Optimized Class Decomposition for Fault Detection

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

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-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 languageEnglish
Title of host publication21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages15-20
Number of pages6
ISBN (Electronic)9781665426848
DOIs
Publication statusPublished - 2021
Event21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Budapest, Hungary
Duration: 18 Nov 202120 Nov 2021

Publication series

Name21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021 - Proceedings

Conference

Conference21st IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2021
Country/TerritoryHungary
CityBudapest
Period18/11/2120/11/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Funding

ACKNOWLEDGMENT This research was funded by the Slovenian Research Agency (research cores funding Nos. P2-0057 and P5-0027).

FundersFunder number
Javna Agencija za Raziskovalno Dejavnost RSP2-0057, P5-0027

    Keywords

    • Class Decomposition
    • Clustering
    • Fault Detection
    • Grey Wolf Optimizer

    Fingerprint

    Dive into the research topics of 'Optimized Class Decomposition for Fault Detection'. Together they form a unique fingerprint.

    Cite this