BullyDetect: Detecting School Physical Bullying With Wi-Fi and Deep Wavelet Transformer
- 24 October 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (5) , 5160-5169
Abstract
More than 246 million children and adolescents suffer from school violence and bullying, e.g., verbal harassment, social harassment, and physical bullying, every year, according to a report from the United Nations Educational, Scientific and Cultural Organization. School violence and bullying severely harm the physical and emotional well-being of the victims, increasing the risks of depression, anxiety, sleep difficulties, lower academic achievement, dropping out of school, and even suicide attempts. Since school physical bullying always happens in the blind spots of surveillance cameras, in this paper, we propose to utilize Wi-Fi, a widely deployed infrastructure, to detect school physical bullying. We design residual wavelet Transformer networks to conduct noise removal and action feature learning in an end-to-end manner. Besides, we propose two data augmentation methods in the temporal domain of Wi-Fi signals to simulate the different speeds and extents of bullying actions performed. Extensive evaluation of 20-paired volunteers demonstrates that (1) Wi-Fi can effectively detect physical school bullying. (2) The proposed approaches outperform Long-Short-Time-Memory networks, ResNet-1D, ViT, etc. (3) The proposed data augmentation methods can work as plug-and-play modules to improve the detection accuracy of all the above-mentioned approaches.Keywords
Funding Information
- National Natural Science Foundation of China (62102307)
- National Natural Science Foundation of China (U21A20462)
- National Natural Science Foundation of China (62372400)
- National Natural Science Foundation of China (62372365)
- National Natural Science Foundation of China (62202368)
- Pioneer and Leading Goose Research and Development Program of Zhejiang (2024C03287)
- Fundamental Research Funds for the Central Universities
This publication has 35 references indexed in Scilit:
- Not only Look, But Also Listen: Learning Multimodal Violence Detection Under Weak Supervision2020
- A dataset for Wi-Fi-based human-to-human interaction recognitionData in Brief, 2020
- WiVi: A Ubiquitous Violence Detection System With Commercial WiFi DevicesIEEE Access, 2019
- Wi-Dog: Monitoring School Violence with Commodity WiFi DevicesLecture Notes in Computer Science, 2017
- Deep Residual Learning for Image Recognition2016
- Peer Victimization, Cyberbullying, and Suicide Risk in Children and AdolescentsJAMA, 2014
- Violence Detection in Video by Using 3D Convolutional Neural Networks2014
- Violence Detection in Video Using Computer Vision Techniques2011
- Violence Content Classification Using Audio Features2006
- Ambient temperature and the occurrence of collective violence: A new analysis.Journal of Personality and Social Psychology, 1979