Human activity recognition, tracking and classification is an essential trend in assisted\nliving systems that can help support elderly people with their daily activities. Traditional activity\nrecognition approaches depend on vision-based or sensor-based techniques. Nowadays, a novel\npromising technique has obtained more attention, namely device-free human activity recognition\nthat neither requires the target object to wear or carry a device nor install cameras in a perceived\narea. The device-free technique for activity recognition uses only the signals of common wireless\nlocal area network (WLAN) devices available everywhere. In this paper, we present a novel elderly\nactivities recognition system by leveraging the fluctuation of the wireless signals caused by human\nmotion. We present an efficient method to select the correct data from the Channel State Information\n(CSI) streams that were neglected in previous approaches. We apply a Principle Component Analysis\nmethod that exposes the useful information from raw CSI. Thereafter, Forest Decision (FD) is adopted\nto classify the proposed activities and has gained a high accuracy rate. Extensive experiments have\nbeen conducted in an indoor environment to test the feasibility of the proposed system with a total\nof five volunteer users. The evaluation shows that the proposed system is applicable and robust to\nelectromagnetic noise.
Loading....