Dataset for Human Activity Recognition using Wi-Fi Channel State Information (CSI) data

The dataset is organised as follows:- There are 3 folders (room_1/2/3), which indicate data collected from 3 different rooms- In each of that rooms there is a different number of folders indicating different data capturing session- In each of that folder, there is data.csv files, which stores CSI data for each packet. Also, there are label.csv and label_boxes.csv which contain labels for activities and person bounding box respectively. Dataset characteristic:Activities - walking, sitting, standing, lying, getting up, getting down, no activity# of people involved - 1# of rooms used - 3WiFi router - TP-Link TL-WDR4300Channel - 60Bandwidth - 40MHzFrequency - 5 GHzAntennas - 2Rx x 2Tx# of subcarriers - 114 Check out http://github.com/retsediv/WIFI_CSI_based_HAR in case if you need the source code of data collection process, processing, analysis or model development Disclaimer: All data were collected by myself and the only person performing activities was me. My purpose was to make the data easier available to the community for further research in time on COVID-19.