Abstract
In this demo, we present a device-free activity monitoring platform exploiting the prevalent WiFi signals to enable real-time activity recognition and user identification in indoor environments. It supports a broad array of real-world applications, such as senior assistance services, fitness tracking, and building surveillance. In particular, the proposed platform takes advantage of channel state information (CSI), which is sensitive to environmental changes introduced by human body movements. To enable immediate response of the platform, we design a real-time mechanism that continuously monitors the WiFi signals and promptly analyzes the CSI readings when the human activity is detected. For each detected activity, we extract representative features from CSI, and exploit a deep neural network (DNN) based scheme to accurately identify the activity type/user identity. Our experimental results demonstrate that the proposed platform could perform activity/user identification with high accuracy while offering low latency.