Ensembling perturbation-based oversamplers for imbalanced datasets.
Jianjun ZhangTing WangWing W. Y. NgWitold PedryczPublished in: Neurocomputing (2022)
Keyphrases
- imbalanced datasets
- cost sensitive learning
- class distribution
- learning from imbalanced data
- ensemble methods
- decision trees
- base classifiers
- class imbalance
- sampling methods
- training dataset
- imbalanced data
- feature selection algorithms
- active learning
- misclassification costs
- binary classification
- learning algorithm
- training set
- learning process
- rule extraction
- training samples
- random forest
- multi class
- rough sets
- cost sensitive
- prediction accuracy