Program
Invited keynote speakers
On RF based Vital Sign Monitoring: Prof. Shiwen Mao (Auburn University) and Dr. Xuyu Wang (California State University, Sacramento)
Vital signs, such as breathing and heartbeat, are useful to health monitoring since they provide important clues to medical conditions. Effective solutions are needed to provide contact-free, easy deployment, low-cost, and long-term vital sign monitoring. Exploiting radio frequency (RF) signals for contact-free vital sign monitoring will be an important part of the future healthcare Internet of Things (IoT). In this talk, we present our recent work on RF based vital sign monitoring. The first part is to use channel state information (CSI) to monitoring breathing and heartbeat with commodity WiFi devices. We will present PhaseBeat, a discrete wavelet transform based design, TensorBeat, a tensor decomposition based design, ResBeat, a fusion method based on CSI amplitude and phase difference, as well as our experimental study to validate their performance. The second part of this talk is to exploit passive RFID tags for vital sign monitoring and abnormal respiration detection. We will present the AutoTag system, an unsupervised recurrent variational autoencoder-based method for respiration rate estimation and abnormal breathing detection with off-the-shelf RFID tags and reader. Also, we will show how to apply RFID based sensing for effective, low-cost driving fatigue detection, such as detecting the nodding movements or the respiration rate of the driver, in the highly noisy driving environment. The accurate detection performance of the proposed systems has been validated by our experimental study.
A glimpse at image-based sensing of physiological and motion parameters and their impact to human health: Prof. Lalit K. Mestha (UT Arlington, KinetiCor Inc.)
Noncontact image-based sensing at wide-range of electromagnetic spectrum with many modalities is finding numerous applications to our daily lives. In this talk I will present the history of my research in physiological sensing since 2010 aimed at creating numerous bio-medical applications to improve human health and highlight on key products developed by several successful StartUps. I will also present the recent research carried at KinetiCor about the technology behind biometric intelligence and AI-based learning which is used for prospective motion correction to MR/CT/PET Images due to patient movement. This technology is aimed at reducing the need for rescans and sedation, while at the same time closely monitor patients without any time-consuming set-up.