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

CNN (convolutional neural network) based method for identifying communication interference signals at large dynamic SNR (signal to noise ratio)

A convolutional neural network and communication interference technology, which is applied in the field of communication interference signal identification under large dynamic signal-to-noise ratio, can solve the problems of low accuracy of interference signal, complex form, and difficulty in feature extraction, and achieves increased convenience and classification. Improve accuracy and reduce the effect of manually extracting features

Inactive Publication Date: 2017-09-26
HARBIN INST OF TECH
View PDF3 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problem that the existing type identification method for interference signals manually extracts features such as statistics and high-order cumulants, which is difficult to extract features, complex in form, and has low accuracy in classifying interference signals.

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
  • CNN (convolutional neural network) based method for identifying communication interference signals at large dynamic SNR (signal to noise ratio)
  • CNN (convolutional neural network) based method for identifying communication interference signals at large dynamic SNR (signal to noise ratio)
  • CNN (convolutional neural network) based method for identifying communication interference signals at large dynamic SNR (signal to noise ratio)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0092] figure 1 It shows the flow chart of the method for identifying communication interference signals based on convolutional neural network under high dynamic signal-to-noise ratio in the embodiment. The communication interference signal identification method based on convolutional neural network under large dynamic signal-to-noise ratio is used to extract interference signals, and then classify the interference signals, so as to effectively suppress the corresponding interference types.

[0093] figure 2 The structural diagram of the convolutional neural network during training in the embodiment is shown, and the specific structural parameters of the convolutional neural network are shown in Table 1.

[0094] image 3 shows the structural diagram of the convolutional neural network during non-training in the embodiment,

[0095] Table 1 Convolutional neural network network structure parameters

[0096]

[0097] refer to Figure 1 to Figure 3 In this embodiment, the ...

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 CNN (convolutional neural network) based method for identifying communication interference signals at large dynamic SNR (signal to noise ratio), relates to the field of interference signal type identification and aims to solve the problems that the conventional interference signal type identification method is high in feature extraction difficulty, complex in form and low in accuracy of interference signal classification due to adoption of artificial extraction of features such as statistics, high-order cumulant and the like. With adoption of the method, totally 15 interference signals including 5 common interference signals and pairwise combinations of the 5 interference signals can be identified, the 5 interference signals include an audio interference signal, a same-frequency-band narrow-band interference signal, a sweeping interference signal, a rectangular pulse interference signal and a spread spectrum interference signal, and the feature that the interference signals have strong robustness at the large dynamic SNR is extracted by establishing a CNN model; SVM (support vector machine) classifiers for the 15 classes are constructed to classify the 15 interference signals and used for classifying the interference signals.

Description

technical field [0001] The invention relates to a method for identifying communication interference signals under a large dynamic signal-to-noise ratio based on a convolutional neural network. It belongs to the field of interference signal type identification. Background technique [0002] Since modern communication technology uses open communication transmission channels, communication systems are likely to suffer from intentional or unintentional interference. Therefore, both civil and military systems must adopt effective anti-interference methods to suppress interference in the system. However, the interference signals in actual communication systems are complex and diverse, and some anti-interference measures will inevitably damage useful signals. Moreover, an interference suppression method is usually only effective for one type of interference. Due to the complexity and variety of interference means in actual communication countermeasures, there may be one or more u...

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): G06K9/62G06N3/08
CPCG06N3/08G06F18/2411
Inventor 吴芝路罗昊宸尹振东杨柱天周思洋
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