I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI)
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
201
9
,
p
p
.
2
4
4
~
2
5
1
I
SS
N:
2
2
5
2
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
8
.i
3
.
p
p
2
4
4
-
2
5
1
244
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
AI
Ex
pert
ju
dg
m
ent
Z
-
Nu
m
bers
as
a r
a
nk
ing
in
dica
tor f
o
r
hiera
rchica
l f
u
zzy lo
g
ic sy
ste
m
Sh
a
if
ul B
a
kh
t
ia
r
bin
Ro
dz
ma
n
1
,
No
r
m
a
ly
K
a
m
a
l I
s
m
a
il
2
,
Nura
zz
a
h Abd Ra
h
m
a
n
3
,
S
y
ed
Ah
m
a
d
Alj
un
id
4
,
Z
ulh
il
m
i M
o
ha
m
e
d No
r
5
,
K
u
M
uh
a
mm
a
d Na
i
m
K
u K
ha
lif
6
1,
2,
3,
4
F
a
c
u
lt
y
o
f
Co
m
p
u
ter &
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
Tek
n
o
l
o
g
i
M
A
RA
,
S
h
a
h
A
la
m
,
M
a
la
y
sia
5
F
a
k
u
lt
i
P
e
n
g
a
ji
a
n
Q
u
ra
n
d
a
n
S
u
n
n
a
h
,
U
n
iv
e
rsiti
S
a
in
s Isla
m
M
a
la
y
sia
,
Ba
n
d
a
r
Ba
ru
Nilai
,
M
a
lay
sia
6
F
a
c
u
lt
y
o
f
In
d
u
strial
S
c
ien
c
e
s a
n
d
T
e
c
h
n
o
lo
g
y
,
Un
iv
e
rsiti
M
a
lay
sia
P
a
h
a
n
g
,
M
a
lay
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
pr
30
,
2
0
1
9
R
ev
i
s
ed
J
u
l
30
,
2
0
1
9
A
cc
ep
ted
A
u
g
2
2
,
2
0
1
9
In
th
is
a
rti
c
le,
th
e
re
se
a
rc
h
e
rs
m
a
i
n
c
o
n
tri
b
u
ti
o
n
is
to
in
v
e
stig
a
te
th
re
e
f
a
c
to
rs
w
h
ich
m
a
y
c
o
rre
late
in
im
p
lem
e
n
tatio
n
o
f
Ex
p
e
rt
Ju
d
g
m
e
n
t
Z
-
N
u
m
b
e
rs
a
s
n
e
w
F
u
z
z
y
L
o
g
ic
Ra
n
k
in
g
In
d
ica
to
r
su
c
h
a
s:
e
x
p
e
rt
re
le
v
a
n
c
e
ju
d
g
m
e
n
t
o
r
sc
o
re
,
th
e
e
x
p
e
rt
c
o
n
f
id
e
n
c
e
a
n
d
t
h
e
lev
e
l
o
f
e
x
p
e
rti
se
.
T
h
e
Ex
p
e
rt
Ju
d
g
m
e
n
t
Z
-
Nu
m
b
e
rs
t
h
e
n
w
il
l
b
e
a
n
i
n
p
u
t
to
th
e
Hie
ra
rc
h
ica
l
F
u
z
z
y
L
o
g
ic
S
y
st
e
m
o
f
Do
m
a
in
S
p
e
c
if
ic
Tex
t
Re
tri
e
v
a
l,
a
lo
n
g
w
it
h
o
t
h
e
r
i
n
d
ica
to
r
s
su
c
h
a
s
On
to
l
o
g
y
BM
2
5
S
c
o
re
,
F
a
b
rica
t
io
n
Ra
te,
S
h
ia
Ra
te
a
n
d
P
o
sit
iv
e
Ra
te
o
f
h
a
d
it
h
d
o
c
u
m
e
n
t.
T
h
e
re
su
lt
s
sh
o
w
e
d
,
th
e
p
ro
p
o
se
d
sy
ste
m
,
w
it
h
th
e
a
d
d
it
i
o
n
a
l
n
e
w
in
d
ica
to
r
o
f
Ex
p
e
rt
Ju
d
g
m
e
n
t
Z
-
Nu
m
b
e
rs,
m
a
y
i
m
p
ro
v
e
th
e
o
rig
in
a
l
BM
2
5
ra
n
k
in
g
f
u
n
c
ti
o
n
,
b
y
y
ield
in
g
b
e
tt
e
r
re
su
lt
s
o
n
2
6
q
u
e
ries
,
o
n
a
ll
e
v
a
lu
a
ti
o
n
m
e
tri
c
s
th
a
t
a
r
e
m
e
a
su
re
d
in
th
is
re
se
a
r
c
h
su
c
h
a
s
P
@1
0
,
%
n
o
m
e
a
su
re
s
a
n
d
M
A
P
,
a
n
d
h
a
s
a
c
h
iev
e
d
b
e
tt
e
r
re
su
lt
s
in
2
8
q
u
e
ries
o
n
P
@
1
0
a
l
o
n
e
,
c
o
m
p
a
re
d
to
th
e
B
M
2
5
o
rig
in
a
l
sc
o
re
,
th
a
t
o
n
ly
y
i
e
ld
b
e
tt
e
r
re
su
lt
s
in
2
q
u
e
ries
o
n
a
ll
e
v
a
lu
a
ti
o
n
m
e
tri
c
s,
a
n
d
a
lso
y
ield
b
e
tt
e
r
re
su
lt
s
in
4
q
u
e
ries
o
n
t
h
e
M
A
P
a
lo
n
e
.
T
h
e
re
su
lt
s
p
ro
v
e
d
th
a
t
t
h
e
p
ro
p
o
se
d
sy
s
tem
h
a
s
a
c
a
p
a
b
il
it
y
to
u
ti
li
z
e
th
e
e
x
p
e
rt
c
o
n
f
id
e
n
c
e
a
n
d
th
e
ir
re
lev
a
n
t
ju
d
g
m
e
n
t
th
a
t
a
re
re
p
re
se
n
ted
in
Z
-
Nu
m
b
e
r,
a
s
a
n
in
d
ica
to
r
to
o
p
ti
m
ize
th
e
e
x
isti
n
g
ra
n
k
in
g
f
u
n
c
ti
o
n
sy
ste
m
a
n
d
h
a
s
a
p
o
ten
ti
a
l
f
o
r
a
f
u
rth
e
r
re
se
a
rc
h
to
b
e
c
o
n
d
u
c
ted
o
n
t
h
e
se
d
o
m
a
in
s.
F
o
r
th
e
f
u
tu
re
w
o
rk
s,
th
e
re
se
a
rc
h
e
rs
w
o
u
ld
li
k
e
to
e
n
h
a
n
c
e
th
is
re
se
a
rc
h
b
y
in
c
lu
d
i
n
g
a
v
a
riety
o
f
e
x
p
e
rt’s
lev
e
l
c
o
n
f
id
e
n
c
e
a
n
d
t
h
e
ir
ju
d
g
m
e
n
t,
a
lso
a
n
e
w
c
a
lcu
latio
n
to
re
p
re
se
n
t
t
h
e
v
a
lu
e
o
f
Z
-
Nu
m
b
e
rs.
K
ey
w
o
r
d
s
:
B
M2
5
m
o
d
el
Do
m
ain
s
p
ec
if
i
c
te
x
t r
etr
ie
v
al
E
x
p
er
t j
u
d
g
m
e
n
t
Fu
zz
y
lo
g
ic
R
an
k
i
n
g
i
n
d
icato
r
Z
-
N
u
m
b
er
s
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sh
ai
f
u
l B
ak
h
tiar
b
in
R
o
d
z
m
a
n
,
Facu
lt
y
o
f
C
o
m
p
u
ter
&
Ma
t
h
e
m
atica
l
Sc
ien
ce
s
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
Sh
a
h
A
la
m
,
Selan
g
o
r
Dar
u
l E
h
s
a
n
,
Ma
la
y
s
ia
.
E
m
ail:
s
h
ai
f
u
l.b
ak
h
tiar
.
r
o
d
zm
an
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
r
o
w
d
s
o
u
r
cin
g
o
f
f
er
s
an
a
f
f
o
r
d
ab
le
an
d
s
ca
lab
le
m
ea
n
to
co
llect
r
elev
an
ce
j
u
d
g
m
en
ts
f
o
r
I
n
f
o
r
m
a
tio
n
R
etr
iev
a
l
(
I
R
)
tes
t
co
llectio
n
s
.
Ho
w
e
v
er
,
cr
o
w
d
ass
es
s
o
r
s
m
a
y
s
h
o
w
h
i
g
h
er
v
ar
ian
ce
in
j
u
d
g
m
en
t
q
u
alit
y
t
h
a
n
tr
u
s
ted
ass
e
s
s
o
r
s
,
(
th
at
th
e
r
esear
c
h
er
s
r
ef
er
r
e
d
to
in
th
is
s
t
u
d
y
as
th
e
ex
p
er
ts
)
[
1
].
T
h
e
ex
p
lo
r
atio
n
o
f
th
is
is
s
u
e
h
as
b
ec
o
m
in
g
v
ita
l,
s
in
ce
t
h
e
ex
p
er
t
j
u
d
g
m
e
n
t
m
a
y
h
a
v
e
th
e
p
o
ten
tial
to
b
e
u
tili
ze
d
i
n
b
r
in
g
i
n
g
i
m
p
r
o
v
e
m
en
t
o
f
t
h
e
e
x
is
t
in
g
r
an
k
in
g
f
u
n
ct
io
n
o
f
I
n
f
o
r
m
ati
o
n
R
etr
ie
v
al
(
I
R
)
.
E
s
p
ec
iall
y
,
in
t
h
e
co
n
te
x
t
o
f
Ma
la
y
T
r
an
s
lated
Had
ith
I
n
f
o
r
m
atio
n
R
e
tr
iev
al
as
o
n
e
e
x
a
m
p
le
o
f
Do
m
ai
n
Sp
ec
if
ic
T
ex
t
R
e
tr
iev
al
,
t
h
e
y
p
o
s
s
ess
e
x
p
er
tis
e
i
n
d
eter
m
i
n
i
n
g
th
e
r
ele
v
a
n
ce
o
f
h
ad
ith
in
s
p
ec
if
ic
to
p
ics
a
n
d
q
u
er
ies
a
n
d
m
o
r
eo
v
er
ass
e
s
s
in
g
t
h
e
a
u
t
h
en
t
icit
y
o
f
h
ad
it
h
d
o
cu
m
e
n
ts
[
2
]
.
I
n
t
h
is
s
t
u
d
y
,
th
e
r
esear
ch
er
s
h
y
p
o
t
h
esize
t
h
at
th
e
cr
o
w
d
j
u
d
g
es
m
a
y
b
e
h
av
e
t
h
e
r
eliab
ilit
y
to
g
i
v
e
th
e
r
elev
a
n
t
j
u
d
g
m
en
t
f
o
r
th
e
ce
r
tain
d
o
cu
m
en
ts
a
n
d
q
u
er
ies,
b
u
t
it
d
ep
en
d
o
n
th
eir
lev
el
o
f
co
n
f
id
en
ce
s
an
d
also
t
h
e
ex
p
er
tis
e.
T
h
e
lev
el
o
f
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
xp
ert ju
d
g
men
t Z
-
N
u
mb
ers
a
s
a
r
a
n
kin
g
in
d
ica
to
r
fo
r
… (
S
h
a
ifu
l B
a
kh
tia
r
b
in
R
o
d
z
ma
n
)
245
cr
o
w
d
ex
p
er
tis
e
an
d
also
th
ei
r
co
n
f
id
en
ce
m
a
y
af
f
ec
t
t
h
e
q
u
alit
y
o
f
th
eir
j
u
d
g
m
e
n
t
an
d
b
r
in
g
th
e
i
m
p
ac
t
to
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
I
R
s
y
s
te
m
[
1
]
,
if
a
n
d
o
n
l
y
i
f
th
e
v
a
lu
e
o
f
t
h
eir
j
u
d
g
m
e
n
t
i
s
ta
k
en
as
an
i
n
d
icato
r
o
f
th
e
r
an
k
i
n
g
f
u
n
ctio
n
.
