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
er
Science
Vo
l.
11
,
No
.
2
,
A
u
g
u
s
t
201
8
,
p
p
.
79
1
~
79
6
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
ee
cs.v
1
1
.
i2
.
p
p
791
-
7
9
6
791
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
O
pinio
n Mini
ng
u
sing
Ma
chine Lea
rning
Approa
ch:
Ca
se Study o
f
Lig
ht
Ra
il Tra
nsi
t
D
ev
elo
p
m
en
t
in
In
do
nesia
Sa
rif
a
h P
utr
i R
a
fl
esia
,
Dind
a
L
esta
rini
,
Dest
y
Ro
dia
h
,
F
irda
us
Co
m
p
u
ter S
c
ien
c
e
F
a
c
u
lt
y
,
Un
iv
e
rsitas
S
riw
ij
a
y
a
Jl.
P
a
lem
b
a
n
g
-
In
d
ra
lay
a
KM.
3
3
,
In
d
ra
lay
a
,
S
o
u
th
S
u
m
a
tra
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
9
,
2
0
1
8
R
ev
i
s
ed
A
p
r
8
,
2
0
1
8
A
cc
ep
ted
Ma
y
1
6
,
2
0
1
8
L
ig
h
t
ra
il
tran
sit
(L
R
T
),
o
r
f
a
st
t
ra
m
is
u
rb
a
n
p
u
b
li
c
tran
sp
o
rt
u
si
n
g
ro
ll
in
g
sto
c
k
si
m
il
a
r
to
a
tra
m
wa
y
,
b
u
t
o
p
e
ra
ti
n
g
a
t
a
h
ig
h
e
r
c
a
p
a
c
it
y
,
a
n
d
o
f
ten
o
n
a
n
e
x
c
lu
siv
e
rig
h
t
-
of
-
wa
y
.
In
d
o
n
e
sia
a
s
o
n
e
o
f
d
e
v
e
lo
p
i
n
g
c
o
u
n
tri
e
s
h
a
s
b
e
e
n
d
e
v
e
lo
p
e
d
t
h
e
L
RT
in
tw
o
c
it
ies
o
f
In
d
o
n
e
sia
,
P
a
lem
b
a
n
g
a
n
d
Ja
k
a
rta.
T
h
e
re
a
re
o
p
in
io
n
s to
w
a
rd
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
L
R
T
,
n
e
g
a
ti
v
e
a
n
d
p
o
siti
v
e
o
p
in
io
n
s.
T
o
re
v
e
a
l
th
e
lev
e
l
o
f
L
R
T
d
e
v
e
lo
p
m
e
n
t
a
c
c
e
p
tan
c
e
,
th
is
re
se
a
rc
h
u
se
s
m
a
c
h
in
e
lea
rn
in
g
a
p
p
r
o
a
c
h
to
a
n
a
ly
z
e
th
e
d
a
ta
w
h
ich
is
g
a
th
e
re
d
th
r
o
u
g
h
so
c
ial
m
e
d
ia.
B
y
c
o
n
d
u
c
ti
n
g
th
is
p
a
p
e
r,
th
e
d
a
ta
is
m
o
d
e
ll
e
d
a
n
d
c
las
sif
i
e
d
in
o
rd
e
r
t
o
a
n
a
ly
z
e
th
e
so
c
ial
se
n
ti
m
e
n
t
to
w
a
rd
s th
e
L
RT
d
e
v
e
lo
p
m
e
n
t.
K
ey
w
o
r
d
s
:
Op
in
io
n
m
i
n
in
g
Ma
ch
i
n
e
L
ea
r
n
i
n
g
So
cial
Me
d
ia
Naiv
e
B
a
y
es
C
las
s
i
f
ier
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
:
Din
d
a
L
e
s
tar
i
n
i
,
C
o
m
p
u
ter
Scien
ce
Fac
u
lt
y
,
Un
i
v
er
s
ita
s
Sri
w
ij
a
y
a
,
J
l.
P
alem
b
an
g
-
I
n
d
r
ala
y
a
KM
.
3
3
,
I
n
d
r
alay
a,
So
u
t
h
S
u
m
atr
a
.
I
n
d
o
n
esia.
E
m
ail:
d
i
n
d
a@
u
n
s
r
i.a
c.
id
1
.
I
NT
RO
DUCTI
O
N
I
n
I
n
d
o
n
es
ia,
th
e
li
g
h
t
r
ail
tr
a
n
s
it
(
L
R
T
)
h
as
b
ee
n
d
ev
elo
p
ed
in
t
w
o
b
i
g
citie
s
,
P
ale
m
b
an
g
a
n
d
J
ak
ar
ta.
Fro
m
t
h
e
o
b
s
er
v
atio
n
th
r
o
u
g
h
co
m
m
u
n
it
y
d
i
s
cu
s
s
io
n
in
r
ea
l
li
f
e
an
d
s
o
cial
m
ed
ia
,
th
e
b
en
ef
it
o
f
L
R
T
b
r
in
g
s
ar
g
u
m
en
t
s
a
n
d
o
p
in
io
n
s
.
So
m
e
p
eo
p
le
clai
m
e
d
t
h
at
th
e
p
r
ese
n
ce
o
f
L
R
T
w
il
l
b
r
in
g
g
o
o
d
v
alu
e
a
n
d
b
en
ef
its
to
citize
n
s
an
d
g
o
v
er
n
m
e
n
t.
