Physical Sciences and Mathematics Commons^™

Beyond Machine Learning: An Fmri Domain Adaptation Model For Multi-Study Integration, Lauryn Michelle Burleigh

LSU Doctoral Dissertations

Traditional machine learning analyses are challenging with functional magnetic
resonance imaging (fMRI) data, not only because of the amount of data that needs to be
collected, adding a particular challenge for human fMRI research, but also due to the change in
hypothesis being addressed with various analytical techniques. Domain adaptation is a type of
transfer learning, a step beyond machine learning which allows for multiple related, but not
identical, data to contribute to a model, can be beneficial to overcome the limitation of data
needed but may address different hypothesis questions than anticipated given the analysis
computation. This dissertation assesses …

Using Physics-Informed Neural Networks For Multigrid In Time Coarse Grid Equations, Jonathan P. Gutierrez

Mathematics & Statistics ETDs

For parallel-in-time integration methods, the multigrid-reduction-in-time (MGRIT) method has shown promising results in both improved convergence and increased computational speeds when solving evolution problems. However, one problem the MGRIT algorithm currently faces is it struggles solving hyperbolic problems efficiently. In particular, hyperbolic problems are generally solved using explicit methods and this causes issues on the coarser multigrid levels, where larger (coarser) time step sizes can violate the stability condition. In this thesis, physics-informed neural networks (PINNs) are used to evaluate the coarse grid equations in the MGRIT algorithm with the goal to improve convergence for problems with hyperbolic behavior, as …

Integrating And Optimizing Genomic, Weather, And Secondary Trait Data For Multiclass Classification, Vamsi Manthena, Diego Jarquín, Reka Howard

Department of Statistics: Faculty Publications

Modern plant breeding programs collect several data types such as weather, images, and secondary or associated traits besides the main trait (e.g., grain yield). Genomic data is high-dimensional and often over-crowds smaller data types when naively combined to explain the response variable. There is a need to develop methods able to effectively combine different data types of differing sizes to improve predictions. Additionally, in the face of changing climate conditions, there is a need to develop methods able to effectively combine weather information with genotype data to predict the performance of lines better. In this work, we develop a novel …

Statistical Analysis Of Ribonucleotide Incorporation In Human Cells, Tejasvi Channagiri

USF Tampa Graduate Theses and Dissertations

During the DNA replication process, ribonucleotides, the building blocks of RNA, may be occasionally incorporated in the newly synthesized DNA. DNA is primarily composed of deoxyribonucleotides and there exist cellular mechanisms for removing ribonucleotides from DNA, which may point towards ribonucleotide incorporation being a replication error. Further, an excess of these ribonucleotides in the genome has been known to lead to genomic instability and has been implicated in human diseases. However, there are also hypotheses that suggest that ribonucleotides may be beneficial in certain circumstances. In this study we examine ribonucleotide incorporation in the human genome in several human cell …

The Effects Of Demographics And Risk Factors On The Morphological Characteristics Of Human Femoropopliteal Arteries, Sayed Ahmadreza Razian, Majid Jadidi, Alexey Kamenskiy

UNO Student Research and Creative Activity Fair

Background: Disease of the lower extremity arteries (Peripheral Arterial Disease, PAD) is associated with high morbidity and mortality. During disease development, the arteries adapt by changing their diameter, wall thickness, and residual deformations, but the effects of demographics and risk factors on this process are not clear.

Methods: Superficial femoral arteries from 736 subjects (505 male, 231 female, 12 to 99 years old, average age 51±17.8 years) and the associated demographic and risk factor variables were used to construct machine learning (ML) regression models that predicted morphological characteristics (diameter, wall thickness, and longitudinal opening angle resulting from the …

Fraud Pattern Detection For Nft Markets, Andrew Leppla, Jorge Olmos, Jaideep Lamba

SMU Data Science Review

Non-Fungible Tokens (NFTs) enable ownership and transfer of digital assets using blockchain technology. As a relatively new financial asset class, NFTs lack robust oversight and regulations. These conditions create an environment that is susceptible to fraudulent activity and market manipulation schemes. This study examines the buyer-seller network transactional data from some of the most popular NFT marketplaces (e.g., AtomicHub, OpenSea) to identify and predict fraudulent activity. To accomplish this goal multiple features such as price, volume, and network metrics were extracted from NFT transactional data. These were fed into a Multiple-Scale Convolutional Neural Network that predicts suspected fraudulent activity based …

