This paper shows the efficiency of neural networks (NN), coupled with the finite element method (FEM), to evaluate the broadband properties of dielectric materials. A characterization protocol is built to characterize dielectric materials and NN are used in order to provide the estimated permittivity. The FEM is used to create the data set required to train the NN. A method based on Bayesian regularization ensures a good generalization capability of the NN. It is shown that NN can determine the permittivity of materials with a high accuracy and that the Bayesian regularization greatly simplifies their implementation.
2. Hornik, K., M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, Vol. 2, 359-366, 1989.
3. Yildiz, B. and M. Turkmen, "Quasi-static models based on artificial neural networks for calculating the characteristic parameters of multilayer cylindrical coplanar waveguide and strip line," Progress In Electromagnetics Research B, Vol. 3, 1-22, 2008.
4. Zainud-Deen, S. H., H. A. Malhat, K. H. Awadalla, and E. S. El-Hadad, "Direction of arrival and state of polarization estimation using radial basis function neural network (RBFNN)," Progress In Electromagnetics Research B, Vol. 2, 137-150, 2008.
5. Guney, K., C. Yildiz, S. Kaya, and M. Turkmen, "Artificial neural networks for calculating the characteristic impedance of airsuspended trapezoidal and rectangular-shaped microshield lines," J. of Electromagn. Waves and Appl., Vol. 20, No. 9, 1161-1174, 2006.
6. Ayestar’an, R. G. and F. Las-Heras, "Near field to far field transformation using neural networks and source reconstruction," J. of Electromagn. Waves and Appl., Vol. 20, No. 15, 2201-2213, 2006.
7. Acikgoz, H., Y. Le Bihan, O. Meyer, and L. Pichon, "Neural networks for broad-band evaluation of complex permittivity using a coaxial discontinuity," Eur. Phys. J. Appl. Phys., Vol. 39, 197-201, 2007.
8. Sarle, W. S., "Neural Network FAQ, Part 2 of 7: Learning, periodic posting to the Usenet newsgroup comp.ai.neural-nets,", Available by ftp://ftp.sas.com/pub/Neural/FAQ.html.
9. MacKay, D. J. C., "Bayesian methods for adaptive models,", Thesis of California Institute of Technology, 1992.
10. Bartley, P. G., R. W. McClendon, and S. O. Nelson, "Permittivity determination by using an artificial neural network," IEEE Instrum. and Meas. Tech. Conference, 27-30, 1999.
11. Tuck, D. and S. Coad, "Neurocomputed model of open-circuited coaxial probes," IEEE Microwave Guided Lett., Vol. 5, 105-107, 1995.
12. Meyer, O., "Instrumentation pour un controle de processus de reticulation sous micro-ondes par caracterisation large bande,", Thesis of the University Pierre et Marie Curie, 1996.
13. Belhadj-Tahar, N. E., A. Fourrier-Lamer, and H. De Chanterac, "Broad-band simultaneous measurement of complex permittivity and permeability using a coaxial discontinuity," IEEE Transactions on Microwave Theory and Techniques, Vol. 38, No. 1, January 1990.
14. Courtois, S. and R. Phan-Tan-Luu, "Neural networks applied to the choice of an experimental design," EDP Sciences, Vol. 26, 304-310, Wiley-VCH, 1998.
15. Sarle, W. S., "Neural Network FAQ, Part 3 of 7: Generalization, periodic posting to the Usenet newsgroup comp.ai.neural-nets,", Available by ftp://ftp.sas.com/pub/Neural/FAQ.html.
16. Foresee, F. D. and M. T. Hagan, "Gauss-Newton approximation to Bayesian learning," IEEE Trans. Neural Networks, Vol. 3, 1930-1935, 1997.