{"title":"A New Computer Tool Based on ANN Technology, Applied in Neutron Spectrometry and Dosimetry Research Areas","authors":"M.-B. Rosario, O.-R.J. Manuel, V.-C.H. Rene","doi":"10.1109/CERMA.2008.106","DOIUrl":null,"url":null,"abstract":"In the neutron spectrometry and dosimetry research areas by means of the Bonner spheres spectrometric system utilizing classical approaches, such as Montecarlo, parametrization and iterative procedures, the weight, time consuming procedure, the need to use an unfolding procedure, the low resolution spectrum, and the need to use the neutron fluence-to-dose conversion coefficients for calculating the equivalent doses are some drawbacks which these approaches offer. Each of the mentioned difficulties has motivated the development of complementary procedures such as maximum entropy, genetic algorithms and artificial neural networks. The use of neural networks to unfold neutron spectra and to calculate equivalent doses from the count rates measured with BSS system has become in an alternative procedure, which has been applied with success, however, it is observed that doesn't exist computer tools based on ANN technology to unfold neutron spectra and to calculate equivalent doses. In this work a customized front end user interface software application, called Neutron Spectrometry and Dosimetry by means of Artificial Neural Networks (NSDANN) based on ANN technology, is presented, which is capable to unfold neutron spectra and to simultaneously calculate 13 equivalent doses, by using only the count rates of a BBS system, in just a few seconds.","PeriodicalId":126172,"journal":{"name":"2008 Electronics, Robotics and Automotive Mechanics Conference (CERMA '08)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 Electronics, Robotics and Automotive Mechanics Conference (CERMA '08)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CERMA.2008.106","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
In the neutron spectrometry and dosimetry research areas by means of the Bonner spheres spectrometric system utilizing classical approaches, such as Montecarlo, parametrization and iterative procedures, the weight, time consuming procedure, the need to use an unfolding procedure, the low resolution spectrum, and the need to use the neutron fluence-to-dose conversion coefficients for calculating the equivalent doses are some drawbacks which these approaches offer. Each of the mentioned difficulties has motivated the development of complementary procedures such as maximum entropy, genetic algorithms and artificial neural networks. The use of neural networks to unfold neutron spectra and to calculate equivalent doses from the count rates measured with BSS system has become in an alternative procedure, which has been applied with success, however, it is observed that doesn't exist computer tools based on ANN technology to unfold neutron spectra and to calculate equivalent doses. In this work a customized front end user interface software application, called Neutron Spectrometry and Dosimetry by means of Artificial Neural Networks (NSDANN) based on ANN technology, is presented, which is capable to unfold neutron spectra and to simultaneously calculate 13 equivalent doses, by using only the count rates of a BBS system, in just a few seconds.