applied

sciences
Article
Artificial Intelligence-Based Model for the Prediction
of Dynamic Modulus of Stone Mastic Asphalt
Thanh-Hai Le 1 , Hoang-Long Nguyen 1, *, Binh Thai Pham 1 , May Huu Nguyen 1 ,
Cao-Thang Pham 2 , Ngoc-Lan Nguyen 3 , Tien-Thinh Le 4, * and Hai-Bang Ly 1, *
1 University of Transport Technology, Hanoi 100000, Vietnam; hailt@utt.edu.vn (T.-H.L.);
binhpt@utt.edu.vn (B.T.P.); maynh@utt.edu.vn (M.H.N.)
2 Le Quy Don Technical University, Hanoi 100000, Vietnam; caothang.cdsb@gmail.com
3 University of Transport and Communications, Hanoi 100000, Vietnam; nguyenngoclan@utc.edu.vn
4 Institute of Research and Development, Duy Tan University, Da Nang 550000, Vietnam
* Correspondence: longnh@utt.edu.vn (H.-L.N.); letienthinh@duytan.edu.vn (T.-T.L.);
banglh@utt.edu.vn (H.-B.L.)




Received: 1 July 2020; Accepted: 26 July 2020; Published: 29 July 2020


Abstract: Stone Mastic Asphalt (SMA) is a tough, stable, rut-resistant mixture that takes advantage
of the stone-to-stone contact to provide strength and durability for the material. Besides, the warm
mix asphalt (WMA) technology allows reducing emissions and energy consumption by reducing
the production temperature by 30–50 ◦ C, compared to conventional hot mix asphalt technology
(HMA). The dynamic modulus |E*| has been acknowledged as a vital material property in the
mechanistic-empirical design and analysis and further reflects the strains and displacements of such
layered pavement structures. The objective of this study is twofold, aiming at favoring the potential
use of SMA with WMA technique. To this aim, first, laboratory tests were conducted to compare the
performance of SMA and HMA through the dynamic modulus. Second, an advanced hybrid artificial
intelligence technique to accurately predict the dynamic modulus of asphalt mixtures was developed.
This hybrid model (ANN-TLBO) was based on an Artificial Neural Network (ANN) algorithm and
Teaching Learning Based Optimization (TLBO) technique. A database containing the as-obtained
experimental tests (96 data) was used for the development and assessment of the ANN-TLBO model.
The experimental results showed that SMA mixtures exhibited higher values of the dynamic modulus
|E*| than HMA, and the WMA technology increased the dynamic modulus values compared with
the hot technology. Furthermore, the proposed hybrid algorithm could successfully predict the
dynamic modulus with remarkable values of R2 of 0.989 and 0.985 for the training and testing datasets,
respectively. Lastly, the effects of temperature and frequency on the dynamic modulus were evaluated
and discussed.

Keywords: stone mastic asphalt; warm mix asphalt; hot mix asphalt; dynamic modulus; artificial
neural network; teaching–learning-based optimization

1. Introduction
In recent decades, the manufacture and application of asphalt mixture have been significantly
increasing because of excellent adhesion to mineral aggregates and viscoelastic properties [1,2]. In order
to address economic and environmental objectives, a number of asphalt mixtures were proposed,
including dense-graded asphalt concrete, stone mastic asphalt (SMA), rubberized asphalt, crumb rubber
asphalt concrete, and asphalt concrete incorporated [3–5]. Additionally, from a practical viewpoint,
mixing techniques were also considered as an important stage for an asphalt mixture, gaining its
targeted performances [3,4,6,7]. Among these, dense-graded asphalt and stone mastic asphalt (SMA)

Appl. Sci. 2020, 10, 5242; doi:10.3390/app10155242 www.mdpi.com/journal/applsci

Appl. Sci. 2020, 10, 5242 2 of 22

mixtures applying the hot (HMA) and warm (WMA) mixing techniques are two typical applications of
asphalt mixtures that received more attention from researchers [4,8–10].
Historically, hot mix asphalt (HMA) has been the most popular paving material for
roadways [11–15]. The mechanism of this technology is based on high temperatures during mixing
and compaction stages to ensure the workability and achieve the desired in-place density of the
asphalt mixture. However, HMA mixtures disclosure some notable defects, such as high energy
consumption, significant greenhouse gas emissions, hazardous fume, and unpleasant odors [12].
In addition, the high-temperature requirement and relatively longer cooling periods somehow limit its
applicability, especially for high volume roadways built with heat-sensitive polymer modified mixes.
Adapting with the need to reduce resource consumption and environmental emissions, Warm Mix
Asphalt (WMA) has gradually been acknowledged as a promising technology in the pavement structure.
This technique includes several notable advantages in the environmental aspect as well as enhances the
characteristics of asphalt binders and mixtures [4,9,12,16,17]. This technology can significantly reduce
the temperature of asphalt mixtures for the mixing and compacting processes by lowering the viscosity
and casing foaming in the asphalt binders. The energy required to produce WMA decreases emissions
and odors from plants and hence creates a better working condition at the plant and the paving
site [18,19]. In this technique, emissions and energy consumption can be significantly reduced due to its
necessary mix temperature lower 30–50 ◦ C compared to conventional HMA [11,16]. These features lead
to numerous benefits in several respects of WMA productions, such as environmental (reduced factory
emissions), cost-effective, production, and paving process (increased workability and compaction
performance) [4,16,17,20,21]. So far, it is quite acceptable to state that WMA is a potential solution that
can balance environmental and performance objectives [3].
Indeed, the changes in features of asphalt mixtures (HMA or SMA) in cases of HMA or WMA
techniques can be reflected through several characteristics, including chemical, physic-mechanical
properties, and durability [3,14,16,17,21]. Among these characteristics, dynamic modulus, |E*|, has not
only been increasingly acknowledged as a vital material property in mechanistic-empirical design
and analysis [22] but has further reflected the pavement structures (e.g., strain and displacement)
caused by loading rate and temperature [23,24]. It is a primary property determined in the superpave
simple performance method protocol that supplements the design of volumetric. Besides, the dynamic
modulus |E*| plays a vital role as an essential linear viscoelastic characteristic that can be employed
in asphalt mixtures and pavements models [25]. In other words, the dynamic modulus |E*| can be
employed as a useful index to evaluate the effectiveness of the mixing technologies.
Various approaches have been, therefore, proposed for predicting the dynamic modulus |E*|
utilizing regression analysis based on laboratory measurements [7,22,26–28], modification of existing
predictive equation in AASHTOWare [29], or Artificial Intelligence (AI) methods [25,30–33]. The most
commonly used comprehensive and scientific approach, in terms of laboratory measurements,
is related to a mechanistic approach, namely Mechanistic-Empirical Pavement Design Guide (MEPDG).
This approach recommended the determination of the dynamic modulus at three levels [34]. However,
the experimental part might not always be possible due to the lack of facilities or equipment. Besides,
several models have been presented to overcome these difficulties, especially those proposed in
the works of Witczak 1999 [35], Witczak 2006 [22], Hirsch [36], and Al-Khateeb [37]. Even though
these models have been roughly validated, the effectiveness is still being questioned, owing to the
variation of predicted results for different asphalt mixtures [22,38–44]. In addition, several studies have
found that these models sometimes seem to overemphasize the effect of temperature, other mixture
properties, or overpredict the dynamic modulus, for instance, in the works of Obulareddy [38],
Birgisson et al. [24], Tran and Hall [40], and Kim et al. [42]. In several extreme conditions, i.e., high or
low temperature, the Witczak 2006 and the Al-Khateeb models have also been found to overpredict the
dynamic modulus [31,45–47]. On the contrary, the Hirsch model has been found to underpredict the
dynamic modulus, as reported in the works of Bari and Witczak [22], Obulareddy [38], Kim et al. [42],
Appl. Sci. 2020, 10, 5242 3 of 22

and Ceylan et al. [47]. These results showed that the prediction models of the expected dynamic
modulus |E*| still need further clarification and investigation.
Considering the modern approach, Ceylan et al. [30] presented and compared a series of Artificial
Neural Network (ANN) models with some existing models to predict the dynamic modulus |E*| of
HMA. The ANN models indicated a notable accuracy compared with the conventional regression
models and can be applied to the mechanistic-empirical pavement design guide. Far et al. [31] attempted
to develop novel models to predict the dynamic modulus |E*| of HMA mixtures in the case of long-term
pavement performance. The data consisted of measured moduli from many geographical places
around the United States. The obtained results indicated that the predicted dynamic modulus |E*|
utilizing ANN and measured dynamic modulus |E*| values were well matched. Sakhaeifar et al. [25]
also proposed a fundamental modeling framework to predict dynamic modulus |E*| of HMA using
viscoelastic principles combined with the physical and mechanical characteristics of the mixture.
The proposed dynamic modulus models were verified as reliable and appropriate for a wide scope of
temperatures and recommended in the AASHTO TP62-03 test protocol. Despite that, the application of
a machine learning approach to SMA mixtures is still limited, and further elaboration of the dynamic
modulus in function of the temperature and frequency is required.
On the basis of sustainable development and environmental standpoints, the current study,
therefore, aims at favoring the potential use of SMA with warm technology from two different angles.
From an experimental point of view, dynamic modulus tests were performed to highlight the beneficial
aspect of SMA using warm technology compared with the hot technology, as well as conventional
dense-graded asphalt concretes. From a simulation angle, a novel machine learning algorithm was
developed to accurately predict the desired mechanical property of the asphalt mixtures, and thus to
facilitate the use in the design process or the construction and operation stages. To this aim, a total of
576 experimental tests on dynamic modulus were carried out to construct a database of 96 instances
by taking the average values per 6. In parallel, the ANN-TLBO machine learning algorithm was
developed, consisting of one well-known machine learning model (ANN) and an effective optimization
algorithm, namely Teaching-Learning Based Optimization (TLBO). The performance of the proposed
ANN-TLBO model was evaluated by three common statistical criteria, including root mean square
error (RMSE), mean absolute error (MAE), and coefficient of determination (R2 ).
The present paper is structured as follows: (i) an overview of the state of the art of the problem is
presented in the first section; (ii) the significance of the study is given in Section 2; (iii) the experimental
procedure is provided in the next section, including the materials, design, mixing, and testing of
the asphalt mixtures; (iv) a brief overview of the machine learning algorithms is given in Section 4;
and (v) the experimental and simulation results are presented in Section 5. Several conclusions and
perspectives are finally given in the last section of the paper.

