Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Theses and Dissertations

Discipline
Institution
Keyword
Publication Year
File Type

Articles 391 - 420 of 8799

Full-Text Articles in Physical Sciences and Mathematics

Promoting Collaboration And Multi-Directional Reliance By Sharing Mental Model Information For Effective Multi-Agent Teaming, Audrey L. Aldridge May 2025

Promoting Collaboration And Multi-Directional Reliance By Sharing Mental Model Information For Effective Multi-Agent Teaming, Audrey L. Aldridge

Theses and Dissertations

Successful human-agent teaming requires teammates to form and maintain a shared or common understanding of several attributes regarding taskwork and teamwork. With enhanced information sharing, mental model development, and team functionality, teammates (human, autonomous) can learn to anticipate each others' behaviors, preferences, and needs as well as understand their capabilities and limitations. In designing a framework to support this type of cooperative teaming, there is a need to determine how sharing knowledge, mental models, and common understandings impacts teaming dynamics and performance. By incorporating each individual's understanding into a human-agent interface, this research enables better team coordination and performance through …

Go to article

Real-Time Enhanced Tornado Warning Product Guidance Based On Tornado Debris Signature Height And Population Density, Alexander Cooke May 2025

Real-Time Enhanced Tornado Warning Product Guidance Based On Tornado Debris Signature Height And Population Density, Alexander Cooke

Theses and Dissertations

This research aims to develop an operational program for enhancing real-time tornado warning capabilities by integrating tornado debris signature (TDS) analysis with population impact assessment. The proposed Python-based tool will ingest Level II radar data to identify and analyze TDS, estimating tornado intensity based on maximum TDS height. For high-intensity tornadoes, the program will project the potential impact area using storm motion vectors and integrate this with population density data. The system will assess whether the situation meets National Weather Service criteria for enhanced warning products, providing forecasters with rapid, objective guidance for critical warning decisions. The program’s performance will …

Go to article

Optimizing Mars Terrain Segmentation With Weakly Supervised Learning: A Focus On Weighted Loss From Annotation Metadata, Malika Dutta May 2025

Optimizing Mars Terrain Segmentation With Weakly Supervised Learning: A Focus On Weighted Loss From Annotation Metadata, Malika Dutta

Theses and Dissertations

The study of planetary surfaces heavily depends upon space rovers that gather detailed images of terrain needed for analysis and navigation. Deep neural networks and other sophisticated machine learning techniques are necessary for autonomous navigation in challenging terrain. However, the inconsistent annotations by citizen scientists frequently hinder the performance of these models. This study seeks to optimize terrain segmentation to improve the autonomous capabilities of future Mars rovers by presenting a novel weakly supervised learning framework to handle noise and unreliability in datasets. Using factors like number of clicks, pixel accuracy, and annotator dependability, the method utilizes annotation metadata in …

Go to article

Application Of Pu Learning In Detection Of Ddos Attacks, Gagana Sathya Narayana Prasad May 2025

Application Of Pu Learning In Detection Of Ddos Attacks, Gagana Sathya Narayana Prasad

Theses and Dissertations

The gcore radar 2024 says, the number of DDoS attacks has been increased by 46% in 12 months. Supervised and unsupervised techniques struggle detecting DDoS attacks due to the scarcity of labeled attack samples and an overwhelming presence of benign traffic. In contrast PU- Learning offers a promising solutions by dividing the data into positive and unlabeled data. This study explores the effectiveness of PU-learning in detecting DDoS attacks by comparing it with unsupervised methods. This method employs PU Bagging, Two Step method and auto-encoder based models to extract meaningful patters from network traffic data, utilizing CICDDoS2017 dataset for evaluation. …

Go to article

Evaluating Rainfall Sensitivity Over Land To Tropical Cyclone Parameters Using Idealized Wrf, Madison C. Yawn May 2025

Evaluating Rainfall Sensitivity Over Land To Tropical Cyclone Parameters Using Idealized Wrf, Madison C. Yawn

Theses and Dissertations

Tropical cyclones (TCs) are extreme weather events impacting the United States nearly every year. These events often cause severe damage due to the associated responses they produce including storm surge and rainfall, and the accurate estimation of these TC hazards is necessary to support coastal engineering, risk assessment, and emergency management activities. Evaluating TC-driven hazards is often done in combination with numerical models to simulate how environmental interactions alter the physical processes and responses of these storms. The purpose of this study was to simulate synthetic TC events using the Advanced Weather Research and Forecasting (WRF) model to understand how …

Go to article

Atmospheric Turbulence Education Effects On Flight Anxiety, Megan A. Hanna May 2025

Atmospheric Turbulence Education Effects On Flight Anxiety, Megan A. Hanna

Theses and Dissertations

This study examines the effect of turbulence education on flight anxiety. A pre-post methodology measured students’ anxiety levels before and after a study abroad flight, using an educational video during the pre-flight survey to change their feelings. The Flight Anxiety Situations (FAS) questionnaire assessed anxiety at three survey points: pre-video, post-video, and post-flight. Qualitative analysis using Friedman’s test and the Wilcoxon Signed-rank test, indicated that turbulence education effectively decreased generalized and anticipatory flight anxiety, particularly in non-phobic students. Text analysis of open-ended responses suggested increased scientific knowledge post-video helped students apply technical atmospheric processes to their feelings. Turbulence education was …

Go to article

Apatite Entrapment Of Iodine For Nuclear Waste Disposal Applications, William E. Laird May 2025

Apatite Entrapment Of Iodine For Nuclear Waste Disposal Applications, William E. Laird

Theses and Dissertations

The purpose of this thesis is to provide baseline knowledge of iodine incorporation into calcium phosphate minerals, specifically apatite. Iodine-129 is a fission product in Spent Nuclear Fuel (SNF) that can administer significant amounts of radiation in small quantities. Apatite (Ca10(PO4)6 (OH, F, Cl)) has been studied for the use of radionuclide confinement. Experimental design was set up to mimic temperatures expected in geologic repositories from 40 to 250℃. Experiments are broken into 2 groups based on iodine species being examined. The first group focuses on iodate (IO3-) which is prevalent under oxidized conditions, and the second handles iodide (I-) …

Go to article

Cyber Security Threat Recognition And Preparedness Of Undergraduate Students, Litany Hope Lineberry May 2025

Cyber Security Threat Recognition And Preparedness Of Undergraduate Students, Litany Hope Lineberry

Theses and Dissertations

Cybersecurity awareness and preparedness are critical competencies for individuals across academic disciplines and professional sectors. However, undergraduate students often lack sufficient knowledge and skills to recognize and mitigate cybersecurity threats. This dissertation examines cybersecurity threat recognition and preparedness among undergraduate students through a three-phase research approach. Study 1 explores faculty perspectives on students' cybersecurity awareness, identifying gaps in knowledge and preparedness across various fields of study. Study 2 investigates industry professionals' perceptions of new hires’ cybersecurity readiness, assessing the alignment between academic training and industry expectations. Study 3 evaluates the effectiveness of an online intervention designed to enhance students' cybersecurity …

Go to article

The Role Of Enso Diversity In Modulating Tornadic Activity In The United States, Davis Boyd Newton May 2025

The Role Of Enso Diversity In Modulating Tornadic Activity In The United States, Davis Boyd Newton

Theses and Dissertations

Tornado activity in the United States is influenced by large-scale climate patterns, especially by the El Niño-Southern Oscillation (ENSO). While prior research has explored ENSO’s impact on severe weather, the influence of ENSO flavors, Central Pacific (CP) and Eastern Pacific (EP), on tornadic activity remains understudied. Using tornado records, reanalysis data, and sea surface temperature anomalies, we assess how convective available potential energy (CAPE), wind shear, and jet stream dynamics influence tornado frequency and distribution. Results indicate that CP La Niña years had significant increases in tornado frequency, particularly across the Midwest, Central Plains, and Southeast. EP ENSO years had …

Go to article

Earth Analogue Analysis Of Volcanic/Tectonic Interactions With Applications To Venusian Stresses, Michael Ortigoza May 2025

Earth Analogue Analysis Of Volcanic/Tectonic Interactions With Applications To Venusian Stresses, Michael Ortigoza

Theses and Dissertations

Venus shares many geological similarities with Earth, yet its tectonic processes and magma injection mechanisms remain poorly understood. A key question in planetary geology is how effusive volcanism persists despite the intense horizontal compression terrestrial bodies experience over time. To explore these issues, we examine the Spanish Peaks dike swarm in Colorado which serves as an ideal site for investigating magma intrusion under compressive stress conditions. Through field mapping, orientation measurements, and structural analysis, we identify a strong relationship between pre-existing joints and dike orientations, suggesting that these fractures serve as critical magma pathways in compressive regimes. Additionally, evidence of …

