Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Active RIS-Assisted MIMO System for Vital Signs Extraction: ISAC Modeling, Deep Learning, and Prototype Measurements

De-Ming Chian, Chao-Kai Wen, Feng-Ji Chen, Yi-Jie Sun, Fu-Kang Wang

TL;DR

This work tackles noncontact vital signs extraction within an ISAC framework by integrating an active RIS into a MIMO‑OFDM system. It introduces DMTNet, a phase‑selector that leverages Möbius transformation to cancel common phase drifts, trained entirely on simulated data but validated experimentally, and DeepMining‑MMV for robust respiration estimation from multi‑antenna measurements. The method combines a practical channel model with MT‑based phase control and a two‑stage respiration estimator (CA‑CFAR detection followed by LS and Newton refinements), achieving high throughput (up to 388 Mbps with 64QAM) and reliable respiration detection. Practically, RIS‑assisted ISAC improves sensing reliability without sacrificing communication performance, demonstrating a viable path toward hardware‑efficient, integrated sensing and communication in realistic wireless environments.

Abstract

We present the RIS-VSign system, an active reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) framework for vital signs extraction under an integrated sensing and communication (ISAC) model. The system consists of two stages: the phase selector of RIS and the extraction of respiration rate. To mitigate synchronization-induced common phase drifts, the difference of Möbius transformation (DMT) is integrated into the deep learning framework, named DMTNet, to jointly configure multiple active RIS elements. Notably, the training data are generated in simulation without collecting real-world measurements, and the resulting phase selector is validated experimentally. For sensing, multi-antenna measurements are fused by the DC-offset calibration and the DeepMining-MMV processing with CA-CFAR detection and Newton's refinements. Prototype experiments indicate that active RIS deployment improves respiration detectability while simultaneously enabling higher-order modulation; without RIS, respiration detection is unreliable and only lower-order modulation is supported.

Active RIS-Assisted MIMO System for Vital Signs Extraction: ISAC Modeling, Deep Learning, and Prototype Measurements

TL;DR

This work tackles noncontact vital signs extraction within an ISAC framework by integrating an active RIS into a MIMO‑OFDM system. It introduces DMTNet, a phase‑selector that leverages Möbius transformation to cancel common phase drifts, trained entirely on simulated data but validated experimentally, and DeepMining‑MMV for robust respiration estimation from multi‑antenna measurements. The method combines a practical channel model with MT‑based phase control and a two‑stage respiration estimator (CA‑CFAR detection followed by LS and Newton refinements), achieving high throughput (up to 388 Mbps with 64QAM) and reliable respiration detection. Practically, RIS‑assisted ISAC improves sensing reliability without sacrificing communication performance, demonstrating a viable path toward hardware‑efficient, integrated sensing and communication in realistic wireless environments.

Abstract

We present the RIS-VSign system, an active reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) framework for vital signs extraction under an integrated sensing and communication (ISAC) model. The system consists of two stages: the phase selector of RIS and the extraction of respiration rate. To mitigate synchronization-induced common phase drifts, the difference of Möbius transformation (DMT) is integrated into the deep learning framework, named DMTNet, to jointly configure multiple active RIS elements. Notably, the training data are generated in simulation without collecting real-world measurements, and the resulting phase selector is validated experimentally. For sensing, multi-antenna measurements are fused by the DC-offset calibration and the DeepMining-MMV processing with CA-CFAR detection and Newton's refinements. Prototype experiments indicate that active RIS deployment improves respiration detectability while simultaneously enabling higher-order modulation; without RIS, respiration detection is unreliable and only lower-order modulation is supported.
Paper Structure (14 sections, 1 theorem, 15 equations, 6 figures)

This paper contains 14 sections, 1 theorem, 15 equations, 6 figures.

Table of Contents

  1. Introduction
  2. ISAC Model
  3. Practical Channel Model
  4. Optimization Model
  5. Phase Selector
  6. Predictor for One Element
  7. DMTNet for Two Elements
  8. Vital Signs Extraction
  9. Vital Signs Signals
  10. Vital Signs Estimation
  11. Perfomance Evaluation
  12. Training Results
  13. Measurements
  14. Conclusion

Key Result

Theorem 1

When $| \theta'_k - \theta_k | = 180^{\circ}$, the complex inner product is $p^{r, t}_{\theta_k} = \mathfrak{Re} \left( p^{r, t}_{\theta_k} \right) + j \mathfrak{Im} \left( p^{r, t}_{\theta_k} \right)$, where

Figures (6)

  • Figure 1: Application of RIS-VSign system.
  • Figure 2: DMTNet architecture for 4R4T MIMO system with 2 active RIS elements controlled by 4-bits DPSs.
  • Figure 3: DMTNet: (a) Loss and accuracy, and (b) error of testing dataset.
  • Figure 4: (a) Structure of active RIS element, (b) measured S parameters of antenna pair, and (c) experimental scenario.
  • Figure 5: (a) $m^{1, 1}_{\rm s}$ and $m^{1, 1}_{\theta_k}$ for all states of DPS. (b) Predicted reward and measuremed signal power. (c) All combinations and (d) controlling processes by using different algorithms.
  • ...and 1 more figures

Theorems & Definitions (1)

  • Theorem 1