Digital Commons Network^™

Human Visual Search Performance For Close Range Detection Of Static Targets From Moving Sensor Platforms, Jennifer Hewitt

Graduate Thesis and Dissertation 2023-2024

Search models based on human perception have been developed by military researchers over the past few decades and have both military and commercial applications for sensor design and implementation. These models are created primarily for static imagery, and accurately predict task performance for systems with stationary targets and stationary sensors, if the observer is given infinite time to make targeting decisions. To account for situations where decisions must be made on a shortened time scale, the time-limited search model was developed to describe how task performance evolves with time. Recent variations of this model have been made to account for …

Deep Learning One-Class Classification With Support Vector Methods, Hayden D. Hampton

Graduate Thesis and Dissertation 2023-2024

Through the specialized lens of one-class classification, anomalies–irregular observations that uncharacteristically diverge from normative data patterns–are comprehensively studied. This dissertation focuses on advancing boundary-based methods in one-class classification, a critical approach to anomaly detection. These methodologies delineate optimal decision boundaries, thereby facilitating a distinct separation between normal and anomalous observations. Encompassing traditional approaches such as One-Class Support Vector Machine and Support Vector Data Description, recent adaptations in deep learning offer a rich ground for innovation in anomaly detection. This dissertation proposes three novel deep learning methods for one-class classification, aiming to enhance the efficacy and accuracy of anomaly detection in …

Advancing Policy Insights: Opinion Data Analysis And Discourse Structuring Using Llms, Aaditya Bhatia

Graduate Thesis and Dissertation 2023-2024

The growing volume of opinion data presents a significant challenge for policymakers striving to distill public sentiment into actionable decisions. This study aims to explore the capability of large language models (LLMs) to synthesize public opinion data into coherent policy recommendations. We specifically leverage Mistral 7B and Mixtral 8x7B models for text generation and have developed an architecture to process vast amounts of unstructured information, integrate diverse viewpoints, and extract actionable insights aligned with public opinion. Using a retrospective data analysis of the Polis platform debates published by the Computational Democracy Project, this study examines multiple datasets that span local …

Enhancing Scanning Tunneling Microscopy With Automation And Machine Learning, Darian Smalley

Graduate Thesis and Dissertation 2023-2024

The scanning tunneling microscope (STM) is one of the most advanced surface science tools capable of atomic resolution imaging and atomic manipulation. Unfortunately, STM has many time-consuming bottlenecks, like probe conditioning, tip instability, and noise artificing, which causes the technique to have low experimental throughput. This dissertation describes my efforts to address these challenges through automation and machine learning. It consists of two main sections each describing four projects for a total of eight studies.

The first section details two studies on nanoscale sample fabrication and two studies on STM tip preparation. The first two studies describe the fabrication of …

Validating Machine And Human Decision-Making In Forensic Fire Debris Analysis, Frances A. Whitehead

Graduate Thesis and Dissertation 2023-2024

This work presents a background on the chemical complexity of fire debris analysis, including an ever-present matrix of pyrolysis products as the catalyst that led to the creation of the National Center for Forensic Science's Fire Debris Database. A selection of these 1,000+ casework-relevant ground truth samples was used to create two newly proposed analyst workflows to connect the current method of categorical reporting with evaluative reporting practices reflective of the strength of the evidence. Both workflows use linear sequential unmasking to help mitigate bias, a discrete scoring system for quantification of the analysis, and receiver operating characteristic (ROC) curves …

The Case For Photothermal Spectroscopy In The Future Of Planetary Science Missions, Christopher T. Cox

Graduate Thesis and Dissertation 2023-2024

Optical PhotoThermal InfraRed (O-PTIR) is a relatively new spectroscopy method for studying materials. It produces transmission-like spectra using a remote reflectance technique that is rapid, requires little sample preparation, and is well-suited for the technique to be adapted for a space flight instrument. The method involves a tunable pulsed IR laser creating a photothermal effect on the surface of a material and measuring the distortion of a probing visible laser in the same region of the sample, which can be obtained at sub-micron spatial resolutions. A measurement campaign was performed utilizing Photothermal Spectroscopy Corporation's O-PTIR instrument, mIRage®. In this campaign, …

Optical Seed Development For Yb-Fiber Laser, James G. Brutus

Graduate Thesis and Dissertation 2023-2024

Master Oscillator Power Amplifiers (MOPA) are laser systems that utilize a seed and pump amplification system to boost the output power of high-quality lower power seeding signals. MOPAs can generate high gain while avoiding many of the nonlinearities that negatively affect resonance-based lasers that are known to feature higher internal intensities. Additionally, MOPAs provide an easy alternative to the construction of novel laser technologies for higher output power as they can be easily combined with existing laser sources to amplify their output power.

This thesis outlines the design of an ytterbium-doped fiber laser (YDFL), featuring a MOPA architecture. The YDFL …

Theoretical Framework Of Exchange Coupled Tripartite Spin Systems With Magnetic Anisotropy And Predictions Of Spin And Electronic Transport Properties For Their Use In Quantum Architectures, Eric Switzer

Electronic Theses and Dissertations, 2020-

There has been significant interest in spin systems involving two or more coupled spins as a single logical qubit, particularly for scalable quantum computing architectures. Recent realizations include the so-called singlet-triplet qubits and coupled magnetic molecules. An important class of coupled-spin systems, the three-spin paradigm for spin greater than 1/2, has not yet been fully realized in scalable qubit architectures. In this thesis, I develop the theoretical framework to investigate a class of tripartite spin models for realistic systems. First, I model a spin 1/2 particle (e.g., an electron) and two spin 1 particles (in a dimer arrangement) coupled with …

Deep Video Understanding With Model Efficiency And Sparse Active Labeling, Aayush Jung Bahadur Rana

Electronic Theses and Dissertations, 2020-

Videos capture the inherently sequential nature of the real world, making automatic video understanding an essential need for automatic understanding of the real world. Due to major advancements in camera, communication, and storage hardware, videos have become a widely used data format for crucial applications such as home automation, security, analysis, robotics, and autonomous driving. Existing methods for video understanding require heavy computation and large training data for good performance, this limits how quick the videos can be processed and how much data can be labeled for training. Real-world video understanding requires analyzing dense scenes and sequential information, which increases …

Topological Data Analysis Using The Mapper Algorithm, Jessica Girard

Electronic Theses and Dissertations, 2020-

Topological data analysis is an expanding field that attempts to obtain qualitative information from a data set using topological ideas. There are two common methods of topological data analysis: persistent homology and the Mapper algorithm; the focus of this thesis is on the latter. In this thesis, we will be discussing the key ideas behind the Mapper algorithm, following the flow from Morse Theory to Reeb graphs to the topological version of the algorithm and finally to the statistical version. Lastly, we will present an application of Mapper to the USAIR97 data set using the RTDAmapper package.

Theoretical Analysis Of Charge Conduction And Rectification In Self-Assembled-Monolayers In Molecular Junctions, Francis Adoah

Electronic Theses and Dissertations, 2020-

As electrical devices shrink to the atomic scale, it is expected that Moore's law will soon be obsolete for semiconductor devices. In 1974, Avriam and Ratner predicted that organic devices could replace semiconductor technology, leading to extensive research on molecular-based organic devices. This dissertation delves into the theoretical frameworks used to examine the transport in molecular junctions and aims to enhance our comprehension of charge transport and conduction properties. The studies presented in this thesis illustrates that a molecule's alteration by just a single atom can change it from an insulator to a conductor, and also that, by fine-tuning the …

Annotation Efficient Visual Recognition: From Semi-Supervised To Few-Shot Learning, Mamshad Nayeem Rizve

