Physical Sciences and Mathematics Commons^™

On The Deployment Of Ris-Mounted Uav Networks, Anupam Mondal

Master’s Dissertations

Reconfigurable intelligent surfaces (RIS) enable smart wireless environments by dynamically controlling signal propagation to enhance communication and localization. Unmanned aerial vehicles (UAVs) can act as flying base stations and thus, improve system performance by avoiding signal blockages. In this paper, we propose a gradient ascent and coordinate search based method to determine the optimal location for a system that consists of a UAV and a RIS, where the UAV serves cellular users (CUs) and the RIS serves device-to-device (D2D) pairs. In particular, by optimizing the net throughput for both the D2D pairs and the CUs, the suggested method establishes the …

Modeling And Verification Of Sigma Delta Neural Networks, Sirshendu Das

Master’s Dissertations

In the context of modern day embedded safety-critical systems and low-resource edge devices in particular, Sigma-Delta Neural Networks (SDNNs) offer a promising alternative to traditional Artificial Neural Networks (ANNs) by leveraging eventdriven, sparse computations inspired by biological neural processing. This energyefficient paradigm makes SDNNs well-suited for neuromorphic hardware and realtime applications, particularly in scenarios with temporal redundancy, such as video processing. However, as neural networks become integral to safety-critical systems, ensuring their robustness against adversarial perturbations is an absolute necessity. In this work, we propose an end-to-end framework for formal modeling and verification of SDNNs using Satisfiability Modulo Theory (SMT). …

Addressing Class Imbalance Problems To Improve Animal Detection Through Aerial Image Data, Suryang Koushal

Master’s Dissertations

Monitoring animal populations in wildlife reserves is essential for conservation, especially for endangered species, but manual censuses are costly, risky, and logistically challenging due to vast, inaccessible terrains. Unmanned Aerial Vehicles (UAVs) with digital cameras provide a safer, scalable solution for collecting aerial imagery to estimate animal populations. However, semi-automated processing of these images faces significant challenges due to class imbalance in datasets, including foreground-background disparities, where background terrain dominates over sparse animal instances, and inter-class imbalances from uneven species representation and varied visual appearances (e.g., species, sizes, fur patterns) against diverse backgrounds like deserts or forests. These imbalances hinder …

Energy-Efficient Uav Movement And User-Uav Association In Multi-Uav Networks, Subhadip Ghosh

Master’s Dissertations

These days, unmanned aerial vehicle (UAV)-based millimeter wave (mmWave) communication systems have drawn a lot of attention due to the increasing demand for faster data rates. Given the susceptibility of mmWave signals to obstacles and high propagation loss of mmWaves, ensuring line-of-sight (LoS) connectivity is critical for maintaining robust and efficient communication. Furthermore, UAVs have limited power resource and limited capacity in terms of number of users it can serve. Most significantly di↵erent users have di↵erent delay requirements and they keep moving while interacting with the UAVs. In this paper, first, we have provided an efficient solution for the optimal …

Enhancing Expressive Power Of Graph Neural Networks Using Geometric Transformations, Suranjan Dey

Master’s Dissertations

Graph Neural Networks (GNNs) are highly effective in many real-world tasks, such as molecular property prediction, modeling protein structures, analyzing user-item relationships, and making link predictions. What sets them apart is their ability to learn meaningful representations by capturing not just the features of individual nodes, but also the overall structure of the graph they belong to. This expressive strength allows GNNs to model complex relationships more accurately. In this work, we take a step further by introducing geometric transformations aimed at improving how GNNs handle spatial information. In particular, we focus on angular aggregation methods that maintain rotational consistency, …

Application Of Deep Learning In Analysis Of Stellar Spectra, Piyush Yayati

Master’s Dissertations

In recent years, the analysis of high-resolution stellar spectra has become increasingly important for estimating key stellar parameters such as effective temperature (Teff ), surface gravity (log g), metallicity ([M/H]), and rotational velocity (v sin i). Traditional methods often rely on manual calibration or spectrum synthesis, which can be time-consuming and error-prone, especially for M dwarfs whose spectra are dense with molecular features. In this study, we investigate the use of convolutional neural networks (CNNs) to automate the estimation of stellar parameters using synthetic and observed data.We adopt a StarNet-like CNN architecture trained on synthetic spectra generated from the PHOENIX-ACES …

Causal Explanations In Deep Learning Systems, Dhruv Vansraj Rathore

Master’s Dissertations

Deep learning models often deliver high predictive accuracy; however, their lack of interpretability can hinder their adoption in critical fields such as healthcare and finance. This thesis explores the concept of Intrinsic Causal Contribution (ICC), a novel method for explaining neural network predictions by quantifying each input feature’s intrinsic causal influence on the output, independent of correlated effects. ICC models the network as a Structural Causal Model and employs Causal Normalizing Flows to handle complex dependencies, with efficient estimation via the Jansen Estimator. Analysis on both synthetic and real data sets provides evidence that ICC produces faithful, interpretable attributions, often …

Universally Consistent Hyperbolic Deep Neural Networks, Sagar Ghosh

Master’s Dissertations

The ubiquitous pertinence of Deep Neural Networks has made it pivotal in modern Computer Science Applications, ranging from Computer Vision to Pattern Recognition and Machine Translation. Although these deep architectures are primarily based on Euclidean Spaces, Hyperbolic Neural Networks (HNN) gained traction in recent times to tackle more complex non-Euclidean data having inherent hierarchical structures. These HNN architectures have shown commendable improvements in test results on tree or graph-like data by exploiting the inherent exponential metric distances of hyperbolic spaces, making them more suitable to embed non-Euclidean data. Although HNNs surpass their conventional Euclidean counterparts by commendable margins, little to …

Cutting Through The Infodemic Efficiently: News Claims Surveillance And Llm-Based Lightweight Fact Verification, Xuan Zhang

Dissertations and Theses Collection (Open Access)

In the context of the current infodemic, the rapid spread of misinformation poses a severe threat to social stability and public health. Recently, the rise of deep learning technologies has offered the potential for accelerating the development of automated misinformation detection and verification. However, current technological capabilities and computational resources often prove inadequate for the exhaustive scrutiny required, rendering the enhancement of processing efficiency a critical imperative. Given the vast amount of data on the internet, current technology and computational power often fall short in timely and accurate scrutiny of each piece of information, making the improvement of processing efficiency …

Interactive Generative Modeling: A Pathway For Improved Simulation And Decision Making, Changyu Chen

Dissertations and Theses Collection (Open Access)

This dissertation presents Interactive Generative Modeling (IGM), a unified perspective that integrates interactive paradigm and generative modeling to advance the development of general-purpose intelligent systems. IGM is motivated by the observation that while reinforcement learning (RL) has mastered a wide range of complex simulated tasks, it struggles to generalize in high-dimensional, open-ended tasks. In contrast, generative models excel in such settings due to their expressivity and their ability to serve as powerful priors (e.g., LLMs pretrained on massive corpora). By bridging these two paradigms, IGM offers a promising path forward.

The first direction explored in this dissertation is IGM for …

Learning And Optimization Under Human-Centric Considerations, Qian Shao

Dissertations and Theses Collection (Open Access)

This dissertation investigates learning and optimization problems shaped by humancentric considerations, such as preferences, demonstrations, behavioral patterns, and resource constraints. As real-world decision-making increasingly involves interaction with human agents, data, and limitations, modeling these factors becomes critical for building practical, adaptive, and robust systems.

The research spans four domains. First, we study preference-aware delivery routing by learning implicit practitioner preferences and incorporating them into a hierarchical route optimization framework. Second, we develop imitation learning methods for cost-constrained settings, enabling agents to mimic expert behavior while respecting safety and resource limitations. Third,we explore early rumor detection in data-limited environments, integrating large …

Final Silver Bow Creek Conservation Area (Sbcca) Butte Reduction Works (Brw) Air Monitoring For Interim Demolition Activities – Phase I Data Summary Report (Dsr), Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Revised Draft Final Bpsou Unreclaimed Sites: Ur-05 Remedial Action Work Plan (Rawp), Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Revised Draft Final Butte Priority Soils Operable Unit (Bpsou) Unreclaimed Sites: Ur-03 Site Remedial Action Work Plan (Rawp), Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Residential Factors Associated With Mental Health In United States Veterans, Air Force Military, And Air Force Employees, Andrew J. Hoisington, Christopher A. Stamper, Molly Penzenik, Meredith Reitter, Elizabeth J. Kovacs, Nazanin H. Bahraini, Lisa A. Brenner

Faculty Publications

Individuals in Westernized countries spend most of their time indoors. However, exploration of residential building factors that may influence occupants’ mental health is limited in scientific literature. The purpose of this study was to explore investigator's perceived areas of importance in residences to mental health via survey methods. To that end, we administered the Housing, Occupancy, Materials, and Environment (HOME) survey to assess factors that may influence mental health to those working in the United States (US) Air Force (n = 230) or past military members, US Veterans (n = 180). Self-reported mental health surveys were also administered to the …

Banach Algebras And The Gelfand Theory Of Group Algebras On Locally Compact Abelian Groups, James Gabriel Bonvanie

Master's Theses

A Banach algebra is a complex algebra that is simultaneously a Banach space in which the norm is submultiplicative. Notably, $L^1(\mathbb{R})$ with the convolutional product is an Abelian, non-unital Banach algebra that admits an approximate identity. We rectify $L^1(\mathbb{R})$ lacking a unit via the unitization $L^1(\mathbb{R})\times\mathbb{C}$ with identity $(0,1)$. Unitization opens the discussion to the spectrum $\sigma(x)$ of a Banach algebra element, in which the spectrum is a nonempty, compact subset of the complex plane. The spectrum of an Abelian Banach algebra is fully characterized with multiplicative linear functionals, and we prove that the Fourier transform is the unique multiplicative …

Spos: An Attestation Solution For The Detection And Mitigation Of Point Of Sale Malware, Damian Singh Dhesi

Master's Theses

Securing 95% of card present transactions, accounting for billions of transactions a year, has made EMV the premier protocol for card-based payment. Created by and named after Europay, Mastercard, and Visa, the EMV protocol provides multiple solutions to resolve security concerns with the outdated, swipe-based, magnetic stripe payment. Such solutions are Chip and PIN which provides a more secure transaction at a significant time cost and EMV contactless which provides improved security to Chip and PIN at greater ease of use with its quick, tap-to-pay based payment. However, regardless of how secure the EMV protocol makes the card side of …

Investigating Social Presence In Collaborative Keys For Asynchronous Courses, Lily P. Cook

Master's Theses

Asynchronous virtual courses have become increasingly popular in the years following the global Covid-19 pandemic. These courses, with no set meeting schedule, offer flexibility to both students and instructors, but pose challenges for developing a collaborative learning environment. The Community of Inquiry framework (Rourke et al., 1999) identifies three essential components in an online course necessary to foster a collaborative environment- teaching presence, cognitive presence, and social presence. Social presence is especially impacted in asynchronous learning settings, which presents challenges for the students to display their personalities and connect with the community. This study investigates Collaborative Keys (CKs), structured collaborative …

On Diffeomorphism Groups Of Surfaces, Madeleine Goertz

Master's Theses

Let $M$ be a closed, connected, smooth manifold. What are the symmetries of $M$? From a geometric viewpoint, the symmetries of $M$ are precisely its isometries, the self maps which preserve lengths and angles. In the smooth category, the symmetries of $M$ are its diffeomorphisms, the self maps which are smooth and have a smooth inverse. Does expanding our notion of symmetries to include diffeomorphisms result in ``more'' symmetries in a meaningful sense? As a formal conjecture, the claim is that the isometry group of $M$ is a deformation retract of the diffeomorphism group of $M$. If $M$ is the …

Filling Gaps In Scientific Data Sets Using Physics Informed Neural Networks: A Case Study In Velocity Fields, Ellen Saunders

Master's Theses

Gaps in scientific data sets are a persistent issue for researchers in a variety of fields, and while nothing makes up for missing out on real data, well-simulated synthetic data can be a useful tool. In the world of image processing, machine learning techniques have become quite sophisticated at taking an image with a missing component and filling in that space with something believable. The aim of this thesis is to take machine learning techniques similar to what gets used in image processing and repurpose them to infill gaps in scientific data sets in a realistic manner. This thesis compares …

Adversarial Deep Reinforcement Learning For Tank Duel Simulation Using Lidar-Based Observations, Braedan Kennedy

Master's Theses

Previous research has demonstrated that reinforcement learning agents can learn to steer differential-drive robots around obstacles using 2D lidar scans as observations. However, these studies typically treat all range returns as undifferentiated obstacles—objects to avoid—without distinguishing between different object types. This thesis builds upon previous research by introducing an adversarial task in which an agent must interpret raw range readings to both avoid static obstacles and identify, pursue, and engage a hostile target.

To investigate this problem, this thesis introduces TankGame, a novel, lightweight 2D tank duel simulator. Each agent receives a 360° lidar scan, controls its motion via tread …

Opening The Black Box With Regal: A Novel Explainable Ai Approach To Uncover Key Predictors In Search And Rescue Success, Brandon Hyunjun Kim

Master's Theses

The outcome of a search and rescue (SAR) operation is influenced by a complex, non-linear interplay among numerous factors, including geographic context, subject-specific characteristics, and environmental conditions. The high dimensionality and intricate dependencies among these variables pose significant challenges to traditional exploratory modeling approaches, limiting their ability to uncover meaningful patterns and relationships associated with mission success. This study introduces Rules Based Explanations for Generated neighborhoods Around Localized cases (REGAL), a novel adaptation of the Local Interpretable Model-agnostic Explanations (LIME) framework to explain deep multimodal neural networks and what key features it assesses to determine search and rescue success. REGAL …

Vertical And Latitudinal Variability Of Marine Heatwaves In The California Current, Gavin M. Plume

Master's Theses

Marine heatwaves (MHWs) are increasing in frequency and intensity globally, with grave effects on marine ecosystems and their dependent industries. There are significant gaps in knowledge of the subsurface behavior and geographic distribution of MHWs, especially in eastern boundary upwelling systems like the California Current. Here, two decades of full water-column temperature observations from a shallow autonomous profiler in San Luis Obispo Bay (~10m) revealed that while MHWs have similar average durations and intensities across all depths, one-third of bottom MHWs occur without a concurrent surface signal. MHWs across the water column initiated during anomalously weak upwelling or downwelling conditions …

Myceli-Yum: Elucidating Structure-Property Relationships For Polymer Degradation By Mycelial Digestion, Jordan Scott Ford

Master's Theses

Since the industrial entrance of polymer plastic materials, plastic has become ubiquitous in both everyday use and waste. Due to inefficiencies and knowledge gaps, current recycling methods are not able to account for the high scale of plastic waste, resulting in the bulk of this waste being landfilled, mishandled, and deposited in the environment. Mycelium, the microorganism responsible for fruiting mushroom bodies and mold growth, holds potential to reduce plastic waste and can potentially be utilized as a method of industrial recycling. Following a drug-design approach, the active site of mycelial enzymes responsible for natural biopolymer degradation have been assessed …

Adaptive Volatility Forecasting Models, Jeffrey K. Tan

Master's Theses

In finance, risk is often quantified by volatility, and computing accurate volatility forecasts — while vital to financial decision making — remains one of the most challenging tasks in financial modeling. This thesis, motivated in part by the Black-Scholes-Merton Model and its limitations, adopts a statistical approach to volatility forecasting. The two main models of interest are the Exponential Weighted Moving Average (EWMA) model and the GARCH(1,1) model. Specifically, this work expands upon a potential adaptive lambda algorithm for EWMA models first proposed by Bernard Bollen (2014), and this work also utilizes the Momentum of Predictability (MoP) to generate adaptive …

The Degrees Of The Irreducible Representations Of The Symmetric Group With Respect To Primes, Vanessa F. Beeler

Master's Theses

In this thesis, we explore the relationship between the degrees of irreducible matrix representations of the symmetric group and prime numbers. We start by building up the required background necessary to construct our results. We dive into topics of discrete mathematics including matrix representations, characters of representations, integer partitions, conjugacy classes, class functions, and tableaux. Some other key ingredients in our work include using character tables to classify the irreducible rep- resentations of the symmetric group and the hook-length formula to easily compute the degrees of these representations. Once we have laid the groundwork for our in- vestigation, we begin …

Comparing Machine Learning Paired Optimization Strategies For Single-Component Waterborne Direct-To-Metal Coatings, Harvir S. Kalkat

Master's Theses

As R&D attempts to fine tune properties before production, the redesign and testing process can become highly iterative. The repetitive nature of formulating can be difficult to escape when relying on chemical intuition alone. To provide some guidance in this process, machine learning (ML) can leverage data from previous trials¹ to design suggestions for subsequent trials. Although ML capabilities have vastly expanded in the last few years, integration of ML into chemistry R&D and education has been slow. Unraveling the mystique of ML can help change what has been a slow embrace in the coatings industry. It is important …

Exposure To Metoprolol And Propranolol Mixtures On Biochemical, Immunohistochemical, And Molecular Alterations In The American Oyster, Crassostrea Virginica, Andrew Salinas, Md Saydur Rahman

School of Earth, Environmental, & Marine Sciences Faculty Publications

Pharmaceutical drugs, particularly beta-blockers (e.g., metoprolol, propranolol, etc.), are extensively used to treat human cardiovascular conditions, yet pose significant risks to non-target aquatic organisms when introduced into coastal and marine environments via wastewater effluent. This study aimed to investigate the effects of short-term exposure (one week) to environmentally relevant concentrations of metoprolol and propranolol (MP) mixtures (low-dose: 50 ng/L propranolol and 250 ng/L metoprolol, and high-dose: 250 ng/L propranolol and 650 ng/L metoprolol) in the American oyster (Crassostrea virginica, a commercially and ecologically important marine bivalve mollusk) under controlled laboratory conditions. Histopathological assessments revealed structural damage to gills, …

Heat, Smoke, And Resilience In East Central Spokane: Community Insights On Climate Adaptation, Sarah Bliss Matousek, Amanda Gray, Dante Jester, Brian G. Henning

Climate, Water, and the Environment Research

This report presents findings from a multi-methods research initiative exploring the impacts of climate-related hazards—specifically extreme heat and wildfire smoke—on residents of Spokane’s East Central neighborhood. The project combined a community survey with a World Café-style symposium to gather both quantitative data and lived experiences from local participants. Key themes that emerged include the need for more cooling infrastructure, accessible health education, improved indoor air quality, and stronger neighborhood-level communication and support networks. The report highlights how systemic underinvestment in East Central intersects with climate vulnerability, underscoring the urgency of equitable, community-driven solutions. Recommendations include expanding tree canopy, increasing funding …

Building A Smoke-Resilient Spokane: Guidance From Community Conversations, Anna Reed, Hannah Mckinley, Dante Jester, Brian G. Henning, Tania Busch Isaksen

Climate, Water, and the Environment Research

Wildfire season has grown in length and severity in the western United States due to decades of fire suppression and climate change. This trend is projected to continue, worsening air quality and increasing the risk to public health. In response, the Gonzaga Institute for Climate, Water, and the Environment, in partnership with the University of Washington, hosted the Smoke Ready Spokane Symposium in July 2024 in Spokane, Washington. The event convened community partners across sectors to reflect on past wildfire smoke events and discuss locally-relevant wildfire smoke exposure reduction strategies. Symposium participants engaged in small group discussions using the World …