Physical Sciences and Mathematics Commons^™

Scenarioxp: A Complete Scenario-Based Testing Framework For The Exploration And Exploitation Of Autonomous Vehicle Validation Scenarios, Quentin Goss

Doctoral Dissertations and Master's Theses

Today is an age of exciting emerging technology where cutting-edge research in autonomous vehicles (AVs) reduces the active human participation in driving and extends awareness beyond human limitations of perception and reaction, improving driving safety and quality of the user experience as a result. The ever-increasing complexity of these autonomous systems poses many challenges towards the validation and verification (V\&V) of these complex systems under time and resource constraints, as the use of artificial intelligence and also the intricacy of the operating environment means that these systems are also black-box and non-deterministic. Scenario-based V\&V testing of such systems, which involves …

Aiw26s: Machine Learning Of Structured Data, Moumita Saha

Paul English Applied Artificial Intelligence (AI) Institute Publications

This workshop introduces the fundamentals of machine learning for structured data, focusing on tabular datasets and real-world applications. Participants explore key concepts such as data types, data preprocessing, feature engineering, and supervised learning methods. The session covers commonly used models, including linear regression, logistic regression, decision trees, and neural networks, along with evaluation metrics such as RMSE, accuracy, and confusion matrices. By the end of the workshop, participants will have gained a practical understanding of how to build, interpret, and evaluate machine learning models for structured data.

From Attention To Reasoning: Beyond Accuracy In Multimodal Ai, Wayner Barrios

Dartmouth College Ph.D Dissertations

Multimodal large language models have achieved impressive performance on vision-language benchmarks by integrating visual encoders with large language models. Yet a critical gap persists between benchmark accuracy and genuine multimodal understanding: current evaluation frameworks assess performance by final answers alone, rewarding confident predictions while leaving systematic reasoning failures undetected.

This thesis addresses this gap through a unified framework that progresses from understanding to reasoning, using video as the most comprehensive multimodal testbed. Video inherently combines vision, audio, and language with temporal dynamics and massive token redundancy; techniques developed for video's comprehensive challenges transfer naturally to simpler multimodal tasks.

On understanding …

Development Of Deep Fused Neural Architecture For Ancient Tamil Palm-Leaf Manuscript Recognition, Hariharan P Mr

Theses and Dissertations

Digitizing Tamil palm-leaf manuscripts is important for education, communication, and the preservation of cultural heritage. The complex structure of the Tamil script, the wide range of handwriting styles, and the degradation seen in ancient Tamil palm-leaf manuscripts make these texts very difficult to read and understand. Digital Image Processing (DIP), document analysis techniques, and traditional Optical Character Recognition (OCR) are unable to handle noise, background interference, faded ink, and limited labelled data, motivating the need for robust, effective Deep Learning (DL)- based solutions.

As a prerequisite to understanding and designing effective recognition systems for ancient manuscripts, this thesis first examines …

Leveraging Machine Learning Techniques To Identify Catastrophic Outliers In Photometric Redshift Estimates, Jason Yoo

Honors Theses

Leveraging the unprecedented data volumes from modern astronomical surveys, this work addresses the critical challenge of identifying catastrophic outliers (COs) in photometric redshift (photo-z) estimates. Reliable redshift estimation is essential for precision cosmology, yet COs (galaxies with severely erroneous photo-z) can introduce significant systematic bias. We develop and evaluate two machine learning approaches for robust CO identification: a multilayer perceptron (MLP) utilizing photo-z point estimates and probability distributions, and a convolutional neural network (CNN) leveraging raw 5-band photometric images. Using datasets emulating LSST conditions, we demonstrate that the MLP model achieves high accuracy and stability across redshift bins, correctly identifying …

Spatial Temporal Modeling Of Infectious Disease Patterns In Texas, Robert E. Lashbrook

Earth & Environmental Sciences Theses

The Texas Department of State Health Services monitors numerous notifiable conditions statewide, including Campylobacter, Salmonella, Shiga toxin-producing Escherichia coli (STEC), Rabies, and West Nile virus (WNV). Given the substantial health, economic, and public health burden associated with these conditions, improving prediction is an important step toward reducing their overall impact. This study evaluated whether external demographic, social, climate, and environmental data could improve prediction of county-year disease activity across Texas. County level data was analyzed using supervised machine learning models, including linear regression, ridge regression, multilayer perceptron, random forest, XGBoost, as well as K-means clustering to identify broader …

Learning Without Training, Ryan O'Dowd

CGU Theses & Dissertations

We live in an era of big data. Whether it be algorithms designed to help corporations efficiently allocate the use of their resources, systems to block or intercept transmissions in times of war, or the helpful pocket companion known as ChatGPT, machine learning is at the heart of managing the real-world problems associated with massive data. With the success of neural networks on such large-scale problems, more research in machine learning is being conducted now than ever before. This dissertation focuses on three different projects rooted in mathematical theory for machine learning applications. Common themes throughout involve the synthesis of …

Blens: Biomedical Literature Extraction And Scoring System, Tyler J. Simone

Honors Theses and Capstones

Systematic reviews and meta-analyses represent the gold standard for evidence synthesis in healthcare, yet their manual execution remains labor-intensive, time-consuming, and vulnerable to human bias. With the exponential growth of biomedical literature, traditional literature screening and analysis has become increasingly unstable and noncomprehensive. This thesis presents the development and validation of an automate literature gathering and review system that integrates multiple scientific databases through a unified desktop application. The platform combines APIs from PubMed (NCBI Entrez), ClinicalTrials.gov, bioRxiv and medRxiv to enable simultaneous, standardized searching across peerreviewed and preprint sources. Built in Python with a PySide6 graphical interface, this standalone …

Tree-Based Graph Neura Networks For Natural Language Inference: From Structure-Only To Hybrid Architectures, Jason P. Lunder

EWU Masters Thesis Collection

Large transformer models achieve strong performance on natural language understanding tasks but require hundreds of millions of parameters and extensive pretraining. This thesis investigates whether graph neural networks operating on dependency parse trees can provide more parameter-efficient sentence representations for natural language inference, evaluated on two NLI tasks: entailment classification and semantic textual similarity.

Tree Matching Networks (TMN) adapt Graph Matching Networks to linguistic dependency trees with rich node and edge features, evaluated against a BERT baseline at matched parameter counts on identical training data. Tree Transformer Networks (TTN) extend TMN with transformer-based aggregation and tree-aware positional encodings, with component …

Network-Aware Airline-Specific Flight Delay Prediction Using Tree-Based Ensemble Models, Mary Dufie Afrane

College of Graduate Studies: Theses & Dissertations

Flight delays pose persistent challenges to the efficiency and reliability of air transportation systems, affecting airlines, airports, regulators, and passengers alike. As traffic demand grows and operational environments become increasingly interconnected, accurately predicting both departure and arrival delays has become crucial for effective planning and mitigation. This study presents a network-aware, airline-specific framework for predicting flight delays in U.S. domestic air transportation systems using tree-based ensemble machine learning models. A large-scale dataset of 1.98 million flights, enriched with weather information, is used to develop predictive models for both departure and arrival delays. To capture the structural and operational complexity of …

Drone Authentication System Using Radio Frequency Fingerprinting, Jamila Muhsen Alnuaimi, Shamma Ghaleb Almansoori, Noura Ahmed Alrumeithi, Richard Ikuesan

All Works

The widespread integration of unmanned aerial vehicles (UAVs) across domains such as logistics, surveillance, and emergency response has introduced critical security challenges, particularly unauthorized access, identity spoofing, and drone cloning. Traditional software-based authentication methods, including GPS tracking and encryption, have proven inadequate against advanced cyber-physical threats. This paper proposes a secure and automated drone authentication framework based on Radio Frequency (RF) fingerprinting, leveraging intrinsic hardware-level signal imperfections to generate unique and unclonable drone identities. Using Random Forest classifiers, the system captures, preprocesses, and analyses RF features to distinguish between authorized and unauthorized UAVs. Validation with real-world RF datasets demonstrates high …

An Llm-Driven System For Doctor-Patient Simulation, Akilan Amithasagaran

Computer Science Theses

Effective physician-patient communication is fundamental to clinical competence, yet traditional simulation-based training methods using standardized patients and high-fidelity manikins are costly, resource-intensive, and difficult to scale. This dissertation presents CLiVR (Conversational Learning system in Virtual Reality), an LLM-driven system that integrates large language models and 3D avatars to simulate doctor-patient interactions for medical communication training.

CLiVR addresses three key limitations in existing virtual reality medical training platforms. First, the system operates on standalone Meta Quest 3 hardware with realistic 3D patient avatars featuring synchronized lip movements and speech-based interaction. Second, CLiVR grounds LLM responses using a curated syndrome-symptom database, constraining …

Beyond The Lace Index: Benchmarking Machine Learning Architectures And Explaining 30-Day Hospital Readmission Risk With Shap Analysis, Carl E. Hughes Iii

Williams Honors College, Honors Research Projects

Unplanned 30-day hospital readmission remains a fundamental challenge in US healthcare, associated with increased risk to patient recovery and representing an estimated $52.4 billion in annual expenses (Beauvais et al., 2022). While the rigorously validated LACE index serves as the clinical standard for readmission modeling, its linear structure and four explanatory variables lack the complexity to capture the high-dimensional and interactive nature of patient risk. This study utilizes an admission granularity level cohort of the MIMIC-IV database to develop and compare machine learning architectures against the baseline LACE index. Due to the imbalanced prevalence of readmission, the penalized logistic regression, …

Challenges And Applications Of Fine-Grained Temporal Action Understanding: Modeling Temporal Granularity And Data Efficiency, Halil I. Helvaci

Theses and Dissertations--Electrical and Computer Engineering

Fine-grained Temporal Action Segmentation (TAS) has become a cornerstone of video understanding, offering dense frame-level predictions essential for clinical assessment, surgical skill evaluation, and human-computer interaction. While TAS methods have delivered strong results on coarse-grained benchmarks, two fundamental challenges persist: (1) global attention mechanisms dilute boundary information critical for subsecond precision, a phenomenon we term the temporal granularity bottleneck, and (2) dense frame-level annotation remains prohibitively expensive, with most datasets requiring exhaustive labeling of lengthy untrimmed videos. These challenges are particularly pronounced in medical domains, where sub-second primitives define clinical outcomes while expert annotation remains scarce. In this dissertation, we …

Real-Time Isolated Asl Recognition: Evaluating Spatial-Temporal Networks And Multimodal Llms, Raga Mouni Batchu

West Chester University Graduate Theses, Dissertations, and Final Projects

This thesis investigates the deployment of high-accuracy Isolated ASL Recognition (ISLR) in resource-constrained edge environments. We train a lightweight Spatio-Temporal Attention Network (SSTAN,∼2.7 M parameters,∼10 MB) on the WLASL-100 benchmark, achieving 75.25% Top-1 and 88.24% Top-5 accuracy with 139 ms CPU-only inference. A systematic comparison against frontier multimodal LLMs (Gemini 3 Flash, Gemini 3.1 Pro, Qwen 3 VL) shows SSTAN outperforms the best LLM baseline by∼1.85×in accuracy while being 22–230×faster and up to 40×cheaper annually. The LLMs’ core limitation is a lack of fine-grained temporal perception; they impose English-language semantic priors rather than learning the articulatory distinctions that define ASL …

High-Resolution Mapping Of Soil Moisture Variation Using Uas Thermal And Multispectral Imagery, Jackline Amma Timah

Theses and Dissertations

In agricultural landscapes, soil moisture regulates hydrologic partitioning, nutrient transport and water quality, land-atmosphere energy exchange that shapes local climate, and ecosystem resilience. However, traditional monitoring approaches, such as in-situ sensors and satellite imagery, often lack the spatial resolution required to capture fine-scale soil moisture variability. This study evaluated whether unmanned aerial system (UAS)-derived thermal, multispectral, and terrain variables can capture fine-scale spatial variability in volumetric water content (VWC) within an SRB in central Illinois.

High-resolution imagery was collected and paired with 50 field-measured VWC observations. Land surface temperature (LST), vegetation indices (NDVI and NDRE), spectral bands, and slope were …

Performance Of Numerical Methods Applied To The Black–Scholes Model, Scott Cameron Williams

UNF Graduate Theses and Dissertations

We compare five numerical approaches for approximating solutions to the Black–Scholes partial differential equation for pricing European call options: FTCS, BTCS, Crank– Nicolson, Monte Carlo simulation, and a physics–informed neural network (PINN). These methods span finite difference techniques, probabilistic simulation, and machine learning. Performance is evaluated based on computational efficiency and accuracy relative to the analytical Black–Scholes solution.

Among the methods, Crank–Nicolson and the PINN demonstrated the strongest overall performance. Crank–Nicolson achieved the highest accuracy but exhibited increased runtime as the number of underlying stock price grid points grew. In contrast, the PINN produced slightly less accurate results but with …

A Comparative Evaluation Of Data Imbalance Handling Techniques In Machine Learning Models For One-Year Mortality Prediction In Liver Cirrhosis, Sumiya Hasan Trisha

UNF Graduate Theses and Dissertations

Liver cirrhosis is associated with substantial morbidity and mortality, making one-year mortality prediction a clinically relevant problem. Using a liver cirrhosis dataset as the motivating application, this thesis evaluates five machine learning classifiers—Logistic Regression, Random Forest, XGBoost, LightGBM, and CatBoost—under five class-imbalance handling strategies: Baseline learning, Random Oversampling, SMOTE-NC, ADASYN, and Cost-Sensitive Learning. Hyperparameter tuning was conducted using randomized search, and predictive performance was assessed over 200 iterations of Monte Carlo Cross-Validation using Accuracy, Precision, Recall, Fl-score, and ROC-AUC.

The results suggest that imbalance-handling strategies can materially affect predictive performance, particularly recall. Because the outcome of interest is death within …

Predicting Oil Contamination In Water Using Machine Learning On Microbial Compositions, Tong Gao, Isaac Bigcraft, Stephen Techtmann, Issei Nakamura

Michigan Tech Publications

We present a compact and generative machine-learning framework that predicts oil contamination based on microbial community compositions from experimental samples. Our method combines dimensionality reduction with data augmentation and generative modeling to address high-dimensional, non-linear, and sparse microbial data. To reduce the 503-dimensional bacterial composition dataset, we compared three dimensionality reduction techniques: feature importance from random forest, principal component analysis (PCA), and t-distributed stochastic neighbor embedding (t-SNE). Feature importance outperformed PCA and t-SNE, improving predictive performance and identifying microbial species most strongly correlated with oil contamination. To mitigate data scarcity, we augmented the training data using an augmented data neural …

Visualizing And Evaluating Binary Classifier Performance With Contingency Space, Colin D. Kehoe, Azim Ahmadzadeh

Undergraduate Research Symposium

Traditional metrics for evaluating binary classifiers, such as Accuracy, F1 Score, and True Skill Statistic (TSS), often obscure the underlying tradeoffs between true positive and true negative performance—particularly in imbalanced or high-stakes domains. This poster introduces the Contingency Space, a two-dimensional representation of classifier behavior defined by true positive rate (TPR) and true negative rate (TNR). Within this space, scalar performance metrics become geometric surfaces, revealing how scores vary across the entire landscape of possible classifier outputs.

We present a Python package that implements this framework, enabling users to map model predictions into the Contingency Space, visualize metric surfaces …

Face Value: A Computational Approach To Subjective Impressions Of Faces, Kevin Kpankou

Undergraduate Research Symposium

Various computational models of first impressions have been developed to uncover the mechanisms driving these judgments. However, the implicit notion of a singular ``human'' often overlooks meaningful individual differences in beliefs, attitudes, and associations, as well as culturally grounded group-level constructs. In this paper, we extend Cultural Consensus Theory (CCT) to estimate culturally shared beliefs about faces by incorporating latent constructs structured around interpretable facial features extracted via computer vision algorithms. We apply our model to a large-scale dataset of people’s first impressions of faces. Our approach reveals a robust mapping between facial features and culturally constructed impressions, allowing us …

Achieving More Accurate And Interpretable Fraud Detection With Double Machine Learning, Jeremy Andrew Berry

Theses and Dissertations

Fraud detection remains a critical challenge across industries such as insurance, healthcare, finance, and government. Global losses from fraud and financial crime are estimated in the trillions annually, including billions in healthcare and insurance fraud alone. While effective for prediction, traditional machine learning methods often lack causal interpretability and struggle to adapt to evolving fraud tactics. This dissertation investigates the application of Double Machine Learning (DML), an emerging causal inference technique, to enhance both the accuracy and interpretability of fraud analytics. The research compares DML against established causal inference approaches, leveraging a meta-learning framework to evaluate model performance on accuracy, …

Flooding Behavior Near The Us/Canada Border: Complications And Approaches, Maria T. Dodson

Honors College Theses

Flood forecasting remains a major challenge due to the nonlinear nature of hydrological systems and uncertainties in environmental data. This study aimed to address the prevalent challenges that arise from forecasting flooding behavior. To address the inherent complexity of hydrological forecasting, a machine learning framework was developed and trained on major contributing factors. To achieve an optimal balance between computational efficiency and predictive performance, a Gated Recurrent Unit (GRU) was selected as the optimal machine learning model. As the chosen dataset, North American Land Data Assimilation System Phase 2 (NLDAS2), is known to have inaccuracies in the important feature Relative …

Toward Understanding Multi-Agent Decision Making In Complex Societies, Jonathan Skaggs

Theses and Dissertations

This dissertation investigates Multi Agent Decision Making (MADM) within Complex Societies (CS), systems of interdependent agents whose collective behaviors emerge from local interactions. Such emergent dynamics are nonlinear and difficult to predict, posing significant challenges towards understanding how individual decisions scale to societal outcomes. Existing approaches often fall short of capturing the combined attributes of CS, including asymmetry, decentralization, and adaptivity. To address this gap, we introduce new models and analyses of agent strategies that explain how cooperation and stability can arise in CS. Structured around three interrelated projects, this dissertation enhances our comprehension of MADM in CS. The research …

A Proposed Study Of Tone Indicators In Sentimental Analysis And Emotion Detection, Andrea Llanas

Infinite Loop

Sentimental analysis and emotion detection have been an ever-growing field in academic literature in recent years [1,2,3]. There are many methods and techniques to distinguish positive and negative tokens as well as classification of emotions respectively. However, the use of tone indicators has been relatively underexplored within the field.

Tone indicators are a relatively recent trend in social media. Users denote a positive or negative connotation as well as an emotion in a sentence at the moment of conception with syntax such as “/s,” “/pos,” and “/neg.” These annotations often are context-free, or do not depend on previously declared information, …

Explainable Ai For Liver Transplant Survival Prediction: Integrating Immunological Mismatch Features, Sourab Shaik

Honors Projects

Liver Transplantations are crucial treatment for end-stage liver disease. However, a persistent deficit of donor organs necessitates maximizing the utility of each available graft to minimize failure rates. We evaluated whether donor–recipient molecular immunogenicity metrics - Electrostatic and Hydrophobic Mismatch Scores (HMS/EMS) and eplet-based counts - improve post–liver-transplant survival prediction. The analytic cohort comprised adult, first time, single-organ deceased-donor transplants drawn from Scientific Registry of Transplant Recipients; follow-up was truncated at five years, and the endpoint was all-cause graft failure (earliest of graft failure or death; otherwise, censored). HLA variables were derived via high- resolution conversion and molecular mismatch computations …

Microgrid Assessment And Ml-Based Power System Faults Detection Leveraging Real-Time Co-Simulation, Diego Normando Gandara Mendez

Open Access Theses & Dissertations

The rapid growth of distributed energy resources (DERs) and the increasing reliance on data-driven decision making have reshaped the operational challenges of modern electric power systems. As microgrids become more prominent in distribution networks, utilities require methods that unify planning, control, and real-time situational awareness to ensure resilient operation under faulted or uncertain conditions. The goal of this MSEE thesis is to design and validate a latency-aware ML framework for rapid, reliable fault detection in distribution grids. To achieve the goal of the thesis, there are three specific objectives. Objective 1 evaluates optimized microgrid configurations under varying DER levels and …

Contextual Embedding Using Machine Learning For Cybersecurity: Access Control And Application, Thanh Bui

Graduate Theses and Dissertations

Access control is a well-established challenge in cybersecurity, with significant research focused on enhancing system autonomy and accuracy across various scenarios. Access control rules can be designed based on users’ roles, attributes, or relationships requesting access to specific resources. However, despite their benefits, these models still require human oversight. As systems expand and grow, it becomes increasingly complex for administrators to maintain precise access control rules, often necessitating extensive system updates or even a complete overhaul. This dissertation introduces a novel approach that leverages contextual embedding for user information to enable the system to autonomously authorize user requests for resources. …

Machine Learning For Anomaly Detection In Neural Network Security And Srf Cavities, Hal Ferguson

Electrical & Computer Engineering Theses & Dissertations

This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications.

First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves …

Efficient Self-Supervised Representation Learning For Large-Scale Time Series Classification, Kevin Garcia

Theses and Dissertations

Recently, there has been a significant advancement in designing Self-Supervised Learning (SSL) frameworks for time series data to reduce the dependency on data labels. Among these works, hierarchical contrastive learning-based SSL frameworks, which learn representations by contrasting data embeddings at multiple resolutions, have gained considerable attention. Due to their ability to gather more information, they exhibit better generalization in various downstream tasks. However, when the time series data length is significant long, the computational cost is often significantly higher than that of other SSL frameworks. In this paper, to address this challenge, we propose an efficient way to train hierarchical …