Neural Network Aided Path Splitting Strategy for Polar Successive Cancellation List Decoding

Bin Dai, Chenyu Gao, Francis C.M. Lau, Yulong Zou

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

Combined with the path splitting selecting (PSS) strategy, the successive cancellation list (SCL) decoder achieves a lower decoding complexity without any performance loss. The main purpose of the PSS strategy is to select fewer non-frozen bits to perform the path splitting and pruning operations. To make the selection more efficient, a neural network aided path splitting selecting strategy is proposed in this paper. In the proposed method, the path splitting is seen as a classification problem. With the help of the neural network, the proposed method can precisely locate the non-frozen bits which are needed to be split. Simulation results verify that the proposed method can reduce the sorting complexity (which is equal to the number of path splitting) without any performance loss.

Original languageEnglish
Article number10049489
Pages (from-to)1-5
Number of pages5
JournalIEEE Transactions on Vehicular Technology
DOIs
Publication statusPublished - Feb 2023

Keywords

  • Artificial neural networks
  • Complexity theory
  • Maximum likelihood decoding
  • neural network
  • Neurons
  • path splitting
  • Polar codes
  • Reliability
  • Sorting
  • successive cancellation list (SCL) decoding

ASJC Scopus subject areas

  • Automotive Engineering
  • Aerospace Engineering
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Neural Network Aided Path Splitting Strategy for Polar Successive Cancellation List Decoding'. Together they form a unique fingerprint.

Cite this