employee
Russian Federation
UDC 796.012.2
The article substantiates the pedagogical and managerial potential of neural network motion recognition technologies for improving the technique of finswimmers at the stage of sports mastery refinement. The purpose of the study is to theoretically substantiate and experimentally verify the effectiveness of using a digital circuit based on neural network motion recognition technologies for the operational correction and refinement of fin-swimming technique among athletes at the stage of sports mastery. Research methods and organization. The trial was conducted at the State Educational Institution of Additional Education of the Tula Region "Regional Comprehensive Sports School of Olympic Reserve" (Tula) in 2025 with the participation of athletes with more than 6 years of sporting experience and holding sports ranks of 1 and Candidate for Master of Sport (CMS). During an 8-week mesocycle, neural network feedback was used for the rapid adjustment of technical tasks. The assessed parameters included the time to swim 100 m with fins on the surface, the final 25 m segment, the variability of the frequency of undulating movements, the stability of the fin angle of attack, and the longitudinal stability of the body. Research results and conclusions. Significant improvements in performance and technical indicators have been identified, reflecting increased equipment resilience in the context of fatigue. It has been shown that algorithmic objectification of errors reduces pedagogical delay, enhances the precision of interventions, and supports the consolidation of an efficient motor pattern at competitive speed in real time.
fins swimming, motion recognition, neural network technologies, computer vision, sports biomechanics, biomechanical analysis, digital feedback
1. Somova A. E. (2022), “Digitalization of physical culture and sports”, Current Problems of Pedagogy and Psychology, Vol. 3, No. 3, pp. 30–35.
2. Prigoda G. S., Sidorenko A. S. (2025), “Analysis of the prospects of scientific and managerial approaches in improving the training process of qualified swimmers”, Proceedings of Tula State University. Physical Culture. Sport, No. 10, pp. 150–156, DOIhttps://doi.org/10.24412/2305-8404-2025-10-150-156.
3. Dudchenko P. P. (2025), “Contrast stimulation in the training process of finswimmers: influence on adaptation to high-intensity work”, Proceedings of Tula State University. Physical Culture. Sport, No. 9, pp. 91–98, DOIhttps://doi.org/10.24412/2305-8404-2025-9-91-98.
4. Chen L., Hu D. (2023), “An effective swimming stroke recognition system utilizing deep learning based on inertial measurement units”, Advanced Robotics, Vol. 37, No. 7, pp. 467–479, DOIhttps://doi.org/10.1080/01691864.2022.2160274.
5. Delhaye E., Bouvet A., Nicolas G., Vilas-Boas J. P., Bideau B., Bideau N. (2022), “Automatic Swimming Activity Recognition and Lap Time Assessment Based on a Single IMU: A Deep Learning Approach”, Sensors, Vol. 22, No. 15, Art. 5786, DOIhttps://doi.org/10.3390/s22155786.
6. Izaak S. I. (2021), “Digitalization and intellectualization of strategic management in sports”, Scientific Notes of the P.F. Lesgaft University, No. 5 (195), pp. 153–156.
7. Victor B., He Z., Morgan S., Miniutti D. (2017), “Continuous Video to Simple Signals for Swimming Stroke Detection with Convolutional Neural Networks”, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Honolulu, HI, USA, pp. 122–131, DOIhttps://doi.org/10.1109/CVPRW.2017.21.
8. Egorova N. M. (2022), “Digitalization of Russian sports: problems and prospects”, Proceedings of St. Petersburg State University of Economics, No. 4 (136), pp. 102–106.
9. Brunner G., Melnyk D., Sigfússon B., Wattenhofer R. (2019), “Swimming Style Recognition and Lap Counting Using a Smartwatch and Deep Learning”, Proceedings of the 2019 ACM International Symposium on Wearable Computers (ISWC ’19), London, United Kingdom, 9–13 Sept. 2019, New York, ACM, pp. 23–31, DOIhttps://doi.org/10.1145/3341163.3347719.
10. Giulietti N., Caputo A., Chiariotti P., Castellini P. (2023), “SwimmerNET: Underwater 2D Swimmer Pose Estimation Exploiting Fully Convolutional Neural Networks”, Sensors, Vol. 23, No. 4, Art. 2364, DOIhttps://doi.org/10.3390/s23042364.
