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

A pulsar candidate recognition method based on artificial neural network integration

An artificial neural network and recognition method technology, applied in the field of pulsar candidate recognition, can solve problems such as low recognition rate, model overfitting, and slow decline of single training gradient, achieve good recognition effect, reduce computing cost, and solve The effect of model overfitting

Inactive Publication Date: 2019-01-25
KUNMING UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a pulsar candidate identification method based on artificial neural network integration, which is used to solve the problems of low recognition rate, slow decline of single training gradient, and model overfitting in the process of pulsar identification and detection. question

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 candidate recognition method based on artificial neural network integration
  • A pulsar candidate recognition method based on artificial neural network integration
  • A pulsar candidate recognition method based on artificial neural network integration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] Embodiment 1: as Figure 1-3 Shown, a kind of pulsar candidate identification method based on artificial neural network integration, the specific steps of the pulsar candidate identification method based on artificial neural network integration are as follows:

[0022] Step1. Obtain a data set containing real pulsars and non-pulsars, and calculate its data characteristics;

[0023] The data characteristics of the step Step1 are signal-to-noise ratio (S / N), pulse period, pulse profile width, time-domain pulse duration, frequency-domain pulse duration, ratio of pulse width to DM smearing time;

[0024] Specifically, the present invention uses a training set composed of 3,000 real pulsars and 90,000 non-pulsars publicly released by M14. And select the signal-to-noise ratio (S / N), pulse period, pulse profile width, time-domain pulse duration, frequency-domain pulse duration, ratio of pulse width to DM smearing time, these six parameter values ​​are used as pulsar character...

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 candidate recognition method based on artificial neural network integration, belonging to the pulsar identification technical field. The invention resamples the original training data set, divides the original training data set into a plurality of sub-training data sets, trains the corresponding neural network models by using each sub-training set, and finally integrates the network models trained by different training sets through a relative majority voting method to finally form a classifier for identifying pulsars. The invention has good recognition effectwhen identifying pulsars with weak signal strength, reduces the calculation cost caused by gradient descent in the iterative process of the neural network, identifies candidate pulsars through an artificial neural network ensemble method, and effectively solves the problem of over-fitting the model.

Description

technical field [0001] The invention relates to a pulsar candidate identification method based on artificial neural network integration, and belongs to the technical field of pulsar identification. Background technique [0002] A pulsar is a type of neutron star, which has a strong magnetic field and has the characteristics of stable and high-speed rotation. The discovery of pulsars is an important milestone in the development of astronomy in the last century. Pulsars have radio radiation. By detecting and receiving the periodic radio radiation signals emitted by pulsars, a series of continuous and stable pulse signals can be generated. Due to the extremely fast speed of pulsars and the very stable pulse signals, pulsars are used in astronomy field has a very wide range of applications. [0003] At present, there are many methods for identifying pulsar signals collected in the universe. The earlier methods include pulsar profile-based and signal-to-noise ratio screening me...

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): G06K9/62
CPCG06F18/214G06F18/24
Inventor 尚振宏陈万敏谢柳
Owner KUNMING UNIV OF SCI & 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