TY - JOUR
T1 - A formwork method selection model based on boosted decision trees in tall building construction
AU - Shin, Yoonseok
AU - Kim, Taehoon
AU - Cho, Hunhee
AU - Kang, Kyung In
N1 - Funding Information:
This research was supported by a grant(code#09 R&D A01) from High-Tech Urban Development Program funded by the Ministry of land, transport and maritime affairs. Also, this research was supported by a Korea University Grant.
PY - 2012/5
Y1 - 2012/5
N2 - 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. 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. 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.
AB - 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. 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. 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.
KW - Boosted decision tree
KW - Formwork method
KW - Tall building construction
UR - http://www.scopus.com/inward/record.url?scp=84863258220&partnerID=8YFLogxK
U2 - 10.1016/j.autcon.2011.12.007
DO - 10.1016/j.autcon.2011.12.007
M3 - Article
AN - SCOPUS:84863258220
VL - 23
SP - 47
EP - 54
JO - Automation in Construction
JF - Automation in Construction
SN - 0926-5805
ER -