Show simple item record

dc.contributor.advisorChan, Philip K.
dc.contributor.authorMahoney, Matthew V.
dc.contributor.authorChan, Philip K.
dc.date.accessioned2013-11-13T15:56:46Z
dc.date.available2013-11-13T15:56:46Z
dc.date.issued2005-03-23
dc.identifier.citationMahoney, M.V., Chan, P.K. (2005). Trajectory boundary modeling of time series for anomaly detection (CS-2005-08). Melbourne, FL. Florida Institute of Technology.en_US
dc.identifier.otherCS-2005-08
dc.identifier.urihttp://hdl.handle.net/11141/163
dc.description.abstractWe address the problem of online detection of unanticipated modes of mechanical failure given a small set of time series under normal conditions, with the requirement that the anomaly detection model be manually verifiable and modifiable. We specify a set of time series features, which are linear combinations of the current and past values, and model the allowed feature values by a sequence of minimal bounding boxes containing all of the training trajectories. The model can be constructed in O(n log n) time. If there are at most three features, the model can be displayed graphically for verification, otherwise a table is used. Test time is O(n) with a guaranteed upper bound on computation time for each test point. The model compares favorably with anomaly detection algorithms based on Euclidean distance and dynamic time warping on the Space Shuttle Marrotta fuel control valve data set.en_US
dc.language.isoen_USen_US
dc.rightsCopyright held by authors.en_US
dc.titleTrajectory boundary modeling of time series for anomaly detectionen_US
dc.typeTechnical Reporten_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record