Big data analysis of mobility patterns and their energy implications

Big data analysis of mobility patterns and their energy implications
28th November 2016 Alison Parker

Transport

Modeling

Analysis

Developing methodologies for deriving individuals travel patterns via big data. The patterns are analysed based on several socio-economic characteristics, built environment characteristics/urban form, transport mode used, time of the day, happiness, weather conditions etc., while scenarios are constructed for the implications of mobility patterns on energy consumption

Overview

In the era of smartphones and big data the quantity and granularity of available information is increasing several fold. Transportation data collection is trailing this trend and is advancing to exploit these new technologies and shift towards improved approaches for analysis. However, the new forms of data collection create uncertainty and errors, which need to be corrected and validated with new methods and visualisation techniques. The aim of this project is to develop methodologies for deriving individuals travel patterns via big data. The patterns are analysed based on several socio-economic characteristics, built environment characteristics/urban form, transport mode used, time of the day, happiness, weather conditions etc., while scenarios are constructed for the implications of mobility patterns on energy consumption.

Key findings

  • Matching GPS traces to underground network
  • Visualisation of happiness while travelling by London underground

Research Lead

Name Surname

Outputs

Papanikolaou, A., N. Vavlas, M. Kamargianni, M. Matyas, and S. Thanos 2016. A Pattern-Based Approach For Assessing And Visualizing User Satisfaction Of London Underground In A Big Data Era. Paper submitted for presentation to the 96th Transportation Research Board, Washington DC, January 2017.