I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
e
r
Science
Vo
l.
1
2
,
No
.
2
,
N
o
v
e
m
b
er
201
8
,
p
p
.
6
0
7
~
6
1
1
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
2
.
p
p
607
-
6
1
1
607
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Yo
uTub
e Spa
m
C
o
m
m
en
t
De
tec
tion Using
Sup
po
rt
Vect
o
r
M
a
chine and
K
–
Nea
rest N
eig
hbo
r
Aqlii
m
a
Aziz
1
,
Ci
k F
er
esa
M
o
hd
F
o
o
zy
2
,
P
a
la
nia
pp
a
n Sh
a
m
a
la
3
,
Z
uri
na
h Sura
di
4
2,
3
A
p
p
li
e
d
C
o
m
p
u
ti
n
g
T
e
c
h
n
o
l
o
g
y
(
A
C
T
)
,
Un
iv
e
rsiti
T
u
n
Hu
ss
e
in
On
n
M
a
lay
sia
(U
T
HM),
P
a
rit
Ra
ja,
Ba
tu
P
a
h
a
t,
8
6
4
0
0
Jo
h
o
r,
M
a
lay
sia
.
1,
2,
3
F
a
c
u
l
ty
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
Un
iv
e
rsiti
T
u
n
Hu
ss
e
in
On
n
M
a
lay
si
a
(UT
HM),
P
a
rit
Ra
ja,
Ba
tu
P
a
h
a
t,
8
6
4
0
0
Jo
h
o
r,
M
a
l
a
y
sia
.
4
De
p
a
rtme
n
t
o
f
M
a
n
a
g
e
m
e
n
t
In
f
o
rm
a
ti
o
n
S
y
ste
m
s,
Co
ll
e
g
e
o
f
Co
m
m
e
rc
e
a
n
d
Bu
sin
e
ss
A
d
m
in
istrati
o
n
s,
Dh
o
f
a
r
Un
iv
e
rsit
y
,
S
a
lala
h
,
Om
a
n
.
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
9
,
2
0
1
8
R
ev
i
s
ed
Ma
y
2
0
,
2
0
1
8
A
cc
ep
ted
Ju
l
11
,
2
0
1
8
S
o
c
ial
n
e
tw
o
rk
in
g
su
c
h
a
s
Yo
u
T
u
b
e
,
F
a
c
e
b
o
o
k
a
n
d
o
th
e
rs
a
re
v
e
ry
p
o
p
u
lar
n
o
w
a
d
a
y
s.
T
h
e
b
e
st
th
in
g
a
b
o
u
t
Yo
u
T
u
b
e
is
u
se
r
c
a
n
su
b
sc
rib
e
a
lso
g
iv
in
g
o
p
i
n
io
n
o
n
t
h
e
c
o
m
m
e
n
t
se
c
ti
o
n
.
Ho
w
e
v
e
r,
th
is
a
tt
ra
c
t
th
e
sp
a
m
m
e
r
b
y
sp
a
m
m
in
g
th
e
c
o
m
m
e
n
ts
o
n
th
a
t
v
id
e
o
s.
T
h
u
s
,
th
is
stu
d
y
d
e
v
e
lo
p
a
Yo
u
T
u
b
e
d
e
tec
ti
o
n
f
ra
m
e
w
o
rk
b
y
u
sin
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
(S
VM
)
a
n
d
K
-
Ne
a
re
st
Ne
i
g
h
b
o
r
(k
-
NN
).
T
h
e
re
a
re
f
i
v
e
(5
)
p
h
a
se
s
in
v
o
lv
e
d
in
t
h
i
s
re
se
a
rc
h
su
c
h
a
s Da
ta Co
ll
e
c
ti
o
n
,
P
re
-
p
r
o
c
e
ss
in
g
,
F
e
a
tu
re
S
e
lec
ti
o
n
,
Clas
sif
ica
ti
o
n
a
n
d
De
tec
ti
o
n
.
T
h
e
e
x
p
e
rime
n
ts
is
d
o
n
e
b
y
u
sin
g
W
e
k
a
a
n
d
Ra
p
id
M
in
e
r.
T
h
e
a
c
c
u
ra
c
y
r
e
su
lt
o
f
S
V
M
a
n
d
KN
N b
y
u
sin
g
b
o
th
m
a
c
h
in
e
lea
rn
in
g
to
o
ls
sh
o
w
g
o
o
d
a
c
c
u
ra
c
y
re
su
lt
.
Oth
e
rs
so
l
u
ti
o
n
t
o
a
v
o
i
d
sp
a
m
a
tt
a
c
k
is
try
in
g
n
o
t
t
o
c
li
c
k
th
e
li
n
k
o
n
c
o
m
m
e
n
ts
to
a
v
o
id
a
n
y
p
ro
b
lem
s.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
Dete
ctio
n
Ma
ch
i
n
e
L
ea
r
n
i
n
g
Yo
u
T
u
b
e
Sp
am
Co
p
y
rig
h
t
©
2
0
1
8
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
q
lii
m
a
A
ziz
,
Facu
lt
y
o
f
C
o
m
p
u
ter
Scien
ce
an
d
I
n
f
o
r
m
atio
n
,
Un
i
v
er
s
iti T
u
n
H
u
s
s
ei
n
On
n
Ma
la
y
s
ia
(
UT
HM
)
,
P
ar
it R
aj
a,
B
atu
P
ah
at,
8
6
4
0
0
J
o
h
o
r
,
Ma
lay
s
ia
.
E
m
ail:
aq
li
m
aa
ziz
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Yo
u
T
u
b
e
is
o
n
e
o
f
th
e
b
ig
g
e
s
t
s
ite
f
o
r
u
s
er
g
et
i
n
f
o
r
m
ati
o
n
o
n
th
e
I
n
ter
n
et
[
1
]
.
B
ec
au
s
e
o
f
th
at,
m
an
y
s
p
a
m
m
er
s
w
ill
tr
ic
k
th
e
Yo
u
T
u
b
e
u
s
er
b
y
s
p
a
m
m
i
n
g
t
h
e
Yo
u
T
u
b
e
co
m
m
e
n
ts
.
A
cc
o
r
d
in
g
to
Ha
m
o
u
[
2
]
,
s
p
a
m
i
s
n
o
w
a
tr
en
d
attac
k
an
d
th
e
Yo
u
T
u
b
e
d
ef
in
e
s
s
p
a
m
a
s
i
n
ap
p
r
o
p
r
iate
co
m
m
en
t
s
,
s
u
c
h
as
ab
u
s
e
o
r
tr
o
llin
g
an
d
al
s
o
p
eo
p
le
tr
y
in
g
to
s
e
ll
t
h
in
g
s
.
Ha
m
ca
n
b
e
d
ef
i
n
ed
as
“g
o
o
d
co
m
m
en
ts
”
o
r
Yo
u
T
u
b
e
f
r
ee
f
r
o
m
s
p
a
m
co
m
m
e
n
t.
Sp
a
m
ca
n
b
e
ca
teg
o
r
ized
as
d
an
g
er
o
u
s
b
ec
au
s
e
s
p
a
m
h
as
t
h
e
p
o
ten
tial
o
f
c
y
b
er
s
ec
u
r
it
y
th
r
ea
t
f
o
r
en
d
u
s
er
s
.
T
h
e
s
p
a
m
m
er
u
s
ed
th
is
o
p
p
o
r
tu
n
i
t
y
to
s
p
r
ea
d
m
al
w
ar
e
t
h
r
o
u
g
h
co
m
m
e
n
t
f
ield
s
,
w
h
ic
h
w
ill
e
x
p
lo
it
v
u
l
n
er
ab
ilit
ie
s
in
t
h
e
u
s
er
’
s
m
ac
h
in
e
s
.
A
n
o
t
h
er
in
te
n
tio
n
in
clu
d
es
s
eizi
n
g
m
o
n
e
y
tr
a
n
s
ac
t
io
n
s
an
d
h
ij
ac
k
in
g
cr
ed
it
ca
r
d
an
d
b
an
k
in
g
i
n
f
o
r
m
atio
n
.
B
esid
e
s
,
s
p
a
m
m
er
te
n
d
s
to
r
u
i
n
t
h
e
co
n
te
n
t
o
f
w
e
b
p
ag
es.
T
h
is
ac
tio
n
w
il
l le
ad
v
is
ito
r
s
to
an
n
o
y
o
v
e
r
all
o
f
th
e
p
o
s
ted
co
n
ten
t [
3
]
.
Yo
u
T
u
b
e
s
p
am
co
m
m
e
n
ts
h
a
s
p
o
ten
tial
to
s
p
r
ea
d
m
al
w
ar
e.
T
h
e
W
an
n
aCr
y
is
s
u
e
is
a
r
ep
r
esen
tat
iv
e
ex
a
m
p
le
o
f
m
al
w
ar
e
u
s
ed
b
y
s
p
a
m
m
er
to
ex
p
lo
it
u
s
er
’
s
v
u
ln
er
ab
ili
ties
.
Ne
x
t,
f
ilele
s
s
m
al
w
ar
e
attac
k
s
ar
e
b
ein
g
ap
p
lied
b
y
attac
k
er
s
a
n
d
c
y
b
er
cr
i
m
i
n
als.
T
h
is
attac
k
m
i
g
h
t
p
r
ev
e
n
t
d
etec
tio
n
a
n
d
m
a
k
e
d
i
f
f
icu
l
t
f
o
r
f
o
r
en
s
ic
i
n
v
e
s
ti
g
a
tio
n
s
.
U
s
u
a
ll
y
,
s
p
a
m
m
er
s
m
ak
i
n
g
u
s
e
o
f
e
x
is
tin
g
to
o
ls
t
h
at
alr
ea
d
y
in
s
ta
lled
o
n
u
s
er
s
’
co
m
p
u
ter
s
.
Fo
r
ex
a
m
p
le,
P
o
w
er
S
h
ell,
P
SEx
ec
,
W
MI
o
r
r
u
n
n
i
n
g
s
i
m
p
le
s
cr
ip
t
s
an
d
s
h
ellco
d
e
s
tr
aig
h
t
i
n
m
e
m
o
r
y
.
Fi
leles
s
m
ea
n
s
cr
ea
ti
n
g
a
f
e
w
f
i
les o
n
h
ar
d
d
is
k
,
wh
ich
les
s
c
h
a
n
ce
o
f
b
ein
g
tr
ac
ed
.
Nex
t,
w
ip
er
s
ar
e
t
y
p
e
m
a
l
w
ar
e
t
h
at
u
s
ed
b
y
s
p
a
m
m
er
s
f
o
r
r
e
m
o
v
i
n
g
tr
ac
k
s
a
f
ter
c
y
b
er
e
s
p
io
n
ag
e
o
cc
u
r
s
[
4
]
.
Mo
r
eo
v
er
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
6
0
7
–
6
1
1
608
m
al
w
ar
e
ca
u
s
e
m
u
ltip
le
b
r
ea
c
h
es
w
h
er
e
lea
k
m
ill
io
n
s
o
f
u
s
er
r
ec
o
r
d
s
.
A
n
e
x
a
m
p
le
o
f
th
e
d
etails
lea
k
ed
s
u
c
h
as
u
s
er
n
a
m
es,
e
m
ai
l
ad
d
r
ess
e
s
an
d
h
as
h
ed
p
ass
w
o
r
d
s
,
p
r
o
b
ab
ly
u
s
e
S
H
A
-
1
w
h
ic
h
i
s
le
s
s
s
ec
u
r
e.
T
h
e
m
ain
f
ac
to
r
th
at
lead
s
to
d
ata
b
r
ea
ch
is
p
o
s
s
ib
l
y
w
ea
k
p
ass
w
o
r
d
w
h
ich
ca
n
ea
s
i
l
y
cr
ac
k
[
5
]
.
T
h
er
e
ar
e
s
ev
er
al
s
tu
d
ies
to
d
e
tect
Yo
u
T
u
b
e
Sp
a
m
s
u
ch
a
s
[
6
]
-
[
9
]
p
r
o
p
o
s
ed
to
class
if
y
t
h
e
Yo
u
T
u
b
e
co
m
m
e
n
t
as
Sp
a
m
a
n
d
Ha
m
b
y
u
s
i
n
g
Su
p
p
o
r
t
Vec
to
r
Ma
c
h
in
e
(
SV
M)
.
T
h
e
s
ig
n
i
f
ica
n
ce
o
f
th
is
r
esear
ch
to
d
ev
elo
p
a
Yo
u
T
u
b
e
Sp
am
d
et
ec
tio
n
f
r
a
m
e
w
o
r
k
a
n
d
Yo
u
T
u
b
e
Sp
am
f
ea
t
u
r
es
s
o
th
e
Yo
u
T
u
b
e
v
is
ito
r
ab
le
to
id
en
ti
f
y
t
h
e
Yo
u
T
u
b
e
Sp
am
ch
ar
ac
ter
is
tic
s
.
W
h
en
th
e
Yo
u
T
u
b
e
u
s
er
s
ab
le
to
id
en
tify
th
e
Yo
u
T
u
b
e
s
p
a
m
f
ea
t
u
r
es,
th
e
y
w
ill b
e
m
o
r
e
a
war
e,
an
d
th
e
m
al
w
ar
e
s
p
r
ea
d
ca
n
b
e
r
ed
u
ce
d
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
er
e
ar
e
m
a
n
y
t
y
p
es
o
f
s
p
a
m
,
s
u
c
h
as
w
eb
s
p
a
m
,
s
h
o
r
t
m
e
s
s
a
g
e
s
p
a
m
,
e
m
ai
l
s
p
a
m
,
s
o
ci
al
n
et
w
o
r
k
sp
a
m
an
d
o
th
er
s
.
I
n
th
i
s
s
ec
tio
n
,
th
e
Yo
u
T
u
b
e
s
p
a
m
d
etec
tio
n
s
t
u
d
ies
w
ill b
e
f
o
cu
s
ed
.
2
.
1
Sp
a
m
Det
ec
t
io
n Appro
a
c
h
Yo
u
T
u
b
e
is
n
o
t
ex
clu
d
ed
f
r
o
m
m
al
icio
u
s
u
s
er
w
h
o
ar
e
o
f
ten
f
o
u
n
d
to
ex
p
o
s
e
in
s
p
a
m
m
i
n
g
a
n
d
p
r
o
m
o
tio
n
al
ac
ti
v
itie
s
[
1
0
]
.
T
h
er
e
ar
e
m
a
n
y
ap
p
r
o
ac
h
es
to
d
etec
t
Sp
a
m
s
u
c
h
as
u
s
i
n
g
Ar
tif
icial
I
n
tel
lig
e
n
t
,
C
r
y
p
to
g
r
ap
h
y
,
Ma
c
h
in
e
L
ea
r
n
in
g
an
d
o
th
er
s
.
Ho
w
ev
er
,
Ma
n
w
ar
[
7
]
s
aid
th
e
m
ac
h
i
n
e
lear
n
in
g
also
ca
p
ab
le
to
d
etec
t Y
o
u
T
u
b
e
s
p
am
.
T
h
e
ex
is
ti
n
g
s
tu
d
y
in
Yo
u
T
u
b
e
Sp
a
m
Dete
ctio
n
is
Ma
n
w
ar
[
7
]
an
d
A
lb
er
to
[
8
]
s
h
o
w
t
h
at
b
o
th
o
f
th
e
au
th
o
r
s
u
s
ed
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
SVM)
as
a
class
if
ie
r
in
class
i
f
icatio
n
p
h
a
s
e.
Ma
n
w
ar
[
7
]
s
tated
th
at
SVM
clas
s
i
f
icatio
n
i
s
i
n
b
in
a
r
y
-
t
w
o
cla
s
s
.
U
s
u
al
l
y
,
cla
s
s
d
en
o
ted
b
y
0
a
n
d
1
.
Ho
w
e
v
er
,
th
e
co
llectio
n
d
ata
h
av
e
b
ee
n
cla
s
s
i
f
ied
i
n
to
t
w
o
class
es.
He
n
ce
,
ea
s
y
f
o
r
p
r
e
-
p
r
o
ce
s
s
in
g
a
n
d
f
ea
t
u
r
e
s
elec
tio
n
to
p
er
f
o
r
m
.
2
.
2
F
ra
m
ew
o
rk
det
ec
t
io
n
B
asi
ca
ll
y
,
t
h
er
e
ar
e
s
ev
er
al
p
h
ase
s
in
d
etec
tio
n
f
r
a
m
e
w
o
r
k
u
s
i
n
g
m
ac
h
i
n
e
lear
n
i
n
g
tec
h
n
iq
u
e
s
s
u
ch
as Da
ta
C
o
llectio
n
,
Featu
r
e
Se
lectio
n
,
C
la
s
s
i
f
icatio
n
an
d
Det
ec
tio
n
.
T
h
e
Data
C
o
llec
tio
n
ar
e
co
lle
cted
f
r
o
m
s
o
cial
m
ed
ia.
Fo
r
e
x
a
m
p
le,
Face
b
o
o
k
,
T
w
itter
,
S
in
a
W
ei
bo
(
I
n
s
tag
r
a
m
)
,
Yo
u
T
u
b
e
an
d
E
m
ail.
T
h
u
s
,
U
C
I
w
ill
co
llect
th
o
s
e
co
m
m
e
n
t
s
an
d
f
o
r
m
a
d
ataset
ac
co
r
d
in
g
t
o
s
o
cial
m
ed
ia
ca
te
g
o
r
ies
s
u
ch
a
s
Yo
u
T
u
b
e,
Face
b
o
o
k
an
d
o
th
er
s
.
Fig
u
r
e
b
elo
w
s
h
o
w
s
r
a
w
d
ata
co
llected
f
r
o
m
UC
I
m
ac
h
i
n
e
lear
n
i
n
g
r
ep
o
s
ito
r
y
.
Ne
x
t,
id
en
ti
f
y
w
h
e
th
er
t
h
e
co
m
m
en
t
is
s
p
a
m
o
r
h
a
m
.
B
ased
o
n
T
ab
le
1
,
r
a
w
d
ata
alr
ea
d
y
class
if
ied
in
s
p
a
m
an
d
h
a
m
.
T
ab
le
1
.
Data
s
ets f
o
r
Yo
u
T
u
b
e
s
p
a
m
co
m
m
e
n
t [
8
]
D
a
t
a
se
t
s
Y
o
u
T
u
b
e
I
D
S
p
a
m
H
a
m
T
o
t
a
l
P
sy
9
b
Z
k
p
7
q
1
9
f
0
1
7
5
1
7
5
3
5
0
K
a
t
y
P
e
r
r
y
C
e
v
x
Zv
S
J
L
k
8
1
7
5
1
7
5
3
5
0
L
M
F
A
O
K
Q
6
z
r
6
k
C
P
j
8
2
3
6
2
0
2
4
3
8
Emi
n
e
m
u
e
l
H
w
f
8
o
7
_
U
2
4
5
2
0
3
4
4
8
S
h
a
k
i
r
a
p
R
p
e
Ed
M
mm
Q
0
1
7
4
1
9
6
3
7
0
I
n
m
ac
h
i
n
e
lear
n
in
g
,
f
ea
t
u
r
e
s
elec
tio
n
is
u
s
ed
to
cla
s
s
i
f
y
t
h
e
clas
s
.
Se
v
er
al
s
tu
d
ie
s
b
y
Af
za
l
[
1
1
]
,
u
s
ed
t
h
e
UR
L
a
s
f
ea
t
u
r
es.
W
u
,
F.,
&
H
u
a
n
g
,
Y.
[
1
2
]
u
s
ed
co
n
ten
t
-
b
ased
f
ea
tu
r
es
to
d
etec
t
t
h
e
s
p
a
m
co
m
m
e
n
t
s
i
n
t
h
e
u
s
er
’
s
m
es
s
a
g
e.
T
h
e
f
ea
t
u
r
es
ar
e
U
R
L
s
,
k
e
y
w
o
r
d
s
,
h
a
s
h
ta
g
s
an
d
b
ad
co
m
m
en
t
s
.
Me
a
n
w
h
ile
o
th
er
s
tu
d
ie
s
ap
p
lied
o
th
er
ty
p
es o
f
f
ea
t
u
r
es.
C
las
s
i
f
icatio
n
w
i
ll
b
e
u
s
ed
to
class
i
f
y
th
e
d
ata
s
et
in
to
s
ev
er
al
class
e
s
b
ased
o
n
th
e
s
u
i
tab
le
f
ea
tu
r
e
s
.
A
cc
o
r
d
in
g
to
[
1
3
]
,
SVM
i
s
o
n
e
o
f
t
h
e
tec
h
n
iq
u
e
s
t
h
at
ca
n
cl
ass
i
f
y
t
h
e
p
r
o
b
le
m
s
[
1
3
]
.
Me
a
n
w
h
ile,
K
-
NN
is
a
s
i
m
p
le
y
et
ef
f
ic
ien
t c
la
s
s
i
f
icat
i
o
n
alg
o
r
ith
m
s
f
o
r
d
ata
m
i
n
i
n
g
[
1
4
]
.
L
ast
l
y
,
t
h
e
r
esu
lts
o
b
tain
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
r
esear
c
h
is
to
c
o
m
p
ar
e
w
h
ich
tec
h
n
iq
u
e
s
p
r
o
v
id
e
b
etter
ac
cu
r
ac
y
r
esu
l
t in
d
etec
t
in
g
t
h
e
Yo
u
T
u
b
e
s
p
am
co
m
m
en
t.
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
er
e
ar
e
(
5
)
s
tep
s
in
th
is
d
etec
tio
n
f
r
a
m
e
w
o
r
k
s
u
c
h
as
Data
C
o
llectio
n
,
Data
P
r
e
-
p
r
o
ce
s
s
in
g
,
Featu
r
e
E
x
tr
ac
tio
n
,
C
las
s
i
f
ica
tio
n
a
n
d
C
o
m
p
ar
i
s
o
n
o
f
R
e
s
u
lts
,
a
s
s
h
o
w
n
i
n
F
ig
u
r
e
1
.
