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

Area of Science:

• Sports Science
• Biomechanical Engineering
• Artificial Intelligence in Sports

Background:

• Traditional athlete fitness assessments use standardized quantitative tests.
• Qualitative analysis can enhance decision-making in sports performance evaluation.
• Limitations exist in current methods for assessing the quality of sports tests.

Purpose of the Study:

• To propose an innovative approach integrating artificial neural networks (ANNs) with wearable technology for sports test quality assessment.
• To overcome limitations in current quantitative sports testing methods.
• To establish diverse criteria for qualitative athlete evaluation and optimize analysis.

Main Methods:

• Utilizing Inertial Motion Units (IMUs) to capture precise movement data during sports tests.
• Computationally processing IMU data for detailed analysis.
• Applying ANNs to optimize the analysis of qualitative movement data and athlete performance.

Main Results:

• Revealed insights into factors affecting athlete performance trajectories, including fatigue, endurance, and biomechanical efficiency.
• Demonstrated significant improvements in the accuracy and depth of athlete performance evaluation.
• Successfully developed and validated novel metrics for sports science and performance analysis.

Conclusions:

• The integration of ANNs and wearable technology offers a more effective method for assessing sports test quality.
• This innovative approach enhances the depth and accuracy of athlete performance evaluation.
• The study contributes novel metrics and methods to advance sports science and performance analysis.