A neural network and extended Kalman filter based adaptive multiuser receiver for CDMA systems

Author

Singh, Navin ; Takawira, Fambirai

Author_Institution

Dept. of Electron. Eng., Natal Univ., Dalbridge, South Africa

Volume

1

fYear

1996

fDate

24-27 Sep 1996

Firstpage

414

Abstract

We investigate the application of multilayer perceptrons to the problem of multiuser detection in code division multiple access systems. The neural network is used as a classifier in an adaptive receiver which incorporates an extended Kalman filter for joint amplitude and delay estimation. The performance is studied via computer simulations showing that the receiver performs favourably compared with others that have appeared in the literature

Keywords

Kalman filters; adaptive signal detection; amplitude estimation; code division multiple access; land mobile radio; multilayer perceptrons; nonlinear filters; pattern classification; radio receivers; telecommunication computing; CDMA systems; adaptive multiuser receiver; classifier; code division multiple access system; extended Kalman filter; joint amplitude/delay estimation; multilayer perceptrons; multiuser detection; neural network; performance; Artificial neural networks; Baseband; Delay estimation; Detectors; Low pass filters; Matched filters; Multiaccess communication; Multiuser detection; Neural networks; Receivers;

fLanguage

English

Publisher

ieee

Conference_Titel

AFRICON, 1996., IEEE AFRICON 4th

Conference_Location

Stellenbosch

Print_ISBN

0-7803-3019-6

Type

conf

DOI

10.1109/AFRCON.1996.563148

Filename

563148