Physical Sciences and Mathematics Commons^™

A Comparative Analysis Of Source Identification Algorithms, Pablo A. Curiel

Biology and Medicine Through Mathematics Conference

No abstract provided.

Improving Tattle-Tale K-Deniability, Nicholas G.E. Morales

Student Research Symposium

Ensuring privacy for databases is an ongoing struggle. While the majority of work has focused on using access control lists to protect sensitive data these methods are vulnerable to inference attacks. A set of algorithms, referred to as Tattle-Tale, was developed that could protect sensitive data from being inferred however its runtime performance wasn’t suitable for production code. This set of algorithms contained two main subsets, Full Deniability and K-Deniability. My research focused on improving the runtime or utility of the K-Deniability algorithms. I investigated the runtime of the K-Deniability algorithms to identify what was slowing the process down. Aside …

Securing The Internet Of Things At Scale, Steven L. Willoughby

Student Research Symposium

The world of the connected “Internet of Things” (IoT), including the "Industrial Internet of Things" (IIoT) is expanding to include more devices which observe and influence our daily lives, routines, locations, and even our state of health. But have the underlying protocols by which they communicate this data kept pace with the need to protect our privacy and security?

My talk will introduce my research into an approach to better secure this information flow using appropriate access controls without sacrificing performance. I will assess the historical challenges and simple access controls applied to IoT networking protocols and how they can …

A Novel Caching Algorithm For Efficient Fine-Grained Access Control In Database Management Systems, Anadi Shakya

Student Research Symposium

Fine-grained access Control (FGAC) in DBMS is vital for restricting user access to authorized data and enhancing security. FGAC policies govern how users are granted access to specific resources based on detailed criteria, ensuring security and privacy measures. Traditional methods struggle with scaling policies to thousands, causing delays in query responses. This paper introduces a novel caching algorithm designed to address this challenge by accelerating query processing and ensuring compliance with FGAC policies. In our approach, we create a circular hashmap and employ different replacement techniques to efficiently manage the cache, prioritizing entries that are visited more frequently. To evaluate …

Integration Of Agent Models And Meta Reinforcement Learning (Meta-Rl) Algorithms For Car Racing Experiment, Vidyavarshini Holenarasipur Jayashankar

Student Research Symposium

Introduction: Achieving optimal performance in 2D racing games presents unique challenges, requiring adaptive strategies and advanced learning algorithms. This research explores the integration of sophisticated agent models with Meta Reinforcement Learning (Meta-RL) techniques, specifically Model-Agnostic Meta-Learning (MAML) and Proximal Policy Optimization (PPO), to enhance decision-making and adaptability within these simulated environments. We hypothesize that this innovative approach will lead to marked improvements in game performance and learning efficiency.

Methods: In our experimental setup, we applied MAML for its rapid adaptation capabilities and PPO for optimizing the agents' policy decisions within a 2D racing game simulator. The objective was …

Story Of Your Lazy Function’S Life: A Bidirectional Demand Semantics For Mechanized Cost Analysis Of Lazy Programs, Laura Israel, Nicholas Coltharp

Student Research Symposium

Lazy evaluation is a powerful tool that enables better compositionality and potentially better performance in functional programming, but it is challenging to analyze its computation cost. Existing works either require manually annotating sharing, or rely on separation logic to reason about heaps of mutable cells. In this paper, we propose a bidirectional demand semantics that allows for reasoning about the computation cost of lazy programs without relying on special program logics. To show the effectiveness of our approach, we apply the demand semantics to a variety of case studies including insertion sort, selection sort, Okasaki's banker's queue, and the push …

Systematic Comparison Of Reservoir Computing Frameworks, Nihar S. Koppolu, Christof Teuscher

Student Research Symposium

In this poster, we present a systematic evaluation and comparison of five Reservoir computing (RC) software simulation frameworks, namely reservoirpy, RcTorch, pyRCN, pytorch-esn, and ReservoirComputing.jl. RC is a specific machine learning approach that leverages fixed, nonlinear systems to map signals into higher dimensions. Its unique strength lies in training only the readout layer, which reduces the training complexity. RC excels in temporal signal processing and is also well suited for various physical implementations. The increasing interest in RC has led to the proliferation of various RC simulation frameworks. Our RC simulation framework evaluation focuses on a feature comparison, documentation quality, …

Behavioral Intention For Ai Usage In Higher Education, Isaac A. Odai, Elliot Wiley

Student Research Symposium

This study sought to further understand the cognitive factors that influence undergraduate students' behavioral intention to use generative AI. Generative AI's presence in academic spaces opens the door for ethical and pedagogical questions. This study surveyed 51 undergraduate communication students to measure their attitudes, subjective norms, self efficacy and their behavioral intention to use GenAI for school work. The results of this study showed behavioral intent had a positive relationship with attitudes and subjective norms. The implications of these findings show that personal beliefs and the perceived beliefs of others are correlated to undergraduate students’ intent to use GenAI for …

Uc-69 Interactive Training Game Suite, Garrett J Perry, Joscelyn Cauley, Issabella Du, Sergiu Ursu, Rahaf Kokash

C-Day Computing Showcase

It is now common knowledge that simple lectures are not the most effective way for the average person to learn and retain knowledge. The Core of Engineers at the Warner Robins Air Logistic Center have tasked us to transform their PowerPoint presentations into interactive training games to improve comprehension, interaction and retention while saving time and logistical resources compared to giving a traditional lecture. We been tasked with creating game modules covering STINFO or what is or is not considered classified information, Records Management, and the No FEAR Act detailing whistleblower rights and protocols. Our team has developed a log …

Uc-105 Model Un Crisis Software, Gregory Hicks, James Ritzi, Vincent K Kipchoge

C-Day Computing Showcase

Utilizing an Agile approach, this project develops a web-based solution, the Model UN Crisis Software, to streamline the management of crisis committees in Model UN conferences. The software is developed using Microsoft Visual Studio and Microsoft SQL Server Management Studio, adhering to the .NET framework and related conventions. It leverages Microsoft Azure SQL Database for back-end data storage and follows the ASP.NET core MVC framework, utilizing powerful .NET tools such as C# and Razor. The developed software provides comprehensive features to reduce the strain of hosting a crisis committee, such as directive and news management, user management, and a messaging …

Gpr-16 Attention Driven Framework For Detecting Mental Illness Causes From Social Media, Abm Adnan Azmee, Dinesh Chowdary Attota, Francis E Nweke

C-Day Computing Showcase

Mental health is a critical aspect of our overall well-being. Mental illness refers to conditions that impact an individual's psychological state, resulting in considerable distress, and limitations in functioning day-to-day tasks. Due to the progress of technology, social media has merged as the platform, for individuals to share their thoughts and emotions. The psychological state of individuals can be accessed with the help of data from these platforms. However, it is challenging for conventional machine learning models to analyze the diverse linguistic contexts of social media data. In this work, we propose a novel attention-driven deep framework to overcome these …

Gpr-18 Case Exploration: Automatic Keyword Matching Framework For Behavioral Health, Francis E Nweke, Abm Adnan Azmee

C-Day Computing Showcase

In this demonstration, we propose a framework for exploring, identifying, and matching repeated behavioral health keywords in first-responder reports to the current set of Behavioral Health Index Terms provided by subject matter experts (SMEs). The tool incorporates behavioral health-related keywords and has a Graphical User Interface (GUI) that allows non-technical users to explore and analyze 911 first-responder reports. We utilized an inverted index, best-matching (BM25), and plain-text searching algorithms to match keywords in first-responder reports. This tool provides a comprehensive approach to report analysis by identifying indicators of mental health disorders and taking into account the assessments of humanities and …

Gpr-63 Adaptive Attention Aware Fusion For Human-In-Loop Behavioral Health Detection, Martin Brown, Abm Adnan Azmee

C-Day Computing Showcase

Identifying behavioral health is paramount for law enforcement officers to provide appropriate follow-up community care. In the current practice, law enforcement offices manually identify these behavioral health cases to allow the designation of the relevant follow-up resources. In this work, we develop a tool to automatically detect behavioral health cases from police public narrative reports by identifying behavioral health indicator signals. We propose a novel adaptive attention-aware fusion model for detecting behavioral health signals in sensitive police reports. Our model leverages contextual and semantic information from the reports and relevant behavioral health cues as keywords from a pre-trained attention-weighted keyword-based …

Uc-100 Indy 7 - Nutrition App, Silas E Hammond, Tho Mai, Christopher P Sarzen, Michael Ehme

C-Day Computing Showcase

This project’s objective is to develop a fully functioning and polished mobile app for keeping track of caloric intake and monitoring other aspects of one’s health. To accomplish this, we will be using React Native to develop a front end which allows users to select their goals and get active assistance in moderating what they eat. This will be done through the scanning of barcodes of any food purchased. These barcodes will then be used to query the Food Data Central API to provide the user with as much information as needed. This will include possible allergies, calorie totals, protein …

Gpr-108 Revolutionizing Reflective Learning In Higher Education: An Llm-Based Analytical Approach, Bharath Y Yadla, Mourya Teja Kunuku

C-Day Computing Showcase

This project introduces a novel LLM-based system to automate The analysis of student reflections, enhancing reflective learning in higher education. Leveraging advanced ML and NLP technologies, the system provides personalized, in-depth feedback by identifying learning outcomes and challenges. Employing the OpenAI API and LangChain framework, it offers a nuanced understanding of student learning trajectories. The methodology involves collecting data via the Minute Paper technique, enabling targeted instructional adjustments. Preliminary results indicate a significant improvement in analyzing and addressing students' educational needs.

Gpr-13 Effect Of Noise And Topologies On Multi-Photon Quantum Protocols, Nitin Jha

C-Day Computing Showcase

Quantum-augmented networks aim to use quantum phenomena to improve detection and protection against malicious actors in a classical communication network. This may include multiplexing quantum signals into classical fiber optical channels and incorporating purely quantum links alongside classical links in the network. In such hybrid networks, quantum protocols based on single photons become a bottleneck for transmission distances and data speeds, thereby reducing entire network performance. Furthermore, many of the security assumptions of the single-photon protocols do not hold up in practice because of the impossibility of manufacturing single-photon emitters. Multi-photon quantum protocols, on the other hand, are designed to …

Uc-40 Asynchronous, Ryan A Whisenhunt, Peyton T Lee, Kenneth Wardlaw, Benjamin T Haaf, Carter L Good, Cory A Ridley

C-Day Computing Showcase

Cultural assimilation is the topic on the mind of the protagonist of our game, Asynchronous. Maxwell, a diplomat from a real-time world, must adapt in a foreign land where the people live turn-based lives. We explore this topic through the lens of traditional JRPG gameplay where the player must decide when to adapt to this new culture and when to act on their own accord. By representing this idea ludically, we hope to better convey the mindset and emotional state of being an outsider to the player.

Ur-12 Multiple Myeloma: Increase Longevity And Quality Of Life Through Early Detection, Desyne Martinez

C-Day Computing Showcase

Multiple Myeloma is a rare form of bone marrow cancer where plasma cells accumulate in the blood stream attacking the skeletal system, nervous system, and kidneys of predominantly African Americans. The disease results in high mortality rates within 5 years of initial diagnosis. Multiple Myeloma has subtle symptoms of bone pain; doctors often send people to physical therapy missing the diagnosis. Current research on the International Myeloma Foundation website includes summaries of blood tests of Multiple Myeloma patients. This study seeks to identify the best blood test predictors of Stage 3, the most aggressive stage of Multiple Myeloma. The cost …

Ur-15 Analyzing Breast Cancer Histopathology Images Using Deep Neural Network Models, Je'dae Lisbon, Michael Bolnik, Sepehr Eshaghian

C-Day Computing Showcase

Our project aims to explore human tissue cells digitized by whole slide scanners for a better understanding of complex tumor microenvironments in breast cancer histopathology images, using various deep neural network models. First, we experimented with 70% percentages of tumor cells on image classification using ResNet50, VGG16, and Inception-ResNet. Second, we performed instance image segmentation using Mask-RCNN. Third, we applied two well-known explainable artificial intelligence (AI) techniques including Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP) to determine the effectiveness of the models.

Uc-43 Aletheianomous Ai: The Chat Bot Providing The Most Accurate Knowledge Information, David E Chavarro, Aimi Tran, Ethan B Byrd, Matthew J Fincher

C-Day Computing Showcase

For this project, our group aimed to create an intelligent chat bot that was accessible through the web client interface. Aletheianomous, our chat bot, was designed to provide accurate information ethically, aligned with human values. When applicable, the AI would offer the user citations to support its responses. For the back-end, a virtual machine (VM) server in AWS with access to the Graphics Processing Unit (GPU) would run three types of models: Sentence Separation Model, Search Query Extractor Model, and the Response Model. The front-end server using Microsoft Azure generates the web page for the user, exchanges chat data with …

Uc-48 Birding With Buddy, Lazare V Sawadogo, Ikhelowa E Adeji, Blake Graham, Zach Alpine, Troy C Sorrells

C-Day Computing Showcase

Birding with Buddy is an educational and entertaining immersive virtual 3D low-poly birdwatching to be experienced at the Carter Lake Nature Center to enable kids to embark on a quest to learn more about birds. Buddy the Beaver guides the user through different terrain types to identify diverse bird species with sounds. Integrate a bird identification system where players click on the binocular icon to switch to a binocular view. In this view, players can choose to Identify (multiple-choice) the correct bird, Hear the Call Again, or Consult a Field Guide. Featuring flippable pages with images and notable markings of …

Ur-89 Performance Analysis Of Post-Quantum Computing Key Encapsulation Mechanism Algorithms, Dillon J Horton, Jose Gutierrez, Tyler G Standard

C-Day Computing Showcase

Within the next twenty years or so experts predict that we will have quantum computers which will make certain kinds of encryption that we rely on ineffective and vulnerable to malicious entities. Post quantum computing (PQC) algorithms fill in that security gap that classical encryption algorithms can not. A particular category of PQC algorithms are key exchange mechanism (KEM) algorithm. The goal of these algorithms is to securely generate a shared symmetric key which can be used for encrypting future communication between the hosts. An important use case for these algorithms is in securing the Transport Layer Security protocol (TLS) …

Uc-60 Myfoodscan, Ibrahima Gueye, Brianna J Noel, Victoria O Kuswita, Je'dae Lisbon

C-Day Computing Showcase

MyFoodScan is a mobile app that enables users to scan barcodes of various food and drink items to ensure they are in compliance with their specific dietary needs. Individuals utilize this application to make a customized profile based on diet, such as vegan, vegetarian, dairy-free, allergies, etc. MyFoodScan promotes compliance with dietary limitations. The application was developed with React Native, Expo Go, Google Firebase, using the React Native Camera for barcode scanning. The OpenFoodFacts API database is used for product information. The goal of this application is to enhance awareness and safety for various dietary needs and monitor dietary restrictions.

Ur-62 Deep Learning Approach To Network Anomaly Detection, Rene P Lisasi, Jamia M Jackson

C-Day Computing Showcase

A model of network anomaly detection capable of detecting a multitude of network attacks. This model is based on the hypothesis that by studying a system’s network records for irregular patterns during system usage, network anomalies can be identified. This model contains information about the type of attacks and metrics. This model is to be used in any type of distributed environment. The general purpose of this model is to detect when an attack is or has happened using deep learning techniques to optimize the training speed, accuracy and robustness of attack detection. This is done to stop the epidemic …

Uc-75 Mineticket Discord Ticket Management Bot, Dean Rice, Arturo Martinez, Grace Shell, Solomon Thao, Palmer Brown

C-Day Computing Showcase

We made use of the discord.py python library to manage the framework of the bot, since discord relies on a RESTful API for all of its bots. This layer of abstraction allowed us to focus on the important things, such as sanitizing inputs for SQL queries and building out a large, fully customizable feature set so future adjustments are made simple and easy as changing entries within a configuration file. Our goal was to make the bot as easy to update as possible, with the hope that, should requirements change in the future, the sponsor can quickly modify existing code …

Uc-81 Drinkinator App, Maximus A Smith, Toby Mose, Grayson Payne

C-Day Computing Showcase

The "Drinkinator" app represents an innovative solution aimed at revolutionizing the beverage industry by providing users with a personalized drink recommendation system. Rooted in a motivation to diversify people's beverage selections and enhance their drinking experiences, the app facilitates exploration of a wide range of mixed drinks, wines, and beers tailored to individual preferences. Leveraging data analysis and user profiling techniques, the app offers tailored suggestions, showcasing a deep understanding of consumer behavior and taste preferences. Utilizing React Native for front-end development and JavaScript for back-end functionality, the app integrates various libraries to ensure seamless user experiences and efficient data …

Uc-71 An Environmentally Conscious Roguelike, Andrew Bland, Brendan Strawser, Adele Rousseau, Bewaji Adewunmi

C-Day Computing Showcase

This semester we have been creating an action-adventure video game based on the theme of "Saving the Environment".

Uc-73 Spacewalkers: Tilt 5, Charles D Mossor, Jacob Hundley, Ifran Ambahun, Joshua Whorton

C-Day Computing Showcase

Our project (and presentation as a whole) is to create an immersive and fun casual game experience using the Tilt 5 system. We made a tower defense game that uses the player’s input with the Tilt 5 in order to defend against enemies. By delivering a variety of enemies, levels, and towers in our game, we further enhanced the experience.

Uc-51 Difference Detection: Automated Defect Detection System For Modernized Display Units, Umer Aziz, Harrison Rosser, Urooj Arshad, Teonta N Pegues, Katherine Vu

C-Day Computing Showcase

In today's high-stakes military environments, the reliability and accuracy of software systems are paramount. Defects within these systems not only pose significant financial risks but can also endanger lives. To ensure the utmost safety and effectiveness, military systems undergo extensive testing and validation processes. However, the lifespan of these systems is far from indefinite. Environmental changes, advancements in adversarial capabilities, evolving mission requirements, and parts obsolescence necessitate continuous improvement efforts. One critical area of focus is the modernization of display units, which are vital for providing pilots with essential mission information and ensuring their safe return. The 402 Software Engineering …

Uc-56 Donation For Dummies, Jayvon L Triplett, Stephen A Mancini, Mitchell Thomason, Kendrell M Niles

C-Day Computing Showcase

Donation For Dummies is a VR game designed to help people feel more relaxed and informed when donating blood. It consists of a theater room where a video plays explaining the process as well as what to do before and after donating. For people wanting a distraction, we have an arcade where players can enjoy minesweeper, matching, or solitaire. For those wishing to relax, we have an art gallery where players can virtually walk around and look at various pieces of art. The more relaxed player that do not wish to move around the game world can instead choose to …