D'Isanto, A.A.D'IsantoCavuoti, S.S.CavuotiBRESCIA, MassimoMassimoBRESCIADonalek, C.C.DonalekLongo, G.G.LongoRICCIO, GIUSEPPEGIUSEPPERICCIODjorgovski, S. G.S. G.Djorgovski2020-05-252020-05-2520160035-8711http://hdl.handle.net/20.500.12386/25154The exploitation of present and future synoptic (multiband and multi-epoch) surveys requires an extensive use of automatic methods for data processing and data interpretation. In this work, using data extracted from the Catalina Real Time Transient Survey (CRTS), we investigate the classification performance of some well tested methods: Random Forest, MultiLayer Perceptron with Quasi Newton Algorithm and K-Nearest Neighbours, paying special attention to the feature selection phase. In order to do so, several classification experiments were performed. Namely: identification of cataclysmic variables, separation between galactic and extragalactic objects and identification of supernovae.STAMPAenArticle10.1093/mnras/stw1572-s2.0-84976885060000373583900065https://academic.oup.com/mnras/article/457/3/3119/25889432016MNRAS.457.3119DFIS/05 - ASTRONOMIA E ASTROFISICAERC sectors::Physical Sciences and Engineering::PE6 Computer Science and Informatics: Informatics and information systems, computer science, scientific computing, intelligent systems::PE6_11 Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)