Tracking Vital Signs During Sleep Leveraging Off-the-shelf WiFi

Abstract

Tracking human vital signs of breathing and heart rates during sleep is important as it can help to assess the general physical health of a person and provide useful clues for diagnosing possible diseases. Traditional approaches (e.g., Polysomnography (PSG)) are limited to clinic usage. Recent radio frequency (RF) based approaches require specialized devices or dedicated wireless sensors and are only able to track breathing rate. In this work, we propose to track the vital signs of both breathing rate and heart rate during sleep by using off-the-shelf WiFi without any wearable or dedicated devices. Our system re-uses existing WiFi network and exploits the fine-grained channel information to capture the minute movements caused by breathing and heart beats. Our system thus has the potential to be widely deployed and perform continuous long-term monitoring. The developed algorithm makes use of the channel information in both time and frequency domain to estimate breathing and heart rates, and it works well when either individual or two persons are in bed. Our extensive experiments demonstrate that our system can accurately capture vital signs during sleep under realistic settings, and achieve comparable or even better performance comparing to traditional and existing approaches, which is a strong indication of providing non-invasive, continuous fine-grained vital signs monitoring without any additional cost.

Security and privacy on physical layer for wireless sensing: A survey

“…Liu et al only leveraged an AP and a single Wi‐Fi device to assemble a system detecting breathing and heart rate. They developed an algorithm to analyze the amplitude and phase of fine‐grained CSI signal to get the data of breathing and heart rate per minute.…”

“…Liu et al tried to use plastic frame of 1 inch, a solid wood door of 2 inches as obstacles between transmitter and the receiver. They found this would not influence their system's accuracy obviously.…”

“…Wireless sensing system may not work so well when set in the multiperson environment for the other people's motion will also cause the reflected signal to change. Some of the applications above had already dealt with this problem such as WiSee, RF‐capture, Liu et al, but the detection accuracy had a sharp decrease when the number of people kept increasing. This is an important challenge to solve to bring wireless sensing technology into practice.…”

“…It leverages the changes in wireless signal caused by the motions in environments and analyzes the changes to reveal the motions in the environment detected. This technology has a bright future applying in many situations with low-cost devices and high sensing accuracy and it has been applied in diverse areas from heart rate detection (1,2) to human detection, (3)(4)(5)(6)(7) localization, (8)(9)(10)(11)(12)(13)(14)(15) even some very innovative ones such as lip language distinguishing, 16 and keystroke detection. (17,18) And in recent years, considerable academic researches about this technology have also been carried out.…”

A Robust and Device-Free System for the Recognition and Classification of Elderly Activities

“…They extracted CSI from the receiver, and then applied some signal processing techniques in both time and frequency domain and machine algorithms to detect the position of an entity. Thereafter, CSI has been leveraged in various applications such as localizations [24,25], motion detection [26,27], and activity recognition [28,29,30]. WiFall [29] considered the abnormal behavior by applying a local outlier factor based algorithm and classifying the fall action by using a one-class support vector machine (SVM).…”