标题:The Reasearch on Photometric Model of Cataclysmic Variable
作者:Wang Wen-yu; Ba Jin-sheng; Jiang Bin; Shi Yu-feng
通讯作者:Ba, JS
作者机构:[Wang Wen-yu; Ba Jin-sheng; Jiang Bin] Shandong Univ, Sch Mech Elect & Informat Engn, Weihai 264209, Peoples R China.; [Shi Yu-feng] Power Supply Co 更多
会议名称:3rd International Conference on Information Science and Control Engineering (ICISCE)
会议日期:JUL 08-10, 2016
来源:2016 3RD INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND CONTROL ENGINEERING (ICISCE)
出版年:2016
页码:1159-1163
DOI:10.1109/ICISCE.2016.249
关键词:CV; Photometric Model; Orthogonal Criterion
摘要:Cataclysmic variable (CV) stars are binary stars that consist of two components: a white dwarf primary, and a mass transferring secondary. Due to the relative faint of cataclysmic variable and a large number of irregular changes, it is not easy to get valuable data and important research results on observation. But they have significant meaning on the subsequent research of these spectra. In general, astronomers classified the types of celestial bodies depend on the characteristics of the spectral lines and physical parameters, where spectral line is a significant feature of classification. Due to the poor performance of color features, the effect on the classification of color features is unsatisfactory. This paper studies color features, and presents different photometric models of the color feature. These photometric models are under the Birkhoff orthogonal constraint, then we design efficient algorithms through Logistic Regression (LR), Artificial Neural Network (AAN), Support Vector Machine (SVM) respectively. At last, through the comparison experiments on Sloan Digital Sky Survey (SDSS) DR12 data, we obtain a photometric model that can improve the classification accuracy of automatic identification. Results show that, the photometric model can effectively improve the classification accuracy compared with the current photometric models, which is feasible.
收录类别:CPCI-S
资源类型:会议论文
TOP