A decision feedback recurrent neural equalizer for digital communication

Sunghwan Ong, Sooyong Choi, Cheolwoo You, Daesik Hong

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

An important problem in high density digital magnetic recording system is that of channel equalization, that is, removal of distortions introduced by linear or nonlinear message corrupting mechanisms in the reconstruction of the original symbols. Severe nonlinear distortions in high density digital magnetic recording systems can make it difficult for conventional equalizers to reconstruct the originally recorded symbols. In this paper, we propose a Decision Feedback Recurrent Neural Equalizer (DFRNE) with a simple structure, which can recover the original symbols correctly under severe nonlinear distortion.

Original languageEnglish
Pages (from-to)2767-2769
Number of pages3
JournalIEEE Transactions on Magnetics
Volume33
Issue number5 PART 1
DOIs
Publication statusPublished - 1997 Dec 1

Fingerprint

pulse communication
Nonlinear distortion
Magnetic recording
Equalizers
magnetic recording
Feedback
Communication
messages

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Physics and Astronomy (miscellaneous)

Cite this

@article{20848779c2de46929a845fa0903cf502,
title = "A decision feedback recurrent neural equalizer for digital communication",
abstract = "An important problem in high density digital magnetic recording system is that of channel equalization, that is, removal of distortions introduced by linear or nonlinear message corrupting mechanisms in the reconstruction of the original symbols. Severe nonlinear distortions in high density digital magnetic recording systems can make it difficult for conventional equalizers to reconstruct the originally recorded symbols. In this paper, we propose a Decision Feedback Recurrent Neural Equalizer (DFRNE) with a simple structure, which can recover the original symbols correctly under severe nonlinear distortion.",
author = "Sunghwan Ong and Sooyong Choi and Cheolwoo You and Daesik Hong",
year = "1997",
month = "12",
day = "1",
doi = "10.1109/20.617724",
language = "English",
volume = "33",
pages = "2767--2769",
journal = "IEEE Transactions on Magnetics",
issn = "0018-9464",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5 PART 1",

}

A decision feedback recurrent neural equalizer for digital communication. / Ong, Sunghwan; Choi, Sooyong; You, Cheolwoo; Hong, Daesik.

In: IEEE Transactions on Magnetics, Vol. 33, No. 5 PART 1, 01.12.1997, p. 2767-2769.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A decision feedback recurrent neural equalizer for digital communication

AU - Ong, Sunghwan

AU - Choi, Sooyong

AU - You, Cheolwoo

AU - Hong, Daesik

PY - 1997/12/1

Y1 - 1997/12/1

N2 - An important problem in high density digital magnetic recording system is that of channel equalization, that is, removal of distortions introduced by linear or nonlinear message corrupting mechanisms in the reconstruction of the original symbols. Severe nonlinear distortions in high density digital magnetic recording systems can make it difficult for conventional equalizers to reconstruct the originally recorded symbols. In this paper, we propose a Decision Feedback Recurrent Neural Equalizer (DFRNE) with a simple structure, which can recover the original symbols correctly under severe nonlinear distortion.

AB - An important problem in high density digital magnetic recording system is that of channel equalization, that is, removal of distortions introduced by linear or nonlinear message corrupting mechanisms in the reconstruction of the original symbols. Severe nonlinear distortions in high density digital magnetic recording systems can make it difficult for conventional equalizers to reconstruct the originally recorded symbols. In this paper, we propose a Decision Feedback Recurrent Neural Equalizer (DFRNE) with a simple structure, which can recover the original symbols correctly under severe nonlinear distortion.

UR - http://www.scopus.com/inward/record.url?scp=0031220826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031220826&partnerID=8YFLogxK

U2 - 10.1109/20.617724

DO - 10.1109/20.617724

M3 - Article

AN - SCOPUS:0031220826

VL - 33

SP - 2767

EP - 2769

JO - IEEE Transactions on Magnetics

JF - IEEE Transactions on Magnetics

SN - 0018-9464

IS - 5 PART 1

ER -