Mobile devices have become one of the main sensors of hu- man behavior, and as such, can be used as proxies to study urban environments. In this paper we describe a method to automatically identify land uses from call detail record databases. Given the inherent diversity of human activities in urban landscapes, we use fuzzy clustering tech- niques to identify land uses in a robust way, characterizing only those geographical areas with well defined behaviors. Finally, we validate the results obtained using expert knowledge.
| 
