CESS Seminar Series - Digital footprints for Mobility Analysis in Public Transport: from Descriptive to Predictive analytics
Event details
| Date | 11.10.2022 |
| Hour | 11:00 › 12:00 |
| Speaker | Dr Latifa Oukhellou, Research Director, Université Gustave Eiffel (France) |
| Location | |
| Category | Conferences - Seminars |
| Event Language | English |
Abstract
The last few decades have seen a faster development of digital systems for observing the mobility of people. Various sensing 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 mobility data can be further enriched with side information, such as text corpora from social media, survey data, and weather information.
These massive data, temporally and spatially structured, are not necessarily designed to analyze mobility. Still, they can benefit from advanced machine learning and data mining methods, providing decision aid tools and contributing to the development of safer, cleaner, and more efficient transportation systems.
The seminar will be the opportunity to present a synthesis of the research work on smart card data collected on the urban transport network of two cities in France (Rennes and Paris). This presentation will first focus on descriptive methods based on unsupervised learning (clustering), highlighting mobility patterns and transport system usage. The second part will focus on predictive analytics in a supervised learning framework to predict quantities of interest, such as transit network ridership or load passengers in a metro line. The implementation of these methods faces challenges related to the incompleteness, heterogeneity, and strong temporal and spatial correlation within the data, and their high dimensionality or volume.
Biography
Latifa Oukhellou is currently Research Director 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 University of Paris-Est Créteil. She founded the Data and Mobility Group at the GRETTIA Laboratory in 2011. Her research interests include data mining, machine learning, and information fusion applied to diagnosis problems and to spatio-temporal data mining for identifying driving behavior, analyzing urban mobility or monitoring energy, and water smart grids. She is involved in several research projects in the field of intelligent transportation systems or urban computing for smart cities. She has authored or coauthored over 150 papers in international scientific journals and conference proceedings in the area of data mining, machine learning and transportation science.
The last few decades have seen a faster development of digital systems for observing the mobility of people. Various sensing 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 mobility data can be further enriched with side information, such as text corpora from social media, survey data, and weather information.
These massive data, temporally and spatially structured, are not necessarily designed to analyze mobility. Still, they can benefit from advanced machine learning and data mining methods, providing decision aid tools and contributing to the development of safer, cleaner, and more efficient transportation systems.
The seminar will be the opportunity to present a synthesis of the research work on smart card data collected on the urban transport network of two cities in France (Rennes and Paris). This presentation will first focus on descriptive methods based on unsupervised learning (clustering), highlighting mobility patterns and transport system usage. The second part will focus on predictive analytics in a supervised learning framework to predict quantities of interest, such as transit network ridership or load passengers in a metro line. The implementation of these methods faces challenges related to the incompleteness, heterogeneity, and strong temporal and spatial correlation within the data, and their high dimensionality or volume.
Biography
Latifa Oukhellou is currently Research Director 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 University of Paris-Est Créteil. She founded the Data and Mobility Group at the GRETTIA Laboratory in 2011. Her research interests include data mining, machine learning, and information fusion applied to diagnosis problems and to spatio-temporal data mining for identifying driving behavior, analyzing urban mobility or monitoring energy, and water smart grids. She is involved in several research projects in the field of intelligent transportation systems or urban computing for smart cities. She has authored or coauthored over 150 papers in international scientific journals and conference proceedings in the area of data mining, machine learning and transportation science.
Practical information
- Informed public
- Free
Organizer
- Prof. Alexandre Alahi, Head of VITA lab, EPFL
Contact
- Prof. Alexandre Alahi, Head of VITA lab, EPFL