Access the full text.
Sign up today, get DeepDyve free for 14 days.
S. Massari, Marcello Ruberti (2013)
Rare earth elements as critical raw materials: Focus on international markets and future strategiesResources Policy, 38
M. Safiuddin, M. Jumaat, M. Salam, Mohammad Islam, R. Hashim (2010)
Utilization of solid wastes in construction materialsInternational Journal of Physical Sciences, 5
P. Mehta (2000)
Point of view : Reflections about technology choices
Ayaz Ahmad, F. Farooq, P. Niewiadomski, K. Ostrowski, Arslan Akbar, Fahid Aslam, Rayed Alyousef (2021)
Prediction of Compressive Strength of Fly Ash Based Concrete Using Individual and Ensemble AlgorithmMaterials, 14
M. Etxeberria, E. Vázquez, A. Marí, M. Barra (2007)
Influence of Amount of Recycled Coarse Aggregates and Production Process on Properties of Recycled Aggregate ConcreteCement and Concrete Research, 37
Muzaffer Tüfekçi, Ö. Çakır (2017)
An Investigation on Mechanical and Physical Properties of Recycled Coarse Aggregate (RCA) Concrete with GGBFSInternational Journal of Civil Engineering, 15
Xiao Jian-zhuang (2006)
Investigation on the Tensile Behavior of Recycled Aggregate ConcreteJournal of Building Materials
Xuping Li (2008)
Recycling and reuse of waste concrete in China: Part I. Material behaviour of recycled aggregate concreteResources Conservation and Recycling, 53
Mehran Khan, M. Ali (2016)
Use of glass and nylon fibers in concrete for controlling early age micro cracking in bridge decksConstruction and Building Materials, 125
(2021)
Reflections about technology choices
Steffen Lehmann (2011)
Optimizing Urban Material Flows and Waste Streams in Urban Development through Principles of Zero Waste and Sustainable ConsumptionSustainability, 3
P. Cachim (2009)
Mechanical properties of brick aggregate concreteConstruction and Building Materials, 23
Farshid Maghool, A. Arulrajah, Yan-jun Du, S. Horpibulsuk, A. Chinkulkijniwat (2017)
Environmental impacts of utilizing waste steel slag aggregates as recycled road construction materialsClean Technologies and Environmental Policy, 19
H. Mikulčić, J. Klemeš, M. Vujanovic, K. Urbaniec, N. Duić (2016)
Reducing Greenhouse Gasses Emissions by Fostering the Deployment of Alternative Raw Materials and Energy Sources in the Cleaner Cement Manufacturing ProcessJournal of Cleaner Production, 136
S. Northey, G. Mudd, T. Werner (2018)
Unresolved Complexity in Assessments of Mineral Resource Depletion and AvailabilityNatural Resources Research, 27
(2004)
Assessment of recycled aggregate structural suitability for road construction Study on Mechanical Behavior of Recycled Aggregate Concrete
Ayaz Ahmad, F. Farooq, K. Ostrowski, Klaudia Śliwa-Wieczorek, S. Czarnecki (2021)
Application of Novel Machine Learning Techniques for Predicting the Surface Chloride Concentration in Concrete Containing Waste MaterialMaterials, 14
(2004)
Study on Mechanical Behavior of Recycled Aggregate Concrete
A. Padmini, K. Ramamurthy, M. Mathews (2009)
Influence of parent concrete on the properties of recycled aggregate concreteConstruction and Building Materials, 23
T. Naik (2008)
Sustainability of Concrete ConstructionPractice Periodical on Structural Design and Construction, 13
How-Ji Chen, T. Yen, Kuan-Hung Chen (2003)
Use of building rubbles as recycled aggregatesCement and Concrete Research, 33
(2001)
Assessment of recycled aggregate structural suitability for road construction
Miao Su, Qingyu Zhong, Hui Peng, Shaofan Li (2020)
Selected machine learning approaches for predicting the interfacial bond strength between FRPs and concreteConstruction and Building Materials
J. Khatib (2005)
Properties of concrete incorporating fine recycled aggregateCement and Concrete Research, 35
Xiao Jian-zhuang (2005)
Study on Relationships between Strength Indexes of Recycled ConcreteJournal of Building Materials
S. Arshad, M. Sharif, Muhammad Irfan-ul-Hassan, Mehran Khan, Jiao-Long Zhang (2020)
Efficiency of Supplementary Cementitious Materials and Natural Fiber on Mechanical Performance of ConcreteArabian Journal for Science and Engineering, 45
I. Marie, Hisham Quiasrawi (2012)
Closed-loop recycling of recycled concrete aggregatesJournal of Cleaner Production, 37
V. Tam, C. Tam, Yongli Wang (2007)
Optimization on proportion for recycled aggregate in concrete using two-stage mixing approachConstruction and Building Materials, 21
K. Rahal (2007)
Mechanical properties of concrete with recycled coarse aggregateBuilding and Environment, 42
K. Nguyen, Quang Nguyen, T. Le, Jiuk Shin, Kihak Lee (2020)
Analyzing the compressive strength of green fly ash based geopolymer concrete using experiment and machine learning approachesConstruction and Building Materials, 247
Yi-Fang Cao, Z. Tao, Z. Pan, R. Wuhrer (2018)
Effect of calcium aluminate cement on geopolymer concrete cured at ambient temperatureConstruction and Building Materials
(2013)
Recycled concrete. In Progress of Recycling in the Built Environment; RILEM State-of-the-Art Reports
Mehran Khan, M. Cao, M. Ali (2018)
Effect of basalt fibers on mechanical properties of calcium carbonate whisker-steel fiber reinforced concreteConstruction and Building Materials
S. Tabsh, A. Abdelfatah (2009)
Influence of recycled concrete aggregates on strength properties of concreteConstruction and Building Materials, 23
M. Santos, J. Brito, A. Silva, A. Hawreen (2020)
Effect of the source concrete with ASR degradation on the mechanical and physical properties of coarse recycled aggregateCement & Concrete Composites, 111
A. Buck (1976)
Recycled concrete as a source of aggregate
Article Compressive Strength Prediction via Gene Expression Programming (GEP) and Artificial Neural Network (ANN) for Concrete Containing RCA 1,2 3, 1 1 4 5 Ayaz Ahmad , Krisada Chaiyasarn *, Furqan Farooq , Waqas Ahmad , Suniti Suparp and Fahid Aslam Department of Civil Engineering, Abbottabad Campus, COMSATS University Islamabad, Islamabad 22060, Pakistan; ayazahmad@cuiatd.edu.pk (A.A.); furqan@cuiatd.edu.pk (F.F.); waqasahmad@cuiatd.edu.pk (W.A.) Faculty of Civil Engineering, Cracow University of Technology, 24 Warszawska Str., 31‐155 Cracow, Poland Faculty of Civil Engineering, Thammasat University Rangsit, Klong Luang Pathumthani, Pathum Thani 12121, Thailand Department of Civil and Environmental Engineering, Faculty of Engineering, Srinakharinwirot University, Bangkok 10110, Thailand; suniti@g.swu.ac.th Department of Civil Engineering, College of Engineering, Al‐Kharj 11942, Saudi Arabia; f.aslam@psau.edu.sa * Correspondence: ckrisada@engr.tu.ac.th Abstract: To minimize the environmental risks and for sustainable development, the utilization of recycled aggregate (RA) is gaining popularity all over the world. The use of recycled coarse aggre‐ gate (RCA) in concrete is an effective way to minimize environmental pollution. RCA does not gain more attraction because of the availability of adhered mortar on its surface, which poses a harmful effect on the properties of concrete. However, a suitable mix design for RCA enables it to reach the Citation: Ahmad, A.; Chaiyasarn, K.; targeted strength and be applicable for a wide range of construction projects. The targeted strength Farooq, F.; Ahmad, W.; Suparp, S.; achievement from the proposed mix design at a laboratory is also a time‐consuming task, which Aslam, F. Compressive Strength Prediction via Gene Expression may cause a delay in the construction work. To overcome this flaw, the application of supervised Programming (GEP) and Artificial machine learning (ML) algorithms, gene expression programming (GEP), and artificial neural net‐ Neural Network (ANN) for work (ANN) was employed in this study to predict the compressive strength of RCA‐based con‐ Concrete Containing RCA. Buildings crete. The linear coefficient correlation (R ), mean absolute error (MAE), mean square error (MSE), 2021, 11, 324. https://doi.org/ and root mean square error (RMSE) were evaluated to investigate the performance of the models. 10.3390/buildings11080324 The k‐fold cross‐validation method was also adopted for the confirmation of the model’s perfor‐ mance. In comparison, the GEP model was more effective in terms of prediction by giving a higher Academic Editor: Emanuele Brunesi 2 2 correlation (R ) value of 0.95 as compared to ANN, which gave a value of R equal to 0.92. In addi‐ tion, a sensitivity analysis was conducted to know about the contribution level of each parameter Received: 27 June 2021 used to run the models. Moreover, the increment in data points and the use of other supervised ML Accepted: 24 July 2021 approaches like boosting, gradient boosting, and bagging to forecast the compressive strength, Published: 27 July 2021 would give a better response. Publisher’s Note: MDPI stays neu‐ tral with regard to jurisdictional Keywords: recycled coarse aggregate; cement; concrete; gene expression programming; artificial claims in published maps and institu‐ neural network; machine learning tional affiliations. 1. Introduction Copyright: © 2021 by the authors. Li‐ The utilization trend of aggregate obtained from natural resources increases sharply censee MDPI, Basel, Switzerland. from the increased manufacturing and usage of concrete in the construction sectors [1,2]. This article is an open access article The largest consumers of the natural aggregates are construction industries [3]. A total of distributed under the terms and con‐ 15 billion tons of concrete material is produced worldwide, which equates to about two ditions of the Creative Commons At‐ tons of concrete per resident per annum [4]. To reduce this flaw and manage this demand, tribution (CC BY) license (http://crea‐ tivecommons.org/licenses/by/4.0/). the origin of good quality natural aggregates is significantly reducing worldwide [5]. The Buildings 2021, 11, 324. https://doi.org/10.3390/buildings11080324 www.mdpi.com/journal/buildings Buildings 2021, 11, 324 2 of 18 approximate amount of aggregate used in the European Union countries has reached two billion each year. The activities related to construction demand a high number of natural materials to produce cement and aggregate. However, the construction sectors are an enormous consumer of natural resources, producing huge amounts of waste [6]. The ap‐ plication of raw materials in the construction industry is the key factor that causes envi‐ ronmental risks and pollution to earth [7]. The usage of raw materials has also led to the depletion of minerals as well as natural resources [8]. Resources including cement, fine aggregate, and coarse aggregate will be at a deprived status because these resources can‐ not manage the increasing demand in the construction industry [9]. Furthermore, sustain‐ able waste management is one of the most crucial matters experienced by the world. Therefore, to minimize the environmental impact and energy consistency of concrete ap‐ plied to construction work, the utilization of demolition and construction wastes can be favorable for a sustainable engineering approach for the mixed design of concrete. The use of recycled coarse aggregate (RCA) can also be a significant and positive aspect to achieve sustainable construction and reduce environmental risks [10]. The main difference between the natural aggregate and recycled coarse aggregate (RCA) is a certain amount of sticky mortar at the surface of RCA [11]. The properties of RCA vary with certain percentages from the natural aggregate. RCA is generally a porous material, having low saturated surface dry density and bulk density, 2310–2620 kg/m and 1290–1470 kg/m , respectively [12]. The porosity of RCA is due to a high content of ad‐ hered mortar on its surface, which also reduces its resistance against the chemical and mechanical effects. In comparison, RCA also shows a high value of water absorption (4% to 9%) as opposed to natural aggregate (1% to 2%) [13]. The porosity and water absorption are normally increased in RCA just because of the amount of adhered mortar [14,15]. The effect on density and absorption capacity is also affected by the adhered mortar. These parameters affect the fresh properties of concrete and reduce the strength properties of concrete. The proper mix design for RCA has assured the acceptable properties of concrete which can be used in several construction projects. The properties of concrete material can also be improved by using other waste materials like silica fume, fly ash, and natural and artificial fibers [16–19]. Several studies were presented regarding the application of recycled aggregate (RA) in concrete at certain percentages [20,21]. Several properties of concrete were investigated upon the inclusion of RA in concrete, including the fresh properties and mechanical prop‐ erties of RA‐based concrete [22–24]. The different qualities of RA were employed in con‐ crete for maintaining or increasing the strength properties of concrete [25–28]. They also showed that the targeted strength was achieved even at an 80% replacement of coarse aggregate with RCA. Khaldoun et al. [23] worked on the effect of mechanical properties of concrete containing RCA. The compressive strength of the specimens at different ages was calculated to analyze the behavior of concrete. Muzaffer et al. [29] described the me‐ chanical and physical properties of RCA concrete GGBFS, in which they concluded that the split tensile strength was improved when tested at various ages of specimens. Etxe‐ berria et al. [30] showed the influence of RCA and the production process on the proper‐ ties of recycled aggregate‐based concrete. They prepared concrete with 0%, 25%, 50%, and 100% recycled aggregate to investigate the properties. Sumayia et al. reported the mechan‐ ical properties of three generations of 100% repetition of RCA. They reported the idea that the repeated RA experienced marginally lower compressive strength than