INTRODUCTION:- For generations, humans have fantasized about the ability to communicate and interact with machines through thought alone or to create devices that can peer into person’s mind and thoughts. These ideas have captured the imagination of humankind in the form of ancient myths and modern science fiction stories. However, it is only recently that advances in cognitive neuroscience and brain imaging technologies have started to provide us with the ability to interface directly with the human brain. This ability is made possible through the use of sensors that can monitor some of the physical processes that occur within the brain that correspond with certain forms of thought. Primarily driven by growing societal recognition for the needs of people with physical disabilities, researchers have used these technologies to build brain computer interfaces (BCIs), communication systems that do not depend on the brain’s normal output pathways of peripheral nerves and muscles. Direct brain - computer interfaces (BCI) is a developing field that has been adding this new dimension of functionality to HCI (Human Computer Interaction). BCI has created a novel communication channel, especially for those users who are unable to generate necessary muscular movements to use typical HCI devices. WHAT IS BCI:- A Brain–Computer Interface (BCI), often called a Mind-Machine Interface (MMI), or sometimes called a Direct Neural Interface (DNI), Synthetic Telepathy Interface (STI) or a Brain–Machine Interface (BMI), is a direct communication pathway between the brain and an external device. In other words, Brain-computer interface (BCI) is a collaboration between a brain and a device that enables signals from the brain to direct some external activity, such as control of a cursor or a prosthetic limb. The interface enables a direct communications pathway between the brain and the object to be controlled. BCIs are often directed at assisting, augmenting, or repairing human cognitive or sensory-motor functions. In the case of cursor control, for example, the signal is transmitted directly from the brain to the
Transcript
INTRODUCTION:-
For generations, humans have fantasized about the ability to communicate and
interact with machines through thought alone or to create devices that can peer into
person’s mind and thoughts. These ideas have captured the imagination of
humankind in the form of ancient myths and modern science fiction stories.
However, it is only recently that advances in cognitive neuroscience and brain
imaging technologies have started to provide us with the ability to interface
directly with the human brain. This ability is made possible through the use of
sensors that can monitor some of the physical processes that occur within the brain
that correspond with certain forms of thought.
Primarily driven by growing societal recognition for the needs of people with
physical disabilities, researchers have used these technologies to build brain
computer interfaces (BCIs), communication systems that do not depend on the
brain’s normal output pathways of peripheral nerves and muscles. Direct brain-
computer interfaces (BCI) is a developing field that has been adding this new
dimension of functionality to HCI (Human Computer Interaction). BCI has created
a novel communication channel, especially for those users who are unable to
generate necessary muscular movements to use typical HCI devices.
WHAT IS BCI:-
A Brain–Computer Interface (BCI), often called a Mind-Machine Interface (MMI),
or sometimes called a Direct Neural Interface (DNI), Synthetic Telepathy Interface
(STI) or a Brain–Machine Interface (BMI), is a direct communication pathway
between the brain and an external device. In other words, Brain-computer interface
(BCI) is a collaboration between a brain and a device that enables signals from the
brain to direct some external activity, such as control of a cursor or a prosthetic
limb. The interface enables a direct communications pathway between the brain
and the object to be controlled. BCIs are often directed at assisting, augmenting, or
repairing human cognitive or sensory-motor functions. In the case of cursor
control, for example, the signal is transmitted directly from the brain to the
mechanism directing the cursor, rather than taking the normal route through the
body's neuromuscular system from the brain to the finger on a mouse.
The potential of BCI systems for helping handicapped people is obvious. In these
systems, users explicitly manipulate their brain activity instead of using motor
movements to produce signals that can be used to control computers or
communication devices. The reason a BCI works at all is because of the way our
brains function. Our brains are filled with neurons, individual nerve cells
connected to one another by dendrites and axons. Every time we think, move, feel
or remember something, our neurons are at work. That work is carried out by small
electric signals that zip from neuron to neuron as fast as 250 mph. The signals are
generated by differences in electric potential carried by ions on the membrane of
each neuron.
Although the paths the signals take are insulated by something called myelin, some
of the electric signal escapes. Scientists can detect those signals, interpret what
they mean and use them to direct a device of some kind. It can also work the other
way around. For example, researchers could figure out what signals are sent to the
brain by the optic nerve when someone sees the color red. They could rig a camera
that would send those exact signals into someone's brain whenever the camera saw
red, allowing a blind person to "see" without eyes.
Working Principle of BCI
There are several computer interfaces designed for disabled people. Most of these
systems, however, require some sort of reliable muscular control such as neck,
head, eyes, or other facial muscles. It is important to note that although requiring
only neural activity, BCI utilizes neural activity generated voluntarily by the user.
Interfaces based on involuntary neural activity, such as those generated during an
epileptic seizure, utilize many of the same components and principles as BCI, but
are not included in this field. BCI systems, therefore, are especially useful for
severely disabled, or locked-in, individuals with no reliable muscular control to
interact with their surroundings.
HISTORY OF BCI:-
The history of brain–computer interfaces (BCIs) starts with Hans Berger's
discovery of the electrical activity of the human brain and the development of
electroencephalography (EEG). In 1924 Berger was the first to record human brain
activity by means of EEG. Berger was able to identify oscillatory activity in the
brain by analyzing EEG traces. Following the work of Hans Berger in 1929 on a
device that later came to be known as Electro Encephalogram (EEG), which could
record electrical potentials generated by brain activity, there was speculation that
perhaps devices could be controlled by using these signals.
HANS BERGER BERGER’S PATIENT
For a long time, however, this remained a speculation. As reviewed by Wolpaw
and colleagues, 40 years later, in the 1970s, researchers were able to develop
primitive control systems based on electrical activity recorded from the head. The
Pentagon's Defence Advanced Research Projects Agency (DARPA), the same
agency involved in developing the first versions of the Internet, funded research
focused on developing bionic devices that would aid soldiers. Early research,
conducted by George Lawrence and coworkers, focused on developing techniques
to improve the performance of soldiers in tasks that had high mental loads. His
research produced a lot of insight on methods of autoregulation and cognitive
biofeedback, but did not produce any usable devices.
DARPA logo
DARPA expanded its focus toward a more general field of biocybemetics. The
goal was to explore the possibility of controlling devices through the real-time
computerized processing of any biological signal. Jacques Vidal from UCLA's
Brain-Computer Interface Laboratory provided evidence that single-trial visual-
evoked potentials could be used as a communication channel effective enough to
control a cursor through a two-dimensional maze.
Work by Vidal and other groups proved that signals from brain activity could be
used to effectively communicate a user's intent. It also created a clear-cut
separation between those systems utilizing EEG activity and those that used EMG
(electromyogram) activity generated from scalp or facial muscular movements.
Future work expanded BCI systems to use neural activity signals recorded not only
by EEG but also by other imaging techniques.
At the European Research and Innovation Exhibition in Paris in June 2006,
American scientist Peter Brunner composed a message simply by concentrating on
a display. Brunner wore a close-fitting (but completely external) cap fitted with a
number of electrodes. Electroencephalographic (EEG) activity from Brunner's
brain was picked up by the cap's electrodes and the information used, along with
software, to identify specific letters or characters for the message.
The BCI Brunner demonstrated is based on a method called the Wadsworth
system. Like other EEG-based BCI technologies, the Wadsworth system uses
adaptive algorithm s and pattern-matching techniques to facilitate communication.
Both user and software are expected to adapt and learn, making the process more
efficient with practice.
Peter Brunner
During the presentation, a message was displayed from an American
neurobiologist who uses the system to continue working, despite suffering from
amyotrophic lateral sclerosis (Lou Gehrig's disease). Although the scientist can no
longer move even his eyes, he was able to send the following e-mail message: "I
am a neuroscientist wHo (sic) couldn't work without BCI. I am writing this with
my EEG courtesy of the Wadsworth Center Brain-Computer Interface Research
Program."
BASIC COMPONENTS OF BCI:-
To understand the requirements of basic research in BCI, it is important to put it in
the context of the entire BCI system. The recent work of Mason and Birch (2003),
which is adapted in this section, presented a general functional model for BCI
systems upon which a universal vocabulary could be developed and different BCI
systems could be compared in a unified framework. The goal of a BCI system is to
allow the user to interact with the device. This interaction is enabled through a
variety of intermediary functional components, control signals, and feedback loops
as detailed in the following figure. Intermediary functional components perform
specific functions in converting intent into action. By definition, this means that
the user and the device are also integral parts of a BCI system. Interaction is also
made possible through feedback loops that serve to inform each component in the
system of the state of one or more components.
Functional components and feedback loops in a brain-computer interface system
The user's brain activity is measured by the electrodes and then amplified and
signal-conditioned by the amplifier. The feature extractor transforms raw signals
into relevant feature vectors, which are classified into logical controls by the
feature translator. The control interface converts the logical controls into semantic
controls that are passed onto the device controller. The device controller changes
the semantic controls into physical device-specific commands that are executed by
the device. The BCI system, therefore, can convert the user's intent into device
action.
A notable experiment has been conducted by Nicolelis and Chapin (2002) on
monkeys to control a robot arm in real time by electrical discharge recorded by
microwires that lay beside a single motor neuron. Various motor-control
parameters, including the direction of hand movement, gripping force, hand
velocity, acceleration, three-dimensional position, etc., were derived from the
parallel streams of neuronal activity by mathematic models. In this system,
monkeys learn to produce complex hand movements in response to arbitrary
sensory cues. The monkeys could exploit visual feedback to judge for themselves
how well the robot could mimic their hand movements. Refer to following figure
for a detailed description.
Experimental design used to test a closed-loop control brain-machine interface for motor control in macaque
monkeys.
Chronically implanted microwire arrays are used to sample the extracellular
activity of populations of neurons in several cortical motor regions. Linear and
nonlinear real-time models are used to extract various motor-control signals from
raw brain activity. The outputs of these models are used to control the movements
of a robot arm. For instance, while one model might provide a velocity signal to
move the robot arm, another model, running in parallel, might extract a force
signal that can be used to allow a robot gripper to hold an object during an arm
movement. Artificial visual and tactile feedback signals are used to inform the
animal about the performance of a robot arm controlled by brain-derived signals.
Visual feedback is provided by using a moving cursor on a video screen to inform
the animal about the position of the robot arm in space. Artificial tactile and
proprioceptive feedback is delivered by a series of small vibromechanical elements
attached to the animal's arm. This haptic display is used to inform the animal about
the performance of the robot arm gripper (whether the gripper has encountered an
object in space, or whether the gripper is applying enough force to hold a particular
object). ANN, artificial neural network; LAN, local area network.
TECHNIQUES:-
INVASIVE TECHNIQUE:-
In a different system, individual electrodes in the Utah electrode are tapered to a
tip, with diameters <90 (xm at their base, and they penetrate only 1-2 mm into the
brain. Invasive techniques cause significant amount of discomfort and risk to the
patient. Researchers use them in human subjects only if it will provide
considerable improvement in functionality over available noninvasive methods. A
majority of the initial research, therefore, is conducted in animals, especially
monkeys and rats, and is also called the brain-machine interface (BMI). Research
in these animals has led to the rapid development of microelectronics that enables
recording electrophysiological activities from a small group of neurons or even a
single neuron. Present technology allows reliable simultaneous sampling of 50-200
neurons, distributed across multiple cortical areas of small primates, for a period of
a few years.
Recording brain activity using invasive signal acquisition methods
Cone-shaped glass electrodes are implanted through the skull and directly into
specific neurons in the brain. The electrode is filled with a neurotrophic factor that
causes neurites to grow into the cone and contact one of the gold wires that
transmits the electrical activity to the receiver unit outside the head and then
amplified and transmitted to the BCI control using a transmitter.
The advantage of these types of invasive techniques is the high spatial and
temporal resolution that can be achieved, as recordings can be made from
individual neurons at very high sampling rates. Intracranially recorded signals
could obtain more information and allow quicker responses, which might lead to
decreased requirements of training and attention (Sanchez et al, 2004). Several
issues, however, have to be considered (Lauer et al, 2000). First, the long-term
stability of the signal over days and years is hard to achieve. The user should be
able to consistently generate the control signal reliably without the need for
frequent retuning. Second is the issue of cortical plasticity following a spinal cord
injury. It has been hypothesized that the motor cortex undergoes reorganization
after a spinal cord injury, but the degree is unknown (Brouwer and Hopkins-
Rosseel, 1997). Finally, if a neuroprosthesis that requires a stimulus to the disabled
limb is used, this stimulus would also produce a significant artifact on the scalp
that might interfere with the signal of interest.
NON-INVASIVE TECHNIQUE:-
There are many methods of measuring brain activity through noninvasive means.
Noninvasive techniques reduce risk for users since they do not require surgery or
permanent attachment to the device. Techniques such as computerized tomography
(CT), positron electron tomography (PET), single-photon emission computed
tomography (SPECT), magnetic resonance imaging (MRI), functional magnetic
resonance imaging (fMRI), magnetoencephalography (MEG), and
electroencephalography (EEG) have all been used to measure brain activity
noninvasively.
