Channel coding pattern recognition method based on one-dimensional convolutional neural network

A convolutional neural network and channel coding technology, which is applied to biological neural network models, channel coding adjustments, neural learning methods, etc., can solve the problem of not being able to know the coding parameters of the code type category

Pending Publication Date: 2021-04-30
NAT UNIV OF DEFENSE TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above methods all estimate the parameters on the premise of knowing the pattern type, but in the actual non-cooperative channel background, it is impossible to know the pattern type and coding parameters used by the other party, so the received 0 / 1 Blind identification of bit streams is an urgent problem to be solved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Channel coding pattern recognition method based on one-dimensional convolutional neural network
  • Channel coding pattern recognition method based on one-dimensional convolutional neural network
  • Channel coding pattern recognition method based on one-dimensional convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0060] combine figure 1 , the present invention is based on a one-dimensional convolutional neural network channel coding pattern identification method, comprising the following steps:

[0061] Step 1. According to the simulated coded data, the three types of channel coded data of Hamming code, cyclic code, and convolutional code are simulated according to the change of the codeword, as follows:

[0062] Step 1.1, encode the Hamming code data:

[0063] The Hamming code on the binary field GF(2) is defined by a positive integer m not less than 3, and its code length is:

[0064] n=2 m -1

[0065] The packet length is:

[0066] k=n-r=2 m -1-m

[0067] The number of checksums is:

[0068] r=n-k=m

[0069] The encoding process is obtained according to the generator matrix G, and the information group is set as M=(m k-1 ,m k-2 ,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a channel coding pattern recognition method based on a one-dimensional convolutional neural network. The method comprises the following steps: firstly, simulating three types of channel coded data which comprises Hamming codes, cyclic codes and convolutional codes according to the change of code words according to simulated coded data; adding noise to each type of codes, and the bit error rate is calculated; randomly superposing each type of codewords to generate a 1000 * 5000 codeword matrix, adding a label to each type of codeword matrix, and taking the first 3500 columns of the matrix as a training set and the last 1500 columns of the matrix as a test set; performing classification processing through a one-dimensional convolutional neural network, and verifying the feasibility of the algorithm by changing the number of convolutional layers, the number of iterations and different learning rates; and finally, performing classification processing by using an RNN network, and comparing the performance of different networks. According to the invention, blind recognition of the channel coding pattern is realized, the calculation speed is fast, the recognition efficiency is high, the anti-noise performance is good, and the engineering applicability is good.

Description

technical field [0001] The invention relates to the technical field of channel coding, in particular to a channel coding pattern recognition method based on a one-dimensional convolutional neural network. Background technique [0002] In recent years, the blind recognition of channel coding has become a hot spot in the field of non-cooperative signal processing. Because of its own error correction capability and strict algebraic structure, channel coding is widely used in communication countermeasures and electronic reconnaissance, and has become a key technology in the fields of adaptive modulation and cognitive radio. [0003] Channel coding techniques include pseudo-random scrambling, error-correcting coding, interleaved coding, concatenated coding, etc. The key lies in error-correcting coding. For the field of information detection, in the context of non-cooperative communication, it is necessary to rely on technical means to identify and analyze error correction coding...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): H04L1/00G06N3/04G06N3/08
CPCH04L1/0038H04L1/0009G06N3/08G06N3/045
Inventor 雷迎科梅凡陈红金虎陈翔张孟伯
Owner NAT UNIV OF DEFENSE TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap