【摘要】 基于分类的支撑向量机可以通过训练,找到2类训练点的分界面.一般2类点都是确定的,但是,在实际情况中,训练点不可能很确定的属于某一集合(具有模糊性),使得每个训练点包含的信息量也不同,传统的支撑向量机算法无法处理这类问题.给每个训练点定义了点模糊度概念,利用点模糊度来度量它包含的分类信息,由此确定点在训练中所占的权重,使包含不同信息量的训练点,在训练中起不同作用,从而得到了一种有效处理包含模糊训练点的算法.更多还原

【Abstract】 A support vector machine(SVM) based on classification learns the decision surface from two distinct classes of the input points. And each point is fully assigned to one of the two classes, but in many applications, a few points are not sure assigned to one of the two classes. A fuzzy degree based on fuzzy membership to each input point is applied and reformulate the SVMs such that different input points can make different constributions to the learning of decision surface.更多还原