Decoding Quadratic Residue Codes Using Deep Neural Networks

Ming Wang; Yong Li; Rui Liu; Huihui Wu; Youqiang Hu; Francis C.M. Lau

doi:10.3390/electronics11172717

Decoding Quadratic Residue Codes Using Deep Neural Networks

Ming Wang, Yong Li, Rui Liu, Huihui Wu, Youqiang Hu, Francis C.M. Lau

Research output: Journal article publication › Journal article › Academic research › peer-review

Abstract

In this paper, a low-complexity decoder based on a neural network is proposed to decode binary quadratic residue (QR) codes. The proposed decoder is based on the neural min-sum algorithm and the modified random redundant decoder (mRRD) algorithm. This new method has the same asymptotic time complexity as the min-sum algorithm, which is much lower than the difference on syndromes (DS) algorithm. Simulation results show that the proposed algorithm achieves a gain of more than 0.4 dB when compared to the DS algorithm. Furthermore, a simplified approach based on trapping sets is applied to reduce the complexity of the mRRD. This simplification leads to a slight loss in error performance and a reduction in implementation complexity.

Original language	English
Article number	2717
Pages (from-to)	1-15
Journal	Electronics (Switzerland)
Volume	11
Issue number	17
DOIs	https://doi.org/10.3390/electronics11172717
Publication status	Published - Sep 2022

Keywords

deep learning
iterative decoding
quadratic residue codes

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Hardware and Architecture
Computer Networks and Communications
Electrical and Electronic Engineering

More information

10.3390/electronics11172717

Cite this

@article{fa209d8109314572be4cc70e9536b53e,

title = "Decoding Quadratic Residue Codes Using Deep Neural Networks",

abstract = "In this paper, a low-complexity decoder based on a neural network is proposed to decode binary quadratic residue (QR) codes. The proposed decoder is based on the neural min-sum algorithm and the modified random redundant decoder (mRRD) algorithm. This new method has the same asymptotic time complexity as the min-sum algorithm, which is much lower than the difference on syndromes (DS) algorithm. Simulation results show that the proposed algorithm achieves a gain of more than 0.4 dB when compared to the DS algorithm. Furthermore, a simplified approach based on trapping sets is applied to reduce the complexity of the mRRD. This simplification leads to a slight loss in error performance and a reduction in implementation complexity.",

keywords = "deep learning, iterative decoding, quadratic residue codes",

author = "Ming Wang and Yong Li and Rui Liu and Huihui Wu and Youqiang Hu and Lau, {Francis C.M.}",

note = "Funding Information: This work was supported by China Natural Science Foundation (NSF) under Grant 61771081, the Fundamental Research Funds for the Central Universities (China) under Grant cstc2019jcyjmsxmX0110. Publisher Copyright: {\textcopyright} 2022 by the authors.",

year = "2022",

month = sep,

doi = "10.3390/electronics11172717",

language = "English",

volume = "11",

pages = "1--15",

journal = "Electronics (Switzerland)",

issn = "2079-9292",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "17",

}

TY - JOUR

T1 - Decoding Quadratic Residue Codes Using Deep Neural Networks

AU - Wang, Ming

AU - Li, Yong

AU - Liu, Rui

AU - Wu, Huihui

AU - Hu, Youqiang

AU - Lau, Francis C.M.

N1 - Funding Information: This work was supported by China Natural Science Foundation (NSF) under Grant 61771081, the Fundamental Research Funds for the Central Universities (China) under Grant cstc2019jcyjmsxmX0110. Publisher Copyright: © 2022 by the authors.

PY - 2022/9

Y1 - 2022/9

N2 - In this paper, a low-complexity decoder based on a neural network is proposed to decode binary quadratic residue (QR) codes. The proposed decoder is based on the neural min-sum algorithm and the modified random redundant decoder (mRRD) algorithm. This new method has the same asymptotic time complexity as the min-sum algorithm, which is much lower than the difference on syndromes (DS) algorithm. Simulation results show that the proposed algorithm achieves a gain of more than 0.4 dB when compared to the DS algorithm. Furthermore, a simplified approach based on trapping sets is applied to reduce the complexity of the mRRD. This simplification leads to a slight loss in error performance and a reduction in implementation complexity.

AB - In this paper, a low-complexity decoder based on a neural network is proposed to decode binary quadratic residue (QR) codes. The proposed decoder is based on the neural min-sum algorithm and the modified random redundant decoder (mRRD) algorithm. This new method has the same asymptotic time complexity as the min-sum algorithm, which is much lower than the difference on syndromes (DS) algorithm. Simulation results show that the proposed algorithm achieves a gain of more than 0.4 dB when compared to the DS algorithm. Furthermore, a simplified approach based on trapping sets is applied to reduce the complexity of the mRRD. This simplification leads to a slight loss in error performance and a reduction in implementation complexity.

KW - deep learning

KW - iterative decoding

KW - quadratic residue codes

UR - http://www.scopus.com/inward/record.url?scp=85137775826&partnerID=8YFLogxK

U2 - 10.3390/electronics11172717

DO - 10.3390/electronics11172717

M3 - Journal article

AN - SCOPUS:85137775826

VL - 11

SP - 1

EP - 15

JO - Electronics (Switzerland)

JF - Electronics (Switzerland)

SN - 2079-9292

IS - 17

M1 - 2717

ER -

Decoding Quadratic Residue Codes Using Deep Neural Networks

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this