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
8
,
No
.
2
,
Ma
y
20
2
5
,
p
p
.
1
402
~
1
4
1
0
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
8
.
i
2
.
pp
1
4
0
2
-
1
4
1
0
1402
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Credit
card
fraud
det
ec
tion usin
g
C
NN and LST
M
Nis
ha
nt
Upa
d
hy
a
y
1
,
Nidh
i B
a
ns
a
l
2
,
Div
y
a
Ra
s
t
o
g
i
3
,
Re
k
h
a
Cha
t
urv
edi
4
,
M
o
ha
m
m
a
d
Asi
m
1
,
Su
ra
j
M
a
lik
5
,
K
hel P
ra
ka
s
h J
a
y
a
nt
6
,
Abha
y
K
um
a
r
Va
j
pa
y
ee
7
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
S
h
a
r
d
a
U
n
i
v
e
r
si
t
y
,
G
r
e
a
t
e
r
N
o
i
d
a
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
M
a
n
a
v
R
a
c
h
n
a
I
n
t
e
r
n
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
R
e
se
a
r
c
h
a
n
d
S
t
u
d
i
e
s (D
e
e
me
d
t
o
b
e
U
n
i
v
e
r
si
t
y
)
,
F
a
r
i
d
a
b
a
d
,
H
a
r
y
a
n
a
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
,
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
h
a
r
d
a
U
n
i
v
e
r
si
t
y
,
G
r
e
a
t
e
r
N
o
i
d
a
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
D
a
t
a
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
I
n
f
o
r
ma
t
i
o
n
S
e
c
u
r
i
t
y
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
M
a
n
i
p
a
l
U
n
i
v
e
r
si
t
y
Ja
i
p
u
r
,
Jai
p
u
r
R
a
j
a
s
t
h
a
n
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
I
I
M
T
U
n
i
v
e
r
si
t
y
,
M
e
e
r
u
t
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
R
a
j
K
u
m
a
r
G
o
e
l
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
G
h
a
z
i
a
b
a
d
,
I
n
d
i
a
7
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
I
n
st
i
t
u
t
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
S
i
t
a
p
u
r
,
L
u
c
k
n
o
w
,
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
May
13
,
2
0
2
4
R
ev
is
ed
Oct
10
,
2
0
2
4
Acc
ep
ted
Oct
30
,
2
0
2
4
Cre
d
it
c
a
rd
fra
u
d
is
a
n
e
v
o
lv
i
n
g
p
ro
b
lem
with
th
e
fra
u
d
ste
rs
d
e
v
e
lo
p
in
g
n
e
w
tec
h
n
o
l
o
g
ies
t
o
p
e
rf
o
rm
fra
u
d
.
F
r
a
u
d
ste
rs h
a
v
e
f
o
u
n
d
d
iv
e
rse
wa
y
s
to
m
a
k
e
a
fra
u
d
tra
n
sa
c
ti
o
n
to
th
e
c
a
rd
h
o
l
d
e
r.
Th
u
s,
d
e
tec
ti
n
g
su
sp
icio
u
s
b
e
h
a
v
io
r
o
f
a
c
a
rd
is
c
rit
ica
l
fo
r
p
re
v
e
n
ti
n
g
fr
a
u
d
u
le
n
t
tran
sa
c
ti
o
n
s
t
o
h
a
p
p
e
n
.
Artifi
c
ial
in
telli
g
e
n
c
e
tec
h
n
iq
u
e
s,
i
n
p
a
rti
c
u
lar
d
e
e
p
lea
rn
i
n
g
a
lg
o
rit
h
m
s
c
a
n
tac
k
le
th
e
se
c
re
d
it
c
a
rd
fra
u
d
a
tt
a
c
k
s
b
y
id
e
n
ti
fy
i
n
g
p
a
tt
e
rn
s
t
h
a
t
p
re
d
ict
tran
sa
c
ti
o
n
s
a
s
fra
u
d
o
r
le
g
it
im
a
te.
On
e
-
d
ime
n
si
o
n
a
l
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(
1
D
CNN
)
a
n
d
l
o
n
g
s
h
o
rt
-
term
m
e
m
o
ry
(
L
S
TM
)
b
o
th
p
e
rfo
rm
s
we
ll
o
n
t
h
e
se
q
u
e
n
ti
a
l
d
a
ta
e
sp
e
c
ially
o
n
tran
sa
c
ti
o
n
s
d
a
ta,
y
e
t
th
e
re
a
re
n
o
t
m
a
n
y
stu
d
ies
d
o
n
e
o
n
c
o
m
b
in
i
n
g
th
e
se
two
a
lg
o
rit
h
m
s
to
m
a
k
e
a
n
e
ffe
c
ti
v
e
fra
u
d
d
e
tec
ti
o
n
a
p
p
r
o
a
c
h
.
Ho
we
v
e
r,
th
e
d
a
tas
e
t
is
h
ig
h
l
y
i
m
b
a
lan
c
e
d
c
o
n
tain
i
n
g
o
n
l
y
4
9
2
fra
u
d
tran
sa
c
ti
o
n
o
u
t
o
f
tw
o
lac
s
t
ra
n
sa
c
ti
o
n
s.
In
th
is
e
x
p
e
rime
n
tal
stu
d
y
,
firstl
y
d
a
ta
se
ts
will
g
e
t
p
re
p
a
re
d
b
y
u
sin
g
d
iffere
n
t
sa
m
p
li
n
g
tec
h
n
i
q
u
e
s
a
lo
n
g
wit
h
th
e
ir
h
y
b
rid
tec
h
n
iq
u
e
s
se
c
o
n
d
l
y
,
o
b
se
rv
i
n
g
th
e
p
e
rfo
rm
a
n
c
e
o
f
i
n
d
i
v
id
u
a
l
C
NN
a
n
d
LS
TM
o
n
t
h
e
d
a
tas
e
ts,
fin
a
ll
y
o
n
th
o
se
d
a
tas
e
ts
in
wh
ich
CNN
a
n
d
LS
TM
a
re
p
e
rf
o
rm
in
g
we
ll
,
b
y
imp
lem
e
n
ti
n
g
e
n
se
m
b
le
o
n
th
o
se
d
a
ta.
Th
e
p
e
rfo
rm
a
n
c
e
o
f
th
e
e
n
se
m
b
les
is
o
b
se
rv
e
d
u
sin
g
t
h
e
p
e
rfo
rm
a
n
c
e
m
e
tri
c
s
n
a
m
e
ly
a
c
c
u
ra
c
y
,
F
1
-
sc
o
re
,
p
re
c
isio
n
a
n
d
re
c
a
ll
.
In
th
e
p
ro
p
o
se
d
e
x
p
e
rime
n
tal
stu
d
y
,
g
e
tt
in
g
th
e
F
1
-
sc
o
re
o
f
9
9
.
9
6
%
a
n
d
9
9
.
8
9
%
in
e
n
se
m
b
le:
e
a
rly
f
u
sio
n
a
n
d
e
n
se
m
b
le:
late
fu
sio
n
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
C
NN
C
r
ed
it c
ar
d
Fra
u
d
d
etec
tio
n
L
STM
On
lin
e
tr
an
s
ac
tio
n
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
:
R
ek
h
a
C
h
atu
r
v
ed
i
Dep
ar
tm
en
t o
f
Data
Scien
ce
an
d
E
n
g
in
ee
r
in
g
,
Sch
o
o
l o
f
I
n
f
o
r
m
atio
n
Secu
r
ity
an
d
Data
Scien
ce
Ma
n
ip
al
Un
iv
er
s
ity
J
aip
u
r
J
aip
u
r
R
ajasth
an
,
I
n
d
ia
E
m
ail:
r
ek
h
a.
ch
at
u
r
v
e
d
i@
jaip
u
r
.
m
an
ip
al.
e
d
u
1.
I
NT
RO
D
UCT
I
O
N
W
ith
th
e
d
ig
ital
tr
an
s
ac
tio
n
s
,
m
o
d
er
n
b
ak
i
n
g
is
g
ettin
g
s
m
ar
t
tr
an
s
ac
tio
n
s
o
v
e
r
th
e
in
ter
n
et.
Ho
wev
er
,
th
is
ea
s
e
o
f
u
s
e
h
as
attr
ac
ted
m
alicio
u
s
ac
to
r
s
an
d
in
cr
ea
s
ed
c
o
n
ce
r
n
s
ab
o
u
t
cr
ed
it
ca
r
d
f
r
au
d
.
T
h
e
p
o
ten
tial
f
in
an
cial
lo
s
s
es
ar
e
s
ig
n
if
ican
t,
with
r
ep
o
r
ts
in
d
icatin
g
b
illi
o
n
s
o
f
eu
r
o
s
lo
s
t
an
n
u
ally
in
E
u
r
o
p
e
alo
n
e
[
1
]
.
Fra
u
d
s
ter
s
ex
p
lo
i
t
v
ar
io
u
s
tactics,
f
r
o
m
co
m
p
r
o
m
is
in
g
d
ata
o
n
p
u
b
lic
W
i
-
Fi
to
u
tili
z
in
g
u
n
d
er
g
r
o
u
n
d
m
a
r
k
etp
lace
s
[
2
]
.
W
h
ile
r
esear
ch
er
s
h
av
e
d
e
v
elo
p
ed
n
u
m
er
o
u
s
f
r
au
d
d
etec
t
io
n
m
eth
o
d
o
lo
g
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
C
r
ed
it c
a
r
d
fr
a
u
d
d
etec
tio
n
u
s
in
g
C
N
N
a
n
d
LS
TM
…
(
N
is
h
a
n
t U
p
a
d
h
y
a
y
)
1403
th
ey
o
f
ten
s
tr
u
g
g
le
with
h
i
g
h
f
alse
p
o
s
itiv
e
r
ates
a
n
d
d
if
f
ic
u
lty
ad
a
p
tin
g
to
e
v
o
lv
in
g
f
r
au
d
p
atter
n
s
[
3
]
,
[
4
]
.
Ad
d
itio
n
ally
,
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
r
ai
s
e
co
n
ce
r
n
s
ab
o
u
t
d
ata
p
r
i
v
ac
y
.
Dee
p
lear
n
in
g
alg
o
r
ith
m
s
s
u
ch
as
co
n
v
o
lu
t
io
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN
)
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
,
h
a
v
e
em
er
g
ed
as
ef
f
ec
tiv
e
to
o
ls
f
o
r
d
etec
tin
g
f
r
a
u
d
b
y
id
en
tify
i
n
g
in
tr
icate
p
atter
n
s
a
n
d
b
eh
a
v
io
r
s
in
t
r
an
s
ac
tio
n
d
ata.
Ho
wev
er
,
d
u
e
to
h
ig
h
ly
i
m
b
alan
ce
d
n
at
u
r
e
o
f
th
e
c
r
ed
it
ca
r
d
d
ata,
im
p
lem
e
n
tin
g
th
es
e
alg
o
r
ith
m
s
p
o
s
es
a
s
ig
n
if
ican
t c
h
allen
g
e.
W
h
ile,
in
d
iv
id
u
al
s
tu
d
ies
h
av
e
s
h
o
wn
p
r
o
m
is
in
g
r
esu
lts
in
f
r
au
d
d
etec
tio
n
u
s
in
g
C
NNs
an
d
L
STM
s
,
th
er
e
is
lim
ited
r
esear
ch
o
n
co
m
b
in
in
g
th
ese
two
alg
o
r
ith
m
s
to
b
u
ild
a
p
o
wer
f
u
l
e
n
s
em
b
le
f
o
r
f
r
au
d
d
etec
tio
n
[
5
]
.
T
h
is
e
x
p
er
im
e
n
tal
s
tu
d
y
aim
s
to
a
d
d
r
ess
th
is
g
ap
b
y
b
u
ild
in
g
an
ef
f
icien
t
en
s
em
b
le
th
r
o
u
g
h
en
s
em
b
le
th
r
o
u
g
h
ea
r
ly
an
d
late
f
u
s
io
n
s
o
f
C
NNs a
n
d
L
STM
s
.
T
o
ac
co
u
n
t
f
o
r
th
e
im
b
ala
n
ce
d
d
ataset,
v
ar
io
u
s
s
am
p
lin
g
tech
n
iq
u
es
ar
e
in
co
r
p
o
r
ated
,
in
clu
d
in
g
h
y
b
r
id
s
am
p
lin
g
m
eth
o
d
s
,
to
ev
alu
ate
m
o
d
el
p
er
f
o
r
m
an
ce
u
n
d
er
d
if
f
er
e
n
t c
ir
cu
m
s
tan
ce
s
.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
im
p
lem
en
tatio
n
in
cl
u
d
e
v
a
r
io
u
s
k
ey
p
o
in
ts
wh
ich
ar
e
lis
ted
h
e
r
e
ca
p
ab
le
o
f
m
a
k
in
g
th
e
s
y
s
tem
ef
f
icien
t
f
o
r
u
s
ef
u
l
tr
an
s
ac
tio
n
s
.
E
x
ec
u
tiv
e
s
u
m
m
ar
y
:
c
r
ed
it
ca
r
d
f
r
au
d
is
a
n
e
v
o
lv
in
g
p
r
o
b
lem
wh
ich
ca
n
co
s
t
b
u
s
in
ess
es
an
d
p
eo
p
le
m
o
n
ey
.
T
h
is
s
tu
d
y
in
v
esti
g
ates
th
e
v
iab
ilit
y
o
f
d
etec
tin
g
cr
ed
it
ca
r
d
f
r
a
u
d
u
s
in
g
an
e
n
s
em
b
le
m
o
d
el
th
at
co
m
b
in
es
L
STM
w
ith
C
NN
s
[
6
]
,
[
7
]
.
T
h
is
s
tr
ateg
y
m
ay
in
c
r
ea
s
e
th
e
ac
cu
r
ac
y
o
f
f
r
au
d
d
etec
tio
n
b
y
u
tili
zin
g
th
e
a
d
v
an
tag
es o
f
b
o
th
C
NN
an
d
L
STM
in
p
r
o
ce
s
s
in
g
s
eq
u
en
tial
d
ata
an
d
co
llectin
g
s
p
atial
in
f
o
r
m
atio
n
.
Pro
ject
d
escr
ip
tio
n
:
th
e
p
r
o
jects
o
b
jectiv
e
is
to
u
s
e
a
C
NN
-
L
STM
en
s
em
b
le
m
o
d
el
t
o
d
esig
n
a
n
d
ass
ess
a
cr
ed
it
ca
r
d
f
r
a
u
d
d
etec
tio
n
s
y
s
tem
.
C
r
ed
it
ca
r
d
tr
an
s
ac
tio
n
d
ata,
co
m
p
r
is
in
g
s
eq
u
en
tial
(
s
u
c
h
as
a
tr
an
s
ac
tio
n
h
is
to
r
y
)
an
d
s
tatic
(
s
u
ch
as
ca
r
d
h
o
ld
er
s
’
d
etails
an
d
lo
ca
tio
n
)
in
f
o
r
m
atio
n
,
will
b
e
p
r
o
ce
s
s
ed
b
y
th
e
s
y
s
tem
.
Ma
r
k
et
an
aly
s
is
:
f
in
an
cial
in
s
ti
tu
tio
n
s
s
u
c
h
as
b
an
k
s
,
cr
ed
it
ca
r
d
co
m
p
a
n
ies
ar
e
lo
o
k
i
n
g
t
o
en
h
an
ce
t
h
eir
f
r
a
u
d
d
etec
tio
n
s
k
ills
ar
e
p
ar
t
o
f
th
e
tar
g
et
m
ar
k
et.
T
h
e
g
lo
b
al
f
r
au
d
lo
s
s
es
ar
e
ex
p
ec
ted
to
r
ea
ch
$
2
0
6
b
illi
o
n
b
y
2
0
2
5
,
in
d
icatin
g
th
e
s
ca
le
o
f
th
is
m
a
r
k
et
[
8
]
,
[
9
]
.
C
u
r
r
e
n
t
f
r
au
d
d
etec
tio
n
p
r
o
g
r
am
s
p
r
o
v
id
ed
b
y
s
ec
u
r
ity
f
ir
m
s
an
d
f
i
n
an
cial
in
s
titu
tio
n
s
th
em
s
elv
es a
r
e
co
m
p
etito
r
s
.
B
y
co
m
b
in
in
g
th
e
b
en
ef
its
o
f
b
o
th
C
NNs
an
d
L
STM
s
,
o
u
r
s
u
g
g
ested
en
s
em
b
le
m
o
d
el
m
a
y
b
e
ad
v
a
n
tag
eo
u
s
in
ter
m
s
o
f
in
cr
ea
s
ed
d
etec
tio
n
r
a
te.
T
ec
h
n
ical
f
ea
s
ib
ilit
y
in
clu
d
es:
−
Stre
n
g
th
s
:
C
NNs
ar
e
p
ar
ticu
lar
ly
g
o
o
d
at
r
em
o
v
in
g
g
eo
g
r
ap
h
ical
ch
ar
ac
ter
is
tics
,
s
u
ch
as
lo
ca
tio
n
,
ca
r
d
h
o
ld
e
r
d
etails
f
r
o
m
d
ata.
T
r
an
s
ac
tio
n
h
is
to
r
y
is
o
n
e
ty
p
e
o
f
s
eq
u
en
tial
d
ata
th
at
L
STM
s
ar
e
g
o
o
d
at
ca
p
tu
r
in
g
tem
p
o
r
al
tr
e
n
d
s
in
.
Fu
s
in
g
b
o
th
m
o
d
els
th
r
o
u
g
h
en
s
em
b
le
lear
n
in
g
m
ay
r
esu
lt
in
im
p
r
o
v
e
d
p
er
f
o
r
m
an
ce
.
−
C
h
allen
g
es:
d
u
e
to
th
e
m
o
d
el’
s
in
tr
icac
y
,
tr
ain
in
g
will
tak
e
a
lar
g
e
am
o
u
n
t
o
f
p
r
o
ce
s
s
in
g
p
o
wer
.
I
t
ca
n
tak
e
a
wh
ile
t
o
f
i
n
e
-
tu
n
e
th
e
h
y
p
er
-
p
ar
am
eter
s
f
o
r
th
e
C
N
N
an
d
L
STM
co
m
p
o
n
en
ts
.
Fo
r
tr
ain
in
g
to
b
e
ef
f
ec
tiv
e,
a
s
izea
b
le,
lab
eled
c
r
ed
it c
ar
d
tr
a
n
s
ac
tio
n
d
ataset
m
u
s
t b
e
av
ailab
le.
−
T
ec
h
n
i
c
al
a
s
s
ets:
a
n
u
m
b
er
o
f
o
p
en
-
s
o
u
r
ce
f
r
am
ewo
r
k
s
,
s
u
ch
as
Py
T
o
r
ch
an
d
T
en
s
o
r
Flo
w,
ca
n
m
ak
e
a
m
o
d
el
d
ev
elo
p
m
en
t
ea
s
ier
.
P
latf
o
r
m
f
o
r
clo
u
d
c
o
m
p
u
tin
g
p
r
o
v
id
e
s
ca
lab
le
r
eso
u
r
ce
s
f
o
r
s
o
p
h
is
ticated
m
o
d
el
tr
ain
in
g
.
Fig
u
r
e
1
is
ab
le
to
s
h
o
w
t
h
e
f
l
o
w
o
f
wo
r
k
o
r
a
p
lan
f
o
r
ex
ec
u
tin
g
a
task
.
W
h
er
e
th
e
d
ata
s
et
n
ee
d
s
to
b
e
f
etch
ed
f
ir
s
t
in
o
r
d
er
to
g
et
it
in
to
p
r
ep
r
o
ce
s
s
in
g
[
1
0
]
,
[
1
1
]
.
T
h
is
will
f
u
r
th
er
m
o
v
e
to
war
d
s
n
ec
ess
ar
y
im
p
lem
en
tatio
n
.
A
n
d
f
in
ally
,
t
h
e
s
y
s
tem
will
b
e
ab
le
to
s
h
o
w
th
e
r
esu
lts
.
C
NN
ar
ch
itectu
r
es
th
at
wer
e
cr
ea
ted
to
h
an
d
le
th
e
q
u
alities
o
f
th
e
d
ataset
wer
e
u
s
ed
in
th
e
m
eth
o
d
o
l
o
g
y
u
s
ed
in
th
is
wo
r
k
.
T
h
is
ap
p
r
o
ac
h
estab
lis
h
ed
a
f
o
u
n
d
atio
n
al
b
en
ch
m
ar
k
f
o
r
th
e
ev
alu
atio
n
o
f
m
o
r
e
c
o
m
p
lex
ar
ch
itect
u
r
es.
Dee
p
C
NNs
:
co
m
m
o
n
l
y
r
e
f
er
r
ed
to
as
C
NNs,
C
o
n
v
Nets,
o
r
DC
NNs,
a
r
e
in
t
h
e
f
ield
s
o
f
co
m
p
u
ter
v
is
io
n
a
n
d
im
a
g
e
p
r
o
ce
s
s
in
g
b
ec
au
s
e
o
f
th
eir
a
b
ilit
y
to
in
ter
p
r
et
d
ata
i
n
th
e
f
o
r
m
o
f
m
a
n
y
ar
r
ay
s
.
As
s
ee
n
in
Fig
u
r
e
2
,
th
e
f
ir
s
t
l
ay
er
,
wh
ich
is
o
f
te
n
a
co
n
v
o
l
u
tio
n
al
lay
er
,
u
s
es
a
s
et
o
f
m
ath
em
atica
l
o
p
er
atio
n
s
to
id
en
tif
y
f
ea
t
u
r
es
in
clu
d
in
g
ed
g
es,
tex
tu
r
es,
an
d
s
h
ap
es.
Su
b
s
eq
u
en
tly
,
th
e
p
o
o
lin
g
la
y
er
s
r
e
d
u
ce
th
e
s
p
atial
d
im
en
s
io
n
s
o
f
th
e
r
ep
r
esen
tatio
n
,
th
e
r
eb
y
r
e
d
u
cin
g
th
e
n
u
m
b
er
o
f
p
a
r
am
ete
r
s
an
d
ca
lcu
latio
n
s
with
in
th
e
n
etwo
r
k
.
T
h
e
n
etw
o
r
k
u
s
u
ally
co
n
s
is
ts
o
f
f
u
lly
co
n
n
ec
ted
lay
er
s
af
ter
s
ev
er
al
co
n
v
o
lu
tio
n
al
a
n
d
p
o
o
lin
g
lay
e
r
s
.
T
h
ese
lay
er
s
ar
e
ty
p
ical
n
eu
r
al
n
etwo
r
k
lay
e
r
s
in
wh
ich
a
lear
n
ed
weig
h
t
co
n
n
ec
ts
ea
ch
in
p
u
t
to
ea
ch
o
u
tp
u
t.
T
o
ca
te
g
o
r
ize
o
r
p
r
ed
ict
th
e
o
u
tp
u
t
at
th
is
p
o
in
t,
th
e
n
etwo
r
k
in
teg
r
ates
all
o
f
th
e
f
ea
tu
r
es
th
at
it h
as lea
r
n
ed
f
r
o
m
th
e
ea
r
lier
lay
er
s
.
2
.
1
.
Da
t
a
s
et
I
n
Sep
tem
b
er
2
0
1
3
,
E
u
r
o
p
ea
n
ca
r
d
h
o
ld
e
r
s
co
n
d
u
cted
cr
ed
it c
ar
d
tr
an
s
ac
tio
n
s
th
at
ar
e
in
clu
d
ed
in
th
e
d
atab
ases
.
T
h
er
e
ar
e
4
9
2
f
r
a
u
d
s
o
u
t
o
f
2
8
4
,
8
0
7
tr
a
n
s
ac
tio
n
s
in
th
is
d
ata
s
et
s
h
o
wn
b
y
F
i
g
u
r
e
s
3
an
d
4
.
T
h
e
g
r
ap
h
a
b
o
v
e
d
e
m
o
n
s
tr
ates
th
a
t
th
e
two
m
o
s
t
p
o
p
u
lar
tr
an
s
ac
tio
n
m
eth
o
d
s
ar
e
T
R
ANSFER
an
d
C
ASH_
OUT
.
I
t
also
d
em
o
n
s
tr
ates
th
at
f
r
au
d
ca
n
o
n
l
y
o
cc
u
r
th
r
o
u
g
h
th
e
s
e
two
m
eth
o
d
s
.
T
h
e
m
o
d
el
h
as
id
en
tifie
d
f
alse
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
8
,
No
.
2
,
May
20
2
5
:
1
4
0
2
-
1
4
1
0
1404
p
o
s
itiv
es
b
u
t
n
ev
er
let
ev
en
a
s
in
g
le
f
alse
n
eg
ativ
e
wh
ich
is
m
o
r
e
im
p
o
r
tan
t
th
an
FP
.
Sin
ce
we
ca
n
’
t
m
is
s
o
u
t
a
f
r
au
d
tr
an
s
ac
tio
n
,
b
u
t w
e
ca
n
m
an
ag
e
f
alse p
o
s
itiv
e
r
esu
lts
b
y
in
v
esti
g
atin
g
t
h
em
.
Fig
u
r
e
1
.
Plan
f
o
r
e
x
ec
u
tio
n
Fig
u
r
e
2
.
Dee
p
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
Fig
u
r
e
3
.
T
y
p
e
o
f
t
r
an
s
ac
tio
n
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
i
x
E
x
p
er
im
en
tal
s
tu
d
y
ad
o
p
ted
a
d
ee
p
lear
n
in
g
a
p
p
r
o
ac
h
t
o
tack
le
cr
ed
it
ca
r
d
f
r
au
d
d
etec
tio
n
.
Her
e
f
o
cu
s
ed
f
o
r
two
p
r
o
m
in
e
n
t
m
o
d
els
-
C
NNs
an
d
L
STM
s
.
T
h
en
we’
ll
b
e
b
u
ild
in
g
a
n
en
s
em
b
le
o
f
th
ese
m
o
d
els,
n
am
ely
e
n
s
em
b
le
ea
r
ly
f
u
s
io
n
:
C
NN
-
L
STM
an
d
e
n
s
em
b
le
l
ate
f
u
s
io
n
:
C
NN
-
L
STM
[
1
2
]
.
T
h
ese
m
o
d
els
wer
e
ch
o
s
en
f
o
r
th
eir
ab
ilit
y
to
lear
n
co
m
p
lex
p
atter
n
s
with
in
cr
e
d
it
ca
r
d
tr
an
s
ac
tio
n
s
d
ataset.
T
o
p
r
ep
ar
e
th
e
d
ata
f
o
r
an
aly
s
is
f
r
o
m
th
e
h
ig
h
ly
i
m
b
alan
ce
d
cr
ed
it
ca
r
d
f
r
au
d
d
ataset
im
p
lem
en
ted
th
e
s
er
ies
o
f
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
[
1
3
]
.
T
h
is
in
clu
d
es
m
ain
task
s
lik
e
s
tan
d
ar
d
izatio
n
,
r
es
h
ap
in
g
an
d
th
en
r
esam
p
lin
g
.
Fo
llo
win
g
th
e
d
ata
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
C
r
ed
it c
a
r
d
fr
a
u
d
d
etec
tio
n
u
s
in
g
C
N
N
a
n
d
LS
TM
…
(
N
is
h
a
n
t U
p
a
d
h
y
a
y
)
1405
p
r
ep
r
o
ce
s
s
in
g
s
tag
e,
later
d
e
s
ig
n
ed
s
ep
ar
ate
ar
ch
itectu
r
es
f
o
r
b
o
th
C
NN
an
d
L
STM
.
T
h
ese
ar
ch
itectu
r
es
d
ef
in
e
th
e
s
tr
u
ctu
r
e
o
f
th
e
m
o
d
els,
in
clu
d
in
g
th
e
ty
p
es
o
f
la
y
er
s
u
s
ed
,
th
eir
ac
tiv
atio
n
f
u
n
ctio
n
s
[
1
4
]
.
Ass
ess
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
ese
m
o
d
els,
u
tili
ze
d
v
ar
io
u
s
ev
alu
atio
n
m
etr
ics
n
am
ely
ac
cu
r
ac
y
,
r
e
ca
ll,
p
r
ec
is
io
n
an
d
F
1
-
s
co
r
e.
Fin
ally
,
b
u
ild
in
g
en
s
em
b
les
n
am
ely
en
s
em
b
le
ea
r
ly
f
u
s
io
n
:
C
NN
-
L
STM
an
d
e
n
s
em
b
le
late
f
u
s
i
on:
C
NN
-
L
STM
an
d
th
en
o
b
s
er
v
in
g
th
eir
p
er
f
o
r
m
an
ce
u
s
in
g
th
e
p
er
f
o
r
m
an
ce
m
et
r
ics.
2
.
2
.
T
est
ca
s
es
Her
e
h
o
w
th
e
d
ata
was
s
p
lit
in
to
tr
ain
in
g
,
v
alid
atio
n
a
n
d
test
in
g
s
ets,
will
g
et
ex
p
lo
r
atio
n
.
T
h
e
tr
ain
in
g
s
et
is
u
s
ed
t
o
tr
ain
th
e
m
o
d
els,
th
e
v
alid
atio
n
s
et
is
u
s
ed
f
o
r
h
y
p
er
p
ar
a
m
eter
tu
n
in
g
,
an
d
th
e
test
in
g
s
et
p
r
o
v
id
es
an
i
n
d
ep
e
n
d
en
t
m
ea
s
u
r
e
o
f
th
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
in
th
e
u
n
s
ee
n
d
ata.
E
m
p
l
o
y
ed
an
8
0
-
2
0
tr
ai
n
-
test
s
p
lit
s
tr
ateg
y
to
d
iv
id
e
o
u
r
cr
ed
it
ca
r
d
tr
an
s
ac
tio
n
d
ata.
Her
e,
8
0
%
o
f
th
e
d
ata
was
allo
ca
ted
f
o
r
tr
ain
in
g
th
e
m
o
d
els,
allo
win
g
t
h
em
to
lear
n
th
e
p
atter
n
s
with
in
leg
itima
te
an
d
f
r
au
d
u
len
t
tr
an
s
ac
tio
n
s
.
T
h
e
r
em
ain
i
n
g
2
0
%
o
f
th
e
d
ata
was
d
esig
n
at
ed
as
th
e
test
s
et
[
1
5
]
.
I
t
is
im
p
o
r
tan
t
to
n
o
te
th
at
th
is
2
0
%
test
s
et
wa
s
f
u
r
th
er
d
iv
id
ed
i
n
to
a
v
alid
atio
n
an
d
a
f
in
al
test
in
g
s
et.
A
s
m
all
p
o
r
tio
n
o
f
th
e
in
itial
2
0
%
test
d
ata
was
u
s
ed
as
th
e
v
alid
atio
n
test
[
1
6
]
.
T
h
is
v
alid
atio
n
s
et
p
lay
ed
a
cr
u
cial
r
o
le
in
h
y
p
er
p
ar
am
eter
t
u
n
in
g
.
B
y
ev
alu
atin
g
m
o
d
els’
p
er
f
o
r
m
an
ce
o
n
t
h
e
v
alid
atio
n
s
et
d
u
r
in
g
tr
ain
in
g
,
we
co
u
ld
ad
ju
s
t
h
y
p
e
r
p
a
r
am
eter
s
lik
e
n
u
m
b
er
o
f
e
p
o
ch
s
o
r
lear
n
in
g
r
ate,
to
o
p
tim
ize
th
e
m
o
d
el’
s
p
er
f
o
r
m
a
n
ce
with
o
u
t
o
v
er
f
itti
n
g
o
n
th
e
f
in
al
test
in
g
s
et.
T
h
e
r
em
ai
n
in
g
p
o
r
tio
n
o
f
th
e
in
itial
2
0
%
test
d
ata
s
er
v
e
d
as
th
e
f
in
al
test
in
g
s
et,
also
s
h
o
wn
b
y
F
ig
u
r
e
s
5
a
n
d
6
.
T
h
is
u
n
s
ee
n
d
ata
p
r
o
v
id
ed
a
m
o
r
e
o
b
jectiv
e
ev
alu
atio
n
o
f
th
e
m
o
d
el
’
s
ab
ilit
y
to
g
e
n
er
alize
to
r
ea
l
wo
r
ld
s
ce
n
ar
io
s
.
All
m
o
d
els
in
d
iv
id
u
al
C
NN,
L
STM
a
n
d
th
eir
en
s
em
b
les
n
am
ely
en
s
em
b
le
ea
r
ly
f
u
s
io
n
an
d
en
s
em
b
le
late
f
u
s
io
n
wer
e
ev
alu
ated
o
n
th
e
f
i
n
al
test
in
g
s
et
u
s
in
g
th
e
v
a
r
io
u
s
p
er
f
o
r
m
an
ce
m
etr
ics
lik
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
a
n
d
F
1
-
s
co
r
e.
Fig
u
r
e
5
.
T
r
ain
-
t
est s
ets
Fig
u
r
e
6
.
Valid
atio
n
s
ets
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
B
y
p
r
o
p
o
s
in
g
a
n
d
d
esig
n
in
g
th
e
m
o
d
el
as
p
er
t
h
e
th
e
m
e
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
in
g
s
y
s
tem
th
e
ef
f
icien
cy
is
b
ein
g
in
cr
ea
s
ed
an
d
also
s
h
o
win
g
b
etter
p
er
f
o
r
m
a
n
ce
wh
en
co
m
p
a
r
in
g
with
v
ar
io
u
s
o
th
er
m
o
d
els.
Mo
r
eo
v
er
,
test
ca
s
es
ar
e
also
lis
ted
in
th
e
p
ap
er
to
s
ec
u
r
e
th
e
co
d
e
with
in
t
h
e
ex
ec
u
tio
n
p
h
ase,
a
n
d
f
in
ally
r
ea
c
h
th
e
o
p
tim
al
s
o
lu
tio
n
in
ter
m
s
o
f
im
p
r
o
v
e
d
ac
cu
r
ac
y
a
n
d
ef
f
icien
c
y
o
f
th
e
s
y
s
tem
.
W
ith
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
:
d
u
e
to
th
e
co
n
tin
u
o
u
s
n
atu
r
e
o
u
t
p
u
ts
o
f
th
e
p
r
ed
ict
f
u
n
ctio
n
,
co
n
v
er
t
ed
it
in
t
o
b
in
ar
y
i.e
0
o
r
1
.
B
y
p
e
r
f
o
r
m
in
g
th
is
co
n
v
er
s
io
n
at
th
r
ee
d
if
f
er
en
t
th
r
esh
o
ld
s
th
at
is
at
0
.
5
,
0
.
6
an
d
0
.
7
.
Ou
t
o
f
w
h
ich
r
esu
lts
in
b
etter
p
er
f
o
r
m
a
n
ce
,
h
as
b
ee
n
tak
en
in
to
ac
co
u
n
t
[
1
7
]
,
[
1
8
]
.
Acc
o
r
d
i
n
g
to
n
u
m
er
ical
v
alu
ed
r
esu
lts
,
th
at
m
u
s
t
b
e
o
n
ly
o
n
s
y
n
t
h
etic
m
in
o
r
ity
o
v
er
-
s
am
p
lin
g
tec
h
n
iq
u
e
(
SMOT
E
)
d
ata
,
Nea
r
Mi
s
s
Un
d
er
-
s
am
p
lin
g
(
NM
US
)
d
ata,
o
v
er
s
am
p
led
(
OS
)
d
ata,
h
y
b
r
id
:
OS
-
NM
US
d
ata
an
d
h
y
b
r
id
:
SMOT
E
-
NM
US
d
ata
b
o
th
m
o
d
els
ar
e
s
h
o
win
g
e
x
ce
p
ti
o
n
al
r
esu
lts
.
W
o
r
s
t
p
er
f
o
r
m
a
n
ce
o
f
C
NN
an
d
L
STM
h
as
b
ee
n
o
b
s
er
v
e
d
in
o
r
ig
in
al
a
n
d
s
ca
led
d
ata.
OS
d
ata
s
h
o
ws
b
etter
p
er
f
o
r
m
an
ce
o
f
C
NN
an
d
L
STM
m
o
d
el
ar
e
n
o
ted
at
t
h
r
esh
o
ld
s
0
.
7
an
d
0
.
5
r
esp
ec
tiv
ely
.
I
n
th
is
ca
s
e
C
NN
o
u
tp
er
f
o
r
m
s
L
ST
M
with
an
ac
cu
r
ac
y
a
n
d
F
1
-
s
c
o
r
e
o
f
9
9
.
8
9
%
an
d
9
9
.
8
9
% r
esp
ec
tiv
el
y
,
with
1
0
0
% r
ec
all
[
1
9
]
.
An
d
also
,
ca
n
s
ay
th
at
th
at
C
NN
i
s
p
r
o
p
er
ly
class
if
y
in
g
5
6
,
9
1
6
tr
an
s
ac
tio
n
s
as
f
r
a
u
d
,
5
6
,
6
8
7
tr
an
s
ac
tio
n
s
as
leg
it,
1
2
3
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
an
d
0
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
Ho
wev
er
,
L
STM
is
p
r
o
p
er
l
y
class
if
y
in
g
5
5
,
2
2
4
t
r
an
s
ac
tio
n
s
as
f
r
au
d
,
5
5
,
6
9
8
tr
an
s
ac
tio
n
s
as
leg
it,
1
,
2
4
0
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
an
d
1
,
5
6
4
f
r
a
u
d
tr
an
s
ac
tio
n
s
as
leg
it.
Fig
u
r
e
s
7
to
1
6
ar
e
d
ep
ictin
g
th
e
ac
tu
al
r
es
u
lts
alo
n
g
with
th
e
ass
u
m
ed
test
ca
s
es.
SM
OT
E
s
h
o
ws
b
etter
p
er
f
o
r
m
an
ce
o
f
C
NN
an
d
L
STM
m
o
d
el
ar
e
n
o
t
ed
at
th
r
esh
o
ld
s
0
.
7
an
d
0
.
5
r
esp
ec
tiv
el
y
,
wh
er
e
C
NN
ag
ain
o
u
tp
er
f
o
r
m
L
STM
with
an
ac
cu
r
ac
y
a
n
d
F
1
-
s
co
r
e
o
f
9
9
.
9
2
%
an
d
9
9
.
9
2
%
r
esp
ec
tiv
ely
,
with
1
0
0
%
r
ec
all.
A
n
d
also
,
ca
n
s
ay
th
at
C
NN
is
p
r
o
p
er
ly
class
if
y
in
g
5
6
,
7
5
7
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
5
8
,
8
8
1
tr
an
s
ac
tio
n
s
as
leg
it,
8
8
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
an
d
0
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
Ho
wev
er
,
L
STM
is
p
r
o
p
er
ly
class
if
y
in
g
5
3
,
4
7
1
tr
a
n
s
ac
tio
n
s
as
f
r
a
u
d
,
5
5
,
9
6
2
tr
a
n
s
ac
tio
n
s
as
leg
it,
1
,
0
0
6
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
8
,
No
.
2
,
May
20
2
5
:
1
4
0
2
-
1
4
1
0
1406
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
a
n
d
3
,
2
8
2
f
r
au
d
tr
an
s
ac
tio
n
s
as
le
g
it.
NM
US
s
h
o
ws
C
NN
o
u
tp
e
r
f
o
r
m
s
L
STM
as
i
n
ca
s
e
o
f
C
NN,
g
ettin
g
all
ac
cu
r
ac
y
,
F
1
-
s
co
r
e,
r
ec
all
,
an
d
p
r
e
cisi
o
n
o
f
1
0
0
%.
An
d
also
,
ca
n
s
ay
th
at
C
NN
i
s
p
r
o
p
er
l
y
class
if
y
in
g
9
2
tr
an
s
a
ctio
n
s
as
f
r
au
d
,
1
0
5
tr
a
n
s
ac
tio
n
s
as
leg
it,
0
leg
it
tr
an
s
ac
ti
o
n
s
as
f
r
au
d
an
d
0
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it
[
2
0
]
.
Ho
wev
er
,
L
STM
is
p
r
o
p
er
ly
class
if
y
in
g
9
4
tr
an
s
ac
t
io
n
s
as
f
r
au
d
,
1
1
6
tr
an
s
ac
tio
n
s
as
leg
it,
0
leg
it
t
r
an
s
ac
tio
n
s
as
f
r
au
d
an
d
2
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
On
h
y
b
r
id
:
OS
-
NM
US
d
em
o
n
s
tr
ates
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
m
o
d
els
o
n
h
y
b
r
id
s
am
p
lin
g
d
ataset
o
f
OS
-
NM
US
.
B
etter
p
er
f
o
r
m
a
n
ce
o
f
C
NN
an
d
L
STM
is
n
o
ted
a
t
th
r
esh
o
ld
s
0
.
7
a
n
d
0
.
5
r
esp
e
ctiv
ely
.
C
lear
ly
C
NN
o
u
tp
e
r
f
o
r
m
s
L
STM
with
an
ac
cu
r
ac
y
a
n
d
F
1
-
s
co
r
e
o
f
9
9
.
8
9
%
an
d
9
9
.
8
4
%
r
esp
ec
tiv
ely
with
1
0
0
%
r
ec
all
[
2
1
]
,
[
2
2
]
.
An
d
also
,
ca
n
s
ay
th
at
C
NN
i
s
p
r
o
p
er
ly
class
if
y
in
g
5
,
7
3
4
tr
a
n
s
ac
tio
n
s
as f
r
au
d
,
1
1
,
3
0
7
tr
an
s
ac
tio
n
s
as leg
it,
1
8
leg
it tr
an
s
ac
tio
n
s
as
f
r
au
d
an
d
0
f
r
a
u
d
tr
an
s
ac
tio
n
s
as
leg
it.
Ho
wev
e
r
,
L
STM
i
s
p
r
o
p
e
r
ly
class
if
y
in
g
5
,
4
6
8
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
1
1
,
3
5
9
tr
an
s
ac
tio
n
s
as leg
it,
8
7
leg
it tr
an
s
ac
tio
n
s
as f
r
au
d
an
d
1
4
5
f
r
au
d
tr
an
s
ac
tio
n
s
as leg
it.
SMOT
E
-
NM
US
d
ata
d
em
o
n
s
tr
ates
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
els
o
n
h
y
b
r
id
s
am
p
lin
g
d
ataset
o
f
OS
-
NM
US
.
B
ette
r
p
er
f
o
r
m
an
ce
o
f
C
NN
an
d
L
S
T
M
is
n
o
te
d
at
th
r
esh
o
ld
s
0
.
7
an
d
0
.
5
r
esp
ec
tiv
ely
,
wh
er
e
C
NN
o
u
tp
er
f
o
r
m
s
L
STM
with
an
ac
cu
r
ac
y
an
d
F
1
-
s
co
r
e
o
f
9
9
.
8
6
%
an
d
9
9
.
7
9
%
r
esp
ec
tiv
ely
.
An
d
also
,
ca
n
s
ay
th
at
C
NN
is
p
r
o
p
er
l
y
class
if
y
in
g
5
,
7
3
6
tr
a
n
s
ac
tio
n
s
as
f
r
au
d
,
1
1
,
3
0
0
tr
a
n
s
ac
tio
n
s
as
leg
it,
2
2
leg
it
tr
a
n
s
ac
tio
n
s
as
f
r
au
d
an
d
1
f
r
au
d
tr
a
n
s
ac
tio
n
s
as
leg
it.
Ho
wev
er
,
L
STM
is
p
r
o
p
e
r
ly
class
if
y
in
g
5
,
2
8
7
tr
an
s
ac
ti
o
n
s
as
f
r
au
d
,
1
1
,
3
7
7
tr
an
s
ac
tio
n
s
as leg
it,
7
0
leg
it tr
an
s
ac
tio
n
s
as f
r
au
d
an
d
3
2
5
f
r
au
d
tr
an
s
ac
tio
n
s
as leg
it.
Fig
u
r
e
7
.
C
NN/L
STM
r
esu
lts
(
s
am
p
le
d
ata)
Fig
u
r
e
8
.
C
NN/L
STM
r
esu
lts
(
SMOT
E
d
ata)
Fig
u
r
e
9
.
C
NN/L
STM
r
esu
lts
(
NM
US)
Fig
u
r
e
1
0
.
C
NN/L
STM
r
esu
lts
(
h
y
b
r
id
)
W
i
t
h
e
n
s
e
m
bl
e
ap
p
r
oa
ch
es:
t
he
pe
r
f
or
m
an
ce
o
f
tw
o
en
s
em
bl
e
le
a
r
ni
ng
m
o
de
ls
na
m
el
y
ear
ly
f
usio
n
:
CN
N
-
L
S
T
M
an
d
la
te
f
usio
n
.
I
t
s
ho
w
s
th
a
t
th
e
e
ar
ly
f
u
s
io
n
is
r
esu
ltin
g
b
etter
o
n
th
e
d
atasets
co
m
p
ar
ed
to
late
f
u
s
io
n
.
B
el
o
w
will
b
e
d
o
in
g
th
r
o
u
g
h
a
n
aly
s
is
o
f
th
e
im
p
ac
t
o
f
th
e
s
e
d
atasets
o
n
th
e
p
er
f
o
r
m
an
ce
o
f
en
s
em
b
les.
N
MU
S
d
ata
s
h
o
ws
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
e
n
s
em
b
les,
o
n
th
e
NM
US
d
ataset.
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
C
r
ed
it c
a
r
d
fr
a
u
d
d
etec
tio
n
u
s
in
g
C
N
N
a
n
d
LS
TM
…
(
N
is
h
a
n
t U
p
a
d
h
y
a
y
)
1407
T
h
r
esh
o
ld
=0
.
5
,
0
.
6
,
0
.
7
g
i
v
in
g
th
e
s
am
e
r
esu
lt
in
ca
s
e
o
f
e
ar
ly
f
u
s
io
n
a
n
d
th
r
esh
o
ld
=0
.
5
in
late
f
u
s
io
n
.
B
o
th
m
o
d
els
h
av
e
h
ig
h
ac
cu
r
ac
y
,
t
h
e
late
f
u
s
io
n
o
u
tp
er
f
o
r
m
s
th
e
ea
r
ly
f
u
s
io
n
,
as
it
o
u
tp
u
ts
h
ig
h
ac
c
u
r
ac
y
an
d
F
1
-
s
co
r
e
o
f
1
0
0
%
an
d
1
0
0
%
r
esp
ec
tiv
ely
[
2
3
]
.
An
d
also
,
ca
n
s
ay
th
at
ea
r
ly
f
u
s
io
n
is
p
r
o
p
er
ly
class
if
y
in
g
9
6
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
9
9
tr
an
s
ac
tio
n
s
as
leg
it,
0
leg
it
tr
a
n
s
ac
tio
n
s
as
f
r
au
d
an
d
2
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
Ho
wev
er
,
late
f
u
s
io
n
is
p
r
o
p
er
ly
class
if
y
in
g
9
8
tr
a
n
s
ac
tio
n
s
as
f
r
a
u
d
,
9
9
tr
an
s
ac
tio
n
s
as
leg
it,
0
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
an
d
0
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
On
SMOT
E
d
em
o
n
s
tr
ates
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
en
s
em
b
les,
o
n
th
e
SMOT
E
d
ataset.
T
h
r
esh
o
ld
=0
.
7
g
iv
in
g
th
e
b
est
r
esu
lt
in
ca
s
e
o
f
ea
r
ly
f
u
s
io
n
an
d
th
r
esh
o
ld
=0
.
5
in
late
f
u
s
io
n
.
E
ar
ly
f
u
s
io
n
o
u
tp
e
r
f
o
r
m
s
th
e
late
f
u
s
io
n
,
as
it
o
u
t
p
u
ts
h
ig
h
ac
cu
r
ac
y
a
n
d
F
1
-
s
co
r
e
o
f
9
9
.
9
6
%
a
n
d
9
9
.
9
6
%
r
esp
ec
tiv
ely
.
An
d
also
,
c
an
s
ay
th
at
ea
r
ly
f
u
s
io
n
is
p
r
o
p
er
ly
class
if
y
in
g
5
6
,
9
7
6
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
5
6
,
7
1
0
tr
an
s
ac
tio
n
s
as
leg
it,
4
0
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
an
d
0
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it
[
2
4
]
.
Ho
wev
er
,
late
f
u
s
io
n
is
p
r
o
p
er
ly
class
if
y
in
g
5
6
,
8
3
8
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
5
6
,
6
4
1
tr
an
s
ac
tio
n
s
as leg
it,
1
0
9
leg
it tr
an
s
ac
tio
n
s
as f
r
au
d
an
d
1
3
8
f
r
au
d
tr
an
s
ac
tio
n
s
as leg
it.
Ov
er
OS d
em
o
n
s
tr
ates
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
en
s
em
b
les,
o
n
th
e
OS
d
ataset.
T
h
r
e
s
h
o
ld
=0
.
7
g
iv
in
g
th
e
b
est
r
esu
lt
in
ca
s
e
o
f
ea
r
ly
f
u
s
io
n
an
d
late
f
u
s
io
n
.
L
ate
f
u
s
io
n
o
u
t
p
er
f
o
r
m
s
th
e
ea
r
ly
f
u
s
io
n
,
as
it
o
u
tp
u
ts
h
ig
h
ac
cu
r
ac
y
an
d
F
1
-
s
co
r
e
o
f
9
9
.
8
9
% a
n
d
9
9
.
8
9
% r
esp
ec
tiv
ely
.
Fig
u
r
e
1
1
.
C
NN/L
STM
r
esu
lts
(
SMOT
E
-
NM
U)
Fig
u
r
e
1
2
.
C
NN/L
STM
r
esu
lts
(
NM
US
-
f
u
s
io
n
)
Fig
u
r
e
1
3
.
C
NN/L
STM
r
esu
lts
(
SMOT
E
-
f
u
s
io
n
)
Fig
u
r
e
1
4
.
C
NN/L
STM
r
esu
lts
(
OS d
ata)
An
d
also
,
ca
n
s
ay
t
h
at
ea
r
ly
f
u
s
io
n
is
p
r
o
p
er
ly
class
if
y
in
g
5
6
,
6
3
7
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
5
6
,
9
2
3
tr
an
s
ac
tio
n
s
as
leg
it,
5
7
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
a
n
d
1
0
9
f
r
au
d
t
r
an
s
ac
tio
n
s
as
leg
it.
H
o
wev
er
,
late
f
u
s
io
n
is
p
r
o
p
er
l
y
class
if
y
in
g
5
6
,
7
4
6
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
5
6
,
8
6
2
tr
an
s
ac
tio
n
s
as
leg
it,
1
1
8
le
g
it
t
r
an
s
ac
tio
n
s
as
f
r
au
d
an
d
0
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
On
h
y
b
r
id
:
(
OS
-
NM
US)
d
ata
d
em
o
n
s
tr
ates
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
en
s
em
b
les,
o
n
th
e
OS
-
NM
US
d
ataset.
T
h
r
esh
o
ld
=0
.
7
g
iv
in
g
th
e
b
est
r
esu
lt
in
ca
s
e
o
f
ea
r
ly
f
u
s
io
n
a
n
d
th
r
esh
o
ld
=0
.
5
in
late
f
u
s
io
n
.
E
ar
ly
f
u
s
io
n
o
u
tp
er
f
o
r
m
s
th
e
late
f
u
s
io
n
,
as
it
o
u
tp
u
ts
h
ig
h
ac
cu
r
ac
y
an
d
F
1
-
s
co
r
e
o
f
9
9
.
9
1
%
an
d
9
9
.
8
6
%
r
esp
ec
tiv
ely
[
2
5
]
.
A
n
d
,
ca
n
s
a
y
th
at
ea
r
ly
f
u
s
io
n
is
p
r
o
p
er
ly
class
if
y
in
g
5
,
7
3
1
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
8
,
No
.
2
,
May
20
2
5
:
1
4
0
2
-
1
4
1
0
1408
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
1
1
,
3
1
3
tr
an
s
ac
tio
n
s
as
leg
it,
8
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
a
n
d
7
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
Ho
wev
er
,
late
f
u
s
io
n
is
p
r
o
p
er
l
y
class
if
y
in
g
5
6
,
6
6
0
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
5
6
,
5
6
1
tr
an
s
ac
tio
n
s
as
leg
it,
1
8
9
le
g
it
tr
an
s
ac
tio
n
s
as
f
r
a
u
d
an
d
3
1
6
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
SMOT
E
-
NM
US
d
ata
d
em
o
n
s
tr
ates
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
en
s
em
b
les
,
o
n
th
e
SMOT
E
-
NM
US
d
ata
s
et.
T
h
r
esh
o
ld
=0
.
5
g
iv
i
n
g
th
e
b
est
r
esu
lt
in
ca
s
e
o
f
ea
r
ly
f
u
s
io
n
an
d
in
late
f
u
s
io
n
.
E
ar
ly
f
u
s
io
n
o
u
tp
er
f
o
r
m
s
th
e
late
f
u
s
io
n
,
as
i
t
o
u
tp
u
ts
h
ig
h
ac
cu
r
ac
y
an
d
F
1
-
s
co
r
e
o
f
9
9
.
9
4
%
an
d
9
9
.
9
2
%
r
esp
ec
tiv
ely
.
An
d
,
ca
n
s
a
y
th
at
ea
r
ly
f
u
s
io
n
is
p
r
o
p
er
l
y
class
if
y
in
g
5
,
7
3
4
tr
an
s
ac
tio
n
s
as
f
r
au
d
,
1
1
,
3
1
6
tr
an
s
ac
tio
n
s
as
leg
it,
5
leg
it
tr
an
s
ac
tio
n
s
as
f
r
au
d
a
n
d
4
f
r
au
d
tr
an
s
ac
tio
n
s
as
leg
it.
Ho
wev
er
,
late
f
u
s
io
n
is
p
r
o
p
er
l
y
class
if
y
in
g
5
,
6
6
4
tr
a
n
s
ac
tio
n
s
as
f
r
au
d
,
1
1
,
3
1
1
tr
a
n
s
ac
tio
n
s
as
leg
it,
1
0
leg
it tr
an
s
ac
tio
n
s
as f
r
au
d
a
n
d
7
4
f
r
a
u
d
tr
a
n
s
ac
tio
n
s
as leg
it.
Fig
u
r
e
1
5
.
C
NN/L
STM
r
esu
lts
(
OS
-
NM
US)
Fig
u
r
e
1
6
.
C
NN/L
STM
r
esu
lts
(
SMOT
E
-
NM
US)
4.
CO
NCLU
SI
O
N
Fro
m
th
e
an
aly
s
is
,
ac
r
o
s
s
v
ar
io
u
s
d
atasets
,
b
o
th
m
o
d
els
C
N
N
an
d
L
STM
s
h
o
wn
im
p
r
ess
i
v
e
r
esu
lts
,
g
en
er
ally
ac
h
iev
i
n
g
h
ig
h
ac
cu
r
ac
y
an
d
F1
-
s
co
r
es.
Ho
wev
e
r
,
s
o
m
e
k
ey
d
if
f
e
r
en
ce
s
ex
is
t.
Data
s
et
g
en
er
ated
u
s
in
g
NM
US,
an
u
n
d
er
-
s
am
p
lin
g
tech
n
iq
u
e
an
d
SMOT
E
,
an
o
v
er
s
am
p
lin
g
tech
n
iq
u
e
s
h
o
w
g
r
ea
t
ac
cu
r
ac
y
an
d
F1
-
s
co
r
es,
s
u
g
g
esti
n
g
m
o
d
els
ar
e
d
o
i
n
g
well
o
n
th
ese
d
atasets
.
Or
ig
in
al
an
d
s
ca
led
d
a
tasets
,
o
n
th
e
o
t
h
er
h
an
d
,
e
x
h
ib
it
lo
wer
p
e
r
f
o
r
m
a
n
ce
,
p
ar
ticu
lar
ly
f
o
r
L
STM
s
,
h
in
tin
g
at
im
b
alan
ce
d
d
ata
o
r
in
h
er
en
t
ch
allen
g
es.
E
n
co
u
r
a
g
in
g
ly
e
n
s
em
b
le
m
o
d
els
o
f
ten
s
u
r
p
ass
in
d
iv
id
u
al
m
o
d
els,
d
em
o
n
s
tr
atin
g
t
h
e
b
e
n
ef
its
o
f
co
m
b
in
in
g
d
iv
er
s
e
lear
n
in
g
s
ty
les.
E
ar
l
y
f
u
s
io
n
en
s
em
b
les
ty
p
ically
ed
g
e
o
u
t
late
f
u
s
io
n
ap
p
r
o
ac
h
,
s
u
g
g
esti
n
g
th
at
f
u
s
in
g
f
ea
tu
r
es
b
ef
o
r
e
in
d
iv
id
u
al
m
o
d
el
p
r
e
d
ictio
n
s
ar
e
m
o
r
e
ef
f
ec
tiv
e,
esp
ec
ially
in
o
u
r
ca
s
e.
Hy
b
r
id
d
atasets
,
co
m
b
in
in
g
SMOT
E
an
d
NM
US,
s
ee
th
e
m
o
s
t
s
ig
n
if
ican
t
g
ain
s
f
r
o
m
th
e
en
s
em
b
le
m
o
d
els,
ev
en
r
ea
c
h
in
g
n
ea
r
-
p
er
f
ec
t a
cc
u
r
ac
y
in
s
o
m
e
in
s
tan
ce
s
.
RE
F
E
R
E
NC
E
S
[
1
]
F
.
T
h
a
b
t
a
h
,
S
.
H
a
mm
o
u
d
,
F
.
K
a
m
a
l
o
v
,
a
n
d
A
.
G
o
n
sa
l
v
e
s,
“
D
a
t
a
i
m
b
a
l
a
n
c
e
i
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
e
x
p
e
r
i
me
n
t
a
l
e
v
a
l
u
a
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
5
1
3
,
p
p
.
4
2
9
–
4
4
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.
2
0
1
9
.
1
1
.
0
0
4
.
[
2
]
D
.
D
h
i
m
a
n
,
A
.
B
i
sh
t
,
A
.
K
u
mari
,
D
.
H
.
A
n
a
n
d
a
r
a
m,
S
.
S
a
x
e
n
a
,
a
n
d
K
.
Jo
s
h
i
,
“
O
n
l
i
n
e
f
r
a
u
d
d
e
t
e
c
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
m
a
rt
C
o
m
m
u
n
i
c
a
t
i
o
n
(
AI
S
C
)
,
Ja
n
.
2
0
2
3
,
p
p
.
1
6
1
–
1
6
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
S
C
5
6
6
1
6
.
2
0
2
3
.
1
0
0
8
5
4
9
3
.
[
3
]
N
.
V
.
C
h
a
w
l
a
,
K
.
W
.
B
o
w
y
e
r
,
L.
O
.
H
a
l
l
,
a
n
d
W
.
P
.
K
e
g
e
l
me
y
e
r
,
“
S
M
O
TE
:
s
y
n
t
h
e
t
i
c
mi
n
o
r
i
t
y
o
v
e
r
-
s
a
m
p
l
i
n
g
t
e
c
h
n
i
q
u
e
,
”
J
o
u
rn
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
s
e
a
rc
h
,
v
o
l
.
1
6
,
p
p
.
3
2
1
–
3
5
7
,
2
0
0
2
,
d
o
i
:
1
0
.
1
6
1
3
/
j
a
i
r
.
9
5
3
.
[
4
]
A
.
P
u
ms
i
r
i
r
a
t
a
n
d
L.
Y
a
n
,
“
C
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
o
n
a
u
t
o
-
e
n
c
o
d
e
r
a
n
d
r
e
s
t
r
i
c
t
e
d
B
o
l
t
z
m
a
n
n
mac
h
i
n
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
8
–
2
5
,
2
0
1
8
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
1
8
.
0
9
0
1
0
3
.
[
5
]
F
.
M
.
M
o
r
e
n
o
,
J.
A
.
N
.
A
n
d
r
a
d
e
,
H
.
T.
S
i
n
o
h
a
r
a
,
a
n
d
P
.
H
.
H
.
N
.
d
e
A
r
a
u
j
o
,
“
Tr
a
n
sf
e
r
l
e
a
r
n
i
n
g
,”
J
o
u
rn
a
l
o
f
c
ri
t
i
c
a
l
r
e
v
i
e
w
s
,
v
o
l
.
7
,
n
o
.
1
4
,
2
0
2
0
,
d
o
i
:
1
0
.
3
1
8
3
8
/
j
c
r
.
0
7
.
1
4
.
1
7
4
.
[
6
]
S
.
M
a
e
s,
K
.
Tu
y
l
s,
a
n
d
B
.
V
a
n
sc
h
o
e
n
w
i
n
k
e
l
,
“
C
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
u
s
i
n
g
B
a
y
e
si
a
n
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
M
a
c
i
u
n
a
s
R
J
,
e
d
i
t
o
r.
I
n
t
e
ra
c
t
i
v
e
i
m
a
g
e
-
g
u
i
d
e
d
n
e
u
r
o
su
r
g
e
ry.
Am
e
r
i
c
a
n
Ass
o
c
i
a
t
i
o
n
N
e
u
r
o
l
o
g
i
c
a
l
S
u
r
g
e
o
n
s
,
p
p
.
2
6
1
–
2
7
0
,
1
9
9
3
.
[
7
]
Z.
C
h
e
n
,
S
.
W
a
n
g
,
D
.
Y
a
n
,
a
n
d
Y
.
Li
,
“
R
e
s
e
a
r
c
h
a
n
d
i
m
p
l
e
me
n
t
a
t
i
o
n
o
f
b
a
n
k
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
sy
st
e
m
b
a
se
d
o
n
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
a
n
d
LSTM
,
”
i
n
2
0
2
3
3
r
d
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
Mo
b
i
l
e
N
e
t
w
o
r
k
s
a
n
d
Wi
r
e
l
e
ss
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
C
MN
WC
)
,
D
e
c
.
2
0
2
3
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
N
W
C
6
0
1
8
2
.
2
0
2
3
.
1
0
4
3
5
8
9
0
.
[
8
]
M
.
L.
G
a
m
b
o
,
A
.
Za
i
n
a
l
,
a
n
d
M
.
N
.
K
a
ssi
m
,
“
A
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
f
o
r
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
S
c
i
e
n
c
e
a
n
d
I
t
s
Ap
p
l
i
c
a
t
i
o
n
s
(
I
C
o
D
S
A)
,
Ju
l
.
2
0
2
2
,
p
p
.
1
9
8
–
2
0
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
D
S
A
5
5
8
7
4
.
2
0
2
2
.
9
8
6
2
9
3
0
.
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
C
r
ed
it c
a
r
d
fr
a
u
d
d
etec
tio
n
u
s
in
g
C
N
N
a
n
d
LS
TM
…
(
N
is
h
a
n
t U
p
a
d
h
y
a
y
)
1409
[
9
]
Y
.
A
.
M
o
h
ma
d
,
“
C
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
u
si
n
g
LST
M
a
l
g
o
r
i
t
h
m,
”
Wa
s
i
t
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
M
a
t
h
e
m
a
t
i
c
s
S
c
i
e
n
c
e
,
v
o
l
.
1
,
n
o
.
3
,
p
p
.
2
6
–
3
5
,
2
0
2
2
,
d
o
i
:
1
0
.
3
1
1
8
5
/
w
j
c
m.
6
0
.
[
1
0
]
B
.
P
.
V
e
r
m
a
,
V
.
V
e
r
ma
,
a
n
d
A
.
B
a
d
h
o
l
i
a
,
“
H
y
p
e
r
-
t
u
n
e
d
e
n
s
e
m
b
l
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
v
e
n
t
i
v
e
C
o
m
p
u
t
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
I
C
T
)
,
J
u
l
.
2
0
2
2
,
p
p
.
3
2
0
–
3
2
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
T5
4
3
4
4
.
2
0
2
2
.
9
8
5
0
9
4
0
.
[
1
1
]
D
.
K
a
u
r
,
A
.
S
a
i
n
i
,
a
n
d
D
.
G
u
p
t
a
,
“
C
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
d
e
e
p
l
e
a
r
n
i
n
g
,
a
n
d
e
n
s
e
mb
l
e
o
f
t
h
e
b
o
t
h
,
”
i
n
2
0
2
2
S
e
v
e
n
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Pa
r
a
l
l
e
l
,
D
i
st
ri
b
u
t
e
d
a
n
d
G
r
i
d
C
o
m
p
u
t
i
n
g
(
PD
G
C
)
,
N
o
v
.
2
0
2
2
,
p
p
.
4
8
4
–
4
8
9
,
d
o
i
:
1
0
.
1
1
0
9
/
P
D
G
C
5
6
9
3
3
.
2
0
2
2
.
1
0
0
5
3
1
7
5
.
[
1
2
]
J.
K
a
r
t
h
i
k
a
a
n
d
A
.
S
e
n
t
h
i
l
se
l
v
i
,
“
C
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
e
n
s
e
mb
l
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
s
si
f
i
e
r
s,”
i
n
2
0
2
2
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ro
n
i
c
s
a
n
d
S
u
s
t
a
i
n
a
b
l
e
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s
(
I
C
E
S
C
)
,
A
u
g
.
2
0
2
2
,
p
p
.
1
6
0
4
–
1
6
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
ESC
5
4
4
1
1
.
2
0
2
2
.
9
8
8
5
6
4
9
.
[
1
3
]
P
.
T
o
mar
,
S
.
S
h
r
i
v
a
s
t
a
v
a
,
a
n
d
U
.
T
h
a
k
a
r
,
“
En
s
e
m
b
l
e
l
e
a
r
n
i
n
g
b
a
se
d
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
,
”
i
n
2
0
2
1
5
t
h
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
C
I
C
T
)
,
D
e
c
.
2
0
2
1
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
C
T
5
3
8
6
5
.
2
0
2
0
.
9
6
7
2
4
2
6
.
[
1
4
]
G
.
G
u
r
so
y
a
n
d
A
.
V
a
r
o
l
,
“
R
i
s
k
s
o
f
d
i
g
i
t
a
l
t
r
a
n
sf
o
r
m
a
t
i
o
n
:
r
e
v
i
e
w
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
i
n
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
2
1
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
I
n
f
o
r
m
a
t
i
c
s
a
n
d
S
o
f
t
w
a
r
e
E
n
g
i
n
e
e
ri
n
g
C
o
n
f
e
r
e
n
c
e
(
I
I
S
EC
)
,
D
e
c
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
I
S
EC
5
4
2
3
0
.
2
0
2
1
.
9
6
7
2
3
5
4
.
[
1
5
]
G
.
K
.
A
r
u
n
a
n
d
K
.
V
e
n
k
a
t
a
c
h
a
l
a
p
a
t
h
y
,
“
C
o
n
v
o
l
u
t
i
o
n
a
l
l
o
n
g
s
h
o
r
t
t
e
r
m
memo
r
y
m
o
d
e
l
f
o
r
c
r
e
d
i
t
c
a
r
d
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
2
0
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
r
o
n
i
c
s,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
Ae
r
o
s
p
a
c
e
T
e
c
h
n
o
l
o
g
y
(
I
C
EC
A)
,
N
o
v
.
2
0
2
0
,
p
p
.
1
1
6
8
–
1
1
7
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
EC
A
4
9
3
1
3
.
2
0
2
0
.
9
2
9
7
6
0
6
.
[
1
6
]
F
.
C
a
r
c
i
l
l
o
,
Y
.
-
A
.
L
e
B
o
r
g
n
e
,
O
.
C
a
e
l
e
n
,
Y
.
K
e
ssa
c
i
,
F
.
O
b
l
é
,
a
n
d
G
.
B
o
n
t
e
m
p
i
,
“
C
o
m
b
i
n
i
n
g
u
n
su
p
e
r
v
i
s
e
d
a
n
d
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
i
n
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
5
5
7
,
p
p
.
3
1
7
–
3
3
1
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.2
0
1
9
.
0
5
.
0
4
2
.
[
1
7
]
S
.
M
a
k
k
i
,
Z.
A
ss
a
g
h
i
r
,
Y
.
Ta
h
e
r
,
R
.
H
a
q
u
e
,
M
.
-
S
.
H
a
c
i
d
,
a
n
d
H
.
Z
e
i
n
e
d
d
i
n
e
,
“
A
n
e
x
p
e
r
i
m
e
n
t
a
l
s
t
u
d
y
w
i
t
h
i
m
b
a
l
a
n
c
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
p
p
r
o
a
c
h
e
s
f
o
r
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
9
3
0
1
0
–
9
3
0
2
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
2
7
2
6
6
.
[
1
8
]
E.
B
t
o
u
sh
,
X
.
Zh
o
u
,
R
.
G
u
r
u
r
a
i
a
n
,
K
.
C
h
a
n
,
a
n
d
X
.
Ta
o
,
“
A
s
u
r
v
e
y
o
n
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
i
n
b
a
n
k
i
n
g
i
n
d
u
st
r
y
f
o
r
c
y
b
e
r
s
e
c
u
r
i
t
y
,
”
i
n
2
0
2
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
B
e
h
a
v
i
o
ra
l
a
n
d
S
o
c
i
a
l
C
o
m
p
u
t
i
n
g
(
BE
S
C
)
,
O
c
t
.
2
0
2
1
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
B
ESC
5
3
9
5
7
.
2
0
2
1
.
9
6
3
5
5
5
9
.
[
1
9
]
J.
H
.
V
i
c
t
o
r
i
a
a
n
d
A
.
Ji
m,
“
A
s
u
r
v
e
y
o
f
o
u
t
l
i
e
r
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
o
l
o
g
i
e
s,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
2
2
,
p
p
.
8
5
–
1
2
6
,
2
0
0
4
.
[
2
0
]
T.
M
a
e
t
a
l
.
,
“
A
n
u
n
s
u
p
e
r
v
i
s
e
d
i
n
c
r
e
men
t
a
l
v
i
r
t
u
a
l
l
e
a
r
n
i
n
g
me
t
h
o
d
f
o
r
f
i
n
a
n
c
i
a
l
f
r
a
u
d
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
9
I
EEE/
AC
S
1
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
y
st
e
m
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(
AI
C
C
S
A)
,
N
o
v
.
2
0
1
9
,
v
o
l
.
2
0
1
9
-
N
o
v
e
m,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
C
C
S
A
4
7
6
3
2
.
2
0
1
9
.
9
0
3
5
2
5
9
.
[
2
1
]
M
.
P
u
h
a
n
d
L.
B
r
k
i
c
,
“
D
e
t
e
c
t
i
n
g
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
u
si
n
g
se
l
e
c
t
e
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
i
n
2
0
1
9
4
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
v
e
n
t
i
o
n
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
M
i
c
r
o
e
l
e
c
t
r
o
n
i
c
s
(
MI
PRO
)
,
M
a
y
2
0
1
9
,
p
p
.
1
2
5
0
–
1
2
5
5
,
d
o
i
:
1
0
.
2
3
9
1
9
/
M
I
P
R
O
.
2
0
1
9
.
8
7
5
7
2
1
2
.
[
2
2
]
N
.
F
.
R
y
ma
n
-
T
u
b
b
,
P
.
K
r
a
u
se,
a
n
d
W
.
G
a
r
n
,
“
H
o
w
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
r
e
se
a
r
c
h
i
m
p
a
c
t
s
p
a
y
m
e
n
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
:
a
su
r
v
e
y
a
n
d
i
n
d
u
st
r
y
b
e
n
c
h
m
a
r
k
,
”
E
n
g
i
n
e
e
r
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
6
,
p
p
.
1
3
0
–
1
5
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
1
8
.
0
7
.
0
0
8
.
[
2
3
]
S
.
X
u
a
n
,
G
.
Li
u
,
Z.
L
i
,
L.
Zh
e
n
g
,
S
.
W
a
n
g
,
a
n
d
C
.
J
i
a
n
g
,
“
R
a
n
d
o
m
f
o
r
e
s
t
f
o
r
c
r
e
d
i
t
c
a
r
d
f
r
a
u
d
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
8
I
EE
E
1
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
N
e
t
w
o
rk
i
n
g
,
S
e
n
si
n
g
a
n
d
C
o
n
t
ro
l
(
I
C
N
S
C
)
,
M
a
r
.
2
0
1
8
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
N
S
C
.
2
0
1
8
.
8
3
6
1
3
4
3
.
[
2
4
]
D
.
H
u
a
n
g
,
D
.
M
u
,
L.
Y
a
n
g
,
a
n
d
X
.
C
a
i
,
“
C
o
D
e
t
e
c
t
:
f
i
n
a
n
c
i
a
l
f
r
a
u
d
d
e
t
e
c
t
i
o
n
w
i
t
h
a
n
o
ma
l
y
f
e
a
t
u
r
e
d
e
t
e
c
t
i
o
n
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
6
,
p
p
.
1
9
1
6
1
–
1
9
1
7
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
8
.
2
8
1
6
5
6
4
.
[
2
5
]
T.
A
mar
a
si
n
g
h
e
,
A
.
A
p
o
n
so
,
a
n
d
N
.
K
r
i
s
h
n
a
r
a
j
a
h
,
“
C
r
i
t
i
c
a
l
a
n
a
l
y
si
s
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
a
p
p
r
o
a
c
h
e
s
f
o
r
f
r
a
u
d
d
e
t
e
c
t
i
o
n
i
n
f
i
n
a
n
c
i
a
l
t
r
a
n
sac
t
i
o
n
s,”
i
n
A
C
M
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
Pro
c
e
e
d
i
n
g
S
e
ri
e
s
,
2
0
1
8
,
p
p
.
1
2
–
1
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
2
3
1
8
8
4
.
3
2
3
1
8
9
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Nisha
n
t
Upa
d
h
y
a
y
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
wit
h
o
v
e
r
fiv
e
y
e
a
r
s
o
f
e
x
p
e
rien
c
e
in
h
ig
h
e
r
e
d
u
c
a
ti
o
n
,
s
p
e
c
ializin
g
i
n
o
p
e
ra
ti
n
g
sy
ste
m
s,
d
a
ta
stru
c
t
u
re
s,
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
He
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
P
h
.
D.
a
n
d
h
o
ld
s
a
n
M
.
Tec
h
.
i
n
Da
ta
S
c
ien
c
e
fro
m
Ja
wa
h
a
rlal
Ne
h
ru
Un
iv
e
rsity
(JN
U).
He
h
a
s
p
u
b
l
ish
e
d
re
se
a
rc
h
in
a
re
a
s
su
c
h
a
s
a
rt
ifi
c
ial
in
telli
g
e
n
c
e
,
n
e
two
r
k
se
c
u
rit
y
,
a
n
d
h
e
a
lt
h
c
a
re
,
a
n
d
h
o
ld
s
p
a
ten
ts
fo
r
se
v
e
ra
l
in
n
o
v
a
ti
o
n
s,
in
c
lu
d
i
n
g
a
sm
a
rtwa
tch
a
p
p
li
c
a
ti
o
n
fo
r
re
a
l
-
ti
m
e
e
lec
tri
c
a
l
sig
n
a
l
d
e
tec
ti
o
n
.
He
h
a
s
tau
g
h
t
a
t
in
stit
u
ti
o
n
s
su
c
h
a
s
G
NIO
T,
G
.
B.
De
g
re
e
Co
ll
e
g
e
,
a
n
d
is
c
u
rre
n
tl
y
wo
r
k
in
g
a
t
S
h
a
rd
a
Un
iv
e
rsit
y
,
G
re
a
ter
No
id
a
.
He
h
a
s
a
lso
wo
rk
e
d
o
n
re
se
a
rc
h
p
ro
jec
ts
re
late
d
t
o
COV
ID
-
1
9
a
n
d
c
li
n
ica
l
tri
a
ls.
His
tec
h
n
ica
l
e
x
p
e
rti
se
in
c
lu
d
e
s
P
y
t
h
o
n
,
AI/
M
L,
d
a
ta
a
n
a
ly
sis,
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
s.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
ish
a
n
t.
u
p
a
d
h
y
a
y
2
3
@g
m
a
il
.
c
o
m
.
Dr
.
Nid
h
i
Ba
n
sa
l
is
a
n
a
ss
o
c
i
a
te
p
ro
fe
ss
o
r
a
t
M
RIIR
S
F
a
rid
a
b
a
d
Ha
ry
a
n
a
,
In
d
ia.
S
h
e
re
c
e
iv
e
d
a
B.
Tec
h
.
fr
o
m
G
BTU
-
UPT
U
Lu
c
k
n
o
w
I
n
d
ia
in
2
0
1
0
,
M
.
E.
fro
m
NIT
TT
R
P
a
n
jab
Un
iv
e
rsity
Ch
a
n
d
ig
a
r
h
In
d
ia
in
2
0
1
4
,
a
n
d
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
fro
m
AK
TU
-
UPT
U
Lu
c
k
n
o
w
I
n
d
ia
in
2
0
2
3
.
He
r
re
se
a
r
c
h
in
tere
sts
a
re
in
c
lo
u
d
c
o
m
p
u
ti
n
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
b
ro
a
d
ly
,
wi
th
a
p
p
li
c
a
ti
o
n
s
in
d
a
ta
sc
ien
c
e
,
a
n
d
c
o
m
p
u
ter
n
e
two
rk
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
i
d
h
i1
8
ju
l@
g
m
a
il
.
c
o
m
.
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
8
,
No
.
2
,
May
20
2
5
:
1
4
0
2
-
1
4
1
0
1410
Div
y
a
R
a
sto
g
i
is
wo
rk
in
g
with
S
h
a
r
d
a
Un
iv
e
rsit
y
g
re
a
ter
No
id
a
a
s
a
ss
istan
t
p
ro
fe
ss
o
r.
S
h
e
is
M
CA
fro
m
U
P
TU
Lu
c
k
n
o
w
a
n
d
M
.
Tec
h
.
(C
S
E)
fro
m
Am
it
y
Un
i
v
e
rsity
,
No
id
a
.
No
w,
sh
e
is
p
u
rsu
i
n
g
a
P
h
.
D
.
(C
S
E)
fro
m
Am
it
y
U
n
iv
e
rsi
ty
,
G
re
a
ter
No
id
a
Ca
m
p
u
s.
He
r
in
tere
st
a
re
a
in
c
lu
d
e
s
c
lo
u
d
c
o
m
p
u
ti
n
g
,
I
o
T
,
n
a
t
u
re
i
n
sp
i
re
d
a
lg
o
r
it
h
m
s,
a
n
d
ima
g
e
p
ro
c
e
ss
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
iv
y
a
.
ra
sto
g
i
0
3
@re
d
iff
m
a
il
.
c
o
m
.
Dr
Re
k
h
a
Cha
tu
r
v
e
d
i
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
M
a
n
i
p
a
l
Un
iv
e
rsity
Ja
ip
u
r.
S
h
e
d
id
B.
E.
(IT
)
fr
o
m
Ra
jas
th
a
n
Un
i
v
e
rsity
,
M
.
Tec
h
(S
o
ftwa
re
En
g
i
n
e
e
rin
g
)
fr
o
m
th
e
S
G
VU
a
n
d
P
h
.
D.
(CS
E
)
fro
m
Am
it
y
Un
i
v
e
r
sity
Ra
jas
th
a
n
.
He
r
re
se
a
rc
h
in
tere
st
in
c
l
u
d
e
s
d
a
ta
m
in
i
n
g
,
ima
g
e
p
r
o
c
e
ss
in
g
,
d
i
g
it
a
l
ima
g
e
wa
term
a
rk
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
so
f
t
c
o
m
p
u
ti
n
g
,
a
n
d
n
a
tu
re
in
s
p
ired
c
o
m
p
u
ti
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
re
k
h
a
c
h
a
tu
r
v
e
d
i1
2
@g
m
a
il
.
c
o
m
.
Mo
h
a
m
m
a
d
As
im
is
p
re
se
n
tl
y
w
o
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
S
h
a
r
d
a
Un
iv
e
rsity
.
He
h
a
s
v
a
st
e
x
p
e
rien
c
e
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
.
He
d
id
h
is
M
.
Tec
h
.
(C
S
E)
a
n
d
B.
Tec
h
.
(CS
E)
fro
m
Dr.
A.P
.
J
Ab
d
u
l
Ka
lam
Tec
h
n
ica
l
Un
iv
e
rsity
,
Lu
c
k
n
o
w
(
F
o
rm
e
r
ly
,
UPT
U,
L
u
c
k
n
o
w)
a
n
d
p
u
rsu
i
n
g
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
r.
m
o
h
d
a
sim
@g
m
a
il
.
c
o
m
.
Dr
.
S
u
r
a
j
Ma
li
k
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
in
IIM
T
Un
i
v
e
rsit
y
.
Ne
two
rk
in
g
is
c
o
n
sid
e
re
d
a
s
h
is
re
se
a
rc
h
a
re
a
.
P
h
.
D
.
d
o
n
e
fro
m
AK
TU
(UPT
U
Lu
c
k
n
o
w)
i
n
2
0
2
1
.
M
a
n
y
re
p
u
ted
p
u
b
li
c
a
ti
o
n
s
h
a
v
e
b
e
e
n
d
o
n
e
re
late
d
t
o
c
o
m
p
u
ter
n
e
tw
o
r
k
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
ra
jma
li
k
@iimtin
d
ia.n
e
t
.
Dr
.
K
h
e
l
Pra
k
a
sh
J
a
y
a
n
t
tea
c
h
e
s
a
t
RK
G
IT,
G
h
a
z
iab
a
d
,
In
d
ia.
He
is
P
h
D
in
CS
E
fro
m
S
J
P
JT
Un
i
v
e
rsity
,
M
T
e
c
h
in
CS
E,
M
CA fro
m
M
NN
IT
Allah
a
b
a
d
.
Als
o
,
2
4
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
a
c
a
d
e
m
ics
.
He
is
a
l
so
wo
r
k
in
g
a
s
F
o
rm
e
r
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
n
d
re
se
a
rc
h
,
EI
T,
Eri
trea
,
No
rt
h
Eas
t
Afric
a
.
His
re
se
a
rc
h
a
re
a
is
AI,
M
L,
a
n
d
a
lg
o
rit
h
m
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
p
jay
a
n
t@g
m
a
il
.
c
o
m
.
Abh
a
y
K
u
m
a
r
Va
jp
a
y
e
e
i
s
p
u
rs
u
in
g
h
is
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fr
o
m
I
n
stit
u
te
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
,
L
u
c
k
n
o
w,
UP,
I
n
d
ia.
He
h
a
s
p
u
b
li
sh
e
d
m
a
n
y
p
a
p
e
rs
a
n
d
g
iv
e
n
talk
o
n
v
a
ri
o
u
s
tec
h
n
o
lo
g
ica
l
to
p
ics
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
y
a
n
ifi
v
e
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.