Avaliação de Desempenho de Equalizador Neural Utilizando Algoritmo Genético (Neural Equalizer Performance Evaluation Using Genetic Algorithm)

Tiago Andrade Mota (tandrademota@gmail.com)2, Jorgean Ferreira Leal (jorgean@anatel.gov.br)1, Antonio Cezar de Castro Lima (acdcl@ufba.br)2

1Agência Nacional de Telecomunicações
2Universidade Federal da Bahia

This paper appears in: Revista IEEE América Latina

Publication Date: Oct. 2015
Volume: 13,   Issue: 10 
ISSN: 1548-0992

Artificial Neural Networks (ANN) have been successfully applied to deal with linear or nonlinear problems. The best ANN architecture choice is not a trivial task to be performed and requires some a priori knowledge. In this work, we propose a Genetic Algorithm (GA) evaluation approach to determine the best combination of ANN and learning algorithm for equalization propose. A comparative analysis, using well known neural architectures, is presented in order to accomplish a 4-QAM equalization of signals submitted to Inter Symbol Interference (ISI), inherent in typical mobile communication channels. MLP, FLANN, PPN and three RNN based ANN structures, trained using backpropagation algorithm and others, have been evaluated.

Index Terms:
Artificial Neural Network, Genetic Algorithm, Multipath Channel, Equalizer   

Documents that cite this document
This function is not implemented yet.

[PDF Full-Text (458)]