Digital Commons Network^™

A Unified Framework For Distributed And Resource-Aware Plant Disease Detection Using Federated And Adaptive Hybrid Deep Learning, Ticauris S. Stokes

Master's Theses

Plant disease detection in precision agriculture must operate under significant computational constraints, particularly in low-resource (LR) environments such as unmanned aerial vehicles (UAVs) and edge devices. While LR models enable efficient real-time inference, they often lack the representational capacity required to accurately detect complex disease patterns. In contrast, high-resource (HR) models achieve superior detection performance due to their deep architectures but are computationally expensive and unsuitable for direct deployment in resource-constrained settings. This fundamental trade-off between efficiency and accuracy presents a major challenge for practical agricultural monitoring systems.

To address the distributed nature of agricultural data, federated learning (FL) is …

Redeveloping Mississippi: A Case Study On Brownfields In Central & Southern Mississippi, Sahrah R. Yeroozedek

Master's Theses

Brownfields, or properties that are or possibly are contaminated with dangerous materials, represent a common obstacle for communities in Mississippi. The real or potential presence of contaminants at these sites often deters investors due to costly cleanup requirements (EPA, n.d. -b). The Environmental Protection Agency (EPA), through its Brownfield Revitalization Program, implemented guidelines for covering the costs and labor associated with the remediation of these properties. The EPA is not, however, responsible for redevelopment that supports long-term environmental and economic sustainability. Although the EPA maintains inventories of all Brownfields, there is also no comprehensive database of Brownfields and their current …

Evaluating Modern Neural Network Architectures For Suicide Prediction, Kyle Brown

Master's Theses

Suicide remains a leading cause of death among adolescents despite more access to healthcare information than ever before. Medical professionals struggle to make accurate diagnoses and catch warning signs with the overwhelming amount of data available. Machine learning algorithms, including neural networks, have previously been employed for this task, yet it remains an understudied domain.

This research aims to evaluate the capabilities of Multi-Layer Perceptron (MLP) and a selection of its successors, ResNet and MLP with a category embedding layer, at the task of predicting suicidal ideation among high-school students. This research finds ResNet to be the most capable at …

Best Practice: Ct-Guided Adaptive Radiotherapy Reference Planning On The Ethos Platform, Xenia Ray, Joseph Harms, Alex Price, Mu-Han Lin, Dennis N Stanley

2020-Current year OA Pubs

Online adaptive radiotherapy (ART) enables treatment plan modifications based on the patient's anatomy at each fraction, addressing limitations of conventional radiotherapy that relies on a static pre-treatment plan. CT-guided ART (CTgART), as implemented on the Varian Ethos platform, has gained increased clinical adoption over the past several years; however, its success is highly dependent on reference plan design due to limited on-table planning flexibility. As a result, clinicians creating and reviewing reference plans will greatly benefit from both understanding how upstream planning decisions affect the downstream adaptive process and proactively incorporating strategies that improve optimization robustness and efficiency on-treatment. We …

Adapt-On-Demand: Enabling Flexible And Scalable Adaptive Radiotherapy Through Workflow Automation, Sean Domal, Min Geon Choi, Justin Visak, Ruiqi Li, Taoran Li, Boon-Keng Kevin Teo, Xiaodong Zhao, Matthew Schmidt, Eric Laugeman, David Parsons, Yang Kyun Park, Shahed Badiyan, David Sher, Mu-Han Lin

2020-Current year OA Pubs

PURPOSE: CT-guided adaptive radiotherapy (CTgART) offers significant clinical benefits, but its utilization is often limited by resource demands and rigid workflows. This study presents a flexible and scalable "Adapt-on-Demand" (AOD) framework that integrates the adaptive capabilities of the Varian Ethos platform with the high-throughput IGRT delivery of the Varian Halcyon, supported by automated scripting.

METHODS: We developed an end-to-end dual-platform workflow that dynamically transitions between ART and IGRT delivery based on patient needs. Key components include Eclipse Scripting API (ESAPI) automation to streamline adapted plan ingestion from the Ethos Treatment Planning and Management System (TPMS) export directory, compatibility conversion for …

Statutory Backups For Endangered Constitutional Rights, Aaron-Andrew P. Bruhl

Faculty Publications

This Article concerns the phenomenon of “statutory backup rights,” or statutes that provide protections parallel to constitutional rights that are believed to be at risk of judicial abrogation. Proposals for backup rights gained attention in the aftermath of the Supreme Court’s 2022 decision in Dobbs v. Jackson Women’s Health Organization, which not only eliminated the constitutional right to abortion but called into question some other constitutional rights as well. Shortly after Dobbs, Congress enacted a limited statutory backup for same-sex marriage. States have created backup rights across a range of topics, some of which appeal mostly to those …

