基于模糊分割的支持向量机分类器

Fuzzy partition based Support Vector Machine classifier

支持向量机算法对噪声点和异常点是敏感的,为了解决这个问题,人们提出了模糊支持向量机,但其中的模糊隶属度函数需要人为设置。提出基于模糊分割的支持向量机分类器。在该算法中,首先根据聚类有效性用模糊c-均值聚类分别对训练集中的正负类数据聚类;然后,选择距离最近的c个聚类对构成c个二分类问题;最后,对c个二分类器用加权平均策略得到最终分类结果。为了验证所提算法的有效性,对三个UCI数据集进行了数值实验,结果表明,该算法能有效提高带噪声点和异常点数据集分类的预测精度。

Support Vector Machine（SVM） is sensitive to noises and outliers.To overcome this drawback,Fuzzy Support Vector Machine（FSVM） is developed,in which the fuzzy membership function is set subjectively.In this study,a Fuzzy Partition based Support Vector machine Classifier（FP-SVC） is presented to deal with the classification problems with noises or outliers.In the proposed algorithm,fuzzy c-means clustering is firstly adopted to cluster each of two classes from the training set based on the clustering validity;Then c nearest pairs of clusters are searched,which form c binary classification problems;Finally,the weighted average strategy is applied to these c binary classifiers for inducing the final classification results.The experiments are conducted on three benchmarking UCI datasets for testing the generalization performance of FP-SVC.The experimental results show that FP-SVC is valid for improving the predicting accuracy of the classification problems with noises or outliers.