PROJECT TITLE :

Clustering Weekly Patterns of Human Mobility Through Mobile Phone Data - 2018

ABSTRACT:

With the fast growth of mobile phone networks during the last decades, decision detail records (CDR) are used as approximate indicators for giant scale studies on human and concrete mobility. Although coarse and limited, CDR are a real marker of human presence. During this Project, we tend to use more than 80zero million CDR to identify weekly patterns of human mobility through itinerant data. Our methodology is predicated on the classification of individuals into six distinct presence profiles where we tend to focus on the inherent temporal and geographical characteristics of each profile among a territory. Then, we have a tendency to use an occurrence-based mostly algorithm to cluster people and we establish twelve weekly patterns. We tend to leverage these results to analyze population estimates adjustment processes and thus, we propose new indicators to characterize the dynamics of a territory. Our model has been applied to real information coming back from more than one.half-dozen million individuals and demonstrates its relevance. The product of our work can be used by native authorities for human mobility analysis and urban designing.