Polar code adaptive decoding method and system

A decoding system and self-adaptive technology, applied in the transmission system, digital transmission system, error correction/detection using linear codes, etc., can solve the problems of reducing decoding complexity, not suitable for long code applications, and high training complexity , to achieve the effect of reducing computational complexity, reducing the number of path extensions, and improving applicability

Active Publication Date: 2019-09-06
南京宁麒智能计算芯片研究院有限公司
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to overcome the shortcomings of the prior art that the SC decoding algorithm based on deep learning has high training complexity and is not suitable for the application of long codes, and provides an adaptive decoding method for polar codes, which can reduce the decoding cost. Complexity, and can meet the different channel environment and configuration requirements of the communication system

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Polar code adaptive decoding method and system
  • Polar code adaptive decoding method and system
  • Polar code adaptive decoding method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] combine figure 1As shown, a polar code adaptive decoding method of the present invention first constructs a neural network and trains it, then inputs the path information to be decoded into the neural network to obtain the maximum number of paths in each layer of the information code binary tree; through the neural network The maximum path number of each layer in the information code binary tree of the decoder is obtained, so that the search width of each layer can be selected and determined, and then it can be applied to various SNR scenarios, improving the applicability of the method. Furthermore, the maximum number of paths in each layer is input to the decoder, and then the path to be decoded is extended in parallel according to the maximum number of paths in each layer to obtain candidate paths, thereby reducing the number of path extensions in each layer, thereby reducing the decoding The time and space complexity of the device; then calculate the transition proba...

Embodiment 2

[0062] combine image 3 In the decoding system shown, the code length N is 8, the number of information bits K is 4, and the search width L max is 4, the black nodes are the nodes visited by the system, and the gray nodes are the nodes visited by the traditional list decoding algorithm. The input vector of the neural network unit in this embodiment is a received codeword with a length of 8, and the output is a search width sequence with a length of 2, which is then transmitted to the decoding unit. In the decoding unit, when i=7, the corresponding Z 1 =1, so only one path is extended, and the same applies when i=8. Compared with the traditional list decoding algorithm, the number of access nodes in this system is significantly reduced, and it has a significant advantage in computational complexity.

[0063] combine Figure 4 as shown, Figure 4 The code length in N=64, the initial maximum search width L max =4, signal-to-noise ratio EbN0=1.0-4.0dB, under various signal-t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a polar code adaptive decoding method and system, and belongs to the field of wireless communication. The method comprises the following steps: firstly constructing and training a neural network, and inputting to-be-decoded path information into the neural network to obtain the maximum path number of each layer; and inputting the maximum path number of each layer into a decoder, and decoding the path information to be decoded by using the decoder to obtain a decoding result. The system comprises a neural network unit and a decoding unit, wherein the neural network unitis electrically connected with the decoding unit; the decoding unit comprises a path expansion unit and a sorting unit, the path expansion unit is electrically connected with the sorting unit, and thepath expansion unit is electrically connected with the neural network unit. The invention aims to overcome the defects that in the prior art, a decoding algorithm based on deep learning is high in training complexity and not suitable for long code application, the decoding complexity can be reduced, and different channel environments and configuration requirements of a communication system can bemet.

Description

technical field [0001] The present invention relates to the field of wireless communication, and more specifically, to a polar code adaptive decoding method and system. Background technique [0002] So far, channel coding has been developed for more than 70 years. The proposed polar code has been proven to be the first code that can achieve the channel capacity of symmetric binary-input, discrete, memoryless channels (B-DMC). In the 5G field test, the polar code has achieved great performance improvement effect, and was selected as the forward error correction (FEC) code for the control channel of the 5G enhanced mobile broadband (eMBB) control channel. To meet the low-latency and high-speed requirements of 5G, researchers have made great efforts to design polar code decoders with high hardware efficiency. At present, it is very urgent and necessary to study an efficient polar code decoder that can balance complexity and performance well. [0003] As one of the most wide...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): H03M13/13H04L1/00
CPCH03M13/13H04L1/0057H04L1/0052
Inventor 李丽宋文清
Owner 南京宁麒智能计算芯片研究院有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap