Effects of different classifiers in detecting infectious regions in chest radiographs

W. S H M W Ahmad, R. Logeswaran, M. F A Fauzi, Wan Mimi Diyana Wan Zaki

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

1 Citation (Scopus)

Abstract

This paper presents the effects of different types of classifiers when analysing the normal and infectious regions in chest radiographs. Three types of classifiers are experimented on: Rule-based, Bayesian and k-nearest neighbour's. The evaluation is based on a few criteria, namely, the classification accuracy, misclassification (error), speed, Kappa statistic, ROC area, and other performance measures specifically the true and false positive rates, and precision and recall. The dataset consists of image features from a total of 102 chest radiographs. The normal and infectious lung regions are extracted and divided into non-overlapping sub-blocks prior to the image feature computation. The quantitative results are presented and discussed for consideration in further analysis of infectious lungs.

Original languageEnglish
Title of host publicationIEEM 2014 - 2014 IEEE International Conference on Industrial Engineering and Engineering Management
PublisherIEEE Computer Society
Pages541-545
Number of pages5
Volume2015-January
ISBN (Electronic)9781479964109
DOIs
Publication statusPublished - 2014
Event2014 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2014 - Selangor, Malaysia
Duration: 9 Dec 201412 Dec 2014

Other

Other2014 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2014
CountryMalaysia
CitySelangor
Period9/12/1412/12/14

Fingerprint

Classifiers
Statistics
Lung
Classifier
K-nearest neighbor
Performance measures
Misclassification error
Rule-based
Evaluation

Keywords

  • Bayes Network
  • chest radiograph
  • Classification
  • IR
  • k-NN
  • lung infection
  • Naive Bayes

ASJC Scopus subject areas

  • Business, Management and Accounting (miscellaneous)
  • Industrial and Manufacturing Engineering
  • Safety, Risk, Reliability and Quality

Cite this

Ahmad, W. S. H. M. W., Logeswaran, R., Fauzi, M. F. A., & Wan Zaki, W. M. D. (2014). Effects of different classifiers in detecting infectious regions in chest radiographs. In IEEM 2014 - 2014 IEEE International Conference on Industrial Engineering and Engineering Management (Vol. 2015-January, pp. 541-545). [7058696] IEEE Computer Society. https://doi.org/10.1109/IEEM.2014.7058696

Effects of different classifiers in detecting infectious regions in chest radiographs. / Ahmad, W. S H M W; Logeswaran, R.; Fauzi, M. F A; Wan Zaki, Wan Mimi Diyana.

IEEM 2014 - 2014 IEEE International Conference on Industrial Engineering and Engineering Management. Vol. 2015-January IEEE Computer Society, 2014. p. 541-545 7058696.

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

Ahmad, WSHMW, Logeswaran, R, Fauzi, MFA & Wan Zaki, WMD 2014, Effects of different classifiers in detecting infectious regions in chest radiographs. in IEEM 2014 - 2014 IEEE International Conference on Industrial Engineering and Engineering Management. vol. 2015-January, 7058696, IEEE Computer Society, pp. 541-545, 2014 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2014, Selangor, Malaysia, 9/12/14. https://doi.org/10.1109/IEEM.2014.7058696
Ahmad WSHMW, Logeswaran R, Fauzi MFA, Wan Zaki WMD. Effects of different classifiers in detecting infectious regions in chest radiographs. In IEEM 2014 - 2014 IEEE International Conference on Industrial Engineering and Engineering Management. Vol. 2015-January. IEEE Computer Society. 2014. p. 541-545. 7058696 https://doi.org/10.1109/IEEM.2014.7058696
Ahmad, W. S H M W ; Logeswaran, R. ; Fauzi, M. F A ; Wan Zaki, Wan Mimi Diyana. / Effects of different classifiers in detecting infectious regions in chest radiographs. IEEM 2014 - 2014 IEEE International Conference on Industrial Engineering and Engineering Management. Vol. 2015-January IEEE Computer Society, 2014. pp. 541-545
@inproceedings{54c2ab77d8ac43cfaf6e927f3621078e,
title = "Effects of different classifiers in detecting infectious regions in chest radiographs",
abstract = "This paper presents the effects of different types of classifiers when analysing the normal and infectious regions in chest radiographs. Three types of classifiers are experimented on: Rule-based, Bayesian and k-nearest neighbour's. The evaluation is based on a few criteria, namely, the classification accuracy, misclassification (error), speed, Kappa statistic, ROC area, and other performance measures specifically the true and false positive rates, and precision and recall. The dataset consists of image features from a total of 102 chest radiographs. The normal and infectious lung regions are extracted and divided into non-overlapping sub-blocks prior to the image feature computation. The quantitative results are presented and discussed for consideration in further analysis of infectious lungs.",
keywords = "Bayes Network, chest radiograph, Classification, IR, k-NN, lung infection, Naive Bayes",
author = "Ahmad, {W. S H M W} and R. Logeswaran and Fauzi, {M. F A} and {Wan Zaki}, {Wan Mimi Diyana}",
year = "2014",
doi = "10.1109/IEEM.2014.7058696",
language = "English",
volume = "2015-January",
pages = "541--545",
booktitle = "IEEM 2014 - 2014 IEEE International Conference on Industrial Engineering and Engineering Management",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Effects of different classifiers in detecting infectious regions in chest radiographs

AU - Ahmad, W. S H M W

AU - Logeswaran, R.

AU - Fauzi, M. F A

AU - Wan Zaki, Wan Mimi Diyana

PY - 2014

Y1 - 2014

N2 - This paper presents the effects of different types of classifiers when analysing the normal and infectious regions in chest radiographs. Three types of classifiers are experimented on: Rule-based, Bayesian and k-nearest neighbour's. The evaluation is based on a few criteria, namely, the classification accuracy, misclassification (error), speed, Kappa statistic, ROC area, and other performance measures specifically the true and false positive rates, and precision and recall. The dataset consists of image features from a total of 102 chest radiographs. The normal and infectious lung regions are extracted and divided into non-overlapping sub-blocks prior to the image feature computation. The quantitative results are presented and discussed for consideration in further analysis of infectious lungs.

AB - This paper presents the effects of different types of classifiers when analysing the normal and infectious regions in chest radiographs. Three types of classifiers are experimented on: Rule-based, Bayesian and k-nearest neighbour's. The evaluation is based on a few criteria, namely, the classification accuracy, misclassification (error), speed, Kappa statistic, ROC area, and other performance measures specifically the true and false positive rates, and precision and recall. The dataset consists of image features from a total of 102 chest radiographs. The normal and infectious lung regions are extracted and divided into non-overlapping sub-blocks prior to the image feature computation. The quantitative results are presented and discussed for consideration in further analysis of infectious lungs.

KW - Bayes Network

KW - chest radiograph

KW - Classification

KW - IR

KW - k-NN

KW - lung infection

KW - Naive Bayes

UR - http://www.scopus.com/inward/record.url?scp=84988274748&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988274748&partnerID=8YFLogxK

U2 - 10.1109/IEEM.2014.7058696

DO - 10.1109/IEEM.2014.7058696

M3 - Conference contribution

AN - SCOPUS:84988274748

VL - 2015-January

SP - 541

EP - 545

BT - IEEM 2014 - 2014 IEEE International Conference on Industrial Engineering and Engineering Management

PB - IEEE Computer Society

ER -