+ All Categories
Home > Documents > 1 Classification of Sleep EEG_GERLA

1 Classification of Sleep EEG_GERLA

Date post: 14-Apr-2018
Category:
Upload: iqbalslimboy
View: 216 times
Download: 0 times
Share this document with a friend

of 21

Transcript
  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    1/21

    Classification of Sleep EEGVclav Gerla ([email protected])

    Gerstner laboratory, Department of CyberneticsTechnick 2, 166 27 Prague, Czech Republic

    Faculty of Electrical Engineering, Czech Technical University in Prague

    - Stages of Sleep

    - Sleep Disorders- Measuring Sleep in the Laboratory

    - Brain Wave Frequencies

    - Artifacts

    - Sleep stages analysis

    mailto:[email protected]:[email protected]:[email protected]:[email protected]
  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    2/21

    Stages of Sleep, Hypnogram

    1. Wake (wakefulness, waking stage)

    2. REM (Rapid Eye Movements) // dreams3. NREM 1 (shallow/drowsy sleep)

    4. NREM 2 (light sleep)

    5. NREM 3 (deepening sleep)

    6. NREM 4 (deepest sleep)

    Hypnogram:

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    3/21

    Sleep DisordersHeadaches

    Insomnia (sleep - -)

    - difficulty falling asleep- waking up frequently during the night

    - waking up too early in the morning

    - unrefreshing sleep

    Sleepiness (sleep + +)

    - fall asleep while driving

    - concentrating at work, school, or home

    - have difficulty remembering

    Restless Legs Syndrome

    - sensations of discomfort in the legs during periods of inactivity

    Narcolepsy

    - sudden and irresistible onsets of sleep during normal waking hours

    Sleep apnea

    REM sleep disorders

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    4/21

    Proportion of REM/NREM stages

    0

    5

    10

    15

    20

    25

    30

    3540

    3 18 40 70

    REM

    NREM(3+4)

    age (years)

    %

    The decrease of NREM sleeping is caused partially by decrease of delta waves.

    (does not meet criteria for delta waves)

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    5/21

    Measuring Sleep in the Laboratory

    Electroencephalogram (EEG): Measures electrical activity of the brain.

    Electrooculogram (EOG): Measures eye movements. An electrode placed near the eye

    will record a change in voltage as the eye moves.

    Electromyogram (EMG): Measures electrical activity of the muscles. In humans, sleep

    researchers usually record from under the chin, as this area undergoes dramatic

    changes during sleep.

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    6/21

    EEG signal example19 EEG signals, EKG signal (+50 Hz artifact)

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    7/21

    Brain Wave Frequencies

    Delta (0.1 to 3 Hz)

    deep / dreamless sleep, non-REM sleep

    Theta (4-8 Hz)

    connection with creativity, intuition, daydreaming, fantasizing

    Alpha (8-12 Hz)relaxation, mental work - thinking or calculating

    Beta (above 12 Hz)

    normal rhythm, absent or reduced in areas of cortical damage

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    8/21

    Binaural Beat Frequencies

    Example of frequencies: // sporadic

    0.15-0.3 Hz - depression4.5-6.5 Hz - wakeful dreaming, vivid images

    4-8 Hz - dreaming sleep, deep meditation, subconscious mind

    5.0-10.0 Hz - relaxation

    5.8 Hz - dizziness

    7 Hz - increased reaction time

    7.83 Hz - earth resonance

    8.6-9.8 Hz - induces sleep, tingling sensations

    15.0-18.0 Hz - increased mental ability

    18 Hz - significant improvements in memory

    55 Hz - Tantric yoga

    LEFT EAR70Hz

    RIGHT EAR74Hz

    Binaural Beat 4Hz

    Brain Wave Generator: http://www.BWgen.com

    http://www.bwgen.com/http://www.bwgen.com/http://www.bwgen.com/http://www.bwgen.com/
  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    9/21

    Stage Wake

    EEG: - rhythmic alpha waves (8-12Hz) // only if the eyes are closed

    - beta waves (20-30Hz)

    EOG: - eye movement (observation process)

    EMG: - continual tonically activity of muscles

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    10/21

    Stage REM

    EEG: - relatively low voltage

    - mixed frequency

    EOG: - contains rapid eye movements

    EMG: - tonically suppressed (Sleep Paralysis)

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    11/21

    Stage NREM 1(shallow/drowsy sleep)

    EEG: - the absence of alpha activity

    - Vertex sharp waves

    EOG: - slow eye movement

    EMG: - relatively lower amplitude

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    12/21

    Stage NREM 2 (light sleep)

    EEG: - sleep spindles (oscillating with the frequency between 12-15 Hz)

    - K-complexes (high voltage, sharp rising and sharp falling wave)

    - relatively low voltage mixed frequency

    EOG: - the absence eye movements

    EMG: - constant tonic activity

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    13/21

    Stage NREM 3 (deepening sleep)

    EEG: - consists of high-voltage (>=75uV)

    - slow delta activity (

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    14/21

    Stage NREM 4 (deepest sleep)

    As NREM 3 + delta activity duration more than 50% for epoch

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    15/21

    Artifacts

    Other artifacts:

    Muscle artifacts:

    - Eye Flutter, slow and rapid eye movements

    - ECG artifact- Sweat artifact

    - Metal contact (touching metal during recording)

    - Salt Bridge (between two electrodes)

    - Static electricity artifact

    - Glossokinetic (movements of tongue)

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    16/21

    System Structure

    reduce data quantity

    (speeds up total computing time)

    divide signal into 1 second segments

    compute mean power density in

    individual frequency bands for each

    segment

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    17/21

    Feature ExtractionHypnogram (rate by expert)

    1Hz

    29 Hz

    .

    Powerspectraldensity

    EEG (Fpz-Cz)

    EEG (Pz-Oz)

    Spectrogram:

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    18/21

    Feature Normalization

    The features contain

    great number of peaks

    -> normalization

    NREM4 stage detection: Wake stage detection:

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    19/21

    Decision RulesSearching suitable decision rules:

    - convert all features of all patients to the Weka format.- Weka (http://www.cs.waikato.ac.nz/ml/weka) is a collection

    of machine learning algorithmus contains tools for data-

    preprocessing, classification, regression, clustering,

    association rules and visualization

    The most significant found rules:EEG 16-30Hz > 20%

    EEG 0.5-3Hz > 85%

    EEG 0.5-3Hz > 65%

    WAKE

    S4

    S3

    EEG 13-15Hz < 15%

    and

    EOG 0.15-1.2Hz > 50%

    EEG 13-15Hz > 20%

    REM

    S2

    EEG 13-15Hz > 10%S1

    true

    false

    true

    false

    http://www.cs.waikato.ac.nz/ml/wekahttp://www.cs.waikato.ac.nz/ml/weka
  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    20/21

    Markov models (utilization of time-dependence)

    Aplication to segments which:

    - all rules are false- more rules are true

    Markov models use

    - contextual information in EEG signa

    - approximate knowledge of transitionsprobability

  • 7/27/2019 1 Classification of Sleep EEG_GERLA

    21/21

    Results

    - Final classification accuracy approximately 80%

    - Problem with detection S1 stage


Recommended