基于支持向量机的不平衡样本集分类算法  

SVM-BASED IMBALANCED DATA CLASSIFICATION ALGORITHM

作　　者：魏亚利[1] 刘丽[1] 项雪琰 齐绪停 

机构地区：[1]山东师范大学信息科学与工程学院,济南250014

出　　处：《山东师范大学学报（自然科学版）》2016年第2期18-21,共4页Journal of Shandong Normal University(Natural Science)

基　　金：国家自然科学基金资助项目(61170145;61373081);教育部博士点基金资助项目(20113704110001);山东省自然科学基金资助项目(ZR2010FM021);山东省科技攻关计划资助项目(2013GGX10125)

摘　　要：提出基于支持向量机的不平衡样本集分类算法,以支持向量机为基础,利用重采样技术及特征子空间等相关理论,通过分层抽样方法和重采样技术,分别对不平衡数据集的样本底层特征和样本数量进行平衡,在不同数据集上进行实验,实验表明该方法能有效提高不平衡数据分类的准确度.An imbalanced data classification method which is based on the SVM algorithm is proposed in this paper. Resampling technology and feature subspace and other related theories are used and the underlying characteristics of the imbalanced data distribution and the sample size are balanced respectively by using stratified sampling method and resampling technology. Experiments are carried out on different data sets and the results show that the algorithm proposed can improve the accuracy of imbalanced data classification effectively.

关 键 词：支持向量机 分层抽样 重采样技术 不平衡数据分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]