Title: Multi-modal Temporal Physiological Modeling Across Varying Time Horizons Using Dynamical Interactions

Date: Wednesday, April 16th, 2025

Time: 11:00 AM - 1:00 PM ET

Location: TSRB 523A

Virtual Link: https://gatech.zoom.us/j/96715615558?pwd=YH3L3hCzKckQX8vQv34ia6C1mDoOSc.1

Cem Okan Yaldiz

Robotics PhD Student

School of Electrical and Computer Engineering

Georgia Institute of Technology

Committee:

Dr. Omer Inan (Advisor) - School of Electrical and Computer Engineering, Georgia Institute of Technology

Dr. Thomas Ploetz - School of Interactive Computing, Georgia Institute of Technology

Dr. Vince Calhoun - School of Electrical and Computer Engineering, Georgia Institute of Technology

Dr. Reza Sameni - Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology

Dr. Aaron Young – George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology

Abstract: 

This thesis explores data-driven approaches for cardiac-based physiological analysis using multi-modal data from wearable devices focusing on dynamical interactions. It addresses both prediction problems with different target horizons, beginning with the early detection of exertional heat stroke and moving toward forecasting cardiac events. The research highlights the benefits of integrating multiple modalities to improve predictive performance and reliability. It further investigates the relationship between brain and cardiac activity, with a focus on event-related potentials and their connection to cardiac responses. Finally, the study examines the potential of advanced multi-modal models to capture deeper brain-heart interactions. Overall, this work contributes to the advancement of physiological modeling and supports the growing role of wearable technologies in health monitoring and psychophysiological applications.