A fatigue driving detection method based on local maximum refined composite multi-scale normalized dispersion entropy and SVM

Zhanghong Wang; Haitao Zhu; Huaquan Chen; Bei Liu; Zhanghong Wang; Haitao Zhu; Huaquan Chen; Bei Liu

doi:10.3934/mbe.2025096

Mathematical Biosciences and Engineering

2025, Volume 22, Issue 10: 2627-2640. doi: 10.3934/mbe.2025096

Previous Article Next Article

Research article Special Issues

A fatigue driving detection method based on local maximum refined composite multi-scale normalized dispersion entropy and SVM

College of Mathematics and Physics, Hunan University of Arts and Science, Changde 415000, China

Received: 20 May 2025 Revised: 15 July 2025 Accepted: 31 July 2025 Published: 20 August 2025

Multi-scale dispersion entropy (MDE) has been extensively applied to capture the nonlinear features of electroencephalography (EEG) signals for fatigue driving detection. However, MDE suffers from information loss and limited robustness during the extraction of EEG signal nonlinearities. To address these issues, a fatigue driving detection approach integrating local maximum refined composite multi-scale normalized dispersion entropy (LMRCMNDE) with support vector machines (SVM) is introduced. To begin, the refined composite multi-scale dispersion entropy (RCMDE) technique is presented. Next, the segmented averaging in the coarse-graining process is substituted with local maximum calculation to alleviate information loss. Finally, normalization of the entropy values is performed to enhance the robustness of feature parameters, leading to the formation of LMRCMNDE. LMRCMNDE serves as the feature descriptor for fatigue driving EEG signals, while SVM is employed for classification. Compared with the MDE-SVM and RCMDE-SVM approaches, the LMRCMNDE-SVM method achieves higher recognition accuracy, reaching up to 98%. The proposed method can effectively identify the fatigue state of drivers and provide a new reliable detection method for automatic fatigue driving detection.
Citation: Zhanghong Wang, Haitao Zhu, Huaquan Chen, Bei Liu. A fatigue driving detection method based on local maximum refined composite multi-scale normalized dispersion entropy and SVM[J]. Mathematical Biosciences and Engineering, 2025, 22(10): 2627-2640. doi: 10.3934/mbe.2025096

Related Papers:

Abstract

Multi-scale dispersion entropy (MDE) has been extensively applied to capture the nonlinear features of electroencephalography (EEG) signals for fatigue driving detection. However, MDE suffers from information loss and limited robustness during the extraction of EEG signal nonlinearities. To address these issues, a fatigue driving detection approach integrating local maximum refined composite multi-scale normalized dispersion entropy (LMRCMNDE) with support vector machines (SVM) is introduced. To begin, the refined composite multi-scale dispersion entropy (RCMDE) technique is presented. Next, the segmented averaging in the coarse-graining process is substituted with local maximum calculation to alleviate information loss. Finally, normalization of the entropy values is performed to enhance the robustness of feature parameters, leading to the formation of LMRCMNDE. LMRCMNDE serves as the feature descriptor for fatigue driving EEG signals, while SVM is employed for classification. Compared with the MDE-SVM and RCMDE-SVM approaches, the LMRCMNDE-SVM method achieves higher recognition accuracy, reaching up to 98%. The proposed method can effectively identify the fatigue state of drivers and provide a new reliable detection method for automatic fatigue driving detection.

References

[1]	G. Sikander, S. Anwar, Driver fatigue detection systems: A review, IEEE Trans. Intell. Transp. Syst., 20 (2018), 2339–2352. https://doi.org/10.1109/TITS.2018.2868499 doi: 10.1109/TITS.2018.2868499
[2]	World Health Organization, Global Status Report on Road Safety 2018, 2018. Avaiable from: https://www.who.int/publications/i/item/9789241565684
[3]	A. Subasi, A. Saikia, K. Bagedo, A. Singh, A. Hazarika, EEG-based driver fatigue detection using FAWT and multiboosting approaches, IEEE Trans. Ind. Inf., 18 (2022), 6602–6609. https://doi.org/10.1109/TII.2022.3167470 doi: 10.1109/TII.2022.3167470
[4]	F. Hu, L. Zhang, X. Yang, W. Zhang, EEG-based driver fatigue detection using spatio-temporal fusion network with brain region partitioning strategy, IEEE Trans. Intell. Transp. Syst., 25 (2024), 9618–9630. https://doi.org/10.1109/TITS.2023.3348517 doi: 10.1109/TITS.2023.3348517
[5]	Y. Zheng, Y. Ma, J. Cammon, S. Zhang, J. Zhang, Y. Zhang, A new feature selection approach for driving fatigue EEG detection with a modified machine learning algorithm, Comput. Biol. Med., 147 (2022), 105718. https://doi.org/10.1016/j.compbiomed.2022.105718 doi: 10.1016/j.compbiomed.2022.105718
[6]	W. Xiang, X. Wu, C. Li, W. Zhang, F. Li, Driving fatigue detection based on the combination of multi-branch 3D-CNN and attention mechanism, Appl. Sci., 12 (2022), 4689. https://doi.org/10.3390/app12094689 doi: 10.3390/app12094689
[7]	T. Zhang, J. Chen, E. He, H. Wang, Sample-entropy-based method for real driving fatigue detection with multichannel electroencephalogram, Appl. Sci., 11 (2021), 10279. https://doi.org/10.3390/app112110279 doi: 10.3390/app112110279
[8]	X. Zuo, C. Zhang, F. Cong, J. Zhao, T. Hämäläinen, Driver distraction detection using bidirectional long short-term network based on multiscale entropy of EEG, IEEE Trans. Intell. Transp. Syst., 23 (2022), 19309–19322. https://doi.org/10.1109/TITS.2022.3159602 doi: 10.1109/TITS.2022.3159602
[9]	F. Wang, M. Ma, R. Fu, X. Zhang, EEG-based detection of driving fatigue using a novel electrode, Sens. Actuators A Phys., 365 (2024), 114895. https://doi.org/10.1016/j.sna.2023.114895 doi: 10.1016/j.sna.2023.114895
[10]	R. Liu, S. Qi, S. Hao, G. Lian, Y. Li, H. Yang, Drivers' workload electroencephalogram characteristics in cognitive tasks based on improved multiscale sample entropy, IEEE Access, 11 (2023), 42180–42190. https://doi.org/10.1109/ACCESS.2023.3270310 doi: 10.1109/ACCESS.2023.3270310
[11]	L. Hussain, W. Aziz, S. Nadeem, S. Shah, A. Majid, Electroencephalography (EEG) analysis of alcoholic and control subjects using multiscale permutation entropy, J. Multidiscip. Eng. Sci. Technol., 1 (2014), 380–387.
[12]	B. Liu, W. Hu, X. Zou, Y. Ding, S. Qian, Recognition of denatured biological tissue based on variational mode decomposition and multi-scale permutation entropy, Acta Phys. Sin., 68 (2019), 028702. https://doi.org/10.7498/aps.68.20181772 doi: 10.7498/aps.68.20181772
[13]	S. Zou, T. Qiu, P. Huang, X. Bai, C. Liu, Constructing Multi-scale entropy based on the empirical mode decomposition (EMD) and its application in recognizing driving fatigue, J. Neurosci. Methods, 341 (2020), 108691. https://doi.org/10.1016/j.jneumeth.2020.108691 doi: 10.1016/j.jneumeth.2020.108691
[14]	H. Azami, M. Rostaghi, D. Abásolo, J. Escudero, Refined composite multiscale dispersion entropy and its application to biomedical signals, IEEE Trans. Biomed. Eng., 64 (2017), 2872–2879. https://doi.org/10.1109/TBME.2017.2679136 doi: 10.1109/TBME.2017.2679136
[15]	J. Lv, W. Sun, H. Wang, F. Zhang, Coordinated approach fusing RCMDE and sparrow search algorithm-based svm for fault diagnosis of rolling bearings, Sensors, 21 (2021), 5297. https://doi.org/10.3390/s21165297 doi: 10.3390/s21165297
