Date of Award


Document Type

Master's Thesis

Degree Name

Master of Science in Electrical Engineering (MS)

College, School or Department Name

Department of Electrical and Computer Engineering


Timothy Havens


Explosive hazards are one of the most deadly threats in modern conflicts. The U.S. Army is interested in a reliable way to detect these hazards at range. A promising way of accomplishing this task is using a forward-looking ground-penetrating radar (FLGPR) system. Recently, the Army has been testing a system that utilizes both L-band and X-band radar arrays on a vehicle mounted platform. Using data from this system, we sought to improve the performance of a constant false-alarm-rate (CFAR) prescreener through the use of three deep learning architechtures; deep belief networks (DBNs), stacked denoising autoencoders (SDAEs), and convolutional neural networks (CNNs). We also compare these deep learning classifiers with two more conventional shallow learning classifiers; single kernel support vector machines (SKSVMs) and multiple kernel learning group lasso (MKLGL). By training the deep learners on a combination of image features and comparing the test results to the conventional shallow learners, we were able to significantly increase the probability of detection over both the CFAR prescreener and the shallow learners while maintaining a nominal number of false alarms per square meter. Our research shows that deep learners are a good candidate for improving detection rates in FLGPR systems.