Hidden pattern discovery on epileptic EEG with 1-D local binary patterns and epileptic seizures detection by grey relational analysis

Basit Öğe Kaydı
dc.contributor.authorKaya, Yilmaz
dc.date.accessioned2024-12-24T19:25:04Z
dc.date.available2024-12-24T19:25:04Z
dc.date.issued2015
dc.departmentSiirt Üniversitesi
dc.description.abstractThis paper proposes a novel approach to detect epilepsy seizures by using Electroencephalography (EEG), which is one of the most common methods for the diagnosis of epilepsy, based on 1-Dimension Local Binary Pattern (1D-LBP) and grey relational analysis (GRA) methods. The main aim of this paper is to evaluate and validate a novel approach, which is a computer-based quantitative EEG analyzing method and based on grey systems, aimed to help decision-maker. In this study, 1D-LBP, which utilizes all data points, was employed for extracting features in raw EEG signals, Fisher score (FS) was employed to select the representative features, which can also be determined as hidden patterns. Additionally, GRA is performed to classify EEG signals through these Fisher scored features. The experimental results of the proposed approach, which was employed in a public dataset for validation, showed that it has a high accuracy in identifying epileptic EEG signals. For various combinations of epileptic EEG, such as A-E, B-E, C-E, D-E, and A-D clusters, 100, 96, 100, 99.00 and 100 % were achieved, respectively. Also, this work presents an attempt to develop a new general-purpose hidden pattern determination scheme, which can be utilized for different categories of time-varying signals.
dc.identifier.doi10.1007/s13246-015-0362-5
dc.identifier.endpage446
dc.identifier.issn0158-9938
dc.identifier.issn1879-5447
dc.identifier.issue3
dc.identifier.pmid26206400
dc.identifier.scopus2-s2.0-84942372108
dc.identifier.scopusqualityN/A
dc.identifier.startpage435
dc.identifier.urihttps://doi.org/10.1007/s13246-015-0362-5
dc.identifier.urihttps://hdl.handle.net/20.500.12604/6233
dc.identifier.volume38
dc.identifier.wosWOS:000361762700006
dc.identifier.wosqualityQ4
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherSpringer
dc.relation.ispartofAustralasian Physical & Engineering Sciences in Medicine
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241222
dc.subjectLocal binary patterns
dc.subjectEEG
dc.subjectHidden patterns
dc.subjectFeature extraction
dc.subjectGrey relational analysis
dc.titleHidden pattern discovery on epileptic EEG with 1-D local binary patterns and epileptic seizures detection by grey relational analysis
dc.typeArticle

Dosyalar

Koleksiyon

WOS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayın Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu