Advertisement

Simulations of nuclear fusion diagnostics based on projections with Venn predictors and context drift detection

  • J. Vega
  • A. Murari
  • S. Dormido-Canto
  • T. Cruz
Article
  • 106 Downloads

Abstract

Tomography is used to reconstruct the inside cross section of an inaccesible object. To this end, a high number of cross section projections are required. In nuclear fusion devices, the plasma follows a toroidal shape and tomography can be used to estimate the two-dimensional spatial distribution of the plasma emission through a cross section. One of the objectives of tomography in plasma physics is to determine the number of localized emission peaks within the cross-section. Due to space restrictions in fusion devices, only a very limited number of projections can be experimentally measured and this introduces limitations to detect the number of emission peaks in the cross-section. This article describes a set of simulations to show that a multi-class classification system can be a valid alternative to tomography in plasma physics, even with the data of a single projection. Each class of the classifier represents the number of perturbations that can appear at any time in the plasma emissivity. To ensure the accuracy and reliability of the predictions, probabilistic classifiers (Venn predictors and Bayesian classifiers) have been used, with more reliable results from the Venn predictors. The probability intervals of Venn predictors with a single projection and intense/low respectively perturbations are [0.85, 0.93] and [0.62, 0.71] (to be compared with a probability 0.2 of a class random assignation). However, when the perturbation peaks are not strong enough and are lost into the emissivity background, the determination of the number of emission peaks can produce unreliable results. In these cases, to detect the plasma transition from an unperturbed state to a perturbed one (regardless of the number of perturbations) a martingale framework has been used. The changes have been detected by testing exchangeability with two different martingales: randomized power martingale and simple mixture martingale. Neither false alarms nor missed alarms have been observed with the former one and the average delay in the change recognition is between 16 and 72 samples (depending on cases). This means between 16 and 72 ms if the sampling period is 1 ms (it should be noted that the discharge length in ITER will be 50 min).

Keywords

Venn predictors Conformal predictors Context drift detection Nuclear fusion diagnostics 

Mathematics Subject Classification (2010)

