BullyDetect is a novel method designed to detect physical bullying and violence in schools by leveraging Wi-Fi signals. This innovative approach aims to enhance safety and well-being in educational environments.
For more details on BullyDetect, refer to our paper: "BullyDetect: Detecting School Physical Bullying with Wi-Fi and Deep Wavelet Transformer"
The dataset used for BullyDetect is essential for training and evaluating the detection models. It includes both the original and preprocessed data.
- Original Dataset: Download Link
- Preprocessed Dataset: Download Link
Ensure you download and prepare the dataset as per the instructions provided to achieve optimal results with the BullyDetect system.
Follow these steps to set up and run the BullyDetect system:
-
Clone the Repository:
git clone https://github.com/aiotgroup/WiFi-BullyDetect.git cd WiFi-BullyDetect -
Install Dependencies: Ensure you have the required Python packages. Install them using:
pip install -r requirements.txt
-
Change
basic_setting.jsonto your own path -
Run the training Script:
python script/basic_train.py
For any queries, you are welcome to open an issue.
BullyDetect is licensed under the MIT License. See the LICENSE file for more details.
If you find our works useful in your research, please consider citing:
@ARTICLE{lan2024bullydetect,
author={Lan, Bo and Wang, Fei and Xia, Lekun and Nai, Fan and Nie, Shiqiang and Ding, Han and Han, Jinsong},
journal={IEEE Internet of Things Journal},
title={BullyDetect: Detecting School Physical Bullying With Wi-Fi and Deep Wavelet Transformer},
year={2024},
keywords={Wireless fidelity;Transformers;Noise;Videos;Data augmentation;Cameras;Sensors;Representation learning;Internet of Things;Surveillance;Wi-Fi sensing;physical bullying detection;wavelet transformer;data augmentation;deep learning},
doi={10.1109/JIOT.2024.3486071}
}