SVD-based newborn EEG seizure detection in the time-frequency domain

Hantid Hassanpour; Mostefa Mesbah; Boualem Boashash

doi:10.1016/S1474-6670(17)33524-3

SVD-based newborn EEG seizure detection in the time-frequency domain

Hantid Hassanpour, Mostefa Mesbah, Boualem Boashash

Research output: Contribution to journal › Conference article › peer-review

Abstract

This paper utilises the Singular Value Decomposition (SVD) technique applied to the time-frequency representation of Electroencephalogram (EEG) signals for detecting EEG seizures in neonates. Seizure in EEG signal may have signature in different frequency areas. This paper, is concentrated on the low frequency (lower than 10 Hz) signature of the seizures. The proposed technique uses the estimated distribution function of the singular vectors associated with the time-frequency representation of the EEG epoch to characterise the patterns embedded in the signal. The estimated distributed functions related to the seizure and nonseizure epochs were used to train a neural network to discriminate between seizure and nonseizure patterns.

Original language	English
Pages (from-to)	329-333
Number of pages	5
Journal	IFAC Proceedings Volumes (IFAC-PapersOnline)
Volume	36
Issue number	15
DOIs	https://doi.org/10.1016/S1474-6670(17)33524-3
Publication status	Published - 2003
Externally published	Yes
Event	5th IFAC Symposium on Modelling and Control in Biomedical Systems 2003 - Melbourne, Australia Duration: Aug 21 2003 → Aug 23 2003

Keywords

Detection
Signal processing
Singular Value Decomposition
Time-frequency representation

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.1016/S1474-6670(17)33524-3

Cite this

@article{d558002c0cf24ea5bf6d28396ffa3a87,

title = "SVD-based newborn EEG seizure detection in the time-frequency domain",

abstract = "This paper utilises the Singular Value Decomposition (SVD) technique applied to the time-frequency representation of Electroencephalogram (EEG) signals for detecting EEG seizures in neonates. Seizure in EEG signal may have signature in different frequency areas. This paper, is concentrated on the low frequency (lower than 10 Hz) signature of the seizures. The proposed technique uses the estimated distribution function of the singular vectors associated with the time-frequency representation of the EEG epoch to characterise the patterns embedded in the signal. The estimated distributed functions related to the seizure and nonseizure epochs were used to train a neural network to discriminate between seizure and nonseizure patterns.",

keywords = "Detection, Signal processing, Singular Value Decomposition, Time-frequency representation",

author = "Hantid Hassanpour and Mostefa Mesbah and Boualem Boashash",

note = "Publisher Copyright: {\textcopyright} 2003 IF AC.; 5th IFAC Symposium on Modelling and Control in Biomedical Systems 2003 ; Conference date: 21-08-2003 Through 23-08-2003",

year = "2003",

doi = "10.1016/S1474-6670(17)33524-3",

language = "English",

volume = "36",

pages = "329--333",

journal = "IFAC Proceedings Volumes (IFAC-PapersOnline)",

issn = "1474-6670",

publisher = "IFAC Secretariat",

number = "15",

}

TY - JOUR

T1 - SVD-based newborn EEG seizure detection in the time-frequency domain

AU - Hassanpour, Hantid

AU - Mesbah, Mostefa

AU - Boashash, Boualem

PY - 2003

Y1 - 2003

N2 - This paper utilises the Singular Value Decomposition (SVD) technique applied to the time-frequency representation of Electroencephalogram (EEG) signals for detecting EEG seizures in neonates. Seizure in EEG signal may have signature in different frequency areas. This paper, is concentrated on the low frequency (lower than 10 Hz) signature of the seizures. The proposed technique uses the estimated distribution function of the singular vectors associated with the time-frequency representation of the EEG epoch to characterise the patterns embedded in the signal. The estimated distributed functions related to the seizure and nonseizure epochs were used to train a neural network to discriminate between seizure and nonseizure patterns.

AB - This paper utilises the Singular Value Decomposition (SVD) technique applied to the time-frequency representation of Electroencephalogram (EEG) signals for detecting EEG seizures in neonates. Seizure in EEG signal may have signature in different frequency areas. This paper, is concentrated on the low frequency (lower than 10 Hz) signature of the seizures. The proposed technique uses the estimated distribution function of the singular vectors associated with the time-frequency representation of the EEG epoch to characterise the patterns embedded in the signal. The estimated distributed functions related to the seizure and nonseizure epochs were used to train a neural network to discriminate between seizure and nonseizure patterns.

KW - Detection

KW - Signal processing

KW - Singular Value Decomposition

KW - Time-frequency representation

UR - http://www.scopus.com/inward/record.url?scp=85064382257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064382257&partnerID=8YFLogxK

U2 - 10.1016/S1474-6670(17)33524-3

DO - 10.1016/S1474-6670(17)33524-3

M3 - Conference article

AN - SCOPUS:85064382257

SN - 1474-6670

VL - 36

SP - 329

EP - 333

JO - IFAC Proceedings Volumes (IFAC-PapersOnline)

JF - IFAC Proceedings Volumes (IFAC-PapersOnline)

IS - 15

T2 - 5th IFAC Symposium on Modelling and Control in Biomedical Systems 2003

Y2 - 21 August 2003 through 23 August 2003

ER -

SVD-based newborn EEG seizure detection in the time-frequency domain

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this