Recurrent Neural Network-Aided BP Decoder Based on Bit-flipping for Polar Codes

Compared with SC decoding, BP decoding with the parallel mechanism has higher throughput and lower latency, which is more suitable for the demand of 5G scene. To further improve its FER performance and reduce the memory overhead, a recurrent neural network-aided bit-flipping BP decoding of polar cod...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of advanced network, monitoring, and controls Vol. 10; no. 1; pp. 38 - 49
Main Authors Li, Guiping, Yun, Chang, Liu, Xiaojie
Format Journal Article
LanguageEnglish
Published Xi'an Sciendo 01.01.2025
De Gruyter Poland
Subjects
Algorithms
Belief Propagation
Bit-flip
Codes
Deep learning
Error correction & detection
Internet of Things
Neural networks
Polar Codes
Recurrent Neural Network
Online AccessGet full text

Cover

More Information
Summary:Compared with SC decoding, BP decoding with the parallel mechanism has higher throughput and lower latency, which is more suitable for the demand of 5G scene. To further improve its FER performance and reduce the memory overhead, a recurrent neural network-aided bit-flipping BP decoding of polar codes is proposed. Firstly, it uses bit flip to correct the wrong decoded bits during the decoding iteration. And then, the offset min-sum approximation is used to replace multiplication operation. Lastly the improved recurrent neural network architecture is adopted to realize parameter sharing. The simulation shows that the proposed scheme has a better error correction ability with fewer flipping times, and can effectively reduce the computational resource consumption and extra memory overhead of BP decoding.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2470-8038
2470-8038
DOI:10.2478/ijanmc-2025-0004