Go to article

Establishing A Baseline For Detecting Lotl Attacks In Windows Operating Systems, Ashlyn Martin Phillips May 2025

Establishing A Baseline For Detecting Lotl Attacks In Windows Operating Systems, Ashlyn Martin Phillips

Theses and Dissertations

There has been an increasing realization of the rise in living off the land (LOTL) attacks where adversaries misuse legitimate system tools, particularly with state-sponsored actors targeting critical infrastructure in the United States. These attacks are difficult to detect because they allow attackers to remain present in a system without the user’s knowledge for an extended period. This thesis establishes an initial baseline specifically for Windows operating systems to measure normal system activity, focusing on CPU usage, memory utilization, and process activity. It particularly examines the use of PowerShell alongside other applications. The findings from this baseline are used to …

Go to article

Investigations Into Fluorescence Of Fluorene Dimers: Linker Impacts And Tuning Potential Through Substituent Addition, Abigail R. Ressler May 2025

Investigations Into Fluorescence Of Fluorene Dimers: Linker Impacts And Tuning Potential Through Substituent Addition, Abigail R. Ressler

Theses and Dissertations

Fluorene-based fluorescing conjugated polymers are being used to develop sensors that show great sensitivity and selectivity, however, important questions about the photophysics of these systems remain unanswered. For example, a fluorescence intensity difference was observed between fluorene dimers linked with either an acetylene (diFA) or phenyl (diFP). The polymers diFA and diFP have similar structures and extinction coefficients, yet diFA yielded a five times higher fluorescence intensity than diFP. In project one, Density Functional Theory (DFT) and Time-Dependent DFT (TD-DFT) were used to calculate the ground and excited states of diFA and diFP. A python code was developed to solve …

Go to article

Integrating Case Studies With Meteorologists’ Insight: Assessing Meteorologists’ Perception And Utilization Of Composite Indices, Brianna Marie Salazar May 2025

Integrating Case Studies With Meteorologists’ Insight: Assessing Meteorologists’ Perception And Utilization Of Composite Indices, Brianna Marie Salazar

Theses and Dissertations

Meteorologists from sectors, including broadcast, academia, and operations, use derived composite indices such as 0-1km and 0-3km energy helicity index (EHI), effective-layer supercell composite parameter (SCP), fixed-layer and effective layer significant tornado parameter (STP), in addition to other resources, when developing severe local storm forecasts. This study utilizes the Weather Research and Forecasting (WRF) model to create simulations of composite indices for two tornado-producing events: 31 March 2023 and 3 May 1999. With modifications to geographical location, these simulated scenarios are then utilized in the survey to gauge how meteorologists assess where tornado potential is highest. Additionally, a combination of …

Go to article

Zeroizing Trust In A Naïve Federated Zero Trust Environment, Keith E. Strandell May 2025

Zeroizing Trust In A Naïve Federated Zero Trust Environment, Keith E. Strandell

Theses and Dissertations

The position of the United States on the global stage is predicated on information dominance and the ability to project power through cooperative engagements with mission partners in both wartime and peacetime. Recent cyber-attacks highlighted the need for a more robust cybersecurity posture. As the United States progresses toward the adoption of Zero Trust, it is incumbent on the Department of Defense to assess the impact to the ability to share data across strategic partnerships while securing the data of both the United States and its partners. This paper proposes research into ensuring an environment rooted in Zero Trust and …

Go to article

Synthetic Data Augmentation For Retinoblastoma Using Diffusion, Andrew Thompson May 2025

Synthetic Data Augmentation For Retinoblastoma Using Diffusion, Andrew Thompson

Theses and Dissertations

Many AI models rely on large and high quality datasets for optimal training. In certain cases, data can be difficult or expensive to obtain, making training difficult. Rare medical conditions are one of these cases. Datasets for retinoblastoma are severely lacking in quantity. Diffusion has been used to create synthetic data in the industrial, medical, and financial domains. By applying the latest Diffusion methods to retinoblastoma, this work seeks to improve predictive model performance on identifying retinoblastoma.

