I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
,
p
p
.
117
~
1
2
4
I
SS
N:
2
2
5
2
-
8814
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
aa
s
.
v
9
.
i
2
.
p
p
1
1
7
-
124
117
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
O
v
ervi
ew
of so
ft
int
ellig
ent
co
m
put
ing
t
echni
que
for
supercriti
ca
l f
lui
d
extractio
n
Sitino
o
r
Adeib I
dris
1
,
M
a
s
t
ura
h M
a
rk
o
m
2
1
F
a
c
u
lt
y
o
f
Ch
e
m
ic
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
M
a
la
y
sia
1,
2
De
p
a
rtem
e
n
t
o
f
Ch
e
m
ica
l
a
n
d
P
r
o
c
e
ss
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
Ke
b
a
n
g
sa
a
n
M
a
la
y
sia
,
M
a
la
y
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
8
,
2
0
1
9
R
ev
i
s
ed
J
u
l 1
4
201
9
A
cc
ep
ted
Feb
11
,
2
0
2
0
Op
ti
m
iza
ti
o
n
o
f
S
u
p
e
rc
rit
ica
l
F
l
u
id
Ex
trac
ti
o
n
p
ro
c
e
ss
w
it
h
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
li
n
g
is
e
ss
e
n
ti
a
l
f
o
r
in
d
u
strial
a
p
p
li
c
a
ti
o
n
s.
T
h
e
re
sp
o
n
se
su
rfa
c
e
m
e
th
o
d
o
lo
g
y
(RS
M
)
h
a
s
b
e
e
n
p
ro
v
e
n
to
b
e
a
u
se
f
u
l
a
n
d
e
ff
e
c
ti
v
e
sta
ti
stica
l
m
e
th
o
d
f
o
r
st
u
d
y
in
g
th
e
re
lati
o
n
sh
i
p
s
b
e
tw
e
e
n
m
e
a
su
re
d
re
sp
o
n
se
s
a
n
d
in
d
e
p
e
n
d
e
n
t
f
a
c
to
rs.
Re
c
e
n
tl
y
th
e
re
a
re
g
ro
w
in
g
in
tere
st
in
a
p
p
l
y
in
g
s
m
a
rt
s
y
ste
m
o
r
a
rti
f
icia
l
tec
h
n
iq
u
e
to
m
o
d
e
l
a
n
d
sim
u
late
a
c
h
e
m
ica
l
p
ro
c
e
ss
a
n
d
a
lso
to
p
re
d
ict,
c
o
m
p
u
te,
c
las
sify
a
n
d
o
p
ti
m
ize
a
s
w
e
ll
a
s
f
o
r
p
ro
c
e
ss
c
o
n
tro
l.
T
h
is
s
y
ste
m
w
o
rk
s
b
y
g
e
n
e
ra
l
izi
n
g
th
e
e
x
p
e
rim
e
n
tal
re
su
lt
a
n
d
t
h
e
p
r
o
c
e
ss
b
e
h
a
v
io
r
a
n
d
f
in
a
ll
y
p
re
d
ict
a
n
d
e
sti
m
a
te
th
e
p
ro
b
lem
.
T
h
is
s
m
a
rt
s
y
ste
m
i
s
a
m
a
jo
r
a
ss
istan
c
e
in
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
p
ro
c
e
ss
f
ro
m
lab
o
ra
to
ry
to
p
i
lo
t
o
r
in
d
u
strial.
T
h
e
m
a
in
a
d
v
a
n
tag
e
o
f
in
telli
g
e
n
t
sy
ste
m
s
is
th
a
t
th
e
p
re
d
ictio
n
s
c
a
n
b
e
p
e
rf
o
r
m
e
d
e
a
sil
y
,
f
a
st,
a
n
d
a
c
c
u
ra
te
w
a
y
,
w
h
ich
p
h
y
sic
a
l
m
o
d
e
ls
u
n
a
b
le
t
o
d
o
.
T
h
is
p
a
p
e
r
sh
a
re
s
se
v
e
r
a
l
w
o
rk
s
th
a
t
h
a
v
e
b
e
e
n
u
ti
l
izin
g
in
telli
g
e
n
t
sy
ste
m
s
f
o
r
m
o
d
e
li
n
g
a
n
d
sim
u
latin
g
th
e
su
p
e
rc
rit
ica
l
f
lu
id
e
x
trac
ti
o
n
p
ro
c
e
ss
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
tec
h
n
iq
u
e
H
y
b
r
id
Neu
r
al
n
et
w
o
r
k
Op
ti
m
izatio
n
S
m
ar
t s
y
s
te
m
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
:
Sit
in
o
o
r
A
d
eib
I
d
r
is
,
Facu
lt
y
o
f
C
h
e
m
ical
E
n
g
in
ee
r
in
g
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
4
0
4
5
0
,
Sh
ah
A
la
m
,
Sela
n
g
o
r
,
Ma
la
y
s
ia.
E
m
ail: a
d
eib
@
s
ala
m
.
u
it
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
r
a
d
itio
n
al
co
m
p
u
tatio
n
a
l
ap
p
r
o
ac
h
es
an
d
m
e
th
o
d
s
co
u
ld
o
n
l
y
m
o
d
el
an
d
an
al
y
ze
s
i
m
p
le
s
y
s
te
m
s
.
C
o
m
p
le
x
s
y
s
te
m
s
s
u
c
h
as
i
n
m
ac
h
in
i
n
g
,
b
io
lo
g
y
,
m
ed
ici
n
e
an
d
s
i
m
ilar
f
ield
s
o
f
te
n
r
e
m
a
in
ed
u
n
s
o
l
v
ab
le
to
co
n
v
e
n
tio
n
al
m
at
h
e
m
atica
l
a
n
d
an
al
y
tica
l
m
e
th
o
d
s
.
A
s
s
u
m
p
tio
n
s
an
d
s
i
m
p
li
f
ica
tio
n
o
f
m
at
h
e
m
a
tical
m
o
d
e
l
ar
e
s
o
m
et
i
m
e
s
n
o
t
r
eliab
le
an
d
m
an
y
co
n
v
en
tio
n
al
m
ath
e
m
atica
l
m
o
d
el
s
h
a
v
e
b
ee
n
b
o
th
ch
alle
n
g
i
n
g
an
d
i
m
p
r
ac
tical.
So
f
t
co
m
p
u
ti
n
g
h
o
w
e
v
er
,
d
ea
ls
w
i
th
i
m
p
r
ec
i
s
io
n
,
u
n
ce
r
tai
n
t
y
,
p
ar
tial
tr
u
t
h
a
n
d
ap
p
r
o
x
im
a
tio
n
to
ac
h
iev
e
tr
ac
tab
ilit
y
,
r
o
b
u
s
t
n
e
s
s
a
n
d
m
o
r
e
i
m
p
o
r
tan
tl
y
lo
w
s
o
lu
t
io
n
co
s
t.
Fi
g
u
r
e
1
s
h
o
w
s
t
h
e
a
v
ailab
le
co
m
p
o
n
e
n
t
s
o
f
s
o
f
t
co
m
p
u
ti
n
g
.
T
h
er
e
ar
e
f
iv
e
t
y
p
es
w
h
ich
ar
e
n
eu
r
al
n
et
w
o
r
k
s
,
f
u
zz
y
s
y
s
te
m
s
,
e
v
o
lu
tio
n
ar
y
co
m
p
u
tatio
n
,
id
ea
s
ab
o
u
t
p
r
o
b
ab
ilit
ies
an
d
s
w
ar
m
i
n
telli
g
e
n
ce
.
T
h
is
s
t
u
d
y
i
s
w
ill
f
o
cu
s
o
n
an
o
v
er
v
ie
w
o
f
p
r
ev
io
u
s
r
esear
c
h
ap
p
l
y
i
n
g
s
o
m
e
o
f
t
h
e
co
m
p
o
n
e
n
t
s
s
u
ch
as
n
e
u
r
al
n
et
w
o
r
k
s
,
f
u
zz
y
s
y
s
te
m
s
,
g
en
et
ic
alg
o
r
ith
m
a
n
d
its
h
y
b
r
id
in
s
u
p
er
cr
itical
f
lu
id
ex
tr
ac
tio
n
p
r
o
ce
s
s
.
C
o
n
v
en
t
io
n
al
tech
n
iq
u
e
s
ar
e
l
ar
g
el
y
b
ased
o
n
f
o
r
m
al
lo
g
ica
l
s
y
s
te
m
s
an
d
r
el
y
h
ea
v
il
y
o
n
co
m
p
u
ter
-
aid
ed
n
u
m
er
ical
an
a
l
y
s
is
.
So
f
t
co
m
p
u
ti
n
g
tech
n
i
q
u
es a
r
e
i
n
t
en
d
ed
to
co
m
p
le
m
e
n
t e
ac
h
o
th
er
.
Har
d
co
m
p
u
ti
n
g
s
ch
e
m
es
s
tr
iv
e
f
o
r
ac
cu
r
aten
e
s
s
an
d
f
u
l
l
tr
u
t
h
w
h
er
ea
s
s
o
f
t
co
m
p
u
ti
n
g
tec
h
n
iq
u
e
s
ex
p
lo
it
th
e
g
iv
e
n
to
ler
an
ce
o
f
i
m
p
r
ec
i
s
io
n
,
p
ar
tial
tr
u
t
h
,
an
d
u
n
ce
r
tai
n
t
y
f
o
r
a
p
ar
tic
u
lar
p
r
o
b
lem
o
r
d
ata.
I
n
o
v
er
all,
s
o
f
t
co
m
p
u
tin
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
I
n
t J
A
d
v
A
p
p
l Sci
,
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
: 1
1
7
–
124
118
tech
n
iq
u
e
is
s
i
m
ilar
an
d
i
m
i
tat
in
g
t
h
e
g
e
n
etic
p
r
o
ce
s
s
es
m
o
r
e
clo
s
el
y
th
a
n
t
h
e
tr
ad
itio
n
al
t
ec
h
n
iq
u
e.
I
t
ap
p
lies
th
e
ab
ilit
y
to
lear
n
,
o
b
s
er
v
e
an
d
m
e
m
o
r
ize
in
a
s
itu
a
tio
n
o
f
f
u
ll o
f
f
ac
to
r
s
an
d
i
m
p
o
r
ta
n
t d
ata.
W
h
er
ea
s
,
h
y
b
r
id
in
tel
lig
e
n
ce
s
y
s
te
m
s
d
ea
l
w
i
th
th
e
in
teg
r
at
io
n
o
f
t
w
o
o
r
m
o
r
e
o
f
th
e
tec
h
n
o
lo
g
ies.
T
h
e
co
m
b
i
n
ed
u
s
e
o
f
tec
h
n
o
lo
g
ies
h
as
r
esu
lted
i
n
e
f
f
ec
tiv
e
p
r
o
b
le
m
s
o
lv
in
g
i
n
co
m
p
ar
i
s
o
n
w
it
h
ea
c
h
tech
n
o
lo
g
y
u
s
ed
i
n
d
iv
id
u
all
y
an
d
e
x
cl
u
s
i
v
el
y
.
As
i
llu
s
tr
ated
in
Fi
g
u
r
e
2
,
ea
ch
o
f
t
h
ese
tech
n
o
lo
g
ie
s
in
d
iv
id
u
all
y
a
n
d
i
n
co
m
b
in
at
io
n
ca
n
b
e
e
m
p
lo
y
ed
to
s
o
lv
e
p
r
o
b
lem
s
.
Fo
r
e
x
a
m
p
le,
wh
en
n
e
u
r
al
n
et
w
o
r
k
co
m
b
i
n
es
w
it
h
f
u
zz
y
s
y
s
te
m
s
,
a
n
eu
r
o
-
f
u
zz
y
h
y
b
r
id
w
ill
d
e
v
elo
p
an
d
w
h
e
n
n
eu
r
al
n
et
w
o
r
k
an
d
ev
o
l
u
tio
n
ar
y
alg
o
r
ith
m
co
m
b
i
n
es,
a
n
e
u
r
o
-
e
v
o
lu
ti
o
n
ar
y
w
i
ll b
e
d
ev
elo
p
ed
.
Fig
u
r
e
1
.
C
o
m
p
o
n
e
n
ts
o
f
s
o
f
t
co
m
p
u
ti
n
g
[
1
]
Fig
u
r
e
2
.
I
n
teg
r
atio
n
o
f
n
e
u
r
al
n
et
w
o
r
k
s
,
f
u
zz
y
s
y
s
te
m
s
an
d
ev
o
lu
tio
n
ar
y
al
g
o
r
ith
m
tec
h
n
o
lo
g
ies b
y
[
2
]
2.
P
RE
VIOU
S
ST
UDY
AP
P
L
YIN
G
SO
F
T
I
NT
E
L
L
I
G
E
N
T
CO
M
P
UT
I
NG
T
E
CH
N
I
Q
UE
I
n
o
r
d
er
t
o
d
ev
elo
p
a
r
eliab
l
e
m
o
d
el
to
r
ep
r
esen
t
th
e
d
at
a,
n
eu
r
al
n
et
w
o
r
k
h
a
v
e
b
ee
n
ap
p
lied
t
o
s
ev
er
al
s
u
p
er
cr
itical
f
lu
id
ex
tr
ac
tio
n
p
r
o
ce
s
s
es
in
p
r
ed
ictin
g
y
ield
o
f
ex
tr
ac
tio
n
[1
-
6]
an
d
s
o
lu
b
ilit
y
p
r
ed
ictio
n
s
[7
-
9]
.
B
esid
es
th
at
,
f
u
zz
y
s
y
s
t
e
m
s
also
h
as
b
ee
n
ap
p
lied
to
d
eter
m
in
e
t
h
e
e
x
tr
ac
tan
t
q
u
a
n
tit
ies
at
d
esire
d
tem
p
er
at
u
r
es a
n
d
p
r
es
s
u
r
es
[
1
0
]
.
T
h
er
e
ar
e
s
ev
er
al
s
tu
d
ies
u
s
i
n
g
a
h
y
b
r
id
m
o
d
el
co
m
b
i
n
i
n
g
A
N
N
an
d
FIS
w
h
ic
h
is
ca
lled
as
A
NFI
S
to
p
r
ed
ict
s
o
lu
b
ilit
y
[
1
1
]
an
d
m
as
s
o
f
ex
tr
ac
t
[
1
2
,
1
3
]
.
A
n
o
th
er
t
y
p
e
o
f
h
y
b
r
id
is
b
y
co
m
b
in
in
g
A
NN
w
i
th
a
co
n
v
e
n
tio
n
al
m
a
th
e
m
atica
l
m
o
d
el
[
1
4
]
.
T
h
is
t
y
p
e
o
f
h
y
b
r
i
d
w
as
m
ai
n
l
y
to
s
o
l
v
e
t
h
e
b
lack
b
o
x
is
s
u
e
s
o
f
n
o
t
u
n
d
er
s
ta
n
d
in
g
t
h
e
p
r
o
ce
s
s
o
f
S
FE.
B
y
A
N
N
-
Ma
th
e
m
atica
l
m
o
d
el
h
y
b
r
id
,
o
n
e
ca
n
s
o
lv
e
t
h
e
is
s
u
e
[
1
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
d
v
A
p
p
l Sci
I
SS
N:
2
2
5
2
-
8814
Ove
r
view o
f so
ft in
tellig
en
t c
o
mp
u
tin
g
tech
n
iq
u
e
fo
r
s
u
p
ercr
itica
l flu
id
ex
tr
a
ctio
n
(
S
itin
o
o
r
A
d
eib
I
d
r
is
)
119
So
m
e
s
t
u
d
ies
e
v
e
n
co
m
p
ar
e
th
e
r
es
u
lt
s
o
f
ap
p
licatio
n
o
f
A
N
N
a
n
d
A
NFI
S
i
n
o
r
d
er
t
o
id
en
ti
f
y
th
e
b
es
t s
y
s
te
m
t
h
at
ca
n
r
ep
r
esen
t th
e
d
ata
a
n
d
r
eliab
le
f
o
r
o
p
ti
m
izat
io
n
p
r
o
ce
s
s
[
1
6
-
19]
.
Gen
etic
al
g
o
r
ith
m
al
s
o
o
n
e
o
f
th
e
p
r
o
m
i
s
i
n
g
to
o
ls
in
o
p
ti
m
izat
io
n
o
f
SF
E
[
2
0
-
24]
.
I
t
h
as
b
ee
n
ap
p
lied
in
d
eter
m
i
n
i
n
g
co
n
s
ta
n
ts
i
n
m
ath
e
m
atica
l
m
o
d
el
in
o
r
d
er
to
m
i
n
i
m
ize
er
r
o
r
b
et
w
ee
n
m
o
d
el
r
es
u
lt
s
an
d
ex
p
er
i
m
e
n
tal
d
ata
[
2
5
]
.
I
t
ca
n
also
b
e
u
s
ed
in
g
e
n
er
atin
g
th
e
n
o
n
-
li
n
ea
r
b
in
ar
y
i
n
ter
ac
tio
n
p
ar
a
m
eter
o
f
th
e
co
n
v
en
t
io
n
al
m
at
h
e
m
a
tical
m
o
d
el
s
u
c
h
as i
n
P
en
g
–
R
o
b
i
n
s
o
n
eq
u
atio
n
[
2
6
]
.
3.
ARTI
F
I
CI
AL
N
E
URA
L
NE
T
WO
RK
(
ANN)
AND
ADA
P
T
I
V
E
NE
U
RO
-
F
U
Z
Z
Y
I
N
F
E
RE
N
CE
SYST
E
M
(
ANF
I
S)
A
d
ap
tiv
e
Neu
r
o
-
F
u
zz
y
I
n
f
er
en
ce
S
y
s
te
m
(
ANFI
S)
is
co
n
s
i
d
er
ed
as
o
n
e
t
y
p
e
o
f
h
y
b
r
id
m
o
d
el
f
o
r
o
p
tim
izatio
n
p
r
o
ce
s
s
s
in
ce
it
co
m
b
i
n
es
t
h
e
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
(
ANN)
a
n
d
F
u
zz
y
I
n
f
er
e
n
ce
S
y
s
te
m
(
FIS)
s
y
s
te
m
.
T
ab
le
1
d
escr
ib
e
s
th
e
ad
v
a
n
ta
g
es a
n
d
d
is
ad
v
an
tag
es a
p
p
l
y
i
n
g
A
NN
m
o
d
el
i
n
d
ep
en
d
en
tl
y
.
T
ab
le
1
.
A
d
v
an
ta
g
es a
n
d
li
m
it
atio
n
s
o
f
ANN
-
b
a
s
ed
m
o
d
els
[2
7
]
A
d
v
a
n
t
a
g
e
s
L
i
mi
t
a
t
i
o
n
s
Ea
sy
f
o
r
c
o
r
r
e
l
a
t
i
o
n
o
f
d
a
t
a
a
l
t
h
o
u
g
h
a
b
se
n
t
o
f
su
i
t
a
b
l
e
f
u
n
c
t
i
o
n
H
a
r
d
t
o
i
n
t
e
r
p
r
e
t
a
n
d
a
n
a
l
y
z
e
t
h
e
o
u
t
p
u
t
T
h
e
mo
d
e
l
c
a
n
e
a
si
l
y
b
e
d
e
v
e
l
o
p
e
d
a
n
d
t
o
o
k
l
e
ss
t
i
me
t
o
b
e
d
e
v
e
l
o
p
e
d
c
o
mp
a
r
e
d
t
o
o
t
h
e
r
mo
d
e
l
s
T
h
e
t
r
a
i
n
i
n
g
o
f
t
h
e
d
a
t
a
mi
g
h
t
t
a
k
e
m
u
c
h
t
i
me
,
e
v
e
n
d
a
y
s
N
o
t
h
e
o
r
e
t
i
c
a
l
k
n
o
w
l
e
d
g
e
o
f
p
r
o
c
e
ss
a
n
d
l
i
t
e
r
a
t
u
r
e
p
a
r
a
me
t
e
r
s
n
e
e
d
e
d
t
o
d
e
v
e
l
o
p
t
h
e
mo
d
e
l
A
l
a
r
g
e
se
t
o
f
e
x
p
e
r
i
me
n
t
a
l
d
a
t
a
n
e
e
d
e
d
c
o
v
e
r
i
n
g
w
i
d
e
o
p
e
r
a
t
i
n
g
c
o
n
d
i
t
i
o
n
s
n
e
e
d
e
d
b
e
c
a
u
se
o
f
h
e
t
r
a
i
n
i
n
g
o
f
a
n
A
N
N
u
se
d
t
h
e
e
x
p
e
r
i
me
n
t
a
l
d
a
t
a
I
t
c
a
n
h
a
n
d
l
e
n
o
i
se
,
i
n
c
o
m
p
l
e
t
e
a
n
d
i
n
c
o
n
s
i
st
e
n
t
d
a
t
a
w
h
e
n
e
v
e
r
t
h
e
o
v
e
r
-
f
i
t
t
i
n
g
i
s
a
v
o
i
d
e
d
T
h
e
a
r
c
h
i
t
e
c
t
u
r
e
d
e
p
e
n
d
s
o
n
t
h
e
v
a
r
i
a
t
i
o
n
o
f
c
o
n
d
i
t
i
o
n
s
w
h
e
n
t
r
a
i
n
e
d
a
n
d
c
a
n
n
o
t
b
e
p
r
e
d
i
c
t
e
d
T
h
e
‘
b
lack
-
b
o
x
’
n
at
u
r
e
o
f
ANN
m
o
d
els
a
n
d
u
n
s
atis
f
ac
to
r
y
e
x
tr
ap
o
latio
n
b
y
ANN
m
o
d
els
h
a
v
e
led
to
th
e
d
ev
elo
p
m
e
n
t
o
f
h
y
b
r
id
n
eu
r
al
n
et
w
o
r
k
m
o
d
els
w
h
ic
h
co
m
b
i
n
e
A
NN
s
w
it
h
s
i
m
p
l
e
m
o
d
els.
T
h
ese
ar
e
ex
p
ec
ted
to
p
er
f
o
r
m
b
etter
th
an
A
NN
s
in
p
r
o
ce
s
s
id
en
ti
f
ic
atio
n
tas
k
s
,
s
in
ce
g
en
er
aliza
ti
o
n
an
d
ex
tr
ap
o
latio
n
ar
e
co
n
f
i
n
ed
o
n
l
y
to
th
e
u
n
ce
r
tain
p
ar
ts
o
f
t
h
e
p
r
o
ce
s
s
w
h
i
l
e
th
e
b
as
ic
m
o
d
el
is
a
l
w
a
y
s
c
o
n
s
is
ten
t
w
it
h
f
ir
s
t
p
r
in
cip
les
[2
8
]
.
I
n
a
s
tu
d
y
o
n
q
u
er
ce
ti
n
ex
tr
a
ctio
n
f
r
o
m
R
o
s
a
d
a
ma
s
ce
n
e
Mill
an
ex
p
er
i
m
e
n
t
w
as
co
n
d
u
cted
u
s
i
n
g
a
m
o
d
if
ied
s
u
p
er
cr
itical
C
O
2
w
it
h
et
h
an
o
l
as
co
-
s
o
lv
e
n
t
[
1
9
]
.
T
h
e
r
ec
o
v
er
y
o
f
e
x
tr
ac
tio
n
w
a
s
p
r
ed
icted
u
s
in
g
A
d
ap
tiv
e
n
e
u
r
o
-
f
u
zz
y
i
n
f
er
en
ce
s
y
s
te
m
(
ANFI
S)
an
d
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
(
A
NN)
.
T
h
e
v
ar
iab
les
w
er
e
tr
an
s
lated
i
n
to
co
d
ed
v
al
u
e
o
f
-
2
,
-
1
,
0
,
+1
an
d
+2
.
T
ab
l
e
2
s
h
o
w
s
th
e
co
d
ed
v
ar
iab
les
f
o
r
t
h
is
p
r
o
ce
s
s
.
T
h
e
co
d
ed
v
ar
iab
les
ar
e
u
s
u
all
y
ap
p
lied
w
h
e
n
R
SM,
AN
N
an
d
ANFI
S
is
g
o
i
n
g
to
b
e
u
s
ed
as
to
o
ls
f
o
r
o
p
tim
izatio
n
p
r
o
ce
s
s
.
T
ab
le
2
.
Un
co
d
ed
an
d
c
o
d
ed
l
ev
els o
f
i
n
d
ep
en
d
en
t v
ar
iab
les
u
s
ed
in
t
h
e
R
SM,
A
NN
a
n
d
ANFI
S
C
o
d
e
d
v
a
r
i
a
b
l
e
s
T
e
mp
e
r
a
t
u
r
e
,
T
(
o
C)
P
r
e
ssu
r
e
,
P
(
M
P
a
)
D
y
n
a
mi
c
t
i
me
,
t
(
mi
n
)
F
l
o
w
r
a
t
e
o
f
C
O
2
,
Q
(
ml
/
mi
n
)
-
2
35
10
40
0
.
3
-
1
40
15
60
0
.
6
0
45
20
80
0
.
9
+1
50
25
1
0
0
1
.
2
+2
55
30
1
2
0
1
.
5
Gen
er
all
y
,
A
N
FIS
ar
ch
itect
u
r
e
co
n
s
is
t
s
o
f
5
lay
er
s
as
s
h
o
wn
in
Fi
g
u
r
e
3
.
T
h
e
ar
ch
itectu
r
e
o
f
A
NFI
S
in
Fi
g
u
r
e
3
m
ap
s
t
h
e
i
n
p
u
t
s
th
r
o
u
g
h
i
n
p
u
t
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
(
MF)
an
d
f
u
zz
y
r
u
les
.
Si
m
i
lar
l
y
,
o
u
tp
u
t
m
ap
p
in
g
is
d
o
n
e
t
h
r
o
u
g
h
o
u
tp
u
t
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
alo
n
g
w
it
h
its
f
u
z
z
y
r
u
les.
T
h
e
n
u
m
b
er
o
f
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
as
s
ig
n
ed
to
ea
ch
i
n
p
u
t
v
ar
iab
le
i
s
ch
o
s
e
n
b
y
tr
ial
an
d
er
r
o
r
.
Fig
u
r
e
3
s
h
o
w
s
th
e
g
en
er
al
ar
c
h
itect
u
r
e
o
f
ANFI
S
f
o
r
SF
E
s
y
s
te
m
.
T
h
e
h
y
b
r
id
o
f
a
n
e
u
r
al
n
et
w
o
r
k
an
d
f
u
zz
y
lo
g
ic
in
ANFI
S
m
ak
es it
h
a
v
e
b
o
th
,
lo
w
-
le
v
el
le
ar
n
in
g
an
d
co
m
p
u
tatio
n
al
p
o
w
er
o
f
n
e
u
r
a
l
n
et
w
o
r
k
an
d
ad
v
a
n
tag
e
s
o
f
h
ig
h
-
le
v
el
h
u
m
an
li
k
e
t
h
in
k
i
n
g
o
f
f
u
zz
y
s
y
s
te
m
s
.
T
h
er
ef
o
r
e,
th
is
n
e
u
r
o
-
f
u
zz
y
m
o
d
el
ab
le
to
o
v
er
co
m
e
t
h
eir
i
n
d
iv
id
u
al
d
i
s
ad
v
a
n
ta
g
es
a
n
d
ca
n
co
m
p
le
m
e
n
t
ea
c
h
o
th
er
[2
9
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
I
n
t J
A
d
v
A
p
p
l Sci
,
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
: 1
1
7
–
124
120
Fig
u
r
e
3
.
A
NFI
S a
r
ch
itect
u
r
e
4.
M
AT
H
E
M
AT
I
CAL M
O
DE
L
-
NE
UR
AL
N
E
T
WO
RK
H
YB
RID
H
y
b
r
id
m
o
d
els
ca
n
al
s
o
b
e
co
m
b
in
i
n
g
b
o
th
p
h
y
s
ical
la
w
s
a
n
d
o
b
s
er
v
ed
m
ea
s
u
r
e
m
e
n
ts
a
n
d
in
clu
d
i
n
g
all
av
ailab
le
k
n
o
w
led
g
e
o
f
t
h
e
p
r
o
ce
s
s
.
T
h
is
m
o
d
el
ca
n
b
e
ar
r
an
g
ed
in
s
er
ies
o
r
in
p
ar
allel.
I
n
th
e
s
er
ie
s
ap
p
r
o
ac
h
,
h
eu
r
is
tic
m
o
d
el
es
ti
m
ate
s
u
n
m
ea
s
u
r
ed
p
r
o
ce
s
s
p
ar
am
eter
s
o
f
m
at
h
e
m
a
tical
m
o
d
eli
n
g
s
u
c
h
th
a
t
th
e
f
ir
s
t
p
r
in
cip
le
co
n
s
tr
ai
n
s
ar
e
s
atis
f
ied
.
I
n
th
e
p
ar
allel
ap
p
r
o
ac
h
,
th
e
h
y
b
r
id
m
o
d
el
p
r
e
d
ictio
n
is
co
m
b
i
n
atio
n
o
f
th
e
o
u
tp
u
ts
o
f
t
h
e
m
at
h
e
m
a
tical
a
n
d
i
n
itial
h
e
u
r
is
t
ic
m
o
d
els
t
h
u
s
r
esid
u
als
b
et
w
ee
n
th
e
p
r
o
ce
s
s
an
d
th
e
m
at
h
e
m
at
ical
m
o
d
el
is
c
o
m
p
e
n
s
ated
[2
7
]
.
T
h
is
ty
p
e
o
f
h
y
b
r
id
ca
n
s
o
lv
e
th
e
b
lack
b
o
x
is
s
u
es
o
f
n
e
u
r
al
n
et
w
o
r
k
w
h
e
r
e
th
e
k
n
o
w
led
g
e
o
f
th
e
p
r
o
ce
s
s
is
lack
i
n
g
.
W
h
en
co
m
b
in
i
n
g
b
o
th
,
t
h
e
m
o
d
el
w
il
l b
ec
o
m
e
m
o
r
e
r
eliab
le
a
n
d
ca
n
r
ep
r
esen
ts
t
h
e
d
ata
w
e
ll.
A
p
ar
allel
h
y
b
r
id
m
o
d
el
w
a
s
d
ev
elo
p
ed
b
y
r
esear
c
h
er
s
f
r
o
m
I
r
an
[
1
3
]
f
o
r
p
r
ed
ictio
n
o
f
E
p
ig
allo
ca
tech
i
n
g
a
llate
(
E
GC
G)
r
ec
o
v
er
y
o
f
s
u
p
er
cr
itical
ex
tr
ac
tio
n
w
h
ic
h
co
m
b
in
es
co
n
v
en
tio
n
a
l
m
at
h
e
m
a
tical
m
o
d
elin
g
b
ased
o
n
t
h
e
d
i
f
f
er
en
tial
m
ass
b
ala
n
ce
i
n
t
h
e
s
o
lid
an
d
m
o
b
ile
p
h
ase
s
w
it
h
ANFI
S
(
Fig
u
r
e
4
)
.
Usi
n
g
an
al
y
tica
l
m
o
d
el
i
n
th
i
s
s
tr
u
c
tu
r
e,
th
e
a
cc
u
r
ac
y
o
f
A
NFI
S
w
o
u
ld
b
e
in
cr
ea
s
ed
in
n
o
n
-
tr
ain
i
n
g
d
o
m
a
in
s
.
A
d
d
itio
n
all
y
,
A
NFI
S
s
o
lv
e
s
t
h
e
p
r
o
b
lem
o
f
u
n
k
n
o
w
n
an
a
l
y
tica
l p
ar
a
m
e
ter
s
.
I
n
o
th
er
w
o
r
d
s
,
th
e
h
y
b
r
id
m
o
d
el
co
u
ld
s
i
m
u
late
t
h
e
ex
tr
ac
tio
n
s
y
s
te
m
w
it
h
h
a
v
in
g
a
n
y
ar
b
itra
r
y
v
alu
e
o
f
ad
j
u
s
tab
le
p
ar
am
eter
s
o
f
m
a
th
e
m
atica
l
m
o
d
elin
g
[2
7
]
.
Fig
u
r
e
4
.
P
ar
allel
co
m
b
in
atio
n
o
f
m
at
h
e
m
atica
l
m
o
d
el
a
n
d
ANFI
S n
et
w
o
r
k
in
a
h
y
b
r
id
s
tr
u
ctu
r
e
b
y
[
1
5
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
d
v
A
p
p
l Sci
I
SS
N:
2
2
5
2
-
8814
Ove
r
view o
f so
ft in
tellig
en
t c
o
mp
u
tin
g
tech
n
iq
u
e
fo
r
s
u
p
ercr
itica
l flu
id
ex
tr
a
ctio
n
(
S
itin
o
o
r
A
d
eib
I
d
r
is
)
121
I
n
2
0
0
3
,
a
g
r
o
u
p
o
f
r
esear
c
h
er
s
f
r
o
m
C
an
ad
a
p
r
o
p
o
s
ed
a
h
y
b
r
id
m
o
d
el
o
f
R
ad
ial
B
asis
F
u
n
ctio
n
-
P
en
g
R
o
b
in
s
o
n
(
R
B
F
-
P
R
)
m
o
d
el.
T
h
e
h
y
b
r
id
m
o
d
el
w
as
d
e
v
elo
p
ed
b
y
f
ir
s
t
d
ev
elo
p
i
n
g
a
s
i
m
p
le
R
B
F
m
o
d
el.
A
s
i
m
p
le
R
B
F
m
o
d
el
co
n
s
is
t
o
f
t
h
r
ee
i
n
p
u
ts
o
f
T
,
p
an
d
o
th
er
f
ac
to
r
s
w
i
th
o
n
e
o
u
tp
u
t
w
h
ic
h
i
s
y
ield
r
ate.
T
h
is
m
o
d
el
h
as
n
o
k
n
o
w
led
g
e
o
n
t
h
e
w
h
o
le
p
r
o
ce
s
s
.
T
o
o
v
er
co
m
e
th
e
b
lack
b
o
x
p
r
o
b
le
m
o
f
t
h
e
R
B
F
m
o
d
el,
th
e
m
o
d
el
is
co
r
r
elate
d
w
it
h
th
e
P
en
g
-
R
o
b
in
s
o
n
eq
u
atio
n
b
ec
o
m
e
s
a
h
y
b
r
id
R
B
F
-
P
R
m
o
d
el
(
Fi
g
u
r
e
5
)
.
I
n
th
e
P
en
g
-
R
o
b
i
n
s
o
n
eq
u
ati
o
n
o
f
s
tate,
th
er
e
i
s
u
n
k
n
o
w
n
in
ter
ac
tio
n
p
ar
a
m
eter
k
12
,
f
o
r
a
b
in
ar
y
m
i
x
tu
r
e,
w
h
er
eb
y
t
h
e
p
r
ed
icted
s
o
lu
b
il
it
y
i
s
s
e
n
s
i
tiv
e.
T
h
e
k
12
ca
n
b
e
o
b
tain
ed
f
r
o
m
t
h
e
p
h
y
s
ica
l
p
r
o
p
er
ty
d
ata
f
o
r
th
e
m
i
x
tu
r
e,
b
u
t
it
r
eq
u
ir
es
tr
ial
an
d
er
r
o
r
p
r
o
ce
s
s
f
o
r
o
b
tain
in
g
it.
B
esid
es,
t
h
e
p
ar
am
eter
s
w
er
e
all
te
m
p
er
atu
r
e
d
ep
en
d
en
t
w
h
ic
h
d
o
es
n
o
t
r
ea
lly
f
it
t
h
e
d
ata
co
m
p
ar
ed
to
p
r
ess
u
r
e.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
b
y
[
3
0
]
ca
n
co
m
p
e
n
s
ate
t
h
e
b
lack
b
o
x
p
r
o
b
lem
.
I
t
ca
n
f
i
t
th
e
e
x
p
er
i
m
e
n
t
d
at
a
v
er
y
w
ell
a
n
d
also
k
ee
p
th
e
p
h
y
s
ical
m
ea
n
i
n
g
o
f
th
e
w
h
o
le
SF
E
p
r
o
ce
s
s
.
T
h
e
d
etailed
d
escr
ip
tio
n
o
n
p
r
ev
io
u
s
r
esear
ch
ap
p
l
y
in
g
A
N
FIS
an
d
t
h
e
h
y
b
r
id
o
f
it
f
o
r
y
ield
an
d
s
o
lu
b
il
it
y
p
r
ed
ictio
n
is
s
h
o
w
n
i
n
T
ab
le
3
.
Fig
u
r
e
5
.
Sch
e
m
atic
d
iag
r
a
m
o
f
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
m
o
d
el
b
y
[3
1
]
T
ab
le
3
.
C
o
m
p
ilatio
n
o
f
r
esear
ch
ap
p
l
y
in
g
h
y
b
r
id
m
o
d
el
-
AN
FIS
to
o
ls
f
o
r
p
r
ed
ictin
g
y
ield
an
d
s
o
lu
b
ilit
y
f
o
r
SF
E
M
o
d
e
l
S
a
mp
l
e
Ex
t
r
a
c
t
P
u
r
p
o
se
R
e
mark
s
R
e
f
e
r
e
n
c
e
s
A
N
F
I
S
S
o
l
i
d
c
o
mp
o
u
n
d
-
Est
i
m
a
t
i
o
n
o
f
so
l
u
b
i
l
i
t
y
T
h
e
i
n
p
u
t
p
a
r
a
me
t
e
r
s:
c
r
i
t
i
c
a
l
p
r
e
ssu
r
e
,
a
c
e
n
t
r
i
c
f
a
c
t
o
r
,
c
r
i
t
i
c
a
l
t
e
mp
e
r
a
t
u
r
e
a
n
d
mo
l
a
r
v
o
l
u
me
a
s
w
e
l
l
a
s t
h
e
o
p
e
r
a
t
i
n
g
t
e
mp
e
r
a
t
u
r
e
a
n
d
p
r
e
ssu
r
e
T
h
e
o
u
t
p
u
t
p
a
r
a
me
t
e
r
:
so
l
u
b
i
l
i
t
y
[
1
3
]
A
N
F
I
S
Pi
m
p
i
n
e
l
l
a
a
n
i
s
u
m
L
.
se
e
d
S
e
e
d
o
i
l
P
r
e
d
i
c
t
i
o
n
mass
o
f
e
x
t
r
a
c
t
T
h
e
i
n
p
u
t
p
a
r
a
me
t
e
r
s:
p
r
e
ssu
r
e
,
so
l
v
e
n
t
mas
s
f
l
o
w
r
a
t
e
,
a
n
d
e
x
t
r
a
c
t
i
o
n
t
i
me
T
h
e
o
u
t
p
u
t
p
a
r
a
me
t
e
r
:
mass
o
f
e
x
t
r
a
c
t
W
i
t
h
i
n
3
6
9
o
b
se
r
v
a
t
i
o
n
s,
2
7
7
o
b
se
r
v
a
t
i
o
n
s
w
e
r
e
u
se
d
t
o
t
r
a
i
n
t
h
e
n
e
t
w
o
r
k
,
a
n
d
t
h
e
r
e
mai
n
i
n
g
92
o
b
se
r
v
a
t
i
o
n
s
w
e
r
e
k
e
p
t
f
o
r
f
u
r
t
h
e
r
t
e
st
i
n
g
t
h
e
d
e
v
e
l
o
p
e
d
n
e
t
w
o
r
k
[
1
4
]
A
N
F
I
S
G
l
y
c
y
rrh
i
z
a
g
l
a
b
ra
L
.
G
l
y
c
y
r
r
h
i
z
i
c
a
c
i
d
(
G
A
)
M
o
d
e
l
i
n
g
t
h
e
r
e
c
o
v
e
r
y
o
f
e
x
t
r
a
c
t
i
o
n
I
n
d
e
p
e
n
d
e
n
t
v
a
r
i
a
b
l
e
s:
d
y
n
a
mi
c
t
i
me
(
t
)
,
p
r
e
ssu
r
e
(
P
)
,
t
e
mp
e
r
a
t
u
r
e
(
T
)
a
n
d
f
l
o
w
r
a
t
e
o
f
S
C
C
O
2
(
Q
)
.
D
e
p
e
n
d
e
n
t
v
a
r
i
a
b
l
e
:
R
e
c
o
v
e
r
y
o
f
G
A
[
1
9
]
A
N
F
I
S
P
o
me
g
r
a
n
a
t
e
S
e
e
d
o
i
l
S
i
mu
l
a
t
i
o
n
o
f
o
i
l
y
i
e
l
d
C
o
mp
a
r
i
n
g
t
h
e
d
a
t
a
o
b
t
a
i
n
e
d
b
e
t
w
e
e
n
A
N
N
a
n
d
A
N
F
I
S
mo
d
e
l
[
2
0
]
A
N
F
I
S
R
o
sa
d
a
m
a
sce
n
e
M
i
l
l
Q
u
e
r
c
e
t
i
n
M
o
d
e
l
i
n
g
t
h
e
r
e
c
o
v
e
r
y
o
f
e
x
t
r
a
c
t
i
o
n
I
n
d
e
p
e
n
d
e
n
t
v
a
r
i
a
b
l
e
s:
d
y
n
a
mi
c
t
i
me
(
t
)
,
p
r
e
ssu
r
e
(
P
)
,
t
e
mp
e
r
a
t
u
r
e
(
T
)
a
n
d
f
l
o
w
r
a
t
e
o
f
S
C
C
O
2
(
Q
)
.
D
e
p
e
n
d
e
n
t
v
a
r
i
a
b
l
e
:
R
e
c
o
v
e
r
y
C
o
mp
a
r
i
n
g
t
h
e
d
a
t
a
o
b
t
a
i
n
e
d
b
e
t
w
e
e
n
A
N
F
I
S
a
n
d
R
S
M
R
e
f
e
r
T
a
b
l
e
2
[
2
1
]
RBF
-
P
R
h
y
b
r
i
d
B
e
n
z
o
i
c
a
c
i
d
-
M
o
d
e
l
i
n
g
t
h
e
y
i
e
l
d
I
n
p
u
t
p
a
r
a
me
t
e
r
s:
Te
mp
e
r
a
t
u
r
e
,
p
r
e
ssu
r
e
a
n
d
o
n
e
o
t
h
e
r
f
a
c
t
o
r
s
O
u
t
p
u
t
p
a
r
a
me
t
e
r
:
y
i
e
l
d
r
a
t
e
M
a
t
h
e
ma
t
i
c
a
l
mo
d
e
l
:
P
e
n
g
-
R
o
b
i
n
so
n
mo
d
e
l
R
e
f
e
r
F
i
g
u
r
e
5
[3
1
]
M
a
t
h
e
ma
t
i
c
a
l
mo
d
e
l
-
A
N
F
I
S
h
y
b
r
i
d
G
r
e
e
n
t
e
a
Ep
i
g
a
l
l
o
c
a
t
e
c
h
i
n
g
a
l
l
a
t
e
(
EG
C
G
)
M
o
d
e
l
i
n
g
t
h
e
r
e
c
o
v
e
r
y
o
f
e
x
t
r
a
c
t
i
o
n
I
n
p
u
t
p
a
r
a
me
t
e
r
s:
d
y
n
a
mi
c
t
i
me
,
p
r
e
ssu
r
e
,
t
e
mp
e
r
a
t
u
r
e
a
n
d
f
l
o
w
r
a
t
e
o
f
S
C
-
C
O
2
O
u
t
p
u
t
p
a
r
a
me
t
e
r
:
mo
d
e
l
o
u
t
p
u
t
M
a
t
h
e
ma
t
i
c
a
l
mo
d
e
l
:
d
i
f
f
e
r
e
n
t
i
a
l
ma
ss
b
a
l
a
n
c
e
i
n
t
h
e
so
l
i
d
a
n
d
mo
b
i
l
e
p
h
a
se
s mo
d
e
l
R
e
f
e
r
F
i
g
u
r
e
4
[
1
5
]
5.
G
E
NE
T
I
C
A
L
G
O
RI
T
H
M
(
G
A)
Gen
etic
al
g
o
r
ith
m
s
ar
e
a
class
o
f
o
p
ti
m
izatio
n
p
r
o
g
r
a
m
s
th
at
ca
n
h
a
n
d
le
co
m
p
licated
p
r
o
b
lem
s
.
T
h
ey
co
n
s
is
t
o
f
a
r
an
d
o
m
-
s
e
ar
ch
m
eth
o
d
,
t
h
at
m
ad
e
e
f
f
i
cien
t
b
y
u
s
i
n
g
e
x
p
lo
r
ativ
e
s
ea
r
ch
.
T
h
e
m
e
th
o
d
r
ese
m
b
les
ev
o
l
u
tio
n
ar
y
d
ev
el
o
p
m
e
n
t
i
n
n
at
u
r
e,
u
s
i
n
g
“m
u
t
atio
n
”
a
n
d
“m
at
in
g
”.
I
n
co
n
tr
ast
to
e
x
p
er
t
s
y
s
te
m
s
n
o
h
e
u
r
is
tic
k
n
o
w
led
g
e
is
ap
p
lied
o
th
er
th
an
t
h
e
u
lti
m
ate
g
o
a
l
[3
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
I
n
t J
A
d
v
A
p
p
l Sci
,
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
: 1
1
7
–
124
122
I
n
2
0
1
6
,
a
g
r
o
u
p
o
f
r
esear
ch
er
s
in
I
r
an
d
id
an
o
p
tim
izatio
n
o
f
ess
en
tial
o
il
ex
tr
ac
tio
n
f
r
o
m
La
u
n
a
ea
a
ca
n
th
o
d
es B
o
is
s
u
s
in
g
g
e
n
eti
c
alg
o
r
ith
m
[3
3
]
.
I
n
t
h
eir
s
t
u
d
y
,
t
h
e
y
ap
p
lied
t
h
e
h
y
b
r
id
A
N
N
-
G
A
m
et
h
o
d
o
lo
g
y
w
h
er
eb
y
,
A
NN
m
o
d
el
w
a
s
u
s
ed
as
th
e
f
it
n
es
s
f
u
n
ctio
n
,
w
h
ic
h
m
ea
s
u
r
e
s
th
e
q
u
al
it
y
o
f
in
d
i
v
id
u
al
s
in
t
h
e
p
o
p
u
latio
n
.
T
h
e
m
o
d
el
w
as
th
e
n
u
s
ed
to
o
b
tain
t
h
e
o
p
ti
m
al
o
p
er
atio
n
co
n
d
itio
n
s
,
s
u
c
h
as
p
r
ess
u
r
e,
te
m
p
er
atu
r
e,
f
lo
w
r
ate,
an
d
c
o
s
o
lv
en
t
b
esid
es
d
eter
m
in
i
n
g
th
e
m
a
x
i
m
u
m
ex
tr
ac
tio
n
y
i
eld
o
f
ess
en
t
ial
o
il
f
r
o
m
L.
a
ca
n
th
o
d
es
.
T
h
e
g
en
e
r
al
p
r
o
ce
d
u
r
e
to
ap
p
ly
G
A
f
o
r
m
o
s
t
s
y
s
te
m
w
as
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
6
.
T
ab
le
4
h
as t
h
e
d
escr
ip
tio
n
o
f
p
r
ev
io
u
s
ap
p
licatio
n
o
f
G
A
in
S
FE
f
o
r
v
ar
io
u
s
m
ater
ial
s
.
Fig
u
r
e
6
.
Gen
etic
al
g
o
r
ith
m
p
r
o
ce
d
u
r
e
f
o
r
o
p
tim
izatio
n
p
r
o
ce
s
s
T
ab
le
4
.
Gen
etic
alg
o
r
ith
m
ap
p
licatio
n
f
o
r
o
p
ti
m
izatio
n
in
S
FE
S
a
mp
l
e
Ex
t
r
a
c
t
P
u
r
p
o
se
R
e
mark
s
R
e
f
e
r
e
n
c
e
s
L
a
u
n
a
e
a
a
c
a
n
t
h
o
d
e
s
B
o
i
ss
Esse
n
t
i
a
l
o
i
l
O
p
t
i
mi
z
a
t
i
o
n
o
f
e
x
t
r
a
c
t
i
o
n
y
i
e
l
d
A
N
N
m
o
d
e
l
w
a
s
u
se
d
a
s
t
h
e
f
i
t
n
e
ss
f
u
n
c
t
i
o
n
,
w
h
i
c
h
me
a
s
u
r
e
s
t
h
e
q
u
a
l
i
t
y
o
f
i
n
d
i
v
i
d
u
a
l
s i
n
t
h
e
p
o
p
u
l
a
t
i
o
n
[3
3
]
S
o
y
b
e
a
n
me
a
l
I
so
f
l
a
v
o
n
e
O
p
t
i
mi
z
a
t
i
o
n
o
f
p
r
o
f
i
t
a
b
i
l
i
t
y
T
h
e
o
b
j
e
c
t
i
v
e
f
u
n
c
t
i
o
n
o
f
t
h
i
s
st
u
d
y
i
s
p
r
o
f
i
t
a
b
i
l
i
t
y
w
h
i
c
h
i
s
mo
r
e
c
o
mp
r
e
h
e
n
si
v
e
t
h
a
n
t
h
e
c
u
mu
l
a
t
i
v
e
i
so
f
l
a
v
o
n
e
p
r
o
d
u
c
t
i
o
n
r
a
t
e
[
2
4
]
G
r
e
e
n
t
e
a
Ep
i
g
a
l
l
o
c
a
t
e
c
h
i
n
g
a
l
l
a
t
e
O
p
t
i
mi
z
a
t
i
o
n
o
f
e
x
t
r
a
c
t
i
o
n
r
e
c
o
v
e
r
y
T
h
e
f
i
t
n
e
ss
f
u
n
c
t
i
o
n
f
o
r
t
h
i
s
st
u
d
y
i
s
e
x
t
r
a
c
t
i
o
n
r
e
c
o
v
e
r
y
[
2
5
]
M
a
c
e
l
a
f
l
o
w
e
r
s
(
Ac
h
y
ro
c
l
i
n
e
sa
t
u
re
i
o
i
d
e
s
)
B
i
o
a
c
t
i
v
e
c
o
mp
o
u
n
d
D
e
t
e
r
mi
n
a
t
i
o
n
o
f
c
o
n
st
a
n
t
A
d
j
u
st
a
b
l
e
p
a
r
a
me
t
e
r
s,
K
,
a
,
a
n
d
b
,
w
e
r
e
d
e
t
e
r
mi
n
e
d
b
y
c
r
i
t
e
r
i
a
t
h
a
t
t
h
e
su
m
o
f
t
h
e
sq
u
a
r
e
s
o
f
t
h
e
d
i
f
f
e
r
e
n
c
e
b
e
t
w
e
e
n
t
h
e
e
x
p
e
r
i
me
n
t
a
l
e
x
t
r
a
c
t
i
o
n
y
i
e
l
d
a
n
d
t
h
e
p
r
e
d
i
c
t
e
d
e
x
t
r
a
c
t
i
o
n
y
i
e
l
d
b
y
t
h
e
mo
d
e
l
sh
o
u
l
d
b
e
m
i
n
i
mi
z
e
d
[2
8
]
S
o
l
i
d
c
o
mp
o
u
n
d
s
-
O
p
t
i
mi
z
a
t
i
o
n
o
f
t
h
e
r
a
d
i
u
s
o
f
i
n
f
l
u
e
n
c
e
o
f
F
I
S
T
h
e
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
(
G
A
)
,
w
h
i
c
h
i
s
a
n
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
,
w
a
s
i
mp
l
e
me
n
t
e
d
t
o
me
a
su
r
e
t
h
e
o
p
t
i
mu
m
v
a
l
u
e
o
f
r
a
d
i
u
s
o
f
i
n
f
l
u
e
n
c
e
o
f
F
I
S
p
a
r
a
me
t
e
r
[
1
3
]
F
e
r
u
l
a
g
a
a
n
g
u
l
a
t
e
-
O
p
t
i
mi
z
a
t
i
o
n
o
f
y
i
e
l
d
T
h
e
A
N
N
mo
d
e
l
c
o
u
p
l
e
d
w
i
t
h
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
(
G
A
)
w
a
s
u
se
d
t
o
g
e
n
e
r
a
t
e
t
h
e
o
p
t
i
m
a
l
v
a
l
u
e
[3
4
]
B
e
n
z
o
i
c
a
c
i
d
-
D
y
n
a
mi
c
o
p
t
i
m
i
z
a
t
i
o
n
o
f
p
r
o
c
e
ss
A
d
y
n
a
mi
c
o
p
t
i
m
i
z
a
t
i
o
n
mo
d
e
l
f
o
r
su
p
e
r
c
r
i
t
i
c
a
l
f
l
u
i
d
e
x
t
r
a
c
t
i
o
n
i
s
p
r
o
p
o
se
d
b
y
c
o
mb
i
n
i
n
g
a
t
r
a
n
sf
o
r
ma
t
i
o
n
b
a
se
d
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
a
n
d
t
h
e
P
e
n
g
-
R
o
b
i
n
so
n
e
q
u
a
t
i
o
n
o
f
st
a
t
e
[3
5
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
d
v
A
p
p
l Sci
I
SS
N:
2
2
5
2
-
8814
Ove
r
view o
f so
ft in
tellig
en
t c
o
mp
u
tin
g
tech
n
iq
u
e
fo
r
s
u
p
ercr
itica
l flu
id
ex
tr
a
ctio
n
(
S
itin
o
o
r
A
d
eib
I
d
r
is
)
123
6.
CO
NCLU
SI
O
N
Ov
er
all,
th
e
ap
p
licatio
n
o
f
s
m
ar
t
s
y
s
te
m
o
r
ar
tif
icial
tec
h
n
iq
u
e
to
m
o
d
el
an
d
s
i
m
u
late
a
ch
e
m
ica
l
p
r
o
ce
s
s
h
as
b
ee
n
d
o
n
e
in
S
FE
p
r
o
ce
s
s
to
g
eth
er
w
it
h
R
SM
m
et
h
o
d
.
S
m
ar
t
s
y
s
te
m
m
o
d
el
s
g
e
n
er
alize
th
e
e
x
p
er
i
m
e
n
tal
r
es
u
lt
an
d
p
r
esen
t p
r
o
ce
s
s
b
eh
a
v
io
r
an
d
f
in
all
y
p
r
ed
ict
an
d
e
s
ti
m
ate
p
r
o
b
le
m
.
T
h
e
m
o
d
el
ca
n
b
e
ap
p
lied
in
d
iv
id
u
a
ll
y
o
r
b
y
co
m
b
i
n
i
n
g
t
w
o
o
r
m
o
r
e
m
o
d
e
ls
ca
lled
a
s
h
y
b
r
id
to
ac
h
ie
v
e
th
e
b
est
est
i
m
at
io
n
an
d
p
r
ed
ictio
n
d
ata.
T
h
e
ap
p
r
o
p
r
iate
m
o
d
el
is
b
en
ef
icial
i
n
th
e
d
ev
elo
p
m
e
n
t
o
f
n
e
w
p
r
o
d
u
cts
b
y
s
a
v
i
n
g
ex
p
er
i
m
e
n
tal
ti
m
e
a
n
d
co
s
t.
Ho
w
e
v
er
,
r
esear
ch
a
n
d
s
t
u
d
y
o
n
d
y
n
a
m
ic
p
r
o
ce
s
s
f
o
r
S
FE
u
s
in
g
ar
ti
f
icial
tech
n
iq
u
e
is
lac
k
i
n
g
an
d
th
e
ar
ea
is
r
ec
o
m
m
e
n
d
ed
f
o
r
f
u
r
th
er
r
esear
ch
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
li
k
e
to
t
h
a
n
k
Mi
n
is
tr
y
o
f
Hi
g
h
er
E
d
u
ca
t
io
n
(
MO
HE
)
a
n
d
Un
iv
er
s
iti
T
ek
n
o
lo
g
i
MA
R
A
,
f
o
r
p
r
o
v
id
in
g
f
i
n
a
n
ci
al
s
u
p
p
o
r
t.
Mo
r
eo
v
er
,
th
e
au
th
o
r
s
w
o
u
ld
lik
e
to
t
h
an
k
U
n
i
v
er
s
iti
Keb
a
n
g
s
aa
n
Ma
la
y
s
ia
f
o
r
p
r
o
v
id
in
g
r
esear
ch
f
ac
i
liti
es.
RE
F
E
R
E
NC
E
S
[1
]
A
.
B.
Ku
rh
e
,
S
.
S
.
S
a
to
n
k
a
r,
P
.
B.
Kh
a
n
a
le,
a
n
d
S
.
A
sh
o
k
,
“
S
o
f
t
Co
m
p
u
ti
n
g
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
s,
”
BIOINF
O
S
o
ft
Co
mp
u
t
.
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
5
–
7
,
2
0
1
1
.
[2
]
S
.
Ra
jas
e
k
a
ra
n
a
n
d
G
.
A
.
V
P
a
i,
Ne
u
ra
l
Ne
two
rk
s,
Fu
zz
y
S
y
ste
ms
a
n
d
Evo
l
u
ti
o
n
a
ry
Al
g
o
rith
ms
:
S
y
n
th
e
sis
a
n
d
Ap
p
li
c
a
ti
o
n
s
.
P
RENT
ICE
-
HA
LL
OF
IND
IA
,
2
0
1
7
.
[3
]
B.
P
a
v
li
c
,
O.
Be
ra
,
S
.
V
i
d
o
v
ic,
L
.
Ili
c
,
a
n
d
Z.
Zek
o
v
ic,
“
Ex
tra
c
t
io
n
k
in
e
ti
c
s
a
n
d
A
NN
si
m
u
latio
n
o
f
su
p
e
rc
rit
ica
l
f
lu
id
e
x
trac
ti
o
n
o
f
sa
g
e
h
e
rb
a
l
d
u
st,”
J
.
S
u
p
e
rc
rit.
Fl
u
id
s
,
v
o
l.
1
3
0
,
p
p
.
3
2
7
–
3
3
6
,
2
0
1
7
.
[4
]
P
.
M
it
ra
,
P
.
C.
Ba
rm
a
n
,
a
n
d
K.
S
.
Ch
a
n
g
,
“
Co
u
m
a
rin
Ex
trac
ti
o
n
f
ro
m
Cu
sc
u
ta
re
f
l
e
x
a
u
sin
g
S
u
p
e
rc
rit
ica
l
F
lu
i
d
Ca
rb
o
n
Dio
x
id
e
a
n
d
De
v
e
lo
p
m
e
n
t
o
f
a
n
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
M
o
d
e
l
to
P
re
d
ict
th
e
Co
u
m
a
r
in
Yie
ld
,
”
Fo
o
d
Bi
o
p
r
o
c
e
ss
T
e
c
h
n
o
l
.
,
v
o
l.
4
,
n
o
.
5
,
p
p
.
7
3
7
–
7
4
4
,
2
0
1
1
.
[5
]
J.
Yin
,
Q.
Xu
,
W
.
W
e
i,
a
n
d
A
.
Wan
g
,
“
Ex
p
e
rime
n
ts
a
n
d
Nu
m
e
rica
l
S
im
u
latio
n
s o
f
S
u
p
e
rc
rit
ica
l
F
l
u
id
Ex
trac
ti
o
n
f
o
r
Hip
p
o
p
h
a
e
r
h
a
m
n
o
id
e
s L
S
e
e
d
Oil
Ba
se
d
o
n
A
rti
f
icia
l,
”
In
d
.
En
g
.
Ch
e
m.
Res
,
v
o
l.
4
4
,
p
p
.
7
4
2
0
–
7
4
2
7
,
2
0
0
5
.
[6
]
L
.
M
.
S
a
ll
e
h
,
S
.
E
.
R.
A
b
e
l,
G
.
Zah
e
d
i,
R.
A
.
Ra
h
m
a
n
,
H.
M
.
Na
sir,
a
n
d
S
.
A
.
S
.
F
a
u
a
’a
d
,
“
Op
ti
m
iza
ti
o
n
o
f
su
p
e
rc
rit
ica
l
c
a
rb
o
n
d
i
o
x
id
e
e
x
trac
ti
o
n
o
f
q
u
e
rc
u
s i
n
f
e
c
to
ria o
il
,
”
J
.
T
e
k
n
o
l.
,
v
o
l.
7
4
,
n
o
.
7
,
p
p
.
7
9
–
8
6
,
2
0
1
5
.
[7
]
P
.
Da
v
o
o
d
i,
S
.
M
.
G
h
o
re
ish
i
,
a
n
d
A
.
He
d
a
y
a
ti
,
“
Op
ti
m
iz
a
ti
o
n
o
f
su
p
e
rc
rit
ica
l
e
x
trac
ti
o
n
o
f
g
a
le
g
in
e
f
ro
m
G
a
le
g
a
o
f
f
i
c
in
a
li
s
L
.
:
Ne
u
ra
l
n
e
t
w
o
rk
m
o
d
e
li
n
g
a
n
d
e
x
p
e
rime
n
tal
o
p
ti
m
iz
a
ti
o
n
v
ia
re
sp
o
n
se
su
rf
a
c
e
m
e
th
o
d
o
l
o
g
y
,
”
Ko
re
a
n
J
.
Ch
e
m.
En
g
.
,
v
o
l.
3
2
,
n
o
.
4
,
p
p
.
1
–
1
2
,
2
0
1
6
.
[8
]
S
.
M
.
G
h
o
re
ish
i
a
n
d
E
.
He
id
a
ri,
“
Ex
trac
ti
o
n
o
f
Ep
ig
a
ll
o
c
a
tec
h
in
-
3
-
g
a
ll
a
te
f
ro
m
g
re
e
n
tea
v
ia
su
p
e
rc
rit
ica
l
f
lu
id
tec
h
n
o
l
o
g
y
:
N
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
li
n
g
a
n
d
re
sp
o
n
se
su
rf
a
c
e
o
p
ti
m
iza
ti
o
n
,
”
J
.
S
u
p
e
rc
rit.
Fl
u
id
s
,
v
o
l.
7
4
,
p
p
.
1
2
8
-
1
3
6
,
2
0
1
3
.
[9
]
A
.
M
.
A
b
b
a
s
Ka
ri
m
a
n
d
A
.
K.
M
u
tl
a
g
,
“
Co
m
p
a
riso
n
S
tu
d
y
f
o
r
th
e
S
o
l
u
b
il
it
y
P
re
d
ictio
n
o
f
P
h
e
n
a
n
t
h
re
n
e
in
S
u
p
e
rc
rit
ica
l
CO2
e
n
train
d
w
it
h
n
-
p
e
n
tan
e
w
h
e
n
u
sin
g
Eq
u
a
ti
o
n
o
f
S
tate
a
n
d
A
rti
f
ici
a
l
Ne
u
ra
l
n
e
t
w
o
rk
s,”
Emira
tes
J
.
En
g
.
Res
e
a
c
rh
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
8
1
–
9
0
,
2
0
1
1
.
[1
0
]
A
.
