Digital Commons Network^™

Generalizing Medical Image Segmentation Task With Efficient Deep Learning Models, Abel A. Reyes-Angulo

Dissertations, Master's Theses and Master's Reports

Medical Image Segmentation is a critical task in the field of medical imaging, playing a crucial role in diagnostics, treatment planning, and disease monitoring. The emergence of Deep Learning (DL) has ushered in a new era in Artificial Intelligence (AI), propelling remarkable advancements in key domains like language translation, object recognition, and recommendation systems. This evolution has been accompanied by continuous enhancements in computational efficiency and improvements in predictive accuracy. The introduction of sophisticated algorithms, such as convolutional neural networks (CNNs) and transformers, exemplifies these advancements. DL algorithms have demonstrated exceptional efficacy in medical image segmentation tasks, showcasing the potential …

Holistic Energy Efficiency Analysis Of Electrified Off-Highway Material Handler: From Drive Cycle Characterization To Powertrain, Hydraulic, And Thermal System Performance, Alexander Czarnecki

Dissertations, Master's Theses and Master's Reports

Three complexities surrounding the operation and testing of hybrid electric, heavy-duty nonroad machines have been addressed experimentally and using 1D simulation. Their resolutions have been intertwined with the development of a prototype machine that was proven to reduce fuel consumption in excess of 20%. A real-world drive cycle that leveraged hydraulic cylinder position was developed and utilized to ensure accurate reproduction of hydraulic work between the baseline and hybrid machines, while simultaneously maintaining less than 5% RMS error in position for main load handling functions. The newly developed, machine-specific drive cycle also contributed towards making equivalent comparisons in energy consumption …

Examining Student And Faculty Perspectives On Hidden Curriculum In Computing Education, Joseph R. Teahen

Dissertations, Master's Theses and Master's Reports

Hidden curriculum (HC) consists of the assumed behaviors, cultural norms, and collective knowledge that students are expected to know, but never taught. Knowledge such as version control tools, interview and resume skills, and self-regulation can fall into the HC. HC exists in a specific institutional and individual context and can change over time, making it hard to address and examine.

My thesis work is situated around uncovering and addressing HC in computing education. In this thesis I will present relevant background about HC and computing related HC, present my previous work on the College of Computing Resource Hub and the …

Performance And Environmental Impact Of Waste Glass Asphalt In Cold Regions, Kai Xin

Dissertations, Master's Theses and Master's Reports

The reuse of waste glass in asphalt mixtures has significant potential in sustainable pavement engineering, yet its performance under cold, freeze–thaw conditions remain underexplored. This dissertation presents a first-of-its-kind comprehensive evaluation of glass asphalt for cold regions, simultaneously assessing its low-temperature cracking resistance, moisture susceptibility, field performance, and life-cycle environmental impacts. A series of laboratory tests were performed on asphalt mixtures incorporating various proportions of crushed waste glass aggregate, including Disk-Shaped Compact Tension (DCT) and Indirect Tensile (IDT) tests for low-temperature fracture resistance, and Tensile Strength Ratio (TSR) and Hamburg Wheel Tracking (HWTT) tests for moisture damage and rutting susceptibility. …

Estimating Unconfined Compressive Strength (Ucs) Of Rocks From Measurement While Drilling (Mwd) Data, Can Erdem

Dissertations, Master's Theses and Master's Reports

Measurement-while-drilling (MWD) technology enables the real-time monitoring of drilling parameters during the drilling process. MWD data can provide valuable insight into the mechanical behavior of intact rocks and rock masses, which is essential for geotechnical applications such as foundation design and underground construction. The aim of this study is to correlate real-time drilling parameters, recorded using a laboratory-developed MWD system, with the unconfined compressive strength (UCS) of rocks. A custom laboratory MWD system was designed to simultaneously record four key drilling parameters: thrust (axial force, crowd), torque, penetration rate, and rotational speed. The custom-built MWD system was used to continuously …

Identifying Patterns In Avian Plasma Metabolites For Use In Comparing Between-Site Differences In Habitat Quality, Katherine A. Brouwer

Dissertations, Master's Theses and Master's Reports

Habitat loss and degradation are especially important considerations for migratory songbirds, since they depend on a variety of distinct habitats within different life phases (such as breeding, wintering, and migration) that are widely dispersed across a spatial scale. Additionally, abundance of migratory songbirds has been in severe decline, making habitat maintenance and recovery of particular interest as a research avenue. Identifying high quality habitats across a bird’s annual range is therefore of increasing importance and represents fundamental information for guiding management decision making. Free-floating metabolites found in blood are frequently used to determine short-term mass changes in birds and have …

