A cost-sensitive ensemble method for class-imbalanced datasets (Q369767): Difference between revisions
From MaRDI portal
Created a new Item |
Changed an Item |
||
Property / author | |||
Property / author: Yong Zhang / rank | |||
Normal rank | |||
Property / review text | |||
Summary: In imbalanced learning methods, resampling methods modify an imbalanced dataset to form a balanced dataset. Balanced data sets perform better than imbalanced datasets for many base classifiers. This paper proposes a cost-sensitive ensemble method based on cost-sensitive support vector machine (SVM), and query-by-committee (QBC) to solve imbalanced data classification. The proposed method first divides the majority-class dataset into several subdatasets according to the proportion of imbalanced samples and trains subclassifiers using the AdaBoost method. Then, the proposed method generates candidate training samples by the QBC active learning method and uses cost-sensitive SVMs to learn the training samples. By using 5 class-imbalanced datasets, experimental results show that the proposed method has higher area under ROC curve (AUC), F-measure, and G-mean than many existing class-imbalanced learning methods. | |||
Property / review text: Summary: In imbalanced learning methods, resampling methods modify an imbalanced dataset to form a balanced dataset. Balanced data sets perform better than imbalanced datasets for many base classifiers. This paper proposes a cost-sensitive ensemble method based on cost-sensitive support vector machine (SVM), and query-by-committee (QBC) to solve imbalanced data classification. The proposed method first divides the majority-class dataset into several subdatasets according to the proportion of imbalanced samples and trains subclassifiers using the AdaBoost method. Then, the proposed method generates candidate training samples by the QBC active learning method and uses cost-sensitive SVMs to learn the training samples. By using 5 class-imbalanced datasets, experimental results show that the proposed method has higher area under ROC curve (AUC), F-measure, and G-mean than many existing class-imbalanced learning methods. / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 68T05 / rank | |||
Normal rank | |||
Property / zbMATH DE Number | |||
Property / zbMATH DE Number: 6209205 / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
cost-sensitive ensemble method | |||
Property / zbMATH Keywords: cost-sensitive ensemble method / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
cost-sensitive support vector machine | |||
Property / zbMATH Keywords: cost-sensitive support vector machine / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
query-by-committee | |||
Property / zbMATH Keywords: query-by-committee / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
imbalanced learning | |||
Property / zbMATH Keywords: imbalanced learning / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
imbalanced dataset | |||
Property / zbMATH Keywords: imbalanced dataset / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
AdaBoost | |||
Property / zbMATH Keywords: AdaBoost / rank | |||
Normal rank |
Revision as of 13:32, 28 June 2023
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | A cost-sensitive ensemble method for class-imbalanced datasets |
scientific article |
Statements
A cost-sensitive ensemble method for class-imbalanced datasets (English)
0 references
19 September 2013
0 references
Summary: In imbalanced learning methods, resampling methods modify an imbalanced dataset to form a balanced dataset. Balanced data sets perform better than imbalanced datasets for many base classifiers. This paper proposes a cost-sensitive ensemble method based on cost-sensitive support vector machine (SVM), and query-by-committee (QBC) to solve imbalanced data classification. The proposed method first divides the majority-class dataset into several subdatasets according to the proportion of imbalanced samples and trains subclassifiers using the AdaBoost method. Then, the proposed method generates candidate training samples by the QBC active learning method and uses cost-sensitive SVMs to learn the training samples. By using 5 class-imbalanced datasets, experimental results show that the proposed method has higher area under ROC curve (AUC), F-measure, and G-mean than many existing class-imbalanced learning methods.
0 references
cost-sensitive ensemble method
0 references
cost-sensitive support vector machine
0 references
query-by-committee
0 references
imbalanced learning
0 references
imbalanced dataset
0 references
AdaBoost
0 references