I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
,
p
p
.
2
0
7
7
~
2
0
8
6
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
3
.
pp
207
7
-
2
0
8
6
2077
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Unv
eiling
perc
ept
io
ns: as
pect
-
ba
sed sentime
nt
a
na
ly
sis
of
M
a
la
y
sia
’
s e
-
ha
iling
reviews
K
hy
rina
Airin F
a
riza
Abu S
a
m
a
h
1
,
M
o
ha
ma
d Az
a
n Am
i
t
1
,
Siti
Sa
lwa
Sa
lleh
2
,
Wa
nn
o
ra
ini
Abd
ul L
a
t
if
1
,
N
urul
‘
Azw
a
K
a
m
a
rudin
1
,
Sh
a
ha
da
n Sa
a
d
1
,
M
o
hd
No
r
H
a
j
a
r
H
a
s
ro
l J
o
no
1
1
C
o
l
l
e
g
e
o
f
C
o
m
p
u
t
i
n
g
,
I
n
f
o
r
mat
i
c
s
a
n
d
M
a
t
h
e
m
a
t
i
c
s
,
U
n
i
v
e
r
si
t
i
Te
k
n
o
l
o
g
i
M
A
R
A
M
e
l
a
k
a
B
r
a
n
c
h
,
J
a
si
n
C
a
m
p
u
s,
M
e
l
a
k
a
,
M
a
l
a
y
s
i
a
2
C
o
l
l
e
g
e
o
f
C
o
m
p
u
t
i
n
g
,
I
n
f
o
r
mat
i
c
s
a
n
d
M
a
t
h
e
m
a
t
i
c
s
,
U
n
i
v
e
r
si
t
i
Te
k
n
o
l
o
g
i
M
A
R
A
N
e
g
e
r
i
S
e
m
b
i
l
a
n
B
r
a
n
c
h
,
N
e
g
e
r
i
S
e
m
b
i
l
a
n
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
ul
10
,
2
0
2
4
R
ev
is
ed
Sep
30
,
2
0
2
4
Acc
ep
ted
Oct
7
,
2
0
2
4
Th
e
g
r
o
win
g
d
e
m
a
n
d
fo
r
e
-
h
a
il
i
n
g
se
rv
ice
s
i
n
M
a
lay
sia
lea
d
s
t
o
in
c
re
a
se
d
c
o
m
p
e
ti
ti
o
n
a
m
o
n
g
m
o
re
t
h
a
n
2
0
li
c
e
n
se
d
e
-
h
a
il
i
n
g
se
rv
ice
p
ro
v
id
e
rs.
Co
n
su
m
e
r
sa
ti
sfa
c
ti
o
n
is a cru
c
ial
fa
c
to
r
in
fl
u
e
n
c
in
g
v
a
riab
les
in
th
e
b
u
sin
e
ss
o
rg
a
n
iza
ti
o
n
,
a
n
d
u
n
d
e
rsta
n
d
i
n
g
c
o
n
su
m
e
rs
’
p
e
rc
e
p
ti
o
n
s
is
v
it
a
l
f
o
r
se
rv
ice
imp
ro
v
e
m
e
n
t.
Re
v
iew
s
o
n
e
-
h
a
il
in
g
se
rv
ice
s
a
re
u
n
stru
c
tu
re
d
d
a
ta
a
n
d
m
a
ss
iv
e
,
m
a
k
in
g
c
o
m
p
a
riso
n
s
d
iffi
c
u
lt
.
T
h
u
s
,
th
is
st
u
d
y
a
ims
t
o
c
las
sify
M
a
lay
sia
’
s
e
-
h
a
il
in
g
se
rv
ice
re
v
i
e
ws
fro
m
G
o
o
g
le
P
lay
S
t
o
re
a
n
d
X
u
sin
g
late
n
t
D
iri
c
h
let
a
ll
o
c
a
ti
o
n
(LD
A)
a
n
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM).
As
p
e
c
t
-
b
a
se
d
se
n
ti
m
e
n
t
a
n
a
ly
sis
(ABSA)
wa
s
p
e
rfo
rm
e
d
u
sin
g
a
t
wo
-
sta
g
e
d
m
e
th
o
d
,
a
p
p
ly
in
g
LDA
fo
r
a
sp
e
c
t
c
a
teg
o
ry
d
e
tec
ti
o
n
a
n
d
S
VM
fo
r
a
sp
e
c
t
se
n
ti
m
e
n
t
c
las
sifica
ti
o
n
se
p
a
ra
tely
.
F
a
re
,
a
v
a
il
a
b
il
i
t
y
,
c
o
m
fo
r
t,
t
ime
,
a
n
d
c
o
n
v
e
n
ien
c
e
a
re
fiv
e
p
re
d
e
term
in
e
d
a
sp
e
c
t
c
a
teg
o
ries
in
th
is stu
d
y
.
Th
e
LDA
fo
r
E
n
g
li
sh
a
n
d
M
a
lay
a
c
h
iev
e
d
a
p
e
rp
lex
it
y
o
f
-
7
.
3
1
a
n
d
-
7
.
4
9
,
re
sp
e
c
ti
v
e
ly
.
Be
sid
e
s,
th
e
a
c
c
u
ra
c
y
sc
o
re
s
o
f
S
VM
fo
r
En
g
li
sh
a
n
d
M
a
la
y
a
re
8
6
.
3
2
%
a
n
d
6
2
.
9
7
%
,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
AB
SA
Data
v
is
u
aliza
tio
n
E
-
h
ailin
g
s
er
v
ices
L
aten
t
D
ir
ich
let
allo
ca
tio
n
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Kh
y
r
in
a
Air
in
Far
iza
Ab
u
Sa
m
ah
C
o
lleg
e
o
f
C
o
m
p
u
tin
g
,
I
n
f
o
r
m
atics a
n
d
Ma
th
em
atics
Un
iv
er
s
iti T
ek
n
o
lo
g
i
MA
R
A
Me
lak
a
B
r
an
ch
,
J
asin
C
am
p
u
s
Me
r
lim
au
,
7
7
3
0
0
,
Me
lak
a,
Ma
lay
s
ia
E
m
ail: k
h
y
r
in
a
7
8
3
@
u
itm
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
o
n
ic
h
ailin
g
s
er
v
ices
(
e
-
h
ailin
g
)
a
r
e
o
n
-
d
em
an
d
tr
a
n
s
p
o
r
tatio
n
s
er
v
ices
th
at
allo
w
co
n
s
u
m
er
s
to
b
o
o
k
a
r
id
e
u
s
in
g
a
m
o
b
ile
ap
p
licatio
n
.
T
h
e
a
d
v
en
t o
f
e
-
h
ailin
g
s
er
v
ices h
as in
tr
o
d
u
ce
d
a
n
ew
alter
n
ativ
e
in
th
e
wo
r
ld
o
f
p
u
b
lic
tr
a
n
s
p
o
r
tatio
n
,
wh
ich
o
f
f
er
s
a
p
er
s
o
n
al
ca
r
s
er
v
ice
[
1
]
.
E
-
h
ailin
g
s
er
v
ices
p
r
o
v
id
e
n
u
m
er
o
u
s
ad
v
an
tag
es
to
co
n
s
u
m
er
s
,
s
u
ch
as
c
h
ea
p
er
f
ar
es,
s
af
e
tr
av
el,
co
n
s
u
m
e
r
r
e
v
iews,
ea
s
y
ac
ce
s
s
,
co
m
f
o
r
t,
an
d
co
n
v
en
ien
ce
[
2
]
.
Mo
r
eo
v
er
,
co
n
s
u
m
e
r
s
f
ee
l
it
is
m
o
r
e
co
m
f
o
r
ta
b
le
u
s
in
g
p
r
i
v
ate
v
eh
icles,
s
u
ch
as
b
u
s
es,
tr
ain
s
,
m
o
n
o
r
ails
,
an
d
co
m
m
u
ter
s
,
th
an
p
u
b
lic
tr
an
s
p
o
r
t.
As
a
r
esu
lt,
co
n
s
u
m
er
s
p
r
ef
er
to
u
s
e
e
-
h
ailin
g
s
er
v
ices
f
o
r
p
u
b
lic
tr
a
n
s
p
o
r
tatio
n
b
ec
a
u
s
e
o
f
th
eir
c
o
n
v
en
ie
n
ce
an
d
p
u
n
ctu
ality
[
1
]
,
[
3
]
.
I
n
Ma
lay
s
ia,
th
e
d
em
an
d
f
o
r
e
-
h
ailin
g
s
er
v
i
ce
s
h
as
ac
ce
ler
ated
b
ased
o
n
i
n
cr
ea
s
ed
d
aily
tr
av
el
d
em
an
d
s
[
4
]
.
Mo
r
e
th
an
2
0
e
-
h
ailin
g
s
er
v
ice
p
r
o
v
id
e
r
s
,
i
n
clu
d
in
g
Gr
ab
,
Ma
x
im
,
an
d
Air
Asi
a
r
id
e,
ar
e
licen
s
ed
b
y
th
e
L
an
d
Pu
b
lic
T
r
an
s
p
o
r
t
Ag
en
c
y
(
APAD)
.
T
h
is
g
r
o
win
g
n
etwo
r
k
o
f
e
-
h
ailin
g
s
er
v
ices
lead
s
to
in
ten
s
if
ied
co
m
p
etitio
n
in
th
e
e
-
h
ailin
g
in
d
u
s
tr
y
[
3
]
,
[
5
]
.
I
n
th
e
co
n
te
x
t
o
f
p
u
b
lic
tr
a
n
s
p
o
r
t
s
er
v
ices,
th
e
im
p
o
r
tan
ce
o
f
co
n
s
u
m
er
s
atis
f
ac
tio
n
p
o
s
itiv
ely
in
f
lu
en
ce
s
s
o
m
e
v
ar
iab
les
in
t
h
e
b
u
s
in
ess
o
r
g
an
izatio
n
[
3
]
,
[
6
]
,
[
7
]
.
I
f
th
e
co
n
s
u
m
e
r
s
ar
e
s
atis
f
ied
,
it
p
r
o
v
es
th
e
co
m
p
an
y
p
r
o
v
id
es
ex
ce
lle
n
t
s
er
v
ice.
Oth
er
wis
e,
it
m
i
g
h
t
m
ea
n
th
at
t
h
e
s
er
v
ice
d
o
es
n
o
t
m
ee
t
th
e
n
ee
d
s
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
7
7
-
2
0
8
6
2078
th
e
co
n
s
u
m
er
s
.
Satis
f
ied
co
n
s
u
m
er
s
will
u
s
e
th
e
e
-
h
ailin
g
s
er
v
ices
ag
ain
,
b
ec
o
m
e
lo
y
al
to
th
e
b
r
an
d
s
an
d
m
ig
h
t
in
f
lu
e
n
ce
o
th
e
r
s
to
u
s
e
th
e
s
am
e
s
er
v
ices.
I
n
o
th
er
wo
r
d
s
,
co
n
s
u
m
e
r
s
atis
f
ac
tio
n
s
u
b
s
tan
tially
af
f
ec
ts
th
e
in
ten
tio
n
to
u
s
e
e
-
h
ailin
g
s
er
v
ices
[
4
]
,
[
8
]
.
I
t
is
in
f
lu
e
n
c
ed
b
y
s
er
v
ice
q
u
ality
d
im
e
n
s
io
n
s
[
9
]
,
[
1
0
]
s
in
ce
g
o
o
d
s
er
v
ice
q
u
ality
lead
s
to
a
s
atis
f
ied
f
ee
lin
g
[
1
1
]
.
Hen
c
e,
u
n
d
er
s
tan
d
i
n
g
th
e
co
n
s
u
m
e
r
s
’
p
er
ce
p
tio
n
an
d
s
atis
f
ac
tio
n
lev
el
to
war
d
s
th
e
s
er
v
ice
is
v
er
y
im
p
o
r
ta
n
t
as
it
ca
n
h
elp
th
e
c
o
m
p
an
y
to
im
p
r
o
v
e
its
s
er
v
ice
an
d
g
r
o
w
its
b
u
s
in
ess
[
1
]
.
C
o
n
s
u
m
er
s
atis
f
ac
tio
n
lev
els
ca
n
b
e
ev
alu
ated
b
y
a
n
aly
zin
g
co
n
s
u
m
er
r
ev
iews.
E
-
h
ailin
g
c
o
n
s
u
m
er
s
s
h
ar
e
th
e
ir
f
ee
d
b
ac
k
,
o
p
in
io
n
s
,
an
d
ex
p
er
ien
ce
s
th
r
o
u
g
h
o
n
lin
e
p
latf
o
r
m
s
s
u
ch
as
s
o
cial
m
ed
ia
an
d
m
o
b
ile
ap
p
licatio
n
s
to
r
es.
So
cial
m
ed
ia
h
as
b
ec
o
m
e
in
t
eg
r
al
to
o
u
r
d
aily
liv
es,
ch
an
g
in
g
h
o
w
p
eo
p
le
co
m
m
u
n
icat
e
an
d
g
ain
in
f
o
r
m
atio
n
.
X,
f
o
r
m
er
ly
k
n
o
wn
as
T
witter
,
r
ec
o
r
d
ed
5
.
5
m
illi
o
n
u
s
er
s
in
Ma
lay
s
ia
in
ea
r
ly
2
0
2
3
[
1
2
]
.
C
o
n
s
u
m
er
s
s
h
ar
e
th
eir
th
o
u
g
h
ts
an
d
v
iews
ab
o
u
t
e
-
h
ailin
g
o
n
X.
I
t
h
as
b
ec
o
m
e
t
h
e
m
o
s
t
p
o
p
u
lar
s
o
cial
m
ed
ia
s
ite
f
o
r
g
ettin
g
in
f
o
r
m
atio
n
d
u
e
to
th
e
av
ailab
ilit
y
,
ac
ce
s
s
ib
ilit
y
,
an
d
r
ich
n
ess
o
f
co
n
ten
t
[
1
3
]
.
B
esid
es,
Go
o
g
le
Play
Sto
r
e
(
Go
o
g
lePS)
is
a
m
o
b
ile
ap
p
licatio
n
s
to
r
e
wh
er
e
th
e
e
-
h
ailin
g
ap
p
licatio
n
ca
n
b
e
d
o
wn
lo
ad
e
d
an
d
in
s
talled
.
Go
o
g
lePS
allo
ws
co
n
s
u
m
er
s
to
r
ate
th
ese
ap
p
licatio
n
s
f
r
ee
ly
an
d
s
u
b
m
it
th
eir
r
ev
iews
an
d
s
u
g
g
esti
o
n
s
ab
o
u
t
th
e
ap
p
lica
tio
n
s
.
W
h
eth
er
p
o
s
itiv
e
o
r
n
e
g
ativ
e,
th
ese
r
ev
iews
ar
e
cr
it
ical
d
ata
th
at
g
iv
e
u
s
ef
u
l
in
f
o
r
m
atio
n
to
th
e
co
m
p
an
ies
an
d
th
e
p
o
ten
tial
e
-
h
ai
lin
g
co
n
s
u
m
er
s
f
o
r
d
ec
is
io
n
-
m
ak
in
g
.
C
o
n
s
u
m
er
s
m
ay
r
e
f
er
t
o
th
is
f
ee
d
b
ac
k
to
co
m
p
a
r
e
a
n
d
c
h
o
o
s
e
th
e
b
est
o
p
tio
n
f
o
r
e
-
h
ailin
g
s
er
v
ice
s
.
C
o
n
s
u
m
er
s
m
u
s
t
an
aly
ze
a
lar
g
e
v
o
lu
m
e
o
f
o
p
i
n
io
n
ated
d
ata
to
g
ain
b
etter
in
s
ig
h
t.
An
aly
zin
g
th
e
r
ev
iews
i
n
v
o
lv
es
e
x
tr
ac
tin
g
r
elate
d
o
p
in
i
o
n
ated
s
en
ten
ce
s
,
r
ea
d
in
g
,
an
d
s
u
m
m
ar
izin
g
th
em
,
an
d
o
r
g
a
n
izin
g
t
h
em
in
to
u
s
ab
le
f
o
r
m
s
[
1
4
]
.
T
h
is
task
m
ak
es it d
if
f
icu
lt f
o
r
h
u
m
an
s
to
h
an
d
le
b
ig
d
ata
m
a
n
u
ally
an
d
co
n
s
u
m
es a
l
o
t o
f
ti
m
e
an
d
ef
f
o
r
t.
Sen
tim
en
ts
ar
e
r
ef
lecte
d
in
t
h
e
co
n
s
u
m
er
r
e
v
iews
b
y
th
e
c
o
n
s
u
m
er
’
s
c
h
o
ice
o
f
to
n
e
o
r
ex
p
r
ess
iv
e
s
ty
le
[
1
5
]
.
T
h
ese
s
en
tim
en
ts
c
an
b
e
eith
er
p
o
s
itiv
e,
n
eg
ativ
e
,
o
r
n
e
u
tr
al.
An
al
y
zin
g
s
en
tim
en
t
f
r
o
m
th
ese
tex
t
d
ata
is
k
n
o
wn
as
s
en
tim
en
t
an
aly
s
is
(
SA)
.
A
r
ev
iew
m
ig
h
t
in
clu
d
e
d
if
f
er
en
t
asp
ec
ts
o
f
th
e
en
tity
u
n
d
er
d
is
cu
s
s
io
n
,
ea
ch
with
its
s
en
tim
en
t
[
1
6
]
,
[
1
7
]
.
I
n
t
h
is
ca
s
e,
we
ap
p
lied
asp
ec
t
-
b
ased
s
en
tim
en
t
an
aly
s
is
(
AB
SA)
.
I
t
p
er
f
o
r
m
s
f
in
er
-
g
r
a
in
ed
an
aly
s
is
an
d
d
is
co
v
er
s
w
h
at
ex
ac
tly
p
eo
p
le
lik
e
o
r
d
is
lik
e.
T
h
u
s
,
AB
SA
is
m
o
r
e
p
r
ac
tical
as
it
p
r
o
v
id
es
ex
ac
t
s
en
tim
en
ts
ab
o
u
t
d
if
f
er
en
t
asp
ec
ts
o
f
en
titi
es
an
d
e
n
titi
es
th
em
s
elv
es,
wh
ich
ar
e
u
s
u
ally
r
eq
u
ir
e
d
f
o
r
ac
tio
n
[
1
8
]
.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
aim
s
to
class
if
y
an
d
v
is
u
alize
th
e
r
ev
iews
ab
o
u
t
e
-
h
ailin
g
s
er
v
ices
f
r
o
m
Go
o
g
lePS
an
d
X
u
s
in
g
AB
S
A.
T
h
is
p
r
o
ject
will
clas
s
if
y
t
h
e
s
en
tim
en
t
o
f
r
ev
iews
ab
o
u
t
e
-
h
ailin
g
s
er
v
ices
in
to
s
ev
er
al
asp
ec
t
ca
teg
o
r
ie
s
,
in
clu
d
in
g
f
ar
e
,
av
ailab
ilit
y
,
co
m
f
o
r
t,
tim
e
,
an
d
c
o
n
v
e
n
ien
ce
.
T
h
ese
asp
ec
t
ca
teg
o
r
ies
ar
e
th
e
s
er
v
ice
q
u
ality
v
ar
iab
les
d
er
iv
ed
f
r
o
m
p
r
ev
io
u
s
s
tu
d
ies
th
at
m
ay
in
f
lu
en
ce
co
n
s
u
m
er
s
’
in
ten
tio
n
to
u
s
e
th
e
e
-
h
ailin
g
s
er
v
ice
th
r
o
u
g
h
co
n
s
u
m
e
r
s
atis
f
ac
tio
n
.
W
e
u
s
ed
two
alg
o
r
ith
m
s
s
in
ce
th
is
s
tu
d
y
in
v
o
lv
ed
two
s
in
g
le
AB
S
A
task
s
:
asp
ec
t
ca
teg
o
r
y
d
etec
tio
n
(
AC
D)
an
d
asp
ec
t
s
en
tim
en
t
class
if
icat
io
n
(
ASC
)
.
W
e
i
m
p
lem
en
ted
laten
t
D
ir
ich
let
allo
ca
tio
n
(
L
DA)
to
d
etec
t
asp
ec
t
ca
teg
o
r
ies
in
r
e
v
iews.
I
t
is
s
im
p
ler
to
tr
ain
,
o
f
f
er
s
g
r
ea
te
r
p
r
ec
is
io
n
[
1
9
]
an
d
is
v
er
y
ef
f
icien
t
with
lar
g
e
co
r
p
u
s
[
2
0
]
.
Ad
d
iti
o
n
ally
,
th
e
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
was
ap
p
lied
to
cl
ass
if
y
th
e
s
en
tim
en
t
o
f
o
p
in
i
o
n
ated
tex
t.
SVM
was
ch
o
s
en
f
o
r
its
h
ig
h
ac
cu
r
a
cy
in
d
iv
er
s
e
s
tu
d
ies
an
d
its
ab
ilit
y
to
co
n
s
id
er
v
ar
io
u
s
d
o
cu
m
en
t
f
ea
tu
r
es,
i
n
clu
d
in
g
th
o
s
e
t
h
at
ar
e
o
f
ten
a
b
s
en
t,
m
itig
atin
g
in
f
o
r
m
atio
n
l
o
s
s
in
th
e
d
ata
[
2
1
]
,
[
2
2
]
.
T
h
e
class
if
icatio
n
alg
o
r
i
th
m
will
class
if
y
th
e
r
ev
iews
r
elate
d
to
e
-
h
ailin
g
s
er
v
ices
d
ir
ec
tly
o
r
in
d
ir
ec
tly
in
to
o
n
e
o
f
th
r
ee
s
en
tim
en
t p
o
l
ar
ities
: “
p
o
s
itiv
e”
,
“n
eg
ativ
e”
,
o
r
“n
e
u
tr
al”.
Data
v
is
u
aliza
tio
n
is
an
ess
en
tial
to
o
l
to
ac
q
u
ir
e
v
alu
ab
le
in
s
ig
h
t
as
it r
ev
ea
ls
h
i
d
d
en
p
atter
n
s
,
tr
en
d
s
,
an
d
co
r
r
elatio
n
s
b
etwe
en
d
at
a
p
iece
s
[
2
3
]
.
T
h
is
s
tu
d
y
u
tili
ze
d
f
o
u
r
d
is
tin
ct
v
is
u
aliza
ti
o
n
tech
n
iq
u
es:
p
ie
ch
ar
ts
,
b
ar
g
r
a
p
h
s
,
lin
e
g
r
ap
h
s
an
d
wo
r
d
clo
u
d
s
.
T
h
e
m
o
d
el
was
d
ev
elo
p
e
d
u
s
in
g
d
atas
ets
in
E
n
g
lis
h
a
n
d
B
ah
asa
Ma
lay
s
ia
to
an
aly
ze
th
e
s
en
tim
en
t
o
f
e
-
h
ailin
g
s
er
v
ice
r
ev
iews
in
b
o
th
lan
g
u
ag
es.
T
h
e
d
ata
is
v
is
u
alize
d
u
s
in
g
Plo
tly
,
an
in
ter
ac
tiv
e
p
lo
ttin
g
lib
r
ar
y
f
o
r
Py
th
o
n
a
f
ter
th
e
AC
D
an
d
A
SC
ar
e
d
o
n
e
.
T
h
e
r
esu
lts
ca
n
b
e
u
s
ed
to
b
o
o
s
t
c
o
n
s
u
m
er
s
atis
f
ac
tio
n
an
d
r
etai
n
th
em
.
T
h
u
s
,
co
n
s
u
m
er
s
will
ex
p
lo
r
e
p
o
ten
tial
n
ew
m
ar
k
ets
an
d
e
f
f
ec
tiv
ely
a
d
d
r
ess
an
y
is
s
u
es
th
ey
en
co
u
n
ter
.
T
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws:
s
ec
tio
n
1
b
eg
in
s
with
a
b
r
ief
in
tr
o
d
u
ctio
n
.
I
n
s
ec
tio
n
2
ex
p
lain
s
th
e
m
eth
o
d
o
lo
g
y
,
f
o
llo
wed
b
y
s
ec
ti
o
n
3
with
r
esu
lt
an
d
d
is
cu
s
s
io
n
.
Fin
ally
,
s
ec
tio
n
4
co
n
cl
u
d
es
th
e
s
tu
d
y
an
d
p
r
o
v
id
es
a
co
n
cise
an
al
y
s
is
o
f
p
o
s
s
ib
le
f
u
tu
r
e
en
h
an
ce
m
e
n
ts
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
r
esear
ch
m
eth
o
d
en
c
o
m
p
ass
es
task
s
s
u
ch
as
d
ata
co
llectio
n
,
p
r
e
-
p
r
o
ce
s
s
in
g
,
an
d
im
p
lem
en
tatio
n
o
f
th
e
L
DA
an
d
SVM
m
o
d
els.
Data
p
r
ep
ar
atio
n
in
clu
d
es
d
ata
ac
q
u
is
itio
n
an
d
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
to
en
s
u
r
e
th
e
r
elia
b
ilit
y
o
f
co
llected
d
ata,
f
o
llo
wed
b
y
th
e
ap
p
licatio
n
o
f
L
D
A
an
d
SVM
m
o
d
els
f
o
r
AC
D
an
d
ASC
,
r
esp
ec
tiv
ely
.
T
h
e
o
u
tp
u
t c
o
m
p
r
is
es v
is
u
alize
d
an
d
r
e
p
o
r
ted
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Un
ve
ilin
g
p
ercep
tio
n
s
:
a
s
p
ec
t
-
b
a
s
ed
s
en
timen
t
…
(
K
h
yrin
a
A
ir
in
F
a
r
iz
a
A
b
u
S
a
ma
h
)
2079
2
.
1
.
Da
t
a
co
llect
i
o
n a
nd
pre
-
pro
ce
s
s
ing
A
s
u
p
er
v
is
ed
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
el
was
em
p
lo
y
e
d
f
o
r
asp
ec
t
s
en
tim
en
t
class
if
icati
o
n
in
b
o
th
E
n
g
lis
h
an
d
Ma
lay
lan
g
u
ag
es.
T
h
u
s
,
a
p
r
elab
elled
d
ataset
is
r
eq
u
ir
ed
to
t
r
ain
an
d
test
th
e
m
o
d
el.
T
h
e
E
n
g
lis
h
d
ataset
was
r
etr
iev
ed
f
r
o
m
Ka
g
g
le,
wh
er
ea
s
t
h
e
Ma
lay
d
ataset
was
d
o
wn
lo
ad
ed
f
r
o
m
Gith
u
b
.
Fo
r
th
e
m
o
d
e
l
tr
ain
in
g
a
n
d
test
in
g
p
u
r
p
o
s
es,
a
g
en
er
al
d
ataset
co
n
s
is
tin
g
o
f
v
ar
io
u
s
d
o
m
ain
s
was
u
tili
ze
d
.
T
h
is
is
b
ec
a
u
s
e
n
o
p
r
elab
elled
d
ataset
r
ep
o
s
ito
r
y
r
elate
d
to
th
e
e
-
h
ailin
g
s
er
v
ice
was
f
o
u
n
d
,
an
d
m
an
u
al
a
n
n
o
t
atio
n
o
f
d
atasets
is
v
er
y
tim
e
-
c
o
n
s
u
m
in
g
.
A
to
tal
o
f
1
6
2
,
9
8
0
E
n
g
lis
h
tex
t d
ata
a
n
d
6
,
7
0
2
Ma
la
y
tex
t d
ata
wer
e
ac
q
u
ir
ed
.
