A suboptimal Bayesian equalizer using an nonlinear multilayer combiner

Author

Choi, Sooyong ; Hong, Daesik

Author_Institution

Dept. of Electron. Eng., Yonsei Univ., Seoul, South Korea

fYear

1999

fDate

36373

Firstpage

353

Lastpage

362

Abstract

In order to reduce the complexity and enhance the performance of the Bayesian equalizer (REQ) using the radial basis function (RBF) network, a new equalizer (RNEQ) using the RBF network with a nonlinear multilayer combiner is proposed. The proposed RNEQ produces the output using nonlinear multilayer combiner. The RNEQ is applied to a digital communication system and a nonlinear magnetic storage system. From computer simulation results, the RNEQ with almost 70% reduced structure over the REQ shows nearly the same performance in a digital communication system. In a nonlinear digital storage system the RNEQ is superior to the REQ. In addition, the RNEQ converges to lower mean squared error value than the other equalizers

Keywords

Bayes methods; digital magnetic recording; equalisers; magnetic storage; multilayer perceptrons; optimisation; radial basis function networks; telecommunication computing; RBF network; RNEQ; complexity reduction; computer simulation results; convergence; digital communication system; mean squared error; multilayer preceptron; nonlinear digital storage system; nonlinear magnetic storage system; nonlinear multilayer combiner; performance; radial basis function network; suboptimal Bayesian equalizer; Bayesian methods; Binary phase shift keying; Computer simulation; Digital communication; Equalizers; Magnetic multilayers; Nonhomogeneous media; Nonlinear magnetics; Radial basis function networks; Telecommunications;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing IX, 1999. Proceedings of the 1999 IEEE Signal Processing Society Workshop.

Conference_Location

Madison, WI

Print_ISBN

0-7803-5673-X

Type

conf

DOI

10.1109/NNSP.1999.788154

Filename

788154