AMAndrea Murari

Andrea Murari

*This is an algorithmically generated author record based on publicly available information.

Andrea Murari has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • On the Potential of Information Theoretic Indicators for the Detection of Image Vibrations and for Image Registration on JET

    by Andrea Murari, Michela Gelfusa, Thibault Lesage, Didier Mazon, G. Arnoux

    In Tokamaks, the use of cameras as diagnostics has increased remarkably in the last years. One of the main technical difficulties, in interpreting the data of camera-based diagnostics, is the presence of movements and vibrations of the field of view, consequence of various plasma phenomena, and modes of operation. Typically, these movements results in rigid transformations of the frames. In this paper, various information theoretic indicators (correlations, entropies, and mutual information) are described and their potential to detect the vibrations and to register images is investigated. The indicators are applied to a representative set of videos collected by Joint European Torus wide-angle infrared camera. For movement detection, the Tsallis entropy is the indicator with the best performance, providing a success rates in excess of 86% and an almost equal number of false and missed detections. Its application to image registration looks also very promising.


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

    by Michal Odstrcil, Andrea Murari, Jan Mlynar

    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 to improve 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. Further, the RVM algorithm performs well when it is trained on a small set of discharges compared to the traditional methods.


  • Exploratory Data Analysis Techniques to Determine the Dimensionality of Complex Nonlinear Phenomena: The L-to-H Transition at JET as a Case Study

    by Andrea Murari, Didier Mazon, N. Martin, Guido Vagliasindi, Michela Gelfusa

    A strategy to identify and select the most relevant variables to study problems in the exact sciences, when large databases of data have to be explored, is formulated. It consists of a first exploratory stage, performed mainly with the classification and regression tree method, to determine the list of most relevant signals to be used in the analysis of the phenomenon of interest. A linear correlation technique, followed by a nonlinear correlation technique (principal component analysis and autoassociative neural networks (NNs), respectively), is then applied to reduce the number of signals to the ones containing nonredundant information. The potential of the approach is illustrated by an application to the problem of identifying the confinement regime in the Joint European Torus. The minimum set of signals has been used to train an NN, and its performance is compared with that of various theoretical models. The success rate of the NN is very high, and it generally further outperforms the available theoretical models.


  • Open Access

    Exploiting Graphic Processing Units Parallelism to Improve Intelligent Data Acquisition System Performance in JET's Correlation Reflectometer

    by Julián Nieto, G. de Arcas, J. Vega, M. Ruiz, J. M Lopez, E. Barrera, A. Murari, A. Fonseca

    The performance of intelligent data acquisition systems relies heavily on their processing capabilities and local bus bandwidth, especially in applications with high sample rates or high number of channels. This is the case of the self adaptive sampling rate data acquisition system installed as a pilot experiment in KG8 B correlation reflectometer at JET. The system, which is based on the ITMS platform, continuously adapts the sample rate during the acquisition depending on the signal bandwidth. In order to do so it must transfer acquired data to a memory buffer in the host processor and run heavy computational algorithms for each data block. The processing capabilities of the host CPU and the bandwidth of the PXI bus limit the maximum sample rate that can be achieved, therefore limiting the maximum bandwidth of the phenomena that can be studied. Graphic processing units (GPU) are becoming an alternative for speeding up compute intensive kernels of scientific, imaging and simulation applications. However, integrating this technology into data acquisition systems is not a straight forward step, not to mention exploiting their parallelism efficiently. This paper discusses the use of GPUs with new high speed data bus interfaces to improve the performance of the self adaptive sampling rate data acquisition system installed on JET. Integration is sues are discussed and performance evaluations are presented.