Operations Research, Systems Engineering and Industrial Engineering Commons^™

Distributionally Robust Unsupervised Domain Adaptation And Its Applications In 2d And 3d Image Analysis, Yibin Wang

Theses and Dissertations

Obtaining ground-truth label information from real-world data along with uncertainty quantification can be challenging or even infeasible. In the absence of labeled data for a certain task, unsupervised domain adaptation (UDA) techniques have shown great accomplishment by learning transferable knowledge from labeled source domain data and adapting it to unlabeled target domain data, yet uncertainties are still a big concern under domain shifts. Distributionally robust learning (DRL) is emerging as a high-potential technique for building reliable learning systems that are robust to distribution shifts. In this research, a distributionally robust unsupervised domain adaptation (DRUDA) method is proposed to enhance the …

Ai-Enabled Modeling And Monitoring Of Data-Rich Advanced Manufacturing Systems, Abdullah Al Mamun

Theses and Dissertations

The infrastructure of cyber-physical systems (CPS) is based on a meta-concept of cybermanufacturing systems (CMS) that synchronizes the Industrial Internet of Things (IIoTs), Cloud Computing, Industrial Control Systems (ICSs), and Big Data analytics in manufacturing operations. Artificial Intelligence (AI) can be incorporated to make intelligent decisions in the day-to-day operations of CMS. Cyberattack spaces in AI-based cybermanufacturing operations pose significant challenges, including unauthorized modification of systems, loss of historical data, destructive malware, software malfunctioning, etc. However, a cybersecurity framework can be implemented to prevent unauthorized access, theft, damage, or other harmful attacks on electronic equipment, networks, and sensitive data. The …

Resources Based Planning Framework For Infrastructure Maintenance And Rehabilitation Projects, Heba Gad

Theses and Dissertations

Infrastructure maintenance and rehabilitation projects involve activities scattered over a large geographical area (e.g., scattered road segments maintenance, telecom towers maintenance program, etc.). Planning such projects require a resource-based approach that accounts for the implications of resource mobility between activities’ locations in terms of time & cost. Existing scheduling techniques fall short of addressing the unique challenges of the scattered nature of these projects in combination with organization's limited resources availability. To address this need, this research presents a resources-based planning framework for infrastructure maintenance and rehabilitation scattered projects with the objective of enhancing resources utilization achieving time and cost …

Portfolio Optimization Using Value Focused Thinking, Tyler Martin

Theses and Dissertations

This thesis explores the application of Value Focused Thinking (VFT) and multi-objective portfolio optimization to create a well-aligned portfolio for an organization faced with over 50 alternatives and limited funding. A novel technique is proposed to develop an optimized portfolio based on VFT scores, utilizing heuristic approaches like evolutionary algorithms. The research outcomes include an optimized portfolio, the total value evaluation of alternatives, and a sensitivity analysis. The new approach outperforms the organization’s previous method, resulting in a portfolio that better addresses the organization’s core values and objectives, scoring 21.21% higher.

Design And Analysis Of Asymmetric “String-Of-Pearls” Common Repeating-Ground-Track Satellite Constellations For Missions Requiring Regional Coverage, Nathaniel Choo

Theses and Dissertations

Satellite constellation design must balance many factors that emerge from multiple sources, including environmental hazards and competing mission objectives. The dynamic nature of space systems makes the problem of ‘optimal’ satellite constellation design even more challenging. Restricting satellite constellation designs to predefined geometric frameworks can alleviate many challenges associated with the design problem; however, it raises an important question: which geometric framework performs best for each mission set? This research leverages simulations, metaheuristics, and mathematical programming techniques to address this question for missions focusing on Earth-observation of one or more regions.

First, this research captures the current state of satellite …

Adaptive Large Neighborhood Search Algorithm – Performance Evaluation Under Parallel Schemes & Applications, Sandip Kumar

Theses and Dissertations

Adaptive Large Neighborhood Search (ALNS) is a fairly recent yet popular single-solution heuristic for solving discrete optimization problems. Even though the heuristic has been a popular choice for researchers in recent times, the parallelization of this algorithm is not widely studied in the literature compared to the other classical metaheuristics. To extend the existing literature, this study proposes several different parallel schemes to parallelize the basic/sequential ALNS algorithm. More specifically, seven different parallel schemes are employed to target different characteristics of the ALNS algorithm and the capability of the local computers. The schemes of this study are implemented in a …

Passive Vs. Active Wearable Technology Monitoring Trunk Flexion In Elementary Teachers, Bailey Jose

Theses and Dissertations

The objective of this study was to assess the biomechanical and subjective measures of elementary school teachers while wearing active and/or passive wearable devices during the average workday. Five elementary school teachers wore a harness that held an Upright GO 2 posture tracking device and a Vicon Blue Trident sensor on the participant's upper back for two school days. Haptic feedback was on for one day and off for the other. Data from the Vicon wearable was analyzed to determine participants’ trunk flexion severity, frequency, and duration. Surveys were used to determine perceived exertion and perception of wearable technology. This …

A Generalizable Method And Case Application For Development And Use Of The Aviation Systems – Trust Survey (As-Ts)., Jamison Hicks

Theses and Dissertations

Automated systems are integral in the development of modern aircraft, especially for complex military aircraft. Pilot Trust in Automation (TIA) in these systems is vital for optimizing the pilot-vehicle interface and ensuring pilots use the systems appropriately to complete required tasks.

The objective of this research was to develop and validate a TIA scale and survey methodology to identify and mitigate trust deficiencies with automated systems for use in Army Aviation testing. There is currently no standard TIA assessment methodology for U.S. Army aviation pilots that identifies trust deficiencies and potential mitigations.

A comprehensive literature review was conducted to identify …

Developing Systems Engineering And Machine Learning Frameworks For The Improvement Of Aviation Maintenance, Fatine Elakramine

Theses and Dissertations

This dissertation develops systems engineering and machine learning models for aviation maintenance support. With the constant increase in demand for air travel, aviation organizations compete to maintain airworthy aircraft to ensure the safety of passengers. Given the importance of aircraft safety, the aviation sector constantly needs technologies to enhance the maintenance experience, ensure system safety, and limit aircraft downtime. Based on the current literature, the aviation maintenance sector still relies on outdated technologies to maintain aircraft maintenance documentation, including paper-based technical orders. Aviation maintenance documentation contains a mixture of structured and unstructured technical text, mainly inputted by operators, making them …

Modeling The Impact Of Scheduling Risks On Multi-Team Agile Projects, Bria Marie Booth

Theses and Dissertations

Agile project management allows for a quick response to a changing project environment. This opens possible avenues for new opportunities, but also may expose ongoing projects to previously unknown or unexpected threats. Risks must be continuously monitored as a product is worked on to avoid lost potential. This paper will propose a discrete event simulation model that multi-team projects may use to predict the impact to the project’s schedule. Using discrete event simulation early in the project’s planning cycle offers a greater understanding of the possible or probable impact of risks on the schedule. This would help to prepare project …

High-Level Requirements For Conceptual Design Of Bridge Deflection Measurement System Using Model-Based Systems Engineering, Mariana Villalabeitia Arenas

Theses and Dissertations

Bridges are essential in the infrastructure transportation system. Repairs and maintenance are the key activities to keep them safe for use. Over the years, the evolution of technology has been applied to improve the way bridges are designed, built, monitored, inspected, and repaired. Nevertheless, there is still a gap between the research efforts and the application of this knowledge in the practical field of bridge inspections. Model-based Systems Engineering is a formalized methodology in the system design that is centered around the model throughout all the life cycle stages of a system, supporting the requirements, design, analysis, verification, and validation …

Causal Modeling Framework For Nuclear Power Plant Licensing Process, Lauren Kimberly Kiser

Theses and Dissertations

Interests in clean energy revived the nuclear power industry. For the first time in decades, innovative technologies and plant designs are being considered by regulatory agencies. This dissertation explores a Bayesian Network and AHP approach to causal modeling of the Combined License review process for new nuclear power plants (NPP). Historically lengthy and expensive, NPP licensing is critical to ensuring safe operation of the plants. With this comes a high standard for applicants to reach that can result in multiple revision cycles and long review times. New plant designs and fluctuating public support lead to a complex and dynamic series …

Geometric Inference In Machine Learning: Applications Of Fisher Information For Model Selection And Other Statistical Applications, Trevor Herntier

Theses and Dissertations

We consider the problem of model selection using the Minimum Description Length (MDL) criterion for distributions with parameters on the hypersphere. Model selection algorithms aim to find a compromise between goodness of fit and model complexity. Variables often considered for complexity penalties involve number of parameters, sample size and shape of the parameter space, with the penalty term often referred to as stochastic complexity. Because Laplace approximation techniques yield inaccurate results for curved spaces, existing criteria incorrectly penalize complexity. We demonstrate how the use of a constrained Laplace approximation on the hypersphere yields a novel complexity measure that more accurately …

Fast And Accurate 3d Object Reconstruction For Cargo Load Planning, Adam R. Nasi

Theses and Dissertations

Cargo load planning involves efficiently packing objects into aircraft subject to constraints such as space and weight distribution. Currently, this is performed manually by loadmasters. The United States Air Force is investigating ways to automate this process in order to improve airlift operational readiness while saving money. The first step in such a process would be generating 3D reconstructions of cargo objects to be used by a load planning algorithm. To that end, this thesis presents a novel method for fast, scaled, and accurate 3D reconstruction of cargo objects. This method can scan a 2.5m×3m×2m object in less than 10 …

Classification And Analysis Of Twitter Bot And Troll Accounts, Callan P. Mccormick

Theses and Dissertations

This research trains, tests, and analyzes bot and troll classification models using publicly available, open source datasets. Specifically, it applies decision tree, random forest, feed forward neural networks, and long-short term memory neural networks with hyperparameters tuned via designed experiment to five labeled bot datasets created between 2011 and 2020 and one dataset labeling state-sponsored disinformation accounts or trolls. The first three models utilize account profile features, while the last model applies natural language processing techniques, specifically GloVe embedding, to analyze a user’s Tweet history. Results indicate that the random forest model outperforms the other three models with an average …

Critical Infrastructure System Resiliency Modeling Using Multi-Layer Network Optimization, Spencer R. Figge

Theses and Dissertations

ccurately modeling the interdependent operation of critical infrastructure systems is an effective and efficient way of proactively evaluating system vulnerabilities and resiliency. Infrastructure systems are designed to transport essential commodities from where they are produced to where they are consumed and network flow-based models are one of the most effective ways to simulate and quantify infrastructure performance. The literature is populated with proposed models that must balance accuracy of interdependent operations, capability to include real-world considerations, and computational cost. This research proposes an alternative network-flow based model called the Critical Infrastructure System Resiliency Model (CISRM) that focuses on modeling a …

Investigation Of Rhine Pointing As A Solution To The Aircraft Human Machine Interface Problem, Alexandra C. Dobranski, Samuel J. Medvec

Theses and Dissertations

The human machine interface in 5th generation aircraft has not evolved proportionally with advances in display size and data density. The traditional cursor slew method fails to rapidly relocate the cursor, especially on large displays. Previous studies at the Air Force Test Pilot School and Air Force Institute of Technology identified methods that have the potential to improve the human machine interface. This research expanded upon those studies by providing an assessment of head tracking technology as a secondary method of cursor manipulation. Specifically, this study examined the effects that visual feedback (visible and invisible head tracking cursors) and cursor …

Long-Term Asset Prioritization To Support District Planning, Melissa R. Sallberg

Theses and Dissertations

The United States Air Force (USAF) relies on its installations to project military power across the globe. However, due to the deferred infrastructure maintenance and recapitalization backlog of $33 billion as of 2019 (Wilson & Goldfein, 2019), it is more critical than ever for base-level community planners to focus their attention to the projects that will achieve each installation’s long-term goals. The recent incorporation of asset management principles into the USAF District Planning Process allows a unique opportunity to improve the existing scoring model for a holistic look at what matters to enterprise leaders and community planners making the plans …

Automated Registration Of Titanium Metal Imaging Of Aircraft Components Using Deep Learning Techniques, Nathan A. Johnston

Theses and Dissertations

Studies have shown a connection between early catastrophic engine failures with microtexture regions (MTRs) of a specific size and orientation on the titanium metal engine components. The MTRs can be identified through the use of Electron Backscatter Diffraction (EBSD) however doing so is costly and requires destruction of the metal component being tested. A new methodology of characterizing MTRs is needed to properly evaluate the reliability of engine components on live aircraft. The Air Force Research Lab Materials Directorate (AFRL/RX) proposed a solution of supplementing EBSD with two non-destructive modalities, Eddy Current Testing (ECT) and Scanning Acoustic Microscopy (SAM). Doing …

An Analysis Of Aircraft Maintenance Leading Indicator Metrics To Unit-Level Aircraft Availability Rates, William C. Hardy

Theses and Dissertations

The purpose of this research is to improve the usefulness of data that is already collected within aircraft maintenance organizations to better identify trends, and outliers, and possibly better explain relationships between leading and lagging indicator metrics. Specifically, this graduate research paper sought to answer two research questions addressing what aircraft maintenance metrics significantly impact aircraft availability, and how to measure those to understand which metrics impact aircraft availability most. The research questions were answered through a comprehensive literature review, and the use of multiple linear regression analysis on data from two specific aircraft maintenance organizations from the same location. …

Uncertainty Quantification In Federated Learning For Persistent Post-Traumatic Headache, Byungmoo Brian Kim

Theses and Dissertations

A post-traumatic headache (PTH), resulting from a mild traumatic brain injury (mTBI), potentially develops into persistent post-traumatic headache (PPTH). Although no known cure for PPTH exists, research has shown that receiving treatment at earlier stages of PTH lowers the risk of patients developing PPTH. Previous studies have shown machine learning (ML) models capable of predicting a patient’s PTH progression, but none have considered the issue of protecting patient privacy. Due to patient privacy, ML models only have access to data within the institution. Federated learning (FL) harnesses data from separate institutions without sacrificing patient privacy as institutions can run ML …

Pattern Of Life Modeling On Maritime Vessels With Bayesian Inferencing, Miles A. Kelly

Theses and Dissertations

Despite decades of research, maritime traffic models’ limited predictive power continues to constrain their operational utility. We build on previous pattern of life modeling algorithms and contribute a Bayesian inferencing model for anomaly detection. Our probabilistic approach provides decision makers the capability to tailor the belief threshold for identifying anomalies and to enact a measured response based on the degree of abnormality. We perform a case study to evaluate the results, verifying that our Bayesian inferencing method accurately refines its probability when given the location and time of a ship of interest, and serving as a proof of concept for …

An Analysis Of A Modular Open System Approach On Program Management Metrics For Cost And Schedule, Kayla I. Vogler

Theses and Dissertations

A modular open system approach (MOSA) and its inclusion of open architecture are among the prevailing acquisition strategies for cost and schedule management. This approach involves the incorporation of reusable, modular packages that can be incrementally added and upgraded throughout programs’ lifecycles. Many practitioners throughout the acquisitions community find that MOSA enables better opportunities for affordability, rapid acquisition, flexibility, enhanced competition, and innovation. A literature review reveals that few studies examine the interaction between MOSA and the extent to which it influences cost and schedule performance. However, no studies to date examine open architecture’s impact via programmatic evaluation of Earned …

Illuminating The Unknown: A Mixed Methods Exploration Of The Dod Software Factory Ecosystem, Zachary O. Ryan

Theses and Dissertations

The Department of Defense’s (DoD) software factories are a collection of modern software acquisition programs that commonly employ the agile, network-based business strategies often found within commercial industries. Having been formally recognized by senior leaders for their revolutionary software development approaches, the software factories highlight a cultural shift within the DoD away from traditional organizational practices. As a result of the factories demonstrated successes, the number of programs employing non-traditional strategies is expanding. While this is notable, it also presents a challenge because a comprehensive understanding of the characteristics, structures, and behaviors of the DoD’s software factories does not currently …

