Digital Commons Network^™

Optimizing Gated Rnns, Joshua Paul Fechete

Honors Projects

Gated recurrent neural networks such as Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) help fix instability present in normal recurrent neural networks. This allows them to be used for various real-world tasks, and due to their architecture, they are uniquely qualified to handle variable sized input such as text. However, even before training can begin on a machine learning model, various hyperparameters must be chosen to decide how the model will be architectured. Choosing good hyperparameters is vital for creating a model that performs well but is not larger and more computationally expensive to run than it needs …

Second Annual Advances In Business Education Conference 2026 Proceedings, Kelsey Metz

Advances in Business Education (ABE) Conference Proceedings

Conference Overview: The Second Annual Advances in Business Education (ABE) Conference was held on May 21–22, 2026, at Lincoln Memorial University in Harrogate, Tennessee. Hosted by the LMU School of Business, the ABE Conference exists to promote teaching excellence, scholarly inquiry, and regional engagement through innovation and collaboration in business education.

With a focus on fostering meaningful dialogue among educators, researchers, students, and industry professionals, the conference welcomed more than 70 attendees representing 11 institutions from across the Appalachian region and beyond.

The event was structured around four key tracks:

Pedagogy and Teaching Excellence: Showcasing innovative teaching methods, instructional technologies, …

Modeling Of Penicillin Fermentation Process Based On A Multi-Stage Lhs-Eprcc Method, Quan Li, Peng Su, Haiying Wan, Chengxi Zhang, Zhijian He, Yiyang Ni

Journal of System Simulation

This paper focused on the modeling of microbial fermentation processes under varying production environments and proposed a novel approach. Considering that the dynamic characteristics of microorganism s differ across growth stages, we introduced the concept of multi-stage sensitivity analysis, in which each stage was investigated separately. The fuzzy C-means (FCM) algorithm was employed to cluster process data under nominal conditions, thereby dividing the penicillin fermentation process into distinct growth stages. Based on this division, the Latin hypercube sampling with partial rank correlation coefficient (LHS-EPRCC) method was applied to conduct sensitivity analysis for each stage, identifying an importance parameter set (IPS) …

Power Flow Calculation Based On Block-Encoded Adiabatic Quantum Newton-Raphson Method, Shengchao Jiang, Yunqing Pei, Hongying Zhai, Guojian Wu, Fang Gao

Journal of System Simulation

To overcome the efficiency bottleneck of the traditional Newton-Raphson (NR)method in high- dimensional power flow calculations for modern power systems and the constraints of variational quantum algorithm frameworks, this paper proposed a power flow calculation framework integrating block encoding technology and adiabatic quantum computing principles. Based on block encoding technology, adiabatic quantum theory, and the NR method, a block-encoded adiabatic quantum power flow calculation framework (BQ-NR) was constructed. The NR correction equations were mapped to a quantum system, and the quantum state encoding of the correction equations was realized by constructing an extended Hermitian matrix and a projection operator; a …

A Predictive Correlational Study Of User Acceptance Of Electronic Medical Record Systems In Nursing Higher Educational Institutions, Clara Awosika

Doctoral Dissertations and Projects

The purpose of this quantitative, predictive correlational study was to examine the extent to which perceived usefulness and perceived ease of use predict behavioral intention and actual usage of electronic medical record systems among nurses who have passed the National Council Licensure Examination for Registered Nurses. Using the Technology Acceptance Model, this study sought to address a gap in the literature regarding the level of user acceptance and utilization of EMR systems among nursing students during their training in higher education institutions. Participants included 85 actively licensed nurses who used EMR systems during their academic preparation. Data were collected using …

Storyteller: Training-Free Narrative Grounding And Forseebench: Evaluation For Long Form Audio Description, Seung Hyun Hahm

Dartmouth College Master’s Theses

Understanding long-form video requires tracking events, motivations, and relationships across time rather than describing isolated frames. However, existing video--language models (VLMs) and audio description (AD) systems often generate short-horizon descriptions that omit narrative context, causal intent, and story continuity, limiting accessibility for blind and low-vision (BLV) audiences. This thesis investigates how long-form AD can be grounded in narrative memory without relying on expensive supervised training pipelines or heavily curated annotations.

