SMOTE-NaN-DE: Addressing the noisy and borderline examples problem in imbalanced classification by natural neighbors and differential evolution.
Junnan LiQingsheng ZhuQuanwang WuZhiyong ZhangYanlu GongZiqing HeFan ZhuPublished in: Knowl. Based Syst. (2021)
Keyphrases
- differential evolution
- imbalanced data sets
- class imbalance
- evolutionary algorithm
- imbalanced data
- imbalanced datasets
- optimization algorithm
- class imbalanced
- differential evolution algorithm
- mutation operator
- test functions
- class distribution
- particle swarm optimization
- particle swarm optimization pso
- convergence speed
- machine learning
- optimization method
- genetic algorithm
- crossover operator
- multi objective optimization
- direct search
- feature selection
- support vector
- parameter optimization
- function optimization problems
- real coded
- decision trees
- minority class
- feature space
- decision boundary
- feature vectors
- multi objective
- data points
- optimization problems
- solving global optimization problems
- neural network
- global optimization problems
- fitness function
- evolutionary strategy
- nearest neighbour
- evolution strategy
- training samples