Digital Commons Network^™

Online And Offline Multi-Variate Time Series Forecasting With Neuroevolution Based Neural Architecture Search, Zimeng Lyu

Theses

Time series forecasting plays a crucial role in various fields, ranging from financial markets and predictive maintenance in industrial settings to healthcare analytics. Traditionally, statistical approaches were employed primarily for univariate forecasting tasks, but modern applications often require robust solutions capable of handling complex, multivariate, noisy, and non-stationary data. Current state-of-the-art solutions predominantly utilize transformer-based models, which demand significant computational resources, limiting their practicality, especially in resource-constrained environments. This dissertation introduces novel and efficient approaches to multivariate time series forecasting, leveraging NeuroEvolution-based Neural Architecture Search (NAS) methodologies. Specifically, two robust algorithms---Evolutionary eXploration of Augmenting Memory Models (EXAMM) for offline forecasting …

Unique Architecture: In Praise Of Paradox Persistence, Odaly Plancarte

Theses

This thesis explores how bold and unconventional architectural designs are first rejected and later embraced by the public. Through a comparative study of the Sydney Opera House, the Louvre Pyramid, and the Walt Disney Concert Hall, it examines how public opinion shifts over time. Using media reports, interviews, and public comments, the study tracks emotional responses (positive, neutral, or negative) assigned a score to measure change over the years. The research applies Everett Rogers’ Diffusion of Innovation Theory to explain this shift in five stages: knowledge, persuasion, decision, implementation, and confirmation. Each building faced early backlash, but eventually became a …

Characterizing Tcap Set-Ups For Effective Separation On Hydrogen Isotope Species, James R. Hanby

Theses

Hydrogen isotope separation was investigated using a series of thermal cycling absorption process (TCAP) experiments. Pulse tests were conducted using deuterium injected into a protium flow over a range of superficial velocities, temperatures, particle sizes, and column diameters to quantify the efficiency of this process for a palladium on kieselguhr catalyst. The resulting response curves, obtained from residual gas analysis, were used to calculate the height equivalent to a theoretical plate (HETP) in each case. These values were then fit with van Deemter curves to illustrate the change in HETP over gas velocity. A strong positive correlation with temperature was …

An Investigation Of Water-Based Cutting Fluids: Choline Amino Acid Protic Ionic Liquids As A Potential Sustainable Additive, Moni I. Chavez-Padilla

Theses

This comprehensive investigation examines the use of choline amino acid protic ionic liquids (CHAAPILs) as environmentally friendly additives for water-based cutting fluids (WBCFs) and showed a significant improvement in both friction and wear compared to traditional cutting fluids. Notably, water alone is ineffective as a boundary lubricant for aluminum machining promoting cyclic hydrolysis that generates brittle Al(OH)3 films while generating friction above dry sliding. As traditional petroleum-based lubricants are increasingly recognized for their detrimental environmental impact, the development of sustainable alternatives has become essential in the tribology community. CHAAPILs derived from renewable amino acids and choline sources were specifically formulated …

Identification Of Strategies To Improve Milking Parlour Efficiency: Insights From Empirical Data And Simulation Analysis, Ryan Prendergast

Theses

The abolishment of European Union milk quotas in 2015 has increased the strain on dairy farm infrastructure and labour availability. For both pasture and confinement-based production  systems, the milking process requires the largest annual labour input. Hence, this area  represents an opportunity for achieving gains in labour efficiency. The aims of this thesis were to 1) document and quantify factors that affect milking process efficiency and 2) develop models that can simulate milking parlour efficiency with respect to these factors. Data were collected from a sample of commercial, pasture-based Irish dairy farms across the Republic of Ireland that used herringbone …

Secure Composite Digital Twin For Collaborative Ecosystems, Pasindu Kuruppuarachchi

Theses

The rise of collaborative digital ecosystems and the growing adoption of Digital Twins (DTs) in sectors like smart manufacturing, energy, and autonomous sys- tems underscore the need for secure, interoperable frameworks. This research proposes a Secure Composite Digital Twin Architecture (CDT) that enables seam- less integration and collaboration among DTs, addressing key challenges in trust, interoperability, and governance. The architecture features a trust analyser to assess DT behaviour and a repu- tation model to enhance security as the ecosystem scales. It supports centralised, decentralised, and hybrid governance via distributed ledger technology, enabling dynamic policies and secure, token-based asset management. For …

Potential Of Blood-Based Assays To Enhance The Diagnosis, Risk Stratification And Monitoring Of Multiple Myeloma Patients, Aisling O Brien

