I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
5
,
Octo
b
er
20
25
,
p
p
.
4
9
6
5
~
4
9
8
2
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
9
6
5
-
4
9
8
2
4965
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Enha
ncing
concr
ete
sus
taina
bili
ty:
a neura
l ne
twork
s hy
brid
o
ptimiza
tion a
pp
ro
a
ch t
o
predi
ctin
g
com
press
iv
e str
eng
th
using
supp
lementary
c
e
mentitious
ma
teri
a
ls
E
s
ra
’
a
Alhena
wi
1
,
Ay
a
t
M
a
h
m
o
ud
Al
-
H
ina
wi
2
,
Z
a
her
Sa
la
h
3
,
O
m
a
r
Alidm
a
t
1
,
E
s
ra
a
Abu E
l
s
o
ud
1
,
Ra
ed
Ala
za
ida
h
1
,
B
a
s
ha
r
Ri
zik
AlSa
y
y
ed
4
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
Z
a
r
q
a
U
n
i
v
e
r
s
i
t
y
,
Za
r
q
a
,
J
o
r
d
a
n
2
D
e
p
a
r
t
me
n
t
o
f
A
l
l
i
e
d
En
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
s
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
T
h
e
H
a
sh
e
mi
t
e
U
n
i
v
e
r
s
i
t
y
,
Za
r
q
a
,
Jo
r
d
a
n
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
P
r
i
n
c
e
A
l
-
H
u
sse
i
n
B
i
n
A
b
d
u
l
l
a
h
I
I
f
o
r
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
Th
e
H
a
s
h
e
m
i
t
e
U
n
i
v
e
r
si
t
y
,
Z
a
r
q
a
,
J
o
r
d
a
n
4
D
e
p
a
r
t
me
n
t
o
f
C
i
v
i
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
o
f
J
o
r
d
a
n
,
A
mm
a
n
,
J
o
r
d
a
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
3
0
,
2
0
2
4
R
ev
is
ed
J
u
n
1
9
,
2
0
2
5
Acc
ep
ted
J
u
n
3
0
,
2
0
2
5
Th
is
re
se
a
rc
h
e
v
a
lu
a
tes
th
e
im
p
l
e
m
e
n
tatio
n
o
f
a
d
v
a
n
c
e
d
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
o
lo
g
ies
f
o
r
c
o
n
c
re
te
m
ix
d
e
sig
n
t
o
a
c
h
iev
e
b
e
tt
e
r
p
re
d
icti
v
e
m
o
d
e
ls
a
n
d
su
sta
i
n
a
b
le
o
u
tco
m
e
s.
T
h
i
s
stu
d
y
d
e
v
e
lo
p
s
a
h
y
b
ri
d
o
p
ti
m
iza
ti
o
n
a
p
p
ro
a
c
h
b
y
c
o
m
b
in
in
g
d
u
n
g
b
e
e
tl
e
o
p
ti
m
ize
r
(DBO
A)
a
n
d
firefl
y
a
lg
o
rit
h
m
(F
LA)
t
o
o
p
ti
m
ize
h
y
p
e
rp
a
ra
m
e
ters
fo
r
c
o
n
v
o
lu
ti
o
n
a
l
-
re
c
u
rr
e
n
t
n
e
u
ra
l
n
e
two
rk
s
i
n
o
rd
e
r
t
o
c
o
rre
c
tl
y
p
r
e
d
ict
c
o
n
c
re
te
c
o
m
p
re
ss
iv
e
stre
n
g
th
w
h
e
n
u
sin
g
su
p
p
lem
e
n
tary
c
e
m
e
n
ti
ti
o
u
s
m
a
teria
ls
(S
C
M
s).
S
h
a
p
ley
a
d
d
it
i
v
e
e
x
p
lan
a
ti
o
n
s
(
S
HA
P
)
p
ro
v
i
d
e
fe
a
tu
re
sig
n
ifi
c
a
n
c
e
a
n
a
ly
sis
,
wh
ich
e
n
s
u
re
s
th
a
t
th
e
m
o
d
e
l
p
r
o
d
u
c
e
s
u
n
d
e
rsta
n
d
a
b
le
c
o
n
c
lu
si
o
n
s
su
p
p
o
rted
b
y
e
m
p
iri
c
a
l
fin
d
i
n
g
s.
T
h
e
fi
n
d
i
n
g
s
d
e
m
o
n
stra
te
th
a
t
th
is
m
e
th
o
d
e
n
h
a
n
c
e
s
th
e
p
re
d
ictiv
e
a
c
c
u
ra
c
y
o
f
stre
n
g
th
a
n
a
ly
sis,
a
lo
n
g
with
o
ffe
ri
n
g
c
rit
ica
l
in
si
g
h
ts
a
b
o
u
t
S
CM
u
sa
g
e
i
n
o
r
d
e
r
to
im
p
ro
v
e
su
sta
in
a
b
le
c
o
n
stru
c
ti
o
n
m
e
t
h
o
d
s
.
Th
e
m
o
d
e
l
p
ro
v
e
s
su
it
a
b
le
fo
r
i
n
teg
r
a
ti
o
n
in
to
a
c
tu
a
l
c
o
n
c
re
te
m
ix
d
e
sig
n
a
n
d
q
u
a
li
t
y
c
o
n
tro
l
s
y
ste
m
s
b
e
c
a
u
se
it
a
c
h
iev
e
s
b
o
t
h
c
o
m
p
u
tatio
n
a
l
s
p
e
e
d
a
n
d
p
a
ss
e
s
v
a
li
d
a
ti
o
n
tes
ts
o
n
d
isti
n
c
t
d
a
tas
e
ts.
T
h
e
re
se
a
rc
h
c
re
a
tes
fo
u
n
d
a
t
io
n
s
fo
r
u
p
c
o
m
i
n
g
stu
d
ies
a
b
o
u
t
m
u
lt
i
m
o
d
a
l
lea
rn
i
n
g
e
n
ric
h
m
e
n
t
a
n
d
d
e
a
ls
with
e
th
ica
l
c
o
n
c
e
rn
s
i
n
c
o
n
stru
c
ti
o
n
site
sa
fe
ty
wh
e
n
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
sy
ste
m
s.
K
ey
w
o
r
d
s
:
Fire
f
ly
alg
o
r
ith
m
o
p
tim
izatio
n
Gas e
m
is
s
io
n
s
Gr
ee
n
h
o
u
s
e
Su
p
p
lem
en
tar
y
ce
m
en
titi
o
u
s
m
ater
ials
Su
s
tain
ab
le
co
n
s
tr
u
ctio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Z
ah
er
Salah
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
Facu
lty
o
f
Prin
ce
A
l
-
Hu
s
s
ein
B
in
Ab
d
u
llah
I
I
f
o
r
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
T
h
e
Hash
em
ite
Un
iv
er
s
ity
Z
ar
q
a,
J
o
r
d
an
E
m
ail:
za
h
er
@
h
u
.
ed
u
.
j
o
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
b
u
ild
i
n
g
in
d
u
s
tr
y
h
as
i
m
p
lem
en
ted
m
a
n
y
ce
m
e
n
t
m
an
u
f
ac
tu
r
i
n
g
g
r
ee
n
h
o
u
s
e
g
as
em
is
s
io
n
r
ed
u
ctio
n
m
ea
s
u
r
es
[
1
]
,
[
2
]
.
Similar
to
b
u
r
n
in
g
g
aso
lin
e,
th
e
m
an
u
f
ac
t
u
r
e
o
f
h
y
d
r
a
u
lic
c
em
en
t
ac
co
u
n
ts
f
o
r
7
%
–
9
%
o
f
wo
r
ld
ca
r
b
o
n
d
io
x
id
e
em
is
s
io
n
s
[
3
]
–
[
5
]
.
T
o
lo
wer
C
O2
em
is
s
io
n
s
,
ce
m
e
n
t
m
ix
es
ca
n
in
clu
d
e
waste
o
r
in
d
u
s
tr
ial
f
lo
ws
a
s
m
u
lti
-
co
m
p
o
n
en
t
b
in
d
e
r
s
[
3
]
,
[
6
]
–
[
1
4
]
.
On
e
way
to
cu
t
g
r
ee
n
h
o
u
s
e
g
as
em
is
s
io
n
s
b
y
4
7
%
to
5
%
is
to
u
s
e
in
d
u
s
tr
ial
waste
in
s
tead
o
f
ce
m
en
t,
s
u
ch
as
g
r
o
u
n
d
g
r
an
u
lated
b
last
f
u
r
n
ac
e
s
lag
(
GGBS
)
f
r
o
m
b
last
f
u
r
n
ac
e
i
r
o
n
o
r
e
ex
tr
ac
tio
n
[
1
5
]
,
[
1
6
]
.
On
e
to
n
o
f
GGBS
p
r
o
d
u
ctio
n
h
as
a
wo
r
ld
wid
e
en
v
ir
o
n
m
en
tal
em
is
s
io
n
f
ac
to
r
o
f
0
.
1
4
3
t
C
O2
-
e/to
n
,
wh
ic
h
is
less
th
an
th
e
s
tan
d
ar
d
estab
lis
h
ed
b
y
m
o
s
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
6
5
-
4
9
8
2
4966
n
atio
n
s
an
d
in
te
r
n
atio
n
al
o
r
g
a
n
izatio
n
s
.
C
em
en
t
u
s
es
9
t
C
O2
-
e/to
n
,
alth
o
u
g
h
co
n
cr
ete
m
ix
es
ar
e
m
ad
e
u
s
in
g
tr
an
s
p
o
r
tatio
n
tech
n
o
lo
g
ies
[
1
7
]
.
Ab
o
u
t
6
0
%
o
f
th
e
5
3
0
m
illi
o
n
to
n
s
o
f
g
lo
b
al
s
lag
(
GGBS
)
i
s
u
s
ed
in
co
n
s
tr
u
ctio
n
[
1
8
]
,
[
1
9
]
.
GGBS
h
as
b
ee
n
s
tu
d
ied
o
n
v
ar
io
u
s
c
o
n
cr
ete
an
d
m
o
r
tar
ty
p
es
[
3
]
,
[
2
0
]
,
[
2
1
]
.
An
o
th
er
s
tu
d
y
[
2
2
]
f
o
u
n
d
t
h
at
MS
an
d
GGBS
s
y
n
er
g
is
tically
im
p
r
o
v
ed
co
n
cr
ete
r
esis
tan
ce
to
u
n
f
av
o
r
ab
le
co
n
s
eq
u
en
ce
s
.
Acc
o
r
d
in
g
to
a
d
if
f
er
en
t
r
esear
ch
[
2
3
]
,
r
esis
tan
ce
an
d
d
u
r
ab
ilit
y
with
o
u
t
PC
wer
e
b
es
t
b
o
o
s
ted
b
y
2
0
%
MBS
m
ad
e
f
r
o
m
r
ice
h
u
s
k
a
n
d
b
y
u
s
in
g
s
lag
p
o
wd
er
in
s
tead
.
B
y
co
n
v
er
tin
g
f
ly
ash
an
d
p
o
wd
er
ed
b
last
f
u
r
n
ac
e
s
lag
,
waste
g
las
s
-
d
er
iv
ed
n
an
o
p
o
wd
er
,
in
to
alk
ali
-
ac
tiv
ated
m
o
r
tar
s
,
d
r
y
in
g
s
h
r
in
k
ag
e
is
d
ec
r
ea
s
ed
an
d
wea
r
,
f
r
ee
z
e
-
th
aw
cy
cles,
an
d
s
u
lf
u
r
ic
ac
id
r
esis
tan
ce
ar
e
en
h
an
ce
d
[
2
4
]
.
Acc
o
r
d
in
g
to
o
th
er
s
tu
d
ies,
GGBS
s
h
o
u
ld
b
e
u
s
ed
in
p
lace
o
f
2
0
%
o
f
ce
m
en
t
b
ef
o
r
e
s
am
p
le
wo
r
k
ab
ilit
y
an
d
p
o
r
o
s
ity
ca
u
s
e
r
esi
s
tan
ce
to
d
r
o
p
[
1
5
]
,
[
2
5
]
.
T
h
e
wo
r
k
ab
ilit
y
,
b
leed
in
g
,
h
e
at
o
f
h
y
d
r
atio
n
,
co
r
r
o
s
io
n
,
p
o
r
o
s
ity
,
an
d
p
er
m
ea
b
ilit
y
o
f
b
o
th
f
r
esh
an
d
h
ar
d
en
e
d
co
n
cr
ete
ar
e
all
im
p
r
o
v
e
d
b
y
GGBS
in
ce
m
en
t
[
2
6
]
–
[
2
9
]
.
Du
e
to
g
r
ea
ter
p
ar
ticle
d
is
tr
ib
u
tio
n
,
GGBS
im
p
r
o
v
ed
co
n
cr
ete
w
o
r
k
ab
ilit
y
b
y
4
0
%
[
3
]
.
C
em
e
n
t
p
aste
f
ills
ag
g
r
e
g
ate
m
icr
o
-
s
p
ac
es
to
r
e
d
u
ce
in
ter
n
al
f
r
ictio
n
b
etwe
en
co
n
c
r
ete
co
m
p
o
n
en
ts
,
im
p
r
o
v
in
g
w
o
r
k
ab
ilit
y
[
2
5
]
,
[
3
0
]
.
T
en
s
ile
s
tr
en
g
th
,
a
v
ital
r
o
ad
co
n
cr
ete
p
r
o
p
er
ty
,
h
as
d
esig
n
p
ar
am
eter
co
n
s
tr
ain
ts
th
at
s
h
o
u
ld
b
e
co
n
tr
o
lled
to
m
in
im
ize
cr
ac
k
s
[
3
1
]
.
C
o
n
c
r
ete
s
h
r
in
k
ag
e
d
ep
en
d
s
o
n
ce
m
e
n
t,
wate
r
,
ag
g
r
e
g
ates,
air
d
r
y
n
ess
,
an
d
r
is
in
g
tem
p
er
atu
r
e
[
3
2
]
.
C
em
en
t
d
o
s
e,
C
3
A
co
n
ten
t,
g
el
co
m
p
o
n
e
n
t,
an
d
alk
ali
co
n
t
en
t
af
f
ec
t
s
h
r
in
k
ag
e
[
3
3
]
.
E
ar
ly
s
ettin
g
r
e
d
u
ce
s
ce
m
en
t p
aste v
o
lu
m
e
b
y
1
% o
f
d
r
y
ce
m
en
t
v
o
lu
m
e
[
3
3
]
,
[
3
4
]
.
Sh
r
in
k
in
g
v
alu
es
f
all
b
el
o
w
ze
r
o
.
C
o
n
c
r
etes
with
a
lo
t
o
f
b
in
d
er
ca
n
r
ea
ch
6
m
m
/m
[
3
5
]
.
Size
d
ec
r
ea
s
es
b
y
5
%
af
ter
o
n
e
m
o
n
th
,
6
0
%
af
ter
th
r
ee
m
o
n
t
h
s
,
an
d
7
5
%
af
ter
a
y
ea
r
[
3
2
]
.
W
/C
r
atio
s
ca
u
s
e
co
n
cr
ete
p
o
r
es
to
ex
p
an
d
,
wh
i
ch
in
cr
ea
s
es
s
h
r
in
k
ag
e.
Ad
d
iti
o
n
al
ag
g
r
e
g
ates
p
r
ev
en
t
s
h
r
in
k
ag
e
b
ec
au
s
e
th
ey
ar
e
co
ar
s
er
[
3
6
]
.
Mo
r
e
th
a
n
5
0
%
r
elativ
e
h
u
m
id
ity
an
d
8
0
0
p
p
m
C
O2
in
c
r
ea
s
e
s
h
r
in
k
ag
e
r
ates
b
ec
a
u
s
e
C
O2
d
is
s
o
lv
es
an
d
elim
in
ates
h
y
d
r
o
s
ilicate
h
y
d
r
atio
n
p
r
o
d
u
cts
[
3
5
]
.
T
h
e
ca
r
b
o
n
atio
n
p
r
o
ce
s
s
is
ac
ce
ler
ated
b
y
h
ig
h
ex
ter
n
al
C
O2
co
n
ce
n
tr
at
io
n
s
,
lo
wer
in
g
th
e
p
H
f
r
o
m
1
2
–
1
3
to
less
th
an
9
an
d
r
u
p
t
u
r
in
g
th
e
r
ein
f
o
r
cin
g
b
ar
'
s
p
ass
iv
atio
n
lay
er
,
wh
ich
ca
u
s
es c
o
r
r
o
s
io
n
[
3
7
]
–
[
4
0
]
.
As
th
e
lar
g
est
co
m
p
o
n
en
t
o
f
co
n
cr
ete,
ag
g
r
eg
ate
u
s
ag
e
h
as
th
e
g
r
ea
test
en
v
ir
o
n
m
en
ta
l
im
p
ac
t.
An
n
u
al
in
ter
n
atio
n
al
b
u
ild
in
g
ag
g
r
eg
ate
d
em
a
n
d
ex
ce
ed
s
1
0
b
illi
o
n
to
n
s
[
4
1
]
–
[
4
4
]
.
R
o
a
d
asp
h
alt
p
av
em
en
t
(
R
AP)
ag
g
r
eg
ates
[
4
5
]
–
[
4
7
]
,
q
u
ar
r
y
s
an
d
(
QS)
[
4
8
]
,
r
ec
y
cled
ag
g
r
eg
ate
c
o
n
cr
ete
(
R
AC
)
f
r
o
m
b
u
ild
in
g
d
em
o
liti
o
n
s
[
4
3
]
,
[
4
4
]
,
a
n
d
ec
o
lo
g
ical
m
o
r
tar
th
at
r
ep
lace
s
n
atu
r
al
ag
g
r
e
g
ates
with
g
lass
waste
[
4
9
]
h
av
e
all
b
ee
n
th
e
s
u
b
ject
o
f
ca
d
a
v
er
ic
r
esear
ch
.
AC
B
FS
is
an
o
th
er
air
-
co
o
led
r
o
ad
c
o
n
cr
ete
a
g
g
r
e
g
ate
s
o
u
r
ce
[
5
0
]
,
[
5
1
]
.
I
t
h
as
b
ee
n
d
e
m
o
n
s
tr
ated
th
at
n
atu
r
al
a
g
g
r
e
g
ates
m
ad
e
f
r
o
m
b
last
f
u
r
n
ac
e
s
lag
m
ay
b
e
u
s
ed
in
asp
h
alt
[
5
2
]
.
Fo
r
co
n
c
r
ete
s
tr
u
ctu
r
es,
th
e
J
ap
an
ese
Gu
id
e
s
u
g
g
ests
a
2
0
%
–
6
0
%
co
m
b
in
atio
n
o
f
n
atu
r
al
an
d
f
in
e
m
ater
ials
[
5
3
]
.
T
h
e
r
ef
er
e
n
ce
s
tan
d
a
r
d
f
o
r
b
last
f
u
r
n
ac
e
s
lag
co
n
cr
ete
ag
g
r
eg
ates
in
o
u
r
n
atio
n
h
as
b
ee
n
SR
E
N
1
2
6
2
0
s
in
ce
2
0
0
3
[
5
4
]
.
I
t
is
p
o
s
s
ib
le
to
in
co
r
p
o
r
ate
s
teel
in
d
u
s
tr
y
waste
m
ater
ials
in
to
r
o
ad
co
n
cr
ete
m
ix
tu
r
es,
b
u
t
it
is
im
p
o
r
tan
t
to
ass
ess
h
o
w
th
ey
af
f
ec
t
b
o
t
h
f
r
esh
an
d
h
a
r
d
en
ed
co
n
c
r
ete
[
5
5
]
.
Utilizin
g
in
n
o
v
ativ
e
tec
h
n
o
lo
g
ies
an
d
r
eu
s
in
g
s
y
n
th
etic
m
ater
ials
ca
n
h
elp
th
e
en
v
ir
o
n
m
en
t b
y
r
e
d
u
cin
g
m
an
u
f
ac
tu
r
i
n
g
co
s
ts
an
d
co
n
s
er
v
in
g
n
o
n
-
r
en
ewa
b
le
r
eso
u
r
ce
s
[
5
6
]
.
A
lo
w
-
ca
r
b
o
n
cir
c
u
lar
ec
o
n
o
m
y
is
a
g
l
o
b
al
g
o
al,
a
n
d
th
e
b
u
ild
in
g
in
d
u
s
tr
y
is
p
r
o
m
o
tin
g
g
r
ee
n
alter
n
ativ
es
an
d
m
in
im
izin
g
e
n
v
ir
o
n
m
en
tal
h
a
r
m
ca
u
s
ed
b
y
th
e
ce
m
e
n
t
in
d
u
s
tr
y
.
T
h
e
p
r
o
d
u
ctio
n
o
f
co
n
cr
ete
an
d
ce
m
en
t
p
r
o
d
u
ce
s
alm
o
s
t
n
o
em
is
s
io
n
s
.
Nin
e
m
etr
ic
to
n
s
o
f
C
O2
m
u
s
t
b
e
r
elea
s
ed
b
y
t
h
e
ce
m
en
t
in
d
u
s
tr
y
f
o
r
ev
er
y
m
etr
ic
to
n
o
f
ce
m
en
t
p
r
o
d
u
ce
d
.
T
h
er
e
a
r
e
m
ajo
r
r
ep
er
cu
s
s
io
n
s
lin
k
ed
to
th
e
g
lo
b
al
em
is
s
io
n
s
f
r
o
m
th
e
b
u
ild
i
n
g
i
n
d
u
s
tr
y
.
T
h
e
r
ef
o
r
e,
o
n
e
o
f
th
e
g
r
ea
test
ap
p
r
o
ac
h
es
to
r
ed
u
ce
g
r
ee
n
h
o
u
s
e
g
as
em
is
s
io
n
s
is
to
r
ep
lace
ce
m
en
t
with
s
im
ilar
m
ater
ials
[
5
7
]
.
Su
p
p
lem
e
n
tar
y
ce
m
en
titi
o
u
s
m
ater
ials
(
SC
Ms)
ar
e
co
s
t
-
ef
f
ec
tiv
e
an
d
ec
o
lo
g
ically
b
en
ef
icial
a
lter
n
ativ
es
to
ce
m
en
t.
Mo
s
t
SC
Ms
ar
e
p
o
zz
o
lan
ic,
wh
ich
im
p
r
o
v
e
c
o
n
cr
ete
m
icr
o
s
tr
u
ctu
r
e,
late
s
tr
en
g
th
,
a
n
d
C
O2
em
is
s
io
n
s
[
5
8
]
.
Fly
ash
(
FA)
f
r
o
m
c
o
al
p
o
wer
s
tatio
n
s
is
th
e
m
o
s
t
co
m
m
o
n
SC
M
in
ce
m
en
t
-
b
ase
d
m
ater
ials
.
I
n
d
u
s
tr
y
s
tan
d
ar
d
s
r
ec
o
m
m
en
d
r
ep
lacin
g
ce
m
en
t
with
FA
b
y
1
0
%
–
3
0
%
[
5
9
]
,
[
6
0
]
.
Hi
g
h
v
o
lu
m
e
f
l
y
ash
(
HVFA
)
co
n
cr
ete
h
as
th
e
b
est
m
ec
h
an
ical
p
r
o
p
er
ties
an
d
d
u
r
ab
ilit
y
,
m
ak
i
n
g
it
a
s
u
s
ta
in
ab
le
co
n
s
tr
u
ctio
n
m
ater
ial
[
6
1
]
–
[
6
6
]
.
Fo
llo
win
g
5
6
a
n
d
9
1
d
ay
s
o
f
m
ix
in
g
F
A
with
ce
m
en
t
an
d
r
e
p
lacin
g
5
0
%
o
f
t
h
e
ce
m
e
n
t
with
FA
at
a
W
/C
r
atio
o
f
0
.
4
2
,
B
o
u
z
o
u
b
aâ
et
a
l.
[
6
7
]
ac
h
iev
ed
c
o
m
p
r
ess
iv
e
s
tr
en
g
th
s
o
f
3
2
.
2
MPa
an
d
3
5
.
2
MPa.
T
h
ese
v
alu
es
wer
e
g
r
ea
ter
th
an
o
r
d
in
ar
y
p
o
r
tlan
d
ce
m
e
n
t
(
OPC
)
co
n
c
r
ete'
s
0
.
5
3
.
Acc
o
r
d
in
g
to
Ma
r
d
an
i
-
Ag
h
a
b
b
ag
l
o
u
an
d
R
am
y
ar
[
6
8
]
,
a
f
ter
1
8
0
d
a
y
s
,
6
0
%
FA
r
ep
lace
m
en
t
in
cr
ea
s
ed
co
m
p
r
ess
o
r
s
tr
en
g
th
b
y
1
5
%
–
1
8
% a
b
o
v
e
OPC
.
Ac
co
r
d
in
g
to
C
h
en
et
a
l.
[
6
9
]
,
d
r
y
in
g
s
h
r
in
k
a
g
e
was d
ec
r
ea
s
ed
b
y
2
3
%
–
3
0
% wh
en
FA
was
s
u
b
s
titu
ted
f
o
r
5
0
%
–
8
0
%
o
f
th
e
c
em
en
t.
Acc
o
r
d
in
g
to
Mü
llau
er
et
a
l.
[
7
0
]
,
7
0
%
FA
s
u
cc
es
s
f
u
lly
d
ec
r
ea
s
ed
alk
ali
-
a
g
g
r
eg
ate
r
ea
ctio
n
s
.
Acc
o
r
d
i
n
g
t
o
W
an
g
et
a
l.
[
7
1
]
,
to
r
ed
u
ce
th
e
p
o
r
o
s
ity
o
f
co
n
cr
ete,
3
0
%
b
y
weig
h
t
o
f
co
a
r
s
e
ag
g
r
e
g
at
e
s
h
o
u
ld
b
e
u
s
ed
f
o
r
FGPS
an
d
1
5
%
f
o
r
FA.
Ad
d
itio
n
ally
,
W
an
g
et
a
l.
[
7
2
]
d
is
co
v
er
ed
th
at
a
d
d
in
g
3
0
%
F
A
to
p
an
el
co
n
cr
ete
im
p
r
o
v
e
d
its
p
er
m
ea
b
ilit
y
an
d
c
o
m
p
r
ess
iv
e
s
tr
en
g
th
with
tim
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
co
n
crete
s
u
s
ta
in
a
b
ilit
y:
a
n
eu
r
a
l
n
etw
o
r
ks h
yb
r
id
o
p
timiz
a
tio
n
…
(
E
s
r
a
’
a
A
lh
e
n
a
w
i
)
4967
G
r
an
u
lated
g
r
o
u
n
d
b
last
f
u
r
n
ac
e
s
lag
(
GGB
FS
)
b
last
f
u
r
n
ac
e
ir
o
n
waste
is
f
r
eq
u
en
tly
u
s
ed
as
a
ce
m
en
t
alter
n
ativ
e.
Glass
y
b
last
f
u
r
n
ac
e
s
lag
is
q
u
en
ch
ed
an
d
co
o
led
to
f
o
r
m
GGBF
S,
wh
ich
b
in
d
s
well.
C
r
o
s
s
in
[
1
6
]
f
o
u
n
d
th
at
GGBF
S
as
an
S
C
M
r
ed
u
ce
d
g
r
ee
n
h
o
u
s
e
g
as
tr
an
s
p
ar
en
cy
b
y
4
7
.
5
%.
Af
ter
2
8
d
ay
s
o
f
cu
r
in
g
,
th
e
m
ec
h
an
ical
s
tr
en
g
th
o
f
ter
n
a
r
y
m
i
x
ed
ce
m
en
t
co
n
tain
in
g
a
lar
g
er
p
er
ce
n
ta
g
e
o
f
GGBF
S
was
g
r
ea
ter
t
h
an
th
at
o
f
OPC
2
2
,
[
2
2
]
,
[
7
3
]
,
[
7
4
]
.
Du
e
to
t
h
e
d
ilu
tin
g
ef
f
ec
t,
L
im
et
a
l.
[
7
5
]
d
is
co
v
er
ed
th
at
ter
n
ar
y
m
ix
ed
ce
m
en
t
co
n
tain
i
n
g
GGBF
S
h
ad
a
lo
wer
p
ea
k
co
m
p
r
ess
iv
e
s
tr
en
g
th
th
an
OPC
.
Ho
wev
er
,
it
d
id
b
etter
th
an
Af
ter
2
8
to
3
6
5
d
ay
s
o
f
th
e
r
ap
y
,
OPC
an
d
ac
q
u
ir
ed
m
o
r
e
b
etwe
en
2
8
an
d
9
1
d
a
y
s
[
7
3
]
–
[
7
7
]
.
C
h
ea
h
et
a
l.
[
7
8
]
i
n
v
esti
g
ated
a
ter
n
ar
y
m
ix
ed
ce
m
en
t
m
o
r
tar
th
at
co
n
tain
e
d
ce
m
en
t,
G
GB
FS
,
an
d
g
r
o
u
n
d
co
al
b
o
tto
m
ash
(
GC
B
A)
.
T
h
ey
d
is
co
v
er
ed
th
at
th
e
m
ec
h
an
i
ca
l
an
d
p
h
y
s
ical
ch
ar
ac
ter
is
tics
o
f
ce
m
en
t
m
o
r
ta
r
wer
e
en
h
an
ce
d
b
y
4
0
% GG
B
FS
an
d
5
% GCB
A
with
o
u
t SP a
n
d
4
0
% GG
B
FS
an
d
1
0
% GCB
A
with
SP
[
7
9
]
.
R
esear
ch
o
n
waste
co
n
cr
ete
ag
g
r
eg
ates
an
d
ter
n
a
r
y
ce
m
e
n
titi
o
u
s
in
g
r
ed
ie
n
ts
lik
e
s
ilica
f
u
m
e
a
n
d
GGBF
S
r
ev
ea
led
th
at
a
d
d
in
g
GGBF
S
to
2
5
%
o
f
ce
m
en
t
in
c
r
ea
s
ed
th
e
GW
P
v
alu
e.
Acc
o
r
d
in
g
to
W
eise
et
a
l.
[
8
0
]
,
th
e
3
0
%
weig
h
t
m
etak
ao
lin
m
ix
co
n
s
u
m
ed
th
e
m
o
s
t
C
H
b
etwe
en
d
ay
s
2
8
an
d
5
6
,
wh
ich
h
ad
an
im
p
ac
t
o
n
s
tr
en
g
th
.
Usi
n
g
SC
Ms
in
co
n
cr
ete
im
p
r
o
v
es
ce
m
e
n
t
r
ea
c
tio
n
,
b
u
t
m
etak
ao
lin
co
n
te
n
t
i
n
cr
ea
s
es
ef
f
icien
cy
[
8
1
]
.
SC
Ms
lik
e
FA
an
d
GG
B
FS
ca
n
en
ab
le
a
lo
w
-
ca
r
b
o
n
cir
cu
lar
ec
o
n
o
m
y
in
b
u
ild
i
n
g
.
T
h
ese
m
ater
ials
r
ed
u
ce
g
r
ee
n
h
o
u
s
e
g
as
em
is
s
io
n
s
an
d
in
c
r
ea
s
e
co
n
cr
ete
s
tr
u
ctu
r
e
e
f
f
icien
cy
an
d
d
u
r
atio
n
,
e
n
co
u
r
ag
in
g
co
n
s
tr
u
ctio
n
s
u
s
tain
ab
ilit
y
.
I
m
p
er
m
ea
b
ilit
y
in
c
o
n
cr
ete
af
f
ec
ts
r
esis
tan
ce
to
wate
r
-
s
o
lu
b
l
e
ch
lo
r
id
e
io
n
s
,
C
O2
,
an
d
s
u
lf
ate,
wh
ich
im
p
air
co
n
cr
ete
d
u
r
ab
ilit
y
.
T
h
ese
ch
em
icals
ca
n
in
f
iltra
te
co
n
cr
ete,
d
e
g
r
ad
e
it,
an
d
lim
it
it
s
life
s
p
an
,
m
ak
i
n
g
th
em
g
lo
b
al
th
r
ea
ts
[
8
2
]
–
[
8
4
]
.
C
o
n
cr
ete
p
o
r
o
s
ity
,
wh
ic
h
af
f
ec
ts
its
p
er
m
ea
b
ilit
y
,
d
ep
e
n
d
s
o
n
its
s
ize,
s
h
ap
e,
an
d
in
ter
f
ac
ial
tr
an
s
itio
n
zo
n
e.
R
ec
y
cled
f
in
e
ag
g
r
eg
ate
(
R
FA
)
%,
W
/
C
r
atio
,
an
d
m
in
er
al
ad
m
ix
tu
r
es
d
ir
ec
tly
af
f
ec
t
r
ec
y
cled
f
in
e
ag
g
r
eg
at
e
co
n
cr
ete
(
R
FAc)
im
p
er
m
ea
b
ilit
y
.
Acc
o
r
d
in
g
to
r
esear
c
h
,
ad
m
ix
tu
r
es
an
d
ad
d
itiv
es o
p
tim
ize
co
n
cr
ete'
s
m
icr
o
s
co
p
ic
s
tr
u
ctu
r
e,
b
o
o
s
tin
g
its
im
p
er
m
ea
b
ilit
y
[
8
5
]
–
[
8
7
]
.
C
o
n
cr
ete
p
o
r
o
s
ity
is
h
ig
h
ly
d
ep
en
d
e
n
t
o
n
R
FA
q
u
an
titati
v
e
p
r
o
p
e
r
ties
.
R
F
A
h
as
f
ewe
r
p
h
y
s
ical
p
r
o
p
er
ties
th
an
n
atu
r
al
f
in
e
ag
g
r
eg
ates.
B
ec
au
s
e
R
F
Ac
u
s
es
m
o
r
e
R
FA,
its
p
er
f
o
r
m
an
ce
is
u
s
u
ally
p
o
o
r
e
r
R
FA
p
ar
ticles
ab
s
o
r
b
g
ap
s
an
d
m
ic
r
o
cr
ac
k
s
f
r
o
m
th
e
p
r
ev
io
u
s
m
o
r
tar
b
ec
au
s
e
o
f
th
eir
p
o
o
r
g
r
ad
in
g
,
wh
ich
m
ak
es
th
e
co
n
cr
ete
p
o
r
o
u
s
.
T
h
u
s
,
R
FAc
r
ep
lace
m
en
t
in
cr
ea
s
es
th
e
wate
r
v
ap
o
r
tr
an
s
m
is
s
io
n
b
ar
r
ier
[
8
8
]
–
[
9
1
]
.
B
ec
au
s
e
R
F
A
is
p
o
r
o
u
s
an
d
a
b
s
o
r
b
s
wate
r
,
SC
C
m
ix
tu
r
es
ab
s
o
r
b
m
o
r
e
wate
r
with
a
h
ig
h
er
R
FA
s
u
b
s
titu
tio
n
r
ate.
Ho
wev
er
,
R
FAc's
p
er
m
ea
b
ilit
y
is
lo
wer
in
a
s
u
lf
ate
en
v
ir
o
n
m
e
n
t
th
an
in
r
e
g
u
lar
co
n
cr
ete,
an
d
its
wate
r
ab
s
o
r
p
tio
n
is
2
5
%
lo
wer
[
9
2
]
.
T
h
e
W
/C
r
atio
is
cr
u
cial
to
co
n
cr
ete
p
r
ep
a
r
atio
n
an
d
p
er
m
ea
b
ilit
y
r
esis
tan
ce
.
A
W
/C
r
atio
o
f
0
.
6
5
r
ed
u
ce
s
im
p
er
m
ea
b
ilit
y
co
m
p
ar
ed
t
o
0
.
5
5
.
B
ec
au
s
e
a
lar
g
er
W
/C
r
atio
s
lo
ws
R
FAc
ce
m
en
t
h
y
d
r
atio
n
,
p
o
r
es f
o
r
m
an
d
co
n
cr
ete
co
m
p
ac
tn
ess
d
ec
r
ea
s
es
[
8
8
]
,
[
8
9
]
,
[
9
3
]
.
FA
ca
n
r
ep
lace
s
ilicate
ce
m
en
t
in
co
n
s
tr
u
ctio
n
d
u
e
to
its
p
o
zz
o
lan
ic
c
h
ar
ac
ter
is
tics
[
9
3
]
.
C
o
n
cr
ete
th
at
co
n
tain
s
f
in
e
f
l
y
ash
h
as
b
etter
h
y
d
r
atio
n
,
ze
o
lite,
ac
cu
m
u
latio
n
,
an
d
n
u
clea
tio
n
[
9
4
]
.
C
o
n
cr
ete
d
en
s
ity
r
is
es
as
a
r
esu
lt
o
f
th
e
ea
r
ly
h
y
d
r
atio
n
r
esp
o
n
s
e
o
f
FA,
wh
ich
in
cr
ea
s
es
th
e
q
u
a
n
tity
o
f
h
y
d
r
atio
n
p
r
o
d
u
cts
in
th
e
p
o
r
es
[
9
5
]
.
T
h
e
p
er
m
ea
b
il
ity
o
f
s
elf
-
co
m
p
ac
tin
g
co
n
cr
et
e
co
n
tain
in
g
1
0
%
FA
an
d
1
0
0
%
R
FA
was
lo
wer
th
an
th
at
o
f
co
n
tr
o
l m
ix
es d
ev
o
id
o
f
FA
[
9
6
]
.
Du
e
to
R
FA'
s
p
o
o
r
p
h
y
s
ical
an
d
c
h
em
ical
ch
ar
a
cter
izatio
n
an
d
R
AC
'
s
wea
k
in
ter
f
ac
ial
tr
an
s
itio
n
zo
n
e
(
I
T
Z
)
,
alter
n
ativ
e
m
i
x
in
g
s
tr
ateg
ies
h
av
e
b
ee
n
in
tr
o
d
u
ce
d
.
T
h
is
co
m
p
r
is
es
th
e
o
p
t
im
al
tr
ip
le
m
ix
in
g
tech
n
iq
u
e
(
OT
M)
,
tr
i
p
le
m
ix
i
n
g
m
eth
o
d
(
T
M)
[
9
7
]
,
an
d
d
o
u
b
le
m
ix
in
g
m
eth
o
d
(
DM
)
[
9
8
]
.
T
o
co
n
clu
d
e,
OT
M
s
taf
f
ad
d
SP
s
,
wate
r
-
r
ed
u
cin
g
a
g
en
ts
,
in
v
ar
ie
d
o
r
d
er
s
.
SP
is
ad
d
ed
to
th
e
m
i
x
with
o
th
er
g
ellin
g
co
m
p
o
n
en
ts
to
in
cr
ea
s
e
g
ellin
g
an
d
I
T
Z
p
r
o
p
o
r
tio
n
.
T
h
is
m
eth
o
d
u
s
es
th
e
ze
o
lite
ef
f
ec
t
m
o
r
e
ef
f
ec
tiv
ely
;
h
en
ce
th
e
R
AC
h
as
an
8
-
p
er
m
ea
b
ilit
y
r
atin
g
[
9
9
]
.
B
y
c
h
o
o
s
i
n
g
th
e
co
r
r
ec
t
m
ater
ials
an
d
r
a
tio
s
an
d
im
p
r
o
v
in
g
p
r
o
ce
d
u
r
es,
th
e
b
u
ild
in
g
in
d
u
s
tr
y
ca
n
wate
r
p
r
o
o
f
a
n
d
s
tr
en
g
th
en
co
n
cr
ete.
T
h
is
p
r
o
v
id
es
d
u
r
a
b
le
co
n
s
tr
u
ctio
n
s
.
R
FA
b
ea
ts
NF
A
d
u
e
to
f
in
e
a
g
g
r
e
g
ate'
s
p
o
o
r
wate
r
ab
s
o
r
p
tio
n
.
R
FA
'
s
wa
ter
co
n
ten
t
m
u
s
t
b
e
ev
alu
ated
b
ef
o
r
e
in
teg
r
atio
n
b
ec
au
s
e
h
ig
h
er
ab
s
o
r
p
tio
n
af
f
e
cts
co
n
cr
ete'
s
m
ec
h
an
ical
q
u
alities
.
AD,
OD,
an
d
SS
D
R
FA
m
eth
o
d
s
wer
e
test
e
d
f
o
r
R
FAc
p
er
m
ea
b
ilit
y
.
T
h
e
s
tu
d
y
f
o
u
n
d
th
at
R
FA
p
er
m
ea
b
ilit
y
r
esis
tan
ce
in
co
n
cr
ete
f
o
llo
ws
th
e
o
r
d
er
SS
D
>
AD
>
OD,
wh
ile
f
o
r
r
ec
y
cled
co
ar
s
e
ag
g
r
eg
ate,
th
e
o
r
d
er
is
r
ev
er
s
ed
(
SS
D
<
AD
<
OD)
[
1
0
0
]
.
C
o
m
p
ar
e
d
to
R
C
A,
R
FA
r
estrict
s
wat
er
m
o
r
e
b
ec
a
u
s
e
its
p
ar
ticles
ar
e
s
m
aller
an
d
its
s
p
ec
if
ic
s
u
r
f
ac
e
ar
ea
is
lar
g
er
[
1
0
1
]
.
C
o
n
c
r
ete
p
o
r
e
s
ize
is
s
ig
n
if
ican
tly
im
p
ac
ted
b
y
R
FA
in
teg
r
atio
n
,
an
d
p
er
m
ea
b
ilit
y
is
d
ec
r
ea
s
ed
b
y
r
aisi
n
g
th
e
W
/C
r
atio
an
d
R
FA r
ep
lace
m
en
t r
ate,
as sh
o
w
n
in
Fig
u
r
e
1
.
Satu
r
ated
s
u
r
f
ac
e
-
d
r
ied
R
FA,
im
p
r
o
v
e
d
m
ix
in
g
,
an
d
f
ly
ash
ad
d
itio
n
,
o
n
th
e
o
th
er
h
a
n
d
,
c
o
n
s
is
ten
tly
lo
wer
R
FAc
p
er
m
ea
b
ilit
y
.
Fly
ash
with
two
p
o
zz
o
lan
ic
m
in
er
als,
s
ilica
f
u
m
e,
an
d
m
etak
ao
lin
,
to
g
eth
e
r
,
in
cr
ea
s
es
th
e
im
p
er
m
ea
b
ilit
y
o
f
R
FAc.
T
ab
le
1
lis
ts
th
e
v
a
r
iab
les
in
f
lu
en
cin
g
R
FAc
s
ea
lin
g
.
I
n
co
n
clu
s
io
n
,
alth
o
u
g
h
in
c
r
ea
s
ed
wate
r
ab
s
o
r
p
tio
n
is
a
p
r
o
b
lem
with
R
FA,
i
ts
p
er
m
ea
b
ilit
y
an
d
d
u
r
ab
ilit
y
m
ay
b
e
s
ig
n
if
ican
tly
in
cr
ea
s
ed
b
y
co
n
tr
o
llin
g
its
m
o
is
tu
r
e
co
n
ten
t,
m
er
g
in
g
SC
M,
an
d
u
s
in
g
th
e
p
r
ec
is
e
m
ix
p
r
o
p
o
r
tio
n
s
f
o
r
R
FAc.
T
h
is
p
ap
er
p
r
esen
ts
a
u
n
iq
u
e
h
y
b
r
id
o
p
tim
izatio
n
tech
n
iq
u
e
th
at
co
m
b
in
es
th
e
d
u
n
g
b
ee
tl
e
o
p
tim
izer
(
DB
OA)
an
d
f
ir
ef
l
y
alg
o
r
ith
m
(
FLA)
to
i
m
p
r
o
v
e
th
e
h
y
p
er
p
ar
am
eter
s
o
f
a
c
o
n
v
o
lu
tio
n
al
-
r
ec
u
r
r
en
t
n
e
u
r
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
6
5
-
4
9
8
2
4968
n
etwo
r
k
in
ad
d
itio
n
to
u
s
in
g
tr
ad
itio
n
al
ap
p
r
o
ac
h
es.
T
h
r
o
u
g
h
th
eir
co
m
b
in
atio
n
,
th
e
a
p
p
r
o
ac
h
p
er
f
o
r
m
s
a
s
tr
o
n
g
g
lo
b
al
s
ea
r
ch
u
s
in
g
F
L
A
alo
n
g
s
id
e
p
r
ec
is
e
lo
ca
l
s
ea
r
ch
o
p
tim
izatio
n
d
o
n
e
b
y
DB
OA.
Ou
r
m
eth
o
d
co
m
b
in
es
co
n
ce
p
tu
al
n
o
v
elty
b
y
ap
p
l
y
in
g
b
io
lo
g
ical
co
n
ce
p
ts
to
m
ater
ial
s
cien
tific
ap
p
licatio
n
s
wh
en
p
r
ed
ictin
g
co
n
c
r
ete
co
m
p
r
ess
iv
e
s
tr
en
g
th
as
a
n
ess
en
tial
f
ac
to
r
f
o
r
s
u
s
tain
ab
le
co
n
s
tr
u
ctio
n
.
I
n
a
d
d
itio
n
,
th
is
r
esear
ch
aim
s
to
ad
d
r
ess
th
e
cr
itical
g
ap
in
s
u
s
tain
ab
le
co
n
s
tr
u
ctio
n
p
r
ac
tices
b
y
s
ig
n
if
i
ca
n
tly
r
ed
u
cin
g
th
e
C
O2
em
is
s
io
n
s
ass
o
ciate
d
with
co
n
v
e
n
tio
n
al
ce
m
e
n
t
p
r
o
d
u
ctio
n
.
T
h
e
s
tu
d
y
ex
am
i
n
es
h
o
w
c
o
n
cr
ete'
s
m
ec
h
an
ical
ch
ar
ac
ter
is
tics
ch
an
g
e
af
ter
s
u
p
p
lem
en
tal
ce
m
e
n
titi
o
u
s
m
ater
ials
(
S
C
Ms)
s
u
ch
f
ly
ash
(
FA)
an
d
g
r
o
u
n
d
g
r
an
u
lated
b
last
f
u
r
n
ac
e
s
lag
(
GGBS
)
ar
e
ad
d
ed
.
Fig
u
r
e
1
.
R
AC
is
th
e
weig
h
t p
er
ce
n
tag
e
o
f
SC
M'
s
r
esid
u
al
wate
r
in
th
e
g
ellin
g
m
ater
ial
o
v
e
r
all;
is
60
–
8
0
% o
f
th
e
p
r
o
d
u
ct
o
f
R
A's we
ig
h
t a
n
d
wate
r
ab
s
o
r
p
tio
n
;
an
d
is
th
e
r
esu
lt o
f
m
ix
e
d
wa
ter
−
−
T
ab
le
1
.
Nu
m
e
r
o
u
s
elem
en
ts
'
ef
f
ec
ts
o
n
R
FA c
o
n
cr
ete'
s
(
R
F
Ac)
im
p
er
m
ea
b
ilit
y
F
a
c
t
o
r
I
mp
a
c
t
V
a
r
i
a
t
i
o
n
R
F
A
mo
i
st
u
r
e
l
e
v
e
l
P
o
si
t
i
v
e
I
n
c
r
e
a
se
M
i
n
e
r
a
l
a
d
d
i
t
i
v
e
s
P
o
si
t
i
v
e
-
En
h
a
n
c
e
d
t
r
i
p
l
e
m
i
x
i
n
g
t
e
c
h
n
i
q
u
e
(
O
TM
)
P
o
si
t
i
v
e
-
R
F
A
p
r
o
p
o
r
t
i
o
n
N
e
g
a
t
i
v
e
I
n
c
r
e
a
se
W
a
t
e
r
-
c
e
me
n
t
r
a
t
i
o
N
e
g
a
t
i
v
e
I
n
c
r
e
a
se
R
esear
ch
r
esu
lts
s
h
o
w
th
at
o
u
r
h
y
b
r
id
alg
o
r
ith
m
o
p
ti
m
ized
n
eu
r
al
n
etwo
r
k
ac
h
ie
v
es
p
r
ec
is
e
co
m
p
r
ess
iv
e
s
tr
en
g
th
p
r
o
g
n
o
s
is
an
d
p
r
o
v
id
es
s
u
s
tain
ab
le
m
ix
tu
r
es
with
lo
wer
en
v
ir
o
n
m
en
tal
ef
f
ec
ts
.
T
h
e
m
an
u
s
cr
ip
t
estab
lis
h
es
m
u
ltip
le
n
ew
f
in
d
in
g
s
f
o
r
b
o
th
co
n
s
tr
u
ctio
n
en
g
in
ee
r
in
g
s
cien
ce
an
d
en
v
ir
o
n
m
en
tal
s
u
s
tain
ab
ilit
y
r
esear
ch
.
T
h
is
m
an
u
s
cr
ip
t
p
r
o
v
es
th
e
ef
f
ec
t
iv
en
ess
o
f
co
m
b
in
in
g
b
io
-
in
s
p
ir
ed
o
p
tim
izatio
n
m
eth
o
d
s
f
o
r
m
ater
ial
ass
ess
m
en
t
p
u
r
p
o
s
es
in
an
aty
p
ical
ap
p
licatio
n
d
o
m
ai
n
.
T
h
e
r
esear
c
h
d
em
o
n
s
tr
ates
th
at
o
p
tim
ized
.
SC
Ms h
av
e
th
e
p
o
t
en
tial to
r
ed
u
ce
g
r
ee
n
h
o
u
s
e
g
a
s
em
is
s
io
n
s
s
u
b
s
tan
tially
.
T
h
e
p
r
ed
ictiv
e
f
ea
tu
r
es
o
f
th
is
r
esear
ch
will
r
esu
lt
in
n
ew
m
o
d
elin
g
ca
p
ab
ilit
ies
f
o
r
p
lan
n
in
g
a
n
d
s
im
u
latio
n
to
o
ls
t
o
in
teg
r
ate
d
ir
ec
tly
in
to
co
n
s
tr
u
ctio
n
p
r
o
ce
s
s
es,
th
u
s
en
ab
lin
g
r
ea
l
-
tim
e,
en
v
i
r
o
n
m
en
tally
r
esp
o
n
s
ib
le
m
ater
ial
s
elec
tio
n
ch
o
ices.
W
e
will
b
eg
in
b
y
p
r
o
v
i
d
in
g
an
o
v
er
v
iew
o
f
th
e
cu
r
r
en
t
s
tate
o
f
ce
m
en
t
m
an
u
f
ac
t
u
r
i
n
g
an
d
its
en
v
ir
o
n
m
en
tal
im
p
ac
ts
,
h
ig
h
li
g
h
tin
g
t
h
e
u
s
e
o
f
SC
Ms
as
a
s
u
s
tain
ab
le
alter
n
ativ
e.
Fo
llo
win
g
th
is
,
we
will
d
elv
e
in
to
th
e
m
eth
o
d
o
lo
g
y
s
e
ctio
n
,
o
u
tlin
in
g
t
h
e
h
y
b
r
id
o
p
tim
izatio
n
tech
n
iq
u
es
an
d
n
eu
r
al
n
etwo
r
k
m
o
d
els
em
p
lo
y
ed
to
en
h
a
n
ce
t
h
e
p
r
e
d
ictiv
e
ac
cu
r
ac
y
o
f
co
n
c
r
ete
co
m
p
r
ess
iv
e
s
tr
en
g
t
h
.
Su
b
s
eq
u
en
t
s
ec
tio
n
s
will
d
is
cu
s
s
th
e
ex
p
er
im
en
tal
s
etu
p
,
r
esu
lts
,
an
d
a
d
etailed
a
n
aly
s
is
o
f
th
e
f
in
d
in
g
s
,
f
o
cu
s
in
g
o
n
th
e
p
er
f
o
r
m
an
c
e
an
d
g
en
e
r
aliza
b
ilit
y
o
f
th
e
m
o
d
el.
Fin
ally
,
we
will
co
n
clu
d
e
with
a
d
is
cu
s
s
io
n
o
n
th
e
i
m
p
licatio
n
s
o
f
o
u
r
r
esear
ch
,
f
u
tu
r
e
r
esear
ch
d
ir
e
ctio
n
s
,
an
d
th
e
p
o
ten
tial
in
te
g
r
atio
n
o
f
o
u
r
f
in
d
in
g
s
in
to
a
c
o
n
cr
ete
m
i
x
d
esig
n
an
d
q
u
ality
co
n
tr
o
l sy
s
tem
s
.
2.
P
RE
VIOU
S WO
RK
Nu
m
er
o
u
s
s
tu
d
ies
o
n
co
n
cr
e
te
tech
n
o
l
o
g
y
h
a
v
e
id
e
n
tifie
d
im
p
o
r
tan
t
f
ac
to
r
s
an
d
en
h
an
ce
d
t
h
e
p
r
ed
ictio
n
o
f
co
n
c
r
ete
s
tr
en
g
t
h
(
C
S)
th
r
o
u
g
h
th
e
u
s
e
o
f
cu
ttin
g
-
ed
g
e
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
.
Fo
r
f
ly
ash
-
b
ased
g
e
o
p
o
ly
m
er
c
o
n
cr
e
te
C
S,
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
s
,
b
ag
g
i
n
g
,
a
n
d
Ad
aBo
o
s
t
r
eg
r
ess
o
r
s
wer
e
u
s
ed
[
1
0
2
]
.
T
h
e
b
ag
g
i
n
g
m
o
d
el
m
ad
e
th
e
b
est
p
r
ed
ictio
n
s
,
w
ith
an
R
-
s
q
u
ar
ed
o
f
0
.
9
7
.
T
h
e
m
o
s
t
cr
u
cial
C
S
ch
ar
ac
ter
is
tics
wer
e
id
en
tifie
d
b
y
a
c
o
m
p
r
e
h
en
s
iv
e
s
en
s
itiv
ity
in
v
esti
g
atio
n
,
s
u
p
p
o
r
tin
g
th
e
en
v
ir
o
n
m
en
tal
s
u
s
tain
ab
ilit
y
o
f
g
eo
p
o
l
y
m
er
c
o
n
cr
ete.
Fen
g
et
a
l.
[
1
0
3
]
d
ev
elo
p
ed
an
in
tellig
en
t CS
p
r
ed
i
ctio
n
m
eth
o
d
b
ased
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
co
n
crete
s
u
s
ta
in
a
b
ilit
y:
a
n
eu
r
a
l
n
etw
o
r
ks h
yb
r
id
o
p
timiz
a
tio
n
…
(
E
s
r
a
’
a
A
lh
e
n
a
w
i
)
4969
o
n
Ad
aBo
o
s
t.
Usi
n
g
Ad
aBo
o
s
t,
th
ey
o
u
tp
e
r
f
o
r
m
ed
ar
tifi
cial
n
eu
r
al
n
etwo
r
k
(
ANN
)
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
o
n
m
o
r
e
th
a
n
1
,
0
3
0
ca
s
e
s
ets.
I
n
th
eir
ar
ticle,
th
ey
u
s
ed
s
en
s
itiv
ity
an
aly
s
is
an
d
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
to
ca
lcu
late
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
.
R
esear
ch
o
n
r
ec
y
clin
g
ag
g
r
e
g
ate
co
n
cr
ete
(
R
AC
)
[
1
0
4
]
u
s
in
g
ANN
s
y
m
b
o
lic
lear
n
in
g
an
d
GE
P.
