Optimization of a neural network model for signal-to-background prediction in gamma-ray spectrometry
Само за регистроване кориснике
2004
Конференцијски прилог (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
The artificial neural network (ANN) model was optimized for the prediction of signal-tobackground (SBR) ratio as a function of the measurement time in gamma-ray
spectrometry. The network parameters: learning rate (α), momentum (µ), number of
epochs (E) and number of nodes in hidden layer (N) were optimized simultaneously
employing variable-size simplex method. The most accurate model with the root mean
square (RMS) error of 0.073 was obtained using ANN with online backpropagation
randomized (OBPR) algorithm with α = 0.27, µ = 0.36, E = 14800 and N = 9. Most of the
predicted and experimental SBR values for the eight radionuclides (226Ra, 214Bi, 235U, 40K, 232Th, 134Cs, 137Cs and 7
Be), studied in this work, reasonably agreed to within 15 %, which
was satisfactory accurace.
Кључне речи:
ANN / radionuclides / soil / measurement timeИзвор:
Proceedings / 5th International Yugoslav Nuclear Society Conference (YUNSC-2004), Belgrade, September 27-30, 2004, 2004, 301-304Издавач:
- Belgrade : Vinča Institute of Nuclear Sciences
Институција/група
Tehnološko-metalurški fakultetTY - CONF AU - Dragović, Snežana AU - Onjia, Antonije PY - 2004 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/7192 AB - The artificial neural network (ANN) model was optimized for the prediction of signal-tobackground (SBR) ratio as a function of the measurement time in gamma-ray spectrometry. The network parameters: learning rate (α), momentum (µ), number of epochs (E) and number of nodes in hidden layer (N) were optimized simultaneously employing variable-size simplex method. The most accurate model with the root mean square (RMS) error of 0.073 was obtained using ANN with online backpropagation randomized (OBPR) algorithm with α = 0.27, µ = 0.36, E = 14800 and N = 9. Most of the predicted and experimental SBR values for the eight radionuclides (226Ra, 214Bi, 235U, 40K, 232Th, 134Cs, 137Cs and 7 Be), studied in this work, reasonably agreed to within 15 %, which was satisfactory accurace. PB - Belgrade : Vinča Institute of Nuclear Sciences C3 - Proceedings / 5th International Yugoslav Nuclear Society Conference (YUNSC-2004), Belgrade, September 27-30, 2004 T1 - Optimization of a neural network model for signal-to-background prediction in gamma-ray spectrometry EP - 304 SP - 301 UR - https://hdl.handle.net/21.15107/rcub_technorep_7192 ER -
@conference{ author = "Dragović, Snežana and Onjia, Antonije", year = "2004", abstract = "The artificial neural network (ANN) model was optimized for the prediction of signal-tobackground (SBR) ratio as a function of the measurement time in gamma-ray spectrometry. The network parameters: learning rate (α), momentum (µ), number of epochs (E) and number of nodes in hidden layer (N) were optimized simultaneously employing variable-size simplex method. The most accurate model with the root mean square (RMS) error of 0.073 was obtained using ANN with online backpropagation randomized (OBPR) algorithm with α = 0.27, µ = 0.36, E = 14800 and N = 9. Most of the predicted and experimental SBR values for the eight radionuclides (226Ra, 214Bi, 235U, 40K, 232Th, 134Cs, 137Cs and 7 Be), studied in this work, reasonably agreed to within 15 %, which was satisfactory accurace.", publisher = "Belgrade : Vinča Institute of Nuclear Sciences", journal = "Proceedings / 5th International Yugoslav Nuclear Society Conference (YUNSC-2004), Belgrade, September 27-30, 2004", title = "Optimization of a neural network model for signal-to-background prediction in gamma-ray spectrometry", pages = "304-301", url = "https://hdl.handle.net/21.15107/rcub_technorep_7192" }
Dragović, S.,& Onjia, A.. (2004). Optimization of a neural network model for signal-to-background prediction in gamma-ray spectrometry. in Proceedings / 5th International Yugoslav Nuclear Society Conference (YUNSC-2004), Belgrade, September 27-30, 2004 Belgrade : Vinča Institute of Nuclear Sciences., 301-304. https://hdl.handle.net/21.15107/rcub_technorep_7192
Dragović S, Onjia A. Optimization of a neural network model for signal-to-background prediction in gamma-ray spectrometry. in Proceedings / 5th International Yugoslav Nuclear Society Conference (YUNSC-2004), Belgrade, September 27-30, 2004. 2004;:301-304. https://hdl.handle.net/21.15107/rcub_technorep_7192 .
Dragović, Snežana, Onjia, Antonije, "Optimization of a neural network model for signal-to-background prediction in gamma-ray spectrometry" in Proceedings / 5th International Yugoslav Nuclear Society Conference (YUNSC-2004), Belgrade, September 27-30, 2004 (2004):301-304, https://hdl.handle.net/21.15107/rcub_technorep_7192 .