T
h
e
r
ev
iew
d
ataset
f
o
r
th
e
th
r
ee
e
-
h
ailin
g
s
er
v
ices,
Gr
ab
,
Ma
x
im
,
an
d
Air
Asi
a
R
id
e,
w
as
o
b
tain
ed
f
r
o
m
Go
o
g
lePS
an
d
X
(
f
o
r
m
er
ly
k
n
o
wn
as
T
witter
)
b
y
u
t
ilizin
g
Py
th
o
n
,
G
o
o
g
le
Play
Scr
ap
er
,
an
d
T
wee
t
Har
v
est.
T
h
e
s
cr
ap
p
e
d
r
e
v
iews
wer
e
d
ated
f
r
o
m
1
J
an
u
ar
y
2
0
2
3
to
3
1
Au
g
u
s
t
2
0
2
3
.
A
t
o
tal
o
f
3
2
,
6
6
4
r
aw
d
ata
wer
e
c
o
llected
in
E
n
g
lis
h
an
d
Ma
lay
,
with
2
1
,
2
9
0
d
a
ta
co
llected
f
o
r
Gr
ab
,
1
0
,
8
4
5
d
ata
c
o
llected
f
o
r
Ma
x
im
,
an
d
5
3
4
d
ata
co
llecte
d
f
o
r
Air
Asi
a
R
id
e.
T
h
e
d
ata
was f
in
ally
s
av
ed
in
a
C
SV f
o
r
m
at.
T
h
e
tex
t
d
ata
u
n
d
er
wen
t
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
.
I
t
in
v
o
lv
ed
d
ata
clea
n
in
g
an
d
p
r
ep
a
r
atio
n
,
r
em
o
v
in
g
ir
r
elev
an
t
f
ea
tu
r
es
th
at
d
o
n
o
t
co
n
tr
ib
u
te
v
alu
e
to
t
h
e
d
ata
an
aly
s
is
.
T
o
en
s
u
r
e
co
n
s
is
ten
cy
,
all
ch
ar
ac
ter
s
in
th
e
d
ataset
wer
e
co
n
v
e
r
ted
t
o
lo
wer
ca
s
e,
m
itig
atin
g
p
o
te
n
tial
ca
s
e
-
s
en
s
itiv
e
is
s
u
es
d
u
r
in
g
p
r
e
-
p
r
o
ce
s
s
in
g
.
Fo
llo
win
g
th
is
,
e
x
tr
an
eo
u
s
ch
ar
ac
ter
s
lik
e
em
o
jis
,
p
u
n
c
tu
atio
n
m
a
r
k
s
,
a
n
d
e
x
ce
s
s
iv
e
wh
ites
p
ac
e
wer
e
r
em
o
v
ed
.
Nu
ll
v
alu
es
an
d
d
u
p
licate
r
ev
iews
wer
e
elim
in
at
ed
f
r
o
m
t
h
e
d
ataset.
Sto
p
wo
r
d
s
wer
e
e
x
clu
d
ed
f
r
o
m
th
e
d
ata
to
r
ed
u
ce
its
d
im
en
s
io
n
ality
.
Su
b
s
eq
u
en
tly
,
th
e
d
ata
u
n
d
e
r
wen
t
to
k
en
izat
io
n
,
in
v
o
lv
in
g
th
e
s
ep
ar
atio
n
o
f
wo
r
d
s
f
r
o
m
th
e
r
est
o
f
th
e
tex
t.
Fo
llo
win
g
to
k
en
izatio
n
,
th
e
r
aw
tex
t
was
co
n
v
er
ted
in
to
s
ets
o
f
to
k
en
s
,
u
s
u
ally
in
d
iv
id
u
al
wo
r
d
s
.
T
h
en
,
tex
t
n
o
r
m
aliza
tio
n
was
d
o
n
e
s
ep
ar
ately
b
ased
o
n
th
e
r
ev
iew
’
s
lan
g
u
ag
e
th
r
o
u
g
h
th
e
lem
m
ati
za
tio
n
p
r
o
ce
s
s
.
T
h
is
p
r
o
ce
s
s
u
tili
ze
d
two
Py
th
o
n
lib
r
ar
ies:
“NL
T
K”
f
o
r
E
n
g
lis
h
tex
t a
n
d
“n
lp
-
i
d
”
f
o
r
Ma
lay
te
x
t.
T
h
is
p
r
o
ce
s
s
r
ed
u
ce
s
in
f
lec
tio
n
al
f
o
r
m
s
an
d
s
o
m
etim
es d
er
iv
atio
n
ally
r
elate
d
f
o
r
m
s
o
f
a
wo
r
d
to
a
co
m
m
o
n
b
ase
f
o
r
m
k
n
o
wn
as
lem
m
a.
I
t
ef
f
ec
tiv
el
y
r
e
d
u
ce
s
th
e
o
v
er
all
wo
r
d
co
u
n
t,
lo
wer
in
g
th
e
tex
t
’
s
d
im
en
s
io
n
ality
.
Af
ter
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
is
co
m
p
leted
,
th
e
f
in
al
d
ataset
is
r
ea
d
y
f
o
r
th
e
AC
D
an
d
ASC
.
T
h
e
m
o
d
el
’
s
ev
alu
atio
n
will b
e
elab
o
r
ate
d
u
p
o
n
in
th
e
f
o
llo
win
g
s
ec
tio
n
.
2
.
2
.
L
a
t
ent
D
irichlet
a
llo
c
a
t
i
o
n m
o
del
L
DA
is
an
u
n
s
u
p
e
r
v
is
ed
p
r
o
b
ab
ilis
tic
to
p
ic
m
o
d
ellin
g
tec
h
n
iq
u
e.
I
ts
f
u
n
d
am
en
tal
co
n
c
ep
t
is
th
at
d
o
cu
m
e
n
ts
ar
e
d
ep
icted
as
s
to
ch
asti
c
co
m
b
in
atio
n
s
o
f
late
n
t
to
p
ics,
with
ea
ch
to
p
ic
d
ef
in
e
d
b
y
a
d
is
tr
ib
u
tio
n
ac
r
o
s
s
wo
r
d
s
.
I
t
aim
s
t
o
id
en
ti
f
y
th
e
p
ar
am
eter
s
o
f
a
to
p
ic
-
w
o
r
d
d
is
tr
ib
u
tio
n
t
h
at
m
ax
im
ize
s
th
e
lik
elih
o
o
d
o
f
d
o
cu
m
e
n
ts
in
th
e
d
ataset
ac
r
o
s
s
a
g
iv
en
n
u
m
b
er
o
f
to
p
ics
.
Du
e
to
L
DA
’
s
em
p
h
asis
o
n
th
e
s
ig
n
if
ican
ce
o
f
ea
ch
to
p
ic
in
ev
er
y
d
o
cu
m
e
n
t
it
lear
n
s
,
it
b
ec
o
m
es
f
ea
s
ib
le
to
ascer
tain
wh
ich
to
p
ic
co
m
p
o
s
itio
n
m
o
s
t
ac
cu
r
ately
ca
p
t
u
r
es
th
e
ess
en
tial
co
n
ten
t
o
f
ea
c
h
d
o
cu
m
e
n
t
[
2
4
]
.
Path
an
a
n
d
Pra
k
ash
[
1
9
]
also
s
u
p
p
o
r
ted
t
h
e
id
ea
th
at
it
is
m
o
r
e
p
r
ec
is
e,
ea
s
ier
to
tr
ain
,
an
d
ca
p
ab
le
o
f
i
n
f
er
r
in
g
to
p
ics
f
r
o
m
a
g
iv
en
c
o
llectio
n
ef
f
o
r
tles
s
ly
with
o
u
t
u
s
in
g
p
r
io
r
k
n
o
wled
g
e
as
in
p
u
t,
m
ak
in
g
L
DA
th
e
m
o
s
t
co
m
m
o
n
to
p
ic
m
o
d
ellin
g
t
ec
h
n
iq
u
e
em
p
lo
y
ed
in
r
ea
l
-
wo
r
ld
s
ce
n
a
r
io
s
.
Fo
llo
win
g
th
e
tex
t
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
,
a
d
o
cu
m
e
n
t
-
ter
m
m
atr
ix
(
DT
M)
was
co
n
s
tr
u
c
ted
with
a
Py
th
o
n
lib
r
ar
y
f
o
r
to
p
ic
m
o
d
ellin
g
k
n
o
wn
as
Gen
s
im
.
T
h
e
s
tep
was
ac
co
m
p
lis
h
ed
b
y
co
n
v
er
tin
g
th
e
p
r
e
-
p
r
o
ce
s
s
ed
r
ea
l
-
w
o
r
ld
d
ata
i
n
to
a
d
ictio
n
ar
y
an
d
c
o
r
p
u
s
.
T
h
e
d
ictio
n
ar
y
estab
lis
h
es
a
m
ap
p
i
n
g
b
etwe
en
wo
r
d
s
an
d
th
eir
co
r
r
esp
o
n
d
in
g
in
te
g
er
I
Ds.
I
n
co
n
tr
ast,
th
e
co
r
p
u
s
is
a
lis
t
o
f
d
o
cu
m
en
ts
ex
p
r
ess
ed
in
a
B
OW
f
o
r
m
at.
Nex
t,
th
e
L
DA
m
o
d
el
was tr
ain
ed
o
n
th
e
p
r
e
v
io
u
s
ly
cr
ea
ted
DT
M
with
th
e
n
u
m
b
e
r
o
f
to
p
ics s
p
ec
if
ied
as
5
to
g
en
er
ate
f
iv
e
d
is
tin
ct
to
p
ics,
with
ea
ch
to
p
ic
b
ein
g
a
co
m
b
in
atio
n
o
f
k
ey
wo
r
d
s
.
T
h
ese
s
tep
s
wer
e
d
o
n
e
f
o
r
two
d
atasets
:
E
n
g
lis
h
an
d
Ma
lay
.
T
h
e
to
p
ics
wer
e
th
en
m
ap
p
ed
t
o
th
e
f
i
v
e
asp
ec
t
ca
te
g
o
r
ies,
n
am
ely
f
ar
e,
av
ailab
ilit
y
,
co
m
f
o
r
t,
tim
e,
an
d
co
n
v
en
ien
ce
,
b
y
r
e
f
er
r
in
g
to
th
e
k
ey
wo
r
d
s
o
f
ea
c
h
to
p
ic.
2
.
3
.
Su
pp
o
rt
v
ec
t
o
r
ma
chine m
o
del
SVM
is
a
n
o
n
-
p
r
o
b
ab
ilis
tic
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
.
I
t
i
d
en
tifie
s
an
o
p
tim
al
h
y
p
e
r
p
la
n
e
with
th
e
m
ax
im
ized
m
a
r
g
in
to
s
ep
ar
a
te
th
e
d
ata
in
to
d
is
tin
ct
class
es.
SVM
co
u
ld
ac
h
iev
e
h
ig
h
p
er
f
o
r
m
a
n
ce
in
p
r
ac
tical
ap
p
licatio
n
s
as
it
is
r
elativ
ely
ea
s
y
to
an
al
y
ze
m
ath
em
atica
lly
,
y
et
it
ca
n
ef
f
ec
tiv
e
ly
h
an
d
le
co
m
p
lex
m
o
d
els
[
2
5
]
.
B
ef
o
r
e
th
e
SVM
m
o
d
el
ca
n
b
e
ap
p
lied
to
r
ea
l
-
wo
r
ld
r
ev
iew
d
ata,
th
e
SVM
alg
o
r
ith
m
n
ee
d
s
to
b
e
tr
ain
ed
with
th
e
p
r
elab
elled
d
ataset
s
in
ce
it
is
a
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
.
As
illu
s
tr
a
ted
in
Fig
u
r
e
1
,
th
e
p
r
o
ce
s
s
o
f
tr
ain
in
g
an
d
test
in
g
th
e
SVM
alg
o
r
ith
m
b
eg
a
n
with
d
ata
p
r
ep
ar
atio
n
,
en
c
o
m
p
ass
in
g
th
e
d
ata
co
llectio
n
an
d
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
.
T
h
e
p
r
elab
elled
d
ataset
s
f
o
r
E
n
g
lis
h
an
d
Ma
lay
m
o
d
els
wer
e
ac
q
u
ir
e
d
f
r
o
m
Kag
g
le
an
d
GitHu
b
.
T
h
e
s
e
d
atasets
wer
e
th
en
p
r
e
-
p
r
o
c
ess
ed
th
r
o
u
g
h
ca
s
e
tr
an
s
f
o
r
m
a
tio
n
,
to
k
en
izatio
n
,
s
to
p
wo
r
d
s
an
d
n
o
is
e
r
em
o
v
al,
an
d
lem
m
atiza
tio
n
,
as e
x
p
lain
ed
in
s
ec
tio
n
2
.
4
.
T
h
e
p
r
elab
elled
d
atasets
wer
e
s
p
lit
in
to
tr
ain
in
g
an
d
test
i
n
g
s
ets
with
an
8
0
:2
0
r
atio
,
wh
er
e
8
0
%
co
n
s
titu
ted
th
e
tr
ain
in
g
d
ata,
an
d
th
e
r
em
ain
in
g
2
0
%
f
o
r
m
ed
th
e
test
in
g
d
ata.
T
o
en
s
u
r
e
s
u
f
f
icien
t
tr
ain
in
g
d
ata,
th
e
test
in
g
s
et
s
h
o
u
ld
n
o
t
ex
ce
ed
th
e
s
ize
o
f
th
e
tr
ain
in
g
s
et.
T
h
e
s
ee
d
f
o
r
th
e
r
an
d
o
m
n
u
m
b
er
g
en
er
ato
r
,
cr
u
cial
f
o
r
r
an
d
o
m
n
ess
,
was
s
et
to
4
2
.
B
o
th
tr
ain
in
g
an
d
te
s
tin
g
s
ets
wer
e
th
en
tr
an
s
f
o
r
m
ed
in
to
n
u
m
er
ical
v
ec
to
r
s
u
s
in
g
T
F
-
I
DF.
T
F
-
I
DF
is
a
weig
h
ted
s
tatis
tical
m
eth
o
d
f
o
r
ev
alu
atin
g
th
e
im
p
o
r
tan
ce
o
f
wo
r
d
s
to
tex
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
7
7
-
2
0
8
6
2080
I
ts
weig
h
tin
g
p
r
o
ce
s
s
im
p
r
o
v
es
th
e
ter
m
r
etr
iev
al
ef
f
ec
t
iv
en
ess
[
2
6
]
.
T
er
m
f
r
eq
u
en
c
y
(
T
F)
co
u
n
ts
th
e
o
cc
u
r
r
e
n
ce
s
o
f
a
p
h
r
ase
in
a
d
o
cu
m
en
t,
w
h
ile
in
v
er
s
e
d
o
cu
m
en
t
f
r
e
q
u
en
c
y
(
I
DF)
g
a
u
g
es
its
r
elev
an
ce
.
Fo
r
m
u
las f
o
r
T
F,
I
DF,
an
d
T
F
-
I
DF a
r
e
d
ef
in
e
d
in
(
1
)
,
(
2
)
,
a
n
d
(
3
)
,
r
esp
ec
tiv
ely
.
(
,
)
=
,
,
,
(
1
)
(
)
=
l
og
(
ℎ
,
)
(
2
)
-
(
,
)
=
(
,
)
×
(
)
(
3
)
Fo
llo
win
g
th
e
s
p
litt
in
g
an
d
v
e
cto
r
izatio
n
p
r
o
ce
s
s
,
th
e
SVM
class
if
icatio
n
m
o
d
el
was
estab
lis
h
ed
b
y
ca
llin
g
th
e
f
u
n
ctio
n
“sv
m
.
L
in
ea
r
SVC
(
)
”
an
d
was
tr
ain
ed
with
th
e
f
ea
tu
r
e
v
ec
to
r
a
n
d
th
e
tar
g
et
v
ar
iab
le
as
in
p
u
ts
.
T
h
is
p
r
o
ce
s
s
is
co
m
m
o
n
ly
k
n
o
wn
as
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
Nex
t,
a
p
r
ed
ictio
n
ca
n
b
e
g
en
er
ate
d
f
o
r
t
h
e
test
d
ataset.
T
h
e
m
o
d
el
’
s
ac
cu
r
ac
y
in
p
r
ed
ictin
g
th
e
test
d
ataset
is
p
r
esen
ted
as
a
p
e
r
ce
n
tag
e
o
f
co
r
r
ec
t
p
r
ed
ictio
n
s
r
elativ
e
to
th
e
to
tal
n
u
m
b
e
r
o
f
p
r
ed
ictio
n
s
g
en
er
at
ed
b
y
t
h
e
m
o
d
el.
2
.
4
.
M
o
del deplo
y
m
ent
Mo
d
el
d
ep
l
o
y
m
en
t
is
th
e
p
r
o
ce
s
s
o
f
p
u
ttin
g
th
e
d
ev
el
o
p
ed
m
o
d
els
in
to
p
r
ac
tical
u
s
e
.
I
n
m
an
y
in
s
tan
ce
s
,
it
in
v
o
lv
es
m
ak
in
g
a
m
o
d
el
ac
ce
s
s
ib
le
th
r
o
u
g
h
r
ea
l
-
tim
e
API
s
,
allo
win
g
f
o
r
th
e
r
etr
iev
al
o
f
in
f
o
r
m
atio
n
in
r
ea
l
-
tim
e.
Du
r
i
n
g
th
e
d
ep
lo
y
m
en
t
s
tag
e,
th
e
L
DA
m
o
d
el
clu
s
ter
ed
th
e
co
llected
r
ev
iews
with
to
p
ic
n
u
m
b
er
s
o
f
“0
”,
“1
”,
“2
”,
“3
”,
an
d
“
4
”.
T
h
e
v
alu
es
w
er
e
th
en
m
a
p
p
ed
with
th
e
asp
ec
t
ca
teg
o
r
ies
b
ased
o
n
th
e
to
p
ics g
en
er
ated
b
y
t
h
e
m
o
d
el,
as p
r
esen
ted
in
Fig
u
r
e
2
an
d
Fig
u
r
e
3
.
On
th
e
o
th
er
h
an
d
,
th
e
SV
M
m
o
d
el
was
r
ea
d
y
f
o
r
d
ep
lo
y
m
en
t.
B
ef
o
r
e
th
e
SVM
m
o
d
el
co
u
ld
p
er
f
o
r
m
th
e
s
en
tim
en
t
class
if
i
ca
tio
n
o
f
th
e
r
ea
l
-
wo
r
ld
r
ev
ie
w
d
ata,
th
e
d
ata
u
n
d
e
r
wen
t
a
v
ec
to
r
izatio
n
p
r
o
ce
s
s
u
s
in
g
T
F
-
I
DF.
O
n
ce
it
was
t
r
an
s
f
o
r
m
ed
in
to
n
u
m
er
ical
f
o
r
m
ats,
th
e
SVM
m
o
d
el
class
if
ied
th
e
r
ea
l
-
wo
r
l
d
r
ev
iew
d
ata
with
s
en
tim
en
t
l
ab
els
o
f
“
-
1
,
”
“0
,
”
an
d
“
1
,
”
co
r
r
esp
o
n
d
in
g
t
o
n
e
g
ativ
e,
n
eu
tr
al,
an
d
p
o
s
itiv
e
s
en
tim
en
ts
,
r
esp
ec
tiv
ely
.
Fig
u
r
e
1
.
Flo
w
d
ia
g
r
am
f
o
r
th
e
tr
ain
in
g
an
d
test
in
g
p
r
o
ce
s
s
o
f
SVM
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Un
ve
ilin
g
p
ercep
tio
n
s
:
a
s
p
ec
t
-
b
a
s
ed
s
en
timen
t
…
(
K
h
yrin
a
A
ir
in
F
a
r
iz
a
A
b
u
S
a
ma
h
)
2081
Af
ter
ap
p
l
y
in
g
th
e
m
o
d
els
t
o
m
ak
e
p
r
ed
ictio
n
s
b
ased
o
n
th
e
ac
q
u
ir
e
d
d
ata
an
d
e
v
a
lu
atin
g
its
p
er
f
o
r
m
an
ce
,
th
e
d
ata
was
v
is
u
alize
d
u
s
in
g
Plo
tly
,
an
o
p
e
n
-
s
o
u
r
ce
in
ter
ac
tiv
e
g
r
ap
h
ics
lib
r
ar
y
f
o
r
Py
th
o
n
.
C
h
ar
ts
wer
e
p
r
o
d
u
ce
d
u
s
in
g
t
h
e
ch
ar
t
s
tu
d
io
in
t
h
e
o
n
lin
e
v
er
s
io
n
o
f
Plo
tly
,
alo
n
g
with
th
e
en
ter
ed
d
ata.
T
h
e
o
u
tco
m
e
was
th
e
n
em
p
l
o
y
ed
i
n
co
n
s
tr
u
ctin
g
an
in
ter
ac
tiv
e
v
is
u
aliza
tio
n
to
o
l
th
at
p
r
esen
ted
th
e
r
esu
lts
o
f
r
ea
l
-
wo
r
ld
d
ata
an
al
y
s
is
.
W
o
r
d
clo
u
d
d
ata
v
is
u
aliza
tio
n
was
u
tili
ze
d
to
r
ep
r
esen
t
th
e
tex
t
d
ata
f
o
r
e
-
h
ailin
g
s
er
v
ices
g
en
er
ated
b
y
th
e
s
y
s
tem
.
W
o
r
d
s
wer
e
d
is
p
lay
ed
in
v
ar
io
u
s
co
lo
r
s
,
an
d
th
e
s
ize
o
f
ea
ch
wo
r
d
em
p
h
asi
ze
s
its
f
r
eq
u
en
cy
in
th
e
tex
t
d
ata.
T
h
e
ter
m
s
ass
o
ciate
d
with
e
-
h
ailin
g
s
er
v
ices
ar
e
r
ea
d
ily
id
en
tifia
b
le
d
u
e
to
th
eir
p
lace
m
en
t
i
n
th
e
wo
r
d
clo
u
d
.
Fig
u
r
e
2
.
T
o
p
ics g
en
e
r
ated
b
y
E
n
g
lis
h
L
DA
m
o
d
el
Fig
u
r
e
3
.
T
o
p
ics g
en
e
r
ated
b
y
Ma
lay
L
DA
m
o
d
el
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
M
o
del per
f
o
rma
nce
T
h
e
ass
ess
m
en
t
o
f
m
o
d
el
p
er
f
o
r
m
a
n
ce
is
cr
u
cial
f
o
r
en
s
u
r
in
g
its
ef
f
ec
tiv
e
n
ess
an
d
r
eliab
ilit
y
.
I
t
in
v
o
lv
es
ev
alu
atin
g
h
o
w
e
f
f
ec
tiv
ely
a
p
r
e
d
ictiv
e
m
o
d
el
ac
h
iev
es
s
p
ec
if
ied
g
o
als
an
d
p
r
o
v
id
es
ac
cu
r
ate
p
r
ed
ictio
n
s
f
o
r
n
ew,
u
n
s
ee
n
d
a
ta.
A
co
m
p
r
eh
en
s
iv
e
u
n
d
er
s
tan
d
in
g
o
f
m
o
d
el
p
er
f
o
r
m
a
n
ce
is
es
s
en
tial f
o
r
well
-
in
f
o
r
m
e
d
d
ec
is
io
n
-
m
a
k
in
g
a
n
d
d
eter
m
in
in
g
th
e
m
o
d
el
’
s
ef
f
ec
tiv
en
ess
in
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
.
Var
io
u
s
m
etr
ics
an
d
ev
alu
ati
o
n
tech
n
iq
u
es
ar
e
em
p
lo
y
ed
to
g
au
g
e
th
e
p
er
f
o
r
m
an
ce
o
f
a
m
o
d
el.
T
h
ese
ass
ess
m
en
ts
ty
p
ically
in
clu
d
e
m
ea
s
u
r
es
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
.
E
ac
h
m
et
r
ic
p
r
o
v
id
es
in
s
ig
h
ts
in
to
d
is
tin
ct
asp
ec
ts
o
f
th
e
m
o
d
el
’
s
p
e
r
f
o
r
m
an
ce
,
allo
win
g
it
to
g
ai
n
a
co
m
p
r
eh
en
s
iv
e
u
n
d
er
s
tan
d
i
n
g
o
f
its
s
tr
en
g
th
s
an
d
wea
k
n
ess
es.
3
.
1
.
1
.
P
er
plex
it
y
a
nd
co
here
nce
s
co
re
o
f
la
t
ent
D
irichlet
a
llo
ca
t
io
n
m
o
dels
Per
p
lex
ity
an
d
co
h
er
en
ce
s
co
r
es
wer
e
u
s
ed
as
t
h
e
ev
al
u
atio
n
m
etr
ics
to
ass
ess
L
DA
p
er
f
o
r
m
a
n
ce
.
Per
p
lex
ity
is
a
m
ea
s
u
r
e
o
f
h
o
w
well
th
e
to
p
ic
m
o
d
el
p
r
ed
icts
n
ew
o
r
u
n
s
ee
n
d
ata.
A
lo
wer
p
er
p
lex
ity
s
co
r
e
s
ig
n
if
ies
th
at
th
e
m
o
d
el
h
as
a
b
etter
p
er
f
o
r
m
an
ce
[
2
7
]
.
B
ased
o
n
Fig
u
r
e
4
,
t
h
e
Per
p
le
x
ity
o
f
E
n
g
lis
h
an
d
Ma
lay
L
DA
m
o
d
els
ar
e
-
7
.
3
1
an
d
-
7
.
4
9
,
r
esp
ec
tiv
ely
.
Alth
o
u
g
h
th
e
Per
p
lex
ity
o
f
b
o
th
m
o
d
els
is
b
elo
w
0
,
th
e
p
er
p
lex
ity
o
f
th
e
Ma
lay
L
DA
m
o
d
el
is
s
lig
h
tly
lo
wer
t
h
an
th
e
E
n
g
lis
h
L
DA
m
o
d
el.
I
t
in
d
icate
s
th
at
th
e
ab
ilit
y
o
f
th
e
Ma
la
y
L
DA
m
o
d
el
to
ac
cu
r
ately
p
r
ed
ict
th
e
asp
ec
t
ca
teg
o
r
y
o
f
e
-
h
ailin
g
r
ev
iews
is
s
lig
h
tly
b
etter
th
an
th
at
o
f
th
e
E
n
g
lis
h
L
DA
m
o
d
el.
On
th
e
o
t
h
er
h
a
n
d
,
th
e
co
h
er
e
n
ce
s
co
r
e
in
d
icate
s
th
e
lev
el
o
f
s
em
an
tic
s
im
ilar
ity
b
etwe
en
wo
r
d
s
o
n
a
to
p
ic.
I
t
is
m
ea
s
u
r
ed
o
n
a
s
ca
le
f
r
o
m
0
to
1
,
wh
er
e
a
h
ig
h
e
r
v
alu
e
m
ea
n
s
s
u
b
s
tan
tial
s
im
ilar
ity
an
d
th
at
th
e
to
p
ic
is
co
n
s
is
ten
t,
clea
r
,
an
d
r
elev
an
t
[
2
8
]
.
As
s
h
o
wn
in
Fig
u
r
e
5
,
th
e
co
h
er
en
ce
s
co
r
es
o
f
E
n
g
lis
h
an
d
Ma
la
y
L
DA
m
o
d
els
ar
e
0
.
5
8
an
d
0
.
4
9
,
r
esp
ec
tiv
ely
.
