文章基本信息

标题：Applying the Support Vector Machine Method to Matching IRAS and SDSS Catalogues
本地全文：下载
作者：Chen Cao
期刊名称：Data Science Journal
电子版ISSN：1683-1470
出版年度：2015
卷号：6
DOI：10.2481/dsj.6.S756
语种：English
出版社：Ubiquity Press
摘要：This paper presents results of applying a machine learning technique, the Support Vector Machine (SVM), to the astronomical problem of matching the Infra-Red Astronomical Satellite (IRAS) and Sloan Digital Sky Survey (SDSS) object catalogues. In this study, the IRAS catalogue has much larger positional uncertainties than those of the SDSS. A model was constructed by applying the supervised learning algorithm (SVM) to a set of training data. Validation of the model shows a good identification performance (∼ 90% correct), better than that derived from classical cross-matching algorithms, such as the likelihood-ratio method used in previous studies.
关键词：Miscellaneous astronomical data bases; Catalogs; Surveys; Sloan Digital Sky; Infra-red astronomy