Nowadays, processing all information of a fusion database is a much more important issue than acquiring more data. Although typically fusion devices produce tens of thousands of discharges, specialized databases for physics studies are normally limited to a few tens of shots. This is due to the fact that these databases are almost always generated manually, which is a very time consuming and unreliable activity. The development of automatic methods to create specialized databases ensures first, the reduction of human efforts to identify and locate physical events, second, the standardization of criteria (reducing the vulnerability to human errors) and, third, the improvement of statistical relevance. Classification and regression techniques have been used for these purposes. The objective has been the automatic recognition of physical events (that can appear in a random and/or infrequent way) in waveforms and video-movies. Results are shown for the JET database. © 2009 EURATOM. Published by Elsevier B.V. All rights reserved.
All Science Journal Classification (ASJC) codes
- Civil and Structural Engineering
- Nuclear Energy and Engineering
- Materials Science(all)
- Mechanical Engineering
Vega, J., Murari, A., Rattá, G. A., González, S., & Dormido-Canto, S. (2010). Progress on statistical learning systems as data mining tools for the creation of automatic databases in Fusion environments. Fusion Engineering and Design, 85(3-4), 399 - 402. https://doi.org/10.1016/j.fusengdes.2009.10.011