Contact-Free In-Home Health Monitoring System with Commodity Wi-Fi

Abstract

Wi-Fi-based in-home health care has attracted much attention over the past years. In this paper, leveraging the complementary amplitude and phase data of Wi-Fi Channel State Information (CSI), we propose a contact-free elderly-focused health monitoring system to simultaneously detect the human presence and monitor the detailed respiration status. By utilizing the Naive Bayes classifier, the proposed system could detect human presence based on the Doppler spectrum. To obtain detailed respiration status, we define the Respiration-to-Noise Ratio (RNR) to select the most sensitive data streams. For detecting and distinguishing abnormal respiratory patterns, we extend the peak detection method and leverage machine learning based classifier in respiration apnea period. We carry out extensive experiments and the results demonstrate the effectiveness of our approach to health monitoring.