Author

Jason G. Seik

Date of Award

3-2021

Document Type

Thesis

Degree Name

Master of Science in Nuclear Engineering

Department

Department of Engineering Physics

First Advisor

Abigail Bickley, PhD

Abstract

There is a need to quickly and accurately determine the likely physical origins of a collected sample for nuclear treaty verification purposes. The objective of this research is to prove there is a means to relate different samples (Q-values) to one another using a 'same versus not-same' artificial neural network called a Siamese network. This would provide the capability of comparing an unknown sample to a database of samples with known physical origins. Using moment transformations on current data has shown to increase the prediction capabilities of a Siamese network, and using a triplet loss function in connection with the Siamese network can further increase these capabilities

AFIT Designator

AFIT-ENP-MS-21-M-135

DTIC Accession Number

AD1145746

Share

COinS