Machine learning assisted human fatigue detection, monitoring, and recovery: a review

Lambay, Arsalan, Liu, Ying ORCID: https://orcid.org/0000-0001-9319-5940, Morgan, Phillip L. ORCID: https://orcid.org/0000-0002-5672-0758 and Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902 2024. Machine learning assisted human fatigue detection, monitoring, and recovery: a review. Digital Engineering 1 , 100004. 10.1016/j.dte.2024.100004

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (2MB) | Preview

Abstract

The use of knowledge-based information systems to improve human performance has been limited by a lack of comprehension of how an individual’s performance diminishes when fatigue accumulates, which might vary between individuals depending on their working environment. Although the rise in automation has been witnessed, there are still some physically demanding and exhausting jobs in the manufacturing environment that, if not appropriately managed, can result in long-term issues including musculoskeletal disorders and impairments to psychological well-being. To detect, comprehend and manage the development of solutions for fatigue detection, Machine Learning (ML) has been a useful tool. This paper presents a review of the use of ML techniques for the detection and monitoring of an operator’s work-related physical fatigue in repetitive work and Human–Robot Collaboration (HRC) settings. The novel review offers an overview of the detection complexity of human fatigue in manufacturing-related contexts. The review has three major components: First, the level of fatigue detection complexity with the help of ML, which presents only specific influencing factors in terms of features selected that vary concerning tasks in the context of human fatigue. Second, the features generated in relation to human performance while operating under fatigue conditions are included — in the human worker and the detecting technology. Finally, the challenges and limitations of the complexity of holistic approaches in the monitoring/recovery of human fatigue in essence to the physical exertion of an individual are critically discussed.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering Psychology
Publisher:	Elsevier
ISSN:	2950-550X
Date of First Compliant Deposit:	3 June 2024
Date of Acceptance:	19 March 2024
Last Modified:	08 Jul 2024 12:42
URI:	https://orca.cardiff.ac.uk/id/eprint/169441

Actions (repository staff only)

Edit Item