Abstract
The discrimination of neutrons from gamma rays in a mixed radiation field is crucial in neutron detection tasks. Several approaches have been proposed to enhance the performance and accuracy of neutron-gamma discrimination. However, their performances are often associated with certain factors, such as experimental requirements and resulting mixed signals. The main purpose of this study is to achieve fast and accurate neutron-gamma discrimination without a priori information on the signal to be analyzed, as well as the experimental setup. Here, a novel method is proposed based on two concepts. The first method exploits the power of nonnegative tensor factorization (NTF) as a blind source separation method to extract the original components from the mixture signals recorded at the output of the stilbene scintillator detector. The second one is based on the principles of support vector machine (SVM) to identify and discriminate these components. In addition to these two main methods, we adopted the Mexican-hat function as a continuous wavelet transform to characterize the components extracted using the NTF model. The resulting scalograms are processed as colored images, which are segmented into two distinct classes using the Otsu thresholding method to extract the features of interest of the neutrons and gamma-ray components from the background noise. We subsequently used principal component analysis to select the most significant of these features wich are used in the training and testing datasets for SVM. Bias-variance analysis is used to optimize the SVM model by finding the optimal level of model complexity with the highest possible generalization performance. In this framework, the obtained results have verified a suitable bias–variance trade-off value. We achieved an operational SVM prediction model for neutron-gamma classification with a high true-positive rate. The accuracy and performance of the SVM based on the NTF was evaluated and validated by comparing it to the charge comparison method via figure of merit. The results indicate that the proposed approach has a superior discrimination quality (figure of merit of 2.20).
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs41365-021-00850-w/MediaObjects/41365_2021_850_Fig11_HTML.png)
Similar content being viewed by others
References
K.-N. Li, X.-P. Zhang, Q. Gui et al., Characterization of the new scintillator Cs2LiYCl6:Ce3+. Nucl. Sci. Tech. 29, 11 (2018). https://doi.org/10.1007/s41365-017-0342-4
M.L. Roush, M.A. Wilson, W.F. Hornyak, Pulse shape discrimination. Nucl. Instrum. Methods A 31, 112–124 (1964). https://doi.org/10.1016/0029-554X(64)90333-7
J. Heltsley, L. Brandon, A. Galonsky et al., Particle identification via pulse-shape discrimination with a charge-integrating ADC. Nucl. Instrum. Methods A 263, 441–445 (1988). https://doi.org/10.1016/0168-9002(88)90984-9
K. Zhou, J. Zhou, Y. Song et al., Compact lithium-glass neutron beam monitor for SANS at CSNS. Nucl. Sci. Tech 29, 127 (2018). https://doi.org/10.1007/s41365-018-0468-z
E. Bayat, N. Divani-Vais, M.M. Firoozadi et al., A comparative study on neutron-gamma discrimination with NE213 and UGLLT scintillators using zero-crossing method. Radiat. Phys. Chem. 81, 217–220 (2012). https://doi.org/10.1016/j.radphyschem.2011.10.016
T. He, P. Zheng, J. **ao, Measurement of the prompt neutron spectrum from thermal-neutron-induced fission in U-235 using the recoil proton method. Nucl. Sci. Tech 30, 112 (2019). https://doi.org/10.1007/s41365-019-0633-z
M.D. Aspinall, B.D. Mellow, R.O. Mackin et al., Verification of the digital discrimination of neutrons and γ rays using pulse gradient analysis by digital measurement of time of flight. Nucl. Instrum. Methods A 583, 432–438 (2007). https://doi.org/10.1016/j.nima.2007.09.041
S. Yousefi, L. Lucchese, Digital discrimination of neutrons and gamma-rays in liquid scintillators using wavelets. Nucl. Instrum. Methods A 598, 551–555 (2009). https://doi.org/10.1016/j.nima.2008.09.028
J.-L. Cai, D.-W. Li, P.-L. Wang et al., Fast pulse sampling module for real-time neutron–gamma discrimination. Nucl. Sci. Tech 30, 84 (2019). https://doi.org/10.1007/s41365-019-0595-1
P. Raj, A. Raman, Handbook of Research on Cloud and Fog Computing Infrastructures for Data Science, 1st edn. (IGI global, Pennsylvanie, 2018), pp. 1–400
T. Sanderson, C. Scott, M. Flaska et al., Machine learning for digital pulse shape discrimination, in IEEE Nuclear Science Symposium and Medical Imaging Conference Record, pp. 1–4 (2012). https://doi.org/10.1109/NSSMIC.2012.6551092
X. Yu, J. Zhu, S. Lin et al., Neutron/gamma discrimination based on the support vector machine method. Nucl. Instrum. Methods A 777, 80–84 (2015). https://doi.org/10.1016/j.nima.2014.12.087
W. Zhang, T. Wu, B. Zheng et al., A real-time neutron-gamma discriminator based on the support vector machine method for the time-of-flight neutron spectrometer. Plasma. Sci. Technol 20, 1–6 (2018). https://doi.org/10.1088/2058-6272/aaaaa9
Z.H. Zhang, C.Y. Hu, X.Y. Fan et al., A direct method of nuclear pulse shape discrimination based on principal component analysis and support vector machine. J. Instrum. 14, 1–10 (2019). https://doi.org/10.1088/1748-0221/14/06/P06020
P. Krömer, Z. Matej, P. Musílek et al., Neutron-Gamma Classification by Evolutionary Fuzzy Rules and Support Vector Machines, in IEEE International Conference on Systems, Man, and Cybernetics, pp. 1–5 (2015). https://doi.org/10.1109/SMC.2015.461
H. Arahmane, A. Mahmoudi, E.-M. Hamzaoui et al., Neutron-gamma discrimination based on support vector machine combined to nonnegative matrix factorization and continuous wavelet transform. Measurement (2020). https://doi.org/10.1016/j.measurement.2019.106958
A. Cichocki, R. Zdunek, S. Choi et al., Non-negative tensor factorization using alpha and beta divergence, in IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1–4 (2007). https://doi.org/10.1109/ICASSP.2007.367106
RCA 7265 photomultiplier tube 2” 14-stage s-20, (2014), http://www.Hofstragroup.Com/product/rca-7265 photomultiplier-tube-2–14-stage-s-20/. Accessed 15 July 2014.
J.G. Proakis, D.G. Manolakis, Digital Signal Processing, 4th edn. (Pearson, London, 2006), p. 1104
S. Mallat, A Wavelet Tour of Signal Processing: The Sparse Way, 3rd edn. (Academic Press, Cambridge, 2009).
A. Muñoz, R. Ertlé, M. Unser, Continuous wavelet transform with arbitrary scales and O (N) complexity. Signal Process 82, 749–759 (2002). https://doi.org/10.1016/S0165-1684(02)00140-8
N. Otsu, A threshold selection method from gray-level histograms. A threshold selection method from gray-level histograms. IEEE. T. Syst. Man. CY-S 9, 62–66 (1979). https://doi.org/10.1109/TSMC.1979.4310076
G. James, D. Witten, T. Hastie, R. Tibshirani, An Introduction to Statistical Learning with Applications in R (Springer, New York, 2013).
A. Cichocki, R. Zdunek, A.H. Phan et al., Nonnegative Matrix and Tensor Factorizations: Application to Exploratory Multi-Way Data Analysis and Blind Sources Separation (Wiley, New Jersey, 2009), p. 500
C. Cortes, V. Vapnik, Support-Vector Networks. Mach. Learn 20, 273–297 (1995). https://doi.org/10.1007/BF00994018
C. Burges, A tutorial on Support Vector Machines for pattern recognition. Data Min. Knowl. Disc. 2(2), 121–167 (1998)
J. Mercer, Functions of positive and negative type and their connection with the theory of integral equations. Philos. Trans. R. Soc. A 209, 415–446 (1909). https://doi.org/10.1098/rsta.1909.0016
G. Valentini, T.G. Dietterich, Bias-variance analysis of support vector machines for the development of SVM-based ensemble methods. J. Mach. Learn. Res. 5, 725–745 (2004). https://doi.org/10.1007/3-540-45428-4_22
G. I. Webb, P. Conilione, Estimating bias and variance from data. (CiteSeerX, 2005), http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.8679.
H. Arahmane, E.-M. Hamzaoui, R.C. El Moursli, Neutron flux monitoring based on blind source separation algorithms in Moroccan TRIGA MARK II reactor. Sci. Technol. Nucl. Inst. 2017, 1–8 (2017). https://doi.org/10.1155/2017/5369614
A. Cichocki, S. Amari, Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications (Wiley, New Jersey, 2002), p. 586
V.V. Vesselinov, M.K. Mudunuru, S. Karra et al., Unsupervised machine learning based on non-negative tensor factorization for analyzing reactive-mixing. J. Comput. Phys. 395, 85–104 (2019). https://doi.org/10.1016/j.jcp.2019.05.039
H. Arahmane, E.-M. Hamzaoui, Y. Ben Maissa et al., Improving neutron-gamma discrimination with stilbene organic scintillation detector using blind nonnegative matrix and tensor factorization methods. J. spectrosc. 2019, 1–9 (2019). https://doi.org/10.1155/2019/8360395
H. Arahmane, E.-M. Hamzaoui, R. Cherkaoui El Moursli, Spectrogram analysis of fission chamber's outputs signals using nonnegative matrix and tensor factorization algorithms, in IEEE International Multi-Conference on Systems, Signals & Devices, pp. 1–6 (2018). https://doi.org/10.1109/SSD.2018.8570624
H. Arahmane, E.-M. Hamzaoui, A. Mahmoudi et al., Time-scale characterization of neutron and gamma signals using continuous wavelet transform, in IEEE International Symposium on signal, Image, Video and Communications, pp. 1–6 (2018). https://doi.org/10.1109/ISIVC.2018.8709206
A. Cichocki and R. Zdunek, NMFLAB for signal processing NMFLAB toolboxes. (2006), http://www.bsp.brain.riken.jp/ICALAB/nmflab. Accessed 15 June 2006.
A.V. Kramarenko, U. Tan, Int. J. Neurosci. 113, 1007–1019 (2002). https://doi.org/10.1080/00207450390220330
A. Cichocki, R. Zdunek, S. Choi et al., Novel multi-layer non-negative tensor factorization with sparsity constraints, in Adaptive and Natural Computing Algorithms, 8th International Conference, ICANNGA 2007, pp. 271-280 (2007). https://doi.org/10.1007/978-3-540-71629-7_31
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by HA. The first draft of the manuscript was written by HA, and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Additional information
This work was supported by L'Oréal-UNESCO for the Women in Science Maghreb Program Grant Agreement No. 4500410340.
Rights and permissions
About this article
Cite this article
Arahmane, H., Hamzaoui, EM., Ben Maissa, Y. et al. Neutron-gamma discrimination method based on blind source separation and machine learning. NUCL SCI TECH 32, 18 (2021). https://doi.org/10.1007/s41365-021-00850-w
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s41365-021-00850-w