Feature Selection for Partially Labeled Data Based on Neighborhood Granulation Measures.
Bingyang LiJianmei XiaoXihuai WangPublished in: IEEE Access (2019)
Keyphrases
- feature selection
- partially labeled data
- semi supervised
- loss function
- active learning
- support vector machine
- co training
- text categorization
- support vector
- text classification
- feature extraction
- rough sets
- multi class
- classification accuracy
- machine learning
- higher order
- semi supervised learning
- unlabeled data
- feature space
- supervised learning
- maximum likelihood
- model selection
- classification models
- three dimensional