Boosting-Based TAN Combination Classifier

Boosting is an effective classifier combination method, which can improve classification performance of an unstable learning algorithm. But it does not make much more improvement of a stable learning algorithm. TAN, tree-augmented nave Bayes, is a tree-like Bayesian network. The standard TAN learning algorithm generates a stable TAN classifier, whose accuracy is difficult to improve by the Boosting technique. In this paper, a new TAN learning algorithm called GTAN is presented, and multiple TAN classifiers generated by GTAN are combined by a combination method called Boosting-MultiTAN. Finally, this TAN combination classifier is compared with the standard TAN classifier by the experiments. Experimental results show that the Boosting MultiTAN has higher classification accuracy than the standard TAN classifier on most data sets.