CS545:
Stanford Data Science / Infoseminar
Winter 2015

Urban mobility meets big data

Alexey Pozdnukhov, University of California Berkeley

Abstract

This talk explores the opportunities for designing smarter urban services based on data analytics. It presents some recent developments tailored for processing geo-referenced streams from city sensing infrastructures and individual-level citizen-generated data to produce a semantically rich representation of urban dynamics in terms of mobility flows, communication and social interaction patterns. It further discusses modelling steps towards designing and evaluating a data-driven decision support framework for managing urban mobility services.

Bio

Prof. Alexei Pozdnoukhov graduated from the Physics Department of the Moscow State University in 2003 with a degree in mathematical physics. In 2006 he received a Ph.D. in computer science from EPFL, Switzerland, following his research in machine learning methods and computer vision that he carried out at IDIAP Research Institute in Martigny, Switzerland. In 2008 he joined the National Centre for Geocomputation, National University of Ireland Maynooth as a recipient of a Stokes Lectureship from the Science Foundation Ireland. Prof. Pozdoukhov leaded a group engaged in several research projects, including the strands of Irish Strategic Reseach Cluster in Advanced Geotechnologies, and several national and European projects. He has developed methodologies to apply machine learning methods in computational environmental modelling, integrate prior knowledge and efficiently process geo-referenced data streams from sensor networks. His current research at CEE, UC Berkeley is in the area of complex data analysis in the domain of Smart Cities, including applications of streaming data analytics in urban mobility and location-based social networks.