Classification of EEG Data Sets with Hilbert Transform

dc.contributor.authorSeker, Mesut
dc.contributor.authorÖzerdem, Mehmet Sirac
dc.date.accessioned2024-04-24T17:33:20Z
dc.date.available2024-04-24T17:33:20Z
dc.date.issued2016
dc.departmentDicle Üniversitesien_US
dc.description24th Signal Processing and Communication Application Conference (SIU) -- MAY 16-19, 2016 -- Zonguldak, TURKEYen_US
dc.description.abstractElectroencephalographic (EEG) records which are related to the electrical activity of the brain are one of the most useful tools which are used in diagnosis of neurologic diseases. The aim of this study was to classify different sets of EEG signals by using Hilbert transform and artificial neural networks (ANN). The EEG data used in this study has been acquired from database of Epileptology Department of Bonn University. The database constitutes of five data sets, namely A, B, C, D and E. Besides, each data set has a difference due to healthy/ epileptic subject, eyes open/ closed, the position of electrode, seizure-free or seizure activity. A-B, A-E, C-D and A-B-E signal groups are classified with each other. For classification, magnitude and phase difference components obtained with Hilbert transform were used. To get the different frequency (theta (4-7Hz), alpha (8-13Hz), beta (12-38Hz), all (0.5-40Hz)) band, the signal filtered with band pass filter. The classification result of phase difference is higher than the amplitude based result. The highest performances of data sets are; 100% for A-B (phase difference, 0.5-40Hz, 7x30x2 network structure), 99.93% for A-E (phase difference, theta band, 7x75x2 network structure), 99.68% for C-D (phase difference, 0.540Hz, 7x30x2 network structure) and 97.72% for A-B-E (phase difference, theta, 7x20x3 network structure).en_US
dc.description.sponsorshipIEEE,Bulent Ecevit Univ, Dept Elect & Elect Engn,Bulent Ecevit Univ, Dept Biomed Engn,Bulent Ecevit Univ, Dept Comp Engnen_US
dc.identifier.endpage1952en_US
dc.identifier.isbn978-1-5090-1679-2
dc.identifier.scopus2-s2.0-84982803669
dc.identifier.scopusqualityN/A
dc.identifier.startpage1949en_US
dc.identifier.urihttps://hdl.handle.net/11468/20629
dc.identifier.wosWOS:000391250900464
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isotren_US
dc.publisherIeeeen_US
dc.relation.ispartof2016 24th Signal Processing and Communication Application Conference (Siu)
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectEegen_US
dc.subjectClassificationen_US
dc.subjectHilbert Transformen_US
dc.subjectAnnen_US
dc.titleClassification of EEG Data Sets with Hilbert Transformen_US
dc.titleClassification of EEG Data Sets with Hilbert Transform
dc.typeConference Objecten_US

Dosyalar