Naslov
A Comparison of MLP and RBF Neural Networks Architectures for Electromagnetic Field Prediction in Indoor Environments

Autori
Vilović, Ivan ; Burum, Nikša

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 5th European Conference on Antennas and Propagation (EUCAP 2011) / Mario Orefice - Rim : EUCAP 2011, 2011, 1830-1834

ISBN
978-88-8202-074-3

Skup
The 5th European Conference on Antennas and Propagation (EUCAP)

Mjesto i datum
Rim, Italija, 10.04.2011. - 15.04.2011

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Neural network; Multilayer perceptron; Radial basis function; Particle Swarm Optimization - PSO

Sažetak
In this paper two different neural network architectures are investigated for enough accurate field strength prediction in the complex indoor environment. The investigation includes multilayer perceptron (MLP) and radial basis function (RBF) neural networks. It has been already shown for neural networks as powerful tool in RF propagation prediction. Standard empirical or deterministic field prediction methods are difficult applicable in the case of complex indoor environments, so the neural networks can be the reasonable choice. The neural network models are trained with measured values of the field strength at arbitrary points. The backpropagation training algorithm (Levenberg-Marquardt with Bayesian regularization) is compared with particle swarm optimization (PSO) algorithm used in neural network training. After careful tuning training algorithm parameters the results showed smaller RMS errors for the PSO training case compared with backpropagation algorithm. Also, the better results are abstained by the RBF network architecture.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika

POVEZANOST RADA