Tutorial Session

Abstract: Wi-Fi sensing is an emerging technology that leverages Wi-Fi signals to detect changes in the physical environment. Wi-Fi is a radio-frequency technology primarily used for communication purposes. However, the same signal can be used for sensing. As Wi-Fi signals travel through space, they reflect off objects, walls, and people, creating subtle distortions in the signal patterns.  These distortions can be analyzed to detect motion, gesture recognition, localization and healthcare applications like breathing or heart rate etc. One of the advantages of Wi-Fi sensing is that it is non-intrusive, non-obtrusive, and privacy preserving compared to camera and traditional sensors. This Wi-Fi sensing  leverages the Channel State Information (CSI) between the transmitter and receiver  of the Wi-Fi communication to detect the environmental changes. CSI captures the    detailed information about the wireless channel, including phase shifts, signal reflections, scattering, multipath effects and attenuations  in signal propagation. This results different CSI streams received at the receiver device and can be used to detect the environmental changes (e.g. human movements) by correlating them with the corresponding channel distortion patterns.  CSI can be processed, modeled, and trained in different domains for different Wi-Fi sensing purposes, e.g., detection, recognition, and estimation. This tutorial provides a comprehensive introduction to WiFi sensing, covering its fundamental concepts, like MIMO, OFDM, Channel state information. Key topics include signal processing techniques, data preprocessing, machine learning models. It provides insights into installing the tools, CSI matrix extraction, decoding the patterns for activity recognition. Moreover, the tutorial will provide a new research direction to the students and young researchers to this exciting and relatively new interdisciplinary domain involving sensing, signal processing, machine learning and pattern recognition.