Abstract
With the remarkable technological evolution of mobile devices, the use of computing resources has become possible at any time and independent of the geographical position of the user. This phenomenon has various names such as omnipresent diffuse computing, pervasive computing, or ubiquitous systems. This new form of computing allows users to have access to shared and ubiquitous services focused on their needs, and it is based on context prediction, especially the prediction of the user's location. This paper aims to present a new approach for predicting a user's next probable location, by presenting an ontological model which is based on the pattern technique. This is carried out by using an ontological model that comprises different user behaviors and presents details about the environment, where the user is located. The results after tested on real data show that the presented ontological model was able to achieve 85% future location-prediction accuracy (in the case of no similar patterns). Future work will focus on the integration of the Bayesian network to improve the results. This approach will be implemented in smart homes or smart cities to reduce energy consumption.