Physical Sciences and Mathematics Commons^™

Advancing Social Media Analytics And Personalized Generation Via Transfer Learning, Discourse-Aware Modeling, And Collaborative Modeling, Gibson Nkhata

Graduate Theses and Dissertations

Social media platforms have become central to information exchange, shaping public opinion across social, political, and economic domains. However, the massive volume of user-generated content, combined with its informal, nuanced, and often noisy nature, presents significant challenges for automated analysis and generation. Tasks such as stance detection, rumor verification, and personalized content generation are further complicated by sarcasm, evolving discourse structures, and diverse user preferences. Addressing these challenges requires models that can effectively leverage linguistic nuance, conversational dynamics, and collaborative user signals. Transfer learning has emerged as a powerful paradigm for improving performance in low-resource and complex language understanding tasks. …

Towards Audio-Driven Photorealistic Avatars For Teleconsultation: A Development And Evaluation Framework Under Constrained Bandwidth Environments, Fnu Himanshu

Graduate Theses and Dissertations

Telehealth can improve access to healthcare services, especially for patients in rural and underserved areas. Many telehealth services use video communication to provide real-time interaction and a visible connection between patients and healthcare providers. However, video communication requires continuous transmission of audio and video data. When network conditions are limited or unreliable, audio and video interruptions can reduce communication quality. This thesis explores an audio-driven photorealistic avatar as a possible visual communication layer for teleconsultation without requiring continuous webcam video transmission. It develops two connected frameworks: the Audio-Driven Photorealistic Avatar Communication Framework and the Evaluation Framework. The Audio-Driven Photorealistic Avatar …

Improving Urban Search And Rescue Team Coordination Through Adaptive Context Awareness, Daniel Reyes Duran

Doctoral Dissertations and Master's Theses

Modern multi-agent Urban Search and Rescue (USAR) operations heavily rely on mobile geospatial Common Operating Pictures (COPs) to maintain team coordination and Situational Awareness (SA). However, the proliferation of high-frequency sensor telemetry at the tactical edge has introduced a data saturation paradox challenge: while information theoretically drives informed decision-making, unmanaged data surges induce increased operator cognitive overload and alert fatigue on mobile End-User Devices (EUDs), while downstream data-broadcasting models inherently strain edge processing and viewport environments.

To resolve these constraints, this dissertation presents a context-aware Value of Information (VoI) data-management framework integrated directly with a custom, event-driven Android Team Awareness …

Investigation Of Early To Late Cretaceous North American Ecosystems And Paleoclimate Using Geochemical Proxies, Clayton William Forster

Graduate Theses and Dissertations

The relationships between the environment and an organism can be traced through stable isotope and trace element geochemistry. This thesis explores the stable oxygen and carbon isotopic composition of fossil vertebrate assemblages in pursuit of revealing the relationships between dinosaurs and their archosaur relatives with the environment in which they lived during the Cretaceous. The Cretaceous Period of North America experienced some of the hottest intervals in the Phanerozoic Eon and the continental vertebrate taxa that existed during this time recorded these periods within the stable isotopic composition of their skeletal bioapatite. Oxygen isotopes in the bioapatite of vertebrates reflect …

Item Response Theory Evaluation Of Mental Health Sentiment Scales, Muhammad Amzad Hossain

Graduate Theses and Dissertations

Mental health is an essential part of overall well-being. Accurate measurement of constructs such as loneliness, anxiety, depression, and life satisfaction is extremely important in research and practice. Traditional approaches based on Classical Test Theory (CTT) are limited. They rely on total test scores and assume constant measurement error across individuals. They may not reflect true variability in measurement precision (Zein & Akhtar, 2025; Marvianto, 2023). In contrast, Item Response Theory (IRT) provides an advanced approach by examining item-level performance. It models the relationship between latent traits and responses (Zein & Akhtar, 2025 ). To address these limitations, this study …

Univariate And Bivariate Binary Spatial Regression Models With Application To Plant Abundance Data, Amir Hamza Akash

Graduate Theses and Dissertations

Analyzing species distributions is of prime interest in ecological research. Prevalence of a species usually depends on several environmental and topographic features not all of which can be quantified or measured. Spatial random effects play an important role as a surrogate for missing features that can explain similarity in species prevalence patterns between neighboring locations. In this thesis, we focus on a dataset on abundance of plants in the southern part of South Africa. First, we build a hierarchical Bayesian model for binary regression, using the probit link, on presence/ absence of a species based on available covariates. Since the …

Eeg P300 Ai Classification And Accessibility Keyboard Control Using Openbci’S Ultracortex Mark Iv For Reactive Brain-Computer Interaction, Grant King

Theses and Dissertations

Brain-computer interfaces provide people who cannot feasibly control a keyboard and mouse with an alternative method to type, to move a cursor, or to generally issue commands and make selections. A non-invasive recording modality for brain-computer interfaces is electroencephalography, or EEG. The OpenBCI Ultracortex Mark IV is an EEG headset enabling relatively low-cost EEG acquisition using wet or dry electrodes. P300 is an event-related potential involving a deflection in an EEG channel's voltage typically 300 milliseconds after the onset of an "oddball" stimulus. A person's P300 response can be used to control a selector application. This study investigates classification of …

Analysis Of Clinical Health Worker Notes With Explainable Artificial Intelligence For A Better Perspective In Preventing Readmission, Christopher Scott Klimp

Theses and Dissertations from DePaul University

Emergency Department (ED) readmissions remain a major challenge for healthcare systems, affecting both patient care quality and financial costs. Most prediction models depend largely on structured data from clinical tools that assign points to a small set of predefined factors – such as comorbidities, previous hospital visits, and behaviors such as smoking and drinking – and then sum those points to produce an overall risk score. These point-based tools leave out important information from Social Determinants of Health and a wealth of information from Community Health Workers (Community health workers (CHWs), trusted members of a community who help connect people …

Using Recommender Systems To Help Revitalize Local News, Payam Pourashraf

Theses and Dissertations from DePaul University

Local news outlets have experienced steep declines in readership as national and global online news sources have expanded and consolidated audience attention. Because many local media companies rely primarily on subscription-based business models, they must increase user engagement and provide clearer value to local subscribers. Personalization and recommender systems offer one promising path toward this goal. However, many recommender systems assume that a user’s past behavior can be summarized in a single unified profile. In practice, preferences are often context-dependent: the same person may prefer different content depending on geography, time, task, or situation. Local news offers a socially important …

Advancing Imbalanced Classification Through Representation Learning, Morteza Mohammady Gharasuie

Computer Science Theses & Dissertations

Real-world datasets frequently exhibit severe class imbalance, where certain categories are significantly underrepresented relative to others, leading standard empirical risk minimization to bias learning toward majority classes and degrade performance on minority categories. This dissertation addresses imbalanced classification across both structured tabular data and long-tailed visual recognition by developing methods that improve representation learning and decision reliability under skewed distributions. For tabular data, it introduces Conditional Probability Representation (CPR), a target-based encoding framework that embeds feature–label relationships directly into the representation space, enhanced by a progressive feature upgrading mechanism for semi-supervised settings and a class-frequency–aware extension that improves robustness to …

On The True Interstellar Anisotropy Of Tev Cosmic Rays And Its Implications For The Local Interstellar Medium, Noufel D. Maalal

Theses and Dissertations

Several ground-based cosmic ray (CR) air shower experiments have produced sky maps of intensity anisotropy in the energy range from 1 TeV to a few hundred TeVs with very high statistics and angular resolution. These measurements provide opportunities to study CR sources and propagation in the interstellar medium (ISM). Such studies present two major difficulties. Firstly, CRs are deflected by the heliospheric magnetic field on the last stretch of their journey to Earth. Secondly, measurements at different latitudes are difficult to compare, leading to uncertainties in latitudinal variations on the order of the observed anisotropy. Experiments usually assume latitudinal variations …

A Machine-Learning-Based Systematic Framework For Modeling Compression And Recompression Indices For Florida Soils, Michael Morales

Doctoral Dissertations and Master's Theses

This thesis develops a machine-learning framework for estimating the compression index and the recompression index of Florida soils from routinely measured index properties, and reports two studies that build it. Consolidation settlement design requires both indices, and both are obtained from the incremental-loading oedometer test, which occupies a specimen for one to two weeks; the index tests that accompany it are complete within hours. Empirical correlations have filled that interval since the 1950s, but their coefficients are calibrated on specific soil populations and transfer poorly between regions. The first study analyzes 376 consolidation tests compiled for the Florida Department of …

Cosmic Chirps: Studies In The Evolution And Detection Of Gravitational Waves From Compact Binary Systems, Calla Irene Bassett Bigg

Graduate Theses and Dissertations

This dissertation will go over three projects that have to do with gravitational wave mechanics and history. The first project is about investigating computationally cheaper approximation methods for modeling EMRI (extreme mass ratio inspiral) orbits using interpolation. Two codes are interpolated together for full coverage of the parameter space. This interpolation has yet to be tested for accuracy but the preliminary outlook is positive. This may well be a useful tool for studying EMRIs. The second project is investigating the origins of the term “chirp mass”, where chirp mass is a combination of the two masses in a binary that …

Soil Moisture Regime Effects On Greenhouse Gas Emissions In A Native Tallgrass Prairie In The Ozark Highlands, Thomas William Dockery

Graduate Theses and Dissertations

The Ozark Highlands is an ecoregion in the mid-southern portion of the United States that is characterized by a mosaic of tallgrass prairies, oak (Quercus spp.) savannas, and oak-hickory (Carya spp.) forests, which represents a unique biophysical transition zone between the relatively dry grasslands of the west and the humid forests of the southeast. Quantifying greenhouse gas (GHG) emissions, namely carbon dioxide (CO2), methane (CH4), and nitrous oxide (N2O), from natural, undisturbed ecosystems is critical to understanding atmospheric warming and climate-change implications. The objective of this study was to simultaneously evaluate CO2, CH4, and N2O emissions in an aquic and …

Physics-Informed Machine Learning For Predictive Digital Twins In Greenhouses, Hoang Kim Tran

Graduate Theses and Dissertations

Greenhouses are widely used to create controlled environments for crop production, where indoor climate variables such as air temperature, relative humidity, CO2 concentration, radiation, and soil or substrate conditions directly affect plant growth, yield, energy consumption, and resource use. However, greenhouse climates are highly dynamic because they are influenced by complex interactions among outdoor weather, greenhouse structure, crop transpiration, heating systems, ventilation, screens, fans, irrigation, and other actuators. Building digital twins for greenhouses provides a powerful way to represent, monitor, and predict these climate dynamics. A predictive digital twin can simulate future indoor climate states based on current greenhouse conditions, …

Benchmarking Current Progress In 3d Content Generation, Vuong Ho

Graduate Theses and Dissertations

In recent years, 3D generation has rapidly advanced with the development of powerful generative AI models capable of producing high-quality 3D content from various modalities, including text, images, and multi-view inputs. These advancements have significantly accelerated progress in applications such as gaming, virtual reality, robotics, and digital content creation. Despite this progress, there is still a lack of standardized and fair benchmarking protocols for evaluating 3D generation methods. Existing approaches are often assessed under inconsistent experimental settings, using different datasets, evaluation metrics, and processing pipelines. Such inconsistencies make reliable and objective comparisons difficult, limiting our understanding of the strengths and …

Iterative Generation Of Feature-Based Cad Models Using An Llm With Domain Specific Constraints, Ammon I. Hepworth

Graduate Theses and Dissertations

This paper presents a method to generate feature-based parametric mechanical CAD models from text input. The method uses domain-specific constraints (DSCs) to guide a large language model (LLM) in the generation of scripts to build models from the CAD API. It also presents a framework for an iterative text-based system that produces parametric CAD models. The method was implemented by developing DSCs for FreeCAD and Open AI GPT-5.2 and incorporated into a web-based software application which generates models that can be visualized with an interactive viewer after each iteration. Tests were run comparing various models with and without this method. …

Statistical Machine Learning For Calibrating Climate Model Wind Fields., Augustine Ouru

Graduate Theses and Dissertations

This thesis investigates statistical calibration methods for wind data from Global Climate Models (GCMs), with emphasis on wind speed and wind direction. The analysis uses 30 years of daily observed and GCM wind records from 9 spatial locations in the South East USA. Wind is represented in polar coordinates, but also often modeled in Cartesian coordinates. Four calibration models are compared: a marginal wind speed model, an independent Cartesian model. The calibration models are based on semi-parametric quantile regression, a flexible conditional density estimator fitted using neural networks. The neural network objective functions are optimized using maximum likelihood estimation (MLE) …

Autoencoders As Classifiers Trained On Single Sources Of Radiographic Images For Generalizability Across Unseen Sources, Ryan M. Putney

USF Tampa Graduate Theses and Dissertations

Artificial neural networks trained to classify X-ray images according to disease state will learn to distinguish between technical or procedural variations in the images rather than features relevant to the disease. For example, the model might learn to recognize the machine that captured the image or to distinguish an image taken while the patient is lying supine or standing upright. The present work is aimed at using autoencoders as a generalizable classifier to detect COVID vs pneumonia (PNA) X-ray images. The first experiment was to find an architecture for a fully convolutional autoencoder (CAE) and for a convolutional autoencoder with …

Trustworthy Reinforcement Learning And Communication-Efficient Multi-Agent Systems, Rui Zuo

Dissertations - ALL

The rapid proliferation of autonomous systems, such as Unmanned Aircraft Systems (UAS) transitioning to large-scale Beyond Visual Line of Sight (BVLOS) operations, demands a paradigm shift toward reliable, transparent, and resilient autonomy. While Deep Reinforcement Learning (DRL) and Multi-Agent Reinforcement Learning (MARL) have demonstrated exceptional capabilities in complex decision-making and coordination, their real-world deployment in safety-critical domains is hindered by two fundamental challenges. First, the opaque, "black-box" nature of DRL models prevents human operators from understanding and trusting the agents' underlying logic. Second, as multi-agent operations scale, they become severely constrained by the stochastic link qualities and strict bandwidth limitations …

Atropisomer Mechanochemistry Of Diarylethene Mechanophores: A Study Of Structure-Mechanical Activity Relationships, Cijun Zhang

Dissertations - ALL

Stimuli-responsive organic structures are advanced, intelligent platforms that dynamically adjust their physical or chemical properties—such solubility, or color—in response to external stimuli including light, heat, pH, redox conditions, mechanical force, or magnetic fields. Among these structures, mechanophores represent an important class that is specifically responsive to mechanical force. Synthetic mechanophores can be rationally engineered to exhibit tunable mechanosensitivity as well as tailored chemical and physical properties. In this work, we designed and synthesized a type of atropisomeric mechanophores based on sterically congested diarylethene photoswitches, and systematically investigated their mechanical and photochemical properties. Chapter 1 Chapter 1 provides a general introduction …

Scaling Logical Reasoning On Modern Hpc Hardware, Yihao Sun

Dissertations - ALL

Deductive logic reasoning has evolved from a theoretical symbolic artificial intelligence tool into a massive computational workload. Modern domains, ranging from static program analysis and binary reverse engineering to knowledge-graph reasoning, rely on Datalog, a logical query language, to express deeply recursive, declarative specifications. However, scaling logic reasoning to these industrial workload exposes two interlocking ceilings in traditional engines. Architecturally, the memory bandwidth and parallel throughput of single-node CPUs fall drastically short of the read- and write-heavy demands of semi-naive evaluation. Asymptotically, traditional query processing algorithms, such as binary join algorithms generate massive intermediate relations that exhaust device memory on …

On The Extension Conjecture For Koszul Algebras, Benjamin Kaufman

Dissertations - ALL

We investigate questions related to the extension conjecture for finite-dimensional algebras. Suppose $\Lambda = \kk Q/I$ is a finite-dimensional algebra given by a quiver with relations. The extension conjecture asserts that if $S$ is a simple right $\Lambda$-module corresponding to a vertex with a loop, that is, $\Ext_\Lambda^1(S,S)\neq 0$, then $\Ext^n_\Lambda(S,S)\neq 0$ for infinitely many $n$. We show that one can obtain information about the non-vanishing of the extensions $\Ext^n_\Lambda(S,S)$ by looking at the graded Cartan matrix and its inverse. We use this connection to prove the extension conjecture for standardly graded $\kk$-algebras on two vertices with Loewy length at …

Using Low-Frequency Vibrational Spectroscopy To Develop Analytical Profiles For Polymorphic Organic Molecular Crystals, Salvatore Zarrella

Dissertations - ALL

Low-frequency vibrational spectroscopy provides a sensitive approach for characterizing polymorphism and intermolecular dynamics in organic molecular crystals. Terahertz time-domain spectroscopy (THz-TDS) and low-frequency Raman spectroscopy probe collective lattice vibrations arising from weak intermolecular interactions, offering direct insight into crystal packing, phase stability, and structural organization that is often inaccessible to conventional diffraction and mid-infrared techniques. To interpret these modes, experimental measurements are combined with periodic solid-state density functional theory (ss-DFT), which enables vibrational assignments to specific intermolecular motions, and crystal structure prediction (CSP), which maps accessible polymorphic energy landscapes. Together, these methods form a unified experimental–computational framework for understanding molecular …

From Detection To Segmentation: A Foundation Model Approach To Organoid Brightfield Image Analysis Using Sam 3, Hiren Manani

Theses - ALL

This thesis presents the first systematic application of SAM 3, a unified foundation model for promptable segmentation, to mouse small intestinal organoid brightfield microscopy image analysis. The work spans the complete pipeline from zero-shot baseline evaluation through domain-specific fine-tuning on a GPU cluster, and documents the full engineering process required to adapt a state-of-the-art foundation model to a novel biomedical imaging domain. A comprehensive literature review of over 20 papers spanning detection-based, classical segmentation, foundation model, and morphological analysis approaches identified a clear research gap that this thesis addresses. Five critical compatibility patches were developed to deploy SAM 3 on …

Constrained Neural Intelligence: Investigations Into Deep Multi-Objective Optimization, Naveed Tahir

Dissertations - ALL

Neural intelligence is identified with complex learning problems optimized over the high-dimensional, non-convex parameter spaces of deep neural networks. Solving such problems generally requires handling competing objectives and conflicting constraints. This is traditionally dealt with using heuristic methods that collapse such complexity into unconstrained, singular objectives. While computationally convenient, this invites a tradeoff against the precision and stability afforded by non-heuristic, geometry-aware approaches. This dissertation explores constrained multi-objective learning in various applied and theoretical contexts and highlights the feasibility of approximate methods as well as the necessity of exact methods. We propose a framework for equality-constrained deep learning via approximate …

Thermal Aberrations And Optical Design For Current And Future Gravitational Wave Detectors, Matthew Richard Todd

Dissertations - ALL

Since the first detection of gravitational waves in 2015, the LIGO-Virgo-KAGRA collabo- ration has detected over 300 gravitational-wave events. Planned upgrades to each detector will further improve gravitational wave sensitivity limits, pushing the frontier of multi- messenger astronomy and paving the way for next-generation detectors, like Cosmic Ex- plorer and Einstein Telescope. Though many challenges to reach sensitivity goals are being addressed, there are still cru- cial aspects of the detectors that are poorly understood and will inhibit gravitational wave detection commissioners from bringing future detectors to their design sensitivity. In par- ticular, increased circulating arm power targets will exacerbate …

Peptide And Peptide Bioconjugate Based Drug Development For The Treatment Of Metabolic Diseases, Nancy Cham

Dissertations - ALL

The Doyle group has coined the term ‘corrination’ to describe the conjugate modification of a peptide, protein, small molecule, or radionuclide with a corrin ring-containing molecule such as cobalamin, also known as vitamin B12 (B12), or cobinamides. By exploiting the innate chemico-physical properties of corrin ring-containing compounds, both in general and specifically via the innate dietary B12 uptake pathway in mammals, corrination has been explored for drug development and targeted/localized delivery of probes and therapeutics. Most recently, it is in the field of peptide-based therapeutics that corrination is generating significant interest, no doubt driven in part by the recent successes …

Image Restoration Regularized By Structured Sparsity Promoting Functions: Theory, Algorithms, And Applications, Jianchen Wei

Dissertations - ALL

Image restoration aims to recover an unknown clean image from observations degraded by blur, subsampling, missing pixels, or noise. This dissertation develops and analyzes variational image restoration models based on structured sparsity promoting functions (SSPFs) and their Moreau-enveloped regularization. The main objective is to design nonconvex regularization models that promote structured sparsity in transformed image representations while remaining analytically tractable and computationally effective. The first part of the dissertation studies an SSPF regularized image restoration model. Under the identifiability condition $\ker(A)\cap \ker(B)=\{\bm0\}$, where $A$ is a linear forward degradation operator and $B$ is a transform operator used to extract image …

Multi-Modal Survival Prediction On Breast Cancer Mammograms And Enabling Multi-Institutional Collaborations With Federated Learning, Nikolas Koutsoubis

USF Tampa Graduate Theses and Dissertations

Cancer remains one of the leading causes of mortality worldwide, and machine learning is well positioned to leverage the large volumes of routinely collected clinical and imaging data to improve patient outcomes. Realizing this potential at scale requires three capabilities that current practice does not yet deliver in combination: models that integrate the multiple data modalities clinicians use, training procedures that respect institutional data-sharing constraints, and tooling that enables sharing of de-identified data when federated approaches are not sufficient. This dissertation develops methods and infrastructure addressing each of these capabilities in the context of breast cancer and oncology more broadly. …