Sliding Mode Control based Support Vector Machine RBF Kernel Parameter Optimization

Support Vector Machine (SVM) is a learning-based algorithm, which is widely used for classification in many applications. Despite its advantages, its application to large scale datasets is limited due to its use of large number of support vectors and dependency of its performance on its kernel parameter. This paper presents a Sliding Mode Control based Support Vector Machine Radial Basis Function's kernel parameter optimization (SMC-SVM-RBF) method, inspired by sliding mode closed loop control theory, which has demonstrated significantly higher performance to that of the standard closed loop control technique. The proposed method first defines an error equation and a sliding surface and then iteratively updates the RBF's kernel parameter based on the sliding mode control theory, forcing SVM training error to converge below a predefined threshold value. The closed loop nature of the proposed algorithm increases the robustness of the technique to uncertainty and improves its convergence speed. Experimental results were generated using nine standard benchmark datasets covering wide range of applications. Results show the proposed SMC-SVM-RBF method is significantly faster than those of classical SVM based techniques. Moreover, it generates more accurate results than most of the state of the art SVM based methods.