Machine learning based Gaussian process regression for fault detection of Biological Systems

Radhia Fezai, Majdi Mansouri, Nasreddine Bouguila, Hazem Nounou, Mohamed Nounou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Effective detection of faults in Biological processes is essential to observe the continuity of good functioning of the system under typical circumstances for ensuring safety. Therefore, the first objective of this paper is to develop a machine learning based Gaussian process regression (GPR) technique that can accurately model biological processes and compute the monitored residuals. The second objective is to apply a generalized likelihood ratio test (GLRT) to the evaluated residuals for fault detection purposes. The detection performance of the GPR-based GLRT is evaluated using a biological process representing a Cad System in E. Coli (CSEC) model. The GPR-based GLRT is used to enhance monitoring of the Cad System in E. coli process through monitoring some of the key variables involved in this process, such as enzymes, lysine, and cadaverine.

Original languageEnglish
Title of host publication2019 International Conference on Internet of Things, Embedded Systems and Communications, IINTEC 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages174-179
Number of pages6
ISBN (Electronic)9781728151847
DOIs
Publication statusPublished - Dec 2019
Externally publishedYes
Event2019 International Conference on Internet of Things, Embedded Systems and Communications, IINTEC 2019 - Gammarth, Tunisia
Duration: 20 Dec 201922 Dec 2019

Publication series

Name2019 International Conference on Internet of Things, Embedded Systems and Communications, IINTEC 2019 - Proceedings

Conference

Conference2019 International Conference on Internet of Things, Embedded Systems and Communications, IINTEC 2019
Country/TerritoryTunisia
CityGammarth
Period20/12/1922/12/19

Keywords

  • Gaussian process regression (GPR)
  • Machine learning (ML)
  • biological process
  • fault detection (FD)
  • generalized likelihood ratio test (GLRT)

Fingerprint

Dive into the research topics of 'Machine learning based Gaussian process regression for fault detection of Biological Systems'. Together they form a unique fingerprint.

Cite this