A neural system for radiation discrimination in nuclear fusion applications

This work presents an approach to discriminate between neutrons and γ-rays in nuclear fusion applications, based on a neural network able to analyze the shape of light pulses produced by these ionizing particles in an organic liquid scintillator. Such an approach is particularly promising especially for the possibility of classifying correctly (either as neutrons or as γ-rays) fast superimposed events (pile-ups). Satisfactory experimental results were obtained at the Frascati Tokamak Upgrade, ENEA-Frascati, Italy.