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 22, 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

SHAP analysis of an improved EEG-based mental workload classification framework: utilizing data augmentation and

Sushil Chaturvedi1, Mitul Kumar Ahirwal2

  • 1Department of Computer Science and Engineering, Maulana Azad National Institute of Technology, Bhopal, M.P., India.

Scientific Reports
|May 20, 2026
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

Causal ordinal connections based characterization of weighted effective brain network for schizophrenia detection.

Psychiatry research. Neuroimaging·2026
Same author

Content-Based Medical Image Retrieval System for Skin Melanoma Diagnosis Based on Optimized Pair-Wise Comparison Approach.

Journal of digital imaging·2022
Same author

IoT-enabled cloud-based real-time remote ECG monitoring system.

Journal of medical engineering & technology·2021
See all related articles

This study enhances mental workload (MWL) classification using electroencephalogram (EEG) by integrating Synthetic Minority Oversampling Technique (SMOTE) and Shapley Additive Explanations (SHAP). The approach significantly improved accuracy and identified key brain regions for MWL processing.

Area of Science:

  • Cognitive Neuroscience
  • Brain-Computer Interface (BCI)
  • Machine Learning for Neuroimaging

Background:

  • Accurate mental workload (MWL) classification from electroencephalogram (EEG) is vital for cognitive neuroscience and BCI applications.
  • EEG signal variability across sessions and individuals necessitates robust, generalizable classification models.
  • Existing models often struggle with data imbalance and lack interpretability regarding influential brain regions.

Purpose of the Study:

  • To develop and validate an improved EEG-based MWL classification framework.
  • To enhance model generalization and performance using data augmentation (SMOTE) and hyperparameter optimization.
  • To increase model interpretability by identifying key EEG channels through SHAP analysis.

Main Methods:

Keywords:
EEGNetElectroencephalography (EEG)Explainable artificial intelligence (XAI)Mental workload (MWL)Synthetic minority oversampling technique (SMOTE)

Related Experiment Videos

Last Updated: May 22, 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

  • Utilized the "An EEG dataset for cross-session mental workload estimation" dataset.
  • Employed the EEGNet model for classifying MWL into Low, Medium, and High categories.
  • Applied Synthetic Minority Oversampling Technique (SMOTE) for data balancing and systematically tuned EEGNet hyperparameters (F1, F2, D).
  • Conducted Shapley Additive Explanations (SHAP) analysis to determine channel importance.

    • Main Results:

    • Achieved classification accuracies of 80.5% without SMOTE and 82.7% with SMOTE.
    • SMOTE application yielded an average performance improvement of approximately 3%, confirmed as statistically significant (p < 0.05).
    • SHAP analysis identified parieto-occipital and temporal EEG channels as most influential for MWL prediction.

    Conclusions:

    • The integrated framework of SMOTE and SHAP significantly enhances EEG-based MWL classification performance and explainability.
    • The findings align with neurophysiological evidence, validating the identified informative EEG channels.
    • This systematic approach offers a more robust and interpretable solution for real-world BCI applications.