CDAIT Student IoT Innovation Capacity Building Challenge 2022 - Results

The Center for the Development and Application of Internet of Things Technologies (CDAIT), and co-sponsors School of Public Policy and GT VentureLab, are pleased to announce winners of the 2nd annual Student IoT Innovation Capacity Building Challenge. In the effort to advance R&D/policy/innovative activities in the area of Internet of Things (IoT) technologies and applications, CDAIT established the Challenge to stimulate rapid response innovative/exploratory research or projects in the field of IoT and associated domains. Students, faculty, and researchers, working in a university setting constitute a rich source of innovative ideas, particularly in technology-related fields.

This Challenge takes an innovative approach by seeking not just engineering and technical solutions, but also proposals from the social sciences, humanities, and multidisciplinary teams. This year, we were interested in projects that focused on: 1) healthcare/biomedical, assistive/inclusive, enhanced living domains (e.g. IoMT), 2) industrial and manufacturing processes (e.g. IIoT), and 3) organizational/digital transformation (public and business). We also looked for projects that built collaborative teams across disciplines. Finally, we encouraged proposals that addressed the effects of IoT on underserved populations or IoT that addresses accessibility, usability and broader social impacts. The price winning projects are presented below.

Project Teams

Blurb / Gallery Set

1st Place, Commercialization

Intelligent Acoustic Monitoring at the Edge


Nathaniel DeVol, Elizabeth McGrath, Christopher Saldana


This project is a low-cost, easy-to-implement application that uses a microphone to learn what a machine typically sounds like and alerts users when anomalous sounds are identified. The application makes use of unsupervised machine learning to automate all stages of deployment including the determination of machine state, learning the typical sound of the machine, and setting the threshold for classifying new sounds.

Project Website

Intelligent Acoustic Monitoring at the Edge [ ]

1st Place, Technology Development

Soft Stethoscope Patch (SSP) for Multi-patient Pulmonary Diagnosis


Sung Hoon Lee, Bryan Starbuck, Maria Sattar


This project consists of three soft stethoscope patches, on the chest, back right and left lower lobes, connect to a HIPAA compliant application with integrated machine learning algorithms to classify abnormalities and send real time severe event notifications to a caregiver. This system provides accurate, continuous, and timely cardiopulmonary information on patients requiring accurate multi-auscultation.

Project Website

Soft Stehoscope Patch (SSP) for Multi-patient Pulmonary Diagnosis [ ]