An optimal feature set for seizure detection systems for newborn EEG signals

QSpace/Manakin Repository

An optimal feature set for seizure detection systems for newborn EEG signals

Show simple item record


dc.contributor.author Zarjam, P
dc.contributor.author Mesbah, M
dc.contributor.author Boashash, B
dc.date.accessioned 2011-07-30T06:20:26Z
dc.date.available 2011-07-30T06:20:26Z
dc.date.issued 2003-05
dc.identifier.citation ISCAS'03, vol:5, pages:v-33-v-36 en_US
dc.identifier.isbn 0-7803-7761-3
dc.identifier.other Digital Object Identifier : 10.1109/ISCAS.2003.1206166
dc.identifier.uri http://hdl.handle.net/10576/10729
dc.description This paper uses mutual information feature selection and DWT to detect EEG new-born seizures. (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 A novel automated method is applied to Electroencephalogram (EEG) data to detect seizure events in newborns. The detection scheme is based on observing the changing behavior of the wavelet coefficients (WCs) of the EEG signal at different scales. An optimizing technique based on mutual information feature selection (MIFS) is employed. This technique evaluates a set of candidate features extracted from the WCs to select an informative subset. This subset is used as an input to an artificial neural network (ANN) classifier. The classifier organizes the EEG signal into seizure or non-seizure activities. The training and test sets are obtained from EEG data acquired from 1 and 5 other neonates, respectively, with ages ranging from 2 days to 2 weeks. The optimized results show an average seizure detection rate of 94%. en_US
dc.language.iso en en_US
dc.publisher IEEE en_US
dc.subject Artificial neural network classifier en_US
dc.subject automated method en_US
dc.subject average seizure detection rate en_US
dc.subject detection scheme en_US
dc.subject electroencephalogram data en_US
dc.subject informative en_US
dc.subject mutual information feature selection en_US
dc.subject newborn electroencephalogram signals en_US
dc.subject non-seizure activities en_US
dc.subject optimizing technique en_US
dc.subject seizure activities en_US
dc.subject seizure events en_US
dc.subject test sets en_US
dc.subject training sets en_US
dc.subject wavelet coefficients en_US
dc.subject DWT en_US
dc.subject Time-scale analysis en_US
dc.subject time-frequency analysis en_US
dc.subject non-stationarity en_US
dc.title An optimal feature set for seizure detection systems for newborn EEG signals en_US
dc.type Article en_US

Files in this item

Files Size Format View
Boashash-Zarjam ... MIFS-seizure-detection.pdf 244.4Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search QSpace


Advanced Search

Browse

My Account