Article Sidebar

PDF
Published: 2026-05-18
Abstract Views: 3
Views PDF: 0
DOI: https://doi.org/10.53747/nst.v12i4.347
Issue
Vol. 12 No. 4 (2022)
Section
Articles
How to Cite
Cao , V. H., Dinh , T. H., Cao , D. L., Le , M. D., & Pham , D. K. (2026). Nuclide identification algorithm for Polyvinyl Toluene scintillation detector based on Deep Neural Network. Nuclear Science and Technology, 12(4), 46-55. https://doi.org/10.53747/nst.v12i4.347

Nuclide identification algorithm for Polyvinyl Toluene scintillation detector based on Deep Neural Network

Cao Van Hiep1, Dinh Tien Hung1, Cao Dang Luu2, Le Manh Duc3, Pham Dinh Khang4
1 Military Institute of Chemical and Environmental Engineering
2 Center 81, Chemical Corps, Ministry of National Defense
3 Department of radiotherapy and radiosurgery, 108 Military Central Hospital
4 Hanoi University of Science and Technology

Main Article Content

Abstract

Radiation portal monitors (RPMs) are now stationed at strategic areas (airports, ports, etc.) to identify the illegal transportation of radioactive sources and nuclear items. RPMs are typically fitted with plastic scintillations detectors with high detection efficiency. Radioisotope identification from the gamma spectrum acquired on this detector usually is not regarded due to the low resolution. This research describes an artificial neural network-based isotope identification algorithm applied to the gamma spectrum collected from the RPM's PVT detector. Measured and simulated gamma spectra of 5 radionuclides are used for training and validating the proposed model, namely 241Am, 133Ba, 137Cs, 60Co, and 152Eu. The recognition accuracy of the proposed model with these radionuclides are 99.0%, 98.0%, 99.0%, 97.5%, and 98.5%, respectively. The model still recognizes the training isotopes with the lowest accuracy of 89.0% for spectra with the displacement in the range of 20%.

Article Details

Keywords

Artificial neural network, plastic scintillation detector, nuclide identification algorithms

References

[1]. P. Olmos et al., “A New Approach to Automatic Radiation Spectrum Analysis,” IEEE Trans. Nucl. Sci., vol. 38, no. 4, pp. 971–975, 1991, doi: 10.1109/23.83860.
[2]. C. Bobin, O. Bichler, V. Lourenço, C. Thiam, and M. Thévenin, “Real-time radionuclide identification in γ-emitter mixtures based on spiking neural network,” Appl. Radiat. Isot., vol. 109, pp. 405–409, 2016, doi: 10.1016/j.apradiso.2015.12.029.
[3]. L. F. Blázquez, F. Aller, S. Vrublevskaya, J. Fombellida, and E. Valtuille, “Classification of radionuclides on polyvinyl toluene radiation portal monitors by a neural network based system,” IFAC-PapersOnLine, vol. 28, no. 21, pp. 852–857, 2015, doi: 10.1016/j.ifacol.2015.09.633.
[4]. L. Chen and Y. X. Wei, “Nuclide identification algorithm based on K-L transform and neural networks,” Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip., vol. 598, no. 2, pp. 450–453, 2009, doi: 10.1016/j.nima.2008.09.035.
[5]. J. Fombellida, L. F. Blazquez, F. Aller, S. Vrublevskaya, and E. Valtuille, “Neural network based radioisotope discrimination on polyvinyl toluene radiation portal monitors,” 2014 22nd Mediterr. Conf. Control Autom. MED 2014, pp. 1099–1104, 2014, doi: 10.1109/MED.2014.6961521.
[6]. M. Kamuda and C. J. Sullivan, “An automated isotope identification and quantification algorithm for isotope mixtures in low-resolution gamma-ray spectra,” Radiat. Phys. Chem., vol. 155, no. August 2017, pp. 281–286, 2019, doi: 10.1016/j.radphyschem.2018.06.017.
[7]. L. J. Kangas, P. E. Keller, E. R. Siciliano, R. T. Kouzes, and J. H. Ely, “The use of artificial neural networks in PVT-based radiation portal monitors,” Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip., vol. 587, no. 2–3, pp. 398–412, 2008, doi: 10.1016/j.nima.2008.01.065.
[8]. J. Kim, K. Park, and G. Cho, “Multi-radioisotope identification algorithm using an artificial neural network for plastic gamma
spectra,” Appl. Radiat. Isot., vol. 147, no. November 2018, pp. 83–90, 2019, doi: 10.1016/j.apradiso.2019.01.005.
[9]. D. Liang et al., “Rapid nuclide identification algorithm based on convolutional neural network,” Ann. Nucl. Energy, vol. 133, pp. 483–490, 2019, doi: 10.1016/j.anucene.2019.05.051.
[10]. V. Pilato, F. Tola, J. M. Martinez, and M. Huver, “Application of neural networks to quantitative spectrometry analysis,” Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip., vol. 422, no. 1–3, pp. 423–427, 1999, doi: 10.1016/S0168-9002(98)01110-3.
[11]. E. Yoshida, K. Shizuma, S. Endo, and T. Oka, “Application of neural networks for the analysis of gamma-ray spectra measured with a Ge spectrometer,” Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip., vol. 484, no. 1–3, pp. 557–563, 2002, doi: 10.1016/S0168-9002(01)01962-3.
[12]. D. T. Hung et al., “Gamma spetrum stabilization for environmental radiation monitoring stations using NaI(Tl) detector,” Radiat. Prot. Dosimetry, vol. 189, no. 1, pp. 48–55, Mar. 2020, doi: 10.1093/rpd/ncaa011.