Iroad: A framework for scalable predictive query processing on road networks

Abdeltawab M. Hendawim, Jie Bao, Mohamed F. Mokbel

Research output: Contribution to journalConference articlepeer-review

14 Scopus citations


This demo presents the iRoad framework for evaluating predictive queries on moving objects for road networks. The main promise of the iRoad system is to support a variety of common predictive queries including predictive point query, predictive range query, predictive KNN query, and predictive aggregate query. The iRoad framework is equipped with a novel data structure, named reachability tree, employed to determine the reachable nodes for a moving object within a specified future time T. In fact, the reachability tree prunes the space around each object in order to significantly reduce the computation time. So, iRoad is able to scale up to handle real road networks with millions of nodes, and it can process heavy workloads on large numbers of moving objects. During the demo, audience will be able to interact with iRoad through a well designed Graphical User Interface to issue different types of predictive queries on a real road network, to obtain the predictive heatmap of the area of interest, to follow the creation and the dynamic update of the reachability tree around a specific moving object, and finally to examine the system efficiency and scalability.

Original languageEnglish (US)
Pages (from-to)1262-1265
Number of pages4
JournalProceedings of the VLDB Endowment
Issue number12
StatePublished - Aug 2013
Event39th International Conference on Very Large Data Bases, VLDB 2012 - Trento, Italy
Duration: Aug 26 2013Aug 30 2013


Dive into the research topics of 'Iroad: A framework for scalable predictive query processing on road networks'. Together they form a unique fingerprint.

Cite this