Improving performance of classification on incomplete data using feature selection and clustering.
Cao Truong TranMengjie ZhangPeter AndreaeBing XueLam Thu BuiPublished in: Appl. Soft Comput. (2018)
Keyphrases
- incomplete data
- feature selection
- irrelevant attributes
- bayes classifier
- high dimensionality
- classification accuracy
- text classification
- unsupervised learning
- support vector machine
- missing data
- support vector
- text categorization
- feature space
- incomplete data sets
- missing values
- classification models
- data pre processing
- model selection
- bayesian networks
- clustering algorithm
- unsupervised feature selection
- class separability
- learning bayesian networks
- feature extraction
- multiple imputation
- feature subset
- feature set
- high dimensional
- em algorithm
- classification rules
- discriminative features
- machine learning
- feature selection algorithms
- feature reduction
- density estimation
- svm classifier
- multi class
- k means
- classification algorithm
- high dimensional data
- naive bayes
- knn
- models built
- feature vectors
- training set
- pattern recognition
- decision trees
- image processing
- missing attribute values
- data sets