Design and Analysis of a Smart Sensor-Based Early Warning Intervention Network for School Sports Bullying among Left-Behind Children

Abstract

This paper constructs a sports bullying early warning intervention system using smart sensors to conduct in-depth research and analysis on early warning intervention of school sports bullying behaviors among left-behind children. Unlike daily behavior recognition based on motion sensors, school sports bullying actions are very random and difficult to be described by a specific motion trajectory. For the characteristics of violent actions and daily actions, action features in the time and frequency domains are extracted and action categories are recognized by BP neural networks; for complex actions, it is proposed to decompose complex actions into basic actions to improve the recognition rate. The algorithm of combining action features and speech features to achieve violence recognition is proposed. For the complexity of audio data features, this paper firstly preprocesses the audio data with preweighting, framing, and windowing and secondly extracts the MFCC feature parameters from the audio data and then builds a deep convolutional neural network to design the violence emotion recognition algorithm. The simulation results show that the algorithm effectively improves the accuracy rate of violent action recognition to 91.25% and the recall rate of violent action recognition to 92.13%. Finally, the LDA dimensionality reduction algorithm is introduced to address the problem of the high complexity of the algorithm due to the high number of feature dimensions. The LDA dimensionality reduction algorithm reduces the number of feature dimensions to 7 dimensions, which reduces the system running time by about 52% and improves the recognition rate of specific complex actions by about 12.1% while ensuring the overall system performance.