Digital Commons Network^™

A Unified Framework For Embedding-Based Synthetic Data Generation With High Cardinality Categorical Features, Cesar Iram Vazquez

Open Access Theses & Dissertations

High-cardinality categorical variables remain difficult to model in tabular data, where classical encoders encounter sparsity, susceptibility to leakage, and the loss of meaningful relational structure. This dissertation develops a unified framework for learning, evaluating, and synthesizing representations of such variables using both traditional encoders and modern embedding methods, including Word2Vec, FastText, Node2Vec, TF–IDF/SVD, and supervised entity embeddings. The framework is applied across three benchmark datasets (Adult, PetFinder, Breast Cancer) and a hierarchical educational case study (IPEDS/CIP). Embedding quality is examined through both downstream predictive performance and structure-focused diagnostics that quantify neighborhood behavior and geometric coherence. To assess whether synthetic data …

The Impact Of Transmission Thresholds Across Multiple Scales On The Spread Of Chronic Wasting Disease In Wisconsin, Jen Mcclure

All Graduate Theses and Dissertations, Fall 2023 to Present

Wildlife diseases can be difficult to control once they are established. This is especially true when they spread through contact with infectious material left in the environment. One such disease is chronic wasting disease (CWD), a fatal illness affecting deer and related species in North America and other regions. CWD is caused by prions, misfolded proteins that can remain infectious for years after shedding by infected hosts.

Recent research shows that CWD infection does not always follow from the gradual accumulation of prions through small contact events. Rather, an individual may need to encounter a certain prion dose all at …

Machine Learning Applications: Cell Tracking And Nonparametric Estimation Of Non-Smooth Divergences, Mina Mahbub Hossain

All Graduate Theses and Dissertations, Fall 2023 to Present

This thesis brings together two important research directions: how to compare different sets of data more accurately, and how to better understand how brain cancer cells move and change shape.

In the first part, we look at a problem in statistics: measuring how different two data sources are from each other. Traditional methods often make strong assumptions, which may not always hold in real situations. Our approach avoids those assumptions by using an ensemble method, a way of combining many weak estimators into one stronger result. This makes the method more flexible and reliable, especially when dealing with complex or …

Two Topics In Survival Analysis: Restricted Distance Covariance Test For Non-Proportional Hazard And A New Estimation For Dropout Rate, Ruizhe Yin

Graduate Theses and Dissertations

When treatment effects change over time, standard statistical methods, such as the log-rank test and the Cox proportional hazards model, may give misleading results. This dissertation presents the restricted distance covariance (rdcov) test, a nonparametric method that compares survival curves between groups within a chosen study period [0, τ] using right censored data. The statistic measures the dependence between pre-specified group labels and survival times using pairwise distances from Kaplan-Meier estimates. Our method does not rely on the proportional hazards assumption, and it equals zero only when survival functions are identical across groups. Thus, this test can be applied to …

Instance-Adaptive Gated Fusion Of Multi-Transform Image Representations, Prince Appiah

Open Access Theses & Dissertations

This dissertation proposes the Instance-Adaptive Gated Fusion (IAGF) framework, a novel deep learning architecture for adaptive and interpretable fusion of multiple time–series image transformations. While existing methods rely on static concatenation or dataset-level optimization, IAGF introduces a learnable gating mechanism that dynamically assigns per-instance weights to Recurrence Plots (RP), Gramian Angular Summation Fields (GASF), and Gramian Angular Difference Fields (GADF). The gating layer performs a convex fusion of transformation-specific embeddings under a softmax constraint, ensuring mathematical stability and interpretability. An entropy-regularized objective prevents dominance collapse and promotes balanced exploration of transformations during training. Comprehensive experiments across eighteen benchmark datasets, spanning …

Multi-Hop Hybrid Graph Neural Network, James Arthur

Open Access Theses & Dissertations

Graph-structured data appear across diverse domains, such as social networks, citation graphs, biological systems, and knowledge bases. Graph Neural Networks (GNNs) have emerged as a powerful framework for learning on such data, yet existing architectures face significant challenges. Graph Convolutional Networks (GCNs) suffer from over-smoothing as depth increases, Graph Attention Networks (GATs) introduce computational and statistical instabilities, and naïve multi-hop propagation inflates memory and computation while failing to adapt to topology. These limitations motivate the development of a new framework that is both expressive and scalable. This dissertation proposes the Multi-Hop Hybrid Graph Neural Network (MHHGNN), a novel architecture that …

Advancing Effective Connectivity Analysis: Robust And Sparse Group Dynamic Causal Modeling Via Extended Parametric Empirical Bayes, Godfred Arhin

Open Access Theses & Dissertations

Dynamic Causal Modeling (DCM) provides a principled framework for estimating effective connectivity in neuroimaging data, with Parametric Empirical Bayes (PEB) enabling hierarchical inference across sessions and subjects. However, standard PEB assumes Gaussian distributions at all hierarchical levels and employs conventional shrinkage priors that do not enforce true sparsity, limiting robustness to outlying subjects and reducing sensitivity to parsimonious connectivity structures. This thesis introduces a robust, sparsity-inducing hierarchical extension to DCM-PEB that addresses these limitations through two key innovations. First, a Student-t group-level likelihood replaces the conventional Gaussian likelihood, automatically downweighting outlying subject-level parameters using adaptive precision weights while retaining computational …

Contributions To Statistical Modeling And Estimation Of Rainfall Intensity–Duration–Frequency Curves, Jiyun Huang

All Dissertations

Extreme rainfall can cause flooding, damage infrastructure, and create serious risks for communities. Engineers use Intensity-Duration-Frequency (IDF) curves to estimate precipitation extremes over different lengths of time, such as one hour or one day, and the average time one would expect wait for one of these events to occur. Several approaches exist for estimating IDF curves, but no single approach is known to be best in all cases. In this dissertation, I study statistical methods that aim to improve IDF curve estimation. I use the Canadian Regional Climate Model (CanRCM4) Large Ensemble, which contains 35 independent climate simulations. These simulations …

Flexible Spatial Priors In Bayesian Neuroimaging: Gmrf, Nngp, And Deep Gmrf, Boyoung Hur

All Dissertations

Structural neuroimaging is essential for understanding neurological disorders such as Alzheimer’s disease, enabling accurate delineation of brain regions through image segmentation. Among various segmentation methods, multi-atlas-based approaches like label fusion have become leading techniques. In statistics, Bayesian hierarchical models for label fusion are increasingly favored for their ability to incorporate uncertainty and prior knowledge. Also, a key challenge in modeling neuroimaging data is spatial dependence among image voxels, making the choice of spatial prior critical—particularly in high-resolution settings where segmentation accuracy and computational efficiency are both essential.

This dissertation proposes fully Bayesian spatial hierarchical models that explore two flex- ible …

The Presentation Of Self In Everyday Digital Life: A Study Of Self- Disclosure And Work Environments, Mackenzie Michelle Skiff

Communication & Theatre Arts Theses

The digital age impacts individuals’ lives in many ways. One impact is how and where work is completed across many careers. The work-from-home strategy enables individuals to complete work that is not within a shared space, such as an office. With the absence of this shared space, communication practices within workplaces could be changing. Specifically, self-disclosure while working from home may differ from self-disclosure within the office or hybrid (both in office and remote) work environments. This thesis investigates whether there are differences in self-disclosure practices across three different types of contemporary work environments and offers a digital update to …

Component Model Development Of Heat Exchangers, Expanders, And Control Valves For Autonomous Cryogenics Plant Cool-Down, William Harris Buhrig Iv

Mechanical & Aerospace Engineering Theses & Dissertations

The traditional method of cryogenic plant cool-down involves having continuous on-call staff to head into the office at any time to modify the existing multi-layered PID control systems if the on-call staff member detects a significant deviation from the cool-down plan. This thesis aims to outline an effective method for modeling the structure of systems with performance characteristics that deviate from design requirements and from ideal inlet-outlet correspondence, enabling the adjustment and modification of existing control structures across all Thomas Jefferson National Accelerator Facility (JLab) cryogenic refrigeration plants. Analytical Modeling and Gaussian Process Regression (GPR) are applied to model the …

Is Complexity Virtuous?, Ryan Elmore, Jack Strauss

Business Information and Analytics: Faculty Scholarship

(Kelly et al., 2024) show that increasing complexity in linear models, with potentially thousands of predictors, is "virtuous". Their work contradicts the dogma of model selection, including the Principles of Parsimony and Occam's Razor. They find that when the number of predictors far exceeds the number of observations, the bias-variance trade-off breaks down, the variance declines, and the Sharpe ratio increases. In the context of ridge regression, we find that very high complexity coupled with large penalty terms (excessive shrinkage) generate forecasts that converge to a rolling window of past returns. For example, we show the past twelve-month moving average …

Benchmarking Dna Foundation Models For Genomic And Genetic Tasks, Haonan Feng, Lang Wu, Bingxin Zhao, Chad Huff, Jianjun Zhang, Jia Wu, Lifeng Lin, Peng Wei, Chong Wu

School of Medicine Faculty Publications

The rapid evolution of DNA foundation models promises to revolutionize genomics, yet comprehensive evaluations are lacking. Here, we present a comprehensive, unbiased benchmark of five models (DNABERT-2, Nucleotide Transformer V2, HyenaDNA, Caduceus-Ph, and GROVER) across diverse genomic and genetic tasks including sequence classification, gene expression prediction, variant effect quantification, and topologically associating domain (TAD) region recognition, using zero-shot embeddings. Our analysis reveals that mean token embedding consistently and significantly improves sequence classification performance, outperforming other pooling strategies. Model performance varies among tasks and datasets; while general purpose DNA foundation models showed competitive performance in pathogenic variant identification, they were less …

Improving Glycemic Control Among Indonesian Urban Adults: A Digital And Behavioral Extension Of The Information–Motivation–Behavioral Skills Model, Imelda Appulembang

Kesmas

Management of type 2 diabetes mellitus (T2DM) in Indonesia continues to face challenges due to behavioral, informational, and technological gaps among patients. This study analyzed the influence of self-regulatory competence and information, motivation, family support, and digital health literacy on glycemic control behavior. A cross-sectional survey was conducted from February to April 2025 among 587 adults aged >30 years with T2DM enrolled in the Chronic Disease Management Program at primary health care in six major cities: Jakarta, Surabaya, Yogyakarta, Medan, Makassar, and Banjarmasin. Data were collected through structured questionnaires and analyzed using partial least squares structural equation modeling. The findings …

Tannin Supplementation Alters Foraging Behavior And Spatial Distribution In Beef Cattle, Bashiri Iddy Muzzo, R. Douglas Ramsey, Kelvyn Bladen, Juan J. Villalba

Wildland Resources Student Research

Beef production on chemically uniform grass monocultures can limit nutrient synchrony and contribute to uneven pasture use. We evaluated whether supplementing tannins with bioactive plant secondary compounds improves foraging dynamics and landscape use by beef cattle grazing a meadow bromegrass monoculture in ways aligned with rangeland sustainability. Twenty-four Angus cow–calf pairs were allocated to six 3.6-ha paddocks (four pairs/paddock), randomly assigned to Control (Ctrl; n = 3) or Tannin treatment (TT; n = 3). Animals received 1 kg/cow/day of DDGs, with TT receiving an added 0.4% tannins (2:1 condensed:hydrolyzable). Grazing occurred during four 15-day periods (July– September) across two years. …

Field Validation Of Multiple Species Distribution Models Shows Variation In Performance For Predicting Aedes Albopictus Distributions At The Invasion Edge, Anna V. Shattuck, Brandon D. Hollingsworth Ph.D., Jared Skrotzki, Scott R. Campbell, Christopher L. Romano, Courtney C. Murdock

Faculty Publications

Background

Climate and land use changes have resulted in range expansion of many species. In this shifting disease landscape, it is important to leverage tools that can predict the distributions of invading vectors to target surveillance and control efforts and identify at-risk populations. Species distribution models (SDMs) are used to predict ranges of invasive species; however, invasive species often violate assumptions of equilibrium and niche conservatism. Moreover, these studies are rarely validated using independent data.

