I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
40
,
No
.
1
,
Octo
b
er
2
0
2
5
,
p
p
.
3
5
6
~
3
6
5
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
40
.i
1
.
pp
356
-
3
6
5
356
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Phishing
U
RL pr
ediction
–
t
wo
-
ph
a
se mo
del using
l
o
g
istic
regres
sio
n and
f
in
ite
sta
t
e auto
ma
ta
Nis
ha
T
N
,
Dha
ny
a
P
ra
m
o
d
S
y
mb
i
o
si
s
C
e
n
t
r
e
f
o
r
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
S
y
m
b
i
o
si
s
I
n
t
e
r
n
a
t
i
o
n
a
l
(
D
e
e
me
d
U
n
i
v
e
r
si
t
y
)
,
P
u
n
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
25
,
2
0
2
4
R
ev
is
ed
Mar
21
,
2
0
2
5
Acc
ep
ted
J
u
l
3
,
2
0
2
5
Th
e
h
u
m
a
n
fa
c
to
r
in
se
c
u
rit
y
i
s
m
o
re
imp
o
r
tan
t
w
h
e
n
th
e
y
b
e
c
o
m
e
th
e
c
a
rriers
o
f
a
tt
a
c
k
s o
n
e
n
terp
rise
s.
P
h
ish
i
n
g
a
tt
a
c
k
s c
a
n
b
e
c
las
sified
a
s in
sid
e
r
a
tt
a
c
k
s
wh
e
n
th
e
e
m
p
lo
y
e
e
s
u
n
i
n
ten
ti
o
n
a
ll
y
p
a
rti
c
i
p
a
te
in
t
h
e
a
tt
a
c
k
p
ro
p
a
g
a
ti
o
n
.
S
in
c
e
c
o
m
p
lete
u
s
e
r
train
in
g
is
a
m
y
t
h
,
e
n
ter
p
ri
se
s
m
u
st
imp
lem
e
n
t
d
e
tec
ti
o
n
to
o
ls
fo
r
p
h
ish
in
g
a
tt
a
c
k
s
o
n
th
e
ir
n
e
tw
o
rk
p
e
rime
ters
.
Th
is
re
se
a
rc
h
d
isc
u
ss
e
s
a
two
-
p
h
a
se
m
o
d
e
l
fo
r
p
h
is
h
in
g
URL
d
e
t
e
c
ti
o
n
,
i
n
wh
ich
th
e
first
p
h
a
se
id
e
n
ti
fies
t
h
e
p
ro
p
e
rti
e
s
o
f
URLs
th
a
t
d
e
tec
t
p
h
ish
in
g
a
n
d
th
e
ir
re
lativ
e
we
ig
h
t
u
si
n
g
l
o
g
isti
c
re
g
re
ss
io
n
.
T
h
e
se
c
o
n
d
p
h
a
se
c
h
e
c
k
s
th
e
p
r
o
b
a
b
i
li
ty
o
f
a
n
e
w
URL
b
e
in
g
c
a
teg
o
rize
d
a
s
p
h
is
h
in
g
u
sin
g
t
h
e
k
n
o
wle
d
g
e
a
c
h
iev
e
d
d
u
rin
g
th
e
first
p
h
a
se
u
si
n
g
th
e
d
y
n
a
m
ica
ll
y
c
re
a
te
d
F
in
it
e
sta
te
m
a
c
h
in
e
s.
Th
e
m
o
d
e
l
d
e
fin
e
s
a
m
a
li
c
io
u
s
sc
o
re
(M
S
),
wh
ich
c
a
n
b
e
u
se
d
t
o
c
h
e
c
k
a
n
y
URL
in
re
a
l
-
ti
m
e
to
id
e
n
ti
fy
wh
e
t
h
e
r
it
is
p
h
ish
i
n
g
o
r
n
o
t.
T
h
e
m
o
d
e
l
d
e
sc
rib
e
d
in
th
is
wo
rk
h
a
s
b
e
e
n
e
x
p
e
rime
n
ted
wit
h
d
iffere
n
t
b
e
n
c
h
m
a
rk
in
g
d
a
tas
e
ts
to
v
e
rif
y
th
e
p
e
rfo
rm
a
n
c
e
.
T
h
e
m
o
d
e
l
p
ro
v
i
d
e
d
a
d
e
c
e
n
t
re
su
lt
i
n
c
las
sify
i
n
g
a
UR
L
a
s
p
h
ish
in
g
o
r
n
a
iv
e
.
Th
e
m
a
li
c
io
u
s
sc
o
re
(M
S
)
d
e
fin
e
d
b
y
t
h
is
m
o
d
e
l
c
a
n
b
e
u
se
d
t
o
e
v
a
l
u
a
te
a
n
y
URL
a
n
d
c
a
n
b
e
u
se
d
a
s
a
fil
teri
n
g
m
e
c
h
a
n
ism
fo
r
e
n
d
-
p
o
in
t
p
h
ish
i
n
g
URL
d
e
tec
ti
o
n
.
Th
e
k
e
y
c
o
n
tri
b
u
t
io
n
is
to
wa
rd
s
d
e
v
e
lo
p
i
n
g
a
tw
o
-
p
h
a
se
m
o
d
e
l
w
h
ich
e
v
a
lu
a
tes
th
e
URL
wit
h
t
h
e
h
e
lp
o
f
se
lf
-
c
ra
fted
fe
a
tu
re
s
with
o
u
t
re
l
ian
c
e
o
n
a
fe
a
tu
re
se
t.
Th
is
a
c
c
o
m
m
o
d
a
tes
th
e
m
o
d
e
l'
s
h
y
p
e
r
-
c
o
m
p
e
ti
ti
v
e
p
h
ish
in
g
UR
L
d
e
tec
ti
o
n
a
re
a
in
c
y
b
e
r
se
c
u
rit
y
.
K
ey
w
o
r
d
s
:
Attack
p
r
o
b
a
b
ilit
y
d
etec
tio
n
Featu
r
e
s
elec
tio
n
Fin
ite
s
tate
m
ac
h
in
e
L
o
g
is
tic
r
eg
r
ess
io
n
Ma
licio
u
s
s
co
r
e
Ph
is
h
in
g
s
ites
Un
in
ten
tio
n
al
in
s
id
er
th
r
ea
ts
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
:
Nis
h
a
T
N
Sy
m
b
io
s
is
C
en
tr
e
f
o
r
I
n
f
o
r
m
at
io
n
T
ec
h
n
o
lo
g
y
,
Sy
m
b
i
o
s
is
I
n
ter
n
atio
n
al
(
Dee
m
ed
Un
iv
er
s
ity
)
Pu
n
e,
I
n
d
ia
E
m
ail:
n
is
h
a@
s
cit.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
I
n
f
o
r
m
atio
n
s
ec
u
r
ity
is
s
u
es
ar
e
in
cr
ea
s
in
g
d
aily
,
r
eg
ar
d
le
s
s
o
f
th
e
in
v
en
tio
n
s
h
ap
p
e
n
in
g
in
th
e
s
ec
u
r
ity
ar
ea
.
As
th
e
s
ay
in
g
g
o
es,
"A
ch
ain
is
o
n
ly
as
s
tr
o
n
g
as
th
e
wea
k
est
lin
k
.
"
T
h
e
wea
k
est
lin
k
in
in
f
o
r
m
atio
n
s
ec
u
r
ity
is
h
u
m
a
n
s
.
Desp
ite
th
e
r
o
b
u
s
t
s
ec
u
r
i
ty
ar
ch
itectu
r
e
an
d
p
o
licies,
o
r
g
an
izatio
n
s
s
till
ex
p
er
ien
ce
b
r
ea
ch
b
ec
au
s
e
o
f
t
h
e
ac
tio
n
s
o
f
h
u
m
an
s
in
v
o
lv
ed
in
th
e
in
f
o
r
m
atio
n
s
ec
u
r
ity
ar
ch
itectu
r
e.
Fo
r
an
y
o
r
g
an
izatio
n
,
em
p
lo
y
ee
s
ar
e
c
o
n
s
id
er
ed
t
o
b
e
th
e
g
r
ea
test
a
s
s
et.
Ho
wev
er
,
f
r
o
m
a
s
ec
u
r
it
y
p
er
s
p
ec
tiv
e
,
th
ey
ca
n
b
e
a
liab
ilit
y
to
th
e
co
m
p
an
y
.
Hu
m
a
n
ac
tio
n
s
,
wh
et
h
er
in
ten
tio
n
al
o
r
u
n
in
te
n
tio
n
al,
g
iv
e
r
is
e
to
s
ec
u
r
ity
im
p
licatio
n
s
.
As
p
er
th
e
2
0
2
4
d
ata
s
ec
u
r
ity
in
cid
en
t
r
e
p
o
r
t
b
y
B
ak
er
Ho
s
tetler
,
s
ec
u
r
ity
in
cid
en
ts
h
av
e
co
n
tin
u
ed
to
b
e
th
e
lead
i
n
g
i
n
th
e
m
ar
k
et,
an
d
r
a
n
s
o
m
war
e
h
as
b
ee
n
t
h
e
ca
u
s
e
f
o
r
th
e
last
f
iv
e
y
ea
r
s
[
1
]
.
Acc
o
r
d
in
g
to
an
I
B
M
r
ep
o
r
t
,
th
er
e
h
as
b
ee
n
a
7
1
%
in
cr
ea
s
e
in
cy
b
er
th
r
ea
ts
,
an
d
in
m
an
y
ca
s
es,
th
e
attac
k
s
wer
e
in
itiated
b
y
u
tili
zin
g
h
u
m
an
b
eh
av
i
o
u
r
[
2
]
.
T
h
ese
p
h
i
s
h
in
g
attac
k
s
ac
co
u
n
t
f
o
r
m
o
s
t
s
ec
u
r
ity
in
cid
en
ts
,
wh
ich
ca
n
b
e
class
if
ied
as
u
n
in
ten
tio
n
al
th
r
ea
ts
,
d
esp
ite
a
s
m
all
f
r
ac
tio
n
o
f
in
ter
n
al
t
h
ef
ts
,
wh
ich
ca
n
b
e
co
n
s
id
er
ed
in
ten
tio
n
al.
On
e
r
e
aso
n
f
o
r
th
is
u
n
i
n
ten
tio
n
al
ex
p
lo
it
o
f
an
o
r
g
an
izatio
n
'
s
s
ec
u
r
ity
p
o
s
tu
r
e
is
s
o
cial
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
h
is
h
in
g
UR
L p
r
ed
ictio
n
–
tw
o
-
p
h
a
s
e
mo
d
el
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
a
n
d
fin
ite
…
(
N
is
h
a
T N
)
357
en
g
in
ee
r
in
g
attac
k
s
.
So
cial
en
g
in
ee
r
in
g
ca
p
italizes
o
n
h
u
m
a
n
p
s
y
ch
o
lo
g
y
an
d
d
ec
eiv
es
th
e
v
ictim
s
to
d
o
th
e
attac
k
.
Attack
s
ar
e
s
h
if
tin
g
f
r
o
m
au
to
m
ated
t
o
o
ls
to
s
o
cial
en
g
in
ee
r
in
g
attac
k
s
,
with
em
ail
b
ein
g
th
e
m
o
s
t
u
s
ed
to
o
l
[
3
]
.
B
ased
o
n
an
ti
-
p
h
is
h
in
g
w
o
r
k
i
n
g
g
r
o
u
p
'
s
(
APW
G
)
r
ep
o
r
t
o
n
th
e
p
h
is
h
in
g
s
ce
n
e
f
o
r
th
e
y
ea
r
2
0
2
4
,
phone
-
b
ased
p
h
is
h
in
g
attac
k
s
ar
e
s
h
o
win
g
an
all
-
tim
e
h
i
g
h
tr
e
n
d
an
d
ar
e
g
o
i
n
g
u
n
d
etec
ted
.
I
t
s
h
o
ws
a
co
n
tin
u
o
u
s
ly
in
cr
ea
s
in
g
tr
e
n
d
ev
e
n
in
p
r
ev
io
u
s
y
ea
r
s
,
a
n
d
f
o
r
y
ea
r
s
,
t
h
e
n
u
m
b
er
o
f
r
ep
o
r
ted
p
h
is
h
in
g
web
s
ites
,
em
ails
,
an
d
tar
g
eted
b
r
an
d
s
h
as
r
is
en
s
tead
ily
.
AP
MG
also
r
ep
o
r
ts
th
at
p
h
is
h
in
g
attac
k
s
o
cc
u
r
m
o
s
t
f
r
eq
u
e
n
tly
o
n
th
e
d
o
m
ain
s
web
m
ail,
f
in
an
cial
a
n
d
p
a
y
m
en
t
s
ec
to
r
s
[
4
]
.
C
r
ea
tin
g
s
ec
u
r
ity
-
awa
r
e
u
s
er
s
th
r
o
u
g
h
t
r
ain
in
g
is
th
e
p
r
ee
m
in
en
t
s
o
lu
tio
n
f
o
r
p
h
is
h
i
n
g
attac
k
d
etec
tio
n
.
As
th
is
aim
is
ch
all
en
g
in
g
to
ac
h
iev
e,
en
ter
p
r
is
es
n
ee
d
to
d
ep
en
d
o
n
t
h
e
class
if
icatio
n
o
f
p
h
is
h
in
g
s
ites
b
y
b
lack
lis
t
in
g
,
h
eu
r
is
tics
,
v
is
u
al
s
im
i
lar
ity
o
r
m
ac
h
in
e
lear
n
in
g
.
Ph
is
h
in
g
d
etec
ti
o
n
b
y
b
lack
lis
tin
g
r
eq
u
ir
es
th
e
UR
L
to
b
e
p
r
ev
io
u
s
ly
d
etec
ted
as
p
h
is
h
,
h
e
u
r
is
tics
d
ep
en
d
o
n
th
e
alr
ea
d
y
p
r
e
s
en
t
ch
ar
ac
ter
is
tics
o
f
th
e
p
h
is
h
in
g
UR
L
an
d
v
is
u
al
s
im
ilar
ity
d
etec
tio
n
is
b
ased
o
n
th
e
c
o
n
ten
t c
o
d
e.
Du
e
to
th
e
av
ailab
ilit
y
o
f
m
ass
iv
e
d
ata
s
ets
o
f
p
h
is
h
in
g
an
d
n
aïv
e
UR
L
d
atab
ases
,
m
ac
h
in
e
lear
n
in
g
-
b
ased
p
h
is
h
in
g
d
etec
tio
n
m
eth
o
d
s
ar
e
p
r
o
m
in
e
n
t
in
th
e
ar
e
a.
Du
e
t
o
th
is
r
ea
s
o
n
,
d
ata
m
in
in
g
a
n
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
ar
e
f
in
d
in
g
th
eir
im
p
o
r
tan
ce
in
p
h
is
h
in
g
UR
L
d
etec
tio
n
,
a
n
d
m
o
d
els
ar
e
co
n
s
tr
u
cted
b
y
tak
in
g
ad
v
an
tag
e
o
f
d
if
f
er
en
t c
lu
s
ter
in
g
alg
o
r
ith
m
s
.
T
h
e
f
ir
s
t
lay
e
r
o
f
d
ef
en
ce
a
g
ain
s
t
p
h
is
h
in
g
is
ac
h
iev
e
d
b
y
id
e
n
tify
in
g
th
e
co
n
te
x
t
o
f
p
h
is
h
in
g
;
b
asically
,
th
e
e
m
ail
ca
r
r
y
in
g
p
h
is
h
in
g
UR
L
s
to
t
h
e
v
ictim
'
s
s
ig
h
t.
Featu
r
es
o
f
e
m
ail
ar
e
i
d
en
tifie
d
an
d
m
o
d
elled
th
e
class
if
ier
s
u
s
in
g
d
if
f
er
en
t
m
ac
h
in
e
lear
n
i
n
g
te
ch
n
iq
u
es
lik
e
SVM
[
5
]
,
W
o
r
d
Net
o
n
to
lo
g
y
[
6
]
,
m
u
ltip
le
d
ee
p
lear
n
in
g
m
o
d
els
[
7
]
,
r
ec
u
r
r
en
t c
o
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
m
o
d
el
[
8
]
,
T
F
-
I
DF b
ased
d
etec
tio
n
[
9
]
,
d
ee
p
lear
n
i
n
g
m
o
d
el
[
1
0
]
ar
e
em
p
lo
y
ed
eith
er
as
Sig
n
atu
r
e
-
b
ased
o
r
r
u
le
-
b
ase
d
m
eth
o
d
s
f
o
r
th
e
class
if
icatio
n
o
f
p
h
is
h
in
g
em
ai
l [
1
1
]
,
[
1
2
]
.
T
h
e
UR
L
to
th
e
m
alicio
u
s
s
ites
lo
o
k
s
d
if
f
er
en
t
t
h
an
a
n
o
r
m
al
UR
L
.
T
h
is
id
ea
is
ap
p
lied
to
UR
L
-
b
ased
p
h
is
h
in
g
em
ail
d
etec
tio
n
.
T
h
e
lex
ical
f
ea
tu
r
es
o
f
UR
L
s
ar
e
id
en
tifie
d
an
d
u
s
ed
to
d
etec
t
p
h
is
h
in
g
UR
L
s
.
T
h
ese
lex
ical
f
ea
tu
r
es a
r
e
an
aly
ze
d
u
s
in
g
d
if
f
er
en
t
m
ac
h
in
e
lear
n
i
n
g
tec
h
n
iq
u
es
s
u
c
h
as
SVM,
r
an
d
o
m
f
o
r
est,
Naïv
e
B
ay
es,
lo
g
is
tic
r
eg
r
ess
io
n
,
d
ec
is
io
n
tr
ee
,
co
n
f
i
d
en
ce
weig
h
ted
alg
o
r
ith
m
,
ad
ap
tiv
e
r
eg
u
latio
n
o
f
weig
h
t
s
AR
O
W
K
-
m
ea
n
s
,
n
eu
r
al
n
etwo
r
k
s
,
SOM,
an
d
c
o
m
p
ar
ed
th
e
r
esu
lts
[
1
3
]
.
UR
L
o
p
t
im
al
f
ea
tu
r
es
o
th
er
th
an
th
ese
ar
e
ex
tr
ac
ted
a
n
d
a
p
p
lied
to
th
e
f
r
eq
u
e
n
t
r
u
le
r
e
d
u
ctio
n
(
FR
R
)
alg
o
r
ith
m
to
d
et
ec
t
p
h
is
h
in
g
UR
L
s
[
1
4
]
.
Stu
d
ies
with
m
u
ltip
le
ML
m
o
d
els
an
d
th
eir
en
h
an
c
em
en
ts
ar
e
also
p
r
o
p
o
s
ed
wit
h
h
ig
h
ac
cu
r
ac
y
an
d
ef
f
icien
cy
[
1
5
]
,
wh
ich
d
o
es n
o
t n
ec
ess
ita
te
a
web
p
ag
e
v
is
it [
1
6
]
.
Attack
er
s
o
b
f
u
s
ca
te
th
e
UR
L
u
s
in
g
d
if
f
er
en
t
tech
n
iq
u
es
to
av
o
id
d
etec
tio
n
b
y
an
aly
zi
n
g
lex
ical
f
ea
tu
r
es.
L
ex
ical
f
ea
tu
r
es
co
m
b
in
ed
with
d
o
m
ai
n
-
b
ased
a
n
d
co
n
ten
t
-
b
ased
,
th
u
s
p
r
o
v
i
d
ed
g
o
o
d
d
etec
tio
n
ac
cu
r
ac
y
wh
ile
u
s
in
g
th
e
s
am
e
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
s
[
1
7
]
.
R
u
le
-
b
ased
alg
o
r
ith
m
s
s
u
ch
as
R
I
PP
E
R
,
R
I
SM,
C
4
.
5
,
C
B
A,
an
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
ar
e
also
u
s
ed
f
o
r
p
h
is
h
in
g
d
etec
tio
n
b
ased
o
n
UR
L
s
an
d
o
th
er
f
ea
tu
r
es [
1
8
]
.
Oth
er
th
an
lex
ical
f
ea
tu
r
es,
th
e
d
if
f
e
r
en
ce
s
b
etwe
en
th
e
v
is
u
al
lin
k
an
d
ac
tu
al
lin
k
an
d
m
is
s
p
elt
o
r
lar
g
e
h
o
s
t
n
am
es
ar
e
s
o
m
e
o
f
th
e
u
n
iq
u
e
f
ea
tu
r
es
r
esear
ch
er
s
id
en
tify
.
A
two
-
p
h
ase
m
o
d
el
with
a
UR
L
p
r
ed
ictio
n
co
m
p
o
n
en
t
an
d
an
ap
p
r
o
x
im
ate
UR
L
m
atch
in
g
co
m
p
o
n
en
t
th
at
m
atch
es
th
e
n
ew
UR
L
with
th
e
b
lack
lis
t
is
al
s
o
d
ev
elo
p
ed
[
1
9
]
.
Alo
n
g
with
lex
ical
an
d
o
t
h
er
f
ea
tu
r
es,
s
o
m
e
m
o
d
els
co
m
b
in
ed
f
u
zz
y
lo
g
ic
[
2
0
]
,
s
o
m
e
with
b
lac
k
lis
ted
d
o
m
ain
s
[
2
1
]
,
an
d
SHA1
h
ash
an
d
p
r
esen
ce
o
f
l
o
g
in
ag
e
[
2
2
]
to
d
etec
t
p
h
is
h
in
g
.
T
h
ese
m
u
lti
-
s
tag
e
d
etec
tio
n
s
a
ls
o
p
r
o
v
id
e
d
n
ew
m
o
d
els f
o
r
p
h
is
h
in
g
d
etec
tio
n
.
C
o
n
ten
t
-
b
ased
p
h
is
h
in
g
d
etec
tio
n
is
also
em
p
lo
y
ed
,
b
u
t
is
cr
iticized
f
o
r
th
e
d
a
n
g
er
o
f
d
o
wn
lo
ad
in
g
th
e
co
n
ten
t
f
o
r
ex
am
in
atio
n
a
n
d
th
e
c
o
s
t
o
f
tim
e,
b
an
d
wid
th
an
d
r
eso
u
r
ce
s
.
T
h
e
an
o
m
alies in
th
e
web
p
ag
e
b
y
an
aly
zin
g
t
h
e
co
n
ten
t
o
f
th
e
w
eb
p
ag
e
with
a
weig
h
ted
T
F
-
I
DF
m
o
d
el
[
2
3
]
,
s
ig
n
atu
r
e
f
o
r
t
h
e
p
ag
e
[
2
4
]
,
MD
5
h
ash
es o
f
th
e
p
a
g
es [
2
5
]
,
lo
g
i
n
p
ag
e
f
ea
tu
r
es [
2
6
]
,
k
e
y
wo
r
d
s
[
2
7
]
,
i
m
ag
es a
n
d
s
cr
ip
ts
[
2
8
]
,
[
2
9
]
.
Ph
is
h
in
g
UR
L
d
etec
tio
n
tech
n
iq
u
es
ev
o
lv
e
d
u
s
in
g
lex
ical,
h
o
s
t
-
b
ased
,
an
d
c
o
n
ten
t
-
ba
s
ed
f
ea
tu
r
es
an
d
lev
er
a
g
in
g
d
ee
p
lear
n
in
g
tech
n
iq
u
es
[
3
0
]
,
[
3
1
]
.
Dee
p
le
ar
n
in
g
m
o
d
els
b
ased
o
n
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
an
d
d
ee
p
n
eu
r
al
n
etwo
r
k
s
a
r
e
also
em
p
lo
y
ed
s
u
cc
ess
f
u
lly
f
o
r
p
h
is
h
in
g
UR
L
d
etec
tio
n
[
3
2
]
.
T
ec
h
n
i
q
u
es
ev
alu
atin
g
th
e
w
o
r
d
em
b
ed
d
i
n
g
s
an
d
c
h
a
r
ac
ter
em
b
ed
d
in
g
s
f
r
o
m
th
e
UR
L
with
a
C
NN
-
b
ased
UR
L
Net
[
3
3
]
an
d
d
ee
p
lear
n
in
g
-
b
ased
T
e
x
c
ep
tio
n
[
3
4
]
also
ev
o
lv
ed
.
T
h
is
r
esear
ch
u
s
es URL
-
b
ased
class
if
icatio
n
as
it will p
r
o
v
id
e
a
g
o
o
d
am
o
u
n
t o
f
p
r
ed
ictab
il
ity
d
u
e
to
th
e
av
ailab
ilit
y
o
f
lar
g
e
n
u
m
b
er
s
o
f
p
h
is
h
in
g
an
d
N
aïv
e
UR
L
d
atab
ases
,
an
d
ca
n
h
an
d
le
f
alse
n
eg
ativ
es
ef
f
ec
tiv
ely
.
T
h
is
m
o
d
el
ca
p
ita
lis
es
o
n
th
e
av
ailab
ilit
y
o
f
a
v
ast
d
ata
s
et
f
o
r
id
en
tif
y
in
g
th
e
f
ea
tu
r
es
th
at
tr
u
l
y
class
if
y
th
e
p
h
is
h
in
g
UR
L
s
,
c
o
n
f
ir
m
in
g
th
e
f
ea
tu
r
es
id
en
tifi
ed
b
y
th
e
liter
at
u
r
e
r
ev
iew
,
an
d
is
v
er
if
ied
u
s
in
g
lo
g
is
tic
r
eg
r
ess
io
n
a
p
p
lied
o
n
d
if
f
er
en
t
d
atasets
.
T
h
is
m
o
d
el
also
r
elies
o
n
th
e
k
n
o
wled
g
e
-
b
ased
s
tate
m
ac
h
in
e
m
o
d
el
as
t
h
e
p
r
o
b
a
b
ilis
tic
m
o
d
el
to
p
r
ed
ict
th
e
UR
L
as
a
m
alicio
u
s
UR
L
.
T
h
is
m
o
d
el
i
s
d
if
f
er
en
t
f
r
o
m
t
h
e
s
tate
m
ac
h
in
e
-
b
ased
m
o
d
el
s
u
g
g
ested
b
y
Ph
is
h
t
ester
[
3
5
]
,
wh
er
e
th
e
b
eh
a
v
io
u
r
o
f
th
e
web
p
ag
e
is
ev
alu
ated
u
s
in
g
th
e
r
eq
u
est
-
r
esp
o
n
s
e
p
a
ir
f
o
r
ea
ch
we
b
p
ag
e
c
o
m
p
o
n
en
t.
T
h
e
n
aiv
e
i
d
ea
o
v
e
r
h
er
e
is
th
at
it
d
o
es
n
o
t
d
ir
ec
tly
d
e
p
en
d
o
n
th
e
in
p
u
t
d
ata
s
et
o
f
p
h
is
h
in
g
a
n
d
n
aïv
e
UR
L
s
.
I
t
u
s
es
th
e
{f
ea
t
u
r
e,
weig
h
t}
tu
p
le
cr
ea
ted
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
40
,
No
.
1
,
Octo
b
er
20
25
:
356
-
3
6
5
358
b
y
th
e
f
ir
s
t
s
tag
e
in
id
en
tify
in
g
th
e
p
r
o
b
ab
ilit
y
o
f
a
UR
L
b
ei
n
g
p
h
is
h
in
g
,
as
we
ar
e
n
o
t
o
p
en
in
g
th
e
m
alicio
u
s
lin
k
in
th
is
m
eth
o
d
u
n
less
th
e
p
r
ev
i
o
u
s
m
o
d
el
r
e
d
u
ce
s
th
e
ch
an
ce
s
o
f
b
ein
g
in
f
ec
ted
.
T
h
is
will
co
n
f
ir
m
t
h
e
UR
L
to
b
e
p
h
is
h
in
g
b
y
co
n
v
e
r
g
in
g
th
e
ef
f
ec
t
o
f
a
p
r
im
ar
ily
u
s
ed
f
ea
tu
r
e
an
d
th
e
p
r
o
b
a
b
ilit
y
g
en
er
ated
b
y
th
e
m
o
d
el.
2.
M
E
T
H
O
D
UR
L
-
b
ased
d
etec
tio
n
is
cr
iti
cize
d
f
o
r
th
e
p
o
s
s
ib
ilit
y
o
f
attac
k
er
s
o
b
f
u
s
ca
tin
g
th
e
lin
k
to
e
v
ad
e
d
etec
tio
n
a
n
d
th
e
d
elay
i
n
b
lack
lis
tin
g
,
wh
ich
in
cr
ea
s
es
th
e
f
alse
n
eg
ativ
es
in
th
e
d
etec
tio
n
.
T
o
a
d
d
r
ess
th
ese
g
ap
s
,
th
is
r
esear
ch
p
r
o
p
o
s
es
a
two
-
p
h
ase
m
o
d
el
to
d
etec
t
p
h
i
s
h
in
g
UR
L
s
b
y
p
r
ed
ictin
g
th
e
UR
L
'
s
p
r
o
b
ab
ilit
y
o
f
b
ein
g
m
alicio
u
s
(
Fig
u
r
e
1
)
.
T
h
e
f
ir
s
t
co
m
p
o
n
en
t
lear
n
s
th
e
s
tr
u
ctu
r
e
o
f
a
p
h
is
h
in
g
UR
L
b
y
im
p
lem
e
n
tin
g
lo
g
is
tic
r
eg
r
ess
io
n
o
n
th
e
f
ea
tu
r
es
an
d
tr
ain
in
g
th
e
class
if
ier
.
I
t
id
en
tifie
s
th
e
p
r
o
p
er
ties
th
at
tr
u
ly
class
if
y
a
UR
L
in
to
n
aiv
e
an
d
p
h
is
h
in
g
u
s
in
g
lo
g
is
tic
r
eg
r
ess
io
n
,
wh
ich
ca
lcu
lates
th
eir
r
elativ
e
r
an
k
s
in
d
etec
tin
g
UR
L
s
.
T
h
e
clas
s
if
ier
will
b
e
tr
ain
ed
b
y
b
o
th
b
lac
k
lis
t
an
d
wh
ite
lis
t
U
R
L
s
co
llected
at
d
if
f
er
en
t
s
o
u
r
ce
s
at
d
if
f
er
en
t
s
co
p
es.
T
h
e
s
ec
o
n
d
co
m
p
o
n
en
t
th
en
u
tili
s
es
th
i
s
p
r
o
b
ab
ilit
y
in
id
e
n
tify
in
g
UR
L
s
u
s
in
g
s
tate
ma
ch
in
e
-
b
ased
e
v
alu
atio
n
.
T
h
e
m
o
d
el
is
test
ed
ag
ain
s
t so
m
e
k
n
o
wn
d
atasets
,
an
d
th
e
r
esu
lt
s
ar
e
ev
alu
ated
.
Fig
u
r
e
1
.
T
wo
-
p
h
ase
p
h
is
h
in
g
d
etec
tio
n
-
g
e
n
er
al
ar
c
h
itectu
r
e
L
o
g
is
tic
r
eg
r
ess
io
n
is
a
p
o
wer
f
u
l
a
n
d
f
lex
ib
le
m
o
d
e
l
th
at
d
e
m
o
n
s
tr
ates
th
e
p
r
o
b
ab
ilis
tic
d
ep
en
d
e
n
cies
o
f
th
e
f
ea
tu
r
es
i
n
v
o
lv
e
d
in
d
ec
is
io
n
-
m
ak
in
g
.
Un
lik
e
th
e
o
th
e
r
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
lo
g
is
tic
r
eg
r
ess
io
n
s
u
f
f
er
s
t
h
e
lo
west
Fals
e
Po
s
it
iv
es,
s
o
it
is
p
r
ef
er
r
ed
as
f
alse
p
o
s
itiv
es
ar
e
m
o
r
e
ex
p
en
s
iv
e
th
a
n
f
alse
n
eg
ativ
es.
Ho
wev
e
r
,
if
u
s
ed
in
d
ep
en
d
e
n
tly
,
lo
g
is
tic
r
e
g
r
ess
io
n
is
n
o
t
th
e
b
est
f
it
f
o
r
p
h
is
h
in
g
d
etec
tio
n
,
an
d
it
co
n
f
licts
with
o
th
er
m
e
th
o
d
s
.
T
h
e
s
im
p
licity
an
d
i
n
ter
p
r
etab
ilit
y
o
f
lo
g
is
tic
r
eg
r
ess
io
n
ju
s
tify
th
e
f
ir
s
t
s
tag
e
o
f
class
if
icatio
n
.
T
h
e
d
is
tin
ctiv
en
ess
o
f
th
is
s
tu
d
y
is
th
e
u
s
e
o
f
lo
g
is
tic
r
eg
r
ess
io
n
as a
p
ar
tial c
o
m
p
o
n
en
t
in
class
if
icatio
n
,
o
th
er
th
an
u
s
in
g
it
as
a
m
eth
o
d
f
o
r
it.
I
n
s
tead
o
f
class
if
y
in
g
th
e
UR
L
o
n
ly
b
ased
o
n
th
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
tr
ain
ed
o
n
a
v
ailab
le
d
atasets
,
we
tr
y
to
lev
er
ag
e
th
e
p
r
o
b
ab
ilit
y
v
alu
e
g
en
er
ated
as
a
f
ea
tu
r
e
weig
h
tag
e
in
ab
n
o
r
m
al
ity
p
r
ed
ictio
n
.
FS
As
o
n
th
e
o
th
er
h
an
d
,
ar
e
ex
ce
llen
t
at
estab
lis
h
in
g
a
s
eq
u
en
tial
r
elatio
n
s
h
ip
b
etwe
en
e
v
en
ts
an
d
k
ee
p
in
g
tr
ac
k
o
f
ac
tiv
ities
o
v
er
tim
e.
I
t
g
u
ar
a
n
tees
th
at
th
e
cu
r
r
en
t
b
e
h
av
io
u
r
d
e
p
e
n
d
s
o
n
all
th
e
p
r
ev
i
o
u
s
ev
en
ts
,
an
d
th
e
d
ep
e
n
d
en
c
y
e
f
f
ec
tiv
ely
p
r
e
d
icts
th
e
p
atter
n
'
s
l
in
ea
r
b
eh
av
io
u
r
.
C
o
m
b
i
n
in
g
th
e
p
r
o
b
ab
ilis
tic
lo
g
is
tic
r
eg
r
ess
io
n
an
d
lin
ea
r
FS
A
ad
d
s
to
th
e
s
tr
en
g
t
h
s
o
f
th
e
two
-
p
h
ase
m
o
d
el.
T
h
is
en
s
u
r
es
th
e
m
o
d
el
wo
r
k
s
with
tem
p
o
r
a
l
d
ep
en
d
e
n
cies e
n
h
an
ce
d
b
y
a
p
r
o
b
ab
ilit
y
-
b
ased
m
o
d
el.
2
.
1
.
P
ha
s
e
1
:
f
ea
t
ure
identif
ica
t
io
n a
nd
ra
nk
ing
(
F
I
R
)
As
th
e
liter
atu
r
e
r
ev
iew
s
u
m
m
ar
is
es,
th
is
p
h
ase
h
elp
s
th
e
m
o
d
el
ch
o
o
s
e
th
e
r
i
g
h
t
f
ea
t
u
r
es
f
o
r
th
e
n
ex
t
k
n
o
wled
g
e
-
b
ased
p
h
is
h
in
g
UR
L
p
r
ed
ictio
n
(
PUP)
p
h
ase.
T
h
e
p
r
o
ce
s
s
m
o
v
es
th
r
o
u
g
h
th
r
ee
s
tep
s
:
f
ea
tu
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
h
is
h
in
g
UR
L p
r
ed
ictio
n
–
tw
o
-
p
h
a
s
e
mo
d
el
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
a
n
d
fin
ite
…
(
N
is
h
a
T N
)
359
id
en
tific
atio
n
,
f
ea
tu
r
e
s
elec
tio
n
an
d
f
ea
tu
r
e
r
a
n
k
in
g
.
T
h
e
p
r
im
ar
y
f
ea
tu
r
e
s
elec
tio
n
is
b
ased
o
n
th
e
liter
atu
r
e
r
ev
iew
o
u
tp
u
t a
n
d
t
h
en
ap
p
r
ai
s
ed
u
s
in
g
lo
g
is
tic
r
eg
r
ess
io
n
.
Featu
r
e
i
d
en
tific
atio
n
h
elp
s
to
d
eter
m
in
e
th
e
r
elativ
e
im
p
o
r
t
an
ce
o
f
th
e
f
ea
tu
r
e
u
n
d
er
co
n
s
id
er
atio
n
.
T
h
e
p
o
wer
o
f
lo
g
is
tic
r
eg
r
e
s
s
io
n
in
q
u
a
n
tify
in
g
th
e
r
el
ativ
e
ef
f
ec
t
o
f
a
n
in
d
ep
e
n
d
e
n
t
v
ar
iab
le
o
n
th
e
d
ep
en
d
e
n
t
v
a
r
iab
le
is
u
s
ed
in
th
is
p
h
ase.
T
h
is
m
o
d
el
d
o
es
n
o
t
d
ep
e
n
d
o
n
th
e
ex
tr
ac
ted
UR
L
f
ea
tu
r
es
lis
t
av
ailab
le
o
n
lin
e.
W
e
ex
tr
ac
ted
th
e
UR
L
f
ea
tu
r
es
f
r
o
m
th
e
UR
L
s
g
iv
en
an
d
id
en
tifie
d
s
o
m
e
f
ea
tu
r
es
th
at
s
u
cc
ess
f
u
lly
class
if
y
th
e
p
h
is
h
in
g
UR
L
f
r
o
m
t
h
e
b
e
n
ig
n
UR
L
.
T
o
f
in
alis
e
th
e
f
ea
tu
r
es
an
d
r
ein
f
o
r
ce
th
eir
r
elativ
e
im
p
o
r
tan
ce
with
o
th
er
f
ea
tu
r
es,
th
ey
ar
e
ch
ec
k
ed
ag
ain
s
t
th
e
s
tan
d
ar
d
d
atasets
.
T
h
e
r
elativ
e
p
r
esen
ce
o
f
th
ese
f
ea
t
u
r
es
is
ev
alu
ated
b
y
th
eir
r
elativ
e
p
r
esen
ce
a
n
d
th
eir
co
n
tr
ib
u
tio
n
to
war
d
s
cl
ass
if
y
in
g
th
e
UR
L
s
a
r
e
s
tu
d
ied
.
T
h
e
co
ef
f
icien
t
v
alu
e
in
th
e
lo
g
is
tic
r
eg
r
ess
io
n
ex
p
r
ess
es
th
e
co
n
tr
ib
u
tio
n
o
f
th
e
p
ar
ticu
lar
f
ea
tu
r
e
in
d
eter
m
in
in
g
wh
eth
er
th
e
UR
L
is
p
h
is
h
in
g
o
r
n
o
t.
Th
e
o
d
d
s
r
atio
m
ea
s
u
r
es
th
e
lik
elih
o
o
d
o
f
an
ev
en
t,
an
d
th
e
p
r
o
b
a
b
ilit
y
v
alu
e
is
d
er
iv
e
d
f
r
o
m
th
e
o
d
d
s
r
atio
as
:
=
(
1
+
)
⁄
(
1
)
2
.
2
.
P
ha
s
e
2
:
p
his
hin
g
UR
L
p
re
dict
io
n (
P
UP
)
T
h
is
p
h
ase
p
r
ed
icts
a
UR
L
to
b
e
m
alicio
u
s
b
y
em
p
lo
y
i
n
g
s
ig
n
atu
r
e
cr
ea
tio
n
,
FS
A
-
b
ased
d
etec
tio
n
an
d
th
e
attac
k
p
r
o
b
ab
ilit
y
p
r
ed
ictio
n
.
Sig
n
atu
r
e
cr
ea
tio
n
u
tili
ze
s
th
e
f
o
r
m
al
lan
g
u
a
g
e
m
o
d
el.
A
f
o
r
m
al
lan
g
u
ag
e
L
1
o
v
er
a
d
ef
i
n
ed
a
lp
h
ab
et
s
et
Ʃ
i
s
an
in
f
in
ite
s
et
o
f
s
tr
in
g
s
d
ef
in
ed
o
v
e
r
th
e
alp
h
ab
et
Ʃ
.
R
eg
u
lar
lan
g
u
ag
e
ca
n
b
e
ex
p
r
ess
ed
u
s
in
g
a
f
o
r
m
u
la
o
f
B
o
o
lean
lo
g
ic,
k
n
o
wn
as
r
eg
u
lar
e
x
p
r
es
s
io
n
s
.
W
e
d
ef
in
e
a
r
eg
u
lar
lan
g
u
ag
e
with
2
s
y
m
b
o
ls
,
{1
,
0
},
as a
b
i
n
ar
y
s
tr
in
g
o
f
n
p
o
s
itio
n
s
:
1
=
{
ϵ
{
1
,
0
}
∗
/
}
(
2
)
T
h
e
v
alu
e
n
is
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
u
s
ed
to
ev
alu
ate
wh
eth
er
th
e
UR
L
i
s
p
h
is
h
in
g
o
r
n
o
t.
T
h
e
lan
g
u
ag
e
d
e
f
in
es
th
e
m
alicio
u
s
UR
L
as
a
s
tr
in
g
with
at
lea
s
t
o
n
e
'
1
’
in
th
e
s
tr
in
g
.
A
s
tr
in
g
with
all
‘
0
's
is
th
e
UR
L
with
n
o
s
ig
n
s
o
f
m
alicio
u
s
tr
ac
es.
T
h
e
g
r
ea
ter
th
e
f
r
eq
u
en
cy
o
f
‘
1
'
s
it
h
as,
th
e
m
o
r
e
p
r
o
b
a
b
le
th
e
UR
L
is
m
alicio
u
s
.
R
eg
u
lar
lan
g
u
ag
es
ar
e
en
co
d
ed
u
s
in
g
f
in
ite
s
tat
e
au
to
m
ata
,
o
r
in
o
th
er
w
o
r
d
s
,
ca
n
b
e
ev
al
u
ated
u
s
in
g
f
in
ite
s
tate
au
to
m
ata
d
ef
in
ed
f
o
r
th
at
lan
g
u
ag
e.
A
f
in
it
e
s
tate
au
to
m
ata
(
d
eter
m
in
is
tic
f
in
ite
au
to
m
ata
)
is
d
ef
in
ed
as a
f
i
v
e
-
tu
p
le
n
o
tatio
n
.
=
(
,
∑
,
,
0
,
)
(
3
)
W
h
er
e
Q
d
en
o
tes
f
in
ite
s
et
o
f
s
tates,
∑
d
en
o
tes
f
in
ite
s
et
o
f
in
p
u
t
s
y
m
b
o
ls
,
δ
d
e
n
o
tes
t
r
an
s
itio
n
f
u
n
ctio
n
,
q0
is
th
e
s
tar
t
s
tate
wh
er
e
q
0
ϵ
Q
an
d
F
is
th
e
s
et
o
f
f
in
al
o
r
ac
ce
p
tin
g
s
tates wh
ich
is
a
s
u
b
s
et
o
f
Q
.
B
ased
o
n
th
e
f
o
r
m
al
d
ef
in
itio
n
o
f
f
i
n
ite
s
tate
au
to
m
ata
,
P
HI
SH_
FS
A,
wh
ich
ev
alu
ates
th
e
r
eg
u
lar
ex
p
r
ess
io
n
s
ig
n
atu
r
e,
is
d
ef
in
ed
as
g
iv
en
in
Fig
u
r
e
2
.
T
h
e
s
tate
m
ac
h
i
n
e
with
9
s
tates
w
h
er
e
s
tate
Q
0
is
th
e
in
itial
s
tate.
T
h
e
s
tate
m
ac
h
in
e
class
if
ies
al
l
s
tr
in
g
s
en
d
in
g
in
Q
1
as
a
s
af
e
UR
L
an
d
d
o
es
n
o
t
co
n
tain
th
e
f
ea
tu
r
es
th
at
d
ef
in
e
a
m
alicio
u
s
UR
L
.
Strin
g
s
en
d
in
g
o
n
a
n
y
o
th
er
s
tate
in
d
icate
th
e
p
r
o
b
ab
ilit
y
o
f
th
e
UR
L
b
ein
g
m
alicio
u
s
an
d
th
e
p
r
o
b
a
b
ilit
y
is
ca
lcu
lated
in
th
e
p
r
o
b
ab
ilit
y
p
r
ed
ictio
n
p
h
ase.
Fig
u
r
e
2
.
PHI
SH_
FS
A
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
40
,
No
.
1
,
Octo
b
er
20
25
:
356
-
3
6
5
360
T
h
e
last
s
tep
in
th
i
s
p
h
ase
is
p
r
o
b
ab
ilit
y
p
r
ed
ictio
n
,
wh
er
e
th
e
p
r
o
b
a
b
ilit
y
o
f
th
e
UR
L
b
ein
g
m
alicio
u
s
is
ev
alu
ated
as
M
S
.
Ma
licio
u
s
_
Sco
r
e
is
d
ef
in
ed
u
s
in
g
two
f
ac
to
r
s
,
p
r
esen
t
f
ea
tu
r
e
co
u
n
t
(
PF
C
)
an
d
p
r
o
b
a
b
ilit
y
v
alu
e
(
PV)
.
T
h
e
f
o
r
m
u
latio
n
co
n
d
en
s
es th
e
co
n
tr
ib
u
tio
n
s
o
f
ea
ch
f
ea
tu
r
e
as a
f
u
n
ctio
n
o
f
its
v
alu
e,
in
d
icatin
g
th
e
p
r
esen
ce
,
p
o
s
itio
n
in
d
icatin
g
t
h
e
r
elev
a
n
ce
,
an
d
p
r
o
b
a
b
ilit
y
in
d
icatin
g
t
h
e
co
n
tr
ib
u
tio
n
i
n
p
r
ed
ictio
n
.
Po
wer
in
g
th
e
p
o
s
i
tio
n
v
alu
e
with
2
will
claim
th
e
co
n
v
er
s
io
n
o
f
th
e
b
in
ar
y
p
o
s
itio
n
al
v
alu
e
to
weig
h
tag
e.
T
h
e
m
ath
em
atica
l
r
ep
r
esen
tatio
n
o
f
MS
is
d
io
s
p
lay
ed
in
(
4
)
a
n
d
(
5
)
.
=
(
,
)
(
4
)
=
∑
(
×
(
2
,
)
×
[
]
)
=
1
(
5
)
wh
er
e
,
is
th
e
v
alu
e
o
f
r
eg
u
lar
ex
p
r
ess
io
n
at
p
o
s
itio
n
i
an
d
,
i
s
th
e
p
o
s
itio
n
o
f
th
e
p
r
esen
t f
e
atu
r
e
in
th
e
r
eg
u
la
r
ex
p
r
ess
io
n
.
Pre
s
en
t
f
ea
tu
r
e
co
u
n
t
(
PF
C
)
r
ef
er
s
to
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
f
o
u
n
d
p
r
esen
t
in
th
e
UR
L
an
d
its
p
o
s
itio
n
in
th
e
r
eg
u
lar
ex
p
r
ess
io
n
,
wh
ich
class
if
ies
it
to
a
m
alicio
u
s
o
n
e
an
d
i
d
en
ti
f
ies
th
e
s
ev
er
ity
o
f
th
e
ch
a
n
ce
o
f
t
h
e
UR
L
b
ein
g
b
lack
lis
ted
.
Pro
b
a
b
ilit
y
v
al
u
e
(
PV)
is
th
e
f
ea
tu
r
e
p
r
o
b
ab
ilit
y
ar
r
ay
d
e
f
in
ed
f
r
o
m
th
e
p
r
ev
io
u
s
s
tag
e.
C
alcu
latin
g
m
alicio
u
s
s
co
r
es
u
s
es
two
f
ea
tu
r
e
p
r
o
p
er
ties
:
f
ea
tu
r
e
p
o
s
itio
n
in
t
h
e
r
e
g
u
lar
ex
p
r
ess
io
n
an
d
th
e
ca
lcu
lated
p
r
o
b
a
b
ilit
y
f
r
o
m
lo
g
is
tic
r
eg
r
ess
io
n
.
T
h
is
em
p
o
wer
s
th
e
p
r
e
d
ictio
n
o
f
m
alicio
u
s
UR
L
s
b
y
im
p
lan
tin
g
th
e
f
ea
tu
r
e
im
p
o
r
t
an
ce
with
p
r
o
b
ab
ilit
y
an
d
f
ea
t
u
r
e
r
elev
a
n
ce
with
p
o
s
itio
n
.
As
th
e
p
r
o
b
ab
ilit
ies
ar
e
ca
lcu
lated
b
y
an
aly
zi
n
g
a
d
ata
s
et
af
ter
id
en
tify
i
n
g
th
e
p
o
p
u
lar
f
ea
tu
r
es
o
f
th
e
m
alicio
u
s
UR
L
,
th
e
f
alse
p
o
s
itiv
es
ar
e
r
e
d
u
ce
d
.
Fin
ally
,
th
e
MS
is
ca
lcu
lated
f
o
r
ea
ch
UR
L
an
d
is
aler
ted
with
t
h
e
s
co
r
e.
T
h
e
n
etwo
r
k
ad
m
in
ca
n
t
h
en
u
tili
ze
th
e
s
co
r
e
to
b
lo
ck
th
e
UR
L
f
r
o
m
th
e
n
etwo
r
k
.
T
h
is
d
etec
tio
n
'
s
cr
itical
ar
ea
is
id
en
tify
in
g
th
e
t
h
r
esh
o
l
d
v
alu
e
with
wh
ich
th
e
M
S
ca
n
b
e
b
en
ch
m
ar
k
ed
.
C
o
n
s
id
er
in
g
t
h
e
f
lex
ib
le
n
at
u
r
e
o
f
th
e
UR
L
f
ea
tu
r
es,
we
d
ec
id
ed
t
o
w
o
r
k
with
a
f
lex
ib
le
th
r
esh
o
ld
v
alu
e.
T
h
e
th
r
esh
o
ld
v
alu
e
is
ca
lcu
lated
b
y
ev
al
u
atin
g
d
if
f
er
e
n
t
d
atasets
av
ailab
le
an
d
ag
r
ee
i
n
g
o
n
th
e
MS
s
co
r
e.
T
h
e
MS
v
alu
e
ca
lcu
lated
is
ev
al
u
ated
to
f
i
n
d
th
e
co
n
f
u
s
io
n
m
atr
ix
to
e
v
alu
ate
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
.
T
h
is
en
ab
les
th
e
m
o
d
el
to
b
e
f
lex
ib
le
en
o
u
g
h
t
o
ac
co
m
m
o
d
ate
an
y
f
u
tu
r
e
ch
an
g
e
in
th
e
f
ea
tu
r
e
ev
alu
atio
n
.
T
h
is
n
ec
ess
itates a
co
n
tin
u
o
u
s
f
ix
atio
n
o
f
th
r
esh
o
ld
v
alu
es b
y
e
v
alu
atin
g
t
h
e
r
ec
en
t d
ataset
tr
en
d
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
s
et
a
nd
ex
perim
ent
a
l set
up
T
h
e
m
o
d
el
r
eq
u
ir
es d
ata
to
b
e
f
ed
in
two
d
if
f
er
e
n
t
p
h
ases
.
T
o
in
clu
d
e
t
h
e
v
ar
ia
b
ilit
y
in
th
e
UR
L
d
ata
s
et,
we
h
av
e
co
llected
d
ata
f
r
o
m
v
a
r
io
u
s
s
o
u
r
ce
s
,
in
clu
d
in
g
Kag
g
le
[
3
3
]
,
Ph
is
h
T
an
k
[
3
4
]
,
an
d
th
e
C
o
m
m
o
n
cr
awl
d
ata
s
et
[
3
5
]
.
T
h
e
s
elec
t
io
n
o
f
d
if
f
er
en
t
d
atasets
f
r
o
m
d
if
f
er
en
t
s
co
p
es
co
n
v
in
ce
s
th
e
m
o
d
el'
s
r
eliab
ilit
y
as
th
e
UR
L
d
ata
is
v
o
latile
a
n
d
co
n
s
tan
tly
ch
an
g
in
g
.
T
h
e
d
a
ta
s
et
p
r
o
v
i
d
es
b
o
th
n
aïv
e
an
d
p
h
is
h
in
g
UR
L
s
to
tr
ain
th
e
m
o
d
el.
Kag
g
le
d
ata
s
ets ar
e
u
s
ed
to
tr
ain
th
e
m
o
d
el
,
b
u
t o
n
ly
ex
tr
ac
t th
e
r
aw
UR
L
s
f
r
o
m
th
e
d
ata
s
et.
Ph
is
h
in
g
d
ata
s
et
is
co
llect
ed
f
r
o
m
Ph
is
h
tan
k
r
eg
u
lar
l
y
,
an
d
n
aïv
e
d
ata
f
r
o
m
C
o
m
m
o
n
C
r
awl.
A
h
eter
o
g
en
e
o
u
s
d
ata
s
et
is
g
en
er
ated
b
y
co
m
b
in
in
g
d
atasets
co
llected
f
r
o
m
d
if
f
er
en
t
d
ata
s
o
u
r
ce
s
at
d
if
f
er
en
t
in
ter
v
als.
W
e
u
s
ed
f
iv
e
tr
ain
i
n
g
d
atasets
with
b
o
th
p
o
s
itiv
e
an
d
n
e
g
ativ
e
UR
L
s
u
n
if
o
r
m
ly
allo
ca
ted
an
d
f
iv
e
d
if
f
er
en
t
d
atasets
f
o
r
test
in
g
,
wh
ich
in
clu
d
ed
u
n
ar
y
d
ata.
T
h
e
m
o
d
el
is
d
ev
elo
p
e
d
b
y
Py
th
o
n
co
d
e
,
v
er
s
io
n
3
.
1
1
.
5
,
with
s
tan
d
ar
d
lib
r
ar
ies
.
T
h
e
ex
p
er
im
en
ts
ar
e
co
n
d
u
ct
ed
in
an
e
n
v
ir
o
n
m
en
t
with
s
p
e
cif
icatio
n
s
s
u
ch
as
a
6
4
-
b
it
o
p
er
atin
g
s
y
s
tem
,
1
6
GB
R
AM
,
an
d
a
1
.
3
0
GHz
I
n
tel
p
r
o
ce
s
s
o
r
.
3
.
2
.
F
e
a
t
ure
identif
ica
t
io
n a
nd
f
ea
t
ure
s
elec
t
io
n
T
h
e
UR
L
s
co
llected
f
r
o
m
d
if
f
e
r
en
t so
u
r
ce
s
ar
e
p
ar
s
ed
,
an
d
th
e
r
eq
u
ir
e
d
f
ea
tu
r
es a
r
e
r
etr
ie
v
ed
.
As th
e
UR
L
s
ar
e
co
llec
ted
f
r
o
m
d
if
f
er
en
t
s
o
u
r
ce
s
to
p
r
eser
v
e
th
e
u
n
p
r
ed
ictab
ilit
y
in
th
e
d
at
a
s
et,
we
ar
e
n
o
t
d
ep
en
d
e
n
t
o
n
th
e
f
ea
tu
r
e
d
ata
s
et
an
d
is
g
en
er
atin
g
o
u
r
o
wn
f
ea
tu
r
e
s
et
b
y
co
m
b
i
n
in
g
d
if
f
e
r
en
t
UR
L
d
atasets
an
d
p
a
r
s
in
g
th
e
d
ata.
T
h
e
s
e
v
en
f
ea
tu
r
es
ar
e
f
in
alize
d
b
y
an
aly
zin
g
th
e
r
elativ
e
f
r
e
q
u
e
n
cy
o
f
th
o
s
e
in
th
e
d
ataset
u
n
d
er
co
n
s
id
er
atio
n
.
T
h
e
f
ea
tu
r
es
s
elec
ted
in
clu
d
ed
b
in
ar
y
f
ea
tu
r
es
as
well
a
s
d
is
cr
ete
v
alu
e
-
b
ased
f
ea
tu
r
es.
T
ab
le
1
s
u
m
m
ar
izes th
e
s
elec
ted
f
ea
tu
r
es a
n
d
th
eir
r
elativ
e
p
r
esen
ce
in
th
e
p
r
ev
i
o
u
s
s
tu
d
ies.
T
h
e
f
ea
tu
r
es
s
elec
ted
a
r
e
f
in
al
is
e
d
by
r
ein
f
o
r
c
in
g
th
eir
r
elativ
e
im
p
o
r
tan
ce
with
o
th
er
f
ea
tu
r
es
.
T
h
e
ev
alu
atio
n
is
co
n
d
u
cte
d
o
n
m
u
ltip
le
s
tan
d
ar
d
d
atasets
,
an
d
th
ei
r
r
elativ
e
im
p
o
r
tan
ce
is
v
er
if
ied
.
B
in
ar
y
f
ea
tu
r
es
lik
e
th
e
p
r
esen
ce
o
f
Un
ico
d
e
an
d
a
s
ec
o
n
d
d
o
u
b
le
s
lash
in
UR
L
s
,
a
s
well
as
I
P
-
b
ased
UR
L
s
,
s
h
o
w
a
clea
r
d
is
tin
ctio
n
b
etwe
en
p
h
is
h
in
g
an
d
g
e
n
u
in
e
UR
L
s
.
Feat
u
r
es
lik
e
th
e
len
g
th
o
f
th
e
UR
L
an
d
th
e
n
u
m
b
e
r
o
f
d
o
ts
an
d
s
lash
es
in
th
e
UR
L
d
is
p
lay
a
co
n
s
tan
t
v
alu
e
r
an
g
e
f
o
r
g
en
u
in
e
a
n
d
p
h
is
h
in
g
U
R
L
s
to
in
d
icate
th
e
s
tr
en
g
th
o
f
th
e
s
am
e
in
p
h
is
h
in
g
UR
L
d
etec
tio
n
.
Fig
u
r
e
3
s
h
o
ws
th
is
f
ea
tu
r
e
a
n
aly
s
is
co
n
d
u
cted
o
n
o
n
e
tr
ain
in
g
d
ataset.
T
h
e
s
am
e
is
r
ep
ea
ted
f
o
r
t
h
e
o
th
e
r
d
atas
ets,
to
o
,
to
s
u
p
p
o
r
t
t
h
e
r
esu
lt
.
T
h
ese
h
an
d
p
ick
e
d
f
ea
tu
r
es a
r
e
f
in
alize
d
an
d
f
o
r
w
ar
d
ed
to
t
h
e
n
ex
t le
v
el
to
aid
i
n
p
h
is
h
in
g
UR
L
d
etec
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
h
is
h
in
g
UR
L p
r
ed
ictio
n
–
tw
o
-
p
h
a
s
e
mo
d
el
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
a
n
d
fin
ite
…
(
N
is
h
a
T N
)
361
T
ab
le
1
.
Featu
r
e
im
p
o
r
tan
ce
a
s
co
n
f
ir
m
ed
b
y
p
r
ev
io
u
s
r
esear
ch
er
s
F
e
a
t
u
r
e
C
o
d
e
F
e
a
t
u
r
e
N
a
me
D
e
scri
p
t
i
o
n
R
e
f
e
r
e
n
c
e
s
I
S
_
I
P
I
P
b
a
sed
U
R
L
A
t
t
a
c
k
e
r
s re
p
l
i
c
a
t
e
t
h
e
p
a
g
e
t
o
l
u
r
e
u
s
e
r
s t
o
a
v
o
i
d
D
N
S
serv
e
r
r
e
g
i
st
r
a
t
i
o
n
.
[
1
0
]
,
[
1
3
]
,
[
1
7
]
,
[
1
8
]
,
[
2
0
]
,
[
2
2
]
LEN
_
U
R
L
Le
n
g
t
h
o
f
U
R
L
A
t
i
n
y
U
R
L
e
n
h
a
n
c
e
s
s
u
sp
i
c
i
o
n
,
j
u
st
a
s a
v
e
r
y
l
a
r
g
e
U
R
L.
[
1
7
]
,
[
2
0
]
,
[
3
3
]
C
H
EC
K
_
@
P
r
e
sen
c
e
o
f
@
i
n
U
R
L
B
r
o
w
sers
i
g
n
o
r
e
a
n
y
p
r
e
c
e
d
i
n
g
c
h
a
r
a
c
t
e
r
o
f
‘
@
’
w
h
i
l
e
p
a
r
s
i
n
g
t
h
e
U
R
L
,
w
h
i
c
h
h
e
l
p
s
t
h
e
a
t
t
a
c
k
e
r
t
o
a
d
d
a
g
e
n
u
i
n
e
-
l
o
o
k
i
n
g
d
o
mai
n
n
a
m
e
b
e
f
o
r
e
h
i
s
ma
l
i
c
i
o
u
s
d
o
m
a
i
n
a
n
d
d
u
p
e
a
v
i
c
t
i
m.
[
1
3
]
,
[
1
7
]
,
[
2
0
]
,
[
2
2
]
C
H
EC
K
_
U
N
I
C
O
D
E
P
r
e
sen
c
e
o
f
U
n
i
c
o
d
e
c
h
a
r
a
c
t
e
r
s
i
n
U
R
L
P
h
i
s
h
i
n
g
d
o
m
a
i
n
s
t
e
n
d
t
o
i
n
c
l
u
d
e
U
n
i
c
o
d
e
t
o
g
e
t
a
v
i
s
u
a
l
si
m
i
l
a
r
i
t
y
t
o
a
g
e
n
u
i
n
e
w
e
b
s
i
t
e
.
[
1
3
]
,
[
1
7
]
,
[
1
8
]
,
[
2
0
]
,
[
2
2
]
N
O
_
O
F
_
D
O
TS_
H
N
A
M
E
N
u
mb
e
r
o
f
d
o
t
s i
n
h
o
st
h
o
s
t
n
a
me
I
n
c
l
u
d
i
n
g
d
o
t
s i
s a
t
e
c
h
n
i
q
u
e
a
t
t
a
c
k
e
r
s
a
d
o
p
t
t
o
h
i
d
e
t
h
e
p
h
i
s
h
i
n
g
d
o
mai
n
i
n
si
d
e
a
l
e
g
i
t
i
m
a
t
e
d
o
m
a
i
n
.
[
1
3
]
,
[
1
8
]
,
[
2
2
]
,
[
3
3
]
S
EC
O
N
D
_
D
O
U
B
_
S
LA
S
H
P
r
e
sen
c
e
o
f
a
se
c
o
n
d
d
o
u
b
l
e
sl
a
s
h
i
n
U
R
L
A
d
d
i
n
g
a
s
e
c
o
n
d
d
o
u
b
l
e
s
l
a
s
h
i
n
U
R
L
w
i
l
l
c
o
n
f
u
s
e
t
h
e
c
r
a
w
l
e
r
s w
i
t
h
d
i
f
f
e
r
e
n
t
v
e
r
si
o
n
s.
N
O
_
O
F
_
S
LA
S
H
ES
N
u
mb
e
r
o
f
sl
a
sh
e
s
i
n
U
R
L
N
u
mb
e
r
o
f
sl
a
sh
e
s
i
n
a
U
R
L
i
n
d
i
c
a
t
e
s
t
h
e
n
u
m
b
e
r
o
f
su
b
d
o
m
a
i
n
s
a
n
d
i
s
a
d
i
r
e
c
t
i
n
d
i
c
a
t
i
o
n
t
h
a
t
a
U
R
L
i
s
u
n
t
r
u
s
t
e
d
.
Fig
u
r
e
3
.
Featu
r
e
d
is
tr
ib
u
tio
n
3
.
3
.
F
e
a
t
ure
r
a
nk
ing
T
h
e
id
en
tifie
d
f
ea
tu
r
e
p
r
o
b
a
b
i
liti
es
ar
e
u
s
ed
f
o
r
f
ea
tu
r
e
r
an
k
in
g
.
As
th
e
tr
ain
in
g
d
ata
is
n
o
t
u
n
if
o
r
m
,
th
e
r
esu
lt
also
s
h
o
ws
h
eter
o
g
e
n
eity
in
th
e
p
r
o
b
ab
ilit
y
v
alu
es
.
T
h
e
h
eter
o
g
en
e
o
u
s
v
alu
es
a
n
d
th
e
r
ea
s
o
n
f
o
r
it
ar
e
clea
r
ly
v
is
ib
le
f
r
o
m
th
e
f
ea
tu
r
e
s
u
m
m
a
r
y
s
tatis
tics
.
T
h
e
p
r
esen
ce
o
r
a
b
s
en
ce
o
f
UR
L
s
am
p
les
with
in
d
iv
id
u
al
f
ea
tu
r
es
lar
g
ely
in
f
lu
en
ce
s
th
e
p
r
o
b
ab
ilit
y
v
al
u
es,
as
ev
id
en
t
f
r
o
m
th
e
d
atasets
.
T
h
is
r
ep
licates
th
e
r
ea
l
-
wo
r
ld
UR
L
d
ata,
wh
e
r
e
t
h
e
m
o
d
el
will wo
r
k
,
wh
ich
h
a
s
n
o
p
r
ed
icta
b
ilit
y
o
n
th
e
f
ea
tu
r
e
p
r
esen
ce
.
L
o
g
is
tic
r
eg
r
ess
io
n
is
ap
p
lied
to
ea
ch
d
ata
s
et
s
ep
ar
ately
,
an
d
attr
ib
u
tes
lik
e
co
ef
f
icien
ts
,
o
d
d
s
r
atio
s
,
an
d
p
r
o
b
a
b
ilit
y
v
al
u
es
ar
e
c
alcu
lated
an
d
an
al
y
ze
d
.
T
h
e
ca
lcu
lated
c
o
ef
f
icien
t
v
alu
e
s
,
o
d
d
s
r
atio
,
a
n
d
p
r
o
b
a
b
ilit
y
ar
e
g
iv
e
n
in
T
a
b
le
2
.
T
h
e
a
v
er
ag
e
v
alu
e
o
f
p
r
o
b
a
b
ilit
y
is
f
o
u
n
d
to
b
e
r
ep
r
esen
t
ativ
e
an
d
is
u
s
ed
in
th
e
f
ea
tu
r
e
r
a
n
k
in
g
p
h
ase.
T
h
e
f
ea
tu
r
e
p
r
o
b
a
b
ilit
y
tu
p
le
f
in
ali
ze
d
is
as g
iv
en
in
T
a
b
le
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
40
,
No
.
1
,
Octo
b
er
20
25
:
356
-
3
6
5
362
T
ab
le
2
.
C
o
ef
f
icien
t,
o
d
d
s
r
atio
an
d
p
r
o
b
ab
ilit
ies o
f
tr
ain
in
g
s
et
D
a
t
a
set
A
t
t
r
i
b
u
t
e
N
a
mes
I
S
_
I
P
LEN
_
U
RL
C
H
EC
K
_
@
C
H
EC
K
_
U
N
I
C
O
D
E
N
O
_
O
F
_
D
O
TS
_
H
N
A
M
E
S
EC
O
N
D
_
D
O
U
B
_
S
L
A
S
H
N
O
_
O
F
_
S
LA
S
H
ES
TR
A
I
N
#
1
Ph
i
s
h
i
n
g
:
5
7
4
1
N
a
ï
v
e
:
5
7
4
0
C
o
e
f
f
i
c
i
e
n
t
s
3
.
1
5
0
.
0
1
3
.
6
2
-
0
.
3
9
0
.
1
8
1
.
9
7
0
.
1
7
O
d
d
s
R
a
t
i
o
2
3
.
4
2
1
.
0
1
3
7
.
3
8
0
.
6
8
1
.
2
0
7
.
1
7
1
.
1
8
P
r
o
b
a
b
i
l
i
t
i
e
s
0
.
9
6
0
.
5
0
0
.
9
7
0
.
4
0
0
.
5
5
0
.
8
8
0
.
5
4
TR
A
I
N
#
2
Ph
i
s
h
i
n
g
:
5
5
0
4
2
N
a
ï
v
e
:
4
0
8
6
8
C
o
e
f
f
i
c
i
e
n
t
s
0
.
0
0
0
.
0
0
0
.
8
9
0
.
5
7
0
.
0
0
0
.
5
3
0
.
0
4
O
d
d
s
R
a
t
i
o
1
.
0
0
1
.
0
0
2
.
4
3
1
.
7
6
1
.
0
0
1
.
7
0
1
.
0
4
P
r
o
b
a
b
i
l
i
t
i
e
s
0
.
5
0
0
.
5
0
0
.
7
1
0
.
6
4
0
.
5
0
0
.
6
3
0
.
5
1
TR
A
I
N
#
3
Ph
i
s
h
i
n
g
:
9
8
0
N
a
ï
v
e
:
8
5
8
C
o
e
f
f
i
c
i
e
n
t
s
-
1
.
5
0
0
.
0
2
0
.
6
5
-
0
.
0
7
0
.
2
7
0
.
0
8
1
.
5
1
O
d
d
s
R
a
t
i
o
0
.
2
2
1
.
0
2
1
.
9
2
0
.
9
3
1
.
3
1
1
.
0
8
4
.
5
2
P
r
o
b
a
b
i
l
i
t
i
e
s
0
.
1
8
0
.
5
1
0
.
6
6
0
.
4
8
0
.
5
7
0
.
5
2
0
.
8
2
TR
A
I
N
#
4
Ph
i
s
h
i
n
g
:
3
6
1
2
N
a
ï
v
e
:
3
2
9
7
C
o
e
f
f
i
c
i
e
n
t
s
0
.
9
5
0
.
0
2
0
.
1
4
0
.
1
8
-
0
.
2
2
-
1
.
1
4
0
.
1
6
O
d
d
s
R
a
t
i
o
2
.
5
9
1
.
0
2
1
.
1
5
1
.
1
9
0
.
8
0
0
.
3
2
1
.
1
8
P
r
o
b
a
b
i
l
i
t
i
e
s
0
.
7
2
0
.
5
0
0
.
5
3
0
.
5
4
0
.
4
5
0
.
2
4
0
.
5
4
TR
A
I
N
#
5
Ph
i
s
h
i
n
g
:
1
9
2
8
3
0
N
a
ï
v
e
:
1
7
9
4
8
5
C
o
e
f
f
i
c
i
e
n
t
s
3
.
0
1
0
.
0
0
2
.
6
6
-
0
.
5
3
2
.
1
0
4
.
3
6
0
.
1
9
O
d
d
s
R
a
t
i
o
2
0
.
2
8
1
.
0
0
1
4
.
2
7
0
.
5
9
8
.
1
7
7
8
.
4
4
1
.
2
0
P
r
o
b
a
b
i
l
i
t
i
e
s
0
.
9
5
0
.
5
0
0
.
9
3
0
.
3
7
0
.
8
9
0
.
9
9
0
.
5
5
T
ab
le
3
.
Selecte
d
f
ea
tu
r
es p
r
o
b
ab
ilit
y
v
alu
es
F
e
a
t
u
r
e
_
N
a
m
e
P
r
o
b
a
b
i
l
i
t
y
v
a
l
u
e
(
A
v
e
r
a
g
e
)
C
H
EC
K
_
@
0
.
7
6
1
6
I
S
_
I
P
0
.
6
6
3
2
S
EC
O
N
D
_
D
O
U
B
_
S
LA
S
H
0
.
6
5
1
4
N
O
_
O
F
_
S
LA
S
H
ES
0
.
5
9
1
6
N
O
_
O
F
_
D
O
TS_
H
N
A
M
E
0
.
5
9
0
0
LEN
_
U
R
L
0
.
5
0
2
8
C
H
EC
K
_
U
N
I
C
O
D
E
0
.
4
8
7
8
3
.
4
.
P
UP
-
p
his
hi
ng
URL
p
re
dict
io
n
T
h
e
MS
o
f
th
e
UR
L
is
ca
lcu
l
ated
an
d
is
aler
ted
if
it
is
m
o
r
e
th
an
th
e
ac
ce
p
ted
th
r
esh
o
ld
v
alu
e.
T
h
e
th
r
esh
o
ld
v
alu
e
f
o
r
MS
is
ca
lcu
lated
b
y
f
ee
d
in
g
th
e
test
in
g
s
et
U
R
L
s
to
th
e
f
in
ite
s
tate
m
ac
h
in
e
(
PHI
SH_
FS
A)
cr
ea
ted
an
d
th
e
th
r
esh
o
ld
v
alu
es
ar
e
f
i
n
alize
d
.
T
h
e
d
atasets
T
E
ST#
1
an
d
T
E
ST#
2
r
etu
r
n
ed
a
th
r
esh
o
ld
v
alu
e
o
f
2
,
m
ea
n
in
g
an
y
UR
L
ev
alu
atio
n
r
esu
lts
i
n
a
MS
g
r
ea
ter
th
an
2
is
s
u
s
p
ec
ted
as
m
alicio
u
s
UR
L
s
.
Fig
u
r
e
4
(
s
ee
i
n
A
p
p
e
n
d
ix
)
r
e
p
r
esen
ts
th
e
ca
lc
u
lated
MS
v
alu
e
f
o
r
th
e
d
if
f
e
r
en
t
UR
L
d
atasets
u
n
d
er
co
n
s
id
er
atio
n
,
with
u
r
l
r
ef
er
e
n
ce
n
u
m
b
er
in
th
e
X
a
x
is
an
d
MS
o
n
th
e
Y
ax
is
.
T
h
e
m
a
licio
u
s
s
co
r
e
v
alu
e
d
is
tr
ib
u
tio
n
f
o
r
th
e
test
in
g
d
a
tasets
.
T
h
e
r
esu
lt
c
o
n
f
ir
m
s
a
th
r
esh
o
ld
v
alu
e
o
f
2
is
en
o
u
g
h
f
o
r
a
UR
L
to
b
e
ca
teg
o
r
ized
as
a
p
h
is
h
in
g
UR
L
.
4.
CO
NCLU
SI
O
N
As
th
is
m
o
d
el
p
er
f
o
r
m
s
th
e
d
etec
tio
n
b
ased
o
n
th
e
s
elf
-
g
en
er
ated
f
ea
tu
r
e
s
et,
th
is
m
o
d
el
s
h
o
ws
d
if
f
er
en
t
p
er
f
o
r
m
a
n
ce
in
d
icato
r
s
co
m
p
ar
ed
to
th
e
p
ar
allel
r
esear
ch
f
in
d
in
g
s
.
Ph
is
h
in
g
tech
n
iq
u
es
ar
e
ev
o
lv
in
g
d
aily
an
d
attac
k
er
s
ar
e
f
in
d
in
g
n
ew
way
s
to
o
b
f
u
s
ca
te
th
e
ir
r
eg
u
lar
ities
in
th
e
UR
L
.
T
h
i
s
m
o
d
el
p
u
t
f
o
r
th
a
h
ig
h
ly
ad
a
p
tab
le
m
o
d
el
f
o
r
th
ese
ch
an
g
es
wh
ich
ca
n
ac
co
m
m
o
d
ate
th
e
n
ew
f
ea
t
u
r
es
co
m
i
n
g
u
p
a
n
d
p
r
o
v
id
e
p
r
o
m
is
in
g
r
esu
lts
.
T
h
e
ch
a
n
g
e
ad
ap
tab
ilit
y
is
g
u
ar
an
teed
b
y
co
n
tin
u
o
u
s
ch
ec
k
in
g
a
n
d
r
e
v
i
s
in
g
o
f
th
e
f
ea
tu
r
e
weig
h
ts
an
d
th
r
esh
o
l
d
v
alu
es.
T
h
e
n
aiv
e
id
ea
o
f
r
ea
l
tim
e
p
h
is
h
in
g
UR
L
d
etec
tio
n
u
s
in
g
f
in
ite
s
tate
au
to
m
ata
is
im
p
lem
en
ted
s
u
cc
ess
f
u
lly
in
th
is
m
o
d
el.
T
h
e
r
ea
l
tim
e
an
aly
s
is
o
f
th
e
UR
L
g
iv
es
th
e
ad
v
an
tag
e
to
th
e
m
o
d
el
as
th
e
m
o
d
el
will
n
o
t
b
e
b
iased
to
war
d
s
a
s
in
g
le
d
ata
s
et
u
s
ed
in
th
e
tr
a
in
in
g
p
h
ase.
T
h
e
m
o
d
el
ex
p
e
r
im
en
tatio
n
s
h
o
ws
p
r
o
m
is
in
g
r
ates
o
f
f
alse
p
o
s
itiv
es
wh
ile
test
ed
with
th
e
n
ai
v
e
d
ata
s
e
t.
T
h
e
f
alse
n
eg
ativ
es
s
till
n
ee
d
to
b
e
im
p
r
o
v
e
d
an
d
r
ea
s
o
n
f
o
u
n
d
to
b
e
th
e
v
er
s
atility
o
f
th
e
p
h
is
h
in
g
UR
L
s
we
co
llect
an
d
ev
alu
ate.
Ho
wev
er
,
th
e
PHI
SH_
FS
A
i
s
m
o
d
elled
s
o
t
h
at
th
ese
ad
ju
s
tm
en
ts
ca
n
b
e
e
asil
y
ac
co
m
m
o
d
ated
,
an
d
th
e
m
o
d
el
ca
n
b
e
tu
n
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
h
is
h
in
g
UR
L p
r
ed
ictio
n
–
tw
o
-
p
h
a
s
e
mo
d
el
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
a
n
d
fin
ite
…
(
N
is
h
a
T N
)
363
T
h
e
F
I
R
p
h
ase
is
also
d
ev
elo
p
ed
,
co
n
s
id
er
i
n
g
th
at
th
ese
n
ew
f
ea
tu
r
es
s
h
o
u
ld
b
e
ac
co
m
m
o
d
ated
with
o
u
t
m
an
y
ch
an
g
es in
th
e
m
o
d
el
.
T
h
e
m
o
d
el
ca
n
b
e
im
p
lem
e
n
t
ed
to
f
in
d
th
e
MS
o
f
th
e
UR
L
,
an
d
th
e
ad
m
in
is
tr
ato
r
ca
n
d
ec
id
e
th
e
th
r
esh
o
ld
an
d
eith
er
ac
ce
p
t
o
r
r
ejec
t
an
y
n
ew
UR
L
en
ter
in
g
th
e
o
r
g
an
izatio
n
al
n
etwo
r
k
te
r
r
ito
r
y
.
T
h
e
m
o
d
el
n
ee
d
s
to
b
e
c
o
n
s
tan
tly
tu
n
ed
with
n
ew
d
atasets
to
i
n
clu
d
e
n
ew
f
ea
tu
r
es
t
h
at
th
e
attac
k
er
s
ca
n
tr
y
,
an
d
it
also
n
ee
d
s
to
r
ev
a
m
p
th
e
PHI
SH_
F
SA a
t r
eg
u
lar
in
ter
v
als s
o
th
at
th
e
er
r
o
r
r
ates a
r
e
r
ed
u
ce
d
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Nis
h
a
T
N
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Dh
an
y
a
Pra
m
o
d
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
is
n
o
t
ap
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
B
a
k
e
r
h
o
s
t
e
t
l
e
r
,
“
B
a
k
e
r
H
o
st
e
t
l
e
r
’
s
2
0
2
5
d
a
t
a
s
e
c
u
r
i
t
y
i
n
c
i
d
e
n
t
r
e
s
p
o
n
s
e
r
e
p
o
r
t
f
i
n
d
s
l
e
ss ma
l
w
a
r
e
u
s
e
d
i
n
2
0
2
4
”
,
2
0
2
5
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
b
a
k
e
r
l
a
w
.
c
o
m
/
i
n
si
g
h
t
s/
b
a
k
e
r
h
o
st
e
t
l
e
r
-
l
a
u
n
c
h
e
s
-
2
0
2
4
-
d
a
t
a
-
s
e
c
u
r
i
t
y
-
i
n
c
i
d
e
n
t
-
r
e
s
p
o
n
s
e
-
r
e
p
o
r
t
-
p
e
r
si
s
t
e
n
t
-
t
h
r
e
a
t
s
-
n
e
w
-
c
h
a
l
l
e
n
g
e
s
/
.
A
c
c
e
sse
d
:
N
o
v
.
1
0
,
2
0
2
4
.
[
2
]
“
En
t
e
r
p
r
i
se
se
c
u
r
i
t
y
s
o
l
u
t
i
o
n
s
,
”
I
b
m.
c
o
m.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
i
b
m
.
c
o
m/
s
e
c
u
r
i
t
y
.
A
c
c
e
ss
e
d
:
N
o
v
,
1
3
,
2
0
2
4
.
[
3
]
F
.
L
.
G
r
e
i
t
z
e
r
,
J.
R
.
S
t
r
o
z
e
r
,
S
.
C
o
h
e
n
,
A
.
P
.
M
o
o
r
e
,
D
.
M
u
n
d
i
e
,
a
n
d
J.
C
o
w
l
e
y
,
“
A
n
a
l
y
s
i
s o
f
u
n
i
n
t
e
n
t
i
o
n
a
l
i
n
s
i
d
e
r
t
h
r
e
a
t
s
d
e
r
i
v
i
n
g
f
r
o
m so
c
i
a
l
e
n
g
i
n
e
e
r
i
n
g
e
x
p
l
o
i
t
s,
”
i
n
2
0
1
4
I
EE
E
S
e
c
u
r
i
t
y
a
n
d
Pr
i
v
a
c
y
Wo
r
k
sh
o
p
s
,
2
0
1
4
.
[
4
]
“
A
P
W
G
,
”
A
p
w
g
.
o
r
g
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
a
p
w
g
.
o
r
g
/
t
r
e
n
d
sr
e
p
o
r
t
s.
A
c
c
e
ss
e
d
:
O
c
t
.
1
3
,
2
0
2
4
.
[
5
]
O
.
C
h
r
i
s
t
o
u
,
N
.
P
i
t
r
o
p
a
k
i
s,
P
.
P
a
p
a
d
o
p
o
u
l
o
s
,
S
.
M
c
K
e
o
w
n
,
a
n
d
W
.
B
u
c
h
a
n
a
n
,
“
P
h
i
s
h
i
n
g
U
R
L
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
t
o
p
-
l
e
v
e
l
d
o
ma
i
n
a
n
a
l
y
si
s
:
A
d
e
s
c
r
i
p
t
i
v
e
a
p
p
r
o
a
c
h
,
”
i
n
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
r
mat
i
o
n
S
y
s
t
e
ms
S
e
c
u
r
i
t
y
a
n
d
P
r
i
v
a
c
y
,
2
0
2
0
,
d
o
i
:
1
0
.
5
2
2
0
/
0
0
0
8
9
0
2
2
0
2
8
9
0
2
9
8
.
[
6
]
A
.
Y
a
si
n
a
n
d
A
.
A
b
u
h
a
s
a
n
,
“
A
n
i
n
t
e
l
l
i
g
e
n
t
c
l
a
ssi
f
i
c
a
t
i
o
n
m
o
d
e
l
f
o
r
p
h
i
sh
i
n
g
e
ma
i
l
d
e
t
e
c
t
i
o
n
,
”
I
n
t
.
J
.
N
e
t
w
.
S
e
c
u
r.
A
p
p
l
.
,
v
o
l
.
8
,
n
o
.
4
,
p
p
.
5
5
–
7
2
,
2
0
1
6
,
d
o
i
:
1
0
.
5
1
2
1
/
i
j
n
s
a
.
2
0
1
6
.
8
4
0
5
.
[
7
]
S
.
A
t
a
w
n
e
h
a
n
d
H
.
A
l
j
e
h
a
n
i
,
“
P
h
i
sh
i
n
g
e
ma
i
l
d
e
t
e
c
t
i
o
n
m
o
d
e
l
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
El
e
c
t
r
o
n
i
c
s
(
Ba
s
e
l
)
,
v
o
l
.
1
2
,
n
o
.
2
0
,
p
.
4
2
6
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
2
0
4
2
6
1
.
[
8
]
Y
.
F
a
n
g
,
C
.
Z
h
a
n
g
,
C
.
H
u
a
n
g
,
L.
L
i
u
,
a
n
d
Y
.
Y
a
n
g
,
“
P
h
i
s
h
i
n
g
e
ma
i
l
d
e
t
e
c
t
i
o
n
u
si
n
g
i
mp
r
o
v
e
d
R
C
N
N
mo
d
e
l
w
i
t
h
m
u
l
t
i
l
e
v
e
l
v
e
c
t
o
r
s a
n
d
a
t
t
e
n
t
i
o
n
me
c
h
a
n
i
sm
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
5
6
3
2
9
–
5
6
3
4
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
1
3
7
0
5
.
[
9
]
N
.
B
.
H
a
r
i
k
r
i
s
h
n
a
n
,
R
.
V
i
n
a
y
a
k
u
m
a
r
,
a
n
d
K
.
P
.
S
o
m
a
n
,
“
A
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
w
a
r
d
s
p
h
i
s
h
i
n
g
e
mai
l
d
e
t
e
c
t
i
o
n
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
A
n
t
i
-
Ph
i
sh
i
n
g
Pi
l
o
t
a
t
A
C
M
I
n
t
e
r
n
a
t
i
o
n
a
l
Wo
r
k
s
h
o
p
o
n
S
e
c
u
ri
t
y
a
n
d
Pr
i
v
a
c
y
A
n
a
l
y
t
i
c
s
(
I
WS
P
A
A
P)
,
v
o
l
.
2
0
1
3
,
p
p
.
4
5
5
–
4
6
8
,
2
0
1
8
.
[
1
0
]
J.
Le
e
,
F
.
T
a
n
g
,
P
.
Y
e
,
F
.
A
b
b
a
si
,
P
.
H
a
y
,
a
n
d
D
.
M
.
D
i
v
a
k
a
r
a
n
,
“
D
-
F
e
n
c
e
:
A
F
l
e
x
i
b
l
e
,
e
f
f
i
c
i
e
n
t
,
a
n
d
c
o
m
p
r
e
h
e
n
s
i
v
e
p
h
i
s
h
i
n
g
e
mai
l
d
e
t
e
c
t
i
o
n
s
y
st
e
m
,
”
i
n
2
0
2
1
I
EE
E
E
u
ro
p
e
a
n
S
y
m
p
o
s
i
u
m
o
n
S
e
c
u
r
i
t
y
a
n
d
Pri
v
a
c
y
(
Eu
r
o
S
&P)
,
I
EEE
,
2
0
2
1
,
p
p
.
5
7
8
–
5
9
7
.
[
1
1
]
D
.
L.
C
o
o
k
,
V
.
K
.
G
u
r
b
a
n
i
,
a
n
d
M
.
D
a
n
i
l
u
k
,
“
P
h
i
s
h
w
i
s
h
:
A
st
a
t
e
l
e
s
s
p
h
i
s
h
i
n
g
f
i
l
t
e
r
u
si
n
g
m
i
n
i
ma
l
r
u
l
e
s,”
i
n
Fi
n
a
n
c
i
a
l
C
ry
p
t
o
g
ra
p
h
y
a
n
d
D
a
t
a
S
e
c
u
ri
t
y
,
B
e
r
l
i
n
,
H
e
i
d
e
l
b
e
r
g
:
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
0
8
,
p
p
.
1
8
2
–
1
8
6
.
[
1
2
]
P
.
A
g
r
a
w
a
l
a
n
d
D
.
M
a
n
g
a
l
,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
p
h
i
s
h
i
n
g
U
R
Ls
D
e
t
e
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
a
n
d
R
e
se
a
rc
h
(
I
J
S
R)
,
v
o
l
.
5
,
n
o
.
5
,
p
p
.
1
1
1
7
–
1
1
2
2
,
2
0
1
5
.
[
1
3
]
M
.
S
.
K
u
mar
a
n
d
B
.
I
n
d
r
a
n
i
,
“
F
r
e
q
u
e
n
t
r
u
l
e
r
e
d
u
c
t
i
o
n
f
o
r
p
h
i
s
h
i
n
g
U
R
L
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
f
u
z
z
y
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
,
”
I
r
a
n
J
.
C
o
m
p
u
t
.
S
c
i
.
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
8
5
–
9
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
2
0
4
4
-
0
2
0
-
0
0
0
6
7
-
x
.
[
1
4
]
A
.
K
a
r
i
m,
M
.
S
h
a
h
r
o
z
,
K
.
M
u
st
o
f
a
,
S
.
B
.
B
e
l
h
a
o
u
a
r
i
,
a
n
d
S
.
R
.
K
.
Jo
g
a
,
“
P
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
s
y
st
e
m
t
h
r
o
u
g
h
h
y
b
r
i
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
o
n
U
R
L,
”
I
EEE
Ac
c
e
s
s,
v
o
l
.
1
1
,
p
p
.
3
6
8
0
5
–
3
6
8
2
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
5
2
3
6
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
40
,
No
.
1
,
Octo
b
er
20
25
:
356
-
3
6
5
364
[
1
5
]
S
.
Ja
l
i
l
,
M
.
U
sma
n
,
a
n
d
A
.
F
o
n
g
,
“
H
i
g
h
l
y
a
c
c
u
r
a
t
e
p
h
i
s
h
i
n
g
U
R
L
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
J
.
Am
b
i
e
n
t
I
n
t
e
l
l
.
H
u
m
a
n
i
z
.
C
o
m
p
u
t
.
,
v
o
l
.
1
4
,
p
p
.
9
2
3
3
-
9
2
1
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
0
2
2
-
0
4
4
2
6
-
3
.
[
1
6
]
L.
X
u
,
Z.
Zh
a
n
,
S
.
X
u
,
a
n
d
K
.
Y
e
,
“
C
r
o
ss
-
l
a
y
e
r
d
e
t
e
c
t
i
o
n
o
f
mal
i
c
i
o
u
s
w
e
b
si
t
e
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
t
h
i
r
d
AC
M
c
o
n
f
e
re
n
c
e
o
n
D
a
t
a
a
n
d
a
p
p
l
i
c
a
t
i
o
n
se
c
u
ri
t
y
a
n
d
p
r
i
v
a
c
y
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
4
5
/
2
4
3
5
3
4
9
.
2
4
3
5
3
6
6
.
[
1
7
]
R
.
M
.
M
o
h
a
mm
a
d
,
F
.
T
h
a
b
t
a
h
,
a
n
d
L.
M
c
C
l
u
s
k
e
y
,
“
I
n
t
e
l
l
i
g
e
n
t
r
u
l
e
‐
b
a
s
e
d
p
h
i
s
h
i
n
g
w
e
b
s
i
t
e
s
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
ET
I
n
f
.
S
e
c
u
r.
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
1
5
3
–
1
6
0
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
i
f
s.
2
0
1
3
.
0
2
0
2
.
[
1
8
]
P
.
P
r
a
k
a
s
h
,
M
.
K
u
mar,
R
.
R
.
K
o
m
p
e
l
l
a
,
a
n
d
M
.
G
u
p
t
a
,
“
P
h
i
s
h
N
e
t
:
P
r
e
d
i
c
t
i
v
e
b
l
a
c
k
l
i
st
i
n
g
t
o
d
e
t
e
c
t
p
h
i
s
h
i
n
g
a
t
t
a
c
k
s,
”
i
n
2
0
1
0
Pro
c
e
e
d
i
n
g
s IEE
E
I
N
FO
C
O
M
,
2
0
1
0
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
F
C
O
M
.
2
0
1
0
.
5
4
6
2
2
1
6
.
[
1
9
]
M
.
A
b
u
r
r
o
u
s
,
M
.
A
.
H
o
ssai
n
,
K
.
D
a
h
a
l
,
a
n
d
F
.
T
h
a
b
t
a
h
,
“
I
n
t
e
l
l
i
g
e
n
t
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
s
y
st
e
m
f
o
r
e
-
b
a
n
k
i
n
g
u
si
n
g
f
u
z
z
y
d
a
t
a
mi
n
i
n
g
,
”
E
x
p
e
rt
S
y
st
.
A
p
p
l
.
,
v
o
l
.
3
7
,
n
o
.
1
2
,
p
p
.
7
9
1
3
–
7
9
2
1
,
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
0
.
0
4
.
0
4
4
.
[
2
0
]
J.
H
o
n
g
,
T.
K
i
m
,
J.
Li
u
,
N
.
P
a
r
k
,
a
n
d
S
.
W
.
K
i
m,
“
P
h
i
sh
i
n
g
u
r
l
d
e
t
e
c
t
i
o
n
w
i
t
h
l
e
x
i
c
a
l
f
e
a
t
u
r
e
s
a
n
d
b
l
a
c
k
l
i
st
e
d
d
o
mai
n
s
”
.
Ad
a
p
t
i
v
e
a
u
t
o
n
o
m
o
u
s s
e
c
u
re
c
y
b
e
r sy
s
t
e
m
s
,
”
p
p
.
2
5
3
–
2
6
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
3
3
4
3
2
-
1
_
1
2
.
[
2
1
]
G
.
X
i
a
n
g
,
J.
H
o
n
g
,
C
.
P
.
R
o
se
,
a
n
d
L
.
C
r
a
n
o
r
,
“
C
a
n
t
i
n
a
+
a
f
e
a
t
u
r
e
-
r
i
c
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
d
e
t
e
c
t
i
n
g
p
h
i
s
h
i
n
g
w
e
b
si
t
e
s
,
”
A
C
M
T
r
a
n
sa
c
t
i
o
n
s
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
S
y
st
e
m
S
e
c
u
ri
t
y
(
T
I
S
S
E
C
)
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
1
–
2
8
,
2
0
1
1
,
d
o
i
:
1
0
.
1
1
4
5
/
2
0
1
9
5
9
9
.
2
0
1
9
6
0
6
.
[
2
2
]
A
.
K
.
J
a
i
n
,
S
.
P
a
r
a
s
h
a
r
,
P
.
K
a
t
a
r
e
,
a
n
d
I
.
S
h
a
r
ma,
“
P
h
i
s
h
S
K
a
P
e
:
A
c
o
n
t
e
n
t
-
b
a
se
d
a
p
p
r
o
a
c
h
t
o
e
sca
p
e
p
h
i
s
h
i
n
g
a
t
t
a
c
k
s,
”
P
ro
c
e
d
i
a
C
o
m
p
u
t
.
S
c
i
.
,
v
o
l
.
1
7
1
,
p
p
.
1
1
0
2
–
1
1
0
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
2
0
.
0
4
.
1
1
8
.
[
2
3
]
Y
.
Z
h
a
n
g
,
J
.
I
.
H
o
n
g
,
a
n
d
L
.
F
.
C
ra
n
o
r,
“
C
a
n
t
i
n
a
:
a
c
o
n
t
e
n
t
-
b
a
se
d
a
p
p
ro
a
c
h
t
o
d
e
t
e
c
t
i
n
g
p
h
i
s
h
i
n
g
w
e
b
s
i
t
e
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
6
t
h
i
n
t
e
rn
a
t
i
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
Wo
r
l
d
W
i
d
e
W
eb
,
2
0
0
7
,
p
p
.
6
3
9
–
6
4
8
,
d
o
i
:
1
0
.
1
1
4
5
/
1
2
4
2
5
7
2
.
1
2
4
2
6
5
9
.
[
2
4
]
B
.
W
a
r
d
ma
n
,
T.
S
t
a
l
l
i
n
g
s,
G
.
W
a
r
n
e
r
,
a
n
d
A
.
S
k
j
e
l
l
u
m
,
“
H
i
g
h
-
p
e
r
f
o
r
ma
n
c
e
c
o
n
t
e
n
t
-
b
a
s
e
d
p
h
i
sh
i
n
g
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
1
e
C
ri
m
e
R
e
se
a
rc
h
e
r
s
S
u
m
m
i
t
,
2
0
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
e
C
r
i
m
e
.
2
0
1
1
.
6
1
5
1
9
7
7
.
[
2
5
]
Y
.
C
a
o
,
W
.
H
a
n
,
a
n
d
Y
.
Le
,
“
A
n
t
i
-
p
h
i
sh
i
n
g
b
a
se
d
o
n
a
u
t
o
m
a
t
e
d
i
n
d
i
v
i
d
u
a
l
w
h
i
t
e
-
l
i
s
t
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
4
t
h
AC
M
w
o
r
k
sh
o
p
o
n
D
i
g
i
t
a
l
i
d
e
n
t
i
t
y
m
a
n
a
g
e
m
e
n
t
,
2
0
0
8
,
p
p
.
5
1
-
6
0
,
d
o
i
:
1
0
.
1
1
4
5
/
1
4
5
6
4
2
4
.
1
4
5
6
4
3
4
.
[
2
6
]
G
.
X
i
a
n
g
a
n
d
J
.
I
.
H
o
n
g
,
“
A
h
y
b
r
i
d
p
h
i
s
h
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
b
y
i
d
e
n
t
i
t
y
d
i
sco
v
e
r
y
a
n
d
k
e
y
w
o
r
d
s
r
e
t
r
i
e
v
a
l
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
W
o
rl
d
Wi
d
e
W
e
b
,
2
0
0
9
,
d
o
i
:
1
0
.
1
1
4
5
/
1
5
2
6
7
0
9
.
1
5
2
6
7
8
.
[
2
7
]
S
.
A
f
r
o
z
a
n
d
R
.
G
r
e
e
n
s
t
a
d
t
,
“
P
h
i
s
h
Zo
o
:
D
e
t
e
c
t
i
n
g
p
h
i
s
h
i
n
g
w
e
b
s
i
t
e
s
b
y
l
o
o
k
i
n
g
a
t
t
h
e
m,”
i
n
2
0
1
1
I
E
EE
Fi
f
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
e
m
a
n
t
i
c
C
o
m
p
u
t
i
n
g
,
2
0
1
1
,
p
p
.
3
6
8
-
3
7
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
.
2
0
1
1
.
5
2
.
[
2
8
]
M
.
D
u
n
l
o
p
,
S
.
G
r
o
a
t
,
a
n
d
D
.
S
h
e
l
l
y
,
“
G
o
l
d
P
h
i
s
h
:
U
s
i
n
g
i
ma
g
e
s
f
o
r
c
o
n
t
e
n
t
-
b
a
s
e
d
p
h
i
s
h
i
n
g
a
n
a
l
y
si
s
,
”
i
n
2
0
1
0
F
i
f
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
r
n
e
t
M
o
n
i
t
o
r
i
n
g
a
n
d
Pr
o
t
e
c
t
i
o
n
,
2
0
1
0
.
[
2
9
]
A
.
O
z
c
a
n
,
C
.
C
a
t
a
l
,
E
.
D
o
n
me
z
,
a
n
d
B
.
S
e
n
t
u
r
k
,
“
A
h
y
b
r
i
d
D
N
N
-
LST
M
mo
d
e
l
f
o
r
d
e
t
e
c
t
i
n
g
p
h
i
sh
i
n
g
U
R
L
s,”
N
e
u
r
a
l
C
o
m
p
u
t
.
Ap
p
l
.
,
v
o
l
.
3
5
,
n
o
.
7
,
p
p
.
4
9
5
7
–
4
9
7
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
2
1
-
0
2
1
-
0
6
4
0
1
-
z.
[
3
0
]
H
.
L
e
,
Q
.
P
h
a
m,
D
.
S
a
h
o
o
,
a
n
d
S
.
C
.
H
.
H
o
i
,
“
U
R
LN
e
t
:
L
e
a
r
n
i
n
g
a
U
R
L
r
e
p
r
e
s
e
n
t
a
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
ma
l
i
c
i
o
u
s
U
R
L
D
e
t
e
c
t
i
o
n
,
”
a
r
X
i
v
[
c
s.
C
R
]
,
2
0
1
8
.
[
3
1
]
F
.
T
a
j
a
d
d
o
d
i
a
n
f
a
r
,
J.
W
.
S
t
o
k
e
s,
a
n
d
A
.
G
u
r
u
r
a
j
a
n
,
“
Te
x
c
e
p
t
i
o
n
:
A
c
h
a
r
a
c
t
e
r
/
w
o
r
d
-
l
e
v
e
l
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
p
h
i
s
h
i
n
g
U
R
L
d
e
t
e
c
t
i
o
n
,
”
i
n
I
C
AS
S
P
2
0
2
0
-
2
0
2
0
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ac
o
u
s
t
i
c
s,
S
p
e
e
c
h
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
(
I
C
A
S
S
P)
,
2
0
2
0
,
p
p
.
2
8
5
7
-
2
8
6
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
S
S
P
4
0
7
7
6
.
2
0
2
0
.
9
0
5
3
6
7
0
.
[
3
2
]
H
.
S
h
a
h
r
i
a
r
a
n
d
M
.
Z
u
l
k
e
r
n
i
n
e
,
“
P
h
i
s
h
Te
s
t
e
r
:
A
u
t
o
ma
t
i
c
t
e
s
t
i
n
g
o
f
p
h
i
s
h
i
n
g
a
t
t
a
c
k
s
,
”
i
n
2
0
1
0
F
o
u
r
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
e
c
u
r
e
S
o
f
t
w
a
r
e
I
n
t
e
g
r
a
t
i
o
n
a
n
d
R
e
l
i
a
b
i
l
i
t
y
I
m
p
r
o
v
e
m
e
n
t
,
2
0
1
0
,
p
p
.
1
9
8
-
2
0
7
,
d
o
i
:
1
0
.
1
1
0
9
/
S
S
I
R
I
.
2
0
1
0
.
1
7
.
[
3
3
]
K
a
g
g
l
e
.
c
o
m.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
.
A
c
c
e
s
se
d
:
S
e
p
.
1
3
,
2
0
2
4
.
[
3
4
]
P
h
i
s
h
t
a
n
k
.
c
o
m.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
p
h
i
s
h
t
a
n
k
.
c
o
m
/
.
A
c
c
e
sse
d
:
O
c
t
.
1
3
,
2
0
2
4
.
[
3
5
]
“
C
o
mm
o
n
c
r
a
w
l
-
o
v
e
r
v
i
e
w
,
”
C
o
m
mo
n
c
r
a
w
l
.
o
r
g
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
c
o
mm
o
n
c
r
a
w
l
.
o
r
g
/
t
h
e
-
d
a
t
a
/
.
A
c
c
e
sse
d
:
M
a
y
.
1
3
,
2
0
2
4
.
AP
P
E
NDI
X
Fig
u
r
e
4
.
Ma
licio
u
s
s
co
r
e
d
is
tr
ib
u
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
h
is
h
in
g
UR
L p
r
ed
ictio
n
–
tw
o
-
p
h
a
s
e
mo
d
el
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
a
n
d
fin
ite
…
(
N
is
h
a
T N
)
365
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Nisha
T
N
sh
e
w
o
rk
s
a
s
As
sista
n
t
P
r
o
fe
ss
o
r
a
t
S
y
m
b
i
o
sis
Ce
n
tr
e
fo
r
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
(S
CIT)
,
a
c
o
n
stit
u
e
n
t
o
f
t
h
e
S
y
m
b
i
o
sis
In
ter
n
a
ti
o
n
a
l
Un
iv
e
rsity
(
S
IU),
P
u
n
e
.
S
h
e
c
o
m
p
lete
d
a
P
h
.
D.
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
S
y
m
b
io
sis
In
tern
a
ti
o
n
a
l
U
n
iv
e
rsit
y
i
n
n
e
two
r
k
in
tru
si
o
n
d
e
tec
ti
o
n
.
S
h
e
h
a
s
a
t
e
a
c
h
in
g
e
x
p
e
rie
n
c
e
o
f
fift
e
e
n
y
e
a
rs
in
th
e
a
re
a
s
su
c
h
a
s
in
fo
rm
a
ti
o
n
se
c
u
rit
y
,
e
th
ica
l
h
a
c
k
in
g
,
p
ro
g
ra
m
m
in
g
c
o
n
c
e
p
ts,
o
p
ti
m
iza
ti
o
n
a
n
d
c
y
b
e
r
in
telli
g
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
ish
a
@s
c
it
.
e
d
u
.
Dha
n
y
a
Pra
m
o
d
s
h
e
is
a
P
ro
fe
ss
o
r
a
n
d
Dire
c
to
r
a
t
t
h
e
S
y
m
b
io
sis
Ce
n
tre
fo
r
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
(S
CI
T)
,
a
c
o
n
sti
tu
e
n
t
o
f
th
e
S
y
m
b
i
o
sis
In
tern
a
ti
o
n
a
l
U
n
iv
e
rsit
y
(S
IU),
P
u
n
e
.
S
h
e
h
a
s
a
Ph
.
D
.
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
S
y
m
b
io
s
is
In
tern
a
ti
o
n
a
l
U
n
iv
e
rsit
y
,
In
d
ia
a
n
d
h
e
r
tea
c
h
in
g
a
n
d
r
e
se
a
rc
h
in
tere
sts
a
re
in
fo
rm
a
ti
o
n
se
c
u
rit
y
,
n
e
two
r
k
s
a
n
d
a
p
p
li
c
a
ti
o
n
se
c
u
rit
y
a
n
d
p
re
d
ictiv
e
a
laly
t
ics
.
Sh
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
h
a
n
y
a
sp
ra
m
o
d
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.