TITLE

A neural networks framework for real-time unfolding of neutron spectroscopic data at JET

AUTHOR(S)
Ronchi, E.; Conroy, S.; Sundén, E. A.; Ericsson, G.; Hjalmarsson, A.; Hellesen, C.; Johnson, M. G.; Weiszflog, M.; JET-EFDA Contributors
PUB. DATE
October 2008
SOURCE
Review of Scientific Instruments;Oct2008, Vol. 79 Issue 10, p10E513
SOURCE TYPE
Academic Journal
DOC. TYPE
Article
ABSTRACT
A determination of fast ion population parameters such as intensity and kinetic temperature is important for fusion reactors. This becomes more challenging with finer time resolution of the measurements, since the limited data in each time slice cause increasing statistical variations in the data. This paper describes a framework using Bayesian-regularized neural networks (NNs) designed for such a task. The method is applied to the TOFOR 2.5 MeV fusion neutron spectrometer at JET. NN training data are generated by random sampling of variables in neutron spectroscopy models. Ranges and probability distributions of the parameters are chosen to match the experimental data. Results have shown good performance both on synthetic and experimental data. The latter was assessed by statistical considerations and by examining the robustness and time consistency of the results. The regularization of the training algorithm allowed for higher time resolutions than simple forward methods. The fast execution time makes this approach suitable for real-time analysis with a time resolution limit in the microsecond time scale.
ACCESSION #
35150233

 

Related Articles

  • A Chaotic Dynamic Local Search Method for Learning Multiple-Valued Logic Networks. Gao Shangce; Zhang Jianchen; Tang Zheng; Cao Qiping // Journal of Multiple-Valued Logic & Soft Computing;2009, Vol. 15 Issue 5/6, p433 

    As a novel optimization technique, chaos has gained much attention and some applications during the past decade. For a given energy or cost function, by following chaotic ergodic orbits, a chaotic dynamic system may eventually reach the global optimum or its good approximation with high...

  • Sports Results Prediction Scheme based on Gray Neural Network Model. Guo Liang; Wang Yin-hui // International Journal of Advancements in Computing Technology;Apr2013, Vol. 5 Issue 8, p1325 

    The gray prediction model doesn't request the large number of the samples and the distribution pattern of the data. The calculation amount is less and this model can be easily operated. But when the BP network studies the samples, the output errors will be feedback corrected. This model has the...

  • Application of artificial neural networks for the rapid classification of archaeological ceramics by means of laser induced breakdown spectroscopy (LIBS). Ramil, A.; López, A. J.; Yáñez, A. // Applied Physics A: Materials Science & Processing;Jul2008, Vol. 92 Issue 1, p197 

    The aim of this work is to analyze the feasibility of artificial neural networks (ANN) for the classification, in function of the provenance, of archaeological ceramics Terra Sigillata analyzed by means of laser-induced breakdown spectroscopy (LIBS). In order to automate and facilitate the task...

  • Validation of Infinite Impulse Response Multilayer Perceptron for Modelling Nuclear Dynamics. Cadini, F.; Zio, E.; Pedroni, N. // Science & Technology of Nuclear Installations;2008, Vol. 2008, p1 

    The article presents a study that examines the nonlinear modeling capabilities of an infinite impulse response multilayer perceptron (IIR-MLP) for nuclear dynamics. It compares the infinite impulse response locally recurrent neural network (IIR-LRNN) to static modeling by a finite impulse...

  • In Situ Calibration of Hot-Film Probes Using a Collocated Sonic Anemometer: Angular Probability Distribution Properties. Kit, E.; Grits, B. // Journal of Atmospheric & Oceanic Technology;Jan2011, Vol. 28 Issue 1, p104 

    In a recent paper by Kit et al., a novel algorithm for the calibration of hot-film probes using a collocated sonic anemometer combined with the neural network approach is described. An important step in the algorithm is the generation of a calibration dataset by an appropriate low-pass filtering...

  • APPLICATION OF ESTIMATES OF ALPHA-STABLE DISTRIBUTION TO DISTRESS FORECAST. KABAŠINSKAS, AUDRIUS; KALSYTŻ, ŽIVILŻ; GOODE, JIMMIE; VASILIAUSKAITŻ, ASTA // Journal of Applied Functional Analysis;Jul-Oct2013, Vol. 8 Issue 3/4, p323 

    This article proposes a method to evaluate the change in distress value of companies belonging to the US health care industry. The method involves the use of stable distribution parameters (as also the key financial ratios) in the formation of neural network committees. For each sector of the...

  • Privacy preserving Back-propagation neural network learning over arbitrarily partitioned data. Bansal, Ankur; Chen, Tingting; Zhong, Sheng // Neural Computing & Applications;Feb2011, Vol. 20 Issue 1, p143 

    Neural networks have been an active research area for decades. However, privacy bothers many when the training dataset for the neural networks is distributed between two parties, which is quite common nowadays. Existing cryptographic approaches such as secure scalar product protocol provide a...

  • Combined application of Monte Carlo method and neural networks to simulate qualitative prompt gamma neutron activation analysis. Doostmohammadi, V.; Sardari, D.; Nasrabadi, A. M. // Journal of Radioanalytical & Nuclear Chemistry;Feb2010, Vol. 283 Issue 2, p403 

    Prompt gamma spectrum produced by thermal neutron absorption and fast neutron inelastic scattering is simulated using Monte Carlo code MCNP4C. The simulated spectrum is analyzed with artificial neural network techniques. The neural network in our study is trained based on back-propagation...

  • Temporal hemodynamic classification of two hands tapping using functional near-infrared spectroscopy. Hai, Nguyen Thanh; Cuong, Ngo Q.; Khoa, Truong Q. Dang; Toi, Vo Van // Frontiers in Human Neuroscience;Sep2013, Vol. 7, p1 

    In recent decades, a lot of achievements have been obtained in imaging and cognitive neuroscience of human brain. Brain's activities can be shown by a number of different kinds of non-invasive technologies, such as: Near-Infrared Spectroscopy (NIRS), Magnetic Resonance Imaging (MRI), and...

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

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

Try another library?
Sign out of this library

Other Topics