Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

On Exploring the Possibilities and the Limits of AI for an Interoperable and Empowering Industry 4.0

Version 1 : Received: 7 February 2022 / Approved: 8 February 2022 / Online: 8 February 2022 (12:31:01 CET)

How to cite: Lelli, F. On Exploring the Possibilities and the Limits of AI for an Interoperable and Empowering Industry 4.0. Preprints 2022, 2022020109. https://doi.org/10.20944/preprints202202.0109.v1 Lelli, F. On Exploring the Possibilities and the Limits of AI for an Interoperable and Empowering Industry 4.0. Preprints 2022, 2022020109. https://doi.org/10.20944/preprints202202.0109.v1

Abstract

This paper aims to raise awareness on certain interoperability issues as we intend to shape industry 5.0 in order to enable a human-centric resilient society. We advocate that the need of sharing small and specific data will become more intensive as AI-based solutions will become more pervasive. Consequently, dataspaces should be carefully designed to address this need. We advance the conversation by presenting a case study from HR demonstrating how to predict the possibility of an employee experiencing attrition. Our experimental results show that we need more than 500 samples for developing a machine learning model to be sufficiently capable to generalize the problem. Consequently, our experimental results show the feasibility of the idea. However, in small and medium sized companies this approach cannot be implemented due to the limited number of samples. At the same time, we advocate that this obstacle may be overcome if multiple companies will join a shared dataspace, thus raising interoperability issues

Keywords

Industry 4.0; industry 5.0 interoperability; Machine Learning; AI; HR; Attrition

Subject

Computer Science and Mathematics, Information Systems

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.