Application of stochastic and artificial intelligence methods for Nuclear Material Identification

Created by W.Langdon from gp-bibliography.bib Revision:1.8129

@TechReport{Pozzi:1999:ORNL,

• title = "Application of stochastic and artificial intelligence methods for Nuclear Material Identification",
• author = "Sara Pozzi and F. J. Segovia",
• institution = "Oak Ridge National Laboratory",
• year = "1999",
• number = "ORNL/TM-1999/320",
• address = "Oak Ridge, Tennessee 37831, USA",
• month = dec,
• notes = "oai:CiteSeerX.psu:10.1.1.483.2883 slightly different",
• keywords = "genetic algorithms, genetic programming",
• URL = "http://www.ornl.gov/reports/1999/3445605368018.pdf",
• size = "49 pages",
• abstract = "Nuclear materials safeguard efforts necessitate the use of non-destructive methods to determine the attributes of fissile samples enclosed in special, non-accessible containers. The sample identification problem, in its most general setting, is then to determine the relationship between the observed features of the measurement and the sample attributes and to combine them for the construction of an optimal identification algorithm. The goal of this paper is to develop an artificial intelligence (AI) approach to this problem whereby neural networks (NN) and genetic programming (GP) algorithms are used for sample identification purposes. Monte Carlo simulations of the source-detector cross correlation function for various sample shapes, mass, and enrichment values of uranium metal have been performed to serve as training set for the artificial intelligence algorithms. Both the NN and GP algorithms have shown good capabilities and robustness for mass and enrichment predictions of uranium metal samples. These results serve as a proof of principle for the application of combined stochastic and AI methods to safeguards procedures.",
• notes = "U.S. DEPARTMENT OF ENERGY contract DE-AC05-960R22464",
• size = "49 pages",

}

Genetic Programming entries for Sara A Pozzi Javier Segovia

Citations