一种面向不平衡数据的结构化SVM集成分类器  

An Ensemble Classifier Based on Structural Support Vector Machine for Imbalanced Data

作　　者：袁兴梅[1,2] 杨明[1] 杨杨[3] 

机构地区：[1]南京师范大学计算机科学与技术学院,南京210023 [2]南京工程学院信息化建设与管理办公室,南京211167 [3]南京师范大学强化培养学院,南京210023

出　　处：《模式识别与人工智能》2013年第3期315-320,共6页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.60873176;40871176;61003116);江苏省自然科学基金重点项目(No.BK2011005);江苏省自然科学基金项目(No.BK2011782;BK2010263);南京工程学院青年基金项目(No.QKJB2011028)资助

摘　　要：为改进面向不平衡数据的SVM分类器性能,以结构化SVM为基础,提出一种基于代价敏感的结构化支持向量机集成分类器模型.该模型首先通过训练样本的聚类,得到隐含在数据中的结构信息,并对样本进行初始加权.运用Ada Boost策略对各样本的权重进行动态调整,适当增大少数类样本的权重,使小类中误分的样本代价增大,以此来改进不平衡数据的分类性能.实验结果表明,该算法可有效提高不平衡数据的分类性能.To improve the performance of Support Vector Machine （SVM） classifier for imbalanced data, an ensemble classifier model based on structural SVM is introduced by incorporating cost-sensitive strategy. In the proposed classifier model, the training data is partitioned into several group by Ward hierarchical clustering algorithm, the structure information hidden in data is obtained, and the weight of,every sample is initialized by using the weight of each sample prior knowledge hidden in clusters. Furthermore, employing AdaBoost strategy, the is dynamically adjusted effectively, and the weights of minority class samples are relatively increased. Hence, the cost of the misclassified positive samples is also increased for improving the classification accuracy of positive samples（ minority class samples）. The experimental results show that the proposed model effectively improves the classification performance of the imbalanced data.

关 键 词：不平衡数据 结构化支持向量机(StASVM) 代价敏感 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]