Pattern recognition in position sensitive γ-ray detectors

The NASA/ESA International Gamma-Ray Astrophysics Laboratory (INTEGRAL) γ-ray telescope satellite will use novel 3-dimensional readout position detectors and energy sensitive photon detectors. Their complexity means that significantly more raw data are generated than can be sent by conventional telemetry channels from satellite to Earth ground stations. The authors present the preliminary results of using an artificial neural network, specifically a multi-level perceptron, to reject unwanted background events and select detector events with a `good´ signature for further processing; thus improving instrument signal to noise ratio. The authors believe that the success of this technique will extend to event pre-processing in high energy physics experiments at particle accelerators and also in the design of event selection systems for positron emission tomography