An Automatic Identifier of Confinement Regimes at JET combining Fuzzy Logic and Classification Trees JET-EFDA, CULHAM SCIENCE CENTER, OX14 3DB, UK G. Vagliasindi 1 , P.Arena 1 , L. Fortuna 1 , A. Murari 2 , G. Mazzitelli 3 , A. Gallo 1 , U. Vagliasindi 1 and JET EFDA Contributors* 1 - Università degli Studi di Catania - Dip. di Ingegneria Elettrica, Elettronica e dei Sistemi, v.le A. Doria 6, 95125, Catania – Italy 2 - Consorzio RFX – Associazione EURATOM ENEA per la Fusione, Corso Stati Uniti 4, I-35127, Padua, Italy 3 - Assoc. Euratom-ENEA sulla Fusione, C.R. Frascati Via Enrico Fermi, 45 00044 Frascati (Rm) - Italy * See the Appendix of M.L.Watkins et al., Fusion Energy 2006 (Proc. 21st Int. Conf. Chengdu, 2006) IAEA, (2006) Abstract. In modern thermonuclear fusion devices it is possible to distinguish distinct types of plasma confinement regimes which have different performance in terms of confinement time. Discriminating among them could represent a useful feature for an efficient control of a plasma experiment. An automatic identifier based on fuzzy logic is here proposed together with an unsupervised technique, using classification and regression trees, for selecting, among several diagnostic signals available, the inputs to be provided to the identifier. 1 Introduction The necessity of reducing the greenhouse gases emission, together with the increasing energy requirements and the expected shortfalls in fossil fuels, pushed the research of alternative energy sources. Among them nuclear fusion, that is the process whereby the nuclei of two atoms fuse together forming an heavier nucleus and energy as a by- product, although not commercially available and still technologically challenging, represents an appealing solution. Nowadays the most promising strategy to achieve nuclear fusion is thermonuclear fusion, which consists of heating the particles of a plasma to sufficiently high temperatures to overcome the electrostatic repulsion of the positive nuclei, in magnetic confinement fusion plants like tokamaks or stellarators. In the last decades, researchers have exerted great efforts to achieve the final goal of a self sustained plasma. Although this has not been accomplished yet, significant improvements in plasma control and confinement were obtained together with a relevant increase in the knowledge of the physics underlying the plasma magnetic 517 ESANN'2008 proceedings, European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning Bruges (Belgium), 23-25 April 2008, d-side publi., ISBN 2-930307-08-0.