Methods 

We use long-term surveillance data for Aedes albopictus, a highly invasive mosquito capable of transmitting several arboviruses, at its range edge to evaluate a …

Exploring The Impact Of Statistics Course Modality On Student Learning: A Mixed Methods Approach, Becky Kelleman

Electronic Theses and Dissertations

The importance of statistical literacy has become increasingly evident, as individuals grapple with interpreting statistics to inform critical decisions. Despite the recognized significance of statistical literacy, challenges persist in both educators’ and students’ efforts to navigate the complexities of statistics education. The purpose of this study is to explore the impact of different course modalities on undergraduate students’ academic performance in introductory statistics courses. Using Social Cognitive Theory (SCT) as a theoretical framework, this research aims to shed light on the complex dynamics influencing statistical literacy attainment. By addressing gaps and inconsistencies in the current literature, this study seeks to …

On Some Algebraic And Dynamical Aspects Of Families Of Polynomials, Prabhakar Ratipal Yadav

Doctoral Theses

This thesis investigates several arithmetic and algebraic properties of polynomials, with a particular emphasis on irreducibility, monogenity, and the behaviour of iterated polynomial sequences. We first study truncated binomial polynomials over the rationals and establish new affirmative results concerning their irreducibility. A substantial part of the work develops a detailed analysis of Newton polygons under polynomial composition. These structural insights yield broad applications, including criteria for stability and eventual stability of large families of polynomials, as well as precise information about the degrees and number of irreducible factors appearing in their iterates. These ideas further connect to questions about ramification …

The Odds Don’T Lie: Mathematical Reasoning And Societal Ignorance In Don’T Look Up, Nysa Vedwan, Shane Carey

LASER Journal

In Adam McKay’s 2021 satirical sci-fi movie Don’t Look Up, two astronomers discover a comet heading directly toward Earth. Despite overwhelming evidence and near-certainty of global extinction, their warnings are ignored and ridiculed. This paper discusses the mathematical and scientific foundations of the movie’s social and political reception, and specifically focuses on orbital prediction and probabilistic modeling as they relate to public understanding of risk. This paper shows how data is often undermined by political and social dynamics, by connecting the fictional events of the movie with real-world crises like the COVID-19 pandemic and the climate emergency. In Don’t Look …

Spatially Mapped Statewide Estimated Potential Evapotranspiration Using An Efficient Surface Interpolation Method: A Case Study Of South Carolina, Sudhanshu S. Panda, Devendra M. Amatya, Ka Kit Liu, Augustine Muwamba, Timothy J. Callahan

Journal of South Carolina Water Resources

Potential evapotranspiration (PET) exhibits substantial spatial and temporal variability across large landscapes, necessitating site-specific estimation for accurate environmental and water resource assessments. However, obtaining PET or ET data for specific locations across an entire state remains challenging due to the limited number of weather stations and associated environmental datasets. This study aimed to develop an automated geospatial modeling framework to map PET distribution across South Carolina, USA, using PET estimated by the temperature-based Hargreaves–Samani (H–S) method with daily weather data from 59 NOAA stations. Because the accuracy of spatial interpolation depends on both the target variable and the desired spatial …

Latent Classification Of Time-Dependent Transition Rates In Longitudinal Binary Outcome Data, Joonha Chang, Wenyaw Chan

School of Public Health Faculty Publications

Continuous-time Markov chain (CTMC) models and latent classification methods are commonly used to analyze longitudinal categorical outcomes in medical research. While CTMC models are popular for their simplicity and effectiveness, their assumption of constant transition rates presents limitations in capturing dynamic behaviors. To address this, non-homogeneous continuous-time Markov chains (NH-CTMCs) have been developed, incorporating time-varying transition rates to enhance model flexibility. In this study, we leverage closed-form transition probabilities for a fully ergodic two-state NH-CTMC model and propose a latent class clustering approach to identify heterogeneous transition rate patterns within the population. We emphasize the potential advantages of these models …

Explainable Post-Operative Patients Recovery Prediction Following Elective Brain Tumor Resection: A Precision Medicine Approach, Eleanor Belkin

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

[Kyda] Biologically Grounded Surrogate-Driven Parameter Inference For Sparsely Observed Dynamical Systems, Joshua C. Macdonald

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

[Project Insight] Spatio-Temporal Analysis Of Domestic Violence In Puerto Rico, Phyllis Muniu

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Mentoring First-Year Stem Students Through Collaborative Research In The Haynes Scholars Program, Alex Capaldi, Laura Tipton

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

[Lele] Incorporating Physiological Constraints In Estimates Of Post-Prandial Insulin Secretion Rate, Justin K. Garrish, Christine L. Chan, Douglas Nychka, Cecilia Diniz Behn

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Correlation With Car Density In Urban Environments And Its Influence On Chronic Obstructive Pulmonary Disease (Copd) Rates In The United States, Daniel Barreiro-Torres, Kedai Cheng

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Statistical Challenges And Simulation Results For Pilot Clinical Trials, Weiliang Cen

USF Tampa Graduate Theses and Dissertations

Background: The effect size estimated from a pilot trial is often an inaccurate reflection of the true effect size observed in a large trial, leading to either underestimation or overestimation. Published data suggest that effect sizes from large trials are typically smaller than those reported in their corresponding pilot trials. To address this discrepancy, conservative or discount adjustment methods are widely recommended to modify pilot trial effect sizes when calculating sample sizes, thereby maintaining adequate statistical power. This study aims to assess effect sizes from both pilot and large trials and to evaluate the performance of existing adjustment methods.

Methods: …

Geographic Patterns Of Educational Achievement: A Methodological Case Study Of Regression Modeling Approaches, Leokadia Lipien

USF Tampa Graduate Theses and Dissertations

This methodological case study introduces a novel approach to investigate the impact of student, teacher, and geographic factors on the academic achievement of virtual school students in Florida. Traditional linear regression models, and even multilevel models, often overlook spatial dependencies, which can lead to biased estimates and incomplete inferences. This research addresses this limitation by comparing a cross-classified multilevel model (CCMM) with a novel cross-classified spatial model (CCSM) that incorporates coefficients from geographically weighted regression (GWR). Utilizing secondary data from a statewide virtual school, including student demographics, teacher characteristics, and standardized test scores, along with U.S. Census Bureau data, the …

Circulating Levels Of Insulin-Like Growth Factor I (Igf-I) And Risk Ofmultiple Myeloma: An Observational And Mendelian Randomisation Study, Yolanda Benavente, Sara Hermosa, Nikos Papadimitriou, Alyssa I. Clay-Gilmour Ph.D., Elizabeth E. Brown, Jonathan N. Hofmann, Nathaniel Rothman, Qing Lan, Sonja I. Berndt, Demetrius Albanes, Mark Purdue, Mitchell J. Machiela, Stephen J. Chanock, Parveen Bhatti, Wendy Cozen, Aaron Norman, Susan L. Slager, James R. Cerhan, Vincent Rajkumar, Shaji J. Kumar, Et. Al.

Faculty Publications

Evidence for an association between insulin-like growth factors (IGF) and multiple myeloma (MM) is inconsistent. We examined total IGF-I concentrations and risk of MM by combining baseline serological data among UK Biobank participants (n = 444 187; 732 incident MM) with a two-sample Mendelian randomisation (MR) analysis using identified genetic variants associated with circulating total IGF-I and IGF-binding protein 3 (IGFBP-3) in the InterLymph consortium (2434 MM and their 2567 controls). Finally, additional lymphoid neoplasm (LN) subtypes were included for comparison with the main hypothesis. Circulating IGF-I level was positively associated with MM risk Hazard ratio-HR-per one standard deviation-SD-increase …