On the identification of sleep stages in mouse electroencephalography time-series

Thomas Lampert, Andrea Plano, Jim Austin, Bettina Platt

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The automatic identification of sleep stages in electroencephalography (EEG) time-series is a long desired goal for researchers concerned with the study of sleep disorders. This paper presents advances towards achieving this goal, with particular application to EEG time-series recorded from mice. Approaches in the literature apply supervised learning classifiers, however, these do not reach the performance levels required for use within a laboratory. In this paper, detection reliability is increased, most notably in the case of REM stage identification, by naturally decomposing the problem and applying a support vector machine (SVM) based classifier to each of the EEG channels. Their outputs are integrated within a multiple classifier system. Furthermore, there exists no general consensus on the ideal choice of parameter values in such systems. Therefore, an investigation into the effects upon the classification performance is presented by varying parameters such as the epoch length; features size; number of training samples; and the method for calculating the power spectral density estimate. Finally, the results of these investigations are brought together to demonstrate the performance of the proposed classification algorithm in two cases: intra-animal classification and inter-animal classification. It is shown that, within a dataset of 10 EEG recordings, and using less than 1% of an EEG as training data, a mean classification errors of Awake 6.45%, NREM 5.82%, and REM 6.65% (with standard deviations less than 0.6%) are achieved in intra-animal analysis and, when using the equivalent of 7% of one EEG as training data, Awake 10.19%, NREM 7.75%, and REM 17.43% are achieved in inter-animal analysis (with mean standard deviations of 6.42%, 2.89%, and 9.69% respectively). A software package implementing the proposed approach will be made available through Cybula Ltd.

Original languageEnglish
Pages (from-to)52-64
Number of pages13
JournalJournal of Neuroscience Methods
Volume246
Early online date11 Mar 2015
DOIs
Publication statusPublished - 15 May 2015

Fingerprint

Sleep Stages
Electroencephalography
Consensus
Software
Research Personnel
Learning

Keywords

  • EEG
  • support vector machine
  • multi-classifier system
  • time-series
  • sleep stage
  • Fourier transform
  • Welch transform

Cite this

On the identification of sleep stages in mouse electroencephalography time-series. / Lampert, Thomas; Plano, Andrea; Austin, Jim; Platt, Bettina.

In: Journal of Neuroscience Methods, Vol. 246, 15.05.2015, p. 52-64.

Research output: Contribution to journalArticle

@article{f21134f6a5cf4e2195f303d2d9614a1c,
title = "On the identification of sleep stages in mouse electroencephalography time-series",
abstract = "The automatic identification of sleep stages in electroencephalography (EEG) time-series is a long desired goal for researchers concerned with the study of sleep disorders. This paper presents advances towards achieving this goal, with particular application to EEG time-series recorded from mice. Approaches in the literature apply supervised learning classifiers, however, these do not reach the performance levels required for use within a laboratory. In this paper, detection reliability is increased, most notably in the case of REM stage identification, by naturally decomposing the problem and applying a support vector machine (SVM) based classifier to each of the EEG channels. Their outputs are integrated within a multiple classifier system. Furthermore, there exists no general consensus on the ideal choice of parameter values in such systems. Therefore, an investigation into the effects upon the classification performance is presented by varying parameters such as the epoch length; features size; number of training samples; and the method for calculating the power spectral density estimate. Finally, the results of these investigations are brought together to demonstrate the performance of the proposed classification algorithm in two cases: intra-animal classification and inter-animal classification. It is shown that, within a dataset of 10 EEG recordings, and using less than 1{\%} of an EEG as training data, a mean classification errors of Awake 6.45{\%}, NREM 5.82{\%}, and REM 6.65{\%} (with standard deviations less than 0.6{\%}) are achieved in intra-animal analysis and, when using the equivalent of 7{\%} of one EEG as training data, Awake 10.19{\%}, NREM 7.75{\%}, and REM 17.43{\%} are achieved in inter-animal analysis (with mean standard deviations of 6.42{\%}, 2.89{\%}, and 9.69{\%} respectively). A software package implementing the proposed approach will be made available through Cybula Ltd.",
keywords = "EEG, support vector machine, multi-classifier system, time-series, sleep stage, Fourier transform, Welch transform",
author = "Thomas Lampert and Andrea Plano and Jim Austin and Bettina Platt",
note = "Copyright {\circledC} 2015 Elsevier B.V. All rights reserved.",
year = "2015",
month = "5",
day = "15",
doi = "10.1016/j.jneumeth.2015.03.007",
language = "English",
volume = "246",
pages = "52--64",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",