T
h
is
f
r
a
m
e
w
o
r
k
i
s
ch
o
s
en
f
r
o
m
[
6
]
b
ec
au
s
e
i
t
c
an
p
r
o
v
id
e
t
h
e
r
e
s
u
l
t
w
i
th
g
o
o
d
ac
cu
r
ac
y
.
T
h
is
f
r
a
m
e
w
o
r
k
also
p
r
o
v
id
es
th
e
p
h
ase
to
co
m
p
ar
e
th
e
r
esu
lts
o
f
SVM
tec
h
n
iq
u
e
a
n
d
k
-
NN
te
ch
n
iq
u
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Yo
u
Tu
b
e
S
p
a
m
C
o
mme
n
t D
etec
tio
n
Usi
n
g
S
u
p
p
o
r
t V
ec
to
r
Ma
ch
in
e
a
n
d
K
–
N
ea
r
est N
eig
h
b
o
r
(
A
q
liima
A
z
iz
)
609
Fig
u
r
e
1
.
Yo
u
T
u
b
e
Sp
am
Det
ec
tio
n
Fra
m
e
w
o
r
k
[
6
]
T
h
e
d
escr
ip
tio
n
f
o
r
ev
er
y
p
h
as
e
in
Yo
u
T
u
b
e
Sp
a
m
d
etec
tio
n
f
r
a
m
e
w
o
r
k
:
a)
Data
C
o
llectio
n
I
n
t
h
is
p
h
ase,
t
h
e
d
ata
s
et
f
o
r
ex
p
er
i
m
e
n
ts
is
d
o
w
n
lo
ad
ed
f
r
o
m
U
C
I
m
ac
h
in
e
lear
n
i
n
g
r
ep
o
s
ito
r
y
.
T
h
e
d
ataset
co
n
tai
n
ed
o
f
f
i
v
e
(
5
)
s
elec
ted
v
id
eo
s
a
n
d
w
er
e
d
o
w
n
lo
ad
ed
f
r
o
m
Yo
u
T
u
b
e
t
h
r
o
u
g
h
A
P
I
[
8
]
.
T
h
e
co
m
m
e
n
t
s
ar
e
f
r
o
m
P
SY,
Ka
t
y
P
er
r
y
,
L
M
F
A
O,
E
m
in
e
m
a
n
d
Sh
a
k
i
r
a.
T
h
e
to
tal
f
o
r
s
p
a
m
an
d
h
a
m
in
P
s
y
v
id
eo
is
3
5
0
,
f
o
llo
w
ed
b
y
Kat
y
P
er
r
y
is
3
5
0
,
L
MF
AO
is
4
3
8
,
E
m
in
e
m
is
4
4
8
an
d
Sh
a
k
ir
a
i
s
3
7
0
.
b)
P
r
e
–
p
r
o
ce
s
s
in
g
Fo
r
Pre
-
p
r
o
ce
s
s
in
g
p
h
ase,
th
e
r
aw
d
ataset
w
il
l
b
e
ex
ec
u
ted
th
e
d
ata
clea
n
in
g
s
u
c
h
as
to
k
en
izatio
n
,
s
to
p
w
o
r
d
s
r
e
m
o
v
al
a
n
d
s
te
m
m
i
n
g
ar
e
p
er
f
o
r
m
ed
.
T
h
e
clea
n
d
ataset
w
il
l
b
e
u
s
ed
f
o
r
n
e
x
t
p
r
o
ce
s
s
o
f
f
ea
tu
r
e
s
elec
tio
n
a
n
d
ex
tr
ac
tio
n
.
c)
Featu
r
e
Select
io
n
an
d
E
x
tr
ac
ti
o
n
Featu
r
e
s
elec
tio
n
is
a
p
r
o
ce
s
s
b
ef
o
r
e
clas
s
i
f
icatio
n
clas
s
.
T
h
e
s
u
itab
le
f
ea
t
u
r
es
w
i
ll
b
e
id
en
ti
f
ied
b
ased
o
n
th
e
d
ataset.
d)
C
las
s
i
f
icatio
n
T
h
er
e
is
tr
ain
i
n
g
an
d
te
s
ti
n
g
p
r
o
ce
s
s
in
th
i
s
p
h
a
s
e.
6
0
%
w
ill
b
e
u
s
ed
f
o
r
tr
ain
i
n
g
a
n
d
4
0
%
f
o
r
test
in
g
.
Af
ter
co
m
p
leti
n
g
t
h
e
s
tep
iii,
s
u
p
p
o
s
ed
to
b
e
th
er
e
is
f
ea
tu
r
es
th
at
is
co
n
s
id
er
ed
as
s
p
a
m
.
T
h
u
s
,
th
e
d
ataset
n
ee
d
s
to
tr
ain
b
ased
o
n
m
ac
h
i
n
e
lear
n
i
n
g
tech
n
iq
u
e
s
.
SVM
is
s
u
cc
es
s
f
u
ll
y
s
u
i
tab
le
i
n
d
if
f
er
e
n
tiati
n
g
p
o
s
iti
v
e
a
n
d
n
eg
at
iv
e
p
r
o
b
lem
s
u
ch
a
s
s
p
am
.
S
VM
i
s
a
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
el
t
h
at
a
n
al
y
ze
s
d
ata
u
s
ed
f
o
r
cla
s
s
i
f
icatio
n
an
d
r
e
g
r
ess
io
n
.
SV
M
m
o
s
t
l
y
u
s
ed
in
cl
ass
i
f
icatio
n
p
r
o
b
lem
s
.
SVM
is
u
s
ed
f
o
r
b
in
ar
y
clas
s
i
f
icatio
n
p
r
o
b
lem
a
n
d
u
s
ed
k
er
n
el
f
u
n
ctio
n
s
.
K
-
NN
is
a
s
u
p
er
v
is
ed
lear
n
i
n
g
m
et
h
o
d
.
Data
is
ap
p
ea
r
in
g
i
n
a
v
ec
to
r
s
p
ac
e
i
n
t
h
e
K
-
N
N
alg
o
r
ith
m
.
K
–
NN
e
m
p
h
as
ize
k
m
o
s
t
s
i
m
i
lar
tr
ain
in
g
d
ata
p
o
in
ts
to
a
te
s
tin
g
d
ata
p
o
in
t.
Af
ter
d
eter
m
i
n
in
g
t
h
e
K
-
Nea
r
es
t
Neig
h
b
o
r
s
,
th
e
al
g
o
r
ith
m
w
i
ll
co
m
b
in
e
s
t
h
e
n
e
ig
h
b
o
r
s
’
to
d
ec
id
e
th
e
lab
el
o
f
te
s
tin
g
d
ata
p
o
in
t.
Fo
r
i
m
p
le
m
en
ta
tio
n
,
lab
els ar
e
co
m
b
in
ed
as t
h
e
lab
els
u
s
ed
s
i
m
p
le
m
aj
o
r
it
y
v
o
te.
e)
C
o
m
p
ar
is
o
n
o
f
r
esu
lts
T
h
e
r
esu
l
t p
er
f
o
r
m
an
ce
w
i
ll b
e
u
s
ed
A
cc
u
r
ac
y
,
P
r
ec
is
io
n
,
R
ec
all
an
d
F
-
m
ea
s
u
r
e.
P
r
ec
is
io
n
=
T
r
u
e
P
o
s
itiv
e/(
Fals
e
P
o
s
iti
v
e
+
T
r
u
e
P
o
s
itiv
e)
(
3
.
1
)
R
ec
all
=
T
r
u
e
P
o
s
itiv
e/
(
Fals
e
P
o
s
iti
v
e
+
T
r
u
e
P
o
s
itiv
e)
(
3
.
2
)
F
-
m
ea
s
u
r
e
=
2
*
R
ec
all
*
P
r
ec
is
io
n
/ Reca
l
l +
P
r
ec
is
io
n
(
3
.
3
)
A
cc
u
r
ac
y
=
(
T
r
u
e
Neg
ati
v
e
+
T
r
u
e
Po
s
itiv
e)
/ (
Fals
e
P
o
s
itiv
e
(
3
.
4
)
+
T
r
u
e
P
o
s
itiv
e
+
Fals
e
Neg
ativ
e
+
T
r
u
e
Neg
ati
v
e)
4.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
h
er
e
ar
e
s
ev
er
al
r
esu
lts
t
h
at
d
is
cu
s
s
ed
in
t
h
i
s
s
ec
tio
n
s
u
ch
a
s
Data
C
o
llectio
n
,
P
r
e
-
P
r
o
ce
s
s
in
g
,
Featu
r
e
Select
io
n
,
C
la
s
s
i
f
icati
o
n
an
d
Dete
ctio
n
R
es
u
lt.
4
.
1
Resul
t
s
i
n Da
t
a
Co
llect
io
n
I
n
o
r
d
er
to
c
o
llect
r
a
w
d
ata,
th
is
r
esear
c
h
u
s
es
U
C
I
m
ac
h
i
n
e
lear
n
in
g
r
ep
o
s
ito
r
y
.
T
h
o
s
e
d
ata
alr
ea
d
y
class
es
in
attr
ib
u
te
s
u
ch
as
u
s
er
s
w
it
h
a
n
ac
co
u
n
t
o
n
Yo
u
T
u
b
e
w
h
e
n
i
m
p
o
r
tin
g
i
n
to
E
x
ce
l
b
ef
o
r
e
g
o
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
6
0
7
–
6
1
1
610
th
r
o
u
g
h
p
r
e
-
p
r
o
ce
s
s
i
n
g
.
T
h
is
d
ata
co
llectio
n
co
n
tain
s
1
0
0
5
s
p
a
m
an
d
9
3
5
h
a
m
(
le
g
iti
m
a
te)
co
m
m
e
n
ts
[
1
5
]
.
Af
ter
th
a
t,
th
e
d
ata
n
ee
d
to
ch
an
g
e
f
ile
t
y
p
e
f
ir
s
t
w
h
ic
h
i
s
.
tx
t b
ef
o
r
e
test
in
g
o
n
R
ap
id
Mi
n
e
r
an
d
W
ek
a.
4
.
2
Resul
t
s
P
re
-
P
ro
ce
s
s
i
ng
On
ce
all
th
e
d
ata
is
co
llected
,
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
is
p
er
f
o
r
m
ed
.
On
ce
d
ata.
tx
t
is
i
n
s
er
t
ed
in
to
th
e
to
o
l,
th
e
to
o
l
w
ill b
e
p
er
f
o
r
m
e
d
to
k
en
izatio
n
,
s
to
p
w
o
r
d
s
r
e
m
o
v
al
an
d
s
te
m
m
i
n
g
p
h
ase.
T
o
k
en
izatio
n
s
ep
ar
ates
th
e
s
tr
in
g
b
lo
ck
b
y
b
lo
ck
.
T
h
u
s
,
t
h
e
to
k
en
izatio
n
m
ak
e
s
th
e
p
r
o
ce
s
s
o
f
s
to
p
w
o
r
d
s
r
em
o
v
al
b
ec
o
m
e
ea
s
y
.
Sto
p
w
o
r
d
s
eli
m
i
n
ate
t
h
e
co
m
m
o
n
l
y
u
s
ed
w
o
r
d
s
u
ch
a
s
“
a”
,
“
a
n
”,
“
th
e”
a
n
d
n
u
m
b
er
s
i
n
th
e
s
e
n
te
n
ce
s
.
T
h
e
p
u
r
p
o
s
e
o
f
s
to
p
w
o
r
d
s
r
e
m
o
v
al
is
to
s
h
o
r
te
n
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
ti
m
e
a
n
d
a
v
o
id
th
o
s
e
w
o
r
d
s
tak
i
n
g
s
p
ac
e
i
n
t
h
e
d
atab
ase.
Nex
t,
s
te
m
m
i
n
g
p
u
r
p
o
s
e
is
to
g
e
t
t
h
e
r
o
o
t
w
o
r
d
u
s
ed
in
q
u
er
y
,
a
v
o
id
f
r
o
m
h
a
v
i
n
g
eq
u
al
m
ea
n
i
n
g
an
d
b
ec
o
m
e
i
n
co
m
p
lete
s
en
t
en
ce
s
.
Fo
r
e
x
a
m
p
le,
th
e
w
o
r
d
s
s
u
b
s
cr
ib
e
a
n
d
p
lease
r
es
p
ec
tiv
el
y
b
ec
o
m
e
“
s
u
b
s
cr
ib
”
an
d
“
p
leas”.
He
n
ce
,
th
e
o
b
tain
ed
d
ata
af
ter
p
r
e
-
p
r
o
ce
s
s
in
g
is
clea
n
ed
.
Nex
t,
t
h
e
p
r
o
ce
s
s
d
ata
n
ee
d
to
ex
tr
ac
t in
e
x
ce
l to
f
ac
ilit
a
te
n
ex
t
s
tep
w
h
ic
h
f
ea
tu
r
e
s
ex
tr
a
ctio
n
ad
f
ea
t
u
r
e
s
elec
tio
n
[
1
6
]
.
4
.
3
Resul
t
s
i
n F
ea
t
ure
E
x
t
ra
ct
io
n a
nd
F
ea
t
ure
Select
io
n
As
f
ea
t
u
r
es
id
en
t
if
ied
f
r
o
m
t
h
e
liter
atu
r
e
r
ev
ie
w
,
v
ar
io
u
s
f
e
atu
r
es
m
a
y
b
e
ex
tr
ac
ted
f
r
o
m
Yo
u
T
u
b
e
class
i
f
icatio
n
p
u
r
p
o
s
es.
B
esid
es,
t
h
e
d
ata
alr
ea
d
y
co
n
s
is
t
s
o
f
t
w
o
(
2
)
clas
s
es
w
h
er
e
th
e
clas
s
es a
r
e
“
s
p
a
m
”
a
n
d
“h
a
m
”
[
1
5
]
.
T
h
u
s
,
ea
s
y
to
ch
o
o
s
e
f
ea
t
u
r
es
t
h
at
ce
r
tai
n
l
y
l
ab
el
as
s
p
a
m
.
Yo
u
T
u
b
e
co
m
m
en
ts
m
a
y
co
n
tai
n
h
y
p
er
li
n
k
s
,
te
x
t,
u
p
p
er
ca
s
e
an
d
lo
w
er
ca
s
e
c
h
ar
ac
ter
s
.
Ho
w
e
v
er
,
th
o
s
e
u
p
p
er
ca
s
e
ch
ar
ac
ter
s
d
o
n
o
t
ex
i
s
t
a
f
ter
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase.
Af
ter
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
t
h
is
s
t
u
d
y
d
ec
id
es
to
u
s
e
k
e
y
w
o
r
d
s
as
f
ea
tu
r
e
s
e
lectio
n
.
T
h
e
ai
m
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
i
s
to
ex
p
lo
r
e
th
e
ad
v
an
ta
g
es o
f
n
e
w
f
ea
tu
r
es i
n
o
r
d
er
to
g
ain
h
i
g
h
ac
c
u
r
ac
y
.
4
.
4
Cla
s
s
if
ica
t
io
n Re
s
ult
I
n
clas
s
i
f
icatio
n
,
a
to
tal
o
f
s
e
v
en
(
7
)
alg
o
r
ith
m
s
i
m
p
le
m
e
n
t
ed
in
R
ap
id
Mi
n
er
an
d
W
e
k
a
w
er
e
s
et
as
class
i
f
ier
s
in
d
etec
ti
n
g
Yo
u
T
u
b
e
s
p
a
m
co
m
m
e
n
t
s
.
T
h
e
p
u
r
p
o
s
e
o
f
i
m
p
le
m
e
n
ted
t
h
e
7
o
f
al
g
o
r
ith
m
s
ar
e
to
co
m
p
ar
e
t
h
e
ac
c
u
r
ac
y
.
T
h
e
cl
ass
i
f
ier
s
w
er
e
f
ed
a
n
d
te
s
ted
b
y
t
h
e
s
a
m
e
d
ataset
s
i
n
cla
s
s
i
f
y
in
g
Yo
u
T
u
b
e
s
p
a
m
b
u
t 6
d
if
f
er
e
n
t a
lg
o
r
it
h
m
s
[
1
6
]
.
T
h
e
class
if
icat
io
n
o
f
ac
cu
r
ac
y
ac
r
o
s
s
s
ev
e
n
(
7
)
d
if
f
er
en
t
class
i
f
icatio
n
alg
o
r
it
h
m
s
s
u
ch
as
Naïv
e
B
ay
e
s
,
Dec
is
io
n
T
r
ee
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e,
R
an
d
o
m
T
r
ee
,
R
an
d
o
m
Fo
r
est,
k
-
Nea
r
est
Neig
h
b
o
r
an
d
L
o
g
i
s
tic
u
s
in
g
d
ata
p
r
o
p
o
r
tio
n
o
f
7
0
:3
0
.
7
0
:3
0
m
ea
n
s
7
0
%
f
o
r
tr
ain
i
n
g
a
n
d
3
0
%
f
o
r
test
i
n
g
.
Me
an
w
h
ile,
i
n
W
ek
a,
Naï
v
e
B
a
y
es,
Dec
i
s
io
n
T
r
ee
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e,
R
an
d
o
m
T
r
ee
,
R
an
d
o
m
Fo
r
est an
d
L
o
g
is
tic
u
s
in
g
d
ata
p
r
o
p
o
r
tio
n
o
f
6
0
:4
0
.
6
0
:
4
0
m
ea
n
s
6
0
% f
o
r
tr
ain
i
n
g
an
d
4
0
% f
o
r
test
i
n
g
.
4
.
5
Resul
t
s
Det
ec
t
io
n
T
h
e
tab
le
2
an
d
3
b
elo
w
s
h
o
w
th
e
ex
p
er
i
m
e
n
t
w
ith
a
d
ata
p
r
o
p
o
r
tio
n
o
f
th
e
p
er
ce
n
tag
e
s
p
lit
tr
ain
in
g
an
d
test
in
g
.
T
h
e
r
es
u
lt
s
h
o
w
s
t
h
at
Na
ïv
e
B
a
y
es
clas
s
if
ier
g
i
v
es
th
e
h
i
g
h
est
ac
cu
r
a
c
y
w
h
e
n
tes
tin
g
i
n
R
ap
id
Min
er
a
m
o
n
g
o
th
er
clas
s
if
ier
s
.
I
n
g
en
er
al,
Naï
v
e
B
ay
es
r
an
k
s
t
h
e
f
ir
s
t,
f
o
llo
w
ed
b
y
Dec
is
io
n
T
r
ee
an
d
L
o
g
i
s
tic.
Me
a
n
w
h
ile,
i
n
W
ek
a,
th
e
r
es
u
lt
s
h
o
w
s
th
e
ac
cu
r
a
c
y
9
0
%
an
d
ab
o
v
e.
T
h
u
s
,
th
e
r
esu
lt
s
o
f
ac
c
u
r
a
c
y
as
:
T
ab
le
2
.
C
lass
if
icatio
n
A
cc
u
r
a
c
y
(
%)
in
W
ek
a
C
l
a
ss
i
f
i
e
r
Pr
e
c
i
s
i
o
n
R
e
c
a
l
l
F
-
m
e
a
su
r
e
A
c
c
u
r
a
c
y
N
a
ï
v
e
B
a
y
e
s
0
.
9
2
8
%
0
.
9
2
8
%
0
.
9
2
8
%
9
2
.
7
8
%
D
e
c
i
si
o
n
T
r
e
e
0
.
9
2
2
%
0
.
9
2
0
%
0
.
9
2
0
%
9
2
.
0
1
%
L
o
g
i
st
i
c
0
.
9
2
8
%
0
.
9
2
8
%
0
.
9
2
8
%
9
2
.
7
8
%
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
0
.
9
1
8
%
0
.
9
1
5
%
0
.
9
1
5
%
9
1
.
4
9
%
R
a
n
d
o
m F
o
r
e
st
0
.
9
0
7
%
0
.
9
0
6
%
0
.
9
0
6
%
9
0
.
5
9
%
R
a
n
d
o
m T
r
e
e
0
.
9
0
4
%
0
.
9
0
2
%
0
.
9
0
2
%
9
0
.
2
0
%
k
-
NN
0
.
9
0
9
%
0
.
9
0
6
%
0
.
9
0
6
%
9
0
.
5
9
%
T
ab
le
3
.
C
lass
if
icatio
n
ac
c
u
r
ac
y
(
%)
in
R
ap
id
Min
er
C
l
a
ss
i
f
i
e
r
A
c
c
u
r
a
c
y
N
a
ï
v
e
B
a
y
e
s
9
2
.
7
8
%
D
e
c
i
si
o
n
T
r
e
e
9
0
.
3
8
%
L
o
g
i
st
i
c
8
8
.
3
2
%
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
7
4
.
4
0
%
R
a
n
d
o
m F
o
r
e
st
7
3
.
5
4
%
R
a
n
d
o
m T
r
e
e
5
2
.
9
2
%
k
-
N
e
a
r
e
st
N
e
i
g
h
b
o
r
5
6
.
7
0
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Yo
u
Tu
b
e
S
p
a
m
C
o
mme
n
t D
etec
tio
n
Usi
n
g
S
u
p
p
o
r
t V
ec
to
r
Ma
ch
in
e
a
n
d
K
–
N
ea
r
est N
eig
h
b
o
r
(
A
q
liima
A
z
iz
)
611
T
h
e
g
o
al
o
f
th
i
s
r
esear
ch
is
t
o
f
in
d
w
h
ich
al
g
o
r
ith
m
s
p
r
o
v
id
e
h
ig
h
an
d
b
est
i
n
ac
cu
r
ac
y
,
p
r
ec
is
io
n
an
d
r
ec
all
to
h
elp
in
d
etec
tin
g
u
n
w
a
n
ted
co
m
m
en
ts
o
n
Yo
u
T
u
b
e.
B
esid
es,
th
e
r
esu
lt
f
o
r
th
is
p
r
o
j
ec
t
m
a
y
a
s
a
b
aselin
e
f
o
r
p
eo
p
le
w
h
o
in
t
er
ested
in
th
e
Yo
u
T
u
b
e
s
p
a
m
co
m
m
en
t
an
d
i
m
p
r
o
v
e
th
e
r
esu
l
ts
f
o
r
f
u
tu
r
e
co
m
p
ar
is
o
n
s
[
8
]
.
First
a
n
d
f
o
r
e
m
o
s
t,
a
d
ataset
o
f
f
iv
e
(
5
)
Yo
u
T
u
b
e
co
m
m
en
ts
w
er
e
co
llected
u
s
in
g
p
u
b
lic
an
d
n
o
n
-
en
co
d
ed
d
ata
[
8
]
.
T
h
is
d
ata
w
i
ll b
e
g
o
in
g
to
test
w
it
h
d
ata
m
i
n
in
g
to
o
l
f
o
r
co
m
p
ar
is
o
n
o
f
r
esu
lt
’
s
ac
c
u
r
ac
y
,
b
y
u
s
i
n
g
d
i
f
f
er
e
n
t
t
y
p
es
o
f
al
g
o
r
i
th
m
s
.
I
n
d
ir
ec
tl
y
,
w
ill
p
r
o
v
e
wh
ich
al
g
o
r
ith
m
s
p
r
o
v
id
e
th
e
b
est
r
es
u
lt
a
n
d
m
o
r
e
ac
cu
r
ate.
B
ased
o
n
o
b
s
er
v
atio
n
,
s
p
a
m
co
m
m
e
n
t
s
f
o
u
n
d
m
o
r
e
th
an
le
g
iti
m
ate
co
m
m
en
t
s
.
Fo
r
f
u
tu
r
e
w
o
r
k
,
s
in
ce
n
o
t
all
o
f
t
h
e
al
g
o
r
ith
m
s
u
s
e
a
s
cla
s
s
i
f
ier
s
g
i
v
e
b
es
t
ac
c
u
r
ac
y
f
o
r
e
v
er
y
s
i
n
g
le
d
ataset
in
R
ap
id
Min
er
,
th
i
s
p
r
o
v
es
th
at
t
h
o
s
e
to
p
th
r
ee
(
3
)
alg
o
r
ith
m
s
o
f
Naïv
e
B
a
y
es,
Dec
is
io
n
T
r
ee
an
d
L
o
g
i
s
tic
ar
e
m
o
r
e
ac
c
u
r
ate.
T
h
ese
to
p
th
r
ee
(
3
)
also
g
iv
e
s
a
n
ac
c
u
r
ac
y
ab
o
v
e
8
0
%.
Ho
w
e
v
er
,
in
W
ek
a
t
h
o
s
e
s
ev
e
n
(
7
)
alg
o
r
ith
m
s
in
d
icat
e
h
ig
h
ac
cu
r
ac
y
.
He
n
ce
,
W
ek
a
is
r
ec
o
m
m
e
n
d
ed
to
d
et
ec
t
Yo
u
T
u
b
e
s
p
am
co
m
m
e
n
t.
W
e
k
a
p
r
o
v
id
es
m
o
r
e
ac
cu
r
ac
y
.
I
n
ad
d
itio
n
,
h
y
b
r
id
tech
n
iq
u
e
f
o
r
t
h
ese
th
r
ee
(
3
)
alg
o
r
ith
m
s
m
a
y
i
m
p
r
o
v
e
p
er
f
o
r
m
a
n
ce
i
n
g
e
t
tin
g
h
ig
h
ac
c
u
r
ac
y
.
F
u
r
th
er
m
o
r
e,
t
h
e
m
o
r
e
f
ea
t
u
r
es
u
s
ed
,
th
e
h
i
g
h
er
th
e
p
er
ce
n
tag
e
o
f
ac
cu
r
ac
y
.
B
esid
es,
to
en
h
a
n
ce
p
er
f
o
r
m
a
n
ce
,
cr
ea
te
n
e
w
to
o
ls
,
esp
ec
iall
y
f
o
r
Yo
u
T
u
b
e
s
p
a
m
ca
n
b
e
m
ad
e
f
o
r
f
u
t
u
r
e
r
esear
ch
s
u
ch
as T
u
b
eSp
a
m
.
T
u
b
eSp
a
m
i
s
an
ex
a
m
p
le
o
f
n
e
w
to
o
l in
d
e
tectin
g
s
p
a
m
[
8
]
.
ACK
NO
WL
E
D
G
E
M
E
NT
W
e
w
o
u
ld
lik
e
to
s
a
y
th
a
n
k
y
o
u
to
Un
i
v
er
s
iti
T
u
n
H
u
s
s
ein
On
n
Ma
la
y
s
ia
(
UT
HM
)
f
o
r
k
in
d
l
y
p
r
o
v
in
g
u
s
w
i
th
t
h
e
i
n
ter
n
al
f
u
n
d
in
g
(
Vo
t B
2
9
0
0
0
)
.
RE
F
E
R
E
NC
E
S
[1
]
S
c
h
e
lt
u
s,
P
.
,
Do
r
n
e
r,
V
.
,
&
L
e
h
n
e
r,
F
.
(
2
0
1
3
).
L
e
a
v
e
a
Co
m
m
e
n
t!
A
n
In
-
De
p
th
A
n
a
l
y
sis
o
f
U
s
e
r
Co
m
m
e
n
ts
o
n
Yo
u
T
u
b
e
.
W
irtsc
h
a
ft
sin
f
o
rm
a
ti
k
,
42
.
[2
]
Ha
m
o
u
,
R.
M
.
,
Am
in
e
,
A
.
,
&
T
a
h
a
r,
M
.
(2
0
1
7
).
T
h
e
Im
p
a
c
t
o
f
th
e
M
o
d
e
o
f
Da
ta
Re
p
re
se
n
tatio
n
f
o
r
t
h
e
Re
su
lt
Qu
a
li
ty
o
f
th
e
De
tec
ti
o
n
a
n
d
F
il
terin
g
o
f
S
p
a
m
.
In
O
n
t
o
lo
g
ie
s
a
n
d
B
ig
D
a
ta
Co
n
sid
e
ra
ti
o
n
s
fo
r
E
ff
e
c
ti
v
e
In
telli
g
e
n
c
e
(p
p
.
1
5
0
-
1
6
8
).
IG
I
G
l
o
b
a
l.
[3
]
A
lsa
l
e
h
,
M
.
,
A
larif
i,
A
.
,
A
l
-
Qu
a
y
e
d
,
F
.
,
&
A
l
-
S
a
lm
a
n
,
A
.
(2
0
1
6
).
Co
m
b
a
ti
n
g
c
o
m
m
e
n
t
sp
a
m
w
it
h
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
e
s.
P
r
o
c
e
e
d
in
g
s
-
2
0
1
5
IEE
E
1
4
th
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
ICM
LA
2
0
1
5
,
2
9
5
–
3
0
0
.
h
tt
p
s:/
/d
o
i.
o
rg
/
1
0
.
1
1
0
9
/IC
M
L
A
.
2
0
1
5
.
1
9
2
[4
]
Eu
ro
p
e
a
n
Un
i
o
n
A
g
e
n
c
y
f
o
r
Ne
t
w
o
rk
a
n
d
In
f
o
rm
a
ti
o
n
S
e
c
u
rit
y
.
(
2
0
1
7
).
ENI
S
A
th
re
a
t
lan
d
sc
a
p
e
re
p
o
rt
2
0
1
7
-
EU
L
a
w
a
n
d
P
u
b
l
ica
ti
o
n
s.
h
tt
p
s://
d
o
i
.
o
rg
/1
0
.
2
8
2
4
/9
6
7
1
9
2
[5
]
Da
ta,
G
.
,
&
Re
g
u
latio
n
,
P
.
(2
0
1
8
)
.
F
ra
u
d
&
se
c
u
rit
y
,
(A
p
ril
).
[6
]
S
a
h
,
U.
K.,
&
P
a
rm
a
r,
N.
(2
0
1
7
)
.
A
n
a
p
p
ro
a
c
h
f
o
r
M
a
li
c
io
u
s S
p
a
m
De
tec
ti
o
n
in
Em
a
il
w
it
h
c
o
m
p
a
ris
o
n
o
f
d
if
f
e
r
e
n
t
c
las
si
f
iers
.
[7
]
M
a
n
w
a
r,
S
.
R.
,
L
a
m
b
h
a
te,
P
.
,
&
P
a
ti
l
,
J.
(2
0
1
7
).
Clas
sif
ica
ti
o
n
M
e
th
o
d
s
f
o
r
S
p
a
m
De
tec
ti
o
n
In
On
li
n
e
S
o
c
ia
l
Ne
tw
o
rk
.
[8
]
A
lb
e
rto
,
T
.
C.
,
L
o
c
h
ter,
J
.
V
.
,
&
A
l
m
e
id
a
,
T
.
A
.
(2
0
1
5
,
De
c
e
m
b
e
r).
T
u
b
e
sp
a
m
:
Co
m
m
e
n
t
sp
a
m
f
il
terin
g
o
n
y
o
u
tu
b
e
.
I
n
M
a
c
h
i
n
e
L
e
a
r
n
in
g
a
n
d
Ap
p
li
c
a
ti
o
n
s
(
ICM
L
A),
2
0
1
5
I
EE
E
1
4
t
h
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
(
p
p
.
1
3
8
-
1
4
3
).
IEE
E.
[9
]
Ha
y
a
ti
,
P
.
,
&
P
o
td
a
r,
V.
(2
0
0
9
,
J
u
n
e
).
T
o
w
a
rd
sp
a
m
2
.
0
:
a
n
e
v
a
lu
a
ti
o
n
o
f
we
b
2
.
0
a
n
ti
-
sp
a
m
m
e
th
o
d
s.
In
I
n
d
u
strial
In
f
o
rm
a
ti
c
s,
2
0
0
9
.
IND
IN
2
0
0
9
.
7
th
I
EE
E
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
(
p
p
.
8
7
5
-
8
8
0
).
IE
E
E.
[1
0
]
Ka
u
sh
a
l,
R.
,
S
a
h
a
,
S
.
,
Ba
jaj,
P
.
,
&
Ku
m
a
ra
g
u
ru
,
P
.
(2
0
1
6
,
De
c
e
m
b
e
r).
Kid
s
T
u
b
e
:
De
tec
ti
o
n
,
c
h
a
ra
c
teriz
a
ti
o
n
a
n
d
a
n
a
ly
sis
o
f
c
h
il
d
u
n
sa
f
e
c
o
n
ten
t
&
p
ro
m
o
ters
o
n
Yo
u
T
u
b
e
.
In
Pri
v
a
c
y
,
S
e
c
u
rity
a
n
d
T
ru
st
(
PS
T
),
2
0
1
6
1
4
th
An
n
u
a
l
Co
n
fer
e
n
c
e
o
n
(p
p
.
1
5
7
-
16
4
)
.
IE
EE
.
[1
1
]
Af
z
a
l,
H.,
&
M
e
h
m
o
o
d
,
K.
(
2
0
1
6
,
Ja
n
u
a
ry
).
S
p
a
m
f
il
terin
g
o
f
b
i
-
li
n
g
u
a
l
tw
e
e
ts
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
.
In
Ad
v
a
n
c
e
d
C
o
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
(
ICACT
),
2
0
1
6
1
8
th
In
te
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
(p
p
.
7
1
0
-
7
1
4
).
IEE
E.
[1
2
]
W
u
,
F
.
,
&
Hu
a
n
g
,
Y.
(
2
0
1
7
).
S
o
c
ial
S
p
a
m
m
e
r
a
n
d
S
p
a
m
M
e
s
s
a
g
e
De
t
e
c
ti
o
n
in
a
n
O
n
li
n
e
S
o
c
i
a
l
Ne
t
w
o
rk
:
A
Co
d
e
tec
ti
o
n
A
p
p
ro
a
c
h
.
S
o
c
ia
l
Ne
two
rk
An
a
lys
is:
In
ter
d
isc
i
p
li
n
a
ry
Ap
p
ro
a
c
h
e
s a
n
d
Ca
se
S
tu
d
ies
,
2
2
5
.
[1
3
]
P
h
a
n
,
A
.
V
.
,
L
e
Ng
u
y
e
n
,
M
.
,
&
Bu
i,
L
.
T
.
(2
0
1
7
)
.
F
e
a
tu
re
w
e
ig
h
ti
n
g
a
n
d
S
VM
p
a
ra
m
e
ters
o
p
ti
m
iz
a
ti
o
n
b
a
se
d
o
n
g
e
n
e
ti
c
a
lg
o
rit
h
m
s
f
o
r
c
las
si
f
ica
ti
o
n
p
ro
b
lem
s.
Ap
p
li
e
d
In
telli
g
e
n
c
e
,
46
(2
),
4
5
5
-
4
6
9
.
[1
4
]
G
u
rso
y
,
M
.
E.
,
In
a
n
,
A
.
,
Ne
r
g
iz,
M
.
E.
,
&
S
a
y
g
in
,
Y.
(2
0
1
7
).
Dif
fe
re
n
ti
a
ll
y
p
riv
a
te
n
e
a
re
st
n
e
ig
h
b
o
r
c
las
si
f
ica
ti
o
n
.
Da
t
a
M
in
i
n
g
a
n
d
K
n
o
w
led
g
e
Disc
o
v
e
ry
,
31
(
5
),
1
5
4
4
-
1
5
7
5
.
[1
5
]
U
y
sa
l,
A
.
K.,
G
u
n
a
l,
S
.
,
Erg
in
,
S
.
,
&
G
u
n
a
l,
E.
S
.
(2
0
1
3
).
T
h
e
imp
a
c
t
o
f
f
e
a
tu
re
e
x
trac
ti
o
n
a
n
d
se
lec
ti
o
n
o
n
S
M
S
sp
a
m
f
il
terin
g
.
El
e
k
tro
n
ik
a
Ir
El
e
k
tro
tec
h
n
ik
a
,
1
9
(5
),
6
7
–
7
2
.
h
tt
p
s:
//
d
o
i
.
o
rg
/1
0
.
5
7
5
5
/j
0
1
.
e
e
e
.
1
9
.
5
.
1
8
2
9
[1
6
]
S
a
d
o
o
n
,
O.
H.,
&
Yu
so
f
,
Y.
(2
0
1
7
).
De
tec
ti
n
g
M
a
li
c
io
u
s
Us
e
r
in
Yo
u
T
u
b
e
Us
in
g
Ed
g
e
Ra
n
k
Ba
se
d
F
e
a
tu
re
S
e
t.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
ft
Co
mp
u
t
in
g
,
12
(
1
),
7
-
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.