Go to article

A Framework For Modular Knowledge Composition In Network Intrusion Detection Systems, Patrick L. Day May 2025

A Framework For Modular Knowledge Composition In Network Intrusion Detection Systems, Patrick L. Day

Theses and Dissertations

Autonomic Intrusion Detection Systems (AIDS) are sophisticated software systems designed to autonomously and adaptively identify and respond to security threats and intrusions in computer networks or systems. One of the fundamental challenges in intrusion detection research lies in the limited availability and scope of publicly available datasets. The proposed research aims to address data-related gaps with autonomic and traditional intrusion detection systems by describing a comprehensive approach to investigate the impact and potential of data augmentation. The goal is to explore various data augmentation techniques, assess their effectiveness in introducing variability, and evaluate their impact on the performance of neural-based …

Go to article

Assessment Of Water Quality And Remediation Of Heavy Metals In A Coastal System, Christiana Fumnanya Eziashi May 2025

Assessment Of Water Quality And Remediation Of Heavy Metals In A Coastal System, Christiana Fumnanya Eziashi

Theses and Dissertations

This research focuses on a three-part study to assess water quality in a coastal system and evaluate the absorption capacity of modified biochar and algae to remediate cadmium (Cd). The first chapter introduces the hypothesis and objectives, and the second chapter provides a detailed literature review. The third chapter focuses on the first study, where surface water samples and water quality data collected from a manned boat and a novel autonomous surface vessel (ASV) in the Western Mississippi Sound (WMS) in the summer of 2021 and 2022 were analyzed and the interrelationship between the nutrient, trace metals, salinity, and chlorophyll-a …

Go to article

Bucket-Based Priority Queues For A* And Related Bounded-Suboptimal And Anytime Search Algorithms: Theoretical And Practical Advancements, Garrett Michael Fereday May 2025

Bucket-Based Priority Queues For A* And Related Bounded-Suboptimal And Anytime Search Algorithms: Theoretical And Practical Advancements, Garrett Michael Fereday

Theses and Dissertations

For shortest-path problems with a small number of integer transition costs, it is well-known that the performance of the classic A* algorithm can be improved by using bucketing to reduce priority queue overhead—in particular, by using a bucket queue data structure for the priority queue, instead of a binary heap. This dissertation describes several theoretical and practical extensions of this approach. First, the traditional two-level bucket queue data structure is modified in simple ways to improve the worst-case complexity of its operations, which leads to the first demonstration that the priority queue operations of a two-level bucket queue for A* …

Go to article

Influence Of Horizontal Grid Spacing On Numerical Weather Prediction Simulations Of Clear Air Turbulence, Kailah Rose Gordon May 2025

Influence Of Horizontal Grid Spacing On Numerical Weather Prediction Simulations Of Clear Air Turbulence, Kailah Rose Gordon

Theses and Dissertations

The focus of this research was to analyze the influence of horizontal grid spacing on numerical simulations of kinetic and thermal forced clear air turbulence (CAT) by quantifying uncertainty using a resolution ensemble. Previous studies indicated that microscale (< 1km) spatial resolutions are necessary to resolve turbulent kinetic energy (TKE) with low uncertainty. Six case studies of moderate or greater CAT, from pilot reports, were simulated at six horizontal grid spacings including 1, 2, 4, 8, 16, and 32km using the Weather Research and Forecast (WRF) Model. Results showed that grid spacing does influence the magnitude of uncertainty; however, the relationship between the grid spacings varied with the type of CAT being simulated and the addition of the cumulus parameterization scheme for grid spacings greater than 4km. Overall, higher precision was found between convective resolutions (1-4km), indicating that microscale resolutions are not necessary to precisely simulate TKE for CAT forecasts.

Go to article

From Tree Rings To Streamflow: Reconstructing The Hydroclimatic History Of The Mississippi River Basin Over The Past Millennia, Brandon Mcdaniel May 2025

From Tree Rings To Streamflow: Reconstructing The Hydroclimatic History Of The Mississippi River Basin Over The Past Millennia, Brandon Mcdaniel

Theses and Dissertations

The Mississippi River Basin (MRB), the largest watershed in the United States, plays a central role in shaping regional hydroclimate. This study reconstructs streamflow variability in the MRB from the year 1200 to 2005 by applying principal component regression to streamflow data from 51 gauges and the North American Drought Atlas (NADA), a tree-ring-based reconstruction of the summer self-calibrating Palmer Drought Severity Index. Verification statistics indicated strong predictive skill across the domain. These findings provide critical insight into long-term hydroclimatic variability in the MRB and underscore the value of paleoclimate records for improving water resource assessments.

