Spatio-Temporal Modeling of Wireless Users Internet Access Patterns Using Self-Organizing Maps

TL;DR

This paper presents a novel approach using self-organizing maps to analyze and visualize large-scale mobile user internet access patterns across multiple locations and web domains, revealing significant correlations.

Contribution

It introduces a systematic SOM-based modeling method for large-scale multi-dimensional analysis of mobile user behavior and proposes a mixture model for realistic wireless network usage simulation.

Findings

Users' trends can be accurately modeled with SOMs.

Distinct characteristics in user behavior based on domains and locations.

Identification of non-trivial correlations between web domains and locations.

Abstract

User online behavior and interests will play a central role in future mobile networks. We introduce a systematic method for large-scale multi-dimensional analysis of online activity for thousands of mobile users across 79 buildings over a variety of web domains. We propose a modeling approach based on self-organizing maps (SOM) for discovering, organizing and visualizing different mobile users' trends from billions of WLAN records. We find surprisingly that users' trends based on domains and locations can be accurately modeled using a self-organizing map with clearly distinct characteristics. We also find many non-trivial correlations between different types of web domains and locations. Based on our analysis, we introduce a mixture model as an initial step towards realistic simulation of wireless network usage.