MODELING OF FLOW NUMBER OF ASPHALT MIXTURES USING A MULTI-KERNEL BASED SUPPORT VECTOR MACHINE APPROACH

Abstract

Flow number of asphalt–aggregate mixtures as an explanatory factor has been proposed in order to assess the rutting potential of asphalt mixtures. This study proposes a multiple–kernel based support vector machine (MK–SVM) approach for modeling of flow number of asphalt mixtures. The MK–SVM approach consists of weighted least squares–support vector machine (WLS–SVM) integrating two kernel functions in order to improve the learning and generalization ability of WLS–SVM. In the proposed method, a linear convex combination of the radial basis function (RBF) and Morlet wavelet kernel functions is adopted, which are considered as the most popular kernel functions. To validate the efficiency of the proposed method, experiments are conducted on a database including 118 uniaxial dynamic creep test results. The results of the statistical criteria show a good agreement between the predicted and measured flow number values. Further, the simulation results demonstrate that the proposed MK–SVM approach has more superior performance than the single kernel based WLS–SVM and other methods found in the literature.