Cost-Sensitive Feature Selection on Heterogeneous Data.
Wenbin QianWenhao ShuJun YangYinglong WangPublished in: PAKDD (2) (2015)
Keyphrases
- cost sensitive
- heterogeneous data
- feature selection
- multi class
- naive bayes
- misclassification costs
- data integration
- class imbalance
- support vector machine
- cost sensitive learning
- cost sensitive classification
- databases
- data management
- data sources
- class distribution
- metadata
- text categorization
- complex data
- classification accuracy
- active learning
- machine learning
- support vector
- decision trees
- text classification
- feature set
- high dimensionality
- dimensionality reduction
- database systems
- feature extraction
- knn
- web data
- feature space
- search engine
- high dimensional
- feature subset
- rough sets
- information sources
- model selection