Fuzzy Rough Set Membership based

Fuzzy Multiple Kernel Support Vector Machine

Qiang He, Jiaoyang Zhang

School of Science, Beijing University of Civil Engineering and Architecture, Beijing, 100044, China

Abstract: Support vector machines (SVMs) are currently widely used machine learning techniques. SVM is used to construct an optimal hyper-plane that implies an extraordinary generalization capability and good performances. So far, SVMs have already been successfully applied to many real fields. In view of the difficulties in kernel selection and sensitivity to noise, we propose fuzzy rough set membership based fuzzy multiple kernel support vector machine in this paper. The membership degree generalized by fuzzy rough set is introduced to fuzzy multiple kernel support vector machine. It not only avoids the problem of kernel selection, but also improves the robustness to noise. The experimental simulation also validates the feasibility and effectiveness of the method.

Keywords: Multiple Kernel Learning; Support Vector Machine; Fuzzy Rough Set; Fuzzy Membership; Classification