Determining the most proper number of cluster in fuzzy clustering by using artificial neural networks


Erilli N. A., Yolcu U., Egrioglu E., ALADAĞ Ç. H., Oner Y.

EXPERT SYSTEMS WITH APPLICATIONS, cilt.38, sa.3, ss.2248-2252, 2011 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 38 Sayı: 3
  • Basım Tarihi: 2011
  • Doi Numarası: 10.1016/j.eswa.2010.08.012
  • Dergi Adı: EXPERT SYSTEMS WITH APPLICATIONS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.2248-2252
  • Anahtar Kelimeler: Artificial neural networks, Cluster validation index, Fuzzy clustering, Number of cluster, VALIDITY INDEX
  • Marmara Üniversitesi Adresli: Hayır

Özet

In a clustering problem, it would be better to use fuzzy clustering if there was an uncertainty in determining clusters or memberships of some units. Determining the number of cluster has an important role on obtaining sensible and sound results in clustering analysis. In many clustering algorithm, it is firstly need to know number of cluster. However, there is no pre-information about the number of cluster in general. The process of determining the most proper number of cluster is called as cluster validation. In the available fuzzy clustering literature, the most proper number of cluster is determined by utilizing cluster validation indices. When the data contain complexity are being analyzed, cluster validation indices can produce conflictive results. Also, there is no criterion point out the best index. In this study, artificial neural networks are employed to determine the number of cluster. The data is taken as input so the output is membership degree. The proposed method is applied some data and obtained results are compared to those obtained from validation indices like PC, XB, and CE. It is shown that the proposed method produce accurate results. (C) 2010 Elsevier Ltd. All rights reserved.