Digital Commons Network^™

Multimodal Aerial Image-Based Ground Object Detection And Classification Using Yolo, Erik Nielsen

All Theses

Object detection in unmanned aerial vehicles (UAVs) present a unique challenge due to small object sizes, varying viewpoints, and changing environmental conditions. These challenges are exacerbated when operating during daytime and nighttime scenarios where illumination differences can heavily impact detection performance. This work is motivated by military object detection applications where the ability to reliably identify small objects such as landmines or unexploded ordnance from aerial imagery presents a critical safety need and a significant technical challenge. In this paper, we investigate object detection using both visible (RGB) and infrared (IR) imagery to improve robustness and reliability across diverse operating …

On The Paleontology Of Belize, Alson Ovando

Electronic Theses and Dissertations

Paleontology can be considered an underrepresented and emerging area of science in Belize. A primary aim of this thesis is to provide a background of paleontology in Belize and present the first comprehensive study of Quaternary vertebrate fossils known from the country. Quaternary fossil sites across Belize include caves, rivers, and sinkholes. In addition to reviewing and assessing material from known sites, this thesis presents new information and discoveries that were made while investigating Belize’s Quaternary fossil record. This thesis also includes a geospatial model depicting ecoregions in Belize during the last glacial maximum. Overall, the results presented here demonstrate …

Stochastic Universal Differential Equations For Epidemiological Modeling: Uncertainty Quantification In Disease Transmission Dynamics, Alice Menaya Armah-Bonney

Electronic Theses and Dissertations

Epidemic forecasting requires not only predictions of expected case counts, but also quantification of uncertainty, although existing surrogate modeling frameworks for agent-based models remain fundamentally deterministic. In this thesis a Stochastic Universal Differential Equation framework is presented that extends the deterministic Universal Differential Equation approach by incorporating a learnable stochastic diffusion term, enabling calibrated probabilistic forecasts while preserving the mechanistic interpretability and computational efficiency of the deterministic baseline. In doing so, a two-phase training algorithm is introduced to ensure stable convergence and the framework is validated against the ensemble output from ExaEpi, an exascale agent-based model of a COVID-19 outbreak …

Attendance Matters: Incentive Programs And Chronic Absenteeism In Elementary Schools, Aubryn Street

Electronic Theses and Dissertations

Chronic absenteeism is a common challenge in elementary education. Schools often use attendance incentive programs, such as rewards or recognition, to encourage students to attend regularly. However, it is not always clear whether these programs actually improve attendance. This study examined whether attendance incentive programs are effective and how school staff view and use these programs.

This mixed-methods study used both school attendance data and interviews with school personnel. Attendance data from two school years showed that schools with incentive programs did not have lower absenteeism rates than schools without them. However, attendance improved overall from one year to the …

On The Algebraicity Of The Tic-Tac-Toe Matroid And Homogeneous Mixed Bowtie Systems, Benjamin R. Allen

Electronic Theses and Dissertations

This thesis is presented in two parts. First, we explore whether the class of algebraic matroids is closed under duality, a decades-old open question. We consider the Tic-Tac-Toe matroid as a potential candidate to answer the open question. The Tic-Tac-Toe matroid is known to satisfy many of the necessary conditions for a matroid to be algebraic and has a non-algebraic dual.  Second, we focus on decompositions of the complete mixed graph into mixed bowties. A complete mixed graph has between every pair of vertices an undirected edge and antiparallel arcs. A mixed bowtie is a graph consisting of two 3-cycles …

Malnutrition And Frailty Risk Among Community Dwelling Older Adults In Northeast Tennessee, Shreeyesha Pradhan

Electronic Theses and Dissertations

Frailty and malnutrition are prevalent conditions among community-dwelling older adults, affecting approximately 10% and 25% of this population, respectively. Despite overlapping symptoms such as functional decline, their relationship remains underexplored in community dwelling older adults. This cross-sectional feasibility study examined the association between frailty and nutritional status among 47 older adults in the East Tennessee Tri-Cities area using the Fried’s Frailty Phenotype (FFP) and the Mini Nutritional Assessment-Long Form (MNA-LF®). Results indicated 13% were pre-frail, 24% were frail, 21% were at risk for malnutrition, and 2% were malnourished. Regression analyses revealed that self-perceived nutritional status (37.6%), daily meal frequency (29.0%), …

Extreme Precipitation Events And Population Exposure: Site Recommendations For The Future Tennessee Mesonet, Victoria G. Redlund

Electronic Theses and Dissertations

This study examines frequency of and population exposure to extreme rainfall events in Tennessee to guide the placement of future mesonet weather stations. Using 1991-2021 daily nClimGrid precipitation records, extreme events were defined as events of rainfall ≥50 mm. These events were collated on an annual scale and normalized alongside square-root-scaled population densities derived from Landscan to develop extreme rainfall vulnerability maps. Results highlight where extreme rainfall is most frequent relative to population densities in each county. The findings were compared with models of mesonet suitability and feasibility to determine how meteorological needs correlate with siting needs such as land …

Ontogeny And The Effects Of Perinatal Stress In The First Immature Skeleton Of Teleoceras Aepysoma (Perissodactyla, Rhinocerotidae), Joe Gajewski

Electronic Theses and Dissertations

Recovery of an immature fossil rhinoceros (Teleoceras aepysoma) skeleton (ETMNH 32999) from the Gray Fossil Site in Tennessee offers the first insights into the ontogeny of the species. ETMNH 32999 is interpreted to be a subadult male in an age class equivalent to ~17-20% of potential lifespan. Comparative analyses support the hypothesis that subadults of related taxa are typically ~91% of average adult size in most dimensions. However, certain cranial dimensions are substantially lower than expected in ETMNH 32999, averaging only ~74% of the average conspecific adult. Such departure from typical growth rates is suggested to be attributable …

Utilizing Physics Informed Neural Networks For Disrupted Signal Dynamics, Nicholas J. Joyner

Electronic Theses and Dissertations

Physics-informed neural networks (PINNs) have been used in many applications including engineering and physical sciences. PINNs allow the incorporation of a priori understanding of a process’ structure into the modeling. We attempt to leverage the PINN structure toward the evaluation of disruptions to classical dynamical models by combining elements of ordinary differential equations into our loss function with sigmoidal gating to balance the penalties for deviations from the data with those for structural deviations. This enables the identification of the signal structure and the limits of disruption influence. As a use case, we consider stock value from 2019-2021, which expresses …

Machine-Learning Landslide Susceptibility And Runout Modeling In The Nolichucky River Gorge After Hurricane Helene, Grace Braver

Electronic Theses and Dissertations

Extreme rainfall from Hurricane Helene (September 2024) triggered widespread landslides across the southern Appalachian region, highlighting the need for rapid landslide susceptibility assessments that capture both landslide initiation and downstream runout. Traditional susceptibility models often focus solely on initiation zones, limiting their ability to identify which slopes will generate destructive landslides or where material will travel. This study addresses that gap by (1) integrating Geographic Information System (GIS)-based machine learning susceptibility modeling using ArcGIS Pro: Maximum Entropy (MaxEnt) and Random Forest-Based and Boosted Classification and Regression (FBBC) and (2) the U.S. Geological Survey (USGS) Grfin (Growth, Flow, and Inundation) runout …

Undergraduate Design Spine For Biological Systems Engineering And Agricultural Engineering, David Mabie, Derek M. Heeren, Deepak R. Keshwani, Heidi A. Diefes-Dux, Nicole M. Iverson, Rachel Padrnos, Greg Bashford, Taryn King, Jenna Hefley, Curtis L. Tomasevicz

Department of Agricultural and Biological Systems Engineering: Presentations and White Papers

