Digital Commons Network^™

Faculty Senate Minutes, Georgia Southern University, Faculty Senate

Faculty Senate Minutes

No abstract provided.

The George-Anne Daily, Georgia Southern University

George-Anne Media Group: Newsletters & Magazines

No abstract provided.

A Real-Time Mobile Robotic System For Crack Detection In Construction Using Two-Stage Deep Learning, Emmanuella Ogun, Yong Ann Voeurn, Doyun Lee

Civil Engineering & Construction: Faculty Publications

The deterioration of civil infrastructure poses a significant threat to public safety, yet conventional manual inspections remain subjective, labor-intensive, and constrained by accessibility. To address these challenges, this paper presents a real-time robotic inspection system that integrates deep learning perception and autonomous navigation. The proposed framework employs a two-stage neural network: a U-Net for initial segmentation followed by a Pix2Pix conditional generative adversarial network (GAN) that utilizes adversarial residual learning to refine boundary accuracy and suppress false positives. When deployed on an Unmanned Ground Vehicle (UGV) equipped with an RGB-D camera and LiDAR, this framework enables simultaneous automated crack detection …

Leveraging Wastewater Resource Recovery To Reduce Landfill Organic Loading: Process Modeling, Environmental, And Economic Impact Assessment, Ahmed I. Yunus, Arjun T. Ramshankar, Zainab O. Akinsemoyin, Thomas Igou, Ameet Pinto, George Fu, Yongsheng Chen, Joe F. Bozeman Iii

Civil Engineering & Construction: Faculty Publications

No abstract provided.

2026 Conference Program, Georgia Southern University

SoTL Commons Conference

No abstract provided.

Security-Oriented Voice Authentication Using Machine Learning, Ifeoluwa Stella Elegbe

College of Graduate Studies: Theses & Dissertations

This study develops and evaluates a machine learning and deep learning-based voice authentication system for secure identity verification. As traditional authentication methods such as passwords, PINs, and security tokens continue to face challenges, including identity theft, forgetting, and unauthorized access, voice biometrics offers a more secure, convenient, and user-friendly alternative, especially for remote, hands-free, and accessibility-focused applications. The study adopts a closed-set speaker identification framework, where the system determines the most likely speaker from a predefined group of enrolled users. A structured methodology is implemented, beginning with audio preprocessing and feature extraction. Key acoustic features, including Mel-Frequency Cepstral Coefficients (MFCCs), …

2026 Spring Commencement, Georgia Southern University

Commencement Programs

No abstract provided.

Assessing The Diversity And Composition Of Crayfish Assemblages In The Ogeechee River Basin, Reginald Turner

College of Graduate Studies: Theses & Dissertations

Crayfish assemblage composition in the southeastern United States is understudied relative to other aquatic taxa, such as aquatic insects and fishes, and the Coastal Plain watersheds of that region are particularly underrepresented in the contemporary literature on this topic. For example, although 38% of the crayfish species in Georgia are considered “species of greatest conservation need,” most of the distributional data used to make these designations are outdated, with some dating back over 50 years. This thesis sought to update our understanding of the contemporary distributions of crayfish species within the Ogeechee River Basin (ORB), a watershed in southeastern Georgia …

Comprehensive Performance Evaluation Of Devops Infrastructure Under Dynamic Workloads, Abdulrazaq Mamud

College of Graduate Studies: Theses & Dissertations

This research aims to investigate performance optimization and reliability issues related to cloud-based computing environments through an analysis of three key infrastructure components: virtualized CPU resource management, distributed API rate limiting, and web server deployment architectures. This research combines machine learning and system experimentation as a way of exploring the impact of infrastructure-level behaviors on overall system performance and scalability. The first component of the research focuses on analyzing CPU Fragmentation in Virtualized Environments, where unbalanced workload allocation on Virtual CPU Cores causes increased tail latency, resulting in Service Level Agreement violations. Metrics are analyzed using the Random Forest classifier …

The Effect Of Chamber Geometry On The Performance Of Oscillating Water Column, Timilehin O. Osunade

College of Graduate Studies: Theses & Dissertations

This thesis investigates the effect of internal chamber geometry on the performance of a piezoelectric oscillating water column (OWC) wave energy harvester. Four acrylic chamber configurations with internal top-surface angles of 0°, 30°, 45°, and 60° were tested under 32 controlled conditions combining synchronous (SYN) and asynchronous (ASC) forcing at input voltages of 4, 6, 8, and 10 V. A 35 mm piezoelectric disc mounted at the chamber roof served as the power take-off element and, subject to the RC-limit caveat disclosed in Section 3.2.1, as a first-order dynamic analogue of the chamber pressure for phase-based compressibility analysis. All test …

Association Between Internet Use For Health Information And Alzheimer’S Disease Diagnosis Among Older Adults With Diabetes In The United States: Examining Racial And Gender Disparities, Henry M. Zeidan

College of Graduate Studies: Theses & Dissertations

This study uses data from the National Health and Aging Trends Study (NHATS) Round 13, collected in 2024, to examine whether internet use for health information is associated with Alzheimer’s disease diagnosis among older adults with diabetes in the United States. Given the rising adoption of digital health, understanding who benefits from online health resources is increasingly important. The research also examines whether these associations differ across racial and gender groups, offering insight into potential disparities in digital health engagement and cognitive outcomes. Findings from this study will inform clinical practice, public health programming, and strategies to ensure equitable access …

A Unified Automated And Explainable Ai Framework For Drug Discovery, Clinical Diagnostics, And Public Health Data Prediction, Lord Coffie

College of Graduate Studies: Theses & Dissertations

This thesis investigates the development of automated, explainable artificial intelligence systems to improve automated scientific discovery, clinical diagnostic support, and public health decision-making. Three independent yet thematically aligned studies were conducted across cheminformatics, radiology, and population health. Study A introduces an automated and explainable machine learning pipeline for Quantitative Structure–Activity Relationship (QSAR) modeling using RDKit-derived molecular descriptors. The pipeline performs systematic preprocessing, consensus-based feature selection (mutual information, random forest importance, RFECV), and benchmarks six supervised models—Random Forest, XGBoost, Support Vector Machine, Balanced Random Forest, EasyEnsembleClassifier, and a blended meta-ensemble, achieving AUC = 0.90 and accuracy = 0.83, while ensuring interpretability …

Viscoelastic Behavior Of Magnetically Filled Pdms Elastomers: Influence Of Filler Loading And Particle Type, Madison Procyk

College of Graduate Studies: Theses & Dissertations

Magnetorheological elastomers (MREs) offer a promising pathway for soft, magnetically actuated drug‑delivery systems, yet material‑selection guidelines remain unclear due to limited comparative data across particle chemistries, size scales, and concentrations. This study systematically evaluates how magnetic filler type (carbonyl iron and magnetite) and particle size (micro vs. nano), at two weight percentages – 40 wt% and 50 wt% – in Sylgard 184 PDMS influence the viscoelastic behavior of MREs intended for compliant biomedical actuation. Eight particle formulations were prepared through sieving, controlled mixing, vacuum degassing, and isotropic curing, producing nineteen total specimens (16 with filler particles and 3 without). Dynamic …

A Real-Time Autonomous Mobile Robotic System For Crack Detection And 3d Laser Profiling In Construction Using Two-Stage Deep Learning, Emmanuella Ogun

College of Graduate Studies: Theses & Dissertations

This thesis presents an autonomous mobile robotic system that integrates real-time visual crack detection with laser-based three-dimensional profiling for building inspection. The system coordinates SLAM-based navigation, deep learning perception, and manipulator-guided measurement within a unified ROS 2 framework, enabling scan-on-demand workflows where laser profiling occurs selectively at visually detected defect locations. The detection pipeline employs a two-stage architecture combining U-Net semantic segmentation with Pix2Pix residual refinement, achieving 73.9% mean intersection-over-union and 76.4% F1-score on the CrackSeg9k benchmark while maintaining 16 frames-per-second real-time throughput. Real-world validation demonstrated 95% detection success on 80 campus images under challenging conditions. The profiling subsystem utilizes …

Ai-Driven Real-Time Detection Of Zero-Day Browser Exploits Using Webassembly-Based Instrumentation, Temitope Damilola Elijah

College of Graduate Studies: Theses & Dissertations

The rapid evolution of web browsers into fully fledged application execution environments has significantly expanded their attack surface, making them prime targets for sophisticated zero-day exploits that evade traditional signature-based security mechanisms. To address this challenge, this research proposes an AI-driven framework for real-time detection and analysis of zero-day exploits in web browsers by integrating browser-level telemetry monitoring, unsupervised anomaly detection, and large language model–based threat interpretation. The framework introduces a lightweight WebAssembly telemetry agent embedded within the browser runtime to capture low-level execution behaviors, including WASM module instantiation, memory growth patterns, network interactions, and runtime API activity. These telemetry …

Impact Of Tactical Breathing On Marksmanship And Cognitive Function After Anaerobic Fatigue In Law Enforcement Personnel, Jackson D. Gilleland

College of Graduate Studies: Theses & Dissertations

Background: Tactical breathing is commonly used in law enforcement training to regulate stress, yet limited evidence exists regarding its acute effectiveness following physical fatigue. Purpose: To examine whether a brief tactical breathing intervention improves shooting performance and heart rate variability (HRV) following anaerobic fatigue in law enforcement officers. Methods: Thirty-eight officers completed baseline HR/HRV and a shoot/no-shoot scenario, followed by a maximal 500-m row and post-fatigue shooting. Participants were assigned to either a control group or a tactical breathing group, which received brief instruction and coaching before post-testing. Results: No significant between-group differences were observed for A-zone accuracy, shot time, …

Ai-Driven Penetration Testing For Arm Systems: A Comprehensive Framework With Experimental Validation, Matthew Ragsdale

College of Graduate Studies: Theses & Dissertations

The convergence of artificial intelligence and cybersecurity presents new opportunities for automated penetration testing capable of discovering, prioritizing, and remediating vulnerabilities at machine speed. However, deployment on resource-constrained ARM platforms remains unexplored despite ARM’s dominance in mobile, IoT, and edge computing with over 280 billion chips deployed globally. This thesis presents systematic experimental evaluation of AI-driven penetration testing across four paradigms—traditional machine learning, deep learning, large language models, and reinforcement learning—on three ARM platform tiers: Raspberry Pi 5 (8GB, Cortex-A76), Radxa ROCK 5B Plus (16GB LPDDR5 with NPU), and NVIDIA Jetson Nano (4GB with Maxwell GPU). The experimental framework generates …

Influence Of The Sst K-Ω Stress-Limiter Coefficient On Transonic Shock Buffet Prediction For The Oat15a Supercritical Airfoil, Melinawo Vowotor

College of Graduate Studies: Theses & Dissertations

Transonic shock buffet predictions using the Shear Stress Transport (SST) k–ω turbulence model are known to be sensitive to the stress-limiter coefficient a₁, yet no systematic investigation of this sensitivity exists. This thesis presents a parametric study of a₁ for two-dimensional URANS simulation of shock buffet on the OAT15A supercritical airfoil at M = 0.73 and Re = 3 × 10⁶. Eleven a₁ values (0.25–0.37) are examined at α = 3.5°, and a matrix of five a₁ values across five angles of attack (3.0°–3.9°) maps the interaction with incidence. The results reveal that a₁ acts as a bifurcation parameter: a …

Network-Aware Airline-Specific Flight Delay Prediction Using Tree-Based Ensemble Models, Mary Dufie Afrane

College of Graduate Studies: Theses & Dissertations

Flight delays pose persistent challenges to the efficiency and reliability of air transportation systems, affecting airlines, airports, regulators, and passengers alike. As traffic demand grows and operational environments become increasingly interconnected, accurately predicting both departure and arrival delays has become crucial for effective planning and mitigation. This study presents a network-aware, airline-specific framework for predicting flight delays in U.S. domestic air transportation systems using tree-based ensemble machine learning models. A large-scale dataset of 1.98 million flights, enriched with weather information, is used to develop predictive models for both departure and arrival delays. To capture the structural and operational complexity of …

Pixel-To-World Mapping For Multi-Camera Warehouse Robot Localization, Mariam Faruque Sharif

College of Graduate Studies: Theses & Dissertations

This thesis presents a comprehensive framework for camera calibration and pixel-to-world coordinate mapping for multi-camera robot localization in a structured warehouse environment. The study is conducted in the APRN-ROWS laboratory, where four overhead cameras observe a planar grid of known barcode locations used as the reference coordinate system.

