Neural network-random generation approach to analyze X-ray fluorescence spectra

Article type: Research Article

Authors: Askri, Boubaker^{a; b}

Affiliations: [a] Department of Physics, College of Science, Qassim University, Buraidah, KSA | [b] Research Unit of Nuclear and High Energy Physics, Faculty of Sciences of Tunis, University of Tunis, Tunis, Tunisia. E-mail: askrib@gmail.com

Abstract: Application of a feed-forward multilayer perceptron neural network to analyze X-ray fluorescence spectra of a compound material is investigated. For this purpose, a general approach is proposed to improve the learning process of the neural network. In this approach, randomly generated composite spectra are constructed from the set of reference spectra corresponding to the pure elements which compose the material. Instead of taking the spectrum as a whole, the input parameters of the neural network arereduced to the neighboring bins of each pure element peak. Bytesting themethodon the spectra of materials made of Ca, Fe, Ni and Cu elements, we obtained an efficiency of about 95% for predicting the relative concentrations of the four elements in the material.

Keywords: Artificial neural networks, XRF spectroscopy, multilayer perceptron, root, random generation

DOI: 10.3233/JCM-150590

Journal: Journal of Computational Methods in Sciences and Engineering, vol. 16, no. 1, pp. 167-174, 2016