A probabilistic relational algebra for the integration of information retrieval and database systems
ACM Transactions on Information Systems (TOIS)
Matching events in a content-based subscription system
Proceedings of the eighteenth annual ACM symposium on Principles of distributed computing
Activity monitoring: noticing interesting changes in behavior
KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Filtering algorithms and implementation for very fast publish/subscribe systems
SIGMOD '01 Proceedings of the 2001 ACM SIGMOD international conference on Management of data
Efficient filtering in publish-subscribe systems using binary decision diagrams
ICSE '01 Proceedings of the 23rd International Conference on Software Engineering
Introduction to Automata Theory, Languages and Computability
Introduction to Automata Theory, Languages and Computability
WebFilter: A High-throughput XML-based Publish and Subscribe System
Proceedings of the 27th International Conference on Very Large Data Bases
Predicate Matching and Subscription Matching in Publish/Subscribe Systems
ICDCSW '02 Proceedings of the 22nd International Conference on Distributed Computing Systems
Modeling Uncertainties in Publish/Subscribe Systems
ICDE '04 Proceedings of the 20th International Conference on Data Engineering
ICDCS '05 Proceedings of the 25th IEEE International Conference on Distributed Computing Systems
Efficient query evaluation on probabilistic databases
The VLDB Journal — The International Journal on Very Large Data Bases
A-TOPSS: a publish/subscribe system supporting approximate matching
VLDB '02 Proceedings of the 28th international conference on Very Large Data Bases
Orion 2.0: native support for uncertain data
Proceedings of the 2008 ACM SIGMOD international conference on Management of data
Complex event processing over uncertain data
Proceedings of the second international conference on Distributed event-based systems
Adaptive content-based routing in general overlay topologies
Proceedings of the 9th ACM/IFIP/USENIX International Conference on Middleware
Probabilistic Event Extraction from RFID Data
ICDE '08 Proceedings of the 2008 IEEE 24th International Conference on Data Engineering
Fast and Simple Relational Processing of Uncertain Data
ICDE '08 Proceedings of the 2008 IEEE 24th International Conference on Data Engineering
Proceedings of the Fifth Balkan Conference in Informatics
Hi-index | 0.00 |
A new publish/subscribe capability is presented: the ability to predict the likelihood that a subscription will be matched at some point in the future. Knowing that some phenomenon of interest is about to take place, applications can take proactive steps to prevent the situation from occurring altogether, or speculatively begin reacting to the event even before it has transpired. A publish/subscribe matching algorithm is developed in which composite subscriptions consisting of temporal and logical operators are efficiently represented by a set of finite state machines and rules. The algorithm trains a Markov model to an application's event workload, and predicts the probability that a given subscription will match within a window in the future event stream. Evaluations demonstrate that the memory and processing costs of the algorithm scale well with the number of subscriptions, and the prediction precision is high, especially when the workload characteristics do not change rapidly. Furthermore, a comparison with a hand-crafted Markov model using real data traces shows that the algorithm consumes much less memory and processing power, yet still delivers prediction precision that approaches that of the hand-crafted model. This is especially impressive since the algorithms lack any of the domain expertise embedded in the hand-crafted model.