CN110719112B

CN110719112B - Parameter self-adaptive RS code decoding method based on deep learning

Info

Publication number: CN110719112B
Application number: CN201910861946.XA
Authority: CN
Inventors: 梁煜; 安翔宇; 张为
Original assignee: Tianjin University
Current assignee: Tianjin University
Priority date: 2019-09-12
Filing date: 2019-09-12
Publication date: 2023-08-29
Anticipated expiration: 2039-09-12
Also published as: CN110719112A

Abstract

The invention relates to a parameter self-adaptive RS code decoding method based on deep learning, which comprises the following steps: RS code encoding is carried out on the information sequence X, and an encoded information sequence u is obtained; performing BPSK modulation on the information sequence u to obtain a transmission sequence s; the transmission sequence passes through a Gaussian white noise channel to obtain a receiving sequence y; constructing a reliability matrix by using the receiving sequence y, and calculating to obtain a reliability sequence R; dividing the reliability sequence R into a training set and a testing set; training a neural network; aiming at the training set of R and the corresponding receiving sequence y, respectively testing by using LCC decoding algorithms with different eta values to find an eta optimal solution corresponding to the training set receiving sequence y one by one; and taking the SNR and the reliability sequence R as input, and taking the minimum eta value obtained by the test as a classification label, wherein the minimum eta value and the classification label together form a data set for training the neural network.

Description

Parameter self-adaptive RS code decoding method based on deep learning

Technical Field

The invention belongs to the field of error control coding in channel coding, and relates to a parameter self-adaptive decoding algorithm based on deep learning.

Background

Error control is a basic method for controlling and correcting transmission errors caused by channel noise by utilizing coding and decoding technology in digital communication so as to ensure the effectiveness and reliability of the communication. Error control coding is widely applied in the field of digital communication and has important research significance. The Reed-Solomon (RS) code is one of error control codes, and was first constructed by Reed and Solomon in 1960, which has a simple structure, short decoding delay, and abundant structural characteristics, and can correct random errors and burst errors. In particular, in applications for correcting burst errors, RS codes perform better than other error control codes. At present, the RS code is widely applied to the fields of wireless communication, optical fiber communication, magnetic disk, solid state storage and the like, and is always a hot spot for research in the industry and academia.

The decoding algorithms of RS codes can be divided into two categories according to the form of the demodulator output symbols: hard decision decoding algorithm and soft decision decoding algorithm. The hard decision decoding algorithm is relatively simple and easy to realize in hardware, but the algorithm does not fully utilize the soft information of the channel, so that the decoding performance is lost. Soft decision decoding trades for improvement in decoding gain at the cost of complexity, and mainly includes KV, BGMD and LCC algorithms. Wherein the LCC algorithm is superior to both in complexity and computation cycle. Meanwhile, the decoding performance and complexity of the algorithm are closely related to the parameter eta of the reassignment process.

In recent years, deep learning has attracted worldwide attention due to its strong ability to solve complex tasks. The deep learning method is also applied to the fields of voice recognition, computer vision, machine translation and the like, and brings great innovation and breakthrough to the fields. The scheme combining the deep learning and coding fields has achieved some research results, and the deep research is developed in the fields of pole codes, BCH codes, LDPC codes and the like. Most current research regards decoding as a classification problem, using neural network structures (e.g., DNN, CNN, RNN) to achieve a complete decoding process. A significant disadvantage of such schemes is that the neural network is very poor in predicting the non-learned codewords (codewords not included in the training set), and the possible exponential explosion of codewords due to the increased codeword length can greatly impact decoder performance. In addition, some researches propose to use deep learning to assist the traditional decoding algorithm to eliminate related noise, predict key parameters and the like so as to improve the performance of the traditional algorithm.

Disclosure of Invention

The invention aims to provide a parameter self-adaptive decoding method based on deep learning, which can reduce complexity and improve efficiency. The technical proposal is as follows:

a parameter self-adaptive RS code decoding method based on deep learning comprises the following steps:

(1) And (3) carrying out RS code encoding on the information sequence X to obtain an encoded information sequence u. And performing BPSK modulation on the information sequence u to obtain a transmission sequence s. The transmission sequence passes through a white gaussian noise channel to obtain a receiving sequence y. And constructing a reliability matrix by using the receiving sequence y, and calculating to obtain a reliability sequence R. The reliability sequence R is divided into a training set and a test set.

(2) Training of the neural network is performed. And aiming at the training set of R and the corresponding receiving sequence y, respectively testing by using LCC decoding algorithms with different eta values, and finding an eta optimal solution corresponding to the training set receiving sequence y one by one. And taking the SNR and the reliability sequence R as input, and taking the minimum eta value obtained by the test as a classification label, wherein the minimum eta value and the classification label together form a data set for training the neural network. The neural network structure uses an MLP structure, the weight w and the bias b of the network are continuously optimized through a back propagation algorithm, and the neural network with high classification accuracy is obtained under the conditions of enough data sets and training algebra, so that the training process is completed.

