PC-SCMA joint iterative detection and decoding method based on deep learning

Abstract

The invention belongs to the field of computer and communication technology, and in particular relates to a joint iterative detection and decoding method based on deep learning; the method includes adding Learnable weight factors; add learnable offsets that can be learned offline in the information iteration of the factor graph of the belief propagation algorithm; and form a joint factor graph; combine the learnable weight factors and learnable offsets in the joint factor graph The amount is used as the hidden layer parameter of the deep neural network, and the scrambled information bit value is input to iteratively update in the deep neural network; the resource node information, prior node information and user node information are iteratively updated in sequence; after updating the resource node information, After the prior information of the user node and the information of the user node, an estimated transmission symbol is output; the present invention can effectively improve the performance of detection and decoding BER while increasing the computational complexity within an acceptable range.

Description

technical field [0001] The present invention is a deep learning (Deep Learning, DL) based PC-SCMA (Polar Coded-Sparse Code Multiple Access) joint iterative detection and decoding (Joint Iterative Detection and Decoding Algorithm, JIDD) method. It has the characteristics of high code and detection accuracy, and can be applied to scenarios with high spectrum utilization and mass user access in the 5th generation mobile communication system, and belongs to the field of computer and communication technology. Background technique [0002] With the continuous development of mobile communications, diversified application scenarios have higher and higher performance requirements for communication technologies. The 5G mobile communication network is expected to achieve high spectral efficiency, which puts forward a demand for the improvement of channel coding and decoding technology and multiple access technology. Channel coding and decoding technology is directly related to the perf...

AI Technical Summary

Problems solved by technology

[0004] However, with the increase of the polar code length and the number of iterations of the decoding algorithm, a large number of learnable parameters introduced after the combination of deep learning technology increase a large number of multiplication operations and storage space occupation, so how to improve the decoding BER performance while Not increasing the computational complexity too much has become a current hot research direction

On the other hand, the SCMA system multi-user detection algorithm combined with deep learning also has problems such as high computational complexity or unsatisfactory detection performance that need to be solved urgently

Images