Leveraging artificial neural networks for enhanced athlete performance evaluation through IMU data analysis

Traditional methods of assessing athletes' physical fitness rely on standardized tests tailored to diverse demographics. However, emerging research suggests that supplementing quantitative assessments with qualitative analyses can significantly enhance decision-making processes. This study proposes an innovative approach that integrates artificial neural networks with wearable technology to overcome limitations in assessing the quality of sports tests. By utilizing Inertial Motion Units (IMUs), precise movement data during various tests are captured and computationally processed. This methodology not only facilitates the establishment of diverse criteria for qualitative athlete evaluation but also harnesses the power of neural networks to optimize analysis and decision-making. By examining data from these tests, the study has revealed insights into factors affecting athletes' performance trajectories, such as fatigue, endurance, and biomechanical efficiency. The results indicate significant improvements in the accuracy and depth of performance evaluation, demonstrating the effectiveness of the proposed method. Additionally, the development and validation of novel metrics contribute to advancing sports science and performance analysis.