University of Central Florida
University of Central Florida (UCF): STARS (Showcase of Text, Archives, Research & Scholarship)Not a member yet
166656 research outputs found
Sort by
Baseball-State of the Game
No full textAs we enter the final week of the baseball season, it might be time to reflect on the state of the game. This is generally the point in the season when there is a rash of jeremiads on the condition and health of the former national pastime. Baseball people seem to always see the game in decline. Over the years, I have dismissed these as overblown and off the mark, because generally they are. Now, for the first time in my multiple decades as a baseball fan, I am ready to join the mournful chorus
Case Report: Adult Patient with Acquired Apraxia of Speech Secondary to a Stroke in Broca\u27s Area
Get PDFThis open educational resource (OER) is a case report about an adult patient with acquired apraxia of speech secondary to stroke in Broca\u27s area. This case report was originally developed for SPA 6236: Motor Speech Disorders, School of Communication Sciences & Disorders, University of Central Florida, by Richard Zraick, Ph.D., CCC-SLP, F-ASHA. The content was based on output from ChatGPT and generated with the prompt: “Create a fictional case report for an adult patient with acquired apraxia of speech secondary to cerebrovascular accident in Broca’s area.” Others are free to reuse this OER to distribute, remix, adapt, and build upon the material in any medium or format, as long as acknowledgment is given to Richard Zraick and ChatGPT. Please review the license, CC BY 4.0, for more information
Handwritten Digit Recognition using Naive Bayes and K-Nearest Neighbor Models
Get PDFThis 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 3, producing the highest accuracy and reducing misclassifcation rates. The comparative analysis helps identify each model’s strengths and limitations and emphasizes the need to explore advanced models in improving and understanding linear classifcation
Uncovering Acoustic Biomarkers to Classify Parkinson Disease through Machine Learning
Get PDFThe 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 offer valuable insights into disease detection
AI-Infusion through a Three-step Model of Assignment Analysis
Get PDFA three-step process model was employed by the instructor to determine if there was an opportunity for using an AI tool as part of completing a summative assignment. Three areas were identified for AI-infusion based on them being secondary to the primary focus of assessment. Resources and guidelines were developed to support students in using ChatGPT to independently generate content to use in editing a project plan
Spreading Hope at Give Kids The World
Get PDFThis semester-long project is aimed to facilitate civic engagement by connecting students with their local community. It provided an opportunity for students to collaborate with their peers in order to gain insight into the organization’s core mission and its root causes. Through this experience, students were empowered to make informed decisions and develop a stronger sense of active citizenship
It is highly expected for students to establish group principles and set clear common goals to forward transformative changes. Therefore, they are responsible for organizing group meetings as well as volunteering to uplift an organization in carrying out its mission.
Through this, I’ve learned the importance of collaboration, how powerful community support can be. Each group member has their own unique volunteering experience. For me, I underestimated the impact of operating amusement park rides, but over time, I saw how simple acts of kindness can make a lasting impact on children facing life-threatening illnesses. Ultimately, this project has deepened my appreciation for the role of volunteerism in achieving meaningful change.https://stars.library.ucf.edu/hip-2025spring/1010/thumbnail.jp
Crafting Cards for Illness Warriors
No full textThis semester, we focused our project on the non-profit organization Cards2Warriors, who aim to deliver countless cards in the form of “Happy mail” to illness warriors, their families, caregivers, and medical professionals in order to spread kindness and love in times of darkness. Through hosting our own community service events in UCF\u27s LEAD Scholars Lounge, we\u27ve been able to add over 100 cards to the 44,152 cards that have already been sent out to this day by the amazing organization! Throughout our time working together as a group, we have learned the true meaning of making a good impact on not only our community but the rest of the world. With hard work, time management, collaboration, and communication, we have been able to make our project as successful as we\u27ve hoped!https://stars.library.ucf.edu/hip-2025spring/1011/thumbnail.jp
The Relationship between the U.S Stock Market and Energy Commodities
Get PDFThis project began with the goal of finding the predictive power of oil and natural gas on the U.S. stock market. We gathered and used government-issued data on foreign oil imports volume and grade, domestic crude oil prices, domestic natural gas prices and volume, and S&P 500 prices from the 2023 fiscal year. We wrote a program in R that used several different criteria to give us the relationship between the above variables in a simple, optimal, mathematical model. We also used methods from our course such as the Box Cox transformation test to refine our variables. Ultimately, we found the value of the S&P 500 is incredibly difficult to predict with energy commodity values, with the only model of significant prediction power simply having natural gas volume as its only variable.https://stars.library.ucf.edu/hip-2025spring/1058/thumbnail.jp