Dam It All: A Multi-Scalar Investigation Into The Ecological Role And Function Of Beaver Dams, Kenneth Larsen

Dissertations, Master's Theses and Master's Reports

The central theme of this dissertation is ecological scaling, which examines how small, localized features, such as beaver ponds, contribute to large-scale watershed processes and how different modeling approaches at various scales reveal distinct insights. Through a combination of probabilistic modeling and high-resolution empirical research, this work demonstrates that small ponded systems, particularly those created by beavers (Castor canadensis), serve as critical biogeochemical control points, whose contributions to sediment and nutrient dynamics have been historically underestimated.

In Chapter 1, I contextualize this research within the broader fields of freshwater ecology, watershed modeling, and ecological restoration. I introduce the …

Innovations In Balanced Mix Design: Establishing Gwp Thresholds For Various Nmas And Evaluating Superpave Vs. Bmd In High Content Rubber Asphalt, Kai Xin

Dissertations, Master's Theses and Master's Reports

Traditional volumetric asphalt mix design methods, such as Superpave, frequently struggle to address critical performance parameters, leading many agencies to seek more robust approaches. Balanced Mix Design (BMD) has emerged as a forward-looking alternative by directly measuring rutting and cracking resistance in the laboratory. In this study, BMD principles were applied to asphalt mixtures featuring three distinct NMAS mixes and two high content rubber mixes, introduced through both dry and semi-wet processes. Compared with conventional volumetric constraints, BMD provided greater flexibility in adjusting binder content and gradation to accommodate elevated crumb-rubber levels. The resulting mixtures satisfied both rutting and cracking …

Bridging Indigenous And Western Knowledge Systems: Centering Ojibwe Perspectives For Just Forest-Climate Futures, Tran Thi Mai Anh

Dissertations, Master's Theses and Master's Reports

This dissertation addresses critical gaps in how environmental science and policy engage with Indigenous knowledges that hinder just and sustainable environmental futures. Through a multi-year partnership with the Keweenaw Bay Indian Community (KBIC), this research tackles a literature gap on applying Traditional Ecological Knowledge (TEK) to forest restoration, an experiential gap in understanding differential climate impacts, and a governance gap perpetuated by colonial metrics that devalue relational ecosystem health.

A multi-method approach systematically addresses these gaps. First, a literature review confirms TEK's application in restoration is under-researched and often extractive. Second, a comparative survey of 232 Tribal and non-Tribal community …

Fine Root And Ectomycorrhizal Functional Traits Of Quercus Rubra Populations From Across A Latitudinal Gradient, Emma L. Shedd

Dissertations, Master's Theses and Master's Reports

Forests are increasingly considered for their carbon sequestration value, but their ability to store carbon is dependent on a close balance between carbon fluxes into and out of ecosystems. Nutrient uptake of roots and associated symbiotic communities results in respiratory carbon release, which is projected to increase with warming and represents a substantial uncertainty in earth system modeling. Traits that are functionally related to nutrient uptake can be used to estimate carbon fluxes, but our understanding of the trade-offs that govern root, and especially fungal, traits is limited. Fine roots in surface soils are responsible for the bulk of plant …

The Combinatorics Of Integer Partitions Enumerated By Some Exotic Weights, Hunter Waldron

Dissertations, Master's Theses and Master's Reports

Identities of integer partitions generally state that two dissimilar appearing families of partitions are in fact equinumerous when both are restricted to any fixed size. Euler's theorem is a classic example of such an identity, which equates the number of partitions with odd parts to the number of partitions with distinct parts. Lately, analogs of known partition identities involving weights other than size have begun to attract research interest. This dissertation is an investigation of two such weights. In Chapter 2, we study Schmidt weights, which count only parts with indices belonging to some given subset of the positive integers. …

Iron Ore Tailings Reprocessing By Electrostatic Separation Plus Two Stages Froth Flotation, Vincent Bailey Arohunmolase

Dissertations, Master's Theses and Master's Reports

The reprocessing of tailings is crucial for recovering valuable iron and reducing the environmental impact associated with tailings disposal. This study investigates the practicality of reprocessing tailings to enhance iron oxide content, combining electrostatic separation with a two-stage froth flotation process using oleic acid (direct flotation) and amine (reverse flotation). The primary goal is to efficiently recover valuable iron from tailings, thereby reducing waste and promoting sustainable resource utilization. The process aims to upgrade the iron oxide content to around 93-99% Fe₂O₃, making the recovered material suitable for the production of direct-reduced iron.

Electrostatic separation was …

Towards Developing Glut2 Specific Probes For Biochemical And Biomedical Applications, Abdelrahman Ismail

Dissertations, Master's Theses and Master's Reports

Facilitated Glucose transporters (GLUTs) are membrane proteins responsible for the uptake of simple sugars and other structurally similar metabolites in all mammalian cells. One of the hallmarks of cancer is dysfunctional sugar metabolism, known as the Warburg effect, and one of the manifestations of that effect is abnormal GLUT expression. There are 14 known GLUT proteins with different expression patterns in different tissues, and tumors tend to express certain GLUTs that are not present in surrounding healthy tissue. Therefore, selective targeting of GLUTs presents a potentially powerful tool for diagnostics and treatment of cancer and other diseases. This has been …

Climate Planning, Energy Sovereignty, And Electric Vehicle Perceptions Among Michigan’S Tribal Nations, Alexis Belle Tater

Dissertations, Master's Theses and Master's Reports

Climate change will especially impact marginalized communities and communities with less government support for funding climate adaptation actions. The first chapter of this report focuses on climate change responses, specifically Tribal Nations in the state of Michigan. In the current U.S. context, funding for large climate change mitigation and adaptation projects in Tribal Nations can be achieved through federal funding from the CPRG (Climate Pollution Reduction Grant), which requires an established PCAP (Priority Climate Action Plans) to guide decision making in alignment with identified priorities. I discuss the importance of Tribal sovereignty, the potential implications of its inclusion and exclusion …

Phase-Field Method Of Fracture In Fiber-Reinforced Polymer Composites: Theory, Modeling, And Validation, Akash Kumar

Dissertations, Master's Theses and Master's Reports

Fiber-reinforced polymer composites (FRPCs) are widely used in aerospace, automotive, and civil engineering due to their high specific strength, stiffness, and durability. However, their anisotropic and heterogeneous nature makes fracture prediction challenging, with damage modes classified as intralaminar failure (matrix cracking, fiber breakage, fiber-matrix debonding) and interlaminar delamination. Delamination, driven by weak through-thickness strength and high interlaminar stresses, is a predominant failure mechanism in FRPCs. While cohesive zone models (CZMs) are commonly used for delamination, they are computationally expensive and inefficient for capturing intralaminar fractures where crack paths are unknown. To address this, we developed a unified phase field-based cohesive …

Molecular Modeling Methods And Applications For Accelerating Polymerization And Pyrolysis Studies, Joshua D. Kemppainen

Dissertations, Master's Theses and Master's Reports

Polymer matrix composites and carbon-carbon composites play critical roles in the aerospace, automotive, and construction industries. Different matrix materials and processing conditions can lead to a large variety of composite materials and composite properties. Integrated computational materials engineering has been used to tailor PMC matrix materials and processing conditions to specific properties and manufacturing techniques. The integrated computational materials engineering process modeling framework uses molecular dynamics at the nanometer length scale to characterize the evolving thermo-mechanical properties of the polymer as it cures. Then finite element analysis is used at the micrometer length scale to adjust cure cycles to tailor …

Schaper Numbers, Palindrome Partitions, And Symmetric Functions, With Applications To Characters Of The Symmetric Group, Karlee J. Westrem

Dissertations, Master's Theses and Master's Reports

Finding the decomposition numbers for the symmetric group is a difficult problem and has led to many different research directions. For a given Specht module, the Schaper sum formula can be refined with knowledge of the Schaper number for the particular partition to give more precise information about the decomposition numbers. In Chapter 2, we give a combinatorial formula for the Schaper number when the partition has at most two columns. At the end, we provide a conjecture for the Schaper number for the partition of shaper (3^n).

