Ensemble Selection Based on Discriminant Functions in Binary Classification Task
The paper describes the dynamic ensemble selection. The proposed algorithm uses values of the discriminant functions and it is dedicated to the binary classification task. The proposed algorithm of the ensemble selection uses decision profiles and the normalization of the discrimination functions is carried out. Additionally, the difference of the discriminant functions is used as one condition of selection. The reported results based on the ten data sets from the UCI repository show that the proposed dynamic ensemble selection is a promising method for the development of multiple classifiers systems.
KeywordsEnsemble selection Multiple classifier system Binary classification task
This work was supported by the Polish National Science Center under the grant no. DEC-2013/09/B/ST6/02264 and by the statutory funds of the Department of Systems and Computer Networks, Wroclaw University of Technology.
- 9.Frank, A., Asuncion, A.: UCI machine learning repository (2010)Google Scholar