Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Radionuclide identification based on energy-weighted algorithm and machine learning applied to a multi-array plastic scintillator

  • Hyun Cheol Lee (Korea Institute of Nuclear Nonproliferation and Control) ;
  • Bon Tack Koo (Department of Integrative Medicine Major in Digital Healthcare, Yonsei University College of Medicine) ;
  • Ju Young Jeon (Korea Institute of Nuclear Nonproliferation and Control) ;
  • Bo-Wi Cheon (Department of Radiation Convergence Engineering, Yonsei University) ;
  • Do Hyeon Yoo (Department of Radiation Oncology, Massachusetts General Hospital and Harvard Medical School) ;
  • Heejun Chung (Korea Institute of Nuclear Nonproliferation and Control) ;
  • Chul Hee Min (Department of Radiation Convergence Engineering, Yonsei University)
  • Received : 2022.12.13
  • Accepted : 2023.07.05
  • Published : 2023.10.25
Download PDF
⟨ Previous Next ⟩

Abstract

Radiation portal monitors (RPMs) installed at airports and harbors to prevent illicit trafficking of radioactive materials generally use large plastic scintillators. However, their energy resolution is poor and radionuclide identification is nearly unfeasible. In this study, to improve isotope identification, a RPM system based on a multi-array plastic scintillator and convolutional neural network (CNN) was evaluated by measuring the spectra of radioactive sources. A multi-array plastic scintillator comprising an assembly of 14 hexagonal scintillators was fabricated within an area of 50 × 100 cm2. The energy spectra of 137Cs, 60Co, 226Ra, and 4K (KCl) were measured at speeds of 10-30 km/h, respectively, and an energy-weighted algorithm was applied. For the CNN, 700 and 300 spectral images were used as training and testing images, respectively. Compared to the conventional plastic scintillator, the multi-arrayed detector showed a high collection probability of the optical photons generated inside. A Compton maximum peak was observed for four moving radiation sources, and the CNN-based classification results showed that at least 70% was discriminated. Under the speed condition, the spectral fluctuations were higher than those under dwelling condition. However, the machine learning results demonstrated that a considerably high level of nuclide discrimination was possible under source movement conditions.

Keywords

Acknowledgement

This research was supported by the Nuclear Safety Research Program through the Korea Foundation Of Nuclear Safety (KoFONS) using financial resources granted by the Nuclear Safety and Security Commission (NSSC) of the Republic of Korea (No. 2106073).

References

  1. P. Dorenbos, J.T.M. de Haas, C.W.E. van Eijk, Non-proportionality in the scintillation response and the energy resolution obtainable with scintillation crystals, IEEE Trans. Nucl. Sci. 42 (6) (1995) 2190-2202.  https://doi.org/10.1109/23.489415
  2. B.L. Rupert, N.J. Cherepy, B.W. Sturm, R.D. Sanner, S.A. Payne, Bismuth-loaded plastic scintillators for gamma-ray spectroscopy, Europhys. Lett. 97 (2) (2012), 22002. 
  3. D.V. Jordan, B.D. Geelhood, P.L. Reeder, D.L. Stephens, R.A. Craig, J.I. McIntyre, Progress Report on the Advanced Large-Area Plastic Scintillators (ALPS) Project, Pacific Northwest National Laboratory (PNNL), Richland, WA (United States), 2003. PNNL-14283. 
  4. H.C. Lee, H.J. Choi, B.T. Koo, C.I. Choi, C.S. Park, H.S. Kim, C.H. Min, Dynamic radionuclide identification using energy weighted algorithm with commercialized radiation portal monitor based on plastic scintillators, Radiat. Phys. Chem. 170 (2020), 108645. 
  5. H.C. Lee, W.G. Shin, H.J. Park, D.H. Yoo, C.I. Choi, C.S. Park, H.S. Kim, C.H. Min, Validation of energy-weighted algorithm for radiation portal monitor using plastic scintillator, Appl. Radiat. Isot. 107 (2016) 160-164.  https://doi.org/10.1016/j.apradiso.2015.10.019
  6. W.G. Shin, H.C. Lee, C.I. Choi, C.S. Park, H.S. Kim, C.H. Min, A Monte Carlo study of an energy-weighted algorithm for radionuclide analysis with a plastic scintillation detector, Appl. Radiat. Isot. 101 (2015) 53-59.  https://doi.org/10.1016/j.apradiso.2015.03.014
  7. H.C. Lee, W. Shin, H.J. Choi, C.I. Choi, C.S. Park, H.S. Kim, C.H. Min, Radioisotope identification using an energy-weighted algorithm with a proof-of-principle radiation portal monitor based on plastic scintillators, Appl. Radiat. Isot. 156 (2020), 109010. 
  8. A.N.S. Institute, American National Standard for Performance Criteria for Spectroscopy-Based Portal Monitors Used in Homeland Security, American National Standards Institute, 2015, p. 46. 
  9. B.T. Koo, H.C. Lee, W.G. Shin, H.J. Park, C.H. Min, Feasibility study for radionuclide identification using multi-array plastic scintillator and energy weighted algorithm of radiation portal monitors: a Monte Carlo study, J. Instrum. 14 (12) (2019), P12015. 
  10. D. Oneata, J. Revaud, J. Verbeek, C. Schmid, Spatio-temporal object detection proposals, in: European Conference on Computer Vision, 2014. Zurich, Switzerland, September 6-12. 
  11. A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, Commun. ACM 60 (6) (2017) 84-90.  https://doi.org/10.1145/3065386
  12. J. Long, E. Shelhamer, T. Darrell, Fully convolutional networks for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015. 
  13. J.R. Koza, F.H. Bennett, D. Andre, M.A. Keane, Automated design of both the topology and sizing of analog electrical circuits using genetic programming, in: Artificial Intelligence in Design'96, 1996. 
  14. A. Ratner, B. Hancock, J. Dunnmon, R. Goldman, C. Re, Snorkel metal: weak supervision for multi-task learning, in: Proceedings of the Second Workshop on Data Management for End-To-End Machine Learning, 2018. 
  15. T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, New York, 2009. 
  16. Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE 86 (11) (1998) 2278-2324.  https://doi.org/10.1109/5.726791
  17. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, Tensorflow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, 2016 arXiv preprint arXiv:1603.04467. 
  18. D. Mishkin, N. Sergievskiy, J. Matas, Systematic evaluation of convolution neural network advances on the imagenet, Comput. Vis. Image Underst. 161 (2017) 11-19.  https://doi.org/10.1016/j.cviu.2017.05.007
  19. Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, Proc. IEEE 86 (11) (1998) 2278-2324.  https://doi.org/10.1109/5.726791
  20. R.H.R. Hahnloser, R. Sarpeshkar, M.A. Mahowald, R.J. Douglas, H.S. Seung, Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit, Nature 405 (6789) (2000) 947-951.  https://doi.org/10.1038/35016072
  21. H. Ide, T. Kurita, Improvement of learning for CNN with ReLU activation by sparse regularization, in: 2017 International Joint Conference on Neural Networks (IJCNN), May 14, 2017. 
  22. T. Fawcett, An introduction to ROC analysis, Pattern recognit. Lett. 27 (8) (2006) 861-874.  https://doi.org/10.1016/j.patrec.2005.10.010
  23. D.M.W. Powers, Evaluation: from Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation, 2020 arXiv preprint arXiv:2010.16061. 
  24. C.J. Van Rijsbergen, The Geometry of Information Retrieval, Cambridge University Press, 2004.