Fatigue plays a critical role in sports science, significantly affecting recovery, training effectiveness, and overall athletic performance. Understanding and predicting fatigue is essential to optimize training, prevent overtraining, and minimize the risk of injuries. The aim of this study is to leverage Human Activity Recognition (HAR) through deep learning methods for dimensionality reduction. The use of Adversarial AutoEncoders (AAEs) is explored to assess and visualize fatigue in a two-dimensional latent space, focusing on both semi-supervised and conditional approaches. By transforming complex time-series data into this latent space, the objective is to evaluate motor changes associated with fatigue within the participants’ motor control by analyzing shifts in the distribution of data points and providing a visual representation of these effects. It is hypothesized that increased fatigue will cause significant changes in point distribution, which will be analyzed using clustering techniques to identify fatigue-related patterns. The data were collected using a Wii Balance Board and three Inertial Measurement Units, which were placed on the hip and both forearms (distal part, close to the wrist) to capture dynamic and kinematic information. The participants followed a fatigue-inducing protocol that involved repeating sets of 10 repetitions of four different exercises (Squat, Right Lunge, Left Lunge, and Plank Jump) until exhaustion. Our findings indicate that the AAE models are effective in reducing data dimensionality, allowing for the visualization of fatigue’s impact within a 2D latent space. The latent space representation provides insights into motor control variations, revealing patterns that can be used to monitor fatigue levels and optimize training or rehabilitation programs.

The accurate measurement of spatiotemporal parameters, such as step length and step frequency, is crucial for analyzing running and sprinting performance. Traditional methods like video analysis and force platforms are either time consuming or limited in scope, prompting the need for more efficient technologies. This study evaluates the effectiveness of a commercial Global Positioning System (GPS) unit integrated with an Inertial Measurement Unit (IMU) in capturing these parameters during sprints at varying velocities. Five experienced male runners performed six 40 m sprints at three velocity conditions (S: Slow, M: Medium, F: Fast) while equipped with a GPS-IMU system and an optical system as the gold standard reference. A total of 398 steps were analyzed for this study. Step frequency, step length and step velocity were extracted and compared using statistical methods, including the coefficient of determination (r²) and root mean square error (RMSE). Results indicated a very large agreement between the embedded system and the reference system, for the step frequency (r² = 0.92, RMSE = 0.14 Hz), for the step length (r² = 0.91, RMSE = 0.07 m) and the step velocity (r² = 0.99, RMSE = 0.17 m/s). The GPS-IMU system accurately measured spatiotemporal parameters across different running velocities, demonstrating low relative errors and high precision. This study demonstrates that GPS-IMU systems can provide comprehensive spatiotemporal data, making them valuable for both training and competition. The integration of these technologies offers practical benefits, helping coaches better understand and enhance running performance. Future improvements in sample rate acquisition GPS-IMU technology could further increase measurement accuracy and expand its application in elite sports.