基于密度法的模糊支持向量机

针对支持向量机对训练样本内的噪音和孤立点特别敏感、极大地影响了支持向量机分类性能的弱点，提出了一种基于密度法的模糊支持向量机，在支持向量机中引入样本密度模糊参数，从而减弱了噪音以及孤立点对支持向量机分类的影响．实验结果证明，在抗击孤立点和噪音点的干扰方面，上述方法优于类中心向量方法以及类中心点距离方法，取得了很好的效果．这一方法大大提高了支持向量机分类的泛化能力，从而大大提高了支持向量机的应用范围．

Fuzzy Support Vector Machine Based on Density

A new fuzzy SVM based on density is proposed , which eliminates the disadvantage that the traditional SVM is so sensitive to noises or outliers in the training samples set that SVM's performance of classification is effected to a large extent by noises and outliers. A fuzzy parameter of sample density is introduced into SVM to diminish the effect of outliers and noises. Several simulations demonstrate that this approach has made a better effect on diminishing the effect of noises and outliers than the method of class-center vectors and the method of distance between the point and its class center in the literature. This approach greatly improves the generalization ability of SVM classification and its application area is extended.