中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Classification of large-scale stellar spectra based on deep convolutional neural network

文献类型:期刊论文

作者Liu, W.2; Zhu, M.2; Dai, C.2; He, D. Y.1; Yao, Jiawen4; Tian, H. F.2; Wang, B. Y.2; Wu, K.2; Zhan, Y.2; Chen, B. -Q.3
刊名MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
出版日期2019-03-01
卷号483期号:4页码:4774-4783
关键词methods: data analysis methods: statistical techniques: spectroscopic astronomical data bases: miscellaneous stars: statistics
ISSN号0035-8711
DOI10.1093/mnras/sty3020
英文摘要Classification of stellar spectra from voluminous spectra is a very important and challenging task. In order to better classify stellar spectra, inspired by the principle of deep convolutional neural network (CNN), we propose a supervised algorithm for stellar spectra classification based on 1D stellar spectra convolutional neural network (1D SSCNN). In 1D SSCNN, we modify the traditional 2D convolutional neural network into 1 D network to adapt to the spectral classification. On the basis of using convolution algorithm, the spectral features are extracted and used for classification. We first use the stellar spectra data to train a ID SSCNN to obtain a well-trained model, and then we apply the well-trained model to classify the unknown spectra. To evaluate the performance of the proposed algorithms, we apply ID SSCNN to classify three spectral types: F-type spectra, G-type spectra, and K-type spectra and 10 subclasses of K-type spectra: A0-type, A5-type, F0-type, F5-type, G0-type, G5-type, K0-type, K5-type, M0-type, and M5-type spectra from Sloan Digital Sky Survey (SDSS). Our 1D SSCNN algorithm obtain higher classification accuracy compared with support vector machine (SVM), random forest (RF), and artificial neural network (ANN).
WOS关键词DIGITAL SKY SURVEY ; FEATURE-SELECTION ; OBJECT DETECTION ; GAIA ; RECOGNITION
资助项目National Natural Science Foundation of China[41272359] ; Ministry of Land and Resources for the Public Welfare Industry Research Projects[201511079-02]
WOS研究方向Astronomy & Astrophysics
语种英语
WOS记录号WOS:000462281900037
出版者OXFORD UNIV PRESS
资助机构National Natural Science Foundation of China ; National Natural Science Foundation of China ; Ministry of Land and Resources for the Public Welfare Industry Research Projects ; Ministry of Land and Resources for the Public Welfare Industry Research Projects ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; Ministry of Land and Resources for the Public Welfare Industry Research Projects ; Ministry of Land and Resources for the Public Welfare Industry Research Projects ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; Ministry of Land and Resources for the Public Welfare Industry Research Projects ; Ministry of Land and Resources for the Public Welfare Industry Research Projects ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; Ministry of Land and Resources for the Public Welfare Industry Research Projects ; Ministry of Land and Resources for the Public Welfare Industry Research Projects
源URL[http://ir.bao.ac.cn/handle/114a11/25344]  
专题中国科学院国家天文台
通讯作者Liu, W.; Yu, X. C.
作者单位1.Jinan Informat Engn Sch, Network Engn Teaching & Res Grp, 316 Chaoshan Wangsheren, Jinan 250101, Shandong, Peoples R China
2.Beijing Normal Univ, Coll Informat Sci & Technol, 19 Waida Jie Xinjie Kou, Beijing 100875, Peoples R China
3.Yunnan Univ, South Western Inst Astron Res, Dongwaihuan South Rd, Kunming 650500, Yunnan, Peoples R China
4.Beijing Normal Univ, Dept Astron, 19 Waida Jie Xinjie Kou, Beijing 100875, Peoples R China
5.Chinese Acad Sci, Natl Astron Observ, 20A Datun Rd, Beijing 100012, Peoples R China
推荐引用方式
GB/T 7714
Liu, W.,Zhu, M.,Dai, C.,et al. Classification of large-scale stellar spectra based on deep convolutional neural network[J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY,2019,483(4):4774-4783.
APA Liu, W..,Zhu, M..,Dai, C..,He, D. Y..,Yao, Jiawen.,...&Yu, X. C..(2019).Classification of large-scale stellar spectra based on deep convolutional neural network.MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY,483(4),4774-4783.
MLA Liu, W.,et al."Classification of large-scale stellar spectra based on deep convolutional neural network".MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 483.4(2019):4774-4783.

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。