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: May 30, 2026

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task
07:08

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task

Published on: December 5, 2025

Adaptive training using an artificial neural network and EEG metrics for within- and cross-task workload

Carryl L Baldwin1, B N Penaranda

  • 1Arch Laboratory and Department of Psychology, George Mason University, Fairfax, VA 22030, USA. cbaldwi4@gmu.edu

Neuroimage
|August 13, 2011
PubMed
Summary

Artificial neural networks (ANNs) can classify mental workload from electroencephalography (EEG) data. ANNs achieve high accuracy when trained on specific tasks, but struggle with cross-task generalization for adaptive training.

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

The Origins of Passive, Active, and Sleep-Related Fatigue.

Frontiers in neuroergonomics·2024
Same author

Preferred Sources of Information, Knowledge, and Acceptance of Automated Vehicle Systems: Effects of Gender and Age.

Frontiers in psychology·2022
Same author

Editorial: Cognitive and Brain Aging: Interventions to Promote Well-Being in Old Age.

Frontiers in aging neuroscience·2020
Same author

Editorial: Cognitive and Brain Aging: Interventions to Promote Well-Being in Old Age.

Frontiers in aging neuroscience·2019
Same author

Comparing the Relative Strengths of EEG and Low-Cost Physiological Devices in Modeling Attention Allocation in Semiautonomous Vehicles.

Frontiers in human neuroscience·2019
Same author

Positive valence music restores executive control over sustained attention.

PloS one·2017

Area of Science:

  • Neuroscience
  • Cognitive Science
  • Machine Learning

Background:

  • Adaptive training systems require real-time mental workload classification.
  • Artificial neural networks (ANNs) show promise but typically need task-specific training data.
  • Current limitations hinder the application of ANNs in dynamic learning environments.

Purpose of the Study:

  • To evaluate the classification accuracy of ANNs for mental workload using electroencephalography (EEG) data.
  • To investigate the performance of ANNs trained on limited, novel task data (within-task vs. cross-task).
  • To assess the feasibility of neurophysiologically driven adaptive training platforms.

Main Methods:

  • Participants performed three working memory tasks at two difficulty levels.

Related Experiment Videos

Last Updated: May 30, 2026

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task
07:08

Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task

Published on: December 5, 2025

  • Electroencephalography (EEG) data were recorded during task performance.
  • ANNs were trained and tested on EEG data from same (within-task) and different (cross-task) conditions.

    • Main Results:

    • Within-task classification accuracies for ANNs were high (87.1% and 85.3%).
    • Cross-task classification accuracies were significantly lower (average 44.8%).
    • Systematic misclassifications were observed across certain tasks and individuals.

    Conclusions:

    • ANNs demonstrate high accuracy for mental workload classification within a specific task.
    • Generalizing workload classification across different tasks remains a significant challenge.
    • Further research is needed to improve cross-task generalization for adaptive neurophysiological training.