A Crowdsourcing Urban Simulation Platform on Smartphone Technology: Strategies for Urban Data Visualization and Transportation Mode Detection

We propose a crowdsourcing simulation environment that brings human intention into the urban simulator. Our fundamental goal is to simulate urban sustainability by employing direct human interaction. In this paper we present a prototype mobile phone application that implements a novel transportation mode detection algorithm. The mobile phone application runs in the background and continuously collects data from the built-in acceleration and network location sensors. The collected data is analyzed by the transportation mode detection algorithm and automatically partitioned into activity segments. A key observation of our work is that walking activity can be robustly detected in the data stream and acts as a separator for partitioning the data stream into other activity segments. Each vehicle activity segment is then sub-classifi ed according to the type of used vehicle. Our approach yields high accuracy despite the low sampling interval and not requiring GPS data that bring minimized device power consumption. Ultimately, the collected information can be translated into real-time urban behavior and will indicate sustainability, both on the personal and the city level.