A simple and efficient filter feature selection method via document-term matrix unitization.
Qing LiShuai ZhaoTengjiao HeJinming WenPublished in: Pattern Recognit. Lett. (2024)
Keyphrases
- feature selection
- computationally efficient
- mutual information
- support vector machine
- information retrieval systems
- edge detection
- similarity measure
- feature space
- cost function
- classification accuracy
- information retrieval
- preprocessing
- feature set
- keywords
- feature extraction
- document collections
- classification method
- auto correlation