Many EEG-based BCI systems use an electrode placement strategy suggested by
the International 10/20 system as detailed in following figure. For better spatial
resolution, it is also common to use a variant of the 10/20 system that fills in the
spaces between the electrodes of the 10/20 system with additional electrodes.
Placement of electrodes for noninvasive signal acquisition using an electroencephalogram (EEG)
This standardized arrangement of electrodes over the scalp is known as the
International 10/20 system and ensures ample coverage of all parts of the head.
The exact positions for each electrode are at the intersection of the lines calculated
from measurements between standard skull landmarks. The letter at each electrode
temporal lobe; C, central lobe; P, parietal lobe; O, occipital lobe). The number or
the second letter identifies its hemispherical location (Z, denoting line zero refers
to an electrode placed along the cerebrum's midline; even numbers represent the
right hemisphere; odd numbers represent the left hemisphere. The numbers are in
ascending order with increasing distance from the midline).
NOTE: Signals captured through invasive or noninvasive methods contain
a lot of noise. The first step in feature extraction and translation is to remove
noise. This is followed by selection of relevant features through several
feature extraction techniques that focus on maximizing the signal-to-noise
ratio. Finally, feature translation techniques are used to classify the relevant
features into one of the possible states. This is illustrated in following figure:
Processing steps required to convert user's intent, encoded in the raw signal, into device action
BCI APPLICATION:-
BCI applications can be broadly classified in two main categories, i.e., Non-
medical applications, and Medical applications.
NON-MEDICAL APPLICATION:
BCIs have a wide range of applications that can be beneficial for users who do not
necessarily have a medical indication to use one. This section provides an
overview of seven (high-level) application areas and a few examples within each
area.
1. DEVICE CONTROL:
One of the driving forces behind the development of BCIs was the desire to
give users who lack full control of their limbs access to devices and
communication systems. Under these circumstances, users can already
benefit from a device even if it has limited speed, accuracy and efficiency.
For healthy users that have full muscular control, a BCI currently cannot act
as a competitive source of control signals due to its limitation in bandwidth
and accuracy. Also, the generation of control signals and the extraction of
these from the brain signals may cause latency in the control loop of several
hundreds of milliseconds or more that makes smooth closed-loop control
impossible. The introduction of a form of shared control between the device
and the user in which the latter gives more high level, open-loop commands
may overcome the latency issue. However, it is possible, that healthy users
could – for limited application scenarios – also benefit from either
additional control channels or hands-free control. Examples include drivers,
divers, and astronauts who need to keep their hands on the steering wheel,
to swim, or to operate equipment. Brain-based control paradigms are
developed for these applications in addition to, for instance, voice control.
This field has a strong body of research work on single task situations and
for patient users but lacks data on control in multi-task environments and
for healthy users. Also, the surplus value over other hands-free input
modalities such as voice or eye movement control must be shown.
2. USER STATE MODELLING:
The future generation user-system interfaces need to be able to understand
and anticipate user’s state and user’s intentions. For instance, automobiles
will react to driver drowsiness and virtual humans could convince users to
follow their diet. These future implementations of so-called usersystem-
symbiosis or affective computing [4] require systems to gather and interpret
information on mental states such as emotions, attention, workload, fatigue,
stress, and mistakes. Another application field is the use of BCIs as a
research tool in neuroscientific research. Compared to slower, lab-based
functional imaging methods it can monitor the acting brain in real time and
in the real world and thus help to understand the role of functional networks
during behavioural tasks. Brain-based indices of these user states are
extending physiological measures like heart rate variability and skin
conduction and are thus complimentary to and not so much in competition
with existing technology. There is a limited but fast growing body of
knowledge for these applications and a very high societal impact and
economic viability. High-end applications for e.g. air traffic controllers and
professional drivers (i.e., driver drowsiness detectors) are seriously
investigated and may have good spinoffs for the general public. Better user
interfaces can have an important contribution to societal challenges such as
providing access to electronic systems and services for all (including the
aging population and people with cognitive challenges), a healthy life style
and (traffic) safety.
