Feature extraction for improved disruption prediction analysis at JET

Rattá, G. A.; Vega, J.; Murari, A.; Johnson, M.; JET-EFDA Contributors
October 2008
Review of Scientific Instruments;Oct2008, Vol. 79 Issue 10, p10F328
Academic Journal
Disruptions are major instabilities and remain one of the main problems in tokomaks. Using Joint European Torus database, a disruption predictor is developed by computational methods including supervised learning techniques. The main objectives of the work are to develop accurate automatic classifiers, to test their performances, and to determine how much in advance of the disruption they can operate with acceptable reliability.


Related Articles

  • Network Video Online Semi-supervised Classification Algorithm Based on Multiple View Co-training. Nanbin Zhang; Xiaoping Liu // Journal of Multimedia;Jun2013, Vol. 8 Issue 3, p206 

    As information integration based on multiple modal has to problems like complexity calculation process and low classification accuracy towards network video classification algorithm, came up with a network video online semi-supervised classification algorithm based on multiple view co-training....

  • Efficient algorithms for finding optimal binary features in numeric and nominal labeled data. Mampaey, Michael; Nijssen, Siegfried; Feelders, Ad; Konijn, Rob; Knobbe, Arno // Knowledge & Information Systems;Feb2015, Vol. 42 Issue 2, p465 

    An important subproblem in supervised tasks such as decision tree induction and subgroup discovery is finding an interesting binary feature (such as a node split or a subgroup refinement) based on a numeric or nominal attribute, with respect to some discrete or continuous target variable. Often...

  • Fast and Efficient Opinion Mining Technique for Online Reviews Using Ranking and Classification Algorithms. Dhanalakshmi, B.; Sekar, A. Chandra // International Review on Computers & Software;Jul2013, Vol. 8 Issue 7, p1587 

    In recent years, the spectacular development of web technologies, lead to an enormous quantity of user generated information in online systems. This large amount of information on web platforms make them viable for use as data sources, in applications based on opinion mining and sentiment...

  • A Pan-Skin Based Positioning Model for Omni-directional Faces. Peng Min-jing; Li Bo // International Journal of Digital Content Technology & its Applic;Nov2012, Vol. 6 Issue 20, p352 

    In order to solve the problem that omni-directional faces, which were in images with complex backgrounds, couldn't be detected fast and accurately, a pan-skin based detection model for omni-directional faces was proposed. In the proposed model, cascade architecture was used to ensemble skin...

  • Bayesian Co-Training. Shipeng Yu; Krishnapuram, Balaji; Rosales, Rómer; Rao, R. Bharat // Journal of Machine Learning Research;Sep2012, Vol. 13 Issue 9, p2649 

    Co-training (or more generally, co-regularization) has been a popular algorithm for semi-supervised learning in data with two feature representations (or views), but the fundamental assumptions underlying this type of models are still unclear. In this paper we propose a Bayesian undirected...

  • A Semi-supervised Approach of Extracting Attribute-Value Pairs of Chinese eBook using Conditional Random Fields. Yongquan DONG; Ping LING; Qiang CHU // Journal of Convergence Information Technology;Jan2013, Vol. 8 Issue 1, p222 

    We describe a method to extract attribute--value pairs from Chinese eBook descriptions in order to augment book databases by representing each eBook as a set of attribute-value pairs. Such a representation is beneficial for tasks such as demand forecasting, product recommendations. Current...

  • An Incremental Classification Algorithm for Mining Data with Feature Space Heterogeneity. Yu Wang // Mathematical Problems in Engineering;2014, p1 

    Feature space heterogeneity often exists in many real world data sets so that some features are of different importance for classification over different subsets. Moreover, the pattern of feature space heterogeneity might dynamically change over time as more and more data are accumulated. In...

  • Feature selection for support vector machines with RBF kernel. Liu, Quanzhong; Chen, Chihau; Zhang, Yang; Hu, Zhengguo // Artificial Intelligence Review;Aug2011, Vol. 36 Issue 2, p99 

    Linear kernel Support Vector Machine Recursive Feature Elimination (SVM-RFE) is known as an excellent feature selection algorithm. Nonlinear SVM is a black box classifier for which we do not know the mapping function $${\Phi}$$ explicitly. Thus, the weight vector w cannot be explicitly computed....

  • Learning to Select Features using their Properties. Krupka, Eyal; Navot, Amir; Tishby, Naftali // Journal of Machine Learning Research;10/1/2008, Vol. 9 Issue 10, p2349 

    Feature selection is the task of choosing a small subset of features that is sufficient to predict the target labels well. Here, instead of trying to directly determine which features are better, we attempt to learn the properties of good features. For this purpose we assume that each feature is...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics