Multi-person Respiration Monitoring Leveraging Commodity WiFi Devices

Monitoring respiration is an important component of personal health care. Though recent developments in WiFi sensing offer a potential tool to achieve contact-free respiration monitoring. Existing proposals for WiFi-based multi-person respiration sensing mainly extract individual’s respiration rate in the frequency domain using the fast Fourier transform (FFT) or multiple signal classification (MUSIC) method, leading to the following limitations: 1) largely ineffective in recovering breaths of multiple persons from received mixed signals and in differentiating individual breaths, 2) unable to acquire the time-varying respiration pattern when the subject has respiratory abnormity, such as apnea and changing respiration rates, and 3) di?icult to identify the real number of subjects when multiple subjects share the same or similar respiration rates. To address these issues, we propose WiFi-enabled MUlti-person SEnsing (WiMUSE) as a signal processing pipeline to perform respiration monitoring for multiple persons simultaneously. Essentially, as a pioneering time domain approach, WiMUSE models the mixed signals of multi-person respiration as a linear superposition of multiple waveforms, so as to form a blind source separation (BSS) problem. The effective separation of the signal sources (respiratory waveforms) further enables us to quantify the differences in the respiratory waveform patterns of multiple subjects, and thus to identify the number of subjects along with their respective respiration waveforms. We implement WiMUSE on commodity WiFi devices and conduct extensive experiments to demonstrate that, compared with the approaches based on FFT or MUSIC method, 90% error of respiration rate can be reduced by more than 60%.