Am
in
ian
,
“
Esti
m
a
ti
n
g
th
e
so
lu
b
il
it
y
o
f
d
i
ff
e
re
n
t
so
lu
tes
in
su
p
e
rc
rit
ica
l
CO2
c
o
v
e
rin
g
a
w
id
e
r
a
n
g
e
o
f
o
p
e
ra
ti
n
g
c
o
n
d
i
ti
o
n
s b
y
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
ls,”
J
.
S
u
p
e
rc
rit.
Fl
u
id
s
,
v
o
l.
1
2
5
,
p
p
.
7
9
–
8
7
,
2
0
1
7
.
[1
1
]
B.
V
a
f
e
ri,
M
.
Ka
rim
i,
M
.
Az
izi,
a
n
d
H.
Esm
a
e
il
i
,
“
Co
m
p
a
riso
n
b
e
tw
e
e
n
th
e
a
rti
f
i
c
ial
n
e
u
ra
l
n
e
tw
o
rk
,
S
A
F
T
a
n
d
P
R
S
V
a
p
p
ro
a
c
h
in
o
b
tain
i
n
g
th
e
so
lu
b
il
it
y
o
f
so
li
d
a
ro
m
a
ti
c
c
o
m
p
o
u
n
d
s
i
n
su
p
e
rc
rit
ica
l
c
a
rb
o
n
d
i
o
x
id
e
,
”
J
.
S
u
p
e
rc
rit.
Fl
u
i
d
s
,
v
o
l
.
7
7
,
p
p
.
4
4
–
5
1
,
2
0
1
3
.
[1
2
]
S
.
S
h
e
u
,
M
.
Ja
n
g
,
C.
W
a
n
g
,
C.
T
sa
i,
a
n
d
Y.
Hs
u
e
h
,
“
De
tc2
0
0
8
-
4
9
1
8
2
S
im
u
latio
n
a
n
d
A
p
p
li
c
a
ti
o
n
o
f
F
u
z
z
y
T
h
e
o
r
y
f
o
r
S
u
p
e
rc
rit
ica
l
Ca
rb
o
n
,
”
i
n
Pr
o
c
e
e
d
in
g
s
o
f
t
h
e
AS
M
E
2
0
0
8
,
2
0
0
8
.
[1
3
]
M
.
R.
Da
d
k
h
a
h
e
t
a
l
.
,
“
P
re
d
icti
o
n
o
f
so
lu
b
il
it
y
o
f
so
li
d
c
o
m
p
o
u
n
d
s
in
su
p
e
rc
rit
ica
l
CO
2
u
sin
g
a
c
o
n
n
e
c
ti
o
n
ist
sm
a
rt
tec
h
n
iq
u
e
,
”
J
.
S
u
p
e
rc
rit.
F
lu
i
d
s
,
v
o
l.
1
2
0
,
p
p
.
1
8
1
–
1
9
0
,
2
0
1
7
.
[1
4
]
M
.
Da
v
o
o
d
y
,
G
.
Zah
e
d
i,
M
.
Big
lari,
M
.
A
.
A
.
M
e
irele
s,
a
n
d
A
.
B
a
h
a
d
o
ri,
“
Ex
p
e
rt
a
n
d
g
ra
y
b
o
x
m
o
d
e
li
n
g
o
f
h
ig
h
-
p
re
ss
u
re
li
q
u
i
d
c
a
rb
o
n
d
i
o
x
id
e
e
x
trac
ti
o
n
o
f
P
im
p
in
e
ll
a
a
n
is
u
m
L
.
se
e
d
,
”
J
.
S
u
p
e
rc
rit.
F
lu
id
s
,
v
o
l.
7
2
,
p
p
.
2
1
3
–
2
2
2
,
2
0
1
2
.
[1
5
]
E.
He
id
a
ri
a
n
d
S
.
M
.
G
h
o
re
ish
i,
“
P
re
d
icti
o
n
o
f
su
p
e
rc
rit
ica
l
e
x
tra
c
ti
o
n
re
c
o
v
e
ry
o
f
E
G
C
G
u
sin
g
h
y
b
rid
o
f
A
d
a
p
ti
v
e
Ne
u
ro
-
F
u
z
z
y
In
f
e
re
n
c
e
S
y
ste
m
a
n
d
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
l,
”
J
.
S
u
p
e
rc
rit.
Fl
u
i
d
s
,
v
o
l
.
8
2
,
p
p
.
1
5
8
–
1
6
7
,
2
0
1
3
.
[1
6
]
S
.
X.
Ya
n
g
,
J.
Zen
g
,
H.
L
i,
X
.
Yu
a
n
,
a
n
d
M
.
M
e
n
g
,
“
M
o
d
e
li
n
g
o
f
S
u
p
e
rc
rit
ica
l
F
l
u
id
Ex
trac
ti
o
n
Us
i
n
g
a
n
In
teg
ra
ted
S
o
f
t
Co
m
p
u
ti
n
g
a
n
d
C
o
n
v
e
n
ti
o
a
n
l
A
p
p
ro
a
c
h
,
”
i
n
Pr
o
c
e
e
d
in
g
s
o
f
t
h
e
2
0
0
3
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ro
b
o
ti
c
s,
I
n
telli
g
e
n
t
S
y
ste
ms
a
n
d
S
ig
n
a
l
Pro
c
e
ss
in
g
,
p
p
.
6
6
8
–
6
7
3
,
2
0
0
3
.
[1
7
]
S
.
X
.
Ya
n
g
,
H.
L
i,
a
n
d
J.
S
h
i,
“
M
o
d
e
li
n
g
o
f
S
u
p
e
rc
rit
ica
l
F
lu
i
d
Ex
t
ra
c
ti
o
n
b
y
Ne
u
ra
l
Ne
t
w
o
rk
s,”
In
tell.
Au
t
o
m.
S
o
f
t
Co
mp
u
t
.
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
3
–
1
2
,
2
0
0
3
.
[1
8
]
J.
S
a
rg
o
lza
e
i,
M
.
Ha
g
h
ig
h
i
A
sl,
a
n
d
A
.
H.
M
o
g
h
a
d
d
a
m
,
“
P
re
d
ictio
n
o
f
S
u
p
e
r
Crit
ica
l
Oil
Ex
trac
t
io
n
Yie
l
d
Us
in
g
S
in
g
le an
d
Co
m
b
in
e
d
I
n
telli
g
e
n
t
S
y
st
e
m
s,”
Glo
b
.
Per
sp
e
c
t.
Arti
f.
I
n
tell.
,
v
o
l.
1
,
n
o
.
2
,
p
p
.
1
5
–
2
2
,
2
0
1
3
.
[1
9
]
A
.
He
d
a
y
a
ti
a
n
d
S
.
M
.
G
h
o
re
ish
i,
“
A
rti
f
icia
l
N
e
u
ra
l
Ne
t
w
o
rk
a
n
d
A
d
a
p
ti
v
e
Ne
u
r
o
-
F
u
z
z
y
In
terfa
c
e
S
y
st
e
m
M
o
d
e
li
n
g
o
f
S
u
p
e
rc
rit
ica
l
CO<
in
f>
2
<
/i
n
f
>
Ex
trac
ti
o
n
o
f
G
l
y
c
y
rrh
izic
Ac
id
fro
m
G
l
y
c
y
rrh
iza
g
l
a
b
ra
L
,
”
Ch
e
m.
Pro
d
.
Pro
c
e
ss
M
o
d
e
l.
,
v
o
l
.
1
1
,
n
o
.
3
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
I
n
t J
A
d
v
A
p
p
l Sci
,
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
: 1
1
7
–
124
124
[2
0
]
J.
S
a
rg
o
lza
e
i
a
n
d
A
.
H.
M
o
g
h
a
d
d
a
m
,
“
P
re
d
ictin
g
th
e
y
ield
o
f
p
o
m
e
g
ra
n
a
te
o
il
f
ro
m
su
p
e
rc
rit
ica
l
e
x
trac
ti
o
n
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
t
w
o
rk
s
a
n
d
a
n
a
d
a
p
ti
v
e
-
n
e
tw
o
rk
-
b
a
se
d
f
u
z
z
y
i
n
f
e
re
n
c
e
s
y
ste
m
,
”
Fro
n
t.
Ch
e
m.
S
c
i.
En
g
.
,
v
o
l.
7
,
n
o
.
3
,
p
p
.
3
5
7
–
3
6
5
,
2
0
1
3
.
[2
1
]
S
.
M
.
G
h
o
re
ish
i,
A
.
He
d
a
y
a
ti
,
a
n
d
S
.
O.
M
o
u
sa
v
i,
“
Qu
e
rc
e
ti
n
e
x
trac
ti
o
n
f
ro
m
Ro
sa
d
a
m
a
sc
e
n
a
M
il
l
v
ia
su
p
e
rc
rit
ica
l
CO2
:
Ne
u
ra
l
n
e
tw
o
rk
a
n
d
a
d
a
p
ti
v
e
n
e
u
ro
f
u
z
z
y
in
terf
a
c
e
s
y
ste
m
m
o
d
e
li
n
g
a
n
d
re
sp
o
n
se
su
rf
a
c
e
o
p
ti
m
iza
ti
o
n
,
”
J
.
S
u
p
e
rc
rit.
Fl
u
i
d
s
,
v
o
l
.
1
1
2
,
p
p
.
5
7
–
6
6
,
2
0
1
6
.
[2
2
]
E.
Ra
h
im
i,
J.
M
.
P
ra
d
o
,
G
.
Zah
e
d
i,
a
n
d
M
.
A
.
A
.
M
e
irele
s,
“
Ch
a
m
o
m
il
e
e
x
trac
ti
o
n
w
it
h
su
p
e
rc
rit
ica
l
c
a
rb
o
n
d
io
x
id
e
:
M
a
th
e
m
a
ti
c
a
l
m
o
d
e
li
n
g
a
n
d
o
p
ti
m
iz
a
ti
o
n
,
”
J
.
S
u
p
e
rc
rit.
F
lu
i
d
s
,
v
o
l.
5
6
,
p
p
.
8
0
–
8
8
,
2
0
1
1
.
[2
3
]
G
.
S
o
d
e
if
ian
,
S
.
A
.
S
a
jad
ian
,
a
n
d
N.
S
a
a
d
a
ti
A
rd
e
sta
n
i,
“
Ex
p
e
rime
n
tal
o
p
t
im
iza
ti
o
n
a
n
d
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
li
n
g
o
f
th
e
su
p
e
rc
rit
ica
l
f
lu
id
e
x
trac
ti
o
n
o
f
e
s
se
n
ti
a
l
o
il
f
ro
m
Er
y
n
g
iu
m
b
il
lard
ieri:
A
p
p
li
c
a
ti
o
n
o
f
si
m
u
late
d
a
n
n
e
a
li
n
g
(S
A
)
a
lg
o
rit
h
m
,
”
J
.
