A UnetNND-BP Architecture for Channel Decoding Under Correlated Noise

Huiying Chen; Pengchao Zhao; Chengju Li

doi:10.1109/LCOMM.2024.3362509

A UnetNND-BP Architecture for Channel Decoding Under Correlated Noise

Huiying Chen, Pengchao Zhao, Chengju Li

Software Engineering Institute

East China Normal University

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

Abstract

In this letter, we introduce a Unet-based neural network denoiser-belief propagation (UnetNND-BP) architecture with two training modes to improve the decoding performance of low-density parity-check (LDPC) codes. In the supervised learning mode, UnetNND-BP achieves better performance than benchmark schemes, while in the self-supervised learning mode, it achieves comparable performance.

Original language	English
Pages (from-to)	823-826
Number of pages	4
Journal	IEEE Communications Letters
Volume	28
Issue number	4
DOIs	https://doi.org/10.1109/LCOMM.2024.3362509
State	Published - 1 Apr 2024

Keywords

Channel decoding
LDPC
correlated noise
self-supervised learning

Access to Document

10.1109/LCOMM.2024.3362509

Cite this

@article{fea2b12b73234bc48f99bf7a4a574564,

title = "A UnetNND-BP Architecture for Channel Decoding Under Correlated Noise",

abstract = "In this letter, we introduce a Unet-based neural network denoiser-belief propagation (UnetNND-BP) architecture with two training modes to improve the decoding performance of low-density parity-check (LDPC) codes. In the supervised learning mode, UnetNND-BP achieves better performance than benchmark schemes, while in the self-supervised learning mode, it achieves comparable performance.",

keywords = "Channel decoding, LDPC, correlated noise, self-supervised learning",

author = "Huiying Chen and Pengchao Zhao and Chengju Li",

note = "Publisher Copyright: {\textcopyright} 1997-2012 IEEE.",

year = "2024",

month = apr,

day = "1",

doi = "10.1109/LCOMM.2024.3362509",

language = "英语",

volume = "28",

pages = "823--826",

journal = "IEEE Communications Letters",

issn = "1089-7798",

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

number = "4",

}

TY - JOUR

T1 - A UnetNND-BP Architecture for Channel Decoding Under Correlated Noise

AU - Chen, Huiying

AU - Zhao, Pengchao

AU - Li, Chengju

PY - 2024/4/1

Y1 - 2024/4/1

N2 - In this letter, we introduce a Unet-based neural network denoiser-belief propagation (UnetNND-BP) architecture with two training modes to improve the decoding performance of low-density parity-check (LDPC) codes. In the supervised learning mode, UnetNND-BP achieves better performance than benchmark schemes, while in the self-supervised learning mode, it achieves comparable performance.

AB - In this letter, we introduce a Unet-based neural network denoiser-belief propagation (UnetNND-BP) architecture with two training modes to improve the decoding performance of low-density parity-check (LDPC) codes. In the supervised learning mode, UnetNND-BP achieves better performance than benchmark schemes, while in the self-supervised learning mode, it achieves comparable performance.

KW - Channel decoding

KW - LDPC

KW - correlated noise

KW - self-supervised learning

UR - https://www.scopus.com/pages/publications/85184799363

U2 - 10.1109/LCOMM.2024.3362509

DO - 10.1109/LCOMM.2024.3362509

M3 - 文章

AN - SCOPUS:85184799363

SN - 1089-7798

VL - 28

SP - 823

EP - 826

JO - IEEE Communications Letters

JF - IEEE Communications Letters

IS - 4

ER -

A UnetNND-BP Architecture for Channel Decoding Under Correlated Noise

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this