Data Science Commons^™

Statins Are Rarely Prescribed For Incidentally Discovered Covert Cerebrovascular Disease: A Retrospective Cohort In A Large Electronic Health Record (Ehr) Identified Using Natural Language Processing, Sunyang Fu, Chengyi X Zheng, Hongfang Liu, Wansu Chen, David M Kent

Faculty, Staff and Student Publications

Introduction: While incidentally discovered covert cerebrovascular diseases (id-CCD) are associated with future stroke, it is not known if patients with id-CCD are prescribed statins.

Methods: Patients age ≥50 with id-CCD on neuroimaging from 2009 to 2019 with no prior ischaemic stroke, transient ischaemic attack or dementia were identified using natural language processing in a large real-world cohort. Robust Poisson multivariable regression was used to assess statin prescription among patients without prior statins.

Results: Among 2 41 050 patients, 74 975 patients (31.1%; 4.7% with covert brain infarcts (CBI); 29.0% with white matter disease (WMD)) had id-CCD. 53.5% (95% CI 53.2 …

The Enact Network Is Acting On Housing Instability And The Unhoused Using The Open Health Natural Language Processing Toolkit, Darren Henderson, Jordan Hilsman, David Oniani, Yanshan Wang

Faculty, Staff and Student Publications

Housing is an environmental social determinant of health that is linked to mortality and clinical outcomes. We developed a lexicon of housing-related concepts and rule-based natural language processing methods for identifying these housing-related concepts within clinical text. We piloted our methods on several test cohorts: a synthetic cohort generated by ChatGPT for initial infrastructure testing, a cohort with substance use disorders (SUD), and a cohort diagnosed with problems related to housing and economic circumstances (HEC). Our methods successfully identified housing concepts in our ChatGPT notes (recall = 1.0, precision = 1.0), our SUD population (recall = 0.9798, precision = 0.9898), …

Preparing Healthcare Education For An Ai-Augmented Future

Faculty, Staff and Student Publications

Artificial intelligence (AI) fundamentally transforms healthcare education as a knowledge enterprise, creating a distributed cognitive system composed of the human brain, which remains relatively unchanged, and AI-based knowledge and cognitive functions, which have accelerated exponentially in scale and power. Education must focus on developing skills to collaborate with AI and on achieving outcomes like problems solved and discoveries made. Curriculum and education policies also need to adapt to this transformation.

Descriptor:Benchmarking Secure Neural Network Evaluation Methods For Protein Sequence Classification (Idash24)

Faculty, Staff and Student Publications

To uniformly test and benchmark the secure evaluation of transformer-based models, we designed the iDASH24 homomorphic encryption track dataset. The dataset comprises a protein family classification model with a transformer architecture and an example dataset that is used to build and test the secure evaluation strategies. This dataset was used in the challenge period of iDASH24 Genomic Privacy Competition, where the teams designed secure evaluation of the classification model using a homomorphic encryption scheme. Combined with the benchmarking results and companion methods, iDASH24 dataset is a unique resource that can be used to benchmark secure evaluation of neural network models.

A Transformer-Based Deep Learning Approach For Fairly Predicting Post-Liver Transplant Risk Factors

Faculty, Staff and Student Publications

Liver transplantation is a life-saving procedure for patients with end-stage liver disease. There are two main challenges in liver transplant: finding the best matching patient for a donor and ensuring transplant equity among different subpopulations. The current MELD scoring system evaluates a patient's mortality risk if not receiving an organ within 90 days. However, the donor-patient matching should also consider post-transplant risk factors, such as cardiovascular disease, chronic rejection, etc., which are all common complications after transplant. Accurate prediction of these risk scores remains a significant challenge. In this study, we used predictive models to solve the above challenges. Specifically, …

Teaching Analytics Online: A Self-Study Of Professional Practice, Andrew J. Collins, Brandon Butler, James F. Leathrum Jr., Christopher J. Lynch

Engineering Management & Systems Engineering Faculty Publications

As the COVID-19 pandemic caused severe disruption to education enterprises throughout the world, the main response by educational institutions was to move to online learning environments. The purpose of this study was to understand better how instructors could improve online learning for a professional-level week-long short course in a highly technical area (data analytics), which had, pre-COVID, been a hands-on computer, laboratory-based learning experience. The authors used self-study of professional practice to elicit and understand the major issues and concerns of the transition to an online learning environment. Under the guidance of a colleague in teacher education, three course instructors …

Methods That Support The Validation Of Agent-Based Models: An Overview And Discussion, Andrew Collins, Matthew Koehler, Christopher Lynch

