Digital Commons Network^™

Systematic Evaluation Of Regression Models For The Prediction Of Influenza Cases, Mukul Kandwal

Theses

This study systematically evaluates machine learning models to forecast influenza outbreaks, aiming to enhance public health preparedness through accurate predictions. Laboratory-confirmed influenza case data from the New York State Department of Health (2009–2023) were used to train and test five regression models—XGBoost, Neural Network (MLP regressor), K-Nearest Neighbors (KNN), Random Forest, and Support Vector Regression (SVR)—with preprocessing techniques including differencing and phasing. A leave-one-season-out cross-validation framework and Symmetric Mean Absolute Percentage Error (SMAPE) were employed to rigorously assess performance. Key findings reveal that the Neural Network (MLP regressor) outperformed other models, achieving the lowest SMAPE score (23.7), underscoring the critical …

Advances In Machine Learning For Pain Recognition: A Review Of Algorithms, Modalities, And Outcomes, Abdulrahman Alsharif

Theses

The emergence of machine learning (ML) in healthcare has unlocked the transformative potential of pain detection and assessment. By providing new ways to address the challenges associated with subjective and inconsistent pain assessment methods. This review synthesizes recent advancements in ML-based approaches for pain detection, focusing on algorithms, modalities, and datasets. Techniques such as neural networks, transformer models, and multimodal fusion frameworks have demonstrated significant promise in identifying pain from diverse sources, including facial expressions, physiological signals, and synthetic datasets. Key contributions include novel transformer-based architectres like PainAttnNet for analyzing electrodermal activity [1], multimodal datasets such as BioVid for advancing …

Alternative Antimicrobial Strategies For Neonatal Infections, Anna Desmond

Theses

Neonatal infections, a significant contributor to infant morbidity and mortality worldwide, are predominantly caused by pathogenic bacteria. Globally, bacterial sepsis accounts for 11.3% of neonatal deaths with Group B Streptococcus (GBS) being the leading cause, along with Escherichia coli, and coagulase negative staphylococci (CoNS). Neonatal infections caused by antibiotic resistant bacteria is now a worldwide concern, further increasing mortality rates and associated healthcare costs. Therefore, there is an urgent need to develop alternative antimicrobial strategies to combat resistance and/or enhance the efficacy of existing antibiotics. The overall aim of this thesis was to investigate alternative antimicrobial strategies for treating and …

Dubai’S Future Mobility: Systems Thinking & Scenarios, Mohammed Mazloum Hanafy

Theses

Transportation is one of the essential pillars of any smart city. The future of transportation in Dubai faces enormous hurdles in urban mobility, including a growing population density, congestion, and environmental issues. Without careful planning and policy actions, these problems would certainly worsen in the future. Thus, the purpose of this thesis is to investigate the future of urban mobility in Dubai and to suggest solutions for constructing a sustainable, efficient, and equitable transportation system by employing future foresight tools. Dubai has emerged in recent years as a global center for technological innovation, altering its built environment and reevaluating its …

Reviving The Golden Age: Exploring Will Eisner's Legacy Through The Creation Of A Multiversal Sequential Art Story, Levi Atkins

Theses

Levi Atkins’ thesis explores the legacy of Will Eisner, a foundational figure in comic book history, through the creation of a multiversal sequential art story. The project combines a seven-page black-and-white comic with a scholarly analysis of Eisner’s storytelling techniques, focusing on his public domain characters from the Golden Age of Comics. Atkins examines how Eisner’s innovations—such as dynamic panel design, cinematic pacing, and genre blending—can inspire modern narratives. By reimagining characters like The Flame and Dollman within a multiverse framework, the thesis both honors Eisner’s legacy and demonstrates how historical comic forms can evolve to engage contemporary readers.

