Linear clustering of objects with multiple attributes
SIGMOD '90 Proceedings of the 1990 ACM SIGMOD international conference on Management of data
Proceedings of the 17th International Conference on Data Engineering
Probabilistic skylines on uncertain data
VLDB '07 Proceedings of the 33rd international conference on Very large data bases
Efficient Evaluation of Probabilistic Advanced Spatial Queries on Existentially Uncertain Data
IEEE Transactions on Knowledge and Data Engineering
Distributed Skyline Retrieval with Low Bandwidth Consumption
IEEE Transactions on Knowledge and Data Engineering
A Survey of Uncertain Data Algorithms and Applications
IEEE Transactions on Knowledge and Data Engineering
Parallel Distributed Processing of Constrained Skyline Queries by Filtering
ICDE '08 Proceedings of the 2008 IEEE 24th International Conference on Data Engineering
Probabilistic Skyline Operator over Sliding Windows
ICDE '09 Proceedings of the 2009 IEEE International Conference on Data Engineering
Efficient and Progressive Algorithms for Distributed Skyline Queries over Uncertain Data
ICDCS '10 Proceedings of the 2010 IEEE 30th International Conference on Distributed Computing Systems
Parallelizing skyline queries for scalable distribution
EDBT'06 Proceedings of the 10th international conference on Advances in Database Technology
Hi-index | 0.01 |
The skyline queries help users make intelligent decisions over complex data. It has been recently extended to the uncertain databases due to the existence of uncertainty in many real-world data. In this paper, we tackle the problem of probabilistic skyline retrieval on physically distributed uncertain data with low bandwidth consumption. The previous work incurs sharply increased communication cost when the underlying dataset is anti-correlated, which is the typical scenario that the skyline is useful. In this paper, we propose a knowledge sharing approach based on a novel grid-based data summary. By sharing the data summary that captures the global data distribution, each local site is able to identify large amounts of unqualified objects early. Extensive experiments on both efficiency and scalability have demonstrated that our approach outperforms the competitor.