Digital Commons Network^™

Evaluating Diagnostic Information Preservation In Weakly Supervised Medical Imaging, Vinceline Bertrand

Electronic Theses and Dissertations 2020 - Present

Weakly supervised medical imaging models trained with coarse image-level labels often report strong performance on metrics such as accuracy and AUC. This thesis argues that these metrics can be misleading: a model may succeed on a coarse diagnostic task while failing to preserve the fine-grained information needed for consequential clinical decisions. It makes this failure measurable through the diagnostic gap, defined as the divergence between coarse and fine-grained diagnostic preservation, across three connected studies. The first shows that near-perfect ovarian ultrasound accuracy reflects visual separability rather than pathological understanding. The second measures the diagnostic gap in a mammographic pipeline, where …

Experimental Material Analysis And Load Monitoring Of Polyurethane–Steel Belts Subjected To Static And Cyclic Dynamic Loading: Implications For Continuous Mooring Line Systems In Wave Energy Converters, Youssef Mohamed

Electronic Theses and Dissertations 2020 - Present

This study experimentally investigates the mechanical and viscoelastic behavior of a steel-cord-reinforced polyurethane synchronous belt capable of withstanding continuous cyclic loading as a potential compliant mooring element for WEC applications. Quasi-static and cyclic tensile tests were conducted to characterize the belt's mechanical response. The quasi-static determined that the belt behaved as a stiff, low-strain tensile member. Under approximately 100 kgf, the belt extended by about 0.107mm over a 250mm gauge length, apparent tensile modulus of 5.41GPa, an axial rigidity of 2.44MN, and an equivalent line stiffness of 9.75MN/m. Cyclic tensile testing showed high dynamic stiffness with stiffness-transfer ratio of 0.924. …

Rfsoc Based Ground Penetrating Radar For Detection And Avoidance Of Underground Utilities, Brady Bowerbank

Theses and Dissertations

Preexisting underground utilities present a considerable danger to underground boring projects. Gas and electrical lines can be damaged, leading to major economic impact and even loss of life. While maps of underground utilities exist, they are not always accurate and gas and electrical lines can shift over time, necessitating tools to accurately detect utilities so that crews can steer the machines away from any possible danger. In this thesis, the design of a new frequency-modulated continuous-wave (FMCW) ground penetrating radar (GPR) is outlined. The design of a lightweight, flexible radar is demonstrated using the CASPER FPGA framework with an operating …

Isoperimetric Soft Robots, Mihai Stanciu

Theses and Dissertations

This thesis presents two advances in isoperimetric soft robotic trusses that improve their performance, modularity, and configurability. The first contribution introduces a large-scale modular robotic truss designed as a lightweight, reconfigurable structure for lunar applications. The system consists of inflatable fabric tubes routed through motorized roller units and interconnected by a newly developed spherical joint that enables multiple robotic triangles to connect at a common vertex. The resulting truss can be assembled into structures beyond a single octahedron while retaining compact stowage when deflated and untethered operation after initial inflation. Experimental validation demonstrates modular assembly, long-term pressure retention, load-bearing capabilities …

Thermophysical Property Studies: 1. Thermodynamic Consistency For Associating Compounds 2. Autoignition Temperature, Cassandra Jane Guffey

Theses and Dissertations

Accurate thermophysical property data are essential for the design, optimization, and safe operation of chemical processes. Properties such as vapor pressure, enthalpy of vaporization, heat capacity, density, and autoignition temperature--which are among the properties studied in this work--are required for equipment sizing, process simulation, hazard assessment, and economic evaluation. A major focus of this dissertation is the application of multi-property thermodynamic consistency techniques to compounds that exhibit strong vapor-phase association. These methods improve confidence in recommended property values by enforcing rigorous thermodynamic relationships among ideal-gas heat capacity, liquid heat capacity, vapor and liquid densities, vapor pressure, and enthalpy of vaporization. …

A Review On Bridge Scour Analysis In Cohesive Soils And Scour-Susceptible Rocks, Darud E. Sheefa, Zhen Liu, Stanley Vitton, Brian Barkdoll

Michigan Tech Publications

Bridge scour analysis, especially scour depth calculation practices implemented mostly by hydraulics and geotechnical engineers, was traditionally built upon flume tests with cohesionless materials, e.g., sands. As a result, the analysis of bridge scour in cohesive materials, i.e., cohesive soils and scour-susceptible rocks, was less understood and thus has been gaining increasing attention. This paper presents a state-of-the-practice survey on the analysis of bridge scour in cohesive materials represented by cohesive soils and scour-susceptible rocks. This includes a literature review covering the concepts and understanding of scour susceptibility, material sampling, erodibility tests, bridge scour calculation methods for cohesive soils and …

Development And Testing Of A Computer Vision Pose Estimation System For Planar Mobile Robots, Andrew Jones

Master's Theses

This thesis details the development and testing of a computer vision-based real-time pose estimation system for differential drive robots. A single camera with a fisheye lens is used to locate ArUco markers placed at fixed locations and attached to robots. Using the OpenCV library, the Perspective-n-Point (PnP) problem is solved to facilitate the transformation of 2-D robot positions in an image to world-frame coordinates. An analytical solution is presented to estimate robot poses based on a single PnP solution, rather than solving the PnP problem for each pose estimate. Pose information is relayed to individual robots using a multi-microcontroller architecture …

Hyperchaotic Noise Generation For Adversarial Encryption In Privacy-Preserving Image Classification, Neeraja Beesetti

Master's Theses

Artificial intelligence systems make useful predictions by taking in data and returning a classification, recommendation, or decision. Obtaining that prediction, however, requires sharing the data first. This creates a fundamental privacy challenge in machine learning: users must expose their data to receive a valuable prediction. Machine learning systems increasingly rely on cloud-based image classification for this reason, transmitting images from edge devices to remote servers rather than running large models locally. This creates a conflict between the accuracy a classifier requires and the privacy a data owner wants. Traditional encryption destroys the image structure on which a classifier depends, while …

Development Of Reduced Conflict U-Turn (Rcut) Guidance In Kentucky, Travis Thompson, Duane Thomas, Jill Asher, Jeff Jasper

Kentucky Transportation Center Research Report

A reduced conflict U-turn (RCUT) intersection eliminates left-turn and through movements from the minor road. Instead, drivers must turn right onto the main road and complete a U-turn at a downstream median opening. Recognized by the Federal Highway Administration (FHWA) as a proven safety countermeasure, RCUT intersections have reduced fatal and injury crashes 22 – 63%. Despite more than 35 RCUT intersections in operation across Kentucky, the Kentucky Transportation Cabinet (KYTC) lacked specific guidance for their planning, design, construction, and operation.

This project, conducted by the Kentucky Transportation Center (KTC) in cooperation with KYTC, addressed this gap through a comprehensive …

Chameleon Carriers In Trucking: Detection, Enforcement, And Financial And Safety Impacts, Brian Howell, Drew Law, Andrew Martin

Kentucky Transportation Center Research Report

Chameleon carriers are motor carriers that evade regulatory enforcement by dissolving and reregistering under new corporate identities. This study, commissioned by the Kentucky Transportation Cabinet (KYTC), examined how states characterize, detect, and respond to chameleon carrier activity and assessed its financial and safety impacts in Kentucky from 2020 through 2025. The research team conducted a literature review of existing agency practices and relevant stakeholder perspectives, reviewed administrative codes and statutes across 13 pilot states, and administered two structured surveys to state motor carrier credentialing officials examining carrier characterization and enforcement practices. An analysis of KYTC's carrier data flagged by CVIEW …

Characterization, Transport Modeling, And Image Analysis Of Rover-Terrain Interaction For Lunar Regolith In-Situ Resource Utilization, Luke A. Manolescu

All Theses

NASA has declared a return to the lunar surface and the need and demand for sophisticated In-situ Resource Utilization (ISRU) is the highest in history. ISRU will require regolith excavation, transport, and processing in order to harvest the valuable resources available, support surface operations, and keep astronauts alive. Characterizing the lunar regolith is essential to understanding the mechanical and physical behavior of the material that will be used to construct berms and structurally support astronaut habitats and landers. Any construction on Earth requires an in-depth geotechnical site assessment prior to any construction to rule out any potential site issues that …

Evaluating Drug Concentration Profiles In Wastewater To Develop A Framework For Estimating Drug User Populations, Carl Michael E. Espinosa

All Theses

Chemical compounds, including licit and illicit drugs can be measured in wastewater and used to assess community drug consumption, providing valuable information for public health agencies, law enforcement, and local communities. While previous research primarily focused on estimating the per capita community drug consumption using back-calculation, this research focused on utilizing literature-derived parameters including drug dosage, renal excretion fraction, and sewer stability to develop a framework to estimate the user populations using Monte Carlo simulations. Samples were collected from two wastewater treatment facilities representing the Generostee Creek WWTP’s sewershed (GCS) and Mauldin Road WRRF’s sewershed (MRS). The target analytes included …

Investigating The Effects Of Draw Parameters On The Refractive Index Profiles Of Phosphosilicate Fibers, Brandi Baldus

All Theses

P₂O₅ is a common dopant core material in silica-based glass optical fibers, in part due to its ability to increase the refractive index of silica, required for the fiber to guide light. However, P₂O₅-doped fibers can show a significant decrease in the refractive index profile compared to that of the parent preform. The question arises as to whether the refractive index decreasing could be a direct result of the fiber draw process and, if so, what is it about the draw process that causing such changes in phosphosilicate fibers. More specifically, this Thesis explores the hypothesis that these draw-induced reductions …

A Transfer-Learning And Continuous Optimization-Based Framework For Predicting Heat Treatment-Dependent Mechanical Properties Of Ded-Processed Low-Alloy Steels, Atiqur Rahman, Sung Heng Wu, Ranjit Joy, Frank Liou

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Directed energy deposition (DED) of low-alloy steels involves strongly coupled effects among alloy composition, solidification behavior, and post-deposition heat treatment, making mechanical property prediction difficult when target-domain data are limited. This study develops a transfer-learning and continuous optimization framework for predicting heat treatment-dependent yield strength (YS), ultimate tensile strength (UTS), hardness (HV), and as-solidified phase fractions of martensite, ferrite, and austenite in DED-processed low-alloy steels. A CALPHAD-based dataset was generated for 125 low-alloy steel compositions. A multilayer perceptron (MLP) surrogate was first trained as a baseline model, then fine-tuned through transfer learning and progressively updated as staged continuous optimization; the …

Missing-Data-Tolerant Diffusion-Based Wind Power Scenario Forecasting Method, Yingying Shi, Xiaochong Dong, Guobin Fu, Miaomiao Ma, Yanhe Li, Xuebin Wang

Journal of System Simulation

Abstract: To address the issue of error accumulation in traditional "imputation-then-forecasting" approaches, a missing data tolerant diffusion framework (MDTDF) is proposed. An XGBoost regression model is employed to map numerical weather prediction data into deterministic power forecasts. The encoder in the denoising network extracts temporal features, which are fused with the deterministic forecasts and fed into the decoder through a cross-attention mechanism to guide the denoising process. A historical constraint mechanism is introduced to directly utilize incomplete historical data and dynamically correct the denoising result at each step through sample gradient updates and noise injection guided by historical information. The …

A Method For Assessing The Contribution Degree Of An Aviation Delivery System And Identifying Key Equipment, Xiaofeng Liu, Chengze Jiang, Xingyu Chen, Deyin Jiang, Bolin Shang, Bifeng Song

Journal of System Simulation

Abstract: Based on the delivery efficiency and delivery quality, a general aviation delivery system effectiveness evaluation model was constructed, and a calculation method of system contribution degree based on efficiency was given. By combining the system calculation experiment and simulation experiment based on agent-based modeling and simulation (ABMS), the design idea of the Monte Carlo simulation experiment for key equipment identification and equipment technology development trend analysis was sorted out, and the key equipment identification method based on ABMS and contribution evaluation was proposed. By taking the intercontinental long-range aviation delivery mission as an example, a variety of simulation experiments …

Sensorless Control Of Pmsm Based On An Improved Super-Twisting Sliding-Mode Observer, Shiyu Chen, Xinmin Chen, Xionglong Hu, Heng Wang, Yepeng Han, Jiajie Chen

Journal of System Simulation

Abstract: To address the chattering in back electromotive force estimation and the gain mismatch across a wide speed range when using a conventional super-twisting sliding-mode observer in the sensorless control system of a permanent-magnet synchronous motor, this paper proposed an improved adaptive-gain super-twisting sliding-mode observer. A linear correction term was introduced into the super-twisting algorithm and integrated with a gain adaptation law based on speed feedback, enabling the system to achieve finite-time convergence and high-precision back electromotive force estimation over a wide speed range. A variable-gain adaptive complex-coefficient filter was constructed to effectively suppress the harmonic components in the observed …

Field Calibration Of Flow Over Tilting Weirs In Canals, Joseph E. Pugh, Timothy K. Gates, S. Karan Venayagamoorthy, Caner Kutlu

