Digital Commons Network^™

Diffusion-Based Negative Sampling On Graphs For Link Prediction, Yuan Fang, Yuan Fang

Research Collection School Of Computing and Information Systems

Link prediction is a fundamental task for graph analysis with important applications on the Web, such as social network analysis and recommendation systems, etc. Modern graph link prediction methods often employ a contrastive approach to learn robust node representations, where negative sampling is pivotal. Typical negative sampling methods aim to retrieve hard examples based on either predefined heuristics or automatic adversarial approaches, which might be inflexible or difficult to control. Furthermore, in the context of link prediction, most previous methods sample negative nodes from existing substructures of the graph, missing out on potentially more optimal samples in the latent space. …

On The Feasibility Of Simple Transformer For Dynamic Graph Modeling, Yuxia Wu, Yuan Fang, Lizi Liao

Research Collection School Of Computing and Information Systems

Dynamic graph modeling is crucial for understanding complex structures in web graphs, spanning applications in social networks, recommender systems, and more. Most existing methods primarily emphasize structural dependencies and their temporal changes. However, these approaches often overlook detailed temporal aspects or struggle with long-term dependencies. Furthermore, many solutions overly complicate the process by emphasizing intricate module designs to capture dynamic evolutions. In this work, we harness the strength of the Transformer’s self-attention mechanism, known for adeptly handling long-range dependencies in sequence modeling. Our approach offers a simple Transformer model, called SimpleDyG, tailored for dynamic graph modeling without complex modifications. We …

Multigprompt For Multi-Task Pre-Training And Prompting On Graphs, Xingtong Yu, Chang Zhou, Yuan Fang, Xinming Zhan

Research Collection School Of Computing and Information Systems

Graph Neural Networks (GNNs) have emerged as a mainstream technique for graph representation learning. However, their efficacy within an end-to-end supervised framework is significantly tied to the availability of task-specific labels. To mitigate labeling costs and enhance robustness in few-shot settings, pre-training on self-supervised tasks has emerged as a promising method, while prompting has been proposed to further narrow the objective gap between pretext and downstream tasks. Although there has been some initial exploration of prompt-based learning on graphs, they primarily leverage a single pretext task, resulting in a limited subset of general knowledge that could be learned from the …

Decentralized Unknown Building Exploration By Frontier Incentivization And Voronoi Segmentation In A Communication Restricted Domain, Huzeyfe M. Kocabas

All Graduate Theses and Dissertations, Fall 2023 to Present

Exploring unknown environments using multiple robots poses a complex challenge, particularly in situations where communication between robots is either impossible or limited. Existing exploration techniques exhibit research gaps due to unrealistic communication assumptions or the computational complexities associated with exploration strategies in unfamiliar domains. In our investigation of multi-robot exploration in unknown areas, we employed various exploration and coordination techniques, evaluating their performance in terms of robustness and efficiency across different levels of environmental complexity.

Our research is centered on optimizing the exploration process through strategic agent distribution. We initially address the challenge of city roadway coverage, aiming to minimize …

The Effect Of Seed Mix Density And Composition On Wetland Plant Community Assembly In The Great Salt Lake Watershed, Elana Feldman

All Graduate Theses and Dissertations, Fall 2023 to Present

Wetlands provide important ecosystem services to society but are in danger across the globe partly due to the spread of invasive species (species that harm humans, the environment, or the economy). One species, Phragmites australis, is a widespread invader across the country, including in the wetlands of the Great Salt Lake and Utah Lake. Phragmites australis spreads widely and quickly outcompetes native species. In places where P. australis has already been removed, seeding wetlands helps block P. australis from returning. Native plants’ ability to prevent invasive species from entering the community is affected by many factors, but two that …

Pedestrian Pathing Prediction Using Complex Contextual Behavioral Data In High Foot Traffic Settings, Laurel Bingham

All Graduate Theses and Dissertations, Fall 2023 to Present

Ensuring the safe integration of autonomous vehicles into real-world environments requires a comprehensive understanding of pedestrian behavior. This study addresses the challenge of predicting the movement and crossing intentions of pedestrians, a crucial aspect in the development of fully autonomous vehicles.

The research focuses on leveraging Honda's TITAN dataset, comprising 700 unique clips captured by moving vehicles in high-foot-traffic areas of Tokyo, Japan. Each clip provides detailed contextual information, including human-labeled tags for individuals and vehicles, encompassing attributes such as age, motion status, and communicative actions. Long Short-Term Memory (LSTM) networks were employed and trained on various combinations of contextual …

Divergence-Free Tensor Densities In Two Dimensions, Tyler Hansen

All Graduate Theses and Dissertations, Fall 2023 to Present

In physics, a common method for exploring the way a physical system changes over time is to look at the system’s energy. Roughly speaking, the energy in these systems are either motion-based (kinetic energy, a bullet in flight) or position-based (potential energy, a rock sitting at the top of a hill). The difference between the system’s total kinetic and potential energies is quantified by an expression called the Lagrangian. Using a special procedure, this Lagrangian is massaged to produce a group of equations called the Euler-Lagrange equations; if the initial configuration of the system is provided, the solution to these …

The Quantitative Analysis And Visualization Of Nfl Passing Routes, Sandeep Chitturi

Computer Science and Computer Engineering Undergraduate Honors Theses

The strategic planning of offensive passing plays in the NFL incorporates numerous variables, including defensive coverages, player positioning, historical data, etc. This project develops an application using an analytical framework and an interactive model to simulate and visualize an NFL offense's passing strategy under varying conditions. Using R-programming and data management, the model dynamically represents potential passing routes in response to different defensive schemes. The system architecture integrates data from historical NFL league years to generate quantified route scores through designed mathematical equations. This allows for the prediction of potential passing routes for offensive skill players in response to the …

Proof-Of-Concept For Converging Beam Small Animal Irradiator, Benjamin Insley

Dissertations & Theses (Open Access)

The Monte Carlo particle simulator TOPAS, the multiphysics solver COMSOL., and

several analytical radiation transport methods were employed to perform an in-depth proof-ofconcept

for a high dose rate, high precision converging beam small animal irradiation platform.

In the first aim of this work, a novel carbon nanotube-based compact X-ray tube optimized for

high output and high directionality was designed and characterized. In the second aim, an

optimization algorithm was developed to customize a collimator geometry for this unique Xray

source to simultaneously maximize the irradiator’s intensity and precision. Then, a full

converging beam irradiator apparatus was fit with a multitude …

Soil Reclamation Strategies In Construction Disturbed Soil, Alexis Koelling

All Graduate Reports and Creative Projects, Fall 2023 to Present

The rapid urbanization occurring in arid environments like the Intermountain West region of the U.S. significantly alters soil conditions. Construction of roads, buildings, and other infrastructure leads to the disturbance of soil structure, nutrient depletion, and reduced fertility. This research addresses the need for sustainable soil management practices that may restore soil health post-construction. In this study, the effectiveness of various soil amendments and application methods on specific soil parameters and turfgrass establishment in construction-disturbed soils was evaluated. The study highlights the critical role of soil amendments, particularly municipal solid waste (MSW) compost, in improving soil quality and plant growth. …

Side Channel Detection Of Pc Rootkits Using Nonlinear Phase Space, Rebecca Clark

Poster Presentations

Cyberattacks are increasing in size and scope yearly, and the most effective and common means of attack is through malicious software executed on target devices of interest. Malware threats vary widely in terms of behavior and impact and, thus, effective methods of detection are constantly being sought from the academic research community to offset both volume and complexity. Rootkits are malware that represent a highly feared threat because they can change operating system integrity and alter otherwise normally functioning software. Although normal methods of detection that are based on signatures of known malware code are the standard line of defense, …

Side Channel Detection Of Pc Rootkits Using Nonlinear Phase Space, Rebecca Clark

Undergraduate Honors Theses

Cyberattacks are increasing in size and scope yearly, and the most effective and common means of attack is through malicious software executed on target devices of interest. Malware threats vary widely in terms of behavior and impact and, thus, effective methods of detection are constantly being sought from the academic research community to offset both volume and complexity. Rootkits are malware that represent a highly feared threat because they can change operating system integrity and alter otherwise normally functioning software. Although normal methods of detection that are based on signatures of known malware code are the standard line of defense, …

Inferring A Hierarchical Input Type For An Sql Query, Santosh Aryal

All Graduate Theses and Dissertations, Fall 2023 to Present

SQL queries are a common method to retrieve information from databases, much like asking a detailed question and getting a precise answer. Plug-and-play queries simplify the process of querying. In a Plug-and-play SQL query a programmer sketches the shape of the input to the query as a hierarchy. But the programmer could make a mistake in specifying the hierarchy and it takes programmer time and effort to specify the hierarchy. A better solution is to automatically infer the hierarchy from a query. This thesis presents a system to infer a hierarchical input type for an SQL query. We consider two …

A Framework That Explores The Cognitive Load Of Cs1 Assignments Using Pausing Behavior, Joshua O. Urry

All Graduate Theses and Dissertations, Fall 2023 to Present

Pausing behavior in introductory Computer Science (CS1) courses has been related to a student’s performance in the course and could be linked to a student’s cognitive load, or assignment difficulty. Having an objective measure of the cognitive load would be beneficial to course instructors as it would help them design assignments that are not too difficult. Two studies are presented in this work. The first study uses Cognitive Load Theory and Vygotsky’s Zone of Proximal Development as a theoretical framework to analyze pause times between keystrokes to better understand what types of assignments need more educational support than others. The …

Exploring Optimal Design Of Experiments For Random Effects Models, Ryan C. Bushman

All Graduate Theses and Dissertations, Fall 2023 to Present

The majority of research in the field of optimal design of experiments has focused on producing designs for fixed effects models. The purpose of this thesis is to explore how the optimal design framework applies to nested random effects models. The object that is being optimized is the model information matrix. We explore the full derivation of the random effects information matrix to highlight the complexity of the problem and show how the optimization is a function of the model's parameters. In conjunction with this research, the ODVC (Optimal Design for Variance Components) package was built to provide tools that …

Spatial Ecology Of Mule Deer Migrations From Grand Teton National Park And The Teton Range, Justin K. Schwabedissen

All Graduate Theses and Dissertations, Fall 2023 to Present

The Greater Yellowstone Ecosystem hosts several of the longest, fully intact ungulate migrations remaining in the continental United States. However, expanding development and an increasing human footprint continue to truncate migratory routes. While the endpoints are often a seasonal range on protected lands, these migration corridors frequently cross other jurisdictional boundaries, including large tracts of private or multiple-use lands, with varying levels of protection. Thus, it is critical resource managers understand the dynamics of migratory movements to define population-level corridors and prioritize appropriate conservation strategies. Mule deer in Wyoming have been documented traveling long distances between summer and winter ranges; …

Exploring Application Of The Coordinate Exchange To Generate Optimal Designs Robust To Data Loss, Asher Hanson

All Graduate Theses and Dissertations, Fall 2023 to Present

The primary objective of this study is to evaluate the efficacy of the coordinate exchange (CEXCH) algorithm in the generation of robust optimal designs. The assessment involves a comparative analysis, wherein designs produced by the Point Exchange (PEXCH) Algorithm are employed as benchmarks for evaluating the efficiency of CEXCH designs. Three modified criteria, selected from the traditional alphabet criteria pool, are utilized to score each algorithm. To enhance the reliability of the comparative analysis, multiple rounds of validation are conducted, focusing on visual assessments, design scores, and criteria efficiencies. The findings from each round of validation contribute to a comprehensive …

Impacts Of Lake Elevation Decline On Tui Chub, A Critical Forage Species For Lahontan Cutthroat Trout In Pyramid Lake, Nevada, Usa, Sarah Barnes

All Graduate Theses and Dissertations, Fall 2023 to Present

Lake level decline affects lakes worldwide, changing the availability and character of nearshore habitat used by fish to spawn, and increasing total dissolved solids (TDS), similar to salinity, a factor that negatively impacts fish health. Lake level decline can affect different lakes in different ways, but typically when lake level declines significantly, there is less nearshore habitat overall, and what nearshore habitat remains has less diverse habitat for fish. We investigated whether both impacts of lake level decline may be causing declines of Tui Chub Siphateles bicolor, a large minnow native to Pyramid Lake that spawns in nearshore habitat. …

