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

China Communications

Construction of protograph LDPC codes based on the convolution neural network

Zhiyuan Xiao, Liguang Li, Jin Xu, Jin Sha

Published Feb 28, 2023• 3 citations
Publisher

Abstract

This paper presents an intelligent protograph construction algorithm. Protograph LDPC codes have shown excellent error correction performance and play an important role in wireless communications. Random search or manual construction are often used to obtain a good protograph, but the efficiency is not high enough and many experience and skills are needed. In this paper, a fast searching algorithm is proposed using the convolution neural network to predict the iterative decoding thresholds of protograph LDPC codes effectively. A special input data transformation rule is applied to provide stronger generalization ability. The proposed algorithm converges faster than other algorithms. The iterative decoding threshold of the constructed protograph surpasses greedy algorithm and random search by about 0.53 dB and 0.93 dB respectively under 100 times of density evolution. Simulation results show that quasi-cyclic LDPC (QC-LDPC) codes constructed from the proposed algorithm have competitive performance compared to other papers.

DOI
10.23919/jcc.2023.00.012

Related papers

Quasi-cyclic expansion and encoding algorithms for protograph LDPC codes

Zhongliang Li, Guojiang Xia

Recently, a new class of Low-Density Parity-Check (LDPC) codes constructed from a template was introduced. This kind of codes were called protograph codes. The protograph serves as a blueprint for constructing LDPC codes of arbitrary size whose performance can be predicted by analyzing the protograph. Protograph LDPC codes perform very well and suit for high-speed encoding and decoding. However, there are few researches on expansion and encoding algorithms for them. In this paper, using isomorphism between matrix ring and polynomial ring, we propose efficient quasi-cyclic expansion and encoding algorithms for protograph LDPC codes. Simulation results show that the protograph LDPC codes which were constructed by the algorithm proposed in this paper, outperform the best known unstructured irregular LDPC codes with the same maximum node degrees.

Chinese Journal of Space Science•Jan 1, 2011•0 citations

Decoding Optimization for 5G LDPC Codes by Machine Learning

Xiaoning Wu, Ming Jiang, Chunming Zhao

In this paper, we propose a generalized minimum-sum decoding algorithm using a linear approximation (LAMS) for protograph-based low-density parity-check (PB-LDPC) codes with quasi-cyclic (QC) structures. The linear approximation introduces some factors in each decoding iteration, which linearly adjust the check node updating and channel output. These factors are optimized iteratively using machine learning, where the optimization can be efficiently solved by a small and shallow neural network with training data produced by the LAMS decoder. The neural network is built according to the parity check matrix of a PB-LDPC code with a QC structure which can greatly reduce the size of the neural network. Since, we optimize the factors once per decoding iteration, the optimization is not limited by the number of the iterations. Then, we give the optimized results of the factors in the LAMS decoder and perform decoding simulations for PB-LDPC codes in fifth generation mobile networks (5G). In the simulations, the LAMS algorithm shows noticeable improvement over the normalized and the offset minimum-sum algorithms and even better performance than the belief propagation algorithm in some high signal-to-noise ratio regions.

IEEE Access•Jan 1, 2018•73 citations

Construction of Efficient High-Rate Protograph QC-LDPC Codes by Joint EXIT Chart, PEG, AWD, and QC-NLACE Techniques

Yiqun Chen, Jianrong Bao, Yanhai Shang +2 more

To obtain efficient channel codes with high power efficiency at moderate signal-to-noise ratios (SNRs), an efficient high-rate protograph quasi-cyclic (QC) low-density parity-check (LDPC) codes is optimally constructed. By an optimized protograph template, the code framework is firstly produced by the extensions of the variable nodes. By enlarging the dimension of the sub-matrices related to the protograph framework, the base QC matrix template is generated with required code rate and length by the extrinsic information transfer (EXIT) chart for better decoding threshold. Then, the elements in the base matrix are split with even smaller square sub-matrices of the same row and column weights. In this procedure, a progressive-edge-growth (PEG) algorithm is employed to find the optimized positions of the QC sub-matrices to obtain larger girth for better error floor performance. Moreover, an asymptotic weight distribution (AWD) is employed to keep a low-code-error floor for the code. Also the circulant offsets in all QC sub-matrices are optimally searched by a QC oriented nested loop approximated cycle extrinsic message degree (QC-NLACE) algorithm, which improves the relationship of the unavoidable loops in the code's Tanner graph to cut the error floor. Simulation results show that the codes produced by the proposed method show quite good bit-error-rate (BER) performance. In addition, they exhibit good properties of high spectrum efficiency brought by the high code rate, and the low complexity by the short code length. Moreover, a series of different rate-compatible LDPC codes can be generated from the same protograph framework with some variable node extensions, which significantly eases the code design. Therefore, the proposed code construction can be efficiently applied in the optimal construction of high-rate and short-length rate-compatible QC-LDPC codes with a high data rate and rational complexity, which makes the codes extremely suited for use in new-generation power-constrained wireless communications.