We propose StoryTeller, a training-free retrieval-augmented framework for long-form audio description. Instead of depending solely on frame-level perception, StoryTeller summarizes observations into structured narrative facts that capture who did what …

3d Puzzle Generation Beyond Voxelized Parts, Iris Xia

Computer Science Theses

Burr puzzles are interlocking assemblies whose pieces must be inserted and removed through tightly constrained motions. Designing them is difficult because geometric fit, interlocking behavior, and disassembly order are tightly coupled, while existing computational methods remain largely limited to voxelized or template-based constructions.

This work presents a framework for 3D puzzle generation beyond voxelized parts. The method replaces local mobility heuristics with a certified search over geometry edits. Starting from a topological contact specification, it constructs signed distance fields for individual parts, applies complementary local edits, and validates each candidate using exact geometric checks and a kernel disassembly graph. The …

Shaping Emergent Competitive And Cooperative Behaviors In Multi-Agent General-Sum Games, Ethan F. Erickson

Honors Projects

Reinforcement learning (RL) algorithms can train agents to solve problems in environments using complex behaviors that are not explicitly programmed, known as emergent behaviors. The goal of our research is to investigate how different RL reward values influence the emergence of competitive and cooperative behaviors in games with teams of multiple agents. Specifically, we focus on general-sum games, in which the sum of gains and losses of each team may be non-zero, allowing situations for agents to mutually benefit or mutually fail. Using Unity’s ML-Agents Toolkit to train agents with RL self-play in bounded 2D environments, we identify high-level behaviors …

Computing Certificates Of Members In Archimedean Quadratic Modules In A[X] And Certifying The Emptiness In Inconsistent Monogenic Archimedean Quadratic Modules In A[X_1, ..., X_N], Jose A. Castellanos Joo

Computer Science ETDs

Polynomials have been found to be a powerful tool over hundreds of years for modeling problems in numerous applications in science, engineering, medicine, and other domains. In the context of formal methods, polynomials arise in modeling in aerospace software and robotics, cyber-physical and hybrid systems, autonomous vehicles and controllers based on neural networks.

A quadratic module is a linear combination of polynomials in a set of generators (including the constant 1) with sum of squares polynomials as multipliers. The membership problem for a finitely generated quadratic module can be decided; however, computing a certificate exhibiting why it is nonnegative under …

From Sparse To Precise: Modeling Beam Profiles Using Wavelet-Based Implicit Neural Network (Winn) For Linear Accelerator Commissioning And Quality Assurance, Maryam Ali Albuainin

Computer Science ETDs

Commissioning and routine quality assurance (QA) in radiotherapy require extensive measurements using bulky water tank systems, making the process time-consuming and costly. This research proposes an efficient framework for radiotherapy commissioning and QA by generating complete LINAC physics data from sparse measurements and developing a portable solid-water detector with embedded diodes for high-resolution dosimetry.

At the core of the framework is a Wavelet-based Implicit Neural Network (WINN) that reconstructs full measurement datasets from limited inputs while maintaining clinical accuracy. The model achieves gamma passing rates above 95% (1%/1 mm) and mean absolute errors below 0.5%, while reducing parameters by 99.46% …

Classification Of Hif Detection In Nev Profile Using Wavelet Transform And Convolution Neural Network, Abdul Hafiz Kassim, Mohd Abdul Talib Mat Yusoh, Aster Smith Valentinie Wilson Nottelmarc, Ahmad Farid Abidin, Sim Sy Yi, Daw Saleh Sasi Mohammed

Turkish Journal of Electrical Engineering and Computer Sciences

High impedance faults (HIFs) present a critical challenge in power systems due to their subtle signal characteristics, which often remain undetected by conventional protection methods. These faults typically do not produce significant phase disturbances, making reliable detection difficult. However, analysis of the neutral-to-earth voltage (NEV) profile under fault conditions provides a promising alternative for fault identification. Existing approaches for detecting and classifying HIFs using NEV signals remain limited and may result in inaccurate maintenance decisions. This paper proposes a fault classification framework for multiple fault types, including HIF, three-phase fault, three-phase fault to ground, double line, double line to ground, …

Degrees Of Access: The Role Of Family Education In Applying To Graduate School, Emma Tweed

Math and Computer Science Honors Theses

Access to graduate education in the United States remains heavily stratified by structural, financial, and informational barriers. While undergraduate first-generation student outcomes are widely studied, fewer structural analyses examine how graduate-level “educational inheritance” shapes prospective applicants' navigational capital, particularly within competitive STEM fields like mathematics. Drawing upon theories of social capital and the “hidden curriculum,” this study investigates the relationship between an individual's knowledge of the graduate school application process and the highest level of education attained by an immediate family member.

