I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
5
,
Octo
b
er
2
0
2
0
,
p
p
.
5
4
5
3
~
5
4
6
1
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
0
i
5
.
pp
5
4
5
3
-
5
4
6
1
5453
Jou
r
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
Fra
m
ew
o
rk
for
o
pinio
n as
a
s
ervi
c
e on
r
ev
iew
d
a
ta o
f
c
usto
m
er
using
s
e
m
a
n
tics
b
a
sed
a
na
ly
tics
Ra
j
esh
w
a
ri
D
.
1
,
Va
g
dev
i S
.
2
1
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
V
isv
e
sv
a
ra
y
a
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsity
(V
T
U
-
RRC
),
In
d
ia
2
De
p
a
rtme
n
t
o
f
I
n
f
o
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
,
Da
y
a
n
a
n
d
a
S
a
g
a
r
A
c
a
d
e
m
y
o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t
(
DSAT
M
)
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
9
,
2
0
1
9
R
ev
i
s
ed
A
p
r
1
3
,
2
0
2
0
A
cc
ep
ted
A
p
r
2
3
,
2
0
2
0
A
t
o
p
in
io
n
m
in
in
g
p
lay
s
a
sig
n
if
ica
n
t
ro
le
in
re
p
re
se
n
ti
n
g
th
e
o
r
ig
in
a
l
a
n
d
u
n
b
ias
e
d
p
e
rc
e
p
ti
o
n
o
f
th
e
p
ro
d
u
c
ts/se
rv
ice
s.
Ho
w
e
v
e
r,
th
e
re
a
re
v
a
rio
u
s
c
h
a
ll
e
n
g
e
s
a
s
so
c
iate
d
w
it
h
p
e
rf
o
r
m
in
g
a
n
e
ffe
c
ti
v
e
o
p
in
io
n
m
in
in
g
in
th
e
p
re
se
n
t
e
ra
o
f
d
istri
b
u
te
d
c
o
m
p
u
ti
n
g
sy
st
e
m
w
it
h
d
y
n
a
m
ic
b
e
h
a
v
io
u
r
o
f
u
se
rs.
Ex
isti
n
g
a
p
p
r
o
a
c
h
e
s
is
m
o
re
lab
o
ri
o
u
s
t
o
w
a
rd
s
e
x
trac
ti
n
g
k
n
o
w
led
g
e
f
ro
m
th
e
re
v
ie
ws
o
f
u
se
r
w
h
ich
is
f
u
rth
e
r
su
b
jec
ted
t
o
v
a
rio
u
s
ro
u
n
d
s
o
f
o
p
e
ra
ti
o
n
w
it
h
c
o
m
p
lex
p
ro
c
e
d
u
re
s.
T
h
e
p
ro
p
o
se
d
sy
st
e
m
a
d
d
re
ss
e
s
th
e
p
r
o
b
lem
b
y
in
tro
d
u
c
in
g
a
n
o
v
e
l
f
ra
m
e
w
o
rk
c
a
ll
e
d
a
s
o
p
in
i
o
n
-
as
-
a
-
se
rv
i
c
e
w
h
ich
is
m
e
a
n
t
f
o
r
d
irec
t
u
ti
li
z
a
ti
o
n
o
f
th
e
e
x
trac
ted
k
n
o
w
led
g
e
in
m
o
st
u
se
r
f
rien
d
ly
m
a
n
n
e
r.
T
h
e
p
r
o
p
o
se
d
s
y
ste
m
in
tro
d
u
c
e
s
a
se
t
o
f
th
re
e
se
q
u
e
n
t
ial
a
lg
o
rit
h
m
th
a
t
p
e
rf
o
rm
s
a
g
g
re
g
a
ted
o
f
in
c
o
m
in
g
str
e
a
m
o
f
o
p
in
io
n
d
a
ta,
p
e
rf
o
r
m
in
g
in
d
e
x
in
g
,
f
o
ll
o
w
e
d
b
y
a
p
p
ly
in
g
s
e
m
a
n
ti
c
s
f
o
r
e
x
trac
ti
n
g
k
n
o
w
led
g
e
.
T
h
e
stu
d
y
o
u
tco
m
e
sh
o
w
s
th
a
t
p
ro
p
o
se
d
sy
ste
m
is
b
e
tt
e
r
th
a
n
e
x
isti
n
g
s
y
ste
m
in
m
in
in
g
p
e
rf
o
rm
a
n
c
e
.
K
ey
w
o
r
d
s
:
An
al
y
tics
B
ig
d
ata
C
lo
u
d
Kn
o
w
led
g
e
Op
in
io
n
m
i
n
in
g
Co
p
y
rig
h
t
©
2
0
2
0
I
n
stit
u
te o
f
Ad
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
aj
esh
w
ar
i
D
.,
Dep
ar
t
m
en
t
o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
,
Vis
v
e
s
v
ar
a
y
a
T
ec
h
n
o
lo
g
ical
Un
i
v
er
s
it
y
(
VT
U
-
R
R
C
),
Kar
n
atak
a
,
I
n
d
ia
.
E
m
ail:
r
aj
esh
w
ar
id
r
esear
ch
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
W
ith
t
h
e
i
n
cr
ea
s
i
n
g
co
m
p
et
iti
v
e
w
o
r
ld
o
f
co
m
m
er
cial
m
ar
k
et,
it
i
s
e
s
s
e
n
tial
to
m
ain
tain
m
ax
i
m
u
m
co
m
p
eti
tiv
e
p
r
o
d
u
cts
o
r
s
er
v
ices
i
n
t
h
e
m
ar
k
et.
C
u
s
to
m
e
r
o
p
in
io
n
is
o
n
e
s
u
c
h
m
ec
h
an
is
m
to
d
ir
ec
tl
y
u
n
d
er
s
ta
n
d
t
h
e
p
er
s
o
n
al
ized
o
p
in
io
n
a
s
s
o
ciate
d
w
i
th
e
v
er
y
p
r
o
d
u
cts/
s
er
v
ice
s
[
1
]
.
Gen
er
all
y
,
s
u
c
h
o
p
in
io
n
s
ar
e
al
w
a
y
s
in
th
e
f
o
r
m
o
f
te
x
t
i
n
a
d
ef
in
ed
f
ield
.
I
n
t
h
i
s
r
eg
ar
d
s
,
o
p
in
io
n
m
in
i
n
g
p
la
y
s
a
cr
itic
al
r
o
le
as
tar
g
ets
to
s
o
lv
e
th
e
is
s
u
e
co
n
n
ec
ted
w
i
t
h
t
h
e
v
ar
ied
o
p
in
io
n
i
n
o
r
d
er
to
en
h
a
n
ce
t
h
e
s
er
v
ice
o
f
f
er
s
t
h
at
in
tu
r
n
w
ill
p
o
s
itiv
el
y
a
f
f
ec
t
s
er
v
ice
q
u
al
it
y
[
2
]
.
I
t
is
also
s
ee
n
t
h
at
o
p
in
io
n
m
i
n
i
n
g
,
e
m
o
tio
n
a
n
al
y
s
i
s
,
an
d
s
e
n
ti
m
e
n
t
an
al
y
s
is
ar
e
in
ter
c
h
an
g
ea
b
l
y
u
s
ed
in
m
a
n
y
s
t
u
d
i
es
[
3
]
.
T
h
e
co
n
ce
p
t
o
f
s
en
ti
m
e
n
t
an
al
y
s
i
s
h
as
a
d
is
ti
n
ct
d
if
f
er
e
n
ce
as c
o
m
p
ar
ed
to
o
p
in
io
n
m
i
n
i
n
g
.
Se
n
ti
m
en
t a
n
a
l
y
s
is
d
ea
ls
w
it
h
i
n
v
e
s
ti
g
ati
n
g
th
e
f
ee
li
n
g
o
r
e
m
o
tio
n
o
f
th
e
u
s
er
f
o
r
a
d
ef
in
ed
p
r
o
d
u
ct
o
r
s
er
v
ices
w
h
ile
th
e
o
u
tco
m
es
ar
e
n
o
r
m
all
y
b
in
ar
ized
i
.
e.
p
o
s
itiv
e
o
r
n
eg
at
iv
e
[
4
]
.
B
u
t
o
p
in
io
n
m
i
n
in
g
is
a
ll
ab
o
u
t
in
v
est
ig
at
in
g
t
h
e
d
ep
th
lev
e
l
to
e
x
tr
ac
t
t
h
e
f
ac
to
r
s
t
h
at
ar
e
r
esp
o
n
s
ib
le
f
o
r
t
h
e
f
ee
lin
g
s
o
r
th
e
e
m
o
tio
n
o
f
th
e
u
s
er
f
o
r
a
d
ef
in
ed
p
r
o
d
u
ct
/s
er
v
ices.
Se
n
ti
m
e
n
t
a
n
al
y
s
is
ca
n
b
e
also
co
n
s
id
er
ed
a
s
a
n
e
x
ten
s
io
n
o
f
k
n
o
w
led
g
e
d
is
co
v
er
y
p
r
o
ce
s
s
an
d
it
u
s
e
s
co
m
p
u
tatio
n
al
li
n
g
u
i
s
tic
-
b
ased
m
et
h
o
d
s
f
o
r
o
b
tain
in
g
t
h
e
o
p
in
io
n
o
f
t
h
e
u
s
er
[
5
]
.
T
h
e
ess
en
tial
i
n
f
o
r
m
atio
n
th
a
t
ar
e
u
s
ed
in
o
p
in
io
n
m
i
n
i
n
g
is
o
b
tain
ed
f
r
o
m
d
if
f
er
e
n
t
s
o
u
r
ce
s
e.
g
.
b
lo
g
s
,
n
e
w
s
w
eb
s
i
te
s
,
s
o
cia
l
n
et
w
o
r
k
s
,
r
ev
ie
w
-
b
ased
s
i
tes,
etc.
in
ac
co
r
d
an
ce
w
it
h
th
e
p
o
lar
it
y
[
6
]
.
Ho
w
e
v
er
th
e
class
i
f
icat
io
n
o
f
th
e
p
o
lar
ity
i
s
ca
r
r
ied
o
u
t
u
s
in
g
p
o
s
it
iv
e
o
r
n
e
g
ati
v
e
o
r
n
e
u
tr
al
s
co
r
e.
A
t
th
e
s
a
m
e
ti
m
e,
it
is
f
ea
s
i
b
le
th
at
t
h
e
n
at
u
r
e
o
f
t
h
e
te
x
t
co
u
ld
b
e
eit
h
er
s
u
b
j
ec
tiv
e
o
r
it
co
u
ld
b
e
also
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
4
5
3
-
5461
5454
o
b
j
ec
tiv
e.
A
s
o
p
in
io
n
m
i
n
in
g
is
g
ai
n
i
n
g
i
m
p
o
r
ta
n
ce
i
n
ex
is
t
in
g
s
y
s
te
m
,
th
er
e
f
o
r
e,
it
is
i
m
p
er
ativ
e
to
e
m
p
h
a
s
ize
o
v
er
th
e
i
n
h
er
e
n
t
ch
alle
n
g
e
s
in
t
h
i
s
ar
ea
.
T
h
e
f
ir
s
t
c
h
alle
n
g
e
i
n
o
p
in
io
n
m
i
n
in
g
i
s
to
m
an
a
g
e
th
e
le
v
e
l
o
f
s
p
ec
i
f
icatio
n
in
te
g
r
it
y
w
h
ic
h
is
b
ec
a
u
s
e
o
f
p
r
e
s
en
ce
o
f
v
ar
io
u
s
s
p
a
m
m
e
s
s
a
g
es,
o
p
in
io
n
f
r
o
m
n
o
n
-
ex
p
er
t,
b
ias
o
p
in
io
n
,
cr
e
d
ib
ilit
y
o
f
o
p
in
io
n
,
g
ap
b
et
wee
n
o
p
in
io
n
to
p
ic
an
d
k
e
y
w
o
r
d
u
s
ed
to
s
ea
r
c
h
it,
t
y
p
o
g
r
ap
h
ical
er
r
o
r
s
,
ir
r
elev
an
c
y
o
f
o
p
in
io
n
,
an
d
d
ep
en
d
en
c
y
o
f
d
o
m
a
in
u
n
d
er
s
en
ti
m
en
t
an
a
l
y
s
is
.
T
h
e
s
ec
o
n
d
ch
alle
n
g
e
i
n
o
p
in
io
n
m
i
n
i
n
g
is
co
n
n
ec
ted
w
i
th
th
e
le
v
el
o
f
w
o
r
d
u
s
ed
w
h
er
e
th
e
p
r
o
b
le
m
s
ar
e
m
ai
n
l
y
r
elate
d
to
th
e
ab
s
en
c
e
o
f
co
n
tex
tu
a
l
in
f
o
r
m
atio
n
,
is
s
u
e
s
o
f
w
o
r
d
o
r
ien
tatio
n
,
u
s
a
g
e
o
f
v
er
b
an
d
ad
j
ec
tiv
e
in
th
e
f
o
r
m
o
f
o
p
in
io
n
w
o
r
d
s
,
an
d
ad
o
p
tio
n
o
f
o
r
th
o
g
o
n
al
w
o
r
d
s
.
T
h
e
th
ir
d
ch
alle
n
g
e
i
n
o
p
in
io
n
m
i
n
in
g
i
s
as
s
o
ciate
d
w
ith
lev
el
o
f
lan
g
u
ag
e
o
r
s
e
n
te
n
ce
s
w
h
ic
h
is
m
ai
n
l
y
ca
u
s
ed
d
u
e
t
o
u
s
ag
e
o
f
d
if
f
er
e
n
t
lin
g
u
i
s
tic,
u
s
a
g
e
o
f
m
u
ltip
le
w
r
i
tin
g
s
t
y
les,
r
e
s
tr
ictio
n
o
f
f
ilter
in
g
c
lass
if
ica
tio
n
,
p
r
o
d
u
ct
o
p
in
io
n
etc.
T
h
er
e
ar
e
m
an
y
ex
i
s
ti
n
g
to
o
l
s
to
ca
r
r
y
o
u
t
o
p
in
io
n
m
i
n
i
n
g
e.
g
.
Op
in
io
n
Ob
s
er
v
er
,
Op
i
n
i
o
n
Fi
n
d
er
,
Nat
u
r
al
L
a
n
g
u
a
g
e
T
o
o
lk
it,
A
p
ac
h
e
Op
en
N
L
P
,
L
i
n
g
P
ip
e,
W
eb
Fo
u
n
ta
in
,
R
e
v
ie
w
Seer
T
o
o
l,
etc.
[
7
,
8
]
.
Th
er
e
is
n
o
d
o
u
b
t
o
f
m
an
y
n
u
m
b
er
o
f
d
ed
icate
d
r
esear
ch
wo
r
k
b
ein
g
ca
r
r
ied
o
u
t
to
w
ar
d
s
en
h
a
n
ci
n
g
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
o
p
in
io
n
m
i
n
in
g
[
9
,
1
0
]
,
h
o
w
ev
er
,
t
h
e
y
ar
e
m
ai
n
l
y
lo
ca
lized
to
p
er
f
o
r
m
a
co
m
p
licated
m
i
n
in
g
o
p
er
atio
n
o
v
er
a
s
tatic
d
ata.
W
ith
th
e
ev
o
lu
tio
n
o
f
clo
u
d
co
m
p
u
tin
g
an
d
s
er
v
ices
o
f
f
er
ed
b
y
it,
th
e
s
ca
le
a
n
d
s
ize
o
f
t
h
e
o
p
in
io
n
d
ata
i
s
e
x
p
o
n
en
tiall
y
i
n
cr
ea
s
i
n
g
.
T
h
is
g
e
n
er
ates
a
h
ig
h
l
y
u
n
s
tr
u
ct
u
r
ed
o
p
in
io
n
d
ata
t
h
at
is
q
u
ite
c
h
allen
g
in
g
to
p
er
f
o
r
m
m
a
n
y
f
u
r
th
er
p
r
o
ce
s
s
i
n
g
a
n
d
t
h
e
y
c
an
n
o
t
b
e
s
to
r
ed
in
co
n
v
e
n
tio
n
al
s
to
r
ag
e
u
n
its
to
o
.
T
h
er
ef
o
r
e,
th
e
co
n
tr
ib
u
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
i
s
to
p
r
esen
t
a
f
r
a
m
e
w
o
r
k
th
at
ca
n
p
er
f
o
r
m
a
n
o
v
el
o
p
in
io
n
m
i
n
in
g
s
u
c
h
th
at
it
s
o
u
t
p
u
t
o
f
ex
tr
ac
ted
k
n
o
w
led
g
e
c
o
u
ld
b
e
o
f
f
er
ed
as
s
er
v
ices.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
u
s
es
a
li
g
h
t
w
e
ig
h
t
d
esi
g
n
m
et
h
o
d
o
lo
g
ies
f
o
r
th
i
s
p
u
r
p
o
s
e
an
d
th
e
d
is
cu
s
s
io
n
h
as
b
ee
n
ca
r
r
ied
o
u
t
to
w
ar
d
s
it
.
T
h
e
o
r
g
an
izatio
n
o
f
t
h
e
p
ap
er
is
as
f
o
llo
w
s
:
Sectio
n
1
(
a)
d
is
cu
s
s
es
ab
o
u
t
th
e
ex
is
ti
n
g
liter
at
u
r
es
w
h
er
e
d
if
f
er
e
n
t
tec
h
n
iq
u
es
ar
e
d
is
cu
s
s
ed
f
o
r
d
etec
tio
n
s
ch
e
m
es
u
s
ed
i
n
p
o
w
e
r
tr
an
s
m
is
s
io
n
lin
e
s
f
o
llo
w
ed
b
y
d
is
c
u
s
s
io
n
o
f
r
esear
ch
p
r
o
b
le
m
s
i
n
Sectio
n
1
(
b
)
an
d
p
r
o
p
o
s
ed
s
o
lu
tio
n
i
n
1
(
c)
.
Sectio
n
2
d
is
cu
s
s
es
ab
o
u
t
alg
o
r
ith
m
i
m
p
le
m
e
n
tat
io
n
f
o
llo
wed
b
y
d
is
cu
s
s
io
n
o
f
r
esu
lt
a
n
a
l
y
s
i
s
in
Sect
io
n
3
.
Fin
all
y
,
t
h
e
co
n
cl
u
s
i
v
e
r
e
m
ar
k
s
ar
e
p
r
o
v
id
ed
in
Sectio
n
4
.
a.
B
ac
k
g
r
o
u
n
d
T
h
is
s
ec
tio
n
d
is
cu
s
s
e
s
ab
o
u
t
th
e
r
ec
en
t
w
o
r
k
b
ei
n
g
ca
r
r
ied
o
u
t
to
w
ar
d
s
s
e
n
ti
m
en
t
an
al
y
s
i
s
o
v
er
th
e
o
p
in
io
n
o
f
v
ar
ied
f
o
r
m
s
u
s
i
n
g
d
i
f
f
er
e
n
t
ap
p
r
o
ac
h
es.
Stu
d
y
to
w
ar
d
s
o
p
in
io
n
m
in
in
g
o
v
er
t
h
e
s
o
cia
l
n
et
w
o
r
k
is
ca
r
r
ied
o
u
t
b
y
R
i
q
u
el
m
e
et
al.
[
1
1
]
.
E
x
is
tin
g
s
y
s
te
m
w
as
al
s
o
r
ec
o
r
d
ed
to
u
s
e
o
n
to
lo
g
y
-
b
a
s
ed
ap
p
r
o
ac
h
f
o
r
ca
r
r
y
in
g
o
u
t
o
p
i
n
io
n
m
in
i
n
g
a
s
s
ee
n
in
th
e
w
o
r
k
o
f
Sid
d
iq
u
i
et
al.
[
1
2
]
.
T
h
e
s
tu
d
y
h
as
a
ls
o
u
s
ed
s
e
m
a
n
tic
s
u
s
in
g
m
at
h
e
m
atica
l
m
o
d
elin
g
to
w
ar
d
s
f
ac
ilit
ati
n
g
f
ea
t
u
r
e
en
g
in
ee
r
i
n
g
.
Stu
d
y
to
w
ar
d
s
s
e
n
ti
m
en
t
an
al
y
s
is
w
as c
ar
r
ied
o
u
t th
e
X
u
et
al.
[
1
3
]
w
h
er
e
m
e
m
o
r
y
-
b
a
s
ed
ap
p
r
o
ac
h
is
u
s
ed
alo
n
g
w
it
h
th
e
cla
s
s
i
f
icat
io
n
ap
p
r
o
ac
h
o
f
n
eu
r
al
n
et
w
o
r
k
.
Si
m
i
lar
n
e
u
r
al
-
n
et
w
o
r
k
b
a
s
ed
ap
p
r
o
ac
h
w
as
a
l
s
o
i
m
p
le
m
en
ted
in
th
e
s
t
u
d
y
of
Yu
et
al.
[
1
4
]
w
h
o
h
a
v
e
ca
r
r
ied
o
u
t
ex
tr
ac
tio
n
o
f
o
p
in
io
n
ter
m
s
w
i
th
a
n
o
b
j
ec
tiv
e
to
f
in
d
c
o
r
r
elatio
n
b
et
w
ee
n
d
if
f
er
e
n
t ta
s
k
s
.
T
h
e
w
o
r
k
o
f
Hu
y
n
h
et
al.
[
1
5
]
h
av
e
u
s
ed
b
ig
d
ata
ap
p
r
o
ac
h
an
d
co
n
v
o
l
u
tio
n
n
e
u
r
al
n
e
t
w
o
r
k
o
v
er
o
p
in
io
n
m
i
n
i
n
g
f
r
o
m
s
o
cial
n
et
w
o
r
k
u
s
i
n
g
Viet
n
a
m
ese
la
n
g
u
ag
e.
T
h
e
w
o
r
k
o
f
He
et
al.
[
1
6
]
h
as
u
s
ed
b
in
ar
y
m
ec
h
a
n
i
s
m
f
o
r
clas
s
i
f
y
i
n
g
o
p
in
io
n
f
r
o
m
o
n
li
n
e
n
et
w
o
r
k
in
o
r
d
er
to
i
d
en
tify
p
o
ten
tial
n
o
d
e.
C
lass
i
f
icatio
n
p
r
o
b
lem
s
a
s
s
o
ciate
d
w
i
th
o
p
in
io
n
f
r
o
m
s
o
cial
n
et
w
o
r
k
w
a
s
i
n
v
esti
g
ated
b
y
Fe
r
n
an
d
es
et
a
l.
[
1
7
]
.
C
o
n
s
id
er
atio
n
o
f
m
etad
ata
co
u
ld
f
u
r
th
er
en
r
ic
h
t
h
e
an
al
y
s
i
s
p
r
o
ce
s
s
t
h
at
is
p
r
o
v
e
n
in
th
e
w
o
r
k
o
f
Kr
en
et
al.
[
1
8
]
w
h
er
e
o
p
in
io
n
ar
e
ex
tr
ac
ted
f
r
o
m
th
e
m
u
lti
m
ed
ia
co
n
ten
t
w
h
er
e
f
i
v
e
d
if
f
er
en
t
class
if
icatio
n
is
ca
r
r
ied
o
u
t
o
v
er
th
e
d
at
a.
A
s
p
ec
if
ic
f
o
cu
s
o
v
er
i
n
f
lu
e
n
tia
l
n
o
d
e
an
d
it
s
p
o
s
s
ib
le
co
n
n
ec
t
io
n
w
it
h
t
h
e
s
o
cial
n
et
w
o
r
k
i
s
ca
r
r
ied
o
u
t
b
y
Mo
h
a
m
m
ad
i
n
ej
ad
et
al.
[
1
9
]
.
T
h
e
s
tu
d
y
h
a
s
al
s
o
u
s
ed
co
n
s
e
n
s
u
s
f
ac
to
r
f
o
r
b
etter
m
o
d
eli
n
g
p
er
s
p
ec
tiv
e.
T
h
e
w
o
r
k
o
f
Mu
ll
ick
et
al.
[
2
0
]
p
r
esen
ts
a
tec
h
n
iq
u
e
to
e
x
tr
ac
t
p
ar
ticu
lar
f
ea
tu
r
e
f
r
o
m
th
e
s
o
cia
l
n
et
w
o
r
k
u
s
in
g
lear
n
in
g
-
b
ased
tech
n
iq
u
e.
U
s
ag
e
o
f
g
en
e
tic
al
g
o
r
ith
m
w
a
s
s
ee
n
i
n
t
h
e
w
o
r
k
o
f
I
q
b
al
et
al.
[
2
1
]
w
h
er
e
t
h
e
f
o
cu
s
w
a
s
o
v
er
r
ed
u
ctio
n
o
f
th
e
f
ea
tu
r
e.
A
d
is
cr
ete
m
o
d
el
w
a
s
co
n
s
tr
u
cted
f
o
r
c
o
m
p
u
ti
n
g
s
o
cial
o
p
in
io
n
b
y
W
u
et
al.
[
2
2
]
w
h
er
e
v
o
tin
g
-
b
ased
ap
p
r
o
ac
h
w
a
s
u
s
ed
f
o
r
p
er
f
o
r
m
i
n
g
p
r
ed
icti
v
e
m
i
n
i
n
g
an
al
y
s
i
s
.
T
h
e
w
o
r
k
o
f
Z
h
an
g
a
n
d
Z
h
o
n
g
[
2
3
]
h
as
ca
r
r
ied
o
u
t
m
in
i
n
g
o
f
th
e
tr
u
s
t
f
ac
to
r
co
n
n
ec
ted
w
it
h
t
w
o
in
d
i
v
id
u
a
l
u
s
i
n
g
s
e
n
ti
m
e
n
t
a
n
al
y
s
e
s
u
s
i
n
g
s
h
o
r
test
p
ath
.
As
k
ar
iSi
c
h
an
i
an
d
J
alili
[
2
4
]
h
av
e
i
n
v
e
s
ti
g
ated
o
v
er
co
m
p
le
x
n
et
w
o
r
k
f
o
r
f
o
r
m
u
lati
n
g
o
p
in
i
o
n
u
s
i
n
g
m
a
x
i
m
u
m
-
a
-
p
o
s
ter
io
r
i
p
r
o
ce
s
s
co
n
s
id
er
in
g
id
e
n
ti
f
i
ca
tio
n
o
f
in
f
l
u
e
n
tia
l
n
o
d
e.
L
v
et
al.
[
2
5
]
h
av
e
u
s
ed
Ma
r
k
o
v
m
o
d
eli
n
g
in
o
r
d
e
r
to
p
er
f
o
r
m
o
p
in
io
n
m
i
n
in
g
o
v
er
ess
e
n
tial
d
ata
r
eso
u
r
ce
s
.
T
h
e
s
tu
d
y
h
as
als
o
u
tili
ze
d
b
elief
p
r
o
p
ag
atio
n
alg
o
r
ith
m
f
o
r
t
h
i
s
p
u
r
p
o
s
e.
Z
u
o
et
a
l.
[
2
6
]
h
av
e
i
m
p
le
m
en
ted
asp
ec
t
-
b
ased
k
n
o
w
led
g
e
e
x
tr
ac
tio
n
p
r
o
ce
s
s
u
s
in
g
Dir
ic
h
let
p
r
o
ce
s
s
es
alo
n
g
w
it
h
t
h
e
in
v
o
lu
n
tar
y
in
d
ex
i
n
g
m
ec
h
a
n
is
m
f
o
r
d
if
f
er
en
tiati
n
g
m
u
ltip
le
o
p
in
io
n
s
.
Z
h
o
u
et
al.
[
2
7
]
h
av
e
co
n
s
id
er
e
d
lan
g
u
ag
e
s
p
ec
if
ic
o
p
in
io
n
m
i
n
i
n
g
ap
p
r
o
ac
h
w
h
e
r
e
a
co
-
r
an
k
in
g
al
g
o
r
ith
m
is
p
r
esen
ted
.
T
h
e
w
o
r
k
o
f
co
m
p
u
t
in
g
s
en
t
i
m
e
n
t
s
w
a
s
ca
r
r
ied
o
u
t
b
y
J
ia
n
g
e
t
al.
[
2
8
]
co
n
s
id
er
in
g
n
e
w
s
d
atase
t
f
r
o
m
s
o
cial
n
et
w
o
r
k
u
s
in
g
s
e
m
an
tics
.
A
d
o
p
tio
n
o
f
laten
t
d
ir
ic
h
let
a
llo
ca
tio
n
to
w
ar
d
s
s
en
ti
m
en
t
an
al
y
s
is
w
a
s
s
ee
n
i
n
w
o
r
k
o
f
Z
h
a
n
g
an
d
C
h
o
w
[
2
9
]
w
h
ile
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:
2
0
8
8
-
8708
F
r
a
mewo
r
k
fo
r
o
p
in
io
n
a
s
a
s
ervice
o
n
r
ev
iew
d
a
ta
o
f c
u
s
to
mer
…
(
R
a
jesh
w
a
r
i D
.
)
5455
co
n
s
id
er
atio
n
o
f
h
u
m
a
n
-
b
ase
d
in
ter
ac
tio
n
w
as
s
ee
n
i
n
w
o
r
k
o
f
C
la
v
el
a
n
d
C
allej
as
[
3
0
]
.
T
h
e
n
ex
t
s
ec
tio
n
b
r
ief
s
o
f
t
h
e
cu
m
u
lati
v
e
o
p
en
en
d
is
s
u
es i
n
ex
is
ti
n
g
ap
p
r
o
ac
h
es to
w
ar
d
s
o
p
in
io
n
m
i
n
i
n
g
.
b.
T
h
e
r
esear
ch
p
r
o
b
lem
T
h
e
s
ig
n
i
f
ica
n
t r
esear
c
h
p
r
o
b
l
e
m
s
ar
e
as
f
o
llo
w
s
:
-
E
x
is
ti
n
g
ap
p
r
o
ac
h
es
u
s
es
co
m
p
lex
m
i
n
i
n
g
ap
p
r
o
ac
h
w
h
ic
h
in
d
u
ce
s
d
ela
y
in
p
r
o
ce
s
s
i
n
g
th
a
t
ca
n
b
e
ap
p
lied
f
o
r
o
f
f
lin
e
a
n
al
y
s
i
s
an
d
n
o
t f
o
r
o
n
lin
e
a
n
al
y
s
is
.
-
T
h
e
p
r
o
b
lem
o
f
d
ata
tr
an
s
f
o
r
m
atio
n
t
h
at
is
es
s
en
tial
p
r
io
r
to
s
to
r
in
g
th
e
d
ata
o
v
er
clo
u
d
co
n
s
id
er
in
g
th
e
v
ar
io
u
s
f
ield
s
o
f
o
p
in
io
n
is
n
ev
er
co
n
s
id
er
ed
in
an
y
p
r
io
r
w
o
r
k
.
-
A
d
o
p
tio
n
o
f
m
ac
h
i
n
e
lea
r
n
i
n
g
ap
p
r
o
ac
h
to
w
ar
d
s
o
p
ti
m
iza
tio
n
h
a
s
h
ig
h
er
d
ep
en
d
en
cie
s
o
v
er
tr
ain
i
n
g
d
ata
w
h
ich
i
s
h
i
g
h
l
y
ti
m
e
co
n
s
u
m
in
g
i
n
th
e
p
r
o
ce
s
s
o
f
y
ield
i
n
g
o
u
tco
m
e
s
.
-
Ma
j
o
r
ity
o
f
t
h
e
ex
i
s
ti
n
g
m
i
n
in
g
ap
p
r
o
ac
h
ar
e
r
eso
u
r
ce
d
ep
en
d
en
t
an
d
n
o
t
m
u
ch
d
is
tr
ib
u
ted
w
h
er
e
ch
an
ce
s
to
ap
p
ly
a
n
ef
f
ec
ti
v
e
t
r
an
s
f
o
r
m
atio
n
tec
h
n
iq
u
e
i
s
ch
allen
g
in
g
.
T
h
e
r
e
f
o
r
e
,
th
e
p
r
o
b
l
em
s
ta
t
em
e
n
t
o
f
th
e
p
r
o
p
o
s
e
d
s
tu
d
y
c
an
b
e
s
t
a
t
e
d
as
“
D
ev
e
l
o
p
in
g
a
f
r
am
ew
o
r
k
t
o
w
a
r
d
s
c
o
s
t
e
f
f
e
ct
iv
e
m
in
in
g
o
f
t
h
e
o
p
in
io
n
d
ata
u
s
i
n
g
s
e
m
an
tic
-
b
ased
s
en
ti
m
en
t a
n
al
y
s
is
is
q
u
ite
a
ch
allen
g
in
g
w
o
r
k
”.
c.
T
h
e
p
r
o
p
o
s
ed
s
o
lu
tio
n
T
h
e
co
r
e
g
o
al
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
to
d
ev
elo
p
a
n
o
v
el
f
r
a
m
e
w
o
r
k
th
at
co
u
l
d
f
ac
ilit
ate
p
r
o
ce
s
s
in
g
t
h
e
u
n
s
tr
u
ct
u
r
ed
o
p
in
io
n
f
r
o
m
e
-
co
m
m
er
ce
a
p
p
licatio
n
in
o
r
d
er
to
ca
r
r
y
o
u
t
e
x
tr
ac
tio
n
o
f
k
n
o
w
led
g
e.
T
h
e
ex
tr
ac
ted
k
n
o
w
led
g
e
i
s
d
eliv
er
ed
i
n
th
e
f
o
r
m
o
f
s
er
v
ice
a
n
d
h
en
ce
th
e
f
r
a
m
e
w
o
r
k
is
co
i
n
ed
as
o
p
in
io
n
d
ata
as
a
Ser
v
ice.
T
h
e
s
ch
e
m
e
o
f
t
h
e
s
er
v
ice
as
p
er
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
d
iag
r
a
m
m
atica
ll
y
s
h
o
w
n
in
F
ig
u
r
e
1.
C
u
s
t
o
m
e
r
O
p
i
n
i
o
n
A
l
g
o
r
i
t
h
m
M
i
n
e
d
d
a
t
a
A
l
g
o
r
i
t
h
m
f
o
r
D
i
s
t
r
i
b
u
t
e
d
D
a
t
a
A
g
g
r
e
g
a
t
i
o
n
A
l
g
o
r
i
t
h
m
f
o
r
O
b
t
a
i
n
i
n
g
I
n
d
e
x
e
d
V
a
l
u
e
s
A
l
g
o
r
i
t
h
m
f
o
r
s
e
m
a
n
t
i
c
-
b
a
s
e
d
K
n
o
w
l
e
d
g
e
E
x
t
r
a
c
t
i
o
n
Fig
u
r
e
1
.
A
d
o
p
ted
s
ch
e
m
e
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
T
h
e
m
a
in
f
o
cu
s
o
f
th
e
i
m
p
le
m
en
tatio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
t
h
at
it
o
f
f
er
s
o
p
i
n
io
n
-
as
-
a
-
s
er
v
ice.
I
n
o
r
d
er
to
d
o
th
is
i
m
p
le
m
e
n
tatio
n
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
p
r
esen
ts
a
co
m
p
r
eh
e
n
s
iv
e
f
r
a
m
e
w
o
r
k
o
f
h
i
g
h
l
y
d
is
tr
ib
u
ted
s
c
h
e
m
e
w
h
er
e
m
u
ltip
l
e
f
o
r
m
s
o
f
u
n
s
tr
u
ctu
r
ed
d
ata
is
ag
g
r
eg
ated
u
n
lik
e
l
y
t
h
e
ex
is
ti
n
g
s
y
s
te
m
.
T
h
e
p
r
im
e
e
m
p
h
a
s
is
is
to
o
f
f
e
r
a
d
is
cr
ete
t
r
an
s
f
o
r
m
atio
n
o
f
th
e
u
n
s
tr
u
ct
u
r
ed
o
p
in
io
n
d
ata
an
d
m
ak
e
it
h
ig
h
l
y
s
tr
u
ct
u
r
ed
s
o
t
h
at
i
t
ca
n
b
e
e
f
f
ec
tiv
el
y
s
to
r
ed
in
t
h
e
d
i
s
tr
ib
u
t
ed
clo
u
d
s
to
r
ag
e
u
n
it
s
.
T
h
e
p
r
o
p
o
s
ed
s
ch
e
m
e
i
n
Fig
u
r
e
1
en
ab
les
ac
ce
p
tan
ce
o
f
d
if
f
er
en
t
t
y
p
e
s
o
f
o
p
in
io
n
d
ata
f
r
o
m
th
e
e
-
co
m
m
er
ce
ap
p
li
ca
tio
n
w
h
ic
h
ar
e
in
th
e
f
o
r
m
o
f
tex
t.
T
h
e
s
tu
d
y
co
n
s
id
er
s
t
h
at
t
h
er
e
ar
e
p
o
s
s
ib
ili
ties
o
f
m
a
s
s
i
v
e
n
u
m
b
er
o
f
o
p
i
n
io
n
i
n
lar
g
e
s
ca
le
f
r
o
m
d
is
tr
ib
u
ted
s
y
s
te
m
w
h
ic
h
is
n
o
t
f
ea
s
ib
le
to
b
e
s
to
r
ed
in
clo
u
d
u
n
its
e
f
f
ec
t
iv
el
y
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
e
d
s
y
s
te
m
u
t
ilizes
a
n
o
v
el
i
n
d
ex
in
g
m
ec
h
an
is
m
w
h
ic
h
is
u
s
ed
to
co
n
s
tr
u
ct
a
n
d
r
etai
n
a
d
ef
in
i
te
m
etad
ata
of
th
e
in
co
m
i
n
g
s
tr
ea
m
o
f
d
ata.
A
ll
t
h
e
in
c
o
m
i
n
g
s
tr
ea
m
o
f
t
h
e
d
ata
is
m
ai
n
tai
n
ed
in
th
e
f
o
r
m
o
f
te
m
p
o
r
ar
y
b
u
f
f
er
w
h
er
e
th
e
s
a
m
p
le
s
o
f
th
e
s
tr
ea
m
ar
e
f
o
r
w
ar
d
ed
to
th
e
alg
o
r
it
h
m
o
v
er
clo
u
d
in
o
r
d
er
to
c
o
n
s
tr
u
ct
a
p
r
o
g
r
ess
iv
e
tr
an
s
f
o
r
m
ed
d
ata.
T
h
e
alg
o
r
ith
m
r
u
n
n
in
g
o
v
er
th
e
clo
u
d
clu
s
ter
s
ar
e
d
ev
elo
p
ed
in
o
r
d
er
to
ca
r
r
y
o
u
t
f
o
llo
w
i
n
g
o
p
er
atio
n
s
eq
u
en
tiall
y
v
iz.
i)
th
e
alg
o
r
i
th
m
i
n
it
iall
y
p
er
f
o
r
m
a
g
g
r
e
g
atio
n
o
f
d
is
tr
ib
u
ted
d
ata
w
it
h
p
r
im
ar
y
i
n
d
ex
i
n
g
,
ii)
th
e
al
g
o
r
ith
m
e
x
tr
ac
ts
all
t
h
e
i
n
d
ex
ed
v
al
u
es
f
r
o
m
t
h
e
i
n
co
m
in
g
d
ata
in
d
e
x
i
n
th
e
f
o
r
m
o
f
f
ile
o
b
j
ec
ts
w
ith
m
u
ltip
le
attr
ib
u
tes,
an
d
iii)
th
e
alg
o
r
it
h
m
al
s
o
ap
p
lies
a
s
e
m
an
tic
-
b
a
s
ed
ap
p
r
o
ac
h
in
o
r
d
e
r
to
p
er
f
o
r
m
a
co
r
r
elatio
n
-
b
ased
ex
tr
ac
tio
n
o
f
t
h
e
m
in
ed
d
ata
in
t
h
e
f
o
r
m
o
f
k
n
o
w
led
g
e.
On
e
o
f
th
e
i
n
ter
esti
n
g
co
n
tr
ib
u
tio
n
s
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
is
th
a
t
i
t
o
f
f
er
s
a
u
s
er
-
f
r
i
en
d
l
y
d
eli
v
er
y
o
f
t
h
e
k
n
o
w
led
g
e
f
r
o
m
t
h
e
m
i
n
ed
o
p
in
io
n
.
A
n
o
t
h
er
ess
e
n
tial
co
n
tr
ib
u
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
t
u
d
y
is
t
h
at
it
d
o
es
n
’
t
s
to
r
e
u
p
th
e
r
a
w
d
ata
o
f
o
p
in
io
n
tex
t
b
u
t
it
r
etai
n
s
o
n
l
y
t
h
e
m
in
ed
in
f
o
r
m
a
tio
n
.
A
ll
th
e
p
r
o
ce
s
s
ed
an
d
in
ter
m
ed
iat
e
d
ata
ar
e
s
to
r
ed
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
4
5
3
-
5461
5456
a
te
m
p
o
r
ar
y
b
u
f
f
er
s
y
s
te
m
w
h
ich
i
s
r
elea
s
ed
f
r
o
m
its
m
e
m
o
r
y
o
n
ce
t
h
e
f
i
n
al
o
u
tco
m
e
in
t
er
m
s
o
f
k
n
o
w
led
g
e
is
r
elea
s
ed
to
t
h
e
u
s
er
as
th
e
r
esp
o
n
s
e
o
f
q
u
er
y
g
e
n
er
ated
b
y
th
e
u
s
er
.
T
h
e
n
ex
t
s
ec
t
io
n
d
is
c
u
s
s
es
ab
o
u
t
th
e
s
y
s
te
m
d
esi
g
n
in
v
o
lv
ed
i
n
th
e
p
r
o
p
o
s
ed
s
tu
d
y
.
2.
SYST
E
M
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
e
co
r
e
ag
en
d
a
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
to
d
esig
n
an
d
d
ev
elo
p
a
m
ec
h
a
n
is
m
t
h
at
is
c
ap
ab
le
o
f
ex
tr
ac
ti
n
g
t
h
e
k
n
o
w
led
g
e
f
r
o
m
t
h
e
o
n
li
n
e
lo
g
f
ile
s
o
f
th
e
c
u
s
to
m
er
o
p
in
io
n
.
T
h
e
i
m
p
le
m
en
ta
tio
n
o
f
th
e
p
r
o
p
o
s
ed
an
al
y
tical
o
p
er
atio
n
is
ca
r
r
ied
o
u
t
u
s
in
g
a
n
o
v
el
s
e
m
a
n
tic
-
b
ased
co
n
ce
p
t
o
v
er
th
e
o
p
in
io
n
d
ata.
T
h
is
s
ec
tio
n
o
v
er
v
ie
w
s
d
if
f
e
r
en
t
ess
e
n
tia
l
in
f
o
r
m
at
io
n
as
s
o
ciate
d
w
i
th
t
h
e
s
y
s
te
m
i
m
p
le
m
en
ta
tio
n
w
i
t
h
r
esp
ec
t to
ass
u
m
p
tio
n
-
d
ep
en
d
en
cies,
i
m
p
le
m
en
tat
io
n
s
t
r
ate
g
y
,
an
d
ex
ec
u
tio
n
f
lo
w
.
2
.
1
.
Ass
u
m
ptio
n a
nd
de
pen
denci
es
T
h
e
p
r
im
ar
y
ass
u
m
p
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
th
at
t
h
er
e
is
a
d
e
d
icate
d
en
ter
p
r
is
e
ap
p
licatio
n
th
at
co
u
ld
p
u
l
l
o
u
t
t
h
e
cu
s
to
m
er
o
p
in
io
n
d
ata
f
r
o
m
d
if
f
er
e
n
t
elec
tr
o
n
ic
co
m
m
er
ce
p
o
r
tals
/ap
p
lic
atio
n
s
f
r
o
m
a
s
p
ec
if
ic
r
eg
io
n
o
f
cu
s
to
m
er
o
p
in
io
n
a
n
d
n
o
t
a
ll
t
h
e
d
ata.
T
h
e
s
ec
o
n
d
ar
y
a
s
s
u
m
p
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
t
h
at
all
t
h
e
c
u
s
to
m
er
o
p
in
io
n
d
ata
co
u
ld
b
e
r
elate
d
to
d
if
f
er
en
t
co
m
m
er
cial
d
o
m
ai
n
co
n
n
ec
ted
w
it
h
v
ar
ied
p
r
o
d
u
ct
o
r
s
er
v
ices.
T
h
e
te
r
ti
ar
y
as
s
u
m
p
tio
n
o
f
i
m
p
le
m
e
n
t
atio
n
is
th
at
all
t
h
e
cu
s
to
m
er
o
p
in
io
n
d
ata
is
in
th
e
f
o
r
m
o
f
tex
t
ex
p
lic
itl
y
.
M
o
r
eo
v
er
,
th
e
s
t
u
d
y
as
s
u
m
e
s
t
h
at
th
er
e
ar
e
g
o
o
d
p
o
s
s
ib
ilit
ie
s
o
f
t
h
e
d
ata
to
b
e
h
ig
h
l
y
u
n
f
o
r
m
atted
as
w
ell
a
s
u
n
s
tr
u
ct
u
r
ed
o
w
i
n
g
to
th
e
d
is
t
r
ib
u
te
d
tr
af
f
ic
s
y
s
te
m
o
v
er
clo
u
d
as
w
e
ll
as
p
ea
k
tr
af
f
ic
co
n
d
itio
n
o
w
i
n
g
to
m
a
s
s
i
v
e
co
n
cu
r
r
en
t
u
s
er
s
.
T
h
e
p
r
i
m
e
d
ep
en
d
en
c
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
th
a
t
a
s
p
ec
if
ic
d
o
m
ain
o
f
cu
s
to
m
er
o
p
in
io
n
is
r
eq
u
ir
ed
in
o
r
d
er
t
o
p
e
r
f
o
r
m
ac
c
u
r
ate
ass
es
s
m
en
t
alt
h
o
u
g
h
th
e
i
m
p
le
m
e
n
ted
m
o
d
el
is
ca
p
ab
le
o
f
an
al
y
z
in
g
an
y
d
ata
f
r
o
m
an
y
co
m
m
er
cial
d
o
m
ai
n
o
f
cu
s
to
m
er
o
p
in
io
n
.
2
.
2
.
I
m
ple
m
ent
a
t
io
n
s
t
ra
t
eg
y
T
h
e
ac
tu
al
id
ea
o
f
th
e
p
r
o
p
o
s
ed
im
p
le
m
en
tatio
n
is
to
p
er
f
o
r
m
o
n
lin
e
(
o
r
in
s
ta
n
ta
n
eo
u
s
)
an
al
y
s
is
o
f
th
e
i
n
co
m
in
g
s
tr
ea
m
s
o
f
d
ata
(
cu
s
to
m
er
o
p
in
io
n
)
.
Ho
w
ev
er
,
th
i
s
o
p
i
n
io
n
o
r
ig
i
n
ates
f
r
o
m
m
u
ltip
le
s
o
u
r
ce
s
o
f
th
e
e
-
co
m
m
er
ce
ap
p
licatio
n
s
w
h
ic
h
ar
e
r
eq
u
ir
ed
to
b
e
g
ath
er
ed
in
o
n
e
p
lace
w
it
h
o
u
t
w
h
ic
h
p
er
f
o
r
m
i
n
g
an
al
y
s
is
i
s
n
o
t
f
ea
s
ib
le
to
b
e
ca
r
r
ied
o
u
t.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
d
e
v
elo
p
s
a
d
is
tr
ib
u
ted
en
v
ir
o
n
m
e
n
t
in
o
r
d
er
to
tak
e
th
e
i
n
p
u
t o
f
d
ata
f
r
o
m
it
s
d
is
tr
ib
u
ted
o
r
ig
in
at
io
n
p
o
in
t.
T
h
e
n
ex
t step
is
to
ca
r
r
y
o
u
t d
is
tr
ib
u
te
d
d
ata
ag
g
r
eg
atio
n
w
ith
p
r
o
p
er
in
d
ex
i
n
g
o
f
an
in
co
m
in
g
s
tr
ea
m
o
f
d
ata
f
o
llo
w
ed
b
y
id
en
ti
f
icatio
n
o
f
th
e
co
r
e
f
ile
o
b
j
ec
ts
.
T
h
e
n
ex
t
p
r
o
ce
s
s
is
to
ex
tr
ac
t
th
e
h
ea
d
er
f
i
les,
w
h
ic
h
r
ep
r
esen
ts
t
h
e
f
ie
ld
o
f
th
e
ess
e
n
tial
v
al
u
e
o
f
th
e
cu
s
to
m
er
d
ata
an
d
r
ep
o
s
it
it
o
v
er
th
e
clo
u
d
d
is
tr
ib
u
ted
s
to
r
ag
e.
Fin
al
l
y
,
t
h
e
p
r
o
p
o
s
e
d
s
y
s
te
m
d
ev
elo
p
s
a
n
o
v
el
s
e
m
an
tic
in
d
e
x
in
g
t
h
at
i
s
u
s
ed
f
o
r
co
r
r
elatin
g
t
h
e
v
alu
e
s
o
f
t
h
e
cu
s
to
m
er
o
p
in
i
o
n
d
ata
in
o
r
d
er
to
ex
tr
ac
t
th
e
k
n
o
w
led
g
e
f
r
o
m
t
h
e
in
d
e
x
ed
ag
g
r
eg
ated
d
ata.
T
h
e
co
m
p
lete
p
r
o
ce
s
s
is
h
i
g
h
l
y
s
eq
u
e
n
tial
a
n
d
h
en
ce
t
h
e
e
x
ec
u
tio
n
i
s
h
ig
h
l
y
p
r
o
g
r
ess
i
v
e
lead
in
g
to
f
ast
er
p
r
o
ce
s
s
o
f
tr
an
s
f
o
r
m
i
n
g
.
Hen
ce
,
a
s
i
m
p
le
a
n
d
f
aster
p
r
o
ce
s
s
o
f
a
n
al
y
z
in
g
t
h
e
cu
s
to
m
er
o
p
in
io
n
d
ata
is
o
b
tain
ed
w
h
o
s
e
o
u
tco
m
e
is
o
f
f
er
ed
as a
s
er
v
ice.
2
.
3
.
E
x
ec
utio
n
f
lo
w
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
i
m
p
l
e
m
en
ted
u
s
i
n
g
d
iv
id
e
a
n
d
co
n
q
u
er
s
r
u
le
w
h
er
e
t
h
e
co
m
p
le
te
p
r
o
b
le
m
o
f
ex
tr
a
cti
n
g
s
p
ec
i
f
ic
k
n
o
w
le
d
g
e
f
r
o
m
t
h
e
c
u
s
to
m
er
o
p
in
io
n
d
ata
in
t
h
e
f
o
r
m
o
f
te
x
t
o
v
e
r
h
ig
h
l
y
d
is
tr
ib
u
te
d
an
d
co
llab
o
r
ativ
e
s
y
s
te
m
.
T
h
e
co
m
p
lete
ex
ec
u
tio
n
i
s
ca
r
r
ied
o
u
t
u
s
in
g
th
r
ee
s
eq
u
e
n
tial
al
g
o
r
ith
m
s
v
iz.
i)
A
l
g
o
r
ith
m
f
o
r
d
is
tr
ib
u
ted
d
ata
ag
g
r
eg
atio
n
,
ii)
al
g
o
r
ith
m
f
o
r
o
b
tain
i
n
g
in
d
e
x
ed
v
al
u
es
,
an
d
iii)
al
g
o
r
ith
m
f
o
r
s
e
m
a
n
tic
-
b
ased
k
n
o
w
led
g
e
ex
tr
ac
tio
n
.
T
h
e
d
is
cu
s
s
io
n
s
o
f
th
e
alg
o
r
it
h
m
s
ar
e
as f
o
llo
w
s
:
2
.
3
.
1
.
Alg
o
rit
h
m
f
o
r
dis
t
ribu
t
ed
da
t
a
a
g
g
re
g
a
t
io
n
I
t
is
to
b
e
n
o
ted
th
at
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
ac
tu
all
y
an
a
n
a
l
y
tic
al
d
esig
n
w
h
er
e
it
is
es
s
en
t
ial
to
d
ev
elo
p
a
h
ig
h
l
y
d
is
tr
ib
u
ted
ter
m
i
n
a
ls
o
f
g
en
er
atio
n
o
f
cu
s
to
m
e
r
d
ata.
T
h
er
ef
o
r
e,
th
is
alg
o
r
ith
m
i
s
b
asicall
y
r
esp
o
n
s
ib
le
f
o
r
co
n
s
tr
u
c
tin
g
a
d
is
tr
ib
u
ted
en
v
ir
o
n
m
e
n
t
t
h
at
ca
n
f
ac
ilit
ate
d
ata
a
g
g
r
eg
at
io
n
in
o
r
d
er
to
o
b
tain
in
d
ex
ed
ag
g
r
eg
a
ted
d
ata
f
o
r
b
etter
d
ata
tr
an
s
f
o
r
m
atio
n
lead
i
n
g
to
e
f
f
ec
t
iv
e
a
n
al
y
s
i
s
o
f
d
is
t
r
ib
u
ted
d
ata.
Algorithm for Distributed Data Aggregation
Input
:
n
(selected opinion
-
files from stream)
Output
: d
agg
(aggregated data)
Start
1.
For
i=1:n
2.
d
index
f
(d
i
)
3. d
agg
g
1
(d
i
, d
index
)
4. d
agg
g
2
(d
agg
)
5.
End
End
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:
2
0
8
8
-
8708
F
r
a
mewo
r
k
fo
r
o
p
in
io
n
a
s
a
s
ervice
o
n
r
ev
iew
d
a
ta
o
f c
u
s
to
mer
…
(
R
a
jesh
w
a
r
i D
.
)
5457
T
h
is
alg
o
r
ith
m
ta
k
e
s
th
e
in
p
u
t
o
f
n
(
s
elec
ted
o
p
in
io
n
-
f
iles
f
r
o
m
s
tr
ea
m
)
th
at
a
f
ter
p
r
o
ce
s
s
in
g
y
ield
s
d
agg
(
a
g
g
r
e
g
ated
d
ata)
.
T
h
e
al
g
o
r
ith
m
co
n
s
tr
u
ct
s
d
i
f
f
er
e
n
t
ter
m
i
n
als
i
n
d
is
tr
ib
u
ted
o
r
d
er
th
a
t
tak
e
s
t
h
e
in
p
u
t
o
f
v
ar
io
u
s
o
p
in
io
n
f
i
le
a
n
d
th
er
e
b
y
ac
t
as
t
h
e
s
o
u
r
ce
o
f
o
r
i
g
in
a
tio
n
p
o
in
t
o
f
d
ata
n
(
L
i
n
e
-
1
)
.
T
h
e
n
ex
t
p
r
o
ce
s
s
i
s
to
ap
p
ly
a
f
u
n
ctio
n
f
(
x
)
to
t
h
e
in
d
iv
id
u
al
d
ata
d
i
f
r
o
m
ea
c
h
s
o
u
r
ce
p
o
in
t
n
(
L
in
e
-
2
)
.
T
h
is
o
p
er
atio
n
is
u
s
e
d
f
o
r
in
d
ex
i
n
g
all
th
e
in
co
m
i
n
g
s
tr
ea
m
o
f
d
ata
w
h
ic
h
is
m
ai
n
tai
n
ed
in
th
e
f
o
r
m
o
f
m
atr
ix
d
index
(
L
in
e
-
2
)
.
T
h
e
n
ex
t
s
tep
is
to
f
u
r
t
h
er
ap
p
ly
a
f
u
n
c
t
io
n
g
1
(
x
)
f
o
r
all
t
h
e
in
d
i
v
id
u
a
l
d
ata
d
i
co
n
s
id
er
in
g
t
h
e
g
en
er
at
ed
d
ata
in
d
ex
d
index
in
p
r
io
r
s
tep
to
co
n
s
tr
u
ct
a
g
g
r
eg
ated
d
ata
d
agg
(
L
i
n
e
-
3
)
.
Fin
a
ll
y
,
a
d
is
cr
ete
f
u
n
c
tio
n
g
2
(
x
)
,
w
h
ic
h
is
r
ef
i
n
e
m
en
t
o
f
g
1
(
x
)
g
en
er
ate
s
a
f
ile
o
b
j
ec
t
o
f
t
h
e
d
ata
w
i
th
its
in
d
e
x
to
f
i
n
all
y
co
n
f
ir
m
ed
t
h
e
i
n
d
ex
ed
a
g
g
r
e
g
ated
d
ata
d
a
gg
(
L
in
e
-
4
)
.
T
h
e
f
lo
w
o
f
th
e
p
r
o
ce
s
s
i
n
v
o
l
v
ed
i
n
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
a
s
f
o
llo
w
s
.
T
h
e
F
ig
u
r
e
2
ill
u
s
tr
ates
p
r
o
ce
s
s
f
lo
w
o
f
alg
o
r
it
h
m
f
o
r
d
is
tr
ib
u
ted
d
ata
ag
g
r
e
g
atio
n
.
N
u
m
b
e
r
o
f
O
p
i
n
i
o
n
f
i
l
e
s
P
r
i
m
a
r
y
i
n
d
e
x
i
n
g
A
g
g
r
e
g
a
t
e
d
d
a
t
a
F
i
l
e
o
b
j
e
c
t
s
d
a
g
g
Fig
u
r
e
2
.
P
r
o
ce
s
s
f
lo
w
o
f
a
l
g
o
r
ith
m
f
o
r
d
is
tr
ib
u
ted
d
ata
a
g
g
r
eg
atio
n
2
.
3
.
2
.
Alg
o
rit
h
m
f
o
r
o
bta
ini
ng
ind
ex
ed
v
a
lues
T
h
is
alg
o
r
it
h
m
p
er
f
o
r
m
s
an
es
s
en
tia
l
o
p
er
atio
n
t
h
at
i
s
r
elate
d
w
it
h
t
h
e
f
u
r
th
er
i
n
d
ex
in
g
o
p
er
atio
n
o
f
th
e
in
co
m
i
n
g
a
g
g
r
eg
ated
d
ata
w
it
h
r
esp
ec
t
to
ess
e
n
tial
attr
i
b
u
tes
o
f
t
h
e
f
ile
o
b
j
ec
ts
.
W
ith
o
u
t
th
i
s
alg
o
r
it
h
m
,
th
e
s
y
s
te
m
w
ill
n
o
t
b
e
ab
le
t
o
p
er
f
o
r
m
in
d
e
x
in
g
o
f
e
x
p
li
ci
t
ar
ea
o
f
th
e
co
r
p
u
s
p
r
esen
t
in
th
e
d
is
cr
ete
f
ile
o
b
j
ec
ts
th
at
w
ill b
e
f
u
r
t
h
er
s
u
b
j
ec
ted
f
o
r
an
aly
s
is
.
Algorithm for Obtaining Indexed Values
Input
: m (number of file objects)
Output
: t
buff
(memory with indexed value)
Start
1.
For
i=
1: m
2. e
obj
c
(d
agg,m
)
3. αf
obj
Enc
obj
(enc
ID
)
4. βf
obj
extract(φ)
5. γf
obj
extract (val
(φ+1)
)
6.
End
7. Store αf
obj,
βf
obj
in cloud
8. t
buff
indexed(γf
obj
)
End
T
h
e
s
y
s
te
m
co
n
s
tr
u
ct
s
an
o
b
j
ec
t
o
f
th
e
e
n
tire
f
ile
(
in
d
i
v
id
u
al
ag
g
r
eg
a
ted
d
ata
d
agg
)
an
d
p
er
f
o
r
m
s
f
u
r
t
h
er
p
r
o
ce
s
s
i
n
g
.
T
h
e
alg
o
r
it
h
m
tak
e
s
t
h
e
in
p
u
t o
f
m
(
n
u
m
b
er
o
f
f
ile
o
b
j
ec
ts
)
th
at
af
ter
p
r
o
ce
s
s
in
g
y
ield
s
t
buf
f
(
m
e
m
o
r
y
w
it
h
i
n
d
ex
ed
v
al
u
e
)
.
E
ac
h
f
ile
o
b
j
ec
t
co
n
s
is
t
o
f
an
ex
p
lic
it
f
ield
s
i
n
t
h
e
f
o
r
m
o
f
h
ea
d
er
s
a
n
d
s
ep
ar
ato
r
th
at
ar
e
r
eq
u
ir
ed
to
b
e
s
to
r
ed
in
a
clo
u
d
s
to
r
ag
e
t
e
m
p
late
s
o
t
h
at
i
t
d
o
esn
’
t
h
av
e
to
s
to
r
e
th
e
s
a
m
e
ev
er
y
ti
m
e
f
o
r
t
h
e
in
co
m
i
n
g
d
ata.
T
h
e
alg
o
r
it
h
m
ap
p
lies
a
f
u
n
ctio
n
c
(
x
)
f
o
r
t
h
e
a
g
g
r
eg
ated
d
ata
w
ith
r
esp
ec
t t
o
n
u
m
b
er
o
f
f
ile
o
b
j
ec
ts
m
in
o
r
d
er
to
g
en
er
ate
an
en
co
d
ed
o
b
j
ec
t
e
obj
o
f
th
e
f
ile
o
b
j
ec
t
(
L
in
e
-
2
)
.
T
h
e
en
co
d
ed
v
er
s
io
n
o
f
t
h
e
f
ile
o
b
j
ec
ts
allo
w
s
m
o
r
e
u
s
er
-
f
r
ien
d
l
y
r
ep
r
esen
tatio
n
o
f
t
h
e
co
r
p
u
s
o
f
o
p
in
io
n
d
ata.
T
h
e
alg
o
r
ith
m
t
h
a
n
p
er
f
o
r
m
s
e
x
tr
ac
tio
n
o
f
al
l th
e
n
ec
es
s
ar
y
f
ield
s
in
t
h
e
in
d
i
v
id
u
a
l f
ile
o
b
j
ec
ts
.
T
h
e
f
ir
s
t
attr
ib
u
te
w
i
th
in
t
h
e
f
ile
o
b
j
ec
t
is
h
ea
d
er
f
iles
α
f
obj
w
h
er
e
th
e
e
n
co
d
ed
o
b
j
ec
ts
ar
e
ex
tr
ac
ted
an
d
r
etain
ed
w
i
th
r
esp
ec
t
to
d
i
s
cr
ete
id
en
tit
y
o
f
e
n
co
d
ed
d
ata
en
c
ID
(
L
i
n
e
-
3
)
.
T
h
e
n
e
x
t
p
ar
t
o
f
t
h
e
al
g
o
r
ith
m
i
s
ab
o
u
t
ex
tr
ac
ti
n
g
t
h
e
s
ep
ar
ato
r
φ
u
s
ed
f
o
r
d
is
ti
n
g
u
is
h
i
n
g
t
h
e
h
ea
d
er
o
b
j
ec
t
an
d
en
co
d
ed
v
alu
e
o
f
t
h
e
r
esp
ec
ti
v
e
h
ea
d
er
o
b
j
ec
t
βf
obj
(
L
i
n
e
-
4
)
.
F
in
all
y
,
th
e
al
g
o
r
ith
m
ex
tr
ac
t
t
h
e
v
al
u
e
w
h
ich
i
s
i
m
m
ed
iatel
y
a
f
ter
t
h
e
s
ep
ar
ato
r
o
b
j
ec
t
an
d
it
is
s
to
r
ed
in
a
d
if
f
er
en
t
m
atr
ix
γ
f
obj
(
L
i
n
e
-
5
)
.
A
clo
s
er
lo
o
k
in
to
th
e
alg
o
r
i
th
m
ic
s
tep
s
w
il
l
s
h
o
w
th
at
o
b
j
ec
ts
lik
e
α
f
obj
an
d
β
f
obj
ar
e
co
n
s
tan
ts
f
o
r
ev
er
y
i
n
co
m
in
g
d
ata
s
tr
ea
m
a
n
d
is
n
o
t
r
eq
u
ir
ed
to
b
e
p
r
o
ce
s
s
ed
ev
er
y
ti
m
e
an
d
h
e
n
ce
,
th
ese
t
w
o
attr
ib
u
te
s
ar
e
d
ir
ec
ted
k
e
y
ed
in
t
h
e
clo
u
d
s
to
r
ag
e
s
y
s
te
m
w
h
ic
h
w
il
l
b
e
f
u
r
th
er
u
s
ed
f
o
r
o
n
l
y
in
d
ex
i
n
g
th
e
r
esp
ec
ti
v
e
v
al
u
e
-
b
ased
f
ile
o
b
j
ec
ts
γ
f
obj
.
Fi
g
u
r
e
3
s
h
o
w
s
p
r
o
ce
s
s
f
lo
w
o
f
t
h
is
al
g
o
r
ith
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
4
5
3
-
5461
5458
A
g
g
r
e
g
a
t
e
d
d
a
t
a
F
i
l
e
o
b
j
e
c
t
s
d
a
g
g
α
f
o
b
j
β
f
o
b
j
γ
f
o
b
j
T
e
m
p
b
u
f
f
e
r
M
e
t
a
d
a
t
a
m
g
m
t
(
i
n
d
e
x
i
n
g
)
Fig
u
r
e
3
.
A
l
g
o
r
ith
m
f
o
r
o
b
tain
in
g
i
n
d
ex
ed
v
alu
e
s
2
.
3
.
3
.
Alg
o
rit
h
m
f
o
r
s
e
m
a
nti
c
-
ba
s
ed
k
no
w
ledg
e
ex
t
ra
ct
io
n
T
h
is
alg
o
r
it
h
m
is
r
e
s
p
o
n
s
ib
le
f
o
r
ex
tr
ac
tin
g
t
h
e
k
n
o
w
led
g
e
f
r
o
m
t
h
e
t
h
ir
d
f
ile
o
b
j
ec
t i.
e.
γ
f
ob
o
b
tain
ed
f
r
o
m
p
r
io
r
al
g
o
r
ith
m
u
s
in
g
s
e
m
an
tics
.
T
h
e
id
ea
is
also
to
co
n
s
tr
u
ct
a
v
er
y
s
i
m
p
lifie
d
s
e
m
a
n
tic
s
t
h
at
u
s
es
co
r
r
elatio
n
-
b
ased
ap
p
r
o
ac
h
to
ex
tr
ac
t
th
e
s
i
g
n
if
ican
t
co
r
p
u
s
attr
ib
u
te
f
r
o
m
t
h
e
v
al
u
es
o
f
th
ir
d
f
ile
o
b
j
ec
t
as
a
r
ep
r
esen
tatio
n
o
f
k
n
o
w
led
g
e
.
T
h
e
p
o
ten
tial
b
en
ef
it
o
f
t
h
is
alg
o
r
ith
m
i
s
its
ap
p
licab
ilit
y
t
o
w
ar
d
s
an
y
d
o
m
ai
n
o
f
p
r
o
d
u
cts/
s
er
v
ices
o
f
cu
s
to
m
er
o
p
in
io
n
w
h
ic
h
eli
m
i
n
ate
s
an
y
c
h
an
ce
s
o
f
d
ep
en
d
en
c
i
es
o
f
le
x
icals
u
n
li
k
e
ex
is
t
in
g
ap
p
r
o
ac
h
es o
f
m
in
i
n
g
.
Algorithm for semantic
-
based Knowledge Extraction
Input
: t
buff
(memory with indexed value)
Output
: h(core
-
semantic)
Start
1.
For
k=1: t
buff
2.
For
z
1
=1:h
1
//POS
3.
For
z
2
=1:h
2
4. y=
μ(c
seg
, h
1
)
5.
If
∑y≥1
6. flag h
7.
End
8.
End
9. obtain h
10.
End
End
T
h
is
alg
o
r
ith
m
tak
e
s
t
h
e
i
n
p
u
t
o
f
t
buff
(
m
e
m
o
r
y
w
i
th
in
d
e
x
ed
v
al
u
e)
f
o
r
g
i
v
in
g
a
n
o
u
t
co
m
e
o
f
h
(
co
r
e
-
s
e
m
a
n
tic)
(
L
in
e
-
1
)
.
T
h
e
a
lg
o
r
ith
m
co
n
s
tr
u
ct
s
v
ar
io
u
s
s
e
m
a
n
tic
s
h
1
w
h
ic
h
ar
e
all
p
o
s
s
ib
le
r
ep
r
esen
tatio
n
o
f
co
r
p
u
s
at
tr
ib
u
tes
(
L
in
e
-
2
)
.
T
h
ese
attr
ib
u
tes
ar
e
m
o
d
i
f
iab
l
e
an
d
t
h
e
al
g
o
r
ith
m
co
n
s
tr
u
ct
s
f
u
r
th
er
c
h
ec
k
s
f
o
r
all
h
2
w
h
ic
h
ar
e
b
asicall
y
u
s
e
d
f
o
r
s
ep
ar
atin
g
ea
ch
co
r
p
u
s
a
ttrib
u
tes
i
n
d
is
ti
n
g
u
is
h
ed
w
a
y
an
d
s
to
r
ed
b
ac
k
in
m
atr
i
x
y
(
L
i
n
e
-
4
)
.
T
h
e
alg
o
r
ith
m
th
e
n
p
er
f
o
r
m
s
s
tr
i
n
g
co
m
p
ar
is
o
n
f
o
r
all
t
h
e
y
m
atr
i
x
w
it
h
t
h
e
p
ar
titi
o
n
ed
co
r
p
u
s
attr
ib
u
te
s
i
n
o
r
d
er
to
f
i
n
d
t
h
e
ap
p
r
o
p
r
iate
s
e
m
a
n
tic
h
(
L
i
n
e
-
6
a
n
d
L
i
n
e
-
9
)
.
T
h
e
F
i
g
u
r
e
4
p
r
esen
t
s
th
e
alg
o
r
it
h
m
f
o
r
s
e
m
an
tic
-
b
a
s
ed
k
n
o
w
led
g
e
e
x
tr
ac
tio
n
.
α
f
o
b
j
β
f
o
b
j
γ
f
o
b
j
T
e
m
p
b
u
f
f
e
r
M
e
t
a
d
a
t
a
m
g
m
t
(
i
n
d
e
x
i
n
g
)
A
p
p
l
y
s
e
m
a
n
t
i
c
I
n
d
e
x
i
n
g
V
a
l
u
e
s
E
x
t
r
a
c
t
e
d
K
n
o
w
l
e
d
g
e
Fig
u
r
e
4
.
A
l
g
o
r
ith
m
f
o
r
s
e
m
a
n
tic
-
b
ased
k
n
o
w
led
g
e
e
x
tr
ac
tio
n
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:
2
0
8
8
-
8708
F
r
a
mewo
r
k
fo
r
o
p
in
io
n
a
s
a
s
ervice
o
n
r
ev
iew
d
a
ta
o
f c
u
s
to
mer
…
(
R
a
jesh
w
a
r
i D
.
)
5459
3.
RE
SU
L
T
S
ANA
L
YS
I
S
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
u
s
es
t
h
e
s
ta
n
d
ar
d
d
ataset
o
f
p
r
o
d
u
ct
r
ev
ie
w
d
ata
f
r
o
m
Am
az
o
n
th
at
i
s
fr
eq
u
en
tl
y
u
s
ed
f
o
r
s
e
n
ti
m
en
t
an
al
y
s
is
[
3
1
]
.
T
h
e
f
o
r
m
at
o
f
t
h
e
d
ata
is
r
ec
o
n
f
ir
m
ed
to
b
e
t
ak
in
g
t
h
e
s
h
ap
e
o
f
b
ig
d
ata
b
y
r
ef
er
r
in
g
p
u
b
lical
l
y
a
v
ailab
le
b
i
g
d
ata
[
3
2
]
.
Hen
ce
,
a
s
y
n
t
h
etic
d
ata
is
co
n
s
tr
u
cted
f
o
r
o
p
in
io
n
m
i
n
in
g
.
T
h
e
d
ataset
co
n
s
i
s
ts
o
f
5
5
0
0
p
la
in
te
x
t
f
iles
w
it
h
m
u
ltip
le
r
e
v
ie
w
s
o
f
s
p
ec
i
f
ic
p
r
o
d
u
cts.
T
h
is
d
ata
s
et
is
tak
e
n
as
an
in
p
u
t
f
o
r
th
e
i
m
p
le
m
en
ta
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
t
h
at
is
ca
r
r
ied
o
u
t
in
MA
T
L
A
B
.
T
h
e
s
tu
d
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
co
m
p
ar
ed
w
ith
t
h
e
s
ta
n
d
ar
d
m
in
i
n
g
ap
p
r
o
ac
h
e.
g
.
s
u
p
er
v
is
ed
lear
n
i
n
g
an
d
d
ictio
n
ar
y
-
b
ased
lear
n
i
n
g
ap
p
r
o
ac
h
.
T
h
e
an
al
y
s
is
is
ca
r
r
ied
o
u
t
with
r
esp
ec
t
to
r
e
s
p
o
n
s
e
ti
m
e,
m
e
m
o
r
y
co
n
s
u
m
p
tio
n
,
an
d
ac
cu
r
ac
y
a
s
th
e
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
.
T
h
e
s
tu
d
y
o
u
tco
m
e
s
h
o
w
s
th
at
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
co
m
p
ar
ativ
el
y
b
etter
th
a
n
ex
is
t
in
g
ap
p
r
o
ac
h
o
f
o
p
in
io
n
m
i
n
in
g
f
o
r
s
e
n
ti
m
en
t
an
al
y
s
i
s
.
T
h
e
p
r
im
e
r
ea
s
o
n
b
eh
i
n
d
b
etter
r
esp
o
n
s
e
ti
m
e
is
th
at
p
r
o
p
o
s
ed
s
y
s
te
m
d
o
es
n
’
t
h
a
v
e
a
n
y
d
ep
en
d
en
c
y
to
ca
r
r
y
o
u
t
iter
ati
v
e
tr
ai
n
i
n
g
o
p
er
atio
n
u
n
li
k
e
th
e
ex
is
ti
n
g
ap
p
r
o
ac
h
.
Mo
r
eo
v
er
,
th
e
co
m
p
lete
p
r
o
ce
s
s
i
s
h
i
g
h
l
y
p
r
o
g
r
ess
iv
e
a
n
d
n
o
t
r
ec
u
r
s
iv
e
w
h
ic
h
r
ed
u
ce
s
th
e
cu
m
u
lati
v
e
ti
m
e
o
f
o
p
er
atio
n
as
s
h
o
w
n
i
n
Fi
g
u
r
e
5
(
a)
.
I
t
ca
n
also
b
e
s
ee
n
t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
al
s
o
o
f
f
er
s
lo
w
er
m
e
m
o
r
y
co
n
s
u
m
p
tio
n
i
n
co
n
tr
as
t to
ex
is
ti
n
g
ap
p
r
o
ac
h
es o
f
o
p
in
io
n
m
in
i
n
g
.
I
t i
s
b
e
ca
u
s
e
o
f
t
h
e
f
ac
t t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
m
a
k
e
u
s
e
o
f
te
m
p
o
r
ar
y
m
e
m
o
r
y
s
y
s
te
m
wh
er
e
th
e
p
r
o
ce
s
s
i
n
g
ta
k
es
p
lac
e
an
d
o
n
l
y
t
h
e
f
i
n
al
m
i
n
ed
d
ata
is
s
to
r
ed
.
