Digital Commons Network^™

Surveying The Role Of Visual Analytics In Human-Machine Teaming, Naga Datha Saikiran Battula

Theses

Humans and machines both possess their unique capabilities and have their strengths and weaknesses, which can be complementary to one another and allow them to achieve a common goal. Teaming in the modern era involves text prompts, voice commands, gesture recognition, touch interfaces, and the latest visualization techniques that allow parties/agents to interact. Communication through visualization plays a vital role in allowing robust insights to be gained through a glance. Using visualization as a medium between humans and machines can increase the communication bandwidth. Human-machine teaming has witnessed much progress, with many theories and practical examples emerging. In the report, …

Automated Segmentation Of The Ulnar Nerve In Mri Using Deep Learning Techniques, Akhil Nagulapalli

Theses

Cubital Tunnel Syndrome (CuTS), a condition caused by compression of the ulnar nerve, results in numbness, tingling, pain, and even muscle atrophy, affecting fine motor skills and diminishing patient quality of life. Accurate diagnosis of CuTS is challenging, as current diagnostic methods—including clinical exams, nerve conduction studies, and unaided MRI—often lack the precision to reliably identify the nerve and detect compression in its early stages. Deep learning-based segmentation offers a promising solution, enabling precise and automated identification of nerve structures in MRI images, which could significantly improve diagnostic accuracy and support timely intervention.

A novel deep learning model for segmenting …

Exploration Of The Iterative Design Process: Integrating A Requirements Matrix And Hazard Analysis Toolsexploration Of The Iterative Design Process: Integrating A Requirements Matrix And Hazard Analysis Tools, Blaine Edlefsen

Theses

The iterative design process is applied to multiple industry sectors from software development to product manufacturing. The cyclical approach integrates the steps of design, prototyping, and testing toward the realization of a user's specified needs. The use of a requirements traceability matrix and hazard analysis documentation that supports the definition of the iterative design process is explored. These design project management tools are applied to a case study involving workholding design for a Wire Electrical Discharge Machining (Wire-EDM) manufacturing process. This industry-relevant case study is conducted in collaboration with New Jersey Precision Technologies, Incorporated (NJPT). The design requirements involve both …

Advancing Prediction Of Stimulant Medication Misuse Through Graph Representation Learning, Hamid Razavi

Theses

The misuse of stimulant prescription medications poses a significant and escalating public health concern in the United States, particularly among young adults. Addressing this issue requires sophisticated methodologies capable of uncovering complex patterns and relationships in data. Geometric Deep Learning, a paradigm designed to analyze data with non-Euclidean structures, has achieved remarkable success across various domains, offering a powerful framework for tackling complex graph structure data challenges.

This study leverages Graph Convolutional Networks (GCNs) to predict the likelihood of stimulant medication misuse using data from the National Survey on Drug Use and Health (NSDUH). Individuals are represented as nodes in …

Optimizing Wind Wing Wall Ventilation In High-Rise Buildings Within Dense Urban Hot And Humid Climate., Arushi Bhatia

Theses

This study investigates how wing walls can increase natural ventilation in high-rise structures, particularly in hot, humid locations such as Mumbai, India. Using wind flow simulations and computational fluid dynamics (CFD) modeling, the study investigates how wind direction and the installation of wing walls affect airflow throughout the building. The study examines four scenarios, each analyzing how airflow varies when a building is located near surrounding structures of differing heights. It uses comprehensive CFD simulations to assess how alternative wing wall depth design can affect ventilation, as well as how wall-to-window ratio variation can contribute to airflows. Following these simulations, …

Comparative Analysis Of Earth-Bermed And Conventional; Single-Family, Residential Homes In The Hudson Valley Region, Beacon, New York, Michael G. Patchen

Theses

This thesis is a comparative analysis of the environmental sustainability between two similar square-foot, single-family residential homes constructed as a bermed shelter and the conventional wood frame in the Hudson Valley Region, Beacon, New York. The research will focus on the two designs' embodied carbon, cost, and energy use. To quantify the environmental impact of these two construction methods, an in-depth understanding of the diverse host climate is necessary. Climate data and the results from the experiments are collected by performing life cycle, cost, and energy analysis, providing insights into the environmental implications of residential construction methods. The methodology will …

From Factories To Homes: A Comparative Analysis Of Adaptive Reuse In New England Industrial Buildings For Multi-Family Residential Conversion, Jeremy Weeden

Theses

The adaptive reuse of industrial buildings offers a promising path toward sustainable urban development, particularly in New England. This study investigates the feasibility and energy efficiency of converting an older, unused industrial building into a multi-family residential structure by evaluating three distinct wall assemblies that preserves the exterior brick facade: existing structural brick, a typical adapted wall assembly with interior 2x4 wood construction, and a high-efficiency adapted wall assembly with an additional interior 2x6 wood construction. Through a detailed case study analysis focusing on the building’s core and shell, this research aims to identify the most effective wall assembly for …

Toward Prototypical Vision Clustering, James Chenhao Liang

Theses

Over the past decades, deep learning methods have emerged as the predominant approach in computer vision. Most approaches rely on complex interactions among pixels, involving heavy computations. However, Human vision possesses a unique attention mechanism that selectively focuses on relevant parts of the visual field while disregarding irrelevant information. This can be likened to a clustering approach, in which individual pixel points are decomposed and reorganized into relevant concepts to address various tasks. This dissertation explores the frontier of vision clustering by integrating innovative prototypical learning with advanced Transformer architectures, which heralds a significant paradigm shift applied to vision clustering. …

Leveraging Machine Learning For Advanced Malware Detection, Khalifa Al Habtoor

Theses

The detection of malware is an important challenge in the field of cybersecurity, which is demanding efficient and accurate solutions for making threats easier. This study is focused on the detection of malware by integrating a framework that uses a Mamdani fuzzy interference system (FIS) and diffusion techniques based on three different deep learning algorithms, which are convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs) for malware detection by using recent dataset. This was done by using their outputs through a voting and routing mechanism. The results of the study show that the fuzzy logic …

Modeling Stormwater Driven Plastic Debris In The Lake Ontario Watershed, Jayson A. Kucharek

Theses

Stormwater-driven plastic debris has emerged as a significant contributor to environmental pollution, particularly in urbanized watersheds like the Lake Ontario basin. This study focuses on developing a comprehensive framework to quantify and predict anthropogenic debris (AD) inputs and transport pathways across Monroe County, NY, using stormwater systems as a key vector. Over two years, empirical data on plastic debris were collected from storm drains retrofitted with LittaTrap™ devices across urban and suburban areas. Debris was weighed, categorized by material and use, and paired with spatial and temporal variables such as land use, rainfall, temperature, and wind events. A Support Vector …

Rental Property Demand And Supply Analysis Using Machine Learning, Ahmed Amiri

Theses

The real estate market in Dubai is famous for its activity and stimulating potential due to the geographical position of the emirate, well-developed transport and legal framework. Timely determination and prediction of rental price is crucial for investors, property owners and managers, tenants and authorities in their decision making to maximize returns and ensure market stability. Traditional approaches are insufficient for the analysis of the temporal and spatial relations between property characteristics and market processes, which require the use of sophisticated machine learning algorithms. This paper aims to predict the rental prices of properties in Dubai using machine learning models …

Amorfe: An Ai-Integrated Interactive Brainstorming Interface, Ipshita Pal

Theses

Amorfe is an interactive multi-touch digital interface that reimagines brainstorming and collaboration using artificial intelligence (AI). Designed to make ideation more dynamic, the platform allows participants to explore, merge, and refine ideas in real time. AI is a creative catalyst, offering unpredictable outcomes and streamlining the brainstorming process. This makes Amorfe engaging, intuitive, and inclusive, encouraging active participation. The platform’s potential was demonstrated through a hypothetical scenario: “How do we create more green spaces on the RIT campus?” Four participants explored various brainstorming phases through touch interaction, leading to the creation of a prototype simulation video and a promotional video. …

Social Media Intelligence: Responding To Crime And Violence In The Digital World, Chloe Lynn Sitton

Theses

The integration of social media into everyday life has transformed how crime is committed, communicated, and investigated. This capstone project examines the emerging field of social media intelligence and its growing influence on modern policing, surveillance, and the community. Drawing from sociological theory, law enforcement practice, legal analysis, and community-based research, this project offers a far-reaching interdisciplinary view of how social media is shaping crime and justice in the United States.

Machine-Learning And Game-Theoretic Inspired Strategies For Adversarial Freeze-Tag, Matthew Giacovelli

Theses

In this thesis, we explore three machine-learning and game-theoretic inspired strategies to address the Freeze-Tag Problem with adversarial agents (FTPA). We develop a custom Gymnasium envi- ronment where unfrozen robots collaborate to “tag” and unfreeze immobile frozen robots while avoiding being tagged by the adversaries. The FTPA models scenarios such as restoring disabled relay towers after a cyberattack where different towers vary in priority, repair difficulty, and ad- versarial threats. We evaluate three strategies: a baseline heuristic where unfrozen robots target the nearest untargeted frozen robot, a hierarchical approach that incorporates adversary interac- tions and likelihood of success into decision-making, …

Improving Obsolescence Management By Enhancing Supplier-Customer Collaboration, Mora Issa

Theses

There are currently many legacy facilities operating in the Middle East & Africa region that have plans in place to extend the plant life. Oil prices have been steadily going up, leading to increases in production, and driving economic growth. In order to extend the life of these older facilities, the sites are budgeting to replace critical parts accordingly. Obsolescence is an inevitable part of every product lifecycle and, with the new wave of technology and AI in the market, facilities face the challenge of increasing profitability in the fast-paced economy. The number of more efficient upgrades available presents an …

Analysis Of Team Size Effects On Technical Debt And Code Quality For Open Source Projects, Tyler Borrelli

Theses

Little research has been done to analyze the relationships between the amount of Technical Debt in an open source software project and the number of developers. This study seeks to identify the effects that team size and number of contributors have on Technical Debt and overall software quality. The results of the study observed after accounting for effects from code size that there was a negative correlation for issues with software quality, for example code smells or complexity, and the number of authors on a per file basis. This suggests that increasing the developer count most likely will not negatively …

Predicting Students At Risk Of Dropping Out In The College Of Medicine At Mohammed Bin Rashid University Of Medicine And Health Sciences. A Machine Learning Approach To Understand Attrition Factors Over The Past Seven Years, Moza Sulaiman Al-Zaabi

Theses

This master’s thesis investigates student attrition within the College of Medicine at Mohammed Bin Rashid University of Medicine and Health Sciences (MBRU) by applying the CRISP-DM methodology to analyse a dataset of 19 variables and around 2,000 records from Student Admission and Academic Performance sources. Although the dataset was relatively small, several machine learning models were developed to predict students at risk of dropping out, including Logistic Regression, Decision Trees, Support Vector Machines (SVM), and Artificial Neural Networks (ANN). Of these models, the ANN model, particularly when combined with Principal Component Analysis (PCA), achieved the highest performance with an accuracy …

Ai-Driven Anomaly Detection In Cybersecurity, Mohamed Almansoori

Theses

India has witnessed a huge level of digitization in the last two decades which has greatly impacted its economy and society. But the increasing use of technology has also intensified the number and level of threats to cyberspace in the country. Signature-based detection systems that have dominated the cybersecurity field for years have not been up to the challenge of modern attackers who use more complex and diverse attack methods. These challenges are well understood and this research focuses on improving the cybersecurity anomaly detection in India during the period between 2003 and 2022 using advanced AI and machine learning. …

