Academic Report

Unobtrusive Vital Sign Monitoring Through Ambient Physical Vibrations


Topic:Unobtrusive Vital Sign Monitoring Through Ambient Physical Vibrations

ReporterDr. Zhenhua Jia (Rutgers University, US), NVIDA R&D Engineer

Time:10:00 a.m., May 8th, 2019 (Wednesday)

Site:Room 105, School of Computer Science

HostZhu Wang, Associate Professor, School of Computer Science, NPU



Vital sign monitoring is critically important to ensuring the well-being of many people, ranging from patients to the elderly. Technologies that support vital sign monitoring should be unobtrusive, and solutions that are accurate and can be easily applied to existing beds is an important need that has been unfulfilled. In this talk, Dr. Jia will talk about the challenge of accurate, low-cost and easy to deploy vital sign monitoring systems. The talk will first show that off-the-shelf analog geophone sensors, when installed under a bed, can be used to detect and extract heartbeats in the presence of environmental noise and other a person may have during sleep. Then, the talk will elaborate how to extend the system towards a more realistic scenario -- monitoring a person’s respiratory rate as well as heart rate, even when she is sharing a bed with another person.

Also, the talk will briefly demonstrate a continuous ammonia monitoring system that is low-power, automatic, accurate, and wireless. The developed system is centered around metal oxide sensors and the work significantly reduces the power consumption of the system by using a predicting algorithm based on long short-term memory (LSTM) neural networks.

Introduction of the Reporter:

Zhenhua Jia received his B.S. degree in Information Engineering at Southeast University, China, in 2010. He received his Ph.D. degree in Computer Engineering at Rutgers University, the U.S., in 2019, advised by Professor Yanyong Zhang. He has been working as an R&D engineer at NVIDIA since 2018. and focuses on developing algorithms for autonomous driving vehicles at NVIDIA. His research interest is on sensor systems, signal processing and neural networks.

Prev:Forum on Medical Imaging and Intelligent Computing Held Successfully Next:Detecting small signals in videos and its applications