T
h
is
v
al
u
e
o
f
r
el
ev
a
n
ce
j
u
d
g
m
e
n
t,
co
n
f
id
en
ce
an
d
t
h
e
ex
p
er
tis
e
ca
n
b
e
r
ep
r
esen
ted
in
o
n
e
s
in
g
le
v
al
u
e
u
s
in
g
Z
-
N
u
m
b
e
r
,
w
h
ic
h
b
ec
o
m
e
s
t
h
e
i
n
p
u
t
o
f
t
h
e
F
u
zz
y
L
o
g
ic
C
o
n
tr
o
ll
er
to
o
p
ti
m
ize
t
h
e
R
an
k
i
n
g
Fu
n
ctio
n
o
f
Do
m
ai
n
Sp
ec
if
ic
T
ex
t Retr
ie
v
al.
Z
ad
eh
et
al.
2
0
1
1
,
in
tr
o
d
u
ce
d
th
e
co
n
ce
p
t
o
f
Z
-
n
u
m
b
er
s
to
d
escr
ib
e
th
e
u
n
ce
r
tai
n
in
f
o
r
m
a
t
io
n
w
h
ic
h
is
a
m
o
r
e
g
e
n
er
alize
d
n
o
tio
n
.
A
Z
-
n
u
m
b
er
is
an
o
r
d
er
ed
p
ai
r
o
f
f
u
zz
y
n
u
m
b
er
s
(
A
,
B
)
[
3
]
.
Her
e
,
A
is
a
v
a
lu
e
o
f
s
o
m
e
v
ar
iab
le
s
a
n
d
B
r
e
p
r
esen
t
s
an
id
ea
o
f
ce
r
tain
t
y
o
r
o
th
er
clo
s
el
y
r
elate
d
c
o
n
ce
p
t
s
s
u
c
h
as
s
u
r
en
es
s
,
co
n
f
id
e
n
ce
,
r
eliab
ilit
y
,
s
tr
e
n
g
th
o
f
tr
u
th
,
o
r
p
r
o
b
a
b
ilit
y
[
4
]
.
I
t
s
h
o
u
ld
b
e
n
o
ted
th
at
in
ev
er
y
d
a
y
d
ec
is
io
n
m
ak
in
g
m
o
s
t
d
ec
is
io
n
s
ar
e
in
th
e
f
o
r
m
o
f
Z
-
n
u
m
b
er
s
.
Var
io
u
s
o
f
r
e
s
ea
r
ch
es
w
er
e
e
x
a
m
in
ed
in
ap
p
licatio
n
o
f
Z
-
n
u
m
b
er
s
i
n
m
a
n
y
ar
ea
s
t
h
a
t
in
v
o
lv
e
f
ac
to
r
s
t
h
at
ar
e
ch
ar
ac
ter
ized
b
y
n
o
t
o
n
l
y
f
u
zz
i
n
e
s
s
,
b
u
t
al
s
o
p
ar
tial
r
eliab
ilit
y
,
s
u
ch
a
s
[
4
-
1
2
]
.
T
h
eir
f
o
c
u
s
m
ain
l
y
o
n
r
esear
ch
o
f
s
i
n
g
le
o
r
Mu
lti
-
cr
iter
i
a
d
ec
is
io
n
-
m
a
k
i
n
g
p
r
o
b
lem
s
a
n
d
it
s
ap
p
licatio
n
w
it
h
Z
-
n
u
m
b
er
s
.
Ot
h
er
r
esear
ch
es,
b
esid
es
d
ec
is
io
n
m
a
k
i
n
g
p
r
o
b
lem
s
u
c
h
as
i
n
[
1
3
]
p
r
o
p
o
s
e
th
e
ap
p
licatio
n
o
f
Z
-
N
u
m
b
er
f
o
r
m
o
d
eli
n
g
t
h
e
ef
f
ec
t o
f
P
ilates e
x
er
cise
o
n
m
o
tiv
atio
n
,
a
tten
tio
n
,
an
x
ie
t
y
,
a
n
d
ed
u
ca
tio
n
a
l
ac
h
iev
e
m
e
n
t.
I
n
[
1
4
]
p
r
o
p
o
s
es
Sen
s
o
r
Data
F
u
s
io
n
w
i
th
Z
-
N
u
m
b
er
s
a
n
d
I
t
s
A
p
p
licatio
n
in
Fa
u
lt
Dia
g
n
o
s
is
u
s
i
n
g
Se
n
s
o
r
d
ata
f
u
s
io
n
t
ec
h
n
o
lo
g
y
.
A
p
p
licatio
n
o
f
e
x
p
er
t
j
u
d
g
m
en
ts
i
n
I
n
f
o
r
m
a
tio
n
R
e
tr
iev
al
ca
n
b
e
s
ee
n
i
n
th
e
w
o
r
k
o
f
[
1
5
-
1
8
]
w
h
ich
f
o
cu
s
o
n
r
esear
ch
o
f
p
s
eu
d
o
r
elev
a
n
ce
j
u
d
g
m
e
n
ts
o
r
ev
id
e
n
ce
t
h
at
w
ill
co
n
tr
ib
u
te
at
th
e
en
d
p
ar
t
o
f
th
e
i
n
f
o
r
m
a
tio
n
r
etr
iev
al
e
v
al
u
atio
n
.
I
n
[
1
9
]
p
r
o
p
o
s
es
to
u
s
e
t
h
e
P
air
w
is
e
P
r
ef
er
en
ce
tec
h
n
iq
u
e
to
co
llect
r
ele
v
an
ce
j
u
d
g
m
e
n
ts
f
r
o
m
a
cr
o
w
d
s
o
u
r
ci
n
g
p
lat
f
o
r
m
in
o
r
d
er
to
h
av
e
a
b
etter
u
n
d
er
s
tan
d
in
g
o
f
t
h
e
u
s
er
s
'
p
er
ce
p
tio
n
o
f
r
elev
a
n
ce
a
n
d
to
co
lle
ct
d
ata
w
it
h
h
i
g
h
f
id
eli
t
y
.
I
n
[
2
0
]
,
f
o
cu
s
e
s
o
n
m
o
d
ellin
g
r
a
n
d
o
m
n
e
s
s
in
r
elev
a
n
ce
j
u
d
g
m
e
n
ts
an
d
ev
alu
a
tio
n
m
ea
s
u
r
es,
an
d
r
ec
en
tl
y
i
n
2
0
1
8
,
in
[
1
]
s
h
o
w
s
th
e
p
o
ten
tial
o
f
cr
o
w
d
j
u
d
g
m
e
n
t
s
to
b
e
u
tili
s
ed
f
o
r
r
eliab
l
y
r
an
k
i
n
g
th
e
I
R
s
y
s
te
m
s
,
i
n
p
u
r
p
o
s
e
o
f
e
v
al
u
atio
n
,
an
d
clo
s
i
n
g
t
h
e
g
ap
o
f
j
u
d
g
e
m
en
t
d
is
a
g
r
ee
m
e
n
t
b
et
w
ee
n
ex
p
er
ts
a
n
d
cr
o
w
d
w
o
r
k
er
s
.
E
n
d
E
v
a
l
u
a
t
i
o
n
E
V
A
L
U
A
T
I
O
N
F
u
z
z
i
f
i
c
a
t
i
o
n
I
n
f
e
r
e
n
c
e
D
e
f
u
z
z
i
f
i
c
a
t
i
o
n
I
R
P
R
O
C
E
S
S
D
A
T
A
S
E
T
S
t
a
r
t
R
u
l
e
B
a
s
e
&
T
e
x
t
S
u
m
m
a
r
i
z
a
t
i
o
n
&
E
x
p
e
r
t
J
u
d
g
m
e
n
t
Z
-
n
u
m
b
e
r
s
C
a
l
c
u
l
a
t
i
o
n
D
o
c
u
m
e
n
t
C
o
l
l
e
c
t
i
o
n
(
M
a
l
a
y
T
r
a
n
s
l
a
t
e
d
H
a
d
i
t
h
)
O
u
e
r
v
T
e
x
t
T
e
x
t
P
r
e
-
P
r
o
c
e
s
s
i
n
g
(
M
a
l
a
y
S
t
e
m
m
e
r
)
I
n
d
e
x
i
n
g
Q
u
e
r
y
O
p
e
r
a
t
i
o
n
R
e
t
r
i
e
v
a
l
a
n
d
R
a
n
k
i
n
g
P
r
o
c
e
s
s
F
i
n
a
l
R
a
n
k
i
n
g
S
c
o
r
e
w
i
t
h
A
d
d
i
t
i
o
n
a
l
O
n
t
o
l
o
g
y
I
n
d
i
c
a
t
o
r
C
o
m
p
u
t
a
t
i
o
n
D
o
c
u
m
e
n
t
R
e
t
r
i
e
v
e
d
O
n
t
o
l
o
g
i
e
s
O
n
t
o
l
o
g
y
S
c
o
r
e
C
a
l
c
u
l
a
t
i
o
n
N
o
t
e
:
B
a
s
i
c
P
r
o
c
e
s
s
P
r
o
p
o
s
e
d
M
e
t
h
o
d
Fig
u
r
e
1
.
C
o
n
ce
p
tu
al
Fra
m
e
wo
r
k
o
f
FB
MI
R
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
F
r
a
m
ew
o
rk
Fig
u
r
e
1
illu
s
tr
ated
all
co
m
p
o
n
en
ts
i
n
t
h
e
f
r
a
m
e
w
o
r
k
o
f
th
e
F
u
z
z
y
B
M2
5
Ma
la
y
I
n
fo
r
ma
tio
n
R
etri
ev
a
l S
ystem
(
F
B
MIR
)
o
f
t
h
is
r
esear
ch
,
t
h
at
in
c
lu
d
es
th
e
b
asic o
f
p
r
o
ce
s
s
o
f
I
n
f
o
r
m
atio
n
R
etr
iev
al
s
u
c
h
as
P
r
e
-
P
r
o
ce
s
s
in
g
,
Qu
ery
Op
era
tio
n
a
n
d
R
etri
ev
a
l
a
n
d
R
a
n
kin
g
P
r
o
ce
s
s
,
w
h
ic
h
n
e
w
co
n
tr
ib
u
tio
n
s
i
n
th
i
s
r
esear
ch
ar
e
d
o
n
e
in
th
i
s
p
ar
ticu
lar
p
r
o
ce
s
s
.
I
n
th
e
s
aid
R
etr
ieva
l
a
n
d
R
a
n
kin
g
P
r
o
ce
s
s
,
th
e
r
esear
ch
er
s
h
a
v
e
o
p
tim
ized
th
e
B
M2
5
r
an
k
i
n
g
f
u
n
ctio
n
,
b
y
ap
p
l
y
i
n
g
t
h
e
d
esig
n
o
f
Hier
ar
c
h
ical
F
u
zz
y
L
o
g
ic
S
y
s
te
m
th
a
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
A
I
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
201
9
:
2
4
4
–
2
5
1
246
in
cl
u
d
es
4
Fu
zz
y
L
o
g
ic
C
o
n
t
r
o
ller
(
FL
C
)
,
w
h
ich
ea
c
h
F
L
C
h
a
s
p
r
o
ce
s
s
es
s
u
c
h
as
F
u
z
z
ifica
tio
n
,
I
n
feren
ce
,
an
d
Defu
z
z
if
ica
tio
n
to
p
r
o
d
u
ce
th
eir
o
w
n
o
u
tp
u
t.
4
FLC
h
av
e
th
eir
o
w
n
in
p
u
t
co
n
s
i
s
t
o
f
On
to
lo
g
y
B
M2
5
Sco
r
e,
Fab
r
icatio
n
R
ate,
Sh
ia
R
ate
an
d
P
o
s
itiv
e
R
ate
o
f
h
ad
ith
d
o
cu
m
e
n
t,
an
d
la
s
tl
y
to
in
clu
d
e
t
h
e
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
as
a
n
e
w
ad
d
itio
n
al
r
an
k
i
n
g
i
n
d
icato
r
.
T
h
e
E
v
alu
atio
n
p
r
o
ce
s
s
h
as
b
ee
n
d
o
n
e
b
y
ca
lcu
lati
n
g
th
e
ev
a
lu
at
io
n
m
e
tr
ic
s
u
ch
a
s
P
@
1
0
,
%n
o
m
e
asu
r
es
a
n
d
MA
P
,
an
d
co
m
p
ar
in
g
t
h
e
r
esu
l
ts
o
f
F
B
MIR
w
it
h
B
M2
5
o
r
ig
in
al
s
c
o
r
e
an
d
V
ec
to
r
Mo
d
el
s
co
r
e.
2
.
2
.
T
he
s
y
s
t
e
m
T
h
e
s
y
s
te
m
i
s
d
esi
g
n
ed
b
ased
o
n
t
h
e
in
teg
r
atio
n
o
f
t
h
e
r
e
s
e
ar
ch
er
s
’
t
w
o
p
r
ev
io
u
s
w
o
r
k
s
w
h
ic
h
ar
e,
Do
m
ain
s
p
ec
i
f
ic
co
n
ce
p
t
o
n
to
lo
g
ies
a
n
d
tex
t
s
u
m
m
ar
izat
io
n
as
h
ier
ar
c
h
ical
f
u
zz
y
lo
g
ic
r
an
k
i
n
g
i
n
d
icato
r
o
n
Ma
la
y
tex
t
co
r
p
u
s
in
[
2
]
,
an
d
P
o
s
itiv
e
R
ate
o
f
Had
it
h
in
[
2
1
]
,
w
i
th
th
e
n
e
w
ad
d
itio
n
a
l
E
x
p
er
t
J
u
d
g
m
e
n
t
w
it
h
Z
-
N
u
m
b
er
s
th
at
w
ill
b
e
th
e
m
ain
co
n
tr
ib
u
tio
n
i
n
t
h
is
ar
ticle
.
T
h
e
d
etails
o
f
t
h
e
d
esi
g
n
o
f
t
h
is
r
esear
ch
w
ill
b
e
ex
p
lain
ed
as
f
o
llo
w
s
.
2
.
2
.
1
.
Da
t
a
co
llect
io
n
T
h
e
s
y
s
te
m
b
a
s
icall
y
u
s
es
th
e
d
ata
o
f
Ma
la
y
T
r
an
s
lated
Ha
d
ith
co
r
p
u
s
t
h
at
co
n
s
i
s
ts
o
f
2
0
2
6
Sah
ih
B
u
k
h
ar
i
tex
t
d
o
cu
m
en
t
s
,
1
6
0
Fab
r
icate
d
h
ad
ith
s
te
x
t
d
o
cu
m
en
t
f
r
o
m
b
o
o
k
o
f
A
l
-
Ma
n
ar
al
-
M
u
n
i
f
Fi
al
-
Sa
h
i
h
wa
-
al
-
D
h
o
if
b
y
I
b
n
Qa
y
y
i
m
al
-
J
a
w
z
i
y
a
h
,
1
,
2
7
0
Sh
ia
Had
i
th
s
f
r
o
m
t
h
e
Ki
th
ab
Us
u
l
a
n
d
R
au
d
a
h
o
f
Kitab
Al
-
K
h
a
f
i,
a
n
d
1
7
2
8
d
o
cu
m
e
n
ts
f
r
o
m
Ki
th
ab
Al
-
Fiq
h
A
l
-
Ma
n
h
aj
i
Ma
z
h
ab
A
l
-
S
y
a
f
ie
b
y
Dr
Z
u
l
k
if
li
b
i
n
Mo
h
a
m
ad
al
-
B
ak
r
i,
an
d
also
t
h
e
h
ad
it
h
d
o
cu
m
e
n
t
s
f
r
o
m
th
e
ex
p
er
t’
s
r
ele
v
an
t j
u
d
g
m
e
n
t.
2
.
2
.
2
.
M
o
del f
o
r
m
o
difica
t
io
n
a
.
Ra
nk
ing
f
un
ct
io
n
T
h
e
s
y
s
te
m
w
i
ll
u
s
e
t
h
e
e
x
is
ti
n
g
m
e
th
o
d
o
f
r
an
k
i
n
g
f
u
n
ctio
n
f
r
o
m
t
h
e
r
esear
c
h
er
s
’
p
r
ev
io
u
s
w
o
r
k
s
i
n
[
2
]
,
s
u
ch
a
s
O
n
to
lo
g
y
Sco
r
e
o
f
B
M2
5
,
th
at
ac
t
s
a
s
t
h
e
f
ir
s
t
in
p
u
t
o
f
r
an
k
i
n
g
s
c
o
r
e
in
Hier
ar
ch
ica
l
Fu
zz
y
L
o
g
ic
S
y
s
te
m
,
t
h
at
ex
p
lain
in
Sec
tio
n
b
.
T
h
e
f
o
r
m
u
la
o
f
t
h
e
ca
lc
u
la
tio
n
o
f
t
h
e
On
to
lo
g
y
Sco
r
e
o
f
B
M2
5
,
D
w
ill b
e
as:
W
h
ile
Q
i
s
th
e
Qu
er
y
th
at
co
n
s
is
t th
e
k
e
y
w
o
r
d
s
o
f
q
1
u
n
til q
n
…
(
,
)
=
∑
(
)
.
(
(
,
)
.
(
1
+
1
)
(
,
)
+
1
.
(
1
−
=
.
|
|
)
)
=
1
(
1
)
On
to
lo
g
y
B
M2
5
Sco
r
e
)
)
,
(
(
)
,
(
Q
D
s
c
o
r
e
O
N
T
Q
D
s
c
o
r
e
(
2
)
W
h
er
e,
ON
T (
s
co
r
e
(
D,
Q)
)
i
s
an
A
cc
u
mu
la
ted
o
f O
n
to
lo
g
y
S
co
r
e
o
f D
o
cu
men
ts
fo
r
g
iven
q
u
ery.
b.
H
iera
rc
hica
l f
uzzy
lo
g
ic
s
y
s
t
e
m
On
e
ad
v
an
tag
e
o
f
Hier
ar
c
h
ica
l
Fu
zz
y
L
o
g
ic
S
y
s
te
m
i
s
its
ca
p
ab
ilit
y
to
d
ec
r
ea
s
e
th
e
am
o
u
n
t
o
f
f
u
zz
y
r
u
les
i
n
th
e
co
m
p
lete
s
y
s
te
m
,
b
y
s
ep
ar
atin
g
th
e
in
p
u
t
i
n
d
i
f
f
er
e
n
t
Fu
zz
y
L
o
g
ic
C
o
n
tr
o
ller
(
F
L
C
)
,
t
h
i
s
ap
p
r
o
ac
h
also
w
il
l
d
ec
r
ea
s
e
th
e
co
m
p
u
tat
io
n
al
ti
m
e
an
d
en
s
u
r
i
n
g
t
h
e
s
y
s
te
m
s
’
r
o
b
u
s
t
n
es
s
an
d
its
ef
f
icie
n
c
y
,
m
o
r
eo
v
er
p
r
o
v
en
to
ca
p
t
u
r
e
an
d
m
an
ip
u
late
t
h
e
e
x
p
er
t
k
n
o
w
led
g
e
a
n
d
in
p
u
t
[
2
2
]
.
I
n
t
h
is
ar
t
icle,
th
e
r
esear
ch
er
s
o
n
ce
ag
ai
n
u
s
e
t
h
e
d
esig
n
o
f
a
Hier
ar
ch
ical
Fu
zz
y
L
o
g
ic
S
y
s
te
m
,
w
h
ic
h
h
as
b
ee
n
d
o
n
e
in
th
e
r
esear
ch
er
s
’
p
r
ev
io
u
s
w
o
r
k
i
n
[
2
,
2
1
]
.
I
n
[
2
]
,
th
e
r
esear
ch
er
s
h
a
v
e
ex
p
lai
n
ed
t
h
e
o
p
er
atio
n
F
L
C
1
a
n
d
F
L
C
2
,
w
h
ic
h
is
i
n
t
h
e
F
u
zz
y
L
o
g
ic
C
o
n
tr
o
ller
(
FLC1
)
o
f
Ma
m
d
a
n
i
Me
t
h
o
d
,
co
n
s
is
t
o
f
t
w
o
in
p
u
ts
s
u
c
h
as
s
u
c
h
a
s
On
to
lo
g
y
B
M2
5
Sco
r
e
an
d
F
ab
r
icatio
n
R
ate.
Fo
r
t
h
e
F
L
C
2
,
it
co
n
s
is
t
s
o
f
t
w
o
in
p
u
ts
s
u
ch
as
t
h
e
o
u
tp
u
t
o
f
FLC1
an
d
Sh
ia
R
ate.
I
n
[
2
1
]
,
th
e
r
esear
ch
er
s
h
av
e
e
x
p
lain
e
d
th
e
co
n
tin
u
o
u
s
d
esig
n
b
y
ad
d
in
g
t
h
e
n
e
w
F
L
C
3
,
w
h
ic
h
co
n
s
is
ts
o
f
t
w
o
i
n
p
u
ts
s
u
ch
as
th
e
o
u
tp
u
t
o
f
F
L
C
2
an
d
P
o
s
iti
v
e
R
ate
o
f
Had
it
h
.
I
n
t
h
i
s
ar
ticle,
th
e
r
esear
ch
er
s
h
av
e
ad
d
ed
a
n
e
w
FLC4
,
th
at
r
u
n
a
f
ter
F
L
C
3
p
r
o
ce
s
s
t
h
at
also
co
n
s
i
s
ts
o
f
t
w
o
in
p
u
t
s
,
s
u
c
h
as
th
e
o
u
tp
u
t
o
f
F
L
C
3
a
n
d
E
x
p
er
t
J
u
d
g
m
en
t
Z
-
Nu
m
b
er
s
,
an
d
y
ie
ld
s
th
e
o
u
tp
u
t
a
s
th
e
Fi
n
al
R
a
n
k
i
n
g
Sco
r
e
o
f
t
h
e
d
o
cu
m
en
t s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
xp
ert ju
d
g
men
t Z
-
N
u
mb
ers
a
s
a
r
a
n
kin
g
in
d
ica
to
r
fo
r
… (
S
h
a
ifu
l B
a
kh
tia
r
b
in
R
o
d
z
ma
n
)
247
Fig
u
r
e
2
.
Hier
ar
ch
ical
Fu
zz
y
L
o
g
ic
C
o
n
tr
o
ller
o
f
F
B
MIR
Fu
zz
y
L
o
g
ic
h
as
a
ca
p
ab
ilit
y
t
o
b
e
u
s
ed
in
an
y
r
etr
ie
v
al
m
o
d
el
th
at
p
o
s
s
e
s
s
e
s
its
o
w
n
r
u
le
b
ased
an
d
allo
w
s
th
e
d
escr
ip
tio
n
o
f
th
e
ex
p
er
tis
e
in
a
m
o
r
e
in
t
u
iti
v
e
an
d
m
o
r
e
h
u
m
a
n
-
lik
e
m
an
n
er
,
esp
ec
iall
y
f
o
r
f
u
zz
y
in
f
er
en
ce
tec
h
n
iq
u
e
o
f
Ma
m
d
an
i
m
et
h
o
d
,
w
h
ic
h
t
h
e
r
esear
c
h
er
s
u
s
e
in
th
i
s
r
esear
c
h
.
