Selecting quasar candidates using a support vector machine classification system

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.http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000318270500002&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701Astronomy & AstrophysicsSCI(E)11ARTICLE42599-260942