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
181
~
1
1
9
4
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
1
8
1
-
1
1
9
4
1181
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
A review
of t
he i
mpa
cts of lin
ked
o
pen data
on cro
s
s
-
do
ma
in
recom
mender
sy
stems for
indiv
idu
a
l and g
ro
ups
Yui Chee
Xua
n
1
,
Ro
s
m
a
m
a
l
m
i Ma
t
Na
wi
1
,
Sh
a
hrul Az
m
a
n M
o
hd
No
a
h
2
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
e
c
u
r
i
t
y
a
n
d
W
e
b
Te
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
y
Tu
n
H
u
sse
i
n
O
n
n
M
a
l
a
y
si
a
,
J
o
h
o
r
,
M
a
l
a
y
s
i
a
2
C
e
n
t
r
e
f
o
r
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
T
e
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
T
h
e
N
a
t
i
o
n
a
l
U
n
i
v
e
r
si
t
y
o
f
M
a
l
a
y
si
a
,
S
e
l
a
n
g
o
r
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
11
,
2
0
2
4
R
ev
is
ed
No
v
6
,
2
0
2
4
Acc
ep
ted
No
v
11
,
2
0
2
4
As
u
se
rs'
v
iew
p
o
i
n
ts
o
n
i
n
fo
rm
a
ti
o
n
se
a
rc
h
in
g
c
h
a
n
g
e
fr
o
m
in
fo
rm
a
ti
o
n
se
e
k
in
g
t
o
i
n
fo
rm
a
ti
o
n
re
c
e
iv
in
g
,
n
e
w
se
a
rc
h
p
a
ra
d
i
g
m
s
a
re
c
o
n
ti
n
u
o
u
sl
y
e
m
e
rg
in
g
.
Ut
il
izin
g
a
re
c
o
m
m
e
n
d
e
r
sy
ste
m
(RS
)
is
o
n
e
o
f
t
h
e
m
o
d
e
rn
wa
y
s
t
o
g
e
t
in
f
o
rm
a
ti
o
n
.
T
h
e
RS
h
a
s
s
u
c
c
e
e
d
e
d
i
n
v
a
rio
u
s
trad
i
ti
o
n
a
l
d
o
m
a
in
s,
in
c
lu
d
in
g
t
o
u
rism
,
h
e
a
lt
h
,
a
n
d
b
o
o
k
s
.
H
o
we
v
e
r,
s
o
m
e
sc
e
n
a
rio
s
a
re
m
o
re
su
it
a
b
le
to
re
c
o
m
m
e
n
d
to
a
g
ro
u
p
o
f
u
se
rs
th
a
n
a
n
i
n
d
i
v
id
u
a
l,
su
c
h
a
s
li
ste
n
in
g
to
m
u
sic
a
t
t
h
e
sa
m
e
p
lac
e
a
n
d
g
ro
u
p
trav
e
li
n
g
.
T
h
e
li
m
it
e
d
a
n
d
i
n
c
o
m
p
lete
n
u
m
b
e
r
o
f
u
se
r
-
it
e
m
ra
ti
n
g
s
tri
g
g
e
rs
th
e
c
h
a
ll
e
n
g
e
s
o
f
th
e
g
ro
u
p
a
n
d
i
n
d
i
v
id
u
a
l
RS
s.
Th
e
d
a
ta
sp
a
rsit
y
p
ro
b
lem
e
m
e
rg
e
s
b
e
c
a
u
se
o
f
th
is
in
c
o
m
p
let
e
n
e
ss
.
Th
e
q
u
a
li
t
y
o
f
re
c
o
m
m
e
n
d
a
ti
o
n
s
o
ffe
re
d
to
i
n
d
i
v
id
u
a
ls
a
n
d
g
ro
u
p
s
su
f
fe
rs
wh
e
n
th
e
re
is
d
a
ta
sp
a
rsity
.
Us
in
g
k
n
o
wle
d
g
e
g
a
in
e
d
fr
o
m
a
so
u
rc
e
d
o
m
a
in
,
c
ro
ss
-
d
o
m
a
in
RS
s
c
a
n
e
n
h
a
n
c
e
re
c
o
m
m
e
n
d
a
ti
o
n
s
i
n
targ
e
t
d
o
m
a
in
.
Cro
ss
-
d
o
m
a
i
n
a
n
d
li
n
k
e
d
o
p
e
n
d
a
ta
a
p
p
ro
a
c
h
e
s
a
re
two
wa
y
s
t
o
i
n
c
re
a
se
re
c
o
m
m
e
n
d
a
ti
o
n
sy
ste
m
s'
p
e
rfo
rm
a
n
c
e
.
Th
e
imp
a
c
ts o
f
t
h
e
two
a
fo
re
m
e
n
ti
o
n
e
d
a
p
p
r
o
a
c
h
e
s o
n
in
d
i
v
id
u
a
l
a
n
d
g
ro
u
p
RS
s
h
a
v
e
b
e
e
n
d
isc
u
ss
e
d
.
F
u
rt
h
e
rm
o
re
,
we
h
ig
h
li
g
h
ted
v
a
rio
u
s
d
o
m
a
in
s
e
m
p
l
o
y
e
d
i
n
c
r
o
ss
-
d
o
m
a
in
RS
s
f
o
r
i
n
d
iv
i
d
u
a
ls
a
n
d
g
ro
u
p
s,
e
x
a
m
in
e
d
d
iv
e
rse
m
e
th
o
d
o
lo
g
ies
a
n
d
a
l
g
o
ri
th
m
s,
o
u
tl
i
n
e
d
c
u
rre
n
t
i
ss
u
e
s,
a
n
d
su
g
g
e
ste
d
f
u
tu
re
d
irec
ti
o
n
s
fo
r
c
ro
ss
-
d
o
m
a
in
RS
s
re
se
a
rc
h
fo
r
g
r
o
u
p
s
lev
e
ra
g
in
g
li
n
k
e
d
o
p
e
n
d
a
ta t
e
c
h
n
o
lo
g
y
.
K
ey
w
o
r
d
s
:
C
r
o
s
s
-
d
o
m
ain
r
ec
o
m
m
en
d
er
s
y
s
tem
s
Gr
o
u
p
r
ec
o
m
m
e
n
d
er
s
y
s
tem
L
in
k
ed
o
p
en
d
ata
Sem
an
tic
web
Sp
ar
s
ity
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
o
s
m
am
alm
i M
at
Naw
i
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Secu
r
ity
an
d
W
eb
T
ec
h
n
o
lo
g
y
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
an
d
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Un
iv
er
s
ity
T
u
n
Hu
s
s
ein
On
n
Ma
lay
s
ia
8
6
4
0
0
B
atu
Pah
at,
J
o
h
o
r
,
Ma
l
ay
s
ia
E
m
ail:
r
o
s
m
am
alm
i@
u
th
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
ec
o
m
m
en
d
e
r
s
y
s
tem
(
R
S)
is
a
b
r
a
n
ch
o
f
in
f
o
r
m
atio
n
r
e
tr
iev
al
an
d
ar
tific
ial
in
tellig
en
ce
.
I
t
is
a
s
u
b
class
o
f
in
f
o
r
m
atio
n
f
ilter
i
n
g
s
y
s
tem
s
th
at
aim
s
to
as
s
is
t
th
e
u
s
er
'
s
s
ea
r
ch
b
eh
av
io
u
r
b
y
s
u
g
g
esti
n
g
item
s
th
at
b
est
m
ee
t
t
h
eir
in
ter
ests
an
d
p
r
e
f
er
en
c
es
[
1
]
.
I
t
is
c
o
n
s
id
er
ed
a
d
ata
f
ilter
in
g
tech
n
iq
u
e.
T
h
e
m
ass
iv
e
g
r
o
wth
o
f
d
ata
an
d
i
n
f
o
r
m
atio
n
is
in
ex
tr
icab
ly
tied
t
o
th
e
2
1
st
ce
n
tu
r
y
'
s
r
ap
id
tech
n
o
lo
g
ical
ad
v
a
n
ce
m
en
ts
in
in
f
o
r
m
atio
n
tech
n
o
l
o
g
y
[
2
]
.
No
wad
ay
s
,
in
f
o
r
m
atio
n
is
o
v
e
r
l
o
ad
ed
o
n
th
e
I
n
ter
n
et
as
we
g
e
n
er
ate
v
ast
am
o
u
n
t
s
o
f
d
iv
er
s
e
d
ata
,
s
u
ch
as im
a
g
e
s
an
d
v
id
eo
s
,
d
aily
[
3
]
.
Ma
n
y
p
eo
p
le
also
wo
u
ld
lik
e
to
r
ed
u
ce
th
eir
s
ea
r
ch
c
o
s
ts
f
o
r
item
s
wh
e
n
th
e
y
wan
t
to
c
ar
r
y
o
u
t
ac
tiv
ities
s
u
ch
as
p
la
n
n
in
g
a
f
a
m
ily
tr
ip
o
r
b
u
y
in
g
b
o
o
k
s
o
n
Am
az
o
n
.
T
h
ey
wo
u
ld
n
ee
d
v
alu
ab
le
r
e
co
m
m
en
d
atio
n
s
to
h
elp
th
em
d
ec
id
e
th
e
least
in
cu
r
r
in
g
co
s
t,
s
u
ch
as
tim
e
an
d
m
o
n
ey
.
He
n
ce
,
R
S c
an
b
e
b
e
n
ef
icial
in
m
ak
in
g
a
p
p
r
o
p
r
iate
d
ec
is
io
n
s
,
esp
ec
ially
with
p
len
ty
o
f
o
n
lin
e
ch
o
ices
th
at
m
ay
lead
to
p
er
p
le
x
ity
.
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
1
8
1
-
1
1
9
4
1182
An
R
S
aim
s
to
m
ak
e
s
u
g
g
esti
o
n
s
to
t
h
e
u
s
er
s
o
n
a
g
iv
e
n
s
o
f
twar
e,
p
latf
o
r
m
,
we
b
s
ite,
o
r
a
p
p
licatio
n
b
ased
o
n
th
eir
h
is
to
r
ical
b
eh
av
io
u
r
s
an
d
p
r
ef
e
r
en
ce
s
.
T
h
e
R
S
r
eq
u
ir
ed
s
o
m
e
u
s
er
an
d
item
d
ata
to
m
ak
e
p
r
ed
ictio
n
s
.
T
h
e
s
y
s
tem
m
u
s
t
u
s
e
th
e
ex
p
licitly
o
r
im
p
lici
tly
co
llected
u
s
er
o
r
item
d
a
ta
to
p
r
o
v
id
e
u
s
e
r
r
ec
o
m
m
en
d
atio
n
s
.
T
h
er
e
ar
e
p
len
ty
o
f
r
ea
l
-
w
o
r
ld
e
x
am
p
les
o
f
u
s
in
g
R
S
o
n
p
latf
o
r
m
s
.
R
ec
o
m
m
en
d
atio
n
s
f
o
r
s
o
n
g
s
o
n
Sp
o
tif
y
o
r
p
r
o
d
u
cts
o
n
Sh
o
p
ee
an
d
L
az
ad
a
ar
e
a
f
ew
ex
am
p
les
o
f
th
e
r
ea
l
-
wo
r
l
d
ap
p
licatio
n
o
f
R
S.
Giv
en
th
e
v
ar
i
o
u
s
n
atu
r
es
o
f
th
e
d
ata,
Yu
et
a
l.
[
4
]
d
esig
n
ed
d
if
f
er
en
t
r
ec
o
m
m
en
d
atio
n
en
g
i
n
es
f
o
r
e
-
co
m
m
er
ce
an
d
m
o
v
ie
d
o
m
ain
s
in
ex
ten
s
iv
e
ex
p
er
im
en
ts
with
Am
az
o
n
an
d
Netf
lix
d
atasets
,
r
esp
e
ctiv
ely
.
Hen
ce
,
th
e
d
esig
n
o
f
th
ese
r
ec
o
m
m
en
d
ati
o
n
en
g
in
es
is
in
f
l
u
en
ce
d
b
y
th
e
n
atu
r
e
o
f
th
e
ac
ce
s
s
ib
le
d
ata
an
d
th
e
d
o
m
ain
.
Fo
r
in
s
tan
ce
,
Netf
lix
u
s
e
r
s
r
ate
th
e
m
o
v
ies
th
ey
ch
o
o
s
e
o
n
a
s
ca
le
o
f
1
to
5
af
ter
th
ey
watc
h
th
em
.
I
t
ca
n
b
e
co
n
v
er
ted
in
to
a
u
s
er
-
item
r
atin
g
m
atr
i
x
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
in
g
a
n
d
p
r
ed
ictio
n
.
T
h
e
r
o
ws
o
f
th
e
m
atr
ix
r
e
p
r
esen
t
a
co
llectio
n
o
f
u
s
er
s
,
wh
ile
th
e
co
lu
m
n
s
o
f
th
e
m
atr
i
x
r
ep
r
ese
n
t
a
co
llectio
n
o
f
item
s
.
T
h
is
d
ata
co
llectio
n
will
h
elp
r
ec
o
r
d
th
e
i
n
ter
ac
tio
n
b
etwe
en
th
e
item
s
an
d
u
s
er
s
.
Alth
o
u
g
h
R
S
ar
e
wid
ely
u
s
ed
t
o
r
ed
u
ce
d
ata
o
v
e
r
lo
ad
b
y
m
ak
in
g
r
ec
o
m
m
en
d
atio
n
s
b
ased
o
n
r
elev
an
t
h
is
to
r
ical
d
ata
in
v
ar
io
u
s
ap
p
licatio
n
s
,
th
ey
a
ls
o
h
av
e
d
r
aw
b
ac
k
s
.
Data
s
p
ar
s
ity
a
n
d
c
o
ld
-
s
tar
t
is
s
u
es
ar
e
th
e
f
u
n
d
am
e
n
tal
p
r
o
b
lem
s
in
RS
s
[
5
]
.
T
h
is
f
ac
t
was
s
u
p
p
o
r
ted
b
y
B
eh
er
a
a
n
d
Nain
[
6
]
,
wh
o
s
tate
th
at
th
e
r
ec
o
m
m
en
d
er
en
v
ir
o
n
m
en
t
al
way
s
s
u
f
f
er
s
f
r
o
m
m
an
y
is
s
u
es,
in
clu
d
in
g
d
ata
s
p
ar
s
ity
an
d
s
ca
lab
ilit
y
,
th
at
s
ev
er
ely
af
f
ec
t
th
e
ac
cu
r
ac
y
o
f
item
r
ec
o
m
m
en
d
atio
n
s
.
T
h
is
is
b
ec
au
s
e
th
e
u
s
er
s
o
n
ly
in
ter
ac
t
with
a
tin
y
p
o
r
tio
n
o
f
th
e
item
s
in
t
h
e
s
p
ec
if
ic
ap
p
licatio
n
d
o
m
ain
,
wh
ich
c
au
s
es
a
s
p
ar
s
ity
p
r
o
b
lem
[
7
]
.
Du
e
t
o
m
o
s
t o
f
t
h
e
g
i
v
en
u
s
er
-
item
m
atr
ices
b
ein
g
s
p
a
r
s
e,
th
e
R
S
s
tr
u
g
g
les
to
m
ak
e
r
ec
o
m
m
en
d
atio
n
s
ef
f
icien
tly
with
o
u
t
co
m
p
le
te
in
f
o
r
m
atio
n
.
Data
s
p
ar
s
ity
is
a
p
r
o
b
lem
th
at
af
f
ec
ts
r
ec
o
m
m
en
d
atio
n
,
an
d
it
is
p
ar
ticu
lar
ly
s
ev
er
e
f
o
r
r
ec
en
tly
r
elea
s
ed
s
y
s
tem
s
th
at
h
a
v
e
n
o
t
h
ad
th
e
tim
e
to
g
at
h
er
e
n
o
u
g
h
d
ata
[
8
]
.
T
h
is
co
m
es
o
u
t w
ith
an
o
th
er
s
er
io
u
s
RS
p
r
o
b
lem
:
th
e
co
ld
-
s
tar
t
i
s
s
u
e
.
I
n
r
e
c
e
n
t
y
e
a
r
s
,
c
r
o
s
s
-
d
o
m
a
i
n
r
e
c
o
m
m
e
n
d
e
r
s
y
s
t
e
m
s
(
C
DR
S
)
a
n
d
R
S
wi
t
h
l
i
n
k
e
d
o
p
e
n
d
a
t
a
t
e
c
h
n
o
l
o
g
y
w
e
r
e
i
n
i
t
i
a
t
e
d
t
o
a
d
d
r
e
s
s
t
h
e
i
s
s
u
e
o
f
d
a
t
a
s
p
a
r
s
i
t
y
i
n
R
S
.
T
h
e
C
DR
S
h
a
s
c
o
m
e
t
o
t
h
e
f
o
r
e
f
r
o
n
t
i
n
r
e
c
e
n
t
y
e
a
r
s
,
a
n
d
r
e
s
e
a
r
c
h
e
r
s
h
a
v
e
b
e
g
u
n
c
o
n
t
r
i
b
u
t
i
n
g
d
i
v
e
r
s
e
p
e
r
s
p
e
c
ti
v
e
s
.
T
h
e
s
e
s
y
s
t
e
m
s
t
r
a
n
s
f
e
r
k
n
o
w
l
e
d
g
e
f
r
o
m
a
d
e
n
s
e
d
a
t
a
s
o
u
r
c
e
d
o
m
a
i
n
t
o
a
s
p
a
r
s
e
d
at
a
ta
r
g
e
t
d
o
m
a
i
n
[
9
]
.
Acc
o
r
d
in
g
to
Ma
s
th
o
f
f
[
1
0
]
,
t
h
er
e
ar
e
n
u
m
er
o
u
s
s
itu
atio
n
s
wh
er
e
ad
ap
tin
g
t
o
a
g
r
o
u
p
r
at
h
er
th
an
an
in
d
iv
id
u
al
is
n
ec
ess
ar
y
.
Fo
r
in
s
tan
ce
,
ch
o
o
s
in
g
b
ac
k
g
r
o
u
n
d
m
u
s
ic
f
o
r
a
f
itn
ess
ce
n
ter
th
at
is
ap
p
r
o
p
r
iate
f
o
r
a
g
r
o
u
p
o
f
p
eo
p
le
ex
e
r
cisi
n
g
at
a
s
p
ec
if
ic
tim
e,
s
u
g
g
esti
n
g
a
s
h
o
w
f
o
r
a
g
r
o
u
p
to
watc
h
o
n
telev
is
io
n
,
an
d
ass
is
tin
g
a
g
r
o
u
p
i
n
r
e
ac
h
in
g
a
co
n
s
en
s
u
s
o
n
th
e
q
u
alities
o
f
to
u
r
is
t
attr
ac
tio
n
s
th
ey
wo
u
ld
lik
e
f
r
o
m
a
p
lan
n
e
d
jo
in
t
v
ac
atio
n
.
T
h
e
im
p
lem
en
tatio
n
o
f
g
r
o
u
p
r
ec
o
m
m
en
d
atio
n
is
b
ased
o
n
u
s
er
-
s
p
ec
if
ic
r
ec
o
m
m
en
d
atio
n
p
a
r
ad
ig
m
s
[
1
1
]
.
As
a
r
esu
lt,
if
a
p
r
o
b
lem
ar
is
es
in
R
S,
th
e
g
r
o
u
p
r
ec
o
m
m
en
d
er
s
y
s
tem
(
GR
S)
will
u
n
d
o
u
b
te
d
ly
e
x
p
er
ien
ce
th
e
s
am
e
is
s
u
e.
W
e
d
is
co
v
er
ed
v
ar
io
u
s
tech
n
i
q
u
es
u
tili
ze
d
to
s
o
lv
e
th
e
d
ata
s
p
ar
s
ity
is
s
u
e
in
R
S.
C
r
o
s
s
-
d
o
m
ain
[
1
2
]
–
[
1
6
]
,
lin
k
ed
o
p
e
n
d
ata
(
L
OD)
[
1
7
]
–
[
1
9
]
,
n
e
u
r
al
n
etwo
r
k
[
6
]
,
[
2
0
]
,
[
2
1
]
,
an
d
h
y
b
r
id
f
ilter
in
g
[
2
2
]
,
ar
e
a
f
ew
ex
am
p
les.
Similar
ly
,
s
o
m
e
GR
S
r
esear
ch
em
p
lo
y
ed
th
ese
tech
n
iq
u
es,
in
clu
d
in
g
th
e
cr
o
s
s
-
d
o
m
ain
ap
p
r
o
ac
h
b
y
R
ich
a
an
d
B
ed
i
[
2
3
]
an
d
L
ian
g
et
a
l.
[
2
4
]
,
wh
ile
th
e
m
eth
o
d
o
f
u
tili
zin
g
L
OD
tech
n
o
lo
g
y
in
GR
S
b
y
Naw
i
et
a
l.
[
2
5
]
.
W
e
h
av
e
n
o
t
y
et
d
is
co
v
er
ed
a
s
tu
d
y
t
h
at
em
p
lo
y
s
th
e
in
teg
r
atio
n
o
f
b
o
th
th
e
cr
o
s
s
-
d
o
m
ain
a
n
d
L
OD
tech
n
iq
u
es in
GR
S,
ev
en
th
o
u
g
h
s
ev
er
al
s
tu
d
ies,
s
u
ch
as th
e
s
tu
d
y
b
y
Nata
r
ajan
et
a
l.
[
2
6
]
an
d
J
ay
ar
atn
e
[
2
7
]
,
u
s
ed
th
e
in
te
g
r
atio
n
o
f
b
o
th
ap
p
r
o
ac
h
es in
i
n
d
iv
id
u
al
R
S.
I
n
th
is
p
ap
er
,
b
esid
es
r
ev
iewin
g
an
d
ex
am
in
i
n
g
th
e
cr
o
s
s
-
d
o
m
ain
ap
p
r
o
a
ch
alo
n
e
in
in
d
iv
i
d
u
al
R
S
an
d
GR
S,
we
also
f
o
cu
s
o
n
ex
am
in
in
g
th
e
C
DR
S
b
y
lev
e
r
ag
in
g
th
e
L
OD
in
b
o
th
asp
ec
ts
o
f
th
e
ap
p
licatio
n
.
T
h
u
s
,
o
u
r
m
ain
m
o
tiv
atio
n
s
a
n
d
p
u
r
p
o
s
es
f
o
r
t
h
is
wo
r
k
ar
e
as
f
o
llo
ws:
(
i)
to
d
is
cu
s
s
th
e
v
iewp
o
in
t
s
u
s
in
g
co
m
p
ar
ativ
e
an
aly
s
is
o
n
v
a
r
io
u
s
c
r
o
s
s
-
d
o
m
ain
alg
o
r
ith
m
s
an
d
tech
n
iq
u
es
f
o
r
i
n
d
iv
id
u
al
R
S
with
an
d
w
ith
o
u
t
le
v
er
ag
in
g
L
OD,
(
ii)
to
d
is
cu
s
s
th
e
im
p
ac
ts
o
f
L
OD
tech
n
o
lo
g
y
an
d
cr
o
s
s
-
d
o
m
ain
ap
p
r
o
ac
h
es in
in
d
iv
id
u
al
R
S a
n
d
GR
S,
an
d
(
iii)
to
id
en
tify
th
e
p
o
s
s
ib
ilit
y
o
f
th
e
f
u
tu
r
e
d
ir
ec
tio
n
o
f
C
DR
S
f
o
r
g
r
o
u
p
s
b
y
e
x
am
in
i
n
g
th
e
p
o
ten
tial
an
d
ex
is
tin
g
ef
f
icac
y
o
f
th
ese
two
m
eth
o
d
s
in
GR
S.
2.
RE
L
AT
E
D
S
T
UDY
Kh
an
et
a
l.
[
2
8
]
r
e
v
iewe
d
C
DR
S
b
u
t
m
er
ely
d
is
cu
s
s
ed
a
s
m
all
p
o
r
tio
n
r
e
g
ar
d
in
g
th
e
m
eth
o
d
s
o
f
th
e
L
OD
an
d
its
in
teg
r
atio
n
with
cr
o
s
s
-
d
o
m
ain
in
in
d
iv
i
d
u
al
R
S.
Hen
ce
,
we
aim
to
ex
am
i
n
e
th
e
C
DR
S
m
o
r
e,
f
o
cu
s
in
g
o
n
L
OD
tech
n
o
lo
g
y
an
d
its
u
tili
za
tio
n
with
th
e
cr
o
s
s
-
d
o
m
ain
ap
p
r
o
ac
h
.
On
e
o
f
o
u
r
n
o
tab
le
f
in
d
i
n
g
s
in
th
is
p
a
p
er
is
a
p
o
te
n
tial
g
ap
b
etwe
en
t
h
e
ex
is
tin
g
s
tu
d
ies
an
d
th
e
u
tili
za
tio
n
o
f
th
e
c
r
o
s
s
-
d
o
m
ain
a
n
d
L
OD
m
eth
o
d
s
th
at
m
ay
b
e
ap
p
licab
l
e
in
GR
S.
T
h
is
s
ec
tio
n
will d
is
cu
s
s
th
e
b
asic k
n
o
wled
g
e
o
f
th
e
cr
itical
co
n
ce
p
ts
o
f
in
d
iv
i
d
u
al
R
S,
GR
S,
C
D
R
S
,
a
n
d
L
OD
tech
n
o
lo
g
y
.
2
.
1
.
I
nd
iv
idu
a
l
re
co
m
m
ende
r
s
y
s
t
em
T
h
er
e
ar
e
at
least
th
r
ee
m
ain
way
s
th
at
lear
n
in
g
alg
o
r
ith
m
s
ca
n
b
e
u
s
ed
in
th
e
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
.
T
h
ese
th
r
ee
ap
p
r
o
ac
h
es
—
co
llab
o
r
ativ
e
f
ilter
in
g
(
C
F),
co
n
te
n
t
-
b
ased
f
ilter
in
g
,
a
n
d
h
y
b
r
id
f
ilter
in
g
—
ca
n
also
b
e
u
s
ed
in
GR
S.
All th
e
s
tr
ateg
ies ar
e
u
s
ed
o
n
v
ar
io
u
s
p
latf
o
r
m
s
,
ea
ch
with
ad
v
an
tag
es a
n
d
d
is
ad
v
an
tag
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
r
ev
iew
o
f th
e
imp
a
cts o
f lin
ke
d
o
p
e
n
d
a
t
a
o
n
cro
s
s
-
d
o
ma
in
r
ec
o
mme
n
d
er sys
tems …
(
Y
u
i Ch
ee
X
u
a
n
)
1183
T
h
e
r
ec
o
m
m
e
n
d
atio
n
s
in
C
F
ar
e
b
ased
o
n
s
im
ilar
u
s
er
s
o
r
s
im
ilar
item
s
,
an
d
th
is
m
eth
o
d
tr
ad
itio
n
ally
u
s
es
th
e
co
n
ce
p
t
o
f
m
atr
ix
f
ac
to
r
izatio
n
(
MF)
,
wh
er
e
a
m
atr
ix
co
n
tain
s
u
s
er
s
,
item
s
,
an
d
t
h
e
r
atin
g
s
p
r
o
v
i
d
ed
b
y
th
e
u
s
er
s
f
o
r
v
ar
io
u
s
item
s
.
Acc
o
r
d
in
g
to
Felf
er
n
ig
et
a
l.
[
2
9
]
,
a
u
s
er
-
item
r
atin
g
m
at
r
ix
i
d
en
tifi
es
h
o
w
m
u
c
h
u
s
er
s
en
jo
y
a
p
ar
ticu
la
r
item
.
A
r
ec
o
m
m
en
d
er
alg
o
r
ith
m
u
s
es
r
atin
g
p
r
ed
ictio
n
s
to
e
v
alu
ate
h
o
w
m
u
c
h
co
n
s
u
m
er
s
wan
t
a
p
r
o
d
u
ct
th
e
y
h
av
e
y
et
to
co
n
s
u
m
e
o
r
r
ate.
I
n
C
F
R
S,
th
e
k
-
n
ea
r
est
n
eig
h
b
o
r
s
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
is
u
tili
ze
d
.
T
h
is
alg
o
r
i
th
m
an
ticip
ates
an
d
ex
tr
a
p
o
l
ates
u
n
k
n
o
w
n
u
s
er
’
s
r
atin
g
s
b
a
s
ed
o
n
u
s
er
o
r
item
s
im
ilar
ities
.
Fo
r
in
s
tan
ce
,
if
t
wo
u
s
er
s
th
at
co
n
s
u
m
e
s
im
ila
r
item
s
ar
e
id
en
tifie
d
,
t
h
e
c
o
llab
o
r
ativ
e
R
S
will
s
u
g
g
est
to
th
e
s
ec
o
n
d
u
s
er
a
n
ew
p
r
o
d
u
ct
t
h
at
th
ey
h
a
v
e
n
o
t
y
et
co
n
s
u
m
e
d
b
ased
o
n
t
h
e
h
i
s
to
r
ical
b
eh
av
io
r
o
f
th
e
f
ir
s
t
u
s
er
an
d
v
ice
v
er
s
a.
I
n
th
is
in
s
tan
ce
,
th
e
s
ec
o
n
d
u
s
er
will
b
e
ad
v
is
ed
to
p
u
r
ch
ase
th
e
ad
d
itio
n
al
p
r
o
d
u
ct
th
e
f
ir
s
t u
s
er
co
n
s
u
m
e
d
.
Ho
wev
er
,
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
in
co
n
ten
t
-
b
ased
f
ilter
in
g
ca
n
p
r
o
v
id
e
r
ec
o
m
m
en
d
atio
n
s
with
o
u
t
r
eq
u
ir
in
g
t
h
e
in
ter
ac
ti
o
n
o
f
u
s
er
s
an
d
item
s
.
I
t
is
s
im
p
ler
to
s
ca
le
th
e
m
o
d
el
b
ec
a
u
s
e
it
s
im
p
ly
h
as
to
k
n
o
w
t
h
e
u
s
er
'
s
in
ter
ests
.
T
h
e
co
n
ten
t
-
b
ased
f
ilter
in
g
m
eth
o
d
r
ep
r
esen
ts
th
e
item
s
as
k
e
y
wo
r
d
s
o
r
d
escr
ip
tio
n
s
.
B
en
d
o
u
ch
et
a
l.
[
3
0
]
ex
tr
ac
ted
o
th
er
s
em
an
tic
f
ea
tu
r
es
f
r
o
m
s
ev
er
al
item
d
escr
ip
tio
n
s
f
o
c
u
s
in
g
o
n
tex
tu
al
an
d
v
is
u
al
in
f
o
r
m
atio
n
in
co
n
ten
t
-
b
ased
R
S
to
p
r
o
v
id
e
b
etter
r
ec
o
m
m
e
n
d
atio
n
s
.
Nev
e
r
th
e
less
,
th
e
m
o
d
el
is
in
ca
p
ab
le
o
f
r
ec
o
m
m
en
d
i
n
g
a
n
y
th
in
g
o
u
ts
id
e
th
e
u
s
er
s
’
ar
ea
o
f
in
ter
est to
th
em
.
I
t c
an
n
o
t id
en
tify
p
r
e
f
er
en
ce
s
o
r
m
ak
e
r
ec
o
m
m
e
n
d
atio
n
s
f
o
r
d
if
f
er
en
t
k
ey
wo
r
d
s
.
Usi
n
g
a
co
n
ten
t
-
b
ased
f
ilter
in
g
alg
o
r
ith
m
,
th
e
RS
p
r
ed
icts
an
d
s
u
g
g
ests
to
u
s
er
s
th
e
item
s
th
at
ar
e
clo
s
e
in
co
n
ten
t
th
at
th
ey
h
av
e
p
r
e
v
io
u
s
ly
en
jo
y
e
d
o
r
th
at
m
atch
th
eir
in
ter
ests
.
Acc
o
r
d
in
g
to
Ag
g
a
r
wal
[
3
1
]
,
tr
ai
n
in
g
d
ata
g
en
e
r
ates
a
u
s
er
-
s
p
ec
if
ic
class
if
ic
atio
n
o
r
r
e
g
r
ess
io
n
m
o
d
elin
g
is
s
u
e
f
r
o
m
th
e
ite
m
d
escr
ip
tio
n
s
in
th
e
co
n
ten
t
-
b
ased
m
eth
o
d
lab
eled
with
r
atin
g
s
.
T
h
e
tr
ain
in
g
m
ater
ials
f
o
r
ea
ch
u
s
er
ar
e
in
ac
co
r
d
an
ce
with
th
e
d
escr
ip
tio
n
s
o
f
t
h
e
p
r
o
d
u
cts
th
e
y
h
a
v
e
p
u
r
ch
ased
o
r
r
ated
.
T
h
is
co
n
ten
t
-
b
ased
f
ilter
in
g
i
s
ap
p
r
o
p
r
iate
f
o
r
th
e
RS
f
o
r
r
ec
o
m
m
en
d
atio
n
s
tied
to
p
er
s
o
n
al
in
ter
ests
,
lik
e
r
ec
o
m
m
en
d
in
g
p
o
liti
ca
lly
r
elev
an
t p
u
b
licatio
n
s
.
An
o
th
e
r
illu
s
tr
atio
n
wo
u
ld
b
e
if
s
o
m
eo
n
e
i
s
in
ter
ested
in
d
ata
s
cien
ce
an
d
wo
u
ld
lik
e
th
e
r
ec
o
m
m
en
d
e
d
in
f
o
r
m
atio
n
ab
o
u
t
d
ata
s
cien
ce
,
an
aly
tics
,
an
d
a
r
t
if
icial
in
tellig
en
ce
.
I
n
a
n
u
ts
h
ell,
th
e
alg
o
r
ith
m
in
th
e
co
n
ten
t
-
b
ased
f
ilter
in
g
s
tr
ateg
y
is
b
ased
o
n
th
e
co
n
ten
ts
o
f
th
in
g
s
.
Ho
we
v
er
,
th
e
alg
o
r
ith
m
in
t
h
e
co
llab
o
r
ativ
e
f
ilter
in
g
ap
p
r
o
ac
h
co
n
s
id
er
s
th
e
r
elatio
n
s
h
ip
b
e
twee
n
th
e
u
s
er
an
d
th
e
item
.
I
t
ca
n
b
e
ch
allen
g
in
g
to
f
o
r
ec
ast
an
d
g
iv
e
th
e
u
s
er
b
etter
r
ec
o
m
m
en
d
atio
n
s
wh
en
b
o
th
m
eth
o
d
o
lo
g
ies
f
o
r
r
ec
o
m
m
e
n
d
atio
n
s
y
s
tem
s
h
av
e
s
o
m
e
d
r
a
wb
ac
k
s
.
I
n
tr
o
d
u
cin
g
h
y
b
r
id
s
y
s
tem
s
th
er
eb
y
a
d
d
r
ess
es
th
e
f
u
n
d
am
e
n
tal
d
is
ad
v
an
tag
es
o
f
th
ese
two
ap
p
r
o
ac
h
es.
T
h
e
s
e
h
y
b
r
id
s
y
s
tem
s
co
m
b
in
e
th
e
ad
v
an
tag
es
o
f
co
llab
o
r
ativ
e
f
ilter
in
g
a
n
d
c
o
n
ten
t
-
b
ased
f
ilter
in
g
to
cr
ea
te
a
s
y
s
tem
th
at
co
m
b
in
es
th
e
b
est
o
f
b
o
th
w
o
r
ld
s
.
Utilizin
g
h
y
b
r
i
d
s
y
s
tem
s
en
h
an
ce
s
th
e
q
u
ality
o
f
r
ec
o
m
m
en
d
atio
n
s
.
C
o
m
p
ar
ed
to
c
o
llab
o
r
ativ
e
f
ilter
in
g
o
r
co
n
ten
t
-
b
ased
a
p
p
r
o
ac
h
es,
th
e
s
e
h
y
b
r
id
s
y
s
tem
s
ar
e
m
o
r
e
r
eliab
le
wh
en
d
ep
l
o
y
ed
o
n
we
b
s
ites
o
r
p
latf
o
r
m
s
.
T
h
e
m
ajo
r
ity
o
f
m
o
d
er
n
web
s
ites
an
d
p
latf
o
r
m
s
u
s
e
h
y
b
r
i
d
RS
s.
2
.
2
.
G
ro
up
re
co
mm
ender
s
y
s
t
em
T
h
e
n
u
m
b
er
o
f
g
r
o
u
p
ac
tiv
ities
av
ailab
le
o
n
th
e
web
h
as
led
to
an
i
n
cr
ea
s
e
in
r
esear
ch
o
n
th
e
GR
S
in
r
ec
en
t
y
ea
r
s
.
GR
S
is
ca
p
ab
le
o
f
s
u
g
g
esti
n
g
item
s
o
r
ac
tiv
iti
es
to
g
r
o
u
p
s
o
f
in
d
iv
id
u
als
wh
o
s
h
ar
e
a
c
o
m
m
o
n
g
o
al
o
r
in
ter
est.
Var
io
u
s
m
eth
o
d
s
h
av
e
b
ee
n
d
e
v
e
lo
p
e
d
to
m
er
g
e
an
d
alig
n
th
e
in
d
iv
id
u
al
p
r
ef
er
en
ce
s
o
f
u
s
er
s
as
a
g
r
o
u
p
to
o
f
f
er
s
atis
f
ac
to
r
y
r
ec
o
m
m
en
d
atio
n
s
.
