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 Videos

EEG-Based Affect and Workload Recognition in a Virtual Driving Environment for ASD Intervention.

Jing Fan, Joshua W Wade, Alexandra P Key

    IEEE Transactions on Bio-Medical Engineering
    |April 20, 2017
    PubMed
    Summary

    This study developed electroencephalogram (EEG)-based models to recognize emotions and mental workload in adolescents with autism spectrum disorder (ASD) during driving training, showing promising results for personalized interventions.

    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

    Cortical Auditory Neural Responses to Speech and Communicative Functioning in Normocephalic Children With Prenatal Exposure to the Zika Virus.

    Ear and hearing·2026
    Same author

    The MIND Randomized Controlled Trial: An Intervention to Improve Neural Speech Processing and 2-Year Language Outcomes of Infants Born Preterm.

    The Journal of pediatrics·2026
    Same author

    Social Visual Engagement in Preterm and Term Children With Autism: Consistent Eye-tracking Patterns Irrespective of Gestational Age.

    Journal of developmental and behavioral pediatrics : JDBP·2026
    Same author

    Resting-state EEG and machine learning to investigate cortical connectivity as a biomarker in chronic mTBI.

    Frontiers in neurology·2026
    Same author

    Social Interactions and Interbrain Synchrony in Early Development: A Scoping Review of Pediatric EEG/MEG Hyperscanning Studies.

    Psychophysiology·2025
    Same author

    Resting-state EEG and machine learning to investigate cortical connectivity as a biomarker in chronic mTBI.

    medRxiv : the preprint server for health sciences·2025

    Area of Science:

    • Neuroscience
    • Autism Spectrum Disorder Research
    • Human-Computer Interaction

    Background:

    • Individuals with autism spectrum disorder (ASD) often face challenges in driving skill acquisition.
    • Understanding affective states and mental workload is crucial for effective driving training interventions for ASD.

    Purpose of the Study:

    • To develop group-level classification models using electroencephalogram (EEG) data to recognize affective states and mental workload in adolescents with ASD during simulated driving.
    • To identify optimal EEG feature types for accurate classification of these states.

    Main Methods:

    • Twenty adolescents with ASD underwent virtual reality driving simulation while EEG data were recorded.
    • Multiple feature extraction methods (statistical, fractal, HOC, power features) were applied to EEG data.

    Related Experiment Videos

  • A two-step calibration removed individual differences, followed by k-nearest neighbors classification and leave-one-subject-out cross-validation.

    • Main Results:

    • Power features from bins achieved high accuracy for engagement (0.95) and boredom (0.78).
    • Higher order crossings (HOC)-based features were effective for enjoyment (0.90), frustration (0.88), and workload (0.86).
    • Offline EEG-based group-level models demonstrated feasibility in recognizing affective states and workload.

    Conclusions:

    • Feasible EEG-based group-level classification models can recognize affective states and mental workload in individuals with ASD during driving.
    • These models form a basis for an EEG-based brain-computer interface for individualized driving skill training.
    • Further development is needed to apply these models in online adaptive driving tasks.