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 Citation (Scopus)

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
Volume2
DOIs
StatePublished - 2008
EventASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008 - Ellicott City, MD, United States
Duration: Oct 28 2008Oct 30 2008

Other

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

Fingerprint

Binary trees
Support vector machines
Classifiers
Discriminant analysis
Data reduction
Fatigue of materials
Sensors

ASJC Scopus subject areas

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

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 (Vol. 2, pp. 289-296) https://doi.org/10.1115/SMASIS2008-640

Feature reduction for computationally efficient damage state classification using binary tree support vector machines. / Coelho, Clyde; Chattopadhyay, Aditi.

Proceedings of the ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008. Vol. 2 2008. p. 289-296.

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

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. vol. 2, pp. 289-296, ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008, Ellicott City, MD, United States, 10/28/08. https://doi.org/10.1115/SMASIS2008-640
Coelho C, Chattopadhyay A. 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. Vol. 2. 2008. p. 289-296 https://doi.org/10.1115/SMASIS2008-640
Coelho, Clyde ; Chattopadhyay, Aditi. / Feature reduction for computationally efficient damage state classification using binary tree support vector machines. Proceedings of the ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008. Vol. 2 2008. pp. 289-296
@inproceedings{7d98742d3365404783183fa0112870b8,
title = "Feature reduction for computationally efficient damage state classification using binary tree support vector machines",
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.",
author = "Clyde Coelho and Aditi Chattopadhyay",
year = "2008",
doi = "10.1115/SMASIS2008-640",
language = "English (US)",
isbn = "9780791843314",
volume = "2",
pages = "289--296",
booktitle = "Proceedings of the ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008",

}

TY - GEN

T1 - Feature reduction for computationally efficient damage state classification using binary tree support vector machines

AU - Coelho, Clyde

AU - Chattopadhyay, Aditi

PY - 2008

Y1 - 2008

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=78149389414&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149389414&partnerID=8YFLogxK

U2 - 10.1115/SMASIS2008-640

DO - 10.1115/SMASIS2008-640

M3 - Conference contribution

AN - SCOPUS:78149389414

SN - 9780791843314

SN - 9780791843321

VL - 2

SP - 289

EP - 296

BT - Proceedings of the ASME Conference on Smart Materials, Adaptive Structures and Intelligent Systems, SMASIS2008

ER -