Feature Selection Based on Rough Set and Gravitational Search Algorithm

Hua-qiang Wang (), Zhan-wen Niu and Li-jun Liang
Additional contact information
Hua-qiang Wang: Tianjin University
Zhan-wen Niu: Tianjin University
Li-jun Liang: Tianjin University

A chapter in Proceedings of 20th International Conference on Industrial Engineering and Engineering Management, 2013, pp 409-418 from Springer

Abstract: Abstract Many approaches have been tried out for feature selection, which is aimed at finding a minimal subset of the original features with predetermined targets. However, a complete search isn’t feasible for even medium-sized datasets and it has been proved that finding a minimal subset of the features is a NP-hard problem. Rough set theory is one of the effective methods to feature selection, and gravitational search algorithm (GSA), which has a flexible and well-balanced mechanism to enhance exploration and exploitation, has been successfully applied in many difficult problems. In this paper, a novel approach, called FSRG, for feature selection based on rough set and GSA is proposed, and 5 UCI datasets are used as an illustrated example. The results demonstrate that FSRG is an efficient method for feature selection.

Keywords: Feature selection; Gravitational search algorithm; Rough set (search for similar items in EconPapers)
Date: 2013
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-642-40063-6_41

Ordering information: This item can be ordered from
http://www.springer.com/9783642400636

DOI: 10.1007/978-3-642-40063-6_41

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().