Electronic Theses and Dissertations, 2020-

In recent years, supervised deep learning has achieved remarkable success in solving a wide range of visual recognition problems. Large-scale labeled datasets have been crucial for this success and the progress has primarily been limited to controlled environments. In this dissertation, we present methods to improve the annotation efficiency of deep visual recognition models and also propose methods to improve the performance of annotation-efficient models in unconstrained open-world settings. To address the annotation bottleneck in supervised learning, we introduce a pseudo-labeling framework for semi-supervised learning. While consistency regularization methods dominate the field, they heavily rely on domain-specific data augmentations, limiting …

Towards Efficient And Effective Representation Learning For Image And Video Understanding, Taojiannan Yang

Electronic Theses and Dissertations, 2020-

Deep learning has achieved tremendous success on various computer vision tasks. However, deep learning methods and models are usually computationally expensive, making it hard to train and deploy, especially on resource-constrained devices. In this dissertation, we explore how to improve the efficiency and effectiveness of deep learning methods from various perspectives. We first propose a new learning method to learn computationally adaptive representations. Traditional neural networks are static. However, our method trains adaptive neural networks that can adjust their computational cost during runtime, avoiding the need to train and deploy multiple networks for dynamic resource budgets. Next, we extend our …

Due Tomorrow, Do Tomorrow: Measuring And Reducing Procrastination Behavior Among Introductory Physics Students In An Online Environment, Zachary Felker

Electronic Theses and Dissertations, 2020-

This work is focused on the measurement and prevention of procrastination behavior among college level introductory physics students completing online assignments in the form of mastery-based online learning modules. The research is conducted in two studies. The first study evaluates the effectiveness of offering students the opportunity to earn a small amount of extra credit for completing portions of their homework early. Unsupervised machine learning is used to identify an optimum cutoff duration which differentiates taking a short break during a continuous study session from a long break between two different study sessions. Using this cutoff, the study shows that …

Human Recognition Theory And Facial Recognition Technology: A Topic Modeling Approach To Understanding The Ethical Implication Of A Developing Algorithmic Technologies Landscape On How We View Ourselves And Are Viewed By Others, Hajer Albalawi

Electronic Theses and Dissertations, 2020-

The emergence of algorithmic-driven technology has significantly impacted human life in the current century. Algorithms, as versatile constructs, hold different meanings across various disciplines, including computer science, mathematics, social science, and human-artificial intelligence studies. This study defines algorithms from an ethical perspective as the foundation of an information society and focuses on their implications in the context of human recognition. Facial recognition technology, driven by algorithms, has gained widespread use, raising important ethical questions regarding privacy, bias, and accuracy. This dissertation aims to explore the impact of algorithms on machine perception of human individuals and how humans perceive one another …

Efficient Convolutional Neural Networks For Image Classification And Regression, Muhammad Tayyab

Electronic Theses and Dissertations, 2020-

Neural networks have been a topic of research since 1970s and the Convolutional Neural Networks (CNNs) were first shown to work well for hand written digits recognition in 1998. These early networks were however still shallow and contained only a few layers. Moreover these networks were mostly trained on a small amount of data in contrast to the modern CNNs which contain hundreds of convolution layers and are trained on millions of images. However, this recent shift in machine learning comes at a cost. Modern neural networks have extremely large number of parameters and require huge amount of computations for …

Florida's Vanishing Heritage: Climate Risk And Adaptation At Florida Heritage Sites, Levi Watson

Electronic Theses and Dissertations, 2020-

This thesis examines history and preservation at coastal cultural heritage sites threatened by climate change and explores climate adaptation strategies at two sites on Florida's Atlantic coast. Current climate change models indicate the planet may see as much as 1.1 meters, or four feet, of global average sea level rise by the year 2100, requiring site managers to intervene by using adaptation techniques to improve resilience and guard against the loss of cultural heritage monuments. Understanding the history and importance of these sites to the surrounding communities and their numerous stakeholders is the first step to ensuring these sites remain …

