On a New Competence Measure Applied to the Dynamic Selection of Classifiers Ensemble
In this paper a new method for calculating the classifier competence in the dynamic mode is developed. In the method, first decision profile of the classified object is calculated using K nearest objects from the validation set. Next, the decision profile is compared with the support vector produced by the classifier. The competence measure reflects the outcome of this comparison and rates the classifier with respect to the similarity of its support vector and decision profile of the test object in a continuous manner. Three different procedures for calculating decision profile and three different measures for comparing decision profile and support vector are proposed, which leads to nine methods of competence calculation. Two multiclassifier systems (MC) with homogeneous and heterogeneous pool of base classifiers and with dynamic ensemble selection scheme (DES) were constructed using the methods developed. The performance of constructed MC systems was compared against seven state-of-the-art MC systems using 15 benchmark data sets taken from the UCI Machine Learning Repository. The experimental investigations clearly show the effectiveness of the combined multiclassifier system in dynamic fashion with the use of the proposed measures of competence regardless of the ensemble type used.
KeywordsMulticlassifier system Dynamic ensemble selection Measure of competence
This work was supported by the statutory funds of the Department of Systems and Computer Networks, Wroclaw University of Technology.
- 1.Lichman, M.: UCI Machine Learning Repository. University of California, School of Information and Computer Science, Irvine (2013). http://archive.ics.uci.edu/ml
- 8.Duin, R., Juszczak, P., et al.: PR-Tools 4.1, A Matlab Toolbox for Pattern Recognition. Delft University of Technology (2007). http://prtools.org
- 9.Giacinto, G., Roli, F.: Methods for dynamic classifier selection. In: Proceedings of the 10th International Conference on Image Analysis and Processing, pp. 659–664 (1999)Google Scholar
- 17.Sabourin, M., Mitiche, A., Thomas, D., Nagy, G.: Classifier combination for hand-printed digit recognition. In: Proceedings of the 2nd International Conference on Document Analysis and Recognition, pp. 163–166 (1993)Google Scholar