You are on page 1of 7

Computers and Concrete, Vol. 32, No.

6 (2023) 607-613
https://doi.org/10.12989/cac.2023.32.6.607 607

Comparative studies of different machine learning algorithms


in predicting the compressive strength of geopolymer concrete
Sagar Paruthi, Ibadur Rahmana and Asif Husainb

Department of Civil Engineering, Jamia Millia Islamia, New Delhi, India

(Received June 17 2023, Revised August 8, 2023, Accepted August 9, 2023)

Abstract. The objective of this work is to determine the compressive strength of geopolymer concrete utilizing four distinct
machine learning approaches. These techniques are known as gradient boosting machine (GBM), generalized linear model
(GLM), extremely randomized trees (XRT), and deep learning (DL). Experimentation is performed to collect the data that is
then utilized for training the models. Compressive strength is the response variable, whereas curing days, curing temperature,
silica fume, and nanosilica concentration are the different input parameters that are taken into consideration. Several kinds of
errors, including root mean square error (RMSE), coefficient of correlation (CC), variance account for (VAF), RMSE to
observation’s standard deviation ratio (RSR), and Nash-Sutcliffe effectiveness (NSE), were computed to determine the
effectiveness of each algorithm. It was observed that, among all the models that were investigated, the GBM is the surrogate
model that can predict the compressive strength of the geopolymer concrete with the highest degree of precision.
Keywords: compressive strength; GBM; geopolymer concrete; GLM; machine learning; XRT

1. Introduction qualities of geopolymer concrete based on these parameters,


machine learning algorithms can be trained on data from
Concrete known as geopolymer is produced from silicon prior trials. The necessity for costly and time-consuming
and aluminum-rich industrial byproducts like fly ash and physical experiments can be reduced as a result.
slag. Geopolymer concrete may be made without using Several machine learning algorithms are available in the
natural resources like limestone, which are essential to literature for predicting the strength of the different types of
produce Portland cement-based concrete. In comparison to concrete. Statistical analysis of different machine learning
conventional concrete, this makes it eco-friendlier and more algorithms in predicting the strength of concrete was
long-lasting. When compared to regular concrete, presented by Young et al. ( 2019). Ben Chaabene et al.
geopolymer concrete offers many benefits. It is more 2020) presented a critical review of different machine
durable, can withstand more stress, and is impervious to learning algorithms employed by the researchers for
chemicals. It’s cheaper to make and has a less carbon predicting the strength of the concrete. Khan et al. 2022) in
footprint. If successful, geopolymer concrete might replace their work highlighted the importance of machine learning
conventional concrete as the material of choice in the algorithms in predicting the behavior of concrete. The
building sector. major challenges towards the application of machine
It takes a long time to calculate the concrete’s strength learning algorithms in concrete industry were presented by
and characteristics once it has solidified. Machine learning Li et al. (2022).
methods may be used for the same purpose. Machine With the help of machine learning algorithms, (Ozcan et
learning is a subfield of AI that focuses on the creation of al. 2017) studied the influence of blast furnace slag and
algorithms with the ability to “learn” from data and then use waste tire rubber on the strength of the concrete. Using
that data to generate inferences and predictions (Chou et al. artificial neural network and neuro-fuzzy system, Miladirad
2014). Financial services, medical care, and even et al. ( 2021) predicted the compressive strength of concrete
transportation have all made use of machine learning. In containing waste tire rubber. Employing four different kinds
recent years, it has been used in the building trade to foretell of soft computing techniques, Dutta et al. (2018) predicted
the characteristics of geopolymer concrete. Several the compressive strength of concrete. Adaptive boosting
variables affect the final geopolymer concrete product, approach was employed by Feng et al. (2020) for predicting
including the raw components and quantities employed, the compressive strength of concrete. Unlu et al. (2020)
curing conditions, and mixing techniques. To forecast the predicted the slump flow of concrete using support vector
regression, random forest, and M5P trees models. With the
help of hybrid surrogate machine learning algorithms,
Corresponding author, Research Scholar Asteris et al. (2021) predicted the compressive strength of
E-mail: sparuthi57@gmail.com the concrete. Garg et al. (2022) predicted the compressive
a
Assistant Professor strength of the concrete containing nanosilica using support
b
Professor vector machine and Gaussian process regression algorithms.
Using radial basis function neural network Al-Gburi et al.
Copyright © 2023 Techno-Press, Ltd.
http://www.techno-press.org/?journal=cac&subpage=8 ISSN: 1598-8198 (Print), 1598-818X (Online)
608 Sagar Paruthi, Ibadur Rahman and Asif Husain

