Research Article Hybridized Deep Learning Model for Perfobond Rib Shear Strength Connector Prediction Jamal Abdulrazzaq Khalaf , 1 Abeer A. Majeed , 2 Mohammed Suleman Aldlemy , 3 Zainab Hasan Ali , 4 Ahmed W. Al Zand , 5 S. Adarsh, 6 Aissa Bouaissi , 7,8 Mohammed Majeed Hameed , 9 and Zaher Mundher Yaseen 10 1 Civil Engineering Department, Collage of Engineering, University of Anbar, Ramadi, Iraq 2 Reconstruction and Projects Department, University of Baghdad, Baghdad, Iraq 3 Department of Mechanical Engineering, Collage of Mechanical Engineering Technology, Benghazi, Libya 4 College of Engineering, Civil Engineering Department, University of Diyala, Baquba, Iraq 5 Department of Civil Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia (UKM), UKM Bangi 43600, Selangor, Malaysia 6 Department of Civil Engineering, TKM College of Engineering Kollam, Kollam, India 7 School of Engineering, University of Plymouth, Plymouth PL4 8AA, UK 8 UNA Developments Ltd., Airport Business Center, Plymouth Devon PL6 7PP, UK 9 Department of Civil Engineering, Al-Maaref University College, Ramadi, Iraq 10 Faculty of Civil Engineering, Ton Duc ang University, Ho Chi Minh City, Vietnam CorrespondenceshouldbeaddressedtoZaherMundherYaseen;zaheryaseen88@gmail.com Received 30 November 2020; Revised 11 February 2021; Accepted 20 February 2021; Published 8 March 2021 AcademicEditor:MostafaAl-Emran Copyright © 2021 Jamal Abdulrazzaq Khalaf et al. is is an open access article distributed under the Creative Commons AttributionLicense,whichpermitsunrestricteduse,distribution,andreproductioninanymedium,providedtheoriginalworkis properly cited. AccurateandreliablepredictionofPerfobondRibShearStrengthConnector(PRSC)isconsideredasamajorissueinthestructural engineeringsector.Besides,selectingthemostsignificantvariablesthathaveamajorinfluenceonPRSCineveryimportantstepfor attaining economic and more accurate predictive models, this study investigates the capacity of deep learning neural network (DLNN) for shear strength prediction of PRSC. e 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. HybridizingAImodelswithGAasaselectortoolisanattempttoacquirethebestaccuracyofpredictionswiththefewestpossible related parameters. In accordance with quantitative analysis, it can be observed that the GA-DLNN models required only 7 input parametersandyieldedthebestpredictionaccuracywithhighestcorrelationcoefficient(R � 0.96)andlowestvaluerootmeansquare error(RMSE � 0.03936KN).However,theothercomparablemodelssuchasGA-M5Tree,GA-ANN,andGA-SVRrequired10input parameterstoobtainarelativelyacceptablelevelofaccuracy.EmployingGAasafeatureparameterselectiontechniqueimprovesthe precision of almost all hybrid models by optimally removing redundant variables which decrease the efficiency of the model. 1. Introduction Steel-concrete composite/hybrid systems have found wide application in several engineering works, due to the recent advancements in structural engineering. In this regard, the shear connector serves as an important component that ensuresthedevelopmentofcompositeactionsbyfacilitating the shear transfer between the concrete slab and the steel profile[1–3].Atthesite,conventionalshearconnectors(i.e., Nelson stud) are beneficial owing to their high level of automation;meanwhile,theyarepronetocertainproblems, especially, in structures that are subjected to stress [3–5]. When compared with other connectors, Nelson stud somehow exhibits low resistance which can lead to the Hindawi Complexity Volume 2021, Article ID 6611885, 21 pages https://doi.org/10.1155/2021/6611885