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

Alp Erilli, N. and Yolcu, Ufuk and Eǧrioǧlu, Erol and Hakan Aladaǧ, Ĉ and Öner, Yüksel (2011) Determining the most proper number of cluster in fuzzy clustering by using artificial neural networks. Expert Systems with Applications, 38 (3). pp. 2248-2252. ISSN 0957-4174

Full text not available from this repository.

Abstract

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.

Item Type:
Journal Article
Journal or Publication Title:
Expert Systems with Applications
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1702
Subjects:
ID Code:
139557
Deposited By:
Deposited On:
16 Dec 2019 16:15
Refereed?:
Yes
Published?:
Published
Last Modified:
11 Mar 2020 07:50