2. Significance of the Study

Considering environmental factors and beneficial aspects of SMA using warm technology,
an in-depth investigation of such an asphalt concrete is crucial. Nevertheless, only limited reports on the
dynamic modulus |E*| of SMA using warm technology have been conducted in the literature [12,48,49].
To the best of the authors’ knowledge, only a few contributions were found in the literature. In addition,
so far, no direct comparison between the dynamic modulus |E*| of SMA and conventional asphalt
concrete applying the hot and warm technologies using machine learning approach has been performed
yet. Therefore, benefitting the present study are the various points as follows: (i) a complete
experimental comparison between two types of asphalt mixtures (i.e., HMA and SMA) and technologies
(i.e., hot and warm) was given for the first time; (ii) success in decreasing the mixing and compacting
temperatures was proven in the literature but only for recycled aggregates [12,48], this study showed a
similarly successful result of the dynamic modulus of asphalt mixture in using conventional aggregates;
(iii) a novel machine learning (ML) algorithm was developed to accurately predict the dynamic
Appl. Sci. 2020, 10, 5242 4 of 22

modulus of the four mentioned asphalt mixtures; (iv) the dependency of the dynamic modulus on
diverse input variables was proposed thanks to the developed ML algorithm.

3. Experimental

3.1. Material Properties

In this study, crushed aggregates, including fine and coarse aggregates, were collected from
a local quarry at Khau Dem, Quan Son commune, Chi Lang district, Lang Son province, in the
North of Vietnam. The compressive strength of the bedrock in the saturated condition is reported as
138.26 MPa. The mineral filler was collected from a local quarry at Kien Khe, Ha Nam Province, Vietnam.
The physical properties of fine, coarse aggregates and mineral filler were given in Table 1. Besides,
Polymer Modified Bitumen III (PMB III) was chosen as the asphalt cement, and the corresponding
physical properties are shown in Table 2. They were provided by the Vietnam National Petroleum
Group (Petrolimex), Ha Noi, Vietnam. Cellulose fiber used in the SMA mixtures was a type of
ARBOCEL ZZ 8/1, provided by JRS Company, JRS, J. RETTENMAIER & SÖHNE Group, Germany.
Sasobit, an organic additive based on polymethylene, was obtained from Sasol Company. The physical
properties of Sasobit are shown in Table 3.

Table 1. Physical properties of coarse and fine aggregates and mineral filler.

Properties Unit Dmax 19 Dmax 12.5 Dmax 5 Mineral Filler Standard

Compressive strength of the bedrock MPa 138.28 138.28 - - TCVN 7572-10
Bulk Specific Gravity - 2.863 2.846 2.792 2.709 AASHTO T85
Apparent Specific Gravity - 2.922 2.916 2.893 2.709 AASHTO T85
Water absorption % 0.695 0.849 1.247 - AASHTO T85
Bulk density kg/m3 1445 1438 1572 - ASTM C29
Los Angeles abrasion % 9.3 12.1 - - AASTHO T96
Flat and elongation in aggregates
% 8.6 10.0 - - ASTM D4791
D ≥ 9.5 mm
Flat and elongation in aggregates
% 0.0 16.2 - - ASTM D4791
D < 9.5 mm
Clay, dust content % 0.7 1.2 2.2 - ASTM C117
Coating and Stripping of Bitumen Level Level 4 Level 4 - - TCVN 7504
Fineness modulus Mk - - - 3.9 - TCVN 7572-2
Sand Equivalent-SE % - - 87.8 - AASHTO T176
Fine Aggregate Angularity % - - 50.7 - AASHTO T 304

Table 2. Physical properties of Polymer Modified Bitumen (PMB) III and PMB III with Sasobit.

Properties PMB III PMB III with Sasobit Standard

Penetration at 25 ◦C (0.1 mm) 51 43 ASTM D 5
Ductility at 25 ◦ C (cm) >100 >100 ASTM D 113
Flash point (◦ C) 248 270 ASTM D 92
Specific gravity at 25 ◦ C (g/cm3 ) 1034 1026 ASTM D 70
Softening point (◦ C) 89 95 ASTM D 36

Table 3. Physical properties of Sasobit.

Properties Value Standard

Crystallizing temperature, ◦C ≈100 DIN-ISO 2207
Softening point (◦ C) 112–120 ASTM D 3954
Flashpoint (◦ C) 285 -
Specific Gravity at 25 ◦ C, kg/m3 950 DIN 51 757
Viscosity at 135 ◦ C, mm2 /s 10–14 DIN 51 562
Specific Gravity at 140 ◦ C, kg/m3 750 DIN 51 757
 Flashpoint (°C) 285 -
Specific Gravity at 25 °C, kg/m3 950 DIN 51 757
Viscosity at 135 °C, mm2/s 10–14 DIN 51 562
Specific Gravity at 140 °C, kg/m3 750 DIN 51 757
Appl. Sci. 2020, 10, 5242 5 of 22
3.2. Mix Design, Sample Preparation, and Testing
3.2. Mix Design,
In this study, Sample
fourPreparation, and Testing
types of mixtures with the 12.5 mm nominal maximum aggregate size were
prepared,
In thisincluding
study, four (1)types
SMAofapplying
mixturesthe withwarm mixing
the 12.5 mmtechniques (denotedaggregate
nominal maximum as SMA-W); size(2) SMA
were
applying the hot mixing techniques (denoted as SMA-H); (3) Dense-graded
prepared, including (1) SMA applying the warm mixing techniques (denoted as SMA-W); (2) SMA asphalt concrete applying
the warmthe
applying mixing techniques
hot mixing (denoted
techniques as HMA-W)
(denoted as SMA-H); and(3)
(4)Dense-graded
Dense-gradedasphalt
asphalt concrete
concrete applying
applying
the hot mixing techniques (denoted as HMA-H).
the warm mixing techniques (denoted as HMA-W) and (4) Dense-graded asphalt concrete applying
the hotThe aggregate
mixing gradation
techniques of SMA-W
(denoted as HMA-H). and SMA-H mixtures was designed according to the
AASHTO M325 [50] and plotted in Figure
The aggregate gradation of SMA-W and SMA-H 1a. Besides, the aggregate
mixtures gradation
was designed of HMA-W
according and HMA-
to the AASHTO
H
M325mixtures
[50] andwere subjected
plotted in Figureto1a.
theBesides,
Vietnamese standard
the aggregate [51] (Decision
gradation of HMA-W858,and
Ministry
HMA-H of mixtures
Transport,
Vietnam)
were and plotted
subjected in Figure 1b.
to the Vietnamese For SMA-W
standard and SMA-H
[51] (Decision mixtures,ofthe
858, Ministry optimalVietnam)
Transport, asphalt content
and
(i.e., PMB III) was found as 6.7% (% weight of the mixture), whereas for
plotted in Figure 1b. For SMA-W and SMA-H mixtures, the optimal asphalt content (i.e., PMB III) wasHMA-W and HMA-H
mixtures,
found as 6.7% the (%optimum
weight of asphalt contentwhereas
the mixture), was 5.1% for (% weight
HMA-W andof HMA-H
the mixture). Thethe
mixtures, cellulose
optimum fiber
content in SMA mixtures was kept constant at 0.3% (% weight of the mixture),
asphalt content was 5.1% (% weight of the mixture). The cellulose fiber content in SMA mixtures whereas no cellulose
fiberkept
was wasconstant
added in at HMA
0.3% (% mixtures.
weight ofThe the mixtures
mixture), were
whereasmanufactured
no cellulose by warm
fiber technology
was added in HMA using
Sasobit
mixtures. additive with 2%were
The mixtures weight of PMB III. Prior
manufactured to thetechnology
by warm mixing process,
usingSasobit
Sasobitadditives
additivewere
with mixed
2%
with PMB
weight III for
of PMB III.20 mintoatthe
Prior 160mixing
°C–170 °C. TheSasobit
process, SMA and HMAwere
additives mixtures
mixedapplying
with PMB the
IIIwarm
for 20 mixing
min
at 160 ◦ C–170
techniques ◦ C. The SMA and HMA mixtures applying the warm mixing techniques were mixed
were mixed and compacted to 160 °C and 140 °C, respectively. The SMA and HMA
and compacted ◦ C and 140 ◦ C, respectively. The SMA and HMA mixtures using the hot mixing
mixtures usingtothe 160 hot mixing techniques were mixed and compacted to 190 °C and 170 °C,
techniques were mixed and compacted to 190 ◦ C and 170 ◦ C, respectively.
respectively.

