Analysis of the pattern and intensity of urban activities through aggregate cellphone usage

摘要: This study applies passive mobile positioning data such as Call Volume, Handover, and Erlang to detect the spatiotemporal distributions of urban activities. We obtained hourly aggregated cellphone from a dataset communications in Lisbon, Portugal. Fuzzy c-mean clustering algorithm was applied create clusters locations with similar features two aspects activities: pattern intensity activities along hours day. In order validate those actual predictors human activity, we compared them formed using ground truth variables namely presence people, buildings, points interest, bus taxi movement. To identify patterns activities, provided better match, giving 69% overall accurate predictions. case Handover highest yielding 80% accuracy He...