Radioisotope identification using sparse representation with dictionary learning approach for an environmental radiation monitoring system
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
A radioactive isotope identification algorithm is a prerequisite for a low-resolution scintillation detectorapplied to an unmanned radiation monitoring system. In this paper, a sparse representation with dictionarylearning approach is proposed and applied to plastic gamma-ray spectra. Label-consistent K-SVDwas used to learn a discriminative dictionary for the spectra corresponding to a mixture of four isotopes(133Ba, 22Na, 137Cs, and 60Co). A Monte Carlo simulation was employed to produce the simulated data aslearning samples. Experimental measurement was conducted to obtain practical spectra. After determiningthe hyper parameters, two dictionaries tailored to the learning samples were tested by varyingwith the source position and the measurement time. They achieved average accuracies of 97.6% and98.0% for all testing spectra. The average accuracy of each dictionary was above 96% for spectra measuredover 2 s. They also showed acceptable performance when the spectra were artificially shifted. Thus, theproposed method could be useful for identifying radioisotopes in gamma-ray spectra from a plasticscintillation detector even when a dictionary is adapted to only simulated data. Furthermore, owing tothe outstanding properties of sparse representation, the proposed approach can easily be built into an insitumonitoring system
Abstract
A radioactive isotope identification algorithm is a prerequisite for a low-resolution scintillation detectorapplied to an unmanned radiation monitoring system. In this paper, a sparse representation with dictionarylearning approach is proposed and applied to plastic gamma-ray spectra. Label-consistent K-SVDwas used to learn a discriminative dictionary for the spectra corresponding to a mixture of four isotopes(133Ba, 22Na, 137Cs, and 60Co). A Monte Carlo simulation was employed to produce the simulated data aslearning samples. Experimental measurement was conducted to obtain practical spectra. After determiningthe hyper parameters, two dictionaries tailored to the learning samples were tested by varyingwith the source position and the measurement time. They achieved average accuracies of 97.6% and98.0% for all testing spectra. The average accuracy of each dictionary was above 96% for spectra measuredover 2 s. They also showed acceptable performance when the spectra were artificially shifted. Thus, theproposed method could be useful for identifying radioisotopes in gamma-ray spectra from a plasticscintillation detector even when a dictionary is adapted to only simulated data. Furthermore, owing tothe outstanding properties of sparse representation, the proposed approach can easily be built into an insitumonitoring system
참고문헌 (24)
- 김준혁, "Efficient Design of ∅2×2 Inch NaI(Tl) Scintillation Detector Coupled with a SiPM in an Aquatic Environment", Nuclear Engineering and Technology, 51(4), pp.1091~1097 (2019), 한국원자력학회[DOI]
- L. Marques, "State-of-the-art mobile radiation detection systems for different scenarios", Sensors, 21, pp.1~67 (2021)[DOI]
- F.G. Knoll, "Radiation Detection and Measurement", 802~ (2000)
- T. Burr, "Radio-Isotope identification algorithms for NaI g spectra", Algorithms, 2, pp.339~360 (2009)[DOI]
- Y. Kim, "Inverse calibration matrix algorithm for radiation detection portal monitors", Radiat. Phys. Chem, 155, pp.127~132 (2019)[DOI]
- H. C. Lee, "Validation of energy-weighted algorithm for radiation portal monitor using plastic scintillator", Appl. Radiat. Isot, 107, pp.160~164 (2016)[DOI]
- J. Kim, "Multi-radioisotope identification algorithm using an artificial neural network for plastic gamma spectra", Appl. Radiat. Isot, 147, pp.83~90 (2019)[DOI]
- D. Liang, "Rapid nuclide identification algorithm based on convolutional neural network", Ann. Nucl. Energy, 133, pp.483~490 (2019)[DOI]
- C. -C. Hung, "Image Texture Analysis" (2019), Springer International Publishing
- M. Aharon, "K-SVD, An algorithm for designing overcomplete dictionaries for sparse representation", IEEE Trans. Signal Process, 54, pp.4311~4322 (2006)[DOI]
- Z. Jiang, "Label consistent K-SVD : learning a discriminative dictionary for recognition", IEEE Trans. Pattern Anal. Mach. Intell, 35, pp.2651~2664 (2013)[DOI]
- D. B. Pelowitz, "MCNP6 User's Manual", ~ (2013)
- G. Davis, "Adaptive greedy approximations", Constructive Approximation, 13(1), pp.57~98 (1997), Springer Science and Business Media LLC[DOI]
- T. T. Cai, "Orthogonal Matching Pursuit for Sparse Signal Recovery With Noise", 4680~4688 (2011)
- I. Kviatkovsky, "On the equivalence of the LCKSVD and the D-KSVD algorithms", IEEE Trans. Pattern Anal. Mach. Intell, 39, pp.411~416 (2017)[DOI]
- Z. Jiang, "Learning A Discriminative Dictionary for Sparse Coding via Label Consistent K-SVD", ~
- Chankyu Kim, "Iterative Monte Carlo simulation with the Compton kinematics-based GEB in a plastic scintillation detector", Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 795, pp.298~304 (2015), Elsevier BV[DOI]
- R. Casanovas, "Temperature peak-shift correction methods for NaI(Tl)and LaBr 3(Ce)gamma-ray spectrum stabilisation", Radiat. Meas, 47, pp.588~595 (2012)[DOI]
- S. Buranurak, "Temperature variations as a source of uncertainty in medical fiber-coupled organic plastic scintillator dosimetry", Radiat. Meas, 56, pp.307~311 (2013)[DOI]
- J. Kim, "Quantitative analysis of NaI(Tl) gamma-ray spectrometry using an artificial neural network", Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip, 2019, pp.162549~ (2019)
- G.C.J. Kim, "Radioisotope Identification and Nonintrusive Depth Estimation of Localized Low-Level Radioactive Contaminants Using Bayesian Inference", Sensors (Switzerland), pp.20~ (2020)
- M. A. El Khaddar, "Emerging wireless technologies in e-health: trends, challenges, and framework design issues", Int. Conf. Multimed. Comput. Syst. ICMCS 2012, pp.440~445 (2012)
- J. Makhoul, "Vector quantization in speech coding", Proc. IEEE, 73, pp.1551~1588 (1985)[DOI]
- W. W. Chang, "Robust vector quantization for wireless channels", IEEE J. Sel. Areas Commun, 19, pp.1365~1373 (2001)[DOI]