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.
37
,
No
.
3
,
Ma
r
ch
20
25
,
p
p
.
1
98
5
~1
99
8
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
37.
i
3
.
p
p
1
98
5
-
1
99
8
1985
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
M
a
rryi
ng
deep
le
a
rning
wit
hin
blo
ckcha
in t
e
chno
lo
g
y
f
o
r cr
edit
ca
rd f
ra
ud
prev
e
ntion
I
m
a
ne
K
a
rka
ba
,
E
l Mehd
i A
dn
a
ni,
M
o
ha
m
m
ed
E
rr
it
a
li
D
a
t
a
S
c
i
e
n
c
e
f
o
r
S
u
st
a
i
n
a
b
l
e
E
a
r
t
h
(
D
a
t
a
Ea
r
t
h
)
L
a
b
o
r
a
t
o
r
y
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
u
l
t
a
n
M
o
u
l
a
y
S
l
i
m
a
n
e
U
n
i
v
e
r
si
t
y
,
B
e
n
i
M
e
l
l
a
l
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
29
,
2
0
2
4
R
ev
is
ed
Sep
29
,
2
0
2
4
Acc
ep
ted
Oct
7
,
2
0
2
4
Ov
e
r
th
e
las
t
d
e
c
a
d
e
o
r
so
,
a
n
e
x
c
e
ss
iv
e
tu
rn
o
u
t
o
n
e
-
fi
n
a
n
c
ial
tr
a
n
sa
c
ti
o
n
s
b
y
c
o
m
p
a
n
ies
a
n
d
c
u
st
o
m
e
rs
re
su
lt
s
i
n
a
p
in
n
a
c
le
g
ro
wt
h
o
f
c
re
d
it
c
a
rd
fra
u
d
u
le
n
t
a
c
ts,
lea
d
in
g
t
h
e
m
to
lo
se
fre
q
u
e
n
tl
y
h
u
g
e
a
m
o
u
n
ts
o
f
m
o
n
e
y
.
In
th
e
ir
tri
a
l
to
f
in
d
t
h
e
k
e
y
to
th
is
is
su
e
,
sp
e
c
ialists
a
n
d
e
x
p
e
rts
h
a
v
e
f
o
u
n
d
e
d
a
b
u
n
c
h
o
f
fra
u
d
d
e
tec
ti
o
n
a
n
d
p
re
v
e
n
ti
o
n
m
o
d
e
ls
re
li
e
d
o
n
d
a
t
a
m
in
in
g
,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
in
g
.
Ye
t,
t
h
e
o
u
tc
o
m
e
s
we
re
n
o
t
e
ffe
c
ti
v
e
n
o
r
o
p
t
ima
l.
Th
e
re
u
p
o
n
,
to
f
o
ste
r
th
e
se
p
r
o
to
t
y
p
e
s’
f
u
n
c
ti
o
n
,
Bl
o
c
k
c
h
a
in
-
a
sa
fe
,
d
e
c
e
n
tralize
d
a
n
d
u
n
c
h
a
n
g
e
a
b
le
d
a
tab
a
se
-
wa
s d
e
p
lo
y
e
d
to
b
a
n
a
n
y
so
r
t
o
f
a
n
o
m
a
ly
o
r
d
a
ta
a
lt
e
ra
ti
o
n
a
fter
sto
r
in
g
.
F
o
r
i
d
e
n
ti
f
y
in
g
m
a
li
c
io
u
s
fin
a
n
c
ial
b
e
h
a
v
io
u
rs,
o
u
r
w
o
rk
m
a
n
a
g
e
d
to
in
term
in
g
le
a
p
re
-
d
e
sig
n
e
d
d
e
e
p
lea
rn
in
g
p
r
o
t
o
ty
p
e
wit
h
Bl
o
c
k
c
h
a
in
.
Th
a
t
is
t
o
sa
y
-
f
o
r
t
h
e
sa
k
e
o
f
p
re
v
e
n
ti
n
g
fra
u
d
u
len
c
e
th
a
t
c
o
n
c
e
rn
s
c
re
d
it
c
a
rd
-
we
a
p
p
li
e
d
t
h
e
fo
rm
e
r
p
ro
t
o
ty
p
e
i
n
Bl
o
c
k
c
h
a
i
n
sy
ste
m
.
S
ti
l
l,
B
lo
c
k
c
h
a
i
n
s
h
o
we
d
imp
o
ten
c
e
in
term
s
o
f
u
sin
g
o
ff
-
c
h
a
i
n
d
a
ta,
wh
ich
e
m
b
e
d
s
d
e
e
p
lea
rn
in
g
p
a
tt
e
rn
,
sp
e
c
ifi
c
a
ll
y
th
r
o
u
g
h
sm
a
rt
c
o
n
trac
t.
He
n
c
e
,
we
a
c
ti
v
a
ted
c
h
a
in
l
in
k
b
o
o
sti
n
g
o
u
r
m
o
d
e
l
t
o
su
rm
o
u
n
t
th
is o
b
sta
c
le.
K
ey
w
o
r
d
s
:
C
r
ed
it c
ar
d
f
r
au
d
Dee
p
lear
n
in
g
B
lo
ck
ch
ain
ar
ch
itectu
r
e
C
r
y
p
to
cu
r
r
e
n
cy
C
h
ain
lin
k
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
I
m
an
e
Kar
k
a
b
a
Data
Scien
ce
f
o
r
Su
s
tain
ab
le
E
ar
th
(
Data
E
ar
th
)
L
ab
o
r
ato
r
y
,
Facu
lty
o
f
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
,
Su
lta
n
Mo
u
lay
Sli
m
an
e
Un
iv
e
r
s
ity
B
en
i M
ellal,
2
3
0
0
0
,
Mo
r
o
cc
o
E
m
ail: im
an
e.
k
ar
k
a
b
a@
u
s
m
s
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
o
d
ay
,
t
h
e
o
n
lin
e
s
co
p
e
m
an
a
g
ed
n
o
t
o
n
ly
to
m
in
im
ize
ef
f
o
r
t a
n
d
co
n
s
er
v
e
tim
e
f
o
r
its
u
s
e
r
s
b
u
t a
ls
o
to
m
ax
im
ize
t
h
e
s
er
v
ices'
q
u
al
ity
;
th
at
is
wh
y
co
m
p
a
n
ies
an
d
in
d
iv
i
d
u
als
d
iv
e
d
ee
p
l
y
in
wh
at
we
ca
ll
'
d
ig
ital'
.
Nev
er
th
eless
,
f
alsi
f
ier
s
an
d
f
r
au
d
s
ter
s
h
av
e
b
ec
o
m
e
e
x
p
er
t
s
in
s
win
d
lin
g
f
in
a
n
cial
o
p
er
atio
n
s
.
Fre
q
u
e
n
tly
,
r
ep
o
r
ts
o
f
f
in
an
cial
in
s
titu
tio
n
s
an
d
b
an
k
s
s
h
o
w
d
r
am
atic
lo
s
s
es
in
b
illi
o
n
s
[
1
]
,
[
2
]
.
So
,
u
s
in
g
o
n
lin
e
s
er
v
ices
as
a
b
less
in
g
tu
r
n
s
in
to
a
cu
r
s
e.
I
n
t
h
is
r
eg
ar
d
,
th
e
in
cr
ea
s
ed
p
ac
e
o
f
r
esear
ch
o
n
c
r
ed
it
ca
r
d
f
r
a
u
d
o
v
er
t
h
e
last
two
d
ec
ad
es
h
as
attr
ac
ted
th
e
atten
tio
n
o
f
s
cien
tis
ts
an
d
e
x
p
er
ts
o
f
f
in
an
cial
s
ec
to
r
f
o
r
in
v
en
tin
g
ef
f
ec
tiv
e
s
y
s
tem
s
th
at
m
a
y
r
eso
lv
e
th
i
s
is
s
u
e;
in
th
e
s
en
s
e
o
f
d
etec
ti
n
g
an
d
s
to
p
p
in
g
illeg
itima
te
i
n
ter
v
en
tio
n
s
.
Ou
r
in
ter
est
in
th
is
s
tu
d
y
lies
in
f
r
au
d
tr
an
s
ac
tio
n
s
o
f
cr
ed
it
ca
r
d
s
,
as
th
er
e
ar
e
v
ar
io
u
s
s
ca
m
s
th
at
ca
n
th
r
ea
ten
f
in
an
cial
ac
co
u
n
t o
wn
er
s
,
c
r
ed
it c
ar
d
h
o
ld
e
r
s
,
en
te
r
p
r
is
es'
ac
co
u
n
ts
,
an
d
o
th
er
s
.
Ser
io
u
s
an
d
ex
ten
s
iv
e
th
in
k
in
g
ab
o
u
t
cr
e
d
it
ca
r
d
f
r
au
d
in
v
o
lv
es
a
m
in
d
-
b
o
g
g
lin
g
jo
u
r
n
ey
th
r
o
u
g
h
a
lab
y
r
in
th
o
f
r
ec
k
o
n
in
g
o
p
er
atio
n
s
an
d
d
iag
n
o
s
is
-
a
p
u
zz
le
th
at
h
as
to
b
e
d
ec
ip
h
er
ed
r
ad
ical
ly
.
A
m
alicio
u
s
ac
t
is
m
u
tab
le
an
d
i
m
itativ
e.
I
n
ad
d
itio
n
,
th
e
f
r
au
d
b
e
h
av
io
u
r
s
ar
e
d
y
n
am
ic;
th
at
is
to
s
ay
,
th
ey
ar
e
n
o
t
s
tick
in
g
to
th
e
p
r
ec
ed
en
t
p
atter
n
wh
en
th
ey
ar
e
ex
p
o
s
ed
to
c
o
m
p
u
tatio
n
al
an
aly
s
is
.
Scam
m
er
s
f
r
eq
u
en
tly
d
u
p
licate
th
e
co
n
s
u
m
er
'
s
ac
tio
n
s
,
to
o
.
Fo
r
th
is
r
ea
s
o
n
,
a
f
r
au
d
u
len
t
ac
t
is
h
ar
d
a
n
d
r
em
ain
s
co
m
p
lex
all
th
e
tim
e
to
b
e
d
etec
ted
.
T
h
er
e
f
o
r
e
-
in
th
eir
attem
p
t
to
p
r
e
d
ict,
d
etec
t
an
d
b
an
f
r
au
d
th
r
ea
ts
-
s
cien
tis
ts
h
av
e
p
r
o
p
o
s
ed
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
98
5
-
1
99
8
1986
p
leth
o
r
a
o
f
ap
p
r
o
ac
h
es.
Data
m
in
in
g
,
m
ac
h
in
e
lear
n
in
g
a
n
d
d
ee
p
lear
n
in
g
a
r
e
d
ee
m
e
d
to
b
e
th
e
m
o
s
t
s
ig
n
if
ican
t
tech
n
iq
u
es
b
ec
au
s
e
th
ey
a
r
e
ch
a
r
ac
ter
ized
with
th
eir
d
etec
tio
n
s
y
s
tem
ef
f
icien
cy
,
esp
ec
ially
wh
e
n
d
ea
lin
g
with
v
ast co
m
p
lex
ity
m
atter
s
[
3
]
–
[
7
]
.
Fo
r
th
e
f
ir
s
t
ca
teg
o
r
y
,
s
cien
tis
ts
r
eso
r
ted
to
a
h
y
b
r
id
ap
p
r
o
a
ch
th
at
h
o
l
d
s
d
ata
m
in
in
g
al
g
o
r
ith
m
s
at
s
ev
er
al
s
tag
es
in
clu
d
in
g
th
e
d
atab
ase
lev
el
an
d
n
etwo
r
k
lev
el
to
b
etter
th
e
ac
cu
r
ac
y
o
f
f
r
au
d
d
etec
tio
n
[
3
]
.
An
o
th
er
s
tu
d
y
c
o
m
b
in
e
d
m
u
lt
ip
le
lear
n
ed
f
r
a
u
d
d
etec
to
r
s
u
n
d
er
a
"c
o
s
t
m
o
d
el"
to
d
ec
r
ea
s
e
lo
s
s
d
u
e
to
f
r
au
d
th
r
o
u
g
h
d
is
tr
ib
u
ted
d
ata
m
in
in
g
o
f
f
r
au
d
m
o
d
els
[
7
]
.
B
esid
es,
s
o
m
e
r
esear
ch
er
s
u
tili
ze
d
B
ay
es
m
in
im
u
m
r
is
k
ap
p
r
o
ac
h
to
r
ea
c
h
o
p
tim
al
r
es
u
lts
an
d
q
u
an
tifie
d
b
y
m
o
n
eta
r
y
s
av
i
n
g
f
o
r
d
etec
tin
g
cr
ed
it
ca
r
d
f
r
au
d
[
8
]
.
T
h
e
s
ec
o
n
d
ca
teg
o
r
y
,
s
tu
d
ies
f
o
cu
s
ed
o
n
t
h
e
p
e
r
f
o
r
m
an
ce
o
f
th
r
ee
d
if
f
e
r
en
t
m
ac
h
in
e
lear
n
in
g
m
o
d
els:
L
o
g
is
tic
r
eg
r
ess
io
n
,
d
ec
is
io
n
tr
ee
an
d
r
an
d
o
m
f
o
r
est,
r
ec
o
m
m
en
d
i
n
g
th
e
th
ir
d
al
g
o
r
ith
m
f
o
r
i
ts
h
ig
h
s
co
r
es
in
class
if
icatio
n
,
p
r
ed
ictio
n
an
d
d
etec
tio
n
o
f
f
r
a
u
d
u
len
t
cr
ed
it
ca
r
d
tr
an
s
ac
tio
n
[
5
]
,
as
w
ell
as
th
ey
a
d
ap
ted
u
n
d
er
s
am
p
lin
g
tech
n
iq
u
e
t
o
o
v
er
co
m
e
a
class
im
b
alan
ce
[
9
]
.
Als
o
,
th
ey
tr
ied
to
en
h
a
n
ce
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
ex
is
tin
g
cr
e
d
it
ca
r
d
f
r
au
d
d
etec
tio
n
s
y
s
tem
an
d
s
u
g
g
este
d
Ap
p
r
o
x
-
SMOT
E
f
e
d
er
ated
lear
n
in
g
c
r
ed
it
ca
r
d
f
r
au
d
d
etec
tio
n
s
y
s
tem
[
1
0
]
.
T
h
e
last
ca
teg
o
r
y
,
au
t
h
o
r
s
wield
ed
a
h
ig
h
p
e
r
f
o
r
m
an
ce
,
d
is
tr
ib
u
ted
clo
u
d
co
m
p
u
tin
g
en
v
ir
o
n
m
en
t
to
n
av
ig
ate
p
ast
co
m
m
o
n
f
r
au
d
d
etec
tio
n
p
r
o
b
lem
s
lik
e
c
lass
im
b
alan
ce
an
d
s
ca
lab
ilit
y
[
4
]
.
I
n
ad
d
itio
n
,
t
h
ey
d
r
ew
at
ten
tio
n
to
Au
to
e
n
co
d
er
as
an
u
n
s
u
p
er
v
is
ed
d
ee
p
lear
n
in
g
m
o
d
el
(
DL
M)
af
ter
p
r
o
v
in
g
its
r
o
b
u
s
tn
ess
wh
en
tr
ain
e
d
o
n
a
h
u
g
e
d
ataset
-
in
co
m
p
a
r
is
o
n
t
o
ANN
an
d
C
NN
alg
o
r
ith
m
s
-
f
o
r
th
e
s
ak
e
o
f
d
et
ec
tin
g
f
r
au
d
tr
an
s
ac
tio
n
s
[
6
]
.
I
n
s
p
ite
o
f
th
e
v
ar
ie
d
s
y
s
tem
s
an
d
f
r
am
ewo
r
k
s
h
a
v
e
b
ee
n
e
m
p
lo
y
ed
f
o
r
d
etec
tin
g
cr
e
d
it
ca
r
d
f
r
au
d
,
m
an
y
s
h
o
r
tco
m
in
g
s
ar
e
s
till
e
m
er
g
in
g
.
T
h
e
f
r
eq
u
en
t
lim
itatio
n
s
co
n
ce
r
n
m
o
s
tly
im
b
alan
c
ed
d
ata,
ad
v
er
s
ar
ial
attac
k
s
,
r
ea
l
-
tim
e
d
ete
ctio
n
,
an
d
d
ata
co
n
f
id
e
n
tiality
.
T
o
s
tar
t
with
,
th
e
im
b
alan
ce
d
o
r
s
k
ewe
d
class
d
is
tr
ib
u
ted
is
d
ee
m
ed
o
n
e
o
f
th
e
co
n
v
en
tio
n
al
h
u
r
d
les
th
at
a
f
f
ec
t
cr
itically
p
r
ed
ictio
n
ac
cu
r
ac
y
.
Ad
d
itio
n
ally
,
alter
atio
n
s
o
f
f
r
au
d
s
tr
ateg
ies,
wh
ich
m
ea
n
s
th
at
s
ca
m
m
er
s
p
er
m
an
en
tly
co
n
ce
i
v
e
n
ew
atta
ck
an
d
f
r
au
d
tactics
to
d
ef
y
cr
e
d
it
ca
r
d
f
r
a
u
d
d
et
ec
tio
n
s
y
s
tem
s
,
p
er
m
itti
n
g
th
em
to
a
v
o
id
s
im
u
ltan
eo
u
s
ly
t
h
e
d
etec
tio
n
o
f
th
e
n
o
v
el
an
d
th
e
ea
r
lier
-
u
n
s
ee
n
f
alsi
f
ied
tr
an
s
ac
tio
n
s
.
T
h
ey
u
s
e
d
if
f
er
en
t
o
p
p
o
s
in
g
tr
ick
s
lik
e
d
ata
p
o
is
o
n
in
g
,
ev
asio
n
attac
k
s
an
d
f
alsi
f
y
in
g
th
e
in
p
u
t
d
ata
t
o
d
ec
eit
th
e
s
y
s
tem
.
Mo
r
eo
v
e
r
,
ch
a
n
g
es
in
ca
r
d
h
o
ld
er
'
s
b
eh
av
io
r
in
a
co
n
tin
u
o
u
s
way
ch
allen
g
es
th
e
s
y
s
tem
s
to
d
etec
t
an
d
p
r
ev
en
t
f
r
a
u
d
u
le
n
t
o
p
er
atio
n
s
.
L
ast
an
d
n
o
t
least,
b
u
ild
in
g
r
ea
l
-
tim
e
d
etec
tio
n
s
y
s
tem
b
ec
o
m
es
c
o
m
p
licated
i
n
f
ield
s
with
h
u
g
e
tr
a
n
s
ac
tio
n
s
an
d
g
ian
t
d
atasets
.
So
,
an
y
m
in
u
te
-
d
elay
in
f
r
a
u
d
d
etec
tio
n
ca
n
lead
to
f
in
an
cial
lo
s
s
es
f
o
r
in
d
iv
id
u
als
(
ca
r
d
h
o
ld
e
r
s
)
an
d
in
s
titu
tio
n
s
.
Af
ter
ass
ess
in
g
n
u
m
er
o
u
s
c
r
e
d
it
ca
r
d
f
r
a
u
d
s
y
s
tem
s
,
we
in
f
er
r
ed
t
h
at
d
ata
m
in
i
n
g
,
m
ac
h
i
n
e
lear
n
i
n
g
o
r
d
ee
p
lear
n
in
g
s
y
s
tem
s
tak
e
ad
v
an
tag
e
o
f
v
a
r
io
u
s
tech
n
i
q
u
es
to
b
o
o
s
t
th
eir
s
tr
en
g
th
an
d
ef
f
icien
cy
.
Yet,
th
ey
p
o
s
s
ess
p
r
o
s
an
d
co
n
s
,
t
h
e
th
in
g
th
at
allo
ws
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
al
g
o
r
ith
m
s
to
ex
ce
l
in
d
etec
tin
g
o
n
e
class
o
f
d
ata
b
u
t
s
tr
u
g
g
le
with
o
th
er
s
,
o
r
th
e
y
m
ay
p
er
f
o
r
m
well
in
a
s
p
ec
if
ic
s
y
s
tem
an
d
f
ail
in
an
o
th
er
.
Ap
ar
t
f
r
o
m
,
th
e
co
m
m
o
n
p
u
r
p
o
s
e
o
f
th
e
m
ajo
r
it
y
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
is
o
n
ly
to
d
etec
t
f
r
au
d
in
n
ew
tr
an
s
ac
tio
n
s
.
I
n
th
e
v
i
ew
o
f
th
ese
s
h
o
r
tc
o
m
i
n
g
s
,
a
p
r
o
p
o
s
ed
m
o
d
el
em
b
ed
d
ed
in
co
n
s
u
m
in
g
a
DL
M
in
B
lo
ck
ch
ain
tech
n
o
lo
g
y
f
o
r
m
an
y
r
ea
s
o
n
s
.
B
lo
ck
ch
ain
is
o
f
k
e
y
im
p
o
r
tan
ce
in
s
to
r
in
g
d
ata,
tam
p
er
r
esis
tan
ce
,
an
d
tr
ac
ea
b
ilit
y
.
Fu
r
th
er
m
o
r
e,
it
u
s
es
cr
y
p
to
g
r
a
p
h
ic
k
n
o
wled
g
e
to
ascer
tai
n
its
im
m
u
ta
b
ilit
y
an
d
u
n
f
o
r
g
ea
b
ilit
y
wh
en
tr
ea
tin
g
f
r
a
u
d
a
n
d
d
ata
co
r
r
u
p
ti
o
n
.
O
n
th
e
o
th
er
s
id
e,
to
ad
d
r
ess
th
e
is
s
u
e
o
f
im
b
alan
ce
d
d
ata,
we
h
a
v
e
d
ep
en
d
e
d
o
n
Au
to
en
c
o
d
er
as
a
d
ee
p
lear
n
in
g
alg
o
r
ith
m
f
o
r
its
ef
f
ec
tiv
en
ess
,
s
h
o
win
g
o
p
ti
m
al
r
esu
lts
s
in
ce
it
d
o
es
n
o
t
d
em
an
d
d
ata
am
en
d
m
en
t.
T
h
er
ef
o
r
e,
we
h
av
e
r
eli
ed
o
n
th
is
d
o
u
b
le
-
k
ey
m
eth
o
d
to
in
ten
s
if
y
s
ec
u
r
ity
an
d
d
ata
p
r
o
tectio
n
as
task
s
r
ef
er
r
ed
to
B
lo
ck
ch
ai
n
,
wh
ile
DL
M
is
r
esp
o
n
s
ib
le
o
f
m
ain
tain
in
g
f
r
au
d
d
etec
tio
n
ac
cu
r
ac
y
.
Fo
r
t
h
is
r
ea
s
o
n
,
o
u
r
p
r
o
to
ty
p
e
is
b
eliev
e
d
to
b
e
m
o
r
e
r
esil
ien
t
an
d
r
o
b
u
s
t
in
b
o
th
d
etec
tio
n
an
d
p
r
ev
en
tio
n
o
f
f
r
au
d
u
len
t tr
a
n
s
ac
tio
n
s
.
T
h
e
r
est
o
f
th
is
ar
ticle
is
p
r
o
c
ee
d
ed
as
f
o
llo
ws:
T
h
e
s
ec
o
n
d
s
ec
tio
n
s
h
o
ws
s
tr
en
g
th
s
an
d
w
ea
k
n
ess
es
o
f
B
lo
ck
ch
ain
ar
c
h
itectu
r
e
a
n
d
s
h
ed
s
lig
h
t
o
n
C
h
ai
n
lin
k
as
a
n
etwo
r
k
co
n
n
ec
tin
g
B
lo
ck
ch
ain
to
th
e
r
ea
l
wo
r
ld
.
T
h
e
th
ir
d
s
ec
tio
n
is
d
e
v
o
ted
to
a
d
escr
ip
tio
n
to
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
.
T
h
e
v
is
u
ali
za
tio
n
(
r
esu
lts
an
d
d
is
cu
s
s
io
n
)
an
d
th
e
c
o
n
clu
s
io
n
ar
e
r
esp
ec
tiv
ely
af
f
o
r
d
ed
in
t
h
e
f
o
u
r
t
h
an
d
th
e
f
if
th
s
ec
tio
n
s
.
2.
B
ACK
G
RO
UND
AN
D
M
O
T
I
VA
T
I
O
N
Sp
ec
ialis
ts
an
d
ex
p
er
ts
a
p
p
r
o
ac
h
an
y
n
ew
is
s
u
e
with
a
n
e
x
is
tin
g
s
et
o
f
s
cien
tific
r
esear
c
h
f
in
d
in
g
s
,
th
r
o
u
g
h
in
s
ig
h
t,
lo
g
ical
in
ter
p
r
etatio
n
s
,
an
d
v
a
r
io
u
s
f
o
r
m
s
o
f
h
y
p
o
th
esis
test
in
g
,
ca
ll
u
p
o
n
wh
atev
e
r
p
r
io
r
ex
p
er
im
en
ts
th
ey
h
a
v
e
co
n
d
u
c
ted
an
d
wh
atev
er
r
esear
ch
o
u
t
co
m
es
th
ey
o
wn
to
attem
p
t
a
s
o
lu
tio
n
.
T
h
u
s
,
it
i
s
co
m
m
o
n
f
o
r
u
s
to
f
o
llo
w
t
h
e
s
am
e
tr
ac
k
,
u
n
til
we
h
av
e
d
is
co
v
er
ed
"Bl
o
ck
ch
ain
tech
n
o
lo
g
y
",
as
a
n
e
f
f
icien
t
to
o
l a
n
d
o
p
tim
al
s
tr
ateg
y
f
o
r
c
r
ed
it c
ar
d
f
r
a
u
d
p
r
ev
en
tio
n
.
'
B
lo
ck
ch
ain
'
is
alm
o
s
t a
s
s
o
ciate
d
with
'B
itco
in
'
,
th
is
lets
a
d
ilem
m
a
f
o
r
p
eo
p
le
t
o
r
ea
lize
d
is
tin
g
u
is
h
ab
ly
th
e
c
o
n
ce
p
t
o
f
b
o
th
B
lo
ck
c
h
ain
an
d
B
itco
in
;
in
th
e
s
en
s
e,
th
ey
o
f
ten
attain
th
e
id
ea
o
f
th
e
f
ir
s
t
(
B
lo
ck
ch
ain
)
o
n
ly
in
th
e
co
n
tex
t
o
f
cr
y
p
t
o
cu
r
r
e
n
cy
,
i
g
n
o
r
in
g
th
e
g
en
u
i
n
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
r
r
yin
g
d
ee
p
lea
r
n
in
g
w
ith
i
n
b
lo
ck
ch
a
in
tech
n
o
lo
g
y
fo
r
cred
it c
a
r
d
fr
a
u
d
p
r
ev
en
tio
n
(
I
m
a
n
e
K
a
r
ka
b
a
)
1987
r
o
le
o
f
th
is
n
o
v
ice
tech
n
o
lo
g
y
.
No
n
eth
eless
,
B
itco
in
r
ests
th
e
p
r
im
e
cr
y
p
to
cu
r
r
en
c
y
th
at
u
s
ed
B
lo
ck
ch
ain
f
o
r
tr
ac
in
g
tr
an
s
ac
tio
n
s
v
ia
a
n
etwo
r
k
in
a
p
r
ec
is
e,
co
n
f
id
en
tial,
an
d
s
ec
u
r
e
m
eth
o
d
b
ey
o
n
d
a
th
ir
d
p
ar
t
y
in
ter
v
en
tio
n
;
t
h
e
s
ce
n
a
r
io
th
at
u
s
u
ally
tak
es
p
lace
in
b
a
n
k
s
an
d
in
v
estme
n
t
co
m
p
a
n
ies
[
1
1
]
.
T
h
e
d
ep
l
o
y
m
e
n
t
o
f
B
lo
ck
c
h
ai
n
f
ir
s
tly
o
cc
u
r
r
ed
in
2
0
0
8
,
b
y
t
h
e
tim
e
Sato
s
h
i
Nak
am
o
to
p
r
o
d
u
ce
d
h
is
ar
ticl
e
n
am
ed
"Bi
tco
in
:
A
p
ee
r
-
to
-
p
ee
r
E
lectr
o
n
ic
C
ash
Sy
s
tem
"
as sh
o
wn
in
Fig
u
r
e
1
[
1
2
]
.
Fig
u
r
e
1
.
P2
P e
lectr
o
n
ic
p
ay
m
en
t sy
s
tem
2
.
1
.
B
lo
c
k
cha
in co
ncept
First
o
f
all,
we
will
clar
if
y
th
e
co
n
ce
p
t
o
f
B
lo
ck
ch
ain
(
wh
at
is
B
lo
ck
ch
ain
?)
,
th
e
n
we
will
d
em
o
n
s
tr
ate
th
e
k
ey
-
m
o
tiv
at
io
n
b
e
h
in
d
d
ev
elo
p
in
g
t
h
is
n
o
v
el
tech
n
o
lo
g
y
.
B
lo
ck
c
h
ai
n
is
a
p
r
o
m
in
en
t
tech
n
o
lo
g
y
th
at
f
ac
ilit
ates
th
e
s
to
r
ag
e
an
d
t
h
e
tr
an
s
m
is
s
io
n
o
f
v
alu
es
th
r
o
u
g
h
in
ter
n
et
in
a
r
ap
id
,
ac
cu
r
ate,
an
d
s
af
e
way
.
I
t d
o
es
n
o
t
n
ec
ess
itate
an
y
in
ter
p
o
s
itio
n
o
f
a
th
i
r
d
p
ar
ticip
an
t
n
o
r
r
e
f
er
t
o
ce
n
tr
al
o
r
g
a
n
co
n
tr
o
l
[
1
3
]
.
I
t
f
u
n
ctio
n
s
as
a
d
atab
ase
en
co
m
p
ass
in
g
th
e
en
tire
h
is
to
r
ic
o
f
tr
an
s
ac
tio
n
s
m
ad
e
ea
r
lie
r
.
T
h
e
m
o
s
t
s
alien
t
asp
ec
t
o
f
B
lo
ck
ch
ain
s
y
s
tem
is
'
d
ec
en
tr
aliza
tio
n
'
[
1
4
]
.
T
h
e
latter
s
tan
d
s
f
o
r
th
e
m
u
ltip
licity
o
f
th
e
s
er
v
er
h
o
s
tin
g
; in
o
th
e
r
wo
r
d
s
,
th
e
h
o
s
tin
g
is
d
o
n
e
b
y
n
u
m
e
r
o
u
s
n
o
d
es a
n
d
n
o
t
o
n
e
s
o
le
s
er
v
er
.
R
ec
en
tly
,
a
tr
em
en
d
o
u
s
wav
e
o
f
in
ter
est
to
war
d
s
I
o
T
h
as
t
ak
en
p
lace
.
I
n
p
ar
allel,
B
lo
ck
ch
ain
h
as
k
n
o
wn
a
n
u
n
p
r
ec
e
d
en
ted
s
p
r
ea
d
in
th
e
f
in
an
cial
s
ec
to
r
.
S
ev
er
al
tech
n
o
lo
g
ies
h
o
ld
B
lo
ck
ch
ain
p
ar
ticu
lar
ly
E
th
er
eu
m
th
at
in
v
o
l
v
es
eth
er
(
eth
)
as
th
e
m
ain
cr
y
p
to
cu
r
r
en
cy
,
u
n
lik
e
B
itco
in
th
at
s
u
f
f
icien
tly
s
to
ck
p
iles
f
in
an
cial
o
p
e
r
atio
n
s
.
So
,
th
e
p
r
ec
ed
en
t
s
to
ws
s
m
ar
t
co
n
tr
ac
t
s
-
u
n
co
n
n
ec
ted
c
r
y
p
to
g
r
ap
h
f
u
n
ctio
n
s
as
s
o
o
n
as
p
r
e
-
f
in
ite
f
a
cto
r
s
em
er
g
e.
A
l
lo
win
g
u
s
er
s
to
g
et
in
to
u
ch
an
d
cir
c
u
late
th
eir
d
ata
in
d
ep
en
d
en
tly
o
f
an
y
s
u
p
r
em
e
o
r
g
an
is
m
'
s
in
ter
m
ed
iatio
n
,
th
e
s
m
ar
t
co
n
tr
ac
t
g
ets
in
to
ef
f
ec
t
as
a
n
o
v
ice
asp
ec
t
m
ain
tain
in
g
d
ec
en
tr
aliza
tio
n
b
e
y
o
n
d
th
e
s
u
p
r
em
ac
y
ex
er
ted
o
n
u
s
er
s
'
d
ata
b
y
Go
o
g
le,
Am
az
o
n
,
Fa
ce
b
o
o
k
,
Mic
r
o
s
o
f
t
(
GAFAM
)
[
1
5
]
.
2
.
2
.
B
lo
c
k
cha
in
f
un
ct
io
na
lity
T
h
e
B
lo
ck
ch
ain
s
y
s
tem
in
q
u
ir
es
v
ar
ied
elem
en
ts
o
f
p
a
r
am
o
u
n
t
im
p
o
r
tan
ce
f
o
r
s
u
s
tain
in
g
its
ef
f
icien
cy
as
Fig
u
r
e
2
d
em
o
n
s
tr
ates.
Prim
ar
ily
,
th
e
'
b
lo
ck
'
n
o
tio
n
is
p
iv
o
tal
as
'
b
lo
ck
s
'
d
ep
ict
th
e
p
r
in
cip
al
h
o
ld
er
s
ca
r
r
y
in
g
a
s
to
r
a
g
e
o
f
tr
an
s
ac
tio
n
s
o
n
B
lo
ck
ch
ain
d
at
ab
ase
-
tr
an
s
ac
tio
n
s
ca
n
n
o
t
b
e
in
v
er
ted
wh
e
n
th
ey
ar
e
ap
p
en
d
ed
to
th
e
b
lo
c
k
.
Si
m
ilar
ly
,
th
e
b
lo
c
k
s
ca
n
n
o
t
b
e
alter
ed
o
n
ce
a
b
lo
ck
is
ad
jo
i
n
e
d
to
th
e
ch
ai
n
.
Sin
ce
B
lo
ck
ch
ain
is
ac
ce
s
s
ib
le,
th
e
wh
o
le
in
f
o
r
m
atio
n
s
to
r
ag
e
in
b
lo
ck
s
will
r
est
ch
a
n
g
eless
[
1
6
]
.
B
ec
au
s
e
o
f
t
h
e
lin
ea
r
way
b
l
o
ck
s
ar
e
l
o
ca
ted
,
v
er
y
clo
s
e
t
o
ea
ch
o
th
er
,
th
ey
ar
e
p
r
o
tecte
d
with
a
c
o
d
in
g
r
u
le
co
m
p
u
tatio
n
ally
lab
elled
'
h
ash
f
u
n
ctio
n
'
.
So
,
r
ein
f
o
r
cin
g
wh
at
was
in
d
icate
d
ea
r
lier
,
ev
er
y
s
in
g
le
b
lo
c
k
co
n
tain
s
a
s
er
ies
o
f
tr
an
s
ac
tio
n
s
with
a
s
o
u
r
ce
r
ef
er
r
ed
to
th
e
'
h
ash
'
o
f
th
e
p
r
ec
ed
en
t
b
lo
ck
;
ea
ch
in
d
i
v
id
u
al
b
lo
ck
is
ap
p
en
d
ed
to
B
lo
ck
ch
ain
af
ter
b
ein
g
m
in
ed
b
y
m
in
er
s
,
wh
ich
a
r
e
a
b
u
n
c
h
o
f
co
m
p
u
ter
s
th
e
p
u
r
p
o
s
e
o
f
wh
ich
is
ac
h
iev
in
g
th
e
ad
eq
u
ate
'
h
ash
'
f
o
r
th
e
b
lo
ck
aim
in
g
at
th
e
tr
an
s
ac
tio
n
ap
p
r
o
v
al.
T
h
e
p
r
o
ce
s
s
is
ter
m
ed
m
in
in
g
wh
ich
is
g
r
o
u
n
d
ed
o
n
a
d
ec
en
tr
alize
d
p
r
o
to
co
l n
a
m
ed
'
p
r
o
o
f
-
of
-
wo
r
k
'
[
1
7
]
.
'
T
r
an
s
ac
tio
n
'
p
r
esen
ts
th
e
s
ec
o
n
d
elem
en
t.
W
h
en
th
e
t
r
an
s
ac
tio
n
tak
es
p
lace
,
it
is
s
to
r
ed
as
a
b
lo
ck
o
f
d
ata.
I
t
d
em
o
n
s
tr
ates
th
e
m
o
b
i
lity
o
r
s
h
if
tin
g
o
f
an
ass
et.
T
h
e
d
ata
b
lo
ck
ca
n
r
ec
o
r
d
i
n
f
o
r
m
atio
n
r
elate
d
to
th
e
u
s
er
'
s
ch
o
ice:
wh
o
,
wh
at,
w
h
en
,
wh
er
e
,
h
o
w
m
u
ch
,
an
d
ev
en
th
e
cir
cu
m
s
tan
ce
d
es
cr
ib
es
a
s
er
v
ice
o
r
a
p
r
o
d
u
ct.
C
o
n
ce
r
n
i
n
g
B
itco
in
,
a
tr
an
s
ac
tio
n
is
a
cr
y
p
to
c
u
r
r
e
n
cy
ex
ch
an
g
e,
b
u
t
in
E
th
e
r
eu
m
,
it
is
an
y
o
p
er
atio
n
m
ay
ch
an
g
e
th
e
s
tatu
s
o
f
th
e
d
ata
s
av
ed
with
in
th
e
B
lo
ck
ch
ai
n
s
y
s
tem
.
'C
o
n
s
en
s
u
s
'
is
th
e
th
ir
d
elem
en
t.
I
t
is
a
g
ad
g
et
to
ler
atin
g
f
ailu
r
es
ef
f
ec
ted
in
B
lo
ck
ch
a
in
[
1
8
]
.
I
t
d
ep
lo
y
s
p
r
o
o
f
-
of
-
wo
r
k
(
Po
W
)
p
r
o
to
c
o
l.
T
h
is
m
ak
es
th
e
n
o
d
es
-
o
f
b
o
th
E
t
h
er
eu
m
an
d
B
itco
in
-
in
ag
r
ee
m
e
n
t
o
n
th
e
s
tatu
s
o
f
all
d
ata
s
to
r
ed
o
n
B
lo
ck
ch
ain
,
an
d
th
e
n
f
o
r
b
i
d
s
o
m
e
ty
p
es
o
f
f
r
au
d
u
len
t
ac
t
s
.
Po
W
an
d
Pr
o
o
f
-
of
-
Stak
e
(
Po
S)
ar
e
th
e
f
am
o
u
s
k
in
d
s
o
f
co
n
s
en
s
u
s
[
1
9
]
.
E
t
h
er
eu
m
a
n
d
B
itco
in
u
s
e
Po
W
b
ec
au
s
e
th
e
m
in
e
r
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
98
5
-
1
99
8
1988
wh
o
f
ir
s
t
ac
co
m
p
lis
h
es
f
o
r
m
in
g
a
n
o
v
el
b
lo
c
k
ch
ar
g
e
d
with
tr
an
s
ac
tio
n
s
,
d
is
tr
ib
u
tes
th
e
o
u
tco
m
es
in
th
e
r
esid
u
e
o
f
th
e
s
y
s
tem
n
etwo
r
k
an
d
g
ain
s
cr
y
p
to
cu
r
r
en
c
y
.
T
h
e
m
in
er
s
ig
n
if
ies
th
e
q
u
ick
e
s
t
co
m
p
u
ter
wh
ich
is
ab
le
to
f
o
r
m
a
n
ew
b
lo
ck
b
y
d
ec
ip
h
er
in
g
a
cr
y
p
to
g
r
a
p
h
ic
r
id
d
le.
'
Sm
ar
t
co
n
tr
ac
ts
'
r
ep
r
esen
t
th
e
u
ltima
te
co
m
p
o
n
e
n
t.
T
h
ey
ca
n
b
e
d
ef
in
e
d
as
r
ec
o
r
d
e
d
p
r
o
g
r
am
s
o
n
B
lo
ck
ch
ain
.
T
h
e
m
ajo
r
f
u
n
ctio
n
o
f
s
m
ar
t
co
n
tr
ac
ts
is
n
o
t
o
n
ly
to
au
to
m
atiz
e
ef
f
ec
tin
g
o
p
er
atio
n
s
with
o
u
t
th
e
in
ter
p
o
s
itio
n
o
f
th
e
th
ir
d
p
ar
ty
b
u
t a
ls
o
to
au
t
o
m
atize
th
e
wo
r
k
-
f
lo
w,
b
y
d
o
in
g
t
h
e
u
p
c
o
m
in
g
p
r
o
ce
s
s
wh
en
th
e
p
er
m
itti
n
g
co
n
d
itio
n
s
ar
e
av
ailab
le.
T
h
eir
f
ir
s
t
u
s
e
wa
s
b
y
th
e
E
th
er
eu
m
B
lo
ck
ch
a
in
ty
p
ically
wh
en
co
n
d
itio
n
s
w
er
e
a
d
d
ed
t
o
tr
an
s
ac
tio
n
s
[
2
0
]
.
Fig
u
r
e
2
.
Stru
ctu
r
e
o
f
B
lo
ck
ch
ain
2
.
3
.
B
lo
c
k
cha
in s
t
re
ng
t
hs
T
h
e
ef
f
icien
c
y
o
f
B
lo
ck
ch
ain
lies
in
its
s
ec
u
r
ity
,
co
n
f
id
e
n
tiality
,
an
d
s
p
ee
d
.
T
h
e
s
y
s
tem
m
atch
es
in
th
e
alter
atio
n
s
ac
co
m
p
an
ied
with
th
e
d
ig
ital
wav
e
.
I
t
is
u
s
ef
u
l
in
ter
m
s
o
f
g
ain
in
g
tim
e
an
d
ef
f
o
r
t
as
m
a
k
in
g
f
in
an
cial
o
p
er
atio
n
s
n
o
wad
a
y
s
n
ee
d
s
tim
e
a
n
d
ef
f
o
r
t
to
r
e
p
licate
s
to
r
ag
e,
d
ep
en
d
in
g
o
n
a
th
ir
d
in
ter
p
o
s
er
ap
p
r
o
v
als.
I
t
also
s
to
p
s
f
r
au
d
u
len
ce
s
in
ce
th
e
s
to
r
ag
e
-
s
av
in
g
m
ec
h
an
is
m
s
ar
e
v
u
l
n
er
ab
le
in
f
r
o
n
t
o
f
t
h
e
h
u
g
e
tid
e
o
f
m
alicio
u
s
ac
ts
.
Mo
r
eo
v
er
,
d
o
u
b
t
a
n
d
lack
o
f
tr
u
s
t
c
an
s
lo
w
d
ata
v
er
if
icatio
n
.
T
h
er
ef
o
r
e,
B
lo
ck
ch
ain
p
o
s
s
ess
es th
e
f
o
r
co
m
in
g
c
h
ar
ac
ter
is
tics
[
2
1
]
–
[
2
3
]
:
−
Dec
en
tr
aliza
tio
n
:
T
h
e
aim
o
f
t
h
is
tr
ait
is
to
d
ec
r
ea
s
e
th
e
co
n
tr
o
l
en
jo
y
ed
b
y
a
ce
n
tr
al
e
n
tity
th
at
h
as
an
ab
s
o
lu
te
au
th
o
r
ity
o
v
e
r
d
ata
u
s
er
s
.
I
t b
r
in
g
s
au
th
o
r
it
y
f
r
o
m
o
n
e
ce
n
tr
al
o
r
g
an
t
o
th
e
s
p
lit
n
e
two
r
k
.
−
T
r
an
s
p
ar
en
c
y
:
T
h
e
d
ec
en
tr
ali
ze
d
n
atu
r
e
o
f
B
lo
ck
c
h
ain
p
er
m
its
tr
an
s
ac
tio
n
s
to
b
e
s
ee
n
b
y
all
th
e
n
o
d
es
o
f
th
e
n
etwo
r
k
;
s
o
,
th
e
tr
an
s
p
ar
en
cy
r
ate
au
g
m
en
ts
eq
u
ally
f
o
r
th
e
s
y
s
tem
o
r
g
an
s
.
T
h
e
r
el
atio
n
b
etwe
en
b
lo
ck
s
an
d
n
o
d
es
p
r
o
v
id
es
a
tr
ac
k
o
f
ea
c
h
tr
a
n
s
ac
tio
n
ar
is
es
in
th
e
n
etwo
r
k
.
T
h
e
c
o
m
b
in
atio
n
o
f
tr
an
s
p
ar
en
cy
a
n
d
co
n
s
en
s
u
s
r
e
n
d
er
s
th
e
B
lo
ck
ch
ain
s
y
s
tem
v
ir
tu
ally
u
n
b
r
ea
k
ab
le.
T
h
er
ef
o
r
e,
th
er
e
is
n
o
r
o
o
m
f
o
r
f
r
au
d
b
eh
a
v
io
u
r
s
s
in
ce
ev
er
y
u
s
er
watc
h
es o
v
er
t
h
e
n
etwo
r
k
.
−
E
f
f
icien
cy
a
n
d
s
p
ee
d
:
B
ec
au
s
e
o
f
th
e
s
h
ar
ed
le
d
g
er
a
m
o
n
g
al
l
o
r
g
an
s
o
f
th
e
s
y
s
tem
,
tim
e
-
wastin
g
r
ec
o
r
d
r
ec
o
n
ciliatio
n
s
ar
e
r
em
o
v
ed
o
f
f
.
T
h
u
s
,
th
e
tr
an
s
ac
tio
n
s
ap
p
r
o
v
al
last
s
s
ec
o
n
d
s
to
b
e
d
o
n
e.
−
I
m
m
u
tab
ilit
y
an
d
s
ec
u
r
ity
:
All
u
s
er
s
ar
e
r
eq
u
ir
ed
to
af
f
o
r
d
d
ata
-
ac
cu
r
ac
y
an
d
all
v
alid
ate
d
tr
an
s
ac
tio
n
s
ar
e
im
m
u
tab
le
as
th
ey
ar
e
s
to
r
ed
en
d
u
r
in
g
ly
.
Neith
er
a
m
o
d
if
icatio
n
n
o
r
a
d
eletio
n
o
f
a
t
r
an
s
ac
tio
n
ca
n
o
cc
u
r
-
e
v
en
b
y
a
s
y
s
tem
ad
m
in
is
tr
ato
r
.
E
ac
h
b
lo
c
k
o
f
in
f
o
r
m
atio
n
r
u
n
s
o
n
a
h
ash
v
alu
e
.
T
h
e
latter
is
m
ad
e
-
u
p
o
f
a
s
et
o
f
alp
h
an
u
m
er
ic
ch
ar
a
cter
s
g
en
er
ated
b
y
ev
er
y
s
in
g
le
b
lo
ck
.
E
ac
h
b
l
o
ck
in
clu
d
es
a
h
ash
f
o
r
its
elf
an
d
a
h
ash
o
f
th
e
p
r
ec
e
d
en
t
b
lo
c
k
.
Mo
r
eo
v
e
r
,
ea
ch
ch
ai
n
o
f
b
lo
ck
s
is
d
u
p
l
icate
d
o
n
all
k
n
o
ts
.
T
h
is
f
ea
tu
r
e
m
ak
es
B
lo
ck
ch
ain
tech
n
o
lo
g
y
s
o
lid
a
n
d
en
s
u
r
es
s
af
ety
;
th
at
n
o
o
n
e
ca
n
al
ter
th
e
d
ata
s
to
r
ed
in
th
e
b
lo
ck
.
2
.
4
.
Wea
k
nes
s
es o
f
b
lo
ck
cha
i
n
Fo
r
ad
o
p
tin
g
B
lo
ck
ch
ain
,
it
is
ess
en
tial
to
co
m
p
r
e
h
en
d
p
r
o
f
o
u
n
d
ly
its
wo
r
k
in
g
m
o
d
e,
co
n
s
i
d
er
in
g
its
p
o
ten
tials
an
d
wea
k
n
ess
es.
All
s
cien
tis
t
s
an
d
we
ad
m
it
th
at
n
o
s
y
s
tem
is
p
u
r
ely
p
e
r
f
ec
t.
T
h
at
is
wh
y
;
we
s
h
o
u
ld
r
ec
o
g
n
ize
th
e
b
ar
r
ier
s
m
ig
h
t
ap
p
ea
r
b
ef
o
r
e
u
s
in
g
th
i
s
ar
ch
itectu
r
e.
T
h
e
co
n
s
id
er
atio
n
s
we
em
p
h
asize
ac
co
r
d
in
g
l
y
ar
e
[
2
4
]
:
−
Scalab
ilit
y
:
Pace
o
f
tr
an
s
ac
tio
n
s
in
th
is
t
ec
h
n
o
lo
g
y
is
u
s
u
ally
in
s
tab
le.
I
t
r
ef
er
s
to
th
e
d
im
en
s
io
n
o
f
th
e
n
etwo
r
k
; in
o
th
er
wo
r
d
s
,
th
e
m
o
r
e
u
s
er
s
(
n
o
d
es)
ar
e
e
n
g
ag
e
d
,
th
e
s
lo
wer
th
e
p
r
o
ce
d
u
r
e
g
e
ts
.
−
Hig
h
-
en
er
g
y
co
n
s
u
m
p
tio
n
:
A
ll
th
e
ac
tu
al
B
lo
ck
ch
ain
-
b
ased
clu
es,
as
B
itco
in
an
d
E
th
er
eu
m
em
p
lo
y
Po
W
p
r
o
to
co
l
to
g
et
an
d
v
alid
ate
tr
an
s
ac
tio
n
s
,
th
e
m
atter
th
at
n
ee
d
s
ex
ce
s
s
iv
e
en
er
g
y
f
o
r
co
m
p
u
tin
g
.
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
Ma
r
r
yin
g
d
ee
p
lea
r
n
in
g
w
ith
i
n
b
lo
ck
ch
a
in
tech
n
o
lo
g
y
fo
r
cred
it c
a
r
d
fr
a
u
d
p
r
ev
en
tio
n
(
I
m
a
n
e
K
a
r
ka
b
a
)
1989
Fees
in
cr
ea
s
e
s
in
ce
r
eso
u
r
ce
s
ar
e
m
an
d
ato
r
y
to
r
ef
r
esh
th
e
h
ar
d
war
e.
T
h
u
s
,
if
Po
W
r
em
ain
s
th
e
o
n
ly
av
ailab
le
o
p
tio
n
,
we
n
ee
d
to
p
ay
with
en
er
g
y
c
o
s
ts
.
Ho
wev
er
,
in
th
e
n
ex
t
v
e
r
s
io
n
o
f
E
t
h
er
eu
m
,
Po
S
is
m
o
r
e
lik
ely
to
b
e
u
s
ed
.
−
Acc
ess
to
o
f
f
-
ch
ain
d
ata:
T
h
e
r
ec
o
r
d
e
d
s
m
ar
t
co
n
tr
ac
ts
o
n
B
lo
ck
ch
ain
e
x
p
lo
it
ju
s
t
th
e
lo
ca
l
d
ata
(
d
ata
o
n
th
e
ch
ain
)
.
I
t
o
n
ly
attain
s
ac
c
ess
to
th
e
ex
ec
u
ted
tr
an
s
ac
tio
n
s
an
d
th
e
ac
co
u
n
t'
s
b
a
lan
ce
.
As
a
r
esu
lt,
to
r
ec
o
v
er
d
ata
f
r
o
m
r
ea
lity
s
tay
s
an
im
p
o
s
s
ib
le
task
.
2
.
5
.
Cha
inl
ink
B
ec
au
s
e
o
f
th
e
wea
k
-
s
p
o
ts
in
v
o
lv
ed
with
in
th
e
tec
h
n
o
lo
g
y
o
f
B
lo
ck
ch
ain
as
cited
an
tece
d
en
tly
,
we
s
u
g
g
est
-
in
o
u
r
wo
r
k
-
'
C
h
ain
lin
k
'
[
2
5
]
wh
ich
p
u
r
p
o
s
es
to
t
r
ig
g
er
a
g
lo
b
al
n
etwo
r
k
o
f
co
m
p
u
ter
s
in
o
r
d
er
t
o
af
f
o
r
d
a
u
th
en
ti
c
d
ata
f
r
o
m
r
e
ality
to
s
m
ar
t
co
n
tr
ac
t
s
tr
ea
m
in
g
o
n
th
e
u
p
p
er
m
o
s
t
ar
ea
o
f
B
lo
ck
ch
ain
s
y
s
tem
[
2
6
]
,
as c
lar
if
ie
d
in
Fg
u
r
e
3
.
Fig
u
r
e
3
.
C
h
ain
lin
k
to
af
f
o
r
d
o
f
f
-
ch
ain
d
ata
2
.
5
.
1
.
Sm
a
rt
co
ntr
a
ct
s
a
nd
o
n
-
t
he
cha
in da
t
a
Sm
ar
t
co
n
tr
ac
ts
ca
n
n
o
t
en
g
a
g
e
in
ag
r
ee
m
e
n
ts
r
elied
o
n
d
ata
f
r
o
m
r
ea
lity
(
o
f
f
-
c
h
ain
)
.
T
h
e
th
in
g
wh
ich
r
estra
in
s
s
m
ar
t
co
n
tr
a
cts
d
ep
lo
y
m
en
t.
T
h
is
d
ef
ea
t
s
tim
u
lates
'Or
ac
le
'
:
an
o
p
e
r
atin
g
s
y
s
tem
th
at
f
u
n
ctio
n
s
as
an
o
v
er
p
ass
lettin
g
a
d
o
u
b
le
-
m
an
n
e
r
tr
an
s
m
i
s
s
io
n
o
f
d
ata
b
etwe
en
s
m
ar
t
co
n
tr
ac
ts
an
d
th
e
co
n
cr
ete
wo
r
l
d
.
T
h
u
s
,
it
is
th
e
Or
ac
le
th
at
allo
ws
u
s
to
s
u
r
m
o
u
n
t
th
e
is
s
u
e
o
f
g
ettin
g
o
u
ter
d
ata
in
a
p
atter
n
o
n
th
e
ch
ain
.
W
e
c
a
n
c
o
n
s
i
d
e
r
ce
n
t
r
a
l
iz
e
d
Or
a
c
l
e
s
a
s
a
l
o
o
p
h
o
l
e
t
h
a
t
d
e
c
r
e
as
e
s
t
h
e
a
d
v
a
n
t
a
g
es
o
f
s
m
a
r
t
c
o
n
t
r
a
c
t
s
.
S
o
,
t
h
e
y
c
a
n
n
o
t
b
e
t
r
u
s
te
d
.
C
o
n
s
e
q
u
e
n
t
l
y
,
C
h
ai
n
l
i
n
k
h
as
c
o
m
e
t
o
l
i
g
h
t
.
T
h
e
s
y
s
t
e
m
i
s
a
d
e
ce
n
t
r
a
li
z
e
d
n
e
tw
o
r
k
m
a
d
e
u
p
o
f
O
r
a
c
l
e
s
w
h
o
s
e
r
o
l
e
is
t
o
c
a
r
r
y
d
a
t
a
f
r
o
m
o
f
f
-
c
h
a
i
n
s
o
u
r
c
e
s
t
o
o
n
-
c
h
a
i
n
c
o
n
t
r
a
c
t
s
w
h
ic
h
a
b
o
l
i
s
h
t
r
u
s
t
w
o
r
t
h
i
n
e
s
s
is
s
u
e
t
h
a
t
c
a
n
h
a
p
p
e
n
b
y
t
h
e
t
i
m
e
o
f
u
t
i
l
iz
i
n
g
o
n
e
c
e
n
t
r
a
l
i
z
e
d
s
o
u
r
c
e
as
s
h
o
w
n
i
n
F
i
g
u
r
e
4
[
2
7
]
.
Fig
u
r
e
4
.
Dif
f
e
r
en
t c
o
m
p
o
n
en
t
s
o
f
ch
ain
lin
k
'
s
Or
ac
le
Netwo
r
k
[
2
8
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
98
5
-
1
99
8
1990
T
h
e
s
m
ar
t
co
n
tr
ac
ts
a
r
e
u
n
ab
le
to
in
te
r
ac
t
n
o
r
to
i
n
ter
co
n
n
ec
t
d
ir
ec
tly
with
t
h
e
r
ea
l
w
o
r
ld
w
h
en
o
b
tain
in
g
d
ata.
T
h
e
r
ea
s
o
n
w
h
y
a
s
m
ar
t
co
n
t
r
ac
t
is
co
n
s
id
er
ed
th
e
co
n
s
u
m
er
n
u
m
b
er
o
n
e
o
f
C
h
ain
lin
k
.
As
a
r
esu
lt,
th
e
p
r
o
ce
s
s
is
ac
h
iev
ed
v
ia
a
s
y
s
tem
wh
er
e
t
h
e
in
q
u
ir
y
f
o
r
ex
ter
n
al
d
ata
is
co
n
v
ey
e
d
th
r
o
u
g
h
tr
an
s
ac
tio
n
s
'
h
ap
p
en
in
g
.
T
h
e
r
ea
f
ter
,
an
ex
tr
in
s
ic
p
ar
ty
is
in
tim
ated
an
d
g
ath
er
s
th
e
d
em
a
n
d
ed
d
ata,
p
r
o
ce
e
d
s
it,
an
d
u
ltima
tely
tr
a
n
s
f
er
s
th
e
r
ep
ly
v
ia
th
e
ch
ain
as it is sh
o
wn
in
Fig
u
r
e
5
[
2
9
]
,
[
3
0
]
.
Fig
u
r
e
5
.
Of
f
-
ch
ain
d
ata
r
eq
u
e
s
t m
ec
h
an
is
m
A
g
ain
,
wh
en
a
s
m
ar
t
co
n
tr
ac
t
r
eq
u
ests
d
ata
b
y
em
itti
n
g
a
t
r
an
s
ac
tio
n
ev
en
t,
th
e
C
h
ain
lin
k
p
r
o
to
c
o
l
r
ec
o
r
d
s
th
is
ev
en
t
a
n
d
c
r
ea
tes
an
s
er
v
ice
lev
el
ag
r
ee
m
en
t
(
S
L
A
)
.
T
h
e
SLA
g
e
n
er
ates
th
r
ee
s
u
b
co
n
tr
ac
ts
:
(
1
)
a
C
h
ain
lin
k
C
o
n
tr
ac
t
R
ep
u
tatio
n
,
wh
o
s
e
f
u
n
ctio
n
is
to
ch
ec
k
th
e
tr
ac
k
in
g
wa
y
(
h
is
to
r
y
)
o
f
an
Or
ac
le
p
r
o
v
id
er
,
to
d
eter
m
in
e
ac
cu
r
ac
y
an
d
p
e
r
f
o
r
m
a
n
ce
,
th
en
to
ev
alu
ate
a
n
d
ex
clu
d
e
less
r
eliab
le
n
o
d
es.
(
2
)
T
h
e
C
h
ain
lin
k
Or
d
er
Ma
tch
in
g
C
o
n
tr
ac
t,
wh
er
eb
y
th
e
n
o
d
es
r
etr
iev
e
th
e
r
eq
u
est
p
r
o
v
id
e
d
b
y
th
e
p
r
ec
u
r
s
o
r
co
n
tr
ac
t
(
th
e
R
ep
u
tatio
n
C
o
n
tr
ac
t)
,
s
elec
ts
t
h
e
n
u
m
b
e
r
an
d
ty
p
e
o
f
n
o
d
es th
at
ar
e
n
ec
ess
ar
y
to
m
ee
t th
e
r
eq
u
est.
Fin
ally
,
(
3
)
C
h
ain
lin
k
Ag
g
r
eg
atio
n
C
o
n
tr
ac
t
wh
ich
co
r
r
ec
ts
in
ac
cu
r
ate
d
ata.
I
t
tak
es
all
th
e
d
ata
s
ele
cted
b
y
th
e
Or
ac
les
an
d
ap
p
r
o
v
es o
r
r
ec
o
n
ciles th
em
to
o
b
tain
a
p
r
ec
is
e
r
esu
lt,
as
Fig
u
r
e
6
s
h
o
ws
.
Fig
u
r
e
6
.
C
h
ain
lin
k
s
m
ar
t c
o
n
t
r
ac
ts
T
h
e
ac
tiv
atio
n
o
f
C
h
ain
lin
k
s
m
o
o
th
s
th
e
p
ath
f
o
r
E
t
h
er
eu
m
to
e
x
p
lo
it
v
ar
io
u
s
o
f
f
-
c
h
ain
d
ata
.
R
ef
er
r
in
g
t
o
its
s
y
s
tem
atic
ess
en
ce
-
h
er
e
-
we
will
b
en
e
f
it
f
r
o
m
B
lo
ck
c
h
ain
,
s
p
ec
if
ically
th
e
E
th
er
eu
m
n
etwo
r
k
,
to
b
an
cr
e
d
it
ca
r
d
f
r
au
d
m
er
g
in
g
th
is
th
o
r
o
u
g
h
g
o
i
n
g
tech
n
o
lo
g
y
with
d
ee
p
lear
n
in
g
as
a
d
etec
tin
g
to
o
l.
T
h
e
n
e
x
t
s
ec
tio
n
r
e
p
r
ese
n
ts
a
s
tag
e
wh
er
e
we
o
v
er
co
m
e
all
th
e
c
h
allen
g
es
c
o
n
f
r
o
n
ted
an
d
d
is
co
v
er
th
e
clu
es to
r
ea
ch
th
e
i
n
ten
d
ed
aim
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
Ma
r
r
yin
g
d
ee
p
lea
r
n
in
g
w
ith
i
n
b
lo
ck
ch
a
in
tech
n
o
lo
g
y
fo
r
cred
it c
a
r
d
fr
a
u
d
p
r
ev
en
tio
n
(
I
m
a
n
e
K
a
r
ka
b
a
)
1991
3.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
is
d
ev
o
ted
to
clar
if
y
th
e
way
we
d
ep
lo
y
d
ee
p
l
ea
r
n
in
g
in
B
lo
ck
ch
ain
f
o
r
d
et
ec
tin
g
an
d
p
r
ev
en
tin
g
cr
ed
it
ca
r
d
f
r
a
u
d
t
r
an
s
ac
tio
n
s
,
m
ak
in
g
t
h
e
s
tr
u
ct
u
r
e
o
f
o
u
r
s
u
g
g
ested
ec
o
s
y
s
tem
cr
y
s
tal
-
clea
r
,
as
Fig
u
r
e
7
d
em
o
n
s
tr
ates.
So
,
af
ter
b
u
ild
in
g
a
m
o
d
e
l
u
s
in
g
Au
to
en
co
d
er
t
o
d
etec
t
f
r
au
d
u
len
t
tr
an
s
ac
tio
n
s
,
B
lo
ck
ch
ain
is
ap
p
lied
to
s
u
b
s
titu
te
th
e
q
u
in
tess
en
tial
d
atab
ase,
o
n
g
r
o
u
n
d
s
o
f
d
u
r
ab
ilit
y
th
at
d
escr
ib
es
it
wh
ich
-
in
tu
r
n
-
e
n
h
an
ce
s
b
an
n
in
g
o
th
er
ty
p
es
o
f
f
r
au
d
lin
k
ed
to
th
e
ch
an
g
e
an
d
co
r
r
u
p
ti
o
n
o
f
th
e
r
ec
o
r
d
ed
d
ata
.
T
h
e
wh
o
le
co
d
e
is
tr
an
s
cr
ib
ed
in
t
h
e
s
m
ar
t
co
n
tr
ac
t,
an
d
th
is
is
th
e
p
o
in
t
wh
en
th
e
ad
v
an
tag
e
o
f
th
e
d
ep
lo
y
e
d
DL
M
is
p
r
o
f
ited
.
Yet,
th
e
s
m
ar
t
co
n
tr
ac
t'
s
i
n
ab
ilit
y
to
o
b
tain
o
f
f
-
ch
ain
d
ata
p
r
o
v
o
k
es
th
e
in
ter
v
en
tio
n
o
f
C
h
ain
lin
k
to
g
et
th
e
o
f
f
-
ch
ai
n
d
ata
in
to
th
e
c
h
ain
,
p
er
m
itti
n
g
t
h
e
c
o
n
s
u
m
p
t
io
n
o
f
o
u
r
m
o
d
el
in
B
lo
ck
ch
ain
.
Ou
r
p
r
in
cip
al
g
o
al
in
th
is
s
ec
tio
n
is
to
s
p
o
tli
g
h
t
th
e
s
ec
o
n
d
h
alf
o
f
th
e
d
o
u
b
le
-
k
e
y
m
et
h
o
d
im
p
lem
en
ted
;
in
o
t
h
er
wo
r
d
s
,
we
f
o
ca
lized
s
y
s
tem
atica
lly
o
n
B
lo
ck
ch
ain
tech
n
o
lo
g
y
an
d
th
e
m
ec
h
a
n
is
m
s
it
in
v
o
lv
es.
W
h
er
ea
s
,
th
e
DL
M
p
ar
t
was
b
r
ief
ly
d
escr
ib
ed
s
in
ce
it
was
alr
ea
d
y
f
o
r
g
ed
i
n
o
u
r
p
r
ev
io
u
s
s
tu
d
y
[
6
]
th
r
o
u
g
h
a
s
eq
u
en
ce
o
f
p
r
o
ce
d
u
r
es
wh
er
e
a
b
u
n
ch
o
f
tech
n
i
q
u
es
ca
m
e
in
to
p
lay
.
Af
ter
th
at
-
in
th
e
s
tu
d
y
in
y
o
u
r
h
an
d
s
-
t
h
e
DL
M
was e
x
p
lo
ited
in
B
lo
ck
ch
ain
tec
h
n
o
lo
g
y
to
p
la
y
a
r
o
le
o
f
a
d
etec
to
r
.
Fig
u
r
e
7
.
A
r
c
h
itectu
r
e
o
f
th
e
s
y
s
tem
f
u
s
in
g
B
lo
ck
ch
ain
with
DL
M
3
.
1
.
Dee
p lea
rning
mo
del
T
h
e
r
ea
s
o
n
wh
y
we
h
a
v
e
p
ick
ed
th
e
Au
to
en
co
d
er
m
o
d
el
f
o
r
d
etec
tin
g
f
r
au
d
u
len
t
tr
an
s
ac
ti
o
n
s
s
tem
s
f
r
o
m
th
e
f
in
d
in
g
s
o
f
a
p
r
e
v
io
u
s
wo
r
k
o
f
o
u
r
s
wh
er
e
we
h
av
e
co
n
d
u
cte
d
a
co
m
p
ar
is
o
n
s
tu
d
y
co
n
ce
r
n
ed
th
e
alg
o
r
ith
m
s
:
ANN,
C
NN,
an
d
Au
to
en
co
d
er
[
6
]
,
tak
in
g
in
to
ac
co
u
n
t
'
p
r
ec
is
io
n
'
,
'
r
ec
all
'
,
an
d
'
ac
cu
r
ac
y
'
a
s
m
etr
ics
o
f
ef
f
icien
cy
m
ea
s
u
r
e
m
en
t.
T
h
is
s
tu
d
y
was
co
n
d
u
cted
o
n
a
d
ataset
(
attain
ed
f
r
o
m
Kag
g
le)
o
f
2
8
4
,
8
0
7
tr
an
s
ac
tio
n
s
,
ju
s
t
4
9
2
o
f
wh
i
ch
wer
e
d
escr
ib
ed
as
m
alicio
u
s
.
T
h
e
m
atter
th
at
m
a
d
e
u
s
en
co
u
n
ter
th
e
f
ir
s
t
ch
allen
g
e
r
elate
d
to
t
h
e
im
b
a
lan
ce
d
d
ata.
Au
to
e
n
co
d
e
r
wo
n
o
v
er
t
h
e
o
th
er
al
g
o
r
ith
m
s
i
n
d
ea
lin
g
with
th
e
p
r
esen
t
d
ataset.
I
t
is
r
elea
s
ed
th
at
th
r
ee
lay
er
s
o
f
en
c
o
d
in
g
ar
e
th
e
o
p
tim
al
p
a
r
am
eter
s
n
o
tic
ed
af
ter
tu
n
in
g
th
e
h
y
p
er
-
p
ar
am
eter
s
: T
an
h
as th
e
ac
tiv
atio
n
f
u
n
ctio
n
alo
n
g
th
e
h
id
d
en
la
y
er
s
an
d
Sig
m
o
id
in
t
h
e
o
u
tp
u
t la
y
er
.
3
.
1
.
1
.
Da
t
a
s
et
des
cr
iptio
n
T
h
e
d
ataset
ex
e
r
ted
in
th
is
w
o
r
k
is
a
E
u
r
o
p
e
cr
ed
it
ca
r
d
d
ataset,
r
ep
r
esen
tin
g
an
im
b
ala
n
ce
d
r
ea
l
-
wo
r
ld
o
n
e.
I
t
in
cl
u
d
es
cr
e
d
it
ca
r
d
tr
an
s
ac
tio
n
s
m
a
d
e
b
y
E
u
r
o
p
ea
n
ca
r
d
h
o
ld
er
s
in
Sep
tem
b
er
2
0
1
3
.
T
h
is
d
ataset
in
tr
o
d
u
ce
s
all
tr
an
s
ac
tio
n
s
o
cc
u
r
r
in
g
o
v
e
r
two
d
ay
s
,
with
4
9
2
in
s
tan
ce
s
o
f
f
r
au
d
id
en
tifie
d
o
u
t
o
f
2
8
4
,
8
0
7
tr
a
n
s
ac
tio
n
s
.
I
t
o
b
v
io
u
s
ly
s
h
o
ws
a
h
ig
h
ly
im
b
alan
c
ed
d
ata,
with
f
r
au
d
u
len
t
tr
an
s
ac
tio
n
s
ac
co
u
n
tin
g
f
o
r
n
ea
r
ly
0
.
1
7
2
% o
f
all
tr
an
s
a
ctio
n
s
.
T
h
e
d
ataset
co
n
tain
s
o
n
ly
n
u
m
er
ical
i
n
p
u
t
v
ar
iab
les wh
ich
ar
e
th
e
r
esu
lt
o
f
a
PC
A
tr
an
s
f
o
r
m
atio
n
d
u
e
to
co
n
f
id
en
tiality
co
n
ce
r
n
s
.
C
o
n
s
eq
u
en
tly
,
p
r
o
v
id
in
g
th
e
o
r
ig
in
al
f
ea
tu
r
es
o
r
m
o
r
e
b
ac
k
g
r
o
u
n
d
in
f
o
r
m
atio
n
is
n
o
t
f
ea
s
ib
le.
T
h
e
f
ea
tu
r
es
ar
e
3
0
p
r
in
cip
al
co
m
p
o
n
en
ts
as
d
etailed
d
escr
ib
ed
in
[
3
1
]
.
3
.
1
.
2
.
Select
ed
a
lg
o
rit
hm
T
h
e
Au
to
en
co
d
er
is
a
s
u
b
s
et
o
f
n
eu
r
al
n
etwo
r
k
s
u
s
ed
to
lear
n
d
ata
en
co
d
in
g
in
an
u
n
s
u
p
er
v
is
ed
m
an
n
er
.
I
ts
p
u
r
p
o
s
e
is
to
lear
n
a
lo
wer
-
d
im
en
s
io
n
al
r
e
p
r
es
en
tatio
n
(
en
c
o
d
in
g
)
f
o
r
h
i
g
h
e
r
-
d
im
en
s
io
n
al
d
ata,
s
p
ec
if
ically
f
o
r
r
ed
u
cin
g
d
im
e
n
s
io
n
ality
,
b
y
tr
ai
n
in
g
t
h
e
n
et
wo
r
k
to
s
elec
t
th
e
m
o
s
t
cr
u
cia
l
co
m
p
o
n
en
ts
o
f
t
h
e
in
p
u
t.
I
ts
ar
ch
itectu
r
e
en
co
m
p
ass
es
s
u
cc
ess
iv
ely
th
r
ee
co
n
s
titu
en
ts
:
E
n
co
d
er
,
B
o
ttlen
ec
k
an
d
Dec
o
d
er
[
3
2
]
.
T
h
e
o
p
tio
n
f
ell
o
n
t
h
is
alg
o
r
ith
m
,
as
it
d
o
es
n
o
t
n
ee
d
a
d
ataset
m
o
d
if
icatio
n
allo
win
g
u
s
to
s
u
r
p
ass
th
e
im
b
alan
ce
d
d
ata
is
s
u
e.
3
.
2
.
B
lo
c
k
cha
in t
ec
hn
o
lo
g
y
Af
ter
th
e
s
tag
e
o
f
d
etec
tin
g
f
r
au
d
u
len
t
tr
an
s
ac
tio
n
s
u
s
in
g
t
h
e
DL
M,
c
o
m
es
th
e
s
tag
e
o
f
s
to
r
in
g
th
e
tr
an
s
ac
tio
n
s
in
th
e
d
atab
ase.
Ho
wev
er
,
we
m
ay
f
ac
e
a
n
o
th
er
ty
p
e
o
f
f
r
a
u
d
r
ep
r
esen
ted
b
y
th
e
c
o
r
r
u
p
tio
n
an
d
alter
atio
n
o
f
d
ata
af
ter
t
h
e
s
to
r
in
g
p
h
ase.
Fo
r
th
is
p
u
r
p
o
s
e,
a
d
ec
en
tr
alize
d
im
m
u
ta
b
le
d
at
ab
ase
was
ad
o
p
ted
,
n
am
ely
E
th
er
e
u
m
B
lo
ck
ch
ai
n
th
at
en
ab
les u
s
to
u
s
e
th
e
s
m
ar
t c
o
n
tr
ac
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
98
5
-
1
99
8
1992
3
.
3
.
M
ec
ha
nis
m
s
f
o
r
t
he
s
y
s
t
em
deplo
y
m
ent
3
.
3
.
1
.
Sm
a
rt
co
ntr
a
ct
a
nd
ex
t
er
na
l a
da
pte
r
T
h
e
s
m
ar
t
co
n
tr
ac
t'
s
in
ep
titu
d
e
ap
p
ea
r
s
wh
en
it
ca
n
n
o
t
b
r
in
g
o
f
f
-
c
h
ain
d
ata
(
d
ata
o
u
t
o
f
B
lo
ck
ch
ain
)
.
T
h
is
is
tr
ea
ted
as
a
s
er
io
u
s
ch
allen
g
e
p
r
e
v
en
tin
g
u
s
to
co
n
s
u
m
e
o
u
r
m
o
d
el
i
n
B
lo
ck
ch
ain
.
T
o
o
v
er
c
o
m
e
th
is
o
b
s
tacle
,
C
h
ain
lin
k
s
h
o
ws
u
p
to
p
r
o
v
i
d
e
th
e
ch
ai
n
with
d
ata
f
r
o
m
th
e
ex
ter
n
al
wo
r
ld
.
T
h
e
ex
ter
n
al
ad
ap
ter
s
f
u
n
ctio
n
as
o
n
e
API
to
d
o
p
er
p
lex
co
m
p
u
tatio
n
s
b
ec
au
s
e
ev
er
y
tr
an
s
ac
tio
n
is
p
aid
o
n
th
e
ch
ain
an
d
t
h
ey
s
er
v
e
C
h
ain
lin
k
in
ter
m
s
o
f
o
f
f
e
r
in
g
it d
ata
d
ir
ec
tly
.
Hen
ce
,
we
h
av
e
u
s
ed
o
u
r
DL
M
in
th
e
ex
ter
n
al
ad
ap
ter
s
o
th
at
it
ca
n
b
e
av
ailab
le
f
o
r
t
h
e
s
m
ar
t
co
n
tr
ac
t a
cr
o
s
s
C
h
ain
lin
k
.
3
.
3
.
2
.
Cha
inl
ink
C
h
ain
lin
k
h
er
e
p
lay
s
t
h
e
r
o
le
o
f
an
in
te
r
m
ed
iar
y
in
s
tr
u
m
e
n
t
b
etwe
en
t
h
e
ex
te
r
n
al
a
d
ap
t
er
an
d
th
e
s
m
ar
t c
o
n
tr
ac
t.
I
t
p
r
o
v
i
d
es o
f
f
-
ch
ain
d
ata
f
r
o
m
e
x
ter
n
al
s
o
u
r
c
es to
th
e
B
lo
ck
ch
ain
n
etwo
r
k
.
3
.
3
.
3
.
Webs
it
e
a
nd
cr
y
pto
curr
ency
Her
eu
p
o
n
,
th
e
s
y
s
tem
b
ec
o
m
es
ap
t
to
r
ec
o
v
er
t
r
an
s
ac
tio
n
s
f
r
o
m
s
to
r
a
g
e
a
n
d
la
b
el
th
em
with
p
r
ed
ictio
n
s
d
o
n
e
b
y
th
e
m
o
d
el.
Af
ter
t
h
at,
it
s
to
r
es
tr
an
s
ac
tio
n
s
an
d
th
eir
co
r
r
esp
o
n
d
i
n
g
p
r
ed
ictio
n
s
o
n
B
lo
ck
ch
ain
in
an
in
alter
ab
le
m
o
d
e.
So
as
to
ju
s
tify
th
e
p
r
a
ctica
lity
o
f
th
is
m
er
g
er
,
a
we
b
s
ite
was
d
ev
elo
p
ed
an
d
co
n
n
ec
ted
to
B
lo
ck
ch
ain
ex
p
lo
itin
g
web
3
.
js
in
o
r
d
er
to
lin
k
th
e
B
lo
ck
ch
ai
n
with
th
e
Me
tam
ask
wallet
[
3
3
]
to
ef
f
ec
t
tr
an
s
ac
tio
n
s
o
n
t
h
e
ch
ain
.
T
h
is
web
s
ite
will
b
e
d
ev
o
ted
t
o
a
co
u
p
le
o
f
u
s
er
s
.
T
h
e
f
ir
s
t
u
s
er
,
a
f
ter
h
is
wallet
d
etec
tio
n
,
all
tr
a
n
s
ac
tio
n
s
h
e
h
as
ex
ec
u
ted
ar
e
ex
p
o
s
ed
to
v
iew
an
d
h
e
o
wn
s
ac
c
ess
to
ex
ec
u
te
m
o
r
e
t
r
an
s
ac
tio
n
s
as
well
as
h
e
ca
n
s
ee
th
eir
p
r
ed
ictio
n
s
b
y
p
a
y
in
g
with
E
T
H
cr
y
p
to
cu
r
r
en
cy
.
I
n
p
ar
allel,
t
h
e
s
ec
o
n
d
u
s
er
is
th
e
o
n
e
wh
o
o
wn
s
th
e
s
m
ar
t
c
o
n
tr
ac
t
-
wh
o
h
as
also
u
s
ed
it.
He
ca
n
ex
a
m
in
e
th
e
b
alan
ce
th
e
s
m
ar
t c
o
n
tr
ac
t sto
r
ed
a
f
ter
ev
e
r
y
p
r
e
d
ictio
n
an
d
h
e
ca
n
with
d
r
aw
th
e
b
alan
ce
to
h
is
wallet,
as we
ll.
4.
VIS
UA
L
I
Z
A
T
I
O
N
So
th
at
we
co
u
ld
m
ar
r
y
th
e
AI
m
o
d
el
with
in
B
lo
ck
c
h
ai
n
tech
n
o
l
o
g
y
,
we
d
esig
n
ed
a
web
u
s
er
in
ter
f
ac
e
th
at
ap
p
lies
all
th
e
p
r
ev
io
u
s
ly
in
d
icate
d
attr
i
b
u
tes.
T
h
is
web
ap
p
co
n
tain
s
th
e
f
o
ll
o
win
g
elem
en
ts
:
−
A
b
u
tto
n
allo
win
g
th
e
u
s
er
t
o
co
n
n
ec
t h
is
wallet.
−
A
s
ec
tio
n
d
ed
icate
d
to
th
e
d
is
p
lay
o
f
p
r
ev
i
o
u
s
tr
an
s
ac
tio
n
s
p
er
f
o
r
m
e
d
b
ased
o
n
th
e
c
o
n
n
ec
t
ed
wallet.
−
A
f
o
r
m
to
e
n
ter
th
e
attr
i
b
u
tes o
f
th
e
tr
a
n
s
ac
tio
n
in
o
r
d
er
to
m
ak
e
a
p
r
e
d
ictio
n
.
−
A
s
ec
tio
n
d
ed
icate
d
to
th
e
o
wn
er
o
f
th
e
s
m
ar
t
co
n
tr
ac
t
f
o
r
with
d
r
awin
g
th
e
co
n
tr
ac
t'
s
b
alan
ce
.
T
h
e
two
f
ig
u
r
es:
Fig
u
r
es 8
a
n
d
9
s
h
o
w
th
e
p
r
im
ar
y
g
r
a
p
h
ical
u
s
er
in
te
r
f
ac
e
b
ef
o
r
e
a
wallet
is
co
n
n
ec
ted
.
Fig
u
r
e
8
.
Ma
in
u
s
er
in
ter
f
ac
e
b
ef
o
r
e
a
wallet
co
n
n
ec
tio
n
(
a)
Fig
u
r
e
9
.
Ma
in
u
s
er
in
ter
f
ac
e
b
ef
o
r
e
a
wallet
co
n
n
ec
t
io
n
(
b
)
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
Ma
r
r
yin
g
d
ee
p
lea
r
n
in
g
w
ith
i
n
b
lo
ck
ch
a
in
tech
n
o
lo
g
y
fo
r
cred
it c
a
r
d
fr
a
u
d
p
r
ev
en
tio
n
(
I
m
a
n
e
K
a
r
ka
b
a
)
1993
4
.
1
.
Reg
ula
r
us
er
A
r
eg
u
lar
u
s
er
(
a
n
o
r
m
al
u
s
er
)
co
u
l
d
lo
g
i
n
b
y
click
in
g
o
n
th
e
"Co
n
n
ec
t"
b
u
tto
n
as
s
h
o
wn
in
Fig
u
r
es
1
0
an
d
11
an
d
th
e
ap
p
licatio
n
will
au
to
m
atica
lly
d
etec
t
th
e
co
n
n
ec
ted
wallet
an
d
th
e
wallet
ad
d
r
ess
will
b
e
d
i
s
p
l
a
y
e
d
a
l
o
n
g
w
i
t
h
t
h
e
r
e
c
o
r
d
s
o
f
t
h
e
p
r
e
v
i
o
u
s
t
r
a
n
s
a
c
t
i
o
n
s
m
a
d
e
b
y
t
h
e
c
u
r
r
e
n
t
a
c
c
o
u
n
t
a
s
s
h
o
w
n
i
n
F
i
g
u
r
e
1
2
.
Fig
u
r
e
10
.
W
allet
co
n
n
ec
tio
n
Fig
u
r
e
11
.
Ma
in
u
s
er
in
ter
f
ac
e
af
ter
a
clien
t w
allet
co
n
n
ec
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
3
,
Ma
r
ch
20
25
:
1
98
5
-
1
99
8
1994
Fig
u
r
e
12
.
T
r
an
s
ac
tio
n
attr
ib
u
t
es f
o
r
m
Her
ea
f
ter
,
b
y
click
i
n
g
o
n
th
e
"
m
ak
e
a
p
r
e
d
ictio
n
"
b
u
tto
n
,
th
e
u
s
er
ca
n
m
ak
e
a
p
r
ed
ictio
n
as
s
h
o
wn
in
Fig
u
r
e
1
1
.
T
h
en
,
a
f
o
r
m
is
d
i
s
p
lay
ed
r
eq
u
esti
n
g
th
e
i
n
p
u
t
o
f
th
e
tr
an
s
ac
tio
n
attr
ib
u
tes
(
Fig
u
r
es
1
3
an
d
14
)
.
Ultim
ately
,
th
e
d
em
an
d
is
p
r
o
ce
ed
ed
an
d
th
e
tr
a
n
s
ac
tio
n
'
s
p
r
ed
ictio
n
is
g
en
er
ated
an
d
d
is
p
lay
ed
as
s
h
o
wn
in
Fig
u
r
e
1
5
.
Fig
u
r
e
13
.
Pre
d
ictin
g
tr
a
n
s
ac
tio
n
s
Fig
u
r
e
14
.
Pre
d
ictio
n
p
ay
m
en
t
Fig
u
r
e
15
.
Pre
d
ictio
n
r
esu
lt
Evaluation Warning : The document was created with Spire.PDF for Python.