Structures as Sensors：Smaller-Data Learning in the Physical World
报告摘要:Machine learning has become a useful tool for many data-rich problems. However, its use incyber-physical systems (CPS) has been limited because of its need for large amounts of well-labeleddata that needed to be tallored for each deployment. This is especlally challenging due to the highnumber of variables that can affect data in the physical space (e.g. weather, time, persons, etc.) This talk introduces the problem through the concept of Structure as Sensors (SaS). In SaS, thestructure (e.g. a building) acts as the physical elements of the sensor, and the structural response isinterpreted to obtain information about the occupants, and environments around the building. Due tothe size and complexity of structures, traditional approaches would require prahibitively large amountof training data in order to obtain the desired robustness needed in a real-world system. This talkintroduces three physical-based approaches to reduce the data demand for robust leaming in SaS: 1)generate data through the use of physical models, 2) improve sensed data through actuation of thesensing system and 3) combine and transfer data from multiple deployments using the physicalunderstanding. 报告人简介:Pei Zhang is an associate research professor in the ECE departments at Carnegie Mellon University.He received his bachelor's degree with honors from Califomia Institute of Technology in 2002, and hisPh.D. degree in Electrical Engineering from Princeton University in 2008. While at PrincetonUniversity, he developed the ZebraNet system, which is used to track zebras in Kenya. It was the firstdeployed, wireless, ad- hoc, mobile sensor network for which he received the Test-of-Time award. Hisrecent work focuses on utilizing the physical properties of devices and structures as a sensor todiscover physical information that surrounds them. As part of this, his work combines machinelearning-based data models, physics models, as well as heuristic models to improve theunderstanding of the sensing system. His approach is applied to the field of medicine, drones, farmingand was part of a startup. His work has been featured in popular media including CNN, ScienceChannel, Discovery Channel, CBS News, CNET, Popular Science, BBC Focus, etc. In addition, hehas won several awards including the NSF CAREER award, SenSys Test of Time Award, Googlefaculty award, and a member of the Department of Defense Computer Sclence Studies Panel.