Clustering in Data Mining Using Modified K-Means Algorithm

The main objective of clustering is to find similarities between data by using Cluster analysis method. Clustering is a type of multivariate statistical analysis. It groups similar samples together to assist in understanding the relationships that exist between them. Cluster analysis is based on mathematical formulation of a measure of similarity.
Clustering is a type of multivariate statistical analysis, unsupervised classification analysis, or numerical taxonomy. The main objective of clustering is to find similarities between experiments or genes, and then group similar samples or genes together to assist in understanding relationships that might exist among them. It is a technique for sorting cases (genes, samples, etc.) into groups, or clusters, so that the degree of association is strong between members of the same cluster and weak between members of different clusters. Data subsets of genes or samples get grouped together (clustered) based on their similarities. 
Cluster Analysis can be used as a general data reduction tool to develop clusters (or) subgroups of data that are more manageable than individual observations. It is used for taxonomy for related animals, insects or plants. 
It suggests statistical models with which to describe populations. It is used to indicate rules for assigning new cases to classes for identification and diagnostic.