September 22, 2023
By Chloe Arrington

Students and alumni in the George W. Woodruff School of Mechanical Engineering were on the first-place teams at the 3rd annual Student IoT Innovation Capacity Building Challenge this summer. The event is sponsored by the Center for the Development and Application of Internet of Things Technologies (CDAIT), and co-sponsored by the School of Public Policy, and the GT VentureLab.

This challenge is an initiative from CDAIT aimed to advance the development of innovation, applications, policy, and activities. The general focus areas of the challenge are the Internet of Things (IoT) technologies and applications, computing at the edge, and cloud technologies.

The challenge for 2023 offered three prize categories: The Verizon Connectivity prize focused on connectivity and edge applications; a Policy/Civic Engagement prize for projects with social, civic/public sector, or community impact; and the IoT Innovation prize, for innovative technologies and applications.

Ph.D. student Nathan Zavanelli and Woodruff School alumnus Jared Matthews, M.S. ME 2023, were awarded first place in the Policy/Civic Engagement category. Their project, Physioconnect, developed a cloud-interfaced wearable device with monitoring for cardiovascular characterization for remote, long-term postpartum monitoring.

The project aimed to address the underlying inequalities in access to healthcare infrastructure and to prevent extreme cardiac complications in postpartum patients such as cardiomyopathy, heart failure, or hypertensive crisis which can occur before the standard postpartum follow up care takes place.

Woodruff School alumna Ira Soltis, ME 2021, M.S. ME 2023, with teammates Kangkyu Kwon and Yoon Jae Lee, received first place in the IoT Innovation category for their project, Soft Upper-Extremity Robotics with Stretchable Artificial Skin Electronics for Deep Learning-Enabled Human Strength Augmentation.

The team developed a soft upper-extremity exoskeleton created for the purpose of human strength augmentation. The project uses new technologies including artificial skin electronics, soft actuators, and deep learning algorithms allowing automatic, real-time identification and classification of a user's movement.

Associate Professor and Woodruff Faculty Fellow W. Hong Yeo served as both teams’ faculty advisor.