] W. Wu, Z. Chen, X. Gao, Y. Li, E. N. Brown, and S. Gao, “Probabilistic
common spatial patterns for multichannel eeg analysis,” Pattern Analysis
and Machine Intelligence, IEEE Transactions on, vol. 37, no. 3, pp. 639–
653, 2015.
[191] P. Khatwani and A. Tiwari, “A survey on different noise removal tech-
niques of eeg signals,” International Journal of Advanced Research in
Computer and Communication, vol. 2, no. 2, 2013.
[192] A. V. Kramarenko and U. Tan, “Effects of high-frequency electromag-
netic fields on human eeg: a brain mapping study,” International Journal
of Neuroscience, vol. 113, no. 7, pp. 1007–1019, 2003.
[193] C. M. Krause, L. Sillanmäki, M. Koivisto, A. Häggqvist, C. Saarela,
A. Revonsuo, M. Laine, and H. Hämäläinen, “Effects of electromagnetic
field emitted by cellular phones on the eeg during a memory task,” Neu-
roreport, vol. 11, no. 4, pp. 761–764, 2000.
[194] J. C. Doyle, R. Ornstein, and D. Galin, “Lateral specialization of cogni-
tive mode: Ii. eeg frequency analysis,” Psychophysiology, vol. 11, no. 5,
pp. 567–578, 1974.
[195] N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iversen, B. Kotchoubey,
A. Kübler, J. Perelmouter, E. Taub, and H. Flor, “A spelling device for
the paralysed,” Nature, vol. 398, no. 6725, pp. 297–298, 1999.
189
[196] H. Jokeit and S. Makeig, “Different event-related patterns of gamma-
band power in brain waves of fast-and slow-reacting subjects,” Proceed-
ings of the National Academy of Sciences, vol. 91, no. 14, pp. 6339–6343,
1994.
[197] “Real-time applications in control and communications.” http:
//catalog.rpi.edu/preview_course_nopop.php?catoid=11&coid=
18464. Accessed: 2014.
[198] E. Niedermeyer and F. L. da Silva, Electroencephalography: basic prin-
ciples, clinical applications, and related fields. Lippincott Williams &
Wilkins, 2005.
[199] K. V. Mardia, “Measures of multivariate skewness and kurtosis with
applications,” Biometrika, vol. 57, no. 3, pp. 519–530, 1970.
[200] J. C. de Munck, S. I. Gonçalves, T. J. Faes, J. P. Kuijer, P. J. Pouwels,
R. M. Heethaar, and F. L. da Silva, “A study of the brain’s resting state
based on alpha band power, heart rate and fmri,” Neuroimage, vol. 42,
no. 1, pp. 112–121, 2008.
[201] L. Goldstein, A. A. Sugerman, M. H. Stolberg, H. B. Murphree, and C. C.
Pfeiffer, “Electro-cerebral activity in schizophrenics and non-psychotic
subjects: Quantitative eeg amplitude analysis,” Electroencephalography
and clinical neurophysiology, vol. 19, no. 4, pp. 350–361, 1965.
190
[202] M. Kaibara, G. M. Holloway, and G. B. Young, Blume’s Atlas of Pedi-
atric and Adult Electroencephalography. Lippincott Williams & Wilkins,
2010.
[203] R. J. Davidson, D. C. Jackson, and C. L. Larson, “Human electroen-
cephalography,” Handbook of psychophysiology, vol. 2, pp. 27–52, 2000.
[204] P. Mirowski, D. Madhavan, Y. LeCun, and R. Kuzniecky, “Classifica-
tion of patterns of eeg synchronization for seizure prediction,” Clinical
neurophysiology, vol. 120, no. 11, pp. 1927–1940, 2009.
[205] W. C. Dement, Some must watch while some must sleep, vol. 37. San
Francisco Book Co., 1976.
[206] J. R. Plant, “Biopsychology (4th edn.), by pj pinel, allyn & bacon, need-
ham heights, ma, 2000. isbn 0-205-28992-4; 544 pp.,” 2000.
