DISTRIBUTED INTUITIONISTIC FUZZY CLUSTERING APPROACH FOR CENSUS DATA SET

Abstract

There may be a new requirement for powerful ways to address disseminated grouping, due to explosion in the quantity of self sustaining records sources.  Intuitionistic Fuzzy Set is a suitable tool to manage defectively characterized actualities and information, and additionally with uncertain learning. In this paper census data analysis can be done by using Intuitionistic Fuzzy based Distributed Fuzzy C-Means Algorithm (IF-DFCM), to group conveyed datasets, without essentially downloading every one of the information into a solitary webpage. The procedure is done in two distinct levels: neighborhood level and worldwide level. In neighborhood level, numerical datasets are transformed into intuitionistic fuzzy data and they are clustered independently from each other using modified fuzzy C-Means algorithm. In worldwide level, centroid is computed by clustering all local cluster centroids. The global centroid is again transmitted to local sites to revise and bring up to date local cluster model. The main objective is to apply and compare the results of Census dataset with Intuitionistic Fuzzy based Distributed Fuzzy C-Means Algorithm              (IF-DFCM) and Intuitionistic Fuzzy based Centralized Fuzzy C-Means Algorithm (IF-CFCM). It is observed that the algorithm IF-DFCM performs better than IF-CFCM algorithm.