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

Journal of Electrical Systems

Neural Network-Based Iterative Process with Soft Decoding Algorithms for Regular and Irregular LDPCC - A Low-Density-Parity-Check Codes Decoder Schema

Harshawardhan Pandharinath Ahire

Published Nov 16, 2024• 0 citations
OpenAlex

Abstract

The development of LoRa networks is employed in various ap- plications with the adoption of simple FEC codes, which include Hamming codes that enable restricted FEC capacity, resulting in unpredictable data transmissions and elevated energy consumption of LoRa nodes. To over- come these gaps, the existing researchers developed LoRa Low-Density Parity-Check(LLDPC), which enables Low-Density Parity-Check coding, especially in LoRa networks. The decoding stage process is to return the original data from the stored or received erroneous encoded data. In the context of classical error correction, LDPC codes were considered one of the significant processes on error-correction code candidates, along with LDPC code-design research, analysis, and iterative decoders for three decades. The current research uses a Neural Network-based iterative process with Soft Decoding Algorithms for Regular and Irregular LDPCC. An LDPC codes decoder Schema has been utilized. Eventually, the neural network training for decoding LDPC codes was considered in the research with the utilized method. The epoch used with the total 209 iterations, time of 00.02, performance procured 0.146, gradient 0.00102, and with the valida- tion checks six has been evaluated.

Related papers

Neural Network-Based Iterative Decoding, Code Design, and Erasure Correction of Low-Density Parity-Check Codes

Xin Wei Xiao

Low-density parity-check (LDPC) codes have been one of the most popular error correction candidates in modern communication and data storage systems for the past three decades due to their capacity-approaching error correction capability under the Belief Propagation (BP) decoding algorithms. In this dissertation, we investigate three topics related to efficient and effective decoding algorithms and the code design of LDPC codes. In the first part of this dissertation, we propose a methodology with the help of artificial intelligence to design Finite Alphabet Iterative Decoders (FAID) for LDPC codes, which are not only of great theoretical but also practical importance. This model-driven neural network (NN) framework unfolds the decoding iterations, introduces quantized neural networks (QNN) to model the FAIDs, and proposes a new cost function, namely, bit error rate (BER), to address the inefficiency in discrete-output channel scenarios. The low precision activations in the QNN and quantization in the cost functions cause a critical issue that their gradients vanish almost everywhere, making it difficult to use classical backward propagation. We design and leverage straight-through estimators as surrogate gradients to tackle this issue and provide a joint training scheme. These QNN-aided FAIDs, are capable of surpassing the floating-point BP algorithms, with much lower complexity and faster convergence. The QNN-aided approach is general, as it can be applied to both continuous and discrete-output channels. In the second part of this dissertation, we propose a new code construction of LDPC codes based on the conventional parity-check matrices of Reed-Solomon (RS) codes. We investigate the girth and cycle structure and introduce an efficient searching algorithm to reduce short cycles in their Tanner graphs and to construct LDPC codes with a girth of at least eight. We use masking to further reduce the number of short cycles and to adjust the column and row weights of the parity-check matrices of the constructed codes for performance improvement. Our designs are systematic and flexible, which balance the requirements of good waterfall performance and low error-floor while maintaining a structure that facilitates implementation. In the third part of this dissertation, we investigate binary quasi-cyclic (QC) LDPC codes and their capability to correct phased bursts of erasures. We prove that the peeling algorithm when applied to such parity-check matrices of column weight two can correct all erasures that can be corrected by a maximum likelihood (ML) decoder. We show that by modifying the parity-check matrices of column weight two and globally coupling them, the erasure correcting capability can be further enhanced. For the Additive White Gaussian Noise (AWGN) channel, we design QC LDPC codes with parity-check matrices of column weight three or more that can correct phased bursts of erasures and perform well over the AWGN channel. Our analysis of QC-LDPC codes with parity-check matrices of column weight two is rather comprehensive as we determine, for all such codes, their dimensions, minimum Hamming distances, and their capabilities to correct phased bursts.

