Operations Research, Systems Engineering and Industrial Engineering Commons^™

Deep Learning Models For Visibility Forecasting, Luz Carolina Ortega Gomez

Theses and Dissertations

This dissertation addresses the task of visibility forecasting via deep learning models using data from weather stations. Visibility is one of the most critical weather impacts on transportation systems. Low visibility conditions can seriously impact safety and traffic operations, leading to adverse scenarios, causing accidents, and jeopardizing transportation systems. Accurate visibility forecasting plays a key role in decision-making and management of transportation systems. However, due to the complexity and variability of weather variables, visibility forecasting remains a highly challenging task and a matter of significant interest for transportation agencies nationwide. This dissertation explores the use of deep learning models for …

Effects Of Resampled Data On Time Series Forecasting Accuracy, Jennifer Garland

Theses and Dissertations

This thesis will look at time series forecasting of the air pollutants in Beijing, China and the power consumption of an individual household located in Sceaux, France. The forecast will be taken from two classical methods, the Holt-Winters’ methods and the Seasonal Autoregressive Integrated Moving Average (SARIMA) method. The Holt-Winters’ method will be looked at from the additive, multiplicative and damped methods. The SARIMA model will be looked at as a uni-variate model. In this thesis, it will be shown that less complex algorithms, such as the Holt-Winters’ methods can process larger data sets without the need of resampling, and …

A Systematic Approach For Automatically Answering General-Purpose Objective And Subjective Questions, Lok Prasad Acharya

Theses and Dissertations

In this era of information explosion, people generally rely on the Internet, and more precisely, the search engines to get answers to their questions. However, what a search engine can do is just retrieve documents. Given some keywords, it only returns the relevant ranked documents that contain the keywords. Although users often want a precise answer to a question, they are left to extract answers from the documents themselves. This is where Automatic Question Answering (AQA) systems come into play. An AQA system takes questions in natural language as input and searches related answers in the set of documents and …

Improving Grapheme-To-Phoneme Translation With The Use Of Nalu Attention Mechanisms, Brian Sheldon Smith

Theses and Dissertations

In recent years, Natural Language Processing in the field of machine learning has seen some major improvements. Data scientists have shown that neural networks are capable of breaking down semantics of sentences, translating languages, and answering complex questions with fast recall. While impressive, these feats all hinge on having access to a massive amount of clean text, or data sets with almost perfect grammar and spelling. Without this, neural networks will usually fail to converge on a meaningful result. To partially this dependency, Grapheme-to-Phoneme conversion can be employed. This is the conversion of words from their spellings to a form …

Uncertainty And Error In Combat Modeling, Simulation, And Analysis, Jason A. Blake

Theses and Dissertations

Due to the infrequent and competitive nature of combat, several challenges present themselves when developing a predictive simulation. First, there is limited data with which to validate such analysis tools. Secondly, there are many aspects of combat modeling that are highly uncertain and not knowable. This research develops a comprehensive set of techniques for the treatment of uncertainty and error in combat modeling and simulation analysis. First, Evidence Theory is demonstrated as a framework for representing epistemic uncertainty in combat modeling output. Next, a novel method for sensitivity analysis of uncertainty in Evidence Theory is developed. This sensitivity analysis method …

Evaluating The Resiliency Of Industrial Internet Of Things Process Control Using Protocol Agnostic Attacks, Hector L. Roldan

Theses and Dissertations

Improving and defending our nation's critical infrastructure has been a challenge for quite some time. A malfunctioning or stoppage of any one of these systems could result in hazardous conditions on its supporting populace leading to widespread damage, injury, and even death. The protection of such systems has been mandated by the Office of the President of the United States of America in Presidential Policy Directive Order 21. Current research now focuses on securing and improving the management and efficiency of Industrial Control Systems (ICS). IIoT promises a solution in enhancement of efficiency in ICS. However, the presence of IIoT …

Development Of Cislunar Space Logistics Networks For Satellite Constellation Support Using Event-Driven Generalized Multi-Commodity Network Flows, Alexander R. Collins

Theses and Dissertations

As space becomes an increasingly congested domain, the risk of damage to satellite constellations is increasing. In response, there is an increasing need for capabilities for unmanned repair, refueling, and reconstitution (R3) of those constellations. Cislunar orbits offer a promising storage and low-cost transfer solution for on-orbit service vehicles and replacement satellites to leverage those capabilities. This research makes use of mixed-integer linear programming-based logistics models to determine the situations in which a cislunar mission architecture would offer a cost-effective alternative to Earth-based R3. The network models presented in this research make use of the latest developments in Event-Driven Generalized …

Operational Decision Making Under Uncertainty: Inferential, Sequential, And Adversarial Approaches, Andrew J. Keith

Theses and Dissertations

Modern security threats are characterized by a stochastic, dynamic, partially observable, and ambiguous operational environment. This dissertation addresses such complex security threats using operations research techniques for decision making under uncertainty in operations planning, analysis, and assessment. First, this research develops a new method for robust queue inference with partially observable, stochastic arrival and departure times, motivated by cybersecurity and terrorism applications. In the dynamic setting, this work develops a new variant of Markov decision processes and an algorithm for robust information collection in dynamic, partially observable and ambiguous environments, with an application to a cybersecurity detection problem. In the …

Analysis Of Pile Driving Monitoring Equipment, Robert Joseph Rogulski Iii

Theses and Dissertations

Rebound is a problem affecting pile driving in Florida. Significant rebound can require excessive blows for a pile to reach bearing capacity and may damage the pile. In order to study rebound, precise instrumentation is required. For that reason, the objective of this thesis is to evaluate the Inopile’s Pile Driving Monitor (PDM) as a tool for measuring the rebound of large diameter pre-stressed concrete piles driven with open ended diesel hammers. Six sites from Florida were selected for testing. Five of the sites had pile driving and two of them had standard penetration testing (which was used as an …

Persuasion, Political Warfare, And Deterrence: Behavioral And Behaviorally Robust Models, William N. Caballero

Theses and Dissertations

This dissertation examines game theory models in the context of persuasion and competition wherein decision-makers are not completely rational by considering two complementary threads of research. The first thread of research pertains to offensive and preemptively defensive behavioral models. Research in this thread makes three notable contributions. First, an offensive modeling framework is created to identify how an entity optimally influences a populace to take a desired course of action. Second, a defensive modeling framework is defined wherein a regulating entity takes action to bound the behavior of multiple adversaries simultaneously attempting to persuade a group of decision-makers. Third, an …

Application Of The Gradient Projection Method To An Optimal Control Problem In Quantum Biology, Rashad Abdulla

Theses and Dissertations

Quantum biology is an emerging field which seeks to understand and analyze the effects of quantum mechanical phenomena on biological systems. One such phenomenon is the formation of radical pairs, compounds which exist in a quantum superposition of two states until they collapse into one or the other. The probability of the collapse into a preferred state can be calculated from the Schrödinger equation, and is in fact dependent on external magnetic fields. This project utilizes principles of mathematical optimal control and quantum biology to determine the precise sequence of magnetic field pulses that maximize the probability of achieving the …

Search And Rescue Operations Forecasting And Optimization, Zachary T. Hornberger

Theses and Dissertations

United States Coast Guard District 14 is responsible for the execution of eleven statutory missions across the Pacific region. Despite having the largest geographic area of responsibility (AOR), District 14 has command of among the fewest resources to accomplish these missions. When search and rescue (SAR) emergencies occur, these events take immediate priority because the ability to rapidly coordinate available assets can be the difference between saving or losing a life. Using historic records of SAR incidents for District 14, we leverage an approach called the stochastic zonal distribution model to evaluate spatiotemporal trends in emergency rates and response strategies …

Fracture Toughness And Fatigue Crack Growth Rate Characterization Of Inconel 718 Formed By Laser Powder Bed Fusion, Charles C. Hohnbaum

Theses and Dissertations

Continuing improvement in the field of AM of metals provides the opportunity for direct fabrication of aerospace parts. AM was once used in large part for rapid prototyping but improvements in technology and increases in the knowledge base of AM materials has provided the opportunity for manufacture of AM parts for operational use. The ability to create low numbers of unique parts without having to invest in expensive tooling provides great economic incentive to utilize this technique. IN718 is the most common high temperature alloy used in the aerospace industry and lends itself readily to formation by LPBF. The superior …

Group Decision-Making, Edward Cook

Theses and Dissertations

The present work explores improvements in group decision-making. It begins with a practical example using state-of-the-art techniques for a complex, high-risk decision. We show how these techniques can reveal a better alternative. Although we created an improved decision process, decision-makers were apt to protect their own organizations instead of the project. This tendency was reduced over the course of the decision-making process but inspired the first conceptual component of this work.

The first concept describes the “Cost of Conflict” that can arise in a group decision, using game theory to represent the non-cooperative approach and comparing the outcome to the …

Material Interactions And Self-Assembly In Inkjet Printing, Karam Nashwan Al-Milaji

Theses and Dissertations

Inkjet printing has attracted much attention in recent years as a versatile manufacturing tool, suitable for printing functional materials. This facile, low-cost printing technique with high throughput and accuracy is considered promising for a wide range of applications including but not limited to optical and electronic devices, sensors, solar cells, biochips, and displays. The performance of such functional devices is significantly influenced by the deposit morphology and printing resolution. Therefore, fabrication functional devices with precise footprints by inkjet printing requires deep understanding of ink properties, material interactions, and material self-assembly.

In conventional inkjet printing process, where sessile droplets are directly …

Real-Time Heuristics And Metaheuristics For Static And Dynamic Weapon Target Assignments, Alexander G. Kline

Theses and Dissertations

The problem of targeting and engaging individual missiles (targets) with an arsenal of interceptors (weapons) is known as the weapon target assignment problem. This problem has been well-researched since the seminal work in 1958. There are two distinct categories of the weapon target assignment problem: static and dynamic. The static weapon target assignment problem considers a single instance in which a known number of incoming missiles is to be engaged with a finite number of interceptors. By contrast, the dynamic weapon target assignment problem considers either follow on engagement(s) should the first engagement(s) fail, a subsequent salvo of incoming missiles, …

Discrete Event Simulation And Cost Model For Optimization Of Manufacturing Resource Usages Associated With Implementation Of A Redesigned Product, Alexander Eierle

Theses and Dissertations

This paper demonstrates an approach to evaluating production factors related to schedule and resources based on changes to the production process. A discrete event simulation model was developed to evaluate different production factors, such as arrival times, number of entities, resource availabilities, and work in process (WIP) times, compared to the total yield at a production facility. This model helped to develop relationships between the required asset resource usages and the overall production resource allocation with the related effects to process wait times and production outputs. A comparative analysis with cost was performed to determine the effect that varied resources …

Characterizing Interfacial Bonds In Hybrid Metal Am Structures, John Ross Linn

Theses and Dissertations

The capabilities of various metal Additive Manufacturing (AM) processes, such as Powder Bed Fusion – Laser (PBF-L) and Direct Energy Deposition (DED) are increasing such that it is becoming ever more common to use them in industrial applications. The ability to print atop a substrate broadens that scope of applications. There is ongoing research regarding the mechanical properties of additively processed materials, but little regarding the interaction between additive material and its substrate. An understanding of the mechanical and performance properties of the AM/substrate interface is imperative. This paper describes a study of the strength properties of AM/substrate interfaces, with …