S
u
p
e
rc
rit.
Fl
u
i
d
s
,
v
o
l.
1
2
7
,
n
o
.
A
p
ril
,
p
p
.
1
4
6
–
1
5
7
,
2
0
1
7
.
[2
4
]
K.
L
u
m
m
a
e
te
e
,
H.
M
.
Ku
,
W
.
W
o
n
g
ra
t,
a
n
d
A
.
El
k
a
m
e
l,
“
O
p
ti
m
iza
ti
o
n
o
f
su
p
e
rc
rit
ica
l
f
lu
i
d
e
x
trac
ti
o
n
o
f
iso
f
lav
o
n
e
f
ro
m
so
y
b
e
a
n
m
e
a
l,
”
Ca
n
.
J
.
Ch
e
m.
E
n
g
.
,
v
o
l
.
9
5
,
n
o
.
6
,
p
p
.
1
1
4
1
–
1
1
4
9
,
2
0
1
7
.
[2
5
]
S
.
M
.
G
h
o
re
ish
i
a
n
d
E.
He
id
a
ri,
“
Ex
trac
ti
o
n
o
f
e
p
ig
a
ll
o
c
a
tec
h
in
g
a
ll
a
te
f
ro
m
g
r
e
e
n
tea
v
ia
m
o
d
ifi
e
d
su
p
e
rc
rit
ica
l
CO2
:
Ex
p
e
rim
e
n
tal,
m
o
d
e
l
in
g
a
n
d
o
p
ti
m
iza
ti
o
n
,
”
J
.
S
u
p
e
rc
rit.
Fl
u
i
d
s
,
v
o
l.
7
2
,
p
p
.
3
6
–
4
5
,
2
0
1
2
.
[2
6
]
G
.
Zah
e
d
i,
A
.
El
k
a
m
e
l,
A
.
L
o
h
i,
a
n
d
T
.
Ha
tam
i,
“
Op
ti
m
iza
ti
o
n
o
f
su
p
e
rc
rit
ica
l
e
x
trac
ti
o
n
o
f
n
im
b
in
f
ro
m
n
e
e
m
se
e
d
s in
p
re
se
n
c
e
o
f
m
e
th
a
n
o
l
a
s c
o
-
so
lv
e
n
t,
”
J
.
S
u
p
e
rc
rit.
Fl
u
i
d
s
,
v
o
l.
5
5
,
n
o
.
1
,
p
p
.
1
4
2
–
1
4
8
,
2
0
1
0
.
[2
7
]
A
.
K.
V
e
rm
a
,
Pro
c
e
ss
M
o
d
e
ll
in
g
a
n
d
S
im
u
la
ti
o
n
in
Ch
e
mic
a
l
,
Bi
o
c
h
e
mic
a
l
a
n
d
En
v
ir
o
n
me
n
t
a
l
En
g
in
e
e
rin
g
.
CRC P
re
ss
,
2
0
1
4
.
[2
8
]
T
.
H
a
ta
m
i,
R.
N.
Ca
v
a
lca
n
ti
,
T.
M
.
T
a
k
e
u
c
h
i,
a
n
d
M
.
A
.
A
.
M
e
irele
s
,
“
T
h
e
Jo
u
rn
a
l
o
f
S
u
p
e
rc
rit
ica
l
F
lu
id
s
S
u
p
e
rc
rit
ica
l
f
lu
id
e
x
trac
ti
o
n
o
f
b
io
a
c
ti
v
e
c
o
m
p
o
u
n
d
s
f
ro
m
M
a
c
e
la
(Ac
h
y
ro
c
li
n
e
sa
tu
re
io
id
e
s)
f
lo
w
e
rs:
Kin
e
ti
c
,
e
x
p
e
ri
m
e
n
ts an
d
m
o
d
e
li
n
g
,
”
J
.
S
u
p
e
rc
rit.
Fl
u
i
d
s
,
v
o
l
.
6
5
,
p
p
.
7
1
-
7
7
,
2
0
1
2
.
[2
9
]
H.
L
i
a
n
d
S
.
X
.
Ya
n
g
,
“
M
o
d
e
ll
i
n
g
o
f
su
p
e
rc
rit
ica
l
f
lu
id
e
x
trac
ti
o
n
b
y
h
y
b
rid
P
e
n
g
-
Ro
b
in
so
n
e
q
u
a
ti
o
n
o
f
sta
te
a
n
d
g
e
n
e
ti
c
a
lg
o
rit
h
m
s,”
Bi
o
sy
st.
En
g
.
,
v
o
l.
8
6
,
n
o
.
1
,
p
p
.
1
7
-
2
5
,
2
0
0
3
.
[3
0
]
D.
C.
P
sic
h
o
g
io
s
a
n
d
L
.
H.
Un
g
a
r,
“
A
h
y
b
rid
n
e
u
ra
l
n
e
tw
o
rk
?
?
?
f
irst
p
rin
c
ip
les
a
p
p
ro
a
c
h
t
o
p
ro
c
e
ss
m
o
d
e
li
n
g
,
”
AICh
E
J
.
,
v
o
l.
3
8
,
n
o
.
1
0
,
p
p
.
1
4
9
9
-
1
5
1
1
,
1
9
9
2
.
[3
1
]
J.
Zen
g
a
n
d
S
.
X
.
Ya
n
g
,
“
Op
ti
m
a
l
Co
n
tr
o
l
o
f
S
u
p
e
rc
rit
ica
l
F
l
u
id
Ex
trac
ti
o
n
w
it
h
a
H
y
b
rid
M
o
d
e
l,
”
in
Pro
c
e
e
d
in
g
s o
f
th
e
2
0
0
3
IEE
E
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
In
tell
ig
e
n
t
Co
n
tro
l
,
2
0
0
3
.
[3
2
]
G
.
Ka
te
m
a
n
,
“
Da
ta
Ha
n
d
li
n
g
in
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
”
in
Da
t
a
Ha
n
d
li
n
g
in
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
L
.
M
.
C
.
Bu
y
d
e
n
s a
n
d
P
.
J
.
S
c
h
o
e
n
m
a
k
e
r
s,
Ed
s.
E
lse
v
ier L
td
,
1
9
9
3
,
p
p
.
2
8
1
-
3
1
0
.
[3
3
]
G
.
S
o
d
e
if
ian
,
S
.
A
.
S
a
jad
ian
,
a
n
d
N.
S
a
a
d
a
ti
A
rd
e
sta
n
i,
“
Op
ti
m
i
z
a
ti
o
n
o
f
e
ss
e
n
ti
a
l
o
il
e
x
trac
ti
o
n
f
ro
m
L
a
u
n
a
e
a
a
c
a
n
th
o
d
e
s
B
o
iss:
Util
iza
ti
o
n
o
f
su
p
e
rc
rit
ica
l
c
a
rb
o
n
d
i
o
x
id
e
a
n
d
c
o
s
o
lv
e
n
t,
”
J
.
S
u
p
e
rc
rit.
F
lu
id
s
,
v
o
l.
1
1
6
,
p
p
.
4
6
-
5
6
,
2
0
1
6
.
[3
4
]
G
.
S
o
d
e
if
ian
,
S
.
A
.
S
a
jad
ian
,
a
n
d
N.
S
a
a
d
a
ti
A
rd
e
sta
n
i,
“
Ev
a
lu
a
t
io
n
o
f
th
e
re
sp
o
n
se
su
rf
a
c
e
a
n
d
h
y
b
rid
a
rti
f
icia
l
ne
u
ra
l
n
e
tw
o
rk
-
g
e
n
e
ti
c
a
lg
o
rit
h
m
m
e
th
o
d
o
lo
g
ies
t
o
d
e
term
in
e
e
x
trac
ti
o
n
y
ield
o
f
F
e
ru
lag
o
a
n
g
u
lata
th
r
o
u
g
h
su
p
e
rc
rit
ica
l
f
lu
id
,
”
J
.
T
a
iw
a
n
In
s
t.
Ch
e
m.
E
n
g
.
,
v
o
l.
6
0
,
p
p
.
1
6
5
–
1
7
3
,
2
0
1
6
.
[3
5
]
S
.
X.
Ya
n
g
,
J.
Zen
g
,
a
n
d
G
.
W
a
n
g
,
Extra
c
ti
o
n
Us
i
n
g
Dy
n
a
mic
Ge
n
e
ti
c
Al
g
o
rit
h
m B
a
se
d
Op
ti
mis
a
ti
o
n
,
v
o
l
.
3
8
,
n
o
.
1
.
IF
A
C,
2
0
0
3
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
S
it
in
o
o
r
A
d
e
ib
Id
ris
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r’s
a
n
d
m
a
ste
r’s
d
e
g
re
e
s
in
c
h
e
m
ica
l
e
n
g
in
e
e
rin
g
f
ro
m
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
(UiT
M
),
S
h
a
h
A
la
m
,
S
e
lan
g
o
r,
M
a
la
y
sia
.
S
h
e
is
a
P
h
D
stu
d
e
n
t
a
t
th
e
De
p
a
rtm
e
n
t
o
f
Ch
e
m
ica
l
E
n
g
in
e
e
rin
g
a
n
d
P
r
o
c
e
ss
,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
n
d
Bu
i
lt
En
v
iro
n
m
e
n
t,
a
t
Un
iv
e
rsiti
Ke
b
a
n
g
sa
a
n
M
a
la
y
sia
(
UK
M
),
Ba
n
g
i,
S
e
lan
g
o
r,
M
a
la
y
sia
.
He
r
re
se
a
rc
h
is i
n
th
e
f
ield
o
f
su
p
e
rc
rit
ica
l
f
lu
id
e
x
trac
ti
o
n
.
M
a
stu
ra
h
M
a
rk
o
m
is
a
n
a
ss
o
c
iate
p
ro
f
e
ss
o
r
o
f
Ch
e
m
i
c
a
l
En
g
in
e
e
rin
g
a
t
th
e
De
p
a
rtm
e
n
t
o
f
Ch
e
m
ic
a
l
En
g
in
e
e
rin
g
a
n
d
P
ro
c
e
ss
,
UK
M
.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
D i
n
2
0
0
7
a
n
d
m
a
ste
r’s d
e
g
re
e
s in
c
h
e
m
i
c
a
l
e
n
g
in
e
e
rin
g
f
ro
m
Un
iv
e
rsiti
M
a
la
y
a
(
UM)
i
n
1
9
9
8
.
He
r
re
se
a
rc
h
in
tere
st
a
re
se
p
a
ra
ti
o
n
tec
h
n
o
l
o
g
y
a
n
d
su
p
e
rc
rit
ica
l
f
lu
id
e
x
trac
ti
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.