BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:CESS Seminar Series - Digital footprints for Mobility Analysis in 
 Public Transport: from Descriptive to Predictive analytics
DTSTART:20221011T110000
DTEND:20221011T120000
DTSTAMP:20260513T020101Z
UID:ca64f8730671c9790469872bf546181dbad3a17fcef6acc35f36af38
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr Latifa Oukhellou\, Research Director\, Université Gustav
 e Eiffel (France)\nAbstract\nThe last few decades have seen a faster devel
 opment of digital systems for observing the mobility of people. Various se
 nsing systems such as radio communication\, Wi-Fi\, Bluetooth\, validation
  of smart cards\, mobile phones\, and road traffic monitoring systems have
  enabled researchers and practitioners to acquire large amounts of data\, 
 which generally refer to individual and collective trajectories. The mobil
 ity data can be further enriched with side information\, such as text corp
 ora from social media\, survey data\, and weather information.\nThese mass
 ive data\, temporally and spatially structured\, are not necessarily desig
 ned to analyze mobility. Still\, they can benefit from advanced machine le
 arning and data mining methods\, providing decision aid tools and contribu
 ting to the development of safer\, cleaner\, and more efficient transporta
 tion systems.\nThe seminar will be the opportunity to present a synthesis 
 of the research work on smart card data collected on the urban transport n
 etwork of two cities in France (Rennes and Paris). This presentation will 
 first focus on descriptive methods based on unsupervised learning (cluster
 ing)\, highlighting mobility patterns and transport system usage. The seco
 nd part will focus on predictive analytics in a supervised learning framew
 ork to predict quantities of interest\, such as transit network ridership 
 or load passengers in a metro line. The implementation of these methods fa
 ces challenges related to the incompleteness\, heterogeneity\, and strong 
 temporal and spatial correlation within the data\, and their high dimensio
 nality or volume.\n\nBiography\nLatifa Oukhellou is currently Research Dir
 ector at Université Gustave Eiffel\, France\, and the head of the GRETTIA
  Laboratory (Transportation Engineering and Computer Science Laboratory). 
 Prior to joining Univ Eiffel\, she was an Assistant Professor at the Unive
 rsity of Paris-Est Créteil. She founded the Data and Mobility Group at th
 e GRETTIA Laboratory in 2011. Her research interests include data mining\,
  machine learning\, and information fusion applied to diagnosis problems a
 nd to spatio-temporal data mining for identifying driving behavior\, analy
 zing urban mobility or monitoring energy\, and water smart grids. She is i
 nvolved in several research projects in the field of intelligent transport
 ation systems or urban computing for smart cities. She has authored or coa
 uthored over 150 papers in international scientific journals and conferenc
 e proceedings in the area of data mining\, machine learning and transporta
 tion science.\n 
LOCATION:GC A3 30 https://plan.epfl.ch/?room==GC%20A3%2030
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR