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

SPEC-Net network architecture for multi-star spectrum automatic identification and identification method

A technology of automatic identification and network architecture, applied in neural architecture, character and pattern recognition, biological neural network models, etc., can solve problems such as the inability to form category attributes and representation of sample differences, difficulty in data mining, etc., and achieve good generalization Effects of generativeness, guaranteed robustness, and stability

Active Publication Date: 2022-05-13
TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it cannot form a representation with category attributes and expression sample differences. The lack of representation of these characteristics will cause difficulties for subsequent data mining.

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
  • SPEC-Net network architecture for multi-star spectrum automatic identification and identification method
  • SPEC-Net network architecture for multi-star spectrum automatic identification and identification method
  • SPEC-Net network architecture for multi-star spectrum automatic identification and identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer, the present invention will be further described in detail in combination with the embodiments and accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. The technical solutions of the present invention will be described in detail below in conjunction with the embodiments and accompanying drawings, but the scope of protection is not limited thereto.

[0056] The present invention comprises a kind of oriented multi-star spectrum automatic identification method, and specific method is (as figure 1 shown):

[0057] 1. The low-dimensional representation set Z of the spectrum is sampled based on the Gaussian distribution N ={z 1 ,z 2 ,...,z i |z i ~N(μ,σ), i=n} and the corresponding category auxiliary information Z C ={z ...

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 SPEC-Net network architecture for multi-star spectrum automatic identification and an identification method. Belongs to the technical field of celestial body spectral data analysis and processing. The network architecture comprises a multi-star spectrum generation calculation model, a multi-star spectrum discrimination calculation model and a multi-star spectrum mapping calculation model. According to the method, feature extraction is carried out for different radial speeds of spectral lines of a multi-star system, multi-star spectral low-dimension representation with intra-class high cohesion and inter-class low coupling characteristics is obtained through an adversarial learning mechanism, and then automatic recognition is carried out on the representation; the SPEC-Net has good generalization generation performance; due to the existence of the multi-star spectrum mapping calculation model, the robustness and the stability of feature mapping are guaranteed; and an end-to-end solution for multi-star spectrum automatic identification is provided.

Description

technical field [0001] The invention belongs to the technical field of analysis and processing of celestial body spectrum data, and in particular relates to a SPEC-Net network framework for multi-star spectrum automatic recognition and a multi-star spectrum automatic recognition method. Background technique [0002] LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope), as the astronomical telescope with the highest stellar spectrum acquisition rate in the world, has successfully acquired 17 million celestial object spectra. In our galaxy, about half of the stars are in binary Among the first-order, third-order or higher-order systems, multiple star systems play an important role in astrophysics, especially binary star systems play a vital role. Combining spectral and photometric information allows the study of characterization of multiple star systems such as orbital parameters. How to complete the identification of multi-star spectra from such a large amount ...

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): G06K9/00G06N3/04
CPCG06N3/045G06F2218/22G06F2218/08G06F2218/12
Inventor 蔡江辉郑爱宇杨海峰赵旭俊
Owner TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY
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