Clustering Weekly Patterns of Human Mobility Through Mobile Phone Data

Abstract

With the rapid growth of cell phone networks during the last decades, call detail records (CDR) have been used as approximate indicators for large scale studies on human and urban mobility. Although coarse and limited, CDR are a real marker of human presence. In this paper, we use more than 800 million of CDR to identify weekly patterns of human mobility through mobile phone data. Our methodology is based on the classification of individuals into six distinct presence profiles where we focus on the inherent temporal and geographical characteristics of each profile within a territory. Then, we use an event-based algorithm to cluster individuals and we identify 12 weekly patterns. We leverage these results to analyze population estimates adjustment processes and as a result, we propose new indicators to characterize the dynamics of a territory. Our model has been applied to real data coming from more than 1.6 million individuals and demonstrates its relevance. The product of our work can be used by local authorities for human mobility analysis and urban planning.

Improved user similarity computation for finding friends in your location

“…Our results are qualitatively similar with those in [32] where for a different problem it was again shown through silhouettes that the increase of K up to a point increases the probability of a user being in the best possible cluster, however the general quality of the solution decreases with a too big increase of K. We derived the best silhouette when K is around 25, i.e., for an average number of 11-12 users per cluster. The best K values when using all other similarity computation methods in eMatch were in the range of [20,23], and for each method we used its best K for the results that follow, in order to make a fair comparison.…”

Mining Human Mobility Data to Discover Locations and Habits

“…Even though there are indications that human movement is highly predictable, daily and weekly routines of individual users constitute a largely unexplored and unexploited area. [12] used more than 800 million of CDR data to identify weekly patterns of human mobility through mobile phone data. In [10], the authors present a methodology based on densitybased clustering, clustering-based sequential mining and Apriori algorithm for analyzing user location information in order to identify user habits.…”

A new method for traffic forecasting in urban wireless communication network

“…The design of the network determines the size of each community. The size of micro-cellular community in urban environment is generally 300 m, and some macro-community in rural environment can reach 30 km [11]. All adjacent cells are overlapping, allowing a continuous connection to the network when the mobile equipment is moving.…”

“…All adjacent cells are overlapping, allowing a continuous connection to the network when the mobile equipment is moving. Many adjacent cells are grouped in zones identified by a local area code (LAC) [11]. Operators will keep detailed records of mobile devices in use.…”