Optimized Class Decomposition for Fault Detection

Saso Karakatic; Dusan Fister; Omer Faruk Beyca; Iztok Fister

doi:10.1109/CINTI53070.2021.9668488

Optimized Class Decomposition for Fault Detection

Saso Karakatic^*, Dusan Fister, Omer Faruk Beyca, Iztok Fister

^*Corresponding author for this work

Department of Industrial Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The paper proposes an innovative approach in solving the fault detection problem of sewerage treatment plant machinery. The proposed approach treats the fault detection data with the class decomposition problem, ensuring that a classification algorithm overlooks no disjunct instances. As the class decomposition technique requires heavy customization to each class of instances in every data set, Grey Wolf Optimizer is used to determine the appropriate clustering method with the appropriate setting for each class of instances. The proposed approach is tested on real-life sensor data from a sewerage treatment plant, and the results show that here proposed approach overshadows several manually proposed class decomposition methods.

Original language	English
Title of host publication	21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	15-20
Number of pages	6
ISBN (Electronic)	9781665426848
DOIs	https://doi.org/10.1109/CINTI53070.2021.9668488
Publication status	Published - 2021
Event	21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Budapest, Hungary Duration: 18 Nov 2021 → 20 Nov 2021

Publication series

Name	21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings

Conference

Conference	21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021
Country/Territory	Hungary
City	Budapest
Period	18/11/21 → 20/11/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

Class Decomposition
Clustering
Fault Detection
Grey Wolf Optimizer

Access to Document

10.1109/CINTI53070.2021.9668488

Cite this

Karakatic, S., Fister, D., Beyca, O. F., & Fister, I. (2021). Optimized Class Decomposition for Fault Detection. In 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings (pp. 15-20). (21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CINTI53070.2021.9668488

Karakatic, Saso ; Fister, Dusan ; Beyca, Omer Faruk et al. / Optimized Class Decomposition for Fault Detection. 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 15-20 (21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings).

@inproceedings{960de565763b4b7885388ebfa3f30210,

title = "Optimized Class Decomposition for Fault Detection",

abstract = "The paper proposes an innovative approach in solving the fault detection problem of sewerage treatment plant machinery. The proposed approach treats the fault detection data with the class decomposition problem, ensuring that a classification algorithm overlooks no disjunct instances. As the class decomposition technique requires heavy customization to each class of instances in every data set, Grey Wolf Optimizer is used to determine the appropriate clustering method with the appropriate setting for each class of instances. The proposed approach is tested on real-life sensor data from a sewerage treatment plant, and the results show that here proposed approach overshadows several manually proposed class decomposition methods.",

keywords = "Class Decomposition, Clustering, Fault Detection, Grey Wolf Optimizer",

author = "Saso Karakatic and Dusan Fister and Beyca, {Omer Faruk} and Iztok Fister",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 ; Conference date: 18-11-2021 Through 20-11-2021",

year = "2021",

doi = "10.1109/CINTI53070.2021.9668488",

language = "English",

series = "21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "15--20",

booktitle = "21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings",

address = "United States",

}

Karakatic, S, Fister, D, Beyca, OF & Fister, I 2021, Optimized Class Decomposition for Fault Detection. in 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings. 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 15-20, 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021, Budapest, Hungary, 18/11/21. https://doi.org/10.1109/CINTI53070.2021.9668488

Optimized Class Decomposition for Fault Detection. / Karakatic, Saso; Fister, Dusan; Beyca, Omer Faruk et al.
21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 15-20 (21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Optimized Class Decomposition for Fault Detection

AU - Karakatic, Saso

AU - Fister, Dusan

AU - Beyca, Omer Faruk

AU - Fister, Iztok

PY - 2021

Y1 - 2021

N2 - The paper proposes an innovative approach in solving the fault detection problem of sewerage treatment plant machinery. The proposed approach treats the fault detection data with the class decomposition problem, ensuring that a classification algorithm overlooks no disjunct instances. As the class decomposition technique requires heavy customization to each class of instances in every data set, Grey Wolf Optimizer is used to determine the appropriate clustering method with the appropriate setting for each class of instances. The proposed approach is tested on real-life sensor data from a sewerage treatment plant, and the results show that here proposed approach overshadows several manually proposed class decomposition methods.

AB - The paper proposes an innovative approach in solving the fault detection problem of sewerage treatment plant machinery. The proposed approach treats the fault detection data with the class decomposition problem, ensuring that a classification algorithm overlooks no disjunct instances. As the class decomposition technique requires heavy customization to each class of instances in every data set, Grey Wolf Optimizer is used to determine the appropriate clustering method with the appropriate setting for each class of instances. The proposed approach is tested on real-life sensor data from a sewerage treatment plant, and the results show that here proposed approach overshadows several manually proposed class decomposition methods.

KW - Class Decomposition

KW - Clustering

KW - Fault Detection

KW - Grey Wolf Optimizer

UR - http://www.scopus.com/inward/record.url?scp=85124983649&partnerID=8YFLogxK

U2 - 10.1109/CINTI53070.2021.9668488

DO - 10.1109/CINTI53070.2021.9668488

M3 - Conference contribution

AN - SCOPUS:85124983649

T3 - 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings

SP - 15

EP - 20

BT - 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021

Y2 - 18 November 2021 through 20 November 2021

ER -

Karakatic S, Fister D, Beyca OF, Fister I. Optimized Class Decomposition for Fault Detection. In 21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2021. p. 15-20. (21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings). doi: 10.1109/CINTI53070.2021.9668488

Optimized Class Decomposition for Fault Detection

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this