T
h
e
co
h
e
r
en
c
e
s
co
r
es
o
f
b
o
th
E
n
g
lis
h
an
d
Ma
lay
L
DA
m
o
d
els
ar
e
in
th
e
m
id
d
le
o
f
th
e
r
an
g
e
b
etwe
en
0
an
d
1
.
Ho
wev
er
,
th
e
co
h
e
r
en
ce
o
f
th
e
E
n
g
lis
h
L
D
A
m
o
d
el
is
s
lig
h
tly
h
ig
h
er
th
a
n
th
e
Ma
la
y
L
DA
m
o
d
el.
I
t
in
d
icate
s
th
at
th
e
d
e
g
r
ee
o
f
s
im
ilar
ity
b
etwe
en
k
ey
w
o
r
d
s
f
o
r
ea
ch
to
p
ic
o
f
th
e
E
n
g
lis
h
L
DA
m
o
d
el
is
s
lig
h
tly
h
ig
h
er
th
an
th
at
o
f
th
e
Ma
lay
L
DA
m
o
d
el.
I
t
ca
n
b
e
in
f
lu
en
ce
d
b
y
th
e
len
g
th
o
f
r
ev
iews
an
d
th
e
c
h
o
s
en
n
u
m
b
er
o
f
to
p
ics.
Sh
o
r
t
r
ev
iews
lack
co
n
tex
t
to
d
is
ce
r
n
m
ea
n
in
g
f
u
l
to
p
ics,
an
d
to
o
f
ew
to
p
ic
n
u
m
b
er
s
m
ay
lead
t
o
a
lo
wer
c
o
h
er
e
n
ce
s
co
r
e.
Ad
d
itio
n
ally
,
it
ca
n
also
b
e
d
u
e
to
f
u
zz
y
to
p
ics th
at
in
clu
d
e
m
a
n
y
d
i
f
f
er
en
t te
r
m
s
o
r
o
v
er
lap
s
em
an
tica
lly
with
o
th
er
to
p
ics
[
2
9
]
.
3
.
1
.
2
.
Acc
ura
cy
o
f
s
up
po
rt
v
ec
t
o
r
ma
chine m
o
dels
I
n
o
r
d
er
to
ev
alu
ate
th
e
ac
cu
r
ac
y
o
f
th
e
SVM
class
if
ier
m
o
d
el,
its
p
er
f
o
r
m
a
n
ce
is
m
ea
s
u
r
ed
b
y
co
m
p
ar
in
g
p
r
e
d
icted
v
alu
es
w
ith
ac
tu
al
v
alu
es
ex
tr
ac
ted
f
r
o
m
a
test
d
ataset.
T
ab
le
1
s
h
o
ws
th
at
th
e
E
n
g
lis
h
SVM
m
o
d
el
ac
h
ie
v
ed
a
n
ac
cu
r
ac
y
s
co
r
e
o
f
8
6
.
3
2
%.
Me
a
n
wh
ile,
th
e
ac
c
u
r
ac
y
s
co
r
e
d
er
iv
ed
f
r
o
m
th
e
Ma
la
y
SVM
m
o
d
el
was
6
2
.
9
7
%.
I
n
t
h
is
s
tu
d
y
,
th
e
c
o
n
f
u
s
io
n
m
atr
i
x
ass
ig
n
s
th
e
class
“n
eg
ativ
e”
to
th
e
n
u
m
b
e
r
-
1
,
“n
eu
tr
al”
to
0
,
an
d
“p
o
s
itiv
e”
t
o
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
7
7
-
2
0
8
6
2082
Mu
s
g
r
av
e
[
3
0
]
,
an
ac
cu
r
ac
y
s
co
r
e
ex
ce
e
d
in
g
9
0
%
is
c
o
n
s
id
er
ed
“E
x
ce
lle
n
t,”
wh
ile
s
co
r
e
s
b
etwe
en
7
0
%
an
d
9
0
%
ar
e
la
b
elled
“G
o
o
d
.
”
Acc
u
r
ac
y
r
an
g
es
b
etwe
e
n
6
0
%
an
d
7
0
%
is
d
ee
m
ed
“O
k
ay
,
”
an
d
an
y
th
in
g
b
elo
w
6
0
%
is
co
n
s
id
er
e
d
“P
o
o
r
.
”
T
h
u
s
,
th
e
ac
c
u
r
ac
y
o
f
t
h
e
E
n
g
lis
h
SVM
m
o
d
el
f
alls
with
in
th
e
“Go
o
d
”
r
an
g
e,
wh
ile
th
at
o
f
th
e
Ma
lay
SVM
m
o
d
el
is
r
eg
ar
d
e
d
as “
Ok
ay
”.
Fig
u
r
e
4
.
T
h
e
Per
p
lex
ity
o
f
E
n
g
lis
h
an
d
Ma
lay
L
DA
m
o
d
els
Fig
u
r
e
5
.
T
h
e
co
h
er
en
ce
s
co
r
e
o
f
E
n
g
lis
h
an
d
Ma
lay
L
DA
m
o
d
els
T
ab
le
1
.
R
esu
lts
o
f
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
an
d
F1
-
s
co
r
e
f
o
r
E
n
g
lis
h
an
d
Ma
lay
M
a
l
a
y
si
a
’
s e
-
h
a
i
l
i
n
g
p
e
r
c
e
p
t
i
o
n
f
o
r
E
n
g
l
i
s
h
a
n
d
M
a
l
a
y
La
n
g
u
a
g
e
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
En
g
l
i
sh
8
6
.
2
3
8
4
.
0
0
9
3
.
0
0
8
8
.
0
0
M
a
l
a
y
6
2
.
9
7
5
4
.
0
0
7
1
.
0
0
7
0
.
0
0
3
.
2
.
Ana
ly
s
is
o
f
a
s
pect
ca
t
eg
o
ries
3
.
2
.
1
.
O
v
er
a
ll ABS
A
T
h
e
co
m
p
lete
d
ata
an
aly
s
is
was
v
is
u
alize
d
u
s
in
g
d
ata
v
is
u
aliza
tio
n
tech
n
iq
u
es
s
u
c
h
as
p
ie
ch
ar
ts
,
b
ar
ch
ar
ts
,
lin
e
ch
ar
ts
an
d
w
o
r
d
cl
o
u
d
s
f
o
r
b
etter
v
is
io
n
.
T
ab
le
2
s
h
o
ws th
e
co
m
p
ar
is
o
n
o
f
s
en
t
im
en
t r
esu
lts
f
o
r
all
e
-
h
ailin
g
s
er
v
ices,
w
h
er
e
o
u
t
o
f
th
e
to
tal
o
f
1
7
,
2
5
7
s
en
tim
en
ts
,
it
was
d
is
tr
ib
u
ted
t
o
1
0
,
2
3
0
p
o
s
itiv
e,
3
,
7
8
6
n
eg
ativ
es
an
d
3
,
2
4
1
n
eu
tr
al
s
en
tim
en
ts
.
Fig
u
r
e
6
s
h
o
ws
th
e
b
ar
c
h
ar
t
o
f
th
e
to
tal
s
en
tim
en
ts
o
f
th
r
ee
e
-
h
ailin
g
s
er
v
ices
in
th
e
d
ataset,
wh
er
e
it
ex
h
ib
its
a
h
ig
h
e
r
f
r
e
q
u
en
c
y
o
f
p
o
s
itiv
e
m
en
tio
n
s
th
a
n
n
eu
tr
al
an
d
n
eg
ativ
e
m
en
tio
n
s
.
T
h
e
u
s
er
m
a
y
im
m
e
d
iately
co
m
p
ar
e
p
o
s
itiv
e,
n
eg
a
tiv
e,
an
d
n
e
u
tr
al
s
en
tim
en
ts
u
s
in
g
th
e
p
ie
ch
ar
t
’
s
p
er
ce
n
tag
e
v
alu
e
an
d
co
lo
r
d
if
f
er
en
ce
s
,
as in
Fig
u
r
e
7
.
T
h
e
asp
ec
t
ca
teg
o
r
ies
b
ased
o
n
f
iv
e
asp
ec
t
ca
teg
o
r
ies,
in
clu
d
in
g
f
ar
e,
a
v
ailab
ilit
y
,
co
m
f
o
r
t,
tim
e,
an
d
co
n
v
en
ie
n
ce
,
ar
e
v
is
u
alize
d
in
th
e
b
ar
g
r
a
p
h
,
as
in
Fig
u
r
e
8
.
User
s
m
ay
v
is
u
alize
th
e
t
o
tal
m
en
tio
n
s
o
f
ea
ch
e
-
h
ailin
g
s
er
v
ice
b
ased
o
n
s
p
ec
if
ic
asp
ec
t
ca
teg
o
r
ies.
Far
e
s
h
o
ws
th
e
h
ig
h
est
-
m
en
tio
n
e
d
s
en
tim
en
ts
f
o
r
all
e
-
h
ailin
g
s
er
v
ices,
an
d
tim
e
s
h
o
ws
th
e
lo
west
-
m
en
tio
n
ed
s
en
tim
en
ts
.
A
s
tack
ed
b
ar
g
r
a
p
h
b
r
ea
k
s
d
o
wn
th
e
an
aly
s
is
o
f
th
e
e
-
h
ailin
g
s
er
v
i
ce
’
s
asp
ec
t
ca
teg
o
r
ies
b
ased
o
n
s
en
tim
en
t
p
o
lar
ities
,
as
in
Fig
u
r
e
9
.
User
s
m
ay
v
is
u
alize
th
e
to
tal
s
en
tim
en
ts
b
ased
o
n
e
-
h
ailin
g
s
er
v
ices f
o
r
ea
ch
asp
ec
t c
ateg
o
r
y
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
r
esu
lts
f
o
r
Gr
ab
,
Ma
x
im
,
an
d
Air
Asi
a
r
id
e
e
-
h
a
i
l
i
n
g
serv
i
c
e
N
u
mb
e
r
o
f
r
e
v
i
e
w
s
N
u
mb
e
r
o
f
p
o
s
i
t
i
v
e
r
e
v
i
e
w
s
N
u
mb
e
r
o
f
n
e
g
a
t
i
v
e
r
e
v
i
e
w
s
N
u
mb
e
r
o
f
n
e
u
t
r
a
l
r
e
v
i
e
w
s
G
r
a
b
1
1
,
0
4
2
6
,
1
1
4
2
,
7
2
9
2
,
1
9
9
M
a
x
i
m
5
,
7
4
8
3
,
9
0
2
8
9
5
9
5
1
A
i
r
A
si
a
r
i
d
e
4
6
7
2
1
4
1
6
2
91
To
t
a
l
1
7
,
2
5
7
1
0
,
2
3
0
3
,
7
8
6
3
,
2
4
1
3
.
2
.
2
.
Wo
rd
clo
ud
AB
SA
I
n
Fig
u
r
e
1
0
s
h
o
ws
th
e
wo
r
d
clo
u
d
AB
SA
v
is
u
ally
f
o
r
th
r
e
e
s
en
tim
en
t
p
o
lar
ities
.
T
h
e
s
ize
o
f
ea
c
h
ter
m
r
ef
lects
its
f
r
e
q
u
en
c
y
in
th
e
d
ataset.
L
ar
g
e
r
s
izes
co
r
r
esp
o
n
d
to
h
ig
h
er
o
cc
u
r
r
en
ce
f
r
eq
u
en
cies.
Fig
u
r
e
1
0
(
a
)
r
ep
r
esen
ts
p
o
s
itiv
e
s
en
tim
en
t
tex
t
d
ata.
No
te
wo
r
th
y
p
o
s
itiv
e
ex
p
r
ess
io
n
s
lik
e
“g
o
o
d
,
”
“
b
a
ik
,
”
“g
r
ea
t,”
an
d
“e
asy
”
a
r
e
f
ea
tu
r
ed
in
th
e
wo
r
d
clo
u
d
,
h
ig
h
lig
h
tin
g
th
eir
ass
o
ciatio
n
with
p
o
s
itiv
e
s
en
tim
en
ts
.
Fig
u
r
e
1
0
(
b
)
d
ep
icts
a
v
is
u
aliza
tio
n
h
i
g
h
lig
h
tin
g
p
h
r
ases
ass
o
ciate
d
with
n
e
g
ativ
e
s
en
tim
en
t.
T
h
e
wo
r
d
cl
o
u
d
in
clu
d
es
ter
m
s
lik
e
“
b
ad
,
”
“
s
u
s
a
h
,
”
“e
x
p
e
n
s
iv
e,
”
an
d
“
u
s
eless
.
”
Fig
u
r
e
1
0
(
c)
ex
h
ib
it
s
th
e
wo
r
d
clo
u
d
r
ep
r
esen
tin
g
n
e
u
tr
al
em
o
tio
n
s
.
T
h
is
v
is
u
aliza
tio
n
h
ig
h
lig
h
ts
ter
m
s
ass
o
ciate
d
wi
th
n
eu
tr
al
m
en
tio
n
s
s
u
ch
as
“o
r
d
er
”,
“c
an
ce
l”,
an
d
“d
r
iv
er
”.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Un
ve
ilin
g
p
ercep
tio
n
s
:
a
s
p
ec
t
-
b
a
s
ed
s
en
timen
t
…
(
K
h
yrin
a
A
ir
in
F
a
r
iz
a
A
b
u
S
a
ma
h
)
2083
Fig
u
r
e
6
.
B
ar
ch
a
r
t o
f
t
h
e
to
tal
s
en
tim
en
ts
e
-
h
ailin
g
s
er
v
ices
Fig
u
r
e
7
.
Pie c
h
a
r
t o
f
p
er
ce
n
ta
g
e
s
en
tim
en
t in
d
ataset
Fig
u
r
e
8
.
B
ar
ch
a
r
t f
o
r
to
tal
m
en
tio
n
s
o
f
e
-
h
ailin
g
s
er
v
ices b
ased
o
n
asp
ec
t c
ateg
o
r
y
Fig
u
r
e
9
.
