Improvement of force-sensor-based heart rate estimation using multichannel data fusion

C. Bruser, Juha M. Kortelainen, S. Winter, M. Tenhunen, J. Pärkkä, S. Lenohardt

Research output: Contribution to journalArticleScientificpeer-review

22 Citations (Scopus)

Abstract

The aim of this paper is to present and evaluate algorithms for heartbeat interval estimation from multiple spatially distributed force sensors integrated into a bed. Moreover, the benefit of using multichannel systems as opposed to a single sensor is investigated. While it might seem intuitive that multiple channels are superior to a single channel, the main challenge lies in finding suitable methods to actually leverage this potential. To this end, two algorithms for heart rate estimation from multichannel vibration signals are presented and compared against a single-channel sensing solution. The first method operates by analyzing the cepstrum computed from the average spectra of the individual channels, while the second method applies Bayesian fusion to three interval estimators, such as the autocorrelation, which are applied to each channel. This evaluation is based on 28 night-long sleep lab recordings during which an eight-channel polyvinylidene fluoride-based sensor array was used to acquire cardiac vibration signals. The recruited patients suffered from different sleep disorders of varying severity. From the sensor array data, a virtual single-channel signal was also derived for comparison by averaging the channels. The single-channel results achieved a beat-to-beat interval error of 2.2% with a coverage (i.e., percentage of the recording which could be analyzed) of 68.7%. In comparison, the best multichannel results attained a mean error and coverage of 1.0% and 81.0%, respectively. These results present statistically significant improvements of both metrics over the single-channel results ($p <0.05$ ).
Original languageEnglish
Pages (from-to)227-235
JournalIEEE Journal of Biomedical and Health Informatics
Volume19
Issue number1
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Sensor arrays
Data fusion
Vibration
Heart Rate
Bayes Theorem
Sensors
Autocorrelation
Sleep
polyvinylidene fluoride
Sleep Wake Disorders

Keywords

  • ballilstocardiography
  • heartbeat intervals
  • mechanocardiography
  • multichannel fusion
  • seismocardiography

Cite this

@article{3fce4766a22945b5bafb8e0756c2c8ac,
title = "Improvement of force-sensor-based heart rate estimation using multichannel data fusion",
abstract = "The aim of this paper is to present and evaluate algorithms for heartbeat interval estimation from multiple spatially distributed force sensors integrated into a bed. Moreover, the benefit of using multichannel systems as opposed to a single sensor is investigated. While it might seem intuitive that multiple channels are superior to a single channel, the main challenge lies in finding suitable methods to actually leverage this potential. To this end, two algorithms for heart rate estimation from multichannel vibration signals are presented and compared against a single-channel sensing solution. The first method operates by analyzing the cepstrum computed from the average spectra of the individual channels, while the second method applies Bayesian fusion to three interval estimators, such as the autocorrelation, which are applied to each channel. This evaluation is based on 28 night-long sleep lab recordings during which an eight-channel polyvinylidene fluoride-based sensor array was used to acquire cardiac vibration signals. The recruited patients suffered from different sleep disorders of varying severity. From the sensor array data, a virtual single-channel signal was also derived for comparison by averaging the channels. The single-channel results achieved a beat-to-beat interval error of 2.2{\%} with a coverage (i.e., percentage of the recording which could be analyzed) of 68.7{\%}. In comparison, the best multichannel results attained a mean error and coverage of 1.0{\%} and 81.0{\%}, respectively. These results present statistically significant improvements of both metrics over the single-channel results ($p <0.05$ ).",
keywords = "ballilstocardiography, heartbeat intervals, mechanocardiography, multichannel fusion, seismocardiography",
author = "C. Bruser and Kortelainen, {Juha M.} and S. Winter and M. Tenhunen and J. P{\"a}rkk{\"a} and S. Lenohardt",
year = "2015",
doi = "10.1109/JBHI.2014.2311582",
language = "English",
volume = "19",
pages = "227--235",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2208",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
number = "1",

}

Improvement of force-sensor-based heart rate estimation using multichannel data fusion. / Bruser, C.; Kortelainen, Juha M.; Winter, S.; Tenhunen, M.; Pärkkä, J.; Lenohardt, S.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 19, No. 1, 2015, p. 227-235.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Improvement of force-sensor-based heart rate estimation using multichannel data fusion

AU - Bruser, C.

AU - Kortelainen, Juha M.

AU - Winter, S.

AU - Tenhunen, M.

AU - Pärkkä, J.

AU - Lenohardt, S.

PY - 2015

Y1 - 2015

N2 - The aim of this paper is to present and evaluate algorithms for heartbeat interval estimation from multiple spatially distributed force sensors integrated into a bed. Moreover, the benefit of using multichannel systems as opposed to a single sensor is investigated. While it might seem intuitive that multiple channels are superior to a single channel, the main challenge lies in finding suitable methods to actually leverage this potential. To this end, two algorithms for heart rate estimation from multichannel vibration signals are presented and compared against a single-channel sensing solution. The first method operates by analyzing the cepstrum computed from the average spectra of the individual channels, while the second method applies Bayesian fusion to three interval estimators, such as the autocorrelation, which are applied to each channel. This evaluation is based on 28 night-long sleep lab recordings during which an eight-channel polyvinylidene fluoride-based sensor array was used to acquire cardiac vibration signals. The recruited patients suffered from different sleep disorders of varying severity. From the sensor array data, a virtual single-channel signal was also derived for comparison by averaging the channels. The single-channel results achieved a beat-to-beat interval error of 2.2% with a coverage (i.e., percentage of the recording which could be analyzed) of 68.7%. In comparison, the best multichannel results attained a mean error and coverage of 1.0% and 81.0%, respectively. These results present statistically significant improvements of both metrics over the single-channel results ($p <0.05$ ).

AB - The aim of this paper is to present and evaluate algorithms for heartbeat interval estimation from multiple spatially distributed force sensors integrated into a bed. Moreover, the benefit of using multichannel systems as opposed to a single sensor is investigated. While it might seem intuitive that multiple channels are superior to a single channel, the main challenge lies in finding suitable methods to actually leverage this potential. To this end, two algorithms for heart rate estimation from multichannel vibration signals are presented and compared against a single-channel sensing solution. The first method operates by analyzing the cepstrum computed from the average spectra of the individual channels, while the second method applies Bayesian fusion to three interval estimators, such as the autocorrelation, which are applied to each channel. This evaluation is based on 28 night-long sleep lab recordings during which an eight-channel polyvinylidene fluoride-based sensor array was used to acquire cardiac vibration signals. The recruited patients suffered from different sleep disorders of varying severity. From the sensor array data, a virtual single-channel signal was also derived for comparison by averaging the channels. The single-channel results achieved a beat-to-beat interval error of 2.2% with a coverage (i.e., percentage of the recording which could be analyzed) of 68.7%. In comparison, the best multichannel results attained a mean error and coverage of 1.0% and 81.0%, respectively. These results present statistically significant improvements of both metrics over the single-channel results ($p <0.05$ ).

KW - ballilstocardiography

KW - heartbeat intervals

KW - mechanocardiography

KW - multichannel fusion

KW - seismocardiography

U2 - 10.1109/JBHI.2014.2311582

DO - 10.1109/JBHI.2014.2311582

M3 - Article

VL - 19

SP - 227

EP - 235

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2208

IS - 1

ER -