A modified clustering algorithm for data mining

Abstract

Clustering is a widely used technique of finding interesting patterns residing in the dataset that were not obviously known. It is a division of data into groups of similar objects. The clustering of large data sets has received a lot of attention in recent years, however, clustering is still a challenging task since many cluster algorithms fail to do well in scaling with the size of the data set and the number of dimensions that describe the points, or in finding arbitrary shapes of clusters, or dealing effectively with the presence of noise. This paper describes a clustering method for unsupervised classification of objects in large data sets. The new methodology combines the simulating annealing algorithm with CLARANS (clustering large application based upon randomized search) in order to cluster large data sets efficiently. At last, the method is experimented on the generated data set. The result shows that the approach is quick than CLARANS and can produce a similar division of data as CLARANS.