Operational Squadron Scheduling, Khaled A. Almannaei

Theses and Dissertations

The 28th Operational Weather Squadron (28th OWS) is responsible for producing and disseminating mission planning and execution weather analyses and forecasts. The squadron must prepare schedules that meet the needs of their mission while dealing with real-world constraints such as time windows, task priorities, and intermittent recurring missions. The 28th OWS's manning consists of active duty, deployed in-place, reserve, civilian and contract personnel. In this research, a scheduling model and algorithm are provided as an approach to crew scheduling for the 28th Operational Weather Squadron. Scheduling in the 28th OWS is complex and can be time consuming. This model will …

Generating Strong Diversity Of Opinions: Agent Models Of Continuous Opinion Dynamics, Christopher W. Weimer

Theses and Dissertations

Opinion dynamics is the study of how opinions in a group of individuals change over time. A goal of opinion dynamics modelers has long been to find a social science-based model that generates strong diversity -- smooth, stable, possibly multi-modal distributions of opinions. This research lays the foundations for and develops such a model. First, a taxonomy is developed to precisely describe agent schedules in an opinion dynamics model. The importance of scheduling is shown with applications to generalized forms of two models. Next, the meta-contrast influence field (MIF) model is defined. It is rooted in self-categorization theory and improves …

Methods To Support The Project Selection Problem With Non-Linear Portfolio Objectives, Time Sensitive Objectives, Time Sensitive Resource Constraints, And Modeling Inadequacies, Neil C. Ranly

Theses and Dissertations

The United States Air Force relies upon information production activities to gain insight regarding uncertainties affecting important system configuration and in-mission task execution decisions. Constrained resources that prevent the fulfillment of every information production request, multiple information requestors holding different temporal-sensitive objectives, non-constant marginal value preferences, and information-product aging factors that affect the value-of-information complicate the management of these activities. This dissertation reviews project selection research related to these issues and presents novel methods to address these complications. Quantitative experimentation results demonstrate these methods’ significance.

The Military Inventory Routing Problem: Utilizing Heuristics Within A Least Squares Temporal Differences Algorithm To Solve A Multiclass Stochastic Inventory Routing Problem With Vehicle Loss, Ethan L. Salgado

Theses and Dissertations

Military commanders currently resupply forward operating bases (FOBs) from a central location within an area of operations mainly via convoy operations in a way that closely resembles vendor managed inventory practices. Commanders must decide when and how much inventory to distribute throughout their area of operations while minimizing soldier risk. Technology currently exists that makes utilizing unmanned cargo aerial vehicles (CUAVs) for resupply an attractive alternative due to the dangers of utilizing convoy operations. Enemy actions in wartime environments pose a significant risk to a CUAV's ability to safely deliver supplies to a FOB. We develop a Markov decision process …

Multi-Level Multi-Objective Programming And Optimization For Integrated Air Defense System Disruption, Aaron M. Lessin

Theses and Dissertations

The U.S. military's ability to project military force is being challenged. This research develops and demonstrates the application of three respective sensor location, relocation, and network intrusion models to provide the mathematical basis for the strategic engagement of emerging technologically advanced, highly-mobile, Integrated Air Defense Systems. First, we propose a bilevel mathematical programming model for locating a heterogeneous set of sensors to maximize the minimum exposure of an intruder's penetration path through a defended region. Next, we formulate a multi-objective, bilevel optimization model to relocate surviving sensors to maximize an intruder's minimal expected exposure to traverse a defended border region, …

A Framework And Exploration Of A Cybersecurity Education Escape Room, Justin Charles Snyder

Theses and Dissertations

This thesis presents a review of educational-escape-room literature followed by a design-oriented framework (the Snyder Escape Room Framework or SERF) and demonstrates the potential efficacy of escape-rooms in cybersecurity education. Several authors have proposed frameworks and guidelines for game and educational design regarding escape rooms. This work coalesces some of those ideas into a more substantial and comprehensive framework (SERF) that designers can use when developing educational escape rooms. The Snyder Escape Room Framework provides heuristics for goals and objectives, players, activities, context, trajectory design, and evaluation. Additionally, this work describes and analyzes the novel prototyped BYU GCC escape room …

A Cognitive Approach To Predicting Academic Success In Computing, Colby Goettel

Theses and Dissertations

This research examines the possible correlations between a computing student's learning preference and their academic success, as well as their overall satisfaction with their major. CS and IT seniors at BYU were surveyed about their learning preferences and satisfaction with their major. The research found that IT students who are more reflective in their learning preference tend to have higher grades in their major. Additionally, it found that student age and their parents' education level were significant players in their academic success. However, there were no correlations found between major satisfaction and academic performance.

An Analysis Of Major Acquisition Reforms Through Text Mining And Grounded Theory Design, Amanda L. Mcgowin

Theses and Dissertations

Cost growth is an established phenomenon within Defense Acquisition that the US Government has attempted to abolish for decades through seemingly endless cycles of reform. Dozens of experts and senior leaders within the acquisition community have published their notions on the reasons for cost growth, nevertheless, legislation has yet to eradicate this presumed conundrum. For this reason, this research is aimed at identifying existing trends within past major Defense Acquisition Reform legislation, as well as in a compendium of views from leaders within the Defense Acquisition community on the efficacy of acquisition reform, to determine the possible disconnect. To accomplish …

A System Dynamics Innovation Diffusion Model Applied To Carbon Nanotube Manufacturing, Frances G. Mackinnon

Theses and Dissertations

The transition of advanced technologies from their nascent state to viable commercial entities is a critical step in assuring the United States' national technological superiority and support is often required to incubate such technological developments. We propose a spiral development to investigate the possible scenarios, underlying economics, and risk associated with scaling up carbon nanotube (CNT) production to a commercially viable scale. As the first stage of this proposed effort, this study characterizes the potential scenarios by which a CNT manufacturing company can generate positive annual net revenue and potentially be considered a competitive manufacturer of CNT products on an …

A Study Of The Air Force Airworthiness Assessment Process With Recommendations For Reusable Launch Vehicles, Austin A. Troya

Theses and Dissertations

Flight safety is a critical design and engineering consideration within the United States Department of Defense (DoD) and particularly the United States Air Force (USAF). This study conducts an independent evaluation of the airworthiness assessment process used by the United States Air Force’s Engineering Directorate through modeling and simulation. The airworthiness process is examined for its ability to effectively verify sound engineering design and efficiency with respect to the implementation of new software-based assessment tools and its impact on timeliness of reviews and resource utilization. Simulation results guide recommendations for reducing non-value-added activities and strategic leveling of resource demands to …

Experimental Designs, Meta-Modeling, And Meta-Learning For Mixed-Factor Systems With Large Decision Spaces, Zachary C. Little

Theses and Dissertations

Many Air Force studies require a design and analysis process that can accommodate for the computational challenges associated with complex systems, simulations, and real-world decisions. For systems with large decision spaces and a mixture of continuous, discrete, and categorical factors, nearly orthogonal-and-balanced (NOAB) designs can be used as efficient, representative subsets of all possible design points for system evaluation, where meta-models are then fitted to act as surrogates to system outputs. The mixed-integer linear programming (MILP) formulations used to construct first-order NOAB designs are extended to solve for low correlation between second-order model terms (i.e., two-way interactions and quadratics). The …

An Open Source Approach To Social Media Data Gathering, Anthony J. Kallhoff

Theses and Dissertations

Modern usage of social media affords the military intelligence and analytic communities novel approaches to gather information. However, the tools and resources to develop these methodologies are still maturing. Furthermore, current data acquisition tools are not available to the DoD for all social media platforms. This thesis addresses a small subset of this problem by developing an open source methodological approach to collect and manage data from a popular social media site that has previously been inaccessible to defense intelligence organizations. This approach was operationalized via the R package called instaExtract, and an exemplar analysis was performed to demonstrate its …