Abstract | ||
---|---|---|
We consider the problem of anomaly detection in multiple co-evolving data streams. In this paper, we introduce FRAHST (Fast Rank-Adaptive row-Householder Subspace Tracking). It automatically learns the principal subspace from N numerical data streams and an anomaly is indicated by a change in the number of latent variables. Our technique provides state-of-the-art estimates for the subspace basis and has a true dominant complexity of only 5Nr operations while satisfying all desirable streaming constraints. FRAHST successfully detects subtle anomalous patterns and when compared against four other anomaly detection techniques, it is the only with a consistent F1 ≥ 80% in the Abilene datasets as well as in the ISP datasets introduced in this work. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1774088.1774434 | SAC |
Keywords | Field | DocType |
consistent f1,anomaly detection,anomaly detection technique,multiple co-evolving data stream,principal subspace tracking,data stream anomaly detection,principal subspace,detects subtle anomalous pattern,latent variable,fast rank-adaptive row-householder subspace,subspace basis,n numerical data stream,data streams,unsupervised learning,satisfiability,time series,dimensionality reduction | Anomaly detection,Data mining,Data stream mining,Dimensionality reduction,Subspace topology,Pattern recognition,Computer science,Data stream,Latent variable,Unsupervised learning,Artificial intelligence | Conference |
Citations | PageRank | References |
19 | 0.91 | 18 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pedro Henriques dos Santos Teixeira | 1 | 26 | 1.57 |
Ruy Luiz Milidiú | 2 | 192 | 20.18 |