Ensembles of Optimum-Path Forest Classifiers Using Input Data Manipulation and Undersampling

The combination of multiple classifiers was proven to be useful in many applications to improve the classification task and stabilize results. In this paper we used the Optimum-Path Forest (OPF) classifier to investigate input data manipulation techniques in order to use less data from the training set without hampering the classification accuracy. The data undersampling can be useful to speed-up the classification task, and could be specially useful with large datasets. The results indicate that the OPF-based ensemble methods allow a significant reduction on the size of the training set, while maintaining or slightly improving accuracy. We provide intuition for a case of failure and report the results of synthetic and real datasets.