Anomaly detection in complex systems

Amit Surana, Asok Ray, Shin Chin

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations

Abstract

This paper presents a novel concept of anomaly detection in complex systems using tools of Symbolic Dynamics and Pattern Discovery. Anomaly is defined as a deviation from the nominal behaviour and can be associated with parametric changes that may gradually evolve. The proposed methodology is based on two-time-scale analysis of observed asymptotic behaviour of the dynamical system. This concept of small change detection in dynamical systems is elucidated through an example of the forced Duffing equation with a slowly varying dissipation parameter.

Original languageEnglish (US)
Pages (from-to)1119-1124
Number of pages6
JournalIFAC Proceedings Volumes (IFAC-PapersOnline)
Volume36
Issue number5
DOIs
StatePublished - 2003
Event5th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, Safeprocess 2003 - Washington, United States
Duration: Jun 9 1997Jun 11 1997

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Anomaly detection in complex systems'. Together they form a unique fingerprint.

Cite this