Engineering Commons^™

A Memory Efficient Deep Recurrent Q-Learning Approach For Autonomous Wildfire Surveillance, Jeremy A. Cantor

UNF Graduate Theses and Dissertations

Previous literature demonstrates that autonomous UAVs (unmanned aerial vehicles) have the po- tential to be utilized for wildfire surveillance. This advanced technology empowers firefighters by providing them with critical information, thereby facilitating more informed decision-making processes. This thesis applies deep Q-learning techniques to the problem of control policy design under the objective that the UAVs collectively identify the maximum number of locations that are under fire, assuming the UAVs can share their observations. The prohibitively large state space underlying the control policy motivates a neural network approximation, but prior work used only convolutional layers to extract spatial fire information from …

Investigating The Role Of Tesserae In Energy Absorption In Shark Cartilage, Molly Dobrow

UNF Graduate Theses and Dissertations

Unlike mammals, shark endoskeletons are composed of cartilage, which is less stiff compared to bone. Despite this structural disadvantage, sharks have risen to become apex predators, with reported maximum posterior bite force estimates approximating 5914 N in bull sharks. Shark jaws are estimated to undergo high cycle loading within the organism’s lifecycle without evidence of failure. Fatigue resistance may relate to mineral distribution within a component of the endoskeletal system – tesserae. Tesserae are thin, roughly hexagonal tiles composed of calcium phosphate hydroxyapatite (HA) crystals and grow by accretion to eventually surround the hyaline cartilage core. Though tesserae dimensions are …

Enhancing Comfort And Sustainability: Analyzing The Impact Of Natural Ventilation And Eco-Friendly Materials On Indoor Temperature Reduction, Hyo Won Lee

UNF Graduate Theses and Dissertations

As the world grapples with issues such as increasing energy consumption, climate change, and environmental degradation, the need for sustainable solutions is becoming more and more urgent. In this context, passive cooling has emerged as one of the promising approaches to achieve energy efficiency in various sectors. This research study the basic concept of passive cooling to new buildings to identify synergies in energy savings when reducing temperature inside buildings and applying eco-friendly materials, and to explore potential benefits for promoting sustainable development. By analyzing existing research, case studies, and technological advancements, this study seeks to highlight the feasibility and …

Transformer-Enabled Deep Reinforcement Learning For Coverage Path Planning, Daniel B. Tiu

UNF Graduate Theses and Dissertations

Coverage path planning (CPP) is the problem of covering all points in an environment and is a well-researched topic in robotics due to its sheer practical relevance. This paper investigates such an offline CPP problem where the primary objective is to minimize the path length to achieve complete coverage. Furthermore, the literature suggests that taking turns leads to a higher energy use than going straight. To this end, we design a novel objective function that aims to minimize the number of turns as well. We have proposed a deep reinforcement learning (DRL)-based framework that uses a Transformer model. Unlike state-of-the-art …

Explainable Automated Inconsistency Detection In Biomedical And Health Literature, Prajwol Lamichhane

UNF Graduate Theses and Dissertations

Given the exponential growth of scientific information online, researchers often face the daunting task of detecting contradictory statements on crucial health topics. This work develops a comprehensive pipeline for automated contradiction detection that integrates an Information Retrieval (IR) system, machine learning classifiers, and Explainable AI (XAI). The Information Retrieval system is tailored for biomedical data and comprises a datastore, syntactic, and semantic components. Users can input queries, initiating a pipeline that identifies top documents through syntactic analysis and refines results via semantic examination for relevant research claims. Employing a diverse range of Large Language Models such as pre-trained Distil-BERT, BioBERT, …

Development Of Erosion Functions For Micp-Treated Beach Sand, Saeed Booshi

UNF Graduate Theses and Dissertations

This thesis investigates the effectiveness of microbially-induced calcium carbonate precipitation (MICP) using the recently introduced bioslurry treatment method via surface percolation. To simulate realistic water forcing conditions, a piston-style erosion rate testing apparatus, specifically the Florida Department of Transportation Sediment Erosion Rate Flume, was used. Initial tests conducted at a high shear stress of 42 Pa revealed that a combination of 15% bioslurry and 85% cementation solution exhibited the strongest erosion resistance when compared to other ratios between bioslurry and cementation solution. Subsequent experiments focused on separating the specimen into a "loose" part and a “surface crust,” with shear stresses …

Process, Structure, & Property Investigation Of Gallium-Based Metallic Alloys Processed At Room Temperature, Jennifer E. Ruliffson

UNF Graduate Theses and Dissertations

Metallic and intermetallic alloys are important in engineering, necessitating a thorough comprehension of their structure, processing, and properties. Amalgams are a class of alloy which are synthesized by various methods to produce diverse properties. Gallium-based amalgams, particularly gallium eutectic alloys, have low melting points, which allow for applications in dentistry and temperature sensitive electronics. This thesis investigates the process-structure-property relationships of gallium-based amalgams mixed with copper. Phases, microstructure, and diffusion processes are investigated using XRD and SEM. Adhesion strength and thermal properties are then correlated to these as well as process steps. This study contributes to advancing the understanding and …

Processing Of Niti Sma For High Reflectivity Applications, Nicholas Dean Asbury

UNF Graduate Theses and Dissertations

Nickel Titanium (NiTi) is a shape memory alloy (SMA) that is capable of being deformed and subsequently returned to the original shape through heating. This unique property makes NiTi a prime material for potential applications in the aerospace industry. As manufacturing capabilities advance, the ability to produce and implement advanced materials, such as shape memory alloys like NiTi, becomes more feasible. One such application being studied is deployable mirrors for imaging satellites. Reflector and mirror surfaces for imaging in the visible and infra-red range of the light spectrum require low surface roughness across the largest allowable area for the collection …

Anomaly Detection Approaches Of Energy Storage Systems Using Kalman Filter And Machine Learning Techniques, Phadungsak Tubuntoeng

UNF Graduate Theses and Dissertations

The increasing prevalence of cyber-attacks poses a significant concern, particularly within critical infrastructures like the power system. Such attacks have the potential to cause substantial impacts on essential services, economic stability, and national security. Energy storage systems (ESS) are integral components of the power grid and are particularly vulnerable to cyber threats. These vulnerabilities can be exploited through various means, including two-way communication, web portals, and remote access.

Given the critical nature of ESS, the ability to detect and mitigate malicious cyber-attacks is imperative. Various methods can be employed for cyber-attack detection, including signature-based, anomaly-based, and behavior-based approaches. In this …

Breast Density Classification Using Deep Learning, Conrad Thomas Testagrose

UNF Graduate Theses and Dissertations

Breast density screenings are an accepted means to determine a patient's predisposed risk of breast cancer development. Although the direct correlation is not fully understood, breast cancer risk increases with higher levels of mammographic breast density. Radiologists visually assess a patient's breast density using mammogram images and assign a density score based on four breast density categories outlined by the Breast Imaging and Reporting Data Systems (BI-RADS). There have been efforts to develop automated tools that assist radiologists with increasing workloads and to help reduce the intra- and inter-rater variability between radiologists. In this thesis, I explored two deep-learning-based approaches …

Towards A Prototype Paleo-Detector For Supernova Neutrino And Dark Matter Detection, Emilie Marie Lavoie-Ingram

UNF Graduate Theses and Dissertations

Using ancient minerals as paleo-detectors is a proposed experimental technique expected to transform supernova neutrino and dark matter detection. In this technique, minerals are processed and closely analyzed for nanometer scale damage track remnants from nuclear recoils caused by supernova neutrinos and possibly dark matter. These damage tracks present the opportunity to directly detect and characterize the core-collapse supernova rate of the Milky Way Galaxy as well as the presence of dark matter. Current literature presents theoretical estimates for these potential tracks, however, there is little research investigating the experimental feasibility of this technique. At the University of North Florida, …

Assessing The Performance Of A Particle Swarm Optimization Mobility Algorithm In A Hybrid Wi-Fi/Lora Flying Ad Hoc Network, William David Paredes

UNF Graduate Theses and Dissertations

Research on Flying Ad-Hoc Networks (FANETs) has increased due to the availability of Unmanned Aerial Vehicles (UAVs) and the electronic components that control and connect them. Many applications, such as 3D mapping, construction inspection, or emergency response operations could benefit from an application and adaptation of swarm intelligence-based deployments of multiple UAVs. Such groups of cooperating UAVs, through the use of local rules, could be seen as network nodes establishing an ad-hoc network for communication purposes.

One FANET application is to provide communication coverage over an area where communication infrastructure is unavailable. A crucial part of a FANET implementation is …

Investigation Of Microstructurally Dependent Mechanical Properties Of Cold Sprayed Copper Using Correlative Microscopy, Quintin Otto

UNF Graduate Theses and Dissertations

This project employs multi-instrument materials characterization to analyze material made with the “Cold Spray” additive manufacturing process. Cold spray is an emerging additive manufacturing technique with unique benefits resulting from its low temperature adhesion process induced by plastic deformation. Metallic powder collides at high speeds creating three dimensional materials and coatings without the need for melting. Copper cold sprayed specimens were analyzed using a series of imaging techniques to characterize the microstructure at varying levels of detail and magnification. Scanning electron microscopy and electron back scattered diffraction were paired with microhardness testing to generate a correlative comparison between microstructure and …

Modified Reactive Sputter Deposition Of Titanium Nitride Thin Films Via Hipims With Kick-Pulse And Improvement Of The Structure-Zone Model, Andrew Miceli

UNF Graduate Theses and Dissertations

Direct current (DC) and radio frequency (RF) sputtering methods have been commonplace in industry for several decades and widely studied in literature. Hard films of nitrides, such as titanium nitride (TiN), have been deposited using reactive DC sputtering onto cutting tools and medical devices extensively as well. For these applications, the films require excellent adhesion, high density, and high hardness. High-Power Impulse Magnetron Sputtering (HIPIMS) has emerged over the last several years as a method to produce films with increased density and mechanical properties. Process-structure-property relationships for reactive HIPIMS are not yet well developed. Additionally, conventional HIPIMS suffers from relatively …

Energy-Efficient Hmac For Wireless Communications, Cesar Enrique Castellon Escobar

UNF Graduate Theses and Dissertations

This thesis introduces the Farming Lightweight Protocol (FLP) optimized for energy-restricted environments that depend upon secure communication, such as multi-robot information gathering systems within the vision of ``smart'' agriculture. FLP uses a hash-based message authentication code (HMAC) to achieve data integrity. HMAC implementations, resting upon repeated use of the SHA256 hashing operator, impose additional resource requirements and thus also impact system availability. We address this particular integrity/availability trade-off by proposing an energy-saving algorithmic engineering method on the internal SHA256 hashing operator. The energy-efficient hash is designed to maintain the original security benefits yet reduce the negative effects on system availability. …

Extracting Road Surface Marking Features From Aerial Images Using Deep Learning, Michael Kimollo

UNF Graduate Theses and Dissertations

The traffic and roadway safety agencies spend significant efforts each year collecting roadway data, including lane configurations and other road surface marking data, such as areas with school zone markings, sidewalks, left turns, right turns, bicycle lanes, etc., for safety analysis and planning purposes. The current manual data collection methods pose significant operational and quality control challenges as they are costly and prone to errors. In addition to that the manual data collection is labor intensive and takes too much time involving high equipment costs, questionable data accuracy guarantees, and concerns about the safety of the crew.

This study aims …

Investigation On The Influence Of Augmented Reality Adoption And Cybersecurity In The Architecture, Engineering And Construction Industry, Kavyaa Boopathy

UNF Graduate Theses and Dissertations

Augmented Reality (AR) applications and the digitization of Architecture, Engineering, and Construction (AEC) industry processes, such as the online building permit process (BPP), have introduced new developments that simplifies tasks, and enhanced data accessibility for stakeholders. This created a digital landscape where sensitive information and critical processes are intertwined, making them vulnerable to cyber-attacks. Existing studies and frameworks on a) AR adoption doesn’t provide essential information (e.g., material availability and costs from different suppliers) and AR features to cater to the diverse needs of different stakeholders. b) threat modeling requires a domain and context specific need investigation, process exploration, critical …

Development Of High Kinetic Inductance Superconducting Nanowire Devices On High Permittivity Strontium Titanate Substrates, Jamie Timmons

UNF Graduate Theses and Dissertations

This thesis involves the fabrication and characterization of devices made from two different superconducting materials: yttrium barium copper oxide (YBCO), a high-TC complex oxide, and niobium nitride (NbN), a low-TC transition metal nitride. Both types of devices are fabricated on strontium titanate substrates, which provides a good lattice match to YBCO and also an extremely large permittivity at low temperature. We demonstrate that wet etching of YBCO thin films via bromine can be a viable microfrabriation technique for the material. Using approximately 35 nm thick epitaxially grown YBCO on an STO substrate, we were able to fabricate YBCO “microwires” with …

