Automatic generation of methods-time measurement analyses for assembly tasks from motion capture data using convolutional neuronal networks - A proof of concept

Deuse, J; Stankiewicz, L; Zwinkau, R; Weichert, F

Automatic generation of methods-time measurement analyses for assembly tasks from motion capture data using convolutional neuronal networks - A proof of concept

Deuse, J

Stankiewicz, L Zwinkau, R Weichert, F

Permalink

Publisher:: Springer
Publication Type:: Conference Proceeding
Citation:: Advances in Human Factors and Systems Interaction, 2020, 959, pp. 141-150
Issue Date:: 2020-01-01

Closed Access

	Filename	Description	Size
	Deuse2020_Chapter_AutomaticGenerationOfMethods-T.pdf	Published version	534.87 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Deuse, J https://orcid.org/0000-0003-4066-4357
dc.contributor.author	Stankiewicz, L
dc.contributor.author	Zwinkau, R
dc.contributor.author	Weichert, F
dc.date	2019-07-24
dc.date.accessioned	2021-05-27T08:45:50Z
dc.date.available	2021-05-27T08:45:50Z
dc.date.issued	2020-01-01
dc.identifier.citation	Advances in Human Factors and Systems Interaction, 2020, 959, pp. 141-150
dc.identifier.isbn	9783030200398
dc.identifier.issn	2194-5357
dc.identifier.issn	2194-5365
dc.identifier.uri	http://hdl.handle.net/10453/149280
dc.description.abstract	This paper describes the research hypothesis that motion data can be utilized to derive MTM analyses. As a first step, manual assembly tasks are recorded with motion capture systems to generate motion data. These motion data are used as a training data set for an end-to-end deep learning architecture for motion classification. The result of this classification is the assignment of data sequences to corresponding basic motions of MTM-1. The paper also describes the prerequisites for an automatic generation of MTM analyses by considering an adaptation of the original MTM methodology to fit for an automatic approach, the acquisition of motion capture data and the automatic annotation of motion data.
dc.language	en
dc.publisher	Springer
dc.relation.ispartof	Advances in Human Factors and Systems Interaction
dc.relation.ispartof	International Conference on Human Factors and Systems Interaction
dc.relation.ispartofseries	Advances in Intelligent Systems and Computing
dc.relation.isbasedon	10.1007/978-3-030-20040-4_13
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Automatic generation of methods-time measurement analyses for assembly tasks from motion capture data using convolutional neuronal networks - A proof of concept
dc.type	Conference Proceeding
utslib.citation.volume	959
utslib.location.activity	Washington D.C., USA
utslib.for	0801 Artificial Intelligence and Image Processing
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2021-05-27T08:45:49Z
pubs.finish-date	2019-07-26
pubs.place-of-publication	Switzerland
pubs.publication-status	Published
pubs.start-date	2019-07-24
pubs.volume	959
dc.location	Switzerland

Abstract:

This paper describes the research hypothesis that motion data can be utilized to derive MTM analyses. As a first step, manual assembly tasks are recorded with motion capture systems to generate motion data. These motion data are used as a training data set for an end-to-end deep learning architecture for motion classification. The result of this classification is the assignment of data sequences to corresponding basic motions of MTM-1. The paper also describes the prerequisites for an automatic generation of MTM analyses by considering an adaptation of the original MTM methodology to fit for an automatic approach, the acquisition of motion capture data and the automatic annotation of motion data.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/149280