Classifier based on support vector machine for JET plasma configurations

S Dormido-Canto; G Farias; J Vega; R Dormido; J Sánchez; N Duro; H Vargas; A Murari; JET-EFDA Contributors

doi:10.1063/1.2972023

Classifier based on support vector machine for JET plasma configurations

Rev Sci Instrum. 2008 Oct;79(10):10F326. doi: 10.1063/1.2972023.

Authors

S Dormido-Canto¹, G Farias, J Vega, R Dormido, J Sánchez, N Duro, H Vargas, A Murari; JET-EFDA Contributors

Affiliation

¹ Departamento de Informática y Automática, UNED, C/Juan del Rosal 16, 5a. 28040 Madrid, Spain.

PMID: 19068531
DOI: 10.1063/1.2972023

Abstract

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%.