Comprehensive evaluation of physical education based on personalized training plan generation algorithm and biomechanics
Abstract
This work builds on advancements in biomechanics and artificial intelligence to develop personalized training plans, enhancing physical education by optimizing movement performance and reducing injury risks. However, limitations include reliance on accurate biomechanical data, potential algorithmic bias in training plan personalization, and challenges in integrating real-time feedback from wearable devices. The aim is to establish a comprehensive evaluation framework for physical education, leveraging personalized training algorithms and biomechanics to enhance performance and create tailored data-driven exercise plans. We propose the Versatile Hunter-Prey Optimizer-tuned Intelligent CNN (VHO-ICNN) to optimize ICNN parameters through VHO algorithms, thereby improving performance analysis, movement optimization, and injury prevention in athletes. The BFP and BMI datasets contain data for various human features and are utilized for biomechanical analysis and optimizing physical activities in sports and education. To preprocess the data, we employ z-score normalization to standardize joint position data, ensuring uniformity across features. Additionally, the Fourier Transform is applied for feature extraction, allowing us to analyze the frequency components of movements and enhance the model's performance. After evaluation, the results demonstrate an F1-score of 92.37%, accuracy of 93.41%, recall of 96.22%, and precision of 92.95%. The results indicate that the VHO-ICNN significantly improves classification accuracy and reduces injury risk, demonstrating its potential as a powerful tool in physical education. At the cell molecular biomechanics level, cells in tissues like muscles and ligaments are affected by mechanical forces during exercise. These forces can change how molecules in cells work. When we design personalized training, understanding these cell changes can help. If we know how cells react to different forces, we can make better training plans. This can make muscles stronger and less likely to get injured. It also ties in with the data we get from biomechanical analysis and the algorithms we use. So, adding cell molecular biomechanics knowledge makes our approach to physical education and athlete training even better.
References
1. Liu, Z. and Wang, X., 2023. Action recognition for sports combined training based on wearable sensor technology and SVM prediction. Preventive Medicine, 173, p.107582. doi:10.1016/j.ypmed.2023.107582
2. Imran, H.A., 2022. Khail-net: A shallow convolutional neural network for recognizing sports activities using wearable inertial sensors. IEEE Sensors Letters, 6(9), pp.1-4. doi:10.1109/LSENS.2022.3197396
3. Zhang, L., 2022. Applying deep learning-based human motion recognition system in sports competition. Frontiers in Neurorobotics, 16, p.860981. doi:10.3389/fnbot.2022.860981
4. Brumann, C., Kukuk, M. and Reinsberger, C., 2021. Evaluation of open-source and pre-trained deep convolutional neural networks suitable for player detection and motion analysis in squash. Sensors, 21(13), p.4550. doi:10.3390/s21134550
5. Han, C. and Liu, P., 2024. Effect of Deep Learning Algorithm Incorporating Attention Module Optimisation on Assisted Training for Youth Running Sports. IEEE Access. doi:10.1109/ACCESS.2024.3443339
6. Liang, W., Wang, F., Fan, A., Zhao, W., Yao, W. and Yang, P., 2023. Extended application of inertial measurement units in biomechanics: From activity recognition to force estimation. Sensors, 23(9), p.4229. doi:10.3390/s23094229
7. Zhang, L., 2022. Applying deep learning-based human motion recognition system in sports competition. Frontiers in Neurorobotics, 16, p.860981.doi:10.3389/fnbot.2022.860981.
