The detectors used in the TS93 balloon flight produced a large volume of information for each cosmic ray trigger. Some of the data was visual in nature, other portions contained energy deposition and timing information. The data sets are amenable to conventional analysis techniques but there is no assurance that conventional techniques make full use of subtle correlations and relations amongst the detector responses. With the advent of neural network technologies, particularly adept at classification of complex phenomena, it would seem appropriate to explore the utility of neural network techniques to classify particles observed with our instrument. In this paper neural network based methodology for signal/background discrimination in a cosmic ray space experiment is discussed. Results are presented for electron and positron classification in the TS93 flight data set and will be compared to conventional analyses.
Use of neural network techniques to identify cosmic ray electrons and positrons during the 1993 balloon flight of the NMSU/Wizard-TS93 instrument / Bellotti, R.; Candusso, M.; Casolino, M.; Castellano, M.; Aversa, F.; Barbiellini, G.; Basini, G.; Bocciolini, M.; Boezio, M.; Brancaccio, F. M.; Bravar, U.; Cafagna, F.; Circella, M.; Colavita, A.; De Cataldo, G.; De Marzo, C.; De Pascale, M. P.; Finetti, N.; Giglietto, N.; Golden, ; R. L., Grimani; Hof, M.; Marangelli, B.; Menn, W.; Mitchel, J. W.; Morselli, A.; Ormes, J. F.; Papini, P.; Perego, A.; Piccardi, S.; Picozza, P.; Rainó, A.; Ricci, M.; Schiavon, P.; Simon, M.; Sparvoli, R.; Spillantini, P.; Spinelli, P.; Stephens, S. A.; Stochaj, S. J.; Streitmatter, R. E.; Vacchi, A.; Zampa, N.. - STAMPA. - (1995), pp. 730-733. (Intervento presentato al convegno 24th International Cosmic Ray Conference, XXIV ICRC tenutosi a Roma, Italy nel August 28 - September 8, 1995).
Use of neural network techniques to identify cosmic ray electrons and positrons during the 1993 balloon flight of the NMSU/Wizard-TS93 instrument
Castellano, M.;Giglietto, N.;
1995-01-01
Abstract
The detectors used in the TS93 balloon flight produced a large volume of information for each cosmic ray trigger. Some of the data was visual in nature, other portions contained energy deposition and timing information. The data sets are amenable to conventional analysis techniques but there is no assurance that conventional techniques make full use of subtle correlations and relations amongst the detector responses. With the advent of neural network technologies, particularly adept at classification of complex phenomena, it would seem appropriate to explore the utility of neural network techniques to classify particles observed with our instrument. In this paper neural network based methodology for signal/background discrimination in a cosmic ray space experiment is discussed. Results are presented for electron and positron classification in the TS93 flight data set and will be compared to conventional analyses.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
