Abstract
This paper deals with the problem of dynamic dimension reduction during the on-line update and evolution of fuzzy classifiers. With ’dynamic’ it is meant that the importance of features for discriminating between the classes changes over time when new data is sent into the classifiers’ update mechanisms. In order to avoid discontinuity in the incremental learning process, i.e. permanently exchanging some features in the input structure of the fuzzy classifiers, we include feature weights (lying in [0,1]) into the training and update of the fuzzy classifiers, which measure the importance levels of the various features and can be smoothly updated with new incoming samples. In some cases, when the weights become (approximately) 0, an automatic switching off of some features and therefore a (soft) dimension reduction is achieved. The approaches for incrementally updating the feature weights are based on a leave-one-feature-out and on a feature-wise separability criterion. We will describe the integration concept of the feature weights in evolving fuzzy classifiers using single and multi-model architecture. The whole approach will be evaluated based on high-dimensional on-line real-world classification scenarios.
This work was funded by the Upper Austrian Technology and Research Promotion. It reflects only the authors’ views.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Angelov, P., Zhou, X.: Evolving fuzzy-rule-based classifiers from data streams. IEEE Transactions on Fuzzy Systems 16(6), 1462–1475 (2008)
Angelov, P., Lughofer, E., Zhou, X.: Evolving fuzzy classifiers using different model architectures. Fuzzy Sets and Systems 159(23), 3160–3182 (2008)
Bouchachia, A.: Incremental induction of classification fuzzy rules. In: 2009 IEEE Symposium Series on Computational Intelligence, pp. 32–39 (2009)
Casillas, J., Cordon, O., Jesus, M.D., Herrera, F.: Genetic feature selection in a fuzzy rule-based classification system learning process for high-dimensional problems. Information Sciences 136, 135–157 (2001)
Draper, N., Smith, H.: Applied Regression Analysis. Probability and Mathematical Statistics. John Wiley & Sons, New York (1981)
Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. Wiley-Interscience, Southern Gate (2000)
Dy, J., Brodley, C.: Feature selection for unsupervised learning. Journal of Machine Learning Research 5, 845–889 (2004)
Filev, D.P., Tseng, F.: Novelty detection based machine health prognostics. In: Proc. of the 2006 International Symposium on Evolving Fuzzy Systems, pp. 193–199. Lake District, UK (2006)
Lughofer, E.: Extensions of vector quantization for incremental clustering. Pattern Recognition 41(3), 995–1011 (2008)
Lughofer, E.: On-line evolving image classifiers and their application to surface inspection. Image and Vision Computing (in press, 2010) doi: 10.1016/j.imavis.2009.07.002
Lughofer, E., Angelov, P., Zhou, X.: Evolving single- and multi-model fuzzy classifiers with FLEXFIS-Class. In: Proceedings of FUZZ-IEEE 2007, London, UK, pp. 363–368 (2007)
Maturino-Lozoya, H., Munoz-Rodriguez, D., Jaimes-Romera, F., Tawfik, H.: Handoff algorithms based on fuzzy classifiers. IEEE Transactions on Vehicular Technology 49(6), 2286–2294 (2000)
Mikenina, L., Zimmermann, H.: Improved feature selection and classification by the 2-additive fuzzy measure. Fuzzy Sets and Systems 107, 197–218 (1999)
Mouchaweh, M.S., Devillez, A., Lecolier, G., Billaudel, P.: Incremental learning in fuzzy pattern matching. Fuzzy Sets and Systems 132, 49–62 (2002)
Nauck, D., Kruse, R.: A neuro-fuzzy method to learn fuzzy classification rules from data. Fuzzy Sets and Systems 89(3), 277–288 (1997)
Pang, S., Ozawa, S., Kasabov, N.: Incremental linear discriminant analysis for classification of data streams. IEEE Transaction on Systems, Men and Cybernetics - part B: Cybernetics 35(5), 905–914 (2005)
Sanchez, L., Suarez, M., Villar, J., Couso, I.: Mutual information-based feature selection and partition design in fuzzy rule-based classifiers from vague data. International Journal of Approximate Reasoning 49, 607–622 (2008)
Sannen, D., Nuttin, M., Smith, J., Tahir, M., Lughofer, E., Eitzinger, C.: An interactive self-adaptive on-line image classification framework. In: Gasteratos, A., Vincze, M., Tsotsos, J. (eds.) ICVS 2008. LNCS, vol. 5008, pp. 173–180. Springer, Heidelberg (2008)
Xydeas, C., Angelov, P., Chiao, S., Reoulas, M.: Advances in eeg signals classification via dependant hmm models and evolving fuzzy classifiers. International Journal on Computers in Biology and Medicine, special issue on Intelligent Technologies for Bio-informatics and Medicine 36(10), 1064–1083 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lughofer, E. (2010). On Dynamic Soft Dimension Reduction in Evolving Fuzzy Classifiers . In: Hüllermeier, E., Kruse, R., Hoffmann, F. (eds) Computational Intelligence for Knowledge-Based Systems Design. IPMU 2010. Lecture Notes in Computer Science(), vol 6178. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-14049-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-14049-5_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-14048-8
Online ISBN: 978-3-642-14049-5
eBook Packages: Computer ScienceComputer Science (R0)