Wi-Fi Sensing via Channel State Information

Abstract

Human presence detection plays a crucial role in various applications such as security systems, home automation, and healthcare monitoring. This paper presents a novel approach to detect human presence utilizing the Channel State Information (CSI) of Wi-Fi signals. By leveraging the unique characteristics of CSI, including signal strength, and phase, we propose a robust and non-intrusive method for human presence detection. The key advantage of our approach lies in its ability to overcome common challenges faced by traditional human presence detection methods, such as occlusion, lighting conditions, and environmental disturbances. By utilizing CSI, which captures fine-grained information about the wireless channel, our system can differentiate between human and non-human objects with higher accuracy and robustness.

We conducted extensive experiments in a real-world indoor environment to evaluate the performance of our proposed system. The results demonstrate that our approach achieves a high detection accuracy, with an average precision of over 90%.