Theses

Multiple Myeloma (MM) remains an incurable haematological malignancy; however, continuous advancements in treatment strategies have significantly improved patient survival. There is now a pressing need for enhanced detection methods to ensure optimal patient outcomes. This includes rapid diagnosis, early detection of relapses, and identification of high-risk patients. Diagnosis: For optimal patient results, initiating early MM diagnosis at the primary care level is essential. Delays in diagnosis can result from nonspecific presenting symptoms such as anaemia and bone pain. A retrospective observational study identified calculated globulin as a promising clinical biomarker to indicate MM in primary care. Subsequent implementation of calculated …

Engineering Microphysiological Systems To Investigate Cellular Responses To Biophysical Cues In Human Tissue Microenvironments, Mehran Mansouri

Theses

Cells constantly sense and respond to biophysical cues in their microenvironment. Understanding how they interpret these mechanical signals is essential for advancing tissue modeling, studying disease mechanisms, and developing more predictive in vitro platforms. This dissertation presents a series of engineered microphysiological systems (MPS) designed to investigate how mechanical stimuli shape cellular behavior in distinct human tissue microenvironments. In Aim 1, I developed a reconfigurable microfluidic platform that mimics key features of human vascular barriers. This system supports the integration of porous membranes, 3D hydrogels, and flow channels, enabling precise control over both mechanical and biochemical cues. The modularity of …

Data-Driven Machine Learning Applications For Predictive Modeling Of Petrochemical And Ecofriendly Systems, Noora Saleh Al Mansoori

Theses

Traditional experimental approaches in industrial processes, such as Fourier Transform Infrared Spectroscopy (FTIR) spectroscopy, thermogravimetric analysis (TGA), and well-drilling operations, are often constrained by time, cost, and operational limitations. This research explores the application of data-driven Machine Learning (ML)-based predictive modeling to improve efficiency and reduce dependency on resource-intensive experimentation. The study develops ML models for three distinct processes: FTIR intensity prediction of bitumen thermal cracking products, thermal degradation of Medium-Density Fibreboard (MDF) using TGA data, and Rate of Penetration (ROP) prediction in petrochemical industry. Six algorithms: Linear Regression (LinReg), Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), Gradient …

Advancing Academic Advising With Knowledge Graphs: Integrating Machine Learning And Llms For Personalized Course Planning, Sara Alshamsi

Theses

Academic advising plays a critical role in helping students make informed decisions, improve academic performance, and successfully navigate their university journey. However, with increasing university enrollment, traditional advising methods often struggle to scale, leading to student frustration and overburdened advisors. Additionally, designing course offerings that match student demand is a complex and error-prone process involving multiple stakeholders. To address these challenges, this thesis proposes an automated, data-driven system for generating personalized academic plans for students. The primary aim of this thesis is to develop a system that reduces students’ dependency on advisors while simultaneously providing accurate estimates of course demand …

Electrospun Membranes From Bio-Renewable Poly (Ethylene Furanoate)/Poly (Ethylene Teraphthalate) (Pef/Pet) Blend For Emulsification Application, Aya Ismat Sayed

Theses

This thesis focuses on manufacturing electrospun fibrous membranes from a blend of poly (ethylene terephthalate) and poly (ethylene furanoate) and using in premix emulsification. Poly (ethylene furanoate), which is a 100% bio-renewable polymer being blended with synthetic poly (ethylene terephthalate) for membrane fabrication contributes towards sustainability in the production of food and pharmaceutical emulsions. The primary objective of this research is to optimize the fabrication conditions of poly (ethylene terephthalate)/poly (ethylene furanoate) porous membranes, characterize their properties, and evaluate their performance in emulsification. This study compares poly (ethylene terephthalate) / poly (ethylene furanoate) blend membranes with individual poly (ethylene terephthalate) …

Associations Between Vitamin D Deficiency And Sociodemographic Factors, Lifestyle Behaviors, And Metabolic Conditions: A Cross-Sectional Study From The Hnnhs In Greece, Asmae Mohamad Sadek

Theses

Vitamin D deficiency (VDD) is a widespread global health concern associated with various sociodemographic, lifestyle, dietary, and metabolic factors. While previous studies examined VDD in Greece, few provided a comprehensive analysis across multiple determinants using representative national data. This study aimed to assess the prevalence and predictors of VDD among Greek adults and to examine its associations with sociodemographic, dietary, behavioral, and metabolic variables using data from the Hellenic National Nutrition and Health Survey (HNNHS). A cross-sectional analysis was conducted among 978 adults (≥19 years) from the HNNHS. Serum 25-hydroxyvitamin D [25(OH)D] concentrations < 20 ng/mL were defined as deficient and ≥20 ng/mL as normal. The median age of participants was 40.2 years, and 62.0% were female. The overall prevalence of VDD was 46.0%, with the highest rate observed among adults aged ≥60 years (62.2%). VDD was significantly associated with older age (p < 0.001), retirement status (62.9% among retired; p < 0.001), low and sedentary physical activity (32.7% and 32.6% vs. 50.8% among highly active; p < 0.001), higher HDL (median 52.0 vs. 49.0 mg/dL among VDD vs Normal; p = 0.001), elevated serum calcium (median 9.4 vs. 9.2 mg/dL among VDD vs Normal; p = 0.020), and lower insulin levels (median 7.5 vs. 8.0 μIU/mL among VDD vs Normal; p = 0.044). Dietary intake (total energy and macronutrients) and body composition were not significantly associated with VDD. In the multivariate model, significant independent predictors of VDD included being retired (AOR = 2.383; 95% CI: 1.596–3.558; p < 0.001), having higher serum calcium levels (AOR = 1.563; 95% CI: 1.078–2.266; p = 0.019), and higher HDL levels (AOR = 1.016; 95% CI: 1.005–1.027; p = 0.001). Physical activity level was also a key determinant; participants classified as sedentary or low active had significantly higher odds of deficiency compared to highly active individuals (AOR = 0.468; 95% CI: 0.319–0.690; p < 0.001). This counterintuitive result may be influenced by factors such as increased indoor physical activity, and warrants further investigation. Dietary intake and body composition were not significantly associated with VDD. The findings underscore the importance of incorporating sociodemographic and lifestyle factors into prevention strategies. Interventions should particularly focus on older adults, retired individuals, even if they have higher HDL and calcium levels, and are physically active.

Gamified Gait Rehabilitation Via Real-Time Biofeedback And Adaptive Hip-Exoskeleton Control, Mariya Huzaifa Tohfafarosh

Theses

Gait impairments arise from systemic diseases, age-related degeneration, musculoskeletal dysfunctions, or neurological conditions. While traditional rehabilitation can be effective, they often face challenges such as high costs, inaccessibility, and low patient engagement. To address these challenges, my work introduces a virtual reality-based rehabilitation (VRBR) system, integrating real-time motion and electromyographic (EMG) muscle activation feedback with a gamified virtual environment for enhanced adaptability and engagement. The system includes a custom-designed hip-exoskeleton that provides adaptive spring-like assistance or resistance, supporting both mobility-impaired users and strength training. Assistance levels can be tuned to match the user's progress. Additionally, a custom pressure insole was …

Predicting Patient No-Show Rate In Healthcare To Improve Operational Excellence, Saeed Ahmed Al Wari

Theses

The challenge of integrating no-show predictive models into healthcare environments is complex and multifaceted, extending far beyond the distinct technical challenge of building accurate models. This thesis will discuss more on the subject of incorporating machine learning into healthcare. While algorithmic accuracy and model validation are critical, they are a mere sub-system of a much larger operational, technological, ethical, legal and human ecosystem. Predictive models face mass deployment in healthcare systems which are complex networks of stakeholders across strict regulatory frameworks and deeply embedded workflows (AlMuhaideb et al., 2019). However, for these models to result in long term and real …

Future Of Inclusive Education In The Uae: Supporting Learning Disabilities In Higher Education, Christina Ayub

Theses

Inclusive education is a critical component of higher education, ensuring that students with learning disabilities (LDs) receive equitable access to academic opportunities and institutional support. While global advancements in inclusive education have been significant, the UAE’s higher education sector faces unique challenges in accommodating students with LDs, particularly as technological disruptions, demographic shifts, and evolving policies reshape the broader educational landscape. This research investigates how a higher education institution in the UAE, such as RIT Dubai, might adapt its support systems for students with LDs, such as ADHD, dyslexia, dyscalculia, dysgraphia, and dyspraxia, under a range of plausible future conditions …

Shopping Quest: Transforming The Shopping Experience By Creating A More Immersive And Enjoyable Experience, Nagasai Vardhan Rao Sarvepalli

Theses

In the post-pandemic era, this thesis looks into how gamification and augmented reality (AR) can get customers back into physical retail settings. Brick-and-mortar stores have found it difficult to stay relevant as consumer preferences have shifted toward online convenience. Shopping Quest attempts to make in-store grocery shopping an engaging experience. The project started with qualitative surveys using a human-centered design process to determine the main frustrations of shoppers, which were navigation and remembering what to buy. The final idea makes use of a wearable AR interface that directs users with a virtual rocket and promotes exploration with collectible digital petals. …

Peach Street, Anastasia Lawrence

Theses

Peach Street connects to the universal phenomenon of losing innocence of childhood and navigating the perils and disappointments of the adult world and visualizes my ongoing experience with anxiety and what psychiatrists call derealization, the feeling of being detached from reality. Set in the same location as where I first felt immense panic, my photos create a fictional narrative where a small town, its residents, and the environment are being controlled by a force emanating from the town’s lake. The lake’s aura blinds the residents to its control, forcing them to live in a set way without personal expression or …

Access To Justice For Deaf Defendants, Anna Zieba

Theses

Deaf individuals face systemic accessibility within the criminal justice system, which emphasizes the importance of the gaps in accommodations by the Americans with Disabilities Act (ADA). Inconsistent legal protection, limited access to interpreters, inadequate training for legal professionals, and a lack of technology resources obstruct effective communication for Deaf individuals. As a result, it prohibits achieving an effective and equitable legal outcome. This research paper will examine case studies, legal frameworks, and academic literature to highlight the critical need for reform, including mandatory Deaf culture training, standardized interpreting qualifications, and more resources to enable equitable access to justice.

Examining Food Choice Determinants In Ncaa Division Iii Athlete Participants Representing Multiple Sports, Olivia Towne

Theses

Objective: To examine determinants of food choice among NCAA Division III athletes using the Athlete Food Choice Questionnaire (AFCQ), focusing on gender, sport type, and seasonal status. Participants: 72 NCAA Division III athletes from 13 sports at a private northeastern university participated in an online survey during Fall 2024. Methods: Participants completed the 32-item AFCQ assessing nine food choice factors. Independent t-tests and Pearson’s correlations were used to compare factor scores by gender, sport type, seasonal status, and team success. Results: Performance, Sensory Appeal, and Food Values and Beliefs emerged as the most influential factors in food choice, while Weight …

From Contact To Care: A Comprehensive Analysis Of Mental Health Practices Across The Criminal Justice Continuum, Violet Ameele

Theses

This capstone attempts to gain a further understanding of the state of mental health training, protocols, and practices across the continuum of the criminal justice system. The various sections of this paper will look at law enforcement, corrections, and court/community and their roles in mental crisis training and interaction. As the topic of mental health is something increasingly discussed in the present day, it is also something that is in need of more research, in order to create higher standards when it comes to individuals with mental health concerns and ensuring that they receive the proper levels of care that …

Police, Prisons, Communities, And Courts: An Examination Of Criminal Legal System Responses To Neurodivergence, Rhys Miller Evans

Theses

Mental health in the United States is largely stigmatized and overlooked as a factor of crime. This capstone project critically analyzes the response of actors in the criminal legal system to neurodivergence and identifies areas for improvement.

Part One focuses on how police respond to those with mental health conditions and community-based supports that can reduce harm during these interactions. This chapter provides an overview of the prevalence of neurodivergence in the United States and how police are, or are not, trained to protect and serve this subset of the population. It explains the Memphis Model of crisis intervention and …

A Systematic Literature Review Of Behavior Analysis In Psychiatric Inpatient Settings, Stephanie Henry, Robbie Hanson

Theses

Applied behavior analysis (ABA) may be best known for the treatment of individuals with intellectual or developmental disabilities, such as those with autism spectrum disorder (ASD). However, ABA also has a long history of effective outcomes with other populations, such as with individuals who are admitted to inpatient psychiatric facilities (Dougher, 2004; Harvey et al., 2009). In 2018, 187,877 individuals in the United States were reported as receiving treatment for mental health disorders (Lutterman, 2022). Given behavior analysis’ success implementing operant procedures with these populations, an updated review of the literature on the use of behavior analysis within these settings …

Glue Laminated Timber: A New Way Of Framing The Residential Architecture Of Upstate New York To Improve Thermal Performance & Energy Use Intensity, Griffin Jones

