SMOTE-RSB *: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data-sets using SMOTE and rough sets theory.
Enislay RamentolYaile CaballeroRafael BelloFrancisco HerreraPublished in: Knowl. Inf. Syst. (2012)
Keyphrases
- imbalanced data sets
- class imbalance
- rough sets theory
- preprocessing
- minority class
- class distribution
- majority class
- active learning
- rough sets
- imbalanced data
- cost sensitive learning
- cost sensitive
- benchmark data sets
- decision rules
- sampling methods
- imbalanced datasets
- rare events
- concept drift
- high dimensionality
- nearest neighbour
- rough set theory
- concept learning
- feature selection
- data sets
- data generation
- decision boundary
- microarray
- test set
- dimensionality reduction
- training data
- feature extraction