Comparison of training algorithms in neural network modeling of gamma spectrometric uncertainty

dc.creator	Dragović, Snežana
dc.creator	Stanković, Slavka
dc.creator	Onjia, Antonije
dc.date.accessioned	2024-02-14T13:55:31Z
dc.date.available	2024-02-14T13:55:31Z
dc.date.issued	2004
dc.identifier.isbn	86-82475-12-X
dc.identifier.uri	http://TechnoRep.tmf.bg.ac.rs/handle/123456789/7235
dc.description.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, 238 U, 235 U, 40K, 232 Th, 134 Cs, 137 Cs and 7 Be) 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 7 Be to 0.9915 for 137 Cs.	sr
dc.language.iso	en	sr
dc.publisher	Belgrade : The Society of Physical Chemists of Serbia	sr
dc.rights	restrictedAccess	sr
dc.source	Physical Chemistry 2004 : proceedings of the 7th International Conference on Fundamental and Applied Aspects of Physical Chemistry, September 21-23, 2004, Belgrade	sr
dc.title	Comparison of training algorithms in neural network modeling of gamma spectrometric uncertainty	sr
dc.type	conferenceObject	sr
dc.rights.license	ARR	sr
dc.citation.epage	440
dc.citation.spage	438
dc.identifier.rcub	https://hdl.handle.net/21.15107/rcub_technorep_7235
dc.type.version	publishedVersion	sr