acm-header
Sign In

Communications of the ACM

ACM TechNews

Rutgers Researchers Show That How Fast You Drive Might Reveal Exactly Where You Are Going


View as: Print Mobile App Share:
With sufficient information on a motorist's driving habits, researchers who know a driver's starting point and driving speed can predict where that driver is headed.

Researchers at Rutgers University have developed elastic pathing, which can predict a motorist's destination given enough information about his/her driving habits, starting point, and driving speed.

Credit: Rutgers Today

Motorists sometimes allow insurance companies to monitor their driving habits in exchange for discounts on their premiums, but researchers at Rutgers University say doing so may disclose where motorists are driving, even in the absence of a global positioning system device or other location-sensing technology.

"We've shown that speed data and a starting point are all we need to roughly identify where you have driven," says Rutgers professor Janne Lindqvist.

Dubbed elastic pathing, the approach predicts pathways by matching speed patterns to street layouts. Lindqvist and his colleagues tested the technique by examining data from six drivers in New Jersey traveling to 46 different destinations over 240 trips, as well as from 21 drivers in Seattle over 691 trips. The technique predicted the final destination within a little less than one-third of a mile from the actual endpoint for more than 20 percent of the trips.

"In time, we expect improvements will be made to our initial approach," Lindqvist says.

He also suggests insurance companies consider alternatives to collecting speedometer readings to ensure better privacy protection.

Rutgers doctoral student Xianyi Gao will present the team's research at the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing in September.

From Rutgers Today
View Full Article

 

Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account