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Tilting weirs are widely used to regulate water levels in open channel irrigation systems and can also provide flow measurement capability that helps optimize irrigation efficiency and ensure equitable water distribution. This case study demonstrates adaptation of lab-based tilting weir ratings to field settings, where flow behavior is more complex. We compile and analyze an extensive data set derived from independent studies of five structures within three canal systems, featuring both lined and unlined channels with discharge ranging from 0.35 to 15 m3/s (12 to 530 ft3/s). Results indicate that lab-based rating equations can be calibrated to account for site-specific …

Evaluation Of General Voronoi Diagram Decomposition For Harmonic Fields In Navigation Of Dynamic Environments, Franco Abullarade

Master's Theses

Harmonic potential fields provide provably minimum-free navigation, but any change to the workspace geometry invalidates the field and forces a costly global recomputation, typically restricting them to static environments. This thesis extends the harmonic map framework of Vlantis et al., which maps the free workspace onto a unit disk and uses an atlas of per-region transformations, to dynamic indoor settings. First, we replace their manually annotated room partition with an automatic decomposition based on the Generalized Voronoi Diagram, allowing the atlas to be built from an arbitrary occupancy grid in an automated way. Second, we introduce a localized repair procedure …

Multidimensional Determinants Of Gait, Balance, And Softball Performance In Female Youth: Biomechanics, Resource Access, And Psychosocial Factors, Allie G. Mcauliffe

Master's Theses

Movement quality is a fundamental indicator of healthy childhood development and supports physical, emotional, psychosocial, and cognitive well-being. Movement quality is influenced by multiple biomechanical, environmental, and psychosocial factors, yet the relationships among them remain poorly understood in underrepresented populations such as female youth, particularly in softball. Previous studies have largely examined biomechanics, resource access, and psychosocial experience independently, and few have investigated how these factors interact in female youth softball players. To address this gap, this study compared gait and balance characteristics between softball (N = 34) and non-softball (N = 7) female youth, examined associations between resource access, …

Evaluation Of Kentucky’S Work Zone Speed Camera Pilot Program: Speed And Crash Analyses, Xu Zhang, William Staats, Eric Green

Kentucky Transportation Center Research Report

Kentucky introduced automated speed enforcement in work zones to mitigate hazards and improve the safety of motorists and workers. This study describes the impacts of automated speed enforcement at five pilot sites. Researchers analyzed speed data and crash data from pilot sites and paired control sites. The control sites and pilot sites had similar traffic volumes, lane configurations, and functional classifications. Analysis drew on over 15 million individual speed records captured using automated enforcement cameras as well as segment-level speed data from HERE.  Active enforcement at pilot sites was associated with lower mean, 85th-percentile, and 99th-percentile vehicle speeds. Average vehicle …

Understanding The Correlation Between Prediction Performance And Trust In Ai Through Scenario-Based Tasks, Likhitha Kammara

Theses and Dissertations

Trust in artificial intelligence is commonly assessed through self-reported scales or behavioral reliance, yet behavioral reliance is retrospective and can only be observed after a decision has already been made. This thesis examines whether prediction accuracy — a user's ability to predict what an AI system will recommend before its output is revealed — can serve as a prospective correlate of trust in the same empirical sense as behavioral reliance. The study was conducted in two phases using scenario-based AI decision tasks across disaster response, healthcare, and infrastructure restoration contexts, employing a between-group design in which participants either predicted AI …

Building Services Engineering July/August 2026

Building Services Engineering

This issue of Building Services Engineering features heat pumps, propane usage, solar power, and ventilation for indoor air quality. Features include district heating, HVACR optimisation, lift retrofitting, EU water policy, and an interview with WiBSE Ireland Chair Heather Holt.

Id-More Vision: Real-Data Machine-Learning Assessment For A Digital-Twin-Inspired, Xr-Ready Rehabilitation Prototype, Rickey L. Clark

Master's Theses

Rehabilitation assessment often relies on periodic observation, while many XR prototypes show scripted rather than recorded-motion evidence. iD-MORE Vision is an offline pipeline trained on KIMORE and IRDS and linked through JSON packets to a two-mode Unity desktop prototype. Both datasets include controls and rehabilitation participants with neurologic, musculoskeletal, or mobility impairments. This improves relevance but does not clinically validate the system.

