Contextual case-based reasoning applied to a mobile device

This paper aims to apply a contextual case-based reasoning (CBR) to a mobile device. The CBR method was chosen because it does not require training, demands minimal processing resources and easily integrates with the dynamic and uncertain nature of pervasive computing. Based on a mobile user’s location and activity, which can be determined through the device’s inertial sensors and GPS capabilities, it is possible to select and offer appropriate services to this user.

The proposed approach comprises two stages. The first stage uses simple semantic similarity measures to retrieve the case from the case base that best matches the current case. In the second stage, the obtained selection of services is then filtered based on current contextual information.

This two-stage method adds a higher level of relevance to the services proposed to the user; yet, it is easy to implement on a mobile device.

A two-stage CBR using light processing methods and generating context aware services is discussed. Ontological location modeling adds reasoning flexibility and knowledge sharing capabilities.