Differential Evolution Based Parameters Selection for Support Vector Machine

This paper addresses the problem of SVM parameter optimization. The authors propose an SVM classification system based on differential evolution(DE) to improve the generalization performance of the SVM classifier. For this purpose, the authors have optimized the SVM classifier design by searching for the best value of the parameters that tune its discriminant function. The experiments are conducted on the basis of benchmark dataset. The obtained results clearly confirm the superiority of the DE-SVM approach compared to default parameters SVM classifier and suggest that further substantial improvements in terms of classification accuracy can be achieved by the proposed DE-SVM classification system.