Self-Learning Algorithms For Intrusion Detection And Prevention Systems (Idps), Juan E. Nunez, Roger W. Tchegui Donfack, Rohit Rohit, Hayley Horn

SMU Data Science Review

Today, there is an increased risk to data privacy and information security due to cyberattacks that compromise data reliability and accessibility. New machine learning models are needed to detect and prevent these cyberattacks. One application of these models is cybersecurity threat detection and prevention systems that can create a baseline of a network's traffic patterns to detect anomalies without needing pre-labeled data; thus, enabling the identification of abnormal network events as threats. This research explored algorithms that can help automate anomaly detection on an enterprise network using Canadian Institute for Cybersecurity data. This study demonstrates that Neural Networks with Bayesian …

Federated Learning Framework Integrating Refined Cnn And Deep Regression Forests, Daniel Nolte, Omid Bazgir, Souparno Ghosh, Ranadip Pal

Department of Statistics: Faculty Publications

Predictive learning from medical data incurs additional challenge due to concerns over privacy and security of personal data. Federated learning, intentionally structured to preserve high level of privacy, is emerging to be an attractive way to generate cross-silo predictions in medical scenarios. However, the impact of severe population-level heterogeneity on federated learners is not well explored. In this article, we propose a methodology to detect presence of population heterogeneity in federated settings and propose a solution to handle such heterogeneity by developing a federated version of Deep Regression Forests. Additionally, we demonstrate that the recently conceptualized REpresentation of Features as …

Federated Learning Framework Integrating Refined Cnn And Deep Regression Forests, Daniel Nolte, Omid Bazgir, Souparno Ghosh, Ranadip Pal

Department of Statistics: Faculty Publications

Predictive learning from medical data incurs additional challenge due to concerns over privacy and security of personal data. Federated learning, intentionally structured to preserve high level of privacy, is emerging to be an attractive way to generate cross-silo predictions in medical scenarios. However, the impact of severe population-level heterogeneity on federated learners is not well explored. In this article, we propose a methodology to detect presence of population heterogeneity in federated settings and propose a solution to handle such heterogeneity by developing a federated version of Deep Regression Forests. Additionally, we demonstrate that the recently conceptualized REpresentation of Features as …

Fuzzy Kc Clustering Imputation For Missing Not At Random Data, Markku A. Malmi Jr.

USF Tampa Graduate Theses and Dissertations

Research has a variety of difficulties, especially when involving human subjects, and one of the most prevalent is the issue of missing data. Missing data will always be present in research due to the fact there is no perfect method for collecting data and protecting against human error or mechanical failure. This requires researchers to be able to mitigate the problems that come along with missing data; reduction in power of an analysis and bias introduced by the missing pattern. This research investigated a non-parametric method using a nested approach of fuzzy K-Modes and fuzzy C-Means clustering to impute missing …

On Characterization Of The Exponential Distribution Via Hypoexponential Distributions, George Yanev

School of Mathematical and Statistical Sciences Faculty Publications and Presentations

The sum of independent, but not necessary identically distributed, exponential random variables follows a hypoexponential distribution. We focus on a particular case when all but one rate parameters of the exponential variables are identical. This is known as exponentially modified Erlang distribution in molecular biology. We prove a characterization of the exponential distribution, which complements previous characterizations via hypoexponential distribution with all rates different from each other.

A Chairpersons Guide To Managing Time And Stress, Christian K. Hansen

Academic Chairpersons Conference Proceedings

In this interactive workshop we discuss time and stress management specifically from the perspective of a department chairperson responsible for leading an academic department through numerous internal and external challenges. The focus will be on practical strategies for effective use of time, not only at a personal level, but also at a department wide level.

