To search, Click below search items.


All Published Papers Search Service


Heterogeneous Density Based Spatial Clustering of Application with Noise


J. Hencil Peter, A.Antonysamy


Vol. 10  No. 8  pp. 210-214


The DBSCAN [1] algorithm is a popular algorithm in Data Mining field as it has the ability to mine the noiseless arbitrary shape Clusters in an elegant way. As the original DBSCAN algorithm expand the Cluster based on the core object condition, it doesn’t have the intelligence to mine the clusters which have different densities and these clusters may or may not be separated by the sparse region. In this paper we propose a new algorithm for mining the density based clusters and the algorithm is intelligent enough to mine the clusters with different densities. For every new cluster expansion, homogeneity core object’s density range (start and end value) will be obtained using a function and based on the range values, cluster(s) will be allowed to expand further. To improve the performance of the new algorithm and without loosing the quality of Clusters, we have used the Memory Effect in DBSCAN Algorithm [7] approach. The new algorithm’s output and performance analysis shows that proposed solution is superior to the existing algorithms.


Density Different Cluster(s), Variance Density DBSCAN, Heterogeneous Density Clusters