A Comparative Analysis of Clustering Algorithms and Recent Developments.

Clustering is very central to the concept of data mining applications and data analysis. It is a very desirable capability to be able to identify regions of highly co-related objects as their count becomes very high and at the same time the data sets enlarge and changes in their properties and relationships among the datasets also altered. It is important to note that the concept of clustering is fundamentally a partitioning of some or many objects based on a set of rules. In the literature, a considerable number of clustering algorithms are available which are classified into various categories. In this paper, an attempt is made to perform a comparative analysis of some state-of-the-art clustering algorithms based on different parameters. At the end, some recent advances of clustering algorithms are also highlighted. [ABSTRACT FROM AUTHOR]