Strong Recovery In Group Synchronization, Bradley Stich

Rose-Hulman Undergraduate Mathematics Journal

The group synchronization problem is to estimate unknown group elements at the vertices of a graph when given a set of possibly noisy observations of group differences at the edges. We consider the group synchronization problem on finite graphs with size tending to infinity, and we focus on the question of whether the true edge differences can be exactly recovered from the observations (i.e., strong recovery). We prove two main results, one positive and one negative. In the positive direction, we prove that for a sequence of synchronization problems containing the complete digraph along with a relatively well behaved prior …

Error Analysis Of A Fully Discrete Projection Method For Magnetohydrodynamic System, Qianqian Ding, Xiaoming He, Xiaonian Long, Shipeng Mao

Mathematics and Statistics Faculty Research & Creative Works

In this paper, we develop and analyze a finite element projection method for magnetohydrodynamics equations in Lipschitz domain. A fully discrete scheme based on Euler semi-implicit method is proposed, in which continuous elements are used to approximate the Navier–Stokes equations and H(curl) conforming Nédélec edge elements are used to approximate the magnetic equation. One key point of the projection method is to be compatible with two different spaces for calculating velocity, which leads one to obtain the pressure by solving a Poisson equation. The results show that the proposed projection scheme meets a discrete energy stability. In addition, with the …

Error Analysis Of A Fully Discrete Projection Method For Magnetohydrodynamic System, Qianqian Ding, Xiaoming He, Xiaonian Long, Shipeng Mao

Mathematics and Statistics Faculty Research & Creative Works

In this paper, we develop and analyze a finite element projection method for magnetohydrodynamics equations in Lipschitz domain. A fully discrete scheme based on Euler semi-implicit method is proposed, in which continuous elements are used to approximate the Navier–Stokes equations and H(curl) conforming Nédélec edge elements are used to approximate the magnetic equation. One key point of the projection method is to be compatible with two different spaces for calculating velocity, which leads one to obtain the pressure by solving a Poisson equation. The results show that the proposed projection scheme meets a discrete energy stability. In addition, with the …

Socioeconomic Factors In The Diagnosis And Treatment Of Malignant Melanoma In Hispanic Vs. Non-Hispanic Patients: A National Cancer Database (Ncdb) Study, Julia Griffin, Sarah J. Aurit, Timothy Malouff, Peter Silberstein

Department of Statistics: Faculty Publications

Background: The incidence of melanoma is rapidly increasing in the United States. There is a paucity of research of how melanoma affects the Hispanic population, the quickest growing population.

Objective: To identify and understand how socioeconomic factors affect a Hispanic patients health outcome and treatment of malignant melanoma with comparisons to white, non-Hispanic (WNH) patients.

Methods: A retrospective study utilizing the National Cancer Database (NCDB) was completed investigating Hispanic patients (n=2282) and WNH patients (n=190,469) with Stage I-IV malignant melanoma. Outcome and socioeconomic variables were identified and compared across groups. Data was analyzed with SPSS and SAS …

Estimating The Prevalence Of Two Or More Diseases Using Outcomes From Multiplex Group Testing, Md S. Warasi, Joshua M. Tebbs, Christopher S. Mcmahan, Christopher R. Bilder

Department of Statistics: Faculty Publications

When screening a population for infectious diseases, pooling individual specimens (e.g., blood, swabs, urine, etc.) can provide enormous cost savings when compared to testing specimens individually. In the biostatistics literature, testing pools of specimens is commonly known as group testing or pooled testing. Although estimating a population-level prevalence with group testing data has received a large amount of attention, most of this work has focused on applications involving a single disease, such as human immunodeficiency virus. Modern methods of screening now involve testing pools and individuals for multiple diseases simultaneously through the use of multiplex assays. Hou et al. (2017, …

Penguins Go Parallel: A Grammar Of Graphics Framework For Generalized Parallel Coordinate Plots, Susan Vanderplas, Yawei Ge, Antony Unwin, Heike Hofmann

Department of Statistics: Faculty Publications

Parallel Coordinate Plots (PCP) are a valuable tool for exploratory data analysis of high-dimensional numerical data. The use of PCPs is limited when working with categorical variables or a mix of categorical and continuous variables. In this article, we propose Generalized Parallel Coordinate Plots (GPCP) to extend the ability of PCPs from just numeric variables to dealing seamlessly with a mix of categorical and numeric variables in a single plot. In this process we find that existing solutions for categorical values only, such as hammock plots or parsets become edge cases in the new framework. By focusing on individual observations …

Evaluating The Feasibility And Potential Impacts Of A Recovery-Oriented Psychosocial Rehabilitation Toolkit In A Health Care Setting In Kenya: A Mixed-Methods Study, Regina Casey, Joshua C. Wiener, Terry Krupa, Rosemary Lysaght, Marlene Janzen Le Ber, Ruth Ruhara, Elizabeth Price, Romaisa Pervez, Sean Kidd, Victoria Mutiso, David M Ndetei, Arlene G Macdougall

Epidemiology and Biostatistics Publications

OBJECTIVES: This pilot study evaluated the feasibility and potential impacts of delivering the Psychosocial Rehabilitation (PSR) Toolkit for people with serious mental illness within a health care setting in Kenya.

METHOD: This study used a convergent mixed-methods design. Participants were people with serious mental illness (n = 23), each with an accompanying family member, who were outpatients of a hospital or satellite clinic in semirural Kenya. The intervention consisted of 14 weekly group sessions of PSR cofacilitated by health care professionals and peers with mental illness. Quantitative data were collected from patients and family members using validated outcome measures before …

Patient And Physician Factors Associated With First Diagnosis Of Non-Affective Psychotic Disorder In Primary Care, Joshua C. Wiener, Rebecca Rodrigues, Jennifer N S Reid, Suzanne Archie, Richard G Booth, Chiachen Cheng, Saadia Hameed Jan, Paul Kurdyak, Arlene G Macdougall, Lena Palaniyappan, Bridget L Ryan, Kelly K. Anderson

Epidemiology and Biostatistics Publications

Primary care physicians play a central role in pathways to care for first-episode psychosis, and their increased involvement in early detection could improve service-related outcomes. The aim of this study was to estimate the proportion of psychosis first diagnosed in primary care, and identify associated patient and physician factors. We used linked health administrative data to construct a retrospective cohort of people aged 14-35 years with a first diagnosis of non-affective psychosis in Ontario, Canada between 2005-2015. We restricted the sample to patients with help-seeking contacts for mental health reasons in primary care in the six months prior to first …

Examining Failures Of Kc-135 Boom Assemblies Using Survival Analysis, Benjamin D. Miller

Theses and Dissertations

The purposes of this study are to confirm the applicability of survival analysis for predicting recurrent failures of a component of a military aircraft and to provide practical insights to maintenance managers and mission planners. The results of this study also can help the United States Department of Defense improve the CBM+ program. This study was able to predict recurrent failures of the component using Nelson-Aalen cumulative estimates. In addition, this study used a Cox proportional hazards regression model with shared frailty for measuring the effect of covariates on recurrent failures and unidentified heterogeneity in the model, which warranted future …

A Review On Derivative Hedging Using Reinforcement Learning, Peng Liu

Research Collection Lee Kong Chian School Of Business

Hedging is a common trading activity to manage the risk of engaging in transactions that involve derivatives such as options. Perfect and timely hedging, however, is an impossible task in the real market that characterizes discrete-time transactions with costs. Recent years have witnessed reinforcement learning (RL) in formulating optimal hedging strategies. Specifically, different RL algorithms have been applied to learn the optimal offsetting position based on market conditions, offering an automatic risk management solution that proposes optimal hedging strategies while catering to both market dynamics and restrictions. In this article, the author provides a comprehensive review of the use of …

Examining Fuel Service System Failures Of The Usaf R11 Using Survival Analysis, Roed M.S. Mejia

Theses and Dissertations

Recent events show that fuel supply is a large contributor to the success or failure of a military operation in response to a contingency. Any future near-peer conflict will stress the supply chain and require fully operational vehicles to be ready for the primary mission sets they support. In the United States Air Force (USAF), the readiness of fuel distribution trucks is crucial to meeting those mission sets in global operations. Utilizing non-parametric and semi-parametric survival models, which do not assume specific probability distributions, this study analyzes maintenance data for R-11 trucks that refuel aircraft.

Debris Survivability Study For Mega-Constellation Architectures, Joseph C. Canoy

Theses and Dissertations

The analysis for the overall theoretical debris survivabilty of mega-constellation architectures, with an emphasis on space-based ballistic missile defense constellation (SB-BMD), is explored via three extensive different Monte Carlo simulations: preliminary analysis of low Earth Orbit (LEO) mega-constellation survivabilty following a fragmentation event within the constellation, analysis of LEO mega-constellation survivability with a fragmentation event occurring on a satellite performing a maneuver to insert itself within the constellation, and the analysis of LEO mega-constellation survivabilty after a fragmentation event resulting from the destruction of a missile. The LEO mega-constellations represent the SB-BMD constellation. The first two analysis sections will include …