}

TY - JOUR

T1 - On the identification of sleep stages in mouse electroencephalography time-series

AU - Lampert, Thomas

AU - Plano, Andrea

AU - Austin, Jim

AU - Platt, Bettina

N1 - Copyright © 2015 Elsevier B.V. All rights reserved.

PY - 2015/5/15

Y1 - 2015/5/15

N2 - The automatic identification of sleep stages in electroencephalography (EEG) time-series is a long desired goal for researchers concerned with the study of sleep disorders. This paper presents advances towards achieving this goal, with particular application to EEG time-series recorded from mice. Approaches in the literature apply supervised learning classifiers, however, these do not reach the performance levels required for use within a laboratory. In this paper, detection reliability is increased, most notably in the case of REM stage identification, by naturally decomposing the problem and applying a support vector machine (SVM) based classifier to each of the EEG channels. Their outputs are integrated within a multiple classifier system. Furthermore, there exists no general consensus on the ideal choice of parameter values in such systems. Therefore, an investigation into the effects upon the classification performance is presented by varying parameters such as the epoch length; features size; number of training samples; and the method for calculating the power spectral density estimate. Finally, the results of these investigations are brought together to demonstrate the performance of the proposed classification algorithm in two cases: intra-animal classification and inter-animal classification. It is shown that, within a dataset of 10 EEG recordings, and using less than 1% of an EEG as training data, a mean classification errors of Awake 6.45%, NREM 5.82%, and REM 6.65% (with standard deviations less than 0.6%) are achieved in intra-animal analysis and, when using the equivalent of 7% of one EEG as training data, Awake 10.19%, NREM 7.75%, and REM 17.43% are achieved in inter-animal analysis (with mean standard deviations of 6.42%, 2.89%, and 9.69% respectively). A software package implementing the proposed approach will be made available through Cybula Ltd.

AB - The automatic identification of sleep stages in electroencephalography (EEG) time-series is a long desired goal for researchers concerned with the study of sleep disorders. This paper presents advances towards achieving this goal, with particular application to EEG time-series recorded from mice. Approaches in the literature apply supervised learning classifiers, however, these do not reach the performance levels required for use within a laboratory. In this paper, detection reliability is increased, most notably in the case of REM stage identification, by naturally decomposing the problem and applying a support vector machine (SVM) based classifier to each of the EEG channels. Their outputs are integrated within a multiple classifier system. Furthermore, there exists no general consensus on the ideal choice of parameter values in such systems. Therefore, an investigation into the effects upon the classification performance is presented by varying parameters such as the epoch length; features size; number of training samples; and the method for calculating the power spectral density estimate. Finally, the results of these investigations are brought together to demonstrate the performance of the proposed classification algorithm in two cases: intra-animal classification and inter-animal classification. It is shown that, within a dataset of 10 EEG recordings, and using less than 1% of an EEG as training data, a mean classification errors of Awake 6.45%, NREM 5.82%, and REM 6.65% (with standard deviations less than 0.6%) are achieved in intra-animal analysis and, when using the equivalent of 7% of one EEG as training data, Awake 10.19%, NREM 7.75%, and REM 17.43% are achieved in inter-animal analysis (with mean standard deviations of 6.42%, 2.89%, and 9.69% respectively). A software package implementing the proposed approach will be made available through Cybula Ltd.

KW - EEG

KW - support vector machine

KW - multi-classifier system

KW - time-series

KW - sleep stage

KW - Fourier transform

KW - Welch transform

U2 - 10.1016/j.jneumeth.2015.03.007

DO - 10.1016/j.jneumeth.2015.03.007

M3 - Article

VL - 246

SP - 52

EP - 64

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

ER -