A Review Of Student Attitudes Towards Keystroke Logging And Plagiarism Detection In Introductory Computer Science Courses, Caleb Syndergaard

All Graduate Theses and Dissertations, Fall 2023 to Present

The following paper addresses student attitudes towards keystroke logging and plagiarism prevention measures. Specifically, the paper concerns itself with changes made to the “ShowYourWork” plugin, which was implemented to log the keystrokes of students in Utah State University’s introductory Computer Science course, CS1400. Recent work performed by the Edwards Lab provided insights into students’ feelings towards keystroke logging as a measure of deterring plagiarism. As a result of that research, we have concluded that measures need to be taken to enable students to have more control over their data and assist students to feel more comfortable with keystroke logging. This …

Generative Ai In Education From The Perspective Of Students, Educators, And Administrators, Aashish Ghimire

All Graduate Theses and Dissertations, Fall 2023 to Present

This research explores how advanced artificial intelligence (AI), like the technology that powers tools such as ChatGPT, is changing the way we teach and learn in schools and universities. Imagine AI helping to summarize thick legal documents into something you can read over a coffee break or helping students learn how to code by offering personalized guidance. We looked into how teachers feel about using these AI tools in their classrooms, what kind of rules schools have about them, and how they can make learning programming easier for students. We found that most teachers are excited about the possibilities but …

Achieving Responsible Anomaly Detection, Xiao Han

All Graduate Theses and Dissertations, Fall 2023 to Present

In the digital transformation era, safeguarding online systems against anomalies – unusual patterns indicating potential threats or malfunctions – has become crucial. This dissertation embarks on enhancing the accuracy, explainability, and ethical integrity of anomaly detection systems. By integrating advanced machine learning techniques, it improves anomaly detection performance and incorporates fairness and explainability at its core.

The research tackles performance enhancement in anomaly detection by leveraging few-shot learning, demonstrating how systems can effectively identify anomalies with minimal training data. This approach overcomes data scarcity challenges. Reinforcement learning is employed to iteratively refine models, enhancing decision-making processes. Transfer learning enables the …

The Influence Of Individual Strategies On Cougar Ecology: Insights From Predation, Space Use, And Reproduction, Kristin Nicole Engebretsen

All Graduate Theses and Dissertations, Fall 2023 to Present

Carnivores are ecologically important to global ecosystems because they interact with their prey species and other carnivores in a variety of ways. Many carnivores have suffered habitat loss and persecution by humans, which has led some populations to become imperiled or locally extirpated. Despite these challenges, cougars (Puma concolor) continue to exist across North, Central, and South America. They exhibit behavioral adaptation across their wide range, thriving in terrain that ranges from temperate forests, to steppe scrub, to rainforest, to rugged deserts. Across these diverse ecosystems, cougars can successfully establish territories, hunt prey, and raise young to persist …

Characterization Of Carbonaceous Fault Rocks, Pioneer Fault Zone, South-Central Idaho, Genna Baldassarre

All Graduate Reports and Creative Projects, Fall 2023 to Present

Differing crystallinities of carbonaceous material are common in fault rocks across a range of geologic settings and spatial scales and may provide constraints on strain rate, the nature of fault slip, fluid-rock interactions, and temperature variations over the earthquake cycle. The Pioneer fault at Little Fall Creek in south-central Idaho provides an excellent opportunity to study nanostructure changes of carbonaceous matter as a function of fault deformation. At this location, the Pioneer Fault exhibits a well-defined principal slip zone (PSZ) composed of multi-layered white siliceous mineralization and black carbon to graphite with a continuously exposed adjacent damage zone that includes …

Information Based Approach For Detecting Change Points In Inverse Gaussian Model With Applications, Alexis Anne Wallace

