Multichannel Bed Pressure Sensor for Sleep Monitoring

Juha Matti Kortelainen (Corresponding author), Mark van Gils, Juha Pärkkä

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

33 Citations (Scopus)

Abstract

A bed sensor with multiple pressure sensitive non-contacting electrodes has been applied for unobtrusive monitoring during sleep. The novelty is in using multichannel algorithms to improve extraction of the heart rate and respiration signal from the recorded ballistocardiographic (BCG) data. Heart rate is extracted by using a sliding Fourier Transform, and after averaging the sensor channels in the frequency domain, the attained resolution enables to detect individual heart beat intervals (HBI) and estimate the heart rate variability (HRV). The respiration signal is calculated from the low pass filtered BCG signals by updating the linear coefficients with an adaptive principal component analysis (PCA) model. In comparison to the reference ECG R-R interval, the relative error of the HBI has been 0.40 % with 88 % measurement coverage for the healthy subjects during normal sleep. The error of the respiratory rate estimated from the bed sensor has been 1.5 % in comparison with the respiratory inductive plethysmogram (RIP). For the group of patients having different kinds of suspected sleep disorders, the measurement coverage varied a lot between subjects due to increased movement artifacts. In this case, some examples of detecting respiratory disorders with bed sensor signals are shown.
Original languageEnglish
Title of host publicationProceedings of the 39th Computing in Cardiology, 2012
Pages313-316
Publication statusPublished - 2012
MoE publication typeA4 Article in a conference publication
Event39th Computing in Cardiology Conference - Krakow, Poland
Duration: 9 Sep 201212 Sep 2012

Conference

Conference39th Computing in Cardiology Conference
CountryPoland
CityKrakow
Period9/09/1212/09/12

Fingerprint

Pressure sensors
Monitoring
Sensors
Electrocardiography
Principal component analysis
Fourier transforms
Sleep
Electrodes

Keywords

  • bed sensor
  • heart rate
  • sleep
  • apnoea
  • ballistocardiographic

Cite this

Kortelainen, J. M., van Gils, M., & Pärkkä, J. (2012). Multichannel Bed Pressure Sensor for Sleep Monitoring. In Proceedings of the 39th Computing in Cardiology, 2012 (pp. 313-316)
Kortelainen, Juha Matti ; van Gils, Mark ; Pärkkä, Juha. / Multichannel Bed Pressure Sensor for Sleep Monitoring. Proceedings of the 39th Computing in Cardiology, 2012. 2012. pp. 313-316
@inproceedings{39b845cef552472f8e3b2a71f95cebc2,
title = "Multichannel Bed Pressure Sensor for Sleep Monitoring",
abstract = "A bed sensor with multiple pressure sensitive non-contacting electrodes has been applied for unobtrusive monitoring during sleep. The novelty is in using multichannel algorithms to improve extraction of the heart rate and respiration signal from the recorded ballistocardiographic (BCG) data. Heart rate is extracted by using a sliding Fourier Transform, and after averaging the sensor channels in the frequency domain, the attained resolution enables to detect individual heart beat intervals (HBI) and estimate the heart rate variability (HRV). The respiration signal is calculated from the low pass filtered BCG signals by updating the linear coefficients with an adaptive principal component analysis (PCA) model. In comparison to the reference ECG R-R interval, the relative error of the HBI has been 0.40 {\%} with 88 {\%} measurement coverage for the healthy subjects during normal sleep. The error of the respiratory rate estimated from the bed sensor has been 1.5 {\%} in comparison with the respiratory inductive plethysmogram (RIP). For the group of patients having different kinds of suspected sleep disorders, the measurement coverage varied a lot between subjects due to increased movement artifacts. In this case, some examples of detecting respiratory disorders with bed sensor signals are shown.",
keywords = "bed sensor, heart rate, sleep, apnoea, ballistocardiographic",
author = "Kortelainen, {Juha Matti} and {van Gils}, Mark and Juha P{\"a}rkk{\"a}",
note = "Project code: 18982",
year = "2012",
language = "English",
pages = "313--316",
booktitle = "Proceedings of the 39th Computing in Cardiology, 2012",

}

Kortelainen, JM, van Gils, M & Pärkkä, J 2012, Multichannel Bed Pressure Sensor for Sleep Monitoring. in Proceedings of the 39th Computing in Cardiology, 2012. pp. 313-316, 39th Computing in Cardiology Conference, Krakow, Poland, 9/09/12.

Multichannel Bed Pressure Sensor for Sleep Monitoring. / Kortelainen, Juha Matti (Corresponding author); van Gils, Mark; Pärkkä, Juha.

Proceedings of the 39th Computing in Cardiology, 2012. 2012. p. 313-316.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Multichannel Bed Pressure Sensor for Sleep Monitoring

AU - Kortelainen, Juha Matti

AU - van Gils, Mark

AU - Pärkkä, Juha

N1 - Project code: 18982

PY - 2012

Y1 - 2012

N2 - A bed sensor with multiple pressure sensitive non-contacting electrodes has been applied for unobtrusive monitoring during sleep. The novelty is in using multichannel algorithms to improve extraction of the heart rate and respiration signal from the recorded ballistocardiographic (BCG) data. Heart rate is extracted by using a sliding Fourier Transform, and after averaging the sensor channels in the frequency domain, the attained resolution enables to detect individual heart beat intervals (HBI) and estimate the heart rate variability (HRV). The respiration signal is calculated from the low pass filtered BCG signals by updating the linear coefficients with an adaptive principal component analysis (PCA) model. In comparison to the reference ECG R-R interval, the relative error of the HBI has been 0.40 % with 88 % measurement coverage for the healthy subjects during normal sleep. The error of the respiratory rate estimated from the bed sensor has been 1.5 % in comparison with the respiratory inductive plethysmogram (RIP). For the group of patients having different kinds of suspected sleep disorders, the measurement coverage varied a lot between subjects due to increased movement artifacts. In this case, some examples of detecting respiratory disorders with bed sensor signals are shown.

AB - A bed sensor with multiple pressure sensitive non-contacting electrodes has been applied for unobtrusive monitoring during sleep. The novelty is in using multichannel algorithms to improve extraction of the heart rate and respiration signal from the recorded ballistocardiographic (BCG) data. Heart rate is extracted by using a sliding Fourier Transform, and after averaging the sensor channels in the frequency domain, the attained resolution enables to detect individual heart beat intervals (HBI) and estimate the heart rate variability (HRV). The respiration signal is calculated from the low pass filtered BCG signals by updating the linear coefficients with an adaptive principal component analysis (PCA) model. In comparison to the reference ECG R-R interval, the relative error of the HBI has been 0.40 % with 88 % measurement coverage for the healthy subjects during normal sleep. The error of the respiratory rate estimated from the bed sensor has been 1.5 % in comparison with the respiratory inductive plethysmogram (RIP). For the group of patients having different kinds of suspected sleep disorders, the measurement coverage varied a lot between subjects due to increased movement artifacts. In this case, some examples of detecting respiratory disorders with bed sensor signals are shown.

KW - bed sensor

KW - heart rate

KW - sleep

KW - apnoea

KW - ballistocardiographic

M3 - Conference article in proceedings

SP - 313

EP - 316

BT - Proceedings of the 39th Computing in Cardiology, 2012

ER -

Kortelainen JM, van Gils M, Pärkkä J. Multichannel Bed Pressure Sensor for Sleep Monitoring. In Proceedings of the 39th Computing in Cardiology, 2012. 2012. p. 313-316