FallViewer: A Fine-Grained Indoor Fall Detection System with Ubiquitous Wi-Fi Devices

The safety of the elderly has attracted much attention nowadays. Among various daily activities, fall is one of the most dangerous events for the elderly, especially those who live alone. Most existing works on fall detection are based on wearable devices, which are inconvenient in using. Several solutions only use coarse-grained Wi-Fi signal information that contains many biases, and lack considerations on environmental changes. These situations motivate us to design a fine-grained and robust fall detection approach. In this article, we propose a fall detection system, called FallViewer, based on analyzing the channel state information (CSI) of Wi-Fi signals. To get fine-grained information, we propose phase and amplitude calibration methods for deviation correction. Then, an adjustment approach for antenna power is designed to eliminate the multipath interference. Furthermore, we apply a double sliding window to get a flexible threshold, which improves the robustness of FallViewer to various environments. Finally, FallViewer extracts features of the processed Wi-Fi signal and sends the features to a LibSVM for classification. Through experiments in different environments, FallViewer can detect fall events with an average accuracy of 95.8%, which indicates that FallViewer can work reliably and effectively.