T
h
e
g
r
o
u
p
'
s
p
r
ef
er
en
ce
s
ar
e
m
o
d
elled
to
cr
ea
te
a
g
r
o
u
p
p
r
o
f
ile,
wh
ic
h
is
g
r
ea
tly
in
f
l
u
e
n
ce
d
b
y
ea
ch
u
s
er
'
s
p
r
ef
er
en
ce
s
an
d
th
e
g
r
o
u
p
'
s
co
m
p
o
s
itio
n
[
3
2
]
.
T
h
e
GR
S
co
m
p
r
is
es
two
s
tag
es.
T
h
e
cr
ea
tio
n
o
f
t
h
e
g
r
o
u
p
p
r
o
f
ile
co
m
es
f
ir
s
t,
f
o
llo
wed
b
y
th
e
r
ec
o
m
m
en
d
atio
n
o
f
p
r
o
d
u
cts
t
o
th
e
g
r
o
u
p
o
f
co
n
s
u
m
er
s
.
T
h
er
e
ar
e
two
m
ajo
r
g
r
o
u
p
s
in
GR
Ss
,
n
am
ely
s
tab
le
g
r
o
u
p
s
an
d
r
an
d
o
m
g
r
o
u
p
s
,
f
r
o
m
th
e
co
n
s
tr
u
ctio
n
o
f
th
e
g
r
o
u
p
p
r
o
f
ile'
s
s
tan
d
p
o
in
t,
r
eg
a
r
d
less
o
f
th
e
s
y
s
tem
d
o
m
ain
[
3
3
]
.
Acc
o
r
d
in
g
to
W
an
g
et
a
l.
[
3
4
]
,
m
em
b
er
s
o
f
s
tab
le
g
r
o
u
p
s
h
av
e
th
e
r
ig
h
t
to
a
d
d
th
eir
p
r
e
f
er
en
ce
s
to
th
e
g
r
o
u
p
p
r
o
f
ile,
an
d
o
v
e
r
tim
e,
th
e
g
r
o
u
p
'
s
p
r
ef
er
en
ce
s
m
ay
b
ec
o
m
e
ce
n
tr
alize
d
.
I
n
c
o
n
tr
ast,
th
e
r
an
d
o
m
g
r
o
u
p
s
h
av
e
n
o
o
p
p
o
r
tu
n
ity
to
ex
p
r
ess
th
eir
o
p
i
n
io
n
s
an
d
h
a
v
e
s
tr
o
n
g
ly
co
n
tr
a
d
icto
r
y
g
r
o
u
p
p
r
ef
e
r
en
ce
s
[
3
4
]
.
As
p
r
ev
io
u
s
ly
s
tated
,
th
e
GR
S
an
d
in
d
i
v
id
u
al
R
S
f
ac
e
s
o
m
e
d
if
f
icu
lties
.
T
h
e
f
ew
a
n
d
in
s
u
f
f
i
cien
t
u
s
er
-
item
r
atin
g
s
r
esu
lt in
th
e
GR
S
an
d
in
d
iv
id
u
al
R
S p
r
o
b
lem
s
.
T
h
is
in
co
m
p
leten
ess
g
iv
es r
is
e
to
th
e
d
ata
s
p
ar
s
ity
is
s
u
e.
Data
s
p
a
r
s
i
ty
is
s
tated
b
y
L
ian
g
et
a
l.
[
3
2
]
as
an
o
th
e
r
p
r
o
b
lem
atic
is
s
u
e
in
GR
S.
T
h
e
d
ata
s
p
ar
s
ity
is
s
u
e
in
GR
S
is
wo
r
s
e
b
ec
au
s
e
th
e
h
is
to
r
ical
r
ec
o
r
d
s
o
f
g
r
o
u
p
s
ar
e
s
ig
n
if
ica
n
tly
s
m
aller
th
an
th
o
s
e
o
f
in
d
iv
id
u
als.
T
h
e
q
u
ality
o
f
r
ec
o
m
m
en
d
atio
n
s
o
f
f
er
e
d
to
a
g
r
o
u
p
s
u
f
f
e
r
s
f
r
o
m
a
lack
o
f
d
ata.
I
t
h
ap
p
e
n
s
d
u
e
t
o
in
ef
f
ec
tiv
e
g
r
o
u
p
cr
ea
tio
n
,
wh
ich
f
r
eq
u
e
n
tly
in
clu
d
es p
eo
p
le
with
s
p
ar
s
e
u
s
er
p
r
o
f
iles
.
T
h
er
e
a
r
e
s
o
m
e
r
elate
d
s
tu
d
ies
o
n
GR
S o
th
er
th
an
L
OD
tech
n
o
lo
g
y
an
d
c
r
o
s
s
-
d
o
m
ain
ap
p
r
o
ac
h
,
s
u
c
h
as
th
e
wo
r
k
s
d
o
n
e
b
y
Allaf
an
d
Kah
an
i
[
3
5
]
,
Ali
et
a
l.
[
3
6
]
,
Villav
icen
cio
et
a
l.
[
3
7
]
an
d
De
Pes
s
em
ier
et
a
l.
[
3
8
]
.
T
h
er
e
ar
e
also
s
o
m
e
r
ela
ted
s
tu
d
ies
o
n
C
DR
S
f
o
r
g
r
o
u
p
s
with
d
iv
er
s
e
alg
o
r
ith
m
s
to
tack
le
th
e
p
r
o
b
lem
s
o
f
GR
S,
s
u
ch
as th
e
em
p
ir
ical
s
tu
d
y
b
y
Su
n
et
a
l.
[
3
9
]
.
2
.
3
.
Cro
s
s
-
do
ma
in re
co
mm
e
nd
er
s
y
s
t
em
C
DR
S
was
d
ev
elo
p
ed
to
ad
d
r
e
s
s
th
e
is
s
u
e
o
f
d
ata
s
p
ar
s
ity
.
R
esear
ch
er
s
h
av
e
o
f
f
er
ed
v
ar
i
o
u
s
o
p
in
io
n
s
as
th
e
C
DR
S
h
as
g
ain
ed
p
r
o
m
in
en
ce
in
r
ec
en
t
y
ea
r
s
.
Acc
o
r
d
in
g
to
L
i
an
d
T
u
z
h
ilin
[
4
0
]
,
th
e
m
o
s
t
co
m
m
o
n
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
1
8
1
-
1
1
9
4
1184
C
DR
S
ar
e
ex
ten
s
io
n
s
o
f
s
in
g
le
-
d
o
m
ain
r
ec
o
m
m
e
n
d
atio
n
m
o
d
els.
T
h
e
C
DR
S
tr
an
s
f
er
s
k
n
o
wl
ed
g
e
f
r
o
m
a
s
o
u
r
ce
d
o
m
ain
with
a
lar
g
e
am
o
u
n
t
o
f
d
ata
to
a
d
esti
n
atio
n
d
o
m
ain
with
lim
ited
d
ata
[
9
]
.
C
DR
S
is
s
u
p
p
o
s
ed
to
s
u
p
p
o
r
t
en
h
an
cin
g
th
e
p
e
r
f
o
r
m
an
ce
o
f
r
ec
o
m
m
en
d
atio
n
s
f
o
r
th
e
tar
g
e
t d
o
m
ain
.
Acc
o
r
d
in
g
to
Z
h
u
et
a
l.
[
4
1
]
,
C
DR
S
h
ad
d
if
f
er
e
n
t
s
ce
n
ar
io
s
f
o
r
t
h
e
r
ec
o
m
m
en
d
atio
n
s
in
th
e
tar
g
et
d
o
m
ain
,
as
s
h
o
wn
in
Fig
u
r
e
1
,
in
clu
d
in
g
s
in
g
le
-
ta
r
g
et,
d
u
al
-
tar
g
et,
m
u
lti
-
tar
g
et,
an
d
m
u
lti
-
d
o
m
ain
.
I
n
th
e
s
ce
n
ar
io
o
f
two
d
o
m
ain
s
,
th
e
co
n
v
en
tio
n
al
s
in
g
le
-
tar
g
et
s
o
l
ely
f
o
c
u
s
es
o
n
allev
iatin
g
a
s
p
ar
s
e
tar
g
et
d
o
m
ain
th
at
a
im
s
to
p
r
o
v
id
e
r
ec
o
m
m
e
n
d
atio
n
s
in
th
at
s
p
ec
if
ic
d
o
m
a
in
,
wh
ile
d
u
al
-
tar
g
et
im
p
r
o
v
es
b
o
th
d
o
m
ain
s
a
n
d
p
r
o
v
id
es
b
etter
r
ec
o
m
m
e
n
d
ati
o
n
s
in
ea
c
h
d
o
m
ain
.
Similar
ly
,
a
m
u
lti
-
tar
g
et
s
ce
n
ar
io
will
b
e
u
s
ed
f
o
r
m
o
r
e
th
an
th
r
ee
d
o
m
ain
s
to
in
cr
ea
s
e
t
h
e
ac
cu
r
ac
y
o
f
ea
c
h
C
DR
S
in
ea
ch
d
o
m
ain
s
im
u
ltan
e
o
u
s
ly
u
s
in
g
th
e
au
x
iliar
y
k
n
o
wled
g
e
ac
r
o
s
s
d
o
m
ain
s
.
Fo
r
m
u
lti
-
d
o
m
ai
n
,
th
e
u
s
er
s
an
d
item
s
o
v
er
lap
ac
r
o
s
s
m
u
ltip
le
d
o
m
ain
s
.
T
h
is
s
ce
n
ar
io
r
ec
o
m
m
en
d
s
a
c
o
llectio
n
o
f
item
s
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
to
a
s
et
o
f
u
s
er
s
in
d
if
f
er
en
t
d
o
m
ain
s
b
y
lev
er
ag
in
g
a
u
x
iliar
y
k
n
o
wled
g
e
ac
r
o
s
s
d
o
m
ain
s
.
T
h
er
e
f
o
r
e,
m
u
lti
-
d
o
m
ain
,
d
u
al
-
tar
g
et,
an
d
m
u
lti
-
tar
g
et
C
DR
S
ar
e
g
en
er
ally
m
o
r
e
s
o
p
h
is
ticated
in
m
o
d
el
d
esig
n
s
an
d
th
eir
p
r
o
ce
s
s
es.
As s
h
o
wn
in
Fig
u
r
e
1
,
cr
o
s
s
-
d
o
m
ain
d
ata
ca
n
b
e
ca
te
g
o
r
ized
f
r
o
m
t
h
r
ee
p
e
r
s
p
ec
tiv
es,
wh
ic
h
ar
e
u
s
er
-
lev
el
r
elev
an
ce
,
item
-
le
v
el
r
e
lev
an
ce
,
a
n
d
co
n
te
n
t
-
lev
el
r
e
lev
an
ce
[
4
1
]
.
I
d
en
tify
i
n
g
t
h
e
r
elev
an
ce
o
f
d
ata
b
etwe
en
d
o
m
ain
s
h
elp
s
tr
an
s
f
er
k
n
o
wled
g
e
to
th
e
ta
r
g
et
d
o
m
ain
.
I
t
ca
n
b
e
b
ased
o
n
th
e
o
v
er
lap
p
i
n
g
o
f
d
ata.
Hen
ce
,
m
ap
p
i
n
g
b
etwe
en
d
o
m
ain
s
with
co
m
m
o
n
f
ea
tu
r
es,
u
s
er
s
,
o
r
item
s
will b
e
m
o
r
e
s
tr
ai
g
h
tf
o
r
war
d
.
Ho
wev
er
,
L
i
an
d
T
u
zh
ilin
[
4
0
]
ar
g
u
ed
th
at
s
o
m
e
m
o
d
els
i
n
C
DR
S
f
ail
to
a
d
eq
u
ately
a
d
d
r
ess
th
e
r
elatio
n
s
h
ip
b
etwe
en
d
if
f
e
r
en
t
d
o
m
ain
s
s
in
ce
th
ey
d
o
n
o
t
s
im
u
ltan
eo
u
s
ly
im
p
r
o
v
e
t
h
e
ef
f
ec
tiv
en
ess
o
f
r
ec
o
m
m
en
d
atio
n
s
in
b
o
t
h
d
o
m
ain
s
,
p
o
s
s
ib
ly
r
estrictin
g
th
e
a
p
p
lica
b
ilit
y
o
f
cr
o
s
s
-
d
o
m
ain
u
s
er
in
ter
ac
tio
n
d
ata.
Gen
er
ally
,
th
e
C
DR
S
s
u
p
p
o
r
ts
en
h
an
cin
g
th
e
ta
r
g
et
d
o
m
ai
n
'
s
p
er
f
o
r
m
an
ce
o
f
r
ec
o
m
m
e
n
d
atio
n
s
.
T
h
er
e
ar
e
n
u
m
er
o
u
s
ap
p
r
o
ac
h
es
to
b
u
ild
in
g
C
DR
S.
T
h
er
e
ar
e
s
o
m
e
r
el
ated
s
tu
d
ies
o
n
C
DR
S
with
d
iv
er
s
e
m
eth
o
d
s
an
d
alg
o
r
it
h
m
s
to
tack
le
t
h
e
p
r
o
b
le
m
s
o
f
in
d
iv
i
d
u
al
R
S
b
ased
o
n
v
ar
io
u
s
ev
alu
atio
n
m
etr
ics
o
n
r
ea
l
-
wo
r
ld
d
o
m
ain
s
an
d
d
atasets
[
4
2
]
–
[
5
4
]
.
T
h
e
co
m
p
ar
ati
ve
an
aly
s
is
r
eg
ar
d
in
g
C
DR
S will b
e
cr
itically
an
aly
ze
d
in
s
ec
tio
n
3
.
Fig
u
r
e
1
.
T
y
p
e
o
f
cr
o
s
s
-
d
o
m
ai
n
RS
2
.
4
.
L
ink
ed
o
pen da
t
a
L
OD
tech
n
o
lo
g
y
is
th
e
f
o
u
n
d
atio
n
f
o
r
cr
e
atin
g
a
k
n
o
wled
g
e
g
r
ap
h
th
at
m
ay
b
e
u
s
ed
in
C
DR
S.
T
h
e
s
em
an
tic
web
is
a
co
r
e.
Hen
ce
,
L
OD
tech
n
o
lo
g
y
is
a
p
a
r
t
o
f
th
e
s
em
an
tic
web
.
L
OD
d
atasets
cr
ea
te
n
ew
d
if
f
icu
lties
an
d
p
r
o
b
lem
s
f
o
r
c
o
m
p
licated
W
eb
ap
p
licatio
n
s
an
d
n
e
x
t
-
g
en
e
r
atio
n
R
Ss
[
5
5
]
.
A
m
ass
iv
e,
d
ec
en
tr
alize
d
k
n
o
wled
g
e
r
ep
o
s
ito
r
y
co
m
p
r
is
es
lin
k
ed
r
eso
u
r
ce
d
escr
ip
tio
n
f
r
am
ewo
r
k
(
R
DF)
s
tatem
en
ts
[
56]
.
Me
t
ad
ata
is
d
escr
ib
ed
an
d
ex
c
h
an
g
ed
u
s
in
g
R
DF
s
tatem
en
t
s
,
allo
win
g
f
o
r
a
s
tan
d
ar
d
ized
d
ata
in
ter
c
h
an
g
e
b
ased
o
n
r
elatio
n
s
h
ip
s
.
Mu
lti
p
le
s
o
u
r
ce
s
o
f
d
ata
ar
e
co
m
b
i
n
ed
u
s
in
g
R
DF.
I
n
ad
d
itio
n
to
p
o
liti
ca
l
an
d
g
eo
g
r
ap
h
ic
d
ata,
th
e
L
OD
clo
u
d
in
clu
d
es
s
tr
u
ctu
r
ed
d
ata
o
n
v
ar
io
u
s
s
u
b
jects,
in
clu
d
in
g
b
io
lo
g
ical
s
cien
ce
s
an
d
m
ed
i
a
(
b
o
o
k
s
an
d
m
o
v
ies).
T
h
e
m
o
s
t
f
r
eq
u
e
n
tly
u
s
ed
way
t
o
ac
ce
s
s
th
ese
d
ata
is
th
r
o
u
g
h
DB
p
ed
ia
,
wh
ich
is
W
ik
ip
ed
ia's
R
D
F
m
ap
p
in
g
an
d
is
wid
ely
ac
k
n
o
wled
g
e
d
as
th
e
ep
icen
ter
o
f
d
ev
elo
p
in
g
web
o
f
d
ata
[
5
6
]
.
Data
m
ap
p
in
g
is
cr
u
cial
in
C
DR
S,
wh
ich
u
s
es
L
OD
tech
n
o
lo
g
y
.
A
s
im
ilar
s
tu
d
y
m
ad
e
u
s
e
o
f
DB
p
ed
ia
an
d
L
OD.
Per
eir
a
[
5
7
]
to
o
k
ad
v
an
tag
e
o
f
L
OD
in
DB
p
ed
ia
to
lo
wer
p
r
ed
ictio
n
er
r
o
r
s
in
C
F R
S,
an
d
th
e
wo
r
k
was p
r
esen
ted
in
th
e
m
aster
'
s
th
esi
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
r
ev
iew
o
f th
e
imp
a
cts o
f lin
ke
d
o
p
e
n
d
a
t
a
o
n
cro
s
s
-
d
o
ma
in
r
ec
o
mme
n
d
er sys
tems …
(
Y
u
i Ch
ee
X
u
a
n
)
1185
T
h
er
e
is
a
lo
t
o
f
in
teg
r
atio
n
o
f
L
OD
tech
n
o
lo
g
y
al
o
n
e
in
in
d
i
v
id
u
al
R
S,
s
u
ch
as
th
e
em
p
ir
ic
al
s
tu
d
y
b
y
Nata
r
ajan
et
a
l.
[
7
]
.
So
m
e
r
el
ated
s
tu
d
ie
s
o
n
in
teg
r
atin
g
L
OD
o
r
s
em
an
tic
an
d
cr
o
s
s
-
d
o
m
ain
ap
p
r
o
ac
h
es
in
i
n
d
i
v
i
d
u
a
l
R
S
,
s
u
c
h
a
s
t
h
e
w
o
r
k
b
y
Z
h
a
n
g
e
t
a
l
.
[
5
8
]
.
H
o
w
e
v
er
,
w
e
c
a
n
f
i
n
d
o
n
l
y
o
n
e
r
e
l
at
e
d
s
t
u
d
y
b
y
N
a
wi
e
t
a
l
.
[
2
5
]
o
n
GR
S
with
L
OD
tech
n
o
lo
g
y
to
tack
le
th
e
p
r
o
b
lem
s
o
f
GR
S
in
tr
o
d
u
cin
g
th
e
in
teg
r
ati
o
n
o
f
L
OD
in
GR
S.
Ho
wev
er
,
t
h
e
in
te
g
r
atio
n
is
wi
th
o
u
t th
e
a
p
p
licatio
n
o
f
a
cr
o
s
s
-
d
o
m
ain
ap
p
r
o
ac
h
.
3.
L
I
NK
E
D
O
P
E
N
DA
T
A
O
N
CRO
SS
-
DO
M
AIN R
E
CO
M
M
E
N
DE
R
SYS
T
E
M
Sectio
n
3
.
1
.
will
co
n
ce
n
tr
ate
o
n
th
e
im
p
ac
ts
o
f
th
e
C
DR
S
m
o
d
el
with
o
u
t
L
OD
tech
n
o
lo
g
y
,
wh
ile
s
ec
tio
n
3
.
2
.
will
f
o
cu
s
o
n
th
e
im
p
ac
ts
o
f
th
e
C
D
R
S
m
o
d
el
u
s
in
g
L
OD
tech
n
o
lo
g
y
.
Sectio
n
3
.
1
.
ex
am
i
n
es
th
ir
teen
ar
ticles o
n
C
DR
S with
o
u
t a
p
p
ly
in
g
L
OD
tech
n
o
lo
g
y
.
W
e
d
is
co
v
e
r
a
n
d
r
ev
iew
f
o
u
r
p
a
p
er
s
co
n
ce
r
n
in
g
th
e
C
DR
S
m
o
d
el
lev
er
ag
i
n
g
L
OD
tech
n
o
lo
g
y
i
n
s
ec
tio
n
3
.
2
.
T
h
e
two
m
en
tio
n
e
d
s
ec
tio
n
s
will
b
e
p
r
esen
ted
with
a
s
u
m
m
ar
ized
tab
le
f
o
r
co
m
p
ar
ativ
e
an
aly
s
is
.
T
h
ese
s
ec
tio
n
s
attem
p
t
to
co
llect
ex
is
tin
g
r
esear
ch
b
y
id
en
ti
f
y
in
g
C
DR
S
o
n
th
e
is
s
u
e,
th
e
m
eth
o
d
ap
p
lied
,
th
e
o
u
tco
m
e,
an
d
th
e
d
o
m
ain
.
V
ar
io
u
s
m
eth
o
d
s
an
d
alg
o
r
ith
m
s
ca
n
b
e
ap
p
lied
to
th
e
cr
o
s
s
-
d
o
m
ain
in
d
iv
id
u
al
RS
to
im
p
r
o
v
e
its
p
er
f
o
r
m
an
ce
o
f
u
s
er
r
ec
o
m
m
en
d
atio
n
s
.
W
e
d
is
co
v
e
r
ed
th
at
L
OD
tech
n
o
lo
g
y
is
o
n
e
o
f
th
e
m
e
th
o
d
s
th
at
ca
n
en
h
a
n
ce
th
e
p
er
f
o
r
m
a
n
ce
o
f
tr
ad
itio
n
al
R
S.
I
n
th
is
s
ec
tio
n
,
we
d
is
cu
s
s
o
u
r
f
in
d
in
g
s
o
n
t
h
e
ex
is
ten
ce
o
f
L
OD
in
C
DR
S
f
o
r
in
d
iv
id
u
als
a
n
d
co
m
p
ar
e
th
e
is
s
u
e,
th
e
m
eth
o
d
ap
p
lied
,
th
e
o
u
tco
m
e,
an
d
th
e
d
o
m
ain
o
f
d
if
f
er
en
t stu
d
ies.
3
.
1
.
Cro
s
s
-
do
m
a
in ind
iv
idu
a
l r
ec
o
mm
ender
s
y
s
t
em
wit
ho
ut
lin
k
ed
o
pen da
t
a
As
s
h
o
wn
in
T
a
b
le
1
,
C
DR
S
ca
n
im
p
lem
e
n
t
a
v
ar
iety
o
f
u
n
i
q
u
e
tech
n
iq
u
es,
s
u
c
h
as
"
g
e
o
m
etr
ic
d
ee
p
lear
n
in
g
(
D
-
GDL
)
with
d
is
cr
im
in
ativ
e
b
asis
"
b
y
Ar
th
u
r
et
a
l.
[
5
9
]
,
"
d
ee
p
g
r
ap
h
m
u
tu
al
lear
n
in
g
(
DGM
L
)
"
b
y
W
an
g
et
a
l.
[
6
0
]
an
d
"
cr
o
s
s
-
d
o
m
ain
co
llab
o
r
ativ
e
r
ec
o
m
m
en
d
atio
n
with
o
u
t
o
v
e
r
lap
p
i
n
g
e
n
titi
es
b
ased
o
n
d
o
m
ain
a
d
ap
tatio
n
(
C
C
R
-
DA)
"
b
y
Z
h
a
n
g
et
a
l.
[
6
1
]
.
T
h
e
o
th
er
s
u
m
m
ar
ies ca
n
b
e
f
o
u
n
d
in
T
ab
le
1
.
Ar
th
u
r
et
a
l.
[
5
9
]
in
tr
o
d
u
ctio
n
o
f
D
-
GDL
with
d
is
cr
im
in
at
iv
e
b
asis
"
f
o
r
C
DR
S
d
em
o
n
s
tr
a
tes
th
at
it
ca
n
p
r
o
v
id
e
ac
cu
r
ate
r
ec
o
m
m
e
n
d
atio
n
s
in
a
way
to
ef
f
icien
tl
y
s
u
p
p
o
r
t
r
ec
o
m
m
en
d
in
g
3
D
o
b
jects,
esp
ec
ially
in
th
e
n
o
n
-
E
u
clid
ea
n
d
o
m
ain
s
(
3
D
v
ir
tu
al
o
b
jects).
T
h
is
s
tu
d
y
was
co
n
d
u
cted
to
p
r
o
p
er
ly
m
an
ag
e
u
s
er
r
ec
o
m
m
en
d
a
tio
n
s
in
s
in
g
le
-
d
o
m
ain
an
d
c
r
o
s
s
-
d
o
m
ain
s
ce
n
a
r
io
s
in
n
o
n
-
E
u
clid
ea
n
d
o
m
ain
s
an
d
ad
d
r
ess
co
ld
-
s
tar
t
an
d
d
ata
s
p
ar
s
ity
co
n
ce
r
n
s
.
T
h
e
s
u
g
g
ested
D
-
GDL
tech
n
iq
u
e
ac
h
iev
es
th
e
b
est
d
ictio
n
ar
y
wh
ile
b
o
o
s
tin
g
th
e
r
ec
o
m
m
e
n
d
ed
s
y
s
tem
s
'
a
b
ilit
y
to
d
is
cr
im
in
ate.
T
o
s
u
c
ce
s
s
f
u
lly
ad
d
r
ess
co
ld
-
s
tar
t
an
d
d
ata
s
p
ar
s
ity
co
n
ce
r
n
s
,
th
is
p
er
m
its
th
e
im
p
l
em
en
tatio
n
o
f
g
e
o
m
etr
ic
DL
r
e
p
r
esen
tatio
n
o
f
th
e
3
D
n
o
n
-
lin
ea
r
f
ea
tu
r
es
in
b
o
th
s
p
ar
s
e
an
d
d
en
s
e
en
v
ir
o
n
m
e
n
t
s
.
Acc
o
r
d
in
g
to
ex
p
er
im
e
n
tal
f
in
d
in
g
s
,
in
co
r
p
o
r
atin
g
g
eo
m
et
r
ic
an
d
k
er
n
el
d
ee
p
lear
n
in
g
(
DL
)
in
to
th
e
d
esig
n
o
f
r
ep
r
esen
tativ
e
s
o
lu
tio
n
s
f
o
r
R
S
n
atu
r
ally
en
h
an
ce
s
p
er
f
o
r
m
an
ce
ac
c
u
r
ac
y
co
m
p
ar
ed
to
o
th
e
r
b
aselin
e
DL
tech
n
iq
u
es.
Du
e
to
p
r
io
r
ap
p
r
o
ac
h
es
t
h
at
p
r
im
ar
ily
s
h
a
r
e
an
d
m
a
p
u
s
er
attr
ib
u
tes
am
o
n
g
d
if
f
er
e
n
t
d
o
m
ain
s
to
tr
an
s
f
er
k
n
o
wled
g
e,
W
an
g
et
a
l.
[
6
0
]
aim
to
ca
p
t
u
r
e
u
s
er
s
'
s
h
ar
ed
in
ter
ests
wh
ile
o
v
er
lo
o
k
in
g
d
o
m
ain
-
s
p
ec
if
ic
p
r
ef
er
en
ce
s
.
T
h
e
au
th
o
r
s
u
s
e
"
m
u
tu
al
r
eg
u
lar
izatio
n
"
tech
n
iq
u
es
to
b
u
ild
th
e
co
m
p
lete
p
r
ef
er
en
ce
th
at
lear
n
ed
f
r
o
m
p
r
o
p
o
s
ed
p
ar
allel
g
r
a
p
h
n
eu
r
al
n
etwo
r
k
s
(
GNN)
r
ec
o
m
m
en
d
atio
n
m
o
d
els,
wh
ich
p
r
o
m
o
te
d
o
m
ain
-
s
p
ec
if
ic
f
ea
tu
r
es
d
is
tin
ct
ac
r
o
s
s
d
o
m
ain
s
wh
ile
s
ta
y
in
g
clo
s
e
to
th
e
d
o
m
ain
-
s
h
ar
ed
f
ea
t
u
r
e
to
en
co
d
e
b
o
th
co
m
m
o
n
a
n
d
s
p
ec
if
ic
u
s
er
p
r
e
f
er
en
ce
s
am
o
n
g
d
if
f
er
en
t
d
o
m
a
in
s
.
E
x
ten
s
iv
e
test
s
o
n
th
e
two
r
ea
l
-
wo
r
ld
d
atasets
lis
ted
in
T
ab
le
1
s
h
o
w
th
e
ef
f
ec
tiv
en
ess
,
in
ter
p
r
etab
ilit
y
,
a
n
d
s
ig
n
if
ican
t
im
p
r
o
v
em
en
ts
o
v
e
r
s
tate
-
of
-
th
e
-
ar
t
m
eth
o
d
s
o
f
th
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
f
o
r
cr
o
s
s
-
d
o
m
ain
r
e
co
m
m
en
d
atio
n
u
tili
zin
g
DG
ML
.
Acc
o
r
d
in
g
to
ex
p
er
im
en
tal
f
in
d
in
g
s
,
th
e
p
e
r
f
o
r
m
a
n
ce
lear
n
ed
f
r
o
m
d
o
m
a
in
-
s
h
ar
ed
d
ata
is
s
u
p
e
r
io
r
to
t
h
e
v
er
s
io
n
lear
n
ed
f
r
o
m
d
ata
f
r
o
m
a
s
in
g
le
u
n
iq
u
e
d
o
m
ai
n
.
Mu
tu
al
r
eg
u
la
r
izatio
n
im
p
r
o
v
es
p
er
f
o
r
m
an
ce
ev
e
n
m
o
r
e
,
illu
s
tr
atin
g
th
e
v
alu
e
o
f
s
h
ar
in
g
an
d
lea
r
n
i
n
g
u
s
er
p
r
ef
er
e
n
ce
s
f
o
r
r
ec
o
m
m
en
d
atio
n
s
ac
r
o
s
s
d
o
m
ain
s
.
On
th
e
o
th
er
h
an
d
,
th
e
d
ev
elo
p
m
en
t
o
f
"
cr
o
s
s
-
d
o
m
ai
n
co
llab
o
r
ativ
e
r
ec
o
m
m
en
d
atio
n
with
o
u
t
o
v
er
lap
p
i
n
g
e
n
titi
es
b
ased
o
n
d
o
m
ai
n
ad
a
p
tatio
n
(
C
C
R
-
D
A)
"
b
y
Z
h
a
n
g
et
a
l.
[
6
1
]
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
u
tp
er
f
o
r
m
s
eig
h
t
n
o
n
-
tr
an
s
f
er
lear
n
i
n
g
an
d
C
DR
S
m
eth
o
d
s
.
T
h
is
s
tu
d
y
g
u
ar
a
n
tee
s
co
n
s
is
ten
cy
wh
e
n
tr
an
s
f
er
r
in
g
k
n
o
wled
g
e
in
cr
o
s
s
-
d
o
m
ain
co
llab
o
r
ativ
e
f
ilter
in
g
RS
s
.
I
n
th
e
p
r
o
p
o
s
ed
C
C
R
-
DA
f
r
am
ewo
r
k
,
th
e
weig
h
ted
co
llectiv
e
m
atr
ix
tr
i
-
f
ac
to
r
izatio
n
f
r
am
ewo
r
k
in
co
r
p
o
r
ates
th
e
m
ax
im
u
m
m
ea
n
d
i
s
cr
ep
an
cy
(
MM
D)
an
d
g
r
ap
h
r
eg
u
lar
izatio
n
ter
m
s
.
Mo
s
t
ex
is
tin
g
cr
o
s
s
-
d
o
m
ain
r
ec
o
m
m
en
d
atio
n
alg
o
r
ith
m
s
r
el
y
o
n
th
e
ass
u
m
p
tio
n
th
at
o
v
er
lap
p
in
g
e
n
titi
es a
r
e
s
h
ar
ed
to
tr
an
s
f
e
r
in
f
o
r
m
atio
n
b
e
twee
n
d
o
m
ain
s
,
b
u
t n
o
t a
ll in
s
t
an
ce
s
s
u
p
p
o
r
t th
is
s
tatem
en
t
[
6
1
]
.
Hen
ce
,
th
ey
i
n
tr
o
d
u
ce
d
th
e
p
r
o
p
o
s
ed
m
eth
o
d
with
o
u
t o
v
e
r
lap
p
in
g
en
titi
es.
T
h
er
e
is
an
in
n
o
v
ativ
e
tech
n
iq
u
e
f
o
r
th
e
m
e
d
ical
d
o
m
ain
b
y
C
h
an
g
et
a
l.
[
6
2
]
in
tr
o
d
u
ctio
n
o
f
"in
f
o
r
m
atio
n
tr
an
s
f
er
f
o
r
m
ed
ical
d
iag
n
o
s
is
(
I
T
MD
)
",
a
s
u
g
g
ested
cr
o
s
s
-
d
o
m
ain
R
S,
th
a
t
o
f
f
er
s
p
h
y
s
ician
s
p
er
s
o
n
alize
d
s
u
g
g
esti
o
n
s
f
o
r
illn
ess
r
is
k
s
.
T
h
e
I
T
MD
o
u
tp
e
r
f
o
r
m
s
f
o
u
r
b
aselin
es
an
d
en
h
a
n
ce
s
th
e
ac
cu
r
ac
y
o
f
d
is
ea
s
e
r
is
k
r
ec
o
m
m
en
d
atio
n
s
in
p
atien
ts
,
to
h
elp
d
o
cto
r
s
m
ak
e
a
f
in
al
m
ed
ical
d
iag
n
o
s
is
wh
en
th
er
e
ar
e
n
o
t
en
o
u
g
h
r
ec
o
r
d
s
,
as
d
em
o
n
s
tr
ated
b
y
ex
p
er
im
e
n
ts
an
d
a
ca
s
e
s
tu
d
y
u
tili
zin
g
r
ea
l
-
wo
r
ld
d
ata.
W
h
en
th
er
e
ar
e
in
s
u
f
f
icien
t
d
iag
n
o
s
tic
r
ec
o
r
d
d
ata
to
tr
ain
a
p
r
ed
ictio
n
m
o
d
el
an
d
p
r
o
v
id
e
r
ec
o
m
m
en
d
atio
n
s
,
th
is
is
k
n
o
wn
as
th
e
"d
ata
s
p
ar
s
ity
p
r
o
b
lem
"
.
Un
ce
r
tain
r
ep
r
esen
tatio
n
s
in
m
ed
ical
r
ec
o
r
d
s
an
d
m
in
im
al
f
ea
tu
r
e
s
p
ac
e
o
v
e
r
lap
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
1
8
1
-
1
1
9
4
1186
ar
e
two
p
r
o
b
lem
s
in
th
e
d
e
v
el
o
p
m
en
t
o
f
C
DR
S
f
o
r
m
ed
ical
d
iag
n
o
s
tics
.
Ho
wev
er
,
b
ased
o
n
th
e
r
esu
lts
o
f
th
is
s
tu
d
y
,
th
e
p
r
o
p
o
s
ed
I
T
MD
'
s
p
er
f
o
r
m
a
n
ce
in
C
DR
S
was
im
p
r
o
v
ed
,
an
d
th
e
two
co
m
m
o
n
is
s
u
es
with
C
D
R
S
f
o
r
m
ed
ical
d
iag
n
o
s
tics
d
ev
elo
p
m
en
t h
av
e
b
ee
n
s
o
lv
ed
.
T
ab
le
1
.
A
s
u
m
m
a
r
y
o
f
cr
o
s
s
-
d
o
m
ain
RS
s
with
o
u
t le
v
er
ag
in
g
lin
k
ed
o
p
en
d
ata
P
a
p
e
r
P
r
o
b
l
e
m
/
p
u
r
p
o
se
M
e
t
h
o
d
D
o
ma
i
n
/
d
a
t
a
se
t
A
r
t
h
u
r
e
t
a
l
.
[
5
9
]
To
s
o
l
v
e
c
o
l
d
-
st
a
r
t
a
n
d
d
a
t
a
sp
a
r
si
t
y
i
s
su
e
s.
D
-
G
D
L
w
i
t
h
d
i
scr
i
mi
n
a
t
i
v
e
b
a
s
i
s"
(
1
)
F
l
i
x
t
e
r
(
s
o
c
i
a
l
n
e
t
w
o
r
k
p
l
a
t
f
o
r
m)
(
2
)
N
e
t
f
l
i
x
(
3
)
C
i
t
e
U
Li
k
e
(
c
i
t
a
t
i
o
n
man
a
g
e
me
n
t
sy
s
t
e
m)
W
a
n
g
e
t
a
l
.
[
6
0
]
To
c
a
p
t
u
r
e
u
s
e
r
s' sh
a
r
e
d
i
n
t
e
r
e
s
t
s w
h
i
l
e
o
v
e
r
l
o
o
k
i
n
g
d
o
m
a
i
n
-
s
p
e
c
i
f
i
c
p
r
e
f
e
r
e
n
c
e
s.
D
G
M
L
(
1
)
D
i
a
n
p
i
n
g
p
l
a
t
f
o
r
m’
s
d
a
t
a
s
e
t
(
p
o
i
n
t
o
f
i
n
t
e
r
e
s
t
a
n
d
f
e
e
d
s
d
o
m
a
i
n
s)
(
2
)
A
maz
o
n
d
a
t
a
se
t
(
C
e
l
l
P
h
o
n
e
s
& El
e
c
t
r
o
n
i
c
s
d
o
m
a
i
n
s)
Zh
a
n
g
e
t
a
l
.
[
6
1
]
To
e
n
s
u
r
e
c
o
n
s
i
st
e
n
c
y
w
h
e
n
t
r
a
n
sf
e
r
r
i
n
g
k
n
o
w
l
e
d
g
e
i
n
a
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
C
D
R
S
.
"
C
o
l
l
a
b
o
r
a
t
i
v
e
C
D
R
S
w
i
t
h
o
u
t
o
v
e
r
l
a
p
p
i
n
g
e
n
t
i
t
i
e
s
b
a
s
e
d
o
n
d
o
ma
i
n
a
d
a
p
t
a
t
i
o
n
(
C
C
R
-
DA)"
(
1
)
N
e
t
f
l
i
x
(
2
)
G
o
o
d
r
e
a
d
s
(
3
)
A
maz
o
n
B
o
o
k
(
4
)
M
o
v
i
e
Le
n
s
2
0
M
(
5
)
D
o
u
b
a
n
B
o
o
k
(
6
)
F
l
i
x
s
t
e
r
C
h
a
n
g
e
t
a
l
.
[
6
2
]
To
a
d
d
r
e
ss
d
a
t
a
s
p
a
r
si
t
y
,
u
n
c
e
r
t
a
i
n
r
e
p
r
e
s
e
n
t
a
t
i
o
n
s
i
n
med
i
c
a
l
r
e
c
o
r
d
s,
a
n
d
mi
n
o
r
o
v
e
r
l
a
p
s
b
e
t
w
e
e
n
f
e
a
t
u
r
e
sp
a
c
e
s.
"
I
n
f
o
r
mat
i
o
n
t
r
a
n
sf
e
r
f
o
r
med
i
c
a
l
d
i
a
g
n
o
si
s
(
I
TM
D
)
"
(
1
)
T
h
y
r
o
i
d
c
a
n
c
e
r
d
a
t
a
set
(
2
)
B
r
e
a
st
c
a
n
c
e
r
d
a
t
a
se
t
O
g
u
n
se
y
i
e
t
a
l
.
[
6
3
]
To
p
r
o
mo
t
e
s
a
f
e
i
n
f
o
r
ma
t
i
o
n
e
x
c
h
a
n
g
e
b
e
t
w
e
e
n
v
a
r
i
o
u
s
d
o
m
a
i
n
s.
"
MF
-
so
m
e
w
h
a
t
h
o
m
o
m
o
r
p
h
i
c
e
n
c
r
y
p
t
i
o
n
(
S
W
H
E)
"
(
1
)
M
o
v
i
e
Le
n
s
-
G
o
o
d
b
o
o
k
s
(
2
)
M
o
v
i
e
Le
n
s
-
B
o
o
k
C
r
o
ss
i
n
g
O
u
y
a
n
g
e
t
a
l
.
[
6
4
]
To
m
o
d
e
l
i
n
t
e
r
a
c
t
i
o
n
s
a
c
r
o
ss
d
o
m
a
i
n
s
t
o
s
o
l
v
e
d
a
t
a
sp
a
r
si
t
y
i
n
t
h
e
t
a
r
g
e
t
d
o
m
a
i
n
.
"
C
r
o
ss
-
g
r
a
p
h
k
n
o
w
l
e
d
g
e
t
r
a
n
sf
e
r
n
e
t
w
o
r
k
"
(
1
)
B
o
o
k
s
(
2
)
M
o
v
i
e
s
(
3
)
C
D
s
(
4
)
TV
(
5
)
V
i
n
y
l
W
a
n
g
e
t
a
l
.
[
6
5
]
To
s
o
l
v
e
c
o
l
d
-
st
a
r
t
i
ss
u
e
s
i
n
t
h
e
e
-
c
o
mm
e
r
c
e
d
o
m
a
i
n
.
"
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
(DNN)"
(
1
)
A
d
s
d
o
ma
i
n
(
p
l
a
t
f
o
r
m
d
a
t
a
s
e
t
)
(
2
)
O
n
l
i
n
e
sh
o
p
p
i
n
g
d
o
ma
i
n
Zh
a
n
g
e
t
a
l
.
[
9
]
To
s
o
l
v
e
t
h
e
p
r
o
b
l
e
m
o
f
d
a
t
a
sp
a
r
si
t
y
.
C
D
R
S
w
i
t
h
m
u
l
t
i
p
l
e
s
o
u
r
c
e
s
(
1
)
Ea
c
h
M
o
v
i
e
(
2
)
M
o
v
i
e
l
e
n
s
1
M
(
3
)
Li
b
r
a
r
y
T
h
i
n
g
(
4
)
A
maz
o
n
B
o
o
k
(
5
)
Y
a
h
o
o
M
u
s
i
c
Zh
a
n
g
e
t
a
l
.
[
8
]
To
a
l
l
e
v
i
a
t
e
t
h
e
d
a
t
a
s
p
a
r
si
t
y
i
ssu
e
i
n
t
h
e
RS
.
"
K
e
r
n
e
l
-
i
n
d
u
c
e
d
k
n
o
w
l
e
d
g
e
t
r
a
n
sf
e
r
,
c
a
l
l
e
d
K
e
r
K
T"
(
1
)
M
o
v
i
e
l
e
n
s
2
0
M
(
2
)
N
e
t
f
l
i
x
(
3
)
A
maz
o
n
B
o
o
k
(
4
)
D
o
u
b
a
n
(
M
o
v
i
e
a
n
d
B
o
o
k
)
Y
u
e
t
a
l
.
[
6
6
]
S
e
e
k
t
o
s
o
l
v
e
t
h
e
i
ss
u
e
o
f
i
n
f
o
r
mat
i
o
n
o
v
e
r
l
o
a
d
i
n
mo
b
i
l
e
m
u
l
t
i
me
d
i
a
a
p
p
l
i
c
a
t
i
o
n
s.
"
F
e
a
t
u
r
e
t
r
a
n
sf
e
r
a
n
d
i
mb
a
l
a
n
c
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
(
F
TI
C
)
"
(
1
)
B
o
o
k
(
2
)
M
u
s
i
c
C
D
(
3
)
V
i
d
e
o
(
4
)
D
V
D
Th
e
n
d
r
a
l
a
n
d
V
a
l
l
i
y
a
mm
a
i
[
6
7
]
To
r
e
d
u
c
e
t
h
e
RS
's
c
o
l
d
s
t
a
r
t
a
n
d
d
a
t
a
s
p
a
r
s
i
t
y
i
s
s
u
e
s.
"
C
l
u
st
e
r
i
n
g
-
b
a
se
d
k
n
o
w
l
e
d
g
e
t
r
a
n
sf
e
r
b
e
t
w
e
e
n
d
o
m
a
i
n
s"
(
1
)
R
e
st
a
u
r
a
n
t
(
2
)
T
o
u
r
i
st
A
t
t
r
a
c
t
i
o
n
V
e
r
a
s
e
t
a
l
.
[
6
8
]
To
a
d
d
r
e
ss
d
i
f
f
i
c
u
l
t
i
e
s wi
t
h
si
n
g
l
e
-
d
o
ma
i
n
R
S
a
n
d
i
mp
r
o
v
e
t
h
e
a
c
c
u
r
a
c
y
o
f
C
D
R
S
.
"
C
o
n
t
e
x
t
-
a
w
a
r
e
a
l
g
o
r
i
t
h
ms
(
p
r
e
-
f
i
l
t
e
r
i
n
g
a
n
d
p
o
s
t
-
f
i
l
t
e
r
i
n
g
)
"
.
(
1
)
B
o
o
k
s
(
2
)
Te
l
e
v
i
s
i
o
n
K
u
mar
e
t
a
l
.
[
6
9
]
To
r
e
d
u
c
e
t
h
e
d
a
t
a
s
p
a
r
s
i
t
y
i
ssu
e
a
n
d
a
c
c
e
l
e
r
a
t
e
p
r
e
d
i
c
t
i
o
n
.
D
i
st
r
i
b
u
t
e
d
a
p
p
r
o
a
c
h
e
s
b
a
se
d
o
n
sh
a
r
i
n
g
l
a
t
e
n
t
r
a
t
i
n
g
p
a
t
t
e
r
n
s
u
si
n
g
b
i
g
d
a
t
a
.
(
1
)
M
o
v
i
e
Le
n
s
(
2
)
B
o
o
k
-
c
r
o
ssi
n
g
T
h
e
d
e
v
elo
p
m
e
n
t
o
f
a
"p
r
iv
ac
y
-
p
r
eser
v
in
g
c
r
o
s
s
-
d
o
m
ain
RS
"
u
s
in
g
a
MF
ap
p
r
o
ac
h
th
at
u
t
ilized
th
e
"
s
o
m
ewh
at
h
o
m
o
m
o
r
p
h
ic
en
c
r
y
p
tio
n
(
SW
HE
)
"
b
y
Og
u
n
s
ey
i
et
a
l.
[
6
3
]
r
ev
ea
ls
th
at
it
ca
n
alwa
y
s
s
af
eg
u
ar
d
u
s
er
p
r
iv
ac
y
ac
r
o
s
s
d
if
f
er
e
n
t
s
tag
es.
I
n
a
d
d
itio
n
to
b
ein
g
p
r
o
tecte
d
f
r
o
m
an
y
p
r
iv
ac
y
leak
a
g
e,
ex
p
er
im
en
ts
o
n
ac
tu
al
an
d
s
im
u
lated
d
atasets
d
em
o
n
s
tr
ate
h
o
w
s
u
cc
ess
f
u
l
th
e
tech
n
iq
u
e
is
at
s
af
eg
u
ar
d
in
g
p
r
iv
ac
y
i
n
C
DR
S.
In
o
u
r
o
p
in
i
o
n
,
RS
s
ar
e
ess
en
tial
to
en
s
u
r
e
th
e
u
s
er
'
s
p
r
iv
a
cy
an
d
p
r
ev
en
t
d
ata
leak
ag
e
wh
ile
co
llectin
g
t
h
e
u
s
er
'
s
p
r
ef
er
en
ce
s
an
d
h
is
to
r
ic
al
d
ata.
W
e
ca
n
p
r
o
m
o
te
s
ec
u
r
e
in
f
o
r
m
atio
n
tr
an
s
f
er
b
etwe
en
d
if
f
er
e
n
t
d
o
m
ai
n
s
u
s
in
g
th
is
tech
n
iq
u
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
A
r
ev
iew
o
f th
e
imp
a
cts o
f lin
ke
d
o
p
e
n
d
a
t
a
o
n
cro
s
s
-
d
o
ma
in
r
ec
o
mme
n
d
er sys
tems …
(
Y
u
i Ch
ee
X
u
a
n
)
1187
A
n
o
v
el
m
o
d
el
k
n
o
w
n
as
a
"c
r
o
s
s
-
g
r
ap
h
k
n
o
wled
g
e
tr
a
n
s
f
er
n
etwo
r
k
"
h
as
b
ee
n
in
tr
o
d
u
ce
d
b
y
Ou
y
an
g
et
a
l.
[
6
4
]
,
a
n
d
it
d
em
o
n
s
tr
ates
h
o
w
it
ca
n
u
s
e
k
n
o
w
led
g
e
f
r
o
m
a
s
o
u
r
ce
d
o
m
ain
to
a
tar
g
et
d
o
m
ai
n
t
o
d
ea
l
with
th
e
p
r
o
b
lem
o
f
d
ata
s
p
ar
s
ity
.
I
t
ca
n
also
ex
p
licitly
d
escr
ib
e
cr
o
s
s
-
d
o
m
ain
co
n
n
ec
tio
n
s
an
d
co
n
s
id
er
th
e
laten
t
d
ata
u
n
d
er
ly
in
g
u
s
e
r
-
item
in
ter
ac
tio
n
s
.
T
h
e
a
u
th
o
r
s
s
p
ec
if
ically
m
o
d
ele
d
in
tr
a
-
d
o
m
ain
a
n
d
cr
o
s
s
-
d
o
m
ain
in
ter
ac
tio
n
s
u
s
in
g
th
e
g
r
ap
h
s
tr
u
ctu
r
e,
wh
ich
th
ey
u
s
ed
to
tr
an
s
f
er
in
f
o
r
m
atio
n
f
r
o
m
th
e
s
o
u
r
ce
d
o
m
ain
s
.
T
h
e
au
th
o
r
s
f
o
cu
s
ed
o
n
p
r
o
d
u
ct
r
ec
o
m
m
en
d
atio
n
s
th
at
f
r
eq
u
en
tly
lev
er
a
g
e
Am
az
o
n
5
-
c
o
r
e
p
r
o
d
u
ct
d
ata.
T
h
e
o
u
tco
m
es
d
e
m
o
n
s
tr
ate
th
at
th
e
m
o
d
el
o
u
t
p
er
f
o
r
m
s
f
iv
e
s
tate
-
of
-
th
e
-
ar
t
tech
n
iq
u
es
[
6
4
]
.
T
h
e
ef
f
ec
tiv
e
n
ess
o
f
r
ec
o
m
m
en
d
atio
n
s
h
as
im
p
r
o
v
e
d
,
an
d
th
is
k
n
o
wled
g
e
g
r
ap
h
m
eth
o
d
is
th
e
co
r
n
er
s
to
n
e
o
f
t
h
e
C
DR
S
with
L
OD.
W
an
g
et
a
l.
[
6
5
]
in
tr
o
d
u
ctio
n
o
f
"DN
N
-
b
ased
C
DR
S"
d
em
o
n
s
tr
ates
th
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
i
n
teg
r
atio
n
m
o
d
el
in
t
h
at
it
ca
n
m
a
k
e
m
o
r
e
p
r
ec
is
e
p
r
o
d
u
ct
r
ec
o
m
m
en
d
atio
n
s
to
cu
s
to
m
er
s
o
f
o
th
er
d
o
m
ain
s
th
r
o
u
g
h
t
h
e
d
is
tr
ib
u
tio
n
o
f
ad
s
,
as
well
as
t
h
e
v
alu
e
o
f
d
ee
p
n
eu
r
al
m
eth
o
d
s
em
p
lo
y
in
g
d
ata
f
r
o
m
a
d
if
f
e
r
en
t
d
o
m
ain
f
o
r
th
e
co
ld
-
s
tar
t
p
r
o
b
lem
.
Usi
n
g
W
o
r
d
2
Vec
,
th
e
au
th
o
r
s
tr
an
s
f
o
r
m
t
ex
tu
al
d
ata
o
n
u
s
er
s
an
d
item
s
in
to
laten
t
v
ec
to
r
s
,
wh
ich
s
er
v
e
as
th
eir
r
ep
r
esen
t
atio
n
s
.
An
o
th
er
p
r
o
p
o
s
ed
R
-
m
etap
ath
2
Vec
m
eth
o
d
is
im
p
r
o
v
in
g
u
s
er
m
o
d
elin
g
to
allev
iate
W
o
r
d
2
Vec
'
s
in
ab
ilit
y
to
ca
p
tu
r
e
s
tr
u
ct
u
r
al
an
d
s
em
an
tic
r
elatio
n
s
h
ip
s
b
etwe
en
v
ar
io
u
s
u
s
er
s
.
A
C
DR
S
with
m
u
ltip
le
s
o
u
r
c
es,
in
tr
o
d
u
ce
d
b
y
Z
h
an
g
et
a
l
.
[
9
]
to
im
p
r
o
v
e
r
ec
o
m
m
en
d
a
tio
n
s
in
a
s
p
ar
s
e
tar
g
et
d
o
m
ain
b
y
ex
tr
a
ctin
g
g
r
o
u
p
-
lev
el
in
f
o
r
m
atio
n
f
r
o
m
m
an
y
s
o
u
r
ce
d
o
m
ain
s
,
ca
n
o
u
tp
er
f
o
r
m
s
ix
b
en
ch
m
ar
k
s
an
d
in
cr
ea
s
e
tar
g
et
d
o
m
ain
r
ec
o
m
m
e
n
d
atio
n
a
cc
u
r
ac
y
.
T
h
is
ap
p
r
o
ac
h
ca
n
s
o
lv
e
th
e
p
r
o
b
lem
o
f
d
ata
s
p
ar
s
ity
b
y
tr
an
s
f
er
r
in
g
k
n
o
wled
g
e
f
r
o
m
a
s
o
u
r
ce
d
o
m
ain
with
d
en
s
e
d
ata
to
a
tar
g
e
t
d
o
m
ain
with
litt
le
d
ata.
Sin
ce
th
e
r
e
m
ay
b
e
in
f
o
r
m
atio
n
in
m
an
y
o
th
e
r
s
o
u
r
ce
d
o
m
ain
s
,
m
o
r
e
th
an
k
n
o
wled
g
e
f
r
o
m
ju
s
t
o
n
e
s
o
u
r
ce
d
o
m
ain
is
n
ee
d
e
d
[
9
]
.
Z
h
an
g
et
a
l.
[
8
]
in
tr
o
d
u
ctio
n
o
f
C
DR
S
b
ased
o
n
"k
er
n
el
-
in
d
u
ce
d
k
n
o
wled
g
e
tr
a
n
s
f
er
(
Ker
KT
)
"
d
em
o
n
s
tr
ates
th
at
it
ca
n
ef
f
ec
t
iv
ely
tr
an
s
f
er
k
n
o
wled
g
e
t
h
r
o
u
g
h
o
v
er
lap
p
in
g
en
titi
es,
r
eso
l
v
in
g
th
e
p
r
o
b
lem
o
f
d
ata
s
p
ar
s
ity
.
Fo
u
r
d
ata
s
ets
with
th
r
ee
d
if
f
e
r
en
t
s
p
ar
s
ity
r
atio
s
wer
e
u
s
ed
in
test
s
,
an
d
Ker
KT
'
s
p
r
ed
ictio
n
ac
cu
r
ac
y
was
s
h
o
wn
to
b
e
1
.
1
3
%
-
2
0
%
g
r
ea
ter
th
an
th
at
o
f
s
ix
b
en
ch
m
a
r
k
s
[
8
]
.
T
h
e
f
in
d
in
g
s
also
s
h
o
w
th
at
k
n
o
wled
g
e
tr
an
s
f
er
f
r
o
m
th
e
s
o
u
r
ce
d
o
m
ai
n
to
th
e
tar
g
et
d
o
m
ain
is
f
ea
s
ib
le
a
n
d
ad
v
a
n
tag
e
o
u
s
with
e
v
en
m
in
o
r
o
v
er
lap
s
.
T
h
is
tech
n
iq
u
e
u
s
es
o
v
er
lap
p
i
n
g
en
titi
es
as
a
l
in
k
b
etwe
en
th
e
s
o
u
r
ce
an
d
tar
g
et
d
o
m
ain
s
.
I
t
ca
n
b
e
u
s
ed
o
n
e
-
co
m
m
er
ce
p
latf
o
r
m
s
lik
e
Am
az
o
n
,
wh
er
e
d
ata
o
n
b
o
o
k
r
atin
g
s
is
ab
u
n
d
an
t
b
u
t
lack
in
g
in
o
th
e
r
ca
teg
o
r
ies.