the normal con‐ crete. Supervised machine learning (ML) techniques are extensively used in the fields of artificial inelegance (AI) and computer science and have a positive reflection in engineer‐ ing. However, it has gained rapid promotion in the field of civil engineering, especially when it comes to predicting the strength properties of concrete. The supervised ML ap‐ proaches can be employed, which can predict the outcomes at high accuracy. Ayaz et al. [31] predicted the compressive strength of fly ash‐based concrete with individual and en‐ semble ML approaches. Miao et al. [32] used MLR, SVM, and ANN to foretell the bond Buildings 2021, 11, 324 3 of 18 strength between the FRPs and concrete, in which they compared the accuracy level of the predictions from the employed techniques. Khoa et al. [33] used ML algorithms to forecast the compressive strength of greenfly ash‐based geopolymer concrete. Marjana et al. used different ML techniques for predicting the compressive strength of concrete. The predicted accuracy and the error distribution were analyzed in the study. Ayaz et al. [34] used arti‐ ficial neural network (ANN), gene expression programming (GEP), and decision tree (DT) techniques to forecast the surface chloride concentration in concrete containing waste ma‐ terial. They indicated that the GEP was a more effective technique for prediction than other employed algorithms. This research also focuses on the application of supervised ML ap‐ proaches to forecast the compressive strength of recycled coarse aggregate‐based concrete. The ANN and GEP algorithms have been investigated to predict the compressive strength of concrete containing recycled aggregate. The various statistical checks, k‐fold cross‐vali‐ dation method, and error distribution are included to confirm the model performance. The focus of this study is on the application of supervised machine learning algorithms (gene expression programming and artificial neural network) to predict the compressive strength of concrete containing recycled coarse aggregate (RCA) of 344 data points. The aim of this research also describes the performance of gene expression programming (GEP) and an artificial neural network (ANN) in terms of the correlation coefficient (R ) value. The statistical checks, evaluation of errors (MAE, MSE, and RMSR), k‐fold cross‐validation, and sensitivity analysis were also involved to evaluate the performance of both GEP and ANN models. This study can be useful for researchers in the field of civil engineering to foretell the strength properties without consuming more time on practical work in the la‐ boratory. 2. Data Description Supervised machine learning algorithms require various input variables to give the output predicted variable. The data used in this study to forecast the compressive strength of recycled coarse aggregate‐based concrete were taken from previously published litera‐ ture and can be seen in Appendix A. A total of nine parameters including water, cement, sand, natural coarse aggregate, recycled coarse aggregate (RCA), superplasticizers, size of RCA, the density of RCA, and water absorption of RCA were taken as input for running the models, and one variable, compressive strength, was taken as an outcome for the mod‐ els. Several input parameters and the total number of data points greatly influence the model’s outcome. A total of 344 data points (mixes) for the prediction of RCA‐based con‐ crete were used in the study. Anaconda software was introduced to run the model for ANN using python coding, while the GEP model was run on the GEP software. The rela‐ tive frequency distribution of each parameter used for the mixes can be seen in Figure 1. The descriptive statistical analysis for all the parameters is listed in Table 1. The flowchart of the research approach can be seen in Figure 2. Table 1. Descriptive analysis of the input parameters. Parameter’s Water Cement *FA *NCA *RCA *SP *SRCA *DRCA *WRCA Descriptions Mean 184.62 386.86 681.89 398.07 650.74 1.32 19.76 2231.06 4.80 Standard Error 1.39 4.43 11.07 19.99 20.37 0.11 0.22 31.32 0.12 Median 180.00 380.00 698.00 471.00 552.00 0.00 20.00 2362.50 4.90 Mode 220.00 380.00 693.00 0.00 138.00 0.00 20.00 2320.00 5.30 Standard 25.84 82.16 205.28 370.71 377.73 2.05 4.02 580.95 2.26 Deviation Sample Variance 667.47 6750.28 42,141.11 137,424.94 142,682.56 4.21 16.16 337,504.80 5.12 Kurtosis −0.13 −0.19 4.17 −1.13 −0.32 0.61 2.23 10.55 1.07 Skewness −0.01 0.43 −1.82 0.30 0.51 1.36 0.08 −3.45 0.06 Range 153.40 442.00 1010.00 1448.25 1726.00 7.80 22.00 2661.00 10.90 Buildings 2021, 11, 324 4 of 18 Minimum 117.60 158.00 0.00 0.00 52.00 0.00 10.00 0.00 0.00 Maximum 271.00 600.00 1010.00 1448.25 1778.00 7.80 32.00 2661.00 10.90 Sum 63,510.69 133,081.00 234,568.66 136,937.02 223,853.20 455.50 6796.00 767,484.00 1652.80 Count 344.00 344.00 344.00 344.00 344.00 344.00 344.00 344.00 344.00 *FA = Fine aggregate, *NCA = Natural coarse aggregate, *SP = Superplasticizer, *SRCA = Maximum size of recycled coarse aggregate, *DRCA = Density of recycled coarse aggregate, *WRCA = Water absorption of recycled‐coarse aggregate. Figure 1. Histograms indicating the relative frequency distribution of the input parameters. Buildings 2021, 11, 324 5 of 18 Figure 2. Flowchart of the research approach. 3. Methodology Two algorithms (GEP and ANN) were introduced in the study to predict the com‐ pressive strength of RAC. Spyder 4.1.1 was selected in the Anaconda navigator to run the model for the artificial neural network (ANN) using python coding. However, the GEP, which is the computer‐based software, was adopted for modeling to give a predicted com‐ pressive result for the concrete containing recycled coarse aggregate. The GEP and ANN used nine parameters as input and one parameter (compressive strength) as the output during the modeling. The predicted outcome from both models presented the correlation 2 2 coefficient (R ) value, which is an indication of the accuracy level. The R value normally ranges from 0–10, and a higher R value indicates a high accuracy between the actual and predicted result. Gene expression programming is from the family of evolutionary algo‐ rithms and is generally associated with genetic programming. GEP being from the evolu‐ tionary algorithms, can design computer programs and models. Computer programming is considered as a composite tree‐like structure that learns and alters by substituting their shapes, compositions, and sizes similar to living organisms. The GEP computer program is included in simple linear chromosomes of fixed length. GEP consists of five compo‐ nents: terminal set, function set, controlee variable, fitness function, and terminate condi‐ tion. Ferreira presents GEP in 2006, which is a modified form of genetic programming (GP) and depends on the population evolutionary theorem. An exceptional tempering in GEP was that the single gene must be transferred to another generation and has no need to reproduce and mutate the complete structure since every alteration takes place in a linear and simple structure. Each gene in GEP contains a fixed‐length variable having ter‐ minal sets and arithmetic operations as a set of functions. GEP makes it possible to learn the complex data in the form of input and gives the resulting output in a simple and easy manner. An artificial neural network (ANN) is generally a segment of a computing system that is designed in such a way that it can simulate just like the human brain and inspect and execute a set of information. ANN is the foundation of artificial intelligence (AI), which can resolve problems that would seem difficult or impossible for a human. It is also comprised of self‐learning potential, which permits them to generate better results. ANN is designed like a human brain having neuron nodes interrelated just like a web. The brain consists of hundreds of billions of cells known as neurons. Every neuron is prepared with Buildings 2021, 11, 324 6 of 18 a cell body that is accountable for executing the information by taking information to‐ wards and away from the brain. The application of ANN is reflected in every industry and field to predict required outcomes. 4.. Results and Their Analyses 4.1. Statistical Analysis The statistical analysis representation between the actual and predicted outcomes (for compressive strength of RCA‐based concrete) from the GEP and ANN models along their error distribution can be seen in Figure 3. The GEP gives high accuracy and less variance between the actual and predicted output. The coefficient correlation (R ) value equals 0.95 and is an indication of its high performance towards the prediction of the re‐ sult, as shown in Figure 3a. The scattering of errors for the GEP model is also illustrated in Figure 3b. The error distribution in Figure 3b represents that the maximum, minimum, and average values of the training set were 22.37 MPa, 0.00 MPa, and 1.84 MPa, respec‐ tively. However, 21.73% of the error data lies below 1 MPa, and 22.96% of the data repre‐ sented the errors between 2 MPa and 5 MPa. However, only 6.97% of the data lies above the 5 MPa. The result of the ANN model is also in the acceptable range with less variance as opposed to the GEP model’s result. The relationship between the actual and predicted result from the ANN model with the value of R equal to 0.92 can be seen in Figure 3c. The distribution of the errors for the ANN model can be seen in Figure 3d. Figure 3d gives the information of the training set of the ANN model, indicating maximum and minimum values of 21.44 MPa and 0.1 MPa, respectively, while giving an average value of 2.72 MPa. In addition, 21.73% of error data lies below 1 MPa, and 36.23% of data lies between 2 MPa and 5 MPa. However, only 7.24% of the error data indicated above the 5 MPa. Targets Predictions Errors y = 0.9385x + 3.2378 (a) R² = 0.9544 (b) 80 80 -20 0 20406080 100 120 0 50 100 150 200 250 300 350 Targets (MPa) Data Set Targets Predictions Errors y = 0.9437x + 3.4573 (c) R² = 0.925 100 100 (d) -20 0 20 40 60 80 100 120 0 10 20 3040506070 Data Set Targets (MPa) Figure 3. Numerical analysis results illustrating the relationship among the actual and predicted outcomes and reflection of errors distribution of the models. ANN (a,b); GEP (c,d). Predictions (MPa) Predictions (MPa) Compressive strength (MPa) Compressive strength (MPa) Buildings 2021, 11, 324 7 of 18 4.2. K‐Fold Cross‐Validation The authenticity of the model’s execution was analyzed through the k‐fold cross‐val‐ idation method. To examine the model’s validity, the k‐fold cross‐validation process is normally adopted, in which the required data has been arranged randomly and divided into ten groups. The nine groups need to be allocated for training and the remaining one for the model’s validation. The procedure also needs repetition (ten times) to have an av‐ erage output. This detailed process of the k‐fold cross‐validation results in the high accu‐ racy of the models. In addition, the statistical checks in the form of the error’s (MSE, MAE, and RMSE) evaluation have also been carried out, as illustrated in Table 2. The response of the models towards the prediction was also checked through the statistical analysis, illustrated in the form of the equations stated below. (Equations (1)–(5)) 𝑚𝑜 (1) ∑ |𝑒𝑥 𝑚𝑜 | (2) 𝐸 ∑ 𝑚𝑜 𝑒𝑥 (3) 𝑥 𝑒𝑥 1 ∑ 𝑚𝑜 (4) 𝑒 𝑛 ∑ 𝑒𝑥 𝑒𝑥 𝑚𝑜 𝑅 (5) ∑ ∑ 𝑒𝑥 𝑒𝑥 𝑚𝑜 𝑚𝑜 where, 𝑒𝑥 = experimental value, 𝑚𝑜 = predicted value, 𝑒𝑥 = mean experimental value, 𝑚𝑜 = mean predicted value obtained by the model, n = number of samples. The resulting evaluation of the k‐fold cross‐validation comprised of four parameters, including the coefficient correlation (R ), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE), and their distribution can be seen in Figure 4. The lesser error of the GEP model with a high value of R indicates the better performer for prediction of outcome. The maximum, minimum, and average values of R for the GEP model were equal to 0.77, 0.00, and 0.49, respectively, as shown in Figure 4a. Similarly, the same values of R for the ANN model were 2.05, 0.00, and 0.68, as depicted in Figure 4b. However, the maximum values of the MAE, MSE, and RMSE for the GEP model were 14.37 MPa, 14.11 MPa, and 3.76 MPa, respectively, as illustrated in Figure 4a, while the validation result for the ANN model gave maximum values of MAE, MSE, and RMSE as 16.80 MPa, 20.89 MPa, and 4.57 MPa, respectively, as shown in the Figure 4b. The mini‐ mum values of the errors (MAE, MSE, and RMSE) for the GEP model were 6.21 MPa, 8.17 MPa, and 2.86 MPa, as reflected in Figure 4a, while for ANN, these values were 5.86 MPa, 4.96 MPa, and 2.23 MPa, as depicted in Figure 4b. Additionally, the validation result for the GEP and ANN models and the statistical checks for both, employing the supervised machine learning algorithms, are illustrated in Tables 2 and 3, respectively. 𝑚𝑜 𝑅𝑅𝑀𝑆𝐸 𝑒𝑥 𝑅𝑆𝐸 𝑀𝐴 𝑅𝑀𝑆𝐸 𝑒𝑥 Buildings 2021, 11, 324 8 of 18 Figure 4. Statistical representation for the k‐fold cross‐validation process. GEP (a); ANN (b). Table 2. Statistical checks of the GEP and ANN models. Machine Learning Algorithms MAE MSE RMSE Gene Expression Programming (GEP) 1.84 9.3 3.05 Artificial Neural Network (ANN) 2.73 19 4.36 Table 3. Analysis of the k‐fold cross‐validation of ANN and GEP models. ANN GEP 2 2 K‐fold MAE MSE RMSE R K‐Fold MAE MSE RMSE R 1 11.77 16.13 4.02 0.22 1 8.17 8.81 2.97 0.49 2 5.86 7.28 2.70 0.91 2 14.37 14.11 3.76 0.70 3 9.04 10.72 3.27 0.70 3 10.57 12.79 3.58 0.77 4 10.81 14.60 3.82 1.82 4 9.31 10.04 3.17 0.43 5 7.46 7.23 2.69 0.20 5 8.51 10.99 3.32 0.12 6 16.80 20.89 4.57 2.05 6 13.55 13.25 3.64 0.74 7 7.54 10.34 3.22 0.49 7 12.07 13.67 3.70 0.00 8 10.70 14.50 3.81 0.00 8 8.77 8.22 2.87 0.56 9 8.86 4.96 2.23 0.26 9 6.21 8.17 2.86 0.69 10 14.58 15.53 3.94 0.16 10 7.49 9.68 3.11 0.44 5. Sensitivity Analysis This analysis refers to the effect of parameters on predicting the compressive strength of concrete containing recycled coarse aggregate, as depicted in Figure 5. The input pa‐ rameters have a significant effect on forecasting the outcomes. The figure illustrates that the highest contributor was the recycled coarse aggregate (RCA) at 41.1%, while the other two main contributors were natural coarse aggregate (NCA) and water at 25% and 20%, respectively. However, the contribution of the other variables was less, and for cement, it showed a 3.8% contribution, fine aggregate 2.3%, superplasticizers 2.6%, the size of coarse aggregate 1.9%, the density of RCA 2%, and water absorption showed 1.3% contribution towards the prediction of the compressive strength of RCA‐based concrete. The following equation was used to calculate the contribution of each variable towards the model’s out‐ put. Buildings 2021, 11, 324 9 of 18 𝑁 𝑓 𝑥 𝑓 𝑥 (6) 𝑆 (7) ∑ 𝑁 where, 𝑓 𝑥 and 𝑓 𝑥 are the maximum and minimum of the estimated output th over the i output. Figure 5. Sensitivity analysis indicates the contribution of parameters towards the prediction. 6. Discussion This research describes the application of supervised machine learning (ML) tech‐ niques to foretell the strength property (compressive strength) of recycled coarse aggre‐ gate‐based concrete. The use of recycled aggregates in concrete is to produce effective ma‐ terial and sustainable construction works. The ML approaches used in this study were gene expression programming (GEP) and an artificial neural network (ANN). The predic‐ tive performance of both algorithms was compared to evaluate the better predictor. The GEP model’s outcome was more accurate by indicating the coefficient correlation (R ) value equal to 0.95 as opposed to the ANN model’s outcome which gave an R value equal to 0.92. The performance of both models was also confirmed from the statistical checks and k‐fold cross‐validation method. The lesser values of the errors indicate the high per‐ formance of the employed model. Moreover, the sensitivity analysis was also carried out to know about the contribution of each parameter towards the prediction of the compres‐ sive strength of concrete containing recycled coarse aggregate. The performance of the models can be affected by the input parameters used to run the model and the number of data points. The contribution level from the sensitivity analysis of all the nine input pa‐ rameters towards the forecasted result indicates the high contributor parameter. 7. Conclusions and Future Recommendations This study describes the application of supervised machine learning approaches to predict the compressive strength of concrete containing recycled coarse aggregate (RCA). The gene expression programming (GEP) and artificial neural network (ANN) algorithms were employed for forecasting the compressive strength of concrete. The GEP model was more effective in terms of prediction as compared to the ANN model, which is confirmed from its higher value of linear correlation coefficient (R ) and lesser values of the errors. The following conclusions can be drawn. Buildings 2021, 11, 324 10 of 18 The results of the GEP model indicate the high performance towards the prediction of concrete containing recycled coarse aggregate (RCA) as opposed to the ANN model. The results from the ANN model are also in the acceptable range and can be used for predicting the outcomes. The high performance of the GEP model has also been confirmed from statistical checks and the k‐fold cross‐validation process. The application of GEP and ANN was proposed in this study to predict the strength property of concrete. The use of ML approaches can predict the strength properties with‐ out casting the samples in the laboratory. However, the use of other supervised machine learning algorithms would give a better idea about the accuracy of the employed ML tech‐ niques. The RCA also showed a significant effect (41.1%) towards predicting the concrete’s compressive strength compared to other input variables. It would be easier to understand the effect of the models by making comparisons of more than two algorithms towards the prediction of the outcomes. It is recommended for future research that datasets should be enhanced from exper‐ imental work, field tests, and other numerical analyses using different approaches (e.g., Monte–Carlo simulation). The input parameters can also be increased by adding the environmental effects (e.g., high temperature and humidity) to provide a better response from the models. The application of the other ensemble ML algorithms (e.g., Adaboost, bagging, and boosting) can be more effective to predict the compressive strength of concrete. Author Contributions: A.A.: conceptualization, methodology, investigation, formal analysis, mod‐ eling, visualization, and writing—original draft preparation. K.C.: funding acquisition, methodol‐ ogy, investigation, formal analysis, writing—reviewing and editing, and supervision. F.F.: re‐ sources, methodology, and writing—reviewing and editing. W.A.: methodology, and writing—re‐ viewing and editing. S.S.: conceptualization, methodology, and writing—reviewing and editing. F.A.: conceptualization, methodology, and writing—reviewing and editing. All authors have read and agreed to the published version of the manuscript. Funding: This project is funded by Thammasat University Rangsit, Klong Luang Pathumthani, Thailand Institutional Review Board Statement: Not applicable Informed Consent Statement: Not applicable Data Availability Statement: Not applicable Acknowledgment: This study was supported by the Thammasat University Research Fund, Con‐ tract No. TUFT 59/2564. Conflicts of Interest: The authors declare no conflict of interest. Appendix A Water Cement NCA RCA SRCA DRCA Strength 3 3 FA (kg/m ) SP (kg/m ) WRCA (%) 3 3 3 3 3 (kg/m ) (kg/m ) (kg/m ) (kg/m ) (mm) (kg/m ) (MPa) 165 370 650 850.5 364.5 2.22 20 2400 4.9 50.6 165 370 650 607.5 607.5 2.22 20 2400 4.9 50.8 165 370 650 0 1215 2.22 20 2400 4.9 50.2 165 460 575 850.5 364.5 2.22 20 2400 4.9 60.8 165 460 575 607.5 607.5 2.22 20 2400 4.9 61.2 165 460 575 0 1215 2.22 20 2400 4.9 60.2 165 560 495 850.5 364.5 2.59 20 2400 4.9 70.2 165 560 495 607.5 607.5 2.59 20 2400 4.9 70.8 165 560 495 0 1215 2.59 20 2400 4.9 70 180 500 486.6 0 1135.4 0 16 0 0 44.5 Buildings 2021, 11, 324 11 of 18 180 500 0 0 1574.3 0 16 0 0 38.7 180 500 486.6 0 1135.4 0 16 0 0 46.1 180 500 0 0 1574.3 0 16 0 0 42.4 180 500 486.6 0 1135.4 0 16 0 0 52.5 180 500 0 0 1574.3 0 16 0 0 50.7 180 500 486.6 0 1135.4 0 16 0 0 45.2 180 500 0 0 1574.3 0 16 0 0 42 180 500 486.6 0 1135.4 0 16 0 0 49.6 180 500 0 0 1574.3 0 16 0 0 45.1 180 500 509.6 0 1135.4 0 16 0 0 54.4 180 500 0 0 1574.3 0 16 0 0 48.2 207.6 400 662 863 153 0 20 2410 5.8 38.1 207.6 400 662 697 298 0 20 2410 5.8 37 207.6 400 662 383 573 0 20 2410 5.8 35.8 207.6 400 662 0 903 0 20 2410 5.8 34.5 217 353 660 861 209 0 20 2330 6.3 44.9 229 353 647 527 513 0 20 2330 6.3 44.7 241 353 625 0 993 0 20 2330 6.3 46.8 230 353 661 853 202 0 20 2330 6.3 43.2 247 353 647 524 496 0 20 2330 6.3 39.7 271 353 625 0 959 0 20 2330 6.3 43.3 206 353 661 864 216 0 20 2330 6.3 43 207 353 649 531 531 0 20 2330 6.3 38.1 165 300 765 905 267 4.98 25 2430 4.4 42 165 318 739 608 537 6.042 25 2430 4.4 41 162 325 683 0 1123 6.175 25 2430 4.4 40 160.6 380 598 1182 52 4.9 20 2165 6.8 62.2 165.4 380 529 1175 103 4.9 20 2165 6.8 58.4 170.2 380 460 1168 154 4.9 20 2165 6.8 61.3 175.6 380 327 1162 254 4.9 20 2165 6.8 60.8 180.9 380 0 1162 509 4.9 20 2165 6.8 61 225 410 642 840 204 0 20 2570 3.5 45.3 225 410 642 524 506 0 20 2570 3.5 42.5 225 410 642 210 814 0 20 2570 3.5 39.2 225 410 642 0 1017 0 20 2570 3.5 37.1 180 400 708 886 215 0 20 2570 3.5 62.4 180 400 708 554 538 0 20 2570 3.5 55.8 180 400 708 0 1075 0 20 2570 3.5 42 225 410 642 840 204 0 20 2570 3.5 45.3 225 410 642 524 506 0 20 2570 3.5 42.5 225 410 642 0 1017 0 20 2570 3.5 38.1 234 360 705 0 1100 0 19 2390 4.4 22.1 190 380 705 0 1100 0 19 2390 4.4 25.1 192 400 705 0 1100 0 19 2390 4.4 27.2 181 420 705 0 1100 0 19 2390 4.4 28.7 184 460 705 0 1100 0 19 2390 4.4 29.5 178 264 835 0 1030 0 30 2520 3.8 18 174 262 830 0 1020 0 30 2510 3.9 15.4 148 427 760 0 1000 4.2 30 2520 3.8 36.4 153 423 755 0 990 4.1 30 2510 3.9 35.7 152 443 855 0 885 3.9 30 2520 3.8 44.4 Buildings 2021, 11, 324 12 of 18 225 410 642 840 204 0 20 2580 3.5 45.3 225 410 642 524 506 0 20 2580 3.5 42.5 225 410 642 0 1017 0 20 2580 3.5 38.1 205 410 662 865 210 0 20 2580 3.5 51.7 205 410 662 541 525 0 20 2580 3.5 47.1 205 410 662 0 1049 0 20 2580 3.5 43.4 180 400 708 886 215 5.6 20 2580 3.5 62.4 180 400 708 554 538 5.6 20 2580 3.5 56.8 180 400 708 0 1075 5.6 20 2580 3.5 52.1 160 400 729 912 221 7.8 20 2580 3.5 69.6 160 400 729 570 554 7.8 20 2580 3.5 65.3 160 400 729 0 1107 7.8 20 2580 3.5 58.5 175 350 730 711 297 1.68 25 2530 1.9 36.7 175 350 730 508 494 1.68 25 2530 1.9 38 175 350 730 0 989 1.68 25 2530 1.9 36 175 350 730 711 282 1.68 25 0 0 32.6 175 350 730 508 469 1.68 25 2400 6.2 30.4 175 350 730 0 938 1.68 25 2400 6.2 29.5 190 380 744.45 756.97 189.24 2.66 20 2338 5.2 47.4 190 380 709.54 471.13 471.12 2.66 20 2338 5.2 47.3 190 380 714.56 0 874.04 5.32 20 2338 5.2 54.8 140 350 732 519 556 4.2 12 2420 6.8 43.3 153 340 723 512 549 3.4 12 2400 6.8 39.6 165 330 715 507 543 2.64 12 2400 6.8 38.1 176 320 708 502 537 1.92 12 2400 6.8 34.5 186 310 702 497 533 1.24 12 2400 6.8 31.6 140 350 732 553 523 4.2 22 2420 8.8 46.1 153 340 723 547 517 3.4 22 2420 8.8 45.8 165 330 715 541 511 2.64 22 2420 8.8 39.9 176 320 708 535 506 1.92 22 2420 8.8 36.3 186 310 702 531 501 1.24 22 2420 8.8 34.7 186 372 617.65 1030.22 257.56 0 20 2400 0 27.2 186 372 617.65 772.67 515.55 0 20 2400 0 26.5 186 372 617.65 515.11 772.67 0 20 2400 0 25.4 186 372 617.65 257.56 1030.22 0 20 2400 0 25.1 186 372 494.12 128.78 123.53 0 20 2630 0 26.4 186 372 370.59 128.78 247.06 0 20 2630 0 25.9 186 372 247.06 128.78 370.59 0 20 2630 0 23.5 186 372 123.53 128.78 494.12 0 20 2630 0 15.4 200 270 750 675 200 1.08 19 2440 5.8 18.5 210 270 750 450 400 1.35 19 2440 5.8 18 220 270 750 225 600 1.62 19 2440 5.8 16.5 165 370 865 760 230 1.48 19 2440 5.8 33 165 370 865 505 455 1.85 19 2440 5.8 34.5 165 370 865 250 680 2.59 19 2440 5.8 34 178.5 275 938.05 723.07 180.77 1.925 16 2400 5 31.7 178.5 275 962.73 423.77 423.77 1.925 16 2400 5 32.4 178.5 275 1005.18 0 756.46 1.925 16 2400 5 30.1 190 380 794.31 750.04 187.57 2.66 16 2400 5 43.7 190 380 811.37 443.71 443.71 2.66 16 2400 5 37.5 190 380 838.29 0 807.97 2.66 16 2400 5 40.5 Buildings 2021, 11, 324 13 of 18 151 335 630 414 720 1.266 19 2420 5.4 41.4 156 349 888 0 792 1.67616 19 2420 5.4 43.9 161 358 645 281 813 1.3584 19 2500 3.3 44.8 156 349 857 0 867 1.2564 19 2500 3.3 45.9 172.43 401 574 911 303 0.2005 20 2661 1.9 47 172.43 401 574 585 585 0.70175 20 2602 2.6 46 172.43 401 574 0 1119 0.90225 20 2510 3.9 42.5 190.8 424 770 0 980 0 19 2490 4.8 41 192.5 350 800 0 1015 0 19 2490 4.8 33.3 191.75 295 814 0 1039 0 19 2490 4.8 24.8 150 250 762 858 286 4.375 19 0 0 26.7 150 250 753 564 564 4.375 19 0 0 21.5 150 250 743 279 836 4.375 19 0 0 21.4 150 250 734 0 1100 4.375 19 0 0 20 180 400 685 770 257 3 19 0 0 38.3 180 400 676 507 507 3 19 0 0 37 180 400 667 250 751 3 19 0 0 35 180 400 659 0 988 3 19 0 0 33.3 175 325 0 0 1762 3.45 32 2263 6 33.2 222 350 0 0 1778 4.5 32 2283 4.2 35.6 221 350 0 0 1771 4.5 32 2292 4.3 34.6 195 325 0 0 1710 3.25 32 2301 5 37.3 123 300 0 192 1728 3 32 2609 1.5 45.4 144 325 0 768 1152 3.25 32 2518 2.7 54.3 123 325 0 754.4 1131.6 3.25 32 2584 1.6 54.4 132 300 0 1448.25 482.75 3 32 2594 1.6 53.4 180 275 625 882 378 0 20 2340 5.3 20 180 295 595 635 635 0 20 2340 5.3 19 180 310 610 0 1240 0 20 2340 5.3 18 180 330 585 872 373 0 20 2340 5.3 23 180 355 560 623 623 0 20 2340 5.3 24 180 372 536 0 1252 0 20 2340 5.3 21 180 355 560 872 373 0 20 2340 5.3 25 180 385 550 613 613 0 20 2340 5.3 29 180 409 525 0 1226 0 20 2340 5.3 30 180 375 544 869 372 0 20 2340 5.3 39 180 405 508 624 624 0 20 2340 5.3 31 180 426 494 0 1241 0 20 2340 5.3 34 193 350 661 1061 57 0 12 2010 10.9 40 194 350 515 1061 170 0 12 2010 10.9 38.6 196 350 368 1061 283 0 12 2010 10.9 37.6 199 158 0 1061 566 0 12 2010 10.9 38.6 158 350 693 1111 59 3.5 12 2010 10.9 53.7 163 350 536 1105 177 3.5 12 2010 10.9 51 168 350 381 1100 294 3.5 12 2010 10.9 47.8 178 350 0 1089 582 3.5 12 2010 10.9 45.1 137 350 713 1143 61 3.5 12 2010 10.9 64.6 139 350 555 1143 183 3.5 12 2010 10.9 65.4 143 350 395 1138 304 3.5 12 2010 10.9 63.2 150 350 0 1132 605 3.5 12 2010 10.9 63 180 281 802 0 970 0 10 2360 4.7 38.6 Buildings 2021, 11, 324 14 of 18 170 293 648 0 919 0 10 2280 6.2 38.1 165 337 841 0 879 0 10 2220 7.8 39.3 190 463 621 0 970 0 10 2360 4.7 60.1 190 500 621 0 919 3.24 10 2280 6.2 60.2 180 600 567 0 879 5.04 10 2220 7.8 62.8 220 537 693 782 138 0 20 2330 4.4 50.8 220 537 693 644 276 0 20 2330 4.4 44.9 220 537 693 506 414 0 20 2330 4.4 44.6 220 537 693 368 552 0 20 2330 4.4 42.4 220 537 693 782 138 0 20 2370 4 54 220 537 693 644 276 0 20 2370 4 56 220 537 693 506 414 0 20 2370 4 54.4 220 537 693 368 552 0 20 2370 4 40.6 220 537 693 782 138 0 20 2390 3.6 55.2 220 537 693 644 276 0 20 2390 3.6 53.5 220 537 693 506 414 0 20 2390 3.6 56.9 220 537 693 368 552 0 20 2390 3.6 54.7 220 537 693 782 138 0 20 2320 4.6 50.5 220 537 693 644 276 0 20 2320 4.6 48.9 220 537 693 506 414 0 20 2320 4.6 45.8 220 537 693 368 552 0 20 2320 4.6 40 220 537 693 782 138 0 20 2390 3.7 54.4 220 537 693 644 276 0 20 2390 3.7 50.2 220 537 693 506 414 0 20 2390 3.7 49.5 220 537 693 368 552 0 20 2390 3.7 40.4 220 537 693 782 138 0 20 2390 3.5 45 220 537 693 644 276 0 20 2390 3.5 46.9 220 537 693 506 414 0 20 2390 3.5 51.4 220 537 693 368 552 0 20 2390 3.5 53.2 220 537 693 782 138 0 20 2380 3.8 55.3 220 537 693 644 276 0 20 2380 3.8 55.9 220 537 693 506 414 0 20 2380 3.8 52.6 220 537 693 368 552 0 20 2380 3.8 48 220 537 693 782 138 0 20 2380 3.8 49.1 220 537 693 644 276 0 20 2380 3.8 49.9 220 537 693 506 414 0 20 2380 3.8 50.3 220 537 693 368 552 0 20 2380 3.8 47.5 220 537 693 782 138 0 20 2400 3.5 43.2 220 537 693 644 276 0 20 2400 3.5 53.7 220 537 693 506 414 0 20 2400 3.5 50 220 537 693 368 552 0 20 2400 3.5 43.3 220 537 693 782 138 0 20 2370 4 52.9 220 537 693 644 276 0 20 2370 4 49.9 220 537 693 506 414 0 20 2370 4 53.7 220 537 693 368 552 0 20 2370 4 46 206 413 606 0 987 0 25 2452 4.1 51 206 413 606 0 987 0 25 2452 4.1 49 206 413 606 0 987 0 25 2452 4.1 48 206 413 606 537 494 0 25 2452 4.1 51 206 413 606 537 494 0 25 2452 4.1 51 206 413 606 537 494 0 25 2452 4.1 51 Buildings 2021, 11, 324 15 of 18 206 413 606 805 245 0 25 2452 4.1 52 206 413 606 805 245 0 25 2452 4.1 50 206 413 606 805 245 0 25 2452 4.1 49 145.6 520 577.2 0 1040 0 25 2260 7.5 38.3 145.6 520 577.2 0 1040 0 25 2260 7.5 32.9 119.6 520 577.2 0 1040 0 25 2260 7.5 33.2 146.2 430 653.6 0 1032 0 25 2260 7.5 31.3 146.2 430 653.6 0 1032 0 25 2260 7.5 28.4 120.4 430 653.6 0 1032 0 25 2260 7.5 28 145.77 339 728.85 0 1050.9 0 25 2260 7.5 26.5 145.77 339 728.85 0 1050.9 0 25 2260 7.5 23.3 118.65 339 728.85 0 1050.9 0 25 2260 7.5 21.6 144.06 294 767.34 0 1029 0 25 2260 7.5 21.6 144.06 294 767.34 0 1029 0 25 2260 7.5 18 117.6 294 767.34 0 1029 0 25 2260 7.5 18.8 146.91 249 804.27 0 1045.8 0 25 2260 7.5 16.1 146.91 249 804.27 0 1045.8 0 25 2260 7.5 13.4 119.52 249 804.27 0 1045.8 0 25 2260 7.5 13.9 179 275 878 735 184 0 20 2320 5.3 41 179 275 849 455 455 0 20 2320 5.3 44 179 275 868 0 830 0 20 2320 5.3 45 190 380 744 757 189 0 20 2320 5.3 50.5 190 380 710 471 471 0 20 2320 5.3 45 190 380 715 0 874 0 20 2320 5.3 56 179 275 961 740 185 0 20 2320 5.3 33.5 179 275 978 408 408 0 20 2320 5.3 32 179 275 1010 0 640 0 20 2320 5.3 32 190 380 813 767 192 0 20 2320 5.3 44 190 380 822 426 427 0 20 2320 5.3 41 190 380 836 0 683 0 20 2320 5.3 41.5 179 325 799 839 210 0 20 2320 5.3 44 179 325 831 490 490 0 20 2320 5.3 41 179 325 825 0 923 0 20 2320 5.3 33.5 173 385 698 892 223 0 20 2320 5.3 53.5 173 385 742 515 515 0 20 2320 5.3 54 173 385 746 0 963 0 20 2320 5.3 40 159.6 380 862.4 489.3 489.3 5.7 20 2330 6.1 41.6 193.8 380 934.1 0 867.7 6.46 20 2330 6.1 31.4 197.6 380 862.4 489.3 489.3 5.7 20 2330 6.1 35.5 231.8 380 934.1 0 867.7 6.46 20 2330 6.1 26 167.2 380 862.4 489.3 489.3 5.7 20 2320 5.8 44.6 193.8 380 934.1 0 867.7 6.46 20 2320 5.8 36.7 235.6 380 934.1 0 867.7 6.46 20 2320 5.8 29.5 155.8 380 818.5 840.9 210.2 4.56 20 2360 3.9 46.1 159.6 380 862.4 489.3 489.3 5.7 20 2360 3.9 45.1 171 380 934.1 0 867.7 6.46 20 2360 3.9 42.9 190 380 818.5 840.9 210.2 4.56 20 2360 3.9 39.3 197.6 380 862.4 489.3 489.3 5.7 20 2360 3.9 39.5 205.2 380 934.1 0 867.7 6.46 20 2360 3.9 37.7 159.6 380 818.5 840.9 210.2 4.56 20 2350 4.5 48.1 163.4 380 862.4 489.3 489.3 5.7 20 2350 4.5 41 Buildings 2021, 11, 324 16 of 18 152 380 934.1 0 867.7 6.46 20 2350 4.5 38.7 193.8 380 818.5 840.9 210.2 4.56 20 2350 4.5 42.7 197.6 380 862.4 489.3 489.3 5.7 20 2350 4.5 35.4 190 380 934.1 0 867.7 6.46 20 2350 4.5 31.4 159.6 380 818.5 840.9 210.2 4.56 20 2350 4.7 48.5 159.6 380 862.4 489.3 489.3 5.7 20 2350 4.7 45.4 163.4 380 934.1 0 867.7 6.46 20 2350 4.7 37 197.6 380 818.5 840.9 210.2 4.56 20 2350 4.7 41.3 197.6 380 862.4 489.3 489.3 5.7 20 2350 4.7 36.8 212.8 380 934.1 0 867.7 6.46 20 2350 4.7 31.2 159.8 340 556 1020 238 0 20 2336 3.6 50 159.8 340 556 638 596 0 20 2315 3.6 45.3 159.8 340 556 319 894 0 20 2295 3.6 44 137.1 380 927 869.2 202 0 10 2470 3.7 108 146.5 380 927 543.2 505.1 0 10 2470 3.7 104.8 162.3 380 927 0 1010.2 0 10 2470 3.7 108.5 138.2 380 927 869.2 195 0 10 2390 4.9 102.5 149.8 380 927 543.2 487.5 0 10 2390 4.9 103.1 170.4 380 927 0 975.1 0 10 2390 4.9 100.8 139.7 380 927 869.2 187.8 0 10 2300 5.9 104.3 153.1 380 927 543.4 469.4 0 10 2300 5.9 96.8 175 380 927 0 938.8 0 10 2300 5.9 91.2 185.4 309 864 848 211 1.0197 16 2380 6.9 42.9 191.7 320 817.5 538 538 1.056 16 2380 6.9 42.5 201.6 336 785 0 1060 1.1088 16 2380 6.9 40.9 192.5 386 829 808 202 2.0458 16 2380 6.9 51.6 200 399 795 504 504 2.1147 16 2380 6.9 51.6 210 420 738 0 1014 2.226 16 2380 6.9 50.3 205 300 697 0 1075 0 20 2450 3.1 35 205 300 697 0 1027 0 20 2370 7.1 29.2 205 300 697 0 1027 0 20 2360 7.8 27.7 180 350 706 0 1089 0 20 2450 3.1 47.6 180 350 706 0 1041 0 20 2370 7.1 42 180 350 706 0 1041 0 20 2360 7.8 42.9 185 425 696 0 1028 0 20 2450 3.1 60 185 425 696 0 982 0 20 2370 7.1 53.7 185 425 696 0 982 0 20 2360 7.8 53.2 165 485 685 0 1039 0 20 2450 3.1 78.2 165 485 685 0 979 0 20 2370 7.1 71.2 165 485 685 0 982 0 20 2360 7.8 65.4 178.3 358 730.4 783.6 299.3 0.3 19 2570 2.7 33.6 178.3 358 730.4 458.3 598.4 0.3 19 2570 2.7 30.4 178.3 358 730.4 0 1020 0.3 19 2570 2.7 29.1 195 300 787.1 756.4 189.1 0 20 2300 5.2 39.5 195 300 737.4 485.5 485.5 0 20 2300 5.2 40.8 195 300 712.6 0 951.4 0 20 2300 5.2 43.7 195 300 814.4 733 183.2 0 20 2300 5.5 41 195 300 804.2 450.7 450.7 0 20 2300 5.5 38.8 195 300 807.9 0 855.2 0 20 2300 5.5 39.9 214.2 210 929 0 966 0 22 2451 7.8 19.7 196 280 866 0 940 0 22 2387 6.9 35.7 Buildings 2021, 11, 324 17 of 18 161 350 858 0 974 3.5 22 2362 4.2 66.8 212.1 210 932 0 970 0 22 2456 7.5 21.8 193.2 280 870 0 970 0 22 2455 6.4 36.1 157.5 350 858 0 1029 3.5 22 2496 4.2 68.5 207.9 210 938 0 953 0 22 2401 7.6 21 187.6 280 877 0 988 0 22 2484 5.4 41.1 150.5 350 868 0 982 3.5 22 2363 3.6 70.2 205.8 210 943 0 977 0 22 2447 6.9 23.6 190.4 280 873 0 962 0 22 2458 5.8 39.7 157.5 350 858 0 1016 3.5 22 2464 3.9 66.5 179 275 878 735 184 0 19 2320 5.3 49.3 179 275 849 455 455 0 19 2320 5.3 47.5 179 275 868 0 830 0 19 2320 5.3 53.7 190 380 714 757 189 0 19 2320 5.3 64.8 190 380 710 471 471 0 19 2320 5.3 63.5 190 380 715 0 874 0 19 2320 5.3 65.1 179 275 961 740 185 0 19 2320 5.3 64.8 179 275 978 408 408 0 19 2320 5.3 63.5 179 275 1010 0 640 0 19 2320 5.3 65.1 190 380 813 767 192 0 19 2320 5.3 54.9 190 380 822 426 427 0 19 2320 5.3 51.5 190 380 836 0 683 0 19 2320 5.3 50.3 179 325 799 839 210 0 19 2320 5.3 56.5 179 325 831 490 490 0 19 2320 5.3 48.9 179 325 825 0 923 0 19 2320 5.3 43.1 173 385 698 892 233 0 19 2320 5.3 67.4 173 385 742 515 515 0 19 2320 5.3 61.2 173 385 746 0 963 0 19 2320 5.3 53.7 References 1. Cachim, P.B. Mechanical properties of brick aggregate concrete. Constr. Build. Mater. 2009, 23, 1292–1297, doi:10.1016/j.conbuildmat.2008.07.023. 2. Kumar Mehta, P. Point of view: Reflections about technology choices. Concr. Int. 1970, 69–76. Available online: http://maquinamole.net/EcoSmartConcrete.com/docs/trmehta99.pdf (accessed on 17 June 2021). 3. Mikulčić, H.; Klemeš, J.J.; Vujanović, M.; Urbaniec, K.; Duić, N. Reducing greenhouse gasses emissions by fostering the deployment of alternative raw materials and energy sources in the cleaner cement manufacturing process. J. Clean. Prod. 2016, 136, 119–132, doi:10.1016/j.jclepro.2016.04.145. 