Engineering Management & Systems Engineering Faculty Publications

Validation is the process of determining if a model adequately represents the system under study for the model’s intended purpose. Validation is a critical component in building the credibility of a simulation model with its end-users. Effectively conducting validation can be a daunting task for both novice and experienced simulation developers. Further compounding the difficult task of conducting validation is that there is no universally accepted approach for assessing a simulation. These challenges are particularly relevant to the paradigm of Agent-Based Modeling and Simulation (ABMS) because of the complexity found in these models’ mechanisms and in the real-world situations they …

Data Driven Trade-Off Analysis For Cybersecurity, Goskel Kucukkaya, Murat Ozer, Murat Balci, Emrah Ugurlu

Engineering Management & Systems Engineering Faculty Publications

Trade-off analysis, a specialization of systems engineering, addresses design criteria like security, cost, performance, and compliance. Monte Carlo simulations are commonly employed to generate impact scenarios for trade-off analysis combined with solution alternatives that accommodate industry-specific considerations and uncertainties. In the cyber domain, this paper proposes a methodology for data-driven trade-off analysis in cybersecurity, leveraging industry reports as primary data sources using confidentiality, integrity, and availability as trade-off analysis objectives. Distribution functions are derived to manage and model uncertainties for various industries. The approach given in this study aims to facilitate informed choices and to enhance cybersecurity decision making and …

A Copula Discretization Of Time Series-Type Model For Examining Climate Data, Dimuthu Fernando, Olivia Atutey, Norou Diawara

Mathematics & Statistics Faculty Publications

The study presents a comparative analysis of climate data under two scenarios: a Gaussian copula marginal regression model for count time series data and a copula-based bivariate count time series model. These models, built after comprehensive simulations, offer adaptable autocorrelation structures considering the daily average temperature and humidity data observed at a regional airport in Mobile, AL.

Understaning Low Vision Graphical Perception Of Bar Charts, Yash Prakash, Akshay Kolgar Nayak, Sampath Jayarathna, Hae-Na Lee, Vikas Ashok

Computer Science Faculty Publications

Bar charts are widely used for their simplicity in data representation, prompting numerous studies to explore and model how users interact with and perceive bar chart information. However, these studies have predominantly focused on sighted users, with a few also targeting blind screen-reader users, whereas the graphical perception of low-vision screen magnifier users is still an uncharted research territory. We fill this knowledge gap in this paper by designing four experiments for a laboratory study with 25 low-vision participants to examine their graphical perception while interacting with bar charts. For our investigation, we built a custom screen magnifier-based logger that …

Improving Usability Of Data Charts In Multimodal Documents For Low Vision Users, Yash Prakash, Akshay Kolgar Nayak, Shoaib Mohammed Alyaan, Pathan Aseef Khan, Hae-Na Lee, Vikas Ashok

Computer Science Faculty Publications

Data chart visualizations and text are often paired in news articles, online blogs, and academic publications to present complex data. While chart visualizations offer graphical summaries of the data, the accompanying text provides essential context and explanation. Associating information from text and charts is straightforward for sighted users but presents significant challenges for individuals with low vision, especially on small-screen devices such as smartphones. The visual nature of charts coupled with the layout of the text inherently makes it difficult for low vision users to mentally associate chart data with text and comprehend the content due to their dependence on …

Enhancing Flight Delay Predictions Using Network Centrality Measures, Joseph Ajayi

College of Graduate Studies: Theses & Dissertations

Accurate prediction of flight delays remains a formidable challenge within the aviation industry, owing to its inherent complexity and the interconnectivity of its operations. Traditional flight prediction methods frequently utilize meteorological conditions—such as temperature, humidity, and dew point—alongside flight-specific data like departure and arrival times. However, these predictors often fall short of capturing the nuanced dynamics that lead to delays. This thesis introduces network centrality measures as novel predictors for enhancing the binary classification of flight arrival delays. Furthermore, it emphasizes the application of tree-based ensemble models, which are recognized for their superior ability to model complex relationships compared to …

Classification In Supervised Statistical Learning With The New Weighted Newton-Raphson Method, Toma Debnath

College of Graduate Studies: Theses & Dissertations

In this thesis, the Weighted Newton-Raphson Method (WNRM), an innovative optimization technique, is introduced in statistical supervised learning for categorization and applied to a diabetes predictive model, to find maximum likelihood estimates. The iterative optimization method solves nonlinear systems of equations with singular Jacobian matrices and is a modification of the ordinary Newton-Raphson algorithm. The quadratic convergence of the WNRM, and high efficiency for optimizing nonlinear likelihood functions, whenever singularity in the Jacobians occur allow for an easy inclusion to classical categorization and generalized linear models such as the Logistic Regression model in supervised learning. The WNRM is thoroughly investigated …

