Rough set based feature selection using modified rough membership function
journal of kerbala university,
2013, Volume 9, Issue 3, Pages 82-92
Abstractfeature selection (FS) is one of the important steps in the knowledge discovery, which aims to reduce the dimensionality of data. In this paper, a feature selection algorithm is proposed. The proposed algorithm use the rough membership function, which is modified in order to be suitable for measuring the effectiveness of each attribute value, and then using it for measuring the effectiveness of each attribute through a new formula called a modified attribute membership (MAM). The experiments shows that the proposed algorithm provides an effective tool for selecting feature and reducing the dimensionality of data.
Keywords: feature selection, modified rough membership function, modified attribute membership, rough set
- Article View: 120
- PDF Download: 53