Me
a
n
w
h
ile,
th
e
o
th
er
s
a
g
r
ee
th
at
t
h
e
cu
r
r
e
n
t
m
a
s
s
p
u
b
lic
tr
an
s
p
o
r
tatio
n
m
u
s
t b
e
i
m
p
r
o
v
ed
.
T
h
e
o
p
in
io
n
,
a
s
u
b
j
ec
tiv
e
p
o
in
t
o
f
v
ie
w
o
r
j
u
d
g
m
e
n
t
f
o
r
s
o
m
et
h
i
n
g
,
h
a
v
e
n
o
co
n
clu
s
i
v
e
s
tate
m
en
t.
B
u
t,
w
h
e
n
o
p
in
io
n
s
co
m
e
f
r
o
m
g
r
o
u
p
o
f
p
eo
p
le
b
y
m
ea
n
s
it
is
g
e
n
er
ated
f
r
o
m
s
o
cial
d
is
cu
s
s
io
n
w
h
ic
h
en
g
ag
ed
t
h
e
s
ta
k
e
h
o
ld
er
s
,
th
e
o
p
in
io
n
s
m
a
y
b
r
in
g
co
n
tr
o
v
er
s
y
[
1
]
.
A
cc
o
r
d
in
g
to
th
i
s
p
h
en
o
m
en
o
n
,
it
is
i
m
p
o
r
tan
t to
d
o
f
u
r
t
h
er
s
tu
d
y
,
an
a
l
y
ze
,
an
d
m
ea
s
u
r
e
t
h
e
le
v
e
l
o
f
L
R
T
ac
ce
p
tan
ce
in
I
n
d
o
n
e
s
ia.
T
h
e
lev
el
o
f
ac
ce
p
ta
n
ce
c
an
b
e
u
s
ed
a
s
o
n
e
o
f
m
ea
s
u
r
e
m
en
t
v
ar
iab
les
w
h
e
n
g
o
v
er
n
m
en
t
n
ee
d
s
to
an
al
y
ze
an
d
ev
a
lu
ate
t
h
e
L
R
T
d
ev
elo
p
m
e
n
t.
I
n
th
i
s
r
esear
ch
,
th
e
s
o
cial
m
e
d
ia
is
ch
o
s
en
as
f
ield
to
g
ath
e
r
th
e
o
p
in
io
n
s
.
So
cial
m
ed
ia
c
o
n
tain
s
th
e
s
o
cial
s
tr
u
ct
u
r
e
s
u
c
h
as
i
n
d
iv
id
u
al
a
n
d
o
r
g
a
n
izatio
n
.
I
n
s
o
cial
m
ed
ia,
p
eo
p
le
w
i
th
s
i
m
ilar
s
o
cial
t
y
p
e
ar
e
r
elate
d
,
th
ey
ca
n
b
e
f
a
m
ili
es
in
r
ea
l
li
f
e,
co
lleag
u
es,
an
d
f
r
ien
d
s
[
2
]
.
So
cial
m
ed
ia
b
r
o
u
g
h
t
n
e
w
w
a
y
i
n
d
o
in
g
i
n
ter
ac
tio
n
,
it
f
ac
i
litate
s
p
eo
p
le
to
co
m
m
u
n
icate
an
y
ti
m
e
a
n
d
a
n
y
w
a
y
w
it
h
o
u
t
co
n
s
i
d
er
in
g
h
o
w
f
ar
th
e
d
is
ta
n
ce
,
ti
m
e,
a
n
d
p
lace
s
[
3
]
.
T
h
e
s
o
cial
m
ed
ia
u
s
er
s
o
f
te
n
u
s
e
s
o
cial
m
ed
ia
to
ex
p
r
ess
t
h
e
m
s
el
v
es
b
y
s
h
ar
i
n
g
th
eir
o
w
n
in
f
o
r
m
atio
n
a
n
d
id
ea
s
.
I
t
d
r
iv
es
th
e
av
ai
lab
ilit
y
o
f
in
f
o
r
m
at
io
n
is
li
m
itles
s
w
h
ich
ca
n
ca
u
s
e
t
h
e
o
p
i
n
io
n
f
lo
o
d
s
.
I
n
th
is
r
esear
ch
,
s
o
cial
m
ed
ia
is
u
s
ed
as
m
ed
ia
to
g
ath
er
th
e
o
p
in
io
n
o
f
I
n
d
o
n
esi
an
p
eo
p
le
ab
o
u
t
L
R
T
.
T
h
e
p
r
o
ce
s
s
o
f
g
ath
er
in
g
o
p
in
io
n
as
d
ata
to
s
u
p
p
o
r
t
t
h
e
an
al
y
s
i
s
is
k
n
o
w
n
as
o
p
in
i
o
n
m
i
n
in
g
.
I
t
ca
n
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,
V
o
l.
1
1
,
No
.
2
,
A
u
g
u
s
t 2
0
1
8
:
7
9
1
–
79
6
792
b
e
d
ef
in
ed
as
a
co
m
p
u
tatio
n
al
s
tu
d
y
o
f
p
e
o
p
le’
s
o
p
in
io
n
s
,
ap
p
r
aisals
,
attitu
d
es,
an
d
e
m
o
tio
n
s
to
w
ar
d
en
titi
e
s
,
i
n
d
iv
id
u
als,
i
s
s
u
es,
e
v
en
t
s
,
to
p
ics
a
n
d
t
h
eir
attr
ib
u
tes
[
4
]
.
Mo
r
eo
v
er
,
it
also
ai
m
s
to
d
eter
m
i
n
e
au
to
m
at
ic
to
o
l
to
ex
tr
ac
t
a
p
ar
ticu
lar
in
f
o
r
m
atio
n
f
r
o
m
n
atu
r
al
lan
g
u
ag
e
te
x
t,
s
u
c
h
as
o
p
in
io
n
s
an
d
s
en
ti
m
e
n
ts
.
T
h
e
i
n
f
o
r
m
atio
n
w
il
l
b
e
u
s
ed
to
cr
ea
te
s
tr
u
ct
u
r
ed
an
d
ac
tio
n
ab
le
k
n
o
w
l
ed
g
e
to
s
u
p
p
o
r
t
th
e
d
ec
is
io
n
m
a
k
in
g
p
r
o
ce
s
s
[
5
]
.
I
t
is
v
er
y
p
o
p
u
lar
b
ec
au
s
e
t
h
is
ap
p
r
o
ac
h
in
v
o
lv
e
s
a
lar
g
e
a
m
o
u
n
t
o
f
d
ata
s
o
th
at
t
h
e
g
e
n
er
ated
in
f
o
r
m
atio
n
is
v
e
r
y
o
b
j
ec
tiv
e.
I
n
t
h
i
s
r
esear
ch
,
o
p
in
io
n
m
in
in
g
w
a
s
d
o
n
e
th
r
o
u
g
h
t
h
e
u
s
e
o
f
s
o
cial
m
ed
ia
ap
p
licatio
n
p
r
o
g
r
a
m
m
in
g
i
n
ter
f
ac
e
(
A
P
I
)
.
Ma
ch
i
n
e
lear
n
in
g
i
s
a
w
ell
-
d
ef
i
n
ed
alg
o
r
it
h
m
,
d
ata
s
tr
u
ct
u
r
es
an
d
t
h
eo
r
y
o
f
lear
n
in
g
,
w
it
h
o
u
t
r
ef
er
r
in
g
to
o
r
g
a
n
is
m
,
p
s
y
c
h
o
lo
g
ical
o
r
ev
o
l
u
tio
n
ar
y
t
h
eo
r
y
[
6
]
.
Ma
ch
i
n
e
lear
n
in
g
u
s
e
d
ata
to
ca
tch
a
p
atter
n
a
n
d
u
s
e
t
h
e
p
atter
n
to
p
r
ed
ict
th
e
f
u
tu
r
e
d
ata
o
r
m
ak
e
a
d
ec
is
io
n
i
n
u
n
ce
r
tain
co
n
d
itio
n
[
7
]
.
Data
is
an
ex
a
m
p
le
t
h
at
d
escr
ib
e
r
elatio
n
s
h
ip
b
et
w
ee
n
o
b
s
er
v
ed
v
ar
iab
les.
Ma
ch
i
n
e
lear
n
in
g
u
s
e
p
r
o
b
ab
ilis
tic
th
eo
r
y
to
b
u
ild
a
m
at
h
e
m
a
ti
c
m
o
d
el.
T
h
e
m
at
h
e
m
a
tic
m
o
d
el
r
ep
r
esen
ts
t
h
e
p
atter
n
t
h
at
ex
p
lai
n
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
o
b
s
er
v
e
v
ar
iab
les.
T
h
e
m
ai
n
f
o
c
u
s
o
f
m
ac
h
i
n
e
lear
n
in
g
r
ese
ar
ch
is
h
o
w
to
au
to
m
at
icall
y
r
ec
o
g
n
ize
a
co
m
p
lex
p
atter
n
i
n
d
etail.
E
v
en
t
u
all
y
,
t
h
is
ap
p
r
o
ac
h
is
v
er
y
h
e
lp
f
u
l
to
m
a
k
e
an
in
telli
g
e
n
t
d
ec
i
s
io
n
b
a
s
ed
o
n
d
ata.
T
h
er
e
ar
e
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e;
(
1
)
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
SVM)
,
(
2
)
k
-
Nea
r
es
t N
eig
h
b
o
r
s
(
KNN)
,
(
3
)
A
r
tif
i
cial
Neu
r
al
Net
w
o
r
k
,
etc.
I
n
th
is
r
esear
c
h
,
th
e
c
h
o
s
e
n
m
ac
h
in
e
lear
n
i
n
g
tec
h
n
iq
u
e
is
N
aiv
e
B
a
y
e
s
C
la
s
s
i
f
ier
(
NB
C
)
.
NB
C
is
an
alg
o
r
it
h
m
u
s
ed
to
f
in
d
t
h
e
h
i
g
h
est
p
r
o
b
ab
ilit
y
to
cl
ass
i
f
y
te
s
ti
n
g
d
ata
in
to
th
e
m
o
s
t
ap
p
r
o
p
r
iate
ca
teg
o
r
y
[
8
]
.
NB
C
ca
n
b
e
u
s
e
d
in
ca
s
es
th
at
h
a
v
e
li
m
ited
n
u
m
b
er
o
f
tar
g
et
ca
te
g
o
r
y
[
9
]
.
I
t
is
also
k
n
o
w
n
as
a
s
i
m
p
le
tec
h
n
iq
u
e
b
u
t
it
h
as
a
h
i
g
h
ac
cu
r
ac
y
[
1
0
]
an
d
s
p
ee
d
[
1
1
]
.
T
h
e
ad
v
an
tag
e
o
f
u
s
i
n
g
NB
C
is
it
r
eq
u
ir
es
a
s
m
all
a
m
o
u
n
t
o
f
tr
a
in
i
n
g
d
ata
to
esti
m
ate
t
h
e
p
ar
am
eter
s
n
ec
ess
ar
y
f
o
r
clas
s
if
ic
atio
n
[
1
2
]
,
[
1
3
]
s
o
th
at
it
h
as
s
h
o
r
t
co
m
p
u
tat
io
n
al
ti
m
e
f
o
r
tr
ain
in
g
p
r
o
ce
s
s
.
NB
C
s
i
m
p
li
f
y
lear
n
i
n
g
b
y
ass
u
m
i
n
g
t
h
at
f
ea
t
u
r
es
ar
e
in
d
ep
en
d
e
n
t
g
i
v
e
n
cla
s
s
[
1
0
]
.
T
h
e
class
i
f
icatio
n
p
r
o
ce
s
s
is
d
o
n
e
to
t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
d
ata
in
2
s
tag
e
s
,
w
h
ich
ar
e
tr
ain
i
n
g
s
t
ag
e
a
n
d
class
if
ica
tio
n
s
tag
e.
I
n
tr
ai
n
in
g
s
ta
g
e,
tr
ain
i
n
g
d
ata
w
il
l
b
e
u
s
ed
i
n
lear
n
in
g
p
r
o
ce
s
s
to
g
ai
n
k
n
o
w
led
g
e.
T
h
e
s
ec
o
n
d
s
tag
e
i
s
class
i
f
icatio
n
s
ta
g
e.
I
n
clas
s
if
icatio
n
s
ta
g
e,
s
y
s
te
m
w
i
ll
class
if
y
an
e
n
tit
y
b
ased
o
n
th
e
tr
ain
in
g
r
esu
lt.
T
h
e
en
tit
y
ca
n
b
e
class
i
f
y
i
n
to
p
o
s
itiv
e
o
r
n
eg
at
iv
e
ca
te
g
o
r
y
.
F
in
al
l
y
,
b
y
co
n
d
u
ct
in
g
t
h
is
p
ap
er
,
th
e
d
ata
is
m
o
d
elled
an
d
clas
s
i
f
ied
in
o
r
d
er
to
an
al
y
ze
t
h
e
s
o
cial
s
en
t
i
m
e
n
t to
w
ar
d
s
t
h
e
L
R
T
d
ev
elo
p
m
e
n
t.
2
.
RE
SE
ARCH
M
E
T
H
O
D
T
h
is
p
ar
t
d
escr
ib
es
a
b
o
u
t
th
e
r
esear
ch
m
et
h
o
d
o
lo
g
y
to
g
et
th
e
r
esear
ch
d
o
n
e.
Fig
u
r
e
1
s
h
o
w
s
t
h
e
r
esear
ch
m
et
h
o
d
o
lo
g
y
w
h
ic
h
c
o
n
tain
s
f
o
u
r
p
h
ases
.
Fig
u
r
e
1
.
R
esear
ch
Me
t
h
o
d
o
lo
g
y
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:
2
5
0
2
-
4752
Op
in
io
n
Min
in
g
u
s
in
g
Ma
ch
in
e
Lea
r
n
in
g
A
p
p
r
o
a
ch
…
(
S
a
r
ifa
h
P
u
tr
i R
a
fles
ia
)
793
2
.
1
.
Da
t
a
Co
llect
io
n
T
h
e
f
ir
s
t
p
h
a
s
e
is
d
ata
co
llect
i
o
n
p
r
o
ce
s
s
.
At
t
h
is
p
h
ase,
p
eo
p
le
o
p
in
io
n
ab
o
u
t
L
R
T
d
ev
elo
p
m
e
n
t
w
er
e
co
llected
f
r
o
m
s
o
cial
m
ed
ia.
I
n
th
is
r
esear
ch
,
d
ata
wer
e
co
llected
f
r
o
m
Face
b
o
o
k
u
s
i
n
g
Face
b
o
o
k
A
P
I
.
T
h
is
p
r
o
ce
s
s
o
b
tain
ed
4
9
4
d
ata
f
r
o
m
Face
b
o
o
k
.
Af
ter
war
d
,
th
o
s
e
o
p
in
io
n
s
ar
e
g
r
o
u
p
e
d
in
to
n
eg
a
tiv
e
an
d
p
o
s
itiv
e
ca
te
g
o
r
y
.
2
.
2
.
P
re
-
pro
ce
s
s
ing
T
h
e
s
ec
o
n
d
p
h
ase
is
p
r
e
-
p
r
o
ce
s
s
i
n
g
.
P
r
e
-
p
r
o
ce
s
s
i
n
g
p
h
a
s
e
ai
m
s
to
clea
n
u
p
th
e
d
ata
f
r
o
m
n
o
is
e.
I
n
th
i
s
r
esear
ch
,
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
co
n
ta
in
ed
4
p
r
o
ce
s
s
es,
w
h
ic
h
ar
e
ca
s
e
f
o
ld
in
g
,
to
k
en
izatio
n
,
s
to
p
w
o
r
d
s
r
e
m
o
v
a
l,
an
d
s
te
m
m
i
n
g
.
Fig
u
r
e
2
s
h
o
w
s
ca
s
e
f
o
ld
in
g
p
r
o
ce
s
s
.
I
n
ca
s
e
f
o
ld
in
g
p
r
o
ce
s
s
,
t
h
e
d
atasets
ar
e
t
u
r
n
ed
in
t
o
lo
w
e
r
ca
s
e
tex
t.
T
h
e
p
r
o
ce
s
s
is
f
o
l
lo
w
ed
b
y
to
k
e
n
izatio
n
p
r
o
ce
s
s
a
s
s
h
o
w
n
i
n
F
i
g
u
r
e
3
.
I
n
to
k
en
i
za
tio
n
p
r
o
ce
s
s
,
p
u
n
ct
u
atio
n
m
ar
k
s
ar
e
d
is
ca
r
d
ed
an
d
th
e
d
ata
ar
e
s
p
lit in
to
a
s
et
o
f
w
o
r
d
s
.
Fig
u
r
e
2
.
C
ase
Fo
ld
in
g
P
r
o
ce
s
s
Fig
u
r
e
3
.
T
o
k
en
izatio
n
P
r
o
ce
s
s
Sto
p
w
o
r
d
s
r
e
m
o
v
al
i
s
u
s
ed
to
d
is
ca
r
d
ir
r
elev
an
t
w
o
r
d
s
a
n
d
co
m
m
o
n
w
o
r
d
s
.
I
n
t
h
is
p
r
o
ce
s
s
,
a
lis
t
o
f
co
m
m
o
n
w
o
r
d
s
is
cr
ea
ted
.
T
h
e
lis
t
co
n
s
is
ted
o
f
co
n
j
u
n
cti
o
n
s
,
p
r
ep
o
s
itio
n
s
o
r
ad
v
er
b
s
.
T
h
e
s
y
s
te
m
w
ill
co
m
p
ar
e
t
h
e
d
ataset
s
an
d
t
h
e
lis
t
o
f
co
m
m
o
n
w
o
r
d
s
.
T
h
e
d
atasets
t
h
at
co
n
tai
n
a
w
o
r
d
i
n
th
e
li
s
t
w
il
l
b
e
r
e
m
o
v
ed
.
Fig
u
r
e
4
s
h
o
w
s
h
o
w
th
is
p
r
o
ce
s
s
is
d
o
n
e.
Fig
u
r
e
4
.
Sto
p
w
o
r
d
s
R
e
m
o
v
al
P
r
o
ce
s
s
T
h
e
last
p
r
o
ce
s
s
in
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
is
s
te
m
m
i
n
g
as
s
h
o
w
n
in
Fi
g
u
r
e
5
.
I
n
th
is
p
r
o
ce
s
s
,
th
e
w
o
r
d
s
ar
e
also
r
ed
u
ce
d
b
y
th
ei
r
r
o
o
t
w
o
r
d
.
T
h
is
is
d
o
n
e
b
y
r
em
o
v
i
n
g
an
y
attac
h
ed
s
u
f
fix
es
an
d
p
r
efi
x
e
s
.
A
lis
t o
f
s
u
f
fix
es a
r
e
d
e
fi
n
ed
a
n
d
w
il
l b
e
co
m
p
ar
ed
w
it
h
d
ataset.
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,
V
o
l.
1
1
,
No
.
2
,
A
u
g
u
s
t 2
0
1
8
:
7
9
1
–
79
6
794
2
.
3
.
T
ra
ini
ng
T
h
e
n
ex
t
p
h
ase
is
tr
ai
n
i
n
g
p
h
ase.
I
n
t
h
is
s
ta
g
e,
tr
ai
n
in
g
d
at
a
w
ill
b
e
u
s
ed
i
n
lear
n
in
g
p
r
o
ce
s
s
to
g
ain
k
n
o
w
led
g
e.
Nai
v
e
B
a
y
e
s
C
las
s
i
fi
er
s
(
NB
C
)
i
s
i
m
p
le
m
en
ted
to
ca
lcu
late
t
h
e
p
r
o
b
ab
ilit
y
o
f
tr
ain
i
n
g
d
ata.
E
q
u
atio
n
(
1
)
s
h
o
w
s
th
e
c
alcu
latio
n
o
f
p
r
o
b
ab
ilit
y
i
n
tr
ai
n
in
g
d
ata
b
ased
o
n
B
a
y
es t
h
eo
r
e
m
.
(
|
)
(
|
)
(
)
(
)
(
1
)
Fig
u
r
e
5
.
Ste
m
m
i
n
g
P
r
o
ce
s
s
T
h
e
p
r
o
b
ab
ilit
y
o
f
a
ca
te
g
o
r
y
g
iv
e
n
a
d
o
cu
m
e
n
t
(
P
(
c|
d
)
)
is
ca
lcu
lated
b
y
m
u
ltip
l
y
i
n
g
th
e
p
r
o
b
a
b
ilit
y
o
f
a
d
o
cu
m
e
n
t
g
i
v
en
a
ca
te
g
o
r
y
(
P
(
d
|c
)
)
an
d
p
r
o
b
ab
ilit
y
o
f
ca
teg
o
r
y
(
P
(
c
)
)
an
d
d
iv
id
ed
t
h
e
r
esu
l
t
w
it
h
p
r
o
b
ab
ilit
y
of
a
d
o
cu
m
en
t
(
P
(
d
)
)
.
