Feature selection by analyzing class regions approximated by ellipsoids.
Shigeo AbeRuck ThawonmasYoshiki KobayashiPublished in: IEEE Trans. Syst. Man Cybern. Part C (1998)
Keyphrases
- feature selection
- text categorization
- machine learning
- finite number
- support vector machine
- classification accuracy
- information gain
- mutual information
- method for feature selection
- unsupervised feature selection
- unsupervised learning
- feature set
- support vector
- image segmentation
- model selection
- linear combination
- class labels
- image regions
- region of interest
- image features
- knn
- feature weighting
- irrelevant features