I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
24
,
p
p
.
6
8
8
3
~
6
8
9
3
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
6
8
8
3
-
6
8
9
3
6883
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
A
no
v
el semi
-
su
p
ervi
sed co
nsens
us
f
uzzy
c
lusteri
ng
metho
d f
o
r
multi
-
v
iew
relatio
na
l data
H
o
a
ng
T
hi Ca
nh
1,
2
,
P
ha
m
H
uy
T
ho
ng
3
,
P
hu
ng
T
he
H
ua
n
2
,
Vu Th
uy
T
ra
ng
4
,
Ng
uy
en
Nhu H
ieu
5
,
Ng
uy
en
T
ien P
h
uo
ng
6
,
Ng
uy
en
Nhu So
n
6
1
G
r
a
d
u
a
t
e
U
n
i
v
e
r
s
i
t
y
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
V
i
e
t
n
a
m A
c
a
d
e
m
y
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
H
a
n
o
i
,
V
i
e
t
n
a
m
2
F
a
c
u
l
t
y
o
f
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
Th
a
i
N
g
u
y
e
n
U
n
i
v
e
r
s
i
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
T
h
a
i
N
g
u
y
e
n
,
V
i
e
t
n
a
m
3
F
a
c
u
l
t
y
o
f
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
H
a
n
o
i
U
n
i
v
e
r
s
i
t
y
o
f
I
n
d
u
st
r
y
,
H
a
n
o
i
,
V
i
e
t
n
a
m
4
F
a
c
u
l
t
y
o
f
M
a
t
h
e
m
a
t
i
c
s,
M
e
c
h
a
n
i
c
s
a
n
d
I
n
f
o
r
mat
i
c
s
,
H
a
n
o
i
U
n
i
v
e
r
s
i
t
y
o
f
S
c
i
e
n
c
e
,
V
i
e
t
n
a
m N
a
t
i
o
n
a
l
U
n
i
v
e
r
si
t
y
,
H
a
n
o
i
,
V
i
e
t
n
a
m
5
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
V
i
e
t
t
e
l
P
o
s
t
C
o
r
p
o
r
a
t
i
o
n
,
H
a
n
o
i
,
V
i
e
t
n
a
m
6
I
n
st
i
t
u
t
e
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
V
i
e
t
n
a
m
A
c
a
d
e
my
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
H
a
n
o
i
,
V
i
e
t
n
a
m
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
5
,
2
0
2
4
R
ev
is
ed
J
u
l 2
2
,
2
0
2
4
Acc
ep
ted
Au
g
6
,
2
0
2
4
M
u
lt
i
-
v
iew
d
a
ta
is
wid
e
ly
e
m
p
l
o
y
e
d
in
v
a
rio
u
s
d
o
m
a
in
s,
h
i
g
h
li
g
h
ti
n
g
th
e
n
e
e
d
fo
r
a
d
v
a
n
c
e
d
c
lu
ste
ri
n
g
m
e
t
h
o
d
o
l
o
g
ies
t
o
e
fficie
n
tl
y
e
x
trac
t
k
n
o
wle
d
g
e
fro
m
th
e
se
d
a
tas
e
ts.
Co
n
se
q
u
e
n
tl
y
,
m
u
lt
i
-
v
iew
c
lu
ste
ri
n
g
h
a
s
e
m
e
rg
e
d
a
s
a
p
ro
m
in
e
n
t
re
se
a
rc
h
to
p
ic
in
re
c
e
n
t
y
e
a
rs.
I
n
t
h
is
p
a
p
e
r,
we
p
ro
p
o
se
a
n
o
v
e
l
a
p
p
ro
a
c
h
:
th
e
se
m
i
-
su
p
e
rv
ise
d
c
o
n
se
n
su
s
f
u
z
z
y
c
lu
ste
ri
n
g
m
e
th
o
d
fo
r
m
u
l
ti
-
v
iew
re
latio
n
a
l
d
a
ta
(S
S
CF
M
C)
.
Th
is
m
e
th
o
d
c
o
m
b
i
n
e
s
th
e
a
d
v
a
n
tag
e
s
o
f
fu
z
z
y
c
lu
ste
ri
n
g
a
n
d
c
o
n
se
n
su
s
c
l
u
ste
rin
g
t
o
a
d
d
re
ss
th
e
c
h
a
ll
e
n
g
e
s
p
o
se
d
b
y
m
u
lt
i
-
v
iew
d
a
ta.
By
le
v
e
ra
g
in
g
a
v
a
il
a
b
le
la
b
e
led
in
f
o
rm
a
ti
o
n
a
n
d
th
e
re
latio
n
a
l
stru
c
t
u
re
a
m
o
n
g
v
iew
s,
o
u
r
m
e
th
o
d
a
ims
to
e
n
h
a
n
c
e
c
lu
ste
rin
g
p
e
rfo
rm
a
n
c
e
.
Ex
ten
si
v
e
e
x
p
e
rime
n
ts o
n
b
e
n
c
h
m
a
rk
d
a
tas
e
ts d
e
m
o
n
stra
te t
h
a
t
o
u
r
m
e
th
o
d
su
rp
a
ss
e
s
e
x
isti
n
g
sin
g
le
-
v
iew
a
n
d
m
u
l
ti
-
v
iew
re
latio
n
a
l
c
lu
ste
rin
g
a
lg
o
rit
h
m
s
in
term
s
o
f
a
c
c
u
ra
c
y
a
n
d
sta
b
il
it
y
.
S
p
e
c
ifi
c
a
ll
y
,
t
h
e
S
S
CF
M
C
a
l
g
o
rit
h
m
e
x
h
ib
it
s
s
u
p
e
rio
r
c
lu
ste
rin
g
p
e
rf
o
rm
a
n
c
e
a
c
ro
ss
v
a
rio
u
s
d
a
tas
e
ts,
a
c
h
iev
in
g
a
n
a
d
ju
ste
d
ra
n
d
i
n
d
e
x
(ARI)
o
f
0
.
6
8
o
n
th
e
m
u
lt
ip
le
fe
a
tu
re
s
d
a
tas
e
t
a
n
d
a
n
F
-
m
e
a
su
re
o
f
0
.
9
1
o
n
th
e
in
tern
e
t
d
a
tas
e
t,
h
ig
h
li
g
h
ti
n
g
it
s
ro
b
u
st
n
e
ss
a
n
d
e
fficie
n
c
y
.
Ov
e
ra
ll
,
t
h
is
st
u
d
y
a
d
v
a
n
c
e
s
m
u
lt
i
-
v
iew
c
lu
ste
ri
n
g
tec
h
n
i
q
u
e
s
fo
r
re
latio
n
a
l
d
a
ta
a
n
d
p
r
o
v
i
d
e
s
v
a
lu
a
b
le
in
sig
h
ts f
o
r
re
se
a
rc
h
e
rs i
n
th
is f
ield
.
K
ey
w
o
r
d
s
:
Mu
lti
-
v
iew
r
elatio
n
al
d
ata
C
lu
s
ter
in
g
Sem
i
-
s
u
p
er
v
is
ed
Fu
zz
y
clu
s
ter
in
g
Mu
lti
-
v
iew
clu
s
ter
in
g
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
:
Ng
u
y
en
Nh
u
So
n
I
n
s
titu
te
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Vietn
a
m
Aca
d
em
y
o
f
S
cien
ce
an
d
T
ec
h
n
o
lo
g
y
1
8
Ho
an
g
Qu
o
c
Viet
R
o
ad
,
C
au
Giay
Dis
tr
ict,
Ha
n
o
i,
Viet
n
am
E
m
ail: n
n
s
o
n
@
io
it.a
c.
v
n
1.
I
NT
RO
D
UCT
I
O
N
Mu
lti
-
v
iew
clu
s
ter
in
g
p
lay
s
a
cr
u
cial
r
o
le
in
d
ata
an
aly
s
is
,
e
s
p
ec
ially
wh
en
co
n
f
r
o
n
ted
with
d
iv
e
r
s
e
d
ata
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
.
U
n
lik
e
tr
ad
itio
n
al
m
et
h
o
d
s
,
it
i
m
p
r
o
v
es
f
le
x
ib
ilit
y
an
d
ac
cu
r
ac
y
b
y
i
n
teg
r
atin
g
in
f
o
r
m
atio
n
f
r
o
m
d
if
f
er
e
n
t
p
e
r
s
p
ec
tiv
es,
o
f
f
er
in
g
a
co
m
p
r
e
h
en
s
iv
e
v
iew
o
f
d
ata
s
tr
u
ctu
r
e
an
d
r
elatio
n
s
h
ip
s
.
T
h
is
n
o
t
o
n
ly
o
p
tim
izes
class
i
f
icatio
n
ca
p
ab
ilit
ies
b
u
t
also
d
ee
p
en
s
in
s
ig
h
ts
,
r
ev
ea
ls
h
id
d
en
in
f
o
r
m
atio
n
,
an
d
r
ed
u
ce
s
th
e
im
p
ac
t
o
f
n
o
is
e.
I
t
d
eliv
er
s
ac
cu
r
ate
an
d
m
ea
n
i
n
g
f
u
l
a
n
aly
tical
r
esu
lts
in
v
ar
io
u
s
f
ield
s
s
u
ch
as
d
ata
m
in
in
g
,
m
ar
k
etin
g
,
h
ea
lth
ca
r
e,
an
d
m
an
y
o
th
er
d
o
m
ain
s
[
1
]
,
[
2
]
.
“M
u
lti
-
v
iew
d
ata”
en
co
m
p
ass
es
in
f
o
r
m
atio
n
f
r
o
m
d
i
v
er
s
e
s
o
u
r
ce
s
,
m
eth
o
d
o
lo
g
ies,
o
r
p
er
s
p
ec
tiv
es
r
eg
ar
d
in
g
a
s
p
ec
if
ic
en
tity
,
ch
ar
ac
ter
ized
b
y
m
u
ltip
le
v
iews
o
f
f
er
in
g
v
ar
ied
in
s
ig
h
ts
with
v
ar
y
in
g
p
r
ec
is
io
n
an
d
r
eliab
ilit
y
.
M
u
lti
-
v
iew
clu
s
ter
in
g
(
Mv
C
)
is
a
cu
ttin
g
-
ed
g
e
ap
p
r
o
ac
h
in
d
ata
an
al
y
s
is
th
at
ad
d
r
ess
es
th
e
co
m
p
lex
ities
o
f
s
u
ch
d
ata
[
3
]
.
T
h
e
co
r
e
p
r
in
cip
le
o
f
m
u
lti
-
v
iew
clu
s
ter
in
g
is
its
a
b
ilit
y
to
h
a
r
n
ess
th
e
co
m
p
lem
en
tar
y
n
at
u
r
e
o
f
d
i
v
er
s
e
p
er
s
p
ec
tiv
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
8
8
3
-
6
8
9
3
6884
B
y
in
teg
r
atin
g
in
s
ig
h
ts
f
r
o
m
m
u
ltip
le
v
iews,
a
m
o
r
e
h
o
lis
tic
an
d
p
r
ec
is
e
r
e
p
r
esen
tatio
n
o
f
en
titi
es
ca
n
b
e
o
b
tain
ed
,
th
e
r
eb
y
g
r
ea
tly
im
p
r
o
v
in
g
d
ata
an
al
y
s
is
an
d
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es
[
3
]
.
T
h
is
in
n
o
v
ativ
e
clu
s
ter
in
g
tech
n
iq
u
e
is
in
cr
ea
s
in
g
ly
g
ain
in
g
p
r
o
m
in
en
ce
in
v
ar
io
u
s
f
iel
d
s
,
o
f
f
e
r
in
g
a
n
u
an
ce
d
an
d
h
o
lis
tic
ap
p
r
o
ac
h
to
u
n
d
er
s
tan
d
in
g
c
o
m
p
lex
d
atasets
an
d
u
n
co
v
e
r
in
g
h
id
d
en
p
atter
n
s
ac
r
o
s
s
d
if
f
er
en
t
d
im
en
s
io
n
s
.
T
h
e
s
u
cc
ess
o
f
th
e
m
u
lti
-
v
iew
clu
s
ter
in
g
(
Mv
C
)
alg
o
r
ith
m
r
elie
s
o
n
two
cr
u
cial
p
r
in
cip
les:
t
h
e
co
m
p
lem
en
tar
y
an
d
co
n
s
en
s
u
s
p
r
in
cip
les
[
4
]
.
T
h
e
c
o
m
p
lem
en
ta
r
y
p
r
in
cip
l
e
ass
er
ts
th
e
u
s
e
o
f
m
u
ltip
le
d
if
f
er
e
n
t
v
iews
to
co
m
p
r
eh
e
n
s
iv
ely
an
d
ac
cu
r
ately
d
escr
ib
e
d
ata
o
b
jects.
W
h
ile
ea
ch
v
iew
m
a
y
o
f
f
er
e
n
o
u
g
h
in
f
o
r
m
atio
n
f
o
r
a
p
ar
ticu
lar
k
n
o
wled
g
e
d
is
co
v
er
y
task
,
d
iv
er
s
e
v
iews
o
f
ten
en
co
m
p
ass
s
u
p
p
lem
en
tar
y
in
f
o
r
m
atio
n
th
at
s
h
o
u
ld
b
e
ex
p
l
o
ited
.
T
h
e
c
o
n
s
en
s
u
s
p
r
in
cip
le
in
m
u
lti
-
v
iew
clu
s
ter
in
g
aim
s
to
m
in
im
ize
co
n
f
licts
am
o
n
g
d
at
a
p
er
s
p
ec
tiv
es,
en
h
an
ci
n
g
c
o
h
e
r
en
ce
an
d
ac
cu
r
ac
y
in
clu
s
ter
in
g
alg
o
r
ith
m
s
b
y
in
te
g
r
atin
g
in
f
o
r
m
atio
n
f
r
o
m
v
ar
io
u
s
v
iewp
o
i
n
ts
co
n
s
is
ten
tly
.
T
h
e
m
u
lti
-
v
iew
clu
s
ter
in
g
m
et
h
o
d
b
r
i
n
g
s
n
u
m
er
o
u
s
ad
v
an
ta
g
es o
v
er
s
in
g
le
-
v
iew
clu
s
ter
in
g
m
eth
o
d
s
,
s
u
ch
as
[
5
]
,
[
6
]
:
Utilizin
g
d
iv
er
s
e
in
f
o
r
m
atio
n
,
in
cr
ea
s
in
g
co
h
er
en
ce
,
en
h
an
cin
g
ac
cu
r
ac
y
,
an
d
im
p
r
o
v
in
g
k
n
o
wled
g
e
d
is
co
v
e
r
y
ca
p
ab
ili
ties
.
Desp
ite
th
e
n
u
m
er
o
u
s
a
d
v
an
tag
es
o
f
m
u
lti
-
v
iew
clu
s
ter
in
g
o
v
er
s
in
g
le
-
v
iew
clu
s
ter
in
g
m
eth
o
d
s
,
it
h
as
also
en
co
u
n
ter
ed
an
d
is
cu
r
r
en
tly
f
ac
in
g
v
ar
io
u
s
d
if
f
icu
l
ties
an
d
ch
allen
g
es
s
u
ch
as
d
ata
s
tan
d
ar
d
izatio
n
[
7
]
,
f
ea
tu
r
e
s
elec
tio
n
[
8
]
,
[
9
]
,
th
e
in
te
g
r
atio
n
o
f
clu
s
ter
in
g
r
esu
lts
[
1
0
]
,
co
m
p
u
tatio
n
al
c
o
m
p
lex
ity
an
d
d
ata
ac
cu
r
ac
y
[
1
1
]
.
R
esear
ch
er
s
wo
r
ld
wid
e
h
av
e
p
r
o
p
o
s
ed
v
ar
io
u
s
s
o
lu
tio
n
s
to
th
ese
ch
allen
g
es.
Z
h
an
g
et
a
l
.
[
1
2
]
i
n
tr
o
d
u
ce
d
a
m
u
ltit
ask
m
u
ltiv
iew
clu
s
ter
in
g
alg
o
r
ith
m
u
tili
zin
g
lo
ca
lly
lin
ea
r
em
b
ed
d
in
g
(
L
L
E
)
an
d
L
ap
lacia
n
eig
en
m
ap
s
(
L
E
)
to
ad
d
r
ess
clu
s
ter
in
g
is
s
u
es
in
h
eter
o
g
en
e
o
u
s
s
ce
n
ar
io
s
.
C
ao
an
d
Xie
[
8
]
p
r
o
p
o
s
ed
a
u
n
i
f
ied
f
r
am
ewo
r
k
f
o
r
u
n
s
u
p
e
r
v
is
ed
m
u
lti
-
v
iew
f
ea
tu
r
e
s
elec
tio
n
,
lev
er
ag
in
g
co
n
s
en
s
u
s
lab
el
i
n
f
o
r
m
atio
n
to
e
n
h
an
ce
p
er
f
o
r
m
an
ce
.
L
iu
et
a
l.
[
1
0
]
in
tr
o
d
u
ce
d
a
m
u
lti
-
v
iew
clu
s
ter
in
g
m
eth
o
d
u
s
in
g
jo
in
t
n
o
n
n
e
g
ativ
e
m
atr
ix
f
ac
to
r
izatio
n
(
NM
F)
to
in
teg
r
ate
in
f
o
r
m
atio
n
an
d
en
h
an
ce
clu
s
ter
in
g
p
er
f
o
r
m
a
n
ce
.
W
an
g
et
a
l.
[
1
3
]
in
tr
o
d
u
ce
d
MV
C
-
L
FA,
a
d
ir
ec
t
an
d
ef
f
ec
tiv
e
ap
p
r
o
ac
h
t
o
m
ax
im
izin
g
alig
n
m
en
t
b
etwe
en
co
n
s
en
s
u
s
a
n
d
weig
h
ted
b
ase
p
a
r
titi
o
n
m
atr
ices
t
h
r
o
u
g
h
o
r
th
o
g
o
n
a
l
tr
an
s
f
o
r
m
atio
n
,
lead
in
g
to
r
ed
u
ce
d
co
m
p
u
tatio
n
al
co
m
p
lex
it
y
an
d
s
u
p
er
io
r
clu
s
ter
in
g
p
e
r
f
o
r
m
an
ce
co
m
p
ar
ed
to
s
tate
-
of
-
th
e
-
ar
t
m
eth
o
d
s
.
C
lu
s
ter
in
g
is
a
ch
allen
g
in
g
task
in
d
ata
m
in
in
g
,
p
ar
ticu
la
r
ly
f
o
r
co
m
p
lex
d
ata
[
1
4
]
,
[
1
5
]
.
D
esp
ite
th
e
wid
esp
r
ea
d
u
s
e
o
f
m
u
lti
-
v
iew
d
ata
in
r
ea
l
-
w
o
r
ld
a
p
p
licatio
n
s
,
m
o
s
t
ex
is
tin
g
clu
s
ter
in
g
alg
o
r
ith
m
s
ar
e
tailo
r
ed
f
o
r
s
in
g
le
-
v
iew
d
ata
[
1
6
]
.
C
o
n
s
eq
u
en
tly
,
th
er
e
is
a
s
tr
o
n
g
d
em
a
n
d
f
o
r
a
d
v
an
ce
d
clu
s
ter
in
g
m
et
h
o
d
s
t
o
ef
f
ec
tiv
ely
ex
tr
ac
t
k
n
o
wled
g
e
f
r
o
m
m
u
lti
-
v
iew
d
atasets
,
m
ak
in
g
m
u
lti
-
v
iew
clu
s
ter
in
g
a
p
r
o
m
in
e
n
t
r
esear
ch
to
p
ic
in
r
ec
en
t
tim
es.
T
o
ad
d
r
ess
th
e
ch
allen
g
es
ass
o
ciate
d
with
clu
s
ter
in
g
d
ata,
th
e
in
tr
o
d
u
ctio
n
o
f
p
ar
tial
s
u
p
er
v
is
io
n
,
co
m
m
o
n
l
y
k
n
o
wn
as
s
em
i
-
s
u
p
er
v
is
io
n
,
h
as
b
ee
n
im
p
lem
en
ted
.
Su
p
er
v
i
s
io
n
in
clu
s
ter
in
g
in
v
o
lv
es u
tili
zin
g
p
r
ev
io
u
s
ly
a
cq
u
ir
ed
k
n
o
wled
g
e
to
g
u
id
e
th
e
p
r
o
ce
s
s
,
ty
p
ically
t
h
r
o
u
g
h
o
b
ject
lab
els.
Un
lik
e
f
u
lly
s
u
p
er
v
is
ed
m
eth
o
d
s
wh
er
e
ev
er
y
o
b
ject
is
lab
eled
,
s
em
i
-
s
u
p
er
v
is
ed
a
p
p
r
o
ac
h
es
la
b
el
o
n
ly
a
s
u
b
s
et
o
f
o
b
jects
[
1
7
]
.
T
h
is
is
ad
v
an
tag
eo
u
s
d
u
e
to
th
e
s
ca
r
city
an
d
p
o
ten
tial
h
ig
h
co
s
t
o
f
f
u
lly
lab
eled
d
atasets
.
As
a
r
esu
lt,
s
em
i
-
s
u
p
er
v
is
io
n
tech
n
iq
u
es
h
av
e
g
a
r
n
er
e
d
atten
tio
n
d
u
e
to
th
eir
ab
ilit
y
to
p
r
o
v
id
e
p
ar
tial
g
u
i
d
an
ce
in
th
e
clu
s
ter
in
g
p
r
o
ce
s
s
,
m
ak
i
n
g
th
em
p
r
e
f
er
ab
le
o
v
er
f
u
ll
y
s
u
p
er
v
is
ed
m
eth
o
d
s
[
1
8
]
,
[
1
9
]
.
W
h
ile
s
em
i
-
s
u
p
er
v
is
io
n
tech
n
iq
u
es
ar
e
ex
t
en
s
iv
ely
s
tu
d
ied
in
d
ata
clu
s
ter
in
g
,
th
eir
ap
p
licatio
n
to
s
em
i
-
s
u
p
er
v
is
ed
m
u
lti
-
v
iew
clu
s
ter
in
g
o
f
f
ea
tu
r
e
d
ata
is
r
elativ
ely
lim
ited
.
Giv
en
th
e
co
n
tex
t
o
u
tlin
ed
a
b
o
v
e,
th
e
im
p
lem
e
n
tatio
n
o
f
s
em
i
-
s
u
p
er
v
is
ed
co
n
s
en
s
u
s
f
u
zz
y
clu
s
ter
in
g
f
o
r
m
u
lti
-
v
iew
r
elatio
n
al
d
ata
is
b
o
th
cr
u
cial
an
d
v
alu
ab
le,
a
n
d
it f
o
r
m
s
th
e
p
r
im
ar
y
f
o
cu
s
o
f
th
is
p
ap
er
.
I
n
th
is
s
tu
d
y
,
we
p
r
o
p
o
s
e
a
n
o
v
el
m
eth
o
d
f
o
r
s
em
i
-
s
u
p
er
v
is
ed
co
n
s
e
n
s
u
s
f
u
zz
y
m
u
lti
-
v
iew
clu
s
ter
in
g
.
T
h
is
m
eth
o
d
is
ap
p
lied
to
co
m
p
lex
an
d
d
iv
er
s
e
d
atasets
co
llected
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
.
W
ith
th
is
ap
p
r
o
a
ch
,
we
f
ir
s
t
p
ar
titi
o
n
th
e
d
ata
p
o
in
ts
in
to
clu
s
ter
s
f
o
r
th
e
u
n
lab
eled
d
ata
in
ea
ch
v
i
ew.
Su
b
s
eq
u
en
tly
,
we
p
er
f
o
r
m
m
u
lti
-
v
iew
f
u
zz
y
s
em
i
-
s
u
p
er
v
is
ed
clu
s
ter
in
g
a
cr
o
s
s
all
v
iews.
Fin
ally
,
we
in
teg
r
ate
in
f
o
r
m
atio
n
f
r
o
m
m
u
ltip
le
v
iews
an
d
ex
ec
u
te
co
n
s
en
s
u
s
clu
s
ter
in
g
ac
r
o
s
s
th
ese
v
iews.
T
h
is
in
teg
r
atio
n
en
s
u
r
es
in
cr
ea
s
ed
c
o
h
es
io
n
an
d
m
a
x
im
izes
co
n
s
en
s
u
s
ac
r
o
s
s
all
v
iews,
th
er
eb
y
im
p
r
o
v
in
g
clu
s
ter
in
g
p
er
f
o
r
m
an
ce
,
ac
h
iev
in
g
m
o
r
e
ac
cu
r
ate
clu
s
ter
in
g
r
esu
lts
,
an
d
m
in
im
izin
g
th
e
im
p
ac
t
o
f
n
o
is
e
an
d
er
r
o
r
s
.
T
h
e
s
ig
n
if
ican
ce
o
f
th
e
s
em
i
-
s
u
p
er
v
is
ed
f
u
zz
y
co
n
s
en
s
u
s
clu
s
ter
in
g
alg
o
r
ith
m
f
o
r
m
u
lti
-
v
iew
r
elatio
n
al
d
a
ta
lies
in
its
ab
ilit
y
to
en
h
an
ce
clu
s
ter
in
g
ac
cu
r
ac
y
an
d
ef
f
icien
cy
b
y
in
teg
r
atin
g
in
f
o
r
m
atio
n
f
r
o
m
m
u
ltip
le
v
iews
an
d
ad
d
r
ess
in
g
d
ata
u
n
ce
r
tain
ty
.
T
h
is
alg
o
r
ith
m
lev
e
r
ag
es
b
o
t
h
lab
eled
an
d
u
n
lab
eled
d
ata
to
m
ax
im
ize
th
e
av
ailab
le
in
f
o
r
m
atio
n
,
wh
ic
h
is
p
ar
ticu
lar
ly
b
en
ef
icial
wh
en
f
u
lly
lab
eled
d
ata
is
d
if
f
icu
lt
o
r
ex
p
e
n
s
iv
e
to
o
b
tain
.
B
y
u
s
in
g
f
u
zz
y
lo
g
ic,
th
e
alg
o
r
ith
m
e
f
f
ec
tiv
ely
h
an
d
les
am
b
ig
u
ity
an
d
u
n
ce
r
tain
ty
i
n
th
e
d
ata,
r
esu
ltin
g
in
m
o
r
e
r
eliab
le
clu
s
ter
in
g
o
u
tco
m
es.
Ad
d
itio
n
ally
,
co
n
s
en
s
u
s
clu
s
ter
in
g
in
c
r
ea
s
es
co
h
esio
n
am
o
n
g
d
if
f
e
r
en
t
v
iews,
en
s
u
r
in
g
th
at
th
e
id
en
tifie
d
d
ata
clu
s
ter
s
ar
e
co
n
s
is
ten
t
ac
r
o
s
s
v
ar
io
u
s
s
o
u
r
ce
s
.
T
h
is
ap
p
r
o
ac
h
also
allo
ws
f
o
r
th
e
d
etec
tio
n
o
f
co
m
p
lex
p
atter
n
s
an
d
m
in
im
izes
th
e
im
p
ac
t
o
f
n
o
is
e
an
d
er
r
o
r
s
,
r
esu
ltin
g
i
n
m
o
r
e
a
cc
u
r
ate
an
d
r
o
b
u
s
t
clu
s
ter
in
g
o
u
tco
m
es.
T
h
e
f
o
llo
win
g
s
ec
tio
n
s
o
f
th
i
s
p
ap
er
ar
e
o
r
g
an
ized
as
f
o
llo
ws:
Sectio
n
2
r
ev
iews
th
e
r
elate
d
wo
r
k
.
Sectio
n
3
g
iv
es
a
d
etailed
o
v
e
r
v
iew
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
,
a
n
d
Sectio
n
4
s
h
o
wca
s
es
th
e
ex
p
er
im
en
tal
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
o
ve
l
s
emi
-
s
u
p
ervis
ed
co
n
s
en
s
u
s
fu
z
z
y
clu
s
ter
in
g
meth
o
d
f
o
r
mu
lti
-
view
…
(
Ho
a
n
g
Th
i
C
a
n
h
)
6885
r
esu
lts
,
an
aly
s
is
,
an
d
c
o
m
p
ar
ativ
e
ev
alu
atio
n
s
.
I
n
th
e
c
o
n
c
lu
s
io
n
s
ec
tio
n
,
k
ey
i
n
s
ig
h
ts
ar
e
h
ig
h
lig
h
ted
,
an
d
p
o
s
s
ib
le
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
in
u
p
c
o
m
in
g
p
u
b
licatio
n
s
ar
e
o
u
tlin
e
d
.
2.
RE
L
AT
E
D
WO
RK
B
ick
el
an
d
Sch
ef
f
er
[
2
0
]
p
io
n
ee
r
ed
r
esear
ch
i
n
m
u
lti
-
v
iew
clu
s
ter
in
g
,
f
o
c
u
s
in
g
o
n
clu
s
ter
in
g
v
ec
to
r
d
ata
f
r
o
m
m
u
ltip
le
v
iews.
T
h
ey
ex
ten
d
e
d
k
-
m
ea
n
s
an
d
ex
p
ec
tatio
n
m
ax
im
izatio
n
(
E
M)
t
o
h
an
d
le
th
e
m
u
lti
-
v
iew
s
ettin
g
ef
f
ec
tiv
ely
,
p
ar
ti
cu
lar
ly
f
o
r
tex
t
d
ata
with
two
co
n
d
itio
n
ally
i
n
d
ep
e
n
d
en
t
v
i
ews.
E
x
p
er
im
en
tal
r
esu
lts
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
with
th
e
m
u
lti
-
v
iew
v
ar
ian
t
o
f
k
-
m
ea
n
s
co
m
p
ar
ed
to
its
s
in
g
le
-
v
iew
co
u
n
ter
p
a
r
t.
T
h
is
f
o
u
n
d
atio
n
al
r
esear
ch
h
as
in
s
p
ir
ed
th
e
d
ev
elo
p
m
en
t
o
f
s
ev
er
al
m
u
lti
-
v
iew
clu
s
ter
in
g
m
eth
o
d
s
[
3
]
,
[
2
1
]
.
C
lu
s
ter
in
g
ca
n
b
e
ap
p
lied
to
eith
er
v
ec
to
r
d
ata
o
r
r
elatio
n
a
l
d
ata.
Vec
to
r
d
ata
is
ch
ar
ac
te
r
ized
b
y
a
m
atr
ix
o
f
q
u
an
titativ
e
o
r
q
u
al
itativ
e
v
alu
es
th
at
d
escr
ib
e
ea
ch
o
b
ject,
r
e
p
r
esen
ted
b
y
an
n
×l
d
ata
m
atr
ix
.
I
n
co
n
tr
ast,
r
elatio
n
al
d
ata
en
c
ap
s
u
lates
th
e
r
elatio
n
s
h
ip
s
b
etwe
en
o
b
jects
th
r
o
u
g
h
d
is
s
im
ilar
ity
m
ea
s
u
r
es.
Desp
ite
r
ec
eiv
in
g
less
atten
ti
o
n
,
r
elatio
n
al
d
ata
is
m
o
r
e
v
e
r
s
atile
an
d
ap
p
licab
le
in
s
ce
n
ar
io
s
wh
er
e
v
ec
to
r
d
ata
is
in
s
u
f
f
icien
t
f
o
r
ac
cu
r
ate
d
escr
ip
tio
n
.
R
elatio
n
al
d
at
a
also
p
r
esen
ts
p
o
ten
tial
ad
v
an
tag
es
in
ter
m
s
o
f
co
n
f
id
en
tiality
,
as
th
e
attr
ib
u
t
es
o
f
o
b
jects
ca
n
b
e
k
ep
t
co
n
f
id
en
tial
o
r
r
em
ain
in
ac
ce
s
s
ib
le
[
2
2
]
.
Mu
lti
-
v
iew
r
elatio
n
al
d
ata
s
ets
co
n
s
is
t
o
f
m
u
ltip
le
d
is
s
im
ilar
ity
m
atr
ices,
ea
ch
r
ep
r
esen
tin
g
a
d
if
f
er
en
t
asp
ec
t
o
f
th
e
o
b
jects
b
ein
g
d
escr
ib
e
d
.
T
o
ac
cu
r
ately
clu
s
ter
c
o
m
p
lex
d
ata,
it
is
c
r
u
cial
to
h
a
v
e
m
u
ltiv
iew
r
elatio
n
al
tech
n
iq
u
es
th
at
ac
c
o
u
n
t
f
o
r
th
e
v
ar
y
in
g
in
f
lu
en
ce
s
o
f
th
ese
d
is
s
im
ilar
ity
m
atr
ices
o
n
th
e
clu
s
ter
in
g
p
r
o
ce
s
s
.
T
h
e
r
esear
ch
d
etailed
in
r
ef
er
en
ce
[
2
3
]
in
tr
o
d
u
ce
s
a
n
o
v
el
s
em
i
-
s
u
p
er
v
is
ed
m
u
lti
-
v
i
ew
f
u
zz
y
clu
s
ter
in
g
alg
o
r
ith
m
k
n
o
wn
as
th
e
s
em
i
-
s
u
p
er
v
is
ed
ap
p
r
o
ac
h
f
o
r
clu
s
t
er
in
g
an
d
ag
g
r
e
g
atin
g
r
elatio
n
al
d
ata
(
SS
C
A
R
D)
.
Sp
ec
if
ically
tailo
r
ed
f
o
r
r
elat
io
n
al
d
ata,
th
is
alg
o
r
ith
m
in
t
eg
r
ates
p
air
wis
e
co
n
s
tr
ain
ts
f
r
o
m
th
e
AFC
C
as
s
u
p
er
v
is
io
n
.
I
t
o
p
er
ates
as
an
iter
ativ
e
alg
o
r
ith
m
r
o
o
ted
in
th
e
clu
s
ter
in
g
an
d
ag
g
r
e
g
atio
n
o
f
r
elatio
n
al
d
ata
with
in
s
tan
ce
-
lev
el
co
n
s
tr
ain
ts
(
C
AR
Dr
)
alg
o
r
ith
m
,
its
elf
b
u
ilt
u
p
o
n
th
e
r
elatio
n
al
f
u
zz
y
c
-
m
ea
n
s
(
R
FC
M)
alg
o
r
ith
m
[
2
2
]
,
[
2
4
]
.
T
h
e
o
b
je
ctiv
e
f
u
n
ctio
n
o
f
SS
C
AR
D
en
co
m
p
ass
es
two
co
m
p
o
n
en
ts
:
o
n
e
ad
d
r
ess
in
g
th
e
u
n
s
u
p
er
v
is
ed
asp
ec
t
a
n
d
th
e
o
th
er
h
a
n
d
lin
g
t
h
e
v
io
latio
n
o
f
p
air
wis
e
co
n
s
tr
ain
ts
(
AFC
C
)
.
C
h
en
et
a
l.
[
2
5
]
in
tr
o
d
u
ce
d
th
e
T
W
-
k
-
m
ea
n
s
alg
o
r
ith
m
,
wh
ich
is
a
two
lev
el
s
weig
h
ted
clu
s
ter
in
g
m
eth
o
d
d
esig
n
ed
f
o
r
m
u
lti
v
iew
v
ec
to
r
d
ata.
T
h
e
alg
o
r
it
h
m
f
ac
ilit
ates
th
e
s
im
u
ltan
eo
u
s
co
m
p
u
tatio
n
o
f
weig
h
ts
f
o
r
v
ar
io
u
s
v
iews
an
d
v
ar
iab
les,
in
co
r
p
o
r
atin
g
two
a
d
d
itio
n
al
s
tep
s
.
Gu
s
m
ão
an
d
C
ar
v
alh
o
[
2
6
]
in
tr
o
d
u
ce
d
NE
R
F
c
-
m
ea
n
s
,
a
f
u
zz
y
clu
s
ter
in
g
alg
o
r
ith
m
d
esig
n
e
d
f
o
r
n
o
n
-
E
u
clid
ea
n
r
elatio
n
al
d
ata.
I
t
ex
ten
d
s
th
e
R
FC
M
al
g
o
r
ith
m
to
h
a
n
d
le
ar
b
itra
r
y
d
is
s
im
ilar
ity
d
ata,
in
clu
d
in
g
tr
an
s
f
o
r
m
ed
s
im
ilar
ity
d
ata.
T
h
e
FANNY
alg
o
r
ith
m
,
b
y
Kau
f
m
an
et
a
l.
[
2
4
]
,
is
a
f
u
zz
y
clu
s
ter
in
g
m
e
th
o
d
f
o
r
d
ata
with
s
im
ilar
ities
,
en
ab
lin
g
o
b
jects
to
b
elo
n
g
t
o
m
u
ltip
le
clu
s
ter
s
with
v
ar
y
in
g
d
eg
r
ee
s
.
C
h
en
et
a
l.
[
2
5
]
also
in
tr
o
d
u
c
es
HC
Md
d
,
a
v
ar
iatio
n
o
f
th
e
K
-
m
e
d
o
id
s
alg
o
r
ith
m
t
h
at
f
o
cu
s
es
o
n
m
e
d
o
id
-
b
ased
cl
u
s
ter
in
g
an
d
ca
n
e
f
f
ec
tiv
ely
h
an
d
le
d
iv
er
s
e
d
ata
t
y
p
es.
I
n
[
2
6
]
,
two
h
y
b
r
id
clu
s
ter
in
g
m
eth
o
d
s
f
o
r
m
u
lti
-
v
iew
r
elatio
n
al
d
ata,
n
am
e
d
an
d
,
ar
e
in
tr
o
d
u
ce
d
.
T
h
e
s
e
m
eth
o
d
s
co
m
b
in
e
p
a
r
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
with
h
ar
d
clu
s
ter
in
g
alg
o
r
ith
m
s
u
tili
zin
g
m
u
ltip
le
d
is
s
im
ilar
ity
m
atr
ices.
T
h
e
an
d
alg
o
r
ith
m
s
e
m
p
lo
y
m
o
d
if
ied
v
er
s
io
n
s
o
f
th
e
an
d
alg
o
r
ith
m
s
,
r
esp
ec
tiv
ely
,
to
u
p
d
ate
p
ar
ticle
p
o
s
itio
n
s
[
2
7
]
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
is
r
esear
ch
p
r
o
p
o
s
es
a
n
o
v
el
ap
p
r
o
ac
h
to
s
em
i
-
s
u
p
er
v
is
ed
co
n
s
en
s
u
s
f
u
zz
y
m
u
lti
-
v
iew
clu
s
ter
in
g
(
SS
C
FM
C
)
.
W
e
ap
p
ly
o
u
r
m
eth
o
d
to
a
d
i
v
er
s
e
m
u
lti
-
v
i
ew
d
ataset
co
llected
f
r
o
m
v
a
r
io
u
s
s
o
u
r
ce
s
.
T
h
is
d
ataset
is
ch
ar
ac
ter
ized
b
y
v
a
r
y
in
g
n
u
m
b
er
s
o
f
r
ec
o
r
d
s
with
in
ea
ch
v
iew,
d
if
f
er
en
t
attr
i
b
u
te
co
u
n
ts
ac
r
o
s
s
v
iews,
an
d
co
m
p
lex
m
an
y
-
to
-
m
an
y
r
elatio
n
s
h
i
p
s
b
etwe
en
v
i
ews.
3
.
1
.
M
a
in idea
T
h
e
SS
C
FM
C
alg
o
r
ith
m
in
v
o
l
v
es two
s
tep
s
.
Step
1:
P
er
f
o
r
m
f
u
zz
y
clu
s
ter
in
g
o
n
th
e
u
n
lab
ele
d
d
ata
with
in
ea
ch
v
iew.
D
u
r
in
g
t
h
is
s
tep
,
th
e
f
u
zz
y
C
-
m
ea
n
s
(
FC
M)
a
lg
o
r
ith
m
is
ap
p
lied
in
d
ep
e
n
d
en
tly
to
ea
ch
v
iew
to
d
iv
id
e
th
e
d
ata
p
o
in
ts
in
to
clu
s
ter
s
[
2
8
]
.
T
h
e
o
u
tco
m
e
o
f
th
is
s
tep
co
m
p
r
is
es
th
e
cl
u
s
ter
ce
n
t
r
o
id
s
an
d
th
e
co
r
r
esp
o
n
d
in
g
m
em
b
er
s
h
ip
d
eg
r
ee
s
f
o
r
ea
ch
v
iew.
T
h
ese
m
em
b
er
s
h
ip
d
eg
r
ee
s
ar
e
d
en
o
t
ed
as
̅
.
Step
2
:
M
u
lti
-
v
iew
f
u
zz
y
s
em
i
-
s
u
p
er
v
is
ed
clu
s
ter
in
g
.
Du
r
in
g
th
is
p
h
ase,
th
e
f
u
zz
y
m
em
b
er
s
h
ip
d
e
g
r
ee
s
(
̅
)
o
b
tain
ed
f
r
o
m
s
tep
1
o
f
th
e
cu
r
r
en
t
v
iew
ar
e
co
m
b
i
n
ed
with
th
e
m
em
b
e
r
s
h
ip
d
eg
r
ee
s
o
f
t
h
e
r
em
ain
in
g
v
iews.
T
h
e
aim
is
to
en
h
an
ce
th
e
ag
r
ee
m
en
t
b
etwe
en
a
ll
v
iews
an
d
r
ea
ch
th
e
h
i
g
h
est
lev
el
o
f
co
n
s
en
s
u
s
.
T
h
e
o
u
tp
u
t
o
f
th
is
s
tep
co
n
s
is
ts
o
f
th
e
f
in
al
clu
s
ter
ce
n
tr
o
i
d
v
alu
es
a
n
d
t
h
eir
co
r
r
esp
o
n
d
i
n
g
m
em
b
er
s
h
ip
d
eg
r
ee
v
alu
es f
o
r
ea
ch
v
iew.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
ic
id
ea
is
d
ep
icted
in
Fig
u
r
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
8
8
3
-
6
8
9
3
6886
3
.
2
.
P
r
o
po
s
ed
m
et
ho
d
T
h
e
alg
o
r
ith
m
d
ia
g
r
am
is
p
r
esen
ted
in
Fig
u
r
e
2
.
T
h
is
f
ig
u
r
e
d
etails
ea
ch
s
tep
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
h
ig
h
lig
h
tin
g
k
ey
co
m
p
o
n
e
n
ts
an
d
th
eir
in
ter
ac
tio
n
s
.
B
y
ex
am
in
in
g
Fig
u
r
e
2
,
a
co
m
p
r
eh
en
s
iv
e
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
alg
o
r
ith
m
'
s
wo
r
k
f
lo
w
an
d
f
u
n
d
am
e
n
tal
p
r
in
cip
les ca
n
b
e
g
ain
ed
.
Fig
u
r
e
1
.
T
h
e
m
ain
i
d
ea
o
f
SS
C
FM
C
Fig
u
r
e
2
.
Alg
o
r
ith
m
d
ia
g
r
am
−
Ma
th
em
atica
l
n
o
tatio
n
:
co
n
s
i
d
er
a
d
ataset
=
{
1
,
2
,
3
,
…
,
}
co
n
s
is
tin
g
o
f
d
ata
s
am
p
les,
wh
er
e
d
en
o
tes th
e
i
-
th
s
am
p
le.
I
n
a
m
u
lti
-
v
iew
d
ataset,
ea
ch
d
ata
s
am
p
le
is
ch
ar
ac
ter
ized
b
y
f
ea
t
u
r
es d
er
iv
ed
f
r
o
m
v
ar
io
u
s
v
iews.
T
h
er
ef
o
r
e,
th
e
m
u
lti
-
v
iew
d
ataset
ca
n
b
e
ex
p
r
ess
ed
as
=
{
1
,
2
,
3
,
…
,
}
,
wh
er
e
∈
×
d
en
o
tes
th
e
d
ata
m
atr
ix
o
f
th
e
l
-
th
v
iew.
Her
e,
L
i
s
th
e
to
tal
n
u
m
b
er
o
f
v
iews,
an
d
is
th
e
d
im
en
s
io
n
ality
o
f
th
e
l
-
th
v
iew.
C
i
s
th
e
to
tal
c
lu
s
ter
co
u
n
t,
is
the
E
u
clid
ea
n
d
is
tan
ce
f
r
o
m
d
ata
p
o
in
t
k
to
clu
s
ter
j
in
v
iew
l
,
r
ep
r
esen
ts
th
e
d
eg
r
ee
to
wh
ich
d
ata
p
o
in
t
k
b
elo
n
g
s
to
clu
s
ter
j
in
v
iew
l,
is
d
ata
p
o
in
t
k
i
n
v
iew
l,
an
d
is
t
h
e
ce
n
ter
o
f
clu
s
ter
j
in
v
iew
l.
−
T
h
e
o
b
jectiv
e
f
u
n
ctio
n
:
Fo
llo
win
g
th
e
id
ea
s
in
tr
o
d
u
ce
d
in
th
e
p
r
ev
io
u
s
s
ec
tio
n
,
th
is
p
ar
t
will
p
r
o
v
id
e
a
d
etailed
ex
p
lan
atio
n
o
f
t
h
e
m
o
d
elin
g
f
o
r
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
Sp
ec
if
ically
,
th
e
o
b
jectiv
e
f
u
n
ctio
n
o
f
th
is
m
eth
o
d
is
d
ef
in
e
d
b
y
th
r
e
e
k
ey
co
m
p
o
n
en
ts
,
as d
etailed
in
(
1
)
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
o
ve
l
s
emi
-
s
u
p
ervis
ed
co
n
s
en
s
u
s
fu
z
z
y
clu
s
ter
in
g
meth
o
d
f
o
r
mu
lti
-
view
…
(
Ho
a
n
g
Th
i
C
a
n
h
)
6887
=
∑
∑
∑
2
|
|
−
|
|
2
=
1
=
1
=
1
+
∑
∑
∑
(
−
u
)
2
=
1
=
1
=
1
|
|
−
|
|
2
+
∑
∑
∑
∑
(
−
)
2
=
1
,
≠
=
1
=
1
=
1
(
|
|
−
|
|
2
+
|
|
−
|
|
2
)
→
(
1
)
−
W
ith
co
n
s
tr
ain
t c
o
n
d
itio
n
s
:
{
∑
=
1
=
1
∈
(
0
,
1
)
T
h
e
o
b
jectiv
e
f
u
n
ctio
n
(
1
)
co
n
s
is
t
s
o
f
th
r
ee
co
m
p
o
n
e
n
ts
,
d
et
ailed
as f
o
llo
ws:
−
T
h
e
co
m
p
o
n
en
t
r
ep
r
esen
ts
f
u
z
zy
clu
s
ter
in
g
:
∑
∑
∑
2
|
|
−
|
|
2
=
1
=
1
=
1
−
T
h
e
co
m
p
o
n
en
t
r
ep
r
esen
ts
s
em
i
-
s
u
p
er
v
is
ed
clu
s
ter
in
g
:
∑
∑
∑
(
−
u
)
2
|
|
−
|
|
2
=
1
=
1
=
1
−
T
h
e
co
m
p
o
n
en
t
r
ep
r
esen
ts
co
n
s
en
s
u
s
m
u
lti
-
v
iew
clu
s
ter
in
g
:
∑
∑
∑
∑
(
−
)
2
(
|
|
−
|
|
2
+
|
|
−
|
|
2
)
=
1
,
≠
=
1
=
1
=
1
I
n
th
is
co
m
p
o
n
en
t,
o
u
r
g
o
al
is
to
in
teg
r
ate
th
e
attr
ib
u
tes
o
f
t
h
e
o
b
ject
ac
r
o
s
s
all
p
er
s
p
ec
tiv
es
to
d
eter
m
in
e
th
e
o
p
tim
al
m
em
b
er
s
h
i
p
d
eg
r
ee
.
T
h
is
m
em
b
er
s
h
ip
d
e
g
r
ee
s
h
o
u
ld
m
in
im
ize
th
e
d
if
f
er
en
ce
s
ac
r
o
s
s
all
v
iews.
T
h
e
clu
s
ter
ce
n
ter
s
ar
e
d
eter
m
in
ed
u
s
in
g
(
2
)
:
=
∑
=
1
+
∑
∑
=
1
,
≠
=
1
∑
=
1
+
∑
∑
=
1
,
≠
=
1
(
2
)
I
n
wh
ich
:
{
=
2
+
(
−
u
)
2
=
(
−
)
2
T
h
e
L
ag
r
a
n
g
e
m
u
ltip
lier
tech
n
iq
u
e
is
em
p
lo
y
e
d
to
ascer
tain
t
h
e
v
alu
e
o
f
:
=
1
−
∑
ℎ
ℎ
=
1
∑
ℎ
ℎ
=
1
+
(
3
)
I
n
wh
ich
:
{
=
∑
(
+
)
=
1
,
≠
=
u
an
d
{
=
(
+
1
)
+
∑
=
1
,
≠
=
+
T
h
e
alg
o
r
ith
m
SS
C
FMC
i
s
s
h
o
wn
in
a
lg
o
r
ith
m
1
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
in
v
o
lv
es
two
d
is
tin
ct
iter
ativ
e
s
tep
s
.
I
n
th
e
f
ir
s
t
s
tep
,
we
u
s
e
t
h
e
F
C
M
alg
o
r
ith
m
,
wh
ic
h
h
as
a
c
o
m
p
lex
ity
o
f
(
.
2
.
)
.
I
n
th
e
s
ec
o
n
d
s
tep
,
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
h
as
a
co
m
p
le
x
ity
o
f
(
.
2
.
2
.
)
.
C
o
n
s
eq
u
e
n
tly
,
th
e
o
v
e
r
all
co
m
p
u
tatio
n
al
co
m
p
lex
ity
o
f
th
e
alg
o
r
ith
m
is
(
.
2
.
2
.
)
.
Alg
o
r
ith
m
1
.
SS
C
FM
C
Input
=
{
1
,
2
,
3
,
…
,
}
,
wh
er
e
∈
×
,
C
is
th
e
nu
mb
er
of
cl
us
te
rs
,
Maxstep
is
th
e
nu
mb
er
of iterations,
ϵ
is the allowable error.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
8
8
3
-
6
8
9
3
6888
Output Cluster
labels
Y
BEGIN
Step
1: Fuzzy clustering for unlabeled data in each view
̅
=
1
̅
̅
̅
,
2
̅
̅
̅
,
…
,
̅
̅
̅
Step 2: Multi
-
view fuzzy
semi
-
supervised clustering
2.1. Init
t = 0
Repeat:
2.2. Update
v
using formula (2)
2.3. Update
u
using formula (3)
Until:
{
|
|
(
)
(
+
1
)
−
(
)
(
)
|
|
}
≤
ϵ
or
≥
Maxstep
END
4.
E
XP
E
R
I
M
E
N
T
A
L
RE
SUL
T
S
T
h
is
s
ec
tio
n
ev
alu
ates
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
o
ac
h
iev
e
th
is
,
we
c
o
m
p
ar
e
it
with
o
th
er
s
in
g
le
-
v
iew
an
d
m
u
lti
-
v
iew
clu
s
ter
in
g
alg
o
r
ith
m
s
.
T
h
e
co
m
p
ar
ativ
e
a
n
aly
s
is
p
r
o
v
id
es
in
s
ig
h
ts
in
to
th
e
s
tr
en
g
th
s
an
d
wea
k
n
ess
es o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
r
elativ
e
to
ex
is
tin
g
tech
n
iq
u
es.
4
.
1
.
E
nv
iro
nm
ent
a
l
co
nfig
ura
t
io
n
T
h
e
ex
p
er
im
e
n
ts
wer
e
co
n
d
u
c
ted
o
n
an
Ap
p
le
Ma
cBo
o
k
Air
M1
f
r
o
m
2
0
2
0
,
e
q
u
ip
p
ed
with
8
GB
o
f
R
AM
,
2
5
6
GB
o
f
s
to
r
ag
e,
an
d
a
7
-
co
r
e
GPU.
T
h
e
Py
th
o
n
p
r
o
g
r
a
m
m
in
g
la
n
g
u
a
g
e
v
er
s
io
n
3
.
1
0
was
u
tili
ze
d
th
r
o
u
g
h
o
u
t
t
h
e
s
tu
d
y
.
All
test
s
wer
e
ex
ec
u
ted
with
in
t
h
e
s
am
e
s
tan
d
ar
d
ized
e
n
v
ir
o
n
m
e
n
t.
T
o
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
,
th
e
f
o
llo
win
g
m
etr
ics
wer
e
em
p
lo
y
ed
:
a
d
ju
s
ted
r
an
d
in
d
ex
(
AR
I
)
a
n
d
F
-
m
ea
s
u
r
e
[
2
9
]
.
T
o
in
tr
o
d
u
ce
r
an
d
o
m
n
ess
in
to
th
e
ex
p
er
im
e
n
ts
,
we
ex
ec
u
te
al
l
alg
o
r
ith
m
s
2
0
tim
es
an
d
p
r
esen
t
th
e
av
er
a
g
e
r
esu
lts
an
d
s
tan
d
ar
d
d
ev
iatio
n
f
o
r
th
e
e
v
alu
atio
n
m
ea
s
u
r
es.
T
o
ev
alu
ate
th
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
,
th
e
r
esear
ch
team
co
n
d
u
cted
s
im
u
latio
n
s
o
n
s
ev
en
d
atasets
f
r
o
m
th
e
UC
I
m
ac
h
in
e
lear
n
in
g
r
ep
o
s
ito
r
y
.
T
ab
le
1
p
r
o
v
id
es
a
co
m
p
r
eh
en
s
iv
e
o
v
er
v
iew
o
f
th
e
ch
ar
ac
ter
is
tics
an
d
d
etails
o
f
t
h
ese
d
atasets
.
T
h
is
in
f
o
r
m
atio
n
o
f
f
er
s
a
clea
r
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
d
ata
u
s
ed
f
o
r
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
.
T
ab
le
1
.
Mu
lti
-
v
iew
d
atasets
D
a
t
a
s
e
t
C
l
a
s
ses
V
i
e
w
s
V
a
r
i
a
b
l
e
s
O
b
j
e
c
t
s
3
_
S
o
u
r
c
e
s
06
03
10
,
259
1
6
9
W
a
t
e
r
_
Tr
e
a
t
m
e
n
t
04
13
38
5
2
7
F
l
o
w
e
r
s
17
04
-
1
,
3
6
0
M
u
l
t
i
p
l
e
_
F
e
a
t
u
r
e
s
10
06
6
4
9
2
,
0
0
0
P
h
o
n
e
m
e
05
03
1
5
0
2
,
0
0
0
I
mag
e
07
16
19
2
,
3
1
0
I
n
t
e
r
n
e
t
02
06
1
,
4
9
2
2
,
3
5
9
4
.
2
.
Resul
t
s
a
n
d dis
c
us
s
io
n
I
n
th
is
s
ec
tio
n
,
we
co
n
d
u
cted
ex
p
er
im
en
ts
o
n
s
ev
en
m
u
lti
-
v
i
ew
d
atasets
to
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
a
n
d
co
m
p
ar
ed
th
e
o
b
tain
ed
r
esu
lts
with
th
o
s
e
o
f
elev
e
n
o
th
e
r
m
eth
o
d
s
.
I
n
clu
d
e:
_
an
d
_
alg
o
r
ith
m
s
[
2
5
]
,
_
[
3
0
]
,
H
ar
d
C
-
Me
d
o
id
s
(
HC
Md
d
)
[
2
4
]
,
NE
R
F
[
2
6
]
,
FANNY
[
2
4
]
,
C
A
R
DR
[
2
3
]
,
_
an
d
_
[
2
7
]
,
PS
O
-
R
W
L
an
d
P
SO
-
R
W
G
[
2
6
]
.
T
h
e
SS
C
FMC
alg
o
r
ith
m
s
wer
e
ex
ec
u
ted
2
0
tim
es,
with
ea
ch
ex
ec
u
tio
n
h
a
v
in
g
a
m
ax
im
u
m
iter
a
tio
n
lim
it o
f
1
0
0
.
T
h
e
ex
p
er
im
en
tal
r
esu
lts
ar
e
p
r
esen
ted
in
T
a
b
le
2
,
with
ev
alu
atio
n
s
co
n
d
u
cted
u
s
in
g
th
e
AR
I
an
d
F
-
m
ea
s
u
r
e
m
etr
ics,
r
esp
ec
tiv
ely
.
I
n
th
e
co
n
tex
t o
f
s
em
i
-
s
u
p
er
v
is
ed
co
n
s
en
s
u
s
f
u
zz
y
m
u
lti
-
v
iew
clu
s
ter
in
g
,
th
e
ad
ju
s
ted
r
an
d
in
d
ex
(
AR
I
)
a
n
d
F
-
m
ea
s
u
r
e
p
r
o
v
id
e
co
m
p
r
e
h
en
s
iv
e
p
e
r
f
o
r
m
an
ce
ev
alu
ati
o
n
s
.
AR
I
m
ea
s
u
r
es
th
e
s
im
ilar
ity
b
etwe
en
p
r
ed
icted
an
d
tr
u
e
clu
s
ter
in
g
,
ad
ju
s
ted
f
o
r
ch
an
ce
,
h
i
g
h
lig
h
tin
g
ac
cu
r
ac
y
b
y
co
n
s
id
er
in
g
b
o
th
co
r
r
ec
t
p
air
i
n
g
s
an
d
c
o
r
r
ec
t
s
ep
a
r
atio
n
s
o
f
d
ata
p
o
i
n
ts
.
A
h
ig
h
e
r
AR
I
v
a
lu
e
in
d
icate
s
m
o
r
e
ac
cu
r
ate
clu
s
ter
in
g
.
AR
I
r
an
g
es
f
r
o
m
-
1
to
1
,
wh
er
e
1
r
ep
r
esen
ts
p
er
f
ec
t
clu
s
ter
in
g
,
0
in
d
icate
s
r
an
d
o
m
clu
s
ter
in
g
r
esu
lts
,
an
d
n
eg
ati
v
e
v
alu
es
d
e
n
o
te
clu
s
ter
in
g
wo
r
s
e
th
an
r
a
n
d
o
m
.
F
-
m
ea
s
u
r
e
is
a
m
etr
ic
th
at
co
m
b
in
es
Pre
cisi
o
n
an
d
R
ec
a
ll.
T
h
e
F
-
m
ea
s
u
r
e
r
an
g
es
f
r
o
m
0
to
1
,
wh
er
e
a
v
alu
e
o
f
1
in
d
icate
s
p
er
f
ec
t
Pre
cisi
o
n
an
d
R
ec
all,
m
ea
n
in
g
th
e
clu
s
ter
s
ar
e
b
o
th
ac
cu
r
ate
an
d
co
m
p
r
e
h
en
s
iv
e.
T
o
g
e
th
er
,
th
ese
m
etr
ics
o
f
f
er
a
h
o
lis
tic
v
iew
o
f
clu
s
t
er
in
g
p
er
f
o
r
m
an
ce
,
e
n
ab
lin
g
co
m
p
ar
is
o
n
s
with
o
th
e
r
alg
o
r
ith
m
s
an
d
ass
ess
in
g
ef
f
ec
tiv
en
ess
ac
r
o
s
s
d
iv
er
s
e
d
atasets
.
T
ab
le
2
d
o
es
n
o
t
d
is
p
lay
th
e
r
esu
lts
o
f
th
e
_
an
d
_
alg
o
r
ith
m
s
o
n
th
e
Flo
wer
s
d
ataset
d
u
e
to
th
e
ab
s
en
ce
o
f
n
ec
ess
ar
y
attr
ib
u
tes
in
th
is
d
a
taset.
Hen
ce
,
o
n
ly
alg
o
r
ith
m
s
ca
p
ab
l
e
o
f
h
a
n
d
lin
g
r
elatio
n
al
d
ata
c
an
b
e
test
ed
u
s
in
g
t
h
is
d
ataset.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
o
ve
l
s
emi
-
s
u
p
ervis
ed
co
n
s
en
s
u
s
fu
z
z
y
clu
s
ter
in
g
meth
o
d
f
o
r
mu
lti
-
view
…
(
Ho
a
n
g
Th
i
C
a
n
h
)
6889
T
ab
le
2
.
R
esu
lts
co
m
p
ar
is
o
n
:
s
in
g
le
-
v
iew
an
d
m
u
lti
-
v
iew
alg
o
r
ith
m
s
Da
tas
e
ts
I
nde
x
3_S
ou
r
c
e
s
W
a
ter
_T
r
e
a
tm
e
nt
F
lowe
r
s
M
ult
ipl
e
_
F
e
a
tur
e
s
P
hone
me
I
mage
I
nter
ne
t
PSO
_
R
A
r
i
0
.
3
2
(
0
.
0
2
)
0
.
0
1
(
0
.
0
0
)
0
.
3
5
(
0
.
0
1
)
0
.
5
0
(
0
.
0
0
)
0
.
7
1
(
0
.
0
0
)
0
.
4
1
(
0
.
0
1
)
0
.
5
0
(
0
.
0
0
)
F_
M
ea
s
u
re
0
.
5
4
(
0
.
0
1
)
0
.
2
0
(
0
.
0
0
)
0
.
5
3
(
0
.
0
2
)
0
.
6
8
(
0
.
0
0
)
0
.
8
5
(
0
.
0
0
)
0
.
6
3
(
0
.
0
1
)
0
.
8
9
(
0
.
0
0
)
PSO
-
R
W
L
A
r
i
0
.
1
1
(
0
.
0
5
)
0
.
0
3
(
0
.
0
0
)
0
.
2
7
(
0
.
0
1
)
0
.
6
6
(
0
.
0
3
)
0
.
7
2
(
0
.
0
1
)
0
.
5
0
(
0
.
0
0
)
0
.
5
3
(
0
.
0
0
)
F_
M
ea
s
u
re
0
.
4
1
(
0
.
0
4
)
0
.
2
5
(
0
.
0
0
)
0
.
4
6
(
0
.
0
1
)
0
.
8
2
(
0
.
0
3
)
0
.
8
5
(
0
.
0
0
)
0
.
6
7
(
0
.
0
0
)
0
.
9
0
(
0
.
0
0
)
PSO
-
R
W
G
A
r
i
0
.
3
6
(
0
.
0
2
)
0
.
0
3
(
0
.
0
0
)
0
.
2
8
(
0
.
0
2
)
0
.
6
2
(
0
.
0
0
)
0
.
7
2
(
0
.
0
0
)
0
.
4
9
(
0
.
0
0
)
0
.
5
0
(
0
.
0
0
)
F_
M
ea
s
u
re
0
.
5
7
(
0
.
0
2
)
0
.
2
7
(
0
.
0
1
)
0
.
4
7
(
0
.
0
2
)
0
.
8
0
(
0
.
0
0
)
0
.
8
5
(
0
.
0
0
)
0
.
6
6
(
0
.
0
0
)
0
.
8
9
(
0
.
0
0
)
H
C
M
-
dd
A
r
i
0
.
1
8
(
0
.
0
3
)
0
.
0
2
(
0
.
0
0
)
0
.
2
5
(
0
.
0
3
)
0
.
3
9
(
0
.
0
4
)
0
.
4
8
(
0
.
0
8
)
0
.
3
3
(
0
.
0
5
)
0
.
4
0
(
0
.
1
3
)
F_
M
ea
s
u
re
0
.
4
6
(
0
.
0
2
)
0
.
2
9
(
0
.
0
1
)
0
.
4
3
(
0
.
0
3
)
0
.
5
8
(
0
.
0
5
)
0
.
6
8
(
0
.
0
7
)
0
.
5
6
(
0
.
0
5
)
0
.
8
5
(
0
.
0
5
)
N
E
RF
A
r
i
0
.
3
9
(
0
.
0
3
)
0
.
0
2
(
0
.
0
0
)
0
.
1
4
(
0
.
0
2
)
0
.
3
2
(
0
.
0
0
)
0
.
2
0
(
0
.
0
1
)
0
.
3
5
(
0
.
0
5
)
0
.
2
9
(
0
.
0
0
)
F_
M
ea
s
u
re
0
.
5
8
(
0
.
0
0
)
0
.
2
1
(
0
.
0
1
)
0
.
2
8
(
0
.
0
2
)
0
.
4
8
(
0
.
0
0
)
0
.
4
7
(
0
.
0
1
)
0
.
5
7
(
0
.
0
5
)
0
.
8
2
(
0
.
0
0
)
FA
N
N
Y
A
r
i
0
.
0
7
(
0
.
0
2
)
0
.
0
1
(
0
.
0
0
)
0
.
2
0
(
0
.
0
5
)
0
.
3
3
(
0
.
0
1
)
0
.
3
9
(
0
.
0
9
)
0
.
3
4
(
0
.
0
5
)
0
.
2
9
(
0
.
0
0
)
F_
M
ea
s
u
re
0
.
3
8
(
0
.
0
2
)
0
.
2
1
(
0
.
0
2
)
0
.
3
5
(
0
.
0
4
)
0
.
5
0
(
0
.
0
2
)
0
.
6
3
(
0
.
0
7
)
0
.
5
6
(
0
.
0
6
)
0
.
8
2
(
0
.
0
0
)
CA
R
D
R
A
r
i
0
.
3
9
(
0
.
0
3
)
-
0
.
0
2
(
0
.
0
0
)
0
.
1
0
(
0
.
0
3
)
0
.
2
2
(
0
.
0
5
)
0
.
2
1
(
0
.
0
4
)
0
.
4
0
(
0
.
0
1
)
0
.
2
0
(
0
.
0
4
)
F_
M
ea
s
u
re
0
.
5
9
(
0
.
0
0
)
0
.
3
3
(
0
.
0
1
)
0
.
2
4
(
0
.
0
3
)
0
.
3
9
(
0
.
0
5
)
0
.
5
1
(
0
.
0
3
)
0
.
5
9
(
0
.
0
2
)
0
.
7
7
(
0
.
0
3
)
MR
D
C
A
_
R
W
L
A
r
i
0
.
2
3
(
0
.
0
6
)
0
.
0
3
(
0
.
0
2
)
0
.
2
7
(
0
.
0
2
)
0
.
5
8
(
0
.
0
6
)
0
.
6
2
(
0
.
1
0
)
0
.
4
0
(
0
.
0
9
)
0
.
2
7
(
0
.
0
4
)
F_
M
ea
s
u
re
0
.
4
9
(
0
.
0
4
)
0
.
2
8
(
0
.
0
2
)
0
.
4
6
(
0
.
0
2
)
0
.
7
4
(
0
.
0
5
)
0
.
7
7
(
0
.
0
8
)
0
.
5
9
(
0
.
0
6
)
0
.
8
0
(
0
.
0
8
)
MR
D
C
A
_
R
W
G
A
r
i
0
.
2
5
(
0
.
0
6
)
0
.
0
3
(
0
.
0
2
)
0
.
2
8
(
0
.
0
3
)
0
.
5
6
(
0
.
0
6
)
0
.
6
0
(
0
.
1
1
)
0
.
3
8
(
0
.
0
9
)
0
.
2
9
(
0
.
2
1
)
F_
M
ea
s
u
re
0
.
5
1
(
0
.
0
5
)
0
.
2
8
(
0
.
0
2
)
0
.
4
7
(
0
.
0
3
)
0
.
7
2
(
0
.
0
6
)
0
.
7
5
(
0
.
0
9
)
0
.
5
8
(
0
.
0
7
)
0
.
8
2
(
0
.
0
6
)
T
W
_
K
mea
n
s
A
r
i
0
.
0
1
(
0
.
0
1
)
0
.
0
4
(
0
.
0
1
)
-
0
.
3
5
(
0
.
0
6
)
0
.
7
1
(
0
.
0
5
)
0
.
3
6
(
0
.
0
4
)
0
.
1
2
(
0
.
2
5
)
F_
M
ea
s
u
re
0
.
0
1
(
0
.
0
1
)
0
.
3
1
(
0
.
0
2
)
-
0
.
5
3
(
0
.
0
6
)
0
.
8
4
(
0
.
0
4
)
0
.
5
7
(
0
.
0
3
)
0
.
7
6
(
0
.
0
9
)
E
W
_
K
mea
n
s
A
r
i
0
.
0
1
(
0
.
1
0
)
0
.
0
2
(
0
.
0
0
)
-
0
.
4
3
(
0
.
0
3
)
0
.
4
1
(
0
.
2
8
)
0
.
3
3
(
0
.
0
7
)
0
.
2
0
(
0
.
2
5
)
F_
M
ea
s
u
re
0
.
3
6
(
0
.
0
4
)
0
.
2
3
(
0
.
0
1
)
-
0
.
6
0
(
0
.
0
4
)
0
.
6
2
(
0
.
2
0
)
0
.
5
7
(
0
.
0
6
)
0
.
7
6
(
0
.
1
1
)
SSCFM
C
A
r
i
0
.
4
5
(
0
.
0
0
)
0
.
0
3
(
0
.
0
0
)
0
.
3
5
(
0
.
0
0
)
0
.
6
8
(
0
.
0
0
)
0
.
5
1
(
0
.
0
1
)
0
.
4
2
(
0
.
0
0
)
0
.
6
0
(
0
.
0
1
)
F_
M
ea
s
u
re
0
.
2
9
(
0
.
0
0
)
0
.
4
1
(
0
.
0
0
)
0
.
3
1
(
0
.
0
0
)
0
.
5
2
(
0
.
0
0
)
0
.
5
3
(
0
.
0
0
)
0
.
6
7
(
0
.
0
0
)
0
.
9
1
(
0
.
0
0
)
I
n
T
ab
le
2
,
th
e
p
r
o
p
o
s
ed
SS
C
FMC
m
eth
o
d
,
ev
alu
ated
u
s
in
g
th
e
AR
I
m
etr
ic,
d
em
o
n
s
tr
ated
th
e
b
est
p
er
f
o
r
m
an
ce
in
4
o
u
t o
f
7
ca
s
es (
f
lo
wer
s
,
in
ter
n
et,
m
u
ltip
le
f
ea
tu
r
es,
3
-
s
o
u
r
ce
s
)
.
T
h
e
p
e
r
f
o
r
m
an
ce
co
m
p
ar
is
o
n
b
ased
o
n
th
e
AR
I
m
ea
s
u
r
e
d
em
o
n
s
tr
ates
th
e
o
u
ts
tan
d
in
g
ca
p
ab
ilit
ies
o
f
th
e
SS
C
FM
C
alg
o
r
ith
m
ac
r
o
s
s
v
ar
io
u
s
d
atasets
.
I
n
th
e
Flo
wer
s
d
ataset,
SS
C
FM
C
ac
h
iev
ed
an
AR
I
s
co
r
e
o
f
0
.
3
5
,
m
atch
i
n
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
PS
O_
R
alg
o
r
ith
m
,
in
d
icatin
g
s
tr
o
n
g
co
m
p
etitiv
e
ab
il
ity
.
Fo
r
th
e
I
m
ag
e
d
ataset,
SS
C
FM
C
attain
ed
an
AR
I
s
co
r
e
o
f
0
.
4
2
,
s
u
r
p
ass
ed
o
n
ly
b
y
PS
O_
R
W
L
(
0
.
5
0
)
an
d
PS
O_
R
W
G
(
0
.
4
9
)
,
h
ig
h
lig
h
ti
n
g
its
h
i
g
h
ef
f
icac
y
in
clu
s
ter
in
g
im
ag
e
d
ata.
No
t
ab
ly
,
in
th
e
in
ter
n
et
d
ataset,
SS
C
FM
C
ac
h
iev
ed
th
e
h
ig
h
est
AR
I
s
co
r
e
o
f
0
.
6
0
am
o
n
g
all
co
m
p
ar
ed
alg
o
r
ith
m
s
,
u
n
d
e
r
s
co
r
in
g
its
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
h
an
d
lin
g
i
n
ter
n
et
-
r
elate
d
d
ata
.
Similar
ly
,
in
t
h
e
m
u
ltip
le
f
ea
t
u
r
es
d
ataset
,
SS
C
FMC
ac
h
iev
ed
an
AR
I
s
co
r
e
o
f
0
.
6
8
,
o
u
tp
er
f
o
r
m
in
g
all
o
th
e
r
m
eth
o
d
s
,
i
n
clu
d
in
g
th
e
to
p
p
er
f
o
r
m
e
r
s
PS
O_
R
W
L
(
0
.
6
6
)
an
d
PS
O_
R
W
G
(
0
.
6
2
)
,
s
h
o
w
ca
s
in
g
its
ex
ce
llen
t
ca
p
ab
ilit
y
in
d
ea
lin
g
with
co
m
p
lex
d
atasets
.
W
h
ile
in
th
e
Ph
o
n
em
e
d
ataset,
SS
C
FM
C
s
co
r
ed
an
AR
I
o
f
0
.
5
1
,
wh
ich
is
lo
wer
th
an
s
o
m
e
alg
o
r
ith
m
s
lik
e
PS
O_
R
(
0
.
7
1
)
an
d
PS
O_
R
W
L
(
0
.
7
2
)
,
it
s
till
s
h
o
ws
co
n
s
id
er
ab
le
p
o
ten
tial
f
o
r
im
p
r
o
v
e
m
en
t.
Fo
r
th
e
wate
r
tr
ea
tm
en
t
d
ataset
,
alth
o
u
g
h
SS
C
FMC
ac
h
iev
ed
a
m
o
d
est
AR
I
s
co
r
e
o
f
0
.
0
3
,
its
p
er
f
o
r
m
a
n
ce
was
co
n
s
is
ten
t
with
o
th
er
alg
o
r
ith
m
s
,
r
ef
lectin
g
th
e
i
n
h
er
en
t
ch
allen
g
es
o
f
th
is
ty
p
e
o
f
d
ata.
Fin
ally
,
in
th
e
3
-
So
u
r
ce
s
d
ataset,
S
SC
F
MC
ac
h
iev
e
d
an
im
p
r
ess
iv
e
AR
I
s
co
r
e
o
f
0
.
4
5
,
s
ig
n
if
ican
tl
y
o
u
tp
er
f
o
r
m
in
g
o
th
e
r
m
eth
o
d
s
,
em
p
h
asizin
g
its
s
tr
en
g
th
in
m
u
lti
-
s
o
u
r
ce
d
ata
in
teg
r
atio
n
.
Ad
d
itio
n
ally
,
t
h
e
e
x
p
er
im
e
n
tal
r
esu
lts
p
r
esen
ted
in
T
ab
le
2
d
em
o
n
s
tr
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
SS
C
FMC
a
lg
o
r
ith
m
ac
r
o
s
s
v
ar
io
u
s
d
atasets
u
s
in
g
th
e
F
-
m
ea
s
u
r
e
m
etr
ic.
T
h
e
SS
C
FM
C
m
eth
o
d
ac
h
iev
e
d
th
e
h
ig
h
est
p
er
f
o
r
m
a
n
ce
in
3
o
u
t
o
f
7
ca
s
es
(
im
ag
e,
in
ter
n
et,
wa
ter
tr
ea
tm
en
t
)
wh
en
ev
alu
ated
with
th
e
F
-
m
ea
s
u
r
e
m
etr
ic.
No
tab
ly
,
SS
C
FMC
ex
ce
ls
in
th
e
in
ter
n
et
d
ataset
with
an
F
-
m
ea
s
u
r
e
o
f
0
.
9
1
,
o
u
tp
er
f
o
r
m
in
g
all
o
th
er
alg
o
r
ith
m
s
an
d
d
e
m
o
n
s
tr
atin
g
its
s
u
p
er
io
r
ca
p
ab
ilit
y
i
n
h
a
n
d
lin
g
in
ter
n
et
-
r
elate
d
d
ata.
I
n
th
e
I
m
ag
e
d
ataset,
SS
C
FMC
ac
h
iev
ed
an
im
p
r
e
s
s
iv
e
F
-
m
ea
s
u
r
e
o
f
0
.
6
7
,
m
at
ch
in
g
th
e
to
p
s
co
r
es
b
y
PS
O
_
R
W
L
(
0
.
6
7
)
an
d
PS
O_
R
W
G
(
0
.
6
6
)
,
wh
ich
u
n
d
er
s
co
r
es
its
ef
f
ec
tiv
e
n
ess
in
clu
s
ter
in
g
im
a
g
e
d
ata.
Ad
d
i
tio
n
ally
,
SS
C
FMC
s
h
o
wed
r
o
b
u
s
tn
ess
in
t
h
e
W
ater
T
r
ea
tm
en
t
d
ataset
with
an
F
-
m
ea
s
u
r
e
o
f
0
.
4
1
,
s
u
r
p
a
s
s
in
g
s
ev
er
al
o
th
e
r
m
eth
o
d
s
in
th
is
ch
allen
g
i
n
g
c
o
n
tex
t.
Ho
wev
e
r
,
th
e
alg
o
r
ith
m
'
s
p
er
f
o
r
m
an
ce
in
th
e
Flo
w
er
s
d
ataset,
with
an
F
-
m
ea
s
u
r
e
o
f
0
.
3
1
,
s
u
g
g
est
s
th
er
e
is
s
ig
n
if
ican
t
r
o
o
m
f
o
r
im
p
r
o
v
em
en
t
c
o
m
p
ar
e
d
to
h
i
g
h
er
-
s
co
r
in
g
alg
o
r
ith
m
s
lik
e
PS
O_
R
(
0
.
5
3
)
,
PS
O_
R
W
G
(
0
.
4
7
)
an
d
M
R
DC
A_
R
W
G
(
0
.
4
7
)
.
Similar
ly
,
in
th
e
M
u
ltip
le
Featu
r
es
d
ataset,
S
SC
FMC
attain
ed
a
co
m
p
etitiv
e
F
-
m
ea
s
u
r
e
o
f
0
.
5
2
,
b
u
t
s
till
lag
g
ed
b
eh
in
d
th
e
to
p
p
er
f
o
r
m
er
s
s
u
ch
as
PS
O_
R
W
L
(
0
.
8
2
)
an
d
PS
O_
R
W
G
(
0
.
8
0
)
,
in
d
icatin
g
ar
ea
s
f
o
r
f
u
r
th
e
r
en
h
a
n
ce
m
en
t.
Fo
r
th
e
Ph
o
n
em
e
d
ataset,
SS
C
FM
C
'
s
F
-
m
ea
s
u
r
e
o
f
0
.
5
3
,
wh
ile
r
esp
ec
tab
le,
tr
ails
b
eh
in
d
lead
i
n
g
alg
o
r
ith
m
s
s
u
ch
as
PS
O_
R
(
0
.
8
5
)
,
PS
O_
R
W
L
(
0
.
8
5
)
an
d
PS
O_
R
W
G
(
0
.
8
5
)
.
I
n
th
e
3
-
So
u
r
ce
s
d
ataset,
SS
C
FM
C
s
co
r
ed
an
F
-
m
ea
s
u
r
e
o
f
0
.
2
9
,
in
d
icatin
g
a
n
ee
d
f
o
r
f
u
r
th
er
r
ef
in
em
en
t t
o
b
etter
in
teg
r
ate
m
u
lti
-
s
o
u
r
ce
d
ata.
T
h
ese
r
esu
lts
h
ig
h
lig
h
t
b
o
th
t
h
e
s
tr
en
g
th
s
an
d
lim
itatio
n
s
o
f
th
e
alg
o
r
ith
m
,
s
u
g
g
esti
n
g
s
p
e
cif
ic
ar
ea
s
f
o
r
o
p
tim
izatio
n
t
o
en
h
an
ce
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
d
iv
er
s
e
d
at
asets
.
No
tab
ly
,
SS
C
FM
C
ex
ce
ls
in
in
ter
n
et
d
ata
clu
s
ter
in
g
,
d
em
o
n
s
tr
atin
g
s
ig
n
if
ican
t
p
o
ten
tial
in
co
m
p
le
x
an
d
in
ter
n
et
-
r
elate
d
d
atasets
.
W
h
ile
th
er
e
is
r
o
o
m
f
o
r
f
u
r
th
er
im
p
r
o
v
em
en
t,
SS
C
FMC
also
s
h
o
ws
h
ig
h
an
d
s
tab
le
p
er
f
o
r
m
an
ce
ac
r
o
s
s
v
ar
io
u
s
d
ata
ty
p
es,
alo
n
g
with
r
em
ar
k
ab
le
f
lex
ib
ilit
y
an
d
ad
ap
tab
ilit
y
,
m
ak
in
g
it a
h
ig
h
ly
u
s
ef
u
l a
n
d
ef
f
ec
tiv
e
clu
s
ter
in
g
to
o
l.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
8
8
3
-
6
8
9
3
6890
Fig
u
r
e
3
s
h
o
wca
s
es
th
e
r
u
n
tim
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
SS
C
F
MC
alg
o
r
ith
m
ac
r
o
s
s
s
ev
en
m
u
lti
-
v
iew
r
elatio
n
al
d
atasets
.
T
h
e
r
esu
lts
r
ev
ea
l
s
ig
n
if
ican
t
d
if
f
er
e
n
ce
s
in
r
u
n
tim
e
am
o
n
g
th
ese
d
atasets
,
o
f
f
er
in
g
v
alu
ab
le
in
s
ig
h
ts
in
to
th
e
alg
o
r
ith
m
'
s
ef
f
icien
cy
an
d
p
o
ten
t
ial
ar
ea
s
f
o
r
e
n
h
an
ce
m
en
t.
T
h
e
m
u
ltip
le
f
ea
tu
r
es
(
Mf
ea
t)
d
ataset
s
h
o
ws
th
e
lo
n
g
est
r
u
n
tim
e,
ap
p
r
o
x
im
ately
1
,
4
0
0
s
ec
o
n
d
s
,
s
u
g
g
esti
n
g
t
h
at
its
co
m
p
lex
ity
r
eq
u
ir
es
s
u
b
s
tan
tial
c
o
m
p
u
tatio
n
al
r
eso
u
r
ce
s
.
I
n
co
n
tr
ast,
th
e
W
ater
an
d
3
-
So
u
r
ce
s
d
atasets
h
av
e
t
h
e
s
h
o
r
test
r
u
n
tim
es,
b
o
th
u
n
d
e
r
2
0
0
s
ec
o
n
d
s
,
d
em
o
n
s
tr
atin
g
SS
C
FM
C
's
ef
f
icien
cy
with
s
im
p
ler
o
r
s
m
aller
d
atasets
.
T
h
e
I
m
ag
e
a
n
d
i
n
ter
n
et
d
atasets
also
ex
h
ib
it
r
elativ
ely
h
ig
h
r
u
n
tim
es,
ar
o
u
n
d
9
0
0
an
d
6
0
0
s
ec
o
n
d
s
r
esp
ec
tiv
ely
,
h
ig
h
lig
h
tin
g
th
e
co
m
p
u
tatio
n
al
in
ten
s
ity
r
e
q
u
ir
ed
f
o
r
p
r
o
c
ess
in
g
im
ag
e
a
n
d
in
ter
n
et
d
at
a.
T
h
e
Flo
wer
a
n
d
Ph
o
n
em
e
d
atasets
h
av
e
m
o
d
er
ate
r
u
n
tim
es
o
f
ab
o
u
t
6
0
0
an
d
3
0
0
s
ec
o
n
d
s
,
r
ef
lect
in
g
th
e
alg
o
r
ith
m
'
s
ef
f
ec
tiv
en
ess
in
d
ea
lin
g
wit
h
m
o
d
er
atel
y
co
m
p
le
x
d
ata.
T
h
ese
f
in
d
in
g
s
u
n
d
er
s
co
r
e
th
e
im
p
o
r
tan
ce
o
f
co
n
s
id
er
in
g
co
m
p
u
tatio
n
al
r
e
s
o
u
r
ce
s
wh
en
ap
p
ly
in
g
th
e
SS
C
FM
C
alg
o
r
ith
m
to
d
if
f
er
e
n
t
d
atasets
.
W
h
ile
SS
C
FMC
d
em
o
n
s
tr
ates
h
ig
h
an
d
s
tab
le
p
er
f
o
r
m
an
ce
ac
r
o
s
s
v
ar
io
u
s
d
ata
ty
p
es,
o
p
tim
izin
g
r
u
n
tim
e
is
cr
u
cial,
esp
ec
ially
f
o
r
co
m
p
lex
d
ataset
s
lik
e
m
u
ltip
le
f
ea
tu
r
es
an
d
im
ag
e
.
Ov
er
all,
Fig
u
r
e
3
p
r
o
v
id
e
s
v
alu
ab
le
in
s
ig
h
ts
in
to
th
e
c
o
m
p
u
tatio
n
al
ef
f
icie
n
cy
o
f
SS
C
FMC
an
d
s
u
g
g
ests
ar
ea
s
wh
er
e
alg
o
r
ith
m
ic
im
p
r
o
v
em
e
n
ts
co
u
ld
en
h
an
ce
p
er
f
o
r
m
an
ce
.
I
n
g
en
er
al,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
ac
h
iev
es
s
u
p
er
io
r
r
esu
lts
co
m
p
ar
ed
to
o
th
er
s
in
g
le
-
v
iew
an
d
m
u
lti
-
v
iew
alg
o
r
ith
m
s
.
A
d
d
itio
n
all
y
,
it
ex
h
ib
its
m
in
im
al
v
a
r
iatio
n
in
t
h
e
q
u
ality
m
ea
s
u
r
es
o
f
t
h
e
g
e
n
er
ated
p
ar
titi
o
n
s
ac
r
o
s
s
all
r
u
n
s
a
n
d
c
o
n
s
is
ten
tly
d
em
o
n
s
tr
ates
h
ig
h
er
m
ea
n
v
alu
es
f
o
r
th
ese
m
etr
i
cs,
as
s
h
o
wn
in
th
e
r
esu
lts
tab
le.
T
h
ese
f
in
d
in
g
s
h
ig
h
lig
h
t th
e
s
tab
le
p
er
f
o
r
m
an
ce
an
d
ca
p
ab
ilit
y
o
f
o
u
r
m
eth
o
d
to
p
r
o
d
u
ce
h
ig
h
er
-
q
u
ality
clu
s
ter
s
co
n
s
is
ten
tly
.
T
o
f
u
r
t
h
er
en
h
an
ce
e
f
f
icien
cy
,
esp
ec
ially
f
o
r
c
o
m
p
lex
d
ata
s
ets,
o
p
tim
izin
g
th
e
alg
o
r
ith
m
'
s
p
r
o
ce
s
s
in
g
s
tep
s
o
r
em
p
lo
y
i
n
g
m
o
r
e
ad
v
an
ce
d
c
o
m
p
u
tatio
n
al
tec
h
n
iq
u
es is
ess
en
tial.
Fig
u
r
e
3
.
E
x
ec
u
tio
n
tim
e
o
f
m
u
lti
-
v
iew
r
elatio
n
al
m
eth
o
d
s
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
I
n
th
is
s
tu
d
y
,
we
in
tr
o
d
u
ce
d
a
n
o
v
el
s
em
i
-
s
u
p
e
r
v
is
ed
co
n
s
en
s
u
s
f
u
zz
y
clu
s
ter
in
g
m
eth
o
d
(
SS
C
FMC
)
s
p
ec
if
ically
d
esig
n
ed
f
o
r
m
u
lt
i
-
v
iew
r
elatio
n
al
d
ata.
Ou
r
m
e
th
o
d
e
f
f
ec
tiv
ely
co
m
b
i
n
es
th
e
s
tr
en
g
th
s
o
f
s
em
i
-
s
u
p
er
v
is
ed
lear
n
in
g
,
co
n
s
en
s
u
s
clu
s
ter
in
g
,
an
d
m
u
lti
-
v
ie
w
d
ata
in
te
g
r
atio
n
to
p
r
o
v
id
e
a
c
o
m
p
r
e
h
en
s
iv
e
s
o
lu
tio
n
f
o
r
co
m
p
lex
cl
u
s
ter
in
g
task
s
.
Ou
r
r
esear
ch
h
as
d
em
o
n
s
tr
ated
s
ev
er
al
s
ig
n
if
ica
n
t
a
d
v
an
ce
m
e
n
ts
.
First,
SS
C
FMC
ac
h
iev
es
h
ig
h
er
clu
s
ter
in
g
ac
cu
r
ac
y
b
y
lev
er
a
g
in
g
b
o
th
lab
eled
an
d
u
n
lab
eled
d
ata,
o
u
tp
er
f
o
r
m
in
g
tr
ad
itio
n
al
s
in
g
le
-
v
iew
an
d
u
n
s
u
p
er
v
is
ed
m
eth
o
d
s
.
T
h
is
r
esu
lts
in
m
o
r
e
r
eliab
le
an
d
r
o
b
u
s
t
clu
s
ter
in
g
o
u
tco
m
es.
Seco
n
d
,
th
e
f
lex
i
b
ilit
y
an
d
ad
ap
ta
b
ilit
y
o
f
SS
C
FM
C
en
ab
le
it
to
h
an
d
le
m
u
ltip
le
v
iews
an
d
in
teg
r
ate
d
i
v
er
s
e
d
ata
s
o
u
r
ce
s
,
p
r
o
v
id
in
g
a
m
o
r
e
h
o
lis
tic
u
n
d
er
s
tan
d
in
g
o
f
th
e
d
ata.
T
h
is
ca
p
ab
ilit
y
is
p
ar
ticu
lar
ly
b
en
ef
icial
f
o
r
co
m
p
lex
d
atasets
o
f
ten
en
co
u
n
t
er
ed
in
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
s
.
L
astl
y
,
SS
C
FMC
m
ain
tain
s
co
m
p
u
tatio
n
al
ef
f
i
cien
cy
wh
ile
p
r
o
ce
s
s
in
g
m
u
l
ti
-
v
iew
d
ata,
m
ak
i
n
g
it
s
u
ita
b
le
f
o
r
lar
g
e
-
s
ca
le
ap
p
licatio
n
s
.
T
h
is
ad
d
r
ess
es a
s
ig
n
if
ican
t lim
itatio
n
o
f
m
a
n
y
ex
is
tin
g
m
eth
o
d
s
th
at
s
tr
u
g
g
le
with
s
ca
lab
ilit
y
.
Ou
r
f
in
d
in
g
s
h
av
e
s
ev
er
al
i
m
p
o
r
tan
t
im
p
licatio
n
s
f
o
r
b
o
th
th
e
r
esear
ch
f
ield
an
d
th
e
b
r
o
ad
e
r
co
m
m
u
n
ity
.
First,
SS
C
FMC
ad
v
an
ce
s
m
u
lti
-
v
iew
clu
s
ter
i
n
g
tech
n
iq
u
es
b
y
in
tr
o
d
u
cin
g
a
r
o
b
u
s
t
m
eth
o
d
ca
p
ab
le
o
f
ef
f
icien
tly
h
a
n
d
li
n
g
th
e
co
m
p
lex
ity
o
f
m
u
lti
-
v
iew
r
elatio
n
al
d
ata.
T
h
is
in
n
o
v
atio
n
p
u
s
h
es
th
e
b
o
u
n
d
ar
ies
o
f
cu
r
r
en
t
clu
s
ter
i
n
g
tech
n
iq
u
es.
Ad
d
itio
n
ally
,
th
e
f
lex
ib
ilit
y
an
d
ac
cu
r
ac
y
o
f
SS
C
FMC
m
ak
e
it
ap
p
licab
le
to
v
ar
io
u
s
d
o
m
ain
s
,
s
u
ch
as
b
io
in
f
o
r
m
atics,
s
o
cial
n
etwo
r
k
an
aly
s
is
,
an
d
m
ar
k
et
r
esear
ch
,
wh
er
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
o
ve
l
s
emi
-
s
u
p
ervis
ed
co
n
s
en
s
u
s
fu
z
z
y
clu
s
ter
in
g
meth
o
d
f
o
r
mu
lti
-
view
…
(
Ho
a
n
g
Th
i
C
a
n
h
)
6891
m
u
lti
-
v
iew
d
ata
is
p
r
ev
alen
t.
On
e
o
f
th
e
o
u
ts
tan
d
in
g
q
u
es
tio
n
s
ad
d
r
ess
ed
b
y
o
u
r
r
esear
ch
is
th
e
ef
f
ec
tiv
e
in
teg
r
atio
n
o
f
m
u
lti
-
v
iew
d
ata
f
o
r
clu
s
ter
in
g
p
u
r
p
o
s
es.
T
h
e
SS
C
FM
C
m
eth
o
d
o
f
f
er
s
a
s
o
lu
tio
n
th
at
s
ig
n
if
ican
tly
im
p
r
o
v
es
clu
s
ter
in
g
ac
cu
r
ac
y
wh
ile
en
h
a
n
cin
g
r
esu
lt
in
ter
p
r
etab
ilit
y
th
r
o
u
g
h
th
e
in
teg
r
atio
n
o
f
m
u
ltip
le
d
ata
p
er
s
p
ec
tiv
es.
T
h
ese
p
r
o
m
is
in
g
f
in
d
in
g
s
p
a
v
e
th
e
way
f
o
r
f
u
r
th
e
r
r
esear
ch
in
m
u
lti
-
v
iew
clu
s
ter
in
g
.
Ho
wev
er
,
d
esp
ite
its
clea
r
ef
f
ec
tiv
en
ess
in
h
a
n
d
lin
g
m
u
lti
-
s
o
u
r
ce
d
ata,
SS
C
FM
C
h
as
ce
r
tain
lim
itatio
n
s
.
On
e
d
r
aw
b
ac
k
o
f
SS
C
FM
C
is
its
s
lo
wer
r
u
n
n
in
g
tim
e,
as
it
is
d
esig
n
ed
to
b
etter
e
x
p
lo
r
e
th
e
s
ea
r
ch
s
p
ac
e.
Ad
d
itio
n
ally
,
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
m
ay
n
o
t b
e
s
u
itab
le
f
o
r
h
an
d
lin
g
v
er
y
l
ar
g
e
d
atasets
d
u
e
to
its
co
m
p
lex
ity
.
Mo
r
eo
v
er
,
it
r
eq
u
ir
es
m
ain
tain
in
g
s
ev
er
al
d
is
s
im
ilar
ity
m
atr
ices,
wh
ich
ca
n
p
o
s
e
m
em
o
r
y
co
n
s
tr
ain
ts
.
E
f
f
ec
tiv
ely
tack
li
n
g
th
e
co
m
p
le
x
ities
o
f
m
u
lti
-
v
iew
d
ata,
esp
ec
ially
wh
e
n
s
o
u
r
ce
d
f
r
o
m
d
i
v
er
s
e
p
er
s
p
ec
tiv
es,
n
ec
ess
itates
th
e
o
n
g
o
in
g
d
ev
elo
p
m
en
t o
f
in
n
o
v
ativ
e
alg
o
r
ith
m
s
in
f
u
tu
r
e
r
es
ea
r
ch
ef
f
o
r
ts
.
Fu
tu
r
e
wo
r
k
co
u
ld
f
o
cu
s
o
n
f
u
r
th
e
r
o
p
tim
izin
g
t
h
e
alg
o
r
ith
m
'
s
p
r
o
ce
s
s
in
g
s
tep
s
o
r
e
x
p
lo
r
i
n
g
m
o
r
e
ad
v
a
n
ce
d
co
m
p
u
tatio
n
al
tec
h
n
iq
u
es to
e
n
h
an
ce
its
p
er
f
o
r
m
a
n
ce
.
I
n
co
n
clu
s
io
n
,
th
e
n
o
v
el
SS
C
FMC
m
eth
o
d
we
h
av
e
p
r
o
p
o
s
ed
o
f
f
er
s
s
ig
n
if
ican
t
im
p
r
o
v
e
m
en
ts
o
v
er
ex
is
tin
g
clu
s
ter
in
g
tech
n
iq
u
es.
I
t
n
o
t
o
n
l
y
ad
d
r
ess
es
th
e
ch
allen
g
es
ass
o
ciate
d
with
m
u
lti
-
v
iew
d
ata
b
u
t
also
s
ets a
f
o
u
n
d
atio
n
f
o
r
f
u
tu
r
e
ad
v
an
ce
m
en
ts
in
th
e
f
ield
.
B
y
p
r
o
v
id
in
g
a
r
o
b
u
s
t,
ef
f
icien
t,
an
d
f
lex
ib
le
clu
s
ter
in
g
s
o
lu
tio
n
,
SS
C
FM
C
h
as th
e
p
o
t
en
tial to
m
ak
e
a
s
u
b
s
tan
tial im
p
ac
t o
n
b
o
th
r
esear
c
h
an
d
p
r
ac
tical
ap
p
licatio
n
s
.
ACK
NO
WL
E
DG
E
M
E
NT
S
W
e
ar
e
g
r
atef
u
l
f
o
r
th
e
s
u
p
p
o
r
t
f
r
o
m
th
e
Gr
a
n
t
C
S2
4
.
0
4
f
u
n
d
e
d
b
y
th
e
I
n
s
titu
te
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Vietn
am
Aca
d
e
m
y
o
f
Scien
ce
a
n
d
T
ec
h
n
o
l
o
g
y
.
RE
F
E
R
E
NC
E
S
[
1
]
C
.
Zh
e
n
g
,
T
.
Li
u
,
A
.
A
b
d
-
El
r
a
h
m
a
n
,
V
.
M
.
W
h
i
t
a
k
e
r
,
a
n
d
B
.
W
i
l
k
i
n
s
o
n
,
“
O
b
j
e
c
t
-
d
e
t
e
c
t
i
o
n
f
r
o
m
mu
l
t
i
-
v
i
e
w
r
e
m
o
t
e
s
e
n
s
i
n
g
i
ma
g
e
s
:
A
c
a
s
e
st
u
d
y
o
f
f
r
u
i
t
a
n
d
f
l
o
w
e
r
d
e
t
e
c
t
i
o
n
a
n
d
c
o
u
n
t
i
n
g
o
n
a
c
e
n
t
r
a
l
F
l
o
r
i
d
a
s
t
r
a
w
b
e
r
r
y
f
a
r
m
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ap
p
l
i
e
d
E
a
rt
h
O
b
ser
v
a
t
i
o
n
a
n
d
G
e
o
i
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
2
3
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
g
.
2
0
2
3
.
1
0
3
4
5
7
.
[
2
]
J.
Z
h
a
n
g
,
Y
.
Z
h
o
u
,
K
.
X
i
a
,
Y
.
J
i
a
n
g
,
a
n
d
Y
.
Li
u
,
“
A
n
o
v
e
l
a
u
t
o
ma
t
i
c
i
ma
g
e
se
g
m
e
n
t
a
t
i
o
n
m
e
t
h
o
d
f
o
r
C
h
i
n
e
se
l
i
t
e
r
a
t
i
p
a
i
n
t
i
n
g
s
u
si
n
g
m
u
l
t
i
-
v
i
e
w
f
u
z
z
y
c
l
u
s
t
e
r
i
n
g
t
e
c
h
n
o
l
o
g
y
,
”
M
u
l
t
i
m
e
d
i
a
S
y
s
t
e
m
s
,
v
o
l
.
2
6
,
n
o
.
1
,
p
p
.
3
7
–
5
1
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
3
0
-
0
1
9
-
0
0
6
2
7
-
7.
[
3
]
Y
.
Y
a
n
g
a
n
d
H
.
W
a
n
g
,
“
M
u
l
t
i
-
v
i
e
w
c
l
u
st
e
r
i
n
g
:
a
su
r
v
e
y
,
”
Bi
g
D
a
t
a
M
i
n
i
n
g
a
n
d
A
n
a
l
y
t
i
c
s
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
8
3
–
1
0
7
,
J
u
n
.
2
0
1
8
,
d
o
i
:
1
0
.
2
6
5
9
9
/
B
D
M
A
.
2
0
1
8
.
9
0
2
0
0
0
3
.
[
4
]
J.
Li
u
,
Y
.
J
i
a
n
g
,
Z.
L
i
,
Z.
H
.
Z
h
o
u
,
a
n
d
H
.
Lu
,
“
P
a
r
t
i
a
l
l
y
s
h
a
r
e
d
l
a
t
e
n
t
f
a
c
t
o
r
l
e
a
r
n
i
n
g
w
i
t
h
m
u
l
t
i
v
i
e
w
d
a
t
a
,
”
I
EEE
T
ra
n
sa
c
t
i
o
n
s o
n
N
e
u
ra
l
N
e
t
w
o
rks
a
n
d
L
e
a
r
n
i
n
g
S
y
st
e
m
s
,
v
o
l
.
2
6
,
n
o
.
6
,
p
p
.
1
2
3
3
–
1
2
4
6
,
J
u
n
.
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
N
LS.
2
0
1
4
.
2
3
3
5
2
3
4
.
[
5
]
G
.
C
h
a
o
,
S
.
S
u
n
,
a
n
d
J.
B
i
,
“
A
s
u
r
v
e
y
o
n
mu
l
t
i
v
i
e
w
c
l
u
s
t
e
r
i
n
g
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
1
4
6
–
1
6
8
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TA
I
.
2
0
2
1
.
3
0
6
5
8
9
4
.
[
6
]
D
.
H
u
a
n
g
,
C
.
D
.
W
a
n
g
,
a
n
d
J
.
H
.
L
a
i
,
“
F
a
st
mu
l
t
i
-
v
i
e
w
c
l
u
st
e
r
i
n
g
v
i
a
e
n
s
e
m
b
l
e
s:
To
w
a
r
d
s s
c
a
l
a
b
i
l
i
t
y
,
s
u
p
e
r
i
o
r
i
t
y
,
a
n
d
s
i
mp
l
i
c
i
t
y
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
3
5
,
n
o
.
1
1
,
p
p
.
1
1
3
8
8
–
1
1
4
0
2
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E.
2
0
2
3
.
3
2
3
6
6
9
8
.
[
7
]
Q
.
W
a
n
g
,
Z.
D
i
n
g
,
Z
.
T
a
o
,
Q
.
G
a
o
,
a
n
d
Y
.
F
u
,
“
P
a
r
t
i
a
l
m
u
l
t
i
-
v
i
e
w
c
l
u
s
t
e
r
i
n
g
v
i
a
c
o
n
si
s
t
e
n
t
G
A
N
,
”
i
n
2
0
1
8
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
M
i
n
i
n
g
(
I
C
D
M)
,
N
o
v
.
2
0
1
8
,
p
p
.
1
2
9
0
–
1
2
9
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
M
.
2
0
1
8
.
0
0
1
7
4
.
[
8
]
Z.
C
a
o
a
n
d
X
.
X
i
e
,
“
S
t
r
u
c
t
u
r
e
l
e
a
r
n
i
n
g
w
i
t
h
c
o
n
se
n
su
s
l
a
b
e
l
i
n
f
o
r
m
a
t
i
o
n
f
o
r
mu
l
t
i
-
v
i
e
w
u
n
s
u
p
e
r
v
i
se
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
8
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
1
8
9
3
.
[
9
]
R
.
Zh
a
n
g
,
F
.
N
i
e
,
X
.
L
i
,
a
n
d
X
.
W
e
i
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
w
i
t
h
mu
l
t
i
-
v
i
e
w
d
a
t
a
:
a
s
u
r
v
e
y
,
”
I
n
f
o
rm
a
t
i
o
n
Fu
si
o
n
,
v
o
l
.
5
0
,
p
p
.
1
5
8
–
1
6
7
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s
.
2
0
1
8
.
1
1
.
0
1
9
.
[
1
0
]
J.
L
i
u
,
C
.
W
a
n
g
,
J.
G
a
o
,
a
n
d
J.
H
a
n
,
“
M
u
l
t
i
-
v
i
e
w
c
l
u
s
t
e
r
i
n
g
v
i
a
j
o
i
n
t
n
o
n
n
e
g
a
t
i
v
e
ma
t
r
i
x
f
a
c
t
o
r
i
z
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
3
S
I
AM
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
M
i
n
i
n
g
,
S
D
M
2
0
1
3
,
M
a
y
2
0
1
3
,
p
p
.
2
5
2
–
2
6
0
,
d
o
i
:
1
0
.
1
1
3
7
/
1
.
9
7
8
1
6
1
1
9
7
2
8
3
2
.
2
8
.
[
1
1
]
L.
F
u
,
P
.
Li
n
,
A
.
V
.
V
a
s
i
l
a
k
o
s,
a
n
d
S
.
W
a
n
g
,
“
A
n
o
v
e
r
v
i
e
w
o
f
r
e
c
e
n
t
m
u
l
t
i
-
v
i
e
w
c
l
u
s
t
e
r
i
n
g
,
”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
0
2
,
p
p
.
1
4
8
–
1
6
1
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
2
0
.
0
2
.
1
0
4
.
[
1
2
]
Y
.
Z
h
a
n
g
,
Y
.
Y
a
n
g
,
T.
Li
,
a
n
d
H
.
F
u
j
i
t
a
,
“
A
mu
l
t
i
t
a
sk
m
u
l
t
i
v
i
e
w
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m
i
n
h
e
t
e
r
o
g
e
n
e
o
u
s
si
t
u
a
t
i
o
n
s
b
a
s
e
d
o
n
LL
E
a
n
d
L
E,
”
K
n
o
w
l
e
d
g
e
-
Ba
s
e
d
S
y
st
e
m
s
,
v
o
l
.
1
6
3
,
p
p
.
7
7
6
–
7
8
6
,
J
a
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
1
8
.
1
0
.
0
0
1
.
[
1
3
]
S
.
W
a
n
g
e
t
a
l
.
,
“
M
u
l
t
i
-
v
i
e
w
c
l
u
s
t
e
r
i
n
g
v
i
a
l
a
t
e
f
u
si
o
n
a
l
i
g
n
me
n
t
m
a
x
i
mi
z
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
T
w
e
n
t
y
-
E
i
g
h
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
A
u
g
.
2
0
1
9
,
p
p
.
3
7
7
8
–
3
7
8
4
,
d
o
i
:
1
0
.
2
4
9
6
3
/
i
j
c
a
i
.
2
0
1
9
/
5
2
4
.
[
1
4
]
P
.
T.
H
u
a
n
e
t
a
l
.
,
“
TS
3
F
C
M
:
t
r
u
s
t
e
d
saf
e
sem
i
-
su
p
e
r
v
i
s
e
d
f
u
z
z
y
c
l
u
st
e
r
i
n
g
m
e
t
h
o
d
f
o
r
d
a
t
a
p
a
r
t
i
t
i
o
n
w
i
t
h
h
i
g
h
c
o
n
f
i
d
e
n
c
e
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
1
,
n
o
.
9
,
p
p
.
1
2
5
6
7
–
1
2
5
9
8
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
2
-
1
2
1
3
3
-
6.
[
1
5
]
A
.
