An Automated Stellar Spectra Classification System Basing on Non-Parameter Regression and Adaboost
LIU Rong1, QIAO Xue-jun2*, ZHANG Jian-nan3, DUAN Fu-qing4
1. Base Department, Beijing Institute Of Fashion Technology, Beijing 100029, China
2. School of Science, Xi’an University of Architecture and Technology, Xi’an 710055, China
3. The National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012, China
4. College of Information Science and Technology, Beijing Normal University, Beijing 100875, China
Abstract:With the analysis of stellar spectra, the evolution and structure of the Milky Way galaxy is studied. Spectral classification is one of the basic tasks of stellar spectral analysis. In this paper, a method of MK classification based on non parametric regression and Adaboost for stellar spectra is proposed, and the stars are classified according to the luminosity type, spectral type as well as the spectral subtype. The spectral type of the stellar spectrum and its sub type represent the effective temperature of the star, while the luminosity type represents the luminous intensity of the star. In the same spectral type, the luminosity type reflects the variation of the shape details of the spectral line, so the classification of the photometric type must be based on the spectral type classification. The spectral type classification is transformed as a regression problem of class label, and the type and subtype of the stellar spectra are recognized with non parametric regression method. The luminosity type of the stellar spectra is recognized using Adaboost method which combines a group of K nearest neighbor classifiers. Adaboost generates a strong classifier with weighted combination of a group of weak classifiers to improve the recognition rate of the luminosity type. Experimental results validate the proposed method. The accuracy of spectral subtype recognition is up to 0.22, and the correct rate of the luminosity type classification is 84% above. Two KNN methods are compared with Adaboost method on luminosity recognition. The results show that the recognition rate can be greatly enhanced with the Adaboost method and using KNN.
[1] Li X R, Lu Y, Comte G, et. al. The Astrophysical Journal Supplement Series, 2015, 218(1): 3.
[2] Li X R, Wu Q M J, Luo A L, et al. The Astrophysical Journal, 2015, 790(2): 85.
[3] Kheirdastan S, Bazarghan M. Astrophysics and Space Science, 2016, 361(9):304.
[4] Liu C, Cui, W Y, Zhang B, et. al. Research in Astronomy and Astrophysics, 2015, 15(8):1137.
[5] Gray R O,Corbally C J. The Astronomical Journal, 2014, 147(4): 80.
[6] McGurk R C, Kimball A E, Ivezic . The Astronomical Journal, 2010, 139(3):1261.
[7] Daniel S, Connolly A, Schneider J, et al. The Astronomical Journal, 2011, 142(6):203.
[8] Yang T, Li X R. Monthly Notices of the Royal Astronomical Society, 2015, 452(1): 158.
[9] Lu Y, Li X R. Monthly Notices Royal Astronomical Society, 2015, 452(2): 1394.
[10] YU Shuang, LIU Guo-hai, XIA Rong-sheng, et al(于 霜, 刘国海, 夏荣盛, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(1): 51.
[11] Rakhlin A,Sridharan K. Computer Science, 2014, 35: 1232.
[12] Zhang Z,Xie X. International Conference on Computer Engineering and Technology, 2010, 1: 647.
[13] Jacoby G H, Hunter D A, Christian C A. The Astrophysical Journal Supplement Series, 1984, 56: 257.
[14] Silva D R, Cornell M E. The Astrophysical Journal Supplement Series, 1992, 81: 865.
[15] Pickles A J. Publications of the Astronomical Society of the Pacific, 1998, 110: 863.