62–07 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Granetz, R.S., Smeulders, P.: X-ray tomography on JET. Nucl. Fusion 28(3), 457–476 (1988)CrossRefGoogle Scholar
  2. 2.
    Navarro, A.P., Ochando, M.A., Weller, A.: Equilibrium-based iterative tomography technique for soft x-ray in stellarators. IEEE Trans. Plasma Sci. 19(4), 569–579 (1991)CrossRefGoogle Scholar
  3. 3.
    Holland, A., Navratil, G.A.: Tomographic analysis of the evolution of plasma cross-sections. Rev. Sci. Instrum. 57(8), 1557–1566 (1986)CrossRefGoogle Scholar
  4. 4.
    Navarro, A.P., Paré, V.K., Dunlap, J.L.: Two-dimensional spatial distribution of volumen emission from line integral data. Rev. Sci. Instrum. 52(11), 1634–1643 (1981)CrossRefGoogle Scholar
  5. 5.
    Vega, J., Murari, A., González, S., Pereira, A., Pastor, I.: Spatial location of local perturbations in plasma emissivity derived from projections using conformal predictors. Nucl. Inst. Methods Phys. Res. A (2013). doi: 10.1016/j.nima.2012.12.046
  6. 6.
    Shafer, G., Vovk, V.: A tutorial on conformal prediction. J. Mach. Learn. Res. 9, 371–421 (2008)zbMATHMathSciNetGoogle Scholar
  7. 7.
    Vovk, V., Gammerman, A., Shafer, G.: Algorithmic Learning in a Random World. Springer, New York (2005)zbMATHGoogle Scholar
  8. 8.
    Li, F., Wechsler, H.: Open set face recognition using transduction. IEEE Trans. Pattern Anal. Mach. Intell. 27(11), 1686–1697 (2005)CrossRefGoogle Scholar
  9. 9.
    Gammerman, A., Nouretdinov, I., Burford, B., Chervonenkis, A., Vovk, V., Luo, Z.: Clinical mass spectrometry proteomic diagnosis by conformal predictors. Stat. Appl. Genet. Mol. Biol. 7(2), Article13 (2008)MathSciNetGoogle Scholar
  10. 10.
    Lambrou, A., Papadopoulos, H., Gammerman, A.: Reliable confidence measures for medical diagnosis with evolutionary algorithms. IEEE Trans. Inf. Technol. Biomed. 15(1), 93–99 (2001)CrossRefGoogle Scholar
  11. 11.
    Balasubramanian, V.N., Gouripeddi, R., Panchanathan, S., Vermillion, J., Bhaskaran, A., Siegel, R.M.: Support vector machine based conformal predictors for risk of complications following a coronary Drug Eluting Stent procedure. Comput. Cardiol. 5–8 (2009)Google Scholar
  12. 12.
    Nouretdinov, I., Costafreda, S.G., Gammerman, A., Chervonenkis, A., Vovk, V., Vapnik, V., Fu, C.H.Y.: Machine learning classification with confidence: application of transductive conformal predictors to MRI-based diagnostic and prognostic markers in depression. NeuroImage 56(2), 809–813 (2011)CrossRefGoogle Scholar
  13. 13.
    Vega, J., Murari, A., Pereira, A., González, S., Pastor, I.: Accurate and reliable image classification by using conformal predictors in the TJ-II Thomson Scattering. Rev. Sci. Instrum. 81(10E118), 4 (2010)Google Scholar
  14. 14.
    Makili, L., Vega, J., Dormido-Canto, S.: Incremental support vector machines for fast reliable image recognition. Fusion Eng. Des. 88, 1170–1173 (2013)CrossRefGoogle Scholar
  15. 15.
    Papadopoulos, H.: Reliable probabilistic classification with neural networks. Neurocomputing 107, 59–68 (2013)CrossRefGoogle Scholar
  16. 16.
    Lambrou, A., Papadopoulos, H., Nouretdinov, I., Gammerman, A.: Reliable probability estimates based on support vector machines for large multiclass datasets. In: AIAI 2012 Workshops, IFIP AICT 382, pp. 182–191. Springer (2012)Google Scholar
  17. 17.
    Nouretdinov, I., Devetyarov, D., Burford, B., Camuzeaux, S., Gentry-Maharaj, A., Tiss, A., et al.: Multiprobabilistic Venn predictors with logistic regression. In: AIAI 2012 Workshops, IFIP AICT 382, pp. 224–233. Springer (2012)Google Scholar
  18. 18.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley-Interscience (2001)Google Scholar
  19. 19.
    Martinez, W.L., Martinez, A.R.: Computational Statistics Handbook with MATLAB. Chapman & Hall/CRC, London (2002)Google Scholar
  20. 20.
    Doob, J.L.: Classical Potential Theory and Its Probabilistic Counterpart. Springer, Berlin (2001)zbMATHCrossRefGoogle Scholar
  21. 21.
    Ho, S.S., Wechsler, H.: A martingale framework for detecting changes in data streams by testing exchangeability. IEEE Trans. Pattern Anal. Mach. Intell. 32(12), 2113–2127 (2010)CrossRefGoogle Scholar
  22. 22.
    Vovk, V., Nouretdinov, I., Gammerman, A.: Testing exchangeability on-line. In: Fawcett, T., Mishra, N. (eds.) Proceedings 20th International Conference Machine Learning, pp. 768–775. (2003)Google Scholar
  23. 23.
    Ho, S.S., Wechsler, H.: Detecting changes in unlabeled data streams using martingale. In: Veloso, M. (ed.)Proceedings 20th International Joint Conference Artificial Intelligence, pp. 1912–1917. (2007)Google Scholar
  24. 24.
    Fedorova, V., Gammerman, A., Nouretdinov, I., Vovk, V.: Plug-in martingales for testing exchangeability on-line. In: Proceedings of the 29th International Conference on Machine Learning. Edinburgh (2012)Google Scholar

Copyright information

© European Atomic Energy Community 2014

Authors and Affiliations

  1. 1.Asociación EURATOM/CIEMAT para FusiónMadridSpain
  2. 2.Consorzio RFX, Associazione EURATOM/ENEA per la FusionePaduaItaly
  3. 3.Universidad Nacional de Educación a Distancia (UNED)MadridSpain

Personalised recommendations