Engineering education is undergoing a shift toward preparing graduates with demonstrated capabilities that integrate technical knowledge, durable skills, and the ability to adapt in a rapidly evolving professional landscape. This paper describes a comprehensive redesign of the undergraduate curriculum in Biological Systems Engineering (BSEN) and Agricultural Engineering (AGEN) at the University of Nebraska–Lincoln. The redesign is grounded in a “Design Spine” framework, which distributes and scaffolds design experiences across all four years of the program to support progressive development of problem solving, systems thinking, communication, and professional skills. The curriculum is organized around clearly defined capabilities and threads that connect …

Uncertainty, Information, And Major Choice: Evidence From Chinese Gaokao, Sikun Dou

Dissertations and Theses Collection (Open Access)

An unresolved background risk makes people more averse to other, independent  risks—most of all when a high-stakes, irreversible choice must be made under that risk. College major choice is such a setting. In China, students are admitted directly into a major they cannot easily change, and in the early 2000s they had to commit before learning their exam scores, bearing a field’s academic risk on top of an unresolved admission risk. Because STEM fields carry more academic risk and women are on average more risk-averse, this burden falls hardest on women’s entry into STEM. Exploiting a reform that moved application …

Extremum Seeking Compensation And Quantification Of Position Sensor Offset Error In Speed-Controlled Permanent Magnet Synchronous Motors, Tessa Biondo

Masters Theses

Position sensor offset errors present a persistent challenge in speed-controlled permanent magnet synchronous motor drives operating under field-oriented control. Even small, constant offsets in the measured rotor position can reduce torque effectiveness, requiring increased current and voltage demand to maintain the commanded speed and resulting in degraded speed regulation performance across a range of operating conditions. These effects are particularly problematic in speed-controlled systems, where speed loop dynamics cause increased electrical effort and limit overall performance. Many existing detection and compensation approaches are either dependent on the system model, require offline calibration, or are primarily designed for torque-controlled operation. This …

Transient Mitigation In Dual Active Bridge Converter Using An Auxiliary Converter With High-Frequency Selective Control For Load Step-Down Condition, Sachith Dilshan Wijesooriya

Masters Theses

Dual Active Bridge (DAB) converters are widely utilized in applications such as electric vehicles, renewable energy systems, and solid-state transformers due to their high efficiency, galvanic isolation, and bidirectional power transfer capability. However, during rapid load transitions, DAB converters frequently exhibit significant output voltage overshoot and prolonged settling times, which increase device stress and adversely affect system reliability. This thesis proposes an auxiliary-circuit-based transient mitigation method to address these limitations. The auxiliary circuit, implemented as a bidirectional Buck–Boost stage, operates in Boost mode during load step-down events to absorb excess energy and suppress the resulting voltage overshoot. The design of …

Increasing Accuracy Of Mapping Local Climatic Zones Using Building Height And Spectral Unmixing, Ian Douglas Stauffer

Masters Theses

Local climatic zone (LCZ) classifications are traditionally done using reflectance, population data, and often climatic data. The goal of this research is to utilize Google’s new “Open Buildings Temporal v1” building data set as well as “spectral unmixing”. With the objective of testing, assessing, and implementing this data set into the workflow of LCZ mapping. After testing the quality of the data against a validated LiDAR data set from the same year as a given “Open Buildings Temporal v1” band, I implemented it into the Random Forest machine learning process. Secondly, I justified the use of spectral unmixing as a …

Darjeeling 1967, Bibhav Basnet '26

A Midwestern Review: A Magazine of the Arts and Issues at DePauw University

Bibhav Basnet is a senior from Nepal and is majoring in Mathematics. He regrets this decision greatly and is skeptical if he will ever graduate from college. He is a member of DePauw's Ethics Bowl team, and of Delta Upsilon fraternity.

Quantifying Discard Mortality Of Undersized And Ovigerous Crabs In The Gulf Of Mexico Blue Crab Fishery, Micayla Cochran

Master's Theses

Blue crabs support a valuable commercial fishery in the Gulf of Mexico. Most states require the release of undersized and ovigerous blue crabs, yet mortality of these discarded crabs is an understudied component of total mortality. The first objective of this project was to quantify discard mortality of non-target crabs using bycatch surveys across the Lake Pontchartrain–Mississippi Sound coastal system. Ovigerous crabs were most common at high salinities and temperatures, whereas undersized crab presence was inversely correlated with soak time, temperature, and the number of crabs per trap, and also varied among geographic locations. A reflex action mortality prediction assessment …

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 …

Modeling The Effects Of Low-Pressure Atmospheric Fronts On Sediment Transport Through Mississippi Sound Barrier Island Inlets, Nicholas J. Gagliano

Master's Theses

Coastal sediment dynamics in the Mississippi Sound are strongly influenced by tropical cyclones and the more frequent passage of low-pressure atmospheric fronts. While hurricanes are well recognized for reshaping barrier islands and altering sediment budgets, the cumulative role of recurrent fronts remains poorly quantified. This thesis investigates the impacts of six low-pressure atmospheric fronts (2015–2017) on sediment flux through six barrier island inlets in the Mississippi Sound.

A high-resolution application of the Regional Ocean Modeling System with the Community Sediment Transport Modeling System was developed to simulate tidal circulation, wind-driven currents, and sediment dynamics. Waves were excluded from the simulations. …

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 …

The Impact Of Place-Based Education Professional Development On Faculty Identity And Perceptions Of Nature-Culture Dichotomies, Reyt Middleton

Master's Theses

This qualitative study analyzes how implementing place-based education (PBE) in undergraduate coursework shapes faculty identity narratives and nature–culture positionalities across conceptual lenses of past, present, and future. Three faculty members at a regional Mississippi university engaged in a PBE professional development program; narratively driven pre- and post-implementation interviews were given to participants, then examined via thematic analysis. Framed primarily through lenses of constructivism, with support from critical pedagogy of place, relational and ecological epistemologies, and scholarship on faculty identity, this study posits two research questions—1: How does teaching PBE influence faculty identity narratives across past, present, and future temporalities? 2: …

Assessment Of Mississippi Landfill Capacity In Relation To Waste Generation And Land-Use Constraints, Jason C. Anderson

Master's Theses

Municipal solid waste (MSW) management presents a growing challenge in Mississippi as population trends, socioeconomic change and regional development continue to place pressure on existing landfill capacity. This thesis examines waste generation and disposal patterns from 2000 through 2022 across Mississippi counties, with projections extending to 2050. Historical landfill tonnage data was gathered and compiled from the Mississippi Department of Environmental Quality (MDEQ) and analyzed using regression models in Excel and RStudio, with forecasts generated for both in-state and out-of-state waste flow. Results highlight significant variations among landfills, including differing closure timelines, changing county service areas and notable shifts in …

The Efficacy Of Ethical Data: An Analytical Study By, Lamar Gebara

Theses

As artificial intelligence and machine learning models become increasingly embedded in decision-making systems across industries, questions about the ethical sourcing of data have grown more pressing; model performance relies heavily on vast, diverse datasets, many of which are harvested without consent, transparency, or equitable representation. This study aims to compare analytics outcomes (accuracy, bias, fairness, and explainability) between ethically sourced and unethically sourced datasets. Using CRISP-DM methodology, the study will develop matched classification models on both dataset types, evaluate their performance and fairness using open-source tools such as Fairlearn and AIF360, and assess broader implications for trust, accountability, and regulatory …

Weaving Ideology: Textiles In Florentine And Venetian Painting Of The Cinquecento, Ruben Verità

