Application of AdaBoost to the Retaining Wall Method Selection in Construction

Abstract

The appropriate selection of construction methods is a critical factor in the successful completion of any construction project. Artificial intelligence techniques are widely used to assist in the selection of a construction method. This paper proposes the use of the adaptive boosting (AdaBoost) model to select an appropriate retaining wall method suitable for particular construction site conditions, in order to examine the applicability of AdaBoost in construction method selection. To verify its applicability, the proposed model was compared with a support vector machine (SVM) model, which have been attracting attention for their high performance in various classification problems. The AdaBoost model showed a slightly more accurate result than the SVM model in the selection of retaining wall methods, demonstrating that AdaBoost has advantages (e.g., robustness against defective data with missing values) in application to decision support systems. Moreover, the AdaBoost model can be used in future projects to assist engineers in determining the appropriate construction method, such as a retaining wall method, at an early stage of the project.