Analysis and Synthesis of the Microstrip Lines Based on Support Vector Regression

Abstract

In this work, the Support Vector Regression is adopted to the analysis and synthesis of microstrip lines on all isotropic/anisotropic dielectric materials, which is a novel technique based on the rigorous mathematical fundamentals and the most competitive technique to the popular artificial neural networks. In this design process, accuracy, computational efficiency and number of support vectors are investigated in detail and the Support Vector Regression performance is compared to an artificial neural network performance. It can be concluded that the artificial neural network may be replaced by the Support Vector Machines in the regression applications due to its high approximation capability and much faster convergence rate with the sparse solution technique. Synthesis is achieved by utilizing the analysis black-box bidirectionally by reverse training. Furthermore, by using the adaptive step size, a much faster convergence rate is obtained in the reverse training. Besides, design of microstrip lines on the most commonly used isotropic/anisotropic dielectric materials are given as the worked examples.