Automated Separation of Stars and Normal Galaxies Based on Statistical Mixture Modeling with RBF Neural Networks
Automated Separation of Stars and Normal Galaxies Based on Statistical Mixture Modeling with RBF Neural Networks
复制标题
DOI：
10.1088/1009-9271/3/3/277
复制
发表时间：
2003-06
期刊：
影响因子：
--
通讯作者：
Dong-mei Qin;Ping Guo;Zhanyi Hu;Yongheng Zhao
中科院分区：
文献类型：
--
作者：
Dong-mei Qin;Ping Guo;Zhanyi Hu;Yongheng Zhao
在我国最大的巡天计划LAMOST中，解决了恒星与星系的光谱自动判别问题，表明PSF检验的结果可以得到明显的改进。然而，当星系的红移不可用时，问题变得更糟。提出了一种基于径向基函数神经网络统计混合模型（SMM-RBFNN）的星星/（正常）星系自动分离方法。这项工作是我们上一项工作的继续，在上一项工作中，活动和非活动天体被成功地分离出来。将本文的方法与以前的方法相结合，可以根据恒星的光谱将恒星与星系和活动星系核有效地分离开来，这是LAMOST的主要目标，也是任何自动光谱分类系统中不可缺少的一步。在我们的工作中，训练集包括标准的恒星光谱，从Alberby的光谱库和模拟的星系光谱的E0，S 0，Sa，Sb类型的红移范围从0到1.2，和测试集的恒星光谱从Pickles的图集和SDSS光谱的正常星系的信噪比为13。实验结果表明，SMM-RBFNN在训练和测试阶段都比BPNN（backpropagationneuralnetworks）更有效，对恒星和正常星系的分类准确率分别达到99.22%和96.52%。
For LAMOST, the largest sky survey program in China, the solution of the problem of automatic discrimination of stars from galaxies by spectra has shown that the results of the PSF test can be significantly refined. However, the problem is made worse when the redshifts of galaxies are not available. We present a new automatic method of star/(normal) galaxy separation, which is based on Statistical Mixture Modeling with Radial Basis Function Neural Networks (SMM-RBFNN). This work is a continuation of our previous one, where active and non-active celestial objects were successfully segregated. By combining the method in this paper and the previous one, stars can now be eectively separated from galaxies and AGNs by their spectra—a major goal of LAMOST, and an indispensable step in any automatic spectrum classification system. In our work, the training set includes standard stellar spectra from Jacoby's spectrum library and simulated galaxy spectra of E0, S0, Sa, Sb types with redshift ranging from 0 to 1.2, and the test set of stellar spectra from Pickles' atlas and SDSS spectra of normal galaxies with SNR of 13. Experiments show that our SMM-RBFNN is more ecient in both the training and testing stages than the BPNN (back propagation neural networks), and more importantly, it can achieve a good classification accuracy of 99.22% and 96.52%, respectively for stars and normal galaxies.