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

Authors:
N. Alp Erilli;Ufuk Yolcu;Erol Eğrioğlu;Ç. Hakan Aladağ;Yüksel Öner
Affiliations:
Department of Statistics, Ondokuz Mayis University, Samsun, Turkey;Department of Statistics, Ondokuz Mayis University, Samsun, Turkey;Department of Statistics, Ondokuz Mayis University, Samsun, Turkey;Department of Statistics, Hacettepe University, Samsun, Turkey;Department of Statistics, Ondokuz Mayis University, Samsun, Turkey
Venue:
Expert Systems with Applications: An International Journal
Year:
2011

Citing 11
Cited 1

A Validity Measure for Fuzzy Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Validating fuzzy partitions obtained through c-shells clustering

Pattern Recognition Letters - Special issue on fuzzy set technology in pattern recognition
A new cluster validity index for the fuzzy c-mean

Pattern Recognition Letters
Membership functions in the fuzzy C-means algorithm

Fuzzy Sets and Systems
Techniques of Cluster Algorithms in Data Mining

Data Mining and Knowledge Discovery
On Clustering Validation Techniques

Journal of Intelligent Information Systems
A cluster validation index for GK cluster analysis based on relative degree of sharing

Information Sciences—Informatics and Computer Science: An International Journal
A cluster validity index for fuzzy clustering

Pattern Recognition Letters
New indices for cluster validity assessment

Pattern Recognition Letters
On fuzzy cluster validity indices

Fuzzy Sets and Systems
Advances in Fuzzy Clustering and its Applications

Advances in Fuzzy Clustering and its Applications

Study on multi-center fuzzy C-means algorithm based on transitive closure and spectral clustering

Applied Soft Computing

Quantified Score

Hi-index	12.05

Visualization

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.