Rough set based feature selection: A Review
Authors:
- 1 May 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 301-306
Abstract
Rough set is a tool with a mathematical foundation to deal with imprecise and imperfect knowledge. It has been widely applied in machine learning, data mining and knowledge discovery. One of the applications of Rough set theory in machine learning is the so-called feature selection especially for classification problems. This is performed by means of finding a reduct set of attributes. Reduct set is a subset of all features which retains classification accuracy as original attributes. Finding a reduct set in decision systems is NP-hard problem which has attracted many researchers to combine different methods with rough set. This paper is a survey of several methods of feature selection using rough set theory.Keywords
This publication has 33 references indexed in Scilit:
- Feature selection with Intelligent Dynamic Swarm and Rough SetExpert Systems with Applications, 2010
- Positive approximation: An accelerator for attribute reduction in rough set theoryArtificial Intelligence, 2010
- Exploring the boundary region of tolerance rough sets for feature selectionPattern Recognition, 2009
- Neighborhood rough set based heterogeneous feature subset selectionInformation Sciences, 2008
- Attribute reduction in decision-theoretic rough set modelsInformation Sciences, 2008
- A novel condensing tree structure for rough set feature selectionNeurocomputing, 2008
- Efficient rough-set-based attribute reduction algorithm with nearest neighbour searchingElectronics Letters, 2007
- Selecting informative features with fuzzy-rough sets and its application for complex systems monitoringPattern Recognition, 2004
- A rough set approach to knowledge reduction based on inclusion degree and evidence reasoning theoryExpert Systems, 2003
- The concept of a linguistic variable and its application to approximate reasoning-IIIInformation Sciences, 1975