Engineering Commons^™

Enhancing Lane Detection In Autonomous Vehicles Using Data Augmentation For Adverse Environmental Conditions, Rutvikkumar Dave

Electronic Theses and Dissertations

To make sure that self-driving and connected automobile technologies are safe and work well, it’s really important that they can correctly identify lanes. But lane detection Algorithms typically have a hard time working well when the weather is bad, such when it rains, fogs, or goes too fast. The circumstances cause visual distortions that make existing computer vision systems less reliable, which makes it harder requires autonomous navigation systems to work well. This paper introduces a comprehensive lane detection system that integrates synthetic Weather-informed data augmentation combined with a Weather-aware Temporal Lane Detection Network (WTLDNet) to make it easier for …

Efficient Intrusion Detection For Iomt: Integrating Machine Learning, Feature Selection, And Fuzzy Logic, Ghaida Mansour Balhareth

Electronic Theses and Dissertations

The internet of medical things (IoMT) has transformed healthcare by enabling real-time patient monitoring, remote diagnoses, and effective data exchange among connected medical devices and clinical systems. The increasing reliance on interconnected medical equipment has also intensified cybersecurity risks, as resource-constrained devices and wireless communication channels are vulnerable to attacks such as man-in-the-middle, spoofing, data injection, and ransomware. Intrusion Detection Systems (IDSs) play a critical role in mitigating these threats; however, traditional IDS approaches often struggle with high-dimensional IoMT data, class imbalance, and uncertainty in traffic patterns, which can increase false alarms and reduce reliability in safety-critical environments. This dissertation …

Acoustic Response Of The Cnt-Reinforced Multilayered Acoustic Foam Composites (Mafc), Trey Brauch

Electronic Theses and Dissertations

Acoustic metamaterials are engineered materials designed to control and manipulate sound propagation. Many such systems incorporate acoustic foams due to their porous structure, low density, and high specific surface area, which promotes efficient sound absorption. However, a major limitation of conventional acoustic foams -particularly open-cell varieties- is their lack of waterproofing, rendering them unsuitable for underwater or moisture-prone environments. To address this limitation, a multilayered acoustic foam composite (MAFC) was developed as a lightweight, waterproof structure with enhanced sound absorption performance. The MAFC consists of five layers: the first and fifth layers are aluminum foam, providing structural integrity; the second …

Predictive Analytics In Oncology And Ophthalmology: Machine Learning Applications For Diabetic Retinopathy And Breast Cancer, Ali Abidalkareem

Electronic Theses and Dissertations

The convergence of artificial intelligence and healthcare represents one of the most transformative developments in modern medicine, with deep learning technologies emerging as powerful tools for addressing complex diagnostic challenges. This dissertation develops and validates machine learning frameworks that address critical challenges in medical diagnosis through innovative approaches to data augmentation, feature learning, and classification, focusing on two fundamental problems: Diabetic Retinopathy (DR) severity classification using multi-model convolutional neural networks (CNNs), and breast cancer stage identification using microRNA (miRNA) gene expression biomarkers. For diabetic retinopathy classification, this work proposes an ensemble deep learning framework that integrates Diffusion-based data augmentation for …

On The Drainage Vortices Of Liquid In A Container With Two Outlets, Radivoje Stankovic

Electronic Theses and Dissertations

Vortices that form over multiple drainage ports may exhibit a distinct, periodic alternating behavior, whereby the air core moves periodically between different drainage ports. The physical processes which govern this behavior have not yet been explained, despite the widespread and thorough attempts to describe the flow of water through single or multiple outlets. Early experiments on the alternating behavior of this vortex resulted in a nondimensional relation between the alternating frequency and water height and container geometry with an R2 = 0.91. Subsequent 2D PIV measurements of the flow were performed at different laser heights of 25 mm and 128 …

Graph-Based And Uncertainty-Aware Machine Learning For Academic Performance Prediction, Anca Olivia Muresan

Electronic Theses and Dissertations

Early identification of students at risk of academic failure is essential for timely pedagogical interventions and reducing dropout rates. While Artificial Intelligence (AI) has significantly advanced predictive modeling in education, two primary challenges persist: effectively modeling the complex, evolving relationships within heterogeneous educational data, and ensuring the reliability of model outputs for high-stakes decision-making. This dissertation addresses these challenges by proposing a comprehensive framework for early and continuous student performance prediction applied to the Open University Learning Analytics (OULA) dataset. First, we introduce a Heterogeneous Graph Neural Network (HGNN) approach that utilizes metapath structures to capture latent interactions between diverse …

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 …

Towards Optimal And Resilient Ac/Dc Microgrids: Control Design, Analysis, And Implementation, Jun Zhang

Electronic Theses and Dissertations

Microgrids serve as a small-scale power grid for utilizing renewable energy to enhance energy reliability, sustainability, and resilience. As an autonomous system, an islanded microgrid can disconnect from the utility grid and operate independently by maintaining system voltage and frequency. However, this new feature introduces coordination problems among distributed generators (DGs), such as 1) how to make sure the voltage profile and current sharing in DC microgrid with different types of converters; 2) how to reduce the impact of cyberattack when the system coordination is performed based on communication, and 3) how to calculate the steady state under a droop …

A Study Of Lost Pla Investment Casting For A356 Aluminum In Resource Constrained Manufacturing Environments, Maverick Beckmann

Electronic Theses and Dissertations

Lost PLA investment casting offers a low tooling route for producing complex aluminum parts, but repeatability depends on material use, burnout behavior, geometric process limits, and dimensional response. This thesis evaluated Lost PLA casting as a resource efficient manufacturing method for complex A356 aluminum components in resource constrained settings through four linked objectives: metal reusability, burnout and PLA selection, process limitations, and feature based dimensional shrinkage. A metal mass balance was performed on six casting trials using salvaged A356. Ash residual behavior was studied through a single tray screening test of eight commercial filaments and three invested mold burnout trials …

A Taxonomy-Driven Modular Defense Against Non-Canonical Language In Vision-Language-Action Models, Viraj Samson

Electronic Theses and Dissertations

Vision-Language-Action (VLA) models have recently achieved strong performance across manipulation benchmarks, but these benchmarks rely on highly templated instructions on which the models are typically fine-tuned, leaving their behavior under realistic language-side perturbation unclear. It remains an open question whether the linguistic flexibility inherited from vision-language pretraining survives this fine-tuning, or whether the resulting policies become narrowly tuned to benchmark phrasing and brittle to the intent-preserving language variation that real users naturally produce. We address this gap with a systematic study of VLA robustness under non-canonical instructions, comprising three components: a structured taxonomy of intent-preserving variations spanning linguistic, orthographic, and …

Fast And Sustainable Video Anomaly Detection With Continual Learning, Preethi Amasa

Electronic Theses and Dissertations

Real-time video anomaly detection systems deployed in surveillance, healthcare, and industrial environments face continuous distribution shifts in lighting, viewpoint, and activity patterns. Existing models often experience performance degradation under these conditions and may suffer catastrophic forgetting when adapting to new environments. This thesis proposes RegiGrow, a parameter-efficient continual adaptation framework built on the Flashback retrieval pipeline. RegiGrow integrates Mixture-of-Experts Low-Rank Adaptation into a frozen ImageBind encoder, enabling sequential domain adaptation without modifying the pretrained backbone. A lightweight router maps visual regime features to a distribution over LoRA experts, each specializing in a distinct normal operating regime. The central contribution is …

Computational Fluid Dynamics Simulation Of In-Situ Plasma- Assisted Cold Spray, Lucas Degen

Electronic Theses and Dissertations

Cold spray is a solid-state form of additive manufacturing with high versatility and widespread applicability, especially in relation to metal coatings. Many applications exist within the fields of aerospace, defense and energy systems to obtain sustainable, temperature and corrosion resistant, robust coatings. High-strength alloys and refractory metals generally encounter challenges with regards to cold spray coating adhesion and overall deposition efficiency. Heat induced methods of post-processing or in-situ treatment have been explored to encourage particle softening in the cold spray plume, as well as coating recrystallization to enhance material properties. These approaches have primarily been limited to an experimental approach, …

Data-Driven Optimization Of Memory Effects And Critical Components In Cascading Failure Interaction Networks, Md Farhan Tanvir

Electronic Theses and Dissertations

Cascading failures are a major concern for modern power systems‚ where a small failure can cascade through the network to create a large blackout. Because such an event could have catastrophic economic and social costs it is important to understand cascading failures‚ how to model them‚ and the possibility of reducing them. In this thesis‚ we develop a data-driven framework based on actual utility outage data to model and reduce cascading failures. The proposed methodology is based on generation-dependent interaction models and in this study interaction matrices obtained from historical outage events are used to describe the interaction between generations. …

Computational Modeling Of Biophysical Transport: Respiratory Drug Delivery And Tissue-Level Physics, Md Tariqul Hossain

Electronic Theses and Dissertations

The nasopharynx, the upper part of the pharynx located at the back of the nose serves as a critical hotspot for initial respiratory infections via inhaled transmission, largely due to the presence of specific surface receptors that pathogens can exploit for cell invasion, combined with a relatively sparse local mucociliary substrate. To enhance the therapeutic efficacy against certain pathogens, such as the SARS and Influenza viruses, it is therefore essential to improve the targeted delivery of drugs to the nasopharynx. This study explores the use of intranasal sprays as a method for drug administration and models the transport of sprayed …

Numerical Investigation Of Injector Location And Equivalence Ratio In A Flame‐Holder Cavity Scramjet, Matthew Sorenson

Electronic Theses and Dissertations

This thesis presents a CFD-based parametric study of injector location and fuel rate in an ethylene-fueled flame-holder cavity scramjet using STAR-CCM+. Simulations are performed for three injector locations (x/D = 18, 36, and 54) and nine equivalence ratios spanning from ϕ = 0.2 to 1.0 in 0.1 increments. The study aims to determine how injector placement and fueling level alter scramjet performance across a broad operating sweep. The results show a clear regime change between ϕ = 0.2 and ϕ ≥ 0.3. At ϕ = 0.2, combustor behavior is weakly sensitive to injector location compared to the higher-fueling cases. For …

Bridging Language And Game Worlds: Semantic Representations And Text-Driven Terrain Generation For Procedural Content, Zhongyu Xie

Electronic Theses and Dissertations

Procedural Content Generation (PCG) systems produce vast quantities of game levels, terrain, and environments, but lack semantic interfaces: no shared vocabulary exists between natural language, designer intent, and the structured representations generators operate on. This thesis addresses the language-content grounding gap in PCG through two complementary studies spanning semantic analysis and semantic synthesis. The first study introduces a group-supervised contrastive learning framework for semantic representation of symbolic PCG maps under many-to-one semantics, where visually distinct maps may share the same design intent. The framework combines parameter-guided semantic grouping, LLM-based caption augmentation, and a multi-positive contrastive objective that aligns language with …

Scalable Carbon-Based Electrodes For Hole-Transport Layer-Free Perovskite Solar Cells., Sharmin Akter

Electronic Theses and Dissertations

Perovskite solar cells (PSCs) have rapidly reached certified single-junction efficiencies near 26%, but deployment is still limited by operational instability, scale-up challenges, and the cost and complexity of typical device stacks. This dissertation explores a simpler, scalable approach: HTL-free PSCs using low-cost, chemically robust carbon (e.g., carbon black) counter electrodes compatible with low-temperature, solution processing. This work demonstrates how carbon-ink formulation, scalable deposition (blade vs. slot-die), and work-function-tuning additives control film quality, interfacial energetics, and device performance. Carbon inks were developed for both coating methods by systematically varying carbon-to-binder ratio, polymer chemistry, and solvent system. Among the binders screened, ethyl …

Emerging Solid Electrolytes For Solid-State Sodium Batteries: Synthesis And Interface Study., Xiaolin Guo

Electronic Theses and Dissertations

Over the past decade, solid-state batteries have attracted significant attention as the next-generation energy storage technology due to their higher energy density and enhanced safety. Given the abundant sodium (Na) resources relative to lithium (Li), the development of sodium-based batteries has become increasingly compelling. Within a solid-state battery, the solid electrolytes (SEs) serve the dual function of (i) electronically insulating and physically separating the electrodes, and (ii) transporting ions between the anode and cathode. To meet these essential requirements, ideal SEs must process high ionic conductivity with negligible electronic conductivity, robust structural and chemical stability, a wide electrochemical window, and …

From 2d To 3d: Multi-Agent Reinforcement Learning For Spectrum-Constrained Urban Air Mobility., Qingyang Li

Electronic Theses and Dissertations

Advanced Air Mobility (AAM) and Urban Air Mobility (UAM) are accelerating a transformation of air transportation but face acute spectrum congestion in dense urban environments. Reliable Control and Non-Payload Communications (CNPC) must be maintained at all times to ensure safe operations, even as fleets of aerial vehicles (AVs) transport passengers and cargo between distributed vertiports. We first develop a 2D formulation that jointly optimizes discrete headings, velocities, and spectrum allocation to minimize total mission time while satisfying quality of service (QoS) and collision-avoidance constraints, and we demonstrate significant gains over non-learning and learning baselines. Building on this 2D framework, we …

Depth-Averaged Two-Dimensional Hydrodynamic Modeling In Headwater Channel And Floodplain Design., Jesse Dylan Robinson

Electronic Theses and Dissertations

In the channels and floodplains of inland waterways the hydrodynamic forces of floods destroy property and infrastructure, threaten lives, and damage aquatic habitat. Flood simulations using robust and efficient depth-averaged two-dimensional hydrodynamic models (2D models) can be interpreted to design effective solutions for areas vulnerable to damage. The reliable interpretation of 2D models for use in design is improved here through direct comparison of 2D model output to observed flood events at 6 headwater research sites. Instrumentation was used for model calibration and to define the surface hydrodynamics at sites with confined flows, wide and shallow flows, at vertical steps, …

Molecular Dynamics Simulations Of Biologically Relevant Interfaces: From Tear Film Lipid Layers To Rna Adsorption On Silica Surfaces., Mahbuba Khanom

Electronic Theses and Dissertations

Molecular dynamics (MD) simulation is an important tool in biochemical sciences for studying complex molecular processes and interfacial interactions at the molecular level. Biological interfaces play key roles in processes such as ocular lubrication and biomolecular adsorption. This dissertation studies interfacial phenomena involving two distinct yet conceptually related systems: the tear film lipid layer (TFLL) at the air–water interface at the surface of the human eye, and RNA adsorption on silica surfaces. These studies provide insight into how interfacial composition, structure, and environmental conditions affect larger-scale behavior. Atomistic MD simulations were used to model the TFLL. The TFLL is essential …

Integrating Due Process Into Large Language Models., Joshua Paul Johnson

Electronic Theses and Dissertations

This research investigates the ability of large language models (LLMs) to recognize due process issues. Due process is a legal concept focused on the protection of the individual during interactions with government when life, liberty, or property are being impacted. Due process presents both substantive and procedural aspects that are challenging to incorporate into generative artificial intelligence. Through assessing model performance, creating benchmarking techniques, retrieval-augmented generation (RAG), and fine-tuning, this work seeks to measure due process recognition performance and improve performance in identifying due process issues. The results of evaluating larger parameter LLMs such as from Google, Meta, and OpenAI …

Thermal Heterogeneity And Lithium Plating During Fast Charging Of Lithium-Ion Battery., Ayodeji Avis Adeniran

Electronic Theses and Dissertations

Presently, widespread adoption of electric vehicles (EVs) is hindered by challenges associated with XFC, including heat generation, lithium plating, and accelerated battery degradation. This dissertation addresses these barriers through two coordinated themes—lithium plating and thermal management—spanning four manuscripts that integrate operando diagnostics, physics-based simulation, and module-level design optimization. The first theme seeks a fundamental investigation into the dynamic interplay between temperature heterogeneity and lithium plating during fast charging, a phenomenon that poses significant limitations on the performance of graphite-based anodes. Firstly, a custom operando cell with a sapphire window was designed to enable synchronized MWIR thermography and optical imaging of …

Alkali-Silica Reactivity And Ionic Transport In Mortar With Hydrophobic Inclusions., Isaac Offei

Electronic Theses and Dissertations

Alkali-silica reaction (ASR) causes extensive damage to concrete infrastructure worldwide, with traditional mitigation strategies increasingly constrained by supplementary cementitious material (SCM) supply limitations. This dissertation investigates an innovative approach to ASR prevention through strategic application of hydrophobic materials to modify moisture and ionic transport pathways in cement mortars. The research employed a comprehensive three-objective experimental program using highly reactive aggregates and three hydrophobic materials: hexamethyldisilazane (HMDS)-treated fumed silica, silane-based emulsion, and silane-based crème. The first objective demonstrated the feasibility of hydrophobic aggregate surface modification, achieving 46% and 38% reductions in ASR expansion for washed and non-washed hydrophobic aggregates, respectively. Microstructural …

Detecting Non-Axisymmetric Instabilities In Fluid-Based Manufacturing Via Multi-View Tensor Analysis., Bidusi Khadka

Electronic Theses and Dissertations

Fluid-based manufacturing processes, such as inkjet printing and electrospinning, fabricate micro- and nano-scale structures with high precision, but are prone to complex fluid dynamics exhibiting axisymmetric and non-axisymmetric instabilities. Conventional monitoring often relies on single-camera inputs and symmetry assumptions, limiting the detection of three-dimensional anomalies like jet deflection. This study presents a novel multi-view streaming video-based anomaly detection framework to address this gap. The framework employs a modified Tensor Sequential Sampling (TSS) algorithm with edge-based sampling to capture geometric spatiotemporal features of each camera view using the videos obtained from an orthogonally positioned dual-camera setup. These features are fused with …

Strategic Enhancement Of Biofuel Production Using Bacillus Subtilis As A Model Organism: A Dual Approach Of Gene Essentiality Mapping And Optimization, Angela A. Zebede

Electronic Theses and Dissertations

With rising global demand for renewable energy, enhancing microbial platforms for biofuel production is vital. This study engineered Bacillus subtilis to improve resilience to solvent stress by targeting membrane lipid biosynthesis pathways essential for integrity. Growth curve analysis (OD₆₀₀) showed that phosphatidylserine (PS) and phosphatidylethanolamine (PE) knockout strains grew significantly slower than wild type (168), indicating the importance of these lipids under stress. Laurdan fluorescence spectroscopy was used to assess membrane properties. Generalized polarization (GP) analysis revealed a concentration-dependent reduction in membrane order upon 1%–2% 1-butanol exposure. GP values declined progressively from control to 2% treatment, reflecting increased membrane fluidity …

Mechanisms Of Correlated Neuronal Activity In The Globus Pallidus, Hamza Albawaliz

Electronic Theses and Dissertations

This thesis investigates the mechanisms of correlated neuronal activity in the globus pallidus externus (GPe), a key structure in the basal ganglia. Neuronal activity in the GPe is reportedly decorrelated in healthy subjects but can become highly correlated in Parkinson’s disease. However, high-density neuronal recordings in the GPe of healthy rats reveal a surprising degree of correlated activity. This raises the question of whether intrinsic properties or network connectivity alone can account for such patterns. To explore this, a computational model was developed in which GPe neurons are represented as coupled phase oscillators influenced by experimentally derived phase-response curves and …

Development Of A Non-Faradaic Impedimetric Biosensor Based On Reduced Graphene Oxide For The Detection Of Brain-Derived Neurotrophic Factor (Bdnf), Mariana N. Martins

Electronic Theses and Dissertations

Neurological disorders affect millions of people worldwide. In the case of Alzheimer’s disease (AD), the rising number of cases significantly increases global healthcare costs. Therefore, early detection of biomarkers at the onset of the disease is essential for early diagnosis. This study presents an electrochemical biosensor designed for the detection of Brain-Derived Neurotrophic Factor (BDNF) in human plasma, incorporating reduced graphene oxide (rGO) to enhance signal sensitivity. Dielectrophoresis (DEP) was employed to deposit rGO flakes on the electrode surface, improving conductivity and sensor performance. Electrochemical impedance spectroscopy (EIS) was used to monitor changes in impedance associated with BDNF binding events, …