(a) (b)
100 100
Lower limit Upper limit
80 80

Passing (%)
Passing (%)

Upper limit Lower limit

60 60
SMA HMA
40 40

20 20

0 0
0.075 0.75 7.5 0.075 0.75 7.5
Sieve size (mm) Sieve size (mm)

Figure 1. Mixture gradation aggregate (a) Stone Mastic Asphalt (SMA) samples, (b) hot mix asphalt
Figure 1. Mixture gradation aggregate (a) Stone Mastic Asphalt (SMA) samples, (b) hot mix asphalt
(HMA) samples.
(HMA) samples.
Regarding the determination of the dynamic modulus |E*|, laboratory tests in accordance with
AASHTORegarding the determination
TP 62 [52] were conducted. of The
the dynamic
short-termmodulus
aging of|E*|, laboratory
asphalt concrete tests in accordance
was firstly conducted,with
AASHTO
followed by TPthe62 AASHTO
[52] were conducted.
R30 standard. TheThe
short-term aging
compaction of asphalt
process concrete
was next was firstly
performed on a conducted,
rotating
followed by the AASHTO R30 standard. The compaction process was next performed
compactor in order to achieve air void content of 7 ± 0.5%. The specimen, flattened at both ends, on a had
rotating
a
compactor in order to achieve air void content
height of 100 mm and a diameter of 100 mm (Figure 2). of 7 ± 0.5%. The specimen, flattened at both ends, had
a height of 100 mm
All samples and
were a diameter
placed of 100 mmchamber
in a thermostatic (Figure 2).
to maintain a constant temperature. The test
was conducted on a CRT NU-14 device (Figure 3). The experimental tests on the dynamic modulus
|E*| used six frequency values, i.e., 0.1 Hz, 0.5 Hz, 1 Hz, 5 Hz, 10 Hz, and 25 Hz and four temperature
values, i.e., 10 ◦ C, 25 ◦ C, 45 ◦ C, 60 ◦ C.
Appl. Sci.
Appl.2020, 10, 5242
Sci. 2020, 10, x 6 of 246 of 22

(a)

(b)

Appl. Sci. Figure

2020,
Figure 2.10,
Thex2. SMA
The SMA samples
samples preparation
preparation and and testing:
testing: (a) Asphalt
(a) Asphalt mixer,
mixer, (b) The
(b) The SMASMA and HMA
and HMA samples.7 of 24
samples.

All samples were placed in a thermostatic chamber to maintain a constant temperature. The test
was conducted on a CRT NU-14 device (Figure 3). The experimental tests on the dynamic modulus
|E*| used six frequency values, i.e., 0.1 Hz, 0.5 Hz, 1 Hz, 5 Hz, 10 Hz, and 25 Hz and four temperature
values, i.e., 10 °C, 25 °C, 45 °C, 60 °C.

(a) (b)

Figure 3. The
TheSMA
SMAsamples preparation
samples and
preparation testing:
and (a) Gyratory
testing: Compactor
(a) Gyratory machine,
Compactor (b) CRT
machine, NU-
(b) CRT
14 machine.
NU-14 machine.

3.3. Instrumentation
The samples were mixed by an asphalt mixer with 30-L capacity manufactured by Daiwakenko
(Tokyo–Japan). The samples were compacted by Gyratory Compactor 4140 manufactured by Troxler
(TROXLER, Durham, NC, USA). All samples were placed in a thermostatic chamber to maintain a
constant testing temperature. The test was conducted on a CRT NU-14 device (Cooper, London, UK).
Appl. Sci. 2020, 10, 5242 7 of 22

3.3. Instrumentation
The samples were mixed by an asphalt mixer with 30-L capacity manufactured by Daiwakenko
(Tokyo–Japan). The samples were compacted by Gyratory Compactor 4140 manufactured by Troxler
(TROXLER, Durham, NC, USA). All samples were placed in a thermostatic chamber to maintain a
constant testing temperature. The test was conducted on a CRT NU-14 device (Cooper, London, UK).

4. Methods Used

4.1. Artificial Neural Network

One of the most common machine learning algorithms is Artificial Neural Network (ANN),
which is based on the behavior of the biological neural networks’ behavior of the human brain to
analyze and mine the data for discovering the knowledge for solving the real-world problems [53,54].
Three layers, namely input, hidden, and output, are connected by neurons, representing the main
components of the ANN structure and network [55]. Out of these layers, output layers represent
the dependent variables, known as the target variables of the problem. Input layers represent the
independent variables, known as the input variables of the problem. Hidden layers used computational
algorithms, called activation functions, to analyze the relationships between input and output layers.
The ANN is known as the black box model with the advantage of extracting the exact pattern between
the input and output variables and it does not require additional explanation and assumptions.
This model has been applied widely to solve different civil engineering problems and fields, such as
geotechnical engineering [56] and material engineering [57,58]. In this study, ANN was used in the
hybrid framework and model for the prediction of dynamic modulus |E*| of SMA mixtures.

4.2. Teaching Learning Based Optimization

Teaching Learning Based Optimization (TLBO), one of the population-based evolutionary
optimization algorithms, is based on the influence of a teacher on the learners in a given class [59].
The advantage of using TLBO is that this algorithm requires no specific parameters except the common
control ones, such as the number of generations and population size. In TLBO, the “Teacher” and
“Learner” are two critical phases [60]. Particularly, in the Teacher Phase, the teacher of the class is
defined as the best solution in the whole population. The teacher teaches the learners by sharing
knowledge to improve the learners’ performance, such as marks or grades. The quality of the teacher
influences the performance of the learners. Besides, in the Learner Phase, the learners learn the
knowledge from other learners to improve their performance. In general, the TLBO is an effective
optimization algorithm. It has been widely applied in solving different real world problems [61,62].
In the present study, TLBO was used to optimize the ANN performance to predict the values |E*| of
SMA mixtures, especially in the selection of the appropriate values of the associated weights and biases.

4.3. Dataset Preparation and Statistical Analysis

As mentioned in the experimental section, the dataset used for the development of ANN-TLBO
contained 96 instances (Appendix A), in which each result was the average of 6 similar samples.
Overall, 576 samples were fabricated and tested in this work. The statistical analysis of the dataset
is presented in Table 4, including the min, max, median, average, and standard deviation values of
the utilized input and output variables. Table A1 (Appendix A) presents the database used in this
study. The dataset was divided into two main parts, namely the training and testing part. Precisely,
the training dataset contained 70% of the data and was used for the development of the ML model.
On the other hand, the testing dataset contained the remaining 30% samples and was used for the
validation of the previously constructed ML model. The chosen 70/30 ratio for the training and testing
datasets in this study was selected, as suggested in the works of Khorsheed and Mohammad [63] and
Leema et al. [64].
Appl. Sci. 2020, 10, 5242 8 of 22

Table 4. Statistical analysis and summary of the input and output variables used in this study.

Values Mixture Technology Frequency Temperature |E*|

Unit - - Hz ◦C MPa
Role Input Input Input Input Output
Min SMA Warm 0.1 10 277.440
Median - - 3 35 1438.637
Average - - 6.933 35 1709.439
Max HMA Hot 25 60 4762.255
St.D. - - 8.829 19.139 1234.724
St.D. = Standard Deviation; |E*| = Dynamic Modulus

4.4. Quality Assessment Criteria

In this study, three common quantitative indicators, namely RMSE, MAE, and R2 were employed
to validate the performance of the model. R indicates the correlation between two values (predicted and
actual) from the predictive model and experiment. RMSE and MAE measure and evaluate the error of
the models [65–69]. In general, higher values of R2 show higher performance of the model, while lower
values of MAE and RMSE show the higher performance of the model [70–73]. Mathematically,
three indicators (RMSE, MAE, and R2 ) can be expressed as the following equations [74–79]:
Pk
i=1 (xcai − xca )(xmei − xme )
R2 = q (1)
Pk 2 2
i=1 (xcai − xca ) (xmei − xme )
v
u
k
t
1X
RMSE = (xcai − xmei )2 (2)
k
i=1

k
1X
MAE = |xcai − xmei | (3)
k
i=1

where, xmei and xme indicate the measured value of the specimen ith and the measured mean value,
respectively; xcai and xca indicate the output value of the specimen ith and the average value of output
predicted from the modeling, respectively; k means the sum of samples.

5. Results and Discussion

5.1. Experimental Results

Figure 4 shows the experimental results on the dynamic modulus |E*| in highlighting the influence
of the testing frequency, whereas Figure 5 shows similar results in highlighting the influence of the
testing temperature. Considering a similar testing frequency, an increase of the testing temperature
reduced the value of the dynamic modulus |E*|. Besides, at similar testing temperature, an increase
of the testing frequency increased the value of the dynamic modulus |E*|. Specifically, the effects of
the testing frequency and temperature on the experimental values |E*| are clearly shown in Figures 4
and 5. The highest value of the dynamic modulus |E*| for four types of mixtures was obtained with a
temperature of 10 ◦ C and a frequency of 25 Hz. The smallest value of the dynamic modulus |E*| was
obtained in the case of 60 ◦ C and 0.1 Hz. At a testing temperature of 10 ◦ C, the value of |E*| of SMA-H
was 1.22–1.33 times higher than HMA-H, whereas it was 1.01–1.42 times at 25 ◦ C, 1.45–1.7 times at 45 ◦ C
and 1.01–1.08 times at 60 ◦ C. For asphalt mixtures made by hot technology at a similar temperature,
the difference was more pronounced with the higher frequency. The difference could be neglected at a
testing temperature of 60 ◦ C. At a testing temperature of 10 ◦ C, the value of the dynamic modulus |E*|
of SMA-W was 1.11–1.22 times higher than HMA-W, whereas it was 1.01–1.15 times at a temperature
of 25 ◦ C, 1.09–1.22 times at a temperature of 45 ◦ C, and 1.08–1.26 times at a temperature of 60 ◦ C.
 technology at a similar temperature, the difference was more pronounced with the higher frequency.
The difference could be neglected at a testing temperature of 60 °C. At a testing temperature of 10 °C,
the value of the dynamic modulus |E*| of SMA-W was 1.11–1.22 times higher than HMA-W, whereas
it was 1.01–1.15 times at a temperature of 25 °C, 1.09–1.22 times at a temperature of 45 °C, and 1.08–
Appl.1.26
Sci. times at 5242
2020, 10, a temperature of 60 °C. 9 of 22

(a) SMA - W
7000
T=10°C T=25°C

Dynamic Modulus |E*|

6000

5000
T=45°C T=60°C

4000

3000

2000

1000

Appl. Sci. 2020, 10, x 0 10 of 24

0 2 4 6 8 10 12 14 16 18 20 22 24 26
Frequency (Hz)
(b) SMA - H
7000
T=10°C T=25°C
Dynamic Modulus |E*|

6000

5000
T=45°C T=60°C

4000

3000

2000

1000

0
0 2 4 6 8 10 12 14 16 18 20 22 24 26
Frequency (Hz)

(c) HMA - W
7000
T=10°C T=25°C
Dynamic Modulus |E*|

6000

5000
T=45°C T=60°C

4000

3000

2000

1000

0
0 2 4 6 8 10 12 14 16 18 20 22 24 26
Frequency (Hz)

(d) HMA - H
7000
T=10°C T=25°C
Dynamic Modulus |E*|

6000

5000
T=45°C T=60°C

4000

3000

2000

1000

0
0 2 4 6 8 10 12 14 16 18 20 22 24 26
Frequency (Hz)

Figure 4. Experimental
Figure 4. Experimentalresults
resultsof
of dynamic
dynamic modulus |E*| in
modulus|E*| functionofofthe
in function thefrequency,
frequency,
inin
thethe case
case of of
(a) SMA-W; (b) SMA-H; (c) HMA-W; and (d) HMA-H.
(a) SMA-W; (b) SMA-H; (c) HMA-W; and (d) HMA-H.
Appl. Sci. 2020, 10, x 11 of 24
Appl. Sci. 2020, 10, 5242 10 of 22

Figure 5. Cont.
Appl. Sci. 2020, 10, x 12 of 24
Appl. Sci. 2020, 10, 5242 11 of 22

Figure 5. Experimental results of dynamic modulus |E*| in function of the test temperature for different
Figure 5. Experimental results of dynamic modulus |E*| in function of the test temperature for
frequencies: (a) 0.1 Hz; (b) 0.5 Hz; (c) 1 Hz; (d) 5 Hz; (e) 10 Hz; (f) 25 Hz.
different frequencies: (a) 0.1 Hz; (b) 0.5 Hz; (c) 1 Hz; (d) 5 Hz; (e) 10 Hz; (f) 25 Hz.

It could be concluded that, compared to the HMA, the SMA showed superior performance in
terms of the dynamic modulus |E*|. Besides, the warm technology exhibited higher dynamic
modulus |E*| than using the hot technology. Considering SMA and the mixtures using the warm
technique, similar observations were also reported in the literature [12]. Indeed, Al-Qadi et al.
Appl. Sci. 2020, 10, 5242 12 of 22

It could be concluded that, compared to the HMA, the SMA showed superior performance in
terms of the dynamic modulus |E*|. Besides, the warm technology exhibited higher dynamic modulus
|E*| than using the hot technology. Considering SMA and the mixtures using the warm technique,
similar observations were also reported in the literature [12]. Indeed, Al-Qadi et al. showed that the
SMA-W exhibited significant improvement compared with SMA-H. Moreover, the authors showed
that, in terms of additives, Sasobit disclosed the highest performance compared with the control mix,
Evotherm, and foamed asphalt. Besides, the curing time was proved to be another critical factor
affecting the dynamic modulus. Several curing times using Sasobit were tested in the work, and the
results showed that 1-day curing time was optimal. In this study, taking advantage of such a result,
the curing time was directly chosen as one day. The analysis of the effect of curing time might be
the objective of further research, as different natures of aggregates, filler, or bitumen might have a
certain influence on the dynamic modulus. Besides, another study confirmed the addition of additives
enhanced the dynamic modulus compared with the control asphalt mixtures, for instance, in the
work of Goh and You [80]. Last but not least, the success in decreasing the mixing and compacting
temperatures was proven in the literature but only for recycled aggregates [12,48]; this study showed a
similarly successful result of the dynamic modulus of asphalt mixture in using conventional aggregates.

5.2. Optimization of the ANN-TLBO Model

Regarding the development of ANN-TLBO algorithms, the determination of the parameters of
such a model is a crucial step. Indeed, the prediction capability is directly dependent on the choice
of the appropriate values of parameters. They could be the activation function of the hidden layer,
cost function, the training algorithm of the ANN model, or the population size, the stopping criterion
of the optimization algorithm. After trial-and-error tests, the parameters of the proposed ANN-TLBO
model were chosen and indicated in Table 5. The final structure of ANN-TLBO was 4-5-1 and denoted
as ANN-TLBO [4-5-1]. Three statistical measurements (i.e., R2 , RMSE, and MAE) were applied for
ANN-TLBO to find the best values of the weights and biases associated with the neurons. This means
that all the results presented herein were the best performance of the proposed ANN-TLBO model,
with the highest value of R2 and the lowest values of MAE, RMSE concerning one selected dataset.
The evaluations of cost functions with respect to R2 , RMSE, and MAE for predicting the dynamic
modulus |E*| are presented in Figure 6. This study focused only on the selection of an appropriate choice
of the stopping criterion. Furthermore, the accuracy of the ML algorithm could not be guaranteed
by the higher number of iteration, for instance in [81], where the best model was found at 20 over
100 performed iterations. As a result, the convergence of the proposed ANN-TLBO in this study was
reached after about 100 iterations, and 200 iterations were sufficient to reach the state of convergence
of all the cost functions.

Table 5. ANN and TLBO parameters.

Parameter Value and Description

Number of neurons in output layer 1
Number of weight parameters 31
Number of hidden layers 1
Number of neurons in the input layer 4
Number of neurons in hidden layer 5
Hidden layer activation function Sigmoid
Output layer activation function Linear
Cost function MSE-Mean square error
Training algorithm TLBO
TLBO population size 30
Stopping iteration 200
Appl. Sci.
Appl.2020, 10, 5242
Sci. 2020, 10, x 13 of 22
14 of 24

Figure 6. Optimization
Figure 6. Optimizationofofweight
weight parameters
parameters ofofANN
ANN models
models using
using the TLBO
the TLBO algorithm:
algorithm: (a) R2 ,
(a) R2, (b)
(b) RMSE,
RMSE,and
and(c)
(c) MAE.
MAE.

5.3. Validation and and

5.3. Validation Comparison of of
Comparison ANN-TLBO
ANN-TLBOwith
with Single ANN
Single ANN
The performance
The performance of the
ofANN model,
the ANN in comparison
model, with the
in comparison withANN-TLBO
the ANN-TLBO algorithm, is presented
algorithm, is
underpresented
regression plots
under (Figureplots
regression 7), showing
(Figure 7),ashowing
comparison between
a comparison the predicted
between andand
the predicted actual values
actual
of thevalues
dynamic
of themodulus |E*|. The|E*|.
dynamic modulus idealThe
regression lines are
ideal regression in are
lines discontinuous style,
in discontinuous whereas
style, whereas the R2
the R
between and actual dynamic modulus |E*| are given (Table 6). The correlation results analysis
2 between predicted and actual dynamic modulus |E*| are given (Table 6). The correlation
predicted
showed thatanalysis
results showedwere
the R2 values that the R2 values
0.907, were
0.948 for the0.907, 0.948and
training for testing
the training and testing
datasets, datasets,
respectively, for the
respectively, for the ANN model. Concerning the ANN-TLBO model, these
ANN model. Concerning the ANN-TLBO model, these values were 0.975, 0.981 for the training values were 0.975, 0.981 and
testing datasets, respectively. These results showed a very good prediction performance of the two
proposed models. However, using an optimization, the ANN-TLBO was found to be the superior
predictor compared with the single ANN.
 Appl. Sci. 2020, 10, x 15 of 24

for the training and testing datasets, respectively. These results showed a very good prediction
performance of the two proposed models. However, using an optimization, the ANN-TLBO was
Appl. Sci. 2020, 10, 5242 14 of 22
found to be the superior predictor compared with the single ANN.

Figure 7. Regression graphs using individual ANN model: (a) training and (b) testing parts; ANN-TLBO
Figure 7. Regression graphs using individual ANN model: (a) training and (b) testing parts; ANN-
model: (c) training and (d) testing parts.
TLBO model: (c) training and (d) testing parts.

Table 6. Summary of prediction capability of the ANN-TLBO model.

Table 6. Summary of prediction capability of the ANN-TLBO model.
Model Data
Model RMSE
Data RMSE MAE ErrorMeanErrorStD
MAE ErrorMean ErrorStDR2 R2
Slope Slope
Unit Unit MPa MPa MPa MPa MPa
MPa MPaMPa - - - -
ANN ANN
TrainingTraining 379.035291.815
379.035 291.815 −126.527
−126.527 360.414 0.907
360.414 0.914 0.914
0.907
Testing Testing 292.828236.917
292.828 236.917 −31.099
−31.099 295.080 0.948
295.080 0.932 0.932
0.948
ANN-TLBOANN-TLBO
TrainingTraining 189.666153.851
189.666 153.851 18.639
18.639 190.396 0.975
190.396 0.958 0.958
0.975
Testing Testing 183.308141.540
183.308 141.540 21.294
21.294 184.511 0.981
184.511 0.936 0.936
0.981
% Gain % Gain
Training +50.0
Training +50.0 +47.3
+47.3 +114.7
+114.7 +47.2+7.5
+47.2 +7.5
+4.8 +4.8
+37.4+37.4 +40.3
Testing Testing +40.3 +168.5
+168.5 +37.5+3.5
+37.5 +3.5
+0.4 +0.4

The summary of the prediction performance of ANN and ANN-TLBO is presented in Table 6.
TheThe
summary
values of of
R2,the prediction
RMSE, and MAEperformance
were calculatedofbased
ANN on and ANN-TLBO
the formulations is presented
given in Table 6.
in the previous
2
The values of R , RMSE, and MAE were calculated based on the formulations given in the previous
section, whereas ErrorMean was the mean values of errors and ErrorStD was the standard deviation of
errors. The “Slope” represented the slope between the ideal regression line (discontinuous lines in
Figure 7) and the linear fit, given by the models (continuous lines in Figure 7). The two additional
error criteria also confirmed that ANN-TLBO is superior to ANN in predicting the dynamic modulus
|E*|. For illustration purposes, the values of the dynamic modulus |E*| in function of sample index
using individual ANN and ANN-TLBO models are plotted in Figure 8 for the training and testing
datasets. It is clearly seen that the predicted values were in excellent agreement with the experimental
dynamic modulus |E*| values.
 Figure 7) and the linear fit, given by the models (continuous lines in Figure 7). The two additional
error criteria also confirmed that ANN-TLBO is superior to ANN in predicting the dynamic modulus
|E*|. For illustration purposes, the values of the dynamic modulus |E*| in function of sample index
using individual ANN and ANN-TLBO models are plotted in Figure 8 for the training and testing
datasets. It is clearly seen that the predicted values were in excellent agreement with the experimental
Appl. Sci. 2020, 10, 5242
dynamic modulus |E*| values. 15 of 22

Appl. Sci. 2020, 10, x 17 of 24

Dynamic
Figure 8.Figure modulus
8. Dynamic in function
modulus ofofsample
in function index,using
sample index, using individual
individual ANNANNmodelmodel for (a) training
for (a) training
part and part
(b) testing part, using
and (b) testing ANN-TLBO
part, using ANN-TLBOmodelmodel for (c)training
for (c) training part
part andand (d) testing
(d) testing part. part.

Overall, the prediction capability of ANN-TLBO was quantified based on various performance
indicators. The proposed hybrid model showed high prediction capability and outperformed
individual ANN, clearly demonstrating the efficiency of using TLBO as an optimization tool.

5.4. Sensitivity Analysis of the Prediction Variables

The sensitivity analysis of the input variables used in the prediction process is presented in this
Appl. Sci. 2020, 10, 5242 16 of 22

Overall, the prediction capability of ANN-TLBO was quantified based on various performance
indicators. The proposed hybrid model showed high prediction capability and outperformed individual
ANN, clearly demonstrating the efficiency of using TLBO as an optimization tool.

5.4. Sensitivity Analysis of the Prediction Variables

The sensitivity analysis of the input variables used in the prediction process is presented in this
section. The temperature and frequency were successively varied at their range of value, whereas
other inputs were kept constant. Precisely, using the ANN-TLBO model developed previously, a new
two-dimensional input space was constructed using the value of each input, recorded at ten different
quantile levels: 0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, and 1.0. The temperature and the frequency
were them successively selected, and the model was run eleven times, once for each percentile value.
Principally, the method provides quantitative disclosures on the change of output when the selected
input changes.
It can be seen that the temperature was the most significant factor influencing the dynamic
modulus |E*|, followed by the frequency (Figure 9). While varying two input variables, the sensitivity
index varied from [200–300] to [−100] for the temperature, whereas it varied from [0] to [100] for
the frequency. Moreover, the nonlinear negative effect was observed for the temperature, whereas a
Appl. Sci. 2020, 10, x 18 of 24
positive linear effect was found for the frequency. These observations were confirmed for all mixtures.

Figure 9. Sensitivity index of frequency and temperature for four combinations of SMA, HMA, H,
Figure 9.
and W.
and W.

As
As indicated
indicatedininmany
many studies
studies[82–85], exploring
[82–85], exploringthe the
relative importance
relative of inputs
importance mightmight
of inputs offer better
offer
in-depth knowledge
better in-depth of the output,
knowledge which which
of the output, could directly assist engineers
could directly duringduring
assist engineers the preparation phase.
the preparation
Considering the testing
phase. Considering thetemperature and frequency,
testing temperature experimental
and frequency, investigations
experimental have been conducted
investigations have been
in several works [12,80]. However, a direct linear interpolation of the as-obtained
conducted in several works [12,80]. However, a direct linear interpolation of the as-obtained results or missing
results
information on the rangeonofthe
or missing information input
rangevalues could
of input lead to
values inexact
could leadobservations. In this work,
to inexact observations. Inan attempt
this work,
was made from an experimental point of view, to cover a broad range
an attempt was made from an experimental point of view, to cover a broad range of testing of testing temperature and
frequency
temperature withandsufficiently
frequencygrid withpoints. The dependency
sufficiently grid points.ofThethe dependency
dynamic modulus of theon inputs was
dynamic then
modulus
analyzed
on inputswith
was the developed
then analyzedML withalgorithm. For each
the developed MLmixture,
algorithm. a fitFor
equation was proposed
each mixture, to highlight
a fit equation was
the dependency of the selected variable to dynamic modulus |E*|. With
proposed to highlight the dependency of the selected variable to dynamic modulus |E*|. Withreasonable accuracy, a linear
equation
reasonable was finally adopted
accuracy, a lineartoequation
fit the frequency versus
was finally the dynamic
adopted to fit themodulus.
frequencyOn versus
the contrary, a cubic
the dynamic
equation was chosen to relate the temperature with the dynamic modulus. Summarized
modulus. On the contrary, a cubic equation was chosen to relate the temperature with the dynamic information on
the sensitivity analysis of the effect of temperature and frequency is presented
modulus. Summarized information on the sensitivity analysis of the effect of temperature and in Table 7, including the
appropriate
frequency isfit, equationinform,
presented Tableand correlationthe
7, including effect. The proposed
appropriate equations
fit, equation could
form, andfacilitate
correlationthe effect.
usage
of asphalt mixtures in selecting the desired dynamic modulus in function of
The proposed equations could facilitate the usage of asphalt mixtures in selecting the desired the testing temperature
and frequency.
dynamic modulus in function of the testing temperature and frequency.

Table 7. Summary of the sensitivity analysis using the ANN-TLBO algorithm.

Appropriate Correlation
Mixture Technology Variable Equation Form
Fit Effect
HMA Hot Frequency Linear y = 134.2x − 15 Positive
Appl. Sci. 2020, 10, 5242 17 of 22

Table 7. Summary of the sensitivity analysis using the ANN-TLBO algorithm.

Mixture Technology Variable Appropriate Fit Equation Form Correlation Effect

HMA Hot Frequency Linear y = 134.2x − 15 Positive
y= +
−57.09x3 428.16x2
Temperature Cubic Negative
− 776.28x + 292.01
HMA Warm Frequency Linear y = 94.74x − 11.21 Positive
y= 44.97x3 + 158.28x2 −
Temperature Cubic Negative
530.81x + 224.69
SMA Hot Frequency Linear y = 96.91x − 11.24 Positive
y= 71.46x3 + 135.6x2
−
Temperature Cubic Negative
569.75x + 254.18
SMA Warm Frequency Linear y = 112.69x − 17.74 Positive
y= 65.66x3 + 102.69x2 −
Temperature Cubic Negative
489.04x + 222.45

6. Conclusions and Outlook

In this study, a novel machine learning algorithm, namely ANN-TLBO, was used to predict
the dynamic modulus |E*| of SMA, one of the most critical mechanical properties of the asphalt
concrete. The proposed model consisted of one well-known machine learning algorithm (ANN) and
an effective optimization algorithm (TLBO). The dataset resulting from experiments consisting of
96 entries (average values per 6 of 576 experimental results) was used for the development of the
algorithm. The performance of the proposed model was assessed by various common statistical
measurements, such as RMSE, MAE, and R.
The validation results showed that the performance of ANN-TLBO was remarkable with ideal
values of R2 (0.975 for the training part and 0.981 for the testing dataset). Such results were superior to
those obtained by a single ANN model (0.907 for the training phase and 0.948 for the testing dataset).
In addition, a sensitivity analysis was performed, and the results showed that the testing temperature
was the most influential factor in the prediction of the dynamic modulus |E*|. These results indicated
that ANN-TLBO could be a promising predictor of the dynamic modulus |E*| of SMA mixtures. It could
thus be used in the designing phase of SMA mixtures, aiming at a more effective and efficient process.
Extending the existing database could be a short-term perspective of the present study. This could
improve the quality of the dataset and expand the ranges of input variables used in the prediction
process. Besides, despite an astonishing performance of ANN-TLBO, the use of alternative machine
learning algorithms or optimization techniques should be examined to improve the effectiveness of the
prediction algorithm.

Author Contributions: Conceptualization, T.-H.L., H.-L.N., H.-B.L., and C. -T.P.; data curation, T.-H.L., M.H.N.,
and N.-L.N.; formal analysis, T.-H.L., H.-L.N., and C.-T.P.; methodology, H.-L.N., H.-B.L., B.T.P. and T.-T.L.; project
administration, H.-L.N. and H.-B.L.; supervision, H.-L.N., H.-B.L., B.T.P., and T.-T.L.; validation, H.-L.N., C.-T.P.,
and H.-B.L.; visualization, T.-H.L., H.-B.L. and T.-T.L.; writing—original draft, all authors.; writing—review &
editing, H.-L.N., H.-B.L., and B.T.P. All authors have read and agreed to the published version of the manuscript.
Funding: This research received no external funding
Conflicts of Interest: The authors declare no conflict of interest

Appendix A

Table A1. The instances used in this study.

ID Mix Tech. Fr. (Hz) T◦ (◦ C) E* (MPa) ID Mix Tech. Fr. (Hz) T◦ (◦ C) E* (MPa)
1 SMA Warm 0.1 10 3221.06 49 HMA Warm 0.1 10 2822.85
2 SMA Warm 0.1 25 1479.78 50 HMA Warm 0.1 25 1470.61
Appl. Sci. 2020, 10, 5242 18 of 22

Table A1. Cont.

ID Mix Tech. Fr. (Hz) T◦ (◦ C) E* (MPa) ID Mix Tech. Fr. (Hz) T◦ (◦ C) E* (MPa)
3 SMA Warm 0.1 45 655.06 51 HMA Warm 0.1 45 581.08
4 SMA Warm 0.1 60 340.66 52 HMA Warm 0.1 60 316.70
5 SMA Warm 0.5 10 3702.71 53 HMA Warm 0.5 10 3340.80
6 SMA Warm 0.5 25 1825.52 54 HMA Warm 0.5 25 1766.28
7 SMA Warm 0.5 45 818.73 55 HMA Warm 0.5 45 748.68
8 SMA Warm 0.5 60 426.55 56 HMA Warm 0.5 60 375.46
9 SMA Warm 1 10 3945.63 57 HMA Warm 1 10 3434.68
10 SMA Warm 1 25 1973.47 58 HMA Warm 1 25 1897.39
11 SMA Warm 1 45 906.37 59 HMA Warm 1 45 829.06
12 SMA Warm 1 60 475.75 60 HMA Warm 1 60 409.06
13 SMA Warm 5 10 4160.71 61 HMA Warm 5 10 3434.08
14 SMA Warm 5 25 2390.24 62 HMA Warm 5 25 2106.09
15 SMA Warm 5 45 1147.24 63 HMA Warm 5 45 994.26
16 SMA Warm 5 60 560.64 64 HMA Warm 5 60 452.40
17 SMA Warm 10 10 4318.67 65 HMA Warm 10 10 3608.55
18 SMA Warm 10 25 2454.36 66 HMA Warm 10 25 2135.47
19 SMA Warm 10 45 1362.23 67 HMA Warm 10 45 1116.60
20 SMA Warm 10 60 598.55 68 HMA Warm 10 60 473.85
21 SMA Warm 25 10 4762.26 69 HMA Warm 25 10 3913.48
22 SMA Warm 25 25 2643.28 70 HMA Warm 25 25 2306.67
23 SMA Warm 25 45 1755.81 71 HMA Warm 25 45 1503.70
24 SMA Warm 25 60 843.93 72 HMA Warm 25 60 690.96
25 SMA Hot 0.1 10 2927.48 73 HMA Hot 0.1 10 2376.47
26 SMA Hot 0.1 25 1205.92 74 HMA Hot 0.1 25 1188.64
27 SMA Hot 0.1 45 661.20 75 HMA Hot 0.1 45 450.33
28 SMA Hot 0.1 60 303.96 76 HMA Hot 0.1 60 277.44
29 SMA Hot 0.5 10 3345.46 77 HMA Hot 0.5 10 2752.67
30 SMA Hot 0.5 25 1572.55 78 HMA Hot 0.5 25 1406.66
31 SMA Hot 0.5 45 815.87 79 HMA Hot 0.5 45 563.33
32 SMA Hot 0.5 60 361.72 80 HMA Hot 0.5 60 335.48
33 SMA Hot 1 10 3560.48 81 HMA Hot 1 10 2723.29
34 SMA Hot 1 25 1750.65 82 HMA Hot 1 25 1516.44
35 SMA Hot 1 45 901.81 83 HMA Hot 1 45 613.94
36 SMA Hot 1 60 395.62 84 HMA Hot 1 60 372.16
37 SMA Hot 5 10 3880.80 85 HMA Hot 5 10 2970.33
38 SMA Hot 5 25 2250.72 86 HMA Hot 5 25 1688.84
39 SMA Hot 5 45 1131.55 87 HMA Hot 5 45 720.14
40 SMA Hot 5 60 426.95 88 HMA Hot 5 60 424.85
41 SMA Hot 10 10 4021.36 89 HMA Hot 10 10 3013.44
42 SMA Hot 10 25 2400.21 90 HMA Hot 10 25 1733.71
43 SMA Hot 10 45 1351.68 91 HMA Hot 10 45 796.31
44 SMA Hot 10 60 448.87 92 HMA Hot 10 60 444.47
45 SMA Hot 25 10 4434.93 93 HMA Hot 25 10 3424.61
46 SMA Hot 25 25 2639.12 94 HMA Hot 25 25 1857.80
47 SMA Hot 25 45 1794.94 95 HMA Hot 25 45 1106.78
48 SMA Hot 25 60 636.84 96 HMA Hot 25 60 629.32

References
1. Shen, D.-H.; Kuo, M.-F.; Du, J.-C. Properties of gap-aggregate gradation asphalt mixture and permanent
deformation. Constr. Build. Mater. 2005, 19, 147–153. [CrossRef]
2. Murali Krishnan, J.; Rajagopal, K.R. Review of the uses and modeling of bitumen from ancient to modern
times. Appl. Mech. Rev. 2003, 56, 149–214. [CrossRef]
3. Capitão, S.D.; Picado-Santos, L.G.; Martinho, F. Pavement engineering materials: Review on the use of
warm-mix asphalt. Constr. Build. Mater. 2012, 36, 1016–1024. [CrossRef]
4. Jamshidi, A.; Hamzah, M.O.; You, Z. Performance of warm mix asphalt containing sasobit® : State-of-the-Art.
Constr. Build. Mater. 2013, 38, 530–553. [CrossRef]
Appl. Sci. 2020, 10, 5242 19 of 22

