Digital Commons Network^™

Semi‑Supervised Graph Anomaly Detection Via Robust Homophily Learning, Guoguo Ai, Hezhe Qiao, Hui Yan, Guansong Pang

Research Collection School Of Computing and Information Systems

Current semi-supervised graph anomaly detection (GAD) methods utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. These methods posit that 1) normal nodes share a similar level of homophily and 2) the labeled normal nodes can well represent the homophily patterns in the entire normal class. However, this assumption often does not hold well since normal nodes in a graph can exhibit diverse homophily in real-world GAD datasets. In this paper, we propose RHO, namely Robust Homophily Learning, to adaptively learn such homophily patterns. RHO consists of …

Marsanywhere: Dataset And Cross-View Diffusion Model For Satellite-To-Ground View Synthesis With Mars Data, Benjamin T. Hinchliff

Master's Theses

Satellite-to-ground view synthesis aims to create a realistic ground view image from a corresponding satellite view image. This is a well-studied problem for street level imagery, with good results being achieved by using modern image synthesis techniques such as diffusion models. However, despite the public availability of satellite and ground level imagery on Mars, these techniques have yet to be applied to the domain due to difficulties in collating and processing the data into a usable form. We address this deficiency by creating a dataset consisting of ground view panorama imagery from the Perseverance rover, along with associated satellite view …

Llm-Assisted Cwe Identification, Severity Assessment, And Vulnerability Description Generation, Mohammad Jalili Torkamani

School of Computing: Dissertations, Theses, and Student Research

Identifying the underlying weakness types and assessing their severity using CWE and CVSS standards are critical steps in software vulnerability management. While timely assessment of vulnerabilities mitigates the impact of severe security incidents, automating joint CWE identification and severity assessment remains challenging due to the heterogeneity of vulnerabilities across different code granularities and programming languages. In addition, generating vulnerability descriptions is often time-consuming, as it requires extensive manual review, validation, and writing by security experts.

In this thesis, we leverage the capabilities of Large Language Models (LLMs) to automate the identification of CWE identifiers and the assessment of their severity …

Curvilinear Image Segmentation Using Multiscale Variational U-Net, Rebekah Fortes

LSU New Orleans Theses and Dissertations

Segmentation of curvilinear structures such as water contours, cracks in cement, and vascular networks in biomedical imaging, poses unique challenges due to extreme class imbalance, irregular morphology, low contrast against complex backgrounds, and the need to preserve global connectivity while detecting fine-scale details. We propose a Multiscale Variational U-Net (MSVU-Net) architecture designed specifically to address these challenges. The model integrates multiscale convolutional filters to capture both global context and local detail, while embedding a variational model in the bottleneck layer to enhance structural representation. To mitigate class imbalance and improve fidelity, the network optimizes a hybrid loss function that combines …

Coupled Machine Learning Models: Combining Observations And Numerical Analysis In A Physics-Regularized Approach, Austin B. Schmidt

LSU New Orleans Theses and Dissertations

This dissertation investigates surrogate modeling for fixed-location environmental forecasting using novel data-combination techniques. The work surveys the landscape of observational measurements and numerically generated data, identifying similar research and gaps in current methodologies. The ratio-coupled training framework is introduced to combine two data sources per predicted feature through a tunable parameter that weights training signal strength. An optimization scheme is developed to simultaneously tune surrogate weights and the coupled signal ratio, allowing relative influence between signals to act as an explicit regularizer. Three case studies demonstrate the methodology and approach in a variety of contexts. The first study is based …

Enhancing Ad/Adrd Management Through Ihelpcare: A Compliant And Culturally Sensitive Ai-Driven Digital Healthcare Platform, Trisha Bhowmick

Master's Theses

The digital healthcare field is expanding fast, and now it requires platforms that use advanced technology and maintain robust data security and compliance practices. In the present paper, we present the main structure, key methods, and compliance strategies of the digital healthcare system iHelpCare, which, while fully meeting the HIPAA/GDPR requirements, provides health services more accessible, efficient, and inclusive. The proposed platform is powered by AI for personalized care solutions, with the main emphasis on preventive health management and providing tools for people with disabilities.

iHelpCare achieves real-time patient monitoring while securing medical data management and easy communication between patients, …

Topic Modeling And Culturomic Analysis Of 30,000 Books Over 100 Years Using Gensim, Michael A. Freeman

Electronic Theses and Dissertations

This thesis explores the cultural influence of historical events on English-language fiction published between 1820 and 1929. Using a corpus of 30,256 digitized books from Project Gutenberg, Latent Dirichlet Allocation (LDA) topic modeling was applied to identify recurring themes across eleven decades. The study sought to determine whether historically significant events could be detected within fictional narratives. One clear instance emerged: Napoleon Bonaparte and the Napoleonic Wars appeared explicitly in the 1820s corpus. Beyond this, several thematic patterns were observed—such as maritime language in the 1840s, national identity in the 1880s, and youth-oriented dialogue in the early 20th century—that plausibly …

Computational Expressions Of Void Reactions In Extended Chemical Reaction Network Models, Aiden J. Massie

Theses and Dissertations

Chemical Reaction Networks (CRNs) are a system of abstraction of real-world chemical dynamics. Each CRN system is defined as a pair of molecular species and reaction rules, which consume a set of reactant species and create a new set of product species. In this paper, we investigate the simple class of void reactions, which cannot create new species and are computationally weak with small-enough sizes in basic CRNs. Here, we study their computational expression in more powerful extended CRN models. Specifically, we consider the Step CRN model, in which new species are added into the system through a sequence of …

Understanding Bias And Fairness In Large Language Models: An Empirical Study, Joshua Johnson

Electrical Engineering and Computer Science Undergraduate Honors Theses

This thesis investigates demographic bias in large language models (LLMs) through the use of evaluating outcome disparities when utilized in decision making tasks as well as underlying associations that could contribute to furthering these disparities. Using profiles from the Adult dataset, we analyze how Gemini 2.0 Flash performs in an income prediction task using zero-shot and few-shot prompting methods. Our findings show that models exhibit measurable differences in demographic parity and false positive rates, with the use of few-shot prompting reducing these disparities. Alongside this line of testing, we tested associational bias in Qwen 2.5 using probability based association tests …

Content And Consequences: Impact Of Representation In Stem Higher Education Instructional Content On Marginalized Students, Nichole Ventura

Doctorate in Education

This qualitative study examined representation of historically marginalized students in STEM instructional content at the higher education level and its impact on their learning experiences. Despite growing diversity initiatives in STEM enrollment, curricular materials often fail to reflect the identities of underrepresented students. Using critical theory and interpretivist approaches, this research investigated how representation—or its absence—shapes students' sense of belonging, academic identity formation, and persistence. Through semi-structured interviews with undergraduate students from historically marginalized backgrounds, and purposeful sampling, this study captured the lived experiences of students engaging with STEM instructional materials. Interview protocols explored how students perceive their representation in …

Investigating Programming Behaviors To Understand Student Engagement And Experience In Introductory Programming Courses, Marcus Eugene Gubanyi

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Introductory programming courses are foundational to developing students’ problem-solving abilities and shaping their persistence in computing pathways. Engagement with programming tasks plays a central role in student learning and experience. Many research measures, including self-reports and code submissions, offer only a limited view of student engagement with programming tasks. This dissertation leverages programming process data, consisting of keystrokes and compilation events, to capture the programming process as it unfolds and to investigate observable programming behaviors. Guided by educational theories, three studies examine how students’ programming behaviors vary across instructional and assessment contexts, how they relate to motivational profiles, and how …

Making Deep Neural Networks Trustworthy: Intelligibility And Safety Through Symbolic Methods, Eleanor Catherine Quint

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

The rapid adoption of deep learning has come at the cost of properties long valued in artificial intelligence: intelligibility and safety. This dissertation develops methods that restore these properties by coupling neural networks with symbolic structure.

First, for supervised classification, I propose a differentiable decision tree integrated with a supervised variational autoencoder. The resulting model maintains competitive accuracy and generative performance while exposing clear macro-features in its latent space, improving interpretability.

Second, for reinforcement learning, I extend constrained Markov decision processes by specifying constraints in formal languages. This formal language constrained MDP enables the use of automata for state augmentation, …

Qualitative Stereo Vision Using Distributed Extended Waltz Filtering, Ben Mathew

Theses and Dissertations

Stereo vision is a fundamental problem in computer vision, aimed at reconstructing three-dimensional scene structure from two or more two-dimensional images. Traditional stereo algorithms rely on quantitative disparity estimation, often constrained by calibration precision, lighting variations, and surface texture. In contrast, our proposed Qualitative Stereo Vision seeks to understand depth relationships and spatial configurations from multiple planar views through symbolic reasoning and constraint satisfaction, offering a more flexible and cognitively plausible approach to scene interpretation.

This dissertation presents a novel framework called Distributed Extended Waltz Filtering, designed to provide qualitative stereo vision, particularly in the presence of occlusions—a persistent challenge …

A Picture Tells A Thousand Words—, But Ecg Signals Have More To Say, Ashley N. Gomez

Theses and Dissertations

With the increasing adoption of deep learning classification models in the medical domain, a critical challenge remains: achieving high predictive accuracy while maintaining clinical Inter-pretability. This study examines how model architecture, dataset origin, and the use of full versus subset data affect both classification performance and Interpretability in Electrocardiogram (ECG) signal analysis. ResNet18 is evaluated using an open-source ECG Image Dataset, thus a custom dataset derived from digitized ECG images. Post-hoc explainability methods, such as Integrated Gradients, are applied to determine which time steps have the most significant influence on model decisions. The findings demonstrate that model architecture and dataset …

Efficient Self-Supervised Representation Learning For Large-Scale Time Series Classification, Kevin Garcia

Theses and Dissertations

Recently, there has been a significant advancement in designing Self-Supervised Learning (SSL) frameworks for time series data to reduce the dependency on data labels. Among these works, hierarchical contrastive learning-based SSL frameworks, which learn representations by contrasting data embeddings at multiple resolutions, have gained considerable attention. Due to their ability to gather more information, they exhibit better generalization in various downstream tasks. However, when the time series data length is significant long, the computational cost is often significantly higher than that of other SSL frameworks. In this paper, to address this challenge, we propose an efficient way to train hierarchical …

Interpretable Alignment Of Textual Weather Reports With Local Sensor Time Series For Extreme Weather Event Visualization, Juan Luis Garza

Theses and Dissertations

This thesis presents an automated and interpretable pipeline that links natural-language weather narratives with local meteorological sensor time series. Using large language models, NOAA-style event reports are transformed into structured records capturing event type, timing, descriptive context, and uncertainty. Each extracted event is aligned with harmonized temperature, precipitation, and wind measurements from nearby weather stations, enabling systematic comparisons between narrative evidence and observed atmospheric conditions.

Across roughly fifty stations and more than two thousand events, the analyses show that discrepancies between narrative descriptions and sensor behavior arise primarily from spatial separation rather than from temporal offsets, sensor preprocessing artifacts, or …

Fractals, Reachability, And Computation In Models Of Dna Self-Assembly And Chemical Reaction Networks, Ryan Arlie Knobel

Theses and Dissertations

This thesis serves as the bridge between results compiled across varying models of tile self-assembly, molecular computation, and game complexity. As such, this thesis is broken into three chapters. In the first part, we show how to generate any Discrete Self-Similar Fractal (DSSF) with a feasible generator in the seeded Tile Assembly model, a model limited to single tile attachments and pairwise state transitions. In the next part, we study models of molecular computation, where we consider the problem of reachability in Chemical Reaction Networks and similar model extensions. The final part is a game-complexity analysis of Celtic! and k-ago, …

Definition Of The 3d Position And Motion Status Of The Moving Heart Based On 2d Projections, Lawrence D. Orijuela

Electronic Theses, Projects, and Dissertations

This thesis presents a novel application of deep learning to the estimation of pulmonary vein coordinates using X-ray image pairs from a FORBILD Thorax phantom derived motion dataset. A Siamese neural network was developed to predict the 3D coordinates of one pulmonary vein at a time, specifically the Right Superior Pulmonary Vein (RSPV), Left Superior Pulmonary Vein (LSPV), Left Inferior Pulmonary Vein (LIPV), or Right Inferior Pulmonary Vein (RIPV), based on two-dimensional projection images.

The input data consisted of over 1.6 million grayscale X-ray image pairs across 1331 virtual patients, each annotated with ground truth 3D coordinates. To manage memory …

A Leslie System For A Demographic Simulation: From An Actuarial Point Of View, David Kings

Electronic Theses and Dissertations

This thesis develops a discrete stochastic linear systems interpretation of age–stage demographic evolution grounded in Leslie operators and realized in a discrete-event simulation implemented with salabim. The central claim is that one annual cycle of the simulation constitutes a cone-preserving, stochastic affine transformation on a high- dimensional population state vector indexed by age, sex, marital status, household type, employment, and education, and that the composition of yearly operators yields a random matrix product whose top Lyapunov exponent is the stochastic counterpart of the Perron–Frobenius growth rate (Caswell, 2001; Tuljapurkar, 1997)[1, 2]. The actuarial bridge is constructed by mapping simulated survival …

