Pruning One-Class Classifier Ensembles by Combining Sphere Intersection and Consistency Measures
- 1.4k Downloads
One-class classification is considered as one of the most challenging topics in the contemporary machine learning. Creating Multiple Classifier Systems for this task has proven itself as a promising research direction. Here arises a problem on how to select valuable members to the committee - so far a largely unexplored area in one-class classification. This paper introduces a novel approach that allows to choose appropriate models to the committee in such a way that assures both high quality of individual classifiers and a high diversity among the pool members. We aim at preventing the selection of both too weak or too similar models. This is achieved with the usage of an multi-objective optimization that allows to consider several criteria when searching for a good subset of classifiers. A memetic algorithm is applied due to its efficiency and less random behavior than traditional genetic algorithm. As one-class classification differs from traditional multi-class problems we propose to use two measures suitable for this problem - consistency measure that allow to rank the quality of one-class models and introduced by us sphere intersection measure that serves as a diversity metric. Experimental results carried on a number of benchmark datasets proves that it outperforms traditional single-objective approaches.
Keywordsmachine learning one-class classification ensemble pruning classifier selection diversity random subspace memetic algorithm multi-objective optimisation
Unable to display preview. Download preview PDF.
- 9.Juszczak, P.: Learning to recognise. A study on one-class classification and active learning. PhD thesis, Delft University of Technology (2006)Google Scholar
- 10.Knowles, J., Corne, D.: Memetic algorithms for multiobjective optimization: Issues, methods and prospects, pp. 325–332. IEEE Press (2004)Google Scholar
- 16.Krawczyk, B., Woźniak, M.: Experiments on distance measures for combining one-class classifiers. In: Proceedings of the FEDCISIS 2012 Conference, pp. 88–92 (2012)Google Scholar
- 17.Liu, B., Zhao, D., Reynaert, P., Gielen, G.G.E.: Synthesis of integrated passive components for high-frequency rf ics based on evolutionary computation and machine learning techniques. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 30(10), 1458–1468 (2011)CrossRefGoogle Scholar
- 18.SIAM: Proceedings of the Eleventh SIAM International Conference on Data Mining, SDM 2011, Mesa, Arizona, USA, April 28-30. SIAM, Omnipress (2011)Google Scholar
- 21.Tax, D.M.J., Müller, K.: A consistency-based model selection for one-class classification. In: Proceedings - International Conference on Pattern Recognition, vol. 3, pp. 363–366 (2004)Google Scholar
- 22.Tax, D.M.J., Duin, R.P.W.: Characterizing one-class datasets. In: Proceedings of the Sixteenth Annual Symposium of the Pattern Recognition Association of South Africa, pp. 21–26 (2005)Google Scholar
- 23.R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2008)Google Scholar