Determination of ultimate bearing capacity of shallow foundations using LSSVM algorithm

Autor: Xinhua Xue, Xin Chen
Jazyk: angličtina
Rok vydání: 2019
Předmět:
Zdroj: Journal of Civil Engineering and Management, Vol 25, Iss 5 (2019)
Druh dokumentu: article
ISSN: 1392-3730
1822-3605
DOI: 10.3846/jcem.2019.9875
Popis: Accurate determination of the ultimate bearing capacity (UBC) of shallow foundations is vital for the safety of structures and buildings. Due to the inherent spatial variability characteristics of soil properties, some new approaches are needed to accurately determine the UBC of shallow foundations. The objective of this study is to develop a hybrid least squares support vector machine (LSSVM) and an improved particle swarm optimization (IPSO) algorithm for determining the UBC of shallow foundations. To validate the hybrid IPSO-LSSVM model, a comparison of the predictions was carried out among different models and theoretical methods. Three statistical indexes, namely the root-mean-square error (RMSE), the mean absolute error (MAE) and the correlation coefficient (R) were employed to measure and evaluate the performance of these models. The results showed that the developed hybrid IPSO-LSSVM model can be used for determining the UBC of shallow foundations with high accuracy.
Databáze: Directory of Open Access Journals