Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

IEEE International Symposium on Microwave, Antenna, Propagation and EMC Technologies for Wireless Communications

A Class of Turbo-Like LDPC Codes and Their Decoding Based on Neural Network

Zijian Zhao, Xiaojuan Wu, Jun Yang

Published Apr 28, 2006• 1 citation
Publisher

Abstract

Turbo codes and LDPC codes are both superior to other error correcting codes. These two families of codes have some similarities. It seems a good idea to design new codes combining these two codes. Through the analysis of turbo codes, we can consider turbo codes as block codes and find their matrix H. In this paper, we give a new class of turbo-like LDPC codes combining the advantages of turbo and LDPC codes and a decoding method based on neural network. A lot of simulations have been made and the results reveal that these codes have robuster performance than turbo codes.

DOI
10.1109/mape.2005.1618080

Related papers

Multi Layer Perceptron Neural Networks Decoder for LDPC Codes

A. R. Karami, Mahmoud Ahmadian‐Attari, Hassan Tavakoli

A very important and near optimum group of the block codes that have been developed in direction of Shannon's theory concept, is low density parity check (LDPC) code. There have been presented different algorithms for decoding of this class of code such as maximum likelihood (ML), bit flipping (BF), a posteriori probability (APP) and sum product (SP) algorithms that the first two of them decode by hard criterion and two others decode by soft criterion. In this article, considering LDPC codes structure and taking advantage of LDPC codes demonstrated by Tanner graph, we have presented a quite new method based on multi layer perceptron (MLP) neural networks that decodes LDPC codes by soft decision manner. This method opens another new way for LDPC and even other block codes decoding. Simulation results display good performance of this method compared to other known algorithms.

International Conference on Wireless Communications, Networking and Mobile Computing•Sep 1, 2009•14 citations

Nonbinary decoding of structured LDPC codes

Daniele Capirone, Giacomo Como, Fabio Fagnani +1 more

A class of serial turbo codes admitting low-density parity-check (LDPC) representation is considered. Their parity matrix has a random and a structured part. Thanks to their turbo structure, these codes are linear-time encodable, while they can be decoded as LDPC codes. An ensemble analysis for the error floor region, on the line of classical results for serial turbo codes, suggests a design parameter. Simulation results using usual LDPC message-passing show poor performance and no dependence on such parameter. A different block-wise decoding algorithm is proposed, which considerably improves performance. With this new decoding scheme, simulations confirm the theoretical design parameters in the medium-high SNR region.

International Zurich Seminar on Communications (IZS)•Mar 1, 2008•3 citations

A Weighted Block-by-Block Decoding Algorithm for CPM-QC-LDPC Code Using Neural Network

Zuohong Xu, Jiang Zhu, Zixuan Zhang +1 more

As one of the most potential types of low-density parity-check (LDPC) codes, CPM-QC-LDPC code has considerable advantages but there still exist some limitations in practical application, for example, the existing decoding algorithm has a low convergence rate and a high decoding complexity.According to the structural property of this code, we propose a new method based on a CPM-RID decoding algorithm that decodes block-by-block with weights, which are obtained by neural network training.From the simulation results, we can conclude that our proposed method not only improves the bit error rate and frame error rate performance but also increases the convergence rate, when compared with the original CPM-RID decoding algorithm and scaled MSA algorithm.

KSII Transactions on Internet and Information Systems•Aug 31, 2018•0 citations

Overview of LDPC Decoding Based on Deep Learning

Xiangwei Ren, Tao Tang, Hong Wen +3 more

LDPC codes, as an error correcting code close to the Shannon limit, are widely used in modern communication systems such as 5 G, satellite communication, deep space communication, and other fields. Traditional LDPC decoding algorithms, such as belief propagation (BP) algorithm and its variants, have achieved good performance, but face challenges such as high complexity and slow convergence, especially when dealing with long code lengths and high noise scenarios. The rise of deep learning has brought new opportunities for LDPC decoding, and its powerful features learning and pattern recognition capabilities are expected to break through the bottleneck of traditional decoding. Based on the overview of deep neural network decoding methods for LDPC codes by data-driven and model driven approaches, this paper analysis and comparison of error rate performance of short code$\mathbf{H} (8,16)$matrix by convolutional neural networks (CNN), residual network (ResNet), and Kolmogorov-Arnold Network (KAN).

IEEE International Conference on Artificial Intelligence, Computer Science and Information Processing (AICSIP)•Jul 25, 2025•0 citations

Research on Performance of Regular LDPC Codes better than Turbo Codes

HE He-yun

A kind of regular LDPC codes is introduced.Its error correcting capability is better than Turbo codes' and approaches to Shannon limit(1.2 dB).The construction of the sparse parity matrix is important,which affects the LDPC codes' error correcting capability.In this paper,the diagonal method is adopted to construct sparse check matrix of(n,3,6) in approximate lower triangle,which meets the numbers of and distribution randomicity of nonzero elements.The belief propagation algorithm is used in decoding simulation,and the vectorization method is proposed to reduce the iteration decoding time.