Sen
s
itiv
ity
s
tu
d
y
r
e
v
ea
led
C
S
-
af
f
ec
tin
g
f
ac
to
r
s
,
a
n
d
GE
P
p
e
r
f
o
r
m
ed
b
etter
th
an
ANN.
Ad
d
itio
n
ally
,
th
e
s
tu
d
y
p
r
o
p
o
s
ed
th
at
b
ag
g
in
g
an
d
b
o
o
s
tin
g
m
i
g
h
t
e
n
h
an
ce
p
r
e
d
ictio
n
.
SF
R
C
b
ea
m
s
h
ea
r
r
esis
tan
ce
was
p
r
ed
icted
b
y
m
a
n
y
m
a
ch
in
e
-
lear
n
in
g
alg
o
r
ith
m
s
[
1
0
5
]
.
T
h
e
d
e
p
en
d
en
t
v
ar
iab
le
was
b
est
p
r
e
d
icted
b
y
XGBo
o
s
t
u
s
in
g
tr
ied
-
a
n
d
-
tr
u
e
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es
.
I
n
p
u
t
p
ar
am
eter
s
ar
e
an
ticip
ated
in
th
e
s
tu
d
y
.
C
h
en
et
a
l.
[
1
0
6
]
GB
R
T
p
r
ed
icted
co
n
cr
ete
-
FR
P
b
o
n
d
r
e
s
is
tan
ce
.
T
h
e
b
est
m
eth
o
d
an
d
m
o
d
el,
GB
R
T
,
p
r
ed
icted
th
e
is
s
u
e.
ANNs
a
n
d
g
en
etic
alg
o
r
ith
m
s
(
Ga
s
)
o
r
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
p
r
e
d
icted
C
E
S
b
o
n
d
s
tr
en
g
th
[
1
0
7
]
.
T
es
t
s
en
s
itiv
ity
an
aly
s
is
id
en
tifie
d
cr
u
cial
v
ar
ia
b
les.
C
S wa
s
ev
alu
ated
at
h
ig
h
tem
p
er
atu
r
es u
s
in
g
Ad
aBo
o
s
t,
R
an
d
o
m
Fo
r
ests
,
an
d
d
ec
is
io
n
tr
e
es
[
1
0
8
]
.
Hig
h
ly
ce
m
en
t
s
en
s
itiv
e
,
Ga
u
s
s
ian
p
r
o
ce
s
s
r
eg
r
ess
io
n
(
G
PR
)
with
th
e
Ma
ter
n
3
2
k
er
n
el
f
u
n
ctio
n
p
r
ed
icted
h
ig
h
-
p
er
f
o
r
m
an
ce
co
n
cr
ete'
s
C
S
b
etter
th
an
ANNs
[
1
0
9
]
.
I
n
th
e
s
en
s
itiv
ity
s
tu
d
y
,
ce
m
en
t
co
n
ce
n
tr
atio
n
a
n
d
test
in
g
ag
e
wer
e
cr
u
cial.
C
S
wa
s
p
r
ed
icted
b
y
R
an
d
o
m
Fo
r
est
u
s
in
g
f
ield
an
d
lab
d
ata
[
1
1
0
]
.
Field
-
tr
ain
ed
m
o
d
els
s
h
o
wed
im
p
r
o
v
ed
ac
cu
r
ac
y
,
in
d
icatin
g
th
at
s
ev
e
r
al
d
ata
s
o
u
r
ce
s
r
ed
u
ce
o
v
er
p
r
ed
ictio
n
.
Dec
is
io
n
tr
e
e
an
d
g
r
a
d
ien
t
b
o
o
s
tin
g
tr
e
e
m
o
d
els
wer
e
u
s
ed
to
ex
am
in
e
th
e
b
en
d
in
g
p
er
f
o
r
m
an
ce
o
f
FR
P
-
r
ein
f
o
r
ce
d
co
n
cr
ete
b
ea
m
s
[
1
1
1
]
.
B
ea
m
d
ep
th
,
f
lex
u
r
al
r
ein
f
o
r
ce
m
en
t
ar
ea
,
an
d
ass
es
s
m
en
t
m
etr
ics
s
u
p
p
o
r
ted
th
e
g
r
ad
ien
t
-
b
o
o
s
tin
g
t
r
ee
m
o
d
el.
AN
N
s
,
d
ec
is
io
n
tr
ee
s
,
B
ag
g
in
g
,
an
d
g
en
e
ex
p
r
ess
io
n
p
r
o
g
r
am
m
in
g
p
r
ed
i
cted
C
S
[
1
1
2
]
.
B
ag
g
i
n
g
was m
o
s
t a
cc
u
r
ate
at
0
.
9
5
R
-
s
q
u
ar
ed
.
T
h
e
XGBo
o
s
t
m
o
d
el
with
m
a
n
u
ally
s
elec
ted
f
ea
tu
r
es
p
e
r
f
o
r
m
ed
well
in
[
1
1
3
]
wh
en
esti
m
atin
g
C
S
b
ased
o
n
c
o
n
cr
ete
c
o
m
p
o
s
itio
n
an
d
c
u
r
e
p
e
r
io
d
.
Acc
o
r
d
in
g
to
th
e
s
tu
d
y
,
a
d
ec
r
ea
s
e
in
d
i
m
en
s
io
n
ality
h
elp
s
th
e
s
u
p
p
o
r
t
v
ec
t
o
r
r
eg
r
ess
io
n
m
o
d
el
.
Ma
ch
in
e
-
lear
n
in
g
a
p
p
r
o
ac
h
es
wer
e
u
s
ed
to
f
o
r
ec
a
s
t
s
ettin
g
tim
e
an
d
s
tr
en
g
th
d
ev
el
o
p
m
e
n
t
in
Or
d
in
ar
y
Po
r
tlan
d
c
em
e
n
t
b
in
d
er
s
[
1
1
4
]
.
T
h
e
r
esu
lts
wer
e
co
m
p
a
r
ab
le
to
ASTM
test
m
eth
o
d
s
.
Fin
ally
,
[
1
1
5
]
test
ed
ANN,
b
o
o
s
tin
g
,
an
d
A
d
aBo
o
s
t
en
s
em
b
le
m
ac
h
in
e
-
lear
n
in
g
ap
p
r
o
ac
h
es
f
o
r
g
eo
p
o
l
y
m
er
co
n
cr
ete
C
S
p
r
ed
ictio
n
u
s
in
g
h
ig
h
-
ca
lciu
m
f
ly
ash
.
Du
e
to
its
ac
cu
r
ac
y
,
th
e
b
o
o
s
tin
g
ap
p
r
o
ac
h
was
ac
k
n
o
wled
g
ed
,
an
d
th
ese
f
in
d
in
g
s
s
u
g
g
est
en
s
em
b
le
m
eth
o
d
s
f
o
r
en
h
an
cin
g
co
n
c
r
ete
f
o
r
s
u
s
tain
ab
le
d
ev
elo
p
m
e
n
t.
T
h
is
s
tu
d
y
aim
s
to
im
p
r
o
v
e
co
n
cr
ete
p
r
o
p
er
ty
f
o
r
ec
asts
.
I
m
p
r
o
v
in
g
p
r
ed
ictiv
e
m
o
d
el
s
r
eq
u
ir
es
u
n
d
er
s
tan
d
i
n
g
th
e
in
tr
icate
r
e
latio
n
s
h
ip
b
etwe
en
m
ater
ial
co
m
p
o
n
en
ts
,
am
b
ien
t
en
v
ir
o
n
m
en
ts
,
an
d
co
n
cr
ete
p
h
y
s
ical
p
r
o
p
er
ties
.
I
n
th
e
c
o
n
s
tr
u
ctio
n
in
d
u
s
tr
y
'
s
q
u
est
f
o
r
ef
f
icien
c
y
an
d
s
u
s
tain
ab
ilit
y
,
th
is
s
tu
d
y
will
en
h
an
ce
t
h
e
p
r
e
d
ictio
n
m
o
d
el'
s
ac
cu
r
ac
y
an
d
ad
a
p
tab
ilit
y
th
r
o
u
g
h
an
an
aly
s
is
o
f
e
n
v
ir
o
n
m
en
tal
im
p
ac
ts
an
d
m
ec
h
an
ical
b
eh
a
v
io
r
s
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
DO
L
O
G
Y
T
h
is
s
tu
d
y
u
s
es
ex
ten
s
iv
e
an
aly
s
is
,
d
ata
m
an
ag
em
en
t
an
d
m
an
ip
u
latio
n
m
eth
o
d
s
,
ad
v
a
n
ce
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
ar
ch
itectu
r
e,
an
d
h
y
b
r
i
d
o
p
tim
izatio
n
al
g
o
r
ith
m
s
.
Fo
r
o
p
tim
al
d
ataset
u
s
e
an
d
h
ig
h
-
q
u
ality
f
in
d
in
g
s
,
t
h
e
d
ataset
was
clea
n
ed
an
d
p
r
ep
r
o
ce
s
s
ed
u
s
in
g
c
o
n
cr
ete
p
r
o
p
e
r
ties
.
Data
was
n
o
r
m
alize
d
to
r
ed
u
ce
s
k
ewn
ess
in
f
ea
tu
r
e
s
ca
les.
T
h
e
n
eu
r
al
n
etwo
r
k
ar
c
h
itectu
r
e
s
er
v
ed
as
th
e
f
o
u
n
d
atio
n
f
o
r
th
e
b
u
ilt
p
r
ed
ictiv
e
m
o
d
el,
wh
ich
in
clu
d
ed
c
o
n
v
o
lu
tio
n
al
a
n
d
r
ec
u
r
r
en
t
la
y
er
s
to
ex
t
r
ac
t
th
e
tem
p
o
r
al
r
elatio
n
s
h
ip
s
o
f
th
e
d
ata
in
o
r
d
er
to
g
u
ar
an
tee
a
n
ac
cu
r
ate
f
o
r
ec
ast
o
f
co
n
cr
ete
s
tr
en
g
th
.
B
ec
au
s
e
it
p
r
o
v
id
e
d
a
s
o
lid
b
asis
f
o
r
f
u
r
th
er
en
h
an
ce
m
e
n
ts
,
th
is
m
o
d
el
ar
r
a
n
g
em
en
t w
as in
itially
ap
p
r
o
p
r
i
ate
f
o
r
test
in
g
p
e
r
f
o
r
m
an
ce
.
T
h
e
s
tu
d
y
ad
v
is
es
cr
ea
tin
g
FLA
an
d
d
u
n
g
b
e
etle
o
p
tim
izer
s
.
T
h
is
p
r
o
ce
d
u
r
e
im
p
r
o
v
ed
m
o
d
el
h
y
p
er
p
ar
am
eter
v
al
u
es
m
o
r
e
th
an
n
o
r
m
al.
FLA
ef
f
ec
tiv
e
ly
ex
p
lo
r
es
p
ar
am
ete
r
s
p
ac
e
v
ia
g
lo
b
al
s
ea
r
ch
o
p
tim
izatio
n
;
DB
OA
f
o
u
n
d
s
th
e
lo
ca
l
o
p
tim
u
m
.
A
lar
g
e
s
o
lu
tio
n
s
p
ac
e
an
d
r
eliab
le
m
o
d
el
p
r
ed
ictio
n
a
r
e
g
u
ar
an
teed
b
y
co
m
p
r
eh
en
s
iv
e
s
ea
r
ch
ap
p
r
o
ac
h
es.
Fig
u
r
e
2
s
h
o
ws
th
e
im
p
o
r
tan
t
m
eth
o
d
o
lo
g
y
'
s
ap
p
licatio
n
an
d
lin
k
ag
es.
Fin
ally
,
t
h
e
FLA+
DB
OA
m
o
d
el's
alg
o
r
ith
m
f
lo
w
an
d
p
r
ed
ictiv
e
m
o
d
el
in
teg
r
atio
n
ar
e
d
is
p
lay
ed
in
th
e
f
o
llo
win
g
Fig
u
r
e
2
.
I
n
o
u
r
m
eth
o
d
o
lo
g
y
,
we
co
n
d
u
cted
a
co
m
p
r
eh
e
n
s
iv
e
d
ata
s
et
p
r
ep
r
o
ce
s
s
in
g
to
en
s
u
r
e
t
h
e
in
teg
r
ity
an
d
co
n
s
is
ten
cy
o
f
o
u
r
m
o
d
el.
T
h
e
im
p
lem
e
n
tatio
n
o
f
n
o
r
m
aliza
tio
n
s
tan
d
ar
d
ized
n
u
m
er
i
ca
l
v
alu
es
to
m
atch
r
an
g
es
wh
ile
m
ain
tain
in
g
s
tab
ilit
y
an
d
co
n
v
er
g
e
n
ce
,
th
r
o
u
g
h
wh
ich
th
e
I
QR
m
eth
o
d
d
etec
ted
o
u
tlier
s
to
r
em
o
v
e
an
o
m
alo
u
s
d
ata
th
at
a
f
f
ec
ted
th
e
an
al
y
s
is
.
T
h
e
Mi
n
-
Ma
x
s
ca
ler
m
et
h
o
d
was
im
p
le
m
en
ted
f
o
r
f
ea
tu
r
e
s
ca
lin
g
in
o
r
d
e
r
to
eq
u
alize
th
e
ef
f
ec
ts
o
f
ea
ch
in
p
u
t
f
ea
tu
r
e
u
p
o
n
m
o
d
el
p
r
ed
ictio
n
s
.
Sh
ap
ley
a
d
d
itiv
e
e
x
p
lan
atio
n
s
(
SHAP
)
ass
es
s
ed
th
e
in
f
l
u
en
ce
o
f
d
if
f
er
en
t
v
ar
iab
les
o
n
co
n
cr
ete
co
m
p
r
ess
iv
e
s
tr
en
g
th
p
r
ed
icti
o
n
s
b
y
ass
ig
n
in
g
v
alu
e
weig
h
ts
to
ea
ch
co
n
tr
i
b
u
tin
g
f
ea
tu
r
e
in
th
e
p
r
ed
ictio
n
.
