Abstract
Spatial relevancy is one of the primary types of relevancies that determine whether a context is spatially related to the user or not. This paper specifically addresses the use of spatial relationships for detecting spatially relevant contexts. A key aspect is the consideration of all types of spatial relationships (metric, directional and topologic). The proposed approach is restricted to the urban network and assumes that in such an environment, the user relates to contexts via linear spatial intervals. The main contribution of this work is that the proposed model is sensitive to the velocity and direction of the user and applies Directed Interval Algebra (DIA) and the Dynamic Range Neighbour Query (DRNQ) to introduce spatially relevant contexts according to their arrangement in space. The Spatial Relevancy Algorithm for Context-aware Systems (SRACS) helps the tourist to find his/her preferred areas that are spatially relevant. The experimental results in a scenario of tourist navigation are evaluated with respect to the accuracy of the model, performance time and satisfaction of users in 25 iterations of the algorithm on 25 routes in Tehran. The evaluation process demonstrated the efficiency of the model in real-world applications.