Inducing rules for selecting retaining wall systems

Nie-Jia Yau, Jyh-Bin Yang and Ting-Ya Hsieh

Construction Management and Economics, 1999, vol. 17, issue 1, 91-98

Abstract: Rule induction is a paradigm of machine learning that governs how knowledge is acquired from experience. This paradigm not only classifies existing data into logical sets, but also expresses them by 'if-then' rules. Rule induction can be applied to the experience-oriented construction industry. A typical example would be to select an appropriate retaining wall system at the project planning stage, in which engineers normally employ certain empirical laws or select from the types for which they have relevant expertise in making appropriate selections. This work presents a novel rule induction approach, capable of inducing from 254 retaining wall cases in engineering design reports into 181 rules, thereby allowing for an appropriate retaining wall system to be selected. A system referred to herein as RULES is also constructed with an illustrative example provided as well. Test results of the system demonstrate that the rule induction approach can effectively resolve retaining wall selection problems at the project planning stage. The approach proposed herein is highly promising for resolving experience-oriented problems in the construction industry.

Keywords: Rule Induction; Retaining Wall Selection; Knowledge Discovery; Artificial Intelligence (search for similar items in EconPapers)
Date: 1999
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.tandfonline.com/doi/abs/10.1080/014461999371853 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:conmgt:v:17:y:1999:i:1:p:91-98

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RCME20

DOI: 10.1080/014461999371853

Access Statistics for this article

Construction Management and Economics is currently edited by Will Hughes

More articles in Construction Management and Economics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().