Application of an artificial neural network for evaluation of activity concentration exemption limits in NORM industry

Hannah Wiedner; Virginia Peyrés; Teresa Crespo; Marcos Mejuto; Eduardo García-Toraño; Franz Josef Maringer

doi:10.1016/j.apradiso.2016.12.044

Application of an artificial neural network for evaluation of activity concentration exemption limits in NORM industry

Appl Radiat Isot. 2017 Aug:126:289-292. doi: 10.1016/j.apradiso.2016.12.044. Epub 2016 Dec 27.

Authors

Hannah Wiedner¹, Virginia Peyrés², Teresa Crespo², Marcos Mejuto², Eduardo García-Toraño², Franz Josef Maringer¹

Affiliations

¹ BEV - Federal Office of Metrology and Surveying, Arltgasse 35, 1160 Wien, Austria.
² CIEMAT - Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas, Avda. Complutense 40, 28040 Madrid, Spain.

PMID: 28108187
DOI: 10.1016/j.apradiso.2016.12.044

Abstract

NORM emits many different gamma energies that have to be analysed by an expert. Alternatively, artificial neural networks (ANNs) can be used. These mathematical software tools can generalize "knowledge" gained from training datasets, applying it to new problems. No expert knowledge of gamma-ray spectrometry is needed by the end-user. In this work an ANN was created that is able to decide from the raw gamma-ray spectrum if the activity concentrations in a sample are above or below the exemption limits.

Keywords: ANN; Artificial neural network; Exemption limit; Gamma-spectrometry; Monte Carlo; NORM; PENELOPE; PENNUC.