Research on optimization and design of sports teaching actions based on biomechanics

Abstract

The design of sports teaching approaches is an important part of improving athletic performance and skill development among players. As sports grow more competitive, the demand for new and effective teaching methods has never been higher. The limitations of conventional coaching techniques sometimes depend on anecdotal evidence and subjective assessments, which provide inconsistent outcomes for training. The purpose of this study is to enhance athletic performance and reduce injury risks by developing sports teaching actions based on biomechanics. The proposed novel chaos sparrow search fine-tuned efficient random forest (CSS-ERF) employed the relationship between biomechanical parameters and performance outcomes. Biomechanical data was gathered from athletes utilizing wearable sensors and motion capture technologies as they performed several sports-related activities. The data preprocessing will be cleaned to remove noise and outliers from the dataset. Ground Reaction Forces (GRF) are used to extract key features relevant to performance and injury risk from the preprocessed data. Findings show that training strategies and athlete performance have significantly improved, and the CSS-ERF model has demonstrated a high degree of accuracy in forecasting the best biomechanical configurations with an F1 value of 0.984, accuracy of 0.989, recall of 0.985, and precision of 0.986. By offering an innovative approach to enhancing sports actions through biomechanical insights and promoting a greater comprehension of movement mechanics and their impact on athletic performance, this research advances the area of sports science.