About the event
Abstract:
Contemporary urban policy makers face a critical challenge over the next decade or so: transport infrastructure needs to be able to cope with growing (and increasingly mobile) populations, yet central and local governments are operating in an era of austerity where major new investment in infrastructure is unlikely. Data science and data-centric engineering offer a potential solution to this problem. Data about the way the infrastructure is used may offer ways of optimising the existing use of infrastructure and open the possibility of improving the performance of existing traffic networks without making major new investments.
This presentation focuses on research seeking to use crowd-sourced data, such as OpenStreetMap and Waze, to improve traffic models and better understand the factors contributing to traffic jams and other traffic issues. Alongside this work, we will present new browser-based visual analytics tools we are developing to help city planners and local government officials access, understand, and generate actionable insights from these new data sources.
This seminar is open to all as part of the Data-Centric Engineering Programme at the Alan Turing Institute.
Bios:
Scott Hale is a Turing Fellow who develops and applies techniques from computer science to research questions in both computer science and the social sciences and seeks to put these results into practice with industry partners. He is particularly interested in multilingualism and user experience, mobilization/collective action, human mobility, and data visualization.
Jonathan Bright is a Senior Research Fellow at the Oxford Internet Institute. His research interests lie in the areas of digital politics (with a focus on online political behaviour) and electronic government (with a particular interest in how data science is enabling new forms of local government). He is also an Editor of the journal Policy & Internet.
Chico Camargo is a Postdoctoral Researcher in Data Science. He uses tools from mathematical modelling and network science to answer questions in the social sciences, focusing on public opinion dynamics, information dynamics, and human mobility.
Graham McNeill is a researcher at the Oxford Internet Institute interested in data science and machine learning. His specific interests include human mobility, visual analytics of spatio-temporal data, and browser-based tools for machine learning.
