In:
PLOS ONE, Public Library of Science (PLoS), Vol. 15, No. 12 ( 2020-12-17), p. e0243030-
Abstract:
Determination of pile bearing capacity is essential in pile foundation design. This study focused on the use of evolutionary algorithms to optimize Deep Learning Neural Network (DLNN) algorithm to predict the bearing capacity of driven pile. For this purpose, a Genetic Algorithm (GA) was developed to select the most significant features in the raw dataset. After that, a GA-DLNN hybrid model was developed to select optimal parameters for the DLNN model, including: network algorithm, activation function for hidden neurons, number of hidden layers, and the number of neurons in each hidden layer. A database containing 472 driven pile static load test reports was used. The dataset was divided into three parts, namely the training set (60%), validation (20%) and testing set (20%) for the construction, validation and testing phases of the proposed model, respectively. Various quality assessment criteria, namely the coefficient of determination (R 2 ), Index of Agreement (IA), mean absolute error (MAE) and root mean squared error (RMSE), were used to evaluate the performance of the machine learning (ML) algorithms. The GA-DLNN hybrid model was shown to exhibit the ability to find the most optimal set of parameters for the prediction process.The results showed that the performance of the hybrid model using only the most critical features gave the highest accuracy, compared with those obtained by the hybrid model using all input variables.
Type of Medium:
Online Resource
ISSN:
1932-6203
DOI:
10.1371/journal.pone.0243030
DOI:
10.1371/journal.pone.0243030.g001
DOI:
10.1371/journal.pone.0243030.g002
DOI:
10.1371/journal.pone.0243030.g003
DOI:
10.1371/journal.pone.0243030.g004
DOI:
10.1371/journal.pone.0243030.g005
DOI:
10.1371/journal.pone.0243030.g006
DOI:
10.1371/journal.pone.0243030.g007
DOI:
10.1371/journal.pone.0243030.g008
DOI:
10.1371/journal.pone.0243030.g009
DOI:
10.1371/journal.pone.0243030.g010
DOI:
10.1371/journal.pone.0243030.g011
DOI:
10.1371/journal.pone.0243030.t001
DOI:
10.1371/journal.pone.0243030.t002
DOI:
10.1371/journal.pone.0243030.t003
DOI:
10.1371/journal.pone.0243030.t004
DOI:
10.1371/journal.pone.0243030.t005
DOI:
10.1371/journal.pone.0243030.t006
DOI:
10.1371/journal.pone.0243030.t007
DOI:
10.1371/journal.pone.0243030.t008
DOI:
10.1371/journal.pone.0243030.t009
DOI:
10.1371/journal.pone.0243030.t010
DOI:
10.1371/journal.pone.0243030.t011
DOI:
10.1371/journal.pone.0243030.t012
DOI:
10.1371/journal.pone.0243030.t013
DOI:
10.1371/journal.pone.0243030.s001
DOI:
10.1371/journal.pone.0243030.s002
DOI:
10.1371/journal.pone.0243030.r001
DOI:
10.1371/journal.pone.0243030.r002
DOI:
10.1371/journal.pone.0243030.r003
DOI:
10.1371/journal.pone.0243030.r004
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2020
detail.hit.zdb_id:
2267670-3
Permalink