Download Now Free registration required
The growing number of sensors on mobile phones is enabling a closer look into the micro-behavior of human users. The authors envision that such behavioral insights can help deliver enhanced network services. While behavior-aware networking is a broad research theme, they take up a narrower problem in the space of 3G-WiFi networks. They show that sensor readings from mobile phones can be analyzed by machine learning algorithms to roughly predict how long a user will stay within a WiFi hotspot. Users predicted to leave soon can be allocated greater WiFi bandwidth (i.e., higher priority), thereby reducing the traffic load that gets carried over to 3G.
- Format: PDF
- Size: 441 KB