April 13, 2011

IBM Technology To Predict Real-time Traffic Jams

Smartphone software designed to predict traffic jams and warn motorists even before they get on the road is being tested by IBM, reports AFP.

The new technology is being tested by IBM employees in San Francisco and the Silicon Valley area in Northern California, which the company hopes "will ultimately help drivers around the world" avoid bad traffic.

IBM has developed a "first-of-its-kind learning and predictive analytics tool" service called Traffic Prediction Tool (TPT) that continuously analyzes congestion data, commuter locations and expected travel start times throughout a metropolitan area. This information can eventually help commuters on highways, rail-lines as well as urban roads.

"The idea is to learn a traveler's habits, then run it on the predictive model to see what traffic they can expect," program manager John Day told the AFP news agency.

"The objective was to make it much more personal and provide it to them just before they were about to leave."

Real-time data from bus or train systems will also be integrated into the technology so that the service could advise people when it would be better to use public transit.

The IBM Smarter Travel program will have location-sensing capabilities that will track where and when an individual drives, says Day.

Information is fed through the Internet to computers that identify patterns a driver makes in commutes to and from work, reports AFP.

Furthermore, analysis of data collected from roadway sensors that are used for online traffic maps will help to determine conditions that lead to trouble in on roadways.

Personalized predictions are then formed from these results to show when a motorist will encounter highway problems.

"We wanted to take advantage of analytic tools to provide predictive capabilities; to get correlations with minor slowdowns and major ones that happen after that," says Day to AFP.

"So you can run a query at any point for a journey and predict 35 or 40 minutes in advance what it will look like, then couple that with a personal approach for the individual traveler," he says.

Individuals are able to receive customized alerts on their smartphones to warn them of possible traffic problems before they even set out on a routine drive or commute.

In addition, the will be able to manage their travel data online as well as privacy protections to include obscuring start and end points of trips.

"Unlike existing traffic alert solutions, we're helping take the guesswork out of commuting," says Stefan Nusser of IBM Almaden Services Research.

"The predictive capabilities are head and shoulders above what exists today," Day said. "Everything out there is showing you traffic as reported five or 10 minutes ago. Nobody does predictive."

IBM has been testing the pilot program in California for about five months and hopes to build a system that can work for the entire world.

On the Net: