Behavior Estimation Based on Multiple Vibration Sensors for Elderly Monitoring Systems

Abstract

Aging has become a global social issue nowadays. We want to provide an elderly care system for older people who live alone. Based on the perspective of an informationally structured space (ISS), we have developed a monitoring system by using high-precision vibration sensors. In preliminary experiments, we observed that the autocorrelation coefficient reflected periodic human activities to a certain extent. Therefore, we propose a time delay neural network (TDNN) with autocorrelation as the input to analyze the vibration data. The system can estimate the current state of the elderly. When the system observes any abnormal situation of the elderly, the system can confirm by voice or notify the caregiver, if necessary. In the experiments, we compared the proposed method with traditional TDNNs using raw data as the input. The results demonstrated that proposed methods had performed well when using vibration sensors to measure user behaviors in the bathroom and living room.