结合代价敏感及多数类分解的非平衡分类  

Imbalance classification combining cost-sensitive and majority class decomposition.

作　　者：蹇涛[1] 李宏[1] 郭跃健[1] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083

出　　处：《计算机工程与应用》2011年第1期150-153,共4页Computer Engineering and Applications

基　　金：湖南省自然科学基金No.10JJ6094~~

摘　　要：提出了一种结合代价敏感及多数类分解的算法CLCC(Classification using Local Clustering with Cost-sensitive)。CLCC通过在多数类中使用局部聚类使得类别之间达到平衡,再引入代价敏感使得整体和少数类的分类错误率在迭代学习过程中不断地降低,提高了少数类的精度以及降低了整体的分类代价。实验结果验证了该算法在处理非平衡类问题时比传统算法要优越。This paper proposes an improved method called CLCC（Classification using Local Clustering with Cost-sensitive） which combines cost-sensitive and majority class decomposition.Using local cluster in the majority class can make a balance between the majority class and the minority class.And the introduction of cost-sensitive to the iterative learning process makes large improvements of the misclassification ratio of the minority class and dataset.Thus,the accuracy of the minority class is enhanced while the classification cost is decreased.The experimental results confirm that this algorithm is superior to the traditional algorithms as for dealing with the imbalanced problem.

关 键 词：非平衡类 代价敏感 K-均值聚类 过采样 ADABOOST算法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]