MultiResp: Robust Respiration Monitoring for Multiple Users Using Acoustic Signal

In recent years, we have seen efforts made to monitor respiration for multiple users. Existing approaches capture chest movement relying on signals directly reflected from chest or separate breath waves based on breath rate difference between subjects. However, several limitations exist: 1) they may fail when subjects face away from the transceiver or are blocked by obstacles or other subjects; 2) they may fail to separate subjects’ breath waves with the same or similar rates (i.e., breath rate difference < 1 bpm); 3) they assume a priori knowledge of number of subjects and cannot adapt to dynamic change of subject number during monitoring. To overcome these limitations, in this paper we propose MultiResp, a multi-user respiration monitoring system using acoustic signal. By fully leveraging the abundant acoustic signals reflected indirectly from subjects’ chest, MultiResp can robustly capture chest movement even when they face away from the transceiver or are blocked. By extracting fine-grained breath rate and phase difference between different subjects, MultiResp can separate the breath waves with the same or similar rates and adapt to dynamic change of subject number during monitoring. Extensive experiments show that MultiResp is able to accurately monitor the respiration of multiple users with a median error of 0.3 bpm in various indoor scenarios, however, it fails when the sound pressure is lower than 55 dB or body movement is happening.

I Introduction

Respiration monitoring plays a crucial role in diagnosing diseases such as chronic obstructive pulmonary disease (COPD) [1], heart failure [2], and sleep Apnea [3]. Monitoring respiration in clinical settings requires dedicated devices such as thoracic impedance pneumography [4], capnography [5] or pulse oximeter [6] which produce highly accurate results but may cause discomfort and even affect the underlying physiological parameters being measured [7]. In addition, these devices are costly and usually operated by well-trained professionals. Respiration monitoring in home settings include a range of devices and sensors such as wearable devices [8], [9], smart mattress, smart pillow embedded with air pressure sensors [10], fiber optic sensor [11], [12] and camera-based systems [13]. However, they can be still costly [10], [11], [12], may require long-time wearing [8], [9] and raise privacy concerns [13].