Data Science Commons^™

Utilizing Physics Informed Neural Networks For Disrupted Signal Dynamics, Nicholas J. Joyner

Electronic Theses and Dissertations

Physics-informed neural networks (PINNs) have been used in many applications including engineering and physical sciences. PINNs allow the incorporation of a priori understanding of a process’ structure into the modeling. We attempt to leverage the PINN structure toward the evaluation of disruptions to classical dynamical models by combining elements of ordinary differential equations into our loss function with sigmoidal gating to balance the penalties for deviations from the data with those for structural deviations. This enables the identification of the signal structure and the limits of disruption influence. As a use case, we consider stock value from 2019-2021, which expresses …

Topic Modeling And Culturomic Analysis Of 30,000 Books Over 100 Years Using Gensim, Michael A. Freeman

Electronic Theses and Dissertations

This thesis explores the cultural influence of historical events on English-language fiction published between 1820 and 1929. Using a corpus of 30,256 digitized books from Project Gutenberg, Latent Dirichlet Allocation (LDA) topic modeling was applied to identify recurring themes across eleven decades. The study sought to determine whether historically significant events could be detected within fictional narratives. One clear instance emerged: Napoleon Bonaparte and the Napoleonic Wars appeared explicitly in the 1820s corpus. Beyond this, several thematic patterns were observed—such as maritime language in the 1840s, national identity in the 1880s, and youth-oriented dialogue in the early 20th century—that plausibly …

Stochastic Functional Data-Driven Models For Real-Time Battery Health Forecasting Under Dynamic Operating Conditions, Joshua Owusu

Electronic Theses and Dissertations

This thesis provides an effective statistical model to predict the real-time state of lithium-ion batteries for reliable Battery Management Systems (BMS). It highlights battery data (voltage, current, temperature) as smooth functional curves. The principal method demonstrates diminishing trends to health outcomes like State of Health (SoH) and Remaining Useful Life (RUL) by employing Functional Principal Component Analysis (FPCA) and Bayesian Functional Linear Models (FLMs). The primary objective is to figure out how uncertain forecasts are. Simulations demonstrate that the highest accuracy (lowest MSE) is achieved through low noise levels along with large sample sizes. The final system provides a highly …

Postprocessing Gan-Generated Synthetic Time Series Using Dynamic Time Warping, Md Raisul Islam Roni

Electronic Theses and Dissertations

Generative Adversarial Networks (GANs) are a class of deep learning models capable of producing realistic synthetic data that preserve the statistical and temporal characteristics of real datasets. The DoppelGANger (DGAN) framework extends this approach to time series data by jointly modeling temporal dependencies and contextual metadata. However, synthetic sequences generated by GAN may show temporal misalignment, resulting in inconsistencies when compared with real data. This study presents a postprocessing framework based on Dynamic Time Warping (DTW) and its differentiable extension Soft-DTW to improve the temporal alignment of synthetic time series. The framework is evaluated using quantitative measures of alignment and …

A Leslie System For A Demographic Simulation: From An Actuarial Point Of View, David Kings

Electronic Theses and Dissertations

This thesis develops a discrete stochastic linear systems interpretation of age–stage demographic evolution grounded in Leslie operators and realized in a discrete-event simulation implemented with salabim. The central claim is that one annual cycle of the simulation constitutes a cone-preserving, stochastic affine transformation on a high- dimensional population state vector indexed by age, sex, marital status, household type, employment, and education, and that the composition of yearly operators yields a random matrix product whose top Lyapunov exponent is the stochastic counterpart of the Perron–Frobenius growth rate (Caswell, 2001; Tuljapurkar, 1997)[1, 2]. The actuarial bridge is constructed by mapping simulated survival …

Grokking Applied To Chaotic Iterates Of The Logistic Map, Felix Donkoh

Electronic Theses and Dissertations

This thesis investigates grokking, the delayed transition from memorization to generalization in neural networks trained on deterministic chaotic data. Using an integer–arithmetic discretization of the logistic map, yn+1 =( a yn(p − yn))/ p 2 , bounded aperiodic sequences were generated across control parameters α ranging from 3.0 to 4.0. Transformer-based models displayed characteristic grokking curves. In periodic and chaotic regimes, validation accuracy rose suddenly after long plateaus, while at the Feigenbaum boundary (α ≈ 3.57) generalization failed completely. Increasing data diversity restored learning in chaotic domains, and explicit α–conditioning enabled a single network to generalize across all regimes. A …

An Income Subsystem As A Discrete Stochastic Leslie System: A Simulation-Based Approach, Fahd Nii Okantah Cobblah

Electronic Theses and Dissertations

This thesis formulates the household-income engine of an integrated population sim- ulator as a Discrete Stochastic Leslie System (DSLS). The nonnegative state vector nt ∈ Rk + aggregates income, savings, debt, employment, and transfers. (Here, the subscript + denotes the positive cone, i.e., vectors with nonnegative components). Annual evolution is linear in state, stochastic in coefficients: nt+1 = Ttnt + εt, with Tt : Rk + → Rk + cone-preserving. Exogenous macro drivers (inflation, employment, tax, salary inflation, mortgage) are forecast via ARIMA; forecasts multiply entries of Tt, preserving linearity in expectation while introducing realistic temporal correlation. The discrete-event implemented …

A Machine Learning Analysis Of Factors Leading To Major League Baseball Postseason Berths, Chase S. Foster

Undergraduate Honors Theses

Machine learning is a method that employs statistical algorithms to identify patterns and make predictions from data. This study applies machine learning techniques to analyze data from Major League Baseball (MLB) teams between 1998 and 2024, with the goal of determining which factors strongly influence a team's likelihood of reaching the postseason and in accurately predicting the teams that do and do not qualify for the postseason. Data exploration and unsupervised machine learning methods such as clustering were used to identify underlying patterns in team performance metrics and determine potential significant contributors to team success. Many different supervised learning methods …

Car Price Prediction Using Machine Learning: Analyzing The Dvm-Car Dataset, Yaman Abu Ghareebaih

Electronic Theses and Dissertations

The objective of this study is to predict car prices using machine learning models and the DVM-CAR dataset, which includes over 1.4 million images and car specifi- cations from 899 car models. Key factors such as mileage, engine power, and year of registration were analyzed for their correlation with car prices. Extensive data cleaning was performed, including filling missing values, identifying outliers, and normalizing numerical variables. Discrete variables like car make and body type were encoded using one-hot encoding. Linear relationships were analyzed with Multiple Logistic Regression, and Random Forest models were used for nonlinear patterns. Model performance was evaluated …

Investigating The Privacy-Utility Trade-O↵ In Synthetic Data Generation Using Correlated Attribute Mode, Kofi Sarfo

Electronic Theses and Dissertations

This thesis explores the privacy-utility trade-off in synthetic data generation using the Correlated Attribute Mode of DataSynthesizer, which employs Bayesian networks to model attribute dependencies. It focuses on integrating differential privacy mechanisms, particularly the Laplace mechanism, to inject controlled noise into synthetic data and enhance privacy protection. As organizations face challenges balancing data-driven decision-making with privacy regulations such as the General Data Protection Regulation and the California Consumer Privacy Act, synthetic data offers a solution by creating artificial datasets that preserve statistical properties while balancing data privacy and utility. This research investigates how different differential privacy parameters epsilon affect data …

Exploring The Diagnostic Potential Of Radiomics-Based Pet Image Analysis For T-Stage Tumor Diagnosis, Victor Aderanti

Electronic Theses and Dissertations

Cancer is a leading cause of death globally, and early detection is crucial for better

outcomes. This research aims to improve Region Of Interest (ROI) segmentation

and feature extraction in medical image analysis using Radiomics techniques

with 3D Slicer, Pyradiomics, and Python. Dimension reduction methods, including

PCA, K-means, t-SNE, ISOMAP, and Hierarchical Clustering, were applied to highdimensional features to enhance interpretability and efficiency. The study assessed the ability of the reduced feature set to predict T-staging, an essential component of the TNM system for cancer diagnosis. Multinomial logistic regression models were developed and evaluated using MSE, AIC, BIC, and Deviance …

Interpreting Shift Encoders As State Space Models For Stationary Time Series, Patrick Donkoh

Electronic Theses and Dissertations

Time series analysis is a statistical technique used to analyze sequential data points collected or recorded over time. While traditional models such as autoregressive models and moving average models have performed sufficiently for time series analysis, the advent of artificial neural networks has provided models that have suggested improved performance. In this research, we provide a custom neural network; a shift encoder that can capture the intricate temporal patterns of time series data. We then compare the sparse matrix of the shift encoder to the parameters of the autoregressive model and observe the similarities. We further explore how we can …

Establishing “The Fossil Record”: A Database Of Vertebrate Paleontological Sites Across The State Of Tennessee, Sarah Mclaurine

Electronic Theses and Dissertations

Fossil localities across the state of Tennessee and the data related to those sites were compiled from Tennessee Division of Geology Bulletin 84, titled “Tennessee’s Prehistoric Vertebrates,” and stored in a Microsoft Access geodatabase housed by the Department of Collections at the East Tennessee State University Museum of Natural History located at the Gray Fossil Site. Included in the database are forms to enter new site localities, view information about those already entered, view and add data to a master faunal list for the state, view sites repository information and store and add documents that are key-word searchable from the …

Exploration And Statistical Modeling Of Profit, Caleb Gibson

Undergraduate Honors Theses

For any company involved in sales, maximization of profit is the driving force that guides all decision-making. Many factors can influence how profitable a company can be, including external factors like changes in inflation or consumer demand or internal factors like pricing and product cost. Understanding specific trends in one's own internal data, a company can readily identify problem areas or potential growth opportunities to help increase profitability.

In this discussion, we use an extensive data set to examine how a company might analyze their own data to identify potential changes the company might investigate to drive better performance. Based …

Implementation Of Hierarchical And K-Means Clustering Techniques On The Trend And Seasonality Components Of Temperature Profile Data, Emmanuel Ogedegbe

Electronic Theses and Dissertations

In this study, time series decomposition techniques are used in conjunction with Kmeans clustering and Hierarchical clustering, two well-known clustering algorithms, to climate data. Their implementation and comparisons are then examined. The main objective is to identify similar climate trends and group geographical areas with similar environmental conditions. Climate data from specific places are collected and analyzed as part of the project. The time series is then split into trend, seasonality, and residual components. In order to categorize growing regions according to their climatic inclinations, the deconstructed time series are then submitted to K-means clustering and Hierarchical clustering with dynamic …

Convolution And Autoencoders Applied To Nonlinear Differential Equations, Noah Borquaye

Electronic Theses and Dissertations

Autoencoders, a type of artificial neural network, have gained recognition by researchers in various fields, especially machine learning due to their vast applications in data representations from inputs. Recently researchers have explored the possibility to extend the application of autoencoders to solve nonlinear differential equations. Algorithms and methods employed in an autoencoder framework include sparse identification of nonlinear dynamics (SINDy), dynamic mode decomposition (DMD), Koopman operator theory and singular value decomposition (SVD). These approaches use matrix multiplication to represent linear transformation. However, machine learning algorithms often use convolution to represent linear transformations. In our work, we modify these approaches to …

A Bridge Between Graph Neural Networks And Transformers: Positional Encodings As Node Embeddings, Bright Kwaku Manu

Electronic Theses and Dissertations

Graph Neural Networks and Transformers are very powerful frameworks for learning machine learning tasks. While they were evolved separately in diverse fields, current research has revealed some similarities and links between them. This work focuses on bridging the gap between GNNs and Transformers by offering a uniform framework that highlights their similarities and distinctions. We perform positional encodings and identify key properties that make the positional encodings node embeddings. We found that the properties of expressiveness, efficiency and interpretability were achieved in the process. We saw that it is possible to use positional encodings as node embeddings, which can be …

A Programmatic Geographic Information Systems Analysis Of Plant Hardiness Zones, Andrew Bowen

Electronic Theses and Dissertations

The Plant Hardiness Zone Map consists of thirteen geographical zones that describe whether a plant can survive based on average annual minimal temperatures. As climate change progresses, minimum temperatures in all regions are expected to change. This work programmatically evaluates predicted future climate projection data and converts it to United States Department of Agriculture-defined hardiness zones. Through the next 80 years, hardiness zones are projected to move poleward; in effect, colder zones will lose area and warmer zones will gain area globally. Some implications include changes in crop growing degree days, which could alter crop productivity, migration and settlement of …

Predicting High-Cap Tech Stock Polarity: A Combined Approach Using Support Vector Machines And Bidirectional Encoders From Transformers, Ian L. Grisham

Electronic Theses and Dissertations

The abundance, accessibility, and scale of data have engendered an era where machine learning can quickly and accurately solve complex problems, identify complicated patterns, and uncover intricate trends. One research area where many have applied these techniques is the stock market. Yet, financial domains are influenced by many factors and are notoriously difficult to predict due to their volatile and multivariate behavior. However, the literature indicates that public sentiment data may exhibit significant predictive qualities and improve a model’s ability to predict intricate trends. In this study, momentum SVM classification accuracy was compared between datasets that did and did not …

Unsupervised Dimension Reduction Techniques For Lung Diagnosis Using Radiomics, Janet Kireta

Electronic Theses and Dissertations

Over the years, cancer has increasingly become a global health problem [12]. For successful treatment, early detection and diagnosis is critical. Radiomics is the use of CT, PET, MRI or Ultrasound imaging as input data, extracting features from image-based data, and then using machine learning for quantitative analysis and disease prediction [23, 14, 19, 1]. Feature reduction is critical as most quantitative features can have unnecessary redundant characteristics. The objective of this research is to use machine learning techniques in reducing the number of dimensions, thereby rendering the data manageable. Radiomics steps include Imaging, segmentation, feature extraction, and analysis. For …

Intraday Algorithmic Trading Using Momentum And Long Short-Term Memory Network Strategies, Andrew R. Whitinger Ii

Undergraduate Honors Theses

Intraday stock trading is an infamously difficult and risky strategy. Momentum and reversal strategies and long short-term memory (LSTM) neural networks have been shown to be effective for selecting stocks to buy and sell over time periods of multiple days. To explore whether these strategies can be effective for intraday trading, their implementations were simulated using intraday price data for stocks in the S&P 500 index, collected at 1-second intervals between February 11, 2021 and March 9, 2021 inclusive. The study tested 160 variations of momentum and reversal strategies for profitability in long, short, and market-neutral portfolios, totaling 480 portfolios. …

Finding A Representative Distribution For The Tail Index Alpha, Α, For Stock Return Data From The New York Stock Exchange, Jett Burns

Electronic Theses and Dissertations

Statistical inference is a tool for creating models that can accurately display real-world events. Special importance is given to the financial methods that model risk and large price movements. A parameter that describes tail heaviness, and risk overall, is α. This research finds a representative distribution that models α. The absolute value of standardized stock returns from the Center for Research on Security Prices are used in this research. The inference is performed using R. Approximations for α are found using the ptsuite package. The GAMLSS package employs maximum likelihood estimation to estimate distribution parameters using the CRSP data. The …

Manifold Learning With Tensorial Network Laplacians, Scott Sanders

Electronic Theses and Dissertations

The interdisciplinary field of machine learning studies algorithms in which functionality is dependent on data sets. This data is often treated as a matrix, and a variety of mathematical methods have been developed to glean information from this data structure such as matrix decomposition. The Laplacian matrix, for example, is commonly used to reconstruct networks, and the eigenpairs of this matrix are used in matrix decomposition. Moreover, concepts such as SVD matrix factorization are closely connected to manifold learning, a subfield of machine learning that assumes the observed data lie on a low-dimensional manifold embedded in a higher-dimensional space. Since …

Applying Deep Learning To The Ice Cream Vendor Problem: An Extension Of The Newsvendor Problem, Gaffar Solihu

Electronic Theses and Dissertations

The Newsvendor problem is a classical supply chain problem used to develop strategies for inventory optimization. The goal of the newsvendor problem is to predict the optimal order quantity of a product to meet an uncertain demand in the future, given that the demand distribution itself is known. The Ice Cream Vendor Problem extends the classical newsvendor problem to an uncertain demand with unknown distribution, albeit a distribution that is known to depend on exogenous features. The goal is thus to estimate the order quantity that minimizes the total cost when demand does not follow any known statistical distribution. The …

Data Science And The Ice-Cream Vendor Problem, Makafui Azasoo

Electronic Theses and Dissertations

Newsvendor problems in Operations Research predict the optimal inventory levels necessary to meet uncertain demands. This thesis examines an extended version of a single period multi-product newsvendor problem known as the ice cream vendor problem. In the ice cream vendor problem, there are two products – ice cream and hot chocolate – which may be substituted for one another if the outside temperature is no too hot or not too cold. In particular, the ice cream vendor problem is a data-driven extension of the conventional newsvendor problem which does not require the assumption of a specific demand distribution, thus allowing …

Machine Learning Approaches To Dribble Hand-Off Action Classification With Sportvu Nba Player Coordinate Data, Dembe Stephanos

Electronic Theses and Dissertations

Recently, strategies of National Basketball Association teams have evolved with the skillsets of players and the emergence of advanced analytics. One of the most effective actions in dynamic offensive strategies in basketball is the dribble hand-off (DHO). This thesis proposes an architecture for a classification pipeline for detecting DHOs in an accurate and automated manner. This pipeline consists of a combination of player tracking data and event labels, a rule set to identify candidate actions, manually reviewing game recordings to label the candidates, and embedding player trajectories into hexbin cell paths before passing the completed training set to the classification …