Theses

This thesis addresses the issue present within the current construction techniques for the residential architecture of Upstate New York. Modern platform framing has long been the dominant fashion for constructing homes in the United States, however the nature of this construction is instilled with the issue of thermal bridging, where the wood studs and structure allow heat to escape due to gaps in the continuous insulation. This study proposed a new way of framing residential architecture for the upstate region of New York, relying on glue-laminated timber (GLT) to replace dimensional sawn lumber. GLT has increased structural strength and stability …

Beyond The Badge: Predicting Military Employee Attrition In The Police Force, Alia Abdulla Alhajji

Theses

This study explores the issue of employee attrition within the military police force, with a focus on predicting which employees are at risk of leaving. Attrition in law enforcement is costly and disruptive, especially in roles that require long training periods and operational readiness. The research specifically targets the internal organizational factors influencing turnover in military police environments and aims to leverage machine learning models to support the early identification of high-risk individuals. Guided by the CRISP-DM framework, the study followed a structured process across six stages: business understanding, data exploration, preparation, modeling, evaluation, and insight generation. A simulated dataset …

Back To The Basics: Extracellular Protein Interaction Networks Of The Human Infant Immune System, Mavis Amity Irwin

Theses

Datamining without an age filter proves challenging, especially when searching for direct data from human infants. Although online databases provide immune interaction networks, they often lack information about the age of data sources, resulting in categorizations as age-unspecified. This limitation underrepresents the physiology of naïve immune systems in infants, particularly since full-term infant immunity transitions to an adult-like phenotype between 24 and 30 months of age. This study aims to reconstruct an age-specific immune interaction network for full-term infants by integrating literature-based evidence with existing online database content. A list of 60 extracellular protein candidates involved in immune responses was …

Innovating Criminal Justice: Predictive Analytics For Effective Recidivism Management, Dina Ali Haidar

Theses

Recidivism—the tendency of previously convicted individuals to reoffend—poses significant challenges to criminal justice systems worldwide. In the United States, a study by the Bureau of Justice Statistics revealed that approximately 68% of released prisoners were rearrested within three years, and 83% within nine years (Bureau of Justice Statistics, 2018). These high rates underscore systemic deficiencies in rehabilitation processes and resource allocation. Traditional risk assessment tools often rely on static factors, failing to account for the dynamic and individualized nature of reoffending risks. This limitation highlights the need for innovative, data-driven methodologies to enhance offender management strategies. This study proposes a …

Predicting Student Dropout Risk Using Machine Learning, Fatma Alameri

Theses

Student dropout remains a persistent challenge in higher education, undermining institutional performance, reducing workforce preparedness, and limiting students’ academic and economic opportunities. Accurately identifying students at risk of attrition is complex, due to the interplay of academic, financial, and behavioral factors. This thesis addresses this challenge by applying a combined machine learning framework—integrating both unsupervised and supervised techniques—to predict student dropout using structured, first-year academic and financial data. The study utilizes a comprehensive dataset of 4,424 undergraduate student records from a European higher education institution, covering ten academic years and comprising 35 variables related to academic performance, enrollment behavior, and …

Mary Kay Reimagined, Allison Terveer

Theses

This project is taking the brand Mary Kay and turning it into a new brand that would be enticing to younger generations and become a staple in everyone and anyone’s routines. Mary Kay was a huge makeup brand in the 1990s and early 2000s, but the cosmetic industry has grown tremendously, and Mary Kay has fallen behind. They mostly target the older generations, the generations that were supporting them in the 1990s and 2000s. They need to expand their target range and get younger consumers to pay attention to them. With updated packaging, new marketing and a new way to …

Countering The Traditional Feminine: The Abject In The Works Of Johanna Hamann, María Evelia Marmolejo, And Regina José Galindo, Sierra Myers

Theses

This thesis explores the ways in which Contemporary Latin American feminist artists have been able to subvert the Western constructed ideas of gender that work to locate the feminine Other as subordinate and inferior. Focusing on the installations and performances by Johanna Hamann, María Evelia Marmolejo, and Regina José Galindo, there is an emphasis on the role of the abject which is used to defamiliarize our established concepts of the traditional feminine in order to allow space for a redefinition and portrayal that excludes a detrimental modern semiology rooted in a zero point epistemology. By analyzing these artists' works in …

Horror Films And Why We Enjoy The Genre, Jessica Thomason

Theses

This project focuses on the research of horror films and why certain individuals enjoy the genre despite having taboo subjects. The primary focus is to find the answer to the research question “why do some individuals enjoy horror?”. The aim of this research was to identify a connection between why individuals enjoy horror through the content. The research then informed the creative process behind the painting series that accompanies this project.