Related Experiment Video
Updated: Jan 9, 2026
06:40
Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
Published on: June 15, 2018
10.6K
Driver Fatigue Detection using EEG Microstate Features and Support Vector Machines
Zahra Yaddasht1, Kamran Kazemi1, Habibollah Danyali1
1Department of Electrical Engineering, Shiraz University of Technology, Shiraz, Iran.
Journal of Biomedical Physics & Engineering
|December 11, 2025
Summary
Electroencephalography (EEG) microstate analysis effectively detects driver fatigue. Combining microstate features with Support Vector Machine (SVM) machine learning achieved 98.77% accuracy, enhancing traffic safety.
Area of Science:
- Neuroscience
- Machine Learning
- Traffic Safety
Background:
- Driver fatigue poses significant risks to road safety.
- Electroencephalography (EEG) signals offer a direct measure of mental states, making them suitable for fatigue detection.
Purpose of the Study:
- To evaluate the efficacy of EEG microstate analysis for identifying driver fatigue.
- To explore variations in microstate features between normal and fatigued states.
Main Methods:
- An analytical study employing supervised machine learning for driver fatigue detection.
- EEG data collected from 10 participants in normal and fatigued states.
- Microstate analysis extracted features (duration, occurrence, coverage, MMP) from microstates A, B, C, D.
- Support Vector Machine (SVM) classifier trained and tested using extracted features.
Main Results:
- High classification accuracy was achieved using EEG microstate features.
- The combination of Microstate Mean Power (MMP) and occurrence features yielded the highest accuracy.
- The highest recorded classification accuracy reached 98.77%.
Conclusions:
- EEG microstate analysis combined with SVM is a viable method for driver fatigue detection.
- This approach can be integrated into real-time driver monitoring and fatigue alert systems.
- Implementation of this technology can significantly improve road safety.
