AI-supported exercise coaching for older adults with mild cognitive impairment

Research Assistant, Ross and Carol Nese College of Nursing, Penn State · PI: Dr. Sangwoo Ahn 

Im implementing clinical protocol by Dr. Ahn as working research prototype. It runs as Python session server connected over WebSockets to a browser front end with MediaPipe pose estimation and scikit-learn classifier scoring movement against reference recordings, everything processed on the local machine and an automated test suite covering session flow, provisional rule-based safety logic and complete-session replay from stored movement features. The protocol keeps the researcher present throughout and participant evaluation is still ahead. Re-scoring held-out clips against different reference sets also showed that reference selection changes movement scores, so choosing the reference set is part of the study design.

Inner Voice Coach

Student Principal Investigator, College of Information Sciences and Technology, Penn State · Advisor: Dr. Saeed Abdullah 

A concise planned single-session feasibility and acceptability study of a web tool which guides students through one bounded, LLM-assisted reframe of a self-critical thought about asking for help. I have written the protocol, the consent and the AI-use documentation. I built the tool so that it does not store what a student writes, and sends only coded session variables to Qualtrics. I also tested the prespecified analysis pipeline with simulated data before finalising the protocol. I am preparing the IRB submission now.