一种改进的模糊多类支持向量机算法

A Improved Algorithms of Fuzzy Support Vector Machines

支持向量机是基于统计学习理论的新一代机器学习技术;由于使用结构风险最小化原则代替经验风险最小化原则,使它较好地解决了小样本情况下的学习问题;针对目前模糊支持向量机方法中,一般使用样本与类中心之间的距离关系构建隶属度函数的不足,以统计学习理论和支持向量机为基础,提出了一种改进的模糊多类支持向量机方法,它是在全局优化分类的基础上,引入模糊隶属函数,然后利用改进的序列最小最优化算法求解模糊多类支持向量机,实验结果显示运行时间减少了,方法是可行的和有效的。

Support Vector Machines（SVM）are a new-generation machine learning technique based on the statistical learning theory.They can solve small-sample learning problems better by using Structural Risk Minimization in place of Experiential Risk Minimization.This paper based on statistic learning theory（SLT） and support vector machine（SVM）.Aimed at the defect in the method of fuzzy support vector machine where the membership function was constructed by means of distance relation between the sample and cluster center,extend to the Multiclass Support Vector Machines method,and with the fuzzy membership of data samples of a given class,to improve classification performance with high generalization capability.We used the improved Sequential Minimal Optimization to solve fuzzy multicategory support vector machine.The experimental results show that the computational load be reduced greatly and with high generalization capability.