Consistently Handling Geographical User Data

A novel soft computing technique for the automatic detection of coreferent locations of POIs is presented and co-location is determined by explicitly considering the scale at which the POI is entered by the user.

Abstract

In the context of digital earth applications, points of interest (POIs) denote geographical locations which might be of interest for some user purposes. Examples are nice views, historical buildings, good restaurants, recreation areas, etc. In some applications, POIs are provided and inserted by the user community. A problem hereby is that users can make mistakes due to which the same POI is, e.g., entered multiple times with a different location and/or description. Such POIs are coreferent as they refer to the same geographical object and must be avoided because they can introduce uncertainty in the map. In this paper, a novel soft computing technique for the automatic detection of coreferent locations of POIs is presented. Co-location is determined by explicitly considering the scale at which the POI is entered by the user. Fuzzy set and possibility theory are used to cope with the uncertainties in the data. An illustrative example is provided.