A Unified Deep Learning Based Polar-LDPC Decoder for 5G Communication Systems

Yaohan Wang, Zhichao Zhang, Shunqing Zhang, Shan Cao, Shugong Xu

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

31 Citations (Scopus)

Abstract

In the 5G communication systems, a hybrid approach to support polar codes for control plane and LDPC codes for data plane has been identified as the channel coding solution for enhanced mobile broadband (eMBB) scenario. One of the major challenges to implement this approach is to design powerful decoders at the terminal side. Inspired from a useful machine learning based polar decoder, we proposed a deep learning based unified polar-LDPC by concatenating an indicator section. Through numerical experiments, we show that the proposed deep neural network (DNN) based decoding architecture can achieve the similar decoding performance compared with the traditional BP-based decoding algorithm. Meanwhile, the proposed unified approach shares the same network architecture and parameters with isolated approaches, which saves significant implementation resources consequently.

Original languageEnglish
Title of host publication2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538661192
DOIs
Publication statusPublished - 30 Nov 2018
Externally publishedYes
Event10th International Conference on Wireless Communications and Signal Processing, WCSP 2018 - Hangzhou, China
Duration: 18 Oct 201820 Oct 2018

Publication series

Name2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018

Conference

Conference10th International Conference on Wireless Communications and Signal Processing, WCSP 2018
Country/TerritoryChina
CityHangzhou
Period18/10/1820/10/18

Keywords

  • deep learning
  • deep neural networks
  • LDPC codes
  • polar codes
  • unified architecture

Fingerprint

Dive into the research topics of 'A Unified Deep Learning Based Polar-LDPC Decoder for 5G Communication Systems'. Together they form a unique fingerprint.

Cite this