T
h
e
p
r
o
b
a
b
ilit
y
of
a
ca
te
g
o
r
y
is
s
i
m
p
l
y
th
e
n
u
m
b
er
o
f
tr
ain
i
n
g
d
o
cu
m
e
n
ts
f
o
r
a
ca
te
g
o
r
y
d
iv
id
ed
b
y
t
h
e
to
tal
n
u
m
b
er
o
f
tr
ai
n
in
g
d
o
cu
m
e
n
ts
.
P
(
c|
d
)
,
w
h
ic
h
is
also
ca
lled
lik
eli
h
o
o
d
,
w
ill b
e
u
s
ed
to
fi
n
d
d
ata
class
i
fi
ca
tio
n
.
2.
4.
T
esting
I
n
test
in
g
p
h
ase,
p
eo
p
le
o
p
in
io
n
ab
o
u
t
L
ig
h
t
R
ail
T
r
an
s
it
(
L
R
T
)
d
ev
elo
p
m
e
n
t
in
I
n
d
o
n
e
s
ia
ar
e
co
llected
a
s
d
ata
test
i
n
g
.
T
h
e
s
e
d
ata
w
ill
b
e
test
ed
u
s
i
n
g
t
h
e
p
r
o
b
ab
ilit
y
o
b
tai
n
ed
in
t
h
e
tr
ain
i
n
g
p
h
ase.
T
h
e
p
r
o
b
ab
ilit
y
v
al
u
e
is
co
m
p
ar
ed
w
it
h
th
r
e
s
h
o
ld
v
al
u
e
to
d
eter
m
i
n
e
th
e
class
if
icatio
n
r
es
u
lt.
E
q
u
atio
n
(
2
)
is
u
s
ed
to
class
i
f
y
d
ata
u
s
i
n
g
NB
C
.
(
)
∏
(
|
)
(
2
)
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:
2
5
0
2
-
4752
Op
in
io
n
Min
in
g
u
s
in
g
Ma
ch
in
e
Lea
r
n
in
g
A
p
p
r
o
a
ch
…
(
S
a
r
ifa
h
P
u
tr
i R
a
fles
ia
)
795
T
h
e
o
p
in
io
n
ca
n
b
e
clas
s
i
f
y
i
n
to
p
o
s
itiv
e
o
r
n
eg
at
iv
e
ca
te
g
o
r
y
.
I
f
p
r
o
b
ab
ilit
y
v
al
u
e
is
eq
u
al
o
r
ex
ce
ed
s
t
h
r
es
h
o
ld
v
al
u
e,
t
h
e
o
p
in
io
n
w
i
ll
b
e
ca
te
g
o
r
ize
i
n
to
p
o
s
itiv
e
o
p
in
io
n
.
O
n
t
h
e
co
n
tr
ar
y
,
th
e
o
p
in
io
n
ca
n
b
e
ca
teg
o
r
ize
in
to
n
e
g
ati
v
e
o
p
in
io
n
w
h
e
n
th
e
p
r
o
b
ab
ilit
y
is
b
elo
w
t
h
r
esh
o
ld
v
a
lu
e.
3
.
RE
SUL
T
AND
A
NAL
YSI
S
T
h
e
i
m
p
le
m
e
n
tat
io
n
o
f
clas
s
i
fi
ca
t
io
n
p
r
o
ce
s
s
i
s
co
n
d
u
cted
u
s
i
n
g
p
h
y
to
n
an
d
P
HP
.
E
v
a
lu
atio
n
p
r
o
ce
s
s
ai
m
s
to
m
ea
s
u
r
e
p
er
f
o
r
m
a
n
ce
o
f
NB
C
i
n
cla
s
s
i
f
y
i
n
g
a
n
o
p
in
io
n
i
n
to
it
s
r
esp
e
ctiv
e
cla
s
s
.
T
h
e
a
m
o
u
n
t
o
f
d
ata
t
h
at
w
e
u
s
ed
as
test
i
n
g
d
ata
i
n
ev
a
lu
at
io
n
p
r
o
ce
s
s
w
er
e
1
2
6
.
T
ab
le
1
s
h
o
w
s
co
n
f
u
s
io
n
m
atr
i
x
f
o
r
class
i
fi
ca
tio
n
p
r
o
ce
s
s
.
T
ab
le
1
.
C
o
n
f
u
s
io
n
Ma
tr
i
x
f
o
r
Naiv
e
B
a
y
es
C
las
s
i
f
icatio
n
D
a
t
a
C
l
a
ss
P
r
e
d
i
c
t
i
o
n
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
T
o
t
a
l
A
c
t
u
a
l
P
o
si
t
i
v
e
65
4
69
N
e
g
a
t
i
v
e
17
40
57
T
o
t
a
l
82
44
1
2
6
Data
in
co
n
f
u
s
io
n
m
atr
ix
w
i
l
l
b
e
u
s
ed
to
ev
alu
ate
p
er
f
o
r
m
an
ce
o
f
class
i
ficatio
n
p
r
o
ce
s
s
.
T
h
e
co
m
m
o
n
m
ea
s
u
r
e
m
e
n
ts
f
o
r
class
i
fi
ca
t
io
n
b
ased
o
n
th
e
co
n
f
u
s
io
n
m
atr
ix
[
1
4
]
ar
e
s
h
o
w
n
o
n
T
ab
le
2
.
T
ab
le
2
.
T
h
e
Me
asu
r
e
m
e
n
t o
f
P
er
f
o
r
m
a
n
ce
M
e
a
su
r
e
me
n
t
V
a
l
u
e
P
r
e
c
i
si
o
n
0
.
79
R
e
c
a
l
l
0
.
9
4
S
p
e
c
i
f
i
c
i
t
y
0
.
7
0
F
-
M
e
a
su
r
e
0
.
8
6
A
c
c
u
r
a
c
y
0.
83
A
r
e
a
U
n
d
e
r
t
h
e
C
u
r
v
e
(
A
U
C
)
0
.
82
P
r
ec
is
io
n
d
escr
ib
es
th
e
p
r
o
p
o
r
tio
n
o
f
p
ed
icted
p
o
s
itiv
e
ca
s
es
th
at
ar
e
co
r
r
ec
tly
class
i
fi
e
d
[
1
5
]
.
I
n
t
h
is
r
esear
ch
,
t
h
e
p
r
ec
is
io
n
v
al
u
e
o
f
cla
s
s
i
ficatio
n
p
r
o
ce
s
s
is
0
,
7
9
.
T
h
is
r
es
u
lt
is
q
u
ite
h
ig
h
w
h
ic
h
in
d
icate
s
t
h
at
th
e
clas
s
i
fi
ca
tio
n
r
esu
lt
o
n
l
y
h
a
v
e
s
m
all
n
u
m
b
er
o
f
f
alse
p
o
s
itiv
e.
Sen
s
iti
v
it
y
a
n
d
s
p
ec
i
fi
cit
y
ar
e
t
w
o
m
ea
s
u
r
e
m
e
n
ts
th
at
ar
e
u
s
ed
to
g
et
h
er
to
m
ea
s
u
r
e
th
e
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
o
f
a
class
i
fi
ca
tio
n
m
o
d
el
[
1
6
]
.
Sen
s
iti
v
it
y
,
w
h
ic
h
is
a
ls
o
k
n
o
w
n
as
r
ec
all,
s
h
o
w
s
th
e
p
r
o
p
o
r
tio
n
o
f
r
ea
l
p
o
s
iti
v
e
ca
s
e
s
th
a
t
co
r
r
ec
tly
cla
s
s
s
i
fi
ed
.
Sp
ec
i
ficit
y
d
escr
ib
es
t
h
e
p
r
o
p
o
r
tio
n
o
f
r
ea
l
n
e
g
ati
v
e
ca
s
es
th
at
ar
e
co
r
r
ec
tl
y
class
i
fi
ed
.
T
h
e
r
ec
all
v
a
lu
e
o
f
cla
s
s
i
ficatio
n
p
r
o
ce
s
s
i
s
0
,
9
4
.
T
h
is
r
es
u
lt
s
h
o
w
s
th
at
t
h
e
cla
s
s
i
ficatio
n
p
r
o
ce
s
s
p
r
o
d
u
ce
s
a
v
er
y
s
m
all
a
m
o
u
n
t
o
f
f
a
ls
e
n
eg
a
tiv
e.
T
h
e
r
esu
lt
a
ls
o
s
h
o
w
s
t
h
at
t
h
e
s
p
ec
ifi
c
it
y
v
al
u
e
i
n
th
is
r
esear
c
h
is
n
o
t q
u
ite
h
ig
h
.
S
y
s
te
m
ca
n
o
n
l
y
clas
s
i
fi
ed
7
0
% r
ea
l n
eg
at
iv
e
ca
s
es c
o
r
r
ec
tly
.
I
n
ad
d
itio
n
to
th
o
s
e
m
ea
s
u
r
e
m
en
ts
,
w
e
also
u
s
e
F
-
m
ea
s
u
r
e
to
e
v
alu
a
te
cla
s
s
s
i
fi
ca
tio
n
r
es
u
lt
.
F
-
m
ea
s
u
r
e
is
co
n
s
id
er
ed
as
a
b
etter
m
ea
s
u
r
e
m
e
n
t
t
h
a
n
p
r
ec
is
io
n
a
n
d
r
ec
all
b
ec
au
s
e
i
t
tak
e
s
b
o
th
p
r
ec
is
io
n
an
d
r
ec
all
m
ea
s
u
r
e
m
e
n
t
i
n
to
co
n
s
id
er
atio
n
.
F
-
m
ea
s
u
r
e
w
ill
p
r
o
d
u
ce
a
h
ig
h
r
es
u
lt
w
h
en
p
r
ec
is
io
n
an
d
r
ec
all
v
alu
e
ar
e
b
alan
ce
.
T
h
e
v
alu
e
o
f
F
-
m
ea
s
u
r
e
in
t
h
i
s
r
esea
r
ch
is
0
,
8
6
.
A
cc
u
r
ac
y
i
s
a
m
ea
s
u
r
e
m
e
n
t
to
ev
al
u
ate
r
atio
o
f
co
r
r
ec
t
p
r
ed
ictio
n
ca
s
e
s
o
v
er
t
h
e
to
tal
n
u
m
b
er
o
f
ca
s
es
[
1
7
]
.
Ov
er
all
ac
cu
r
ac
y
o
f
clas
s
i
fi
ca
t
io
n
u
s
i
n
g
n
ai
v
e
b
a
y
es
i
s
0
.
8
3
.
T
h
is
r
es
u
lt
s
h
o
w
s
th
at
t
h
e
s
y
s
te
m
ca
n
co
r
r
ec
tl
y
class
i
fi
ed
8
3
% c
ases
o
v
er
all
t
h
e
g
i
v
e
n
ca
s
es.
