Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel

The neural successive cancellation (NSC) decoder with tanh-based modified log-likelihood ratio (LLR) is proposed for reducing the decoding latency of polar codes over free space optical (FSO) turbulence channel. The conventional successive cancellation (SC) decoder is partitioned into multiple sub-b...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiafei Fang, Meihua Bi, Shilin Xiao, Hang Yang, Zhiyu Chen, Zhiyang Liu, Weisheng Hu
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9222501/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417448763162624
author Jiafei Fang
Meihua Bi
Shilin Xiao
Hang Yang
Zhiyu Chen
Zhiyang Liu
Weisheng Hu
author_facet Jiafei Fang
Meihua Bi
Shilin Xiao
Hang Yang
Zhiyu Chen
Zhiyang Liu
Weisheng Hu
author_sort Jiafei Fang
collection DOAJ
description The neural successive cancellation (NSC) decoder with tanh-based modified log-likelihood ratio (LLR) is proposed for reducing the decoding latency of polar codes over free space optical (FSO) turbulence channel. The conventional successive cancellation (SC) decoder is partitioned into multiple sub-blocks, which are replaced by multiple sub neural network (NN) decoders with tanh-based modified LLR. The recursive characteristic of the polar sequences reliability ranking given in 5G standard enables the sub-NN decoder to be uniquely determined by code length and the number of information bits. Confirmed by the simulation, the bit error rate (BER) performance of NSC decoder with tanh-based modified LLR is close to the conventional SC decoder over turbulence channel for the practical-length polar codes. Regarding turbulence-stability, the NSC decoder trained in moderate and strong turbulence conditions have stable performance in a wide range of turbulence conditions. Moreover, in comparison of decoding latency, the NSC decoder with tanh-based modified LLR takes less than 25% time steps of SC decoder in the same code length.
format Article
id doaj-art-de9f3deb6a5f4e23ae13c8aa289d4ba9
institution Kabale University
issn 1943-0655
language English
publishDate 2020-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-de9f3deb6a5f4e23ae13c8aa289d4ba92025-08-20T03:32:50ZengIEEEIEEE Photonics Journal1943-06552020-01-0112611010.1109/JPHOT.2020.30306189222501Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence ChannelJiafei Fang0https://orcid.org/0000-0003-3128-554XMeihua Bi1https://orcid.org/0000-0001-8177-1808Shilin Xiao2https://orcid.org/0000-0003-0887-782XHang Yang3Zhiyu Chen4Zhiyang Liu5Weisheng Hu6https://orcid.org/0000-0002-6168-2688The State Key Laboratory of Advanced Optical Communication System and Networks, Shanghai Jiao Tong University, Shanghai, ChinaThe State Key Laboratory of Advanced Optical Communication System and Networks, Shanghai Jiao Tong University, Shanghai, ChinaThe State Key Laboratory of Advanced Optical Communication System and Networks, Shanghai Jiao Tong University, Shanghai, ChinaThe State Key Laboratory of Advanced Optical Communication System and Networks, Shanghai Jiao Tong University, Shanghai, ChinaThe State Key Laboratory of Advanced Optical Communication System and Networks, Shanghai Jiao Tong University, Shanghai, ChinaThe State Key Laboratory of Advanced Optical Communication System and Networks, Shanghai Jiao Tong University, Shanghai, ChinaThe State Key Laboratory of Advanced Optical Communication System and Networks, Shanghai Jiao Tong University, Shanghai, ChinaThe neural successive cancellation (NSC) decoder with tanh-based modified log-likelihood ratio (LLR) is proposed for reducing the decoding latency of polar codes over free space optical (FSO) turbulence channel. The conventional successive cancellation (SC) decoder is partitioned into multiple sub-blocks, which are replaced by multiple sub neural network (NN) decoders with tanh-based modified LLR. The recursive characteristic of the polar sequences reliability ranking given in 5G standard enables the sub-NN decoder to be uniquely determined by code length and the number of information bits. Confirmed by the simulation, the bit error rate (BER) performance of NSC decoder with tanh-based modified LLR is close to the conventional SC decoder over turbulence channel for the practical-length polar codes. Regarding turbulence-stability, the NSC decoder trained in moderate and strong turbulence conditions have stable performance in a wide range of turbulence conditions. Moreover, in comparison of decoding latency, the NSC decoder with tanh-based modified LLR takes less than 25% time steps of SC decoder in the same code length.https://ieeexplore.ieee.org/document/9222501/FSOPolar CodesDeep Learning
spellingShingle Jiafei Fang
Meihua Bi
Shilin Xiao
Hang Yang
Zhiyu Chen
Zhiyang Liu
Weisheng Hu
Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel
IEEE Photonics Journal
FSO
Polar Codes
Deep Learning
title Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel
title_full Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel
title_fullStr Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel
title_full_unstemmed Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel
title_short Neural Successive Cancellation Polar Decoder With Tanh-Based Modified LLR Over FSO Turbulence Channel
title_sort neural successive cancellation polar decoder with tanh based modified llr over fso turbulence channel
topic FSO
Polar Codes
Deep Learning
url https://ieeexplore.ieee.org/document/9222501/
work_keys_str_mv AT jiafeifang neuralsuccessivecancellationpolardecoderwithtanhbasedmodifiedllroverfsoturbulencechannel
AT meihuabi neuralsuccessivecancellationpolardecoderwithtanhbasedmodifiedllroverfsoturbulencechannel
AT shilinxiao neuralsuccessivecancellationpolardecoderwithtanhbasedmodifiedllroverfsoturbulencechannel
AT hangyang neuralsuccessivecancellationpolardecoderwithtanhbasedmodifiedllroverfsoturbulencechannel
AT zhiyuchen neuralsuccessivecancellationpolardecoderwithtanhbasedmodifiedllroverfsoturbulencechannel
AT zhiyangliu neuralsuccessivecancellationpolardecoderwithtanhbasedmodifiedllroverfsoturbulencechannel
AT weishenghu neuralsuccessivecancellationpolardecoderwithtanhbasedmodifiedllroverfsoturbulencechannel