#PAGE_PARAMS# #ADS_HEAD_SCRIPTS# #MICRODATA#

Kernel-based Gaussian process for anomaly detection in sparse gamma-ray data


Autoři: Gregory R. Romanchek aff001;  Zheng Liu aff001;  Shiva Abbaszadeh aff001
Působiště autorů: Department of Nuclear, Plasma, and Radiological Engineering, Grainger College of Engineering, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States of America aff001;  Department of Electrical and Computer Engineering, Jack Baskin School of Engineering, University of California Santa Cruz, Santa Cruz, California, United States of America aff002
Vyšlo v časopise: PLoS ONE 15(1)
Kategorie: Research Article
doi: https://doi.org/10.1371/journal.pone.0228048

Souhrn

In radioactive source surveying protocols, a number of task-inherent features degrade the quality of collected gamma ray spectra, including: limited dwell times, a fluctuating background, a large distance to the source, weak source activity, and the low sensitivity of mobile detectors. Thus, collected gamma ray spectra are expected to be sparse and noise dominated. For extremely sparse spectra, direct background subtraction is infeasible and many background estimation techniques do not apply. In this paper, we present a statistical algorithm for source estimation and anomaly detection under such conditions. We employ a fixed-hyperparameter Gaussian processes regression methodology with a linear innovation sequence scheme in order to quickly update an ongoing source distribution estimate with no prior training required. We have evaluated the effectiveness of this approach for anomaly detection using background spectra collected with a Kromek D3S and simulated source spectrum and hyperparameters defined by detector characteristics and information derived from collected spectra. We attained an area under the ROC curve of 0.902 for identifying sparse source peaks within a sparse gamma ray spectrum and achieved a true positive rate of 93% when selecting the optimum thresholding value derived from the ROC curve.

Klíčová slova:

Algorithms – Covariance – Dwell time – Gamma rays – Gamma spectrometry – Kernel functions – Machine learning algorithms – Noise reduction


Zdroje

1. Ziock KP, Goldstein WH. The lost source, varying backgrounds and why bigger may not be better. InAIP Conference Proceedings 2002 Oct 10 (Vol. 632, No. 1, pp. 60–70). AIP.

2. Ristic B, Gunatilaka A. Information driven localisation of a radiological point source. Information fusion. 2008 Apr 1;9(2):317–26.

3. Liu Z, Abbaszadeh S. Double Q-Learning for Radiation Source Detection. Sensors. 2019;19:960.

4. Jarman KD, Runkle RC, Anderson KK, Pfund DM. A comparison of simple algorithms for gamma-ray spectrometers in radioactive source search applications. Applied Radiation and Isotopes. 2008 Mar 1;66(3):362–71. doi: 10.1016/j.apradiso.2007.09.010 17980610

5. Ely JH, Kouzes RT, Geelhood BD, Schweppe JE, Warner RA. Discrimination of naturally occurring radioactive material in plastic scintillator material. IEEE Transactions on Nuclear Science. 2004 Aug;51(4):1672–6.

6. Kouzes RT, Ely JH, Geelhood BD, Hansen RR, Lepel EA, Schweppe JE, et al. Naturally occurring radioactive materials and medical isotopes at border crossings. In2003 IEEE Nuclear Science Symposium. Conference Record (IEEE Cat. No. 03CH37515) 2003 Oct 19 (Vol. 2, pp. 1448–1452). IEEE.

7. Philips GW, Nagel DJ, Coffey T. A Primer on the detection of nuclear and radiological weapons. National Defense University Washington DC Center for Technology and National Security Policy; 2005 May.

8. Kirkpatrick JM, Young BM. Poisson statistical methods for the analysis of low-count gamma spectra. IEEE Transactions on Nuclear Science. 2009 Jun;56(3):1278–82.

9. Fischer R, Hanson KM, Dose V, von Der Linden W. Background estimation in experimental spectra. Physical Review E. 2000 Feb 1;61(2):1152.

