Feature Selection for the Classification of Large Document Collections.
Janez BrankDunja MladenicMarko GrobelnikNatasa Milic-FraylingPublished in: J. Univers. Comput. Sci. (2008)
Keyphrases
- feature selection
- classification accuracy
- feature set
- feature space
- classification models
- feature extraction
- support vector machine
- support vector
- text classification
- model selection
- machine learning
- high dimensionality
- method for feature selection
- machine learning algorithms
- automatic classification
- feature selection algorithms
- text categorization
- dimension reduction
- cross validation
- unsupervised learning
- feature selection and classification
- redundant features
- small sample
- web page classification
- classification performances
- fold cross validation
- information gain
- feature subset selection
- microarray data
- feature subset
- classification method
- class labels
- support vector machine svm
- decision trees
- mutual information
- dimensionality reduction
- multi class
- training data
- irrelevant features
- select relevant features
- selecting relevant features
- support vector classification
- feature level fusion
- pattern recognition
- preprocessing
- data pre processing
- unsupervised feature selection
- feature vectors
- terms of classification accuracy
- pattern classification
- accurate classification
- feature ranking
- bayesian classifier
- eeg signals
- image classification
- data sets