Combining machine learning models via adaptive ensemble weighting for prediction of shear capacity of reinforced-concrete deep beams

This study presents a novel artificial intelligence (AI) technique based on two support vector machine (SVM) models and symbiotic organisms search (SOS) algorithm, called “optimized support vector machines with adaptive ensemble weighting” (OSVM-AEW), to predict the shear capacity of reinforced-concrete (RC) deep beams. This ensemble learning-based system combines two supervised learning models—the support vector machine (SVM) and least-squares support vector machine (LS-SVM)—with the SOS optimization algorithm as the optimizer. In OSVM-AEW, SOS is integrated to simultaneously select the optimal parameters of SVM and LS-SVM, and control the coordination process of the learning outputs. Experimental results show that OSVM-AEW achieves the greatest evaluation criteria for coefficient of correlation (0.9620), coefficient of determination (0.9254), mean absolute error (0.3854 MPa), mean absolute percentage error (7.68%), and root-mean-squared error (0.5265 MPa). This paper demonstrates the successful application of OSVM-AEW as an efficient tool for helping structural engineers in the RC deep beams design process.

[1]  F. Kong,et al.  WEB REINFORCEMENT EFFECTS ON DEEP BEAMS , 1970 .

[2]  M. Hajihassani,et al.  Prediction of building damage induced by tunnelling through an optimized artificial neural network , 2019, Engineering with Computers.

[3]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[4]  James K. Wight,et al.  Strength of Struts in Deep Concrete Members Designed Using Strut-and-Tie Method , 2006 .

[5]  Nhat-Duc Hoang,et al.  Hybrid artificial intelligence approach based on metaheuristic and machine learning for slope stability assessment: A multinational data analysis , 2016, Expert Syst. Appl..

[6]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[7]  Hossam Faris,et al.  A multi-verse optimizer approach for feature selection and optimizing SVM parameters based on a robust system architecture , 2017, Neural Computing and Applications.

[8]  T. Hancock,et al.  A performance comparison of modern statistical techniques for molecular descriptor selection and retention prediction in chromatographic QSRR studies , 2005 .

[9]  Nantiwat Pholdee,et al.  Structural optimization using multi-objective modified adaptive symbiotic organisms search , 2019, Expert Syst. Appl..

[10]  Nguyen Quoc Thanh,et al.  Spatial prediction of rainfall-induced landslides for the Lao Cai area (Vietnam) using a hybrid intelligent approach of least squares support vector machines inference model and artificial bee colony optimization , 2017, Landslides.

[11]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[12]  Daniel A. Kuchma,et al.  Strut-and-Tie Model Analysis for Strength Prediction of Deep Beams , 2007 .

[13]  Ezugwu E. Absalom,et al.  Symbiotic organisms search algorithm: Theory, recent advances and applications , 2019, Expert Syst. Appl..

[14]  M. Chenga,et al.  Modeling the Permanent Deformation Behavior of Asphalt Mixtures Using a Novel Hybrid Computational Intelligence , 2016 .

[15]  Sumit Kumar,et al.  Modified symbiotic organisms search for structural optimization , 2018, Engineering with Computers.

[16]  Min-Yuan Cheng,et al.  Predicting productivity loss caused by change orders using the evolutionary fuzzy support vector machine inference model , 2015 .

[17]  Seyed Mohammad Mirjalili,et al.  Truss optimization with natural frequency bounds using improved symbiotic organisms search , 2017, Knowl. Based Syst..

[18]  Nhat-Duc Hoang,et al.  Prediction of soil compression coefficient for urban housing project using novel integration machine learning approach of swarm intelligence and Multi-layer Perceptron Neural Network , 2018, Adv. Eng. Informatics.

[19]  Min-Yuan Cheng,et al.  A self-tuning least squares support vector machine for estimating the pavement rutting behavior of asphalt mixtures , 2019, Soft Comput..

[20]  Hossam Faris,et al.  Simultaneous Feature Selection and Support Vector Machine Optimization Using the Grasshopper Optimization Algorithm , 2018, Cognitive Computation.

[21]  Sujin Bureerat,et al.  Topology and Size Optimization of Trusses with Static and Dynamic Bounds by Modified Symbiotic Organisms Search , 2018, J. Comput. Civ. Eng..

[22]  Min-Yuan Cheng,et al.  Prediction of permanent deformation in asphalt pavements using a novel symbiotic organisms search–least squares support vector regression , 2018, Neural Computing and Applications.

[23]  K. N. Smith,et al.  Shear Strength of Deep Beams , 1982 .

