Comparison of Advanced Machine Learning Tools for Disruption Prediction and Disruption Studies

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61389021%3A_____%2F13%3A00421353" target="_blank" >RIV/61389021:_____/13:00421353 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/TPS.2013.2264880" target="_blank" >http://dx.doi.org/10.1109/TPS.2013.2264880</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPS.2013.2264880" target="_blank" >10.1109/TPS.2013.2264880</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of Advanced Machine Learning Tools for Disruption Prediction and Disruption Studies

Popis výsledku v původním jazyce

Machine learning tools have been used since a long time ago to study disruptions and to predict their occurrence. On the other hand, the challenges posed by the quality and quantities of the data available remain substantial. In this paper, methods to optimize the training data set and the potential of kernels-based advanced machine learning tools are explored and assessed. Various alternatives, ranging from appropriate selection of the weights to the inclusion of artificial points, are investigated toimprove the quality of the training data set. Support vector machines (SVM), relevance vector machines (RVMs), and one-class SVM are compared. The relative performances of the different approaches are initially assessed using synthetic data. Then they are applied to a relatively large database of JET disruptions. It is shown that in terms of final results, the optimization of the training databases proved to be very productive.

Název v anglickém jazyce

Comparison of Advanced Machine Learning Tools for Disruption Prediction and Disruption Studies

Popis výsledku anglicky

Machine learning tools have been used since a long time ago to study disruptions and to predict their occurrence. On the other hand, the challenges posed by the quality and quantities of the data available remain substantial. In this paper, methods to optimize the training data set and the potential of kernels-based advanced machine learning tools are explored and assessed. Various alternatives, ranging from appropriate selection of the weights to the inclusion of artificial points, are investigated toimprove the quality of the training data set. Support vector machines (SVM), relevance vector machines (RVMs), and one-class SVM are compared. The relative performances of the different approaches are initially assessed using synthetic data. Then they are applied to a relatively large database of JET disruptions. It is shown that in terms of final results, the optimization of the training databases proved to be very productive.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

BL - Fyzika plasmatu a výboje v plynech

OECD FORD obor

—

Projekt

<a href="/cs/project/GAP205%2F10%2F2055" target="_blank" >GAP205/10/2055: Numerická analýza a fyzikální interpretace ITER-relevantních experimentálních dat ze Společného evropského toru JET</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2013

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Plasma Science

ISSN

0093-3813

e-ISSN

—

Svazek periodika

41

Číslo periodika v rámci svazku

7

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

9

Strana od-do

1751-1759

Kód UT WoS článku

000321625400009

EID výsledku v databázi Scopus

—