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

Deep neural network modulation signal open set identification method and system

A deep neural network and modulated signal technology, applied in the field of deep neural network modulated signal open set identification method and system, can solve the problems of high signal quality requirements, no consideration of open set identification, noise sensitivity, etc., to improve the recognition accuracy, The effect of enhancing robustness and generalization

Pending Publication Date: 2022-02-01
XIDIAN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a deep neural network modulation signal open-set recognition method and system, which solves the problem in the prior art that the modulation recognition algorithm is sensitive to noise and does not consider the open-set recognition in the real environment, and cannot distinguish unknown modulations. Type signals, technical issues that require high signal quality
Through signal enhancement, the problems of sensitivity to noise, inability to distinguish signals of unknown modulation types, and high requirements for signal quality have been solved. By adding signals of unknown modulation types and loss functions to the training data, open-set recognition is realized and recognition accuracy is improved. rate, the technical effect of enhancing robustness and generalization

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
  • Deep neural network modulation signal open set identification method and system
  • Deep neural network modulation signal open set identification method and system
  • Deep neural network modulation signal open set identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Such as figure 1 As shown, the embodiment of the present application provides a deep neural network modulation signal open set identification method, wherein the method includes:

[0032] S100: Establish a data set X of known modulation type and a data set V of unknown modulation type in the first environment, where X={x 1 ,x 2 ,...,x n},n=1,2,...,N,V={v 1 ,v 2 ,...,v m},m=1,2,...,M;

[0033] Specifically, the first environment refers to any complex environment including a Gaussian white noise environment with different signal-to-noise ratios and a real environmental noise channel environment, etc., and the known modulation types include amplitude modulation (Amplitude Modulation, AM), frequency modulation (Frequency Modulation, FM), frequency shift keying (Frequency Shift Keying, FSK) and phase shift keying (Phase Shift Keying, PSK) binary phase frequency shift keying (Binary Phase Shift Keying, BPSK), four phase frequency shift keying ( Quadrature Phase Shift K...

Embodiment 2

[0097] Based on the same inventive concept as that of a deep neural network modulation signal open set recognition method in the foregoing embodiments, as Figure 9 As shown, the embodiment of the present application provides a deep neural network modulation signal open set recognition system, wherein the system includes:

[0098] A first establishing unit 11, the first establishing unit 11 is used to establish a data set X of a known modulation type and a data set V of an unknown modulation type in a first environment, where X={x 1 ,x 2 ,...,x n},n=1,2,...,N,V={v 1 ,v 2 ,...,v m},m=1,2,...,M;

[0099] The first execution unit 12, the first execution unit 12 is used to initialize the parameters of the generator G and the discriminator D;

[0100] A first obtaining unit 13, the first obtaining unit 13 is configured to obtain a preset parameter update times threshold;

[0101] The second execution unit 14, the second execution unit 14 is configured to update the parameter...

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 provides a deep neural network modulation signal open set identification method and system, and the method comprises the steps: building a data set X of a known modulation type and a data set V of an unknown modulation type in a first environment, and initializing the parameters of a generator G and a discriminator D; obtaining a preset parameter updating frequency threshold value; performing parameter updating on the discriminator D and the generator G according to a preset parameter updating frequency threshold value, and performing signal enhancement on the data set X and the data set V; modeling the modulation signal through a one-dimensional convolution residual network to obtain a 1D-ResNet network model; and inputting the test set S into the 1D-ResNet network model to obtain a first identification result. The technical problems that in the prior art, a modulation recognition algorithm is sensitive to noise, open set recognition in a real environment is not considered, signals of unknown modulation types cannot be distinguished, and the requirement for signal quality is high are solved.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a deep neural network modulation signal open-set recognition method and system. Background technique [0002] In recent years, with the rise of neural network (Neural Network, NN) technology, neural networks have been applied to modulation recognition tasks due to their excellent feature extraction and data mapping capabilities. In a complex realistic electromagnetic environment, it is difficult for the training set to collect all types of debugging data for neural network training, so there will be some modulation types in the test set that have not appeared in the training set. Knowing the modulation type of the signal, but also identifying the signal of the unknown modulation type, such an identification task is called open set identification. Since the wireless signal is easily affected by interference and noise in the real environment, the signal quality of the signa...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F2218/08G06F2218/12G06F18/23G06F18/241
Inventor 王泽林赵光辉金星
Owner XIDIAN UNIV
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