Babcock University Research Portal

A New Clustering Validity Index (CVI) for Fuzzy C Means Algorithm Based on Measure Of Disparity

Authors: EBIESUWA Oluwaseun

Publication Type: Journal article

Journal: International Journal Of Advanced Research In Computer Engineering & Technology

ISSN Number:

Downloads

Views

Abstract

Cluster validity indexes have been used to evaluate the fitness of partitions produced by clustering algorithms. This paper presents a new validity index for fuzzy clustering called inter-cluster and intra-cluster separation (IC2S) index. Therefore, we proposed the function of disparity which combines the intra and inter-cluster separation existing between the clusters. The results of comparative study show that the proposed IC2S index has high ability in producing a good cluster number estimate. This performance is achieved by taking into consideration the existing disparity between clusters. To assess the new validation index, two data sets (Fisher’s IRIS and Butterfly data set) were used and the results show that IC2S outperforms other clustering validation index for fuzzy c-means.

Access to Documents

External Link
Download
Digital Object Identifier

Keywords

EBIESUWA,O. . (2014). A New Clustering Validity Index (CVI) for Fuzzy C Means Algorithm Based on Measure Of Disparity, 3 (), 3053-3053.

EBIESUWA,O. . "A New Clustering Validity Index (CVI) for Fuzzy C Means Algorithm Based on Measure Of Disparity" 3, no (), (2014): 3053-3053.

EBIESUWA,O. and . (2014). A New Clustering Validity Index (CVI) for Fuzzy C Means Algorithm Based on Measure Of Disparity, 3 (), pp3053-3053.

EBIESUWAO, . A New Clustering Validity Index (CVI) for Fuzzy C Means Algorithm Based on Measure Of Disparity. 2014, 3 ():3053-3053.

EBIESUWA,Oluwaseun , . "A New Clustering Validity Index (CVI) for Fuzzy C Means Algorithm Based on Measure Of Disparity", 3 . (2014) : 3053-3053.

E.Oluwaseun , "A New Clustering Validity Index (CVI) for Fuzzy C Means Algorithm Based on Measure Of Disparity" vol.3, no., pp. 3053-3053, 2014.

Access to Documents

Keywords

About Us

Admissions

Contact Us

Policies

ALUMNI

STUDENT POPULATION