Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Classification and identification method for communication signal modulating mode based on ART2A-DWNN

A technology of ART2A and modulation mode, which is applied in the direction of character and pattern recognition, modulated carrier system, neural learning method, etc., can solve the problems of long classification recognition judgment cycle and low recognition accuracy, and achieve good self-adaptive learning and self-categorization Capability, simple calculation process, and good scalability

Inactive Publication Date: 2010-03-10
HARBIN INST OF TECH
View PDF0 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the problem of long period of judgment and low recognition accuracy for the classification and recognition of communication signal modulation methods using a single neural network, and to provide a method for classification and recognition of communication signal modulation methods based on ART2A-DWNN

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
  • Classification and identification method for communication signal modulating mode based on ART2A-DWNN
  • Classification and identification method for communication signal modulating mode based on ART2A-DWNN
  • Classification and identification method for communication signal modulating mode based on ART2A-DWNN

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0026] Specific implementation mode one: the following combination Figure 1 to Figure 5 Describe this embodiment, this embodiment is realized based on ART2A neural network and DWNN neural network, ART2A neural network is made up of attention subsystem, orientation subsystem and modulation type secondary judgment module, attention subsystem is represented by short-term memory characteristic field F 1 and short-term memory category representation field F 2 composition, the warning threshold ρ is pre-stored in the orientation subsystem, and the classification and identification process of its communication signal modulation mode is:

[0027] Step 1. Extract the eigenvector of the communication signal, use the extracted eigenvector as the input vector of the ART2A neural network, and apply the ART2A-E algorithm to process the input vector of the ART2A neural network: set the input vector as an N-dimensional column vector X(k), input the N-dimensional column vector X(k) to the sh...

specific Embodiment approach 2

[0041] Specific implementation mode two: this implementation mode is a further description of step two in the first implementation mode: the first winning label j in the above step two 1 * (k) is calculated as:

[0042] j 1 * (k)=arg(min[||X(k)-W j*(k) (k)||]), j=1~μ(k),

[0043] Where: ||X(k)-W j*(k) (k)|| means X(k) and W j*(k) the Euclidean distance of (k),

[0044] X(k) and W j*(k) The formula for calculating the Euclidean distance of (k) is:

[0045] | | X ( k ) - W j * ( k ) ( k ) | | = [ Σ i = 1 N ...

specific Embodiment approach 3

[0048] Specific embodiment three: this embodiment is a further description of step three in embodiment one: in step three, the second judgment module of the modulation type determines the vector Y(k) output after clustering as L-type modulation type MT i The modulation method is: the class L modulation type MT i Set the corresponding warning threshold value for each type of modulation type, according to the warning threshold value, one or more continuous output nodes [Y i (k),...,Y j (k)] T Decision as a modulation type MT i , where 1≤i≤j≤M.

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 relates to a classification and identification method for a communication signal modulating mode based on ART2A-DWNN, belonging to the field of classification and identification of communication signal modulating modes and solving the problem that single neural network has long period and low accuracy for classifying and identifying communication signals. In the method, an ART2A-E algorithm based on an ART2A network is taken as a first layer of a combined neural network, and similar modes is roughly classified by selecting relatively smaller vigilance parameters; a DWNN is directly connected with the output layer with the corresponding type of the ART2A network, Morlet mother wavelet Phi(x) with higher resolution in frequency domain and time domain are adopted, learning is carried out by utilizing error back-propagation algorithm, a synaptic weight can be modified with a conjugate gradient method till output is within the error range, and the number of modes in each typeis reduced after rough ART2-E classification, so that the DWNN can quickly converge. The invention is used for classification and identification of communication signals.

Description

technical field [0001] The invention relates to an ART2A-DWNN-based method for classifying and identifying communication signal modulation modes, and belongs to the field of classifying and identifying communication signal modulation modes. Background technique [0002] At present, the identification methods for the modulation mode of communication signals are mainly divided into the maximum likelihood hypothesis testing method based on decision theory and the statistical pattern recognition method based on feature extraction. Among the statistical pattern recognition methods based on feature extraction, the identification based on artificial neural network The method is widely used because of its nonlinear and adaptive characteristics. At present, the network of classifier based on artificial neural network for classifying communication signals mainly includes feedforward BP neural network, radial basis function RBF neural network, wavelet neural network WNN, support vector...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/66G06N3/063G06N3/08H04L27/00
Inventor 赵雅琴陈淞任广辉吴芝路
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com