EXAMINING ASSOCIATION BETWEEN CONSTRUCTION INSPECTION GRADES AND CRITICAL DEFECTS USING DATA MINING AND FUZZY LOGIC
Open Access
- 29 June 2018
- journal article
- research article
- Published by Vilnius Gediminas Technical University in JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT
- Vol. 24 (4) , 301-317
Abstract
This paper explores the relations between defect types and quality inspection grades of public construction projects in Taiwan. Altogether, 499 defect types (classified from 17,648 defects) were found after analyzing 990 construction projects from the Public Construction Management Information System of the public construction commission which is a government unit that administers all the public construction. The core of this research includes the following steps. (1) Data mining (DM) was used to derive 57 association rules which altogether contain 30 of the 499 defect types. (2) K-means clustering was used to regroup the 990 projects of two attributes (defect frequency and original grading score of each project) into four new quality classes, so the 990 projects can be more evenly distributed in the four new classes and the correctness and reliability of the following analyses can be ensured. (3) Finally analysis of variance (ANOVA), fuzzy logic, and correlation analysis were used to verify that the aforementioned 30 defect types are the important ones determining inspection grades. Results of this research can help stakeholders of construction projects paying more attention on the root causes of the critical defect types so to dramatically raise their management effectiveness.Keywords
This publication has 54 references indexed in Scilit:
- Analysis of Causes of Construction Defects Using Fault Trees and Risk Importance MeasuresJournal of Construction Engineering and Management, 2013
- A Study of Contribution Factors to Building Failures and Defects in Construction IndustryProcedia Engineering, 2011
- CAS-Mine: providing personalized services in context-aware applications by means of generalized rulesKnowledge and Information Systems, 2010
- Neuro-fuzzy network for the classification of buried pipe defectsAutomation in Construction, 2006
- Defect analysis in wet areas of buildingsConstruction and Building Materials, 2005
- Using Information Retrieval techniques for supporting data miningData & Knowledge Engineering, 2005
- Finding interesting associations without support pruningIEEE Transactions on Knowledge and Data Engineering, 2001
- Scalable algorithms for association miningIEEE Transactions on Knowledge and Data Engineering, 2000
- A comparison of defects in houses constructed by owners and registered builders in the Australian State of VictoriaStructural Survey, 1999
- The causes and costs of defects in constructionAutomation in Construction, 1999