Generalized Model for Linear Referencing in Transportation
Geoinformatica
Mining GPS Traces for Map Refinement
Data Mining and Knowledge Discovery
Temporal moving pattern mining for location-based service
Journal of Systems and Software
ST-DBSCAN: An algorithm for clustering spatial-temporal data
Data & Knowledge Engineering
Location query based on moving behaviors
Information Systems
Traffic density-based discovery of hot routes in road networks
SSTD'07 Proceedings of the 10th international conference on Advances in spatial and temporal databases
TrajPattern: mining sequential patterns from imprecise trajectories of mobile objects
EDBT'06 Proceedings of the 10th international conference on Advances in Database Technology
Spatio-temporal similarity analysis between trajectories on road networks
ER'05 Proceedings of the 24th international conference on Perspectives in Conceptual Modeling
| Hi-index | 0.00 |
Advances in wireless transmission and increasing quantity of GPS in vehicles flood us with massive amount of trajectory data. The large amounts of trajectories imply considerable quantity of interesting road condition that current traffic database lacks. Mining live traffic condition from trajectories is a challenge due to complexity of road network model, uncertainty of driving behavior as well as imprecision of trajectories. In this paper, road linear reference system, road segmentation and road condition models are employed in preprocessing trajectory data to lower dimension of trajectory mining problems and reduce uncertainties and imprecision of raw trajectories. The trajectory mining problem includes the one near road intersection and the one in general road segment. The former focuses on finding turn information of road intersection, while the latter focuses on extracting road live condition. The experimental results show that the mining algorithm is effective and efficient in traffic condition mining.