A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram

John M. O'Toole, Mostefa Mesbah, Boualem Boashash, Paul Coldiiz

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

3 Citations (Scopus)

Abstract

The electroencephalogram (EEG) is an important tool in determining the presence or absence of clinical seizures in neonates. The design of an efficient automated EEG seizure detection method suitable for use in the clinical environment would be beneficial. Existing methods include a time-frequency (TF) matched filter approach, which correlates TF seizure templates with time-frequency distributions (TFDs) of the EEG to detect seizure. A major problem with this method is the pre-selection of a template set that adequately represents all different TFD seizure types. To overcome this problem, a new method is proposed that applies the TF matched filter but eliminates the need for a predefined template set. Preliminary results are presented for both real and simulated EEG data.

Original languageEnglish
Title of host publication2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings
DOIs
Publication statusPublished - 2007
Event2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007 - Sharjah, United Arab Emirates
Duration: Feb 12 2007Feb 15 2007

Other

Other2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007
CountryUnited Arab Emirates
CitySharjah
Period2/12/072/15/07

Fingerprint

Electroencephalography
Matched filters

ASJC Scopus subject areas

  • Signal Processing

Cite this

O'Toole, J. M., Mesbah, M., Boashash, B., & Coldiiz, P. (2007). A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram. In 2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings [4555347] https://doi.org/10.1109/ISSPA.2007.4555347

A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram. / O'Toole, John M.; Mesbah, Mostefa; Boashash, Boualem; Coldiiz, Paul.

2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings. 2007. 4555347.

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

O'Toole, JM, Mesbah, M, Boashash, B & Coldiiz, P 2007, A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram. in 2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings., 4555347, 2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Sharjah, United Arab Emirates, 2/12/07. https://doi.org/10.1109/ISSPA.2007.4555347
O'Toole JM, Mesbah M, Boashash B, Coldiiz P. A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram. In 2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings. 2007. 4555347 https://doi.org/10.1109/ISSPA.2007.4555347
O'Toole, John M. ; Mesbah, Mostefa ; Boashash, Boualem ; Coldiiz, Paul. / A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram. 2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings. 2007.
@inproceedings{d498417fe72c4f1897e0787799e36609,
title = "A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram",
abstract = "The electroencephalogram (EEG) is an important tool in determining the presence or absence of clinical seizures in neonates. The design of an efficient automated EEG seizure detection method suitable for use in the clinical environment would be beneficial. Existing methods include a time-frequency (TF) matched filter approach, which correlates TF seizure templates with time-frequency distributions (TFDs) of the EEG to detect seizure. A major problem with this method is the pre-selection of a template set that adequately represents all different TFD seizure types. To overcome this problem, a new method is proposed that applies the TF matched filter but eliminates the need for a predefined template set. Preliminary results are presented for both real and simulated EEG data.",
author = "O'Toole, {John M.} and Mostefa Mesbah and Boualem Boashash and Paul Coldiiz",
year = "2007",
doi = "10.1109/ISSPA.2007.4555347",
language = "English",
isbn = "1424407796",
booktitle = "2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings",

}

TY - GEN

T1 - A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram

AU - O'Toole, John M.

AU - Mesbah, Mostefa

AU - Boashash, Boualem

AU - Coldiiz, Paul

PY - 2007

Y1 - 2007

N2 - The electroencephalogram (EEG) is an important tool in determining the presence or absence of clinical seizures in neonates. The design of an efficient automated EEG seizure detection method suitable for use in the clinical environment would be beneficial. Existing methods include a time-frequency (TF) matched filter approach, which correlates TF seizure templates with time-frequency distributions (TFDs) of the EEG to detect seizure. A major problem with this method is the pre-selection of a template set that adequately represents all different TFD seizure types. To overcome this problem, a new method is proposed that applies the TF matched filter but eliminates the need for a predefined template set. Preliminary results are presented for both real and simulated EEG data.

AB - The electroencephalogram (EEG) is an important tool in determining the presence or absence of clinical seizures in neonates. The design of an efficient automated EEG seizure detection method suitable for use in the clinical environment would be beneficial. Existing methods include a time-frequency (TF) matched filter approach, which correlates TF seizure templates with time-frequency distributions (TFDs) of the EEG to detect seizure. A major problem with this method is the pre-selection of a template set that adequately represents all different TFD seizure types. To overcome this problem, a new method is proposed that applies the TF matched filter but eliminates the need for a predefined template set. Preliminary results are presented for both real and simulated EEG data.

UR - http://www.scopus.com/inward/record.url?scp=51549116778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51549116778&partnerID=8YFLogxK

U2 - 10.1109/ISSPA.2007.4555347

DO - 10.1109/ISSPA.2007.4555347

M3 - Conference contribution

SN - 1424407796

SN - 9781424407798

BT - 2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings

ER -