Spatial Clustering in Large Databases Using Packed X-tree

In this paper, we are proposing a new algorithm that improves the performance of the DBSCAN clustering algorithm using a packed X-tree. The proposed algorithm does not require the minpoints and eps values. We have extensively described how the system is achieved and we have also proposed a new effective method for finding the k-nearest neighbours of spatial objects in a large database. The study shows that the proposed method is very efficient and will greatly accelerate the operations of density based clustering in large dataset as against the existing methods.