Newborn EEG seizure pattern characterisation using time-frequency analysis

Boualem Boashash, Mostefa Mesbah, Paul Colditz

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Previous techniques for seizure detection in newborn are inefficient. The main reason for their relative poor performance resides in their assumption of stationarity of the EEG. To remedy this problem, we use time-frequency distributions (TFD) to analyse and characterise the newborn EEG seizure patterns as a first step toward a time-frequency (TF) based seizure detection and classification scheme. This paper presents the results of the analysis of these time-frequency patterns for two abnormal newborn EEGs. We demonstrate that the newborn EEG seizures are well described by a class of mono- and multi-component linear FM signals. This result is novel and contradicts the simplistic assumptions routinely made in the field.

Original languageEnglish
Pages (from-to)1041-1044
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
DOIs
Publication statusPublished - 2001

Fingerprint

Electroencephalography

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

@article{449360ea98bc4abeb1836f8edf1b4f2f,
title = "Newborn EEG seizure pattern characterisation using time-frequency analysis",
abstract = "Previous techniques for seizure detection in newborn are inefficient. The main reason for their relative poor performance resides in their assumption of stationarity of the EEG. To remedy this problem, we use time-frequency distributions (TFD) to analyse and characterise the newborn EEG seizure patterns as a first step toward a time-frequency (TF) based seizure detection and classification scheme. This paper presents the results of the analysis of these time-frequency patterns for two abnormal newborn EEGs. We demonstrate that the newborn EEG seizures are well described by a class of mono- and multi-component linear FM signals. This result is novel and contradicts the simplistic assumptions routinely made in the field.",
author = "Boualem Boashash and Mostefa Mesbah and Paul Colditz",
year = "2001",
doi = "10.1109/ICASSP.2001.941097",
language = "English",
volume = "2",
pages = "1041--1044",
journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
issn = "0736-7791",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Newborn EEG seizure pattern characterisation using time-frequency analysis

AU - Boashash, Boualem

AU - Mesbah, Mostefa

AU - Colditz, Paul

PY - 2001

Y1 - 2001

N2 - Previous techniques for seizure detection in newborn are inefficient. The main reason for their relative poor performance resides in their assumption of stationarity of the EEG. To remedy this problem, we use time-frequency distributions (TFD) to analyse and characterise the newborn EEG seizure patterns as a first step toward a time-frequency (TF) based seizure detection and classification scheme. This paper presents the results of the analysis of these time-frequency patterns for two abnormal newborn EEGs. We demonstrate that the newborn EEG seizures are well described by a class of mono- and multi-component linear FM signals. This result is novel and contradicts the simplistic assumptions routinely made in the field.

AB - Previous techniques for seizure detection in newborn are inefficient. The main reason for their relative poor performance resides in their assumption of stationarity of the EEG. To remedy this problem, we use time-frequency distributions (TFD) to analyse and characterise the newborn EEG seizure patterns as a first step toward a time-frequency (TF) based seizure detection and classification scheme. This paper presents the results of the analysis of these time-frequency patterns for two abnormal newborn EEGs. We demonstrate that the newborn EEG seizures are well described by a class of mono- and multi-component linear FM signals. This result is novel and contradicts the simplistic assumptions routinely made in the field.

UR - http://www.scopus.com/inward/record.url?scp=0034856254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034856254&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2001.941097

DO - 10.1109/ICASSP.2001.941097

M3 - Article

VL - 2

SP - 1041

EP - 1044

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

SN - 0736-7791

ER -