Physical Sciences and Mathematics Commons^™

Enhancing Flight Delay Predictions Using Network Centrality Measures, Joseph Ajayi

Electronic Theses and 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 …

Exploring The Consistency Of Flow Regimes Within And Among Ecoregions Of The Southeastern United States, Frank Paul Braun Iv

Electronic Theses and Dissertations

Human manipulation of river systems has long been a known contributor to the loss of freshwater biodiversity. By accounting for environmental causes of hydrologic variation among rivers, we can better understand how ecoregion mediates flow regimes and forecast species that may be at risk. Presumably, natural variation associated with ecoregion boundaries exerts strong influence on flow regimes, and may mediate relationships between other features (e.g., land use, dam operations) and hydrology. However, such between-ecoregion variation is poorly investigated, particularly at fine spatial and temporal scales. I characterized 10 hydrologic metrics, representing the five key dimensions of the flow regime (magnitude, …

Reinforcement Learning: Applying Low Discrepancy Action Selection To Deep Deterministic Policy Gradient, Aleksandr Svishchev

Electronic Theses and Dissertations

Reinforcement learning (RL) is a subfield of machine learning concerned with agents learning to behave optimally by interacting with an environment. One of the most important topics in RL is how the agent should explore, that is, how to choose actions in order to rate their impact on long-term reward. For example, a simple baseline strategy might be uniformly random action selection. This thesis investigates the heuristic idea that agents will learn faster if they explore by factoring the environment’s state into their decision and intentionally choose actions which are as different as possible from what they have previously observed. …

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

Electronic Theses and 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 …

The Distribution Of The Significance Level, Paul O. Monnu

Electronic Theses and Dissertations

Reporting the p-value is customary when conducting a test of hypothesis or significance. The likelihood of getting a fictitious second sample and presuming the null hypothesis is correct is the p-value. The significance level is a statistic that interests us to investigate. Being a statistic, it has a distribution. For the F-test in a one-way ANOVA and the t-tests for population means, we define the significance level, its observed value, and the observed significance level. It is possible to derive the significance level distribution. The t-test and the F-test are not without controversy. Specifically, we demonstrate that as sample size …

Network Intrusion Detection Using Deep Reinforcement Learning, Hamed T. Sanusi

Electronic Theses and Dissertations

This thesis delves into cybersecurity by applying Deep Reinforcement(DRL) Learning in network intrusion detection. One advantage of DRL is the ability to adapt to changing network conditions and evolving attack methods, making it a promising solution for addressing the challenges involved in intrusion detection. The thesis will also discuss the obstacles and benefits of using Classification methods for network intrusion detection and the need for high-quality training data. To train and test our proposed method, the NSL-KDD dataset was used and then adjusted by converting it from a multi-classification to a binary classification, achieved by joining all attacks into one. …

Assessment Of Atmospheric Correction Algorithms For The Remote Sensing Of Water Quality In Southeastern U.S. Estuaries, Jerome Reimers

Electronic Theses and Dissertations

Water quality is a key indicator in understanding and representing an environment's overall health. Through developments in remote sensing, we can utilize satellite imagery to measure water parameters in each aquatic system. When accurate atmospheric correction is performed, remote sensing can account for atmospheric attenuation and scattering effects to better measure the reflectance and estimate optically active constituents (OAC) present in upper water columns. Atmospheric Correction for OLI lite (ACOLITE) is an atmospheric correction algorithm designed specifically for robust atmospheric correction of water surfaces, in comparison to algorithms designed more for land surfaces such as the European Space Agency’s (ESA) …

Development And Praxis Of Ph Drug Delivery System Contra Zika, Julissa Rodriguez

Electronic Theses and Dissertations

As the effects of global warming continue to spread throughout the world, another critical issue is slowly gaining attention in many urban tropical countries. The Emerging Infectious Diseases/ Pathogens list from the National Institutes of Health (NIH) listed the Zika virus as a potential pandemic threat. In 2015, an outbreak of Zika was noted in several South American countries until the spread reached an all-time high of 87 countries in 2017. During the outbreaks, adults affected were noted to have joint and muscle pains, fevers, and rashes. The worst cases reported would ultimately lead to Guillain-Barre symptoms. Still, pregnant women …

Middle Savannah River: An A/R/Tographic Ecopedagogical Ethnography Experimenting With Rhizomatic Perspectives, Lisa Augustine-Chizmar

Electronic Theses and Dissertations

This research is an experiment in perspective. Using the four commonplaces (Schwab, 1978), I practiced letting the Savannah River teach me what there is to know about the water, the land, the people, and the other entities that depend on ki through artistic, ethnographic, and ecopedagogical lenses. The ethnographic findings describe the social actors that depend on ki and give a voice to the River. The a/r/tographic findings display the River on a canvas map through two hundred years using paint, clay, photography, video, abstract acrylics, and fabric. Together, these methods contribute to a unique ecopedagogical journey. This word cloud …

Application Of Big Data Technology, Text Classification, And Azure Machine Learning For Financial Risk Management Using Data Science Methodology, Oluwaseyi A. Ijogun

Electronic Theses and Dissertations

Data science plays a crucial role in enabling organizations to optimize data-driven opportunities within financial risk management. It involves identifying, assessing, and mitigating risks, ultimately safeguarding investments, reducing uncertainty, ensuring regulatory compliance, enhancing decision-making, and fostering long-term sustainability. This thesis explores three facets of Data Science projects: enhancing customer understanding, fraud prevention, and predictive analysis, with the goal of improving existing tools and enabling more informed decision-making. The first project examined leveraged big data technologies, such as Hadoop and Spark, to enhance financial risk management by accurately predicting loan defaulters and their repayment likelihood. In the second project, we investigated …

Comparative Analysis Of Fullstack Development Technologies: Frontend, Backend And Database, Qozeem Odeniran

Electronic Theses and Dissertations

Accessing websites with various devices has brought changes in the field of application development. The choice of cross-platform, reusable frameworks is very crucial in this era. This thesis embarks in the evaluation of front-end, back-end, and database technologies to address the status quo. Study-a explores front-end development, focusing on angular.js and react.js. Using these frameworks, comparative web applications were created and evaluated locally. Important insights were obtained through benchmark tests, lighthouse metrics, and architectural evaluations. React.js proves to be a performance leader in spite of the possible influence of a virtual machine, opening the door for additional research. Study b …

Leveraging Targeted Regions Of Interest By Analyzing Code Comprehension With Ai-Enabled Eye-Tracking, Md Shakil Hossain

Electronic Theses and Dissertations

Code comprehension studies techniques for extracting information that give insights on how code is understood. For educators teaching programming courses, this is an important but often difficult task, especially given the challenges of large class sizes, limited time, and grading resources. By analyzing where a student looks during a code comprehension task, instructors can gain insights into what information the student deems important and assess whether they are looking in the right areas of the code. The proportion of time spent viewing a part of the code is also a useful indicator of the student's decision-making process. The goal of …

The Influence Of Urban Forms And Street Infrastructure On Pedestrian-Motorist Collisions, Taylor J. Foreman

Electronic Theses and Dissertations

Unwalkable cities are afflicted by serious issues such as increasing rates of pedestrian traffic accidents, public health concerns, and the denied right to have an accessible city. This study examines how different types of urban forms and street infrastructure contribute to the prevalence of traffic accidents in two major metropolitan cities in the United States: Atlanta, Georgia, and Boston, Massachusetts. This study utilizes geospatial analysis through the Average Nearest Neighbor and Optimized Hot Spot Analysis tools to determine the spatial distribution of traffic accidents throughout both cities. Additionally, statistical tests were conducted to explore the relationships between the number of …

Developing Best Practices For The Propagation Of Spartina Alterniflora For Use In Salt Marsh Restortaion, Justin Hinson

Electronic Theses and Dissertations

Coastal salt marshes are valuable ecosystems under threat from climate change and sea level rise. Living shorelines offer a promising solution, often incorporating the foundational salt marsh species Spartina alterniflora due to its ability to tolerate natural stressors and maintain sediment stability. However, research suggests that seed-based propagation protocols should be developed on a local scale due to the genetic heterogeneity within and between S. alterniflora populations. Here, we attempt to contribute to the development of one such protocol for coastal Georgia S. alterniflora.

In Fall 2021, seeds were collected bi-monthly from four marshes of varying ocean proximity and …

Blockchain Securities Issues: Decentralized Identity System With Key Management Perspective, Olalekan O. Adaramola

Electronic Theses and Dissertations

Blockchain was created many years ago to solve the problems of data transfer Integrity, several years later the issues persist. Blockchain securities are one of the most important considerations to be investigated, and data integrity is about ensuring the accuracy and validity of messages such that when they are read, they are the same as when they were first written. It is of the opinion that passing information across from one person to another cannot be the same as it was first said at the onset. Our work investigated Blockchain security issues, studying Integrity emanating from transactions across the blocks …

Campus Safety Data Gathering, Classification, And Ranking Based On Clery-Act Reports, Walaa F. Abo Elenin

Electronic Theses and Dissertations

Most existing campus safety rankings are based on criminal incident history with minimal or no consideration of campus security conditions and standard safety measures. Campus safety information published by universities/colleges is usually conceptual/qualitative and not quantitative and are based-on criminal records of these campuses. Thus, no explicit and trusted ranking method for these campuses considers the level of compliance with the standard safety measures. A quantitative safety measure is important to compare different campuses easily and to learn about specific campus safety conditions.

In this thesis, we utilize Clery-Act reports of campuses to automatically analyze their safety conditions and generate …

A Comparison Of Tung Oil Resin Reinforcements Using Fibrous Proteins And Peptides For Biological And Materials Applications, Parker L. Williams

Electronic Theses and Dissertations

In this study a tung oil based thermoset was reinforced with collagen and fibroin, and the resulting composites were analyzed for their physical properties. Tung tree seed oil is a great candidate for biobased polymer production because its triglycerides are primarily made of alpha eleostearic acid, a fatty acid with three conjugated carbon-carbon double bonds. These double bonds allow for mechanically strong crosslinking in the polymer. It has been observed that polymerized tung oil forms a gel. This issue has been addressed using divinylbenzene (DVB) and n-butyl methacrylate (BMA) as co-monomers. Similar bio-based polymers have been studied and tend to …

Using Machine Learning Classification And Esa Sentinel 2 Multispectral Imager Data To Delineate Marsh Vegetation And Measure Ecotone Movement In Coastal Georgia, Thomas A. Pudil

Electronic Theses and Dissertations

Tidal marshes are unique communities that are subjected to environmental stressors including sea level rise, salinity change, and drought, resulting in constant change. It is important to monitor these changing areas because of the ecosystem services they provide to us, such as protection from storms and carbon sequestration. The proposed work for this thesis project is focused on the study of tidal marshes and the dynamics between the vegetation species within them. The aim of this project is to use geospatial technology and analyses, along with machine learning classification methods, to monitor change in these valuable ecosystems. The Georgia coast …

Remote Sensing Of Georgia Tidal Marsh Habitats Using Aerial Photography And Planetscope Satellite Imagery, Harrison M. Currin

Electronic Theses and Dissertations

Globally, tidal marshes cover about 90,800 km. Within the state of Georgia tidal marshes are primarily located behind the barrier islands and total 1,619 km². The combination of high salinity environments and daily inundation, and being dependent on river output, make these dynamic systems. Tidal marshes provide numerous ecosystem services such as carbon and nitrogen sequestration, flood control, coastal protection, and numerous biogeochemical processes. Due to their unique position, tidal marshes are under threat from sea level rise, drought, coastal development, and large-scale disturbance events. Tidal freshwater marshes are especially susceptible to these threats due to their geographic …

Fabrication And Investigation Of Microfluidic Devices That Produce Non-Linear Chemical Gradients, Elijah L. Waters

Electronic Theses and Dissertations

Investigation of cell chemotaxis requires controlled chemical gradients. We investigated microfluidic devices that could enhance small populations' cell assays because of their ability to generate various chemical gradients. Our five designs generate different chemical concentration landscapes that we can easily convert into tools to study cell response to growth factors. Gradient landscapes occurred by splitting and mixing two input fluid concentrations using bifurcations, trifurcations, and Y-mixing junctions in three consecutive steps. Such fluid flow manipulations resulted in nine concentration streams entering a 0.54-mm-wide gradient chamber. The first design used a 1:1 ratio Y-mixer (unbiased) when blending two concentrations, resulting in …

Analysis Of Bio-Alcohols With Mie-Scattering And Ltc For Lowered Emissions In Pcci, Cesar E. Carapia

Electronic Theses and Dissertations

An investigation was conducted on the optimal engine parameters for facilitating lower NOX and soot emissions of PCCI combustion with either ethanol or n-butanol. The PFI fuels selected were tested at loads of 3, 4, and 5 Bar IMEP for a total of 28 total combustion tests with variations made to the EGR% and boost pressure for each test in order to find the optimal emissions strategy. A Mie-scattering spray fuel analysis was also conducted on the three fuels to gain insight on their influence on combustion/emissions characteristics. It was found that ethanol had a greater average Sauter Mean Diameter …

The Synthesis And Biocatalytic Reduction Of Beta-Keto Alkynes, Rhema M. Francis

Electronic Theses and Dissertations

The preparation of enantiopure homopropargyl alcohols (but-3-yn-ols) is of high importance to the scientific community. They are employed as valuable pharmaceutical intermediates and are opportune to generate antiviral nucleoside analogues. Chiral inducement of these molecules thus far has been poor (low ee) and has constituted a key challenge for asymmetric synthesis in the last few decades. Enzyme-catalyzed enantioselective reductions of ketones have become popular to produce thus-prepared synthons on an industrial scale. Among them, biocatalysts (dehydrogenases, reductases) emerge as a biodegradable option for chemical transformations, in comparison to chiral catalysts that employ highly toxic metals. This research investigates the catalytic …

Non-Inferiority Testing: Kernel Estimation And Overlap Measure, Larie C. Ward

Electronic Theses and Dissertations

In non-inferiority testing, the decision of whether a proposed treatment is non-inferior to a reference treatment depends on model assumptions and choices of acceptable tolerance limits. Here, we consider a method that employs kernels to estimate the probability density functions of both the experimental and reference populations from two independent samples. Based on these densities, we introduce a quantity called the overlap coefficient or overlap measure. A bootstrap technique is helpful in exploring the distribution and variance empirically. We derive the distribution of this measure and define a hypothesis test that can be applied to the non-inferiority setting under some …

License Plate Image Quality Enhancement Utilizing Super Resolution Generative Adversarial Networks, Mark Moelter

Electronic Theses and Dissertations

This thesis focuses primarily on enhancing the image quality of blurred license plates through the use of Super-Resolution Generative Adversarial Networks (SRGANs) [1]. We propose a synthetic dataset with SRGAN model to promote blurred image quality enhancement, and allow for model evaluation on a multitude of image input and output size combinations. SRGAN is mainly used for low-resolution image enhancement, but by heavily blurring the input images, the model is tested on its ability to blindly deblur and upsample images to the desired super-resolution (SR) size. The model enhances the image quality to nearly that of the reference images. The …

The Application Of Deep Learning And Cloud Technologies To Data Science, Ian A. Trawinski

Electronic Theses and Dissertations

Machine Learning and Cloud Computing have become a staple to businesses and educational institutions over the recent years. The two forefronts of big data solutions have garnered technology giants to race for the superior implementation of both Machine Learning and Cloud Computing. The objective of this thesis is to test and utilize AWS SageMaker in three different applications: time-series forecasting with sentiment analysis, automated Machine Learning (AutoML), and finally anomaly detection. The first study covered is a sentiment-based LSTM for stock price prediction. The LSTM was created with two methods, the first being SQL Server Data Tools, and the second …

Biomimetic Synthesis Of Palladium Nanoparticles For Catalytic Application, Emily A. Groover

Electronic Theses and Dissertations

The synthesis of palladium nanoparticles (Pd NPs) using materials-directed peptides is a novel, nontoxic approach which exerts a high level of control over the particle size and shape. This biomimetic technique is environmentally benign, featuring nonhazardous ligands and ambient conditions. Nanoparticles are extremely reactive catalysts, boasting a large surface-to-volume ratio when compared to their bulk counterparts. The rational design of these nanoparticles using peptides has been very successful in aqueous environments, but no research has been done to apply it in organic systems. As such, the biomimetic synthesis of Pd NPs in an organic system is here investigated, with ethanol …

Reinforcement Learning: Low Discrepancy Action Selection For Continuous States And Actions, Jedidiah Lindborg

Electronic Theses and Dissertations

In reinforcement learning the process of selecting an action during the exploration or exploitation stage is difficult to optimize. The purpose of this thesis is to create an action selection process for an agent by employing a low discrepancy action selection (LDAS) method. This should allow the agent to quickly determine the utility of its actions by prioritizing actions that are dissimilar to ones that it has already picked. In this way the learning process should be faster for the agent and result in more optimal policies.

Ring Bose–Einstein Condensate Atomtronic Rotation Sensor, Oluwatobi I. Adeniji

Electronic Theses and Dissertations

We propose a design for an atomtronic rotation sensor consisting of an array of Bose– Einstein condensates (BECs) confined in a double–target–array potential. The purpose of the sensor is to measure the rotation speed, Ω_R, of the sensor’s rest frame with respect to the “fixed stars.” The atomtronic system consists of an ultracold gas of sodium atoms compressed, using laser light, into a thin horizontal sheet and subjected to a double–target– array potential within the horizontal plane. A “target” BEC consists of a disk–shaped condensate surrounded by a concentric ring–shaped condensate. A “double–target” BEC is two adjacent target …

Eeg Signals Classification Using Lstm-Based Models And Majority Logic, James A. Orgeron

Electronic Theses and Dissertations

The study of elecroencephalograms (EEGs) has gained enormous interest in the last decade with the increase of computational power and availability of EEG signals collected from various human activities or produced during medical tests. The applicability of analyzing EEG signals ranges from helping impaired people communicate or move (using appropriate medical equipment) to understanding people's feelings and detecting diseases.

We proposed new methodology and models for analyzing and classifying EEG signals collected from individuals observing visual stimuli. Our models rely on powerful Long-Short Term Memory (LSTM) Neural Network models, which are currently the state of the art models for performing …

Design And Implementation Of An Automatic Word Generator For Word Matching Interactives, Evan Miles Gertis

Electronic Theses and Dissertations

An Automatic Word Match Generator is a software tool that can be used to generate word-matching interactives automatically. The purpose of a word-matching interactive is to provide students with the mechanism to learn new vocabulary and improve their reading comprehension skills. This thesis will present the design and implementation of an Automatic Word Match Generator, as well as the research and algorithms used in the program.