Density-Based Clustering in Spatial Databases: The Algorithm GDBSCAN and Its Applications
Data Mining and Knowledge Discovery
Artificial Intelligence: A Modern Approach
Artificial Intelligence: A Modern Approach
A model for enriching trajectories with semantic geographical information
Proceedings of the 15th annual ACM international symposium on Advances in geographic information systems
Drools JBoss Rules 5.0 Developer's Guide
Drools JBoss Rules 5.0 Developer's Guide
Predestination: inferring destinations from partial trajectories
UbiComp'06 Proceedings of the 8th international conference on Ubiquitous Computing
Hi-index | 0.00 |
GPS technology enables collection of moving object's positions remotely. Recent research on moving objects concerns analysis of their movement to increase the knowledge about their movement patterns. Discovery of biogeographically significant locations such as a den, rendezvous sites or kill-sites is very important in order to gain insight into animals' behaviour, habitat selection and predator-prey interactions. Animals interact with their environment in a complex way; their movement is conditioned with underlying geographical space and semantics. Existing computerized methods for discovery of significant locations take only raw positions and time stamp into account, without necessary animal characteristics and pertaining geographical space. We propose an expert system to discover significant locations which enables inclusion of knowledge about both intrinsic and extrinsic properties of animals. Our expert rules are adaptable to different application domains, based on characteristics of animal and algorithm parameters. The results of this study will be useful to community members engaged in studies of wildlife, but we believe that out method could be applied not only to different kinds of animals but also to other classes of moving objects.