Estimating Activity Patterns Using Spatio-temporal Data of Cellphone Networks

The tendency towards using activity-based models to predict trip demand has increased dramatically over recent years, but these models have suffered insufficient data for calibration. This paper discusses ways to process the cellphone spatio-temporal data in a manner that makes it comprehensible for traffic interpretations and proposes methods on how to infer urban mobility and activity patterns from the aforementioned data. Movements of each subscriber is described by a sequence of stays and trips and each stay is labeled by an activity. The type of activities are estimated using features such as land use, duration of stay, frequency of visit, arrival time to that activity and its distance from home. Finally, the chains of trips are identified and different patterns that citizens follow to participate in activities are determined. The data comprises 144 million records of the location of 300,000 citizens of Shiraz at five-minute intervals