Assessing Implicit Knowledge in BIM Models with Machine Learning

Thomas Krijnen; Martin Tamke

Assessing Implicit Knowledge in BIM Models with Machine Learning

Publications: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

The promise, which comes along with Building Information Models, is that they are information rich, machine readable and represent the insights of multiple building disciplines within single or linked models. However, this knowledge has to be stated explicitly in order to be understood. Trained architects and engineers are able to deduce non-explicitly explicitly stated information, which is often the core of the transported architectural information. This paper investigates how machine learning approaches allow a computational system to deduce implicit knowledge from a set of BIM models.

Original language	English
Title of host publication	Modelling Behaviour : Design Modelling Symposium 2015
Editors	Mette Ramsgaard Thomsen , Martin Tamke, Christoph Gengnagel, Billie Faircloth, Fabian Scheurer
Number of pages	10
Place of Publication	Cham
Publisher	Springer
Publication date	2015
Pages	397-406
ISBN (Print)	978-3-319-24206-4
ISBN (Electronic)	978-3-319-24208-8
Publication status	Published - 2015
Event	Design Modelling Symposium Copenhagen 2015: Modelling Behaviour - KADK, Copenhagen, Denmark Duration: 28 Sept 2015 → 2 Oct 2015

Conference

Conference	Design Modelling Symposium Copenhagen 2015
Location	KADK
Country/Territory	Denmark
City	Copenhagen
Period	28/09/2015 → 02/10/2015

Artistic research

No

Access to Document

http://link.springer.com/chapter/10.1007%2F978-3-319-24208-8_33

Cite this

@inproceedings{9bd5d4197f2b4be3b1b1df4cf179baec,

title = "Assessing Implicit Knowledge in BIM Models with Machine Learning",

abstract = "The promise, which comes along with Building Information Models, is that they are information rich, machine readable and represent the insights of multiple building disciplines within single or linked models. However, this knowledge has to be stated explicitly in order to be understood. Trained architects and engineers are able to deduce non-explicitly explicitly stated information, which is often the core of the transported architectural information. This paper investigates how machine learning approaches allow a computational system to deduce implicit knowledge from a set of BIM models.",

author = "Thomas Krijnen and Martin Tamke",

year = "2015",

language = "English",

isbn = "978-3-319-24206-4",

pages = "397--406",

editor = "{Ramsgaard Thomsen }, {Mette } and Martin Tamke and Christoph Gengnagel and Billie Faircloth and Fabian Scheurer",

booktitle = "Modelling Behaviour",

publisher = "Springer",

note = "Design Modelling Symposium Copenhagen 2015 : Modelling Behaviour, DMS ; Conference date: 28-09-2015 Through 02-10-2015",

}

Krijnen, T & Tamke, M 2015, Assessing Implicit Knowledge in BIM Models with Machine Learning. in M Ramsgaard Thomsen , M Tamke, C Gengnagel, B Faircloth & F Scheurer (eds), Modelling Behaviour: Design Modelling Symposium 2015. Springer, Cham, pp. 397-406, Design Modelling Symposium Copenhagen 2015, Copenhagen, Denmark, 28/09/2015. <http://link.springer.com/chapter/10.1007%2F978-3-319-24208-8_33>

Assessing Implicit Knowledge in BIM Models with Machine Learning. / Krijnen, Thomas; Tamke, Martin.
Modelling Behaviour: Design Modelling Symposium 2015. ed. / Mette Ramsgaard Thomsen ; Martin Tamke; Christoph Gengnagel; Billie Faircloth; Fabian Scheurer. Cham: Springer, 2015. p. 397-406.

Publications: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Assessing Implicit Knowledge in BIM Models with Machine Learning

AU - Krijnen, Thomas

AU - Tamke, Martin

PY - 2015

Y1 - 2015

N2 - The promise, which comes along with Building Information Models, is that they are information rich, machine readable and represent the insights of multiple building disciplines within single or linked models. However, this knowledge has to be stated explicitly in order to be understood. Trained architects and engineers are able to deduce non-explicitly explicitly stated information, which is often the core of the transported architectural information. This paper investigates how machine learning approaches allow a computational system to deduce implicit knowledge from a set of BIM models.

AB - The promise, which comes along with Building Information Models, is that they are information rich, machine readable and represent the insights of multiple building disciplines within single or linked models. However, this knowledge has to be stated explicitly in order to be understood. Trained architects and engineers are able to deduce non-explicitly explicitly stated information, which is often the core of the transported architectural information. This paper investigates how machine learning approaches allow a computational system to deduce implicit knowledge from a set of BIM models.

M3 - Article in proceedings

SN - 978-3-319-24206-4

SP - 397

EP - 406

BT - Modelling Behaviour

A2 - Ramsgaard Thomsen , Mette

A2 - Tamke, Martin

A2 - Gengnagel, Christoph

A2 - Faircloth, Billie

A2 - Scheurer, Fabian

PB - Springer

CY - Cham

T2 - Design Modelling Symposium Copenhagen 2015

Y2 - 28 September 2015 through 2 October 2015

ER -