Increasing soft classification accuracy through the use of an ensemble of classifiers.
Thi Xuan Huong DoanGiles M. FoodyPublished in: IGARSS (2005)
Keyphrases
- classification accuracy
- training set
- training data
- multiple classifier systems
- naive bayes
- feature selection
- ensemble learning
- support vector
- multiple classifiers
- ensemble classifier
- classifier ensemble
- feature subset
- ensemble pruning
- combining classifiers
- feature set
- base classifiers
- improving classification accuracy
- classification rate
- increase classification accuracy
- accurate classification
- final classification
- majority voting
- ensemble methods
- individual classifiers
- highest accuracy
- decision trees
- imbalanced data
- randomized trees
- neural network
- data sets
- ensemble members
- decision tree classifiers
- high classification accuracy
- classifier combination
- ensemble classification
- feature space
- machine learning
- correctly classified
- training samples
- random forests
- diversity measures
- weighted voting
- multi class
- rule induction algorithm
- supervised learning
- class label noise
- accurate classifiers
- random forest
- classification systems
- cross validation
- feature ranking
- svm classifier
- text categorization
- class labels
- bayesian network classifiers
- prediction accuracy
- class probabilities
- publicly available data sets
- majority vote
- trained classifiers
- machine learning algorithms
- learning algorithm
- bias variance decomposition
- classification algorithm
- mining concept drifting data streams
- text classification