Research Papers
Applying the Support Vector Machine Method to Matching IRAS and SDSS Catalogues
Author:
Chen Cao
National Astronomical Observatories, CAS, Beijing 100012, China Graduate School, Chinese Academy of Sciences, Beijing 100039, China
Abstract
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.
How to Cite:
Cao, C., 2007. Applying the Support Vector Machine Method to Matching IRAS and SDSS Catalogues. Data Science Journal, 6, pp.S756–S759. DOI: http://doi.org/10.2481/dsj.6.S756
Published on
26 Oct 2007.
Peer Reviewed
Downloads