Digital Commons Network^™

Generative Ai's Copyright Enigma: A Comparative Study Of Fair Use And Fair Dealing, Taysir Awad

IP Theory

At the dawn of this decade, generative Artificial Intelligence (AI) models were at the apogee of modern science and technology. Their emergence introduced the world to a new paradigm of creativity and innovation, where machines can synthesize art, literature, and design with unprecedented sophistication, blurring the boundaries between human ingenuity and algorithmic computation. These models have the capacity to regenerate Oscar Wilde with the depiction of Ansel Adams, rewrite Harry Potter with William Shakespear’s proverbial tongue, and redesign St. Peter’s Basilica with Gothic arches, Seljuk carved stones, and an Antoni Gaudi roof architecture, relocated in the heart of New York …

Multimodal Feature Fusion And Machine Learning For Adhd Detection Using Neuroimaging Data, Isabel Pham

Master's Projects

Attention Deficit Hyperactivity Disorder (ADHD) is a common neurodevelopment disorder that can significantly affect a person’s attention, impulse control, and executive function. Currently, the traditional diagnosis method often relies on clinical assessments and observations. However, these methods can be subjective and lead to inconsistencies in diagnosis between individuals. To address this challenge, neuroimaging and machine learning (ML) are promising tools for providing a more objective diagnosis of ADHD. The goal of this project is to apply a multimodal approach in which structural and functional features of specific regions of the brain are used to develop a more accurate and objective …

Copyright In The Age Of Artificial Intelligence: Navigating Access To Algorithmic Training Materials And The Three‐Step Test For Text And Data Mining In Nigeria, Morris Odeh

Articles, Book Chapters, & Popular Press

Over the past decade, the Nigerian government has sought to leverage Artificial Intelligence (AI) to drive socioeconomic transformation and improve the welfare of its citizenry. Recent initiatives, such as the establishment of the National Centre for AI and Robotics (NCAIR) and the development of several strategic AI policies, highlight the country's commitment to this objective. This article explores the often‐overlooked issue of how the Nigeria's copyright regime hinders these initiatives, revealing that the regime permits only fair dealing and the transient or incidental reproductions of copyrighted materials for limited technological purposes. This study argues that this regime is unduly restrictive …

Training Set Augmentation And Harmonization Enables Radiomic Models To Detect Early Onset Of Lung Cancer, Claire Huchthausen, Menglin Shi, Gabriel L.A. Sousa, James Larner, Einsley Janowski, Jonathan Colen, Krishni Wijesooriya

Data Science Faculty Publications

Radiomics-based machine learning models have the potential to detect lung cancer at inception from CT scans and transform patient outcomes. Low malignancy rates in early-development pulmonary nodules (PNs) and variable image acquisition hinder development of clinically applicable radiomics-based early detection models. To address these challenges, we augmented training using later-development PNs and harmonized for acquisition effects. We first trained machine learning models to predict PN malignancy using radiomic features from scans of early-development benign and malignant PNs (n = 187) harmonized using ComBat. Observing near-chance performance, we augmented training with later-development benign and malignant PNs (n = 225). We evaluated …

Putting Risk Assessment In The Pilots’ Hands: Refining A Cognitive Health Assessment Tool For Aviators, Kathleen Van Benthem, Emily Larkin, Rawan Othman, Alexia Bierlaire, Chris M. Herdman

International Symposium on Aviation Psychology - 2025

Cognitive factors like poor situational awareness or memory failures can causeserious incidents, especially in single-crew operations. This work introducesCANFLY, an on-demand, self-administered online cognitive assessment for pilots,using realistic flight scenarios and interactive tasks. CANFLY targets key cognitivedomains for safe flight: situation awareness, prospective memory, and taskmanagement. Accessible from any internet-connected computer with speakers,CANFLY currently takes 50 minutes, but reducing this by 50 percent couldenhance user experience and adoption. Preliminary machine learning results from47 licensed pilots show that responses to short “flight” scenarios testing levels 1and 2 situational awareness and prospective memory can classify risk with over 80percent accuracy. Challenges and …

Machine Learning For Computer-Aided Diagnostics From Complex Medical Images, Afsah Saleem