Money Laundering Transactions Chronology Analysis Using Artificial Intelligence, Marwan Alawadhi

Theses

Money laundering is one of the most significant threats for the financial systems of the world, as it promotes other crimes and destabilizes the economy. This thesis presents an enhanced analysis of AI and ML on financial transaction data for the identification of patterns that relate to money laundering. It uses techniques like the Isolation Forest for the identification of outliers and clustering techniques like K-means and DBSCAN for identification of unusual transaction patterns across the four high risk countries that include United States, United Kingdom, Japan and Italy. The preprocessed dataset included different types of transactions like cross-border transactions, …

Comparative Analysis Of Artificial Intelligence And Statistical Models For Li-Ion Battery Cells State Estimation In Electric Vehicles, Rasha H.A. Tabasha

Theses

This graduate paper presents a comparative study of statistical modeling and Artificial Intelligence (AI) approaches for estimating essential parameters of lithium-ion (Li-ion) batteries in electric vehicles (EVs). The key parameters estimated in this study are voltage, current, and temperature of Li-ion battery cells in EVs. A precise state estimation is required to ensure safety operation, to optimize the Battery Management System (BMS), and to enhance the battery life. Variations in EVs batteries parameters may occur due to different reasons such as sensor faults or attacks. As a result, obtaining an accurate estimation is essential to maintain EV battery efficiency. Using …

Applications Of Neural Networks In Parkinson’S Disease Diagnosis, Saladin Minhaaj

Theses

Parkinson's disease (PD) is a complex and debilitating neurodegenerative disorder that affects millions of people worldwide. Early and accurate diagnosis is crucial for effective treatment and management of PD. This thesis explores the application of neural networks in PD diagnosis, leveraging their ability to learn patterns from large datasets and make accurate predictions.

Thesis provides an overview of PD, including its symptoms, diagnosis, and current challenges in diagnosis. We then delve into the fundamentals of neural networks, including supervised learning, mathematical interpretations, and parametric models. This research focuses on the development of neural network models that can accurately diagnose PD …

Lost Roots, Graziela Larroca

Theses

Lost Roots is an interactive 2.5D exploration game where players unite spirits by growing an underground network of roots. With a limited amount of roots to grow, players must unlock memories of the deceased and navigate through a cemetery in order to advance. The game serves as a unique take on the idea of purgatory, where the soul is essentially stuck and the player must find their own way out. The player first awakens underneath a tombstone with no memories of the past. Their only ability is to navigate through the dirt as a singular root, navigating around obstacles to …

Near Real-Time Center Of Gravity Estimation Of An Unmanned Aerial Vehicle, Carola Vasquez

Theses

As UAV technology advances and finds broader applications across industries, real-time estimation of the center of gravity (CG) becomes crucial for ensuring safe and efficient flight. Accurate CG estimation is vital not only for UAVs but also for manned aircraft, as it significantly influences stability and control by indicating the point where the entire weight is evenly distributed. Variations in CG, resulting from changes in altitude, attitude, speed, fuel consumption, and payload, directly impact stability and may lead to compromised performance and increased risk of accidents if not monitored. Existing methods focus on regression analysis, multi-accelerometer measurements, and pitching moment …

Community Response To Floods In The Cache River Watershed Of Southern Illinois: Application Of A Proposed Framework For Assessing General And Specified Community Resilience, Raymond Albert Bieri Iii

Theses

Recent years have seen increased awareness about the potential adverse impacts of climate change on hydrologic systems and human communities. The concept of community resilience – the capacity of communities to respond to drivers of change in a manner that maintains or improves upon community well-being – is widely recognized as a suitable framework for informing climate change adaptation policies. Emerging insights from the community resilience literature highlight the importance of the distinction between general resilience, which refers to the resilience of social-ecological systems to all kinds of drivers of change, and specified resilience, which is concerned with the resilience …

Predator-Prey Interactions And Space Use Strategies For Two Mesocarnivores, Abigail Weber

