Optimization of ANN applied to non-linear system identification based in UWB

Author

Corral, Pablo ; Júnior, Oswaldo L. ; de Castro Lima, A.C.

Author_Institution

Dept. of Signal Theory & Commun., Univ. Miguel Hernandez, Elche

fYear

2006

fDate

24-27 June 2006

Firstpage

56

Lastpage

59

Abstract

In this work we propose a hybrid technique for artificial neural network optimization based in UWB system. This technique is a combination of real-coded genetic (GA) and back propagation (BP) algorithms simulating an ultra wideband (UWB) system. The main idea is to apply the back propagation over the five more adapted individuals of each generation produced by the real coded GA, in order to allow the evolution of these individuals before the crossover operation. The combined algorithms are used in non-linear system identification. Some solutions are presented to solve common problems arising from the application of genetic algorithm

Keywords

backpropagation; genetic algorithms; multilayer perceptrons; neural nets; nonlinear control systems; telecommunication computing; ultra wideband communication; ANN; UWB system; artificial neural network optimization; back propagation algorithms; nonlinear system identification; real-coded genetic algorithms; ultra wideband system; Artificial neural networks; Bandwidth; Genetic algorithms; Irrigation; Mechatronics; Neurons; Nonlinear control systems; OFDM modulation; System identification; Ultra wideband technology;

fLanguage

English

Publisher

ieee

Conference_Titel

Mobile Future, 2006 and the Symposium on Trends in Communications. SympoTIC '06. Joint IST Workshop on

Conference_Location

Bratislava

Print_ISBN

1-4244-0368-5

Type

conf

DOI

10.1109/TIC.2006.1708021

Filename

1708021