student
Russian Federation
This article explores the construction and evaluation of the XGBoost machine learning model for classifying fitness exercises. Assessing the accuracy of human fitness exercise performance is a hot topic in machine learning and artificial intelligence. Machine learning algorithms used to address this issue can identify errors in movement technique, evaluate training effectiveness, and provide personalized recommendations for correcting physical activity and improving the biomechanics of human movement during patient rehabilitation. To address this issue, train, and test the model, the "Physical Therapy Exercises Dataset" from the UCI Machine Learning Repository was selected. The dataset consists of 1,378,015 records collected during gym training sessions involving five subjects performing eight types of physical therapy exercises using inertial measurement units and magnetic sensors. Each of the eight exercise classes is represented by 55 files (12.5% of the dataset), ensuring a balanced sample and eliminating model bias. All data were randomly divided into a training (80%) and a test (20%) set. The XGBoost model was built using the PyCharm integrated development environment and Notepad++. Data decimation was used to optimize performance, significantly reducing the time it took to build and evaluate the model. The user can select a decimation coefficient from 1 to 10. With maximum decimation (sample_rate=10), the sampling frequency is reduced from 25 Hz to 2.5 Hz. This optimization provides a tenfold acceleration in loading (from 3-5 minutes to 20-30 seconds) while maintaining classification accuracy at 90-92%. Data batching was also implemented, involving batch processing of 10,000 records per iteration to reduce the load on RAM. The accuracy of the constructed model was also compared with that of other classification methods. A streamlit application was selected for the interactive presentation of the study results. Among all the models built, XGBoost demonstrated the highest accuracy results, indicating its effectiveness. Therefore, the model can be effectively used as a tool for assessing the correctness of fitness exercises, for example, using a mobile or web app.
FITNESS EXERCISE CLASSIFICATION, MACHINE LEARNING, XGBOOST MODEL, TIME SERIES ANALYSIS, MODELING, CLASSIFICATION QUALITY METRICS
1. A.A. Vasilyuk, Innovations. Science. Education, 32, 1487-1492 (2021). EDN: https://elibrary.ru/LFAXEV
2. M.A. Podolskaya, A.S. Katasev, Kazan Medical Journal, 88, 4, 346-351 (2007). EDN: https://elibrary.ru/KVJJOL
3. A.S. Katasev, M.A. Podolskaya, Neurological Bulletin, 38, 3-4, 85-90 (2006). EDN: https://elibrary.ru/JVUFZT
4. A.Y. Nikitaeva, A.B.M. Salem, Journal of Institutional Studies, 14, 1, 108-126 (2022). DOI: https://doi.org/10.17835/2076-6297.2022.14.1.108-126; EDN: https://elibrary.ru/BSCCQN
5. V.F. Karpovich, Innovative science, 1, 2-2, 117-121 (2026). EDN: https://elibrary.ru/RCMJCI
6. V.V. Noskin, A.R. Donskaya, D.R. Cherkashin, S.G. Groshev, Modeling, Optimization and Information Technologies, 13, 4 (51) (2025).
7. V.I. Yankovsky, N.D. Todosiev, S.A. Shchukin, Yu.E. Gapanyuk, Dynamics of Complex Systems - 21st Century, 14, 3, 35-43 (2020). DOI: https://doi.org/10.18127/j19997493-202003-03; EDN: https://elibrary.ru/SZPWLT
8. G.P. Ivanova, Proceedings of the Department of Biomechanics of the P.F. Lesgaft University, 17, 6-10 (2023). EDN: https://elibrary.ru/HLPITG
9. R.N. Minnikhanov, T.R. Batorshin, R.M. Gabbazov, R.I. Fakhraziev, A.S. Katasev, M.V. Dagaeva, I.R. Badrutdinov, Electronic libraries, 28, 4, 884-902 (2025). DOI: https://doi.org/10.26907/1562-5419-2025-28-4-884-902; EDN: https://elibrary.ru/UFIWKX
10. O.A. Pyrnova, R.S. Zaripova, Information technologies in construction, social and economic systems, 1 (15), 82-84 (2019). EDN: https://elibrary.ru/AHFBTU
11. I.A. Medvedeva, M.V. Vanslav, M.A. Ragozina, Natural and Technical Sciences, 7 (170), 177-178 (2022).
12. M.V. Dagaeva, D.V. Kataseva, A.S. Katasev, Information and Security, 21, 4, 540-545 (2018). EDN: https://elibrary.ru/YTEQEP
13. A.S. Katasev, Ch.F. Akhatova, Science and Education: Scientific Publication of the Bauman Moscow State Technical University, 12, 34-42 (2012). EDN: https://elibrary.ru/PMKDOP
14. M.G. Nuriev, R.M. Gizatullin, V.A. Drozdikov, E.I. Pavlova, Journal of Radio Electronics, 6, 14-29 (2019). DOI: https://doi.org/10.30898/1684-1719.2019.6.7; EDN: https://elibrary.ru/HBOBRH
15. A.D. Obukhov, Scientific and Technical Bulletin of Information Technologies, Mechanics and Optics, 25, 5, 833-843 (2025). DOI: https://doi.org/10.17586/2226-1494-2025-25-5-833-843; EDN: https://elibrary.ru/CMRNEX
16. YES. Nabiullin, V.V. Kononova, S.V. Novikova, Herald of Technological University, 24, 6, 103-107 (2021). EDN: https://elibrary.ru/PJNLIK
17. K.A. Matveeva, R.N. Minnikhanov, A.S. Katasev, Herald of Technological University, 27, 1, 76-80 (2024). DOI: https://doi.org/10.55421/1998-7072_2024_27_1_76; EDN: https://elibrary.ru/ZLWHXQ
18. D.V. Kataseva, A.I. Barinov, Herald of Technological University, 25, 1, 69-72 (2022). EDN: https://elibrary.ru/ELCOYU