(3) And inputting the test set of SNR and R, and calculating an eta optimal solution through the trained neural network. And then, performing LCC decoding by using the eta value subjected to parameter self-adaption to obtain a decoded sequence X', and finally finishing decoding.

Drawings

FIG. 1 is a system block diagram of a parameter adaptive decoding algorithm based on deep learning

Training process of the neural network of FIG. 2

Detailed Description

The parameter self-adaptive decoding algorithm based on deep learning provided by the invention is an algorithm for assisting traditional RS code LCC decoding by using deep learning. According to analysis, the key parameter eta in the LCC algorithm is closely related to the channel environment and reliability information, and the size of the eta value determines the decoding performance and complexity of the LCC algorithm. Solving the problem of the eta optimal solution can be regarded as a simple classification problem, and the neural network has strong mode classification capability and can simply and efficiently select the eta optimal solution. The key parameter eta in the LCC algorithm is adaptively changed along with the channel environment and the reliability information of the receiving sequence by a deep learning method, so that the decoding efficiency can be improved on the premise of not affecting the decoding performance.

The parameter self-adaptive decoding algorithm based on deep learning specifically comprises two stages, namely a training stage and a decoding stage.

(1) The training phase implements the process of building and training the neural network. Based on supervised learning, the invention constructs a multi-layer perceptron (MLP) neural network structure, and the number of nodes and the number of layers are determined by the code length. In the aspect of a training data set, the signal-to-noise ratio and likelihood ratio are connected as input, and the eta optimal solution is obtained by testing a corresponding traditional decoding algorithm and is used as a classification label. Through training and debugging, the neural network with excellent classification accuracy is obtained.

(2) And in the decoding stage, the signal-to-noise ratio and the likelihood ratio of the specific code word are input into a trained neural network to obtain an eta optimal solution. And then carrying out traditional LCC decoding according to the optimal solution.

The technical scheme of the invention is further specifically described below with reference to the accompanying drawings.

As shown in fig. 1, the parameter adaptive decoding algorithm based on deep learning specifically includes the following steps:

(4) And (3) carrying out RS code encoding on the information sequence X to obtain an encoded information sequence u. To convert the encoded information into a pattern suitable for transmission in the channel, the information sequence u is BPSK modulated to obtain a transmission sequence s. The transmission sequence passes through a white gaussian noise channel (AWGN) to obtain a reception sequence y (y=s+n, n is AWGN channel noise). And constructing a reliability matrix by using the receiving sequence y, and calculating to obtain a reliability sequence R. The reliability sequence R is divided into a training set and a testing set, and the ratio of the training set to the testing set is 9:1.

(5) As in fig. 2, training of the neural network is performed. For the training set of R and the corresponding receiving sequence y, LCC decoding algorithms with different eta values are used for testing respectively, and eta optimal solutions (minimum values under the condition of correct decoding) corresponding to the training set receiving sequence y one by one are found. And taking the SNR and the reliability sequence R as input, and taking the minimum eta value obtained by the test as a classification label, wherein the minimum eta value and the classification label together form a data set for training the neural network. The neural network structure uses a multi-layer perceptron (MLP) structure, the weight w and the bias b of the network are continuously optimized through a back propagation algorithm, and the neural network with high classification accuracy is obtained under the conditions of enough data sets and training algebra, so that the training process is completed.

(6) And inputting the test set of SNR and R, and calculating an eta optimal solution through the trained neural network. And then, performing LCC decoding by using the eta value subjected to parameter self-adaption to obtain a decoded sequence X', and finally finishing decoding.

The above examples are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above examples, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principle of the present invention should be made in the equivalent manner, and the embodiments are included in the protection scope of the present invention.

Claims

1. A parameter self-adaptive RS code decoding method based on deep learning comprises the following steps:

(1) RS code encoding is carried out on the information sequence X, and an encoded information sequence u is obtained; performing BPSK modulation on the information sequence u to obtain a transmission sequence s; the transmission sequence s passes through a Gaussian white noise channel to obtain a receiving sequence y; constructing a reliability matrix by using the receiving sequence y, and calculating to obtain a reliability sequence R; dividing the reliability sequence R into a training set and a testing set;

(2) Training of the neural network is performed: η is a key parameter in the LCC decoding algorithm and is closely related to channel environment and reliability information, the size of the η value determines the decoding performance and complexity of the LCC algorithm, the LCC decoding algorithms with different η values are used for respectively testing a training set and a corresponding receiving sequence y of R, and an η optimal solution corresponding to the training set receiving sequence y one by one is found, wherein the η optimal solution is the minimum value under the condition of correct decoding; taking SNR and reliability sequence R as input, and taking the minimum eta value obtained by test as a classification label, and forming a data set of neural network training together; the neural network structure uses an MLP structure, the weight w and the bias b of the network are continuously optimized through a back propagation algorithm, and the neural network with high classification accuracy is obtained under the conditions of enough data sets and training algebra, so that the training process is completed.