期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2011
卷号：27
期号：1
出版社：Journal of Theoretical and Applied
摘要：Data clustering is a process of putting similar data into groups. A clustering algorithm partitions a data set into several groups such that the similarity within a group is larger than among groups. In the field of data mining, various clustering algorithms are proved for their clustering quality. This research work deals with, two of the most representative clustering algorithms namely centroid based K-Medoids and representative object based Fuzzy C-Means are described and analyzed based on their basic approach using the distance between two data points. For both the algorithms, a set of n data points are given in a two-dimensional space and an integer K (the number of clusters) and the problem is to determine a set of n points in the given space called centers, so as to minimize the mean squared distance from each data point to its nearest center. The performance of the algorithms is investigated during different execution of the program for the given input data points. Based on experimental results the algorithms are compared regarding their clustering quality and their performance, which depends on the time complexity between the various numbers of clusters chosen by the end user. The total elapsed time to cluster all the data points and Clustering time for each cluster are also calculated in milliseconds and the results compared with one another.
关键词：K-Medoids Algorithm; Fuzzy C-Means Algorithm; Cluster Analysis; Data Analysis