Probability Of Agreement As A Simulation Validation Methodology, Matthew C. Ledwith

Theses and Dissertations

Determining whether a simulation model is operationally valid requires the rigorous assessment of agreement between observed functional responses of the simulation model and the corresponding real world system or process of interest. This research seeks to extend and formulate the probability of agreement approach to the operational validation of simulation models. The first paper provides a methodological approach and an initial demonstration which leverages bootstrapping to overcome situations where one’s ability to collect real-world data is limited. The second paper extends the probability of agreement approach to account for second-order heteroscedastic variability structures and establishes a weighted probability of agreement …

Institutional Design And Policy Responsiveness In Us States, Scott J. Lacombe

Government: Faculty Publications

There is significant disagreement on the moderating role of institutions on policy responsive- ness, yet overwhelmingly research in state politics has focused on single institutions. This project leverages a new aggregate scale of state institutions to evaluate if the collective insti- tutional context moderates the influence of public opinion on policy. I use a recently released latent scale of institutional context and find that high levels of accountability pressure strongly strengthen public opinion’s influence on policy for both economic and social policy, while the strength of a state’s checks and balance system is largely unrelated to policy responsiveness. These results …

Presidential Vote Share And Covid-19 Vaccination Rate In Indonesia: A District-Level Cross-Sectional Ecological Study, Gede Benny Setia Wirawan, Ni Luh Zallila Gustina, Ivy Cerelia Valerie, I Gusti Ayu Indah Pradnyani Rs, Muchamad Zaenal Arifin, Pande Putu Januraga

Kesmas

Political affiliation has been reported as a determinant of COVID-19 vaccine acceptance in some countries, although few studies have examined the Asian context. This study aims to fill this gap by employing an ecological study design using Indonesian regions as data points. Political affiliation was represented by incumbent President Jokowi’s vote share in the 2019 presidential election. Potential confounders included population density, human development index, availability of hospitals and primary health care, 2019–2020 economic growth, COVID-19 mortality rate, and proportion of Muslims in the population. The final analysis included 201 out of 501 districts and cities in Indonesia. Controlling for …

Information-Motivation-Behavioral Skill In Diabetes Self-Management Using Structural Equation Modeling Analysis, Dien Kurtanty, Adang Bachtiar, Cicilya Candi, Alya Pramesti, Almira Fanny Rahmasari

Kesmas

Diabetes is the “mother” of various diseases increasing the risk of morbidity and mortality. Diabetes self-management, an effort made by patients to control blood sugar levels, is an important part of the management strategy. Therefore, this study analyzed information, motivation, and behavioral skills associated with diabetes self-management. Data were collected in the Special Capital Region of Jakarta, with 277 diabetic patients selected using a questionnaire by a systematic random sampling method. The analyzed variables were information (with indicator variables of information on physical activity, nutritional intake, drug consumption, and blood sugar monitoring); sociodemographic (age, sex, occupation, education level, and duration …

Obesity And Asthma Risk In Indonesian Adults: Findings From The 2018 Indonesia Basic Health Research, Hoirun Nisa

Kesmas

Obesity and asthma are both global public health challenges. Mounting evidence suggests that obesity may increase asthma risk in adults; however, the association by sex remains uncertain. This study examined the association of obesity with asthma risk in Indonesian adult men and women. Data were obtained from the 2018 Indonesia Basic Health Research. The analysis included 299,837 men and 333,218 women aged ≥18 years. Asthma was identified by the self-report of a doctor’s diagnosis. Obesity was defined as a body mass index ≥30 kg/m2. A logistic regression was used for data analysis. Asthma prevalence was 2.7% (2.5% in men and …

Developing A New Tool For Early Detection Of The Nutritional And Health Risk Factors Of Urban Workers’ Productivity, Hildagardis Meliyani Erista Nai, Arimbi Karunia Estri, Christina Ririn Widianti

Kesmas

Nutrition and health play vital roles in work productivity. This study aimed to develop a risk self-assessment tool called Early Detection of the Nutritional and Health Risk Factors on the productivity of urban workers. This study was conducted in two stages: 1) the development of the tool to determine the nutritional and health risk factors that affect productivity based on literature reviews and scoring systems and 2) the testing of validity and reliability. Finally, the tool contained 63 items, including 28 items on nutritional risk factors and 35 on health risk factors. The validity of the tool was assessed using …