Robust Respiration Sensing Based on Wi-Fi Beamforming

Wenchao Song, Zhu Wang, Zhuo Sun, Hualei Zhang, Bin Guo, Zhiwen Yu, Luke Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Currently, the robustness of most Wi-Fi sensing systems is very limited due to that the target’s reflection signal is quite weak and can be easily submerged by the ambient noise. To address this issue, we take advantage of the fact that Wi-Fi devices are commonly equipped with multiple antennas and introduce the beamforming technology to enhance the reflected signal as well as reduce the time-varying noise. We adopt the dynamic signal energy ratio for sub-carrier selection to solve the location dependency problem, based on which a robust respiration sensing system is designed and implemented. Experimental results show that when the distance between the target and the transceiver is 7m,the mean absolute error of the respiration sensing system is less than0.729bpm and the corresponding accuracy reaches 94.79%, which out performs the baseline methods.
Original languageEnglish
Title of host publicationProceedings of the 16th EAI International Conference on Pervasive Computing Technologies for Healthcare
Publication statusAccepted/In press - 11 Nov 2022
Event16th EAI International Conference on Pervasive Computing Technologies for Healthcare - Thessaloniki, Greece
Duration: 12 Dec 202214 Dec 2022
https://pervasivehealth.eai-conferences.org/2022/

Conference

Conference16th EAI International Conference on Pervasive Computing Technologies for Healthcare
Abbreviated titleEAI Pervasive Health 2022
Country/TerritoryGreece
CityThessaloniki
Period12/12/2214/12/22
Internet address

Cite this