10. Fagan DK, Robinson SM, Runkle RC. Statistical methods applied to gamma-ray spectroscopy algorithms in nuclear security missions. Applied Radiation and Isotopes. 2012 Oct 1;70(10):2428–39. doi: 10.1016/j.apradiso.2012.06.016 22871449

11. Alamaniotis M, Mattingly J, Tsoukalas LH. Kernel-based machine learning for background estimation of NaI low-count gamma-ray spectra. IEEE Transactions on Nuclear Science. 2013 Jun;60(3):2209–21.

12. D3S ID wearable RIID gamma neutron detector. Kromek Group. [cited 14 April 2019]. Available from: https://www.kromek.com/product/d3s_riid/.

13. Liu Z, Abbaszadeh S, Sullivan CJ. Spatial-temporal modeling of background radiation using mobile sensor networks. PloS one. 2018 Oct 19;13(10):e0205092. doi: 10.1371/journal.pone.0205092 30339704

14. Advanced Radioactive Threat Detection System Completes First Large-Scale Citywide Test [Internet]. Defense Advanced Research Projects Agency (DARPA). 2016 Nov 10 [cited 2019 Feb 15], Available from: www.darpa.mil/news-events/2016-10-11.

15. Fischer A, Wrobel M. Sensing [Internet]. Defense Advanced Research Projects Agency (DARPA). 2017 June 15 [cited 2019 Feb 15]. Available from: www.darpa.mil/attachments/sensingfischerwrobel-a.pdf. Slide. 15.

16. Bishop C. Pattern Recognition and Machine Learning. New York, NY: Springer-Verlag; 2016. p. 291–324.

17. Rasmussen CE, Williams CKI. Gaussian Processes for Machine Learning. Cambridge, MA: MIT Press; 2006.

18. Ayat NE, Cheriet M, Suen CY. Automatic model selection for the optimization of SVM kernels. Pattern Recognition. 2005 Oct 1;38(10):1733–45.

19. Duvenaud D. Automatic model construction with Gaussian processes [dissertation]. Cambridge, UK: University of Cambridge; 2014.

20. Krishnamoorthy A, Menon D. Matrix inversion using Cholesky decomposition. In2013 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) 2013 Sep 26 (pp. 70–72). IEEE.

21. Seeger Matthias. "Gaussian processes for machine learning." International journal of neural systems 14.02 (2004): 69–106.

22. Csató Lehel, and Opper Manfred. "Sparse on-line Gaussian processes." Neural computation 14.3 (2002): 641–668. doi: 10.1162/089976602317250933 11860686

23. Tipping Michael E. "Sparse Bayesian learning and the relevance vector machine." Journal of machine learning research 1.Jun (2001): 211–244.

24. Hajekm B. Random Processes for Engineers. Cambridge, UK: Cambridge University Press; 2015.

25. Burgess DD, Tervo RJ. Background estimation for gamma-ray spectrometry. Nuclear Instruments and Methods in Physics Research. 1983 Sep 1;214(2–3):431–4.

26. Tervo RJ, Kennett TJ, Prestwich WV. An automated background estimation procedure for gamma ray spectra. Nuclear Instruments and Methods in Physics Research. 1983 Oct 15;216(1–2):205–18.


Článek vyšel v časopise

PLOS One


2020 Číslo 1
Nejčtenější tento týden
Nejčtenější v tomto čísle
Kurzy

Zvyšte si kvalifikaci online z pohodlí domova

KOST
Koncepce osteologické péče pro gynekology a praktické lékaře
nový kurz
Autoři: MUDr. František Šenk

Sekvenční léčba schizofrenie
Autoři: MUDr. Jana Hořínková

Hypertenze a hypercholesterolémie – synergický efekt léčby
Autoři: prof. MUDr. Hana Rosolová, DrSc.

Svět praktické medicíny 5/2023 (znalostní test z časopisu)

Imunopatologie? … a co my s tím???
Autoři: doc. MUDr. Helena Lahoda Brodská, Ph.D.

Všechny kurzy
Kurzy Podcasty Doporučená témata Časopisy
Přihlášení
Zapomenuté heslo

Zadejte e-mailovou adresu, se kterou jste vytvářel(a) účet, budou Vám na ni zaslány informace k nastavení nového hesla.

Přihlášení

Nemáte účet?  Registrujte se

#ADS_BOTTOM_SCRIPTS#