Abstract
This paper presents a novel fuzzy compensation multi-class support vector machine (FCM-SVM) to improve the outlier and noise sensitivity problem of traditional support vector machine (SVM) for multi-class data classification. The basic idea is to give the dual effects to penalty term through treating every data point as both positive and negative classes, but with different memberships. We fuzzify penalty term, compensate weight to classification, reconstruct the optimization problem and its restrictions, reconstruct {Lagrangian} formula, and present the theoretic deduction. By this way the new fuzzy compensation multi-class support vector machine is expected to have more generalization ability while preserving the merit of insensitive to outliers. Experimental results on benchmark data set and real data set show that the proposed method reduces the effect of noise data and yields higher classification rate than traditional multi-class SVM does.
Similar content being viewed by others
References
Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. The Fifth Annual Workshop on computational Learning Theory, pp 144–152
Cortes C, Vapnik VN (1995) Support vector networks. Mach Learn 20(3):273–297
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York
Muller KR, Mike S, Ratsch G et al (2001) An introduction to kernel based learning algorithms. IEEE Trans Neur Netw 12(2):181–201
Schölkopf B, Smola AJ (2002) Learning with Kernels. MIT Press, Cambridge, MA
Burges JC, Schölkopf B (1997) Improving the accuracy and speed of support vector learning machines. Advances in neural information processing systems. MIT Press, Cambridge, MA, pp 375–381
Osuna E, Freund R, Girosi F (1997) Training support vector machines: an application to face detection. In IEEE Conference on Computer Vision and Pattern Recognition, pp 130–136
Schmidt M (1996) Identifying speaker with support vector networks. In Interface ’96 Proceedings, Sydney
Conforti D, Guido R (2005) Kernel-based support vector machine classifiers for early detection of myocardial infarction. Optim Meth Softw 20(2):395–407
Gilardi N, Kanevski M, Maignan M et al (1997) Environmental and pollution spatial data classification with support vector machines and geostatistics. ACAI99, Greece, pp 43–51
Brown M, Grundy W, Lin D et al (2000) Knowledge-base analysis of microarray gene expression data using support vector machines. PNAS 97(1):262–267
Xu JH, Zhang XG, Li YD (2004) Advances in support vector machines. Contr Dec (in Chinese) 19(5):481–484
Platt JC, Cristianini N, Shawe-Taylor J (2000) Large margin DAG’s for multiclass classification. Advances in neural information processing systems. MIT Press, Cambridge, MA, pp 547–553
Weston J, Watkins C (1998) Multi-class support vector machines. Department of Computer Science, Royal Holloway University of London Technical Report, SD2TR298204
Platt JC (1999) Fast training of support vector machines using sequential minimal optimization. Advances in Kernel methods-support vector learning. MIT Press, Cambridge, MA, pp 185–208
Hsu CW, Lin CJ (2002) A comparison of methods for multi-class support vector machines. IEEE Trans Neur Netw 13(2):415–425
Suykens J, Vandewalle J (1999) Least squares support vector machines classifiers. Neur Process Lett 9(3):293–300
Schölkopf B, Smola AJ, Williamson RC et al (2000) New support vector algorithms. Neur Comput 12(5):1207–1245
Huang HP, Liu YH (2002) Fuzzy support vector machines for pattern recognition and data mining. Int’l J Fuzzy Syst 4(3):826–835
Inoue T, Abe S (2001) Fuzzy support vector machines for pattern classification. In Proceedings of International Joint Conference on Neural Networks, pp 1449–1454
Lin CF, Wang SD (2002) Fuzzy support vector machine. IEEE Trans Neur Netw 13(2):464–471
Sun ZH, Sun YX (2003) Fuzzy support vector machine for regression estimation. IEEE Intl Conf Syst Man Cybern 4:3336–3341
Hong DH, Hwang C (2003) Support vector fuzzy regression machines. Fuzzy Sets Syst 138(2):271–281
Kecman V (2001) Learning and soft computing, support vector machines, neural networks and fuzzy logic models. The MIT Press, Cambridge, MA
Xie ZX, Hu QH, Yu D (2005) Fuzzy output support vector machines for classification. In Proceedings of the International Conference on Natural Computation, pp 1190–1197
Guyon I, Matić N, Vapnik VN (1996) Discovering information patterns and data cleaning. MIT Press, Cambridge, MA
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, Y., Chi, Zx., Liu, Xd. et al. A novel fuzzy compensation multi-class support vector machine. Appl Intell 27, 21–28 (2007). https://doi.org/10.1007/s10489-006-0027-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-006-0027-x