5. Sangiorgi, C.; Tataranni, P.; Simone, A.; Vignali, V.; Lantieri, C.; Dondi, G. Stone mastic asphalt (SMA)
with crumb rubber according to a new dry-hybrid technology: A laboratory and trial field evaluation.
Constr. Build. Mater. 2018, 182, 200–209. [CrossRef]
6. Wang, H.; Liu, X.; Apostolidis, P.; Scarpas, T. Review of warm mix rubberized asphalt concrete: Towards a
sustainable paving technology. J. Clean. Prod. 2018, 177, 302–314. [CrossRef]
7. Witczak, M.W.; Fonseca, O.A. Revised predictive model for dynamic (complex) modulus of asphalt mixtures.
Transp. Res. Rec. 1996, 1540, 15–23. [CrossRef]
8. Silva, H.M.R.D.; Oliveira, J.; Ferreira, C.I.G.; Pereira, P.A.A. Assessment of the performance of warm mix
asphalts in road pavements. Int. J. Pavement Res. Technol. 2010, 3, 119–127.
9. Sanchez-Alonso, E.; Vega-Zamanillo, A.; Castro-Fresno, D.; DelRio-Prat, M. Evaluation of compactability and
mechanical properties of bituminous mixes with warm additives. Constr. Build. Mater. 2011, 25, 2304–2311.
[CrossRef]
10. Zaumanis, M. Warm Mix Asphalt Investigation. Master’s Thesis, Technical University of Denmark in
cooperation with the Danish Road Institute, Kgs. Lyngby, Denmark, 2010.
11. Peinado, D.; de Vega, M.; García-Hernando, N.; Marugán-Cruz, C. Energy and exergy analysis in an asphalt
plant’s rotary dryer. Appl. Therm. Eng. 2011, 31, 1039–1049. [CrossRef]
12. Al-Qadi, I.L.; Baek, J.; Leng, Z.; Wang, H.; Doyen, M.; Kern, J.; Gillen, S. Short-Term Performance of Modified Stone
Matrix Asphalt (SMA) Produced with Warm Mix Additives; Technical Report; Illinois Center for Transportation:
Rantoul, IL, USA, 2012.
13. Zaumanis, M.; Mallick, R.B.; Frank, R. 100% recycled hot mix asphalt: A review and analysis.
Resour. Conserv. Recycl. 2014, 92, 230–245. [CrossRef]
14. Petersen, J.C. A review of the fundamentals of asphalt oxidation: Chemical, physicochemical,
physical property, and durability relationships. Transp. Res. Circ. 2009. [CrossRef]
15. Baghaee Moghaddam, T.; Baaj, H. The use of rejuvenating agents in production of recycled hot mix asphalt:
A systematic review. Constr. Build. Mater. 2016, 114, 805–816. [CrossRef]
16. D’Angelo, J.; Cowsert, J.; Newcomb, D.D. Warm-Mix Asphalt: European Practice; No. FHWA-PL-08-007;
United States, Federal Highway Administration, Office of International Programs: Washington, DC,
USA, 2008.
17. Rubio, M.C.; Martínez, G.; Baena, L.; Moreno, F. Warm mix asphalt: An overview. J. Clean. Prod. 2012,
24, 76–84. [CrossRef]
18. Prowell, B.D.; Hurley, G.C.; Crews, E. Field performance of warm-mix asphalt at national center for asphalt
technology test track. Transp. Res. Rec. 2007, 1998, 96–102. [CrossRef]
19. Graham, C.H.; Brian, D.P. Evaluation of Aspha-Min®Zeolite for Use in Warm Mix Asphalt; NCAT Report 05-04;
Auburn University: Auburn, AL, USA, 2005.
20. Olard, F.; Noanc, L.E. Low energy asphalts. In Proceedings of the 23rd Piarc World Road Congress, Paris,
France, 17–21 September 2007.
21. Jullien, A.; Baudru, Y.; Tamagny, P.; Olard, F.; Zavan, D. A Comparison of Environmental Impacts of Hot and
Warm Mix Asphalt; World Road Association—PIARC: Paris, France, 2011.
22. Bari, J. Development of a New Revised Version of the Witczak E* Predictive Models for Hot Mix Asphalt Mixtures;
Arizona State University: Tempe, AZ, USA, 2005.
23. Flintsch, G.W.; Loulizi, A.; Diefenderfer, S.D.; Diefenderfer, B.K.; Galal, K.A. Asphalt material characterization
in support of mechanistic–empirical pavement design guide implementation in virginia. Transp. Res. Rec.
2008, 2057, 114–125. [CrossRef]
24. Birgisson, B.; Sholar, G.; Roque, R. Evaluation of a predicted dynamic modulus for florida mixtures.
Transp. Res. Rec. 2005, 1929, 200–207. [CrossRef]
25. Sakhaeifar, M.S.; Richard Kim, Y.; Kabir, P. New predictive models for the dynamic modulus of hot mix
asphalt. Constr. Build. Mater. 2015, 76, 221–231. [CrossRef]
26. Shu, X.; Huang, B. Micromechanics-Based dynamic modulus prediction of polymeric asphalt concrete
mixtures. Compos. Part B Eng. 2008, 39, 704–713. [CrossRef]
27. Shu, X.; Huang, B. Predicting dynamic modulus of asphalt mixtures with differential method. Road Mater.
Pavement Des. 2009, 10, 337–359. [CrossRef]
28. Cho, Y.-H.; Park, D.-W.; Hwang, S.-D. A predictive equation for dynamic modulus of asphalt mixtures used
in Korea. Constr. Build. Mater. 2010, 24, 513–519. [CrossRef]
Appl. Sci. 2020, 10, 5242 20 of 22

29. Rahman, A.A.; Islam, M.R.; Tarefder, R.A. Dynamic modulus and phase angle models for New Mexico’s
superpave mixtures. Road Mater. Pavement Des. 2019, 20, 740–753. [CrossRef]
30. Ceylan, H.; Gopalakrishnan, K.; Kim, S. Looking to the future: The next-generation hot mix asphalt dynamic
modulus prediction models. Int. J. Pavement Eng. 2009, 10, 341–352. [CrossRef]
31. Far, M.S.S.; Underwood, B.S.; Ranjithan, S.R.; Kim, Y.R.; Jackson, N. Application of Artificial neural networks
for estimating dynamic modulus of asphalt concrete. Transp. Res. Rec. 2009, 2127, 173–186. [CrossRef]
32. Sakhaeifar, M.S.; Underwood, B.S.; Kim, Y.R.; Puccinelli, J.; Jackson, N. Development of artificial neural
network predictive models for populating dynamic moduli of long-term pavement performance sections.
Transp. Res. Rec. 2010, 2181, 88–97. [CrossRef]
33. Dharamveer, S.; Musharraf, Z. Commuri sesh artificial neural network modeling for dynamic modulus of
hot mix asphalt using aggregate shape properties. J. Mater. Civ. Eng. 2013, 25, 54–62. [CrossRef]
34. Olidis, C.; Hein, D. Guide for the mechanistic-empirical design of new and rehabilitated pavement structures
materials characterization: Is your agency ready. In Proceedings of the 2004 Annual Conference of the
Transportation Association of Canada, Quebec City, QC, Canada, 19–22 September 2004.
35. Andrei, D.; Witczak, M.W.; Mirza, M.W. Development of a revised predictive model for the dynamic
(complex) modulus of asphalt mixtures. In Development of the 2002 Guide for the Design of New and Rehabilitated
Pavement Structures; NCHRP: Washington, DC, USA, 1999.
36. Christensen, D.W., Jr.; Pellinen, T.; Bonaquist, R.F. Hirsch model for estimating the modulus of asphalt
concrete. J. Assoc. Asph. Paving Technol. 2003, 72, 97–121.
37. Al-Khateeb, G.; Shenoy, A.; Gibson, N.; Harman, T. A new simplistic model for dynamic modulus predictions
of asphalt paving mixtures. J. Assoc. Asph. Paving Technol. 2006, 75, 1–40.
38. Obulareddy, S. Fundamental characterization of Louisiana HMA mixtures for the 2002 mechanistic-empirical
design guide. LSU Master’s Theses, Andhra University, Visakhapatnam, India, 2006.
39. Dongre, R.; Myers, L.; D’Angelo, J.; Paugh, C.; Gudimettla, J. Field evaluation of Witczak and Hirsch models
for predicting dynamic modulus of hot-mix asphalt (with discussion). J. Assoc. Asph. Paving Technol. 2005,
74, 381–442.
40. Tran, N.; Hall, K. Evaluating the predictive equation in determining dynamic moduli of typical asphalt
mixtures used in Arkansas. Natl. Acad. Sci. Eng. Med. 2005, 74E, 1–17.
41. Azari, H.; Al-Khateeb, G.; Shenoy, A.; Gibson, N. Comparison of simple performance test |E*| of
accelerated loading facility mixtures and prediction |E*| use of NCHRP 1-37A and witczak’s new equations.
Transp. Res. Rec. 2007, 1998, 1–9. [CrossRef]
42. Kim, Y.R.; King, M.; Momen, M. Typical dynamic moduli values of hot mix asphalt in North Carolina and
their prediction. In Proceedings of the Transportation Research Board 84th Annual Meeting compendium of
papers CD-ROM, Washington, DC, USA, 9–13 January 2005; pp. 5–2568.
43. Schwartz, C.W. Evaluation of the Witczak dynamic modulus prediction model. In Proceedings of the 84th
Annual Meeting of the Transportation Research Board, Washington, DC, USA, 9–13 January 2005.
44. Pellinen, T.K.; Witczak, M.W. Use of stiffness of hot-mix asphalt as a simple performance test. Transp. Res. Rec.
2002, 1789, 80–90. [CrossRef]
45. ARA, I. Guide for Mechanistic–Empirical Design of New and Rehabilitated Pavement Structures; Final Report,
NCHRP Project 1-37A; ERES Division 505 West University Avenue Champaign: Champaign, IL, USA, 2004.
46. Abdo, A.A.; Bayomy, F.; Nielsen, R.; Weaver, T.; Jung, S.J.; Santi, M.J. Prediction of the dynamic modulus of
Superpave mixes. In Proceedings of the 8th International Conference on the Bearing Capacity of Roads,
Railways and Airfields (BCR2A’09), Champaign, IL, USA, 29 June–2 July 2009; pp. 305–314.
47. Ceylan, H.; Gopalakrishnan, K.; Kim, S. Advanced approaches to hot-mix asphalt dynamic modulus
prediction. Can. J. Civ. Eng. 2008, 35, 699–707. [CrossRef]
48. Al-Qadi, I.L.; Leng, Z.; Baek, J.; Wang, H.; Doyen, M.; Gillen, S.L. Short-Term performance of plant-mixed
warm stone mastic asphalt: Laboratory testing and field evaluation. Transp. Res. Rec. 2012, 2306, 86–94.
[CrossRef]
49. Leng, Z.; Gamez, A.; Al-Qadi, I.L. Mechanical property characterization of warm-mix asphalt prepared with
chemical additives. J. Mater. Civ. Eng. 2014, 26, 304–311. [CrossRef]
50. AASHTO M 325-08. Available online: https://www.techstreet.com/standards/aashto-m-325-08-2017?product_
id=1583186 (accessed on 18 March 2020).
Appl. Sci. 2020, 10, 5242 21 of 22

51. Vietnam Standard, M. of T. of V. Vietnam Standard—Guiding the Application of the Current System of Technical
Standards to Enhance the Quality Management of the Design and Construction of Hot Mix Asphalt for Large-Scale
Roads, Issued; Tổng cục Tiêu chuẩn Ðo lường Chất lượng: Hanoi, Vietnam, 2014.
52. AASHTO TP 62—Standard Method of Test for Determining Dynamic Modulus of Hot Mix Asphalt (HMA)
| Engineering360. Available online: https://standards.globalspec.com/std/1283471/AASHTO%20TP%2062
(accessed on 27 December 2019).
53. Pham, B.T.; Nguyen, M.D.; Bui, K.-T.T.; Prakash, I.; Chapi, K.; Bui, D.T. A novel artificial intelligence approach
based on multi-layer perceptron neural network and biogeography-based optimization for predicting
coefficient of consolidation of soil. Catena 2019, 173, 302–311. [CrossRef]
54. Dao, D.V.; Ly, H.-B.; Trinh, S.H.; Le, T.-T.; Pham, B.T. Artificial intelligence approaches for prediction of
compressive strength of geopolymer concrete. Materials 2019, 12, 983. [CrossRef]
55. Bayat, M.; Ghorbanpour, M.; Zare, R.; Jaafari, A.; Pham, B.T. Application of artificial neural networks
for predicting tree survival and mortality in the Hyrcanian forest of Iran. Comput. Electron. Agric. 2019,
164, 104929. [CrossRef]
56. Shahin, M.A.; Jaksa, M.B.; Maier, H.R. Artificial neural network applications in geotechnical engineering.
Aust. Geomech. 2001, 36, 49–62.
57. Zhang, Z.; Friedrich, K. Artificial neural networks applied to polymer composites: A review.
Compos. Sci. Technol. 2003, 63, 2029–2044. [CrossRef]
58. Sha, W.; Edwards, K. The use of artificial neural networks in materials science based research. Mater. Des.
2007, 28, 1747–1752. [CrossRef]
59. Črepinšek, M.; Liu, S.-H.; Mernik, L. A note on teaching–learning-based optimization algorithm. Inf. Sci.
2012, 212, 79–93. [CrossRef]
60. Rao, R.V.; Savsani, V.J.; Vakharia, D. Teaching-Learning-Based optimization: A novel method for constrained
mechanical design optimization problems. Comput. Aided Des. 2011, 43, 303–315. [CrossRef]
61. Zou, F.; Wang, L.; Hei, X.; Chen, D. Teaching-Learning-Based optimization with learning experience of other
learners and its application. Appl. Soft Comput. 2015, 37, 725–736. [CrossRef]
62. Rao, R.V.; Savsani, V.J.; Vakharia, D. Teaching-Learning-Based optimization: An optimization method for
continuous non-linear large scale problems. Inf. Sci. 2012, 183, 1–15. [CrossRef]
63. Khorsheed, M.S.; Al-Thubaity, A.O. Comparative evaluation of text classification techniques using a large
diverse Arabic dataset. Lang Resour. Eval. 2013, 47, 513–538. [CrossRef]
64. Leema, N.; Nehemiah, H.K.; Kannan, A. Neural network classifier optimization using differential evolution
with global information and back propagation algorithm for clinical datasets. Appl. Soft Comput. 2016,
49, 834–844. [CrossRef]
65. Pham, B.T.; Nguyen, M.D.; Van Dao, D.; Prakash, I.; Ly, H.-B.; Le, T.-T.; Ho, L.S.; Nguyen, K.T.; Ngo, T.Q.;
Hoang, V. Development of artificial intelligence models for the prediction of compression coefficient of soil:
An application of Monte Carlo sensitivity analysis. Sci. Total Environ. 2019, 679, 172–184. [CrossRef]
66. Asteris, P.G.; Mokos, V.G. Concrete compressive strength using artificial neural networks.
Neural Comput. Appl. 2019. [CrossRef]
67. Asteris, P.G.; Ashrafian, A.; Rezaie-Balf, M. Prediction of the compressive strength of self-compacting concrete
using surrogate models. Comput. Concr. 2019, 24, 137–150.
68. Asteris, P.G.; Kolovos, K.G. Self-compacting concrete strength prediction using surrogate models.
Neural Comput. Appl. 2019, 31, 409–424. [CrossRef]
69. Asteris, P.G.; Armaghani, D.J.; Hatzigeorgiou, G.D.; Karayannis, C.G.; Pilakoutas, K. Predicting the shear
strength of reinforced concrete beams using artificial neural networks. Comput. Concr. 2019, 24, 469–488.
70. Asteris, P.G.; Apostolopoulou, M.; Skentou, A.D.; Moropoulou, A. Application of artificial neural networks
for the prediction of the compressive strength of cement-based mortars. Comput. Concr. 2019, 24, 329–345.
71. Duan, J.; Asteris, P.G.; Nguyen, H.; Bui, X.-N.; Moayedi, H. A novel artificial intelligence technique to predict
compressive strength of recycled aggregate concrete using ICA-XGBoost model. Eng. Comput. 2020, 1–18.
[CrossRef]
72. Asteris, P.G.; Plevris, V. Anisotropic masonry failure criterion using artificial neural networks.
Neural Comput. Appl. 2017, 28, 2207–2229. [CrossRef]
73. Asteris, P.G.; Nikoo, M. Artificial bee colony-based neural network for the prediction of the fundamental
period of infilled frame structures. Neural Comput. Appl. 2019, 31, 4837–4847. [CrossRef]
Appl. Sci. 2020, 10, 5242 22 of 22

74. Ly, H.-B.; Monteiro, E.; Le, T.-T.; Le, V.M.; Dal, M.; Régnier, G.; Pham, B.T. Prediction and sensitivity analysis
of bubble dissolution time in 3D selective laser sintering using ensemble decision trees. Materials 2019,
12, 1544. [CrossRef]
75. Nguyen, H.-L.; Le, T.-H.; Pham, C.-T.; Le, T.-T.; Ho, L.S.; Le, V.M.; Pham, B.T.; Ly, H.-B. Development of
hybrid artificial intelligence approaches and a support vector machine algorithm for predicting the Marshall
parameters of stone matrix asphalt. Appl. Sci. 2019, 9, 3172. [CrossRef]
76. Nguyen, H.-L.; Pham, B.T.; Son, L.H.; Thang, N.T.; Ly, H.-B.; Le, T.-T.; Ho, L.S.; Le, T.-H.; Tien Bui, D.
Adaptive network based fuzzy inference system with meta-heuristic optimizations for international roughness
index prediction. Appl. Sci. 2019, 9, 4715. [CrossRef]
77. Pham, B.T.; Le, L.M.; Le, T.-T.; Bui, K.-T.T.; Le, V.M.; Ly, H.-B.; Prakash, I. Development of advanced artificial
intelligence models for daily rainfall prediction. Atmos. Res. 2020, 237, 104845. [CrossRef]
78. Phong, T.V.; Phan, T.T.; Prakash, I.; Singh, S.K.; Shirzadi, A.; Chapi, K.; Ly, H.-B.; Ho, L.S.; Quoc, N.K.;
Pham, B.T. Landslide susceptibility modeling using different artificial intelligence methods: A case study at
Muong Lay district, Vietnam. Geocarto Int. 2019, 1–24. [CrossRef]
79. Le, T.-T.; Pham, B.T.; Ly, H.-B.; Shirzadi, A.; Le, L.M. Development of 48-hour precipitation forecasting
model using nonlinear autoregressive neural network. In Proceedings of the CIGOS 2019, Innovation for
Sustainable Infrastructure; Ha-Minh, C., Dao, D.V., Benboudjema, F., Derrible, S., Huynh, D.V.K., Tang, A.M.,
Eds.; Springer: Singapore, 2020; pp. 1191–1196.
80. Goh, S.W.; You, Z. Resilient modulus and dynamic modulus of warm mix asphalt. In Proceedings of the
GeoCongress 2008: Geosustainability and Geohazard Mitigation, New Orleans, LA, USA, 9–12 March 2008;
pp. 1000–1007.
81. Ly, H.-B.; Le, L.M.; Duong, H.T.; Nguyen, T.C.; Pham, T.A.; Le, T.-T.; Le, V.M.; Nguyen-Ngoc, L.; Pham, B.T.
Hybrid Artificial intelligence approaches for predicting critical buckling load of structural members under
compression considering the influence of initial geometric imperfections. Appl. Sci. 2019, 9, 2258. [CrossRef]
82. Qi, C.; Tang, X.; Dong, X.; Chen, Q.; Fourie, A.; Liu, E. Towards Intelligent mining for backfill: A genetic
programming-based method for strength forecasting of cemented paste backfill. Miner. Eng. 2019, 133, 69–79.
[CrossRef]
83. Dao, D.V.; Adeli, H.; Ly, H.-B.; Le, L.M.; Le, V.M.; Le, T.-T.; Pham, B.T. A Sensitivity and robustness analysis
of GPR and ANN for high-performance concrete compressive strength prediction using a monte carlo
simulation. Sustainability 2020, 12, 830. [CrossRef]
84. Ly, H.-B.; Le, T.-T.; Le, L.M.; Tran, V.Q.; Le, V.M.; Vu, H.-L.T.; Nguyen, Q.H.; Pham, B.T. Development
of Hybrid machine learning models for predicting the critical buckling load of I-shaped cellular beams.
Appl. Sci. 2019, 9, 5458. [CrossRef]
85. Dao, D.V.; Ly, H.-B.; Vu, H.-L.T.; Le, T.-T.; Pham, B.T. Investigation and optimization of the C-ANN structure
in predicting the compressive strength of foamed concrete. Materials 2020, 13, 1072. [CrossRef]

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).