Go to article

Ai Enabled Autonomic, Safe, And Interactive Intrusion Response System, Damodar Panigrahi May 2025

Ai Enabled Autonomic, Safe, And Interactive Intrusion Response System, Damodar Panigrahi

Theses and Dissertations

The exponential rise in internet usage has precipitated a corresponding surge in cyber threats, underscoring the urgent need for advanced cybersecurity solutions. While traditional intrusion detection systems (IDS) can identify these threats, their inability to self-recover leaves systems vulnerable. Intrusion response systems (IRS) have been developed to address this, aiming to auto- matically restore systems to their desired state post-security breach. However, current IRSs often necessitate manual intervention and may not be su!ciently robust against sophisticated threats. To overcome these limitations, we propose an AI-powered Autonomic, Safe, and Interactive Intrusion Response System called ‘Intrusion Response System Digital Assistant (IRSDA)’. IRSDA …

Go to article

Enhancing Chemical Synthesis For Sustainability And Process Monitoring Utilizing Group Ten Metal Catalysis, Amanda M. Perkins May 2025

Enhancing Chemical Synthesis For Sustainability And Process Monitoring Utilizing Group Ten Metal Catalysis, Amanda M. Perkins

Theses and Dissertations

This thesis explores two sustainable methodologies by modifying established catalytic processes using group ten metal complexes from nickel and palladium. Efforts were made to provide alternatives for processes that often do not follow the principles of green chemistry. In the first project, a nickel(II) N-heterocyclic carbene complex was used to perform catalytic hydrogenation of 2-acetylpyridine under mild conditions. The complex was synthesized and characterized with techniques including mass spectrometry and 1H-NMR. Following this, the reactions were carried out to optimize conditions and yield moderate conversions. For the second project, the Suzuki-Miyaura cross coupling of 7-chlorotryptophan occurred utilizing a palladium complex …

Go to article

Efficient Eeg Epilepsy Classification And Feature Selections Based On Hellinger Distance, Muhammed Sadiq May 2025

Efficient Eeg Epilepsy Classification And Feature Selections Based On Hellinger Distance, Muhammed Sadiq

Theses and Dissertations

Accurate and efficient detection of epileptic seizures from EEG signals remains a critical challenge due to high-dimensional data, class imbalance, and the limitations of standard classifiers. This thesis introduces two novel models to address these challenges. The first model presents a new classifier based on the Hellinger Distance, specifically designed to enhance discriminative capability and robustness against imbalanced datasets. By integrating the Hellinger Distance Classifier with Particle Swarm Optimization (PSO) for feature selection, this model significantly improves classification performance while reducing computational complexity. Experimental evaluations on the Bonn dataset demonstrate an accuracy of 96.25%, an F1-score of 97.74%, a recall …

Go to article

Applications Of The Mathieu Groups And Information Theory In Dna Encoding Functions, Juan C. Nava Jr May 2025

Applications Of The Mathieu Groups And Information Theory In Dna Encoding Functions, Juan C. Nava Jr

Theses and Dissertations

A foundational idea in mathematics lies in breaking down existing components into their bare fundamentals. As evidenced by prime numbers and composites, we learn this idea at an early age. Categorizing these broken-down components into their simplest form allows mathematicians to construct proofs from emergent patterns. John Conway’s Atlas of Finite Groups in the 1990s was particularly concerned with the categorization of structures known as groups. There are certain axioms a group must adhere to, which amount to the retention of symmetry; ultimately a group helps us to better understand symmetric actions performed on a set with a binary operation. …

Go to article

The Evolution And Impact Of Blog Analysis Tools: A Study Of Blogtracker's Comprehensive Approach To Digital Discourse Analysis, Oyindamola Koleoso May 2025

The Evolution And Impact Of Blog Analysis Tools: A Study Of Blogtracker's Comprehensive Approach To Digital Discourse Analysis, Oyindamola Koleoso

Theses and Dissertations

This study presents BlogTracker, a comprehensive web-based platform designed to address the growing complexities of analyzing the modern blogosphere. We detail BlogTracker's evolution from earlier blog analysis tools, highlighting its innovative integration of features including real-time data collection, advanced content analysis, sentiment analysis, influence tracking, and narrative analysis. At the core of our contribution is a robust content extraction system that achieves 91.33% accuracy across diverse blog formats, providing a reliable foundation for all analytical functions. This extraction system effectively distinguishes between primary content and peripheral elements, ensuring high-quality inputs for downstream analysis regardless of source blog structure. The platform's …

Go to article

Modeling Cross-Platform Narrative Templates: A Temporal Knowledge Graph Approach, Ridwan Amure May 2025

Modeling Cross-Platform Narrative Templates: A Temporal Knowledge Graph Approach, Ridwan Amure

Theses and Dissertations

Over the past decade, social media platforms have rapidly evolved in scale, functionality, and user engagement, encouraging individuals to maintain active presences across multiple networks. This complex, interconnected ecosystem has also enabled information actors to exploit cross-platform dynamics to amplify the reach of their content and strategically target diverse audiences. Recognizing the persistence and adaptability of such actors, this research emphasizes the need for robust models that can effectively capture and analyze cross-platform narrative diffusion. To this end, we propose a framework that utilizes temporal knowledge graphs to model the evolution and relationships among narratives across platforms. We extract temporal …

Go to article

Existence Of Traveling Waves In A Predator-Prey Invasion Model With Nonlocal Dispersal And Delayed Effects In Dispersal, Austin Simms May 2025

Existence Of Traveling Waves In A Predator-Prey Invasion Model With Nonlocal Dispersal And Delayed Effects In Dispersal, Austin Simms

Theses and Dissertations

We investigate the existence and stability of traveling wave solutions in a predator--prey population model that incorporates both nonlocal dispersal and time-delayed interactions. The problem arises when species distributions and feeding or reproduction processes do not respond instantaneously, but rather exhibit lags in space and time. Our aim is to understand how these delays and nonlocal effects impact the wavefront speed and the eventual establishment of a predator population in previously prey-dominated regions. To accomplish this, we derive a PDE--integro--delay system from ecological considerations of prey self-regulation, predator ratio dependence, and jump-type dispersal kernels. We then employ a traveling wave …

Go to article

A Preliminary Study Of Hilbert–Kunz Functions: Coefficient Behavior In A Normal Affine Semigroup Ring, Jesus A. Mendiola Herrera May 2025

A Preliminary Study Of Hilbert–Kunz Functions: Coefficient Behavior In A Normal Affine Semigroup Ring, Jesus A. Mendiola Herrera

Theses and Dissertations

In 1890, David Hilbert published a set of notes on what now constitutes one of the bases of Commutative Algebra; his work would eventually influence the efforts of mathematicians like Ernst Kunz. In 1969, Ernst Kunz introduced a particular mapping regarding modules of regular local rings. His goal was to characterize Noetherian local rings of prime characteristic by computing the length of the composition series under Frobenius power transformations. In this thesis, the focus will be on stating the initial steps on finding the coefficients of the Hilbert-Kunz function of the normal affine semigroup ring of the form R = …

Go to article

Assessing The Effect Of Covid-19 On Air Quality For Five Texas Metro Areas Using Daily Air Quality Index Values, Rahul Sahajpal May 2025

Assessing The Effect Of Covid-19 On Air Quality For Five Texas Metro Areas Using Daily Air Quality Index Values, Rahul Sahajpal

Theses and Dissertations

Air pollution is one of the biggest health hazards known to humans. The quality of the air that we breath is mainly determined by the level of six major air pollutants, Carbon Monoxide (CO), Nitrogen dioxide (NO2), Particulate Matter 10 (PM 10), Particulate Matter 2.5 (PM 2.5), Sulfur dioxide (SO2) and Ozone (O3). The main source of these air pollutants are fossil fuels (Oil, Coal and Natural gas). Their levels in the air are reported using an Air Quality Index (AQI). Higher AQI values indicate bad air quality and vice versa. In this study …

Go to article

Dynamic Approaches To Missing Data In Healthcare: Evaluating Ensemble Models, Feature Selection, And Meta-Features, Dylan Dominguez Sulca May 2025

Dynamic Approaches To Missing Data In Healthcare: Evaluating Ensemble Models, Feature Selection, And Meta-Features, Dylan Dominguez Sulca

Theses and Dissertations

Missing data is pervasive in healthcare, where incomplete observations commonly arise from patient dropout, sensor failures, or privacy constraints. This research presents an investigation into handling such data, focusing on (1) Missingness-Aware Dynamic Ensemble Weighting (MDEW), (2) feature selection under varying missing rates, (3) autoencoder-based imputation (ODAE), and (4) a meta-feature analysis guiding pipeline selection. We evaluate our experiments on four diverse datasets, Cleveland Heart Disease, Diabetic Retinopathy, Breast Cancer Wisconsin, EEG Eye State. Our research shows that MDEW adaptively selects imputer classifier pipelines, outperforming single model and uniform averaging baselines at moderate to high missingness 10% to 50%. Filter …

Go to article

First Prev Next Last