[207] I. Miller and R. A. Miller, “The schumann’s resonances and human psy-
chobiology,” Nexus Magazine, vol. 10, no. 3, pp. 43–49, 2003.
[208] B. J. Baars and N. M. Gage, Cognition, brain, and consciousness: In-
troduction to cognitive neuroscience. Academic Press, 2010.
[209] F. H. Duffy, V. G. Iyer, and W. W. Surwillo, Clinical electroencephalog-
raphy and topographic brain mapping: Technology and practice. Springer
Science & Business Media, 2012.
[210] B. Gawronski and G. V. Bodenhausen, Theory and explanation in social
psychology. Guilford Publications, 2014.
191
[211] M. P. Walker and R. Stickgold, “Sleep-dependent learning and memory
consolidation,” Neuron, vol. 44, no. 1, pp. 121–133, 2004.
[212] T. Yamada and E. Meng, Practical guide for clinical neurophysiologic
testing: EEG. Lippincott Williams & Wilkins, 2012.
[213] M. S. Livingstone and D. H. Hubel, “Anatomy and physiology of a color
system in the primate visual cortex,” J Neurosci, vol. 4, no. 1, pp. 309–
356, 1984.
[214] S. P. Springer and G. Deutsch, Left brain, right brain: Perspectives from
cognitive neuroscience . WH Freeman/Times Books/Henry Holt & Co,
1998.
[215] J. Goutsias, L. Vincent, and D. S. Bloomberg, Mathematical morphology
and its applications to image and signal processing, vol. 18. Springer
Science & Business Media, 2006.
[216] D. Girton and J. Kamiya, “A simple on-line technique for removing eye
movement artifacts from the eeg,” Electroencephalography and clinical
Neurophysiology, vol. 34, no. 2, pp. 212–216, 1973.
[217] J. Barlow and A. Remond, “Eye movement artifact nulling in eegs by
multichannel on-line eog subtraction,” Electroencephalography and clin-
ical neurophysiology, vol. 52, no. 5, pp. 418–423, 1981.
[218] C. A. Joyce, I. F. Gorodnitsky, and M. Kutas, “Automatic removal of
eye movement and blink artifacts from eeg data using blind component
separation,” Psychophysiology, vol. 41, no. 2, pp. 313–325, 2004.
192
[219] S. Makeig, A. J. Bell, T.-P. Jung, T. J. Sejnowski, et al., “Independent
component analysis of electroencephalographic data,” Advances in neural
information processing systems, pp. 145–151, 1996.
[220] R. Cooper, J. W. Osselton, and J. C. Shaw, EEG technology.
Butterworth-Heinemann, 2014.
[221] G. Pfurtscheller and F. L. Da Silva, “Event-related eeg/meg synchroniza-
tion and desynchronization: basic principles,” Clinical neurophysiology,
vol. 110, no. 11, pp. 1842–1857, 1999.
[222] J. R. Wolpaw, D. J. McFarland, and T. M. Vaughan, “Brain-computer
interface research at the wadsworth center,” Rehabilitation Engineering,
IEEE Transactions on, vol. 8, no. 2, pp. 222–226, 2000.
[223] A. Schlogl and C. Brunner, “Biosig: a free and open source software
library for bci research,” Computer, vol. 41, no. 10, pp. 44–50, 2008.
[224] G. Schalk, D. J. McFarland, T. Hinterberger, N. Birbaumer, and J. R.
Wolpaw, “Bci2000: a general-purpose brain-computer interface (bci) sys-
tem,” Biomedical Engineering, IEEE Transactions on, vol. 51, no. 6,
pp. 1034–1043, 2004.
[225] Y. Renard, F. Lotte, G. Gibert, M. Congedo, E. Maby, V. Delannoy,
O. Bertrand, and A. Lécuyer, “Openvibe: an open-source software plat-
form to design, test, and use brain-computer interfaces in real and virtual
environments,” Presence: teleoperators and virtual environments, vol. 19,
no. 1, pp. 35–53, 2010.
193
[226] C. A. Kothe and S. Makeig, “Bcilab: a platform for brain–computer
interface development,” Journal of neural engineering, vol. 10, no. 5,
p. 056014, 2013.