Method for detecting anomalies in a time series data with trajectory and stochastic components
作者： Michael J Jones
DOI:
关键词:
摘要: A method detects anomalies in time series data by comparing universal features extracted from testing with the acquired training to determine a score. The characterize trajectory components of and stochastic data. Then, an anomaly is detected if score above threshold.
lens.org 参考文章(12)
Thorsten Edelhaeusser, Michael Philippsen, Gabriella Kókai, Hans Holm Fruehauf, Concept for encoding data defining coded positions representing a trajectory of an object ,(2011)
Guy Jacobson, Greg B. Kinne, Arnold Lent, Colin Goodall, Method and apparatus for multi-domain anomaly pattern definition and detection ,(2007)
Hisae Shibuya, Shunji Maeda, Anomaly detection method and anomaly detection system ,(2010)
Steven Hartman, Eric Gebhardt, Xiaomo Jiang, Michael Bernard, Fault Prediction of Monitored Assets ,(2012)
Stephan W. Wegerich, Robert Matthew Pipke, Andre Wolosewicz, Diagnostic systems and methods for predictive condition monitoring ,(2002)
Salvatore J Stolfo, Janak Parekh, Ke Wang, Systems, Methods, and Media for Outputting a Dataset Based Upon Anomaly Detection ,(2007)
Meir Kalech, Gal Kaminka, Eliahu Khalastchi, Raz Lin, Anomaly detection methods, devices and systems ,(2012)
John C. Handley, Sankar Virdhagriswaran, Method and system for retrieving time series data ,(2007)
Vijaykumar Chhaganlal Patel, Ziad Hasan Abu-El-Zeet, Method of condition monitoring ,(2006)
Daniel Nikolaev Nikovski, Michael Jeffrey Jones, Method for detecting anomalies in multivariate time series data ,(2012)