Proposing Cluster_Similarity Method in Order to Find as Much Better Similarities in Databases

Abstract: Different ways of entering data into databases result in duplicate records that cause increasing of databases' size. This is a fact that we cannot ignore it easily. There are several methods that are used for this purpose. In this paper, we have tried to increase the accuracy of operations by using cluster similarity instead of direct similarity of fields. So that clustering is done on fields of database and according to accomplished clustering on fields, similarity degree of records is obtained. In this method by using present information in database, more logical similarity is obtained for deficient information that in general, the method of cluster similarity could improve operations 24% compared with previous methods.