Automatic classification of eclipsing binaries light curves using neural networks

¹ Dpt. de Inteligencia Artificial, U.N.E.D., c/ Juan del Rosal, 16, 28040 Madrid, Spain e-mail: lsb@dia.uned.es
² Laboratorio de Astrofísica Espacial y Física Fundamental, PO Box 50727, 28080 Madrid, Spain
³ XMM-Newton SOC, ESAC, PO Box 50727, 28080 Madrid, Spain e-mail: Celia.Sanchez@sciops.esa.int
⁴ Research and Scientific Support Department, ESA, ESTEC, Postbus 299, 2200 AG Noordwijk, The Netherlands e-mail: agimenez@rssd.esa.int

Received: 7 February 2005
Accepted: 26 August 2005

Abstract

In this work we present a system for the automatic classification of the light curves of eclipsing binaries. This system is based on a classification scheme that aims to separate eclipsing binary systems according to their geometrical configuration in a modified version of the traditional classification scheme. The classification is performed by a Bayesian ensemble of neural networks trained with Hipparcos data of seven different categories including eccentric binary systems and two types of pulsating light curve morphologies.