Human mobility prediction based on individual and collective geographical preferences
Open Access
- 1 September 2010
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Understanding and predicting human mobility is a crucial component of transportation planning and management. In this paper we propose a new model to predict the location of a person over time based on individual and collective behaviors. The model is based on the person's past trajectory and the geographical features of the area where the collectivity moves, both in terms of land use, points of interests and distance of trips. The effectiveness of the proposed prediction model is tested using a massive mobile phone location dataset available for the Boston metropolitan area. Experimental results show good levels of accuracy in terms of prediction error and prove the advantage of using the collective behavior in the prediction model.Keywords
This publication has 13 references indexed in Scilit:
- Limits of Predictability in Human MobilityScience, 2010
- WhereNextPublished by Association for Computing Machinery (ACM) ,2009
- Understanding the Spreading Patterns of Mobile Phone VirusesScience, 2009
- Eigenbehaviors: identifying structure in routineBehavioral Ecology and Sociobiology, 2009
- Mining user similarity based on location historyPublished by Association for Computing Machinery (ACM) ,2008
- Understanding mobility based on GPS dataPublished by Association for Computing Machinery (ACM) ,2008
- Understanding individual human mobility patternsNature, 2008
- Cellular Census: Explorations in Urban Data CollectionIEEE Pervasive Computing, 2007
- Learning and inferring transportation routinesArtificial Intelligence, 2007
- Reality mining: sensing complex social systemsPersonal and Ubiquitous Computing, 2005