19. O.A. Pyrnova, D.P. Nikonorov, Economics and Management: Problems, Solutions, 12, 2 (155), 118-123 (2025).
20. R.I. Yusupova, R.S. Zaripova, M.G. Nuriev, Kazan science, 2, 201-203 (2025). EDN: https://elibrary.ru/BQNPGY
21. L.Yu. Emaletdinova, N.R. Vildanov, A.S. Katasev, Scientific and Technical Bulletin of the Volga Region, 6, 62-64 (2023). EDN: https://elibrary.ru/BLDCMH
22. E.V. Burnaev, Information Processes, 20, 2, 161-170 (2020). EDN: https://elibrary.ru/BBXRMQ
23. R.G. Asadullaev, A.N. Afonin, E.S. Shchetinina, Economics. Informatics, 48, 4, 735-746 (2021). DOI: https://doi.org/10.52575/2687-0932-2021-48-4-735-746; EDN: https://elibrary.ru/NFDBUX
24. https://archive.ics.uci.edu/: website. – URL: https://archive.ics.uci.edu/dataset/730/physical+therapy+exercises+dataset (date of access: 24.03.2026).
25. D.V. Kataseva, D.D. Loseva, Herald of Technological University, 25, 1, 77-80 (2022). EDN: https://elibrary.ru/JREERL
26. D.T. Le, M.H. Dao, Q.L.T. Nguyen, Information and Control Systems, 3 (106), 59-70 (2020).
27. R.N. Minnikhanov, T.R. Batorshin, R.M. Gabbazov, R.I. Fakhraziev, A.S. Katasev, Bulletin of Voronezh State University. Series: Systems Analysis and Information Technology, 3, 110-122 (2025). DOI: https://doi.org/10.17308/sait/1995-5499/2025/3/110-122; EDN: https://elibrary.ru/IZSMOZ
28. V.V. Dyakova, In Situ, 6, 8-11 (2022). DOI: https://doi.org/10.54296/18186173_2022_1_11
29. A.S. Katasev, D.V. Kataseva, Yu.N. Smirnov, V.L. Vasiliev, Herald of Technological University, 27, 9, 115-119 (2024). DOI: https://doi.org/10.55421/1998-7072_2024_27_9_115; EDN: https://elibrary.ru/FXYJYX
30. T.A. Puzynya, Innovations and Investments, 5, 520-521 (2024). EDN: https://elibrary.ru/JFLWNV
31. I.V. Anikin, R.N. Minnikhanov, M.V. Dagaeva, A.Z. Makhmutova, A.R. Mardanova, Bulletin of the National Center for Railways, 4 (50), 24-34 (2021). EDN: https://elibrary.ru/BDQRQN
32. K.V. Bellonin, A.V. Shokurov, Intelligent Systems. Theory and Applications, 25, 4, 256-260 (2021). EDN: https://elibrary.ru/YBKIPF
33. I.V. Anikin, A.R. Mardanova, Mathematical methods in technology and engineering, 1, 83-87 (2021). DOI: https://doi.org/10.52348/2712-8873_MMTT_2021_1_83; EDN: https://elibrary.ru/ABNHRI
34. C. Wang, C. Deng, S. Wang, Pattern Recognition Letters, 136, 190-197 (2020). DOI: https://doi.org/10.1016/j.patrec.2020.05.035; EDN: https://elibrary.ru/MUBEUP
35. O. N. Madyar, E. A. Popova, Economy: Yesterday, Today, Tomorrow, 14, 11-1, 226-239 (2024). DOI: https://doi.org/10.34670/AR.2024.95.50.025; EDN: https://elibrary.ru/LQXBQE
36. V.A. Bulanov, O.E. Fomicheva, Devices and systems. Management, control, diagnostics, 3, 33-37 (2020). DOI: https://doi.org/10.25791/pribor.03.2020.1160; EDN: https://elibrary.ru/QLMAXY
37. B. Kurbanov, A.S. Katasev, D.V. Kataseva, B.R. Zinnurov, Herald of Technological University, 27, 12, 158-164 (2024). DOI: https://doi.org/10.55421/1998-7072_2024_27_12_158; EDN: https://elibrary.ru/BWIUXW
38. A.N. Boruah, S.K. Biswas, S. Bandyopadhyay, Evolving Systems, 14, 1, 69-83 (2023). DOI: https://doi.org/10.1007/s12530-022-09434-4; EDN: https://elibrary.ru/LMDIZB
39. O.A. Pyrnova, A.S. Katasev, Engineering Herald of the Don, 4 (112), 578-584 (2024). EDN: https://elibrary.ru/TPGUGD
40. Q. Qiu, Applied and Computational Engineering, 135, 1, 175-183 (2025) DOI: https://doi.org/10.54254/2755-2721/2025.21217; EDN: https://elibrary.ru/VTNYNU