Theses: Doctorates and Masters

Machine learning has significantly transformed medical image analysis in the current age of artificial intelligence offering vast potential in improving disease diagnosis and management. Cardiovascular diseases (CVDs) are among the leading cause of global mortality, emphasizing the need for early detection for effective intervention and prevention. Abdominal Aortic Calcification (AAC) is an early indicator and contributor to Atherosclerotic Cardiovascular Diseases (ASCVDs) and is commonly assessed through imaging modalities such as computed tomography (CT), X-rays, and Dual-energy X-ray Absorptiometry (DXA). Among these, lateral spine DXA scans, commonly used for osteoporosis screening, offer a cost-effective and low-radiation opportunity for opportunistic CVD risk …

Fake News Detection In Arabic Media Using Machine Learning And The Afnd Dataset, Hussain Ali Bahri

Theses

The proliferation of fake news in digital media poses a significant challenge to information credibility, particularly in linguistically diverse regions such as the Arab world. This study addresses the critical problem of detecting fake news in Arabic media by leveraging advanced natural language processing (NLP) techniques and the AFND dataset, which contains over 600,000 news articles categorized into "credible," "not credible," and "undecided" classes. The research focuses on developing a robust system using AraBERT, a transformer-based model specifically pre-trained for Arabic text. Key contributions of this work include a comprehensive preprocessing pipeline tailored to Arabic linguistic complexities, incorporating stopword removal, …

Automated Prioritization And Routing Of It Support Tickets Using Machine Learning, Mohamed Almarzooqi

Theses

The increasing complexity of IT service management underscores the need for efficient and scalable solutions to manage IT tickets. This thesis explores the application of machine learning techniques for automated prioritization & routing of IT tickets. So by leveraging publicly available dataset from Kaggle containing IT ticket the study aims to reduce manual intervention, improve resolution times, & optimize resource allocation within IT environments. The study will evaluate various machine learning algorithms, including SVM, Random Forest, & ensemble models, for their ability to classify and prioritize tickets accurately. to accurately classify and prioritize tickets. Advanced data preprocessing techniques like TF-IDF …

Uncertainty-Aware Meta-Learning For Learning From Limited Data, Deep Shankar Pandey

Theses

Deep Learning (DL) models have achieved great success in large data fields ranging from computer vision and natural language processing to digital arts and robotics. However, the effectiveness of the DL models is challenged by many real-world limited data problems (e.g., medicine, healthcare, and security intelligence) where data for model training is scarce. Unlike DL models, humans can use the prior knowledge stored in their brains to quickly learn new tasks with limited data. Inspired by such human learning, various meta-learning models have been developed that aim to address the challenge of learning from limited data. However, existing models are …

Optimization Of A Vertical-Axis Wind Turbine Airfoils Using Machine Learning, Numerical And Experimental Methodologies, Leovigildo Torres Angel

CGU Theses & Dissertations

This study aimed to enhance the aerodynamic performance of a Vertical-Axis Wind Turbine (VAWT) airfoil through a multidisciplinary approach that combines Machine Learning (ML), Computational Fluid Dynamics (CFD), and experimental validation. The focus was on enhancing the lift-to-drag coefficients ratio (퐶 푙 /퐶 퐷 ), particularly at higher Angles of Attack (AoA ≥ 20°), a critical operational regime for VAWTs. A baseline airfoil of 12-inch chord length and 10-inch wingspan was analyzed using ANSYS Fluent across a range of AoA (0°–90°) at a constant freestream velocity of 10 m/s (Re ≈ 2.0 × 10 5 ). This served as a …

Premier League Results Predictions, Laura Consuegra

ICT

This project applies machine learning techniques to predict outcomes in the English Premier League, one of the most prestigious and widely followed football competitions worldwide. By analysing historical and real-time match data, including performance metrics such as goals scored, shots on target, and cards received, predictive models are developed to forecast match results with higher accuracy. The study evaluates the effectiveness of these models and explores the influence of key statistical features on team performance. The findings aim to provide strategic insights for fans, bookmakers, and coaching staff, supporting performance evaluation, tactical decision-making, and a deeper understanding of the factors …

Credit Card Fraud Detection., Sonia Ndonga

ICT

This capstone project applies machine learning to detect credit card fraud, addressing a critical financial threat to banks and payment providers. Using an anonymised dataset of 284,807 transactions, which is highly imbalanced with only 0.172% fraudulent cases, three models—Logistic Regression, Random Forest, and Gradient Boosting—were developed and evaluated. The pipeline incorporates data preprocessing, feature engineering, hyperparameter tuning, cross-validation, and interpretability analysis using SHAP values, SHAPASH, and permutation importance. Random Forest achieved the highest performance with an ROC AUC of 0.97 and Average Precision of 0.66. The study also considers fairness, threshold optimisation, and practical deployment strategies, providing a robust automated …

