摘要
传统的Bagging分类方法对不平衡数据集进行分类时,虽然能够达到很高的分类精度,但是对其中少数类的分类准确率不高。为提高其对少数类数据的分类精度,利用SMOTE算法对样例集中的少数类样例进行加工,在Bagging算法中根据类值对各个样例的权重进行调整。混淆矩阵和ROC曲线表明改进算法达到了既能保证整体的分类准确率,又能提高少数类分类精度的目的。
The traditional Bagging method can achieve a high accuracy for imbalance data,but gets low accuracy of the minority class samples.In order to improve the accuracy of the minority class samples with Bagging algorithm,the paper proposes a two-step approach.Firstly,SMOTE algorithm is used to increase the number of the minority class samples and then adjusts the weight for each instance in Bagging according to its class value.Results of the confusing matrix and the ROC show the approach improves not only the classification performance of data as a whole but also that of the minority part.
出处
《计算机工程与应用》
CSCD
北大核心
2010年第30期40-42,共3页
Computer Engineering and Applications
基金
山东省高新技术自主创新工程专项计划(No.2007ZZ17)
山东省自然科学基金No.Y2007G16
山东省科技攻关计划No.2008GG10001015
山东省电子发展基金(No.2008B0026)~~