Institute of Research and Journals (IRAJ)
K-means method is one of the renowned and generally used partitioning clustering techniques. However, the major problem with this method is that it cannot ensure the global optimum results due to the random selection of initial cluster center. In this paper, the authors proposed a clustering algorithm-KCVD (K-means Clustering algorithm with Voronoi Diagram) using the concept of Voronoi cells and k-means. KCVD algorithm brings the hidden data objects in a given data set in picture. As a result, the proposed algorithm automates the selection of initial cluster centroid according to increasing of x-axis, and evaluates the actual cluster value.