EFFICIENT FEATURE SELECTION TECHNIQUE BASED ON MODIFIED FUZZY C-MEANS CLUSTERING WITH ROUGH SET THEORY

Abstract

Feature selection plays an important role in classification, since it can shorten the learning time, simplify the learning classifiers, and improve the classification performance. There may be complex interaction among features; it is generally difficult to find the best feature subset. This article presents an efficient feature selection based on Modified Fuzzy c-Means clustering with Rough Set Theory (MFCM-RST), the classification will be done based on the SVM classifier. The proposed algorithm involves the amalgamation of concepts of rough sets, fuzzy sets, and c-Means clustering algorithm. While the fuzzy set enables efficient handling of overlapping partitions, the concept of rough set deals with uncertainty, vagueness, incompleteness, and indiscernibility in class definition. Whereas, the kernel trick projecting the feature space into a higher dimension using an appropriate non-linear mapping function ensures linear separability of the complex clusters which are otherwise not linearly separable in its original feature space. Finally, finds the near optimum values of the different parameters used in the proposed method. The effectiveness of the proposed algorithm is evaluated using a UCI machine learning datasets. Experimental results justify the superiority of the proposed method in comparison to other traditional techniques.