8. Meng, Q., 2024. Intelligent Generation System for Personalized Physical Training Programs and the Effect of Practical Application. Applied Mathematics and Nonlinear Sciences, 9(1). doi:10.2478/amns-2024-2166
9. Zhang, L., Sengan, S. and Manivannan, P., 2022. The capture and evaluation system of student actions in physical education classroom based on deep learning. Journal of Interconnection Networks, 22(Supp02), p.2143025. doi:10.1142/S0219265921430258
10. Ba, Y. and Qi, L., 2021. Construction of WeChat mobile teaching platform in the reform of physical education teaching strategy based on deep neural network. Mobile Information Systems, 2021(1), p.3532963. doi:10.1155/2021/3532963
11. Fang, L., 2022. Construction of Physical Education Quality Evaluation Index and Analysis with Wearable Device. Computational Intelligence and Neuroscience, 2022(1), p.1190394. doi:10.1155/2022/1190394
12. Liu, T., Wilczyńska, D., Lipowski, M. and Zhao, Z., 2021. Optimization of a sports activity development model using artificial intelligence under new curriculum reform. International Journal of Environmental Research and Public Health, 18(17), p.9049. doi:10.3390/ijerph18179049
13. Zhao, L., 2023. A hybrid deep learning-based intelligent system for sports action recognition via visual knowledge discovery. IEEE Access, 11, pp.46541-46549. doi:10.1109/ACCESS.2023.3275012
14. Qiu, Y., Guan, Y. and Liu, S., 2023. The analysis of infrared high-speed motion capture system on motion aesthetics of aerobics athletes under biomechanics analysis. Plos one, 18(5), p.e0286313. doi:10.1371/journal.pone.0286313
15. Wu, C.H., Wu, T.C. and Lin, W.B., 2023. Exploration of applying pose estimation techniques in table tennis. Applied Sciences, 13(3), p.1896. doi:10.3390/app13031896
16. Shao, E., Mei, Q., Ye, J., Ugbolue, U.C., Chen, C. and Gu, Y., 2022. Predicting coordination variability of selected lower extremity couplings during a cutting movement: An investigation of deep neural networks with the LSTM structure. Bioengineering, 9(9), p.411. doi:10.3390/bioengineering9090411
17. Amerineni, R., Gupta, L., Steadman, N., Annauth, K., Burr, C., Wilson, S., Barnaghi, P. and Vaidyanathan, R., 2021. Fusion models for generalized classification of multi-axial human movement: Validation in sports performance. Sensors, 21(24), p.8409. doi:10.3390/s21248409
18. Liu, X., Gao, B., Suleiman, B., You, H., Ma, Z., Liu, Y. and Anaissi, A., 2023. Privacy-preserving personalized fitness recommender system P3FitRec: a multi-level deep learning approach. ACM Transactions on Knowledge Discovery from Data, 17(6), pp.1-24. doi:10.1145/3572899
19. Chatterjee, A., Prinz, A., Riegler, M.A. and Meena, Y.K., 2023. An automatic and personalized recommendation modeling in activity eCoaching with deep learning and ontology. Scientific Reports, 13(1), p.10182. doi:10.1038/s41598-023-37233-7
20. Aguilar-Agon KW, Capel AJ, Martin NRW, Player DJ, Lewis MP. Mechanical loading stimulates hypertrophy in tissue-engineered skeletal muscle: Molecular and phenotypic responses. J Cell Physiol. 2019;234(12):23547-23558. doi:10.1002/jcp.28923
21. Baldwin KM, Haddad F. Skeletal muscle plasticity: cellular and molecular responses to altered physical activity paradigms. Am J Phys Med Rehabil. 2002;81(11 Suppl):S40-S51. doi:10.1097/01.PHM.0000029723.36419.0D
22. Furrer R, Handschin C. Molecular aspects of the exercise response and training adaptation in skeletal muscle. Free Radic Biol Med. 2024;223:53-68. doi:10.1016/j.freeradbiomed.2024.07.026
23. Coffey VG, Hawley JA. The molecular bases of training adaptation. Sports Med. 2007;37(9):737-763. doi:10.2165/00007256-200737090-00001
24. Camera DM, Smiles WJ, Hawley JA. Exercise-induced skeletal muscle signaling pathways and human athletic performance. Free Radic Biol Med. 2016;98:131-143. doi:10.1016/j.freeradbiomed.2016.02.007
25. Constantin-Teodosiu D, Constantin D. Molecular Mechanisms of Muscle Fatigue. Int J Mol Sci. 2021;22(21):11587. Published 2021 Oct 27. doi:10.3390/ijms222111587
27. Jiao, X., 2022. A factorization deep product neural network for student physical performance prediction. Computational Intelligence and Neuroscience, 2022(1), p.4221254.
28. Jiang, G., 2022. Construction of Correlation Analysis Model of College Students’ Sports Performance Based on Convolutional Neural Network. Computational Intelligence and Neuroscience, 2022(1), p.3621316.
Copyright (c) 2025 Bingjie Sun
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.
Submit a Paper
