IBM training computers to predict traffic (AP)
SAN FRANCISCO – Traffic websites, with their color-coded maps of obstructed streets and freeways, are beatific at informing commuters when crowding is already awful. But what if they could know not exclusive where you drive, but if the line is feat to be bad today, and warned you aweigh of time?
A aggroup of researchers at IBM Corp. are working on a grouping that would do meet that.
They've combined sophisticated analytics software with a network of sensors the state has already embedded in roadways throughout California. With the support of a database of time reciprocation tie-ups, they feature they crapper prognosticate when they'll hap in the future.
IBM, which worked with the state Department of Transportation and the Calif. Center for Innovative Transportation at the University of California, Berkeley, can't tell you when an accident is feat to hap — yet. But John Day, an IBM manager, says that's a uncolored spreading of the impact his aggroup has been doing, and one period could well be something they could fairly derive from the accumulation they're collecting.
For now, the researchers are display that they crapper go a travel beyond what's available on regional reciprocation websites, which report current conditions. The most that strength tell you is that your drive is already hardback up.
"Instead of meet display them look how grotesque this looks, or what it looked like 5 transactions ago, let's wage them an idea of what this looks like 30-40 transactions from now," Day said in an interview.
IBM's information relies on a tactic some strength encounter invasive — using GPS coordinates from users' cellphones — to see their regular commutes so it crapper offer suggestions when those routes are clogged. (Google Inc.'s traffic-monitoring information uses locations reported by radiotelephone chips, but exclusive to amount out if there's congestion.)
Day says the project, which is still in the research stage, could yet be combined with another accumulation much as train schedules and another installation data, to wage a fuller picture of people's regular migrations and take a constant beat of the upbeat of a region's installation infrastructure.
Source
0 comments:
Post a Comment