Development Of Practical Assessment Techniques For Sinkhole Potential In Florida Based On Sinkhole Vulnerability Indices, Sylvia Pesha

UNF Graduate Theses and Dissertations

Sinkholes are natural geohazards prevalent in Florida's distinctive karst geology, posing risks to public safety, infrastructure, and groundwater integrity. Considering the increasing frequency of sinkhole occurrences in Florida due to land development in vulnerable soils, understanding the potential for sinkhole occurrence can aid in the identification of high-risk locations and inform effective mitigation strategies. Researchers have developed three point-based indices to be used when assessing the vulnerability a project site has to sinkhole formation based on the encountered subsurface conditions. Engineers have historically used an index based on the subsurface layer thicknesses, called the Raveling Index (RI). In recent years, …

Crystalline Analysis Of Geomicrobially-Induced Calcium Carbonate Precipitation In Sands Using A Surface Percolation Treatment Technique, Justin Edward Mulloney

UNF Graduate Theses and Dissertations

Ottawa 50/70 sand specimens and natural beach sand samples were treated using bio-augmented geomicrobies via a surface percolation technique. Testing was conducted on these specimens to determine how resultant calcium carbonate precipitation changed as a function of temperature, depth from the surface, and in the presence of magnesium. Specifically, x-ray Diffraction (XRD), a Scanning Electron Microscope (SEM), and Energy Dispersive X-ray Spectroscopy (EDS) were used to determine and quantify the presence of calcium carbonate and its associated phase. Results showed a direct relationship between temperature and precipitated calcium carbonate. In addition, as an unintended consequence associated with the treatment, ammonium …

A Predictive Modeling Approach To Counter Failures In Heat Seal Process Verification Methods, Charles Albanese

UNF Graduate Theses and Dissertations

Most products sold today are packaged in a protective shell that involves the design of a box or wrapper. A subset of such products also adds a second layer of protection via sterilization. For both sterilized and non-sterilized products, a procedure referred to as the heat seal process creates the protective barrier from outside influence. For sterilized products, the American Society for Testing and Materials provides standards to test or verify seal strength, and this verification is normally accomplished by using a process called a Design of Experiments (DOE). The DOE method makes systematic use of powerful data collection and …

Comparison Between Pervious Oyster Shell Habitat (Posh) Unit And Reef Ball Performance Along An Eroding Shoreline In Northeast Florida, Jacob Waggoner

UNF Graduate Theses and Dissertations

This study compared two methods of shoreline protection – the common Reef Ball and the novel Pervious Oyster Shell Habitat (POSH). Both structures are meant to attenuate wave energy and subsequently reduce shoreline erosion. While Reef Balls have a long, documented history of effectively mitigating beach erosion, POSH units are new structures and their effectiveness had not yet been previously assessed. Clusters of POSH units and Reef Balls were deployed at the Timucuan Ecological and Historic Preserve’s shoreline at Kingsley Plantation. Wave staffs were placed seaward and shoreward from these clusters and wave heights were measured over a holiday weekend …

Histological Comparison Of Shark Dermis Across Various Ecomorphologies, Olivia Schuitema

UNF Graduate Theses and Dissertations

The integument plays essential roles in the structural support, protection, and hydrodynamic capability among fishes. Most shark skin research has been done on the external epidermal layer containing the dermal denticles, while the larger dermis layer has been mostly ignored. The dermis layer in sharks is composed of two layers, the upper stratum laxum and the lower stratum compactum, holding supportive collagen and elastin fibers. There may be morphological and compositional differences in the dermis layers across various species of sharks, although the extent of such is unknown. These potential differences may be represented by various dermal thicknesses and different …

Methodology To Treat Bottom Friction Losses For Modeling Wave Transformation From Deepwater To The Nearshore: An Application In Northeast Florida, Oscar Solisromero

UNF Graduate Theses and Dissertations

Designers and other practitioners confront a wide range of problems in the coastal zone, which often require long-term nearshore wave data. However, such data are usually quite scarce. Consequently, either wave measurements from buoys deployed in deep water, or archived deepwater wave hindcast information, must be utilized by rigorous, physics-based transformation to the site of interest using one of many available numerical models. A main issue in conducting such an effort is accounting for losses in wave energy due to bottom friction, for which establishing a suitable bed friction coefficient (C_f) can be problematic. In the present study, …

Prolonged Exposure To Microgravity Increases Susceptibility To Traumatic Brain Injury, Ryan Baskerville

UNF Graduate Theses and Dissertations

With the prospect of semi-permanent and permanent habitable fixtures on the moon and Mars, the complications associated with long-term exposure to microgravity should be investigated exhaustively. Spaceflight Associated Neuro-Ocular Syndrome (SANS), a group of neurological and ocular effects resulting from prolonged exposure to microgravity, is characterized by significant fluid shifts into the cranium, namely cerebrospinal fluid and blood, and an upward shift of the brain relative to the skull. This syndrome, along with its immediate effects on visual acuity, cognitive ability, and motor function are recognized by NASA, but its effects on susceptibility to traumatic brain injury have yet to …

Investigating Changes In Trends Of Traffic Crashes Due To Covid-19 Pandemic In Florida’S Freeways, Ntagwanko Kisabanzira

UNF Graduate Theses and Dissertations

The COVID-19 pandemic outbreak caused a shift in traffic patterns that have in turn influenced a change in traffic accident trends. Due to stay-at-home orders that were issued across the United States, transportation agencies reported low traffic demands on highways after the pandemic outbreak. Low traffic volumes are associated with relatively higher speeds that are linked to increased severity of crashes. Several states reported an increase in fatal crashes after the outbreak of the COVID-19 pandemic. This paper evaluates the traffic crash trends on three interstates in Florida (I-10, I-75, and I-95) and sheds light on what happened before, during, …

Bounded-Degree Plane Geometric Spanners: Connecting The Dots Between Theory And Practice, Matthew Alexander Graham

UNF Graduate Theses and Dissertations

The construction of bounded-degree plane geometric spanners has been a focus of interest since 2002 when Bose, Gudmundsson, and Smid proposed the first algorithm to construct such spanners. To date, eleven algorithms have been designed with various trade-offs in degree and stretch factor. We have implemented these sophisticated algorithms in C++ using the CGAL library and experimented with them using large synthetic and real-world pointsets. Our experiments have revealed their practical behavior and real-world efficacy. We share the implementations via GitHub for broader uses and future research.

We present a simple practical algorithm, named AppxStretchFactor, that can estimate stretch factors …

Advance Metallic Reinforcement Of Vat Photo Polymerized Parts, Scott Zinn

UNF Graduate Theses and Dissertations

The metallization or metallic reinforcement of polymer parts has been widely used in industry for several decades. Polymer parts are classically metalized for aesthetics, chemical and thermal resistance, electrical conductivity, and mechanical strength. Metallization has been shown to increase strength of polymer parts when compared to the strength of the bulk material without metallization. Additive manufacturing (AM) techniques that have emerged in the last few decades produce parts with different surface features and chemistry than the typical polymer part produced through injection molding. AM parts are typically weaker than traditionally manufactured parts from the same material due to intrinsic details …

The Investigation Of The Underlying Microstructure Associated With Fracture Features In 6061 Cold Sprayed Aluminum, Justin White

UNF Graduate Theses and Dissertations

Cold gas dynamic spraying commonly known as cold spray is a process currently used for restoration, re-tolerancing, and application of coatings. With additional resources allocated towards the development of a through process model aimed at predicting the properties of bulk material produced via the Cold Spray process, more lab testing and investigation must be done to capture the effects of the varying microstructure in CS materials. The properties of ultra-fine-grained materials are derived from data collected from coarse grained materials and processes that do not accurately capture the effects as elevated strain rates and ultra-fine-grained materials. The lack of property …

Modeling Coastal Vulnerability Of The St. Johns River And Northeastern Florida Shorelines, Madison E. Heppe

UNF Graduate Theses and Dissertations

Coastal and riverine communities, with anthropogenic congestion and natural and economic resources, are vulnerable to climate change impacts including rising sea levels and increasing severity and frequency of storms. Coastal habitats are being increasingly recognized as natural infrastructure that provides resiliency against these stressors. However, few studies have analyzed coastal vulnerability at landscape scale with finely resolved spatial data that account for habitats and demographics. The purpose of this study is to map the coastal vulnerability of the St. Johns River and adjacent Northeastern Florida Atlantic shoreline within the St. Johns River Water Management District. Unique to this study is …