Digital Commons Network^™

Using Generative Ai To Enrich Instructional Videos With Embedded Quizzes, Efren De La Mora Velasco, Shaurya Agarwal

Teaching Online Pedagogical Repository

This entry describes a strategy to enhance student engagement in asynchronous online courses by embedding AI-generated quizzes into instructional videos. Using ChatGPT and video transcripts, the instructor created targeted multiple-choice questions that aligned with key video topics and improved interactivity. Results from the CGN5341 course showed increased video view duration, higher engagement, and positive student feedback on the usefulness of short, segmented videos with embedded quizzes.

Exploring The Role Of Graduate Teaching Assistants In Facilitating Adaptive Learning, Vanessa Tien Pham, Piyali Chakraborty, Rachid Ait Maalem Lahcen

Teaching Online Pedagogical Repository

This paper explores the growing role of Graduate Teaching Assistants (GTAs) in adaptive learning classrooms, where technology and instruction work together to support student success. As adaptive educational software becomes more common across many subjects, GTAs help bridge the gap between technology and students’ academic ability. Drawing from our experiences in College Algebra, Precalculus Algebra, Trigonometry, we show how GTAs use learning data to identify common struggles and provide focused, one-on-one support through tutoring and review sessions. These real-time interventions help personalize the learning experience beyond what the software provides.

Comparative Evaluation Of Linear Regression, Cross Validation And Regularization Approaches In Multivariate Data Analysis, Ransford Owusu, Felix Yeboah, Francis Effah Boateng

Data Science and Data Mining

This study evaluates linear regression and its enhanced variants incorporating cross-validation and regularization techniques for high-dimensional, multivariate datasets. We address challenges such as multicollinearity and overfitting. Methods including Ridge, LASSO, and Elastic Net are compared against ordinary least squares regression. Empirical analysis using an automobile dataset for fuel efficiency prediction shows that while OLS regression captures basic relationships, its limitations are mitigated through regularization and cross-validation, resulting in improved model interpretability. The findings provide a comprehensive framework for predictive modeling in complex data environments and offer insights into statistical methodology and practical applications in the automobile industry.

A Report On Health Care Access By The United States Citizens., Kelvin Njuki, Emil Agbemade

Data Science and Data Mining

Access to health care is a critical factor in ensuring public health. This study analyzes data from the National Health Interview Survey (NHIS) for the years 2015–2018 to examine the relationship between health care coverage, affordability, and costs among U.S. families. Re-sults indicate that families with at least one member covered by health insurance were more likely to afford medical care and incur lower health care costs. Despite a high proportion of families with health care coverage during this period, the number of insured family members declined over the years. These findings underscore the importance of health care coverage in …

Modeling The Relationship Between Calories And Activity Metrics: A Regression Analysis With Variable Selection, Felix Yeboah

Data Science and Data Mining

Physical activity monitors have become integral to daily routines, with wearable devices such as the Apple Watch and Fitbit offering continuous data on users’ physical activity. This study compares the measurement accuracy of these devices by examining how they record parameters relevant to fitness and health. Employing multiple linear regression, we modeled the relationship between calories expended and a set of explanatory variables, including heart rate, steps, distance, age, activity level, weight, and device type. Evaluation of all possible variable combinations identified heart rate, steps, distance, weight, and watch type as the most effective predictors of calorie expenditure. Although the …

Optimized Hiv/Aids Resource Allocation In Ohio: A Linear Programming Approach, Godfred Ahenkroa Kesse

Data Science and Data Mining

This study employs a linear and integer programming approach to optimize HIV resource allocation in Ohio, aiming to minimize new infections and enhance the impact of limited resources. With the advances in HIV prevention and treatment, Ohio faces challenges in addressing disparities in access to healthcare, particularly among high-risk populations. The proposed model integrates data on infection rates, transmission patterns, demographic factors, and cost-effectiveness to provide a decision-support framework for policymakers. Using epidemiological data and equity constraints, the model prioritizes high-risk regions and populations while ensuring fair resource distribution. Results indicate that increased funding allocations significantly enhance the potential to …

Ai-Integrated Cross-Disciplinary Liberal Arts Colloquium, Diana S. Perdue, Niloofar Gholamrezaei, Jennifer Krusinger, Shannon Hogan

Teaching Repository of AI-Infused Learning

What began organically as an AI-focused collaboration between faculty in different disciplines along with researchers in the college’s Center for Instructional Innovation, has evolved into college-wide pedagogical workshops and the development of a studio model that affects courses, programs, and paradigms for faculty scholarship.

Lessons from these collaborations inform understandings of how key features of liberal arts education can be supported through intentional AI-integration within a Cross-Disciplinary Liberal Arts Colloquium. More specifically, this colloquium offers recommendations on adapting a collaborative, interdisciplinary, and reflective studio model to in-person, online, and hybrid educational environments facilitated through a Technological Pedagogical Content Knowledge (TPACK) …

Uncovering Acoustic Biomarkers To Classify Parkinson Disease Through Machine Learning, Felix Yeboah

Data Science and Data Mining

The early detection of diseases profoundly influences treatment efficacy, and accurate classification methodologies are essential for effective disease identification. In this project, we examined fve different classifers—Logistic Regression, Gaussian Naive Bayes, K Nearest Neighbor (KNN), Extreme Gradient Boosting (XGBoost), and Support Vector Machines—and evaluated their performance in detecting Parkinson’s disease (PD) based on voice features. The study aims to identify the best classifier for detecting PD. XGBoost performed the best, with an accuracy of 91% on the full dataset. After variable selection, KNN had the best performance with an accuracy of 91%. These findings suggest that Machine learning algorithms(classifiers) can …

Evaluation Of Variable Selection Techniques On The Genetic Architecture Of Flowering Time In Maize, Felix Yeboah

Data Science and Data Mining

In this project, we investigate several variable selection procedures to give an overview of how well they perform on a genomic dataset using three different penalized regression approaches. Comparisons between different methods were performed. These methods include Ridge, lasso, and Elastic Net. We utilized 4494 observations with 7389 SNPs gene scores to predict time to male flowering (dtoa). We assessed the performance of these three models in terms of mean square error. Not surprisingly, Lasso and Elastic Net perform better than Ridge Regression. Overall, Elastic Net performed better in predicting the time of male flowering (dtoa).

Comparison Of Two Strategies Of Screening Experiments: Single-Shot Experiment Vs. Two-Stage Screening Experiment, Kelvin Njuki, Emil Agbemade

Data Science and Data Mining

Experiments involving many factors are often complex, time-consuming, and expensive. Screening out the least important factors helps the experimenter(s) allocate the limited resources efciently to the most important factors. Supersaturated and orthogonal array designs are among the designs used to conduct screening experiments. Supersaturated designs (SSDs) are those where the number of runs (observations) is less than the number of factors, while orthogonal array (OA) designs are those where at least the columns are orthogonal to each other. In this study, we conduct a simulation study to compare two strategies of screening experiments. Strategy one is a single shot experiment …

Advanced Machine Learning Techniques For Cardiovascular Disease Risk Prediction, Godfred Ahenkroa Kesse

Data Science and Data Mining

of mortality, necessitating advanced predictive models to aid early detection and prevention. This study explores the application of machine learning techniques, including Lo- gistic Regression, K-Nearest Neighbors (KNN), Random Forest, and XGBoost, to predict CVD risk using a dataset of 69,997 observations encompassing demographic, clinical, and lifestyle factors. Data preprocessing involved one-hot encoding of cat- egorical variables and scaling to ensure compatibility with all models. Model performance was evaluated using metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. Among the models, XGBoost demonstrated the highest accuracy at 74%, leveraging its gradient-boosting framework to effectively handle feature interactions and imbalanced …

Predicting Blood Glucose Levels: A Linear Regression Approach For Non-Invasive Monitoring, Godfred Ahenkroa Kesse

Data Science and Data Mining

Accurate monitoring of blood glucose levels is vital for the management of diabetes, a chronic condition affecting millions worldwide. This study explores a linear regression approach to estimate glucose levels non-invasively using a dataset enriched with demographic, physiological, and sensor-based variables. Following rigorous data preparation, including normalization and encoding, a Box-Cox transformation was applied to address violations of regression assumptions, stabilizing variance and improving model validity. Stepwise selection and hypothesis testing were employed to refne the model, retaining signifcant predictors such as AGE, GENDER, HEARTRATE, and DIABETIC, while excluding variables like NIR Reading and LAST EATEN for their minimal contribution. …