Detecting Team Conflict From Multiparty Dialogue, Ayesha Enayet

Electronic Theses and Dissertations, 2020-

The emergence of online collaboration platforms has dramatically changed the dynamics of human teamwork, creating a veritable army of virtual teams composed of workers in different physical locations. The global world requires a tremendous amount of collaborative problem solving, primarily virtual, making it an excellent domain for computer scientists and team cognition researchers who seek to understand the dynamics involved in collaborative tasks to provide a solution that can support effective collaboration. Mining and analyzing data from collaborative dialogues can yield insights into virtual teams' thought processes and help develop virtual agents to support collaboration. Good communication is indubitably the …

A Study On Robustness And Semantic Understanding Of Visual Models, Madeline Chantry

Electronic Theses and Dissertations, 2020-

Vision models have improved in popularity and performance on many tasks since the emergence of large-scale datasets, improved access to computational resources, and new model architectures like the transformer. However, it is still not well understood if these models can be deployed in the real world. Because these models are "blackbox" architectures, we do not fully understand what these models are truly learning. An understanding of what models learn "underneath the hood" would result in better improvements for real-world scenarios. Motivated by this, we benchmark these impressive visual models using newly proposed datasets and tasks on their robustness and their …

Studying Memes During Covid Lockdown As A Lens Through Which To Understand Video-Mediated Communication Interactions, Tatyana Claytor

Electronic Theses and Dissertations, 2020-

The purpose of this study is to analyze image macros about video-mediated communication (VMC) created during the time frame of 2020-2021 when people all over the world started using Zoom and VMC for work and school. It is a unique opportunity to study how users' interactions with themselves and with others were affected at a time when a lot of people started using the technology at the same time. Because the focus is on interactions, I narrowed it down to three topics to analyze the memes: presence, self, and space and place to analyze the memes. I chose memes relating …

Design Of Stormwater Bmps For Surface And Groundwater Protection Based On Site-Scale Soil Properties: Phase I, Kelly Kibler, Lisa Chambers, Melanie Beazley

Florida DOT

Much of Earth’s nutrient cycling takes place in soils. Characteristics of soils control physical, chemical, and biological processes that determine rates of nutrient fluxes, storage, or transformation. As remediation of excess nutrients in stormwater runoff is one function of stormwater Best Management Practices (BMPs), the soil profile constitutes one of the most important factors of BMP design. Variation observed in BMP effectiveness (e.g., why one BMP design works effectively in one place and not another) can often be explained by variations in the soil profile, either through direct means or by a soil’s influence on hydraulics of stormwater flow through …

An Interactional Account Of Empathy In Human-Machine Communication, Shauna Concannon, Ian Roberts, Marcus Tomalin

Human-Machine Communication

Efforts to develop empathetic agents, or systems capable of responding appropriately to emotional content, have increased as the deployment of such systems in socially complex scenarios becomes more commonplace. In the context of human-machine communication (HMC), the ability to create the perception of empathy is achieved in large part through linguistic behavior. However, studies of how language is used to display and respond to emotion in ways deemed empathetic are limited. This article aims to address this gap, demonstrating how an interactional linguistics informed methodological approach can be applied to the study of empathy in HMC. We present an analysis …

Theme Park Visitors Prefer Human-Like Robots In Customer Service Interactions, Ady Milman, Asli D.A. Tasci

Rosen Research Review

Service robots are becoming increasingly popular in many industries and social settings, including education, childcare, elderly therapy centers, and even theme parks. Tourism and hospitality industries are adopting robots enthusiastically and are being closely studied to observe guest engagement and reaction to robotic services. Service robots are becoming increasingly popular in many industries and social settings, including education, childcare, elderly therapy centers, and even theme parks. Tourism and hospitality industries are adopting robots enthusiastically and are being closely studied to observe guest engagement and reaction to robotic services. UCF Rosen College of Hospitality Management researchers, Dr. Ady Milman and Dr. …

Linear Regression With Regularization On The Genetic Architecture Of Maize Flowering Time, Roland Fiagbe

Data Science and Data Mining

Over a century, the maize crop has been one of the most important crop species that is targeted for genetic investigations and experiments. One of the major experiments that have been a topic of interest is crossing inbred lines to produce better offspring through a process called heterosis. Crossing the inbred lines create numerous SNP markers that determine the time to male flowering. This project seeks to explore the SNP markers to select the most relevant ones for predicting time to male flowering using linear regression with regularization methods due to the fact that p > n in our dataset. Various …

