An Automated Stellar Spectra Classification System Based on Non-Parameter Regression and Nearest Neighbor Method
ZHANG Jian-nan1, ZHAO Yong-heng1, LIU Rong2
1. National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012, China 2. Base Department, Beijing Institute of Clothing Technology, Beijing 100029, China
Abstract：The automated classification and recognition of stellar spectra is an important research for the spectra processing system of modern telescope survey project. For the spectra without flux calibration, the authors present an automated stellar spectra classification system to achieve two goals: one is the spectral class and spectral subclass classification, and the other is luminosity type recognition. The system is composed of three units: (1) continuum normalization method based on wavelet technique; (2) non-parameter regression method for spectral class and spectral subclass classification; (3) χ２ method based on nearest neighbor for luminosity type determination. The experiments on low-resolution spectra show that the system achieves 3.2 spectral subclass precision for spectral and spectral subclass classification, 60% correct rate for luminosity recognition, and 78% rate for the luminosity recognition with error less than or equal to 1. The system is easy, rapid in training, and feasible for the automated spectra classification.
[1] HUANG Run-qian(黄润乾). Stellar Physics(恒星物理). Beijing: Science Press(北京：科学出版社)，1998. 8. [2] Kurtz M J. Progress in Automation Techiques for MK Classification. In Garrison R F, Editor. Proceedings of the Workshop in Honour of Morgan W W, Keenan P C. David Dunlap Observatory, Toronto, Canada, 1984. 136. [3] Lasala J. In Chris Corbally, Gray R O, Garrison R F Editor. The MK Process at 50 Years. A Powerful Tool for Astrophysical Insight. Astronomical Society of the Pacific Conference Series, Proceedings of a Workshop of the Vatican Observatory, Tucson Arizona, USA, September, 1993. 312. [4] Hippel T, Storrie-Lombardi L, Storrie-Lombardi M C, et al. Monthly Notices of the Royal Astronomical Society, 1994, 269: 97. [5] Gulati R K, Gupta R, Ran N K. Astronomy & Astrophysics, 1997, 322: 933. [6] Bailer-Jones C A L, Irwin M, Hippel T. Monthly Notices of the Royal Astronomical Society, 1998, 298: 361. [7] XUE Jianqiao, LI Qibin, ZHAO Yongheng. Chinese Astronomy and Astrophysics, 2001，25(1): 120. [8] Qin D M, Hu Z, Zhao Y. In: Shen J, Pankanti S, Wang S, eds. Object Detection, Classification, and Tracking Technologices. Proceedings of SPIE. Bellingham: SPIE, 2001, 4554: 268. [9] ZHANG Jian-nan, WU Fu-chao, LUO A-li, et al(张健楠，吴福朝，罗阿理，等). Acta Astronomica Sinica(天文学报)，2005, 46(4): 404. [10] Jacoby G H, Hunter D A, Christian C A. The Astrophysical Journal Supplement Series, 1984, 56: 257. [11] Pickles A J. Publications of the Astronomical Society of the Pacific, 1998, 110: 863. [12] Silva D R, Cornell M E. The Astrophysical Journal Supplement Series, 1992, 81: 865.
