Classification problems arise in so many different parts of life – from sorting machine parts to diagnosing a disease. Humans make these classifications utilizing vast amounts of data, filtering observations for useful information, and then making a decision based on a subjective level of cost/risk of classifying objects incorrectly. This study investigates the translation of the human decision process into a mathematical problem in the context of a border security problem: How does one find special nuclear material being smuggled inside large cargo crates while balancing the cost of invasively searching suspect containers against the risk of al lowing radioactive material to escape detection? This may be phrased as a classification problem in which one classifies cargo containers into two categories – those containing a smuggled source and those containing only innocuous cargo. This task presents numerous challenges, e.g., the stochastic nature of radiation and the low signal-to-noise ratio caused by background radiation and cargo shielding. In the course of this work, we will break the analysis of this problem into three major sections – the development of an optimal decision rule, the choice of most useful measurements or features, and the sensitivity of developed algorithms to physical variations. This will include an examination of how accounting for the cost/risk of a decision affects the formulation of our classification problem. Ultimately, a support vector machine (SVM) framework with F -score feature selection will be developed to provide nearly optimal classification given a constraint on the reliability of detection provided by our algorithm. In particular, this can decrease the fraction of false positives by an order of magnitude over current methods. The proposed method also takes into account the relationship between measurements, whereas current methods deal with detectors independently of one another.

Due to increasing terrorist threats and illegal proliferation of nuclear material and technology, there is a need for increased research in the area of detection of smuggled fissile material, some of which is designated by the International Atomic Energy Agency as special fissile material. This thesis focuses on a hypothetical scenario in which a terrorist organization has managed to smuggle an amount of special fissile material onto a personal recreational watercraft and sail it into a marina. If the boat could be forced to go through a detector system, then the contents could be interrogated and a determination made of whether any special fissile material was aboard. This thesis examines the hypothesis that active interrogation may be used successfully in the detection of special fissile material in such an environment. It shows that it is feasible to use an active neutron system to detect a significant quantity of special fissile material onboard a small boat via the differential dieaway technique. The MCNP Monte Carlo transport code was used to simulate the use of a pulsed neutron generator to induce fission in the fissile material and then estimate the detector response. The detector modeled was based on elastic scattering-induced recoil protons using pure hydrogen gas. There was a significant difference between the system with and without the presence of fissile material, and the estimated detector response for the system with fissile material present was shown to be sufficiently greater than the response due to background radiation only. Additionally, dose was estimated and found to be small enough that the system would not likely pose a significant radiological health risk to passengers on the boat.