Feature reduction for computationally efficient damage state classification using binary tree support vector machines

Clyde Coelho, Aditi Chattopadhyay

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

1 Scopus citations

Abstract

This paper proposes a computationally efficient methodology for classifying damage in structural hotspots. Data collected from a sensor instrumented lug joint subjected to fatigue loading was preprocessed using a linear discriminant analysis (LDA) to extract features that are relevant for classification and reduce the dimensionality of the data. The data is then reduced in the feature space by analyzing the structure of the mapped clusters and removing the data points that do not affect the construction of interclass separating hyperplanes. The reduced data set is used to train a support vector machines (SVM) based classifier and the results of the classification problem are compared to those when the entire data set is used for training. To further improve the efficiency of the classification scheme, the SVM classifiers are arranged in a binary tree format to reduce the number of comparisons that are necessary. The experimental results show that the data reduction does not reduce the ability of the classifier to distinguish between classes while providing a nearly fourfold decrease in the amount of training data processed.

Original languageEnglish (US)
Title of host publicationProceedings of the ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008
Pages289-296
Number of pages8
DOIs
StatePublished - Dec 1 2008
EventASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008 - Ellicott City, MD, United States
Duration: Oct 28 2008Oct 30 2008

Publication series

NameProceedings of the ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008
Volume2

Other

OtherASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008
CountryUnited States
CityEllicott City, MD
Period10/28/0810/30/08

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Control and Systems Engineering
  • Mechanics of Materials
  • Building and Construction

Fingerprint Dive into the research topics of 'Feature reduction for computationally efficient damage state classification using binary tree support vector machines'. Together they form a unique fingerprint.

  • Cite this

    Coelho, C., & Chattopadhyay, A. (2008). Feature reduction for computationally efficient damage state classification using binary tree support vector machines. In Proceedings of the ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008 (pp. 289-296). (Proceedings of the ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008; Vol. 2). https://doi.org/10.1115/SMASIS2008-640