在一般典型的分類(Classification)問題中，通常只有一些模糊且攏統的資訊，以及一些來自於分類樣本的特定子集合，所以必須利用這些現有的資訊，尋找有效的方法設計一些正確的分類器。
在現有模糊支持向量機中，許多研究求解前須事先利用測量技術以獲得模糊資料的訊息；有些的求解方法則是過於複雜，因而降低了演算法的可行性。本研究則提出一種新的且有效率的模糊支持向量機(Fuzzy Support Vector Machines：FSVMs)，該決策方案直接對原始的資源量做推廣性的容忍技術，因此克服採集額外資訊的困難。
在理論建構上，合理的使用模糊不等式來表達模糊來源的線性規劃問題，這提供了加入容忍到限制式以滿足與擴大實務性的非線性系統成為可能。為了驗證這個分類器，本研究從UCI資料庫中解決幾個真實世界中的分類問題。實驗結果顯示一個具模糊限制式之模糊支持向量機能改善原支持向量機性能且能達到較低得測試誤差率。

Classification approaches usually present the poor generalizeation performance with an apparent class imbalance problem. There are many researches reported in the literature that the characteristics of data sets have strongly influenced the performance of different classifiers. Unfortunately, it is necessary to get the information of fuzzy datasets by some methods in advance. These methods are too complicated to increase the utility of this algorithm. There is a latest and more efficient Fuzzy Support Vector Machines reported in this study. In addition, it uses an extensively tolerance technique to raw data directly, so as to overcome the difficulty of collecting extra information. According to the structure of the theorem, it is reasonable to use fuzzy inequalities as the fuzzy resource programming and thus adding tolerance into the constraints to satisfy and extend the reality of nonlinear programming is possible. For validating this classifier, seven true cases from UCI database are solved and these results obviously show that fuzzy membership function can improve the performance of traditional SVMs and obtain the lower rate of classification error.

[1]V. N. Vapnik, “The Nature of Statistical Learning Theory, “ Springer-Verlag, Berlin Heidelberg, New York, 1995.
[2]V. N. Vapnik, “An Overview of Statistical Learning Theory,” IEEE Transaction on Neural Networks, Vol. 10, pp 988-999, 1999.
[3]V. N. Vapnik, Statistical Learning Theory, Wiley, New York, 1998.
[4]C. F. Lin and S. D. Wang, “Fuzzy support vector machines, ” IEEE Transaction on Neural Networks, Vol. 13, pp 467-471, 2002.
[5]D. M. J. Tax, and R. P. W. Duin, ”Characterizing one-class datasets.”In Proceedings of the 16th Annual Symposium of the Pattern Recognition Association of South Africa, , 2005,pp. 21-26.
[6]R. C. Prati, G. E. A. P. A. Batista, and M. C. Monard, Class imbalances versus class overlapping: An analysis of a learning system behavior. In MICAI, 2004, pp. 312-321.
[7]C. C. Hsu, M. H. Fan, S. H. Chang, H. Y. Chung,. Fuzzy support vector machines with the uncertainty of parameter C. Expert Systems with Applications (2008).
[8]Y. J. Lai and C.L. Hwang, Fuzzy Mathematical Programming. Springer-Verlag, Berlin Heidelberg, New York, 1992.
[9]C. R. Bector and S. Chandra, Fuzzy Mathematical Programming and Fuzzy Matrix Games, Springer-Verlag, Berlin Heidelberg, New York, 2005.
[10]L. A. Zadeh,“Fuzzy Sets,＂Information and Control, Vol. 8, No.1, 1965, pp. 338-353.
[11]H. J. Zimmermann, ＂Fuzzy programming and linear programming with several objective functions＂, Fuzzy Sets and Systems 1 (1978) 45-55.
[12]R. E. Bellman and L.A. Zadeh, ＂Decision making in a fuzzy environment＂, Management Sciences 17 (1970) B141-B164.
[13]S. M. Guu and Y.K. Wu, ＂Weighted coefficients in two-phase approach for solving the multiple objective programming problems＂, Fuzzy Sets and Systems,85(1997)45-48.
[14]Y. J., Lai and C. L., Hwang, ＂A new approach to some possibility linear programming problem＂, Fuzzy Sets and Systems 35 (1981) 143-150.
[15]B. Werners, ＂Interactive multiple objective programming subject to flexible constraints＂Eur. J. Oper. Res. 31 (1987) 342-349.
[16]B. Werner, ＂An interactive fuzzy programming system＂, Fuzzy Sets and Systems, val.23,pp131-147,1987.
[17]B. Schölkopf and A. J. Smola, Learning with Kernel: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press, Cambridge, MA, 2001, pp. 25−60.
[18]B. Schölkopf and A. J. Smola, K. R. Müller, “Nonlinear Component Analysis as a Kernel Eigenvalue Problem,” Neural Computing, Vol. 10, No. 5, pp. 1299−1319, 1998.
[19]M. F. Han, “Fuzzy Support Vector Machines with the Uncertainty of Parameter C,” Master Thesis, Department of Electrical Engineering, National Central University, Taiwan, 2008.
[20]T. Hastie, R. Tibshirani, and J. Friendman, The Element of Statistical Learning: Data Mining, Inference and Prediction, Springer−Verlag, Berlin Heidelberg New York, pp. 214−217, 2001.
[21]L. Breiman, Bias, Variance and Arcing Classifiers. Technical Report 460, Berkeley, CA: Statistics Department, University of California at Berkeley, 1996.
[22]P. M. Murphy, UCI−Benchmark Repository of Artificial and Real Data Sets, http://www.ics.uci.edu/~mlearn, University of California Irvine, CA, 1995.
[23]P. Vlachos, and M. Meyer, StatLib, http://lib.stat.cmu.edu/, Department of Statistics, Carnegie Mellon University, 1989.
[24]J. S. Taylor, “An Extension on “Statistical Comparisons of Classifiers over Multiple Data Sets” for all Pairwise Comparisons,” Journal of Machine Learning Research 9, pp. 2677-2694, Aug. 2008.
[25]D. Sch, “Statistical Comparisons of Classifiers over Multiple Data Sets,” Journal of Machine Learning Research 7, pp. 1-30, Jan. 2006.