Manufacturing workers fatigue - an exploratory study on predictive machine learning and cross-subject generalization with implications for work design

Aug 6, 2026

Manufacturing workers’ fatigue is a recognized challenge affecting well-being, health, safety, and operational performance. The study addresses uncertainty about whether fatigue estimation and prediction models trained on data from specific individuals generalize to other workers. Using an exploratory cross-subject design, it evaluates machine-learning approaches for fatigue estimation and identifies cases with sufficiently accurate performance. It also analyzes lower-generalization outcomes and links them to personal characteristics, supporting improved work design.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Introduction

Background on manufacturing fatigue and impacts

Prior machine-learning and physiological-signal approaches

Methods

Cross-subject vs. intra-subject learning framing

Model training and generalization evaluation

Results and Discussion

Cases showing accurate generalization

Lower-generalization cases and links to personal characteristics

Implications

Relevance for work design and operator support

University of Groningen Manufacturing workers fatigue Emmanouilidis, Christos; Montini, Elias; Cutrona, Vincenzo; Rožanec, Jože Published in: 18th IFAC Symposium on Information Control Problems in Manufacturing (INCOM 2024) DOI: 10.1016/j.ifacol.2024.09.271 IMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check the document version below. Document Version Publisher's PDF, also known as Version of record Publication date: 2024 Link to publication in University of Groningen/UMCG research database Citation for published version (APA): Emmanouilidis, C. , Montini, E. , Cutrona, V. , & Rožanec, J. (2024) . Manufacturing workers fatigue: an exploratory study on predictive machine learning and cross-subject generalization with implications for work design. In S. Schlund, & F. Ansari (Eds.), 18th IFAC Symposium on Information Control Problems in Manufacturing (INCOM 2024) (pp. 557-562) . (IFAC PapersOnline; Vol. 58, No. 19) . Elsevier. [https://doi.org/10.1016/j.ifacol.2024.09.271](https://doi.org/10.1016/j.ifacol.2024.09.271) Copyright Other than for strictly personal use, it is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license (like Creative Commons) . The publication may also be distributed here under the terms of Article 25fa of the Dutch Copyright Act, indicated by the “Taverne” license. More information can be found on the University of Groningen website: [https://www.rug.nl/library/open-access/self-archiving-pure/taverne](https://www.rug.nl/library/open-access/self-archiving-pure/taverne)amendment. Take-down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim. Downloaded from the University of Groningen/U MCG research database (Pure): [http://www.rug. nl/research/portal. For technical reasons the](http://www.rug. nl/research/portal. For technical reasons the)[ ](http://www.rug. nl/research/portal. For technical reasons the)[number of authors shown on this cover page is limited to 10 maximum.](number of authors shown on this cover page is limited to 10 maximum.) Download date: 01-01-2026 [Available online at](Available online at www.sciencedirect.com)[ www.sciencedirect.com](Available online at www.sciencedirect.com) ScienceDirect IFAC PapersOnLine 58-19 (2024) 557–562 Manufacturing workers fatigue: an exploratory study on predictive machine learning and cross-subject generalization with implications for work design Christos Emmanouilidis ∗ Elias Montini ∗∗ Vincenzo Cutrona ∗∗∗ Joˇze M. Roˇzanec ∗∗∗∗ ∗ University of Groningen, Groningen, The Netherlands (e-mail: [c.emmanouilidis@rug.nl](c.emmanouilidis@rug.nl)) ∗∗ Politecnico di Milano, Dipartimento di Elettronica, Informazione e Bioingegneria, Milano, Italy (e-mail: [elias.montini@polimi.it](elias.montini@polimi.it)) ∗∗∗ DTI-University of Applied Sciences and Arts of Southern Switzerland, Lugano, Switzerland (e-mail: [vincenzo.cutrona@supsi.ch](vincenzo.cutrona@supsi.ch)) ∗∗∗∗ Joˇzef Stefan Institute, Ljubljana, Slovenia (e-mail: [joze.rozanec@ijs.si](joze.rozanec@ijs.si)) Abstract: Manufacturing workers’ fatigue is an acknowledged concern with implications for well-being, health, safety, and operational performance. Past studies have employed physiological measurements obtained from smartwatches and wearable devices, seeking to assess and classify the fatigue state of workers. However, the extent to which models developed based on data obtained from individual workers could apply to other workers remains unclear. This paper presents the results of an exploratory study in which data from different subjects are employed to develop a range of fatigue estimation and predictive machine learn

FAQs

What problem does the paper focus on regarding fatigue prediction models?

It examines how well models trained on one worker’s data apply to other workers, since cross-worker generalization remains unclear.

How is the study designed to test predictive machine learning for fatigue?

An exploratory cross-subject study uses data from different individuals to develop fatigue estimation and predictive machine learning models.

What insights are provided when generalization performance is lower?

The paper analyzes cases of lower generalization and connects them to personal characteristics.

Aug 6, 2026

Upload by Olivia Brown