Stack
b
ar
ch
a
r
t f
o
r
to
tal
s
en
tim
en
ts
o
f
e
-
h
ailin
g
s
er
v
ices f
o
r
ea
c
h
asp
ec
t c
ateg
o
r
y
(
a)
(
b
)
(
c)
Fig
u
r
e
1
0
.
W
o
r
d
clo
u
d
s
f
o
r
(
a)
p
o
s
itiv
e
s
en
tim
en
ts
,
(
b
)
n
eg
at
iv
e
s
en
tim
en
ts
,
an
d
(
c
)
n
eu
tr
al
s
en
tim
en
ts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
7
7
-
2
0
8
6
2084
4.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
a
web
-
b
ased
ap
p
licatio
n
was
d
esig
n
e
d
an
d
d
ev
el
o
p
ed
to
class
if
y
th
e
r
ev
iews
o
f
Ma
lay
s
ia
’
s
e
-
h
ailin
g
s
er
v
ices:
Gr
ab
,
Ma
x
im
,
a
n
d
Air
Asi
a
R
id
e.
T
h
e
v
is
u
aliza
tio
n
o
f
A
B
SA
wa
s
ex
tr
ac
ted
f
r
o
m
Go
o
g
lePS
an
d
X
f
r
o
m
1
st
J
an
u
ar
y
2
0
2
3
to
3
1
st
Au
g
u
s
t
2
0
2
3
.
User
s
ca
n
u
tili
ze
th
e
em
b
ed
d
e
d
L
DA
an
d
SVM
m
o
d
els
o
n
an
y
tex
t
d
at
a
with
in
th
e
s
y
s
tem
.
T
h
e
d
at
a
co
llected
th
r
o
u
g
h
th
e
a
p
p
li
ca
tio
n
aid
s
u
s
er
s
i
n
ev
alu
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
e
-
h
ailin
g
s
er
v
ices
an
d
m
ak
in
g
in
f
o
r
m
ed
d
ec
is
io
n
s
f
o
r
th
e
f
u
tu
r
e.
I
n
ad
d
itio
n
,
th
e
web
-
b
ased
ap
p
licatio
n
i
n
co
r
p
o
r
ates
v
ar
io
u
s
v
is
u
aliza
tio
n
s
,
f
ac
ilit
atin
g
a
clea
r
u
n
d
er
s
tan
d
in
g
o
f
th
e
e
-
h
ailin
g
s
er
v
ices
av
ailab
le
in
Ma
lay
s
ia.
T
h
is
v
is
u
aliza
tio
n
f
ea
tu
r
e
en
ab
les
co
n
s
u
m
er
s
to
ef
f
icien
tly
co
m
p
a
r
e
d
if
f
er
en
t
e
-
h
ailin
g
o
p
tio
n
s
,
s
av
in
g
t
h
em
tim
e
an
d
ef
f
o
r
t
wh
ile
g
ain
in
g
m
o
r
e
ac
c
u
r
ate
in
s
ig
h
ts
.
Mo
r
e
o
v
er
,
it
o
f
f
er
s
a
m
o
r
e
d
etailed
co
m
p
ar
is
o
n
o
f
th
e
e
-
h
ailin
g
s
er
v
ices
b
ased
o
n
f
iv
e
asp
ec
ts
,
in
clu
d
in
g
f
a
r
e,
av
ailab
ilit
y
,
co
m
f
o
r
t,
tim
e,
a
n
d
co
n
v
en
ien
ce
.
Hen
ce
,
it
im
p
r
o
v
es
co
n
s
u
m
er
s
’
d
ec
is
io
n
-
m
ak
in
g
b
y
allo
win
g
th
em
to
o
b
tain
q
u
ick
an
d
d
e
ep
er
in
s
ig
h
ts
.
I
t
is
r
ec
o
m
m
en
d
ed
th
at
in
th
e
f
u
tu
r
e,
th
e
ev
alu
atio
n
s
o
f
Ma
lay
r
ev
iews
b
e
m
eticu
lo
u
s
ly
ex
a
m
in
ed
o
n
e
b
y
o
n
e
to
e
n
s
u
r
e
th
e
ab
s
en
ce
o
f
I
n
d
o
n
esian
wo
r
d
s
.
Nex
t,
m
o
r
e
in
f
o
r
m
atio
n
ca
n
b
e
ex
p
an
d
e
d
b
y
s
cr
ap
in
g
f
r
o
m
o
th
er
s
o
u
r
ce
s
s
u
ch
as
Face
b
o
o
k
o
r
T
h
r
ea
d
s
an
d
b
y
p
r
o
lo
n
g
in
g
th
e
d
u
r
atio
n
o
f
d
ata
s
cr
a
p
in
g
.
Giv
en
t
h
at
em
o
jis
co
n
v
ey
u
s
er
s
’
in
ten
tio
n
s
in
ex
p
r
ess
in
g
th
eir
o
p
in
io
n
s
,
in
teg
r
atin
g
th
em
in
to
th
e
class
if
icatio
n
p
r
o
ce
s
s
is
ess
en
tial.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
r
esear
ch
was
f
u
n
d
ed
b
y
a
g
r
an
t
f
r
o
m
Un
iv
e
r
s
iti
T
ek
n
o
lo
g
i
MA
R
A
C
awa
n
g
an
Me
l
ak
a
(
T
E
J
A
Gr
an
t 2
0
2
4
GDT
2
0
2
4
/1
-
1
5
)
.
RE
F
E
R
E
NC
E
S
[
1
]
O
.
B
.
C
h
e
n
a
n
d
S
.
A
.
N
a
z
a
r
,
“
Ex
p
l
o
r
i
n
g
f
a
c
t
o
r
s
i
n
f
l
u
e
n
c
i
n
g
e
-
h
a
i
l
i
n
g
s
e
r
v
i
c
e
s
i
n
K
l
a
n
g
V
a
l
l
e
y
,
”
MA
L
AYS
I
A.
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
O
f
B
u
s
i
n
e
ss
An
d
Ec
o
n
o
m
y
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
3
2
–
4
6
,
2
0
2
1
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
m
y
j
ms
.
mo
h
e
.
g
o
v
.
m
y
/
i
n
d
e
x
.
p
h
p
/
i
j
b
e
c
J
o
u
r
n
a
l
w
e
b
si
t
e
:
h
t
t
p
:
/
/
m
y
j
ms.m
o
h
e
.
g
o
v
.
m
y
/
i
n
d
e
x
.
p
h
p
/
i
j
b
e
c
h
t
t
p
:
/
/
m
y
j
ms.mo
h
e
.
g
o
v
.
m
y
/
i
n
d
e
x
.
p
h
p
/
i
j
b
e
c
.
[
2
]
S
.
S
a
l
i
m,
M
.
A
.
H
.
S
a
l
m
a
n
,
a
n
d
M
.
N
.
S
a
l
ma
n
,
“
P
r
o
f
i
l
i
n
g
o
f
p
a
s
se
n
g
e
r
s
b
y
e
-
h
a
i
l
i
n
g
s
e
r
v
i
c
e
s
i
n
M
a
l
a
y
si
a
M
A
LA
Y
S
I
A
*
C
o
r
r
e
s
p
o
n
d
i
n
g
A
u
t
h
o
r
D
e
s
i
g
n
a
t
i
o
n
,
”
Mu
l
t
i
d
i
sc
i
p
l
i
n
a
ry
Ap
p
l
i
e
d
Re
se
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
o
n
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
6
0
–
6
9
,
2
0
2
1
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
d
o
i
.
o
r
g
/
1
0
.
3
0
8
8
0
/
m
a
r
i
.
2
0
2
1
.
0
2
.
0
2
.
0
0
8
.
[
3
]
D
.
Y
e
o
,
H
.
A
n
n
,
a
n
d
M
.
A
.
S
h
a
f
i
,
“
F
a
c
t
o
r
s
i
n
f
l
u
e
n
c
i
n
g
c
o
n
s
u
mer
sa
t
i
sf
a
c
t
i
o
n
t
o
w
a
r
d
s
e
-
h
a
i
l
i
n
g
ser
v
i
c
e
a
m
o
n
g
M
a
l
a
y
si
a
n
,
”
Re
se
a
rc
h
i
n
Ma
n
a
g
e
m
e
n
t
o
f
T
e
c
h
n
o
l
o
g
y
a
n
d
B
u
si
n
e
s
s
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
7
2
–
0
8
4
,
2
0
2
2
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
p
u
b
l
i
sh
e
r
.
u
t
h
m.
e
d
u
.
m
y
/
p
e
r
i
o
d
i
c
a
l
s/
i
n
d
e
x
.
p
h
p
/
r
m
t
b
.
[
4
]
N
.
Z.
U
b
a
i
d
i
l
l
a
h
,
C
.
Y
.
Y
i
,
M
.
K
.
H
.
H
a
ssan
,
S
.
S
.
S
.
A
l
i
,
a
n
d
J.
Y
.
T.
H
w
a
n
g
,
“
T
h
e
d
e
t
e
r
m
i
n
a
n
t
s
o
f
g
e
n
e
r
a
t
i
o
n
z
i
n
t
e
n
t
i
o
n
t
o
u
s
e
t
h
e
g
r
a
b
e
-
h
a
i
l
i
n
g
s
e
r
v
i
c
e
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ac
a
d
e
m
i
c
Re
s
e
a
r
c
h
i
n
Bu
s
i
n
e
ss
a
n
d
S
o
c
i
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
9
,
n
o
.
1
1
,
p
p
.
4
8
3
–
4
9
5
,
2
0
1
9
,
d
o
i
:
1
0
.
6
0
0
7
/
i
j
a
r
b
ss/
v
9
-
i
1
1
/
6
5
7
0
.
[
5
]
A
.
K
.
.
A
l
-
S
h
a
k
h
r
i
t
,
K
.
A
.
M
a
sr
i
,
a
n
d
C
.
P
.
O
t
h
ma
n
,
“
Th
e
s
o
c
i
a
l
a
n
d
e
c
o
n
o
m
i
c
i
m
p
a
c
t
s
o
f
e
-
h
a
i
l
i
n
g
a
p
p
l
i
c
a
t
i
o
n
i
n
M
a
l
a
y
si
a
:
a
r
e
v
i
e
w
,
”
C
o
n
s
t
r
u
c
t
i
o
n
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
4
0
–
4
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
5
2
8
2
/
c
o
n
s
t
r
u
c
t
i
o
n
.
v
1
i
2
.
6
6
6
0
.
[
6
]
F
.
F
.
F
.
H
a
m
d
a
n
,
N
.
N
.
A
.
R
a
h
i
m,
A
.
K
.
O
t
h
ma
n
,
A
.
M
a
h
m
u
d
,
N
.
I
b
r
a
h
i
m,
a
n
d
A
.
Z.
Z
a
i
n
u
d
d
i
n
,
“
Th
e
d
e
t
e
r
mi
n
a
n
t
s
o
f
serv
i
c
e
q
u
a
l
i
t
y
a
n
d
c
u
st
o
m
e
r
sa
t
i
sf
a
c
t
i
o
n
i
n
M
a
l
a
y
si
a
n
e
-
h
a
i
l
i
n
g
s
e
r
v
i
c
e
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ac
a
d
e
m
i
c
Re
s
e
a
r
c
h
i
n
E
c
o
n
o
m
i
c
s
a
n
d
Ma
n
a
g
e
m
e
n
t
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
5
5
0
–
5
5
7
,
2
0
2
2
,
d
o
i
:
1
0
.
6
0
0
7
/
i
j
a
r
e
ms/v
1
1
-
i
2
/
1
4
0
5
5
.
[
7
]
M
.
N
.
M
d
N
o
r
,
S
.
M
d
.
S
a
b
r
i
,
a
n
d
N
.
F
.
M
.
I
sa,
“
E
-
h
a
i
l
i
n
g
s
e
r
v
i
c
e
sa
t
i
sf
a
c
t
i
o
n
:
a
c
a
se
st
u
d
y
o
f
st
u
d
e
n
t
s
i
n
a
h
i
g
h
e
r
e
d
u
c
a
t
i
o
n
i
n
s
t
i
t
u
t
i
o
n
i
n
P
e
r
l
i
s,
M
a
l
a
y
si
a
,
”
J
u
r
n
a
l
I
n
t
e
l
e
k
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
1
3
8
–
1
5
0
,
2
0
2
1
,
d
o
i
:
1
0
.
2
4
1
9
1
/
j
i
.
v
1
6
i
2
.
4
2
3
.
[
8
]
V
.
A
r
u
m
u
g
a
m,
M
.
R
.
I
smai
l
,
a
n
d
M
.
J
o
e
h
a
r
e
e
,
“
A
r
e
v
i
e
w
a
n
d
c
o
n
c
e
p
t
u
a
l
d
e
v
e
l
o
p
m
e
n
t
o
f
t
h
e
f
a
c
t
o
r
s
i
n
f
l
u
e
n
c
i
n
g
c
o
n
s
u
me
r
i
n
t
e
n
t
i
o
n
t
o
w
a
r
d
s
E
-
h
a
i
l
i
n
g
s
e
r
v
i
c
e
i
n
M
a
l
a
y
si
a
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
o
n
,
C
re
a
t
i
v
i
t
y
a
n
d
C
h
a
n
g
e
,
v
o
l
.
1
1
,
n
o
.
1
1
,
p
p
.
2
2
4
–
2
4
2
,
2
0
2
0
.
[
9
]
K
.
L
.
K
h
o
o
,
“
A
st
u
d
y
o
f
serv
i
c
e
q
u
a
l
i
t
y
,
c
o
r
p
o
r
a
t
e
i
ma
g
e
,
c
u
st
o
m
e
r
sat
i
sf
a
c
t
i
o
n
,
r
e
v
i
si
t
i
n
t
e
n
t
i
o
n
a
n
d
w
o
r
d
-
of
-
mo
u
t
h
:
e
v
i
d
e
n
c
e
f
r
o
m t
h
e
K
TV
i
n
d
u
s
t
r
y
,
”
PS
U
Re
s
e
a
r
c
h
Re
v
i
e
w
,
v
o
l
.
6
,
n
o
.
2
,
p
p
.
1
0
5
–
1
1
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
8
/
P
R
R
-
08
-
2
0
1
9
-
0
0
2
9
.
[
1
0
]
A
.
R
.
M
a
h
a
r
s
i
,
R
.
S
.
N
j
o
t
o
p
r
a
j
i
t
n
o
,
B
.
H
a
d
i
a
n
t
o
,
a
n
d
J.
W
i
r
a
a
t
maj
a
,
“
T
h
e
e
f
f
e
c
t
o
f
s
e
r
v
i
c
e
q
u
a
l
i
t
y
a
n
d
c
u
st
o
mer
sat
i
sf
a
c
t
i
o
n
o
n
p
u
r
c
h
a
si
n
g
i
n
t
e
n
t
i
o
n
:
a
c
a
se
s
t
u
d
y
i
n
I
n
d
o
n
e
si
a
,
”
J
o
u
r
n
a
l
o
f
As
i
a
n
F
i
n
a
n
c
e
,
Ec
o
n
o
m
i
c
s
a
n
d
Bu
s
i
n
e
ss
,
v
o
l
.
8
,
n
o
.
4
,
p
p
.
4
7
5
–
4
8
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
3
1
0
6
/
j
a
f
e
b
.
2
0
2
1
.
v
o
l
8
.
n
o
4
.
0
4
7
5
.
[
1
1
]
N
.
L.
P
.
S
u
c
i
p
t
a
w
a
t
i
,
N
.
L.
P
.
S
.
P
.
P
a
r
a
mi
t
a
,
a
n
d
I
.
P
.
A
r
i
st
a
y
a
sa,
“
C
u
s
t
o
mer
sat
i
sf
a
c
t
i
o
n
a
n
a
l
y
s
i
s
b
a
se
d
o
n
s
e
r
v
i
c
e
q
u
a
l
i
t
y
:
c
a
s
e
o
f
l
o
c
a
l
c
r
e
d
i
t
p
r
o
v
i
d
e
r
i
n
B
a
l
i
,
”
i
n
J
o
u
r
n
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s
,
2
0
1
9
,
v
o
l
.
1
3
2
1
,
n
o
.
2
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
3
2
1
/
2
/
0
2
2
0
5
5
.
[
1
2
]
S
.
K
e
m
p
,
“
D
i
g
i
t
a
l
2
0
2
3
:
M
a
l
a
y
s
i
a
,
”
D
a
t
a
R
e
p
o
r
t
a
l
,
2
0
2
3
.
.
[
1
3
]
Z.
D
r
u
s
a
n
d
H
.
K
h
a
l
i
d
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
i
n
s
o
c
i
a
l
me
d
i
a
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
:
s
y
s
t
e
m
a
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
i
n
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
2
0
1
9
,
v
o
l
.
1
6
1
,
p
p
.
7
0
7
–
7
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
1
9
.
1
1
.
1
7
4
.
[
1
4
]
S
.
Ç
a
l
ı
a
n
d
Ş
.
Y
.
B
a
l
a
m
a
n
,
“
I
mp
r
o
v
e
d
d
e
c
i
s
i
o
n
s
f
o
r
m
a
r
k
e
t
i
n
g
,
s
u
p
p
l
y
a
n
d
p
u
r
c
h
a
s
i
n
g
:
m
i
n
i
n
g
b
i
g
d
a
t
a
t
h
r
o
u
g
h
a
n
i
n
t
e
g
r
a
t
i
o
n
o
f
sen
t
i
m
e
n
t
a
n
a
l
y
s
i
s
a
n
d
i
n
t
u
i
t
i
o
n
i
st
i
c
f
u
z
z
y
m
u
l
t
i
c
r
i
t
e
r
i
a
a
s
sessm
e
n
t
,
”
C
o
m
p
u
t
e
rs
a
n
d
I
n
d
u
st
r
i
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
2
9
,
n
o
.
2
0
1
9
,
p
p
.
3
1
5
–
3
3
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
e
.
2
0
1
9
.
0
1
.
0
5
1
.
[
1
5
]
H
.
Ta
h
e
r
d
o
o
st
a
n
d
M
.
M
a
d
a
n
c
h
i
a
n
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
se
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s:
a
r
e
v
i
e
w
i
n
c
o
m
p
e
t
i
t
i
v
e
r
e
s
e
a
r
c
h
,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
1
–
1
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
e
r
s1
2
0
2
0
0
3
7
.
[
1
6
]
S
.
S
h
a
r
ma,
M
.
S
a
r
a
sw
a
t
,
a
n
d
A
.
K
.
D
u
b
e
y
,
“
M
u
l
t
i
-
as
p
e
c
t
s
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
u
s
i
n
g
d
o
ma
i
n
o
n
t
o
l
o
g
i
e
s,
”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
i
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
,
v
o
l
.
1
6
8
6
C
C
I
S
,
p
p
.
2
6
3
–
2
7
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
1
4
2
2
-
6
_
1
9
.
[
1
7
]
S
.
W
e
n
e
t
a
l
.
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
s
i
s
o
f
so
c
i
a
l
m
e
d
i
a
c
o
mm
e
n
t
s
b
a
s
e
d
o
n
r
a
n
d
o
m
f
o
r
e
st
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
,
”
i
n
2
0
2
2
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
s
i
n
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
A
EEC
A
2
0
2
2
,
2
0
2
2
,
p
p
.
2
7
7
–
2
8
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
EEC
A
5
5
5
0
0
.
2
0
2
2
.
9
9
1
8
9
5
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Un
ve
ilin
g
p
ercep
tio
n
s
:
a
s
p
ec
t
-
b
a
s
ed
s
en
timen
t
…
(
K
h
yrin
a
A
ir
in
F
a
r
iz
a
A
b
u
S
a
ma
h
)
2085
[
1
8
]
S
.
D
a
s
g
u
p
t
a
a
n
d
J.
S
e
n
,
“
A
f
r
a
mew
o
r
k
o
f
c
u
s
t
o
m
e
r
r
e
v
i
e
w
a
n
a
l
y
s
i
s
u
si
n
g
t
h
e
a
s
p
e
c
t
-
b
a
se
d
o
p
i
n
i
o
n
mi
n
i
n
g
a
p
p
r
o
a
c
h
,
”
i
n
2
0
2
2
O
I
T
S
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
O
C
I
T
)
,
2
0
2
2
,
p
p
.
2
3
3
–
2
3
7
,
d
o
i
:
1
0
.
1
1
0
9
/
o
c
i
t
5
6
7
6
3
.
2
0
2
2
.
0
0
0
5
2
.
[
1
9
]
A
.
F
.
P
a
t
h
a
n
a
n
d
C
.
P
r
a
k
a
s
h
,
“
U
n
su
p
e
r
v
i
s
e
d
a
sp
e
c
t
e
x
t
r
a
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
o
p
i
n
i
o
n
mi
n
i
n
g
u
s
i
n
g
t
o
p
i
c
mo
d
e
l
i
n
g
,
”
i
n
G
l
o
b
a
l
T
ra
n
si
t
i
o
n
s P
r
o
c
e
e
d
i
n
g
s
,
2
0
2
1
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
4
9
2
–
4
9
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
l
t
p
.
2
0
2
1
.
0
8
.
0
0
5
.
[
2
0
]
K
.
E
.
C
h
u
,
P
.
K
e
i
k
h
o
sr
o
k
i
a
n
i
,
a
n
d
M
.
P
.
A
sl
,
“
A
t
o
p
i
c
mo
d
e
l
i
n
g
a
n
d
se
n
t
i
men
t
a
n
a
l
y
s
i
s
mo
d
e
l
f
o
r
d
e
t
e
c
t
i
o
n
a
n
d
v
i
su
a
l
i
z
a
t
i
o
n
o
f
t
h
e
mes
i
n
l
i
t
e
r
a
r
y
t
e
x
t
s
,
”
Pe
r
t
a
n
i
k
a
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
0
,
n
o
.
4
,
p
p
.
2
5
3
5
–
2
5
6
1
,
2
0
2
2
,
d
o
i
:
1
0
.
4
7
8
3
6
/
p
j
s
t
.
3
0
.
4
.
1
4
.
[
2
1
]
F
.
J.
P
i
n
e
m,
R
.
A
n
d
r
e
sw
a
r
i
,
a
n
d
M
.
A
.
H
a
s
i
b
u
a
n
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
t
o
me
a
su
r
e
c
e
l
e
b
r
i
t
y
e
n
d
o
r
sm
e
n
t
’
s
e
f
f
e
c
t
u
s
i
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
a
l
g
o
r
i
t
h
m
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
EEC
S
I
)
,
2
0
1
8
,
v
o
l
.
2
0
1
8
-
O
c
t
o
b
e
r
,
p
p
.
6
9
0
–
6
9
5
,
d
o
i
:
1
0
.
1
1
0
9
/
E
EC
S
I
.
2
0
1
8
.
8
7
5
2
6
8
7
.
[
2
2
]
H
.
R
a
z
a
,
M
.
F
a
i
z
a
n
,
A
.
H
a
mz
a
,
A
.
M
u
s
h
t
a
q
,
a
n
d
N
.
A
k
h
t
a
r
,
“
S
c
i
e
n
t
i
f
i
c
t
e
x
t
se
n
t
i
me
n
t
a
n
a
l
y
si
s
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
0
,
n
o
.
1
2
,
p
p
.
1
5
7
–
1
6
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
4
5
6
9
/
i
j
a
c
s
a
.
2
0
1
9
.
0
1
0
1
2
2
2
.
[
2
3
]
A
.
P
r
o
t
o
p
sa
l
t
i
s,
P
.
S
a
r
i
g
i
a
n
n
i
d
i
s,
D
.
M
a
r
g
o
u
n
a
k
i
s
,
a
n
d
A
.
L
y
t
o
s
,
“
D
a
t
a
v
i
su
a
l
i
z
a
t
i
o
n
i
n
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
:
t
o
o
l
s
,
me
t
h
o
d
o
l
o
g
i
e
s
,
a
n
d
c
h
a
l
l
e
n
g
e
s,”
2
0
2
0
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
0
7
0
2
3
.
3
4
0
9
2
2
8
.
[
2
4
]
M
.
C
.
R
a
h
m
a
d
a
n
,
A
.
N
.
H
i
d
a
y
a
n
t
o
,
D
.
S
.
E
k
a
s
a
r
i
,
B
.
P
u
r
w
a
n
d
a
r
i
,
a
n
d
T
h
e
r
e
s
i
a
w
a
t
i
,
“
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
a
n
d
t
o
p
i
c
m
o
d
e
l
l
i
n
g
u
si
n
g
t
h
e
LD
A
m
e
t
h
o
d
r
e
l
a
t
e
d
t
o
t
h
e
f
l
o
o
d
d
i
s
a
st
e
r
i
n
J
a
k
a
r
t
a
o
n
Tw
i
t
t
e
r
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
-
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
c
s,
Mu
l
t
i
m
e
d
i
a
,
C
y
b
e
r,
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
,
I
C
I
MC
I
S
2
0
2
0
,
2
0
2
0
,
p
p
.
1
2
6
–
1
3
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
M
C
I
S
5
1
5
6
7
.
2
0
2
0
.
9
3
5
4
3
2
0
.
[
2
5
]
G
.
C
i
a
b
u
r
r
o
,
“
M
a
c
h
i
n
e
f
a
u
l
t
d
e
t
e
c
t
i
o
n
me
t
h
o
d
s
b
a
se
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms:
a
r
e
v
i
e
w
,
”
M
a
t
h
e
m
a
t
i
c
a
l
Bi
o
s
c
i
e
n
c
e
s
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
9
,
n
o
.
1
1
,
p
p
.
1
1
4
5
3
–
1
1
4
9
0
,
2
0
2
2
,
d
o
i
:
1
0
.
3
9
3
4
/
m
b
e
.
2
0
2
2
5
3
4
.
[
2
6
]
A
.
A
l
a
msy
a
h
a
n
d
I
.
R
a
c
h
ma
d
i
a
n
s
y
a
h
,
“
M
a
p
p
i
n
g
o
n
l
i
n
e
t
r
a
n
s
p
o
r
t
a
t
i
o
n
s
e
r
v
i
c
e
q
u
a
l
i
t
y
a
n
d
m
u
l
t
i
c
l
a
ss
c
l
a
ss
i
f
i
c
a
t
i
o
n
p
r
o
b
l
e
m
so
l
v
i
n
g
p
r
i
o
r
i
t
i
e
s
,
”
i
n
J
o
u
rn
a
l
o
f
Ph
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
A
p
r
.
2
0
1
8
,
v
o
l
.
9
7
1
,
n
o
.
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
9
7
1
/
1
/
0
1
2
0
2
1
.
[
2
7
]
R
.
C
h
u
r
c
h
i
l
l
a
n
d
L
.
S
i
n
g
h
,
“
T
h
e
E
v
o
l
u
t
i
o
n
o
f
T
o
p
i
c
M
o
d
e
l
i
n
g
,
”
AC
M
C
o
m
p
u
t
i
n
g
S
u
rv
e
y
s
,
v
o
l
.
5
4
,
n
o
.
1
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
0
7
9
0
0
.
[
2
8
]
M
.
P
i
c
k
e
t
t
,
D
.
C
l
i
n
e
,
a
n
d
J.
R
y
a
n
,
“
E
x
p
l
o
r
i
n
g
c
o
h
e
r
e
n
c
e
me
t
r
i
c
s fo
r
o
p
t
i
mi
z
i
n
g
t
o
p
i
c
m
o
d
e
l
s
o
f
h
u
m
p
b
a
c
k
s
o
n
g
,
”
p
p
.
1
–
1
8
,
2
0
2
0
.
[
2
9
]
H
.