T
h
is
p
h
e
n
o
m
e
n
o
n
n
o
t
o
n
l
y
o
p
ti
m
ize
th
e
s
to
r
ag
e
s
p
ac
e
in
d
ata
ce
n
ter
o
v
er
clo
u
d
b
u
t
also
o
f
f
er
s
f
aster
p
r
o
ce
s
s
i
n
g
o
f
th
e
q
u
er
ies
to
w
ar
d
s
lead
i
n
g
to
o
u
t
p
u
t
o
f
m
i
n
ed
d
ata
as
s
h
o
w
n
i
n
Fig
u
r
e
5
(
b
)
.
A
p
ar
t
f
r
o
m
th
is
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
ls
o
o
f
f
er
s
h
i
g
h
er
ac
cu
r
ac
y
s
co
r
e
to
w
ar
d
s
m
i
n
in
g
p
er
f
o
r
m
an
ce
as
it
m
a
k
es
u
s
e
o
f
co
n
te
x
t t
h
at
ar
e
f
o
r
m
u
lated
f
r
o
m
t
h
e
s
e
m
an
t
ics
u
s
e
d
i
n
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
as
s
h
o
w
n
i
n
Fig
u
r
e
5
(
c)
.
T
h
ese
p
er
f
o
r
m
a
n
ce
o
u
tco
m
es
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
a
r
o
b
u
s
t
co
n
f
ir
m
atio
n
t
h
at
in
o
r
d
er
to
r
ela
y
t
h
e
s
er
v
ices
in
th
e
f
o
r
m
o
f
m
i
n
ed
o
p
in
io
n
.
An
o
th
er
in
ter
esti
n
g
p
o
in
t
o
f
t
h
e
o
u
tco
m
e
i
s
th
at
it
i
s
ca
p
ab
l
e
to
m
i
n
e
an
y
f
o
r
m
o
f
p
r
o
d
u
cts
o
r
s
er
v
ices
a
n
d
h
en
ce
th
e
y
ar
e
h
i
g
h
l
y
ap
p
licab
le
f
o
r
h
eter
o
g
e
n
eo
u
s
d
ata
to
o
.
I
t
also
o
f
f
er
s
a
f
lex
ib
ilit
y
to
p
er
f
o
r
m
m
i
n
i
n
g
b
ased
o
n
s
p
ec
if
ic
d
o
m
ai
n
o
f
q
u
er
y
s
y
s
te
m
e.
g
.
d
eg
r
ee
o
f
s
ati
s
f
ac
tio
n
,
p
r
o
d
u
cts
in
h
ig
h
er
d
e
m
a
n
d
s
,
c
u
s
to
m
er
b
u
y
i
n
g
b
e
h
av
io
r
,
o
v
er
all
u
til
izatio
n
s
co
r
e
o
f
p
r
o
d
u
cts/
s
er
v
ices
u
n
d
er
tak
e
n
b
y
th
e
u
s
er
.
He
n
ce
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
a
h
ig
h
l
y
co
s
t
e
f
f
ec
tiv
e
co
m
p
u
tatio
n
al
m
o
d
el
th
at
is
ca
p
ab
le
o
f
d
eliv
er
in
g
o
p
in
io
n
a
s
a
s
er
v
ice
w
it
h
h
ig
h
er
ac
cu
r
ac
y
.
(
a)
(
b
)
(
c)
Fig
u
r
e
5
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
,
(
a)
r
esp
o
n
s
e
t
i
m
e
, (
b
)
m
e
m
o
r
y
c
o
n
s
u
m
p
tio
n
, (
c)
ac
cu
r
ac
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
5
4
5
3
-
5461
5460
4.
CO
NCLU
SI
O
N
Op
in
i
o
n
m
in
in
g
is
g
ain
in
g
p
r
o
lif
er
ati
o
n
o
w
in
g
to
its
im
p
o
r
ta
n
ce
in
alm
o
s
t
ev
e
r
y
f
iel
d
o
f
p
r
o
d
u
ct
an
d
s
er
v
i
ce
d
eliv
e
r
y
.
Fr
o
m
th
e
p
ast
d
e
ca
d
e
,
th
er
e
h
as
b
ee
n
v
ar
io
u
s
r
esea
r
ch
w
o
r
k
ca
r
r
i
e
d
o
u
t
to
w
ar
d
s
o
p
in
i
o
n
m
in
in
g
an
d
s
en
tim
en
t a
n
aly
s
is
,
h
o
w
ev
er
,
th
ey
ar
e
all
c
o
n
ce
r
n
ed
ab
o
u
t
ce
n
t
r
al
iz
ed
s
y
s
tem
o
f
ap
p
ly
in
g
an
aly
tics
.
I
n
clu
s
i
o
n
o
f
d
is
t
r
i
b
u
te
d
co
m
p
u
tin
g
l
ea
d
s
t
o
v
ar
io
u
s
ch
al
l
en
g
es
in
th
e
m
in
in
g
p
r
o
c
ess
as
w
ell
as
in
d
at
a
ag
g
r
eg
at
io
n
p
r
o
c
ess
to
o
.
T
h
e
r
ef
o
r
e,
th
e
p
r
o
p
o
s
e
d
s
y
s
te
m
in
tr
o
d
u
c
es
a
n
o
v
el
f
r
am
e
w
o
r
k
w
ith
f
o
llo
w
in
g
co
n
t
r
i
b
u
ti
o
n
v
iz.
i)
th
e
p
r
o
p
o
s
ed
s
y
s
tem
is
ca
p
a
b
le
o
f
s
y
n
ch
r
o
n
izin
g
al
l
th
e
in
c
o
m
in
g
s
tr
e
am
s
o
f
d
ata
o
f
o
p
in
i
o
n
an
d
p
e
r
f
o
r
m
a
s
tr
u
ctu
r
e
d
ag
g
r
eg
a
ti
o
n
,
i
i)
th
e
p
r
o
p
o
s
ed
s
y
s
tem
ca
n
als
o
p
e
r
f
o
r
m
a
p
e
r
f
ec
t
in
d
ex
in
g
o
f
all
th
e
f
i
le
o
b
je
cts
f
o
ll
o
w
ed
b
y
ex
tr
ac
tin
g
en
t
er
ed
v
alu
es
o
f
d
i
r
e
ct
r
e
p
r
esen
t
ati
o
n
o
f
o
p
in
io
n
,
an
d
iii
)
p
r
o
p
o
s
e
d
s
y
s
te
m
ap
p
lies
a
v
e
r
y
u
n
iq
u
e
m
ec
h
an
is
m
o
f
s
e
m
an
tics
-
b
ase
d
k
n
o
w
led
g
e
d
is
c
o
v
e
r
y
p
r
o
ce
s
s
w
h
ich
is
n
o
t
o
n
ly
f
ast
b
u
t
als
o
m
ak
es th
e
d
esig
n
f
r
ee
f
r
o
m
u
s
ag
e
o
f
l
ex
ica
l u
n
li
k
e
an
y
ex
is
tin
g
m
in
in
g
ap
p
r
o
a
ch
.
RE
F
E
R
E
NC
E
S
[1
]
R.
A
g
ra
w
a
l
a
n
d
N
.
G
u
p
ta
,
“
Ex
trac
ti
n
g
K
n
o
w
le
d
g
e
f
r
o
m
O
p
in
i
o
n
M
i
n
i
n
g
,
”
IG
I
Gl
o
b
a
l
,
2
0
1
8
.
[2
]
U
.
Ka
n
g
,
e
t
a
l
.
,
“
T
re
n
d
s a
n
d
A
p
p
l
i
c
a
ti
o
n
s
i
n
Kn
o
w
le
d
g
e
D
isc
o
v
e
ry
a
n
d
Da
t
a
M
in
i
n
g
,
”
S
p
r
i
n
g
e
r
,
2
0
1
7
.
[3
]
E
.
Ca
m
b
ri
a
,
e
t
a
l
.
,
“
A
P
ra
c
t
ica
l
G
u
i
d
e
t
o
S
e
n
ti
m
e
n
t
A
n
a
ly
sis
,
”
S
p
r
i
n
g
e
r
,
2
0
1
7
.
[4
]
J
.
S
il
ge
a
n
d
D
.
R
o
b
i
n
s
o
n
,
“
T
e
x
t
M
i
n
i
n
g
w
i
t
h
R:
A
T
i
d
y
A
p
p
r
o
a
c
h
,
”
J
o
u
r
n
a
l
o
f
S
t
a
ti
s
ti
c
a
l
S
o
f
tw
a
re
,
v
o
l
.
8
3
,
201
8
.
[5
]
S
.
P
o
r
ia
,
e
t
a
l
.
,
“
M
u
lt
im
o
d
a
l
S
e
n
t
i
m
e
n
t
A
n
a
ly
sis
,
”
S
p
ri
n
g
e
r
,
2
0
1
8
.
[6
]
R
.
S
a
ta
p
a
t
h
y
,
e
t
a
l
.
,
“
S
e
n
t
im
e
n
t
A
n
a
ly
sis
i
n
t
h
e
Bi
o
-
M
e
d
ica
l
Do
m
a
i
n
:
T
e
c
h
n
i
q
u
e
s
,
T
o
o
ls
,
a
n
d
A
p
p
li
c
a
t
i
o
n
s,
”
S
p
r
i
n
g
e
r
,
2
0
1
7
.
[7
]
S
.
S.
K
h
a
n
,
e
t
a
l.
,
“
C
h
a
l
le
n
g
e
s
i
n
o
p
i
n
i
o
n
m
i
n
i
n
g
,
a
c
o
m
p
r
e
h
e
n
si
v
e
re
v
iew
,”
A
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
J
o
u
r
n
a
l
,
v
o
l
.
33
,
n
o
.
1
1
,
pp.
123
-
135
,
2
0
1
8
.
[8
]
M
.
C
h
a
u
d
h
a
r
i
a
n
d
S
.
G
o
v
i
lk
a
r
,
“
A
su
rv
e
y
o
f
m
a
c
h
i
n
e
lea
r
n
i
n
g
te
c
h
n
iq
u
e
s f
o
r
se
n
ti
m
e
n
t
C
las
s
if
ica
ti
o
n
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
&
Ap
p
li
c
a
ti
o
n
s
(
IJ
C
S
A)
,v
o
l
.
5
,
n
o.
3
,
p
p
.
1
3
-
2
3
,
J
u
n
.
2015
.
[9
]
C
.
J.
Ra
m
e
sh
b
h
a
i
a
n
d
J.
P
a
u
l
o
se
,
“
Op
in
io
n
m
in
in
g
o
n
n
e
w
sp
a
p
e
r
h
e
a
d
li
n
e
s
u
sin
g
S
VM
a
n
d
NL
P
,”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
t
e
r E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
9
,
n
o
.
3
,
p
p.
2
1
5
2
-
2
1
6
3
,
2
0
1
9
.
[1
0
]
A
.
M
.
A
b
iram
i
a
n
d
V
.
G
a
y
a
th
ri
,
“
A
su
rv
e
y
o
n
se
n
t
im
e
n
t
a
n
a
ly
sis
m
e
t
h
o
d
s
a
n
d
a
p
p
r
o
a
c
h
,
”
2
0
1
6
E
i
g
h
t
h
I
n
ter
n
a
t
i
o
n
a
l
Co
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
ti
n
g
(
I
C
o
A
C
)
,
C
h
e
n
n
a
i
,
p
p
.
7
2
-
76
,
2017
.
[1
1
]
F.
R
i
q
u
e
lm
e
,
e
t
a
l.
,
“
I
d
e
n
ti
f
y
in
g
O
p
i
n
i
o
n
L
e
a
d
e
rs o
n
S
o
c
ia
l
Ne
tw
o
rk
s T
h
r
o
u
g
h
M
i
les
t
o
n
e
s De
f
i
n
i
ti
o
n
,”
IEE
E
Acc
e
ss
,
v
o
l
.
7
,
p
p
.
75670
-
75677
,
2019
.
[1
2
]
S.
S
i
d
d
i
q
u
i
,
e
t
a
l
.
,
“
On
t
o
l
o
g
y
Driv
e
n
F
e
a
t
u
re
E
n
g
i
n
e
e
r
i
n
g
f
o
r
O
p
i
n
io
n
M
i
n
i
n
g
,”
I
E
E
E
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
6
7
3
9
2
-
6
7
4
0
1
,
2019
.
[1
3
]
G.
Xu
,
e
t
a
l.
,
“
S
e
n
t
im
e
n
t
A
n
a
ly
si
s
o
f
Co
m
m
e
n
t
T
e
x
ts
Ba
se
d
o
n
B
iL
S
T
M
,”
I
EE
E
Acc
e
ss
,
v
o
l.
7
,
p
p
.
51522
-
51532
,
2019
.
[1
4
]
J.
Y
u
,
e
t
a
l
.
,
“
G
l
o
b
a
l
i
n
f
e
re
n
c
e
f
o
r
a
s
p
e
c
t
a
n
d
o
p
i
n
i
o
n
t
e
rm
s
c
o
-
e
x
trac
ti
o
n
b
a
se
d
o
n
m
u
lt
i
-
tas
k
n
e
u
r
a
l
n
e
tw
o
rk
s
,”
IE
EE
/A
CM
T
r
a
n
s
a
c
t
i
o
n
s
o
n
A
u
d
i
o
,
S
p
e
e
c
h
a
n
d
L
a
n
g
u
a
g
e
Pr
o
c
e
ss
i
n
g
(
T
A
S
L
P
)
,
v
o
l.
2
7
,
n
o
.
1
,
p
p
.
168
-
177
,
2019
.
[1
5
]
H.
X
.
H
u
y
n
h
,
e
t
a
l.
,
“
D
is
tr
i
b
u
t
e
d
F
ra
m
e
w
o
rk
f
o
r
A
u
t
o
m
a
ti
n
g
Op
i
n
i
o
n
Disc
re
ti
z
a
t
io
n
F
r
o
m
T
e
x
t
C
o
r
p
o
ra
o
n
F
a
c
e
b
o
o
k
,”
IE
EE
Acc
e
s
s
,
v
o
l
.
7
, p
p.
78675
-
78684
,
2019
.
[1
6
]
J.
S
.
He
,
e
t
a
l
.
,
“
S
p
re
a
d
i
n
g
so
c
ia
l
in
f
l
u
e
n
c
e
w
it
h
b
o
t
h
p
o
si
ti
v
e
a
n
d
n
e
g
a
ti
v
e
o
p
i
n
i
o
n
s
i
n
o
n
li
n
e
n
e
tw
o
rk
s
,”
Bi
g
D
a
t
a
M
in
i
n
g
a
n
d
An
a
ly
ti
c
s
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
100
-
1
1
7
,
2
0
1
9
.
[1
7
]
F
e
r
n
a
n
d
e
s
,
F
e
li
x
C.
,
I
m
e
d
B
o
u
a
z
izi
,
a
n
d
Y
o
u
n
g
k
w
o
n
L
im
,
"
S
t
o
r
a
g
e
a
n
d
c
a
rr
iag
e
o
f
g
re
e
n
m
e
ta
d
a
ta
f
o
r
d
i
sp
lay
a
d
a
p
tat
i
o
n
,
"
U
.
S
.
P
a
te
n
t
9
5
2
0
079
B2
,
De
s
.
2016.
[1
8
]
M.
B
o
u
a
z
iz
i
a
n
d
T
.
O
h
t
s
u
k
i
,
“
M
u
l
t
i
-
c
las
s
s
e
n
t
im
e
n
t
a
n
a
ly
sis
i
n
T
w
it
te
r:
W
h
a
t
if
c
las
s
if
ica
ti
o
n
i
s
n
o
t
t
h
e
a
n
sw
e
r
,”
IE
EE
Acc
e
ss
,
v
o
l
.
6
,
p
p
.
6
4
4
8
6
-
64502
,
2018
.
[1
9
]
C.
Vi
rm
a
n
i,
e
t
a
l.
,
“
Clu
ste
ri
n
g
in
Ag
g
re
g
a
ted
Us
e
r
P
ro
f
il
e
s
a
c
ro
ss
M
u
lt
i
p
le
S
o
c
ial
Ne
tw
o
rk
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
7
,
n
o
.
6
,
p
p
.
3
6
9
2
-
3
6
9
9
,
2
0
1
7
.
[2
0
]
A.
M
u
l
li
c
k
,
e
t
a
l
.
,
“
Ha
r
n
e
ss
i
n
g
T
w
it
te
r
f
o
r
A
n
sw
e
ri
n
g
O
p
i
n
i
o
n
L
is
t
Q
u
e
r
ies
,”
I
E
EE
T
r
a
n
s
a
c
ti
o
n
s
o
n
Co
m
p
u
t
a
ti
o
n
a
l
S
o
c
ia
l
S
y
s
tem
s
,
v
o
l
.
5
,
n
o
.
4
,
p
p
.
1083
-
1095
,
2018
.
[2
1
]
F.
I
q
b
a
l
,
e
t
a
l
.
,
“
A
Hy
b
ri
d
F
r
a
m
e
w
o
rk
f
o
r
S
e
n
ti
m
e
n
t
A
n
a
ly
sis
Us
i
n
g
G
e
n
e
t
ic
A
lg
o
ri
t
h
m
Ba
se
d
F
e
a
t
u
re
R
e
d
u
c
t
i
o
n
,”
IE
EE
Acc
e
ss
,
v
o
l
.
7
,
p
p
.
1
4
6
3
7
-
14652
,
2019
.
[2
2
]
S
.
X
.
W
u
,
e
t
a
l.
,
“
Es
ti
m
a
t
i
n
g
s
o
c
ial
o
p
i
n
i
o
n
d
y
n
a
m
ics
m
o
d
e
ls
f
ro
m
v
o
ti
n
g
re
c
o
r
d
s
,”
I
E
EE
T
r
a
n
s
a
c
ti
o
n
s
o
n
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
,
v
o
l.
6
6
,
n
o
.
1
6
,
p
p
.
4193
-
4206
,
2018
.
[2
3
]
S.
Z
h
a
n
g
a
n
d
H
.
Z
h
o
n
g
,
“
M
i
n
i
n
g
u
se
rs t
r
u
s
t
f
ro
m
e
-
c
o
m
m
e
rc
e
re
v
ie
w
s b
a
se
d
o
n
se
n
t
im
e
n
t
sim
i
lar
it
y
a
n
a
ly
sis
,
”
IE
E
E
Acc
e
ss
,
v
o
l
.
7
,
p
p
.
1
3
5
2
3
-
1
3
5
3
5
,
2019
.
[2
4
]
O.
A
.
S
ic
h
a
n
i
a
n
d
M
.
J
a
l
il
i
,
“
I
n
f
e
re
n
c
e
o
f
h
i
d
d
e
n
s
o
c
i
a
l
p
o
w
e
r
t
h
ro
u
g
h
o
p
in
i
o
n
f
o
rm
a
ti
o
n
i
n
c
o
m
p
l
e
x
n
e
tw
o
rk
s
,”
IE
EE
T
r
a
n
s
a
c
ti
o
n
s
o
n
Ne
t
w
o
rk
S
c
ie
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
,
n
o
.
3
,
p
p
.
154
-
1
6
4
,
2
0
1
7
.
[2
5
]
Y.
L
v
,
e
t
a
l.
,
“
O
p
i
n
i
o
n
e
d
p
o
s
t
d
e
te
c
ti
o
n
i
n
S
i
n
a
W
e
i
b
o
,”
I
EE
E
Acc
e
s
s
,
v
o
l
.
5
,
p
p
.
7
2
6
3
-
7
2
7
1
,
2
0
1
7
.
[2
6
]
Y.
Z
u
o
,
e
t
a
l
.
,
“
C
o
m
p
lem
e
n
t
a
r
y
a
sp
e
c
t
-
b
a
se
d
o
p
i
n
i
o
n
m
in
i
n
g
,”
I
EE
E
T
r
a
n
sa
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
0
,
n
o
.
2
,
p
p
.
2
4
9
-
262
,
201
8
.
[2
7
]
X.
Z
h
o
u
,
e
t
a
l
.
,
“
CM
i
n
e
r
:
O
p
i
n
i
o
n
e
x
t
ra
c
ti
o
n
a
n
d
s
u
m
m
a
r
iza
t
io
n
f
o
r
c
h
i
n
e
s
e
m
icr
o
b
l
o
g
s
,”
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
Kn
o
wle
d
g
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l.
2
8
,
n
o
.
7
,
p
p
.
1
6
5
0
-
1663
,
2016
.
[2
8
]
D.
J
ia
n
g
,
e
t
a
l.
,
“
S
e
n
ti
m
e
n
t
c
o
m
p
u
t
i
n
g
f
o
r
t
h
e
n
e
w
s
e
v
e
n
t
b
a
se
d
o
n
t
h
e
s
o
c
ial
m
e
d
ia
b
ig
d
a
ta
,”
I
EE
E
Acc
e
ss
,
v
o
l.
5
,
p
p
.
2373
-
2382
,
201
7
.
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:
2
0
8
8
-
8708
F
r
a
mewo
r
k
fo
r
o
p
in
io
n
a
s
a
s
ervice
o
n
r
ev
iew
d
a
ta
o
f c
u
s
to
mer
…
(
R
a
jesh
w
a
r
i D
.
)
5461
[2
9
]
J.
Z
h
a
n
g
a
n
d
C
.
C
h
o
w
,
“
Cra
ts
:
A
n
l
d
a
-
b
a
se
d
m
o
d
e
l
f
o
r
j
o
i
n
tl
y
m
in
in
g
la
te
n
t
c
o
m
m
u
n
it
ies
,
re
g
i
o
n
s
,
a
c
ti
v
it
ies
,
t
o
p
ics
,
a
n
d
se
n
t
im
e
n
ts
f
r
o
m
g
e
o
s
o
c
ia
l
n
e
tw
o
rk
d
a
ta
,”
I
E
EE
T
ra
n
sa
c
t
i
o
n
s
o
n
K
n
o
w
le
d
g
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
8
,
n
o
.
1
1
,
p
p
.
2895
-
2909
,
2016
.
[3
0
]
C.
Clav
e
l
a
n
d
Z
.
Ca
l
le
jas
,
“
S
e
n
t
i
m
e
n
t
a
n
a
ly
sis: f
r
o
m
o
p
i
n
i
o
n
m
in
i
n
g
t
o
h
u
m
a
n
-
a
g
e
n
t
i
n
tera
c
t
i
o
n
,”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
a
f
fec
t
ive
c
o
m
p
u
ti
n
g
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
74
-
93
,
201
6
.
[3
1
]
M.
G
u
p
ta
a
n
d
S
.
S
e
b
a
stian
,
“
F
ra
m
e
w
o
rk
to
A
n
a
l
y
z
e
Cu
sto
m
e
r’s
F
e
e
d
b
a
c
k
in
S
m
a
rtp
h
o
n
e
In
d
u
str
y
Us
in
g
Op
in
io
n
M
in
i
n
g
,”
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
8
,
n
o
.
5
,
p
p.
3
3
1
7
-
3
3
2
4
,
2
0
1
8
.
[3
2
]
“
Ci
ty
o
f
Va
n
c
o
u
v
e
r
,
”
[O
n
li
n
e
].
A
v
a
il
a
b
le
:
h
tt
p
s
:
//
d
a
ta
.
v
a
n
c
o
u
v
e
r
.
c
a
/
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
S
m
t.
Ra
j
e
s
h
w
a
r
i.
D
,
w
o
rk
in
g
a
s
A
s
st.
P
r
o
f
e
ss
o
r,
De
p
a
rtme
n
t
o
f
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
NIE
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
,
M
y
so
re
,
In
d
ia.
S
h
e
h
a
s
c
o
m
p
lete
d
h
e
r
M
.
T
e
c
h
f
ro
m
V
isv
e
sv
a
ra
y
a
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsity
Be
lag
a
v
i,
In
d
ia.
S
h
e
is
p
u
rsu
i
n
g
h
e
r
P
h
D
f
ro
m
V
isv
e
sv
a
ra
y
a
T
e
c
h
n
o
l
o
g
ica
l
Un
iv
e
rsit
y
B
e
lag
a
v
i,
In
d
ia.
He
r
a
re
a
s
o
f
in
tere
st
a
re
Da
ta
S
c
ien
c
e
,
Co
m
p
il
e
r
De
sig
n
,
a
n
d
A
u
to
m
a
ta
T
h
e
o
r
y
.
S
h
e
h
a
s a
ro
u
n
d
1
5
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
Dr
.
V
a
g
d
e
v
i
S
,
P
ro
f
e
ss
o
r,
De
p
a
rtme
n
t
o
f
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
Da
y
a
n
a
n
d
a
S
a
g
a
r
A
c
a
d
e
m
y
o
f
T
e
c
h
n
o
lo
g
y
a
n
d
M
a
n
a
g
e
m
e
n
t,
Be
n
g
a
lu
ru
,
I
n
d
i
a
.
S
h
e
h
a
s
a
ro
u
n
d
3
0
y
e
a
rs
o
f
w
o
rk
e
x
p
e
rien
c
e
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
1
8
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
l,
7
in
t
e
rn
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
a
n
d
1
1
n
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
p
a
p
e
rs
.
Evaluation Warning : The document was created with Spire.PDF for Python.