Graduation Year
2024
Document Type
Dissertation
Degree
Ph.D.
Degree Name
Doctor of Philosophy (Ph.D.)
Degree Granting Department
Electrical Engineering
Major Professor
Wilfrido A. Moreno, Ph.D.
Committee Member
Ismail Uysal, Ph.D.
Committee Member
Chung Seop Jeong, Ph.D.
Committee Member
Autar Kaw, Ph.D.
Committee Member
Dhinesh Balaji Radhakrishnan, Ph.D.
Keywords
Bayesian network, Education Data Mining, Multi-criteria Team Formation, Synthetic data
Abstract
As the engineering education system continuously evolves to meet the demands of modern industry and society, there is a need for a methodology that would manage and resolve the complexities inherent in engineering educational systems. Model-based Systems Engineering (MBSE) is a structured approach to system design that utilizes models across all stages of the system's life cycle and supports requirements management, design, analysis, verification, and validation processes. While MBSE has been applied successfully in industries like defense, aerospace, and automotive, its application in engineering educational systems remains unexplored. This dissertation develops a dynamic model of the university-level engineering education system using an MBSE framework, which is named “Engineering Learning Analytic Systems (ELAS)”. ELAS is a human-centered entity involving students, educators, administrators, and industry partners. It aims to improve student learning and performance across all levels by focusing on enhancing professional competencies like communication and teamwork. This is achieved through the development of a multi-criteria team formation algorithm for grouping students in capstone projects and engineering courses. The research also addresses challenges in model simulation and evaluation due to the lack of datasets available for engineering education system research, which is addressed by developing a generative synthetic data model using Bayesian network and Gibb sampling. The research concludes by highlighting the transformative potential of Model-Based Systems Engineering (MBSE) in engineering education, illustrating the necessity of integrating 21st-century tools such as MBSE, System Simulation, Artificial Intelligence, and Machine Learning to address 21st-century challenges. It demonstrates how systems engineering tools and frameworks can facilitate a more adaptable, efficient, and student-centered approach to learning.
Scholar Commons Citation
Singh, Pallavi, "Model-Based Systems Engineering for Engineering Education Systems Simulation" (2024). USF Tampa Graduate Theses and Dissertations.
https://digitalcommons.usf.edu/etd/10565
