Understanding Human Movement Semantics: A Point of Interest Based Approach

Abstract : The recent availability of human mobility traces has driven a new wave of research -- on human movement -- with straightforward applications in wireless/cellular network algorithmic problems. However, all of the studies isolate movement from the environment that surrounds people, i.e., the points of interest that they visit. In this paper we revisit the human mobility problem with new assumptions. We believe that human movement is not independent of the surrounding locations; most of the time people travel with specific goals in mind, visit specific points of interest, and frequently revisit favorite places. Points of interest are also differently spread. We study the correlation between people's trajectories and the differently spread points of interest nearby. More specifically, by analyzing GPS mobility traces of a large number of users located across two distinct geographical locations, we find that: (i) users do not articularly visit only locations that are close to them but the functional aspect of the location matters as well, (ii) although users in different parts of the globe exhibit different time-of-day behavior, we also find that there is a striking correlation in the frequency of visits to the basic points-of-interest categories that we define.
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger

Contributeur : Kévin Huguenin <>
Soumis le : mercredi 1 février 2012 - 09:16:49
Dernière modification le : vendredi 16 novembre 2018 - 01:38:14
Document(s) archivé(s) le : vendredi 11 mai 2012 - 16:11:42


Fichiers produits par l'(les) auteur(s)


  • HAL Id : inria-00616876, version 2


Ionut Trestian, Kévin Huguenin, Ling Su, Aleksandar Kuzmanovic. Understanding Human Movement Semantics: A Point of Interest Based Approach. [Research Report] RR-7716, Inria. 2011, pp.21. 〈inria-00616876v2〉



Consultations de la notice


Téléchargements de fichiers