Local Density Differ Spatial Clustering in Data Mining

Clustering in data mining is a discovery process that groups a set of data objects so that the inter-cluster similarity is minimized and intracluster similarity is maximized. In presence of noise and outlier in high dimensional data base it is a difficult task to find out the clusters of different shapes, sizes and differ in density. Density based clustering algorithms like DBSCAN finds the clusters based on density property but still within the same cluster the major density difference may exist due to the only minimum point value. In this paper we propose a Local density differ clustering algorithm which capable to handle the local density variation within the cluster. It calculates the density variance in its surrounding and if any core object that have the density variance less than a given threshold value K than that core object can start the formation of cluster. The proposed clustering algorithm generates more density based homogenous cluster in comparison to DBSCAN.