ECG Signal Reconstruction Using FMCW Radar and a Convolutional Neural Network for Contactless Vital-Sign Sensing

Daiki TODA; Ren ANZAI; Koichi ICHIGE; Ryo SAITO; Daichi UEKI

doi:10.1587/transcom.2022EBP3005

ECG Signal Reconstruction Using FMCW Radar and a Convolutional Neural Network for Contactless Vital-Sign Sensing

Daiki TODA, Ren ANZAI, Koichi ICHIGE, Ryo SAITO, Daichi UEKI

Full Text Views

0

Cite this

Summary :

A method of radar-based contactless vital-sign sensing and electrocardiogram (ECG) signal reconstruction using deep learning is proposed. A radar system is an effective tool for contactless vital-sign sensing because it can measure a small displacement of the body surface without contact. However, most of the conventional methods have limited evaluation indices and measurement conditions. A method of measuring body-surface-displacement signals by using frequency-modulated continuous-wave (FMCW) radar and reconstructing ECG signals using a convolutional neural network (CNN) is proposed. This study conducted two experiments. First, we trained a model using the data obtained from six subjects breathing in a seated condition. Second, we added sine wave noise to the data and trained the model again. The proposed model is evaluated with a correlation coefficient between the reconstructed and actual ECG signal. The results of first experiment show that their ECG signals are successfully reconstructed by using the proposed method. That of second experiment show that the proposed method can reconstruct signal waveforms even in an environment with low signal-to-noise ratio (SNR).

Publication: IEICE TRANSACTIONS on Communications Vol.E106-B No.1 pp.65-73

Publication Date: 2023/01/01

Publicized: 2022/06/29

Online ISSN: 1745-1345

DOI: 10.1587/transcom.2022EBP3005

Type of Manuscript: PAPER

Category: Sensing

Authors

Daiki TODA
  Yokohama National University
Ren ANZAI
  Yokohama National University
Koichi ICHIGE
  Yokohama National University
Ryo SAITO
  Murata Manufacturing Co., Ltd.
Daichi UEKI
  Murata Manufacturing Co., Ltd.

Keyword

frequency-modulated continuous-wave radar, convolutional neural network, electrocardiogram, heartbeat

Cite this

Copy

Daiki TODA, Ren ANZAI, Koichi ICHIGE, Ryo SAITO, Daichi UEKI, "ECG Signal Reconstruction Using FMCW Radar and a Convolutional Neural Network for Contactless Vital-Sign Sensing" in IEICE TRANSACTIONS on Communications, vol. E106-B, no. 1, pp. 65-73, January 2023, doi: 10.1587/transcom.2022EBP3005.
Abstract: A method of radar-based contactless vital-sign sensing and electrocardiogram (ECG) signal reconstruction using deep learning is proposed. A radar system is an effective tool for contactless vital-sign sensing because it can measure a small displacement of the body surface without contact. However, most of the conventional methods have limited evaluation indices and measurement conditions. A method of measuring body-surface-displacement signals by using frequency-modulated continuous-wave (FMCW) radar and reconstructing ECG signals using a convolutional neural network (CNN) is proposed. This study conducted two experiments. First, we trained a model using the data obtained from six subjects breathing in a seated condition. Second, we added sine wave noise to the data and trained the model again. The proposed model is evaluated with a correlation coefficient between the reconstructed and actual ECG signal. The results of first experiment show that their ECG signals are successfully reconstructed by using the proposed method. That of second experiment show that the proposed method can reconstruct signal waveforms even in an environment with low signal-to-noise ratio (SNR).
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2022EBP3005/_p

Copy

@ARTICLE{e106-b_1_65,
author={Daiki TODA, Ren ANZAI, Koichi ICHIGE, Ryo SAITO, Daichi UEKI, },
journal={IEICE TRANSACTIONS on Communications},
title={ECG Signal Reconstruction Using FMCW Radar and a Convolutional Neural Network for Contactless Vital-Sign Sensing},
year={2023},
volume={E106-B},
number={1},
pages={65-73},
abstract={A method of radar-based contactless vital-sign sensing and electrocardiogram (ECG) signal reconstruction using deep learning is proposed. A radar system is an effective tool for contactless vital-sign sensing because it can measure a small displacement of the body surface without contact. However, most of the conventional methods have limited evaluation indices and measurement conditions. A method of measuring body-surface-displacement signals by using frequency-modulated continuous-wave (FMCW) radar and reconstructing ECG signals using a convolutional neural network (CNN) is proposed. This study conducted two experiments. First, we trained a model using the data obtained from six subjects breathing in a seated condition. Second, we added sine wave noise to the data and trained the model again. The proposed model is evaluated with a correlation coefficient between the reconstructed and actual ECG signal. The results of first experiment show that their ECG signals are successfully reconstructed by using the proposed method. That of second experiment show that the proposed method can reconstruct signal waveforms even in an environment with low signal-to-noise ratio (SNR).},
keywords={},
doi={10.1587/transcom.2022EBP3005},
ISSN={1745-1345},
month={January},}

Copy

TY - JOUR
TI - ECG Signal Reconstruction Using FMCW Radar and a Convolutional Neural Network for Contactless Vital-Sign Sensing
T2 - IEICE TRANSACTIONS on Communications
SP - 65
EP - 73
AU - Daiki TODA
AU - Ren ANZAI
AU - Koichi ICHIGE
AU - Ryo SAITO
AU - Daichi UEKI
PY - 2023
DO - 10.1587/transcom.2022EBP3005
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E106-B
IS - 1
JA - IEICE TRANSACTIONS on Communications
Y1 - January 2023
AB - A method of radar-based contactless vital-sign sensing and electrocardiogram (ECG) signal reconstruction using deep learning is proposed. A radar system is an effective tool for contactless vital-sign sensing because it can measure a small displacement of the body surface without contact. However, most of the conventional methods have limited evaluation indices and measurement conditions. A method of measuring body-surface-displacement signals by using frequency-modulated continuous-wave (FMCW) radar and reconstructing ECG signals using a convolutional neural network (CNN) is proposed. This study conducted two experiments. First, we trained a model using the data obtained from six subjects breathing in a seated condition. Second, we added sine wave noise to the data and trained the model again. The proposed model is evaluated with a correlation coefficient between the reconstructed and actual ECG signal. The results of first experiment show that their ECG signals are successfully reconstructed by using the proposed method. That of second experiment show that the proposed method can reconstruct signal waveforms even in an environment with low signal-to-noise ratio (SNR).
ER -