黑料福利网

Topic 

Transforming everyday spaces into contactless, ambient Health Monitoring Systems

Abstract

Advances in sensing and machine learning are creating opportunities to monitor human physiology and behavior passively, without wearables, cameras, or disruptions to daily life. This talk presents our recent efforts to turn everyday spaces鈥攂eds, rooms, and wireless environments鈥攊nto passive, contact-free health and behavior sensing systems.

First, bed-mounted micro-vibration sensing, where we use seismic signals to capture subtle cardiorespiratory and movement patterns. This enables fully contactless monitoring of bed occupancy, sleep posture, sleep apnea, and even continuous blood pressure across both home and clinical settings. Second, ambient intelligence from sparse environmental sensors, including event-triggered, spatially grounded, and cross-modal models for recognizing activities of daily living, understanding spatiotemporal routines, and generating synthetic sensor streams to address data scarcity.

Together, these efforts demonstrate how furniture, rooms, and everyday environments can be transformed into privacy-preserving sensing platforms that support continuous monitoring and early detection, laying the foundation for scalable, unobtrusive health and behavior technologies.

About the speaker

Fei Dou is an Assistant Professor in the School of Computing at the University of Georgia. She received her Ph.D. in Computer Science and Engineering from the University of Connecticut in 2023, where she conducted research in the Laboratory of Machine Learning & Health Informatics.

Her work spans machine learning for Internet of Things and cyber-physical systems, with contributions in federated learning, reinforcement learning, and self-supervised representation learning.

Fei鈥檚 research focuses on advancing machine intelligence for ubiquitous and distributed environments, with an emphasis on scalable, privacy-preserving, and context-aware AI. She develops ambient and contactless sensing systems that leverage wireless signals, micro-vibration sensors, and event-driven environmental data to monitor human physiology and behavior unobtrusively.

Her work aims to bridge ML theory, sensing, and real-world deployment to enable intelligent environments that support long-term health and well-being.

Your host

Linghan Zhang, assistant Professor at the department of Industrial Engineering & Innovation Sciences.

Registration is required but free of charge.