Spatio-Temporal Modeling of Wireless Users Internet Access Patterns Using Self-Organizing Maps
Users behavior and interests will play a central role in future mobile networks. They introduce a systematic method for large-scale multi-dimensional analysis of online activity for thousands of mobile users across 79 buildings over 100 web domains. They propose a modeling approach based on self-organizing maps for discovering, organizing and visualizing different mobile users' trends from billions of WLAN and net-flow records. They find surprisingly that users' trends based on domains or locations can be modeled using a self-organizing map with clearly distinct characteristics.