LuckyChirp: Opportunistic Respiration Sensing Using Cascaded Sonar on Commodity Devices

Qiuyue (Shirley) Xue, D Shin, Anupam Pathak, Jake Garrison, Jonathan Hsu, Mark Malhotra, Shwetak Patel

Abstract

We present LuckyChirp, a contactless, passive, op- portunistic respiratory tracking solution for commodity device using cascaded sonar modeling. Compared to conventional sonar methods that only solve the respiratory estimation problem (“what is the respiratory rate”), LuckyChirp also solves the additional respiratory detection problem (“is the human present and static enough for respiration sensing”). LuckyChirp uses a custom neural network on pulsed sonar’s wavelet transformed features to detect respiration. The classifier is then cascaded with a respiratory rate estimator. Such holistic design eliminates user friction of manually activating the system and enables passive respiration monitoring for all-day natural use. With Google Nest Hub and Pixel 4 as experimental devices, LuckyChirp achieves a mean absolute error of 0.48 ± 0.98 and 1.07 ± 1.67 breaths/min, respectively, for 20 users participating in a whole-night study. Compared to direct respiratory estimation without respiration classification, this is a ×6 (Nest Hub) and ×4 (Pixel) reduction in error.