A Gaussian mixture model based statistical classification system for neonatal seizure detection

Eoin M. Thomas; Andriy Temko; Gordon Lightbody; William P. Marnane; Geraldine B. Boylan

doi:10.1109/MLSP.2009.5306203

A Gaussian mixture model based statistical classification system for neonatal seizure detection

Eoin M. Thomas
, Andriy Temko
, Gordon Lightbody
, William P. Marnane
, Geraldine B. Boylan

University College Cork

Research output: Chapter in Book/Report/Conference proceedings › Chapter › peer-review

Abstract

A neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. Linear discriminant analysis and principal component analysis are compared for the task of feature vector preprocessing. A postprocessing scheme is developed from the probability of seizure estimate in order to improve the performance of the system. Results are reported on a dataset of 17 patients with a total duration of 267.9 hours, the average ROC area of the system is 95.6%.

Original language	English
Title of host publication	Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009
DOIs	https://doi.org/10.1109/MLSP.2009.5306203
Publication status	Published - 2009
Event	Machine Learning for Signal Processing XIX - 2009 IEEE Signal Processing Society Workshop, MLSP 2009 - Grenoble, France Duration: 2 Sep 2009 → 4 Sep 2009

Publication series

Name	Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009

Conference

Conference	Machine Learning for Signal Processing XIX - 2009 IEEE Signal Processing Society Workshop, MLSP 2009
Country/Territory	France
City	Grenoble
Period	2/09/09 → 4/09/09

Keywords

Gaussian mixture models
Linear discriminant analysis
Neonatal seizure detection
Principal component analysis

Access to Document

10.1109/MLSP.2009.5306203

Cite this

Thomas, E. M., Temko, A., Lightbody, G., Marnane, W. P., & Boylan, G. B. (2009). A Gaussian mixture model based statistical classification system for neonatal seizure detection. In Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009 Article 5306203 (Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009). https://doi.org/10.1109/MLSP.2009.5306203

Thomas, Eoin M. ; Temko, Andriy ; Lightbody, Gordon et al. / A Gaussian mixture model based statistical classification system for neonatal seizure detection. Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009. 2009. (Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009).

@inbook{a3e72e85a4ba4187abe4ec6460189867,

title = "A Gaussian mixture model based statistical classification system for neonatal seizure detection",

abstract = "A neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. Linear discriminant analysis and principal component analysis are compared for the task of feature vector preprocessing. A postprocessing scheme is developed from the probability of seizure estimate in order to improve the performance of the system. Results are reported on a dataset of 17 patients with a total duration of 267.9 hours, the average ROC area of the system is 95.6\%.",

keywords = "Gaussian mixture models, Linear discriminant analysis, Neonatal seizure detection, Principal component analysis",

author = "Thomas, \{Eoin M.\} and Andriy Temko and Gordon Lightbody and Marnane, \{William P.\} and Boylan, \{Geraldine B.\}",

year = "2009",

doi = "10.1109/MLSP.2009.5306203",

language = "English",

isbn = "9781424449484",

series = "Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009",

booktitle = "Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009",

note = "Machine Learning for Signal Processing XIX - 2009 IEEE Signal Processing Society Workshop, MLSP 2009 ; Conference date: 02-09-2009 Through 04-09-2009",

}

Thomas, EM, Temko, A, Lightbody, G , Marnane, WP & Boylan, GB 2009, A Gaussian mixture model based statistical classification system for neonatal seizure detection. in Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009., 5306203, Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009, Machine Learning for Signal Processing XIX - 2009 IEEE Signal Processing Society Workshop, MLSP 2009, Grenoble, France, 2/09/09. https://doi.org/10.1109/MLSP.2009.5306203

A Gaussian mixture model based statistical classification system for neonatal seizure detection. / Thomas, Eoin M.; Temko, Andriy; Lightbody, Gordon et al.
Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009. 2009. 5306203 (Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009).

Research output: Chapter in Book/Report/Conference proceedings › Chapter › peer-review

TY - CHAP

T1 - A Gaussian mixture model based statistical classification system for neonatal seizure detection

AU - Thomas, Eoin M.

AU - Temko, Andriy

AU - Lightbody, Gordon

AU - Marnane, William P.

AU - Boylan, Geraldine B.

PY - 2009

Y1 - 2009

N2 - A neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. Linear discriminant analysis and principal component analysis are compared for the task of feature vector preprocessing. A postprocessing scheme is developed from the probability of seizure estimate in order to improve the performance of the system. Results are reported on a dataset of 17 patients with a total duration of 267.9 hours, the average ROC area of the system is 95.6%.

AB - A neonatal seizure detection system is proposed based on a Gaussian mixture model classifier. Linear discriminant analysis and principal component analysis are compared for the task of feature vector preprocessing. A postprocessing scheme is developed from the probability of seizure estimate in order to improve the performance of the system. Results are reported on a dataset of 17 patients with a total duration of 267.9 hours, the average ROC area of the system is 95.6%.

KW - Gaussian mixture models

KW - Linear discriminant analysis

KW - Neonatal seizure detection

KW - Principal component analysis

UR - https://www.scopus.com/pages/publications/77950948400

U2 - 10.1109/MLSP.2009.5306203

DO - 10.1109/MLSP.2009.5306203

M3 - Chapter

AN - SCOPUS:77950948400

SN - 9781424449484

T3 - Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009

BT - Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009

T2 - Machine Learning for Signal Processing XIX - 2009 IEEE Signal Processing Society Workshop, MLSP 2009

Y2 - 2 September 2009 through 4 September 2009

ER -

Thomas EM, Temko A, Lightbody G , Marnane WP , Boylan GB. A Gaussian mixture model based statistical classification system for neonatal seizure detection. In Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009. 2009. 5306203. (Machine Learning for Signal Processing XIX - Proceedings of the 2009 IEEE Signal Processing Society Workshop, MLSP 2009). doi: 10.1109/MLSP.2009.5306203

A Gaussian mixture model based statistical classification system for neonatal seizure detection

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this