Directional neural evolution channel coding and decoding method, storage medium and device

Abstract

The invention discloses a directional neural evolution channel coding and decoding method, a storage medium and a device, and the method comprises the steps: a transmitting end carries out the channel coding of a to-be-transmitted information bit, and obtains a first channel output sequence; a receiving end carries out channel decoding, if a decoding result is correct, decoding is ended, and otherwise, disturbance noise is randomly added; decoding the sequence added with the disturbance noise until the number of adding times reaches a first threshold value; calling a table function, and loading directional noise under a corresponding signal-to-noise ratio in a directional noise table; and adding the directional noise to the first channel output sequence, and decoding until the number of adding times reaches a second threshold value. Neural evolution learning is applied to a channel coding and decoding algorithm, the directivity of the noise is ensured, and the generation of the directional noise adopts offline operation, so that the decoding complexity cannot be improved; the addition of random noise and the addition of directional noise are only introduced after the upper-level decoding fails, so that the delay of the system is reduced.

Description

technical field [0001] The present invention relates to the technical field of channel coding, in particular to a directional neuroevolutionary channel coding and decoding method, storage medium and device. Background technique [0002] Channel coding, also called error control coding, is the cornerstone of all modern communication systems. In the process of signal transmission, due to the inevitable interference of the environment and the inevitable physical defects of the transmission medium, bit errors occur in the transmitted data. Channel coding is used to generate additional redundancy for the information to be sent in exchange for the reliability of the received information. It can improve the error correction ability and anti-interference ability of the system. In recent years, LDPC codes (Low-Density Parity-Checkcodes) approaching the Shannon limit and polar codes (Polar codes) with a capacity limit have become the focus of widespread attention due to their stronge...

Images