Selecting quasar candidates using a support vector machine classification system
Selecting quasar candidates using a support vector machine classification system
复制标题
使用支持向量机分类系统选择类星体候选者
DOI：
10.1111/j.1365-2966.2012.21191.x
复制
发表时间：
2012-10-01
影响因子：
4.8
通讯作者：
Wu, Xue-bing
中科院分区：
文献类型：
--
作者：
Peng, Nanbo;Zhang, Yanxia;Wu, Xue-bing
我们开发并演示了一个由多个支持向量机(SVM)分类器组成的分类系统，该系统可用于从斯隆数字巡天(SDSS)、英国红外望远镜红外深空巡天(UKIDSS)和星系演化探测器(GALEX)等大型巡天项目中选择类星体候选。在这里，我们详细介绍了一种构造这种支持向量机分类系统的方法。当支持向量机分类系统在测试集上预测类星体候选时，它获得了93.21%的效率和97.49%的完备率。为了进一步证明该系统的可靠性和可行性，我们随机选取了两个数据块与SDSS-III重子振荡谱测量(BOSS)中使用的XDQSO方法的性能进行了比较。实验结果表明，该系统所选择的候选类星体与XDQSO技术提取的候选类星体在去极化I带星等17.75~22.45之间有明显的重叠，尤其是在去极化I带星等20.0之间。在这两个测试区，系统预测的类星体候选者中，有57.38%和87.15%也是XDQSO方法的目标。同样，根据红移预测类星体的亚类星体与这两种方法有很高的重叠程度。根据该系统的有效性，支持向量机分类系统可以用于为郭守敬望远镜(也称为大天空区域多目标光纤光谱望远镜)或其他光谱巡天项目创建类星体的输入星表。为了获得更高的类星体候选者置信度，可以使用该支持向量机系统和XDQSO方法选择的候选者的交叉结果。
We develop and demonstrate a classification system that is made up of several support vector machine (SVM) classifiers, which can be applied to select quasar candidates from large sky survey projects, such as the Sloan Digital Sky Survey (SDSS), the UK Infrared Telescope Infrared Deep Sky Survey (UKIDSS) and the Galaxy Evolution Explorer (GALEX). Here, we present in detail a method for constructing this SVM classification system. When the SVM classification system works on the test set to predict quasar candidates, it acquires an efficiency of 93.21 per cent and a completeness of 97.49 per cent. In order to further prove the reliability and feasibility of this system, two chunks are randomly chosen to compare its performance with that of the XDQSO method used for the SDSS-III’s Baryon Oscillation Spectroscopic Survey (BOSS). The experimental results show that there is distinct overlap between the quasar candidates selected by this system and those extracted by the XDQSO technique in the dereddened i-band magnitude range between 17.75 and 22.45, especially in the interval of dereddened i-band magnitude <20.0. In the two test areas, 57.38 and 87.15 per cent of the quasar candidates predicted by the system are also targeted by the XDQSO method. Similarly, the prediction of subcategories of quasars according to redshift achieves a high level of overlap with these two approaches. Depending on the effectiveness of this system, the SVM classification system can be used to create an input catalogue of quasars for the Guoshoujing Telescope (also called the Large Sky Area Multi-Object Fiber Spectroscopic Telescope) or other spectroscopic sky survey projects. In order to obtain a higher confidence of quasar candidates, the cross-results from the candidates selected by this SVM system and by the XDQSO method can be used.