4. Naik, T.R. Sustainability of Concrete Construction. Pract. Period. Struct. Des. Constr. 2008, 13, 98–103, doi:10.1061/(asce)1084‐ 0680(2008)13:2(98). 5. Barreto Santos, M.; de Brito, J.; Santos Silva, A.; Hawreen, A. Effect of the source concrete with ASR degradation on the mechanical and physical properties of coarse recycled aggregate. Cem. Concr. Compos. 2020, 111, 103621, doi:10.1016/j.cemconcomp.2020.103621. 6. Lehmann, S. Optimizing urban material flows and waste streams in urban development through principles of zero waste and sustainable consumption. Sustainability 2011, 3, 155–183, doi:10.3390/su3010155. 7. Massari, S.; Ruberti, M. Rare earth elements as critical raw materials: Focus on international markets and future strategies. Resour. Policy 2013, 38, 36–43, doi:10.1016/j.resourpol.2012.07.001. 8. Northey, S.A.; Mudd, G.M.; Werner, T.T. Unresolved Complexity in Assessments of Mineral Resource Depletion and Availability. Nat. Resour. Res. 2018, 27, 241–255, doi:10.1007/s11053‐017‐9352‐5. 9. Safiuddin, M.; Jumaat, M.Z.; Salam, M.A.; Islam, M.S.; Hashim, R. Utilization of solid wastes in construction materials. Int. J. Phys. Sci. 2010, 5, 1952–1963, doi:10.5897/IJPS.9000617. 10. Maghool, F.; Arulrajah, A.; Du, Y.J.; Horpibulsuk, S.; Chinkulkijniwat, A. Environmental impacts of utilizing waste steel slag aggregates as recycled road construction materials. Clean Technol. Environ. Policy 2017, 19, 949–958, doi:10.1007/s10098‐016‐1289‐ 6. Buildings 2021, 11, 324 18 of 18 11. Marie, I.; Quiasrawi, H. Closed‐loop recycling of recycled concrete aggregates. J. Clean. Prod. 2012, 37, 243–248, doi:10.1016/j.jclepro.2012.07.020. 12. Al‐Ali, A.Y. Assessment of recycled aggregate structural suitability for road construction. In Proceedings of the First International Conference and Exhibition on Quality Control and Quality Assurance of Construction Materials, Dubai, United Arab Emirates, 2001. Available online: https://scholarworks.uaeu.ac.ae/all_thesesTheses.383.https://scholarworks.uaeu.ac.ae/all_theses/383 (accessed on 17 June 2021). 13. Li, J. Study on mechanical behavior of recycled aggregate concrete. Shanghai, Tongji University. Thesis, Master of Engineering, October 2004. 14. Vázquez, E. Recycled concrete. In Progress of Recycling in the Built Environment; RILEM State‐of‐the‐Art Reports; Springer: Berlin, Germany, 2013; pp. 175–194, doi:10.1007/978‐94‐007‐4908‐5_4. 15. Buck, A.D. Recycled concrete as a source of aggregate. J. Am. Concr. Inst. 1977, 74, 212–219, doi:10.14359/11004. 16. Khan, M.; Ali, M. Use of glass and nylon fibers in concrete for controlling early age micro cracking in bridge decks. Constr. Build. Mater. 2016, 125, 800–808, doi:10.1016/j.conbuildmat.2016.08.111. 17. Arshad, S.; Sharif, M.B.; Irfan‐ul‐Hassan, M.; Khan, M.; Zhang, J.L. Efficiency of Supplementary Cementitious Materials and Natural Fiber on Mechanical Performance of Concrete. Arab. J. Sci. Eng. 2020, 45, 8577–8589, doi:10.1007/s13369‐020‐04769‐z. 18. Khan, M.; Cao, M.; Ali, M. Effect of basalt fibers on mechanical properties of calcium carbonate whisker‐steel fiber reinforced concrete. Constr. Build. Mater. 2018, 192, 742–753, doi:10.1016/j.conbuildmat.2018.10.159. 19. Cao, Y.F.; Tao, Z.; Pan, Z.; Wuhrer, R. Effect of calcium aluminate cement on geopolymer concrete cured at ambient temperature. Constr. Build. Mater. 2018, 191, 242–252, doi:10.1016/j.conbuildmat.2018.09.204. 20. Tabsh, S.W.; Abdelfatah, A.S. Influence of recycled concrete aggregates on strength properties of concrete. Constr. Build. Mater. 2009, 23, 1163–1167, doi:10.1016/j.conbuildmat.2008.06.007. 21. Li, X. Recycling and reuse of waste concrete in China. Part I. Material behaviour of recycled aggregate concrete. Resour. Conserv. Recycl. 2008, 53, 36–44, doi:10.1016/j.resconrec.2008.09.006. 22. Xiao J.Z.; Lan, Y. Investigation on the tensile behavior of recycled aggregate concrete. Jianzhu Cailiao Xuebao. J. Build. Mater. 2006, 9, 154‐8. 23. Rahal, K. Mechanical properties of concrete with recycled coarse aggregate. Build. Environ. 2007, 42, 407–415, doi:10.1016/j.buildenv.2005.07.033. 24. Xiao, J.Z.; Li, J.B. Study on relationships between strength indexes of recycled concrete. Jianzhu Cailiao Xuebao/J. Build. Mater. 2005, 8, 197–201. Available online: https://en.cnki.com.cn/Article_en/CJFDTotal‐JZCX20050200H.htm (accessed on 17 June 2021). 25. Khatib, J.M. Properties of concrete incorporating fine recycled aggregate. Cem. Concr. Res. 2005, 35, 763–769, doi:10.1016/j.cemconres.2004.06.017. 26. Chen, H.J.; Yen, T.; Chen, K.H. Use of building rubbles as recycled aggregates. Cem. Concr. Res. 2003, 33, 125–132, doi:10.1016/S0008‐8846(02)00938‐9. 27. Tam, V.W.Y.; Tam, C.M.; Wang, Y. Optimization on proportion for recycled aggregate in concrete using two‐stage mixing approach. Constr. Build. Mater. 2007, 21, 1928–1939, doi:10.1016/j.conbuildmat.2006.05.040. 28. Padmini, A.K.; Ramamurthy, K.; Mathews, M.S. Influence of parent concrete on the properties of recycled aggregate concrete. Constr. Build. Mater. 2009, 23, 829–836, doi:10.1016/j.conbuildmat.2008.03.006. 29. Tüfekçi, M.M.; Çakır, Ö. An Investigation on Mechanical and Physical Properties of Recycled Coarse Aggregate (RCA) Concrete with GGBFS. Int. J. Civ. Eng. 2017, 15, 549–563, doi:10.1007/s40999‐017‐0167‐x. 30. Etxeberria, M.; Vázquez, E.; Marí, A.; Barra, M. Influence of amount of recycled coarse aggregates and production process on properties of recycled aggregate concrete. Cem. Concr. Res. 2007, 37, 735–742, doi:10.1016/j.cemconres.2007.02.002. 31. Ahmad, A.; Farooq, F.; Niewiadomski, P.; Ostrowski, K.; Akbar, A.; Aslam, F.; Alyousef, R. Prediction of compressive strength of fly ash based concrete using individual and ensemble algorithm. Materials 2021, 14, 794, doi:10.3390/ma14040794. 32. Su, M.; Zhong, Q.; Peng, H.; Li, S. Selected machine learning approaches for predicting the interfacial bond strength between FRPs and concrete. Constr. Build. Mater. 2021, 270, 121456, doi:10.1016/j.conbuildmat.2020.121456. 33. Nguyen, K.T.; Nguyen, Q.D.; Le, T.A.; Shin, J.; Lee, K. Analyzing the compressive strength of green fly ash based geopolymer concrete using experiment and machine learning approaches. Constr. Build. Mater. 2020, 247, 118581, doi:10.1016/j.conbuildmat.2020.118581. 34. Ahmad, A.; Farooq, F.; Ostrowski, K.A.; Śliwa‐Wieczorek, K.; Czarnecki, S. Application of novel machine learning techniques for predicting the surface chloride concentration in concrete containing waste material. Materials 2021, 14, 2297, doi:10.3390/ma14092297.
Buildings – Multidisciplinary Digital Publishing Institute
Published: Jul 27, 2021
Keywords: recycled coarse aggregate; cement; concrete; gene expression programming; artificial neural network; machine learning
You can share this free article with as many people as you like with the url below! We hope you enjoy this feature!
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.