C
l
a
r
k
e
,
S
.
C
l
a
r
k
,
M
.
B
i
r
k
i
n
,
H
.
I
l
e
s
-
S
mi
t
h
,
A
.
G
l
a
ser,
a
n
d
M
.
A
.
M
o
r
r
i
s
,
“
U
n
d
e
r
s
t
a
n
d
i
n
g
b
a
r
r
i
e
r
s
t
o
n
o
v
e
l
d
a
t
a
l
i
n
k
a
g
e
s
:
t
o
p
i
c
mo
d
e
l
i
n
g
o
f
t
h
e
r
e
s
u
l
t
s
o
f
t
h
e
L
i
f
e
I
n
f
o
su
r
v
e
y
,
”
J
o
u
r
n
a
l
o
f
Me
d
i
c
a
l
I
n
t
e
r
n
e
t
Re
se
a
rc
h
,
v
o
l
.
2
3
,
n
o
.
5
,
2
0
2
1
,
d
o
i
:
1
0
.
2
1
9
6
/
2
4
2
3
6
.
[
3
0
]
K
.
M
u
s
g
r
a
v
e
,
“
C
o
r
r
e
c
t
l
y
e
v
a
l
u
a
t
i
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
C
o
r
n
e
l
l
U
n
i
v
e
r
si
t
y
,
2
0
2
3
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
K
h
y
r
in
a
Air
i
n
F
a
r
iza
Ab
u
S
a
m
a
h
is
a
se
n
io
r
lec
tu
re
r
a
t
th
e
C
o
ll
e
g
e
o
f
Co
m
p
u
ti
n
g
,
In
f
o
rm
a
ti
c
s
a
n
d
M
a
th
e
m
a
ti
c
s
in
Un
iv
e
rsiti
Tek
n
o
lo
g
i
M
ARA
(UiTM
)
M
e
lak
a
Bra
n
c
h
,
Ja
sin
Ca
m
p
u
s.
Be
fo
re
jo
in
in
g
UiTM
,
sh
e
h
a
d
1
3
y
e
a
rs
o
f
wo
rk
i
n
g
e
x
p
e
rien
c
e
in
th
e
se
m
ico
n
d
u
c
to
r
in
d
u
str
y
.
S
h
e
h
a
s
a
Dip
lo
m
a
,
Ba
c
h
e
lo
r
’
s
De
g
re
e
a
n
d
M
a
ste
r
’
s
De
g
re
e
in
Co
m
p
u
ter S
c
ien
c
e
a
n
d
P
h
.
D
.
i
n
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
.
He
r
re
se
a
rc
h
in
tere
sts a
re
in
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
lg
o
rit
h
m
a
n
a
l
y
sis,
m
a
c
h
in
e
lea
rn
in
g
o
p
ti
m
iza
ti
o
n
,
a
n
d
e
v
a
c
u
a
ti
o
n
a
l
g
o
rit
h
m
s
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
h
y
rin
a
7
8
3
@
u
it
m
.
e
d
u
.
m
y
.
Mo
h
a
m
a
d
Az
a
n
Am
it
is
a
b
a
c
h
e
lo
r
’
s
stu
d
e
n
t
in
Co
m
p
u
ter
S
c
ien
c
e
c
u
rre
n
tl
y
u
n
d
e
r
g
o
i
n
g
a
n
in
tern
s
h
ip
p
ro
g
ra
m
m
e
.
His
re
se
a
rc
h
in
tere
sts
a
r
e
d
a
ta
m
in
in
g
,
m
a
c
h
in
e
lea
rn
i
n
g
a
lg
o
rit
h
m
s,
d
a
ta
a
n
a
l
y
sis
,
a
n
d
v
i
su
a
li
z
a
ti
o
n
.
He
is
a
c
ti
v
e
ly
in
v
o
l
v
e
d
in
th
e
re
se
a
rc
h
g
ro
u
p
a
t
UiTM
.
C
u
rre
n
tl
y
,
h
e
is
p
u
rs
u
in
g
a
n
in
tern
s
h
ip
a
t
Ex
a
c
t
As
ia
De
v
e
lo
p
m
e
n
t
Ce
n
tre
S
d
n
B
h
d
,
Ku
a
la L
u
m
p
u
r,
M
a
lay
sia
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
d
a
z
a
n
1
2
1
6
@g
m
a
il
.
c
o
m
.
S
iti
S
a
lwa
S
a
ll
e
h
is
a
se
n
i
o
r
lec
tu
re
r
in
th
e
C
o
ll
e
g
e
o
f
Co
m
p
u
ti
n
g
,
I
n
fo
rm
a
ti
c
s
a
n
d
M
a
t
h
e
m
a
ti
c
a
l
S
c
ien
c
e
s
a
t
th
e
Un
iv
e
rsity
Tec
h
n
o
l
o
g
y
M
ARA
(UiTM
)
Ne
g
e
ri
S
e
m
b
il
a
n
Bra
n
c
h
.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
.
D
.
i
n
c
o
m
p
u
ter
v
isi
o
n
a
n
d
ima
g
i
n
g
f
ro
m
th
e
Un
i
v
e
rsity
o
f
P
u
tra
M
a
lay
sia
in
2
0
0
8
.
T
h
e
a
re
a
s
o
f
h
e
r
re
se
a
rc
h
in
tere
st
a
re
d
a
ta
v
is
u
a
li
z
a
ti
o
n
,
m
u
lt
imo
d
a
l
in
tera
c
ti
o
n
d
e
sig
n
,
a
n
d
tem
p
o
ra
l
m
e
d
ia
p
ro
c
e
ss
in
g
.
S
h
e
re
c
e
n
tl
y
fo
c
u
se
d
h
e
r
tea
c
h
in
g
a
n
d
lea
rn
in
g
a
s
we
ll
a
s
re
se
a
rc
h
o
n
m
u
lt
ime
d
ia
d
e
si
g
n
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
a
rti
ficia
l
i
n
telli
g
e
n
c
e
in
t
h
e
d
o
m
a
in
o
f
tran
sp
o
rt,
su
p
p
l
y
c
h
a
i
n
a
n
d
m
o
b
il
it
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ss
a
lwa
@u
it
m
.
e
d
u
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
7
7
-
2
0
8
6
2086
Wa
n
n
o
r
a
in
i
Abd
u
l
La
tif
is
a
se
n
io
r
lec
tu
re
r
a
t
t
h
e
Co
ll
e
g
e
o
f
Co
m
p
u
ti
n
g
,
In
fo
rm
a
ti
c
s
a
n
d
M
a
th
e
m
a
ti
c
s
in
Un
iv
e
rsiti
Te
k
n
o
lo
g
i
M
ARA
(Ui
TM
)
M
e
lak
a
Bra
n
c
h
,
Ja
sin
Ca
m
p
u
s.
Be
fo
re
jo
in
i
n
g
UiT
M
,
sh
e
h
a
d
5
y
e
a
rs
o
f
wo
rk
i
n
g
e
x
p
e
rien
c
e
in
p
riv
a
te
u
n
iv
e
rsit
y
(M
S
U,
S
h
a
h
Ala
m
)
a
s
a
lec
tu
re
r.
S
h
e
h
a
s
a
Ba
c
h
e
lo
r
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
(m
a
jo
rin
g
i
n
Artifi
c
ial
In
telli
g
e
n
c
e
)
a
n
d
M
a
ste
r
o
f
S
c
ien
c
e
in
I
n
telli
g
e
n
t
S
y
s
tem
fro
m
Un
iv
e
rsiti
Uta
ra
M
a
lay
sia
(UU
M
).
He
r
re
s
e
a
rc
h
in
tere
sts
a
re
a
rti
ficia
l
in
telli
g
e
n
c
e
,
e
x
p
e
rt
sy
ste
m
,
n
e
u
ra
l
n
e
two
rk
,
d
a
ta
m
i
n
in
g
,
m
a
c
h
in
e
l
e
a
rn
in
g
,
v
ir
tu
a
l
re
a
li
t
y
,
we
b
,
a
n
d
s
y
ste
m
d
e
v
e
l
o
p
m
e
n
t.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
b
y
e
m
a
il
:
wa
n
n
o
ra
in
i9
6
0
@u
it
m
.
e
d
u
.
m
y
.
Nurul
‘
Az
wa
K
a
m
a
r
u
d
i
n
is
a
se
n
io
r
lec
tu
re
r
a
t
th
e
Co
ll
e
g
e
o
f
Co
m
p
u
ti
n
g
,
In
fo
rm
a
ti
c
s
a
n
d
M
a
th
e
m
a
ti
c
s
in
Un
iv
e
rsiti
Te
k
n
o
lo
g
i
M
ARA
(Ui
TM
)
M
e
lak
a
Bra
n
c
h
,
Ja
sin
Ca
m
p
u
s.
S
h
e
h
a
s
a
M
a
ste
r
o
f
S
c
ien
c
e
s
d
e
g
re
e
fr
o
m
UiT
M
S
h
a
h
Ala
m
.
Wi
t
h
a
so
li
d
e
d
u
c
a
ti
o
n
a
l
b
a
c
k
g
ro
u
n
d
,
sh
e
b
rin
g
s
e
x
p
e
rti
se
a
n
d
k
n
o
wle
d
g
e
to
h
e
r
ro
le,
c
o
n
tr
ib
u
ti
n
g
to
th
e
a
c
a
d
e
m
ic
e
n
v
iro
n
m
e
n
t.
He
r
re
se
a
rc
h
in
tere
sts
re
v
o
l
v
e
a
ro
u
n
d
m
a
th
e
m
a
ti
c
s,
o
p
e
ra
ti
o
n
s
re
se
a
rc
h
,
we
ll
-
b
e
in
g
a
n
d
e
d
u
c
a
ti
o
n
.
He
r
f
o
c
u
s
o
n
t
h
e
se
c
u
tt
in
g
-
e
d
g
e
a
re
a
s
d
e
m
o
n
stra
tes
h
e
r
d
e
d
ica
ti
o
n
to
in
v
e
stig
a
ti
n
g
i
n
n
o
v
a
ti
v
e
a
p
p
ro
a
c
h
e
s
a
n
d
u
n
d
e
rsta
n
d
in
g
th
e
i
n
tera
c
ti
o
n
a
m
o
n
g
th
o
se
a
re
a
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
z
wa
7
0
0
@u
it
m
.
e
d
u
.
m
y
.
S
h
a
h
a
d
a
n
S
a
a
d
is
a
lec
tu
r
e
r
a
t
t
h
e
Co
ll
e
g
e
o
f
C
o
m
p
u
ti
n
g
,
In
f
o
rm
a
ti
c
s,
a
n
d
M
a
th
e
m
a
ti
c
s
a
t
Un
iv
e
rsiti
Tek
n
o
l
o
g
i
M
ARA
(UiTM
)
M
e
lak
a
Bra
n
c
h
,
Ja
sin
Ca
m
p
u
s.
P
ri
o
r
to
jo
in
i
n
g
UiT
M
,
h
e
a
c
c
u
m
u
late
d
4
y
e
a
rs
o
f
e
x
p
e
rien
c
e
a
s
a
P
r
o
g
ra
m
m
e
r
a
n
d
o
n
e
y
e
a
r
a
s
a
Ne
two
rk
E
n
g
i
n
e
e
r
a
n
d
S
y
ste
m
Co
n
su
l
tan
t.
He
h
o
ld
s
a
Dip
l
o
m
a
in
Co
m
p
u
ter S
c
ien
c
e
,
a
d
e
g
re
e
in
d
a
ta
c
o
m
m
u
n
ica
ti
o
n
a
n
d
n
e
tw
o
rk
i
n
g
,
a
n
d
a
M
a
ste
r
’
s
in
S
c
ien
c
e
(In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
)
.
His
re
se
a
rc
h
in
tere
sts
li
e
in
n
e
t
wo
rk
i
n
g
,
se
c
u
rit
y
,
a
n
d
AI.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
a
h
a
d
a
n
@u
it
m
.
e
d
u
.
m
y
.
Mo
h
d
N
o
r
H
a
ja
r
H
a
sr
o
l
J
o
n
o
is
a
se
n
io
r
lec
tu
re
r
a
t
th
e
Co
ll
e
g
e
o
f
Co
m
p
u
ti
n
g
,
In
fo
rm
a
ti
c
s
a
n
d
M
a
th
e
m
a
ti
c
s
in
Un
iv
e
rsiti
Te
k
n
o
lo
g
i
M
ARA
(Ui
TM
)
M
e
lak
a
Bra
n
c
h
,
Ja
sin
Ca
m
p
u
s.
He
g
ra
d
u
a
ted
wi
th
a
P
h
.
D
.
i
n
M
u
lt
ime
d
ia
Ed
u
c
a
ti
o
n
,
Un
iv
e
rsiti
P
e
n
d
id
i
k
a
n
S
u
lt
a
n
Id
ris.
M
S
c
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
UiTM
a
n
d
Ba
c
h
e
l
o
r
’
s
De
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsiti
Tek
n
o
l
o
g
i
M
a
lay
sia
.
On
c
e
se
rv
e
d
a
s
a
so
ftwa
re
d
e
v
e
l
o
p
e
r
a
t
a
lea
d
in
g
c
o
m
p
a
n
y
i
n
M
a
lay
sia
.
As
a
n
a
c
a
d
e
m
ic,
re
s
e
a
r
c
h
is o
n
e
o
f
t
h
e
a
re
a
s o
f
in
tere
st f
o
r
d
e
v
e
l
o
p
i
n
g
i
d
e
a
s,
sh
a
rin
g
sk
il
ls,
a
n
d
a
p
p
ly
i
n
g
t
h
e
late
st
i
n
n
o
v
a
t
io
n
s
a
c
c
o
rd
i
n
g
t
o
t
h
e
late
st
tec
h
n
o
lo
g
y
a
n
d
e
d
u
c
a
ti
o
n
tren
d
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
sro
l@
u
it
m
.
e
d
u
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.