A4 Article in conference proceedings
Explainable AI for Industry 4.0 : Semantic Representation of Deep Learning Models (2022)

Terziyan, V., & Vitko, O. (2022). Explainable AI for Industry 4.0 : Semantic Representation of Deep Learning Models. In F. Longo, M. Affenzeller, & A. Padovano (Eds.), 3rd International Conference on Industry 4.0 and Smart Manufacturing (pp. 216-226). Elsevier. Procedia Computer Science, 200. https://doi.org/10.1016/j.procs.2022.01.220

JYU authors or editors

Publication details

All authors or editors: Terziyan, Vagan; Vitko, Oleksandra

Parent publication: 3rd International Conference on Industry 4.0 and Smart Manufacturing

Parent publication editors: Longo, Francesco; Affenzeller, Michael; Padovano, Antonio

Conference:

Place and date of conference: Linz, Austria, 17.-19.11.2021

Journal or series: Procedia Computer Science

ISSN: 1877-0509

eISSN: 1877-0509

Publication year: 2022

Number in series: 200

Pages range: 216-226

Number of pages in the book: 1918

Publisher: Elsevier

Publication country: Netherlands

Publication language: English

DOI: https://doi.org/10.1016/j.procs.2022.01.220

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/80213

Abstract

Artificial Intelligence is an important asset of Industry 4.0. Current discoveries within machine learning and particularly in deep learning enable qualitative change within the industrial processes, applications, systems and products. However, there is an important challenge related to explainability of (and, therefore, trust to) the decisions made by the deep learning models (aka black-boxes) and their poor capacity for being integrated with each other. Explainable artificial intelligence is needed instead but without loss of effectiveness of the deep learning models. In this paper we present the transformation technique between black-box models and explainable (as well as interoperable) classifiers on the basis of semantic rules via automatic recreation of the training datasets and retraining the decision trees (explainable models) in between. Our transformation technique results to explainable rule-based classifiers with good performance and efficient training process due to embedded incremental ignorance discovery and adversarial samples (“corner cases”) generation algorithms. We have also shown the use-case scenario for such explainable and interoperable classifiers, which is collaborative condition monitoring, diagnostics and predictive maintenance of distributed (and isolated) smart industrial assets while preserving data and knowledge privacy of the users.

Keywords: industry; production technology; condition monitoring; maintenance; artificial intelligence; machine learning; deep learning; semantic web

Free keywords: Explainable Artificial Intelligence; Industry 4.0; semantic web; predictive maintenance

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2022

JUFO rating: 1