相关噪声下基于深度学习的LDPC码码率半盲识别算法

打开文本图片集

中图分类号：TN92 文献标志码：A DOI：10.12305/j.issn.1001-506X.2025.04.30

Abstract：In order to correctly identify the channel coding parameters of low-density parity-check coded wireless communication systems with high-order modulation over correlated noise，two novel deep learningbased semi-blind identification algorithms for code rates are proposed under the asumption that the candidate set of code rates and the corresponding parity check matrices are known. The proposed neural networks consist of the denoising subnetwork and the code-rate identification subnetwork.Moreover，the denoising subnetwork designs the real-valued denoising subnetwork and the complex-valued denoising subnetwork. Compared to the real-valued denoising subnetwork，the complex-valued denoising subnetwork has a beter ability to process complex-valued signals with the cost of high complexity.Furthermore，inorder to reduce thecomplexity of the complex-valued denoising subnetwork，a novel network compression algorithm based on network pruning technology is proposed. Simulation results show that，by using the novel multi-task learning strategy which jointly optimizes the denoising loss function and the lossfunction corresponding to code-rate identification，on one hand，the proposed neural networks have better identification performance comparing with the traditional algorithms with correlated noise，on the other hand，the identification algorithm based on complex-valued denoising subnetwork stilloutperforms the identification algorithm based on real-valued denoising subnetwork when its complexity approaches to thatof the identification algorithm basedonreal-valued denoising subnetwork by using the network compression algorithm.

Keywords：correlated noise；blind identification of channel coding；low-density parity-check（LDPC） code; deep learning；complex-valued network

0引言

随着以深度学习（deeplearning，DL）为代表的人工智能（artificialintelligence，AI）技术的快速发展，DL与通信融合而成的智能通信成为通信领域新的研究热点，如基于DL的语义通信[2、信道估计[3]、信道译码算法设计[4]等。（剩余18629字）