I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
10
,
No
.
2
,
May
201
8
,
p
p
.
7
7
8
~7
8
5
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
0
.
i2
.
p
p
778
-
7
8
5
778
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Selective
Co
llig
a
tion a
nd Selec
tive
Scra
m
bl
ing
for
P
riv
a
cy
Preserva
tion
in
D
a
ta M
ining
I
s
hw
a
ry
a
M
.
V
1
,
K
.
Ra
m
esh
K
u
m
a
r
2
1
H
in
d
u
sth
a
n
In
st
it
u
te
o
f
T
e
c
h
n
o
lo
g
y
a
n
d
S
c
ien
c
e
,
P
a
d
u
r
1
CS
E
De
p
t
,
S
ri
S
a
iRam
En
g
in
e
e
rin
g
Co
ll
e
g
e
T
a
m
b
a
ra
m
,
Ch
e
n
n
a
i,
T
a
m
il
N
a
d
u
,
In
d
ia
2
De
p
a
rtm
e
n
t
o
f
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
, H
in
d
u
sth
a
n
In
stit
u
te o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
ien
c
e
,
P
a
d
u
r
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
2
5
,
2
0
1
7
R
ev
i
s
ed
J
an
1
2
,
2
0
1
8
A
cc
ep
ted
F
eb
2
1
,
2
0
1
8
T
h
e
w
o
rk
is
to
e
n
h
a
n
c
e
th
e
ti
m
e
e
ff
icie
n
c
y
in
re
tri
e
v
in
g
th
e
d
a
ta
f
ro
m
e
n
o
rm
o
u
s
b
a
n
k
d
a
tab
a
se
.
T
h
e
m
a
jo
r
d
ra
w
b
a
c
k
in
re
tri
e
v
in
g
d
a
ta
f
ro
m
larg
e
d
a
tab
a
se
s
is
ti
m
e
d
e
la
y
.
T
h
is
ti
m
e
h
in
d
ra
n
c
e
is
o
w
e
d
a
s
th
e
a
lrea
d
y
e
x
isti
n
g
m
e
th
o
d
(
S
VM),
A
b
stra
c
t
Da
ta
Ty
p
e
(
A
D
T
)
tree
p
u
rsu
e
s
so
m
e
e
lo
n
g
a
ted
S
e
q
u
e
n
t
ial
ste
p
s.
T
h
e
se
tec
h
n
iq
u
e
s
tak
e
s
a
d
d
it
io
n
a
l
siz
e
a
n
d
w
it
h
a
re
d
u
c
ti
o
n
o
f
sp
e
e
d
in
train
in
g
a
n
d
tes
ti
n
g
.
A
n
o
th
e
r
m
a
jo
r
n
e
g
a
ti
v
e
a
sp
e
c
t
o
f
th
e
s
e
tec
h
n
iq
u
e
s
is
it
s
A
lg
o
rit
h
m
i
c
c
o
m
p
lex
it
y
.
T
h
e
c
l
a
ss
i
f
ica
ti
o
n
a
lg
o
rit
h
m
s
h
a
v
e
f
iv
e
c
a
teg
o
ries
.
T
h
e
y
a
re
ID3
,
k
-
n
e
a
re
st
n
e
ig
h
b
o
u
r,
De
c
isio
n
tree
,
A
NN
,
a
n
d
Na
ïv
e
B
a
y
e
s
a
lg
o
rit
h
m
.
T
o
tri
u
m
p
h
o
v
e
r
th
e
d
ra
w
b
a
c
k
s
in
S
V
M
t
e
c
h
n
iq
u
e
s,
w
e
w
o
rn
a
tec
h
n
iq
u
e
c
a
ll
e
d
Na
ïv
e
Ba
y
e
s
Clas
si
f
ica
ti
o
n
(NBC)
A
l
g
o
rit
h
m
th
a
t
w
o
rk
s
in
p
a
ra
ll
e
l
m
a
n
n
e
r
ra
th
e
r
th
a
n
se
q
u
e
n
ti
a
l
m
a
n
n
e
r.
F
o
r
f
u
rth
e
r
e
n
h
a
n
c
e
m
e
n
t
we
c
o
m
m
e
n
c
e
d
a
Na
ïv
e
Ba
y
e
s
u
p
d
a
tab
le
a
lg
o
rit
h
m
w
h
ich
is
th
e
a
d
v
a
n
c
e
d
v
e
r
sio
n
o
f
Na
ïv
e
Ba
y
e
s
c
l
a
ss
i
f
ica
ti
o
n
a
lg
o
rit
h
m
.
T
h
u
s
th
e
p
ro
p
o
se
d
tec
h
n
i
q
u
e
Na
ïv
e
b
a
y
e
s
a
lg
o
rit
h
m
e
n
su
re
s
th
a
t
m
in
e
r
c
a
n
m
in
e
m
o
re
e
ff
ici
e
n
tl
y
f
ro
m
th
e
e
n
o
rm
o
u
s d
a
t
a
b
a
se
.
K
ey
w
o
r
d
s
:
A
N
N
B
ay
e
s
ian
Alg
o
r
it
h
m
Data
Min
i
n
g
P
r
iv
ac
y
P
r
eser
v
atio
n
SVM
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
I
s
h
w
ar
y
a
M.
V,
Hin
d
u
s
t
h
an
I
n
s
tit
u
te
o
f
T
ec
h
n
o
lo
g
y
an
d
Scie
n
ce
,
P
ad
u
r
,
C
SE
Dep
t,
Sri
Sai
R
a
m
E
n
g
in
e
er
in
g
C
o
lleg
e,
T
am
b
ar
a
m
,
C
h
e
n
n
ai,
T
a
m
ilNa
d
u
,
I
n
d
ia
E
m
ail: i
s
h
w
ar
y
a.
cse
@
s
air
a
m
.
ed
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
e
x
is
tin
g
s
y
s
te
m
,
i
t
w
o
r
k
s
i
n
a
ch
r
o
n
o
lo
g
ical
p
r
o
g
r
ess
io
n
.
I
t
w
i
ll
en
s
u
r
e
o
n
l
y
o
n
e
p
r
o
ce
s
s
at
a
ti
m
e
eit
h
er
co
m
p
ar
is
o
n
o
r
cla
s
s
i
f
icatio
n
an
d
ex
tr
ac
tio
n
o
r
p
r
ed
ictio
n
.
So
it
tak
es
ad
d
itio
n
al
ti
m
e
to
r
elay
t
h
e
r
eg
r
ess
io
n
.
T
h
e
f
o
r
e
m
o
s
t
p
h
a
s
e
o
f
Su
p
p
o
r
t
V
ec
to
r
Ma
ch
in
e
alg
o
r
ith
m
is
to
class
i
f
y
th
e
r
elev
an
t
d
ata
a
n
d
ir
r
elev
an
t
d
ata
f
r
o
m
t
h
e
u
n
s
tr
u
ctu
r
ed
m
as
s
i
v
e
d
atab
ase.
T
h
en
,
it
co
m
p
ar
es
t
h
e
g
i
v
en
q
u
e
r
y
w
it
h
t
h
e
r
ele
v
a
n
t
d
ata.
Af
ter
ca
r
r
y
in
g
o
u
t
th
e
co
m
p
ar
is
o
n
p
r
o
ce
d
u
r
e
t
h
en
it
ten
d
s
to
p
r
ec
ed
e
t
h
e
e
x
tr
ac
t
i
o
n
p
r
o
ce
s
s
.
I
n
t
h
e
ex
tr
ac
tio
n
p
r
o
g
r
ess
io
n
,
it
r
etr
iev
es
th
e
r
eq
u
ested
d
ata
w
h
ic
h
is
g
i
v
e
n
b
y
t
h
e
u
s
er
.
Su
b
s
eq
u
en
tl
y
,
it
p
r
o
ce
ed
s
to
co
m
p
lete
t
h
e
p
r
ed
ictio
n
p
r
o
ce
s
s
b
y
r
ati
n
g
.
I
t
ta
k
es
ad
d
itio
n
al
s
ize
an
d
ad
d
itio
n
al
ti
m
e
to
co
m
p
u
te.
As
i
n
th
e
ex
is
t
in
g
s
y
s
te
m
t
h
e
p
r
o
ce
s
s
wo
u
ld
b
e
in
s
eq
u
e
n
tial o
r
d
er
,
lead
s
to
in
cr
ea
s
e
in
ti
m
e
a
n
d
in
c
r
ea
s
e
in
m
e
m
o
r
y
.
Yan
g
et
al.
[
1
]
ex
p
r
ess
ed
d
esig
n
m
ec
h
a
n
i
s
m
s
,
w
h
e
n
g
i
v
e
n
a
p
r
ef
er
en
ce
p
r
o
f
ile
s
u
b
m
itte
d
b
y
a
u
s
er
th
at
s
ea
r
ch
a
p
er
s
o
n
w
it
h
m
atc
h
in
g
p
r
o
f
ile
in
d
ec
en
tr
alize
d
m
u
lti
-
h
o
p
m
o
b
ile
s
o
cial
n
et
w
o
r
k
s
.
T
h
e
m
ec
h
a
n
i
s
m
s
ar
e
p
r
iv
ac
y
-
p
r
ese
r
v
in
g
:
n
o
p
ar
ticip
an
ts
‘
p
r
o
f
ile
an
d
th
e
s
u
b
m
itted
p
r
ef
er
e
n
ce
p
r
o
f
ile
ar
e
ex
p
o
s
ed
.
Go
g
a
et
al.
[
2
]
ex
p
lo
r
ed
th
e
r
eliab
l
y
m
atch
p
r
o
f
i
les
i
n
p
r
ac
tic
al
k
n
o
w
led
g
e,
ac
r
o
s
s
r
ea
l
-
w
o
r
ld
s
o
cial
n
et
w
o
r
k
s
,
b
y
e
x
p
lo
itin
g
p
u
b
lic
attr
ib
u
te
s
,
p
u
b
licl
y
p
r
o
v
id
e
ab
o
u
t
th
em
s
el
v
es.
I
t
also
d
ef
in
ed
a
s
et
o
f
p
r
o
p
er
ties
f
o
r
p
r
o
f
ile
attr
ib
u
te
s
–
A
v
ailab
il
it
y
,
C
o
n
s
is
te
n
c
y
,
n
o
n
-
I
m
p
r
ess
io
n
ab
ilit
y
,
a
n
d
Dis
cr
i
m
i
n
ab
ilit
y
(
AC
I
D)
–
th
at
ar
e
b
o
th
n
ec
e
s
s
ar
y
a
n
d
s
u
f
f
icien
t
to
d
eter
m
i
n
e
t
h
e
r
eliab
ili
t
y
o
f
a
m
atc
h
i
n
g
s
c
h
e
m
e.
Su
n
e
t
al.
[
3
]
co
m
p
o
s
ed
ar
ea
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
S
elec
tive
C
o
llig
a
tio
n
a
n
d
S
ele
ctive
S
cra
mb
lin
g
fo
r
P
r
iva
cy
P
r
eser
va
tio
n
in
Da
ta
Min
in
g
(
I
s
h
w
a
r
ya
M.V
)
779
b
ased
in
f
o
r
m
al
o
r
g
a
n
izatio
n
a
d
m
in
i
s
tr
atio
n
s
(
L
B
SNS)
h
a
v
e
b
ee
n
ex
p
lo
r
ed
;
th
is
r
e
v
ie
w
co
n
s
tr
u
cts
a
m
o
d
el
to
an
al
y
ze
t
h
e
s
ec
u
r
it
y
m
a
th
,
ad
v
an
tag
e
s
tr
u
ct
u
r
e,
an
d
s
e
x
co
n
tr
asts
.
P
r
ak
ash
et
al.
[
4
]
im
p
le
m
en
ted
an
ap
p
r
o
x
i
m
atio
n
au
to
m
ated
s
tr
u
ct
u
r
e,
ca
lled
Fil
ter
ed
W
all
(
FW
)
an
d
it
f
il
ter
ed
d
is
p
o
s
ed
o
f
s
u
b
s
ta
n
ce
f
r
o
m
OSN
cl
ien
t
s
u
b
s
tan
ce
s
.
T
h
e
g
o
al
is
to
u
t
ilize
e
f
f
icien
t
cla
s
s
i
f
icatio
n
p
r
o
ce
d
u
r
e
to
s
ta
y
a
w
a
y
f
r
o
m
o
v
er
p
o
w
er
ed
b
y
u
n
s
u
cc
ess
f
u
l
m
es
s
ag
e
s
.
I
n
OSN
s
,
co
n
ten
t
f
i
lter
in
g
ca
n
also
b
e
ab
u
s
ed
f
o
r
a
u
n
iq
u
e,
m
o
r
e
r
ea
ctiv
e.
I
n
[
5
]
ex
p
lai
n
ed
in
te
g
r
at
io
n
o
f
A
d
ap
tiv
e
W
ei
g
h
t
R
a
n
k
i
n
g
P
o
lic
y
(
A
W
R
P
)
w
it
h
i
n
telli
g
e
n
t
class
if
ier
s
(
NB
-
A
W
R
P
-
D
A
a
n
d
J
4
8
-
AW
R
P
-
D
A
)
v
ia
d
y
n
a
m
ic
ag
i
n
g
f
ac
to
r
to
i
m
p
r
o
v
e
class
i
f
ier
s
p
o
w
er
o
f
p
r
ed
ictio
n
.
T
h
e
m
et
h
o
d
s
ar
e
u
s
ed
to
ch
o
o
s
e
th
e
b
est
s
u
b
s
e
t
o
f
f
ea
t
u
r
es
.
I
n
[
6
]
in
tr
o
d
u
ce
d
a
n
e
w
f
r
a
m
e
w
o
r
k
ca
lled
F
u
zz
y
b
ased
co
n
tex
t
u
al
r
ec
o
m
m
en
d
atio
n
s
y
s
te
m
f
o
r
class
i
f
icatio
n
o
f
cu
s
to
m
er
r
ev
ie
w
s
.
I
t
ex
tr
ac
t
s
th
e
i
n
f
o
r
m
atio
n
f
r
o
m
t
h
e
r
ev
ie
w
s
b
ase
d
o
n
th
e
co
n
tex
t
g
i
v
e
n
b
y
u
s
e
r
s
.
I
n
[
7
]
s
tu
d
ied
to
id
en
ti
f
y
t
h
e
b
est
class
i
f
ier
s
f
o
r
class
i
m
b
ala
n
ce
d
h
ea
lth
d
atas
ets
th
r
o
u
g
h
a
co
s
t
-
b
a
s
ed
co
m
p
ar
is
o
n
o
f
class
i
f
ier
p
er
f
o
r
m
a
n
ce
.
T
h
e
u
n
eq
u
al
m
is
class
i
f
icatio
n
co
s
ts
w
er
e
r
ep
r
esen
ted
i
n
a
co
s
t
m
atr
i
x
,
an
d
co
s
t
-
be
n
ef
it.
Dh
i
v
ak
ar
et
al
[
8
]
elab
o
r
ated
r
ec
en
t
ap
p
r
o
ac
h
es
w
h
ic
h
ar
e
in
v
o
lv
ed
i
n
p
r
iv
ac
y
p
r
eser
v
a
tio
n
li
k
e
a
r
an
d
o
m
izatio
n
,
An
o
n
y
m
iza
tio
n
,
p
er
tu
r
b
atio
n
an
d
d
is
tr
ib
u
te
d
p
r
iv
ac
y
p
r
eser
v
atio
n
m
eth
o
d
s
.
J
an
b
an
d
h
u
et
a
l
[
9
]
ex
p
r
ess
ed
p
r
iv
ac
y
p
r
eser
v
in
g
in
d
ata
m
i
n
i
n
g
o
f
m
a
n
y
tec
h
n
iq
u
es
alo
n
g
w
ith
t
h
e
ir
ad
v
an
ta
g
e
s
a
n
d
d
is
ad
v
an
ta
g
es.
I
t
also
d
is
c
u
s
s
ed
ab
o
u
t
p
r
esen
t
li
m
itat
io
n
s
a
n
d
s
co
p
e
f
o
r
f
u
t
u
r
e
r
esear
c
h
i
n
p
r
iv
ac
y
p
r
eser
v
i
n
g
d
ata
m
i
n
i
n
g
.
P
atel
et
a
l
[
1
0
]
in
tr
o
d
u
ce
d
a
ce
r
tai
n
tr
an
s
f
o
r
m
atio
n
ap
p
r
o
ac
h
to
d
ea
l
w
i
th
th
e
p
r
iv
ac
y
d
u
r
i
n
g
m
i
n
in
g
.
T
h
is
ap
p
r
o
ac
h
m
ai
n
o
b
j
ec
tiv
e
is
to
p
r
o
v
id
e
m
o
r
e
ac
cu
r
ac
y
o
f
s
p
ec
i
f
ic
d
ata
an
d
p
r
eser
v
i
n
g
p
r
iv
ac
y
o
f
o
r
ig
in
al
d
ata.
T
o
o
v
er
co
m
e
th
e
s
e
li
m
itatio
n
s
w
e
w
il
l
in
tr
o
d
u
ce
an
al
g
o
r
ith
m
ca
lled
Naïv
e
B
a
y
es
cla
s
s
i
f
icatio
n
alg
o
r
ith
m
.
T
h
is
al
g
o
r
it
h
m
d
o
e
s
th
e
ab
o
v
e
p
r
o
ce
s
s
i
n
a
p
ar
allel
m
a
n
n
er
.
T
h
u
s
t
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
Naï
v
e
b
ay
e
s
alg
o
r
it
h
m
en
s
u
r
e
s
th
at
m
i
n
er
ca
n
m
in
e
m
o
r
e
ef
f
ici
en
tl
y
f
r
o
m
th
e
e
n
o
r
m
o
u
s
d
at
ab
ase.
Naïv
e
B
a
y
e
s
C
las
s
i
f
icatio
n
al
g
o
r
ith
m
i
s
u
s
ed
to
p
er
k
u
p
th
e
ti
m
e
ef
f
icie
n
c
y
.
I
t
h
as
w
o
r
k
ed
q
u
i
te
w
ell
in
m
an
y
i
n
tr
icate
r
ea
l
-
w
o
r
ld
cir
cu
m
s
ta
n
ce
s
.
N
aïv
eb
a
y
e
s
cla
s
s
i
f
icatio
n
al
g
o
r
ith
m
c
h
ar
ac
ter
izes
a
lo
t
o
f
le
ar
n
in
g
al
g
o
r
it
h
m
s
.
Naiv
e
B
a
y
e
s
is
a
n
k
ee
n
f
ast
le
ar
n
in
g
clas
s
i
f
ier
.
T
h
u
s
,
it c
o
u
l
d
b
e
u
s
ed
f
o
r
m
a
k
i
n
g
p
r
ed
ictio
n
s
i
n
r
ea
l ti
m
e.
I
t i
s
ea
s
y
to
b
u
ild
a
n
d
p
r
ed
o
m
i
n
a
n
t
l
y
p
o
s
iti
v
e
f
o
r
v
er
y
b
u
lk
y
cla
s
s
y
c
lass
if
ica
tio
n
m
et
h
o
d
s
.
Naï
v
e
B
a
y
e
s
clas
s
i
f
ier
s
in
lear
n
i
n
g
p
r
o
b
le
m
s
r
eq
u
ir
es
lo
t
o
f
co
n
s
tr
ain
t
s
lin
ea
r
in
lo
t
o
f
v
ar
iab
les.
Naïv
e
B
a
y
e
s
is
r
ep
r
esen
ted
in
ter
m
s
o
f
p
r
o
b
ab
ilit
ies.
T
h
ese
p
r
o
b
ab
i
liti
es
ar
e
co
llected
to
f
o
r
m
a
f
ile.
Fo
r
a
lear
n
ed
n
ai
v
esb
a
y
e
s
m
o
d
el
t
h
ese
f
ile
s
w
er
e
u
tili
ze
d
.
Fi
n
all
y
n
aï
v
e
b
ay
es
al
g
o
r
ith
m
is
ea
s
y
to
i
m
p
l
e
m
en
t
an
d
it
w
o
r
k
s
i
n
m
o
r
e
b
en
ef
icial
w
a
y
.
I
t
is
p
r
ef
er
r
ed
to
ch
o
o
s
e
th
i
s
n
aï
v
e
b
a
y
es
al
g
o
r
it
h
m
r
ath
er
t
h
a
n
o
th
er
cl
as
s
i
f
icatio
n
al
g
o
r
ith
m
s
.
T
h
i
s
m
eth
o
d
i
s
p
o
p
u
lar
ly
k
n
o
w
n
as
“
p
u
n
c
h
i
n
g
b
ag
”
f
o
r
s
m
ar
ter
alg
o
r
it
h
m
s
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
b
an
k
d
atab
ase
m
a
n
a
g
e
m
e
n
t
s
y
s
te
m
,
w
e
ar
e
g
o
in
g
to
ap
p
l
y
Naï
v
e
B
a
y
es
clas
s
i
f
icatio
n
alg
o
r
ith
m
esp
ec
iall
y
i
n
lo
a
n
s
ec
to
r
.
I
f
t
h
e
p
er
s
o
n
ap
p
l
ies
f
o
r
a
p
ar
ticu
l
ar
lo
an
in
a
b
a
n
k
,
t
h
e
b
an
k
m
an
ag
e
m
e
n
t
c
h
ec
k
s
th
e
p
r
ev
io
u
s
h
i
s
to
r
y
o
f
t
h
e
p
er
s
o
n
.
W
h
et
h
er
t
h
e
p
er
s
o
n
p
aid
th
e
p
r
ev
io
u
s
lo
an
b
ala
n
ce
o
r
n
o
t
an
d
w
h
eth
er
th
e
p
er
s
o
n
is
ab
le
to
p
a
y
th
e
c
u
r
r
en
t
lo
an
b
ased
o
n
t
h
e
p
r
o
p
er
ty
o
f
t
h
e
p
er
s
o
n
.
T
h
e
cu
s
to
m
er
s
h
o
u
ld
p
r
o
v
id
e
th
e
p
r
o
p
er
r
ea
s
o
n
f
o
r
ac
q
u
ir
in
g
th
e
lo
an
an
d
th
en
t
h
e
y
s
h
o
u
ld
s
atis
f
y
t
h
e
lo
an
cr
iter
ia
an
d
f
o
l
lo
w
ed
b
y
th
i
s
,
th
e
lo
an
w
i
ll
b
e
af
f
o
r
d
ed
.
I
f
w
e
ap
p
ly
n
aï
v
e
b
a
y
es
al
g
o
r
ith
m
in
b
an
k
d
atab
ase
th
e
p
r
ed
ictio
n
w
i
ll
b
e
ac
cu
r
ate.
T
h
e
m
aj
o
r
u
s
e
o
f
n
aï
v
e
b
a
y
es
alg
o
r
ith
m
i
n
d
atab
ase
m
an
a
g
e
m
en
t
s
y
s
te
m
is
to
i
n
cr
ea
s
e
t
h
e
ti
m
e
ef
f
icie
n
c
y
b
ec
au
s
e
th
e
NB
C
alg
o
r
it
h
m
f
o
llo
w
s
p
ar
allel
p
r
o
ce
s
s
in
g
.
W
e
ar
e
g
o
in
g
to
i
m
p
le
m
e
n
t
a
to
o
l
ca
lled
w
ek
a
to
r
u
n
ar
f
f
f
o
r
m
at
o
f
t
h
e
b
a
n
k
d
atab
ase.
T
h
e
o
u
tp
u
t
o
f
o
u
r
p
r
o
j
ec
t
s
h
o
w
s
t
h
e
r
etr
ie
v
al
ti
m
e,
tr
u
e
p
o
s
itiv
e
a
n
d
f
als
e
p
o
s
itiv
e
r
ate.
T
h
e
m
aj
o
r
u
s
e
o
f
t
h
e
alg
o
r
it
h
m
is
to
in
cr
ea
s
e
t
h
e
ti
m
e
e
f
f
icien
c
y
a
n
d
ac
cu
r
at
e
p
r
ed
ictio
n
o
f
lo
an
s
ec
to
r
in
b
a
n
k
d
atab
ase
u
s
i
n
g
n
aïv
e
b
a
y
es
clas
s
i
f
icatio
n
alg
o
r
ith
m
.
U
s
i
n
g
n
aï
v
e
b
a
y
es
alg
o
r
it
h
m
w
e
ca
n
r
ed
u
ce
th
e
ti
m
e
co
n
s
u
m
p
tio
n
in
lar
g
e
s
ec
to
r
s
.
F
ig
u
r
e
1
s
h
o
w
t
h
e
s
y
s
te
m
ar
c
h
itect
u
r
e
with
d
ata
p
r
o
ce
s
s
in
g
s
tep
-
w
i
s
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
7
8
–
7
8
5
780
Fig
u
r
e
1
.
S
y
s
te
m
A
r
c
h
itect
u
r
e
Diag
r
a
m
2.
1
.
P
r
o
po
s
ed
T
ec
hn
i
qu
e
L
et
P
T
b
e
th
e
p
r
iv
ate
tab
le
co
n
tai
n
in
g
a
ttrib
u
te
s
A
1
,
…,
An
w
h
er
e
A
1
i
s
t
h
e
f
ir
s
t
a
ttrib
u
te
an
d
A
n
i
s
th
e
las
t
attr
ib
u
te.
L
et
A
i,….
,
A
j
b
e
th
e
s
et
o
f
q
u
as
i
id
en
ti
f
i
er
s
o
f
P
T
s
u
ch
th
at
(
A
i,
….
,
A
j
)
⊆
(
A
1
,
…,
A
n
)
.
L
et
th
e
to
tal
n
u
m
b
er
o
f
t
u
p
les
in
P
T
b
e
d
en
o
ted
as
r
.
Hen
ce
let
t1
,
…,
tr
r
ep
r
esen
t th
e
t
u
p
les o
f
P
T
.
T
h
e
alg
o
r
ith
m
i
s
as f
o
llo
w
s
:
a.
Select
th
e
q
u
a
s
i id
en
tifie
r
w
i
th
th
e
h
i
g
h
est
n
u
m
b
er
o
f
u
n
iq
u
e
v
alu
e
s
s
a
y
Am
s
u
ch
t
h
at
Am
⊆
A
i,….
,
A
j
.
b.
P
er
f
o
r
m
s
e
lectiv
e
C
o
lli
g
atio
n
o
n
Am
as d
escr
ib
ed
in
p
o
in
t
s
1
to
2.
1)
L
et
G1
,
…,
G
n
b
eg
r
o
u
p
s
s
u
c
h
t
h
at
t
u
p
les
i
n
ea
ch
g
r
o
u
p
h
a
v
e
s
a
m
e
v
al
u
eo
f
Am
.
T
h
e
tu
p
les
n
o
t
in
a
n
y
g
r
o
u
p
o
f
G1
,
….
,
Gn
ar
e
g
e
n
er
a
lized
.
2)
Fo
r
th
e
t
u
p
les
i
n
G1
,
….
,
G
n
we
co
n
s
id
er
th
e
r
e
m
ai
n
i
n
g
q
u
as
i
id
en
ti
f
ier
s
o
f
A
i,….
,
A
j
.
Fo
r
ea
ch
g
r
o
u
p
in
G1
to
Gn
r
ep
ea
t step
2
.
2
.
1
F
o
r
c
in
1
to
n
in
2
.
2
.
1
:
a)
Fo
r e
a
ch tup
le in G
c
rep
eat
st
eps
2
.3.
1
.1
to
2
.
3
.1.2
.
2
.
2
.
1
.
1
.
Fo
r
a
tu
p
le
en
s
u
r
e
t
h
at
it
h
a
s
at
least
o
n
e
m
o
r
e
tu
p
le
in
t
h
e
s
a
m
e
g
r
o
u
p
w
h
ic
h
s
h
o
u
ld
h
av
e
all
th
e
q
u
as
i id
en
ti
f
ier
v
al
u
e
s
(
Ai,
….
,
A
j
)
s
a
m
e
as i
t.
I
f
s
o
g
o
to
s
tep
2
.
2
.
1
.
E
ls
e
g
o
to
s
tep
2
.
2
.
1
.
2
.
Gen
er
alize
th
e
tu
p
le.
3
.
Fo
r
ea
ch
g
en
er
alize
d
tu
p
le
i
n
P
T
r
ep
ea
t step
3
.
1
.
3
.
1
.
Select
tu
p
les
w
h
ic
h
h
a
v
e
u
n
iq
u
e
q
u
as
i id
en
ti
f
ier
s
et
A
i,
….
,
A
j
.
4
.
Sli
ce
PT
s
u
ch
th
a
t
ea
ch
s
lic
ed
tab
le
co
n
tain
s
h
ig
h
l
y
co
r
r
elate
d
v
alu
e
s
.
L
e
t
th
e
s
liced
tab
les
o
f
P
T
b
e
B
1
,
….
,
B
k
,
s
u
ch
t
h
at
k
is
t
h
e
to
tal
n
u
m
b
er
o
f
s
liced
tab
les.
5
.
I
n
th
e
s
liced
tab
les s
elec
t a
t
ab
le
B
h
in
B
1
,
….
,
B
k
s
u
ch
t
h
at
it h
as a
t le
as
t o
n
e
q
u
as
i id
en
ti
f
ier
.
6
.
P
e
r
f
o
r
m
s
elec
ti
v
e
s
h
u
f
f
li
n
g
o
n
th
e
s
elec
ted
tab
le
B
h
.
T
h
is
is
d
o
n
e
b
y
s
h
u
f
f
lin
g
t
h
e
tu
p
le
s
s
elec
ted
in
s
tep
3
.
2.
2
Select
iv
e
Co
llig
a
t
io
n
B
ased
o
n
th
e
ab
o
v
e
alg
o
r
ith
m
w
e
p
er
f
o
r
m
s
elec
ti
v
e
C
o
lli
g
a
tio
n
to
o
u
r
tab
le
to
s
h
o
w
h
o
w
it
w
o
r
k
s
.
T
h
e
s
elec
ted
q
u
asi
id
en
tif
ier
(
s
a
y
in
o
u
r
tab
le
ag
e)
to
g
en
er
alize
w
e
p
er
f
o
r
m
s
elec
ti
v
e
C
o
llig
atio
n
.
Firstl
y
w
e
tr
y
to
id
en
t
if
y
t
h
e
t
u
p
les
th
at
h
av
e
th
e
s
a
m
e
a
g
e
v
a
lu
e.
I
n
t
h
e
f
o
llo
w
in
g
tab
le
t
h
e
s
a
m
e
c
o
lo
r
ed
tu
p
les
h
a
v
e
s
a
m
e
a
g
e
v
al
u
e.
No
w
th
e
tu
p
le
s
i
n
b
lac
k
co
lo
r
ar
e
u
n
iq
u
e
tu
p
les,
ea
ch
h
a
v
in
g
u
n
iq
u
e
a
g
e
v
al
u
es.
So
,
s
u
ch
t
u
p
les
ca
n
n
o
t
b
e
ev
icted
f
r
o
m
C
o
l
lig
atio
n
.
C
o
n
s
id
er
i
n
g
g
r
o
u
p
ed
tu
p
les
w
e
f
ir
s
t
c
h
ec
k
t
h
ei
r
r
e
m
ai
n
in
g
q
u
asi
id
en
ti
f
ier
s
(
s
e
x
,
B
ill Am
o
u
n
t,
A
d
d
r
ess
)
.
A
s
p
er
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
n
a
g
i
v
e
n
g
r
o
u
p
(
s
a
m
e
co
lo
r
)
f
o
r
ev
er
y
T
u
p
le
in
a
g
r
o
u
p
en
s
u
r
e
th
at
it
h
as
at
least
o
n
e
m
o
r
e
tu
p
le
i
n
th
e
s
a
m
e
g
r
o
u
p
w
h
ich
s
h
o
u
ld
h
av
e
all
t
h
e
q
u
as
i
id
en
ti
f
ier
v
al
u
es
s
a
m
e
a
s
it.
F
o
r
ex
a
m
p
le
co
n
s
id
er
i
n
g
r
ed
g
r
o
u
p
tu
p
les
w
e
ca
n
s
XX
t
h
at
th
e
t
u
p
les
Z
Z
Z
a
n
d
VVV
h
a
v
e
s
a
m
e
q
u
asi
id
e
n
ti
f
i
er
v
alu
es
(
2
3
,
M,
1
6
0
0
0
,
Z
Z
)
an
d
th
e
t
u
p
les
UUU
a
n
d
W
W
W
h
av
e
s
a
m
e
q
u
a
s
i
id
en
ti
f
ier
v
al
u
es
(
2
3
,
F,
2
0
0
0
0
,
T
T
)
,
s
o
w
e
n
XXd
n
o
t
g
e
n
er
alize
it
as
it
ca
n
’
t
b
e
id
en
ti
f
ied
b
ec
au
s
e
o
f
it
s
co
m
m
o
n
n
e
s
s
i
n
all
q
u
asi
id
en
tif
ier
v
al
u
es
w
i
th
at
least
o
n
e
m
o
r
e
t
u
p
le.
C
o
n
s
id
er
i
n
g
t
h
e
y
ello
w
g
r
o
u
p
tu
p
les,
tu
p
les
XXX
a
n
d
QQQ
h
av
e
s
a
m
e
q
u
asi
i
d
en
ti
f
ier
v
al
u
es
(
2
7
,
F,
2
6
0
0
0
,
XX)
,
w
h
ic
h
n
XXd
n
o
t
b
e
g
en
er
alize
d
b
u
t
th
e
tu
p
le
Z
Z
Z
h
a
v
in
g
d
if
f
er
en
t
q
u
asi
id
en
t
if
ier
v
alu
e
s
(
2
7
,
M,
3
1
0
0
0
,
Z
Z
)
f
r
o
m
XXX
an
d
QQQ,
n
XXd
to
b
e
g
en
er
alize
d
.
C
o
n
s
id
er
in
g
t
h
e
g
r
XX
n
g
r
o
u
p
tu
p
les
s
i
n
ce
b
o
th
o
f
th
e
m
h
av
e
d
if
f
er
en
t
v
alu
es
f
o
r
th
e
q
u
asi
id
en
ti
f
ier
“A
d
d
r
ess
”
w
e
g
e
n
er
alize
th
e
m
.
T
ab
le
1
ex
p
r
ess
es t
h
e
s
elec
ti
v
e
co
lli
g
atio
n
f
o
r
p
atien
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
S
elec
tive
C
o
llig
a
tio
n
a
n
d
S
ele
ctive
S
cra
mb
lin
g
fo
r
P
r
iva
cy
P
r
eser
va
tio
n
in
Da
ta
Min
in
g
(
I
s
h
w
a
r
ya
M.V
)
781
T
ab
le
1
: Sam
p
le
P
atien
t
Data
s
et
f
o
r
Selectiv
e
C
o
lli
g
atio
n
N
a
me
A
g
e
S
e
x
B
i
l
l
A
mo
u
n
t
N
o
o
f
c
h
e
c
k
ups
A
d
d
r
e
ss
C
r
i
t
i
c
a
l
i
t
y
r
a
t
e
o
f
D
i
se
a
se
(
O
u
t
o
f
1
0
)
ZZZ
23
M
1
6
0
0
0
2
ZZ
7
YYY
35
M
2
0
0
0
0
2
YY
5
XXX
27
F
2
6
0
0
0
2
XX
9
W
WW
31
M
2
0
0
0
0
2
YY
6
ZZZ
27
M
3
1
0
0
0
2
ZZ
10
VVV
23
M
1
6
0
0
0
1
ZZ
8
XXX
30
M
2
0
0
0
0
1
YY
8
UUU
23
F
2
0
0
0
0
1
TT
7
T
T
T
35
M
2
0
0
0
0
3
YY
7
QQQ
27
F
2
6
0
0
0
2
XX
9
W
WW
23
F
2
0
0
0
0
3
TT
7
RRR
29
M
3
5
0
0
0
1
ZZ
8
SSS
33
M
3
1
0
0
0
2
ZZ
8
T
ab
le
2
: Sam
p
le
P
atien
t
Data
s
et
f
o
r
C
o
llig
a
tio
n
N
a
me
A
g
e
S
e
x
B
i
l
l
A
mo
u
n
t
N
o
o
f
c
h
e
c
k
ups
A
d
d
r
e
ss
C
r
i
t
i
c
a
l
i
t
y
r
a
t
e
o
f
D
i
se
a
se
(
O
u
t
o
f
1
0
)
ZZZ
23
M
1
6
0
0
0
2
ZZ
7
YYY
30
-
40
M
2
0
0
0
0
2
YY
5
XXX
27
F
2
6
0
0
0
2
XX
9
W
WW
30
-
40
M
2
0
0
0
0
2
YY
6
ZZZ
20
-
30
M
3
1
0
0
0
2
ZZ
10
VVV
23
M
1
6
0
0
0
1
ZZ
8
XXX
30
-
40
M
2
0
0
0
0
1
YY
8
UUU
23
F
2
0
0
0
0
1
TT
7
T
T
T
30
-
40
M
2
0
0
0
0
3
YY
7
QQQ
27
F
2
6
0
0
0
2
XX
9
W
WW
23
F
2
0
0
0
0
3
TT
7
RRR
20
-
30
M
3
5
0
0
0
1
ZZ
8
SSS
30
-
40
M
3
1
0
0
0
2
ZZ
8
2
.
3
Scra
m
bli
ng
a
nd
Se
lect
iv
e
Co
llig
a
t
io
n
I
n
t
h
e
ab
o
v
e
T
ab
le
2
af
ter
p
er
f
o
r
m
i
n
g
s
elec
ti
v
e
C
o
lli
g
ati
o
n
,
w
e
ca
n
s
XX
t
h
at
s
o
m
e
g
en
er
alize
d
tu
p
les
s
t
ill
h
a
v
e
u
n
iq
u
e
q
u
asi
id
en
ti
f
ier
s
et
w
h
ich
i
s
a
th
r
ea
t
to
p
r
iv
ac
y
.
Fo
r
ex
a
m
p
le
t
u
p
les
lik
e
Z
Z
Z
(
y
ello
w
g
r
o
u
p
)
an
d
R
R
R
b
o
th
h
a
v
e
a
g
e
in
th
e
r
a
n
g
e
2
0
-
3
0
,
b
u
t
th
e
y
d
if
f
er
in
t
h
e
q
u
a
s
i
id
en
ti
f
ier
B
ill
Am
o
u
n
t
w
h
ic
h
m
ak
e
s
th
e
m
u
n
iq
u
e
an
d
h
e
n
ce
id
en
ti
f
iab
le.
Si
m
ilar
l
y
S
SS
a
l
s
o
d
if
f
er
s
in
b
o
th
B
il
l
Am
o
u
n
t
an
d
lo
ca
tio
n
w
ith
th
e
s
i
m
ilar
r
an
g
ed
tu
p
le
s
YY
Y
an
d
W
W
W
.
So
b
ef
o
r
e
s
licin
g
w
e
s
elec
t
s
u
c
h
tu
p
les
as
p
er
th
e
alg
o
r
ith
m
a
s
in
tab
le
3
.
Af
ter
s
elec
tio
n
w
e
s
li
ce
th
e
tab
le
u
s
in
g
o
n
e
o
f
t
h
e
ex
is
t
in
g
s
lici
n
g
alg
o
r
it
h
m
s
t
h
at
h
as
th
e
b
est
ti
m
e
ef
f
icien
c
y
an
d
it
s
h
o
w
n
i
n
tab
le
4
.
I
n
th
e
s
liced
tab
les
w
e
s
el
ec
t
an
y
tab
le
as
p
er
o
u
r
w
is
h
(
w
it
h
t
h
e
co
n
s
tr
ai
n
t
th
at
i
t
s
h
o
u
ld
h
a
v
e
at
least
o
n
e
q
u
asi
id
en
ti
f
ier
)
a
n
d
s
h
u
f
f
le
th
e
t
u
p
les
th
at
w
e
s
el
ec
ted
b
ef
o
r
e
s
licin
g
p
r
o
ce
s
s
.
B
y
d
o
in
g
s
e
lecti
v
e
s
h
u
f
f
l
in
g
w
e
h
a
v
e
e
li
m
in
a
ted
t
h
e
p
o
s
s
ib
ilit
y
o
f
p
r
iv
ac
y
b
r
XXc
h
to
ce
r
tain
r
ec
o
r
d
s
t
h
at
th
e
p
o
s
s
ib
ilit
y
o
f
b
ein
g
id
e
n
ti
f
ie
d
(
eg
r
ec
o
r
d
s
lik
e
S
SS
,
R
R
R
)
ev
e
n
a
f
ter
th
e
C
o
lli
g
atio
n
p
r
o
ce
s
s
.
Mo
r
eo
v
er
s
elec
ti
v
e
C
o
llig
a
tio
n
co
n
s
u
m
e
s
les
s
ti
m
e
as
co
m
p
ar
ed
to
f
u
ll
C
o
lli
g
atio
n
a
s
n
o
e
x
is
ti
n
g
s
h
u
f
f
li
n
g
al
g
o
r
ith
m
ca
n
g
u
ar
an
tX
X
a
ti
m
e
ef
f
icie
n
c
y
o
f
O(
1
)
an
d
h
en
ce
th
e
ti
m
e
ef
f
icie
n
c
y
o
f
s
h
u
f
f
li
n
g
p
r
o
ce
s
s
d
ep
en
d
s
o
n
in
p
u
t
s
ize.
T
ab
le
3
ex
p
lain
s
t
h
e
tu
p
l
es to
b
e
s
h
u
f
f
led
af
ter
ap
p
l
y
i
n
g
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
ab
le
3
: Sele
ctio
n
o
f
tu
p
les to
b
e
s
h
u
f
f
led
.
N
a
me
A
g
e
S
e
x
B
i
l
l
A
mo
u
n
t
N
o
o
f
c
h
e
c
k
u
p
s
A
d
d
r
e
ss
C
r
i
t
i
c
a
l
i
t
y
r
a
t
e
o
f
D
i
se
a
se
(
O
u
t
o
f
1
0
)
ZZZ
23
M
1
6
0
0
0
2
ZZ
7
YYY
30
-
40
M
2
0
0
0
0
2
YY
5
XXX
27
F
2
6
0
0
0
2
XX
9
W
WW
30
-
40
M
2
0
0
0
0
2
YY
6
*
Z
Z
Z
20
-
30
M
3
1
0
0
0
2
ZZ
10
VVV
23
M
1
6
0
0
0
1
ZZ
8
XXX
30
-
40
M
2
0
0
0
0
1
YY
8
UUU
23
F
2
0
0
0
0
1
TT
7
T
T
T
30
-
40
M
2
0
0
0
0
3
YY
7
QQQ
27
F
2
6
0
0
0
2
XX
9
W
WW
23
F
2
0
0
0
0
3
TT
7
*
R
R
R
20
-
30
M
3
5
0
0
0
1
ZZ
8
*
S
S
S
30
-
40
M
3
1
0
0
0
2
ZZ
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
7
8
–
7
8
5
782
T
u
p
les
w
it
h
aster
i
s
k
ar
e
s
elec
t
ed
.
T
ab
le
4
ex
p
lain
ed
th
e
s
liced
m
et
h
o
d
f
o
r
p
atien
t
d
ataset
f
o
r
ag
e,
s
ex
,
b
ilein
g
d
etails
w
it
h
Dis
ea
s
e
.
T
h
e
p
r
iv
ac
y
p
r
eser
v
atio
n
tech
n
iq
u
e
ca
n
b
e
ap
p
ilied
f
o
r
s
elec
ted
ar
ttib
u
tes
o
f
d
ataset.
T
a
b
le
5
ex
p
lo
r
es
t
h
e
s
u
f
f
li
n
g
p
r
o
ce
s
s
o
f
s
elec
ted
cr
ed
en
tial a
r
r
tib
u
te
s
.
T
ab
le
4
: Sliced
T
ab
les
f
o
r
P
ati
en
t D
atase
t
{A
g
e
,
S
e
x
,
B
i
l
l
A
mo
u
n
t
}
{N
o
o
f
c
h
e
c
k
u
p
s,A
d
d
r
e
ss,
C
r
i
t
i
c
a
l
i
t
y
r
a
t
e
o
f
D
i
se
a
se
(
o
u
t
o
f
1
0
)
}
{2
3
,
M
,
1
6
0
0
0
}
{2
,
Z
Z
,
7
}
{3
0
-
4
0
,
M
,
2
0
0
0
0
}
{2
,
Y
Y
,
5
}
{2
7
,
F
,
2
6
0
0
0
}
{2
,
X
X
,
9
}
{3
0
-
4
0
,
M
,
2
0
0
0
0
}
{2
,
Y
Y
,
6
}
*
{2
0
-
3
0
,
M
,
3
1
0
0
0
}
{2
,
Z
Z
,
1
0
}
{2
3
,
M
,
1
6
0
0
0
}
{1
,
Z
Z
,
8
}
{3
0
-
4
0
,
M
,
2
0
0
0
0
}
{1
,
Y
Y
,
8
}
{2
3
,
F
,
2
0
0
0
0
}
{1
,
T
T
,
7
}
{3
0
-
4
0
,
M
,
2
0
0
0
0
}
{3
,
Y
Y
,
7
}
{2
7
,
F
,
2
6
0
0
0
}
{2
,
X
X
,
9
}
{2
3
,
F
,
2
0
0
0
0
}
{3
,
T
T
,
7
}
*
{2
0
-
3
0
,
M
,
3
5
0
0
0
}
{1
,
Z
Z
,
8
}
*
{3
0
-
4
0
,
M
,
3
1
0
0
0
}
{2
,
Z
Z
,
8
}
T
ab
le
5
: A
f
ter
Selec
tiv
e
Sh
u
f
f
lin
g
{A
g
e
,
S
e
x
,
B
i
l
l
A
mo
u
n
t
}
{N
o
o
f
c
h
e
c
k
u
p
s,A
d
d
r
e
ss,
C
r
i
t
i
c
a
l
i
t
y
r
a
t
e
o
f
D
i
se
a
se
(
o
u
t
o
f
1
0
)
}
{2
3
,
M
,
1
6
0
0
0
}
{2
,
Z
Z
,
7
}
{3
0
-
4
0
,
M
,
2
0
0
0
0
}
{2
,
Y
Y
,
5
}
{2
7
,
F
,
2
6
0
0
0
}
{2
,
X
X
,
9
}
{3
0
-
4
0
,
M
,
2
0
0
0
0
}
{2
,
Y
Y
,
6
}
*
{2
0
-
3
0
,
M
,
3
1
0
0
0
}
{2
,
Z
Z
,
8
}
{2
3
,
M
,
1
6
0
0
0
}
{1
,
Z
Z
,
8
}
{3
0
-
4
0
,
M
,
2
0
0
0
0
}
{1
,
Y
Y
,
8
}
{2
3
,
F
,
2
0
0
0
0
}
{1
,
T
T
,
7
}
{3
0
-
4
0
,
M
,
2
0
0
0
0
}
{3
,
Y
Y
,
7
}
{2
7
,
F
,
2
6
0
0
0
}
{2
,
X
X
,
9
}
{2
3
,
F
,
2
0
0
0
0
}
{3
,
T
T
,
7
}
*
{2
0
-
3
0
,
M
,
3
5
0
0
0
}
{2
,
Z
Z
,
1
0
}
*
{3
0
-
4
0
,
M
,
3
1
0
0
0
}
{1
,
Z
Z
,
8
}
2
.
4
E
nh
a
ncing
ef
f
iciency
in da
t
a
m
ini
ng
us
ing
cla
s
s
if
ica
t
io
n a
lg
o
rit
h
m
:
2
.
4
.
1
.
Da
t
a
co
llect
io
n:
Data
co
llectio
n
is
a
m
ea
n
s
f
o
r
g
at
h
er
in
g
f
ac
t
s
,
s
tatis
tics
an
d
d
etails
f
r
o
m
d
i
f
f
er
en
t
s
o
u
r
ce
s
.
I
n
t
h
i
s
s
tag
e,
d
ata
s
et
co
n
s
i
s
ts
o
f
lar
g
e
n
u
m
b
er
o
f
f
ile
s
1
0
0
0
d
ata
f
r
o
m
d
is
tr
i
b
u
ted
d
ata
o
u
t
o
f
w
h
ic
h
1
0
0
ar
e
f
r
o
m
p
ar
ticu
lar
in
s
ta
n
ce
s
.
T
h
i
s
h
o
s
ts
i
n
f
o
r
m
a
tio
n
ab
o
u
t
d
i
f
f
er
e
n
t
t
y
p
es
o
f
lo
an
s
a
n
d
th
eir
cr
iter
ia
in
f
o
r
m
atio
n
.
