TREE AUGMENTED NAIVE BAYES BASED ON OPTIMIZATION

Tree Augmented Naive Bayes is an efficient form of Bayesian Network. It is factored representations of probability distributions that generalize the Naive Bayes, yet at the same time maintains the robustness of Naive Bayes. In this paper, we propose a new optimization model for Tree Augmented Naive Bayes by considering some of class probabilities as unknown variables. Results of numerical experiments on 10 real world data sets demonstrate that the proposed model can significantly improve the classification accuracy of Tree Augmented Naive Bayes