GUESS: Prediction of the User Position in a Context-aware Mobile Environment through Qualitative Spatial Reasoning
The increasing availability of mobile networks and mobile devices motivate the emerging of new paradigms of interaction between users and between a user and the surrounding environment. In particular, when the position of a user is known, applications running on local or on mobile devices can adapt their behaviour accordingly to the position of the user. These applications are known as location-aware applications. In these applications, the position information is obtained from a set of position sensors, or from network-based location services, and is often used directly, without any further processing, as a parameter in the adaptation process. Besides this usual behaviour of the applications, location-aware applications could be pro-active, providing services that could be useful for the users before the user ask for them. For this kind of actions, location-aware applications need to anticipate the user position, predicting where the user is going to be.
This project aims the definition of a qualitative spatial reasoning system that allows the prediction of the user position based on his/her current position and looking at the topological relations existing among the geographical objects present in the analysed space. In order to achieve this goal, the qualitative spatial reasoning system, several objectives are defined:
- Identification of the topological spatial relations that can exist between the geographic objects in analysis: points (user position) and lines (objects in which movement in space is possible).
- Definition of the conceptual neighbourhood graphs that allow the prediction of the user position based on conceptual restrictions imposed by the geographic context in which the user is located.
- Identification of filters that allow the optimization of the prediction.
- Implementation of a qualitative spatial reasoning system prototype, allowing the verification of its applicability and usefulness to context-aware systems.
Running since October 2006.
- Maribel Yasmina Campos Alves Santos, Principal Investigator (University of Minho)
- Adriano Jorge Cardoso Moreira, Investigator (University of Minho)
- Arminda Manuela Andrade Pereira Gonçalves, Investigator (University of Minho)
- Raquel Menezes da Mota Leite, Investigator (University of Minho)
- Fernando José Ferreira Lucas Bação, Investigator (New University of Lisbon)
- Victor José Almeida Sousa Lobo, Investigator (New University of Lisbon)