•Jan 1, 2021•0 citations

A multistage scheduled decoder for short block length low-density parity-check codes

Nazanin Elhami-Khorasani

Recent advances in coding theory have uncovered the previously forgotten power of Low-Density Parity-Check (LDPC) codes. Their popularity can be related to their relatively simple iterative decoders and their potential to achieve high performance close to shannon limit. These make them an attractive candidate for error correcting application in communication systems. In this thesis, we focus our research on the iterative decoding algorithms for Low-Density Parity-Check codes and present an improved decoding algorithm. First, the graph structure of LDPC codes is studied and a graph-based search algorithm to find the shortest closed walk and shortest cycle for each node of the graph is proposed. Then, the Deterministic schedule is applied on nodes of the graph with the objective of preserving the optimality of the algorithms. Finally, Hybrid Switch-Type technique is applied on the improved algorithms to provide a desirable complexity/performance trade-off. Hybrid Technique and Deterministic schedule are combined for decoding regular and irregular LDPC codes. The performance and complexity of the decoder is studied for Sum-Product and Gallager A algorithms. The result is a flexible decoder for any available LDPC code and any combination of decoding algorithms based on the communication systems need. In this technique, we benefit the high performance of soft-decision algorithms and low complexity of hard-decision algorithms by changing the decoding rule after a few iterations. Hence, a desirable performance can be obtained with less average number of soft iterations. Moreover, all the nodes do not update messages in each iteration. As a result, the total number of computations is reduced considerably

•Jan 1, 2007•0 citations

Non iterative LDPC decoding by syndrome generation using Artificial Neural Network

Dinesh Kumar, Alkesh Agrawal, Gopal Singh Phartiyal

Low density parity-check code (LDPC) is an error correcting code used in noisy communication channel (e.g. AWGN) to reduce the probability of error in information. By using LDPC codes, this probability can be made comparatively small, so that the data transmission rate can be as close to Shannon's limit. The decoding of Low Density Parity Check (LDPC) codes by iterative process of belief propagation gives challenges for designers looking for real time performance in communication systems. This thesis work proposes the use of Artificial Neural Networks (ANN) to replace belief propagation to approach closer to Shannon's limit more closer than other traditional decoding methods. This thesis is intended to design a new methodology to decode LDPC codes in Non-iterative manner with the help of ANN and Look Up Table (LUT). This work is at initial stage and will be extended for better performance.

National Conference on Recent Advances in Electronics & Computer Engineering (RAECE)•Feb 1, 2015•1 citation

Low Complexity Neural Network-Aided NMS LDPC Decoder

Honghao Shi, Mingyang Zhong, Zhiyong Luo +1 more

For recent years, deep learning has been studied and utilized among decoders in wireless and optical communication. For low density parity check (LDPC) codes, most works use neural network (NN) to implement the belief propagation (BP) decoder and unfold its iterations into layers activated by different functions. However, the whole decoder composed by neural network performs lots of non-linear operations, which are time consuming and unfriendly to hardware implementation. In this work, a neural network-aided normalized min-sum (NN-aided NMS) decoder for LDPC code is proposed, in which the normalization factors are inferred from input log likelihood ratio (LLR) by apre-trained NN, while maintaining check and variable nodes processing the same as in min-sum (MS) decoder. In order to test the proposed decoder with irregular LDPC code, a rate-7/8 one was constructed using progressive edge growth (PEG) algorithm, showing better error correction capability than the standard of consultative committee for space data systems (CCSDS) LDPC (8176,7154) code by 0.08 dB with the same rate. Simulation results show that, NN-aided NMS decoder outperforms MS decoder by 0.3 dB, and its performance approaches BP decoder with a gap of 0.02 dB, which is 50% closer than the best NMS decoder using 0.7 as the normalization factor. The proposed decoder has good performance for both regular and irregular LDPC codes, and needs much less computation complexity than BP decoder. It introduces more linear computation than NMS decoder but achieves better bit error rate (BER) performance, thus becoming a good complement between BP and NMS decoder when trading off among complexity, error correction performance and hardware implementation for wireless and satellite communication.

