| Automated Stellar Classification for Large Surveys with EKF and RBF Neural Networks |
| |
| 作者姓名： | Ling Bai Ping Quo and Zhan-Yi Hu |
| |
| 作者单位： | [1]DepartmentofComputerScience,BeijingNormalUniversity,Beijing100875／／NationalLaboratoryofPatternRecognition,InstituteofAutomation,ChineseAcademyofSciences,Beijing100080 [2]DepartmentofComputerScience,BeijingNormalUniversity,Beijing100875 [3]NationalLaboratoryofPatternRecognition,InstituteofAutomation,ChineseAcademyofSciences,Beijing100080 |
| |
| 基金项目： | Supported by the National Natural Science Foundation of China (Project No. 60275002)
The National High Technology Research and Development Program of China (863 Program, Project No.2003AA133060). |
| |
| 摘 要： | An automated classification technique for large size stellar surveys is proposed. It uses the extended Kalman filter as a feature selector and pre-classifier of the data, and the radial basis function neural networks for the classification. Experiments with real data have shown that the correct classification rate can reach as high as 93%, which is quite satisfactory. When different system models are selected for the extended Kalman filter, the classification results are relatively stable. It is shown that for this particular case the result using extended Kalman filter is better than using principal component analysis.
|
| 关 键 词： | 分光镜 普通星系 恒星含量 数据处理 卡尔曼滤波 |
Automated Stellar Classification for Large Surveys with EKF and RBF Neural Networks |
| |
| Ling Bai,Ping Quo and Zhan-Yi Hu.Automated Stellar Classification for Large Surveys with EKF and RBF Neural Networks[J].Chinese Journal of Astronomy and Astrophysics,2005,5(2):203-210. |
| |
| Authors: | LingBai PingGuo Zhan-YiHu |
| |
| Abstract: | An automated classification technique for large size stellar surveys is proposed. It uses the extended Kalman filter as a feature selector and pre-classifier of the data, and the radial basis function neural networks for the classification. Experiments with real data have shown that the correct classification rate can reach as high as 93%, which is quite satisfactory. When different system models are selected for the extended Kalman filter, the classification results are relatively stable. It is shown that for this particular case the result using extended Kalman filter is better than using principal component analysis. |
| |
| Keywords: | methods: data analysis - techniques: spectroscopic - stars: general- galaxies: stellar content |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
