Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/16479
Title: A Bayesian Approach for Best Practice Recommendations in Collaborative Designs of Construction Projects
Authors: Liang, X
Shen, GQP 
Bu, S
Issue Date: 2014
Publisher: American Society of Civil Engineers (ASCE)
Source: ICCREM 2014: Smart Construction and Management in the Context of New Technology - Proceedings of the 2014 International Conference on Construction and Real Estate Management, 2014, p. 721-732 How to cite?
Abstract: With the accelerated growth of scale, complexity and diversity of construction projects, accurate demand analysis has become a crucial issue impacting effect and efficiency in collaborative design. However, comprehending deviations between clients and designers is ubiquitous because of the information asymmetry. Choosing a best practice as reference is considered to be a promising method to help solve this kind of problems, so the key problem is the best practices selection. This paper proposes a novel data mining approach based on Bayesian probability for best practice recommendation (BPR), integrating the satisfactions of former projects and similarity between former projects and the recent one. This approach is applicable because it reasons top ranking practices to help clarify requirement, so that design collaboration and clients' satisfaction should be improved with more probability. A green building retrofit example is presented to demonstrate the application of this approach.
Description: 2014 International Conference on Construction and Real Estate Management: Smart Construction and Management in the Context of New Technology, ICCREM 2014, 27-28 September 2014
URI: http://hdl.handle.net/10397/16479
ISBN: 9780784413777
DOI: 10.1061/9780784413777.084
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

1
Last Week
0
Last month
0
Citations as of Sep 22, 2017

Page view(s)

53
Last Week
0
Last month
Checked on Sep 24, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.