Entropy•May 28, 2026•0 citations

A Novel Construction Method of QC-LDPC Based on BIBD and Protograph

Sheng Huang, Rui Zhang, Jia Xueting +2 more

A novel construction method of Quasi-Cyclic Low-Density Parity-Check (QC-LDPC) code is proposed in this paper, which is based on protograph and Balanced Block Design (BIBD) in combinational mathematics.The method is to fill the base matrix of protograph with the base set elements of BIBD in accordance with certain mathematical rules.And the base matrix of protograph proposed in the paper has special double diagonal structure, which overcomes the low weight code words in general structure and achieves rapid encoding at the same time.The QC-LDPC code in this paper possesses lower encoding complexity and less memory occupation; therefore it is easy for hardware implementation.In addition, it effectively avoids girth 4. Simulation results show that when the Bit Error Rate (BER) is 10 -7 , QC-LDPC codes based on Protograph and BIBD (PBIBD-LDPC) proposed in this paper has 0.5dB Net Coding Gain (NCG) compared with the protograph QC-LDPC codes that based on Vander monde matrix and PEG algorithm structure, and has 0.15dB NCG compared with the excellent code QC-LDPC that based on the lifting structure.

International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT)•Jan 1, 2017•0 citations

Optimized Construction of Protograph G-LDPC Codes by Modified EXIT Chart and MACE for New-Generation Wireless Communications

Jianrong Bao, Bin Jiang, Chao Liu

In this paper, a new systematic construction of optimized protograph generalized low-density parity-check codes with good decoding threshold and low error floor is proposed. First, a typical code graph is generated by combining an accumulate-repeat-accumulate seed protograph with a Tanner graph extension of a simple linear block node. Subsequently, it is analyzed and optimized theoretically, especially with the puncture mechanism, by a modified extrinsic information transfer chart and an asymptotic weight distribution. The generated graph is then extended to a base matrix by a copy-and-permute procedure, accompanied with the matrix split, which is optimized by a progressive edge growth for good randomness and girth property. Finally, the proposed code matrix is created by replacing “1”in the above base matrix with square circulant sub-matrices, the offsets of which are searched by a quasi-cyclic (QC)-oriented modified approximate cycle extrinsic message degree algorithm to improve the cycle relationship, especially for the compound cycles. Simulation results show that the codes exhibit excellent performance in both error floor and waterfall region on an additive white Gaussian noise channel. Moreover, they are also characterized by faster encoding due to the QC structure as well as lower decoding complexity and less latency, which make them a natural fit for new-generation power constrained wireless communications.

IEEE Access•Jan 1, 2018•4 citations

Protograph-Based LDPC Codes with Local Irregularity

Vincent Wüst, Erdem Eray Cil, Laurent Schmalen

Forward error correcting (FEC) codes are used in many communication standards with a wide range of requirements. FEC codes should work close to capacity, achieve low error floors, and have low decoding complexity. In this paper, we propose a novel category of low-density parity-check (LDPC) codes, based on protograph codes with local irregularity. This new code family generalizes conventional protograph-based LDPC codes and is capable of reducing the iterative decoding threshold of the conventional counterpart. We introduce an adapted version of the protograph extrinsic information transfer (PEXIT) algorithm to estimate decoding thresholds on the binaryinput additive white Gaussian noise channel, perform optimizations on the local irregularity, and simulate the performance of some constructed codes.

