S. Bagherzadeh-Atashchi, N. Ghal-Eh, F. Rahmani, R. Izadi-Najafabadi, S. V. Bedenko, C. H. Ordoñez
{"title":"Application of TENIS and artificial neural networks in neutron spectroscopy for BNCT beams in IRT-T and TRR: additional research","authors":"S. Bagherzadeh-Atashchi, N. Ghal-Eh, F. Rahmani, R. Izadi-Najafabadi, S. V. Bedenko, C. H. Ordoñez","doi":"10.1140/epjp/s13360-025-06813-z","DOIUrl":null,"url":null,"abstract":"<div><p>Following the successful results of the ThErmal Neutron Imaging System (TENIS) for mono- and poly-energetic neutron sources, in this research, real-time data obtained from the TENIS were utilized for neutron spectroscopy at the exits of the Beam Shaping Assemblies (BSAs) located at the beam ports of Tomsk Polytechnic University Research Reactor (IRT-T) and Tehran Research Reactor (TRR). To achieve this purpose, 70-pixel thermal neutron images were generated for 109 mono-energetic neutrons, referred to as the neutron fluence response matrix, using the MCNP6.1 code. These images were used as the input of the artificial neural network (ANN) tools in MATLAB. Results indicated that the sigmoid transfer function in both hidden and output layers gives the best correlation between the predicted and actual spectra of Boron Neutron Capture Therapy (BNCT) beam lines in IRT-T and TRR, with correlation coefficients (R<sup>2</sup>) of 0.74 and 0.86, and root-mean-square error of 0.020 and 0.014, respectively (<i>i.e.</i>, a max–min problem). The results suggest that the ANN-unfolded TENIS results can also accurately predict the energy spectrum of neutrons suitable for the BNCT.</p></div>","PeriodicalId":792,"journal":{"name":"The European Physical Journal Plus","volume":"140 9","pages":""},"PeriodicalIF":2.9000,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The European Physical Journal Plus","FirstCategoryId":"4","ListUrlMain":"https://link.springer.com/article/10.1140/epjp/s13360-025-06813-z","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Following the successful results of the ThErmal Neutron Imaging System (TENIS) for mono- and poly-energetic neutron sources, in this research, real-time data obtained from the TENIS were utilized for neutron spectroscopy at the exits of the Beam Shaping Assemblies (BSAs) located at the beam ports of Tomsk Polytechnic University Research Reactor (IRT-T) and Tehran Research Reactor (TRR). To achieve this purpose, 70-pixel thermal neutron images were generated for 109 mono-energetic neutrons, referred to as the neutron fluence response matrix, using the MCNP6.1 code. These images were used as the input of the artificial neural network (ANN) tools in MATLAB. Results indicated that the sigmoid transfer function in both hidden and output layers gives the best correlation between the predicted and actual spectra of Boron Neutron Capture Therapy (BNCT) beam lines in IRT-T and TRR, with correlation coefficients (R2) of 0.74 and 0.86, and root-mean-square error of 0.020 and 0.014, respectively (i.e., a max–min problem). The results suggest that the ANN-unfolded TENIS results can also accurately predict the energy spectrum of neutrons suitable for the BNCT.
期刊介绍:
The aims of this peer-reviewed online journal are to distribute and archive all relevant material required to document, assess, validate and reconstruct in detail the body of knowledge in the physical and related sciences.
The scope of EPJ Plus encompasses a broad landscape of fields and disciplines in the physical and related sciences - such as covered by the topical EPJ journals and with the explicit addition of geophysics, astrophysics, general relativity and cosmology, mathematical and quantum physics, classical and fluid mechanics, accelerator and medical physics, as well as physics techniques applied to any other topics, including energy, environment and cultural heritage.