Classification of damage through Isomap-based dimensional scaling technique

B. H. Koh, M. Jeong

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

While PCA has been widely used to separate damage-sensitive features from unsupervised conditions of measurement noise or environmental uncertainties, Isomap was recently proven to be a powerful nonlinear data classification technique. This study compares the performances of the PCA and the Isomap algorithm in classifying damage locations in terms of modal frequency changes. It is demonstrated that the Isomap algorithm successfully enhances the quality of patterns and classifications related to damage locations through various simulation examples.

Original languageEnglish
Title of host publicationProceedings of the 6th European Workshop - Structural Health Monitoring 2012, EWSHM 2012
Pages1656-1660
Number of pages5
StatePublished - 2012
Event6th European Workshop on Structural Health Monitoring 2012, EWSHM 2012 - Dresden, Germany
Duration: 3 Jul 20126 Jul 2012

Publication series

NameProceedings of the 6th European Workshop - Structural Health Monitoring 2012, EWSHM 2012
Volume2

Conference

Conference6th European Workshop on Structural Health Monitoring 2012, EWSHM 2012
Country/TerritoryGermany
CityDresden
Period3/07/126/07/12

Fingerprint

Dive into the research topics of 'Classification of damage through Isomap-based dimensional scaling technique'. Together they form a unique fingerprint.

Cite this