Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?
Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur Graph Search.
Swimming coaches provide regular timed and technical feedback to swimmers and guide them efficiently in training sessions. Due to the complexity of swimmers' performance, which is not visible in qualitative observation, quantitative and objective performance evaluation can better assist the coach in this regard. Inertial measurement units (IMUs) are used in swimming for objective performance evaluation. In this study, we propose a new performance evaluation feedback (SmartSwim) using IMU and investigate its effects on the swimmer's weekly progress. Measurements were conducted each week with 15 competitive swimmers for 10 weeks using a Sacrum IMU. The SmartSwim report included a comprehensive representation of performance based on goal metrics of each phase extracted from the IMU signals. The swimmers were divided into two groups: the experimental and control groups. The SmartSwim report for each swimmer in the experimental group was given to the coach, who used it to adjust the training accordingly. The results showed that the experimental group outperformed the control group when comparing each swimmer, each session and the whole sessions. At the level of each individual, more members of the experimental group showed significant downward trend of average lap time (Mann-Kendall trend test, 95% confidence level). While comparing the sessions, the experimental group showed significantly lower lap time than the control group from the sixth session onwards (p-value < 0.05 from t-test). Considering all sessions, the experimental group showed significantly higher progress, lower average lap time, and more consistent records (Mann-Whitney U test at 95% confidence level) than the control group. This study demonstrated that SmartSwim can assist coaching by quantitatively assessing swimmers' performance, leading to more efficient training.
Kamiar Aminian, Farzin Dadashi, Fabien Massé, Mahdi Hamidi Rad, Vincent Gremeaux
Jian Wang, Matthias Finger, Qian Wang, Yiming Li, Matthias Wolf, Varun Sharma, Yi Zhang, Konstantin Androsov, Jan Steggemann, Leonardo Cristella, Xin Chen, Davide Di Croce, Rakesh Chawla, Matteo Galli, Anna Mascellani, João Miguel das Neves Duarte, Tagir Aushev, Lei Zhang, Tian Cheng, Yixing Chen, Werner Lustermann, Andromachi Tsirou, Alexis Kalogeropoulos, Andrea Rizzi, Ioannis Papadopoulos, Paolo Ronchese, Hua Zhang, Siyuan Wang, Tao Huang, David Vannerom, Michele Bianco, Sebastiana Gianì, Sun Hee Kim, Kun Shi, Wei Shi, Abhisek Datta, Jian Zhao, Federica Legger, Gabriele Grosso, Ji Hyun Kim, Donghyun Kim, Zheng Wang, Sanjeev Kumar, Wei Li, Yong Yang, Geng Chen, Ajay Kumar, Ashish Sharma, Georgios Anagnostou, Joao Varela, Csaba Hajdu, Muhammad Ahmad, Ekaterina Kuznetsova, Ioannis Evangelou, Muhammad Shoaib, Milos Dordevic, Meng Xiao, Sourav Sen, Xiao Wang, Kai Yi, Jing Li, Rajat Gupta, Zhen Liu, Muhammad Waqas, Hui Wang, Seungkyu Ha, Long Wang, Pratyush Das, Miao Hu, Anton Petrov, Xin Sun, Xin Gao, Chen Chen, Valérie Scheurer, Giovanni Mocellin, Muhammad Ansar Iqbal, Lukas Layer