WiFi CSI Dataset for Indoor Presence Detection

This dataset contains WiFi Channel State Information (CSI) records collected for device-free binary human presence detection in a residential environment using two ESP32-S3 microcontrollers. Captured over a 2.4 GHz ESP-NOW dedicated link with 40 MHz bandwidth (HT40) at a 30 Hz sampling rate, the dataset is structured into raw and processed directories. The raw folder houses data from an initial validation test and a controlled pilot collection, providing continuous CSV time-series records and JSON metadata for three distinct experimental conditions: empty room, static occupation, and moving occupation. The processed folder contains the output of the initial data pipeline (pipeline_v0) in CSV and Parquet formats, yielding a perfectly balanced tabular dataset of 1,200 non-overlapping 2-second windows (600 empty and 600 occupied). Each processed window comprises 648 temporal statistical features (variance, mean absolute deviation, range, and interquartile range) extracted from 162 shared valid subcarriers. Designed as part of an undergraduate engineering thesis, this dataset supports exploratory signal analysis and baseline supervised machine learning for indoor presence classification.