Performance Analysis of A Feed-Forward Artifical Neural Network With Small-World Topology

Basit Öğe Kaydı
dc.authoridERKAYMAZ, OKAN/0000-0002-1996-8623
dc.contributor.authorErkaymaz, Okan
dc.contributor.authorOzer, Mahmut
dc.contributor.authorYumusak, Nejat
dc.date.accessioned2024-09-29T16:00:37Z
dc.date.available2024-09-29T16:00:37Z
dc.date.issued2012
dc.departmentKarabük Üniversitesien_US
dc.description1st World Conference on Innovation and Software Development (INSODE) -- OCT 02-10, 2011 -- Bahcesehir Univ, Istanbul, TURKEYen_US
dc.description.abstractFeed Forward Artificial Neural Networks are the most widely used models to explain the information processing mechanism of the brain. Network topology plays a key role in the performance of the feed forward neural networks. Recently, the small-world network topology has been shown to meet the properties of the real life networks. Therefore, in this study, we consider a feed forward artificial neural network with small-world topology and analyze its performance on classifying the epilepsy. In order to obtain the small-world network, we follow the Watts-Strogatz approach. An EEG dataset taken from healthy and epileptic patients is used to test the performance of the network. We also consider different numbers of neurons in each layer of the network. By comparing the performance of small-world and regular feed forward artificial neural networks, it is shown that the Watts-Strogatz small-world network topology improves the learning performance and decreases the training time. To our knowledge, this is the first attempt to use small-world topology in a feed forward artificial neural network to classify the epileptic case.en_US
dc.identifier.doi10.1016/j.protcy.2012.02.062
dc.identifier.endpage296en_US
dc.identifier.issn2212-0173
dc.identifier.startpage291en_US
dc.identifier.urihttps://doi.org/10.1016/j.protcy.2012.02.062
dc.identifier.urihttps://hdl.handle.net/20.500.14619/5242
dc.identifier.volume1en_US
dc.identifier.wosWOS:000318909900049en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.language.isoenen_US
dc.publisherElsevier Science Bven_US
dc.relation.ispartofFirst World Conference On Innovation and Computer Sciences (Insode 2011)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectFeed Forward Neural Networksen_US
dc.subjectSmall-World Networksen_US
dc.subjectWatts-Strogatz Small-World Networken_US
dc.subjectEEG-Epilepsyen_US
dc.titlePerformance Analysis of A Feed-Forward Artifical Neural Network With Small-World Topologyen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu