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.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
,
p
p
.
4
3
6
4
~
4
3
7
1
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
1
3
.
i4
.
p
p
4
3
6
4
-
4
3
7
1
4364
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Predic
ting lev
els
o
f
leg
a
l cas
e dif
fic
ulties using
ma
chi
ne learning
I
lm
iy
a
t
i Sa
ri,
Rif
k
i
K
o
s
a
s
ih,
Dina
I
nd
a
rt
i
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
c
s,
F
a
c
u
l
t
y
o
f
I
n
d
u
s
t
r
i
a
l
T
e
c
h
n
o
l
o
g
y
,
G
u
n
a
d
a
r
ma
U
n
i
v
e
r
s
i
t
y
,
D
e
p
o
k
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
3
,
2
0
2
4
R
ev
is
ed
Ap
r
1
,
2
0
2
4
Acc
ep
ted
Ap
r
17
,
2
0
2
4
Law
y
e
rs
p
lay
a
c
ru
c
ial
ro
le
in
t
h
e
c
o
u
rtro
o
m
,
a
ss
isti
n
g
c
li
e
n
ts
in
th
e
i
r
d
e
fe
n
se
.
Be
c
a
u
se
o
f
th
e
ir
lac
k
o
f
leg
a
l
e
x
p
e
rti
se
,
a
p
e
rso
n
o
r
o
r
g
a
n
iza
ti
o
n
fa
c
in
g
leg
a
l
issu
e
s
re
q
u
ires
p
ro
fe
ss
io
n
a
l
a
id
.
H
o
we
v
e
r,
we
n
e
e
d
to
k
n
o
w
h
o
w
m
u
c
h
m
o
n
e
y
will
b
e
sp
e
n
t
o
n
p
a
y
in
g
law
y
e
rs.
T
h
e
lev
e
l
o
f
c
o
m
p
lex
it
y
i
n
a
c
a
se
c
a
n
b
e
u
se
d
to
d
e
term
in
e
law
y
e
r
c
o
sts.
Th
e
re
f
o
re
,
in
t
h
is r
e
se
a
rc
h
,
we
p
ro
p
o
se
e
m
p
lo
y
i
n
g
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
o
lo
g
ies
,
i.
e
.
,
ra
n
d
o
m
fo
re
st
c
las
sifiers
a
n
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
(S
VM),
to
d
e
term
in
e
th
e
lev
e
l
o
f
leg
a
l
c
a
se
d
iffi
c
u
lt
ies
.
Th
e
n
o
v
e
l
ty
o
f
t
h
is
re
se
a
rc
h
is
a
p
p
ly
i
n
g
a
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
i
n
p
re
d
ictin
g
th
e
lev
e
l
o
f
d
iffi
c
u
lt
y
o
f
leg
a
l
c
a
se
s.
Th
e
d
a
ta
u
ti
li
z
e
d
c
o
n
sists
o
f
9
9
0
re
c
o
rd
s
,
wh
ich
a
re
d
i
v
id
e
d
in
to
train
i
n
g
a
n
d
tes
t
i
n
g
d
a
ta
in
a
9
0
:1
0
ra
ti
o
.
Th
e
term
fre
q
u
e
n
c
y
-
i
n
v
e
rse
d
o
c
u
m
e
n
t
fre
q
u
e
n
c
y
(
TF
-
IDF)
a
p
p
r
o
a
c
h
wa
s
t
h
e
n
u
ti
li
z
e
d
to
p
e
rfo
rm
tex
t
p
re
p
r
o
c
e
ss
in
g
.
T
h
e
tex
t
-
p
re
p
ro
c
e
ss
in
g
fi
n
d
i
n
g
s
a
re
u
ti
li
z
e
d
a
s
in
p
u
t
in
t
h
e
c
las
sifica
ti
o
n
p
r
o
c
e
ss
.
Ac
c
o
rd
in
g
t
o
th
e
re
se
a
rc
h
fin
d
i
n
g
s
,
a
n
a
c
c
u
ra
c
y
v
a
lu
e
o
f
8
5
%
,
a
v
a
lu
e
o
f
we
ig
h
te
d
a
v
e
ra
g
e
p
re
c
isio
n
is
8
8
%
,
a
n
d
a
v
a
lu
e
o
f
we
ig
h
ted
a
v
e
ra
g
e
re
c
a
ll
is
8
5
%
,
fo
r
su
p
p
o
r
t
v
e
c
to
r
m
a
c
h
i
n
e
.
Us
in
g
ra
n
d
o
m
f
o
re
st,
we
a
c
h
ie
v
e
a
n
a
c
c
u
ra
c
y
v
a
lu
e
o
f
8
9
%
,
a
v
a
lu
e
o
f
we
ig
h
te
d
a
v
e
ra
g
e
p
re
c
isio
n
is 8
5
.
6
%
,
a
n
d
a
v
a
lu
e
o
f
we
ig
h
ted
a
v
e
ra
g
e
re
c
a
ll
is 8
0
%
.
K
ey
w
o
r
d
s
:
L
awy
er
s
L
eg
al
ca
s
e
d
if
f
icu
lties
Ma
ch
in
e
lear
n
in
g
R
an
d
o
m
f
o
r
est
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
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
:
I
lm
iy
ati
Sar
i
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
I
n
d
u
s
tr
ial
T
ec
h
n
o
lo
g
y
,
Gu
n
ad
ar
m
a
Un
iv
er
s
ity
J
R
J
M+
9
7
4
,
Po
n
d
o
k
C
in
a,
B
eji,
Dep
o
k
C
ity
,
W
est J
av
a,
I
n
d
o
n
esia
E
m
ail
: ilm
iy
ati@
s
taf
f
.
g
u
n
ad
a
r
m
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
W
h
en
co
n
f
r
o
n
te
d
with
a
leg
al
s
itu
atio
n
,
m
o
s
t
p
eo
p
le
h
av
e
to
f
ir
s
t
co
n
s
u
lt
with
a
lawy
er
.
A
p
er
s
o
n
o
r
co
r
p
o
r
atio
n
th
at
is
ex
p
er
ien
cin
g
leg
al
p
r
o
b
lem
s
n
ee
d
s
p
r
o
f
es
s
io
n
al
ass
is
tan
ce
in
th
e
leg
al
f
ield
b
ec
au
s
e
o
f
th
eir
lim
ited
k
n
o
wled
g
e
o
f
cr
im
in
al
ca
s
es.
I
n
s
o
m
e
leg
al
ca
s
es,
o
th
e
r
leg
al
p
r
o
b
lem
s
o
f
ten
ar
is
e.
Fo
r
e
x
am
p
le,
s
o
m
eo
n
e
wh
o
r
ep
o
r
ts
b
ec
au
s
e
th
ey
f
ee
l
lik
e
a
v
ictim
m
ay
b
e
p
u
n
is
h
ed
b
ec
au
s
e
th
ey
c
o
u
l
d
b
e
r
ep
o
r
ted
ag
ain
.
T
h
er
ef
o
r
e,
th
e
s
er
v
ices
o
f
a
lawy
er
wh
o
u
n
d
e
r
s
tan
d
s
th
e
law
well
ar
e
n
ee
d
ed
s
o
th
a
t
th
ese
p
r
o
b
lem
s
ca
n
b
e
r
eso
lv
ed
.
E
v
er
y
th
in
g
leg
al
ca
n
b
e
ea
s
ily
ex
p
lain
ed
a
n
d
u
n
d
er
s
to
o
d
with
th
e
h
elp
o
f
a
lawy
e
r
.
Hir
in
g
a
lawy
er
ca
n
g
iv
e
n
u
m
er
o
u
s
b
e
n
ef
its
,
in
clu
d
in
g
p
r
e
v
en
tin
g
clien
ts
f
r
o
m
g
ettin
g
in
to
lar
g
e
r
tr
o
u
b
les an
d
a
n
ticip
atin
g
t
h
e
wo
r
s
t
-
ca
s
e
s
ce
n
ar
io
s
th
at
m
ay
ar
is
e.
As
a
r
esu
lt,
en
g
ag
in
g
a
s
k
illed
lawy
er
ca
n
ass
is
t
th
e
clien
t
m
ak
e
a
b
etter
d
ec
is
io
n
an
d
a
v
o
id
a
h
ar
s
h
e
r
t
r
ial
v
er
d
ict.
Ho
we
v
er
,
th
e
m
o
s
t
im
p
o
r
tan
t
c
o
n
s
id
er
atio
n
wh
e
n
h
ir
in
g
a
lawy
er
is
th
e
co
s
t.
T
h
e
am
o
u
n
t
o
f
leg
al
f
ee
s
is
ty
p
ically
d
eter
m
in
ed
b
y
th
e
d
if
f
icu
lty
o
f
th
e
ca
s
e
at
h
an
d
.
T
o
d
eter
m
in
e
th
e
lev
el
o
f
d
if
f
icu
lty
o
f
th
e
ca
s
e
b
ein
g
f
ac
ed
,
lawy
er
s
u
s
u
all
y
ask
q
u
esti
o
n
s
s
u
ch
as wh
at
t
y
p
e
o
f
ca
s
e
is
b
ei
n
g
f
ac
ed
,
wh
at
ev
id
en
ce
h
as
b
ee
n
o
b
tain
ed
,
an
d
th
e
esti
m
ated
len
g
th
o
f
tim
e
th
e
clien
t
will
r
ec
eiv
e
th
e
s
en
ten
ce
.
T
o
h
elp
s
p
ee
d
u
p
d
eter
m
in
in
g
th
e
lev
el
o
f
d
if
f
icu
lty
o
f
a
ca
s
e,
in
th
is
r
esear
ch
we
p
r
o
p
o
s
e
a
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
,
i.e
.
,
a
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
an
d
a
r
a
n
d
o
m
f
o
r
est
class
if
ier
.
Ma
ch
in
e
lear
n
in
g
is
an
alg
o
r
ith
m
u
s
ed
t
o
p
er
f
o
r
m
lea
r
n
in
g
b
ased
o
n
tr
ain
i
n
g
d
ata.
On
e
u
s
e
o
f
m
ac
h
i
n
e
lear
n
in
g
is
f
o
r
class
if
icatio
n
,
i.e
.
,
SVM
an
d
r
an
d
o
m
f
o
r
est.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2
2
5
2
-
8
9
3
8
P
r
ed
ictin
g
leve
ls
o
f le
g
a
l c
a
s
e
d
iffi
cu
lties
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
(
I
lmiya
ti S
a
r
i)
4365
Sev
er
al
p
r
ev
i
o
u
s
s
tu
d
ies
h
av
e
m
ad
e
p
r
e
d
ictio
n
s
in
th
e
leg
al
f
ield
,
i.e
.
,
Şu
lea
et
a
l.
[
1
]
p
r
ed
icted
ca
s
e
d
ec
is
io
n
s
at
th
e
Fre
n
ch
s
u
p
r
em
e
co
u
r
t
u
s
in
g
d
ata
f
r
o
m
Fre
n
ch
h
ig
h
co
u
r
t
leg
al
d
ec
is
io
n
s
u
s
in
g
th
e
SVM
m
eth
o
d
with
a
lin
ea
r
k
er
n
el.
I
n
h
is
r
esear
ch
,
f
1
s
co
r
e
o
f
7
5
.
9
%
was
o
b
tain
ed
[
1
]
.
B
h
ilar
e
et
a
l
.
[
2
]
em
p
lo
y
ed
d
escr
ip
tiv
e
d
ata
f
r
o
m
le
g
al
ca
s
es
to
esti
m
ate
th
e
r
esu
lt
o
f
co
u
r
t
d
ec
is
io
n
s
u
s
in
g
th
e
n
aiv
e
b
ay
es
an
d
SVM.
I
n
th
e
r
esu
lt,
SVM
u
s
in
g
a
lin
ea
r
k
er
n
el
p
er
f
o
r
m
ed
7
8
%
b
etter
th
an
n
ai
v
e
B
ay
es
[
2
]
.
Su
p
p
o
r
t
v
ec
to
r
r
eg
r
ess
io
n
with
a
lin
ea
r
k
er
n
el
is
also
u
s
ed
i
n
r
esear
c
h
f
r
o
m
[
3
]
to
id
en
tify
ca
s
es
at
th
e
E
u
r
o
p
ea
n
c
o
u
r
t.
T
h
e
d
ata
u
tili
ze
d
co
m
p
r
is
es
ca
s
es
r
elev
an
t
to
th
e
co
n
v
en
tio
n
'
s
p
ar
ag
r
ap
h
s
3
,
6
,
an
d
8
.
Acc
o
r
d
in
g
to
th
e
r
esear
ch
r
esu
lts
,
an
ac
cu
r
ac
y
r
ate
o
f
7
9
%
was
ac
h
iev
ed
[
3
]
.
Fu
r
th
e
r
m
o
r
e,
Katz
et
a
l.
[
4
]
em
p
l
o
y
s
th
e
r
an
d
o
m
f
o
r
est
to
esti
m
ate
th
e
b
eh
av
i
o
r
o
f
th
e
US Su
p
r
em
e
C
o
u
r
t i
n
a
g
en
e
r
a
l e
n
v
ir
o
n
m
en
t.
T
h
e
ca
s
e
-
lev
el
an
d
v
o
te
-
ju
s
tice
d
ata
ar
e
f
r
o
m
th
e
d
atab
ase
o
f
th
e
US
Su
p
r
em
e
C
o
u
r
t.
Acc
o
r
d
in
g
to
th
e
r
esear
ch
r
esu
lts
,
at
th
e
ca
s
e
lev
el,
th
e
v
alu
e
o
f
ac
c
u
r
ac
y
is
7
0
.
2
%,
wh
ile
at
th
e
s
o
u
n
d
f
air
n
ess
lev
el,
th
e
v
alu
e
o
f
ac
cu
r
ac
y
is
7
1
.
9
%
[
4
]
.
P
r
e
d
i
c
ti
o
n
s
o
f
c
o
u
r
t
c
a
s
e
s
i
n
I
n
d
o
n
e
s
i
a
w
e
r
e
p
r
e
d
i
c
te
d
u
s
i
n
g
t
e
r
m
f
r
e
q
u
e
n
c
y
-
i
n
v
e
r
s
e
d
o
c
u
m
e
n
t
f
r
e
q
u
e
n
c
y
(
TF
-
I
D
F
)
a
n
d
t
h
e
k
-
n
e
a
r
e
s
t
n
e
ig
h
b
o
r
s
(
KNN
)
a
l
g
o
r
i
t
h
m
i
n
a
s
t
u
d
y
[
5
]
.
T
h
e
d
a
t
a
u
t
il
i
z
e
d
i
s
1
0
0
d
a
t
a
p
o
i
n
ts
f
r
o
m
B
a
n
d
u
n
g
d
i
s
t
r
i
ct
c
o
u
r
t
s
e
n
t
e
n
ce
d
e
c
i
s
i
o
n
s
.
A
c
c
o
r
d
i
n
g
t
o
h
is
s
t
u
d
y
,
t
h
e
r
e
a
r
e
f
o
u
r
c
a
t
e
g
o
r
i
e
s
o
f
l
e
g
a
l
c
a
s
es
:
s
m
a
ll
c
r
i
m
i
n
a
l
ca
s
es
,
m
e
d
i
u
m
c
r
i
m
i
n
a
l
c
as
e
s
,
h
u
g
e
c
r
i
m
i
n
a
l
c
a
s
e
s
,
an
d
c
o
r
r
u
p
t
i
o
n
c
a
s
es
.
A
n
a
cc
u
r
a
c
y
r
a
t
e
i
n
h
is
r
es
e
a
r
c
h
i
s
8
6
.
6
6
6
7
%
,
a
p
r
e
c
is
i
o
n
v
a
l
u
e
i
s
8
5
.
2
8
6
2
%
,
a
n
d
a
r
e
c
a
ll
v
a
l
u
e
i
s
8
6
.
6
6
6
7
%
.
F
u
r
t
h
e
r
m
o
r
e
,
S
a
r
i
e
t
a
l
.
[
6
]
e
m
p
l
o
y
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
n
g
s
e
n
t
e
n
c
e
l
e
n
g
t
h
.
T
h
e
d
a
t
a
u
s
ed
c
o
n
s
is
t
s
o
f
1
0
0
s
e
n
t
e
n
c
es
o
f
d
e
c
i
s
i
o
n
d
at
a
.
I
n
h
is
r
e
s
e
a
r
c
h
,
c
as
e
s
w
e
r
e
g
r
o
u
p
e
d
i
n
t
o
t
h
r
e
e
c
l
a
s
s
es
,
n
a
m
e
l
y
c
la
s
s
1
f
o
r
i
m
p
r
i
s
o
n
m
e
n
t
o
f
l
e
s
s
t
h
a
n
5
y
e
a
r
s
,
c
l
a
s
s
2
f
o
r
i
m
p
r
i
s
o
n
m
e
n
t
o
f
5
-
1
0
y
e
a
r
s
,
a
n
d
c
l
a
s
s
3
f
o
r
i
m
p
r
i
s
o
n
m
e
n
t
o
f
m
o
r
e
t
h
a
n
1
0
y
e
a
r
s
.
T
h
e
l
o
n
g
e
r
t
h
e
p
r
i
s
o
n
p
e
r
i
o
d
t
h
e
y
r
e
c
e
i
v
e
,
t
h
e
m
o
r
e
c
o
m
p
l
ic
a
t
e
d
t
h
e
l
e
g
a
l
c
as
es
t
h
e
y
f
a
ce
b
e
c
o
m
e
.
T
h
e
a
p
p
r
o
a
c
h
e
s
e
m
p
l
o
y
e
d
i
n
c
l
u
d
e
n
a
i
v
e
B
a
y
e
s
a
n
d
KN
N
.
T
h
e
K
N
N
h
a
s
a
n
a
c
c
u
r
a
c
y
r
a
te
is
8
4
%
,
a
p
r
e
c
i
s
i
o
n
is
9
0
%
,
a
n
d
a
r
ec
a
l
l
i
s
8
4
%
.
T
h
e
n
a
i
v
e
B
a
y
es
c
l
a
s
s
i
f
ie
r
h
a
s
a
n
a
cc
u
r
a
c
y
r
a
t
e
is
8
0
%
,
a
p
r
e
c
is
i
o
n
is
7
2
.
1
6
8
4
4
%
,
a
n
d
a
r
e
c
a
ll
is
8
0
%
.
B
ased
o
n
p
r
ev
io
u
s
r
esear
c
h
,
SVM
ca
n
b
e
u
s
ed
to
p
r
ed
ict
o
r
id
en
tify
leg
al
ca
s
es
[
1
]
,
[
2
]
.
M
ea
n
wh
ile,
alter
n
ativ
e
m
ac
h
in
e
lear
n
in
g
a
lg
o
r
ith
m
s
,
i.e
.
,
n
aiv
e
B
ay
es a
n
d
KNN,
h
av
e
b
ee
n
u
s
ed
in
a
s
tu
d
y
[
6
]
to
esti
m
ate
th
e
len
g
th
o
f
p
u
n
is
h
m
en
t
u
s
in
g
1
0
0
d
ata.
T
h
is
s
tu
d
y
co
n
t
in
u
es
th
e
r
esear
ch
o
f
[
6
]
,
w
h
ich
r
ec
o
m
m
en
d
e
d
em
p
lo
y
in
g
an
o
th
er
m
ac
h
in
e
le
ar
n
in
g
al
g
o
r
ith
m
s
,
i.e
.
,
SVM
a
n
d
r
a
n
d
o
m
f
o
r
est,
to
p
r
ed
ict
th
e
lev
el
o
f
d
if
f
ic
u
lty
o
f
a
leg
al
ca
s
e.
T
h
e
d
ata
u
s
ed
in
th
is
r
esear
ch
was
e
x
p
an
d
e
d
to
9
9
0
le
g
al
d
ec
is
io
n
d
ata
c
o
n
tain
in
g
ev
id
en
ce
u
s
ed
in
th
e
ca
s
e.
2.
M
E
T
H
O
D
T
o
p
r
ed
ict
th
e
lev
el
o
f
d
if
f
icu
l
ty
o
f
a
leg
al
ca
s
e,
n
u
m
er
o
u
s
s
tag
es
ar
e
r
eq
u
ir
ed
,
as
s
h
o
wn
in
Fig
u
r
e
1
.
W
e
co
llected
990
d
ata
f
r
o
m
th
e
B
an
d
u
n
g
d
is
tr
ict
co
u
r
t.
T
h
is
d
ata
r
ep
r
esen
ts
ca
s
e
d
ec
is
i
o
n
s
at
th
e
B
an
d
u
n
g
Dis
tr
ict
C
o
u
r
t.
T
h
e
d
ec
is
io
n
co
n
tain
s
th
e
attr
ib
u
tes
o
f
t
h
e
ev
id
en
ce
a
n
d
th
e
len
g
th
o
f
th
e
d
ef
en
d
a
n
t'
s
p
u
n
is
h
m
en
t.
T
h
ese
attr
ib
u
tes
will b
e
u
s
ed
as f
ea
tu
r
es to
p
r
e
d
ict
th
e
d
if
f
icu
lty
lev
el
o
f
a
ca
s
e.
Fig
u
r
e
1
.
T
h
e
f
lo
wch
a
r
t o
f
t
h
e
AI
-
b
ased
m
o
d
els an
d
ex
p
er
im
en
tal
m
eth
o
d
s
ap
p
lied
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
3
6
4
-
4
3
7
1
4366
T
h
e
d
ata
is
d
iv
id
ed
in
to
4
ca
t
eg
o
r
ies
b
ased
o
n
th
e
lev
el
o
f
ca
s
e
d
if
f
icu
lty
.
W
e
d
iv
id
e
t
h
e
d
ata
in
to
a
tr
ain
in
g
an
d
a
test
in
g
d
ataset
with
a
r
atio
o
f
9
0
:1
0
.
T
h
e
n
ex
t
s
tag
e
is
to
ca
r
r
y
o
u
t
p
r
e
p
r
o
ce
s
s
in
g
o
n
th
e
s
en
te
n
ce
d
ec
is
io
n
d
ata
s
o
th
at
th
e
d
ata
c
an
b
e
u
s
ed
.
2
.
1
.
Da
t
a
prepro
ce
s
s
ing
Data
p
r
ep
r
o
ce
s
s
in
g
is
u
s
ed
to
r
em
o
v
e
n
o
is
e
f
r
o
m
th
e
d
ata.
I
n
th
is
s
tu
d
y
,
we
u
s
e
f
o
u
r
s
tep
s
,
i.e
.
,
ca
s
e
f
o
ld
in
g
,
to
k
en
izin
g
,
s
to
p
p
in
g
wo
r
d
s
,
an
d
s
tem
m
in
g
.
T
h
e
ca
s
e
f
o
ld
in
g
s
tag
e
in
v
o
lv
es
ch
an
g
in
g
ca
p
ital
letter
s
to
lo
wer
ca
s
e.
T
h
e
n
ex
t
s
tag
e
is
t
h
e
to
k
en
izin
g
s
tag
e,
wh
ich
in
v
o
lv
es
b
r
ea
k
in
g
d
o
wn
s
en
ten
c
es
in
to
s
in
g
le
wo
r
d
s
[
7
]
.
T
h
e
n
e
x
t
s
tag
e
is
to
d
o
f
ilt
er
in
g
b
y
p
e
r
f
o
r
m
in
g
s
to
p
wo
r
d
r
em
o
v
al,
wh
ich
m
ea
n
s
th
at
ev
er
y
wo
r
d
g
e
n
er
ated
b
y
to
k
e
n
izin
g
is
r
e
v
iewe
d
,
a
n
d
an
y
p
r
e
p
o
s
itio
n
s
th
at
h
a
v
e
n
o
th
in
g
to
d
o
with
a
n
aly
s
is
ar
e
elim
in
ated
[
8
]
.
Stem
m
in
g
is
th
e
last
s
tag
e
o
f
p
r
ep
r
o
ce
s
s
in
g
.
I
n
th
is
s
tep
,
wo
r
d
s
ar
e
ch
a
n
g
ed
to
b
asic
wo
r
d
s
[
9
]
.
I
n
t
h
e
n
e
x
t
s
tag
e,
we
p
er
f
o
r
m
weig
h
tin
g
o
f
wo
r
d
s
.
2
.
2
.
Weig
hting
o
f
wo
rd
W
eig
h
tin
g
o
f
wo
r
d
s
is
th
e
p
r
o
ce
s
s
o
f
ass
ig
n
in
g
weig
h
ts
to
e
ac
h
wo
r
d
b
y
u
s
in
g
th
e
T
F
-
I
DF
ap
p
r
o
ac
h
,
as
in
(
1
)
an
d
(
2
)
,
s
o
th
at
it
m
a
y
b
e
u
tili
ze
d
as
in
p
u
t
in
th
e
class
if
icatio
n
.
T
h
e
p
h
ases
o
f
wo
r
d
weig
h
tin
g
u
s
in
g
TF
-
I
DF
ar
e
as
f
o
llo
ws
[
1
0
]
.
T
h
e
in
itial
s
tep
in
wo
r
d
weig
h
tin
g
is
to
co
m
p
u
te
th
e
ter
m
f
r
eq
u
en
cies
(
T
F)
f
o
r
ea
ch
wo
r
d
.
Sen
ten
ce
s
th
at
h
av
e
b
ee
n
b
r
o
k
en
d
o
wn
in
to
wo
r
d
s
will
b
e
s
co
r
ed
.
E
ac
h
w
o
r
d
will
b
e
ass
ig
n
ed
a
v
alu
e
o
f
1
.
T
h
e
f
o
llo
win
g
s
tep
is
to
d
et
er
m
in
e
th
e
d
o
cu
m
en
t
f
r
eq
u
e
n
c
ies
(
DF)
f
o
r
ea
ch
wo
r
d
b
y
s
u
m
m
in
g
th
e
T
F
v
alu
es
f
o
r
ea
ch
wo
r
d
.
T
h
e
th
ir
d
s
tag
e
is
to
co
m
p
u
te
th
e
in
v
er
s
e
d
o
c
u
m
en
t f
r
e
q
u
en
cies (
I
DF)
as in
(
1
)
.
(
)
=
l
og
(
(
)
)
(
1
)
Af
ter
th
at,
we
ass
ig
n
a
weig
h
t
to
ea
ch
wo
r
d
.
W
e
m
u
ltip
ly
th
e
T
F v
alu
e
b
y
th
e
I
DF a
s
in
(
2
)
.
=
×
l
og
(
2
)
T
h
e
wo
r
d
weig
h
tin
g
r
esu
lts
will
b
e
u
tili
ze
d
as
in
p
u
t
f
o
r
th
e
cl
ass
if
icatio
n
p
r
o
ce
s
s
,
wh
ich
will
em
p
lo
y
t
h
e
SVM
an
d
r
an
d
o
m
f
o
r
est cla
s
s
if
ier
.
2
.
3
.
Su
pp
o
rt
v
ec
t
o
r
ma
chine
I
n
SVM,
we
f
in
d
th
e
h
y
p
e
r
p
l
an
e
in
th
e
f
ea
tu
r
e
s
p
ac
e
th
at
b
est
d
iv
id
es
th
e
d
ata
in
to
d
is
tin
ct
class
e
s
[
1
1
]
,
as sh
o
w
n
in
(
3
)
.
(
)
=
∙
+
(
3
)
wh
er
e
(
)
is
s
u
b
s
p
ac
e
o
f
s
et
o
f
h
y
p
er
p
lan
es,
is
s
p
ac
e
o
f
in
p
u
t,
is
weig
h
ted
v
ec
to
r
,
an
d
is
b
ias.
A
lin
e
is
ca
lled
a
h
y
p
er
p
la
n
e
in
two
d
i
m
en
s
io
n
s
.
I
t
r
e
f
er
s
to
s
u
b
s
p
ac
e
in
h
ig
h
er
d
im
en
s
io
n
s
.
T
h
e
m
ar
g
in
is
th
e
d
is
tan
ce
b
etwe
en
th
e
h
y
p
e
r
p
lan
e
an
d
th
e
clo
s
est
d
ata
p
o
in
t
f
r
o
m
e
ac
h
class
,
an
d
SVM
s
ee
k
s
t
h
e
h
y
p
e
r
p
lan
e
th
at
m
ax
im
izes th
is
[
1
2
]
–
[
1
5
]
.
As s
ee
n
in
Fig
u
r
e
2
,
th
e
clo
s
est d
ata
p
o
in
t is ca
lled
th
e
s
u
p
p
o
r
t
v
ec
to
r
.
Fig
u
r
e
2
.
T
h
e
m
ec
h
a
n
is
m
o
f
S
VM
B
y
u
tili
zin
g
a
k
e
r
n
el
tr
ick
,
SVM
ca
n
h
a
n
d
le
n
o
n
-
lin
ea
r
d
ec
is
i
o
n
b
o
u
n
d
ar
ies
[
1
6
]
–
[
1
9
]
.
T
h
e
f
ea
tu
r
es
o
f
th
e
in
p
u
t
m
u
s
t
b
e
m
ap
p
ed
in
o
r
d
er
to
co
n
s
tr
u
ct
a
lin
e
ar
d
e
cisi
o
n
b
o
u
n
d
ar
y
.
I
n
SVM,
th
e
r
e
ar
e
th
r
ee
k
er
n
e
l
f
u
n
ctio
n
s
,
i.e
.
,
lin
ea
r
,
th
e
r
ad
ia
l
b
asis
f
u
n
ctio
n
(
R
B
F)
an
d
p
o
l
y
n
o
m
ial
k
er
n
els
[
2
0
]
–
[
2
2
]
.
I
n
p
r
ac
tical
s
ce
n
ar
io
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2
2
5
2
-
8
9
3
8
P
r
ed
ictin
g
leve
ls
o
f le
g
a
l c
a
s
e
d
iffi
cu
lties
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
(
I
lmiya
ti S
a
r
i)
4367
wh
er
e
th
e
d
ata
ex
h
ib
its
s
o
m
e
o
v
er
lap
o
r
is
n
o
t
en
tire
ly
s
ep
a
r
ab
le,
SVM
ca
n
b
e
ex
ten
d
ed
t
o
ac
co
m
m
o
d
ate
a
ce
r
tain
d
eg
r
ee
o
f
m
is
class
if
icatio
n
.
T
h
is
e
x
ten
s
io
n
is
k
n
o
wn
as
a
"so
f
t
m
ar
g
in
,
"
an
d
th
e
SV
M
alg
o
r
ith
m
s
tr
iv
es
to
f
in
d
a
b
alan
ce
b
etwe
en
m
a
x
im
izin
g
th
e
m
ar
g
in
an
d
m
in
i
m
izin
g
m
is
class
if
icatio
n
s
.
On
ce
th
e
h
y
p
er
p
lan
e
is
estab
lis
h
ed
,
th
e
p
r
o
ce
s
s
o
f
class
if
y
in
g
a
n
ew
d
ata
p
o
in
t
in
v
o
lv
es
d
eter
m
in
in
g
o
n
wh
ic
h
s
id
e
o
f
th
e
h
y
p
e
r
p
lan
e
it
r
esid
es
[
2
3
]
,
[
2
4
]
.
SVM
f
in
d
e
x
ten
s
iv
e
a
p
p
licatio
n
s
in
d
iv
er
s
e
f
ield
s
s
u
c
h
as
im
ag
e
class
if
icatio
n
,
tex
t
ca
teg
o
r
izatio
n
,
an
d
b
io
in
f
o
r
m
atics.
T
h
eir
ef
f
ec
tiv
en
ess
lies
in
th
eir
ad
ep
tn
ess
at
m
an
ag
in
g
in
tr
icate
r
elatio
n
s
h
ip
s
with
in
d
ata
an
d
e
x
h
ib
itin
g
r
o
b
u
s
t g
e
n
er
aliza
tio
n
to
p
r
ev
i
o
u
s
ly
u
n
s
ee
n
d
ata.
2
.
4
.
Ra
nd
o
m
f
o
re
s
t
cl
a
s
s
if
ier
A
r
an
d
o
m
f
o
r
est en
s
em
b
le
lea
r
n
in
g
a
p
p
r
o
ac
h
is
u
s
ed
f
o
r
class
if
icatio
n
.
I
t g
e
n
er
ates a
h
u
g
e
n
u
m
b
er
o
f
d
ec
is
io
n
tr
ee
s
d
u
r
in
g
tr
ai
n
in
g
,
th
en
p
r
o
d
u
ce
s
th
e
m
ea
n
p
r
e
d
ictio
n
,
o
r
th
e
m
o
d
e
o
f
th
e
cl
ass
es
f
o
r
ea
ch
tr
ee
[
2
5
]
–
[
2
8
]
.
A
co
m
p
r
eh
e
n
s
iv
e
o
u
tlin
e
o
f
th
e
r
an
d
o
m
f
o
r
est alg
o
r
ith
m
is
p
r
o
v
id
ed
:
−
R
an
d
o
m
s
am
p
lin
g
with
r
ep
lac
em
en
t
u
s
in
g
b
o
o
ts
tr
ap
s
:
ch
o
o
s
e
a
p
o
r
tio
n
o
f
th
e
tr
ain
in
g
d
ata
at
r
an
d
o
m
u
s
in
g
r
ep
lace
m
en
t.
T
h
is
im
p
lies
th
at
ce
r
tain
ca
s
es m
ig
h
t b
e
in
cl
u
d
ed
twice
in
th
e
s
u
b
s
et
an
d
o
th
e
r
s
m
ig
h
t n
o
t.
−
Featu
r
e
r
an
d
o
m
izatio
n
:
f
o
r
ea
ch
d
ec
is
io
n
tr
ee
n
o
d
e,
o
n
l
y
a
r
an
d
o
m
f
ea
tu
r
e
is
co
n
s
id
er
ed
f
o
r
s
p
litt
in
g
.
T
h
is
co
n
tr
ib
u
tes to
th
e
in
tr
o
d
u
ctio
n
o
f
tr
ee
d
iv
er
s
ity
.
−
B
u
ild
in
g
d
ec
is
io
n
tr
ee
s
:
d
ev
elo
p
a
d
ec
is
io
n
tr
ee
f
o
r
ea
ch
co
llectio
n
o
f
f
ea
tu
r
es
an
d
d
at
a.
R
ec
u
r
s
iv
ely
,
g
r
o
win
g
th
e
tr
ee
in
v
o
lv
es
p
er
io
d
ically
d
iv
id
i
n
g
t
h
e
d
ata
ac
co
r
d
in
g
to
t
h
e
ch
o
s
en
f
ea
tu
r
e
s
u
n
til
a
h
altin
g
co
n
d
itio
n
is
s
atis
f
ied
(
e.
g
.
,
m
i
n
im
u
m
s
am
p
les p
er
lea
f
an
d
m
ax
im
u
m
d
ep
th
attain
ed
)
.
−
Vo
tin
g
o
r
a
v
er
ag
in
g
:
in
class
if
icatio
n
,
ea
ch
tr
ee
"v
o
tes"
f
o
r
a
c
lass
,
an
d
th
e
class
with
th
e
m
o
s
t
v
o
tes
b
ec
o
m
e
th
e
p
r
ed
icted
class
.
T
o
d
eter
m
in
e
th
e
f
in
al
r
e
g
r
ess
io
n
p
r
ed
icti
o
n
f
o
r
a
g
iv
e
n
r
eg
r
ess
io
n
task
,
th
e
p
r
ed
ictio
n
s
m
ad
e
b
y
ea
ch
tr
ee
a
r
e
av
er
a
g
e
d
.
−
C
o
llectiv
e
o
u
tco
m
e:
th
e
co
m
b
in
ed
o
u
tc
o
m
e
o
f
ea
ch
i
n
d
iv
i
d
u
al
tr
ee
is
th
e
u
ltima
te
o
u
tp
u
t.
T
h
r
o
u
g
h
th
e
r
ed
u
ctio
n
o
f
o
v
e
r
f
itti
n
g
a
n
d
t
h
e
ca
p
tu
r
e
o
f
a
m
o
r
e
r
o
b
u
s
t
p
atter
n
in
th
e
d
ata,
th
is
en
s
e
m
b
le
tech
n
iq
u
e
co
n
tr
ib
u
tes to
th
e
en
h
a
n
ce
m
en
t o
f
th
e
m
o
d
el'
s
r
esil
ien
ce
an
d
g
en
er
aliza
tio
n
.
T
h
e
b
en
ef
its
o
f
r
a
n
d
o
m
f
o
r
est
ar
e
h
ig
h
ac
cu
r
ac
y
,
r
o
b
u
s
tn
es
s
to
o
v
er
f
itti
n
g
,
an
d
f
ea
tu
r
e
i
m
p
o
r
tan
ce
.
T
h
e
d
r
awb
ac
k
s
o
f
u
s
in
g
r
an
d
o
m
f
o
r
est
ar
e
co
m
p
lex
ity
an
d
co
m
p
u
tatio
n
al
c
o
s
t
[
2
9
]
.
R
an
d
o
m
f
o
r
ests
ar
e
a
wid
ely
u
s
ed
ap
p
r
o
ac
h
b
ec
au
s
e
th
ey
m
ay
b
e
u
s
ed
f
o
r
a
wid
e
r
an
g
e
o
f
ac
tiv
ities
a
n
d
d
ata
ty
p
es.
T
h
ey
ar
e
wid
ely
u
s
ed
in
m
ac
h
in
e
lear
n
in
g
d
u
e
to
th
eir
r
o
b
u
s
tn
ess
an
d
ab
ilit
y
t
o
m
an
ag
e
co
m
p
le
x
d
ata
in
ter
a
ctio
n
s
.
2
.
5
.
E
v
a
lua
t
i
o
n m
o
del
W
e
ev
alu
ate
th
e
m
o
d
el
b
y
ca
l
cu
latin
g
ac
cu
r
ac
y
(
Acc
)
,
p
r
ec
i
s
io
n
an
d
r
ec
all
as
in
(
4
)
to
(
6
)
[
3
0
]
–
[
3
2
]
.
Acc
u
r
ac
y
is
o
n
e
o
f
th
e
m
etr
ic
s
u
s
ed
to
m
ea
s
u
r
e
th
e
ac
cu
r
ac
y
o
f
d
ata
b
y
ca
lcu
latin
g
th
e
c
o
m
p
ar
is
o
n
b
etwe
en
th
e
co
r
r
ec
t
p
r
e
d
ictio
n
s
an
d
th
e
en
tire
d
ata.
Pre
cisi
o
n
is
th
e
co
m
p
ar
is
o
n
b
etwe
en
tr
u
e
p
o
s
itiv
e
p
r
ed
ictio
n
s
an
d
th
e
o
v
er
all
p
o
s
itiv
e
p
r
ed
icted
r
esu
lts
,
wh
ile
r
ec
all
is
th
e
co
m
p
ar
is
o
n
b
etwe
en
tr
u
e
p
o
s
itiv
e
p
r
ed
ictio
n
s
a
n
d
all
tr
u
e
p
o
s
itiv
e
d
ata.
Fo
r
m
u
lti
-
c
lass
ca
s
es,
weig
h
tin
g
is
n
ee
d
e
d
to
ca
lcu
late
p
r
ec
is
io
n
an
d
r
e
ca
ll
u
s
in
g
weig
h
ted
av
er
ag
e
p
r
ec
is
io
n
(
W
AP)
an
d
weig
h
ted
av
er
a
g
e
r
ec
all
(
W
AR
)
as in
(
7
)
an
d
(
8
)
.
=
+
+
+
+
×
100%
(
4
)
=
+
×
100%
(
5
)
=
∑
=
1
∑
=
1
(
6
)
=
+
×
100%
(
7
)
=
∑
=
1
∑
=
1
(
8
)
with
T
P
an
d
T
N
a
r
e
tr
u
e
p
o
s
i
tiv
e
an
d
tr
u
e
n
e
g
ativ
e,
FP
an
d
FN
ar
e
f
alse
p
o
s
itiv
e
an
d
f
alse
n
eg
ativ
e,
p
k
is
p
r
ec
is
io
n
in
k
class
,
d
k
is
ac
tu
al
d
ata
in
th
e
class
,
an
d
r
k
is
r
ec
all
in
class
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
o
u
r
r
esear
c
h
,
we
c
o
llect
9
9
0
d
ata
o
n
s
en
ten
ce
d
ec
is
io
n
s
a
t th
e
B
an
d
u
n
g
Dis
tr
ict
C
o
u
r
t.
W
e
d
iv
id
ed
th
e
d
ata
in
to
two
d
atasets
:
tr
ain
in
g
an
d
test
in
g
,
with
a
r
atio
o
f
9
0
:1
0
.
1
c
o
n
tain
s
ex
am
p
les
o
f
th
e
d
ata
th
at
h
as
b
ee
n
co
llected
.
T
ab
le
1
d
ata
f
r
o
m
s
en
ten
cin
g
d
ec
is
io
n
s
at
th
e
b
an
d
u
n
g
d
is
tr
ict
co
u
r
t (
4
o
f
9
9
0
d
ataset)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
3
6
4
-
4
3
7
1
4368
T
ab
le
1
.
Data
s
et
o
f
s
en
ten
cin
g
d
ec
is
io
n
s
at
th
e
b
an
d
u
n
g
d
is
tr
ict
co
u
r
t (
4
o
f
9
9
0
d
ataset)
D
e
c
i
s
i
o
n
C
o
d
e
S
t
a
t
e
d
t
h
a
t
t
h
e
d
e
f
e
n
d
a
n
t
G
R
ED
Y
P
A
N
TER
A
A
l
s
I
Y
A
N
G
B
i
n
G
U
G
U
N
G
U
N
A
W
A
N
w
a
s
p
r
o
v
e
n
t
o
h
a
v
e
c
o
mm
i
t
t
e
d
t
h
e
c
r
i
m
i
n
a
l
a
c
t
"
A
t
t
e
m
p
t
o
r
e
v
i
l
c
o
n
sp
i
r
a
c
y
t
o
c
o
mm
i
t
a
N
a
r
c
o
t
i
c
s
c
r
i
me
w
i
t
h
o
u
t
a
n
y
r
i
g
h
t
o
r
a
g
a
i
n
s
t
t
h
e
l
a
w
t
o
p
o
ss
e
ss,
k
e
e
p
i
n
p
o
ss
e
ssi
o
n
o
f
o
r
p
r
o
v
i
d
e
C
l
a
s
s
I
N
a
r
c
o
t
i
c
s
w
h
i
c
h
a
r
e
n
o
t
p
l
a
n
t
s
a
s
i
n
t
e
n
d
e
d
i
n
p
a
r
a
g
r
a
p
h
(
1
)
w
e
i
g
h
i
n
g
mo
r
e
t
h
a
n
5
(
f
i
v
e
)
g
r
a
ms”
2
.
T
h
e
d
e
f
e
n
d
a
n
t
G
R
ED
Y
P
A
N
TER
A
A
l
s
I
Y
A
N
G
B
i
n
G
U
G
U
N
G
U
N
A
W
A
N
w
a
s
sen
t
e
n
c
e
d
t
o
i
m
p
r
i
s
o
n
me
n
t
f
o
r
7
(
se
v
e
n
)
y
e
a
r
s
a
n
d
a
f
i
n
e
o
f
R
p
.
1
,
0
0
0
,
0
0
0
,
0
0
0
.
3
.
S
t
a
t
e
e
v
i
d
e
n
c
e
i
n
t
h
e
f
o
r
m
o
f
;
1
b
o
x
o
f
S
a
m
p
o
e
r
n
a
M
i
l
d
c
i
g
a
r
e
t
t
e
s
c
o
n
t
a
i
n
s
t
w
o
sma
l
l
p
l
a
st
i
c
c
l
i
p
p
a
c
k
a
g
e
s
o
f
c
r
y
st
a
l
met
h
a
mp
h
e
t
a
m
i
n
e
w
e
i
g
h
i
n
g
0
.
3
2
6
0
g
r
a
ms
.
2
0
(
t
w
e
n
t
y
)
sma
l
l
p
l
a
st
i
c
c
l
i
p
p
a
c
k
a
g
e
s
o
f
N
a
r
k
o
t
i
j
a
t
y
p
e
c
r
y
st
a
l
m
e
t
h
a
m
p
h
e
t
a
mi
n
e
w
e
i
g
h
i
n
g
5
.
2
5
2
5
g
r
a
ms.
1
u
n
i
t
o
f
O
p
p
o
b
r
a
n
d
c
e
l
l
p
h
o
n
e
;
3
S
t
a
t
e
d
t
h
a
t
t
h
e
D
e
f
e
n
d
a
n
t
s
:
1
.
A
s
e
p
W
a
r
man
b
i
n
M
a
ma
t
,
2
.
Y
a
d
i
S
e
t
i
a
d
i
a
l
i
a
s
Ta
h
u
b
i
n
M
a
ma
t
R
a
h
m
a
t
,
3
.
T
a
t
a
n
g
S
u
p
r
i
a
d
i
b
i
n
M
a
n
s
y
u
r
S
.
me
n
t
i
o
n
e
d
a
b
o
v
e
,
w
e
r
e
p
r
o
v
e
n
t
o
h
a
v
e
c
o
mm
i
t
t
e
d
"
v
i
o
l
e
n
c
e
a
g
a
i
n
s
t
p
e
o
p
l
e
w
h
o
c
a
u
sed
i
n
j
u
r
y
"
a
s
i
n
t
h
e
f
i
r
st
a
l
t
e
r
n
a
t
i
v
e
i
n
d
i
c
t
men
t
;
I
mp
o
se
p
r
i
s
o
n
se
n
t
e
n
c
e
s
o
f
1
(
o
n
e
)
y
e
a
r
a
n
d
4
(
f
o
u
r
)
m
o
n
t
h
s
r
e
sp
e
c
t
i
v
e
l
y
;
Est
a
b
l
i
s
h
a
s
e
v
i
d
e
n
c
e
1
B
M
C
b
r
a
n
d
h
e
l
me
t
a
n
d
1
D
o
u
b
l
e
S
t
i
c
k
;
1
S
t
a
t
e
d
t
h
a
t
t
h
e
D
e
f
e
n
d
a
n
t
A
G
U
S
S
U
H
ER
M
A
N
B
i
n
H
A
R
U
N
K
O
M
A
R
U
D
I
N
w
a
s
p
r
o
v
e
n
t
o
b
e
C
i
r
c
u
l
a
t
i
n
g
C
o
u
n
t
e
r
f
e
i
t
R
u
p
i
a
h
"
.
S
e
n
t
e
n
c
e
d
A
G
U
S
S
U
H
ER
M
A
N
B
i
n
H
A
R
U
N
K
O
M
A
R
U
D
I
N
t
o
2
y
e
a
r
s
a
n
d
f
i
n
e
d
R
p
.
2
0
0
,
0
0
0
,
0
0
0
,
O
r
d
e
r
t
h
e
d
e
f
e
n
d
a
n
t
t
o
r
e
mai
n
i
n
d
e
t
e
n
t
i
o
n
;
e
v
i
d
e
n
c
e
i
n
t
h
e
f
o
r
m
o
f
:
F
a
k
e
r
u
p
i
a
h
c
u
r
r
e
n
c
y
a
mo
u
n
t
i
n
g
t
o
R
p
.
1
0
,
0
0
0
,
0
0
0
-
w
h
i
c
h
i
s
st
i
l
l
t
i
e
d
w
i
t
h
a
mo
n
e
y
r
o
p
e
,
R
p
.
1
0
0
,
0
0
0
f
o
r
1
0
0
sh
a
r
e
s
;
2
D
EC
I
D
ES
D
e
c
l
a
r
i
n
g
t
h
a
t
t
h
e
p
r
o
se
c
u
t
i
o
n
o
f
t
h
e
D
e
f
e
n
d
a
n
t
Y
A
Y
A
H
W
I
L
I
Y
A
H
B
i
n
t
i
A
L
M
M
.
H
A
R
I
S
i
s
d
i
s
c
o
n
t
i
n
u
e
d
b
e
c
a
u
s
e
t
h
e
p
e
r
s
o
n
c
o
n
c
e
r
n
e
d
h
a
s
d
i
e
d
;
O
r
d
e
r
t
h
e
R
e
g
i
st
r
a
r
t
o
r
e
c
o
r
d
t
h
e
d
i
sm
i
ssa
l
o
f
t
h
e
p
r
o
s
e
c
u
t
i
o
n
a
g
a
i
n
st
t
h
e
d
e
f
e
n
d
a
n
t
Y
A
Y
A
H
W
I
LI
Y
A
H
B
i
n
t
i
A
L
M
M
.
H
A
R
I
S
i
n
t
h
e
C
r
i
m
i
n
a
l
c
a
se
r
e
g
i
st
e
r
N
u
mb
e
r
:
5
4
/
P
i
d
.
B
/
2
0
2
2
/
P
N
.
B
d
g
;
4
T
o
p
r
e
d
ict
th
e
le
v
el
o
f
d
if
f
icu
l
ty
o
f
a
leg
al
ca
s
e,
tex
t
p
r
ep
r
o
c
ess
in
g
is
f
ir
s
t
ca
r
r
ied
o
u
t
.
T
h
e
f
ir
s
t
s
tep
is
ca
s
e
f
o
ld
in
g
,
wh
ic
h
co
n
v
er
ts
all
letter
s
to
lo
wer
ca
s
e.
T
o
k
en
iz
in
g
in
v
o
l
v
es
b
r
ea
k
in
g
d
o
wn
s
en
ten
ce
s
in
to
s
in
g
le
wo
r
d
s
.
T
h
e
n
ex
t
s
tep
is
th
e
s
to
p
wo
r
d
s
tag
e,
b
asically
,
ea
ch
wo
r
d
is
r
ev
iewe
d
,
an
d
if
th
er
e
ar
e
wo
r
d
s
th
at
h
av
e
n
o
th
in
g
to
d
o
wi
th
an
aly
s
is
,
will
b
e
elim
in
ated
.
Fin
ally
,
d
u
r
in
g
th
e
s
tem
m
in
g
s
tep
,
th
e
co
llectio
n
o
f
wo
r
d
s
p
r
o
ce
s
s
ed
with
s
to
p
wo
r
d
s
is
tr
an
s
f
o
r
m
ed
in
to
th
e
f
o
r
m
o
f
b
asic
wo
r
d
s
o
r
a
f
f
ix
es
a
r
e
r
e
m
o
v
e
d
.
T
a
b
le
2
d
is
p
lay
s
th
e
o
u
tco
m
es o
f
d
ata
p
r
ep
r
o
ce
s
s
in
g
.
T
ab
le
2
.
R
esu
lt o
f
d
ata
p
r
ep
r
o
ce
s
s
in
g
(
4
o
f
9
9
0
d
ataset)
D
e
c
i
s
i
o
n
C
o
d
e
i
n
d
i
c
t
m
e
n
t
o
f
G
r
e
d
y
P
a
n
t
e
r
a
A
l
s
I
y
a
n
g
b
i
n
G
u
g
u
n
G
u
n
a
w
a
n
,
e
v
i
d
e
n
c
e
o
f
a
c
r
i
m
i
n
a
l
a
c
t
,
a
t
t
e
m
p
t
e
d
c
o
n
s
p
i
r
a
c
y
,
c
r
i
mi
n
a
l
a
c
t
o
f
n
a
r
c
o
t
i
c
s,
H
a
k
a
,
y
o
u
a
r
e
a
g
a
i
n
s
t
t
h
e
l
a
w
,
p
o
ssess
i
o
n
,
p
o
ss
e
s
si
o
n
o
f
p
o
w
e
r
o
f
a
t
t
o
r
n
e
y
f
o
r
n
a
r
c
o
t
i
c
s,
c
l
a
ss
o
f
p
l
a
n
t
i
n
g
,
p
a
r
a
g
r
a
p
h
1
,
w
e
i
g
h
i
n
g
m
o
r
e
t
h
a
n
5
,
f
i
v
e
g
r
a
ms,
2
c
o
n
v
i
c
t
i
o
n
s,
i
n
d
i
c
t
m
e
n
t
o
f
G
r
e
d
y
P
a
n
t
e
r
a
A
l
s
I
y
a
n
g
b
i
n
G
u
g
u
n
G
u
n
a
w
a
n
,
i
mp
r
i
so
n
men
t
f
o
r
7
s
e
v
e
n
y
e
a
r
f
i
n
e
R
p
.
1
,
0
0
0
,
0
0
0
,
0
0
0
c
h
a
r
g
e
o
r
d
e
r
t
o
d
e
t
a
i
n
o
r
d
e
r
t
o
d
e
t
a
i
n
3
i
t
e
ms
o
f
e
v
i
d
e
n
c
e
1
o
n
e
b
o
x
o
f
S
a
m
p
o
e
r
n
a
m
i
l
d
c
i
g
a
r
e
t
t
e
s
c
o
n
t
a
i
n
i
n
g
t
w
o
p
l
a
st
i
c
p
a
c
k
e
t
s
o
f
n
a
r
c
o
t
i
c
c
l
i
p
s,
t
y
p
e
o
f
m
e
t
h
a
mp
h
e
t
a
m
i
n
e
,
h
e
a
v
y
0
3
2
6
0
g
r
a
ms
2
0
t
w
e
n
t
y
p
a
c
k
a
g
e
s
o
f
p
l
a
st
i
c
c
l
i
p
s
o
f
n
a
r
c
o
t
i
c
n
a
r
c
o
t
i
c
s
,
t
y
p
e
o
f
met
h
a
m
p
h
e
t
a
mi
n
e
,
h
e
a
v
y
5
2
5
2
5
g
r
a
ms 1
u
n
i
t
O
p
p
o
b
r
a
n
d
c
e
l
l
p
h
o
n
e
3
I
n
d
i
c
t
me
n
t
1
A
s
e
p
W
a
r
ma
n
B
i
n
M
a
m
a
t
2
Y
a
d
S
e
t
i
a
d
i
a
l
i
a
s
B
i
n
M
a
m
a
t
R
a
h
mat
3
T
a
t
a
n
g
S
u
p
r
i
a
d
i
B
i
n
M
a
n
s
y
u
r
S
o
n
e
v
i
d
e
n
c
e
o
f
c
r
i
mi
n
a
l
a
c
t
s
o
f
v
i
o
l
e
n
t
b
e
h
a
v
i
o
r
o
f
p
e
o
p
l
e
d
u
e
t
o
i
n
j
u
r
i
e
s
A
l
t
e
r
n
a
t
i
v
e
c
h
a
r
g
e
s
o
n
e
f
a
l
l
c
r
i
mi
n
a
l
c
h
a
r
g
e
p
r
i
s
o
n
se
n
t
e
n
c
e
1
y
e
a
r
4
f
o
u
r
m
o
n
t
h
s
s
t
i
l
l
a
r
r
e
st
d
e
t
a
i
n
e
d
o
n
t
h
e
r
o
a
d
C
h
a
r
g
e
l
e
ss
c
r
i
m
i
n
a
l
f
a
l
l
S
t
i
l
l
a
c
c
u
se
d
,
st
i
l
l
h
o
l
d
e
v
i
d
e
n
c
e
i
n
t
h
e
f
o
r
m
o
f
1
B
M
C
b
r
a
n
d
h
e
l
me
t
,
1
d
o
u
b
l
e
s
t
i
c
k
1
I
n
d
i
c
t
e
d
A
g
u
s
S
u
h
e
r
ma
n
b
i
n
H
a
r
u
n
K
o
mar
u
d
i
n
,
l
e
g
a
l
e
v
i
d
e
n
c
e
o
f
w
r
o
n
g
d
o
i
n
g
i
n
t
h
e
c
r
i
me
o
f
c
i
r
c
u
l
a
t
i
n
g
c
o
u
n
t
e
r
f
e
i
t
r
u
p
i
a
h
,
c
o
n
v
i
c
t
e
d
.
I
n
d
i
c
t
e
d
b
y
A
g
u
s
S
u
h
e
r
ma
n
b
i
n
H
a
r
u
n
K
o
mar
u
d
i
n
,
2
-
2
y
e
a
r
s
i
mp
r
i
so
n
m
e
n
t
,
f
i
n
e
o
f
I
D
R
2
0
0
,
0
0
0
,
0
0
0
,
o
f
c
o
u
r
se
t
h
e
f
i
n
e
w
i
l
l
b
e
p
a
i
d
i
n
l
i
e
u
o
f
i
m
p
r
i
s
o
n
me
n
t
f
o
r
2
m
o
n
t
h
s,
st
i
l
l
d
e
t
a
i
n
e
d
o
n
t
h
e
r
o
a
d
.
I
n
su
f
f
i
c
i
e
n
t
s
e
n
t
e
n
c
e
f
a
l
l
s.
O
r
d
e
r
t
o
i
n
d
i
c
t
d
e
t
a
i
n
e
d
.
r
e
m
a
i
n
s e
v
i
d
e
n
c
e
o
f
f
a
k
e
r
u
p
i
a
h
c
u
r
r
e
n
c
y
R
p
.
1
0
,
0
0
0
,
0
0
0
-
t
i
e
a
st
r
i
n
g
t
i
e
d
b
r
o
k
e
n
m
o
n
e
y
R
p
.
1
0
0
,
0
0
0
-
1
0
0
p
i
e
c
e
s
2
Y
a
y
a
h
W
i
l
i
y
a
h
B
i
n
t
i
A
l
m
M
H
a
r
i
s
h
a
s
d
i
e
d
a
n
d
r
e
ma
i
n
s
i
n
v
o
l
v
e
d
i
n
t
h
e
w
o
r
l
d
,
t
h
e
c
l
e
r
k
's
o
r
d
e
r
i
s
t
o
r
e
c
o
r
d
t
h
e
f
a
i
l
u
r
e
t
o
p
r
o
sec
u
t
e
Y
a
y
a
h
W
i
l
i
y
a
h
B
i
n
t
i
A
l
m M
H
a
r
i
s,
c
r
i
mi
n
a
l
c
a
se
r
e
g
i
st
r
a
t
i
o
n
n
u
m
b
e
r
5
4
P
I
D
B
2
0
2
2
P
N
B
D
G
4
L
ater
,
we
p
er
f
o
r
m
wo
r
d
weig
h
tin
g
b
y
u
s
in
g
th
e
T
F
-
I
DF m
et
h
o
d
,
as in
(
1
)
an
d
(
2
)
.
T
h
is
r
esu
lt is
in
p
u
t
f
o
r
th
e
class
if
icatio
n
p
r
o
ce
s
s
.
T
o
p
er
f
o
r
m
class
if
icatio
n
,
we
em
p
lo
y
SVM
an
d
r
an
d
o
m
f
o
r
est
class
if
ier
s
.
T
ab
les 3
an
d
4
p
r
esen
t t
h
e
class
if
icatio
n
r
esu
lts
.
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
SVM
P
r
e
d
i
c
t
i
o
n
A
c
t
u
a
l
C
l
a
s
s
1
2
3
4
1
40
1
0
1
2
8
30
2
1
3
1
1
13
0
4
0
0
0
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2
2
5
2
-
8
9
3
8
P
r
ed
ictin
g
leve
ls
o
f le
g
a
l c
a
s
e
d
iffi
cu
lties
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
(
I
lmiya
ti S
a
r
i)
4369
I
n
T
a
b
le
3
,
in
th
e
ac
t
u
al
s
itu
atio
n
,
as
m
an
y
as
4
0
leg
al
ca
s
es
with
a
class
1
d
if
f
icu
lty
lev
el
a
r
e
p
r
e
d
icted
to
en
ter
class
1
,
1
ca
s
e
is
p
r
ed
i
cted
to
en
te
r
class
2
,
a
n
d
1
ca
s
e
is
p
r
ed
icted
to
en
te
r
class
4
.
Fo
r
leg
al
ca
s
es
with
class
2
d
if
f
icu
lty
lev
el,
in
ac
tu
al
cir
cu
m
s
tan
ce
s
,
3
0
ca
s
es a
r
e
p
r
ed
icted
to
e
n
ter
class
2
,
8
ca
s
es a
r
e
p
r
e
d
icted
to
en
ter
class
1
,
2
ca
s
es a
r
e
p
r
ed
i
cted
to
en
ter
class
3
a
n
d
1
ca
s
e
is
p
r
ed
icted
to
e
n
ter
class
4
.
Fo
r
leg
al
ca
s
es with
a
d
if
f
icu
lty
lev
el
o
f
class
3
,
in
ac
tu
al
cir
cu
m
s
tan
ce
s
,
1
3
ca
s
es
ar
e
p
r
ed
icted
to
en
ter
class
3
,
1
is
p
r
ed
icted
to
en
ter
class
1
an
d
1
is
p
r
e
d
icted
to
en
ter
class
2
.
Me
an
w
h
ile,
f
o
r
ca
s
es
with
a
class
4
d
if
f
icu
lty
lev
el,
i
t
is
p
r
ed
icte
d
to
en
ter
class
4
as m
an
y
as 1
c
ase.
Acc
o
r
d
in
g
t
o
T
ab
le
4
,
i
n
t
h
e
ac
tu
a
l
s
it
u
at
io
n
,
4
4
l
eg
al
c
ases
w
ith
a
class
1
d
i
f
f
i
c
u
lt
y
le
v
el
a
r
e
p
r
ed
ict
e
d
to
e
n
t
e
r
cl
ass
1
,
a
n
d
1
ca
s
e
is
p
r
e
d
i
cte
d
t
o
e
n
t
er
cl
ass
2
.
I
n
ac
t
u
al
ci
r
c
u
m
s
ta
n
c
es,
3
0
l
eg
al
c
as
es wit
h
a
d
i
f
f
ic
u
l
ty
lev
el
o
f
class
2
a
r
e
p
r
e
d
i
cte
d
to
en
te
r
class
2
,
4
ca
s
es
a
r
e
p
r
e
d
i
cte
d
t
o
e
n
te
r
class
1
,
2
ca
s
es
a
r
e
p
r
ed
ict
ed
t
o
e
n
t
e
r
class
3
,
a
n
d
1
c
ase
is
p
r
e
d
i
cte
d
t
o
e
n
t
er
cl
ass
4
.
I
n
ac
t
u
al
ci
r
c
u
m
s
ta
n
c
es,
1
3
le
g
a
l
c
ases
wi
th
a
d
i
f
f
ic
u
l
ty
le
v
e
l o
f
class
3
ar
e
a
n
ti
ci
p
at
e
d
to
en
te
r
cl
ass
3
,
1
is
p
r
e
d
i
cte
d
t
o
e
n
te
r
cl
ass
1
,
1
is
p
r
e
d
ict
e
d
to
en
t
er
c
lass
2
,
a
n
d
1
is
p
r
e
d
ic
te
d
to
e
n
t
e
r
class
4
.
M
ea
n
w
h
il
e,
f
o
r
c
ases
wit
h
a
c
lass
4
d
i
f
f
ic
u
l
ty
l
e
v
el
,
it
is
p
r
e
d
i
ct
e
d
to
en
te
r
class
4
as
m
a
n
y
as
1
c
ase
.
T
h
e
m
o
d
el
is
th
e
n
e
v
al
u
ate
d
b
y
c
o
m
p
u
ti
n
g
t
h
e
ac
c
u
r
ac
y
v
al
u
e
,
w
ei
g
h
te
d
a
v
e
r
a
g
e
o
f
p
r
ec
is
io
n
,
an
d
wei
g
h
t
ed
a
v
er
ag
e
o
f
r
e
ca
ll
wit
h
(
4
)
,
(
6
)
,
an
d
(
8
)
.
T
a
b
le
5
s
u
m
m
a
r
i
ze
s
t
h
e
m
o
d
el
e
v
al
u
at
i
o
n
r
es
u
lts
.
T
ab
le
4
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
r
an
d
o
m
f
o
r
est
P
r
e
d
i
c
t
i
o
n
A
c
t
u
a
l
C
l
a
s
s
1
2
3
4
1
44
1
0
0
2
4
30
2
1
3
1
1
13
1
4
0
0
0
1
T
ab
le
5
.
R
esu
lt o
f
ev
al
u
atio
n
m
o
d
el
C
l
a
s
s
S
V
M
R
a
n
d
o
m
f
o
r
e
s
t
N
u
mb
e
r
o
f
t
e
st
d
a
t
a
A
c
c
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
A
c
c
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
1
8
2
9
5
90
98
4
2
94
74
94
82
1
3
87
87
87
81
3
4
0
0
0
0
4
85
89
W
e
i
g
h
t
e
d
A
v
e
r
a
g
e
8
8
8
5
91
8
9
T
ab
le
5
s
u
m
m
ar
izes
th
e
o
v
er
a
ll
ev
alu
atio
n
r
esu
lts
.
T
h
e
m
o
d
el,
wh
ich
was
co
n
s
tr
u
cted
with
a
SVM
,
h
as
a
cc
u
r
ac
y
v
alu
e
o
f
8
5
%,
a
W
AP
o
f
8
8
%,
an
d
a
W
AR
o
f
8
5
%.
Usi
n
g
r
an
d
o
m
f
o
r
est,
we
ac
h
iev
e
an
ac
cu
r
ac
y
v
alu
e
o
f
8
9
%,
a
v
alu
e
o
f
W
AP
is
8
5
.
6
%,
an
d
a
v
alu
e
o
f
W
AR
is
8
0
%.
B
ased
o
n
th
ese
r
esu
lts
,
it
ca
n
b
e
co
n
clu
d
ed
th
at
th
e
r
an
d
o
m
f
o
r
est
m
eth
o
d
h
as
b
etter
r
esu
lts
th
an
u
s
in
g
th
e
SVM
m
eth
o
d
in
p
r
ed
ictin
g
t
h
e
lev
el
o
f
d
if
f
icu
lt
y
o
f
a
leg
al
ca
s
e.
4.
CO
NCLU
SI
O
N
On
e
f
ac
to
r
in
d
eter
m
in
in
g
atto
r
n
ey
f
ee
s
is
th
e
lev
el
o
f
d
if
f
i
cu
lty
o
f
th
e
leg
al
ca
s
e
b
ein
g
f
ac
ed
.
T
h
e
m
o
r
e
d
if
f
icu
lt
th
e
ca
s
e
is
to
r
es
o
lv
e,
th
e
m
o
r
e
ex
p
en
s
iv
e
it
wil
l
b
e
to
p
ay
a
lawy
er
.
T
h
er
ef
o
r
e,
it
is
v
er
y
im
p
o
r
tan
t
f
o
r
u
s
to
k
n
o
w
t
h
e
lev
el
o
f
d
i
f
f
icu
lty
o
f
th
e
leg
al
ca
s
e
we
a
r
e
f
ac
in
g
.
I
n
th
is
r
esear
ch
,
we
p
r
o
p
o
s
e
SVM
an
d
r
an
d
o
m
f
o
r
est
class
if
ier
s
to
esti
m
ate
th
e
lev
el
o
f
d
if
f
ic
u
lty
o
f
a
le
g
al
ca
s
e.
T
h
e
d
ata
u
s
ed
c
o
n
s
is
ts
o
f
9
9
0
d
ata.
W
e
d
iv
id
e
th
e
d
ata
with
a
r
atio
o
f
9
0
:1
0
f
o
r
t
r
ain
in
g
d
ata
a
n
d
test
i
n
g
d
ataset.
Af
ter
th
at,
tex
t
p
r
ep
r
o
ce
s
s
in
g
was
ca
r
r
ied
o
u
t
u
s
in
g
th
e
T
F
-
I
DF
m
eth
o
d
.
T
h
e
r
esu
lts
o
f
th
e
p
r
ep
r
o
ce
s
s
in
g
tex
t
ar
e
u
s
ed
as
in
p
u
t
in
th
e
class
if
icatio
n
p
r
o
ce
s
s
.
B
ased
o
n
th
e
r
esear
ch
r
esu
lts
,
an
ac
cu
r
ac
y
v
alu
e
o
f
8
5
%,
a
v
alu
e
o
f
W
AP
is
8
8
%,
a
n
d
a
v
alu
e
o
f
W
AR
is
8
5
%.
Us
in
g
r
an
d
o
m
f
o
r
est,
we
ac
h
iev
e
an
ac
cu
r
ac
y
v
alu
e
o
f
8
9
%,
a
v
alu
e
o
f
W
AP i
s
8
5
.
6
%,
an
d
a
v
alu
e
o
f
W
AR
i
s
8
0
%.
I
n
th
e
ca
s
e
o
f
th
is
d
ata,
it
ca
n
b
e
co
n
clu
d
e
d
th
a
t
th
e
r
an
d
o
m
f
o
r
est
m
eth
o
d
is
a
b
etter
m
o
d
el
th
an
th
e
SVM
f
o
r
p
r
ed
ictin
g
th
e
le
v
el
o
f
d
if
f
icu
lty
o
f
a
leg
al
ca
s
e.
Fo
r
f
u
r
t
h
er
r
esear
ch
,
o
th
er
m
eth
o
d
s
ca
n
also
b
e
u
s
ed
as a
co
m
p
ar
is
o
n
,
s
u
ch
as
a
d
ee
p
lear
n
i
n
g
ap
p
r
o
ac
h
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
r
esear
ch
was
f
u
n
d
ed
b
y
PTUPT
2
0
2
3
R
esear
ch
Gr
an
t,
Min
is
tr
y
o
f
E
d
u
ca
tio
n
,
C
u
ltu
r
e,
R
esear
ch
an
d
T
ec
h
n
o
lo
g
y
,
I
n
d
o
n
esia to
Gu
n
ad
ar
m
a
U
n
iv
er
s
ity
No
.
0
7
3
/E5
/PG.0
2
.
0
0
.
PL/2
0
2
3
in
1
2
Ap
r
il 2
0
2
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
3
6
4
-
4
3
7
1
4370
RE
F
E
R
E
NC
E
S
[
1
]
O.
-
M
.
Ş
u
l
e
a
,
M
.
Z
a
mp
i
e
r
i
,
M
.
V
e
l
a
,
a
n
d
J
.
V.
G
e
n
a
b
i
t
h
,
“
P
r
e
d
i
c
t
i
n
g
t
h
e
l
a
w
a
r
e
a
a
n
d
d
e
c
i
s
i
o
n
s
o
f
F
r
e
n
c
h
s
u
p
r
e
me
c
o
u
r
t
c
a
s
e
s,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
Re
c
e
n
t
A
d
v
a
n
c
e
s
i
n
N
a
t
u
ra
l
L
a
n
g
u
a
g
e
Pr
o
c
e
ssi
n
g
,
p
p
.
7
1
6
–
7
2
2
,
2
0
1
7
,
d
o
i
:
1
0
.
2
6
6
1
5
/
9
7
8
-
9
5
4
-
4
5
2
-
049
-
6
_
0
9
2
.
[
2
]
P
.
B
h
i
l
a
r
e
,
N
.
P
a
r
a
b
,
N
.
S
o
n
i
,
a
n
d
B
.
T
h
a
k
u
r
,
“
P
r
e
d
i
c
t
i
n
g
o
u
t
c
o
m
e
o
f
j
u
d
i
c
i
a
l
c
a
ses
a
n
d
a
n
a
l
y
si
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
Re
s
e
a
r
c
h
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
I
R
J
ET)
,
v
o
l
.
3
2
6
,
p
p
.
3
2
6
–
3
3
0
,
2
0
0
8
.
[
3
]
N
.
A
l
e
t
r
a
s,
D
.
Ts
a
r
a
p
a
t
sa
n
i
s
,
D
.
P
.
-
P
i
e
t
r
o
,
a
n
d
V
.
La
m
p
o
s,
“
P
r
e
d
i
c
t
i
n
g
j
u
d
i
c
i
a
l
d
e
c
i
si
o
n
s
o
f
t
h
e
E
u
r
o
p
e
a
n
c
o
u
r
t
o
f
h
u
m
a
n
r
i
g
h
t
s
:
A
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
p
e
r
s
p
e
c
t
i
v
e
,
”
P
e
e
r
J
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
0
1
6
,
n
o
.
1
0
,
p
p
.
1
–
1
9
,
2
0
1
6
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s.
9
3
.
[
4
]
D
.
M
.
K
a
t
z
,
M
.
J
.
B
o
mm
a
r
i
t
o
,
a
n
d
J.
B
l
a
c
k
m
a
n
,
“
A
g
e
n
e
r
a
l
a
p
p
r
o
a
c
h
f
o
r
p
r
e
d
i
c
t
i
n
g
t
h
e
b
e
h
a
v
i
o
r
o
f
t
h
e
S
u
p
r
e
me
C
o
u
r
t
o
f
t
h
e
U
n
i
t
e
d
S
t
a
t
e
s,”
PL
o
S
O
n
e
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
1
–
1
8
,
2
0
1
7
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
1
7
4
6
9
8
.
[
5
]
I
.
S
a
r
i
a
n
d
R
.
K
o
s
a
si
h
,
“
P
r
e
d
i
c
t
i
o
n
t
y
p
e
s
o
f
l
e
g
a
l
c
a
s
e
s
i
n
i
n
d
o
n
e
si
a
u
s
i
n
g
t
h
e
TF
-
I
D
F
met
h
o
d
a
n
d
t
h
e
K
N
N
a
l
g
o
r
i
t
h
m,
”
AI
P
C
o
n
f
e
re
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
v
o
l
.
2
6
8
9
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
1
4
5
4
3
.
[
6
]
I
.
S
a
r
i
,
R
.
K
o
sas
i
h
,
a
n
d
A
.
F
a
h
r
u
r
o
z
i
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
p
r
e
d
i
c
t
i
n
g
l
e
n
g
t
h
o
f
p
u
n
i
s
h
me
n
t
a
t
B
a
n
d
u
n
g
C
o
u
r
t
,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
f
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
i
n
S
m
a
rt
A
d
m
i
n
i
s
t
ra
t
i
o
n
(
I
C
S
I
N
T
E
S
A)
,
2
0
2
2
,
p
p
.
1
2
–
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
I
N
TESA
5
6
4
3
1
.
2
0
2
2
.
1
0
0
4
1
6
9
3
.
[
7
]
C
.
F
i
a
r
n
i
,
H
.
M
a
h
a
r
a
n
i
,
a
n
d
R
.
P
r
a
t
a
ma,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
sy
s
t
e
m
f
o
r
I
n
d
o
n
e
s
i
a
o
n
l
i
n
e
r
e
t
a
i
l
s
h
o
p
r
e
v
i
e
w
u
si
n
g
h
i
e
r
a
r
c
h
y
N
a
i
v
e
B
a
y
e
s
t
e
c
h
n
i
q
u
e
,
”
2
0
1
6
4
t
h
i
n
t
e
rn
a
t
i
o
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
i
n
f
o
rm
a
t
i
o
n
a
n
d
c
o
m
m
u
n
i
c
a
t
i
o
n
t
e
c
h
n
o
l
o
g
y
(
I
C
o
I
C
T
)
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
I
C
T.
2
0
1
6
.
7
5
7
1
9
1
2
.
[
8
]
N
.
N
o
r
ma
h
,
“
N
a
ï
v
e
B
a
y
e
s
a
l
g
o
r
i
t
h
m
f
o
r
se
n
t
i
me
n
t
a
n
a
l
y
si
s
w
i
n
d
o
w
s
p
h
o
n
e
st
o
r
e
a
p
p
l
i
c
a
t
i
o
n
r
e
v
i
e
w
s,”
S
i
n
k
rO
n
,
v
o
l
.
3
,
n
o
.
2
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
3
9
5
/
s
i
n
k
r
o
n
.
v
3
i
2
.
2
4
2
.
[
9
]
H
.
C
h
r
i
st
i
a
n
,
M
.
P
.
A
g
u
s,
a
n
d
D
.
S
u
h
a
r
t
o
n
o
,
“
S
i
n
g
l
e
d
o
c
u
me
n
t
a
u
t
o
ma
t
i
c
t
e
x
t
s
u
mm
a
r
i
z
a
t
i
o
n
u
s
i
n
g
t
e
r
m
f
r
e
q
u
e
n
c
y
-
i
n
v
e
r
se
d
o
c
u
me
n
t
f
r
e
q
u
e
n
c
y
(
TF
-
I
D
F
)
,
”
C
o
m
T
e
c
h
:
C
o
m
p
u
t
e
r,
M
a
t
h
e
m
a
t
i
c
s
a
n
d
En
g
i
n
e
e
ri
n
g
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
7
,
n
o
.
4
,
2
0
1
6
,
d
o
i
:
1
0
.
2
1
5
1
2
/
c
o
mt
e
c
h
.
v
7
i
4
.
3
7
4
6
.
[
1
0
]
S
.
W
.
K
i
m
a
n
d
J
.
M
.
G
i
l
,
“
R
e
s
e
a
r
c
h
p
a
p
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
s
y
st
e
ms
b
a
se
d
o
n
T
F
-
I
D
F
a
n
d
LD
A
s
c
h
e
mes
,
”
H
u
m
a
n
-
c
e
n
t
r
i
c
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
9
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
6
7
3
-
0
1
9
-
0
1
9
2
-
7.
[
1
1
]
I
.
L.
M
a
h
a
r
g
y
a
a
n
d
G
.
F
.
S
h
i
d
i
k
,
“
I
mp
r
o
v
e
me
n
t
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
u
si
n
g
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
i
n
f
a
r
mers
t
e
r
m
o
f
t
r
a
d
e
p
r
e
d
i
c
t
i
o
n
at
C
e
n
t
r
a
l
Ja
v
a
I
n
d
o
n
e
s
i
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
A
d
v
a
n
c
e
d
S
c
i
e
n
c
e
,
E
n
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
6
,
p
p
.
2
2
6
1
–
2
2
6
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
8
5
1
7
/
i
j
a
se
i
t
.
1
0
.
6
.
9
4
0
0
.
[
1
2
]
Y
.
B
.
S
a
l
e
m,
M
.
N
.
A
b
d
e
l
k
r
i
m
,
a
n
d
Y
.
B
.
S
a
l
e
m,
“
T
e
x
t
u
r
e
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
f
a
b
r
i
c
d
e
f
e
c
t
s
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
0
,
n
o
.
4
,
p
p
.
4
3
9
0
–
4
3
9
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
0
i
4
.
p
p
4
3
9
0
-
4
3
9
9
.
[
1
3
]
N
.
N
.
M
o
o
n
e
t
a
l
.
,
“
N
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ss
i
n
g
b
a
se
d
a
d
v
a
n
c
e
d
m
e
t
h
o
d
o
f
u
n
n
e
c
e
ss
a
r
y
v
i
d
e
o
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
,
n
o
.
6
,
p
p
.
5
4
1
1
–
5
4
1
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
6
.
p
p
5
4
1
1
-
5
4
1
9
.
[
1
4
]
I
.
S
.
A
.
-
M
e
j
i
b
l
i
,
J
.
K
.
A
l
w
a
n
,
a
n
d
D
.
H
.
A
b
d
,
“
T
h
e
e
f
f
e
c
t
o
f
g
a
mm
a
v
a
l
u
e
o
n
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
p
e
r
f
o
r
ma
n
c
e
w
i
t
h
d
i
f
f
e
r
e
n
t
k
e
r
n
e
l
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
,
n
o
.
5
,
p
p
.
5
4
9
7
–
5
5
0
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
I
JEC
E
.
V
1
0
I
5
.
P
P
5
4
9
7
-
5
5
0
6
.
[
1
5
]
L.
K
.
R
a
m
a
sam
y
,
S
.
K
a
d
r
y
,
Y
.
N
a
m,
a
n
d
M
.
N
.
M
e
q
d
a
d
,
“
P
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
si
s
o
f
se
n
t
i
me
n
t
s
i
n
t
w
i
t
t
e
r
d
a
t
a
se
t
u
s
i
n
g
S
V
M
m
o
d
e
l
s
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
,
n
o
.
3
,
p
p
.
2
2
7
5
–
2
2
8
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
3
.
p
p
2
2
7
5
-
2
2
8
4
.
[
1
6
]
I
.
M
.
H
a
y
d
e
r
,
G
.
A
b
d
u
l
,
N
.
A
l
,
a
n
d
H
.
A
.
Y
o
u
n
i
s,
“
P
r
e
d
i
c
t
i
n
g
r
e
a
c
t
i
o
n
b
a
se
d
o
n
c
u
s
t
o
mer’
s
t
r
a
n
s
a
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
0
8
6
–
1
0
9
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
1
.
p
p
1
0
8
6
-
1
0
9
6
.
[
1
7
]
Y
.
K
.
Z
a
mi
l
,
S
.
A
.
A
l
i
,
a
n
d
M
.
A
.
N
a
ser,
“
S
p
a
m
i
ma
g
e
e
ma
i
l
f
i
l
t
e
r
i
n
g
u
si
n
g
K
-
N
N
a
n
d
S
V
M
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
2
4
5
-
2
5
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
1
.
p
p
2
4
5
-
2
5
4
.
[
1
8
]
G
.
W
.
-
W
e
n
,
Y
.
L
v
,
Y
.
J
.
Y
u
,
Z
.
W
a
n
g
,
a
n
d
S
.
Y
.
-
H
a
i
,
“
F
a
s
t
su
p
p
o
r
t
v
e
c
t
o
r
c
l
a
ssi
f
i
e
r
w
i
t
h
g
e
n
e
r
a
l
i
z
a
t
i
o
n
-
m
e
m
o
r
i
z
a
t
i
o
n
k
e
r
n
e
l
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
1
4
,
p
p
.
5
5
–
6
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
2
2
.
1
1
.
1
4
8
.
[
1
9
]
A
.
B
.
G
u
me
l
a
r
,
A
.
Y
o
g
a
t
a
ma
,
D
.
P
.
A
d
i
,
F
r
i
sm
a
n
d
a
,
a
n
d
I
.
S
u
g
i
a
r
t
o
,
“
F
o
r
w
a
r
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
f
o
r
t
o
x
i
c
s
p
e
e
c
h
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
a
n
d
r
a
n
d
o
m
f
o
r
e
st
,
”
I
A
ES
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
-
AI
)
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
7
1
7
–
7
2
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
1
.
i
2
.
p
p
7
1
7
-
7
2
6
.
[
2
0
]
B
.
A
b
u
h
a
i
j
a
e
t
a
l
.
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
st
u
d
y
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
n
g
c
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
se
a
se
u
si
n
g
W
e
k
a
a
n
d
S
P
S
S
t
o
o
l
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
1
8
9
1
–
1
9
0
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
2
.
p
p
1
8
9
1
-
1
9
0
2
.
[
2
1
]
B
.
T
.
K
h
o
a
a
n
d
T.
T
.
H
u
y
n
h
,
“
F
o
r
e
c
a
st
i
n
g
st
o
c
k
p
r
i
c
e
m
o
v
e
me
n
t
d
i
r
e
c
t
i
o
n
b
y
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
2
,
n
o
.
6
,
p
p
.
6
6
2
5
–
6
6
3
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
2
i
6
.
p
p
6
6
2
5
-
6
6
3
4
.
[
2
2
]
M
.
D
.
S
a
l
a
w
u
e
t
a
l
.
,
“
A
c
h
i
-
sq
u
a
r
e
-
S
V
M
b
a
se
d
p
e
d
a
g
o
g
i
c
a
l
r
u
l
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
f
o
r
mi
c
r
o
a
r
r
a
y
d
a
t
a
a
n
a
l
y
si
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
s
i
n
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
9
3
–
1
0
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
a
s
.
v
9
.
i
2
.
p
p
9
3
-
1
0
0
.
[
2
3
]
A
.
S
u
sa
n
t
o
,
C
.
A
.
S
a
r
i
,
H
.
R
a
h
m
a
l
a
n
,
a
n
d
M
.
A
.
S
.
D
o
h
e
i
r
,
“
S
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
b
a
s
e
d
d
i
scr
e
t
e
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m
f
o
r
m
a
g
n
e
t
i
c
r
e
so
n
a
n
c
e
i
ma
g
i
n
g
b
r
a
i
n
t
u
m
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
T
EL
K
O
MN
I
K
A
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
ro
n
i
c
s
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
2
1
,
n
o
.
3
,
p
p
.
5
9
2
–
5
9
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
2
9
2
8
/
TE
LK
O
M
N
I
K
A
.
v
2
1
i
3
.
2
4
9
2
8
.
[
2
4
]
C
.
B
.
Ta
n
,
M
.
H
.
A
.
H
i
j
a
z
i
,
a
n
d
P
.
N
.
E.
N
o
h
u
d
d
i
n
,
“
A
c
o
m
p
a
r
i
s
o
n
o
f
d
i
f
f
e
r
e
n
t
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
k
e
r
n
e
l
s f
o
r
a
r
t
i
f
i
c
i
a
l
s
p
e
e
c
h
d
e
t
e
c
t
i
o
n
,
”
T
ELKO
MN
I
K
A
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
ro
n
i
c
s
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
9
7
–
1
0
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
2
9
2
8
/
TEL
K
O
M
N
I
K
A
.
v
2
1
i
1
.
2
4
2
5
9
.
[
2
5
]
V
.
Y
.
K
u
l
l
a
r
n
i
a
n
d
P
.
K
.
S
i
n
h
a
,
“
R
a
n
d
o
m
f
o
r
e
st
c
l
a
ss
i
f
i
e
r
:
a
s
u
r
v
e
y
a
n
d
f
u
t
u
r
e
r
e
sea
r
c
h
d
i
r
e
c
t
i
o
n
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r Te
c
h
n
o
l
o
g
y
,
v
o
l
.
3
6
,
n
o
.
1
,
p
p
.
1
1
4
4
–
1
1
5
6
,
2
0
1
3
.
[
2
6
]
L.
B
r
e
i
m
a
n
,
“
B
a
g
g
i
n
g
p
r
e
d
i
c
t
o
r
s
,
”
in
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
1
2
3
–
1
4
0
,
1
9
9
6
,
d
o
i
:
1
0
.
1
0
0
7
/
b
f
0
0
0
5
8
6
5
5
.
[
2
7
]
R
.
M
e
e
n
a
l
,
P
.
A
.
M
i
c
h
a
e
l
,
D
.
P
a
m
e
l
a
,
a
n
d
E.
R
a
j
a
se
k
a
r
a
n
,
“
W
e
a
t
h
e
r
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
s
t
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
2
,
n
o
.
2
,
p
p
.
1
2
0
8
–
1
2
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
2
.
i
2
.
p
p
1
2
0
8
-
1
2
1
5
.
[
2
8
]
M
.
H
.
M
u
t
a
r
,
E
.
H
.
A
h
m
e
d
,
M
.
R
.
M
.
A
Lse
maw
i
,
H
.
O
.
H
a
n
o
o
sh
,
a
n
d
A
.
H
.
A
b
b
a
s,
“
Ea
r
r
e
c
o
g
n
i
t
i
o
n
sy
st
e
m
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
s
t
a
n
d
h
i
st
o
g
r
a
ms
o
f
o
r
i
e
n
t
e
d
g
r
a
d
i
e
n
t
s
t
e
c
h
n
i
q
u
e
s
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
1
8
1
–
1
8
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
7
.
i
1
.
p
p
1
8
1
-
1
8
8
.
[
2
9
]
A
.
A
.
K
h
a
l
e
e
l
,
A
.
A
.
M
.
A
.
-
A
z
z
a
w
i
,
a
n
d
A
.
M
.
A
l
k
h
a
z
r
a
j
i
,
“
R
a
n
d
o
m
f
o
r
e
st
f
o
r
l
u
n
g
c
a
n
c
e
r
a
n
a
l
y
s
i
s
u
s
i
n
g
a
p
a
c
h
e
ma
h
o
u
t
a
n
d
h
a
d
o
o
p
b
a
se
d
o
n
so
f
t
w
a
r
e
d
e
f
i
n
e
d
n
e
t
w
o
r
k
i
n
g
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
2
,
n
o
.
2
,
p
p
.
1
0
8
6
–
1
0
9
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
3
2
.
i
2
.
p
p
1
0
8
6
-
1
0
9
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2
2
5
2
-
8
9
3
8
P
r
ed
ictin
g
leve
ls
o
f le
g
a
l c
a
s
e
d
iffi
cu
lties
u
s
in
g
ma
ch
in
e
lea
r
n
in
g
(
I
lmiya
ti S
a
r
i)
4371
[
3
0
]
M
.
C
o
n
c
i
a
t
o
r
i
,
A
.
V
a
l
l
e
t
t
a
,
a
n
d
A
.
S
e
g
a
l
i
n
i
,
“
I
mp
r
o
v
i
n
g
t
h
e
q
u
a
l
i
t
y
e
v
a
l
u
a
t
i
o
n
p
r
o
c
e
ss
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
a
p
p
l
i
e
d
t
o
l
a
n
d
s
l
i
d
e
t
i
me
seri
e
s a
n
a
l
y
si
s
,”
C
o
m
p
u
t
e
rs &
G
e
o
s
c
i
e
n
c
e
s
,
v
o
l
.
1
8
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
a
g
e
o
.
2
0
2
4
.
1
0
5
5
3
1
.
[
3
1
]
C
.
A
r
o
e
f
,
Y
.
R
i
v
a
n
,
a
n
d
Z.
R
u
st
a
m,
“
C
o
mp
a
r
i
n
g
r
a
n
d
o
m
f
o
r
e
st
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s
f
o
r
b
r
e
a
s
t
c
a
n
c
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
T
ELKO
MN
I
K
A
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
1
8
,
n
o
.
2
,
p
p
.
8
1
5
–
8
2
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
2
9
2
8
/
TEL
K
O
M
N
I
K
A
.
v
1
8
i
2
.
1
4
7
8
5
.
[
3
2
]
S
.
O
.
-
A
r
i
a
s,
J.
S
.
P
i
ñ
a
,
R
.
T
.
-
S
o
t
o
,
L
.
F
.
C
.
-
O
ssa
,
R
.
G
u
y
o
t
,
a
n
d
G
.
I
saz
a
,
“
M
e
a
su
r
i
n
g
p
e
r
f
o
r
ma
n
c
e
m
e
t
r
i
c
s
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms f
o
r
d
e
t
e
c
t
i
n
g
a
n
d
c
l
a
ss
i
f
y
i
n
g
t
r
a
n
s
p
o
s
a
b
l
e
e
l
e
m
e
n
t
s
,
”
Pr
o
c
e
sses
,
v
o
l
.
8
,
n
o
.
6
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
P
R
8
0
6
0
6
3
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ilm
iy
a
ti
S
a
r
i
re
c
e
iv
e
d
h
e
r
B.
S
.
d
e
g
re
e
in
M
a
t
h
e
m
a
ti
c
s
fro
m
Un
iv
e
rsity
o
f
In
d
o
n
e
si
a
in
2
0
0
9
,
h
e
r
M
.
S
.
in
M
a
t
h
e
m
a
ti
c
s
fro
m
Un
iv
e
rsity
o
f
I
n
d
o
n
e
sia
i
n
2
0
1
2
a
n
d
h
e
r
d
o
c
to
ra
l
i
n
G
u
n
a
d
a
rm
a
Un
iv
e
rsity
in
2
0
1
8
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
e
x
ten
si
v
e
ly
i
n
t
h
e
a
re
a
o
f
v
id
e
o
p
r
o
c
e
ss
in
g
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
y
n
a
m
ic
m
o
d
e
ls,
sta
ti
stics
,
ima
g
e
p
ro
c
e
ss
in
g
,
v
i
d
e
o
p
r
o
c
e
ss
in
g
,
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
il
m
i
y
a
ti
@s
taff.g
u
n
a
d
a
rm
a
.
a
c
.
id
.
Rifk
i
K
o
sa
sih
re
c
e
iv
e
d
th
e
B.
S
.
d
e
g
re
e
in
M
a
th
e
m
a
ti
c
s
fro
m
Un
iv
e
rsity
o
f
In
d
o
n
e
sia
,
In
d
o
n
e
sia
,
in
2
0
0
9
,
th
e
M
.
S
.
d
e
g
re
e
in
M
a
th
e
m
a
ti
c
s fro
m
Un
iv
e
rsity
o
f
I
n
d
o
n
e
sia
in
2
0
1
2
,
a
n
d
th
e
P
h
.
D.
d
e
g
re
e
fro
m
G
u
n
a
d
a
rm
a
Un
iv
e
rsity
,
In
d
o
n
e
sia
,
in
2
0
1
5
.
He
is a l
e
c
tu
re
r
in
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
c
s
(Gu
n
a
d
a
rm
a
Un
iv
e
rsity
).
His
re
se
a
rc
h
in
tere
sts
a
re
i
m
a
g
e
p
ro
c
e
ss
in
g
,
o
b
jec
t
re
c
o
g
n
it
io
n
,
d
a
ta
sc
ien
c
e
,
m
a
n
ifo
l
d
lea
rn
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
d
e
e
p
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
rifk
i_
k
o
sa
sih
@s
taff.
g
u
n
a
d
a
rm
a
.
a
c
.
id
.
Din
a
Ind
a
r
ti
re
c
e
iv
e
d
h
e
r
B.
S
.
d
e
g
re
e
in
M
a
th
e
m
a
ti
c
s
fro
m
Un
iv
e
rsity
o
f
In
d
o
n
e
sia
in
2
0
0
8
,
h
e
r
M
.
S
.
in
M
a
t
h
e
m
a
ti
c
s
fro
m
Un
iv
e
rsity
o
f
I
n
d
o
n
e
sia
i
n
2
0
1
1
a
n
d
h
e
r
d
o
c
to
ra
l
i
n
G
u
n
a
d
a
rm
a
Un
iv
e
rsity
i
n
2
0
1
4
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
e
x
ten
si
v
e
ly
in
th
e
a
re
a
o
f
ima
g
e
p
r
o
c
e
ss
in
g
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
sta
ti
stics
,
ima
g
e
p
r
o
c
e
ss
in
g
,
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
i
n
a
_
i
n
d
a
rti
@
sta
ff.
g
u
n
a
d
a
rm
a
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.