A hybrid method to face class overlap and class imbalance on neural networks and multi-class scenarios.
Roberto AlejoRosa Maria ValdovinosVicente GarcíaJ. H. Pacheco-SanchezPublished in: Pattern Recognit. Lett. (2013)
Keyphrases
- multi class problems
- hybrid method
- multi class
- class imbalance
- cost sensitive
- binary classification problems
- multi class classification
- support vector machine
- neural network
- binary classification
- minority class
- multiple classes
- multiclass classification
- active learning
- cost sensitive learning
- class distribution
- feature selection
- imbalanced datasets
- sampling methods
- high dimensionality
- pattern recognition
- naive bayes
- concept drift
- binary classifiers
- pairwise
- data streams
- decision trees
- learning algorithm
- base classifiers
- data distribution
- benchmark datasets
- k nearest neighbor
- face images
- supervised learning
- learning process