Seizure detection in newborns’ EEG signals using time-scale analysis

QSpace/Manakin Repository

Seizure detection in newborns’ EEG signals using time-scale analysis

Show simple item record


dc.contributor.author Zarjam, P
dc.contributor.author Mesbah, M
dc.contributor.author Boashash, B
dc.date.accessioned 2012-02-15T06:11:14Z
dc.date.available 2012-02-15T06:11:14Z
dc.date.issued 2006-01
dc.identifier.citation GESTS International Transactions on Computer Science and Engineering, Vol. 27, No.01, pp. 7-14 en_US
dc.identifier.issn 1738-6438
dc.identifier.uri http://hdl.handle.net/10576/10783
dc.description This paper proposes an algorithm for automatic seizure detection based on the DWT characteristics of the EEG newborns, using a feature vector to discriminate between seizure and non-seizure. (Additional details can be found in the comprehensive book on Time-Frequency Signal Analysis and Processing (see http://www.elsevier.com/locate/isbn/0080443354). In addition, the most recent upgrade of the original software package that calculates Time-Frequency Distributions and Instantaneous Frequency estimators can be downloaded from the web site: www.time-frequency.net. This was the first software developed in the field, and it was first released publicly in 1987 at the 1st ISSPA conference held in Brisbane, Australia, and then continuously updated). en_US
dc.description.abstract The discrete wavelet transform (DWT) has proven one of the most suitable tools for analyzing non-stationary signals such as EEGs. In this paper, a novel automated method for detecting seizures in the newborns using the DWT of the EEG signals is proposed. The detection scheme is based on observing the changing behavior of the statistical quantities of the wavelet coefficients (WCs) of the EEGs at various scales. The used statistical quantities of the EEGs are: the number of zero-crossings, the average distance between zero-crossings of the adjacent WCs, the number of extrema, and the average distance between extrema of the adjacent WCs of certain scales. These statistics form a feature set of size 8 for each EEG segment of 6 seconds length. The extracted feature set is then fed to an artificial neural network (ANN) classifier to organize the EEG signals into seizure and nonseizure activities. The study population consists of 6 neonates’ EEGs, with ages ranging from 2 days to 2 weeks. The obtained results show the high performance of the selected feature set by the average seizure detection rate of 95%. en_US
dc.language.iso en en_US
dc.publisher Global Engineering, Science and Technology Society (GESTS) en_US
dc.subject Newborn EEG seizure detection en_US
dc.subject DWT en_US
dc.subject Discrete Wavelet Transform en_US
dc.subject ANN en_US
dc.subject Artificial Neural Network en_US
dc.subject time-scale analysis en_US
dc.subject Seizure detection en_US
dc.subject feature selection en_US
dc.subject feature characterization en_US
dc.title Seizure detection in newborns’ EEG signals using time-scale analysis en_US
dc.type Article en_US

Files in this item

Files Size Format View
Boashash-Zarjam ... n-newborns-EEG signals.pdf 117.9Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search QSpace


Advanced Search

Browse

My Account