Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector Prediction

Accurate and reliable prediction of Perfobond Rib Shear Strength Connector (PRSC) is considered as a major issue in the structural engineering sector. Besides, selecting the most significant variables that have a major influence on PRSC in every important step for attaining economic and more accurat...

Full description

Saved in:
Bibliographic Details
Main Authors: Jamal Abdulrazzaq Khalaf, Abeer A. Majeed, Mohammed Suleman Aldlemy, Zainab Hasan Ali, Ahmed W. Al Zand, S. Adarsh, Aissa Bouaissi, Mohammed Majeed Hameed, Zaher Mundher Yaseen
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2021/6611885
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849692746335387648
author Jamal Abdulrazzaq Khalaf
Abeer A. Majeed
Mohammed Suleman Aldlemy
Zainab Hasan Ali
Ahmed W. Al Zand
S. Adarsh
Aissa Bouaissi
Mohammed Majeed Hameed
Zaher Mundher Yaseen
author_facet Jamal Abdulrazzaq Khalaf
Abeer A. Majeed
Mohammed Suleman Aldlemy
Zainab Hasan Ali
Ahmed W. Al Zand
S. Adarsh
Aissa Bouaissi
Mohammed Majeed Hameed
Zaher Mundher Yaseen
author_sort Jamal Abdulrazzaq Khalaf
collection DOAJ
description Accurate and reliable prediction of Perfobond Rib Shear Strength Connector (PRSC) is considered as a major issue in the structural engineering sector. Besides, selecting the most significant variables that have a major influence on PRSC in every important step for attaining economic and more accurate predictive models, this study investigates the capacity of deep learning neural network (DLNN) for shear strength prediction of PRSC. The proposed DLNN model is validated against support vector regression (SVR), artificial neural network (ANN), and M5 tree model. In the second scenario, a comparable AI model hybridized with genetic algorithm (GA) as a robust bioinspired optimization approach for optimizing the related predictors for the PRSC is proposed. Hybridizing AI models with GA as a selector tool is an attempt to acquire the best accuracy of predictions with the fewest possible related parameters. In accordance with quantitative analysis, it can be observed that the GA-DLNN models required only 7 input parameters and yielded the best prediction accuracy with highest correlation coefficient (R = 0.96) and lowest value root mean square error (RMSE = 0.03936 KN). However, the other comparable models such as GA-M5Tree, GA-ANN, and GA-SVR required 10 input parameters to obtain a relatively acceptable level of accuracy. Employing GA as a feature parameter selection technique improves the precision of almost all hybrid models by optimally removing redundant variables which decrease the efficiency of the model.
format Article
id doaj-art-9275f2625df04f4db9866f2c4798dafa
institution DOAJ
issn 1076-2787
1099-0526
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-9275f2625df04f4db9866f2c4798dafa2025-08-20T03:20:37ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/66118856611885Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector PredictionJamal Abdulrazzaq Khalaf0Abeer A. Majeed1Mohammed Suleman Aldlemy2Zainab Hasan Ali3Ahmed W. Al Zand4S. Adarsh5Aissa Bouaissi6Mohammed Majeed Hameed7Zaher Mundher Yaseen8Civil Engineering Department, Collage of Engineering, University of Anbar, Ramadi, IraqReconstruction and Projects Department, University of Baghdad, Baghdad, IraqDepartment of Mechanical Engineering, Collage of Mechanical Engineering Technology, Benghazi, LibyaCollege of Engineering, Civil Engineering Department, University of Diyala, Baquba, IraqDepartment of Civil Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia (UKM), UKM Bangi 43600, Selangor, MalaysiaDepartment of Civil Engineering, TKM College of Engineering Kollam, Kollam, IndiaSchool of Engineering, University of Plymouth, Plymouth PL4 8AA, UKDepartment of Civil Engineering, Al-Maaref University College, Ramadi, IraqFaculty of Civil Engineering, Ton Duc Thang University, Ho Chi Minh City, VietnamAccurate and reliable prediction of Perfobond Rib Shear Strength Connector (PRSC) is considered as a major issue in the structural engineering sector. Besides, selecting the most significant variables that have a major influence on PRSC in every important step for attaining economic and more accurate predictive models, this study investigates the capacity of deep learning neural network (DLNN) for shear strength prediction of PRSC. The proposed DLNN model is validated against support vector regression (SVR), artificial neural network (ANN), and M5 tree model. In the second scenario, a comparable AI model hybridized with genetic algorithm (GA) as a robust bioinspired optimization approach for optimizing the related predictors for the PRSC is proposed. Hybridizing AI models with GA as a selector tool is an attempt to acquire the best accuracy of predictions with the fewest possible related parameters. In accordance with quantitative analysis, it can be observed that the GA-DLNN models required only 7 input parameters and yielded the best prediction accuracy with highest correlation coefficient (R = 0.96) and lowest value root mean square error (RMSE = 0.03936 KN). However, the other comparable models such as GA-M5Tree, GA-ANN, and GA-SVR required 10 input parameters to obtain a relatively acceptable level of accuracy. Employing GA as a feature parameter selection technique improves the precision of almost all hybrid models by optimally removing redundant variables which decrease the efficiency of the model.http://dx.doi.org/10.1155/2021/6611885
spellingShingle Jamal Abdulrazzaq Khalaf
Abeer A. Majeed
Mohammed Suleman Aldlemy
Zainab Hasan Ali
Ahmed W. Al Zand
S. Adarsh
Aissa Bouaissi
Mohammed Majeed Hameed
Zaher Mundher Yaseen
Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector Prediction
Complexity
title Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector Prediction
title_full Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector Prediction
title_fullStr Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector Prediction
title_full_unstemmed Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector Prediction
title_short Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector Prediction
title_sort hybridized deep learning model for perfobond rib shear strength connector prediction
url http://dx.doi.org/10.1155/2021/6611885
work_keys_str_mv AT jamalabdulrazzaqkhalaf hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction
AT abeeramajeed hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction
AT mohammedsulemanaldlemy hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction
AT zainabhasanali hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction
AT ahmedwalzand hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction
AT sadarsh hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction
AT aissabouaissi hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction
AT mohammedmajeedhameed hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction
AT zahermundheryaseen hybridizeddeeplearningmodelforperfobondribshearstrengthconnectorprediction