|
|
|
|
|
|
Fast Classification Method of Star Spectra Data Based on Convolutional Neural Network |
WANG Nan-nan1, QIU Bo1*, MA Jie1*, SHI Chao-jun1, SONG Tao1, GUO Ping2* |
1. School of Electronics and Information Engineering, Hebei University of Technology, Tianjin 300401, China
2. School of Systems Science, Beijing Normal University, Beijing 100875, China |
|
|
Abstract Classification of stellar spectral data is one of the most basic tasks in automatic recognition of celestial spectra. The study of spectral classification can provide clues to the evolution of stars. With the development of science and technology, astronomical data are also moving towards the era of big data. The number of stars that need to be processed is increasing. How to classify them automatically and accurately has become one of the difficult problems that astronomers have to solve. At present, there are few methods to solve the problem of Star automatic classification. In this paper, a convolution neural network based method is used to classify star spectral MK system. The network is composed of data input layer, four convolution layers, four pooling layers, full connection layer and output layer. Compared with traditional network, it has the advantages of local perception and parameter sharing. In this paper, a simple and efficient convolution neural network with four convolution layers is constructed by Tensorflow in Python 3.5 environment. Dropout is applied to the full connection layer to prevent over fitting. Dropout’s basic idea: When the network model is trained, some neural network nodes are discarded in a certain proportion, so that they do not play a role temporarily. Dropout can be understood as a very efficient neural network model averaging method, because it does not depend on some local features, it can make the network model more robust. The one-dimensional star spectrogram used in the experiment was downloaded from the LAMOST DR3 database. First, the spectrum was intercepted by pretreatment. After uniform sampling, it was initialized by min-max standardization method. The experiment consists of two parts. The first part classifies the spectrum according to the star spectrum MK system. Each training sample contains 1 000 spectral data and 400 spectral data. First, the CNN network is trained by training samples, and then 3 000 iterations are carried out. Then, the test samples are divided into several parts by the trained network. The second part is the classification of adjacent two types of star spectra, in which the O-type star data set sample is 250 spectra, and the rest are 4 000 spectra. The data are divided into five parts, one of which is selected as test set each time, the rest as training set, using 5 fold crossover. The accuracy of the model was calculated by the verification method, and the BP neural network was used for comparative experiments. The indicators to evaluate the network model include accuracy rate P, recall rate R, F-score and accuracy rate A. The experimental results show that the classification accuracy of the six types of stars is more than 95%. When classifying the adjacent types of stars, the classification results are not ideal because of the small sample size of O type stars. The classification accuracy of the other types of stars is higher than 98%. All the above results prove that CNN algorithm can classify the stars. The classification of stellar spectra is well solved.
|
Received: 2018-09-05
Accepted: 2019-01-19
|
|
Corresponding Authors:
QIU Bo, MA Jie, GUO Ping
E-mail: qiubo@hebut.edu.cn;jma@hebut.edu.cn;pguo@bnu.edu.cn
|
|
[1] Li Xiangru, Pan Ruyang, Duan Fuqing. Research in Astronomy and Astrophysics, 2017, 17(4): 36.
[2] Morgan W W. Chicago ILL the University of Chicago Press, 1943, 1: 3.
[3] Schierscher F, Paunzen E. Astronomische Nachrichten, 2011, 332(6): 597.
[4] Singh H P, Gulati R K, Gupta R. Monthly Notices of the Royal Astronomical Society, 1998, 295(2): 312.
[5] Daniel S F, Connolly A, Schneider J, et al. Astronomical Journal, 2011, 142(6): 203.
[6] Liu C, Cui W Y, Zhang B, et al. Research in Astronomy and Astrophysics, 2015, 15(8): 1137.
[7] XUE Jian-qiao, LI Qi-bin, ZHAO Yong-heng(薛建桥, 李启斌, 赵永恒). Acta Astrophysica Sinica(天体物理学报), 2000, 20(4): 437.
[8] ZHOU Jun-yu, ZHAO Yan-ming(周俊宇, 赵艳明). Computer Engineering and Applications(计算机工程与应用), 2017, 53(13): 34.
