Weighed Aging Ensemble of Heterogenous Classifiers for Incremental Drift Classification
Nowadays simple methods of data analysis are not sufficient for efficient management of an average enterprize, since for smart decisions the knowledge hidden in data is highly required, among them methods of collective decision making called classifier ensemble are the focus of intense research. Unfortunately the great disadvantage of traditional classification methods is that they ”assume” that statistical properties of the discovered concept (which model is predicted) are being unchanged. In real situation we could observe so-called concept drift, which could be caused by changes in the probabilities of classes or/and conditional probability distributions of classes. The paper presents extension of Weighted Aging Classifier Ensemble (WAE), which is able to adapt to the changes in data stream. It assumes that the classified data stream is given in a form of data chunks, and the concept drift could appear in the incoming data chunks. Instead of drift detection WAE tries to construct self-adapting classifier ensemble. Therefore on the basis of the each chunk one individual is trained and WAE checks if it could form valuable ensemble with the previously trained models. The presented extension uses the ensemble of heterogeneous classifiers, what boosts the classification accuracy, what was confirmed on the basis of the computer experiments.
Keywordsmachine learning classifier ensemble data stream concept drift incremental learning forgetting
Unable to display preview. Download preview PDF.
- 1.Alpaydin, E.: Introduction to Machine Learning, 2nd edn. The MIT Press (2010)Google Scholar
- 2.Bifet, A., Holmes, G., Pfahringer, B., Read, J., Kranen, P., Kremer, H., Jansen, T., Seidl, T.: MOA: A real-time analytics open source framework. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011, Part III. LNCS, vol. 6913, pp. 617–620. Springer, Heidelberg (2011)CrossRefGoogle Scholar
- 5.Hulten, G., Spencer, L., Domingos, P.: Mining time-changing data streams. In: Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 97–106 (2001)Google Scholar
- 7.Klinkenberg, R., Renz, I.: Adaptive information filtering: Learning in the presence of concept drifts, pp. 33–40 (1998)Google Scholar
- 8.Kolter, J.Z., Maloof, M.A.: Dynamic weighted majority: a new ensemble method for tracking concept drift. In: Third IEEE International Conference on Data Mining, ICDM 2003, pp. 123–130 (November 2003)Google Scholar
- 9.Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience (2004)Google Scholar
- 13.Platt, J.C.: Fast training of support vector machines using sequential minimal optimization. In: Advances in Kernel Methods, pp. 185–208. MIT Press, Cambridge (1999)Google Scholar
- 14.Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann Series in Machine Learning. Morgan Kaufmann Publishers (1993)Google Scholar
- 18.Widmer, G., Kubat, M.: Learning in the presence of concept drift and hidden contexts. Mach. Learn. 23(1), 69–101 (1996)Google Scholar
- 19.Wolpert, D.H.: The supervised learning no-free-lunch theorems. In: Proc. 6th Online World Conference on Soft Computing in Industrial Applications, pp. 25–42 (2001)Google Scholar