The proposed approach combines geometric modeling and optimization-based techniques to estimate camera parameters. Initially, camera extrinsic parameters, including position and orientation, are derived using physical measurements and geometric relationships. Principal point locations are estimated through a zoom-based alignment method, ensuring accurate correspondence between the optical axis and the world coordinate system. Intrinsic …

Enhancing Military Health System Organizational Efficiency And Quality Of Care Through A Social-Ecological Framework, Eric L. Peipelman

College of Graduate Studies: Theses & Dissertations

Timely and fair adjudication of incivility-related actions within the Department of Defense (DoD) and Military Health System (MHS) is increasingly crucial for maintaining accountability, mission readiness, and quality of care. Ongoing delays in resolving workplace complaints and inefficiencies in resource-heavy adjudications highlight the need to shift from reactive complaint handling toward proactive civility promotion and transparent decision-making. This Integrated Learning Experience (ILE) introduces the Peipelman Civility Discussion and Assessment Toolkit (PCDAT)—a comprehensive, evidence-based framework designed to improve civility, optimize resources, and enhance communication, even in the MHS. Based on the Social-Ecological Model (SEM) and adapted from the Workplace Power and …

The Effect Of Complexity Of Expert Testimony And The Presence Of A Defensive Rebuttal On Jurors' Decisions In Criminal Trials, Shelby E. Madden

College of Graduate Studies: Theses & Dissertations

Forensic science plays a critical role in criminal trials, yet forensic techniques vary in their reliability. Expert testimony, often held in high regard by jurors, can be a decisive factor in verdicts, but its influence is complicated by factors such as technical complexity, adversarial bias, and heuristic processing. The present study examined how the complexity of prosecution expert testimony and the presence of a defensive rebuttal influenced jurors’ decisions when presented with faulty forensic evidence. Participants (N = 142) were randomly assigned to one of four conditions in a 2 (testimony complexity: high v. low) x 2 (defensive rebuttal …

Examining Firefighter Perceptions Of Stress And Recovery Across A Shift And Engagement In Recovery Activities, Nathan T. Ebersole

College of Graduate Studies: Theses & Dissertations

The occupational demands of firefighting, such as fire suppression and rescue tasks, working in hazardous conditions, inconsistent sleep patterns, and exposure to traumatic events, can lead to work-related injuries, burnout, and feelings of isolation. To date, there is limited research on the impact of a single work-shift on firefighter perceptions of stress and recovery and the recovery activities that may influence these perceptions. Thus, the purpose of this study was to examine the effect of a single work-shift on firefighter perceptions of stress and recovery status as well as the recovery activities firefighters choose to engage in. Forty-three firefighters across …

Emotion Regulation: The Effectiveness Of Reappraisal And Potential Benefit Of Music, Ezra J. Greidinger

College of Graduate Studies: Theses & Dissertations

Literature has supported potential benefits to cognitive reappraisal as a method of emotion regulation, as well as intentional music usage as an enhancer of these effects. It has been suggested that instruction be provided to individuals to use these methods, especially in highly stressed populations (Sakka et al., 2018). However, there has not been an experimental study to follow up on these claims. When instruction is provided, is cognitive reappraisal more effective than naturally developed habits in regulating anxiety, and would music enhance these effects? College students (N = 170) were randomly assigned to three treatment conditions: control, cognitive reappraisal, …

Early Icu Physiological Subtyping From Time-Series Data: A Comparative Study Of Feature Complexity, Predictive Performance, And Model Interpretability, Rojeena Khadka

College of Graduate Studies: Theses & Dissertations

Intensive Care Unit (ICU) patients do not follow a single uniform physiological pattern. Patients admitted with the same diagnosis show different clinical trajectories over time making standardized classification and treatment approaches insufficient. The increasing availability of large-scale electronic health records in MIMIC-IV makes it possible to investigate such heterogeneity through data-driven approach that captures how physiology evolves during the early phase of ICU admission. This thesis compares two analytical pipelines designed to identify physiological subtypes from the first 48 hours of ICU time series data. This study then assesses how well these subtypes predict in-hospital mortality. The first approach, referred …

Modeling Accreditation Standards And Evaluation Methods To Inform Strategic Planning In Public Health Education, Debra Rich

College of Graduate Studies: Theses & Dissertations

Public health has long benefited from the relationship between postsecondary education, accreditation, and government employment. Assessment and accreditation are important tools in postsecondary education to ensure fiscal responsibility, professional competencies, and quality assurance. The competency standards implemented in post-secondary education are not under the direct control of the federal government; however, policy amendments aimed at specific accreditation criteria could result in changes to public health curriculum and create eligibility barriers for students who rely on federal financial support. The Central Washington University Public Health program has provided educational support in professional public health for decades, and there is an increased …

The Battle Of Eden Station: Locating The Linchpin In Sherman’S Savannah Campaign, Roberto J. Jorge Jr

College of Graduate Studies: Theses & Dissertations

In December 1864, General William T. Sherman’s Union army approached Savannah, Georgia, towards the end of his “March to the Sea.” The Fifteenth Army Corps, part of Sherman’s Right Wing and commanded by General P. J. Osterhaus, crossed the Ogeechee River at Jencks and Wright’s Bridges, and advanced towards Station No.2 on the Central of Georgia Railway and the crossroads at Eden Station, located in Effingham County, Georgia. Three companies of the Tenth Battalion, North Carolina Heavy Artillery contested the crossing, falling back to multiple defensive positions before escaping by train in an effort to delay Sherman’s inevitable advance on …

Roadway Runoff Impacts To Trout Streams Studies For Ms4 Permit, Jobayed Hossain Badhan

College of Graduate Studies: Theses & Dissertations

Roadway runoff from Georgia Department of Transportation (GDOT) highway infrastructure poses measurable, but temporally constrained threats to cold-water trout ecosystems in northern Georgia. This study investigates temperature and dissolved oxygen (DO) dynamics in three secondary trout streams receiving GDOT roadway discharges, with the primary objective of evaluating compliance with Georgia Rule 391-3-6-.03(6)(ii),(v) under the Municipal Separate Storm Sewer System (MS4) permit framework. Field monitoring was conducted from April 2024 through October 2025 across two consecutive summer seasons using a tiered, multi-instrument approach: YSI ProDSS handheld grab sampling provided regulatory-grade reference measurements; HOBO MX-801 optical DO dataloggers recorded continuous 5-minute-interval temperature …

Effects Of Composition, Nodularity, Pouring Temperature, Inoculation, And Mold Strength On Wall-Movement In Sgi Castings During Solidification And Cooling, Noah Brack

College of Graduate Studies: Theses & Dissertations

The iron-carbon casting alloy known as spheroidal graphite iron (SGI), nodular graphite iron, or ductile iron (DI) experiences complex volume changes during its solidification and cooling as graphite nodules and austenite form. These volume changes result in forces on the mold cavity walls and can deform the mold walls in cases when mold walls lack the strength to resist the deformation. This wall movement can cause the formation of casting defects such as swell, warped part geometry, and shrinkage porosity. Though this phenomenon has been studied in the past, it remains difficult to predict casting wall movement with existing data. …

Formalizing Asymmetric Control-Telemetry Separation In Distributed Industrial Control Systems, Andrew Manison

College of Graduate Studies: Theses & Dissertations

Distributed industrial control systems often place control and telemetry traffic on the same communication substrate even though the two workloads impose different requirements. Control paths need bounded request-response latency and predictable acknowledgement semantics, whereas telemetry paths benefit from scalable publish-subscribe fanout and tolerance for consumer-side delay. This thesis argues that, for the tested class of mixed workloads on shared commodity infrastructure, these communication roles should be separated architecturally rather than forced through a single protocol. To evaluate that claim, the thesis formalizes an asymmetric control- telemetry pattern and instantiates it in the Asymtra framework using gRPC for synchronous control and …