Assessing Implicit Knowledge in BIM Models with Machine Learning

Krijnen, Thomas; Tamke, Martin

doi:10.1007/978-3-319-24208-8_33

Cited by 34 publications

(30 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first approach is adopted from [1]. Krijnen and Tamke, here after referred as "Krijnen's approach", explored the use geometric features of individual components to detect misclassifications using outlier detection.…”

Section: Methodsmentioning

confidence: 99%

“…The research used existing work performed by from [1] as its initial point of departure. [1] proposed using 'outlier detection' to check the correct classification of individual elements.…”

Section: Introductionmentioning

confidence: 99%

“…[1] proposed using 'outlier detection' to check the correct classification of individual elements. To verify the scalability of this approach, we first performed outlier detection on two BIM models with increasing components, from which we identified specific limitations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Employing Outlier and Novelty Detection for Checking the Integrity of BIM to IFC Entity Associations

Koo

Shin

Krijnen

2017

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

-Although Industry Foundation Classes (IFC) provide standards for exchanging BuildingInformation Modeling (BIM) data, authoring tools still require manual mapping between BIM entities and IFC classes. This leads to errors and omissions, which results in corrupted data exchanges that are unreliable and compromise the interoperability of BIM models. This research explored the use of two machine learning techniques for identifying anomalies, namely outlier and novelty detection to determine the integrity of IFC classes to BIM entity mappings. Both approaches were tested on three BIM models, to test their accuracy in identifying misclassifications. Results showed that outlier detection, which uses Mahalanobis distances, had difficulties when several types of dissimilar elements existed in a single IFC class and conversely was not applicable for IFC classes with insufficient number of elements. Novelty detection, using one-class SVM, was trained a priori on elements with dissimilar geometry. By creating multiple inlier boundaries, novelty detection resolved the limitations encountered in the former approach, and consequently performed better in identifying outliers correctly.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The research used existing work performed by from [1] as its initial point of departure. [1] proposed using 'outlier detection' to check the correct classification of individual elements.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Employing Outlier and Novelty Detection for Checking the Integrity of BIM to IFC Entity Associations

Koo

Shin

Krijnen

2017

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

show abstract

“…In the field of buildings and constructions, ML is primarily adopted for automatic designing and detection [17][18][19][20][21]. For instance, Krijnen et al proposed a self-learning algorithm for the automatic selections of structures based on building information models [17]. Dornaika et al presented a generic framework that exploited recent advances in image segmentation and region descriptor extraction for the automatic and accurate detection of buildings on aerial orthophotos [18].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Structural Type for City-Scale Seismic Damage Simulation Based on Machine Learning

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Being the necessary data of the city-scale seismic damage simulations, structural types of buildings of a city need to be collected. To this end, a prediction method of structural types of buildings based on machine learning (ML) is proposed herein. Specifically, using the training data of 230,683 buildings in Tangshan city, China, a supervised ML solution based on a decision forest model was designed for the prediction. The scale sensitivity and regional applicability of the designed solution are discussed, respectively, and the results show that the supervised ML solution can maintain high accuracy for different scales; however, it is only suitable for cities similar to the sample city. For wide applicability for various cities, a semi-supervised ML solution was designed based on sampling investigation and self-training procedures. The downtowns of Daxing and Tongzhou districts in Beijing were selected as a case study for the designed semi-supervised ML solution. The overall prediction accuracies of structural types for Daxing and Tongzhou downtowns can reach 94.8% and 99.5%, respectively, which are acceptable for seismic damage simulations. Based on the predicted results, the distributions of seismic damage in Daxing and Tongzhou downtown were output. This study provides a smart and efficient method for obtaining structural types for a city-scale seismic damage simulation.

show abstract

“…Parameters can bring additional information to the model about the connectivity of the BIM objects or the location of nearest recycling facilities…etc. (Akbarnezhad et al 2014;Krijnen and Tamke 2015) 17 Verification of parameter values added to a BIM model can be achieved. By developing a plug-in that can be added to the BIM authoring tool, different parameters can be retrieved and analyzed.…”

mentioning

confidence: 99%

An Exploration of BIM and Lean Interaction in Optimizing Demolition Projects

Elmaraghy¹,

Voordijk²,

Marzouk³

2018

Annual Conference of the International Group for Lean Construction

View full text Add to dashboard Cite

Construction and demolition wastes have an adverse environmental impact. The demolition wastes are resulted from the linear economic behaviour that the Construction industry is currently adopting. IT-enabled processes like BIM have been used to eliminate wastes in Construction Projects. The alignment of these processes with Lean Construction principles was seen to reap high benefits. This research investigates the possibility of extending BIM functionalities to support deconstruction processes in alignment with Lean Principles. Based on the existing interaction matrix between BIM functionalities and Lean Principles and its subsequent extensions, the synergies between BIM and Lean are explored from a deconstruction perspective. The evidence of using BIM capabilities in deconstruction projects is mainly interpreted from research in addition to the current initiatives in the demolition and renovation projects in The Netherlands. The main aim is to integrate discrete efforts in industry and academia towards leveraging the recovery rate of salvaged elements. The evidence is then validated against Lean principles and the results reveal a major conformity between BIM and Lean. This exploratory research may contribute to the adoption of a structured framework in deconstruction projects that exploits BIM and Lean capabilities towards achieving a circular economy.

show abstract

Assessing Implicit Knowledge in BIM Models with Machine Learning

Cited by 34 publications

References 6 publications

Employing Outlier and Novelty Detection for Checking the Integrity of BIM to IFC Entity Associations

Employing Outlier and Novelty Detection for Checking the Integrity of BIM to IFC Entity Associations

Prediction of Structural Type for City-Scale Seismic Damage Simulation Based on Machine Learning

An Exploration of BIM and Lean Interaction in Optimizing Demolition Projects

Contact Info

Product

Resources

About