Data Science Commons^™

Ai Project Facilitation Guidance For Research Computing And Data (Rcd) Professionals, Anna Alber, Laura Briggs, Paul Brunk, Manasvita Joshi, Atish P. Kamble, Amira Kefi, Timothy Middelkoop, Semir Sarajlic, Ana Maria Sokovic, Jeffrey N. Valdez, Ying Zhang

Administration and Staff Articles and Research

The role of Artificial Intelligence (AI) in research and education continues to rapidly grow, resulting in increased collaboration between researchers in AI and Research Computing and Data (RCD) professionals to meet the research and teaching demands. RCD professionals bridge the gap between research and technology by guiding and collaborating with researchers and educators through the process of selecting the hardware, software, and services best suited for executing their AI projects. This includes ensuring compliance with funding and regulatory requirements across the entire lifecycle of the project. In this paper, we present an overview of the AI project lifecycle and how …

Towards Leveraging Social Media Data For Fostering Collaborations Among Non-Profits, Monazil Chowdhury

LSU Doctoral Dissertations

Nonprofit organizations serve a crucial role in tackling a wide range of significant social, environmental, and economic issues. But it is often hard to get a clear picture of their work because their information is spread out and it is difficult to see how they are collaborating. To address this issue we developed a web-based tool to collect scattered data—from a variety of sources, such as the IRS, social media, and the Census, into one easy-to-use resource. The tool begins by taking IRS records and geocoding each nonprofit’s physical address With its coordinates. It then retrieves census tract information from …

A Study Of Machine Learning Techniques In Solving Biochemical And Chemical Problems, Kenneth Micheal Plackowski

Chemistry and Chemical Biology ETDs

Data-driven approaches to solving problems in biology and chemistry require utilization of reliable techniques and machine learning algorithms are the modern reliable approach. This work presents three problems that involve use of supervised learning techniques when classification is the goal and unsupervised learning techniques when global data representation is the goal.

In the first problem, we demonstrate the use of unsupervised clustering techniques, self-organizing maps and K-means, to ascertain analyte detection capabilities of carbon nitride dots. In the second problem, we add scalability features to a functional group classification model applied to infrared data and evaluate its ability to inform …

Seeking Structure In Complex Systems: From Feature Analysis To Space-Time Causal Discovery With Earth Science Applications, Jeffrey J. Nichol

Computer Science ETDs

Complex systems are difficult to study because of their many interacting parts, emergent phenomena, and feedback loops. These systems underpin all life on Earth. We need improved tools for seeking an understanding of them. This body of research presents my investigations into data-driven methods for understanding complex systems, including my invention of a novel causal discovery meta-algorithm for space-time gridded data. I demonstrated machine learning feature importance and causal discovery capabilities for comparing simulated and observed climate data. I developed a new benchmark for modeling space-time dynamics of locally driven phenomena and examined a prominent causal discovery algorithm. Finding that …

Modifications To The Spiral Array: A Computational Approach To Music Analysis, Rose Bittle

DePaul Discoveries

The Spiral Array is a geometric model of musical tonality and exists as a tool in computer-aided music analysis. The model was first published in 2000 by Elaine Chew, PhD, in her thesis, Towards a Mathematical Model of Tonality. This project aimed to restructure the Spiral Array, limiting user ambiguity and optimizing the application of musical key finding. The existing model defines pitch, chord, and key location to form a series of spirals dependent on a set of flexible weights. In our research we were able to identify potential issues with the pitch definitions themselves and experiment with methods …

Modeling, Analysis, And Prediction Of Covid-19 Dynamics With Interacting Subpopulations And Implicit Behavior Using Physics-Informed Neural Networks, Naima Aubry-Romero, Alonso Ogueda-Oliva, Padmanabhan Seshaiyer

Spora: A Journal of Biomathematics

In this paper, we consider an extended SEIR compartmental model that incorporates young and old interacting subpopulations, allowing for cross-group transmission dynamics. Implicit behavioral changes are included to determine the influence of social behavior on coronavirus transmission dynamics. The basic reproduction number, the average number of secondary cases of infection produced by a single primary case, is derived for both the explicit and implicit model using the next-generation matrix method. We solve the associated differential equation systems and estimate useful parameters in the explicit model using physics-informed neural networks (PINNs). Our results point to how the PINNs approach offers an …

3d Solid Models, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

3D solid models for model vehicles, target panels, objects, and the desert terrain model in STL file format.

Ground Truth Images, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Laboratory and scenario ground truth images for the Model Desert Terrain Monochromatic DoT dataset.

Polarimetric Data: Scenario 01, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Polarimetric data Scenario 01 collected within the Automated Remote Sensing Solar Simulation Lab at the University of Dayton. The data were collected using a visible monochromatic division-of-time imaging polarimeter. The dataset is parameterized across different sensor, scene, and illumination geometries that mimic outdoor solar irradiance conditions.

Dataset Description, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Polarimetric dataset containing data collected within the Automated Remote Sensing Solar Simulation Lab at the University of Dayton. The data were collected using a visible monochromatic division-of-time imaging polarimeter. A model desert terrain model was constructed and imaged for eight different scenarios consisting of different model panel and vehicle targets. The dataset is parameterized across different sensor, scene, and illumination geometries that mimic outdoor solar irradiance conditions.

Use Of High-Throughput Phenomics With And Without Fungicide As A Wheat Breeding Tool, Gerardo Ivan Rivera Collazo

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Wheat (Triticum aestivum) is an important food staple for many countries around the world and current consumption and production data demonstrate a production deficit. Breeders are challenged to help close this gap in production by selecting better cultivars with improved yields. Several methods aim to accelerate the breeding process to reduce the time required for releasing an elite variety. One of the main breeding bottlenecks is the lack of fast and reliable phenotypic data acquisition that could dissect physiological and morphological plant data. High-throughput remote sensing could have the potential to reduce this bottleneck by streamlining data acquisition, …

Measuring How Much Judges Matter For Case Outcomes, Ryan W. Copus, Ryan Hübert

Faculty Works

A large empirical literature examines how judges’ traits affect how cases get resolved. This literature has led many to conclude that judges matter for case outcomes. But how much do they matter? Existing empirical findings understate the true extent of judicial influence over case outcomes since standard estimation techniques hide some disagreement among judges. We devise a machine learning method to reveal additional sources of disagreement. Applying this method to the Ninth Circuit, we estimate that at least 38% of cases could be decided differently based solely on the panel they were assigned to.

From Disruption To Integration: Cryptocurrency Prices, Financial Fluctuations, And Macroeconomy, Zhengyang Chen

Faculty Publications

This paper examines cryptocurrency shock transmission to financial markets and the macroeconomy using a Bayesian structural VAR with Pandemic Priors from 2015 to 2024. By affecting overall risk appetite, cryptocurrency price shocks generate positive financial market spillovers, accounting for 18% of equity and 27% of commodity price fluctuations. Real economic effects are significant in driving investment but remain limited, contributing only 4% to unemployment and 6% to industrial production variance. However, cryptocurrency shocks explain 18% of price-level forecast error variance at long horizons. Narrative analysis reveals sentiment and technology as primary shock drivers. These findings demonstrate cryptocurrency's deep financial system …

Data Annotations, Bradley M. Ratliff

Model Desert Terrain Monochromatic DoT Dataset

Pixel-wise object masks for each polarimetric scene in ASL file format for the Model Desert Terrain Monochromatic DoT data.

Quantum Analysis Of Protein–Ligand Binding By Integrating Structural Resolution, Sequence Homology, And Ligand Properties, Don Roosan, Samira Samrose, Rubayat Khan, Saif Nirzhor, Brian Provencher

Computer and Data Science Faculty Publications

Predicting protein–ligand binding affinity is a fundamental challenge in computational biology and drug discovery, complicated by diverse factors including protein sequence variability, ligand chemical diversity, and structural resolution. Here, we present an integrative study that combines classical machine learning and quantum-enhanced modeling to investigate how crystal structure resolution, sequence similarity, and ligand properties jointly influence binding affinity. Using a curated “refined” dataset from PDBbind and an expanded general dataset, we first conduct correlation and regression analyses to quantify the relationships among binding affinity, ligand descriptors (e.g., molecular weight, logP), and protein structural metrics (resolution, R-factor). We observe moderate positive correlations …

Comparing Methods For Glomerular Filtration Rate Estimation, Xiaoqian Zhu, Tariq Shafi, Keith Norris, Jeannette Simino, Srishti Shrestha, Thomas H. Mosley, Michael E. Griswold, Seth T. Lirette

Data Science Publications

Background: The glomerular filtration rate (GFR), estimated from serum creatinine (SCr), is widely used in clinical practice for kidney function assessment, but SCr-based equations are limited by non-GFR determinants and may introduce inaccuracies across racial groups. Few studies have evaluated whether advanced modeling techniques enhance their performance. Methods: Using multivariable fractional polynomials (MFP), generalized additive models (GAM), random forests (RF), and gradient boosted machines (GBM), we developed four SCr-based GFR-estimating equations in a pooled data set from four cohorts (n = 4665). Their performance was compared to that of the refitted linear regression-based 2021 CKD-EPI SCr equation using bias (median …

Enhancing Biosecurity In Tamper-Resistant Large Language Models With Quantum Gradient Descent, Fahmida Hai, Saif Nirzhor, Rubayat Khan, Don Roosan

Computer and Data Science Faculty Publications

This paper introduces a tamper-resistant framework for large language models (LLMs) in medical applications, utilizing quantum gradient descent (QGD) to detect malicious parameter modifications in real time. Integrated into a LLaMA-based model, QGD monitors weight amplitude distributions, identifying adversarial fine-tuning anomalies. Tests on the MIMIC and eICU datasets show minimal performance impact (accuracy: 89.1 to 88.3 on MIMIC) while robustly detecting tampering. PubMedQA evaluations confirm preserved biomedical question-answering capabilities. Compared to baselines like selective unlearning and cryptographic fingerprinting, QGD offers superior sensitivity to subtle weight changes. This quantum-inspired approach ensures secure, reliable medical AI, extensible to other high-stakes domains.

A Modern Approach To Classifying Medieval Latin Scripts, Robert L. Lane Jr, Rafia Mirza, Robert Slater

SMU Data Science Review

Paleography, the study of historical handwriting, is essential for preserving societal understanding of cultural, social, and legal frameworks from the past. Medieval manuscripts, often exhibiting refined craftsmanship, present unique challenges to modern readers due to differences in handwriting conventions and the absence of standardized punctuation and spaces. These texts hold valuable insights into the evolution of written communication, literacy, and language development. However, interpreting them requires specialized knowledge and technological solutions. Convolutional Neural Networks (CNNs) can be leveraged to classify scripts, an important step in Historical Document analysis. These models extract and analyze hierarchical features from images, addressing inconsistencies in …

Enhancing News Article Generation With Ai Tools, Adam Ercanbrack, Christopher Johnson, Max Pagan, Nibhrat Lohia

SMU Data Science Review

Abstract. This paper aims to present a comparative analysis of a custom-built AI Journalist Assistant and ChatGPT 4.0 for news article generation. The goal is to evaluate the performance of each model based on accuracy, speed, ethical safeguards, and relevance, particularly in the context of journalism. While ChatGPT is widely used for general-purpose content creation, its reliance on older data and potential for plagiarism presents challenges in the fast-paced, high-stakes world of news reporting. To address these issues, we will design and implement an AI Assistant using Retrieval-Augmented Generation (RAG) techniques, focusing on real-time data access, bias reduction, and plagiarism …

Predictive Modeling Of Colorectal Cancer Risk: Leveraging Health, Demographic, And Socioeconomic Factors For Targeted Screening, Anish Bhandari, Shawn Deng, Michael Olheiser, Robert Slater

SMU Data Science Review

Colorectal cancer (CRC) remains a significant public health concern, affecting millions in the United States and worldwide. This study investigates the risk factors associated with CRC using data from the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial and aims to develop predictive models to identify high-risk individuals for targeted screening and increased awareness. The dataset integrates CRC incidence data from the National Cancer Institute with socioeconomic indicators from U.S. Census Bureau, linked by zip code. We employ Logistic Regression and Neural Network models to predict CRC risk, incorporating health, demographic, and socio-economic features. While the results suggest that …