000002195 001__ 2195
000002195 005__ 20160701171700.0
000002195 0247_ $$2DOI$$a10.1111/j.1365-2966.2012.21752.x
000002195 037__ $$aASTROimport-352
000002195 100__ $$aRimoldini, L.
000002195 245__ $$aAutomated classification of Hipparcos unsolved variables
000002195 260__ $$c2012
000002195 520__ $$aWe present an automated classification of stars exhibiting periodic, non-periodic and irregular light variations. The Hipparcos catalogue of unsolved variables is employed to complement the training set of periodic variables of Dubath et al. with irregular and non-periodic representatives, leading to 3881 sources in total which describe 24 variability types. The attributes employed to characterize light-curve features are selected according to their relevance for classification. Classifier models are produced with random forests and a multistage methodology based on Bayesian networks, achieving overall misclassification rates under 12 per cent. Both classifiers are applied to predict variability types for 6051 Hipparcos variables associated with uncertain or missing types in the literature. 
000002195 700__ $$a Dubath, P.
000002195 700__ $$a Süveges, M.
000002195 700__ $$a López, M.
000002195 700__ $$a Sarro, L. M.
000002195 700__ $$a Blomme, J.
000002195 700__ $$a De Ridder, J.
000002195 700__ $$a Cuypers, J.
000002195 700__ $$a Guy, L.
000002195 700__ $$a Mowlavi, N.
000002195 700__ $$a Lecoeur-Taïbi, I.
000002195 700__ $$a Beck, M.
000002195 700__ $$a Jan, A.
000002195 700__ $$a Nienartowicz, K.
000002195 700__ $$a Ordóñez-Blanco, D.
000002195 700__ $$a Lebzelter, T.
000002195 700__ $$a Eyer, L.
000002195 773__ $$c2917-2937$$i4$$pMonthly Notices of the Royal Astronomical Society$$v427$$y2012
000002195 85642 $$ahttp://esoads.eso.org/abs/2012MNRAS.427.2917R
000002195 905__ $$apublished in
000002195 980__ $$aREFERD