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.

In this paper, the algorithm of the deep convolutional neural network is used to conduct in-depth research and analysis of sports health big data, and an intelligent analysis system is designed for the practical process. A convolutional neural network is one of the most popular methods of deep learning today. The convolutional neural network has the feature of local perception, which allows a complete image to be divided into several small parts, by learning the characteristic features of each local part and then merging the local information at the high level to get the full representation information. In this paper, we first apply a convolutional neural network for four classifications of brainwave data and analyze the accuracy and recall of the model. The model is then further optimized to improve its accuracy and is compared with other models to confirm its effectiveness. A demonstration platform of emotional fatigue detection with multimodal data feature fusion was established to realize data acquisition, emotional fatigue detection, and emotion feedback functions. The emotional fatigue detection platform was tested to verify that the proposed model can be used for time-series data feature learning. According to the platform requirement analysis and detailed functional design, the development of each functional module of the platform was completed and system testing was conducted. The big data platform constructed in this study can meet the basic needs of health monitoring for data analysis, which is conducive to the formation of a good situation of orderly and effective interaction among multiple subjects, thus improving the information service level of health monitoring and promoting comprehensive health development.