Artificial neural network as an effective tool to calculate parameters of positron annihilation lifetime spectra

The paper presents the application of multi-layer perceptron regressor model for predicting parameters positron annihilation lifetime spectra using example alkanes in solid phase. Good agreement calculation results was found when approach is compared with commonly used methods, e.g., LT. presented method can be as an alternative quick and accurate tool decomposition spectroscopy (PALS) general. advantages disadvantages this new are discussed. We show preliminary where trained network give better outcomes than yielded by programs based on analysis a single PALS spectrum.