M
u
r
u
g
a
n
,
D
.
G
o
b
i
n
a
t
h
,
S
.
G
a
n
e
s
h
K
u
m
a
r
,
B
.
M
u
r
u
g
a
n
a
n
t
h
a
m,
a
n
d
S
.
V
e
l
u
s
a
m
y
,
“
A
t
i
m
e
e
f
f
i
c
i
e
n
t
a
n
d
a
c
c
u
r
a
t
e
r
e
t
r
i
e
v
a
l
o
f
r
a
n
g
e
a
g
g
r
e
g
a
t
e
q
u
e
r
i
e
s
u
s
i
n
g
f
u
z
z
y
c
l
u
st
e
r
i
n
g
me
a
n
s
(
F
C
M
)
a
p
p
r
o
a
c
h
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
4
1
5
–
4
2
0
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
0
i
1
.
p
p
4
1
5
-
4
2
0
.
[
1
6
]
W
.
A
l
o
mo
u
s
h
,
A
.
A
l
r
o
sa
n
,
A
.
A
l
m
o
ma
n
i
,
K
.
A
l
i
ss
a
,
O
.
A
.
K
h
a
s
h
a
n
,
a
n
d
A
.
A
l
-
N
a
w
a
sr
a
h
,
“
S
p
a
t
i
a
l
i
n
f
o
r
mat
i
o
n
o
f
f
u
z
z
y
c
l
u
st
e
r
i
n
g
b
a
s
e
d
m
e
a
n
b
e
st
a
r
t
i
f
i
c
i
a
l
b
e
e
c
o
l
o
n
y
a
l
g
o
r
i
t
h
m
f
o
r
p
h
a
n
t
o
m
b
r
a
i
n
i
ma
g
e
s
e
g
m
e
n
t
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
4
0
5
0
–
4
0
5
8
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
5
.
p
p
4
0
5
0
-
4
0
5
8
.
[
1
7
]
T.
M
.
T
u
a
n
e
t
a
l
.
,
“
A
n
e
w
a
p
p
r
o
a
c
h
f
o
r
sem
i
-
su
p
e
r
v
i
s
e
d
f
u
z
z
y
c
l
u
s
t
e
r
i
n
g
w
i
t
h
m
u
l
t
i
p
l
e
f
u
z
z
i
f
i
e
r
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
F
u
zz
y
S
y
s
t
e
m
s
,
v
o
l
.
2
4
,
n
o
.
8
,
p
p
.
3
6
8
8
–
3
7
0
1
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
8
1
5
-
0
2
2
-
0
1
3
6
3
-
3.
[
1
8
]
D
.
P
.
D
i
o
g
o
a
n
d
F
.
d
e
A
.
F
r
a
n
c
i
sc
o
d
e
,
“
M
e
d
o
i
d
b
a
s
e
d
sem
i
-
su
p
e
r
v
i
s
e
d
f
u
z
z
y
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
m
u
l
t
i
-
v
i
e
w
r
e
l
a
t
i
o
n
a
l
d
a
t
a
,
”
F
u
zzy
S
e
t
s
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
4
6
9
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
ss
.
2
0
2
3
.
1
0
8
6
3
0
.
[
1
9
]
H
.
C
a
i
,
B
.
L
i
u
,
Y
.
X
i
a
o
,
a
n
d
L.
Y
.
Li
n
,
“
S
e
m
i
-
su
p
e
r
v
i
s
e
d
m
u
l
t
i
-
v
i
e
w
c
l
u
s
t
e
r
i
n
g
b
a
se
d
o
n
o
r
t
h
o
n
o
r
m
a
l
i
t
y
-
c
o
n
s
t
r
a
i
n
e
d
n
o
n
n
e
g
a
t
i
v
e
mat
r
i
x
f
a
c
t
o
r
i
z
a
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
5
3
6
,
p
p
.
1
7
1
–
1
8
4
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
2
0
.
0
5
.
0
7
3
.
[
2
0
]
S
.
B
i
c
k
e
l
a
n
d
T.
S
c
h
e
f
f
e
r
,
“
M
u
l
t
i
-
v
i
e
w
c
l
u
st
e
r
i
n
g
,
”
i
n
F
o
u
rt
h
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
a
t
a
Mi
n
i
n
g
(
I
C
D
M’0
4
)
,
2
0
0
4
,
p
p
.
1
9
–
2
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
M
.
2
0
0
4
.
1
0
0
9
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
8
8
3
-
6
8
9
3
6892
[
2
1
]
F
.
Y
e
,
Z.
C
h
e
n
,
H
.
Q
i
a
n
,
R
.
L
i
,
C
.
C
h
e
n
,
a
n
d
Z.
Z
h
e
n
g
,
“
N
e
w
a
p
p
r
o
a
c
h
e
s
i
n
mu
l
t
i
-
v
i
e
w
c
l
u
st
e
r
i
n
g
,
”
i
n
R
e
c
e
n
t
A
p
p
l
i
c
a
t
i
o
n
s
i
n
D
a
t
a
C
l
u
st
e
ri
n
g
,
I
n
Te
c
h
,
2
0
1
8
.
[
2
2
]
H
.
F
r
i
g
u
i
,
C
.
H
w
a
n
g
,
a
n
d
F
.
C
h
u
n
g
-
H
o
o
n
R
h
e
e
,
“
C
l
u
st
e
r
i
n
g
a
n
d
a
g
g
r
e
g
a
t
i
o
n
o
f
r
e
l
a
t
i
o
n
a
l
d
a
t
a
w
i
t
h
a
p
p
l
i
c
a
t
i
o
n
s
t
o
i
ma
g
e
d
a
t
a
b
a
se
c
a
t
e
g
o
r
i
z
a
t
i
o
n
,
”
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
4
0
,
n
o
.
1
1
,
p
p
.
3
0
5
3
–
3
0
6
8
,
N
o
v
.
2
0
0
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
0
7
.
0
2
.
0
1
9
.
[
2
3
]
H
.
F
r
i
g
u
i
a
n
d
C
.
H
w
a
n
g
,
“
F
u
z
z
y
c
l
u
s
t
e
r
i
n
g
a
n
d
a
g
g
r
e
g
a
t
i
o
n
o
f
r
e
l
a
t
i
o
n
a
l
d
a
t
a
w
i
t
h
i
n
s
t
a
n
c
e
-
l
e
v
e
l
c
o
n
st
r
a
i
n
t
s,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
F
u
zzy
S
y
st
e
m
s
,
v
o
l
.
1
6
,
n
o
.
6
,
p
p
.
1
5
6
5
–
1
5
8
1
,
D
e
c
.
2
0
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
T
F
U
ZZ.
2
0
0
8
.
2
0
0
5
6
9
2
.
[
2
4
]
S
.
M
o
d
a
k
,
“
F
i
n
d
i
n
g
g
r
o
u
p
s
i
n
d
a
t
a
:
a
n
i
n
t
r
o
d
u
c
t
i
o
n
t
o
c
l
u
st
e
r
a
n
a
l
y
s
i
s
,
a
u
t
h
o
r
e
d
b
y
Le
o
n
a
r
d
K
a
u
f
m
a
n
a
n
d
P
e
t
e
r
J.
R
o
u
ssee
u
w
,
Jo
h
n
W
i
l
e
y
a
n
d
S
o
n
s,
2
0
0
5
,
I
S
B
N
:
0
-
47
-
1
-
7
3
5
7
8
-
7
,
”
J
o
u
r
n
a
l
o
f
Ap
p
l
i
e
d
S
t
a
t
i
st
i
c
s
,
v
o
l
.
5
1
,
n
o
.
8
,
p
p
.
1
6
1
8
–
1
6
2
0
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
0
2
6
6
4
7
6
3
.
2
0
2
3
.
2
2
2
0
0
8
7
.
[
2
5
]
X
.
C
h
e
n
,
X
.
X
u
,
J.
Z.
H
u
a
n
g
,
a
n
d
Y
.
Y
e
,
“
TW
-
(
k
)
-
mea
n
s:
a
u
t
o
ma
t
e
d
t
w
o
-
l
e
v
e
l
v
a
r
i
a
b
l
e
w
e
i
g
h
t
i
n
g
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
mu
l
t
i
v
i
e
w
d
a
t
a
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
5
,
n
o
.
4
,
p
p
.
9
3
2
–
9
4
4
,
A
p
r
.
2
0
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E.
2
0
1
1
.
2
6
2
.
[
2
6
]
R
.
P
.
d
e
G
u
smã
o
a
n
d
F
.
d
e
A
.
T
.
d
e
C
a
r
v
a
l
h
o
,
“
C
l
u
st
e
r
i
n
g
o
f
m
u
l
t
i
-
v
i
e
w
r
e
l
a
t
i
o
n
a
l
d
a
t
a
b
a
se
d
o
n
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
3
,
p
p
.
3
4
–
5
3
,
J
u
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
8
.
1
2
.
0
5
3
.
[
2
7
]
F
.
D
.
A
.
T.
D
e
C
a
r
v
a
l
h
o
,
Y
.
L
e
c
h
e
v
a
l
l
i
e
r
,
a
n
d
F
.
M
.
D
e
M
e
l
o
,
“
P
a
r
t
i
t
i
o
n
i
n
g
h
a
r
d
c
l
u
s
t
e
r
i
n
g
a
l
g
o
r
i
t
h
ms
b
a
sed
o
n
mu
l
t
i
p
l
e
d
i
ss
i
mi
l
a
r
i
t
y
m
a
t
r
i
c
e
s,
”
P
a
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
4
4
7
–
4
6
4
,
J
a
n
.
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
1
1
.
0
5
.
0
1
6
.
[
2
8
]
K
.
V
.
R
a
j
k
u
m
a
r
,
A
.
Y
e
s
u
b
a
b
u
,
a
n
d
K
.
S
u
b
r
a
h
m
a
n
y
a
m,
“
F
u
z
z
y
c
l
u
s
t
e
r
i
n
g
a
n
d
f
u
z
z
y
C
-
M
e
a
n
s
p
a
r
t
i
t
i
o
n
c
l
u
st
e
r
a
n
a
l
y
si
s
a
n
d
v
a
l
i
d
a
t
i
o
n
s
t
u
d
i
e
s
o
n
a
su
b
se
t
o
f
C
i
t
e
S
c
o
r
e
d
a
t
a
se
t
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
2
7
6
0
–
2
7
7
0
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
9
i
4
.
p
p
2
7
6
0
-
2
7
7
0
.
[
2
9
]
H
.
W
a
n
g
,
Y
.
Y
a
n
g
,
a
n
d
B
.
L
i
u
,
“
G
M
C
:
g
r
a
p
h
-
b
a
se
d
mu
l
t
i
-
v
i
e
w
c
l
u
s
t
e
r
i
n
g
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
2
,
n
o
.
6
,
p
p
.
1
1
1
6
–
1
1
2
9
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E
.
2
0
1
9
.
2
9
0
3
8
1
0
.
[
3
0
]
R
.
P
.
D
e
G
u
sm
ã
o
a
n
d
F
.
D
.
A
.
T.
D
e
C
a
r
v
a
l
h
o
,
“
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
a
p
p
l
i
e
d
t
o
r
e
l
a
t
i
o
n
a
l
d
a
t
a
c
l
u
st
e
r
i
n
g
,
”
i
n
2
0
1
6
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
y
st
e
m
s,
M
a
n
,
a
n
d
C
y
b
e
rn
e
t
i
c
s,
S
M
C
2
0
1
6
-
C
o
n
f
e
re
n
c
e
Pro
c
e
e
d
i
n
g
s
,
O
c
t
.
2
0
1
7
,
p
p
.
1
6
9
0
–
1
6
9
5
,
d
o
i
:
1
0
.
1
1
0
9
/
S
M
C
.
2
0
1
6
.
7
8
4
4
4
8
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
o
a
n
g
Th
i
C
a
n
h
is
a
re
se
a
rc
h
e
r
a
n
d
P
h
.
D
.
st
u
d
e
n
t
a
t
th
e
G
ra
d
u
a
te
Un
i
v
e
rsity
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
Vie
t
n
a
m
Ac
a
d
e
m
y
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
.
S
h
e
re
c
e
iv
e
d
a
b
a
c
h
e
lo
r'
s
in
i
n
fo
rm
a
ti
o
n
tec
h
n
o
lo
g
y
a
t
T
h
a
i
Ng
u
y
e
n
U
n
iv
e
rsit
y
(ICTU),
Vie
tn
a
m
in
2
0
0
9
.
S
h
e
g
o
t
a
m
a
ste
r'
s
d
e
g
re
e
o
n
c
o
m
p
u
ter
sc
ien
c
e
a
t
ICTU
in
2
0
1
2
.
H
e
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
d
a
ta m
in
in
g
,
so
ft
c
o
m
p
u
ti
n
g
,
a
n
d
fu
z
z
y
c
o
m
p
u
ti
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
tca
n
h
@ic
tu
.
e
d
u
.
v
n
.
Ph
a
m
H
u
y
Th
o
n
g
r
e
c
e
i
v
e
d
t
h
e
P
h
.
D
.
d
e
g
r
e
e
i
n
m
a
t
h
e
m
a
t
i
c
s
a
n
d
i
n
f
o
r
m
a
t
i
c
f
r
o
m
V
N
U
U
n
i
v
e
r
s
i
t
y
o
f
S
c
i
e
n
c
e
,
V
i
e
t
n
a
m
N
a
t
i
o
n
a
l
U
n
i
v
e
r
s
i
t
y
,
H
a
n
o
i
,
i
n
2
0
2
0
.
H
e
i
s
c
u
r
r
e
n
t
l
y
a
t
e
a
c
h
e
r
a
n
d
r
e
s
e
a
r
c
h
e
r
o
f
H
a
n
o
i
U
n
i
v
e
r
s
i
t
y
o
f
I
n
d
u
s
t
r
y
.
H
i
s
r
e
s
e
a
r
c
h
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
d
a
t
a
m
i
n
i
n
g
,
s
o
f
t
c
o
m
p
u
t
i
n
g
,
a
n
d
f
u
z
z
y
c
o
m
p
u
t
i
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
t
h
o
n
g
p
h
@
h
a
u
i.
e
d
u
.
v
n
.
Ph
u
n
g
Th
e
H
u
a
n
r
e
c
e
i
v
e
d
th
e
P
h
.
D
.
d
e
g
re
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
t
Un
iv
e
rsity
o
f
In
fo
rm
a
ti
o
n
a
n
d
C
o
m
m
u
n
ica
ti
o
n
Tec
h
n
o
l
o
g
y
,
Th
a
i
Ng
u
y
e
n
Un
iv
e
rsity
(ICTU)
in
2
0
2
3
.
He
re
c
e
iv
e
d
a
b
a
c
h
e
lo
r’s
in
i
n
fo
rm
a
t
io
n
tec
h
n
o
l
o
g
y
a
t
ICTU,
Vie
tn
a
m
in
2
0
0
9
.
He
g
o
t
a
m
a
ste
r'
s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
t
ICTU
in
2
0
1
2
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
g
e
o
g
ra
p
h
ic
in
fo
rm
a
ti
o
n
sy
ste
m
s,
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
d
a
ta
m
i
n
in
g
,
s
o
ft
c
o
m
p
u
ti
n
g
,
a
n
d
fu
z
z
y
c
o
m
p
u
t
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
th
u
a
n
@ic
tu
.
e
d
u
.
v
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.