Related Experiment Video
Updated: Jan 16, 2026
08:27
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
1.6K
A fatigue driving detection method based on local maximum refined composite multi-scale normalized dispersion entropy
Zhanghong Wang1, Haitao Zhu1, Huaquan Chen1
1College of Mathematics and Physics, Hunan University of Arts and Science, Changde 415000, China.
Mathematical Biosciences and Engineering : MBE
|September 30, 2025
Summary
A new method, Local Maximum Refined Composite Multi-scale Normalized Dispersion Entropy (LMRCMNDE), improves electroencephalography (EEG) analysis for detecting driver fatigue. This approach enhances accuracy in identifying fatigue states, offering a more reliable detection system.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Signal Processing
Background:
- Multi-scale dispersion entropy (MDE) is used for analyzing electroencephalography (EEG) signals in fatigue driving detection.
- Existing MDE methods face challenges with information loss and limited robustness in extracting nonlinear EEG features.
Purpose of the Study:
- To introduce an improved fatigue driving detection approach using Local Maximum Refined Composite Multi-scale Normalized Dispersion Entropy (LMRCMNDE) and Support Vector Machines (SVM).
- To enhance the accuracy and robustness of EEG-based fatigue detection.
Main Methods:
- Developed Refined Composite Multi-scale Dispersion Entropy (RCMDE) and subsequently LMRCMNDE by replacing segmented averaging with local maximum calculation during coarse-graining.
- Normalized entropy values to improve feature parameter robustness.
- Utilized LMRCMNDE as the feature descriptor and SVM for classifying EEG signals to detect driver fatigue.
Main Results:
- The LMRCMNDE-SVM method achieved a recognition accuracy of up to 98%.
- Demonstrated superior performance compared to MDE-SVM and RCMDE-SVM approaches in fatigue driving detection.
Conclusions:
- The proposed LMRCMNDE-SVM method effectively identifies driver fatigue states.
- Offers a novel and reliable approach for automatic fatigue driving detection systems.
