Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

A Self-Powered Wireless Temperature Sensor Platform for Foot Ulceration Monitoring.

Sensors (Basel, Switzerland)·2024

Same author

Analysis of Inverter Efficiency Using Photovoltaic Power Generation Element Parameters.

Sensors (Basel, Switzerland)·2024

Same author

Cognitive workload estimation using physiological measures: a review.

Cognitive neurodynamics·2024

Same author

Proposal of a Token-Based Node Selection Mechanism for Node Distribution of Mobility IoT Blockchain Nodes.

Sensors (Basel, Switzerland)·2023

Same author

ssFPN: Scale Sequence (<i>S</i><sup>2</sup>) Feature-Based Feature Pyramid Network for Object Detection.

Sensors (Basel, Switzerland)·2023

Same author

Attention-Based Bi-Prediction Network for Versatile Video Coding (VVC) over 5G Network.

Sensors (Basel, Switzerland)·2023

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 15, 2025

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

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

Published on: May 24, 2020

Subject-Specific Cognitive Workload Classification Using EEG-Based Functional Connectivity and Deep Learning.

Anmol Gupta¹, Gourav Siddhad¹, Vishal Pandey²

¹Department of Computer Science and Engineering, Indian Institute of Technology, Roorkee 247667, India.

Sensors (Basel, Switzerland)

|October 26, 2021

Summary

This summary is machine-generated.

Researchers used electroencephalography (EEG) and deep learning to classify cognitive workload. Combining functional connectivity metrics with deep learning models achieved high accuracy in distinguishing workload levels, paving the way for real-time applications.

Keywords:

CNN LSTM cognitive workload functional connectivity analysis mental workload mutual information phase locking value phase transfer entropy

More Related Videos

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

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

Published on: July 14, 2023

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Related Experiment Videos

Last Updated: Oct 15, 2025

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

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

Published on: May 24, 2020

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

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

Published on: July 14, 2023

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Area of Science:

Neuroscience
Machine Learning
Cognitive Science

Background:

Cognitive workload is critical in dynamic, high-risk decision-making tasks.
Electroencephalography (EEG) offers a portable, cost-effective alternative to fMRI for workload estimation.
Functional connectivity, correlations between brain regions, is linked to cognitive phenotypes.

Purpose of the Study:

To explore the use of model-free functional connectivity metrics with deep learning for cognitive workload classification.
To compare the efficacy of different functional connectivity metrics (Phase Transfer Entropy, Mutual Information, Phase Locking Value) and deep learning models (CNN, LSTM, Conv-LSTM).
To develop subject-specific classifiers due to high inter-subject variability in EEG and cognitive workload.

Main Methods:

Collected 64-channel EEG data from 19 participants performing the n-back task (1-back, 2-back, 3-back).
Extracted functional connectivity features: Phase Transfer Entropy (PTE), Mutual Information (MI), and Phase Locking Value (PLV).
Employed deep learning classifiers (CNN, LSTM, Conv-LSTM) for multi-class workload classification using subject-specific models.

Main Results:

State-of-the-art multi-class classification accuracy achieved with MI and CNN (80.87%), followed by PLV and CNN (75.88%), and MI and LSTM (71.87%).
Highest subject-specific performance reached 97.92% with PLV and Conv-LSTM, and PLV and CNN.
MI with CNN (95.83%) and MI with Conv-LSTM (93.75%) also demonstrated high subject-specific accuracy.

Conclusions:

The combination of EEG-based model-free functional connectivity metrics and deep learning is effective for classifying cognitive workload.
Subject-specific models yield superior performance, highlighting the personalized nature of EEG functional connectivity.
This approach holds potential for real-time cognitive workload assessment in complex, dynamic environments.