Radio Engineering of China•Jan 1, 2008•0 citations

Research on Regular LDPC Codes with better Performance than Turbo Codes

Jian-Bing Han, He Yun He

A kind of regular LDPC codes is introduced. Its error correct ability is better than Turbo codes' and near to Shannon limit (1.2 dB). The construct of the sparse parity matrix is important. This effects the LDPC codes' error correct ability. In this paper, diagonal method is adopted to construct sparse check matrix of (n,3,6) in approximate lower triangular form by it. This meets the numbers of nonzero elements and randomness. The Belief Propagation algorithm is used in decoding simulation, to this, vector method is proposed which reduces operation time.

WASE International Conference on Information Engineering•Jul 1, 2009•4 citations
Turbo codes and LDPC codes are both superior to other error correcting codes. These two families of codes have some similarities. It seems a good idea to design new codes combining these two codes. Through the analysis of turbo codes, we can consider turbo codes as block codes and find their matrix H. In this paper, we give a new class of turbo-like LDPC codes combining the advantages of turbo and LDPC codes and a decoding method based on neural network. A lot of simulations have been made and the results reveal that these codes have robuster performance than turbo codes.
A very important and near optimum group of the block codes that have been developed in direction of Shannon's theory concept, is low density parity check (LDPC) code. There have been presented different algorithms for decoding of this class of code such as maximum likelihood (ML), bit flipping (BF), a posteriori probability (APP) and sum product (SP) algorithms that the first two of them decode by hard criterion and two others decode by soft criterion. In this article, considering LDPC codes structure and taking advantage of LDPC codes demonstrated by Tanner graph, we have presented a quite new method based on multi layer perceptron (MLP) neural networks that decodes LDPC codes by soft decision manner. This method opens another new way for LDPC and even other block codes decoding. Simulation results display good performance of this method compared to other known algorithms.
A class of serial turbo codes admitting low-density parity-check (LDPC) representation is considered. Their parity matrix has a random and a structured part. Thanks to their turbo structure, these codes are linear-time encodable, while they can be decoded as LDPC codes. An ensemble analysis for the error floor region, on the line of classical results for serial turbo codes, suggests a design parameter. Simulation results using usual LDPC message-passing show poor performance and no dependence on such parameter. A different block-wise decoding algorithm is proposed, which considerably improves performance. With this new decoding scheme, simulations confirm the theoretical design parameters in the medium-high SNR region.
As one of the most potential types of low-density parity-check (LDPC) codes, CPM-QC-LDPC code has considerable advantages but there still exist some limitations in practical application, for example, the existing decoding algorithm has a low convergence rate and a high decoding complexity.According to the structural property of this code, we propose a new method based on a CPM-RID decoding algorithm that decodes block-by-block with weights, which are obtained by neural network training.From the simulation results, we can conclude that our proposed method not only improves the bit error rate and frame error rate performance but also increases the convergence rate, when compared with the original CPM-RID decoding algorithm and scaled MSA algorithm.
LDPC codes, as an error correcting code close to the Shannon limit, are widely used in modern communication systems such as 5 G, satellite communication, deep space communication, and other fields. Traditional LDPC decoding algorithms, such as belief propagation (BP) algorithm and its variants, have achieved good performance, but face challenges such as high complexity and slow convergence, especially when dealing with long code lengths and high noise scenarios. The rise of deep learning has brought new opportunities for LDPC decoding, and its powerful features learning and pattern recognition capabilities are expected to break through the bottleneck of traditional decoding. Based on the overview of deep neural network decoding methods for LDPC codes by data-driven and model driven approaches, this paper analysis and comparison of error rate performance of short codeH(8,16)\mathbf{H} (8,16)H(8,16)matrix by convolutional neural networks (CNN), residual network (ResNet), and Kolmogorov-Arnold Network (KAN).
A kind of regular LDPC codes is introduced.Its error correcting capability is better than Turbo codes' and approaches to Shannon limit(1.2 dB).The construction of the sparse parity matrix is important,which affects the LDPC codes' error correcting capability.In this paper,the diagonal method is adopted to construct sparse check matrix of(n,3,6) in approximate lower triangle,which meets the numbers of and distribution randomicity of nonzero elements.The belief propagation algorithm is used in decoding simulation,and the vectorization method is proposed to reduce the iteration decoding time.
A kind of regular LDPC codes is introduced. Its error correct ability is better than Turbo codes' and near to Shannon limit (1.2 dB). The construct of the sparse parity matrix is important. This effects the LDPC codes' error correct ability. In this paper, diagonal method is adopted to construct sparse check matrix of (n,3,6) in approximate lower triangular form by it. This meets the numbers of nonzero elements and randomness. The Belief Propagation algorithm is used in decoding simulation, to this, vector method is proposed which reduces operation time.