Annealed neural network based multiuser detector in code division multiple access communications

Author

Yoon, S.H. ; Rao, S.S.

Author_Institution

Dept. of Comput. Sci., North Carolina A&T State Univ., Greensboro, NC, USA

Volume

147

Issue

1

fYear

2000

fDate

2/1/2000 12:00:00 AM

Firstpage

57

Lastpage

62

Abstract

An annealed neural network based multiuser detector in code division multiple access (CDMA) communications is presented. This detector combines features of the Hopfield neural network and simulated annealing. Unlike existing neural network based detectors, this detector does not need good initial estimates or optimal selection of network parameters. The BER performance of the proposed detector is close to the theoretical lower bound of the BER performance, especially in `near-far´ situations. Extensive numerical evaluation of the proposed technique as well as various suboptimal multiuser detectors is conducted using Monte-Carlo simulation

Keywords

Gaussian channels; Hopfield neural nets; Monte Carlo methods; code division multiple access; digital simulation; error statistics; multiuser channels; signal detection; simulated annealing; spread spectrum communication; telecommunication computing; BER performance; CDMA; Gaussian channel; Hopfield neural network; Monte-Carlo simulation; analogue VLSI neural network chips; annealed neural network based multiuser detector; code division multiple access communications; lower bound; near-far situations; simulated annealing; spread spectrum communication; suboptimal multiuser detectors;

fLanguage

English

Journal_Title

Communications, IEE Proceedings-

Publisher

iet

ISSN

1350-2425

Type

jour

DOI

10.1049/ip-com:20000228

Filename

838089