Quadratic time-frequency distribution selection for seizure detection in the newborn

N. Stevenson, M. Mesbah, B. Boashash

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

7 Citations (Scopus)

Abstract

Several, recently proposed, newborn EEG seizure detection techniques use quadratic time-frequency distributions (QTFDs) to generate the time-frequency representations (TFRs) at their core. The specific type of QTFD that provides the best discrimination between the TFR of nonseizure and seizure epochs of EEG, however, has yet to be thoroughly investigated. This paper proposes the selection of an optimal QTFD that maximises the the absolute error between seizure and nonseizure QTFDs calculated on a database of newborn EEG. The optimisation procedure is a data driven process that selects the optimal QTFD based on the distribution of the absolute error between nonseizure/nonseizure QTFDs and the seizure/nonseizure QTFDs. Several non-adaptive QTFDs were selected for comparison and those selected were subjected to a restriction on the kernel's volume to ensure that the QTFD can accurately represent the time-frequency distribution of signal energy. The results show that a lag independent or narrowband QTFD such as the modified B distribution provides a QTFD that best highlights the difference in time-frequency signal energy between newborn EEG seizure and nonseizure.

Original languageEnglish
Title of host publicationProceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
Pages923-926
Number of pages4
Publication statusPublished - 2008
Event30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 - Vancouver, BC, Canada
Duration: Aug 20 2008Aug 25 2008

Other

Other30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08
CountryCanada
CityVancouver, BC
Period8/20/088/25/08

Fingerprint

Electroencephalography
Seizures

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Cite this

Stevenson, N., Mesbah, M., & Boashash, B. (2008). Quadratic time-frequency distribution selection for seizure detection in the newborn. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08 (pp. 923-926). [4649305]

Quadratic time-frequency distribution selection for seizure detection in the newborn. / Stevenson, N.; Mesbah, M.; Boashash, B.

Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 923-926 4649305.

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

Stevenson, N, Mesbah, M & Boashash, B 2008, Quadratic time-frequency distribution selection for seizure detection in the newborn. in Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08., 4649305, pp. 923-926, 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08, Vancouver, BC, Canada, 8/20/08.
Stevenson N, Mesbah M, Boashash B. Quadratic time-frequency distribution selection for seizure detection in the newborn. In Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. p. 923-926. 4649305
Stevenson, N. ; Mesbah, M. ; Boashash, B. / Quadratic time-frequency distribution selection for seizure detection in the newborn. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08. 2008. pp. 923-926
@inproceedings{0de619db5ead497cb34c7d16647c7274,
title = "Quadratic time-frequency distribution selection for seizure detection in the newborn",
abstract = "Several, recently proposed, newborn EEG seizure detection techniques use quadratic time-frequency distributions (QTFDs) to generate the time-frequency representations (TFRs) at their core. The specific type of QTFD that provides the best discrimination between the TFR of nonseizure and seizure epochs of EEG, however, has yet to be thoroughly investigated. This paper proposes the selection of an optimal QTFD that maximises the the absolute error between seizure and nonseizure QTFDs calculated on a database of newborn EEG. The optimisation procedure is a data driven process that selects the optimal QTFD based on the distribution of the absolute error between nonseizure/nonseizure QTFDs and the seizure/nonseizure QTFDs. Several non-adaptive QTFDs were selected for comparison and those selected were subjected to a restriction on the kernel's volume to ensure that the QTFD can accurately represent the time-frequency distribution of signal energy. The results show that a lag independent or narrowband QTFD such as the modified B distribution provides a QTFD that best highlights the difference in time-frequency signal energy between newborn EEG seizure and nonseizure.",
author = "N. Stevenson and M. Mesbah and B. Boashash",
year = "2008",
language = "English",
isbn = "9781424418152",
pages = "923--926",
booktitle = "Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08",

}

TY - GEN

T1 - Quadratic time-frequency distribution selection for seizure detection in the newborn

AU - Stevenson, N.

AU - Mesbah, M.

AU - Boashash, B.

PY - 2008

Y1 - 2008

N2 - Several, recently proposed, newborn EEG seizure detection techniques use quadratic time-frequency distributions (QTFDs) to generate the time-frequency representations (TFRs) at their core. The specific type of QTFD that provides the best discrimination between the TFR of nonseizure and seizure epochs of EEG, however, has yet to be thoroughly investigated. This paper proposes the selection of an optimal QTFD that maximises the the absolute error between seizure and nonseizure QTFDs calculated on a database of newborn EEG. The optimisation procedure is a data driven process that selects the optimal QTFD based on the distribution of the absolute error between nonseizure/nonseizure QTFDs and the seizure/nonseizure QTFDs. Several non-adaptive QTFDs were selected for comparison and those selected were subjected to a restriction on the kernel's volume to ensure that the QTFD can accurately represent the time-frequency distribution of signal energy. The results show that a lag independent or narrowband QTFD such as the modified B distribution provides a QTFD that best highlights the difference in time-frequency signal energy between newborn EEG seizure and nonseizure.

AB - Several, recently proposed, newborn EEG seizure detection techniques use quadratic time-frequency distributions (QTFDs) to generate the time-frequency representations (TFRs) at their core. The specific type of QTFD that provides the best discrimination between the TFR of nonseizure and seizure epochs of EEG, however, has yet to be thoroughly investigated. This paper proposes the selection of an optimal QTFD that maximises the the absolute error between seizure and nonseizure QTFDs calculated on a database of newborn EEG. The optimisation procedure is a data driven process that selects the optimal QTFD based on the distribution of the absolute error between nonseizure/nonseizure QTFDs and the seizure/nonseizure QTFDs. Several non-adaptive QTFDs were selected for comparison and those selected were subjected to a restriction on the kernel's volume to ensure that the QTFD can accurately represent the time-frequency distribution of signal energy. The results show that a lag independent or narrowband QTFD such as the modified B distribution provides a QTFD that best highlights the difference in time-frequency signal energy between newborn EEG seizure and nonseizure.

UR - http://www.scopus.com/inward/record.url?scp=61849177957&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=61849177957&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781424418152

SP - 923

EP - 926

BT - Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS'08

ER -