A WiFi-Based Smart Home Fall Detection System Using Recurrent Neural Network

Abstract

Falls among the elderly living on their own have been regarded as a major public health worry that can even lead to death. Fall detection system (FDS) that alerts caregivers or family members can potentially save lives of the elderly. However, conventional FDS involves wearable sensors and specialized hardware installations. This article presents a passive device-free FDS based on commodity WiFi framework for smart home, which is mainly composed of two modules in terms of hardware platform and client application. Concretely, commercial WiFi devices collect disturbance signal induced by human motions from smart home and transmit the data to a data analysis platform for further processing. Based on this basis, a discrete wavelet transform (DWT) method is used to eliminate the influence of random noise presented in the collected data. Next, a recurrent neural network (RNN) model is utilized to classify human motions and identify the fall status automatically. By leveraging Web Application Programming Interface (API), the analyzed data is able to be uploaded to the proxy server from which the client application then obtains the corresponding fall information. Moreover, the system has been implemented as a consumer mobile App that can help the elderly saving their lives in smart home, and detection performance of the proposed FDS has been evaluated by conducting comprehensive experiments on real-world dataset. The results confirm that the proposed FDS is able to achieve a satisfactory performance compared with some state-of-the-art algorithms.