R. Bellotti et al., A NEURAL-NETWORK FOR POSITRON IDENTIFICATION BY TRANSITION RADIATION DETECTOR, Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment, 350(3), 1994, pp. 556-560
A neural network algorithm has been applied in order to distinguish po
sitrons from protons by a transition radiation detector (TRD). New var
iables are introduced, that simultaneously take into account spatial a
nd energy TRD information. This method is found to be better than the
one based on classical analysis: the results improve the detector perf
ormance in particle identification for efficiency higher than 90%. The
high accuracy achieved with this method is used to identify positrons
versus protons with 3 x 10(-3) contamination, as required by TRAMP-SI
cosmic ray space experiment on the NASA Balloon-Borne Magnet Facility
.