Uniteformer: Unifying Node And Edge Modalities In Transformers For Vehicle Routing Problem, Dian Meng, Zhiguang Cao, Jie Gao, Yaoxin Wu, Yaqing Hou

Research Collection School Of Computing and Information Systems

Neural solvers for the Vehicle Routing Problem (VRP) have typically relied on either node or edge inputs, limiting their flexibility and generalization in real-world scenarios. We propose UniteFormer, a unified neural solver that supports node-only, edge-only, and hybrid input types through a single model trained via joint edge-node modalities. UniteFormer introduces: (1) a mixed encoder that integrates graph convolutional networks and attention mechanisms to collaboratively process node and edge features, capturing cross-modal interactions between them; and (2) a parallel decoder enhanced with query mapping and a feed-forward layer for improved representation. The model is trained with REINFORCE by randomly sampling …

Learning Memory-Enhanced Improvement Heuristics For Flexible Job Shop Scheduling, Jiaqi Wang, Zhiguang Cao, Peng Zhao, Rui Cao, Yubin Xiao, Yuan Jiang, You Zhou

Research Collection School Of Computing and Information Systems

The rise of smart manufacturing under Industry 4.0 introduces mass customization and dynamic production, demanding more advanced and flexible scheduling techniques. The flexible job-shop scheduling problem (FJSP) has attracted significant attention due to its complex constraints and strong alignment with real-world production scenarios. Current deep reinforcement learning (DRL)-based approaches to FJSP predominantly employ constructive methods. While effective, they often fall short of reaching (near-)optimal solutions. In contrast, improvement-based methods iteratively explore the neighborhood of initial solutions and are more effective in approaching optimality. However, the flexible machine allocation in FJSP poses significant challenges to the application of this framework, including …

Instance-Level Video Depth In Groups Beyond Occlusions, Yuan Liang, Yang Zhou, Ziming Sun, Tianyi Xiang, Guiqing Li, Shengfeng He

Research Collection School Of Computing and Information Systems

Depth estimation in dynamic, multi-object scenes remains a major challenge, especially under severe occlusions. Existing monocular models, including foundation models, struggle with instance-wise depth consistency due to their reliance on global regression. We tackle this problem from two key aspects: data and methodology. First, we introduce the Group Instance Depth (GID) dataset, the first large-scale video depth dataset with instance-level annotations, featuring 101,500 frames from real-world activity scenes. GID bridges the gap between synthetic and real-world depth data by providing high-fidelity depth supervision for multi-object interactions. Second, we propose InstanceDepth, the first occlusion-aware depth estimation framework for multi-object environments. Our …

Robust Hallucination Detection In Llms Via Adaptive Token Selection, Mengjia Niu, Hamed Haddadi, Guansong Pang

Research Collection School Of Computing and Information Systems

Hallucinations in large language models (LLMs) pose significant safety concerns that impede their broader deployment. Recent research in hallucination detection has demonstrated that LLMs’ internal representations contain truthfulness hints, which can be harnessed for detector training. However, the performance of these detectors is heavily dependent on the internal representations of predetermined tokens, fluctuating considerably when working on free-form generations with varying lengths and sparse distributions of hallucinated entities. To address this, we propose HaMI, a novel approach that enables robust detection of hallucinations through adaptive selection and learning of critical tokens that are most indicative of hallucinations. We achieve this …

Sempo: Lightweight Foundation Models For Time Series Forecasting, Hui He, Kun Yi, Yuanchi Ma, Qi Zhang, Zhengdong Niu, Guansong Pang

Research Collection School Of Computing and Information Systems

The recent boom of large pre-trained models witnesses remarkable success in developing foundation models (FMs) for time series forecasting. Despite impressive performance across diverse downstream forecasting tasks, existing time series FMs possess massive network architectures and require substantial pre-training on large-scale datasets, which significantly hinders their deployment in resource-constrained environments. In response to this growing tension between versatility and affordability, we propose SEMPO, a novel lightweight foundation model that requires pretraining on relatively small-scale data, yet exhibits strong general time series forecasting. Concretely, SEMPO comprises two key modules: 1) energy-aware SpEctral decomposition module, that substantially improves the utilization of pre-training …

Ai In Consideration Of Her: Accounting For Gendered Workplace Dynamics In The Design And Evaluation Of Human-Centered Ai Integration In Everyday Workplaces, Kelsea S. Schulenberg

