Classifier based on support vector machine for JET plasma configurations
S. Dormido-Canto, Gonzalo Farías, Jesús Vega, Raquel Dormido, José Sánchez, Natividad Duro, Hermann Vargas, Andrea Murari, JET-EFDA Contributors · Review of Scientific Instruments · 2008
The last flux surface can be used to identify the plasma configuration of discharges. For automated recognition of JET configurations, a learning system based on support vector machines has been developed. Each configuration is described by 12 geometrical parameters. A multiclass system has been developed by means of the one-versus-the-rest approach. Results with eight simultaneous classes (plasma configurations) show a success rate close to 100%.