Study on the Intelligent Muscle Force Monitoring System Assisting Elite Hurdle Athletes in Personalized Take-off Point Selection and Muscle Force Precision Improvement

Abstract

The rationality of the takeoff point and the precision of muscle strength are key factors determining elite hurdlers' hurdling efficiency, rhythm between hurdles, and injury risk. Current training relies on coaches' subjective experience (e.g., step counting/visual estimation) to determine the takeoff point, while muscle strength parameters (e.g., electromyographic activation timing, peak force) lack real-time quantification. This hinders the development of personalized training programs (tailored for lower-body strength, flexibility, etc.), limiting athletic performance while increasing the risk of muscle injuries (quadriceps/hamstrings) during the takeoff phase. This study employed a proprietary lightweight monitoring system to analyze 22 elite national/provincial hurdlers (15 males, 7 females; including 8 National Athletes and 14 First-Class Athletes). By integrating multimodal data and applying machine learning, the system overcomes traditional empirical limitations to enable personalized quantification of takeoff points. This approach enhances muscle force precision and athletic performance while reducing injury risk. The findings demonstrate that the “data collection-model prediction-intervention-outcome validation” framework is replicable for complex track and field events, validating the feasibility of integrating sports technology with competitive training.