Handwritten Digit Recognition Using Naive Bayes And K-Nearest Neighbor Models, Godfred Ahenkroa Kesse

Data Science and Data Mining

This paper explores the performance of two fundamental classifcation algorithms. It uses Naive Bayes and K-Nearest Neighbors (KNN), framing it within the context of digit recognition of the MNIST dataset. The MNIST dataset has 70,00 grayscale images of handwritten digits, offering a standard for assessing classifcation models. This paper focuses on key performance metrics such as precision, accuracy, recall, and F1score to examine the effciency of each model. The results reveal that Naive Bayes has moderate accuracy and misclassifcations because of its notion of feature independence. The paper concludes that the KNN model performs better with the optimal k-value of …

Variable Selection Using Lasso Regression, Godfred Ahenkroa Kesse

Data Science and Data Mining

This study employs Lasso regression to analyze highdimensional genetic data for predicting flowering time in maize, specifically Days to Anthesis (DtoA). Lasso, or Least Absolute Shrinkage and Selection Operator, is a form of linear regression that introduces an L1 penalty to the model, encouraging sparsity by shrinking some coefficients to zero. This attribute makes Lasso ideal for feature selection in large datasets, as it highlights the most influential predictors while discarding irrelevant variables. Unlike Ridge regression, which applies an L2 penalty to minimize the squared magnitude of coefficients, Lasso’s L1 penalty induces sparsity, providing a clearer interpretation of the selected …

Classification And Evaluation Of Machine Learning Algorithms On The Mnist Dataset, Felix Yeboah

Data Science and Data Mining

This paper discusses the use of machine learning algorithms in classifying the MNIST handwritten dataset. The MNIST dataset consists of 28x28 grayscale handwritten images with 10 classes from 0 to 9. The dataset was normalized by scaling the pixel values to a range between 0 and 1 by dividing each pixel value by 255. We compare and evaluate the K-nearest Neighbor and Naive Bayes algorithm based on performance metrics such as accuracy, error rate, f1-score, and precision. The K-nearest Neighbor algorithm achieved better performance in all the evaluation criteria.

Ucf Pegasus Plan - 1st Grade - Maps & Globes, Cecilia Nuss, Mackenzie Luley, Jessenia Diaz, Alyssa Arnott, Miranda Howley

Pegasus Plans: Social Studies Unit Plans for Florida Teachers

During this unit, students will explore and create various maps and globes through multimedia resources, Hands-on activities, and assessments. The daily lessons cover topics such as a compass rose, cardinal directions, map titles, and physical features on maps and globes. By the end of this unit, students will be able to identify key elements and locate physical features of maps and globes. Through the use of songs, hands-on activities, games, books, and class discussions, students will be engaged throughout the unit.

Predicting Superconducting Critical Temperature From Composition-Derived Features: A Transparent Linear And Regularized Regression Study, Md Ahiduzzaman

Data Science and Data Mining

We study prediction of superconducting critical temperature (Tc) from 81 composition-derived descriptors across 21,263 materials. To keep the analysis transparent and repro- ducible, we focus on linear models: Ordinary Least Squares (OLS), Ridge, Lasso, and Elastic Net (ENet). All models share a single evaluation protocol (5-fold cross-validation with standardized inputs) and are compared on RMSE, MAE, and R2. On this feature set, OLS attains the best cross-validated performance (RMSE = 17.6 K, MAE = 13.3 K , R2 = 0.735), with Lasso/ENet essentially tied next (RMSE ≈ 17.7 K , R2 ≈ 0.734); Ridge underperforms (RMSE = 18.9 K , …

Comparative Analysis Of Lasso, Ridge, And Elastic Net For Variable Selection In High-Dimensional Maize Data, Md Ahiduzzaman

Data Science and Data Mining

In high-dimensional genomic data analysis, traditional linear regression techniques often struggle due to the presence of a large number of predictor variables relative to observations. Penalized regression methods such as LASSO, Ridge, and Elastic Net have emerged as effective solutions by imposing regularization, which helps in managing multicollinearity and enhancing prediction accuracy. This study applies these techniques to the Maize dataset to model the time to male flowering, selecting relevant genetic markers as predictors. Our findings suggest that Elastic Net is particularly effective for high-dimensional data with correlated variables, achieving a balance between prediction accuracy and variable selection. The results …

Handwritten Digit Recognition Using Machine Learning Classifiers, Md Ahiduzzaman

Data Science and Data Mining

This project explores and compares the performance of various machine learning classifiers for handwritten digit recognition using the MNIST dataset. The classifiers include Logistic Regression, k-Nearest Neighbors, and Convolutional Neural Networks. Each classifier is evaluated based on accuracy, precision, recall, F1-score, and confusion matrix analysis.

Captivating Chemistry: Luminous Lava Lamps, Linsey Vo, Brinlie Bergman, Kylie Daum, Shayan Noor, Akshay Aramjisingh

High Impact Practices Student Showcase Fall 2025

Our group participated in STEM Day, an engaging biannual event that brings together K–12 students to explore the wonders of science, technology, engineering, and mathematics through hands-on experiences. When planning our presentation, we aimed to create an activity that was both visually exciting and easy for students of all ages to understand. We chose to demonstrate the concepts of polarity and density through a fun and interactive experiment in which students created their own lava lamps. This activity allowed the students to observe scientific principles in action while encouraging curiosity and enthusiasm for STEM learning.

Multidimensional Approaches In Bug Detection For Parallel Programming And Text-To-Code Semantic Parsing, May Alsofyani

Graduate Thesis and Dissertation post-2024

This dissertation applies deep learning and large language models to two domains: parallel programming fault detection and text-to-code translation, aiming to enhance software reliability and natural language-driven code generation. Due to their unpredictable nature, concurrency bugs-particularly data race bugs— present significant challenges in fault detection for parallel programming. We investigate deep learning and LLM-based approaches for detecting data race bugs in OpenMP programs. Our proposed methods include a transformer encoder and GPT-4 through prompt engineering and fine-tuning. Experimental results demonstrate that the transformer encoder achieves competitive accuracy compared to LLMs, highlighting its effectiveness in understanding complex OpenMP directives. Expanding this …

Advancing Temporal Safety Performance Functions: A Comprehensive Evaluation Of Express Lanes, Ramps, And Ramp Metering Effects On Freeway Safety, Abdulrahman Khalid Faden

Graduate Thesis and Dissertation post-2024

Freeway safety remains a critical concern, especially in high-risk areas such as ramps, merges, and managed lane segments, where complex traffic interactions significantly elevate crash risks. This dissertation advances crash frequency prediction by developing short-term Safety Performance Functions (SPFs) that address the limitations of traditional long-term SPFs models and real-time safety analysis. By leveraging high-resolution microscopic traffic detector data from multiple states, the dissertation introduces innovative methodologies and delivers actionable insights into freeway safety dynamics. The dissertation pioneers the application of Multivariate Poisson-Lognormal (MVPLN) models to identify interdependencies between crashes at ramp and merge segments. To address challenges like data …

The Spray And Atomization Characteristics Of An Lrdre Injector, Samuel J. Schuetz

Graduate Thesis and Dissertation post-2024

The Ongoing effort to advance the Technology Readiness Level (TRL) of Rotating Detonation Engines (RDEs) has faced significant challenges with respect to the development of accurate analytical models for the performance of liquid fueled detonations. A key issue lies in the lack of comprehensive experimental data to validate and refine these models. To address this gap, the present study seeks to provide detailed characterization data on a specific Liquid Rotating Detonation Rocket Engine (LRDRE) injector, which can be leveraged to improve simulation accuracy and predictive capabilities. This investigation is divided into two primary phases. The first phase focuses on the …

Grid-Forming Inverters: Comprehensive Review, Design, And Implementation Of Advanced Control Methods, Yousef H. Abudyak

Graduate Thesis and Dissertation post-2024

The growing integration of renewable energy (RE) resources into power systems requires urgent measures by system operators to address stability challenges caused by the intermittency of such resources. GridForming (GFM) inverters have emerged as a promising solution to mitigate such grid instabilities. Their ability to establish and regulate voltage and frequency under various load and grid conditions makes them a potential alternative to Grid-Following (GFL) inverters, which are highly susceptible to loss of synchronism in grid conditions with low Short Circuit Ratios (SCRs). Numerous GFM control methods have been proposed in the literature, each addressing specific research gaps, however, several …

Developing Real-Time Crash Prediction System Using Ai-Based Methods On Interstate Incorporating Express Lanes, Samgyu Yang