The U.S. Army Officer-To-Unit Assignment Problem, Andrea L. Phillips

Theses and Dissertations

Every two to three years, U.S. Army officers must change duty stations, which entails a selection process based on preferences. Currently, officers are assigned to units using a stable-marriage algorithm. Two impracticalities occur within this process. First, officers are required to submit strictly ranked preferences, not allowing indifference among units. Second, the stable-marriage algorithm does not give flexibility to alternative priorities. This research focuses on two modifications to the current model. First, a mixed integer program is created that allows the user, U.S. Army Human Resources Command, to consider other priorities: unit preferences and maximum officer disappointment. Second, generated data …

An Approximate Dynamic Programming Approach For Solving An Air Combat Maneuvering Problem With Directed Energy Weapons, Elisha A. Palm

Theses and Dissertations

Performing within visual range (WVR) air combat involves the execution of complex air maneuvers and rapid sequential decision making. The complexity of these decisions can increase even further when including additional weapon capabilities. The advancement of unmanned autonomous vehicle technology and weapon capabilities can help combat the hindrance that comes with human limitations. Autonomous unmanned combat aerial vehicles (AUCAVs) and the implementation of advanced weapon capabilities such as Directed Energy Weapons (DEWs) can prove to be vital in a WVR air combat context. This derives the question – Can AUCAV’s possess the proper artificial intelligence and weapon capabilities to attain …

Team And Skill Matching For Disaster Recovery Operations, Emily B. Frahm

Theses and Dissertations

United States Air Force (USAF) bases are key power projection platforms that ensure mission readiness and help bring humanitarian aid to locations in need. Recovering airfields after attack or natural disaster is a key mission of USAF civil engineers, and accomplishing this repair as swiftly as possible is key to maintaining our position in the global order. Accomplishing a disaster recovery project is a set of teams, each assigned to a specific task, and made up of a series of personnel. The question answered within this paper is: how do we match the right person with the appropriate skills to …

Bayesian Recurrent Neural Networks For Real Time Object Detection, Stephen Z. Kimatian

Theses and Dissertations

Neural networks have become increasingly popular in real time object detection algorithms. A major concern with these algorithms is their ability to quantify their own uncertainty, leading to many high profile failures. This research proposes three novel real time detection algorithms. The first of leveraging Bayesian convolutional neural layers producing a predictive distribution, the second leveraging predictions from previous frames, and the third model combining these two techniques together. These augmentations seek to mitigate the calibration problem of modern detection algorithms. These three models are compared to the state of the art YOLO architecture; with the strongest contending model achieving …

U.S. Army Force Structure Optimization And Sufficiency Analysis, Francis P. Gargin

Theses and Dissertations

The United States Army perpetually deploys rotational forces across the globe in support of the National Security Strategy. These forces meet a set of discrete mission demands over an extended time period before redeploying, modernizing, and preparing for the next deployment. The U.S. Army now utilizes the Regionally Aligned Readiness and Modernization Model to execute these cyclical stages for unit deployments. Specific emphasis is placed on aligning forces against a Geographic Combatant Command, which allows units to build readiness and lethality oriented towards the same series of threats, physical terrain, and civilian considerations. This research provides an Integer Programming model …

Analysis And Optimization Of Contract Data Schema, Franklin Sun

Theses and Dissertations

agement, development, and growth of U.S Air Force assets demand extensive organizational communication and structuring. These interactions yield substantial amounts of contracting and administrative information. Over 4 million such contracts as a means towards obtaining valuable insights on Department of Defense resource usage. This set of contracting data is largely not optimized for backend service in an analytics environment. To this end, the following research evaluates the efficiency and performance of various data structuring methods. Evaluated designs include a baseline unstructured schema, a Data Mart schema, and a snowflake schema. Overall design success metrics include ease of use by end …