Title: Crowd location forecasting at points of interest

Authors: Jorge Alvarez-Lozano; J. Antonio García-Macías; Edgar Chávez

Addresses: Computer Science Department, CICESE Research Center, Carr. Ensenada-Tijuana 3918, Ensenada, México ' Computer Science Department, CICESE Research Center, Carr. Ensenada-Tijuana 3918, Ensenada, México ' Institute of Mathematics, Universidad Nacional Autónoma de México. Circuito Exterior, Ciudad Universitaria, Coyoacán, 04510, México, D.F.

Abstract: Predicting the location of a mobile user in the near future can be used for a large number of user-centred ubiquitous applications. This can be extended to crowd-centred applications if a large number of users is included. In this paper we present a spatio-temporal prediction approach to forecast user location in a medium-term period. Our approach is based on the hypothesis that users exhibit a different mobility pattern for each day of the week. Once factored out this weekly pattern, user mobility among points of interest is postulated to be markovian. We trained a hidden Markov model to forecast user mobility and evaluated our approach using a public dataset. The experimental results show that our approach is effective considering a time period of up to 7 h. We obtained an accuracy of up to 81.75% for a period of 30 min, and 66.25% considering 7 h.

Keywords: data mining; data sharing; spatio-temporal crowd locations; crowd location forecasting; user location predictability; user mobility similarity; points of interest; mobile users; mobility patterns; weekly patterns; hidden Markov model; HMM.

DOI: 10.1504/IJAHUC.2015.069056

International Journal of Ad Hoc and Ubiquitous Computing, 2015 Vol.18 No.4, pp.191 - 204

Received: 27 Feb 2013
Accepted: 24 Sep 2013
Published online: 26 Apr 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article