Computer Sciences Commons^™

Generative Artificial Intelligence Dependency: Scale Development, Validation, And Its Motivational, Behavioral, And Psychological Correlates, Adalia Yin Hui Goh

Dissertations and Theses Collection (Open Access)

The growing integration of generative artificial intelligence (AI) into everyday life has raised questions about its potential psychological and behavioral consequences. The present research develops and validates the Generative AI Dependency Scale, a multidimensional tool developed to assess individual differences in dependency on generative AI systems. Across six studies involving 1,223 participants from the United States and Singapore, the Generative AI Dependency Scale demonstrated strong psychometric properties, including a stable three-factor structure (cognitive preoccupation, negative consequences, withdrawal) and good test-retest reliability (ICC = .85). Confirmatory factor analysis supported a higher-order dependency construct, and scalar measurement invariance was established across sex …

Cuegen: Customizing Sensor Captions For Neon Bending Tutorials, Gunnika Kapoor

2025 Spring Honors Capstone Projects - Archive

Methods of knowledge transfer that rely primarily on visual and/or auditory formats do not effectively convey context-specific or implicit skills, known as tacit skills. This limits knowledge transfer. In this work, the use of customizable pitch captions and spatial audio vibration captions is proposed to aid in conveying this tacit knowledge for neon glass bending video tutorials. Such a system is designed to provide users with greater control and support, which may maximize the information they obtain from, improve the autonomy they have with, and experience they have with a learning tool. As such, a system interface was developed that …

Controlling A Mobile Inverted Pendulum And Optimizing Leaning Angle To Apply Force Using Reinforcement Learning, Aryan Mediratta

2025 Spring Honors Capstone Projects - Archive

Reinforcement Learning is a Machine Learning paradigm that involves simulating learning through rewards and penalties in intelligent systems. This technique is often employed in robotics when traditional control methods are insufficient or when human intuition does not provide a good solution on how to control robot systems, This project involves training a Segway-style Mobile Inverted Pendulum (MIP) robot to balance and push a box forward. The BeagleBone Blue board is used that includes a built-in Inertial Measurement Unit (IMU) and encoder ports. These sensors enable the system to measure its current state. The goal is to find the optimal leaning …

Generating Motivational Messages For Behavior Change: Encouraging Users To Be More Physically Active, Hananeel Pankaj

2025 Spring Honors Capstone Projects - Archive

High levels of sedentary lifestyles can cause adverse effects in individuals’ health. This has prompted researchers to analyze ways to increase physical activity, including the use of Large Language Models (LLMs) to generate motivational messages. While research has found LLMs to be feasible for this task, the findings are limited in availability and scope given that the research focuses on a conversational, chatbot setting—which is not ideal in the real world. This research assesses OpenAI’s GPT-4o mini’s (one of several models powering ChatGPT) ability to tailor messages towards a user. This is done by passing user health data to the …

Navigation Of Unmanned Aerial Vehicle Using Computer Vision In Raytheon Drone Competition, Joseph R. Pavlik Iii

2025 Spring Honors Capstone Projects - Archive

A major problem with using GPS to navigate an unmanned aerial vehicle is that GPS signals do not accurately work while inside a building. This work presents the usage of the Simultaneous Localization and Mapping library, ORB-SLAM2, in C++ to solve this issue. By using the camera attached to the unmanned aerial vehicle, a map of the area covered by the drone will be created, and landmarks in area will be utilized to navigate throughout the interior of the building without the GPS. Based on previous studies, this navigation method should be viable. Preliminary tests show that this method will …

Usage Of Natural Language Processing And Deep-Learning Techniques On Thematic Apperception Tests To Predict Big Five Personality Traits, Blayten Jones

Electrical Engineering and Computer Science Undergraduate Honors Theses

The usage of personality as a method of behavioral prediction and outcomes of success has grown considerably over the last few decades. This project explores predicting user personality profiles via the Big Five personality index through the integration of advanced natural language processing techniques as well as neural networks. Using a dataset provided by Dr. James W. Pennebaker, participants analyze an image—formally referred to as a thematic apperception test—and write a thorough paragraph describing the details. This free-form text, along with their personality test results, is captured in a structured dataset. Many deep-learning and machine learning models have been used …

A Novel Approach To Attention-Based Models In Image Completion: Weighted Spatial-Attention Using Radial Distance, Tyler D. Kuper

Electrical Engineering and Computer Science Undergraduate Honors Theses

Humans infer missing visual information by focusing on spatial relationships in the context of their surroundings. Machine learning aims to replicate this skill through image completion, a fundamental task in current computer vision research. While advances in self-attention layers have recently enhanced generative machine learning models for text, these mechanisms still currently lack the capability to handle sparse image completion efficiently. We introduce a distance-based attention mechanism that uses radial-based weights to efficiently reconstruct an image. We compare this attention mechanism with self-attention and a fully connected network on an image completion task using the MNIST dataset. Our results show …

Defend: A 1m Dataset Foundation Model For Tobacco Analysis, Matthew J. Shepard

Electrical Engineering and Computer Science Undergraduate Honors Theses

The study of tobacco imagery and marketing is a complex challenge that involves extremely large datasets. It also demands a detailed analysis of the so- cial context and specific types of tobacco being marketed. Despite major recent advances in computer vision and foundation model technology, this still poses a substantial challenge. Through the DEFEND model, we aspire to address these obstacles by integrating features such as multimodal learning, hierarchical under- standing, and feature extraction to develop a foundation model designed to handle the unique challenges of tobacco image analysis. One of the core elements of DE- FEND is the Tobacco …

Multimodal Learning For Visual Perception And Robotic Action, Taisei Hanyu

Electrical Engineering and Computer Science Undergraduate Honors Theses

Multimodal learning aims to weave information from images, language, depth, and other sensors into one coherent representation, much as people naturally combine sight, speech, and sound. Progress toward that goal is slowed by three gaps: vision encoders that cannot balance crisp object boundaries with global context, 3-D semantic maps that are computationally prohibitive for real-time, open-vocabulary queries, and vision-language-action pipelines that depend on large token pools with weak relational grounding.

We first introduce AerialFormer, a lightweight hybrid of convolutional and Transformer layers that captures long-range structure without sacrificing fine detail. On the large-scale iSAID benchmark it reaches 69.3% mean IoU, …

Diversity-Augmented Training For Generalizable Ai Agents, Wenjun Li

Dissertations and Theses Collection (Open Access)

Deep Reinforcement Learning (RL) has achieved remarkable success over the past decade, from superhuman performance in video games to real-world applications like robotics. However, RL models often lack generalization, making them unreliable when deployed in unfamiliar scenarios. For example, robots must adapt to varying terrains with different slopes and obstacles, yet standard RL training does not explicitly promote such adaptability. While various methods have been proposed to enhance RL robustness, achieving reliable generalization remains an open challenge.

This dissertation focuses on improving the generalization capability of agents in three major settings: infinite horizon RL agents, finite horizon RL agents, and …

Deepfakes On Trial: Developing A High-Accuracy, Court-Admissible Ai Pipeline For Deepfake Detection In Corporate Fraud Litigation, Aiden J. Green

Honors College Theses

As deepfake technology advances, cybercriminals are increasingly using AI-generated videos and audios to impersonate executives and carry out sophisticated CEO fraud schemes. These synthetic forgeries target human trust and corporate communication systems, creating an urgent need for forensic tools capable of authenticating digital evidence with legal accuracy. This thesis presents a forensic-grade AI deepfake detection pipeline designed for this purpose, emphasizing courtroom admissibility, reproducibility, and evidentiary integrity. Built entirely with free, opensource tools, the framework combines metadata analysis, AI-powered spectrogram analysis, neural artifact detection, and facial manipulation recognition into a transparent workflow that accurately identifies synthetic media. It was trained …

Enhancing Sub-Optimal Trajectory Stitching: Spatial Composition Rvs For Offline Rl, Sheng Zang, Zhiguang Cao, Bo An, Senthilnath Jayavelu, Xiaoli Li

Research Collection School Of Computing and Information Systems

Reinforcement learning via supervised learning (RvS) has been known as a burgeoning paradigm for offline reinforcement learning (RL). While return-conditioned RvS (RvS-R) predominates across a wide range of datasets pertaining to the offline RL tasks, recent findings suggest that goal-conditioned RvS (RvS-G) outperforms in specific sub-optimal datasets where trajectory stitching is crucial for achieving optimal performance. However, the underlying reasons for this superiority remain insufficiently explored. In this paper, employing didactic experiments and theoretical analysis, we reveal that the proficiency of RvS-G in stitching trajectories arises from its adeptness in generalizing to unknown goals during evaluation. Building on this insight, …

Worldcuisines: A Massive-Scale Benchmark For Multilingual And Multicultural Visual Question Answering On Global Cuisines, Genta Indra Winata, Et. Al

Research Collection School Of Computing and Information Systems

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside …

From The Bleachers To The Browser: Redefining Fan Experience With Ar And Ai In Smaller Teams, Jennifer Lee Wunder

Theses

This project documents the creation and deployment of HootyHoo, an interactive augmented reality (AR) mascot experience designed for the O’Fallon Hoots, a small-scale collegiate summer baseball team. Built using accessible, open-source tools such as WebXR, Mixamo, Meshy, Botpress, Claude and ChatGPT, this prototype merges AI-driven conversation with animated 3D avatar interaction—redefining how fans engage with sports organizations digitally. Unlike enterprise-level applications used by professional franchises, HootyHoo is entirely browser-based, eliminating the need for app downloads and ensuring maximum accessibility for families and new fans with smartphones. The experience centers on Hooty, the team mascot, who answers questions about baseball and …

Implementation Of Residual Tandem Neural Networks For Photonic Inverse Design, Ponthea A. Zahraii

Electrical Engineering and Computer Science (MS) Theses

Deep-learning approaches can greatly benefit the modeling and design of nanophotonic and optical structures. Traditional full-wave simulations are time and resource-intensive, which can act as a bottleneck in photonic design. On the other hand, deep-learning approaches for designing the response of nanophotonic geometries can be computationally inexpensive and produce accurate and efficient results. In this project, we specifically investigate the case of optical forces near meta-structures. We propose using an inverse design approach with residual blocks to account for the deep nature of this architecture and inherently address the non-uniqueness problem. A tandem approach, which consists of two interconnected models, …

Computer Vision In Soccer: Yolov11 Analytics Engine For Quantifying Game Strategy, Connor S. Maurer

Data Science Undergraduate Honors Theses

Single-shot object detection capabilities significantly reduce computational overhead for real-time computer vision in sports analytics at 60 FPS. YOLO11’s lightweight CNN gives promising accuracy while meeting the low-latency demand of dynamic soccer matches. As data-driven approaches take over the sport of soccer, efficient player tracking systems become critical for informing coach’s strategies. I prototype the ETL (Extract, Transform, Load) process of data collected from a single- shot detection program and evaluate its viability for estimating player fatigue. YOLO11 detects players, the ball, and other characteristics, with the output transformed by homography to estimate the positions in the real world. These …

Reinforcement Learning, Modeling Markets, And Professional Basketball Free Agency, Jacob Cohn

Computational and Data Sciences (PhD) Dissertations

This dissertation presents a reinforcement learning-based approach to modeling and optimizing decision-making in professional basketball free agency and related economic environments. A Markov Decision Process (MDP) framework is introduced to capture the strategic interactions of NBA teams bidding for free agents under budgetary and roster constraints. To address computational scalability challenges, a reinforcement learning (RL) environment is developed, leveraging Proximal Policy Optimization (PPO) to approximate optimal policies for team decision-making.

Empirical results demonstrate that the RL agent successfully learns strategic bidding behavior that aligns with dynamic programming benchmarks in simplified settings while scaling effectively to larger, intractable environments. The study …

Artificial Intelligence Through Young Eyes: A Study Of Students’ Perspectives And Experiences With Artificial Intelligence In Education, Chad Preston Salyer

Ed.D. Dissertations

Artificial intelligence was an emergent and powerful new force in education. The public release of ChatGPT 3.0 in 2022 transformed learning for many students. This phenomenological qualitative study sought to record and analyze student’s perspectives on the influence of artificial intelligence on their learning routines. This study collected data through surveys and interviews with undergraduate students, analyzing patterns of artificial intelligence usage, perceived benefits, and challenges. The findings revealed that most students used artificial intelligence as a primary learning tool and that those students viewed artificial intelligence as beneficial for personalized learning and skill development. However, concerns about over-reliance on …

Towards Mitigation Of The Light Network Load Performance Penalty Of The Network Link Outlier Factor (Nlof), Jaime Merin Guzman

Open Access Theses & Dissertations

Detecting and localizing faults in communication networks is critical to maintaining reliable and efficient network operations. The Network Link Outlier Factor with Most Likely Link (NLOF: MLL) algorithm has demonstrated its potential to automate this task but suffers from significant performance degradation under low network load conditions, where limited network flow data reduces its ability to localize faults. This thesis proposes and evaluates the performance of a synthetic traffic generation algorithm to be used with NLOF:MLL. This algorithm strategically injects synthetic flows that supplement the insufficient real network flows, thereby improving NLOF:MLL's performance under low-load conditions. Specifically, we select network …

Machine Learning And Protein Engineering Approaches To Understanding Kinesin-5 Activity, Jason Eden Sanchez

Open Access Theses & Dissertations

Cancer is a term describing a collection of diseases that result in uncontrolled cell growth. Cancer has manifold etiologies and underlying cancers are rouge biochemical pathways involving many different proteins. In the current work, two approaches are used to enhance knowledge of kinesin-5, a potential cancer target involved in cell division. Kinesin-5 promotes cell division by cross-linking and separating microtubules in dividing cells. The first approach uses machine learning (ML) to identify small molecule inhibitors for kinesin-5. Though decades of research have uncovered classes of small-molecules which inhibit kinesin-5 in vitro and in vivo, no candidates have reached phase III …

Strengthening The Bonds Between Us: An Empirical Investigation Of Morale In Human-Ai Teams And The Socially Supportive Ai Teammates Who Empower It, Rohit Mallick

All Dissertations

This dissertation investigates how artificial intelligence (AI) can be designed to improve the collective emotion within a team. A team's collective emotion, or morale, describes how motivated, optimistic, and enthusiastic the group is in accomplishing its goals. We conducted four studies that compared different social support strategies that AI teammates can provide to the team. Study 1A found that AI teammates who communicate with emotions can better motivate human team members and promote awareness of team dynamics and environmental changes. Study 1B found that human teammates become more motivated and happier when their AI teammates express joy and are close …

Automated Solar Pv Analysis With Machine Learning And Computer Vision: Dataset And Methodology, Malachi Massey

Electrical Engineering and Computer Science Undergraduate Honors Theses

Solar power is a vital resource in a world being threatened with the ever-evolving impacts of climate change. A combination of new and developing technologies have allowed solar photovoltaic installation to increase at an exponential rate. With this rapid and unprecedented growth comes the task of maintaining tens of thousands of square miles of solar photovoltaic panels. Manually observing and testing solar PV panels for defects or obstructions is costly and time-consuming, distracting valuable resources from the continued installation of new units. This research aims to (i) firstly, introduce a novel dataset on solar PV obstruction, named De-Solar dataset; (ii) …

Toward Robust Semantic Segmentation In Levee Infrastructure Monitoring: Enhancing Accuracy With High-Fidelity Synthetic Data And Ensemble Learning, Padam Jung Thapa

LSU New Orleans Theses and Dissertations

Abstract: Levees serve as critical flood protection structures, but failures due to inadequate maintenance and extreme water pressures have led to devastating events such as Hurricane Katrina. Manual inspections are slow, labor-intensive, and prone to human error, necessitating the development of automated solutions. This study proposes an AI-driven framework for levee inspection utilizing deep learning-based semantic segmentation to detect rutting and enhance the identification of sand boils. To address dataset limitations, high-fidelity synthetic images are generated using DreamBooth for fine-tuning, while ControlNet adds structural constraints to enhance realism and consistency. A semi-automatic convex hull annotation technique enhances labeling efficiency, and …

Animal Burrow Detection In Levee Systems Using Res-Net 34, Christopher D. Moore

LSU New Orleans Theses and Dissertations

Animal burrow detection is a time-consuming and costly task for levee inspectors. Annual budgets run up to approximately $16 million per state. The inspectors typically will have to travel to the inspection sites using government-assigned transportation. Depending on the distance to the site, it may take minutes or hours to arrive before any productive inspections occur. Once at the site, the inspectors were subject to human error, overgrown foliage, severe weather, or prohibitive landscaping that would make any human inspection impossible. Also, animal burrows could be small enough or overgrown, so the human inspector misses the problem areas. We aimed …

Phoneme Recognition For Pronunciation Improvement, Matthew Heywood

Theses/Capstones/Creative Projects

This project aims to improve English pronunciation by investigating speech errors and developing a tool to provide precise feedback. The study focuses on creating a new pronunciation tool that offers localized feedback, identifies specific errors, and suggests corrective measures. By addressing the shortcomings of current methods, this research seeks to enhance pronunciation refinement.

Utilizing cutting-edge technology, the tool leverages speech-to-phoneme AI models and modified lazy string matching algorithms to compare the user's spoken input with the intended pronunciation. This allows for a detailed analysis of discrepancies, providing users actionable insights into their phonetic errors. The speech-to-phoneme AI models mark a …

Comparative Analysis Of Classical And Machine Learning Pathfinding Approaches, Miguel Gapud

Honors Theses

Pathfinding is an essential task for any autonomous robot. Graph-based classical pathfinding algorithms and machine learning approaches have both been used for this end, but they are often not compared against each other. An implementation of end-to-end (E2E) pathfinding using Proximal Policy Optimization (PPO) and an Alexnet architecture is compared against an implementation of Hybrid A*. A digital twin in Unity3D is used as the testing environment with the Clearpath Dingo as the pathfinding robot. In machine learning, the robot is controlled using PPO through ROS-Noetic with a camera as its sensor. Hybrid A* and its controls are implemented directly …

Adversarial Machine Learning: Methods For Attacks And Defenses, Minh Hao Van

Graduate Theses and Dissertations

With the rapid development of machine learning in real-world applications, enhancing security plays an important role. Adversarial machine learning focuses on understanding malicious actions from attackers and developing defensive techniques against such threats when deploying machine learning systems. An attack can occur in different scenarios, such as poisoning attacks during the training stage and evasion attacks during the testing stage. Although extensive research has explored defense strategies to deal with these harmful attacks, there is a need for further research into areas such as how to counteract malicious attacks with healthy noise or how to train an adaptive defense against …

Quasipseudometric Value Functions With Dense Rewards, Khadichabonu Valieva

Honors Theses

Goal-conditioned reinforcement learning (GCRL) serves as an extension of reinforce- ment learning (RL) that focuses on goals that can be adjusted, making it useful for many applications, especially in complex robotics tasks. Recent research has established that the optimal value function of GCRL, denoted as Q∗(s, a, g), has a quasipseudometric structure. This finding has led to the development of targeted neural architectures that respect such a structure. However, prior analyses have predominantly focused on sparse reward settings, which are known to increase challenges related to sample complexity. In this work, I with the guidance of my advisor show that …

Cache-Augmented Generation In Rag Pipelines: Fast And Memory-Efficient Approach To Multi-Agent Knowledge Query Systems, Yaju Gopal Shrestha

Honors Theses

This thesis presents an implementation and evaluation of Cache-Augmented Generation (CAG) for knowledge query systems, building upon the approach introduced by Chan et al. (2024). Traditional Retrieval-Augmented Generation (RAG) systems (Lewis et al., 2020) face challenges including high latency, excessive memory usage, and complex infrastructure requirements. By implementing a cache-augmented architecture that preloads relevant knowledge and eliminates real-time retrieval, our approach significantly improves response time while reducing resource requirements. The research demonstrates the effectiveness of CAG through a comprehensive implementation for The University of Southern Mississippi's chatbot system, achieving a 49.02% improvement in response time compared to traditional RAG approaches. …

What References Are Chatgpt, Gemini, Copilot, And Perplexity Providing For Consumer Health Questions?, Scott Johnson, Catherine Johnson, Ivan Portillo

Library Presentations, Posters, and Audiovisual Materials

Background

With the growing popularity of generative artificial intelligence (AI) models such as ChatGPT, consumers may turn to these tools to easily seek health information. To our knowledge, no study has analyzed the references provided by multiple models for consumer health questions.

Objective

We aimed to analyze the references provided by ChatGPT, Gemini, Copilot, and Perplexity for consumer health questions in order to determine the most frequently appearing references.

Methods

AI generative models ChatGPT 4.0, Google Gemini, Microsoft Copilot, and Perplexity were each asked 30 consumer health questions and prompted to provide the corresponding references. The references were recorded.

The …