Using Wireless Sensor Network to Correct Posture in Sports Training Based on Hidden Markov Matching Algorithm

Abstract

This paper combines the research of wireless sensor networks and sports training and proposes a wireless sensor network-based intelligent sports training system. According to the requirements of the system, this design uses the wireless sensor network system as the platform for development and the ZigBee module for wireless communication. The advantage of this system is to transmit the obtained information to the ZigBee coordinator module, and after the processing of information and the resultant decision, a nonwearable unmonitored motion training model based on visual sensing is proposed. The motion terminal collects video data streams of user motion actions and extracts features to establish HMM motion recognition algorithm to achieve recognition of motion actions, automatic counting, and intelligent scoring functions. The template matching algorithm based on dynamic time regularization and weighted Euclidean distance realizes a universal real-time motion recognition algorithm with high standard and low latency and can guide the user’s motion action based on similarity calculation. The intelligent sports training system is designed and developed to maintain a high-quality human-computer interaction experience with a real-time feedback client and uploads sports data to a cloud server via the HTTP protocol, which supports real-time sports proximity query and training plan development on the website. After practical application tests, the intelligent sports training system based on the wireless sensor network proposed in this paper is stable and reliable and adds fun and competitiveness to boring sports. The research of this paper has some reference value for the application of wireless sensor networks and the research of the motion recognition algorithm.

Accuracy of Hidden Markov Models in Identifying Alterations in Movement Patterns during Biceps-Curl Weight-Lifting Exercise

“…Furthermore, this analysis could provide a more solid basis for qualitative exercise analysis, as described by Knudson and Morrison [5], as well as single out inadequate loads [6] or postures during the performance of resistance exercises. For example, the HMM method has been explored as an additional tool to help amateur athletes learn correct movements for a specific action in a sport, aiming to improve their skill level [63], as well as an analysis to support personalized sport training prescriptions according to the uncommon abilities of practitioners [66].…”