Structural pattern recognition techniques for data retrieval in massive fusion databases

J. Vega, A. Murari, G.A. Rattá, P. Castro, A. Pereira, A. Portas

Research output: Contribution to conferencePaper

2 Citations (Scopus)


Diagnostics of present day reactor class fusion experiments, like the Joint European Torus (JET), generate thousands of signals (time series and video images) in each discharge. There is a direct correspondence between the physical phenomena taking place in the plasma and the set of structural shapes (patterns) that they form in the signals: bumps, unexpected amplitude changes, abrupt peaks, periodic components, high intensity zones or specific edge contours. A major difficulty related to data analysis is the identification, in a rapid and automated way, of a set of discharges with comparable behavior, i.e. discharges with "similar" patterns. Pattern recognition techniques are efficient tools to search for similar structural forms within the database in a fast an intelligent way. To this end, classification systems must be developed to be used as indexation methods to directly fetch the more similar patterns. © 2008 American Institute of Physics.
Original languageEnglish
Publication statusPublished - 2008
Externally publishedYes
EventInternational Conference on Burning Plasma Diagnostics - , Italy
Duration: 1 Jan 2008 → …


ConferenceInternational Conference on Burning Plasma Diagnostics
Period1/1/08 → …


All Science Journal Classification (ASJC) codes

  • Physics and Astronomy(all)

Cite this

Vega, J., Murari, A., Rattá, G. A., Castro, P., Pereira, A., & Portas, A. (2008). Structural pattern recognition techniques for data retrieval in massive fusion databases. Paper presented at International Conference on Burning Plasma Diagnostics, Italy.