Dissertation/Thesis Abstract

Predicting the emplacement of improvised explosive devices: An innovative solution
by Lerner, Warren D., Sc.D., Capitol College, 2013, 152; 3570322
Abstract (Summary)

In this quantitative correlational study, simulated data were employed to examine artificial-intelligence techniques or, more specifically, artificial neural networks, as they relate to the location prediction of improvised explosive devices (IEDs). An ANN model was developed to predict IED placement, based upon terrain features and objects related to historical IED detonation events, the associated visual and radio-frequency lines of sight of these features and objects, and the volume of target-vehicle traffic during a 24-hour period. The architecture of the model contains a multilayer perceptron network to realize advanced performance. The findings indicate that the model is suitable for IED placement prediction. This research also established that opportunities exist for the development of sophisticated techniques, grounded in AI, that can predict the location of emplaced IEDs.

Indexing (document details)
Advisor: Pittman, Jason M.
Commitee: Barker, Helen G., Giulianelli, Lisa C.
School: Capitol College
Department: Information Assurance
School Location: United States -- Maryland
Source: DAI-B 74/09(E), Dissertation Abstracts International
Subjects: Information Technology, Artificial intelligence, Computer science
Keywords: Device emplacement, Improvised explosive devices, Neural networks, RF propagation
Publication Number: 3570322
ISBN: 9781303143823
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy