Combined Kernel Function for Support Vector Machine and Learning Method Based on Evolutionary Algorithm

Abstract

This paper proposes a new combined kernel function and its learning method for support vector machine which results in higher learning rate and better classification performance. A set of simple kernel functions are combined to create a new kernel function, which is trained by a learning method employing evolutionary algorithm. The learning method results in the optimal decision model consisting of a set of features as well as a set of the parameters for combined kernel function. The new kernel function and the learning method were applied to obtain the optimal decision model for classification of proteome patterns, and in the comparison with other kernel functions, the combined kernel function showed a higher convergence rate and a greater flexibility in learning a problem space than single kernel functions.