Computer Sciences Commons^™

Grm-042 Ihelp: A Care Partner Activation Program Mhealth System For Ad/Adrd Caregivers, Trisha Bhowmick

C-Day Computing Showcase

The iHelpCare platform is designed to offer a seamless and supportive experience for patients and caregivers through a clear and user-friendly interface. Users begin at the login page, where they can either sign in or create a new account. Once logged in, the home page provides access to essential services such as a 24/7 helpline, emergency visit coordination, emergency support, and a service directory. It also includes engagement tools like discussion forums, learning modules, and resource materials, along with community-focused features such as events, activities, and support groups. The personalized dashboard allows users to monitor health conditions, review patient history, …

Grm-081 Evaluation Of Hand-Crafted Features With Mask Images Obtained From Pannuke Dataset Using Bayesian Optimization And Machine Learning Models, Siri Yellu

C-Day Computing Showcase

Semantic image segmentation enables computing systems to understand the semantic patterns of image pixels by using deep learning models to classify the pixels into specific labels. The deep-learning models’ performance in image classification has been evaluated by comparing the predicted images using deep-learned features with human-labeled images or mask images. However, there remains a substantial need to investigate the performance of machine learning models that do not use deep learned features but use hand-crafted features. In this project, we perform a comprehensive evaluation of the performance of the eight machine learning models using 46 hand-crafted features extracted from the PanNuke …

Grp-087 Empowering Alzheimer’S Caregivers: Designing Explainable And Personalized Ai For Mental Health Support​, Syeda Umme Salma, Chandra Rekha Renduchintala, Isa Siddique

C-Day Computing Showcase

This study presents the design of an AI-powered caregiver support app aimed at personalized mental health and burden management for individuals caring for Alzheimer’s patients. The design is grounded in insights drawn from a comprehensive analysis of 28 recent studies on AI-driven mental health interventions. These findings informed the implementation of key features, including machine learning models such as Random Forest, clustering, and supervised learning to create adaptive care plans tailored to patient and caregiver profiles. The system dynamically adjusts task schedules based on engagement data and provides interpretable recommendations through SHAP. With built-in emotional check-ins, mood tracking, and caregiver-centric …

Grp-077 Mulisa: Mhealth-Enabled User-Friendly Light-Based Stroke Screening And Assessment In Pediatric Sickle Cell Disease In Uganda, Nursat Jahan, Ayushi Bharath Raj

C-Day Computing Showcase

This research presents a novel mHealth-enabled solution for stroke screening of sickle cell disease children in LMICs using light-based stroke screening technologies. We conducted a systematic literature review to identify key barriers and used these insights to develop a conceptual framework guiding the design of an integrated system. Our prototype includes a SWIR SCOS device and a wearable oximeter, combined with an AI-enhanced mHealth platform. The proposed mHealth framework aims to improve screening accessibility and adoption in low-resource settings.

Grp-088 Nutrilyzer: A Vision-Based App For Macronutrient Estimation And Blood Glucose Response Prediction, El Arbi Belfarsi

C-Day Computing Showcase

This study predicts postprandial glucose peaks and spike durations using 10-day multimodal data from 10 participants. Glucose, meals, workouts, and insulin doses were logged via the Nutrilyzer web app. Macronutrient content carbs, fats, and proteins was extracted using GPT-Vision, a highly accurate food analysis tool. These tuples were normalized to baseline glucose and aligned with a 3-hour window post-meal. Three models were tested: LSTM, Time Series Transformer, and ARIMA. LSTM performed best with 83.78% accuracy, followed by Transformer (71.43%) and ARIMA (62.41%). Results show the promise of AI-based food logging and time series modeling for personalized glucose forecasting.

Uc-023 Bathtub Racing Game, Sasha Melbourne, Sulaiman Bah, Damari Brown, Deylin Ealy, Adam Calo

C-Day Computing Showcase

The Virtual Bathtub Racing Game is a capstone project that uses an interactive 3D digital experience to preserve and modernize the long-standing bathtub racing tradition at Southern Polytechnic State University (SPSU). With real-world physics, adjustable features, and multiplayer capabilities, the Unity-developed game recreates the famous event where students raced imaginatively designed bathtub carts. Since stakeholder input influences the creation of tracks, sound profiles, and gameplay elements that replicate the original races, alumni involvement is crucial in determining the authenticity of the game. In order to provide a captivating user experience for both new players and past SPSU students, the project …

Uc-026 Pet Matchmaker, Victoria Davis, Colton Baldwin, Edward Sadler

C-Day Computing Showcase

Angel Among Us is a non-profit organization that saves animals from high-killing rate shelters in Georgia. Their goal is to find homes for homeless pets. To increase their efforts, they are developing a web-based application to help improve adoption processes. The goal is to increase adoption rates and be able to provide adopters with information about pets and overall reduce the number of pet returns. This will be accomplished by using adopters’ information and preferences from the web-based application to find long-term compatibility with their recommended pets. The objective is to create a web application interface that includes many core …

Uc-028 Intelligent Arm Meets Machine Vision, Alvaro Esteche, Sergio Sanchez-Alvares

C-Day Computing Showcase

Most AI and robots have been used to make mundane tasks easier for humans however intricate tasks, such as monitoring have not been tackled. Using the OpenMANIPULATOR-X, Robot Operating System (ROS2), and machine vision, we planned on having AI tracking monitor with 4 degrees of freedom.

Uc-029 Graphbat: Subterranean Data Visualizer, Caroline Roberson, Abdalla Ugas, Nathan Karg, Hayden Harper

C-Day Computing Showcase

GraphBat is a desktop data visualization application designed for speleology and similar fields that bundles common graph types with a unique heatmap tool which few comparable apps provide. It was developed in Python and is intended as an open-source tool available for use and extension by the scientific community. The heatmaps offer two data interpolation methods—inverse distance weighting and linear interpolation—to visualize the spread of data across a space using a real-world map and sensor data relative to the space. GraphBat aims to expediate scientific analysis and facilitate the presentation of results across many fields of subterranean study.

Uc-046 Cat Classification Of 20 Distinct Breeds, Tabitha Washington, Ashley Nestor

C-Day Computing Showcase

Cat breed classification algorithms have been made time and time before due to cats being such a popular and beloved animal. As such, classification algorithms aim to identify their breeds for veterinary pursuits and wildlife tracking which necessitates accurate classification. Our classification algorithm identifies 20 different CFA-recognized pedigreed cat breeds utilizing TensorFlow with the MobileNetV3 Large model as the base for training. Our preliminary results over 25 initial epochs and 25 fine tuning epochs resulted in a model with a test accuracy of 65%. In the future, we plan to add more techniques to prevent overfitting and experimenting with a …

Uc-061 From Frustration To Function: Enhancing Usability In Public Transportation, Marcus Harrison, Hong Nguyen, Mohamed Khatib, Austin Krusemark

C-Day Computing Showcase

Public transportation apps have recently become an essential tool for helping individuals navigate complex transit systems, however, many users still face issues with usability, accessibility, and reliability. Taking this into consideration, this project aims to evaluate the user experience of these apps and how one in particular can be improved. In doing so, our group hopes to create a more user-friendly experience that can make public transportation easier and more reliable for everyone.

Uc-066 Thought-Memory Model For Multi-Agent Simulation, Nicholas Hodge, Josue Sandoval, Greyson Paschall

C-Day Computing Showcase

A 2D web-based multi-agent simulation leverages Large Language Models to model human-like interactions among generative agents. A Thought-Memory system retrieves relevant data and prior memories from a database to construct JSON-style prompts for the LLM, which outputs intended agent actions. The system allows for observable, emergent interactions between agents within the simulated space.

Uc-072 “Command Center, Do You Copy?”, Sawyer Strickland, Ezavier Miller, Max Hardy

C-Day Computing Showcase

“Command Center, do you copy?” is a sci-fi themed survival horror game where players must sneak around and fend off an alien like enemy using their flashlight while also trying to find the parts needed to fix their communications system to call for help.

Uc-085 Berry And Carrot - A 2.5d Unity Platformer Game, Everett Joiner, Rin Egl, Carter Griffin, Kcyana Redmon

C-Day Computing Showcase

In Berry and Carrot, you play as two stuffed animals, a bear and a bunny, who are trying to escape from a claw machine that they have been trapped in for years. Each character has different strengths, and the player must use these skills strategically by switching between the two characters to solve puzzles themed around the inner workings of the claw machine featuring screws, springs, levers, and more.

Uc-092 Cookly.Io - Advanced Recipe Generator, Mikita Slabysh, Evan Valencia, Chris Martinez

C-Day Computing Showcase

Cookly.io was a passion project started during the AI Club Hackathon where it was awarded 3rd place. Cookly is an AI powered recipe assistant that helps users use available ingredients into delicious meals. Users can input ingredients manually or upload a photo of the pantry or fridge where Cookly will use computer vision to identify the ingredients and SBERT to match the ingredients with the perfect recipe.

Uc-100 Agentic Ai Quiz Generation: Personalized Tutoring Through Intelligent Retrieval And Adaptive Learning, Devananda Sreekanth

C-Day Computing Showcase

This research presents a personalized, agentic AI-powered system for multiple-choice question (MCQ) generation tailored to college-level tutoring in machine learning and software engineering domains. The primary objective is to enhance adaptive learning through reliable, context-aware quiz generation using long-context large language models (LLMs) and modular agent workflows. Our methodology is based on an eight-stage agentic architecture that separates tasks into two main phases: vector indexing and personalized quiz generation. In the indexing phase, academic PDFs are parsed, chunked with LangChain’s RecursiveCharacterTextSplitter, embedded via Google's text-embedding-005, and indexed using FAISS. A verification agent ensures topic alignment and integrity of the vector …

Ur-086 Whole Slide Image Analysis, Pranav Kartha, Jazwaur Ankrah

C-Day Computing Showcase

Whole Slide Images are used to capture details of patient cells. Hospitals and clinics have different processes and methods to create WSIs resulting in WSIs not being standardized. Different file formats are used and different colors are used to represent different features. The normalization process helps set up the WSI into a format that the current model can easily process.

Ur-099 Empowering Mental Wellness: A Comprehensive Study And Design Of A Predictive System For Early Mental Health Intervention​, Anh Duong

C-Day Computing Showcase

Mental health is an essential part of living a balanced and fulfilling life, but it is often overlooked compared to physical health. While physical health is important for performing daily activities, mental health plays a crucial role in how we manage stress, build connections, and make decisions. Previous research studies have shown that nearly 60 million Americans experienced a mental illness in 2024, yet there were only 340 people for every one mental health provider in the U.S. Furthermore, young adults aged 18–25—who are the most digitally connected generation—suffer from the highest rates of severe mental illness yet are the …

Ur-114 K86: 16-Bit Computer Design, Optimization, And Implementation​, Calvin Crose, Juan Ferreira, Brendan Moore, Caleb Oglesby, Jack Vega

C-Day Computing Showcase

This research focused on the implementation of modern computing systems by designing and simulating a 16-bit RISC-based ISA computer. The computer is built on a Von Neumann memory architecture with 1024×16-bit word-addressable space and a 6-bit ISA with 36 implemented instructions. The central processing unit (CPU) includes a control unit (CU) that automatically drives the fetch-decode-execute (FDE) cycle, four addressable general-purpose registers (GPRs), and an Arithmetic Logic Unit (ALU) comprising 21 operations and producing four flags. We validated the system by executing Euclid's GCD algorithm, generating the binaries with a custom assembler written in Python.

Ur-112 Monarch: A Privacy-Focused Nlp Model For Emotional Pattern Detection, Tyler Clanton, Derick Burbano-Ramon

C-Day Computing Showcase

Introducing: Monarch — a privacy-focused deep learning model that interprets emotional patterns in text. Monarch is trained on large, lexicon-based datasets and uses fine-tuned NLP models (BERT) to identify patterns associated with sadness, worry, anger, and distress. It runs entirely offline with no data collection, making it ideal for private use. Monarch evaluates text and returns clear, readable probability scores across emotional categories, giving users insight into emotional trends. Monarch is interpretive, not diagnostic, displaying results based on scientifically backed linguistic patterns. Its potential use in schools could help flag early signs of distress, giving educators a chance to support …

Uc-130 Some Kind Of Tundra Escape, Tiffany Field, Patrynna Mensah, Tahjir Beene, Daniel Worrel

C-Day Computing Showcase

Some Kind of Tundra Escape is an action-adventure game where you play as a penguin trying to escape a vast, walled-in tundra. As you explore, you’ll rescue other penguins scattered throughout the area. Your goal is to gather all the penguins and escape together, but the journey is far from easy. The tundra is full of danger, including snowmen who ambush you and ice golems who patrol certain areas. You'll need to avoid these monsters and set traps to stay safe while rescuing your fellow penguins. As your group grows, so does the challenge—more penguins means more obstacles to overcome. …

Ur-017 Sherlock: Self-Supervised Histopathological Evaluation For Recognition Of Lymphocytes And Other Cancerous Kinds, Charles Pagano

C-Day Computing Showcase

Whole Slide Images (WSI) are gigantic images (e.g. 100k x 100k pixels) of tissue samples. The goal of SHERLOCK is to detect cancer cells in those tissue samples. We do this by using a pretrained Masked Autoencoder (MAE), from Facebook’s research lab, that we finetune on the PanNuke dataset. The benefit of using an MAE is that unlike supervised learning the WSI’s don’t need to be labeled. This is important because it will save a lot of time and money that would be spent on labeling WSI’s.

Ur-018 Towards Bounding The Behavior Of Deep Neural Networks, Aidan Boyce

C-Day Computing Showcase

Recent advances in Artificial Intelligence (AI) have unlocked many new possibilities but have also brought with it many new challenges. While modern AI systems have been continuously exceeding expectations, our ability to interpret and understand their behavior lags behind. For example, an AI model trained to detect pneumonia from X-rays may fail in new hospitals because it learned to recognize hospital logos instead of medical patterns. Why do some succeed while others fail? Do they truly understand their tasks, or are they relying on patterns that may not always hold? To enumerate the most informative explanations of a neuron’s behavior, …

Ur-047 Empathetic Vr Classroom, Seth Brice

C-Day Computing Showcase

We used a virtual reality classroom setting to investigate how accurately humans can determine the emotional state of NPC avatars based on nonverbal body language. Volunteers presented a topic in front of several virtual agents, who would respond with a gesture that reflected their current emotional state, giving the presenter the opportunity to physically and emotionally respond to these changes.

Ur-063 K86: 16b Computer And Assembler Design And Implementation​, Vera Warren-Aliff, Ethan Dingle

C-Day Computing Showcase

With this project, we designed a general-purpose 16-bit RISC+CISC computer architecture, alongside an assembler, instruction embedder, and preliminary compiler. Our computer architecture, K86 (Kennesaw 86), is inspired by the Intel x86 and ARM architectures that have enabled computing systems to perform many of the modern functionalities we rely on today. To allow for fluid programming and processing, KASM (Kennesaw Assembler) translates assembly code into machine instructions which will be stored in the computer memory by the embedder. With the addition of a preliminary compiler to produce assembly from high-level source code, our project defines much of the foundation of a …

Analysis Of Cybersecurity Threats And Mitigation Strategies: Theory In To Practice, Project Proposal, Fransly Dutervil

Student Academic Conference

Cybersecurity threats pose significant risks to individuals and organizations, leading to data breaches, financial losses, and operational disruptions. This presentation explores key threats such as malware, phishing, DDoS attacks, insider threats, and zero-day exploits. It also discusses mitigation strategies, including network security measures, multi-factor authentication, encryption, and incident response planning. Through case studies of real-world cyber incidents, we highlight lessons learned and best practices to strengthen security defenses. The goal is to enhance awareness and promote proactive cybersecurity measures in an increasingly digital world.

Ai Assistance In Legal Analysis: An Empirical Study, Johnathan H. Choi, Daniel Schwarcz

Journal of Legal Education

No abstract provided.

Leveraging Benford’S Law And Machine Learning For Financial Fraud Detection, Benjamin R. Fu

Cybersecurity Undergraduate Research Showcase

Financial fraud, particularly credit card fraud, continues to pose substantial challenges to financial institutions due to its increasing frequency and impact on consumer trust. While traditional rule-based methods have provided foundational defenses, their limitations in scalability and adaptability have accelerated the adoption of machine learning (ML) techniques. Concurrently, Benford’s Law—a statistical principle often used in forensic accounting—has demonstrated efficacy in detecting anomalies within naturally occurring numerical datasets. This study explores a hybrid fraud detection approach that integrates Benford’s Law with supervised machine learning algorithms, including Logistic Regression, Random Forest, and k-Nearest Neighbors. Using the publicly available European credit card fraud …

Disentanglement In Representation Learning: Interpretability In Dimension Reduction With Vae, Minh Hong Vu

LSU Doctoral Dissertations

This research explores both theoretical and practical aspects of disentangled representation learning by extending the VAE framework. We address the core challenge of extracting independent generative factors from observed data while preserving high reconstruction fidelity. To this end, we propose two novel VAE variants: (i) the $\lambda\beta$-VAE, which incorporates an additional $\ell^2$-norm reconstruction loss to improve accuracy, and (ii) the $\gamma\beta$-VAE, which introduces a mutual information regularization term to encourage independence across latent dimensions.

Our theoretical analysis is conducted in a linear Gaussian setting, where we derive optimal solutions for these VAE-based models. We further examine how varying levels of …

Leveraging Attention Mechanism To Unlock Gene And Protein Attributes, Ala Jararweh

Computer Science ETDs

Advancing personalized medicine depends on effectively integrating and interpreting the vast, heterogeneous landscape of biological data, from genomic sequences and transcriptomics to the insights embedded in scientific literature. Current machine learning models often focus on single data modalities, limiting their capacity to capture the multifaceted nature of biological systems. We address this gap by developing three attention-based machine-learning models integrating diverse data modalities. Firstly, DeepVul is a multi-task model that leverages cancer transcriptome data to predict genes critical for cancer survival and their corresponding drugs. Subsequently, LitGene refines gene representations by integrating textual information from the scientific literature. Finally, Protein2Text …