Digital Commons Network^™

Real Time Waste Classification Using Deep Learning: Comparing Mobilenetv2 And Resnet 18 With Transfer Learning And Fine Tuning, Abdul Moaiz

ICT

Waste contamination is a major problem all over the world. The Environmental Protection Agency reports that over two thirds of waste found in general household and commercial bins could have been placed in the recycling or organic waste bins instead in Ireland, with food waste and plastics being the most common misplaced items. This project presents a deep learning solution to classify nine categories of waste from camera images in real time with the goal of helping users sort waste correctly at the source. Following the CRISP DM framework, two convolutional neural network architectures were trained and compared, MobilenetV2 and …

Bitcoin Prediction System Usind Machine Learning Techniques, Carolina Azevedo De Castro

ICT

This project investigated the use of machine learning techniques to predict short-term Bitcoin price direction using historical market data obtained from Yahoo Finance. Following the CRISP-DM methodology, the dataset was analysed, prepared, and transformed through feature engineering techniques including moving averages, volatility indicators, return measures and price position metrics. Multiple classification algorithms were evaluated, including Bayesian Classification, K-Nearest Neighbour, Decision Tree, Random Forest, Logistic Regression, Support Vector Machine and XGBoost. Several optimisation strategies were also tested, including feature selection, hyperparameter tuning, feature scaling and class weight balancing. Results showed that predicting short-term Bitcoin price movements remains challenging, with most models …

Predictive Maintenance For Manufacturing Equipment, Paloma De Andrade Batista

ICT

Unplanned equipment downtime is a significant challenge in manufacturing, resulting in substantial productivity losses and operational costs. Predictive maintenance, enabled by machine learning and big data analytics, offers an opportunity to identify potential equipment failures before they occur and improve maintenance efficiency. This report extends a previous capstone project that applied Random Forest and Logistic Regression to the AI4I 2020 Predictive Maintenance Dataset. The current study expands the analysis by incorporating XGBoost, systematic hyperparameter optimisation, cross-validation, and SHAP-based model interpretability. In addition, SWOT and PESTLE analyses, alongside a legal and ethical assessment, examine the broader strategic and responsible implementation of …

Predicting Loneliness Among Older Adults In Ireland Using Supervised Machine Learning, Ariadne Chaves Miranda

ICT

Over the last two decades, technology has grown exponentially and has facilitated communication that helps individuals remain connected. However, this has also contributed to social isolation and lack of physical interaction. One consequence of this phenomenon is loneliness, which is understood as an unpleasant subjective state of discrepancy between the desired amount of companionship or emotional support and what is available in the person’s environment (Prohaska and Burholt, 2020). In the European context, Ireland has emerged as the loneliest country in Europe with 20% of its population that have reported feeling lonely most or all the time (Schnepf et al., …

Southern Adventist University Annual Report 2025-2026, Southern Adventist University

Annual Reports

The Annual Report for Southern Adventist University for 2025 to 2026.

Transforming Lives For Eternity: 2026-2031 Strategic Plan, Southern Adventist University

Strategic Plans

Southern Adventist University's 2026-2031 Strategic Plan.

The Political Economy Of Pfas Treatment And Water Regionalization In Harrison County, Kentucky, Jackson S. Patru, Rajan Sampat

MPA/MPP/MPFM Capstone Projects

The discovery of per- and polyfluoroalkyl substances (PFAS) in the water supply of Harrison County, Kentucky has prompted an urgent reevaluation of local treatment infrastructure. This situation has exposed a complex political economy between the City of Cynthiana, which owns and operates the municipal water plant, and the Harrison County Water Association (HCWA), which represents the majority of the ratepayers supplied by the plant. Using a qualitative research design grounded in inductive thematic analysis, semi-structured interviews were conducted with leadership from both Cynthiana and HCWA, as well as operators at the treatment plant, to evaluate two proposed solutions: a $14 …

Kentucky Space Futures: Defining The Driving And Limiting Factors Of Growth In The State Aerospace Industry, Ashley M. Grospitch, Isabella A. Sibold

MPA/MPP/MPFM Capstone Projects

Kentucky’s aerospace industry has quietly become one of the state’s most significant economic drivers, generating almost $19 billion in exports in 2024 and ranking third nationally in aerospace exports in 2023 (Mattingly, 2025; Babbage & Hartsough, 2024). Despite this, Kentucky remains largely invisible as an aerospace state, both to Kentuckians and national audiences. This work was conducted on behalf of our client, Kentucky Space Futures, to identify the factors shaping the growth of Kentucky’s aerospace industry, including its driving and limiting factors, and provide actionable guidance for policymakers and industry leaders.

Using a qualitative research design, this study triangulated findings …

The Purimspiel: A Compilation Play, Jordan G. Becknell

Scripps Senior Theses

This thesis covers the process of researching, writing, and developing The Purimspiel: A Compilation Play. This playwrighting project explores the dissonance between the cultural memory of the Jewish holiday Purim and the holiday’s long-documented association with Jewish violence and vengeance as it connects to the modern questions of Jewish identity in the wake of the ongoing genocide in Gaza.

Modern Psychological Distress: An Expressionist Lens, Abigail Adell

Scripps Senior Theses

“Static Overwhelm” showcases collective stress born from perpetual engagement with the internet and social media. The piece began as a personal reflection of my felt anxiety from online overuse. However, it quickly became a greater social commentary on the modern condition of internet dependence, stress, and unease.

With any basic search engine, any amount or type of information that I could ever need, is at my fingertips. We constantly experience the stress effects of the internet’s misinformation, political pressure, and addictive design.

Inspired by the expressionist movement, I have created a piece that focuses on the expression of raw emotion, …

Seeing Through The Fuzz: Understanding Conformational Diversity In The Fuzzy Coat Of Amyloids Across Fibril Polymorphs Using Solid-State Nmr, Carah K. Allen

Scripps Senior Theses

The aggregation of α-synuclein (α-syn) into amyloid fibrils is a central pathological hallmark of Parkinson’s disease and other related synucleinopathies. Although monomeric α-syn is intrinsically disordered, the protein assembles into multiple fibril polymorphs that differ in their β-sheet core structures. Surrounding each polymorph is the “fuzzy coat,” which is a highly dynamic, intrinsically disordered region (IDR) that is not resolved by high-resolution structural techniques, such as Cryo-EM, but is thought to influence fibril interactions, propagation, and toxicity. Understanding whether different polymorphs maintain distinct fuzzy-coat conformational ensembles is therefore essential for connecting amyloid structure to biological function. To address this question, …

Boredom And Creativity: The Effects Of Unstructured Play Versus Screen Time On Creative Performance, Vivienne J. Swenson

Scripps Senior Theses

Children today spend increasing amounts of time engaged with digital media, raising questions about how screens may displace developmental experiences that support creativity. Although research suggests that unstructured play and even mild boredom can facilitate divergent thinking, few studies have directly compared unstructured, self-directed play with passive screen use in early childhood. The present study proposes an experimental design to examine whether 20 minutes of unstructured play leads to higher creativity scores on the Thinking Creatively in Action and Movement (TCAM) than an equivalent period of passive screen engagement among children ages 3–5. Using matched-group assignment based on demographic, cognitive, …

Indirect Effects Of Coral Bleaching On Tursiops Truncatus Diet And Foraging Behavior In Bocas Del Toro, Panama, Annabel Fiero

Scripps Senior Theses

Indirect effects, where another species or factor mediates the effects of a given species, are critical to ecosystem structure and resilience. Shifts in fish community structure, as a result of rapidly declining coral reefs in the Caribbean due to warming-induced bleaching, pose a threat to apex predators like Tursiops truncatus (bottlenose dolphins). Branching corals create habitat niches for numerous fish species. These fish rely on coral for food and habitat, and in turn provide food for upper trophic levels. Prior research has highlighted how coral bleaching will disrupt Acroporid reef building corals and fish community structure, but the effects of …

Shrines On Asphalt Shoulders: Documenting Roadside Memorials In Western U.S. Roadscapes, Isabella R. Sullivan

Scripps Senior Theses

This thesis analyses the practice of documenting and uploading roadside memorials in the Western United States as a socially transformative process facilitated between two distinct kinds of noticing. Drawing on (auto)ethnographies of roadside memorial sites in Colorado and California, interviews with photographers and cartographers working primarily in the American Southwest, and Google Street View media, this research examines how recognition of the social negotiations involving memory and mortality that are already present in the physical shrines evolves when documenters capture and transpose them online. First, these documenters have developed the “eyes to see” roadside memorials for various significant reasons in …

The Demand For Attention: Notification Technology And The Restructuring Of Communication, Sabrina Feld

Scripps Senior Theses

This thesis argues that notifications are not merely features of digital devices but infrastructural forces that quietly reorganize the conditions under which communication is perceived, enacted, and understood. Drawing on Science, Technology, and Society (STS) frameworks, specifically Actor-Network Theory and Langdon Winner's concept of Forms of Life, the first chapter traces how notifications produce a Form of Life organized around continuous responsiveness, in which incoming information appears as a pending demand, silence carries new moral weight, and the capacity for self-determined availability is structurally foreclosed. Understood this way, notifications become a case study for a broader pattern in which technological …

Lead Biosorption By Oceanobacillus Profundus Kbz 3-2: Strategies For Bioremediation Systems In Kabwe, Danielle S. Desmarteau

Scripps Senior Theses

Lead contamination remains a significant global public health concern, particularly in Kabwe, Zambia, the site of a former lead mining operation. Bioremediation, which utilizes biological materials and processes to remove environmental contaminants, represents a promising approach for addressing lead pollution. However, the development of effective bioremediation systems requires a detailed understanding of the mechanisms underlying metal removal and the feasibility of implementation in low-resource settings. Oceanobacillus profundus KBZ 3-2, a bacterium isolated from Kabwe mine waste, has demonstrated the ability to remove lead from aqueous environments. This study proposes to investigate the mechanism of lead biosorption by this organism, …

Advancing Nanotechnology For Hematological And Osteological Disorders, Chase K. Hamilton

Integrated Studies

When people think of medicine, they often picture stethoscopes, routine clinical checkups, surgeries, and standard prescriptions. One field that needs more acknowledgement is the technological side. As technology continues to evolve, healthcare advances alongside it, with nanotechnology emerging as a substantial area of innovation. This paper reflects the expanding role of nanotechnology in modern medicine, focusing on its potential applications in trauma and internal medicine care and in the treatment of blood and bone disorders as well as bone and blood related cancers. By working at an extremely small scale, nanotechnology allows for more precise and targeted treatment, reducing damage …

How Baseball Stadium Design Influences Player Performance, Jacob D. Roettgen

Integrated Studies

How Baseball Stadium Design Influences Player Performance

Baseball stadiums on all levels have unique designs and dimensions. The MLB had 45,000+ seats to watch professionals battle it out. College baseball ranges from a field with a couple hundred seats to massive stadiums with almost 20,000. This paper is going to investigate how these dimensions and number of seats can affect player performance. Certain professional stadiums have interesting quirks to their field that provide advantages and disadvantages depending on how it is looked at. For example, Fenway Park, home of the Boston Redsox, has a huge left field wall called “The …

Improving Flood Risk Mapping By Incorporating Local-Scale Calibration Data Derived From Stakeholder Input, Jennifer M. Holifield, Wei Wu, Patrick D. Biber, Margo Posten, Dennis Mcgrury, Stephen C. Deal, Alexandria Hancock

Gulf and Caribbean Research

Globally, flooding is the most frequent and costly natural hazards, disproportionately affecting populations based on environmental, social, and economic factors. Understanding the spatial variability of flood risk as well as the respective flood drivers is essential for informing cost-effective mitigation strategies and enhancing community resilience. Here we mapped flood risk that combines flood hazards and vulnerability in an under-resourced coastal community prone to compound flooding. Our approach integrates stakeholder engagement with GIS-based analysis using open-access datasets.

We first developed an initial flood hazard map using an equal-weight combination of factors commonly associated with flood occurrence/prevention, including upslope area, impervious surface …

Stress-Strain Behavior Of Saturated Clays From Vane Shear Test Results: A Numerical Approach, Gustavo Rodrigues De Avila Oliveira

Master’s Theses

The vane shear test (VST) is widely used to estimate the undrained shear strength of soft cohesive soils; however, it does not directly provide constitutive information such as the stress–strain response. Smoothed Particle Hydrodynamics (SPH), a mesh-free numerical method, offers an attractive alternative for modeling the large deformations involved in the VST and extracting additional information from the test.

This study develops and calibrates a two-dimensional SPH model to simulate the field vane shear test and investigate the stress–strain behavior of soft soils. The VST was implemented within an SPH framework, while field and laboratory data were used to define …

Unified Attack Modeling And Mitigation Framework For Multiple Physical Attacks In Sensor Networks For Advanced Manufacturing, Mohammad Mezanur Rahman Monjur

Doctoral Dissertations

The advanced manufacturing industry (AMI) faces unique challenges in security assurance. Security threats in AMI can originate from both software and hardware. Over the past decade, software security has been addressed extensively, but hardware security has not received enough attention. This work focuses on the security vulnerabilities of typical electronic devices deployed to AMI. Three attack models are proposed to characterize sensing nodes, local processing edge devices, and wired/wireless communication interfaces. Moreover, practical security attacks on hardware are demonstrated to inspire the development of feasible countermeasures against common physical attacks. To explore effective attack mitigation methods, we examine two attack …

The Garden Of The Machine: Simulated Wildness And Digital Domestication In American Literature 1970-2020, Cameron Netland

Doctoral Dissertations

Studying American literature produced during the Information Age, from 1970 to 2020, reveals an evolution of wild human resistance to the increasing powers of digital technology. These increasing powers include capturing attention, fostering dependence, and training behavior through a process I call digital domestication. Digital domestication distances people from wildness, and as William Cronon writes in “The Trouble with Wilderness”, “Learning to honor the wild—learning to remember and acknowledge the autonomy of the other—means striving for critical self-consciousness in all of our actions.” (20). Through this framework of wildness, one reads characters in fictional narratives resisting non-coercive new technologies as …

The Development Of A Convenient And Consistent Methodology For Flight Proficiency To Certify Multi-Rotor Uas Pilots For State Departments Of Transportation, Colin H. Dees, Joseph M. Burgett

The Professional Constructor

To fly an unmanned aircraft system (UAS), commonly referred to as a “drone,” the Federal Aviation Administration (FAA) requires pilots to pass a knowledge test. There is no requirement at the state or federal level for drone operators to demonstrate the ability to operate a UAS. The National Institute of Science and Technology (NIST) has created an exam for public and private entities to assess basic UAS flight proficiency. It is the only nationally recognized flight proficiency protocol. NIST does not provide a scoring recommendation and leaves it to the user to determine the minimum criteria to pass. There is …

Feasibility Of Upcycling Spent Lithium-Ion Battery To Carbon Dioxide Capture Adsorbent, Chimezie Frank Onwudinjo

Master’s Theses

This study investigates the feasibility of repurposing spent lithium-ion battery (SLIB) to lithium orthosilicate (Li₄SiO₄), a high temperature carbon dioxide sorbent. Two synthesis pathways including conventional acid-leaching method (Scenario 1) and a pyrolysis-based route (Scenario 2) were explored. Additionally, techno-economic analysis (TEA) and lifecycle assessment (LCA) of the two processes were also performed. Different analytical characterization techniques were performed to understand the material properties of Li₄SiO₄ including surface area, crystallinity, morphology and thermal stability. CO₂ capture performance of the synthesized Li₄SiO₄ was tested in a thermogravimetric analyzer (TGA) using …

Control System Emendation And Ai-Driven Optimization For Enhancing A Smart Residential Microgrid, Anthony Nyoyoko

Master’s Theses

This thesis began with a simple idea: to restore the control system of a smart residential microgrid to respond intelligently to electricity prices while remaining safe, reliable, and practical on low-cost hardware. At the start, the goal was to design an economically aware microgrid that could look at electricity prices from the PJM market and make better operational decisions than traditional rule-based control. The motivation was straightforward. As residential renewable energy adoption increases, microgrids are expected to do more than just supply power. They are expected to respond to price volatility, integrate renewable generation, and operate reliably using embedded controllers …

Discovering Naturally Occurring Antifreeze Peptides From Microbiome By Integrating Protein Language Models And Molecular Dynamics Simulation, Ibrahim A. Imam, Trevor Morey, Yuexu Jiang, Duolin Wang, Dong Xu, Qing Shao

Chemical and Materials Engineering Faculty Publications

Antifreeze peptides inhibit ice crystal growth and recrystallization, and are promising components of cryoprotective formulations for cell, tissue, and food preservation, as well as anti-icing surface coatings. However, the discovery of new antifreeze peptides has been hindered by their sequence diversity and the limited scalability of experimental screening. In this study, we identify novel antifreeze peptide candidates from a microbiome-derived sequence library using ensemble machine learning and molecular dynamics (MD) simulations. We developed an ensemble classifier composed of 10 adapter-tuned protein-language models and a random forest meta-learner. After training on a curated dataset of 73 766 sequences, we applied this …

Functionalization Of Microfiltration Media Towards Catalytic Hydrogenation Of Selected Halo-Organics From Water, Subrajit Bosu, Samuel S. Thompson, Doo Young Kim, Noah D. Meeks, Dibakar Bhattacharyya

Chemical and Materials Engineering Faculty Publications

Contaminated water detoxification remains difficult due to the presence of persistent halo-organic contaminants, such as perfluorooctanoic acid (PFOA) and chlorophenols, which are chemically stable and resist conventional purification methods. Functionalized membrane-based separation and decontamination have garnered immense attention in recent years. Commercially available microfiltration membrane (PVDF) and polymeric non-woven fiber filters (glass and composite) are functionalized with poly(methacrylic acid) (PMAA) that shows outstanding pH-responsive performance and tunable water permeability under ambient conditions perfect for environmental applications. Polymer loading based on weight gain measurements on PMAA–microglass composite fibers (137%) and microglass fibers (116%) confirmed their extent of functionalization, which was significantly …

Stochastic Mechanical Mesoscale Modeling Of Cylindrical Cavities In Metallic Foams, Mujan N. Seif, Alexandre Martin, Matthew J. Beck

Chemical and Materials Engineering Faculty Publications

Aluminum foam is a critical component of state-of-the-art micrometeoroid and orbital debris shielding. However, its randomly oriented constituent ligaments create significant variability in properties at different length scales. Previous efforts have thoroughly characterized the statistical implications of micro- to macro-scale-length transitions on the homogenized elastic behavior of damage-free, pre–micrometeroid and orbital debris (MMOD) strike structures. In this work, the properties of the residual material post MMOD impact are assessed by introducing cylindrical cavities representing the damage track. It was observed that configuring the cavity parallel to the through-the-thickness direction transformed a nominally isotropic foam into an anisotropic (transverse isotropic) material, …

Overview And Methods Of Molecular Paleontology: A Review, Shelby Touchstone

Williams Honors College, Honors Research Projects

Molecular paleontology—the study of ancient biomolecules preserved in fossils and sediments, including ancient DNA, lipids, and proteins—has motivated researchers since the 1950s, inspiring both scientific inquiry and broader cultural imagination. Think Jurassic Park. This honors thesis presents a comprehensive review of the history, current state, and methods of the field of molecular paleontology. Drawing on peer-reviewed literature and scholarly resources accessed through databases such as EBSCO and Bierce library, this review examines key techniques such as Next Generation Sequencing and amino acid racemization and will go over limitations and controversies in the field. It will also explore potential new …

Beyond The Lace Index: Benchmarking Machine Learning Architectures And Explaining 30-Day Hospital Readmission Risk With Shap Analysis, Carl E. Hughes Iii

Williams Honors College, Honors Research Projects

Unplanned 30-day hospital readmission remains a fundamental challenge in US healthcare, associated with increased risk to patient recovery and representing an estimated $52.4 billion in annual expenses (Beauvais et al., 2022). While the rigorously validated LACE index serves as the clinical standard for readmission modeling, its linear structure and four explanatory variables lack the complexity to capture the high-dimensional and interactive nature of patient risk. This study utilizes an admission granularity level cohort of the MIMIC-IV database to develop and compare machine learning architectures against the baseline LACE index. Due to the imbalanced prevalence of readmission, the penalized logistic regression, …