[24]  Min-Yuan Cheng,et al.  Prediction of Concrete Compressive Strength from Early Age Test Result Using an Advanced Metaheuristic-Based Machine Learning Technique , 2017 .

[25]  Min-Yuan Cheng,et al.  Symbiotic Organisms Search: A new metaheuristic optimization algorithm , 2014 .

[26]  Jui-Sheng Chou,et al.  Optimizing the Prediction Accuracy of Concrete Compressive Strength Based on a Comparison of Data-Mining Techniques , 2011, J. Comput. Civ. Eng..

[27]  Amir Hossein Alavi,et al.  An empirical model for shear capacity of RC deep beams using genetic-simulated annealing , 2013 .

[28]  Kang Hai Tan,et al.  A STRUT-AND-TIE MODEL FOR DEEP BEAMS SUBJECTED TO COMBINED TOP-AND-BOTTOM LOADING , 1997 .

[29]  T. N. Singh,et al.  Regression-based models for the prediction of unconfined compressive strength of artificially structured soil , 2017, Engineering with Computers.

[30]  Doddy Prayogo,et al.  Optimizing the Prediction Accuracy of Friction Capacity of Driven Piles in Cohesive Soil Using a Novel Self-Tuning Least Squares Support Vector Machine , 2018 .

[31]  Vivek K. Patel,et al.  Adaptive symbiotic organisms search (SOS) algorithm for structural design optimization , 2016, J. Comput. Des. Eng..

[32]  Mahesh Pal,et al.  Support vector regression based shear strength modelling of deep beams , 2011 .

[33]  Jui-Sheng Chou,et al.  Predicting Disputes in Public-Private Partnership Projects: Classification and Ensemble Models , 2013, J. Comput. Civ. Eng..

[34]  Sung-Woo Shin,et al.  Shear Strength of Reinforced High-Strength Concrete Deep Beams , 2001 .

[35]  James K. Wight,et al.  Experimental Evaluation of Design Procedures for Shear Strength of Deep Reinforced Concrete Beams , 2002 .

[36]  Nhat-Duc Hoang,et al.  Groutability estimation of grouting processes with cement grouts using Differential Flower Pollination Optimized Support Vector Machine , 2016, Appl. Soft Comput..

[37]  Nantiwat Pholdee,et al.  Multiobjective adaptive symbiotic organisms search for truss optimization problems , 2018, Knowl. Based Syst..

[38]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[39]  Jui-Sheng Chou,et al.  Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength , 2013 .

[40]  Arthur P. Clark.  Diagonal Tension in Reinforced Concrete Beams , 1951 .

[41]  Nhat-Duc Hoang,et al.  Predicting earthquake-induced soil liquefaction based on a hybridization of kernel Fisher discriminant analysis and a least squares support vector machine: a multi-dataset study , 2018, Bulletin of Engineering Geology and the Environment.

[42]  Masoud Rais-Rohani,et al.  Ensemble of Metamodels with Optimized Weight Factors , 2008 .

[43]  K. Tan,et al.  High-strength concrete deep beams with effective span and shear span variations , 1995 .

[44]  R. Shah,et al.  Least Squares Support Vector Machines , 2022 .

[45]  Johan A. K. Suykens,et al.  LS-SVMlab Toolbox User's Guide version 1.7 , 2003 .

[46]  Min-Yuan Cheng,et al.  High-performance concrete compressive strength prediction using Genetic Weighted Pyramid Operation Tree (GWPOT) , 2014, Eng. Appl. Artif. Intell..

[47]  Min-Yuan Cheng,et al.  Optimization model for construction project resource leveling using a novel modified symbiotic organisms search , 2018 .

[48]  Jui-Sheng Chou,et al.  Peak Shear Strength of Discrete Fiber-Reinforced Soils Computed by Machine Learning and Metaensemble Methods , 2016, J. Comput. Civ. Eng..

[49]  Julio A. Ramirez,et al.  DETAILING OF STIRRUP REINFORCEMENT , 1989 .

[50]  Kang Hai Tan,et al.  Interactive Mechanical Model for Shear Strength of Deep Beams , 2004 .

[51]  Min-Yuan Cheng,et al.  Novel Genetic Algorithm-Based Evolutionary Support Vector Machine for Optimizing High-Performance Concrete Mixture , 2014, J. Comput. Civ. Eng..

[52]  Dinesh Mavaluru,et al.  Applying several soft computing techniques for prediction of bearing capacity of driven piles , 2019, Engineering with Computers.

[53]  Yu-Ren Wang,et al.  Predicting construction cost and schedule success using artificial neural networks ensemble and support vector machines classification models , 2012 .