Graduate Thesis and Dissertation post-2024

This research develops a real-time crash prediction system that integrates machine learning techniques and real-time data to forecast crash likelihood across various road segments. The system particularly addresses newly constructed Interstate 4 Express managed lanes, modeling them separately due to their unique challenges, such as limited crash data and new road designs. By treating these segments individually, the system ensures more accurate predictions that account for their distinct traffic behaviors. By leveraging anomaly detection learning (ADL), the system identifies rare crash events by detecting deviations from normal traffic behavior, even with imbalanced data. ADL is applied specifically to the influenced …

Statistical Analysis Of Interstitial Impacts On Shock-Driven Fuel Droplet Atomization, Miguel L. Moran

Graduate Thesis and Dissertation post-2024

Understanding the deformation and aerobreakup of liquid droplets is critical for designing fuel injectors for pressure gain combustion systems. Previous literature has observed the morphology and timescales of individual liquid droplets exposed to the convective flow fields behind moving shocks propagating between Mach 1 and Mach 10. However, the liquid droplets produced by an injection system are not isolated and have many close neighbor droplets of similar diameter. Understanding interactions between these droplets is necessary to reconcile existing theory with droplet behavior observed in liquid jets and droplet clouds. The present study uses a simple injector to create vertically oriented …

Wetting Dynamics On Ultrasoft Materials: Effects Of Surface Chemistry And Elasticity On The Maximum Speed Of Wetting, Damian Hundley

Graduate Thesis and Dissertation post-2024

The study of wetting dynamics on ultrasoft materials has gained significant attention due to its critical implications for flexible technologies, thermal management systems, and advanced coatings. This research explores the effects of surface chemistry and elasticity on the maximum speed of wetting, with a focus on the unique viscoelastic properties of Ecoflex 00-30. Using high-speed imaging and controlled experiments, the links between surface energy, material stiffness, and thickness are analyzed to uncover key mechanisms controlling wetting behavior.

The results show that maximum wetting speed is primarily influenced by surface chemistry, while elasticity plays a less important role unless coupled with …

Mitigation Of Transverse Gusts On Morphing Wings Via Span-Wise Twisting, Alex Ruiz

Graduate Thesis and Dissertation post-2024

Wind gust encounters create a highly unstable and unpredictable environment for air vehicles. Small aircraft are especially susceptible to gust-induced disturbances due to their limited size and weight, leading to significant fluctuations during flight. This study introduces a novel concept involving a twisting mechanism along the wingspan, allowing for span wise variations in pitch. Using a towing tank and a gust generator apparatus, we demonstrate the effectiveness of the proposed mechanism. Force data and flow field data obtained from Particle Image Velocimetry (PIV) provide insights into the vortex mechanisms at play. A Modified Discrete Vortex Method using the leading-edge separation …

Fundamental Breakup Mechanisms Of Micron-Scale Fuel Droplets Behind Hypersonic Shock Waves, Steven Schroeder

Graduate Thesis and Dissertation post-2024

The enhanced efficiency of pressure-gain combustion through detonation has fueled renewed research towards how liquid droplets atomize within a hypersonic shock-driven flow field. The heightened energy of post-hypersonic-shock flow compared to post-supersonic-shock flow leads to increased heating of the droplet, and faster phase change rate, which could potentially alter dominant breakup modes from mass loss via aerodynamic drag towards evaporation. As such, the displacement, deformation, and breakup timescales of various micron-scale liquid fuel droplets (RP-2, Jet A-1, and dodecane) behind hypersonic shocks were observed via high-speed 5 MHz shadowgraph imaging. The role of aerodynamic drag was quantified by modulating the …

Dynamic Ground Response Of Sandy Soils Under Vibratory Roller Compaction, Jorge Eliecer Ballesteros Ortega

Graduate Thesis and Dissertation post-2024

Vibratory roller compaction is a common technique for densifying granular materials in road construction, utilizing a combination of static and dynamic loads for greater efficiency. However, the vibrations generated during compaction activities can cause structural damage and human discomfort. This thesis investigates the dynamic ground response of sandy soils under vibratory roller compaction, aiming to predict the induced ground vibrations and deformations. Field tests were performed at different road construction sites in Central Florida by using geophones and settlement transducers to provide empirical support for the analysis. Finite element and finite difference models, implementing Hypoplasticity Sand and PM4Sand as constitutive …