IEEE International Symposium on Information Theory (ISIT)•Jun 22, 2025•0 citations
This paper presents an intelligent protograph construction algorithm. Protograph LDPC codes have shown excellent error correction performance and play an important role in wireless communications. Random search or manual construction are often used to obtain a good protograph, but the efficiency is not high enough and many experience and skills are needed. In this paper, a fast searching algorithm is proposed using the convolution neural network to predict the iterative decoding thresholds of protograph LDPC codes effectively. A special input data transformation rule is applied to provide stronger generalization ability. The proposed algorithm converges faster than other algorithms. The iterative decoding threshold of the constructed protograph surpasses greedy algorithm and random search by about 0.53 dB and 0.93 dB respectively under 100 times of density evolution. Simulation results show that quasi-cyclic LDPC (QC-LDPC) codes constructed from the proposed algorithm have competitive performance compared to other papers.
Recently, a new class of Low-Density Parity-Check (LDPC) codes constructed from a template was introduced. This kind of codes were called protograph codes. The protograph serves as a blueprint for constructing LDPC codes of arbitrary size whose performance can be predicted by analyzing the protograph. Protograph LDPC codes perform very well and suit for high-speed encoding and decoding. However, there are few researches on expansion and encoding algorithms for them. In this paper, using isomorphism between matrix ring and polynomial ring, we propose efficient quasi-cyclic expansion and encoding algorithms for protograph LDPC codes. Simulation results show that the protograph LDPC codes which were constructed by the algorithm proposed in this paper, outperform the best known unstructured irregular LDPC codes with the same maximum node degrees.
In this paper, we propose a generalized minimum-sum decoding algorithm using a linear approximation (LAMS) for protograph-based low-density parity-check (PB-LDPC) codes with quasi-cyclic (QC) structures. The linear approximation introduces some factors in each decoding iteration, which linearly adjust the check node updating and channel output. These factors are optimized iteratively using machine learning, where the optimization can be efficiently solved by a small and shallow neural network with training data produced by the LAMS decoder. The neural network is built according to the parity check matrix of a PB-LDPC code with a QC structure which can greatly reduce the size of the neural network. Since, we optimize the factors once per decoding iteration, the optimization is not limited by the number of the iterations. Then, we give the optimized results of the factors in the LAMS decoder and perform decoding simulations for PB-LDPC codes in fifth generation mobile networks (5G). In the simulations, the LAMS algorithm shows noticeable improvement over the normalized and the offset minimum-sum algorithms and even better performance than the belief propagation algorithm in some high signal-to-noise ratio regions.
To obtain efficient channel codes with high power efficiency at moderate signal-to-noise ratios (SNRs), an efficient high-rate protograph quasi-cyclic (QC) low-density parity-check (LDPC) codes is optimally constructed. By an optimized protograph template, the code framework is firstly produced by the extensions of the variable nodes. By enlarging the dimension of the sub-matrices related to the protograph framework, the base QC matrix template is generated with required code rate and length by the extrinsic information transfer (EXIT) chart for better decoding threshold. Then, the elements in the base matrix are split with even smaller square sub-matrices of the same row and column weights. In this procedure, a progressive-edge-growth (PEG) algorithm is employed to find the optimized positions of the QC sub-matrices to obtain larger girth for better error floor performance. Moreover, an asymptotic weight distribution (AWD) is employed to keep a low-code-error floor for the code. Also the circulant offsets in all QC sub-matrices are optimally searched by a QC oriented nested loop approximated cycle extrinsic message degree (QC-NLACE) algorithm, which improves the relationship of the unavoidable loops in the code's Tanner graph to cut the error floor. Simulation results show that the codes produced by the proposed method show quite good bit-error-rate (BER) performance. In addition, they exhibit good properties of high spectrum efficiency brought by the high code rate, and the low complexity by the short code length. Moreover, a series of different rate-compatible LDPC codes can be generated from the same protograph framework with some variable node extensions, which significantly eases the code design. Therefore, the proposed code construction can be efficiently applied in the optimal construction of high-rate and short-length rate-compatible QC-LDPC codes with a high data rate and rational complexity, which makes the codes extremely suited for use in new-generation power-constrained wireless communications.
A novel construction method of Quasi-Cyclic Low-Density Parity-Check (QC-LDPC) code is proposed in this paper, which is based on protograph and Balanced Block Design (BIBD) in combinational mathematics.The method is to fill the base matrix of protograph with the base set elements of BIBD in accordance with certain mathematical rules.And the base matrix of protograph proposed in the paper has special double diagonal structure, which overcomes the low weight code words in general structure and achieves rapid encoding at the same time.The QC-LDPC code in this paper possesses lower encoding complexity and less memory occupation; therefore it is easy for hardware implementation.In addition, it effectively avoids girth 4. Simulation results show that when the Bit Error Rate (BER) is 10 -7 , QC-LDPC codes based on Protograph and BIBD (PBIBD-LDPC) proposed in this paper has 0.5dB Net Coding Gain (NCG) compared with the protograph QC-LDPC codes that based on Vander monde matrix and PEG algorithm structure, and has 0.15dB NCG compared with the excellent code QC-LDPC that based on the lifting structure.
In this paper, a new systematic construction of optimized protograph generalized low-density parity-check codes with good decoding threshold and low error floor is proposed. First, a typical code graph is generated by combining an accumulate-repeat-accumulate seed protograph with a Tanner graph extension of a simple linear block node. Subsequently, it is analyzed and optimized theoretically, especially with the puncture mechanism, by a modified extrinsic information transfer chart and an asymptotic weight distribution. The generated graph is then extended to a base matrix by a copy-and-permute procedure, accompanied with the matrix split, which is optimized by a progressive edge growth for good randomness and girth property. Finally, the proposed code matrix is created by replacing “1”in the above base matrix with square circulant sub-matrices, the offsets of which are searched by a quasi-cyclic (QC)-oriented modified approximate cycle extrinsic message degree algorithm to improve the cycle relationship, especially for the compound cycles. Simulation results show that the codes exhibit excellent performance in both error floor and waterfall region on an additive white Gaussian noise channel. Moreover, they are also characterized by faster encoding due to the QC structure as well as lower decoding complexity and less latency, which make them a natural fit for new-generation power constrained wireless communications.
Forward error correcting (FEC) codes are used in many communication standards with a wide range of requirements. FEC codes should work close to capacity, achieve low error floors, and have low decoding complexity. In this paper, we propose a novel category of low-density parity-check (LDPC) codes, based on protograph codes with local irregularity. This new code family generalizes conventional protograph-based LDPC codes and is capable of reducing the iterative decoding threshold of the conventional counterpart. We introduce an adapted version of the protograph extrinsic information transfer (PEXIT) algorithm to estimate decoding thresholds on the binaryinput additive white Gaussian noise channel, perform optimizations on the local irregularity, and simulate the performance of some constructed codes.