AI-Powered Multimodal Analytics of Learner Dynamics in Learner-Centered Activities

Learner-centered learning environments encourage autonomy, collaboration, and creative problem-solving, but they also present challenges in understanding how students engage and progress individually. This project leverages AI-driven multimodal analytics to examine learners’ dynamics using video data collected from a learner-centered classroom, focusing on how learners interact with peers, tools, and tasks. By using computer vision, machine learning techniques, and multimodal large language models (MLLMs), the project aims to detect key events such as collaboration, focus shifts, tool use, and moments of guidance-seeking. The ultimate goal is to develop an AI model that supports timely and personalized feedback, offering instructors and learners deeper insights into the learning process and helping to shape more responsive educational practices.

AI-Powered Multimodal Hybrid Instruction for Growth in Nursing Simulation (AIM HIGH-SIM)

Simulation-based learning plays an important role in nursing education but often faces challenges due to being resource-intensive, which limits accessibility and scalability. The AIM HIGH-SIM project, in collaboration with the School of Nursing at Georgia State University, aims to establish a flexible framework for facilitating simulation-based learning through a conversational AI-augmented simulator. This framework will provide instructors the flexibility to easily add scenario cases along with related assessment criteria. These scenarios will support learners in practicing simulations within physical simulation rooms as part of their nursing education, with assessments drawn from both dialogue interactions and visual data within the simulation space. The system will provide personalized feedback, supporting both simulation centers and individual practice. By leveraging the capabilities of AI and structured framework design, the project enables learners to continuously practice and refine critical thinking and communication skills in a realistic, flexible, and authentic environment.

NSF IUSE-Engaged Student Learning (Level 1): AI-Scaffolded Pre-Classroom Learning for Large/Introductory Undergraduate Physics Courses

This Engaged Student Learning Level 1 project aims to serve the national interest by designing and implementing an Artificial Intelligence (AI)-augmented formative assessment and feedback system. This system will help students develop source-based STEM arguments, such as STEM text summarization, or problem spaces, which are mental representations of a problem and of multiple paths to solving it. This will be implemented in large, undergraduate introductory physics courses at an urban university that serves diverse and historically underrepresented student groups. Persistent learner engagement in pre-classroom learning activities is critical to learner success in introductory STEM courses. The innovation of the project will include AI-generated adaptive scaffolding information and learning progress feedback with data visualization techniques to help students with concept learning and self-regulatory behaviors. The unique learning opportunities supported by an AI-scaffolded feedback system will significantly increase students' engagement levels in self-paced online pre-classroom learning. This, in turn, will help students acquire content knowledge and build a proper understanding of problems to prepare themselves for success in in-classroom interactive problem-solving activities.