An Approach for Sleep Apnea Detection based on Radar Spectrogram Envelopes

Y.  Han; A. Yarovoy; F. Fioranelli

doi:10.23919/EuRAD50154.2022.9784585

An Approach for Sleep Apnea Detection based on Radar Spectrogram Envelopes

Microwave Sensing, Signals & Systems

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

5 Citations (SciVal)

108 Downloads (Pure)

Abstract

This research aims to develop a contactless, radar-based sleep apnea detection method. A novel identification approach for this is proposed, based on the envelope of UWB radar spectrograms and machine learning. The envelope of the spectrogram is extracted by an image-based method, followed by signal smoothing via variational mode decomposition (VMD). The method is validated via simulations, and experimental data collected on 14 volunteers in controlled conditions, including supine, side and prone positions and the presence of a blanket. Initial results show that the proposed approach provides over 90% accuracy, precision and recall.

Original language	English
Title of host publication	Proceedings of the 18th European Radar Conference
Publisher	IEEE
Pages	17-20
Number of pages	4
ISBN (Electronic)	978-2-87487-065-1
ISBN (Print)	978-1-6654-4723-2
DOIs	https://doi.org/10.23919/EuRAD50154.2022.9784585
Publication status	Published - 2022
Event	The 18th European Radar Conference - London, United Kingdom Duration: 5 Apr 2022 → 7 Apr 2022

Conference

Conference	The 18th European Radar Conference
Country/Territory	United Kingdom
City	London
Period	5/04/22 → 7/04/22

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

UWB radar
contactless vital sign detection
sleep apnea
machine learning

Access to Document

10.23919/EuRAD50154.2022.9784585

An_Approach_for_Sleep_Apnea_Detection_based_on_Radar_Spectrogram_EnvelopesFinal published version, 1.15 MB

Cite this

@inproceedings{ffb0d401fff6407ca1cf0905711fb000,

title = "An Approach for Sleep Apnea Detection based on Radar Spectrogram Envelopes",

abstract = "This research aims to develop a contactless, radar-based sleep apnea detection method. A novel identification approach for this is proposed, based on the envelope of UWB radar spectrograms and machine learning. The envelope of the spectrogram is extracted by an image-based method, followed by signal smoothing via variational mode decomposition (VMD). The method is validated via simulations, and experimental data collected on 14 volunteers in controlled conditions, including supine, side and prone positions and the presence of a blanket. Initial results show that the proposed approach provides over 90% accuracy, precision and recall.",

keywords = "UWB radar, contactless vital sign detection, sleep apnea, machine learning",

author = "Y. Han and A. Yarovoy and F. Fioranelli",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; The 18th European Radar Conference ; Conference date: 05-04-2022 Through 07-04-2022",

year = "2022",

doi = "10.23919/EuRAD50154.2022.9784585",

language = "English",

isbn = "978-1-6654-4723-2",

pages = "17--20",

booktitle = "Proceedings of the 18th European Radar Conference",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - An Approach for Sleep Apnea Detection based on Radar Spectrogram Envelopes

AU - Han, Y.

AU - Yarovoy, A.

AU - Fioranelli, F.

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - This research aims to develop a contactless, radar-based sleep apnea detection method. A novel identification approach for this is proposed, based on the envelope of UWB radar spectrograms and machine learning. The envelope of the spectrogram is extracted by an image-based method, followed by signal smoothing via variational mode decomposition (VMD). The method is validated via simulations, and experimental data collected on 14 volunteers in controlled conditions, including supine, side and prone positions and the presence of a blanket. Initial results show that the proposed approach provides over 90% accuracy, precision and recall.

AB - This research aims to develop a contactless, radar-based sleep apnea detection method. A novel identification approach for this is proposed, based on the envelope of UWB radar spectrograms and machine learning. The envelope of the spectrogram is extracted by an image-based method, followed by signal smoothing via variational mode decomposition (VMD). The method is validated via simulations, and experimental data collected on 14 volunteers in controlled conditions, including supine, side and prone positions and the presence of a blanket. Initial results show that the proposed approach provides over 90% accuracy, precision and recall.

KW - UWB radar

KW - contactless vital sign detection

KW - sleep apnea

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85133136450&partnerID=8YFLogxK

U2 - 10.23919/EuRAD50154.2022.9784585

DO - 10.23919/EuRAD50154.2022.9784585

M3 - Conference contribution

SN - 978-1-6654-4723-2

SP - 17

EP - 20

BT - Proceedings of the 18th European Radar Conference

PB - IEEE

T2 - The 18th European Radar Conference

Y2 - 5 April 2022 through 7 April 2022

ER -

An Approach for Sleep Apnea Detection based on Radar Spectrogram Envelopes

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this