Divisive Hierarchical Clustering for Random Data Points Based on Farthest Distance (DHCRF)?

The term ‘Clustering’ means grouping of input datasets into subsets, which is commonly called ’clusters’ .The elements in the clusters, are somewhat similar. Many clustering algorithms require the specification of the number of clusters to be produced, prior to execution of the algorithm. The specified method proposes a simple and efficient clustering method. This paper presents an overview of different pattern clustering methods from a statistical pattern recognition perspective. In this paper, we review the possibility of applying a variety of distance metrics and rely on Euclidean distance. The performance of the algorithm is evaluated based on time complexity, execution time and number of clusters formed. The attractive feature of the proposed method is that it solves ‘local minima problem’.