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 Conference on Electronic Information and Communication Technology (ICEICT)

CNN-SC Decoder for Polar Codes under Correlated Noise Channels

Wenyuan Rao, Zhibin Liu, Li Huang, Jiancheng Sun, Liyun Dai

Published Nov 13, 2020• 6 citations
Publisher

Abstract

In 5G mobile communication standard, polar codes have been used as coding on control channels. Although the polar code has good performance, the performance of its short code is still facing huge challenges. Moreover, the size limitation of using the deep learning model as the decoder of the polar code has always been the focus of researchers seeking a breakthrough. In this paper, the convolutional neural network (CNN) model in deep learning is cascaded with a successive cancellation (SC) decoder to achieve the decoding of polar codes under additive correlated Gaussian noise (ACGN) channels, thereby improving the decoding performance of short polar codes under ACGN and alleviating the code length limitation of a single deep learning model as a decoder. The cascaded decoding structure is represented as a CNN-SC decoder, which can effectively estimate colored noise. The simulation shows that the CNN-SC decoder improves the performance of polar codes under ACGN channels significantly.

DOI
10.1109/iceict51264.2020.9334237

Related papers

A Novel Decoding Scheme for Polar Code Using Convolutional Neural Network

Chen Wen, Jian Xiong, Lin Gui +2 more

Polar code is the first capacity-achieving channel coding scheme which has been selected for the next generation of wireless communication standard(5G). However, the traditional decoding schemes such as CA-SCL and BP algorithms cannot take into account both BER and latency performance. Inspired by the deep learning technology, we propose a scheme that combine convolutional neural network (CNN) with traditional Belief Propagation (BP) decoding. By exploiting noise correlation for channel decoding under colored noise environment, the proposed scheme can obtain a more accurate estimation of channel noise. We simulate the performance of the proposed scheme under BPSK and 4QAM modulation. For QAM modulation, a scheme that extend the conventional real-valued CNN technique to the complex-valued one is given. The results demonstrate that bit error rates (BER) performance can be improved after removing the estimated noise. Compare to the traditional Polar decoding schemes, the proposed scheme has better trade-off between BER and latency performance under colored noise environment.

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)•Jun 1, 2019•7 citations

A RNN Based Decoder for Polar Codes

Yuan Chai, Zuting Chen, Shuai Han +1 more

Polar code is the first type of constructive coding with achievable capacity, which has become the encoding scheme for 5G mobile communication systems and is a cutting-edge direction in channel coding research. However, traditional decoding algorithms for Polar codes still need to be improved in terms of errorcorrection performance and decoding delay. For Polar code short codes, due to the phenomenon of incomplete Polar, the traditional SC decoding algorithm has a problem of poor decoding performance. Algorithms that utilize deep learning for direct or auxiliary operations often yield more accurate computational results with lower computational complexity. Therefore, considering that applying deep learning to the communication field is a mainstream trend in the 6G era, a (16,8) short Polar code decoder based on recurrent neural network (RNN) is proposed. At the same time, a suitable dataset construction method was proposed, which achieved better performance than SC decoding algorithm under low signal-to-noise ratio by adjusting network parameters and training under the appropriate dataset.

International Conference on Information Processing and Network Provisioning (ICIPNP)•Oct 26, 2023•2 citations

Deep-learning-aided fast successive cancellation decoding of polar codes

Haogang Feng, H. L. Xiao, Shida Zhong +3 more

With the continuous evolution of 5G communication technology to B5G and the next generation of communication technology, Deep Learning technology will also lead the automation and intelligent transformation of communication systems. Existing research has shown that the combination of deep learning and communication technology is expected to break some performance bottlenecks of traditional communication algorithms and solutions. This paper explores the application of deep learning (DL) in polar decoding algorithms, proposing a DL-aided-FSC (DL-FSC) polar code decoder algorithm. For the DL-FSC decoding algorithm, the conventional successive cancellation (SC) decoder is partitioned into multiple sub-blocks, which are replaced by R0 nodes, R1 nodes and sub-DL decoder. The log-likelihood ratio (LLR) and frozen bit pattern are input to the sub-DL decoder to predict decode codewords under any decoding code rate. Through simulation verification, under the PBCH channel of 5G communication, the DL-FSC decoder achieves similar block error rate (BLER) performance to the SC decoder, even improving by about 1%. In order to verify the performance optimization effect of the proposed algorithm at the hardware level, the DL-FSC deocder circuit design was completed. Through FPGA synthesis, the proposed decoder achieves a throughput of about 4571 Mbps, which is 1.71× improvement in decoding throughput at the expense of increased logic resources.

Journal of Communications and Networks•Dec 1, 2024•2 citations

Error Correction Enhancement in SCL Decoding of Polar Codes Using LSTM Network

Fatemeh Alia, Bahareh Akhbari, Mahmoud Ahmadian‐Attari

Polar codes have been selected as the channel coding scheme for the Enhanced Mobile Broadband (eMBB) control channel in 5G, which requires short length codes. One of the main challenges in utilizing polar codes is the design of low-complexity decoders with adequate error-correcting performance. The Successive Cancellation (SC) decoder was introduced as the first algorithm enabling polar codes to achieve the channel capacity for long codelengths. However, for shorter codelengths, this decoder does not provide satisfactory error-correction performance. To address this limitation, the Successive Cancellation List (SCL) decoder has been proposed, which performs decoding by maintaining a list of candidate paths and selecting the best one based on a path metric. In this paper, we propose improving the error-correction performance of the SCL decoder using concatenated Cyclic Redundancy Check (CRC) codes and Long Short-Term Memory (LSTM) network. Simulation results demonstrate that the proposed method outperforms the Belief Propagation (BP) decoder in terms of Bit Error Rate (BER) curves. Furthermore, the accuracy of the LSTM model in this study improves from 73 percent in previous research to 93.77 percent.

•May 13, 2025•0 citations

DLSTM-Based Successive Cancellation Flipping Decoder for Short Polar Codes

Jianming Cui, Wenxiu Kong, Xiaojun Zhang +2 more

Polar code has been adopted as the control channel coding scheme for the fifth generation (5G), and the performance of short polar codes is receiving intensive attention. The successive cancellation flipping (SC flipping) algorithm suffers a significant performance loss in short block lengths. To address this issue, we propose a double long short-term memory (DLSTM) neural network to locate the first error bit. To enhance the prediction accuracy of the DLSTM network, all frozen bits are clipped in the output layer. Then, Gaussian approximation is applied to measure the channel reliability and rank the flipping set to choose the least reliable position for multi-bit flipping. To be robust under different codewords, padding and masking strategies aid the network architecture to be compatible with multiple block lengths. Numerical results indicate that the error-correction performance of the proposed algorithm is competitive with that of the CA-SCL algorithm. It has better performance than the machine learning-based multi-bit flipping SC (ML-MSCF) decoder and the dynamic SC flipping (DSCF) decoder for short polar codes.

Entropy•Jul 6, 2021•3 citations

Deep-Learning-Aided Successive-Cancellation Decoding of Polar Codes

Seyyed Ali Hashemi, Nghia Doan, Thibaud Tonnellier +1 more

A deep-learning-aided successive-cancellation list (DL-SCL) decoding algorithm for polar codes is introduced with deep-learning-aided successive-cancellation (DL-SC) decoding being a specific case of it. The DL-SCL decoder works by allowing additional rounds of SCL decoding when the first SCL decoding attempt fails, using a novel bit-flipping metric. The proposed bit-flipping metric exploits the inherent relations between the information bits in polar codes that are represented by a correlation matrix. The correlation matrix is then optimized using emerging deep-learning techniques. Performance results on a polar code of length 128 with 64 information bits concatenated with a 24-bit cyclic redundancy check show that the proposed bit-flipping metric in the proposed DL-SCL decoder requires up to 66% fewer multiplications and up to 36% fewer additions, without any need to perform transcendental functions, and by providing almost the same error-correction performance in comparison with the state of the art.

arXiv:1912.01086•Asilomar Conference on Signals, Systems and Computers (ACSSC)•Nov 1, 2019•10 citations
In 5G mobile communication standard, polar codes have been used as coding on control channels. Although the polar code has good performance, the performance of its short code is still facing huge challenges. Moreover, the size limitation of using the deep learning model as the decoder of the polar code has always been the focus of researchers seeking a breakthrough. In this paper, the convolutional neural network (CNN) model in deep learning is cascaded with a successive cancellation (SC) decoder to achieve the decoding of polar codes under additive correlated Gaussian noise (ACGN) channels, thereby improving the decoding performance of short polar codes under ACGN and alleviating the code length limitation of a single deep learning model as a decoder. The cascaded decoding structure is represented as a CNN-SC decoder, which can effectively estimate colored noise. The simulation shows that the CNN-SC decoder improves the performance of polar codes under ACGN channels significantly.
Polar code is the first capacity-achieving channel coding scheme which has been selected for the next generation of wireless communication standard(5G). However, the traditional decoding schemes such as CA-SCL and BP algorithms cannot take into account both BER and latency performance. Inspired by the deep learning technology, we propose a scheme that combine convolutional neural network (CNN) with traditional Belief Propagation (BP) decoding. By exploiting noise correlation for channel decoding under colored noise environment, the proposed scheme can obtain a more accurate estimation of channel noise. We simulate the performance of the proposed scheme under BPSK and 4QAM modulation. For QAM modulation, a scheme that extend the conventional real-valued CNN technique to the complex-valued one is given. The results demonstrate that bit error rates (BER) performance can be improved after removing the estimated noise. Compare to the traditional Polar decoding schemes, the proposed scheme has better trade-off between BER and latency performance under colored noise environment.
Polar code is the first type of constructive coding with achievable capacity, which has become the encoding scheme for 5G mobile communication systems and is a cutting-edge direction in channel coding research. However, traditional decoding algorithms for Polar codes still need to be improved in terms of errorcorrection performance and decoding delay. For Polar code short codes, due to the phenomenon of incomplete Polar, the traditional SC decoding algorithm has a problem of poor decoding performance. Algorithms that utilize deep learning for direct or auxiliary operations often yield more accurate computational results with lower computational complexity. Therefore, considering that applying deep learning to the communication field is a mainstream trend in the 6G era, a (16,8) short Polar code decoder based on recurrent neural network (RNN) is proposed. At the same time, a suitable dataset construction method was proposed, which achieved better performance than SC decoding algorithm under low signal-to-noise ratio by adjusting network parameters and training under the appropriate dataset.
With the continuous evolution of 5G communication technology to B5G and the next generation of communication technology, Deep Learning technology will also lead the automation and intelligent transformation of communication systems. Existing research has shown that the combination of deep learning and communication technology is expected to break some performance bottlenecks of traditional communication algorithms and solutions. This paper explores the application of deep learning (DL) in polar decoding algorithms, proposing a DL-aided-FSC (DL-FSC) polar code decoder algorithm. For the DL-FSC decoding algorithm, the conventional successive cancellation (SC) decoder is partitioned into multiple sub-blocks, which are replaced by R0 nodes, R1 nodes and sub-DL decoder. The log-likelihood ratio (LLR) and frozen bit pattern are input to the sub-DL decoder to predict decode codewords under any decoding code rate. Through simulation verification, under the PBCH channel of 5G communication, the DL-FSC decoder achieves similar block error rate (BLER) performance to the SC decoder, even improving by about 1%. In order to verify the performance optimization effect of the proposed algorithm at the hardware level, the DL-FSC deocder circuit design was completed. Through FPGA synthesis, the proposed decoder achieves a throughput of about 4571 Mbps, which is 1.71× improvement in decoding throughput at the expense of increased logic resources.
Polar codes have been selected as the channel coding scheme for the Enhanced Mobile Broadband (eMBB) control channel in 5G, which requires short length codes. One of the main challenges in utilizing polar codes is the design of low-complexity decoders with adequate error-correcting performance. The Successive Cancellation (SC) decoder was introduced as the first algorithm enabling polar codes to achieve the channel capacity for long codelengths. However, for shorter codelengths, this decoder does not provide satisfactory error-correction performance. To address this limitation, the Successive Cancellation List (SCL) decoder has been proposed, which performs decoding by maintaining a list of candidate paths and selecting the best one based on a path metric. In this paper, we propose improving the error-correction performance of the SCL decoder using concatenated Cyclic Redundancy Check (CRC) codes and Long Short-Term Memory (LSTM) network. Simulation results demonstrate that the proposed method outperforms the Belief Propagation (BP) decoder in terms of Bit Error Rate (BER) curves. Furthermore, the accuracy of the LSTM model in this study improves from 73 percent in previous research to 93.77 percent.
Polar code has been adopted as the control channel coding scheme for the fifth generation (5G), and the performance of short polar codes is receiving intensive attention. The successive cancellation flipping (SC flipping) algorithm suffers a significant performance loss in short block lengths. To address this issue, we propose a double long short-term memory (DLSTM) neural network to locate the first error bit. To enhance the prediction accuracy of the DLSTM network, all frozen bits are clipped in the output layer. Then, Gaussian approximation is applied to measure the channel reliability and rank the flipping set to choose the least reliable position for multi-bit flipping. To be robust under different codewords, padding and masking strategies aid the network architecture to be compatible with multiple block lengths. Numerical results indicate that the error-correction performance of the proposed algorithm is competitive with that of the CA-SCL algorithm. It has better performance than the machine learning-based multi-bit flipping SC (ML-MSCF) decoder and the dynamic SC flipping (DSCF) decoder for short polar codes.
A deep-learning-aided successive-cancellation list (DL-SCL) decoding algorithm for polar codes is introduced with deep-learning-aided successive-cancellation (DL-SC) decoding being a specific case of it. The DL-SCL decoder works by allowing additional rounds of SCL decoding when the first SCL decoding attempt fails, using a novel bit-flipping metric. The proposed bit-flipping metric exploits the inherent relations between the information bits in polar codes that are represented by a correlation matrix. The correlation matrix is then optimized using emerging deep-learning techniques. Performance results on a polar code of length 128 with 64 information bits concatenated with a 24-bit cyclic redundancy check show that the proposed bit-flipping metric in the proposed DL-SCL decoder requires up to 66% fewer multiplications and up to 36% fewer additions, without any need to perform transcendental functions, and by providing almost the same error-correction performance in comparison with the state of the art.