Credit Card Default Prediction Using Machine Learning., Yassine Zohair

ICT

This project investigates the use of machine learning to predict credit card payment defaults, aiming to help banks and credit card companies mitigate financial losses. Using historical customer data, including demographics, income, education, and previous payment behaviour, three machine learning algorithms were implemented to forecast the likelihood of default. Techniques such as cross-validation, hyperparameter tuning, and SHAPASH were applied to improve model performance and interpretability. Accurate prediction of potential defaulters enables financial institutions to take proactive measures, such as adjusting credit limits or providing targeted financial guidance, thereby enhancing risk management and customer retention.

Exploring The Determinants Of Life Expectancy At Birth: Predicting And Forecasting Global Health Trends Using Statistical, Machine Learning, And Deep Learning Models., Emma Rath

ICT

Accurate life expectancy forecasting is essential for health policy planning, yet research comparing statistical, machine learning, and deep learning approaches under real-world constraints remains limited. This study evaluates ARIMA/ARIMAX, tree-based, and neural network models using Irish and global datasets, considering small samples, missing data, and COVID-19 shocks. ARIMAX with lagged socioeconomic variables outperformed LSTM and other ML/DL methods. Income-based stratification improved predictive accuracy and interpretability, with SHAP analysis highlighting GDP per capita for developed countries and school enrolment and trade indicators for developing contexts. Results provide practical guidance for policymakers and establish limits for model complexity under constrained health data.

Transformer-Based Symbolic Music Generation, Ben Buentello

Master’s Theses

This thesis investigates the capacity of transformer-based architectures to learn generalized musical patterns through symbolic generation. To support this exploration, a complete music generation pipeline was developed, beginning with the construction and classification of a large-scale dataset of over 170,000 MIDI files. The dataset was processed using rule-based heuristics and custom neural classifiers to separate tracks by musical function and contour. A novel tokenization scheme, MINTii, was introduced to encode musical information compactly through interval-based representations, reducing redundancy and promoting generalization. Using this infrastructure, a transformer model was trained to generate single-track melodic sequences. Its performance was evaluated through both …

Analysis Of Crowd Logistics Networks Using Agent-Based Models, Preetam Kulkarni

Industrial, Manufacturing, and Systems Engineering Dissertations - Archive

Crowd logistics is a system in which an online platform connects a group of non-professional couriers (crowd/carriers), who use their under-utilized resources to offer delivery service to other individuals or businesses (senders) for a fee. While crowd logistics platforms have the potential to offer more flexible and responsive delivery services for much lower rates than traditional logistics providers, it is difficult for platforms to be successful as it is challenging to meet carriers’ and senders’ expectations. Crowd logistics has been applied in the context of food and grocery delivery, parcel pickup and drop-off services and last-mile delivery, however, it has …

Information-Theoretic Methods For Efficient Training And Robust Evaluations In Self-Supervised Learning, Oscar Skean

Theses and Dissertations--Computer Science

Self-supervised learning (SSL) has become a cornerstone of modern machine learning, offering a scalable alternative to costly human annotation by constructing pretext tasks directly from raw data. While SSL has delivered strong results across vision, language, and multimodal domains, two major limitations persist: (1) SSL methods are often significantly slower to train than supervised counterparts, and (2) evaluation protocols remain narrow, with most studies relying on linear probing accuracy on the pretraining dataset. . These challenges are particularly acute for large language models (LLMs), where training costs and interpretability of intermediate representations are critical concerns.

In this work, we propose …

Cnns And Transformers For Visual Understanding: From Feature Alignment To Image Captioning, Xuehao Liu

Doctoral

Deep learning has developed rapidly since the introduction of Deep Belief Networks during the past decade. As an area of machine learning, it still has many open challenges. Among these open challenges is the issue of transparency, with deep learning models known as black boxes. Both explainability of a model for understanding the decision making process, and the transparency of the relationship between the input and output are crucial for understanding a model. The understanding of models can build trust between AI systems and humans, verify models behavior, and identify potential biases or errors.

