Date of Award

Summer 8-2026

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Electrical & Computer Engineering

Program/Concentration

Electrical and Computer Engineering

Committee Director

Yuzhong Shen

Committee Member

Charles I. Sukenik

Committee Member

James Leathrum

Committee Member

Xinyue Ren

Abstract

Rapid advancements in modeling and simulation (M&S) and artificial intelligence (AI) present new opportunities to enhance various aspects of STEM education, from virtual laboratories that simulate physical lab environments in software to intelligent teaching assistants that provide on-demand, curriculum-aligned instructional support. Virtual laboratories offer a potential solution to the access and scalability challenges of laboratory courses by allowing students to conduct experiments without physical equipment or geographical constraints. AI-powered teaching assistants, particularly those grounded in course-specific materials, can help mitigate the instructional support gap that arises when students work independently in digital learning environments. This dissertation presents three-phase research into virtual laboratory systems and AI-powered teaching assistants for STEM education. The first phase developed and evaluated a virtual laboratory for the Intermediate Experimental Physics course at Old Dominion University, examining the implementation strategies and design decisions that support its development. The second phase introduced the Intelligent Lab Assistant (ILA), a Retrieval-Augmented Generation (RAG) enabled assistant embedded within the virtual laboratory, and evaluated whether grounding the system in course-specific materials produced more accurate and pedagogically appropriate responses than a general-purpose large language model (LLM). The third phase examined the generalizability of this RAGenabled architecture by deploying the Intelligent Teaching Assistant (ITA) across three courses with distinct pedagogical goals within a learning management system (LMS).

This dissertation produces two deliverables: a fully developed virtual laboratory and a RAG-enabled AI teaching assistant architecture deployed in both virtual laboratory and LMS settings. This work contributes (1) implementation strategies and design decisions for the rapid development of virtual laboratories, (2) empirical evidence that RAG-enabled grounding produces more accurate and pedagogically appropriate responses than a general-purpose LLM, and (3) evidence that this architecture generalizes across courses with distinct pedagogical goals within a learning management system. These contributions are grounded in the development and evaluation of both deliverables, including a preliminary evaluation of the virtual laboratory’s effectiveness and usability, and an empirical assessment of the AI assistant across multiple course contexts.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/m87d-3v14

ISBN

9798193214694

ORCID

0000-0002-1434-8011

Download

Share

COinS