3. EVALUATION:
Evaluation applications can be used in an online fashion (by constant
monitoring) and an offline fashion. Neuromarketing and neuroergonomics
are two evaluation examples. Neuroergonomics has a clear link to Human-
Computer Interaction: it evaluates how well a technology matches human
capabilities and limitations. An illustrative example is the recent research on
cell phone use during driving: brain-imaging results show that even hands-
free or voice activated use of a mobile phone is as dangerous as being
under the influence of alcohol during driving. The body of evidence in this
area is mainly based on fundamental neuroscientific studies and would
benefit from a transition to more applied studies. The societal impact is rated
low; it is merely a tool that adds to current evaluation tools but has no direct
contribution to solving societal issues. The economic viability is potentially
high: design and evaluation are relevant for many services and products
(e.g., electronics, food, buildings). These methods should prove their added
value over for instance questionnaires.
4. TRAINING:
Most aspects of training are related to the brain and its plasticity. Measuring
this plasticity and changes in the brain can help to improve training methods
in general and an individual’s training schedule in particular. With respect to
the latter, indicators such as learning state and rate of progress (novice /
expert) are useful for automated training systems and virtual instructors.
Currently, this application area is in a conceptual phase with limited
experimental evidence. However, (permanent) education (also known as
lifelong learning) and the need for efficient and effective (automated)
tutoring systems have a good societal as well as economic impact, especially
for societies with a knowledge-based economy, facing an aging population
and/or requiring a flexible workforce. Applications may be both in a
professional environment and for home use, making the price sensitivity
difficult to rate.
5. GAMING AND ENTERTAINMENT:
The entertainment industry is often front runner in introducing new concepts
and paradigms; among others in human-computer interaction for consumers
(recent examples are 3D movies at home and gesture-based game
controllers). Over the past few years, new games have been developed that
are exclusively for use with a EEG headset by companies like Neurosky,
Emotiv, Uncle Milton, MindGames, and Mattel. Additional, there is a
general conviction that experiences of existing game and entertainment
systems are enriched, intensified and/or extended by using BCIs, for
example by tailoring games to the affective state of the user (immersion,
flow, frustration, surprise etc.). For instance, several game designers linked
mental states to the popular game World of Warcraft® so that the
appearance of an avatar is no longer controlled through the keyboard, but
reflects the mental state of the gamer. The first (mass) application of non-
medical BCIs may actually be in the field of gaming/entertainment where
the first stand-alone examples came to the market in 2009 and a broadening
to console games may follow soon. We expect that successful applications
will be based on state monitoring and not on the user directly controlling the
game (although this can add a new fun factor to existing games). Although
BCIs for gaming were suggested a decade ago, the research basis is still
small but growing rapidly in a mainly application-driven manner and not
theory. The societal impact is judged low, but the economic viability is very
high (according to a survey held by GameStrata - the leading online
community for gamers - in 2008, an average North American gamer
spends more than $30,500 on games and gaming hardware over their peak
gaming years between 18 and 48). The price sensitivity is very high, with
important requirements with regard to ease of use, amongst others.
6. COGNITIVE IMPROVEMENT:
Some argue that improvement of cognitive performance is an everyday
reality, for instance through the use of coffee or tea. However, the debate
about cognitive enhancement has gained importance, amongst others
through the increased use of prescription drugs like Modafinil and Ritalin
without a medical indication, by both students and professional workers.
BCIs are also considered a means to improve cognitive functioning of
healthy users. Neurofeedback training (brain activity alteration through
operant conditioning), for instance to improve attention, working memory,
and executive functions is relatively common among healthy users. Another
potential application area is the optimized presentation of learning content.
Although there is currently lack of good experimental data on its
effects, the effect size is probably small and limited to specific cognitive
tasks. Generally, there may be a thin line between medical and non-medical
use of neurofeedback.
7. SAFETY & SECURITY:
EEG alone or combined EEG and eye movement data of expert observers
could support the detection of deviant behaviour and suspicious objects. In
an envisioned scenario an observer or multiple observers are watching
CCTV recordings or baggage scans to detect deviant (suspicious or criminal)
behaviour or objects. EEG and eye movements might be helpful to identify
potential targets that may otherwise not be noticed consciously. Also,
images may be inspected much faster than normal (RSVP paradigm). It is
already known that eye fixations as well as event related potentials in the
EEG reflect what is (unconsciously perceived as being) relevant, and that
brain signals indicate relevant pictures in a rapidly presented stream of
images up to 50 images per second. Other applications in this area include
using EEG in lie detection and person identification, but both are under
fierce debate. The body of research shows that this application area can be
considered a niche and the field is still in a concept development phase.
