Neonatal EEG seizure detection using a time-frequency matched filter with a reduced template set

John O'Toole, Mostefa Mesbah, Boualem Boashash

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Electroencephalographic (EEG) recordings are an important diagnostic resource in determining the presence or absence of clinical seizures in neonates. These nonstationary signals require some form of nonstationary analysis to detect seizures in the EEG data. A time-frequency (TF) matched filter has been previously proposed to detect seizures in both adult and newborn EEG. A method which constructs a reference or template set from a feature of EEG seizures, rather than the whole EEG seizure, displayed the most promising results. However this method suffered from an inability to adequately represent patient variability in the template set while simultaneously maintaining a low false detection rate. A new method of the TF matched filter is proposed that halves the template set required by approximating the templates with a more general ambiguity domain function representation. This proposed method is also less sensitive to false detections when a larger reference set is used, as evidenced by the findings on both simulated and real neonatal EEG.

Original languageEnglish
Title of host publicationProceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005
Pages215-218
Number of pages4
Volume1
DOIs
Publication statusPublished - 2005
Event8th International Symposium on Signal Processing and its Applications, ISSPA 2005 - Sydney, Australia
Duration: Aug 28 2005Aug 31 2005

Other

Other8th International Symposium on Signal Processing and its Applications, ISSPA 2005
CountryAustralia
CitySydney
Period8/28/058/31/05

Fingerprint

Matched filters

ASJC Scopus subject areas

  • Engineering(all)

Cite this

O'Toole, J., Mesbah, M., & Boashash, B. (2005). Neonatal EEG seizure detection using a time-frequency matched filter with a reduced template set. In Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005 (Vol. 1, pp. 215-218). [1580234] https://doi.org/10.1109/ISSPA.2005.1580234

Neonatal EEG seizure detection using a time-frequency matched filter with a reduced template set. / O'Toole, John; Mesbah, Mostefa; Boashash, Boualem.

Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005. Vol. 1 2005. p. 215-218 1580234.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

O'Toole, J, Mesbah, M & Boashash, B 2005, Neonatal EEG seizure detection using a time-frequency matched filter with a reduced template set. in Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005. vol. 1, 1580234, pp. 215-218, 8th International Symposium on Signal Processing and its Applications, ISSPA 2005, Sydney, Australia, 8/28/05. https://doi.org/10.1109/ISSPA.2005.1580234
O'Toole J, Mesbah M, Boashash B. Neonatal EEG seizure detection using a time-frequency matched filter with a reduced template set. In Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005. Vol. 1. 2005. p. 215-218. 1580234 https://doi.org/10.1109/ISSPA.2005.1580234
O'Toole, John ; Mesbah, Mostefa ; Boashash, Boualem. / Neonatal EEG seizure detection using a time-frequency matched filter with a reduced template set. Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005. Vol. 1 2005. pp. 215-218
@inproceedings{91f11535d92249d7be7797caa18aab72,
title = "Neonatal EEG seizure detection using a time-frequency matched filter with a reduced template set",
abstract = "Electroencephalographic (EEG) recordings are an important diagnostic resource in determining the presence or absence of clinical seizures in neonates. These nonstationary signals require some form of nonstationary analysis to detect seizures in the EEG data. A time-frequency (TF) matched filter has been previously proposed to detect seizures in both adult and newborn EEG. A method which constructs a reference or template set from a feature of EEG seizures, rather than the whole EEG seizure, displayed the most promising results. However this method suffered from an inability to adequately represent patient variability in the template set while simultaneously maintaining a low false detection rate. A new method of the TF matched filter is proposed that halves the template set required by approximating the templates with a more general ambiguity domain function representation. This proposed method is also less sensitive to false detections when a larger reference set is used, as evidenced by the findings on both simulated and real neonatal EEG.",
author = "John O'Toole and Mostefa Mesbah and Boualem Boashash",
year = "2005",
doi = "10.1109/ISSPA.2005.1580234",
language = "English",
isbn = "0780392434",
volume = "1",
pages = "215--218",
booktitle = "Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005",

}

TY - GEN

T1 - Neonatal EEG seizure detection using a time-frequency matched filter with a reduced template set

AU - O'Toole, John

AU - Mesbah, Mostefa

AU - Boashash, Boualem

PY - 2005

Y1 - 2005

N2 - Electroencephalographic (EEG) recordings are an important diagnostic resource in determining the presence or absence of clinical seizures in neonates. These nonstationary signals require some form of nonstationary analysis to detect seizures in the EEG data. A time-frequency (TF) matched filter has been previously proposed to detect seizures in both adult and newborn EEG. A method which constructs a reference or template set from a feature of EEG seizures, rather than the whole EEG seizure, displayed the most promising results. However this method suffered from an inability to adequately represent patient variability in the template set while simultaneously maintaining a low false detection rate. A new method of the TF matched filter is proposed that halves the template set required by approximating the templates with a more general ambiguity domain function representation. This proposed method is also less sensitive to false detections when a larger reference set is used, as evidenced by the findings on both simulated and real neonatal EEG.

AB - Electroencephalographic (EEG) recordings are an important diagnostic resource in determining the presence or absence of clinical seizures in neonates. These nonstationary signals require some form of nonstationary analysis to detect seizures in the EEG data. A time-frequency (TF) matched filter has been previously proposed to detect seizures in both adult and newborn EEG. A method which constructs a reference or template set from a feature of EEG seizures, rather than the whole EEG seizure, displayed the most promising results. However this method suffered from an inability to adequately represent patient variability in the template set while simultaneously maintaining a low false detection rate. A new method of the TF matched filter is proposed that halves the template set required by approximating the templates with a more general ambiguity domain function representation. This proposed method is also less sensitive to false detections when a larger reference set is used, as evidenced by the findings on both simulated and real neonatal EEG.

UR - http://www.scopus.com/inward/record.url?scp=33847166189&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847166189&partnerID=8YFLogxK

U2 - 10.1109/ISSPA.2005.1580234

DO - 10.1109/ISSPA.2005.1580234

M3 - Conference contribution

AN - SCOPUS:33847166189

SN - 0780392434

SN - 9780780392434

VL - 1

SP - 215

EP - 218

BT - Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005

ER -