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

The MADS-box Transcription Factor OfDEFA Orchestrates Floral Aroma Biosynthesis in Osmanthus fragrans Flowers through a Dual-Layer Transcriptional Regulatory Network.

Plant & cell physiology·2026
Same author

Emotion Recognition Based on Fusion of Topological Features and Trajectory Images Derived from EEG Phase Space Reconstruction.

Sensors (Basel, Switzerland)·2026
Same author

Construction and evaluation of an AOP framework to explore cobalt-induced nonalcoholic fatty liver disease.

Ecotoxicology and environmental safety·2026
Same author

Multi-component dissolved gas dynamics as early warning indicators for algal bloom development in the three gorges reservoir.

Water research·2026
Same author

Unified quasi-solid electrolyte design for coupled stabilization of Zn anode and I<sub>2</sub> cathode in aqueous Zn-I<sub>2</sub> batteries.

Science bulletin·2026
Same author

Violet Arsenic Phosphorus: Switching p-Type into High Performance n-Type Semiconductor by Arsenic Substitution.

Nano-micro letters·2026

Related Experiment Video

Updated: May 10, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.6K

Task-Independent Cognitive Workload Discrimination Based on EEG with Stacked Graph Attention Convolutional Networks.

Chenyu Wei1, Xuewen Zhao1, Yu Song1

  • 1Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems, School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, China.

Sensors (Basel, Switzerland)
|April 26, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel stacked graph attention convolutional networks (SGATCNs) model for task-independent cognitive workload assessment using electroencephalography (EEG) spatial data. The model achieved 65.11% accuracy in recognizing workload levels across different tasks.

Keywords:
cognitive workloadelectroencephalogramfunctional connectgraph neural networkgraph theory

More Related Videos

Measuring the Switch Cost of Smartphone Use While Walking
07:00

Measuring the Switch Cost of Smartphone Use While Walking

Published on: April 30, 2020

1.8K
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

7.6K

Related Experiment Videos

Last Updated: May 10, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.6K
Measuring the Switch Cost of Smartphone Use While Walking
07:00

Measuring the Switch Cost of Smartphone Use While Walking

Published on: April 30, 2020

1.8K
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

7.6K

Area of Science:

  • Neuroscience
  • Cognitive Science
  • Machine Learning

Background:

  • Assessing cognitive workload is vital in neuroeconomics, but task-independent methods using EEG data are challenging.
  • Existing decentralized studies for task-independent cognitive load classification yield suboptimal results.
  • Developing robust methods for real-world applications requires improved task-independent workload assessment.

Purpose of the Study:

  • To present a novel stacked graph attention convolutional networks (SGATCNs) model for task-independent cognitive workload assessment.
  • To leverage EEG spatial information and advanced network architectures for improved workload recognition.
  • To evaluate the model's performance across diverse cognitive tasks and workload levels.

Main Methods:

  • Utilized differential entropy (DE) and power spectral density (PSD) features from EEG channels across delta, theta, alpha, and beta bands.
  • Constructed functional brain networks using phase-locked values (PLVs), phase-lag indices (PLIs), Pearson correlation coefficients (PCCs), and mutual information (MI).
  • Employed stacked graph attention layers for spatial information aggregation and a convolution module for frequency domain analysis.

Main Results:

  • The SGATCNs model demonstrated an average accuracy of 65.11% in recognizing task-independent cognitive workload.
  • Performance was evaluated across three distinct psychological experimental task paradigms (N-back, mental arithmetic, Sternberg).
  • The framework successfully identified varying cognitive workload levels (low, medium, high) independent of specific tasks.

Conclusions:

  • The proposed SGATCNs model offers a promising approach for task-independent cognitive workload assessment using EEG.
  • Integrating spatial and frequency domain features enhances the model's ability to capture workload variations.
  • This framework has potential for real-world neuroeconomic applications requiring robust cognitive state monitoring.