Data Science Commons^™

A New Approach To Generate Combinatorial Patterns In Logical Analysis Of Data And Its Application To Predict College Retention, Salihah Ahmed E. Jaafari

Theses and Dissertations

Student retention and degree completion remain central challenges for higher-education institutions, with significant implications for student success, institutional effectiveness, and public accountability. While advances in predictive analytics have enabled earlier identification of students at risk of withdrawal, many commonly used machine learning approaches suffer from limited interpretability, constraining their practical usefulness for advising, intervention, and policy decision making. This dissertation addresses the problem of predicting student persistence by developing and evaluating optimization based, interpretable classification models within the Logical Analysis of Data (LAD) framework. Building on existing LAD formulations, this research introduces two novel pattern generation models, the Best Term …

Topological Data Analysis Of New York City Taxi Trip Data Using Advanced Dimensionality Reduction And Clustering Techniques – Uncovering Structure And Timeliness, Mahalakshmi Sakthivel

Theses and Dissertations

In this project, we used Topological Data Analysis (TDA) to explore the shape and structure of high-dimensional data and the timeliness dimension of information quality through topological data analysis, with the long-term goal of automatically computing timeliness values that reflect how useful data items are for decision making. The project followed a two-phase approach: in the first half, we employed the Kepler Mapper library along with techniques like Principal Component Analysis (PCA), Uniform Manifold Approximation and Projection (UMAP), T-SNE (t-Distributed Stochastic Neighbor Embedding) and Customized Embedding to analyze and visualize complex datasets. In the second phase, we specifically applied our …

Data Defines Success: Algorithm For Dataset Quality Assessment In Deep Learning For Malware Detection, Matei Ionescu

Theses and Dissertations

The field of artificial intelligence is based upon the premise of constructing architectures through which to propagate training data. However, the majority of existing research literature is focused on architecture. While necessary, the attention devoted to the architecture should not so precipitously exceed that of the data. It should be noted that this disparity is not without reasonable cause. Data quality is often exceedingly difficult to verify due to particularities of the field or subfield; LLM repositories of text are distinct from image recognition pictures of dog breeds which are distinct from EEG waveforms of human brains which are distinct …

An Integrated Data-Driven Framework For Arctic Shipping: Analyzing Vessel Speed, Environmental And Ecological Factors Through Innovative Statistical Spatio-Temporal Methods, Inverse Optimization And Machine Learning, Mauli Pant

Theses and Dissertations

This dissertation develops an integrated data-driven framework to analyze vessel navigation and ecological risk in the United States Arctic from 2010 to 2019. As environmental change and maritime activity increase in the region, understanding how vessels respond to dynamic conditions and how those responses interact with marine ecosystems has become increasingly important. A central theme of this dissertation is the treatment of vessel speed as both an observed outcome and a decision variable reflecting trade- offs among operational, environmental, and ecological factors. The first chapter develops a predictive framework for vessel speed over ground (SOG) using Gaussian Process Boosting (GPBoost), …

Impacts Of Climate Disruption On Mobility Aircraft Performance In The Pacaf Region, Hannah M. Dauterman

Theses and Dissertations

This thesis investigates the projected impacts of climate disruption on the performance and fuel management of the C-17 Globemaster III, a critical mobility aircraft in the Pacific Air Forces (PACAF) region. As rising global temperatures reduce air density, the performance of aircraft is compromised, resulting in increased fuel consumption, as well as the potential for extended runway requirements and diminished cargo capacity. Using climate projection data from Coupled Model Intercomparison Project Phase 6 (CMIP6), this research analyzes future air temperature trends and their implications for C-17 fuel consumption. Results suggest that by 2049, the U.S. Air Force may incur an …

Dynamic Approaches To Missing Data In Healthcare: Evaluating Ensemble Models, Feature Selection, And Meta-Features, Dylan Dominguez Sulca

Theses and Dissertations

Missing data is pervasive in healthcare, where incomplete observations commonly arise from patient dropout, sensor failures, or privacy constraints. This research presents an investigation into handling such data, focusing on (1) Missingness-Aware Dynamic Ensemble Weighting (MDEW), (2) feature selection under varying missing rates, (3) autoencoder-based imputation (ODAE), and (4) a meta-feature analysis guiding pipeline selection. We evaluate our experiments on four diverse datasets, Cleveland Heart Disease, Diabetic Retinopathy, Breast Cancer Wisconsin, EEG Eye State. Our research shows that MDEW adaptively selects imputer classifier pipelines, outperforming single model and uniform averaging baselines at moderate to high missingness 10% to 50%. Filter …

Advancing Precision And Autonomy In Agriculture And Medical Imaging Through Ai And Computer Visions, Tan-Hanh Pham

Theses and Dissertations

Deep learning has revolutionized numerous fields by enhancing precision, automation, and decision-making capabilities. This dissertation explores its applications in agriculture and medical image processing, introducing novel methodologies to improve accuracy and efficiency in these domains. These fields hold critical societal importance -- agriculture underpins global food security and sustainability, while medical imaging drives advancements in diagnostics and personalized healthcare, both benefiting significantly from data-driven innovations. In agriculture, deep learning is applied to precision spray systems through droplet analysis. Specifically, a generative model is designed to create synthetic droplet images, addressing the challenge of limited training samples, which are expensive …

Forecasting Army Recruiting Mission Distribution, Maxwell A. Deihl

Theses and Dissertations

The Army’s recruiting landscape has changed markedly in recent years, raising questions about whether forecasting methods of Army contracts remain robust. This thesis recreates the presented models in Joshua McDonald’s 2015 thesis. It replicates and evaluates the models with updated data (2018–2023) to assess their current validity and compare them to novel alternative approaches, such as simpler regression models or neural networks. While the 2015 model remains a valuable baseline, results suggest that either refining its variables or adopting alternative methods can improve predictive accuracy and interpretability. Ultimately, the United States Army Recruiting Command has many options regarding how it …

Analyzing U.S. Army Recruiter Productivity Through Cohort Differentiation And Behavioral Tendency Composition, Mary M. Bates

Theses and Dissertations

This research analyzes differences among aggregate achievements of U.S. Army recruiting cohorts, determines which behavioral tendencies are indicative of performance level, and investigates aggregate behavioral composition with cohort achievement. Analyses require implementation of OLS regression, ANOVA, Tukey’s Test, Mann-Whitney U test, Holm-Bonferroni adjustment, XGBoost decision tree, logistic regression, and the Kolmogorov-Smirnov test. The results show insignificant achievement differences among cohorts and weak yet prevalent abilities of select measures of behavioral tendencies to indicate recruiter performance.

Class Imbalance: A Landscape Of Classification Models, Joshua L. Edmonds

Theses and Dissertations

Class imbalance poses significant challenges in machine learning classification. This study evaluates the performance of seven models (ANN, k-Means, kNN, LDA, LR, SVM, XGBoost) across multiple imbalance levels (10\%, 5\%, 1 \%, 0.5\%) and investigates the effectiveness of sampling techniques (Undersampling, SMOTE, SMOTE-ENN). ANOVA results confirm that model choice is the most critical factor, with XGBoost and SVM demonstrating superior robustness. SMOTE improves recall but reduces precision, while undersampling generally degrades overall performance. While significant, imbalance levels do not play a critical role in model effectiveness.

Tracking News Narratives: Topic Modeling, Sentiment, And Media Coverage Patterns, Alexandria G. Lai

Theses and Dissertations

This study introduces a novel content-driven influence measurement framework, built around a custom influence formula that integrates Non-negative Matrix Factorization (NMF) topic modeling, sentiment analysis, and influence metrics to analyze media narratives over time. Applied to news coverage of the 2020 U.S. presidential election and the COVID-19 pandemic, the framework identifies key topics, sentiment patterns, and influential sources. Results demonstrate its ability to distinguish between transient political controversies and sustained public health discourse while capturing shifts in media influence. While effective, refinements in topic separation, sentiment analysis, and temporal weighting could enhance adaptability. This study highlights the novel influence formula …

A Reinforcement Learning Approach For Maneuvering And Firing Decisions In Sead Operations, Nathaniel Garcia

Theses and Dissertations

The integration of automated processes in defense continues to expand, enhancing the lethality of military forces. Artificial intelligence accelerates decision-making cycles, removes the constraints of human-operated hardware, and improves coordination by enabling seamless integration across multiple systems. Suppression of Enemy Air Defenses (SEAD) missions are critical to the United States (U.S.) military, as they neutralize hostile air defense systems, ensuring air superiority and enabling safe and effective operations for aircraft in contested environments. Therefore, it is necessary to pair emerging autonomous capabilities with an important mission set in defense. This research investigates the Autonomous Unmanned Air-to-Ground Strike (AUAGS) problem, modeling …

Symbology Detection And Numerical Recognition For T-38 Heads-Up Display Recordings, Ben T. Hepner

Theses and Dissertations

The extraction of symbology and numerical data from the T-38 Heads-Up Display (HUD) enhances post-flight analysis and supports real-time decision-making. This research develops a deep learning pipeline using YOLO-based object detection and Optical Character Recognition (OCR) to analyze HUD video data. Model evaluations showed mAP0.5:0.95 ranging from 0.422 (YOLOv11m, hard test set) to 0.696 (YOLOv8m, medium test set), demonstrating robust symbology detection. Numeric detection performed well (mAP_0.5:0.95 = 0.764), but OCR struggled with glare and resolution limitations, achieving a recognition accuracy of 17.35%. These results validate deep learning for HUD data extraction but highlight the need for improved robustness …

Practical Estimation Of Action-Generation Mechanisms In Repeated Games, Vladimer Kellachow Iii

Theses and Dissertations

The goal of this research is to gain insight into how players of a game learn their strategy during the course of repeated play. The study employs the Experience Weighted Attraction (EWA) model, developed by Dr. Colin F. Camerer and Dr. Teck-Hua Ho, as the foundational behavioral framework. Using historic observed strategy decisions, the parameter values that define an opponent’s learning process are updated using various inference methods.

Machine Learning With Flight Data Recorder Data For Flight Fuel Consumption Predictions, Adam C. Levandowski

Theses and Dissertations

This study applies advanced Machine Learning (ML) to Flight Data Recorder (FDR) data for fuel consumption predictions. It explores feature engineering, model selection, and Hyper-Parameter Optimization (HPO) across all flight phases. Baseline models like Ordinary Least Squares (OLS) regression, Multi- Layer Perceptrons (MLPs), and decision trees are compared to Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs) with Gated Recurrent Unit (GRU) layers, and XGBoost. Results analyze segmentation strategies, tailored features, and model performance. A counterfactual analysis compares ML models to operational fuel predictions, demonstrating their deployment potential. Findings establish a foundation for future ML-driven advancements in aviation fuel optimization.

Data Lakehouse And Machine Learning Pipeline For Aircraft Fuel Efficiency Experimentation, Skyler G. Kepley

Theses and Dissertations

Fuel efficiency is crucial for the U.S. Air Force, impacting mission success, aircraft performance, and cost savings. This study presents an information system that integrates flight and maintenance data using a data lakehouse. It automates ingestion, enrichment, and predictive modeling, leveraging AutoML for optimization and SHAP for transparency. A case study on C-130J aircraft shows that optimizing D Check cycles can save 11.52 pounds of fuel per flight hour. These findings highlight the effectiveness of data-driven decision-making in aviation, offering a scalable, automated solution for improving fuel efficiency and reducing costs.

Proximal Policy Optimization Applied To The Beyond Visual Range Air Combat Maneuvering Problem, Daniel B. Joseph

Theses and Dissertations

Artificial intelligence (AI) grows ever-more important in warfighting. Emerging technologies allow for the use of AI to control aircraft and weapons systems. This research investigates the application of reinforcement learning (RL) through the Proximal Policy Optimization (PPO) algorithm to a two-versus-two (2v2) beyond-visual-range (BVR) air combat maneuvering problem (ACMP). Implemented in the Advanced Framework for Simulation, Integration, and Modeling (AFSIM), the methodology frames the engagement as a Markov decision process, wherein an autonomous RL agent learns continuous control decisions—throttle, pitch, roll, and yaw—under a cooperative communication scheme. A multi-phase curriculum-learning approach facilitates the progressive acquisition of flight stability, weapon deployment, …

Hyperparameter Tuning For Robust Autonomous Vehicle Vision, Nico D. De Ros

Theses and Dissertations

Classification “flickering,” where the classification of an object changes inconsistently between consecutive video frames, remains a persistent issue in modern object classification algorithms. This problem undermines the reliability of autonomous vision systems and poses significant risks in high-stakes applications such as autonomous vehicles. This thesis explores the use of response surface methodology, a statistical design of experiments technique, to optimize hyperparameters across three object classification pipelines. The first pipeline combines YOLOv8 with SORT to establish a benchmark. The second integrates a Bayesian back-end, while the third employs an exponential smoothing back-end. Hyperparameter tuning was conducted using a two-step process: an …

Machine Learning Techniques To Predict Solar Particle Events And Radiation Of Aircrew, Haley Traub

Theses and Dissertations

Solar Particle Events (SPEs) are high-energy phenomena from the Sun that pose risks to technology, human health, and Air Force operations. Accurate prediction of SPEs exceeding 100 MeV is crucial for mitigating these risks. This thesis explores using Bayesian statistical models to predict such events, integrating prior knowledge from solar physics with the ability to update predictions based on new data. The research uses a dataset spanning three solar cycles (21–23) and incorporates attributes like flare fluence, peak flux, latitude, longitude, and class. Four Bayesian models (PyMC, Bnlearn, and two Dredge models) were compared to machine learning models. The Bayesian …

Geo-Spatial Mapping Of Sentiment Analysis With Transformer-Based Models, Dugan J. Turnbow

Theses and Dissertations

The public sentiment of events of interest, and their impacts, is vital for decision makers to allocate resources. This research develops a robust algorithm for aggregating sentiment analysis from social media and published articles, while contextualizing results through spatial and temporal mapping. The methodology employs two transformer-based language models for sentiment analysis and named entity recognition (NER). Sentiment scores are generated and augmented using explicit location data, such as latitude and longitude, and implicit location data derived through NER or location features. Results are mapped using a geo-tagged location dictionary, enabling visualization of sentiment trends at state and county levels …

Improving Zero Shot Learning By Linking Multi-Label Cnns With Llms, Michael A. Wegner

Theses and Dissertations

Classifying previously unseen objects poses a significant challenge for traditional computer vision algorithms, which rely on extensive labeled training data. Zero-shot reasoning offers a way to overcome this limitation. This research explores a novel method for image recognition using the Animals with Attributes 2 (AWA2) dataset as a proof of concept. A multi-label ResNet50 model predicts core attributes like color, ear shape, or number of limbs. Those attributes then feed into ChatGPT which leverages its extensive knowledge base to classify the animal based on the provided attributes. This novel approach skips the need to train on every possible class. Instead, …

Leveraging Distributed Semantics From Deep Learning Architectures For Literature-Based Discovery, Clint A. Cuffy

Theses and Dissertations

Literature-based discovery (LBD) is a scientific process that introduces methods to automatically identify novel insights between non-interacting sets of literature. To date, numerous statistical and machine learning-based methods have been applied in the biomedical domain to find treatments for diseases such as Raynaud's disease, Parkinson's disease, and Multiple Sclerosis. However, the lack of standardized practices and creation of bespoke methodologies produces a scenario where the adoption of LBD remains challenging in real-world systems. Our work addresses these concerns through the improvement of five critical areas: 1) error propagation within LBD's a priori dependent tasks, 2) exploring the integration of modern …

Beyond Homogeneity: Exploring Causal Heterogeneity In Psychopathology, Philip B. Vinh

Theses and Dissertations

Traditional models in psychiatric research often impose assumptions of causal homogeneity, treating population-level associations as reflective of uniform underlying mechanisms. This dissertation challenges that assumption by introducing statistical and machine learning frameworks designed to detect and model causal heterogeneity in the development of psychopathology. Central to this approach is the advancement of finite mixture structural equation modeling (FM-SEM) to identify latent subgroups characterized by distinct, and sometimes opposing, causal pathways.

The dissertation comprises three integrated empirical studies. The first introduces mixDoC, a finite mixture extension of the classical Direction of Causation (DoC) model applied to twin data, enabling the detection …

Centralized Deep Reinforcement Learning For Homogeneous Multi-Component Maintenance Optimization, Joseph W. Wittrock

Theses and Dissertations

This thesis explores an application of reinforcement learning (RL) in maintenance optimization. Recent advances in hardware-accelerated computation and deep learning have made RL a powerful tool for solving optimization problems which are too complex for traditional methods. Maintenance optimization involves improving the efficiency and effectiveness of maintenance activities through data-driven approaches, ultimately reducing costs and increasing asset availability. Making informed maintenance decisions is crucial to long-term sustainability.

A desirable maintenance policy maximizes a utility signal while minimizing the cost of maintenance. Techniques in sequential decision making such as dynamic programming (DP) and RL have found success in optimizing these maintenance …

Multitask Learning For Named Entity Recognition And Relationship Extraction, Adrienne D. Hembrick

Theses and Dissertations

Information Extraction (IE) is a fundamental task in Natural Language Processing (NLP), involving the identification of structured information from unstructured text. Two core components of IE—Named Entity Recognition (NER) and Relation Extraction (RE)—are widely used to extract key concepts and the relationships between them across various domains. However, the sequential dependency of RE on the output of NER makes it vulnerable to error propagation: inaccuracies in entity recognition can negatively affect downstream relation extraction.

To mitigate this issue, Multitask Learning (MTL) has been proposed as an approach that jointly models NER and RE, aiming to improve overall performance and reduce …

Optimal Data Splitting Methods, Sujay Mudalgi

Theses and Dissertations

In predictive modeling, effective data splitting is crucial for creating statistically representative training and validation sets. The state-of-the-art data splitting methods are based on minimizing the energy distance between the split subsets. However, there are a number of limitations in the existing methods, which this dissertation aims to address. First, the existing methods were computationally inefficient. Thus, Chapter 2 proposes a method to scale up these approaches for big data. Here, we introduce scalable Twinning (s-Twinning), which significantly improves the execution speed of data splitting without sacrificing accuracy. Second, the existing methods did not consider the predictive relationship in the …

Machine Learning Models Leveraging Patient-Similarity And Clinical Temporality For Disease Prognoses, Ahmad F. Al Musawi

Theses and Dissertations

Electronic Health Records (EHRs) constitute a comprehensive and high-dimensional repository of clinical data, encompassing a wide array of patient-level information such as diagnoses, procedures, medications, laboratory results, and unstructured clinical narratives. These data hold immense potential for advancing predictive modeling in healthcare, including tasks such as disease progression modeling, hospital readmission prediction, and length of stay (LoS) estimation. However, the intrinsic complexity of EHR data—manifested in its heterogeneity, sparsity, and temporal dynamics—poses significant analytical challenges that limit the generalizability and interpretability of conventional machine learning models. Recent methodological advancements in deep learning and graph-based learning, particularly Graph Neural Networks (GNNs), …

Learning From Non-Stationary Data Streams, Gabriel Jonas Aguiar

Theses and Dissertations

The rapid growth of data from sources such as mobile applications, sensors, and network monitoring has increased the need for machine learning algorithms capable of handling non-stationary data streams. However, learning from such streams presents significant challenges due to their evolving nature and the presence of concept drift. One of the most complex issues is learning from imbalanced data streams, where shifting data distributions, combined with feature space drifts, complicate continuous adaptation. These challenges become even more pronounced in multi-class scenarios, which are common in real-world applications. Detecting concept drift in such contexts is particularly demanding, as it requires tracking …

Decoding Neural Networks: An Information-Theoretic Guide To Interpretability, Error Analysis And Efficiency, Mackenzie J. Meni

Theses and Dissertations

This dissertation addresses critical challenges in neural network design by leveraging entropy-based techniques to improve model efficiency, interpretability, and bias reduction. Focusing on the unique demands of computer vision applications, particularly object detection and classification for real-time systems, this work introduces a series of innovative methods centered on information theory. At the core of these methods is the Probabilistic Explanations of Entropic Knowledge (PEEK) framework, a tool developed to analyze and visualize entropy distributions across feature maps. PEEK offers insights into information flow within neural networks, making it possible to pinpoint layers that contribute meaningfully to decision-making or identify those …

A Machine Learning Approach For Survival Analysis Of Transplanted Kidneys Based On Donors’ And Recipients’ Factors., Alain Edward Despeignes

Theses and Dissertations

Over seven thousand people on average die each year in the United States waiting for an organ transplant due to the shortage of donated organs. With this alarming concern, efforts from the health organizations like the United Network Organ Sharing (UNOS) and government officials have considered avenues to remedy this distress, one of which is to investigate the characteristics among donors and recipients that affects the longevity of donated organs. The goal of this project is to investigate the survival time of transplanted kidneys from 1987 to 2018 with regards to the donors’ and the recipients’ characteristics including gender, ethnicity, …