I
n
ter
m
s
o
f
f
o
u
r
s
ep
ar
ate
ass
ess
m
en
t
m
ea
s
u
r
es
—
m
ea
n
a
b
s
o
lu
te
er
r
o
r
(
MA
E
)
,
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
,
p
r
ec
is
io
n
,
an
d
r
ec
all
—
th
e
d
ev
elo
p
m
en
t
o
f
"CDR
S
with
f
ea
tu
r
e
tr
an
s
f
er
an
d
u
n
b
al
an
ce
d
class
if
icatio
n
(
FTI
C
)
"
b
y
Yu
et
a
l.
[
6
6
]
d
e
m
o
n
s
tr
ates
th
at
it
is
s
u
p
er
io
r
.
I
tem
f
ea
tu
r
es
ar
e
co
llected
f
r
o
m
W
ik
ip
ed
ia,
an
d
ad
d
itio
n
al
u
s
er
f
ea
tu
r
es
ar
e
ex
t
r
a
cted
with
a
f
u
n
k
-
SVD
m
o
d
el
f
r
o
m
u
s
e
-
s
id
e
au
x
iliar
y
d
o
m
ai
n
s
.
An
im
b
alan
ce
d
class
if
icatio
n
m
o
d
el
(
Ad
aBo
o
s
t.N
C
)
s
o
lv
es
th
e
r
esu
ltin
g
im
b
alan
ce
d
class
if
icatio
n
p
r
o
b
le
m
.
B
y
in
f
e
r
r
in
g
u
s
e
r
p
r
ef
er
en
ce
s
f
r
o
m
u
s
er
ac
tio
n
s
,
s
u
ch
as
r
atin
g
m
at
r
ices,
th
e
C
DR
S
ca
n
u
til
ize
th
is
n
o
v
el
a
p
p
r
o
ac
h
to
a
d
d
r
ess
th
e
is
s
u
e
o
f
in
f
o
r
m
atio
n
o
v
er
lo
a
d
in
m
o
b
ile
m
u
ltime
d
ia
a
p
p
lic
atio
n
s
.
Ho
wev
er
,
b
ec
au
s
e
u
s
e
r
s
ar
e
co
n
s
is
ten
tly
r
elu
ctan
t
to
r
ate
th
in
g
s
,
esp
ec
ially
o
n
es
th
ey
d
is
lik
e,
r
atin
g
m
atr
ices
ar
e
v
er
y
s
ca
r
ce
an
d
d
is
to
r
ted
.
Pre
v
io
u
s
r
ec
o
m
m
en
d
atio
n
alg
o
r
ith
m
s
c
an
n
o
t su
cc
ess
f
u
lly
h
a
n
d
le
th
e
i
s
s
u
es o
f
s
p
ar
s
ity
an
d
s
k
ewe
d
d
is
tr
ib
u
tio
n
[
6
6
]
.
T
h
en
d
r
al
an
d
Valliy
am
m
ai
[
6
7
]
in
tr
o
d
u
ctio
n
o
f
"c
lu
s
ter
in
g
-
b
ased
k
n
o
wled
g
e
t
r
an
s
f
er
"
b
e
twee
n
th
e
d
o
m
ain
s
in
C
DR
S
s
u
p
p
o
r
ts
th
e
ass
er
tio
n
th
at
o
n
e
tr
a
n
s
f
er
le
ar
n
in
g
m
eth
o
d
,
clu
s
ter
in
g
,
ca
n
ef
f
ec
tiv
ely
ad
d
r
ess
th
e
co
ld
s
tar
t
an
d
s
p
ar
s
ity
d
if
f
icu
lties
in
RS
s
.
User
af
f
in
ity
d
is
co
v
er
ed
th
r
o
u
g
h
clu
s
ter
in
g
is
ef
f
ec
tiv
ely
ap
p
lied
to
tr
a
n
s
f
er
k
n
o
wled
g
e
b
etwe
en
clo
s
ely
r
elate
d
d
o
m
ain
s
.
As
u
s
er
af
f
in
ity
,
th
e
k
n
o
wled
g
e
is
tr
a
n
s
f
er
r
ed
s
u
cc
ess
f
u
lly
an
d
ef
f
ec
tiv
ely
[
6
7
]
.
Acc
o
r
d
in
g
to
Ver
as
et
a
l.
[
6
8
]
,
r
ar
e
r
esear
ch
h
as
b
ee
n
d
o
n
e
o
n
C
DR
S'
u
s
ag
e
o
f
c
o
n
tex
tu
a
l
f
ea
tu
r
es.
Acc
o
r
d
in
g
to
e
x
p
er
im
e
n
tal
e
v
alu
atio
n
u
s
in
g
a
r
ea
l
d
ataset,
ad
o
p
tin
g
c
o
n
tex
t
-
awa
r
e
co
l
lab
o
r
ativ
e
f
ilter
in
g
alg
o
r
ith
m
s
o
v
er
c
r
o
s
s
-
d
o
m
ain
d
atasets
b
y
Ver
as
et
a
l.
[
6
8
]
is
an
ex
ce
llen
t
s
tr
ateg
y
to
b
o
o
s
t
cr
o
s
s
-
d
o
m
ain
r
ec
o
m
m
en
d
atio
n
ac
cu
r
a
c
y
co
m
p
ar
ed
to
t
y
p
ical
c
o
llab
o
r
ativ
e
f
ilter
in
g
alg
o
r
ith
m
s
o
v
er
c
r
o
s
s
-
d
o
m
ain
d
atasets
.
I
n
C
DR
S,
th
is
s
tu
d
y
em
p
lo
y
s
two
co
n
tex
t
-
awa
r
e
alg
o
r
ith
m
s
,
p
r
e
-
f
ilter
in
g
,
a
n
d
p
o
s
t
-
f
ilter
in
g
,
th
at
u
s
e
d
iv
er
s
e
c
o
n
t
e
x
t
u
a
l
v
a
r
i
a
b
le
s
[
6
8
]
.
T
h
is
a
p
p
r
o
a
c
h
c
a
n
i
m
p
r
o
v
e
C
DR
S
ac
c
u
r
a
c
y
a
n
d
f
i
x
p
r
o
b
l
e
m
s
w
i
t
h
s
i
n
g
l
e
-
d
o
m
a
i
n
RS
s.
W
e
ex
am
in
e
th
e
last
p
ap
er
i
n
th
is
s
ec
tio
n
.
Acc
o
r
d
in
g
to
Ku
m
ar
et
a
l.
[
6
9
]
,
co
n
s
tr
u
ctin
g
a
d
is
tr
ib
u
ted
im
p
lem
en
tatio
n
o
f
a
C
DR
S
b
ased
o
n
laten
t
r
atin
g
p
atter
n
s
h
ar
in
g
u
s
in
g
b
i
g
d
ata
was
m
o
r
e
s
ca
lab
le
th
an
th
e
s
eq
u
en
tial
m
eth
o
d
.
B
y
ac
ce
le
r
atin
g
p
r
ed
ictio
n
an
d
u
tili
zin
g
in
f
o
r
m
atio
n
f
r
o
m
o
th
er
f
ield
s
,
th
is
s
tr
ateg
y
ca
n
ad
d
r
ess
th
e
p
r
o
b
lem
o
f
d
ata
s
p
ar
s
ity
[
6
9
]
.
I
n
a
n
u
ts
h
ell,
C
DR
S
o
u
tp
er
f
o
r
m
ed
co
n
v
e
n
tio
n
al
R
S
b
ased
o
n
th
e
f
ac
ts
ab
o
v
e.
Acc
o
r
d
i
n
g
t
o
Z
h
u
et
a
l.
[
4
1
]
,
th
e
r
e
ar
e
s
p
ec
if
ic
ch
alle
n
g
es
f
ac
ed
b
y
ea
c
h
ty
p
e
o
f
C
DR
S.
I
n
s
in
g
le
-
tar
g
et
C
DR
S,
lear
n
in
g
ac
cu
r
ate
m
ap
p
in
g
r
elatio
n
s
,
g
en
er
atin
g
ac
cu
r
ate
r
atin
g
p
atter
n
s
,
an
d
b
u
ild
in
g
co
n
te
n
t
-
b
ased
lin
k
s
is
ch
allen
g
in
g
.
On
th
e
o
th
er
h
an
d
,
it
is
c
h
allen
g
in
g
to
d
esig
n
a
f
ea
s
ib
le
m
eth
o
d
o
r
f
r
am
ewo
r
k
a
n
d
o
p
tim
ize
t
h
e
u
s
er
s
a
n
d
item
s
em
b
ed
d
e
d
in
a
d
u
al
-
tar
g
et
C
DR
S,
wh
ile
m
u
lti
-
tar
g
et
C
DR
S
is
ch
allen
g
in
g
to
av
o
i
d
n
eg
ativ
e
tr
an
s
f
er
.
Ho
wev
er
,
we
h
av
e
s
ee
n
th
e
s
u
cc
ess
o
f
C
DR
S
in
im
p
r
o
v
in
g
th
e
ac
c
u
r
ac
y
o
f
r
ec
o
m
m
en
d
atio
n
s
.
Yu
et
a
l.
[
4
]
d
esig
n
e
d
a
s
o
p
h
is
ticated
f
r
am
ewo
r
k
to
e
x
tr
ac
t
an
d
f
u
lly
ex
p
an
d
u
s
er
-
an
d
i
tem
-
s
id
e
f
ea
tu
r
es
in
s
in
g
le
-
tar
g
et
C
DR
S
b
y
u
tili
zin
g
th
e
s
o
u
r
ce
d
o
m
ain
’
s
laten
t f
ac
to
r
s
p
ac
e
an
d
its
in
f
o
r
m
atio
n
.
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
1
8
1
-
1
1
9
4
1188
3
.
2
.
Cro
s
s
-
do
ma
in ind
iv
idu
a
l r
ec
o
mm
ender
s
y
s
t
em
wit
h link
ed
o
pen da
t
a
C
o
m
p
ar
ed
t
o
T
a
b
le
1
,
wh
ich
c
o
n
tain
s
s
o
lely
C
DR
S
with
o
u
t
L
OD
tech
n
o
lo
g
y
,
th
e
f
o
llo
win
g
d
is
cu
s
s
io
n
f
o
cu
s
es
o
n
C
DR
S
th
at
lev
er
ag
es
L
OD
tech
n
o
lo
g
y
.
T
h
er
e
ar
e
two
s
em
an
tic
m
ea
s
u
r
es to
ex
p
lo
r
e
th
e
co
r
r
elatio
n
b
etwe
en
d
if
f
e
r
en
t
L
OD
d
o
m
ai
n
s
,
wh
ich
ar
e
s
im
ilar
ity
an
d
r
elate
d
n
ess
.
Acc
o
r
d
in
g
to
T
a
b
le
2
,
C
DR
S
with
L
OD
is
ca
p
ab
le
o
f
s
ev
er
al
in
n
o
v
ativ
e
s
tr
ateg
ies,
in
clu
d
in
g
"
c
r
o
s
s
-
d
o
m
ain
s
em
an
tic
r
elate
d
n
ess
-
b
ased
m
atr
ix
f
ac
to
r
izatio
n
m
o
d
el
(
C
D
-
Sem
MF)
"
[
2
6
]
,
"CDR
S
with
L
OD
b
ased
o
n
MF
u
s
in
g
cr
o
s
s
-
d
o
m
ain
co
r
r
elatio
n
"
[
7
0
]
,
"
c
o
m
b
i
n
i
n
g
l
i
n
k
e
d
o
p
e
n
d
a
t
a
s
im
i
l
a
r
i
t
y
a
n
d
r
e
l
a
te
d
n
e
s
s
f
o
r
c
r
o
s
s
o
n
li
n
e
s
o
c
i
a
l
n
e
t
w
o
r
k
s
(
OS
N)
R
e
c
o
m
m
e
n
d
a
ti
o
n
"
[
7
1
]
a
n
d
a
"
c
r
o
s
s
-
d
o
m
a
i
n
r
e
c
o
m
m
e
n
d
e
r
s
y
s
t
e
m
b
as
e
d
o
n
c
o
m
m
o
n
-
s
e
n
s
e
k
n
o
w
l
e
d
g
e
b
as
e
s
"
[
7
2
]
.
T
ab
le
2
.
A
s
u
m
m
a
r
y
o
f
cr
o
s
s
-
d
o
m
ain
R
Ss
with
lin
k
ed
o
p
en
d
ata
P
a
p
e
r
P
r
o
b
l
e
m
/
p
u
r
p
o
se
M
e
t
h
o
d
D
o
ma
i
n
/
d
a
t
a
se
t
N
a
t
a
r
a
j
a
n
e
t
a
l
.
[
2
6
]
To
a
d
d
r
e
ss
t
h
e
u
s
e
r
c
o
l
d
s
t
a
r
t
p
r
o
b
l
e
m
i
n
a
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
R
S
w
i
t
h
LO
D
.
CD
-
S
e
mM
F
(
1
)
B
o
o
k
(
2
)
M
u
s
i
c
(
3
)
M
o
v
i
e
s
Y
.
W
a
n
g
e
t
a
l
.
[
7
0
]
To
s
t
u
d
y
t
h
e
e
mp
i
r
i
c
a
l
i
m
p
a
c
t
o
f
s
e
m
a
n
t
i
c
mea
s
u
r
e
s
i
n
C
D
R
S
i
n
a
u
ser
c
o
l
d
-
st
a
r
t
sce
n
a
r
i
o
.
MF
-
c
o
r
r
e
l
a
t
i
o
n
(
N
e
i
g
h
b
o
r
M
F
-
P
I
C
S
S
a
n
d
C
e
n
t
r
o
i
d
M
F
-
P
I
C
S
S
)
(
1
)
M
o
v
i
e
s
(
2
)
B
o
o
k
s
B
o
u
b
e
n
i
a
e
t
a
l
.
[
7
1
]
Ex
a
m
i
n
e
t
h
e
f
e
a
si
b
i
l
i
t
y
o
f
c
o
m
b
i
n
i
n
g
si
mi
l
a
r
i
t
y
a
n
d
r
e
l
a
t
e
d
n
e
ss i
n
LO
D
sp
a
c
e
a
n
d
i
n
t
r
o
d
u
c
e
a
n
o
v
e
l
LO
D
-
b
a
s
e
d
si
mi
l
a
r
i
t
y
me
a
su
r
e
t
o
d
e
a
l
w
i
t
h
c
o
l
d
s
t
a
r
t
i
ssu
e
.
M
i
x
e
d
a
p
p
r
o
a
c
h
e
s
o
f
r
e
l
a
t
e
d
n
e
ss,
a
s
LD
S
D
a
n
d
R
e
s
i
m,
a
n
d
t
h
e
si
mi
l
a
r
i
t
y
o
f
d
e
scri
p
t
i
o
n
,
a
s L
O
D
S
.
O
S
N
s
(
1
)
Tw
i
t
t
e
r
-
Y
o
u
Tu
b
e
Tsa
i
e
t
a
l
.
[
7
2
]
To
r
e
t
r
i
e
v
e
t
e
c
h
n
i
c
a
l
p
h
r
a
s
e
s fr
o
m
v
a
r
i
o
u
s
d
o
m
a
i
n
s
a
n
d
r
e
c
o
mm
e
n
d
t
h
e
m.
C
D
R
S
b
a
s
e
d
o
n
c
o
mm
o
n
-
se
n
se
k
n
o
w
l
e
d
g
e
b
a
ses
(
1
)
I
TR
I
k
n
o
w
l
e
d
g
e
b
a
s
e
(
2
)
C
o
n
c
e
p
t
N
e
t
(
3
)
W
i
k
i
p
e
d
i
a
Acc
o
r
d
in
g
to
t
h
e
ex
p
er
im
en
t
al
s
tu
d
y
in
th
e
s
ev
er
e
u
s
er
c
o
ld
s
tar
t
s
ce
n
ar
io
s
,
Nata
r
ajan
et
a
l.
[
2
6
]
in
tr
o
d
u
ctio
n
o
f
C
D
-
Sem
MF
p
r
o
v
id
es
ac
cu
r
ate
s
u
g
g
esti
o
n
s
f
o
r
n
ew
u
s
er
s
in
th
e
tar
g
et
d
o
m
ai
n
b
y
u
tili
zin
g
item
m
etad
ata
b
ased
o
n
th
e
s
o
u
r
ce
an
d
tar
g
et
d
o
m
ain
s
in
v
o
lv
ed
in
th
e
r
ec
o
m
m
en
d
atio
n
p
r
o
ce
s
s
.
I
t
is
a
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
r
ec
o
m
m
en
d
atio
n
s
th
at
ex
p
lo
it
th
e
co
m
p
u
ted
r
ela
ted
n
ess
b
etwe
en
item
s
to
lin
k
k
n
o
wled
g
e
ac
r
o
s
s
d
if
f
er
en
t
d
o
m
ain
s
.
Usi
n
g
th
is
ap
p
r
o
ac
h
,
th
e
p
r
o
b
lem
o
f
u
s
er
c
o
ld
s
tar
t
in
a
co
llab
o
r
ativ
e
f
ilter
in
g
R
S
u
s
in
g
L
OD
ca
n
b
e
r
eso
lv
e
d
ea
s
ily
with
p
u
b
licly
av
ailab
le
d
ata.
Acc
o
r
d
in
g
to
r
esear
ch
o
n
th
e
em
p
ir
ical
ef
f
ec
ts
o
f
s
em
an
tic
m
ea
s
u
r
es
in
a
C
DR
S
in
a
u
s
er
co
ld
-
s
tar
t
s
ce
n
ar
io
b
y
W
an
g
et
a
l.
[
7
0
]
,
r
elate
d
n
ess
m
ea
s
u
r
es
ca
n
p
r
o
d
u
ce
a
wid
e
r
an
g
e
o
f
r
ec
o
m
m
en
d
atio
n
s
th
r
o
u
g
h
tr
ials
o
n
a
r
ea
l
-
wo
r
l
d
d
ataset.
I
n
co
n
tr
ast,
th
e
u
s
er
'
s
ex
is
tin
g
in
ter
ests
ca
n
b
e
p
r
ec
is
ely
ca
p
tu
r
ed
b
y
s
im
ilar
ity
m
ea
s
u
r
es.
T
h
e
s
tu
d
y
also
s
h
o
wed
th
at
ev
en
in
th
e
co
ld
-
s
tar
t
s
ce
n
ar
io
,
th
e
cr
o
s
s
-
d
o
m
a
in
r
ec
o
m
m
en
d
ati
o
n
ap
p
r
o
ac
h
co
u
ld
p
r
o
v
id
e
co
n
s
u
m
er
s
with
p
er
tin
en
t
an
d
s
atis
f
y
in
g
r
ec
o
m
m
en
d
atio
n
s
[
7
0
]
.
