Study of the possibility of using an artificial neural network to recognize and assess the contribution of individual radionuclides to the total beta spectrum
https://doi.org/10.21514/1998-426X-2020-13-4-74-81
Abstract
The aim of this work is to study the possibility of using an artificial neural network for identification and quantitative assessment of the content of individual radionuclides in the total beta spectrum. The neural network implemented by using of Matlab R2020b. A single-layer feedforward neural network with one invisible layer of 10 neurons and 3 outputs (according to the number of radionuclides) was used. To test and study the capabilities of the artificial neural network, 3 smooth model spectra were selected — 40K, 137Cs and 90Sr, obtained on the liquid spectrometer Quantulus 1220. The results of the study showed that neural networks are an effective method for recognizing of the contribution of an individual radionuclide or establishing its presence in the total beta spectrum. The recognition accuracy depends on the smoothness of the spectrum and does not exceed 30% if the share of the radionuclide in the total spectrum is more than 10%, which is quite suitable for practical use. For statistically «noising» spectra, the method can be used to preliminary estimate the weight coefficients of individual radionuclides, the final value of which can be obtained by minimization methods with subsequent statistical criterial fitting of the total spectrum shape.
About the Author
V. S. Repin
Saint-Petersburg Research Institute of Radiation Hygiene after Professor P.V. Ramzaev, Federal Service for Surveillance on Consumer Rights Protection and Human Well-Being
Russian Federation
Russian Federation
Viktor S. Repin - Doctor of Biological Sciences, Head of the Ecology Laboratory.
Mira str., 8, Saint-Petersburg, 197101References
1. Official site of the laboratory of spectrometry and radiometry (LSRM). Available from: http://www.lsrm.ru/products/detail.php?ELEMENT_CODE=spectraline_1.6/ [Accessed Nov 20, 2020] (In Russian)
2. Official site of Ltd STC [«RADEC»]. Available from: https://www.radek.ru/product/Programmnoe-obespechenie/95[Accessed Nov 20, 2020] (In Russian)
3. Official site of Ltd «Spectr». Available from: http://spectrrad.ru/ [Accessed Nov 20, 2020] (In Russian)
4. Official site of Ltd [«STC Amplituda»]. Available from: http://amplituda.ru/catalog/radiatsionnyy-kontrol/programmnoe-obespe-chenie/ [Accessed Nov 20, 2020] (In Russian)
5. Official site of the company «TALS OY». Available from: https://www.tals.eu/spectradec [Accessed Nov 20, 2020]
6. Ermakov AI, Kashirin IA, Malinovsky SV, Sobolev AI, Tikhomirov VA. Liquid в—a-spectrometry. Atomnaya ener-giya = Atomic Energy. 2002;92(1): 68-75 (In Russian)
7. Kashirin IA, Ermakov AI, Malinovsky SV, Belanov SV, Sapozhnikov YA, Efimov KM, et al. Liquid scintillation determination of low-level components in complex mixtures of ra-dlonuclides. Applied Radiation and Isotopes. 2000;53(1-2): 303-308.
8. Belanov SV, Kashirin IA, Malinovsky SV, et al. Method for identifying radlonuclides in probes using a liquid scintillation sensor. PCT № 94/30185.
9. Belanov SB, Kashirin IA, Malinovsky SV. et al. Method for the identification of radionuclides using a liquid counter. Pat. № 2120646 (priority date 08.12.97) (In Russian)
10. Methods for measuring the activity of radionuclides using a scintillation gamma spectrometer with the «Progress» software. Moscow; 2016. (In Russian)
11. Ososkov GA, Polyansky A, Puzynin IV. Modern methods of processing experimental data in high energy physics. Fizika elementarnykh chastits i atomnogo yadra = Physics of elementary particles and atomic nucleus. 2002; 33(3): 676-745 (In Russian)
12. Vakulenko SA, Zhikhareva AA. Practical course on neural networks. Saint-Petersburg: ITMO University; 2018. 71 p. (In Russian)
13. Galushkin AI. Theory of neural networks. Moscow: IPRZhR; 2000. 241 p. (In Russian)
14. Galushkin AI, Tsypkin YaZ. Neural networks: history of devel- opment. Moscow: IPRZhR; 2002. 735 p. (In Russian)
15. Gaskarov DV. Intelligent information systems. Textbook for universities. Moscow: Vysshaya shkola; 2003. 413 p. (In Russian)
16. Golovko VA. Neural networks: training, organization and application. Moscow: IPRZhR; 2001. 256 p. (In Russian)
17. Devyatkov VV. Artificial intelligence systems. Moscow: Publishing house Bauman Moscow State Technical University; 2001. 352 p. (In Russian)
18. Dzhekson P. Expert systems. Moscow: Williams Publishing House; 2001. 624 p. (In Russian)
19. Komartsova L.G., Maksimov A.V. Neurocomputers. Moscow: Publishing house Bauman Moscow State Technical University; 2004. 400 p. (In Russian)
20. Kisel IV, Neskoromnyy VN, Ososkov GA. Application of neural networks in experimental physics. EChAYa = ECHAYA. 1993;24(6): 1551-1595 (In Russian)
21. Ososkov GA, Palchik VV, Potrebennikov YuK, Tatishvili GT, Shepelev VB. Using neural networks to improve the interpretation of the EXCHARM experiment. Matematicheskoe mod-elirovanie = Mathematical modeling. 1999;11(10): 116-126 (In Russian)
22. Komashinsky VI, Smirnov DA. Neural networks and their application in control and communication systems. Moscow: Telecom hotline; 2002. 94 p. (In Russian)
23. Kirichenko AA. Neuropackages are a modern intellectual tool of the researcher. Online electronic publication of the textbook; 2013. 297 p. (In Russian)
24. Brilyuk DV, Starovoytov VV. Human recognition by facial image using neural network methods. Minsk; 2002. 54 p. (Preprint/Cybernetics University of NAS of Belarus; No 2) (In Russian)
25. Masters T. Practical Neural Network Recipies in C++. Morgan Kaufmann; 1993. 493 p.
26. Baiev O, Lazurik V. Advantages of neural networks for deriving an electrons spectrum from depth-charge curve. «IEEE Nuclear Science Symposium and Medical Imaging Conference», Conference Publications, Valencia, Spain; 2011. P. 1395-1397.
27. Baiev O, Lazurik V, Didenko I. Use of Neural Networks for Monitoring Beam Spectrum of Industrial Electron Accelerators. International Conference on Information and Communication Technologies in Education, Research, and Industrial Applications (ICTERI), 2013.
28. Malinovsky SV, Kashirin IA, Tikhomirov VA. Creation of a unified library of LSS spectra TRICARB. Collection of materials of the XVI annual seminar «Spectrometric analysis. Hardware and data processing on a PC», Obninsk, GCIPK; 2010. P. 2335. (In Russian).
29. Nikolaev SG. Neural networks. Implementation in Matlab: a Tutorial. Kazan: Kazan. State Energ. Univer.; 2015. 92 p. (In Russian).
30. Dyakonov VV. Matlab 6: Tutorial. Saint-Petersburg: Piter; 2002. 672 p. (In Russian).
31. Burakov MV. Neural networks and neurocontrollers: textbook. Saint-Petersburg: GUAP; 2013. 284 p. (In Russian).
32. Kovalev SM, Khatlamadzhiyan AE. Modeling artificial neural networks in MATLAB environment: Study guide for laboratory work. Rostov. St. University of Railway Transport. Rostov; 2008. 35 p. (In Russian).
33. Medvedev VS, Potemkin VG. Neural networks. Matlab 6. Moscow: Dialog-MEPhI; 2002. 496 p. (In Russian).
34. Nikolaev SV, Bazhenov RI. Pattern recognition using neural networks in the MatlabR2009b environment. 2015. No. 13 (13-2015). Available from: http://nauka-rastudent.ru/13/2355/ [Accessed October 20, 2020]. (In Russian).
Review
For citations:
Repin V.S. Study of the possibility of using an artificial neural network to recognize and assess the contribution of individual radionuclides to the total beta spectrum. Radiatsionnaya Gygiena = Radiation Hygiene. 2020;13(4):74-81. (In Russ.) https://doi.org/10.21514/1998-426X-2020-13-4-74-81
Views:
864
Email this article 