• Sep 20, 2019 News!IJMMM Had Implemented Online Submission System, Please Submit New Submissions through This System Only!   [Click]
  • Feb 26, 2018 News!'Writing Tips' shared by Prof. Ian McAndrew!   [Click]
  • Mar 23, 2021 News!Vol. 7, No. 2 has been indexed byInspec (IET)!   [Click]
General Information
    • ISSN: 1793-8198 (Print)
    • Abbreviated Title: Int. J. Mater. Mech. Manuf.
    • Frequency: Bimonthly
    • DOI: 10.18178/IJMMM
    • Editor-in-Chief: Prof. Ian McAndrew
    • Co-editor-in-Chief: Prof. K. M. Gupta
    • Executive Editor: Cherry L. Chen
    • Abstracting/Indexing: Inspec (IET), Chemical Abstracts Services (CAS),  ProQuest, Crossref, Ulrich's Periodicals Directory,  EBSCO.
    • E-mail ijmmm@ejournal.net

Prof. Ian McAndrew
Capitol Technology University, USA
It is my honor to be the editor-in-chief of IJMMM. I will do my best to work with the editorial team and help make this journal better.

IJMMM 2019 Vol.7(1): 27-32 ISSN: 1793-8198
DOI: 10.18178/ijmmm.2019.7.1.423

Decision Tree Analysis of the Relationship between Defects and Construction Inspection Grades

Chien-Liang Lin and Ching-Lung Fan
Abstract—Defects are an important indicator of project quality; moreover, eliminating defects is a key objective of project management. Therefore, using the appropriate analytical tools and methods, training and testing the defect data, and selecting the best algorithm for the defect feature are important. These steps can directly reveal the decision rules for each defect, and they can assist in determining key approaches to construction site management for effective defect prevention. In this study, a model obtained by using the chi-squared automatic interaction detection (CHAID) algorithm was validated, and its prediction benefits were calculated. A total of 499 defect types were retrieved from the Public Construction Management Information System in Taiwan and used as the foundation of a statistical analysis of 990 construction projects with 17,648 construction defects. First, a cluster analysis of inspection scores and defect frequencies was performed to reclassify and establish a new grade. Next, five rules were established for using the decision tree to classify defects and inspection grades. Finally, results revealed that the prediction accuracy of the CHAID algorithm was 75.45%. The five rules can be used for defect management and prevention strategies.

Index Terms—Decision tree, CHAID, defect, inspection grades.

Chien-Liang Lin is with the Department of Construction Engineering, National Kaohsiung of Science and Technology, 2 Jhuo-yue Rd., Nan-zih, 81164, Kaohsiung, Taiwan (e-mail: ken@nkfust.edu.tw).
Ching-Lung Fan is with Institute of Engineering Science and Technology, National Kaohsiung University of Science and Technology & Department of Civil Engineering, the Republic of China Military Academy,1 Wei-Wu Rd., Fengshan, 83059, Kaohsiung, Taiwan (e-mail: u0315916@ nkfust.edu.tw).


Cite: Chien-Liang Lin and Ching-Lung Fan, "Decision Tree Analysis of the Relationship between Defects and Construction Inspection Grades," International Journal of Materials, Mechanics and Manufacturing vol. 7, no. 1, pp. 27-32, 2019.

Copyright © 2008-2020. International Journal of Materials, Mechanics and Manufacturing. All rights reserved.
E-mail: ijmmm@ejournal.net