Pulse shape discrimination of neutrons and gamma rays using kohonen artificial neural networks

Abstract

The potential of two Kohonen artificial neural networks (ANNs) - linear vector quantization (LVQ) and the self organising map (SOM) - is explored for pulse shape discrimination (PSD), i.e. for distinguishing between neutrons (n's) and gamma rays (γ's). The effect that (a) the energy level, and (b) the relative size of the training and test sets, have on identification accuracy is also evaluated on the given PSD dataset. The two Kohonen ANNs demonstrate complementary discrimination ability on the training and test sets: while the LVQ is consistently more accurate on classifying the training set, the SOM exhibits higher n/γ identification rates when classifying new patterns regardless of the proportion of training and test set patterns at the different energy levels; the average time for decision making equals 100 μs in the case of the LVQ and ∼450 μs in the case of the SOM.