This 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.

This study aims to profile biomechanical abilities during sprint front crawl by identifying technical stroke characteristics, in light of performance level. Ninety-one recreational to world-class swimmers equipped with a sacrum-worn IMU performed 25 m all-out. Intra and inter-cyclic 3D kinematical variabilities were clustered using a functional double partition model. Clusters were analysed according to (1) swimming technique using continuous visualisation and discrete features (standard deviation and jerk cost) and (2) performance regarding speed and competition calibre using respectively one-way ANOVA and Chi-squared test as well as Gamma statistics. Swimmers displayed specific technical profiles of intra-cyclic (smoothy and jerky) and inter-cyclic stroke regulation (low, moderate and high repeatability) significantly discriminated by speed (p < 0.001, η² = 0.62) and performance calibre (p < 0.001, V = 0.53). We showed that combining high levels of both kinds of variability (jerky + low repeatability) are associated with highest speed (1.86 ± 0.12 m/s) and competition calibre (ℽ = 0.75, p < 0.001). It highlights the crucial importance of variabilities combination. Technical skills might be driven by a specific alignment of stroke pattern and its associated dispersion according to the task constraints. This data-driven approach can assist eyes-based technical evaluation. Targeting the development of an explosive swimming style with a high level of body stability should be considered during training of sprinters.

Purpose: To investigate technical regulation mechanisms of long-distance swimmers that differentiate optimal pacing strategies and the underlying kinematic parameters. Methods: Twenty-one national and international swimmers were equipped with a sacrum-worn inertial measurement unit performed during 5000-m indoor French championships. Percentage of critical swimming speed (CSS), stroke rate, stroke length, jerk cost, stroke index, and mechanical proficiency score were computed by lap. Athletes were divided into groups of pacing effectiveness based on optimal potential performance level (OPPL)—optimal (nearOPPL) and suboptimal (farOPPL)—using functional clustering of percentage of the CSS. Race sections were analyzed with a change-in-slope detection method. Common stroke-regulation abilities and deviations by pacing groups were profiled by fitting hierarchical generalized additive models between mechanical variables and laps. Results: The 2 clusters were discriminated by percentage of the CSS sustainment (P < .01). Optimal performers showed a +41.4% more stable pacing (2 race sections vs 3 for farOPPL) and a +36.7% higher end spurt, with a trend combining higher overall stroke rate (P = .08) with lower jerk cost (P = .17). Functional profiles showed that maintaining a higher stroke length and stroke index in a fatigued state, rather than overall values, allows the swinner to reach OPPL (P < .001). High regulation of mechanical proficiency score across the race, in line with pacing expectations of particular race sections, is a game changer to sustain CSS (P < .001). Conclusions: Specific profiles of stroke regulations, regarding tradeoff between stroke smoothness and resultant speed, lead to optimal pacing during the 5000-m. The results of this study enhance the technical understanding of optimal pacing in long-distance pool races for coaches and swimmers.

This study explores the use of GPS tracking to analyse pacing and trajectory patterns continuously throughout a 10-km open-water race. Five elite or world-class swimmers were monitored during the French National Championships using a global navigation satellite system device recording 1 Hz position data to assess latitude-longitude time series, distance, and modelled instantaneous swimming speed via locally estimated scatterplot smoothing. Based on individual critical velocity (CV), time and distance spent in four intensity zones ( 102%CV) were calculated. Substantial intra- and inter-individual variability in pacing intensity and race trajectories were highlighted over the race. Swimmers covered a median of 10,262 m[10259- 10,268], spending 619 m[593-632] >CV and 8585 m[8346-9183] <98%CV. Marked differences in pacing regulations were observed, with the race winner delaying high-intensity efforts until the end-spurt and managing intra-lap periodic accelerations around buoys and feeding stations while remaining CV could be associated with poorer outcomes. Beyond traditional split-time analysis, combining high-resolution GPS devices with CV modelling enabled spatiotemporal profiling of race dynamics and individual behaviour, offering novel tactical insights into pivotal race moments, drafting use and related trajectory selection. Although exploratory, this proof-of-concept supports advanced performance analysis in open-water elite swimming.

This study aims to identify the stroke mechanics regulations that underlie pacing optimization and differentiate final performance in the 400 m front-crawl across different performance levels. 157 all-out 400 m trials from trained to elite swimmers equipped with a sacrum worn IMU were analyzed. Hierarchical generalized additive models were fitted to describe (1) the technical predictors of final performance, through the interrelationships between averaged kinematics (i.e., stroke rate (SR), stroke length (SL), jerk cost (JC)) and mean speed, and (2), the profiles of pacing and associated stroke mechanics regulations leading to performance. These models depict both the common patterns shared by all swimmers and the specific group deviations by performance level (G1 -slowest- to G4 -fastest-) from population trends. All swimmers shared a reverse-J-shaped pacing (p < 0.001). The fastest swimmers reduce pacing variability with a relatively slower start, a minimized drop in speed in the middle of the race, and a greater end-spurt than the population trend (p < 0.05). Their stroke mechanics are effectively adapted to the requirements of such specific race sections, both through a U-shaped JC with higher magnitude (p < 0.001) and a continuous adaptation of the SR (p < 0.01) and SL (p < 0.01) combination. A high average SL (i.e., at least 1.50 m.stroke-1), coupled with an SR close to 70 strokes.min-1 and maximizing stroke smoothness at race pace, are critical technical abilities for optimizing final performance. Technical training should prioritize the reduction of intra-cyclic acceleration variations at race pace as a key driver of 400 m performance development. The best performers lower pacing variability by amplifying the magnitude of kinematic regulations, particularly in terms of stroke smoothness management. Such underlying adaptations in stroke mechanics play a pivotal role in continuous speed control throughout the race. The findings of this study enhance the technical understanding of discriminative 400 m pacing skills for coaches and swimmers.