Physical Sciences and Mathematics Commons^™

Gpr-148 A Study Of Different Real-Time Robotic Applications, Yongshuai Wu

C-Day Computing Showcase

Real-time operating systems (RTOS) are widely used in various robotic applications such as path planning and obstacle avoidance, which require real-time communication and interaction with the environment, posing significant challenges for RTOS design.In this paper, we will first explore different robotic control and decision-making applications based on RTOS. Then, we will study the implementations of several widely employed RTOS frameworks. Finally, we will analyze how different RTOS implementations impact overall system performance and discuss the advantages and limitations of these RTOS frameworks based on previous research.

Gpr-155 Integration Of Quantum Natural Language Processing (Qnlp) With Neo4j Llm Knowledge Graphs For Enhanced Nlp Tasks, Suman Bharti

C-Day Computing Showcase

This study investigates the integration of Quantum Natural Language Processing (QNLP) with Neo4j LLM Knowledge Graphs (KGs) to enhance natural language understanding tasks. By leveraging quantum circuit simulations, we aim to improve the probabilistic interpretation of relationships between entities. Our preliminary findings suggest that QNLP offers deeper insights compared to traditional NLP methods, particularly in modeling complex entity relationships. This approach also addresses significant limitations in Neo4j-based Large Language Model (LLM) Graph Databases, such as handling high dimensional relationships and capturing semantic nuances. The integration of QNLP into Neo4j refines relationship modeling and enhances performance in tasks like entity extraction …

Gpr-161 Meta-Reinforcement Learning With Discrete World Models For Adaptive Load Balancing, Cameron J Redovian

C-Day Computing Showcase

We present a novel integration of the RL^2 meta-reinforcement learning algorithm with discrete world models, employing the DreamerV3 architecture, to enhance load balancing in operating systems. This integration allows for rapid adaptation to dynamic workload distributions with minimal retraining. In experiments using the Park load balancing environment, our approach outperformed the traditional AC3 algorithm in both standard and adaptive trials. Additionally, it exhibited strong resilience to catastrophic forgetting, maintaining high performance despite continuous variations in workload distribution and size. These results demonstrate the effectiveness of combining recurrent policy networks with discrete world models, offering a significant advancement in meta-learning capabilities …

Gpr-2212 Explainable Multi-Label Classification Framework For Behavioral Health Based On Domain Concepts, Francis E Nweke, Abm Adnan Azmee

C-Day Computing Showcase

Behavioral health, which covers mental health, lifestyle choices, addictions, and crises, poses serious issues in the community. Thus, appropriately analyzing and classifying behavioral health data is crucial for making informed healthcare decisions. Traditional deep learning and natural language processing approaches struggle to effectively identify behavioral health issues because the data is unstructured, complex, and lacks sufficient context. Furthermore, subject matter experts must be consulted to ensure effective identification. In this work, we proposed a deep learning-based framework consisting of several modules: A) domain concept encoder converts the keywords and their evidence types to vectors, which were predefined by a subject …

Gpr-2238 Tech Guru: A Domain Specific Llm For Tech. Industry​, Francis E Nweke, Long Vu, Nitin Jha

C-Day Computing Showcase

This project focuses on developing a domain-specific chatbot tailored for the tech industry. The chatbot utilizes articles sourced from blogs written by developers and engineers at leading companies such as Google and NVIDIA. Titles and content from these articles are extracted to form a question-answer dataset, with the titles acting as questions and the article content serving as answers. To refine the questions, we implemented a custom method to format the dataset to follow Alpaca format. The resulting question-answer pairs are then used to fine-tune a language model, adapting it to the specialized domain of the tech industry. Following this, …

Uc-129 Angel Among Us Pet Rescue - Website Enhancement With Chatbot, Koen Victorica, John Huffstutler, Chaz Dooley, Elizabeth A Kovaltchouk

C-Day Computing Showcase

This project integrates an AI-powered chatbot into the Angels Among Us Pet Rescue website, enhancing user experience by efficiently addressing common queries. The chatbot uses large language model (LLM) technology, which in this project is ChatGPT, to understand and respond to user questions dynamically. A content management system (CMS) supports easy updates to the chatbot’s responses, allowing Angels Among Us staff to manage FAQ entries without technical intervention. The chatbot integrates seamlessly with the existing website, maintaining the organization’s aesthetic, accessibility, and compatibility across devices. This enhancement improves user engagement and streamlines support, enabling the nonprofit to focus more on …

Uc-141 It Capstone Project 17 - Ksu Esports Tournament Bot, Patricia G Helfrick, Niranjanaa Jayakumar, Daniel J Schroeder, Trinity F Miller, Jackson M Stogsdill

C-Day Computing Showcase

In this project, our team has automated tournament tasks in the KSU eSports Discord server, with a focus on the League of Legends tournaments. Our team has implemented a matchmaking algorithm that forms teams consisting of players placed within one tier of each other, so teams are evenly matched. Our team has also created a database that stores player statistics and has been integrated with the Discord bot. Furthermore, our team has integrated the developer API with the Discord bot, which pulls player data from the API when players join the server, and the team has been working to improve …

Uc-144 Attack Surface Management And Analysis, Danard S Mclemore, Nick A Tanner, Keshaun Berry, Nelson Thairu, Niang Ciin

C-Day Computing Showcase

Recent advancements in AI have made knowledge more accessible, but this also introduces risks, as vulnerabilities can now be quickly found and exploited. To address this, we developed a comprehensive, cloud-native attack surface monitoring suite in Google Cloud. Integrating open-source intelligence tools like OWASP Amass and Project Discovery, along with custom Python-based processing, we gather extensive security data—covering subdomain enumeration, open ports, HTTP responses, and DNS configurations. This data is stored in BigQuery, processed, and visualized in Looker Studio for easy client interpretation. A containerized, scalable backend with a Flask-based API ensures seamless tool integration and adaptability. BigQuery ML further …

Uc-156 Swap - A Solo Developed Fps Game, Noah G Schultz

C-Day Computing Showcase

SWAP is an FPS game that blends tactical thinking with quick reflexes and player expression. Your dog Chomper has been kidnapped by the Big Dogs Mafia, and you must infiltrate their undercover locations to bring Chomper back home safe and sound. Along the way, the player will be asked to think on the fly, grabbing anything they can get their hands on to use as a weapon. From pistols and shotguns to forks, screwdrivers and keyboards, everything that the player can pick up is a deadly weapon.

Uc-166 The Eternal Guest - A 2d Hack-And-Slash Game, Luke H Gamage, Zion Johnson, Benjamin J Hedges, Bryanna N Walker, Avis A. Ewing

C-Day Computing Showcase

The Eternal Guest is a narrative-driven, hack-and-slash combat and exploration game where you make meaningful friendships, battle enemies, and regain lost memories as you traverse a strange, non-euclidian hotel. Use a wide array of weapons and abilities alongside the knowledge you gain from other guests to attempt to escape the bloodlust of a homicidal vampire. The Eternal Guest emphasizes 2D, top-down, melee combat in combination with ranged abilities, offering an exciting dynamic to gameplay. Our game also presents a unique spin on randomized exploration through its unique D.R.E.A.D. system, creating a sense of unease and uncertainty when exploring. This unique …

Uc-173 Leveraging Large Language Models To Empower Caretakers Of People With Dementia, Mercy Olaniran, Emily A Centeno

C-Day Computing Showcase

Behavioral symptoms of Alzheimer's Disease and Related Dementias (ADRD) are detrimental to the quality of life for individuals with ADRD and their caregivers. Symptoms such as wandering, agitation, and confusion can often overwhelm caregivers leading to stress, depression, or burnout which can lead to a decrease in the quality of care. These challenges often result in increased hospitalizations and care costs, creating a need for a solution to support informal caregivers. This project proposes the development of an AI-based Dementia Care Voice Assistant application to meet the needs of caregivers. Using large language models, the application will provide real-time and …

Uc-176 Cybriant: Attack Surface Management, Diwakar Rai, Nicholas Agyen-Frempong, David Laurent, Daniel Gutierrez, Jose R Mendoza

C-Day Computing Showcase

As businesses and organizations expand their operation digitally, so too do the vectors for attack expand. In partnership with Cybriant, this application develops an Attack Surface Composite Score by breaking down various attack common vectors. DKIM records, Open Port Scanning, and other metrics are compiled with the aid of Google Cloud Run jobs, deposited into Google BigQuery for analysis, and packaged and generated using (Grafana/Kibana) as the front-end for our software stack. Our resulting application presents rapid, easy-to-understand breakdowns of various cybersecurity metrics and their impact.

Uc-180 Intelligent Object Retrieval Using Mobile Manipulator, Zhiwen Zheng, Ellie Ireland

C-Day Computing Showcase

A mobile manipulator for intelligent object retrieval is presented. The system was integrated using state of the art R&D hardware and software, which implemented autonomous navigation, object recognition, and object pose estimation based optimal grasping. The retrieval of an object of interest is commanded that involves subsequent object detection and recognition while autonomously navigating using the known map and starting from an arbitrary position. From close proximity, object pose estimation based optimal grasp is selected to pick up the object. The object is retrieved back to the start position in this scenario. An 84% trial-phase precision in object retrieval is …

Uc-182 Designing A User-Centered Mobile Application For Anderson Power Services, Ryan Guzman, Cooper Goswick, Anthony Phan, Marie Fotso, Larnel Francois

C-Day Computing Showcase

This paper presents the design and development process of a mobile application for Anderson Power Services, emphasizing both frontend and backend aspects as well as their design. The frontend focuses on creating a visually appealing and user-friendly interface by utilizing clear text, an accessible color scheme, appropriate logos, animations, and modern typography. On the development side, the app leverages tools like Expo for rapid front-end development and integrates the Java-based backend with the Google Sheets API for easy data management. The backend architecture incorporates OAuth 2.0 for secure authentication, Gradle to facilitate a connection between the JavaScript frontend to the …

Uc-186 Ksu Esport: Competitive Speedrun Plugin For Minecraft Java Edition, Rachel Amponsah, Adam Y Greene, Christopher Kirkwood, Weeldy Benjamin, Steven A Kelsey

C-Day Computing Showcase

The KSU Esports Minecraft Speedrun plugin transforms traditional, manually managed speedruns into an automated team-based competition event. Players are challenged to complete a set of objectives within a set time limit – promoting teamwork and strategic planning. Various modes are supported, such as weighted/unweighted speedruns, team-based speedruns, and player free-for-all. Designed for flexibility, the plugin allows for customizable settings and support for future versions of Minecraft.

Uc-189 Chessai, Joshua M Peeples, Ashton D Miller, Matthew D Corvacchioli, Dylan Luong, Allen L Smith

C-Day Computing Showcase

Chess is a widely acclaimed two-player strategy game, where the primary objective is to checkmate the opponent's king, placing it in a position of imminent threat from which it cannot escape. Our aim was to innovate within this classic framework by developing a novel chess game that adheres to the traditional rules while enhancing accessibility for players of all skill levels. This game features a selection of AI models, each offering unique decision-making processes that create diverse gameplay experiences based on the chosen model. The AI operates by simulating every possible move on the board, meticulously evaluating each resulting position. …

Uc-197 It Capstone 4983: Honeybaked Ham Intranet Sharepoint Site Transformation Presentation, Martez D Andrews Ii, Kayla Pyram, Amir Abdolkarimi, Precious Flowers, Ardarius Ceasar

C-Day Computing Showcase

The purpose of our team’s research is to explore and define ways in which we can advance aesthetics and functionalities of how website content and ideas are presented to HoneyBaked Ham end users. Our team has goals of identifying crucial focal point areas and various ways we can overall improve upon such. We will utilize practicality, ingenuity and creativity, in order to demonstrate and perform deliveries of proper new perspectives of the site. We will seek out such advancements we can add while remaining within necessary parameters, maintaining the respected, well renowned HoneyBaked Ham Brand. We would like it to …

Uc-202 Indy-5 Building Map Application, Harrison Varnadoe, Eduardo A Payan, Zach W Wilson, Lucas A Haas

C-Day Computing Showcase

This project’s goal is to develop a simple secure mobile application for all devices to provide a detailed interior map that can guide users to any location in the building. It will use QR codes for ease of access, and the app will provide guidance via room numbers and a visual route. Our scope includes designing the architecture of the app, creating a responsive and interactive map User interface in an app that is compatible across all devices for a nice user experience.

Uc-226 Real-Time Bus Monitoring Using Kafka, Samuel A Bostian, Michael Rizig, Charlie Mclarty, Brian A Pruitt, Allen Roman

C-Day Computing Showcase

The GCPS Real-Time Bus Monitoring System aims to enhance bus operations for Gwinnett County Public Schools by transitioning from a polling-based system to a real-time Kafka event-streaming architecture. This project processes telemetry data from over 2,000 buses, simulating a scalable, near-instantaneous data flow into an SQL Server database. Key features include real-time data validation, efficient data storage, and containerized deployment for consistency across environments. Using an Agile approach, our team handled evolving requirements from the sponsor, who is new to senior project collaborations. This system enables GCPS to monitor bus locations with reduced latency, enhanced accuracy, and improved resource management, …

Uc-231 Symptom-Based Disease Prediction, Jarred M Barber, Kody Clark, Ryan Mwangi, Zhiwen Zheng

C-Day Computing Showcase

This project focuses on leveraging large-scale data sets and advanced analytical techniques to predict the onset of diseases. By integrating data from medical records, genetic information, and environmental factors, the project aims to identify patterns and risk factors associated with various diseases. Machine learning algorithms and statistical models are employed to enhance the accuracy of predictions, enabling early diagnosis and personalized healthcare interventions. This approach improves patient outcomes and contributes to the efficiency and effectiveness of healthcare systems.

Uc-248 Campus Ai Companion Mobile App, Dorian Taponzing Donfack, Aurelien Takou, Leopold Sokoudjou Gatsing, Yann Djoumessi, Manuella Koodjo

C-Day Computing Showcase

The Campus AI Companion app is designed to enhance students' university experiences by providing personalized recommendations for courses, events, clubs, and career paths. Leveraging OpenAI’s language model and developed using React Native, this mobile application integrates academic and social guidance, tailored for individual users based on their interests and performance. This AI-driven companion aims to help students better navigate their university journey by providing seamless access to resources, activities, and support that align with their academic and personal goals.

Ur-147 An 8-Bit Digital Computer Design & Implementation (Team Coa-Wm1), Adrian L Sherard, Jesus Flores, Biswash Lamsal, Blake Hammontree, William Pitts

C-Day Computing Showcase

8 bit computer design using NI multisim

Improving Students’ Cognitive Abilities In Remote Learning Environment Using Brain Computer Interface And Eye-Tracking, Nuraini Jamil

Thesis/ Dissertation Defenses

Attention and cognitive engagement are crucial factors in remote learning environments, where the absence of physical presence often diminishes learning outcomes. Traditional methods for assessing these cognitive states, such as observation and self-reporting, are limited by subjectivity and inefficiency. Automated solutions, particularly those based on biometric data like EEG and eye-tracking, offer a more accurate and scalable alternative. However, developing robust systems that leverage biometric data in real-time presents significant challenges. These include handling large volumes of complex data, ensuring low-latency processing, and adapting machine learning models to diverse learning environments and individual cognitive states. Additionally, the integration of neurofeedback …

Quantum Markov Chains Related To Certain Lattice Models, Ali Alalaai

Thesis/ Dissertation Defenses

A central open problem in quantum field theory is the construction of a general theory of quantum field, this thesis introduces quantum probability and applies it via the construction of quantum Markov chains on different hierarchical lattices (Cayley trees). Furthermore, these trees correspond to the Ising-XY-Model which then the existence of a unique Markov chain can be utilized to detect phase transitions.

