Digital Commons Network^™

Improving Robustness Of Learning-Based Approaches In Autonomous Systems And Engineering Education, Godwyll Aikins

Theses and Dissertations

This dissertation advances the development of robust learning-based approaches across two complementary domains: engineering education and autonomous systems. Through four studies, this research addresses critical challenges in preparing data-proficient engineers and developing reliable autonomous systems that can operate under uncertainty and incomplete information. The engineering education study examines how mechanical and aerospace engineering undergraduates conceptualize and develop data proficiency skills essential for modern engineering practice. Through interviews with 27 students, the research employs the How People Learn framework to analyze student perspectives on information literacy, data interpretation, and computational thinking. The findings inform pedagogical strategies for developing data proficiency in …

The Design And Implementation Of A Modular Tissue Engineering Test Bed To Pursue An Alternate Pathway Of Cell Culture Based Research, Ryley Patrick Griffin

Theses and Dissertations

The development of a Modular Automated Tissue Engineering Test Bed (MATETB) is the next step in the development of cheap and easily available in vitro cell regulatory systems for both academic and industrial purposes. This project outlined the framework and requirements for a device that could automatically regulate and collect data on a cell culture through the manipulation of its liquid environment. From this framework, a prototype was built. The device would fulfill cell culture needs while collecting data automatically and allowing for live viewing and imaging of cells. The device was comprised of a mechanical skeleton (MS), an environmental …

End-To-End Learning For A Low-Cost Robotics Arm, Abhishek Chothani

Theses and Dissertations

Robotic manipulation is a cornerstone of automation, with the ultimate goal of developing versatile systems capable of executing a wide range of real-world tasks autonomously. Traditional robotics approaches, while reliable and widely adopted in industrial settings, often struggle with adaptability, perception, and dynamic task execution. This thesis explores the evolution from classical robotics techniques to modern learning-based approaches, leveraging advancements in artificial intelligence to overcome these limitations.

Initially, the thesis presents a pick-and-place pipeline built using the Drake robotics framework and the KUKA iiwa robotic arm. This system employs a pseudoinverse controller for inverse kinematics to perform structured tasks like …

Hands-On Training About Data Clustering With Orange Data Mining Toolbox, Janez Demšar, Blaž Zupan

Faculty, Staff and Students Publications

Data clustering is a core data science approach widely used and referenced in the scientific literature. Its algorithms are often intuitive and can lead to exciting, insightful results that are easy to interpret. For these reasons, data clustering techniques could be the first method encountered in data science training. This paper proposes a hands-on approach to data clustering training suitable for introductory courses. The education approach features problem-based training that starts with the data and gradually introduces various data processing and analysis methods, illustrating them through visual representations of data and models. The proposed training is suitable for a general …

Experiences In Providing A Community Educational Resource For The All Of Us Researcher Workbench, Deborah I Ritter, Jinyoung Byun, Jun Wang, Stephen Richards, Pamela N Luna, Laterrica Williams, Julie R Coleman, Jasmine N Baker, Shamika Ketkar, Ashley M Butler, Latanya Hammonds-Odie, Elizabeth G Atkinson, Kim C Worley, Debra D Murray, Brendan Lee, Steven E Scherer

Faculty, Staff and Students Publications

OBJECTIVE: Educational offerings to fill the bioinformatics knowledge gap are a key component to enhancing access and use of health data from the All of Us Research Program. We developed a Train the Trainer-based, innovative training series including project-based learning, modular on-demand demonstrations, and unstructured tutorial time as a model for educational engagement in the All of Us community.

MATERIALS AND METHODS: We highlight our training modules and content, with training survey data informing cycles of development in the creation of a 6-module training series with modular demonstrations.

RESULTS: We have conducted 2 public iterations of the Train the Trainer …

Health Implications Of Racial Differences In Serum Growth Differentiation Factor Levels Among Men With Obesity, Siresha Bathina, Virginia Fuenmayor Lopez, Mia Prado, Elliot Ballato, Georgia Colleluori, Maryam Tetlay, Dennis Tan Villareal, Sanjay Mediwala, Rui Chen, Clifford Qualls, Reina Armamento-Villareal

Faculty, Staff and Students Publications

Growth differentiation factor (GDF15) has been considered a biomarker and recently a hormonal driver for diseases in different populations. However, the role of GDF15 as a biomarker of health outcomes in obese men from different racial/ethnic background has not been evaluated. The objective of this study was to investigate the racial/ethnic differences on the relationship between GDF15 and markers of glucometabolic status, hormonal profile, body composition and bone mineral density (BMD) in obese men. One hundred ninety-three obese men from diverse racial/ethnic backgrounds were enrolled. BMD and body composition were measured by dual energy X-ray absorptiometry. Serum GDF15, osteocalcin, C-terminal …

Tumor Expression Of Cd83 Reduces Glioma Progression And Is Associated With Reduced Immunosuppression, Malcolm F Mcdonald, Rachel Naomi Curry, Isabella O'Reilly, Brittney Lozzi, Alexis Cervantes, Zhung-Fu Lee, Anna Rosenbaum, Peihao He, Carrie Mohila, Arif O Harmanci, Akdes Serin Harmanci, Benjamin Deneen, Ganesh Rao

Faculty, Staff and Student Publications

Immunosuppression in malignant glioma remains a barrier to therapeutic development. CD83 overexpression in human and mouse glioma increases survival. CD83+ tumor cells promote signatures related to cytotoxic T cells, enhanced activation of CD8+ T cells, and increased proinflammatory cytokines. These findings suggest that tumor-expressed CD83 could mediate tumor-immune communications.

Analytical Solutions For Acoustic Vortex Beam Radiation From Planar And Spherically Focused Circular Pistons, Chirag A Gokani, Michael R Haberman, Mark F Hamilton

Faculty, Staff and Student Publications

Analytical solutions for acoustic vortex beams radiated by sources with uniform circular amplitude distributions are derived in the paraxial approximation. Evaluation of the Fresnel diffraction integral in the far field of an unfocused source and in the focal plane of a focused source leads to solutions in terms of an infinite series of Bessel functions for orbital numbers ℓ>-2. These solutions are reduced to closed forms for 0≤ℓ≤4, which correspond to orbital numbers commonly used in experiments. A scaling law for the vortex ring radius is derived, and its relevance is characterized using ray theory.

“How Can I Teach When I Was Not Taught How?”: Teacher Education For Mother Tongue Instruction For Stem In Southwest Nigeria, Motunrayo Adeosun

Theses and Dissertations

In this qualitative study, the experiences, training, and challenges of teachers in primary schools in a community in southwest Nigeria were explored. The purpose of this study was to identify the experiences of teachers about their training for mother tongue instruction and how they teach pupils with the mother tongue or local language of the community, the challenges faced by teachers in teaching with the mother tongue, and the strategies used by teachers to overcome the challenges. This study found that teachers received no training and there is no curriculum for the training of teachers to teach in the mother …

The Positivity Principle: Investigating A School Administrator Training Series Designed To Promote Systemic Positivity, Catherine Gillach

Theses and Dissertations

Education has historically been recognized as a stressful profession, yet the Covid-19 pandemic (2020) paired with intensified socio-political influences have exacerbated educator stress, anxiety, and negativity, prematurely pushing more career educators to leave the profession. Teacher and principal pre-service preparation programs largely neglect to train educators in strategies for personally managing negative stressors, and negativity mitigation strategies are often overlooked as a critical facet of school climate and culture. Therefore, the purpose of this dissertation in practice was to examine the degree to which a school administrator training series could stimulate personal and systemic positivity within participants’ schools in a …

Investigating The Relationship Between Teachers’ State Evaluation Rating And Their Classroom-Based Assessment Practices And Systems, Christopher Jones

Theses and Dissertations

This quantitative research study investigates the relationship between teachers’ evaluation rating and their classroom-based assessment practices using a survey approach. Four middle schools consisting of 39 (grades six through eight) teachers in the Southwestern U.S. participated in the study. Research has shown that when teachers regularly use a system of evidence-based classroom assessment practices, student achievement increases. The problem addressed within this investigation is that students nationwide are performing at lower proficiency rates in math and English Language Arts than previously seen. Results from this study indicate that even teachers rated “highly effective” on evaluations are not employing evidence-based assessment …

Investigation Of The Existence Of Vertically Oriented Ice Crystals In Winter Storms, Kendra R. Sand

Theses and Dissertations

The existence of vertically oriented ice crystals is investigated in winter storms, as observed through remote sensing and analyzed during the NASA Earth Venture Investigation of Microphysics and Precipitation for Atlantic Coast-Threatening Snowstorms (IMPACTS) field campaign field campaign. The primary objective was to determine if a preferred angle of ice crystal orientation could be identified in situ using contemporary airborne sampling instruments. Additionally, the study sought to explore potential correlations between the vertical orientation of ice crystals and electric field anomalies at cloud top, as well as the relationship between crystal orientation and particle concentration. To achieve these objectives, Two-Dimensional …

