LDPC hard decision decoding method based on depth learning and decoder

A technology of deep learning and hard judgment, which is applied in the direction of error detection coding, coding, and code conversion of multiple parity bits, and can solve problems such as low decoding efficiency, difficult implementation, and large calculation and comparison values. , to achieve high decoding efficiency, reduce the amount of calculation and complexity

Active Publication Date: 2017-04-19
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When k is large, the value of calculation and comparison is too large, it is very difficult to realize, and the decoding efficiency is not high

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
  • LDPC hard decision decoding method based on depth learning and decoder
  • LDPC hard decision decoding method based on depth learning and decoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] The present invention takes the 1 / 2 code rate LDPC code as an example, and describes in detail the LDPC hard-decision decoding method and decoder based on deep learning provided by the present invention.

[0030] For the (16,32) LDPC code with a code rate of 1 / 2, Y represents the correct information sequence, and there are a total of 2 16 group, X represents the encoded codeword sequence of Y, and there are 2 16 Group.

[0031] like figure 1 As shown, a deep learning-based LDPC hard-decision decoding method includes the following steps:

[0032] (1) Establish a LDPC decoding sample set: a set of (X, Y) is used as a labeled data, and a large number of labeled samples (X, Y) are obtained to form a decoding sample set. For a code rate of 1 / 2 The (16,32) LDPC code, Y represents the correct information sequence, a total of 2 16 group, X represents the encoded codeword sequence of Y, and there are 2 16 Group;

[0033] (2) Establishment of deep learning decoding model: e...

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 LDPC hard decision decoding method based on depth learning; the method comprises the following steps: 1, using a group (X, Y) as a group of labeled data; 2, building a LDPC decoding sample set; 3, building a depth learning decoding model; 4, pre-training the depth learning decoding model; 5, allowing the depth learning decoding model to decode and output data. The invention also discloses a decoder using the LDPC hard decision decoding method based on depth learning; the decoder comprises an input unit, the depth learning decoding model, an output unit, and a controller. The invention imports the LDPC hard decision decoding method based on depth learning on the basis of a conventional maximum likelihood decoding algorithm, thus reducing decoding computational quantity and complexity, and improving decoding efficiency.

Description

technical field [0001] The present invention relates to the technical field of electronic communication, in particular to an LDPC hard-decision decoding method and a decoder based on deep learning. Background technique [0002] Low Density Parity Check Code (LDPC, Low Density Parity Check Code) is a linear block error correction code with low decoding complexity and good performance. Its bit error performance is close to the Shannon limit in information theory. Due to its superior performance and easy parallel implementation, it is widely used in various fields of modern communication, such as high-speed optical fiber communication, high-definition digital TV broadcasting, and is recognized by various modern communication standards. use. [0003] After Professor Hinton published the contrastive divergence algorithm in 2002, deep learning has greatly promoted the development of deep learning, and at the same time reduced the computational complexity of the deep learning netw...

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): H03M13/11
CPCH03M13/1108
Inventor 姜小波李杰魏凯
Owner SOUTH CHINA UNIV OF TECH
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