A priori synthetic over-sampling methods for increasing classification sensitivity in imbalanced data sets.
William A. RiveraPetros XanthopoulosPublished in: Expert Syst. Appl. (2016)
Keyphrases
- imbalanced data sets
- class imbalance
- sampling methods
- imbalanced data
- minority class
- class distribution
- imbalanced datasets
- active learning
- decision trees
- sampling algorithm
- text classification
- machine learning algorithms
- benchmark datasets
- random sampling
- feature selection
- roc curve
- classification algorithm
- concept drift
- class labels
- classification accuracy
- classification error
- ensemble methods
- data sets
- kernel function
- training samples
- cost sensitive learning
- model selection
- support vector machine
- machine learning