https://github.com/ermongroup/wifi_activity_recognition
Code for IEEE Communication Magazine (A Survey on Behaviour Recognition Using WiFi Channle State Information)
https://github.com/ermongroup/wifi_activity_recognition
Last synced: 6 months ago
JSON representation
Code for IEEE Communication Magazine (A Survey on Behaviour Recognition Using WiFi Channle State Information)
- Host: GitHub
- URL: https://github.com/ermongroup/wifi_activity_recognition
- Owner: ermongroup
- License: gpl-3.0
- Created: 2017-07-20T21:20:18.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2023-06-08T04:26:54.000Z (over 2 years ago)
- Last Synced: 2025-04-02T06:08:44.679Z (6 months ago)
- Language: Jupyter Notebook
- Size: 2.2 MB
- Stars: 269
- Watchers: 14
- Forks: 75
- Open Issues: 19
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Wifi_Activity_Recognition using LSTM
Latest dataset & Tensorflow code for IEEE Communication Magazine.
Title: [A Survey on Behaviour Recognition Using WiFi Channel State Information](http://ieeexplore.ieee.org/document/8067693/)
Work by Siamak Yousefi, Hirokazu Narui, Sankalp Dayal, [Stefano Ermon](http://cs.stanford.edu/~ermon), Shahrokh Valaee
## Prerequisite
Tensorflow >= 1.0
numpy
pandas
matplotlib
scikit-learn
## How to run
0. Download dataset from [here](https://drive.google.com/file/d/19uH0_z1MBLtmMLh8L4BlNA0w-XAFKipM/view?usp=sharing)
-> **Notice: Dataset size is ~4GB**
1. "git clone" this repository.
2. Run the cross_vali_data_convert_merge.py
-> This script makes csv files(input features & label) of each activity in "input_files" folder.
3. Run the cross_vali_recurrent_network_wifi_activity.py
-> This script makes learning curve images & confusion matrix in a new folder.
## Dataset
We collect dataset using [Linux 802.11n CSI Tool](https://dhalperi.github.io/linux-80211n-csitool/).
The files with "input_" prefix are WiFi Channel State Information data.
-> 1st column shows timestamp.
-> 2nd - 91st column shows (30 subcarrier * 3 antenna) amplitude.
-> 92nd - 181st column shows (30 subcarrier * 3 antenna) phase.
The files with "annotation_" prefix are annotation data.
## Jupyter notebook
[PCA_STFT](https://github.com/ermongroup/Wifi_Activity_Recognition/blob/master/PCA_STFT_visualize.ipynb) file visualize the data from .csv file. This code refers to [CARM](https://www.cse.msu.edu/~alexliu/publications/WeiCARM/WeiCARM_MOBICOM15.pdf).