An improved and random synthetic minority oversampling technique for imbalanced data.
Guoliang WeiWeimeng MuYan SongJun DouPublished in: Knowl. Based Syst. (2022)
Keyphrases
- imbalanced data
- minority class
- majority class
- class imbalance
- class distribution
- imbalanced datasets
- classification error
- decision boundary
- nearest neighbour
- cost sensitive learning
- highly imbalanced
- class imbalanced
- sampling methods
- support vector machine
- training dataset
- original data
- imbalanced class distribution
- ensemble learning
- feature selection
- training set
- linear regression
- random forest
- high dimensionality
- misclassification costs
- test set
- training samples
- active learning
- hyperplane
- training data
- ensemble methods
- cost sensitive
- machine learning methods
- class labels
- multi class
- machine learning