Non-Negative Matrix Factorization-Based Blind Source Separation for Non-Contact Heartbeat Detection

Chen Ye, Kentaroh Toyoda, Tomoaki Ohtsuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recently, through exploiting the spectral sparsity of heartbeat component, a heartbeat detection method using a stochastic gradient approach has enabled a high-resolution of heartbeat spectrum reconstruction by Doppler radar signal, which also suppresses the residual noises after signal decomposition. However, the interference from respiration and/or body motion often corrupts the decomposition of signal by singular spectrum analysis (SSA), resulting in an inaccurate extraction of heartbeat component. In this paper, a non-negative matrix factorization (NMF)-based blind source separation (BSS) is first applied to non-contact heartbeat detection for better heartbeat extraction, incorporating the stochastic gradient approach. Specifically, motion noise is taken into account as one of sources, achieving relatively stable separation in various scenarios. In our proposed BSS approach, the spectrogram originated from radar signal is decomposed twice by NMF, which is used to learn the basis spectra (BS) relying on spectral correlation. Experimental results showed the improved accuracy and robustness of our method over conventional methods, on the heart rate (HR) measurement against subjects' sitting still or typewriting.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Communications, ICC 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538680889
DOIs
Publication statusPublished - 2019 May 1
Event2019 IEEE International Conference on Communications, ICC 2019 - Shanghai, China
Duration: 2019 May 202019 May 24

Publication series

NameIEEE International Conference on Communications
Volume2019-May
ISSN (Print)1550-3607

Conference

Conference2019 IEEE International Conference on Communications, ICC 2019
CountryChina
CityShanghai
Period19/5/2019/5/24

Fingerprint

Blind source separation
Factorization
Decomposition
Doppler radar
Spectrum analysis
Radar

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Ye, C., Toyoda, K., & Ohtsuki, T. (2019). Non-Negative Matrix Factorization-Based Blind Source Separation for Non-Contact Heartbeat Detection. In 2019 IEEE International Conference on Communications, ICC 2019 - Proceedings [8761743] (IEEE International Conference on Communications; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICC.2019.8761743

Non-Negative Matrix Factorization-Based Blind Source Separation for Non-Contact Heartbeat Detection. / Ye, Chen; Toyoda, Kentaroh; Ohtsuki, Tomoaki.

2019 IEEE International Conference on Communications, ICC 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8761743 (IEEE International Conference on Communications; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ye, C, Toyoda, K & Ohtsuki, T 2019, Non-Negative Matrix Factorization-Based Blind Source Separation for Non-Contact Heartbeat Detection. in 2019 IEEE International Conference on Communications, ICC 2019 - Proceedings., 8761743, IEEE International Conference on Communications, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Conference on Communications, ICC 2019, Shanghai, China, 19/5/20. https://doi.org/10.1109/ICC.2019.8761743
Ye C, Toyoda K, Ohtsuki T. Non-Negative Matrix Factorization-Based Blind Source Separation for Non-Contact Heartbeat Detection. In 2019 IEEE International Conference on Communications, ICC 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8761743. (IEEE International Conference on Communications). https://doi.org/10.1109/ICC.2019.8761743
Ye, Chen ; Toyoda, Kentaroh ; Ohtsuki, Tomoaki. / Non-Negative Matrix Factorization-Based Blind Source Separation for Non-Contact Heartbeat Detection. 2019 IEEE International Conference on Communications, ICC 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (IEEE International Conference on Communications).
@inproceedings{1c109bc66be64122a54e6a025260a0ce,
title = "Non-Negative Matrix Factorization-Based Blind Source Separation for Non-Contact Heartbeat Detection",
abstract = "Recently, through exploiting the spectral sparsity of heartbeat component, a heartbeat detection method using a stochastic gradient approach has enabled a high-resolution of heartbeat spectrum reconstruction by Doppler radar signal, which also suppresses the residual noises after signal decomposition. However, the interference from respiration and/or body motion often corrupts the decomposition of signal by singular spectrum analysis (SSA), resulting in an inaccurate extraction of heartbeat component. In this paper, a non-negative matrix factorization (NMF)-based blind source separation (BSS) is first applied to non-contact heartbeat detection for better heartbeat extraction, incorporating the stochastic gradient approach. Specifically, motion noise is taken into account as one of sources, achieving relatively stable separation in various scenarios. In our proposed BSS approach, the spectrogram originated from radar signal is decomposed twice by NMF, which is used to learn the basis spectra (BS) relying on spectral correlation. Experimental results showed the improved accuracy and robustness of our method over conventional methods, on the heart rate (HR) measurement against subjects' sitting still or typewriting.",
author = "Chen Ye and Kentaroh Toyoda and Tomoaki Ohtsuki",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICC.2019.8761743",
language = "English",
series = "IEEE International Conference on Communications",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE International Conference on Communications, ICC 2019 - Proceedings",

}

TY - GEN

T1 - Non-Negative Matrix Factorization-Based Blind Source Separation for Non-Contact Heartbeat Detection

AU - Ye, Chen

AU - Toyoda, Kentaroh

AU - Ohtsuki, Tomoaki

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Recently, through exploiting the spectral sparsity of heartbeat component, a heartbeat detection method using a stochastic gradient approach has enabled a high-resolution of heartbeat spectrum reconstruction by Doppler radar signal, which also suppresses the residual noises after signal decomposition. However, the interference from respiration and/or body motion often corrupts the decomposition of signal by singular spectrum analysis (SSA), resulting in an inaccurate extraction of heartbeat component. In this paper, a non-negative matrix factorization (NMF)-based blind source separation (BSS) is first applied to non-contact heartbeat detection for better heartbeat extraction, incorporating the stochastic gradient approach. Specifically, motion noise is taken into account as one of sources, achieving relatively stable separation in various scenarios. In our proposed BSS approach, the spectrogram originated from radar signal is decomposed twice by NMF, which is used to learn the basis spectra (BS) relying on spectral correlation. Experimental results showed the improved accuracy and robustness of our method over conventional methods, on the heart rate (HR) measurement against subjects' sitting still or typewriting.

AB - Recently, through exploiting the spectral sparsity of heartbeat component, a heartbeat detection method using a stochastic gradient approach has enabled a high-resolution of heartbeat spectrum reconstruction by Doppler radar signal, which also suppresses the residual noises after signal decomposition. However, the interference from respiration and/or body motion often corrupts the decomposition of signal by singular spectrum analysis (SSA), resulting in an inaccurate extraction of heartbeat component. In this paper, a non-negative matrix factorization (NMF)-based blind source separation (BSS) is first applied to non-contact heartbeat detection for better heartbeat extraction, incorporating the stochastic gradient approach. Specifically, motion noise is taken into account as one of sources, achieving relatively stable separation in various scenarios. In our proposed BSS approach, the spectrogram originated from radar signal is decomposed twice by NMF, which is used to learn the basis spectra (BS) relying on spectral correlation. Experimental results showed the improved accuracy and robustness of our method over conventional methods, on the heart rate (HR) measurement against subjects' sitting still or typewriting.

UR - http://www.scopus.com/inward/record.url?scp=85070188320&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070188320&partnerID=8YFLogxK

U2 - 10.1109/ICC.2019.8761743

DO - 10.1109/ICC.2019.8761743

M3 - Conference contribution

AN - SCOPUS:85070188320

T3 - IEEE International Conference on Communications

BT - 2019 IEEE International Conference on Communications, ICC 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -