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

Interference identification model based on deep convolutional neural network and intelligent identification algorithm

A neural network and interference identification technology, applied in biological neural network models, neural learning methods, neural architectures, etc., to achieve the effects of clear physical meaning, reduced computational complexity, and improved models

Active Publication Date: 2020-04-10
ARMY ENG UNIV OF PLA
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, as far as the current research status is concerned, most of the research on the identification of interference signals focuses on the feature extraction of different interference signals in different communication systems, and there are relatively few studies on classification algorithms, which also shows that the characteristics of interference identification based on feature extraction The importance of extraction, there is still a lot of research space for general interference signal classification algorithms such as convolutional neural networks

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
  • Interference identification model based on deep convolutional neural network and intelligent identification algorithm
  • Interference identification model based on deep convolutional neural network and intelligent identification algorithm
  • Interference identification model based on deep convolutional neural network and intelligent identification algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] The first embodiment of the present invention is specifically described as follows. The system simulation adopts the python language and is based on the tensorflow deep learning framework, and the parameter setting does not affect the generality. This example verifies the validity of the proposed model and method, Figure 4 Verify the validity of the fixed-frequency interference mode. The parameters are set as: the frequency band of interference is 20MHz, the frequency resolution of spectrum sensing is 100kHz, the receiver performs full-band sensing every 1ms, and keeps the sensed spectrum data for 200ms. Therefore, S t The matrix size is 200×200, the interference signal bandwidth is 4MHz, the signal waveform is raised cosine wave, and the roll-off coefficient is α=0.5. The interference power is 30dBm. In Embodiment 1, two fixed-frequency interference modes are considered:

[0073] 1. Single-tone interference, the interference frequency is 2MHz.

[0074] 2. Multi-to...

Embodiment 2

[0077] The second embodiment of the present invention is specifically described as follows. The system simulation adopts the python language and is based on the tensorflow deep learning framework, and the parameter setting does not affect the generality. This example verifies the validity of the proposed model and method, Figure 4 To verify the validity of the fixed frequency interference mode, Figure 5 Verify the effectiveness of swept frequency interference identification. The parameters are set as: the frequency band of interference is 20MHz, the frequency resolution of spectrum sensing is 100kHz, the receiver performs full-band sensing every 1ms, and keeps the sensed spectrum data for 200ms. Therefore, S t The matrix size is 200×200, the interference signal bandwidth is 4MHz, the signal waveform is raised cosine wave, and the roll-off coefficient is α=0.5. The interference power is 30dBm. In Embodiment 2, the frequency sweep interference mode is considered: frequency ...

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 an interference identification model based on a deep convolutional neural network and an intelligent identification algorithm. Describing the interference identification modelbased on the deep convolutional neural network as follows: describing the interference identification model based on the deep convolutional neural network; the receiver used for interference identification collects data of interference signals sent by one or more jammers. And taking the frequency spectrum waterfall plot of the receiver as a receiving end as a network input layer to carry out a plurality of trainings, and taking the frequency spectrum waterfall plot of the receiver as network input to carry out online identification according to a trained storage model and the frequency spectrum waterfall of the receiving end after an enough fitting degree training model is reached. And in combination with other structures or methods, the model is complete, the physical significance is clear, the design algorithm is reasonable and effective, and the interference identification scene based on the deep convolutional neural network algorithm can be better described.

Description

technical field [0001] The invention relates to the technical field of wireless communication, in particular to an interference identification model and an intelligent identification algorithm based on a deep convolutional neural network. Background technique [0002] Communication confrontation refers to the electromagnetic struggle in the field of radio communication by the use of common radio communication equipment and special communication countermeasure equipment. Due to the increasing number of frequency-using equipment in the communication environment, communication confrontation has become a hot topic, and in-depth research on how to better avoid the impact of the enemy and its own on its own frequency has become a top priority. With the rapid development of machine learning, the intelligence level of various devices has been continuously improved, and intelligent interference and intelligent anti-interference have also become one of the research topics in the field...

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): H04W24/06G06N3/04G06N3/08
CPCH04W24/06G06N3/08G06N3/045
Inventor 宋绯蔡源陈瑾徐煜华崔丽宋轩初晓婧张潇
Owner ARMY ENG UNIV OF PLA
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