Energy harvesting IoT devices for sports person health monitoring

Abstract

Presently, the continuous monitoring of complex activities is valuable for understanding human health behavior and providing activity-aware services. At the same time, recognizing these health activities requires both movement and location information that can quickly drain batteries on wearable devices. The energizing factor in the wearable Internet of things (IoT) devices for Sports Person required prominent solutions in optimizing the performance and energy consumption of the health monitoring device of sports-person. Hence in this research, IoT assisted energy harvesting devices for sportspersons (IoT-EHDS) in health monitoring is the probabilistic system for harvesting energy in IoT devices for sports health monitoring. Energy harvesting is achieved in the IoT devices with the probabilistic framework (PF), which improves the accomplished interruption of the user to interact with versatile energy harvesting and frame demand procedure. The PF helps to smoothly prefetch the frames in accordance with contemporary user behavior from the end device. Parameters for sports-based devices are obtained using an energy harvesting method that is further graded and evaluated in terms of quantitative performance probability. Bayesian neural network (BNN) incorporates wearable device-based information to promote the health of sportsperson and to increase the quality of sports people’s safety. BNN is used to classify sports person health activities. The experimental results show that the suggested system is validated by mHealth datasets, enhances the accuracy ratio of 96.42%, and less consumption of energy to promote the energy harvesting IoT devices for sportspersons in healthcare.