I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
,
p
p
.
35
~
40
I
SS
N:
2252
-
8938
35
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
A
I
Preventing
O
nli
n
e Socia
l Dece
ptio
n using
Dec
eption
Ma
trix
Al
k
a
*
,
H
a
rj
o
t
K
a
ur*
*
D
e
p
a
rt
m
e
n
t
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
G
u
ru
Na
n
a
k
De
v
Un
iv
e
rsity
G
u
rd
a
sp
u
r
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
4
,
2
0
1
5
R
ev
i
s
ed
Feb
7
,
2
0
1
6
A
cc
ep
ted
Feb
2
5
,
2
0
1
6
T
h
e
o
rg
a
n
iza
ti
o
n
c
o
ll
a
b
o
ra
ti
o
n
is
v
e
r
y
i
m
p
o
rtan
t
f
o
r
th
e
su
c
c
e
ss
o
f
th
e
o
rg
a
n
iza
ti
o
n
.
T
h
e
p
e
rso
n
s
w
h
o
e
n
ter
i
n
to
th
e
o
rg
a
n
iza
ti
o
n
w
il
l
i
n
t
e
ra
c
t
w
it
h
th
e
o
t
h
e
r
m
e
m
b
e
rs
o
f
th
e
o
rg
a
n
iza
ti
o
n
.
T
h
e
re
e
x
ist
lea
d
e
rs
o
f
th
e
c
o
m
m
u
n
it
y
w
h
o
w
il
l
b
e
re
s
p
o
n
si
b
le
f
o
r
t
h
e
m
a
n
a
g
e
m
e
n
t
o
f
th
e
c
o
m
m
u
n
ica
ti
o
n
a
m
o
n
g
th
e
p
e
rso
n
s
w
it
h
in
th
e
o
rg
a
n
iza
ti
o
n
.
S
o
m
e
ti
m
e
s
th
e
in
f
o
r
m
a
ti
o
n
p
re
se
n
ted
b
y
th
e
n
e
w
p
e
rso
n
jo
in
i
n
g
th
e
c
o
m
m
u
n
it
y
is
n
o
t
c
o
rre
c
t.
T
h
a
t
in
f
o
r
m
a
ti
o
n
w
il
l
c
a
u
se
th
e
d
e
c
e
p
ti
o
n
o
v
e
r
th
e
n
e
t
wo
rk
.
In
th
e
p
u
rp
o
se
d
p
a
p
e
r
d
e
c
e
p
t
io
n
w
it
h
in
th
e
so
c
ial
m
e
d
ia
is
g
o
in
g
to
b
e
a
n
a
ly
z
e
d
.
De
c
e
p
ti
o
n
w
il
l
c
a
u
se
leg
io
n
o
f
p
ro
b
lem
s
a
n
d
so
m
e
ti
m
e
s
d
e
a
th
o
f
th
e
p
e
rso
n
w
h
o
is
d
e
c
e
iv
e
d
.
T
h
e
p
ro
p
o
se
d
p
a
p
e
r
su
g
g
e
sts th
e
m
e
c
h
a
n
ism
f
o
r
tac
k
li
n
g
su
c
h
d
e
c
e
p
ti
o
n
s
.
K
ey
w
o
r
d
:
C
o
llab
o
r
atio
n
I
n
ter
ac
t
I
n
f
o
r
m
a
tio
n
Dec
ep
tio
n
So
cial
m
ed
ia
Co
p
y
rig
h
t
©
2
0
1
6
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
l
k
a
,
Dep
ar
t
m
en
t
C
o
m
p
u
ter
Scie
n
c
e
an
d
E
n
g
i
n
ee
r
i
n
g
,
Gu
r
u
Na
n
a
k
Dev
U
n
i
v
er
s
it
y
G
u
r
d
asp
u
r
,
E
m
ail
:
al
k
at
h
ap
er
@
y
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
p
r
o
lif
er
atio
n
o
f
w
eb
b
ase
d
tech
n
o
lo
g
ies
h
a
s
b
ee
n
m
o
d
i
f
y
t
h
e
w
a
y
t
h
at
th
e
co
n
te
n
t
i
s
g
en
er
ated
an
d
ex
c
h
an
g
ed
th
r
o
u
g
h
th
e
i
n
t
er
n
et,
lead
in
g
to
p
r
o
lif
er
atio
n
o
f
s
o
cial
m
ed
ia
ap
p
licatio
n
s
a
n
d
s
er
v
ice
s
.
So
cial
m
ed
ia
lik
e
f
ac
eb
o
o
k
en
ab
le
cr
ea
tio
n
an
d
ex
ch
a
n
g
e
o
f
u
s
er
g
en
er
ated
co
n
ten
t
an
d
d
esig
n
o
f
r
an
g
e
o
f
I
n
ter
n
e
t
b
ased
ap
p
licatio
n
s
.
T
h
e
s
er
v
i
ce
s
p
r
o
v
id
ed
b
y
t
h
e
in
ter
n
et
h
av
e
i
n
cr
ea
s
ed
.
T
h
is
n
o
t
o
n
l
y
p
r
o
v
id
es
th
e
ex
tr
a
f
ac
ilit
ies
to
th
e
u
s
er
s
b
u
t
al
s
o
h
as
attr
ac
ted
l
ar
g
e
n
u
m
b
er
o
f
u
s
er
s
to
w
ar
d
s
t
h
e
in
ter
n
et
b
as
ed
tech
n
o
lo
g
ie
s
.
As
m
o
r
e
an
d
m
o
r
e
u
s
er
s
ar
e
in
ten
d
ed
to
w
ar
d
th
e
in
ter
n
e
t
s
o
d
o
es
th
e
s
o
cial
n
et
w
o
r
k
i
n
g
s
ites
.
I
n
to
d
a
y
’
s
en
v
ir
o
n
m
e
n
t
t
h
er
e
ex
is
ts
lar
g
e
n
u
m
b
er
o
f
s
o
cial
n
et
w
o
r
k
in
g
w
eb
s
i
tes.
T
h
ese
s
o
cial
n
et
w
o
r
k
in
g
w
eb
s
ite
s
u
s
es
lar
g
e
n
u
m
b
er
o
f
i
n
ter
ac
ti
v
e
m
ec
h
an
i
s
m
s
to
i
m
p
r
es
s
th
e
u
s
er
s
.
E
ac
h
s
o
cial
n
et
w
o
r
k
i
n
g
w
e
b
s
ite
n
ee
d
s
u
s
er
.
So
th
ese
s
o
cial
n
et
w
o
r
k
in
g
s
ites
d
o
n
o
t
u
s
e
a
n
y
s
o
lid
m
ec
h
an
i
s
m
o
f
a
u
t
h
e
n
ticatio
n
s
.
T
h
is
ca
n
ca
u
s
e
f
r
a
u
d
s
o
v
er
th
e
s
o
cial
n
et
w
o
r
k
i
n
g
s
ites
.
P
r
ev
io
u
s
w
o
r
k
o
n
d
ec
ep
tio
n
f
o
u
n
d
t
h
at
p
eo
p
le
in
g
e
n
er
al
l
i
e
r
o
u
ti
n
el
y
a
n
d
s
e
v
er
al
e
f
f
o
r
ts
h
a
v
e
b
ee
n
m
ad
e
to
d
etec
t
an
d
u
n
d
er
s
ta
n
d
th
e
d
ec
ep
tio
n
.
Dec
ep
tio
n
h
as
b
ee
n
u
s
ed
in
v
ar
io
u
s
co
n
tex
t
s
th
r
o
u
g
h
o
u
t
h
u
m
an
h
is
to
r
y
to
en
h
a
n
ce
attac
k
er
’
s
t
ac
tics
.
So
c
ial
m
ed
ia
p
r
o
v
id
e
n
e
w
e
n
v
ir
o
n
m
e
n
ts
an
d
tech
n
o
lo
g
ies
f
o
r
p
o
ten
tial
d
ec
eiv
er
s
.
T
h
er
e
ar
e
m
an
y
e
x
a
m
p
le
s
o
f
p
eo
p
le
b
ein
g
d
ec
eiv
ed
t
h
r
o
u
g
h
s
o
cial
m
ed
ia,
w
it
h
s
o
m
e
s
u
f
f
er
in
g
d
ev
astati
n
g
co
n
s
eq
u
e
n
ce
s
to
t
h
eir
p
er
s
o
n
al
liv
e
s
.
Dec
ep
tio
n
in
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
il
l
b
e
co
n
s
id
er
ed
th
e
d
elib
er
ate
atte
m
p
t to
m
is
lead
o
th
er
s
.
I
n
t
h
e
d
ec
ep
tio
n
th
e
p
e
r
s
o
n
w
h
o
is
d
ec
ei
v
ed
m
a
y
n
o
t
b
e
a
w
ar
e
o
f
th
e
f
ac
t
th
at
h
e/s
h
e
is
b
ec
o
m
in
g
d
ec
ei
v
ed
.
T
h
e
d
ec
ep
tio
n
w
ill
b
e
m
o
r
e
p
r
o
f
o
u
n
d
i
n
th
e
ar
ea
w
h
er
e
b
o
u
n
d
ar
y
b
et
w
ee
n
p
r
iv
ac
y
an
d
d
ec
eiv
i
n
g
o
th
er
s
i
s
n
o
t
clea
r
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
t
e
m
w
ill
b
e
u
s
ed
in
o
r
d
er
to
in
tr
o
d
u
ce
th
e
s
ec
u
r
it
y
m
ec
h
a
n
i
s
m
k
n
o
w
n
a
s
p
h
y
s
ica
l
ch
ec
k
m
ec
h
a
n
i
s
m
to
e
n
s
u
r
e
t
h
at
t
h
e
ac
co
u
n
t
o
n
th
e
s
o
cial
n
et
w
o
r
k
in
g
w
eb
s
ites
ca
n
o
n
l
y
b
e
cr
ea
ted
if
t
h
e
b
ac
k
g
r
o
u
n
d
c
h
ec
k
i
s
s
u
cc
ess
f
u
ll
y
p
e
r
f
o
r
m
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
35
–
40
36
Fig
u
r
e
1
.
in
ter
ac
tio
n
w
it
h
d
ec
e
p
tio
n
.
2.
M
E
T
H
O
D
S
P
a
r
ticip
a
n
ts
and
p
r
o
ce
d
u
r
e
A
m
es
s
ag
e
i
n
v
iti
n
g
p
eo
p
le
to
an
s
w
er
a
w
eb
-
b
ased
q
u
es
ti
o
n
n
air
e
w
a
s
p
o
s
ted
in
14
d
i
s
c
u
s
s
io
n
g
r
o
u
p
s
.
T
h
ese
d
is
c
u
s
s
io
n
g
r
o
u
p
s
w
er
e
r
a
n
d
o
m
l
y
s
elec
t
ed
f
r
o
m
t
h
r
ee
d
if
f
er
e
n
t
p
o
p
u
lar
I
s
r
ae
li
por
-
tals
.
T
h
ese
d
is
cu
s
s
io
n
g
r
o
u
p
s
v
ar
ied
in
co
n
te
n
t,
a
n
d
in
cl
u
d
e
d
b
o
th
g
r
o
u
p
s
th
at
d
is
cu
s
s
a
p
ar
ticu
lar
s
u
b
-
j
ec
t
(
e.
g
.
,
m
et
e
o
r
o
l
o
g
y
,
i
n
ter
n
et
c
u
lt
u
r
e,
or
n
e
w
a
g
e)
an
d
g
r
o
u
p
s
th
at
h
a
v
e
m
o
r
e
g
en
er
al,
u
n
s
p
ec
i
f
ic
t
o
p
-
ics
(
lik
e
a
g
r
o
u
p
f
o
r
30
+,
u
n
iv
e
r
s
it
y
s
tu
d
e
n
ts
,
or
m
a
le
s
)
.
A
to
tal
of
257
p
eo
p
le
r
etu
r
n
e
d
th
e
q
u
esti
o
n
n
a
ir
e;
68%
r
ep
o
r
ted
b
ein
g
f
e
m
ale.
T
h
e
r
ep
o
r
ted
m
ea
n
ag
e
w
as
30
(
r
an
g
e:
14
–
7
0
)
,
w
it
h
t
h
e
f
o
llo
w
i
n
g
d
i
s
tr
ib
u
-
t
io
n
:
17%
u
n
d
er
th
e
a
g
e
of
20,
44%
20
–
30,
27%
30
–
4
0
,
an
d
th
e
r
est
o
v
er
40.
Sev
en
t
y
-
n
in
e
p
er
ce
n
t
r
ep
o
r
ted
h
av
i
n
g
an
ac
ad
e
m
ic
ed
u
c
atio
n
(
s
t
u
d
e
n
t
s
in
h
ig
h
er
ed
u
ca
t
io
n
i
n
s
t
itu
tes
or
p
o
s
tg
r
ad
u
ate)
.
On
t
h
e
av
er
a
g
e,
p
eo
p
le
r
e
p
o
r
ted
s
p
en
d
in
g
3
.
5
h
p
er
d
a
y
o
n
lin
e
(
r
a
n
g
e
0
.
5
–
18
h
)
.
A
v
e
r
a
g
e
r
ep
o
r
ted
on
-
li
n
e
co
m
p
eten
ce
w
as
3
.
2
p
o
in
ts
(
o
u
t
of
5
)
;
64%
re
-
p
o
r
ted
h
ig
h
er
t
h
an
3
.
5
p
o
in
ts
in
th
is
m
ea
s
u
r
e.
A
t
w
o
-
p
ar
t
“
Dec
ep
tio
n
Qu
es
tio
n
n
ai
r
e”
w
as
co
n
-
s
tr
u
cte
d
.
T
h
e
f
i
r
s
t
p
a
r
t
in
clu
d
e
d
th
e
f
o
ll
o
w
in
g
q
u
es
-
tio
n
s
ask
ed
on
f
i
v
e
-
p
o
in
t
L
i
k
er
t
s
ca
le
s
(
w
h
er
e
1
=
n
o
t
p
r
e
v
a
l
en
t/n
ev
e
r
,
an
d
5
=
h
ig
h
l
y
p
r
ev
al
en
t
a
l
w
ay
s
:
(
1
)
In
y
o
u
r
o
p
i
n
i
o
n
,
to
w
h
a
t
ex
t
en
t
is
o
n
l
in
e
d
e
c
e
p
t
i
o
n
(
s
o
m
e
o
n
e
w
h
o
in
t
e
n
t
i
o
n
a
l
l
y
g
i
v
e
s
i
n
c
o
r
-
r
e
c
t
d
e
t
a
i
ls
a
b
o
u
t
h
im
s
e
l
f
)
p
r
e
v
a
l
e
n
t
?
(
2
)
H
a
v
e
y
o
u
e
v
e
r
d
e
c
eiv
e
d
o
n
l
in
e
?
(
3
)
H
a
v
e
y
o
u
ev
e
r
s
en
s
ed
t
h
at
s
o
m
e
o
n
e
h
as
d
e
ce
iv
e
d
y
o
u
o
n
l
in
e
?
Th
o
s
e
w
h
o
ad
-
m
it
t
e
d
to
h
a
v
i
n
g
d
e
c
eiv
e
d
o
n
l
i
n
e
at
l
e
a
s
t
o
n
c
e
w
e
r
e
a
s
k
e
d
to
m
a
r
k
a
l
l
is
s
u
es
a
b
o
u
t
w
h
i
ch
th
ey
g
av
e
in
c
o
r
r
e
c
t
i
n
f
o
r
m
a
t
i
o
n
w
h
e
n
d
e
c
e
i
v
i
n
g
s
o
m
e
o
n
e
o
n
l
i
n
e
.
T
h
e
i
s
s
u
es
w
e
r
e
a
g
e
,
s
e
x
,
r
e
s
i
d
e
n
c
e
,
m
a
r
i
t
a
l
s
t
a
tu
s
,
h
e
ig
h
t
,
w
eig
h
t
,
s
ex
u
a
l
p
r
e
f
e
r
e
n
c
e
,
h
e
a
l
th
s
t
a
tu
s
,
o
c
c
u
p
a
ti
o
n
,
a
s
al
i
en
t
p
e
r
s
o
n
al
ity
t
r
ai
t
,
or
s
o
m
e
th
in
g
e
l
s
e
(
i
f
t
h
e
l
as
t
o
p
ti
o
n
w
as
m
a
r
k
e
d
,
r
e
s
p
o
n
d
e
n
t
s
w
e
r
e
a
s
k
e
d
to
p
r
o
v
i
d
e
d
e
t
a
i
l
s
)
.
F
o
r
ea
c
h
of
th
e
is
s
u
es
m
a
r
k
e
d
,
r
e
s
p
o
n
d
e
n
t
s
w
e
r
e
a
s
k
e
d
to
m
a
r
k
w
h
a
t
m
o
ti
v
a
t
e
d
th
em
m
o
s
t
to
do
s
o
.
T
h
e
o
p
t
i
o
n
s
w
er
e
(
a
)
s
a
f
e
ty
r
e
a
s
o
n
s
,
(
b
)
i
d
e
n
ti
ty
p
l
a
y
,
(
c
)
ch
an
g
in
g
s
t
atu
s
,
an
d
(
d
)
i
n
c
r
e
a
s
e
d
a
t
t
r
a
c
tiv
e
n
e
s
s
.
N
ex
t
,
th
ey
w
e
r
e
a
s
k
e
d
if
th
ey
f
e
lt
th
at
o
t
h
e
r
s
s
u
s
p
e
c
t
e
d
it
w
as
f
a
ls
e
i
n
f
o
r
m
at
i
o
n
.
In
a
d
d
i
t
i
o
n
,
th
ey
w
e
r
e
a
s
k
e
d
to
m
a
r
k
t
h
e
em
o
-
t
i
o
n
s
t
h
a
t
t
h
e
y
e
x
p
e
r
i
e
n
c
e
d
w
h
i
l
e
d
e
c
e
i
v
i
n
g
o
n
l
i
n
e
.
E
m
o
t
i
o
n
s
i
n
c
l
u
d
e
d
t
e
n
s
i
o
n
,
e
x
c
i
t
e
m
e
n
t
,
e
n
j
o
y
m
en
t
,
s
t
r
e
s
s
,
o
d
d
n
e
s
s
,
a
n
d
“
an
o
th
e
r
f
e
el
in
g
.
”
T
h
e
s
ec
o
n
d
p
ar
t
of
t
h
e
q
u
esti
o
n
n
ai
r
e
ask
ed
f
o
r
d
e
m
o
g
r
ap
h
ic
d
etails
(
ag
e,
g
en
d
e
r
,
h
o
u
r
s
o
n
lin
e,
a
n
d
o
cc
u
p
atio
n
)
a
n
d
o
n
li
n
e
co
m
p
ete
n
ce
.
On
lin
e
co
m
p
ete
n
ce
w
a
s
an
a
v
er
ag
e
s
c
o
r
e
of
n
in
e
ite
m
s
th
at
t
h
e
r
esp
o
n
d
en
ts
w
er
e
ask
ed
to
r
ep
o
r
t
th
eir
co
m
p
ete
n
ce
w
it
h
(
w
h
er
e
“
1
”
m
ea
n
s
h
av
e
no
co
m
p
eten
ce
an
d
“
5
”
m
ea
n
s
b
ei
n
g
h
i
g
h
l
y
co
m
p
eten
t)
.
T
h
e
n
i
n
e
co
m
p
eten
ce
ite
m
s
w
er
e:
s
ea
r
ch
in
g
f
o
r
in
f
o
r
m
atio
n
o
v
er
t
h
e
I
n
ter
n
et,
p
ar
ticip
atin
g
i
n
as
y
n
ch
r
o
n
o
u
s
d
is
cu
s
s
io
n
g
r
o
u
p
s
,
p
ar
ticip
atin
g
in
C
h
at
r
o
o
m
s
,
d
o
w
n
lo
ad
i
n
g
m
u
s
ic
a
n
d
m
o
v
ie
s
,
u
s
i
n
g
e
-
m
ail,
u
s
i
n
g
o
n
lin
e
b
an
k
i
n
g
,
b
u
y
i
n
g
o
n
li
n
e,
p
ar
ticip
atin
g
i
n
o
n
lin
e
g
a
m
es,
an
d
u
s
i
n
g
o
n
li
n
e
d
atin
g
s
er
v
ices.
Si
n
ce
th
i
s
is
a
f
ir
s
t
atte
m
p
t
to
ex
p
l
o
r
e
o
n
lin
e
d
ec
ep
tio
n
a
m
o
n
g
I
s
r
ae
li
u
s
er
s
,
no
ex
ter
n
al
r
ef
er
en
ce
s
or
cr
iter
ia
w
er
e
av
ailab
le
to
test
th
e
ex
ter
n
a
l
v
alid
-
it
y
of
th
e
q
u
esti
o
n
n
ai
r
e
.
Sin
ce
p
ar
ticip
an
ts
ac
ted
an
o
n
y
m
o
u
s
ly
,
r
eli
ab
i
lity
(
p
r
etest
/p
o
s
t
test
s
tab
ili
t
y)
co
u
ld
n
o
t
be
test
ed
.
H
o
w
ev
e
r
,
as
w
ill
be
d
is
cu
s
s
ed
l
a
t
e
r
,
th
e
r
esu
l
ts
a
r
e
s
im
i
lar
to
th
o
s
e
r
e
p
o
r
t
e
d
f
o
r
o
th
er
p
o
p
u
latio
n
s
.
3.
RE
L
AT
E
D
WO
RK
Dec
ep
tio
n
w
ill ca
u
s
e
le
g
io
n
o
f
p
r
o
b
lem
s
.
So
m
e
p
r
o
b
lem
s
ar
e
s
ig
n
i
f
ica
n
t a
n
d
s
o
m
e
ar
e
j
u
s
t
f
o
r
m
atter
o
f
lau
g
h
.
T
h
e
w
o
r
k
h
a
s
b
ee
n
d
o
n
e
to
w
ar
d
th
e
d
ec
ep
tio
n
w
i
th
i
n
t
h
e
s
o
cial
m
ed
ia.
[
1
]
th
e
co
n
ce
p
t
o
f
d
ig
ital
d
ec
ep
tio
n
is
co
n
s
id
er
e
d
in
th
is
ca
s
e.
T
h
e
m
ec
h
an
is
m
o
f
d
ec
ep
tio
n
is
ca
u
s
ed
b
ec
au
s
e
h
u
m
a
n
b
ein
g
n
atu
r
e
is
to
lie.
T
h
er
e
ar
e
ef
f
o
r
ts
w
h
ic
h
ar
e
m
ad
e
i
n
o
r
d
er
to
d
etec
t
th
e
d
ec
ep
tio
n
w
it
h
i
n
th
e
s
o
cial
m
ed
ia.
B
u
t
n
o
s
o
li
d
m
ec
h
a
n
i
s
m
is
s
u
g
g
e
s
ted
.
So
a
n
al
y
s
i
s
o
f
all
t
h
e
tec
h
n
iq
u
es
wh
i
ch
ar
e
p
r
ese
n
t
w
ill
b
e
m
ad
e
in
t
h
is
p
ap
er
.
[
2
]
I
n
th
e
p
ast
d
ec
ad
e
s
o
cial
n
et
w
o
r
k
in
g
s
er
v
i
ce
s
(
SNS)
f
lo
o
d
ed
th
e
W
eb
.
T
h
e
n
atu
r
e
o
f
s
u
ch
s
ites
m
ak
e
s
id
en
t
it
y
d
ec
ep
tio
n
ea
s
y
,
o
f
f
er
i
n
g
a
q
u
ick
w
a
y
to
s
e
t
u
p
a
n
d
m
an
a
g
e
id
en
titi
e
s
,
an
d
t
h
e
n
co
n
n
ec
t
w
ith
an
d
d
ec
ei
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
P
r
ev
en
tin
g
On
lin
e
S
o
ci
a
l D
ec
ep
tio
n
u
s
in
g
Dec
e
p
tio
n
Ma
tr
ix
(
A
lka
)
37
o
th
er
s
.
Fi
g
h
ti
n
g
d
ec
ep
tio
n
r
eq
u
ir
es
a
co
o
r
d
in
ated
ap
p
r
o
ac
h
b
y
u
s
er
s
a
n
d
d
ev
elo
p
er
s
to
e
n
s
u
r
e
d
etec
tio
n
a
n
d
p
r
ev
en
tio
n
.
T
h
is
ar
ticle
id
en
tif
ie
s
t
h
e
m
o
s
t
p
r
ev
alen
t
ap
p
r
o
ac
h
es
in
d
etec
tin
g
a
n
d
p
r
ev
en
ti
n
g
id
e
n
tit
y
d
ec
ep
tio
n
(
f
r
o
m
b
o
th
a
u
s
er
'
s
an
d
d
ev
e
lo
p
er
'
s
p
er
s
p
ec
ti
v
e)
,
ev
al
u
ati
n
g
t
h
eir
ef
f
icie
n
c
y
,
an
d
p
r
o
v
id
i
n
g
r
ec
o
m
m
e
n
d
atio
n
s
to
h
elp
er
ad
icate
th
is
is
s
u
e.
[
3
]
as
in
ter
n
et
is
b
ec
o
m
i
n
g
m
o
r
e
ex
p
o
s
ed
to
th
e
u
s
er
s
,
s
o
d
o
es
th
e
v
u
l
n
er
ab
ilit
ies.
T
h
er
e
ex
is
ts
w
id
e
v
er
it
y
o
f
u
s
er
s
o
v
er
th
e
in
ter
n
et.
T
h
e
in
te
n
s
io
n
o
f
t
h
e
u
s
er
s
w
ill
n
o
t
b
e
ce
r
tain
.
So
th
e
p
er
s
o
n
w
it
h
t
h
e
w
r
o
n
g
i
n
ten
s
io
n
m
a
y
ca
u
s
e
th
e
p
r
o
b
lem
o
v
er
th
e
o
n
li
n
e
s
o
cial
m
ed
ia.
T
h
is
d
ec
ep
tio
n
is
an
al
y
ze
d
w
it
h
in
th
is
p
ap
er
.
[
4
]
W
h
at
m
ak
e
s
d
ec
ep
tiv
e
attac
k
s
o
n
s
o
cial
m
ed
ia
p
ar
ticu
lar
l
y
v
ir
u
le
n
t
i
s
th
e
lik
el
ih
o
o
d
o
f
a
co
n
tag
io
n
ef
f
ec
t,
w
h
er
e
a
p
er
p
etr
ato
r
tak
es
ad
v
a
n
tag
e
o
f
th
e
co
n
n
ec
tio
n
s
a
m
o
n
g
p
eo
p
le
to
d
ec
eiv
e
th
e
m
.
T
o
e
x
a
m
in
e
t
h
i
s
,
th
e
c
u
r
r
en
t
s
tu
d
y
ex
p
er
i
m
e
n
tal
l
y
s
ti
m
u
late
s
a
p
h
is
h
i
n
g
t
y
p
e
attac
k
,
ter
m
ed
as
f
ar
ci
n
g
,
o
n
Face
b
o
o
k
u
s
er
s
.
Far
cin
g
attac
k
s
o
cc
u
r
in
t
w
o
s
tag
e
s
:
a
f
ir
s
t
s
ta
g
e
w
h
er
e
p
h
is
h
er
s
u
s
e
a
p
h
o
n
y
p
r
o
f
ile
to
f
r
ien
d
v
icti
m
s
,
an
d
a
s
ec
o
n
d
s
ta
g
e,
w
h
er
e
p
h
is
h
er
s
s
o
lic
it
p
er
s
o
n
al
i
n
f
o
r
m
atio
n
d
ir
ec
tl
y
f
r
o
m
v
icti
m
s
.
I
n
t
h
e
p
r
esen
t
s
t
u
d
y
,
clo
s
e
to
o
n
e
in
f
iv
e
r
esp
o
n
d
e
n
ts
f
ell
v
ic
ti
m
to
th
e
f
ir
s
t
s
tag
e
attac
k
an
d
o
n
e
in
ten
f
e
ll
v
icti
m
to
th
e
s
ec
o
n
d
s
tag
e
attac
k
.
I
n
d
i
v
id
u
al
s
f
e
ll
v
icti
m
to
a
lev
el
1
attac
k
b
ec
au
s
e
t
h
e
y
r
elied
p
r
im
ar
il
y
o
n
t
h
e
n
u
m
b
er
o
f
f
r
i
en
d
s
o
r
th
e
p
ict
u
r
e
o
f
th
e
r
eq
u
ester
as a
h
eu
r
i
s
tic
c
u
e
a
n
d
m
a
d
e
s
n
ap
j
u
d
g
m
en
t
s
.
Victi
m
s
a
ls
o
d
e
m
o
n
s
tr
ated
a
h
er
d
m
e
n
tal
it
y
,
g
r
a
v
itati
n
g
to
a
p
h
is
h
er
w
h
o
s
e
p
ag
e
s
h
o
w
ed
m
o
r
e
co
n
n
ec
t
io
n
s
.
Su
c
h
p
r
o
f
iles
ca
u
s
ed
a
n
u
p
w
ar
d
in
f
o
r
m
atio
n
ca
s
ca
d
e,
w
h
er
e
ea
ch
v
icti
m
at
tr
ac
ted
m
a
n
y
m
o
r
e
v
icti
m
s
t
h
r
o
u
g
h
a
s
o
cial
co
n
ta
g
io
n
e
f
f
ec
t.
I
n
d
iv
id
u
al
s
r
ec
eiv
i
n
g
a
le
v
el
2
in
f
o
r
m
atio
n
r
eq
u
est
o
n
Fac
eb
o
o
k
p
er
ip
h
er
all
y
f
o
cu
s
ed
o
n
th
e
s
o
u
r
ce
o
f
th
e
r
eq
u
est
b
y
u
s
in
g
t
h
e
s
en
d
er
’
s
p
ictu
r
e
in
t
h
e
m
es
s
a
g
e
as
a
cr
ed
ib
ilit
y
cu
e.
[
5
]
T
h
e
in
cr
ea
s
ed
u
s
e
o
f
e
m
er
g
i
n
g
d
i
g
ital
p
lat
f
o
r
m
s
as
n
e
w
to
o
ls
i
n
co
m
m
u
n
ica
tio
n
h
as
b
ec
o
m
e
an
in
teg
r
al
p
ar
t
o
f
b
u
s
i
n
ess
ac
tiv
ities
a
n
d
th
e
s
o
c
ial
liv
e
s
o
f
m
a
n
y
i
n
d
i
v
id
u
al
s
.
Giv
e
n
t
h
e
I
n
ter
n
et’
s
v
u
l
n
er
ab
l
e
d
esig
n
,
h
o
w
e
v
er
,
th
e
r
ap
id
g
r
o
w
t
h
o
f
o
n
l
in
e
d
e
ce
p
tio
n
p
o
s
es
an
ex
tr
e
m
el
y
s
er
io
u
s
p
r
o
b
lem
,
a
n
d
th
er
e
is
s
till
lit
tle
s
c
h
o
lar
l
y
w
o
r
k
o
n
t
h
i
s
is
s
u
e.
Us
in
g
o
n
li
n
e
d
ec
ep
tio
n
ca
s
es
f
r
o
m
T
ai
w
an
,
th
e
a
u
th
o
r
s
u
n
d
er
to
o
k
t
h
e
cu
r
r
en
t
s
t
u
d
y
w
i
th
a
t
w
o
f
o
ld
o
b
j
ec
tiv
e:
(
1
)
to
in
v
esti
g
ate
t
h
e
d
is
tr
ib
u
tio
n
an
d
p
atter
n
s
o
f
d
ec
ep
tio
n
tactics,
an
d
(
2
)
to
test
h
y
p
o
t
h
eses
ab
o
u
t
h
o
w
th
e
id
e
n
tit
y
o
f
a
p
o
ten
tial
v
icti
m
a
n
d
th
e
p
u
r
p
o
r
ted
id
en
tit
y
o
f
t
h
e
d
ec
eiv
er
af
f
ec
t
t
h
e
s
elec
tio
n
o
f
a
s
p
ec
if
ic
d
ec
ep
t
io
n
tactic.
T
h
e
y
f
o
u
n
d
t
h
at
t
h
e
s
elec
tio
n
o
f
d
ec
ep
tio
n
tac
ti
cs
is
s
ig
n
i
f
ica
n
tl
y
in
f
lu
e
n
ce
d
b
y
t
h
e
ch
ar
ac
ter
i
s
tics
o
f
t
h
e
d
ec
eiv
er
s
a
n
d
t
h
e
ir
tar
g
ets.
I
m
p
licat
io
n
s
o
f
t
h
eir
r
esu
lts
ar
e
al
s
o
d
is
cu
s
s
ed
.
Ke
y
w
o
r
d
s
:
E
lectr
o
n
ic
co
m
m
er
ce
,
o
n
li
n
e
d
ec
ep
t
io
n
,
d
ec
ep
tio
n
tac
tics
,
co
n
te
n
t
an
al
y
s
is
,
lo
g
i
s
tic
r
eg
r
ess
io
n
.
[
6
]
T
h
e
u
n
k
n
o
w
n
an
d
th
e
i
n
v
is
ib
le
e
x
p
lo
it
th
e
u
n
w
ar
y
a
n
d
th
e
u
n
in
f
o
r
m
ed
f
o
r
illi
cit
f
in
a
n
cial
g
ai
n
an
d
r
ep
u
tatio
n
d
a
m
a
g
e.
Fro
m
t
h
e
ab
o
v
e
w
e
h
a
v
e
a
n
al
y
ze
d
th
a
t
t
h
e
p
r
ev
io
u
s
w
o
r
k
d
o
es
n
o
t
co
n
ce
n
tr
ate
in
en
s
u
r
i
n
g
a
s
tr
o
n
g
b
ac
k
g
r
o
u
n
d
ch
ec
k
m
ec
h
a
n
i
s
m
in
o
r
d
er
to
en
s
u
r
e
th
at
u
s
er
w
it
h
m
o
lli
f
ied
i
n
ten
s
io
n
s
h
o
u
l
d
n
o
t
ab
le
to
cr
ea
te
ac
co
u
n
t
o
v
er
th
e
s
o
cial
m
ed
ia
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
w
ill
s
u
g
g
es
t
a
s
tr
o
n
g
b
ac
k
g
r
o
u
n
d
ch
ec
k
m
ec
h
a
n
i
s
m
to
en
s
u
r
e
th
at
t
h
e
d
ec
ep
tio
n
o
v
er
th
e
s
o
cial
m
ed
ia
ca
n
b
e
r
ed
u
ce
d
4.
P
RO
P
O
SE
D
M
O
DE
L
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
w
ill
g
o
i
n
g
to
cr
ea
te
s
y
s
te
m
in
w
h
ic
h
t
h
e
in
f
o
r
m
atio
n
p
r
ese
n
ted
b
y
t
h
e
u
s
er
w
ill
b
e
p
ass
ed
th
r
o
u
g
h
th
e
f
i
lter
.
T
h
at
f
ilter
w
i
ll
v
er
if
y
t
h
e
i
n
f
o
r
m
atio
n
p
r
ese
n
ted
b
y
th
e
u
s
er
.
I
n
ca
s
e
t
h
e
in
f
o
r
m
atio
n
p
r
ese
n
ted
b
y
th
e
u
s
er
is
f
alse
t
h
e
n
leg
al
ac
tio
n
ca
n
b
e
tak
en
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
w
ill
en
s
u
r
e
t
h
at
th
e
d
ec
ep
tio
n
o
v
er
t
h
e
n
et
w
o
r
k
ca
n
b
e
r
ed
u
ce
d
.
W
e
w
il
l
i
n
t
r
o
d
u
ce
th
e
co
n
ce
p
t
o
f
j
ai
l.
I
f
t
h
e
p
er
s
o
n
lie
s
t
h
e
n
th
e
p
er
s
o
n
ac
co
u
n
t
w
i
ll
b
e
s
ea
led
.
T
h
e
p
er
s
o
n
w
ill
b
e
p
u
n
is
h
ed
in
ca
s
e
o
f
d
ec
ep
tio
n
.
T
h
e
d
ec
ep
tio
n
m
atr
ix
is
cr
ea
ted
in
o
r
d
er
to
v
er
if
y
wh
eth
er
p
er
s
o
n
i
s
d
ec
ep
tiv
e
o
r
n
o
t.
Set
o
f
p
ar
a
m
eter
s
ar
e
i
n
clu
d
ed
w
it
h
i
n
th
e
d
ec
ep
tiv
e
m
atr
i
x
.
A
ll t
h
e
p
ar
am
eter
s
i
f
s
u
cc
es
s
f
u
l
l
y
s
a
tis
f
ied
th
en
t
h
e
p
er
s
o
n
i
s
n
o
t d
ec
ep
ti
v
e.
T
h
e
s
tr
u
ct
u
r
e
o
f
th
e
d
ec
ep
tio
n
m
atr
i
x
is
a
s
f
o
ll
o
w
s
T
ab
le
1
: Sh
o
w
i
n
g
th
e
Dec
ep
ti
o
n
Ma
tr
ix
Pho
n
e
N
o
E
-
M
a
i
l
S
c
h
o
o
l
C
o
l
l
e
g
e
D
e
c
e
p
t
i
o
n
1
1
1
1
F
a
l
s
e
1
0
1
1
Tr
u
e
1
1
0
0
T
r
u
e
0
0
0
0
T
r
u
e
1
1
1
1
F
a
l
s
e
1
’
s
i
n
th
e
d
ec
ep
tio
n
m
atr
i
x
in
d
icate
s
t
h
at
co
r
r
esp
o
n
d
in
g
co
n
d
itio
n
is
s
ati
s
f
ied
a
n
d
0
’
s
i
n
t
h
e
d
ec
ep
tio
n
m
a
tr
i
x
in
d
icate
s
t
h
at
co
r
r
esp
o
n
d
in
g
c
o
n
d
itio
n
is
n
o
t
s
atis
f
ied
.
T
h
e
f
ailu
r
e
o
f
e
v
e
n
s
i
n
g
le
p
ar
a
m
ete
r
w
ill
r
esu
lt
i
n
th
e
d
ec
ep
tiv
e
ag
en
t d
ec
lar
atio
n
.
T
h
is
m
atr
i
x
w
ill b
e
cr
itical
in
d
e
ter
m
i
n
atio
n
o
f
f
air
an
d
d
ec
ep
ti
v
e
ag
e
n
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
35
–
40
38
T
h
e
alg
o
r
ith
m
f
o
r
th
e
s
a
m
e
w
il
l b
e
as f
o
llo
w
s
A
l
g
o
C
h
ec
k
(
)
//
T
h
is
al
g
o
r
ith
m
b
u
ild
a
n
e
t
w
o
r
k
in
w
h
ich
in
f
o
r
m
at
io
n
is
r
ec
eiv
ed
f
r
o
m
t
h
e
u
s
er
(
I
u)
an
d
th
e
n
v
alid
atio
n
m
ec
h
an
i
s
m
v
er
i
f
y
t
h
e
d
ata
1)
R
ec
o
r
d
L
en
g
t
h
o
f
th
e
R
ec
o
r
d
(
R
f
)
in
I
.
2)
L
o
o
p
u
n
ti
l I
>0
a)
Ma
k
e
u
s
er
p
ass
th
r
o
u
g
h
t
h
e
s
e
r
ies o
f
Qu
e
s
tio
n
s
(
Q)
.
b)
I
f
I
n
Valid
(
Q)
th
e
n
B
1
)
Dec
lar
e
u
s
er
f
alsi
f
i
y
(
F)
an
d
r
etu
r
n
E
ls
e
B
2
)
Go
to
c
E
n
d
if
c)
P
er
f
o
r
m
B
ac
k
g
r
o
u
n
d
(
B
)
C
h
ec
k
d)
I
f
I
s
Valid
(
B
)
th
en
D1
)
Dec
lar
e
u
s
er
Valid
an
d
g
o
to
s
tep
e.
E
ls
e
D2
)
Dec
lar
e
u
s
er
in
v
alid
.
E
n
d
o
f
if
e)
I
=I
-
1
E
n
d
L
o
o
p
3)
Sto
p
T
h
e
ab
o
v
e
alg
o
r
ith
m
s
u
g
g
es
ts
th
at
t
h
e
u
s
er
h
a
s
to
g
o
t
h
r
o
u
g
h
s
er
ies o
f
s
tep
s
b
ef
o
r
e
u
s
er
w
il
l
b
e
ab
le
to
cr
ea
te
ac
c
o
u
n
t
o
v
er
th
e
n
et
w
o
r
k
.
T
h
e
q
u
esti
o
n
n
air
es
ar
e
also
u
s
ed
s
o
th
at
v
alid
it
y
o
f
th
e
u
s
er
ca
n
b
e
v
er
i
f
ied
.
5.
RE
SU
L
T
S
T
h
e
f
o
llo
w
i
n
g
tab
le
s
h
o
w
s
a
g
e
w
i
s
e
d
ec
ep
tio
n
w
h
ic
h
o
cc
u
r
s
o
v
er
th
e
s
o
cial
n
e
t
w
o
r
k
li
k
e
f
a
ce
b
o
o
k
.
A
GE
AND
I
NT
E
R
NE
T
C
OM
P
E
T
E
NC
Y
DI
FF
E
R
E
N
C
E
S
IN
DI
FF
E
R
E
NT
I
SS
UE
S
OF
DE
C
E
P
T
I
ON
T
ab
le
2
: Sh
o
w
i
n
g
Dec
ep
tio
n
Ag
e
w
is
e
I
n
tern
et
co
mp
e
ten
cy
A
g
e
d
iffer
en
ce
s
d
iffer
en
ce
s
F
r
eq
u
en
cy
of
u
s
e
Sex
No
d
if
f
er
e
n
ce
No
d
if
f
er
e
n
ce
Fre
q
u
en
t
>
I
n
f
r
eq
u
e
n
t,
y
2
(
1
)
=
1
7
.
6
9
,
p
<
0
.
0
0
1
Ag
e
Y
o
u
n
g
e
r
>
Old
er
C
o
m
p
ete
nt
>
No
n
-
Fre
q
u
en
t
>
I
n
f
r
e
q
u
en
t
,
y
2
(
3
)
=
9
.
7
5
,
p
<
0
.
0
5
co
m
p
ete
n
t,
y
2
(
1
)
=
7
.
2
7
,
y
2
(
1
)
=
8
.
3
6
,
p
<
0
.
0
0
5
p
<
0
.
0
1
R
esid
en
c
y
Y
o
u
n
g
e
r
>
Old
er
C
o
m
p
ete
n
t
>
No
n
-
Fre
q
u
en
t
>
I
n
f
r
e
q
u
en
t
,
y
2
(
3
)
=
1
0
.
7
3
,
p
<
0
.
0
5
co
m
p
ete
n
t,
yc
2
(
1
)
=
7
.
2
7
,
y
2
(
1
)
=
4
.
4
6
,
p
<
0
.
0
5
p
<
0
.
0
1
Ma
r
ital
s
tat
u
s
No
d
if
f
e
r
en
c
e
C
o
m
p
ete
n
t
>
No
n
-
co
m
p
ete
n
t
Fre
q
u
en
t
>
I
n
f
r
e
q
u
en
t
,
co
m
p
ete
n
t
y
2
(
1
)
=
8
.
1
8
,
y
2
(
1
)
=
4
.
4
5
,
p
<
0
.
0
5
p
<
0
.
0
0
5
Occ
u
p
atio
n
No
d
if
f
e
r
en
c
e
No
d
if
f
e
r
en
c
e
Fre
q
u
en
t
>
I
n
f
r
e
q
u
en
t
,
y
2
(
1
)
=
6
.
9
8
,
p
<
0
.
0
1
T
h
e
d
ec
ep
tio
n
m
o
d
el
w
e
h
av
e
cr
ea
ted
is
in
n
etlo
g
o
.
T
h
e
d
ec
ep
tio
n
w
ill
b
e
h
a
n
d
led
b
y
th
e
u
s
e
o
f
lead
er
o
f
th
e
co
m
m
u
n
it
y
.
T
h
e
n
e
w
u
s
er
w
i
ll
en
ter
i
n
to
th
e
s
y
s
te
m
a
n
d
in
ter
ac
t
w
it
h
th
e
lea
d
er
.
I
f
lead
er
allo
w
th
e
n
e
w
a
g
en
t
to
en
ter
in
to
th
e
s
y
s
te
m
t
h
en
cr
ed
e
n
tia
l
w
ill
b
e
ch
ec
k
ed
.
I
f
th
e
cr
ed
en
tial
s
ar
e
n
o
t
v
alid
th
e
n
th
e
n
e
w
a
g
en
t
e
n
ter
i
n
g
in
to
t
h
e
s
y
s
te
m
w
ill
b
e
j
ailed
.
T
h
e
co
n
ce
p
t
o
f
j
ailed
w
ill
b
e
u
s
ed
to
h
a
n
d
le
th
e
d
ec
ep
tio
n
p
r
esen
t
w
it
h
in
t
h
e
o
n
l
in
e
s
o
cial
m
ed
ia.
T
h
e
s
cr
ee
n
s
h
o
t
s
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
ill b
e
as
f
o
llo
w
s
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
P
r
ev
en
tin
g
On
lin
e
S
o
ci
a
l D
ec
ep
tio
n
u
s
in
g
Dec
e
p
tio
n
Ma
tr
ix
(
A
lka
)
39
Fig
u
r
e
2
.
s
h
o
w
i
n
g
t
h
e
d
ec
ep
tio
n
m
o
d
el
th
r
o
u
g
h
n
etlo
g
o
T
h
e
ag
en
t t
y
p
e
s
w
ill b
e
lis
ted
t
h
r
o
u
g
h
t
h
e
g
r
ap
h
a
s
f
o
llo
w
s
Fig
u
r
e
3
.
Sh
o
w
in
g
t
h
e
ag
e
n
t t
y
p
e
s
6.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
T
h
e
d
ec
ep
tio
n
ca
n
b
e
th
e
b
ig
p
r
o
b
lem
w
h
ic
h
is
p
r
e
s
e
n
t
w
it
h
i
n
t
h
e
s
o
cial
m
ed
ia.
Det
ec
tin
g
th
e
d
ec
ep
tio
n
an
d
i
m
p
o
s
in
g
t
h
e
f
i
n
e
o
n
th
e
m
w
i
ll
b
e
t
h
e
p
r
i
m
e
o
b
j
ec
tiv
e
o
f
th
i
s
p
ap
er
.
T
h
e
p
ap
er
p
u
r
p
o
s
es
th
e
b
ac
k
g
r
o
u
n
d
ch
ec
k
m
ec
h
a
n
i
s
m
in
o
r
d
er
t
o
en
s
u
r
e
th
at
t
h
e
d
ec
ep
tio
n
n
ev
er
o
cc
u
r
in
t
h
e
s
y
s
te
m
.
T
h
e
tech
n
iq
u
e
s
u
g
g
e
s
ted
i
n
t
h
i
s
p
ap
er
w
ill
e
f
f
icie
n
tl
y
d
etec
t
a
n
d
r
eso
l
v
e
t
h
e
p
r
o
b
lem
s
p
r
esen
t
w
it
h
i
n
t
h
e
o
n
lin
e
s
o
cial
m
ed
ia
lik
e
f
ac
eb
o
o
k
.
T
h
e
m
ai
n
p
r
o
b
le
m
t
h
at
is
p
r
esen
t
w
it
h
i
n
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
is
t
h
at
it
w
ill
b
e
ti
m
e
co
n
s
u
m
i
n
g
to
p
er
f
o
r
m
s
u
c
h
a
ch
ec
k
.
So
i
n
t
h
e
f
u
t
u
r
e
w
e
w
il
l
tr
y
to
in
v
e
n
t
a
tech
n
iq
u
e
in
o
r
d
er
to
r
eso
lv
e
th
e
is
s
u
e
o
f
ti
m
e
co
n
s
u
m
p
tio
n
.
RE
F
E
R
E
NC
E
S
[1
]
J.
T
.
Ha
n
c
o
c
k
,
“
Dig
it
a
l
De
c
e
p
ti
o
n
:
W
h
y
,
W
h
e
n
a
n
d
Ho
w
P
e
o
p
le L
ie On
li
n
e
,
”
Ox
fo
rd
H
a
n
d
b
.
In
t
e
rn
e
t
Psy
c
h
o
l
.
,
p
p
.
2
8
9
–
3
0
1
,
2
0
0
7
.
[2
]
M
.
T
sik
e
rd
e
k
is
a
n
d
S
.
Zea
d
a
ll
y
,
“
De
tec
ti
n
g
a
n
d
P
re
v
e
n
ti
n
g
On
l
in
e
Id
e
n
ti
ty
De
c
e
p
ti
o
n
i
n
S
o
c
ial
Ne
tw
o
rk
in
g
S
e
rv
ice
s,”
IEE
E
In
ter
n
e
t
Co
m
p
u
t.
,
v
o
l.
1
9
,
n
o
.
3
,
p
p
.
4
1
–
4
9
,
M
a
y
2
0
1
5
.
[3
]
M
.
T
sik
e
rd
e
k
is
a
n
d
S
.
Zea
d
a
ll
y
,
“
On
li
n
e
d
e
c
e
p
ti
o
n
in
so
c
ial
m
e
d
ia,”
Co
mm
u
n
.
ACM
,
v
o
l.
5
7
,
n
o
.
9
,
p
p
.
7
2
–
8
0
,
S
e
p
.
2
0
1
4
.
[4
]
A
.
V
ish
w
a
n
a
th
,
“
Diff
u
sio
n
o
f
d
e
c
e
p
ti
o
n
in
so
c
ial
m
e
d
ia:
S
o
c
ial
c
o
n
tag
io
n
e
f
fe
c
ts
a
n
d
it
s an
tec
e
d
e
n
ts,
”
In
f.
S
y
st.
Fro
n
t.
,
v
o
l.
1
7
,
n
o
.
6
,
p
p
.
1
3
5
3
–
1
3
6
7
,
Ju
n
.
2
0
1
4
.
[5
]
C.
-
D.
Ch
e
n
a
n
d
L
.
-
T
.
Hu
a
n
g
,
“
O
n
li
n
e
De
c
e
p
ti
o
n
I
n
v
e
stig
a
ti
o
n
:
C
o
n
ten
t
A
n
a
ly
sis a
n
d
Cro
ss
-
Cu
lt
u
ra
l
Co
m
p
a
riso
n
,
”
In
t.
J
.
Bu
s.
I
n
f.
,
v
o
l.
6
,
n
o
.
1
,
p
p
.
9
1
–
1
1
1
,
2
0
1
1
.
[6
]
M
.
T
sik
e
rd
e
k
is
a
n
d
S
.
Zea
d
a
ll
y
,
“
On
li
n
e
De
c
e
p
ti
o
n
i
n
S
o
c
ial
M
e
d
i
a
,
”
Co
mm
u
n
.
ACM
,
v
o
l.
5
7
,
n
o
.
9
,
p
p
.
7
2
–
8
0
,
2
0
1
4
.
[7
]
A
.
Ca
sp
i
a
n
d
P
.
G
o
rsk
y
,
“
On
li
n
e
De
c
e
p
ti
o
n
:
P
re
v
a
len
c
e
,
M
o
ti
v
a
ti
o
n
,
a
n
d
Em
o
ti
o
n
,
”
Cy
b
e
rp
sy
c
h
o
l
o
g
y
Beh
a
v
.
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
5
4
–
6
0
,
2
0
0
6
.
[8
]
M
.
T
sik
e
rd
e
k
is
a
n
d
S
.
Zea
d
a
ll
y
,
“
On
li
n
e
d
e
c
e
p
ti
o
n
in
so
c
ial
m
e
d
ia,”
Co
mm
u
n
.
ACM
,
v
o
l.
5
7
,
n
o
.
9
,
p
p
.
7
2
–
8
0
,
S
e
p
.
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
35
–
40
40
[9
]
M
.
T
sik
e
rd
e
k
is
a
n
d
S
.
Zea
d
a
ll
y
,
“
De
tec
ti
n
g
a
n
d
P
re
v
e
n
ti
n
g
On
l
in
e
Id
e
n
ti
ty
De
c
e
p
ti
o
n
i
n
S
o
c
ial
Ne
tw
o
rk
in
g
S
e
rv
ice
s,”
IEE
E
In
ter
n
e
t
Co
m
p
u
t.
,
v
o
l.
1
9
,
n
o
.
3
,
p
p
.
4
1
–
4
9
,
M
a
y
2
0
1
5
.
[1
0
]
M
.
T
sik
e
rd
e
k
is
a
n
d
S
.
Zea
d
a
ll
y
,
“
M
u
lt
i
p
l
e
A
c
c
o
u
n
t
I
d
e
n
ti
ty
De
c
e
p
ti
o
n
De
tec
ti
o
n
i
n
S
o
c
ial
M
e
d
ia Usi
n
g
No
n
v
e
rb
a
l
Be
h
a
v
io
r,
”
IEE
E
T
r
a
n
s.
In
f.
Fo
re
n
sic
s S
e
c
u
r.
,
v
o
l
.
9
,
n
o
.
8
,
p
p
.
1
3
1
1
–
1
3
2
1
,
A
u
g
.
2
0
1
4
.
[1
1
]
“
On
li
n
e
De
c
e
p
ti
o
n
in
S
o
c
ial
M
e
d
ia.” [
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:/
/ca
c
m
.
a
c
m
.
o
rg
/
m
a
g
a
z
in
e
s/2
0
1
4
/9
/1
7
7
9
3
6
-
o
n
li
n
e
-
d
e
c
e
p
ti
o
n
-
in
-
so
c
ial
-
m
e
d
ia/a
b
stra
c
t.
[
A
c
c
e
ss
e
d
:
2
5
-
F
e
b
-
2
0
1
6
].
[1
2
]
“
T
h
e
S
tran
g
e
r
Am
o
n
g
Us
:
Id
e
n
ti
t
y
D
e
c
e
p
ti
o
n
in
On
li
n
e
Co
m
m
u
n
it
ies
o
f
Ch
o
ice
|
P
a
tri
c
ia J M
o
o
re
-
A
c
a
d
e
m
ia.ed
u
.
”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:
//
ww
w
.
a
c
a
d
e
m
i
a
.
e
d
u
/1
6
2
9
3
4
3
/T
h
e
_
S
tran
g
e
r_
Am
o
n
g
_
Us
_
Id
e
n
ti
ty
_
De
c
e
p
ti
o
n
_
in
_
On
l
in
e
_
C
o
m
m
u
n
it
ies
_
o
f
_
C
h
o
ice
.
[
A
c
c
e
ss
e
d
:
2
5
-
F
e
b
-
2
0
1
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.