Automated classification of Hipparcos unsolved variables
Abstract
We present an automated classification of stars exhibiting periodic, non-periodic and irregular light variations. The Hipparcos catalogue of unsolved variables is employed to complement the training set of periodic variables of Dubath et al. with irregular and non-periodic representatives, leading to 3881 sources in total which describe 24 variability types. The attributes employed to characterize light-curve features are selected according to their relevance for classification. Classifier models are produced with random forests and a multistage methodology based on Bayesian networks, achieving overall misclassification rates under 12 per cent. Both classifiers are applied to predict variability types for 6051 Hipparcos variables associated with uncertain or missing types in the literature.
Keywords
Cite
@article{arxiv.1301.1545,
title = {Automated classification of Hipparcos unsolved variables},
author = {L. Rimoldini and P. Dubath and M. Süveges and M. López and L. M. Sarro and J. Blomme and J. De Ridder and J. Cuypers and L. Guy and N. Mowlavi and I. Lecoeur-Taïbi and M. Beck and A. Jan and K. Nienartowicz and D. Ordóñez-Blanco and T. Lebzelter and L. Eyer},
journal= {arXiv preprint arXiv:1301.1545},
year = {2013}
}
Comments
This article was published on the Monthly Notices of the Royal Astronomical Society 427, 2917-2937 (2012) by Blackwell Publishing. The definitive version is available at wileyonlinelibrary.com/journal/mnr or directly at the following link: http://onlinelibrary.wiley.com/doi/10.1111/j.1365-2966.2012.21752.x/abstract