EDP Sciences
Free access
Issue
A&A
Volume 446, Number 1, January IV 2006
Page(s) 395 - 402
Section Instruments, observational techniques, and data processing
DOI http://dx.doi.org/10.1051/0004-6361:20052830


A&A 446, 395-402 (2006)
DOI: 10.1051/0004-6361:20052830

Automatic classification of eclipsing binaries light curves using neural networks

L. M. Sarro1, C. Sánchez-Fernández2, 3 and Á. Giménez4

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.


Key words: stars: binaries: eclipsing -- stars: binaries: general -- methods: data analysis -- methods: statistical

SIMBAD Objects



© ESO 2006