Particle swarm optimization-deep belief network-based rare class prediction model for highly class imbalance problem.
Jaekwon KimYoungshin HanJong Sik LeePublished in: Concurr. Comput. Pract. Exp. (2017)
Keyphrases
- prediction model
- rare class
- class imbalance
- imbalanced datasets
- imbalanced class distribution
- majority class
- rare events
- class distribution
- active learning
- regression model
- cost sensitive learning
- minority class
- sampling methods
- cost sensitive
- high dimensionality
- concept drift
- imbalanced data
- emerging patterns
- feature selection
- neural network
- small disjuncts
- ensemble methods
- training data
- decision trees
- test set
- attribute selection
- nearest neighbour
- misclassification costs
- ensemble learning
- benchmark datasets
- prediction accuracy
- error rate
- bayesian networks