基于模糊支持向量机与决策树的文本分类器

针对模糊支持向量机在文本分类应用中的隶属度函数确定问题，提出了一种基于模糊支持向量机与决策树的文本分类器的构建方法。该方法不仅考虑了样本与类中心之间的关系，还根据传统支持向量机中包含支持向量且平行于分类面的平面构建切球,来确定类中各个样本之间的关系，由样本点与球的位置关系计算其隶属度，可以合理地区分有效样本和噪音、孤立点样本。并与决策树方法相结合，实现多类分类。实验结果表明,该方法具有良好的分类效果。

Text classifier based on fuzzy support vector machine and decision tree

For determining the membership function in text classification with fuzzy support vector machine, a construction approach of text classifier based on fuzzy support vector machine and decision tree was proposed. The relationship between the sample and its cluster center was considered and the tangent sphere was constructed by the hyperplane that contained the support vectors and paralleled the classification hyperplane in traditional support vector machine, so to further determine the relation of all samples in the class. The membership of one sample to a class could be computed by the location of the sample in the sphere, so the efficient samples, noises and outliers could be distinguished rationally. Integrating the decision tree method, the classification of multi-classes was realized. The experimental results demonstrate the method has preferable classification effect.