| 基于NPSVM模型的超新星识别方法 |
| |
| 引用本文： | 王精东,陈星星,梁吴颖,黄泽锋,全少武,沈锦泫,石雄辉.基于NPSVM模型的超新星识别方法[J].天文学报,2021,62(2):15-53. |
| |
| 作者姓名： | 王精东 陈星星 梁吴颖 黄泽锋 全少武 沈锦泫 石雄辉 |
| |
| 作者单位： | 广东海洋大学数学与计算机学院湛江524088;北京师范大学数学科学学院北京100875;湖南科技大学材料科学与工程学院湘潭411201 |
| |
| 基金项目： | 广东省大学生创新创业训练计划项目(S201910566087)资助 |
| |
| 摘 要： | 巡天观测与高能物理、黑洞天文等领域均有密切的联系.基于星系-超新星二分类问题,研究光谱数据预处理,结合余弦相似度改善PCA(Principal Component Analysis)光谱分解特征提取方法,用SDSS(the Sloan Digital Sky Survey)、WISeREP(the Weizmann Interactive Supernova data REPository)组成的5620条光谱数据集训练支持向量机,可以得到0.498%泛化误差的识别模型和新样本分类概率.使用Neyman-Pearson决策方法建立NPSVM(Neyman-Pearson Support Vector Machine)模型可进一步降低超新星的漏判率.
|
| 关 键 词： | 超新星:普通 星系:普通 技术:光谱学 方法:数据分析 |
| 收稿时间： | 2020/6/5 0:00:00 |
A Supernova Recognition Method Based on NPSVM |
| |
| WANG Jing-dong,CHEN Xing-xing,LIANG Wu-ying,HUANG Ze-feng,QUAN Shao-wu,SHEN Jin-xuan,SHI Xiong-hui.A Supernova Recognition Method Based on NPSVM[J].Acta Astronomica Sinica,2021,62(2):15-53. |
| |
| Authors: | WANG Jing-dong CHEN Xing-xing LIANG Wu-ying HUANG Ze-feng QUAN Shao-wu SHEN Jin-xuan SHI Xiong-hui |
| |
| Institution: | College of Mathematics and Computer Science, Guangdong Ocean University, Zhanjiang 524088;School of Mathematical Sciences, Beijing Normal University, Beijing 100875;School of Materials Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201 |
| |
| Abstract: | Sky survey is closely related to the developments of many domains such as high energy physics and black hole astrophysics. In order to solve the classification problem between galaxy and supernova, an available supernova recognition method based on NPSVM (Neyman-Pearson Support Vector Machine) has been proposed. The dataset, which is collected from WISeREP (the Weizmann Interactive Supernova data REPository), SDSS (the Sloan Digital Sky Survey) and supernova templates made by Nugent, has 3427 supernova spectra and 2193 galaxy spectra. After preprocessing spectral data, the decomposed spectrum feature based on the Principal Component Analysis (PCA) is extracted, and the redundant features are decreased with the cosine similarity method. The classification model based on Support Vector Machine (SVM) has a low level of generalization error evaluated 0.498%, and can calculate the classification probability for a new sample. Furthermore, the improved NPSVM model can limit the missing rate on supernovae with the Neyman-Pearson criterion. |
| |
| Keywords: | supernovae: general galaxies: general techniques: spectroscopic methods: data analysis |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《天文学报》浏览原始摘要信息 |
| 点击此处可从《天文学报》下载免费的PDF全文 |
|
