加入收藏  设为首页
 
Home | 中文  
   Home   |   About Journal   |   Editorial Board   |   Instruction   |   Rewarded   |   Indexed-in   |   Impect Factor   |   Subscriptions   |   Contacts Us
SPECTROSCOPY AND SPECTRAL ANALYSIS  2018, Vol. 38 Issue (02): 660-664    DOI: 10.3964/j.issn.1000-0593(2018)02-0660-05
|
Stellar Spectra Classification with Entropy-Based Learning Machine
LIU Zhong-bao1, REN Juan-juan2, SONG Wen-ai1*, ZHANG Jing1, KONG Xiao2, FU Li-zhen1
1. School of Software, North University of China, Taiyuan 030051, China
2. Key Laboratory of Optical Astronomy, National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012, China
Download: PDF (410 KB)  
Export: BibTeX | EndNote (RIS)      
Abstract  Data mining are widely used in the stellar spectra classification. In order to improve the efficiencies of traditional spectra classification methods, Entropy-based Learning Machine (ELM) was proposed in this paper. The entropy was used to describe the uncertainty of classification in ELM. In order to obtain the desired classification efficiencies, the classification uncertainty should be minimized, based on which, we can obtain the optimization problem of ELM. It can be verified that ELM performs well in the binary classification and in the rare spectra mining. Several comparative experiments on the 4 subclasses of K-type spectra, 3 subclasses of F-type spectra and 3 subclasses of G-type spectra from Sloan Digital Sky Survey (SDSS) verified that ELM performs better than kNN (k Nearest Neighbor) and SVM (Support Vector Machine) in dealing with the problem of stellar spectra classification on the SDSS datasets.
Key words:Data mining; Stellar spectra classification; Entropy; Sloan digital sky survey (SDSS)
Received: 2016-12-25     Accepted: 2017-06-01    
ZTFLH:  P144.1  
Corresponding Authors: SONG Wen-ai     E-mail: songwenai@nuc.edu.cn
Cite this article:   
URL:  
https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2018)02-0660-05     OR      https://www.gpxygpfx.com/EN/Y2018/V38/I02/660