Computational Fluid Dynamics-Based Risk Stratification Of Modified Blalock-Taussig-Thomas Shunt Thrombogenicity, Yi Qiao, Ethan Penn, Jacob Miller, Scott Bugenhagen, Ram Rohatgi, Kelsey Mercer, Blaire Kulp, Jinli Wang, Pirooz Eghtesady, Guy M Genin, Edon J Rabinowitz, David Bark

2020-Current year OA Pubs

BACKGROUND: The modified Blalock-Taussig-Thomas shunt (mBTTS) is a critical palliative procedure for infants with single-ventricle physiology, but thrombosis-related occlusion affects 8% to 12% of infants and carries nearly 50% mortality. Meanwhile, existing antithrombotic strategies fail to address the hemodynamic factors driving thrombosis, highlighting the need for a deeper understanding of flow dynamics in shunt failure.

OBJECTIVES: This study aims to identify how mBTTS geometry influences hemodynamics and thrombosis risk, providing quantitative guidance for surgical planning and shunt design optimization.

METHODS: We used patient-specific imaging data to test 54 idealized mBTTS configurations, systematically varying key geometric factors: pulmonary artery diameter, shunt …

Sticky Charters? The Surprisingly Tepid Embrace Of Officer-Protecting Waivers In Delaware, Jens Frankenreiter, Eric L. Talley

Faculty Scholarship

This article examines the response to Delaware’s much-heralded 2022 legal reform that permitted corporations, for the first time, to adopt charter provisions exculpating corporate officers from liability for breaching their fiduciary duty of care. Contrary to widespread predictions that corporate actors would swiftly adopt officer exculpation provisions, our analysis — using both traditional and generative artificial intelligence (AI) methods — reveals a surprisingly low rate of uptake, over three years after the reform’s enactment.

Our study makes both methodological and substantive contributions. Methodologically, we present a novel application of large language models (LLMs) to identify and interpret technical clauses in …

The Federal Reserve’S Fiscal Agent Mandate And The Problem For Central Bank Independence, Lev Menand, Joshua Younger

Faculty Scholarship

The Federal Reserve is among the most powerful organs of government. It is tasked primarily with maintaining the growth of monetary and credit aggregates consistent with long-run maximum employment and price stability. This mandate is widely known and the subject of extensive public debate. But another mandate lies within the statute that is largely overlooked — to serve as fiscal agent of the United States. This distinct responsibility is older, and also important. This Article offers a comprehensive assessment of where the Fed’s two mandates overlap and occasionally sharply conflict: in the market for U.S. government debt. First, it identifies …

High-Performance Simulations Of Higher Representations Of Wilson Fermions, Vincent Drach, Sofie Martins, Claudio Pica, Antonio Rago

School of Engineering, Computing and Mathematics

We present HiRep v2, an open-source software suite for high-performance lattice field theory simulations with dynamical Wilson fermions in higher representations of SU(Ng) gauge groups. This new version fully supports graphics processing unit (GPU) acceleration, optimizing both gauge configuration generation and measurements for NVIDIA and AMD GPUs. HiRep v2 integrates improved gauge and fermionic lattice actions, advanced inverters, and Monte Carlo algorithms, including the (Rational) Hybrid Monte Carlo ((R)HMC) with Hasenbusch acceleration. It exhibits excellent scalability across multiple GPUs and nodes with minimal efficiency loss, making it a robust tool for large-scale simulations in physics beyond the Standard Model.

Together In Sync: Assessing Prosocial Behavior With A Full-Body Interactive Mixed Reality Experience, Sena Beste Ercan, Belen Gonzalez, Olga Gali, Gray Atherton, Liam Cross, Narcis Pares

School of Psychology

This study investigates how interpersonal synchrony (IPS) in full-body interactive Mixed Reality (MR) environments can shape children's prosocial behavior. We introduce DragonIce 2.0, a two-part MR game designed to induce synchronous or asynchronous group activity and assess their impact on prosocial behavior. To examine changes in affiliation (team belonging and peer liking) and collaboration (overt joint actions), we conducted a comparative study with children aged 9–10, using both system logs and self-report measures. The results highlight the importance of context, task structure, and perceived coordination in shaping social outcomes, offering insights into how interaction dynamics shape social engagement in immersive …

Pedagogical Strategies In Medical Laboratory Science Student Learning Outcomes: A Comparative Study Of Learner-Centered And Lecture-Based Instruction, Kasey Kuker

Medical Laboratory Science Independent Study Projects

Learner centered teaching (LCT) has gained prominence across the health sciences, yet its specific impact on Medical Laboratory Science (MLS) education remains underexamined. This comparative literature review synthesizes findings from various empirical studies to evaluate how active, learner centered pedagogies - such as flipped classrooms, blended learning, team based learning, simulation, gamification, and structured feedback - perform relative to traditional lecture based instruction. Across diverse MLS and allied health contexts, LCT consistently improved cognitive outcomes including examination performance, laboratory skill proficiency, and long term retention. Equally significant were gains in affective outcomes: heightened self efficacy, motivation, engagement, teamwork, and professional …

Evaluation Of Radar-Derived Polarimetric Precipitation Estimates For Extreme Rain Events Using A Dense Network Of Rain Gauges, Bong Chul Seo, Witold F. Krajewski, James A. Smith, Alexander V. Ryzhkov

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The study evaluates radar-based quantitative precipitation estimations (QPEs) for 10 extreme rain events that occurred between 2013 and 2019 in the Kansas City metropolitan area, United States. These precipitation estimates were derived at hourly and approximately 0.5-km scales using two polarimetric QPE algorithms}one based on specific attenuation (A) and the other on specific differential phase (KDP)} for the study area covered by two overlapping radars in Topeka, Kansas, and Kansas City, Missouri. The polarimetric QPE assessment for extreme rain events was motivated by improved flood forecasting and precipitation frequency analysis. The analysis utilizes ground reference observations from a dense network …

Smart-Charge: Stable Matching Algorithm For Electric Vehicle Charging In Subscription-Based Models, Arindam Khanda, Anurag Satpathy, Sajal K. Das

Computer Science Faculty Research & Creative Works

The transition from internal combustion engine (ICE) to electric vehicles (EVs) introduces several challenges, including limited charging infrastructure, unpredictable charging wait times, and inefficient selection of charging points (CPs). To address these issues, we propose SMART-CHARGE, a framework that efficiently assigns EVs to CPs through an edge-level coordination mechanism within each service region, enforced by roadside units (RSUs). Operating under a novel subscription-based charging model, SMART-CHARGE enforces predefined charging time limits via service-level agreements (SLAs). The EV-CP assignment problem is formulated as a one-to-many matching game that captures EV user preferences. To construct bounded yet efficient EV coalitions at each …

Leading Ai Adoption In Organizations: Introducing A Behavioral Human-Centered Approach, Shane Schweitzer, Devesh Narayan, Jack Mcguire, David De Cremer

Research Collection Lee Kong Chian School Of Business

Initiatives to implement AI technologies in organizations fail at an alarming rate. We argue that leading the adoption of AI is not a simple engineering exercise but rather represents a behavioral exercise where change management principles—the process by which organizations plan, implement, and embed changes in practices—are employed. However, many AI initiatives in business focus predominantly on the AI systems themselves, assuming humans will fall in line. To solve this, we integrate ideas from change management with scholarship on human-centered artificial intelligence to offer a behavioral approach that accounts for the impact of AI adoption on humans at all stages …

Inequity In Education Through The Lens Of Social Studies Curriculum Using Studies Weekly, Emma Roy

Honors Theses

This study examines the representation of the Civil Rights Movement within the Studies Weekly elementary social studies curriculum and evaluates its alignment with culturally relevant pedagogy, critical race theory, and civic education frameworks. Through a qualitative content analysis of twelve assessment questions and accompanying lesson materials, the findings reveal consistent patterns of oversimplification, limited historical nuance, and an overreliance on factual recall. Key themes including systemic racism, collective activist, and diverse historical perspectives are minimized or omitted altogether. These omissions contribute to what scholars identify as curriculum bias, where dominant narratives are privileged while marginalized voices are unheard. The results …

The Privacy Paradox: How Does Concern About Privacy Impact Actions In The Digital Age?, Julia Laduke

Honors Theses

The privacy paradox occurs when people claim to care about their digital privacy, but do not take actions to keep their data from being spread across the internet. This study examines college students, being primarily Generation Z, and their concerns and actions regarding digital privacy and security. A survey of 15 college students, 7 in humanities and 8 in STEM, was used to analyze their thoughts and concerns about their digital privacy. This survey also asked whether they took actions concerning their privacy, and if so, what tools they used to protect it. The results show that about 50% of …

Calibrating Human Trust In The Age Of Generative Ai: An Examination Of Ethical And Social Challenges, Abigail M. Mondido

Honors Theses

Generative AI (GenAI), a set of AI technologies with the ability to generate original, human-like outputs, is beginning to transform the way that information is distributed, composed, published, obtained, analyzed, and consumed. GenAI has seen massive adoption by internet users, businesses, and organizations in recent years despite the persistence of major ethical concerns and social implications. In particular, existing research has identified multiple critical trust-related issues associated with AI in general, including widespread mistrust and distrust, overreliance on AI, and a lack of trustworthiness of AI. There remains a need for a broader understanding of these issues as they relate …

Hardware Integration Of Preamble Based 802.11a Wi-Fi Frame Location For Usrp Radios, Nicholas P. Margavio

Honors Theses

Internet of Things (IoT) refers to a network of devices that can exchange information over the internet, and its deployments are projected to reach 30.9 billion by 2025, with most lacking encryption. One solution for these unencrypted devices is to use Specific Emitter Identification (SEI). SEI exploits distinct, native, and unintentional features of a radio’s signal to identify it and enhance wireless network security uniquely. For example, IEEE 802.11a Wireless-Fidelity (Wi-Fi) radio waveforms have a fixed structure that occupies the first 16 microseconds, from which SEI features can be extracted and used to identify the originating radio. By removing the …

Creative Nonfiction Essays, Colby S. Langley

Honors Theses

To write about the present with any authority requires a keen eye for the past. To write from our lives into meaningful creative nonfiction requires a firm understanding that experience is the composite of life experience blending into the current moment. The writing is then drawn irreversibly towards emotion: indulgent and oppressive. The extremity of emotion dictates the difficulty of transcribing the experience onto the page, and violence is a source of both extreme emotion and experience. It is important to note that I am primarily considering personal violence for this essay, while societal and institutional violence have their own …

Resilience By Living With The Land And Community: A Case Study Of A Local Food Forest, Olivia Beck

Honors Theses

Imagine a public space where food, leisure, outdoor activity, and community engagement occur in one place, all in an urban forest ecosystem. For many, this is a hopeful vision of the future, and that is exactly what the idea of an urban food forest provides. In agroecology, a food forest or forest garden consists of planting diverse edible plants and mimicking the patterns of natural ecosystems. The intricate planning and design ensure the forest is self-sustaining, much like a natural forest, making it very resilient once established. However, they face many challenges and take time to grow and develop to …

Preliminary Vascular Plant Checklist Of The City Of Chattanooga, Matthew J. Scott

Honors Theses

The City of Chattanooga, Tennessee was designated as a National Park City in April 2025 by the National Park City Foundation. Yet, there has not been a comprehensive vascular flora compiled for the city, though there have been extensive collections and observations made of the plant biodiversity in the area from the late 1800s onward. The goal of this project was to examine both the existing herbarium collections and public observation records from iNaturalist to compile a preliminary vascular plant checklist for Chattanooga, and to include conservation and ecological data for the species currently documented to provide a holistic review …

Contrasting Roles Of Downed Wood And Leaf Litter In Structuring Aphaenogaster Ants And Other Forest-Floor Arthropod Communities, Danielle E. Dolan

Great Lakes Center Masters Theses

Forest floors are dynamic and spatially heterogenous landscapes characterized by differing amounts of light, temperature, and moisture. Bounded substrates, like downed wood and leaf litter, add further complexity to this landscape. Specifically, downed wood is noted for its ability to retain a higher moisture level than the surrounding environment, and as such can serve as an ideal microhabitat for desiccation intolerant organisms (e.g., salamanders and eusocial insects). Here, I attempt to disentangle the relationship between forest floor arthropods and microhabitat selection (i.e., downed wood vs leaf litter) on a northeastern forest floor. The ant, Aphaenogaster picea, was chosen as my …

The 5i’S Framework Of Creative Self-Leadership, Maggie Cubbler

Creativity and Change Leadership Graduate Student Master's Projects

The purpose of this Master of Science in Creativity and Change Leadership project is to establish a framework for Creative Self-Leadership (CSL) development. Viewed through a gendered lens, the framework addresses how women's intrapersonal processes—the 5I's of introspection, interoception, intuition, imagination, and intrinsic motivation—are often compromised by sustained environmental and systemic pressure, and proposes practices designed to restore and strengthen these internal guides.

By recalibrating these intrapersonal processes toward accurate self-knowledge, CSL employs the science of creativity to lead women in their own quest for change, agency, and resilience while remaining cognizant of the dynamic between her and her environment.

Techno-Imagination: Elevating Creativity Through Xr And Ai, Christopher Spitzer

Creativity and Change Leadership Graduate Student Master's Projects

Techno-Imagination: Elevating Creativity Through XR and AI explores the history of creativity and computing technology, supported by research and academic literature, and looks at the possibilities of a convergence between the two. In parallel, a brief biographical story of the author shares how a passion for creativity emerged, along with a growing interest in science and technology—specifically extended reality—which ultimately came together in the creation of this master’s project. The project also highlights how the Creative Problem Solving (CPS) process was used alongside AI bots and twenty research-based creative thinking skills in developing the business model canvas. Finally, the outcome …

Leading The Choreography: Preserving Creative Agency In Ai-Supported Problem-Solving, Mikhaila Ackerbauer

Creativity and Change Leadership Graduate Student Master's Projects

As artificial intelligence tools become increasingly present in creative and problem-solving contexts, a critical question emerges: how can users engage with AI in ways that preserve rather than erode their own creative capacity? This project explores that question through research synthesis, practitioner conversations, coursework, international conference presentations, and the development of custom AI chatbots trained in the Creative Problem-Solving process. The central finding is a theoretical triangle comprising three interdependent capacities: autonomy, creative self-efficacy, and critical thinking. Grounded in Rhodes' (1961) Four P's framework, the triangle sits within the Person dimension. Convergent themes across the literature, practitioner conversations, and direct …

News, Breaking: The Enduring Role Of Local Journalism Amidst Rapid Digitalization And Media Market Decline, Emily Atha

Senior Honors Theses

The landscape of media production and consumerization is evolving with the ushering in of an increasingly digital era. Print newspapers are declining, digital media is delivered faster than ever and social platforms are gaining dominance. The evolution of the industry challenges the role of local news organizations and the ethics they are built upon. Not only have the modes of news collection and delivery changed, but the core perceptions and relationship between the media and public are shifting. This thesis seeks to understand how the digitalization of media and integration of artificial intelligence into digital journalism affect public trust, particularly …

An Exploration Of The Autorotating Pendulum Model, Vlad Nita

Theses, Dissertations and Culminating Projects

Autorotation is the spontaneous rotation of an object, usually caused by an external fluid flow. The study of autorotation has many physical applications, such as in the design of wind/water turbines. In this thesis, we explore a nonlinear pendulum ordinary differential equation (ODE) which is used to model rotating plates in a fluid and has the capacity to reveal autorotation. In the context of an ODE, autorotation emerges as a bifurcation past oscillations, when the initial velocity of the system crosses a particular threshold. In his classic study from 1983, Lugt [14] utilizes this equation to capture experimental autorotation. Copeland’s …

Benthic Faunal Recruitment To Hesco Units In Barnegat Bay, Nj, Luke C. Blanchard

Theses, Dissertations and Culminating Projects

Forked River in Barnegat Bay, New Jersey, has undergone multiple ecological restoration and coastal remediation efforts in recent years. Among these initiatives is the installation of HESCO units, large wire-mesh cages filled with rock and shell substrate, designed to reduce shoreline erosion while simultaneously providing structural foundation for oyster-reef development. This study evaluated benthic fish and decapod recruitment associated with these installations using smaller-scale oyster boxes as analogs for HESCO habitat. Ten oyster boxes, each consisting of wire-mesh containers filled with oyster shell substrate, were deployed adjacent to the HESCO units beginning in June 2025 and retrieved at monthly intervals …

Examining Dimensions And Patterns Of Arts Participation In Relation To Positive Youth Development Outcomes Across Socioeconomic Contexts, Yasmine Perry

Theses, Dissertations and Culminating Projects

Grounded in the Phenomenological Variant of Ecological Systems Theory and the Positive Youth Development framework, the purpose of the current study was to examine how dimensions of arts participation, specifically breadth, intensity, and duration, relate to Positive Youth Development (PYD) outcomes and whether socioeconomic status (SES) moderates these associations over time. Data were drawn from three waves of the 4-H Study of Positive Youth Development. The analytic sample included 747 adolescents aged 12 to 18, capturing a developmental period marked by identity exploration and increased engagement in organized activities. A combination of longitudinal, person-centered, and moderation analyses was used to …