DMCA
¸¸μÉ·¥ ´ § ¤ Î ¨¤¥´É¨Ë¨ ± ͨ ¨ Ô¥±É·μ´μ¢/¶¨μ´μ ¢ ¢ Ô±¸¶¥·¨¥´É ¥ ‘‚Œ ´ μ¸´μ¢ ¥ ¨μ´¨ § Í¨μ´´ÒÌ ¶μÉ¥·Ó Ô´¥·£¨ ¨ ¨ ¶¥·¥Ìμ¤´μ£μ ¨§ÊÎ¥´¨Ö ¢ ¤¥É¥±Éμ·¥
BibTeX
@MISC{Akishina_ ¸¸μé·¥,
author = {E. P. Akishina and T. P. Akishina and V. V. Ivanov and A. I. Maevskaya and O. A. Afanas'ev and Using A Multilayer Perceptron},
title = { ¸¸μÉ·¥ ´ § ¤ Î ¨¤¥´É¨Ë¨ ± ͨ ¨ Ô¥±É·μ´μ¢/¶¨μ´μ ¢ ¢ Ô±¸¶¥·¨¥´É ¥ ‘‚Œ ´ μ¸´μ¢ ¥ ¨μ´¨ § Í¨μ´´ÒÌ ¶μÉ¥·Ó Ô´¥·£¨ ¨ ¨ ¶¥·¥Ìμ¤´μ£μ ¨§ÊÎ¥´¨Ö ¢ ¤¥É¥±Éμ·¥},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Akishina E. P. et al. E10-2007-17 Electron/Pion Identiˇcation in the CBM TRD Using a Multilayer Perceptron The problem of electron/pion identiˇcation in the CBM experiment based on the measurements of energy losses and transition radiation in the TRD detector is discussed. We consider a possibility to solve such a problem by applying an artiˇcial neural network (ANN). As input information for the network we used both the samples of energy losses of pions or electrons in the TRD absorbers and the ®clever ¯ variable obtained on the basis of the original data. We show that usage of this new variable permits one to reach a reliable level of particle recognition no longer than after 10Ä20 training epochs; there are practically no uctuations against the trend, and the needed level of pions suppression is obtained under the condition of a minimal loss of electrons. The investigation has been performed at the Laboratory of Information Tech-nologies, JINR.
Keyphrases
energy loss particle recognition information tech-nologies e10-2007-17 electron pion identi cation transition radiation multilayer perceptron reliable level input information trd absorber original data cbm experiment cbm trd training epoch minimal loss needed level pion suppression trd detector electron pion identi cation arti cial neural network