Towards Characterizing And Quantifying Interpretability Of Knowledge Graph Embedding Models, Narayanan Asuri Krishnan

Theses

Knowledge graphs are structured representations of real-world information, where entities are connected by edges with labels known as predicates. These graphs contain logical patterns, known as inference patterns, such as symmetry, transitivity and composition, to name a few. To leverage the information contained within a knowledge graph, embedding methods have been developed to encode entities and predicates as numerical vectors in a multi-dimensional space. These embeddings aim to capture the semantic and structural information of the graph, including the inference patterns. However, the sub-symbolic nature of these embeddings present significant challenges in terms of interpretability. Additionally, each embedding model utilizes …

Analytical Method For Solving Systems Of Fractional Initial Value Problems Using The Modified Atangana-Baleanu Derivative, Lana Mohammad Aref

Theses

This thesis presents an analytical method to solve systems of fractional initial value problems using the Modified Atangana-Baleanu Fractional Derivative. The proposed approach leverages an improved operational matrix method, incorporating an iterative, direct computation technique to simplify the solution process and reduce computational costs. Foundational concepts in fractional calculus and block pulse functions are introduced, followed by the derivation of operational matrices tailored for fractional systems. Theoretical analysis establishes the existence and uniqueness of solutions, along with uniform convergence and error estimates. Practical examples and applications are presented that demonstrate the efficiency, accuracy, and versatility of the method in solving …

Under The Bay: Analysis Of Green Sea Turtle (Chelonia Mydas) Dive Behavior In The Urban San Diego Bay, Emily Carter

Theses

Sea turtles are air-breathing marine reptiles that spend their lives performing dives to travel, forage, and rest. Several dive types have been previously recorded for sea turtles, each type being associated with a different set of behaviors. U-dives, or Type 1 dives are widely characterized by extensive benthic periods preceded by and concluding with abrupt descent and ascent phases respectively (Minamikawa et al. 1997; Houghton et al. 2002; Seminoff et al. 2006). These dives are widely affiliated with turtle resting behavior though can be indicative of additional activities including benthic travel and foraging. Previous research of green turtle dive behavior …

Climate Influence On Both Spatial And Temporal Patterns Of Rocky Intertidal Community Structure In San Diego, California, Emily Jenkins

Theses

The rocky intertidal ecosystem, the coastal area between high and low tides, serves as a critical buffer between land and sea. This ecosystem supports a diverse array of species and provides rich opportunities for exploration and education. With the influence of climate change, this ecosystem faces significant shifts in species distribution, resilience and recovery from environmental disturbances, as well as habitat loss (Jackson & McIlvenny 2011; Jueterbock et al. 2013; Menge & Gravem 2022; Rilov et al. 2021; Sagarin & Barry 1999). Between 2014-2016, climate anomalies El Niño (ENSO) and the Pacific Decadal Oscillation (PDO) combined to create a period …

Enhancement Of Firefighter Mental Performance: A Review, Nicole A. Ness

Theses

Background: The life-or-death nature of firefighting exposes those who respond to calls to an increased number of stressors that can impact performance and overall well-being. To combat this, the mental element of firefighting can be optimized through psychological skills training programs and mindfulness training. Other tactical populations, such as the police force, military, and emergency medicine units have found success in implementing these interventions, Literature suggests a similar effect may be observed in firefighters because of their similar demands; although, little research exists regarding the effects of mental performance programs on firefighter populations specifically.

Methods: A review of existing literature …

Predicting Customer Churn In B2b Consulting Services, Mediya Alfalasi

Theses

The aim of this research was to develop a machine learning model that can predict customer churn in the consulting industry. The goal was to help businesses identify customers who might leave, allowing them to take action before it happens. To achieve this, a dataset was created by combining different data sources to reflect real-world customer behaviors. After cleaning the data and addressing issues like missing values and data imbalance, four machine learning algorithms—XGBoost, Neural Network, Random Forest, Logistic Regression, and Support Vector Machines (SVM)—were used to build the prediction models. The findings showed that XGBoost performed the best, achieving …

Fake News Detection On X (Twitter), Sultan Mayoof Almutaiwei

Theses

The most important innovation globally is the internet, which is used by a huge number of people all around the world. People use the internet for different purposes. By using different social media platforms people share content and news. Thus, some people use these internet platforms to share false news or fake news among people. Propaganda against a person, group, organization, or political party may be present in this news. For an individual, it is difficult to distinguish between false and true news over the internet. Therefore, machine learning is the smart solution that can identify fake news on the …

Enhancing Waste Management And Circular Economy Practices In Higher Education Institutions In Uae: A Study On Current Policies And Strategic Framework, Muna Ali

Theses

This study investigates the integration of Circular Economy (CE) principles within higher education institutions (HEIs) in UAE as a method to address waste challenges in UAE. Despite the announcement of UAE 2021-2031 Circular Economy Policy, and the nationwide continues promotion of sustainability initiatives, HEI’s lack the availability of tailored policies and procedures as well as guiding framework to address their waste challenges and adapt CE within their institutions. To assess this problem, a survey has been distributed to 45 CAA accredited public and private universities in UAE. A qualitative approach has been used to analyze the survey responses. The survey …

An Integrated Decision Support System (Dss) For Sustainable Supplier Selection, Evaluation, And Benchmarking Using A Fis And Molp Approach, Saleem Ghannam

Theses

Applications of sustainable supplier selection criteria in supply chain management are less developed compared to other evaluation methods. This study focuses on three main dimensions of sustainable supplier performance: economic, environmental, and social criteria. The research aims to identify significant criteria within each dimension that are crucial for the sustainable supplier selection process. These criteria will be utilized to develop a hybrid decision support system that integrates a fuzzy inference system with multi-objective linear programming. This comprehensive model will evaluate and benchmark supplier sustainable performance, providing an overall assessment of supplier performance. The proposed model offers a holistic approach to …

Prediction Of Vessel Arrival Time To Optimize Berth Allocation In Ports Using Machine Learning Methods, Anfal Mansour Albloushi

Theses

80% of the world trade is carried out through the sea, which shows the importance of maintaining transportation efficiency in the maritime industry. The vessel arrival time and berth allocation pose a significant challenge in the marine field's day-to-day operation, especially when a high number of vessels are waiting at the anchorage to deliver the goods on time. This increases the pressure on the responsible stakeholders and good owners as some cargo must be delivered urgently. Artificial intelligence and machine learning play a vital role in improving the operation of different fields; utilizing such technologies in the maritime industry will …

The Effect Of Biochar As Partial Cement Replacement On Mechanical, Durability, Thermal, And Microstructural Properties Of Concrete - Comparison With Biomass, Aysha Yousef Alsaadi

Theses

This thesis paper examines the use of 1% cement replacement with date palm derived biochar and compares it to 1% replacement of biomass. The main aim of this idea is to reduce the carbon emissions from concrete production factories and utilize the abundant waste from date palm plants, which is prevalent in the UAE. Three samples of concrete were used: 1% biochar mix, 1% biomass mix, and a control mix. Mechanical tests, including compressive, tensile, and flexural strengths, were evaluated. Thermal conductivity, chloride penetration, water absorption, and characterization testing by XRD, TGA, SEM, and FTIR were conducted. As for compressive …

Space-Time Analysis Of The Sea Level Variability Of The Arabian Sea Using Satellite Altimetry Data, Saleha Saeed Binishaq

Theses

The ongoing effects of climate change are contributing to a gradual rise in sea levels, which has become a significant environmental concern. It creates a serious threat to coastal areas, especially in the Gulf Region, which includes various cities bordering the Arabian Gulf, the Red and the Arabian Sea. This phenomenon has the potential to significantly influence the socioeconomics of the region by altering coastal marine ecosystems and can pose serious infrastructure sustainability challenges. This research focuses on analyzing the sea-level variability in the Arabian Sea using satellite altimetry data from 1993 to 2023. The analysis was conducted along a …

Extraction Of Activated Carbon From Date Palm Biowaste And Subsequent Preparation Of Ferrite Nanocomposite For Water Treatment In Uae, Anood Lashkary Ahmed Ibrahim

Theses

Ensuring access to clean and safe water remains a pressing global challenge, particularly in arid regions like the Gulf, where freshwater scarcity is severe. The United Arab Emirates heavily depends on energy-intensive desalination, which is increasingly turning to treated wastewater as a sustainable alternative. In this context, the recovery and reuse of biowaste and the development of advanced treatment technologies are critical. This study presents an innovative approach to wastewater treatment by utilizing biomass waste—specifically date palm leaves, an abundant agricultural residue in the UAE—as a raw material for producing activated carbon. Through pyrolysis, the biowaste is transformed into porous …

User Perceptions Of Ai Services In Abu Dhabi Government: An Empirical Study Of Satisfaction And Acceptance Factors On The Tamm Platform, Muneera Ali Zaher Alsulaimani

