StudyontheClassificationofLAMOSTStellarSpectraBasedonDeepBeliefNetwork

›› 2019, Vol. 4 ›› Issue (6): 10-14.

StudyontheClassificationofLAMOSTStellarSpectraBasedonDeepBeliefNetwork

（1.SchoolofMathematicsandComputerScience,YunnanMinzuUniversity,Kunming650500,China;2.KeyLaboratoryofthe StructureandEvolutionofCelestialObjects,ChineseAcademyofSciences,Kunming650011,China）

Received:2019-01-15 Online:2019-06-15 Published:2019-06-15

Abstract

Abstract: Stellarspectralclassificationisanimportantmethodofspectralanalysis,anditisanimportantpartofcelestialdata mining.Inaccordancewiththeselectedspectraldataof33000F,GandKtypestarsfromLAMOST（theLargeSkyAreaMulti-Object FiberSpectroscopicTelescope）DataRelease5（DR5）,amethodbasedonthedeepbeliefnetworkforclassificationwasadopted.The deepbeliefnetworkmodelisestablishedbyhierarchicalfeaturelearningofstellarspectraldataduringtraining,andfinally,thestellar spectralclassificationtestofthismodelshowsthattheclassificationaccuracyofthethreestarsF,GandKare0.93,0.90and0.98 respectively,whichverifiesthecorrectnessofthemodelanditshighclassificationaccuracyrateandisofgreatsignificanceforthe processingofmassivecelestialspectraldata.

Key words: spectralclassification, featurelearning, deeplearning, deepbeliefnetwork

CLC Number:

TN911.74

ZhangJingmin1,XuTingting1,DuLiting1,ZhouWeihong1,2* . StudyontheClassificationofLAMOSTStellarSpectraBasedonDeepBeliefNetwork[J]. , 2019, 4(6): 10-14.

References

〔1〕杨海峰.天体光谱数据挖掘与分析〔M〕 .北京：电子工业出版社，2016： 2-14. 〔2〕RODRIGUEZA，ARCAYB，DAFONTEC，etal.Automat? edknowledge-basedanalysisandclassificationofstellar spectrausingfuzzyreasoning〔J〕.ExpertSystemswithAp? plications，2004，27（2）：237-244. 〔3〕覃冬梅，胡占义，赵永恒.一种基于主分量分析的恒星光谱快速分类法〔J〕 . 光谱学与光谱分析，2003，23（1）： 182-186. 〔4〕LIUZT，QIUKM.Amethodforauto-recognizingthestars based on spectral feature〔J〕. Spectroscopy & Spectral Analysis，2010， 30（1）：274-277. 〔5〕PANJC，WANGJ，JIANGB，etal.AMethodofStellar Spectral Classification Based on Map/Reduce Distributed Computing〔J〕.Spectroscopy&SpectralAnalysis，2016，36 （8）：2651-2654. 〔6〕艾丽雅.天体光谱的分类算法研究〔D〕 .鞍山：辽宁科技大学，2016. 〔7〕刘蓉，乔学军，张健楠，等.基于非参数回归与Adaboost 的恒星光谱自动分类方法〔J〕 . 光谱学与光谱分析， 2017， 37（5）：1553-1557. 〔8〕张静，刘忠宝，宋文爱，等.基于多类支持向量机的恒星光谱分类方法〔J〕 . 光谱学与光谱分析，2018，38（7）： 2307-2310. 〔9〕ZHONGJ，LEPINES，HOUJ，etal.Automatedidentifica? tionof2612late-kandMdwarfsintheLAMOSTcommis? sioningdatausingtheclassificationtemplatefits〔J〕.Astro? nomicalJournal，2015，150（2）：928-932. 〔10〕LIUC，CUIWY，ZHANGB，etal.Spectralclassification ofstarsbasedonLAMOSTspectra〔J〕.ResearchinAs? tronomy&Astrophysics，2015， 15（8）：1137-1153. 〔11〕李玉鑑，张婷，等. 深度学习导论及案例分析〔M〕 . 北京：机械工业出版社，2016： 38-63. 〔12〕WANGK，GUOP，LUOAL.Anewautomatedspectral featureextractionmethodanditsapplicationinspectral classificationanddefectivespectrarecovery〔J〕.Monthly NoticesoftheRoyalAstronomicalSociety，2017，465（4）： 4311-4324.