Physical Sciences and Mathematics Commons^™

Robustness Of Vision Language Models For Pedestrian Detection Tasks, Ostonya K. Thomas

All Theses

Autonomous vehicle (AV) systems typically employ modular systems in which discrete components handle separate tasks such as perception, computation, and path planning. While flexible, this approach allows errors to propagate and compound across the pipeline, and many AI systems offer little transparency into their internal decision-making. Such limitations are particularly concerning in safety-critical domains where failures can carry lethal consequences. Vision Language Models (VLMs) have emerged as a promising alternative because they support end-to-end implementations that bypass compounding error risks and provide natural language explanations of their outputs. Despite these advantages, prior research has demonstrated that both computer vision systems …

Taking A Deeper Look: Attributing Tonal Values Of Photolumens To Their Emulsions Using Scanning Electron Microscopy, Anna M. Moore

All Theses

This thesis examines whether tonal variation in photolumens made with historic silver gelatin photographic papers can be linked to differences in elemental composition. Photolumens are cameraless photographic images created by placing objects directly on light-sensitive paper and exposing them to ultraviolet light. Because expired and historic darkroom papers often produce unpredictable colors and tones, this study asks whether visually defined tonal groups also show measurable chemical differences.

Twenty historic paper samples were exposed, documented, and sorted into five tonal groups based on visible image characteristics. Each sample was then analyzed using scanning electron microscopy with energy dispersive X-ray spectroscopy (SEM-EDS) …

Multimodal Aerial Image-Based Ground Object Detection And Classification Using Yolo, Erik Nielsen

All Theses

Object detection in unmanned aerial vehicles (UAVs) present a unique challenge due to small object sizes, varying viewpoints, and changing environmental conditions. These challenges are exacerbated when operating during daytime and nighttime scenarios where illumination differences can heavily impact detection performance. This work is motivated by military object detection applications where the ability to reliably identify small objects such as landmines or unexploded ordnance from aerial imagery presents a critical safety need and a significant technical challenge. In this paper, we investigate object detection using both visible (RGB) and infrared (IR) imagery to improve robustness and reliability across diverse operating …

Beyond The Interface: Human Perceptions Of Generative-Ai Chatbots As Conversational Partners, Browning W.E. Blair

All Theses

Generative AI (gen-AI) chatbots are becoming embedded in everyday communicative life, yet it remains unclear whether users perceive these systems as socially reciprocative conversational partners. Therefore, this study examines how young adults understand and interact with gen-AI chatbots, focusing on perceptions of conversational partnership, anthropomorphism, politeness, discomfort, and technical understanding. Guided by the CASA framework, Media Equation Theory, and the uncanny valley hypothesis, this study employed four semi-structured, online focus groups with 15 undergraduate students and recent college graduates in the United States. Findings indicate that participants did not broadly perceive gen-AI chatbots as conversational partners in the interpersonal sense. …

Regional Assessment Of South Texas Wells Produced Water, Hunter T. Barnett

Water Resources Science and Technology Theses and Graduate Research Reports (Archived)

This study presents a regional assessment of produced water (PW) quality from oil and gas wells in South Texas, with a focus on variability and its implications for treatment and reuse. As oil and gas production continues to expand, PW waste streams will continue to grow. With a focus on the Eagle Ford Shale, understanding the chemical composition is critical for effective PW management. A total of 28 PW samples were collected from wells located in Pleasanton, Jourdanton, and Tilden, Texas. Samples were analyzed for key parameters including total dissolved solids (TDS), chloride, total hardness, and calcium. The results showed …

Ai Institute Summer Camp Webinar Summary, Dora Nguyen

Paul English Applied Artificial Intelligence (AI) Institute Publications

This report summarizes the AI Institute Summer Camp informational webinar hosted by the Paul English Applied Artificial Intelligence Institute (PEAAII) at the University of Massachusetts Boston. The webinar introduced the structure, curriculum, learning objectives, and student outcomes associated with the 2026 AI Institute Summer Camp. In addition to summarizing the webinar content, this report analyzes participant questions, engagement trends, and areas of audience interest. Findings indicate strong interest in coding accessibility, mentorship opportunities, student outcomes, research experiences, and program flexibility. The report also identifies opportunities for improving future webinar delivery, including expanded eligibility guidance, pre-camp learning resources, enhanced presentation of …

Moodify: A Mood-Based Music Recommendation System, Meghana Kagitha

Theses and Dissertations

Music has long been recognised as a powerful tool for emotional regulation, yet existing music streaming platforms often fail to align song recommendations with a user's current emotional state. Moodify is a mood-based music recommendation system designed to bridge this gap by delivering personalised playlists that reflect how a user feels in real time.

This project presents the design, development, and evaluation of Moodify, a mobile application that leverages the Circumplex Model of Emotion to capture user mood through an intuitive two-dimensional valence-arousal interface. Rather than relying on text input or manual search, users plot their emotional state directly onto …

Manned Exploration Of Satellites Of The Outer Planets: An Analysis Of Current Technologies And A Discussion Of Advancements Required, Joshua Carson Meador

Theses and Dissertations

The Solar System’s outer planets have many satellites, some of which are known to be the most likely places to find extraterrestrial life in our celestial backyard. Multiple scientific missions have been sent to glean information from these satellites, yet the possibility of a manned expedition has long been exclusive to science fiction stories. This paper intends to collect and analyze the current state of space travel technology to explore the feasibility of such a mission with modern technology and to discuss which future advancements should be the focal point for making such missions a reality. To begin, data on …

Hdra-Fusion: Hybrid Detection With Routed Architecture For Manipulation-Aware Ai Face Forgery Detection, Omar Ebeid

Theses and Dissertations

With the rapid advancements in artificial intelligence-based image generation and manipulation tools, it is extremely difficult to detect if an image is genuine or artificially crafted. Despite extensive research in this area, existing image detection systems suffer from three major problems: suboptimal cross-dataset generalization due to shortcut learning of dataset-specific patterns, unreliable probability estimates due to domain shift, particularly in cross-manipulation evaluation settings, and an inability to detect images manipulated by multiple types of manipulations within a single detection framework. To address these limitations, we propose HDRA-Fusion (Hybrid Detection with Routed Architecture), a framework built on the conclusion that different …

Quantifying Noise In Monte Carlo Simulations Of Cosmic Rays In A Shock, Abhro Rahman

Theses and Dissertations

Cosmic rays are a phenomenon known to humankind from the early 1900s, and yet today the details of their physical behavior are not fully settled. While the observed spectral fluxes of cosmic rays follow a power-law trend when plotted against particle energy, the exact mechanisms under which they get to such high energies are still under study. This thesis will undertake a subsection of that task, where the Monte Carlo simulation of particle accelerations is described in Warren (2015), and we aim to identify and quantify the noise inherent in such simulations. This document takes a long path through particle …

Hybrid Machine Learning For Zero-Day Malware Detection: An Adaptive Static-Dynamic Analysis Approach, Garrett Farmer

Theses and Dissertations

In an era of swiftly evolving cyber threats, zero-day malware continues to be one of the most challenging classes of attacks to detect and mitigate. Traditional signature-based methods often fail to detect novel malicious code, leaving institutions vulnerable to unknown exploits. This thesis proposes a machine learning (ML)-based framework that is designed to detect unknown malware variants. By combining both static and dynamic techniques, such as file structure exam ination and sandbox-based runtime analysis, this approach aims to successfully capture malicious characteristics. The proposed custom pipeline addresses the computational overhead that is associ ated with deep inspections, outlining a staged …

Bounding The Average Kissing Number, Including New Bounds For Three-Dimensional Binary Sphere Packings, Mark William Bockhaus

Theses and Dissertations

The average kissing number is defined as the supremum over all sphere packings of the value: two times the number of tangencies divided by the number balls in the packing. In this paper, we present a survey of the literature about bounding the average kissing number, beginning with the first non-trivial results, through the most up-to-date bounds. We then turn our focus to binary sphere packings: those which contain spheres of two different radii. We improve upon known bounds for the average kissing number for binary sphere packings in three-dimensions and find exact bounds for many packings.

Modeling Causal Interactions Across Brain Functional Systems For Population-Specific Disease Analysis, Alissen Moreno

Theses and Dissertations

Functional brain connectivity provides critical insight into neural mechanisms underlying neurodegenerative and affective disorders. Traditional neuroimaging studies rely on undirected or region-specific connectivity measures developed predominantly using racially homogeneous cohorts, limiting fairness and generalizability across diverse populations.

