METHOD FOR CONSTRUCTING A CLASSIFIER OF STARS FROM THE GAIA DR2 CATALOG FOR THE PRESENCE OF EXOPLANETS
Bikmurzin R.V., Fedchenko D.P.
In this paper, we propose a method for constructing a classifier of stars by the presence of exoplanets (EPs) based on information from the GAIA DR2 star catalog and data obtained during observations from the Kepler space telescope. Three types of classifiers have been developed using machine learning methods such as logistic regression, random forest and artificial neural network. Comparative evaluation of the results of the classifiers was carried out using the error matrix.
Keywords: exoplanet, stellar classification, neural network, random forest, Gaia catalogue.
UDC: 524.3, 004.8
Please cite this article in English as: Bikmurzin R.V., Fedchenko D.P. Method for constructing a classifier of stars from the GAIA DR2 catalog for the presence of exoplanets. Space, Time and Fundamental Interactions, 2020, no. 4, pp. 4-9.