Simplified neural network equalizer with noise whitening function for GPRML system

Hisashi Osawa; Masaya Hino; Nobuhiko Shinohara; Yoshihiro Okamoto; Yasuaki Nakamura; Hiroaki Muraoka

doi:10.1109/TMAG.2008.2002425

Simplified neural network equalizer with noise whitening function for GPRML system

Hisashi Osawa, Masaya Hino, Nobuhiko Shinohara, Yoshihiro Okamoto, Yasuaki Nakamura, Hiroaki Muraoka

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

19 Citations (Scopus)

Abstract

A new design method of the simplified neural network equalizer (NNE) with the noise whitening function for a generalized partial response (GPR) channel is proposed. The long-term bit error rate performance of GPR class-I maximum likelihood (GPR1ML) system employing NNE in perpendicular magnetic recording (PMR) channel with thermal decay is also obtained by computer simulation using our thermal decay model for a CoPtCr-SiO₂ PMR medium with K _uV/κT = 60. The performance of GPR1ML system with NNE (GPR1ML-NNE) is superior to that of GPR1ML with a transversal filter equalizer. The PR1ML system using a noise whitening NNE and a two-state Viterbi detector provides almost equivalent performance to that of GPR1ML-NNE having a 16-state detector.

Original language	English
Pages (from-to)	3777-3780
Number of pages	4
Journal	IEEE Transactions on Magnetics
Volume	44
Issue number	11 PART 2
DOIs	https://doi.org/10.1109/TMAG.2008.2002425
Publication status	Published - 2008 Nov
Externally published	Yes

Keywords

Generalized partial response class-I maximum likelihood (GPR1ML) system
Neural network equalizer
Perpendicular magnetic recording (PMR)
Thermal decay

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Access to Document

10.1109/TMAG.2008.2002425

Cite this

@article{3ec0acc70dd24aedacb91289e07f8899,

title = "Simplified neural network equalizer with noise whitening function for GPRML system",

abstract = "A new design method of the simplified neural network equalizer (NNE) with the noise whitening function for a generalized partial response (GPR) channel is proposed. The long-term bit error rate performance of GPR class-I maximum likelihood (GPR1ML) system employing NNE in perpendicular magnetic recording (PMR) channel with thermal decay is also obtained by computer simulation using our thermal decay model for a CoPtCr-SiO2 PMR medium with K uV/κT = 60. The performance of GPR1ML system with NNE (GPR1ML-NNE) is superior to that of GPR1ML with a transversal filter equalizer. The PR1ML system using a noise whitening NNE and a two-state Viterbi detector provides almost equivalent performance to that of GPR1ML-NNE having a 16-state detector.",

keywords = "Generalized partial response class-I maximum likelihood (GPR1ML) system, Neural network equalizer, Perpendicular magnetic recording (PMR), Thermal decay",

author = "Hisashi Osawa and Masaya Hino and Nobuhiko Shinohara and Yoshihiro Okamoto and Yasuaki Nakamura and Hiroaki Muraoka",

note = "Funding Information: This work was supported in part by the Japan Society for the Promotion of Science (JSPS) under Grants-in-Aid for Scientific Research 17360182, and by the Storage Research Consortium (SRC), Japan, under Grants-in-Aid. The authors would like to thank Prof. S. Tazaki of Onomichi University and Dr. M. Z. Ahmed of University of Plymouth for their helpful discussions.",

year = "2008",

month = nov,

doi = "10.1109/TMAG.2008.2002425",

language = "English",

volume = "44",

pages = "3777--3780",

journal = "IEEE Transactions on Magnetics",

issn = "0018-9464",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "11 PART 2",

}

TY - JOUR

T1 - Simplified neural network equalizer with noise whitening function for GPRML system

AU - Osawa, Hisashi

AU - Hino, Masaya

AU - Shinohara, Nobuhiko

AU - Okamoto, Yoshihiro

AU - Nakamura, Yasuaki

AU - Muraoka, Hiroaki

N1 - Funding Information: This work was supported in part by the Japan Society for the Promotion of Science (JSPS) under Grants-in-Aid for Scientific Research 17360182, and by the Storage Research Consortium (SRC), Japan, under Grants-in-Aid. The authors would like to thank Prof. S. Tazaki of Onomichi University and Dr. M. Z. Ahmed of University of Plymouth for their helpful discussions.

PY - 2008/11

Y1 - 2008/11

N2 - A new design method of the simplified neural network equalizer (NNE) with the noise whitening function for a generalized partial response (GPR) channel is proposed. The long-term bit error rate performance of GPR class-I maximum likelihood (GPR1ML) system employing NNE in perpendicular magnetic recording (PMR) channel with thermal decay is also obtained by computer simulation using our thermal decay model for a CoPtCr-SiO2 PMR medium with K uV/κT = 60. The performance of GPR1ML system with NNE (GPR1ML-NNE) is superior to that of GPR1ML with a transversal filter equalizer. The PR1ML system using a noise whitening NNE and a two-state Viterbi detector provides almost equivalent performance to that of GPR1ML-NNE having a 16-state detector.

AB - A new design method of the simplified neural network equalizer (NNE) with the noise whitening function for a generalized partial response (GPR) channel is proposed. The long-term bit error rate performance of GPR class-I maximum likelihood (GPR1ML) system employing NNE in perpendicular magnetic recording (PMR) channel with thermal decay is also obtained by computer simulation using our thermal decay model for a CoPtCr-SiO2 PMR medium with K uV/κT = 60. The performance of GPR1ML system with NNE (GPR1ML-NNE) is superior to that of GPR1ML with a transversal filter equalizer. The PR1ML system using a noise whitening NNE and a two-state Viterbi detector provides almost equivalent performance to that of GPR1ML-NNE having a 16-state detector.

KW - Generalized partial response class-I maximum likelihood (GPR1ML) system

KW - Neural network equalizer

KW - Perpendicular magnetic recording (PMR)

KW - Thermal decay

UR - http://www.scopus.com/inward/record.url?scp=77955158583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955158583&partnerID=8YFLogxK

U2 - 10.1109/TMAG.2008.2002425

DO - 10.1109/TMAG.2008.2002425

M3 - Article

AN - SCOPUS:77955158583

SN - 0018-9464

VL - 44

SP - 3777

EP - 3780

JO - IEEE Transactions on Magnetics

JF - IEEE Transactions on Magnetics

IS - 11 PART 2

ER -

Simplified neural network equalizer with noise whitening function for GPRML system

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this