BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:ENAC Seminar Series by Dr S. Xu
DTSTART:20200226T093000
DTEND:20200226T103000
DTSTAMP:20260917T073523Z
UID:f712c6c712442ce2281ed8c19bcb4fc731f1515f4104a32007119c69
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr Susu Xu\n09:30 – 10:30 – Dr Susu Xu\nResearch Scientist
 \, Qualcomm Technologies\, San Diego\, USA\n\nTowards a Self-adaptive Smar
 t City: Collaboratively Integrating Sensing\, Learning and Actuation for M
 onitoring Urban Infrastructure Systems\n\nWith increasing populations and 
 demand for high-quality urban services\, there is an urgent need to build 
  “self-adaptive” cities which can autonomously adapt their monitoring
  and management strategies for urban infrastructure systems under constant
 ly changing urban dynamics. The recent rapid development of sensor network
 s and 5G technologies are enabling large-scale multi-source data and real-
 time multi-agent control. However\, these large-scale and interdependent p
 hysical infrastructure systems pose challenges to data-driven monitoring a
 nd management strategies. For instance\, how to design low-cost paradigms 
 for large-scale and complex infrastructure sensing\, how to capture and an
 alyze the physical dynamic interplay between infrastructure systems from n
 oisy and incomplete data\, how to timely react to changes of urban dynamic
 s\, and more importantly\, how to automate the process of sensing\, learni
 ng and actuation to improve the quality of the urban services.\n\nIn this 
 talk\, Dr Xu will introduce a framework that collaboratively integrates re
 source-aware sensing\, physics-informed learning and user-incentivizing me
 chanisms for monitoring large-scale urban infrastructure systems. First\, 
 she will talk about her work on embedding prior physical knowledge of infr
 astructures into adversarial transfer learning algorithms for infrastructu
 re damage diagnosis. This framework enables knowledge transfer across diff
 erent infrastructures without any labelled data on the target structure. T
 his is especially important when the data is scarce\, such as in post-disa
 ster scenarios. Further\, she will introduce the integration of indirect s
 ensing methods\, including “buildings as sensors” and “vehicles as s
 ensors”\, and physics-informed learning for large-scale infrastructure m
 onitoring. Finally\, Dr Xu will briefly mention her works on incentivizing
  vehicle mobilities and human activities to react to the detected changes 
 in urban infrastructure systems\, which improves the efficiency\, reliabil
 ity and sustainability of future cities.
LOCATION:GC B1 10 https://plan.epfl.ch/?room==GC%20B1%2010
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR