Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Feb 20, 2026

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.9K

Bayesian multi-subject factor analysis to predict microsleeps from EEG power spectral features.

Reza Shoorangiz, Stephen J Weddell, Richard D Jones

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |October 25, 2017
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Altered cerebrovascular haemodynamics in Parkinson's disease: Insights from 4D flow MRI.

    NPJ Parkinson's disease·2026
    Same author

    Magnetic Resonance Imaging as a Readout of CLN5 Gene Therapy Efficacy in Sheep.

    Brain and behavior·2025
    Same author

    The New Zealand Parkinson's progression programme.

    Journal of the Royal Society of New Zealand·2024
    Same author

    Conscious but not thinking-Mind-blanks during visuomotor tracking: An fMRI study of endogenous attention lapses.

    Human brain mapping·2024
    Same author

    Cerebral perfusion is not impaired in persons with moderate obstructive sleep apnoea when awake.

    Sleep & breathing = Schlaf & Atmung·2024
    Same author

    Direct wavefront reconstruction with the cone wavefront sensor using the inverse radon transform.

    Applied optics·2023

    Predicting imminent microsleeps using electroencephalography (EEG) data is crucial for safety. A novel Bayesian algorithm shows promise in identifying pre-microsleep patterns to forecast these events, though precision requires further improvement.

    Area of Science:

    • Neuroscience
    • Machine Learning
    • Signal Processing

    Background:

    • Microsleeps are brief, unintentional episodes of unconsciousness.
    • Predicting microsleeps can prevent accidents and save lives.
    • Electroencephalography (EEG) data offers insights into pre-microsleep brain activity.

    Purpose of the Study:

    • To develop and evaluate a novel Bayesian algorithm for predicting imminent microsleeps.
    • To identify common pre-microsleep patterns in EEG data across subjects.
    • To achieve early prediction of microsleep events.

    Main Methods:

    • Utilized EEG data from 8 subjects.
    • Developed a Bayesian algorithm with sparsity-promoting priors to identify common EEG components.
    • Employed variational Bayesian methods for posterior probability approximation.

    More Related Videos

    Quantifying Infra-slow Dynamics of Spectral Power and Heart Rate in Sleeping Mice
    10:56

    Quantifying Infra-slow Dynamics of Spectral Power and Heart Rate in Sleeping Mice

    Published on: August 2, 2017

    10.6K
    Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
    06:40

    Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

    Published on: June 15, 2018

    10.8K

    Related Experiment Videos

    Last Updated: Feb 20, 2026

    Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
    04:13

    Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

    Published on: November 13, 2019

    12.9K
    Quantifying Infra-slow Dynamics of Spectral Power and Heart Rate in Sleeping Mice
    10:56

    Quantifying Infra-slow Dynamics of Spectral Power and Heart Rate in Sleeping Mice

    Published on: August 2, 2017

    10.6K
    Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
    06:40

    Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

    Published on: June 15, 2018

    10.8K
  • Extracted EEG log-power spectral features from 5-second windows.
  • Used Bayesian multi-subject factor analysis for dimensionality reduction.
  • Applied Linear Discriminant Analysis (LDA) for classification.
  • Evaluated performance using leave-one-subject-out cross-validation.

    • Main Results:

    • The proposed method achieved an Area Under the Receiver Operating Characteristic curve (AUC_ROC) of 0.90.
    • A Geometric Mean (GM) of 0.80 was achieved.
    • The system demonstrated a precision of 0.29 for microsleep prediction.
    • Identified common components of pre-microsleep activity across subjects.

    Conclusions:

    • The Bayesian algorithm shows potential for predicting microsleeps 0.25 seconds in advance.
    • The model effectively identifies common pre-microsleep EEG patterns.
    • While AUC_ROC and GM are promising, precision needs enhancement for practical application.