Digital Commons Network^™

Generative Ai In Enterprises: Optimizing Applications With Large Language Models, Donghao Huang

Dissertations and Theses Collection (Open Access)

This dissertation investigates how to deploy Large Language Models (LLMs) effectively in enterprise settings, where accuracy, reliability, cost, privacy, and operational constraints often matter more than benchmark performance alone. Drawing on seventeen peer-reviewed publications (eleven published and six accepted for publication), the work develops and validates optimization strategies across three connected themes: retrieval-augmented generation (RAG), agentic AI for workflow automation, and deployment guidelines for real-world enterprise environments.

First, we study RAG optimization through systematic evaluation of open and proprietary models, highlighting conditions under which efficient open-weight models can match or exceed proprietary alternatives. To address a pervasive failure mode in …

Explainable Artificial Intelligence In The Image Domain And Its Applications To The Medical Field, Mirtha Lucas

Theses and Dissertations from DePaul University

This dissertation investigates the development of Explainable Artificial Intelligence (XAI) methods for deep learning models in the image domain, with a particular focus on medical imaging applications. Although neural networks achieve high predictive performance, their lack of interpretability limits their adoption in critical domains such as healthcare, where transparency and trust are essential. This work addresses this challenge by proposing novel approaches that improve the interpretability and reliability of model predictions.   A primary contribution is the introduction of Riemann–Stieltjes Integrated Grad-CAM (RSI Grad-CAM), a gradient-based attribution method that generates more relevant and spatially localized saliency maps. The method is evaluated …

Implementation And Costs Of A Food Insecurity Resource Navigation Program For Primary Care Patients With Diabetes And Hypertension In South Carolina, Deeksha Gupta, Darin Thomas, Stella Coker Watson Self Ph.D., Ms, Edward A. Frongillo Jr. Ph.D., Alain H. Litwin, Joseph A. Ewing, Lynnette Ramos-Gonzalez, Lynnette Ramos-Gonzalez

Faculty Publications

Objective

To examine food insecurity resource navigation program costs and how navigation intensity relates to clinical outcomes, healthcare costs, and quality of life (QOL) for diabetes and/or hypertension patients.

Methods

This retrospective study included patients receiving resource navigation (July 12, 2021-December 31, 2022 with twelve-month follow-up) across three primary care practices in South Carolina's largest health system. Participants were 18+ years old (from electronic medical records/Epic), had food insecurity (from Hunger Vital Sign™), and diabetes and/or hypertension (from Epic registries). Matched controls came from food insecurity screening-only practices. Patients in each group (n= 219) had diabetes (9.13%), hypertension …

Math 242: Elements Of Probability And Statistics (Syllabus), Ahmad Almomani Ph.D.

School of Arts & Sciences

This syllabus was developed by SUNY Geneseo Professor Ahmad Almomani during the spring 2026 semester.

Course Objectives:

Upon successful completion of Math 242, R/Elements of Probability and Statistics, a student will be able to: 

• Organize, present and interpret statistical data, both numerically and graphically; 
• Use various methods to compute the probabilities of events; 
• Analyze and interpret statistical data using appropriate probability distributions, e.g. binomial and normal. 
• Apply central limit theorem to describe inferences; 
• Construct and interpret confidence intervals to estimate means, standard deviations and proportions for populations; 
• Perform parameter testing techniques, including single and multi-sample tests for means, standard deviations …

Statistical Investigation Project, Ahmad Almomani Ph.D.

School of Arts & Sciences

The assignment was developed by SUNY Geneseo Professor Ahmad Almomani for the course, MATH 242: Elements of Probability and Statistics in the spring 2026 semester.

The objective for this assignment is that students will apply statistical methods to analyze real-world data and communicate meaningful conclusions.

Discovery Of A New Cataclysmic Variable, Galex J211240.9–422959, Via The Exoasteroids Citizen Science Project, Mei Lin, Aaron Meisner, Siyi Xu, Arttu Sainio, Liliana E. Rivera Sandoval, Paula Szkody, Christopher Tanner, Laura K. Rogers, Sarah Casewell, Austin Humphreys

Physics & Astronomy Faculty Publications

We report the discovery and spectroscopic classification of a new cataclysmic variable (CV), GALEX J211240.9–422959 (Gaia DR3 source ID 6580244356829724928). This object was initially identified as a source exhibiting strong mid-infrared variability in Wide-field Infrared Survey Explorer (WISE) time-series data by a volunteer participating in the Exoasteroids citizen science project. Prompted by this strong variability at 3–5 μm, we obtained a follow-up optical spectrum using the Gemini Multi-Object Spectrograph at the Gemini South Observatory. The resulting spectrum displays a blue continuum dominated by strong, broad emission lines of the hydrogen Balmer series and neutral helium, spectral signatures characteristic of …

Do Purpleair Monitors Democratize Data For The Environment?, Christopher Rick, Kyla Lorden

Student Publications

PurpleAir monitors may serve a vital role in marginalized or under-monitored communities nationwide. These low-cost monitors—roughly $300—give communities the ability to monitor their air quality at local geographies in ways that are infeasible for expensive, regulatory-grade air monitors. They also have the potential to aid community advocacy efforts around environmental and transportation policy by giving community members literal ownership over the monitoring, including precise locations, and philosophical ownership over the advocacy efforts. To determine the potential democratization of air quality data by PurpleAir monitors in socially disadvantaged communities, we analyze the sociodemographic characteristics of neighborhoods with PurpleAir monitors. We find …

The Importance Of Body Size And Spatial Scale In Modeling Winter Bird Distributions, Carissa M. Mobley

Student Publications

Birds’ annual cycles include biologically linked breeding and non-breeding seasons, yet most research and bird atlases focus exclusively on the breeding season. There have been very few winter bird atlas projects in North America, and none have been published for the northeastern United States. Short daylight hours and harsh weather limit winter survey coverage, making species distribution models (SDMs) essential for addressing spatial gaps.

I evaluated the optimal spatial scale for SDMs across bird species differing in body size and tested whether optimal scale varies with body mass. Using 16,967 eBird checklists collected during the first winter survey period (December …

Interspecific Overlap In Seabird Diet Throughout The Breeding Season, Alexis V. Berkey

Student Publications

Seabirds are central-place foragers that breed in multi-species colonies, providing an opportunity to study species coexistence. I quantified interspecific competition among four seabird species (common terns Sterna hirundo, Arctic terns Sterna paradisaea, Atlantic puffins Fratercula arctica, black guillemots Cepphus grylle) breeding in the Gulf of Maine in 2022, 2024, and 2025. I hypothesized that, throughout the breeding season, 1) seabird diet would change and 2) interspecific overlap in diet would increase. I compared diets across species and time using direct observation of prey feeds and stable isotope values of seabird egg membranes and blood, which provide …

Draft 2025 Butte Priority Soils Operable Unit Residential Metals Abatement Program Construction Completion Report, Abby Peltomaa

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

The Eye: A Science-Fiction Screenplay Examining Space-Time, Meteorology, And Human Connection, Ella K. Lukowiak

Senior Theses

This thesis explores the nature of time, meteorology, and human interconnection to the universe through the lens of a science-fiction screenplay. The creative project spans a three-act, detailed outline, and a screenplay draft of Act I. It is based upon extensive scientific research regarding hurricane development, the inner workings of organizations such as the National Weather Service, Einstein’s Theory of Relativity, and the space-time continuum. I will delve into the various factors that shaped my science-fiction premise, including pivotal films such as Christopher Nolan’s INTERSTELLAR (2014) and Denis Villeneuve’s ARRIVAL (2016). Both of these filmmakers integrated complex science-fiction concepts into …

Exploring The U.S. Public Service Employees’ Experiences With Gamified Cybersecurity Awareness Training, Bisola Adepoju

Human Resource Development Theses and Dissertations

The purpose of this qualitative study was to explore the U.S. public service employees' experiences with gamified cybersecurity awareness training. The primary research question guiding this inquiry was: How do U.S. public service employees make sense of their lived experiences with gamified cybersecurity awareness training? Two secondary questions examined what aspects of the training employees perceive as meaningful or disengaging, and how they interpret their motivation, engagement, and cybersecurity awareness during training. I chose an interpretive qualitative research design grounded in a constructivist paradigm and purposefully selected 11 U.S. public service employees who had participated in gamified cybersecurity awareness training. …

Leveraging Section 208 Water Quality Planning To Mitigate Pfas Contamination In Watersheds Across The Waccamaw Region, Anna Dimatteo

Goal 6: Clean Water and Sanitation

No abstract provided.

Personality Predictors Of Cybersecurity Vulnerability: Insights From Self-Reports And Stimulated Threat Scenarios, Saroja Roy Grandhi

Psychology Theses & Dissertations

In this cyber dependent and enabled era, understanding the role of human factors in digital security is essential. This study investigates the relationship between Big-Five personality traits and cybersecurity behaviors by examining both self-reported and stimulated behaviors in security threat scenarios. Participants completed validated questionnaires to report their personality traits, cybersecurity practices and engage in task-based stimulations to capture behaviors such as phishing detection, password creation, and response to security alerts. The study tested whether higher conscientiousness, openness, and agreeableness would be associated with stronger cybersecurity practices and smaller discrepancies between self-reported and observed behaviors. And, whether greater extraversion and …

Ai-Assisted 3d Pre-Visualization: Streamlining Animatics For Filmmakers, Nishit Thapa

Honors Theses

Pre-visualization is a core part of film pre-production. Creators use it to test blocking, lighting, camera movement, and spatial relationships before committing to a shot. Despite this, three-dimensional pre-visualization remains out of reach for many entry-level filmmakers, as the software is expensive and takes substantial time to learn.

Recent AI developments have produced generative systems capable of creating highly re-alistic imagery and video from text prompts. These systems open new possibilities for visual sto-rytelling but are not built for the iterative, hands-on process that pre-visualization requires, where creators must adjust scene parameters, camera logic, and spatial configurations throughout.

This thesis …

Deep Learning-Based Automated Pneumonia Detection From Chest X-Rays: A Comparative Study Of Custom Cnn And Transfer Learning Architectures, Ahmed Sajim

Honors Theses

Pneumonia is a leading global cause of mortality, claiming approximately 2.5 million lives an-nually and placing exceptional diagnostic pressure on radiologists in resource-limited settings. Manual interpretation of chest X-ray (CXR) images is time-consuming, subject to inter-observer variability, and limited by radiologist availability. This thesis presents a systematic investiga-tion into deep learning-based automated pneumonia detection comparing five convolutional neural network (CNN) architectures: a custom-designed 2D CNN and four pretrained transfer learning models—ResNet, DenseNet, MobileNet, and VGG19.

A targeted data augmentation pipeline addresses the severe class imbalance in the Kag-gle Chest X-Ray Pneumonia dataset, expanding the Normal class from 1,583 to 9,495 …

Generative Artificial Intelligence With A Human Touch: Building Hana, Conrad Johnson

Faculty Scholarship

This Essay examines how generative artificial intelligence (GenAI) can be integrated into legal education and public interest law practice in a way that meaningfully enhances — rather than diminishes — human judgment, professional responsibility, and access to justice. Drawing on the experience of Columbia Law School’s Lawyering in the Digital Age Clinic, the Essay situates GenAI within an experiential pedagogy that emphasizes competence, ethical awareness, and collaborative problem-solving. It argues that law students and lawyers must move beyond a passive or uncritical use of GenAI tools; toward a deeper understanding of how these systems operate, the risks they pose, and …

Understanding Codebase Like A Professional! Human-Ai Collaboration For Code Comprehension, Jie Gao, Yue Xue, Xiaofei Xie, Junming Cao, Soemin Thant, Erika Lee, Bowen Xu

Research Collection School Of Computing and Information Systems

Understanding an unfamiliar codebase is an essential task for developers in various scenarios, such as during the onboarding process. Especially when the codebase is large and time is limited, achieving a decent level of comprehension remains challenging for both experienced and novice developers, even with the assistance of large language models (LLMs). Existing studies have shown that LLMs often fail to support users in understanding code structures or to provide user-centered, adaptive, and dynamic assistance in real-world settings.To address this, we propose learning from the perspective of a unique role, code auditors, whose work often requires them to quickly familiarize …