Leveraging Intrinsic Properties For Classification Of Coal Seams Towards Spontaneous Combustion Proclivity And Predicting Susceptibility Using Machine Learning: Smart And Sustainable Mining Approach, Siddhartha Agarwal, Pradeep K. Gautam, Yuhao Zou, Rishabh Dwivedi, Durga C. Panigrahi, Cihan H. Dagli, A. Singh

Engineering Management and Systems Engineering Faculty Research & Creative Works

Mine fires and other hazards caused by spontaneous coal combustion are a pervasive and longstanding issue in Jharia coalfields, India. This study proposes a novel approach to classify coal seams based on their propensity to spontaneous combustion using the intrinsic properties of 30 coal samples from different seams. This method eliminates the need for expensive and time-consuming experimental determinations of susceptibility indices (SI) such as crossing point temperature (CPT), critical air blast (CAB), and differential thermal analysis (DTA). All clustering models, viz. hierarchical, k-means, and multidimensional scaling, aptly classify coal seams into three categories: highly risky, medium risky, and low …

Nanotube Spectral Fingerprinting And Machine Learning For Optimized Bioimaging/Sensing And Disease Detection Applications In Als, Rodrigo Monroy Lopez

Open Access Master's Theses

Single-walled carbon nanotubes (SWCNTs) possess unique physicochemical and optical properties that make them ideal candidates for biomedical imaging, biosensing, and disease diagnostics. This thesis explores the potential of SWCNT-based spectral fingerprinting combined with ML (Machine Learning) algorithms to optimize bioimaging, disease detection and prediction, with a specific focus on differentiating between healthy and amyotrophic lateral sclerosis (ALS) lymphoblastic patient samples. By functionalizing SWCNTs with single-stranded DNA, we enhance their stability and target specificity, enabling their application in serum patient samples.

A comprehensive spectral analysis of DNA-SWCNTs was conducted using near-infrared fluorescence spectroscopy and other characterization techniques, including UV-Vis-absorption spectroscopy. The …

Lost In Translation: The Impact Of Intermediate Language Representations On Machine Learning Applications, Logan Cannan

Dissertations

Machine learning assisted binary analysis is an area of great interest in cybersecurity research. Training accurate machine learning models requires methods of binary lifting, which can require binaries to be translated through an intermediate language representation. This dissertation postulates that different intermediate language representations change the performance characteristics of these machine learning models. This dissertation takes a published machine learning frameworks as a control, modifies their input methodology to include different intermediate language representation transforms, and performs direct comparisons of model performance to ascertain bias in performance caused by different intermediate languages. This research enables the machine learning engineer, focused …

Neural And Computational Approach To Understanding Environmental Modulation Of Behavioral Identity In Zebrafish, John W. Hageter

Graduate Theses, Dissertations, and Problem Reports (ETD)

Organisms rely on behavior for survival. Animals engage in behaviors that allow for feeding, mating, exploring and navigating their environment among others. Necessary for these behaviors to develop are the environmental factors and underlying circuitry which make behavior possible. Specifically, how the environment guides underlying neural circuitry to develop unique facets or phenotypes of a larger behavior are key to understanding why unique behaviors exist. In this thesis, I build foundational evidence for determining these mechanisms through the use of the zebrafish local search behavior. This is a behavior that zebrafish employ following the loss of environmental illumination where they …

Augmentation And Hybridization Of Conventional Forms Of Process Control With Advanced Control Methods, Daniel Paul Beahr

Graduate Theses, Dissertations, and Problem Reports (ETD)

Within the last decade in the field of process control, there has developed a distinct gap between the technological advancements of today and the well-established theory that has preceded it. This is most evident where the novel developments and structures often outpace the necessary guarantees and strong foundation required to ensure the possibility of widespread adoption. Therefore, the goals of this work are to broadly integrate those novel advanced control methods into the field of process control in such a way to increase the applicability and encourage implementation.

The first portion of this work seeks to further explore the nature …

Identification, Mapping And Treatment Of The Invasive Rosa Multiflora Using Unmanned Aerial Systems And Machine Learning Models, Kylie Virginia Shaw

Graduate Theses, Dissertations, and Problem Reports (ETD)

Invasive species are introduced species that cause detrimental impacts to the native ecosystem or cause harm to human health. The work necessary for land managers to survey for and treat invasive species takes up limited time, labor, and financial resources. This study assesses how Unmanned Aerial Systems (UAS) and machine learning models can be used to make the identification, mapping, and treatment of invasive vegetation more efficient and effective. A UAS-mounted multispectral camera captured images of our target species, Rosa multiflora (multiflora rose), throughout its growing season in southwest Pennsylvania. A random forest machine learning model was trained on these …

Fares On Fairness: Using A Total Error Framework To Examine The Role Of Measurement And Representation In Training Data On Model Fairness And Bias, Patrick Oliver Schenk, Christoph Kern, Trent D. Buskirk

Data Science Faculty Publications

Data-driven decisions, often based on predictions from machine learning (ML) models are becoming ubiquitous. For these decisions to be just, the underlying ML models must be fair, i.e., work equally well for all parts of the population such as groups defined by gender or age. What are the logical next steps if, however, a trained model is accurate but not fair? How can we guide the whole data pipeline such that we avoid training unfair models based on inadequate data, recognizing possible sources of unfairness early on? How can the concepts of data-based sources of unfairness that exist in the …

Predicting Early Hospital Readmissions For Diabetic Patients Using Machine Learning, Amanda Ferraz, Leonardo Oliveira

ICT

This project applies machine learning to predict whether diabetic patients will be readmitted to a hospital within 30 days of discharge. Early readmissions are a costly and critical issue in healthcare, often signalling gaps in post-discharge care and risk management. Diabetic patients face unfair high readmission rates compared to the general population. According to the CDC Diabetes Report Card 37.3 million people in the U.S. or 11.3% of the population had diabetes as of 2019 (CDC, 2021). Our goal here is to develop a binary classification model capable of flagging high risk patient (< 30-day readmission) based on their clinical, demographic, and administrative data. This lets healthcare institutions to take measures,

European Air Pollution And The Proposed Timelines Of Implementing The World Health Organization 2021 Air Quality Guidelines Ca3., Lukia Hartin

ICT

This research examines Ireland’s air pollution trends and evaluates whether current reductions in PM2.5, PM10, and NO₂ are sufficient to meet the WHO 2021 Air Quality Guidelines by 2040. Using four years of EPA-validated pollutant data (2020–2023), alongside Building Energy Rating (BER) and national transport datasets, the study applies the CRISP-DM methodology to guide analysis, preprocessing, modelling, and evaluation. Extensive data cleaning and alignment were required due to inconsistent station coverage, varying formats, and missing values. Forecasting models—including Random Forest, Gradient Boosting, SVR, and linear regression—were assessed using MSE, R², and trend significance to project pollutant levels across different Irish …

Customer Service Support. Utilizing Machine Learning To Classify, Prioritize And Summarize Issues., Hoai Nhan Nguyen

ICT

This capstone project investigates the application of machine learning and natural language processing (NLP) to enhance customer support operations through automated ticket classification, prioritization, and summarization. Using the multilingual Customer Support Emails dataset from Kaggle, the project follows the CRISP-DM methodology, performing extensive data cleaning, preprocessing, feature engineering, and class balancing. Five machine learning models—Decision Tree, KNN, LinearSVC, Naive Bayes, and Random Forest—were evaluated using hyperparameter tuning, cross-validation, confusion matrix analysis, and learning curves. LinearSVC demonstrated the strongest performance for both queue and priority classification, achieving accuracies of 89.8% and 81.2% respectively, with consistent generalization across folds. For summarization, extractive …

Predicting Repeat Purchases In E-Commerce Using Interpretable Machine Learning, Zahid Bhatti

ICT

This project investigates the prediction of repeat purchase behaviour in e-commerce using machine learning, with a focus on balancing predictive accuracy and interpretability. Large volumes of transactional and behavioural data are analysed to identify customer-level features that drive loyalty and repeat purchases. Various supervised learning models, including Random Forests and Logistic Regression, are evaluated for predictive performance, while SHAP (SHapley Additive Explanations) is employed to provide both global and local interpretability. The study aims to generate actionable insights for customer relationship management and marketing strategy, demonstrating how advanced predictive models can support informed business decisions without sacrificing transparency.

The Actuarial Applications Of Machine Learning And Big Data In The Life Assurance Industry: Managing Customer Retention And Customer Outcomes By The Application Of Data Science., Brian Cunningham

ICT

Lapses are an issue in the insurance industry in general. They affect a company’s profitability, cash flows and solvency. High levels of lapses can cause reputational damage that could provoke a cycle of even more lapses. It is therefore incumbent on a company to do its utmost to retain the business it has written for the term it was written for.

If a company could predict which of its policies were about to lapse, it could proactively attempt to prevent them by contacting the policyholder and engaging in a discussion to ascertain the likelihood of their choosing to leave. In …