Browse > Article
http://dx.doi.org/10.1016/j.net.2021.06.020

A comparative study of machine learning methods for automated identification of radioisotopes using NaI gamma-ray spectra  

Galib, S.M. (Department of Nuclear Engineering and Radiation Science, Missouri University of Science and Technology)
Bhowmik, P.K. (Department of Nuclear Engineering and Radiation Science, Missouri University of Science and Technology)
Avachat, A.V. (Department of Nuclear Engineering and Radiation Science, Missouri University of Science and Technology)
Lee, H.K. (Department of Nuclear Engineering, University of New Mexico)
Publication Information
Nuclear Engineering and Technology / v.53, no.12, 2021 , pp. 4072-4079 More about this Journal
Abstract
This article presents a study on the state-of-the-art methods for automated radioactive material detection and identification, using gamma-ray spectra and modern machine learning methods. The recent developments inspired this in deep learning algorithms, and the proposed method provided better performance than the current state-of-the-art models. Machine learning models such as: fully connected, recurrent, convolutional, and gradient boosted decision trees, are applied under a wide variety of testing conditions, and their advantage and disadvantage are discussed. Furthermore, a hybrid model is developed by combining the fully-connected and convolutional neural network, which shows the best performance among the different machine learning models. These improvements are represented by the model's test performance metric (i.e., F1 score) of 93.33% with an improvement of 2%-12% than the state-of-the-art model at various conditions. The experimental results show that fusion of classical neural networks and modern deep learning architecture is a suitable choice for interpreting gamma spectra data where real-time and remote detection is necessary.
Keywords
Artificial neural network; Gamma-ray spectroscopy; Radioisotope identification; Real-time processing; Nuclear security; Nuclear threat detection;
Citations & Related Records
연도 인용수 순위
  • Reference
1 C.J. Sullivan, S.E. Garner, M. Lombardi, K.B. Butterfield, M.A. Smith-Nelson, Evaluation of key detector parameters for isotope identification, in: 2007 IEEE Nuclear Science Symposium Conference Record, IEEE, 2007, pp. 1181-1184.
2 S. Salaymeh, R. Jeffcoat, Radioisotope Identification of Shielded and Masked Snm Rdd Materials. Technical Report, Savannah River Site (SRS), 2010.
3 Juri Opitz, Sebastian Burst, Macro F1 and Macro F1, 2019 arXiv preprint arXiv: 1911.03347.
4 Dehua Wang, Yang Zhang, Yi Zhao, Lightgbm: an effective mirna classification method in breast cancer patients, in: Proceedings of the 2017 International Conference on Computational Biology and Bioinformatics, ICCBB, New York, NY, USA, 2017, pp. 7-11, 2017. ACM.
5 D. Connor, P.G. Martin, T.B. Scott, Airborne radiation mapping: overview and application of current and future aerial systems, Int. J. Rem. Sens. 37 (24) (2016) 5953-5987.   DOI
6 Yukihisa Sanada, Tatsuo Torii, Aerial radiation monitoring around the fukushima dai-ichi nuclear power plant using an unmanned helicopter, J. Environ. Radioact. 139 (2015) 294-299.   DOI
7 Masahiro Hosoda, Kazumasa Inoue, Mitsuaki Oka, Yasutaka Omori, Kazuki Iwaoka, Shinji Tokonami, Environmental radiation monitoring and external dose estimation in aomori prefecture after the fukushima daiichi nuclear power plant accident, 保健物理 51 (1) (2016) 41-50.
8 Wei Ouyang, Casper F. Winsnes, Hjelmare Martin, Anthony J. Cesnik, Lovisa Akesson, Hao Xu, Devin P. Sullivan, Shubin Dai, Jun Lan, Jinmo Park, et al., Analysis of the human protein atlas image classification competition, Nat. Methods 16 (12) (2019) 1254-1261.   DOI
9 T.R. Twomey, A.J. Caffrey, D.L. Chichester, Nondestructive Identification of Chemical Warfare Agents and Explosives by Neutron Generator-Driven Pgnaa. Technical Report, Idaho National Laboratory (INL), 2007.
10 Yoshinori Uekusa, Hiromi Nabeshi, Rika Nakamura, Tomoaki Tsutsumi, Akiko Hachisuka, Rieko Matsuda, Reiko Teshima, Surveillance of radioactive cesium in domestic foods on the Japanese market (fiscal years 2012 and 2013). Shokuhin eiseigaku zasshi, J. Food Hyg. Soc. Jpn. 56 (2) (2015) 49-56.   DOI
11 Miyuki Sasaki, Yukihisa Sanada, Estiner W. Katengeza, Akio Yamamoto, New method for visualizing the dose rate distribution around the fukushima daiichi nuclear power plant using artificial neural networks, Sci. Rep. 11 (1) (2021) 1-11.   DOI
12 Huseyin Sahiner, Gamma Spectroscopy by Artificial Neural Network Coupled with MCNP, PhD thesis, 2017.
13 Miltiadis Alamaniotis, Heifetz Alexander, Apostolos C. Raptis, Lefteri H. Tsoukalas, Fuzzy-logic radioisotope identifier for gamma spectroscopy in source search, IEEE Trans. Nucl. Sci. 60 (4) (2013) 3014-3024, 8.   DOI
14 Mucci Anthony, Drone Tours in Security Systems, US Patent App, April 28 2016, 14/516,651.
15 Dean J. Mitchell, Lee T. Harding, GADRAS Isotope ID User's Manual for Analysis of Gamma-Ray Measurements and API for Linux and Android. Technical Report, Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States), 2014, 5.
16 G. Daniel, F. Ceraudo, O. Limousin, D. Maier, A. Meuris, Automatic and real-time identification of radionuclides in gamma-ray spectra: a new method based on convolutional neural network trained with synthetic data set, IEEE Trans. Nucl. Sci. 67 (4) (2020) 644-653.   DOI
17 Olga Russakovsky, Deng Jia, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, Li Fei-Fei, ImageNet large scale visual recognition challenge, Int. J. Comput. Vis. 115 (3) (2015) 211-252, 12.
18 Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom, Teaching machines to read and comprehend, in: Advances in Neural Information Processing Systems, 2015, pp. 1693-1701.
19 Detecting radiological threats in urban areas - challenge, Accessed on 01/05/2021, https://www.topcoder.com/challenges/30085346.
20 Tom Burr, Michael Hamada, Radio-isotope identification algorithms for NaI γ spectra, Algorithms 2 (2009) 339-360.   DOI
21 Mark Kamuda, Jacob Stinnett, C.J. Sullivan, Automated isotope identification algorithm using artificial neural networks, IEEE Trans. Nucl. Sci. 64 (7) (2017) 1858-1864.   DOI
22 Alex Graves, Abdel-rahman Mohamed, Geoffrey Hinton, Speech recognition with deep recurrent neural networks, in: Acoustics, Speech and Signal Processing (Icassp), 2013 Ieee International Conference on, IEEE, 2013, pp. 6645-6649.
23 Changfan Zhang, Gen Hu, Fei Luo, Yongchun Xiang, Ge Ding, Chengsheng Chu, Jun Zeng, Ze Rende, Qingpei Xiang, Identification of SNM based on low-resolution gamma-ray characteristics and neural network, Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip. 927 (155-160) (2019), 5.
24 Elsayed K. Elmaghraby, M. Tohamy, M.N.H. Comsan, Determination of isotopes activity ratio using gamma ray spectroscopy based on neural network model, Appl. Radiat. Isot. 148 (19-26) (2019) 6.
25 Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, Imagenet classification with deep convolutional neural networks, in: Advances in Neural Information Processing Systems, 2012, pp. 1097-1105.
26 Shaikat M. Galib, Hyoung K. Lee, Christopher L. Guy, Matthew J. Riblett, Geoffrey D. Hugo, A fast and scalable method for quality assurance of deformable image registration on lung ct scans using convolutional neural networks, Med. Phys. 47 (1) (2020) 99-109.   DOI
27 Shaikat Mahmood Galib, Applications of Machine Learning in Nuclear Imaging and Radiation Detection, 2019.
28 Tom Burr, Michael Hamada, Radio-isotope identification algorithms for nai γ spectra, Algorithms 2 (1) (2009) 339-360.   DOI
29 D.R. Rangaswamvi, J. Sannappa, E. Srinivasa, Estimation of radiological dose from radon, thoron and their progeny levels in the dwellings of shivamogga district, Karnataka, India, in: Proceedings of the Thirty-Third IARP International Conference on Developments towards Improvement of Radiological Surveillance at Nuclear Facilities and Environment: Book of Abstracts, 2018.
