RFS: Efficient feature selection method based on R-value

Feature selection is one of the most important issues in classification. Many filter and wrapper methods have been proposed. Here, we propose a new efficient feature selection method based on the R-value, which is a measure that is used to capture the overlapped areas among classes in a feature. Our strategy was to select features that have low overlapping areas among classes. Proposed idea is simple, but powerful for feature selection. The experiment results showed that the proposed method is better than previous typical methods in many cases. Accordingly, the proposed method can be used in combination with other feature selection methods. (C) 2012 Elsevier Ltd. All rights reserved.