A comparison between a neural network and the likelihood method to evaluate the performance of the a transition radiation detector

A classification system able to evaluate the performances of a transition radiation detector prototype for electrons/hadrons discrimination is presented. It is based both on a layered feed-forward neural network trained using back-propagation and a likelihood ratio technique. The information fed into the classification system consists of the number of hits detected by each multiwires proportional chamber of the detector. The best results are obtained by the neural network approach that successfully identifies 4.0 GeV/c electrons with an hadron contamination of about 4 x 10(-3) at 98% acceptance efficiency.