Two stage ensemble selection algorithm

• Autorzy: Baczyńska P. , Burduk R.
• Języki publikacji: EN

Abstrakty

EN

Multiple Classifiers Systems (MCSs) very often improve the accuracy of classification when compared with base classifiers. The building of MCSs consists of three phases: generation, selection and integration. The paper presents the two stage dynamic ensemble selection based on the analysis of the discriminant functions. The proposed in the work algorithm is applied to the binary classification tasks. In the integration phase we use the sum rule. Reported results based on the ”Pima” data set show that the proposed two stage ensemble selection is a promising method for the development of MCSs.

Słowa kluczowe

EN

ensemble selection; multiple classifier system; binary classification task

• Wydawca: Komisja Informatyki Polskiej Akademii Nauk, Oddział w Gdańsku
• Czasopismo: Journal of Theoretical and Applied Computer Science
• Rocznik: 2015
• Tom: Vol. 9, nr 1
• Strony: 3--8
• Opis fizyczny: Bibliogr. 27 poz., tab.

Twórcy

autor

Baczyńska P.

• Department of Systems and Computer Networks, Wroclaw University of Technology, Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, Poland

autor

Burduk R.

• Department of Systems and Computer Networks, Wroclaw University of Technology, Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, Poland

Bibliografia

• [1] C. M. Bishop. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag New York, Inc., Secaucus, NJ, USA, 2006.
• [2] R. Burduk. Classifier fusion with interval-valued weights. Pattern Recognition Letters, 34(14):1623-1629, 2013.
• [3] P. R. Cavalin, R. Sabourin, C. Y. Suen. Dynamic selection approaches for multiple classifier systems. Neural Computing and Applications, 22(3-4):673–688, 2013.
• [4] A. S. Britto, R. Sabourin, L. E. S. Oliveira. Dynamic selection of classifiers A comprehensive review Pattern Recognition, 47(11):3665–368, 2014.
• [5] B. Cyganek. One-class support vector ensembles for image segmentation and classification. Journal of Mathematical Imaging and Vision, 42(2-3):103–117, 2012.
• [6] B. Cyganek, M.Woźniak. Vehicle Logo Recognition with an Ensemble of Classifiers. Lecture Notes in Computer Science, 8398:117–126, 2014.
• [7] L. Didaci, G. Giacinto, F. Roli, G. L. Marcialis. A study on the performances of dynamic classifier selection based on local accuracy estimation. Pattern Recognition, 38:2188–2191, 11/2005 2005.
• [8] P. Forczmański, P. Łabędź. Recognition of Occluded Faces Based on Multi-subspace Classification. Lecture Notes in Computer Science, 8104:148–157, 2013.
• [9] P. Forczmański, P. Łabędź. Improving the Recognition of Occluded Faces by Means of Two-dimensional Orthogonal Projection into Local Subspaces. Lecture Notes in Computer Science, 9164:229–238, 2015.
• [10] A. Frank, A. Asuncion. UCI machine learning repository, 2010.
• [11] D. Frejlichowski. An Algorithm for the Automatic Analysis of Characters Located on Car License Plates. Lecture Notes in Computer Science, 7950:774–781, 2013.
• [12] G. Giacinto, F. Roli. An approach to the automatic design of multiple classifier systems. Pattern Recognition Letters, 22:25–33, 2001.
• [13] T. K. Ho, J. J. Hull, S. N. Srihari. Decision combination in multiple classifier systems. IEEE Trans. Pattern Anal. Mach. Intell., 16(1):66–75, 1994.
• [14] K. Jackowski, B. Krawczyk, M. Woźniak. Improved adaptive splitting and selection: The hybrid training method of a classifier based on a feature space partitioning. International Journal of Neural Systems, 24(03), 2014.
• [15] K. Jackowski, M. Woźniak. Method of classifier selection using the genetic approach. Expert Systems, 27(2):114–128, 2010.
• [16] J. Kittler, F. M. Alkoot. Sum versus vote fusion in multiple classifier systems. IEEE Trans. Pattern Anal. Mach. Intell., 25(1):110–115, 2003.
• [17] L. I. Kuncheva. A theoretical study on six classifier fusion strategies. IEEE Trans. Pattern Anal. Mach. Intell., 24(2):281–286, 2002.
• [18] L. I. Kuncheva. Combining Pattern Classifiers: Methods and Algorithms. John Wiley and Sons, Inc., 2004.
• [19] L. Lam, C. Y. Suen. Application of majority voting to pattern recognition: an analysis of its behavior and performance. IEEE Transactions on Systems, Man, and Cybernetics, Part A, 27(5):553–568, 1997.
• [20] M. Przewoźniczek, K. Walkowiak, M. Woźniak. Optimizing distributed computing systems for k-nearest neighbours classifiersevolutionary approach. Logic Journal of IGPL, 19(2):357–372, 2010.
• [21] R. Ranawana, V. Palade. Multi-classifier systems: Review and a roadmap for developers. International Journal of Hybrid Intelligent Systems, 3(1):35–61, 2006.
• [22] I. Rejer. Genetic algorithms in eeg feature selection for the classification of movements of the left and right hand. In Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013, pages 579–589. Springer, 2013.
• [23] D. Ruta, B. Gabrys. Classifier selection for majority voting. Information Fusion, 6(1):63–81, 2005.
• [24] C. Y. Suen, R. Legault, C. P. Nadal, M. Cheriet, L. Lam. Building a new generation of handwriting recognition systems. Pattern Recognition Letters, 14(4):303–315, 1993.
• [25] K. Trawiński, O. Cordon, A. Quirin. A study on the use of multiobjective genetic algorithms for classifier selection in furia-based fuzzy multiclassifiers. International Journal of Computational Intelligence Systems, 5(2):231–253, 2012.
• [26] A. Ulas, M. Semerci, O. T. Yildiz, E. Alpaydin. Incremental construction of classifier and discriminant ensembles. Information Science, 179(9):1298–1318, Apr. 2009.
• [27] T. Woloszyński, M. Kurzyński. A probabilistic model of classifier competence for dynamic ensemble selection. Pattern Recognition, 44(10-11):2656–2668, 2011.