Publications scientifiques & conférences

Publications Scientifiques

Automatic Swimming Activity Recognition and Lap Time Assessment Based on a Single IMU: A Deep Learning ApproachThis study presents a deep learning model devoted to the analysis of swimming using a single Inertial Measurement Unit (IMU) attached to the sacrum. Gyroscope and accelerometer data were collected from 35 swimmers with various expertise levels during a protocol including the four swimming techniques. The proposed methodology took high inter- and intra-swimmer variability into account and was set up for the purpose of predicting eight swimming classes (the four swimming techniques, rest, wallpush, underwater, and turns) at four swimming velocities ranging from low to maximal. The overall F1-score of classification reached 0.96 with a temporal precision of 0.02 s. Lap times were directly computed from the classifier thanks to a high temporal precision and validated against a video gold standard. The mean absolute percentage error (MAPE) for this model against the video was 1.15%, 1%, and 4.07%, respectively, for starting lap times, middle lap times, and ending lap times. This model is a first step toward a powerful training assistant able to analyze swimmers with various levels of expertise in the context of in situ training monitoring.

Drafting of two passive swimmer scale models for open-water racesWe examined interactions in water channels between swimmer-shaped objects moving at different speeds. Results showed that the ideal place for drafting is at the hip of a neighboring swimmer or just behind a lead swimmer. The former reduces drag by 30% and the latter reduces drag by 40%. Results were confirmed by CFD simulations.

Effect of breathing conditions on relationships between impairment, breathing laterality and coordination symmetry in elite para swimmers - Scientific Reports

Fête de la Science 2023

Projet_depart_V1.pdf

Projet_Drafting_V1.pdf

Conférences

www.spowi.uni-leipzig.de/sportbiomechanik/bms

Page updated

Google Sites

Report abuse