Time-frequency based newborn EEG seizure detection using low and high frequency signatures

Hamid Hassanpour, Mostefa Mesbah, Boualem Boashash

Research output: Contribution to journalArticle

33 Citations (Scopus)

Abstract

The nonstationary and multicomponent nature of newborn EEG seizures tend to increase the complexity of the seizure detection problem. In dealing with this type of problem, time-frequency based techniques were shown to outperform classical techniques. Neonatal EEG seizures have signatures in both low frequency (lower than 10 Hz) and high frequency (higher than 70 Hz) areas. Seizure detection techniques have been proposed that concentrate on either low frequency or high frequency signatures of seizures. They, however, tend to miss seizures that reveal themselves only in one of the frequency areas. To overcome this problem, we propose a detection method that uses time-frequency seizure features extracted from both low and high frequency areas. Results of applying the proposed method on five newborn EEGs are very encouraging.

Original languageEnglish
Pages (from-to)935-944
Number of pages10
JournalPhysiological Measurement
Volume25
Issue number4
DOIs
Publication statusPublished - Aug 2004

Fingerprint

Electroencephalography
Seizures

Keywords

  • EEG seizure detection
  • Singular vector
  • Spike detection
  • Time-frequency

ASJC Scopus subject areas

  • Biophysics
  • Physiology
  • Physiology (medical)

Cite this

Time-frequency based newborn EEG seizure detection using low and high frequency signatures. / Hassanpour, Hamid; Mesbah, Mostefa; Boashash, Boualem.

In: Physiological Measurement, Vol. 25, No. 4, 08.2004, p. 935-944.

Research output: Contribution to journalArticle

@article{bbf4dcb8abcb4827b883eef7bdc9c21c,
title = "Time-frequency based newborn EEG seizure detection using low and high frequency signatures",
abstract = "The nonstationary and multicomponent nature of newborn EEG seizures tend to increase the complexity of the seizure detection problem. In dealing with this type of problem, time-frequency based techniques were shown to outperform classical techniques. Neonatal EEG seizures have signatures in both low frequency (lower than 10 Hz) and high frequency (higher than 70 Hz) areas. Seizure detection techniques have been proposed that concentrate on either low frequency or high frequency signatures of seizures. They, however, tend to miss seizures that reveal themselves only in one of the frequency areas. To overcome this problem, we propose a detection method that uses time-frequency seizure features extracted from both low and high frequency areas. Results of applying the proposed method on five newborn EEGs are very encouraging.",
keywords = "EEG seizure detection, Singular vector, Spike detection, Time-frequency",
author = "Hamid Hassanpour and Mostefa Mesbah and Boualem Boashash",
year = "2004",
month = "8",
doi = "10.1088/0967-3334/25/4/012",
language = "English",
volume = "25",
pages = "935--944",
journal = "Physiological Measurement",
issn = "0967-3334",
publisher = "IOP Publishing Ltd.",
number = "4",

}

TY - JOUR

T1 - Time-frequency based newborn EEG seizure detection using low and high frequency signatures

AU - Hassanpour, Hamid

AU - Mesbah, Mostefa

AU - Boashash, Boualem

PY - 2004/8

Y1 - 2004/8

N2 - The nonstationary and multicomponent nature of newborn EEG seizures tend to increase the complexity of the seizure detection problem. In dealing with this type of problem, time-frequency based techniques were shown to outperform classical techniques. Neonatal EEG seizures have signatures in both low frequency (lower than 10 Hz) and high frequency (higher than 70 Hz) areas. Seizure detection techniques have been proposed that concentrate on either low frequency or high frequency signatures of seizures. They, however, tend to miss seizures that reveal themselves only in one of the frequency areas. To overcome this problem, we propose a detection method that uses time-frequency seizure features extracted from both low and high frequency areas. Results of applying the proposed method on five newborn EEGs are very encouraging.

AB - The nonstationary and multicomponent nature of newborn EEG seizures tend to increase the complexity of the seizure detection problem. In dealing with this type of problem, time-frequency based techniques were shown to outperform classical techniques. Neonatal EEG seizures have signatures in both low frequency (lower than 10 Hz) and high frequency (higher than 70 Hz) areas. Seizure detection techniques have been proposed that concentrate on either low frequency or high frequency signatures of seizures. They, however, tend to miss seizures that reveal themselves only in one of the frequency areas. To overcome this problem, we propose a detection method that uses time-frequency seizure features extracted from both low and high frequency areas. Results of applying the proposed method on five newborn EEGs are very encouraging.

KW - EEG seizure detection

KW - Singular vector

KW - Spike detection

KW - Time-frequency

UR - http://www.scopus.com/inward/record.url?scp=4344636860&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4344636860&partnerID=8YFLogxK

U2 - 10.1088/0967-3334/25/4/012

DO - 10.1088/0967-3334/25/4/012

M3 - Article

C2 - 15382832

AN - SCOPUS:4344636860

VL - 25

SP - 935

EP - 944

JO - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 4

ER -