Communications of the ACM
Inferring rban Travel Patterns From Cellphone Data
Researchers from MIT and Ford Motor have developed a new computational system that uses cellphone location data to infer urban mobility patterns.
Credit: MIT News
A new computational system can use cellphone location data to infer urban mobility patterns.
The system's developers, from the Massachusetts Institute of Technology (MIT) and Ford Motor, say they launched the system over six weeks in the Boston area and were able to use residents' data to quickly assemble the kind of model of urban mobility patterns that typically takes years to build.
"Our framework...learns mobility features from a large number of users, without having to ask them directly about their mobility choices," says MIT professor Marta Gonzalez. "Based on that, we create individual models to estimate complete daily trajectories of the vast majority of mobile-phone users."
The team validated the system by comparing the model it generated to the model currently used by Boston's city planners, and found the two models compared favorably.
The team views the method and model as potential tools for planners considering the next generation of infrastructure. They say the system could deliver more accurate and timely data about urban mobility, and determine whether various efforts to address cities' transportation needs are working.
"Likely, in time, we will see that this brings the comparative advantage of making urban transportation planning faster and smarter and even allows directly communicating recommendations to device users," Gonzalez says.
From MIT News
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found