We propose a population-aware framework modeling directed causal interactions across large-scale brain functional subnetworks. Resting-state fMRI data from the HABS-HD cohort were used to construct subject-level causal connectivity matrices via ICA-LiNGAM, aggregated into interpretable system-level hyper-connectomes representing interactions among eleven canonical brain subsystems. These features trained nonlinear models for Alzheimer’s disease stage classification and trait worry prediction.

Results demonstrate that MLP models outperform …

Vision-Language Guided Quadruped Navigation With Reinforcement Learning Control, Chen Yuan Wang

Theses and Dissertations

Large Language Models and their multimodal variants, Vision-Language Models (VLMs), can interpret natural language instructions and visual context. Reinforcement Learning (RL) methods such as Proximal Policy Optimization (PPO) have been shown to successfully learn stable quadruped locomotion. This work investigates whether a VLM integrated with an RL controller can control a quadruped robot to perform instruction-following navigation to a predefined target using text instructions, egocentric vision, and proprioceptive state.

Most VLM-based robotics work directly target prediction of robot actions from multimodal inputs. This approach often depends on large amounts of expert demonstration data, generated by controllers such as trained RL …

On The Structure Of The Homotopy Lie Algebra Of Local Rings, Dawson M. Strong

Theses and Dissertations

This thesis investigates the construction and homological properties of the homotopy Lie algebra π(R) of a commutative local ring (R,m,k). Drawing upon the theoretical framework of differential graded (DG) algebras, we first establish the theory of minimal free resolutions and other standard topics in homological algebra. The core of this work details the iterative construction of the acyclic closure R⟨Y⟩ of k over R, which is achieved by the systematic adjunction of exterior and divided power variables to eliminate cycles in homology. We demonstrate that this acyclic closure serves as a minimal free resolution and provides the means to define …

Accurate Polyp Segmentation With Visual Mamba, Diego Adame

Theses and Dissertations

Medical image segmentation is a fundamental task in computer-aided diagnosis because it enables precise delineation of anatomical structures and pathological regions from clinical images. While convolutional neural networks and Transformer-based models have achieved strong performance on many medical segmentation benchmarks, CNNs struggle to model long-range dependencies and Transformers often incur high computational complexity for high-resolution medical images. Recently, state space models have emerged as an efficient alternative for dense prediction tasks due to their ability to capture long-range dependencies with linear complexity. However, existing Mamba-based segmentation models still rely on pixel-wise raster scanning that disrupts spatial locality and use simple …

Assessment Of Mississippi Landfill Capacity In Relation To Waste Generation And Land-Use Constraints, Jason C. Anderson

Master's Theses

Municipal solid waste (MSW) management presents a growing challenge in Mississippi as population trends, socioeconomic change and regional development continue to place pressure on existing landfill capacity. This thesis examines waste generation and disposal patterns from 2000 through 2022 across Mississippi counties, with projections extending to 2050. Historical landfill tonnage data was gathered and compiled from the Mississippi Department of Environmental Quality (MDEQ) and analyzed using regression models in Excel and RStudio, with forecasts generated for both in-state and out-of-state waste flow. Results highlight significant variations among landfills, including differing closure timelines, changing county service areas and notable shifts in …

Quantifying Discard Mortality Of Undersized And Ovigerous Crabs In The Gulf Of Mexico Blue Crab Fishery, Micayla Cochran

Master's Theses

Blue crabs support a valuable commercial fishery in the Gulf of Mexico. Most states require the release of undersized and ovigerous blue crabs, yet mortality of these discarded crabs is an understudied component of total mortality. The first objective of this project was to quantify discard mortality of non-target crabs using bycatch surveys across the Lake Pontchartrain–Mississippi Sound coastal system. Ovigerous crabs were most common at high salinities and temperatures, whereas undersized crab presence was inversely correlated with soak time, temperature, and the number of crabs per trap, and also varied among geographic locations. A reflex action mortality prediction assessment …

Modeling The Effects Of Low-Pressure Atmospheric Fronts On Sediment Transport Through Mississippi Sound Barrier Island Inlets, Nicholas J. Gagliano

Master's Theses

Coastal sediment dynamics in the Mississippi Sound are strongly influenced by tropical cyclones and the more frequent passage of low-pressure atmospheric fronts. While hurricanes are well recognized for reshaping barrier islands and altering sediment budgets, the cumulative role of recurrent fronts remains poorly quantified. This thesis investigates the impacts of six low-pressure atmospheric fronts (2015–2017) on sediment flux through six barrier island inlets in the Mississippi Sound.

A high-resolution application of the Regional Ocean Modeling System with the Community Sediment Transport Modeling System was developed to simulate tidal circulation, wind-driven currents, and sediment dynamics. Waves were excluded from the simulations. …

The Impact Of Community On Professional Identity In Computer Science Education, Ian A. Kollipara

School of Computing: Dissertations, Theses, and Student Research

This thesis explores the application of Communities of Practice (CoPs) in Computer Science Education. The work consists of two qualitative studies examining related but distinct populations: (1) K–12 CS teachers and (2) undergraduate CS students. The first study presents a retrospective analysis of conneCTION, an online CoP for K–12 CS educators, identifying strengths, weaknesses, and design considerations that inform future platform development. The second study investigates how participation in a CoP can mitigate negative and exclusionary stereotypes in CS. This study was conducted in an under-explored context: a small, private, religious, Midwestern university, and examines an existing community, the Programming …

A Webcam Eye Tracking Infrastructure For Software Engineering Tasks, Zachary M. Kozak

School of Computing: Dissertations, Theses, and Student Research

Performing eye tracking utilizing commodity webcams has been explored for over a decade, but limited camera quality and sensitivity to head movements have hindered its adoption in research settings. Recent advances in consumer-grade webcams and machine learning methods present an opportunity to improve the accuracy of webcam eye tracking and extend the feasibility of studies beyond controlled laboratory environments.

Current popular webcam eye tracking methods restrict implementations to the browser and rely on continuous user interactions for calibration, limiting the kinds of studies that can be conducted. This thesis presents a feature-based gaze prediction system that incorporates eye geometry and …

Detecting Doubt In Reflective Learning: A Learning Analytics Study With Large And Small Language Models, Eng Lieh Ouh, Kar Way Tan, Siaw Ling Lo, Yuhao Zhang

Research Collection School Of Computing and Information Systems

Reflective learning enhances understanding, especially when instructors promptly address difficulties raised in student reflections. Automated doubt detection can reduce time for instructors, yet existing classification approaches take substantial time for manual annotation and model training. This paper investigates whether large and small language models (LLMs, SLMs) can automate doubt detection without time-consuming training. Using a dataset of anonymized student reflections, we evaluate zeroshot, few-shot prompting, and multi-step reasoning against prior supervised classification baselines. We show that LLMs (GPT-4o, Claude-4, Gemini-2.5) surpass earlier F1 scores without prompting, while prompting further improves their performance. However, using proprietary LLMs can raise cost and …

Modeling Water Quality And Cyanobacteria Blooms In St. Lucie Estuary, Florida, Mohmmad Masudur Rahman

Electronic Theses and Dissertations 2020 - Present

The St. Lucie Estuary (SLE) on Florida’s east coast is vital for diverse aquatic life and provides essential services to local communities. However, the estuary’s health is threatened by water quality deterioration due to nutrient-driven phytoplankton blooms, particularly cyanobacteria, which have increased in frequency over recent decades. These blooms may worsen water quality by reducing dissolved oxygen, altering pH, and increasing turbidity. Moreover, some phytoplankton species, including Microcystis aeruginosa, a freshwater cyanobacteria species, produce harmful toxins, posing risks to both marine aquatic life and human health in this area. Primary nutrient sources in this estuary include watershed freshwater discharges, …

A Generative Ai Method For Minority Class Handling In Anomaly Detection With Drift And Explainability Analysis, Kelvin J. Mwiga, Mussa A. Dida, Ahmad Mohsin, Iqbal H. Sarker

Research outputs 2022 to 2026

Artificial Intelligence, particularly machine learning (ML) algorithms, plays a crucial role in detecting cyberattacks, including anomalies and intrusions. However, machine learning models trained on imbalanced cybersecurity datasets often struggle to accurately detect minority data instances and potential threats, thereby weakening overall system security. Despite extensive research, a persistent challenge is the inadequate explanation for model predictions concerning minority data classes. This study aims to address these limitations by developing a generative AI-based approach to manage minority classes in anomaly detection, incorporating concept drift handling and explainability analysis. We introduce an over-sampling technique, CGGReaT, designed to enhance the presence of minority …

Public Pool Usage As Adaptation Against Urban Heat, Stefan Borsky, Eric Fesselmeyer

Research Collection College of Integrative Studies

This paper examines the relationship between urban heat and outdoor public pool usage. Using attendance data from all 53 outdoor public pools in New York City, we analyze nonlinear effects of heat on pool usage across socioeconomic contexts. Pool attendance rises sharply with heat, especially in low-income neighborhoods where alternative coping options are likely limited. We also find that public pools reduce heat-related emergency medical service calls. Our findings highlight the need for equitable investment in blue infrastructure to enhance urban climate resilience and demonstrate how this type of adaptive infrastructure can play a critical role in managing urban heat.

Optimisation Of Photosensitive Recording Materials For Broadband Holographic Optical Elements, Michael Murray

Doctoral

The introduction of broadband (white) LED outdoor lighting has led to significant energy savings. However, this has come at the cost of increased light pollution which has negative impacts both on ecological systems and human health. This light pollution is largely the result of the lack of control measures for the directionality of the light emitted by outdoor LED lighting. The lack of directionality also results in higher energy consumption in order to compensate for the light scattered to the atmosphere and sufficiently illuminate the target area. In this thesis holographic optical elements (HOEs) are proposed as a complementary technology …

At The Intersection Of Science And Sustainability: A Qualitative Study Of Food Scientists' Personal And Professional Perspectives, Srushti Parikh

Theses, Dissertations and Culminating Projects

Sustainable food systems require not only technological innovation but a more profound understanding of the professionals involved in the field. Even though the topic of sustainability is currently gaining importance throughout the food industry, the real expertise of food scientists is under-researched. PURPOSE: The purpose of this study is to explore food scientists' perspectives on sustainability, how these perceptions influence the way they pursue their careers, and how they view their impact in the larger sustainability agenda of the food industry. METHODS AND MATERIALS: This study captured detailed insights of 22 food scientists’ perspectives through qualitative methods. Food scientists in …

Computational And Molecular Modeling Of Asphaltene Aggregation And The Effect Of Radicals And Nonradicals, Lyla Salyani

Theses, Dissertations and Culminating Projects

Asphaltenes are the heaviest component of crude oil consisting of a wide range of polyaromatic compounds with molar mass in the range of 500-800 g/mol. Asphaltenes tend to aggregate and form nanoclusters which lead to clogged pipelines. Understanding asphaltene aggregation has been a long-standing effort of industry and academia. Such systems are a typical example of systems studied to understand the impact of non-covalent interactions that drive the aggregation. Interactions that can be found to contribute to the stability of these aggregates can be π-π stacking, dispersion forces, and pancake stacking. A small fraction, 3%-4%, of the asphaltenes exist as …

Analysis Of Collective Behavior In Living And Nonliving Systems, Kaitlyn Cohan

Theses, Dissertations and Culminating Projects

This thesis aims at understanding the phenomenon of of self-organization in complex dissipative systems, living and nonliving. Dissipative systems are characterized by their search for energy, interactions with their surroundings and the production of entropy, all of which result in the creation of stable structures or patterns, which persist as long as the initial environmental conditions are maintained. The two specific models that we chose to study here are (a) Futbol (or Soccer) and (b) a chemical system involving free-floating menthol crystals floating on a fluid surface to represent nonliving systems. Using experiments and mathematical models, we will try to …

Investigation Of Curing And Degradation Mechanisms In Lead White Oil Paint Systems: Impact Of Methyl Linoleate On Paint Matrix Formation And Solvent Extractability, Andrea Serrano Trujillo

Theses, Dissertations and Culminating Projects

Oil-based paints composed of drying oils and lead-containing pigments undergo complex chemical transformations during curing that influence long-term stability and degradation. Despite centuries of use, the molecular mechanisms governing oxidative polymerization and additive incorporation in lead white oil paint systems remain incompletely understood. This study investigates the role of methyl linoleate, a monoester analog of linoleic acid, in the curing and degradation pathways of lead carbonate and linseed oil paint films. A deep focus was placed on determining whether methyl linoleate becomes chemically integrated into the developing polymeric network or remains as an extractable and unbound component, as this distinction …