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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Interpretable feature-transformer framework for cross-subject MCI detection using nonlinear dynamical and graph-theoretic EEG features.

Cognitive neurodynamics·2026
Same author

Detecting Mild Cognitive Impairment to Alzheimer's Disease Progression by fMRI Using Convolutional Neural Network and Long-short Term Memory.

Basic and clinical neuroscience·2026
Same author

Connectivity-Based Pain Recognition from fNIRS: Parsimonious Subject-Independent Classification.

Sensors (Basel, Switzerland)·2026
Same author

Towards the Development of a Deep Learning Framework Using Adaptive and Non-Adaptive Time-Frequency Features for EEG-Based Depression Therapy Prediction.

Brain sciences·2026
Same author

Interpretable Feature-Transformer Framework for Cross-Subject MCI Detection Using Nonlinear Dynamical and Graph-Theoretic EEG Features.

Research square·2026
Same author

Application of artificial intelligence in colonoscopy imaging for polyp analysis-A systematic review.

Computer methods and programs in biomedicine·2026

Related Experiment Video

Updated: Jun 28, 2025

Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task
13:18

Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task

Published on: May 24, 2020

7.7K

Classification of mental workload using brain connectivity and machine learning on electroencephalogram data.

MohammadReza Safari1, Reza Shalbaf2, Sara Bagherzadeh3

  • 1Institute for Cognitive Science Studies, Tehran, Iran.

Scientific Reports
|April 21, 2024
PubMed
Summary

This study introduces a novel method to assess mental workload using electroencephalography (EEG) brain connectivity and machine learning. The approach achieved 89.53% accuracy in classifying workload levels.

Keywords:
Brain connectivityEEGFeature selectionMental workload

More Related Videos

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

870

Related Experiment Videos

Last Updated: Jun 28, 2025

Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task
13:18

Conducting Concurrent Electroencephalography and Functional Near-Infrared Spectroscopy Recordings with a Flanker Task

Published on: May 24, 2020

7.7K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

870

Area of Science:

  • Neuroscience
  • Cognitive Science
  • Biomedical Engineering

Background:

  • Mental workload assessment is crucial for system design, clinical medicine, and industrial applications.
  • Existing methods for mental workload evaluation often lack precision and efficiency.
  • Electroencephalography (EEG) offers a non-invasive window into cognitive processes.

Purpose of the Study:

  • To develop and validate innovative methods for assessing mental workload using EEG data.
  • To leverage effective brain connectivity and advanced feature selection for improved workload classification.
  • To identify optimal machine learning models for accurate mental workload detection.

Main Methods:

  • Utilized the Simultaneous Task EEG Workload (STEW) dataset comprising EEG data from 48 subjects.
  • Extracted effective brain connectivities using the Direct Directed Transfer Function (DDTF).
  • Employed hierarchical feature selection, including forward feature selection, Relief-F, and Minimum Redundancy Maximum Relevance (mRMR), combined with machine learning models (SVM, LDA, Random Forest, Decision Tree).

Main Results:

  • Support Vector Machine (SVM) combined with forward feature selection demonstrated superior performance.
  • The proposed method achieved a classification accuracy of 89.53% (±1.36) for mental workload levels.
  • Forward feature selection and SVM proved most effective among the tested algorithms.

Conclusions:

  • The integration of effective brain connectivity, hierarchical feature selection, and machine learning provides a robust framework for mental workload assessment.
  • This approach offers a significant advancement in accurately quantifying cognitive effort from EEG signals.
  • The findings have potential implications for optimizing human-computer interaction and monitoring cognitive states in critical applications.