Analysis of wireless network access logs for a hierarchical characterization of user mobility

2026-05-14

AI Summary

This study addresses the challenges of modeling user mobility in large-scale Wi-Fi logs, particularly the trade-off between model complexity and geographic adaptability. The authors propose a hierarchical modeling approach that constructs user trajectories from sequences of Wi-Fi access points, recursively clusters geographic features to derive multi-granular spatial regions, and integrates user profiles to learn state transition matrices and dwell-time vectors. Evaluated on a campus dataset from the University of the Balearic Islands, the method significantly reduces model complexity while preserving accuracy and enhancing generalization across diverse geographic contexts. Experimental results demonstrate that the hierarchical approach substantially outperforms non-hierarchical baselines in modeling transition dynamics, although dwell-time prediction remains an area requiring further refinement.

Abstract

This paper presents a method that generates a hierarchical user mobility model from the analysis of the data available from Wi-Fi connections. The data obtained from the Wi-Fi infrastructure is defined in terms of the coverage areas of the access points that the users move through. These access points are recursively grouped into different levels of granularity based on their geospatial features. The track of a user is defined as a sequence of Wi-Fi access points, which is enough to simulate user mobility in, for example, fog scenarios. The hierarchical definition of the region under study is proposed to reduce the complexity of the model in high-scale scenarios and to increase the adaptability between scenarios with different geospatial features. The model creation is based on a user profiling method that uses a clustering algorithm and each user type is defined with a transition matrix between coverage areas and a time length vector for the areas. The method is applied to the case of the campus of the University of the Balearic Islands. From the analysis of the mean square error of the results, we determined that the proposed method obtains good results for the transition matrices, but that the time vector definition should be improved. The results also show lower complexity in the case of the hierarchical model, with one area for each building and three levels, in regard to a non-hierarchical model, with only one area and one level for the whole campus.

Problem

• user mobility
• Wi-Fi access logs
• hierarchical modeling
• geospatial features
• mobility characterization

Innovation

• hierarchical mobility modeling
• Wi-Fi access logs
• user profiling
• clustering algorithm
• transition matrix