A decision feedback recurrent neural equalizer for digital communication

Sunghwan Ong; Sooyong Choi; Cheolwoo You; Daesik Hong

doi:10.1109/20.617724

A decision feedback recurrent neural equalizer for digital communication

Sunghwan Ong, Sooyong Choi, Cheolwoo You, Daesik Hong

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article › peer-review

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 language	English
Pages (from-to)	2767-2769
Number of pages	3
Journal	IEEE Transactions on Magnetics
Volume	33
Issue number	5 PART 1
DOIs	https://doi.org/10.1109/20.617724
Publication status	Published - 1997

Bibliographical note

Funding Information:
Manuscript received February 4, 1997. This work was supported in part by a research grant of the university supporting program from the Ministry of Information & Communication and the Video Industrial R&D Association of Republic of Korea. e-mail : shong@catseye.yonsei.ac.kr

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Access to Document

10.1109/20.617724

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",

note = "Funding Information: Manuscript received February 4, 1997. This work was supported in part by a research grant of the university supporting program from the Ministry of Information & Communication and the Video Industrial R&D Association of Republic of Korea. e-mail : shong@catseye.yonsei.ac.kr",

year = "1997",

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",

}

TY - JOUR

T1 - A decision feedback recurrent neural equalizer for digital communication

AU - Ong, Sunghwan

AU - Choi, Sooyong

AU - You, Cheolwoo

AU - Hong, Daesik

N1 - Funding Information: Manuscript received February 4, 1997. This work was supported in part by a research grant of the university supporting program from the Ministry of Information & Communication and the Video Industrial R&D Association of Republic of Korea. e-mail : shong@catseye.yonsei.ac.kr

PY - 1997

Y1 - 1997

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

SN - 0018-9464

VL - 33

SP - 2767

EP - 2769

JO - IEEE Transactions on Magnetics

JF - IEEE Transactions on Magnetics

IS - 5 PART 1

ER -

A decision feedback recurrent neural equalizer for digital communication

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this