Computer Sciences Commons^™

Multi-Fidelity Machine Learning Modeling For Aerodynamic Response Prediction Of Aerospace Vehicles, Ethan S. Jackman

Theses and Dissertations

Hypersonic vehicle design requires understanding complex aerodynamic phenomena across the full flight regime. This study presents a novel MF surrogate modeling methodology that enables the prediction the full field response across a vehicle’s surface. A Space-Filling Curve (SFC) is used to convert unstructured data into 1D vectors. The a Convolutional Autoencoder is used with transfer learning to reduce the dimensionality of the data. An Emulator-Embedded Neural Network (E2NN) combines multi-fidelity data for fast, accurate predictions. A benchmark analytical example and hypersonic application are used to evaluate the methodology. Using various numbers of samples and sampling strategies it is found that …

Evaluating Adjustment And Proficiency Disparities In Virtual Reality, Mohammad Jahed Murad Sunny

Theses and Dissertations

The rapid integration of VR in various application domains necessitates a deeper understanding of how levels of user experience impact user performance and task efficiency. This study investigates the relationship between experience with VR, expertise in 3d computer gaming, and physiological skills across multiple performance metrics, such as task-completion time, task load, accuracy, manipulation speed, and related spatial requirements. In a comprehensive analysis of multiple levels of VR experience and 3d computer-game expertise, we identified key trends that indicate increased experience in both domains significantly enhances task efficiency while at the same time reduces perceived workload and improves task accuracy. …

Unboxing The Black Box: Graph-Based Interpretability In Transformer Models, Ramak Nassiri

Theses and Dissertations

This thesis introduces a novel interpretability framework for transformer encoder models by hypothesizing that their internal embedding updates define a state transition system. We propose that transformers implicitly learn token-to-token influence dynamics, which can be analyzed using graph-theoretic methods. To validate this, we construct transition graphs from embedding changes and rank token importance using the PageRank algorithm. We develop two transformer models from scratch: a self-supervised model that incorporates serotype tokens to learn contextualized embeddings, and a supervised model initialized with these embeddings. Cosine similarity analysis of their token influence patterns reveals strong structural alignment, with values exceeding 93%. This …

Autonomous Generation Of Ids Rules From Threat Intelligence, Azim Bazarov

Theses and Dissertations

Signature-based Intrusion Detection Systems (IDS) detect malicious activities by matching network or host activity against predefined rules. These rules are derived from Cyber Threat Intelligence (CTI), which includes attack signatures and behavioral patterns obtained through automated tools and manual threat analysis, such as sandboxing. The CTI is then transformed into actionable rules for the IDS engine, enabling real-time detection and prevention of threats. The constant evolution of cyber threats necessitates frequent rule updates, which delay deployment time and weaken overall security readiness. Recent advancements in autonomous agentic systems powered by Large Language Models (LLMs) offer the potential for automatic IDS …

Topnet R1: A Multi-Stage Ai Framework For Topic Discovery In Scientific Abstracts, Md Elias Hossain

Theses and Dissertations

Scientific abstracts are rich sources of knowledge, yet extracting meaningful topics remains challenging due to limitations in existing topic modeling techniques. Traditional methods often struggle with interpretability, scalability, and contextual understanding. To overcome these issues, we introduce TopNet R1, a multi-stage ensemble framework that integrates traditional topic models with contextual embeddings from Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer 4 (GPT-4) large language models (LLMs). Top- Net R1 operates in three phases: (1) topic generation using Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), Latent Semantic Analysis (LSA), and Hierarchical Dirichlet Process (HDP); (2) LLM-assisted pattern recognition …

Augmenting Healthcare Communication: Context-Aware Ai Frameworks For Clinical Decision Support And Automated Summarization, Subash Neupane

Theses and Dissertations

Healthcare communication is plagued by fragmented medical knowledge, patient misunderstanding of care plans, and clinician burnout from documentation burdens. These inefficiencies cost the U.S. healthcare system over $300 billion annually due to preventable nonadherence and administrative waste [47, 19]. While Artificial Intelligence (AI) technology like Large Language Models (LLMs) offer potential solutions, existing systems fail to deliver personalized, context-aware guidance or automate documentation without sacrificing accuracy. This dissertation addresses these gaps through three novel context-aware AI frameworks such as MedInsight, ClinicSum, and ClinicDuo. MedInsight leverages a multi-source context augmentation approach to synthesize patient centric medical responses by integrating Electronic Health …

Extreme Artifacts Removal With Curriculum Learning, Sushant Gautam

Theses and Dissertations

Restoring severely blurred images remains a significant challenge in computer vision, impacting applications in autonomous driving, medical imaging, and photography. This thesis introduces a novel training strategy based on curriculum learning to improve the robustness of deep learning models for extreme image deblurring. Unlike conventional approaches that train on only low to moderate blur levels, this method progressively increases the difficulty by introducing images with higher blur severity over time, allowing the model to adapt incrementally. Additionally, perceptual loss and hinge loss were integrated during training to enhance fine detail restoration and improve training stability. Various curriculum learning strategies were …

Estimating Reliability Of Electric Vehicle Charging Ecosystem Using Principle Of Maximum Entropy, Himanshu Tripathi

Theses and Dissertations

This thesis addresses the challenge of estimating electric vehicle (EV) charging system reliability against unpredictable threats like cyberattacks and extreme weather, where traditional methods fail. We utilize the Principle of Maximum Entropy (PME), a statistical tool that provides unbiased risk estimates using limited information. Applied to the EV charging ecosystem, our case study shows how PME models stress factors to predict failures and optimize maintenance. This approach extends beyond EVs to other complex systems with scarce data, such as smart grids or healthcare devices. By linking uncertainty directly to reliability, PME offers a universal method to improve decision-making under unpredictable …

Low-Cost Monitoring And Fingerprinting Of High-Powered Electric Systems, Kwabena Buamono Aboagye-Otchere

Theses and Dissertations

Electric motors are vital to industry, transport, and energy, yet their maintenance challenges persist. While traditional reactive maintenance leads to costly downtime and safety risks, predictive maintenance, especially through IoT and machine learning offers early fault detection and operational efficiency. However, this shift introduces security concerns due to unintended magnetic emissions from motors. These emissions, though useful for non-intrusive monitoring, can be exploited to eavesdrop on sensitive industrial processes. This dissertation explores the dual nature of magnetic emissions: their value in motor diagnostics and their potential as a security vulnerability. It demonstrates how emissions can identify motors, monitor health, and …

Advancing Real-World Implementation Of The Well Optimized Linear Finder (Wolf) High-Speed Atmospheric Turbulence Compensation Method, Timothy Evan Coon

Theses and Dissertations

This dissertation advances the real-world implementation of the Well Optimized Linear Finder (WOLF) method for high-speed Atmospheric Turbulence Compensation (ATC). Atmospheric turbulence introduces phase aberrations into optical wavefronts and degrades image quality in terrestrial imaging systems. Traditional phase diversity methods are computationally intensive and poorly suited to real-time operation. The WOLF method addresses these limitations through a novel, point-wise formulation of the optical transfer function (OTF) as a structured autocorrelation of the generalized pupil function (GPF). This formulation enables the estimation of phase aberrations at individual spatial coordinates with distributed computational complexity.

The research begins by developing a MATLAB-based simulation …

Secure Frameworks For User Motion Data In Virtual Reality, Jayasri Sai Nikitha Guthula

Theses and Dissertations

Virtual Reality is an innovative technology transforming industries such as gaming, healthcare, and remote collaboration. The increasing deployment of these systems results in the continuous collection of telemetry data, including motion patterns, hand gestures, and spatial interactions. This data is valuable for enhancing user experiences and optimizing system performance. However, it also introduces significant privacy risks. Unlike traditional digital footprints, motion data captures fine-grained physical behaviors that can be linked to individual users, making anonymization ineffective in preventing re-identification.This research introduces secure frameworks for user motion data in virtual reality, each proposed framework addressing privacy preservation from a different angle. …

Causal Neuro-Symbolic Artificial Intelligence: Synergy Between Neuro-Symbolic And Causal Artificial Intelligence, Utkarshani Jaimini

Theses and Dissertations

Understanding and reasoning about cause and effect is innate to human cognition. In everyday life, humans continuously engage in causal reasoning and hypothetical retrospection to make decisions, plan actions, and interpret events. This cognitive ability allows us to ask questions such as: “What caused this situation?”, “What will happen if I take this action?”, or “What would have happened had I chosen differently?” This intuitive capacity to form mental models of the world, infer causal relationships, and reason about alternative scenarios, particularly counterfactuals, is central to our intelligence and adaptability. In contrast, current machine learning (ML) and artificial intelligence (AI) …

Process-Grounded Knowledge-Infused Learning And Decision Making, Kaushik Roy

Theses and Dissertations

This dissertation introduces process-grounded knowledge-infused learning and reasoning, a novel framework for integrating domain-expertise-based process knowledge into the learning and reasoning mechanisms of artificial intelligence systems. This approach is designed to produce controlled, transparent, and reliable predictions in critical tasks such as medical diagnosis and recommendation. By focusing on the case study of mental illness diagnosis and recommendation—where decision-making must be grounded in processes such as disorder-specific diagnostic criteria—this work demonstrates methods to embed structured decision-making directly into the system architecture during both training and inference. This integration facilitates end-to-end training and reasoning while ensuring that outputs strictly adhere to …

A Neuro-Symbolic Ai Approach To Scene Understanding In Autonomous Systems, Ruwan Tharanga Wickramarachchige Don

Theses and Dissertations

Effectively understanding scenes requires a unified representation of scene data and background knowledge. A neuro-symbolic AI approach to scene understanding leverages such a unified representation to enable advanced expression, inference, and labeling of scenes, improving the perception of autonomous systems.

Scene understanding remains a central challenge in the machine perception of autonomous systems. It requires the integration of multiple sources of information, background knowledge, and heterogeneous sensor data to perceive, interpret, and reason about both physical and semantic aspects of dynamic environments. Current approaches to scene understanding primarily rely on computer vision and deep learning models that operate directly on …

An Efficient Detection And Deep Clustering Based Pipeline For Reliable Rodent Ultrasonic Vocalization Analysis, Sabah S. Anis

Theses and Dissertations

Ultrasonic vocalizations (USVs) are critical for understanding rodents' emotional states and social behaviors. However, manual analysis of USVs is time-consuming, subjective, and prone to errors. This thesis presents an automated pipeline that addresses these challenges by performing efficient USV detection and clustering. The proposed approach significantly reduces the time and effort needed to analyze USV data while improving accuracy and reproducibility.

To address this gap, we introduce ContourUSV, a five-step pipeline for USV detection. First, it begins with generating spectrograms from audio recordings, which are then pre-processed to enhance the contrast between USVs and background noise. Key steps include median …

Hardware Accelerated Simulation Of Buck Converters Using Physics-Informed Neural Networks, James Clayton Crews

Theses and Dissertations

Physics-informed neural networks (PINNs) are an emerging machine learning method for learning the behavior of physical systems described by governing differential equations. Dc-dc power-electronic converters are used in a variety of industry applications such as motor drives or power supplies where real-time simulation is critical for control and safety. This thesis investigates physics-informed machine learning as an approach to develop a real-time digital twin for dc-dc power converters. Traditional numerical integration methods are used to approximate discretized behavior, and the results are compared with a trained PINN model. Modern ML frameworks (such as PyTorch and TensorFlow/Keras) are used to quickly …

Physics Oriented Deep Learning For Material Prediction And Generation, Nihang Fu

Theses and Dissertations

The discovery of new materials is critical to advancing various industries, but traditional experimental methods for materials discovery remain slow and resource-intensive. Recent advances in machine learning (ML), particularly deep learning (DL), have greatly improved and accelerated two main aspects of modern computational material discovery: material design (e.g., material generation) and material screening (e.g., property prediction). However, a key challenge remains: standard ML models often struggle to perform domain-specific tasks effectively. Incorporating domain-specific knowledge, specifically the underlying physics of materials, into ML/DL models is key to improving the accuracy and reliability of material generation and prediction models.

This dissertation discusses …

Elevating Next Generation Wireless Devices Towards Contactless Sensing For Healthcare Applications, Aakriti Adhikari

Theses and Dissertations

There is an increasing interest in technologies that can understand and perceive at-home human activities to provide personalized healthcare monitoring, aimed at early detection of disease markers and assisting physicians in making clinical decisions. Existing approaches, such as wearables, require users to wear sensors that can be cumbersome and cause discomfort. Vision based solutions, such as optical cameras, IRs, LiDARs, etc., can be used to design contactless at-home monitoring systems. However, these systems are limited by poor lighting and occlusion, and they are privacy-invasive. Fortunately, high-frequency millimeter-wave wireless devices provide an effective alternative to the existing systems to enable fine-grained …

Multi-Task Deep Learning Approach For Segmenting And Classifying Competitive Swimming Activities Using A Single Imu, Mark Shperkin

Theses and Dissertations

Competitive swimming performance analysis has traditionally relied on manual video review and multi-sensor systems, both of which are resource-intensive and impractical for everyday training use. This study investigates whether a single wrist-worn inertial measurement unit (IMU) can be used to automatically segment and classify swimming activities with high accuracy. We propose a multi-task deep learning pipeline based on the MTHARS (Multi-Task Human Activity Recognition and Segmentation) architecture introduced by Duan et al. to perform stroke classification, lap segmentation, stroke count estimation, and underwater kick count estimation. Data were collected from eleven collegiate-level swimmers wearing left-wrist-mounted IMUs, each performing five 100-yard …

Explainable Process Recommendation Through Multi-Contextual Grounding Of Dynamic Multimodal Process Knowledge Graphs, Revathy Venkataramanan

Theses and Dissertations

Can I eat this food or not? Is this food suitable for diabetes and why? Which AI pipeline is best suited for a given task and dataset? How should an end-to-end pipeline be constructed? These questions differ from factual question-answering tasks. Recipes and AI pipelines are processes consisting of several entities interacting with each other. A recipe consists of ingredients, cooking methods, and their interactions, while an AI pipeline includes datasets, preprocessing techniques, models, hyperparameters, tasks, and results. Each entity must be analyzed individually, and collective inferencing is performed to derive the final decision. This decision-making process, known as compositional …

Martingale Methods For Structural Change Detection And Feature Attribution In Dynamic Networks, Izhar Ali

Theses and Dissertations

Dynamic networks undergo structural changes when their generative process shifts at a change-point. We need to detect this change-point with minimal delay while identifying its underlying causes. This is an optimization problem of minimizing the expected detection delay while controlling the false alarm probability below a threshold---leading to three critical challenges: non-parametric detection without distributional assumptions, exact feature attribution, and early detection with rigorous false alarm control. We construct additive martingale statistics from multiple graph features using conformal prediction, providing false alarm guarantees via Ville's inequality. Our key theoretical contribution proves the Martingale-Shapley equivalence: each feature's martingale value equals its …

Hierarchy Viz: A Visual Analytics Framework For Visualizing Hierarchical Data Using Machine Learning, Vinay Kumar Uppalapati

Theses and Dissertations

Automated visualization systems aim to generate visualizations directly from raw data with minimal user inputs. However, while existing systems focus on data visualizations mainly using line charts and scatter plots to explore the data patterns, they struggle with hierarchical data representation where data relationship is essential. Hierarchical visualization, crucial for understanding multi-level relationships, typically requires users to manually define hierarchies and have expertise in visualization tools to create meaningful representations. This makes the process complex, time-consuming, and reliant on domain knowledge. To address this, we propose HierarchyViz, an automated system that detects multiple hierarchies in raw datasets and generates intuitive …

Deep Neural Networks For Particle Identification In Simulated Proton-Proton Collisions At Lhc And Rhic, Omar Mazhar Khalaf

Theses and Dissertations

Particle identification is an essential part of experimental high-energy physics, which allows the study of the most fundamental constituents of matter. This thesis explores the use of deep neural networks for identifying particles in simulated proton-proton collisions at the Large Hadron Collider (LHC) and the Relativistic Heavy Ion Collider (RHIC). The deep neural networks were trained on LHC datasets which have various momentum ranges including regions of high transverse momentum above 3 GeV/c. The key findings of thesis include achieving an accuracy of 99.99%, 98.3%, and 90.14% for 3-5 pt, 5-7 pt and above 7 pt regions respectively for the …

Efficient Signal Synthesis For Data Augmentation Using Generative Ai, Yagna Veera Narayan Kaasaragadda

Theses and Dissertations

Modern signal processing AI applications face increasing demands for diverse training data while operating under computational constraints. State-of-the-art generative models, though effective, often require prohibitive resources, limiting their deployment in real-time or embedded systems. This thesis proposes a computationally efficient framework for synthetic signal generation using a two-stage architecture that combines a Vector Quantized Variational Autoencoder (VQ-VAE) with either a decoder-only transformer or a discrete diffusion model. The VQ-VAE encodes high-dimensional signals into discrete latent tokens, significantly reducing model complexity while enabling symbolic sequence modeling. These discrete representations are then modeled using transformer-based autoregressive models or Score Entropy Discrete Diffusion …

From Lists To Infinite Scroll: A Comparative Analysis Of Youtube’S Two Recommendation Algorithms, Selimhan Dagtas

Theses and Dissertations

As social media platforms increasingly dominate information consumption, the role of recommendation algorithms in determining user experience has grown both in complexity and impact. This thesis investigates the behavioral patterns and algorithmic preferences embedded within YouTube’s recommendation systems, comparing long- form videos with the rapidly growing category of short-form content, YouTube Shorts. Through a combination of automated data collection, engagement metric analysis, emotional sentiment detection, and toxicity assessment, this study analyzes the evolution of content over successive recommendation depths. Using a controlled digital environment, the research explores how content recommendations change in response to user behavior, including varying watch times …

Contract Quality Feature Extraction Using Llm, Aaron C. Washington

Theses and Dissertations

This study explored the potential insights generated from linguistic complexity measurements and large language model (LLM) based assessments on the quality of contract documents. By combining structured True/False prompts with log-probability analysis and ambiguity scoring, the study introduced novel contract-quality assessment methods. Results support a feature-driven approach to contract evaluation, one that offers automated, scalable insights for triaging risk and improving drafting practices. These assessment methods contribute to the growing field of legal natural language processing by offering modular tools for effective contract analysis.

Blockchain-Enabled Master Data Management, Shakhawat Hossain

Theses and Dissertations

Master Data Management (MDM) is essential for maintaining data quality, accuracy, consistency, and governance within organizations. However, traditional centralized MDM systems continue to face challenges related to data integrity, security, and scalability. This research presents a blockchain-enabled MDM framework designed to overcome these limitations by leveraging blockchain’s decentralized, immutable, and secure architecture. The study aims to identify and address the shortcomings of conventional MDM practices, examine the applicability of blockchain technology in enhancing these systems, and develop a functional prototype to validate the proposed model. The framework incorporates decentralized review mechanisms that improve auditability and ensure trusted data verification by …

Cyber Security Threat Recognition And Preparedness Of Undergraduate Students, Litany Hope Lineberry

Theses and Dissertations

Cybersecurity awareness and preparedness are critical competencies for individuals across academic disciplines and professional sectors. However, undergraduate students often lack sufficient knowledge and skills to recognize and mitigate cybersecurity threats. This dissertation examines cybersecurity threat recognition and preparedness among undergraduate students through a three-phase research approach. Study 1 explores faculty perspectives on students' cybersecurity awareness, identifying gaps in knowledge and preparedness across various fields of study. Study 2 investigates industry professionals' perceptions of new hires’ cybersecurity readiness, assessing the alignment between academic training and industry expectations. Study 3 evaluates the effectiveness of an online intervention designed to enhance students' cybersecurity …

Ai Enabled Autonomic, Safe, And Interactive Intrusion Response System, Damodar Panigrahi

Theses and Dissertations

The exponential rise in internet usage has precipitated a corresponding surge in cyber threats, underscoring the urgent need for advanced cybersecurity solutions. While traditional intrusion detection systems (IDS) can identify these threats, their inability to self-recover leaves systems vulnerable. Intrusion response systems (IRS) have been developed to address this, aiming to auto- matically restore systems to their desired state post-security breach. However, current IRSs often necessitate manual intervention and may not be su!ciently robust against sophisticated threats. To overcome these limitations, we propose an AI-powered Autonomic, Safe, and Interactive Intrusion Response System called ‘Intrusion Response System Digital Assistant (IRSDA)’. IRSDA …

Synthetic Data Augmentation For Retinoblastoma Using Diffusion, Andrew Thompson

Theses and Dissertations

Many AI models rely on large and high quality datasets for optimal training. In certain cases, data can be difficult or expensive to obtain, making training difficult. Rare medical conditions are one of these cases. Datasets for retinoblastoma are severely lacking in quantity. Diffusion has been used to create synthetic data in the industrial, medical, and financial domains. By applying the latest Diffusion methods to retinoblastoma, this work seeks to improve predictive model performance on identifying retinoblastoma.