T
h
is
s
tu
d
y
is
a
C
D
R
S
with
L
OD
b
ased
o
n
MF
u
s
in
g
cr
o
s
s
-
d
o
m
ain
co
r
r
elatio
n
.
Acc
o
r
d
in
g
to
B
o
u
b
en
ia
et
a
l.
[
7
1
]
,
t
h
e
m
ix
e
d
tech
n
iq
u
es
o
f
r
elate
d
n
ess
an
d
s
im
ilar
ity
f
o
r
c
r
o
s
s
-
OSN
s
ig
n
if
ican
tly
im
p
r
o
v
e
wh
en
s
im
ilar
ity
an
d
r
elate
d
n
ess
ar
e
c
o
m
b
in
ed
.
T
h
e
r
elate
d
n
ess
,
as
lin
k
ed
d
ata
s
em
an
tic
d
is
tan
ce
(
L
DSD)
an
d
r
eso
u
r
ce
s
im
ilar
ity
(
R
esim)
,
wh
ich
is
a
r
ev
is
ed
v
er
s
io
n
o
f
L
DSD,
ar
e
m
ix
ed
in
d
if
f
e
r
en
t
co
m
b
in
atio
n
s
with
th
e
s
im
ilar
ity
,
as
L
OD
S
(
a
s
em
an
tic
s
im
ilar
ity
m
etr
ic
th
at
m
ak
es
u
s
e
o
f
m
o
r
e
L
OD
f
ea
tu
r
es).
Acc
o
r
d
in
g
to
th
e
ex
p
e
r
im
en
t
al
o
u
tco
m
es,
in
teg
r
atin
g
L
O
DS
with
th
e
R
es
im
o
f
f
er
s
th
e
b
est
ac
cu
r
ac
y
an
d
d
iv
er
s
ity
tr
ad
e
-
o
f
f
.
T
h
is
in
teg
r
ated
ap
p
r
o
a
ch
is
a
r
o
b
u
s
t
C
DR
S
with
L
OD
to
s
o
lv
e
th
e
co
ld
-
s
tar
t
p
r
o
b
lem
ef
f
icien
tly
with
p
u
b
licly
av
ail
ab
le
d
ata.
T
h
e
a
u
th
o
r
s
s
u
g
g
est th
at
th
e
m
ix
ed
tec
h
n
iq
u
es o
f
b
o
th
r
elate
d
n
ess
an
d
s
im
ilar
ity
m
ea
s
u
r
es
p
r
o
d
u
ce
a
b
etter
p
er
f
o
r
m
a
n
ce
o
f
a
C
DR
S,
p
ar
ticu
lar
ly
th
e
OSNs
C
DR
S,
co
m
p
ar
ed
to
a
s
in
g
le
m
ea
s
u
r
e.
T
h
e
las
t
p
a
p
er
t
o
b
e
ex
a
m
in
ed
in
t
h
is
s
ec
tio
n
is
th
e
C
DR
S
b
ased
o
n
co
m
m
o
n
s
en
s
e
k
n
o
wled
g
e
b
ases
b
y
T
s
ai
et
a
l.
[
7
2
]
.
T
h
e
s
y
s
tem
s
elec
ts
s
ig
n
if
ican
t
ter
m
s
f
r
o
m
p
r
o
v
id
ed
d
o
cu
m
en
ts
b
ased
o
n
u
s
er
q
u
e
r
ies
an
d
th
en
ca
lcu
lates
th
e
s
em
an
tic
co
s
in
e
s
im
ilar
ity
b
etwe
en
th
o
s
e
ter
m
s
.
C
o
n
s
eq
u
en
tly
,
n
etwo
r
k
s
tr
u
ctu
r
es
co
n
n
ec
t
t
h
e
q
u
er
ies
to
th
o
s
e
ex
tr
ac
ted
k
ey
wo
r
d
s
b
y
u
tili
zin
g
ex
ter
n
a
l
co
m
m
o
n
s
en
s
e
k
n
o
wled
g
e
b
ases
.
Acc
o
r
d
in
g
to
th
e
ex
p
er
im
e
n
tal
r
esear
ch
,
e
m
p
lo
y
in
g
th
e
W
ik
ip
ed
ia
in
te
r
m
ed
iar
y
te
r
m
s
ca
n
im
p
r
o
v
e
s
ea
r
ch
r
esu
lts
f
o
r
tech
n
ical
ter
m
s
f
r
o
m
th
e
I
n
d
u
s
tr
ial
T
ec
h
n
o
lo
g
y
R
ese
ar
ch
I
n
s
titu
te
(
I
T
R
I
)
k
n
o
wled
g
e
b
a
s
e.
I
t
is
a
b
asic
an
d
s
im
p
le
k
n
o
wled
g
e
g
r
a
p
h
f
o
r
tr
an
s
f
er
r
in
g
in
f
o
r
m
atio
n
f
r
o
m
a
s
o
u
r
ce
d
o
m
ain
to
a
tar
g
et
d
o
m
ain
.
I
t c
an
b
e
m
o
r
e
co
m
p
lex
to
f
u
lly
e
x
p
lo
it th
e
b
en
ef
its
o
f
th
e
s
em
an
tic
web
i
n
th
e
C
DR
S.
On
b
alan
ce
,
C
DR
S,
b
y
lev
er
ag
in
g
L
OD
tech
n
o
lo
g
y
,
g
en
er
all
y
s
o
lv
ed
th
e
p
r
o
b
lem
s
o
f
R
S,
p
ar
ticu
lar
ly
th
e
co
ld
-
s
tar
t
is
s
u
e.
T
h
is
is
b
ec
au
s
e
L
OD
tech
n
o
lo
g
y
ca
n
e
x
tr
ac
t
an
d
ac
ce
s
s
p
u
b
licly
a
v
ailab
le
d
ata
o
f
u
s
er
s
o
n
a
n
ew
p
latf
o
r
m
th
at
o
n
ly
h
as
litt
le
o
r
n
o
in
f
o
r
m
atio
n
ab
o
u
t
th
e
u
s
e
r
s
.
Mo
r
eo
v
er
,
L
OD
t
ec
h
n
o
lo
g
y
ca
n
b
e
lev
er
ag
ed
b
y
e
x
tr
ac
tin
g
p
u
b
licly
av
ailab
le
d
ata,
s
u
ch
as
a
u
s
er
-
item
r
atin
g
m
atr
ix
,
t
o
all
ev
iate
d
ata
s
p
ar
s
ity
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
r
ev
iew
o
f th
e
imp
a
cts o
f lin
ke
d
o
p
e
n
d
a
t
a
o
n
cro
s
s
-
d
o
ma
in
r
ec
o
mme
n
d
er sys
tems …
(
Y
u
i Ch
ee
X
u
a
n
)
1189
Alth
o
u
g
h
c
r
o
s
s
-
d
o
m
ain
a
n
d
L
OD
ca
n
s
er
v
e
as
an
ap
p
r
o
a
ch
to
allev
iate
d
ata
s
p
ar
s
ity
i
s
s
u
es,
g
en
er
atin
g
a
m
ap
p
i
n
g
r
elatio
n
b
etwe
en
d
if
f
er
en
t d
o
m
ai
n
s
u
s
in
g
L
OD
tech
n
o
lo
g
y
m
ig
h
t
b
e
ch
allen
g
in
g
.
4.
DIS
CU
SS
I
O
N
R
S
is
cr
u
cial
to
d
ay
f
o
r
b
o
o
s
tin
g
a
p
ar
ticu
lar
web
s
ite'
s
o
r
o
n
lin
e
b
u
s
in
ess
's
r
ev
en
u
e
[
7
3
]
.
As
an
illu
s
tr
atio
n
,
co
n
s
id
er
an
o
n
lin
e
b
o
o
k
s
to
r
e
t
h
at
u
tili
ze
s
a
RS
t
o
p
r
o
v
id
e
b
o
o
k
r
ec
o
m
m
e
n
d
ati
o
n
s
to
en
h
a
n
ce
th
e
o
v
er
all
u
s
er
ex
p
e
r
ien
ce
a
n
d
i
n
cr
ea
s
e
th
e
ch
a
n
ce
o
f
th
e
tr
an
s
ac
tio
n
o
cc
u
r
r
in
g
[
7
4
]
.
Acc
o
r
d
in
g
to
Ma
an
d
L
iu
[
7
5
]
,
r
a
t
i
n
g
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
cy
i
n
a
w
e
b
s
it
e
t
h
at
u
t
i
li
z
es
a
RS
i
n
f
l
u
e
n
c
es
t
h
e
u
s
e
r
e
x
p
e
r
i
e
n
ce
a
n
d
t
h
e
c
o
m
p
a
n
y
'
s
p
r
o
f
i
t
a
b
i
l
i
t
y
.
A
RS
'
s
c
o
l
d
-
s
t
a
r
t
a
n
d
d
a
t
a
s
p
a
r
s
i
t
y
i
s
s
u
es
m
u
s
t
b
e
a
d
d
r
e
s
s
e
d
t
o
g
u
a
r
a
n
t
e
e
r
a
t
i
n
g
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
.
W
e
u
n
d
er
s
tan
d
th
at
a
C
DR
S
is
well
-
v
er
s
ed
in
s
o
lv
in
g
th
e
co
ld
-
s
tar
t
p
r
o
b
lem
an
d
allev
i
atin
g
d
ata
s
p
ar
s
i
ty
is
s
u
es.
Ho
wev
er
,
th
e
p
r
iv
ac
y
a
n
d
leg
al
co
n
ce
r
n
s
o
f
u
s
er
s
p
r
ev
en
t
d
o
m
ain
s
with
e
n
o
u
g
h
r
atin
g
s
f
r
o
m
s
h
ar
in
g
th
eir
u
s
er
s
'
r
atin
g
s
wit
h
o
th
er
R
S
o
r
d
o
m
ain
s
[
6
3
]
.
Giv
en
th
e
ad
v
an
tag
es
o
f
th
e
C
DR
S
m
o
d
el,
s
ec
u
r
e
u
s
er
s
'
p
r
iv
ac
y
c
an
av
o
id
leg
al
co
n
ce
r
n
s
an
d
s
im
u
ltan
eo
u
s
ly
e
n
s
u
r
e
C
DR
S
's
p
er
f
o
r
m
a
n
ce
.
H
o
wev
er
,
we
r
e
q
u
ir
e
o
p
en
-
ac
ce
s
s
d
ata
th
at
ca
n
b
e
u
tili
ze
d
in
C
D
R
S.
Fo
r
tu
n
ately
,
we
d
is
co
v
er
ed
an
d
e
x
am
in
ed
t
h
e
C
DR
S
th
at
u
s
es
L
OD
to
allev
iate
d
ata
s
p
ar
s
it
y
is
s
u
es
s
in
ce
L
OD
i
s
a
k
n
o
wled
g
e
g
r
ap
h
th
at
ca
n
b
e
ac
c
ess
ed
o
p
en
ly
.
I
n
th
e
m
ea
n
tim
e,
we
ca
n
e
n
s
u
r
e
th
e
h
ig
h
p
e
r
f
o
r
m
an
ce
o
f
th
e
C
DR
S.
Acc
o
r
d
in
g
t
o
Ver
as
et
a
l.
[
6
8
]
,
th
e
lack
o
f
p
u
b
licly
av
ailab
l
e
d
ata
in
d
icatin
g
th
e
r
atin
g
s
o
f
th
e
s
am
e
u
s
er
s
o
n
th
in
g
s
ca
teg
o
r
ized
in
s
ev
er
al
d
o
m
ain
s
m
ak
es
test
in
g
cr
o
s
s
-
d
o
m
ain
RS
s
ch
allen
g
in
g
.
Hen
ce
,
to
tack
le
th
e
lack
o
f
p
u
b
licly
av
aila
b
le
d
ata,
we
ca
n
a
p
p
ly
L
OD
in
C
DR
S.
I
t
is
ea
s
y
to
q
u
er
y
,
ac
ce
s
s
,
an
d
in
teg
r
ate
th
e
d
ata
o
p
en
ly
with
th
e
av
ailab
le
k
n
o
wled
g
e
g
r
ap
h
o
n
th
e
s
em
a
n
tic
web
.
T
h
is
s
tu
d
y
h
as e
x
a
m
in
ed
th
e
im
p
ac
ts
o
f
L
OD
in
th
e
p
er
f
o
r
m
a
n
ce
o
f
C
DR
S.
I
n
s
o
m
e
s
itu
atio
n
s
wh
er
e
p
r
o
v
id
in
g
r
ec
o
m
m
e
n
d
atio
n
s
to
a
g
r
o
u
p
o
f
u
s
er
s
r
ath
er
th
an
an
in
d
iv
id
u
al
is
p
r
ev
alen
t
an
d
n
ec
ess
ar
y
,
th
i
s
also
m
o
tiv
ates
u
s
to
ex
a
m
in
e
ex
is
tin
g
m
eth
o
d
o
lo
g
ies
th
at
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
an
d
r
ec
o
m
m
en
d
atio
n
q
u
ality
o
f
GR
S.
W
h
ile
ea
r
lier
s
tu
d
ies
h
av
e
ex
p
lo
r
e
d
th
e
im
p
ac
ts
o
f
L
OD
tech
n
o
lo
g
y
o
r
c
r
o
s
s
-
d
o
m
ain
a
p
p
r
o
ac
h
in
d
ep
e
n
d
en
tl
y
in
GR
S,
th
ey
h
av
e
n
o
t
ex
p
licitly
ad
d
r
ess
ed
th
e
in
f
lu
en
ce
o
f
in
teg
r
atin
g
b
o
th
L
OD
tech
n
o
lo
g
y
an
d
cr
o
s
s
-
d
o
m
ain
ap
p
r
o
ac
h
es
in
GR
S.
Hen
ce
,
we
d
is
co
v
er
ed
th
e
g
ap
s
i
n
p
r
ev
io
u
s
r
esear
c
h
an
d
th
e
GR
S's
p
o
ten
tial f
u
tu
r
e
d
i
r
ec
tio
n
.
4
.
1
.
Cro
s
s
-
do
ma
in o
n g
ro
up
re
co
mm
ender
s
y
s
t
em
Un
lik
e
C
DR
S,
a
tr
en
d
f
o
r
i
n
d
iv
id
u
al
R
S,
th
e
id
ea
o
f
cr
o
s
s
-
d
o
m
ain
h
as
y
et
to
b
e
ex
p
lo
ited
to
its
f
u
ll
p
o
ten
tial
in
GR
S.
Acc
o
r
d
in
g
to
L
ian
g
et
a
l.
[
2
4
]
,
v
a
r
io
u
s
cr
o
s
s
-
d
o
m
ain
s
o
lu
tio
n
s
ar
e
o
f
ten
d
ev
elo
p
ed
f
o
r
in
d
iv
id
u
al
R
S
an
d
c
a
n
n
o
t
b
e
a
p
p
l
i
e
d
d
i
r
e
c
t
l
y
i
n
t
o
t
h
e
c
o
n
t
e
x
t
o
f
G
R
S
.
W
e
m
u
s
t
c
o
n
s
i
d
e
r
t
h
e
f
u
n
d
a
m
e
n
t
a
l
p
r
o
c
e
s
s
o
f
G
R
S
w
h
i
le
c
r
e
a
ti
n
g
a
n
e
w
s
o
l
u
t
i
o
n
t
o
s
o
l
v
e
i
ts
d
r
a
w
b
a
c
k
s
,
a
s
d
is
c
u
s
s
e
d
p
r
e
v
i
o
u
s
l
y
i
n
s
e
c
t
io
n
1
:
I
n
t
r
o
d
u
c
t
i
o
n
.
T
h
e
e
x
i
s
t
i
n
g
s
t
u
d
i
es
i
n
v
o
l
v
i
n
g
C
DR
S
f
o
r
g
r
o
u
p
s
w
i
l
l
b
e
t
h
e
m
a
i
n
f
o
c
u
s
o
f
t
h
e
f
o
l
l
o
w
i
n
g
d
i
s
c
u
s
s
i
o
n
.
I
n
t
h
e
p
u
b
l
i
s
h
e
d
e
v
i
d
e
n
c
e
,
w
e
f
o
u
n
d
t
h
a
t
t
h
e
C
DR
S
f
o
r
g
r
o
u
p
s
is
n
o
t
f
r
e
q
u
e
n
t
l
y
o
b
s
e
r
v
e
d
.
I
n
l
i
g
h
t
o
f
t
h
i
s
,
w
e
h
a
v
e
p
r
e
p
a
r
e
d
a
s
u
m
m
a
r
y
o
f
t
h
r
e
e
p
r
i
o
r
s
t
u
d
i
es
co
n
ce
r
n
in
g
t
h
e
C
DR
S f
o
r
g
r
o
u
p
s
,
as sh
o
wn
in
T
a
b
le
3
.
Ac
co
r
d
in
g
to
R
ich
a
an
d
B
ed
i
[
2
3
]
,
th
e
"c
r
o
s
s
d
o
m
ain
g
r
o
u
p
r
ec
o
m
m
en
d
e
r
s
y
s
tem
(
C
DGR
S
)
"
m
eth
o
d
,
s
h
o
wn
in
T
ab
le
3
,
is
s
u
p
er
i
o
r
to
th
e
tr
ad
itio
n
al
GR
S.
T
h
e
au
t
h
o
r
s
in
tr
o
d
u
ce
th
e
cr
o
s
s
-
d
o
m
a
in
w
ay
an
d
C
DGRS
to
d
ea
l
with
th
e
s
ev
er
e
co
ld
-
s
tar
t
an
d
d
ata
s
p
ar
s
ity
p
r
o
b
le
m
s
in
th
e
GR
S
tar
g
et
d
o
m
ain
b
y
u
tili
zin
g
th
e
k
n
o
wled
g
e
f
r
o
m
t
h
e
s
o
u
r
c
e
d
o
m
ai
n
.
Delh
i'
s
r
estau
r
a
n
ts
,
to
u
r
is
t
attr
ac
tio
n
s
,
s
h
o
p
p
in
g
ar
ea
s
,
a
n
d
ac
co
m
m
o
d
atio
n
s
in
Delh
i
ar
e
all
in
clu
d
ed
in
f
o
u
r
s
u
b
d
o
m
ain
s
o
f
th
e
to
u
r
is
m
d
ataset.
"Z
o
m
ato
",
"M
ak
eM
y
T
r
ip
",
"T
r
ip
Ad
v
is
o
r
",
"De
lh
i
T
o
u
r
is
m
",
an
d
"Sh
o
p
Kh
o
jc"
web
s
ites
ar
e
u
s
ed
to
co
llect
in
f
o
r
m
ati
o
n
ab
o
u
t r
estau
r
a
n
ts
,
h
o
tels
,
to
u
r
i
s
t d
esti
n
atio
n
s
,
an
d
s
h
o
p
p
in
g
l
o
ca
tio
n
s
.
I
n
th
is
s
tu
d
y
,
o
n
ly
th
e
u
s
er
s
with
a
g
o
o
d
r
ep
u
tatio
n
an
d
tr
u
s
two
r
th
in
ess
ar
e
in
f
lu
en
tial
an
d
ca
n
co
n
tr
ib
u
te
th
eir
o
p
in
io
n
s
to
th
e
g
r
o
u
p
r
ec
o
m
m
en
d
atio
n
s
.
T
r
ad
itio
n
al
GR
S
s
er
v
ed
as
a
b
a
s
elin
e
m
eth
o
d
to
c
o
m
p
ar
e
with
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
a
n
d
v
er
if
y
th
e
ef
f
ec
tiv
e
n
ess
o
f
C
DGRS
b
y
u
s
in
g
"F
-
me
asu
r
e"
,
"
m
ea
n
a
b
s
o
lu
te
er
r
o
r
"
,
"p
r
ec
is
io
n
",
an
d
"r
ec
all
".
T
h
e
p
r
o
p
o
s
ed
C
DGRS
o
u
tp
er
f
o
r
m
s
tr
ad
itio
n
al
GR
S.
Mo
r
eo
v
er
,
L
ian
g
et
a
l.
[
3
2
]
s
u
p
p
o
r
t
th
e
r
esu
lts
o
f
C
DGRS
b
y
R
ich
a
an
d
B
ed
i
[
2
3
]
.
T
h
e
au
th
o
r
s
b
eliev
e
th
at
u
s
in
g
in
d
iv
i
d
u
al
R
S
m
eth
o
d
s
in
GR
S
with
p
r
e
-
d
e
f
in
ed
ag
g
r
eg
atio
n
s
tr
ateg
ies
is
wh
y
GR
S
s
u
f
f
er
s
f
r
o
m
d
ata
s
p
ar
s
ity
is
s
u
es.
Acc
o
r
d
in
g
to
L
ian
g
e
t
a
l.
[
3
2
]
,
th
e
s
u
g
g
este
d
C
DGR
S
with
a
g
en
er
alize
d
ag
g
r
eg
atio
n
s
tr
ateg
y
g
iv
es
d
ec
is
io
n
-
m
ak
er
s
m
o
r
e
f
l
ex
ib
ilit
y
to
ch
o
o
s
e
th
e
id
ea
l
a
g
g
r
eg
atio
n
tech
n
iq
u
e
b
ased
o
n
p
r
ac
ti
ca
l
d
ec
is
io
n
s
ce
n
ar
io
s
.
T
h
is
is
b
ec
au
s
e
th
e
p
r
o
p
o
s
ed
C
DGRS
in
clu
d
es
th
e
av
er
ag
e,
m
ax
im
u
m
,
a
n
d
m
i
n
im
u
m
s
tr
ateg
ies
as
ag
g
r
eg
atio
n
s
tr
ateg
ies
in
s
tead
o
f
t
h
e
p
r
i
o
r
GR
S'
s
s
in
g
le
ag
g
r
e
g
atio
n
s
tr
ateg
y
.
T
h
e
p
r
o
p
o
s
ed
C
DGRS
o
u
tp
er
f
o
r
m
s
th
e
o
th
er
b
aselin
e
m
eth
o
d
s
th
a
t w
er
e
ch
o
s
en
b
y
th
e
au
th
o
r
s
in
th
e
ex
p
er
im
e
n
ts
u
s
in
g
a
r
ea
l
-
wo
r
ld
d
ata
s
et
C
A
MRa2
0
1
1
,
wh
ich
is
a
m
o
v
ie
r
atin
g
r
ec
o
r
d
o
f
g
r
o
u
p
m
em
b
er
s
b
ased
o
n
two
e
v
alu
atio
n
m
etr
ics
-
"M
AE
"
an
d
"
R
MSE
".
Data
s
p
ar
s
ity
in
GR
S is
a
well
-
k
n
o
wn
is
s
u
e
th
at
L
ian
g
et
a
l.
[
2
4
]
o
f
f
er
e
d
a
n
o
v
el
a
p
p
r
o
ac
h
to
ad
d
r
ess
th
is
,
ca
lled
th
e
"h
ier
a
r
ch
ical
atten
tio
n
n
eu
r
al
-
n
etwo
r
k
-
b
ase
d
cr
o
s
s
-
d
o
m
ai
n
g
r
o
u
p
r
ec
o
m
m
en
d
atio
n
m
eth
o
d
(
HAN
-
C
DG
R
)
",
as su
m
m
ar
is
ed
in
T
a
b
le
3
.
T
h
e
r
esu
lts
o
f
t
h
i
s
p
r
o
p
o
s
ed
m
eth
o
d
o
u
tp
er
f
o
r
m
th
e
o
t
h
er
b
aselin
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
2
,
May
20
2
5
:
1
1
8
1
-
1
1
9
4
1190
m
eth
o
d
s
ch
o
s
en
b
y
th
e
au
th
o
r
s
in
th
e
e
x
p
er
im
en
t.
Fo
r
in
s
tan
ce
,
"Bay
esian
p
er
s
o
n
alize
d
r
an
k
in
g
(
B
PR
)
"
f
o
r
in
d
iv
id
u
al
an
d
g
r
o
u
p
r
ec
o
m
m
en
d
atio
n
s
[
7
6
]
,
C
DR
S
with
it
em
o
v
er
lap
p
i
n
g
f
o
r
g
r
o
u
p
r
ec
o
m
m
en
d
atio
n
task
s
[
7
7
]
b
aselin
e
m
eth
o
d
s
.
E
f
f
ec
tiv
e
k
n
o
wled
g
e
tr
an
s
f
er
f
r
o
m
a
s
o
u
r
ce
d
o
m
ai
n
to
a
tar
g
et
d
o
m
ain
is
ac
co
m
p
lis
h
ed
th
r
o
u
g
h
a
d
v
er
s
ar
ial
lea
r
n
in
g
.
T
h
e
au
t
h
o
r
s
c
r
ea
ted
a
v
a
r
ian
t
o
f
HAN
-
C
DGR,
ca
lled
HAN
-
GR
,
th
at
ex
clu
d
es
ad
v
er
s
ar
ial
lear
n
in
g
in
th
e
c
r
o
s
s
-
d
o
m
ain
k
n
o
wled
g
e
tr
an
s
f
er
p
r
o
ce
s
s
to
v
alid
ate
th
e
h
ier
ar
ch
ical
n
eu
r
al
n
etwo
r
k
'
s
ef
f
ec
tiv
en
ess
.
C
o
m
p
ar
in
g
th
e
r
esu
lts
o
f
HAN
-
C
DGR an
d
HAN
-
GR
s
h
o
wed
th
at
th
e
GR
S,
u
s
in
g
th
e
cr
o
s
s
-
d
o
m
ain
m
eth
o
d
,
d
r
am
ati
ca
lly
en
h
a
n
ce
s
th
e
p
er
f
o
r
m
an
c
e
o
f
b
o
th
u
s
er
a
n
d
g
r
o
u
p
r
ec
o
m
m
en
d
atio
n
s
i
n
th
e
tar
g
et
d
o
m
ain
.
B
y
tr
an
s
f
er
r
i
n
g
in
f
o
r
m
atio
n
f
r
o
m
a
s
o
u
r
ce
d
o
m
ain
,
HAN
-
C
DGR
ca
n
o
u
tp
er
f
o
r
m
th
e
o
th
er
elev
en
b
aselin
e
m
eth
o
d
s
,
in
clu
d
in
g
HAN
-
GR
.
T
h
e
au
th
o
r
s
v
alid
ate
th
e
s
tr
en
g
th
o
f
cr
o
s
s
-
d
o
m
ain
in
GR
S.
I
n
ter
m
s
o
f
th
e
d
ataset,
th
e
Ma
f
en
g
wo
d
ataset
f
r
o
m
th
e
to
u
r
i
s
m
web
s
ite,
th
e
Yelp
d
ataset
f
r
o
m
th
e
r
estau
r
an
t
d
o
m
ain
,
C
AM
R
a2
0
1
1
,
wh
ich
i
s
a
m
o
v
ie
r
atin
g
r
ec
o
r
d
o
f
g
r
o
u
p
m
em
b
er
s
,
Mo
v
ieL
en
s
1
M,
M
o
v
ieL
en
s
2
5
M,
an
d
Mo
v
ieL
en
s
-
Simi
d
atasets
ar
e
b
ein
g
u
s
ed
i
n
th
e
ex
p
er
im
en
ts
.
T
ab
le
3
.
A
s
u
m
m
a
r
y
o
f
ex
is
tin
g
wo
r
k
s
r
e
g
ar
d
in
g
th
e
cr
o
s
s
-
d
o
m
ain
g
r
o
u
p
RS
s
P
a
p
e
r
P
r
o
b
l
e
m
/
p
u
r
p
o
se
M
e
t
h
o
d
D
o
ma
i
n
/
d
a
t
a
se
t
R
i
c
h
a
a
n
d
B
e
d
i
[
2
3
]
To
s
o
l
v
e
c
o
l
d
s
t
a
r
t
a
n
d
d
a
t
a
sp
a
r
si
t
y
i
s
su
e
s i
n
G
R
S
C
D
G
R
S
(
1
)
R
e
st
a
u
r
a
n
t
(
2
)
H
o
t
e
l
(
3
)
T
o
u
r
i
st
P
l
a
c
e
s
(
4
)
S
h
o
p
p
i
n
g
Li
a
n
g
e
t
a
l
.
[
3
2
]
To
a
l
l
e
v
i
a
t
e
d
a
t
a
s
p
a
r
s
i
t
y
i
n
G
R
S
C
D
G
R
S
w
i
t
h
a
g
e
n
e
r
a
l
i
z
e
d
a
g
g
r
e
g
a
t
i
o
n
st
r
a
t
e
g
y
(
1
)
M
o
v
i
e
(
u
s
e
r
a
n
d
g
r
o
u
p
’
s
r
a
t
i
n
g
s)
Li
a
n
g
e
t
a
l
.
[
2
4
]
To
s
o
l
v
e
d
a
t
a
s
p
a
r
s
i
t
y
i
n
G
R
S
HAN
-
C
D
G
R
(
1
)
T
o
u
r
i
sm
(
2
)
R
e
st
a
u
r
a
n
t
(
3
)
M
o
v
i
e
I
n
R
S a
n
d
GR
S,
th
e
d
ata
s
p
ar
s
ity
is
s
u
e
is
s
ev
er
e.
T
h
e
r
e
ar
e
m
an
y
way
s
to
s
im
u
ltan
e
o
u
s
ly
r
ed
u
ce
d
ata
s
p
ar
s
ity
an
d
en
h
an
ce
th
e
p
er
f
o
r
m
an
ce
o
f
R
S
an
d
GR
S.
T
h
er
e
ar
e
s
o
m
e
f
in
d
in
g
s
o
n
th
e
im
p
a
ct
o
f
cr
o
s
s
-
d
o
m
ain
an
d
L
OD
o
n
th
e
p
er
f
o
r
m
an
ce
o
f
R
S
an
d
GR
S.
W
e
f
o
u
n
d
t
h
at
o
n
ly
C
DR
S
f
o
r
g
r
o
u
p
s
an
d
C
DR
S
with
L
OD
tech
n
o
lo
g
y
f
o
r
in
d
i
v
id
u
al
R
S
ar
e
im
p
lem
en
ted
in
cu
r
r
e
n
t
r
esear
ch
,
b
u
t
n
o
t
b
o
th
.
Sin
ce
th
er
e
ar
e
s
o
m
e
em
p
ir
ical
s
tu
d
ies
o
n
t
h
e
in
teg
r
atio
n
o
f
L
OD
an
d
cr
o
s
s
-
d
o
m
ai
n
ap
p
r
o
ac
h
in
th
e
i
n
d
iv
id
u
al
R
S
b
ase
d
o
n
th
e
liter
atu
r
e
r
ev
ie
w,
th
is
s
tu
d
y
s
u
g
g
ests
ex
p
lo
r
in
g
th
e
i
n
teg
r
atio
n
o
f
L
O
D
an
d
cr
o
s
s
-
d
o
m
ain
a
p
p
r
o
ac
h
in
GR
S
th
at
h
as
y
et
to
b
e
s
tu
d
ied
to
in
cr
ea
s
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
g
r
o
u
p
r
ec
o
m
m
e
n
d
atio
n
s
.
T
h
is
is
b
ec
au
s
e
n
o
r
elate
d
wo
r
k
s
o
n
th
e
cr
o
s
s
-
d
o
m
ain
GR
S
with
L
OD
tech
n
o
lo
g
y
ar
e
cu
r
r
e
n
tly
ex
p
lo
r
ed
.
Hen
ce
,
o
u
r
s
tu
d
y
id
en
tifie
d
th
e
r
esear
ch
g
ap
s
th
at
n
ee
d
to
b
e
ex
p
lo
r
ed
i
n
f
u
t
u
r
e
r
esear
ch
.
W
e
ex
p
er
im
en
ted
with
th
e
c
o
m
b
in
atio
n
o
f
c
r
o
s
s
-
d
o
m
ain
an
d
L
OD
ap
p
r
o
ac
h
es
an
d
v
e
r
if
ied
th
e
p
er
f
o
r
m
an
ce
with
b
etter
ac
cu
r
ac
y
r
esu
lts
in
in
d
iv
id
u
al
R
S
[
7
8
]
.
Ou
r
s
tu
d
y
d
em
o
n
s
tr
ated
th
at
th
is
in
teg
r
atio
n
o
f
m
eth
o
d
o
l
o
g
ies
was
s
u
p
er
io
r
to
o
th
er
co
m
p
ar
ab
le
r
esu
lts
in
th
at
p
ap
er
.
Ho
wev
er
,
f
u
r
th
e
r
an
d
in
-
d
e
p
th
an
aly
s
is
m
ay
b
e
n
ee
d
ed
to
co
n
f
ir
m
its
p
er
f
o
r
m
a
n
ce
in
GR
S
in
s
tead
o
f
in
d
iv
id
u
al
R
S,
esp
ec
ially
r
eg
ar
d
in
g
th
e
allev
iatio
n
o
f
d
ata
s
p
ar
s
ity
is
s
u
e.
Fu
tu
r
e
s
tu
d
ies
m
ay
ex
p
lo
r
e
to
f
u
r
th
er
allev
iate
d
ata
s
p
ar
s
i
ty
i
s
s
u
e
wi
th
f
ea
s
ib
le
way
s
o
f
in
teg
r
atin
g
c
r
o
s
s
-
d
o
m
ain
an
d
L
OD
ap
p
r
o
a
ch
es
p
r
io
r
t
o
g
r
o
u
p
f
o
r
m
atio
n
o
f
a
n
ew
g
r
o
u
p
p
r
o
f
ile
an
d
v
e
r
if
y
its
p
er
f
o
r
m
an
ce
in
GR
S.
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
Fro
m
th
e
ex
ten
s
iv
e
liter
atu
r
e
r
ev
iew
o
n
cr
o
s
s
-
d
o
m
ain
tec
h
n
i
q
u
es,
we
c
a
n
c
o
n
clu
d
e
th
at
th
e
C
DR
S
i
s
g
en
er
ally
s
u
p
er
io
r
to
th
e
tr
ad
itio
n
al
R
S
f
o
r
in
d
iv
id
u
als
an
d
g
r
o
u
p
s
.
Sin
ce
L
OD
tech
n
o
lo
g
y
h
as
r
ec
en
tly
g
ain
ed
p
o
p
u
lar
ity
in
i
n
d
iv
id
u
al
R
S
to
allev
iate
th
e
R
S
p
r
o
b
lem
s
,
p
ar
t
icu
lar
ly
th
e
d
ata
s
p
ar
s
ity
,
L
OD
tech
n
o
lo
g
y
s
h
o
u
ld
b
e
f
u
lly
e
x
p
lo
ited
a
n
d
im
p
le
m
en
ted
in
C
DR
S f
o
r
g
r
o
u
p
s
to
a
llev
iate
th
e
d
ata
s
p
ar
s
ity
is
s
u
e.
T
h
is
wo
r
k
em
p
h
asizes
th
e
ap
p
ar
en
t
p
o
ten
tial
r
esear
ch
g
ap
o
n
o
u
r
d
is
cu
s
s
ed
to
p
ic
co
m
p
ar
ed
to
ex
is
tin
g
s
tu
d
ies.
B
esid
es
th
at,
we
aim
t
o
id
en
tif
y
th
e
f
u
tu
r
e
d
ir
ec
tio
n
s
f
o
r
th
e
r
esear
ch
p
o
s
s
ib
ilit
ies
i
n
GR
S.
I
n
ad
d
itio
n
to
co
n
tr
i
b
u
tin
g
to
th
e
GR
S,
th
i
s
wo
r
k
will
f
ac
ilit
ate
g
r
o
u
p
r
e
s
ea
r
ch
o
n
C
DR
S
'
s
f
u
tu
r
e
d
ir
ec
tio
n
s
,
em
p
h
asizin
g
th
e
u
s
e
o
f
lin
k
ed
o
p
en
d
ata.
I
n
a
n
u
ts
h
ell,
b
ased
o
n
th
e
r
e
v
iew
an
d
v
iewp
o
in
t
an
aly
s
is
ab
o
v
e,
we
b
e
liev
e
th
at
th
e
C
DR
S,
b
y
lev
er
ag
in
g
L
O
D
tech
n
o
lo
g
y
,
e
n
s
u
r
es
th
e
p
er
f
o
r
m
an
ce
o
f
a
co
m
p
lex
RS
th
at
ca
n
g
iv
e
ex
ce
llen
t
an
d
r
elev
a
n
t r
ec
o
m
m
en
d
atio
n
s
to
u
s
er
s
u
s
in
g
p
u
b
licly
av
aila
b
le
d
ata
th
r
o
u
g
h
DB
p
ed
ia,
as
an
ex
am
p
le.
Hen
ce
,
th
e
co
m
b
in
atio
n
o
f
L
OD
an
d
cr
o
s
s
-
d
o
m
ain
ap
p
r
o
ac
h
es
in
GR
S
s
h
o
u
ld
b
e
in
v
esti
g
ated
in
d
ep
th
in
f
u
tu
r
e
r
esear
ch
.
T
h
is
is
b
ec
au
s
e
th
e
GR
S i
s
also
p
r
ag
m
atic
in
s
o
m
e
cir
cu
m
s
tan
ce
s
.
I
n
th
e
f
u
tu
r
e
s
tu
d
y
,
with
th
e
g
o
als
an
d
m
o
tiv
atio
n
s
to
im
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
GR
S
to
p
r
o
v
id
e
m
o
r
e
ac
cu
r
ate
r
ec
o
m
m
en
d
atio
n
s
to
a
g
r
o
u
p
o
f
u
s
er
s
in
t
h
e
u
s
e
ca
s
es
we
d
is
cu
s
s
ed
in
in
t
r
o
d
u
ctio
n
,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.