An improved data characterization method and its application in classification algorithm recommendation.
Guangtao WangQinbao SongXiaoyan ZhuPublished in: Appl. Intell. (2015)
Keyphrases
- classification algorithm
- synthetic data
- input data
- data sets
- test data
- classification method
- training phase
- missing data
- support vector machine
- k nearest neighbor
- database
- data analysis
- classifier ensemble
- training samples
- knn
- training data
- accurate classification
- training set
- naive bayes
- object recognition
- input features
- multi label classification
- real world
- data mining
- data distribution
- similarity measure
- support vector machine svm
- text classification
- probabilistic model
- small number