Evaluation of the suitability of neural network method for prediction of uranium activity ratio in environmental alpha spectra
| Autor: | Reza Ghaderi, Mohammad Reza Einian, Seyed Mahmood Reza Aghamiri |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Radiation
Artificial neural network Alpha spectrometry Computer science Spectrum Analysis chemistry.chemical_element Uranium Alpha Particles computer.software_genre Spectral line Alpha (programming language) chemistry Humans Environmental Pollutants Neural Networks Computer Data mining Biological system Monte Carlo Method computer Radioactive Pollutants |
| Zdroj: | Applied Radiation and Isotopes. 105:225-232 |
| ISSN: | 0969-8043 |
| Popis: | 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 234U/238U 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect