Correlation analysis of seizure detection features

L. Kuhlmann; M. J. Cook; K. Fuller; D. B. Grayden; A. N. Burkitt; I. M Y Mareels

doi:10.1109/ISSNIP.2008.4762005

Correlation analysis of seizure detection features

L. Kuhlmann, M. J. Cook, K. Fuller, D. B. Grayden, A. N. Burkitt, I. M Y Mareels

Department of Data Science & AI

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

10 Citations (Scopus)

Abstract

Automated seizure detection is important for speeding up epilepsy diagnosis or for controlling an implantable brain stimulator to avert seizures. Various features calculated from the electroencephalogram (EEG) can be used to detect seizures, and combining features can give superior detection performance. This paper investigates the correlation between seizure detection features in order to determine which ones should be combined for the purposes of seizure detection. Combinations of three features involving relative average amplitude, relative scale energy, coefficient of variation of amplitude, relative power, relative gradient and bounded variation tended to show the lowest correlations.

Original language	English
Title of host publication	ISSNIP 2008 - Proceedings of the 2008 International Conference on Intelligent Sensors, Sensor Networks and Information Processing
Pages	309-314
Number of pages	6
DOIs	https://doi.org/10.1109/ISSNIP.2008.4762005
Publication status	Published - 1 Dec 2008
Event	International Conference on Intelligent Sensors, Sensor Networks and Information Processing 2008 - Sydney, Australia Duration: 15 Dec 2008 → 18 Dec 2008 Conference number: 4th https://ieeexplore.ieee.org/xpl/conhome/4752632/proceeding (Proceedings)

Conference

Conference	International Conference on Intelligent Sensors, Sensor Networks and Information Processing 2008
Abbreviated title	ISSNIP 2008
Country/Territory	Australia
City	Sydney
Period	15/12/08 → 18/12/08
Internet address	https://ieeexplore.ieee.org/xpl/conhome/4752632/proceeding (Proceedings)

Access to Document

10.1109/ISSNIP.2008.4762005

Cite this

@inproceedings{9be0383e5687454980074a42b782812e,

title = "Correlation analysis of seizure detection features",

abstract = "Automated seizure detection is important for speeding up epilepsy diagnosis or for controlling an implantable brain stimulator to avert seizures. Various features calculated from the electroencephalogram (EEG) can be used to detect seizures, and combining features can give superior detection performance. This paper investigates the correlation between seizure detection features in order to determine which ones should be combined for the purposes of seizure detection. Combinations of three features involving relative average amplitude, relative scale energy, coefficient of variation of amplitude, relative power, relative gradient and bounded variation tended to show the lowest correlations.",

author = "L. Kuhlmann and Cook, {M. J.} and K. Fuller and Grayden, {D. B.} and Burkitt, {A. N.} and Mareels, {I. M Y}",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/ISSNIP.2008.4762005",

language = "English",

isbn = "9781424429578",

pages = "309--314",

booktitle = "ISSNIP 2008 - Proceedings of the 2008 International Conference on Intelligent Sensors, Sensor Networks and Information Processing",

note = "International Conference on Intelligent Sensors, Sensor Networks and Information Processing 2008, ISSNIP 2008 ; Conference date: 15-12-2008 Through 18-12-2008",

url = "https://ieeexplore.ieee.org/xpl/conhome/4752632/proceeding",

}

Kuhlmann, L, Cook, MJ, Fuller, K, Grayden, DB, Burkitt, AN & Mareels, IMY 2008, Correlation analysis of seizure detection features. in ISSNIP 2008 - Proceedings of the 2008 International Conference on Intelligent Sensors, Sensor Networks and Information Processing. pp. 309-314, International Conference on Intelligent Sensors, Sensor Networks and Information Processing 2008, Sydney, New South Wales, Australia, 15/12/08. https://doi.org/10.1109/ISSNIP.2008.4762005

TY - GEN

T1 - Correlation analysis of seizure detection features

AU - Kuhlmann, L.

AU - Cook, M. J.

AU - Fuller, K.

AU - Grayden, D. B.

AU - Burkitt, A. N.

AU - Mareels, I. M Y

N1 - Conference code: 4th

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Automated seizure detection is important for speeding up epilepsy diagnosis or for controlling an implantable brain stimulator to avert seizures. Various features calculated from the electroencephalogram (EEG) can be used to detect seizures, and combining features can give superior detection performance. This paper investigates the correlation between seizure detection features in order to determine which ones should be combined for the purposes of seizure detection. Combinations of three features involving relative average amplitude, relative scale energy, coefficient of variation of amplitude, relative power, relative gradient and bounded variation tended to show the lowest correlations.

AB - Automated seizure detection is important for speeding up epilepsy diagnosis or for controlling an implantable brain stimulator to avert seizures. Various features calculated from the electroencephalogram (EEG) can be used to detect seizures, and combining features can give superior detection performance. This paper investigates the correlation between seizure detection features in order to determine which ones should be combined for the purposes of seizure detection. Combinations of three features involving relative average amplitude, relative scale energy, coefficient of variation of amplitude, relative power, relative gradient and bounded variation tended to show the lowest correlations.

UR - http://www.scopus.com/inward/record.url?scp=63149112147&partnerID=8YFLogxK

U2 - 10.1109/ISSNIP.2008.4762005

DO - 10.1109/ISSNIP.2008.4762005

M3 - Conference Paper

AN - SCOPUS:63149112147

SN - 9781424429578

SP - 309

EP - 314

BT - ISSNIP 2008 - Proceedings of the 2008 International Conference on Intelligent Sensors, Sensor Networks and Information Processing

T2 - International Conference on Intelligent Sensors, Sensor Networks and Information Processing 2008

Y2 - 15 December 2008 through 18 December 2008

ER -

Correlation analysis of seizure detection features

Abstract

Conference

Access to Document

Other files and links

Cite this