Digital Commons Network^™

Achieving More Accurate And Interpretable Fraud Detection With Double Machine Learning, Jeremy Andrew Berry

Theses and Dissertations

Fraud detection remains a critical challenge across industries such as insurance, healthcare, finance, and government. Global losses from fraud and financial crime are estimated in the trillions annually, including billions in healthcare and insurance fraud alone. While effective for prediction, traditional machine learning methods often lack causal interpretability and struggle to adapt to evolving fraud tactics. This dissertation investigates the application of Double Machine Learning (DML), an emerging causal inference technique, to enhance both the accuracy and interpretability of fraud analytics. The research compares DML against established causal inference approaches, leveraging a meta-learning framework to evaluate model performance on accuracy, …

Enviromental Dna (Edna) Tools For Invasive Mosquitofish (Gambusia Affinis) Surveillance At The Shoshone Pupfish (Cyprinidon Nevadensis Shoshone) Refugium, Yusuf Olamilekan Umar

UNLV Theses, Dissertations, Professional Papers, and Capstones

Spring-fed aquatic ecosystems of the North American Southwest and U.S. Great Basin hosts a plethora of endemic fish species due to the effects of hydrologic fragmentation that resulted from Pleistocene aridification. Threats to endemic fishes worldwide include human intentional or unintentional release of exotic species into their habitats. Early detection of invasive species, while corrective actions are still possible, is critical for management, yet traditional survey methods are often disruptive to sensitive ecosystems, costly, and limited in sensitivity. The recent development of environmental DNA (eDNA) approaches offers powerful alternatives for invasive species monitoring in aquatic systems. In this study, a …

Advancing Cybersecurity Practice: Explainable Machine Learning For Network Intrusion Detection, Adam Grabowski, Shengjie Xu

Journal of Cybersecurity Education, Research and Practice

This research investigates explainable artificial intelligence (XAI) integration within machine learning (ML)-based intrusion detection systems (IDS), focusing on distinguishing malicious from benign network activities. We employed Random Forest and XGBoost models evaluated on widely recognized datasets, including NSL-KDD and UNSW-NB15, using both binary and multi-class classification tasks. The objective was to enhance cybersecurity operations through improved model transparency and interpretability. By integrating SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations), the study offers comprehensive global and local insights into model decision-making processes. Results demonstrate SHAP's effectiveness in providing a broad, dataset-wide understanding of feature interactions and importance, while …

Cybercamp: An Experience Report On The Transformations Of An Intensive Cybersecurity Summer Camp For High School Students, Jose R. Ortiz Ubarri, Kariluz Dávila Diaz Ph.D., Rafael A. Arce Nazario

Journal of Cybersecurity Education, Research and Practice

The Cybercamp is a Cybersecurity summer camp for high school students that has been held for the last nine years at a Hispanic Serving Institution. Since its inception in 2016 the Cybercamp has undergone several transformations in response to budget reductions and the COVID pandemic, to finally become its current version: a rich, hands-on learning experience that we believe is easily replicable even in resource-challenged environments.

In this paper, we document the transformations of the Cybercamp and discuss the developed curriculum and materials in hopes that others will reuse, adapt, and improve upon them. In the Cybercamp, we apply active …

Patterns Of Llm Weaponization: A Comparative Analysis Of Exploitation Incidents Across Commercial Ai Systems, George Antoniou

Faculty and Staff Publications & Presentations

This comparative study examines patterns of Large Language Model (LLM) weaponization through systematic analysis of four major exploitation incidents spanning 2023-2025. While existing research focuses on isolated incidents or theoretical vulnerabilities, this study provides the first comprehensive comparative framework analyzing exploitation patterns across state-sponsored cyber-espionage (Anthropic Claude incident), academic security research (GPT-4 autonomous privilege escalation), social engineering platforms (SpearBot phishing framework), and underground criminal commoditization (WormGPT/FraudGPT ecosystem). Through comparative analysis across eight dimensions—adversary sophistication, target selection, exploitation techniques, autonomy levels, detection evasion, attribution challenges, defensive gaps, and capability democratization—this research identifies critical cross-case patterns informing defensive prioritization. Findings reveal three …

Fault Structure, Deformation Mechanisms, And Why Fault Zones Matter To Society, Elizabeth S. Petrie, David A. Ferrill, Kelly K. Bradbury, James P. Evans

Geosciences Faculty Publications

Faults are widespread geologic structures that form in sediment and all rock types, occur in all tectonic regimes, and can be a blessing or a curse to society. Faults and fault zones act as conduits for underground movement of water and as plumbing systems for aquifers and springs essential for human habitation in many semi-arid and arid regions worldwide. Faults also provide pathways for natural oil and gas migration and high-permeability zones in hydrocarbon reservoirs, as well as barriers contributing to trapping and reservoir compartmentalization. By enhancing permeability in many geothermal energy systems, faults can be essential for fluid circulation …

The Effect Of Phosphate Fertilizer And Organic Matter On Phosphorus Status, Ph, And Cabbage Yield In Andisols, Mahfud Arifin, Emma Trinurani Sofyan, Anni Yuniarti, Rina Devnita, Sastrika Anindita

Jurnal Kultivasi

Andisols are characterized by high phosphorus (P) retention, which often limits P availability for crops. This study aimed to analyze the independent and interactive effects of P fertilizer and organic matter (i.e. manure and rice straw compost) on P retention, total P, available P, P uptake, soil pH, and cabbage yield. This research was conducted in pot experiments in plastic house, applying P fertilizer (0, 90, 180, 270 kg ha-1) and organic matter (20 kg ha-1 of chicken, sheep, cow manures and rice straw compost) on Andisols planted with cabbage. The experiment used a factorial randomized design. The results showed …

A Bump Hunting Approach To Finding Interpretable Data Pockets, Tushar Ojha

Electrical and Computer Engineering ETDs

This dissertation approaches the problem of extracting simple interpretations from local regions of data. This is sometimes called bump hunting because the local regions of interest have a high concentration of a particular output value. This work develops a bump hunting method for discrete-valued tabular data where each bump is modeled by a rectangular region of the input data space so its rule-based description admits a simple logical interpretation that can inform decisions. This method is designed for labeled data where each input feature has a distinct meaning that may or may not be related to the output, and the …

Kakeya Sets Over The Heisenberg Group, Gabriel Jacob Gress

Mathematics & Statistics ETDs

The Hausdorff dimension of Kakeya sets is an interesting problem where the two-dimensional case can be proven directly, but even obtaining bounds on the higher dimension analogues can require highly technical machinery. The difficulty of the general case has inspired analysts to look at Kakeya sets from non-Euclidean viewpoints.

In this paper, we explore a construction of the Kakeya set in the first Heisenberg group H^1. By utilizing the sub-Riemannian manifold of H^1 we can apply tools in geometric measure theory which at this time cannot be applied in R^3. We restate and provide a detailed proof for a sharp …

On Sharpest Tail Bounds For Functions Of Tail Bounded Random Variables, Stephen Harrison

Mathematics & Statistics ETDs

Consider n real/complex, independent/dependent random variables with respective tail bounds and g a measurable function of the r.v.’s. Consider f the “sharpest” tail bound of g (sharpest in the sense, if f were any less, then for some X1, ..., Xn satisfying the conditions, g(X1, ..., Xn) would not satisfy the tail f). Significant research has been done to approximate f often with high accuracy. These results are often of the form, for g in this family, and tail bounds of Xk in this family, f is bounded by some f′ with high accuracy. However, the question “what would it …

Improving The Electrochemical Properties Of Mno2 By Doping With Fe For Water Splitting And Supercapacitor Application, Joseph Okwe

Electronic Theses & Dissertations

An Abstract of the Thesis by

Joseph Okwe

These days when the issue of energy is talked about, it is usually more than just the usefulness of different types of energy. This topic now encompasses ways of generating and storing energy in the most efficient and sustainable way. For this reason, various research has shown that materials that are fabricated for the purpose of energy storage and conversion also find applications in other areas such as water splitting and supercapacitors. And so certain materials, when synthesized, can serve more than one purpose in either generating or storing energy. This project …

Dense Temporary Array Investigation Of Jemez Uplift Seismicity, Jillian D. Podmore

Earth and Planetary Sciences ETDs

A protracted multi-stage tectonic and magmatic evolution combined with low regional crustal strain rates make it challenging to characterize active structure that may host earthquakes in the Jemez Mountains of New Mexico. Here, we leverage temporary 1-month deployments of nodal seismometers to gain new insights into seismicity of the Jemez Mountains, which only have continuous seismic monitoring on their eastern flank as a result of the Los Alamos Seismic Network. Our catalog is built using 4 steps: phase picking in continuous seismic data, association of picks to detect unique events, event magnitude estimation, and absolute hypocenter estimation. We detect and …

Seismological Investigations Of Magmatic Systems Using Dense Nodal Arrays, Wenkai Song

Earth and Planetary Sciences ETDs

Understanding the internal architecture of magmatic systems is crucial for volcanology, yet conventional geophysical techniques often lack the resolution to image their fine-scale structures. This dissertation leverages unique datasets from dense nodal arrays to investigate the upper crustal magmatic systems beneath Yellowstone Caldera, Valles Caldera, and Mount St. Helens. At Yellowstone, I processed vibroseis data to delineate the top of the modern magma reservoir and evaluate the thermal connection between the magmatic and the overlying hydrothermal systems. At Valles, 3D radial seismic anisotropy imaging reveals strong positive radial anisotropy within the reservoir, indicating an organized structure of horizontally sill-like melt …

A Comprehensive Study Of Clique Graphs And Clique Regular Graphs, Connor Phillips

Senior Honors Projects, 2020-current

If Γ is a graph for which every edge is in exactly one clique of order ω, then one can form a new graph with vertex set equal to these cliques.  This is a generalization of the line graph of Γ.  We discover many general results and classifications related to these clique graphs that will be useful to researchers studying graphs with this property. In particular, we find bounds on the spectrum of Γ (with exact results when Γ is k-regular) and some complete classifications when Γ is strongly regular. We apply our results to derive novel information about the …

Contemporary Martian Geomorphic Processes And The Suitability Characterization Of Terrestrial Analogues, Daniel Paul Mason

Earth and Planetary Sciences ETDs

Both historical and contemporary evidence for geomorphic activity on the surface of Mars is apparent. This evidence is showcased by features including a) well-preserved deltaic remnants in an otherwise cold and arid environment, present along the western flank of Jezero Crater, and b) the seasonal appearance of candidate recurring slope lineae throughout Martian equatorial, lower, and mid-latitudes as seen within both the Eos Chasma region and on the walls of Raga, Lohse, Rauna, and Tivat Craters. In this dissertation, I elucidate the role that geomorphic processes, whether aqueous or dry, have played in shaping both the ancient and contemporary Martian …

Modeling Mineral Redistribution In Biological Tissue Using Apple As An In Vitro Analogue, Daler Djuraev, Ali Algemsh, Halima Alazeb, Zeenia Ahmed

Publications and Research

This project aims to model mineral (ion) redistribution that occurs in human soft tissue after injury or mechanical/thermal stress. Because direct, repeatable in vivo measurements are difficult, we use apples as an in vitro analogue: their mineral content is relatively uniform and the tissue can be cut, dried, and repeatedly imaged under controlled conditions. Using X-ray imaging, we tracked how minerals in apple tissue move toward damaged regions immediately after cutting, and how subsequent drying at room temperature drives a redistribution toward the central core. We also observed that biological degradation (decay) alters mineral density over time, indicating that even …

Assessment Of Fish Community Dynamics, Movement, And Morphology In Relation To Stream Barriers In The Upper Illinois Bayou Watershed, Risa Mccollough

ATU Theses and Dissertations 2021 - Present

Intermittent streams are increasingly recognized as vital components of river networks by supporting dynamic fish communities shaped by variable hydrology and habitat connectivity. They are becoming increasingly vulnerable to fragmentation by anthropogenic activities, namely road crossings, dams, and climate shifts that intensify seasonal drying. In response, I conducted two studies in the Illinois Bayou watershed in Arkansas to assess the effects of fragmentation on fish community dynamics and morphology in intermittent streams.

In the first study, I examined temporal fish community dynamics across two barriers: a natural waterfall in Dare Creek and a low-water crossing in Dry Creek. Simultaneously, I …

Health Implications Of Heavy Metal Contamination In Commercially Available Deodorant And Antiperspirant Products Sold In Benghazi, Libya, Maysson Yaghi, Khaled Elsherif

Al-Bahir

The extensive usage of deodorants and antiperspirants raises concerns about the potential health risks posed by heavy metal content. This study quantified the levels of five heavy metals: Aluminum, Zirconium, Lead, Cadmium, and Chromium in 22 commercial products widely used in Benghazi, Libya, and assessed the associated health risks. Samples, categorized into gel, stick, and roll-on formulations, were analyzed using iCAP TQ ICP-MS. Al and Zr showed the widest concentration ranges, reflecting their intentional use as active ingredients. Al levels ranged from trace amounts (0.032 mg/kg) up to a maximum of 99.10 mg/kg, while Zr was found exclusively in gel …

Adapting Master’S-Level Chemistry Education In The United States: Insights From Industry, Academia, And The Literature, Brian Johnson, Amanda Lindell, Nina M. Goodey

Department of Chemistry and Biochemistry Faculty Scholarship and Creative Works

As the chemical industry evolves in response to technological and global challenges, Master’s-level chemistry programs must adapt to prepare graduates for workforce success. This article explores how such programs can better integrate professional skills such as communication, collaboration, and research. Drawing on literature and stakeholder interviews from a review of the Chemistry M.S. and Pharmaceutical Biochemistry M.S. programs at Montclair State University, a Hispanic Serving Institution in New Jersey’s pharmaceutical hub, we identified four key themes: the importance of hands-on research experiences, the integration of professional skills development, the need for flexible course and credit requirements, and the challenges of …

Decarbonizing California Wine: Navigating Scope 3 Emissions Challenges And Opportunities, Olivia Regalia

Master's Projects and Capstones

Climate change is already impacting the California wine industry through increases in extreme weather, such as prolonged heatwaves and atmospheric rivers. For the industry to survive, it is important for California wineries to mitigate the effects of climate change and adapt to current and future impacts. Scope 3 greenhouse gas emissions (i.e., emissions generated throughout the supply chain) from glass packaging make up 29% of a typical California winery's carbon footprint, representing both the largest Scope 3 climate impact and greatest opportunity for reductions. This research examined key factors shaping California wineries’ Scope 3 emissions reductions efforts. A mixed-methods approach …

Microbial Metabolism Amplified Warming In Three Phanerozoic Hyperthermal Events, Yuyang Wu, Haijun Song, Daoliang Chu, Ying Cui, Jacopo Dal Corso, Genming Luo, Huyue Song, Li Tian, Hanchen Song, Enhao Jia, Jinnan Tong

Department of Earth and Environmental Studies Faculty Scholarship and Creative Works

The ocean’s biological carbon pump (BCP) plays a crucial role in climate regulation by facilitating long-term removal of atmospheric CO2. However, BCP changes during past hyperthermals remain poorly understood. Here we use the vertical carbon isotope (δ13C) gradients between surface and mid-waters to trace the BCP changes during the Permian−Triassic, early Toarcian, and Palaeocene−Eocene hyperthermals, detecting a two- to three-fold increase in the vertical δ13C gradients. We found that enhanced organic matter remineralization, driven by increased microbial respiration under warming, are the primary trigger for increased vertical δ13C gradients. Warming-induced enhancements in microbial metabolism caused a two- to six-fold reduction …

Developing An Ai-Assisted Grading System Using Large Language Models, Andrei Modiga

MS in Computer Science Project Reports

We present a grading system that accelerates evaluation of open-ended student work across scanned and digital workflows. The system crops answer regions from PDFs, assigns submissions via OCR on identity regions only, and groups answers by visual semantics using a vision LLM. Instructors review and edit groups, apply rubric items once per group, and export grades from an on-screen table. The solution integrates Ghostscript rasterization, PdfPig page orchestration, SkiaSharp region extraction, Tesseract identity OCR, and GPT-4o Vision for grouping. We detail the architecture, token-budgeted batching strategy, and persistence design, then describe testing results for grouping quality, time-on-task, and usability. The …

Constructing Genotype And Phenotype Network Helps Reveal Disease Heritability And Phenome-Wide Association Studies, Xuewei Cao, Lirong Zhu, Xiaoyu Liang, Shuanglin Zhang, Qiuying Sha

Michigan Tech Publications

Background

Analyses of a bipartite Genotype and Phenotype Network (GPN), linking the genetic variants and phenotypes based on statistical associations, provide an integrative approach to elucidate the complexities of genetic relationships across diseases and identify pleiotropic loci. In this study, we assess contributions to constructing a well-defined GPN with a clear representation of genetic associations by comparing the network properties with a random network, including connectivity, centrality, and community structure. Then, we extend our discussion to include two applications of bipartite GPN in disease heritability enrichment analysis and phenome-wide association studies (PheWAS).

Results

We construct network topology annotations of genetic …

Free Probability Theory Over The Scaled Hyperbolic Numbers, Daniel Alpay, Ilwoo Choo

Mathematics, Physics, and Computer Science Faculty Articles and Research

In this paper, we introduce a notion of free probability over the scaled hyperbolic numbers. Scaled hypercomplex numbers {D_t} _t∈R are constructed as sub-structures of scaled hypercomplex numbers {H_t} _t∈R under the scales (or, the moments) of the set R of real numbers.We show that if t < 0, then the classical free probability theory covers our free probability on {D_t} _{t< 0}; if t > 0, then our free probability on {D_t} _t>0 is represented by the free probability over the classical hyperbolic numbers D = D₁; and if t = 0, then the free probability on D₀ is actually over the …

Flooding Behavior Near The Us/Canada Border: Complications And Approaches, Maria T. Dodson

Honors College Theses

Flood forecasting remains a major challenge due to the nonlinear nature of hydrological systems and uncertainties in environmental data. This study aimed to address the prevalent challenges that arise from forecasting flooding behavior. To address the inherent complexity of hydrological forecasting, a machine learning framework was developed and trained on major contributing factors. To achieve an optimal balance between computational efficiency and predictive performance, a Gated Recurrent Unit (GRU) was selected as the optimal machine learning model. As the chosen dataset, North American Land Data Assimilation System Phase 2 (NLDAS2), is known to have inaccuracies in the important feature Relative …

Mississippi River Pre-Loess Terrace Deposits: Distribution Of Aggregate Resources, Jonathan Leard

Theses and Dissertations

Pre-loess Terrace Deposits are a Pleistocene, high-quality aggregate resource of gravel, sand, and clay subjacent to loess of varying thickness along the eastern valley wall of the Yazoo Basin in Mississippi. This project delineated 1,230 mi2 of this resource with a volume greater than 33 billion yd3 from the misinterpreted Citronelle Formation in Desoto, Tate, Marshall, Panola, Tallahatchie, Yalobusha, Grenada, Carroll, Holmes, Yazoo, Madison, Hinds, Warren, Jefferson, Claiborne, Adams, Franklin, and Wilkinson Counties with nine terrace base levels at 40, 180, 220, 250, 270, 300, 330, 340, and 370 feet msl indicated by test holes, gravel mine data, outcrop studies, …

Application Of Augmented Reality Technology As A Dietary Monitoring And Control Measure Among Adults: A Systematic Review, Gabrielle Victoria Gonzalez, Bingjing Mao, Ruxin Wang, Wen Liu, Chen Wang, Tung Sung Tseng

School of Public Health Faculty Publications

Background/Objectives: Traditional dietary monitoring methods such as 24 h recalls rely on self-report, leading to recall bias and underreporting. Similarly, dietary control approaches, including portion control and calorie restriction, depend on user accuracy and consistency. Augmented reality (AR) offers a promising alternative for improving dietary monitoring and control by enhancing engagement, feedback accuracy, and user learning. This systematic review aimed to examine how AR technologies are implemented to support dietary monitoring and control and to evaluate their usability and effectiveness among adults. Methods: A systematic search of PubMed, CINAHL, and Embase identified studies published between 2000 and 2025 that evaluated …

Toward A Unified Network Flow Framework: From Conservation Principles To Fluid Dynamics Models, Zonghan Zhang

Theses and Dissertations

Network flows govern a wide range of critical systems, from tangible infrastructures like transportation and power grids to replicable processes such as information spread and epidemics. While tangible flows obey conservation laws and physical constraints, replicable flows, like rumors or viruses, can grow, decay, or vanish unpredictably. Despite their increasing interaction in real-world settings, these flow types are typically modeled in isolation, using disconnected mathematical frameworks. This dissertation presents a unified modeling approach that bridges the gap between conserved and replicable flows by embedding principles from fluid dynamics into graph-based propagation models. I introduce physically informed extensions to classical models, …

The Effects Of Nanobubble Fertigation And Soil Conditioners To Improve Nutrient Dynamics, Soil Microbial Activity, And Chili Productivity, Betty Natalie Fitriatin, Euis Ahah Rokayah, Elsa Naila Elmyra, Tualar Simarmata, Nicky Oktav Fauziah, Hanif Fakhrurroja

Jurnal Kultivasi

Drip fertigation is a fertilization method that integrates nutrient delivery with an irrigation system, which is capable of optimizing the direct delivery of nutrients to the root zone. This experiment aims to investigate the effect of drip fertigation with nanobubble technology, and soil conditioners on the population of Phosphate-Solubilizing Bacteria (PSB) and Azotobacter spp., available phosphorus, total nitrogen, growth, and yield of red chili. The study used a Strip Plot Design with two factors and three replications. The first factor was nutrient application (solid NPK fertilizing as control; drip fertigation; and drip fertigation with nanobubble technology), and the second factor …

Using Quantum Annealing For Sampling And Pattern Generation In Generative Machine Learning And Catastrophic Forgetting Mitigation, Abdelmoula El Yazizi

Theses and Dissertations

The first goal of this dissertation was to understand the reasons for the absence in previous investigations of significant and consistent improvements in the trainability of Restricted Boltzmann Machines (RBM) when the Quantum Annealer (QA) was used for sampling from the RBM probability distribution. The second goal was to address the shortcomings of those previous investigations, explore possibilities of improving RBM training, and identify other machine learning applications that could benefit from sampling or from generating patterns by the QA. The first part of this dissertation focused on a Local-Valley (LV) centered approach to assessing the quality of sampling. QA-based …