A Comparative Analysis of Simulated Annealing Based Intuitionistic Fuzzy K-Mode Algorithm for Clustering Categorical Data

Abstract

In this paper we introduce the concept of simulated annealing on intuitionistic fuzzy k-mode algorithm to cluster categorical data. This notion is an extension of intuitionistic fuzzy k-mode in which we have added the concept of energy related objective functions, temperature ranges and probability so as to provide better clusters for the data objects. There is a deep and useful connection between statistical mechanics and the kind of multivariate optimization we are doing here. A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems. This connection to statistical mechanics exposes new information and provides an unfamiliar perspective on traditional optimization problems and methods. So simulated annealing has been used here. Also the intuitionistic parameter has been retained for the calculation of membership values of element x in a given cluster. Systematic experiments were carried out with datasets taken from the UCI Machine learning repository. The results and a comparative evaluation show a high performance and consistency of the proposed method, which achieves significant improvement compared to intuitionistic fuzzy k-mode. Simulated Annealing based Intuitionistic fuzzy k-mode is very efficient when clustering large categorical data sets, which is very much critical to data mining applications.