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

Radiation source individual identification method based on multi-domain feature fusion

A feature fusion and recognition method technology, applied in the field of information detection and recognition, can solve the problems of incomplete feature information, low individual recognition rate of radiation sources, and weak generalization ability of classifiers, so as to improve generalization ability and improve radiation source The effect of the individual identification effect

Active Publication Date: 2020-10-13
HARBIN ENG UNIV
View PDF10 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a multi-domain feature-based method that solves the problems of incomplete feature information, weak generalization ability of the classifier, strong subjectivity of expert analysis, and low identification rate of radiation source individuals in the existing radiation source individual identification method. Fusion individual radiation source identification method

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
  • Radiation source individual identification method based on multi-domain feature fusion
  • Radiation source individual identification method based on multi-domain feature fusion
  • Radiation source individual identification method based on multi-domain feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] A radiation source individual identification method based on multi-domain feature fusion, comprising the following steps:

[0049] Step 1: Input a signal set containing multiple different radar radiation source transmitters, and perform discrete processing on each signal in the signal set to obtain the original data set; divide the original data set randomly into cyclic neural network signal data set and A dataset of transmitter signals from known radiation sources;

[0050] Step 2: use the cyclic neural network signal data set to train the cyclic neural network to obtain the cyclic neural network feature extractor;

[0051] Step 3: Select a signal data x from the known radiation source transmitter signal data set i (n), put x i (n) Input to the cyclic neural network feature extractor to obtain the time-domain cyclic feature F i1 ; Wherein, i=1,2,...,R, R is the number of data in the known radiation source transmitter signal data set; n is the signal data x i The nu...

Embodiment 2

[0076] Obtain signal data x in step 4 i The time-frequency domain phase characteristic F of (n) i2 The specific method is:

[0077] Step 4.1: For signal data x i (n) Perform Cui-Williams time-frequency distribution calculation to obtain CWD(n,ω); perform time-frequency domain processing on CWD(n,ω) to obtain the phase absolute value result Φ(n,ω);

[0078]

[0079]

[0080]

[0081] Among them, * represents the conjugate operation; σ is the scaling factor; ω is the angular frequency; γ is the time shift variable; μ is the time variable; A three-dimensional phase image is obtained. The value of the angular frequency ω in Φ(n,ω) is continuous, take a positive integer and write it as The value of n is already a positive integer, and discrete phase values ​​can be obtained 2D phase image Fig for discrete 3D phase images 1 Obtain. Define a two-dimensional image, the position of any pixel in the image is defined by Indicates that the pixel is located in the nth r...

Embodiment 3

[0086] The pre-trained convolutional neural network model in described step 4.3 is the VGG-16 network model based on ImageNet image data set pre-training; Described VGG-16 network model contains input layer, hidden layer and output layer, wherein hidden layer Containing 13 convolutional layers and 3 fully connected layers, the output layer of the VGG-16 network model is the third fully connected layer.

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 belongs to the technical field of information detection and identification, and particularly relates to a radiation source individual identification method based on multi-domain featurefusion. The radiation source individual identification method can solve the problems of poor classifier generalization ability, strong expert analysis subjectivity, low radiation source individual recognition rate and the like in the existing radiation source individual identification methods, multi-domain features such as a time domain, a time-frequency domain, a high-order domain and the like are fused, and a multi-layer neural network model is designed as a classifier so as to achieve radiation source individual recognition. The multi-domain features are fused to solve the problem that feature information is not comprehensive, a neural network model is adopted for recognition and classification, and the problems that prior information such as a radiation source signal modulation mode isrelied on during recognition, and subjectivity of an expert system is high are solved. Meanwhile, the neural network model improves the generalization capability of the system, and obtains a better radiation source individual recognition effect.

Description

technical field [0001] The invention belongs to the technical field of information detection and identification, and in particular relates to a radiation source individual identification method based on multi-domain feature fusion. Background technique [0002] As one of the important identification means, individual radiation source identification plays an irreplaceable role in battlefield target identification. Individual radiation source identification is to compare the characteristic parameters of the radiation source signal intercepted by the passive reconnaissance receiver with the radiation source characteristic parameter database, so as to confirm the identity of the radiation source and provide information support for subsequent mission execution and actions. The key steps of individual radiation source identification are feature parameter extraction and classifier design. The traditional feature extraction is based on the intentional pulse-to-pulse modulation char...

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): G06K9/00G06K9/62G06N3/04G06N3/08G01S7/02
CPCG06N3/084G01S7/021G06N3/045G06F2218/08G06F2218/12G06F18/23213G06F18/2415G06F18/253
Inventor 高敬鹏王旭项建弘王甫高路白锦良秦鹏王上月
Owner HARBIN ENG 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