A novel embedded min-max approach for feature selection in nonlinear Support Vector Machine classification.
Asunción Jiménez-CorderoJuan Miguel MoralesSalvador PinedaPublished in: Eur. J. Oper. Res. (2021)
Keyphrases
- min max
- support vector machine classification
- feature selection
- multiobjective optimization
- max min
- mutual information
- text categorization
- privacy preserving
- support vector
- high dimension
- feature set
- text classification
- model selection
- feature selection algorithms
- multi task
- machine learning
- neural network
- embedded systems
- selected features
- classification accuracy
- irrelevant features
- similarity measure
- feature subset
- dimensionality reduction
- denoising
- knn
- evolutionary algorithm