Computing, Communications and IoT Applications (ComComAp)•Nov 26, 2021•8 citations

Compound codes based on irregular graphs and their iterative decoding.

Telex Magloire Ngatched. Nkouatchah

Low-density parity-check (LDPC) codes form a Shannon limit approaching class of linear block codes. With iterative decoding based on their Tanner graphs, they can achieve outstanding performance. Since their rediscovery in late 1990's, the design, construction, and decoding of LDPC codes as well as their generalization have become one of the focal research points. This thesis takes a few more steps in these directions. The first significant contribution of this thesis is the introduction of a new class of codes called Generalized Irregular Low-Density (GILD) parity-check codes, which are adapted from the previously known class of Generalized Low-Density (GLD) codes. GILD codes are generalization of irregular LDPC codes, and are shown to outperform GLD codes. In addition, GILD codes have a significant advantage over GLD codes in terms of encoding and decoding complexity. They are also able to match and even beat LDPC codes for small block lengths. The second significant contribution of this thesis is the proposition of several decoding algorithms. Two new decoding algolithms for LDPC codes are introduced. In principle and complexity these algorithms can be grouped with bit flipping algorithms. Two soft-input soft-output (SISO) decoding algorithms for linear block codes are also proposed. The first algorithm is based on Maximum a Posteriori Probability (MAP) decoding of low-weight subtrellis centered around a generated candidate codeword. The second algorithm modifies and utilizes the improved Kaneko's decoding algorithm for soft-input hard-output decoding. These hard outputs are converted to soft-decisions using reliability calculations. Simulation results indicate that the proposed algorithms provide a significant improvement in error performance over Chase-based algorithm and achieve practically optimal performance with a significant reduction in decoding complexity. An analytical expression for the union bound on the bit error probability of linear codes on the Gilbert-Elliott (GE) channel model is also derived. This analytical result is shown to be accurate in establishing the decoder performance in the range where obtaining sufficient data from simulation is impractical.

•Jan 1, 2004•0 citations

Correcting capabilities of binary irregular LDPC code under low-complexity iterative decoding algorithm

Pavel S. Rybin

This paper deals with the irregular binary low-density parity-check (LDPC) codes and two iterative low-complexity decoding algorithms. The first one is the majority error-correcting decoding algorithm, and the second one is iterative erasure-correcting decoding algorithm. The lower bounds on correcting capabilities (the guaranteed corrected error and erasure fraction respectively) of irregular LDPC code under decoding (error and erasure correcting respectively) algorithms with low-complexity were represented. These lower bounds were obtained as a result of analysis of Tanner graph representation of irregular LDPC code. The numerical results, obtained at the end of the paper for proposed lower-bounds achieved similar results for the previously known best lower-bounds for regular LDPC codes and were represented for the first time for the irregular LDPC codes.

Journal of Communications Technology and Electronics•Dec 1, 2016•2 citations
The development of LoRa networks is employed in various ap- plications with the adoption of simple FEC codes, which include Hamming codes that enable restricted FEC capacity, resulting in unpredictable data transmissions and elevated energy consumption of LoRa nodes. To over- come these gaps, the existing researchers developed LoRa Low-Density Parity-Check(LLDPC), which enables Low-Density Parity-Check coding, especially in LoRa networks. The decoding stage process is to return the original data from the stored or received erroneous encoded data. In the context of classical error correction, LDPC codes were considered one of the significant processes on error-correction code candidates, along with LDPC code-design research, analysis, and iterative decoders for three decades. The current research uses a Neural Network-based iterative process with Soft Decoding Algorithms for Regular and Irregular LDPCC. An LDPC codes decoder Schema has been utilized. Eventually, the neural network training for decoding LDPC codes was considered in the research with the utilized method. The epoch used with the total 209 iterations, time of 00.02, performance procured 0.146, gradient 0.00102, and with the valida- tion checks six has been evaluated.
Low-density parity-check (LDPC) codes have been one of the most popular error correction candidates in modern communication and data storage systems for the past three decades due to their capacity-approaching error correction capability under the Belief Propagation (BP) decoding algorithms. In this dissertation, we investigate three topics related to efficient and effective decoding algorithms and the code design of LDPC codes. In the first part of this dissertation, we propose a methodology with the help of artificial intelligence to design Finite Alphabet Iterative Decoders (FAID) for LDPC codes, which are not only of great theoretical but also practical importance. This model-driven neural network (NN) framework unfolds the decoding iterations, introduces quantized neural networks (QNN) to model the FAIDs, and proposes a new cost function, namely, bit error rate (BER), to address the inefficiency in discrete-output channel scenarios. The low precision activations in the QNN and quantization in the cost functions cause a critical issue that their gradients vanish almost everywhere, making it difficult to use classical backward propagation. We design and leverage straight-through estimators as surrogate gradients to tackle this issue and provide a joint training scheme. These QNN-aided FAIDs, are capable of surpassing the floating-point BP algorithms, with much lower complexity and faster convergence. The QNN-aided approach is general, as it can be applied to both continuous and discrete-output channels. In the second part of this dissertation, we propose a new code construction of LDPC codes based on the conventional parity-check matrices of Reed-Solomon (RS) codes. We investigate the girth and cycle structure and introduce an efficient searching algorithm to reduce short cycles in their Tanner graphs and to construct LDPC codes with a girth of at least eight. We use masking to further reduce the number of short cycles and to adjust the column and row weights of the parity-check matrices of the constructed codes for performance improvement. Our designs are systematic and flexible, which balance the requirements of good waterfall performance and low error-floor while maintaining a structure that facilitates implementation. In the third part of this dissertation, we investigate binary quasi-cyclic (QC) LDPC codes and their capability to correct phased bursts of erasures. We prove that the peeling algorithm when applied to such parity-check matrices of column weight two can correct all erasures that can be corrected by a maximum likelihood (ML) decoder. We show that by modifying the parity-check matrices of column weight two and globally coupling them, the erasure correcting capability can be further enhanced. For the Additive White Gaussian Noise (AWGN) channel, we design QC LDPC codes with parity-check matrices of column weight three or more that can correct phased bursts of erasures and perform well over the AWGN channel. Our analysis of QC-LDPC codes with parity-check matrices of column weight two is rather comprehensive as we determine, for all such codes, their dimensions, minimum Hamming distances, and their capabilities to correct phased bursts.
Recent advances in coding theory have uncovered the previously forgotten power of Low-Density Parity-Check (LDPC) codes. Their popularity can be related to their relatively simple iterative decoders and their potential to achieve high performance close to shannon limit. These make them an attractive candidate for error correcting application in communication systems. In this thesis, we focus our research on the iterative decoding algorithms for Low-Density Parity-Check codes and present an improved decoding algorithm. First, the graph structure of LDPC codes is studied and a graph-based search algorithm to find the shortest closed walk and shortest cycle for each node of the graph is proposed. Then, the Deterministic schedule is applied on nodes of the graph with the objective of preserving the optimality of the algorithms. Finally, Hybrid Switch-Type technique is applied on the improved algorithms to provide a desirable complexity/performance trade-off. Hybrid Technique and Deterministic schedule are combined for decoding regular and irregular LDPC codes. The performance and complexity of the decoder is studied for Sum-Product and Gallager A algorithms. The result is a flexible decoder for any available LDPC code and any combination of decoding algorithms based on the communication systems need. In this technique, we benefit the high performance of soft-decision algorithms and low complexity of hard-decision algorithms by changing the decoding rule after a few iterations. Hence, a desirable performance can be obtained with less average number of soft iterations. Moreover, all the nodes do not update messages in each iteration. As a result, the total number of computations is reduced considerably
