Title: General regression neural network approach to prediction of electric field level in the reverberation chamber

Authors: Muhammet Hilmi Nisanci, Yavuz Cengiz, Ovunc Polat, Antonio Orlandi, Alistair Duffy

Addresses: Department of Electrical Engineering, University of L'Aquila, L'Aquila, 67100, Italy. ' Department of Electronics and Communication Engineering, Suleyman Demirel University, Isparta, 32260, Turkey. ' Department of Electronics and Communication Engineering, Suleyman Demirel University, Isparta, 32260, Turkey. ' Department of Electrical Engineering, University of L'Aquila, L'Aquila, 67100, Italy. ' Department of Engineering, De Monfort University, Leicester, UK

Abstract: This study presents an approach for the prediction of electric field level which depends on the positions of stirrer and frequency in the mode stirred reverberation chamber. A general regression neural network (GRNN) is used for prediction process. In order to show the system performance, feature selective validation (FSV) technique is given. The simulation results show that the predicted values of electrical field have been obtained with high accuracy. Thus, this technique will facilitate estimation of electric field level in the reverberation chamber which is component of especially mode stirrer reverberation chamber test method.

Keywords: reverberation chambers; general regression neural networks; GRNN; electric field level prediction; feature selective validation; simulation; feature selection.

DOI: 10.1504/IJRIS.2010.036862

International Journal of Reasoning-based Intelligent Systems, 2010 Vol.2 No.3/4, pp.168 - 175

Published online: 12 Nov 2010 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article