Applications of generalized RBF-NN for path loss prediction

Author

Popescu, Ileana ; Kanstas, A. ; Angelou, Evangelos ; Nafornita, Ioan ; Constantinou, Philip

Author_Institution

Mobile Radiocommunications Lab., Nat. Tech. Univ. of Athens, Greece

Volume

1

fYear

2002

fDate

15-18 Sept. 2002

Firstpage

484

Abstract

This paper presents the results of the generalized radial basis function neural networks applications for the prediction of propagation path loss in urban and suburban environment. We have studied two types of neural network based models; the first one is used for path loss prediction while the second one is a hybrid prediction model based on error control. The performances of the neural models are compared to the path loss values measured in the city of Kavala and in Oia village on Santorini Island, Greece, based on the absolute mean error, standard deviation and root mean square error between predicted and measured values.

Keywords

electromagnetic wave absorption; loss measurement; radial basis function networks; radiowave propagation; telecommunication computing; 1.89 MHz; Greece; Kavala; Oia village; Santorini Island; absolute mean error; data measurements; error control; generalized RBF-NN; generalized radial basis function neural networks; hybrid prediction model; neural network based models; propagation path loss prediction; radiowave propagation; root mean square error; standard deviation; suburban environment; urban environment; Cities and towns; Error correction; Loss measurement; Measurement standards; Neural networks; Performance evaluation; Predictive models; Propagation losses; Radial basis function networks; Root mean square;

fLanguage

English

Publisher

ieee

Conference_Titel

Personal, Indoor and Mobile Radio Communications, 2002. The 13th IEEE International Symposium on

Print_ISBN

0-7803-7589-0

Type

conf

DOI

10.1109/PIMRC.2002.1046748

Filename

1046748