Our goal is to rationalize the human (digital) footprint for sustainable development. Mobility solutions such as better route selection, parking, and car sharing do not use data driven models of instant information. We seek to tackle these challenges by using the information leveraged by our models into on-line applications. Current models of travel demand are based in Census and Activity Surveys which get outdated and are limited in size.
For example, We parse OpenStreetMaps (OSM) inferring various street properties such as number of lanes, speed, and capacity to create routable and comparable road networks in many cities currently lacking such data. We implement a fast, distributed incremental traffic assignment algorithm to route millions of trips captured by mobile phone data and made between intersections in cities in seconds. Results are presented in an interactive visualization platform for use by researchers, citizens, and policy makers to better inform their decisions regarding transportation.
Source: The path most travelled: Mining road usage patterns from massive call data , pdf, 2014.
As another example, we also analyze transit agencies’ publicly available General Transit Feed Specification (GTFS) data and their live XML feeds of bus GPS coordinates. Here we specifically focus on the Massachusetts Bay Transit Authority (MBTA) bus network centered around Boston through May 2011. After performing map-matching of real time coordinates to the shapes of the road network, we can analyze travel time dynamics and, more importantly, detect the time when each bus arrives and departs to and from each stop. Based on this we calculate and model the delay of a buses within a bus route, taking into account zones with traffic and busier stops.
Source: Analyzing Cell Phone Location Data for Urban Travel: Current Methods, Limitations and Opportunities (Serdar Çolak, Lauren P. Alexander, Bernardo Guatimosim Alvim, Shomik R. Mehndiretta and Marta Gonzalez), in press, Transportation Research Records, (“Practice Ready” for Presentation in the annual TRB meeting 2014) [pdf]
We present methodology for extracting ODs from mobile phone data that compares favorably with the transportation models of cities, extracted via travel surveys.
Source: The Potential of Low-Frequency AVL Data for the Monitoring and Control of Bus Performance , Transportation Research Record: Journal of the Transportation Research Board, Volume 2351, pp. 54-64, Transit 2013, Vol. 2 (2013) [pdf] (in Proceedings of the: Transportation Research Board 92nd Annual Meeting, 2013).