Autoencoder Alignment Approach to Run-Time Interoperability for System of Systems Engineering

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: onr:"swepub:oai:DiVA.org:ltu-80561" > Autoencoder Alignme...

1 av 1
Föregående post
Nästa post
Till träfflistan

LIBRIS Formathandbok (Information om MARC21)

Fältnamn	Indikatorer	Metadata
000		03185naa a2200397 4500
001		oai:DiVA.org:ltu-80561
003		SwePub
008		200826s2020 \| \|\|\|\|\|\|\|\|\|\|\|000 \|\|eng\|
024	7	a https://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-805612 URI
024	7	a https://doi.org/10.1109/INES49302.2020.91471682 DOI
040		a (SwePub)ltu
041		a engb eng
042		9 SwePub
072	7	a vet2 swepub-contenttype
072	7	a kon2 swepub-publicationtype
100	1	a Nilsson, Jacobu Luleå tekniska universitet,EISLAB4 aut0 (Swepub:ltu)jacnil
245	1 0	a Autoencoder Alignment Approach to Run-Time Interoperability for System of Systems Engineering
264	1	b IEEE,c 2020
338		a print2 rdacarrier
500		a ISBN för värdpublikation: 978-1-7281-1059-2, 978-1-7281-1060-8
520		a We formulate the challenging problem to establish information interoperability within a system of systems (SoS) as a machine-learning task, where autoencoder embeddings are aligned using message data and metadata to automate message translation. An SoS requires communication and collaboration between otherwise independently operating systems, which are subject to different standards, changing conditions, and hidden assumptions. Thus, interoperability approaches that are based on standardization and symbolic inference will have limited generalization and scalability in the SoS engineering domain. We present simulation experiments performed with message data generated using heating and ventilation system simulations. While the unsupervised learning approach proposed here remains unsolved in general, we obtained up to 75% translation accuracy with autoencoders aligned by back-translation after investigating seven different models with different training protocols and hyperparameters. For comparison, we obtain 100% translation accuracy on the same task with supervised learning, but the need for a labeled dataset makes that approach less interesting. We discuss possibilities to extend the proposed unsupervised learning approach to reach higher translation accuracy.
650	7	a TEKNIK OCH TEKNOLOGIERx Elektroteknik och elektronikx Annan elektroteknik och elektronik0 (SwePub)202992 hsv//swe
650	7	a ENGINEERING AND TECHNOLOGYx Electrical Engineering, Electronic Engineering, Information Engineeringx Other Electrical Engineering, Electronic Engineering, Information Engineering0 (SwePub)202992 hsv//eng
653		a Adapter design pattern
653		a Autoencoder alignment
653		a Embeddings
653		a M2M-Communication
653		a System of systems
653		a Electronic systems
653		a Elektroniksystem
700	1	a Delsing, Jerker,d 1957-u Luleå tekniska universitet,EISLAB4 aut0 (Swepub:ltu)jerker
700	1	a Sandin, Fredrik,d 1977-u Luleå tekniska universitet,EISLAB4 aut0 (Swepub:ltu)fresan
710	2	a Luleå tekniska universitetb EISLAB4 org
773	0	t IEEE 24th International Conference on Intelligent Engineering Systemsd : IEEEg , s. 139-144q <139-144
856	4 8	u https://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-80561
856	4 8	u https://doi.org/10.1109/INES49302.2020.9147168

Till lärosätets databas

1 av 1
Föregående post
Nästa post
Till träfflistan

Hitta mer i SwePub

Av författaren/redakt...: Nilsson, Jacob; Delsing, Jerker, ...; Sandin, Fredrik, ...

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Annan elektrotek ...

Artiklar i publikationen: IEEE 24th Intern ...

Av lärosätet: Luleå tekniska universitet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst. Hantera kakor

LIBRIS.kb.se