I
n
t
h
is
r
esear
ch
,
in
e
v
er
y
FLC
t
h
at
i
s
m
en
t
io
n
ed
i
n
t
h
is
s
ec
tio
n
,
i
n
v
o
lv
es
th
e
F
u
zz
y
P
r
o
ce
s
s
in
g
,
t
h
at
i
n
cl
u
d
es p
r
o
ce
s
s
es o
f
F
u
z
z
ifica
tio
n
,
I
n
feren
ce
an
d
Defu
z
z
ifica
tio
n
to
p
r
o
d
u
ce
th
e
r
esu
lt,
w
e
c
an
s
ee
t
h
e
e
x
a
m
p
le
s
o
f
t
h
e
ap
p
licatio
n
o
f
th
i
s
m
et
h
o
d
in
[
2
3
-
2
5
]
.
F
u
z
z
ifica
tio
n
:
T
h
e
p
r
o
ce
s
s
o
f
d
ef
in
i
n
g
th
e
d
eg
r
ee
o
f
m
e
m
b
e
r
s
h
ip
o
f
a
cr
is
p
v
alu
e
f
o
r
ea
ch
f
u
zz
y
s
et
an
d
th
e
m
a
th
e
m
atica
l
m
ea
n
in
g
o
f
t
h
e
lin
g
u
is
t
ic
v
ar
iab
les.
I
n
t
h
is
ar
ticle,
th
e
r
esear
ch
er
s
ex
p
lai
n
th
e
lin
g
u
is
t
ic
v
ar
iab
les
as
s
h
o
w
s
i
n
T
ab
le
1
an
d
T
ab
le
2
,
f
o
r
m
u
lat
io
n
an
d
ca
lcu
la
tio
n
o
f
n
e
w
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
n
u
m
b
er
s
r
esp
ec
ti
v
el
y
th
a
t
will
b
e
u
s
ed
i
n
FLC4
.
T
h
e
d
etails
o
f
t
h
e
l
in
g
u
is
tic
v
ar
iab
les,
t
h
e
f
o
r
m
u
latio
n
an
d
th
e
ca
lcu
la
tio
n
o
f
F
L
C
1
,
FL
C
2
,
a
n
d
F
L
C
3
w
h
ic
h
ca
n
b
e
s
ee
n
i
n
t
h
e
r
esear
ch
er
s
’
p
r
ev
io
u
s
w
o
r
k
s
in
[
2
,
2
1
]
.
I
n
FLC4
,
th
e
m
o
d
el
u
s
e
s
o
n
e
i
n
p
u
t
w
h
ic
h
i
s
th
e
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
an
d
f
o
u
r
-
o
u
tp
u
t
v
al
u
es o
f
th
e
Fin
a
l Sco
r
e
R
an
k
i
n
g
w
h
ic
h
co
n
s
is
t
s
o
f
t
h
r
ee
tr
ian
g
u
lar
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
.
I
t a
ls
o
in
cl
u
d
es
L
i
n
g
u
i
s
tic
v
ar
iab
le
co
n
s
is
ts
o
f
F
in
al
R
a
n
k
i
n
g
S
co
r
e,
an
d
an
at
tr
ib
u
te
o
f
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
,
Fo
u
r
-
o
u
tp
u
t
v
ar
i
ab
les
an
d
ei
g
h
t
in
p
u
t
v
ar
iab
le
s
ar
e
id
en
ti
f
ied
a
n
d
ev
al
u
ated
b
y
th
e
d
o
m
ai
n
ex
p
er
t a
lo
n
g
w
i
th
,
t
h
e
v
ar
iab
le
s
an
d
r
an
g
e
o
f
p
o
s
s
ib
le
v
al
u
e.
I
n
feren
ce
:
T
h
e
p
r
o
ce
s
s
o
f
f
o
r
m
u
lati
n
g
th
e
m
ap
p
i
n
g
f
r
o
m
a
g
i
v
en
i
n
p
u
t
to
a
n
o
u
tp
u
t
u
s
i
n
g
f
u
zz
y
lo
g
ic,
r
ig
h
t
a
f
ter
t
h
e
F
u
zz
i
f
icatio
n
p
r
o
ce
s
s
.
T
h
e
m
ap
p
i
n
g
t
h
e
n
p
r
o
v
id
es
a
b
asis
f
r
o
m
w
h
ic
h
d
ec
is
io
n
s
ca
n
b
e
m
ad
e
an
d
g
i
v
e
o
u
t t
h
e
v
a
lu
e
f
o
r
th
e
v
ar
iab
le
o
f
th
e
f
u
zz
y
s
e
t
.
D
efu
z
z
ifica
tio
n
:
T
h
e
v
al
u
e
f
r
o
m
t
h
e
Fu
zz
y
I
n
f
er
e
n
ce
r
esu
lts
w
il
l
b
e
th
e
i
n
p
u
t
f
o
r
Def
u
zz
i
f
i
ca
tio
n
p
r
o
ce
s
s
.
Def
u
zz
if
icatio
n
i
s
th
e
p
r
o
ce
s
s
o
f
o
b
tain
i
n
g
a
s
i
n
g
l
e
n
u
m
b
er
(
o
u
tp
u
t)
f
r
o
m
t
h
e
ca
lcu
la
tio
n
o
f
t
h
e
a
g
g
r
e
g
ated
f
u
zz
y
s
et.
I
n
t
h
i
s
r
esear
c
h
,
t
h
e
r
esear
ch
e
r
s
w
i
ll
u
s
e
t
h
e
ce
n
ter
o
f
ar
ea
(
C
O
A
)
Def
u
zz
if
icatio
n
m
et
h
o
d
.
T
h
e
C
O
A
m
eth
o
d
b
asicall
y
,
r
etu
r
n
s
t
h
e
v
al
u
e
o
f
t
h
e
ce
n
ter
o
f
ar
ea
u
n
d
er
th
e
cu
r
v
e,
as it
s
m
e
th
o
d
is
to
p
r
o
d
u
ce
th
e
ca
lc
u
latio
n
o
f
f
in
a
l sco
r
e
o
f
th
e
r
an
k
in
g
f
u
n
ctio
n
.
R
u
les
:
Fu
zz
y
r
u
le
s
ar
e
u
s
ed
w
ith
i
n
f
u
zz
y
lo
g
ic
s
y
s
te
m
s
to
in
f
er
an
o
u
tp
u
t
b
ased
o
n
in
p
u
t
v
ar
iab
les
an
d
it
is
i
m
p
o
r
tan
t
as
a
s
tar
t
in
g
p
o
in
t
o
f
th
e
F
u
zz
y
P
r
o
ce
s
s
in
g
.
I
n
th
is
r
esear
c
h
,
th
e
r
u
le
s
ar
e
p
r
o
d
u
ce
d
b
y
th
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
o
f
t
h
e
ex
p
e
r
ts
’
k
n
o
w
led
g
e
b
y
th
e
e
x
p
er
ts
w
h
ic
h
ap
p
lie
s
t
h
e
Ma
m
d
a
n
i
T
y
p
e
R
u
les
o
f
Fu
zz
y
L
o
g
ic.
T
h
is
ta
k
e
s
t
w
o
a
ttrib
u
tes
f
o
r
ea
c
h
Fu
zz
y
L
o
g
ic
C
o
n
tr
o
ller
o
f
F
L
C
4
s
u
c
h
a
s
,
o
u
tp
u
t
o
f
F
L
C
3
an
d
E
x
p
er
t J
u
d
g
m
e
n
t Sco
r
e
in
T
a
b
le
3
.
T
ab
le
1
.
I
n
p
u
t lin
g
u
i
s
tic
v
ar
ia
b
le
L
i
n
g
u
i
st
i
c
v
a
r
i
a
b
l
e
V
a
l
u
e
R
a
n
g
e
O
u
t
p
u
t
o
f
F
L
C
3
Z
e
r
o
[
0
,
0
,
4
0
]
L
o
w
[
2
0
,
4
0
,
6
0
]
H
ig
h
[
4
0
,
6
0
,
8
0
]
V
e
r
y
H
i
g
h
[
6
0
,
1
0
0
,
1
0
0
]
Ex
p
e
r
t
Ju
d
g
me
n
t
S
c
o
r
e
(
̃
,
̃
)
L
o
w
[
0
,
0
,
4
0
]
M
e
d
i
u
m
[
2
0
,
4
0
,
6
0
]
H
i
g
h
[
4
0
,
6
0
,
8
0
]
V
e
r
y
H
i
g
h
[
6
0
,
1
0
0
,
1
0
0
]
T
ab
le
2
.
Ou
tp
u
t lin
g
u
is
tic
v
ar
i
ab
le
L
i
n
g
u
i
st
i
c
v
a
r
i
a
b
l
e
V
a
l
u
e
R
a
n
g
e
F
i
n
a
l
R
a
n
k
i
n
g
S
c
o
r
e
Z
e
r
o
[
0
,
0
,
4
0
.
0
0
]
L
o
w
[
2
0
,
4
0
,
6
0
]
H
ig
h
[
4
0
,
6
0
,
8
0
]
V
e
r
y
H
i
g
h
[
6
0
,
1
0
0
,
1
0
0
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
A
I
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
201
9
:
2
4
4
–
2
5
1
248
T
ab
le
3
.
R
u
les o
f
F
L
C
4
C
a
se
R
u
l
e
s
F
i
n
a
l
R
a
n
k
i
n
g
S
c
o
r
e
1
i
f
Ex
p
e
r
t
=
V
H
&
F
L
C
3
=
L
H
i
g
h
2
i
f
Ex
p
e
r
t
=
V
H
&
F
L
C
3
=
M
V
e
r
y
H
i
g
h
3
i
f
Ex
p
e
r
t
=
V
H
&
F
L
C
3
=
H
V
e
r
y
H
i
g
h
4
i
f
Ex
p
e
r
t
=
V
H
&
F
L
C
3
=
V
H
V
e
r
y
H
i
g
h
5
I
f
Ex
p
e
r
t
=
H
&
F
L
C
3
=
L
L
o
w
6
I
f
Ex
p
e
r
t
=
H
&
F
L
C
3
=
M
H
i
g
h
7
I
f
Ex
p
e
r
t
=
H
&
F
L
C
3
=
H
H
i
g
h
8
I
f
Ex
p
e
r
t
=
H
&
F
L
C
3
=
V
H
V
e
r
y
H
i
g
h
9
i
f
Ex
p
e
r
t
=
M
&
F
L
C
3
=
L
L
o
w
10
i
f
Ex
p
e
r
t
=
M
&
F
L
C
3
=
M
L
o
w
11
i
f
Ex
p
e
r
t
=
M
&
F
L
C
3
=
H
L
o
w
12
i
f
Ex
p
e
r
t
=
M
&
F
L
C
3
=
V
H
H
i
g
h
13
i
f
Ex
p
e
r
t
=
L
&
F
L
C
3
=
L
Z
e
r
o
14
i
f
Ex
p
e
r
t
=
L
&
F
L
C
3
=
M
L
o
w
15
i
f
Ex
p
e
r
t
=
L
&
F
L
C
3
=
H
L
o
w
16
i
f
Ex
p
e
r
t
=
L
&
F
L
C
3
=
V
H
H
i
g
h
2
.
3
.
P
r
o
po
s
ed
Ca
lcula
t
io
n o
f
Z
-
Nu
m
b
er
s
I
n
t
h
is
ar
ticle,
t
h
e
r
esear
ch
er
s
in
v
e
s
ti
g
ate
th
r
ee
f
ac
to
r
s
w
h
ic
h
m
a
y
co
r
r
elate
i
n
t
h
e
i
m
p
le
m
en
tatio
n
o
f
th
is
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
as
Fu
zz
y
L
o
g
ic
R
a
n
k
i
n
g
I
n
d
icato
r
s
u
ch
as:
ex
p
er
t
s’
r
el
ev
an
ce
j
u
d
g
m
en
t
o
r
s
co
r
e
,
th
e
e
x
p
er
t
s’
co
n
f
id
en
ce
an
d
t
h
e
le
v
el
o
f
e
x
p
er
ti
s
e.
F
o
llo
w
i
n
g
th
is
,
w
e
r
ep
r
esen
t
th
e
t
w
o
f
ac
to
r
s
i
n
Z
n
u
m
b
er
s
Z
=
(
A
,
B
)
.
T
ab
le
4
s
h
o
w
n
t
h
e
fi
r
s
t
co
m
p
o
n
en
t
A
,
a
r
estrictio
n
o
n
th
e
v
al
u
e
s
,
is
a
r
ea
l
-
v
al
u
ed
u
n
ce
r
tai
n
v
ar
iab
le
X
o
r
in
th
is
ca
se
th
e
r
esear
ch
er
s
tak
e
t
h
e
s
co
r
e
o
n
r
elev
an
ce
j
u
d
g
m
e
n
t
f
r
o
m
0
.
1
ti
ll
1
.
0
.
T
ab
le
5
s
h
o
w
n
t
h
e
s
ec
o
n
d
co
m
p
o
n
en
t
B
is
a
m
ea
s
u
r
e
o
f
r
eliab
ilit
y
o
f
t
h
e
fi
r
s
t
co
m
p
o
n
e
n
t
o
r
in
th
is
s
tu
d
y
we
tak
e
th
e
co
n
f
id
e
n
ce
o
f
th
eir
j
u
d
g
m
e
n
t,
w
h
ic
h
i
n
m
et
h
o
d
o
lo
g
y
a
s
th
e
r
esear
c
h
er
s
tak
e
t
h
e
s
ca
le
an
d
ap
p
r
o
ac
h
by
[
5
]
.
T
h
is
n
u
m
b
er
w
ill
b
e
co
n
v
er
t
ed
in
to
th
e
cr
is
p
n
u
m
b
er
b
y
u
s
i
n
g
th
e
d
ef
u
zz
i
f
icati
o
n
ap
p
r
o
ac
h
th
at
is
s
u
g
g
e
s
ted
by
[
9
]
:
Step
1
:
Dete
r
m
in
e
t
h
e
w
ei
g
h
t
s
o
f
ev
al
u
atio
n
cr
iter
ia.
T
h
e
w
eig
h
t
o
f
ev
alu
at
io
n
cr
i
te
r
i
a
a
r
e
em
p
lo
y
ed
as
s
am
e
v
alu
e,
0
.
2
f
o
r
ea
ch
c
r
it
er
io
n
,
w
ith
m
ax
i
m
u
m
is
1
.
Step
2
:
C
o
n
s
tr
u
ct
th
e
f
u
zz
y
d
e
cisi
o
n
m
atr
ix
f
o
r
alter
n
ati
v
es
’
ev
alu
a
tio
n
.
T
ab
le
4
.
L
in
g
u
i
s
tic
T
er
m
s
an
d
T
h
eir
C
o
r
r
esp
o
n
d
in
g
Gen
er
al
is
ed
Fu
zz
y
Nu
m
b
er
s
[
9
]
L
i
n
g
u
i
st
i
c
t
e
r
ms
G
e
n
e
r
a
l
i
se
d
f
u
z
z
y
n
u
mb
e
r
s
A
b
so
l
u
t
e
l
y
-
l
o
w
(
A
L
)
(
0
.
0
,
0
.
0
,
0
.
0
,
0
.
0
;
1
)
V
e
r
y
-
l
o
w
(
V
L
)
(
0
.
0
,
0
.
0
,
0
.
0
2
,
0
.
0
7
;
1
)
L
o
w
(
L
)
(
0
.
0
4
,
0
.
1
0
,
0
.
1
8
,
0
.
2
3
;
1
)
F
a
i
r
l
y
-
l
o
w
(
F
L
)
(
0
.
1
7
,
0
.
2
2
,
0
.
3
6
,
0
.
4
2
;
1
)
M
e
d
i
u
m (
M
)
(
0
.
3
2
,
0
.
4
1
,
0
.
5
8
,
0
.
6
;
1
)
F
a
i
r
l
y
-
h
i
g
h
(
F
H
)
(
0
.
5
8
,
0
.
6
3
,
0
.
8
0
,
0
.
8
6
;
1
)
H
i
g
h
(
H
)
(
0
.
7
2
,
0
.
7
8
,
0
.
9
2
,
0
.
9
7
;
1
)
V
e
r
y
-
h
i
g
h
(
V
H
)
(
0
.
9
3
,
0
.
9
8
,
1
.
0
,
1
.
0
;
1
)
A
b
so
l
u
t
e
l
y
-
h
i
g
h
(
A
H
)
(
1
.
0
,
1
.
0
,
1
.
0
,
1
.
0
;
1
)
T
ab
le
5
.
R
eliab
ilit
y
L
in
g
u
is
t
ic
T
e
r
m
s
an
d
T
h
eir
C
o
r
r
esp
o
n
d
in
g
Z
-
N
u
m
b
er
s
[
5
]
.
L
i
n
g
u
i
st
i
c
t
e
r
ms
G
e
n
e
r
a
l
i
se
d
f
u
z
z
y
n
u
mb
e
r
s
V
e
r
y
-
l
o
w
(
V
L
)
(
0
,
0
,
0
,
0
.
2
5
;
1
)
L
o
w
(
L
)
(
0
,
2
5
,
0
.
2
5
,
0
.
5
;
1
)
M
e
d
i
u
m (
M
)
(
0
.
2
5
,
0
.
5
,
0
.
5
,
0
.
7
5
;
1
)
H
i
g
h
(
H
)
(
0
.
5
,
0
.
7
5
,
0
.
7
5
,
1
;
1
)
V
e
r
y
-
h
i
g
h
(
V
H
)
(
0
.
7
5
,
1
,
1
,
1
;
1
)
Step
3
: Co
n
v
er
t t
h
e
z
-
n
u
m
b
er
s
in
to
r
eg
u
lar
f
u
zz
y
n
u
m
b
er
s
.
T
h
e
f
u
zz
y
d
ec
i
s
io
n
m
atr
ices o
f
p
r
ef
er
en
ce
s
o
f
z
-
n
u
m
b
er
s
ar
e
co
n
v
er
ted
an
d
ag
g
r
eg
ated
u
s
i
n
g
m
ai
n
(
3
)
an
d
m
u
ltip
les eq
u
a
tio
n
a
n
d
th
eo
r
em
th
a
t s
u
g
g
ested
b
y
[
9
]
,
th
at
c
an
b
e
co
m
p
u
ted
as
18
7
,
18
)
(
7
)
(
2
)
~
,
~
(
~
3
2
4
1
~
~
A
A
A
h
a
a
a
a
y
x
I
V
C
(
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
xp
ert ju
d
g
men
t Z
-
N
u
mb
ers
a
s
a
r
a
n
kin
g
in
d
ica
to
r
fo
r
… (
S
h
a
ifu
l B
a
kh
tia
r
b
in
R
o
d
z
ma
n
)
249
w
h
er
e
x
~
: th
e
ce
n
tr
o
id
p
o
in
t o
n
t
h
e
h
o
r
i
zo
n
tal
x
-
a
x
is
y
~
: th
e
ce
n
tr
o
id
p
o
in
t o
n
t
h
e
v
er
t
ical
y
-
a
x
is
)
~
,
~
(
y
x
: th
e
ce
n
tr
o
id
co
o
r
d
in
ate
o
f
f
u
zz
y
n
u
m
b
er
A
~
Step
4
:
Z
-
n
u
m
b
er
s
i
s
a
v
er
ag
e
d
an
d
n
o
r
m
al
ized
as
a
n
e
w
v
al
u
e
o
f
E
x
p
er
t
J
u
d
g
m
e
n
t
Sco
r
e
f
o
r
a
p
ar
ticu
lar
d
o
cu
m
en
t.
I
n
ap
p
ea
r
an
ce
w
it
h
m
a
n
y
e
x
p
er
tis
e,
t
h
e
s
y
s
te
m
w
i
ll
ca
l
cu
late
t
h
e
v
al
u
e
o
f
t
h
e
a
v
er
ag
e
o
f
Z
-
n
u
m
b
er
s
,
ac
co
r
d
in
g
to
th
eir
lev
el
o
f
ex
p
er
tis
e
s
u
ch
as
(
P
h
D,
Ma
s
ter
,
Deg
r
ee
an
d
User
)
,
as
th
e
f
in
al
Z
-
n
u
m
b
er
s
.
Fo
r
ca
lcu
latio
n
o
f
th
e
r
an
k
in
g
o
f
th
e
ce
r
tai
n
d
o
cu
m
en
t
s
,
t
h
e
s
y
s
te
m
w
ill
u
ti
lis
e
th
e
v
al
u
e
o
f
th
e
h
i
g
h
er
le
v
el
o
f
ex
p
er
tis
e
Z
-
n
u
m
b
er
s
,
to
r
ep
r
esen
t
th
e
r
elev
a
n
ce
j
u
d
g
m
e
n
t
o
f
a
p
ar
tic
u
lar
d
o
cu
m
en
t
.
F
o
r
ex
a
m
p
le,
i
f
t
h
e
av
er
ag
e
o
f
Z
-
n
u
m
b
er
s
o
f
P
h
D
av
ai
lab
le,
th
e
s
y
s
te
m
w
ill
u
s
e
th
i
s
v
al
u
e
i
n
s
tead
o
f
a
n
o
t
h
er
ca
te
g
o
r
y
.
I
f
t
h
e
v
alu
e
f
r
o
m
P
h
D
is
n
o
t
a
v
ailab
le,
th
e
s
y
s
te
m
w
i
ll
u
s
e
th
e
v
al
u
e
f
r
o
m
t
h
e
Ma
s
ter
a
n
d
s
o
o
n
.
T
h
e
p
r
io
r
ity
o
f
t
h
i
s
s
elec
tio
n
i
s
d
eter
m
i
n
ed
b
y
t
h
e
ex
p
er
ts
o
f
h
ad
it
h
s
t
h
at
ar
e
p
er
tain
i
n
g
to
Ma
la
y
s
ia
n
’
s
ce
n
ar
i
o
.
T
h
e
ca
lcu
latio
n
o
f
av
er
ag
e
o
f
Z
-
n
u
m
b
er
s
t
h
en
w
il
l b
e
u
s
ed
as a
n
i
n
p
u
t f
o
r
a
F
u
z
z
y
Lo
g
ic
C
o
n
tr
o
ller
4
o
r
F
LC
4
.
Step
5
: E
x
p
er
t J
u
d
g
m
e
n
t Sco
r
e
w
ill b
e
an
i
n
p
u
t f
o
r
Fu
zz
y
L
o
g
ic
C
o
n
tr
o
ller
4
o
r
FL
C
4
.
T
h
e
Z
-
n
u
m
b
er
is
t
h
en
i
n
v
o
lv
e
d
in
Fu
zz
y
P
r
o
ce
s
s
in
g
in
F
L
C
4
,
to
y
ield
th
e
r
es
u
lt a
s
th
e
r
es
ea
r
ch
er
s
m
e
n
tio
n
ed
in
p
r
ev
io
u
s
s
ec
tio
n
.
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
I
n
th
i
s
r
esear
ch
,
eig
h
t
e
x
p
er
ts
f
r
o
m
f
o
u
r
ca
teg
o
r
ies
(
P
h
D,
Ma
s
ter
,
Deg
r
ee
an
d
User
)
,
w
h
ich
m
ea
n
s
,
t
w
o
e
x
p
er
ts
f
r
o
m
ea
c
h
ca
te
g
o
r
y
,
ar
e
i
n
v
o
lv
e
d
i
n
t
h
is
r
e
s
ea
r
ch
to
j
u
d
g
e
t
h
e
h
ad
ith
d
o
cu
m
en
ts
o
n
ei
g
h
t
to
p
ics,
w
h
ic
h
co
n
s
i
s
t
o
f
th
e
to
tal
o
f
3
0
q
u
er
ies,
w
i
th
av
er
a
g
e
th
r
e
e
q
u
er
ies
f
o
r
ea
ch
to
p
ic
[
2
]
.
