Software 'predicts' phone app you need

U.S. researchers say a "predictive" system can speed up loading of cellphone apps, often slow to load due to ever-richer graphics and overloaded networks. The system developed at the University of Massachusetts could mean the desired app might be ready and waiting the moment before a user needs it, NewScientist.com reported Wednesday. Called predictive caching, the technique involves guessing which software is most likely to be needed for the next stage of a computerized process so that an app is primed to run when called on, without having to boot from scratch. The system uses the phone's location and motion sensors to learn when the user typically runs a particular app, researcher Tingxin Yan and colleagues said. As an example, they said, as a user walks to a railway station each day, they may open a train times app to see if the trains are running on time when they reach a particular street corner. The predictive software can check the time the user usually does this, senses the user is walking and preloads the app with the current train info retrieved by the time the user arrives at the corner where they normally request it. Researchers said in tests the software cut 6 seconds from the average 20-second boot-up time for apps on Windows phones.