QPSK error vector magnitude demodulation with RBF neural network in Rayleigh fading channels

Author

Lerkvaranyu, Somkiat ; Miyanaga, Yoshikazu

Author_Institution

Dept. of Electron. Eng., Hokkaido Univ., Sapporo, Japan

Volume

2

fYear

2004

fDate

26-29 Oct. 2004

Firstpage

825

Abstract

This work proposes a method to enhance the demodulation of QPSK error vector magnitude (EVM) in a direct conversion receiver (DCR). The proposed method is a radial basis function (RBF) neural network, which is used to learn the characteristics of signal constellation. The hybrid learning method is used to train the RBF network. The hidden layer is trained by the hard k means clustering and the supervised learning is used to train the output layer with given input-output pairs. This study is worked in a Rayleigh fading channel.

Keywords

Rayleigh channels; demodulation; learning (artificial intelligence); pattern clustering; quadrature phase shift keying; radial basis function networks; radio receivers; telecommunication computing; DCR; EVM; QPSK error vector magnitude demodulation; RBF neural network; Rayleigh fading channels; direct conversion receiver; hard k means clustering; hidden layer training; hybrid learning method; output layer input-output pairs; radial basis function neural network; signal constellation characteristics; supervised learning; Constellation diagram; Demodulation; Electronic mail; Fading; Intelligent networks; Neural networks; Phase modulation; Quadrature phase shift keying; Radial basis function networks; Transceivers;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Information Technology, 2004. ISCIT 2004. IEEE International Symposium on

Print_ISBN

0-7803-8593-4

Type

conf

DOI

10.1109/ISCIT.2004.1413832

Filename

1413832