Anomaly detection in heterogeneous media via saliency analysis of propagating wavefields

Jeffrey M. Druce, Jarvis D Haupt, Stefano Gonella

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

This work investigates the problem of anomaly detection by means of an agnostic inference strategy based on the concepts of spatial saliency and data sparsity. Specifically, it addresses the implementation and experimental validation aspects of a salient feature extraction methodology that was recently proposed for laser-based diag- nostics and leverages the wavefield spatial reconstruction capability offered by scanning laser vibrometers. The methodology consists of two steps. The first is a spatiotemporal windowing strategy designed to partition the structural domain in small sub-domains and replicate impinging wave conditions at each location. The second is the construction of a low-rank-plus-outlier model of the regional data set using principal component analysis. Regions are labeled salient when their behavior does not belong to a common low-dimensional subspace that successfully describes the typical behavior of the anomaly-free portion of the surrounding medium. The most at- tractive feature of this method is that it requires virtually no knowledge of the structural and material properties of the medium. This property makes it a powerful diagnostic tool for the inspection of media with pronounced heterogeneity or with unknown or unreliable material property distributions, e.g., as a result of severe material degradation over large portions of their domain.

Original languageEnglish (US)
Title of host publicationHealth Monitoring of Structural and Biological Systems 2014
PublisherSPIE
ISBN (Print)9780819499905
DOIs
StatePublished - Jan 1 2014
EventHealth Monitoring of Structural and Biological Systems 2014 - San Diego, CA, United States
Duration: Mar 10 2014Mar 13 2014

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume9064
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

OtherHealth Monitoring of Structural and Biological Systems 2014
CountryUnited States
CitySan Diego, CA
Period3/10/143/13/14

Keywords

  • Anomaly detection
  • Laser vibrometer
  • Low-rank-plus-outlier models
  • Machine learning
  • Non-destructive evaluation
  • Saliency
  • Sparsity

Fingerprint Dive into the research topics of 'Anomaly detection in heterogeneous media via saliency analysis of propagating wavefields'. Together they form a unique fingerprint.

Cite this