Experimental identification of hard data sets for classification and feature selection methods with insights on method selection.
Cuiju LuanGuozhu DongPublished in: Data Knowl. Eng. (2018)
Keyphrases
- synthetic data
- classification accuracy
- benchmark data sets
- classification method
- high accuracy
- data sets
- objective function
- cross validation
- preprocessing
- support vector machine svm
- classification scheme
- significant improvement
- pattern classification
- selection strategy
- probabilistic model
- machine learning algorithms
- machine learning
- classification algorithm
- support vector machine
- similarity measure
- decision rules
- machine learning methods
- classification process
- detection method
- feature set
- cost function
- feature vectors
- pattern recognition
- training samples
- unsupervised learning
- text classification
- dynamic programming
- training set
- support vector