Spatial tessellations: concepts and applications of Voronoi diagrams
Spatial tessellations: concepts and applications of Voronoi diagrams
Triangle: Engineering a 2D Quality Mesh Generator and Delaunay Triangulator
FCRC '96/WACG '96 Selected papers from the Workshop on Applied Computational Geormetry, Towards Geometric Engineering
Spatial Data Mining: A Database Approach
SSD '97 Proceedings of the 5th International Symposium on Advances in Spatial Databases
Neighborhood based detection of anomalies in high dimensional spatio-temporal sensor datasets
Proceedings of the 2004 ACM symposium on Applied computing
DM-AMS: employing data mining techniques for alert management
dg.o '05 Proceedings of the 2005 national conference on Digital government research
Agency interoperation for effective data mining in border control and homeland security applications
dg.o '04 Proceedings of the 2004 annual national conference on Digital government research
Modeling and Simulating Terrorist Networks in Social and Geospatial Dimensions
IEEE Intelligent Systems
| Hi-index | 0.00 |
There are numerous applications that require one to identify anomalous geospatial trajectories in the domain of homeland security. Examples include: (i) a customs agent may want to discover anomalies among cargo routes to identify potentially dangerous shipments even before they cross the border, (ii) an FDA inspector may want to trace anomalous paths in the food supply chain to identify potential agro terrorism threats, etc. To accomplish this, in this paper, we propose an approach that relies on spatial characterization and spatio-semantic path associations. In particular, we consider atomic geospatial units and generate micro neighborhoods around them. We will then form similarly behaving regions, called macro neighborhoods, through selectively merging these micro neighborhoods by considering the spatial and semantic relationships among them. We will then identify associations among the geospatial trajectories and all the macro neighborhoods. Any strong association between a macro neighborhood and a part of the trajectory that does not reside in the macro neighborhood indicates a potential anomaly.