Stellar Spectra Classification with Entropy-Based Learning Machine
LIU Zhong-bao1, REN Juan-juan2, SONG Wen-ai1*, ZHANG Jing1, KONG Xiao2, FU Li-zhen1
1. School of Software, North University of China, Taiyuan 030051, China
2. Key Laboratory of Optical Astronomy, National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012, China
Abstract Data mining are widely used in the stellar spectra classification. In order to improve the efficiencies of traditional spectra classification methods, Entropy-based Learning Machine (ELM) was proposed in this paper. The entropy was used to describe the uncertainty of classification in ELM. In order to obtain the desired classification efficiencies, the classification uncertainty should be minimized, based on which, we can obtain the optimization problem of ELM. It can be verified that ELM performs well in the binary classification and in the rare spectra mining. Several comparative experiments on the 4 subclasses of K-type spectra, 3 subclasses of F-type spectra and 3 subclasses of G-type spectra from Sloan Digital Sky Survey (SDSS) verified that ELM performs better than kNN (k Nearest Neighbor) and SVM (Support Vector Machine) in dealing with the problem of stellar spectra classification on the SDSS datasets.
[1] Geobel J, Stutz J, Volk K, et al. A&A, 1989, 222(1-2): 5.
[2] Gulati R K, Gupta R, Gothoskar P. A&A, 1997, 322(3): 933.
[3] Stark P B, Herron M M, Matteson A. Applied Spectroscopy, 1993, 47(11): 1820.
[4] Mahdi B. Astrophysics and Space Science, 2012, 337(1): 93.
[5] Navarro S G, Corradi R L M, Mampaso A. A&A, 2012, 538(A76): 1.
[6] Li X R, Hu Z Y. International Journal of Computer Vision, 2010, 89(1):1.
[7] Qin Dongmei, Hu Zhanyi, Zhao Yongheng. Spectroscopy and Spectral Analysis, 2003, 23(1): 182.
[8] Liu Z T, Li X R, Wu F C, et al. Chinese Journal of Electronics, 2007, 35(1): 157.
[9] Xu Xin, Yang Jinfu, Wu Fuchao, et al. Spectroscopy and Spectral Analysis, 2006, 26(10): 1960.
[10] Yang J F, Wu C F, Luo A L, et al. Pattern Recognition and Artificial Intelligence, 2006, 19 (3): 368.
[11] Cai J H, Zhao X J, Sun S W, et al. RAA, 2013, 13(3): 334.
[12] Liu Z B, Song L P, Zhao W J. MNRAS, 2016, 455(4), 4289.
[13] Penalver B A, Escolano F. IEEE TNN, 2009, 20(11): 1756.
[14] Lv S G, Feng Y L. Journal of Mathematical Analysis and Applications, 2012, 386(1): 205.
[15] Kim J, Scott C D. IEEE TPAMI, 2010, 32(10):1822.
[16] Deeming T J. MNRAS, 1964, 127:493.