Artificial neural network modelling of uncertainty in gamma-ray spectrometry
Samo za registrovane korisnike
2005
Članak u časopisu (Objavljena verzija)
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
An artificial neural network (ANN) model for the prediction of measuring uncertainties in gamma-ray spectrometry was developed and optimized. A three-layer feed-forward ANN with back-propagation learning algorithm was used to model uncertainties of measurement of activity levels of eight radionuclides (Ra-226, U-238, U-235, K-40, Th-232, Cs-134, Cs-137 and Be-7) in soil samples as a function of measurement time. It was shown that the neural network provides useful data even from small experimental databases. The performance of the optimized neural network was found to be very good, with correlation coefficients (R-2) between measured and predicted uncertainties ranging from 0.9050 to 0.9915. The correlation coefficients did not significantly deteriorate when the network was tested on samples with greatly different uranium-to-thorium (U-238/Th-232) ratios. The differences between measured and predicted uncertainties were not influenced by the absolute values of uncertainties of measured... radionuclide activities. Once the ANN is trained, it could be employed in analyzing soil samples regardless of the U-238/Th-232 ratio. It was concluded that a considerable saving in time could be obtained using the trained neural network model for predicting the measurement times needed to attain the desired statistical accuracy.
Ključne reči:
ANN / radionuclides / uncertainty / measurement time / soilIzvor:
Nuclear Instruments & Methods in Physics Research Section A-Accelerators Spectrometers Detectors And, 2005, 540, 2-3, 455-463Izdavač:
- Elsevier, Amsterdam
DOI: 10.1016/j.nima.2004.11.045
ISSN: 0168-9002
WoS: 000228031400025
Scopus: 2-s2.0-17844383973
Institucija/grupa
Tehnološko-metalurški fakultetTY - JOUR AU - Dragović, Snežana D. AU - Onjia, Antonije AU - Stanković, Srboljub J. AU - Aničin, Ivan V. AU - Bacić, G PY - 2005 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/814 AB - An artificial neural network (ANN) model for the prediction of measuring uncertainties in gamma-ray spectrometry was developed and optimized. A three-layer feed-forward ANN with back-propagation learning algorithm was used to model uncertainties of measurement of activity levels of eight radionuclides (Ra-226, U-238, U-235, K-40, Th-232, Cs-134, Cs-137 and Be-7) in soil samples as a function of measurement time. It was shown that the neural network provides useful data even from small experimental databases. The performance of the optimized neural network was found to be very good, with correlation coefficients (R-2) between measured and predicted uncertainties ranging from 0.9050 to 0.9915. The correlation coefficients did not significantly deteriorate when the network was tested on samples with greatly different uranium-to-thorium (U-238/Th-232) ratios. The differences between measured and predicted uncertainties were not influenced by the absolute values of uncertainties of measured radionuclide activities. Once the ANN is trained, it could be employed in analyzing soil samples regardless of the U-238/Th-232 ratio. It was concluded that a considerable saving in time could be obtained using the trained neural network model for predicting the measurement times needed to attain the desired statistical accuracy. PB - Elsevier, Amsterdam T2 - Nuclear Instruments & Methods in Physics Research Section A-Accelerators Spectrometers Detectors And T1 - Artificial neural network modelling of uncertainty in gamma-ray spectrometry EP - 463 IS - 2-3 SP - 455 VL - 540 DO - 10.1016/j.nima.2004.11.045 ER -
@article{ author = "Dragović, Snežana D. and Onjia, Antonije and Stanković, Srboljub J. and Aničin, Ivan V. and Bacić, G", year = "2005", abstract = "An artificial neural network (ANN) model for the prediction of measuring uncertainties in gamma-ray spectrometry was developed and optimized. A three-layer feed-forward ANN with back-propagation learning algorithm was used to model uncertainties of measurement of activity levels of eight radionuclides (Ra-226, U-238, U-235, K-40, Th-232, Cs-134, Cs-137 and Be-7) in soil samples as a function of measurement time. It was shown that the neural network provides useful data even from small experimental databases. The performance of the optimized neural network was found to be very good, with correlation coefficients (R-2) between measured and predicted uncertainties ranging from 0.9050 to 0.9915. The correlation coefficients did not significantly deteriorate when the network was tested on samples with greatly different uranium-to-thorium (U-238/Th-232) ratios. The differences between measured and predicted uncertainties were not influenced by the absolute values of uncertainties of measured radionuclide activities. Once the ANN is trained, it could be employed in analyzing soil samples regardless of the U-238/Th-232 ratio. It was concluded that a considerable saving in time could be obtained using the trained neural network model for predicting the measurement times needed to attain the desired statistical accuracy.", publisher = "Elsevier, Amsterdam", journal = "Nuclear Instruments & Methods in Physics Research Section A-Accelerators Spectrometers Detectors And", title = "Artificial neural network modelling of uncertainty in gamma-ray spectrometry", pages = "463-455", number = "2-3", volume = "540", doi = "10.1016/j.nima.2004.11.045" }
Dragović, S. D., Onjia, A., Stanković, S. J., Aničin, I. V.,& Bacić, G.. (2005). Artificial neural network modelling of uncertainty in gamma-ray spectrometry. in Nuclear Instruments & Methods in Physics Research Section A-Accelerators Spectrometers Detectors And Elsevier, Amsterdam., 540(2-3), 455-463. https://doi.org/10.1016/j.nima.2004.11.045
Dragović SD, Onjia A, Stanković SJ, Aničin IV, Bacić G. Artificial neural network modelling of uncertainty in gamma-ray spectrometry. in Nuclear Instruments & Methods in Physics Research Section A-Accelerators Spectrometers Detectors And. 2005;540(2-3):455-463. doi:10.1016/j.nima.2004.11.045 .
Dragović, Snežana D., Onjia, Antonije, Stanković, Srboljub J., Aničin, Ivan V., Bacić, G, "Artificial neural network modelling of uncertainty in gamma-ray spectrometry" in Nuclear Instruments & Methods in Physics Research Section A-Accelerators Spectrometers Detectors And, 540, no. 2-3 (2005):455-463, https://doi.org/10.1016/j.nima.2004.11.045 . .