Contextual Location Prediction Using Spatio-Temporal Clustering

D. Guessoum, Miraoui, M., Tadj, C.

The prediction of a context, especially of a user’s location, is a fundamental task in the field of pervasive computing. Such predictions open up a new and rich field of proactive adaptation for context-aware applications. The proposed methodology predicts a user’s location on the basis of a user’s mobility history. The method uses contextual information (current position, day of the week, time, speed) that can be acquired easily and accurately with the help of common sensors such as GPS. This information is then used to find the points of interest that a user visits frequently and to determine the sequence of these visits with the aid of spatial clustering, temporal segmentation, and speed filtering. The proposed method was tested with a real dataset using several supervised classification algorithms, which yielded very interesting results.

Keywords: pervasive computing, context, location prediction, clustering, dbscan.