Digital Commons Network^™

An Informative Analysis Of Applying Feature Reduction Methods To Supervised Machine Learning Algorithms, Mustafa S. Abd

Baghdad Science Journal

Feature reduction techniques are fundamental to enhancing machine learning (ML) algorithms by reducing the number of features in a dataset. The study here explores the impact of Principle Component Analysis (PCA) on ML algorithms within an unbalanced classification framework, in partnership with feature selection techniques like Cluster Variation Attribute Evaluator (CVAE) and Correlation Attribute Evaluator (CAE). In addition, the research introspects a comparison analysis evaluating the effectiveness of several ML methods, including Multilayer Perceptron (MLP), Decision Tree J48, k-Nearest Neighbor (k-NN) and Sequential Minimal Optimization (SMO). The informative analysis of results signifies that the MLP technique with PCA minimized the …

Family-Based Gwas Of Cognitive Endophenotypes Reveals Genetic Architecture Of Memory And Executive Function In Alzheimer’S Disease, Kesheng Wang, Xueying Yang, Gayenell Magwood, Chun Xu, R. Osvaldo Navia, Jean Neils-Strunjas, Xiaoming Li

Health & Biomedical Sciences Faculty Publications

Alzheimer’s disease (AD), the most common cause of dementia, is characterized by progressive memory and cognitive decline. Conventional genome-wide association studies (GWAS) comparing AD cases and controls may miss genetic influences that act along a continuum of cognitive function. Using data from 3007 participants in the National Institute on Aging Late-Onset Alzheimer’s Disease Family Study (NIA-LOAD GWAS), we conducted a family-based GWAS of eight quantitative cognitive phenotypes encompassing episodic memory (Logical Memory IA and IIA), working memory (Digit Span Forward, Backward, and Ordering), and semantic fluency (Animal, Fruit and Vegetable, and Vegetable Fluency). Family-based association testing in PLINK v1.9 identified …

Weight Concerns And Body Image Dissatisfaction Elicit Maternal Psychological Control Through Escalating Appearance Anxiety Behaviors, Madeleine Guillont

Electronic Theses and Dissertations 2020 - Present

The current study examines bidirectional associations between adolescent body-related concerns and maternal psychological control, and the behavioral mechanism through which these associations operate. Participants were 723 sixth- through ninth-grade students (350 girls, 373 boys; ages 11–15) attending all public middle and secondary schools in a mid-sized Lithuanian community. Self-report surveys were collected at three time points across the course of a school year. Results from full longitudinal mediation models indicated that higher body image dissatisfaction and weight concerns at the beginning of the school year predicted increases in maternal psychological control at the end of the school year, through increases …

Llm For Clinical Named Entity Recognition: A Study On Rag With Pubmed And Umls, Apoorv Tripathi

Electronic Theses and Dissertations 2020 - Present

The first step of biomedical NLP is recognizing clinical named entities, which consist of identifying and categorizing a variety of clinical entities such as diseases, symptoms, genetics, diagnostic tests, procedures, etc. from a body of unstructured clinical text. This study presents a PubMed and UMLS based Retrieval Augmented Generation framework which improves the performance of the Large Language Models to identify clinical entities by providing context. In particular, the framework consists of a two-stage pipeline, where candidate tokens are identified from initial LLM-based classification and refined with retrieved context from either PubMed or UMLS. The proposed framework is assessed across …

Differentiable Objectives For 3d Scene Relighting Via Gradient Descent On Olat Basis Coefficients, Anson Savage

Theses and Dissertations

Designing effective lighting is an iterative and often time-consuming process. This work contributes to automatic lighting design research by presenting a render-engine agnostic optimization routine: gradient descent on RGB multipliers of one-light-at-a-time (OLAT) basis images. We compare several objective functions to accomplish lighting tasks and show that our method is capable of quickly and effectively exploring different lighting styles using either text prompts or reference images. We also present several datasets specific to lighting tasks and show that fine-tuning on these datasets can improve performance.

April 23, 2026, James Madison University

The Breeze, 2020-

The Breeze is the student newspaper of James Madison University in Harrisonburg, Virginia.

Predicting Telecom Customer Churn: A Statistically Validated Kpi Framework With Machine Learning And Revenue Impact Modeling, Moeez Islam Malik '27, Amy Ehinomen Eremionkhale

Student Research

This capstone project addresses a core business problem in the telecommunications industry: how to detect, measure, and prevent customer churn before it occurs, using a KPI framework validated by statistical analysis and machine learning. Applied to 7,043 customer records across 37 variables from a California-based telecom operator, the analysis integrates descriptive KPI computation, Pearson correlation analysis, chi-square tests of independence, and logistic regression churn prediction. The research confirms that customer tenure (r = −0.352, p < 0.001) and contract type (Cramér's V = 0.410, p < 0.001) are the dominant predictors of churn, and that a logistic regression model achieves AUC-ROC = 0.8307 — sufficient for proactive deployment. A 5-percentage-point churn reduction preserves $273,670 in annual revenue and $1.55M in customer lifetime value. The project delivers an integrated analytical framework, a predictive retention model, a 16-chart visualization suite, and a 12-page Power BI executive dashboard.

What Happens After Oil And Gas Decommissioning? A Global Systematic Review Of Marine Environmental Effects, Anaelle Lemasson Lemasson, Antony M. Knights

School of Biological and Marine Sciences

The thousands of oil and gas (OG) platforms placed at sea for fossil fuel extraction have introduced new hard substrate to the marine environment. Over time, these structures can become colonized by a diversity of marine life, fostering novel ecosystems. However, an increasing number of OG platforms are reaching decommissioning age and decisions regarding their fate must be made. Some view these artificial structures as litter that ought to be removed; others view them as valuable contributors to marine biodiversity worth preserving. Evidence of the environmental effects of these structures following different decommissioning strategies is needed to identify the potential …

Mechanism Of Improved Miscibility Of Co2–Oil Systems By Multiester-Headgroup Surfactants, Ning Xu, Yanling Wang, Baojun Bai, Yu Zhang, Wenjing Shi, Zhaonian Zhang, Wenhui Ding, Peixu Ma, Zan Gao

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

In the pursuit of carbon neutrality, the CO₂-enhanced oil recovery provides dual benefits by enabling both carbon sequestration and incremental oil production. However, its application is limited by high minimum miscibility pressure. CO₂-philic and oil-affinitive surfactants have emerged as an effective, low-dosage, and cost-efficient strategy to reduce the minimum miscibility pressure. In this study, macroscopic phase behavior experiments combined with molecular dynamics simulations were employed to systematically elucidate the influence of multiester-head surfactants on CO₂–oil miscibility. Using a modified pressure–volume–temperature apparatus equipped with optical power monitoring, we determined that multiester-head surfactants reduced the first-contact …

Exam Analysis: A Quantitative Approach To Software Pedagogy, Christopher Shepard

Theses

Software engineering exams serve as a tool for evaluating a broad range of skills in the classroom, including theoretical understanding, practical application, and process reasoning. Despite their importance, post-assessment analysis is often overlooked, and the absence of structured reflection by instructors can limit their effectiveness and mask patterns in student performance. By treating exams as data, educators can uncover trends that drive more effective teaching strategies, refine evaluation methods, and work to strengthen student support systems. We conducted a systematic analysis of existing exam data and administered a student survey to determine if student perceptions align with actual outcomes, asking …

Psychometric Analysis Of The German Version Of The Barriers To Healthcare Checklist-Short Form, Judith Peth, Nicole David, Sophia Duckert, Petia Gewohn, Daniel Schottle, Pascal Rahlff, Alexander Konnopka, Hannah Konig, Kai Vogeley, Christina Nicolaidis, Dora M. Raymaker, Holger Schulz

School of Social Work Faculty Publications and Presentations

Background: Autistic people face multiple barriers to health care. To recognize specific barriers in a standardized way, autistic people, health care providers, and researchers need a suitable measure. The Academic Autistic Spectrum Partnership in Research and Education successfully developed the Barriers to Healthcare Checklist— Short Form (BHC-SF). It remains unclear whether (1) a German version of the BHC-SF performs well in terms of psychometric properties and (2) the BHC-SF consists of multiple constructs (i.e., assessing structural validity). Methods: We created a translated and culturally adapted version of the 17-item BHC-SF and used it with 345 autistic people in Germany. Psychometric …

The Effects Of Oleuropein In Olive Leaf Extract Alone Or Combined With Calcitriol On The Viability And Migration Of Human Endometrial Cells In Vitro, Katelyn Devereaux

Electronic Theses and Dissertations 2020 - Present

Endometriosis is a chronic inflammatory disease affecting approximately 10% of reproductive-aged women worldwide and is commonly associated with pelvic pain, infertility, and reduced quality of life. Current management strategies, including hormonal therapies and surgical intervention, often provide only temporary relief and are associated with recurrence and adverse effects. These limitations highlight the need for alternative, non-hormonal therapeutic approaches that target underlying inflammatory and cellular mechanisms of disease progression.

This study evaluated the effects of oleuropein, contained within an olive leaf extract, and calcitriol, the active form of vitamin D, on cellular viability and migration in immortalized human endometriotic epithelial (12Z) …

Optimization Of Pediatric Multidetector Ct Imaging Parameters Using A Machine Learning–Based Monte Carlo Simulation Model, Ali O. Masoud, Adithya Rajnaryanan, Khamis O. Amour, Ahmed M. Jusabani, Justin E Ngaile, Manoj Kumar, Mwingereza John Kumwenda Dr

Tanzania Journal of Science

This study utilized Monte Carlo (MC) simulations to optimize radiation doses in pediatric multidetector computed tomography (MDCT) head scans by analyzing key parameters like tube current (mA), tube voltage (kV), pitch, and slice thickness. The findings indicate that reducing tube current significantly lowers the Computed Tomography Dose Index (CTDIvol) and Dose Length Product (DLP), effectively minimizing patient radiation exposure. Higher pitch values (0.7–0.9) further reduced radiation by decreasing beam overlap, while using a thinner slice thickness (0.6 mm) improved dose efficiency. A comparison highlighted the effectiveness of optimization: simulated parameters kVp 100, mAs 81, pitch 0.98 yielded a CTDIvol of …

Dual Membrane-Spanning Anti-Sigma 2 Controls Omv Biogenesis And Colonization Fitness In Bacteroides Thetaiotaomicron, Evan J Pardue, Tengfei Zhong, Nichollas E Scott, Biswanath Jana, Wandy Beatty, Juan C Ortiz-Marquez, Mohammed Kaplan, Clay Jackson-Litteken, Mario F Feldman

2020-Current year OA Pubs

UNLABELLED:

IMPORTANCE: Dual membrane-spanning anti-sigma factors (Dma) are a novel class of regulatory proteins found solely among Bacteroidota. Previous studies demonstrated the importance of Dma1 in vesiculation, but the overall role of the Dma family in Bacteroides physiology remains poorly understood. Here, we show that Dma2 modulates vesiculation and the expression of select polysaccharide utilization loci (PULs) that target host-associated glycans

Excavations At Jerusalem: The Byzantine Street (Area S2), Moran Hagbi, Joe Uziel

'Atiqot

This report presents the results of an excavation conducted on the northwestern corner of the City of David, between the Giv‘ati Parking Lot and the Ottoman walls of the Old City of Jerusalem. Six strata were exposed, spanning the Early Roman and Early Islamic periods. The main archaeological feature exposed was a section of a stone-paved street dating to the late Byzantine period. The street, previously exposed in other excavations, was a primary south–north artery running along the Tyropoeon Valley and linking between the City of David and the upper parts of Jerusalem. This street was likely an important route, …

Aspects Of Urban Planning In Bet She’An-Scythopolis: A View From Rhometalkes’ Alleys, Benjamin Y. Arubas, Leah Di Segni

'Atiqot

Intercity roads, colonnaded and drained streets, agoras and forums of the Roman and Late-Antiquity city of Bet She’an-Scythopolis—all have been widely studied, producing an ample bibliography. Not so are alleys, although they must have served various functions as thoroughfares for foot traffic or in relation to the buildings that overlooked them. These buildings could have been domestic, commercial or public, causing the function of the alley to surely change accordingly. This paper is dedicated to the study of two such alleys, which existed solely amidst public buildings, and whose story can be told based on the results of excavations and …

Exploring The Dual Advising System For Students’ Success: A Developmental Advising Model, Louisa Godwyll, Eugene Kwarteng-Nantwi, Pious Jojo Adu-Akoh

Mid-Western Educational Researcher

This qualitative study explored the dual advising system for student success at a U.S. higher education institution. Research has indicated that approximately 40–60% of students enrolled in doctoral programs do not complete their doctoral degrees. High attrition rates have led some institutions to adopt a dual advising system, a form of developmental advising, to support doctoral students’ success. Creamer and Creamer’s (1994) developmental advising model served as the conceptual framework of the study. The model defines the first stage of advising as defining task, where advisors engage in teaching and utilize strategies to help students attain educational, career, and individual …

Gc-178-191 Communication App: Ai-Assisted Aac Platform​, Alex Wills, Maryam Koya

C-Day Computing Showcase

The Communication App is an accessibility-focused mobile application designed to support individuals with speech impairments, strong or unrecognized accents, and neurodivergent communication needs. The system leverages AI assisted speech-to-text (STT) and text-to-speech (TTS) technologies to enable real-time and seamless communication between users.This project aims to bridge communication gaps by providing a customizable, adaptive platform that learns user speech patterns over time. The application integrates cloud-based services, secure communication protocols, and an intuitive user interface to ensure usability, performance, and accessibility.

Grm-012-173 Can You Trust Ai Code? Understanding And Detecting Breaking Changes Using Llms, K M Ferdous, Kowshik Chowdhury

C-Day Computing Showcase

AI-generated code is increasingly prevalent in software engineering practices, yet its reliability in preserving backward compatibility remains underexplored. This paper presents a unified study of (i) how often AI-generated code introduces breaking changes and (ii) whether large language models (LLMs) can detect such changes from commit-level diffs with explanations. We analyze 7,191 agent-generated and 1,402 human-authored pull requests from Python repositories using an AST-based approach to identify potential breaking changes. Our results show that AI agents introduce fewer breaking changes overall than humans (3.45% vs. 7.40%) in code generation tasks. However, agents show higher risk in maintenance tasks, where refactoring …

Grm-081-207 Leveraging Non-Parametric Longitudinal Rank Sum Tests (Lrst) For Robust Global Treatment Effect Estimation In Alzheimer’S Disease, Imaan Shahid

C-Day Computing Showcase

Parametric approaches, such as Mixed Models for Repeated Measures (MMRM), are standard in Alzheimer’s Disease (AD) clinical trials. However, these models often falter when data violates assumptions of normality or follows non-linear trajectories—common occurrences in AD due to floor/ceiling effects on cognitive scales and heterogeneous disease progression. This study evaluates Longitudinal Rank Sum Tests (LRST) as a non-parametric alternative to maintain statistical power and robustness.

Grm-169-137 Predicting The Stock Market's Next Move: How Neural Network Architecture Shapes Forecasting Accuracy, Roderick Powell

C-Day Computing Showcase

Three feedforward neural network (FFNN) architectures — bottleneck, parallel multi-path, and residual parallel — were trained on ten years of daily S&P 500 (SPY ETF) price and volume data to predict next-day market direction (Up/Down). All three demonstrated predictive ability above random chance. Architectural choice directly determined class prediction bias: the bottleneck concentrated errors on Up days, the parallel architecture distributed them evenly, and residual connections inverted the bias toward Down days. Model 2 (parallel) achieved the highest test accuracy (58.2%) and the most balanced class predictions among the three configurations.

Uc-011-171 Beyond Postseason Awards: Predicting Accolades Via Real-Time Control Chart Signals In The Ncaa Transfer Era, Daniel Bowen, Shayaan Cyclewalla

C-Day Computing Showcase

In the era of the NCAA transfer portal, collegiate basketball coaches face the critical challenge of identifying and targeting elite recruits within a condensed 15-day window. This study investigates the predictability of elite player performance by analyzing postseason award winners within the Coastal Athletic Association (CAA). Utilizing game-by-game data on player efficiency, usage percentages, and Player Efficiency Ratings (PER), we implemented an Exponentially Weighted Moving Average (EWMA) control chart—a technique from the Statistical Process Control (SPC) family—to monitor performance signals. Our results indicate that the EWMA model successfully identifies future award-winning players after an average of only 8.58 games. By …

Uc-082-216 Ai Driven Guest Support For Vacationsforyou​, Cassidie Grogan, Kendal Elison, Benjamin Dulcio, Ezra Begashaw, Wilfred Faltz

C-Day Computing Showcase

The AI Guest Support Assistant is a proof-of-concept, web-based chatbot designed to streamline guest support for a high-volume vacation rental operation. The system leverages a Large Language Model (LLM) combined with a Retrieval-Augmented Generation (RAG) approach to deliver accurate, context-aware responses to common guest inquiries, such as reservation details and check-in times. Built using a React frontend and a FastAPI backend, the platform integrates securely with the StreamlineVRS property management system. The solution aims to reduce call center workload by automating repetitive inquiries while maintaining a clear escalation path for more complex requests. This project evaluates the feasibility, usability, and …

Uc-122-135 Mutatio Mentis, Isaac Alderman, Braden Mizell, Collin Sutton

C-Day Computing Showcase

Mutatio Mentis is a first person, narrative heavy, puzzle-lite RPG that follows the story of a renaissance era plague doctor and their attempt to alter the minds of three subjects; a gardener, a street urchin, and a priest. The narrative is set in 1637 Florence, Italy, in the wake of the Great Plague of Milan, and draws heavily from renaissance culture. Each of the three subjects have progressively more complex personal conflicts, which present through the gameplay aesthetics of each act, as the gameplay changes to reflect the problems of each subject. Our focus is on tackling mental and emotional …

