Machine Learning-Based Classification of Badminton Strokes Using IMU-Integrated Racket
DOI:
https://doi.org/10.15282/mekatronika.v7i1.12004Keywords:
Badminton, Machine Learning, Classification, IMUAbstract
Badminton, a fast-paced racket sport, demands precision, power, and strategic execution. While previous research has explored using inertial measurement units (IMUs) for stroke classification, this study presents an integration of sensor-embedded rackets with IMUs to provide a more accurate and automated approach. The collected motion data was processed and classified using machine learning models such as logistic regression, k-nearest neighbors (k-NN), and support vector machines (SVM). Of these, k-NN achieved the highest accuracy at 75 percent, with backhand strokes showing better classification precision. However, challenges in classifying forehand strokes suggest a need for further refinement in feature extraction. The study contributes a framework for improving stroke classification accuracy in badminton and offers insights into optimizing ML-driven motion analysis for more precise performance assessment in badminton.
References
[1] R. Venkat, “Badminton at the Olympics: A brief history,” [Online] 6 August 2024. Available from: https://olympics.com/en/featured-news/olympics-badminton-history-winners-debut-barcelona-1992
[2] Bernama, “Khairy says badminton is now Malaysia’s number one sport,” [Online] 15 December 2015. Available from: https://www.malaymail.com/news/sports/2015/12/15/khairy-says-badminton-is-now-malaysias-number-one-sport/1023599
[3] R. L. Sweeting, J. S. Wilson, Badminton: Basic Skills and Drills, Mayfield Publishing Company, 1991.
[4] B. V. Brahms, H. Ross (translator), Badminton Handbook: Training, Tactics, Competition, Meyer & Meyer Sport (UK) Limited, 2014.
[5] D. Toshniwal, A. Patil, N. Vachhani, “AI coach for badminton,” 2022 3rd International Conference for Emerging Technology (INCET), Belgaum, India, pp. 1-7, 2022.
[6] N. F. Ghazali, N. Shahar, M. A. As'Ari, “Badminton strokes recognition using inertial sensor and machine learning approach,” In 2022 2nd International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA), pp. 1-5, 2022.
[7] J. Lin, C. W. Chang, T. U. Ik, Y. C. Tseng “Sensor-based badminton stroke classification by machine learning methods,” In 2020 International Conference on Pervasive Artificial Intelligence (ICPAI), pp. 94-100, 2020.
[8] Y. Wang, W. Fang, J. Ma, X. Li, A. Zhong, “Automatic badminton action recognition using CNN with adaptive feature extraction on sensor data,” In book: Intelligent Computing Theories and Application, pp. 131-143, 2019.
[9] J. Lin, C. W. Chang, C. H. Wang, H. C. Chi, C. W. Yi, Y. C. Tseng, et al. “Design and implement a mobile badminton stroke classification system,” In 2017 19th Asia-Pacific Network Operations and Management Symposium (APNOMS), pp. 235-238, 2017.
[10] K. Xia, H. Wang, M. Xu, Z. Li, S. He, Y. Tang, “Racquet sports recognition using a hybrid clustering model learned from integrated wearable sensor,” Sensors, vol. 20, no. 6, p. 1638, 2020.
[11] D. Peralta, B. Van Herbruggen, J. Fontaine, W. Debyser, J. Wieme, E. De Poorter, “Badminton stroke classification based on accelerometer data: from individual to generalized models,” In 2022 IEEE International Conference on Big Data (Big Data), pp. 5542-5548, 2022.
[12] S. Mekruksavanich, P. Jantawong, N. Hnoohom, A. Jitpattanakul, “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, 2022.
[13] Y. Liu, “Recognition of badminton stroke actions using sensor technology,” UPB Scientific Bulletin, Series D: Mechanical Engineering, vol. 84, no. 1, pp. 55-64, 2022.
[14] Z. Y. Yip, I. Mohd Khairuddin, W. H. Mohd Isa, A. P. P. Abdul Majeed, M. A. Abdullah, M. A. Mohd Razman, “Badminton smashing recognition through video performance by using deep learning”, Mekatronika: Journal of Intelligent Manufacturing and Mechatronics, vol. 4, no. 1, pp. 70–79, 2022.
[15] I. Ghosh, S. R. Ramamurthy, A. Chakma, N. Roy, “DeCoach: Deep learning-based coaching for badminton player assessment,” Pervasive and Mobile Computing, vol. 83, p. 101608, 2022.
[16] W. H. M. Isa, M. A. Abdullah, M. A. M. Razman, A. P. P. A. Majeed, I. M. Khairuddin, “Deep learning algorithms for recognition of badminton strokes: A study using SDNN, RNN, and RNN-GRU models with off-court video capture,” International Conference on Mechatronics and Intelligent Robotics, pp. 53-60, 2023.
[17] M. Seong, G. Kim, D. Yeo, Y. Kang, H. Yang, J. DelPreto, et al. “Multi sense badminton: Wearable sensor–based biomechanical dataset for evaluation of badminton performance,” Scientific Data, vol. 11, no. 1, p. 343, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
