Sleep onset detection based on Time-Varying Autoregressive models with particle filter estimation

Ramiro Chaparro-Vargas, P. Chamila Dissayanaka, Thomas Penzel, Beena Ahmed, Dean Cvetkovic

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

3 Citations (Scopus)

Abstract

In this paper, we introduce a computer - Assisted approach for the characterisation of sleep onset periods. The processing of polysomnographic (PSG) recordings involves the modelling of Time-Varying Autoregressive Moving Average (TVARMA) processes with recursive particle filtering. The feature set engages the computation of electroencephalogram (EEG) frequency bands δ, θ, α, ς, β, mean amplitude of electrooculogram (EOG) and electromyogram (EMG) signals. This is subsequently transferred to an ensemble classifier to detect Wake (W), non-REM1 (N1) and non-REM2 (N2) sleep stages. As a result, novel contributions in terms of non-Gaussian modelling of biosignal processes, approximation to PSG distributions with particle filtering and time-frequency analysis by complex Morlet wavelets within sleep staging, are discussed. The findings revealed performance metrics achieving in the best cases 93:18% accuracy, 6:82% error and 100% sensitivity/specificity rates.

Original languageEnglish
Title of host publicationIECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet"
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages436-441
Number of pages6
ISBN (Electronic)9781479940844
DOIs
Publication statusPublished - 23 Feb 2015
Event3rd IEEE Conference on Biomedical Engineering and Sciences, IECBES 2014 - Kuala Lumpur, Malaysia
Duration: 8 Dec 201410 Dec 2014

Other

Other3rd IEEE Conference on Biomedical Engineering and Sciences, IECBES 2014
CountryMalaysia
CityKuala Lumpur
Period8/12/1410/12/14

Fingerprint

Electroencephalography
Frequency bands
Classifiers
Processing
Sleep

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Chaparro-Vargas, R., Dissayanaka, P. C., Penzel, T., Ahmed, B., & Cvetkovic, D. (2015). Sleep onset detection based on Time-Varying Autoregressive models with particle filter estimation. In IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet" (pp. 436-441). [7047537] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IECBES.2014.7047537

Sleep onset detection based on Time-Varying Autoregressive models with particle filter estimation. / Chaparro-Vargas, Ramiro; Dissayanaka, P. Chamila; Penzel, Thomas; Ahmed, Beena; Cvetkovic, Dean.

IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet". Institute of Electrical and Electronics Engineers Inc., 2015. p. 436-441 7047537.

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

Chaparro-Vargas, R, Dissayanaka, PC, Penzel, T, Ahmed, B & Cvetkovic, D 2015, Sleep onset detection based on Time-Varying Autoregressive models with particle filter estimation. in IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet"., 7047537, Institute of Electrical and Electronics Engineers Inc., pp. 436-441, 3rd IEEE Conference on Biomedical Engineering and Sciences, IECBES 2014, Kuala Lumpur, Malaysia, 8/12/14. https://doi.org/10.1109/IECBES.2014.7047537
Chaparro-Vargas R, Dissayanaka PC, Penzel T, Ahmed B, Cvetkovic D. Sleep onset detection based on Time-Varying Autoregressive models with particle filter estimation. In IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet". Institute of Electrical and Electronics Engineers Inc. 2015. p. 436-441. 7047537 https://doi.org/10.1109/IECBES.2014.7047537
Chaparro-Vargas, Ramiro ; Dissayanaka, P. Chamila ; Penzel, Thomas ; Ahmed, Beena ; Cvetkovic, Dean. / Sleep onset detection based on Time-Varying Autoregressive models with particle filter estimation. IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet". Institute of Electrical and Electronics Engineers Inc., 2015. pp. 436-441
@inproceedings{1922be2226204edfb9d8c5e48fc2aaf4,
title = "Sleep onset detection based on Time-Varying Autoregressive models with particle filter estimation",
abstract = "In this paper, we introduce a computer - Assisted approach for the characterisation of sleep onset periods. The processing of polysomnographic (PSG) recordings involves the modelling of Time-Varying Autoregressive Moving Average (TVARMA) processes with recursive particle filtering. The feature set engages the computation of electroencephalogram (EEG) frequency bands δ, θ, α, ς, β, mean amplitude of electrooculogram (EOG) and electromyogram (EMG) signals. This is subsequently transferred to an ensemble classifier to detect Wake (W), non-REM1 (N1) and non-REM2 (N2) sleep stages. As a result, novel contributions in terms of non-Gaussian modelling of biosignal processes, approximation to PSG distributions with particle filtering and time-frequency analysis by complex Morlet wavelets within sleep staging, are discussed. The findings revealed performance metrics achieving in the best cases 93:18{\%} accuracy, 6:82{\%} error and 100{\%} sensitivity/specificity rates.",
author = "Ramiro Chaparro-Vargas and Dissayanaka, {P. Chamila} and Thomas Penzel and Beena Ahmed and Dean Cvetkovic",
year = "2015",
month = "2",
day = "23",
doi = "10.1109/IECBES.2014.7047537",
language = "English",
pages = "436--441",
booktitle = "IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: {"}Miri, Where Engineering in Medicine and Biology and Humanity Meet{"}",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Sleep onset detection based on Time-Varying Autoregressive models with particle filter estimation

AU - Chaparro-Vargas, Ramiro

AU - Dissayanaka, P. Chamila

AU - Penzel, Thomas

AU - Ahmed, Beena

AU - Cvetkovic, Dean

PY - 2015/2/23

Y1 - 2015/2/23

N2 - In this paper, we introduce a computer - Assisted approach for the characterisation of sleep onset periods. The processing of polysomnographic (PSG) recordings involves the modelling of Time-Varying Autoregressive Moving Average (TVARMA) processes with recursive particle filtering. The feature set engages the computation of electroencephalogram (EEG) frequency bands δ, θ, α, ς, β, mean amplitude of electrooculogram (EOG) and electromyogram (EMG) signals. This is subsequently transferred to an ensemble classifier to detect Wake (W), non-REM1 (N1) and non-REM2 (N2) sleep stages. As a result, novel contributions in terms of non-Gaussian modelling of biosignal processes, approximation to PSG distributions with particle filtering and time-frequency analysis by complex Morlet wavelets within sleep staging, are discussed. The findings revealed performance metrics achieving in the best cases 93:18% accuracy, 6:82% error and 100% sensitivity/specificity rates.

AB - In this paper, we introduce a computer - Assisted approach for the characterisation of sleep onset periods. The processing of polysomnographic (PSG) recordings involves the modelling of Time-Varying Autoregressive Moving Average (TVARMA) processes with recursive particle filtering. The feature set engages the computation of electroencephalogram (EEG) frequency bands δ, θ, α, ς, β, mean amplitude of electrooculogram (EOG) and electromyogram (EMG) signals. This is subsequently transferred to an ensemble classifier to detect Wake (W), non-REM1 (N1) and non-REM2 (N2) sleep stages. As a result, novel contributions in terms of non-Gaussian modelling of biosignal processes, approximation to PSG distributions with particle filtering and time-frequency analysis by complex Morlet wavelets within sleep staging, are discussed. The findings revealed performance metrics achieving in the best cases 93:18% accuracy, 6:82% error and 100% sensitivity/specificity rates.

UR - http://www.scopus.com/inward/record.url?scp=84925639534&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925639534&partnerID=8YFLogxK

U2 - 10.1109/IECBES.2014.7047537

DO - 10.1109/IECBES.2014.7047537

M3 - Conference contribution

SP - 436

EP - 441

BT - IECBES 2014, Conference Proceedings - 2014 IEEE Conference on Biomedical Engineering and Sciences: "Miri, Where Engineering in Medicine and Biology and Humanity Meet"

PB - Institute of Electrical and Electronics Engineers Inc.

ER -