Classification of awake, REM, and NREM from EEG via singular spectrum analysis

Mohammad Ghavami; S Sanei

doi:10.1109/EMBC.2015.7319460

Classification of awake, REM, and NREM from EEG via singular spectrum analysis

Mohammad Ghavami, S Sanei

Electrical and Electronic Engineering

Research output: Contribution to conference › Item › peer-review

19 Citations (Scopus)

Abstract

© 2015 IEEE. In this study, a single-channel electroencephalography (EEG) analysis method has been proposed for automated 3-state-sleep classification to discriminate Awake, NREM (non-rapid eye movement) and REM (rapid eye movement). For this purpose, singular spectrum analysis (SSA) is applied to automatically extract four brain rhythms: delta, theta, alpha, and beta. These subbands are then used to generate the appropriate features for sleep classification using a multi class support vector machine (M-SVM). The proposed method provided 0.79 agreement between the manual and automatic scores.

Original language	English
Pages	4769-4772
DOIs	https://doi.org/10.1109/EMBC.2015.7319460
Publication status	Published - 4 Nov 2015
Event	International Conference of the IEEE Engineering in Medicine and Biology Society - Duration: 11 Apr 2015 → …

Conference

Conference	International Conference of the IEEE Engineering in Medicine and Biology Society
Period	11/04/15 → …

Keywords

Sleep
Signal Processing, Computer-Assisted
Support Vector Machine
Wakefulness
Humans
Electroencephalography
Sleep, REM
Brain

Access to Document

10.1109/EMBC.2015.7319460Licence: CC BY 4.0

Cite this

@conference{e49164c2d784433e9b0e07774c9972ae,

title = "Classification of awake, REM, and NREM from EEG via singular spectrum analysis",

abstract = "{\textcopyright} 2015 IEEE. In this study, a single-channel electroencephalography (EEG) analysis method has been proposed for automated 3-state-sleep classification to discriminate Awake, NREM (non-rapid eye movement) and REM (rapid eye movement). For this purpose, singular spectrum analysis (SSA) is applied to automatically extract four brain rhythms: delta, theta, alpha, and beta. These subbands are then used to generate the appropriate features for sleep classification using a multi class support vector machine (M-SVM). The proposed method provided 0.79 agreement between the manual and automatic scores.",

keywords = "Sleep, Signal Processing, Computer-Assisted, Support Vector Machine, Wakefulness, Humans, Electroencephalography, Sleep, REM, Brain",

author = "Mohammad Ghavami and S Sanei",

year = "2015",

month = nov,

day = "4",

doi = "10.1109/EMBC.2015.7319460",

language = "English",

pages = "4769--4772",

note = "International Conference of the IEEE Engineering in Medicine and Biology Society ; Conference date: 11-04-2015",

}

TY - CONF

T1 - Classification of awake, REM, and NREM from EEG via singular spectrum analysis

AU - Ghavami, Mohammad

AU - Sanei, S

PY - 2015/11/4

Y1 - 2015/11/4

N2 - © 2015 IEEE. In this study, a single-channel electroencephalography (EEG) analysis method has been proposed for automated 3-state-sleep classification to discriminate Awake, NREM (non-rapid eye movement) and REM (rapid eye movement). For this purpose, singular spectrum analysis (SSA) is applied to automatically extract four brain rhythms: delta, theta, alpha, and beta. These subbands are then used to generate the appropriate features for sleep classification using a multi class support vector machine (M-SVM). The proposed method provided 0.79 agreement between the manual and automatic scores.

AB - © 2015 IEEE. In this study, a single-channel electroencephalography (EEG) analysis method has been proposed for automated 3-state-sleep classification to discriminate Awake, NREM (non-rapid eye movement) and REM (rapid eye movement). For this purpose, singular spectrum analysis (SSA) is applied to automatically extract four brain rhythms: delta, theta, alpha, and beta. These subbands are then used to generate the appropriate features for sleep classification using a multi class support vector machine (M-SVM). The proposed method provided 0.79 agreement between the manual and automatic scores.

KW - Sleep

KW - Signal Processing, Computer-Assisted

KW - Support Vector Machine

KW - Wakefulness

KW - Humans

KW - Electroencephalography

KW - Sleep, REM

KW - Brain

U2 - 10.1109/EMBC.2015.7319460

DO - 10.1109/EMBC.2015.7319460

M3 - Item

SP - 4769

EP - 4772

T2 - International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 11 April 2015

ER -

Classification of awake, REM, and NREM from EEG via singular spectrum analysis

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this