Athletes muscle fatigue recognition model based on KPCA and SVM

  • Xingping Chu College of Sports and Health, Jiangxi University of Chinese Medicine, Nanchang 330004, China
  • Dongqin Huang College of Sports and Health, Jiangxi University of Chinese Medicine, Nanchang 330004, China
  • Yan Yi College of Sports and Health, Jiangxi University of Chinese Medicine, Nanchang 330004, China
Keywords: fatigue; muscle fatigue; feature dimension reduction; the classification model
Article ID: 1514

Abstract

The muscle fatigue is the inevitable phenomenon occurring in the process of athletes in sports training, usually after intense exercise or sustainability movement, characterized by muscle soreness, fatigue and so on. When the muscle fatigue to a certain extent can cause human body damage, to avoid this kind of circumstance, can choose reasonable physiological signals, determine the level of fatigue of human body, scientific and effective means of fatigue recovery can help athletes maintain good state of movement, reduce the risk of sports injury, and electromyographic signal because for observation and has high real-time performance, in terms of evaluation of muscle fatigue Attention. This paper in order to build the classification model of muscle fatigue, athletes improve the correct recognition rate of the model, first of all, analyzes the generation mechanism, features and electromyographic signal denoising method, the dimension of feature set, and reduce the redundancy between characteristics; Finally after dimension reduction and Fisher linear discriminant analysis, a new feature set K neighbor and three kinds of support vector machine classifier combination, nine fatigue classification model is set up, on muscle relaxed state, transition state of fatigue and fatigue state classification of three states, and the results show that the kernel principal component analysis and support vector machine classification model for the fatigue of the average recognition rate is highest, at 91.5%, higher than the other fatigue classification model, this method can obtain better athletes the classification results of muscle fatigue, for athletes muscle fatigue degree of judgment has important research significance.

References

1. Boyas S, Guevel A. Neuromuscular fatigue in healthy muscle: Underlying factors and adaptation mechanisms. Annals of Physical and Rehabilitation Medicine. 2011; 54(2): 88–108.

2. Hughes E, Bell A. A wireless surface electromyography system. Vcu. Etd. Archive. 2007; 65(8): 53.

3. Jero SE, Ramakrishnan S. Order frequency spectral correlation based cyclo-nonstationary analysis of surface EMG signals in biceps brachii muscles. In: Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 23–27 July 2019; Berlin, Germany.

4. Moniri A, Terracina D, Rodriguez-Manzano J, et al. Real-time forecasting of sEMG features for trunk muscle fatigue using machine learning. IEEE Trans. Biomed. Eng. 2021; 68(2): 718–727.

5. Bueno DR, Lizano JM, Montano L. Muscular fatigue detection using sEMG in dynamic contractions. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 2015; 494–497.

6. Xu B, Wu Q, Xi C, He R. Recognition of the fatigue status of pilots using BF-PSO optimized multi-class GP classification with sEMG signals. Reliability Engineering and System Safety. 2020; 199(2).

7. Rampichini S, Vieira TM, Castiglioni P, et al. Complexity analysis of surface electromyography for assessing the myoelectric manifestation of muscle fatigue: A review. Entropy, 2020, 22(5): 529.

8. Lan N. Analysis of an optimal control model of multipoint arm movements. Biological Cybernetics. 1997.

9. De Luca CJ. Physiology and mathematics of myoelectric signals. IEEE Trans. Biomed. Eng. 1979; 26(6): 313–325.

10. Sun Z, Xi X, Yuan C, et al. Surface electromyography signal denoising via EEMD and improved wavelet thresholds. Math. Biosci. Eng. 2020; 17(6): 6945–6962.

11. Zhang Y, Chen Y, Yu H, et al. Learning Effective Spatial-Temporal Features for sEMG Armband-Based Gesture Recognition. IEEE Internet of Things Journal. 2020; 7: 6979–6992.

12. Georgakis A, Stergioulas L, Giakas G. Fatigue analysis of the surface EMG signal in isometric constant force contractions using the averaged instantaneous frequency. IEEE Transactions on Biomedical Engineering. 2003; 50(2): 262–265.

13. Kahl L, Hofmann UG. Comparison of algorithms to quantify muscle fatigue in upper limb muscles based on sEMG signals. Med. Eng. Phys. 2016; 38(11): 1260–1269.

14. Trybek P, Nowakowski M, Salowka J, et al. Sample Entropy of sEMG Signals at different stages of rectal cancer treatment. Entropy. 2018; 20(11): 863.

15. Mugnosso M, Zenzeri J, Hughes CML, et al. Coupling robot-aided assessment and surface electromyography (sEMG) to evaluate the effect of muscle fatigue on wrist position sense in the flexion-extension plane. Frontiers in Human Neuroscience. 2019; 13: 396.

16. Toro SFD, Santos-Cuadros S, Olmeda E, et al. Is the use of a low-cost sEMG sensor ualid to measure muscle fatigue? Sensors. 2019; 19(14): 3204.

17. Skavhaug IM, Lyons KR, Nemchuk A, et al. Learning to modulate the partial powers of a single sEMG power spectrum through a novel human-computer interface. Human Movement Science. 2016; 47: 60–69.

18. Liu Q, Liu Y, Zhang C, et al. sEMG-based dynamic muscle fatigue classification using SVM with improved whale optimization algorithm. IEEE Internet of Things Journal. 2021; 99: 1

19. Yun I, Jeung J, Song Y. Non-invasive quantitative muscle fatigue estimation based on correlation between sEMG signal and muscle mass. IEEE Access. 2020; 8: 51–57

20. Karlsson S, Yu J, Akay M. Time-frequency analysis of myoelectric signals during dynamic contractions: A comparative study. IEEE Trans. Biomed. Eng. 2000; 47(2): 228–238.

21. Dash M. Feature selection for classification. Intelligent Data Analysis. 1997.

22. Khalid S, Khalil T, Nasreen S. A survey of feature selection and feature extraction techniques in machine learning. In: Proceedings of the 2014 Science and Information Conference. 27–29 August 2014; London, UK.

23. Jain AK, Duin RPW, Mao J. Statistical pattern recognition: A review. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2000; 22(1): 4–37.

24. Cover T, Hart P. Nearest neighbor pattern classification. IEEE Transactions on Information Theory. 1967; 13(1): 21–27.

25. Cortes C, Vapnik V. Support-vector networks. Machine Learning. 1995; 20(3): 273–297.

Published
2025-03-24
How to Cite
Chu, X., Huang, D., & Yi, Y. (2025). Athletes muscle fatigue recognition model based on KPCA and SVM. Molecular & Cellular Biomechanics, 22(5), 1514. https://doi.org/10.62617/mcb1514
Section
Article