Networks

Researchers from Kyonggi University Report Details of New Studies and Findings in the Area of Automation Science

  2012 MAY 14 - (VerticalNews.com) -- "In tall building construction with reinforced concrete structures, the appropriate selection of the formwork method is a crucial factor in successful project completion. The selected formwork method significantly influences the project duration and cost as well as subsequent activities," scientists writing in the journal Automation in Construction report.

  "However, in practice, this selection has depended mainly on the subjective and intuitive opinions of practitioners with restricted experience. Therefore, we propose a formwork method selection model based on boosted decision trees to assist the practitioner's decision making. To evaluate its performance, the proposed model was compared with an artificial neural network model and a decision tree model. The results showed that the proposed model was slightly more accurate than the others in the selection of the formwork method," wrote Y. Shin and colleagues, Kyonggi University.

  The researchers concluded: "Moreover, the result also demonstrated the advantages of the new method, i.e., single parameter setting, accuracy and stability improvement, and a comprehensible process in decision making."

  Shin and colleagues published their study in Automation in Construction (A formwork method selection model based on boosted decision trees in tall building construction. Automation in Construction, 2012;23():47-54).

  Additional information can be obtained by contacting Y. Shin, Kyonggi Univ, Dept. of Plant Architectural Engn, Gyeonggi Do 443760, South Korea.

  The publisher of the journal Automation in Construction can be contacted at: Elsevier Science Bv, PO Box 211, 1000 Ae Amsterdam, Netherlands.

  Keywords: City:Gyeonggi Do, Country:South Korea, Region:Asia, Machine Learning, Automation Science, Emerging Technologies

  This article was prepared by VerticalNews Networks editors from staff and other reports. Copyright 2012, VerticalNews Networks via VerticalNews.com.