Data Science Commons^™

Reinforcement Learning, Modeling Markets, And Professional Basketball Free Agency, Jacob Cohn

Computational and Data Sciences (PhD) Dissertations

This dissertation presents a reinforcement learning-based approach to modeling and optimizing decision-making in professional basketball free agency and related economic environments. A Markov Decision Process (MDP) framework is introduced to capture the strategic interactions of NBA teams bidding for free agents under budgetary and roster constraints. To address computational scalability challenges, a reinforcement learning (RL) environment is developed, leveraging Proximal Policy Optimization (PPO) to approximate optimal policies for team decision-making.

Empirical results demonstrate that the RL agent successfully learns strategic bidding behavior that aligns with dynamic programming benchmarks in simplified settings while scaling effectively to larger, intractable environments. The study …

Explainable Ai In Medical Imaging: An Interdisciplinary Translational Approach, Caitlyn Chavez

Computational and Data Sciences (PhD) Dissertations

Advances in computer vision and image processing have made a clear impact on many fields, from healthcare diagnostics to autonomous driving. However, as these models become more complex, understanding their decision-making processes has grown increasingly challenging, making explainable AI (XAI) a crucial component of modern AI systems. The focus of this work is to integrate these new technologies alongside foundational methods of image processing to create tools that can be used by domain experts who are not programmers. Prior to delving into the projects which investigate these concepts, the methodologies, background, and the overall frameworks are discussed. In the first …

Medical Image Analysis Based On Graph Machine Learning And Variational Methods, Sina Mohammadi

Computational and Data Sciences (PhD) Dissertations

This study explores advanced methodologies for enhancing brain tumor segmentation, addressing the complexity and diversity of tumor sub-regions in medical imaging. We introduce a novel approach utilizing Graph Neural Networks (GNNs) that incorporate both spectral and spatial insights for segmentation. By leveraging various supervoxel creation methods such as VCCS, SLIC, Watershed, Meanshift, and Felzenszwalb-Huttenlocher, we structured 3D MRI images into a graph format. This format enabled the implementation of Spectral and Spatial GNNs to capture comprehensive local and global tumor characteristics effectively. Our Spectral-Spatial GNN model, integrating the Laplacian matrix, demonstrated significant improvements in segmenting distinct tumor sub-regions of Necrosis, …

A Novel Correction For The Multivariate Ljung-Box Test, Minhao Huang

Computational and Data Sciences (PhD) Dissertations

This research introduces an analytical improvement to the Multivariate Ljung-Box test that addresses significant deviations of the original test from the nominal Type I error rates under almost all scenarios. Prior attempts to mitigate this issue have been directed at modification of the test statistics or correction of the test distribution to achieve precise results in finite samples. In previous studies, focused on designing corrections to the univariate Ljung-Box, a method that specifically adjusts the test rejection region has been the most successful of attaining the best Type I error rates. We adopt the same approach for the more complex, …

Machine Learning And Geostatistical Approaches For Discovery Of Weather And Climate Events Related To El Niño Phenomena, Sachi Perera

Computational and Data Sciences (PhD) Dissertations

El Nino and La Nina are worldwide environmental phenomena brought about by repetitive changes in the water temperature of the Pacific Ocean. Even though the El-Nino impact focuses on a smaller area in the Pacific Ocean near the Equator, these developments have global repercussions, where temperature and precipitation are influenced across the globe, causing droughts and floods simultaneously. In this dissertation, we first derived a drought vulnerability index for the Nile basin, identifying regions with high and low drought risk under ENSO conditions. Next, we evaluated the coherence and periodicity of the ENSO signal to detect its implications on MENA …

Global To Glocal: A Confluence Of Data Science And Earth Observations In The Advancement Of The Sdgs, Rejoice Thomas

Computational and Data Sciences (PhD) Dissertations

The United Nations' (UN) Sustainable Development Goals (SDGs), part of Agenda 2030, comprise 17 interconnected goals and 169 actionable targets, providing an effective framework for addressing diverse issues ranging from individual challenges such as poverty, hunger, and health to broader corporate and global challenges like climate change and equality. Among these interconnected SDGs, this dissertation focuses on the role of climate and infrastructure in global and local sustainability. To this end, earth observations have been conducted utilizing data science techniques to advance these SDGs. For this dissertation, the author has conducted earth studies serving the following SDGs:

1. SDG 3 (Good …

Applications Of Causal Inference Methods For The Estimation Of Effects Of Bone Marrow Transplant And Prescription Drugs On Survival Of Aplastic Anemia Patients, Yesha M. Patel

Computational and Data Sciences (PhD) Dissertations

This dissertation provides an in-depth exploration into the treatment effectiveness for aplastic anemia using causal inference methods, structured around three pivotal research papers. Each paper contributes to a nuanced understanding of treatment impacts, specifically focusing on bone marrow transplantation (BMT) and prescription drugs, and the identification of optimal treatment strategies.

The first paper, "Causal Inference Analysis for Assessing the Effect of Bone Marrow Transplantation on the One-Year Survival of Adult and Pediatric Aplastic Anemia Patients," sets the foundation. It examines the short-term effectiveness of BMT in both adult and pediatric patients, providing crucial insights into how this treatment affects survival …

Random Variable Spaces: Mathematical Properties And An Extension To Programming Computable Functions, Mohammed Kurd-Misto

Computational and Data Sciences (PhD) Dissertations

This dissertation aims to extend the boundaries of Programming Computable Functions (PCF) by introducing a novel collection of categories referred to as Random Variable Spaces. Originating as a generalization of Quasi-Borel Spaces, Random Variable Spaces are rigorously defined as categories where objects are sets paired with a collection of random variables from an underlying measurable space. These spaces offer a theoretical foundation for extending PCF to natively handle stochastic elements.

The dissertation is structured into seven chapters that provide a multi-disciplinary background, from PCF and Measure Theory to Category Theory with special attention to Monads and the Giry Monad. The …

Stochastic Processes And Multi-Resolution Analysis: A Trigonometric Moment Problem Approach And An Analysis Of The Expenditure Trends For Diabetic Patients, Isaac Nwi-Mozu

Computational and Data Sciences (PhD) Dissertations

This dissertation is divided into two distinct parts. The main theme of the first part is to study stochastic processes (and related signal processing questions) using tools in wavelet analysis, functional analysis (we use in particular the trigonometric moment problem), the theory of realization of rational functions, and reproducing kernel Hilbert spaces. A novel form of multiresolution analysis is formulated in the discrete case that is used to study some stochastic processes. Using the trigonometric moment problem, we associate with a vector-valued wide-sense stationary process a multiresolution of a new kind. The notion of realization of rational functions was used …

Causal Inference And Machine Learning Methods In Parkinson's Disease Data Analysis, Albert Pierce

Computational and Data Sciences (PhD) Dissertations

This dissertation documents an investigation into Parkinson’s Disease utilizing machine learning and causal inference methods. I will cover a descriptive analysis of Parkinson’s Disease (PD) in a vast, high-quality database and present costs associated with Parkinson’s Disease medications. I also researched a causal inference method assessing the Carbidopa-Levodopa effect on two-year survival and a causal survival analysis on a one-to-five-year survival comparing no drug use and Carbidopa-Levodopa in Parkinson’s Disease patients.

For my classification with Parkinson’s gait, patients were monitored with a smartphone and an additional 6 Inertial Measurement Unit (IMU) sensors to collect clinical gait measures. I used classical …

Application Of Machine Learning Algorithms For Elucidation Of Biological Networks From Time Series Gene Expression Data, Krupa Nagori

Computational and Data Sciences (PhD) Dissertations

This dissertation provides a deep dive into understanding gene expression, interaction, regulation, and the intricate mechanisms behind heliotropism and phototropism. Additionally, the research accentuates the significance of machine learning techniques, specifically for gene regulatory networks (GRNs).

Chapter 1 offers an exhaustive benchmarking of GRN methodologies, furthering our comprehension of machine-learning models relevant to GRNs. The evaluation revealed that GRNTE, SWING, and BiXGBoost emerged as top-performing methods in GRN inference. The suitability of these models varies depending on specific research criteria such as computational needs, dataset dimensions, and performance metric emphasis. An innovation of this chapter was the introduction of Colab …

Computational Analysis Of Antibody Binding Mechanisms To The Omicron Rbd Of Sars-Cov-2 Spike Protein: Identification Of Epitopes And Hotspots For Developing Effective Therapeutic Strategies, Mohammed Alshahrani

Computational and Data Sciences (PhD) Dissertations

The advent of the Omicron strain of SARS-CoV-2 has elicited apprehension regarding its potential influence on the effectiveness of current vaccines and antibody treatments. The present investigation involved the implementation of mutational scanning analyses to examine the impact of Omicron mutations on the binding affinity of four categories of antibodies that target the Omicron receptor binding domain (RBD) of the Spike protein. The study demonstrates that the Omicron variant harbors 23 unique mutations across the RBD regions I, II, III, and IV. Of these mutations, seven are shared between RBD regions I and II, while three are shared among RBD …

Integration Of Computer Algebra Systems And Machine Learning In The Authoring Of The Sanyms Intelligent Tutoring System, Sam Ford

Computational and Data Sciences (PhD) Dissertations

Computer-based feedback is an increasingly common tool in mathematics education. The feedback that such programs provide can range from indicating whether an answer was correct, to giving an answer or worked out solution or suggesting a similar practice problem. One type of computer-based feedback, the Intelligent Tutoring Systems (ITS), is able to provide feedback not just once per problem, but at multiple points during the process of solving a problem. Creating an ITS that gives feedback for even a narrow topic is often a time-intensive process, and machine learning is only recently being integrated into the ITS authoring process.

We …

Causal Inference In Psychology And Neuroscience: From Association To Causation, Dehua Liang

Computational and Data Sciences (PhD) Dissertations

In psychology and neuroscience, inferring causality in non-experimental studies is almost taboo, because data in these studies, e.g., survey data and resting-state neuroimaging data, are often contaminated by unmeasured confounders. Psychologists and neuroscientists are often cautious about their results, and reluctant to make false claims about causality in non-experimental studies. Therefore, they adopt less stringent statistical analysis techniques that can only infer associational relations. However, the ambiguity about causality in traditional statistical analysis creates much confusion in interpreting analytical results - some studies make implicit causal claims about their results using words such as “impacts”, “lead to” and “affects”. This …

Computational Approaches To Facilitate Automated Interchange Between Music And Art, Rao Hamza Ali

Computational and Data Sciences (PhD) Dissertations

Recently, there has been a tremendous increase in generating and synthesizing music and art using various computational techniques. An area that is still under-researched, however, is how one medium can be converted into the other, while maintaining the overall aesthetics. Over the last few centuries, artists, composers, and scholars, have attempted to use substitute one form of art for the other: by proposing techniques where music notes are synonymous to colors, by inventing instruments that combine the aesthetics of music and visual art, and by incorporating the two media in live performances. A widely accepted computational approach, for the conversion, …

Multi-Modal Data Fusion, Image Segmentation, And Object Identification Using Unsupervised Machine Learning: Conception, Validation, Applications, And A Basis For Multi-Modal Object Detection And Tracking, Nicholas Lahaye

Computational and Data Sciences (PhD) Dissertations

Remote sensing and instrumentation is constantly improving and increasing in capability. Included within this, is the increase in amount of different instrument types, with various combinations of spatial and spectral resolutions, pointing angles, and various other instrument-specific qualities. While the increase in instruments, and therefore datasets, is a boon for those aiming to study the complexities of the various Earth systems, it can also present a large number of new challenges. With this information in mind, our group has set our aims on combining datasets with different spatial and spectral resolutions in an effective and as-general-as-possible way, with as little …

Exploring Behaviors Of Software Developers And Their Code Through Computational And Statistical Methods, Elia Eiroa Lledo

Computational and Data Sciences (PhD) Dissertations

As Artificial Intelligence (AI) increasingly penetrates all aspects of society, many obstacles emerge. This thesis identifies and discusses the issues facing Computer Vision and significant deficiencies in the Software Development Life-cycle that need to be resolved to facilitate the evolution toward true artificial intelligence. We explicitly review the concepts behind Convolutional Neural Network (CNN) models, the benchmark for computer vision. Chapter 2 highlights the mechanisms that have popularized CNNs while also specifying significant gaps that could garner the model inadequate for future use in safety-critical systems. We put forward two main limitations. Namely, CNNs do not use lack of information …

Assessing The Re-Identification Risk In Ecg Datasets And An Application Of Privacy Preserving Techniques In Ecg Analysis, Arin Ghazarian

Computational and Data Sciences (PhD) Dissertations

In this work, first we investigate the use of ECG signal as a biometric in human identification systems using deep learning models. We train convolutional neural network models on ECG samples from approximately 81k patients. Our models achieved an over-all accuracy of 95.69%. Further, we assess the accuracy of our ECG identification model for distinct groups of patients with particular heart conditions and combinations of such conditions. For example, we observed that the identification accuracy was the highest (99.7%) for patients with both ST changes and supraventricular tachycardia. On the other hand, we also found that the identification rate was …

Optimal Analytical Methods For High Accuracy Cardiac Disease Classification And Treatment Based On Ecg Data, Jianwei Zheng

Computational and Data Sciences (PhD) Dissertations

This work constitutes six projects. In the first project, a newly inaugurated research database for 12-lead electrocardiogram signals was created under the auspices of Chapman University and Shaoxing People's Hospital (Shaoxing Hospital Zhejiang University School of Medicine). This database aims to enable the scientific community in conducting new studies on arrhythmia and other cardiovascular conditions. In the second project, we created a new 12-lead ECG database under the auspices of Chapman University and Ningbo First Hospital of Zhejiang University that aims to provide high quality data enabling detection of the distinctions between idiopathic ventricular arrhythmia from right ventricular outflow tract …

Novel Applications Of Statistical And Machine Learning Methods To Analyze Trial-Level Data From Cognitive Measures, Chelsea Parlett

Computational and Data Sciences (PhD) Dissertations

Many cognitive tasks and measures can benefit from trial-level analyses including Item Response Theory models as well as other Bayesian and Machine Learning models. Specifically, this dissertation focuses mainly on task-based measures of metamemory and how within-set variability as well as item-level characteristics can improve the inferences researchers make about these measures.First, a clustering analysis of judgements of learning across a task is examined in order to detect different participant strategies on a metamemory task and whether strategy use differs by age. Second, the benefits of using item response theory models to analyze both individual and item-level differences in metamemory …

Forecasting The Prices Of Cryptocurrencies Using A Novel Parameter Optimization Of Varima Models, Alexander Barrett

Computational and Data Sciences (PhD) Dissertations

This work is a comparative study of different univariate and multivariate time series predictive models as applied to Bitcoin, other cryptocurrencies, and other related financial time series data. ARIMA models, long regarded as the gold standard of univariate financial time series prediction due to both its flexibility and simplicity, are used a baseline for prediction. Given the highly correlative nature amongst different cryptocurrencies, this work aims to show the benefit of forecasting with multivariate time series models—primarily focusing on a novel parameter optimization of VARIMA models outlined in this paper.

These models are trained on 3 years of historical data, …

Applications Of Machine Learning To Facilitate Software Engineering And Scientific Computing, Natalie Best

Computational and Data Sciences (PhD) Dissertations

The use of machine learning has risen in recent years, though many areas remain unexplored due to lack of data or lack of computational tools. This dissertation explores machine learning approaches in case studies involving image classification and natural language processing. In addition, a software library in the form of two-way bridge connecting deep learning models in Keras with ones available in the Fortran programming language is also presented.

In Chapter 2, we explore the applicability of transfer learning utilizing models pre-trained on non-software engineering data applied to the problem of classifying software unified modeling language diagrams where data is …

A Novel Correction For The Adjusted Box-Pierce Test — New Risk Factors For Emergency Department Return Visits Within 72 Hours For Children With Respiratory Conditions — General Pediatric Model For Understanding And Predicting Prolonged Length Of Stay, Sidy Danioko

Computational and Data Sciences (PhD) Dissertations

This thesis represents the results of three research projects that underline the breadth and depth of my interests.

Firstly, I devoted some efforts to the well-known Box-Pierce goodness-of-fit tests for time series models which has been an important research topic over the last few decades. All previously proposed tests are focused on changes of the test statistics. Instead, I adopted a different approach that takes the best performing test and modifying the rejection region. Thus, I developed a semiparametric correction of the Adjusted Box-Pierce test that attains the best I error rates for all sample sizes and lags and outperforms …

Gaining Computational Insight Into Psychological Data: Applications Of Machine Learning With Eating Disorders And Autism Spectrum Disorder, Natalia Rosenfield

Computational and Data Sciences (PhD) Dissertations

Over the past 100 years, assessment tools have been developed that allow us to explore mental and behavioral processes that could not be measured before. However, conventional statistical models used for psychological data are lacking in thoroughness and predictability. This provides a perfect opportunity to use machine learning to study the data in a novel way. In this paper, we present examples of using machine learning techniques with data in three areas: eating disorders, body satisfaction, and Autism Spectrum Disorder (ASD). We explore clustering algorithms as well as virtual reality (VR).

Our first study employs the k-means clustering algorithm to …