Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Integrating Health Sensing into Cellular Networks: Human Sleep Monitoring Using 5G Signals

Ruxin Lin, Peihao Yan, Jie Lu, Qijun Wang, Huacheng Zeng

TL;DR

The first experimental study of human sleep monitoring using realistic 5G signals collected from commercial cellular infrastructure is presented, and a lightweight signal processing pipeline for respiration rate estimation and a CNN model for sleep body movement classification is designed.

Abstract

Cellular networks offer a unique opportunity to enable device-free and wide-area health monitoring by exploiting the sensitivity of radio-frequency (RF) propagation to human physiological activities. In this paper, we present the first experimental study of human sleep monitoring using realistic 5G signals collected from commercial cellular infrastructure. We investigate a practical scenario in which a smartphone is placed near a bed, and a 5G base station periodically configures uplink sounding reference signal (SRS) transmissions to obtain fine-grained channel state information (CSI). Leveraging uplink CSI measurements, we design a lightweight signal processing pipeline for respiration rate estimation and a CNN model for sleep body movement classification. Through extensive experiments conducted on an indoor private 5G network, our system achieves over 91.2% accuracy in respiration rate estimation and 85.5% accuracy in sleep movement classification.

Integrating Health Sensing into Cellular Networks: Human Sleep Monitoring Using 5G Signals

TL;DR

The first experimental study of human sleep monitoring using realistic 5G signals collected from commercial cellular infrastructure is presented, and a lightweight signal processing pipeline for respiration rate estimation and a CNN model for sleep body movement classification is designed.

Abstract

Cellular networks offer a unique opportunity to enable device-free and wide-area health monitoring by exploiting the sensitivity of radio-frequency (RF) propagation to human physiological activities. In this paper, we present the first experimental study of human sleep monitoring using realistic 5G signals collected from commercial cellular infrastructure. We investigate a practical scenario in which a smartphone is placed near a bed, and a 5G base station periodically configures uplink sounding reference signal (SRS) transmissions to obtain fine-grained channel state information (CSI). Leveraging uplink CSI measurements, we design a lightweight signal processing pipeline for respiration rate estimation and a CNN model for sleep body movement classification. Through extensive experiments conducted on an indoor private 5G network, our system achieves over 91.2% accuracy in respiration rate estimation and 85.5% accuracy in sleep movement classification.
Paper Structure (15 sections, 7 equations, 9 figures)

This paper contains 15 sections, 7 equations, 9 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Understanding 5G CSI for Sensing
  4. Uplink CSI Measurement in 5G Networks
  5. CSI for Sleep Monitoring
  6. Design
  7. CSI Feature Extraction
  8. Respiration Rate Estimation
  9. Sleep Movement Classification
  10. Experimental Evaluation
  11. Implementation
  12. Experimental Setting and Performance Metrics
  13. Respiration Rate Estimation
  14. Body Movement Classification
  15. Conclusion

Figures (9)

  • Figure 1: Human sleep monitoring using 5G networks.
  • Figure 2: 5G NR slot structure with SRS and DMRS
  • Figure 3: Influence of moving objects on CSI when the moving objects are at different locations. $S(t)$ is CSI amplitude variance over time, i.e., $S(t) = \sum_{\forall k}|H(k, t) - H(k, t-1)|$.
  • Figure 4: An instance of measured raw CSI and normalized CSI.
  • Figure 5: MSU's private 5G network platform.
  • ...and 4 more figures