StevenMHernandez / ESP32-CSI-Tool

Extract Channel State Information from WiFi-enabled ESP32 Microcontroller. Active and Passive modes available. (https://stevenmhernandez.github.io/ESP32-CSI-Tool/)
https://stevenmhernandez.github.io/ESP32-CSI-Tool/
MIT License
259 stars 71 forks source link

regarding the paper"WiFi Sensing on the Edge: Signal Processing Techniques and Challenges for Real-World Systems" #82

Open du7092 opened 1 year ago

du7092 commented 1 year ago

Dear Sir, My name is Dheeraj, and I am a sophomore at the International Institute of Information Technology in Raipur. I am studying in electronics and communication engineering. could you kindly provide us machine learning codes so that we may use them to deploy on our dataset and change them appropriately to improve accuracy for our fall detection for older persons using Wi-Fi signals.

Arijitdutta19910601 commented 1 year ago
  1. Dheeraj, it is not that difficult. Use the codes present in the Python_utils folder of this project directory to visualize the changes. For your particular application the machine learning algorithm and model may differ. But for standard solutions, you need to first remove the noise (smoothening) from the signal, and henceforth you may chose a subcarrier from the CSI data you recieved using PCA (Prinicipal Component Analysis). After that you can label your data and apply ML algos like KNN, Random Forest, Logistic Regression, SVM etc. For your reference, look at these research works:

  2. [https://doi.org/10.3390/app122211809]

  3. [https://doi.org/10.1109/ACCESS.2022.3226248]