Determining threshold value on information gain feature selection to increase speed and prediction accuracy of random forest.
Maria Irmina PrasetiyowatiNur Ulfa MaulideviKridanto SurendroPublished in: J. Big Data (2021)
Keyphrases
- information gain
- prediction accuracy
- random forest
- ensemble methods
- decision trees
- feature selection
- feature set
- text categorization
- chi squared
- mutual information
- fold cross validation
- improve the prediction accuracy
- ensemble learning
- multi label
- naive bayes
- selected features
- feature subset
- base classifiers
- training set
- feature ranking
- feature extraction
- ensemble classifier
- knn
- feature space
- logistic regression
- machine learning
- document frequency
- correlation coefficient
- image processing
- correlation based feature selection
- machine learning algorithms
- kernel function
- graph cuts
- text classification
- multi class
- support vector machine
- classification accuracy
- artificial neural networks
- support vector
- training data
- information retrieval