An artificial neural network based neutron-gamma discrimination and pile-up rejection framework for the BC-501 liquid scintillation detector

BC-501 is a liquid scintillation detector sensitive to both neutrons and gamma rays. As these produce slightly different signals in the detector, they can be discriminated based on their pulse shape (Pulse Shape Discrimination, PSD). This paper reports on results obtained with several PSD techniques and compares them with a method based on artificial neural networks (NN) developed for this application. Results indicated a large performance advantage of NN especially in the region of small deposited energy which typically contains the majority of the events. NN were also applied for discrimination of pile-up events with good results. This framework can be implemented on some of the most recent programmable data acquisition cards and it is suitable for real-time application. (C) 2009 Elsevier B.V. All rights reserved.