Comparison of training algorithms in neural network modeling of gamma spectrometric uncertainty
2004
Download 🢃
Conference object (Published version)
,
Society of Physical Chemists of Serbia
Metadata
Show full item recordAbstract
A three-layer feed-forward artificial neural network with six different algorithms applied on different training sets was used to model uncertainties of activity levels of eight radionuclides (226Ra, 238U, 235U, 40K, 232Th, 134Cs, 137Cs and 7Be) in soil samples as a function of measurement time. The performance of applied neural network architecture is found to be very good, with correlation (R2) values between measured and predicted uncertainties ranging from 0.9291 for 7Be to 0.9915 for 137Cs.
Source:
Physical chemistry 2004: 7th international conference on fundemental and applied aspract of physical chemistry, 2004, 1, 438-440Publisher:
- Society of Physical Chemists of Serbia
Note:
- Physical chemistry 2004 : 7th international conference on fundamental and applied aspects of physical chemistry; Belgrade (Serbia); 21-23 September 2004
Collections
Institution/Community
VinčaTY - CONF AU - Dragović, Snežana D. AU - Stanković, Slavka AU - Onjia, Antonije E. PY - 2004 UR - https://vinar.vin.bg.ac.rs/handle/123456789/9510 AB - A three-layer feed-forward artificial neural network with six different algorithms applied on different training sets was used to model uncertainties of activity levels of eight radionuclides (226Ra, 238U, 235U, 40K, 232Th, 134Cs, 137Cs and 7Be) in soil samples as a function of measurement time. The performance of applied neural network architecture is found to be very good, with correlation (R2) values between measured and predicted uncertainties ranging from 0.9291 for 7Be to 0.9915 for 137Cs. PB - Society of Physical Chemists of Serbia C3 - Physical chemistry 2004: 7th international conference on fundemental and applied aspract of physical chemistry T1 - Comparison of training algorithms in neural network modeling of gamma spectrometric uncertainty VL - 1 SP - 438 EP - 440 UR - https://hdl.handle.net/21.15107/rcub_vinar_9510 ER -
@conference{ author = "Dragović, Snežana D. and Stanković, Slavka and Onjia, Antonije E.", year = "2004", abstract = "A three-layer feed-forward artificial neural network with six different algorithms applied on different training sets was used to model uncertainties of activity levels of eight radionuclides (226Ra, 238U, 235U, 40K, 232Th, 134Cs, 137Cs and 7Be) in soil samples as a function of measurement time. The performance of applied neural network architecture is found to be very good, with correlation (R2) values between measured and predicted uncertainties ranging from 0.9291 for 7Be to 0.9915 for 137Cs.", publisher = "Society of Physical Chemists of Serbia", journal = "Physical chemistry 2004: 7th international conference on fundemental and applied aspract of physical chemistry", title = "Comparison of training algorithms in neural network modeling of gamma spectrometric uncertainty", volume = "1", pages = "438-440", url = "https://hdl.handle.net/21.15107/rcub_vinar_9510" }
Dragović, S. D., Stanković, S.,& Onjia, A. E.. (2004). Comparison of training algorithms in neural network modeling of gamma spectrometric uncertainty. in Physical chemistry 2004: 7th international conference on fundemental and applied aspract of physical chemistry Society of Physical Chemists of Serbia., 1, 438-440. https://hdl.handle.net/21.15107/rcub_vinar_9510
Dragović SD, Stanković S, Onjia AE. Comparison of training algorithms in neural network modeling of gamma spectrometric uncertainty. in Physical chemistry 2004: 7th international conference on fundemental and applied aspract of physical chemistry. 2004;1:438-440. https://hdl.handle.net/21.15107/rcub_vinar_9510 .
Dragović, Snežana D., Stanković, Slavka, Onjia, Antonije E., "Comparison of training algorithms in neural network modeling of gamma spectrometric uncertainty" in Physical chemistry 2004: 7th international conference on fundemental and applied aspract of physical chemistry, 1 (2004):438-440, https://hdl.handle.net/21.15107/rcub_vinar_9510 .