Research on recognition of Wushu motion boxing method based on PSO-BP neural network

  • Jianhui Wang Department of Physical Education, North China Institute of Aerospace Engineering, Langfang 065000, China
  • Peiyuan Li Department of Physical Education, North China Institute of Aerospace Engineering, Langfang 065000, China
  • Shichun Li Department of Physical Education, North China Institute of Aerospace Engineering, Langfang 065000, China
  • Yufeng Sun Department of Physical Education, North China Institute of Aerospace Engineering, Langfang 065000, China
  • Dengyue Li Department of Physical Education, Hebei University of Water Resources and Electric Engineering, Cangzhou 061000, China
DOI: https://doi.org/10.62617/mcb835
Keywords: neural network; Wushu action boxing; particle swarm optimization algorithm; identify the framework.
Article ID: 835

Abstract

Wushu movement full hair is a kind of fitness activity, and it is one of the ways for people to cultivate their self-cultivation and sentiment. It is of great significance to use motion capture system and data gloves to capture human movement posture and guide boxing practice in real time. The research of this topic uses neural network technology to construct a complete recognition framework of martial arts movements. Firstly, the collected martial arts movements are sorted out and a database is constructed. Because of the inherent defects of traditional BP algorithm, this is also because during the training of the modified algorithm, The network converges slowly, and easy to receive local minimum constraints, so this topic uses particle swarm optimization algorithm to optimize the initial weights and improved neural network algorithm to improve the learning rate and increase the reliability of the algorithm. Finally, through the martial arts action boxing recognition framework for testing, it is determined that the proposed algorithm is more effective.

References

1. Chang S, Wang J, Zhu H L C. Nonlinear dynamical modeling of neural activity using volterra series with GA-enhanced particle swarm optimization algorithm. Cognitive Neurodynamics, 2023, 17: 467–476.

2. Mohamed I, Helmi A M, Mohamed G. Estimation of solar cell parameters through utilization of adaptive sine–cosine particle swarm optimization algorithm. Neural computing & applications, 2024, 36: 8757–8773.

3. Ning C, Li X. Research on license plate recognition system based on BP neural network. In 2010 International Conference on Computer Application and System Modeling (ICCASM 2010), Taiyuan, 2021, 11: 482–485.

4. Sundarajoo S, Soomro D. Particle Swarm Optimization Trained Feedforward Neural Network for Under-Voltage Load Shedding. ECTI Transactions on Electrical Engineering, Electronics, and Communications, 2023, 21: 1-16.

5. Chen Y, Peng D, Xia F, et al. Infrared image recognition based on region growing method and BP neural network. Laser and Infrared, 2018, 48: 401–408.

6. Zhao Y, Li R, Zhou Y, et al. Identification accuracy of bridge moving load based on BP neural network. Science Technology and Engineering, 2021, 21: 6446–6453.

7. Jian Y, Wang X. Application of BP neural network in degumming damage identification of hidden frame glass curtain wall. Journal of the Chinese Ceramic Society, 2019, 47: 1073–1079

8. Zeng K, Jiang Z. BP Neural Network Face Recognition Based on Multi-genetic Algorithm. Computer Technology and Development, 2021, 22: 89-95.

9. Xian H, Song W, Wang X, et al. Method of identifying high-speed carrier station area by wavelet transform + BP neural network. Information Technology, 2020, 4: 139–143.

10. Li Z, Wang Z, Mao F. Design of BP neural network recognition system based on FPGA. Journal of Qingdao University: Engineering Technology Edition, 2019, 34: 2369–2372.

11. Monisha S, Nalini N. Implementation of tongue based leukemia detection using novel cat swarm optimization and compare with discrete particle swarm optimization algorithm using MATLAB. AIP Conference Proceedings, 2024, 2853: 020062.

12. Zhang D. Behavior recognition algorithm based on a dual-stream residual convolutional neural network. Journal of Intelligent Systems, 2024, 33: 142–6.

13. Alajlan A, Abdul R. ESOA-HGRU: egret swarm optimization algorithm-based hybrid gated recurrent unit for classification of diabetic retinopathy. Artificial Intelligence Review: An International Science and Engineering Journal, 2023, 56: 1617-1646.

14. Liu Z, Zhao K, Liu X, et al. Design and optimization of haze prediction model based on particle swarm optimization algorithm and graphics processor. Scientific Reports, 2024, 14: 9650.

Published
2025-01-24
How to Cite
Wang, J., Li, P., Li, S., Sun, Y., & Li, D. (2025). Research on recognition of Wushu motion boxing method based on PSO-BP neural network. Molecular & Cellular Biomechanics, 22(2), 835. https://doi.org/10.62617/mcb835
Issue
Vol. 22 No. 2 (2025)
Section
Article

Copyright (c) 2025 Author(s)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.

Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.