Communications of the ACM
Motion-Sensing Phones That Predict Your Every Move
Credit: Sam Lin
Technical University of Delft researchers have developed a smartphone program that learns users' behavior patterns to provide better cell phone service. The program, developed by Delft's Arjen Peddemors and colleagues, uses predictable actions such as locking the front door, opening the garage, or getting into the car to create an electronic signature of particular events. A neural network program installed on the phone is then trained to predict what happens next and act accordingly. If a certain route takes the user out of the range of cell phone service, the program can pause downloads or negotiate with the cell phone network to maintain 3G capacity.
Peddemors says the idea of predicting mobility events could be useful in situations when preventing the loss of data is critical, such as the transmission of physiological data in heart-rate and blood-pressure machines. "By predicting the patient's movements, the upload of that critical data won't be attempted unless their behavior says it can be completed," he says.
From New Scientist
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA 
No entries found