Physiological workload assessment for highly flexible fine-motory assembly tasks using machine learning

Markus Brillinger; Samuel Manfredi; Dominik Leder; Martin Bloder; Markus Jäger; Konrad Diwold; Amer Kajmakovic; Michael Haslgrübler; Rudolf Pichler; Martin Brunner; Stefan Mehr; Viktorijo Malisa

doi:10.1016/j.cie.2023.109859

Physiological workload assessment for highly flexible fine-motory assembly tasks using machine learning

Markus Brillinger^*, Samuel Manfredi, Dominik Leder, Martin Bloder, Markus Jäger, Konrad Diwold, Amer Kajmakovic, Michael Haslgrübler, Rudolf Pichler, Martin Brunner, Stefan Mehr, Viktorijo Malisa

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

In assembly of small-volume products, tasks are still frequently executed manually. However, the lead times foreseen for these tasks, often do not take into account the actual capabilities of the employees, which in turn leads to increased workload and the associated stress among the employees. This paper investigates how a commercially available wearable low-cost sensor and two machine learning algorithms can be applied to measure and evaluate heart rate, heart rate variability and respiration rate to establish a relationship with workload. The investigated algorithms, namely Random Forest and K-Nearest-Neighbours are able to distinguish between tasks phases and rest phases as well as between easy and difficult tasks executed by the employee, which is the main novelty of this paper.

Original language	English
Article number	109859
Journal	Computers and Industrial Engineering
Volume	188
Early online date	3 Jan 2024
DOIs	https://doi.org/10.1016/j.cie.2023.109859
Publication status	Published - Feb 2024

Keywords

Assembly of small-volume products
Commercially available wearable low-cost sensor
Random forest and K-Nearest-Neighbours
Workload assessment

ASJC Scopus subject areas

General Computer Science
General Engineering

Access to Document

10.1016/j.cie.2023.109859Licence: CC BY 4.0

1-s2.0-S0360835223008835-mainFinal published version, 2.19 MBLicence: CC BY 4.0

Cite this

Brillinger, M., Manfredi, S., Leder, D., Bloder, M., Jäger, M., Diwold, K., Kajmakovic, A., Haslgrübler, M., Pichler, R., Brunner, M., Mehr, S., & Malisa, V. (2024). Physiological workload assessment for highly flexible fine-motory assembly tasks using machine learning. Computers and Industrial Engineering, 188, Article 109859. https://doi.org/10.1016/j.cie.2023.109859

@article{60b6e3d143e14084b905f219cbf52513,

title = "Physiological workload assessment for highly flexible fine-motory assembly tasks using machine learning",

abstract = "In assembly of small-volume products, tasks are still frequently executed manually. However, the lead times foreseen for these tasks, often do not take into account the actual capabilities of the employees, which in turn leads to increased workload and the associated stress among the employees. This paper investigates how a commercially available wearable low-cost sensor and two machine learning algorithms can be applied to measure and evaluate heart rate, heart rate variability and respiration rate to establish a relationship with workload. The investigated algorithms, namely Random Forest and K-Nearest-Neighbours are able to distinguish between tasks phases and rest phases as well as between easy and difficult tasks executed by the employee, which is the main novelty of this paper.",

keywords = "Assembly of small-volume products, Commercially available wearable low-cost sensor, Random forest and K-Nearest-Neighbours, Workload assessment",

author = "Markus Brillinger and Samuel Manfredi and Dominik Leder and Martin Bloder and Markus J{\"a}ger and Konrad Diwold and Amer Kajmakovic and Michael Haslgr{\"u}bler and Rudolf Pichler and Martin Brunner and Stefan Mehr and Viktorijo Malisa",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s)",

year = "2024",

month = feb,

doi = "10.1016/j.cie.2023.109859",

language = "English",

volume = "188",

journal = "Computers and Industrial Engineering",

issn = "0360-8352",

publisher = "Elsevier Ltd.",

}

TY - JOUR

T1 - Physiological workload assessment for highly flexible fine-motory assembly tasks using machine learning

AU - Brillinger, Markus

AU - Manfredi, Samuel

AU - Leder, Dominik

AU - Bloder, Martin

AU - Jäger, Markus

AU - Diwold, Konrad

AU - Kajmakovic, Amer

AU - Haslgrübler, Michael

AU - Pichler, Rudolf

AU - Brunner, Martin

AU - Mehr, Stefan

AU - Malisa, Viktorijo

PY - 2024/2

Y1 - 2024/2

N2 - In assembly of small-volume products, tasks are still frequently executed manually. However, the lead times foreseen for these tasks, often do not take into account the actual capabilities of the employees, which in turn leads to increased workload and the associated stress among the employees. This paper investigates how a commercially available wearable low-cost sensor and two machine learning algorithms can be applied to measure and evaluate heart rate, heart rate variability and respiration rate to establish a relationship with workload. The investigated algorithms, namely Random Forest and K-Nearest-Neighbours are able to distinguish between tasks phases and rest phases as well as between easy and difficult tasks executed by the employee, which is the main novelty of this paper.

AB - In assembly of small-volume products, tasks are still frequently executed manually. However, the lead times foreseen for these tasks, often do not take into account the actual capabilities of the employees, which in turn leads to increased workload and the associated stress among the employees. This paper investigates how a commercially available wearable low-cost sensor and two machine learning algorithms can be applied to measure and evaluate heart rate, heart rate variability and respiration rate to establish a relationship with workload. The investigated algorithms, namely Random Forest and K-Nearest-Neighbours are able to distinguish between tasks phases and rest phases as well as between easy and difficult tasks executed by the employee, which is the main novelty of this paper.

KW - Assembly of small-volume products

KW - Commercially available wearable low-cost sensor

KW - Random forest and K-Nearest-Neighbours

KW - Workload assessment

UR - http://www.scopus.com/inward/record.url?scp=85184743476&partnerID=8YFLogxK

U2 - 10.1016/j.cie.2023.109859

DO - 10.1016/j.cie.2023.109859

M3 - Article

AN - SCOPUS:85184743476

SN - 0360-8352

VL - 188

JO - Computers and Industrial Engineering

JF - Computers and Industrial Engineering

M1 - 109859

ER -

Physiological workload assessment for highly flexible fine-motory assembly tasks using machine learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this