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
.
3
,
Ma
r
ch
20
2
5
,
p
p
.
1
6
7
2
~
1
681
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
3
.
pp
1
6
7
2
-
1
6
8
1
1672
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Autom
a
ted
a
dv
er
sa
ria
l det
ection
in
mo
bile app
s usin
g
API
ca
lls
a
nd permiss
io
n
s
Sa
nja
ik
a
nth
E
Va
da
kk
et
hil
So
m
a
na
t
ha
n P
illa
i
1
,
Ro
hith
Va
lla
bh
a
neni
2
,
Sri
niv
a
s
A
V
a
dd
a
di
2
,
Sa
nto
s
h Re
dd
y
Ad
du
la
2
,
B
h
uv
a
nes
h Ana
ntha
n
3
1
S
c
h
o
o
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
y
o
f
N
o
r
t
h
D
a
k
o
t
a
,
G
r
a
n
d
F
o
r
k
s,
U
S
A
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
y
o
f
t
h
e
C
u
m
b
e
r
l
a
n
d
s,
W
i
l
l
i
a
m
sb
u
r
g
,
U
S
A
3
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
P
S
N
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
T
i
r
u
n
e
l
v
e
l
i
,
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
Mar
19
,
2
0
2
4
R
ev
is
ed
Sep
13
,
2
0
2
4
Acc
ep
ted
Oct
7
,
2
0
2
4
An
d
ro
id
m
o
b
i
le
p
h
o
n
e
s
’
g
ro
wi
n
g
p
o
p
u
larit
y
h
a
s
le
d
t
o
d
e
v
e
l
o
p
e
rs
c
re
a
ti
n
g
m
o
re
m
a
li
c
io
u
s
a
p
p
s,
wh
ich
c
a
n
b
e
in
c
lu
d
e
d
in
t
h
ir
d
-
p
a
rty
a
rc
a
d
e
s
a
s
p
ro
tec
ted
a
p
p
li
c
a
ti
o
n
s.
De
tec
ti
n
g
th
e
se
m
a
lwa
r
e
a
p
p
li
c
a
ti
o
n
s
is
c
h
a
ll
e
n
g
i
n
g
d
u
e
t
o
ti
m
e
-
c
o
n
s
u
m
in
g
a
n
d
h
i
g
h
-
c
o
st
tec
h
n
iq
u
e
s.
Th
is
stu
d
y
p
ro
p
o
se
s
a
ro
b
u
st
d
e
e
p
lea
rn
in
g
(DL)
m
o
d
e
l
fo
r
d
e
tec
ti
n
g
a
d
v
e
rsa
rial
th
i
rd
-
p
a
rty
a
p
p
s
u
sin
g
a
d
a
p
ti
v
e
fe
a
tu
re
lea
rn
in
g
.
T
h
e
stra
teg
y
in
v
o
l
v
e
s
p
re
p
ro
c
e
ss
in
g
ra
w
a
p
k
fil
e
s,
e
x
trac
ti
n
g
p
e
rm
issio
n
b
e
h
a
v
io
ra
l
fe
a
tu
re
s,
a
n
d
u
si
n
g
t
h
e
p
ro
p
o
se
d
sp
a
ti
a
l
d
r
o
p
o
u
t
-
a
ss
is
ted
c
o
n
v
o
lu
t
io
n
a
l
a
u
to
e
n
c
o
d
e
r
(S
D_
C
o
n
v
AE)
m
o
d
e
l
to
d
e
term
in
e
if
th
e
a
p
p
is
b
e
n
i
g
n
o
r
m
a
li
g
n
a
n
t.
Th
e
a
p
p
r
o
a
c
h
is
sim
u
l
a
ted
u
sin
g
a
P
y
t
h
o
n
t
o
o
l
a
n
d
a
ss
e
ss
e
d
u
sin
g
v
a
ri
o
u
s
m
e
a
su
re
s
li
k
e
a
c
c
u
ra
c
y
,
re
c
a
ll
,
we
ig
h
ted
F
-
sc
o
re
(W
-
F
S
)
,
fa
lse
d
isc
o
v
e
ry
ra
te
(F
DR)
,
a
n
d
k
a
p
p
a
c
o
e
fficie
n
t
.
Th
e
o
v
e
ra
ll
a
c
c
u
ra
c
ies
a
c
h
iev
e
d
b
y
t
h
e
d
e
v
e
l
o
p
e
d
tec
h
n
i
q
u
e
s
a
re
a
b
o
u
t
9
9
.
6
%
a
n
d
9
9
%
f
o
r
d
e
tec
ti
n
g
b
e
n
ig
n
a
n
d
m
a
li
g
n
a
n
t
a
p
p
s,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
An
d
r
o
id
m
o
b
ile
ap
p
s
Ap
p
licatio
n
p
r
o
g
r
am
m
in
g
in
ter
f
ac
e
ca
lls
Dee
p
lear
n
in
g
Per
m
is
s
io
n
SD_
C
o
n
v
AE
m
o
d
el
T
h
ir
d
-
p
a
r
ty
attac
k
s
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
:
San
jaik
an
th
E
Vad
ak
k
eth
il
So
m
an
ath
an
Pil
lai
Sch
o
o
l o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
an
d
C
o
m
p
u
ter
Scien
ce
,
Un
iv
er
s
ity
o
f
No
r
th
Dak
o
ta
Gr
an
d
Fo
r
k
s
,
USA
E
m
ail:
s
.
ev
ad
ak
k
eth
il@
u
n
d
.
e
d
u
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
ay
-
to
-
d
a
y
life
,
s
m
ar
t
p
h
o
n
es
ar
e
p
lay
in
g
an
ess
en
tial
p
ar
t
as
th
ey
ca
n
p
r
o
v
i
d
e
s
im
ilar
a
d
v
an
tag
es
as
d
esk
to
p
co
m
p
u
ter
s
s
u
ch
as
o
n
lin
e
s
h
o
p
p
in
g
,
o
n
lin
e
b
an
k
i
n
g
,
web
s
ite
b
r
o
wsi
n
g
,
an
d
s
o
cial
n
etwo
r
k
in
g
[
1
]
.
Mo
r
eo
v
er
,
a
d
d
itio
n
al
f
ea
tu
r
e
s
lik
e
lo
ca
tio
n
s
er
v
ices,
m
ess
ag
in
g
f
ac
ilit
ies,
u
p
d
atin
g
d
a
ta
an
d
wo
r
ld
wid
e
ac
ce
s
s
.
Ho
wev
er
,
th
is
f
ea
tu
r
es
an
d
f
u
n
ctio
n
alities
m
ak
es
th
e
s
m
ar
tp
h
o
n
e
m
o
r
e
p
r
o
n
e
to
m
alwa
r
e
attac
k
s
[
2
]
.
As
a
r
esu
lt,
th
e
th
ir
d
-
p
ar
t
d
e
v
elo
p
er
s
u
tili
ze
s
th
ese
ad
v
an
tag
es
b
y
f
etch
in
g
u
s
er
co
n
f
id
en
tial
in
f
o
r
m
atio
n
,
ac
ce
s
s
in
g
ch
ar
g
e
r
s
f
r
o
m
th
e
u
s
er
s
with
ex
clu
s
i
o
n
s
h
o
r
t
m
ess
ag
in
g
s
er
v
ices
(
SMS)
an
d
ca
lls
.
I
t
is
d
elib
er
ated
th
at
m
o
r
e
th
an
6
5
0
K
m
o
b
ile
ap
p
licatio
n
s
(
ap
p
s
)
ar
e
av
ailab
le
o
n
o
f
f
icial
an
d
r
o
id
p
latf
o
r
m
[
3
]
.
Mo
r
eo
v
er
,
th
e
r
ep
o
r
ts
f
r
o
m
F
o
r
tin
et
en
co
m
p
ass
es
th
at
m
o
r
e
th
an
2
K
t
h
ir
d
-
p
ar
ty
a
p
p
s
ar
e
p
r
esen
ted
f
r
o
m
8
0
d
iv
er
s
e
f
am
ilies
.
T
h
e
n
u
m
b
e
r
o
f
ad
v
er
s
ar
ial
ap
p
s
k
ee
p
s
o
n
i
n
cr
ea
s
in
g
b
ec
au
s
e
o
f
o
p
en
s
o
u
r
ce
an
d
g
en
e
r
o
u
s
ly
co
n
tem
p
lated
a
n
d
r
o
i
d
cu
s
to
m
i
ze
d
m
an
u
f
ac
tu
r
es [
4
]
.
T
h
e
ev
o
lv
in
g
o
f
n
ew
m
alwa
r
e
f
am
ilies
m
ak
es
th
e
tech
n
ician
s
d
if
f
icu
lt
in
d
etec
tin
g
th
ir
d
-
p
ar
t
attac
k
s
u
s
in
g
co
n
v
en
tio
n
al
m
ec
h
a
n
is
m
s
.
So
m
e
co
m
m
o
n
ch
allen
g
e
s
ar
e
r
ep
o
r
ted
i
n
[
5
]
s
u
ch
as
f
ailu
r
e
in
v
is
ib
ilit
y
o
v
er
m
o
b
ile
p
latf
o
r
m
s
,
n
etwo
r
k
an
o
n
y
m
ity
,
r
eso
u
r
ce
c
o
n
s
tr
ictio
n
s
,
an
d
r
eq
u
i
r
es
cu
s
to
m
iz
ed
ap
p
s
w
h
ich
u
s
es
r
em
o
te
ca
p
ab
ilit
ies.
Sev
er
al
ex
is
tin
g
s
tu
d
ies
u
tili
ze
d
p
er
m
is
s
io
n
to
d
eter
m
in
e
th
e
th
ir
d
-
p
a
r
ty
b
eh
av
io
r
s
o
f
an
ap
p
licatio
n
[
6
]
.
Ho
wev
er
,
it
is
co
m
p
lex
to
d
ec
lar
e
th
at
th
e
p
er
m
is
s
io
n
s
b
ei
n
g
ap
p
lie
d
o
n
th
e
ap
p
licatio
n
co
d
e.
T
h
er
e
is
s
o
m
e
o
t
h
er
t
r
ad
itio
n
a
l
tech
n
iq
u
e
th
at
u
s
es
o
n
ly
AP
I
ca
ll
d
etails
to
ex
ce
r
p
t
f
ea
tu
r
es
u
s
in
g
f
r
eq
u
e
n
cy
co
m
p
o
n
en
ts
o
n
a
lar
g
er
d
atab
ase
[
7
]
.
B
u
t
th
ese
tech
n
iq
u
es
n
ec
ess
itates
ad
ap
tiv
e
f
ea
tu
r
e
l
ea
r
n
in
g
ca
p
ab
ilit
y
to
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
A
u
to
ma
ted
a
d
ve
r
s
a
r
ia
l d
etec
tio
n
in
mo
b
ile
a
p
p
s
b
a
s
ed
…
(
S
a
n
ja
ika
n
t
h
E
V
a
d
a
kk
eth
il S
o
m
a
n
a
th
a
n
P
illa
i
)
1673
lear
n
th
e
m
alwa
r
e
f
ea
tu
r
es
ac
cu
r
ately
[
8
]
.
No
wad
ay
s
,
ar
tifi
cial
in
tellig
en
ce
(
AI
)
b
ased
d
ee
p
lear
n
i
n
g
(
DL
)
tech
n
iq
u
es
ar
e
b
ec
o
m
in
g
m
o
r
e
p
o
p
u
lar
am
o
n
g
th
e
r
esear
ch
er
s
in
id
e
n
tify
in
g
m
alwa
r
e
ap
p
s
b
y
u
tili
zin
g
co
m
p
lex
API
an
d
p
er
m
is
s
io
n
lev
el
f
ea
tu
r
es
o
v
er
l
ar
g
er
d
ata
b
ases
[
9
]
.
Hen
ce
,
th
is
r
esear
ch
p
u
t
f
o
r
th
a
r
o
b
u
s
t
h
y
b
r
id
ize
d
DL
f
r
a
m
ewo
r
k
f
o
r
d
etec
tin
g
th
e
ad
v
er
s
ar
ial
th
ir
d
-
p
ar
ty
ap
p
s
u
s
in
g
co
m
p
lex
m
al
ev
o
len
t f
ea
tu
r
es
.
Mo
tiv
atio
n
:
d
u
e
to
r
ap
id
tech
n
o
lo
g
ical
a
d
v
an
ce
m
en
ts
,
th
er
e
h
av
e
ca
u
s
ed
m
aj
o
r
e
n
h
an
ce
m
en
t
in
th
e
n
etwo
r
k
in
g
ca
p
ab
ilit
ies
an
d
co
m
p
u
tin
g
p
o
wer
o
v
e
r
m
o
b
ile
p
h
o
n
es.
I
n
to
d
a
y
’
s
s
ce
n
ar
io
,
s
m
ar
tp
h
o
n
es,
co
m
p
u
ter
s
an
d
tab
lets
ar
e
co
n
s
id
er
ed
as
th
e
p
o
wer
f
u
l
t
o
o
l
th
at
co
m
b
in
es
lar
g
er
wi
r
eless
b
r
o
ad
ca
s
tin
g
n
etwo
r
k
s
.
Fo
r
p
er
f
o
r
m
in
g
m
u
ltip
le
task
s
,
u
s
er
u
s
e
s
m
o
b
ile
p
h
o
n
es
r
ath
er
th
an
th
e
c
o
n
v
en
tio
n
al
co
m
p
u
ter
s
y
s
tem
s
.
T
h
e
im
p
r
o
v
em
en
ts
in
u
s
er
-
co
m
p
u
ter
in
ter
ac
tio
n
h
av
e
p
av
ed
th
e
way
to
ac
ce
s
s
in
g
m
o
b
ile
d
ev
ices
with
o
u
t
an
y
tech
n
ical
k
n
o
wl
ed
g
e.
As
a
r
esu
lt,
n
u
m
er
o
u
s
ap
p
licatio
n
s
ar
e
p
r
esen
t
th
at
ar
e
ce
n
tr
alize
d
to
ad
v
er
s
ar
ial
r
e
p
o
s
ito
r
ies.
Ho
w
ev
er
,
th
ese
a
p
p
s
ar
e
h
ar
m
f
u
l
th
at
illeg
ally
g
ai
n
s
u
s
er
’
s
co
n
f
i
d
en
tial
in
f
o
r
m
atio
n
b
y
u
s
in
g
API
ca
lls
o
r
p
er
m
is
s
io
n
lev
el
a
p
p
licatio
n
c
o
d
es.
D
etec
tin
g
th
ese
k
in
d
s
o
f
t
h
ir
d
-
p
ar
ty
ap
p
s
is
h
ig
h
ly
ch
allen
g
in
g
an
d
n
ee
d
s
ef
f
ec
tiv
e
tech
n
iq
u
es
f
o
r
lear
n
in
g
th
e
c
o
m
p
lex
m
alev
o
len
t
f
e
atu
r
es.
At
p
r
esen
t,
DL
tech
n
iq
u
es
ar
e
p
r
o
v
id
in
g
f
ascin
atin
g
p
er
f
o
r
m
a
n
ce
in
d
etec
tin
g
ad
v
e
r
s
ar
ial
attac
k
s
o
n
m
o
b
ile
d
ev
ices
.
T
h
ese
k
in
d
s
o
f
m
ajo
r
co
n
ce
r
n
s
m
o
tiv
ate
to
d
ev
elo
p
an
in
n
o
v
ativ
e
DL
m
o
d
el
f
o
r
d
etec
tin
g
th
e
b
en
ig
n
an
d
m
alig
n
an
t m
o
b
ile
ap
p
s
ef
f
ec
tiv
ely
.
T
h
e
c
o
n
tr
ib
u
tio
n
s
ar
e:
−
T
o
d
ev
el
o
p
a
n
in
n
o
v
ativ
e
DL
s
p
atial
d
r
o
p
o
u
t
ass
is
ted
co
n
v
o
lu
tio
n
al
au
to
e
n
co
d
e
r
(
SD
_
C
o
n
v
AE
)
b
ased
tech
n
iq
u
e
to
d
etec
t th
e
th
ir
d
p
ar
ty
m
o
b
ile
a
p
p
s
u
s
in
g
m
alwa
r
e
b
eh
av
i
o
r
al
f
ea
tu
r
es
−
T
o
p
r
e
p
r
o
ce
s
s
th
e
a
n
d
r
o
id
ap
k
f
iles
b
y
p
er
f
o
r
m
in
g
b
i
n
ar
y
v
ec
to
r
co
n
v
er
s
io
n
an
d
to
e
x
tr
ac
t
API
ca
lls
an
d
p
er
m
is
s
io
n
f
ea
tu
r
es p
r
esen
t i
n
th
e
m
o
b
ile
ap
p
licatio
n
s
.
−
T
o
p
r
esen
t a
r
o
b
u
s
t SD_
C
o
n
v
AE
m
o
d
el
to
d
etec
t w
h
eth
er
th
e
m
o
b
ile
ap
p
s
ar
e
n
o
r
m
al
o
r
m
alwa
r
e.
−
T
o
v
alid
ate
th
e
d
ev
el
o
p
ed
m
e
th
o
d
with
v
ar
io
u
s
co
n
v
e
n
tio
n
al
s
ch
em
es
b
y
ass
es
s
in
g
s
ev
er
al
p
er
f
o
r
m
an
ce
m
ea
s
u
r
es
lik
e
ac
cu
r
ac
y
,
f
alse
d
is
co
v
er
y
r
ate
(
FDR
)
,
r
ec
all,
weig
h
ted
F
-
m
ea
s
u
r
e
(
W
-
FM)
an
d
k
ap
p
a
co
ef
f
icien
t f
o
r
id
en
tif
y
in
g
b
o
t
h
n
o
r
m
al
an
d
m
alwa
r
e
ap
p
s
.
Th
e
f
o
r
th
co
m
in
g
s
ec
tio
n
s
ar
e:
t
h
e
wo
r
k
s
ass
o
ciate
d
to
a
n
d
r
o
id
m
alwa
r
e
d
etec
tio
n
u
s
in
g
DL
m
o
d
els
ar
e
in
ter
p
r
eted
in
s
ec
tio
n
2
.
T
h
e
d
ev
el
o
p
ed
m
eth
o
d
o
lo
g
y
is
d
escr
ib
e
d
i
n
s
ec
tio
n
3
.
T
h
e
o
u
tco
m
es
ar
e
d
escr
ib
ed
in
s
ec
tio
n
4
.
T
h
e
c
o
n
clu
s
io
n
o
f
t
h
e
d
e
v
elo
p
ed
s
tu
d
y
is
p
r
esen
ted
in
s
ec
tio
n
5
.
2.
RE
L
AT
E
D
WO
RK
S
Millar
et
a
l
.
[
1
0
]
d
ef
in
e
d
th
e
ze
r
o
-
d
a
y
-
b
ased
m
alev
o
len
t
d
e
tectio
n
in
a
n
d
r
o
id
p
h
o
n
es
u
s
i
n
g
th
e
DL
tech
n
iq
u
e.
I
n
th
is
s
tu
d
y
,
a
p
e
r
m
is
s
io
n
n
eu
r
al
n
etwo
r
k
with
API
ca
lls
co
n
v
o
lu
tio
n
al
n
eu
r
a
l
n
etwo
r
k
s
(
C
NN
)
b
ased
Mu
ltiv
iew
DL
m
o
d
el
was
in
tr
o
d
u
ce
d
t
o
ex
tr
ac
t
a
n
d
s
elec
t
h
an
d
-
c
r
af
ted
f
ea
tu
r
e
s
f
o
r
d
etec
tin
g
th
e
m
alwa
r
e
ap
p
s
.
Fo
r
th
e
e
x
p
er
im
en
tatio
n
p
r
o
ce
s
s
,
f
o
u
r
d
if
f
er
en
t
d
atasets
n
am
ely
Ma
lg
e
n
o
m
e,
d
eb
r
in
,
an
d
AM
D,
an
d
p
u
b
licly
av
ailab
l
e
Go
o
g
le
Play
Sto
r
e
d
atasets
co
n
s
is
tin
g
o
f
m
o
r
e
th
an
2
8
K
s
am
p
les
with
m
alig
n
an
t
an
d
b
e
n
ig
n
ap
p
s
wer
e
co
n
s
id
er
ed
.
I
n
an
aly
zin
g
th
e
s
im
u
latio
n
p
ar
t,
th
e
f
-
m
ea
s
u
r
e
was
co
m
p
u
ted
an
d
c
o
m
p
ar
e
d
with
o
th
er
tech
n
iq
u
es.
Ho
wev
e
r
,
t
h
is
tech
n
iq
u
e
f
ac
es
h
ig
h
d
ata
r
ed
u
n
d
an
c
y
p
r
o
b
lem
s
d
u
e
to
a
lo
w
ef
f
ec
tiv
e
f
ea
tu
r
e
s
elec
tio
n
(
FS
)
s
ch
em
e.
Ma
h
in
d
r
u
an
d
San
g
al
[
1
1
]
p
u
t
f
o
r
th
FS
with
m
ac
h
in
e
lear
n
in
g
(
ML
)
-
b
ased
d
etec
tio
n
s
c
h
em
es
f
o
r
an
aly
zin
g
m
alev
o
len
t
ap
p
s
ac
c
u
r
ately
.
I
n
itially
,
API
ca
lls
-
b
a
s
ed
f
ea
tu
r
es
wer
e
ex
tr
ac
te
d
an
d
s
elec
ted
f
r
o
m
th
e
an
d
r
o
id
ap
k
f
iles
.
T
h
en
,
th
e
least
s
q
u
ar
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
L
SS
VM
)
tech
n
iq
u
e
was
in
tr
o
d
u
ce
d
to
id
en
tify
wh
eth
e
r
th
e
a
p
p
s
wer
e
th
ir
d
-
p
a
r
ty
o
r
n
o
t.
Fo
r
th
e
e
x
p
er
im
en
tatio
n
p
r
o
ce
s
s
,
m
o
r
e
th
an
2
lak
h
a
n
d
r
o
id
s
am
p
les
wer
e
co
n
s
id
er
e
d
.
I
n
a
n
aly
zin
g
t
h
e
s
im
u
latio
n
p
ar
t,
t
h
e
ac
cu
r
ac
y
,
c
o
s
t,
an
d
F
-
s
co
r
e
wer
e
in
v
esti
g
ated
an
d
co
m
p
a
r
ed
with
d
if
f
er
e
n
t
k
er
n
els.
Ho
wev
er
,
th
is
te
ch
n
i
q
u
e
f
ac
es
h
ig
h
tim
e
co
m
p
le
x
ity
an
d
o
v
er
f
itti
n
g
is
s
u
es wh
ile
p
r
o
ce
s
s
in
g
with
lar
g
er
m
alwa
r
e
a
p
p
s
.
I
m
tiaz
et
a
l
.
[
1
2
]
in
tr
o
d
u
ce
d
a
d
ee
p
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
DANN
)
f
o
r
d
etec
tin
g
an
d
i
d
en
tify
in
g
th
e
an
d
r
o
id
m
ale
v
o
len
ts
ef
f
ic
ien
tly
.
I
n
itially
,
m
in
-
m
ax
n
o
r
m
aliza
tio
n
was
p
er
f
o
r
m
ed
to
r
escale
th
e
r
an
d
o
m
v
alu
es
in
to
a
f
i
x
ed
r
a
n
g
e.
T
h
en
,
FE
was
p
er
f
o
r
m
ed
w
h
ich
ex
tr
ac
ts
s
tatic
an
d
d
y
n
am
ic
f
ea
tu
r
es
b
ased
o
n
n
etwo
r
k
lay
er
s
.
Fin
ally
,
th
e
DANN
m
o
d
el
d
etec
ts
wh
eth
e
r
th
e
ap
p
licatio
n
s
wer
e
n
o
r
m
a
l
o
r
m
alig
n
an
t.
B
u
t,
th
is
m
eth
o
d
f
ailed
t
o
o
v
e
r
co
m
e
th
e
b
lack
b
o
x
is
s
u
es wh
ile
d
ea
lin
g
with
p
er
m
is
s
io
n
an
d
A
PI
ca
lls
.
Yad
av
et
a
l
.
[
1
3
]
d
ef
in
e
d
a
two
-
s
tag
e
DL
m
o
d
el
f
o
r
r
ec
o
g
n
izin
g
a
n
d
r
o
id
m
alwa
r
e
b
ased
o
n
m
alev
o
len
t
im
a
g
es.
Her
e,
th
e
ef
f
icien
tNetB
0
m
o
d
el
was
in
tr
o
d
u
ce
d
to
d
e
tect
m
o
b
il
e
th
ir
d
-
p
ar
ty
ap
p
s
ac
cu
r
ately
.
Mo
r
e
o
v
er
,
ML
cl
ass
if
ier
s
lik
e
lin
ea
r
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
L
SVM)
an
d
R
F
tech
n
iq
u
e
wer
e
u
tili
ze
d
to
ef
f
icien
tly
class
if
y
th
e
v
ar
io
u
s
m
alig
n
an
t
attac
k
s
lik
e
Ad
s
war
e,
Ad
war
e,
T
r
o
jan
,
an
d
Sp
y
war
e.
I
n
th
e
s
im
u
latio
n
p
a
r
t,
ac
cu
r
ac
y
was
an
aly
ze
d
an
d
d
is
tin
g
u
is
h
e
d
f
r
o
m
o
t
h
er
s
tu
d
ies.
Ho
wev
er
,
th
is
m
eth
o
d
h
ad
a
h
ig
h
er
r
o
r
as it f
ailed
to
co
n
s
id
er
th
e
ef
f
ec
tiv
e
f
ea
tu
r
es f
o
r
th
e
d
etec
tio
n
p
r
o
ce
s
s
.
Kim
et
a
l
.
[
1
4
]
estab
lis
h
ed
a
p
r
ac
tical
-
o
r
ien
ted
DL
m
o
d
el
f
o
r
d
eter
m
i
n
in
g
m
alwa
r
e
is
s
u
es
in
m
o
b
ile
p
h
o
n
es.
I
n
th
is
wo
r
k
,
C
NN
b
ased
DL
m
o
d
el
was
in
tr
o
d
u
ce
d
to
d
etec
t
th
ir
d
-
p
ar
t
y
ap
p
s
o
n
a
n
d
r
o
id
p
latf
o
r
m
s
.
Mo
r
eo
v
er
,
API
ca
ll
-
b
ased
f
e
atu
r
es
wer
e
co
n
s
id
er
ed
f
o
r
l
ea
r
n
in
g
th
e
m
alig
n
an
t
a
p
p
s
ef
f
ec
tiv
ely
.
Fo
r
th
e
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
.
3
,
Ma
r
ch
20
2
5
:
1
672
-
1
6
8
1
1674
s
im
u
latio
n
p
r
o
ce
s
s
,
Go
o
g
le
P
lay
Sto
r
e
ap
p
s
co
n
s
is
tin
g
o
f
1
0
,
0
0
0
a
n
d
r
o
id
s
am
p
les
w
er
e
u
tili
ze
d
.
I
n
t
h
e
s
im
u
latio
n
p
ar
t,
ac
c
u
r
ac
y
was
an
aly
ze
d
a
n
d
d
is
tin
g
u
is
h
ed
f
r
o
m
o
t
h
er
s
tu
d
ies.
Ho
wev
e
r
,
t
h
is
m
eth
o
d
ca
u
s
es
h
ig
h
g
r
ad
ien
t e
x
p
lo
s
io
n
p
r
o
b
le
m
s
an
d
o
v
e
r
f
itti
n
g
is
s
u
es wh
en
p
r
o
ce
s
s
in
g
with
lar
g
er
s
am
p
l
es.
I
n
an
ef
f
o
r
t
to
p
o
is
o
n
th
e
ad
ap
tiv
e
f
ac
e
r
ec
o
g
n
itio
n
s
y
s
tem
,
B
ig
g
io
an
d
Z
h
u
[
1
5
]
-
[
1
7
]
m
ad
e
an
attem
p
t.
T
h
e
attac
k
er
’
s
p
ictu
r
e
m
ay
b
e
v
alid
ated
b
y
in
s
er
tin
g
f
r
au
d
u
len
t
d
ata
d
u
r
i
n
g
th
e
m
o
d
el
u
p
d
ate,
wh
ich
s
h
if
ted
th
e
ce
n
tr
al
v
alu
e
o
f
th
e
r
ec
o
g
n
itio
n
f
ea
tu
r
e
i
n
th
e
m
o
d
el.
B
ig
g
io
et
a
l.
[
1
8
]
lau
n
c
h
ed
ass
au
lts
ag
ain
s
t
SVM,
a
tech
n
iq
u
e
u
s
ed
f
o
r
s
u
p
er
v
is
ed
lear
n
in
g
.
T
h
e
e
x
p
er
im
en
tal
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
m
o
d
el
class
if
ier
’
s
test
er
r
o
r
m
a
y
b
e
s
u
b
s
tan
tially
am
p
lifie
d
as
th
e
g
r
ad
ie
n
t
r
is
es.
T
o
f
o
o
l
th
e
m
o
d
el,
t
h
e
in
jecte
d
s
am
p
le
d
ata
m
u
s
t
ad
h
er
e
to
ce
r
tain
r
u
les,
an
d
th
e
attac
k
er
m
u
s
t
o
wn
th
e
in
jectio
n
p
o
in
t
lab
el.
T
o
test
p
o
is
o
n
in
g
attac
k
s
o
n
n
e
u
r
al
n
etwo
r
k
lear
n
in
g
alg
o
r
ith
m
s
,
Y
an
g
et
a
l.
[
1
9
]
r
a
n
an
ex
p
er
im
en
t.
T
h
e
s
u
g
g
ested
tech
n
iq
u
e
m
a
y
d
o
u
b
le
th
e
s
p
ee
d
o
f
attac
k
s
am
p
le
cr
ea
tio
n
w
h
en
co
m
p
ar
ed
t
o
th
e
d
i
r
ec
t g
r
a
d
ien
t a
p
p
r
o
ac
h
.
W
h
ile
it
’
s
tr
u
e
th
at
a
p
o
is
o
n
i
n
g
attac
k
m
ig
h
t
ca
u
s
e
th
e
m
o
d
el
to
m
alf
u
n
ctio
n
,
th
e
p
er
p
etr
ato
r
m
u
s
t
ex
er
t
s
o
m
e
ef
f
o
r
t
to
f
ig
u
r
e
o
u
t
h
o
w
to
in
tr
o
d
u
ce
h
ar
m
f
u
l
d
ata.
An
m
o
r
e
p
r
ev
ale
n
t
tech
n
iq
u
e,
a
d
v
er
s
ar
ial
s
am
p
le
ass
au
lt,
m
ay
q
u
ick
ly
lead
m
o
d
els
to
th
e
in
co
r
r
ec
t
co
n
clu
s
io
n
.
I
t
was
Szeg
ed
y
e
t
a
l
.
[
2
0
]
wh
o
f
ir
s
t
s
u
g
g
ested
th
e
id
ea
o
f
ad
v
e
r
s
ar
ial
s
am
p
les.
T
h
e
p
er
tu
r
b
e
d
s
am
p
les
will
co
n
f
id
en
tly
lead
t
h
e
m
o
d
el
to
p
r
o
v
i
d
e
an
in
ac
c
u
r
ate
an
s
wer
b
y
in
ten
tio
n
ally
alter
in
g
th
e
d
ataset
in
a
s
m
all
way
.
T
h
e
in
itially
p
r
o
p
er
ly
ca
teg
o
r
is
ed
s
am
p
le
m
ay
m
o
v
e
t
o
th
e
o
th
er
s
id
e
o
f
th
e
d
ec
is
io
n
r
e
g
io
n
an
d
b
e
r
ec
lass
if
ied
in
to
a
d
if
f
er
en
t
ca
teg
o
r
y
if
ad
v
er
s
ar
ial
s
am
p
les
r
aise
th
e
m
o
d
el
’
s
p
r
e
d
ictio
n
er
r
o
r
.
A
d
v
er
s
ar
ial
s
am
p
les
m
ay
ex
p
l
o
it
ex
is
tin
g
m
o
d
els
[
2
1
]
-
[
2
4
]
.
Fro
m
th
e
d
etailed
liter
atu
r
e
r
ev
iew,
th
e
f
o
llo
win
g
r
esear
c
h
g
ap
s
a
r
e
id
e
n
tifie
d
.
E
f
f
ec
ti
v
en
ess
o
f
s
p
atialize
d
d
r
o
p
o
u
t
in
a
d
v
er
s
ar
ial
d
etec
tio
n
.
Op
tim
izin
g
s
p
atialize
d
d
r
o
p
o
u
t
:
w
h
ile
s
p
a
tialized
d
r
o
p
o
u
t
is
in
ten
d
ed
t
o
im
p
r
o
v
e
m
o
d
el
g
en
er
aliza
tio
n
a
n
d
r
o
b
u
s
t
n
ess
,
r
esear
ch
is
n
ee
d
ed
to
o
p
tim
ize
its
p
ar
am
eter
s
s
p
ec
if
ically
f
o
r
a
d
v
er
s
ar
ial
d
e
tectio
n
in
m
o
b
ile
ap
p
s
.
Stu
d
i
es
co
u
ld
ex
p
lo
r
e
th
e
im
p
ac
t
o
f
d
if
f
e
r
en
t
d
r
o
p
o
u
t
s
tr
ateg
ies
o
n
th
e
d
etec
tio
n
ac
cu
r
ac
y
o
f
v
ar
io
u
s
ad
v
e
r
s
ar
ial
tech
n
iq
u
es.
C
o
m
p
ar
is
o
n
with
o
th
er
r
eg
u
lar
izatio
n
tech
n
iq
u
es
:
t
h
er
e
is
a
n
ee
d
f
o
r
co
m
p
ar
ativ
e
s
tu
d
ies
to
ev
alu
at
e
th
e
ef
f
ec
tiv
e
n
ess
o
f
s
p
atialize
d
d
r
o
p
o
u
t
ag
ain
s
t
o
th
er
r
e
g
u
lar
izatio
n
tec
h
n
iq
u
e
s
lik
e
b
atch
n
o
r
m
aliza
tio
n
,
s
ta
n
d
ar
d
d
r
o
p
o
u
t,
o
r
L
2
r
e
g
u
lar
iz
atio
n
in
th
e
c
o
n
tex
t
o
f
ad
v
e
r
s
ar
ial
d
e
tectio
n
.
Featu
r
e
en
g
in
ee
r
in
g
an
d
s
elec
tio
n
.
API
ca
ll
an
d
p
er
m
is
s
io
n
f
ea
tu
r
e
r
elev
a
n
ce
:
r
esear
ch
c
o
u
ld
f
o
c
u
s
o
n
id
en
tif
y
in
g
wh
ich
s
p
ec
if
ic
API
ca
lls
an
d
p
er
m
is
s
io
n
f
ea
t
u
r
es
ar
e
m
o
s
t
in
d
icativ
e
o
f
ad
v
er
s
ar
ial
b
eh
av
i
o
r
.
T
h
is
in
v
o
lv
es
ex
p
lo
r
in
g
FS
tech
n
iq
u
es
t
h
at
ca
n
en
h
a
n
ce
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
.
Dy
n
am
ic
v
s
.
s
tatic
f
ea
tu
r
es
:
t
h
e
ef
f
ec
tiv
en
ess
o
f
s
tatic
f
ea
tu
r
es
(
e.
g
.
,
p
e
r
m
is
s
io
n
s
d
ec
lar
e
d
in
th
e
m
an
if
es
t)
v
er
s
u
s
d
y
n
a
m
ic
f
ea
tu
r
es
(
e.
g
.
,
r
u
n
tim
e
API
ca
lls
)
in
d
etec
tin
g
ad
v
er
s
ar
ial
at
tack
s
n
ee
d
s
f
u
r
th
e
r
in
v
esti
g
atio
n
.
R
esear
ch
co
u
l
d
ex
p
lo
r
e
h
o
w
th
e
m
o
d
el
ca
n
b
a
lan
ce
o
r
in
teg
r
ate
th
ese
two
ty
p
es o
f
f
ea
tu
r
es.
R
o
b
u
s
tn
ess
to
ev
asiv
e
ad
v
e
r
s
ar
ial
tech
n
iq
u
es
.
Dete
ctio
n
o
f
s
o
p
h
is
ticated
ad
v
e
r
s
ar
ial
attac
k
s
:
n
ew
ty
p
es
o
f
ad
v
er
s
ar
ial
attac
k
s
co
n
tin
u
e
to
em
e
r
g
e,
m
a
k
in
g
it
ess
en
tial
to
test
th
e
r
o
b
u
s
tn
ess
o
f
th
e
SD
-
C
AE
m
o
d
el
ag
ain
s
t
m
o
r
e
s
o
p
h
is
ticated
ev
asio
n
tech
n
iq
u
es.
R
esear
ch
co
u
l
d
ex
p
lo
r
e
h
o
w
to
ad
ap
t
th
e
m
o
d
el
to
d
etec
t
n
o
v
el
attac
k
s
th
at
e
x
p
l
o
it
wea
k
n
ess
es
in
b
o
th
API
ca
lls
an
d
p
er
m
is
s
io
n
-
b
ased
f
e
atu
r
es.
Gen
er
aliza
ti
on
to
u
n
k
n
o
wn
attac
k
s
:
t
h
e
ab
ilit
y
o
f
th
e
m
o
d
el
to
g
en
e
r
alize
a
n
d
d
etec
t
u
n
k
n
o
w
n
o
r
ze
r
o
-
d
a
y
ad
v
er
s
ar
ial
attac
k
s
in
m
o
b
ile
ap
p
s
r
em
ain
s
an
o
p
en
ch
allen
g
e
.
Dev
elo
p
i
n
g
m
eth
o
d
s
to
en
h
an
ce
th
e
m
o
d
el
’
s
ad
ap
tab
ilit
y
to
u
n
f
o
r
eseen
ad
v
e
r
s
ar
ial
b
eh
av
i
o
r
s
is
cr
u
cial
.
Scalab
ilit
y
an
d
p
er
f
o
r
m
a
n
ce
i
n
r
ea
l
-
wo
r
ld
s
ce
n
a
r
io
s
.
R
ea
l
-
tim
e
d
etec
tio
n
ca
p
a
b
ilit
ies
:
t
h
e
f
ea
s
ib
ilit
y
o
f
d
ep
lo
y
i
n
g
th
e
SD
-
C
AE
m
o
d
el
f
o
r
r
ea
l
-
tim
e
a
d
v
er
s
ar
ial
d
etec
tio
n
in
m
o
b
ile
ap
p
s
,
esp
e
cially
o
n
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
d
ev
ices,
is
an
ar
e
a
th
at
r
eq
u
ir
es
f
u
r
th
e
r
r
esear
c
h
.
Stu
d
ies
co
u
ld
f
o
c
u
s
o
n
o
p
ti
m
izin
g
th
e
m
o
d
el
to
r
ed
u
ce
co
m
p
u
tatio
n
al
o
v
er
h
e
ad
wh
ile
m
ain
tain
in
g
h
ig
h
d
etec
tio
n
ac
cu
r
ac
y
.
Scalab
ilit
y
ac
r
o
s
s
d
iv
e
r
s
e
ap
p
ec
o
s
y
s
t
em
s
:
r
esear
ch
co
u
ld
ex
p
lo
r
e
h
o
w
well
th
e
m
o
d
e
l
s
ca
les
ac
r
o
s
s
d
if
f
er
en
t
ty
p
es
o
f
m
o
b
ile
ap
p
s
(
e.
g
.
,
g
am
es,
s
o
cial
m
ed
ia,
f
i
n
an
cial
ap
p
s
)
a
n
d
d
if
f
er
en
t
o
p
er
atin
g
s
y
s
tem
s
(
e.
g
.
,
An
d
r
o
i
d
,
iOS),
wh
ich
m
a
y
h
av
e
v
ar
y
in
g
API
ca
ll
p
atter
n
s
an
d
p
e
r
m
is
s
io
n
s
tr
u
ctu
r
es.
2
.
1
.
P
r
o
blem
s
t
a
t
e
m
ent
Fro
m
th
e
d
ee
p
an
aly
s
is
o
f
t
h
e
co
n
v
e
n
tio
n
al
tec
h
n
iq
u
es,
s
ev
er
al
d
r
aw
b
ac
k
s
h
a
v
e
b
ee
n
n
o
ted
wh
ile
d
etec
tin
g
a
d
v
er
s
ar
ial
a
p
p
s
ac
c
u
r
ately
.
T
h
e
e
x
is
tin
g
m
o
d
els
a
r
e
less
ca
p
ab
le
o
f
lear
n
in
g
t
h
e
co
m
p
le
x
m
alwa
r
e
ap
k
f
iles
d
u
e
to
co
m
p
le
x
ap
p
licatio
n
co
d
es
a
n
d
b
lack
b
o
x
is
s
u
es.
So
m
e
p
ast
s
tu
d
ies
u
tili
ze
d
u
s
er
p
er
m
is
s
io
n
s
an
d
API
ca
ll
f
ea
tu
r
es
to
d
ete
r
m
in
e
th
e
th
ir
d
-
p
ar
t
y
ap
p
s
th
at
r
esu
lt
in
o
u
ts
tan
d
in
g
d
etec
tio
n
p
er
f
o
r
m
an
ce
.
Ho
wev
er
,
th
e
tech
n
iq
u
es
r
ed
u
ce
its
g
en
er
aliza
tio
n
ab
ilit
y
wh
ile
p
r
o
ce
s
s
in
g
with
lar
g
er
d
a
tab
as
es.
T
o
tack
le
th
ese
is
s
u
es,
AI
-
b
ased
DL
tech
n
iq
u
es
ar
e
in
tr
o
d
u
ce
d
t
h
a
t
au
to
m
atica
lly
lear
n
th
e
r
el
ev
an
t
co
m
p
licated
m
alwa
r
e
f
ea
tu
r
es
an
d
r
ec
o
g
n
ize
th
e
u
n
wan
ted
m
alev
o
len
t
ap
p
s
th
er
eb
y
p
r
ev
en
tin
g
d
i
m
en
s
io
n
ality
is
s
u
es.
T
h
u
s
,
th
is
a
r
ticle
d
escr
ib
es
a
r
o
b
u
s
t
ap
p
r
o
ac
h
to
id
en
tif
y
th
ir
d
-
p
ar
t
y
a
p
p
s
u
s
in
g
p
e
r
m
is
s
io
n
an
d
API
ca
l
l
f
ea
tu
r
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
A
u
to
ma
ted
a
d
ve
r
s
a
r
ia
l d
etec
tio
n
in
mo
b
ile
a
p
p
s
b
a
s
ed
…
(
S
a
n
ja
ika
n
t
h
E
V
a
d
a
kk
eth
il S
o
m
a
n
a
th
a
n
P
illa
i
)
1675
3.
DE
V
E
L
O
P
E
D
M
E
T
H
O
D
No
wad
ay
s
,
th
e
p
o
p
u
lar
ity
o
f
t
h
e
an
d
r
o
id
m
o
b
ile
p
h
o
n
es
h
as b
ee
n
g
r
o
win
g
an
d
t
h
is
p
o
p
u
lar
ity
m
ak
es
th
e
d
ev
el
o
p
er
s
f
o
r
c
r
ea
tin
g
th
eir
s
o
licitatio
n
s
(
ap
p
s
)
o
n
th
is
p
latf
o
r
m
.
Du
e
to
t
h
e
in
cr
ea
s
ed
n
u
m
b
er
o
f
ap
p
s
,
m
ad
e
an
ad
v
a
n
tag
e
o
n
d
ev
elo
p
in
g
v
ar
i
o
u
s
m
alev
o
len
t
an
d
in
clu
d
e
th
em
o
n
a
th
ir
d
p
a
r
ty
a
r
ca
d
es
as
p
r
o
tecte
d
ap
p
licatio
n
.
Fig
u
r
e
1
d
ep
icts
th
e
wo
r
k
f
l
o
w
o
f
th
e
d
ev
elo
p
e
d
f
r
am
ewo
r
k
.
Dete
ctin
g
t
h
ese
k
in
d
s
o
f
m
alwa
r
e
ap
p
licatio
n
is
a
ch
allen
g
in
g
ta
s
k
as
it
is
tim
e
co
n
s
u
m
in
g
an
d
r
eq
u
ir
es
h
ig
h
co
s
t
tech
n
iq
u
e
s
.
Hen
ce
,
th
is
s
tu
d
y
p
u
t
f
o
r
th
a
r
o
b
u
s
t
DL
m
o
d
els
f
o
r
d
etec
tin
g
th
e
a
d
v
er
s
ar
ial
th
ir
d
p
a
r
ty
a
p
p
s
with
ad
a
p
tiv
e
f
ea
tu
r
e
lear
n
in
g
.
T
h
e
d
ev
elo
p
ed
s
tr
ateg
y
co
m
p
r
is
es
o
f
th
r
ee
s
tag
es:
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
class
if
icatio
n
.
I
n
itially
,
th
e
r
aw
ap
k
f
iles
co
n
s
is
t
o
f
ex
iled
,
ac
ce
s
s
ib
le
an
d
r
eg
is
ter
ed
s
u
b
s
ets
o
f
ap
p
licatio
n
s
ar
e
p
r
ep
r
o
ce
s
s
ed
,
f
o
llo
wed
b
y
API
an
d
p
er
m
is
s
io
n
b
eh
a
v
io
r
a
l
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
.
Fin
a
l
ly
,
th
e
ex
ce
r
p
ted
f
ea
tu
r
es
ar
e
g
iv
e
n
in
to
th
e
p
r
o
p
o
s
ed
SD_
C
o
n
v
AE
a
p
p
r
o
a
ch
f
o
r
i
d
en
tify
in
g
wh
eth
er
t
h
e
ap
p
is
b
en
ig
n
o
r
m
alig
n
an
t.
3
.
1
.
F
e
a
t
ure
ex
t
r
a
ct
io
n a
nd
prepro
ce
s
s
i
ng
W
h
en
a
m
o
b
ile
ap
p
is
in
s
talled
o
n
an
a
n
d
r
o
id
d
ev
ice,
it
i
s
g
r
an
ted
p
er
m
is
s
io
n
s
to
ac
c
ess
s
y
s
tem
r
eso
u
r
ce
s
.
API
ca
lls
an
d
p
er
m
is
s
io
n
s
r
eq
u
ested
b
y
th
e
a
p
p
a
r
e
th
e
n
e
x
tr
ac
ted
to
an
aly
ze
its
b
eh
a
v
io
r
.
T
h
ese
f
ea
tu
r
es
r
ev
ea
l
h
o
w
th
e
ap
p
in
ter
ac
ts
with
th
e
d
ev
ice,
id
en
tify
in
g
p
o
ten
tial
s
ec
u
r
ity
r
is
k
s
o
r
m
alicio
u
s
ac
tiv
ity
.
An
aly
zin
g
API
ca
lls
an
d
p
er
m
is
s
io
n
s
h
elp
s
d
etec
t a
d
v
er
s
ar
ial
b
eh
a
v
io
r
s
in
m
o
b
ile
ap
p
s
.
3
.
1
.
1
.
AP
I
ca
lls
-
ba
s
ed
f
ea
t
ure
ex
t
ra
ct
i
o
n
T
h
e
p
r
e
-
d
ef
in
ed
c
o
d
es
p
r
esen
t
in
an
d
r
o
id
lib
r
ar
ies
ar
e
co
n
s
id
er
ed
as
th
e
API
ca
lls
.
B
y
s
t
atis
ticall
y
in
v
esti
g
atin
g
th
e
s
am
p
les,
th
e
m
o
s
t
r
elev
an
t
API
ca
ll
f
ea
tu
r
es
ar
e
in
v
o
lv
ed
f
o
r
tr
ain
i
n
g
p
r
o
ce
s
s
.
T
o
p
er
f
o
r
m
th
is
,
lar
g
er
b
en
ig
n
a
n
d
m
alig
n
an
t
a
n
d
r
o
i
d
s
am
p
les
ar
e
tak
en
th
at
lear
n
s
th
e
i
d
en
tity
o
f
m
alev
o
len
t
ap
p
licatio
n
s
.
T
h
e
API
ca
ll
f
ea
tu
r
es
ar
e
ex
tr
ac
t
ed
b
ased
o
n
th
e
n
atu
r
e
o
f
th
e
r
eso
u
r
ce
s
r
eq
u
ested
an
d
th
ey
ar
e
o
f
two
ty
p
es
b
r
o
ad
ca
s
t
API
s
an
d
telep
h
o
n
y
m
a
n
ag
er
A
PIs.
T
h
e
f
u
n
ctio
n
alities
o
f
th
ese
f
ea
tu
r
es
ar
e
d
ep
icted
as
f
o
llo
ws.
T
ab
le
1
d
ep
icts
th
e
ex
tr
ac
ted
telep
h
o
n
y
m
an
a
g
er
API
an
d
b
r
o
ad
c
ast
API
s
wi
th
th
eir
f
u
n
ctio
n
alities
.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
th
e
d
e
v
elo
p
ed
f
r
am
ewo
r
k
T
ab
le
1
.
T
elep
h
o
n
y
m
an
a
g
er
API
an
d
b
r
o
ad
ca
s
t
API
s
with
th
eir
f
u
n
ctio
n
alities
A
P
I
c
a
l
l
f
e
a
t
u
r
e
s
F
u
n
c
t
i
o
n
a
l
i
t
i
e
s
g
e
t
D
a
t
a
A
c
t
i
v
i
t
y
(
)
Y
i
e
l
d
s
a
c
o
n
st
a
n
t
,
r
e
p
r
e
se
n
t
i
n
g
t
h
e
a
c
t
i
v
i
t
y
t
y
p
e
g
e
t
Li
n
e
n
u
m
b
e
r
(
)
Y
i
e
l
d
s
t
h
e
n
u
mb
e
r
o
f
st
r
i
n
g
s f
o
r
e
a
c
h
l
i
n
e
g
e
t
C
a
l
l
S
t
a
t
e
(
)
Y
i
e
l
d
s
c
a
l
l
s
t
a
t
e
g
e
t
D
e
v
i
c
e
I
d
(
)
Y
i
e
l
d
s I
M
EI
n
u
mb
e
r
g
e
t
S
I
M
O
p
e
r
a
t
o
r
(
)
Y
i
e
l
d
s
t
h
e
p
r
o
v
i
d
e
r
’
s
mo
b
i
l
e
n
e
t
w
o
r
k
a
n
d
c
o
u
n
t
r
y
c
o
d
e
o
f
t
h
e
S
I
M
c
a
r
d
g
e
t
S
u
b
scr
i
b
e
r
I
D
(
)
Y
i
e
l
d
s I
M
S
I
n
u
m
b
e
r
o
f
e
a
c
h
d
e
v
i
c
e
g
e
t
N
e
t
w
o
r
k
Ty
p
e
(
)
Y
i
e
l
d
s
t
y
p
e
o
f
n
e
t
w
o
r
k
f
o
r
p
r
e
se
n
t
d
a
t
a
l
i
n
k
P
h
o
n
e
C
a
l
l
R
e
c
e
i
v
e
r
P
h
o
n
e
c
h
a
n
g
e
s s
t
a
t
e
w
h
e
n
c
a
l
l
b
a
c
k
t
h
a
t
f
i
r
e
o
f
f
s
A
u
t
o
S
M
S
R
e
c
e
i
v
e
r
A
u
t
o
ma
t
i
c
a
l
l
y
r
e
c
e
i
v
e
s i
n
c
o
m
i
n
g
S
M
S
a
b
o
r
t
B
r
o
a
d
c
a
st
A
u
t
o
ma
t
i
c
a
l
l
y
d
i
s
t
r
a
c
t
s
t
h
e
p
r
e
se
n
t
b
r
o
a
d
c
a
st
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
.
3
,
Ma
r
ch
20
2
5
:
1
672
-
1
6
8
1
1676
3
.
1
.
2
.
P
er
m
is
s
io
n
-
lev
el
f
ea
t
u
re
ex
t
ra
ct
i
o
n
T
h
e
p
er
m
is
s
io
n
s
ar
e
f
in
alize
d
b
y
th
e
a
n
d
r
o
id
d
ev
elo
p
e
r
t
o
g
ain
th
e
a
p
p
ac
ce
s
s
to
s
o
m
e
s
ec
u
r
ed
a
n
d
r
o
id
API
s
.
Ho
wev
er
,
s
o
m
e
ap
p
s
r
eq
u
est
ac
ce
s
s
(
p
e
r
m
is
s
io
n
)
th
at
is
n
o
t
r
eq
u
ir
ed
f
o
r
th
e
n
o
r
m
al
im
p
lem
en
tatio
n
p
r
o
ce
s
s
.
T
h
e
s
et
o
f
p
er
m
is
s
io
n
s
th
at
ar
e
ex
tr
ac
ted
b
y
th
e
m
alig
n
an
t
ap
p
l
icatio
n
s
to
b
ar
g
ain
u
s
er
co
n
f
i
d
en
tial
in
f
o
r
m
atio
n
an
d
co
n
n
ec
t
to
r
em
o
te
s
er
v
e
r
s
f
r
o
m
th
e
c
u
s
to
m
er
s
f
o
r
co
m
m
er
cial
p
u
r
p
o
s
es.
So
m
e
o
f
th
e
co
m
m
o
n
p
er
m
is
s
io
n
r
eq
u
ests
b
y
t
h
e
m
alev
o
len
t
ap
p
s
ar
e
d
ep
icted
i
n
th
e
tab
le
g
iv
en
b
elo
w
.
T
ab
le
2
d
e
p
icts
th
e
ex
tr
ac
ted
Per
m
is
s
io
n
-
lev
el
f
ea
tu
r
es
wi
th
th
eir
f
u
n
ctio
n
alities
T
h
ese
f
ea
tu
r
es
ar
e
th
e
n
co
n
v
er
ted
in
to
b
i
n
ar
y
f
o
r
m
(
0
,
1
)
to
a
v
o
id
c
o
n
f
u
s
io
n
d
u
r
in
g
t
h
e
tr
ain
in
g
p
r
o
ce
s
s
.
T
ab
le
2
.
Per
m
is
s
io
n
-
lev
el
f
ea
t
u
r
es with
th
eir
f
u
n
ctio
n
alities
P
e
r
mi
ssi
o
n
f
e
a
t
u
r
e
s
F
u
n
c
t
i
o
n
a
l
i
t
i
e
s
A
c
c
e
ss
_
N
e
t
w
o
r
k
_
S
t
a
t
e
A
sk
i
n
g
f
o
r
p
e
r
m
i
ssi
o
n
t
o
a
c
c
e
ss
d
a
t
a
a
b
o
u
t
n
e
t
w
o
r
k
s
C
a
l
l
_
P
h
o
n
e
A
sk
i
n
g
f
o
r
p
e
r
m
i
ssi
o
n
t
o
a
c
c
e
ss
a
n
y
n
u
mb
e
r
w
i
t
h
o
u
t
g
o
i
n
g
t
o
t
h
e
d
i
a
l
e
r
S
e
n
d
_
S
M
S
A
sk
i
n
g
f
o
r
p
e
r
m
i
ssi
o
n
t
o
a
c
c
e
ss
a
n
d
r
e
a
d
mess
a
g
e
s
R
e
a
d
_
P
h
o
n
e
_
S
t
a
t
e
A
sk
i
n
g
f
o
r
p
e
r
m
i
ssi
o
n
t
o
a
c
c
e
ss
t
h
e
p
h
o
n
e
st
a
t
e
I
n
t
e
r
n
e
t
A
sk
i
n
g
f
o
r
p
e
r
m
i
ssi
o
n
t
o
a
c
c
e
ss
o
p
e
n
n
e
t
w
o
r
k
p
l
u
g
s
C
h
a
n
g
e
_
N
e
t
w
o
r
k
_
S
t
a
t
e
A
sk
i
n
g
f
o
r
p
e
r
m
i
ssi
o
n
t
o
a
c
c
e
ss
n
e
t
w
o
r
k
c
o
n
n
e
c
t
i
v
i
t
y
G
e
t
_
A
c
c
o
u
n
t
s
A
sk
i
n
g
f
o
r
p
e
r
m
i
ssi
o
n
t
o
a
c
c
e
ss
a
c
c
o
u
n
t
d
e
t
a
i
l
s
R
e
a
d
_
C
o
n
t
a
c
t
s
A
sk
i
n
g
f
o
r
p
e
r
m
i
ssi
o
n
t
o
a
c
c
e
ss
u
s
e
r
c
o
n
t
a
c
t
s
3
.
2
.
Adv
er
s
a
ria
l a
pp
det
ec
t
io
n us
ing
S
D_
Co
nv
AE
t
ec
hn
i
q
ue
T
h
e
ex
tr
ac
ted
f
ea
tu
r
es
ar
e
th
en
f
ed
in
to
th
e
d
ev
elo
p
e
d
SD_
C
o
n
v
AE
ap
p
r
o
ac
h
f
o
r
i
d
en
tify
in
g
wh
eth
er
th
e
ap
p
is
g
en
u
in
e
o
r
m
alig
n
an
t.
T
h
e
p
r
o
p
o
s
ed
C
o
n
v
AE
is
co
m
p
o
s
ed
o
f
two
s
ec
ti
o
n
s
n
am
ely
en
c
o
d
er
an
d
d
e
co
d
er
.
Her
e,
a
lo
s
s
f
u
n
ctio
n
is
u
tili
ze
d
to
d
eter
m
in
e
th
e
lo
s
s
es
at
th
e
tim
e
o
f
t
r
ain
in
g
.
T
h
e
o
b
tain
ed
ch
an
n
el
f
ea
tu
r
es
f
r
o
m
th
e
ac
t
u
al
in
p
u
t
s
ig
n
al
ar
e
h
ig
h
ly
s
i
m
ilar
o
n
ly
wh
e
n
th
e
lo
s
s
es
ar
e
s
m
all
o
r
n
eg
lig
ib
le.
T
h
e
en
c
o
d
in
g
an
d
d
ec
o
d
in
g
p
ar
am
eter
s
o
f
th
e
AE
ar
e
o
p
ti
m
ized
u
s
in
g
th
e
lo
s
s
f
u
n
ctio
n
.
Fo
r
e
x
tr
ac
tin
g
th
e
ch
an
n
el
p
r
o
p
er
ties
,
3
D
co
n
v
o
lu
tio
n
al
(
3
D
-
C
o
n
v
)
lay
er
s
ar
e
u
s
ed
an
d
th
e
m
ath
em
atica
l
f
o
r
m
u
latio
n
f
o
r
ex
tr
ac
ted
f
ea
tu
r
es
f
r
o
m
e
n
co
d
e
r
an
d
d
ec
o
d
e
r
ar
e
d
e
p
icted
as
(
1
)
.
=
(
∗
+
)
(
1
)
Her
e,
m
an
ip
u
lates
th
e
C
o
n
v
k
er
n
els,
r
ep
r
esen
ts
th
e
i
n
p
u
t,
an
d
m
an
ip
u
lates
th
e
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
e
e
n
co
d
e
r
p
ar
t
o
f
AE
co
n
s
is
ts
o
f
d
u
al
C
o
n
v
lay
er
s
an
d
s
in
g
le
a
v
er
ag
e
p
o
o
lin
g
(
AP)
lay
e
r
s
.
Mo
r
eo
v
er
,
in
th
e
d
ec
o
d
er
p
a
r
t
d
u
al
d
e
-
c
o
n
v
o
lu
tio
n
al
lay
e
r
s
ar
e
p
r
esen
t
to
d
ec
o
d
e
th
e
en
co
d
ed
f
ea
tu
r
es
ac
cu
r
ately
.
T
h
e
C
o
n
v
lay
er
s
i
n
th
e
AE
p
er
f
o
r
m
lo
ca
l
c
o
m
p
u
tatio
n
s
a
n
d
th
e
p
o
o
lin
g
lay
er
s
p
er
f
o
r
m
t
h
e
d
o
wn
-
s
am
p
lin
g
p
r
o
ce
s
s
.
T
h
e
o
u
tco
m
e
ca
n
b
e
m
at
h
em
atica
lly
in
ter
p
r
eted
as
(
2
)
.
=
‖
̃
−
‖
2
(
2
)
Her
e,
in
d
icate
s
th
e
lo
s
s
,
̃
r
ep
r
esen
ts
th
e
r
ec
o
n
s
tr
u
cted
ch
an
n
el
p
ar
am
eter
s
a
n
d
m
an
ip
u
lates
th
e
in
p
u
t
s
ig
n
al.
I
n
ad
d
itio
n
to
th
i
s
,
a
n
o
r
m
aliza
tio
n
f
u
n
ctio
n
an
d
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U)
ac
tiv
atio
n
f
u
n
ctio
n
(
AF)
ar
e
in
clu
d
ed
to
s
p
ee
d
u
p
th
e
e
x
tr
ac
tio
n
p
r
o
ce
s
s
.
Hen
ce
,
th
e
AF
is
n
o
t
d
ep
lo
y
ed
o
n
th
e
f
i
n
al
d
e
-
c
o
n
v
lay
er
s
.
T
o
o
v
er
co
m
e
th
is
is
s
u
e,
a
s
p
atialize
d
d
r
o
p
o
u
t
lay
e
r
is
i
n
tr
o
d
u
ce
d
in
th
e
C
o
n
v
AE
m
o
d
el
t
o
lear
n
th
e
ex
tr
ac
ted
f
ea
tu
r
es a
cc
u
r
ately
.
T
h
e
d
r
o
p
o
u
t
f
u
n
ctio
n
wo
r
k
s
d
y
n
am
ically
u
n
d
er
ze
r
o
elem
en
ts
an
d
co
m
p
u
tes
s
ca
le
tr
an
s
f
o
r
m
atio
n
f
r
o
m
th
e
n
o
n
-
ze
r
o
elem
e
n
ts
.
T
h
e
s
ca
lar
co
n
v
er
s
io
n
m
ag
n
itu
d
e
is
h
ig
h
ly
ass
o
ciate
d
with
d
r
o
p
o
u
t
lay
er
s
.
Af
ter
p
er
f
o
r
m
in
g
ze
r
o
o
p
e
r
atio
n
s
,
th
e
ze
r
o
p
a
r
ts
ar
e
r
em
o
v
e
d
f
r
o
m
th
e
tr
ai
n
in
g
p
r
o
ce
s
s
.
T
h
e
r
em
ain
in
g
p
ar
ts
ar
e
g
iv
en
in
to
th
e
DL
th
e
d
e
co
d
in
g
p
ar
t
o
f
th
e
C
o
n
v
AE
m
o
d
el
to
d
eter
m
in
e
t
h
e
o
u
tco
m
e.
E
ac
h
d
r
o
p
o
u
t
is
r
an
d
o
m
in
n
atu
r
e
a
n
d
h
en
ce
,
t
h
e
m
o
d
el
is
f
o
r
ce
d
to
tr
ain
th
e
lo
w
-
lev
el
f
ea
tu
r
es r
esu
ltin
g
i
n
a
c
h
an
g
in
g
o
f
tim
e
f
o
r
lear
n
in
g
th
e
f
ea
tu
r
es.
Hen
ce
,
th
e
f
ea
tu
r
es
co
n
s
id
er
ed
f
o
r
th
e
tr
ain
in
g
m
u
s
t
n
o
t
p
r
o
d
u
ce
an
y
o
v
er
f
itti
n
g
is
s
u
es
d
u
e
t
o
d
im
en
s
io
n
ality
is
s
u
es.
T
h
e
s
p
atia
lized
d
r
o
p
o
u
t
is
alm
o
s
t
s
im
ilar
to
co
n
v
en
tio
n
a
l
d
r
o
p
o
u
t
h
o
wev
e
r
it
d
etac
h
es
th
e
co
m
p
lete
f
ea
t
u
r
e
s
ets
i
n
s
tead
o
f
u
s
in
g
o
n
e
-
d
im
en
s
i
o
n
al
(
1
D)
f
ea
tu
r
es.
T
h
e
n
o
r
m
aliza
tio
n
f
ails
wh
en
th
er
e
is
n
o
s
tr
o
n
g
co
r
r
elatio
n
b
etwe
en
th
e
ex
tr
ac
ted
f
ea
tu
r
es
wh
ile
p
r
o
ce
s
s
in
g
with
co
n
v
en
tio
n
al
d
r
o
p
o
u
ts
.
Ho
wev
er
,
th
e
SDs
ca
n
en
h
an
ce
th
e
s
tr
o
n
g
in
d
ep
en
d
en
ce
am
o
n
g
th
e
f
ea
t
u
r
es
an
d
it sets
r
an
d
o
m
ly
to
ze
r
o
s
f
o
r
a
p
ar
ticu
lar
d
im
e
n
s
io
n
in
Fig
u
r
e
2
.
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
A
u
to
ma
ted
a
d
ve
r
s
a
r
ia
l d
etec
tio
n
in
mo
b
ile
a
p
p
s
b
a
s
ed
…
(
S
a
n
ja
ika
n
t
h
E
V
a
d
a
kk
eth
il S
o
m
a
n
a
th
a
n
P
illa
i
)
1677
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
o
f
SA_
C
o
n
v
AE
m
o
d
el
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
p
r
o
ce
s
s
ed
an
d
ex
p
er
im
en
ted
u
s
i
n
g
th
e
Py
th
o
n
s
im
u
latio
n
to
o
l.
Var
io
u
s
ex
is
tin
g
s
ch
em
es
lik
e
k
-
n
ea
r
e
s
t
n
ea
r
est
n
eig
h
b
o
r
(
KNN)
,
DL
-
an
d
r
o
i
d
(
DL
-
d
r
o
id
)
,
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
,
L
STM
,
an
d
B
i
-
d
ir
ec
tio
n
al
L
STM
(
B
i
-
L
STM
)
ar
e
also
ex
am
in
ed
an
d
d
is
tin
g
u
is
h
ed
f
r
o
m
th
e
d
ev
elo
p
e
d
m
et
h
o
d
b
y
co
m
p
u
t
in
g
d
i
f
f
er
en
t
m
ea
s
u
r
es
ac
c
u
r
a
cy
(
Acc
)
,
weig
h
te
d
F
-
s
co
r
e
(
W
-
FS
)
,
r
ec
all
(
R
ec
)
,
FDR
an
d
k
ap
p
a
co
ef
f
icien
t.
F
o
r
th
e
ex
p
e
r
im
en
tatio
n
p
r
o
ce
s
s
,
a
to
tal
o
f
1
6
0
0
m
o
b
ile
ap
p
li
ca
tio
n
s
ar
e
co
llected
th
at
ar
e
av
ailab
le
a
p
k
f
iles
.
O
u
t
o
f
1
.
6
K
a
p
p
licatio
n
s
,
8
0
0
a
r
e
ad
v
er
s
ar
ial
th
ir
d
-
p
ar
t
y
a
p
p
s
an
d
r
em
ai
n
in
g
ar
e
nor
m
al
ap
p
s
in
s
talled
f
r
o
m
a
u
th
o
r
ized
an
d
u
n
au
t
h
o
r
ized
a
n
d
r
o
id
p
latf
o
r
m
s
.
T
h
ese
m
alev
o
len
t
s
am
p
les
ar
e
co
llected
f
r
o
m
an
d
r
o
id
ap
p
g
e
n
o
m
e
p
r
o
ject
[
2
5
]
th
at
c
o
n
s
is
ts
o
f
4
9
m
ale
v
o
len
t f
a
m
ilies
.
4
.
1
.
Ass
ess
m
ent
m
et
rics
T
h
e
m
etr
ics
s
h
o
wn
ass
e
s
s
class
if
icatio
n
m
o
d
el
p
er
f
o
r
m
an
ce
.
Acc
u
r
ac
y
m
ea
s
u
r
es
th
e
o
v
er
all
co
r
r
ec
tn
ess
o
f
p
r
ed
ictio
n
s
,
wh
ile
W
-
FS
b
alan
ce
s
p
r
ec
is
io
n
an
d
r
ec
all,
weig
h
te
d
b
y
class
im
p
o
r
tan
ce
.
R
ec
all
(
s
en
s
it
iv
ity
)
em
p
h
asizes
th
e
id
en
tific
atio
n
o
f
tr
u
e
p
o
s
itiv
es,
u
s
ef
u
l
wh
en
m
in
im
izin
g
m
is
s
ed
p
o
s
itiv
es.
FDR
h
elp
s
as
s
es
s
th
e
r
eliab
ilit
y
o
f
p
o
s
itiv
e
p
r
ed
ictio
n
s
b
y
f
o
cu
s
in
g
o
n
f
alse
p
o
s
itiv
es.
Kap
p
a
c
o
ef
f
icien
t
ac
co
u
n
ts
f
o
r
ch
an
ce
a
g
r
ee
m
e
n
t,
in
d
icatin
g
m
o
d
el
r
eliab
ilit
y
b
ey
o
n
d
r
an
d
o
m
p
r
ed
ictio
n
s
.
(
%
)
=
+
+
+
+
×
100%
(
3
)
h
(
%
)
=
(
)
(
)
+
×
100%
(
4
)
(
%
)
=
+
×
100%
(
5
)
=
+
×
100%
(
6
)
=
2
∗
(
×
−
×
)
(
+
)
∗
(
+
)
∗
(
+
)
∗
(
+
)
(
7
)
H
er
e,
,
,
,
in
d
icate
s
th
e
tr
u
e
n
eg
ativ
e
(
T
N)
,
tr
u
e
p
o
s
itiv
e
(
T
P),
f
alse
n
eg
ativ
e
(
FN)
,
an
d
f
alse
p
o
s
itiv
e
(
FP
)
r
esp
ec
tiv
ely
.
4
.
2
.
Sim
ula
t
i
o
n a
na
ly
s
is
o
f
t
he
dev
elo
ped f
ra
m
ewo
rk
o
v
e
r
co
nv
ent
io
na
l schem
es
I
n
th
is
s
ec
tio
n
,
th
e
p
er
f
o
r
m
a
n
ce
ac
h
iev
ed
b
y
th
e
s
u
g
g
ested
m
eth
o
d
is
an
aly
ze
d
v
ia
tab
u
la
tio
n
u
n
d
er
v
ar
io
u
s
co
n
v
e
n
tio
n
al
tech
n
i
q
u
es.
T
h
e
an
aly
s
is
is
m
ad
e
f
o
r
d
etec
tio
n
o
f
b
o
th
n
o
r
m
al
an
d
m
alwa
r
e
ap
p
s
u
s
in
g
d
if
f
er
en
t
ass
ess
m
en
t
m
ea
s
u
r
es.
Var
io
u
s
ex
is
tin
g
s
tu
d
ies
lik
e
KNN,
DL
-
d
r
o
id
,
R
NN,
L
S
T
M,
an
d
B
i
-
L
STM
ar
e
co
m
p
ar
ed
with
th
e
d
ev
el
o
p
ed
m
e
th
o
d
to
d
eter
m
in
e
its
ef
f
icien
cy
.
T
h
e
d
etailed
an
al
y
s
is
o
f
th
e
o
b
tain
ed
p
er
f
o
r
m
an
ce
is
co
n
q
u
er
e
d
b
el
o
w:
Fig
u
r
e
3
s
tates
th
e
ac
c
u
r
ac
y
-
l
o
s
s
cu
r
v
es
o
f
t
h
e
p
r
o
p
o
s
ed
S
D_
C
o
n
v
AE
b
y
v
ar
y
in
g
t
h
e
ep
o
ch
v
alu
es.
T
ab
le
s
3
a
n
d
4
illu
s
tr
ates
th
e
p
er
f
o
r
m
an
ce
an
aly
s
is
o
f
v
ar
io
u
s
tech
n
iq
u
es
f
o
r
d
etec
tin
g
b
e
n
ig
n
a
n
d
m
alig
n
a
n
t
m
o
b
ile
ap
p
s
.
Fro
m
th
e
ta
b
u
latio
n
,
it
is
clea
r
th
at
th
e
d
ev
elo
p
ed
m
et
h
o
d
ac
h
ie
v
ed
b
etter
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
co
n
v
en
tio
n
al
tech
n
iq
u
es.
T
h
e
d
ev
elo
p
ed
m
et
h
o
d
ac
cu
r
ately
lear
n
s
m
alev
o
le
n
t
f
ea
tu
r
es
o
f
m
o
b
ile
ap
p
s
an
d
p
r
o
v
id
es
o
u
ts
tan
d
in
g
p
er
f
o
r
m
an
ce
th
a
n
o
th
e
r
tech
n
iq
u
es.
Ho
wev
er
,
th
e
co
n
v
e
n
tio
n
al
tech
n
iq
u
es
s
h
o
wed
less
p
er
f
o
r
m
an
ce
d
u
e
to
p
o
o
r
g
e
n
er
aliza
tio
n
ca
p
ab
ilit
y
wh
ile
p
r
o
ce
s
s
in
g
with
co
m
p
le
x
f
ea
t
u
r
es.
Mo
r
eo
v
er
,
th
e
er
r
o
r
is
h
ig
h
wh
en
m
alwa
r
e
f
e
atu
r
es c
o
m
p
ar
e
d
to
b
en
ig
n
ap
k
f
iles
.
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
.
3
,
Ma
r
ch
20
2
5
:
1
672
-
1
6
8
1
1678
T
ab
le
3
.
Per
f
o
r
m
an
ce
an
aly
s
is
o
f
v
ar
i
o
u
s
tech
n
iq
u
es f
o
r
d
ete
ctin
g
b
en
ig
n
m
o
b
ile
ap
p
s
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
(
%)
W
e
i
g
h
t
e
d
F
-
me
a
s
u
r
e
(
%)
F
D
R
R
e
c
a
l
l
(
%)
K
a
p
p
a
(
%)
K
N
N
8
9
.
5
89
1
0
.
5
88
90
DL
-
D
r
o
i
d
9
7
.
7
9
7
.
2
3
.
3
9
6
.
5
9
7
.
3
R
N
N
9
8
.
2
98
2
.
8
97
9
7
.
9
LSTM
9
8
.
7
9
8
.
3
2
.
3
9
7
.
9
9
8
.
3
Bi
-
LST
M
99
9
8
.
9
1
9
8
.
2
9
8
.
8
P
r
o
p
o
se
d
S
A
_
C
o
n
v
A
E
9
9
.
6
9
9
.
7
0
.
4
99
9
9
.
5
4
T
ab
le
4
.
Per
f
o
r
m
an
ce
an
aly
s
is
o
f
v
ar
i
o
u
s
tech
n
iq
u
es f
o
r
d
ete
ctin
g
m
alig
n
an
t
m
o
b
ile
ap
p
s
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
(
%)
W
e
i
g
h
t
e
d
F
-
me
a
s
u
r
e
(
%)
F
D
R
R
e
c
a
l
l
(
%)
K
a
p
p
a
(
%)
K
N
N
8
7
.
9
8
7
.
1
1
1
2
.
1
8
7
.
6
6
8
7
.
6
DL
-
D
r
o
i
d
9
6
.
8
5
9
6
.
2
2
3
.
2
9
6
.
8
2
9
6
.
5
R
N
N
9
7
.
2
97
2
.
8
9
7
.
1
5
9
7
.
2
1
LSTM
9
7
.
8
9
7
.
3
4
2
.
2
9
7
.
7
9
9
7
.
8
0
Bi
-
LST
M
9
8
.
0
1
9
7
.
9
8
1
.
9
9
9
7
.
9
0
9
7
.
9
8
P
r
o
p
o
se
d
S
A
_
C
o
n
v
A
E
99
9
8
.
9
7
1
9
8
.
9
9
9
8
.
9
Fig
u
r
e
3
.
Acc
u
r
ac
y
-
lo
s
s
cu
r
v
e
s
o
f
th
e
p
r
o
p
o
s
ed
SD_
C
o
n
v
AE
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
h
a
v
e
th
e
f
o
l
lo
win
g
p
r
ac
tical
im
p
ac
ts
:
4
.
2
.
1
.
E
nh
a
nced
m
o
bil
e
s
ec
u
rit
y
I
m
p
r
o
v
ed
th
r
ea
t
d
etec
tio
n
:
b
y
an
aly
zin
g
API
ca
lls
an
d
p
er
m
is
s
io
n
f
ea
tu
r
es,
th
e
SD
-
C
AE
m
o
d
el
ca
n
d
etec
t
ad
v
er
s
ar
ial
b
e
h
av
io
r
i
n
m
o
b
ile
ap
p
s
with
h
ig
h
ac
c
u
r
ac
y
.
T
h
is
im
p
r
o
v
es
th
e
o
v
er
al
l
s
ec
u
r
ity
o
f
m
o
b
ile
d
ev
ices,
p
r
o
tectin
g
u
s
er
s
f
r
o
m
m
alicio
u
s
ac
tiv
ities
lik
e
u
n
au
th
o
r
ize
d
d
ata
ac
ce
s
s
,
m
al
war
e,
an
d
p
r
iv
ac
y
b
r
ea
ch
es.
R
ea
l
-
tim
e
d
ef
e
n
s
e
:
t
h
e
m
o
d
el
ca
n
b
e
in
teg
r
ated
in
to
m
o
b
ile
s
ec
u
r
it
y
s
o
lu
tio
n
s
t
o
p
r
o
v
id
e
r
ea
l
-
tim
e
d
etec
tio
n
o
f
ad
v
er
s
ar
ial
attac
k
s
,
allo
win
g
f
o
r
im
m
e
d
iate
r
esp
o
n
s
e
an
d
m
itig
atio
n
,
th
er
e
b
y
r
ed
u
cin
g
th
e
r
is
k
o
f
d
am
ag
e.
4
.
2
.
2
.
User
priv
a
cy
pro
t
ec
t
i
o
n
Dete
ctio
n
o
f
p
r
i
v
ac
y
in
v
asio
n
s
:
t
h
e
m
o
d
el
’
s
ab
ilit
y
to
m
o
n
ito
r
an
d
an
aly
ze
p
er
m
is
s
io
n
r
eq
u
ests
en
s
u
r
es
th
at
m
o
b
ile
ap
p
s
d
o
n
o
t
o
v
e
r
r
ea
ch
in
ac
ce
s
s
in
g
s
en
s
itiv
e
u
s
er
d
ata.
T
h
is
ca
n
p
r
e
v
en
t
a
p
p
s
f
r
o
m
co
llectin
g
m
o
r
e
i
n
f
o
r
m
atio
n
th
an
n
ec
ess
ar
y
,
th
e
r
eb
y
p
r
o
tectin
g
u
s
er
p
r
iv
ac
y
.
C
o
m
p
lian
ce
with
p
r
iv
ac
y
r
eg
u
lati
o
n
s
:
t
h
e
im
p
lem
en
tati
o
n
o
f
th
is
m
o
d
el
ca
n
h
elp
a
p
p
d
e
v
elo
p
er
s
a
n
d
p
latf
o
r
m
p
r
o
v
id
er
s
c
o
m
p
ly
with
p
r
iv
ac
y
r
eg
u
latio
n
s
s
u
ch
as
g
en
er
al
d
ata
p
r
o
tectio
n
r
e
g
u
lati
o
n
(
GDPR
)
an
d
ca
lifo
r
n
ia
co
n
s
u
m
er
p
r
iv
ac
y
ac
t
(
C
C
PA
)
b
y
en
s
u
r
in
g
th
at
ap
p
s
ad
h
er
e
to
p
r
o
p
er
d
ata
h
an
d
lin
g
p
r
ac
tices.
4
.
2
.
3
.
Reduct
io
n in f
a
ls
e
po
s
i
t
iv
es
Acc
u
r
ate
th
r
ea
t
class
if
icatio
n
:
t
h
e
u
s
e
o
f
s
p
atialize
d
d
r
o
p
o
u
t
in
th
e
SD
-
C
AE
m
o
d
el
h
el
p
s
to
r
e
d
u
ce
o
v
er
f
itti
n
g
,
lead
i
n
g
to
m
o
r
e
ac
cu
r
ate
d
etec
tio
n
an
d
class
if
icatio
n
o
f
ad
v
e
r
s
ar
ial
th
r
ea
ts
.
T
h
is
r
ed
u
ce
s
th
e
n
u
m
b
er
o
f
f
alse
p
o
s
itiv
es,
m
i
n
im
izin
g
u
n
n
ec
ess
ar
y
aler
ts
a
n
d
im
p
r
o
v
i
n
g
u
s
er
e
x
p
er
ien
ce
.
E
f
f
icien
t
r
eso
u
r
ce
u
tili
za
tio
n
:
b
y
ac
cu
r
ately
d
is
tin
g
u
is
h
in
g
b
etwe
en
b
en
i
g
n
a
n
d
m
alicio
u
s
b
e
h
av
io
r
s
,
th
e
m
o
d
el
e
n
s
u
r
es
th
at
s
ec
u
r
ity
r
eso
u
r
ce
s
ar
e
o
n
l
y
d
ep
lo
y
e
d
wh
en
tr
u
ly
n
ec
ess
ar
y
,
o
p
tim
izin
g
b
o
th
c
o
m
p
u
tatio
n
al
an
d
h
u
m
a
n
r
eso
u
r
ce
s
.
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
A
u
to
ma
ted
a
d
ve
r
s
a
r
ia
l d
etec
tio
n
in
mo
b
ile
a
p
p
s
b
a
s
ed
…
(
S
a
n
ja
ika
n
t
h
E
V
a
d
a
kk
eth
il S
o
m
a
n
a
th
a
n
P
illa
i
)
1679
4
.
2
.
4
.
I
m
pro
v
ed
us
er
t
rus
t
a
nd
a
pp
a
do
ptio
n
I
n
cr
ea
s
ed
co
n
f
i
d
en
ce
in
ap
p
s
ec
u
r
ity
:
a
s
m
o
b
ile
ap
p
s
b
ec
o
m
e
m
o
r
e
s
ec
u
r
e
with
in
teg
r
ated
ad
v
er
s
ar
ial
d
etec
tio
n
m
ec
h
an
i
s
m
s
,
u
s
er
s
ar
e
m
o
r
e
lik
ely
to
tr
u
s
t
th
ese
ap
p
s
.
T
h
is
in
cr
ea
s
e
d
tr
u
s
t
ca
n
lead
to
h
ig
h
er
ad
o
p
tio
n
r
ates
an
d
u
s
er
en
g
ag
em
en
t.
Po
s
itiv
e
b
r
an
d
r
e
p
u
tatio
n
:
f
o
r
ap
p
d
ev
elo
p
er
s
an
d
p
latf
o
r
m
p
r
o
v
id
e
r
s
,
th
e
im
p
lem
e
n
tatio
n
o
f
s
u
ch
ad
v
an
ce
d
s
ec
u
r
ity
f
ea
tu
r
es
ca
n
en
h
a
n
ce
th
e
ir
b
r
an
d
r
ep
u
tatio
n
as
s
ec
u
r
ity
-
co
n
s
cio
u
s
an
d
u
s
er
-
f
o
cu
s
ed
,
attr
ac
tin
g
m
o
r
e
u
s
er
s
a
n
d
r
etain
in
g
ex
is
tin
g
o
n
es.
5.
CO
NCLU
SI
O
N
T
h
e
s
u
g
g
ested
f
r
am
ewo
r
k
in
tr
o
d
u
ce
d
an
d
in
v
esti
g
ated
a
r
o
b
u
s
t
SD_
C
o
n
v
AE
tech
n
iq
u
e
f
o
r
r
ec
o
g
n
izin
g
h
a
r
m
f
u
l
t
h
ir
d
-
p
ar
t
y
ap
p
s
u
s
in
g
ad
a
p
tiv
e
f
ea
tu
r
e
lear
n
in
g
.
T
h
e
d
ev
elo
p
e
d
SD_
C
o
n
v
AE
tech
n
iq
u
e
em
p
h
asized
a
n
o
v
el
d
r
o
p
o
u
t
m
ec
h
an
is
m
th
at
p
r
ev
e
n
ts
s
ep
ar
ate
FS
s
ch
em
es
f
o
r
r
ed
u
c
in
g
d
im
en
s
io
n
ality
is
s
u
es.
Mo
r
eo
v
er
,
th
e
d
e
v
elo
p
ed
f
r
am
ewo
r
k
co
n
q
u
e
r
ed
th
e
a
p
k
f
iles
th
at
co
n
s
is
t
o
f
API
ca
l
ls
an
d
p
er
m
is
s
io
n
-
lev
el
in
f
o
r
m
ati
o
n
an
d
p
r
o
v
id
e
s
o
u
ts
tan
d
in
g
d
etec
tio
n
p
e
r
f
o
r
m
an
ce
.
Fu
r
th
e
r
m
o
r
e
,
b
in
a
r
y
v
ec
to
r
co
n
v
er
s
io
n
i
s
p
er
f
o
r
m
ed
to
av
o
id
co
n
f
u
s
io
n
o
v
er
t
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
s
im
u
lated
v
ia
a
Py
th
o
n
to
o
l
an
d
v
ar
i
o
u
s
ass
ess
m
en
t
m
ea
s
u
r
es
l
ik
e
ac
cu
r
ac
y
,
W
-
FS
,
FDR
,
r
ec
all,
an
d
k
ap
p
a
ar
e
in
v
esti
g
ated
an
d
co
m
p
ar
ed
with
co
n
v
en
tio
n
al
s
ch
em
es.
T
h
e
d
ev
elo
p
ed
m
eth
o
d
ac
h
iev
es
o
v
er
all
ac
c
u
r
ac
ies
o
f
9
9
.
6
%
an
d
9
9
%
f
o
r
d
etec
tin
g
b
o
t
h
m
alig
n
an
t
an
d
b
en
ig
n
ap
p
s
r
esp
ec
tiv
ely
.
Ho
wev
er
,
d
u
e
to
th
e
u
n
av
ail
ab
il
ity
o
f
th
e
p
r
o
p
er
d
ataset,
f
ewe
r
ap
k
s
am
p
les
a
r
e
co
n
s
id
er
ed
f
o
r
th
e
ex
p
er
i
m
en
tatio
n
p
r
o
ce
s
s
.
I
n
th
e
f
u
t
u
r
e,
th
e
d
ev
elo
p
ed
f
r
am
ewo
r
k
will
b
e
ex
ten
d
e
d
b
y
d
elib
er
atin
g
lar
g
e
r
ap
k
s
am
p
les
f
o
r
d
etec
tin
g
th
e
m
al
war
e
ap
p
s
,
an
d
its
p
er
f
o
r
m
an
ce
will
b
e
an
aly
ze
d
.
Fu
tu
r
e
r
esear
c
h
c
o
u
ld
ex
p
lo
r
e
co
m
b
in
in
g
th
e
SD
-
C
AE
m
o
d
el
with
o
th
e
r
ad
v
er
s
ar
ial
d
ef
en
s
e
m
ec
h
an
is
m
s
s
u
ch
as
ad
v
er
s
ar
ial
tr
ain
i
n
g
,
d
ef
en
s
iv
e
d
is
till
atio
n
,
o
r
g
r
ad
ien
t
m
ask
in
g
to
en
h
an
ce
its
r
o
b
u
s
tn
ess
ag
ain
s
t
s
o
p
h
is
ticated
attac
k
s
.
Dev
elo
p
in
g
m
u
lti
-
s
tag
e
f
r
am
e
wo
r
k
s
wh
er
e
th
e
SD
-
C
AE
m
o
d
el
is
o
n
e
c
o
m
p
o
n
en
t
o
f
a
b
r
o
ad
e
r
d
etec
tio
n
s
y
s
tem
co
u
ld
b
e
a
n
ar
ea
o
f
in
ter
est.
T
h
is
co
u
ld
in
v
o
lv
e
lay
er
in
g
d
if
f
e
r
en
t
d
etec
tio
n
m
o
d
els
to
ca
p
tu
r
e
a
wid
er
r
an
g
e
o
f
ad
v
er
s
ar
ial
b
e
h
av
io
r
s
.
R
esear
ch
co
u
l
d
f
o
cu
s
o
n
d
ev
el
o
p
in
g
ad
ap
tiv
e
lea
r
n
i
n
g
tech
n
i
q
u
es
th
at
allo
w
th
e
m
o
d
el
to
co
n
tin
u
o
u
s
ly
lear
n
f
r
o
m
n
ew
a
d
v
er
s
ar
ial
attac
k
s
an
d
ev
o
lv
e
its
d
etec
tio
n
s
tr
ateg
ies
o
v
er
tim
e.
T
h
is
co
u
ld
in
clu
d
e
o
n
lin
e
lea
r
n
in
g
o
r
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
ap
p
r
o
ac
h
es tailo
r
ed
t
o
m
o
b
ile
s
ec
u
r
ity
.
RE
F
E
R
E
NC
E
S
[
1
]
I
.
A
l
mo
ma
n
i
,
A
.
A
l
k
h
a
y
e
r
,
a
n
d
W
.
El
-
S
h
a
f
a
i
,
“
A
n
a
u
t
o
m
a
t
e
d
v
i
s
i
o
n
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
e
f
f
i
c
i
e
n
t
d
e
t
e
c
t
i
o
n
o
f
a
n
d
r
o
i
d
mal
w
a
r
e
a
t
t
a
c
k
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
2
7
0
0
–
2
7
2
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
4
0
3
4
1
.
[
2
]
J.
S
e
n
a
n
a
y
a
k
e
,
H
.
K
a
l
u
t
a
r
a
g
e
,
a
n
d
M
.
O
.
A
l
-
K
a
d
r
i
,
“
A
n
d
r
o
i
d
m
o
b
i
l
e
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
a
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
El
e
c
t
ro
n
i
c
s (
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
1
3
,
p
.
1
6
0
6
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
0
1
3
1
6
0
6
.
[
3
]
N
.
Z
h
a
n
g
,
Y
.
a
n
Ta
n
,
C
.
Y
a
n
g
,
a
n
d
Y
.
L
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
e
a
t
u
r
e
e
x
p
l
o
r
a
t
i
o
n
f
o
r
a
n
d
r
o
i
d
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
0
2
,
p
.
1
0
7
0
6
9
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
0
.
1
0
7
0
6
9
.
[
4
]
M
.
E.
Z.
N
.
K
a
mb
a
r
,
A
.
Esm
a
e
i
l
z
a
d
e
h
,
Y
.
K
i
m,
a
n
d
K
.
Ta
g
h
v
a
,
“
A
s
u
r
v
e
y
o
n
m
o
b
i
l
e
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
me
t
h
o
d
s
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
2
I
EEE
1
2
t
h
An
n
u
a
l
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
Wo
r
k
sh
o
p
a
n
d
C
o
n
f
e
re
n
c
e
,
C
C
W
C
2
0
2
2
,
I
EEE,
Ja
n
.
2
0
2
2
,
p
p
.
2
1
5
–
2
2
1
.
d
o
i
:
1
0
.
1
1
0
9
/
C
C
W
C
5
4
5
0
3
.
2
0
2
2
.
9
7
2
0
7
5
3
.
[
5
]
G
.
I
a
d
a
r
o
l
a
,
F
.
M
a
r
t
i
n
e
l
l
i
,
F
.
M
e
r
c
a
l
d
o
,
a
n
d
A
.
S
a
n
t
o
n
e
,
“
T
o
w
a
r
d
s
a
n
i
n
t
e
r
p
r
e
t
a
b
l
e
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
mo
b
i
l
e
m
a
l
w
a
r
e
d
e
t
e
c
t
i
o
n
a
n
d
f
a
mi
l
y
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
S
e
c
u
r
i
t
y
,
v
o
l
.
1
0
5
,
p
.
1
0
2
1
9
8
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
s
e
.
2
0
2
1
.
1
0
2
1
9
8
.
[
6
]
T.
S
h
a
r
ma
,
H
.
A
.
D
y
e
r
,
a
n
d
M
.
B
a
sh
i
r
,
“
E
n
a
b
l
i
n
g
u
s
e
r
-
c
e
n
t
e
r
e
d
p
r
i
v
a
c
y
c
o
n
t
r
o
l
s
f
o
r
mo
b
i
l
e
a
p
p
l
i
c
a
t
i
o
n
s
:
C
O
V
I
D
-
1
9
p
e
r
sp
e
c
t
i
v
e
,”
AC
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
rn
e
t
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
1
–
2
4
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
3
4
7
7
7
.
[
7
]
A
.
M
y
l
o
n
a
s,
M
.
T
h
e
o
h
a
r
i
d
o
u
,
a
n
d
D
.
G
r
i
t
z
a
l
i
s
,
“
A
ss
e
ssi
n
g
p
r
i
v
a
c
y
r
i
s
k
s
i
n
a
n
d
r
o
i
d
:
a
u
s
e
r
-
c
e
n
t
r
i
c
a
p
p
r
o
a
c
h
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
ser
i
e
s
L
e
c
t
u
re
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
8
4
1
8
LN
C
S
,
2
0
1
4
,
p
p
.
2
1
–
3
7
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
319
-
0
7
0
7
6
-
6
_
2
.
[
8
]
G
.
L.
S
c
o
c
c
i
a
,
I
.
M
a
l
a
v
o
l
t
a
,
M
.
A
u
t
i
l
i
,
A
.
D
i
S
a
l
l
e
,
a
n
d
P
.
I
n
v
e
r
a
r
d
i
,
“
E
n
h
a
n
c
i
n
g
t
r
u
st
a
b
i
l
i
t
y
o
f
a
n
d
r
o
i
d
a
p
p
l
i
c
a
t
i
o
n
s
v
i
a
u
s
e
r
-
c
e
n
t
r
i
c
f
l
e
x
i
b
l
e
p
e
r
m
i
ssi
o
n
s,”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
S
o
f
t
w
a
r
e
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
7
,
n
o
.
1
0
,
p
p
.
2
0
3
2
–
2
0
5
1
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TSE.
2
0
1
9
.
2
9
4
1
9
3
6
.
[
9
]
N
.
V
i
n
a
y
a
g
a
-
S
u
r
e
sh
k
a
n
t
h
,
R
.
W
i
j
e
w
i
c
k
r
a
m
a
,
A
.
M
a
i
t
i
,
a
n
d
M
.
J
a
d
l
i
w
a
l
a
,
“
A
n
i
n
v
e
st
i
g
a
t
i
v
e
s
t
u
d
y
o
n
t
h
e
p
r
i
v
a
c
y
i
mp
l
i
c
a
t
i
o
n
s
o
f
mo
b
i
l
e
e
-
sco
o
t
e
r
r
e
n
t
a
l
a
p
p
s
,
”
i
n
W
i
S
e
c
2
0
2
2
-
P
ro
c
e
e
d
i
n
g
s o
f
t
h
e
1
5
t
h
AC
M
C
o
n
f
e
re
n
c
e
o
n
S
e
c
u
ri
t
y
a
n
d
Pri
v
a
c
y
i
n
Wi
r
e
l
e
ss a
n
d
Mo
b
i
l
e
N
e
t
w
o
r
k
s
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
M
a
y
2
0
2
2
,
p
p
.
1
2
5
–
1
3
9
.
d
o
i
:
1
0
.
1
1
4
5
/
3
5
0
7
6
5
7
.
3
5
2
8
5
5
1
.
[
1
0
]
S
.
M
i
l
l
a
r
,
N
.
M
c
La
u
g
h
l
i
n
,
J.
M
a
r
t
i
n
e
z
d
e
l
R
i
n
c
o
n
,
a
n
d
P
.
M
i
l
l
e
r
,
“
M
u
l
t
i
-
v
i
e
w
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
z
e
r
o
-
d
a
y
a
n
d
r
o
i
d
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
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
8
,
p
.
1
0
2
7
1
8
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
i
s
a
.
2
0
2
0
.
1
0
2
7
1
8
.
[
1
1
]
A
.
M
a
h
i
n
d
r
u
a
n
d
A
.
L.
S
a
n
g
a
l
,
“
F
S
D
r
o
i
d
:
-
a
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
t
o
d
e
t
e
c
t
m
a
l
w
a
r
e
f
r
o
m
a
n
d
r
o
i
d
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s:
F
S
D
r
o
i
d
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
0
,
n
o
.
9
,
p
p
.
1
3
2
7
1
–
1
3
3
2
3
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
020
-
1
0
3
6
7
-
w.
[
1
2
]
S
.
I
.
I
mt
i
a
z
,
S
.
u
r
R
e
h
ma
n
,
A
.
R
.
Ja
v
e
d
,
Z.
J
a
l
i
l
,
X
.
Li
u
,
a
n
d
W
.
S
.
A
l
n
u
m
a
y
,
“
D
e
e
p
A
M
D
:
d
e
t
e
c
t
i
o
n
a
n
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
n
d
r
o
i
d
mal
w
a
r
e
u
s
i
n
g
h
i
g
h
-
e
f
f
i
c
i
e
n
t
d
e
e
p
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
F
u
t
u
re
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
e
r
S
y
st
e
m
s
,
v
o
l
.
1
1
5
,
p
p
.
8
4
4
–
8
5
6
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
0
.
1
0
.
0
0
8
.
[
1
3
]
P
.
Y
a
d
a
v
,
N
.
M
e
n
o
n
,
V
.
R
a
v
i
,
S
.
V
i
s
h
v
a
n
a
t
h
a
n
,
a
n
d
T.
D
.
P
h
a
m,
“
A
t
w
o
-
s
t
a
g
e
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
i
ma
g
e
-
b
a
se
d
a
n
d
r
o
i
d
mal
w
a
r
e
d
e
t
e
c
t
i
o
n
a
n
d
v
a
r
i
a
n
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
8
,
n
o
.
5
,
p
p
.
1
7
4
8
–
1
7
7
1
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
1
1
/
c
o
i
n
.
1
2
5
3
2
.
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
.
3
,
Ma
r
ch
20
2
5
:
1
672
-
1
6
8
1
1680
[
1
4
]
J.
K
i
m,
Y
.
B
a
n
,
E.
K
o
,
H
.
C
h
o
,
a
n
d
J.
H
.
Y
i
,
“
M
A
P
A
S
:
a
p
r
a
c
t
i
c
a
l
d
e
e
p
l
e
a
r
n
i
n
g
-
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
st
e
m,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
,
v
o
l
.
2
1
,
n
o
.
4
,
p
p
.
7
2
5
–
7
3
8
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
2
0
7
-
02
2
-
0
0
5
7
9
-
6.
[
1
5
]
B
.
B
i
g
g
i
o
,
L
.
D
i
d
a
c
i
,
G
.
F
u
mera
,
a
n
d
F
.
R
o
l
i
,
“
P
o
i
s
o
n
i
n
g
a
t
t
a
c
k
s
t
o
c
o
mp
r
o
m
i
se
f
a
c
e
t
e
m
p
l
a
t
e
s,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
1
3
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
B
i
o
m
e
t
r
i
c
s,
I
C
B
2
0
1
3
,
I
EEE,
Ju
n
.
2
0
1
3
,
p
p
.
1
–
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
B
.
2
0
1
3
.
6
6
1
3
0
0
6
.
[
1
6
]
B
.
B
i
g
g
i
o
,
G
.
F
u
mer
a
,
a
n
d
F
.
R
o
l
i
,
“
P
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
s
y
st
e
ms
u
n
d
e
r
a
t
t
a
c
k
:
d
e
si
g
n
i
ss
u
e
s
a
n
d
r
e
sea
r
c
h
c
h
a
l
l
e
n
g
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
a
n
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
2
8
,
n
o
.
7
,
p
.
1
4
6
0
0
0
2
,
N
o
v
.
2
0
1
4
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
8
0
0
1
4
1
4
6
0
0
0
2
7
.
[1
7]
X
.
Z
h
u
,
“
S
u
p
e
r
-
c
l
a
ss
d
i
scri
mi
n
a
n
t
a
n
a
l
y
si
s
:
a
n
o
v
e
l
s
o
l
u
t
i
o
n
f
o
r
h
e
t
e
r
o
s
c
e
d
a
s
t
i
c
i
t
y
,
”
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
L
e
t
t
e
r
s
,
v
o
l
.
3
4
,
n
o
.
5
,
p
p
.
5
4
5
–
5
5
1
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
r
e
c
.
2
0
1
2
.
1
1
.
0
0
6
.
[
1
8
]
B
.
B
i
g
g
i
o
,
B
.
N
e
l
s
o
n
,
a
n
d
P
.
La
sk
o
v
,
“
P
o
i
so
n
i
n
g
a
t
t
a
c
k
s
a
g
a
i
n
s
t
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
s,”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
9
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
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
,
I
C
ML 2
0
1
2
,
v
o
l
.
2
,
p
p
.
1
8
0
7
–
1
8
1
4
,
2
0
1
2
.
[
1
9
]
C
.
Y
a
n
g
,
Q
.
W
u
,
H
.
L
i
,
a
n
d
Y
.
C
h
e
n
,
“
G
e
n
e
r
a
t
i
v
e
p
o
i
s
o
n
i
n
g
a
t
t
a
c
k
me
t
h
o
d
a
g
a
i
n
s
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
2
0
1
7
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
1
7
0
3
.
0
1
3
4
0
[
2
0
]
C
.
S
z
e
g
e
d
y
,
W
.
Za
r
e
mb
a
,
I
.
S
u
t
s
k
e
v
e
r
,
J.
B
r
u
n
a
,
D
.
Er
h
a
n
,
I
.
G
o
o
d
f
e
l
l
o
w
,
a
n
d
R
.
F
e
r
g
u
s
,
“
I
n
t
r
i
g
u
i
n
g
p
r
o
p
e
r
t
i
e
s
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
a
r
X
i
v
,
2
0
1
3
,
a
r
X
i
v
:
1
3
1
2
.
6
1
9
9
.
[
2
1
]
N
.
C
a
r
l
i
n
i
a
n
d
D
.
W
a
g
n
e
r
,
“
To
w
a
r
d
s
e
v
a
l
u
a
t
i
n
g
t
h
e
r
o
b
u
s
t
n
e
ss
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
2
0
1
7
I
EEE
S
y
m
p
o
si
u
m
o
n
S
e
c
u
ri
t
y
a
n
d
Pri
v
a
c
y
(
S
P)
,
I
EEE,
M
a
y
2
0
1
7
,
p
p
.
3
9
–
57
,
d
o
i
:
1
0
.
1
1
0
9
/
S
P
.
2
0
1
7
.
4
9
.
[
2
2
]
S
.
M
.
M
o
o
s
a
v
i
-
D
e
z
f
o
o
l
i
,
A
.
F
a
w
z
i
,
O
.
F
a
w
z
i
,
a
n
d
P
.
F
r
o
ss
a
r
d
,
“
U
n
i
v
e
r
sa
l
a
d
v
e
r
s
a
r
i
a
l
p
e
r
t
u
r
b
a
t
i
o
n
s
,
”
a
r
X
i
v
,
2
0
1
7
,
a
r
X
i
v
:
1
6
1
0
.
0
8
4
0
1
.
[
2
3
]
D
.
W
a
r
d
e
-
F
a
r
l
e
y
a
n
d
I
.
G
o
o
d
f
e
l
l
o
w
,
“
A
d
v
e
r
s
a
r
i
a
l
p
e
r
t
u
r
b
a
t
i
o
n
s
o
f
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
i
n
P
e
rt
u
r
b
a
t
i
o
n
s,
O
p
t
i
m
i
z
a
t
i
o
n
,
a
n
d
S
t
a
t
i
st
i
c
s
,
T
h
e
M
I
T
P
r
e
ss,
2
0
1
6
,
p
p
.
3
1
1
–
3
4
2
,
d
o
i
:
1
0
.
7
5
5
1
/
m
i
t
p
r
e
ss
/
1
0
7
6
1
.
0
0
3
.
0
0
1
2
.
[
2
4
]
N
.
P
a
p
e
r
n
o
t
,
P
.
M
c
D
a
n
i
e
l
,
S
.
J
h
a
,
M
.
F
r
e
d
r
i
k
s
o
n
,
Z.
B
.
C
e
l
i
k
,
a
n
d
A
.
S
w
a
mi
,
“
T
h
e
l
i
mi
t
a
t
i
o
n
s
o
f
d
e
e
p
l
e
a
r
n
i
n
g
i
n
a
d
v
e
r
sari
a
l
set
t
i
n
g
s
,
”
i
n
2
0
1
6
I
EE
E
E
u
r
o
p
e
a
n
S
y
m
p
o
si
u
m
o
n
S
e
c
u
r
i
t
y
a
n
d
Pri
v
a
c
y
(
E
u
ro
S
&P)
,
I
EEE,
M
a
r
.
2
0
1
6
,
p
p
.
3
7
2
–
387
,
d
o
i
:
1
0
.
1
1
0
9
/
Eu
r
o
S
P
.
2
0
1
6
.
3
6
.
[
2
5
]
Y
.
Z
h
o
u
a
n
d
X
.
Ji
a
n
g
,
“
D
i
ss
e
c
t
i
n
g
a
n
d
r
o
i
d
ma
l
w
a
r
e
:
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
a
n
d
e
v
o
l
u
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
I
EE
E
S
y
m
p
o
s
i
u
m
o
n
S
e
c
u
r
i
t
y
a
n
d
P
ri
v
a
c
y
,
I
EEE,
M
a
y
2
0
1
2
,
p
p
.
9
5
–
1
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
S
P
.
2
0
1
2
.
1
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
a
n
j
a
ik
a
n
th
E
Va
d
a
k
k
e
th
il
S
o
m
a
n
a
th
a
n
Pi
l
la
i
(
se
n
io
r
m
e
m
b
e
r
,
IEE
E)
h
o
l
d
s
a
n
M
.
S
.
in
S
o
f
twa
re
En
g
i
n
e
e
rin
g
fro
m
Th
e
Un
iv
e
rsity
o
f
T
e
x
a
s
a
t
Au
stin
,
Tex
a
s,
USA,
a
n
d
a
B
.
E
.
fro
m
t
h
e
Un
i
v
e
rsity
o
f
Ca
li
c
u
t,
Ke
ra
la,
In
d
ia
.
Cu
rre
n
tl
y
p
u
rsu
i
n
g
a
Ph
.
D
.
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
th
e
Un
i
v
e
rsity
o
f
No
rt
h
Da
k
o
ta,
G
ra
n
d
F
o
r
k
s,
N
o
rth
Da
k
o
ta,
USA,
h
is
re
se
a
rc
h
sp
a
n
s
d
iv
e
rse
a
re
a
s
su
c
h
a
s
m
o
b
il
e
n
e
two
rk
s,
n
e
tw
o
r
k
se
c
u
rit
y
,
p
ri
v
a
c
y
,
lo
c
a
ti
o
n
-
b
a
se
d
se
rv
ice
s,
a
n
d
m
isin
fo
rm
a
ti
o
n
d
e
tec
ti
o
n
.
He
is
a
p
ro
u
d
m
e
m
b
e
r
o
f
S
ig
m
a
Xi,
th
e
sc
ien
ti
fic
re
se
a
rc
h
h
o
n
o
r
so
c
iety
,
u
n
d
e
r
li
n
in
g
h
is
c
o
m
m
it
m
e
n
t
to
a
d
v
a
n
c
in
g
sc
ien
ti
fic
k
n
o
wle
d
g
e
a
n
d
re
se
a
rc
h
e
x
c
e
ll
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s.e
v
a
d
a
k
k
e
t
h
il
@u
n
d
.
e
d
u
.
Dr
.
Ro
h
ith
V
a
ll
a
b
h
a
n
e
n
i
is
a
d
e
d
ica
ted
w
o
rk
e
r
wit
h
a
str
o
n
g
wo
rk
e
t
h
ic
in
lea
d
in
g
tea
m
s
to
so
lv
e
o
r
g
a
n
iza
ti
o
n
a
l
issu
e
s.
He
is
c
a
p
a
b
le
o
f
l
e
a
rn
in
g
a
ll
a
sp
e
c
ts
o
f
in
fo
rm
a
ti
o
n
with
in
a
c
o
m
p
a
n
y
a
n
d
u
sin
g
th
e
tec
h
n
ica
l
k
n
o
wle
d
g
e
a
n
d
b
u
sin
e
s
s
b
a
c
k
g
ro
u
n
d
t
o
e
ffe
c
ti
v
e
l
y
a
n
a
l
y
z
e
se
c
u
rit
y
m
e
a
su
re
s
to
d
e
term
in
e
th
e
ir
e
ffe
c
ti
v
e
n
e
ss
i
n
o
rd
e
r
to
stre
n
g
t
h
e
n
th
e
o
v
e
ra
ll
se
c
u
rit
y
p
o
stu
re
.
He
h
a
s
g
re
a
t
wo
rk
e
th
ic
a
n
d
o
u
tstan
d
in
g
tea
m
lea
d
e
rsh
ip
s
k
il
ls
a
n
d
se
e
k
to
a
c
c
o
m
p
li
sh
o
r
g
a
n
iza
ti
o
n
a
l
g
o
a
ls
,
wh
il
e
g
r
o
win
g
in
k
n
o
wle
d
g
e
a
n
d
e
x
p
e
rien
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ro
h
it
.
v
a
ll
a
b
h
a
n
e
n
i
.
2
2
2
2
@g
m
a
il
.
c
o
m
.
S
r
in
iv
a
s
A
V
a
d
d
a
d
i
is
a
d
y
n
a
m
ic
a
n
d
f
o
rwa
rd
-
th
in
k
in
g
p
ro
fe
ss
io
n
a
l
i
n
th
e
field
o
f
Clo
u
d
a
n
d
De
v
S
e
c
Op
s.
Wi
th
a
so
li
d
e
d
u
c
a
ti
o
n
a
l
f
o
u
n
d
a
ti
o
n
in
c
o
m
p
u
ter
sc
ien
c
e
,
S
rin
i
v
a
s
e
m
b
a
rk
e
d
o
n
a
jo
u
rn
e
y
o
f
c
o
n
ti
n
u
o
u
s
lea
rn
i
n
g
a
n
d
p
r
o
fe
ss
io
n
a
l
g
r
o
wth
.
T
h
e
ir
re
len
tl
e
ss
p
u
rsu
i
t
o
f
k
n
o
wle
d
g
e
a
n
d
c
o
m
m
it
m
e
n
t
t
o
sta
y
in
g
a
t
t
h
e
fo
re
fro
n
t
o
f
i
n
d
u
str
y
a
d
v
a
n
c
e
m
e
n
ts
h
a
s
e
a
rn
e
d
th
e
m
re
c
o
g
n
it
i
o
n
a
s
a
th
o
u
g
h
t
lea
d
e
r
in
th
e
c
lo
u
d
a
n
d
De
v
S
e
c
Op
s sp
a
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
Vs
a
d
9
3
@g
m
a
il
.
c
o
m
.
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
A
u
to
ma
ted
a
d
ve
r
s
a
r
ia
l d
etec
tio
n
in
mo
b
ile
a
p
p
s
b
a
s
ed
…
(
S
a
n
ja
ika
n
t
h
E
V
a
d
a
kk
eth
il S
o
m
a
n
a
th
a
n
P
illa
i
)
1681
S
a
n
t
o
sh
Re
d
d
y
Add
u
la
a
se
n
io
r
m
e
m
b
e
r
o
f
IEE
E,
is
a
re
se
a
rc
h
sc
h
o
lar
a
t
th
e
Un
i
v
e
rsity
o
f
th
e
C
u
m
b
e
rlan
d
s.
His
e
d
u
c
a
ti
o
n
a
l
q
u
a
li
fica
ti
o
n
s
in
c
lu
d
e
a
P
h
.
D.
a
n
d
a
M
a
ste
r
o
f
S
c
ien
c
e
i
n
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
.
Wi
t
h
e
x
ten
siv
e
e
x
p
e
rien
c
e
i
n
t
h
e
I
T
in
d
u
stry
,
h
e
h
a
s
d
e
m
o
n
stra
ted
e
x
p
e
rti
se
a
c
ro
ss
m
u
l
ti
p
le
d
o
m
a
in
s.
S
a
n
to
sh
is
a
n
in
n
o
v
a
to
r
wh
o
h
a
s
m
a
d
e
sig
n
ifi
c
a
n
t
c
o
n
tri
b
u
ti
o
n
s
t
o
a
c
a
d
e
m
ic
re
se
a
rc
h
th
ro
u
g
h
h
is
a
rti
c
les
a
s
a
n
a
u
th
o
r
a
n
d
c
o
-
a
u
t
h
o
r
.
Ad
d
it
io
n
a
ll
y
,
h
e
se
rv
e
s
a
s
a
r
e
v
iew
e
r
f
o
r
e
ste
e
m
e
d
jo
u
rn
a
ls,
d
e
m
o
n
stra
ti
n
g
h
is
c
o
m
m
it
m
e
n
t
to
a
d
v
a
n
c
in
g
k
n
o
wle
d
g
e
a
n
d
u
p
h
o
l
d
in
g
h
i
g
h
sta
n
d
a
rd
s
i
n
sc
h
o
larly
p
u
b
l
ica
ti
o
n
s
wit
h
in
h
is
field
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
n
to
sh
a
d
d
u
lait@
g
m
a
il
.
c
o
m
.
Dr
.
Bh
u
v
a
n
e
sh
Ana
n
th
a
n
re
c
e
iv
e
d
th
e
B.
E.
d
e
g
re
e
in
E
lec
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
ri
n
g
fr
o
m
An
n
a
Un
i
v
e
rsity
i
n
2
0
1
2
,
M
.
T
e
c
h
.
in
P
o
we
r
S
y
ste
m
En
g
i
n
e
e
rin
g
fro
m
Ka
las
a
li
n
g
a
m
Un
iv
e
rsity
in
2
0
1
4
a
n
d
P
h
.
D.
d
e
g
re
e
fro
m
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
o
f
An
n
a
U
n
iv
e
rsit
y
in
2
0
1
9
.
He
h
a
s p
u
b
l
ish
e
d
m
o
re
th
a
n
6
5
p
a
p
e
rs
in
re
p
u
te
d
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls,
2
5
p
a
p
e
rs
in
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
1
0
b
o
o
k
s.
He
is
a
li
fe
ti
m
e
m
e
m
b
e
r
o
f
In
tern
a
ti
o
n
a
l
S
o
c
iety
fo
r
Re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t,
In
tern
a
ti
o
n
a
l
As
so
c
iat
io
n
o
f
En
g
i
n
e
e
rs.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
h
u
v
a
n
e
sh
.
a
n
a
n
t
h
a
n
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.