Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

TinyML Gamma Radiation Classifier

  • Moez Altayeb (The Abdus Salam International Centre For Theoretical Physics, ICTP) ;
  • Marco Zennaro (The Abdus Salam International Centre For Theoretical Physics, ICTP) ;
  • Ermanno Pietrosemoli (The Abdus Salam International Centre For Theoretical Physics, ICTP)
  • Received : 2022.05.09
  • Accepted : 2022.09.28
  • Published : 2023.02.25
Download PDF
⟨ Previous Next ⟩

Abstract

Machine Learning has introduced many solutions in data science, but its application in IoT faces significant challenges, due to the limitations in memory size and processing capability of constrained devices. In this paper we design an automatic gamma radiation detection and identification embedded system that exploits the power of TinyML in a SiPM micro radiation sensor leveraging the Edge Impulse platform. The model is trained using real gamma source data enhanced by software augmentation algorithms. Tests show high accuracy in real time processing. This design has promising applications in general-purpose radiation detection and identification, nuclear safety, medical diagnosis and it is also amenable for deployment in small satellites.

Keywords

References

  1. Rui Costa, The internet of moving things [industryview], IEEE Technol. Soc. Mag. 37 (1) (2018) 13-14. https://doi.org/10.1109/MTS.2018.2795092
  2. Robert David, et al., Tensorflow lite micro: embedded machine learning on tinyml systems, CoRR (2020), 08678 abs/2010.
  3. Edge Impulse. https://www.edgeimpulse.com. (Accessed March 2022).
  4. V. Saveliev, V. Golovin, Silicon avalanche photodiodes on the base of metal-resistor-semiconductor (mrs) structures, Nucl. Inst. Methods Phys. Res. Sect. A: Accel. Spectrom. Detect. Assoc. Equip. 442 (1) (2000) 223-229. https://doi.org/10.1016/S0168-9002(99)01225-5
  5. Fabio Acerbi, Stefan Gundacker, Understanding and simulating sipms. Nuclear instruments and methods in Physics research section A: accelerators, spectrometers, detectors and associated equipment, Silicon Photomultipliers Technol. Char. Appl. 926 (2019) 16-35.
  6. Giulia Cozzi, Paolo Busca, Marco Carminati, Carlo Fiorini, Alberto Gola, Claudio Piemonte, Veronica Regazzoni, Development of a sipm-based detection module for prompt gamma imaging in proton therapy, in: IEEE Nuclear Science Symposium, Medical Imaging Conference and Room-Temperature Semiconductor Detector Workshop (NSS/MIC/RTSD), 2016, pp. 1-5, 2016.
  7. Odille F. Karcher et al. Fully digital pet is unaffected by any deterioration in tof resolution and tof image quality in the wide range of routine pet count rates. EJNMMI Phys., 8(1), 2021.
  8. S.I.P.M. J-Series, Silicon phomultiplier sensors. https://www.onsemi.com/products/sensors/photodetectors-sipm-spad/silicon-photomultipliers-sipm/j-series-sipm/. Accessed on June 2022.
  9. https://www.onsemi.com/pdf/datasheet/microj-series-d.pdf. (Accessed August 2022).
  10. Zhenhua Lin, Hautefeuille Benoit, Sung-Hee Jung, Jinho Moon, Jang-Guen Park, The design of a scintillation system based on sipms integrated with gain correction functionality, Nucl. Eng. Technol. 52 (1) (2020) 164-169. https://doi.org/10.1016/j.net.2019.07.005
  11. Minju Lee, Daehee Lee, Eunbie Ko, Kyeongjin Park, Junhyuk Kim, Kilyoung Ko, Manish Sharma, Gyuseong Cho, Pulse pileup correction method for gammaray spectroscopy in high radiation fields, Nucl. Eng. Technol. 52 (5) (2020) 1029-1035. https://doi.org/10.1016/j.net.2019.12.003
  12. G.F. Knoll, Radiation Detection and Measurement, WILEY, 2010.
  13. https://www.ortec-online.com/-/media/ametekortec/other/amplifier-introduction.pdf. (Accessed August 2022).
  14. https://www.seeedstudio.com/Wio-Terminal.html. (Accessed August 2022).