[16]	F. Wang, A. Luo, D. Chen, Real-time EEG-based detection of driving fatigue using a novel semi-dry electrode with self-replenishment of conductive fluid, Comput. Methods Biomech. Biomed. Eng., (2024), 1–18. https://doi.org/10.1080/10255842.2024.2423268
[17]	M. Henkel, W. Weijtjens, C. Devriendt, Fatigue stress estimation for submerged and sub-soil welds of offshore wind turbines on monopiles using modal expansion, Energies, 14 (2021), 7576. https://doi.org/10.3390/en14227576 doi: 10.3390/en14227576
[18]	F. Lyu, X. Ding, Q. Li, S. Chen, S. Zhang, X. Huang, et al., Research on fault diagnosis method of reciprocating compressor based on RSSD and optimized parameter RCMDE, Appl. Sci., 14 (2024), 11556. https://doi.org/10.3390/app142411556 doi: 10.3390/app142411556
[19]	W. Zheng, B. Lu, Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks, IEEE Trans. Auton. Ment. Dev., 7 (2015), 162–175. https://doi.org/10.1109/TAMD.2015.2431497 doi: 10.1109/TAMD.2015.2431497
[20]	M. Hakraborty, D. Mitra, Automated detection of epileptic seizures using multiscale and refined composite multiscale dispersion entropy, Chaos Solitons Fractals, 146 (2021), 110939. https://doi.org/10.1016/j.chaos.2021.11093 doi: 10.1016/j.chaos.2021.11093
[21]	B. Liu, H. Bai, W. Chen, H. Chen, Z. Zhang, Automatic detection method of epileptic seizures based on IRCMDE and PSO-SVM, Math. Biosci. Eng., 20 (2022), 9349–9363. https://doi.org/10.3934/mbe.2023410 doi: 10.3934/mbe.2023410
[22]	B. Wang, W. Qiu, X. Hu, W. Wang, A rolling bearing fault diagnosis technique based on recurrence quantification analysis and bayesian optimization SVM, Appl. Soft Comput., 156 (2024), 111506. https://doi.org/10.1016/j.asoc.2024.111506 doi: 10.1016/j.asoc.2024.111506
[23]	H. Long, T. Chen, H. Chen, X. Zhou, W. Deng, Principal space approximation ensemble discriminative marginalized least-squares regression for hyperspectral image classification, Eng. Appl. Artif. Intell., 133 (2024), 108031. https://doi.org/10.1016/j.engappai.2024.108031 doi: 10.1016/j.engappai.2024.108031
[24]	M. Tang, P. Li, H. Zhang, L. Deng, S. Liu, Q. Zheng, D. Gao, HMS-TENet: A hierarchical multi-scale topological enhanced network based on EEG and EOG for driver vigilance estimation, Biomed. Technol., 8 (2024), 92–103. https://doi.org/10.1016/j.bmt.2024.10.003 doi: 10.1016/j.bmt.2024.10.003
[25]	D. Gao, P. Li, M. Wang, Y. Liang, S. Liu, J. Zhou, L. Wang, Y. Zhang, CSF-GTNET: A novel multi-dimensional feature fusion network based on Convnext-GeLU-BILSTM for EEG-signals-enabled fatigue driving detection, IEEE J. Biomed. Health Inf., 28 (2024), 2558–2568. https://doi.org/10.1109/jbhi.2023.3240891 doi: 10.1109/jbhi.2023.3240891
[26]	B. Peng, Y. Zhang, M. Wang, J. Chen, D. Gao, TA-MFFNET: Multi-feature fusion network for eeg analysis and driving fatigue detection based on time domain network and attention network, Comput. Biol. Chem., 104 (2023), 107863. https://doi.org/10.1016/j.compbiolchem.2023.107863 doi: 10.1016/j.compbiolchem.2023.107863
[27]	Y. Ding, R. Neethu, C. Tong, Q. Zeng, C. Guan, LGGNET: Learning from local-global-graph representations for brain-computer interface, IEEE Trans. Neural Networks Learn. Syst., 35 (2023), 9773–9786. https://doi.org/10.1109/tnnls.2023.3236635 doi: 10.1109/tnnls.2023.3236635
[28]	D. Gao, H. Zhang, P. Li, T. Tang, S. Liu, Z. Zhou, et al., A local-ascending-global learning strategy for brain-computer interface, Proc. AAAI Conf. Artif. Intell., 38 (2024), 10039–10047. https://doi.org/10.1609/aaai.v38i9.28867 doi: 10.1609/aaai.v38i9.28867

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)