Data Science Commons^™

Generalized Detection Of Animal Behavior Using Accelerometers, Alexander J. Arrieta

Master's Theses

Animal mounted sensors are becoming increasingly used to passively monitor both domestic and wild animals. Advances in lightweight accelerometer and GPS technology have allowed many animals to be fitted with high accuracy sensors for extended periods of time. This leads to new opportunities to study animal behavior without direct observation. However, interpreting the raw data is difficult due to the high volume and missing context of the information. Machine learning techniques excel at extracting information from raw data streams and are excellent candidates for processing the sensor data. However, due to large variance in how different animals execute the same …

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 …

Reverse (Bio)Engineering: A Machine Learning Approach To Optimize Baseball Pitcher Health And Performance, Robert C. Moore

All Dissertations

Ball tracking systems are becoming ubiquitous in sport, creating an unprecedented opportunity for big data applications to optimize human health and performance. These applications are especially common in baseball, a sport known for analyzing ball flight data to quantify performance. Analysts routinely use ball flight data to identify the attributes of top performing pitchers, finding that the best pitchers throw with optimal combinations of release speed and spin to precise locations. However, for certain pitchers, the throwing motion required to produce optimal ball flight places exceedingly high biomechanical load on the elbow, and consequently injury rates continue to rise. This …

Generating Predictive Gene Expression Signatures For Alzheimer's Disease Using Postmortem Brain Tissue, Ashley Duche

Pharmaceutical Sciences (PhD) Dissertations

Background: Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder characterized by the accumulation of amyloid-beta (Aβ) plaques and tau protein aggregates. These pathological features develop in specific brain regions, but why some areas are more vulnerable to early AD-related changes remains unclear. To address this, predictive gene expression signatures were developed to explore the molecular mechanisms underlying regional susceptibility to AD pathology.

Methods: This was performed using postmortem brain (PMB) tissue from participants in the Religious Orders Study and Memory and Aging Project (ROSMAP), Mayo Clinic, and Mount Sinai Brain Bank (MSBB) to generate gene expression signatures from six brain …

An Objective Method To Locate Shear Lines During The Northeast Monsoon Season In The Philippines, Lyndon Mark P. Olaguera, John A. Manalo, Jun Matsumoto, Faye Abigail T. Cruz, Jose Ramon T. Villarin

SOSE Affiliate: Manila Observatory

The shear line is a narrow zone of maximum horizontal wind shear, typically identified as a confluence zone of low-level wind streams. Previous studies showed that this system can trigger heavy to extreme rainfall events in the Philippines during the northeast monsoon season. However, a research gap remains in objectively identifying and locating this system. Thus, this study develops a detection method that may be used for monitoring and forecasting the location of shear lines. Results show that the gradient of meridional winds in the y-direction (∂V925hPa/∂y), the boundary layer moisture flux convergence, and the 925 hPa relative vorticity may …

Mobile Computer Vision Application For Agricultural Disease Detection Of Pepper Diseases Using Two-Stage Deep Learning System, Carlos Jose Estevez, Mai Dang, Ryan Bass

SMU Data Science Review

Plant diseases pose a significant threat to food security, particularly in developing countries where farmers often lack the resources and infrastructure for early detection. In nations like Mexico and the Dominican Republic, the spread of harmful plant diseases impacts key agricultural commodities, such as habanero peppers, leading to substantial yield losses. This study presents a computer vision system based on Convolutional Neural Networks (CNNs) and an object detection model (YOLO) to help farmers detect pepper diseases efficiently. The system uses a two-stage approach: YOLOv11n first detects pepper leaves in images, then a lightweight MobileNetV3Small model classifies whether the detected leaves …

Predicting Simulation Times For Multiphase Thermal-Hydraulic Models, Andrew Yule, Andrew Taylor

SMU Data Science Review

Addressing the challenge of computationally intensive OLGA

simulations in the oil and gas industry, a machine learning framework is

developed for accurate runtime prediction. A specialized feature extraction

pipeline identifies key parameters—such as simulation time, time step,

number of branches, and section count—from OLGA input files that serve as

high-impact predictors. Multiple predictive models, including regression,

tree-based ensembles, and neural networks, are implemented to validate

accuracy and robustness. Results reveal that prioritizing simulations based on

predicted runtimes optimizes licensing resources and reduces operational

costs, making real-time scheduling more efficient. This research demonstrates

the effectiveness of data-driven runtime prediction in enhancing …

Ai-Powered Compliance: Accelerating Efficiency And Decision-Making For Compliance Related Inquiries., Amberly R. Rodriguez

SMU Data Science Review

This research examines the potential of an AI-powered chatbot to streamline compliance workflows by reducing the time and effort required to locate and interpret complex compliance documents. The prototype integrates a centralized MySQL-based document repository, a contextual document querying engine, and a Streamlit web interface, enabling employees to retrieve accurate, document-backed answers within seconds. The system supports both stored and user-uploaded documents, with features such as automated summarization and source citations to enhance transparency and trust. Manual evaluation demonstrated notable gains in efficiency and accuracy compared to traditional search methods, with strong potential to improve adherence to compliance policies. Future …

Ai-Driven Optimization Of Wind Energy Distribution In Texas Using Multi-Agent Reinforcement Learning, Waleed Amer, Owolabi Oluwadamilola, Bassey Ogbonnaya

SMU Data Science Review

Abstract. The integration of large-scale wind power into modern electrical grids presents persistent challenges due to variability, curtailment, and compliance with operational constraints. This study proposes a multi-agent reinforcement learning (MARL) framework for optimizing wind energy distribution within the Texas power grid. The system employs three specialized agents—managing wind curtailment, storage utilization, and load adjustments—to collaboratively balance supply and demand under dynamic grid conditions. Using historical operational data from the Electric Reliability Council of Texas (ERCOT), the framework was trained and evaluated on a range of scenarios encompassing both typical and extreme operating conditions. Results demonstrate substantial performance improvements compared …

A Comparative Time Series Analysis Of The Arima And Temporal Fusion Transformer (Tft) Models, Catherine Ticzon, Aaron Abromowitz, Bivin Sadler

SMU Data Science Review

Several new transformer-based time series models have been developed in the past five years and research has provided evidence of these models’ superior performance compared to classic statistical models such as ARIMA. While transformer-based models show impressive performance on baseline datasets, no research has been done on the robustness of these models on datasets with controlled modifications and in a replicable manner. In this paper, the Temporal Fusion Transformer (TFT) model was compared to the classical statistical model ARIMA on simulated data using multiple horizons. Data were simulated using a linear combination of exogenous variables; in total, 50 realizations of …

Analyzing The Global Happiness Index, Victoria Hernandez, Christy W. Wachira

SMU Data Science Review

This study explores the Global Happiness Index using data compiled from the OECD and Our World in Data to identify key factors contributing to societal well-being. Six primary predictors were analyzed: GDP per capita, social support, healthy life expectancy, freedom to make life choices, generosity, and perceptions of corruption. Regression and clustering techniques were employed to uncover patterns among countries. By expanding the analytical scope beyond conventional economic and social indicators, this study helps identify new pathways for improving well-being across diverse cultural and economic landscapes. Additional variables such as perceived safety, political engagement, and values related to family and …

A Blockchain-Enabled Deep Learning Framework For Secure Omics Data Sharing And Attack Detection, Don Roosan, Md Rahatul Ashakin, Rubyat Kahn, Mazharul Karim

Computer and Data Science Faculty Publications

No abstract provided.

Shape: Spatial Health And Population Estimator, Emma M. Von Hoene, Aanya Gupta, Hamdi Kavak, Amira Roess, Taylor Anderson

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Explainable Post-Operative Patients Recovery Prediction Following Elective Brain Tumor Resection: A Precision Medicine Approach, Eleanor Belkin

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Modeling The Cancer Cell Growth Predictions Based On Classical Mathematical Models With Physics-Informed Neural Network, Widodo Samyono

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Reconstructing Gene Regulatory Networks From Time-Series Data In Knime, Raina Robeva

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Properties Of Liquid Fe-Ni Alloys Under Planetary Core Conditions And Their Geophysical Implications, Sajin Satyal

LSU Doctoral Dissertations

The composition of Earth’s core remains unsolved, yet it carries critical implications for planetary evolution, thermal history, magnetic fields, and habitability. Planetary models derived from seismological observations, such as the Preliminary Reference Earth Model (PREM), indicate that Earth’s core is significantly less dense than pure iron, implying the presence of light elements, including sulfur, carbon, hydrogen, oxygen, and silicon. However, the exact composition and distribution of these elements remain largely unknown. In constraining Earth’s core composition, the density and compressional wave velocity of iron-rich alloys are often compared with seismologically derived models. However, no single iron–light-element alloy can simultaneously reproduce …

[Project Insight] [Foag] Data-Driven Machine Learning Approaches To Modeling Pertussis Vaccine Scare Behavior, Gleb Gribovskii

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Modeling Social Isolation: A Data-Driven Index Function Design And Implementation, Jeremis N. Morales Morales, Carmen Caiseda, Phyllis Muniu, Joshua Atsu, Folashade B. Agusto

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.