Engineering Commons^™

Taylorkan-Vit: Parameter-Efficient Vision Transformers For Medical Image Classification, Kaniz Fatema, Dr. Emad Mohammed, Dr. Sukhjit Singh Sehra

Theses and Dissertations (Comprehensive)

Effective and interpretable classification of medical images remains a critical challenge in computer-aided diagnosis, particularly in data-scarce and resource-constrained clinical settings where traditional deep learning models prove impractical. This study addresses the fundamental barrier to Vision Transformer adoption in medical imaging—massive parameter counts and data requirements—through a systematic two-phase methodology. Phase 1 evaluates three spline-based Kolmogorov–Arnold Network (KAN) variants to identify the optimal nonlinear approximation function for parameter-efficient medical image classification: SBTAYLOR-KAN (B-splines with Taylor series), SBRBF-KAN (B-splines with Radial Basis Functions), and SBWAVELET-KAN (B-splines with Morlet wavelets). Comprehensive experiments across brain MRI, chest X-rays, and tuberculosis datasets—without any image …

Assessing Dissolved Organic Matter Sources And Dynamics In Urban Stormwater: Implications For Greenhouse Gases, Harper W. Schmalz

Theses and Dissertations (Comprehensive)

Stormwater management ponds (SWMPs) are important aspects of land-use planning and increasingly recognized as active sites of biogeochemical processing that influence carbon cycling; however, little research has investigated the controls on dissolved organic and dissolved inorganic carbon (DOC and DIC) within these systems. This thesis examined the processing and transformations of dissolved carbon between three compartments to support the development of a greenhouse gas (GHG) box-model for urban stormwater ponds, including SWMP sediment, surface water, and vegetation. The objective of this thesis was to assess the biogeochemical processes that govern the rate and transformation of DOC and DIC between these …

Evaluating The Impact Of Cognitive Distraction On Spaceflight-Relevant Task Performance Using Surface Electromyography And Motion Capture, Allyson K. Mitchell

UNF Graduate Theses and Dissertations

Cognitive distraction poses a risk to astronaut performance during complex, multitasking operations in spaceflight environments. This study examined the effects of cognitive load on neuromuscular coordination and task execution using surface electromyography (sEMG) and motion capture. Thirteen participants performed spaceflight-relevant tasks under undistracted and distracted conditions, with distraction induced through verbal questioning. EMG signals from eight upper-extremity muscles were processed using envelope filtering, peak normalization, and time normalization to enable inter-subject comparison, and group-level mean activation with standard deviation was analyzed. While overall muscle activation was similar between conditions, phase-dependent differences were observed, with undistracted trials showing higher activation during …

Mechanical Behavior Of Additively Manufactured Ti-6al-4v Eli Parts: Effects Of Laser Parameter Selection, Samuel Lopez

UNF Graduate Theses and Dissertations

Additive manufacturing (AM) of TI-6AL‑4V Extra‑Low Interstitial (ELI) enables complex geometries for fatigue‑critical medical device applications, yet fatigue performance remains sensitive to process‑induced defects. This work investigates the effect of laser process parameter selection on the microstructure, mechanical properties, and fatigue behavior of TI- 6AL‑4V ELI fabricated via laser powder bed fusion (L‑PBF) using a Renishaw RenAM system. The influence of laser parameters was isolated by holding powder chemistry, build orientation, scan strategy, sub‑transus annealing, and post‑processing constant between a non‑optimized baseline and an optimized parameter set selected based on tensile performance.

Optical microscopy showed the optimized condition exhibited improved …

Structural Batteries For Aerospace Applications, Tariqullah Wardak

Honors Undergraduate Theses

There is increasing pressure on the aviation sector to lower carbon emissions and switch to entirely electric and hybrid propulsion systems. However, the feasibility of standard lithium-ion batteries for long-range aircraft is limited, as they add substantial weight and occupy significant volume. Structural batteries, which combine load-bearing capability with energy storage, offer a potential pathway to lighter and more efficient aerospace systems.

This work investigates a carbon-fiber-based structural battery that utilizes carbon fiber as both a current-collecting, load-bearing electrode and a component of the composite structure. In contrast to lithium-ion chemistries, a zinc-based aqueous electrolyte is chosen for better environmental …

Preventing G/J Tube Dislodgement: A Device And Communication Innovation, Sarah Clark

2026

The Problem
G/J tube dislodgement is a frequent complication in pediatric patients
Leads to:

• Emergency department visits
• Hospital admissions
• Delays in nutrition/medication

Impact on Patients & Families:

• IV placement (traumatic)
• Radiation exposure
• Overnight hospital stays

Impact on Nurses & System:

• Increased workload (admissions, coordination)
• Occupied inpatient beds for stable patients
• Inefficient care processes

Aims/Objectives
Aim: Reduce unplanned G/J tube dislodgements and related hospital utilization.
Objectives: Develop a breakaway connector prototype

Implementation and Evaluation
Setting: Pediatric inpatient & outpatient system
Participants: Nurses (bedside, GI, IR), caregiver, innovation team
Process:
Roundtable discussions → identified workflow gaps
Communication/workflow audit
Developed device …

Using A Study Journal To Support Class Engagement And The Development Of Entrepreneurial Mindset Habits, Otilia Popescu, Dimitrie C. Popescu

Engineering Technology Faculty Publications

Engineering Technology programs were historically introduced to support non-traditional students and offer college pathways for students working and having already a developing career. This is even more true in the current academic environment, with a large percentage of students enrolled in engineering technology programs being either fully or part-time employed, active or retired military, and at different stages in their lives, usually with families to care for. Often, non-traditional students attend classes online, either synchronously or even more often asynchronously, due to their schedule constraints. Course instructors regularly face schedule or time management constraints from the students’ side, and they …

Towards Supporting Real-Time Estimation Of Vehicle Fuel Consumption And Co2 Emissions In Smart City Applications, Abrar Alali, Stephan Olariu

Computer Science Faculty Publications

This paper evaluates a simplified physics-based energy demand model designed to estimate vehicle fuel consumption and CO₂ emissions—a critical tool for sustainable transportation planning and smart city applications. Unlike data-driven regression models that lack generalizability for user-defined conditions or complex physics-based approaches that rely on extensive, often proprietary data, the simplified model is distinguished by its minimal parameter requirements, depending primarily on a single, overarching powertrain efficiency value. A key contribution is the comprehensive empirical evaluation of the simplified model against official Environmental Protection Agency (EPA) test data across multiple driving cycles and vehicle types, providing a rigorous validation previously …

Privacy-Preserving Federated Learning With Optimized Ensemble Weighting And Knowledge Distillation For Covid-19 Detection From Non-Iid Medical Imaging Data, Richard Annan, Hong Qin, Robert Newman, Madhuri Siddula, Letu Qingge

Computer Science Faculty Publications

Medical imaging enables rapid and accurate diagnosis of COVID-19, with CT scans proving especially effective. However, data privacy concerns limit collaborative model development across hospitals. To address this issue, we introduce a novel federated learning framework. It is referred to as Independent Knowledge Distillation with post-Ensemble Federated Learning (IKDEFL). Differential Privacy (DP) is integrated into the framework to improve privacy guarantees. Three DP mechanisms are evaluated. These include Fixed Gaussian, Gaussian Adaptive, and Tree Adaptive. The evaluation has been conducted on heterogeneous and Non-Independent and Identically Distributed (Non-IID) datasets. These datasets reflect real-world hospital scenarios. Results show that IKDEFL significantly …

Biosecure-Llm Framework: Protecting Llms From Cyberbiosecurity Threats And The Case For Independent Ai Safety Governance, Xavier-Lewis Palmer, Lucas Potter, Srdjan Lesaja, Sotirios Karathanasis, Mohammad Ghasemigol

Computer Science Faculty Publications

Large Language Models (LLMs) are becoming critical infrastructure in scientific, healthcare, and governmental contexts. As frontier AI laboratories increasingly partner with government agencies, a fundamental question arises: Who should control the safety and policy-enforcement layers that constrain model behavior? Current safety mechanisms (LLM guardrails) are typically designed for generic "harmlessness" and operate by detecting semantic patterns and refusing requests. However, they are inadequate governance instruments because they cannot implement auditable, domain-specific controls tied to external regulatory policy objects (e.g., control lists or rules governing personally identifying information). Even a perfectly aligned model is not able to express institution-specific policy without …

A Comparative Analysis Of Explainable Ai (Xai) Techniques For Transparent And Reliable Image Classification, Sovon Chakraborty, Shakib Mahmud Dipto, Kevin R. Pilkiewicz, Michael L. Mayo, Pratip Rana

Computer Science Faculty Publications

Evaluating the trustworthiness of black-box machine learning models remains a significant methodological challenge. Their lack of transparency and interpretability limits applicability, because stakeholders often seek transparency before trusting the results of black-box machine learning models. Explainable AI (XAI) methods provide for human-understandable justifications and informed decision-making of these black-box architectures. Therefore, it is imperative to select the proper XAI model tailored to specific tasks. In this research, we focus on examining four XAI techniques: PEEK, LRP, GRAD-CAM, and LIME to understand how they perform against each other for image classification tasks. We evaluate the performance, robustness, generalizability, noise stability, and …

Isotropic Shrinkage Of Patterned Vacancies Enables Three-Dimensional Nanoprecise Metastructures For Visible Light Applications, Quansan Yang, Gaojie Yang, Takahiro Nambara, Hiroyuki Kusaka, Yuichiro Kunai, Alex C. Matlock, Corban Swain, Brett Pryor, Yannick Salamin, Daniel Oran, Hasindu Kariyawasam, Ramith Hettiarachchi, Dushan Wadduwage, Marin Soljačić, Peter T. C. Soflaei, Edward S. Boyden

Computer Science Faculty Publications

Three-dimensional metastructures with nanoscale feature sizes exhibit unique properties compared with structures with larger feature sizes, but are difficult to fabricate. Here we introduce implosion carving (ImpCarv), a method for photopatterning vacancies of complex geometry throughout materials, followed by isotropic shrinkage (>10-fold). ImpCarv works by photoactivating sensitizers to generate reactive oxygen species that cleave a swollen hydrogel at defined points, followed by controlled shrinkage via dehydration. ImpCarv creates three-dimensional metastructures where the refractive index of each point throughout a material can be specified with nanoscale precision via material presence or absence. By leveraging refractive index programmability for precise phase …

Memebuddy: Dialog-Style Audio Representations For Engaging Non-Visual Meme Experiences, Chirag Bhansali, Vikas Ashok, Hae-Na Lee

Computer Science Faculty Publications

Image memes are a pervasive form of online communication, widely used to convey humor, opinions, and cultural references. Prior work has explored making memes accessible to blind users, primarily through auto-generated descriptive captions. While these approaches improve comprehensibility and sometimes incorporate prosodic or emotional cues, they often fail to capture the humor, narrative structure, and contextual nuances that make memes engaging. We present MemeBuddy, a system that models memes as dialog, generating structured, multi-turn audio representations using role-based speakers. MemeBuddy reinterprets a meme as a conversation between two speakers, integrating extracted meme text with contextual knowledge implicitly inferred by a …

Susceptibility To High-Fidelity Misinformation: An Eye-Tracking Analysis, Yasasi Abeysinghe, Gavindya Jayawardena, Enkelejda Kasneci, Sampath Jayarathna

Computer Science Faculty Publications

With the rise of online misinformation and AI-generated text, understanding human perception of news truthfulness is critical. In this study, we examine visual attention and cognitive processing using eye-tracking measures as individuals read fake and real news articles sharing nearly identical structure and imagery, differing only in subtle textual changes. Using the public FakeNewsPerception dataset, we analyze advanced gaze measures, including scanpaths, AOI transitions, and luminance-corrected pupil measures, beyond basic gaze features, in relation to news truthfulness and perceived believability. Results show that, given the high fidelity of the fake news, readers exhibited comparable visual scanning patterns, attention allocation across …

Distributed Semi-Speculative Parallel Anisotropic Mesh Adaptation, Kevin Garner, Polykarpos Thomadakis, Nikos Chrisochoides

Computer Science Faculty Publications

This paper presents a distributed memory method for anisotropic mesh adaptation that is designed to avoid the use of collective communication and global synchronization techniques. In the presented method, meshing functionality is separated from performance aspects by utilizing a separate entity for each - a multicore cc-NUMA-based (shared memory) mesh generation software and a parallel runtime system that is designed to help applications leverage the concurrency offered by emerging high-performance computing (HPC) architectures. First, an initial mesh is decomposed and its interface elements (subdomain boundaries) are adapted on a single multicore node (shared memory). Subdomains are then distributed among the …

Untrained Position-Encoded Multilayer Perceptron Network For Structured Illumination Microscopy Reconstruction, Sahil Sharma, Leonidas Zimianitis, Krishnendu Samanta, Balpreet Singh Ahluwalia, Joby Joseph, Dushan N. Wadduwage

Computer Science Faculty Publications

Structured Illumination Microscopy (SIM) enables super-resolution imaging by encoding high-frequency spatial information through patterned light. While traditional Fourier-based reconstruction methods are prone to artifacts under suboptimal conditions, recent deep learning approaches often require large training datasets and lack adaptability across different imaging setups. In this work, we present Position Encoded Multi-Layer Perceptron (PEM) network that leverages implicit neural representations (INRs) and SIM forward-model-driven modeling to reconstruct super-resolved images without any training data. PEM-SIM represents each spatial coordinate as a combination of sinusoidal functions across multiple frequencies, enabling rich encoding of fine spatial detail. A forward model grounded in SIM image …

Adaptive Self-Attention For Enhanced Segmentation Of Adult Gliomas In Multi-Modal Mri, Evan P. Savaria, Jiangwen Sun

Computer Science Faculty Publications

Every year there are an estimated 80,000–90,000 new glioma cases, highlighting the need for reliable imaging-based decision support. Although deep learning has improved tumor sub-region segmentation, many state-of-the-art models fail to fully capture complementary information across T1, T1Gd, T2, and FLAIR MRI modalities and often operate as “black boxes,” limiting physician trust when precise delineation is critical for surgical planning, radiation targeting, and treatment monitoring. To address these limitations, we propose AIMS, an Adaptive Integrated Multi-Modal Segmentation framework that maintains modality-specific feature streams and employs adaptive self-attention within a hierarchical CNN-Transformer architecture to prioritize and fuse multi-modal MRI features. We …

Application Paths Of Semantic Modeling In Financial Fraud Detection And Risk Identification, Victor P. Gauthier, Daniel S. Wu

Computer Science Faculty Publications

Financial fraud and risk pose significant threats to economic stability and individual well-being. Traditional detection methods often struggle to keep pace with increasingly sophisticated fraudulent schemes. Semantic modeling, which focuses on understanding the meaning and relationships within data, offers a promising avenue for enhancing fraud detection and risk identification. This review paper explores the application paths of semantic modeling in this domain. We begin with a historical overview of fraud detection techniques, highlighting the limitations of traditional approaches. Subsequently, we delve into core themes, including knowledge graph-based fraud detection and semantic rule-based inference for risk assessment. We then compare and …

Study Of Bearing Capacity Testing And Soil Preparation Techniques In Lunar Highlands Simulant At Field Scale, Christi A. Lecaptain

Dissertations, Master's Theses and Master's Reports

Humanity seeks to return to the surface of the Moon with the advent of the Artemis missions. These endeavors plan to be the beginning of a new era as NASA and other space organizations seek to establish a lunar base. Ahead of any astronauts or mining infrastructure, the physical groundwork will need to be laid to support the arrival of rockets, boots, and rover wheels. As surfaces are prepared, they will need to be tested and verified to ensure the stability of any structures placed on top. Understanding the bearing capacity is vital to soil quality testing. A standard terrestrial …

Beyond Receptive Measures: Development And Validation Of The Spatial Grid Drawing Assessment (Sgda) As A Productive Measure Of Spatial Skill, Katrina L. Carlson

