Abstract
Classification is the primal problem in pattern recognition. The quadratic loss function is not good approximation of the misclassification error. In the presented paper a nonlinear extension of the IRLS classifier, which uses different loss functions, is proposed. The extension is done by means of fuzzy if-then rules. The fuzzy clustering with pairs of prototypes is applied to establish rules parameters values. Classification quality and computing time obtained for six benchmark databases is compared with the Lagrangian SVM method.
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
Duda, R., Hart, P., Stork, D.: Pattern classification. John Wiley&Sons, New York (2001)
Leski, J.: An ε-margin nonlinear classifier based on if-then rules. IEEE Trans. Systems, Man and Cybernetics - Part B: Cybernetics 34(1), 68–76 (2004)
Leski, J.: Neuro-fuzzy systems. WNT, Warszawa (2008) (in Polish)
Leski, J.: Iteratively reweighted least squares classifier and its ℓ2- and ℓ1-regularized kernel versions. Bull. Pol. Ac.: Tech. 58(1), 171–182 (2010)
Leski, J., Jezewski, M.: Clustering algorithms for classification methods. Journal of Medical Informatics and Technologies 20, 11–18 (2012)
Mangasarian, O., Musicant, D.: Lagrangian support vector machines. Jou. Mach. Learn. Res. 1(1), 161–177 (2001)
Ripley, B.: Pattern recognition and neural networks. Cambridge University Press, Cambridge (1996)
Tou, J., Gonzalez, R.: Pattern recognition principles. Addison-Wesley, London (1974)
Vapnik, V.: Statistical learning theory. Wiley, New York (1998)
Webb, A.: Statistical pattern recognition. Arnold, London (1999)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Jezewski, M., Leski, J.M. (2013). Nonlinear Extension of the IRLS Classifier Using Clustering with Pairs of Prototypes. In: Burduk, R., Jackowski, K., Kurzynski, M., Wozniak, M., Zolnierek, A. (eds) Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013. Advances in Intelligent Systems and Computing, vol 226. Springer, Heidelberg. https://doi.org/10.1007/978-3-319-00969-8_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-00969-8_12
Publisher Name: Springer, Heidelberg
Print ISBN: 978-3-319-00968-1
Online ISBN: 978-3-319-00969-8
eBook Packages: EngineeringEngineering (R0)