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: Oct 3, 2025

Polygraphic Recording Procedure for Measuring Sleep in Mice
08:45

Polygraphic Recording Procedure for Measuring Sleep in Mice

Published on: January 25, 2016

24.3K

EEG-Based Cross-Subject Driver Drowsiness Recognition With an Interpretable Convolutional Neural Network.

Jian Cui, Zirui Lan, Olga Sourina

    IEEE Transactions on Neural Networks and Learning Systems
    |February 16, 2022
    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

    [Comprehensive Analysis of the Relationship between m6A Methylation Patterns and Immune Microenvironment in Lung Adenocarcinoma].

    Zhongguo fei ai za zhi = Chinese journal of lung cancer·2022
    Same author

    Insight into the surface property modification-enhanced C<sub>3</sub>N<sub>4</sub> performance of photocatalytic nitrogen fixation.

    Chemical communications (Cambridge, England)·2022
    Same author

    A matching algorithm with isotope distribution pattern in LC-MS based on support vector machine (SVM) learning model.

    RSC advances·2022
    Same author

    Facile fabrication of long-chain alkyl functionalized ultrafine reduced graphene oxide nanocomposites for enhanced tribological performance.

    RSC advances·2022
    Same author

    Efficient Metal-Oriented Electrodeposition of a Co-Based Metal-Organic Framework with Superior Capacitive Performance.

    ChemSusChem·2022
    Same author

    Nanophotonic Approach to Study Excited-State Dynamics in Semiconductor Nanocrystals.

    The journal of physical chemistry letters·2022

    This study introduces an interpretable deep learning model for electroencephalogram (EEG)-based driver drowsiness recognition. The novel approach achieves high accuracy by identifying meaningful EEG features, improving upon existing methods for calibration-free systems.

    Area of Science:

    • Neuroscience
    • Machine Learning
    • Biomedical Engineering

    Background:

    • Driver drowsiness recognition using electroencephalogram (EEG) signals faces challenges due to inter-subject and inter-session variability, hindering calibration-free systems.
    • Existing deep learning models for EEG-based mental state recognition often function as black boxes, with limited understanding of learned features and susceptibility to noise.
    • The need for interpretable models that can identify biologically meaningful patterns in EEG data for accurate drowsiness detection is critical.

    Purpose of the Study:

    • To develop a novel, interpretable deep learning model for calibration-free driver drowsiness recognition using EEG signals.
    • To analyze the features learned by the model and assess their biological meaningfulness and impact of noise.
    • To enhance the accuracy and reliability of EEG-based drowsiness detection systems.

    More Related Videos

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

    Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

    Published on: November 13, 2019

    12.3K
    Author Spotlight: IntelliSleepScorer &#8212; A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
    04:54

    Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

    Published on: November 8, 2024

    693

    Related Experiment Videos

    Last Updated: Oct 3, 2025

    Polygraphic Recording Procedure for Measuring Sleep in Mice
    08:45

    Polygraphic Recording Procedure for Measuring Sleep in Mice

    Published on: January 25, 2016

    24.3K
    Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
    04:13

    Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

    Published on: November 13, 2019

    12.3K
    Author Spotlight: IntelliSleepScorer &#8212; A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
    04:54

    Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

    Published on: November 8, 2024

    693

    Main Methods:

    • Development of a compact convolutional neural network (CNN) utilizing separable convolutions for spatial-temporal EEG signal processing.
    • Integration of a sample-wise interpretation technique to analyze important features for classification.
    • Evaluation using leave-one-out cross-subject drowsiness recognition on data from 11 subjects.

    Main Results:

    • The proposed interpretable CNN model achieved an average accuracy of 78.35% in cross-subject drowsiness recognition, outperforming conventional baselines (53.40%-72.68%) and state-of-the-art deep learning methods (71.75%-75.19%).
    • Interpretation analysis confirmed the model learned to identify biologically meaningful EEG features, such as alpha spindles, as key indicators of drowsiness across subjects.
    • The interpretation technique facilitated the exploration of misclassified samples, providing insights for future model improvements.

    Conclusions:

    • Interpretable deep learning models offer a promising avenue for discovering meaningful patterns in complex EEG signals for mental state recognition.
    • The developed model demonstrates effective calibration-free driver drowsiness recognition by leveraging biologically relevant EEG features.
    • This approach enhances the transparency and reliability of EEG-based drowsiness detection, paving the way for safer transportation systems.