T
h
e
r
elev
an
ce
o
f
th
e
d
o
cu
m
en
ts
,
p
o
s
s
ib
le
r
an
g
e
o
f
Fu
zz
y
L
o
g
ic
C
o
n
tr
o
ller
,
p
r
io
r
it
y
s
elec
tio
n
o
f
Z
-
num
b
er
s
v
a
lu
e
th
a
t
h
a
v
e
b
ee
n
u
s
ed
i
n
th
is
r
esear
c
h
w
er
e
d
eter
m
i
n
ed
an
d
ex
a
m
i
n
ed
b
y
t
w
o
e
x
p
er
ts
,
Dr
A
h
m
ad
Y
u
n
u
s
Mo
h
d
No
o
r
f
r
o
m
Un
i
v
er
s
iti
Keb
an
g
s
aa
n
Ma
la
y
s
ia
a
n
d
Dr
Z
u
l
h
il
m
i
b
in
Mo
h
a
m
ed
No
r
f
r
o
m
U
n
i
v
er
s
iti
Sai
n
s
I
s
la
m
Ma
la
y
s
ia.
T
h
e
E
v
alu
a
tio
n
p
r
o
ce
s
s
h
as
b
ee
n
d
o
n
e
b
y
th
e
ca
lc
u
latio
n
o
f
t
h
e
e
v
al
u
atio
n
m
etr
ic
s
u
c
h
a
s
P
@
1
0
(
P
r
ec
is
io
n
at
R
an
k
1
0
)
,
%n
o
m
ea
s
u
r
es
(
th
e
p
er
ce
n
tag
e
o
f
t
h
e
q
u
er
y
w
i
th
n
o
r
elev
an
t
d
o
cu
m
e
n
t
i
n
th
e
to
p
ten
r
etr
iev
ed
)
an
d
MA
P
(
Me
an
A
v
er
a
g
e
P
r
ec
is
io
n
)
,
an
d
th
e
co
m
ap
r
is
o
b
et
w
ee
n
th
e
r
es
u
lt
s
o
f
F
B
MIR
w
i
th
B
M2
5
o
r
ig
in
al
s
co
r
e
an
d
V
ec
to
r
Mo
d
el
s
co
r
e.
T
h
e
r
esu
lt
s
ar
e
s
h
o
w
n
i
n
th
e
T
ab
le
6
as f
o
llo
w
s
.
T
ab
le
6
.
R
esu
lts
o
f
E
x
p
er
i
m
e
n
t
N
o
.
TO
P
I
C
FBM
I
R
P
@
10
BM
2
5
P
@
10
Ve
c
t
o
r
P
@
10
FBM
I
R
%
no
BM
2
5
%n
o
V
e
c
t
o
r
%n
o
FBM
I
R
M
A
P
BM
2
5
M
AP
V
e
c
t
o
r
M
A
P
1
Ma
k
a
n
a
n
1
.
0
0
.
8
0
.
4
6
6
0
20
5
3
.
4
1
.
0
0
.
8
2
0
.
5
0
2
2
Ad
a
b
0
.
8
7
5
1
0
.
7
5
1
2
.
5
0
25
0
.
8
9
1
0
.
7
1
5
3
S
o
l
a
t
0
.
9
0
.
4
7
6
0
.
5
8
10
5
2
.
4
42
0
.
8
7
6
5
0
.
4
8
6
0
.
5
8
4
4
I
m
a
n
1
.
0
0
.
4
6
6
0
.
4
4
4
0
5
3
.
4
5
5
.
6
1
.
0
0
.
4
6
3
0
.
5
6
5
5
Be
rsu
c
i
0
.
9
5
0
.
9
3
7
0
.
5
1
3
5
6
.
3
4
8
.
7
0
.
9
5
2
0
.
9
6
8
0
.
5
3
4
6
I
b
a
d
a
h
0
.
9
4
7
0
.
3
5
0
.
5
4
1
5
.
3
65
4
5
.
9
0
.
9
5
5
7
0
.
7
2
5
0
.
5
7
7
7
S
i
r
a
h
1
0
.
7
3
3
0
.
7
3
3
0
2
6
.
7
2
6
.
7
1
0
.
9
6
4
0
.
9
0
5
8
U
m
u
m
0
.
8
9
8
0
0
.
3
3
3
0
.
3
5
3
1
0
.
2
6
6
.
7
7
4
.
7
0
.
8
5
9
6
0
.
3
2
4
0
.
3
8
2
B
ased
o
n
T
ab
le
6
,
in
ter
m
o
f
T
o
p
ics
o
f
th
e
q
u
er
y
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
,
w
it
h
t
h
e
ad
d
iti
o
n
al
n
e
w
in
d
icato
r
o
f
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
,
h
a
s
a
b
etter
r
esu
lt
o
n
s
ev
en
to
p
ic
s
ets
s
u
c
h
as
“M
ak
an
a
n
”,
“
S
o
la
t”,
“Im
a
n
”,”Be
r
s
u
ci”,“I
b
a
d
a
h
”,
“
S
i
r
a
h
”
an
d
“
U
mu
m”
o
n
t
h
e
P
@
1
0
a
n
d
%
n
o
m
ea
s
u
r
e
s
.
Fo
r
M
A
P
alo
n
e,
F
B
MIR
h
as
a
b
etter
r
esu
lt
o
n
s
ix
to
p
ic
s
ets
o
f
q
u
er
y
r
esu
lts
s
u
c
h
as
“
Ma
k
a
n
a
n
”,
“
S
o
la
t”,
“Im
a
n
”,
“Ib
a
d
a
h
”,
“
S
ir
a
h
”
a
n
d
“
Umu
m”
o
n
th
e
P
@
1
0
an
d
%
n
o
m
ea
s
u
r
es
.
B
M2
5
o
r
ig
in
al
s
co
r
e
o
n
l
y
h
as
b
etter
r
esu
lt
o
n
o
n
e
to
p
ic
s
et
o
f
“
A
d
a
b
”
w
h
er
ea
s
MAP
a
lo
n
e
h
as b
etter
r
esu
lt in
t
w
o
to
p
ic
s
ets o
f
“
A
d
a
b
”a
n
d
“Be
r
s
u
ci”.
I
n
ter
m
o
f
t
h
e
o
v
er
all
q
u
er
ie
s
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
,
w
it
h
th
e
ad
d
itio
n
al
n
e
w
i
n
d
icato
r
o
f
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
,
m
a
y
b
r
in
g
t
h
e
i
m
p
r
o
v
e
m
e
n
t
to
th
e
o
r
ig
i
n
al
B
M2
5
r
an
k
in
g
f
u
n
ctio
n
,
b
y
y
ield
i
n
g
b
etter
r
esu
lt
s
o
n
2
6
q
u
er
ie
s
,
o
n
all
ev
alu
a
tio
n
m
etr
ics
th
at
ar
e
m
ea
s
u
r
ed
in
t
h
i
s
r
esear
ch
s
u
ch
as
P
@
1
0
,
%n
o
m
ea
s
u
r
es
an
d
M
A
P
,
an
d
h
as
ac
h
iev
ed
th
e
b
etter
r
esu
lt
s
in
2
8
q
u
er
ies
o
n
P
@
1
0
alo
n
e,
co
m
p
ar
ed
to
th
e
B
M2
5
o
r
ig
in
al
s
co
r
e,
t
h
at
o
n
l
y
y
ield
b
etter
r
es
u
lt
i
n
t
w
o
q
u
er
ie
s
o
f
all
ev
a
lu
atio
n
m
etr
ic
s
a
n
d
f
o
u
r
q
u
er
ies
o
n
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
A
I
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
201
9
:
2
4
4
–
2
5
1
250
MA
P
alo
n
e.
I
n
th
i
s
r
esear
ch
,
Vec
to
r
Sp
ac
e
Mo
d
el
h
as
n
o
t
o
u
tp
er
f
o
r
m
ed
FB
MI
R
a
n
d
B
M2
5
Or
ig
in
al
Sco
r
e
i
n
an
y
q
u
er
ies.
W
it
h
th
e
ap
p
licat
io
n
o
f
O
n
to
lo
g
y
B
M2
5
Sco
r
e,
Fab
r
icatio
n
R
ate,
Sh
ia
R
ate
,
P
o
s
itiv
e
o
f
F
L
C
1
,
FLC2
a
n
d
F
L
C
3
th
a
t
t
h
e
r
ese
ar
ch
er
s
r
ep
o
r
ted
in
[
2
1
]
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
h
as
a
b
etter
r
esu
lt
o
n
f
i
v
e
to
p
ics
an
d
2
6
q
u
er
ies.
W
ith
th
e
ad
d
i
tio
n
al
o
f
t
h
e
E
x
p
er
t
J
u
d
g
m
e
n
t
w
it
h
Z
-
Nu
m
b
er
s
i
n
t
h
is
r
esea
r
ch
,
th
e
r
es
u
lts
ar
e
i
m
p
r
o
v
ed
w
h
en
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
y
ie
ld
s
b
etter
r
esu
lts
o
n
s
ev
e
n
to
p
ics
an
d
2
6
q
u
er
ies
co
m
p
ar
ed
to
th
e
o
th
er
m
o
d
el.
On
e
i
m
p
o
r
ta
n
t
f
i
n
d
in
g
f
r
o
m
t
h
i
s
ex
p
er
i
m
e
n
t
i
s
t
h
at
t
h
e
r
es
u
lts
w
ill
b
e
d
if
f
er
en
t
i
f
t
h
e
Hier
ar
ch
ical
F
u
zz
y
L
o
g
ic
ar
e
r
u
n
w
it
h
d
if
f
er
en
t
o
r
d
er
.
Fo
r
ex
a
m
p
le,
t
h
e
r
esu
l
ts
ar
e
g
e
ttin
g
w
o
r
s
e
i
f
th
e
P
o
s
itiv
e
R
ate
is
tak
e
n
as
an
in
p
u
t
in
F
L
C
1
an
d
th
e
Fab
r
icate
d
an
d
Sh
ia
r
ate
in
FL
C
2
an
d
FLC3
,
co
m
p
ar
ed
to
th
e
o
r
d
er
th
at
th
e
r
esear
ch
er
s
s
u
g
g
es
t
in
s
ec
t
io
n
2
.
2
.
Mo
r
eo
v
er
,
th
e
r
esu
lts
o
r
th
e
r
an
k
in
g
li
s
t
th
at
ar
e
r
etr
iev
ed
af
ter
F
L
C
3
,
w
ill
m
ak
e
t
h
e
ex
p
er
ts
ea
s
ier
to
j
u
d
g
e,
b
ec
au
s
e
th
e
r
an
k
in
g
lis
t
o
f
h
ad
it
h
ar
e
o
p
ti
m
ized
ea
r
lier
an
d
w
il
l
m
a
k
e
m
o
s
t
r
elev
a
n
ce
d
o
cu
m
e
n
t
s
ar
e
alr
ea
d
y
i
n
t
h
e
to
p
o
f
th
e
li
s
t,
d
u
e
to
th
e
p
r
o
ce
s
s
i
n
g
o
f
F
L
C
1
,
F
L
C
2
an
d
F
L
C
3
.
Fo
r
f
u
tu
r
e
w
o
r
k
s
,
t
h
e
r
esear
ch
er
s
w
a
n
t
to
ap
p
l
y
t
h
e
d
if
f
er
e
n
t
lo
g
ic
o
r
ca
lcu
latio
n
to
m
a
n
ip
u
la
te
th
e
all
v
al
u
e
f
r
o
m
d
if
f
er
e
n
t
ca
teg
o
r
ies
o
f
ex
p
er
t
j
u
d
g
m
e
n
t,
i
n
s
tead
o
f
u
s
i
n
g
th
e
v
al
u
e
o
f
h
i
g
h
er
ca
te
g
o
r
ies
o
f
ex
p
er
t th
at
t
h
e
r
esear
ch
er
s
h
av
e
d
o
n
e
in
th
i
s
p
ar
ticu
lar
r
esear
ch
.
4.
CO
NCLU
SI
O
N
T
h
is
ar
ticles
p
r
ese
n
ted
t
h
e
i
m
p
le
m
en
ta
tio
n
o
f
E
x
p
er
t
J
u
d
g
m
en
t
Z
-
Nu
m
b
er
s
a
s
a
R
a
n
k
i
n
g
I
n
d
icato
r
f
o
r
Hier
ar
ch
ical
Fu
zz
y
L
o
g
ic
S
y
s
te
m
.
T
h
e
r
esear
ch
er
s
h
a
v
e
p
r
o
p
o
s
ed
th
e
d
esig
n
o
f
t
h
e
Hier
ar
ch
ical
Fu
zz
y
L
o
g
ic
S
y
s
te
m
w
it
h
t
h
e
ad
d
it
io
n
al
n
e
w
in
d
icato
r
s
u
c
h
as
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
th
at
e
n
h
a
n
ce
s
th
e
r
esu
lt
s
o
f
th
e
r
esear
ch
er
s
’
p
r
e
v
io
u
s
w
o
r
k
s
i
n
[
2
,
2
1
]
.
I
n
th
is
ar
ticle,
th
e
r
esear
ch
er
s
i
n
v
e
s
tig
a
te
th
r
ee
f
ac
to
r
s
w
h
ic
h
m
a
y
co
r
r
elate
i
n
t
h
e
i
m
p
le
m
e
n
tat
io
n
o
f
th
is
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
as
F
u
zz
y
L
o
g
ic
R
a
n
k
i
n
g
I
n
d
icato
r
s
u
c
h
as
: e
x
p
er
t r
ele
v
an
ce
j
u
d
g
m
en
t,
t
h
e
ex
p
er
t c
o
n
f
id
en
ce
a
n
d
t
h
e
le
v
el
o
f
ex
p
er
t
is
e.
Fo
llo
w
i
n
g
th
i
s
,
w
e
r
ep
r
esen
t
t
h
e
t
w
o
f
ac
to
r
s
i
n
Z
n
u
m
b
er
s
Z
=
(
A
,
B
)
.
T
h
e
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
t
h
en
w
il
l
b
e
an
in
p
u
t
to
Hier
ar
ch
ical
Fu
zz
y
L
o
g
ic
S
y
s
te
m
o
f
Do
m
a
in
Sp
ec
i
f
ic
T
ex
t
R
etr
ie
v
al,
alo
n
g
w
it
h
o
t
h
e
r
in
d
icato
r
s
s
u
c
h
a
s
On
to
lo
g
y
B
M2
5
Sco
r
e,
Fab
r
icatio
n
R
ate,
Sh
ia
R
ate
an
d
P
o
s
itiv
e
R
ate
o
f
h
ad
it
h
d
o
cu
m
en
t.
T
h
e
r
esu
lts
s
h
o
w
ed
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
,
w
ith
t
h
e
ad
d
itio
n
al
n
e
w
i
n
d
icato
r
o
f
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
N
u
m
b
er
s
,
m
a
y
b
r
i
n
g
th
e
i
m
p
r
o
v
e
m
e
n
t to
t
h
e
o
r
ig
i
n
al
B
M2
5
r
an
k
in
g
f
u
n
ctio
n
,
b
y
y
ield
b
etter
r
esu
l
t o
n
2
6
q
u
er
ies,
o
n
all
e
v
alu
a
tio
n
m
etr
ic
t
h
at
m
ea
s
u
r
e
in
t
h
is
r
es
ea
r
ch
s
u
c
h
as
P
@
1
0
,
%
n
o
m
e
asu
r
es
an
d
M
A
P
,
a
n
d
h
as
ac
h
i
ev
ed
b
etter
r
es
u
lt
s
in
2
8
q
u
er
ies
o
n
P
@
1
0
alo
n
e,
co
m
p
ar
e
to
th
e
B
M2
5
o
r
ig
in
al
s
co
r
e,
th
at
o
n
l
y
y
ield
b
etter
r
esu
lt
i
n
t
w
o
q
u
er
ies
o
f
all
ev
al
u
atio
n
m
etr
ics,
a
n
d
also
y
ield
b
etter
r
esu
l
t
in
f
o
u
r
q
u
er
ies
o
n
t
h
e
M
A
P
alo
n
e.
Fo
r
th
e
f
u
r
th
er
en
h
a
n
ce
m
en
t,
th
e
r
esear
ch
er
w
a
n
t
to
ap
p
ly
a
n
d
p
r
o
p
o
s
e
n
ew
ca
lcu
latio
n
a
n
d
n
e
w
lo
g
ic
t
o
m
a
n
ip
u
la
te
th
e
all
v
alu
e
f
r
o
m
d
if
f
er
en
t
ca
te
g
o
r
ie
s
o
f
ex
p
er
t
j
u
d
g
m
e
n
t,
i
n
s
tead
u
s
e
t
h
e
p
r
io
r
ity
o
f
v
al
u
e
o
f
h
i
g
h
er
ca
te
g
o
r
ies
o
f
ex
p
er
t
th
at
th
e
r
esear
c
h
er
s
h
a
v
e
d
o
n
e
in
th
i
s
p
ar
ticu
lar
r
ese
ar
ch
.
T
h
e
r
esu
lts
s
h
o
w
ed
th
a
t
E
x
p
er
t
J
u
d
g
m
e
n
t
Z
-
Nu
m
b
er
s
as
Fu
zz
y
L
o
g
ic
R
a
n
k
in
g
I
n
d
icato
r
o
f
f
er
s
a
p
r
o
m
i
s
in
g
m
e
th
o
d
to
le
v
er
ag
e
t
h
e
cr
o
w
d
i
n
co
m
b
i
n
atio
n
of
tr
u
s
ted
j
u
d
g
es,
th
eir
co
n
f
id
en
ce
an
d
also
th
eir
lev
el
o
f
e
x
p
er
tis
e
f
o
r
ac
cu
r
ate
an
d
af
f
o
r
d
ab
le
b
u
ild
in
g
o
f
I
R
test
co
llectio
n
s
an
d
m
a
y
ele
v
at
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
r
an
k
i
n
g
Fu
n
ctio
n
f
o
r
Do
m
ai
n
Sp
ec
if
ic
T
ex
t Retr
iev
al.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esear
ch
is
f
u
n
d
ed
b
y
t
h
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
(
MO
E
)
Ma
lay
s
ia
u
n
d
er
FR
GS
R
e
s
e
ar
ch
Gr
an
t
at
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
S
h
a
h
A
la
m
(
6
0
0
-
I
R
MI
/
FR
GS 5
/3
(
0
2
1
/2
0
1
7
)
)
.
RE
F
E
R
E
NC
E
S
[1
]
M
u
c
a
h
id
K
u
tl
u
,
e
t
a
l.
,
"
Cro
w
d
v
s.
Ex
p
e
rt:
W
h
a
t
Ca
n
Re
lev
a
n
c
e
Ju
d
g
m
e
n
t
Ra
ti
o
n
a
les
Tea
c
h
Us
A
b
o
u
t
A
ss
e
ss
o
r
Disa
g
re
e
m
e
n
t?,"
in
S
IG
IR
’1
8
:
T
h
e
4
1
st
In
tern
a
ti
o
n
a
l
A
CM
S
IG
IR
Co
n
fe
re
n
c
e
o
n
Re
se
a
rc
h
&
De
v
e
lo
p
m
e
n
t
in
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l,
Ju
ly
8
–
1
2
,
2
0
1
8
,
A
n
n
A
rb
o
r,
M
I,
U
S
A
.
A
CM
,
Ne
w
Yo
rk
,
NY
,
USA
,
1
0
p
a
g
e
s.
h
tt
p
s:/
/d
o
i.
o
rg
/1
0
.
1
1
4
5
/3
2
0
9
9
7
8
.
3
2
1
0
0
3
3
.
[2
]
S
h
a
if
u
l
Ba
k
h
ti
a
r
b
i
n
R
o
d
z
m
a
n
,
e
t
a
l.
,
"
Do
m
a
in
sp
e
c
if
ic
c
o
n
c
e
p
t
o
n
to
lo
g
ies
a
n
d
tex
t
su
m
m
a
riza
ti
o
n
a
s
h
iera
rc
h
ica
l
f
u
z
z
y
lo
g
ic
ra
n
k
in
g
in
d
ica
to
r
o
n
m
a
la
y
t
e
x
t
c
o
rp
u
s,"
In
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
5
,
n
o
.
3
,
S
e
p
tem
b
e
r
2
0
1
9
.
[3
]
Zad
e
h
L
.
A
,
“
A
n
o
te o
n
Z
-
n
u
m
b
e
rs,”
J
.
In
f.
S
c
i
,
v
o
l.
1
8
1
,
p
p
.
2
9
2
3
-
2
9
3
2
,
2
0
1
1
.
[4
]
Yu
Ya
n
g
a
n
d
Jia
n
-
q
ian
g
W
a
n
g
,
"
S
M
AA
-
b
a
se
d
m
o
d
e
l
f
o
r
d
e
c
isio
n
a
id
in
g
u
sin
g
re
g
re
t
th
e
o
ry
in
d
isc
re
te
Z
-
n
u
m
b
e
r
c
o
n
tex
t,
"
Ap
p
l
ied
S
o
ft
Co
mp
u
ti
n
g
,
v
o
l.
6
5
,
p
p
.
5
9
0
-
6
0
2
,
A
p
ril
2
0
1
8
.
[5
]
Bin
g
Yi
Ka
n
g
a
n
d
D.
W
e
i,
Y.
L
i.
Y.
De
n
g
,
“
De
c
isio
n
m
a
k
in
g
u
sin
g
Z
-
n
u
m
b
e
rs
u
n
d
e
r
u
n
c
e
rtain
e
n
v
iro
n
m
e
n
t,
"
J
o
u
rn
a
l
o
f
Co
m
p
u
t
a
ti
o
n
a
l
I
n
fo
rm
a
ti
o
n
S
y
ste
ms
,
v
o
l.
8
,
n
o
.
7
,
p
p
.
2
8
0
7
-
2
8
1
4
.
A
p
ril
2
0
1
2
.
[6
]
R.
A
.
A
li
e
v
,
e
t
a
l.
,
"
Ra
n
k
in
g
o
f
Z
-
Nu
m
b
e
rs
a
n
d
Its
A
p
p
li
c
a
ti
o
n
in
De
c
isio
n
M
a
k
in
g
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
&
De
c
isi
o
n
M
a
k
i
n
g
,
v
o
l.
1
5
,
n
o
.
0
6
,
p
p
.
1
5
0
3
-
1
5
1
9
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
xp
ert ju
d
g
men
t Z
-
N
u
mb
ers
a
s
a
r
a
n
kin
g
in
d
ica
to
r
fo
r
… (
S
h
a
ifu
l B
a
kh
tia
r
b
in
R
o
d
z
ma
n
)
251
[7
]
L
a
la
M
.
Zein
a
lo
v
a
,
e
t
a
l.
,
"
A
Z
-
Nu
m
b
e
r
V
a
lu
e
d
Re
g
re
ss
io
n
M
o
d
e
l
a
n
d
it
s
A
p
p
li
c
a
ti
o
n
,
”
I
n
telli
g
e
n
t
Au
t
o
ma
ti
o
n
&
S
o
ft
Co
mp
u
ti
n
g
,
DO
I:
1
0
.
1
0
8
0
/
1
0
7
9
8
5
8
7
.
2
0
1
7
.
1
3
2
7
5
5
1
.
[8
]
Da
u
d
M
o
h
a
m
a
d
,
e
t
a
l.
,
"
Ord
e
rin
g
o
f
Z
-
n
u
m
b
e
rs,"
A
IP
Co
n
f
e
re
n
c
e
P
r
o
c
e
e
d
in
g
s 1
8
7
0
,
0
4
0
0
4
9
,
2
0
1
7
.
[9
]
K Kh
a
li
f
,
KM
Na
im
,
e
t
a
l.
,
"
H
y
b
r
id
f
u
z
z
y
M
CDM
m
o
d
e
l
f
o
r
Z
-
n
u
m
b
e
rs u
sin
g
in
tu
it
iv
e
v
e
c
to
rial
c
e
n
tro
i
d
,
”
J
o
u
rn
a
l
o
f
In
telli
g
e
n
t
&
Fu
zz
y
S
y
ste
ms
,
2
0
1
7
.
[1
0
]
A
h
m
a
d
S
y
a
f
a
d
h
li
A
b
u
Ba
k
a
r,
e
t
a
l.
,
"
M
u
lt
i
-
L
a
y
e
r
De
c
isio
n
M
e
th
o
d
o
lo
g
y
f
o
r
Ra
n
k
in
g
Z
-
Nu
m
b
e
rs
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
S
y
ste
ms
,
v
o
l.
8
,
n
o
.
2
,
p
p
,
3
9
5
-
4
0
6
,
2
0
1
5
.
[1
1
]
Ha
m
e
d
A
b
o
u
to
ra
b
,
e
t
a
l.
,
"
ZBW
M
:
T
h
e
Z
-
n
u
m
b
e
r
e
x
ten
sio
n
o
f
B
e
st
W
o
rst
M
e
th
o
d
a
n
d
it
s a
p
p
li
c
a
ti
o
n
f
o
r
su
p
p
l
ier
d
e
v
e
lo
p
m
e
n
t,
"
Exp
e
rt S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
o
l.
1
0
7
,
p
p
.
1
1
5
-
1
2
5
,
Oc
to
b
e
r
2
0
1
8
.
[1
2
]
Ho
n
g
-
g
a
n
g
P
e
n
g
a
n
d
Jia
n
-
q
ian
g
Wan
g
,
“
Ou
tran
k
in
g
De
c
isio
n
-
M
a
k
in
g
M
e
th
o
d
w
it
h
Z
-
Nu
m
b
e
r
Co
g
n
it
iv
e
In
f
o
rm
a
ti
o
n
"
Co
g
n
it
ive
Co
m
p
u
t
a
t
io
n
,
v
o
l.
1
0
,
n
o
.
5
,
p
p
.
7
5
2
–
7
6
8
,
Oc
to
b
e
r
2
0
1
8
.
[1
3
]
Ra
f
i
k
A
li
e
v
a
n
d
Ko
n
u
l
M
e
m
m
e
d
o
v
a
,
“
A
p
p
li
c
a
ti
o
n
o
f
Z
-
Nu
m
b
e
r
Ba
se
d
M
o
d
e
li
n
g
in
P
sy
c
h
o
lo
g
i
c
a
l
Re
se
a
rc
h
,
"
Co
mp
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
a
n
d
N
e
u
ro
sc
ien
c
e
,
v
o
l.
2
0
1
5
,
h
tt
p
:/
/
d
x
.
d
o
i.
o
rg
/1
0
.
1
1
5
5
/2
0
1
5
/
7
6
0
4
0
3
.
[1
4
]
W
e
n
Jia
n
g
,
e
t
a
l.
,
"
S
e
n
so
r
Da
ta
F
u
sio
n
w
it
h
Z
-
Nu
m
b
e
rs
a
n
d
Its
A
p
p
li
c
a
ti
o
n
in
F
a
u
lt
Dia
g
n
o
sis,"
S
e
n
so
rs
2
0
1
6
,
1
6
,
1
5
0
9
;
d
o
i:
1
0
.
3
3
9
0
/s1
6
0
9
1
5
0
9
.
[1
5
]
P
ra
b
h
a
Ra
jag
o
p
a
l,
e
t
a
l.
,
"
Re
lev
a
n
c
e
Ju
d
g
m
e
n
ts
Ex
c
lu
siv
e
o
f
Hu
m
a
n
A
ss
e
ss
o
rs
in
L
a
rg
e
S
c
a
le
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l
Ev
a
lu
a
ti
o
n
Ex
p
e
rim
e
n
ta
ti
o
n
,
"
M
a
la
y
sia
n
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
2
7
,
n
o
.
2
,
p
p
.
8
0
-
9
4
,
2
0
1
4
.
[1
6
]
P
a
r
n
ia
S
a
m
i
m
i
a
n
d
S
ri
De
v
i
Ra
v
a
n
a
,
“
Cre
a
ti
o
n
o
f
Re
li
a
b
le
Re
l
e
v
a
n
c
e
Ju
d
g
m
e
n
ts
in
In
f
o
r
m
a
ti
o
n
Re
tri
e
v
a
l
S
y
ste
m
s
Ev
a
lu
a
ti
o
n
Ex
p
e
rim
e
n
tatio
n
t
h
ro
u
g
h
Cro
w
d
so
u
rc
i
n
g
:
A
Re
v
ie
w
,
"
Hin
d
a
wi
P
u
b
l
ish
i
n
g
C
o
rp
o
r
a
ti
o
n
e
S
c
ien
ti
fi
c
W
o
rld
J
o
u
r
n
a
l
,
v
o
l.
2
0
1
4
,
h
tt
p
:/
/d
x
.
d
o
i.
o
rg
/1
0
.
1
1
5
5
/2
0
1
4
/1
3
5
6
4
1
.
[1
7
]
S
ri
De
v
i
Ra
v
a
n
a
,
e
t
a
l.
,
"
Ra
n
k
in
g
re
tri
e
v
a
l
s
y
ste
m
s
u
sin
g
p
se
u
d
o
re
lev
a
n
c
e
ju
d
g
m
e
n
ts,"
A
slib
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
M
a
n
a
g
e
me
n
t
,
v
o
l.
6
7
n
o
.
6
,
p
p
.
7
0
0
-
7
1
4
,
2
0
1
5
h
t
tp
s://
d
o
i.
o
rg
/
1
0
.
1
1
0
8
/A
JIM
-
03
-
2
0
1
5
-
0
0
4
6
.
[1
8
]
Da
v
id
E.
L
o
sa
d
a
,
e
t
a
l.
,
"
A
ra
n
k
fu
sio
n
a
p
p
r
o
a
c
h
b
a
se
d
o
n
sc
o
re
d
i
strib
u
ti
o
n
s
f
o
r
p
ri
o
rit
izin
g
re
lev
a
n
c
e
a
ss
e
ss
m
e
n
ts
in
i
n
f
o
rm
a
ti
o
n
re
tri
e
v
a
l
e
v
a
lu
a
ti
o
n
,
"
In
f
o
rm
a
ti
o
n
F
u
si
o
n
,
v
o
l.
3
9
,
p
p
.
5
6
-
7
1
,
Ja
n
u
a
ry
2
0
1
8
.
[1
9
]
Zi
y
in
g
Ya
n
g
,
“
Re
l
e
v
a
n
c
e
Ju
d
g
m
e
n
ts:
P
re
f
e
re
n
c
e
s,
S
c
o
re
s
a
n
d
T
ie
s,“
in
P
r
o
c
e
e
d
in
g
S
IG
IR
'
1
7
P
ro
c
e
e
d
in
g
s
o
f
th
e
4
0
t
h
I
n
tern
a
ti
o
n
a
l
A
CM
S
IG
IR
Co
n
f
e
re
n
c
e
o
n
Re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
in
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l,
p
p
.
1
3
7
3
-
1
3
7
3
S
h
in
ju
k
u
,
T
o
k
y
o
,
Ja
p
a
n
-
A
u
g
u
st 0
7
-
1
1
,
2
0
1
7
.
[2
0
]
M
a
rc
o
F
e
rra
n
te,
e
t
a
l.
,
"
M
o
d
e
ll
i
n
g
Ra
n
d
o
m
n
e
ss
in
Re
lev
a
n
c
e
Ju
d
g
m
e
n
ts an
d
Ev
a
lu
a
ti
o
n
M
e
a
su
re
s,"
in
A
d
v
a
n
c
e
s in
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l.
P
ro
c
.
4
0
th
Eu
ro
p
e
a
n
Co
n
f
e
re
n
c
e
o
n
IR
Re
se
a
rc
h
ECIR,
2
0
1
8
.
[2
1
]
S
.
B.
b
i
n
Ro
d
z
m
a
n
e
t
a
l.
,
"
Ex
p
e
r
im
e
n
t
w
it
h
Tex
t
S
u
m
m
a
riz
a
ti
o
n
a
s
a
P
o
siti
v
e
Hie
ra
rc
h
ica
l
F
u
z
z
y
L
o
g
ic
Ra
n
k
in
g
In
d
ica
to
r
f
o
r
Do
m
a
in
S
p
e
c
if
ic
Re
tri
e
v
a
l
o
f
M
a
la
y
T
r
a
n
sla
ted
Ha
d
it
h
,
"
in
2
0
1
9
IEE
E
9
t
h
S
y
m
p
o
siu
m
o
n
Co
m
p
u
te
r
A
p
p
li
c
a
ti
o
n
s &
In
d
u
str
ial
El
e
c
tro
n
ics
(IS
CA
IE)
,
M
a
lay
sia
,
2
0
1
9
,
p
p
.
2
9
9
-
3
0
4
.
d
o
i
:
1
0
.
1
1
0
9
/I
S
CA
IE.
2
0
1
9
.
8
7
4
3
9
8
8
.
[2
2
]
M
o
h
a
m
a
d
D,
e
t
a
l.
,
"
Hie
ra
rc
h
ica
l
F
u
z
z
y
L
o
g
i
c
Co
n
tro
l
S
y
ste
m
fo
r
M
a
lay
sia
n
M
o
to
r
T
a
riff
w
it
h
Risk
F
a
c
to
rs,"
Be
rr
y
M
.
,
Hj.
M
o
h
a
m
e
d
A
.
,
Ya
p
B.
(e
d
s)
S
o
f
t
Co
m
p
u
ti
n
g
in
Da
ta
S
c
ien
c
e
.
S
CDS
2
0
1
6
.
Co
m
m
u
n
ica
ti
o
n
s
i
n
Co
m
p
u
ter a
n
d
I
n
f
o
rm
a
ti
o
n
S
c
ien
c
e
,
v
o
l,
6
5
2
.
S
p
rin
g
e
r,
S
i
n
g
a
p
o
re
.
[2
3
]
A
n
il
Ku
m
a
r
T
i
w
a
ri,
e
t
a
l.
,
"
p
e
rf
o
rm
a
n
c
e
p
re
d
ictio
n
a
lg
o
rit
h
m
b
a
se
d
o
n
f
u
z
z
y
d
a
ta
m
in
in
g
,
"
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
(
IJ
-
AI)
,
v
o
l,
8
,
n
o
.
1
,
M
a
rc
h
2
0
1
9
.
[2
4
]
F
a
rz
in
P
il
tan
,
e
t
a
l.
,
"
Qu
a
li
ty
M
o
d
e
l
a
n
d
A
rti
f
icia
l
In
telli
g
e
n
c
e
B
a
se
F
u
e
l
Ra
ti
o
M
a
n
a
g
e
m
e
n
t
w
it
h
A
p
p
li
c
a
ti
o
n
s
t
o
A
u
to
m
o
ti
v
e
En
g
in
e
,
"
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Arti
fi
c
i
a
l
In
tell
ig
e
n
c
e
(
IJ
-
AI)
,
v
o
l.
3
,
n
o
.
1
,
M
a
rc
h
2
0
1
4
.
[2
5
]
T
e
jal
D.
A
p
a
le,
A
ja
y
B.
P
a
ti
l.
,
"
Op
ti
m
iza
ti
o
n
stu
d
y
o
f
f
u
z
z
y
p
a
r
a
m
e
tri
c
u
n
c
e
rtain
s
y
ste
m
,
"
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
(
IJ
-
AI)
,
v
o
l,
8
,
n
o
.
1
,
M
a
rc
h
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.