An Analysis Of Curricular Complexity Patterns In Undergraduate Mechanical Engineering Programs Using Federally Reported Data, Shane Schellpfeffer

Theses and Dissertations

With the recent development of curricular analytics tools designed to quantify the structure of a curriculum (Heileman, Abdallah, et al., 2018), some institutions of higher education are examining their curricula to find ways that these pathways to graduation can be improved (McMurtrie, 2021). The tools used to analyze curricula were created to address an issue of importance in the field of undergraduate engineering, that issue being the decreasing enrollment trend over the past two decades. The decrease in undergraduate engineering graduates in programs across the United States led to conversations in both academia and industry regarding potential solutions for this …

Barriers To Faculty Adoption Of Assessment: A Case Study In Engineering, Melodie A. R. Williams

Theses and Dissertations

This case study at an undergraduate teaching-focused engineering program in a small faith-based liberal arts university is designed to evaluate tools for assessing the engineering accreditor ABET’s Student Outcome Five – teamwork skills of engineering students. This evaluation would set the foundation for developing an assessment program that meets the needs of faculty, administrators, and accreditors. Activity theory is used as the theoretical framework for the study. A literature review lays the foundation for a novel conceptual framework asserting “faculty resistance” is actually “systemic friction.” The methodology is described, including data collection procedures, data analysis methods, and the approaches to …

Explainable Artificial Intelligence And Domain Adaptation For Predicting Hiv Infection With Graph Neural Networks, Evan Yu, Jingcheng Du, Yang Xiang, Xinyue Hu, Jingna Feng, Xi Luo, John A Schneider, Degui Zhi, Kayo Fujimoto, Cui Tao

Faculty, Staff and Student Publications

OBJECTIVE: Investigation of explainable deep learning methods for graph neural networks to predict HIV infections with social network information and performing domain adaptation to evaluate model transferability across different datasets.

METHODS: Network data from two cohorts of younger sexual minority men (SMM) from two U.S. cities (Chicago, IL, and Houston, TX) were collected between 2014 and 2016. Feature importance from graph attention network (GAT) models were determined using GNNExplainer. Domain adaptation was performed to examine model transferability from one city dataset to the other dataset, training with 100% of the source dataset with 30% of the target dataset and prediction …

Artificial Intelligence Uncertainty Quantification In Radiotherapy Applications – A Scoping Review, Kareem A Wahid, Zaphanlene Y Kaffey, David P Farris, Laia Humbert-Vidan, Amy C Moreno, Mathis Rasmussen, Jintao Ren, Mohamed A Naser, Tucker J Netherton, Stine Korreman, Guha Balakrishnan, Clifton D Fuller, David Fuentes, Michael J Dohopolski

Faculty, Staff and Student Publications

Background/purpose: The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions.

Methods: We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual …

Artificial Intelligence And Machine Learning In Cancer Pain: A Systematic Review, Vivian Salama, Brandon Godinich, Yimin Geng, Laia Humbert-Vidan, Laura Maule, Kareem A Wahid, Mohamed A Naser, Renjie He, Abdallah S R Mohamed, Clifton D Fuller, Amy C Moreno

Faculty, Staff and Student Publications

Background/objectives: Pain is a challenging multifaceted symptom reported by most cancer patients. This systematic review aims to explore applications of artificial intelligence/machine learning (AI/ML) in predicting pain-related outcomes and pain management in cancer.

Methods: A comprehensive search of Ovid MEDLINE, EMBASE and Web of Science databases was conducted using terms: "Cancer," "Pain," "Pain Management," "Analgesics," "Artificial Intelligence," "Machine Learning," and "Neural Networks" published up to September 7, 2023. AI/ML models, their validation and performance were summarized. Quality assessment was conducted using PROBAST risk-of-bias andadherence to TRIPOD guidelines.

Results: Forty four studies from 2006 to 2023 were included. Nineteen studies used …

Time Series Decomposition Of Land Surface Temperature For Long-Term Trend Forecasting And Impact On Nesting Sea Turtle Habitats In The Arabian Gulf, Sachi Perera, Rommel H. Maneja, Mohamed Allali, Cyril Rakovski, Erik Linstead, Daniele Struppa, Ali Qasem, Hesham El-Askary

Mathematics, Physics, and Computer Science Faculty Articles and Research

Improving land surface temperature (LST) modeling is vital for mitigating climate change effects on various ecosystems and marine habitats such as important sea turtle habitats. Over the past decade, extreme temperatures have likely significantly affected nesting sea turtle habitats in the Arabian Gulf, with predominantly female hatchlings creating an imbalance in the sex ratio. Such shifts have profound implications for these habitats’ long-term survival and conservation management. This study leverages statistical machine learning models to measure ongoing temporal variations in LST. We break down the LST time series into trend, seasonal, and noise components using classical decomposition methods like X11, …

Predictive Model For Listeria Monocytogenes In Rte Meats Using Exclusive Food Matrix Data, N.A. Nanje Gowda, Manjari Singh, Gijs Lommerse, Saurabh Kumar, Eelco Heintz, Jeyamkondan Subbiah

Food Science Faculty Publications and Presentations

Post-processing contamination of Listeria monocytogenes has remained a major concern for the safety of ready-to-eat (RTE) meat products that are not reheated before consumption. Mathematical models are rapid and cost-effective tools to predict pathogen behavior, product shelf life, and safety. The objective of this study was to develop and validate a comprehensive model to predict the Listeria growth rate in RTE meat products as a function of temperature, pH, water activity, nitrite, acetic, lactic, and propionic acids. The Listeria growth data in RTE food matrices, including RTE beef, pork, and poultry products (731 data sets), were collected from the literature …

Basic Safety Message Generation Through A Video-Based Analytics For Potential Safety Application, Abyad Enan

All Theses

With the advancement of modern artificial intelligence techniques, computer vision can play a vital role in enhancing roadway safety by reducing the risk of imminent collisions. To do so, a vision-based safety application is required, where a roadside camera can monitor the roadway traffic and predict potential risks of crashes in real-time. If any risky situation or behavior is observed that may lead to a crash, then a safety application can send warnings to the vehicles at risk. For vision-based safety applications on a roadway section, it is important to accurately monitor each vehicle’s location, speed, acceleration, heading direction, etc. …

Learning To Represent Temporal Dynamics And Generative Factors For Intelligent Visual Navigation, Sahand Khoshdel

All Theses

Visual navigation systems are crucial in various applications, including autonomous driving, unmanned aerial systems (UAS), and industrial automation. For these systems to operate efficiently in dynamic environments, they must not only interpret complex surroundings but also anticipate changes over time. Temporal prediction—forecasting environmental changes like moving obstacles or shifting lighting conditions—enables navigation systems to act proactively, enhancing both safety and performance. This dissertation investigates representation learning methods both as a backbone feature extractor for RL agents as well as a proxy for systems oriented for Explainable AI (XAI). Two main projects are presented as case studies to achieve the aforementioned …

Hardware Applications Of High-Speed Fault Detection Algorithms, Daniel Zintsmaster

All Theses

The growing need for a sustainable electric energy infrastructure has driven research into control, protection, and optimization of power systems. A key challenge is that the changing grid must operate at increasingly higher speeds, but many current hardware devices cannot meet these demands. This thesis focuses on power system protection, aiming to design a hardware solution that can detect and isolate faults in microseconds, ensuring faster, more reliable grid operations. The first hardware developed was for a low-voltage direct current (LVdc) microgrid, which faces challenges due to a lack of protection schemes and novel speed requirements. This thesis presents protection …

Exploiting Randomness In Secret Sharing, Cailyn Bass

All Theses

Shamir's (k,n)-threshold scheme is a method for sharing a secret among n participants such that any group of k or more participants can recover the secret. Additionally, any group of participants with size less than k should learn nothing about the secret. The scheme works by distributing a share to each participant, where each share is a linear combination of the secret and k-1 random symbols. This allows any group of k or more participants to solve a linear system to compute the secret. Any group of less than k participants does not have enough to determine anything about the …

Comparative Analysis Of Design-Build And Design-Bid-Build Project Delivery Methods Through Cost, Schedule And Quality Performance For Warehousing And Storage Facilities, Vijaya Ravi Prasanth Reddi

All Theses

Storage facilities are essential for e-commerce operations, providing inventory, distribution, and delivery space. As per the Bureau of Labor Statistics, the number of warehousing and storage businesses in the United States increased from 15,152 in 2010 to 21,287 in 2024, showing continuous growth over the decade. Given the recent surge, there is a need to understand the performance of these facilities better. This study aims to contrast the measure of quantitative performance of design-build (DB) versus traditional design-bid-build (DBB) project delivery methods (PDM) based on cost, schedule, and quality metrics for storage facilities. This research conducted a literature review to …

Application Of Lossy And Lossless Compression To Dicom Files, Yizhe Yang

All Theses

The Digital Imaging and Communications in Medicine (DICOM) standard is widely utilized for the management, storage, and transfer of medical images. However, the substantial file sizes associated with DICOM data present challenges in terms of storage and data transmission. Data reduction techniques help address these challenges by minimizing the size of the data while preserving its integrity. This thesis examines various compression methods aimed at reducing the size of DICOM files. We evaluate five lossless compressors and four lossy compressors on DICOM data to compare and assess their performance. Through an analysis of each compressor’s compression efficiency and resulting image …

Informing Management Of American Shad (Alosa Sapidissima) In The Carolinas: Evaluating Novel Fish Passage Approaches And Acoustic Tracking Methods, Margaret Gaither

All Theses

Acoustic telemetry is a valuable tool for fisheries scientists to study the movements and migratory behaviors of aquatic organisms. A critical assumption of this method is that tagged fish exhibit similar behaviors and survival rates as their untagged counterparts. To investigate this, we conducted a 12-week laboratory study on adult American Shad (Alosa sapidissima) using gastroesophageal insertion of acoustic transmitters. We implanted 80 fish with dummy transmitters and monitored tag retention and survival. Our analysis, employing a mixed effects Cox’s proportional hazards model, revealed no significant differences in survival between tagged and control fish, regardless of sex. Additionally, …

Multiple Cut Systems Of Cannabis Sativa L. For Micropropagation Without The Use Of Cytokinins, Molly Mckay

All Theses

Micropropagation is a technique used to propagate clean, high-quality clonal stock plants using plant growth regulators (PGR) in a single harvest batch system. This two-part study uses an in vitro multiple harvest system “hedging” combined with the fed- batch media process, to observe (1) the effects of modified physical state and (2) LED light quality to improve shoot production and quality. In Experiment 1, four genotypes of Cannabis sativa (‘Cherry 1’,‘BaOx’,‘T1’,‘Peach’) were observed in three different physical states: stationary agar (A), stationary Oasis® infused with liquid (OIL_s) and agitated Oasis® infused with liquid (OIL_a). Fifteen …

Unsupervised Moving Object Segmentation With Atmospheric Turbulence, Dehao Qin

All Theses

Moving object segmentation in the presence of atmospheric turbulence is a highly challenging task due to the irregular and time-varying distortions induced by the atmospheric turbulence. This thesis presents an unsupervised approach for segmenting moving objects in videos affected by such atmospheric turbulence. The proposed methodology is grounded in a detect-then-grow scheme: the algorithm begins by identifying a small set of moving object pixels (seed points) with high confidence and progressively expanding a foreground mask from these seed points to segment all moving objects. The proposed approach capitalizes on rigid geometric consistency across video frames to disentangle different types of …

Shifting Perspectives With Procedural Modeling Techniques And Vertex Animated Textures For Real-Time Interactive Morphing, Stephanie Schulze

All Theses

As humans experience reality, they intake external stimuli using sensory receptors to process information, forming a perception. Perceptions are subjective and shape each individual’s reality. Naturally then, by changing one’s perceptions, their experience of reality is altered, for better or worse. To emphasize the idea that perception is malleable and encourage a mindset of questioning alternative ways to look at a situation, an interactive experience in Unreal Engine is developed where a dull cityscape morphs and transforms into a surreal oversized nature scene. Procedural modeling techniques are used to create a variety of morphing assets, while Vertex Animated Textures are …

Ai At The Helm: Transforming Crisis Communication Through Theory And Advancing Technology, Timothy Whims

All Theses

This thesis investigates the integration of artificial intelligence (AI), particularly large language models, into crisis communication, focusing on how AI technologies can enhance response strategies and stakeholder engagement during crises. By leveraging established communication frameworks such as Image Repair Theory, Situational Crisis Communication Theory, and the Discourse of Renewal, this research explores the potential for AI to improve both the speed and precision of crisis responses. The study highlights how AI can assist in monitoring public sentiment, drafting tailored responses, and managing real-time information during crisis events. However, it also addresses the limitations of AI, such as its inability to …