An efficient feature selection technique for clustering based on a new measure of feature importance.
Saptarsi GoswamiAmlan ChakrabartiBasabi ChakrabortyPublished in: J. Intell. Fuzzy Syst. (2017)
Keyphrases
- feature importance
- feature selection
- random forest
- text categorization
- mutual information
- feature set
- dimensionality reduction
- classification accuracy
- feature selection algorithms
- semi supervised
- information gain
- multi class
- support vector machine
- feature extraction
- relevance feedback
- model selection
- microarray data
- feature subset
- classification models
- irrelevant features
- selected features
- data sets
- naive bayes
- text classification
- nearest neighbor
- feature space