Universiti Teknologi Malaysia Institutional Repository

Novel metaheuristic classification approach in developing mathematical model-based solutions predicting failure in shallow footing

Moayedi, Hossein and Nguyen, Hoang and A. Rashid, Ahmad Safuan (2021) Novel metaheuristic classification approach in developing mathematical model-based solutions predicting failure in shallow footing. Engineering with Computers, 37 (1). pp. 223-230. ISSN 0177-0667

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1007/s00366-019-00819-9

Abstract

This study evaluated and compared several novel classification approaches to develop the most reliable stability model-based solution in the prediction of shallow footing’s allowable settlement. By applying the biogeography-based algorithm, this study presents an optimized metaheuristic classification approach with mathematical-based multi-layer perceptron neural network and fuzzy inference system to achieve a better assessment of the recognition of a complex failure phenomenon. By the contribution of a large number of finite element simulation, and considering seven key factors, the settlement of a shallow footing placed on a two-layered soil was measured as the target variable. Then, to change into the classification method, two overall situations of stability or failure were considered for the proposed soil layer. The ensemble of BBO–MLP and BBO–FIS are developed, and the results are evaluated by well-known accuracy indices. The results showed that employing BBO helps both MLP and FIS to have a better analysis. Besides, referring to the obtained total ranking scores of 6, 5, 11, and 8, respectively, for the MLP, FIS, BBO–MLP, and BBO–FIS, the BBO–MLP found to be the most accurate model, followed by BBO–FIS, MLP, and FIS.

Item Type:Article
Uncontrolled Keywords:Hybrid, Metaheuristic classification
Subjects:T Technology > TA Engineering (General). Civil engineering (General)
Divisions:Civil Engineering
ID Code:95107
Deposited By: Widya Wahid
Deposited On:29 Apr 2022 22:24
Last Modified:29 Apr 2022 22:24

Repository Staff Only: item control page