Using the Knowledge-GAP survey instrument funded by the National Science Foundation, data were collected from a diverse sample …

From Natural Language To Cryptographic Protocol Specifications: Evaluating Llms For Cpsa Generation, Martin Duclos

Theses and Dissertations

Formal verification can prove the security properties of cryptographic protocols, but translating natural language specifications into formal models requires specialized expertise, limiting the broader adoption of formal verification methods. This dissertation investigates whether large language models (LLMs) can lower this barrier by automatically generating Cryptographic Protocol Shapes Analyzer (CPSA) models from natural language protocol specifications. We evaluate three complementary strategies for improving LLM-based CPSA code generation through systematic experimentation across 104 protocols and 15 language models. First, we analyze prompt engineering and find that moderate structured guidance yields the most accurate outputs, while excessive prompt complexity degrades performance. Second, we …

An Evaluation Of Artificial Intelligence Chatbots As Alternatives To Specialized Software In Teaching Bayesian Pharmacokinetic Analysis, Reza Mehvar

Pharmacy Faculty Articles and Research

Objective

Methods

Iterative Silver-Label Refinement For Temporal Information Extraction In Biomedical Literature, Chan Lee

UNLV Theses, Dissertations, Professional Papers, and Capstones

Temporal information extraction plays a critical role in the biomedical domain, where the ability to identify events and their temporal relationships is central to interpreting research findings. However, annotated corpora for this task remain scarce and costly to produce and the existing models developed for clinical text do not transfer well. This work bridges that gap through iterative silver-label refinement. A temporal model originally trained on news-domain data is adapted to biomedical text through cycles of automatic labeling, targeted correction, and retraining without the need for comprehensive manual annotation.

Key contributions include a practical iterative refinement methodology demonstrating that the …

A Descriptive Analysis Of Plant Leaf Disease Detection Using Machine Learning And Deep Learning Models: A Systematic Review, Arzoo Chamoli, Anuj Kumar

Turkish Journal of Electrical Engineering and Computer Sciences

Plant leaf disease detection (PLDD) is a growing active research area with burgeoning practical applications across various sectors such as agricultural monitoring, food security, and environmental conservation. Accurate segmentation and classification of plant leaf diseases remains a key challenge in the field of plant leaf disease prediction. The challenge demands automated methods for the plant disease identification because it needs to develop better crop management systems, which will boost agricultural production. In this article, we provide a systematic review of various machine learning (ML) and deep learning (DL) methods extensively used for PLDD. The review strategy follows a formal protocol, …

Integrating Augmented Reality Visualizations Into Data Science Notebooks Using Microsoft Hololens 2, Derek Willis

Theses and Dissertations

Data-science notebooks support iterative analysis but are limited to two-dimensional (2D) displays. This work presents an approach to extend such environments with rapid augmented reality (AR) visualization while preserving conventional 2D workflows. An opensource R package was developed to convert notebook objects into three-dimensional (3D) models, export them in the Graphics Language Transmission Format (glTF), and transfer directly to a Microsoft HoloLens 2 via a USB connection for viewing in the native 3D Viewer application. The proposed workflow eliminates manual conversion and transfer steps required by earlier methods. A user study employing a post-session questionnaire indicated that participants found the …

Beyond English: Auditing And Mitigating Cross-Lingual Data Contamination In Multimodal Large Language Models, Pavan Dharma Adapa

Theses and Dissertations

This thesis extends data contamination auditing for multimodal large language models to multilingual settings. Using LLaVA 1.5 and a high-fidelity French parallel dataset derived from ScienceQA, the study evaluates how performance changes when identical image-question pairs are translated from English to French. The resultsshow a substantial cross-lingual performance decline and frequent flips from correct English predictions to incorrect French predictions, indicating that benchmark performance can depend heavily on memorized English-specific patterns rather than stable multimodal reasoning. To address this weakness, the thesis introduces an inference-time mitigation strategy based on perturbation ensembling and cross-lingual consistency aggregation. The proposed method reduces instance-level …

Evaluation And Mitigation Of Bias And Toxicity In Open-Source Large Language Models Using Crows-Pairs And Bold, Sai Harika Gade

Theses and Dissertations

This thesis evaluates bias and harmful language generation in five open-source language models and tests practical mitigation methods that do not require retraining. Two masked models are assessed with a sentence-pair benchmark for stereotype preference, and three generative models are assessed with a prompt-based benchmark for harmful continuations across demographic domains. The study uses a unified experimental workflow to compare model behavior, summarize differences across bias categories, and measure changes after intervention. Results show that the masked models favor stereotypical content above a random baseline, while the generative models usually produce low average toxicity but still show uneven risk across …

Accelerating Defensive Cyber Operations Via Unsupervised Log Clustering And Automated Regex Template Synthesis, Charles Matthew Jones

Theses and Dissertations

Modern Security Operations Centers (SOCs) ingest millions of log entries per day, but manual parsing does not scale to the volume, heterogeneity, and rapid evolution of log formats. This dissertation investigates whether unsupervised clustering can automate the generation of candidate field-extraction templates while remaining deployable in production and feasible under realistic runtime and memory constraints. The central research question asks whether a machine-learning-assisted pipeline that proposes extraction templates for security engineer review—relative to reproducible human-authored baselines such as hand-written regular expressions—can measurably improve rule-set deployability and corpus-scale extraction quality. Improvement is quantified using four applicability metrics: Coverage Rate (CR), Exclusive …

A Pedagogically Effective Conceptual Framework For The Resilience Of Unit Test Suites To Refactoring, Daniel Paul Knight

Theses and Dissertations

Unit test suites are intended to support safe and efficient source code refactoring, yet in practice they can hinder rather than help when tests are tightly coupled to implementation details. Such non-resilient tests require frequent co-evolution, consume valuable engineering time, and may disincentivize beneficial code improvements. While concepts such as passive and active resilience, test smells, and technical debt have been studied individually, they have not been integrated into a single actionable framework, nor has their pedagogical value been systematically evaluated. This dissertation introduces a novel conceptual framework for the resilience of unit test suites to refactoring, grounded in resilience …

Agentic Synthetic Data Generation For Automated Model Development, Frederick Eugene Diehl

Theses and Dissertations

Large Language Model research has made large strides in capabilities from sentiment analysis to writing code. These advancements have been realized thanks to research into specific capabilities such as prompting techniques. Language models today have demonstrated the ability to create content, transform, and classify. These capabilities are not limited to academic exploration but also found in commercial products that are positioning themselves from application augmentation to personal assistants. These commercial products tend to steer towards single actions such as “summarize this article” or “write a function that performs action...” In parallel research has continued to advance towards more advanced constructs …

Automatically Constructed Preference Pairs For Chain-Of-Thought: Consistency Gains With Accuracy Tradeoffs, Cameron Scolari, Lanyu Shang

Honors Thesis

We investigate preference optimization over chain-of-thought (CoT) reasoning using automatically constructed preference signals derived from the accuracy and internal consistency of a model. Our results show that framing reasoning as a preference learning problem improves both the accuracy of the final answer and the structure of the model outputs. We observe a non-monotonic relationship between performance and the Direct Preference Optimization (DPO) scaling parameter β, where moderate values maximize accuracy while lower values improve stability, highlighting a tradeoff between optimization strength and reliable generation. We further identify a tradeoff between reasoning consistency and accuracy. Increasing the consistency weight improves agreement …

Ai Shell, Jacqueline Roebuck Sakho

Books

An AI Configuration Shell to train and deploy an Argumentation Coach. Presented and distributed to the UNC Commons Collective in May 2026.

Pwnagotchi: Deauthentication Attacks, Wpa Handshakes, And Wireless Network Security, Emily Musgrove

Computer Science Honors Papers

Wireless networks are the foundation of modern device communication infrastructure. This project examines the security implications of automated WPA/WPA2 handshake collection using the Pwnagotchi, a portable Wi-Fi network auditing and penetration testing device. The paper provides a technical analysis of WPA and WPA2 authentication mechanisms, including the structure of the 4-way handshake, the creation of cryptographic keys, and the role of deauthentication attacks in forcing reconnections for handshake capture. Additionally, the project explores the vulnerabilities associated with using legacy wireless security protocols such as WEP and TKIP to allow for older technologies that continue to require such encryption methods. This …

Synthergy: Social Deduction And Deception In Llm-Powered Agents, Lauren Campbell, Andrew Forney

Honors Thesis

Synthergy is an online social deduction game designed to enable comparative analysis of how large language model-powered agents engage in social deduction and deception under conditions of asymmetric information. Inspired by social deduction games such as Town of Salem, Throne of Lies, and Mafia, the game consists of two factions, Harmony and Discord, to which agents are secretly assigned. Agents must infer others’ affiliations through dialogue, in-game abilities, and voting behavior. To evaluate agent behavior, we conducted 100 simulated games across six agent types: a random baseline agent (RandomSynth), an LLM-based agent (Synth), a chain-of-thought agent (CoT Synth), a Bayesian …

A Governance-Aware Multi-Agent Framework For Enhancing Fairness & Temporal Accuracy In Disaster Response Systems, Md. Ashfaqur Rahman

Theses and Dissertations

Large Language Models (LLMs) have demonstrated significant potential in disaster-response decision support, however, their deployment in high-stakes humanitarian settings raises critical concerns regarding factual reliability, fairness, temporal validity, and governance compliance. Hallucinated outputs, demographic bias, and outdated recommendations can directly impact vulnerable populations and undermine public trust. This dissertation proposes a governance-aware multi-agent framework designed to enhance fairness and temporal accuracy in disaster-response systems through structured Retrieval-Augmented Generation (RAG), verification-driven orchestration, and adaptive correction mechanisms.The proposed architecture decomposes response generation into specialized agents responsible for real-time retrieval, fact-checking, bias auditing, temporal validation, threshold-based correction, and monitoring. By embedding governance constraints …

Llms In Compiler Construction, Raffi Khatchadourian

Open Educational Resources

These lecture slides survey the use of large language models (LLMs) in compiler construction for a graduate compiler course (CSc 81010). They situate LLMs across the compiler pipeline and examine representative work: foundation models trained on LLVM IR and assembly (Meta's LLM Compiler), LLM-driven code optimization, binary decompilation (LLM4Decompile), and LLM-assisted automated refactoring—alongside the challenges of applying probabilistic models to tasks that demand correctness. The slides are a self-contained HTML (W3C Slidy) deck with editable Pandoc Markdown source. Part of a two-session unit on advanced compiler topics; see also "Deep Learning Compilers."

Deep Learning Compilers, Raffi Khatchadourian

Open Educational Resources

These lecture slides introduce deep learning compilers for a graduate compiler-construction course (CSc 81010). Building on the classical compiler pipeline, they show how modern machine-learning systems compile tensor programs: static tensor and type analysis (illustrated by a WALA/Ariadne-based refactoring of imperative TensorFlow code to graph mode), MLIR-based end-to-end compilation with IREE, and the PyTorch 2.x stack—TorchDynamo graph capture, AOTAutograd, PrimTorch operator decomposition, and TorchInductor lowering to Triton (GPU) and C++/OpenMP (CPU). The slides are a self-contained HTML (W3C Slidy) deck with editable Pandoc Markdown source. Part of a two-session unit on advanced compiler topics; see also "LLMs in Compiler Construction."

Dynamic Trust Calibration, Bruno Miranda Henrique

Dartmouth College Ph.D Dissertations

Trust calibration between humans and Artificial Intelligence (AI) is crucial for optimal decision-making in collaborative settings. Excessive trust can lead users to accept AI-generated outputs without question, overlooking critical flaws, while insufficient trust may result in disregarding valuable insights from AI systems, hindering performance. Despite its importance, there is currently no definitive and objective method for measuring trust calibration between humans and AI. Current approaches lack standardization and consistent metrics that can be broadly applied across various contexts, and they don’t distinguish between the formation of opinions and subsequent human decisions. This thesis brings a novel and objective method for …