Detector Optimization Based on Artificial Neural Network Training

Artificial neural networks were used for event-wise analysis of model data for a microchannel plate detector. Based on this data, the impact parameter and the collision point coordinates for each event were estimated. An analysis based on several Monte-Carlo collision models was performed. Even though the quality of the existing models of events is not sufficient for a reliable, model-independent estimation of the collision parameters, the proposed method of parameter reconstruction allows one to estimate the optimal technical characteristics of the detector.