“AIoT for Urban Safety, Health, and Mental Wellness”

Hosted by the Department of Computer Science & Engineering (CSE)

Abstract: The combination of artificial intelligence and internet-of-things, or artificial intelligence of things (AIoT), promises to transform the world. At Columbia Intelligent and Connected Systems Lab, AIoT enables us to sense and understand urban situations and people, and allows us to take actions like never before. In this talk, I will present several projects focused on AIoT for urban safety, health, and mental wellness.

In the urban safety space, we create a wearable AIoT system that uses multichannel audio 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 first build on top of the intelligent audio filter to create an AIoT system for non-intrusive breathing detection and demonstrate its potential in infant monitoring. We then 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. Early results from a 10-month study inside a multi-practice clinic will be presented. In the mental wellness space, we introduce a glasses-based wearable platform for in-situ bio-signal acquisition and emotion recognition, followed by an AI-based mental status examination (MSE), the first interactive MSE platform that enables anyone to self-administer MSE at home through a web browser, helping to lower the barrier for accessing mental healthcare.

For inquiries contact Maria Sanchez.