T
h
e
p
r
e
d
ictiv
e
m
o
d
el
g
ain
ed
b
o
th
e
n
h
an
ce
d
in
ter
p
r
etab
ilit
y
an
d
tr
a
n
s
p
ar
en
cy
wh
en
u
s
in
g
SHAP,
wh
ich
r
ev
ea
led
v
ital f
ea
tu
r
es to
g
eth
e
r
with
clea
r
er
ex
p
lan
atio
n
s
to
i
n
cr
ea
s
e
th
e
r
eliab
ilit
y
o
f
p
r
e
d
ictio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
6
5
-
4
9
8
2
4970
Fig
u
r
e
2
.
Pro
p
o
s
ed
s
ch
em
e
T
h
e
m
o
d
el
p
er
f
o
r
m
e
d
its
tr
ain
in
g
o
n
h
ar
d
war
e
o
p
tim
ized
f
o
r
GPU
co
m
p
u
tin
g
to
d
ec
r
ea
s
e
p
r
o
ce
s
s
in
g
tim
e
wh
ile
attem
p
tin
g
to
s
ca
le
th
e
s
y
s
tem
.
T
h
e
d
esig
n
e
n
ab
les
o
u
r
s
y
s
tem
to
p
r
o
ce
s
s
ex
ten
d
ed
d
atasets
ef
f
ec
tiv
ely
th
u
s
en
a
b
lin
g
p
r
a
ctica
l
ap
p
licatio
n
s
th
at
n
ee
d
im
m
ed
iate,
p
r
ec
is
e
o
u
tc
o
m
es.
T
h
e
im
p
lem
en
te
d
m
o
d
el
r
elies
o
n
s
tate
-
of
-
th
e
-
ar
t
co
m
p
u
ter
to
o
ls
an
d
m
eth
o
d
s
to
g
u
ar
an
tee
co
m
p
u
tatio
n
al
p
r
o
d
u
ctiv
ity
.
A
co
n
v
o
lu
tio
n
al
-
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
er
v
es
as
o
u
r
m
ain
co
m
p
u
tatio
n
al
elem
e
n
t
to
p
r
o
ce
s
s
s
eq
u
en
tial
an
d
s
p
atial
co
n
cr
ete
m
ix
d
ata
ef
f
icien
tly
.
T
h
e
m
o
d
el
r
u
n
s
o
n
a
co
m
p
u
tin
g
p
latf
o
r
m
with
p
o
wer
f
u
l
GPUs
f
o
r
its
d
ep
lo
y
m
e
n
t.
T
h
e
s
p
ec
if
ic
co
n
f
ig
u
r
atio
n
s
er
v
es
as
a
n
ess
en
tial
r
eq
u
i
r
em
en
t
to
m
ak
e
d
e
ep
lear
n
i
n
g
m
o
d
els
p
er
f
o
r
m
q
u
ick
ly
d
u
r
in
g
tr
ain
i
n
g
an
d
in
f
er
e
n
ce
,
th
u
s
en
ab
li
n
g
f
ast
p
r
o
ce
s
s
in
g
o
f
b
ig
d
at
asets
an
d
in
tr
icate
o
p
er
atio
n
s
.
Usi
n
g
GPUs
in
th
e
s
y
s
tem
en
h
an
ce
s
b
o
th
p
r
o
ce
s
s
in
g
s
p
ee
d
an
d
m
o
d
el
s
ca
lab
ilit
y
th
u
s
allo
win
g
th
e
an
aly
s
is
o
f
lar
g
e
d
atasets
at
h
ig
h
p
er
f
o
r
m
an
ce
r
ates.
T
h
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
u
tili
ze
s
T
en
s
o
r
Flo
w
an
d
Ker
as
f
r
am
ewo
r
k
s
as
o
p
tim
i
ze
d
d
ee
p
lear
n
in
g
ap
p
licatio
n
s
s
p
ec
if
ically
d
esig
n
e
d
f
o
r
th
is
p
u
r
p
o
s
e.
T
h
e
f
r
am
ewo
r
k
s
o
f
f
er
ef
f
icien
t
n
eu
r
al
n
etwo
r
k
im
p
lem
e
n
tatio
n
,
wh
ich
in
clu
d
es
au
to
m
atic
d
if
f
er
en
tiatio
n
an
d
GPU
ac
ce
ler
atio
n
ca
p
ab
ilit
ies
b
u
ilt r
ig
h
t in
to
th
eir
s
y
s
tem
.
T
h
e
p
r
o
v
id
ed
s
u
p
p
o
r
t m
ax
im
ize
s
r
eso
u
r
ce
u
s
ag
e
in
o
r
d
er
to
e
n
h
an
ce
m
o
d
el
s
p
ee
d
an
d
ac
cu
r
ac
y
d
u
r
in
g
c
o
m
p
u
t
atio
n
s
.
T
h
e
co
m
p
u
tatio
n
p
r
o
c
ess
ad
o
p
ts
s
tan
d
ar
d
s
o
f
twar
e
en
g
in
ee
r
in
g
p
r
in
cip
l
es
th
at
in
clu
d
e
lo
g
ical
m
o
d
u
lar
izatio
n
o
f
co
d
e
with
o
p
tim
i
ze
d
d
ata
ar
r
ay
s
an
d
p
ar
allel
alg
o
r
ith
m
ex
ec
u
tio
n
ap
p
r
o
ac
h
es.
Mo
d
el
m
ain
ten
an
c
e
b
ec
o
m
es
s
im
p
ler
th
r
o
u
g
h
th
ese
p
r
ac
tices,
wh
ile
ca
lcu
latio
n
s
r
u
n
f
aster
,
a
n
d
th
e
s
y
s
tem
b
ec
o
m
es r
ea
d
y
f
o
r
g
r
o
wth
r
eq
u
ir
em
e
n
ts
.
T
h
e
p
r
e
d
ictiv
e
ac
cu
r
ac
y
o
f
o
u
r
m
o
d
el
was
v
alid
ated
th
r
o
u
g
h
s
tatis
tical
test
s
th
at
in
clu
d
ed
t
-
test
s
an
d
ANOV
A
f
o
r
co
m
p
ar
in
g
d
if
f
e
r
en
t
co
n
f
ig
u
r
atio
n
r
esu
lts
.
T
h
e
m
o
d
el
p
er
f
o
r
m
an
ce
was
ev
alu
ated
th
r
o
u
g
h
an
an
aly
s
is
th
at
d
eter
m
in
ed
th
e
ef
f
ec
ts
o
f
s
h
if
tin
g
GGBS
o
r
f
ly
ash
p
er
ce
n
ta
g
es.
Ou
r
m
o
d
el
r
eq
u
ir
ed
th
is
ev
alu
atio
n
to
d
em
o
n
s
tr
ate
its
p
er
f
o
r
m
an
ce
ac
r
o
s
s
v
ar
io
u
s
c
o
n
cr
ete
m
ix
e
d
co
n
d
itio
n
s
as
we
aim
ed
to
g
en
e
r
ate
r
o
b
u
s
t f
in
d
in
g
s
ap
p
lica
b
le
to
d
if
f
er
en
t p
r
o
d
u
ctio
n
s
ce
n
ar
io
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
co
n
crete
s
u
s
ta
in
a
b
ilit
y:
a
n
eu
r
a
l
n
etw
o
r
ks h
yb
r
id
o
p
timiz
a
tio
n
…
(
E
s
r
a
’
a
A
lh
e
n
a
w
i
)
4971
T
h
e
d
e
p
ictio
n
in
Fig
u
r
e
2
s
h
o
ws
h
o
w
th
e
FLA
a
n
d
DB
OA
co
m
b
in
e
in
a
h
y
b
r
id
o
p
tim
izatio
n
s
tr
u
ctu
r
e
with
o
u
t
in
ter
r
u
p
tio
n
s
.
T
h
e
d
iag
r
am
s
h
o
ws
h
o
w
t
h
e
iter
ativ
e
s
tep
s
o
f
th
e
d
u
al
alg
o
r
ith
m
f
u
n
ctio
n
th
r
o
u
g
h
p
ar
am
eter
estab
lis
h
m
en
t
an
d
p
o
p
u
latio
n
in
itial
cr
ea
tio
n
.
T
h
e
s
y
s
tem
co
m
p
u
tes
f
itn
ess
v
alu
es
to
g
u
id
e
th
e
s
ea
r
ch
d
ir
ec
tio
n
to
war
d
s
o
p
tim
al
s
o
lu
tio
n
s
af
ter
th
is
p
r
o
c
ed
u
r
e.
T
h
e
DB
OA
s
ec
tio
n
allo
ws
th
e
m
o
d
el
to
wo
r
k
with
o
u
t
o
b
s
tacle
s
b
y
r
ea
d
ju
s
tin
g
i
n
d
iv
id
u
a
l
p
o
s
itio
n
s
th
r
o
u
g
h
an
eq
u
atio
n
d
esig
n
e
d
f
o
r
im
p
r
o
v
e
d
alg
o
r
ith
m
ex
p
lo
r
atio
n
.
B
y
d
etec
tin
g
lo
ca
l
m
in
i
m
u
m
o
b
s
tacle
s
,
th
e
tr
ajec
to
r
y
m
ak
es
in
ten
d
e
d
m
o
d
if
icatio
n
s
th
at
allo
w
s
m
o
o
th
n
av
ig
atio
n
to
war
d
s
o
p
tim
al
s
o
lu
tio
n
s
.
T
h
e
alg
o
r
ith
m
c
o
n
d
u
cts
a
r
e
n
ewa
l
p
r
o
ce
d
u
r
e
wh
en
ev
e
r
it
d
is
co
v
er
s
an
o
p
tim
al
s
o
lu
tio
n
,
wh
ich
allo
ws
it
to
p
er
f
o
r
m
m
o
r
e
p
r
ec
is
e
ch
ec
k
s
r
eg
ar
d
in
g
b
o
u
n
d
a
r
y
o
v
er
s
tep
f
r
o
m
p
r
io
r
r
u
n
s
.
T
h
e
FLA
b
eg
i
n
s
its
h
y
b
r
i
d
s
y
s
tem
o
p
er
atio
n
s
b
y
estab
lis
h
in
g
ad
ju
s
tab
le
p
ar
am
eter
s
th
at
d
er
iv
e
f
r
o
m
DB
OA
o
u
tp
u
ts
.
A
d
y
n
am
ic
f
ee
d
b
ac
k
m
ec
h
a
n
is
m
cr
ea
ted
b
etwe
en
th
e
alg
o
r
ith
m
s
im
p
r
o
v
e
s
b
o
th
ad
ap
tab
ilit
y
an
d
r
o
b
u
s
tn
ess
d
u
r
in
g
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
.
FLA
s
e
p
ar
ates
its
p
o
p
u
latio
n
ac
r
o
s
s
two
g
r
o
u
p
s
,
wh
ic
h
co
n
d
u
ct
p
o
s
itio
n
u
p
d
ates
b
ased
o
n
f
itn
ess
ev
alu
atio
n
s
th
at
ar
e
r
ec
alcu
lated
af
ter
ev
er
y
p
o
s
itio
n
al
r
ea
d
ju
s
tm
en
t.
T
h
e
alg
o
r
ith
m
d
iv
id
es
its
ex
ec
u
tio
n
in
to
m
u
lti
p
le
p
h
ases
,
wh
ich
ac
tiv
ate
wh
en
iter
atio
n
co
u
n
ts
r
ea
ch
th
eir
d
ef
in
ed
t
h
r
esh
o
ld
s
in
o
r
d
e
r
to
ac
h
ie
v
e
ef
f
icien
t e
x
p
lo
r
atio
n
a
n
d
ex
p
lo
itatio
n
o
f
t
h
e
s
ea
r
ch
s
p
ac
e.
B
o
th
alg
o
r
ith
m
s
u
p
d
ate
th
ei
r
s
tr
ateg
ies
with
ea
ch
iter
atio
n
u
s
in
g
ch
an
g
es
in
s
ea
r
ch
s
p
ac
e
co
n
d
itio
n
s
to
r
ea
ch
th
eir
f
in
al
i
d
en
tific
atio
n
o
f
th
e
g
lo
b
al
b
est p
o
s
itio
n
an
d
f
itn
ess
.
T
h
is
in
ter
ac
tiv
e
al
g
o
r
ith
m
m
ec
h
an
is
m
b
o
th
en
h
an
ce
s
in
d
iv
id
u
al
alg
o
r
ith
m
ef
f
ec
tiv
en
ess
wh
ile
u
tili
zin
g
th
eir
co
llectiv
e
p
o
wer
to
p
r
o
d
u
ce
a
n
o
p
tim
ized
s
o
lu
tio
n
,
wh
ich
r
ep
r
esen
ts
ef
f
icien
t
m
an
ag
em
en
t
o
f
ex
p
lo
r
atio
n
an
d
e
x
p
lo
itatio
n
r
eso
u
r
ce
s
n
ee
d
ed
f
o
r
s
o
p
h
is
ticated
o
p
tim
izatio
n
p
r
o
b
lem
s
.
Ou
r
m
o
d
el
ev
al
u
atio
n
i
n
clu
d
e
s
ex
am
in
atio
n
o
f
p
h
y
s
ics
-
in
f
o
r
m
ed
m
ac
h
in
e
lear
n
in
g
(
PIM
L
)
b
ec
au
s
e
we
s
ee
k
to
elev
ate
b
o
th
in
ter
p
r
etab
ilit
y
an
d
r
eliab
ilit
y
o
f
o
u
r
p
r
ed
ictiv
e
m
eth
o
d
s
.
PIM
L
s
tr
en
g
th
en
s
m
o
d
el
o
u
tco
m
es
b
y
im
p
lem
en
tin
g
d
o
m
ain
k
n
o
wled
g
e
in
t
o
tr
ain
i
n
g
b
ec
au
s
e
it
e
n
ab
les
u
s
er
s
to
u
n
d
er
s
tan
d
h
o
w
co
n
cr
ete
m
ix
d
esig
n
p
r
in
cip
l
es
af
f
ec
t
p
r
ed
ictio
n
s
,
wh
ich
l
ea
d
s
to
m
o
r
e
ac
cu
r
ate,
tr
u
s
two
r
th
y
r
esu
lts
.
T
h
is
m
eth
o
d
p
r
o
v
es
u
s
ef
u
l
in
m
a
ter
ial
s
cien
ce
b
ec
au
s
e
its
an
aly
s
is
h
an
d
les
co
m
p
lex
p
h
y
s
ical
an
d
ch
em
ical
in
ter
ac
tio
n
s
th
at
ex
h
ib
it st
r
o
n
g
n
o
n
lin
ea
r
ity
.
3
.
1
.
Da
t
a
s
et
o
v
er
v
iew
T
h
e
m
ain
d
ataset
u
s
ed
f
o
r
th
i
s
s
tu
d
y
ex
a
m
in
es
co
n
c
r
ete
m
i
x
tu
r
es
as
a
w
h
o
le
s
y
s
tem
to
u
n
d
er
s
tan
d
h
o
w
co
m
p
o
n
en
ts
wo
r
k
to
g
eth
er
d
u
r
in
g
co
m
p
r
ess
io
n
test
s
.
T
h
e
1
,
0
3
0
s
am
p
les
h
a
v
e
eig
h
t
ch
ar
ac
ter
is
tics
an
d
o
n
e
tar
g
et
v
ar
iab
le
.
T
h
e
ty
p
e
(
1
0
class
es)
an
d
ag
e
ar
e
also
lis
ted
.
W
ith
an
av
er
ag
e
v
o
lu
m
e
p
er
m
ix
o
f
2
8
1
.
1
7
k
g
,
ce
m
en
t,
th
e
p
r
im
a
r
y
b
in
d
e
r
in
co
n
cr
ete,
is
cr
u
ci
al
to
th
e
s
tr
u
ctu
r
al
b
eh
av
i
o
r
a
n
d
lo
n
g
e
v
ity
o
f
t
h
e
m
aso
n
r
y
in
d
u
s
tr
y
.
Su
p
p
lem
en
tar
y
tab
le
ce
m
e
n
titi
o
u
s
m
ater
ials
av
er
ag
e
7
3
.
9
0
k
g
b
last
f
u
r
n
ac
e
s
lag
a
n
d
5
4
.
1
9
k
g
f
ly
a
s
h
.
R
ea
d
I
n
tr
o
.
T
h
ese
im
p
r
o
v
e
d
u
r
ab
ilit
y
an
d
wo
r
k
ab
ilit
y
,
b
u
t
th
eir
p
r
o
p
o
r
tio
n
s
v
ar
y
,
p
r
o
v
id
in
g
a
v
ar
iety
o
f
ex
p
er
im
en
tal
m
i
x
es.
W
ater
,
wh
ich
is
n
ee
d
ed
f
o
r
c
o
n
cr
ete
wo
r
k
ab
ilit
y
a
n
d
s
tr
en
g
t
h
,
we
ig
h
s
1
8
1
.
5
7
k
g
p
er
m
ix
,
wh
er
ea
s
s
u
p
er
p
last
icize
r
s
,
wh
ich
in
cr
ea
s
e
co
n
c
r
e
te
f
lu
id
ity
with
o
u
t
r
e
d
u
cin
g
s
tr
en
g
th
,
weig
h
6
.
2
0
k
ilo
g
r
am
p
er
m
ix
.
T
h
e
b
u
lk
o
f
th
e
m
ix
is
c
o
m
p
o
s
ed
o
f
b
o
th
co
ar
s
e
a
n
d
f
in
e
ag
g
r
eg
ates,
weig
h
i
n
g
9
7
2
.
9
2
k
g
an
d
7
7
3
.
5
8
k
g
,
r
e
s
p
ec
tiv
ely
.
T
h
ese
f
ac
to
r
s
af
f
ec
t
co
n
cr
ete
tex
tu
r
e
,
d
en
s
ity
,
an
d
s
tr
en
g
th
.
T
h
e
av
er
ag
e
ag
e
o
f
c
o
n
cr
ete
s
am
p
les
was
4
5
.
6
6
d
a
y
s
,
r
ep
r
ese
n
tin
g
a
cu
r
e
p
er
io
d
,
a
k
e
y
p
a
r
am
eter
f
o
r
s
tr
en
g
th
g
r
o
wth
la
y
er
s
.
C
o
n
c
r
ete
u
n
d
er
g
o
es
ch
e
m
ical
p
r
o
ce
s
s
es
th
at
r
elea
s
e
lo
ad
-
b
ea
r
in
g
p
r
o
p
e
r
ties
.
T
h
e
a
v
er
ag
e
co
m
p
r
ess
iv
e
s
tr
en
g
th
,
o
r
lo
a
d
-
ca
r
r
y
i
n
g
ab
ilit
y
,
o
f
co
n
c
r
e
te
is
3
5
.
8
2
MPa
in
th
i
s
d
a
taset.
Oth
er
h
ig
h
-
d
im
en
s
io
n
al
m
eta
-
f
ea
tu
r
es
p
o
s
s
es
s
th
is
s
ca
le,
in
d
icatin
g
a
p
titu
d
e
f
o
r
tr
ain
in
g
p
r
ed
ictiv
e
m
o
d
els
th
at
ca
n
h
an
d
le
m
an
y
co
n
s
tr
u
ctio
n
s
p
ec
if
icatio
n
s
an
d
s
itu
atio
n
s
.
I
n
c
o
n
clu
s
io
n
,
th
e
d
ataset
h
elp
s
es
tim
ate
q
u
en
ch
-
f
lo
w
co
m
p
o
s
ite
co
m
p
r
ess
iv
e
s
tr
en
g
th
b
y
m
ea
s
u
r
in
g
in
g
r
e
d
ien
ts
an
d
wea
th
er
co
n
d
itio
n
s
an
d
m
o
n
ito
r
in
g
d
if
f
icu
l
t
co
n
cr
ete
m
ix
i
n
ter
ac
tio
n
s
.
T
h
is
lar
g
e
d
ata
co
llectio
n
en
a
b
les
d
ee
p
er
ex
am
in
ati
o
n
o
f
em
p
ir
ical
r
elatio
n
s
h
ip
s
th
at
af
f
ec
t c
o
n
c
r
ete
p
er
f
o
r
m
a
n
ce
an
d
cu
s
to
m
ized
m
ix
d
esig
n
s
f
o
r
d
iv
er
s
e
c
o
n
s
tr
u
ctio
n
a
p
p
l
icatio
n
s
.
I
n
ad
d
itio
n
,
we
h
a
v
e
i
n
clu
d
ed
a
co
m
p
r
eh
e
n
s
iv
e
co
m
p
ar
ativ
e
T
ab
le
2
th
at
d
etails
v
ar
io
u
s
o
p
tim
izatio
n
m
eth
o
d
s
alo
n
g
s
i
d
e
th
e
FLA
an
d
DB
OA.
E
ac
h
o
p
tim
izatio
n
tech
n
i
q
u
e'
s
ac
cu
r
ac
y
,
t
o
g
eth
er
with
its
co
m
p
u
tatio
n
al
tim
in
g
a
n
d
b
en
ef
its
an
d
d
r
awb
ac
k
s
,
a
p
p
e
ar
s
in
th
is
tab
le,
wh
ich
in
clu
d
es
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
an
d
g
e
n
et
ic
alg
o
r
ith
m
,
an
d
B
ay
esian
o
p
tim
izatio
n
.
An
o
r
g
an
ized
an
al
y
s
is
en
ab
les
b
etter
co
m
p
r
eh
e
n
s
io
n
r
e
g
ar
d
in
g
wh
y
FLA
an
d
DB
OA
wer
e
s
elec
ted
f
o
r
t
h
is
r
esear
ch
b
ec
au
s
e
o
f
th
eir
p
ar
ticu
lar
ad
v
an
tag
es in
r
eso
lv
in
g
c
o
m
p
l
ex
m
u
lti
-
d
im
en
s
io
n
al
o
p
tim
iza
tio
n
is
s
u
es in
co
n
cr
ete
m
ix
tu
r
e
d
esig
n
.
Ou
r
an
aly
s
is
o
f
th
e
d
ataset
c
o
m
p
o
s
itio
n
h
as
b
ee
n
ca
r
r
ied
o
u
t
to
co
n
f
ir
m
th
e
i
n
clu
s
io
n
o
f
d
i
v
er
s
e
ce
m
en
t
ty
p
es
ac
r
o
s
s
d
if
f
er
e
n
t
g
eo
g
r
a
p
h
ic
r
eg
i
o
n
s
,
wh
ich
r
ed
u
ce
s
b
iases
r
elate
d
to
m
ater
ials
an
d
r
eg
io
n
s
.
T
h
is
an
aly
s
is
co
n
f
ir
m
s
o
u
r
m
o
d
el'
s
ab
ilit
y
to
ap
p
ly
to
v
a
r
io
u
s
ce
m
en
t
m
ater
ials
th
r
o
u
g
h
d
if
f
er
en
t
test
in
g
s
y
s
tem
s
f
o
r
s
u
s
tain
ab
le
g
lo
b
al
co
n
s
tr
u
c
tio
n
d
ep
lo
y
m
en
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
6
5
-
4
9
8
2
4972
T
ab
le
2
.
An
o
v
er
v
iew
o
f
th
e
c
o
n
cr
ete
d
ataset'
s
s
tat
is
tic
s
F
e
a
t
u
r
e
C
o
u
n
t
M
e
a
n
S
t
d
D
e
v
M
i
n
2
5
%
5
0
%
75%
M
a
x
Ce
m
en
t
1
0
3
0
2
8
1
.
1
7
1
0
4
.
5
1
1
0
2
.
0
0
1
9
2
.
3
8
2
7
2
.
9
0
3
5
0
.
0
0
5
4
0
.
0
0
Bl
as
t
fu
rn
ac
e
sl
a
g
1
0
3
0
7
3
.
9
0
8
6
.
2
8
0
.
0
0
0
.
0
0
2
2
.
0
0
1
4
2
.
9
5
3
5
9
.
4
0
F
l
y
a
sh
1
0
3
0
5
4
.
1
9
6
4
.
0
0
0
.
0
0
0
.
0
0
0
.
0
0
1
1
8
.
3
0
2
0
0
.
1
0
W
at
er
1
0
3
0
1
8
1
.
5
7
2
1
.
3
5
1
2
1
.
8
0
1
6
4
.
9
0
1
8
5
.
0
0
1
9
2
.
0
0
2
4
7
.
0
0
S
u
p
erp
l
ast
i
ci
ze
r
1
0
3
0
6
.
2
0
5
.
9
7
0
.
0
0
0
.
0
0
6
.
4
0
1
0
.
2
0
3
2
.
2
0
C
o
arse
a
g
g
reg
at
e
1
0
3
0
9
7
2
.
9
2
7
7
.
7
5
8
0
1
.
0
0
9
3
2
.
0
0
9
6
8
.
0
0
1
0
2
9
.
4
0
1
1
4
5
.
0
0
F
i
n
e
a
g
g
reg
at
e
1
0
3
0
7
7
3
.
5
8
8
0
.
1
8
5
9
4
.
0
0
7
3
0
.
9
5
7
7
9
.
5
0
8
2
4
.
0
0
9
9
2
.
6
0
A
g
e
1
0
3
0
4
5
.
6
6
6
3
.
1
7
1
.
0
0
7
.
0
0
2
8
.
0
0
5
6
.
0
0
3
6
5
.
0
0
S
t
r
e
n
g
t
h
(
M
P
a
)
1
0
3
0
3
5
.
8
2
1
6
.
7
1
2
.
3
3
2
3
.
7
1
3
4
.
4
5
4
6
.
1
4
8
2
.
6
0
3
.
2
.
P
re
pro
ce
s
s
ing
a
nd
ex
plo
ra
t
o
r
y
da
t
a
a
na
ly
s
is
I
n
th
e
in
itial
s
tag
e
o
f
em
p
i
r
ical
r
esear
ch
,
th
e
co
n
c
r
ete
d
ataset
an
d
ac
cu
r
ate
p
r
o
ce
s
s
in
g
wer
e
p
r
io
r
itized
.
T
h
e
d
ataset
was
ad
ju
s
ted
to
s
ca
le
all
in
p
u
t
f
ea
tu
r
es
to
s
im
ilar
r
an
g
es
to
g
en
er
a
lize
th
em
an
d
m
ak
e
n
eu
r
al
n
etwo
r
k
lear
n
in
g
ea
s
ier
.
Stan
d
ar
d
izin
g
v
a
r
iab
les
p
r
ev
en
ts
th
e
m
o
d
el
f
r
o
m
p
r
i
o
r
itizin
g
f
ea
tu
r
es
with
g
r
ea
ter
n
u
m
b
er
s
,
b
alan
cin
g
f
e
atu
r
e
r
elev
an
ce
.
Fig
u
r
e
3
p
r
esen
ts
a
co
m
p
r
e
h
e
n
s
iv
e
an
aly
s
is
o
f
th
e
d
is
tr
ib
u
tio
n
o
f
v
a
r
io
u
s
co
n
c
r
ete
m
ix
co
m
p
o
n
e
n
ts
th
r
o
u
g
h
h
is
to
g
r
am
s
,
ea
c
h
d
etailin
g
th
e
f
r
eq
u
en
cy
an
d
r
an
g
e
o
f
o
n
e
p
a
r
ticu
lar
i
n
g
r
ed
ie
n
t.
T
h
e
v
is
u
aliza
tio
n
b
eg
in
s
with
ce
m
en
t,
d
is
p
lay
in
g
a
r
ig
h
t
-
s
k
ewe
d
d
is
tr
ib
u
tio
n
th
at
r
ef
lects
a
co
n
ce
n
tr
atio
n
o
f
v
alu
es
at
lo
wer
am
o
u
n
ts
with
a
g
r
a
d
u
al
d
ec
l
in
e
as
th
e
q
u
an
tity
i
n
cr
ea
s
es.
T
h
is
p
atter
n
s
u
g
g
ests
th
at
s
m
aller
am
o
u
n
ts
o
f
ce
m
en
t a
r
e
m
o
r
e
co
m
m
o
n
ly
u
s
ed
in
th
e
m
ix
tu
r
es with
in
th
e
d
ataset.
Mo
v
in
g
t
o
th
e
b
last
f
u
r
n
ac
e
s
lag
an
d
f
ly
ash
h
is
to
g
r
am
s
,
b
o
t
h
s
h
o
w
a
s
ig
n
i
f
ican
t
n
u
m
b
er
o
f
s
am
p
les
co
n
tain
in
g
m
in
im
al
to
n
o
am
o
u
n
ts
,
h
ig
h
lig
h
ted
b
y
th
e
s
h
ar
p
p
ea
k
s
at
th
e
lo
wer
en
d
o
f
th
e
s
ca
le.
T
h
ese
s
u
p
p
lem
en
tar
y
m
ate
r
ials
ar
e
ap
p
lied
o
n
a
n
o
p
tio
n
al
b
asis
o
r
in
m
in
im
al
q
u
a
n
titi
es
ac
r
o
s
s
m
an
y
co
n
cr
ete
f
o
r
m
u
latio
n
s
f
o
u
n
d
in
t
h
e
d
ata
s
et.
T
h
e
d
is
tr
ib
u
tio
n
s
h
ap
es
o
f
wa
ter
,
alo
n
g
with
s
u
p
er
p
last
icize
r
an
d
b
o
th
co
ar
s
e
an
d
f
in
e
a
g
g
r
eg
ates,
d
em
o
n
s
tr
ate
ty
p
ical
u
s
ag
e
p
atter
n
s
an
d
v
alu
e
r
an
g
es
with
in
co
n
cr
ete
m
ix
tu
r
es.
T
h
e
wate
r
d
is
tr
ib
u
tio
n
in
d
icate
s
th
at
m
o
s
t
co
n
cr
ete
m
ix
es
u
s
e
am
o
u
n
ts
th
at
f
all
n
ea
r
th
eir
m
ed
ian
v
alu
es.
Su
p
er
p
last
icize
r
s
ar
e
co
n
ce
n
tr
ated
b
elo
w
th
e
m
ed
ia
n
am
o
u
n
t
,
wh
ich
s
h
o
ws
m
an
y
m
ix
tu
r
es
o
n
ly
u
s
e
m
in
im
al
a
m
o
u
n
ts
b
ec
au
s
e
th
is
s
u
b
s
tan
ce
f
u
n
ctio
n
s
as a
n
a
d
v
a
n
ce
d
ad
d
itiv
e
r
ath
er
t
h
an
a
r
eg
u
lar
m
ix
tu
r
e
co
m
p
o
n
en
t.
B
ec
au
s
e
o
f
th
eir
ess
en
tial
r
o
l
e
in
th
e
co
m
p
o
s
itio
n
o
f
c
o
n
cr
ete
m
ix
tu
r
es,
co
a
r
s
e
an
d
f
in
e
ag
g
r
eg
ates
ap
p
ea
r
to
h
av
e
a
wid
e
r
a
n
g
e
o
f
ap
p
licatio
n
s
.
Stan
d
ar
d
s
in
cu
r
in
g
p
er
io
d
s
h
av
e
s
h
ap
e
d
t
h
e
o
b
s
er
v
e
d
p
ea
k
s
with
in
th
e
ag
e
d
is
tr
ib
u
tio
n
s
in
ce
m
an
y
c
o
n
cr
ete
m
i
x
tu
r
es r
ec
eiv
e
th
eir
p
r
escr
ib
e
d
cu
r
i
n
g
d
u
r
atio
n
s
.
C
o
m
p
r
ess
iv
e
s
tr
en
g
th
d
ata
f
o
llo
ws
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
,
g
iv
in
g
e
v
id
en
ce
o
f
ty
p
ical
c
o
n
cr
ete
m
ix
b
eh
av
io
r
al
p
atter
n
s
i
n
th
e
te
s
ted
s
am
p
les.
T
h
is
v
is
u
aliza
tio
n
n
o
t
o
n
ly
aid
s
i
n
u
n
d
er
s
t
an
d
in
g
th
e
ty
p
ical
p
r
o
p
er
ties
o
f
th
e
m
ater
ials
u
s
ed
b
u
t
also
s
er
v
es
as
a
cr
itic
al
to
o
l
f
o
r
id
en
tify
in
g
tr
en
d
s
,
an
o
m
alies,
an
d
th
e
o
v
er
all
b
eh
a
v
io
r
o
f
th
e
c
o
m
p
o
n
en
ts
in
co
n
c
r
ete
m
ix
f
o
r
m
u
lat
io
n
.
Stan
d
ar
d
ized
ex
p
lo
r
ato
r
y
d
ata
an
aly
s
is
(
E
DA)
id
en
tifie
d
v
ar
iab
le
co
n
n
ec
tio
n
s
an
d
d
is
tr
ib
u
tio
n
s
.
T
h
e
h
is
to
g
r
am
s
in
Fig
u
r
e
3
s
h
o
w
th
at
th
e
"d
is
tr
ib
u
tio
n
o
f
d
is
tr
ib
u
tio
n
"
ca
n
b
e
o
f
an
y
k
in
d
an
d
th
at
th
e
d
ata
d
is
tr
ib
u
tio
n
d
if
f
er
s
f
o
r
ea
ch
d
ata
s
et.
B
ec
au
s
e
o
f
lo
w
d
e
n
s
ity
at
h
ig
h
ce
m
en
t
co
n
ce
n
tr
atio
n
an
d
d
en
s
er
lo
ca
tio
n
s
at
lo
w
ce
m
en
t
lev
el
s
,
th
e
ce
m
en
t
f
ea
tu
r
e
d
is
p
lay
s
a
s
k
ewe
d
r
ig
h
t
d
is
tr
ib
u
tio
n
.
T
h
is
s
k
ewn
ess
is
im
p
o
r
tan
t b
ec
a
u
s
e
ce
m
en
t d
et
er
m
in
es th
e
s
tr
en
g
th
a
n
d
d
u
r
a
b
ilit
y
o
f
co
n
cr
ete.
At
ze
r
o
,
th
e
d
is
tr
ib
u
tio
n
o
f
f
ly
ash
an
d
b
last
f
u
r
n
ac
e
s
lag
is
n
o
tewo
r
th
y
;
th
u
s
,
m
an
y
m
ix
tu
r
es
d
o
n
o
t
u
s
e
th
em
.
As s
h
o
wn
b
y
th
eir
wid
esp
r
ea
d
u
s
e
in
v
a
r
io
u
s
f
iel
d
s
,
th
ey
ca
n
im
p
r
o
v
e
co
n
cr
ete
p
r
o
p
er
ties
.
W
ater
is
cr
u
cial
to
th
e
co
n
cr
ete
m
ix
r
atio
,
b
u
t
m
o
s
t
co
m
p
o
n
en
ts
ar
e
b
alan
ce
d
.
T
h
e
r
ig
h
t
w
ater
lev
els
af
f
ec
t
cu
r
in
g
,
h
y
d
r
atio
n
,
co
n
cr
ete
s
tr
en
g
th
,
an
d
m
o
v
em
en
t.
Su
p
er
p
last
icize
r
is
le
s
s
p
o
p
u
lar
th
an
Fre
q
u
en
t
L
im
esto
n
e.
W
ith
o
u
t
wate
r
,
m
ix
ed
wo
r
k
ab
ilit
y
m
u
s
t
b
e
im
p
r
o
v
e
d
d
u
e
t
o
its
in
cr
ea
s
ed
f
r
eq
u
en
c
y
at
less
er
lev
els.
Giv
en
th
at
th
e
b
u
l
k
o
f
co
n
cr
ete'
s
v
o
lu
m
e
is
co
m
p
o
s
ed
o
f
co
u
r
s
e
a
n
d
f
in
e
a
g
g
r
e
g
ate
,
th
eir
d
is
tr
ib
u
tio
n
s
aid
in
ex
p
lain
in
g
t
h
is
.
T
h
e
v
ar
iatio
n
in
th
eir
q
u
a
n
titi
es
in
th
e
two
s
am
p
les
s
u
g
g
ests
th
ey
ca
n
ch
a
n
g
e
m
ix
d
en
s
ity
an
d
s
tr
en
g
th
.
Fig
u
r
e
4
co
r
r
elatio
n
h
ea
tm
a
p
d
em
o
n
s
tr
ates
a
s
tr
o
n
g
in
v
er
s
e
r
elatio
n
s
h
ip
b
etwe
en
wate
r
an
d
s
u
p
er
p
last
icize
r
s
,
s
h
o
win
g
th
at
s
u
p
er
p
last
icize
r
s
r
ed
u
ce
wate
r
u
s
e
an
d
s
tr
en
g
th
en
m
ix
es.
I
n
th
e
lin
e
p
lo
t
as
s
h
o
wn
in
Fig
u
r
e
5
,
th
e
p
o
s
itiv
e
co
r
r
elatio
n
b
etwe
en
Ag
e
a
n
d
Stre
n
g
t
h
em
p
h
asizes
th
e
n
ec
ess
ity
o
f
cu
r
in
g
,
wh
er
e
s
tr
en
g
th
g
r
o
ws
with
ti
m
e.
C
o
n
cr
ete
q
u
ality
s
h
o
u
ld
b
e
ev
alu
ated
b
ased
o
n
its
ag
e
.
T
h
ese
ex
p
l
o
r
ato
r
y
d
is
co
v
er
ies
h
elp
o
p
tim
ize
co
n
cr
ete
m
ix
d
esig
n
s
f
o
r
g
r
ea
ter
p
er
f
o
r
m
an
ce
an
d
s
u
s
tain
ab
ilit
y
in
co
n
s
tr
u
ctio
n
b
y
u
n
d
er
s
tan
d
i
n
g
th
e
in
tr
icate
i
n
ter
ac
tio
n
o
f
co
n
cr
ete
c
o
m
p
o
n
en
ts
.
T
h
is
r
i
g
o
r
o
u
s
in
v
est
ig
atio
n
illu
m
in
ates
co
n
cr
ete
s
tr
en
g
th
p
ar
am
ete
r
s
,
p
av
in
g
t
h
e
r
o
a
d
f
o
r
b
u
ild
i
n
g
m
ater
ial
s
cien
ce
ad
v
an
ce
m
en
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
co
n
crete
s
u
s
ta
in
a
b
ilit
y:
a
n
eu
r
a
l
n
etw
o
r
ks h
yb
r
id
o
p
timiz
a
tio
n
…
(
E
s
r
a
’
a
A
lh
e
n
a
w
i
)
4973
Fig
u
r
e
3
.
His
to
g
r
am
s
o
f
co
n
cr
ete
co
m
p
o
n
en
ts
Fig
u
r
e
4
.
C
o
n
c
r
ete
f
ea
tu
r
es c
o
r
r
elatio
n
m
atr
ix
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
6
5
-
4
9
8
2
4974
Fig
u
r
e
5
.
I
m
p
ac
t
o
f
f
ea
tu
r
es o
n
co
m
p
r
ess
iv
e
s
tr
en
g
th
2
.
3
.
H
y
brid co
nv
o
lutio
na
l
-
r
ec
urre
nt
neura
l net
wo
rk
(
Co
nv
1
D
-
L
ST
M
-
G
RU)
a
rc
hit
ec
t
ure
C
o
n
v
o
lu
tio
n
al
an
d
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
s
m
an
a
g
e
s
eq
u
en
tial
in
p
u
t
an
d
p
r
e
d
ict
co
n
cr
ete
s
tr
en
g
th
u
s
in
g
co
m
p
o
s
itio
n
p
r
o
f
iles
a
n
d
tim
e
s
eq
u
en
ce
in
T
ab
le
3
.
L
ay
er
o
n
e
,
a
1
D
co
n
v
o
lu
ti
o
n
al
lay
er
,
ca
p
tu
r
es
s
p
atial
r
elatio
n
s
h
ip
s
in
th
e
d
a
ta.
T
wo
k
er
n
els
an
d
6
4
f
ilter
s
co
m
p
r
is
ed
th
is
lay
er
.
T
h
is
r
ev
ea
ls
co
m
p
licated
p
atter
n
s
in
s
eq
u
en
tial
in
p
u
t
d
ata
lik
e
co
n
cr
ete
m
ix
in
g
r
ed
i
en
t
in
ter
ac
tio
n
s
.
T
h
e
m
o
d
el'
s
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
f
o
llo
ws
th
e
co
n
v
o
lu
tio
n
al
la
y
e
r
.
T
h
is
lay
er
h
as
5
0
L
STM
u
n
its
th
at
ca
n
lear
n
f
o
r
war
d
an
d
b
ac
k
war
d
d
ep
e
n
d
en
cies.
Pro
ce
s
s
in
g
d
ata
in
b
o
t
h
d
ir
ec
tio
n
s
r
ed
u
ce
s
th
e
n
ee
d
t
o
co
m
p
r
eh
e
n
d
ea
ch
d
ata
p
o
in
t'
s
co
n
tex
t,
r
ev
ea
lin
g
p
atter
n
s
th
at
o
n
e
-
d
ir
ec
tio
n
al
a
n
aly
s
is
m
is
s
e
s
.
Ad
d
in
g
a
s
ec
o
n
d
b
i
d
ir
ec
tio
n
a
l
lay
er
with
GR
U
in
cr
ea
s
es
m
o
d
el
c
o
m
p
lex
ity
an
d
ca
p
a
b
ilit
y
.
GR
U
co
n
tain
s
5
0
u
n
its
an
d
ac
ce
p
ts
two
-
way
d
ata
lik
e
L
STM
.
GR
Us
ar
e
m
o
r
e
e
f
f
ec
tiv
e
a
n
d
co
m
p
u
tatio
n
all
y
Evaluation Warning : The document was created with Spire.PDF for Python.