International Journal of Advanced Network, Monitoring, and Controls | |
Optimization and Improvement of BP Decoding Algorithm for Polar Codes Based on Deep Learning | |
article | |
Li Ge1  Guiping Li1  | |
[1] School of Computer Science and Engineering Xi’an Technological University Xi’an | |
关键词: Polar Codes; Belief Propagation; Deep Learning; | |
DOI : 10.2478/ijanmc-2023-0057 | |
学科分类:社会科学、人文和艺术(综合) | |
来源: Asociación Regional De Diálisis Y Trasplantes Renales | |
【 摘 要 】
In order to solve the high latency problem of polar codes belief propagation decoding algorithm in the 5G and the dimension limitation problem of belief propagation decoding algorithm under deep learning, a multilayer perceptron belief propagation decoding (MLP-BP) algorithm based on partitioning idea is proposed. In this work, polar codes is decoded using neural networks in partitioning, and the right transfer message value of BP decoding algorithm is also set to complete the propagation process. Simulation results show that, compared with BP decoding algorithm, the proposed algorithm has better decoding performance, reducing the decoding latency, and it is also applicable to long polar codes.
【 授权许可】
CC BY-NC-ND
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO202307160003481ZK.pdf | 1052KB | download |