Operational Research Commons^™

Data-Driven Dynamic Decision-Making Using Discrete Optimization And Supervised Machine Learning, Navid Rashedi

Dartmouth College Ph.D Dissertations

In recent years, the operations research community has developed data-driven optimization techniques to solve complex combinatorial problems with the aid of machine learning. This thesis contributes to these efforts by combining machine learning with optimization to expedite online decision-making, with applications in transportation and healthcare.

In the domain of airline operations recovery, the focus is on the aircraft recovery process—repairing disrupted schedules by minimizing overall disruption costs. Traditional exact methods are too time-consuming, while heuristic approaches often yield poor solution quality and lack generalizability across varying formulations. To address these challenges, this research employs supervised machine learning to identify near-optimal …

Community Wastewater Treatment Resilience Assessment, Tristan Veal

All Theses

With the rising threat of climate change and cascading impacts from infrastructure failure there is a growing need to strengthen community resilience. Theoretical and practical resilience frameworks are available, but they vary in aim and scope; there is no standard tool to assess resilience. This research expands on the resilience matrix (RM) application methods of previous research completed by the United States Army Corps of Engineers (USACE) and Clemson University. That work focused on drinking water treatment systems and developed a few dozen specific indicators, or metrics, to quantify resilience. This research adds wastewater infrastructure with the aim of identifying …

Decomposition And Coordination For Multiobjective Optimization: A Framework And Methodology, Philip J. De Castro

All Dissertations

In this work, we consider finding Pareto efficient solutions for complex multiobjective optimization problems (MOPs). Complex MOPs are unique in the literature because they have many more objective functions than is typically considered. In fact, such complex MOPs will have 30+ objective functions. This large problem size presents computational and coginitive difficulties. Computationally, standard techniques for solving MOPs are often ineffective and cognitively it is difficult for a decision maker (DM) to handle all of the information provided in such a large problem. To address these challenges, we develop a decomposition and coordination framework. This framework will allow us to …

Multistage Random Key Genetic Algortihm Optimization For Scheduling Flexible Flow Lines With Sequence Depenedent Setup Times, Aadithan Anbuvanan

All Theses

This thesis proposes a new variation to the Random Key Genetic Algorithm (RKGA) for scheduling optimization in flexible flow line manufacturing with sequence dependent setup times. The proposed RKGA representation decodes scheduling information independently at each stage, unlike the traditional RKGA, which is only sequenced based on the first stage, limiting flexibility. The proposed method's performance is compared to the traditional method with varying numbers of jobs and stages. It is compared regarding performance ratio and statistical significance of differences through the Wilcoxon Signed Rank Test. Results show that the proposed RKGA outperformed traditional RKGA in high complexity (8 Stage …

The Food Truck: A Multi-Product Newsvendor With Trans-Shipment Cost, Samuel Ajibola

Electronic Theses and Dissertations

The Newsvendor Problem is a key model in supply chain management that focuses on determining the optimal order quantity to minimize costs under uncertain demand. This thesis introduces the Food Truck Problem, an extension of the Newsvendor model that incorporates nonlinear transshipment costs for inventory transportation. In this context, a Food Truck must determine the optimal stock levels for multiple products while minimizing costs related to stock shortages, excess inventory, and transportation. Unlike traditional Newsvendor models, our approach explicitly considers a quadratic transshipment cost, which necessitates the use of Lagrangian duality and Karush-Kuhn-Tucker (KKT) conditions for analysis. Moreover, we apply …

Decision Space Decomposition For Multiobjective Programs, Emma Soriano

All Dissertations

Being inspired by the parametric decomposition theorem for multiobjective optimization problems (MOPs) of Cuenca and Miguel (2017), and by the block- coordinate descent for single objective optimization problems, we present a decom- position theorem for computing the set of minimal elements of a partially ordered set. This set is decomposed into subsets whose minimal elements are used to retrieve the overall minimal elements. We apply this approach to strictly convex MOPs de- composing their decision space into lines. The line decomposition benefits from the fact that a multiobjective line search problem is equivalent to solving a collection of single objective …

Kennesaw State University Student Managed Investment Fund Sector Sensitivity Analysis, John Kiersznowski, Joe Johnson, Kyler Howell, Geranger Lewis

Senior Design Project For Engineers

The Kennesaw State University Student Managed Investment Fund (SMIF) Sector Sensitivity Analysis focuses on improving the fund’s decision-making and performance through data science. The SMIF is a diversified index fund designed to outperform indices like the S&P 500. This project investigates how macroeconomic variables—such as GDP growth, inflation, interest rates, and commodity prices—impact sector performance. By structuring data, developing a sustainable data pipeline, and leveraging advanced statistical techniques and predictive modeling, our team was able to provide the framework and proof of actionable insights that enhance the fund's ability to manage risks and optimize returns.

On The Provenance Of Software Systems: Automating Software Traceability With Knowledge Graph And Large Language Model Synergy, Tyler Procko

Doctoral Dissertations and Master's Theses

The present dissertation delineates a system that enables those engaged in software development to automatically generate and maintain project life cycle provenance. All projects are implemented and made manifest with the development of artifacts, e.g., papers, code files, etc. Tools exist to accelerate artifact creation, but little focus is paid to the processes that produce them. In terms of Ontology, or, from Ancient Greek, the study of being, the two most basic entities in reality are Continuant and Occurrent, or, roughly, “Artifact” and “Process”. This dissertation posits that for any created artifact, its process of creation, i.e., its life …

Modeling And Characterization Of On-Orbit Servicing Architectures For Efficient Mission Planning, Samantha Q. Vi Tang

Theses and Dissertations

As space-based systems become increasingly critical to global infrastructure, efficient satellite maintenance and resource management have become essential to ensuring operational longevity. On-orbit servicing has emerged as a key strategy for extending satellite lifespans, mitigating space debris accumulation, and enhancing the cost effectiveness of space operations. This study presents a comprehensive mixed-integer programming (MIP) model to optimize servicer task assignments and routing while minimizing propellant consumption. The model captures the operational complexities of servicing a network of satellites across multiple orbits by incorporating realistic constraints, such as fuel limitations and task completion time windows. Sensitivity analysis allows mission planners to …

The Location Set Covering Disruption Problem, Richard A. Sheldon

Theses and Dissertations

This research models and analyzes a variant of the Location Set Covering Problem (LSCP) in a bilevel, game theoretic setting by posing the LSCP as a non-cooperative attacker-defender Stackelberg game, where facilities are to be emplaced by the defender from a boarder set of potential facility locations to cover a set of demands; however, an attacker removes the possibility of emplacing q specific facility locations with the objective to remove the maximum weighted value demands, and then lexicographically maximize the cost of coverage of remaining demands. A novel methodology leveraging lexicographic programming computed an optimal solution for 98% of all …

Forecasting Army Recruiting Mission Distribution, Maxwell A. Deihl

Theses and Dissertations

The Army’s recruiting landscape has changed markedly in recent years, raising questions about whether forecasting methods of Army contracts remain robust. This thesis recreates the presented models in Joshua McDonald’s 2015 thesis. It replicates and evaluates the models with updated data (2018–2023) to assess their current validity and compare them to novel alternative approaches, such as simpler regression models or neural networks. While the 2015 model remains a valuable baseline, results suggest that either refining its variables or adopting alternative methods can improve predictive accuracy and interpretability. Ultimately, the United States Army Recruiting Command has many options regarding how it …

Machine Learning Techniques To Detect Anomalies In T-38 Flight Sensor Data, Sydney M. Wekamp

Theses and Dissertations

Accurate sensors are critical for ensuring the safety of aircrew. However, detecting faulty sensors remains a significant challenge for the Test Pilot School at Edwards Air Force Base in California. Current methods rely on either student pilots identifying anomalies or waiting for sensors to fail completely before repairs are made—an approach that lacks reliability and consistency. This research aims to address these shortcomings by implementing machine learning techniques to detect sensor faults proactively. To date, applying machine learning to a dataset of this size, encompassing numerous sensors on the same aircraft, is unprecedented. The project focuses on establishing strong baseline …

Evaluating Weather Effects On Sortie Generation Using Discrete Event Simulation, Markus Case

Theses and Dissertations

United States Air Force (USAF) operations rely on sortie generation, a complex system involving aircraft maintenance, operational planning, munitions, security forces, and aircrew. Failures in any of these areas can jeopardize a mission, and extreme weather events such as lightning, high winds, and snow further complicate operations. This thesis examines the impact of extreme weather on sortie generation, focusing on developing a data-driven discrete-event simulation (DES) to predict generation timelines and identify high-risk areas. The model allows users to adjust key inputs, including the month, number of aircraft, processing times, and personnel/equipment availability. By simulating real-world conditions, the model helps …

Data Lakehouse And Machine Learning Pipeline For Aircraft Fuel Efficiency Experimentation, Skyler G. Kepley

Theses and Dissertations

Fuel efficiency is crucial for the U.S. Air Force, impacting mission success, aircraft performance, and cost savings. This study presents an information system that integrates flight and maintenance data using a data lakehouse. It automates ingestion, enrichment, and predictive modeling, leveraging AutoML for optimization and SHAP for transparency. A case study on C-130J aircraft shows that optimizing D Check cycles can save 11.52 pounds of fuel per flight hour. These findings highlight the effectiveness of data-driven decision-making in aviation, offering a scalable, automated solution for improving fuel efficiency and reducing costs.

Island Nation Duress: Simulating Passive Peer-To-Peer Bluetooth Communication During Disaster Relief, Jason K. Medeiros

Theses and Dissertations

Pacific Islands under U.S. jurisdiction are highly vulnerable to natural disasters, yet many lack the infrastructure to effectively respond and recover. Clear communication during and after such events is critical for evacuation, hazard awareness, and first responders’ coordination. This research explores a simulation-based approach using Bluetooth communication to relay messages across Guam, assessing its efficiency through statistical analysis. By examining regional differences and geographic impacts on Bluetooth messaging, the study aims to identify key factors that enhance peer-to-peer communication for timely and effective disaster response.

Machine Learning With Flight Data Recorder Data For Flight Fuel Consumption Predictions, Adam C. Levandowski

Theses and Dissertations

This study applies advanced Machine Learning (ML) to Flight Data Recorder (FDR) data for fuel consumption predictions. It explores feature engineering, model selection, and Hyper-Parameter Optimization (HPO) across all flight phases. Baseline models like Ordinary Least Squares (OLS) regression, Multi- Layer Perceptrons (MLPs), and decision trees are compared to Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs) with Gated Recurrent Unit (GRU) layers, and XGBoost. Results analyze segmentation strategies, tailored features, and model performance. A counterfactual analysis compares ML models to operational fuel predictions, demonstrating their deployment potential. Findings establish a foundation for future ML-driven advancements in aviation fuel optimization.

Class Imbalance: A Landscape Of Classification Models, Joshua L. Edmonds

Theses and Dissertations

Class imbalance poses significant challenges in machine learning classification. This study evaluates the performance of seven models (ANN, k-Means, kNN, LDA, LR, SVM, XGBoost) across multiple imbalance levels (10\%, 5\%, 1 \%, 0.5\%) and investigates the effectiveness of sampling techniques (Undersampling, SMOTE, SMOTE-ENN). ANOVA results confirm that model choice is the most critical factor, with XGBoost and SVM demonstrating superior robustness. SMOTE improves recall but reduces precision, while undersampling generally degrades overall performance. While significant, imbalance levels do not play a critical role in model effectiveness.

Reinforcement Learning For Aeromedical Evacuation In Nonstationary Combat Environments, Micah J. Kartchner

Theses and Dissertations

This research formulates the medical evacuation (MEDEVAC) dispatching problem as a sequential decision process and investigates the application of reinforcement learning under nonstationary conditions. We model the dynamic arrival rate of MEDEVAC requests using a nonstationary Hawkes process and design a Double Deep Q-Network algorithm that incorporates belief states to anticipate future requests. Through computational experimentation, we analyze the impact of belief formulation on decision quality and system performance. Results indicate that policies incorporating belief states significantly outperform myopic dispatching policies, reducing urgent casualty wait times by up to 49.68% and increasing on-time evacuations by up to 21.91%.

A Reinforcement Learning Approach For Maneuvering And Firing Decisions In Sead Operations, Nathaniel Garcia

Theses and Dissertations

The integration of automated processes in defense continues to expand, enhancing the lethality of military forces. Artificial intelligence accelerates decision-making cycles, removes the constraints of human-operated hardware, and improves coordination by enabling seamless integration across multiple systems. Suppression of Enemy Air Defenses (SEAD) missions are critical to the United States (U.S.) military, as they neutralize hostile air defense systems, ensuring air superiority and enabling safe and effective operations for aircraft in contested environments. Therefore, it is necessary to pair emerging autonomous capabilities with an important mission set in defense. This research investigates the Autonomous Unmanned Air-to-Ground Strike (AUAGS) problem, modeling …

Evaluating The Performance Of Conformal Prediction Generated Uncertainty Sets In Robust Optimization, Zion C. Johnson

Theses and Dissertations

Uncertainty is a major challenge in optimization, especially in problems where unpredictable costs impact decision-making. Robust optimization addresses this by modeling uncertainty via uncertainty sets. These sets are then used such that solutions hold under worst-case scenarios, with success depending on the accuracy of the uncertainty sets. This research examines the use of conformal prediction to construct uncertainty sets for RO, an approach that has not been widely explored. We test split and full conformal prediction in a robust optimization minimum cost flow problem, and comparing them to interval-based and normal-based ellipsoidal uncertainty sets. Experiments run across different network structures …