BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:0-5481@eng.ufl.edu
DTSTART;TZID=America/New_York:20221214T123000
DTEND;TZID=America/New_York:20221214T133000
DTSTAMP:20221115T155424Z
URL:https://www.eng.ufl.edu/news-events/events/female-leaders-in-transport
 ation-seminar-dr-yueyue-fan/
SUMMARY:Female Leaders in Transportation Seminar: Dr. Yueyue Fan
DESCRIPTION:Research Seminar:\nTitle: Physics-informed data analytics appro
 aches using constrained optimization - exploiting domain knowledge with ha
 rd information in a transportation network\nAbstract: Civil infrastructure
  as a system often faces challenges and complexity brought by interactions
  between spatially- and functionally- distributed components. Recognizing 
 and incorporating these physical interactions in data driven approaches pr
 esent challeng-es but also unique research opportunities for domain expert
 s. In this talk\, I will use transportation networks as examples to discus
 s how constrained optimization\, by provid-ing a flexible modeling framewo
 rk for integrating domain knowledge\, statistics\, and data-driven approac
 hes\, could help addressing some fundamental data challenges that fre-quen
 tly arise in transportation applications. The first example shows how stoc
 hastic pro-gramming (SP) can be used to provide a statistically consistent
  and efficient estimate of global variables (network-level travel demand) 
 that are not directly measurable based on partial local measurements (link
 -level traffic flows). In this example\, domain knowledge reflecting netwo
 rk physics is modeled explicitly as constraints\, and data samples are tre
 ated in some sense as uncertain scenarios in a SP framework. The second ex
 ample shows how domain knowledge regarding the usage of data may be direct
 ly incorporated in data compression to support end-to-end learning. In thi
 s example\, objectives of the downstream application may be included in th
 e design of the loss function in the data di-mension reduction process. Th
 e results demonstrate the importance of application-aware data compression
  approaches for networked data.\nPresenter: Yueyue Fan is a professor in C
 ivil and Environmental Engineering at University of Califor-nia\, Davis. S
 he is also a faculty member in the graduate program of Applied Mathematics
  at UC Davis. Dr. Fan’s research is on transportation and energy infrast
 ructure systems modeling\, with a special interest in integrating applied 
 mathematics and engineering domain knowledge to address fundamental challe
 nges brought by data and system uncertainty\, dynamics\, and underdetermin
 ed issues. Dr. Fan is currently serving as the program director of the Civ
 il Infrastructure Systems (CIS) program at the National Science Foundation
 .
CATEGORIES:Seminars
LOCATION:\, \, 
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=\, ;X-APPLE-RADIUS=100;X-TI
 TLE=:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20221106T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR