DOI: 10.55176/2414-1038-2021-4-5-17
Authors & Affiliations
Bobrovsky T.L., Prusachenko P.S., Khryachkov V.A.
A.I. Leypunsky Institute for Physics and Power Engineering, Obninsk, Russia
Bobrovsky T.L. – Research Engineer. Contacts: 1, pl. Bondarenko, Obninsk, Kaluga region, Russia, 249033. Tel.: +7 (900) 571-04-77; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
Prusachenko P.S. – Researcher.
Khryachkov V.A. – Research Director, Dr. Sci. (Phys.-Math.).
Abstract
Machine learning is one of the leading directions in digital signal processing. For example, in neutron spectrometry, artificial neural networks are actively used to suppress gamma background when analyzing signals from scintillation detectors. This article describes a method for determining the quality of n/γ-separation by an artificial neural network. The efficiency of the method is demonstrated by analyzing the signals obtained by measuring the prompt neutron spectrum of 252Cf spontaneous fission using a scintillation detector based on a stilbene crystal. The essence of the method is to determine the proportion of falsely identified events for each of the analyzed signal classes using a known reference method. An exemplary gamma-ray source was used to determine the false count of recoil protons. This approach made it possible to estimate the fraction of events from electrons identified as recoil protons and the fraction of recoil protons perceived as electrons, depending on the light yield of the scintillation signal. This, in turn, made it possible to reconstruct the true energy spectra for different types of particles, including for the region of low signal amplitudes, where the separation quality is usually poor. The reconstructing error was less than 8 % for the light yield region of less than 120 keVee.
Keywords
artificial neural networks, pulse shape separation, scintillation detector, n/γ separation, stilbene, classification, Keras, separation parameter, mixed radiation fields, neutron spectrometry
Article Text (PDF, in Russian)
References
- Adams J.M., White G. A versatile pulse shape discriminator for charged particle separation and its application to fast neutron time-of-flight spectroscopy. Nuclear Instruments and Methods, 1978, vol. 156, issue 3, pp. 459–476.
- Winyard R.A., Lutkin J.E. and McBeth G.W. Pulse shape discrimination in inorganic and organic scintillators. Nuclear instruments and methods, 1971, vol. 95, pp. 141–153.
- Kukhtevich V.I., Trykov L.A., Trykov O.A. Odnokristal'nyy stsintillyatsionnyy spektrometr (s organicheskim fosforom)[Single crystal scintillation spectrometer (with organic phosphorus)]. Moscow, Atomizdat, 1971. 136 p.
- Sosa C.S. et al. Comparison of analog and digital pulse-shape-discrimination systems. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2016, vol. 826, pp. 72–79.
- Sӧderstӧrm P.-A. et al. Neutron detection and γ-ray suppression using artificial neural networks with the liquid scintillators BC-501A and BC-537. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2019, vol. 916, pp. 238–245.
- Griffiths J. et al. Pulse shape discrimination and exploration of scintillation signals using convolutional neural network. Instrumentation and Detectors (physics.ins-det), 2018. Available at: https://arxiv.org/pdf/1807.06853.pdf (accessed 12.11.2021).
- Fu C. et al. Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators. Annals of Nuclear Energy, 2018, vol. 120, pp. 410–421.
- Doucet E. et al. Machine learning n/γ discrimination in CLYC scintillators. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2020, vol. 954. doi: https://doi.org/10.1016/j.nima.2018.09.036.
- Zhong Cao, Miller L.F., Buckner M. Implementation of dynamic bias for neutron-photon pulse shape discrimination by using neural network classifiers. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 1998, vol. 416, pp. 438–445.
- Poulton Mary M. Chapter 3: Multi-layer perceptrons and back-propagation learning. Handbook of Geophysical Exploration: Seismic Exploration, 2001, vol. 30, pp. 27–53.
- Prusachenko P.S. et al. Optimization of the n/γ separation algorithm for a digital neutron spectrometer. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2018, vol. 905, pp. 160–170.
- Abdulnasir Yildiz et al. Classification and analysis of epileptic EEG recordings using convolutional neural network and class activation mapping. Biomedical Signal Processing and Control, 2021, vol. 68, p. 102720.
- Keras: The Python Deep Learning library. Available at: https://keras.io (accessed 12.11.2021).
- Simpson G. et al. Performance of four digital algorithms for γ-γ timing with LaBr3(Ce) scintillators. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2019, vol. 940, pp. 50–55.
- Kingma Deiderik, Ba Jimmy. Adam: A Method for Stochastic Optimization. Machine Learning (cs.LG), 22 December 2014. Available at: https://arxiv.org/abs/1412.6980v9 (accessed 12.11.2021).
UDC 539.1
Problems of Atomic Science and Technology. Series: Nuclear and Reactor Constants, 2021, issue 4, 4:1
