Class clustering with ant colony rank optimization (CCACRO) for data categorization

Self-Organizing Map (SOM) is in the more prominent concern nowadays because of the chain of importance making in document association. It will be better for those issues where we required bunching and representation. This paper provides an efficient direction for better clustering and classification techniques which will be significant in archive association. In this paper an efficient Class Clustering with Ant Colony Rank Optimization (CCACRO) for Data Categorization have been proposed. In this method first the data is classified and parsed numerically and then alphabetical parsing is done so that grammatical terms have been removed for proper data filtration. Ant Colony Optimization have then applied for finding the threshold ranking for finding the optimize rank in the similar class group. For experimentation we have connected our methodology on distinctive information and accomplish better results in correlation to the past strategies.