Use of an Artificial Neural Network-based Metamodel to Reduce the Computational Cost in a Ray-tracing Prediction Model

Sheila Santisi Travessa, Walter Pereira Carpes Jr.


The purpose of this article is based on analyzing the use of RTQ3D ("quasi-3D`` ray tracing technique) to produce the value of the initial electromagnetic fields or fitness for a hundred and sixty receivers according to the possible positions of two antennas to be distributed in a closed environment. The problem variables consist of the values of the magnetic fields for one hundred and sixty receptors depending on the positions of the antennas to the base stations, which serve as input data for the algorithm to the RMLP (Artificial Neural Network, multilayer perceptron with Real backpropagation learning algorithm). The values of the magnetic fields associated with the positions of the antennas are the values to be learned by the network, the teacher of RMLP. This study aims to develop efficient techniques for optimization of electromagnetic problems. We use the PSO (Particle Swarm Optimization) algorithm  associated with a metamodel based on an ANN (Artificial Neural Network). Specifically, we use the MLP (Multilayer Perceptron) with the backpropagation algorithm in order to evaluate objective functions in an efficient way. The ANN will be used to assist the technique of "quasi 3D`` ray-tracing in order to reduce the high computational cost of this technique in PSO optimization.


Artificial Neural Networks, Multilayer Perceptron, electromagnetic fields, Particle Swarm Optimization, metamodeling.

Full Text:



H.P. Schwefel, E. L. Taylor, "Evolution and Optimum Seeking, `` John Wiley & Sons. Inc, United States of America, pp. 87-88, 1994.

G. Venter, and J. Sobieszczanski-sobieski, "Particle Swarm Optimization,`` Proceedings of the 43rd AIAA/ASME/ASCE/AHS/ASC Strutures, Structural Dynamics, and Materials Conference, Denver, CO, Vol. AIAA-2002-1235, April 22-25 2002.

L. Lebensztjan, C. A. R. Marretto, M. C. Costa, J. L. Coulomb, "Kriging: a useful tool for electromagnetic device optimization,`` vol.40, No.2. IEEE Transactions on Magnetics, March 2004, p. 1196-99.

M. T. M. EMMERICH, C. M. VARCOL, "Metamodel–Assisted Evolution Strategies in Electromagnetic Compatibility Design``. EUROGEN. 1-12, 2005.

O. A. Mohammed, D. C. Park, F. G. Ãœle; C. Zigiang, "Design optimization of electromagnetic devices using artificial neural networks,`` vol.28, No.5 IEEE Transactions on Magnetics, September 1992, p. 2805-07.

Rahmat-Samii Y., N. JIN, "Particle Swarm Optimization (PSO) in Engineering Electromagnetics: A Nature-Inspired Evolutionary Algorithm,`` IEEE, 2007. Inc, United States of America, 1994 pp. 87-88.

R. C. Eberhart and Y. Shi, "Particle Swarm Optimization: Developments, Applications and Resources``, Congress on Evolutionary Computation, 2001, vol. 1, pp. 81-86, 2001.

S. Grubisic, W. P. Carpes Jr, J. P. A. Bastos, "An Efficient indoor ray- tracing propagation model with a quasi-3D approach,`` IEEE CEFC 2012, November 2012, Oita/Japan.

S. Grubisic, W. P. Carpes Jr, J. P. A. Bastos, G. Santos, "Association of a PSO optimizer with a quasi-3D ray-tracing propagation model for mono and multi-criterion antenna positioning in indoor environments,`` IEEE TRANSACTIONS ON MAGNETICS, VOL. 49, NO. 5, MAY 2013.

Haykin, S., Neural Networks: A Comprehensive Foundation, Prentice Hall, 1999.

J. M. Barreto, "Neural Networks: Mathematical and Computational Aspects,`` Annals of the Brazilian Society of Applied and Computational Mathematics (BSACM), 1996.



  • There are currently no refbacks.

© Copyright 2007-2016 JMOe Brazilian Microwave and Optoelectronics Society (SBMO) and Brazilian Society of Electromagnetism (SBMag)