A Recommender System For Movie Ratings With Matrix Factorization Algorithm, Amir Alipour Yengejeh

Data Science and Data Mining

Nowadays, a Recommender System is a technology
that aims to predict preferences based on the user’s selections.
These systems are applied in numerous fields, such as movies,
music, news, books, research articles, search queries, social tags,
and various products. In this study, we use this potential tool to
predict the ratings of users’ preferences in MovieLens datasets. To
do so, we applied the matrix factorization algorithm and calculate
the RMSE as our evaluation metric. The results represent that
RMSE estimated for the train and test set are 0.83 and 0.93 that
are very close one another. This results indicates that …

Genome-Wide Association Study Of The Maize Crop By The Lasso Regression Analysis, Amir Alipour Yengejeh

Data Science and Data Mining

The accurate estimation of the male flowering period in Maize crops is key for the prediction crop fertility. The recent scientific investigations has shown that the genetic single nucleotic polymorphism (SNP) can contribute in this regard. The genomewide association study (GWAS) is employed to generate these attributes (SNP). But it caused a high-dimensional data in which 4,981 observations with 7,389 SNP attributes. Hence, in this study, we used the penalized regression approach with the least absolute shrinkage and selection operator (Lasso) to reduce the dataset. In this regard, we set the regularization parameter to 0.21. It resulted in a set …

Analysis Of Credit Approval By Decision Tree, Amir Alipour Yengejeh

Data Science and Data Mining

Nowadays, machine learning algorithms are com-
monly used by the financial institutions or bankers to evaluate
the applications’ requires for credit card. In this study, we used
the decision tree algorithm to predict credit card approval based
on the other associated features applicants like age, employment
status, Education Level, etc. Our results shows that the applicants’
Prior Default and Debt, and Employed have more contribution
in the credit card approval.

Movie Recommender System Using Matrix Factorization, Roland Fiagbe

Data Science and Data Mining

Recommendation systems are a popular and beneficial field that can help people make informed decisions automatically. This technique assists users in selecting relevant information from an overwhelming amount of available data. When it comes to movie recommendations, two common methods are collaborative filtering, which compares similarities between users, and content-based filtering, which takes a user’s specific preferences into account. However, our study focuses on the collaborative filtering approach, specifically matrix factorization. Various similarity metrics are used to identify user similarities for recommendation purposes. Our project aims to predict movie ratings for unwatched movies using the MovieLens rating dataset. We developed …

Characterizing Particle Bed Stratigraphy As A Function Of Particle Size In An Airless, Microgravity Environment, Gillian Gomer, Michael Fraser, Anthony Meola, Raquel Guzman

The Pegasus Review: UCF Undergraduate Research Journal

Asteroids and other small planetary bodies are covered in a loose, dynamic layer of multi-sized dusty particles. We are focused on developing methods to further understand this surface regolith behavior to inform future landing missions on these small bodies for resource collection. The Strata-1 experiment was designed to study granular behavior in a passive, microgravity, airless environment. These conditions, simulating that of an asteroid’s surface, were attained by installing Strata-1 aboard the International Space Station for 347 days. In this experiment, we took images of red, green, and blue multi-sized glass shards within a tube to better understand their stratigraphy. …

How Hurricanes Impact Florida's Tourism Industry, Arthur Huang

Rosen Research Review

Almost every year, hurricanes bear down upon the state of Florida. The storms appear to be growing in occurrence and severity. While the media cover the damage and death toll, the impacts on the state's critical tourism sector remain largely anecdotal. The full story lies buried in data. Dr. Arthur Huang from UCF's Rosen College of Hospitality Management has investigated different data sets to understand the impact of hurricanes on the tourism industry. What has been uncovered has significance not only for Florida but for tourism sectors elsewhere affected by these giant storms.