样本属性重要度的支持向量机方法

支持向量机(SVM)是一种新的机器学习方法,已经广泛应用于模式识别和函数估计等问题中.针对现有的加权支持向量机(WSVM)和模糊支持向量机(FSVM)只考虑样本重要性而没有考虑属性重要性对分类结果的影响的缺陷,提出了基于样本属性重要度的支持向量机方法,该方法首先利用信息论中的信息增益技术计算各个样本特征属性对分类属性的重要度,然后对所有样本的同一特征属性的值分别用对应的属性重要度进行加权,最后所得数据集用于训练和测试SVM.数值实验的结果表明,该方法提高了分类器的分类精度.

Support Vector Machine Based on Weightiness of Sample Attribute

As a new machine learning method,support vector machine(SVM) has been applied in many research fields,such as pattern recognition and function estimate.There is a shortcoming in Weighted SVM and Fuzzy SVM,which takes the weightiness of sample into account but neglects the influence of weightiness of attribute on classification result.In this paper we propose a SVM approach based on the weightiness of attribute,which firstly calculates the weightiness of the feature attributes corresponds to the classification attribute by applying the information gain technology,then calculates the multiplication between the value of the same feature attribute and the corresponding weightiness of attribute for all samples, finally the samples are used for SVM training and testing.The experimental results show that the approach can improve the classification precision of the classifier.