Performing Holt-Winters Time Series Forecasting Using Neural Network Based Models, Kazeem Olanrewaju Bankole

College of Graduate Studies: Theses & Dissertations

We show how to create Artificial Neural Network based models for performing the well- known Holt-Winters time series analysis. Our work fares well compared to the well-known Holt-Winter time series prediction method while avoiding the burden of searching for the parameters of the model. We present the theoretical justification of the connection between the two models and experimental results showing the similarities of these models

Data Driven And Machine Learning Based Modeling And Predictive Control Of Combustion At Reactivity Controlled Compression Ignition Engines, Behrouz Khoshbakht Irdmousa

Dissertations, Master's Theses and Master's Reports

Reactivity Controlled Compression Ignition (RCCI) engines operates has capacity to provide higher thermal efficiency, lower particular matter (PM), and lower oxides of nitrogen (NOx) emissions compared to conventional diesel combustion (CDC) operation. Achieving these benefits is difficult since real-time optimal control of RCCI engines is challenging during transient operation. To overcome these challenges, data-driven machine learning based control-oriented models are developed in this study. These models are developed based on Linear Parameter-Varying (LPV) modeling approach and input-output based Kernelized Canonical Correlation Analysis (KCCA) approach. The developed dynamic models are used to predict combustion timing (CA50), indicated mean effective pressure (IMEP), …

Identifying And Predicting Patterns Of Snowpack Ripening With Machine Learning Methods, Clement Cherblanc

Graduate Student Theses, Dissertations, & Professional Papers

The timing of water release from the snowpack plays key roles in ecosystem services, groundwater recharge, and water resource management. However, two internal barriers in a standing snowpack must be overcome before runoff can outflow from the base: 1) the cold content must be exhausted, and 2) the interconnected network of snow grains must be filled with liquid water to residual saturation. Expressing the liquid water as latent heat allows the two barriers to be grouped as an energy (J/m²) to define a snowpack’s Runoff Energy Hurdle (REH). The growth and loss of REH is driven by evolution of pore …

Transformer-Enabled Deep Reinforcement Learning For Coverage Path Planning, Daniel B. Tiu

UNF Graduate Theses and Dissertations

Coverage path planning (CPP) is the problem of covering all points in an environment and is a well-researched topic in robotics due to its sheer practical relevance. This paper investigates such an offline CPP problem where the primary objective is to minimize the path length to achieve complete coverage. Furthermore, the literature suggests that taking turns leads to a higher energy use than going straight. To this end, we design a novel objective function that aims to minimize the number of turns as well. We have proposed a deep reinforcement learning (DRL)-based framework that uses a Transformer model. Unlike state-of-the-art …

A Clustering-Based Approached To Analyze Impacts Of Digital Divide On Undercounting Issues In Census In Florida, Partha Protim Datta

UNF Graduate Theses and Dissertations

According to the US Census Bureau 2020 data, Florida is one of the six states where the population was undercounted. The census in the US is conducted every ten years and plays a pivotal role in shaping government representation, resource allocation, policy making and federal assistance distribution. Consequently, undercounting of population impacts demographic equality, potentially leading to inequitable distribution of resources. The state of Florida will lose billions of dollars by the end of the decade due to this undercounting issue. So, it is an important task to find the proper reason and sources of undercounting in Florida. The US …

Editorial: Artificial Intelligence, Machine Learning, And Data-Mining Techniques To Increase Cost-Effectiveness In Healthcare., P Wilner Jeanty, Marie-Rachelle Narcisse, Romain Crastes Dit Sourd

Ambulatory and Primary Care Articles

No abstract provided.

Self-Exciting Point Processes In Real Estate, Ian Fraser

Theses and Dissertations (Comprehensive)

This thesis introduces a novel approach to analyzing residential property sales through the lens of stochastic processes by employing point processes. Herein, property sales are treated as point patterns, using self-exciting point process models and a variety of statistical tools to uncover underlying patterns in the data. Key findings include the identification and explanation of clustering in both space and time, and the efficacy of a temporal Hawkes process with a sinusoidal background in predicting home sale occurrences. The temporal analysis starts by employing the state of art techniques for time series data like regression, autoregressive, and autoregressive integrated moving …