Study of the Effectivity of Hybridized Partition-based and Hierarchical-based Clustering using Minkowski Distances on Spatial Data of Tennis Serve Pose for Sports Players to Maintain Good Health

This study examines the effectiveness of Partition-based and Hierarchical-based Clustering methods of utilizing Minkowski distances in analyzing spatial data of tennis serve poses, with the aim of improving sports players' health and performance. The research focuses on identifying biomechanical inefficiencies and patterns in serve poses that may contribute to injuries or suboptimal performance. By leveraging spatial data from motion-capture systems, the Random Forest algorithm classifies serve poses based on key biomechanical parameters, with Minkowski distances used to measure variations in spatial positioning. The proposed approach effectively identifies critical pose deviations and provides actionable insights for players and coaches to enhance technique while minimizing injury risks. Experimental results demonstrate the method's high accuracy in pose classification and its potential for real-time feedback systems in sports training. This research contributes to the field of sports analytics by offering a robust framework for pose analysis and promoting healthier athletic practices.