Automated estimation of L/H transition times at JET by combining Bayesian statistics and support vector machines

This paper describes a pattern recognition method for off-line estimation of both L/H and H/L transition times in JET. The technique is based on a combined classifier to identify the confinement regime (L or H) at any time instant during a discharge. The classifier is a combination of two different classification systems: a Bayesian classifier whose likelihood is computed by means of a non-parametric statistical classifier (Parzen window) and a support vector machine classifier. They are combined through a fuzzy aggregation operator, in particular the Einstein sum. The success rate achieved exceeds 99% for the L to H transition and 96% for the H to L transition. The estimation of transition times is accomplished by following the temporal evolution of the confinement regimes.

[1]  David G. Stork,et al.  Pattern Classification , 1973 .

[2]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[3]  Hans-Jürgen Zimmermann,et al.  Fuzzy Set Theory - and Its Applications , 1985 .

[4]  Vladimir Cherkassky,et al.  Learning from data , 1998 .

[5]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[6]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[7]  Angel R. Martinez,et al.  Computational Statistics Handbook with MATLAB , 2001 .

[8]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[9]  Teruhisa Hochin,et al.  Search and retrieval method of similar plasma waveforms , 2004 .

[10]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[11]  P. Arena,et al.  Fuzzy logic and support vector machine approaches to regime identification in JET , 2006, IEEE Transactions on Plasma Science.

[12]  J. Vega.  Intelligent methods for data retrieval in fusion databases , 2008 .

[13]  A. A. Lukianitsa,et al.  Analyses of ITER operation mode using the support vector machine technique for plasma discharge classification , 2008 .

[14]  J. Vega,et al.  Overview of intelligent data retrieval methods for waveforms and images in massive fusion databases , 2009 .

[15]  D. C. McDonald,et al.  The application of classification methods in a data driven investigation of the JET L–H transition , 2010 .

[16]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..