All Dissertations

Rapid advancements in the technical capabilities and availability of generative Artificial Intelligence (AI) systems, such as OpenAI's ChatGPT, have drawn widespread attention to the opportunities and challenges associated with AI integration into everyday workplaces (i.e., office-type work). Following calls for organizations to consider the ethical and workplace-specific impacts of generative AI's use before integrating it into the workplace, this dissertation addresses three critical gaps in Human-Centered Computing (HCC) and AI workplace integration research. First, this dissertation unpacks the underdeveloped links between women's representation - or lack thereof - in AI-related fields and how their experiences with gendered workplace dynamics in …

Accelerating Relationship Discovery In Chronic Lower Back Pain Through Knowledge Graph And Ontology Enhanced Large Language Models, Damon Lin

Master's Theses

Chronic lower back pain (cLBP) is a widespread public health burden linked to anxiety, depression, and opioid addiction. Interventions aimed at treating cLBP have shown minimal improvements in pain outcomes, leading researchers to reexamine our understanding of cLBP through constructing a causal model. However, constructing causal models through Randomized Controlled Trials are often unfeasible, and relying on domain expertise requires extensive and time-consuming research, posing a serious bottleneck for designing effective treatments. To accelerate this process, we apply Knowledge Graphs, Ontologies, and Large Language Models (LLMs) to aid researchers in determining possible causal relationships. First, we demonstrate how LLMs can …

A Comparative Evaluation Of Feedback Strategies For Enhancing Student Software Test Suite Writing Outcomes, Ashton Alonge

Master's Theses

Background and Context

Software testing is a fundamental component of computer science education, forming the basis for students’ ability to ensure program correctness and reliability. Despite its importance, many students struggle to design test cases that effectively expose faults and achieve meaningful test coverage. Traditional instructional approaches often emphasize code coverage metrics such as line or branch coverage, but these metrics may not adequately capture the quality of student tests. Mutation analysis, which measures how well tests detect small, artificial faults (mutants) introduced into the program, offers a potentially richer measure of test effectiveness. However, little is known about how …

Generalized Detection Of Animal Behavior Using Accelerometers, Alexander J. Arrieta

Master's Theses

Animal mounted sensors are becoming increasingly used to passively monitor both domestic and wild animals. Advances in lightweight accelerometer and GPS technology have allowed many animals to be fitted with high accuracy sensors for extended periods of time. This leads to new opportunities to study animal behavior without direct observation. However, interpreting the raw data is difficult due to the high volume and missing context of the information. Machine learning techniques excel at extracting information from raw data streams and are excellent candidates for processing the sensor data. However, due to large variance in how different animals execute the same …

Detection Of Phase-Binning And Interpolation Artifacts In 4-Dimensional Computed Tomography Imaging Using Deep Learning And Rule-Based Approaches, Jorge Cisneros, Nathan H. Feldt, Yevgeniy Vinogradskiy, Richard Castillo, Edward Castillo

Department of Radiation Oncology Faculty Papers

BACKGROUND: Four-dimensional computed tomography (4DCT) imaging is a crucial component to lung cancer radiotherapy planning and enables CT-ventilation-based functional avoidance planning to mitigate radiation toxicity. However, 4DCT scans are frequently impaired by acquisition artifacts that corrupt downstream analyses that depend on lung segmentation and deformable image registration, such as CT-ventilation and dose accumulation.

PURPOSE: This study develops 3D deep learning models to identify phase-binning artifacts at the voxel level and a heuristic, rule-based method to identify interpolation slices within 4DCT images.

METHODS: We introduce a generator that systematically inserts synthetic phase-binning and interpolation artifacts into any artifact-free breathing phase obtained …

Intelligent Predictive Frameworks Under Data Scarcity And Uncertainty, Solayman Hossain Emon

Open Access Theses & Dissertations

Modern predictive systems frequently operate under conditions of limited annotated data, high uncertainty, and the need for reliable decision-making. When the predictive models expand across heterogeneous data types (e.g., spatial, temporal streams), the challenge lies not only in accurate prediction but also in adapting in data distributions shifts or label scarcity. To address these issues, this thesis explores an Intelligent Predictive Framework that operates robustly under data scarcity and uncertainty across two distinct domains: medical imaging (spatial) and time-series forecasting (temporal). In the first part of this work, a semi-supervised mean teacher (MT) paradigm is tailored for medical image segmentation …