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 Videos

EEG-based mental fatigue measurement using multi-class support vector machines with confidence estimate.

Kai-Quan Shen1, Xiao-Ping Li, Chong-Jin Ong

  • 1Department of Mechanical Engineering, National University of Singapore, EA, #07-08, 9 Engineering Drive 1, Singapore, Singapore. mpeskq@nus.edu.sg

Clinical Neurophysiology : Official Journal of the International Federation of Clinical Neurophysiology
|May 13, 2008
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

Biophysical and Biochemical Assays for Screening Small Molecule Inhibitors Targeting Toxin-Ribosome Interactions.

Toxins·2026
Same author

[Coupling Coordination Measurement and Convergence of Provincial Carbon Emissions and New Quality Productivity in China].

Huan jing ke xue= Huanjing kexue·2026
Same author

Gastrointestinal diseases-induced cardiovascular dysfunction: Focus on clinical presentation, pathogenesis and therapeutic implications of gastrocardiac syndrome.

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2026
Same author

Intraductal papillary neoplasm of the biliary tract with typical clinicopathological, endoscopic features: A case report.

World journal of gastrointestinal surgery·2026
Same author

[Mechanism of Xiangshao Granules in alleviating anxiety and depression in mice based on integrated metabolomics and gut microbiota].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2025
Same author

Two-Dimensional Dual-Switchable Ferroelectric Altermagnets: Altering Electrons and Magnons.

Nano letters·2025

This study introduces a novel electroencephalogram (EEG)-based system for monitoring mental fatigue. The probabilistic support vector machine (SVM) method achieved higher accuracy in detecting fatigue levels, proving its feasibility for real-world applications.

Area of Science:

  • Neuroscience
  • Machine Learning
  • Human Factors Engineering

Background:

  • Mental fatigue poses significant risks, particularly in safety-critical domains like transportation.
  • Current methods for monitoring mental fatigue are often subjective or invasive.
  • Developing objective, automated systems for fatigue detection is crucial for accident prevention.

Purpose of the Study:

  • To evaluate an electroencephalogram (EEG)-based system for automatic mental fatigue monitoring.
  • To compare a probabilistic multi-class support vector machine (SVM) with a standard multi-class SVM for fatigue classification.
  • To assess the system's accuracy and confidence estimation in predicting mental fatigue levels.

Main Methods:

  • Ten participants underwent 25 hours of sleep deprivation with continuous EEG monitoring.

Related Experiment Videos

  • EEG data were segmented into 3-second epochs and classified into five mental fatigue levels based on auditory vigilance task (AVT) performance.
  • A probabilistic multi-class SVM and a standard multi-class SVM were employed for classification.

    • Main Results:

    • The probabilistic multi-class SVM achieved a classification accuracy of 87.2%, outperforming the standard SVM at 85.4%.
    • Incorporating confidence estimates aggregation further improved accuracy to 91.2%.
    • The probabilistic SVM provided reliable confidence estimates for fatigue level predictions.

    Conclusions:

    • Probabilistic multi-class SVM offers superior accuracy and valuable confidence estimates for EEG-based mental fatigue detection.
    • The study demonstrates the feasibility of an automated EEG method for assessing and monitoring mental fatigue.
    • This technology holds potential for applications in traffic safety and other fields requiring fatigue management.