|
This article is cited in 2 scientific papers (total in 2 papers)
Computational methods and algorithms
Neural network applications for improved treatment of the EXCHARM experiment
G. A. Ososkov, V. V. Palichik, Yu. K. Potrebennikov, G. T. Tatishvili, V. B. Shepelev Joint Institute for Nuclear Research
Abstract:
The charged particles track recognition method based on Denby–Peterson segment model
(DPSM) for Hopfield full-connected artificial neural network (ANN) is developed for
handling of the EXCHARM experimental data. The specifics of the EXCHARM experiment
(heavy background conditions, effects related to inefficiency of chambers and presence of
secondary vertices) required the essential modification of the DPSM. The results of testing
show that our modified ANN scheme has higher recognition efficiency than the current
version of EXCHARM data processing software, but yields it in speed. The basic difference
between two algorithms results in a small intersection of sets of badly recognized events.
It gave us a possibility to create a combined event reconstruction algorithm based on the
both current data processing program for majority of events and the ANN program for more
complicated events. The combined approach allows to achieve 99% of event recognition
efficiency in real conditions.
Received: 07.10.1998
Citation:
G. A. Ososkov, V. V. Palichik, Yu. K. Potrebennikov, G. T. Tatishvili, V. B. Shepelev, “Neural network applications for improved treatment of the EXCHARM experiment”, Matem. Mod., 11:10 (1999), 116–126
Linking options:
https://www.mathnet.ru/eng/mm1177 https://www.mathnet.ru/eng/mm/v11/i10/p116
|
Statistics & downloads: |
Abstract page: | 455 | Full-text PDF : | 243 | First page: | 1 |
|