Optimization research on biomechanical characteristics and motion detection technology of lower limbs in basketball sports
Abstract
In basketball, the biomechanics of the lower limbs play a significant role in executing specific movements like sprints, jumps, and directional changes. Optimizing the performance of these movements is necessary for enhancing overall athletic performance and reducing injury risks. The objective of the research is to generate and execute a motion detection algorithm focusing on lower limbs in basketball utilizing a deep learning (DL) based approach. The study proposes the Refined Harries Hawks optimized Intelligent Long-Short Term Memory (RHH-ILSTM) method to improve the accuracy of detecting and analyzing biomechanical characteristics of lower limb movements. Data collection involved basketball players equipped with wearable sensors on their lower limbs to gather on-time data throughout dynamic movements to train the method. The data is pre-processed to remove noise, normalize values, and segment movements into discrete time intervals. Principal Component Analysis (PCA) is utilized to extract characteristics by reducing the dimensionality of the data while maintaining significant biomechanical aspects. The RHH-ILSTM system combines the exploration capabilities of the RHH optimization algorithm with ILSTM’s capacity to handle time-series data, leading to improved detection accuracy of lower limb biomechanics. The model efficiently captures crucial lower limb biomechanics, achieving a higher accuracy (94.58%) and recall (95.62%) in detecting movement phases and joint stresses. The proposed RHH-ILSTM method provides a robust solution for monitoring and analyzing lower limb movements in basketball.
References
1. Li, B. and Xu, X., 2021. Application of artificial intelligence in basketball sport. Journal of Education, Health and Sport, 11(7), pp.54-67.
2. Cabarkapa, D., Fry, A.C., Cabarkapa, D.V., Myers, C.A., Jones, G.T., Philipp, N.M., Yu, D. and Deane, M.A., 2022. Differences in biomechanical characteristics between made and missed jump shots in male basketball players. Biomechanics, 2(3), pp.352-360.
3. Liu, Y., 2022. A Study on the Importance of Core Strength and Coordination Balance during Basketball Based on Biomechanics. Molecular & Cellular Biomechanics, 19(3).
4. Laribi, M.A. and Zeghloul, S., 2020. Human lower limb operation tracking via motion capture systems. In Design and operation of human locomotion systems (pp. 83-107). Academic Press.
5. Bicer, M., Phillips, A.T., Melis, A., McGregor, A.H. and Modenese, L., 2022. Generative deep learning applied to biomechanics: A new augmentation technique for motion capture datasets. Journal of Biomechanics, 144, p.111301.
6. Hindle, B.R., Keogh, J.W. and Lorimer, A.V., 2021. Inertial‐Based Human Motion Capture: A Technical Summary of Current Processing Methodologies for Spatiotemporal and Kinematic Measures. Applied Bionics and Biomechanics, 2021(1), p.6628320.
7. Jiang, L. and Zhang, D., 2023. Deep learning algorithm based wearable device for basketball stance recognition in basketball. International Journal of Advanced Computer Science and Applications, 14(3).
8. Zhang, L., 2022. Applying deep learning-based human motion recognition system in sports competition. Frontiers in Neurorobotics, 16, p.860981.
9. Ji, R., 2020. Research on basketball shooting action based on image feature extraction and machine learning. IEEE Access, 8, pp.138743-138751.
10. Xu, T. and Tang, L., 2021. Adoption of machine learning algorithm-based intelligent basketball training robot in athlete injury prevention. Frontiers in Neurorobotics, 14, p.620378.
11. Chen, F. and Xu, J., 2024. Deep learning algorithm-based wearable device in basketball motion dynamic analysis. Applied Mathematics and Nonlinear Sciences.
12. Cheng, Y., Liang, X., Xu, Y. and Kuang, X., 2022. Artificial intelligence technology in basketball training action recognition. Frontiers in Neurorobotics, 16, p.819784.
13. Zhao, B., 2024. Deep learning-based basketball free throw attitude analysis and hit probability prediction system research. Applied Mathematics and Nonlinear Sciences, 9(1).
14. Zhang, L., 2024. Deep learning based fine-grained recognition technology for basketball movements. Systems and Soft Computing, 6, p.200134.
15. Zhao, Y., Wang, X., Li, J., Li, W., Sun, Z., Jiang, M., Zhang, W., Wang, Z., Chen, M. and Li, W.J., 2023. Using IoT Smart Basketball and Wristband Motion Data to Quantitatively Evaluate Action Indicators for Basketball Shooting. Advanced Intelligent Systems, 5(12), p.2300239.
16. Bo, Y., 2022. A Reinforcement Learning‐Based Basketball Player Activity Recognition Method Using Multisensors. Mobile Information Systems, 2022(1), p.6820073.
17. Zhang, L., 2022. Behaviour detection and recognition of college basketball players based on multimodal sequence matching and deep neural networks. Computational Intelligence and Neuroscience, 2022(1), p.7599685.
18. Liang, H., 2023. Improved EfficientDET algorithm for basketball players’ upper limb movement trajectory recognition. Applied Artificial Intelligence, 37(1), p.2225906.
19. Khobdeh, S.B., Yamaghani, M.R. and Sareshkeh, S.K., 2024. Basketball action recognition based on the combination of YOLO and a deep fuzzy LSTM network. The Journal of Supercomputing, 80(3), pp.3528-3553.
20. Luo, Y., Peng, Y. and Yang, J., 2024. Basketball Free Throw Posture Analysis and Hit Probability Prediction System Based on Deep Learning. International Journal of Advanced Computer Science & Applications, 15(4).
21. Lan, J. and Dong, X., 2024. Improved Q-Learning-Based Motion Control for Basketball Intelligent Robots Under Multi-Sensor Data Fusion. IEEE Access.
22. Gong, M., 2023. Prediction of Spinal Cord Injury in Basketball Sports Based on Machine Learning and Rehabilitation Treatment Effect of Upper Limb Dyskinesia.
23. Guo, X., Brown, E., Chan, P.P., Chan, R.H. and Cheung, R.T., 2023. Skill level classification in basketball free-throws using a single inertial sensor. Applied Sciences, 13(9), p.5401.
24. Li, X., Luo, R. and Islam, F.U., 2024. Tracking and detection of basketball movements using multi-feature data fusion and hybrid YOLO-T2LSTM network. Soft Computing, 28(2), pp.1653-1667.
25. Zheng, Z., Ma, H., Yan, W., Liu, H. and Yang, Z., 2021. Training data selection and optimal sensor placement for deep-learning-based sparse inertial sensor human posture reconstruction. Entropy, 23(5), p.588.
26. Hao, Z., Wang, X. and Zheng, S., 2021. Recognition of basketball players’ action detection based on visual image and Harris corner extraction algorithm. Journal of Intelligent & Fuzzy Systems, 40(4), pp.7589-7599.
Copyright (c) 2024 Weidong Cheng, Weimin Cheng
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
