Digital Commons Network^™

Machine Learning For Elderly Behavior And Risk Incident Modeling, Muhammad Tanveer Jan

Electronic Theses and Dissertations

The rapid expansion of the aging population presents critical challenges to healthcare systems, particularly in maintaining independent living, ensuring mobility safety, and optimizing emergency interventions. Traditional monitoring solutions are often fragmented, reactive, and hindered by the scarcity of data regarding rare high-risk events. This dissertation proposes a comprehensive, multi-modal machine learning framework designed to model elderly behavior and predict risk incidents across three critical environments: the home, the vehicle, and the clinical setting.

To address the fundamental challenge of class imbalance in medical and behavioral datasets—where risk events are statistically rare—this research first introduces a dual-phase data augmentation strategy. By …

Advances In Real-Time American Sign Language Recognition System Using Deep Learning Techniques For Enhanced Accessibility, Bader Alsharif

Electronic Theses and Dissertations

Advancements in technology have significantly contributed to the development of innovative tools aimed at improving communication and accessibility for individuals with hearing impairments. This dissertation explores various machine learning and deep learning techniques for recognizing American Sign Language (ASL) gestures, focusing on enhancing accessibility and bridging the communication gap between hearing-impaired and hearing individuals. Traditional machine learning models, such as Random Forest, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN), alongside deep learning architectures like AlexNet, ResNet-50, EfficientNet, ConvNeXt, and VisionTransformer, were investigated for their effectiveness. Experiments conducted on an extensive dataset of 87,000 ASL gesture images revealed exceptional recognition …

Uas Path Planning With Dynamic Rerouting Using A Space-Time Graph, Kimoy Williams

Electronic Theses and Dissertations

UAS systems have emerged as multifaceted technologies with applications across a wide range of sectors. Their ability to access areas that are difficult or unsafe for manned systems has made them invaluable tools in various domains. As a result, UAS have transformed numerous industries, including infrastructure inspection, delivery and logistics, military and defense, as well as precision agriculture and environmental monitoring.

The advancement in UAS technology is fundamentally reliant upon ongoing research efforts in the specialized area of UAS path planning. Optimal flight planning is essential for a UAV to effectively execute its mission’s task safely, effectively, and in congruence …

Impact Of The Lace Index Scoring Tool On Sepsis Readmissions, Tabitha M. Keaty Sheppard

Electronic Theses and Dissertations

Sepsis is a life-threatening medical emergency that negatively affects patients and healthcare organizations worldwide. Consequently, sepsis survivors are presented with even greater health risks following acute hospitalizations, and the financial implications on healthcare organizations increase with each patient readmission. This quality improvement project studied the impact of the LACE Index Scoring Tool on sepsis readmissions within a single healthcare organization in the southern region of the United States. Per quality metric data, sepsis readmissions have remained a prevalent issue at the project site. The purpose of this doctoral project was to reduce 30-day sepsis readmissions following the implementation of the …

Longevity, Resilience, And Thriving Of Women In Ministry: A Case Study Of Women In Ministry From A United Pentecostal Holiness Church, Eunice Cheryl Feltus Little

Electronic Theses and Dissertations

Abstract

The problem of ministry attrition caused by burnout is well documented. Research attributes the impact of burnout on the resilience, longevity, and thriving of ministry workers to role-related stress and adversity. High attrition rates throughout religious organizations and a lag in longevity and resilience contribute to a shortage of ministry workers. Some ministry workers leave the vocation because of stress and burnout, yet others persevere. Despite the possible adverse effects, many men and women find a sense of well-being and joy in ministry work. This qualitative distributive case study focused on those who stayed in ministry and the strategies …

Leader Rounding For Outcomes To Improve Employee Retention, Laura R. Escobar

Electronic Theses and Dissertations

Intention to leave a nursing staff position, if not addressed, may lead to an increased rate of nursing turnover. High turnover rates can negatively affect staffing patterns, increase organizational costs, and disrupt the continuity of patient care. A quantitative quasi-experimental pre-/posttest design was used to evaluate the impact of the High Reliability Organization Leader Rounding for Outcomes tool to reduce the intent-to-leave scores, as measured by the Turnover Intention Scale (TIS-6), compared to current practice over 12 weeks. Implementation of the tool provided a structured leader rounding process designed to strengthen communication, recognize staff contributions, and proactively identify workplace concerns. …

Patient Wait Time And Throughput Interventions In The Cardiology Outpatient Setting, Chioma Ohiri Tawose

Electronic Theses and Dissertations

Healthcare collaboration and patient care require effective communication. Poor communication impacts wait time. Inadequate communication in the outpatient cardiology clinic can lead to disruptive patient throughput, or workflow, and extend patient length of visit. The purpose of this project was to implement a means of communication for clinicians and healthcare assistants to improve patient flow and cut down idleness, ultimately reducing patient wait time. The project established the incorporation of a built-in electronic health record communication notification system, the Event Button, for asynchronous communication between staff. A quantitative quality improvement design was used to conduct this project. Inferential and descriptive …

The Built Environment And Its Effects On Health Outcomes In Metropolitan Miami, Jared Sanchez Hoehing

Electronic Theses and Dissertations

Obesity, depression and social isolation rates are an increasing worry in the United States. As planners, we help shape the built environment, which can influence a person’s health outcomes. To assess the effects the built environment has on health outcomes, this paper looks at the percentage of park space, the population density and the national walk index score, combined with several demographic and socioeconomic variables in the Metropolitan Miami region. The study uses the spatial autoregression results of the variables on each health measurement to determine the connection with each health outcome. Despite initial hypotheses that the built environment leads …

Personalized 3d-Printed Tablets For Diabetes And Related Complications: Design, Optimization, And Evaluation, Thirupathi Reddy Anekalla

Electronic Theses and Dissertations

This study aimed to explore potential use of pneumatic-based thermoplastic 3D bioprinter to create personalized tablets in a single-step process. In investigates the development of a single pill containing two model drugs: Metformin HCl (a highly soluble drug) for extended-release and Atorvastatin Calcium Trihydrate (a low-solubility drug) for immediate release with enhanced solubility. To achieve this, Eudragit RSPO as extended-release polymer and Polyethylene Oxide (PEO N10) as immediate release polymer was used, and the tablets were fabricated using Direct Powder Extrusion (DPE) Technology with pneumatic-based thermoplastic print heads. Key processing parameters, such as nozzle printing speed, infill density, printhead temperature, …

Defending Darnassus: Self-Disclosure Between Characters In World Of Warcraft, Molly Peterson

Electronic Theses and Dissertations

This study examined why players substitute physical contact with people for virtual contact with people, why players engage in self-disclosure, and how they interact with other players. A content analysis analyzed data collected from an online questionnaire. Using data from 125 questionnaires, the research gathered information on why players self-disclose within the game World of Warcraft and if they have experienced any advantages or disadvantages from those interactions.

A Systematic Review: Comparative Analysis Of Healthcare Waste Management Practices In Kenya And In The United States, Esther Nyokabi Gathungu

Electronic Theses and Dissertations

This comparative study used a systematic literature review to explore waste management practices in Kenya and the USA, examining predefined concepts to identify new patterns relevant to sustainable healthcare waste management (HCWM) practices. The study aimed to understand sustainable practices in healthcare waste management and how developing nations such as Kenya can benchmark from practices in developed nations such as the USA. While the study identified challenges in waste management across Kenya and the USA, it also identified sustainable practices that could be adopted across contexts. The study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines …

Butting Heads With Respiratory Disease: Post-Epizootic Demography And Movement-Driven Spillover Risk In A Badland’S Bighorn Sheep (Ovis Canadensis) Meta-Population, Sean P. Ryder

Electronic Theses and Dissertations

Respiratory disease caused by Mycoplasma ovipneumoniae is among the most significant threats to bighorn sheep (Ovis canadensis) conservation in North America. In July 2021, contact between bighorn sheep rams and domestic sheep north of Badlands National Park (BADL), South Dakota, USA introduced M. ovipneumoniae into the Badlands bighorn sheep meta-population, triggering an epizootic that reduced the population by approximately 80%. I evaluated the post-outbreak status of this population through two complementary studies conducted from 2023 to 2025. In Chapter 1, I quantified disease prevalence, adult survival, lamb recruitment, and population growth rate (λ) using serial quantitative polymerase chain reaction (qPCR) …

