| A Comparison of BBN,ADTree and MLP in separating Quasars from Large Survey Catalogues |
| |
| 作者姓名： | Yan-Xia Zhang and Yong-Heng Zhao National Astronomical Observatories Chinese Academy of Sciences Beijing |
| |
| 作者单位： | Yan-Xia Zhang and Yong-Heng Zhao National Astronomical Observatories，Chinese Academy of Sciences，Beijing 100012; |
| |
| 摘 要： | We compare the performance of Bayesian Belief Networks (BBN), Multilayer Perception (MLP) networks and Alternating Decision Trees (ADtree) on separating quasars from stars with the database from the 2MASS and FIRST survey catalogs. Having a train- ing sample of sources of known object types, the classifiers are trained to separate quasars from stars. By the statistical properties of the sample, the features important for classifica- tion are selected. We compare the classification results with and without feature selection. Experiments show that the results with feature selection are better than those without feature selection. From the high accuracy found, it is concluded that these automated methods are robust and effective for classifying point sources. They may all be applied to large survey projects (e.g. selecting input catalogs) and for other astronomical issues, such as the parame- ter measurement of stars and the redshift estimation of galaxies and quasars.
|
| 关 键 词： | astronomical databases: miscellaneous—catalogs—methods: data analysis—methods: statistical |
A Comparison of BBN, ADTree and MLP in separating Quasars from Large Survey Catalogues |
| |
| Yan-Xia Zhang and Yong-Heng Zhao National Astronomical Observatories,Chinese Academy of Sciences,Beijing ,.A Comparison of BBN,ADTree and MLP in separating Quasars from Large Survey Catalogues[J].Chinese Journal of Astronomy and Astrophysics,2007,7(2):289-296. |
| |
| Authors: | Yan-Xia Zhang Yong-Heng Zhao |
| |
| Institution: | National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012 |
| |
| Abstract: | We compare the performance of Bayesian Belief Networks (BBN), Multilayer Perception (MLP) networks and Alternating Decision Trees (ADtree) on separating quasars from stars with the database from the 2MASS and FIRST survey catalogs. Having a train- ing sample of sources of known object types, the classifiers are trained to separate quasars from stars. By the statistical properties of the sample, the features important for classifica- tion are selected. We compare the classification results with and without feature selection. Experiments show that the results with feature selection are better than those without feature selection. From the high accuracy found, it is concluded that these automated methods are robust and effective for classifying point sources. They may all be applied to large survey projects (e.g. selecting input catalogs) and for other astronomical issues, such as the parame- ter measurement of stars and the redshift estimation of galaxies and quasars. |
| |
| Keywords: | astronomical databases: miscellaneous - catalogs - methods: data analysis - methods: statistical |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