Dissertations, Master's Theses and Master's Reports

Spatial skills are vital in many STEM disciplines, starting at or prior to university training, and often extending throughout one’s career. The most widely used spatial ability measures (e.g., PSVT: R, MRT) rely on what I refer to as receptive skills: examining an object or design, mentally transforming it, and comparing it to given alternatives. But because work in many STEM disciplines also involves productive spatial skill such as drawing, I hypothesize that a productive measure of spatial skill may predict distinct aspects of spatial ability. This research investigates the relationship between traditional receptive Spatial Visualization (SV) assessments, such as …

Design And Validation Of A Low-Cost Wearable Electromyography (Emg) System For Monitoring Exercise-Induced Changes In Muscle Activity, Ingrid E. Halverson

Dissertations, Master's Theses and Master's Reports

Wearable technologies have expanded opportunities for monitoring athletic performance, but many existing systems remain costly and confined to laboratory or medical settings. This thesis presents the design, development, and evaluation of a low-cost, wearable EMG platform for monitoring neuromuscular activity during exercise. A wireless device incorporating a surface EMG sensor, an ESP32 microcontroller, and Wi-Fi transmission was developed to acquire muscle activation data. Signal processing techniques, including filtering, root-mean-square (RMS), mean frequency (MNF), and median frequency (MDF) analyses, were used to evaluate changes in muscle activation. Experimental testing demonstrated reliable wireless data acquisition and successful capture of physiological changes before …

Open Source Tools For Ecological Research, Alex P. Riebe

Dissertations, Master's Theses and Master's Reports

This thesis presents the development of an open source wireless sensor network for hibernacula manipulation with an emphasis on accessibility and reproducibility. It addresses the design of the electrical hardware, guidance on antennas and RF implementation, and design of an application-specific communication protocol, all with the explicit goal of enabling ecologists and other conservationists to be able to manufacture, deploy, operate, and maintain the system for their research. The resulting sensor network designed in this thesis is to control the temperature inside bat hibernacula during the winter to study the relationship between temperature and bat mortality rate due to White …

Using Automotive Lidar To Reduce The Energy Consumption Of An Ego Autonomous Vehicle, Logan P. Schexnaydre

Dissertations, Master's Theses and Master's Reports

There is significant potential to reduce the energy consumption of the transportation sector through autonomous vehicles. Prior work on autonomous vehicle energy efficiency focuses on the whole system or the control subsystem. Yet, the sensing and processing components, which have direct and indirect effects on net energy use, are less explored. This dissertation fills this gap by modeling and evaluating these effects for lidar sensors, which provide high-resolution spatial data at the cost of high power and processing demands. I apply lidar to the energy-saving tasks of automated vehicle following and road surface profiling. For automated vehicle following, I model …

High-Performance Circuit Manufacturing And Testing Exercises, Benjamin S. Keppers

Dissertations, Master's Theses and Master's Reports

An advanced demonstrator Printed Circuit Board (PCB) has been designed and implemented providing a framework for advancing students’ knowledge in hands-on PCB design and manufacturing process through industry recognized test coupons, stack ups, and transmission lines. Students are guided through several key aspects of design and simulation relating to manufacturing and qualifications. Manufacturing allows students to refine process development and analyze performance data with respect to qualification tests specified by Global Electronics Association standards. Results are then used to build a stackup model, and complete a design activity for calculating expected test results for a series of controlled impedance electrical …

Antenna-Based Sensors For Dielectric Characterization Of Materials, Hilary Scott Nkimbeng Cho

Dissertations, Master's Theses and Master's Reports

This research introduces antenna-based sensors for dielectric characterization aimed at overcoming the limitations of conventional microwave sensors. Although traditional microwave sensors are widely used for their noncontact operation, high sensitivity, and ability to penetrate various materials, they often face challenges such as large size and high-power consumption. To address these issues, antenna-based sensors are explored for their compactness, ease of fabrication, and flexible design adaptability across diverse sensing applications. An in-depth analysis of multiple antenna sensor configurations is conducted, followed by the design and development of high-performance sensing structures. A saw-tooth slot antenna sensor is developed for highly sensitive liquid …

Robust State Estimation And Scene Understanding For Autonomous Ground Vehicles In Challenging Environments, Nader J. Abu-Alrub