  15. https://www.ti.com/lit/ds/slas826e/slas826e.pdf. (Accessed August 2022).
  16. K.J. Bilton, T.H. Joshi, M.S. Bandstra, J.C. Curtis, B.J. Quiter, R.J. Cooper, K. Vetter, Non-negative matrix factorization of gamma-ray spectra for background modeling, detection, and source identification, IEEE Trans. Nucl. Sci. 66 (5) (2019) 827-837. https://doi.org/10.1109/TNS.2019.2907267
  17. Deborah K. Fagan, Sean M. Robinson, Robert C. Runkle, Statistical methods applied to gamma-ray spectroscopy algorithms in nuclear security missions, Appl. Radiat. Isot. 70 (10) (2012) 2428-2439. https://doi.org/10.1016/j.apradiso.2012.06.016
  18. David Michael P fund, Robert C. Runkle, Kevin K. Anderson, Kenneth D. Jarman, Examination of count-starved gamma spectra using the method of spectral comparison ratios, IEEE Trans. Nucl. Sci. 54 (4) (2007) 1232-1238. https://doi.org/10.1109/TNS.2007.901202
  19. C.J. Sullivan, M.E. Martinez, S.E. Garner, Wavelet analysis of sodium iodide spectra, IEEE Nucl. Sci. Symp. Conf. Rec. 1 (2005) 302-306, 2005.
  20. 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. https://doi.org/10.1109/TNS.2011.2179313
  21. Kyle J. Bilton, H. Tenzing, Y. Joshi, Mark S. Bandstra, Joseph C. Curtis, Daniel Hellfeld, Kai Vetter, Neural network approaches for mobile spectroscopic gamma-ray source detection, J. Nucl. Eng. 2 (2) (2021) 190-206. https://doi.org/10.3390/jne2020018
  22. S.M. Galib, P.K. Bhowmik, A.V. Avachat, H.K. Lee, A comparative study of machine learning methods for automated identification of radioisotopes using Nai Gamma-Ray spectra, Nucl. Eng. Technol. (2021).
  23. Andrew D. Nicholson, Douglas E. Peplow, James M. Ghawaly, Michael J. Willis, Daniel E. Archer, Generation of synthetic data for a radiation detection algorithm competition, IEEE Trans. Nucl. Sci. 67 (8) (2020) 1968-1975. https://doi.org/10.1109/TNS.2020.3001754
  24. 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 (2018) 1-8. https://doi.org/10.1016/j.anucene.2017.09.032
  25. S.C. Wong, A. Gatt, V. Stamatescu, M.D. McDonnell, Understanding data augmentation for classification: when to warp?, in: 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2016, pp. 1-6, https://doi.org/10.1109/DICTA.2016.7797091.
  26. C. Shorten, T.M. Khoshgoftaar, A survey on image data augmentation for deep learning, J. Big Data (2019).
  27. Alexandre Szenicer, et al., Seismic savanna: machine learning for classifying wildlife and behaviours using ground based vibration field recordings, Remote Sens. Ecol. Conserv. 8 (2) (November 2021).
  28. Francisco J. Moreno-Barea, Fiammetta Strazzera, Jose M. Jerez, Daniel Urda, Leonardo Franco, Forward noise adjustment scheme for data augmentation, in: IEEE Symposium Series on Computational Intelligence (SSCI), 2018, pp. 728-734, 2018.
  29. https://www.qoitech.com. (Accessed August 2022).
  30. https://lacuna.space. (Accessed August 2022).
  31. Kai Vogelgesang, Juan A. Fraire, Holger Hermanns, Uplink transmission probability functions for lora-based direct-to-satellite iot: a case study, IEEE Glob. Commun. Conf. (GLOBECOM) (2021), 01-06, 2021.
  32. Doroshkin Alexander, A.M. Zadorozhny, Oleg Kus, Vitaliy Prokopyev, Yuri Prokopyev, Laboratory testing of lora modulation for cubesat radio communications, MATEC Web Conf. 158 (2018), 01008, 01.
  33. I. Kwon, D. Shin, J. Oh, C.-H. Kim, H. Kim, Preprocessing energy intervals on spectrum for real-time radionuclide identification, IEEE Trans. Nucl. Sci. 68 (8) (2021) 2202-2209, Aug, https://doi.org/10.1109/TNS.2021.3097389.
  34. G. Daniel, F. Ceraudo, O. Limousin, D. Maier, A. Meuris, Automatic and realtime 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) (April 2020) 644-653, https://doi.org/10.1109/TNS.2020.2969703.