Under fixed subject-wise splits, the primary five-seed Random Forest predicted KIMORE clinician scores with MAE 6.087 ± 0.044 cTS and R² 0.568 ± 0.006; the subject-level R² interval crossed zero. The primary IRDS five-run CUDA GRU averaged 0.877 …

Developing A Rapid Urban Forest Assessment System For Sustainable City Greenification, Daniel Gonzalez

Master's Theses

This thesis presents the Rapid Urban Forest Assessment (RUFA) system, a web-based platform that integrates urban tree inventories and aerial tree detection to assess forest health across California’s census-designated places. RUFA combines inventoried tree records with coordinates detected from high-resolution multispectral imagery using convolutional neural networks, then computes a composite RUFA Score from four metrics: canopy cover percentage, trees per capita, tree diversity (TD-50), and tree evenness. The thesis addresses two engineering challenges in building the dashboard: querying and aggregating over seven million tree records in real time, and rendering spatial summaries at multiple zoom levels without recomputing cluster assignments …

Probabilistic Modeling Of Hurricane Hazards And Structural Reliability Of Offshore Wind Turbines Under Climate Change, Susmita Bhowmik

All Dissertations

Hurricanes are among the most destructive natural hazards in the United States, especially along the Atlantic and Gulf coasts. Climate change is expected to affect hurricane activity by changing important environmental conditions. At the same time, offshore wind energy is expanding, creating a need to understand hurricane risks to offshore wind turbines.

This dissertation develops a stochastic hurricane simulation framework to estimate hurricane wind hazards for coastal and offshore regions along the U.S. East Coast and Gulf Coast. The framework generates synthetic hurricane tracks using updated storm-frequency data and is validated against historical records from HURDAT2, NOAA buoy wind observations, …

A Surface-Bound Detection Architecture For Label-Free Evanescent-Wave Sensing Of Cobalt In Complex Fluids, Jeremiah W. Carpenter

All Dissertations

Cobalt exposure is a clinical concern in orthopedic implant surveillance, where cobalt-chromium wear debris can release ions detectable in blood and urine, and an environmental concern in mining-affected and industrial water systems. Reference laboratory methods, including inductively coupled plasma mass spectrometry, provide sensitive quantification but require centralized instrumentation, trained personnel, and controlled sample handling, which limits their availability for routine screening in decentralized clinical and environmental contexts. This dissertation develops a surface-bound detection architecture for label-free evanescent-wave sensing of cobalt in complex fluids. The architecture rests on a physical necessity argument grounded in interfacial optics: at physiologically and environmentally relevant …

Theory-Informed Generative Agents For Human Behavioral Modeling In Disasters, Liming Lu

All Dissertations

This dissertation develops a theory-informed generative-agent framework for modeling human behavioral decisions in disasters. Existing flood and disaster preparedness models often emphasize physical hazards, infrastructure exposure, or statistical correlations, but they struggle to capture the heterogeneous and evolving choices households make. This limitation is especially important for climate-related hazards, where future damage depends not only on changes in rainfall, inundation, and urban development, but also on decentralized protective actions such as house elevation, flood insurance, evacuation, and early preparedness. The dissertation integrates two empirical studies: a flood-risk study in Charleston, South Carolina, and a household disaster-preparedness study across hurricane contexts. …

Smart Process Planning For Automated Fiber Placement, Matthew J. Godbold

All Dissertations

Automated Fiber Placement (AFP) is a preeminent manufacturing technology for producing high-performance composite structures, offering precise material placement, reduced waste, and the potential for highly optimized lightweight designs. While AFP has been widely adopted in aerospace applications, its broader use across industries such as automotive, wind energy, maritime, and sporting goods remains limited. A key barrier to wider adoption is the traditional separation of design, manufacturing, and inspection processes, which drives up cost and results in inefficiencies, sub-optimal designs, and limited feedback between lifecycle stages. In current practice, manufacturing is treated as an isolated process, disconnected from early-stage design decisions …

Integrated Power, Energy, And Thermal Management For Autonomous Hybrid Off-Road Vehicles: Multi-Timescale Modeling, Predictive Control, And Resilient Thermal Design, Anirudh Sundar

All Dissertations

Electrification and autonomy are increasingly important for off-road vehicles operating in construction, agriculture, mining, defense, and other demanding environments. These platforms must deliver high tractive power under unstructured terrain, harsh ambient conditions, low-speed operation, and large auxiliary loads. While hybrid and electrified powertrains offer improved efficiency, mobility, and auxiliary power capability, they also introduce significant challenges in managing tightly coupled power, energy, and thermal subsystems. In particular, lithium-ion batteries, power electronics, electric machines, and internal combustion engine-generator systems operate across different temperature limits and timescales, requiring coordinated management to ensure efficiency, durability, and safe operation. This dissertation develops modeling, planning, …