Abstract
We have applied a new imputation-based method for analyzing incomplete data, called Monte Carlo Bayesian Database Generation (MCBDG), to the spent fuel isotopic composition (SFCOMPO) database. About 60 % of the entries in SFCOMPO are absent. The method estimates missing values of a property from a probability distribution created from the existing data for the property, and then generates multiple instances of the completed database for training a machine learning algorithm. Uncertainty in the data is represented by an empirical or an assumed error distribution. The method makes few assumptions about the underlying data, and it compares favorably against results obtained by replacing missing information with constant values.
Similar content being viewed by others
References
Mayer K, Wallenius M, Fanghänel T (2007) J Alloys Compd 444–445:50–56
Hutcheon ID, Kristo MJ, Knight KB (2013) Nonproliferation nuclear forensics. In: Burns PC, Sigmon GE (eds.) Uranium: cradle to grave. Mineralogical Association of Canada Short Course, vol. 43, pp 7–14
http://www-ns.iaea.org/downloads/security/itdb-fact-sheet.pdf
Jones AE, Turner P, Zimmerman C, Goulermas JY (2014) Anal Chem 86:5399–5405
Robel M, Kristo MJ (2008) J Environ Radioact 99:1789–1797
Alamaniotis M, Hernandez H, Jevremovic T (2013) Role of nuclear forensics defined as a digital problem with neurofuzzy approach in various applications. In: Proceedings of the American Institute of Chemical Engineers Annual Conference 2013 (AIChE 2013), San Francisco, CA, 3–8 November 2013, pp 1–7
Sutton E, Reynolds C, Gey FC, Larson RR (2012) Applying digital library technologies to nuclear forensics. In: Zaphiris P, Buchanan G, Rasmussen E, Loizides F (eds) Theory and practice of digital libraries, lecture notes in computer science, vol 7489. Springer, Berlin, pp 144–149
Sullivan C (2014) Nuclear forensics driven by geographic information systems and big data analytics. In: Proceedings of the Information Analysis Technologies, Techniques and Methods for Safeguards, Nonproliferation and Arms Control Verification Workshop, Portland, OR, 12–14 May 2014, pp 273–286
Suyama K, Nouri A, Mochizuki H, Nomura Y (2003) JAERI Conf 2:890–892
Little RJA, Rubin DB (2002) Statistical analysis with missing data, 2nd edn. Wiley, Hoboken
Enders CK (2010) Applied missing data analysis. Guilford Press, New York
Allison PD (2001) Missing data. Sage Publications, Thousand Oaks
Mason A, Richardson S, Plewis I, Best NJ (2012) Off Stat 28:279–302
Saar-Tsechansky M, Provost F (2007) J Mach Learn Res 8:1625–1657
Little RJA, Rubin DB (1983) Encycl Stat Sci 4:46–53
Dempster AP, Laird NM, Rubin DB (1977) J R Stat Soc B 39:1–38
Hartley HO, Hocking RR (1971) Biometrics 27:783–808
Afifi AA, Elashoff RM (1966) J Am Stat Assoc 61:595–604
Chiu ST (1991) Ann Stat 4:1883–1905
Acknowledgments
This manuscript has been authored by Consolidated Nuclear Security, LLC, (CNS) and Oak Ridge National Laboratory (ORNL) under Contract Nos. DE-NA0001942 and DE-AC05-00OR22725, respectively, with the U.S. Department of Energy. The work was performed under an Interagency Agreement with the Department of Homeland Security. The content is solely the responsibility of the authors and does not necessarily represent the official views of the Department of Energy, CNS, or ORNL. The authors are grateful to Dr. Michael Sharp, of the University of Tennessee at Knoxville, for a critical review of the manuscript.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing financial interest.
Rights and permissions
About this article
Cite this article
Langan, R.T., Archibald, R.K. & Lamberti, V.E. Nuclear forensics analysis with missing data. J Radioanal Nucl Chem 308, 687–692 (2016). https://doi.org/10.1007/s10967-015-4458-x
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10967-015-4458-x