A pulsar recognition method based on convolution neural network

A convolutional neural network and recognition method technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of low recognition rate and cumbersome recognition process, achieve fast and accurate recognition, and avoid artificial design features process, the effect of facilitating practical promotion and application

Inactive Publication Date: 2019-01-25
KUNMING UNIV OF SCI & TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a pulsar recognition metho...

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
  • A pulsar recognition method based on convolution neural network
  • A pulsar recognition method based on convolution neural network
  • A pulsar recognition method based on convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] Embodiment 1: as Figure 1-4 Shown, a kind of pulsar identification method based on convolutional neural network, the concrete steps of described method are as follows:

[0023] Step1. Obtain the pulse profile of the star signal as a sample set, and divide it into a training sample set, a verification sample set and a test sample set;

[0024] In Step 1, the pulse profile of the star signal includes a pulsar pulse profile and a non-pulsar pulse profile.

[0025] In the step Step1, the pulse profile of the star signal is as follows figure 2 and image 3 shown. Use graphic aids to collect 500 pulse contours of star signals as sample pictures, including 200 pulsar pulse contours and 300 non-pulsar pulse contours, and add labels to all sample pictures, and finally 80% of the sample pictures As a training sample set, 10% of the sample pictures are used as a verification sample set, and 10% of the sample pictures are used as a test sample set;

[0026] Step2. Construct ...

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 pulsar identification method based on a convolution neural network, belonging to the pulsar identification technical field. The invention iteratively trains the sample training set through the convolution neural network, thereby realizing the recognition of pulsars by using the trained convolution neural network model. The method converts the problem of pulsar recognition into the problem of image recognition and classification, which can identify pulsars quickly and accurately. Moreover, the method can maximize the use of more pulsar features, avoid the process of traditional manual feature design, greatly save time and cost, has real-time and simplicity, and is easy to be popularized and applied in practice.

Description

technical field [0001] The invention relates to a pulsar identification method based on a convolutional neural network, belonging to the technical field of pulsar identification. Background technique [0002] Pulsars are compact celestial bodies left behind by supernova explosions of late-evolved intermediate-mass stars, which provide the first indirect evidence for the existence of gravitational waves, and also offer the possibility of revealing extreme phenomena in neutron star astrophysics. Therefore, pulsar hunting is a prerequisite for gravitational wave and astrophysics research. [0003] Pulsar identification is an important step in the pulsar search process. Since the first pulsar was discovered in 1967, the identification of pulsars has undergone various methods: from simple identification of candidates based on pulse profiles and signal-to-noise ratios, to graphical tool-assisted and web-based candidate screening systems, And in recent years, candidate sorting al...

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): G06K9/62G06K9/00
CPCG06F2218/08G06F18/214
Inventor 尚振宏谢柳陈万敏
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap