Abstract
In the paper measures of classifier competence and diversity using a probabilistic model are proposed. The multiple classifier system (MCS) based on dynamic ensemble selection scheme was constructed using both measures developed. The performance of proposed MCS was compared against three multiple classifier systems using six databases taken from the UCI Machine Learning Repository and the StatLib statistical dataset. The experimental results clearly show the effectiveness of the proposed dynamic selection methods regardless of the ensemble type used (homogeneous or heterogeneous).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Aksela, M.: Comparison of classifier selection methods for improving committee performance. In: Windeatt, T., Roli, F. (eds.) MCS 2003. LNCS, vol. 2709, pp. 84–93. Springer, Heidelberg (2003)
Aksela, M., Laaksonen, J.: Using diversity of errors for selecting members of a committee classifier. Pattern Recognition 39, 608–623 (2006)
Berger, J.O.: Statistical Decision Theory and Bayesian Analysis. Springer, New York (1987)
Brown, G., Wyatt, J., Harris, R., Yao, X.: Diversity creation methods: a survey and categorisation. Information Fusion 6, 5–20 (2005)
Canuto, A., Abreu, M., et al.: Investigating the influence of the choice of the ensemble members in accuracy and diversity of selection-based and fusion-based methods for ensemble. Pattern Recognition Letters 28, 472–486 (2007)
Didaci, L., Giacinto, G., Roli, F., Marcialis, G.: A study on the performances of dynamic classifier selection based on local accuracy estimation. Pattern Recognition 38, 2188–2191 (2005)
Dietterich, T.G.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation 10, 1895–1923 (1998)
Duda, R., Hart, P., Stork, G.: Pattern Classification. John Wiley and Sons, New York (2000)
Duin, R., Juszczak, P., Paclik, P., et al.: PRTools4. In: A Matlab Toolbox for Pattern Recognition, Delft University of Technology (2007)
Eulanda, M., Santos, D., Sabourin, R., Maupin, P.: A dynamic overproduce-and-choose strategy for the selection of classifier ensembles. Pattern Recognition 41, 2993–3009 (2008)
Giacinto, G., Roli, F.: Dynamic classifier selection based on multiple classifier behaviour. Pattern Recognition 34, 1879–1881 (2001)
Huenupan, F., Yoma, N., et al.: Confidence based multiple classifier fusion in speaker verification. Pattern Recognition Letters 29, 957–966 (2008)
Kanal, L.: Patterns in pattern recognition. IEEE Trans. Information Theory 20, 697–722 (1974)
Ko, A., Sabourin, R., Britto, A.: From dynamic classifier selection to dynamic ensemble selection. Pattern Recognition 41, 1718–1733 (2008)
Kuncheva, I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley Interscience, Hoboken (2004)
Smits, P.: Multiple classifier systems for supervised remote sensing image classification based on dynamic classifier selection. IEEE Trans. on Geoscience and Remote Sensing 40, 717–725 (2002)
Woloszynski, M., Kurzynski, M.: A measure of competence based on randomized reference classifier for dynamic ensemble selection. In: 20th Int. Conf. on Pattern Recognition, pp. 4194–4197. IEEE Computer Press, Istanbul (2010)
Woloszynski, T.: Matlab Central File Enchange (2010), http://www.mathwork.com/matlabcentral/fileenchange/28391-classifier-competence-based-on-probabilistic-modeling
Woods, K., Kegelmeyer, W., Bowyer, W.: Combination of multiple classifiers using local accuracy estimates. IEEE Trans. on Pattern Analysis and Machine Learning 19, 405–410 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lysiak, R., Kurzynski, M., Woloszynski, T. (2011). Probabilistic Approach to the Dynamic Ensemble Selection Using Measures of Competence and Diversity of Base Classifiers. In: Corchado, E., Kurzyński, M., Woźniak, M. (eds) Hybrid Artificial Intelligent Systems. HAIS 2011. Lecture Notes in Computer Science(), vol 6679. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21222-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-21222-2_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21221-5
Online ISBN: 978-3-642-21222-2
eBook Packages: Computer ScienceComputer Science (R0)