|
|
|
|
|
|
Research on Spectral Classification of Stellar Subtypes Based on
SSTransformer |
FAN Ya-wen, LIU Yan-ping*, QIU Bo, JIANG Xia, WANG Lin-qian, WANG Kun |
Hebei University of Technology, Tianjin 300400, China
|
|
|
Abstract The classification of stars has always been a hot topic in recent astronomical research. The classification of stellar subtypes is significant for exploring stellar evolution and identifying rare celestial bodies. This paper designs the SSTransformer (Stellar Spectrum Transformer) classification model for the LAMOST spectral subtype classification problem. The model mainly comprises three parts, including the input module, the embedding module, and the SST encoding module. In the input module, the spectral data is processed into blocks, which are mapped to vectors through a linear projection layer. In the embedding module, in order to extract useful data features, the output of the linear projection layer is added to a learnable category embedding block. In order to preserve the position information, a position embedding block is added, and then these data feature vectors are sent to the SST encoding module. Finally, the data features are extracted in the SST coding module, and the stellar spectrum is classified using the multilayer perceptron combined with the new features. In this paper,the spectral data of type A, F, G, K, and M starsis all from the one-dimensional low-resolution spectra in LAMOST DR8, 35256 pieces of one-dimensional spectral data are used for training the SSTransformer model, and 8 815 pieces of one-dimensional spectral data are used for testing the SSTransformer model. In order to speed up the convergence of the model, Z-Score normalization is used for the data. Because this is a multi-classification problem, the experiment adopts five evaluation indicators: accuracy rate, precision rate, recall rate, F1-Score, and Kappa coefficient. The experimental results show that the SSTransformer model can effectively screen and classify one-dimensional stellar spectral data, and the classification accuracy reaches 98.36%, which is higher than the support vector machine (SVM) algorithm, eXtreme Gradient Boosting (XGBoost) algorithm, and convolutional neural networks (CNN).
|
Received: 2022-04-12
Accepted: 2022-08-11
|
|
Corresponding Authors:
LIU Yan-ping
E-mail: liu13312181255@163.com
|
|
[1] Hou Wen, Luo Ali, Li Yinbi, et al. The Astronomical Journal, 2020, 159(2): 43.
[2] Wang Jiangtao, Fu Jianning, Zong Weikai, et al. The Astrophysical Journal Supplement Series, 2020, 251(2): 27.
[3] Liu Zhongbao, Zhou Fangxiao, Qin Zhentao, et al. Astrophysics and Space Science, 2018, 363(7): 140.
[4] Yue Lili, Yi Zhenping, Pan Jingchang, et al. Optik, 2021, 225: 165535.
[5] JIANG Bin, ZHAO Zi-liang, WANG Shu-ting, et al(姜 斌,赵梓良,王淑婷,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(9): 2913.
[6] Wang K, Guo P, Luo A L. Monthly Notices of the Royal Astronomical Society, 2017, 465(4): 4311.
[7] Liu W, Zhu M, Dai C, et al. Monthly Notices of the Royal Astronomical Society, 2019, 483(4): 4774.
[8] DU Li-ting, HONG Li-hua, YANG Jin-tao, et al(杜利婷,洪丽华,杨锦涛,等). Acta Astronomica Sinica(天文学报), 2021, 62(1): 90.
[9] Lu Yakun, Qiu Bo, Luo Ali, et al. Monthly Notices of the Royal Astronomical Society, 2021, 507(3): 4095.
[10] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, et al. International Conference on Learning Representations, 2020.
[11] Nicolas Carion, Francisco Massa, Gabriel Synnaeve, et al. European Conference on Computer Vision, 2020: 213.
[12] Zheng Sixiao, Lu Jiachen, Zhao Hengshuang, et al. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 6877.
[13] Bu Yude, Chen Fuqiang, Pan Jingchang. New Astronomy, 2014, 28: 35.
[14] Chen T Q, Guestrin C. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 785.
|
[1] |
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. |
[2] |
OUYANG Ke-chen1, 2, XING Li2, WANG Zheng2, 3, FENG Xiao-juan2*, ZHANG Jin-tao2, REN Cheng1, YANG Xing-tuan1. Analysis and Suppression of Laser-Induced Error in Temperature
Measurement Based on Nitrogen-Vacancy Centers in Diamond[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 1242-1247. |
[3] |
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. |
[4] |
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. |
[5] |
WANG Tian-xiang1, 2, FAN Yu-feng1*, WANG Xiao-li1, LONG Qian1, WANG Chuan-jun1. Prediction of Stellar Spectrum Categories Based on Deep Residual Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(05): 1602-1606. |
[6] |
JIN Zhi1, MA Jian-feng2, FU Yue-jin1*. Research on the Distribution of Cell Wall Components and Porosity in Populous Nigra Tension Wood Fiber Based on Raman Imaging Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(03): 801-806. |
[7] |
ZHOU Si-han1,2, HU Xin-yu1,2, TANG Bin1,2,3*, ZHAO Ming-fu1,2, LI Feng-xiao1,2, WANG Ren-jie1,2, XIAO Qi-sen1,2, XIAO Yu1,2. Application Research of Normalization Algorithm Based on EWMA-PCA in Standardization of Water Quality Spectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(11): 3443-3450. |
[8] |
JIANG Bin, ZHAO Zi-liang, WANG Shu-ting, WEI Ji-yu, QU Mei-xia*. Decomposition and Classification of Stellar Spectra Based on t-SNE[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(09): 2913-2917. |
[9] |
WANG Nan-nan1, QIU Bo1*, MA Jie1*, SHI Chao-jun1, SONG Tao1, GUO Ping2*. Fast Classification Method of Star Spectra Data Based on Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(10): 3297-3301. |
[10] |
XUE Ren-zheng1, CHEN Shu-xin1*, HUANG Hong-ben2. Line Index of A-Type Stellar Astronomical Spectrum Predict Effective Temperature by Ridge Regression Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(08): 2624-2629. |
[11] |
LIU Zhong-bao1, 2, QIN Zhen-tao1, LUO Xue-gang1, ZHOU Fang-xiao1, ZHANG Jing1. Stellar Spectra Classification by Support Vector Machine with Spectral Distribution Properties[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(04): 1307-1311. |
[12] |
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. |
[13] |
LIU Zhong-bao1,2, LEI Yu-fei1, SONG Wen-ai2, ZHANG Jing2, WANG Jie3, TU Liang-ping4. Stellar Spectra Classification by Support Vector Machine with Unlabeled Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(03): 948-952. |
[14] |
LI Meng-meng, JIANG Jin-bao*, LIU Dong. Detection of Microleakage Point of Underground Natural Gas Using Hyperspectral Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(12): 3809-3814. |
[15] |
GENG Shi-ying, SUN Hua-lin, WANG Xiao-yan*, XIONG Qin-xue*, ZHANG Jing-lin. Relationships between Characteristics of Wheat Canopy and Leaf Spectral Reflectance and Yield under Different Nitrogen Treatments[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(11): 3534-3540. |
|
|
|
|