Recent results on structural pattern recognition for Fusion massive databases

Abstract

Physics studies in fusion devices require statistical analyses of a large number of discharges. Given the complexity of the plasma and the non-linear interactions between the relevant parameters, connecting a physical phenomenon with the signal patterns that it generates can be quite demanding Up to now, data retrieval has been typically accomplished by means of signal name and shot number. The search of the temporal segment to analyze has been carried out in a manual way. Manual searches in databases must be replaced by intelligent techniques to look for data in an automated way. Structural pattern recognition techniques have proven to be very efficient methods to index and retrieve data in JET and TJ-II databases. Waveforms and images can be accessed through several structural pattern recognition applications.