Low density parity-check code (LDPC) is an error correcting code used in noisy communication channel (e.g. AWGN) to reduce the probability of error in information. By using LDPC codes, this probability can be made comparatively small, so that the data transmission rate can be as close to Shannon's limit. The decoding of Low Density Parity Check (LDPC) codes by iterative process of belief propagation gives challenges for designers looking for real time performance in communication systems. This thesis work proposes the use of Artificial Neural Networks (ANN) to replace belief propagation to approach closer to Shannon's limit more closer than other traditional decoding methods. This thesis is intended to design a new methodology to decode LDPC codes in Non-iterative manner with the help of ANN and Look Up Table (LUT). This work is at initial stage and will be extended for better performance.
For recent years, deep learning has been studied and utilized among decoders in wireless and optical communication. For low density parity check (LDPC) codes, most works use neural network (NN) to implement the belief propagation (BP) decoder and unfold its iterations into layers activated by different functions. However, the whole decoder composed by neural network performs lots of non-linear operations, which are time consuming and unfriendly to hardware implementation. In this work, a neural network-aided normalized min-sum (NN-aided NMS) decoder for LDPC code is proposed, in which the normalization factors are inferred from input log likelihood ratio (LLR) by apre-trained NN, while maintaining check and variable nodes processing the same as in min-sum (MS) decoder. In order to test the proposed decoder with irregular LDPC code, a rate-7/8 one was constructed using progressive edge growth (PEG) algorithm, showing better error correction capability than the standard of consultative committee for space data systems (CCSDS) LDPC (8176,7154) code by 0.08 dB with the same rate. Simulation results show that, NN-aided NMS decoder outperforms MS decoder by 0.3 dB, and its performance approaches BP decoder with a gap of 0.02 dB, which is 50% closer than the best NMS decoder using 0.7 as the normalization factor. The proposed decoder has good performance for both regular and irregular LDPC codes, and needs much less computation complexity than BP decoder. It introduces more linear computation than NMS decoder but achieves better bit error rate (BER) performance, thus becoming a good complement between BP and NMS decoder when trading off among complexity, error correction performance and hardware implementation for wireless and satellite communication.
Low-density parity-check (LDPC) codes form a Shannon limit approaching class of linear block codes. With iterative decoding based on their Tanner graphs, they can achieve outstanding performance. Since their rediscovery in late 1990's, the design, construction, and decoding of LDPC codes as well as their generalization have become one of the focal research points. This thesis takes a few more steps in these directions. The first significant contribution of this thesis is the introduction of a new class of codes called Generalized Irregular Low-Density (GILD) parity-check codes, which are adapted from the previously known class of Generalized Low-Density (GLD) codes. GILD codes are generalization of irregular LDPC codes, and are shown to outperform GLD codes. In addition, GILD codes have a significant advantage over GLD codes in terms of encoding and decoding complexity. They are also able to match and even beat LDPC codes for small block lengths. The second significant contribution of this thesis is the proposition of several decoding algorithms. Two new decoding algolithms for LDPC codes are introduced. In principle and complexity these algorithms can be grouped with bit flipping algorithms. Two soft-input soft-output (SISO) decoding algorithms for linear block codes are also proposed. The first algorithm is based on Maximum a Posteriori Probability (MAP) decoding of low-weight subtrellis centered around a generated candidate codeword. The second algorithm modifies and utilizes the improved Kaneko's decoding algorithm for soft-input hard-output decoding. These hard outputs are converted to soft-decisions using reliability calculations. Simulation results indicate that the proposed algorithms provide a significant improvement in error performance over Chase-based algorithm and achieve practically optimal performance with a significant reduction in decoding complexity. An analytical expression for the union bound on the bit error probability of linear codes on the Gilbert-Elliott (GE) channel model is also derived. This analytical result is shown to be accurate in establishing the decoder performance in the range where obtaining sufficient data from simulation is impractical.
This paper deals with the irregular binary low-density parity-check (LDPC) codes and two iterative low-complexity decoding algorithms. The first one is the majority error-correcting decoding algorithm, and the second one is iterative erasure-correcting decoding algorithm. The lower bounds on correcting capabilities (the guaranteed corrected error and erasure fraction respectively) of irregular LDPC code under decoding (error and erasure correcting respectively) algorithms with low-complexity were represented. These lower bounds were obtained as a result of analysis of Tanner graph representation of irregular LDPC code. The numerical results, obtained at the end of the paper for proposed lower-bounds achieved similar results for the previously known best lower-bounds for regular LDPC codes and were represented for the first time for the irregular LDPC codes.