Biomechanical analysis and tactical awareness cultivation of badminton players’ variable speed running training
Abstract
In recent years, the combination of machine learning (ML) and computer vision has influenced sports training approaches, notably for monitoring player performance. This research gives a detailed biomechanical analysis of badminton players during speed-running training, using insights from ML techniques. Key biomechanical metrics such as gait, speed, and acceleration are assessed by tracking players’ motions and the dynamics of their running patterns using computer vision techniques. The badminton stroke video dataset was collected from the Kaggle source. To ensure high-quality input for analysis, the data preprocessing stages include video stabilization with the Kalman filter, noise reduction with Gaussian smoothing, and frame extraction using temporal sampling. Feature extraction approaches like the histogram of oriented gradients (HOG) are used for shape recognition and optical flow for motion tracking. The study provides the use of a simulation environment built on a Modified Ant Lion Optimized Decision Trees (MALO+DT) model trained on historical training data, which allows for the prediction of player movement and biomechanical adjustments based on contextual features such as environment variations and player fatigue. The findings demonstrate that speed running training improves tactical awareness and decision-making in dynamic environments. The performance of the suggested approach was evaluated on the Python platform. The model achieves good prediction accuracy (98.3%), recall (97.4%), F1-score (98%), and precision (97.5%), demonstrating a model's abilities for analysis the effect of training on player biomechanics. Furthermore, the significance of this study is assessed for tactical awareness development, providing coaches and analysts with actionable insights to enhance practices and increase player performance. The findings show that combining biomechanical analysis with speed running training significantly improves players’ adaptability and responsiveness during matches, resulting in a more strategic approach to badminton teaching.
References
1. Chen, Y., Zulnaidi, H. and Syed Ali, S.K.B. Study on the eye movement characteristics of badminton practitioners of different levels regarding visual attention. Frontiers in Psychology; 2023.13, p.1026006.
2. Yinghao, L. and Jawis, M.N. Modeling performance evaluation in badminton sports: a fuzzy logic approach. Salud, Ciencia y Tecnología-Serie de Conferencias; 2024.3, pp.986-986.
3. Zhao, W., Wang, C., Bi, Y. and Chen, L. Effect of integrative neuromuscular training for injury prevention and sports performance of female badminton players. BioMed research international; 2021.2021(1), p.5555853.
4. He, Z., Liu, G., Zhang, B., Ye, B. and Zhu, H. Impact of specialized fatigue and backhand smash on the ankle biomechanics of female badminton players. Scientific Reports; 2024.14(1), p.10282.
5. Alsaudi, A.T.B.D. The influence of drill exercise and eye coordination foot methods toward the smash skill of badminton. In 1st South Borneo International Conference on Sport Science and Education (SBICSSE 2019) (pp. 76-82). Atlantis Press.2020.
6. Wang, W.Y., Shuai, H.H., Chang, K.S. and Peng, W.C., 2022, June. Shuttlenet: Position-aware fusion of rally progress and player styles for stroke forecasting in badminton. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 4, pp. 4219-4227).
7. Darden, G. and Wilson, S. From Practice to Competition: A Coach’s Guide for Designing Training Sessions to Improve the Transfer of Learning. Rowman & Littlefield. 2023.
8. Tan, S. and Toe, T. Predicting Shot Accuracy in Badminton Using Quiet Eye Metrics and Neural Networks.2024.
9. Robertson, K., De Waelle, S., Deconinck, F.J. and Lenoir, M. Differences in expertise level for anticipatory skill between badminton ‘in game’strokes and serves. International Journal of Sports Science & Coaching; 2022.17(4), pp.782-791.
10. Liu, W., Zhu, Y., Guo, W., Wang, X. and Yu, S. Gaming Tree Based Evaluation Model for Badminton Tactic Benefit Analysis and Prediction. Applied Sciences; 2023.13(13), p.7380.
11. Luo, J., Hu, Y., Davids, K., Zhang, D., Gouin, C., Li, X. and Xu, X. Vision-based movement recognition reveals badminton player footwork using deep learning and binocular positioning. Heliyon; 2022.8(8).
12. Peng, X. and Tang, L. Biomechanics analysis of real-time tennis batting images using Internet of Things and deep learning. The Journal of Supercomputing; 2022.78(4), pp.5883-5902.
13. Ma, S., Soh, K.G., Japar, S.B., Xu, S. and Guo, S. Maximizing the performance of badminton athletes through core strength training: Unlocking their full potential using machine learning (ML) modeling. Heliyon; 2024.
14. Malik, A. and Jain, R., 2023, June. Badminton Action Analysis Using LSTM. In 2023 International Conference on Applied Intelligence and Sustainable Computing (ICAISC) (pp. 1-6). IEEE.
15. Yu, L., 2023, August. Badminton Action Recognition and Detection using Artificial Intelligence and Neural Network Technology. In 2023 International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) (pp. 501-506). IEEE.
16. Mekruksavanich, S., Jantawong, P., Hnoohom, N. and Jitpattanakul, A., 2022, October. Badminton activity recognition and player assessment based on motion signals using deep residual network. In 2022 IEEE 13th International Conference on Software Engineering and Service Science (ICSESS) (pp. 80-83). IEEE.
17. Jian, C.Z., Abdullah, J. and Lenando, H., 2022, December. DL-Shuttle: Badminton Coaching Training Assistance System Using Deep Learning Approach. In 2022 International Conference on Digital Transformation and Intelligence (ICDI) (pp. 1-7). IEEE.
18. Rahmad, N.A. and As’ari, M.A., 2020, April. The new Convolutional Neural Network (CNN) local feature extractor for automated badminton action recognition on vision based data. In Journal of Physics: Conference Series (Vol. 1529, No. 2, p. 022021). IOP Publishing.
19. Liu, J. and Liang, B. An action recognition technology for badminton players using deep learning. Mobile Information Systems; 2022.2022(1), p.3413584.
20. Deng, J., Zhang, S. and Ma, J. Self-Attention-Based Deep Convolution LSTM Framework for Sensor-Based Badminton Activity Recognition. Sensors; 2023.23(20), p.8373.
21. Wang, Y. and Wu, L. Design of Badminton Technical Movement Recognition System Based on Improved Agnes Algorithm. Journal of Electrical Systems. 2024.20(6s), pp.1981-1991.
22. Lianju, L. and Haiying, Z. Research on badminton take-off recognition method based on improved deep learning. Journal of Ambient Intelligence and Humanized Computing; 2024. pp.1-14.
23. Van Herbruggen, B., Fontaine, J., Simoen, J., De Mey, L., Peralta, D., Shahid, A. and De Poorter, E. Strategy analysis of badminton players using deep learning from IMU and UWB wearables. Internet of Things; 2024.27, p.101260.
24. Xu, F. and Zhu, W. Evaluation of neurodiagnostic insights for enhanced evaluation and optimization of badminton players’ physical function via data mining technique. SLAS technology; 2024. p.100138.
25. Kaggle. badminton_storke_video.Available online:https://www.kaggle.com/datasets/shenhuichang/badminton-storke-video(accessed on 03 October2024).
26. Zhao, W., Wang, C., Bi, Y. and Chen, L. Effect of integrative neuromuscular training for injury prevention and sports performance of female badminton players. BioMed research international; 2021.2021(1), p.5555853.
Copyright (c) 2024 Weiguo Li
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