T
h
e
r
elate
d
d
ata
ar
e
co
llected
b
ased
o
n
v
ar
io
u
s
s
u
r
v
e
y
s
,
r
ec
o
r
d
s
,
f
ee
d
b
ac
k
s
,
c
u
s
to
m
er
i
n
f
o
r
m
atio
n
,
an
d
lo
a
n
d
etail
s
i
n
d
if
f
er
e
n
t b
r
an
ch
e
s
o
f
a
b
an
k
d
etails i
n
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
Data
C
o
llectio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
S
elec
tive
C
o
llig
a
tio
n
a
n
d
S
ele
ctive
S
cra
mb
lin
g
fo
r
P
r
iva
cy
P
r
eser
va
tio
n
in
Da
ta
Min
in
g
(
I
s
h
w
a
r
ya
M.V
)
783
2
.
4
.
2
D
a
t
a
s
et
cr
e
a
t
io
n:
T
h
e
d
ata
s
et
p
r
ep
r
o
ce
s
s
in
g
s
te
p
s
ar
e
ex
p
lain
ed
d
etails i
n
Fi
g
u
r
e
3.
Fig
u
r
e
3
.
Data
s
et
C
r
ea
tio
n
2
.
4
.
3
.
F
ea
t
ure
ex
t
ra
ct
i
o
n
T
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
is
ap
p
lied
to
ex
tr
ac
t
th
e
f
ea
r
tu
r
e
f
r
o
m
p
r
ep
r
o
ce
s
s
ed
d
atas
et
w
h
ich
d
etails
ar
e
ex
p
lain
ed
Fi
g
u
r
e
4
.
Hen
ce
; th
e
p
r
o
p
o
s
ed
class
if
ier
w
ill p
r
ed
i
ct
th
e
d
ataset
f
o
r
v
is
u
aliza
tio
n
s
.
Fig
u
r
e
4
.
Featu
r
e
E
x
tr
ac
tio
n
2
.
4
.
4
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chi
ne:
Af
ter
th
e
f
ea
t
u
r
te
ex
tr
ac
tio
n
,
S
u
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e
p
r
o
ce
s
s
th
e
p
r
ed
ictio
n
p
r
o
ce
s
s
to
v
is
u
l
aize
d
ata
w
it
h
p
r
iv
ac
y
.
T
h
e
SVM
p
r
ed
ict
th
e
p
r
iv
ac
y
p
r
eser
v
ed
d
ata
b
ased
o
n
s
lecte
d
attr
ib
u
tes t
h
at
p
r
o
ce
s
s
d
etails ar
e
ex
p
lain
ed
i
n
Fi
g
u
r
e
5
.
Fig
u
r
e
5
.
Su
p
p
o
r
t V
ec
to
r
Ma
c
h
in
e
2
.
4
.
5.
Na
i
v
e
ba
y
es c
la
s
s
if
ier:
We
u
s
e
Naï
v
e
B
a
y
e
s
C
las
s
i
f
i
ca
tio
n
al
g
o
r
ith
m
to
p
er
k
u
p
t
h
e
ti
m
e
ef
f
icie
n
c
y
.
I
t
h
as
w
o
r
k
ed
q
u
ite
w
ell
i
n
m
an
y
in
tr
icate
r
ea
l
-
w
o
r
ld
cir
cu
m
s
ta
n
ce
s
.
Nai
v
e
B
a
y
es
is
a
k
ee
n
f
ast
lear
n
i
n
g
clas
s
if
ier
.
T
h
u
s
,
it
co
u
ld
b
e
u
s
ed
f
o
r
m
ak
i
n
g
p
r
ed
icti
o
n
s
i
n
r
ea
l
ti
m
e
t
h
at
d
etail
s
h
o
w
s
i
n
Fi
g
u
r
e
6
.
I
t
is
ea
s
y
to
b
u
ild
a
n
d
p
r
ed
o
m
in
a
n
tl
y
p
o
s
it
iv
e
f
o
r
v
er
y
b
u
l
k
y
d
atasets
an
d
i
t
is
k
n
o
w
n
to
s
u
r
p
as
s
e
v
en
ex
ce
ed
in
g
l
y
clas
s
y
class
i
f
icatio
n
m
et
h
o
d
s
.
Fig
u
r
e
6
.
Naïv
e
B
a
y
es
C
las
s
i
f
i
er
COLL
ECT
I
ON
OF
INFORM
AT
ION
DA
TA
S
E
T
CREAT
ION
DA
TA
S
E
T
AR
FF
File
Featu
r
e
E
x
tr
ac
tio
n
I
n
p
u
t File
C
las
s
i
f
icatio
n
R
es
u
lts
SVM
C
las
s
i
f
ier
A
l
g
o
r
ith
m
Data
s
et
Data
s
et
NB
C
class
i
f
ier
alg
o
r
ith
m
C
las
s
i
f
ier
r
esu
lt
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
10
,
No
.
2
,
Ma
y
2
0
1
8
:
7
7
8
–
7
8
5
784
Fig
u
r
e
7
.
P
r
ed
icte
d
R
esu
lt o
f
Naïv
e
B
a
y
es
C
las
s
i
f
ier
Fig
u
r
e
8
.
C
o
m
p
ar
ativ
e
R
es
u
lt
o
f
NB
(
Naïv
e
B
a
y
es
)
&
SVM
Su
p
p
o
r
t V
ec
to
r
Ma
ch
in
e
)
Fig
u
r
e
7
esh
o
w
s
Naï
v
e
B
a
y
es
C
lass
i
f
icat
io
n
tech
n
iq
u
es
r
es
u
lt
ef
f
icie
n
c
y
,
in
cl
u
d
es
C
P
U
p
r
o
ce
s
s
in
g
ti
m
e,
r
etr
iev
al
ti
m
e,
co
m
p
u
ta
tio
n
ti
m
e
.
Naï
v
e
b
a
y
es
al
g
o
r
ith
m
e
n
s
u
r
es
t
h
at
m
i
n
er
ca
n
s
ec
u
r
e
m
i
n
e
m
o
r
e
ef
f
icien
tl
y
f
r
o
m
t
h
e
en
o
r
m
o
u
s
d
atab
ase
.
Hen
ce
,
Fi
g
u
r
e
8
d
ep
icts
th
e
p
r
o
p
o
s
ed
Naïv
e
B
a
y
es
C
las
s
i
f
icatio
n
tech
n
iq
u
es
b
est r
es
u
lt c
o
m
p
ar
e
th
e
o
th
er
tech
n
iq
u
es.
3
.
Co
nclus
io
n
B
y
Naï
v
e
B
a
y
e
s
C
las
s
i
f
icati
o
n
al
g
o
r
ith
m
,
t
h
e
w
h
o
le
ti
m
e
w
h
ic
h
in
cl
u
d
es
C
P
U
p
r
o
ce
s
s
i
n
g
ti
m
e,
r
etr
iev
al
ti
m
e,
co
m
p
u
ta
tio
n
ti
m
e
w
i
ll
b
e
r
ed
u
ce
d
.
B
ec
au
s
e
o
f
t
h
e
p
ar
allel
p
r
o
ce
s
s
in
g
,
t
h
e
s
p
ee
d
o
f
r
etr
iev
i
n
g
d
ata
f
r
o
m
lar
g
e
d
ataset
s
o
r
e
n
o
r
m
o
u
s
d
atab
ase
i
s
i
n
cr
e
ase
d
.
Naïv
e
B
a
y
e
s
A
l
g
o
r
ith
m
w
i
ll
also
p
r
ed
ict
m
o
r
e
ac
cu
r
atel
y
.
T
h
e
p
r
ed
ictio
n
will
b
ase
o
n
t
h
e
cr
iter
ia
g
i
v
e
n
b
y
t
h
e
m
a
n
ag
e
m
e
n
t
s
y
s
te
m
.
I
t
is
v
er
y
s
i
m
p
le
r
ep
r
esen
tatio
n
a
n
d
d
o
esn
’
t
al
lo
w
f
o
r
r
ich
h
y
p
o
th
e
s
es.
I
t
n
ee
d
s
a
v
er
y
s
m
all
a
m
o
u
n
t
o
f
tr
ain
i
n
g
d
ata.
F
o
r
f
u
r
t
h
er
en
h
a
n
ce
m
e
n
t
w
e
co
m
m
en
ce
d
a
Naï
v
e
B
a
y
es
u
p
d
atab
le
alg
o
r
ith
m
w
h
ich
i
s
th
e
a
d
v
an
ce
d
v
er
s
io
n
o
f
Naïv
e
B
a
y
es
clas
s
i
f
icatio
n
al
g
o
r
ith
m
.
