Before many travelers head to the beach or up to the mountains to go apple picking or skiing, they check a weather app.
One day, they also may check a traffic app that will help them get to the beach or the mountains without getting stuck in a traffic jam or waylaid by an accident.
Researchers at the Virginia Tech Transportation Institute are working on a cloud-based application that will use real-time information and historical data to predict when and where traffic is likely to snarl and slow a trip.
To build the travel app, university researchers created an algorithm that combines historical and real-time data to predict traffic patterns and congestion, according to Virginia Tech. To create a useful app, it's key to not only look at what is currently happening on a road but to factor in historical information.
When congestion occurs over and over, and events happen repeatedly, patterns emerge, and those patterns can be used to make predictions.
"Most people think traffic prediction has been implemented, used long ago, but it's actually new," said Hao Chen, a Ph.D candidate at Virginia Tech and a researcher on the project.
Mapping applications typically rely on mileage and speed limits to predict travel times, and digital traffic warning signs set up beside highways tend to only announce traffic jams that are already happening.
"They don't have the confidence to tell you what will happen," Chen added in a statement. "We can provide on average 95% prediction accuracy for travel time."
Researchers noted that one of the challenges they faced with creating a smartphone app that can predict traffic patterns and travel times is the sheer volume of information needed.
To overcome that, they used cloud computing.
"All the information resides up in the cloud," said Wu Feng, a professor in the departments of Computer Science and Electrical and Computer Engineering at Virginia Tech. "An end user merely queries the cloud. The cloud computes the answer and then ships it back to your phone or laptop. The big data simply remains in the cloud."