Dissertations, Master's Theses and Master's Reports

Autonomous ground vehicles require reliable state estimation and scene understanding to operate safely in challenging environments. Poor illumination, adverse weather, degraded visibility, snow-covered roads, and sensor noise can reduce the reliability of conventional localization and perception pipelines. Addressing these challenges requires sensing and algorithmic strategies that exploit the complementary strengths of different modalities. Radar is particularly attractive because of its resilience to lighting and weather variations, while inertial, camera, and lidar measurements provide additional motion, appearance, and geometric information. This dissertation investigates compact radar-based and sensor-fusion approaches for improving autonomous ground-vehicle state estimation and scene understanding under degraded sensing conditions. …

Coupled Shrinking Core And Bubble Dynamics Model For Enhancement Of Metal-Water Reactions With Acoustic Cavitation, Troy Metz

Dissertations, Master's Theses and Master's Reports

Hydrogen is a valuable fuel. Hydrogen can be produced in several ways including thermochemical cycles, electrolysis, and metal-water reactions. Thermochemical cycles typically use high temperatures, often with corrosive species. Electrolysis requires high purity water. Metal-water reactions do not have these drawbacks. Activators such as lithium and gallium are often used to enhance metal-water reactions. However, these activators add to the complexity of metal-water reactions and may not work for all metals. A novel method to improve metal-water reactions is cavitation. During bubble collapse, shock waves and microjets are produced that can cause surface erosion. The objective of this work is …

Design And Experimental Evaluation Of A Custom Vision-Guided Approach To 2d Part Localization For Industrial Robots, Faisal Ali

Dissertations, Master's Theses and Master's Reports

Vision-guided robots offer a clear advantage over teach-pendant programming for battery handling, where modern packs hold thousands of cells and teaching each position by hand does not scale. Commercial vision systems address this need, but their calibration, detection, and coordinate-conversion stages are closed to the user, making it hard to incorporate newer learning-based methods. This work presents a modular, custom-built vision-guided system using an Orbbec Gemini 435Le eye-in-hand camera, an NVIDIA Jetson Orin Nano, an Allen-Bradley Micro850 PLC, and a FANUC LR Mate 200iC, communicating over Modbus TCP and EtherNet/IP. A per-hole classification model resolves each known hole into a …

Climate Change Impacts On Hydrology In The Upper James Watershed, Imiya Mudiyanselage Chathuranika, Dalya Ismael

Engineering Technology Faculty Publications

Hydrological modeling of the Upper James Watershed (UJW), Virginia, is critical for predicting water availability, flood management, agriculture, ecosystem protection, and hydropower production under increasing climate change. The Hydrologic Engineering Center-Hydrologic Modeling System (HEC-HMS) is applied to evaluate climate change impacts on key hydrological components within the watershed. Future climate conditions were assessed for the near (NF: 2026-2050), mid (MF: 2051-2075), and far (FF: 2076-2100) periods using three Global Climate Models (GCMs) under Shared Socioeconomic Pathways SSP 2-4.5 and SSP 5-8.5. Climate data were bias-corrected using the Linear Scaling Method (LSM) and used to drive the HEC-HMS model. Results project …

Identifying Industry-Preferred Automation Software In Engineering: An Indeed-Based Analysis To Inform Engineering Technology Curriculum Design, Triet Minh Phan, Collins Okafor, Winifred Okafor, Devang Mehta, Mohsen Souissi, Jenora Waterman, Connie Mayberry, Misty Thomas, Orlando Ayala, Angie Price, Maurizio Manzo

Engineering Technology Faculty Publications

In the evolving field of automation engineering, staying aligned with industry software demands is critical to preparing graduates for the modern workforce. This study investigates the prevalence of leading industrial automation platforms—Rockwell / Allen-Bradley (RSLogix / Studio 5000), Siemens (TIA Portal / Step 7), and Schneider Electric (EcoStruxure / Unity Pro)—across job postings collected from Indeed using the keyword "automation engineering." The research compiles a structured dataset of job postings with seven fields: ID, Job Title, Organization, Rockwell / Allen-Bradley, Siemens, Schneider Electric, and Posting URL. Each entry is manually coded to indicate whether the listed software platforms are mentioned, …