(2022) predicted the compressive strength of concrete. understood throughout the learning process.
Several works are available in literature regarding the Additive modelling is the foundation of boosting
prediction of compressive strength of different types of algorithms. The basic idea is to combine multiple smaller
concrete. functions to create a more complex one. As in gradient
The compressive strength of geopolymer paste, mortar, boosting, a complex model is created by combining
and concrete was predicted by Nazari and Sanjayan (2015) multiple simpler models. Gradient boosting employs a
using a variety of optimization approaches in conjunction weighted sum of a sufficient number of base learners to
with support vector machine and artificial neural network train a model.
algorithms. Gene expression programming technique was
𝐹0 (𝑥) = arg ∙ min ∑𝑛𝑖=1 𝐿(𝑦𝑖 , 𝛾) (1)
used by Shahmansouri et al. (2020) for predicting the 𝛾
compressive strength of GGBS-based geopolymer concrete.
For predicting the compressive strength of fly ash-based where, (𝑥𝑖 , 𝑦𝑖 )𝑛𝑖=1 represents the input dataset, 𝐿 (𝑦, 𝐹(𝑥))
geopolymer concrete, Nguyen et al. (2020) presented a deep is the differentiable loss function, and 𝑀 is the number of
residual network with no dropout and no normalization. iterations.
According to the study of Ahmad et al. (2021), the boosting For 𝑚 = 1 to 𝑀, the pseudo-residual is computed as
strategy outperformed ANN and AdaBoost for predicting 𝜕𝐿(𝑦𝑖 ,𝐹(𝑥𝑖 ))
the compressive strength of high calcium fly ash 𝑟𝑖𝑚 = − [ ]
𝜕𝐹(𝑥𝑖 )
geopolymer concrete. Cao et al. (2022) demonstrated that
𝐹(𝑥)=𝐹𝑚−1 (𝑥) (2)
XGBoost outperformed support vector machine and for 𝑖 = 1,2, … , 𝑛.
multilayer perceptron techniques in predicting the After that, a base learner ℎ𝑚 (𝑥) is fitted to the pseudo-
compressive strength of GPC. residuals i.e., it is trained using the training set. The
The use of machine learning techniques for predicting multiplier 𝛾𝑚 is computed as the optimization of the Eq. (3)
the strength of geopolymer concrete is relatively a new area as
to explore. In literature, most of the researchers used single
machine learning technique to predict the compressive 𝛾𝑚 = arg ∙ min ∑𝑛𝑖=1 𝐿(𝑦𝑖 , 𝐹𝑚−1 (𝑥𝑖 ) + 𝛾ℎ𝑚 (𝑥𝑖 )) (3)
𝛾
strength of geopolymer concrete. Present study aims to
carry out the compressive strength of geopolymer concrete The model is then updated as
using four different machine learning techniques, namely,
gradient boosting machine (GBM), generalized linear 𝐹𝑚 (𝑥) = 𝐹𝑚−1 (𝑥) + 𝛾𝑚 ℎ𝑚 (𝑥) (4)
model (GLM), extremely randomized trees (XRT), and
deep learning (DL) techniques. The data used for training 2.2 Generalized linear model (GLM)
the models are obtained experimentally. Four different input
parameters (curing days, curing temperature, silica fume, The response variable “y” is described in a linear
and nanosilica content) are taken as the input parameters regression model as a function or linear combination of all
while compressive strength is the response variable. The the predictors “X”. The underlying linear relationship
efficiency of each technique is worked out by computing between the predictors and response variables. Additionally,
the various errors such as, root mean square error (RMSE), the response variable’s error distribution should follow a
coefficient of correlation (CC), variance account for (VAF), normal distribution. Consequently, a linear model will be
RMSE to observation’s standard deviation ratio (RSR), and created. There are three main components in the case of
Nash-Sutcliffe Efficiency (NSE) were calculated. Amongst GLM: linear predictor (linear relation), link function (the
the models studied, GBM was found to be the most accurate function links linear predictor and the parameter for
surrogate model which can predict the compressive strength probability distribution), and probability distribution.
of the geopolymer concrete. Mathematically, the same can be expressed as
In 𝜆𝑖 = 𝑏0 + 𝑏1 𝑥1 (5)
2. Mathematical modeling
𝑦𝑖 ~Poisson(𝜆𝑖 ) (6)
In this section, the mathematical modeling for the GBM, where, ln is the link function and 𝑏0 + 𝑏1 𝑥𝑖 is the linear
GLM, XRT, and DL techniques is presented. predictor.
In next, the Poisson regression is applied. The prediction
2.1 Gradient boosting machine (GBM) curve looks like an exponential curve.
𝜆𝑖 = 𝑒𝑥𝑝(𝑏0 + 𝑏1 𝑥𝑖 ) (7)
A type of ensemble learning is the boosting approach.
These approaches’ fundamental principles revolve around
two steps: (1) learning about the base learners; and (2) 2.3 Extremely randomized trees (XRT)
combining all the learned models into a single forecast.
Gradient Boosting can be used with any differentially The XRT algorithm was presented by Geurts et al.
differentiable loss function because it is a generic model, (2006) and same has been employed during the present
however just because it can be demonstrated to work with a study.
squared loss model does not imply that it can be fully XRT builds the regression trees. This algorithm chooses
Comparative studies of different machine learning algorithms in predicting the compressive strength of geopolymer… 609

Table 1 Performance evaluation parameters with the ideal value


Index Ideal Value
1 2
Root Mean Square Error (RMSE) √ ∑𝑟𝑖=1(𝑥𝑖 − 𝑥𝑖𝑝 ) 0
𝑟
∑𝑟𝑖=1(𝑥𝑖 −𝑥̅𝑖 )(𝑥𝑖𝑝 −𝑥̅𝑖𝑝 )
Correlation Coefficient (CC) 2 1
√∑𝑟𝑖=1(𝑥𝑖 −𝑥̅ 𝑖 )2 ∑𝑟𝑖=1(𝑥𝑖𝑝 −𝑥̅𝑖𝑝 )
var(𝑥𝑖 −𝑥𝑖𝑝 )
Variance Account For (VAF) 1− 100
var(𝑥𝑖 )
RMSE
RMSE to observations’ standard deviation ratio (RSR) 0
Standard Deviation
2
∑𝑟𝑖=1(𝑥𝑖 −𝑥𝑖𝑝 )
Nash-Sutcliffe Efficiency (NSE) 1 − [∑𝑟 ] 1
𝑖=1(|𝑥𝑖 −𝑥𝑖𝑝 |+|𝑥𝑖 −𝑥̅ 𝑖 |)

carefully the nodes which are to be cut at random and to taken as the input, whereas the compressive strength of the
grow new trees. At first, a node is to be spilt based on the geopolymer concrete is the response variable.
attributes of the dataset 𝑆. If the split is true, then the code
will return nothing, else, it will select the attributes 𝐾 2.6 Performance evaluation
among nonconstant attributes. Then the splits are drawn as
For evaluating the performance of the four ML
{𝑠1 … 𝑠𝑘 } (8) algorithms employed during the present work, the errors are
where 𝑠𝑖 represents a randomized split that has to be determined as reported in Table 1.
considered. Where, 𝑥𝑖 and 𝑥𝑖𝑝 are the actual and predicted value for
Now, the score is calculated as the compressive strength of the geopolymer concrete and 𝑟
denotes the total dataset count used. The bar above the 𝑥
𝑆𝑐𝑜𝑟𝑒(𝑠∗ , 𝑆) = 𝑚𝑎𝑥𝑖=𝑖…𝑘 𝑆𝑐𝑜𝑟𝑒(𝑠𝑖 , 𝑆) (9) represents the mean value.
In the similar manner, if the split from all the nodes
returns as constant, the XRT gives that value as the final
predicted output. 3. Results and discussion

2.4 Deep learning (DL) In this investigation, compressive strength of samples is


determined for experimental results by using different mix
proportion as shown in Table 2 and then MATLAB was
Some of the data pre-processing that is generally
used to create a variety of machine learning models. The
involved with machine learning is eliminated with deep
AMD Ryzen 5 5625U 2.30 GHz laptop with Radeon
learning. These algorithms can handle text and visual data
Graphics is used to assess the model’s performance,
that is unstructured and automate feature extraction,
together with 8 GB of RAM. All the input data is
reducing the need for human specialists.
normalized between zero and one to ensure objectivity. To
Deep neural networks are made up of many layers of further eliminate bias in the ML algorithm’s training
interconnected nodes, each of which improves upon the process, its training data % was selected at random. For
prediction or categorization made by the one underneath it. obtaining the effective percentage of the data to be used for
Forward propagation refers to the movement of calculations training the model, the models are trained using 40%, 50%,
through the network. A deep neural network’s visible layers 60%, 70%, and 80% training data. The errors are computed
are its input and output layers. The deep learning model for predicted value of the compressive strength for the
ingests the data for processing in the input layer, and the unseen dataset (testing dataset). The violin-box plots are
final prediction or classification is performed in the output plotted for the range of errors obtained. The results for the
layer. same are reported in Fig. 1. In the present study, 80% of the
Backpropagation is a different method that uses data is used for training the model and remaining 20% is
techniques like gradient descent to calculate prediction used for testing the model as the error is least in this case.
errors before changing the function’s weights and biases by The various errors obtained for the training (Tr) and the
iteratively going back through the layers to train the model. testing (Te) models are represented in Table 3.
A neural network can make predictions and make necessary The GBM model predicted the compressive strength of
corrections for any faults thanks to forward propagation and the geopolymer concrete most effectively as the errors
backpropagation working together. The algorithm obtained for GBM model is nearer to the ideal values (ideal
continuously improves in accuracy over time. values are reported in Table 2 in brackets) followed by DL
algorithm. GLM was found to perform worst in predicting
2.5 Dataset the compressive strength of geopolymer concrete amongst
the models studied.
The dataset used for training the model is obtained Details of models trained: Hereby, the details of the
experimentally. The four variables namely, curing days, GBM, GLM, XRT, and DL models trained using 80%
curing temperature, silica fume, and nanosilica content are training dataset is presented. Fig. 2 presents the variation of
610 Sagar Paruthi, Ibadur Rahman and Asif Husain

Table 2 GPC mix proportions of materials for different grades of concrete (kg/m 3)
Coarse Curing
Mix FA GGBS Alccofine Nano Silica Silica Fume Sand
Aggregate temperature (°C)
N0C27 149.17 213.1 63.93 0 0 547.8 1276.8 27
N0C60 149.17 213.1 63.93 0 0 547.8 1276.8 60
N0C75 149.17 213.1 63.93 0 0 547.8 1276.8 75
N0C90 149.17 213.1 63.93 0 0 547.8 1276.8 90
N0120 149.17 213.1 63.93 0 0 547.8 1276.8 120
N0.5C27 149.17 213.1 63.93 2.13 21.13 547.8 1276.8 27
N0.5C60 149.17 213.1 63.93 2.13 21.13 547.8 1276.8 60
N0.5C75 149.17 213.1 63.93 2.13 21.13 547.8 1276.8 75
N0.5C90 149.17 213.1 63.93 2.13 21.13 547.8 1276.8 90
N0.5C120 149.17 213.1 63.93 2.13 21.13 547.8 1276.8 120
N1C27 149.17 213.1 63.93 4.26 42.6 547.8 1276.8 27
N1C60 149.17 213.1 63.93 4.26 42.6 547.8 1276.8 60
N1C75 149.17 213.1 63.93 4.26 42.6 547.8 1276.8 75
N1C90 149.17 213.1 63.93 4.26 42.6 547.8 1276.8 90
N1C120 149.17 213.1 63.93 4.26 42.6 547.8 1276.8 120
N1.5C27 149.17 213.1 63.93 6.39 63.9 547.8 1276.8 27
N1.5C60 149.17 213.1 63.93 6.39 63.9 547.8 1276.8 60
N1.5C75 149.17 213.1 63.93 6.39 63.9 547.8 1276.8 75
N1.5C90 149.17 213.1 63.93 6.39 63.9 547.8 1276.8 90
N1.5C120 149.17 213.1 63.93 6.39 63.9 547.8 1276.8 120

(a) (b)

(c) (d)
Fig. 1 Variation of % error (×100) (represented as range on Y-axis) for unseen dataset [% error=(predicted value-actual
value×100)/actual value] for different count of training dataset used for training the machine learning algorithm (a) GBM, (b)
GLM, (c) XRT and (d) DL (The error is determined for the testing dataset, i.e., unseen dataset (Range on Y-axis indicates the
error range in the prediction of the compressive strength of the concrete for model obtained using different % of training
dataset in training the model).)
Comparative studies of different machine learning algorithms in predicting the compressive strength of geopolymer… 611

Table 3 Statistical errors in predicting the compressive strength of the geopolymer concrete
RMSE (0) CC (1) VAF (100) RSR (0) NSE (1)
Model
Tr Te Tr Te Tr Te Tr Te Tr Te
GBM 0.0204 0.0357 0.9142 0.8870 98.940 96.342 0.0289 0.0401 0.9091 0.8762
DL 0.0791 0.0952 0.8308 0.7771 96.703 94.551 0.0810 0.0993 0.8123 0.7853
XRT 0.1789 0.2150 0.7017 0.6545 93.392 91.187 0.2072 0.3260 0.6004 0.5499
GLM 0.4002 0.4471 0.5893 0.5102 90.568 88.045 0.4291 0.5529 0.5132 0.4885

(a) (b)

(c) (d)
Fig. 2 Variation of the training and testing deviance for (a) GBM, (b) GLM, (c) XRT and (d) DL for different model
parameters

the training and deviance of the compressive strength of the predicted values lie outside the range of ±5%. Thus, GBM
geopolymer concrete for different model parameters. For can predict the compressive strength of geopolymer
GBM, as the number of trees reaches 135, the deviance concrete with good accuracy.
becomes constant. Similar types of studies are also carried Reason for the best performance of GBM compared to
out with respect to the leaves and depth. In the case of XRT, the other modes studied: The GBM is found to perform best
the model trained using 30 number of trees shows minimum compared to the DL, XRT, and GLM models. The reason
value for the deviance. Hence, the same number of trees are for the same can be summarized as:
adopted for training the XRT model. In the case of GLM, • Because the gradient boosting model adheres to
after 20 iterations, the deviance became constant. Therefore, ensemble learning, handling and interpreting the data is
the same is adopted in further studies. DL trained using simpler.
8000 epochs is used for further studies. The details of the • GBM is one of the best methods for processing bigger
GBM and XRT models are presented in Table 4. datasets and computing with weak learners at least loss.
Fig. 3 shows the agreement line diagram for the • A robust technique for machine learning that can
predicted v/s the actual value for the compressive strength quickly detect overfitting training datasets is the
of the geopolymer concrete using the trained models. For gradient boosting algorithm.
the GBM model, most of the values lie within the error Sensitivity analysis: The output variable is always
range of ±5% with maximum values lying near to the dependent on the several input variables. However, the
perfect agreement line i.e., the line on which the actual and extent of the dependency of the output is different for all the
predicted values are same. In the case of GLM, most of the input variables adopted. Hereby, the results for the
612 Sagar Paruthi, Ibadur Rahman and Asif Husain

(a) (b)

(c) (d)
Fig. 3 Actual v/s predicted value for compressive strength of geopolymer concrete obtained using (a) GBM, (b) DL, (c) XRT
and (d) GLM models for unseen dataset

Table 4 Model parameters for GBM and GLM models


Model parameters GBM GLM
Number of trees 135 30
Minimum depth 2 5
Maximum depth 3 9
Minimum leaves 3 10
Maximum leaves 4 31

4. Conclusions

Fig. 4 Sensitivity of the output variable i.e., compressive Present study aims to predict the compressive strength
strength on different input variables adopted over the scaled of geopolymer concrete using four different machine
importance to 1 learning techniques, namely, GBM, DL, XRT, and GLM.
Four different input parameters were considered for training
the models. The dataset used during the present study was
sensitivity analysis are presented in Fig. 4. It can be seen obtained experimentally. It was observed that the GBM was
that all the algorithms predicted that the nanosilica content able to predict the compressive strength of the geopolymer
widely affects the compressive strength of the GPC. This is concrete with good accuracy followed by DL technique.
true to a large extent as the nanosilica is the finest material GLM was not able to predict the compressive strength as
that is adopted in the present work. Finer the material is the error in case of GLM was large.
used during the preparation of the concrete, more will be
the compressive strength obtained, keeping the other
parameters constant. Followed by nanosilica content, References
temperature is observed to be the second most important
Ahmad, A., Ahmad, W., Chaiyasarn, K., Ostrowski, K.A., Aslam,
variable affecting the compressive strength of the concrete, F., Zajdel, P. and Joyklad, P. (2021), “Prediction of geopolymer
while silica fume being the lowest one. concrete compressive strength using novel machine learning
Comparative studies of different machine learning algorithms in predicting the compressive strength of geopolymer… 613

algorithms”, Polym., 13, 3389. Build. Eng., 31, 101326.


https://doi.org/10.3390/polym13193389. https://doi.org/10.1016/j.jobe.2020.101326.
Al-Gburi, S.N.A., Akpinar, P. and Helwan, A. (2022), “Machine Unlu, R. (2020), “An assessment of machine learning models for
learning in concrete’s strength prediction”, Comput. Concrere, slump flow and examining redundant features”, Comput.
29, 433-444. https://doi.org/10.12989/cac.2022.29.6.433. Concrete, 25, 565-574.
Asteris, P.G., Skentou, A.D., Bardhan, A., Samui, P. and https://doi.org/https://doi.org/10.12989/cac.2020.25.6.565.
Pilakoutas, K. (2021), “Predicting concrete compressive Young, B.A., Hall, A., Pilon, L., Gupta, P. and Sant, G. (2019),
strength using hybrid ensembling of surrogate machine learning “Can the compressive strength of concrete be estimated from
models”, Cement Concrete Res., 145, 106449. knowledge of the mixture proportions?: New insights from
https://doi.org/10.1016/j.cemconres.2021.106449. statistical analysis and machine learning methods”, Cement
Ben Chaabene, W., Flah, M. and Nehdi, M.L. (2020), “Machine Concrete Res., 115, 379-388.
learning prediction of mechanical properties of concrete: https://doi.org/10.1016/j.cemconres.2018.09.006.
Critical review”, Constr. Build. Mater., 260, 119889.
https://doi.org/10.1016/j.conbuildmat.2020.119889.
Cao, R., Fang, Z., Jin, M. and Shang, Y. (2022), “Application of CC
machine learning approaches to predict the strength property of
geopolymer concrete”, Mater., 15, 2400.
https://doi.org/10.3390/ma15072400.
Chou, J.S., Tsai, C.F., Pham, A.D. and Lu, Y.H. (2014), “Machine
learning in concrete strength simulations: Multi-nation data
analytics”, Constr. Build. Mater., 73, 771-780.
https://doi.org/10.1016/j.conbuildmat.2014.09.054.
Dutta, S., Samui, P. and Kim, D. (2018), “Comparison of machine
learning techniques to predict compressive strength of
concrete”, Comput. Concrete, 21, 463-470.
https://doi.org/10.12989/cac.2018.21.4.463.
Feng, D.C., Liu, Z.T., Wang, X.D., Chen, Y., Chang, J.Q., Wei,
D.F. and Jiang, Z.M. (2020), “Machine learning-based
compressive strength prediction for concrete: An adaptive
boosting approach”, Constr. Build. Mater., 230, 117000.
https://doi.org/10.1016/j.conbuildmat.2019.117000.
Garg, A., Aggarwal, P., Aggarwal, Y., Belarbi, M.O., Chalak,
H.D., Tounsi, A. and Gulia, R. (2022), “Machine learning
models for predicting the compressive strength of concrete
containing nano silica”, Comput. Concrete, 30, 33-42.
https://doi.org/10.12989/cac.2022.30.1.033.
Geurts, P., Ernst, D. and Wehenkel, L. (2006), “Extremely
randomized trees”, Mach. Learn., 63, 3-42.
https://doi.org/10.1007/s10994-006-6226-1.
Khan, K., Ahmad, W., Amin, M.N. and Ahmad, A. (2022), “A
systematic review of the research development on the
application of machine learning for concrete”, Mater., 15, 4512.
https://doi.org/10.3390/ma15134512.
Li, Z., Yoon, J., Zhang, R., Rajabipour, F., Srubar III, W.V, Dabo,
I. and Radlińska, A. (2022), “Machine learning in concrete
science: Applications, challenges, and best practices”, Comput.
Mater., 8, 127. https://doi.org/10.1038/s41524-022-00810-x.
Miladirad, K., Golafshani, E.M., Safehian, M. and Sarkar, A.
(2021), “Modeling the mechanical properties of rubberized
concrete using machine learning methods”, Comput. Concrete,
28, 567-583. https://doi.org/10.12989/cac.2021.28.6.567.
Nazari, A. and Sanjayan, J.G. (2015), “Modelling of compressive
strength of geopolymer paste, mortar and concrete by optimized
support vector machine”, Ceram. Int., 41, 12164-12177.
https://doi.org/10.1016/j.ceramint.2015.06.037.
Nguyen, K.T., Nguyen, Q.D., Le, T.A., Shin, J. and Lee, K.
(2020), “Analyzing the compressive strength of green fly ash
based geopolymer concrete using experiment and machine
learning approaches”, Constr. Build. Mater., 247, 118581.
https://doi.org/10.1016/j.conbuildmat.2020.118581.
Ozcan, G., Kocak, Y. and Gulbandilar, E. (2017), “Estimation of
compressive strength of BFS and WTRP blended cement
mortars with machine learning models”, Comput. Concrete, 9,
275-282. https://doi.org/10.12989/cac.2017.19.3.275.
Shahmansouri, A.A., Akbarzadeh Bengar, H. and Ghanbari, S.
(2020), “Compressive strength prediction of eco-efficient
GGBS-based geopolymer concrete using GEP method”, J.

You might also like