Optimal classifier selection for adaptive boosting algorithm

Boosting is a general approach for improving classifier performances. In this research we investigated these issues with the latest Boosting algorithm Adaptive Boosting M1 (AdaBoostM1). A trial and error classifier feeding with the AdaBoostM1 algorithm is a regular practice for classification tasks in the research community. We provide a statistical information-based rule method for optimal classifier selection with the AdaBoostM1 algorithm. The classification performance is ranked based on confusion matrix outcome. The solution also verified a wide range of benchmark classification problems.