Successful applications can contribute to societal issues, for instance
regarding the safety of main transport hubs. The niche character makes the
economic viability limited and the horizon to application 5-10 years away.
MEIDCAL APPLICATIONS:
Over the past 30 years, many BCI systems have been developed that have targeted
different applications. However, the main goal of all of them is to
translate the intent of the user into an action without using the periphery nerves
and muscles. Because of the number of methods in feature extraction and
translation and the increasing target audience, it became difficult to make a
universal scoring method to compare different systems. However there have been
a few successful trials to make a general framework for BCI design technology.
Researchers at Keim and Aunon developed a BCI system for patients with severe
physical disabilities that enabled them to spell a specific code words. They placed
electrodes on the whole surface of the scalp, enabling the system to detect the
difference in lateralized spectral power levels. Farwell Donchin developed a BCI
system to type words by making the user select letters and words from a display.
The system flashes letters randomly on a 6 by 6 matrix on the screen while the
user thinks about the next letter they want to type. They used the P300 signal
obtained from several electrodes on the scalp to control the BCI system.
Rebsamen et al. developed a brain-controlled wheelchair (The Aware Chair).
They adopted the widely used P300 component method. It was claimed in this
work that users can navigate inside a typical office or hospital with a BCI
controlled wheelchair safely but slowly.
Aware Chair Control Interface
DRAWBACKS & INNOVATORS:
Although we already understand the basic principles behind BCIs, they don't work perfectly. There are several reasons for this:
1. The brain is incredibly complex. To say that all thoughts or actions are the result of
simple electric signals in the brain is a gross understatement. There are about 100 billion neurons in a human brain. Each neuron is constantly sending and receiving
signals through a complex web of connections. There are chemical processes involved as well, which EEGs can't pick up on.
2. The signal is weak and prone to interference. EEGs measure tiny voltage
potentials. Something as simple as the blinking eyelids of the subject can generate much stronger signals. Refinements in EEGs and implants will probably overcome
this problem to some extent in the future, but for now, reading brain signals is like listening to a bad phone connection. There's lots of static.
3. The equipment is less than portable. It's far better than it used to be -- early systems were hardwired to massive mainframe computers. But some BCIs still require a
wired connection to the equipment, and those that are wireless require the subject to carry a computer that can weigh around 10 pounds. Like all technology, this will
surely become lighter and more wireless in the future.
BCI Innovators
A few companies are pioneers in the field of BCI. Most of them are still in the research stages, though a few products are offered commercially.
Neural Signals is developing technology to restore speech to disabled people. An implant in an area of the brain associated with speech (Broca's area) would
transmit signals to a computer and then to a speaker. With training, the subject could learn to think each of the 39 phonemes in the English language and
reconstruct speech through the computer and speaker.
NASA has researched a similar system, although it reads electric signals from
the nerves in the mouth and throat area, rather than directly from the brain. They succeeded in performing a Web search by mentally "typing" the term "NASA" into
Google.
Cyberkinetics Neurotechnology Systems is marketing the BrainGate, a neural
interface system that allows disabled people to control a wheelchair, robotic prosthesis or computer cursor.
Japanese researchers have developed a preliminary BCI that allows the user to control their avatar in the online world Second Life.
CONCLUSION:
A brain–computer interface is a communication and control channel that does not
depend on the brain’s normal output pathways of peripheral nerves and muscles.
At present, the main impetus to BCI research and development is the expectation
that BCI technology will be valuable for those whose severe neuromuscular
disabilities prevent them from using conventional augmentative communication
methods. These individuals include many with advanced amyotrophic lateral
sclerosis (ALS), brainstem stroke, and severe cerebral palsy.
Successful BCI operation requires that the user acquire and maintain a new skill, a
skill that consists not of muscle control but rather of control of EEG or single-unit
activity. BCI inputs include slow cortical potentials, P300 evoked potentials, and
rhythms from sensorimotor cortex, and single unit activity from motor cortex.
Recording methodologies seek to maximize signal-to-noise ratio. Noise consists
of EMG, EOG, and other activity from sources outside the brain, as well as brain
activity different from the specific rhythms or evoked potentials that comprise the
BCI input. A variety of temporal and spatial filters can reduce such noise and
thereby increase the signal-to-noise ratio. BCI translation algorithms include
linear equations, neural networks, and numerous other classification techniques.
