中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 国家天文台
  3. 中国科学院国家天文台
Celestial Spectra Classification Network Based on Residual and Attention Mechanisms

文献类型：期刊论文

作者Zou, Zhiqiang2,3; Zhu, Tiancheng2; Xu, Lingzhe4; Luo, A-Li1,5
刊名PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC
出版日期2020-04-01
卷号132期号:1010页码:10
关键词miscellaneous methods data analysis methods statistical stars statistics techniques spectroscopic
ISSN号0004-6280
DOI10.1088/1538-3873/ab7548
英文摘要In astronomy, it is important to categorize celestial bodies by classifying collected spectral data. The currently available methods present unsatisfactory spectral classification accuracy and incur high computing costs. We propose a celestial spectral classification network based on a residual and attention based convolutional network (RAC-Net). In this network, convolution operations can extract shallow and deep features of spectral data and classify them without relying on redshifts. The residual mechanism can augment the depth of the network and make training more efficient. The attention mechanism allows the network to focus on specific bands and specific features, rendering the learning more targeted. To evaluate the performance of the RAC-Net, we conducted a comparative test using a celestial spectral data set that consisted of 70,000 spectra collected by the large sky area multi-object fiber spectroscopic telescope. The experimental results showed that the classification accuracy of our network was up to 98.92%. Compared with the leading one-dimensional, convolutional neural network 1D SSCNN model, the RAC-Net presented higher classification accuracy and fewer network parameters.
WOS关键词STELLAR SPECTRA
资助项目National Natural Science Foundation of P. R. China[41601449] ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University[2016LSDMIS07] ; National Natural Science Foundation of China[U1931209] ; National Natural Science Foundation of China[U1931207] ; Chinese Academy of Sciences[U1931209] ; Chinese Academy of Sciences[U1931207] ; National Development and Reform Commission
WOS研究方向Astronomy & Astrophysics
语种英语
WOS记录号WOS:000521365300001
出版者IOP PUBLISHING LTD
资助机构National Natural Science Foundation of P. R. China ; National Natural Science Foundation of P. R. China ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences ; Chinese Academy of Sciences ; National Development and Reform Commission ; National Development and Reform Commission ; National Natural Science Foundation of P. R. China ; National Natural Science Foundation of P. R. China ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences ; Chinese Academy of Sciences ; National Development and Reform Commission ; National Development and Reform Commission ; National Natural Science Foundation of P. R. China ; National Natural Science Foundation of P. R. China ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences ; Chinese Academy of Sciences ; National Development and Reform Commission ; National Development and Reform Commission ; National Natural Science Foundation of P. R. China ; National Natural Science Foundation of P. R. China ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University ; Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences ; Chinese Academy of Sciences ; National Development and Reform Commission ; National Development and Reform Commission
源URL[http://ir.bao.ac.cn/handle/114a11/55572]  
专题中国科学院国家天文台
通讯作者Zou, Zhiqiang
作者单位1.Chinese Acad Sci, Natl Astron Observ, Key Lab Opt Astron, Beijing 100101, Peoples R China
2.Nanjing Univ Posts & Telecommun, Coll Comp, Nanjing 210023, Jiangsu, Peoples R China
3.Jiangsu Key Lab Big Data Secur & Intelligent Proc, Nanjing 210023, Jiangsu, Peoples R China
4.Chinese Acad Sci, Natl Astron Observ, Nanjing Inst Astron Opt & Technol, Dept Telescopes New Technol, Nanjing 210042, Jiangsu, Peoples R China
5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Zou, Zhiqiang,Zhu, Tiancheng,Xu, Lingzhe,et al. Celestial Spectra Classification Network Based on Residual and Attention Mechanisms[J]. PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC,2020,132(1010):10.
APA Zou, Zhiqiang,Zhu, Tiancheng,Xu, Lingzhe,&Luo, A-Li.(2020).Celestial Spectra Classification Network Based on Residual and Attention Mechanisms.PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC,132(1010),10.
MLA Zou, Zhiqiang,et al."Celestial Spectra Classification Network Based on Residual and Attention Mechanisms".PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC 132.1010(2020):10.

入库方式： OAI收割

来源：国家天文台

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。