Normalization based K-means Data Analysis Algorithm

Abstract

Data mining is analysis step to knowledge discovery in the database process. It is the process of extraction knowledge from large databases. Clustering is a process of partitioning a set of data (or objects) into a set of meaningful sub-classes, called clusters. Used either as a stand-alone tool to get insight into datadistribution or as a preprocessing step for other algorithms. K-means is a good clustering technique. With the proposed algorithm, normalization of data prior to clustering. Then a efficient algorithm used for clustering which is better than simple k-means algorithm.