Abstract
In order to reduce the sports injury caused by high intensity sports classes, it is necessary to monitor the state of the sports load. Therefore, the sport’s load monitoring system based on a threshold classification algorithm is proposed. In this paper, we design the hardware and software structures of the sports load monitoring systems in a physical education class. In this system, the state parameters of the sports load are collected by wireless sensor network nodes, and the feature parameters are fused and clustered by the integrated information fusion method. After that, we establish the movement target image acquisition model, which unifies the ZigBee networking realization to the high intensity sports classroom movement load monitoring. Simulation results show that the designed PE classroom sports load monitoring system based on the threshold classification algorithm has high performance for sports parameter monitoring and can effectively avoid sports injury caused by overload.
Highlights
As people pay more and more attention to their physical health, they begin to take intensive physical exercise gradually to improve their physical fitness [1]
Reference [4] proposes to monitor the athletic performance of male athletes and to measure the change of athletic performance in 1 year after arthroscopic treatment of femoral and acetabular impact injuries
The methods mentioned above have the problems of poor antiinterference and low output stability in the monitoring of the sports class load
Summary
As people pay more and more attention to their physical health, they begin to take intensive physical exercise gradually to improve their physical fitness [1]. In Reference [6], the authors proposed a multilabel classification based on a random forest algorithm for a nonintrusive load monitoring system. This paper proposes a multilabel classification method using random forest (RF) as a learning algorithm for nonintrusive load identification. The speed of this feature extraction obviously cannot meet the needs of big data video analysis In response to these two problems exposed by Action Bank under large-scale data, this paper proposes to apply the template learning method based on spectral clustering to Action Bank, which replaces the cumbersome manual selection template step and is easy to generalize to different databases. We use the threshold classification algorithm to study the sports class load monitoring system.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
