Improving Energy Efficiency in Sports Training Facilities through Adaptive Control Systems and Sport-Inspired Optimization Techniques

Abstract

Athletes need to track their health and sports performance in order to be at their best and prevent injuries. For players who participate in physically demanding sports like football, good health is crucial. Before engaging in strenuous sports and tournaments, they need to develop a healthy body. In this research the sensor based sports player energy efficiency using machine learning model and optimization. Here the body sensor based player activity monitoring has been carried out and their adaptive control system has been analysed. In the healthcare industry, the Internet of Things and deep learning reduce illness by transitioning from in-person consultations to telemedicine. Real-time physiological indicator monitoring is essential to safeguard athletes against potentially fatal situations and injuries sustained during training and competition. Then through edge cloud system the monitored data has been transmitted and classified for abnormality in player activity using Q-markov recurrent fuzzy encoder model. the simulation results has been analysed based on various player activity monitoring dataset in terms of training accuracy, random precision, recall, throughput, latency. The proposed technique attained random precision 95%, recall 93%, THROUGHPUT 97%, training  accuracy 94%, and Latency 98%