Clustered Bayesian classification for within-class separation

Abstract

The Bayesian classification is one of the frequently used approaches in machine learning. This approach obtains probabilities based on attributes of classes using Bayes' theorem and makes predictions according to these probabilities. Bayesian classifiers employ densities such as Gaussian, kernel, multivariate Gaussian, and Copula densities when attributes consist of continuous variables. These densities partially produce rough density values. When the attributes of any of the classes are concentrated on more than one region, above mentioned densities are not inherently suitable. In order to overcome this problem, this study introduces a novel approach called Clustered Bayesian classification. The proposed method creates a new class variable by detecting the different concentrations within the class using the Gaussian Mixture Clustering method. It makes predictions by setting a model over the new class variable. Then, the probabilities of the original classes are calculated over the probabilities of the new classes. The proposed method is compared with 5 different Bayesian classifiers on 27 different data sets. As a result, it has been seen that Clustered Bayesian classification outperformed all Bayesian classifiers for different performance metrics.