Title :
Microwave Characterization Using Ridge Polynomial Neural Networks and Least-Square Support Vector Machines
Author :
Hacib, T. ; Le Bihan, Y. ; Smail, M.K. ; Mekideche, M.R. ; Meyer, O. ; Pichon, L.
Author_Institution :
Lab. d´´Etudes et de Modelisation en Electrotech., Univ. Jijel, Jijel, Algeria
fDate :
5/1/2011 12:00:00 AM
Abstract :
This paper shows that Ridge Polynomial Neural Networks (RPNN) and Least-Square Support Vector Machines (LS-SVM) technique provide efficient tools for microwave characterization of dielectric materials. Such methods avoids the slow learning properties of multilayer perceptrons (MLP) which utilize computationally intensive training algorithms and can get trapped in local minima. RPNN and LS-SVM are combined in this work with the Finite Element Method (FEM) to evaluate the dielectric materials properties. The RPNN is constructed from a number of increasing orders of Pi-Sigma units, it maintains fast learning properties and powerful mapping capabilities of single layer High Order Neural Networks (HONN). LS-SVM is a statistical learning method that has good generalization capability and learning performance. The FEM is used to create the data set required to train the RPNN and LS-SVM. The performance of a LS-SVM model depends on a careful setting of its associated hyper-parameters. In this study the LS-SVM hyper-parameters are optimized by using a Bayesian regularization technique. Results show that LS-SVM can achieve good accuracy and faster speed than neural network methods.
Keywords :
belief networks; dielectric materials; finite element analysis; learning (artificial intelligence); least squares approximations; multilayer perceptrons; polynomials; statistical analysis; support vector machines; Bayesian regularization technique; FEM; LSSVM; computationally intensive training algorithms; dielectric materials; finite element method; hyperparameters; least-square support vector machines; microwave characterization; multilayer perceptrons; pi-sigma units; ridge polynomial neural networks; single layer high order neural networks; slow learning properties; statistical learning method; Admittance; Artificial neural networks; Finite element methods; Microwave theory and techniques; Polynomials; Support vector machines; Training; Least-square support vector machines; microwave characterization; ridge polynomial neural networks;
Journal_Title :
Magnetics, IEEE Transactions on
DOI :
10.1109/TMAG.2010.2087743