|
|
|
|
|
|
Besvm: A-Type Star Spectral Subtype Classification Algorithm Based on Transformer Feature Extraction |
LI Shuang-chuan, TU Liang-ping*, LI Xin, WANG Li-li |
School of Science,University of Science and Technology Liaoning,Anshan 114051,China
|
|
|
Abstract Stellar spectrum classification is one of the important tasks of stellar spectrum analysis. Chinese large-scale survey project LAMOST can obtain massive stellar spectral data. In order to efficiently classify massive stellar spectral data, especially stellar spectral subtype data, we need to study fast and effective stellar spectral automatic classification algorithms. This paper proposes a hybrid deep learning algorithm based on Transformer feature extraction, Bert+svm (abbreviated as Besvm), to classify the spectral subtypes of type A stars automatically. The algorithm takes 26 line indices of the spectrum of A-type stars as input features and uses the Bert model to perform a deeper learning of the 26 line indices. By learning the internal correlation of the 26 line indices, it extracts the spectrum more conducive to the A-type stars classification characteristics. The extracted new features are input into the classifier algorithm Support Vector Machine (SVM for short), and then the three subtypes A1, A2, and A3 of the A-type star spectrum are automatically classified. Previously, the SVM algorithm has been applied in the stellar spectrum classification task, and some derivative SVM algorithms also have a higher classification accuracy rate in the stellar spectrum classification task. Compared with the SVM algorithm previously applied to the stellar spectral classification task, our hybrid deep learning algorithm is less affected by the signal-to-noise ratio of the data, and the low-signal-to-noise ratio data can also have a higher classification accuracy. The amount of data used is relatively small. This paper verifies the effectiveness and superiority of the algorithm through five sets of experiments: Experiment 1 is used to compare and select excellent kernel functions, and through the matching experiment of spectral data, the radial basis kernel function RBF is finally selected; Experiment 2 compares the performance indicators of the Besvm algorithm with the other four traditional excellent algorithms verify the superiority of the Besvm algorithm; Experiment 3 is used to test the stability of the Besvm algorithm; Experiment 4 analyzes the influence of the amount of data on the Besvm algorithm; Experiment 5 analyzes the influence of different signal-to-noise ratios data on the classification accuracy of Besvm algorithm. The analysis of comprehensive experimental results shows that the hybrid deep learning algorithm Besvm proposed in this paper can still maintain a high classification accuracy rate on a small-scale data set with a low signal-to-noise ratio. The overall classification error rate of Besvm is below 0.01, which is much lower than the error rate of the classic traditional machine learning algorithm LDA algorithm, Bp neural network algorithm, SVM algorithm and Xgboost algorithm. The classification accuracy is too limited by the number of hidden neurons.
|
Received: 2022-02-26
Accepted: 2022-06-04
|
|
Corresponding Authors:
TU Liang-ping
E-mail: tlp_kd@163.com
|
|
[1] Lu Y K,Qiu B,Xiang G J,et al. International Conference on Electrical, Automation and Mechanical Engineering,2020.
[2] Zhang J M,Ma C Y,Wang L,et al. Chinese Astronomy and Astrophysics,2020, 44(3): 334.
[3] Li X R,Lin Y T,Qiu K B,et al. Research in Astronomy and Astrophysics,2019, 19(8): 56.
[4] Kheirdastan S,Bazarghan M. Astrophysics and Space Science,2016, 361(9): 304.
[5] Du L T,Hong L H,Yang L T,et al. Chinese Astronomy and Astrophysics,2021, 45(3): 352.
[6] Liu W,Zhu M,Dai C,et al. Monthly Notices of the Royal Astronomical Society, 2019, 483(4): 4774.
[7] Wang K,Guo P,Luo A L. Monthly Notices of the Royal Astronomical Society, 2017, 465(4): 4311.
[8] Du C D,Luo A L,Yang H F. New Astronomy,2017, 51: 51.
[9] Sharma K,Kembhavi A,Kembhavi A,et al. Monthly Notices of the Royal Astronomical Society, 2020, 491(2): 2280.
[10] Vaswani A,Shazeer N, et al. Conference on Neural Information Processing Systems,2017.
[11] ZHANG Xiao,LUO A-li(张 枭,罗阿理). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2019,39(10): 3292.
|
[1] |
XIE Peng, WANG Zheng-hai*, XIAO Bei, CAO Hai-ling, HUANG Yi, SU Wen-lin. Hyperspectral Quantitative Inversion of Soil Selenium Content Based on sCARS-PSO-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3599-3606. |
[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] |
JIN Cheng-liang1, WANG Yong-jun2*, HUANG He2, LIU Jun-min3. Application of High-Dimensional Infrared Spectral Data Preprocessing in the Origin Identification of Traditional Chinese Medicinal Materials[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2238-2245. |
[4] |
WU Chao1, QIU Bo1*, PAN Zhi-ren1, LI Xiao-tong1, WANG Lin-qian1, CAO Guan-long1, KONG Xiao2. Application of Spectral and Metering Data Fusion Algorithm in Variable Star Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1869-1874. |
[5] |
WU Xue1, 2, FENG Wei-wei2, 3, 4*, CAI Zong-qi2, 3, WANG Qing2, 3. Study on Rapid Recognition of Microplastics Based on Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(11): 3501-3506. |
[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] |
CHEN Jin-hao, JIANG Da-peng, ZHANG Yi-zhuo*, WANG Ke-qi*. Research on Data Migration Modeling Method for Bending Strength of
Solid Wood Based on SWCSS-GFK-SVM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1471-1477. |
[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] |
ZHOU Peng, WANG Wei-chao, YANG Wei*, JI Rong-hua, LI Min-zan. Effect of Soil Particle Size on Prediction of Soil Total Nitrogen Using Discrete Wavelength NIR Spectral Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(12): 3682-3687. |
[10] |
. Study on Rapid Spectral Reappearing and Hyperspectral Classification of Invisible Writing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3524-3531. |
[11] |
HUANG Han1, CHEN Hong-yan2*, LI Xiao-lu1, LIU Jia-hao1, ZHAO Yong-jia2, CHEN Liang3. Calculation and Study of Methane Absorption Coefficient at Variable Pressure and Temperature Under 3 016.49 cm-1 Wave Number[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(08): 2462-2468. |
[12] |
ZOU Jin-ping1, ZHANG Shuai2, DONG Wen-tao2, ZHANG Hai-liang2*. Application of Hyperspectral Image to Detect the Content of Total Nitrogen in Fish Meat Volatile Base[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(08): 2586-2590. |
[13] |
LI Wen-xin1, CHEN Guang-hui1, 3, ZENG Qing-dong1, 2*, YUAN Meng-tian1, 3, HE Wu-guang1, JIANG Ze-fang1, LIU Yang1, NIE Chang-jiang1, YU Hua-qing1, GUO Lian-bo2. Rapid Classification of Steel by a Mobile Laser-Induced Breakdown Spectroscopy Based on Optical Fiber Delivering Laser Energy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(08): 2638-2643. |
[14] |
CHEN Hua-zhou1,2, XU Li-li3, QIAO Han-li1,2, HONG Shao-yong4*. Latent Variable Machine Learning Methods Applied for NIR Quantitative Analysis of Coffee[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(05): 1441-1445. |
[15] |
MA Yang, ZHANG Ji-fu, CAI Jiang-hui, YANG Hai-feng, ZHAO Xu-jun*. Parallel Extraction and Analysis of Abnormal Features of QSO Spectra Based on Sparse Subspace[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(04): 1086-1091. |
|
|
|
|