Uc-139-175 Agentic Debugger And Documenter, Olaoluwa Omodemi, Jade Le, Preston Dietz

C-Day Computing Showcase

Modern software development teams routinely introduce subtle bugs — mutable default arguments, bare exception handlers, insecure eval()/exec() calls, resource leaks, hardcoded secrets — that escape manual review but accumulate into technical debt and security risk. Existing linters identify problems but leave remediation to the developer. This project investigates whether a coordinated multi-agent system, combining rule-based static analysis with generative LLM reasoning, can autonomously detect, fix, and document such issues with no developer involvement beyond providing the input file.

Gc-168-220 Active Directory To Cloud Security Data Pipeline, Michael Butler, Shahiba Shamshad, Mounia Touil, Koko Afantchao

C-Day Computing Showcase

This project builds an automated pipeline that extracts identity and asset data from on-prem Active Directory, stages it in Google BigQuery, and securely sends normalized data to Lucid through Google Cloud Run. Using PowerShell scripts, the system collects users, groups, computers, DNS, DHCP, and related metadata without changing the source environment. BigQuery serves as the staging layer for validation and processing, while Cloud Run transforms and transfers the latest data to Lucid for visualization. The goal is to provide a repeatable, traceable, and reliable workflow that improves visibility into identity relationships for security investigations, auditing, and validation in a controlled …

Grm-179-195 A Retrieval-Augmented Generation (Rag) System For Bible Question Answering Using Scriptural Text And Commentary, Maryam Koya, Pragya Mishra

C-Day Computing Showcase

This project develops and evaluates a question-answering (QA) system designed to address theological and interpretive questions about the New Testament. It uses a Retrieval-Augmented Generation (RAG) framework that integrates a pretrained large language model with a structured knowledge base consisting of public-domain Berean Standard Bible (BSB) New Testament and New Testament commentaries. User queries are embedded to retrieve semantically relevant passages, which are then supplied as contextual input for answer generation. The system is evaluated based on retrieval quality, answer faithfulness, and comparison to ground truth. Performance is benchmarked against a baseline BM25 keyword retrieval system without commentary, demonstrating that …

Grp-07-163 Smishguard: An Ai-Powered Framework For Sms Phishing Detection And Alert System For Vulnerable Users, Jiban Krisna Das

C-Day Computing Showcase

This research introduces SMISH-GUARD, a multi-layer framework for adaptive SMS phishing (smishing) detection that integrates language-aware semantic modeling, graph-theoretic campaign reasoning, and cost-sensitive decision calibration within a unified architecture. The framework integrates dual transformer encoders for multilingual semantic understanding with a heterogeneous temporal graph layer that captures relational attack signals such as shared URLs, sender reuse, and campaign propagation patterns. A cost-sensitive decision optimization module is further incorporated to translate probabilistic model outputs into risk-aware alert policies that explicitly balance false-positive inconvenience against the higher societal and financial cost of missed smishing attacks. The study evaluates four integrated datasets comprising …

Gc-140-126 Machine Learning Models For Solar Power Output Prediction: A Comparative Study With Adaptive Pso-Based Random Forest Tuning, Hasitha Mahabaduge

C-Day Computing Showcase

Accurate prediction of solar power output is essential for energy scheduling, grid reliability, and efficient integration of renewable resources. Because photovoltaic generation is governed by changing atmospheric conditions, forecasting output is inherently a nonlinear learning problem. This study evaluates four machine learning models — Linear Regression, Random Forest, Multi-Layer Perceptron (MLP), and an Adaptive Particle Swarm Optimization-tuned Random Forest (Adaptive PSO-RF) — using irradiance, temperature, humidity, wind speed, cloud cover, and time-derived features drawn from a dataset of 6,738 observations. Random Forest achieved the strongest overall performance, with an RMSE of 1,816.24 and an R² of 0.9533. The Adaptive PSO-RF …

Gc-154-201 Evaluation Of Generative Ai Responses To Pharmacy Prompts, Abrar Syed

C-Day Computing Showcase

Generative AI (GenAI) is increasingly used in pharmacy for drug information and decision support, yet accuracy remains variable. We systematically reviewed studies that reported full prompts and model responses to evaluate correctness across pharmacy‑relevant tasks. GenAI performed well on basic drug facts but was inconsistent for patient-specific recommendations and interaction checking, with occasional hallucinations. Findings support cautious, supplementary use in pharmacy practice and education.