Automatic sleep staging based on ballistocardiographic signals recorded through bed sensors

Matteo Migliorini, Anna M. Bianchi, Juha M. Kortelainen, Edgar Arce-Santana, Sergio Cerutti, Martin O. Mendez, Domenico Nisticò

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

22 Citations (Scopus)

Abstract

This study presents different methods for automatic sleep classification based on heart rate variability (HRV), respiration and movement signals recorded through bed sensors. Two methods for feature extraction have been implemented: time variant-autoregressive model (TVAM) and wavelet discrete transform (WDT); the obtained features are fed into two classifiers: Quadratic (QD) and Linear (LD) discriminant for staging sleep in REM, nonREM and WAKE periods. The performances of all the possible combinations of feature extractors and classifiers are compared in terms of accuracy and kappa index, using clinical polysomographyc evaluation as golden standard. 17 recordings from healthy subjects, including also polisomnography, were used to train and test the algorithms. When automatic classification is compared. QD-TVAM algorithm achieved a total accuracy of 76.81 ± 7.51% and kappa index of 0.55 ± 0.10, while LD-WDT achieved a total accuracy of 79 ± 10% and kappa index of 0.51 ± 0.17. The results suggest that a good sleep evaluation can be achieved through non-conventional recording systems that could be used outside sleep centers.
Original languageEnglish
Title of host publication2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010)
Subtitle of host publicationBuenos Aires, Argentina, 31 Aug. - 4 Sept. 2010
Place of PublicationPiscataway, NJ, USA
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages3273-3276
ISBN (Print)978-1-4244-4123-5, 978-1-4244-4124-2
DOIs
Publication statusPublished - 2010
MoE publication typeA4 Article in a conference publication

Fingerprint

Discrete wavelet transforms
Sensors
Classifiers
Feature extraction
Sleep

Cite this

Migliorini, M., Bianchi, A. M., Kortelainen, J. M., Arce-Santana, E., Cerutti, S., Mendez, M. O., & Nisticò, D. (2010). Automatic sleep staging based on ballistocardiographic signals recorded through bed sensors. In 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010): Buenos Aires, Argentina, 31 Aug. - 4 Sept. 2010 (pp. 3273-3276). Piscataway, NJ, USA: Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/IEMBS.2010.5627217
Migliorini, Matteo ; Bianchi, Anna M. ; Kortelainen, Juha M. ; Arce-Santana, Edgar ; Cerutti, Sergio ; Mendez, Martin O. ; Nisticò, Domenico. / Automatic sleep staging based on ballistocardiographic signals recorded through bed sensors. 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010): Buenos Aires, Argentina, 31 Aug. - 4 Sept. 2010. Piscataway, NJ, USA : Institute of Electrical and Electronic Engineers IEEE, 2010. pp. 3273-3276
@inproceedings{620a29e9ec29425ba26f78be9e767f24,
title = "Automatic sleep staging based on ballistocardiographic signals recorded through bed sensors",
abstract = "This study presents different methods for automatic sleep classification based on heart rate variability (HRV), respiration and movement signals recorded through bed sensors. Two methods for feature extraction have been implemented: time variant-autoregressive model (TVAM) and wavelet discrete transform (WDT); the obtained features are fed into two classifiers: Quadratic (QD) and Linear (LD) discriminant for staging sleep in REM, nonREM and WAKE periods. The performances of all the possible combinations of feature extractors and classifiers are compared in terms of accuracy and kappa index, using clinical polysomographyc evaluation as golden standard. 17 recordings from healthy subjects, including also polisomnography, were used to train and test the algorithms. When automatic classification is compared. QD-TVAM algorithm achieved a total accuracy of 76.81 ± 7.51{\%} and kappa index of 0.55 ± 0.10, while LD-WDT achieved a total accuracy of 79 ± 10{\%} and kappa index of 0.51 ± 0.17. The results suggest that a good sleep evaluation can be achieved through non-conventional recording systems that could be used outside sleep centers.",
author = "Matteo Migliorini and Bianchi, {Anna M.} and Kortelainen, {Juha M.} and Edgar Arce-Santana and Sergio Cerutti and Mendez, {Martin O.} and Domenico Nistic{\`o}",
year = "2010",
doi = "10.1109/IEMBS.2010.5627217",
language = "English",
isbn = "978-1-4244-4123-5",
pages = "3273--3276",
booktitle = "2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010)",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Migliorini, M, Bianchi, AM, Kortelainen, JM, Arce-Santana, E, Cerutti, S, Mendez, MO & Nisticò, D 2010, Automatic sleep staging based on ballistocardiographic signals recorded through bed sensors. in 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010): Buenos Aires, Argentina, 31 Aug. - 4 Sept. 2010. Institute of Electrical and Electronic Engineers IEEE, Piscataway, NJ, USA, pp. 3273-3276. https://doi.org/10.1109/IEMBS.2010.5627217

