https://doi.org/10.1140/epjs/s11734-025-01701-0
Regular Article
Combining continuous wavelet transform and interpretable machine learning for evaluating rowing proficiency: a pilot study
1
Department of Biomedical Studies, Recreational and Adaptive Physical Education, Kursk State University, Radishcheva St., 33, 305000, Kursk, Russia
2
Department of Physical Rehabilitation and Sport Medicine, Polessky State University, Dneprovskoj Flotilii St., 23, 225710, Pinsk, Belarus
3
Department of Theoretical Physics, Kursk State University, Radishcheva St., 33, 305000, Kursk, Russia
a
anpilogov.sport@yandex.ru
b
postnikov@kursksu.ru
Received:
28
March
2025
Accepted:
19
May
2025
Published online:
26
May
2025
We address the possibility of evaluating the quality of the rowing technique and a level of rowing proficiently, in general, using quantitative measurable parameters, which are given by the continuous wavelet transform of the angular velocity time series obtained from gyroscope sensors fixed on a rower’s back. The wavelet-spectral characteristics of such periodic motions during three stages of elevating power load are compared for two groups of rowers: skilled and unskilled ones. To reveal, which quantitative features are the most valuable, the Principal Component Analysis and Stable and Interpretable RUle Sets (SIRUS) algorithms were applied. The comparison of machine learning-based quantitative rules with the rating given by professional sports trainers argues in favour of the proposed method’s usability for practical applications.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.