Analysis of Digital Long Jump Take-off Wearable Sensor Monitoring System

Abstract

The wearable sensor monitoring system builds a long jump take-off recognition network model based on different digital feature extraction methods (one-dimensional digital feature extraction method, two-dimensional digital feature extraction method, and feature extraction method combining one-dimensional digitization and recursion). Experimental verification and analysis are performed on the processed sample data, and the identification effects, advantages, and disadvantages of the four methods are obtained. First, the sensor behavior movement collection software is designed based on the Android system, and the collection time and frequency are specified at the same time. In addition, for the problem of multisensor behavior recognition, an effective result fusion method is proposed. In a multisensor behavior recognition system, constructing a parallel processing architecture is conducive to improving the rate of behavior recognition. To maintain or increase the rate of behavior recognition, the result fusion method plays a vital role. Finally, this paper analyzes the process of multitask behavior recognition and constructs a residual model that can effectively integrate multitask results and fully mine data information. The experimental results show that, for the monitoring of exercise volume, we use step count statistics to extract feature values that can distinguish activity types based on human motion characteristics. This paper proposes a sample autonomous learning method to find the optimal sample training set and avoid occurrence of overfitting problems. In the recognition of 11 types of long jump take-offs, the average accuracy rate reached 98.7%. The average replacement method is used to count the number of steps, which provides a data reference for the user’s daily exercise volume.