Empirical Similarity for Absent Data Generation in Imbalanced Classification.
Arash PourhabibPublished in: CoRR (2015)
Keyphrases
- data generation
- imbalanced data sets
- machine learning
- classification accuracy
- support vector
- feature selection
- decision trees
- support vector machine
- active learning
- feature extraction
- similarity measure
- feature space
- data sets
- imbalanced datasets
- class imbalance
- classification algorithm
- real time
- training set
- small number
- text classification
- training samples
- class labels
- data structure
- class distribution
- co training
- feature vectors
- learning environment