DATA CLUSTERING BASED ON FUZZY C-MEANS AND CHAOTIC WHALE OPTIMIZATION ALGORITHMS

Basit Öğe Kaydı
dc.contributor.authorArslan, Hatice
dc.contributor.authorToz, Metin
dc.date.accessioned2020-05-01T09:11:17Z
dc.date.available2020-05-01T09:11:17Z
dc.date.issued2019
dc.departmentDÜ, Teknoloji Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.descriptionWOS: 000505058700005en_US
dc.description.abstractClustering is the process of sub-grouping data according to certain distance and similarity criteria. One of the most commonly used clustering algorithms in the literature is the Fuzzy C-Means (FCM) algorithm based on the fuzzy clustering principle. Although FCM is an efficient algorithm, random selection of initial cluster centers is a disadvantage since it easier trap the algorithm into local optimum. This problem can be solved by approaching the clustering problem as an optimization problem. In this article, Whale Optimization Algorithm (WOA), a global optimization algorithm developed by inspiration from hunting behaviors of humpback whales, has been improved with chaos maps using an adaptive normalization method and chaotic WOA algorithms are proposed. They are then hybridized with FCM algorithm. The performances of the proposed chaotic optimization algorithms are tested with thirteen different benchmark functions. Results are evaluated with means and standard deviations of the objective function values and with the Wilcoxon Sign Rank Test at 0.05 significance level. The clustering performances of the proposed hybrid algorithms measured according to the objective function, the Rand Index and the Adjusted Rand Index values and compared with the K-Means, FCM and some of the other hybrid algorithms for six different data sets selected from the UCI Repository database. In addition, the new hybrid clustering algorithms are improved by using Chebyshev distance function instead of the classical Euclidean distance for the FCM algorithm in order to increase their data clustering performances. As a result, it has been seen that the used chaos functions improve the optimization performance of WOA algorithm, integrating chaotic WOA algorithms with FCM algorithm enhances the disadvantages of FCM algorithm and changing the distance function increases clustering performance of the proposed algorithms.en_US
dc.identifier.endpage1124en_US
dc.identifier.issn1304-7205
dc.identifier.issn1304-7191
dc.identifier.issue4en_US
dc.identifier.startpage1103en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12684/5459
dc.identifier.volume37en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.language.isoenen_US
dc.publisherYildiz Technical Univen_US
dc.relation.ispartofSigma Journal Of Engineering And Natural Sciences-Sigma Muhendislik Ve Fen Bilimleri Dergisien_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectData clusteringen_US
dc.subjectWOAen_US
dc.subjectFCMen_US
dc.subjectoptimizationen_US
dc.subjectchaosen_US
dc.titleDATA CLUSTERING BASED ON FUZZY C-MEANS AND CHAOTIC WHALE OPTIMIZATION ALGORITHMSen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
Ä°sim:
5459.pdf
Boyut:
1.26 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
Ä°ndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Makale Koleksiyonu