Automatic sleep staging based on ballistocardiographic signals recorded through bed sensors. / Migliorini, Matteo; Bianchi, Anna M.; Kortelainen, Juha M.; Arce-Santana, Edgar; Cerutti, Sergio; Mendez, Martin O.; Nisticò, Domenico.

2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010): Buenos Aires, Argentina, 31 Aug. - 4 Sept. 2010. Piscataway, NJ, USA : Institute of Electrical and Electronic Engineers IEEE, 2010. p. 3273-3276.

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

TY - GEN

T1 - Automatic sleep staging based on ballistocardiographic signals recorded through bed sensors

AU - Migliorini, Matteo

AU - Bianchi, Anna M.

AU - Kortelainen, Juha M.

AU - Arce-Santana, Edgar

AU - Cerutti, Sergio

AU - Mendez, Martin O.

AU - Nisticò, Domenico

PY - 2010

Y1 - 2010

N2 - This study presents different methods for automatic sleep classification based on heart rate variability (HRV), respiration and movement signals recorded through bed sensors. Two methods for feature extraction have been implemented: time variant-autoregressive model (TVAM) and wavelet discrete transform (WDT); the obtained features are fed into two classifiers: Quadratic (QD) and Linear (LD) discriminant for staging sleep in REM, nonREM and WAKE periods. The performances of all the possible combinations of feature extractors and classifiers are compared in terms of accuracy and kappa index, using clinical polysomographyc evaluation as golden standard. 17 recordings from healthy subjects, including also polisomnography, were used to train and test the algorithms. When automatic classification is compared. QD-TVAM algorithm achieved a total accuracy of 76.81 ± 7.51% and kappa index of 0.55 ± 0.10, while LD-WDT achieved a total accuracy of 79 ± 10% and kappa index of 0.51 ± 0.17. The results suggest that a good sleep evaluation can be achieved through non-conventional recording systems that could be used outside sleep centers.

AB - This study presents different methods for automatic sleep classification based on heart rate variability (HRV), respiration and movement signals recorded through bed sensors. Two methods for feature extraction have been implemented: time variant-autoregressive model (TVAM) and wavelet discrete transform (WDT); the obtained features are fed into two classifiers: Quadratic (QD) and Linear (LD) discriminant for staging sleep in REM, nonREM and WAKE periods. The performances of all the possible combinations of feature extractors and classifiers are compared in terms of accuracy and kappa index, using clinical polysomographyc evaluation as golden standard. 17 recordings from healthy subjects, including also polisomnography, were used to train and test the algorithms. When automatic classification is compared. QD-TVAM algorithm achieved a total accuracy of 76.81 ± 7.51% and kappa index of 0.55 ± 0.10, while LD-WDT achieved a total accuracy of 79 ± 10% and kappa index of 0.51 ± 0.17. The results suggest that a good sleep evaluation can be achieved through non-conventional recording systems that could be used outside sleep centers.

U2 - 10.1109/IEMBS.2010.5627217

DO - 10.1109/IEMBS.2010.5627217

M3 - Conference article in proceedings

SN - 978-1-4244-4123-5

SN - 978-1-4244-4124-2

SP - 3273

EP - 3276

BT - 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010)

PB - Institute of Electrical and Electronic Engineers IEEE

CY - Piscataway, NJ, USA

ER -

Migliorini M, Bianchi AM, Kortelainen JM, Arce-Santana E, Cerutti S, Mendez MO et al. Automatic sleep staging based on ballistocardiographic signals recorded through bed sensors. In 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2010): Buenos Aires, Argentina, 31 Aug. - 4 Sept. 2010. Piscataway, NJ, USA: Institute of Electrical and Electronic Engineers IEEE. 2010. p. 3273-3276 https://doi.org/10.1109/IEMBS.2010.5627217