Optimization Design of Polar-LDPC Concatenated Scheme Based on Deep Learning. (June 2020)

• Record Type: Journal Article
• Authors: Wang, Xiumin; Li, Jun; Chang, Hong; He, Jinlong
• Is Part Of: Computers & electrical engineering. Volume 84(2020)
• Publication Date: 2020-06
• Subjects: Polar codes -- LDPC codes -- Polar-LDPC concatenated codes -- Deep learning -- Time complexity; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2020.106636
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: In 5G communication system, because of incomplete polarization of the polar codes, the performance of the polar codes is poor at low and medium SNR. Concatenating the polar codes and low-density parity-check codes (LDPC), the Polar-LDPC concatenated scheme improves decoding performance. Although the decoding performance of the Polar-LDPC concatenated scheme is improved, the decoding delay is increased compared with the non-concatenated scheme. In order to solve this problem, we propose a Polar-LDPC concatenated scheme based on deep learning by paralleling multiple neural networks. The decoding delay of the polar codes assisted by the neural network is reduced in the proposed Polar-LDPC concatenated scheme. The experiment results show that the proposed concatenated scheme can reduce time complexity compared with the non-concatenated scheme under the same code length.