Simplification of neural network equalizer for perpendicular magnetic recording

Hisashi Osawa; Toshimasa Shimizu; Takumi Nakaoka; Yoshihiro Okamoto; Hidetoshi Saito; Hiroaki Muraoka; Yoshihisa Nakamura

doi:10.1002/ecjb.20197

Simplification of neural network equalizer for perpendicular magnetic recording

Hisashi Osawa, Toshimasa Shimizu, Takumi Nakaoka, Yoshihiro Okamoto, Hidetoshi Saito, Hiroaki Muraoka, Yoshihisa Nakamura

Broadband Engineering Division

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

2 Citations (Scopus)

Abstract

In this paper, we examine neural network equalization in a perpendicular magnetic recording channel with jitter medium noise and MR nonlinear distortion. First, we propose simplifying a neural network equalizer by using a hybrid genetic algorithm. Next, we determine the bit error rate of a PR2ML method provided with the simplified neural network equalizer and compare it to those of a conventional neural network equalizer and a transversal filter equalizer. The results were improvements of about 0.8 and 2.0 dB in the SNR of the PR2ML method using the simplified neural network equalizer compared to the conventional neural network equalizer and the transversal filter equalizer, respectively.

Original language	English
Pages (from-to)	19-27
Number of pages	9
Journal	Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)
Volume	89
Issue number	2
DOIs	https://doi.org/10.1002/ecjb.20197
Publication status	Published - 2006 Feb 1

Keywords

Genetic algorithm
Jitter medium noise
MR nonlinear distortion
Neural network equalizer
Perpendicular magnetic recording

ASJC Scopus subject areas

Physics and Astronomy(all)
Computer Networks and Communications
Electrical and Electronic Engineering

Access to Document

10.1002/ecjb.20197

Cite this

Simplification of neural network equalizer for perpendicular magnetic recording. / Osawa, Hisashi; Shimizu, Toshimasa; Nakaoka, Takumi et al.

In: Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi), Vol. 89, No. 2, 01.02.2006, p. 19-27.

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

@article{3afe2ec2a9ab4b3196124897489be72b,

title = "Simplification of neural network equalizer for perpendicular magnetic recording",

abstract = "In this paper, we examine neural network equalization in a perpendicular magnetic recording channel with jitter medium noise and MR nonlinear distortion. First, we propose simplifying a neural network equalizer by using a hybrid genetic algorithm. Next, we determine the bit error rate of a PR2ML method provided with the simplified neural network equalizer and compare it to those of a conventional neural network equalizer and a transversal filter equalizer. The results were improvements of about 0.8 and 2.0 dB in the SNR of the PR2ML method using the simplified neural network equalizer compared to the conventional neural network equalizer and the transversal filter equalizer, respectively.",

keywords = "Genetic algorithm, Jitter medium noise, MR nonlinear distortion, Neural network equalizer, Perpendicular magnetic recording",

author = "Hisashi Osawa and Toshimasa Shimizu and Takumi Nakaoka and Yoshihiro Okamoto and Hidetoshi Saito and Hiroaki Muraoka and Yoshihisa Nakamura",

year = "2006",

month = feb,

day = "1",

doi = "10.1002/ecjb.20197",

language = "English",

volume = "89",

pages = "19--27",

journal = "Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)",

issn = "8756-663X",

publisher = "Scripta Technica",

number = "2",

}

TY - JOUR

T1 - Simplification of neural network equalizer for perpendicular magnetic recording

AU - Osawa, Hisashi

AU - Shimizu, Toshimasa

AU - Nakaoka, Takumi

AU - Okamoto, Yoshihiro

AU - Saito, Hidetoshi

AU - Muraoka, Hiroaki

AU - Nakamura, Yoshihisa

PY - 2006/2/1

Y1 - 2006/2/1

N2 - In this paper, we examine neural network equalization in a perpendicular magnetic recording channel with jitter medium noise and MR nonlinear distortion. First, we propose simplifying a neural network equalizer by using a hybrid genetic algorithm. Next, we determine the bit error rate of a PR2ML method provided with the simplified neural network equalizer and compare it to those of a conventional neural network equalizer and a transversal filter equalizer. The results were improvements of about 0.8 and 2.0 dB in the SNR of the PR2ML method using the simplified neural network equalizer compared to the conventional neural network equalizer and the transversal filter equalizer, respectively.

AB - In this paper, we examine neural network equalization in a perpendicular magnetic recording channel with jitter medium noise and MR nonlinear distortion. First, we propose simplifying a neural network equalizer by using a hybrid genetic algorithm. Next, we determine the bit error rate of a PR2ML method provided with the simplified neural network equalizer and compare it to those of a conventional neural network equalizer and a transversal filter equalizer. The results were improvements of about 0.8 and 2.0 dB in the SNR of the PR2ML method using the simplified neural network equalizer compared to the conventional neural network equalizer and the transversal filter equalizer, respectively.

KW - Genetic algorithm

KW - Jitter medium noise

KW - MR nonlinear distortion

KW - Neural network equalizer

KW - Perpendicular magnetic recording

UR - http://www.scopus.com/inward/record.url?scp=32944455293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=32944455293&partnerID=8YFLogxK

U2 - 10.1002/ecjb.20197

DO - 10.1002/ecjb.20197

M3 - Article

AN - SCOPUS:32944455293

SN - 8756-663X

VL - 89

SP - 19

EP - 27

JO - Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)

JF - Electronics and Communications in Japan, Part II: Electronics (English translation of Denshi Tsushin Gakkai Ronbunshi)

IS - 2

ER -

Simplification of neural network equalizer for perpendicular magnetic recording

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this