University of Cambridge > Talks.cam > Mobile and Wearable Health Seminar Series > AIoT for Safer, Healthier, and Smarter Environments

AIoT for Safer, Healthier, and Smarter Environments

Add to your list(s) Download to your calendar using vCal

  • UserXiaofan (Fred) Jiang, Columbia University World_link
  • ClockTuesday 31 October 2023, 16:00-17:00
  • HouseOnline only.

If you have a question about this talk, please contact Cecilia Mascolo.

https://cam-ac-uk.zoom.us/j/89965171767?pwd=RlJSUCtaVHlPL0laTzM2VzB6d1V6UT09

The combination of artificial intelligence and the internet-of-things, or artificial intelligence of things (AIoT), promises to transform the world. In this talk, I will present several projects at Columbia Intelligent and Connected Systems Lab that focus on AIoT for safety, health, and smarter environments. In the urban safety space, we create a mobile AIoT system that uses acoustic sensors combined with embedded machine learning to help alert pedestrians and construction workers of dangers from nearby vehicles. We further introduce a generalized audio filtering architecture that enables a wide range of applications. In the health space, we present a low-cost vision-based AIoT system for continuous multi-person fever screening. By using novel algorithms and models that take advantage of multiple frames of information from both thermal and RGB domains, our system achieves better accuracy than commercial solutions at a fraction of the cost. In the wearable space, we introduce a glasses-based platform for in-situ bio-signal acquisition and emotion recognition, followed by an AR-assisted intelligent stethoscope that enables self-screening at home. In the mental wellness space, we present an AI therapist for daily functioning assessment and intervention using custom-trained GPT models. Finally, in the smart homes space, we introduce a modular sensing architecture and a reconfigurable drone platform for enabling ambient assistive applications.

This talk is part of the Mobile and Wearable Health Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity