Title :
Nonlinear multilayer combining techniques for Bayesian equalizers using the radial basis function network as a digital magnetic storage equalizer
Author :
Choi, Sooyong ; Hong, Daesik
Author_Institution :
Yonsei Univ., Seoul, South Korea
fDate :
9/1/1999 12:00:00 AM
Abstract :
In order to reduce the complexity and enhance the performance of the Bayesian equalizer using the radial basis function (RBF) network, a new equalizer using the RBF network with a nonlinear multilayer combiner (RNEQ) is proposed. The RNEQ is applied to a digital storage system in which the primary element of impairment is nonlinear distortion due to partial erasure. From computer simulation results, the RNEQ with almost 70% reduced structural complexity over the conventional equalizer using RBF network has nearly the same performance in terms of bit-error rate (BER) and mean squared error
Keywords :
Bayes methods; digital magnetic recording; equalisers; nonlinear distortion; radial basis function networks; Bayesian equalizer; RNEQ; bit error rate; computer simulation; digital magnetic storage; mean squared error; nonlinear distortion; nonlinear multilayer combiner; partial erasure; radial basis function network; Bayesian methods; Binary phase shift keying; Bit error rate; Degradation; Equalizers; Magnetic multilayers; Nonhomogeneous media; Nonlinear distortion; Process design; Radial basis function networks;
Journal_Title :
Magnetics, IEEE Transactions on