30 Yan T. Yang, Barak Fishbain, Dorit S. Hochbaum, Eric B. Norman, Erik Swanberg, The supervised normalized cut method for detecting, classifying, and identifying special nuclear materials, Inf. J. Comput. 26 (1) (2013) 45-58.   DOI
31 Ian Goodfellow, Yoshua Bengio, Aaron Courville, Yoshua Bengio, Deep learning, 1, MIT press Cambridge, 2016.
32 M.T. Batdorf, W.K. Hensley, C.E. Seifert, L.J. Kirihara, L.E. Erikson, D.V. Jordan, Isotope identification in the GammaTracker handheld radioisotope identifier, in: 2009 IEEE Nuclear Science Symposium Conference Record (NSS/MIC), IEEE, 2009, pp. 868-872, 10.
33 R.C. Runkle, M.F. Tardiff, K.K. Anderson, D.K. Carlson, L.E. Smith, Analysis of spectroscopic radiation portal monitor data using principal components analysis, IEEE Trans. Nucl. Sci. 53 (3) (2006) 1418-1423, 6.   DOI
34 David Boardman, Mark Reinhard, Alison Flynn, Principal component analysis of gamma-ray spectra for radiation portal monitors, IEEE Trans. Nucl. Sci. 59 (1) (2012) 154-160.   DOI
35 P.M. Saz Parkinson, H. Xu, P.L.H. Yu, D. Salvetti, M. Marelli, A.D. Falcone, CLASSIFICATION and RANKING OFFERMILAT GAMMA-RAY sources from the 3fgl CATALOG using machine learning techniques, Astrophys. J. 820 (1) (mar 2016), 8.   DOI
36 Scale - ornl, Accessed on 01/05/2021, https://www.ornl.gov/scale.
37 Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, Phil Blunsom, Teaching Machines to Read and Comprehend, 2015, pp. 1-9.
38 Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean, Efficient Estimation of Word Representations in Vector Space, 2013 arXiv preprint arXiv:1301.3781.
39 Sergey Ioffe, Christian Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, 2015 arXiv preprint arXiv:1502.03167.
40 Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res. 15 (1) (2014) 1929-1958.
41 Francois Chollet, et al., Keras. https://keras.io, 2015.
42 Alex Graves, Generating Sequences with Recurrent Neural Networks, 2013 arXiv preprint arXiv:1308.0850.
43 Jianping He, Xiaobin Tang, Pin Gong, Peng Wang, Liangsheng Wen, Xi Huang, Zhenyang Han, Yan Wen, Le Gao, Rapid radionuclide identification algorithm based on the discrete cosine transform and BP neural network, Ann. Nucl. Energy 112 (1-8) (2018) 2.
44 M. Kamuda, J. Stinnett, C.J. Sullivan, Automated isotope identification algorithm using artificial neural networks, IEEE Trans. Nucl. Sci. 64 (7) (2017) 1858-1864, 7.   DOI
45 C. Bobin, O. Bichler, V. Lourenco, C. Thiam, M. Thevenin, Real-time radionu-clide identification in γ-emitter mixtures based on spiking neural network, Appl. Radiat. Isot. 109 (405-409) (2016), 3.   DOI
46 Ilya Sutskever, Oriol Vinyals, V Le Quoc, Sequence to sequence learning with neural networks, in: Advances in Neural Information Processing Systems, 2014, pp. 3104-3112.
47 Alex Graves, Greg Wayne, Ivo Danihelka, Neural Turing Machines, 2014 arXiv preprint arXiv:1410.5401.
48 S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Comput. 9 (8) (11 1997) 1735-1780.   DOI
49 Barzilov Alexander, Ivan Novikov, Material classification by analysis of prompt photon spectra induced by 14-mev neutrons, Physics Procedia 66 (2015) 396-402. The 23rd International Conference on the Application of Accelerators in Research and Industry - CAARI 2014.   DOI
50 Diederik Kingma, Ba Jimmy, Adam: A Method for Stochastic Optimization, 2014 arXiv preprint arXiv:1412.6980.