Electronic Theses, Projects, and Dissertations

Change point analysis is a method used to estimate the time point at which a change in the mean or variance of data occurs. It is widely used as changes appear in various datasets such as the stock market, temperature, and quality control, allowing statisticians to take appropriate measures to mitigate financial losses, operational disruptions, or other adverse impacts. In this thesis, we develop a change point detection procedure in the Inverse Gaussian (IG) model using the Modified Information Criterion (MIC). The IG distribution, originating as the distribution of the first passage time of Brownian motion with positive drift, offers …

Interpreting Shift Encoders As State Space Models For Stationary Time Series, Patrick Donkoh

Electronic Theses and Dissertations

Time series analysis is a statistical technique used to analyze sequential data points collected or recorded over time. While traditional models such as autoregressive models and moving average models have performed sufficiently for time series analysis, the advent of artificial neural networks has provided models that have suggested improved performance. In this research, we provide a custom neural network; a shift encoder that can capture the intricate temporal patterns of time series data. We then compare the sparse matrix of the shift encoder to the parameters of the autoregressive model and observe the similarities. We further explore how we can …

Supporting Text And Data Analysis Across Campus From The Academic Library, Amy Kirchhoff, Hejin Shin Phd

Digital Initiatives Symposium

The ability to comprehend and communicate with text-based data is essential to future success in academics and employment, as evidenced in a recent survey from Bloomberg Research Services which shows that nearly 97% of survey respondents now use data analytics in their companies and 58% consider data and text mining a business analytics tool (https://www.sas.com/content/dam/SAS/bp_de/doc/studie/ba-st-the-current-state-of-business-analytics-2317022.pdf). This has fueled a substantial growth in text analysis research (involving the use of technology to analyze un- and semi-structured text data for valuable insights, trends, and patterns) across disciplines and a corresponding demand on academic libraries to support text analysis pedagogy and text analysis …

X-Ray Fluorescence Analysis Of Historic Art Paint Pigments, Sofia A. Stirpe, Juergen Thieme

Binghamton University Undergraduate Journal

Utilizing synchrotron radiation, X-ray fluorescence (XRF) microscopy enables researchers to deduce the elemental composition of paint pigments with a higher sensitivity and resolution than that of lab-based XRF instruments. With this information, art historians can date paintings by examining the elemental makeup of paint pigments and the time periods in which they were used. One painting, Christ and the Woman Taken in Adultery, has been duplicated by Pieter Brueghel the Younger and other artists, leading to confusion over which artworks are Brueghel masterpieces or copies by other artists. Art historian Maurizio Seracini, retaining a painting that could be assigned …

Mauvais Coulee Hydrologic Simulation Data, Sharhad Wainty, Taufique H. Mahmood, Christopher Spence, Diane F. Van Hoy

Datasets

The authors compiled a hydrologic model for the Mauvais Coulee Basin using Cold Region Hydrologic Platform. The datasets include observed and simulated streamflow, observed climatic data, land use maps and hydrological representative unit maps (HRU) maps. This study detected a mechanism of hydrologic change to wetting using a cold region hydrologic model during 1990-2004 period.

Gc-8 Informal Learning Artificial Intelligence Large Language Model Fine-Tuning On The Select Topic Of Entrepreneurship, Kristen Gabby, Melina Castellon, Jyothi Sampathirao

C-Day Computing Showcase

This project explored the usage and development of open-source Large Language Model (LLM) Artificial Intelligence (AI) with a chat feature, specifically to fine-tune on the topic of entrepreneurship. This project sought to showcase the adaptability of open-source LLMs and highlight challenges and solutions faced in leveraging those LLMs. The primary goal was to show proof of concept that training a LLM on the selected subject can create a specialized AI chat for informal learning.

Gmr-29 Identification Of Ai-Generated Images, Chris Foster, Joshua Brock, Harini Kottala, Srilatha Korrapati

C-Day Computing Showcase

With the quick rise of Artificial Intelligence (AI), generative AI models have greatly increased the volume and velocity of data creation. Among that data, AI-generated images have become a highly discussed topic, especially when discussing the potential dangers of these AI models. Due to these dangers, being able to distinguish AI-generated art from human-made art is becoming a necessity. Additionally, as these AI-models improve, it is becoming increasingly difficult for humans to determine whether art is AI-generated or human-made. This paper proposes the further exploration of the effectiveness of a current state of the art AI-image identification model.