T
h
u
s
th
e
p
r
o
p
o
s
ed
tec
h
n
iq
u
e
Naïv
e
b
a
y
e
s
alg
o
r
ith
m
en
s
u
r
es
t
h
at
m
in
er
ca
n
m
i
n
e
m
o
r
e
ef
f
icie
n
tl
y
f
r
o
m
t
h
e
e
n
o
r
m
o
u
s
d
at
ab
ase.
Fi
n
all
y
n
aïv
e
b
a
y
e
s
al
g
o
r
ith
m
i
s
ea
s
y
to
i
m
p
le
m
e
n
t
an
d
it
w
o
r
k
s
in
m
o
r
e
b
en
ef
ic
ial
w
a
y
.
I
t
is
p
r
ef
er
r
ed
to
ch
o
o
s
e
th
is
n
aïv
e
b
a
y
es
al
g
o
r
ith
m
r
ath
er
th
a
n
o
th
e
r
class
i
f
icatio
n
alg
o
r
it
h
m
s
.
T
h
is
m
eth
o
d
is
p
o
p
u
lar
l
y
k
n
o
w
n
a
s
“
p
u
n
c
h
i
n
g
b
a
g
”
f
o
r
s
m
ar
ter
al
g
o
r
ith
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
S
elec
tive
C
o
llig
a
tio
n
a
n
d
S
ele
ctive
S
cra
mb
lin
g
fo
r
P
r
iva
cy
P
r
eser
va
tio
n
in
Da
ta
Min
in
g
(
I
s
h
w
a
r
ya
M.V
)
785
RE
F
E
R
E
NC
E
S
[
1
]
Zh
a
n
g
,
L
.
,
L
i,
X
.
Y.,
&
L
iu
,
Y.
M
e
ss
a
g
e
in
a
se
a
led
b
o
tt
le:
Priva
c
y
p
re
se
r
v
in
g
frien
d
in
g
in
so
c
i
a
l
n
e
two
rk
s
.
In
Distrib
u
te
d
Co
m
p
u
ti
n
g
S
y
ste
m
s (ICDCS)
,
2
0
1
3
IEE
E
3
3
rd
I
n
tern
a
t
io
n
a
l
C
o
n
f
e
re
n
c
e
o
n
IEE
E,
2
0
1
3
;
3
2
7
-
3
3
6
.
[
2
]
G
o
g
a
,
O.,
L
o
ise
a
u
,
P
.
,
S
o
m
m
e
r,
R.
,
T
e
ix
e
ira,
R.
,
&
G
u
m
m
a
d
i,
K.
P
.
On
th
e
re
li
a
b
il
it
y
o
f
p
ro
fi
le ma
t
c
h
in
g
a
c
ro
ss
la
rg
e
o
n
l
in
e
so
c
i
a
l
n
e
two
r
k
s
.
In
P
r
o
c
e
e
d
in
g
s o
f
th
e
2
1
st A
CM
S
IG
KD
D In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Kn
o
w
led
g
e
Disc
o
v
e
r
y
a
n
d
Da
ta M
in
i
n
g
,
2
0
1
5
;
1
7
9
9
-
1
8
0
8
.
[
3
]
S
u
n
,
Y.,
W
a
n
g
,
N.,
S
h
e
n
,
X
.
L
.
,
&
Zh
a
n
g
,
J.
X
.
L
o
c
a
ti
o
n
in
f
o
rm
a
ti
o
n
d
isc
lo
su
re
in
l
o
c
a
ti
o
n
-
b
a
se
d
so
c
ial
n
e
tw
o
rk
se
r
v
ice
s:
P
riv
a
c
y
c
a
lcu
lu
s,
b
e
n
e
f
it
s
stru
c
tu
re
,
a
n
d
g
e
n
d
e
r
d
if
fe
re
n
c
e
s.
Co
mp
u
ter
s
in
Hu
ma
n
Beh
a
v
i
o
r
,
2
0
1
5
;
5
2
:
2
7
8
-
2
9
2
[
4
]
P
ra
k
a
sh
,
G
.
,
S
a
u
ra
v
,
N.,
&
Ke
t
h
u
,
V
.
R.
,
“
A
n
Ef
f
e
c
ti
v
e
Un
d
e
sire
d
Co
n
ten
t
F
il
tratio
n
a
n
d
P
re
d
icti
o
n
s
F
ra
m
e
w
o
rk
in
On
li
n
e
S
o
c
ial
Ne
t
w
o
rk
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s in
S
i
g
n
a
l
a
n
d
Ima
g
e
S
c
ie
n
c
e
s,
v
o
l.
2
,
n
o
.
2
,
p
p
.
1
-
8
,
2
0
1
6
.
[
5
]
Ola
n
re
wa
ju
,
R.
F
.
,
&
A
z
m
a
n
,
A
.
W
.
,
“
In
telli
g
e
n
t
Co
o
p
e
ra
ti
v
e
A
d
a
p
ti
v
e
W
e
ig
h
t
Ra
n
k
in
g
P
o
li
c
y
v
i
a
d
y
n
a
m
ic
a
g
in
g
b
a
se
d
o
n
NB
a
n
d
J4
8
c
las
sif
iers
”
,
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
In
fo
rm
a
t
ics
(
IJ
EE
I)
,
v
o
l.
5
,
n
o
.
4
,
p
p
.
3
5
7
-
3
6
5
,
2
0
1
7
.
[
6
]
S
u
lt
h
a
n
a
,
R.
,
&
Ra
m
a
sa
m
y
,
S
.
,
“
Co
n
tex
t
Ba
se
d
Clas
sif
ic
a
ti
o
n
o
f
Re
v
ie
w
s
Us
in
g
As
so
c
iatio
n
Ru
le
M
in
i
n
g
,
F
u
z
z
y
L
o
g
i
c
s
a
n
d
On
to
lo
g
y
”
,
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
In
fo
rm
a
ti
c
s
(
BE
EI)
,
v
o
l.
6
,
n
o
.
3
,
p
p
.
2
5
0
-
2
5
5
,
2
0
1
7
.
[
7
]
Ra
o
,
R.
R.
,
&
M
a
k
k
it
h
a
y
a
,
K.,
“
L
e
a
rn
in
g
f
ro
m
a
Clas
s
I
m
b
a
lan
c
e
d
P
u
b
li
c
He
a
lt
h
Da
tas
e
t:
a
Co
st
-
b
a
se
d
Co
m
p
a
riso
n
o
f
Clas
si
f
ier
P
e
rf
o
rm
a
n
c
e
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
7
,
n
o
.
4
,
p
p
.
2
2
1
5
-
2
2
2
2
,
2
0
1
7
.
[
8
]
Dh
iv
a
k
a
r
K.,
M
o
h
a
n
a
S
.
,
“
A
S
u
rv
e
y
o
n
P
riv
a
c
y
P
re
se
rv
a
ti
o
n
Re
c
e
n
t
A
p
p
ro
a
c
h
e
s
a
n
d
T
e
c
h
n
iq
u
e
s”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
t
i
v
e
Res
e
a
rc
h
in
Co
mp
u
ter
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
o
l.
2
,
issu
e
1
1
,
2
0
1
4
,
p
p
.
6
5
5
9
-
6
5
6
6
.
[
9
]
Ja
n
b
a
n
d
h
u
S
.
,
C
h
a
w
a
re
S
.
M
,
“
S
u
rv
e
y
o
n
Da
ta
M
in
in
g
w
it
h
P
riv
a
c
y
P
re
se
rv
a
ti
o
n
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
ies
,
Vo
l.
5
,
N
o
.
4
,
2
0
1
4
,
p
p
.
5
2
7
9
-
5
2
8
3
.
[
1
0
]
P
a
tel
J.
D.,
P
a
tel
S
.
,
“
A
S
u
rv
e
y
o
n
Da
ta
P
e
rtu
r
b
a
ti
o
n
T
e
c
h
n
iq
u
e
s
f
o
r
P
riv
a
c
y
P
re
se
rv
in
g
in
Da
t
a
M
in
in
g
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
f
o
r
S
c
ien
ti
fi
c
Res
e
a
rc
h
&
De
v
e
lo
p
me
n
t,
v
o
l.
3
,
issu
e
0
1
,
p
p
.
5
2
-
5
4
,
2
0
1
5
Evaluation Warning : The document was created with Spire.PDF for Python.