Position-Free Breath Detection During Sleep via Commodity WiFi
Hongyang Zhuo, Xianda Wu, Qinghua Zhong, Han Zhang
Abstract
In recent years, contactless sleep breath detection using WiFi signals has gained significant attention. In this article, we present a position-free breath detection system that utilizes the channel state information (CSI) from a pair of WiFi devices. To address the “blind-spot” issue, we propose a robust detection method that takes advantage of both the amplitude and phase of the CSI ratio, ensuring comprehensive coverage for breath detection. We also utilize the periodicity and variability features to select the most suitable breath pattern from the resulting signals. To mitigate the noise interference in nonideal sleep positions, we propose a novel principal component analysis-variational mode decomposition (PCA-VMD) fusion method to fully exploit the complementary advantage of sensing over different TX–RX pairs. In this way, we can extract the fine breath frequency component for the breath rate estimation. Extensive experiments are conducted to demonstrate the superiority of the proposed scheme to the existing state of the arts.