Embedded AI for Health and Wellness

Join the meeting now

Meeting ID: 242 199 385 743

Passcode: fA2Vz6gH

Abstract:

The rapid advancements in artificial intelligence are transforming embedded sensing systems, bridging the physical and digital worlds in unprecedented ways. In health and wellness, embedded AI empowers everyday environments and devices to proactively support both physical and mental well-being. This talk highlights projects from the Columbia Intelligent and Connected Systems Lab (ICSL) that exemplify this convergence.

In healthcare, we present a low-cost, vision-based AIoT system for fever screening that achieves superior accuracy at a fraction of commercial costs. In the wearable space, we introduce a glasses-based platform for biosignal acquisition and emotion recognition, as well as an AR-assisted intelligent stethoscope for self-health screening. In the fitness space, we showcase a smartphone-based system that accurately estimates key running metrics like cadence and ground contact time, providing real-time feedback without requiring additional wearable devices. In intelligent environments, we present a reconfigurable drone platform that supports on-demand task execution through natural language interfaces powered by large language and vision models. Extending this to the mental health space, we introduce Katie, a smart home AI therapist system that continuously monitors day-to-day functioning and delivers personalized psychotherapeutic interventions including motivational interviewing and cognitive behavioral therapy.

These projects illustrate how embedded intelligence research at ICSL is shaping the future of health and wellness, redefining the relationship between humans, machines, and their environments.