Chapter 3 covers the joint work with my advisor, David Hemmer, and …

Great Lakes And Its Regional Climate In The Future, Miraj Bhakta Kayastha

Dissertations, Master's Theses and Master's Reports

The overarching objective of this dissertation is to enhance our predictive understanding of the Great Lakes regional climate by utilizing advanced modeling techniques and provide comprehensive insights into the future of the Great Lakes. This dissertation focuses on four areas pertinent to the future of the Great Lakes hydroclimate and extreme events, beginning with the derivation of robust water level projections for the Great Lakes in Chapter 2. Using a regional climate modeling system with a two-way coupled three-dimensional (3D) hydrodynamic lake and ice model for the Great lakes, we analyze long-term future changes in the over-lake precipitation, lake evaporation, …

From Plasmonics To Superfluorescence: Engineering Light- Matter Interactions For Quantum Optical Phenomena, Aaron J. Wildenborg

Dissertations, Master's Theses and Master's Reports

This work presents different ways to engineer light-matter interactions by using nanostructures to exploit quantum-optical phenomena. First, sodium (Na) is predicted to be an ideal plasmonic material due to its ultra-low optical losses from the visible to the near-infrared (NIR). However, Na has practical limitations due to its high chemical reactivity. Using a scalable fabrication method for Na plasmonic nanostructures by combining phase-shift photolithography and a thermo-assisted spin-coating process, we produced nano-pit arrays of varying periodicities (300-600 nm), supporting tunable surface plasmon polariton (SPP) modes spanning visible to NIR. These structures demonstrated SPP resonances as narrow as 9.3 nm, with …

Investigating Dimensions Of Social Vulnerability To Wildfire: A Case Study Of Western Montana, Ella Brodowski

Dissertations, Master's Theses and Master's Reports

Communities across the US are facing increased wildfire risks due in part to historic fire suppression efforts, a warming climate, and an influx of people residing in wildland urban interface (WUI) landscapes. Because of these increasing risks, there have been growing concerns about the social factors that can increase individual and community vulnerability to wildfires. This research adds to the discussion of social vulnerability by examining how people living in a geographic area with heightened wildfire risk think about the ways in which people can be more or less vulnerable to wildfires. Using semi-structured interviews, round table discussions, and field …

Relict Ponderosa Pine Mortality And Fuels Study In The Bob Marshall Wilderness, Montana, Usa, Laura K. Schimmel

Dissertations, Master's Theses and Master's Reports

Many forests have historically experienced mixed-severity fire regimes that were disrupted during the 20th century due to fire exclusion policy. A stand of relict Pinus ponderosa in the Bob Marshall Wilderness Complex that burned in 2003, 2011, and 2018 provides a unique case study for investigating the effects of returned fire to the landscape. Many of the trees have fire scars or Indigenous bark-peeling scars, preserving valuable ecological and anthropological history. We sought to determine whether scarred trees were more susceptible to fire damage, if larger trees had greater fire resilience than smaller trees, and if fuel loads have changed …

Proximal Seismic Tracking Of Pyroclastic Density Currents At Volcán De Fuego, Guatemala, Jacob A. Krier

Dissertations, Master's Theses and Master's Reports

Pyroclastic Density Currents (PDCs) are deadly flows of ash, tephra, gas, and solidified magma which predominantly occur when an ash plume collapses during a volcanic eruption. PDCs are also able to form when large deposits of ash at the summit of a volcano are displaced during an eruption and flow downslope. This is typically the mechanism behind PDCs that occur at Volcán de Fuego such as one that occurred in 2018 killing at least 430 people. The purpose of this paper is to track the propagation of PDCs that occurred at Fuego seismologically in order to better understand how they …

Knowledge Integrated Deep Learning For Enhanced Fault Diagnosis And Prognosis For Rotating Machinery And Its Applications On Marine Systems, Yunsheng Su

Dissertations, Master's Theses and Master's Reports

This dissertation develops a knowledge-informed deep learning framework for robust fault diagnosis and prognosis across various engineered systems, including bearings, lithium-ion batteries, and mooring systems in wave energy converters (WECs). A deep transfer learning (DTL) method is first developed to improve bearing fault diagnosis by fusing data from multiple sources and extracting key features using convolutional neural networks (CNNs). Building upon this, a knowledge-informed deep network (KIDN) framework is proposed, integrating physics-based features with deep learning to enhance diagnostic accuracy and generalizability. A constrained Gaussian process (CGP) model is further employed to guide adaptive network design and reduce model tuning …

Barbie Vlogger As Teen Influencer For Little Girls, Brilynn A. Janckila

Dissertations, Master's Theses and Master's Reports

Mattel’s YouTube Barbie Vlogs series (2015-2022) targets 6–11-year-old girls with short narratives and prosocial messages addressing their prevalent interests and everyday experiences. While the vlog is clearly an attempt by Mattel to appeal to a market sector that includes both little girls and their Millennial parents, this analysis examines Barbie Vlogger as a social media influencer in order to explore how little girls learn to become older girls through the performance of teenage girlhood as enacted in the Barbie Vlogs. What is Barbie doing in the vlogs to show little girls who a teen girl is and what she …

Processing And Densification Of Multi-Phase High-Entropy Ceramics, Steven Smith

Doctoral Dissertations

"This work focuses on the processing and densification of multiphase, high-entropy ceramics to promote their use in friction stir welding technologies. Several high-entropy systems including high-entropy borides, carbides, and their composites were produced. Boro/carbothermal and carbothermal synthesis were used to produce high-entropy powders from oxide powder mixtures. Composites of high-entropy borides and high-entropy carbides were produced using a sequential approach to produce both phases. The carbide was first produced using carbothermal reduction, then ZrH2 and B4C were added to the carbide powder to produce the high-entropy boride phase. The resulting powder was densified by spark plasma sintering and pressureless sintering, …

Application Of Artificial Intelligence Techniques To Improve Leadership Decision Making With Uncertainty, Michael David Parrish

Doctoral Dissertations

"Every good leader is a good manager, but not every good manager is a good leader. The difference between the leader and the manager is critical decision-making. Today’s decision-making environment is characterized as Volatile, Uncertain, Complex, and Ambiguous (VUCA). With the exponential increase in the technical capabilities of systems, the human has become the weakest link in the use of such systems. To remain relevant, good leaders must continuously adapt to new advances in technology and processes.

The research contributions of this work provide several unique and novel solutions for leaders to utilize artificial intelligence tools to improve and optimize …

A Hybrid Data Processing, Computational Intelligence, And Complex Systems Modeling Approach For Describing And Predicting The Bitcoin Market, Oluwadamilare Akinpelu Omole

Doctoral Dissertations

"The Bitcoin market, like traditional financial markets, is a complex system with intricate interdependencies and nonlinear interactions among various market elements. This, coupled with the inherent uncertainty and high volatility present, makes predicting Bitcoin price movements difficult. The lack of understanding of the underlying market dynamics often results in significant losses for investors and traders. Existing studies have focused on the use of predictive models, which have not sufficiently captured the complexities of the market and cannot forecast extreme market events. This research endeavors to bridge this gap by combining data processing techniques, computational intelligence, and complex systems theory to …

Atmospheric Transport Of Radionuclides, Meteorological Data Mining & Synthesis For Site Data Supplementation, Ben Yao Sonpon

Doctoral Dissertations

"This research aligns with the NRC's vision of implementing risk-informed decision-making to support its regulatory charter. The suite of tools developed includes automated procedures for data mining and extracting meteorological (met) data from various national and regional repositories. A second data analytics tool automates the process of data fusion into a uniform format while preserving data fidelity. Autocorrelations were then established, and correlation coefficients were calculated between the Callaway Nuclear Power Plant (Callaway) and nearby off-site weather stations. The complexity of these correlations depends on factors such as physical proximity, geographic features, and topology, potentially necessitating multivariate analysis (MVA). Furthermore, …

Lifelong Machine Learning With Adaptive Resonance Theory, Sasha Petrenko

Doctoral Dissertations

"This publication option dissertation is composed of three papers concerning the study of the problem lifelong machine learning with Adaptive Resonance Theory (ART) algorithms. Lifelong learning (L2) is a challenging machine learning paradigm that both encompasses and formalizes the fields of continual learning and incremental learning. The field is concerned with the mitigation of the phenomenon of catastrophic forgetting whereby learning agents that are faced with incrementally novel information deleteriously overwrite previous knowledge if that learning process is not regularized to counteract this consequence. ART algorithms solve this stability-plasticity dilemma by optimally assigning learning to categories or instantiating new knowledge …

Nmr Relaxometry Approach For The Detection Of Asphalt Binder Performance Properties, Rebecca Herndon

Doctoral Dissertations

"Asphalt is a necessary material for transportation infrastructure. Understanding the material properties of asphalt binders is critical for improving infrastructure and enhancing the lifetime of pavements. While the physical properties of asphalt binders are well-defined by standard procedures and parameters, the chemical environment lacks definition. Physical parameters like viscosity and stiffness are traditionally used to differentiate asphalt binders, describe aging, and indicate the impact of additives. However, these tests have limited insight into the material's chemical environment. Therefore, a nondestructive analytical technique, nuclear magnetic resonance (NMR) relaxometry, was employed to investigate the chemical environment of asphalt binders. Although NMR relaxometry …