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: Jun 29, 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

Hybrid deep learning for mental workload classification using EEG with enhanced preprocessing and interpretability.

Osama Abdelrahman1, Chew XinYing1, Esraa Faisal Malik2

  • 1School of Computer Sciences, Universiti Sains Malaysia, Gelugor, Penang, Malaysia.

Plos One
|June 26, 2026
PubMed
Summary

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

Intelligent Patient Management in Viral Diseases: An Integrated Regression Model and Multi-Criteria Decision-Making Approach to Convalescent Plasma Transfusion.

Healthcare (Basel, Switzerland)·2025
Same author

ACG-SFE: Adaptive cluster-guided simple, fast, and efficient feature selection for high-dimensional microarray data in binary classification.

PloS one·2025
Same author

Economic-statistical design of synthetic np chart with estimated process parameter.

PloS one·2020
Same journal

Analysis of strength degradation of coal and rock masses and stability of mined areas under long term immersion environment.

PloS one·2026
Same journal

Biogenic Silver-Selenium nanocomposite with anticancer activity and potent efficacy against vancomycin-resistant Staphylococcus aureus.

PloS one·2026
Same journal

Preparation and physicochemical characterization of a biodegradable chitosan/carboxymethyl cellulose hydrogel synthesized in NaOH/urea medium.

PloS one·2026
Same journal

Action-guilt, survivor-guilt, and depression in combat-related PTSD.

PloS one·2026
Same journal

Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability.

PloS one·2026
Same journal

Deep learning based two-way feature depiction model for brain tumor detection.

PloS one·2026
See all related articles
This summary is machine-generated.

This study introduces a hybrid deep learning framework for accurate electroencephalogram-based mental workload classification. The model enhances noise reduction and interpretability, achieving 83.9% accuracy in classifying workload levels.

Area of Science:

  • Neuroscience
  • Machine Learning
  • Biomedical Engineering

Background:

  • Electroencephalography (EEG)-based mental workload classification is vital for safety-critical domains like aviation and healthcare.
  • Existing EEG methods struggle with generalizability, noise, and interpretability.
  • Robust and interpretable mental workload classification using EEG remains a significant challenge.

Purpose of the Study:

  • To develop an integrated hybrid deep learning framework for robust and interpretable EEG-based mental workload classification.
  • To address limitations in generalizability, noise robustness, and interpretability of current EEG approaches.
  • To enable accurate classification of mental workload levels using advanced deep learning techniques.

Main Methods:

  • A hybrid deep learning framework combining Variational Autoencoder (VAE), Convolutional Block Attention Module (CBAM), and Bidirectional Long Short-Term Memory (BiLSTM) networks.

Related Experiment Videos

Last Updated: Jun 29, 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

  • VAE for noise reduction and feature extraction from band-wise topographical EEG data.
  • CBAM for adaptive spatial-channel feature focus and BiLSTM for temporal dependency modeling.
  • Leave-one-subject-out cross-validation for robust performance evaluation.
  • Gradient-weighted Class Activation Mapping (Grad-CAM) for model interpretability and visualization of relevant brain regions and frequency bands.

    • Main Results:

    • The proposed hybrid deep learning model achieved the highest overall accuracy compared to baseline methods.
    • An average accuracy of 83.9% was obtained across subjects for classifying four distinct mental workload levels.
    • Ablation studies confirmed the significant contribution of VAE, CBAM, and BiLSTM components to performance enhancement.
    • Sensitivity analyses identified an optimal 10-second window length for balancing temporal context and specificity.
    • Grad-CAM visualization highlighted key frontal-parietal regions and specific frequency bands associated with mental workload dynamics.

    Conclusions:

    • The integrated hybrid deep learning framework offers a robust and interpretable solution for EEG-based mental workload classification.
    • The model's architecture effectively handles noise, extracts relevant features, and captures temporal dynamics.
    • The findings provide neurophysiological insights into workload-related brain activity, enhancing model interpretability.
    • Future work should focus on adaptive windowing, multimodal integration, and cross-dataset validation for improved generalizability.