RFBoost

Datasets and PyTorch code for RFBoost: Understanding and Boosting Deep WiFi Sensing via Physical Data Augmentation.

Prerequisites

Clone this repo and download preprocessed Widar3 dataset from the link (password:hku-aiot-rfboost24): You can download raw data from Widar3 website.
```
unzip NPZ-pp.zip -d "dataset/NPZ-pp/"
```
(Optional) Setup cache path in config.yaml:
```
cache_folder: "/path/to/cache/dir/"
```

Use Conda to manage python environment:

% create rfboost-pytorch2
conda env create -f environment.yml

How to Run

Start the batch runner with:
```
python source/batch_runner.py
```
If everything goes well, training logs are recorded in ./log/<dataset>/<model>/, final results are available under ./record, and TensorBoard logs are located at ./runs.

Support methods

The current version supports data augmentation methods for the Widar3 dataset and models using DFS input. In batch_runner.py file, uncomment the method you want to use. Available options include "PCA", "All Subcarriers", "RDA" and "ISS-6".

Note that customized augmentation method will be defined in "augment.py". (TODO: We will refactor the definition logic in the future.)

Files and Directories

About `source/batch_runner.py`: task runner

This is a multi-task queue that allows multiple augmentation combinations to be submitted at once to test performance. Currently, you can adjust the Dataset, Model, default_window, augmentation, hyperparameters, and so on.

By default, it uses the RFNet model and Widar3 dataset with default parameters, testing for Cross-RX evalution.

About `dataset/` & `source/Datasets.py`: Dataset and Splits

The original data are stored in the dataset/ directory, but for different tasks, different data splits are needed. So that we save split files in the source/<model>/ folder. By default, main.py also supports K-fold cross-validation.

About `source/augment.py`: Repo of augmentation methods

Users can write their own augmentation rules in this file.

Notes

This repository is built upon UniTS repo. We owe our gratitude for their initial work.

Citation

@article{hou2024rfboost,
author = {Hou, Weiying and Wu, Chenshu},
title = {RFBoost: Understanding and Boosting Deep WiFi Sensing via Physical Data Augmentation},
year = {2024},
journal = {Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.},
}

License

This project is licensed under the GPL v3 License - see the LICENSE file for details.

aiot-lab/RFBoost