NAOC Open IR  > 光学天文研究部
A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery
Wang, Ke1; Guo, Ping1,2; Luo, A-Li3
2017-03-01
发表期刊MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
卷号465期号:4页码:4311-4324
摘要Spectral feature extraction is a crucial procedure in automated spectral analysis. This procedure starts from the spectral data and produces informative and non-redundant features, facilitating the subsequent automated processing and analysis with machine-learning and data-mining techniques. In this paper, we present a new automated feature extraction method for astronomical spectra, with application in spectral classification and defective spectra recovery. The basic idea of our approach is to train a deep neural network to extract features of spectra with different levels of abstraction in different layers. The deep neural network is trained with a fast layer-wise learning algorithm in an analytical way without any iterative optimization procedure. We evaluate the performance of the proposed scheme on real-world spectral data. The results demonstrate that our method is superior regarding its comprehensive performance, and the computational cost is significantly lower than that for other methods. The proposed method can be regarded as a new valid alternative general-purpose feature extraction method for various tasks in spectral data analysis.
文章类型Article
关键词Methods: Data Analysis Methods: Numerical Methods: Statistical Techniques: Spectroscopic
WOS标题词Science & Technology ; Physical Sciences
资助者National Natural Science Foundation of China(61375045) ; National Natural Science Foundation of China(61375045) ; Beijing Natural Science Foundation(4142030) ; Beijing Natural Science Foundation(4142030) ; National Natural Science Foundation of China (NSFC)(U1531242) ; National Natural Science Foundation of China (NSFC)(U1531242) ; Chinese Academy of Sciences (CAS)(U1531242) ; Chinese Academy of Sciences (CAS)(U1531242) ; National Natural Science Foundation of China(61375045) ; National Natural Science Foundation of China(61375045) ; Beijing Natural Science Foundation(4142030) ; Beijing Natural Science Foundation(4142030) ; National Natural Science Foundation of China (NSFC)(U1531242) ; National Natural Science Foundation of China (NSFC)(U1531242) ; Chinese Academy of Sciences (CAS)(U1531242) ; Chinese Academy of Sciences (CAS)(U1531242)
DOI10.1093/mnras/stw2894
关键词[WOS]DEEP NEURAL-NETWORKS ; DIGITAL SKY SURVEY ; STELLAR SPECTRA ; 2-DIMENSIONAL CLASSIFICATION ; TELESCOPE LAMOST ; GALAXY ; DIMENSIONALITY ; ASTRONOMY
收录类别SCI
语种英语
资助者National Natural Science Foundation of China(61375045) ; National Natural Science Foundation of China(61375045) ; Beijing Natural Science Foundation(4142030) ; Beijing Natural Science Foundation(4142030) ; National Natural Science Foundation of China (NSFC)(U1531242) ; National Natural Science Foundation of China (NSFC)(U1531242) ; Chinese Academy of Sciences (CAS)(U1531242) ; Chinese Academy of Sciences (CAS)(U1531242) ; National Natural Science Foundation of China(61375045) ; National Natural Science Foundation of China(61375045) ; Beijing Natural Science Foundation(4142030) ; Beijing Natural Science Foundation(4142030) ; National Natural Science Foundation of China (NSFC)(U1531242) ; National Natural Science Foundation of China (NSFC)(U1531242) ; Chinese Academy of Sciences (CAS)(U1531242) ; Chinese Academy of Sciences (CAS)(U1531242)
WOS研究方向Astronomy & Astrophysics
WOS类目Astronomy & Astrophysics
WOS记录号WOS:000395170200040
引用统计
被引频次:4[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.bao.ac.cn/handle/114a11/8265
专题光学天文研究部
作者单位1.Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China
2.Beijing Normal Univ, Image Proc & Pattern Recognit Lab, Beijing 100875, Peoples R China
3.Chinese Acad Sci, Natl Astron Observ, Key Lab Optic Astron, Beijing 100012, Peoples R China
推荐引用方式
GB/T 7714
Wang, Ke,Guo, Ping,Luo, A-Li. A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery[J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY,2017,465(4):4311-4324.
APA Wang, Ke,Guo, Ping,&Luo, A-Li.(2017).A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery.MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY,465(4),4311-4324.
MLA Wang, Ke,et al."A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery".MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 465.4(2017):4311-4324.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Ke]的文章
[Guo, Ping]的文章
[Luo, A-Li]的文章
百度学术
百度学术中相似的文章
[Wang, Ke]的文章
[Guo, Ping]的文章
[Luo, A-Li]的文章
必应学术
必应学术中相似的文章
[Wang, Ke]的文章
[Guo, Ping]的文章
[Luo, A-Li]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。