A method of feature selection using contribution ratio based on boosting.
Masamitsu TsuchiyaHironobu FujiyoshiPublished in: ICPR (2008)
Keyphrases
- feature selection
- high precision
- cost function
- high accuracy
- probabilistic model
- mutual information
- feature set
- support vector machine
- data sets
- preprocessing
- computational cost
- significant improvement
- classification accuracy
- active learning
- training set
- bayesian networks
- model selection
- support vector machine svm
- clustering method
- detection method
- genetic algorithm