Art and Art History Honors Projects

Renaissance art historical scholarship has largely ignored the political and cultural significance woven into the representation of textiles, as well as their communicative potential in paintings. In this study, I examine how textiles in their various forms carry the potential to go beyond their normative categorization as decoration. Through a comparative analysis of the paintings produced in two politically distinct polities—Florence and Venice—during the sixteenth century, I integrate Louis Althusser’s theory of ideology and Michael Baxandall’s period eye to elucidate how painted fabric was not the representation of a passive decorative ornament. Rather, it was an active and legible proxy …

Discipling Students On Non-Adventist College And University Campuses, Ronald R. Pickell

Journal of Adventist Youth and Young Adult Ministries

Social science has long demonstrated the importance of faith development in the period of college life. An Adventist faith development process is needed for the spiritual life and faith development of students who attend non-Adventist universities. This paper expands on my previous research on this topic and features the Journey—a series of student Bible study small group experiences. Journey introduces students to the mission and message of Jesus, inviting them to believe in Jesus and follow Him in lifelong discipleship. This small group Bible study series contributes to the discipleship process for students in the unique setting of today’s university …

Draft Final 2024 Reclamation Improvement Sampling: Bres No. 78 – Original Mine Yard Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Sevoauth: Secure Voiceprint Authentication With Hash-Based Feature Transformation, Rui Zhang, Zheng Yan, Robert H. Deng

Research Collection School Of Computing and Information Systems

While voiceprint authentication offers convenient user authentication and access control through voice feature recognition, a critical research gap remains: existing voiceprint authentication systems fail to simultaneously achieve sound security against replay, spoofing, and adversarial attacks, preserve voice privacy leakage, and satisfy usability demand. Previous efforts have struggled to balance these issues comprehensively. To bridge this gap, we present SeVoAuth, a cloud-based Voiceprint Authentication as a Service (VAaaS) system designed to provide privacy preservation, robust security, and enhanced usability. SeVoAuth stores a synthesized voiceprint of a user in the cloud during user registration, thereby safeguarding the privacy of the real voiceprint …

Synthesis And Evaluation Of Long-Term History-Aware Medical Dialogue, Hebin Hu, Renke Dai, Ah-Hwee Tan, Yilin Kang

Research Collection School Of Computing and Information Systems

An effective healthcare agent must be able to recall and reason over a patient’s longitudinal medical history. However, the absence of datasets with realistic long-term dialogue timelines limits systematic evaluation. Real clinical text is constrained by privacy and ethics, while existing benchmarks focus on isolated interactions, failing to capture cross-session reasoning. We introduce a framework for synthesizing high-quality, long-term medical dialogues with LLMs. Our approach entails a knowledge-guided decomposition into three stages: constructing synthetic patient profiles with diverse disease and complication trajectories, generating multiturn dialogues per encounter, and integrating them into a coherent longitudinal history dataset, MediLongChat. We establish three …

Open Source Software Development Tool Installation: Challenges And Strategies For Novice Developers, Larissa Salerno, Christoph Treude, Patanamon Thongtanunam

Research Collection School Of Computing and Information Systems

As the world of technology advances, so do the tools that software developers use to create new programs. In recent years, software development tools have become more popular, allowing developers to work more efficiently and produce higher-quality software. Still, installing such tools can be challenging for novice developers at the early stage of their careers, as they may face issues such as compatibility problems (e.g., with operating systems) and unclear instructions. Therefore, this work aims to investigate the challenges novice developers face when installing software development tools and the strategies they employ to overcome them. To investigate these, we conducted …

Generation Of Elaborated, Targeted And Effective Feedback For Novice Programmers Using Llm, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

Programming errors and misconceptions are pervasive in novice programmers which causes difficulty in the learning of computer programming. Large Language Models (LLMs), with their ability to comprehend and generate programming codes have shown promising results in the automatic identification of errors. This can potentially benefit student programmers by providing them with timely formative feedback at efficiencies and scale that were not attainable previously. In this study, we leveraged an LLM - OpenAI o4-mini for the generation of elaborated, targeted feedback for novice programmers across PHP and JavaScript exercises. We contend that the feedback needs to be effective and targeted other …