Theses

Mesocarnivores, including bobcats (Lynx rufus) and coyotes (Canis latrans), serve an important ecological role, functioning as the top predators throughout much of the eastern United States due to the extirpation of larger-bodied carnivores. Mesocarnivores are often described as generalists due to their flexibility in forage and habitat preferences and their ability to persist in human-dominated landscapes. However, this characterization overlooks the fact that many individuals within these populations act as specialists, with movement, space use, and predation strategies varying between individuals and across environmental contexts. Quantifying variability in mesocarnivore space use and movement from multiple perspectives can provide a better …

Utilizing Machine Learning For Categorizing Disaster-Related Tweets, Ahmad Alfalasi

Theses

This study presents the development of a machine-learning model that recognizes tweets about disasters in real-time. The fast-paced development of social media, especially Twitter, has drastically changed the field of news transmission during crises. This change creates new challenges for the management of the volume, velocity, and veracity of data that are generated in such situations. The present tools do not have the capabilities of real-time processing of the huge volume of data; hence, new solutions are required. The model we are proposing addresses this problem by using advanced machine learning methods, such as natural language processing, to filter and …

Using Machine Learning For Road Accident Severity Prediction And Optimal Rescue Pathways, Mohammad Yousuf Sulaiman Alhashmi

Theses

Road traffic accidents remain a critical challenge for urban planners, transportation authorities, and public safety stakeholders worldwide. Despite advancements in road infrastructure and traffic management, the frequency and severity of accidents continue to strain emergency response systems and compromise public safety. Accident hotspots, are particularly concerning, as they often exhibit recurring patterns of accidents due to factors such as poor road design, high traffic density, and adverse weather conditions. This thesis addresses the challenge of predicting accident severity and identifying accident-prone areas through a data-driven approach. Using a large dataset of over 7.7 million accident records containing geographical, environmental, and …

Mitigating Network Congestion In High-Density Areas Through Advanced Distributed Antenna Systems, Amal Abdulrahman Albeshr

Theses

This dissertation investigates the optimization of Distributed Antenna Systems (DAS) to address network performance challenges, enhance user satisfaction, and improve operational efficiencies in high-density environments. The study explores the integration of DAS with smart city infrastructure to support modern urban needs, such as real-time monitoring and IoT device connectivity. Set against the backdrop of growing urbanization and increasing demand for reliable connectivity, this research provides a comprehensive analysis of DAS as a transformative solution for telecommunications and smart city applications. The primary research question guiding this study was: How can Distributed Antenna Systems (DAS) be optimized to enhance network performance …

Parametric Analysis Of Wire Arc Additively Manufactured Low-Carbon Steel Using Response Surface Methodology, Mirzagha Halilov

Theses

As the manufacturing sector continues on its path towards sustainability, additive manufacturing (AM) remains as one of its most promising streams, aiming to reduce material waste while also allowing for increased design complexity. In the extensive area of metal 3D printing, one method that is steadily gaining traction is wire-arc additive manufacturing (WAAM). This method of AM utilizes the energy created by an electric arc formed between a continuous consumable metal wire and a metal base, fusing the two together and ultimately creating a 3D component layer by layer. WAAM has several notable advantages over other metal 3D printing methods …

Harnessing Federated Learning For Stock Analysis And Portfolio Optimisation, Nishanth Sagar Panthangi

Theses

Financial technology is rapidly transforming, with machine learning becoming crucial in stock analysis and portfolio optimization. Traditional stock analysis faces data privacy challenges when pooling data. Federated Learning addresses this by training models collaboratively without sharing raw data. This thesis explores Federated Learning in stock analysis, focusing on optimizing portfolio strategies using client-specific data.The proposed Federated Learning framework allows entities to develop independent models while maintaining data privacy. By combining diverse trading strategies, a global model is built, enhancing adaptability and predictive accuracy. The global model achieved a 25.08% CAGR and a Sharpe ratio of 4.46, outperforming individual models, which …