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.
3
7
,
No
.
2
,
Feb
r
u
ar
y
20
2
5
,
p
p
.
985
~
994
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
2
.
pp
985
-
9
9
4
985
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Enha
ncing
m
a
lw
a
re
detec
tion
ca
p
a
bilities
using
de
e
p learning
with
a
dv
a
nced
hy
perpa
ra
meter
t
un
ing
Wa
lid
E
l
M
o
uh
t
a
di
,
Ya
s
s
ine
M
a
leh
,
So
ufy
a
ne
M
o
un
ir
La
S
TI
La
b
o
r
a
t
o
r
y
,
N
a
t
i
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
K
h
o
u
r
i
b
g
a
,
S
u
l
t
a
n
M
o
u
l
a
y
S
l
i
ma
n
e
U
n
i
v
e
r
si
t
y
,
B
e
n
i
M
e
l
l
a
l
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
23
,
2
0
2
4
R
ev
is
ed
Sep
16
,
2
0
2
4
Acc
ep
ted
Sep
29
,
2
0
2
4
As
th
e
th
re
a
t
lan
d
sc
a
p
e
e
v
o
lv
e
s
with
so
p
h
isti
c
a
ted
m
a
lwa
re
a
n
d
a
d
v
a
n
c
e
d
p
e
rsiste
n
t
t
h
re
a
ts
(APT
s),
t
h
e
n
e
e
d
f
o
r
e
ffe
c
ti
v
e
d
e
tec
ti
o
n
so
lu
ti
o
n
s
in
c
re
a
se
s.
Trad
it
io
n
a
l
m
e
th
o
d
s,
su
c
h
a
s
sig
n
a
tu
re
-
b
a
se
d
a
n
d
h
e
u
risti
c
a
n
a
ly
sis,
str
u
g
g
le
t
o
k
e
e
p
u
p
w
it
h
ra
p
id
l
y
c
h
a
n
g
i
n
g
m
a
li
c
io
u
s
a
c
ti
v
it
ies
.
Wh
il
e
m
a
c
h
in
e
lea
rn
in
g
o
ffe
rs
a
p
ro
m
isin
g
a
p
p
r
o
a
c
h
,
it
o
f
ten
fa
ll
s
sh
o
rt
d
u
e
to
t
h
e
m
a
n
u
a
l
e
x
trac
ti
o
n
a
n
d
se
lec
ti
o
n
o
f
fe
a
t
u
re
s,
lea
d
i
n
g
to
ti
m
e
-
c
o
n
su
m
in
g
a
n
d
e
rro
r
-
p
r
o
n
e
p
ro
c
e
ss
e
s.
Th
is
re
se
a
rc
h
in
tro
d
u
c
e
s
a
n
o
v
e
l
m
a
lwa
re
d
e
tec
ti
o
n
so
l
u
ti
o
n
lev
e
ra
g
in
g
d
e
e
p
lea
rn
in
g
a
n
d
f
o
c
u
sin
g
o
n
p
o
rtab
le
e
x
e
c
u
tab
le
(
PE
)
f
il
e
a
n
a
l
y
sis
to
a
d
d
re
ss
th
e
se
we
a
k
n
e
ss
e
s.
By
c
u
sto
m
izin
g
th
e
h
y
p
e
rp
a
ra
m
e
ters
o
f
a
rti
ficia
l
n
e
u
ra
l
n
e
tw
o
rk
s
(AN
N),
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
s
(CNN
),
a
n
d
re
c
u
rre
n
t
n
e
u
ra
l
n
e
two
r
k
s
(RNN
),
th
e
p
ro
p
o
se
d
a
p
p
r
o
a
c
h
e
n
h
a
n
c
e
s
d
e
tec
ti
o
n
c
a
p
a
b
il
it
ies
.
Th
e
p
rima
r
y
o
b
jec
ti
v
e
is
t
o
o
v
e
rc
o
m
e
th
e
l
imitatio
n
s
o
f
tra
d
it
i
o
n
a
l
a
n
d
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
s
b
y
tail
o
rin
g
t
h
e
se
d
e
e
p
lea
rn
i
n
g
a
lg
o
rit
h
m
s.
Th
e
m
e
th
o
d
o
l
o
g
y
in
c
lu
d
e
s
a
c
o
m
p
a
ra
ti
v
e
stu
d
y
to
d
e
m
o
n
stra
te
th
e
a
d
v
a
n
tag
e
s
o
f
th
e
c
u
sto
m
ize
d
a
p
p
ro
a
c
h
o
v
e
r
c
o
n
v
e
n
ti
o
n
a
l
m
e
th
o
d
s.
Ke
y
fi
n
d
i
n
g
s
re
v
e
a
l
th
e
p
ro
p
o
se
d
so
l
u
ti
o
n
’
s
su
p
e
ri
o
r
p
e
rfo
rm
a
n
c
e
,
a
c
c
u
ra
c
y
,
a
n
d
a
d
a
p
t
a
b
il
it
y
i
n
c
o
m
b
a
ti
n
g
e
v
o
lv
i
n
g
c
y
b
e
r
t
h
r
e
a
ts.
Th
is
re
se
a
rc
h
c
o
n
tri
b
u
tes
to
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
ro
b
u
st a
n
d
a
d
a
p
ti
v
e
m
a
lwa
re
d
e
tec
ti
o
n
so
l
u
ti
o
n
s.
K
ey
w
o
r
d
s
:
ANN
C
NN
Data
b
alan
cin
g
D
ee
p
lear
n
in
g
Ma
lwar
e
d
etec
tio
n
Op
tim
izatio
n
R
NN
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
:
W
alid
E
l M
o
u
h
tad
i
L
aST
I
L
ab
o
r
ato
r
y
,
Natio
n
al
Sch
o
o
l o
f
Ap
p
lied
Scien
ce
s
Kh
o
u
r
ib
g
a
,
Su
ltan
Mo
u
la
y
Sli
m
an
e
Un
iv
er
s
ity
C
asab
lan
ca
,
Mo
r
o
cc
o
E
m
ail:
walid
.
elm
o
u
h
tad
i@
u
s
m
s
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
co
n
s
tan
tly
ch
an
g
in
g
th
r
ea
t
lan
d
s
ca
p
e
[
1
]
,
ch
ar
ac
ter
i
ze
d
b
y
ad
v
an
ce
d
m
alwa
r
e
[
2
]
,
r
eq
u
ir
es
in
n
o
v
ativ
e
d
etec
tio
n
s
o
lu
tio
n
s
.
T
r
ad
itio
n
al
m
eth
o
d
s
[
3
]
,
s
u
ch
as si
g
n
atu
r
e
-
b
ased
[
4
]
an
d
h
e
u
r
is
tic
an
aly
s
is
[
5
]
,
ar
e
in
cr
ea
s
in
g
ly
i
n
ad
eq
u
ate.
Sig
n
atu
r
e
-
b
ased
tech
n
iq
u
es
[
6
]
,
alth
o
u
g
h
in
itially
ef
f
ec
tiv
e,
f
a
il
to
ad
d
r
ess
n
o
v
el
t
h
r
e
a
t
s
d
u
e
t
o
t
h
e
i
r
r
e
l
i
a
n
ce
o
n
k
n
o
w
n
p
a
t
t
e
r
n
s
[
7
]
.
H
e
u
r
i
s
t
i
c
m
e
t
h
o
d
s
a
t
t
e
m
p
t
t
o
d
e
t
ec
t
m
a
li
c
i
o
u
s
b
e
h
a
v
i
o
r
[
8
]
b
u
t a
r
e
p
r
o
n
e
to
f
alse p
o
s
itiv
es a
n
d
r
e
q
u
ir
e
c
o
n
s
tan
t u
p
d
ates.
R
esear
ch
er
s
h
av
e
tu
r
n
ed
to
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es
[
9
]
,
wh
ic
h
an
al
y
ze
s
p
atter
n
s
in
lar
g
e
d
atasets
f
o
r
m
alwa
r
e
d
etec
tio
n
.
W
h
ile
m
ac
h
in
e
lear
n
in
g
h
a
s
im
p
r
o
v
ed
d
etec
tio
n
ca
p
a
b
ilit
ies
[
1
0
]
,
it
ty
p
ically
r
elies
o
n
m
an
u
al
f
ea
tu
r
e
ex
tr
ac
tio
n
[
1
1
]
,
wh
ich
is
lab
o
r
-
in
ten
s
iv
e
an
d
er
r
o
r
-
p
r
o
n
e
[
1
2
]
.
R
ec
en
t
ad
v
an
ce
s
in
d
ee
p
lear
n
in
g
[
1
3
]
o
f
f
er
p
r
o
m
is
in
g
s
o
lu
tio
n
s
b
y
au
t
o
m
ati
n
g
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
a
d
ap
tin
g
to
ev
o
lv
in
g
th
r
ea
ts
,
p
ar
ticu
lar
ly
wh
en
d
ea
lin
g
with
PE
f
iles
[
1
4
]
,
wh
ich
ar
e
a
co
m
m
o
n
tar
g
et
f
o
r
m
alwa
r
e
[
1
5
]
.
Sig
n
if
ican
t
co
n
t
r
ib
u
tio
n
s
i
n
th
is
ar
ea
in
clu
d
e
Ab
u
alh
aj
et
a
l
.
[
1
6
]
u
s
ed
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
alg
o
r
ith
m
,
wh
ich
f
o
cu
s
es
o
n
d
ata
tr
an
s
f
o
r
m
atio
n
a
n
d
n
o
r
m
aliza
tio
n
t
o
en
h
an
ce
p
er
f
o
r
m
an
ce
.
T
h
ei
r
MW
-
KNN
m
o
d
el
ad
d
r
ess
es
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
s
ig
n
atu
r
e
-
b
ased
m
eth
o
d
s
,
p
a
r
ticu
lar
ly
f
o
r
p
o
ly
m
o
r
p
h
ic
a
n
d
m
etam
o
r
p
h
ic
m
alwa
r
e.
An
o
th
er
n
o
tab
le
wo
r
k
is
Ma
lNet
b
y
Yan
et
a
l.
[
1
7
]
wh
ic
h
d
is
cu
s
s
es
a
d
ee
p
lear
n
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
8
5
-
9
9
4
986
m
eth
o
d
f
o
r
m
alwa
r
e
d
etec
tio
n
th
at
an
aly
ze
s
W
in
d
o
ws
ex
ec
u
tab
le
f
iles
th
r
o
u
g
h
g
r
a
y
s
ca
le
im
ag
e
co
n
v
e
r
s
io
n
f
o
r
C
NN
an
d
o
p
co
d
e
s
eq
u
en
ce
an
aly
s
is
u
s
in
g
L
STM
n
et
wo
r
k
s
.
T
h
is
d
u
al
ap
p
r
o
ac
h
i
m
p
r
o
v
es
d
etec
tio
n
ac
cu
r
ac
y
a
n
d
a
u
to
m
ates
f
ea
tu
r
e
lear
n
in
g
.
Yılm
az
an
d
B
ak
ır
[
1
8
]
u
s
ed
a
s
y
s
tem
b
ased
o
n
m
ac
h
in
e
lear
n
i
n
g
f
o
r
an
d
r
o
id
d
ev
ices
to
o
p
tim
ize
p
er
f
o
r
m
a
n
ce
th
r
o
u
g
h
m
et
h
o
d
s
l
ik
e
SMOT
E
an
d
C
lu
s
ter
C
en
tr
o
id
s
f
o
r
im
b
alan
ce
d
d
atasets
,
ac
h
iev
in
g
a
d
etec
tio
n
ac
cu
r
ac
y
o
f
9
8
.
9
8
%.
AL
Go
r
ain
an
d
C
lar
k
[
1
9
]
in
v
esti
g
at
ed
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
tec
h
n
iq
u
es
f
o
r
m
alwa
r
e
d
etec
tio
n
,
p
ar
ticu
la
r
ly
f
o
cu
s
in
g
o
n
W
in
d
o
ws
PE
f
iles
,
an
d
d
em
o
n
s
tr
ated
th
e
im
p
o
r
tan
ce
o
f
tailo
r
ed
p
a
r
am
eter
tu
n
in
g
.
L
ad
an
d
Ad
a
m
u
th
e
[
2
0
]
p
r
o
p
o
s
ed
a
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
s
tatic
PE
f
iles
m
alwa
r
e
d
etec
tio
n
,
ac
h
iev
in
g
h
i
g
h
ac
c
u
r
ac
y
o
f
9
7
.
5
3
%
an
d
9
4
.
0
9
%
f
o
r
t
h
e
2
0
1
7
a
n
d
2
0
1
8
d
atasets
Desp
ite
th
ese
ad
v
an
ce
m
en
ts
,
ch
allen
g
es
r
em
ain
,
p
a
r
ticu
lar
l
y
in
au
to
m
atin
g
f
ea
tu
r
e
ex
tr
a
ctio
n
an
d
ad
ap
tin
g
to
n
ew
th
r
ea
ts
.
Hy
p
e
r
p
ar
am
eter
tu
n
i
n
g
in
d
ee
p
lear
n
in
g
is
a
cr
itical
y
et
o
f
ten
u
n
d
er
ex
p
lo
r
ed
asp
e
ct
th
at
ca
n
s
ig
n
if
ican
tly
im
p
ac
t
p
er
f
o
r
m
an
ce
[
2
1
]
.
T
h
is
s
tu
d
y
b
u
ild
s
u
p
o
n
th
ese
ex
is
tin
g
wo
r
k
s
b
y
f
o
c
u
s
in
g
o
n
h
y
p
er
p
ar
am
eter
tu
n
i
n
g
ac
r
o
s
s
m
u
ltip
le
d
ee
p
lear
n
in
g
m
o
d
e
ls
ANN,
C
NN,
an
d
R
NN
s
p
ec
if
ically
ap
p
lied
to
PE
f
iles
.
B
y
cu
s
to
m
izin
g
th
ese
p
ar
am
eter
s
,
o
u
r
ap
p
r
o
ac
h
aim
s
to
s
u
r
p
ass
cu
r
r
en
t
d
etec
tio
n
ac
cu
r
ac
y
lev
els
an
d
im
p
r
o
v
e
th
e
d
etec
tio
n
o
f
ev
o
lv
in
g
m
alwa
r
e
th
r
ea
ts
,
o
f
f
er
in
g
a
m
o
r
e
r
o
b
u
s
t
an
d
co
m
p
r
eh
en
s
iv
e
s
o
lu
tio
n
th
an
p
r
e
v
io
u
s
ly
p
r
o
p
o
s
ed
m
et
h
o
d
s
.
T
h
is
r
esear
ch
aim
s
to
ad
v
a
n
c
e
m
alwa
r
e
d
etec
tio
n
b
y
d
e
v
el
o
p
in
g
a
h
ig
h
l
y
o
p
tim
ized
d
ee
p
lear
n
i
n
g
f
r
am
ewo
r
k
th
at
e
n
h
an
ce
s
d
ete
ctio
n
ac
cu
r
ac
y
a
n
d
im
p
r
o
v
es
p
r
ec
is
io
n
to
r
aise
th
e
a
d
ap
tab
i
lity
o
f
d
etec
tio
n
t
o
n
ew
an
d
s
o
p
h
is
ticated
m
alwa
r
e
s
tr
ain
s
.
Do
in
g
s
o
,
we
s
e
ek
to
co
n
tr
ib
u
te
a
m
o
r
e
r
esil
ien
t
s
o
lu
tio
n
to
th
e
cy
b
er
s
ec
u
r
ity
co
m
m
u
n
ity
a
n
d
p
r
o
v
id
e
a
f
o
u
n
d
atio
n
f
o
r
f
u
tu
r
e
s
ec
u
r
ity
r
esear
ch
.
Ou
r
a
p
p
r
o
ac
h
is
d
esig
n
ed
to
r
ea
d
ily
ap
p
l
y
to
o
t
h
er
s
ec
u
r
ity
s
o
lu
tio
n
s
,
u
ltima
tely
r
aisi
n
g
th
e
m
atu
r
ity
o
f
th
e
m
alwa
r
e
d
ete
ctio
n
f
ield
.
T
h
e
p
r
esen
t
p
a
p
er
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws:
s
ec
tio
n
2
o
f
f
e
r
s
a
d
etailed
ex
p
lan
atio
n
o
f
th
e
ad
o
p
ted
m
eth
o
d
o
l
o
g
y
an
d
th
e
p
r
o
p
o
s
e
d
f
r
a
m
ewo
r
k
d
esig
n
,
d
e
m
o
n
s
t
r
atin
g
h
o
w
o
u
r
ap
p
r
o
ac
h
ad
d
r
ess
es
th
e
ch
allen
g
es
in
cu
r
r
e
n
t
m
eth
o
d
s
.
Sectio
n
3
co
v
er
s
th
e
f
in
d
i
n
g
s
,
ex
am
i
n
a
tio
n
s
,
d
is
cu
s
s
io
n
,
an
d
ass
ess
m
en
t
m
eth
o
d
o
lo
g
y
,
s
h
o
win
g
th
e
ef
f
ec
tiv
en
ess
o
f
o
u
r
o
p
tim
ized
m
o
d
els.
Fin
ally
,
s
ec
tio
n
4
d
elin
ea
tes
an
d
s
u
m
m
ar
izes
th
e
s
tu
d
y
’
s
o
v
er
all
co
n
clu
s
io
n
,
alo
n
g
wi
th
th
e
p
lan
n
ed
f
u
tu
r
e
wo
r
k
,
h
ig
h
lig
h
tin
g
o
u
r
r
esear
ch
’
s
co
n
tr
ib
u
tio
n
s
an
d
p
o
ten
tial im
p
ac
t.
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
c
o
llect
io
n
T
h
is
r
esear
ch
m
ay
lead
to
a
n
ew
ap
p
r
o
ac
h
to
d
e
ep
lear
n
in
g
,
we
’
v
e
d
ev
elo
p
e
d
an
ef
f
i
cien
t
an
d
o
p
tim
ized
ar
c
h
itectu
r
e
a
n
d
a
s
tr
o
n
g
wo
r
k
f
lo
w
to
ad
d
r
ess
a
s
p
ec
if
ic
c
h
allen
g
e.
W
e
aim
to
e
n
h
an
ce
d
ata
p
r
o
ce
s
s
in
g
an
d
wo
r
k
f
lo
w
b
y
tack
lin
g
wea
k
n
ess
es
th
r
o
u
g
h
m
eth
o
d
s
lik
e
d
ata
b
alan
cin
g
an
d
h
y
p
er
p
ar
am
eter
tu
n
in
g
.
T
h
is
h
elp
s
av
o
id
is
s
u
es
ca
u
s
ed
b
y
co
m
p
lex
m
o
d
els,
p
r
e
v
en
tin
g
o
v
er
f
itti
n
g
f
o
r
m
o
r
e
ef
f
ec
tiv
e
r
esu
lts
.
T
h
is
r
esear
ch
p
r
o
ject
f
o
cu
s
es
o
n
an
aly
zi
n
g
a
s
u
b
s
tan
tial
n
u
m
b
er
o
f
m
alicio
u
s
an
d
leg
iti
m
ate
f
iles
,
lev
er
ag
in
g
d
atasets
s
o
u
r
ce
d
f
r
o
m
t
h
e
Kag
g
le
[
2
2
]
.
T
h
e
te
s
tin
g
p
h
ase
i
n
co
r
p
o
r
ates
d
iv
e
r
s
e
s
am
p
les
f
r
o
m
Vir
u
s
to
tal
[
2
3
]
an
d
Vir
u
s
s
h
ar
e
[
2
4
]
.
T
h
is
s
tu
d
y
aim
s
to
d
ev
elo
p
an
ef
f
ec
tiv
e
d
ee
p
lear
n
in
g
alg
o
r
ith
m
f
o
r
m
alwa
r
e
d
etec
tio
n
b
y
u
tili
zin
g
a
r
o
b
u
s
t
d
ataset
co
m
p
r
is
in
g
1
3
7
,
0
0
0
f
iles
with
5
7
f
ea
tu
r
es,
in
clu
d
in
g
9
6
,
0
0
0
m
alicio
u
s
a
n
d
4
1
,
0
0
0
leg
itima
te
s
am
p
les
.
T
h
is
ap
p
r
o
ac
h
en
s
u
r
es
th
e
ef
f
ec
tiv
e
n
ess
o
f
d
ata
d
is
tr
ib
u
tio
n
in
b
o
th
th
e
lear
n
in
g
an
d
test
in
g
p
h
ase
s
,
m
itig
atin
g
b
ias
th
at
co
u
ld
c
o
m
p
r
o
m
is
e
th
e
ac
cu
r
ac
y
o
f
r
e
s
u
lts
.
A
m
eticu
lo
u
s
h
y
p
er
p
ar
am
eter
tu
n
in
g
p
r
o
ce
s
s
is
co
n
d
u
cted
f
o
r
t
h
e
ANN,
C
NN,
an
d
R
NN
to
o
p
tim
ize
t
h
e
p
er
f
o
r
m
an
ce
o
f
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
.
T
h
i
s
co
n
f
ig
u
r
atio
n
aim
s
to
im
p
r
o
v
e
th
e
co
n
f
u
s
io
n
m
atr
ix
v
alu
e
s
an
d
en
h
an
ce
ea
c
h
m
o
d
el’
s
ac
cu
r
ac
y
a
n
d
p
r
ec
is
i
o
n
.
E
ac
h
d
ee
p
lear
n
in
g
alg
o
r
i
th
m
u
n
d
e
r
g
o
es
tr
ain
in
g
a
n
d
e
v
alu
atio
n
u
s
i
n
g
th
e
p
r
ep
ar
e
d
d
ataset.
E
v
al
u
atio
n
m
etr
ics
ar
e
co
m
p
u
ted
to
ass
es
s
ea
ch
m
o
d
el’
s
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
o
p
tim
ize
d
co
n
f
u
s
io
n
m
atr
ix
.
T
h
e
b
est
-
p
e
r
f
o
r
m
in
g
m
o
d
el
is
s
elec
ted
b
a
s
ed
o
n
it
i
s
ef
f
ec
tiv
e
an
d
r
o
b
u
s
t
co
n
f
u
s
io
n
m
atr
ix
an
d
h
ig
h
ac
cu
r
ac
y
an
d
p
r
ec
is
i
o
n
.
T
h
is
m
o
d
el
is
s
av
ed
f
o
r
f
u
t
u
r
e
u
s
e
in
class
if
y
in
g
u
n
s
ee
n
f
iles
.
W
h
en
an
u
n
s
ee
n
f
ile
r
eq
u
ir
e
s
an
aly
s
is
f
o
r
clas
s
if
icatio
n
,
th
e
h
ea
d
er
o
f
its
PE
is
ex
tr
ac
ted
[
2
5
]
,
f
ea
tu
r
e
s
elec
tio
n
is
au
to
m
atica
lly
p
er
f
o
r
m
ed
b
ased
o
n
im
p
o
r
tan
ce
,
an
d
th
e
p
r
e
v
io
u
s
ly
s
av
ed
b
e
s
t
m
o
d
el
is
u
tili
ze
d
f
o
r
class
if
y
in
g
t
h
e
f
ile
.
T
h
e
r
esu
lt
o
f
th
e
class
if
icatio
n
(
m
alicio
u
s
o
r
leg
itima
te)
is
d
eter
m
in
ed
b
y
t
h
e
s
av
ed
m
o
d
el,
e
n
h
an
ci
n
g
th
e
d
etec
tio
n
ca
p
ab
ilit
y
an
d
im
p
r
o
v
in
g
th
e
q
u
ality
an
d
s
p
ee
d
o
f
f
il
e
class
if
icatio
n
.
T
h
e
ex
am
p
les
b
elo
w
i
n
Fig
u
r
e
1
d
etail
th
e
m
o
d
el
o
p
tim
i
za
tio
n
wo
r
k
f
l
o
w,
o
u
tlin
in
g
e
ac
h
s
tep
in
r
ef
in
in
g
d
ata
p
r
o
ce
s
s
in
g
an
d
m
o
d
el
tr
ain
in
g
to
m
ax
im
ize
d
etec
tio
n
ac
cu
r
ac
y
.
Fig
u
r
e
2
,
i
n
tu
r
n
,
illu
s
tr
ates
th
e
ar
ch
itectu
r
e
d
esig
n
ed
f
o
r
th
e
ac
cu
r
ate
class
if
icatio
n
o
f
p
r
ev
io
u
s
ly
u
n
s
ee
n
f
iles
,
h
ig
h
li
g
h
tin
g
th
e
n
o
tab
le
im
p
ac
t o
f
th
is
ap
p
r
o
ac
h
o
n
im
p
r
o
v
in
g
m
alwa
r
e
d
etec
tio
n
ca
p
ab
ilit
ies.
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:
2
5
0
2
-
4
7
52
E
n
h
a
n
ci
n
g
m
a
lw
a
r
e
d
etec
tio
n
ca
p
a
b
ilit
ies u
s
in
g
d
ee
p
lea
r
n
i
n
g
w
ith
a
d
va
n
ce
d
…
(
Wa
lid
E
l Mo
u
h
ta
d
i
)
987
Fig
u
r
e
1.
Mo
d
el
o
p
tim
izatio
n
wo
r
k
f
lo
w
an
d
d
ata
p
r
o
ce
s
s
in
g
Fig
u
r
e
2
.
Ad
v
an
ce
d
ar
ch
itectu
r
e
f
o
r
ac
c
u
r
ate
class
if
icatio
n
o
f
u
n
s
ee
n
f
iles
2
.
2
.
Da
t
a
f
a
irness
t
hro
ug
h d
a
t
a
ba
la
ncing
T
h
i
s
s
t
e
p
o
f
d
a
t
a
b
a
l
a
n
ci
n
g
e
n
s
u
r
e
s
t
h
a
t
t
h
e
t
r
a
i
n
i
n
g
d
a
ta
i
s
e
v
e
n
l
y
s
p
r
e
a
d
a
c
r
o
s
s
a
ll
c
l
ass
e
s
,
p
r
e
v
e
n
t
i
n
g
a
n
y
b
i
a
s
i
n
t
h
e
m
o
d
e
l
.
B
al
a
n
c
in
g
t
h
e
d
a
t
a
is
c
r
u
c
ia
l
,
a
s
a
n
u
n
e
v
e
n
d
i
s
t
r
i
b
u
t
i
o
n
c
a
n
l
e
a
d
t
o
a
d
i
s
t
o
r
t
e
d
m
o
d
e
l
.
T
h
e
F
i
g
u
r
e
s
3
a
n
d
4
s
h
o
w
h
o
w
t
h
e
c
l
a
s
s
d
is
t
r
i
b
u
t
i
o
n
c
h
a
n
g
es
b
e
f
o
r
e
a
n
d
a
f
t
e
r
b
a
l
a
n
c
i
n
g
t
h
e
d
a
ta
.
F
i
g
u
r
e
3
.
B
e
f
o
r
e
b
a
la
n
c
i
n
g
F
i
g
u
r
e
4
.
A
f
t
e
r
b
a
la
n
c
i
n
g
I
d
en
tify
in
g
k
e
y
ch
a
r
ac
ter
is
tics
is
ess
en
tial
f
o
r
ac
cu
r
ately
c
ateg
o
r
izin
g
f
iles
as
eith
er
m
a
licio
u
s
o
r
b
en
ig
n
.
Af
ter
p
r
ep
r
o
ce
s
s
in
g
th
e
d
ataset
b
y
r
em
o
v
in
g
co
lu
m
n
s
s
u
ch
as
Nam
e
o
f
th
e
f
ile,
MD
5
,
an
d
lab
el,
a
to
tal
o
f
5
4
f
ea
tu
r
es
wer
e
r
etain
ed
f
r
o
m
th
e
o
r
i
g
in
al
5
7
co
lu
m
n
s
,
th
e
m
eticu
lo
u
s
s
elec
tio
n
o
f
th
e
m
o
s
t
in
f
o
r
m
ativ
e
f
ea
tu
r
es
b
ec
o
m
es
im
p
er
ativ
e
to
cir
c
u
m
v
e
n
t
o
v
e
r
f
itti
n
g
[
2
6
]
,
p
r
eser
v
e
m
o
d
el
in
ter
p
r
etab
ilit
y
,
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
8
5
-
9
9
4
988
r
ed
u
ce
co
m
p
u
tatio
n
al
e
x
p
en
s
es.
T
h
e
a
b
u
n
d
an
ce
o
f
f
ea
tu
r
es
ca
n
d
et
r
im
en
tally
a
f
f
ec
t
m
o
d
el
p
er
f
o
r
m
an
ce
,
in
tr
o
d
u
cin
g
co
m
p
lex
ity
a
n
d
im
p
ed
in
g
p
atter
n
r
ec
o
g
n
iti
o
n
.
Fu
r
th
er
m
o
r
e,
ex
ce
s
s
f
ea
tu
r
es
ex
ten
d
th
e
co
m
p
u
tatio
n
al
tim
e
r
e
q
u
ir
e
d
f
o
r
tr
ain
i
n
g
a
n
d
p
r
e
d
ictio
n
[
2
7
]
.
T
h
u
s
,
a
c
o
m
p
r
e
h
en
s
iv
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
b
ec
o
m
es
ess
en
tial
to
s
tr
ea
m
lin
e
th
e
m
o
d
el,
en
h
an
ce
ef
f
icien
cy
[
2
8
]
,
an
d
f
o
cu
s
o
n
th
e
m
o
s
t
p
er
tin
en
t
f
ea
tu
r
es
.
I
n
th
is
s
tu
d
y
,
f
ea
tu
r
e
s
elec
tio
n
p
er
f
o
r
m
ed
b
y
d
ee
p
lear
n
i
n
g
alg
o
r
ith
m
s
p
la
y
ed
a
cr
u
cial
r
o
le
in
aid
in
g
f
ile
class
if
icatio
n
,
p
in
p
o
in
tin
g
1
3
f
ea
tu
r
es
ess
en
tial
f
o
r
ac
cu
r
ate
ca
teg
o
r
izatio
n
.
T
h
e
u
tili
za
tio
n
o
f
th
ese
k
e
y
f
ea
tu
r
es
s
ig
n
if
ican
tly
b
o
ls
ter
e
d
class
if
icatio
n
ac
cu
r
ac
y
,
u
n
d
er
s
co
r
in
g
t
h
e
ef
f
ec
tiv
en
ess
o
f
th
e
d
ee
p
lea
r
n
in
g
alg
o
r
ith
m
s
in
id
en
tif
y
in
g
p
iv
o
tal
f
ea
tu
r
es
f
o
r
f
ile
class
if
i
ca
tio
n
.
Fig
u
r
e
5
p
r
esen
ts
th
e
r
elev
an
t
f
ea
tu
r
es
s
elec
ted
b
y
d
ee
p
lea
r
n
in
g
an
d
th
eir
im
p
o
r
ta
n
ce
.
Fig
u
r
e
5
.
I
m
p
o
r
tan
t r
elev
a
n
t f
ea
tu
r
e
2
.
3
.
E
x
perim
ent
a
l
s
et
up
a
nd
ex
ec
utio
n e
nv
iro
nm
ent
T
h
is
r
esear
ch
p
r
o
ject
ca
r
r
ied
o
u
t
tr
ials
o
n
a
co
m
p
u
tin
g
s
y
s
te
m
eq
u
ip
p
e
d
with
an
I
n
tel
C
o
r
e
i5
ce
n
tr
al
p
r
o
ce
s
s
in
g
u
n
it
(
C
PU)
b
o
asti
n
g
8
Gig
ab
y
tes
(
GB
)
o
f
r
an
d
o
m
-
ac
ce
s
s
m
em
o
r
y
(
R
AM
)
a
n
d
an
I
n
tel®
UHD
g
r
ap
h
ics
p
r
o
ce
s
s
in
g
u
n
it
(
GP
U)
f
ea
tu
r
in
g
4
.
1
Gig
ab
y
tes
o
f
d
ed
icate
d
v
i
d
eo
m
em
o
r
y
.
T
h
e
u
tili
ze
d
o
p
er
atin
g
s
y
s
tem
was
W
in
d
o
ws
1
0
.
T
h
e
tr
ials
wer
e
ex
ec
u
ted
u
s
in
g
th
e
Py
th
o
n
p
r
o
g
r
am
m
i
n
g
lan
g
u
ag
e,
s
p
ec
if
ically
v
er
s
io
n
3
.
8
.
5
,
an
d
an
a
r
r
ay
o
f
lib
r
ar
ies,
in
clu
d
in
g
Nu
m
Py
,
Pan
d
as,
Scik
it
-
lear
n
,
PeFil
e
,
an
d
T
en
s
o
r
Flo
w.
T
h
e
d
ata
em
p
lo
y
e
d
in
th
e
tr
ials
wer
e
lo
ca
lly
s
to
r
ed
as f
iles
.
3.
P
RO
P
O
SE
D
DE
E
P
L
E
ARN
I
NG
F
O
R
M
AL
WAR
E
DE
T
E
CT
I
O
N
F
RA
M
E
WO
RK
On
ce
th
e
f
u
n
d
a
m
en
tal
attr
ib
u
tes
h
av
e
b
ee
n
id
en
tifie
d
,
th
e
s
u
b
s
eq
u
en
t
s
tag
e
in
v
o
lv
es
tr
a
in
in
g
an
d
test
in
g
v
ar
io
u
s
class
i
f
icatio
n
alg
o
r
ith
m
s
u
s
in
g
th
ese
attr
ib
u
t
es.
T
h
is
ca
n
b
e
ac
h
iev
ed
b
y
p
ar
titi
o
n
in
g
th
e
d
ata
in
to
a
tr
ain
in
g
s
et
an
d
a
test
s
et
an
d
u
tili
zin
g
th
e
tr
ain
in
g
s
et
f
o
r
th
e
m
o
d
el
’
s
tr
ain
in
g
,
wh
ile
th
e
test
s
et
is
em
p
lo
y
ed
to
a
p
p
r
aise
th
e
m
o
d
el
’
s
p
er
f
o
r
m
a
n
ce
.
T
h
e
d
a
ta
d
iv
is
io
n
was
co
n
d
u
cted
to
g
u
ar
a
n
tee
th
e
ass
ess
m
en
t
o
f
th
e
ac
cu
r
a
cy
o
f
th
e
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
.
T
h
e
tr
ain
in
g
s
et
co
m
p
r
is
ed
“
X
tr
ain
”
an
d
“
y
tr
ain
.
”
“
X
tr
ai
n
”
en
ca
p
s
u
lates
all
th
e
f
ea
tu
r
e
v
alu
es
f
o
r
ea
ch
r
o
w,
ex
clu
d
in
g
th
e
lab
el
co
lu
m
n
,
wh
ile
“
y
tr
ai
n
”
ex
clu
s
iv
ely
co
n
tain
s
th
e
lab
el
v
alu
es
f
o
r
e
ac
h
r
o
w.
I
n
th
e
ex
p
er
im
en
t,
t
h
r
ee
d
ee
p
lea
r
n
in
g
al
g
o
r
ith
m
s
wer
e
in
co
r
p
o
r
ated
f
o
llo
win
g
t
h
e
d
ata
d
iv
is
io
n
,
in
clu
d
in
g
ANN,
C
NN,
an
d
R
NN,
th
e
tr
ain
e
d
m
o
d
els
wer
e
s
u
b
s
eq
u
en
tly
u
tili
ze
d
to
ca
teg
o
r
ize
th
e
d
ata
in
th
e
test
s
et
“
X
te
s
t
”
an
d
“
y
test
”
an
d
ass
ess
th
eir
ac
cu
r
ac
y
.
T
h
e
o
u
tco
m
es
o
f
th
is
ev
alu
atio
n
y
ield
in
s
ig
h
ts
in
to
t
h
e
ef
f
icac
y
a
n
d
p
er
f
o
r
m
an
ce
o
f
ea
ch
d
ee
p
lear
n
in
g
alg
o
r
ith
m
.
Fo
llo
win
g
co
m
m
o
n
r
esear
c
h
p
r
ac
tices,
it
is
r
ec
o
m
m
en
d
ed
t
o
f
o
llo
w
a
s
p
ec
if
ic
s
er
ies
o
f
s
tep
s
.
First,
tr
ain
an
d
ass
e
s
s
th
e
co
m
p
u
tat
io
n
al
m
eth
o
d
s
.
Af
te
r
c
o
m
p
let
in
g
th
is
p
r
o
ce
s
s
,
it
’
s
c
r
u
cial
t
o
id
en
tif
y
t
h
e
m
o
s
t
ef
f
ec
tiv
e
f
r
am
ew
o
r
k
b
y
ca
lcu
l
atin
g
v
ar
io
u
s
m
etr
ics s
u
ch
as p
r
ec
is
io
n
,
f
alse p
o
s
itiv
es,
an
d
f
alse n
eg
ativ
es.
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:
2
5
0
2
-
4
7
52
E
n
h
a
n
ci
n
g
m
a
lw
a
r
e
d
etec
tio
n
ca
p
a
b
ilit
ies u
s
in
g
d
ee
p
lea
r
n
i
n
g
w
ith
a
d
va
n
ce
d
…
(
Wa
lid
E
l Mo
u
h
ta
d
i
)
989
Fin
ally
,
s
av
e
th
e
f
r
am
ewo
r
k
with
th
e
h
ig
h
est
ef
f
ec
tiv
en
ess
as
a
f
ile
f
o
r
f
u
tu
r
e
u
s
e.
T
h
e
ef
f
icien
cy
o
f
ea
ch
co
m
p
u
tatio
n
al
m
eth
o
d
is
ev
alu
ated
u
s
in
g
m
etr
ics
lik
e
p
r
ec
is
io
n
,
f
alse
p
o
s
itiv
e
r
atio
,
an
d
f
alse
n
eg
ati
v
e
r
atio
.
Fra
m
ewo
r
k
ac
c
u
r
ac
y
is
ass
es
s
ed
u
s
in
g
th
e
s
co
r
in
g
f
u
n
ctio
n
f
r
o
m
t
h
e
Py
th
o
n
Scik
it
l
ib
r
ar
y
.
C
alcu
latin
g
f
alse
p
o
s
itiv
e
an
d
f
alse
n
eg
ati
v
e
r
atio
s
is
d
o
n
e
u
s
in
g
t
h
e
co
n
f
u
s
io
n
m
atr
i
x
,
an
d
th
e
er
r
o
r
m
atr
ix
.
T
h
is
m
atr
ix
s
u
m
m
ar
izes
th
e
p
er
f
o
r
m
an
ce
o
f
a
b
in
ar
y
ca
teg
o
r
izatio
n
tech
n
iq
u
e
b
y
co
m
p
ar
i
n
g
p
r
ed
icte
d
v
alu
es
with
ac
tu
al
v
alu
es,
as illu
s
tr
ated
in
T
ab
le
1
.
T
ab
le
1
.
C
o
n
f
u
s
io
n
m
atr
ix
A
c
t
u
a
l
P
o
si
t
i
v
e
(
1
)
N
e
g
a
t
i
v
e
(
0
)
P
r
e
d
i
c
t
e
d
P
o
si
t
i
v
e
(
0
)
Tr
u
e
p
o
si
t
i
v
e
F
a
l
se
p
o
si
t
i
v
e
N
e
g
a
t
i
v
e
(
1
)
F
a
l
se
n
e
g
a
t
i
v
e
Tr
u
e
n
e
g
a
t
i
v
e
N
o
t
e
:
Tr
u
e
p
o
si
t
i
v
e
s
(
TP)
:
t
h
e
n
u
mb
e
r
o
f
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
e
d
i
n
st
a
n
c
e
s
a
s
p
o
si
t
i
v
e
.
F
a
l
s
e
p
o
s
i
t
i
v
e
s
(
F
P
)
:
t
h
e
n
u
m
b
e
r
o
f
i
n
s
t
a
n
c
e
s
p
r
e
d
i
c
t
e
d
a
s
p
o
s
i
t
i
v
e
b
u
t
w
e
r
e
a
c
t
u
a
l
l
y
n
e
g
a
t
i
v
e
.
Tr
u
e
n
e
g
a
t
i
v
e
s
(
TN
)
:
t
h
e
n
u
mb
e
r
o
f
c
o
r
r
e
c
t
l
y
p
r
e
d
i
c
t
e
d
i
n
s
t
a
n
c
e
s
a
s
n
e
g
a
t
i
v
e
.
F
a
l
se
n
e
g
a
t
i
v
e
s
(
F
N
)
:
t
h
e
n
u
m
b
e
r
o
f
i
n
st
a
n
c
e
s
p
r
e
d
i
c
t
e
d
a
s
n
e
g
a
t
i
v
e
b
u
t
w
e
r
e
a
c
t
u
a
l
l
y
p
o
s
i
t
i
v
e
.
T
h
e
m
etr
ics
T
PR
,
T
NR
,
p
r
ec
i
s
io
n
,
an
d
ac
cu
r
ac
y
ca
n
b
e
ca
l
cu
lated
u
s
in
g
th
e
v
alu
es
in
th
e
co
n
f
u
s
io
n
m
atr
ix
,
lik
e
illu
s
tr
ated
in
T
ab
le
2
.
I
n
s
u
m
m
ar
y
,
th
e
tr
u
e
p
o
s
itiv
e
r
ate
(
T
PR
)
an
d
tr
u
e
n
eg
ativ
e
r
ate
(
T
NR
)
in
d
icate
th
e
alg
o
r
ith
m
’
s
ca
p
a
city
to
co
r
r
ec
tly
f
o
r
ec
ast
p
o
s
itiv
e
an
d
n
eg
ativ
e
in
s
tan
ce
s
.
P
r
ec
is
io
n
g
au
g
es
th
e
alg
o
r
ith
m
’
s
ef
f
ec
tiv
en
ess
in
g
en
er
atin
g
p
r
ec
is
e
p
o
s
itiv
e
p
r
ed
ictio
n
s
,
wh
ile
ac
cu
r
ac
y
s
er
v
es
as
a
co
m
p
r
eh
e
n
s
iv
e
m
etr
ic
f
o
r
ev
al
u
atin
g
th
e
alg
o
r
ith
m
’
s
o
v
er
all
p
er
f
o
r
m
an
ce
.
T
ab
le
2
.
Me
tr
ics f
o
r
p
er
f
o
r
m
a
n
ce
alg
o
r
ith
m
M
e
t
r
i
c
D
e
scri
p
t
i
o
n
C
a
l
c
u
l
a
t
i
o
n
Tr
u
e
p
o
si
t
i
v
e
r
a
t
e
(
TP
R
)
S
e
n
s
i
t
i
v
i
t
y
o
r
R
e
c
a
l
l
:
F
r
a
c
t
i
o
n
o
f
a
c
t
u
a
l
p
o
s
i
t
i
v
e
s
c
o
r
r
e
c
t
l
y
c
l
a
ss
i
f
i
e
d
a
s
p
o
s
i
t
i
v
e
.
T
PR
=
(
TP
FN
)
F
a
l
se
p
o
si
t
i
v
e
r
a
t
e
(
TN
R
)
S
p
e
c
i
f
i
c
i
t
y
:
F
r
a
c
t
i
o
n
o
f
a
c
t
u
a
l
n
e
g
a
t
i
v
e
s
i
n
c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
a
s
p
o
s
i
t
i
v
e
.
FPR
=
(
FP
FP
+
TN
)
P
r
e
c
i
s
i
o
n
F
r
a
c
t
i
o
n
o
f
p
o
s
i
t
i
v
e
p
r
e
d
i
c
t
i
o
n
s
t
h
a
t
w
e
r
e
a
c
t
u
a
l
l
y
p
o
si
t
i
v
e
.
Pr
e
c
i
s
i
o
n
=
(
TP
TP
+
FP
)
A
c
c
u
r
a
c
y
F
r
a
c
t
i
o
n
o
f
i
n
s
t
a
n
c
e
s c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
b
y
t
h
e
a
l
g
o
r
i
t
h
m
.
A
c
c
u
r
a
c
y
=
(
TP
TP
+
FP
)
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
A
s
er
ies
o
f
ca
s
e
s
tu
d
ies
wer
e
co
n
d
u
cte
d
,
an
d
th
e
p
e
r
f
o
r
m
an
ce
m
etr
ics
f
o
r
ea
ch
d
ef
a
u
lt
p
ar
am
eter
f
o
r
ea
ch
alg
o
r
ith
m
u
n
d
er
c
o
n
s
id
er
atio
n
ar
e
p
r
esen
ted
b
elo
w
in
T
a
b
le
3
.
T
h
ese
ca
s
e
s
tu
d
ies
en
ca
p
s
u
late
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
,
illu
s
tr
atin
g
th
e
p
r
ac
tical
ef
f
icac
y
o
f
o
u
r
m
o
d
els
in
d
is
tin
g
u
is
h
in
g
b
et
wee
n
m
alicio
u
s
an
d
leg
itima
te
f
iles
.
T
ab
le
3
.
B
ef
o
r
e
tu
n
n
i
n
g
M
e
t
r
i
c
A
N
N
b
e
f
o
r
e
h
y
p
e
r
p
a
r
a
met
e
r
t
u
n
i
n
g
C
N
N
b
e
f
o
r
e
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
R
N
N
b
e
f
o
r
e
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
A
c
c
u
r
a
c
y
0
.
4
9
8
9
7
0
.
9
1
5
2
6
0
.
7
5
1
4
1
P
r
e
c
i
s
i
o
n
0
.
5
0
4
1
1
0
.
9
1
5
3
7
0
.
7
5
1
6
0
Tr
u
e
p
o
si
t
i
v
e
0
6
8
9
2
5
4
2
1
Tr
u
e
n
e
g
a
t
i
v
e
8
3
3
3
8
2
3
9
7
0
0
3
F
a
l
se
p
o
si
t
i
v
e
0
94
1
3
3
0
F
a
l
se
n
e
g
a
t
i
v
e
8
1
9
7
1
3
0
5
2
7
7
6
TPR
0
.
0
0
0
0
0
0
.
8
4
0
8
0
0
.
9
0
1
7
9
FPR
0
.
0
0
0
0
0
0
.
0
1
1
2
8
0
.
0
1
4
6
4
R
u
n
n
i
n
g
ti
me
(
i
n
s
e
c
)
9
.
2
3
6
4
9
0
.
7
2
3
6
4
9
.
2
3
6
4
9
4
.
1
.
Co
m
pa
riso
n o
f
m
o
del c
re
a
t
io
n a
nd
ev
a
lua
t
io
n
Hy
p
er
p
ar
a
m
eter
tu
n
in
g
is
a
cr
itical
asp
ec
t
o
f
o
p
tim
izin
g
n
eu
r
al
n
etwo
r
k
s
,
an
d
th
e
jo
u
r
n
ey
f
r
o
m
a
n
o
r
ig
in
al
im
p
lem
en
tatio
n
to
a
r
ef
in
ed
m
o
d
el
in
v
o
lv
es
ad
ju
s
tin
g
k
ey
p
ar
am
eter
s
.
T
ab
les
4
-
6
s
h
o
wca
s
e
th
e
tr
an
s
f
o
r
m
atio
n
o
f
h
y
p
er
p
ar
a
m
eter
s
o
f
ANN,
C
NN,
an
d
R
NN
f
r
o
m
th
e
o
r
ig
i
n
al
im
p
lem
en
tatio
n
to
r
ec
o
m
m
en
d
ed
s
ettin
g
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
8
5
-
9
9
4
990
4
.
2
.
P
er
f
o
r
m
a
nce
m
e
t
rics a
f
t
er
t
un
ing
Per
f
o
r
m
an
ce
ev
alu
atio
n
is
cr
u
cial
f
o
r
u
n
d
e
r
s
tan
d
in
g
h
o
w
tu
n
in
g
af
f
ec
ts
alg
o
r
ith
m
p
er
f
o
r
m
an
ce
.
Ad
ju
s
tin
g
h
y
p
e
r
p
ar
am
ete
r
s
is
a
k
ey
p
r
o
ce
s
s
in
o
p
tim
izin
g
d
ee
p
lear
n
i
n
g
m
o
d
els,
an
d
th
e
im
p
ac
t
o
f
th
ese
ad
ju
s
tm
en
ts
is
ev
id
en
t
in
t
h
e
p
er
f
o
r
m
a
n
ce
m
etr
ics.
B
y
e
x
am
i
n
in
g
th
e
p
er
f
o
r
m
a
n
ce
cr
iter
ia
v
alu
es,
o
n
e
ca
n
s
ee
h
o
w
f
in
e
-
tu
n
in
g
e
n
h
an
ce
s
m
o
d
el
ef
f
ec
tiv
e
n
ess
.
T
h
e
im
p
r
o
v
em
en
ts
ac
h
iev
ed
th
r
o
u
g
h
th
is
p
r
o
ce
s
s
h
ig
h
lig
h
t
th
e
s
ig
n
if
ican
ce
o
f
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
in
r
ef
i
n
in
g
p
er
f
o
r
m
an
ce
.
T
h
is
an
aly
s
is
is
e
s
s
en
tial
f
o
r
ev
alu
atin
g
th
e
s
u
cc
ess
o
f
tu
n
in
g
an
d
g
u
id
in
g
f
u
tu
r
e
en
h
a
n
c
em
en
ts
.
T
o
p
r
ep
ar
e
th
at,
we
wil
l
r
ev
iew
T
ab
le
7
,
wh
ich
d
is
p
lay
s
th
e
v
alu
es o
f
p
er
f
o
r
m
a
n
ce
cr
iter
ia
f
o
r
ea
ch
alg
o
r
ith
m
a
f
ter
tu
n
in
g
.
T
ab
le
4
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
h
y
p
er
p
a
m
eter
s
ettin
g
s
in
A
NN
o
p
tim
izatio
n
H
y
p
e
r
p
a
r
a
me
t
e
r
ANN
o
r
i
g
i
n
a
l
i
m
p
l
e
m
e
n
t
a
t
i
o
n
ANN
r
e
c
o
mm
e
n
d
e
d
h
y
p
e
r
p
a
r
a
m
e
t
e
r
N
u
mb
e
r
o
f
n
e
u
r
o
n
s (La
y
e
r
1
)
1
2
8
(
D
e
n
s
e
l
a
y
e
r
)
‘
u
n
i
t
s
1
’
(
1
2
8
,
D
e
n
s
e
l
a
y
e
r
)
D
r
o
p
o
u
t
r
a
t
e
(
La
y
e
r
1
)
0
.
2
(
D
r
o
p
o
u
t
l
a
y
e
r
)
N
/
A
(
N
o
t
t
u
n
e
d
i
n
C
o
d
e
2
)
N
u
mb
e
r
o
f
n
e
u
r
o
n
s (La
y
e
r
2
)
6
4
(
D
e
n
s
e
l
a
y
e
r
)
‘
u
n
i
t
s
2
’
(
6
4
,
D
e
n
se
l
a
y
e
r
)
D
r
o
p
o
u
t
ra
t
e
(
La
y
e
r
2
)
0
.
2
(
D
r
o
p
o
u
t
l
a
y
e
r
)
N
/
A
(
N
o
t
t
u
n
e
d
i
n
C
o
d
e
2
)
N
u
mb
e
r
o
f
n
e
u
r
o
n
s (La
y
e
r
3
)
4
(
D
e
n
se
l
a
y
e
r
)
‘
u
n
i
t
s
3
’
(
4
,
D
e
n
se
l
a
y
e
r
)
Le
a
r
n
i
n
g
r
a
t
e
‘
a
d
a
m
’
o
p
t
i
mi
z
e
r
u
s
e
d
(
n
o
s
p
e
c
i
f
i
c
l
e
a
r
n
i
n
g
r
a
t
e
)
‘
l
e
a
r
n
i
n
g
_
r
a
t
e
’
(
0
.
0
0
1
,
G
r
i
d
S
e
a
r
c
h
C
V
)
N
u
mb
e
r
o
f
e
p
o
c
h
s
20
5
(
E
p
o
c
h
s fo
r
G
r
i
d
S
e
a
r
c
h
C
V
)
B
a
t
c
h
s
i
z
e
32
3
2
(
B
a
t
c
h
S
i
z
e
f
o
r
G
r
i
d
S
e
a
r
c
h
C
V
)
V
e
r
b
o
s
e
1
(
P
r
i
n
t
s
p
r
o
g
r
e
ss
b
a
r
)
0
(
V
e
r
b
o
s
e
f
o
r
G
r
i
d
S
e
a
r
c
h
C
V
)
T
ab
le
5
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
h
y
p
er
p
a
m
eter
s
ettin
g
s
in
C
NN
o
p
tim
izatio
n
H
y
p
e
r
p
a
r
a
me
t
e
r
C
N
N
o
r
i
g
i
n
a
l
i
m
p
l
e
me
n
t
a
t
i
o
n
C
N
N
r
e
c
o
mm
e
n
d
e
d
h
y
p
e
r
p
a
r
a
me
t
e
r
N
u
mb
e
r
o
f
f
i
l
t
e
r
s (
C
o
n
v
1
)
3
2
(
C
o
n
v
1
D
l
a
y
e
r
)
3
2
(
B
e
s
t
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
N
u
mb
e
r
o
f
f
i
l
t
e
r
s (
C
o
n
v
2
)
6
4
(
C
o
n
v
1
D
l
a
y
e
r
)
6
4
(
B
e
s
t
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
K
e
r
n
e
l
s
i
z
e
(
C
o
n
v
1
)
3
(
C
o
n
v
1
D
l
a
y
e
r
)
3
(
B
e
st
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
K
e
r
n
e
l
s
i
z
e
(
C
o
n
v
2
)
3
(
C
o
n
v
1
D
l
a
y
e
r
)
3
(
B
e
st
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
P
o
o
l
i
n
g
s
i
z
e
(
M
a
x
P
o
o
l
1
)
2
(
M
a
x
P
o
o
l
i
n
g
1
D
l
a
y
e
r
)
2
(
B
e
st
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
P
o
o
l
i
n
g
s
i
z
e
(
M
a
x
P
o
o
l
2
)
2
(
M
a
x
P
o
o
l
i
n
g
1
D
l
a
y
e
r
)
2
(
B
e
st
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
D
e
n
se
u
n
i
t
s
1
(
D
e
n
se
l
a
y
e
r
)
1
(
B
e
st
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
Le
a
r
n
i
n
g
r
a
t
e
N
/
A
0
.
0
0
1
(
B
e
s
t
v
a
l
u
e
f
r
o
m
G
r
i
d
S
e
a
r
c
h
C
V
)
N
u
mb
e
r
o
f
e
p
o
c
h
s
20
5
(
B
e
st
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
B
a
t
c
h
s
i
z
e
32
3
2
(
B
e
s
t
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
V
e
r
b
o
s
e
0
0
(
V
e
r
b
o
s
e
f
o
r
G
r
i
d
S
e
a
r
c
h
C
V
)
T
ab
le
6
.
Per
f
o
r
m
an
ce
af
ter
h
y
p
er
p
am
eter
s
ettin
g
s
in
R
NN
o
p
tim
izatio
n
H
y
p
e
r
p
a
r
a
me
t
e
r
R
N
N
o
r
i
g
i
n
a
l
i
m
p
l
e
me
n
t
a
t
i
o
n
R
N
N
r
e
c
o
mm
e
n
d
e
d
h
y
p
e
r
p
a
r
a
me
t
e
r
t
u
n
i
n
g
N
u
mb
e
r
o
f
u
n
i
t
s
6
4
(
S
i
m
p
l
e
R
N
N
l
a
y
e
r
)
6
4
(
B
e
s
t
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
Le
a
r
n
i
n
g
r
a
t
e
N
/
A
0
.
0
0
1
(
B
e
s
t
v
a
l
u
e
f
r
o
m
G
r
i
d
S
e
a
r
c
h
C
V
)
N
u
mb
e
r
o
f
e
p
o
c
h
s
20
5
(
B
e
st
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
B
a
t
c
h
s
i
z
e
32
3
2
(
B
e
s
t
v
a
l
u
e
f
r
o
m G
r
i
d
S
e
a
r
c
h
C
V
)
V
e
r
b
o
s
e
0
0
(
V
e
r
b
o
s
e
f
o
r
G
r
i
d
S
e
a
r
c
h
C
V
)
T
ab
le
7
.
Per
f
o
r
m
an
ce
o
f
alg
o
r
ith
m
af
ter
tu
n
n
in
g
M
e
t
r
i
c
ANN
b
e
f
o
r
e
t
u
n
i
n
g
ANN
a
f
t
e
r
t
u
n
i
n
g
C
N
N
b
e
f
o
r
e
t
u
n
i
n
g
C
N
N
a
f
t
e
r
t
u
n
i
n
g
R
N
N
b
e
f
o
r
e
t
u
n
i
n
g
R
N
N
a
f
t
e
r
t
u
n
i
n
g
A
c
c
u
r
a
c
y
0
.
4
9
8
9
7
0
.
8
7
6
0
.
9
1
5
2
6
0
.
9
5
0
0
.
7
5
1
4
1
0
.
8
2
0
P
r
e
c
i
s
i
o
n
0
.
5
0
4
1
1
0
.
8
8
3
0
.
9
1
5
3
7
0
.
9
4
7
0
.
7
5
1
6
0
0
.
8
3
1
Tr
u
e
p
o
si
t
i
v
e
0
6
7
5
9
6
8
9
2
7
3
3
3
5
4
2
1
6
5
7
0
Tr
u
e
n
e
g
a
t
i
v
e
8
3
3
3
8
2
4
5
8
2
3
9
8
2
2
3
7
0
0
3
7
4
8
9
F
a
l
se
p
o
si
t
i
v
e
0
88
94
1
1
0
1
3
3
0
8
4
4
F
a
l
se
n
e
g
a
t
i
v
e
8
1
9
7
1
4
3
8
1
3
0
5
8
6
4
2
7
7
6
1
6
2
7
Tr
u
e
p
o
si
t
i
v
e
r
a
t
e
0
.
0
0
0
0
0
0
.
8
2
4
0
.
8
4
0
8
0
0
.
8
9
5
0
.
9
0
1
7
9
0
.
8
0
1
F
a
l
se
p
o
si
t
i
v
e
r
a
t
e
0
.
0
0
0
0
0
0
.
0
1
0
0
.
0
1
1
2
8
0
.
0
1
3
0
.
0
1
4
6
4
0
.
1
0
1
R
u
n
n
i
n
g
t
i
me
(
s
e
c
)
9
.
2
3
6
4
9
9
.
5
0
0
0
.
7
2
3
6
4
0
.
7
5
0
9
.
2
3
6
4
9
9
.
8
0
0
Fig
u
r
es
6
-
8
p
r
esen
t
th
e
c
o
n
f
u
s
io
n
m
atr
ices
f
o
r
th
e
ANN,
C
NN,
an
d
R
NN
m
o
d
els
af
ter
h
y
p
er
p
ar
am
eter
t
u
n
in
g
,
h
ig
h
lig
h
tin
g
t
h
e
class
if
icatio
n
ac
cu
r
ac
y
an
d
th
e
im
p
ac
t
o
f
tu
n
i
n
g
o
n
tr
u
e
p
o
s
itiv
es,
f
alse
p
o
s
itiv
es,
tr
u
e
n
eg
ativ
es,
an
d
f
alse
n
eg
ativ
es
.
Fig
u
r
e
9
p
r
esen
ts
th
e
R
O
C
C
u
r
v
es
f
o
r
ANN,
C
NN,
an
d
R
NN
m
o
d
els
af
ter
h
y
p
er
p
ar
a
m
eter
tu
n
in
g
.
T
h
ese
cu
r
v
es
illu
s
tr
ate
th
e
tr
ad
e
-
o
f
f
b
etwe
en
t
h
e
tr
u
e
p
o
s
itiv
e
r
ate
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:
2
5
0
2
-
4
7
52
E
n
h
a
n
ci
n
g
m
a
lw
a
r
e
d
etec
tio
n
ca
p
a
b
ilit
ies u
s
in
g
d
ee
p
lea
r
n
i
n
g
w
ith
a
d
va
n
ce
d
…
(
Wa
lid
E
l Mo
u
h
ta
d
i
)
991
an
d
f
alse
p
o
s
itiv
e
r
ate
f
o
r
ea
ch
m
o
d
el,
h
i
g
h
lig
h
tin
g
th
e
ef
f
ec
ts
o
f
h
y
p
er
p
ar
a
m
eter
ad
ju
s
tm
en
ts
o
n
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
p
r
o
v
id
e
c
o
m
p
ellin
g
ev
id
e
n
ce
s
u
p
p
o
r
tin
g
th
e
i
n
itial
h
y
p
o
t
h
esis
t
h
at
p
r
io
r
itizin
g
h
y
p
er
p
ar
am
eter
t
u
n
in
g
wo
u
ld
s
ig
n
if
ican
tly
en
h
an
ce
th
e
ef
f
ec
tiv
e
n
ess
an
d
ac
cu
r
ac
y
o
f
d
ee
p
lear
n
in
g
m
o
d
els
in
m
alwa
r
e
d
etec
tio
n
.
Am
o
n
g
t
h
e
m
o
d
els
test
ed
,
th
e
C
NN
co
n
s
is
t
en
tly
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
,
with
p
o
s
t
-
tu
n
in
g
ac
cu
r
ac
y
im
p
r
o
v
in
g
f
r
o
m
0
.
9
1
5
to
0
.
9
5
0
an
d
p
r
ec
i
s
io
n
f
r
o
m
0
.
9
1
5
to
0
.
9
4
7
.
T
h
e
s
u
b
s
tan
tial
in
cr
ea
s
e
in
th
e
C
NN
T
P
R
f
r
o
m
0
.
8
4
0
to
0
.
8
9
5
f
u
r
th
er
u
n
d
er
s
c
o
r
es
its
ex
ce
p
tio
n
al
ab
ilit
y
to
ca
p
t
u
r
e
a
n
d
d
if
f
er
e
n
tiate
co
m
p
lex
p
atter
n
s
in
th
e
d
ata.
T
h
is
is
r
ef
lecte
d
i
n
its
h
ig
h
est
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
AUC)
o
f
0
.
9
2
,
co
n
f
i
r
m
in
g
th
e
h
y
p
o
th
esis
th
at
th
e
C
NN,
wh
en
o
p
tim
ized
,
wo
u
l
d
b
e
th
e
m
o
s
t
r
o
b
u
s
t
an
d
ef
f
icien
t so
lu
tio
n
f
o
r
th
is
ap
p
licatio
n
.
Fig
u
r
e
6
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
ANN
af
ter
h
y
p
er
p
ar
am
eter
tu
n
in
g
Fig
u
r
e
7
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
C
NN
af
ter
h
y
p
er
p
ar
am
eter
tu
n
in
g
Fig
u
r
e
8
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
R
NN
af
ter
h
y
p
er
p
ar
am
eter
t
u
n
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
8
5
-
9
9
4
992
Fig
u
r
e
9
.
R
OC
cu
r
v
e
f
o
r
ANN
,
C
NN,
an
d
R
NN
af
ter
h
y
p
e
r
p
ar
am
eter
tu
n
in
g
Ou
r
ch
o
ice
to
em
p
h
asize
h
y
p
er
p
ar
am
eter
tu
n
i
n
g
as
a
cr
it
ical
co
m
p
o
n
en
t
o
f
t
h
e
m
eth
o
d
o
lo
g
y
is
s
tr
o
n
g
ly
s
u
p
p
o
r
te
d
b
y
b
o
th
th
eo
r
etica
l
f
o
u
n
d
atio
n
s
an
d
em
p
ir
ical
r
esu
lts
.
Fo
r
i
n
s
tan
ce
,
th
e
s
ig
n
if
ica
n
t
im
p
r
o
v
em
e
n
ts
o
b
s
er
v
ed
i
n
th
e
ANN,
wh
er
e
ac
cu
r
ac
y
ju
m
p
e
d
f
r
o
m
0
.
4
9
8
to
0
.
8
7
6
an
d
p
r
ec
is
io
n
f
r
o
m
0
.
5
0
4
to
0
.
8
8
3
,
v
alid
ate
th
e
h
y
p
o
th
e
s
is
th
at
s
u
ch
tu
n
in
g
is
ess
en
ti
al
f
o
r
en
h
a
n
cin
g
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
eo
r
etica
l
in
s
ig
h
ts
in
m
ac
h
in
e
lear
n
in
g
s
u
g
g
est
th
at
w
h
e
n
p
r
o
p
e
r
ly
tu
n
ed
,
m
o
d
els
lik
e
ANN
an
d
C
NN
ca
n
b
etter
ca
p
tu
r
e
in
tr
icate
r
elatio
n
s
h
ip
s
with
in
d
ata,
lead
in
g
t
o
im
p
r
o
v
ed
g
en
er
aliza
tio
n
an
d
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
is
was
ev
id
en
t
as
th
e
ANN
AUC
im
p
r
o
v
ed
t
o
0
.
9
1
p
o
s
t
-
tu
n
in
g
,
alig
n
in
g
with
o
u
r
h
y
p
o
th
esis
r
eg
a
r
d
in
g
th
e
p
o
te
n
tial
o
f
o
p
tim
ized
m
o
d
els.
I
n
co
n
tr
ast,
wh
ile
th
e
R
NN
al
s
o
im
p
r
o
v
ed
p
o
s
t
-
tu
n
in
g
with
ac
cu
r
ac
y
r
is
in
g
f
r
o
m
0
.
7
5
1
to
0
.
8
2
0
an
d
p
r
ec
is
io
n
f
r
o
m
0
.
7
5
1
to
0
.
8
3
1
,
it
s
till
lag
s
b
eh
i
n
d
th
e
C
NN
in
o
v
er
all
p
er
f
o
r
m
an
ce
,
ac
h
iev
i
n
g
a
n
AUC
o
f
0
.
8
5
.
T
h
is
o
u
tco
m
e
was
an
ticip
ated
in
o
u
r
h
y
p
o
th
esis
,
wh
ich
r
ec
o
g
n
ized
th
at
wh
ile
R
NN
ar
e
well
-
s
u
ited
f
o
r
s
eq
u
en
tial
d
ata
p
r
o
ce
s
s
in
g
,
th
ey
ar
e
less
ef
f
e
ctiv
e
th
an
C
NN
in
ca
p
tu
r
in
g
th
e
co
m
p
lex
s
p
atial
f
ea
tu
r
es
cr
itical
f
o
r
h
ig
h
-
p
er
f
o
r
m
an
ce
m
alwa
r
e
d
etec
tio
n
.
T
h
is
co
m
p
ar
ativ
e
an
aly
s
is
f
u
r
th
er
s
o
lid
if
ies
th
e
r
atio
n
ale
b
eh
in
d
o
u
r
m
eth
o
d
o
l
o
g
ical
ch
o
ices,
r
ein
f
o
r
cin
g
th
e
ef
f
ec
tiv
en
ess
o
f
C
NN
in
th
is
d
o
m
ain
.
I
n
d
ev
elo
p
i
n
g
o
u
r
ap
p
r
o
ac
h
,
we
p
r
io
r
itized
m
o
d
els
b
ased
o
n
th
ei
r
s
tr
en
g
th
s
in
d
if
f
e
r
en
t
asp
ec
ts
o
f
p
atter
n
r
ec
o
g
n
itio
n
C
NN
f
o
r
s
p
atial
d
ata
an
d
R
NN
f
o
r
s
eq
u
en
tial
d
ata
wh
ile
em
p
h
asizin
g
th
e
cr
itical
r
o
le
o
f
h
y
p
er
p
ar
am
eter
tu
n
in
g
.
T
h
e
r
esu
lts
co
n
f
ir
m
th
at
o
u
r
in
itial
h
y
p
o
th
esis
was
co
r
r
ec
t,
th
e
C
NN
ar
ch
itectu
r
e,
o
p
tim
ized
t
h
r
o
u
g
h
ca
r
ef
u
l
tu
n
in
g
,
p
r
o
v
es
to
b
e
th
e
m
o
s
t
ef
f
ec
tiv
e
m
o
d
el
f
o
r
d
is
tin
g
u
is
h
in
g
b
etwe
en
m
alwa
r
e
an
d
n
o
n
-
m
alwa
r
e
s
am
p
les.
T
h
e
s
ig
n
if
ican
t
g
ain
s
ac
r
o
s
s
all
m
o
d
els
p
o
s
t
-
tu
n
in
g
also
r
ea
f
f
ir
m
t
h
e
th
eo
r
etica
l
p
r
em
is
e
th
at
o
p
tim
al
h
y
p
er
p
ar
am
eter
co
n
f
ig
u
r
atio
n
s
ar
e
ess
en
tial
f
o
r
u
n
lo
ck
in
g
a
m
o
d
el
’
s
f
u
ll
p
o
ten
tial.
Ou
r
C
NN
m
o
d
el
’
s
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
,
with
a
n
ac
cu
r
ac
y
o
f
0
.
9
5
0
an
d
an
AUC
o
f
0
.
9
2
,
s
u
r
p
ass
es
KNN
-
b
ased
m
eth
o
d
s
,
co
m
p
lex
h
y
b
r
i
d
m
o
d
els l
ik
e
Ma
l
Net,
an
d
f
ea
tu
r
e
-
in
ten
s
iv
e
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es.
Ach
iev
in
g
th
ese
r
esu
lts
th
r
o
u
g
h
s
im
p
ler
,
y
et
ef
f
ec
tiv
e,
h
y
p
er
p
ar
am
eter
tu
n
in
g
co
n
f
ir
m
s
o
u
r
h
y
p
o
th
esis
th
at
th
is
ap
p
r
o
ac
h
wo
u
ld
d
eliv
er
h
ig
h
e
r
p
r
ec
is
io
n
an
d
ac
c
u
r
ac
y
with
o
u
t
r
eq
u
ir
in
g
ex
ten
s
iv
e
p
r
e
-
p
r
o
ce
s
s
in
g
o
r
c
o
m
p
lex
co
n
f
ig
u
r
atio
n
s
.
T
h
e
em
p
ir
ical
r
esu
lts
v
alid
ate
o
u
r
m
eth
o
d
o
l
o
g
y
,
s
h
o
win
g
th
at
o
u
r
wo
r
k
o
u
tp
er
f
o
r
m
s
r
elate
d
m
eth
o
d
o
l
o
g
ies in
b
o
th
ac
cu
r
ac
y
an
d
ef
f
icien
cy
,
m
ak
in
g
it th
e
m
o
s
t r
eliab
le
ap
p
r
o
ac
h
f
o
r
m
a
lwar
e
d
etec
tio
n
as
h
y
p
o
th
esized
.
T
h
e
a
p
p
licatio
n
s
an
d
m
eth
o
d
s
d
e
v
elo
p
ed
t
h
r
o
u
g
h
th
is
wo
r
k
ar
e
p
o
is
e
d
f
o
r
ad
o
p
tio
n
b
y
r
esear
ch
er
s
wh
o
ar
e
s
ee
k
in
g
r
ea
d
y
-
to
-
im
p
lem
en
t
s
o
lu
tio
n
s
,
with
o
u
t
th
e
n
ee
d
f
o
r
f
u
r
th
er
en
er
g
y
-
i
n
ten
s
iv
e
in
v
esti
g
atio
n
s
to
en
h
a
n
ce
alg
o
r
ith
m
p
er
f
o
r
m
a
n
ce
.
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:
2
5
0
2
-
4
7
52
E
n
h
a
n
ci
n
g
m
a
lw
a
r
e
d
etec
tio
n
ca
p
a
b
ilit
ies u
s
in
g
d
ee
p
lea
r
n
i
n
g
w
ith
a
d
va
n
ce
d
…
(
Wa
lid
E
l Mo
u
h
ta
d
i
)
993
5.
CO
NCLU
SI
O
N
Ou
r
co
n
tr
ib
u
tio
n
to
th
e
ev
o
lu
tio
n
o
f
d
ee
p
lear
n
in
g
al
g
o
r
ith
m
s
ANN,
C
NN,
a
n
d
R
NN
h
as
u
n
d
er
s
co
r
e
d
th
e
tr
an
s
f
o
r
m
ativ
e
p
o
wer
o
f
h
y
p
er
p
a
r
am
eter
tu
n
in
g
.
T
h
is
p
r
o
ce
s
s
em
er
g
ed
a
s
a
u
n
if
y
in
g
f
o
r
ce
,
g
u
id
in
g
ea
c
h
alg
o
r
ith
m
to
wa
r
d
en
h
an
ce
d
p
er
f
o
r
m
a
n
ce
b
y
ad
d
r
ess
in
g
th
e
u
n
iq
u
e
ch
allen
g
es
in
h
er
en
t
i
n
d
if
f
er
en
t
d
atasets
.
T
h
e
s
ig
n
if
ican
ce
o
f
cu
s
to
m
izatio
n
in
m
o
d
el
tr
ain
in
g
was
ev
id
en
t,
as
it
en
ab
led
th
ese
m
o
d
els
to
ac
h
iev
e
s
u
p
er
io
r
a
cc
u
r
ac
y
an
d
p
r
ec
is
io
n
.
T
h
e
d
iv
er
g
en
ce
in
p
er
f
o
r
m
a
n
ce
am
o
n
g
th
e
alg
o
r
ith
m
s
b
ec
am
e
clea
r
,
with
C
NN
s
tan
d
in
g
o
u
t
d
u
e
t
o
its
ex
ce
p
tio
n
al
ab
ilit
y
to
ca
p
tu
r
e
in
tr
icate
p
atter
n
s
,
d
em
o
n
s
tr
atin
g
a
n
u
a
n
ce
d
s
tr
en
g
th
d
is
tin
ct
f
r
o
m
ANN
a
n
d
R
NN.
Alth
o
u
g
h
ANN
a
n
d
R
NN
s
h
o
wed
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
,
C
NN
ab
ilit
y
t
o
ex
ce
l
in
m
alwa
r
e
d
etec
tio
n
task
s
r
e
af
f
ir
m
ed
its
p
o
s
itio
n
as
th
e
m
o
s
t
r
o
b
u
s
t
m
o
d
el
in
th
is
co
n
tex
t.
T
h
e
iter
ativ
e
n
atu
r
e
o
f
h
y
p
er
p
ar
a
m
eter
tu
n
i
n
g
h
ig
h
lig
h
ted
th
e
ad
ap
tab
ilit
y
an
d
r
esp
o
n
s
iv
en
ess
o
f
th
ese
d
ee
p
ea
r
n
in
g
m
o
d
els,
co
n
tr
ib
u
tin
g
to
th
eir
o
v
er
all
p
r
ed
ictiv
e
ca
p
ab
ilit
ies.
L
o
o
k
in
g
ah
ea
d
,
f
u
tu
r
e
wo
r
k
will
in
v
o
lv
e
co
m
b
i
n
in
g
o
u
r
r
ec
en
t
co
n
t
r
ib
u
tio
n
s
f
o
c
u
s
ed
o
n
r
ef
in
i
n
g
m
alwa
r
e
d
etec
tio
n
u
s
in
g
en
h
an
ce
d
m
ac
h
i
n
e
lea
r
n
in
g
alg
o
r
ith
m
s
an
d
h
y
p
er
p
ar
am
eter
tu
n
in
g
with
th
is
r
e
s
ea
r
ch
to
c
r
ea
te
a
co
m
p
r
eh
e
n
s
iv
e
an
ti
-
m
alwa
r
e
s
o
lu
tio
n
.
T
h
is
s
o
lu
tio
n
will
in
co
r
p
o
r
ate
th
e
a
r
ch
itectu
r
e
o
u
tlin
ed
,
wh
er
e
d
ata
s
am
p
les
u
n
d
er
g
o
p
r
e
p
r
o
ce
s
s
in
g
an
d
class
if
icatio
n
b
ased
o
n
th
eir
ty
p
e
(
b
y
te
o
r
ass
em
b
ly
)
.
B
y
lev
er
ag
in
g
tech
n
iq
u
es
lik
e
o
p
co
d
e
an
al
y
s
is
f
o
r
ass
em
b
ly
co
d
e
an
d
m
u
lti
-
an
tiv
ir
u
s
v
alid
atio
n
,
th
i
s
ap
p
r
o
ac
h
aim
s
to
en
h
an
ce
th
e
ac
c
u
r
ac
y
an
d
p
r
ec
is
io
n
o
f
d
etec
tio
n
.
T
h
is
co
m
p
r
e
h
en
s
iv
e
a
n
ti
-
m
alwa
r
e
f
r
am
ewo
r
k
co
u
l
d
s
ig
n
if
ican
tly
co
n
t
r
ib
u
te
t
o
f
u
tu
r
e
an
tiv
ir
u
s
an
d
en
d
p
o
in
t
d
e
tectio
n
an
d
r
esp
o
n
s
e
(
E
DR
)
s
y
s
tem
s
,
o
f
f
er
in
g
a
r
o
b
u
s
t
d
ef
e
n
s
e
m
ec
h
an
is
m
a
g
ain
s
t
ev
o
lv
in
g
t
h
r
ea
ts
.
Ad
d
iti
o
n
ally
,
ex
p
lo
r
in
g
en
s
em
b
le
m
eth
o
d
s
to
co
m
b
in
e
th
e
s
tr
en
g
th
s
o
f
m
u
ltip
le
alg
o
r
ith
m
s
an
d
lev
er
ag
in
g
tr
an
s
f
er
lear
n
in
g
with
p
r
e
-
tr
ain
e
d
m
o
d
els
will
b
e
cr
u
cial
in
ad
v
a
n
cin
g
th
e
f
ield
.
E
m
p
h
asis
o
n
in
ter
p
r
etab
ilit
y
an
d
r
ea
l
-
wo
r
l
d
ap
p
licab
ilit
y
r
e
m
ain
s
ess
e
n
tial
f
o
r
wid
esp
r
ea
d
ad
o
p
tio
n
,
an
d
co
n
tin
u
o
u
s
iter
atio
n
to
s
tay
ab
r
ea
s
t
o
f
th
e
latest
d
ev
elo
p
m
en
ts
in
Dee
p
L
ea
r
n
in
g
will b
e
k
ey
to
u
n
lo
ck
i
n
g
n
ew
p
o
s
s
ib
ilit
ies.
RE
F
E
R
E
NC
E
S
[
1
]
C
.
D
o
X
u
a
n
a
n
d
M
.
H
.
D
a
o
,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
A
P
T
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
c
o
m
b
i
n
e
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
3
,
n
o
.
2
0
,
p
p
.
1
3
2
5
1
–
1
3
2
6
4
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
021
-
0
5
9
5
2
-
5.
[
2
]
D
a
t
a
m
i
n
i
n
g
.
S
TY
LU
S
P
u
b
l
i
s
h
i
n
g
,
2
0
1
7
.
[
3
]
S
.
K
.
S
a
h
a
y
,
A
.
S
h
a
r
ma,
a
n
d
H
.
R
a
t
h
o
r
e
,
“
Ev
o
l
u
t
i
o
n
o
f
M
a
l
w
a
r
e
a
n
d
i
t
s
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
i
n
Ad
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
2
0
2
0
,
p
p
.
1
3
9
–
1
5
0
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
13
-
7
1
6
6
-
0
_
1
4
.
[
4
]
J.
S
c
o
t
t
,
“
S
i
g
n
a
t
u
r
e
b
a
se
d
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
i
s
d
e
a
d
,
”
C
y
b
e
rs
e
c
u
ri
t
y
T
h
i
n
k
T
a
n
k
,
I
n
st
i
t
u
t
e
f
o
r
C
r
i
t
i
c
a
l
I
n
f
ra
s
t
r
u
c
t
u
re
T
e
c
h
n
o
l
o
g
y
,
p
p
.
1
–
1
5
,
2
0
1
7
.
[
5
]
M
.
N
a
s
e
e
r
e
t
a
l
,
"
M
a
l
w
a
r
e
D
e
t
e
c
t
i
o
n
:
I
ssu
e
s
a
n
d
C
h
a
l
l
e
n
g
e
s,"
J
o
u
rn
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
r
e
n
c
e
S
e
r
i
e
s
,
v
o
l
.
1
8
0
7
,
n
o
.
1
,
p
.
0
1
2
0
1
1
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
8
0
7
/
1
/
0
1
2
0
1
1
.
[
6
]
R
.
G
u
t
i
e
r
r
e
z
,
W
.
V
i
l
l
e
g
a
s
-
C
h
,
L.
N
a
r
a
n
j
o
G
o
d
o
y
,
A
.
M
e
r
a
-
N
a
v
a
r
r
e
t
e
,
a
n
d
S
.
Lu
j
á
n
-
M
o
r
a
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
r
e
a
l
-
t
i
m
e
a
u
t
o
ma
t
i
c
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
0
7
7
4
2
–
1
0
7
7
5
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
3
6
5
8
8
.
[
7
]
Y
.
F
a
n
,
Y
.
Y
e
,
a
n
d
L.
C
h
e
n
,
“
M
a
l
i
c
i
o
u
s
se
q
u
e
n
t
i
a
l
p
a
t
t
e
r
n
m
i
n
i
n
g
f
o
r
a
u
t
o
m
a
t
i
c
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
E
x
p
e
rt
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
2
,
p
p
.
1
6
–
2
5
,
J
u
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
6
.
0
1
.
0
0
2
.
[
8
]
H
.
S
.
G
a
l
a
l
,
Y
.
B
.
M
a
h
d
y
,
a
n
d
M
.
A
.
A
t
i
e
a
,
“
B
e
h
a
v
i
o
r
-
b
a
se
d
f
e
a
t
u
r
e
s
mo
d
e
l
f
o
r
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Vi
ro
l
o
g
y
a
n
d
H
a
c
k
i
n
g
T
e
c
h
n
i
q
u
e
s
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
5
9
–
6
7
,
M
a
y
2
0
1
6
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
4
1
6
-
015
-
0
2
4
4
-
0.
[
9
]
A
.
V
.
K
o
z
a
c
h
o
k
a
n
d
V
.
I
.
K
o
z
a
c
h
o
k
,
“
C
o
n
s
t
r
u
c
t
i
o
n
a
n
d
e
v
a
l
u
a
t
i
o
n
o
f
t
h
e
n
e
w
h
e
u
r
i
s
t
i
c
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
me
c
h
a
n
i
sm
b
a
se
d
o
n
e
x
e
c
u
t
a
b
l
e
f
i
l
e
s
s
t
a
t
i
c
a
n
a
l
y
si
s
,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
V
i
ro
l
o
g
y
a
n
d
H
a
c
k
i
n
g
T
e
c
h
n
i
q
u
e
s
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
2
2
5
–
2
3
1
,
A
u
g
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
S
1
1
4
1
6
-
0
1
7
-
0
3
0
9
-
3
/
M
E
TR
I
C
S
.
[
1
0
]
A
.
I
j
a
z
e
t
a
l
.
,
“
I
n
n
o
v
a
t
i
v
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
a
n
d
B
i
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
7
,
n
o
.
1
,
2
0
2
4
.
[
1
1
]
F
.
N
a
w
sh
i
n
,
R
.
G
a
d
,
D
.
U
n
a
l
,
A
.
K
.
A
l
-
A
l
i
,
a
n
d
P
.
N
.
S
u
g
a
n
t
h
a
n
,
“
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
f
o
r
m
o
b
i
l
e
c
o
mp
u
t
i
n
g
u
s
i
n
g
s
e
c
u
r
e
a
n
d
p
r
i
v
a
c
y
-
p
r
e
ser
v
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
:
A
c
o
mp
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
7
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
4
.
1
0
9
2
3
3
.
[
1
2
]
J.
Q
i
u
,
J.
Z
h
a
n
g
,
W
.
Lu
o
,
L.
P
a
n
,
S
.
N
e
p
a
l
,
a
n
d
Y
.
X
i
a
n
g
,
“
A
s
u
r
v
e
y
o
f
a
n
d
r
o
i
d
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
w
i
t
h
d
e
e
p
n
e
u
r
a
l
m
o
d
e
l
s
,”
AC
M
C
o
m
p
u
t
i
n
g
S
u
rv
e
y
s
,
v
o
l
.
5
3
,
n
o
.
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
1
7
9
7
8
.
[
1
3
]
F
.
X
i
a
o
,
Z.
Li
n
,
Y
.
S
u
n
,
a
n
d
Y
.
M
a
,
“
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
o
f
b
e
h
a
v
i
o
r
g
r
a
p
h
s
,
”
M
a
t
h
e
m
a
t
i
c
a
l
Pro
b
l
e
m
s
i
n
En
g
i
n
e
e
ri
n
g
,
n
o
.
1
,
J
a
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
9
/
8
1
9
5
3
9
5
.
[
1
4
]
S
.
J.
K
a
t
t
a
m
u
r
i
,
R
.
K
.
V
.
P
e
n
m
a
t
s
a
,
S
.
C
h
a
k
r
a
v
a
r
t
y
,
a
n
d
V
.
S
.
P
.
M
a
d
a
b
a
t
h
u
l
a
,
“
S
w
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
e
d
t
o
P
E
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
t
o
w
a
r
d
s
c
y
b
e
r
t
h
r
e
a
t
i
n
t
e
l
l
i
g
e
n
c
e
,
”
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
1
2
,
n
o
.
2
,
Jan
.
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
0
2
0
3
4
2
.
[
1
5
]
H
.
B
o
s
t
a
n
i
a
n
d
V
.
M
o
o
n
sa
my
,
“
E
v
a
d
e
D
r
o
i
d
:
A
p
r
a
c
t
i
c
a
l
e
v
a
s
i
o
n
a
t
t
a
c
k
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
b
l
a
c
k
-
b
o
x
A
n
d
r
o
i
d
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
ri
t
y
,
v
o
l
.
1
3
9
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
s
e
.
2
0
2
3
.
1
0
3
6
7
6
.
[
1
6
]
M
.
M
.
A
b
u
a
l
h
a
j
,
A
.
A
.
A
b
u
-
S
h
a
r
e
h
a
,
Q
.
Y
.
S
h
a
m
b
o
u
r
,
S
.
N
.
A
l
-
K
h
a
t
i
b
,
a
n
d
M
.
O
.
H
i
a
r
i
,
“
T
u
n
i
n
g
t
h
e
k
v
a
l
u
e
i
n
k
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
s
f
o
r
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
I
A
ES
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
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
3
,
n
o
.
2
,
p
p
.
2
2
7
5
–
2
2
8
2
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
2
.
p
p
2
2
7
5
-
2
2
8
2
.
[
1
7
]
J.
Y
a
n
,
Y
.
Q
i
,
a
n
d
Q
.
R
a
o
,
“
D
e
t
e
c
t
i
n
g
M
a
l
w
a
r
e
w
i
t
h
a
n
e
n
sem
b
l
e
me
t
h
o
d
b
a
se
d
o
n
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,”
S
e
c
u
ri
t
y
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
rk
s
,
p
p
.
1
–
1
6
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
8
/
7
2
4
7
0
9
5
.
[
1
8
]
E.
K
A
V
A
LC
I
Y
I
LM
A
Z
a
n
d
H
.
B
A
K
I
R
,
“
H
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
n
i
n
g
a
n
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
me
t
h
o
d
s
f
o
r
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,”
Po
l
i
t
e
k
n
i
k
D
e
r
g
i
si
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
3
4
3
–
3
5
3
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
2
3
3
9
/
p
o
l
i
t
e
k
n
i
k
.
1
2
4
3
8
8
1
.
[
1
9
]
F
.
T
.
A
LG
o
r
a
i
n
a
n
d
J
.
A
.
C
l
a
r
k
,
“
B
a
y
e
si
a
n
h
y
p
e
r
-
p
a
r
a
m
e
t
e
r
o
p
t
i
m
i
sa
t
i
o
n
f
o
r
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
1
0
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
1
1
0
1
6
4
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
8
5
-
9
9
4
994
[
2
0
]
S
.
S
.
La
d
.
a
n
d
A
.
C
.
A
d
a
m
u
t
h
e
,
“
I
mp
r
o
v
e
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
st
a
t
i
c
P
E
F
i
l
e
s
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
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
C
o
m
p
u
t
e
r
N
e
t
w
o
rk
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
ri
t
y
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
1
4
–
2
6
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
5
8
1
5
/
i
j
c
n
i
s
.
2
0
2
2
.
0
2
.
0
2
.
[
2
1
]
A
.
D
j
e
n
n
a
,
A
.
B
o
u
r
i
d
a
n
e
,
S
.
R
u
b
a
b
,
a
n
d
I
.
M
.
M
a
r
o
u
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
b
a
se
d
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
a
n
a
l
y
si
s,
a
n
d
mi
t
i
g
a
t
i
o
n
,
”
S
y
m
m
e
t
ry
,
v
o
l
.
1
5
,
n
o
.
3
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m
1
5
0
3
0
6
7
7
.
[
2
2
]
“
K
a
g
g
l
e
:
y
o
u
r
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
a
t
a
s
c
i
e
n
c
e
c
o
mm
u
n
i
t
y
.
”
A
c
c
e
sse
d
:
A
u
g
.
1
1
,
2
0
2
4
.
[
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
/
.
[
2
3
]
“
V
i
r
u
s
To
t
a
l
-
H
o
me
.
”
A
c
c
e
sse
d
:
A
u
g
.
1
1
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
v
i
r
u
st
o
t
a
l
.
c
o
m/
g
u
i
/
h
o
me
/
u
p
l
o
a
d
.
[
2
4
]
“
V
i
r
u
sS
h
a
r
e
.
c
o
m.
”
A
c
c
e
ss
e
d
:
A
u
g
.
1
1
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
v
i
r
u
ss
h
a
r
e
.
c
o
m/
a
b
o
u
t
.
[
2
5
]
H
.
H
.
A
l
-
K
h
s
h
a
l
i
a
n
d
M
.
I
l
y
a
s
,
“
I
mp
a
c
t
o
f
p
o
r
t
a
b
l
e
e
x
e
c
u
t
a
b
l
e
h
e
a
d
e
r
f
e
a
t
u
r
e
s
o
n
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
a
c
c
u
r
a
c
y
,
”
C
o
m
p
u
t
e
rs
,
Ma
t
e
r
i
a
l
s
a
n
d
C
o
n
t
i
n
u
a
,
v
o
l
.
7
4
,
n
o
.
1
,
p
p
.
1
5
3
–
1
7
8
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc.
2
0
2
3
.
0
3
2
1
8
2
.
[
2
6
]
E.
S
.
A
l
o
m
a
r
i
e
t
a
l
.
,
“
M
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
c
o
r
r
e
l
a
t
i
o
n
-
b
a
s
e
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
”
S
y
m
m
e
t
r
y
,
v
o
l
.
1
5
,
n
o
.
1
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
sy
m
1
5
0
1
0
1
2
3
.
[
2
7
]
D
.
Ö
.
Ş
a
h
i
n
,
O
.
E.
K
u
r
a
l
,
S
.
A
k
l
e
y
l
e
k
,
a
n
d
E.
K
ı
l
ı
ç
,
“
A
n
o
v
e
l
p
e
r
mi
ss
i
o
n
-
b
a
s
e
d
A
n
d
r
o
i
d
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
u
s
i
n
g
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
b
a
s
e
d
o
n
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
5
,
n
o
.
7
,
p
p
.
4
9
0
3
–
4
9
1
8
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
1
-
0
5
8
7
5
-
1.
[
2
8
]
K
.
S
h
a
u
k
a
t
,
S
.
Lu
o
,
a
n
d
V
.
V
a
r
a
d
h
a
r
a
j
a
n
,
“
A
n
o
v
e
l
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
sed
a
p
p
r
o
a
c
h
f
o
r
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
En
g
i
n
e
e
ri
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
2
2
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
3
.
1
0
6
0
3
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Wa
li
d
El
Mo
u
h
t
a
d
i
is
a
P
h
.
D.
stu
d
e
n
t
a
t
LaST
I
Lab
o
ra
to
r
y
,
ENS
A
Kh
o
u
ri
b
g
a
,
p
a
rt
o
f
S
u
lt
a
n
M
o
u
la
y
S
li
m
a
n
e
Un
iv
e
rsity
,
M
o
r
o
c
c
c
o
,
sin
c
e
2
0
2
2
.
He
wo
rk
s
a
s
M
a
n
a
g
e
r
G
lo
b
a
l
S
OC
(S
e
c
u
rit
y
O
p
e
ra
ti
o
n
s
Ce
n
ter),
M
o
r
o
c
c
o
,
si
n
c
e
2
0
2
4
.
H
e
re
c
e
iv
e
d
In
g
é
n
ieu
r
d
’Ét
a
t
in
Ne
two
rk
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
s
En
g
i
n
e
e
rin
g
,
fro
m
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
s
(Éco
le
Na
ti
o
n
a
le
d
e
s
S
c
ien
c
e
s
Ap
p
li
q
u
é
e
s
d
e
Kh
o
u
ri
b
g
a
),
fr
o
m
S
u
lt
a
n
M
o
u
lay
S
l
ima
n
e
Un
iv
e
rsity
,
sin
c
e
2
0
2
1
.
His
re
se
a
e
c
h
in
tere
st
in
c
l
u
d
e
s
c
y
b
e
r
se
c
u
ri
ty
,
m
a
lwa
re
a
n
a
ly
sis,
d
ig
i
tal
fo
re
n
sic
s,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
d
e
e
p
lea
rn
i
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
wa
li
d
.
e
lmo
u
h
tad
i@
u
sm
s.a
c
.
m
a
.
Ya
ss
in
e
Ma
leh
is
a
n
a
ss
o
c
iat
e
p
ro
fe
ss
o
r
o
f
c
y
b
e
rse
c
u
rit
y
a
n
d
IT
g
o
v
e
rn
a
n
c
e
a
t
S
u
lt
a
n
M
o
u
lay
S
li
m
a
n
e
U
n
iv
e
rsi
ty
,
M
o
r
o
c
c
o
,
si
n
c
e
2
0
1
9
.
He
is
a
d
o
u
b
le
P
h
.
D
.
i
n
c
o
m
p
u
ter
sc
ien
c
e
s
a
n
d
IT
m
a
n
a
g
e
m
e
n
t.
He
is
th
e
fo
u
n
d
in
g
c
h
a
ir
o
f
IEE
E
Co
n
su
l
tan
t
Ne
two
rk
M
o
r
o
c
c
o
a
n
d
fo
u
n
d
in
g
p
re
sid
e
n
t
o
f
th
e
Afric
a
n
Re
se
a
r
c
h
Ce
n
ter
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
n
d
Cy
b
e
rse
c
u
rit
y
.
He
is
a
se
n
i
o
r
m
e
m
b
e
r
o
f
IEE
E
He
h
a
s
p
u
b
li
sh
e
d
o
v
e
r
th
a
n
1
4
0
p
a
p
e
rs
(in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls,
b
o
o
k
c
h
a
p
ters
a
n
d
c
o
n
fe
re
n
c
e
s/wo
rk
sh
o
p
s),
2
7
e
d
i
ted
b
o
o
k
s,
a
n
d
5
a
u
th
o
re
d
b
o
o
k
s.
He
is
th
e
e
d
it
o
r
-
in
-
c
h
ief
o
f
t
h
e
In
tern
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
In
f
o
rm
a
ti
o
n
S
e
c
u
rit
y
a
n
d
P
ri
v
a
c
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
y
.
m
a
leh
@u
sm
s.m
a
.
S
o
u
f
y
a
n
e
Mo
u
n
ir
is
a
ss
o
c
i
a
te
p
ro
fe
ss
o
r
in
t
h
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
s
o
f
S
u
lt
a
n
M
o
u
lay
S
li
m
a
n
e
S
li
m
a
n
e
,
Be
n
i
M
e
ll
a
l,
M
o
r
o
c
c
o
,
sin
c
e
2
0
1
4
.
He
g
o
t
h
is
Ph
.
D
.
in
e
lec
tro
n
ics
a
n
d
tele
c
o
m
m
u
n
ica
ti
o
n
,
fr
o
m
Un
i
v
e
rsity
Ha
ss
a
n
1
st
,
M
o
ro
c
c
o
.
His
re
se
a
rc
h
i
s
m
u
lt
id
isc
ip
li
n
a
r
y
t
h
a
t
fo
c
u
se
s
o
n
t
e
lec
o
m
m
u
n
ica
ti
o
n
s,
V
o
IP
,
sig
n
a
l
p
r
o
c
e
ss
in
g
,
e
m
b
e
d
d
e
d
sy
ste
m
s
a
n
d
c
y
b
e
r
se
c
u
rit
y
.
He
is
a
n
a
c
ti
v
e
m
e
m
b
e
r
o
f
LaST
I
Lab
o
ra
to
r
y
,
ENS
A
Kh
o
u
r
ib
g
a
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s.m
o
u
n
ir@u
sm
s.m
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.