A Study on the Outlier Mining System for LAMOST Spectra
ZHANG Ji-fu1, 2,CAI Jiang-hui1
1. School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China 2. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China
Abstract：To find unknown celestial bodies is one of main goals in mankind’s universe exploration, and outlier mining is a kind of effective way of finding unknown celestial bodies from mass spectrum data. In the present work, using VC++ and Oracle9i as development tools, an outlier mining system for star spectra is designed and realized, and its software architecture and function modules are outlined. At the same time, the system’s key components such as star spectrum data preprocessing based on median filters, clustering of star spectrum data based on distance, outlier mining of star spectrum data based on distance support and three-dimensional visualization of star spectrum outlier based on PCA, are elaborated. The preliminary experimental results based on SDSS star spectrum data show that the system is workable for outlier mining of celestial body spectrum data, and a new kind of effective way of finding unknown and peculiar celestial body spectrum data.
Key words：Celestial body spectrum data;Outliers;Clustering;Distance support
张继福1, 2,蔡江辉1. 面向LAMOST的天体光谱离群数据挖掘系统研究[J]. 光谱学与光谱分析, 2007, 27(03): 606-609.
ZHANG Ji-fu1, 2,CAI Jiang-hui1 . A Study on the Outlier Mining System for LAMOST Spectra. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2007, 27(03): 606-609.
[1] ZHAO Rui-zhen, HU Zhan-yi, ZHAO Yong-heng(赵瑞珍，胡占义，赵永恒). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2005，25(1)：153. [2] QIN Dong-mei，HU Zhan-yi, ZHAO Yong-heng(覃冬梅，胡占义，赵永恒). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2003，23(1)：182. [3] LIU Rong, LIU San-yang, ZHAO Rui-zhen(刘 蓉，刘三阳，赵瑞珍). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2006，26(3)：583. [4] QIU Bo，HU Zhan-yi, ZHAO Yong-heng (邱 波，胡占义，赵永恒). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2002，22(3)：523. [5] Barnett V, Lewis T. Outliers in Statistical Data. New York: John Wiley & Sons, 1994. [6] Luis Malagon-Borja, Olac Fuentes. An Object Detection System Using Image Reconstruction with PCA，The 2nd Canadian Conference on Computer and Robot Vision (CRV’05), 2. [7] HUANG Xi-tao(黄熙涛). Two-dimensional Digital Signal Processing Ⅱ: Transforms and Median Filters (二维数字信号处理Ⅱ: 变换与中值滤波器). Beijing: Science Technology Press(北京：科学技术出版社)，1985. [8] Karypis G, Han E H，Kumar V. IEEE Computer, 1999, 32(8): 68.
