基于集成学习的极化码BP译码算法
BP Decoding Algorithm Based on Ensemble Learning
DOI: 10.12677/SEA.2023.122036, PDF,   
作者: 徐 坤：上海理工大学光电信息与计算机工程学院，上海
关键词: 极化码；BP译码；加权BP译码；集成学习；弱学习器；Polar Code； BP Decoding； Weighted BP Decoding； Integrated Learning； Individual Learner
摘要: 集成学习被广泛用于解决复杂任务，方法是通过学习得到不同的弱学习器，利用其各自的泛化能力，获得强学习器来解决问题。BPL译码算法和WBP译码算法是BP译码算法的两种主要优化算法，两种优化算法均具有不同的优势。基于此，提出了一种基于集成学习的BP译码算法，该算法借助集成学习的优势，来获取更优异的译码性能。通过训练多组具有不同的权重参数的WBP译码器，并将其组合成类似BPL译码算法的一种新的译码器，该译码器的权重参数由离线训练得来。仿真结果表明，该译码算法可以达到与BPL译码算法相近的译码性能，同时具有更低的计算复杂度及更少的迭代次数。
Abstract: Ensemble learning is widely used to solve complex tasks by learning different individual learners, using their respective generalization capabilities to obtain strong learners to solve problems. BPL decoding algorithm and WBP decoding algorithm are the two main optimization algorithms of BP decoding algorithm, and both optimization algorithms have different advantages. Based on this, a BP decoding algorithm based on ensemble learning is proposed, which obtains better decoding performance by virtue of the advantages of ensemble learning. By training multiple sets of WBP decoders with different weight parameters, and combining them into a new decoder similar to the BPL decoding algorithm, the weight parameters of the decoder are obtained from offline training. Simulation results show that the decoding algorithm can achieve similar decoding performance as the BPL decoding algorithm, and has lower computational complexity and fewer iterations.
文章引用：徐坤. 基于集成学习的极化码BP译码算法[J]. 软件工程与应用, 2023, 12(2): 354-365. https://doi.org/10.12677/SEA.2023.122036

参考文献

[1] 崔晨. 不等差错保护极化码编码方法研究[D]: [博士学位论文]. 哈尔滨: 哈尔滨工业大学, 2022.
[2] 张川, 申怡飞, 周文岳, 季厚任. 5G信道编译码: 算法与实现[M]. 北京: 科学出版社, 2021.
[3] Simsek, C. and Turk, K. (2016) Simplified Early Stopping Criterion for Belief-Propagation Polar Code Decoders. IEEE Communications Letters, 20, 1515-1518. [Google Scholar] [CrossRef] 
[4] Elkelesh, A., Ebada, M., Cammerer, S., et al. (2018) Belief Propagation List Decoding of Polar Codes. IEEE Communications Letters, 22, 1536-1539. [Google Scholar] [CrossRef] 
[5] Doan, N., Hashemi, S.A., Mondelli, M., et al. (2018) On the Decoding of Polar Codes on Permuted Factor Graphs. 2018 IEEE Global Communications Conference (GLOBECOM), Abu Dhabi, 9-13 December 2018, 1-6. [Google Scholar] [CrossRef] 
[6] Elkelesh, A., Ebada, M., Cammerer, S., et al. (2018) Belief Propagation Decoding of Polar Codes on Permuted Factor Graphs. 2018 IEEE Wireless Communications and Networking Conference (WCNC), Barcelona, 15-18 April 2018, 1-6. [Google Scholar] [CrossRef] 
[7] Arlı, A.Ç. and Gazi, O. (2019) Noise-Aided Belief Propagation List Decoding of Polar Codes. IEEE Communications Letters, 23, 1285-1288. [Google Scholar] [CrossRef] 
[8] Geiselhart, M., Elkelesh, A., Ebada, M., et al. (2020) CRC-Aided Belief Propagation List Decoding of Polar Codes. 2020 IEEE International Symposium on Information Theory (ISIT), Los Angeles, 21-26 June 2020, 395-400. [Google Scholar] [CrossRef] 
[9] Ren, Y., Shen, Y., Zhang, Z., et al. (2020) Efficient Belief Propagation Polar Decoder with Loop Simplification Based Factor Graphs. IEEE Transactions on Vehicular Technology, 69, 5657-5660. [Google Scholar] [CrossRef] 
[10] Yu, Y., Pan, Z., Liu, N., et al. (2019) Belief Propagation Bit-Flip Decoder for Polar Codes. IEEE Access, 7, 10937- 10946. [Google Scholar] [CrossRef] 
[11] Shen, Y., Song, W., Ren, Y., et al. (2020) Enhanced Belief Propagation Decoder for 5G Polar Codes with Bit-Flipping. IEEE Transactions on Circuits and Systems II: Express Briefs, 67, 901-905. [Google Scholar] [CrossRef] 
[12] Shen, Y., Song, W., Ji, H., et al. (2020) Improved Belief Propagation Polar Decoders with Bit-Flipping Algorithms. IEEE Transactions on Communications, 68, 6699-6713. [Google Scholar] [CrossRef] 
[13] Doan, N., Hashemi, S.A. and Gross, W.J. (2020) Decoding Polar Codes with Reinforcement Learning. GLOBECOM 2020-2020 IEEE Global Communications Conference, Taipei, 7-11 December 2020, 1-6. [Google Scholar] [CrossRef] 
[14] 徐鹏, 孔令军, 赵生妹, 郑宝玉. 基于PD-CNN的Polar码译码算法[J]. 信号处理, 2019, 35(10): 1652-1660.
[15] 何彦琦, 彭大芹, 赵雪志. 一种基于循环神经网络的极化码BP译码算法[J]. 计算机工程, 2022, 48(1): 197-203.
[16] Nachmani, E., Be’ery, Y. and Burshtein, D. (2016) Learning to Decode Linear Codes Using Deep Learning. 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, 27-30 September 2016, 341-346. [Google Scholar] [CrossRef] 
[17] Nachmani, E., Marciano, E., Lugosch, L., et al. (2018) Deep Learning Methods for Improved Decoding of Linear Codes. IEEE Journal of Selected Topics in Signal Processing, 12, 119-131. [Google Scholar] [CrossRef] 
[18] Lugosch, L. and Gross, W.J. (2017) Neural Offset Min-Sum Decoding. 2017 IEEE International Symposium on Information Theory (ISIT), Aachen, 25-30 June 2017, 1361-1365. [Google Scholar] [CrossRef] 
[19] Xu, W., Wu, Z., Ueng, Y.L., et al. (2017) Improved Polar Decoder Based on Deep Learning. 2017 IEEE International Workshop on Signal Processing Systems (SiPS), Lorient, 3-5 October 2017, 1-6. [Google Scholar] [CrossRef] 
[20] Teng, C.F., Wu, C.H.D., Ho, A.K.S., et al. (2019) Low-Complexity Recurrent Neural Network-Based Polar Decoder with Weight Quantization Mechanism. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, 12-17 May 2019, 1413-1417. [Google Scholar] [CrossRef] 
[21] Huang, Y., Zhang, M. and Dou, Y. (2020) A Low-Complexity Residual Neural Network Based BP Decoder for Polar Codes. 2020 International Conference on Wireless Communications and Signal Processing (WCSP), Nanjing, 21-23 October 2020, 889-893. [Google Scholar] [CrossRef] 
[22] Oliveira, L.M., Oliveira, R.M. and de Lamare, R.C. (2021) Decoding of Polar Codes Based on Q-Learning-Driven Belief Propagation.
https://arxiv.org/abs/2111.00673
[23] Raviv, T., Raviv, N. and Be’ery, Y. (2020) Data-Driven Ensembles for Deep and Hard-Decision Hybrid Decoding. 2020 IEEE International Symposium on Information Theory (ISIT), Los Angeles, 21-26 June 2020, 321-326. [Google Scholar] [CrossRef] 
[24] Raviv, T., Goldmann, A., Vayner, O., et al. (2023) CRC-Aided Learned Ensembles of Belief-Propagation Polar Decoders.
https://arxiv.org/abs/2301.06060

为你推荐