By Jason Jacks
As a respected researcher whose knowledge is sought in certain scientific circles, Phil Yang has work that has him traveling often on Washington, D.C., area roads. In other words, he knows traffic.
“It’s kind of a headache,” Yang says of not knowing when and where a backup may occur. “It’s not predictable.”
But Yang, who is codirector of Mason’s Joint Center for Intelligent Spatial Computing (CISC), may have a solution in the form of a system his team developed that uses real-time and historical traffic data to predict congestion hot spots.
Nationwide, according to the Texas Transportation Institute’s 2009 Urban Mobility Report, traffic is blamed for the loss of about $87 billion worth of fuel and productivity annually. That amounts to about $750 for every traveler in the country.
Yang’s portfolio of software technologies—collectively called the Road Traffic Prediction System—is designed to ease this mounting problem. By tapping into local sources of weather, roads, construction, and law enforcement information, the system calculates and predicts possible traffic tie-ups “on the fly,” Yang says. In making these calculations, the system could also suggest alternative routes to avoid those tie-ups.
So far, Yang; fellow CISC researcher Ying Cao, who has worked extensively on the project; and other team members have tested the system using simulated traffic scenarios. To get it in the hands of consumers, they are talking with several entrepreneurs about creating a company to commercialize the technology. The system, he says, would couple nicely with a global positioning system unit or could be a cell phone application.
“This could benefit anyone who drives,” Yang predicts.
Funding for the system, which totaled more than $2 million, came from NASA, the U.S. Department of Transportation, and the U.S. Geological Survey.