I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
4
,
No
.
3
,
Sep
tem
b
er
201
5
,
p
p
.
109
~
116
I
SS
N:
2252
-
8814
109
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
AAS
So
ng
Reco
m
m
e
n
da
tion Sy
ste
m
Usi
ng
Ma
x
im
a
l
b
-
M
a
tching
Dee
pa
S
,
Va
rsh
a
R
,
P
a
rv
a
t
hi
R
S
c
h
o
o
l
o
f
Co
m
p
u
ti
n
g
S
c
ien
c
e
s an
d
E
n
g
in
e
e
rin
g
,
V
IT
Un
iv
e
rsity
,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
5
,
2
0
1
5
R
ev
i
s
ed
A
u
g
10
,
2
0
1
5
A
cc
ep
ted
A
u
g
26
,
2
0
1
5
T
h
e
las
t
d
e
c
a
d
e
h
a
s
w
it
n
e
ss
e
d
a
f
u
n
d
a
m
e
n
tal
p
a
ra
d
ig
m
sh
if
t
o
n
h
o
w
in
f
o
rm
a
ti
o
n
c
o
n
ten
t
is
d
istr
ib
u
ted
a
m
o
n
g
p
e
o
p
le.
No
w
a
d
a
y
s,
a
n
in
c
re
a
sin
g
n
u
m
b
e
r
o
f
p
lat
f
o
r
m
s
a
ll
o
w
e
v
e
ry
o
n
e
to
p
a
rti
c
ip
a
te
b
o
th
in
in
f
o
r
m
a
ti
o
n
p
ro
d
u
c
ti
o
n
a
n
d
in
f
o
rm
a
ti
o
n
c
o
n
s
u
m
p
ti
o
n
.
T
h
e
p
h
e
n
o
m
e
n
o
n
h
a
s
b
e
e
n
c
o
in
e
d
a
s
d
e
m
o
c
ra
ti
z
a
ti
o
n
o
f
c
o
n
ten
t.
H
o
w
e
v
e
r,
a
s
th
e
o
p
p
o
r
tu
n
it
ies
to
f
in
d
re
lev
a
n
t
in
f
o
rm
a
ti
o
n
a
n
d
re
lev
a
n
t
a
u
d
ien
c
e
in
c
re
a
se
s,
so
d
o
e
s
th
e
c
o
m
p
lex
it
y
o
f
a
s
y
ste
m
th
a
t
w
o
u
ld
a
ll
o
w
su
p
p
l
iers
a
n
d
c
o
n
su
m
e
rs
to
m
e
e
t
in
th
e
m
o
st
e
ff
ici
e
n
t
w
a
y
.
Ou
r
m
o
ti
v
a
ti
o
n
is
b
u
i
ld
i
n
g
a
“
f
e
a
tu
re
d
it
e
m
”
c
o
m
p
o
n
e
n
t
f
o
r
so
c
ial
-
m
e
d
ia
a
p
p
li
c
a
ti
o
n
s.
S
u
c
h
a
c
o
m
p
o
n
e
n
t
w
o
u
ld
p
ro
v
id
e
re
c
o
m
m
e
n
d
a
ti
o
n
s to
c
o
n
su
m
e
rs e
a
c
h
ti
m
e
th
e
y
lo
g
in
th
e
s
y
ste
m
.
Th
e
e
x
isti
n
g
s
y
ste
m
f
o
ll
o
w
s
e
it
h
e
r
c
o
ll
a
b
o
r
a
ti
v
e
f
il
terin
g
o
r
c
o
n
te
n
t
b
a
se
d
f
il
terin
g
.
Co
ll
a
b
o
ra
ti
v
e
f
il
terin
g
m
e
th
o
d
s
a
re
b
a
se
d
o
n
c
o
ll
e
c
ti
n
g
a
n
d
a
n
a
ly
z
in
g
a
larg
e
a
m
o
u
n
t
o
f
in
f
o
r
m
a
ti
o
n
o
n
u
se
r‟
s
b
e
h
a
v
io
u
rs,
a
c
ti
v
it
ies
o
r
p
re
f
e
r
e
n
c
e
s
a
n
d
p
re
d
icti
n
g
w
h
a
t
u
se
rs
w
il
l
li
k
e
b
a
se
d
o
n
th
e
ir
sim
il
a
rit
y
to
o
th
e
r
u
se
rs.
Co
n
ten
t
-
b
a
se
d
f
il
terin
g
m
e
th
o
d
s
a
re
b
a
se
d
o
n
a
d
e
sc
rip
ti
o
n
o
f
th
e
it
e
m
a
n
d
a
p
ro
f
il
e
o
f
th
e
u
se
r'
s
p
re
fe
re
n
c
e
.
B
o
th
o
f
th
e
se
m
e
th
o
d
s
re
q
u
i
re
in
p
u
t
f
ro
m
th
e
u
se
r
in
th
e
f
o
r
m
o
f
ra
ti
n
g
s
o
r
o
th
e
r
u
se
r'
s
li
k
e
s.
Bu
t
so
c
ial
c
o
n
ten
t
m
a
tch
in
g
tak
e
s
in
to
a
c
c
o
u
n
t
o
n
ly
th
e
u
se
r'
s
p
re
fe
re
n
c
e
s
a
n
d
a
lso
th
e
c
a
p
a
c
it
y
c
o
n
stra
in
ts.
F
o
r
e
a
c
h
it
e
m
'
t'
a
n
d
e
a
c
h
u
se
r
'
u
'
,
c
o
n
sid
e
r
c
o
n
stra
in
ts
o
n
th
e
m
a
x
i
m
u
m
n
u
m
b
e
r
o
f
e
d
g
e
s
th
a
t
t
a
n
d
u
c
a
n
p
a
rti
c
ip
a
te
i
n
th
e
m
a
tc
h
in
g
.
T
h
e
se
c
a
p
a
c
it
y
c
o
n
stra
in
ts
c
a
n
b
e
e
sti
m
a
ted
b
y
th
e
a
c
ti
v
it
y
o
f
e
a
c
h
u
se
r
a
n
d
th
e
re
lativ
e
f
re
q
u
e
n
c
y
w
it
h
w
h
ich
it
e
m
s
n
e
e
d
to
b
e
d
e
li
v
e
re
d
.
He
re
we
in
tro
d
u
c
e
th
e
c
o
n
c
e
p
t
c
a
ll
e
d
b
-
m
a
tch
in
g
g
o
a
l
is
to
f
in
d
a
m
a
t
c
h
in
g
th
a
t
sa
ti
sf
ie
s
a
ll
c
a
p
a
c
it
y
c
o
n
stra
i
n
ts
a
n
d
m
a
x
i
m
iz
e
s
th
e
to
tal
w
e
i
g
h
t
o
f
th
e
e
d
g
e
s
in
th
e
m
a
tch
in
g
.
T
h
e
re
su
lt
o
f
b
-
m
a
tch
in
g
is
th
e
se
t
o
f
so
n
g
s
th
a
t
a
re
to
b
e
re
c
o
m
m
e
n
d
e
d
to
t
h
e
u
se
r
b
a
se
d
o
n
h
is
li
k
e
s.
K
ey
w
o
r
d
:
B
-
m
atc
h
i
n
g
B
ig
d
ata
Had
o
o
p
Ma
p
R
ed
u
ce
B
ip
ar
tite g
r
ap
h
Co
p
y
rig
h
t
©
201
5
In
s
t
it
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Dr
.
P
ar
v
ath
i R,
Dep
ar
te
m
en
t o
f
C
o
m
p
u
ti
n
g
Sc
ien
ce
s
a
n
d
E
n
g
in
ee
r
i
n
g
,
VI
T
Un
iv
er
s
it
y
,
Van
d
alu
r
,
Kela
m
b
ak
k
a
m
R
o
a
d
,
C
h
en
n
ai,
T
am
il Na
d
u
6
0
0
1
2
7
.
E
m
ail:
p
ar
v
at
h
i.r
@
v
it.a
c.
i
n
1.
I
NT
RO
D
UCT
I
O
N
So
cial
m
ed
ia
in
g
en
er
al
e
x
h
ib
it
a
r
ich
v
ar
iet
y
o
f
in
f
o
r
m
atio
n
th
at
ca
n
b
e
b
o
th
s
tr
u
c
tu
r
ed
an
d
u
n
s
tr
u
ct
u
r
ed
f
r
o
m
d
if
f
er
e
n
t
s
o
u
r
ce
s
.
Su
c
h
t
y
p
e
o
f
d
ata
i
s
v
er
y
d
i
f
f
icu
l
t
to
p
r
o
ce
s
s
t
h
at
co
n
tain
s
t
h
e
b
illi
o
n
s
r
ec
o
r
d
s
o
f
m
illi
o
n
s
p
eo
p
le
in
f
o
r
m
at
io
n
th
at
i
n
cl
u
d
e
s
th
e
w
e
b
s
ales,
s
o
cial
m
ed
ia,
au
d
io
s
,
i
m
a
g
es
an
d
s
o
o
n
.
T
h
e
n
ee
d
o
f
b
ig
d
ata
co
m
es
f
r
o
m
th
e
B
i
g
C
o
m
p
a
n
ie
s
li
k
e
Y
ah
o
o
,
Go
o
g
le,
an
d
Face
b
o
o
k
etc
f
o
r
th
e
p
u
r
p
o
s
e
o
f
an
al
y
s
is
o
f
b
i
g
a
m
o
u
n
t
o
f
d
ata
w
h
ich
i
s
in
u
n
s
tr
u
ct
u
r
ed
f
o
r
m
.
Go
o
g
le
co
n
tai
n
s
t
h
e
lar
g
e
am
o
u
n
t
o
f
in
f
o
r
m
atio
n
s
o
t
h
er
e
is
t
h
e
n
ee
d
o
f
B
ig
Data
An
al
y
tic
s
t
h
at
is
t
h
e
p
r
o
ce
s
s
i
n
g
o
f
t
h
e
co
m
p
lex
a
n
d
m
as
s
iv
e
d
atasets
.
B
ig
d
ata
a
n
al
y
s
i
s
f
u
n
d
a
m
e
n
tall
y
tr
a
n
s
f
o
r
m
s
o
p
er
atio
n
al,
f
in
a
n
cial
a
n
d
co
m
m
er
cial
p
r
o
b
lem
s
t
h
at
w
er
e
p
r
ev
io
u
s
l
y
u
n
s
o
l
v
ab
le
with
i
n
ec
o
n
o
m
i
c
an
d
h
u
m
an
ca
p
ital
co
n
s
tr
ain
t
s
u
s
i
n
g
d
is
cr
et
e
d
ata
s
et
s
a
n
d
o
n
p
r
em
i
s
es
h
ar
d
w
ar
e.
Us
u
all
y
t
h
e
b
ig
co
m
p
lai
n
t i
n
s
o
cial
en
ter
p
r
is
e
is
t
h
e
lo
s
s
o
f
p
r
iv
ac
y
.
B
u
t th
i
s
is
th
e
s
u
r
f
ac
e
n
o
t th
e
r
ea
s
o
n
.
I
t is t
h
e
u
n
i
n
tel
lig
e
n
t
w
a
y
o
f
u
s
in
g
d
ata,
w
it
h
n
o
e
m
p
ath
y
a
n
d
n
o
d
ee
p
in
s
i
g
h
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
4
,
No
.
3
,
Sep
tem
b
er
2
0
1
5
:
1
0
9
–
1
1
6
110
B
ig
d
ata
is
th
e
e
x
p
r
ess
io
n
f
o
r
a
g
r
o
u
p
o
f
d
ata
s
ets
s
o
o
u
t
s
ized
an
d
m
u
lti
f
ac
eted
th
a
t
it
b
ec
o
m
es
d
if
f
ic
u
lt
to
p
r
o
ce
s
s
u
s
i
n
g
r
ea
d
il
y
av
ailab
le
d
atab
ase
m
a
n
ag
e
m
e
n
t
to
o
ls
o
r
tr
ad
itio
n
al
d
ata
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
.
B
ig
d
ata
r
eq
u
ir
es
ex
ce
p
t
io
n
al
tec
h
n
o
lo
g
ies
Ma
s
s
i
v
el
y
P
ar
allel
-
P
r
o
ce
s
s
in
g
(
MP
P
)
d
atab
ases
,
s
ea
r
ch
-
b
ased
ap
p
licatio
n
s
,
d
ata
-
m
i
n
in
g
g
r
id
s
,
d
i
s
tr
ib
u
ted
f
ile
s
y
s
te
m
s
,
d
is
tr
ib
u
ted
d
atab
ases
,
clo
u
d
b
ased
in
f
r
astru
ct
u
r
e
(
ap
p
licatio
n
s
,
s
t
o
r
ag
e
an
d
co
m
p
u
tin
g
r
eso
u
r
ce
s
)
an
d
th
e
I
n
ter
n
et
to
ef
f
icie
n
tl
y
p
r
o
ce
s
s
lar
g
e
q
u
an
tit
ies
o
f
d
ata
w
i
th
i
n
to
ler
ab
le
elap
s
ed
ti
m
e
s
.
B
ig
Dat
a
p
r
o
v
id
es
an
in
f
r
astr
u
ct
u
r
e
f
o
r
tr
an
s
p
ar
en
c
y
i
n
v
ar
io
u
s
i
n
d
u
s
tr
ies,
to
u
n
r
a
v
el
u
n
ce
r
tai
n
tie
s
s
u
ch
as
i
n
co
n
s
is
ten
t
co
m
p
o
n
e
n
t
p
er
f
o
r
m
a
n
ce
an
d
to
en
h
an
ce
t
h
e
ea
s
e
o
f
u
s
e.
T
h
e
m
o
s
t
w
ell
-
k
n
o
w
n
tech
n
o
lo
g
y
u
s
ed
f
o
r
B
ig
Data
is
Had
o
o
p
.
Had
o
o
p
is
a
f
r
ee
,
J
av
a
-
b
ased
p
r
o
g
r
a
m
m
in
g
f
r
a
m
e
w
o
r
k
t
h
at
s
u
p
p
o
r
ts
th
e
p
r
o
ce
s
s
in
g
o
f
lar
g
e
d
ata
s
ets
in
a
r
eliab
le,
s
ca
lab
le,
d
is
tr
ib
u
ted
co
m
p
u
ti
n
g
en
v
ir
o
n
m
en
t.
I
t
is
a
d
is
r
u
p
tiv
e
f
o
r
ce
in
th
e
tr
ad
itio
n
al
d
ata
m
an
a
g
e
m
e
n
t
s
p
ac
e.
I
t
is
p
ar
t
o
f
t
h
e
A
p
ac
h
e
p
r
o
j
ec
t
s
p
o
n
s
o
r
ed
b
y
th
e
A
p
ac
h
e
So
f
t
w
ar
e
F
o
u
n
d
atio
n
.
Had
o
o
p
w
a
s
i
n
s
p
ir
ed
b
y
Go
o
g
le
'
s
Ma
p
R
ed
u
ce
,
a
s
o
f
t
w
ar
e
f
r
a
m
e
wo
r
k
in
w
h
ich
an
ap
p
licatio
n
i
s
b
r
o
k
en
d
o
w
n
i
n
to
n
u
m
er
o
u
s
s
m
all
p
ar
ts
.
An
y
o
f
th
ese
p
ar
ts
(
a
ls
o
ca
lled
f
r
ag
m
e
n
ts
o
r
b
lo
ck
s
)
ca
n
r
u
n
o
n
an
y
n
o
d
e
in
th
e
cl
u
s
ter
.
A
p
ac
h
e
Had
o
o
p
ec
o
s
y
s
te
m
c
o
n
s
is
ts
o
f
t
h
e
Had
o
o
p
k
er
n
el,
Ma
p
R
ed
u
ce
,
t
h
e
Had
o
o
p
d
is
tr
ib
u
ted
f
i
le
s
y
s
te
m
(
HDFS)
an
d
a
n
u
m
b
er
o
f
r
elat
ed
p
r
o
j
ec
ts
s
u
ch
as
A
p
ac
h
e
Hi
v
e,
HB
ase
an
d
Z
o
o
k
ee
p
er
.
Fig
u
r
e
1
.
Had
o
o
p
A
r
ch
itect
u
r
e
As
Had
o
o
p
ca
n
b
e
h
o
s
ted
o
n
co
m
m
o
d
it
y
h
ar
d
w
ar
e
(
u
s
u
all
y
I
n
tel
P
C
o
n
L
i
n
u
x
w
i
th
o
n
e
o
r
2
C
P
U
an
d
a
f
e
w
T
B
o
n
HDD,
w
i
th
o
u
t
a
n
y
R
A
I
D
r
ep
licatio
n
tec
h
n
o
lo
g
y
)
,
it
allo
w
s
t
h
e
m
to
s
to
r
e
h
u
g
e
q
u
an
t
it
y
o
f
d
ata
(
p
eta
-
b
y
tes
o
r
ev
e
n
m
o
r
e)
at
v
er
y
lo
w
co
s
t
co
m
p
ar
e
d
to
th
e
o
th
er
s
y
s
te
m
s
.
T
h
e
p
r
o
b
lem
t
h
at
m
o
s
t
co
m
m
o
n
l
y
o
cc
u
r
s
i
n
ec
o
n
o
m
i
c
m
ar
k
et
s
,
lab
o
u
r
m
ar
k
ets,
i
n
t
er
n
et
ad
v
er
tis
i
n
g
,
an
d
else
w
h
er
e
is
th
e
m
atc
h
in
g
h
itc
h
.
Ma
tc
h
i
n
g
p
r
o
b
lem
s
ar
e
o
m
n
ip
r
esen
t.
I
n
th
i
s
p
ap
er
we
f
o
cu
s
o
n
a
n
ap
p
licatio
n
o
f
m
atc
h
in
g
in
s
o
cial
m
ed
ia.
Mu
s
ic
ian
s
ar
e
co
m
p
et
in
g
f
o
r
an
a
u
d
ien
ce
a
m
o
n
g
m
illi
o
n
s
o
f
o
t
h
er
s
tr
y
i
n
g
j
u
s
t
as
h
ar
d
.
An
d
it
‟
s
n
o
t
th
e
lis
ten
er
‟
s
f
a
u
lt
i
f
th
e
y
m
is
s
o
u
t
o
n
s
o
m
et
h
i
n
g
t
h
at
w
i
ll
ch
an
g
e
t
h
eir
li
v
es
–
th
e
s
e
d
a
y
s
,
an
y
o
n
e
ca
n
g
ai
n
ac
ce
s
s
to
a
lib
r
ar
y
o
f
o
v
er
1
5
m
illi
o
n
s
o
n
g
s
o
n
d
e
m
an
d
f
o
r
f
r
ee
.
R
ec
o
m
m
e
n
d
atio
n
tec
h
n
o
l
o
g
y
is
p
o
w
er
i
n
g
th
e
n
e
w
r
ad
io
an
d
th
er
e
is
a
ch
a
n
c
e
to
m
a
k
e
it
v
alu
ab
le
f
o
r
m
o
r
e
th
an
j
u
s
t th
e
to
p
5
p
er
ce
n
t o
f
m
u
s
icia
n
s
.
I
t is ass
u
m
ed
th
at
m
u
s
ic
r
ec
o
m
m
en
d
atio
n
u
s
u
al
l
y
m
ea
n
s
:
A
r
tis
t
o
r
s
o
n
g
s
imila
r
ity:
an
a
n
o
n
y
m
o
u
s
li
s
t
o
f
s
i
m
ilar
ite
m
s
is
r
ec
o
m
m
e
n
d
ed
.
T
h
is
is
s
ee
n
o
n
al
m
o
s
t
an
y
m
u
s
ic
s
er
v
ice.
W
ith
o
u
t
a
n
y
co
n
te
x
t,
t
h
is
i
s
j
u
s
t
a
s
u
g
g
esti
o
n
o
f
w
h
at
o
th
er
ar
ti
s
ts
o
r
s
o
n
g
s
ar
e
s
i
m
i
lar
to
th
e
o
n
e
y
o
u
ar
e
lo
o
k
in
g
at.
F
o
r
m
all
y
,
t
h
i
s
is
n
o
t tr
u
l
y
a
r
ec
o
m
m
en
d
atio
n
as t
h
er
e
is
n
o
u
s
e
r
m
o
d
el
i
n
v
o
l
v
ed
.
P
ers
o
n
a
liz
ed
r
ec
o
mme
n
d
a
tio
n
:
Giv
e
n
a
“u
s
er
m
o
d
el”
a
lis
t
o
f
s
o
n
g
s
o
r
ar
tis
t
s
t
h
at
th
e
s
er
v
ice
d
o
es
n
o
t th
i
n
k
th
e
u
s
er
k
n
o
w
s
ab
o
u
t
y
et.
P
la
ylis
t
g
en
era
tio
n
:
T
h
is
is
d
if
f
er
en
t
f
r
o
m
th
e
ab
o
v
e
t
w
o
i
n
a
w
a
y
th
a
t
th
e
u
s
er
r
ec
eiv
e
s
a
lis
t
o
f
ite
m
s
in
s
o
m
e
o
r
d
er
(
u
s
u
al
l
y
m
ea
n
t
to
b
e
lis
ten
ed
to
at
t
h
e
ti
m
e.
)
T
h
e
p
la
y
lis
t
ca
n
b
e
p
er
s
o
n
alize
d
(
f
r
o
m
a
u
s
er
m
o
d
el)
o
r
n
o
t,
an
d
it
ca
n
b
e
w
it
h
i
n
ca
talo
g
u
e.
T
h
e
p
lay
lis
t
s
h
o
u
ld
v
ar
y
ar
tis
ts
a
n
d
t
y
p
e
s
o
f
s
o
n
g
s
a
s
it
p
r
o
g
r
ess
es,
an
d
m
a
n
y
r
el
y
o
n
s
o
m
e
f
o
r
m
o
f
s
teer
i
n
g
o
r
f
ee
d
b
ac
k
(
th
u
m
b
s
u
p
,
s
k
ip
s
,
etc.
)
.
T
h
e
m
ain
a
m
az
i
n
g
a
n
d
u
s
e
f
u
l
f
ea
t
u
r
e
o
f
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
s
ar
e
t
h
at
it
ca
n
f
i
n
d
th
i
n
g
s
f
o
r
y
o
u
th
at
y
o
u
w
o
u
ld
n
‟
t
h
av
e
o
th
er
w
i
s
e
co
m
e
ac
r
o
s
s
.
S
o
cial
m
u
s
ic
r
ec
o
m
m
en
d
atio
n
s
e
n
ab
led
b
y
s
o
cial
n
et
w
o
r
k
s
ar
e
ex
tr
e
m
el
y
v
al
u
ab
le
i
n
m
u
s
ic
d
is
co
v
er
y
as t
h
e
y
ca
n
au
to
m
atica
ll
y
p
r
ed
ict
an
y
t
h
i
n
g
w
it
h
t
h
e
h
elp
o
f
e
x
p
licit
s
o
cial
s
ig
n
al
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
Song
R
ec
o
mme
n
d
a
tio
n
S
ystem
Usi
n
g
Ma
xima
l b
-
Ma
tch
in
g
(
Dee
p
a
S
)
111
1
.
1
.
L
it
er
a
t
ure
Su
rv
ey
T
h
e
q
u
alit
y
o
f
u
s
er
-
g
e
n
er
ated
co
n
te
n
t
v
ar
ies
d
r
ast
icall
y
f
r
o
m
e
x
ce
lle
n
t
to
ab
u
s
e
an
d
s
p
am
.
As
t
h
e
av
ailab
ilit
y
o
f
s
u
c
h
co
n
te
n
t
i
n
cr
ea
s
es,
th
e
tas
k
o
f
id
en
t
if
y
in
g
h
ig
h
-
q
u
ali
t
y
co
n
te
n
t
i
n
s
ites
b
ased
o
n
u
s
er
co
n
tr
ib
u
tio
n
i
n
s
o
cial
m
ed
ia
s
ites
b
ec
o
m
e
s
i
n
cr
ea
s
i
n
g
l
y
i
m
p
o
r
tan
t
as
d
e
s
cr
ib
ed
b
y
E
.
Ag
ich
tei
n
,
C
.
C
asti
l
lo
,
D.
Do
n
ato
,
A
.
Gio
n
is
,
an
d
G
.
Mish
n
e
in
Fin
d
i
n
g
h
i
g
h
-
q
u
a
lit
y
co
n
te
n
t
i
n
s
o
cial
m
ed
ia,
2
0
0
8
.
C
o
m
m
u
n
it
y
Qu
est
io
n
An
s
w
er
in
g
(
C
Q
A
)
h
as
e
m
er
g
ed
a
s
a
p
o
p
u
lar
f
o
r
u
m
f
o
r
u
s
er
s
to
p
o
s
e
q
u
esti
o
n
s
f
o
r
o
th
er
u
s
er
s
to
an
s
w
er
.
B
u
t
t
h
e
q
u
alit
y
o
f
t
h
e
in
f
o
r
m
atio
n
r
etr
ie
v
ed
f
r
o
m
t
h
ese
f
o
r
u
m
s
v
ar
ies
s
o
t
h
at
a
lar
g
e
q
u
a
n
tit
y
o
f
t
h
i
s
in
f
o
r
m
atio
n
ca
n
n
o
t
b
e
u
s
ed
a
s
m
en
tio
n
ed
i
n
L
ea
r
n
i
n
g
to
R
ec
o
g
n
ize
R
eliab
le
U
s
er
s
an
d
C
o
n
te
n
t
in
So
cial
Me
d
ia
w
it
h
C
o
u
p
led
Mu
tu
al
R
ein
f
o
r
ce
m
e
n
t,
J
B
ian
,
Y
L
i
u
,
D
Z
h
o
u
,
E
Ag
ic
h
tei
n
,
H
Z
h
a
in
2
0
0
9
.
T
h
ese
C
Q
A
s
f
o
r
m
t
h
e
b
asis
o
f
t
h
e
r
e
co
m
m
e
n
d
atio
n
s
y
s
te
m
s
w
h
er
e
in
t
h
e
p
ast
in
f
o
r
m
at
io
n
ca
n
b
e
u
s
ed
a
s
r
ef
er
e
n
ce
s
to
s
i
m
ilar
q
u
er
ies.
T
h
e
ta
s
k
o
f
d
is
co
v
er
in
g
s
i
m
ilar
o
b
j
ec
ts
w
ith
i
n
a
g
i
v
en
co
llectio
n
is
co
m
m
o
n
to
m
a
n
y
r
ea
l
w
o
r
ld
ap
p
licatio
n
s
a
n
d
m
ac
h
i
n
e
lear
n
i
n
g
p
r
o
b
lem
s
.
Ma
n
y
a
p
p
r
o
ac
h
es
ca
n
b
e
u
s
ed
to
f
i
n
d
th
e
s
i
m
ilar
o
b
j
ec
ts
an
d
o
n
e
s
u
c
h
ap
p
r
o
ac
h
is
s
i
m
ilar
it
y
s
el
f
-
j
o
in
a
s
p
r
o
p
o
s
ed
b
y
B
ar
ag
lia,
R
.
;
De
Fra
n
cisci
Mo
r
ales,
G.
;
L
u
cc
h
e
s
e,
C
i
n
Do
c
u
m
e
n
t
Si
m
ilar
it
y
Sel
f
-
J
o
in
w
it
h
Ma
p
R
ed
u
ce
,
2
0
1
0
.
As
d
e
f
in
ed
,
g
iv
en
a
co
llect
io
n
o
f
o
b
j
ec
ts
,
th
e
Si
m
ilar
it
y
Sel
f
J
o
in
p
r
o
b
lem
r
eq
u
ir
es
to
d
is
co
v
er
all
th
o
s
e
p
air
s
o
f
o
b
j
ec
ts
w
h
o
s
e
s
i
m
ilar
it
y
is
ab
o
v
e
a
u
s
er
d
ef
in
ed
t
h
r
es
h
o
ld
.
Ged
im
in
a
s
A
d
o
m
a
v
ici
u
s
,
A
le
x
a
n
d
er
T
u
zh
ilin
,
T
o
w
ar
d
t
h
e
Ne
x
t
Ge
n
er
atio
n
o
f
R
ec
o
m
m
e
n
d
er
S
y
s
te
m
s
:
A
Su
r
v
e
y
o
f
t
h
e
State
-
of
-
t
h
e
-
Ar
t
an
d
P
o
s
s
ib
le
E
x
te
n
s
io
n
s
,
2
0
0
5
,
h
av
e
ex
p
lai
n
ed
th
e
c
u
r
r
en
t
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
s
,
th
eir
f
u
n
c
tio
n
ali
t
y
a
n
d
li
m
itat
io
n
s
.
I
t
g
i
v
es
c
lear
in
s
ig
h
t
s
in
to
h
o
w
t
h
e
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
s
w
o
r
k
an
d
th
e
t
h
i
n
g
s
t
h
at
ca
n
b
e
d
o
n
e
to
i
m
p
r
o
v
e
t
h
e
p
r
o
ce
s
s
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
u
s
u
all
y
d
ea
ls
m
ain
l
y
w
it
h
t
h
e
s
o
n
g
p
r
ef
er
en
ce
s
o
f
a
s
o
cial
m
ed
ia
u
s
er
.
T
h
er
e
ar
e
h
u
n
d
r
ed
s
o
f
g
en
r
e
s
o
f
s
o
n
g
s
a
n
d
p
r
ef
er
en
ce
s
o
f
a
u
s
er
ca
n
n
o
t
b
e
r
estricte
d
to
a
f
e
w
.
So
ta
k
i
n
g
in
to
ac
co
u
n
t
t
h
e
v
ar
io
u
s
c
h
o
ices
o
f
t
h
e
u
s
er
o
u
r
s
y
s
te
m
w
i
ll
r
ec
o
m
m
e
n
d
s
o
n
g
s
th
a
t
ar
e
s
i
m
il
ar
.
Fin
d
in
g
o
u
t
th
e
r
ig
h
t
s
o
n
g
s
i
s
in
it
s
el
f
a
ted
io
u
s
ta
s
k
.
Her
e
th
e
m
il
lio
n
s
o
n
g
d
ataset
w
h
ich
co
n
s
i
s
ts
o
f
tr
ip
lets
ab
o
u
t
s
o
n
g
s
,
u
s
er
s
a
n
d
p
lay
co
u
n
t
f
r
o
m
s
e
v
er
al
w
eb
s
ite
s
lik
e
L
a
s
t.
f
m
i
s
u
s
ed
.
T
h
e
Millio
n
So
n
g
Data
s
et
w
as
cr
ea
ted
u
n
d
er
a
g
r
an
t
f
r
o
m
t
h
e
Natio
n
al
Scie
n
ce
Fo
u
n
d
atio
n
,
p
r
o
j
ec
t I
I
S
-
0
7
1
3
3
3
4
.
T
h
e
o
r
ig
in
al
d
ata
w
as
co
n
tr
ib
u
ted
b
y
T
h
e
E
ch
o
Nest,
as
p
ar
t
o
f
NSF
-
s
p
o
n
s
o
r
ed
GOAL
I
co
llab
o
r
atio
n
.
Millio
n
s
o
n
g
d
ataset
co
n
ta
in
s
s
o
n
g
s
b
ased
o
n
tag
s
b
u
t
th
e
n
t
h
er
e
ar
e
th
o
u
s
an
d
s
o
f
s
o
n
g
s
f
r
o
m
a
s
i
n
g
le
ta
g
,
all
o
f
w
h
ich
ca
n
'
t
b
e
r
ec
o
m
m
e
n
d
ed
.
Usi
n
g
J
SO
N
p
ar
s
er
th
e
d
ataset
w
ill
b
e
p
ar
s
ed
an
d
a
lis
t
o
n
s
o
n
g
s
b
a
s
ed
o
n
t
h
e
g
en
r
e
s
w
il
l
b
e
e
x
tr
ac
t
ed
.
T
h
en
u
s
in
g
t
h
e
co
n
ce
p
t o
f
b
-
m
a
tch
i
n
g
th
e
b
e
s
t so
n
g
w
o
u
ld
b
e
r
ec
o
m
m
e
n
d
ed
to
th
e
u
s
er
.
Fig
u
r
e
2
.
Ma
p
R
ed
u
ce
ar
ch
itec
tu
r
e
R
ec
o
m
m
e
n
d
er
s
y
s
te
m
s
t
y
p
ica
ll
y
p
r
o
d
u
ce
a
lis
t
o
f
r
ec
o
m
m
e
n
d
atio
n
s
i
n
o
n
e
o
f
t
w
o
w
a
y
s
-
th
r
o
u
g
h
co
llab
o
r
ativ
e
o
r
co
n
ten
t
-
b
ase
d
f
ilter
i
n
g
.
C
o
llab
o
r
ativ
e
f
ilte
r
in
g
ap
p
r
o
ac
h
es
b
u
ild
i
n
g
a
m
o
d
el
f
r
o
m
a
u
s
er
's
p
ast
b
eh
av
io
u
r
(
ite
m
s
p
r
ev
io
u
s
l
y
p
u
r
c
h
ased
o
r
s
elec
ted
an
d
/o
r
n
u
m
er
ical
r
atin
g
s
g
i
v
en
to
th
o
s
e
ite
m
s
)
as
w
e
ll
as
s
i
m
ilar
d
ec
is
io
n
s
m
ad
e
b
y
o
th
er
u
s
er
s
;
th
e
n
u
s
e
th
a
t
m
o
d
el
to
p
r
ed
ict
ite
m
s
(
o
r
r
atin
g
s
f
o
r
ite
m
s
)
t
h
at
t
h
e
u
s
er
m
a
y
h
a
v
e
a
n
i
n
ter
es
t
i
n
.
C
o
n
te
n
t
-
b
ased
f
ilter
in
g
ap
p
r
o
ac
h
es
u
til
ize
a
s
er
ie
s
o
f
d
is
cr
e
te
ch
ar
ac
ter
is
t
ics
o
f
an
ite
m
in
o
r
d
er
to
r
ec
o
m
m
e
n
d
ad
d
itio
n
al
ite
m
s
w
i
th
s
i
m
ilar
p
r
o
p
e
r
ties
.
C
o
llab
o
r
ativ
e
f
ilter
i
n
g
m
et
h
o
d
s
ar
e
b
ased
o
n
co
llectin
g
an
d
an
al
y
z
in
g
a
lar
g
e
a
m
o
u
n
t
o
f
i
n
f
o
r
m
atio
n
o
n
u
s
er
s
‟
b
e
h
av
io
u
r
s
,
ac
ti
v
itie
s
o
r
p
r
ef
er
en
ce
s
an
d
p
r
ed
ictin
g
w
h
a
t
u
s
er
s
w
ill
l
ik
e
b
ased
o
n
th
e
ir
s
i
m
ilar
it
y
to
o
th
er
u
s
er
s
.
C
o
llab
o
r
ativ
e
Fil
t
er
in
g
ar
e
b
ased
o
n
th
e
a
s
s
u
m
p
tio
n
th
at
p
eo
p
le
w
h
o
ag
r
ee
i
n
p
ast
w
ill
a
g
r
ee
in
f
u
tu
r
e
to
o
an
d
th
at
t
h
e
y
w
ill li
k
e
th
e
s
i
m
ilar
k
i
n
d
s
o
f
ite
m
s
a
s
th
e
y
li
k
ed
in
t
h
e
p
as
t.
C
o
n
te
n
t
-
b
ased
f
il
ter
in
g
m
e
th
o
d
s
ar
e
b
ased
o
n
a
d
escr
ip
tio
n
o
f
th
e
ite
m
a
n
d
a
p
r
o
f
ile
o
f
th
e
u
s
er
‟
s
p
r
ef
er
en
ce
.
I
n
p
ar
ticu
lar
,
v
ar
io
u
s
ca
n
d
id
ate
ite
m
s
ar
e
co
m
p
ar
ed
w
it
h
ite
m
s
p
r
ev
io
u
s
l
y
r
at
ed
b
y
th
e
u
s
er
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
4
,
No
.
3
,
Sep
tem
b
er
2
0
1
5
:
1
0
9
–
1
1
6
112
th
e
b
est
-
m
atch
i
n
g
ite
m
s
ar
e
r
e
co
m
m
e
n
d
ed
.
A
k
e
y
i
s
s
u
e
w
it
h
co
n
ten
t
-
b
ased
f
i
lter
in
g
i
s
w
h
eth
er
th
e
s
y
s
te
m
is
ab
le
to
lear
n
u
s
er
p
r
ef
er
en
ce
s
f
r
o
m
u
s
er
'
s
ac
tio
n
s
r
eg
ar
d
in
g
o
n
e
co
n
ten
t
s
o
u
r
ce
an
d
u
s
e
th
e
m
ac
r
o
s
s
o
th
er
co
n
ten
t
t
y
p
es.
W
h
en
th
e
s
y
s
te
m
i
s
li
m
ited
to
r
ec
o
m
m
e
n
d
in
g
co
n
te
n
t
o
f
t
h
e
s
a
m
e
t
y
p
e
as
th
e
u
s
er
i
s
alr
ea
d
y
u
s
i
n
g
,
th
e
v
alu
e
f
r
o
m
t
h
e
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
is
s
i
g
n
i
f
ica
n
tl
y
less
t
h
a
n
w
h
e
n
o
th
er
co
n
ten
t
t
y
p
e
s
f
r
o
m
o
th
er
s
er
v
ices c
a
n
b
e
r
ec
o
m
m
en
d
ed
.
B
o
th
o
f
th
ese
m
eth
o
d
s
r
eq
u
ir
e
in
p
u
t
f
r
o
m
th
e
u
s
er
in
t
h
e
f
o
r
m
o
f
r
ati
n
g
s
o
r
o
th
er
u
s
er
's
lik
es.
B
u
t
s
o
cial
co
n
ten
t
m
atc
h
i
n
g
ta
k
es
in
to
ac
co
u
n
t
o
n
l
y
th
e
u
s
er
'
s
p
r
ef
er
en
ce
s
an
d
also
th
e
ca
p
a
cit
y
co
n
s
tr
ain
t
s
.
Fo
r
ea
ch
ite
m
'
t
'
a
n
d
ea
ch
u
s
er
'u
'
,
co
n
s
id
er
co
n
s
tr
ai
n
ts
o
n
t
h
e
m
ax
i
m
u
m
n
u
m
b
er
o
f
ed
g
e
s
th
at
t
an
d
u
ca
n
p
ar
ticip
ate
in
th
e
m
atc
h
i
n
g
.
T
h
ese
ca
p
ac
it
y
co
n
s
tr
ain
t
s
ca
n
b
e
esti
m
ated
b
y
th
e
ac
tiv
it
y
o
f
ea
ch
u
s
er
an
d
t
h
e
r
elativ
e
f
r
eq
u
e
n
c
y
w
it
h
w
h
ich
ite
m
s
n
ee
d
to
b
e
d
eliv
er
ed
.
Her
e
w
e
in
tr
o
d
u
ce
th
e
co
n
ce
p
t
ca
lled
b
-
m
atc
h
i
n
g
w
h
o
s
e
g
o
al
is
to
f
in
d
a
m
atc
h
in
g
t
h
at
s
ati
s
f
ies
a
ll
ca
p
ac
it
y
co
n
s
tr
ain
ts
an
d
m
a
x
i
m
i
ze
s
t
h
e
to
tal
w
ei
g
h
t
o
f
th
e
ed
g
es in
t
h
e
m
atc
h
in
g
.
Ou
r
g
o
al
is
to
i
m
p
le
m
en
t
s
o
n
g
s
r
ec
o
m
m
e
n
d
er
s
y
s
te
m
f
o
r
t
h
e
s
o
cial
m
ed
ia
co
n
ten
t.
W
e
ar
e
g
iv
e
n
a
s
et
o
f
s
o
n
g
id
s
S=
{s1
,
.
.
.
,
s
n
},
w
h
ic
h
ar
e
to
b
e
d
eliv
er
ed
to
a
s
et
o
f
co
n
s
u
m
er
s
C
=
{c
1
,
.
.
.
,
cm
}.
Fo
r
ea
ch
cj
an
d
s
i,
w
e
ass
u
m
e
w
e
ar
e
ab
le
to
m
ea
s
u
r
e
t
h
e
in
ter
es
t
o
f
co
n
s
u
m
er
cj
in
s
o
n
g
s
i
w
i
th
a
p
o
s
itiv
e
w
ei
g
h
t
w
(
cj
,
s
i)
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
th
e
s
o
n
g
s
S
to
th
e
co
n
s
u
m
er
s
C
c
an
b
e
clea
r
l
y
s
ee
n
as
a
m
atc
h
i
n
g
p
r
o
b
le
m
o
n
t
h
e
b
ip
ar
tite
g
r
ap
h
w
i
th
n
o
d
es
S
an
d
C
,
an
d
ed
g
e
w
e
ig
h
t
s
w
(
s
i,c
j
)
.
I
n
o
r
d
er
to
av
o
id
th
at
ea
ch
co
n
s
u
m
er
c
j
r
ec
eiv
e
to
o
m
an
y
s
o
n
g
r
ec
o
m
m
en
d
atio
n
s
,
w
e
e
n
f
o
r
ce
a
ca
p
ac
it
y
co
n
s
tr
ai
n
t
b
(
cj
)
o
n
t
h
e
n
u
m
b
er
o
f
ite
m
s
t
h
at
ar
e
m
atc
h
ed
to
cj
.
S
i
m
i
lar
l
y
,
w
e
w
o
u
ld
li
k
e
to
a
v
o
id
t
h
e
s
ce
n
ar
io
w
h
e
n
o
n
l
y
a
f
e
w
s
o
n
g
s
(
e.
g
.
t
h
e
m
o
s
t
p
o
p
u
lar
o
n
es)
p
ar
ticip
ate
in
th
e
m
atch
in
g
.
T
o
th
is
en
d
,
w
e
in
tr
o
d
u
ce
a
ca
p
ac
ity
co
n
s
tr
ai
n
t b
(
s
i)
o
n
th
e
n
u
m
b
er
o
f
co
n
s
u
m
er
s
t
h
at
ea
ch
ite
m
s
i
is
m
atc
h
ed
to
.
T
h
is
v
ar
ian
t
o
f
th
e
m
atc
h
in
g
p
r
o
b
lem
i
s
w
ell
k
n
o
w
n
in
t
h
e
th
eo
r
etica
l
c
o
m
p
u
ter
s
cien
ce
co
m
m
u
n
it
y
a
s
th
e
b
−
m
atc
h
i
n
g
p
r
o
b
le
m
.
W
e
w
i
s
h
to
f
i
n
d
a
b
-
m
atch
in
g
o
f
m
ax
i
m
u
m
w
ei
g
h
t.
Fig
u
r
e
3
.
Sa
m
p
le
b
ip
ar
tite g
r
a
p
h
m
atc
h
i
n
g
b
et
w
ee
n
co
n
s
u
m
er
s
(
C
)
an
d
s
o
n
g
s
(
S)
2
.
1
.
b
-
M
a
t
ching
P
ro
ble
m
Giv
e
n
a
g
r
ap
h
G
=
(
V,
E
)
,
a
m
atch
i
n
g
M
i
n
G
is
a
s
et
o
f
p
air
w
i
s
e
n
o
n
-
ad
j
ac
en
t e
d
g
e
s
; th
a
t is,
n
o
t
w
o
ed
g
es s
h
ar
e
a
co
m
m
o
n
v
er
tex
.
A
v
er
te
x
i
s
m
atch
ed
(
o
r
s
at
u
r
ated
)
if
it i
s
a
n
e
n
d
p
o
in
t o
f
o
n
e
o
f
t
h
e
ed
g
e
s
i
n
t
h
e
m
atc
h
in
g
.
Ot
h
er
w
is
e
t
h
e
v
er
te
x
is
u
n
m
atc
h
ed
.
A
m
ax
i
m
al
m
atc
h
in
g
is
a
m
a
t
ch
in
g
M
o
f
a
g
r
ap
h
G
w
i
th
t
h
e
p
r
o
p
er
ty
th
a
t
if
an
y
ed
g
e
n
o
t
in
M
is
ad
d
ed
to
M,
it
is
n
o
lo
n
g
er
a
m
atc
h
in
g
,
th
a
t
is
,
M
is
m
a
x
i
m
al
if
it
is
n
o
t
a
p
r
o
p
er
s
u
b
s
et
o
f
an
y
o
th
er
m
atc
h
i
n
g
in
g
r
ap
h
G.
I
n
o
th
er
w
o
r
d
s
,
a
m
atc
h
i
n
g
M
o
f
a
g
r
ap
h
G
is
m
ax
i
m
al
i
f
ev
er
y
ed
g
e
in
G
h
a
s
a
n
o
n
-
e
m
p
t
y
in
ter
s
ec
tio
n
w
it
h
at
least o
n
e
e
d
g
e
in
M.
A
m
a
x
i
m
al
m
atch
in
g
ca
n
b
e
f
o
u
n
d
w
it
h
a
s
i
m
p
le
g
r
ee
d
y
alg
o
r
ith
m
.
A
m
a
x
i
m
al
m
atch
i
n
g
w
it
h
k
ed
g
es
is
a
n
ed
g
e
d
o
m
in
a
tin
g
s
et
w
it
h
k
ed
g
es.
C
o
n
v
er
s
el
y
,
if
w
e
ar
e
g
iv
e
n
a
m
in
i
m
u
m
e
d
g
e
d
o
m
i
n
ati
n
g
s
et
w
it
h
k
ed
g
es,
w
e
ca
n
co
n
s
tr
u
c
t
a
m
a
x
i
m
al
m
atc
h
in
g
w
it
h
k
ed
g
es
in
p
o
l
y
n
o
m
ial
ti
m
e.
T
h
er
ef
o
r
e
th
e
p
r
o
b
lem
o
f
f
i
n
d
i
n
g
a
m
i
n
i
m
u
m
m
a
x
i
m
al
m
atc
h
in
g
i
s
es
s
en
t
iall
y
eq
u
al
to
th
e
p
r
o
b
le
m
o
f
f
i
n
d
in
g
a
m
in
i
m
u
m
ed
g
e
d
o
m
i
n
ati
n
g
s
et.
Fo
r
th
e
s
o
n
g
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
,
b
-
m
a
tch
i
n
g
is
u
s
ed
to
f
i
n
d
th
e
li
s
t
o
f
s
o
n
g
s
f
o
r
ea
ch
co
n
s
u
m
er
b
ased
o
n
th
e
w
eig
h
t
o
f
t
h
e
s
i
m
ilar
it
y
o
f
t
h
e
m
atc
h
.
T
h
e
ca
p
ac
it
y
co
n
s
tr
ain
t
i
s
also
tak
e
n
i
n
to
ac
co
u
n
t
w
h
er
ei
n
ea
ch
co
n
s
u
m
er
ca
n
n
o
t
h
a
v
e
m
o
r
e
th
an
„
n
‟
r
ec
o
m
m
en
d
atio
n
s
an
d
ea
ch
s
o
n
g
ca
n
n
o
t
b
e
r
ec
o
m
m
en
d
ed
to
m
o
r
e
th
an
„
n
‟
co
n
s
u
m
er
s
.
Fro
m
t
h
e
m
illi
o
n
s
o
f
s
o
n
g
s
t
h
at
ar
e
av
ai
lab
le,
th
e
b
-
m
atch
in
g
p
r
o
b
le
m
ch
o
o
s
es
th
e
s
o
n
g
s
w
it
h
t
h
e
m
a
x
i
m
u
m
m
atc
h
i
n
g
w
ei
g
h
t.
F
u
r
th
er
el
i
m
in
at
io
n
s
ar
e
d
o
n
e
u
s
i
n
g
t
h
e
δ(
e)
f
u
n
cti
o
n
th
at
r
ed
u
ce
s
t
h
e
n
u
m
b
er
o
f
w
ea
k
l
y
co
v
er
ed
ed
g
es.
T
h
e
s
tac
k
M
R
al
g
o
r
ith
m
i
s
in
c
lu
s
iv
e
o
f
b
o
th
th
e
b
-
m
atc
h
in
g
t
h
e
r
e
m
o
v
i
n
g
o
f
w
ea
k
ed
g
e
s
b
y
p
u
s
h
i
n
g
an
d
p
o
p
p
in
g
th
e
ed
g
es i
n
to
th
e
s
ta
ck
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
Song
R
ec
o
mme
n
d
a
tio
n
S
ystem
Usi
n
g
Ma
xima
l b
-
Ma
tch
in
g
(
Dee
p
a
S
)
113
2
.
2
.
Sta
ck
-
M
R
Alg
o
rit
h
m
Fig
u
r
e
4
.
Stack
MR a
l
g
o
r
ith
m
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
r
esu
lt
g
en
er
ated
b
y
t
h
e
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
i
s
th
e
n
a
m
e
o
f
th
e
u
s
er
an
d
th
e
li
s
t
o
f
s
o
n
g
s
th
a
t
ca
n
b
e
r
ec
o
m
m
e
n
d
ed
to
th
at
u
s
er
.
T
h
e
s
tack
M
R
alg
o
r
it
h
m
h
a
s
h
i
g
h
p
er
f
o
r
m
a
n
ce
r
esu
lts
.
I
t
p
er
f
o
r
m
s
w
el
l
u
n
d
er
a
lar
g
e
n
u
m
b
er
o
f
ed
g
e
s
.
T
h
e
b
-
m
atch
in
g
al
g
o
r
i
th
m
w
o
r
k
s
b
etter
w
it
h
m
o
r
e
ed
g
e
s
an
d
p
r
o
d
u
ce
s
le
s
s
ad
d
itio
n
al
o
v
er
h
ea
d
.
T
h
is
b
eh
av
io
u
r
is
e
x
p
ec
ted
,
as
th
e
n
u
m
b
er
o
f
ed
g
es
i
n
cr
ea
s
e
t
h
e
al
g
o
r
ith
m
s
h
a
v
e
m
o
r
e
f
le
x
ib
ilit
y
.
Sin
ce
w
e
ad
d
ed
g
es
b
y
lo
w
er
i
n
g
t
h
e
ed
g
e
-
s
i
m
i
l
ar
it
y
th
r
es
h
o
ld
,
th
e
g
a
in
i
n
th
e
b
-
m
atc
h
i
n
g
v
al
u
e
ten
d
s
to
s
at
u
r
ate
a
n
d
s
o
it
r
eq
u
ir
es
le
s
s
n
u
m
b
er
o
f
m
ap
r
ed
u
ce
s
tep
s
.
T
h
e
s
tack
M
R
al
g
o
r
ith
m
p
r
o
p
o
s
es
to
its
n
eig
h
b
o
u
r
ed
g
e
s
c
h
o
s
en
u
n
i
f
o
r
m
l
y
at
r
an
d
o
m
an
d
s
o
th
e
n
u
m
b
er
o
f
ed
g
e
s
t
h
at
ar
e
c
h
o
s
en
b
ased
o
n
s
i
m
ilar
it
y
is
less
lead
i
n
g
to
ea
s
ier
p
r
o
ce
s
s
in
g
.
T
h
e
b
ip
ar
tite
g
r
ap
h
s
ca
n
b
e
r
ep
r
esen
ted
in
t
h
e
f
o
r
m
o
f
ad
j
ac
en
c
y
l
is
t
w
h
er
e
ea
ch
n
o
d
e
in
o
n
e
s
id
e
o
f
th
e
g
r
ap
h
co
n
tai
n
s
a
lis
t o
f
co
n
n
ec
ted
n
o
d
es in
t
h
e
o
th
er
s
id
e
o
f
th
e
g
r
ap
h
.
Fig
u
r
e
5
r
ep
r
esen
t
s
t
h
e
u
s
er
a
n
d
s
o
n
g
in
f
o
r
m
a
tio
n
in
th
e
f
o
r
m
o
f
ad
j
ac
en
c
y
lis
t.
I
t
d
ep
icts
th
e
l
is
t
o
f
u
s
er
w
h
o
h
av
e
l
is
te
n
ed
to
a
p
a
r
ticu
lar
s
o
n
g
.
Fig
u
r
e
5
.
A
d
j
ac
en
c
y
li
s
t o
f
s
o
n
g
s
an
d
u
s
er
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
4
,
No
.
3
,
Sep
tem
b
er
2
0
1
5
:
1
0
9
–
1
1
6
114
Ou
tp
u
t:
Fig
u
r
e
6
.
T
h
e
d
ata
o
b
tain
ed
f
r
o
m
M
illi
o
n
So
n
g
d
ataset
Fig
u
r
e
6
co
n
tai
n
s
th
e
d
ata
o
b
tain
ed
f
r
o
m
t
h
e
m
illi
o
n
s
o
n
g
d
atase
t.
T
h
e
m
illi
o
n
s
o
n
g
d
ataset
h
as
in
f
o
r
m
atio
n
ab
o
u
t t
h
e
li
s
t o
f
s
o
n
g
s
,
u
s
er
s
,
t
h
e
p
la
y
co
u
n
t,
ar
t
is
t in
f
o
r
m
a
tio
n
a
n
d
alb
u
m
i
n
f
o
r
m
atio
n
.
Fig
u
r
e
7
.
W
eig
h
ted
u
s
er
-
s
o
n
g
d
ata
Fig
u
r
e
7
s
h
o
w
s
th
e
u
s
e
r
,
s
o
n
g
s
an
d
th
e
a
s
s
o
ciate
d
w
ei
g
h
t in
f
o
r
m
at
io
n
o
b
tain
ed
f
r
o
m
th
e
m
i
llio
n
s
o
n
g
d
ataset.
Fig
u
r
e
8
.
User
,
s
o
n
g
s
an
d
th
e
w
ei
g
h
ted
av
er
ag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
Song
R
ec
o
mme
n
d
a
tio
n
S
ystem
Usi
n
g
Ma
xima
l b
-
Ma
tch
in
g
(
Dee
p
a
S
)
115
Fig
u
r
e
8
d
ep
icts
th
e
u
s
er
,
s
o
n
g
,
t
h
e
w
ei
g
h
ted
a
v
er
ag
e
a
n
d
t
h
e
δ(
e)
t
h
at
is
u
s
ed
to
r
e
m
o
v
e
th
e
w
ea
k
l
y
co
v
er
ed
ed
g
es.
Fig
u
r
e
9
.
R
ec
o
m
m
en
d
ed
So
n
g
s
f
o
r
a
p
ar
ticu
lar
u
s
er
Fig
u
r
e
9
d
ep
icts
th
e
f
i
n
al
r
ec
o
m
m
en
d
atio
n
b
ased
o
n
ea
ch
i
n
d
iv
id
u
al
u
s
er
.
4.
CO
NCLU
SI
O
N
T
h
e
p
r
o
b
lem
o
f
s
o
cial
co
n
ten
t
m
atc
h
i
n
g
is
in
v
es
tig
a
ted
u
s
i
n
g
Ma
p
R
ed
u
ce
a
lg
o
r
it
h
m
.
A
l
th
o
u
g
h
all
th
e
al
g
o
r
ith
m
s
ca
n
d
ea
l
w
ith
an
y
u
n
d
ir
ec
ted
g
r
ap
h
,
w
e
f
o
c
u
s
o
n
b
ip
ar
tite
g
r
ap
h
s
w
h
ich
ar
e
r
elev
an
t
i
n
o
u
r
ap
p
licatio
n
s
ce
n
ar
io
s
.
Fu
r
t
h
er
m
o
r
e
u
s
in
g
t
h
e
d
ata
f
r
o
m
th
e
s
o
cial
n
et
w
o
r
k
in
g
s
ites
m
a
k
es
th
e
e
n
d
r
esu
lt
m
o
r
e
r
ef
in
ed
.
A
ls
o
s
o
m
e
o
f
t
h
e
p
r
o
b
lem
s
in
t
h
e
r
ec
o
m
m
e
n
d
ati
o
n
s
y
s
te
m
s
li
k
e
cr
o
s
s
d
o
m
ai
n
r
ec
o
m
m
en
d
atio
n
s
,
co
n
s
tr
ain
t
b
ased
r
ec
o
m
m
e
n
d
atio
n
s
,
g
r
o
u
p
r
ec
o
m
m
e
n
d
atio
n
s
,
an
d
co
n
tex
t
a
w
ar
e
r
ec
o
m
m
en
d
atio
n
s
ar
e
n
o
t
d
ea
lt
w
it
h
.
Cro
s
s
-
Do
m
a
in
Rec
o
mm
e
nd
a
t
io
n:
C
u
r
r
en
t
s
y
s
te
m
s
ar
e
r
ea
ll
y
g
o
o
d
at
lear
n
in
g
p
r
ef
er
en
ce
s
in
o
n
e
d
o
m
ai
n
(
Sa
y
m
o
v
ie
s
)
,
b
u
t
th
e
s
a
m
e
alg
o
r
it
h
m
s
d
o
n
o
t
w
o
r
k
as
w
e
ll
in
o
th
er
d
o
m
ain
s
.
So
if
a
u
s
er
lik
es
a
p
ar
ticu
lar
g
e
n
r
e
o
f
s
o
n
g
s
w
h
a
t
d
o
es
it
h
a
v
e
to
s
a
y
ab
o
u
t
h
i
s
tast
e
i
n
m
o
v
ies?
T
h
ese
cr
o
s
s
-
d
o
m
ai
n
s
o
lu
tio
n
s
ca
n
b
e
d
ea
lt
w
it
h
i
n
th
e
f
u
tu
r
e.
Co
ns
t
ra
int
-
Do
m
a
i
n
Rec
o
mm
e
nd
a
t
io
n:
Mo
s
t
o
f
th
e
r
es
ea
r
ch
h
as
f
o
cu
s
s
ed
o
n
t
h
e
v
i
r
tu
al
g
o
o
d
s
s
u
c
h
as
m
o
v
ies
an
d
m
u
s
ic,
w
h
er
e
an
ite
m
ca
n
b
e
r
ec
o
m
m
en
d
ed
u
n
li
m
ited
n
u
m
b
er
o
f
ti
m
e
s
.
I
n
th
e
r
ea
l
w
o
r
ld
,
th
at
'
s
o
f
te
n
n
o
t t
h
e
ca
s
e.
C
o
n
s
i
d
er
r
estau
r
an
t
s
.
I
f
a
g
r
ea
t r
esta
u
r
an
t
is
r
ec
o
m
m
en
d
ed
to
m
o
r
e
p
eo
p
le
th
an
it c
a
n
h
an
d
le,
it
s
tr
u
g
g
les
to
co
p
e
u
p
w
it
h
t
h
e
lo
ad
an
d
its
s
er
v
ic
es
d
ec
lin
e.
Ho
w
ca
n
r
ec
o
m
m
e
n
d
atio
n
s
b
e
d
o
n
e
i
n
d
o
m
ai
n
s
w
h
er
e
th
e
ite
m
s
ar
e
li
m
ited
?
Her
e
th
e
r
ec
o
m
m
e
n
d
atio
n
b
ec
o
m
es
a
m
o
r
e
r
el
ax
ed
v
er
s
io
n
o
f
t
h
e
class
ic
m
atc
h
in
g
p
r
o
b
le
m
.
G
ro
up
Rec
o
mm
e
nd
a
t
io
n:
H
er
e,
th
e
b
asic
p
r
e
m
is
e
is
to
r
e
co
m
m
e
n
d
a
n
ite
m
to
a
g
r
o
u
p
o
f
p
eo
p
le
(
e.
g
.
)
g
o
in
g
to
a
m
o
v
ie
to
g
et
h
er
.
T
y
p
ical
m
o
d
els
co
m
p
u
te
i
n
d
iv
id
u
al
r
ec
o
m
m
e
n
d
atio
n
s
an
d
th
en
u
s
e
a
s
m
ar
t
w
a
y
to
co
m
b
in
e
t
h
e
m
.
B
u
t
o
f
ten
t
h
er
e
w
ill
b
e
d
is
ag
r
ee
m
en
ts
,
an
d
d
i
f
f
er
e
n
t
g
r
o
u
p
s
m
a
y
h
a
v
e
d
if
f
er
en
t
d
y
n
a
m
ics.
T
h
er
e
is
a
v
ast
li
ter
atu
r
e
o
n
co
n
s
en
s
u
s
an
d
v
o
tin
g
s
tr
ateg
ie
s
an
d
m
ec
h
an
i
s
m
s
th
at
co
u
ld
b
e
ex
p
lo
r
ed
,
as
w
ell
as
m
u
ltip
le
-
s
tag
ed
u
s
er
-
i
n
ter
ac
tio
n
p
ar
ad
ig
m
s
.
Co
nt
ex
t
-
a
w
a
re
Rec
o
m
m
e
nd
a
t
io
n:
W
ith
in
cr
ea
s
i
n
g
u
s
e
o
f
m
o
b
ile
d
ev
ice
s
,
u
s
er
s
el
f
-
d
is
clo
s
e
a
lo
t
o
f
co
n
tex
tu
al
i
n
f
o
r
m
atio
n
(
e.
g
.
)
lo
ca
tio
n
,
cu
r
r
en
t
ac
ti
v
it
y
e
t
c.
T
h
ese
d
ata
s
o
u
r
ce
s
g
i
v
e
r
ea
l
-
ti
m
e
i
n
f
o
r
m
atio
n
,
w
h
ic
h
ar
e
b
o
th
an
o
p
p
o
r
tu
n
i
t
y
an
d
c
h
allen
g
e
f
o
r
a
r
ec
o
m
m
en
d
er
s
y
s
te
m
.
Ho
w
to
in
co
r
p
o
r
ate
s
u
ch
f
i
n
e
g
r
ain
ed
i
n
f
o
r
m
atio
n
i
n
r
ec
o
m
m
en
d
er
m
o
d
els?
T
h
ese
ar
e
s
o
m
e
o
f
th
e
c
h
alle
n
g
e
s
th
a
t
ar
e
f
ac
ed
b
y
th
e
r
ec
o
m
m
e
n
d
atio
n
s
y
s
te
m
s
t
h
at
ar
e
y
et
to
b
e
o
v
er
co
m
e.
T
h
e
s
o
lu
tio
n
s
to
th
ese
ch
alle
n
g
es c
an
h
elp
i
m
p
r
o
v
e
th
e
b
u
s
i
n
e
s
s
ac
r
o
s
s
th
e
w
o
r
ld
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
4
,
No
.
3
,
Sep
tem
b
er
2
0
1
5
:
1
0
9
–
1
1
6
116
RE
F
E
R
E
NC
E
S
[1
]
G
ian
m
a
r
c
o
De
F
ra
n
c
isc
i
M
o
ra
les
,
A
risti
d
e
s
G
io
n
is
a
n
d
M
a
u
ro
S
o
z
io
,
“
S
o
c
ial
Co
n
ten
t
M
a
tch
i
n
g
in
M
a
p
Re
d
u
c
e
”,
IEE
E
tra
n
s.Co
m
p
,
V
o
l.
4
,
p
p
.
4
6
0
-
4
6
9
,
A
p
ril
2
0
1
1
.
[2
]
J.
De
a
n
a
n
d
S
.
G
h
e
m
a
w
a
t
,
“
M
a
p
Re
d
u
c
e
:
sim
p
li
f
ied
d
a
ta
p
ro
c
e
ss
in
g
o
n
larg
e
c
lu
ste
rs”
,
Co
mm
u
n
ica
ti
o
n
s
o
f
th
e
CACM
,
V
o
l.
51
,
No
.
1
,
p
p
.
1
0
7
–
1
1
3
,
2
0
0
8
.
[3
]
R.
Ba
ra
g
li
a
,
G
.
De
F
ra
n
c
isc
i
M
o
ra
les
,
a
n
d
C.
L
u
c
c
h
e
se
,
“
Do
c
u
m
e
n
t
sim
il
a
rit
y
se
l
f
-
jo
in
w
it
h
M
a
p
Re
d
u
c
e
”
,
I
n
ICDM
,
p
p
.
7
3
1
–
7
3
6
,
2
0
1
0
.
[4
]
Ore
il
ly
,
“
H
a
d
o
o
p
T
h
e
De
f
in
it
iv
e
G
u
id
e
”
,
3
rd
E
d
it
i
o
n
,
M
c
G
ra
w
-
Hil
l
,
2
0
1
2
.
[5
]
Ch
u
c
k
L
a
m
,
“
Ha
d
o
o
p
i
n
a
c
ti
o
n
”
,
Dre
a
m
T
e
c
h
p
re
ss
,
2
0
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.