ARGUS: Rete + DBMS = Efficient Persistent Profile Matching on Large-Volume Data Streams

by: Chun Jin, Jaime Carbonell, Phil Hayes

Foundations of Intelligent Systems (2005), pp. 142-151.

View FullText article

Springer (DOI)

Reviews [Write a review of this article]

There are no reviews of this article

Find related articles from these CiteULike users

mircea

Find related articles with these CiteULike tags

databases, rete

Abstract

Efficient processing of complex streaming data presents multiple challenges, especially when combined with intelligent detection of hidden anomalies in real time. We label such systems Stream Anomaly Monitoring Systems (SAMS), and describe the CMU/Dynamix ARGUS system as a new kind of SAMS to detect rare but high value patterns combining streaming and historical data. Such patterns may correspond to hidden precursors of terrorist activity, or early indicators of the onset of a dangerous disease, such as a SARS outbreak. Our method starts from an extension of the RETE algorithm for matching streaming data against multiple complex persistent queries, and proceeds beyond to transitivity inferences, conditional intermediate result materialization, and other such techniques to obtain both accuracy and efficiency, as demonstrated by the evaluation results outperforming classical techniques such as a modern DMBS.

@incollection{citeulike:2842347, abstract = {Efficient processing of complex streaming data presents multiple challenges, especially when combined with intelligent detection of hidden anomalies in real time. We label such systems Stream Anomaly Monitoring Systems (SAMS), and describe the CMU/Dynamix ARGUS system as a new kind of SAMS to detect rare but high value patterns combining streaming and historical data. Such patterns may correspond to hidden precursors of terrorist activity, or early indicators of the onset of a dangerous disease, such as a SARS outbreak. Our method starts from an extension of the RETE algorithm for matching streaming data against multiple complex persistent queries, and proceeds beyond to transitivity inferences, conditional intermediate result materialization, and other such techniques to obtain both accuracy and efficiency, as demonstrated by the evaluation results outperforming classical techniques such as a modern DMBS.}, author = {Jin, Chun and Carbonell, Jaime and Hayes, Phil }, citeulike-article-id = {2842347}, doi = {10.1007/11425274\_15}, journal = {Foundations of Intelligent Systems}, keywords = {databases, rete}, pages = {142--151}, posted-at = {2008-05-28 18:58:56}, priority = {2}, title = {ARGUS: Rete + DBMS = Efficient Persistent Profile Matching on Large-Volume Data Streams}, url = {http://dx.doi.org/10.1007/11425274\_15}, year = {2005} }

RIS record

TY - CHAP ID - citeulike:2842347 L3 - citeulike-article-id:2842347 TI - ARGUS: Rete + DBMS = Efficient Persistent Profile Matching on Large-Volume Data Streams JF - Foundations of Intelligent Systems SP - 142 EP - 151 N2 - Efficient processing of complex streaming data presents multiple challenges, especially when combined with intelligent detection of hidden anomalies in real time. We label such systems Stream Anomaly Monitoring Systems (SAMS), and describe the CMU/Dynamix ARGUS system as a new kind of SAMS to detect rare but high value patterns combining streaming and historical data. Such patterns may correspond to hidden precursors of terrorist activity, or early indicators of the onset of a dangerous disease, such as a SARS outbreak. Our method starts from an extension of the RETE algorithm for matching streaming data against multiple complex persistent queries, and proceeds beyond to transitivity inferences, conditional intermediate result materialization, and other such techniques to obtain both accuracy and efficiency, as demonstrated by the evaluation results outperforming classical techniques such as a modern DMBS. KW - databases KW - rete AU - Jin, Chun AU - Carbonell, Jaime AU - Hayes, Phil PY - 2005/// UR - http://dx.doi.org/10.1007/11425274_15 ER -

RIS BibTeX