Drone Vs. Drone, Mariah Smith

Cybersecurity Undergraduate Research Showcase

This paper focuses on the problems that drones pose to digital and physical infrastructure, as well as potential solutions to combat these issues. One solution is incorporating drone usage into ethical hacking. These drone-based attacks are affecting not only economic spaces but also seemingly high-security areas such as prison systems. It is only a matter of time before critical infrastructure is targeted. Conversely, by simulating drone attacks, drones equipped with complex hacking tools and sensors can detect unauthorized pathways and infiltrate networks for the greater good. Incorporating these new practices would enhance digital and physical protection. "Drone vs. Drone" highlights …

Ongoing Efforts To Develop Open Climate Change Resources: An Interview With Dr. Tamara Shapiro Ledley, James Thibeault

Open Educational Resources Publications

This article explores the significant contributions of Dr. Tamara Shapiro Ledley in developing open educational resources (OER) for climate change education. Through an interview with Dr. Ledley, the article highlights her journey from a climate science researcher to a passionate advocate for open access to scientific information. Dr. Ledley's work, funded by prominent organizations such as the National Science Foundation (NSF), NASA, and NOAA, has focused on creating and disseminating freely accessible resources to enhance public understanding of climate science. Key initiatives discussed include the Earth Exploration Toolbook (EET), EarthLabs, and the Climate Literacy and Energy Awareness Network (CLEAN). These …

Improving Data Curation With Spectral Clustering And Shannon Entropy: An Unsupervised Approach Within The Data Washing Machine, Erin Hathorn

Theses and Dissertations

In the ever-expanding landscape of digital technologies, the exponential growth of data presents both challenges and opportunities, demanding innovative approaches to data curation. Effective data curation is pivotal for extracting meaningful insights from vast and complex datasets. This study explores the integration of spectral clustering and Shannon Entropy within the Data Washing Machine (DWM), a novel tool designed to streamline unsupervised data curation processes. The DWM incorporates Shannon Entropy into its clustering process, allowing for adaptive refinement of clustering strategies based on entropy levels observed within data clusters. Spectral clustering, known for its ability to handle complex and non-linearly separable …

Strategies To Alleviate Flickering: Bayesian And Smoothing Methods For Deep Learning Classification In Video, Noah Miller, Glen Ryan Drumm, Lance Champagne, Bruce A. Cox, Trevor Bihl

Faculty Publications

Excerpt: Increasing reliance on autonomous systems requires confidence in the accuracies produced from computer vision classification algorithms. Computer vision (CV) for video classification provides phenomenal abilities, but it often suffers from “flickering” of results. Flickering occurs when the CV algorithm switches between declared classes over successive frames. Such behavior causes a loss of trust and confidence in their operations.

Uc-131 Karah Khronicles, Dion Green, Jake Stipetich, Grace Bowe, Jesse Israel, Vedasri Malatker

C-Day Computing Showcase

Karah is a thief with a heart of gold, you raid enemy camps and dungeons to steal back the money stolen from towns and villages and upgrade enchanted items to deal with dangerous foes. After successfully returning the wealth to the local town, you must then face down and defeat a general of the evil king.

Should We Stay Or Should We Leave? Multi-Objective Tradeoffs In Identifying Robust Beach Nourishment And Managed Retreat, Prabhat Hegde

Sustainability Seminar Series

In some low-lying coastal areas around the world, decision-makers are beginning to consider “managed retreat” of human populations to adapt to sea-level rise. One of the main challenges in designing a managed retreat strategy is determining when to trigger retreat. Decision-makers lack tools and scientific understanding to evaluate whether the benefits of interim response strategies, like beach nourishment, outweigh the costs of waiting longer to trigger retreat.

In this talk, I will contextualize the coastal beach nourishment problem within the umbrella of decision analyses frameworks for climate change adaptation. I will demonstrate how considerations of uncertainty and multiple objectives improve …