Application of artificial neural networks for the rapid classification of archaeological ceramics by means of laser induced breakdown spectroscopy (LIBS)

The aim of this work is to analyze the feasibility of artificial neural networks (ANN) for the classification, in function of the provenance, of archaeological ceramics Terra Sigillata analyzed by means of laser-induced breakdown spectroscopy (LIBS). In order to automate and facilitate the task of comparison of LIBS spectra, two ANN algorithms are proposed: One is fed with the whole LIBS spectra and the other with the areas of the most intense peaks of the spectra. In both cases, an analysis of the network architecture as a function of the number of hidden neurons and number of epochs of training was carried out in order to optimize the performance of the network. Following both procedures, the correct classification (higher than the 95% of success) of Terra Sigillata pieces from their LIBS spectra can be achieved in a systematic and objective way.