Feasibility Study For Lithium Mining In South Dakota, Neha Karna

Electronic Theses and Dissertations

The increasing demand for lithium in the battery manufacturing industry, boosted by the growth of electric vehicles and smartphones, has led to concern over its sustainable supply chain in the United States. Historically, South Dakota has played a significant role in U.S. lithium production. The recent surge of interest in lithium exploration in South Dakota, specifically Black Hills, underscores the importance of evaluating the feasibility of lithium mining in Black Hills. This research aims to study the economic feasibility of a lithium mining operation in Black Hills, South Dakota. Our specific objective is to estimate cut-off grade using Lane’s model …

Chemical Load: An Unseen Herbicide Filter In Restored Prairies?, Rylie Franklin

Electronic Theses and Dissertations

Community Assembly Theory is a framework used to describe the process by which species from a regional species pool disperse and encounter various abiotic and biotic conditions that act as filters, limiting which species will populate a specific local community. Prairie restoration success can be improved by understanding abiotic and biotic filters. As agricultural practices have adopted integrated weed management plans, that include the use of both chemical and non-chemical techniques, another filter needs to be considered during restoration: the chemical load of soils, i.e., herbicide residue from recent on-site applications and herbicide drift from adjacent areas. To examine the …

Towards Energy Access For All: Developing The Lived Energy Experience Index (Leei), Kentina Annie Ishimwe

Electronic Theses and Dissertations

Energy is the fuel that powers the engine of civilization. Energy access metrics ensure that nations continuously work towards providing access for all. However, the prevalent binary indicator fails to consider that energy needs to be usable, accessible, affordable, and reliable. As a result, numerous tiered and multidimensional metrics, such as the Multi-Tier Framework, came about to bridge the gap but proved to be complex and complicated to implement. This study presents the existing literature review, assesses the limitations of current energy access measurement frameworks, and compares household energy needs with reported access statistics. Based on the findings, the Lived …

Evaluating Supplementation Strategies Using Precision Livestock Technologies And Energy Based Models In Developing Beef Heifers Grazing Dormant Rangeland, Kali-Jo Bentz

Electronic Theses and Dissertations

Replacement beef heifer development in extensive grazing systems is challenged by variation in forage quality, supplement intake, and animal behavior, all of which influence the ability to achieve targeted growth prior to breeding. Precision livestock technologies (PLT) enable continuous monitoring of individual animal performance, while energy-based nutritional models support individualized supplementation. However, their application under extensive grazing conditions remains poorly understood. Therefore, the objectives of this thesis were to (1) evaluate heifer utilization of multiple precision livestock technologies and their relationship with animal performance and (2) evaluate the accuracy of an individualized energy-based supplementation model by comparing predicted supplement allotments …

New Era Of Academic Advising: Integration Of Artificial Intelligence Within Academic Advising By, Rachel Elaine Schmitz

Electronic Theses and Dissertations

Academic advising is a critical component of student success, directly impacting institutional retention, GPA, and student autonomy. This thesis explores the transition of this profession into my proposed fifth era characterized by the integration of Artificial Intelligence (AI) as a supportive tool, rather than a replacement, for human connection. Grounded in Peplau’s Interpersonal Relations Theory (IRT), this study examines advisors’ perception of how advanced technology can impact the interpersonal process between students and advisors. A qualitative methodology was used, consisting of seven (N = 7) semi-structured interviews with professional advisors at South Dakota State University. Thematic analysis revealed that AI …

Production Of Fungal Biomass And Crude Chitin From Cheese Whey: Effects Of Whey Type And Lactose Hydrolysis On Aspergillus Niger And Trichoderma Reesei, Anye Catharine Nora Drum

Electronic Theses and Dissertations

Chitin is a biodegradable and biocompatible biopolymer with broad applications in the food, biomedical, pharmaceutical, and packaging industries. Conventional chitin production from crustacean shells is associated with seasonal availability, intensive chemical processing, and environmental concerns, creating interest in more sustainable alternatives. Filamentous fungi represent a promising source of chitin because of their rapid growth and ability to utilize low cost agro-industrial residues. This study evaluated the feasibility of producing fungal biomass and crude chitin from cheese whey through submerged fermentation while investigating the effects of whey type and enzymatic lactose hydrolysis on fungal growth, substrate utilization, and wastewater remediation. Aspergillus …

