Cover Image

Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms

Effective prediction of the peak shear strength (PSS) is of crucial importance in evaluating the stability of a rock slope with interlayered rocks and has both theoretical and practical significance. This paper offers two novel prediction tools for the PSS prediction based on radial basis function n...

Full description

Saved in:
Bibliographic Details
Main Authors: Gao, Juncheng, Nait Amar, Menad, Motahari, Mohammad Reza, Hasanipanah, Mahdi, Jahed Armaghani, Danial
Format: Article
Published: Springer Verlag 2022
Online Access:http://eprints.um.edu.my/33869/
https://doi.org/10.1007/s00366-020-01059-y
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.33869
record_format eprints
spelling my.um.eprints.338692024-11-12T02:43:12Z http://eprints.um.edu.my/33869/ Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms Gao, Juncheng Nait Amar, Menad Motahari, Mohammad Reza Hasanipanah, Mahdi Jahed Armaghani, Danial Effective prediction of the peak shear strength (PSS) is of crucial importance in evaluating the stability of a rock slope with interlayered rocks and has both theoretical and practical significance. This paper offers two novel prediction tools for the PSS prediction based on radial basis function neural network (RBFNN) and meta-heuristic computing paradigms. For this work, the gray wolf optimization (GWO) and ant colony optimization (ACO) algorithms were used to select the optimal parameters of RBFNN. Then, these two new models were compared with the gene expression programming (GEP) model. A total of 158 experimental data were used to train and test the proposed models using three input parameters, i.e., normal stress, compressive strength ratio of joint walls, and joint roughness coefficient. Finally, the computational result revealed that the RBFNN-GWO model, with the coefficient of determination (R-2) of 0.997, produced a better convergence speed and higher accuracy compared with RBFNN-ACO and GEP models, with the R-2 of 0.995 and 0.996, respectively. The RBFNN-GWO model was found an efficient predictive tool that can help rock engineers in the slopes design processes. Springer Verlag 2022-02 Article PeerReviewed Gao, Juncheng and Nait Amar, Menad and Motahari, Mohammad Reza and Hasanipanah, Mahdi and Jahed Armaghani, Danial (2022) Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms. Engineering with Computers, 38 (1). pp. 129-140. ISSN 0177-0667, DOI https://doi.org/10.1007/s00366-020-01059-y <https://doi.org/10.1007/s00366-020-01059-y>. https://doi.org/10.1007/s00366-020-01059-y 10.1007/s00366-020-01059-y
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
description Effective prediction of the peak shear strength (PSS) is of crucial importance in evaluating the stability of a rock slope with interlayered rocks and has both theoretical and practical significance. This paper offers two novel prediction tools for the PSS prediction based on radial basis function neural network (RBFNN) and meta-heuristic computing paradigms. For this work, the gray wolf optimization (GWO) and ant colony optimization (ACO) algorithms were used to select the optimal parameters of RBFNN. Then, these two new models were compared with the gene expression programming (GEP) model. A total of 158 experimental data were used to train and test the proposed models using three input parameters, i.e., normal stress, compressive strength ratio of joint walls, and joint roughness coefficient. Finally, the computational result revealed that the RBFNN-GWO model, with the coefficient of determination (R-2) of 0.997, produced a better convergence speed and higher accuracy compared with RBFNN-ACO and GEP models, with the R-2 of 0.995 and 0.996, respectively. The RBFNN-GWO model was found an efficient predictive tool that can help rock engineers in the slopes design processes.
format Article
author Gao, Juncheng
Nait Amar, Menad
Motahari, Mohammad Reza
Hasanipanah, Mahdi
Jahed Armaghani, Danial
spellingShingle Gao, Juncheng
Nait Amar, Menad
Motahari, Mohammad Reza
Hasanipanah, Mahdi
Jahed Armaghani, Danial
Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms
author_facet Gao, Juncheng
Nait Amar, Menad
Motahari, Mohammad Reza
Hasanipanah, Mahdi
Jahed Armaghani, Danial
author_sort Gao, Juncheng
title Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms
title_short Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms
title_full Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms
title_fullStr Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms
title_full_unstemmed Two novel combined systems for predicting the peak shear strength using RBFNN and meta-heuristic computing paradigms
title_sort two novel combined systems for predicting the peak shear strength using rbfnn and meta-heuristic computing paradigms
publisher Springer Verlag
publishDate 2022
url http://eprints.um.edu.my/33869/
https://doi.org/10.1007/s00366-020-01059-y
_version_ 1816130383703441408
score 13.223943

Similar Items