The hubness is a good measure of point centrality with in a high-dimensional data cluster, and by depicts the hubness-based clustering methods, gives that the hubs can be used effectively as cluster prototypes that are used for searching the centroid-based cluster configurations. The results demonstrate good performance of the algorithms in different stages, particularly in the presence of large quantities of noise. The core objective of Shared Nearest Neighbor Clustering is to find the number of cluster points which gives out the points which are more similar to other points in a cluster which are different. SNNC estimates the relative density, i.e., probability density, is a place which are so nearer and obtains a more robust definition of density. The experimental performance of kernel mapping and shared neighbor clustering algorithm is used in in spite of clustering quality, distance measurement ratio, clustering time, and energy consumption.