Abstract

This paper proposes a new feature selection methodology. The methodology is based on the stepwise variable selection procedure, but, instead of using the traditional discriminant metrics such as Wilks' Lambda, it uses an estimation of the misclassification error as the figure of merit to evaluate the introduction of new features. The expected misclassification error rate (MER) is obtained by using the densities of a constructed function of random variables, which is the stochastic representation of the conditional distribution of the quadratic discriminant function estimate. The application of the proposed methodology results in significant savings of computational time in the estimation of classification error over the traditional simulation and cross-validation methods. One of the main advantages of the proposed method is that it provides a direct estimation of the expected misclassification error at the time of feature selection, which provides an immediate assessment of the benefits of introducing an additional feature into an inspection/classification algorithm.

Original languageEnglish (US)
Pages (from-to)1338-1344
Number of pages7
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume31
Issue number7
DOIs
StatePublished - 2009

Fingerprint

Misclassification Error
Feature Selection
Inspection
Feature extraction
Methodology
Stochastic Representation
Discriminant Function
Selection Procedures
Variable Selection
Classification Algorithm
Conditional Distribution
Quadratic Function
Discriminant
Cross-validation
Error Rate
Figure
Random variable
Random variables
Metric
Evaluate

Keywords

  • Feature selection
  • Misclassification error rate
  • Quadratic discriminant function

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Software
  • Computational Theory and Mathematics
  • Applied Mathematics

Cite this

@article{8d6d8814744d4a55b5a6f62dbe844ef7,
title = "A novel feature selection methodology for automated inspection systems",
abstract = "This paper proposes a new feature selection methodology. The methodology is based on the stepwise variable selection procedure, but, instead of using the traditional discriminant metrics such as Wilks' Lambda, it uses an estimation of the misclassification error as the figure of merit to evaluate the introduction of new features. The expected misclassification error rate (MER) is obtained by using the densities of a constructed function of random variables, which is the stochastic representation of the conditional distribution of the quadratic discriminant function estimate. The application of the proposed methodology results in significant savings of computational time in the estimation of classification error over the traditional simulation and cross-validation methods. One of the main advantages of the proposed method is that it provides a direct estimation of the expected misclassification error at the time of feature selection, which provides an immediate assessment of the benefits of introducing an additional feature into an inspection/classification algorithm.",
keywords = "Feature selection, Misclassification error rate, Quadratic discriminant function",
author = "Garcia, {Hugo C.} and Jesus Villalobos and Rong Pan and George Runger",
year = "2009",
doi = "10.1109/TPAMI.2008.276",
language = "English (US)",
volume = "31",
pages = "1338--1344",
journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",
issn = "0162-8828",
publisher = "IEEE Computer Society",
number = "7",

}

TY - JOUR

T1 - A novel feature selection methodology for automated inspection systems

AU - Garcia, Hugo C.

AU - Villalobos, Jesus

AU - Pan, Rong

AU - Runger, George

PY - 2009

Y1 - 2009

N2 - This paper proposes a new feature selection methodology. The methodology is based on the stepwise variable selection procedure, but, instead of using the traditional discriminant metrics such as Wilks' Lambda, it uses an estimation of the misclassification error as the figure of merit to evaluate the introduction of new features. The expected misclassification error rate (MER) is obtained by using the densities of a constructed function of random variables, which is the stochastic representation of the conditional distribution of the quadratic discriminant function estimate. The application of the proposed methodology results in significant savings of computational time in the estimation of classification error over the traditional simulation and cross-validation methods. One of the main advantages of the proposed method is that it provides a direct estimation of the expected misclassification error at the time of feature selection, which provides an immediate assessment of the benefits of introducing an additional feature into an inspection/classification algorithm.

AB - This paper proposes a new feature selection methodology. The methodology is based on the stepwise variable selection procedure, but, instead of using the traditional discriminant metrics such as Wilks' Lambda, it uses an estimation of the misclassification error as the figure of merit to evaluate the introduction of new features. The expected misclassification error rate (MER) is obtained by using the densities of a constructed function of random variables, which is the stochastic representation of the conditional distribution of the quadratic discriminant function estimate. The application of the proposed methodology results in significant savings of computational time in the estimation of classification error over the traditional simulation and cross-validation methods. One of the main advantages of the proposed method is that it provides a direct estimation of the expected misclassification error at the time of feature selection, which provides an immediate assessment of the benefits of introducing an additional feature into an inspection/classification algorithm.

KW - Feature selection

KW - Misclassification error rate

KW - Quadratic discriminant function

UR - http://www.scopus.com/inward/record.url?scp=67349255973&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67349255973&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2008.276

DO - 10.1109/TPAMI.2008.276

M3 - Article

C2 - 19443930

AN - SCOPUS:67349255973

VL - 31

SP - 1338

EP - 1344

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

SN - 0162-8828

IS - 7

ER -