Page Evidence Promotion For Open-Domain Multimodal Document Question Answering, Abdolhossein Erfanshekooh

Electronic Theses and Dissertations

Open-domain multimodal document question answering requires retrieving a small set of answer-bearing pages from a large document collection before a vision-language model can generate an answer. Although modern retrieval systems may return hundreds or thousands of candidate pages, the answer model typically receives only the highest-ranked few. Consequently, relevant evidence may already be present in the candidate pool yet remain unavailable to the answer model because it is ranked below the reader cutoff. This thesis identifies this retrieval-to-reader gap as a page evidence promotion problem and proposes a framework for diagnosing and addressing it. First, page-level pseudo-supervision is derived from …

Semantic Discovery Of Genomic Datasets With Ai, Lawrence Allibah

Electronic Theses and Dissertations

Traditional keyword-based search in genomic databases often fails to capture the latent semantic context of biological studies, leading to a ``Lexical Gap" in research discovery. This thesis presents a high-performance dual-engine discovery system built upon 10,000 studies. By utilizing 1,536-dimensional vector embeddings, with large language models (LLMs) we implement a search engine coupled with a novel Hybrid Boosting layer that integrates semantic intent with factual metadata. Furthermore, we apply a high-dimensional K-Means clustering algorithm for unsupervised topic discovery. Empirical benchmarking demonstrates that the Hybrid Boosting engine achieves a 38.1% gain in precision and a 41.2% increase in Mean Reciprocal Rank …

Detecting And Characterizing Latent Subpopulations Of Classes Via Mixture Models, Andrew Simpson

Electronic Theses and Dissertations

A class of problems in statistical pattern recognition exists in which there is high-dimensional data with few realizations per class, commonly referred to as few-shot learning. Data that arises in forensic source identification, which deals with providing a probabilistic value of evidence with regard to the source of some object, falls into this class of problems. Namely, the data is sampled from a hierarchical sampling process, lives in a high-dimensional space, the number of sources (or classes) tends towards infinity, and there are few observations per source. This can be thought of as a few-shot learning problem. Because of these …

Spatio-Temporal Demand Forecasting For Optimizing Electric Vehicle Charging Network Operations, Subhamyu Mani Nepal

Electronic Theses and Dissertations

The primary objective of this thesis is to create a framework for modeling, forecasting Electric Vehicle load demand and optimizing the EV charging network operation for Charging network operators. As EV’s popularity grows accurate forecasting of EV charging demand and its effect on the distribution network is critical for the efficient planning and operation of charging infrastructure, as well as for enabling Charging Network Operators to participate effectively in wholesale electricity markets. The first part of the work develops Mt /M/1 & Mt /M/c queuing models calibrated using real-world EV charging data to characterize station-level operations under time-varying arrival rates. …

Effect Of Increasing Potency Of Steroidal Implants In Beef Steers At Weaning From Dry-Lot To Finish, Weston Joseph Peschel

Electronic Theses and Dissertations

The receiving phase is a stressful transition period in beef production. Newly weaned cattle are offered low-energy, high-forage diets promoting lean tissue and bone development prior to the finishing phase. Steroidal implants containing trenbolone acetate (TBA) and estradiol benzoate (EB) enhance lean gain. Aggressive early implant exposure has been shown to negatively impact intramuscular fat deposition. This two-part study evaluated the initial and carryover effects of increasing doses of combined TBA and EB weaning implants on growth performance, serum metabolites, and carcass traits. In Exp. 1, newly weaned Charolais × Red Angus crossbred beef steers [n = 240 initially; body …

A Framework For Reliable Domain Ai: Knowledge-Grounded Data And Logic-Graph Reasoning, Yangxiao Bai

Electronic Theses and Dissertations

Large language models (LLMs) perform well on general tasks, yet their deployment in specialized, high-stakes domains such as public health remains unreliable. Models hallucinate facts, combine multi-step evidence incorrectly, and retrieve context that corrupts downstream reasoning. Three root causes underlie these failures: training data that underrepresents rare but critical domain themes, reasoning that is opaque and unverifiable, and evidence use that cannot be re-checked when the evidence changes. This dissertation addresses all three. First, we introduce HDBSCAN_SSA, a coarse-to-fine topic-modeling pipeline that couples density-based clustering with a novel Semantic Seed Aggregation algorithm. Using samples drawn from a larger corpus of …

Task-Aligned Knowledge Transfer For Vision-Language Models Across Diverse Visual Challenges, Dongyoun Kim

Electronic Theses and Dissertations

Pretrained vision–language models (VLMs) encode broad visual and semantic knowledge, but this knowledge does not always translate into reliable performance on specialized visual tasks. Multi-object region understanding requires fine-grained relational alignment, scientific document question answering requires structured reasoning over tables and charts, and robotic manipulation requires task-relevant perception to influence action generation. This dissertation studies these gaps as a problem of knowledge utilization: helping a pretrained model use available knowledge in a form aligned with the target task. Its central claim is that effective adaptation depends not only on model scale, data volume, or full-backbone fine-tuning, but also on three …

Demographic Impact And Diagnostic Evaluation Of Mycoplasma Ovipneumoniae In Bighorn Sheep Of The Pine Ridge Badlands, Jeffrey Tillery

Electronic Theses and Dissertations

Mycoplasma ovipneumoniae (M. ovi) decimates bighorn sheep (Ovis canadensis) populations through acute die-offs followed by years or decades of failed lamb recruitment. Test-and-remove management has emerged as the primary intervention to restore population growth, and this thesis quantifies the demographic costs of endemic M. ovi infection and evaluates the diagnostic tools upon which this strategy depends. I quantified vital rates across five bighorn sheep subherds (four infected, one uninfected) on the Pine Ridge Reservation (2023–2025), supplemented by pre-outbreak data (2017–2018) from the North Unit of Badlands National Park. Infected subherds declined (λ = 0.965, 95% CrI: 0.813–1.039) while the uninfected …

The Price Of Alfalfa: Estimating The Cost To Desalinate Irrigation Water In Arizona, Clifford Hall Iv

Electronic Theses and Dissertations

No abstract provided.

Effect Of Corn Processing Methods On Growth Performance, Carcass Characteristics, And Gastrointestinal Health In Ruminants Fed Finishing Diets, Reanna Rae Byrnes-Schoen

Electronic Theses and Dissertations

The objective of this work was to evaluate different feed processing techniques and their impacts on growth performance, carcass traits, and gastrointestinal health in ruminant animals fed in confinement during the finishing phase. Two studies were conducted. The first study evaluated the effect of kernel processing high moisture ear corn (HMEC) on growth performance and carcass characteristics of finishing beef steers. The second study used feeder lambs to evaluate the effect of steam-flaking corn in a finishing diet on growth performance, carcass characteristics, and gastrointestinal tract (GIT) health. The results from the first study using steers demonstrated that feeding kernel …

Plant-Insect Interactions In Great Plains Restoration And Invasion Ecology, Joseph H. Cammarano

Electronic Theses and Dissertations

Prairie ecosystem loss and invasive plant species are major ecological problems in the Great Plains. Plant-insect interactions have important consequences for both the restoration of prairie ecosystems and management of invasive plant species. Pollinating insects are vital to the sustainability of prairie ecosystems, and herbivorous insects can provide biological control of invasive plant species. Understanding how restoration strategies may influence potential pollinator communities can have important consequences for restoration sustainability and success and understanding how biological control strategies may help manage invasive plant populations can also help land managers reach restoration and conservation goals. In Ch. 2, I sought to …

Data-Driven Decision-Making Frameworks For Energy Procurement And Dynamic Pricing In Electric Vehicle Charging Networks, Pallavi Khanal

Electronic Theses and Dissertations

The continued growth of electric vehicles (EVs) is increasing the demand for charging infrastructure and creating new operational challenges for charging network operators (CNOs). Uncertainty in charging demand, electricity market prices, and user charging behavior can significantly impact both the economic performance and reliability of charging network operations. To address these challenges, this thesis develops an integrated data-driven framework that combines charging demand modeling, risk-aware energy procurement, machine learning, and reinforcement learning for intelligent EV charging network operation. The research begins by developing queueing-based models to characterize EV charging demand under time-varying and stochastic arrival conditions. Time-varying Mt/M/1 and Mt/M/c …