[9] LI Jun-feng, WANG Yue-le, HU Sheng(李俊峰, 汪月乐, 胡 升). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(10): 3261.
[10] Hinton G E, Srivastava N, Krizhevsky A, et al. arXiv preprint arXiv: 2012,1207.0580.
[11] Hinton G E, Srivastava N, Krizhevsky A, et al. Computer Science, 2012, 3(4): 212. |
[1] |
LI He1, WANG Yu2, FAN Kai2, MAO Yi-lin2, DING Shi-bo3, SONG Da-peng3, WANG Meng-qi3, DING Zhao-tang1*. Evaluation of Freezing Injury Degree of Tea Plant Based on Deep
Learning, Wavelet Transform and Visible Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 234-240. |
[2] |
FAN Ya-wen, LIU Yan-ping*, QIU Bo, JIANG Xia, WANG Lin-qian, WANG Kun. Research on Spectral Classification of Stellar Subtypes Based on
SSTransformer[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2523-2528. |
[3] |
CAI Hai-hui1, ZHOU Ling2, SHI Zhou3, JI Wen-jun4, LUO De-fang1, PENG Jie1, FENG Chun-hui5*. Hyperspectral Inversion of Soil Organic Matter in Jujube Orchard
in Southern Xinjiang Using CARS-BPNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2568-2573. |
[4] |
JIANG Xia*, QIU Bo, WANG Lin-qian, GUO Xiao-yu. Automatic Classification Method of Star Spectra Based on
Semi-Supervised Mode[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1875-1880. |
[5] |
GUI Jiang-sheng1, HE Jie1, FU Xia-ping2. Hyperspectral Detection of Soybean Heart-Eating Insect Pests Based on Image Retrieval[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2931-2934. |
[6] |
LU Ya-kun1, QIU Bo1*, LUO A-li2, GUO Xiao-yu1, WANG Lin-qian1, CAO Guan-long1, BAI Zhong-rui2, CHEN Jian-jun2. Classification of 2D Stellar Spectra Based on FFCNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1881-1885. |
[7] |
TIAN Qing-lin1, GUO Bang-jie1, YE Fa-wang1, LI Yao2, LIU Peng-fei1, CHEN Xue-jiao1. Mineral Spectra Classification Based on One-Dimensional Dilated Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 873-877. |
[8] |
LIU Zhong-bao1, WANG Jie2*. Research on the Improvement of Spectra Classification Performance With the High-Performance Hybrid Deep Learning Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 699-703. |
[9] |
TANG Yong-sheng, CHEN Zheng-guang*. Soil pH Prediction Based on Convolution Neural Network and Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(03): 892-897. |
[10] |
SHI Chao-jun1, QIU Bo1*, ZHOU Ya-tong1, DUAN Fu-qing2*. Automatic Classification Method of Star Spectra Data Based on Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(04): 1312-1316. |
[11] |
ZHANG Jing, LIU Zhong-bao*, SONG Wen-ai, FU Li-zhen, ZHANG Yong-lai. Stellar Spectra Classification Method Based on Multi-Class Support Vector Machine[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(07): 2307-2310. |
[12] |
WANG Wen-yu, GUO Ge-lin, JIANG Bin, WANG Li* . Discovering WDMS with Automatic Classification System Based on RBF Neural Network [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(10): 3360-3363. |
[13] |
LIU Zhong-bao1, GAO Yan-yun2, WANG Jian-zhen3 . Automatic Classification Method of Star Spectra Data Based on Manifold Fuzzy Twin Support Vector Machine [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(01): 263-266. |
[14] |
LIU Zhong-bao1, WANG Zhao-ba2, ZHAO Wen-juan3 . Automatic Classification Method of Star Spectra Data Based on Manifold-Based Discriminant Anaysis and Support Vector Machine[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(01): 263-266. |
[15] |
CAI Jiang-hui,ZHANG Ji-fu*,ZHAO Xu-jun. Research on Two-Stage Fuzzy Clustering Method for Spectrum Data Based on PSO[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(04): 1137-1141. |
|
|
|
|