Evaluation of the suitability of neural network method for prediction of uranium activity ratio in environmental alpha spectra.
Journal:
Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine
PMID:
26340268
Abstract
Applying Artificial Neural Network to an alpha spectrometry system is a good idea to discriminate the composition of environmental and non-environmental materials by the estimation of the (234)U/(238)U activity ratio. Because it eliminates limitations of classical approaches by the extraction the desired information from the average of a partial uranium raw spectrum. The network was trained by an alpha spectrum library which was developed in this work. The results indicated that there was a small difference between the target values and the predictions. These results were acceptable, because the thickness of samples and the inferring elements were different in the real library.