This study explores the intersection of human intelligence and Artificial Intelligence (AI) to design knowledge-in-use science assessments for supporting students' deep science learning. In the context of evolving educational paradigms, it seeks to harness AI tools (GPT), to enhance knowledge-in-use assessment design, ensuring equitable…

Computational learning theory studies the design and analysis of learning algorithms, and it is integral to the foundation of machine learning. In the modern era, classical computational learning theory is growingly unable to catch up with new practical demands. In particular, problems arise in the following aspects: i). "scalability":…

The COVID-19 pandemic led to an increase in Online learning. With this increase comes several challenges for instructors and students such as connectivity issues and student engagement. Organizations are spending millions of dollars developing emerging technologies such as emotion AI and other AI applications without taking cognizance of users'…

This dissertation used synthetic datasets, semi-synthetic datasets, and a real-world dataset from an educational intervention to compare the performance of 15 machine learning and multiple imputation methods to estimate the individual treatment effect (ITE). In addition, it examined the performance of five evaluation metrics that can be used to…

This dissertation aimed to explore the use of machine learning (ML) models in in-patient clinical settings. A literature review was conducted to identify existing guidelines and frameworks for such models, and an in-depth study was conducted on ML-based models to understand their behavior and implications on patient outcomes. A conceptual…

Artificial intelligence (AI), utilizing machine learning techniques to 'learn' from data, as humans learn from experiences, has the promise to perform various cognitive tasks, such as learning, thinking, problem-solving, and decision-making, which usually demands human cognition. In recent decades, the remarkable advancements in AI have led to its…

Software powered by artificial intelligence (AI) is used widely in the United States in education as a tool for teaching, administration, student assessment, and other purposes. Curriculum delivery, tutoring, support for students with disabilities and resource allocations are some of the applications of the technology. The normative, ideological,…

This qualitative descriptive case study explores how genealogists describe the mechanism of epistemic change in their research, highlighting the roles of epistemological doubt, epistemological volition, and resolution strategies. It explores the integration of digital technologies in genealogical practices in the United States and their…

With the latest advances in conversational agents like Siri and Alexa, and Large Language Models (LLMs) like ChatGPT and PaLM, Question Answering (QA) systems have become more important. Users submit millions of queries per day and it is up to the system to provide reliable, to-the-point answers. In this dissertation, we explore various aspects to…

To build an Artificial Intelligence system that can assist us in daily lives, the ability to understand the world around us through visual input is essential. Prior studies train visual perception models by defining concept vocabularies and annotate data against the fixed vocabulary. It is hard to define a comprehensive set of everything, and thus…

This study explored the role of artificial intelligence (AI)-powered conversational agents in human-computer interaction, particularly in the post-coronavirus (COVID-19) era, where digital technologies are central to healthcare, customer service, and education sectors. The research investigated the disruption of context continuity when users…

The dream of intelligent assistants to enhance programmer productivity has now become a concrete reality, with rapid advances in artificial intelligence. Large language models (LLMs) have demonstrated impressive capabilities in various domains based on the vast amount of data used to train them. However, tasks which require structured reasoning or…

This dissertation examines the effectiveness of machine learning algorithms and feature engineering techniques for analyzing process data and predicting test performance. The study compares three classification approaches and identifies item-specific process features that are highly predictive of student performance. The findings suggest that…

Immunosuppressive therapy is vital for the success of a kidney transplant, yet it entails potential risks and side effects. The challenge lies in finding the right balance between suppressing the immune response enough to prevent rejection while minimizing the risk of infections, organ toxicity, and other complications associated with long-term…

The rise of Artificial Intelligence technology has raised concerns about the potential compromise of privacy due to the handling of personal data. Private AI prevents cybercrimes and falsehoods and protects human freedom and trust. While Federated Learning offers a solution by model training across decentralized devices or servers, thereby…