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

Petrositis caused by fluconazole-resistant candida: case report and literature review.

BMC infectious diseases·2022

Same author

Analysis of the Prevalence, Location, and Morphology of Maxillary Sinus Septa in a Northern Chinese Population by Cone Beam Computed Tomography.

Computational and mathematical methods in medicine·2022

Same author

The Beneficial Effects of Hydrogen-Rich Saline Irrigation on Chronic Rhinitis: A Randomized, Double-Blind Clinical Trial.

Journal of inflammation research·2022

Same author

Impaired sleep quality in children with allergic conjunctivitis and their parents.

Eye (London, England)·2022

Same author

Association of renal function with diabetic retinopathy and macular oedema among Chinese patients with type 2 diabetes mellitus.

Eye (London, England)·2022

Same author

Impact of family history of coronary artery disease on clinical outcomes in Takotsubo cardiomyopathy.

Journal of investigative medicine : the official publication of the American Federation for Clinical Research·2022

Search research articles

Related Experiment Video

Updated: Aug 30, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Application of Graph Neural Network in Driving Fatigue Detection Based on EEG Signals.

Zhendong Mu¹, Ling Jin¹, Jinghai Yin¹

¹The Center of Collaboration and Innovation, Jiangxi University of Technology, Nanchang 330098, Jiangxi, China.

Computational Intelligence and Neuroscience

|September 2, 2022

Summary

This study introduces a novel graph neural network (GNN) approach for detecting driver fatigue using electroencephalogram (EEG) signals. The improved method achieves a higher recognition rate, enhancing road safety.

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

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

Related Experiment Videos

Last Updated: Aug 30, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

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

Area of Science:

Neuroscience
Machine Learning
Road Safety

Background:

Driving fatigue is a significant cause of road accidents.
Current methods for detecting driver fatigue have limitations.
Electroencephalogram (EEG) signals offer a promising avenue for objective fatigue assessment.

Purpose of the Study:

To develop and evaluate a Graph Neural Network (GNN) based system for driving fatigue detection (DFD).
To improve the accuracy and efficiency of DFD using EEG signals.
To enhance overall road safety by mitigating risks associated with driver fatigue.

Main Methods:

Utilized a multilayer perceptron overlimit learning machine with an unsupervised self-encoding structure for pattern classification.
Applied an improved soft threshold denoising algorithm for preprocessing electroencephalogram (EEG) signals.
Employed Graph Neural Networks (GNNs) for feature extraction and classification of driving fatigue.

Main Results:

The proposed GNN-based method achieved an average recognition rate of 87.5% for driver fatigue.
This represents a significant improvement over traditional algorithms like Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) convolutional neural networks, which showed rates of 79% and 81% respectively.
The preprocessing step using the improved soft threshold algorithm enhanced EEG signal feature extraction efficiency.

Conclusions:

Graph Neural Networks (GNNs) demonstrate superior performance in driving fatigue detection (DFD) compared to conventional machine learning algorithms.
The developed system offers a more accurate and reliable method for identifying driver fatigue from EEG signals.
The findings suggest a potential for widespread application of this technology to improve road safety.