Respiration Estimation for Indoor Human via Commodity WiFi Based on Time-frequency Analysis

Research output: Contribution to journalConference articlepeer-review

Abstract

In this article, we use WIFI signals to estimate the human respiratory rate. We propose a method for estimating static human respiration rate using CSI signals. We perform continuous wavelet transform on the CSI signal to obtain a time-frequency graph, and propose the Breath-net to learn the features related to respiration in the time-frequency graph. Finally, the Breath-net estimates the respiration rate. The results show that the average absolute error of this method for predicting respiratory rate can reach approximately 0.2 bpm.

Original languageEnglish
Pages (from-to)3814-3819
Number of pages6
JournalIET Conference Proceedings
Volume2023
Issue number47
DOIs
StatePublished - 2023
Externally publishedYes
EventIET International Radar Conference 2023, IRC 2023 - Chongqing, China
Duration: 3 Dec 20235 Dec 2023

Keywords

  • Channel state information
  • commodity Wi-Fi
  • deep learning
  • respiration estimation
  • time-frequency analysis

Fingerprint

Dive into the research topics of 'Respiration Estimation for Indoor Human via Commodity WiFi Based on Time-frequency Analysis'. Together they form a unique fingerprint.

Cite this