Theses

Artificial Intelligence (AI) is transforming how governments deliver services by enabling automation, personalization, and data-driven decisionmaking. In the United Arab Emirates, particularly in Abu Dhabi Emirate, the TAMM platform exemplifies this transformation, integrating AI to streamline citizen-government interaction. Understanding the factors that influence the user’s satisfaction of Powered AI services in the public sector is crucial for effective policy implementation and user engagement. This study employs a sequential explanatory mixed-methods approach, grounded in the Unified Theory of Acceptance and Use of Technology (UTAUT), extended with User Satisfaction as a fifth construct. Quantitative data were collected from 137 TAMM platform users …

The Role And The Limitation Of Ai Implementations In Pcb Defect Detection, Hamad Saeed Mohammed Alyammahi

Theses

This research explores the transformative impact of Artificial Intelligence (AI) on quality control in Printed Circuit Board (PCB) fabrication, explicitly focusing on enhancing defect detection processes. As PCB designs become increasingly complex and dense, traditional inspection methods, such as manual inspection and Automated Optical Inspection (AOI), need to be revised to meet the precision and efficiency demands of modern electronics manufacturing. Manual inspection is often slow and labor-intensive, while AOI needs help with accuracy in detecting subtle defects in intricate designs, leading to potential errors in quality assurance. This study investigates AI-driven techniques to overcome these challenges, leveraging deep learning …

A Comparative Analysis Of Machine Learning Models For Predictive Process Monitoring Using Objectcentric Event Logs, Buthaina Hasan Aidaros Alhebshi

Theses

The increasing complexity of business processes drives the need for advanced predictive monitoring solutions capable of handling multi-entity interactions. Traditional case-centric event logs fall short of capturing these complexities, leading to the emergence of Object-Centric Event Logs (OCEL). Despite the growing interest in OCELs, their structural complexity and impact on predictive performance remain unexplored. This thesis investigates how process complexity influences the performance of machine learning models in predictive process monitoring using OCEL. A framework combining Graph Neural Networks and graph embedding-based models is applied across three predictive tasks: next activity, next timestamp, and remaining time prediction. The evaluation covers …

An Inclusive Learning Metaverse: A Virtual Reality Approach To Supporting Dyslexic Children, Reem Salem Mohammed Salem

Theses

Dyslexia is one of the most common learning difficulties worldwide, often requiring tailored interventions targeting phonological awareness, reading comprehension, and cognitive support. This study explores the design and evaluation of a metaverse-based virtual reality (VR) application to support dyslexic children in the UAE. Using a usercentered, explanatory sequential mixed-methods approach, the research involved three phases: a stakeholder survey with therapists, educators, and parents (N = 151), development of a multi-featured VR prototype, and evaluation by six dyslexia experts. The survey identified key priorities such as progress tracking, adaptive learning, accessibility, working memory, and attention, along with concerns about VR unfamiliarity, …

Evaluating Bias In Facial Recognition Datasets : A Study On Representation And Classification Fairness, Milyonta Williams

Theses

Facial recognition technology is widely used in security and identity verification but exhibits biases that disproportionately impact certain demographic groups. This thesis examines racial and skin tone biases in commonly used facial recognition datasets, assessing their influence on classification models. Using manual classification via the Fitzpatrick scale and numerical skin tone representations from LAB color values, we identified significant dataset imbalances, with lighter skin tones (Fitzpatrick Types 1 and 2) overrepresented and darker tones (Types 4-6) underrepresented. Model evaluation using Random Forest, SVM, and XGBoost showed an overall accuracy of 72\%, but classification for Asian individuals was notably weaker (0.45 …

Modifying The L-Tryptophan Affinity Of The Ribosomal Arrest Peptide Tnac, Alexis Orlando Delgado Castillo

Theses

Since creating biosensors from zero has proven a more challenging enterprise than expected, resorting into naturally occurring regulatory systems already characterized represents a more accurate, rapid, and attractive option. Various previous strategies have sought to exploit and modify regulatory elements that sense for different molecules, including monosaccharides (Tang et al., 2008), secondary metabolites (Flachbart et al., 2021), and other amino acids (Della Corte et al., 2020). This study aims to leverage current scientific knowledge and advances concerning the structure and function of the ribosomal arrest peptide TnaC. With this research I integrated the TnaC ribosome-arresting peptide into a new biosensor …

Aviation Weather Forecasting Utilizing An Artificial Neural Network, Joshua Mote

Theses

Weather forecasting is critical to minimize risk and maximize efficiency for flying operations and is challenging due to the uncertainty involved in atmospheric changes. Operational area weather is becoming more critical with the growing reliance on air domain for transportation. This study investigates whether the forecasting accuracy using a Hybrid Long-Short Term Memory (LSTM) Artificial Neural Network (ANN) outperforms the San Antonio International Airport (KSAT) Terminal Aerodrome Forecast (TAF) by integrating diverse data sources – regional Meteorological Aerodrome Report (METAR), TAF, Avian Advisory System (AHAS) Data and geomagnetic activity K Index Data. When tested on one year of historical data, …

Improving Satellite Needs Working Group Assessment Process Through Automation And Process Consolidation, Raj Dangol

Theses

The increasing complexity of modern software ecosystems, presents significant challenges to system resilience, maintainability and automation. This work presents a proof-of-concept implementation of an automation system to address these challenges for a large scale fragmented software systems. Succinctly we address these challenges in the context of Satellite Needs Working Group (SNWG), which is responsible for collecting and communicating federal agencies' Earth observation needs to National Aeronautics and Space Administration (NASA). Multiple automation scripts and applications exist to support the SNWG's assessment cycle, encompassing the areas of data validation, visualization, report generation, and user management. However, the dispersion of these tools …

Sliding Mode Control Design Using Generalized Relative Degree Approach : Aerospace Application, Robert J. Jesionowski

Theses

The relative degree (RD) approach is a powerful tool, for obtaining a system’s input-output dynamics of an output tracking controller design with minimum phase dynamics. Designs using RD alone can fail due to insufficient control authority in minimum phase systems, and instability of internal/zero dynamics attributed to non-minimum phase systems. Generalized RD (GRD) in minimum phase systems can identify parasitic control terms (PCTs). An Alternate GRD (AGRD) is investigated, to determine the impact of discarding these PCTs. A novel definition for Practical GRD (PGRD) is proposed and used in concert with Sliding Mode Control (SMC) compensating system perturbations in minimum …

Surveying Subterranean Biodiversity Of The Tongass National Forest Using Traditional Survey Approaches And Environmental Dna (Edna) Metabarcoding, Jared P. Higgs

Theses

The Tongass National Forest (TNF) is a large temperate rainforest in southeastern Alaska, much of which is underlain by karst. Timber harvest, among other threats, can have detrimental effects on karst habitats; however, the subterranean fauna of this region is understudied and lacks a baseline for monitoring. I spent three field seasons conducting biological assessments of caves in the TNF using two approaches: traditional specimen-based sampling and eDNA metabarcoding. To improve the reference sequence database, I generated 213 novel sequences from invertebrate specimens collected from 35 caves. I also collected 125 water samples from 39 sites for environmental DNA (eDNA) …

Experimental Evaluation Of Recent Theoretical Real-Time Signal Higher-Order Sliding Mode Differentiators On Noisy Sensors, Jessica Hamer

Theses

This thesis explores the performance of higher-order sliding mode differentiators applied to sensor signals under varying sampling rates and switching functions. Two differentiator designs are evaluated: a hybrid algorithm that combines a super-twisting algorithm with a linear observer, and a fixed-time higher-order sliding mode differentiator. Each was tested on a physical sensor testbed using position data from a servomotor and electronic compass. The differentiators were implemented in a ROS2 environment, and their estimates were evaluated by obtaining the minimum and maximum position and velocity values, as well as analyzing graphs to capture the nature of the algorithms' noise reduction. The …

Utilization Of Artificial Intelligence To Predict Surface Energy Budget, Joseph Bonucchi

Theses

Estimating heat and moisture exchange between the land and atmosphere has several important practical applications, including water resource management, air pollution forecasting, and atmospheric propagation modeling. Turnkey systems for measuring the surface energy budget typically cost between $5,000 and over $50,000. This study explores the use of artificial intelligence (AI) to predict sensible heat flux (SHF) and latent heat flux (LHF) using inexpensive surface meteorology data and downwelling solar radiation measurements as inputs. Observations from Amer- iFlux sites were used to train several AI models—Convolutional Neural Networks (CNNs), One Dimensional Transformers (1D Transformers), Artificial Neural Net- works (ANNs), and Long …