Fully Decentralized Hierarchical Federated Learning At The Edge With Post-Quantum Secure Communication, Tariq Qayyum

Dissertations

Federated learning (FL) enables collaborative model training without centralizing raw data, but deploying FL at scale in real edge environments remains challenging because iterative training and aggregation must operate over heterogeneous, resource-constrained, and often mobile devices with time-varying connectivity. Conventional hierarchical federated learning (HFL) partially mitigates communication cost by introducing fog/edge aggregation, yet many designs retain cloud-based global aggregation and cloud-centric coordination. This places wide-area network latency on the critical path of every training round, creates a single point of failure, and limits responsiveness as model sizes and federation scale grow. Moreover, moving coordination and aggregation closer to the edge …

Rethinking Artifact Evaluation For Software Engineering In The Age Of Generative Ai, Christoph Treude, Christopher M. Poskitt, Rashina Hoda

Research Collection School Of Computing and Information Systems

Peer review in software engineering research operates under tight time constraints, while generative AI has substantially reduced the human effort required to produce polished research narratives. Reviewer attention is often spent on aspects of submissions such as writing quality or literature positioning that have become relatively less effort-intensive to address, rather than on evaluating the scientific substance of a paper. At the same time, assessing whether methods are implemented correctly, analyses are sound, and claims are supported by evidence remains effort-intensive and dependent on human expertise. In software engineering research, this substance is frequently embodied in artifacts, including code, data, …

Federated Retrieval-Augmented Generation For Cybersecurity In Resource-Constrained Iot And Edge Environments: A Deployment-Oriented Scoping Review, Hangyu He, Yuan, Kai Wu, Wei Ni

Research outputs 2022 to 2026

Cybersecurity operations in IoT and edge environments require fast, evidence-grounded decisions under strict resource and trust constraints. While large language models can support triage and incident analysis, their parametric knowledge may be outdated and prone to hallucination. Retrieval-augmented generation (RAG) improves grounding by conditioning responses on retrieved evidence, but also introduces new risks such as knowledge-base poisoning, indirect prompt injection, and embedding leakage. Federated learning enables collaborative adaptation without centralizing sensitive data, motivating federated RAG (FedRAG) architectures for distributed cybersecurity deployments. This study presents a deployment-oriented scoping review of FedRAG for cybersecurity. The review follows PRISMA-ScR reporting guidance and synthesizes …

Transport Of Quantum Walks In Electric Fields, Yousef Mohammad Yousef Salah

Theses

This thesis presents an analysis of transport in one-dimensional discrete-time quantum walks (DTQWs) on the Hilbert space ℓ²(ℤ) ⊗ ℂ². Quantum walks serve as fundamental models of coherent quantum transport and exhibit ballistic spreading driven by superposition and interference. The primary focus of this work is the review and derivation of sharp maximal velocity bounds for several classes of quantum walk step operators, including the shift-coin walk, the split-step walk, and models with constant as well as position-dependent coin operators. We establish general a priori bounds that remain valid beyond the translation-invariant regime. For homogeneous models, Fourier and spectral analysis …

Trustgen: A Platform Of Dynamic Benchmarking On The Trustworthiness Of Generative Foundation Models, Yue Huang, Et. Al

Research Collection School Of Computing and Information Systems

Generative foundation models (GenFMs), such as large language models and text-to-image systems, have demonstrated remarkable capabilities in various downstream applications. As they are increasingly deployed in high-stakes applications, assessing their trustworthiness has become both a critical necessity and a substantial challenge. Existing evaluation efforts are fragmented, rapidly outdated, and often lack extensibility across modalities. This raises a fundamental question: how can we systematically, reliably, and continuously assess the trustworthiness of rapidly advancing GenFMs across diverse modalities and use cases? To address these gaps, we introduce TrustGen, a dynamic and modular benchmarking system designed to systematically evaluate the trustworthiness of GenFMs …

Intelligent Deep Learning-Based Sign Language Translation System, Nada Rasem Shahin

Dissertations

The Deaf and Hard of Hearing (DHH) community uses sign language as a primary means of communication. However, the shortage of sign language interpreters and the existence of hundreds of sign languages limit accessibility and inclusion. Sign Language Machine Translation (SLMT) systems present a promising solution for bridging the communication gap between the DHH and the hearing individuals, supporting inclusive societies. In smart cities, such systems play an essential role in improving the quality of life on a community level. In particular, as the population’s well-being is critical, developing intelligent assistive technologies, such as SLMT systems, is necessary to provide …

Application Of The Tridiagonal Representation Approach And The J- Matrix Method Of Scattering In Theoretical Physics, Tunde Joseph Osunmusanmi

Dissertations

This dissertation is about the application of the Tridiagonal Representation Approach (TRA) in handling linear phenomenons, and for the first time, the J-matrix method of scattering in handling nonlinear phenomenons. The TRA is an algebraic method for solving linear ordinary differential equations of the second order. The advantage of the method in being algebraic is reinforced by the analytic power of orthogonal polynomials and special functions. On the computational side, it is favored as being reliant on powerful numerical techniques that deal with tridiagonal matrices such as Gauss quadrature and continued fraction. In the method, the solution of the differential …

A Comparative Study On Performance Of Iot-Driven Ml-Enabled Forecasting Models For Efficient Air Quality Monitoring, Bara Ksiksi

Theses

Air pollution is one of the most critical environmental challenges affecting public health globally, responsible for approximately 4.2 million premature deaths annually according to the World Health Organisation. This thesis presents a comparative study of IoT-driven machine learning forecasting models for air quality monitoring in Abu Dhabi, UAE, introducing a zonal approach combined with satellite-based spatial validation. The primary objective is to evaluate forecasting performance across three distinct activity zones using ground station data from the Environment Agency Abu Dhabi (EAD), and to incorporate a spatial validation component using satellite imagery to assess the consistency of ground-based predictions at a …

Ideals And Lattices In Number Fields, Sarah Ali Alyammahi

Theses

This thesis investigates algebraic number fields and their rings of integers, which

generalize the ring of integers ℤ in ℚ. The study focuses on ideals, units, and ideal class

groups, which describe the arithmetic structure of number fields and the failure of unique factorization. Key invariants such as the norm, trace, and discriminant are developed and applied, with particular emphasis on quadratic number fields and classical examples such as the Gaussian and Eisenstein integers. Some explicit computations of ideal class groups are carried out. The thesis also explores connections with lattice theory by interpreting rings of integers as lattices and …

Draft Final 2025 Bpsou Subdrain Data Summary Report (Dsr), Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Pushing High-Performance Private Inference Towards Resource-Constrained Edge Clients, Xiangrui Xu

Computer Science Theses & Dissertations

The widespread adoption of Machine Learning as a Service (MLaaS) has enabled resource constrained edge clients, such as mobile and IoT devices, to leverage powerful deep learning mod els hosted on the cloud. However, this paradigm introduces critical privacy challenges regarding the client’s sensitive input data and the server’s proprietary model parameters. While cryptographic techniques like Homomorphic Encryption (HE) and Multi-Party Computation (MPC) enable Private Inference (PI), existing frameworks impose prohibitive computational and communication overheads that render them impractical for edge deployment. This dissertation introduces three novel frameworks—SPOT, LUTless, and PrivShap—to systematically address the efficiency bottlenecks of PI in edge …

Advancing Paleontologic Mapping: A Gis And Drone Photogrammetry Approach To The Lance Formation Beds Of Glenrock, Wyoming, William H. Steelman, Monika Angner, Norman S. Levine, W S. Persons

The Compass: Earth Science Journal of Sigma Gamma Epsilon

Small museums and volunteer-driven field programs often lack the resources required for detailed geological mapping, limiting the stratigraphic data associated with their fossil collections. To address this challenge, an affordable and replicable mapping workflow was developed that combined drone-based photogrammetry, GIS analysis, and targeted structural measurements using the Glenrock Exposure of the Lance Formation as a study site. The resulting 3D outcrop models, bedding-plane reconstructions, and 750-m-thick stratigraphic column provide the first comprehensive spatial framework for 35 fossil quarries curated by the Glenrock Paleon Museum. The results reveal tightly clustered fossil-bearing horizons, a long interval lacking preservation, and a notable …