A
U
C
is
a
m
ea
s
u
r
e
m
en
t
to
e
v
alu
ate
t
h
e
ab
ilit
y
o
f
clas
s
i
fi
er
in
av
o
id
i
n
g
f
alse
cla
s
s
i
ficatio
n
[
1
4
]
.
A
U
C
is
b
elie
v
ed
as
a
b
etter
m
ea
s
u
r
e
m
en
t
to
e
v
alu
a
te
a
m
ac
h
in
e
lear
n
i
n
g
tec
h
n
iq
u
e
t
h
a
n
ac
cu
r
ac
y
b
ec
au
s
e
A
U
C
i
s
m
o
r
e
d
is
cr
i
m
i
n
ati
n
g
an
d
s
tati
s
ticall
y
co
n
s
i
s
ten
t
[
1
8
]
.
A
s
s
h
o
w
n
i
n
T
ab
le
2
,
A
UC
v
alu
e
in
th
i
s
r
esear
ch
is
0
.
8
2
.
4
.
CO
NCLUS
I
O
N
I
n
th
is
r
esear
c
h
,
w
e
u
s
ed
m
a
ch
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
to
cl
ass
i
f
y
u
s
er
p
er
ce
p
tio
n
o
f
L
i
g
h
t
R
ail
T
r
an
s
it
in
I
n
d
o
n
esia.
W
e
i
m
p
le
m
e
n
ted
NB
C
to
d
eter
m
in
e
p
r
o
b
a
b
ilit
y
a
n
d
lik
el
ih
o
o
d
r
atio
.
Naiv
e
b
a
y
e
s
class
i
fi
er
h
ad
b
ee
n
ch
o
s
e
n
b
ec
au
s
e
it
r
eq
u
ir
es
a
s
m
all
a
m
o
u
n
t
o
f
tr
ain
i
n
g
d
ata
an
d
s
h
o
r
t
co
m
p
u
tatio
n
a
l
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,
V
o
l.
1
1
,
No
.
2
,
A
u
g
u
s
t 2
0
1
8
:
7
9
1
–
79
6
796
ti
m
e
f
o
r
tr
ai
n
i
n
g
p
r
o
ce
s
s
.
Da
t
asets
w
er
e
co
llected
f
r
o
m
Fac
eb
o
o
k
u
s
i
n
g
Face
b
o
o
k
A
P
I
.
T
h
e
te
s
ti
n
g
r
esu
lt
s
h
o
w
s
t
h
at
t
h
e
tech
n
iq
u
e
i
s
q
u
ite
e
f
f
ec
ti
v
e
i
n
clas
s
i
f
y
i
n
g
p
eo
p
le
o
p
in
io
n
ab
o
u
t
L
R
T
d
ev
elo
p
m
e
n
t.
T
h
i
s
r
esu
lt
also
in
d
icate
s
th
at
t
h
e
te
ch
n
iq
u
e
ca
n
b
e
u
s
ed
to
g
ain
k
n
o
w
led
g
e
in
o
r
d
er
to
s
u
p
p
o
r
t d
ec
is
io
n
-
m
a
k
i
n
g
p
r
o
ce
s
s
r
eg
ar
d
in
g
L
R
T
d
ev
elo
p
m
e
n
t i
n
I
n
d
o
n
e
s
ia.
REFEREN
CES
[1
]
N.
A
n
ste
a
d
a
n
d
B.
O’L
o
u
g
h
li
n
,
“
S
o
c
ial
m
e
d
ia
a
n
a
l
y
sis
a
n
d
p
u
b
li
c
o
p
i
n
io
n
:
T
h
e
2
0
1
0
UK
g
e
n
e
ra
l
e
lec
ti
o
n
,
”
J
.
Co
mp
u
t
.
Co
mm
u
n
.
,
v
o
l.
2
0
,
n
o
.
2
,
p
p
.
2
0
4
–
2
2
0
,
2
0
1
5
.
[2
]
J.
A
.
Ba
rn
e
s,
“
Gra
p
h
th
e
o
ry
a
n
d
so
c
ial
n
e
t
w
o
rk
s:
A
tec
h
n
ica
l
c
o
m
m
e
n
t
o
n
c
o
n
n
e
c
ted
n
e
ss
a
n
d
c
o
n
n
e
c
ti
v
it
y
,
”
S
o
c
io
lo
g
y
,
v
o
l.
3
,
n
o
.
2
,
p
p
.
2
1
5
–
2
3
2
,
1
9
6
9
.
[3
]
A
.
W
h
it
in
g
a
n
d
D.
W
il
li
a
m
s,
“
Wh
y
p
e
o
p
le
u
se
so
c
ial
m
e
d
ia:
a
u
se
s
a
n
d
g
ra
ti
f
ica
ti
o
n
s
a
p
p
ro
a
c
h
,
”
Qu
a
l.
M
a
rk
.
Res
.
An
I
n
t.
J
.
,
v
o
l.
1
6
,
n
o
.
4
,
p
p
.
3
6
2
–
3
6
9
,
2
0
1
3
.
[4
]
B.
L
iu
a
n
d
L
.
Zh
a
n
g
,
“
A
su
rv
e
y
o
f
o
p
in
io
n
m
in
in
g
a
n
d
se
n
ti
m
e
n
t
a
n
a
ly
sis,”
in
M
in
in
g
tex
t
d
a
t
a
,
S
p
ri
n
g
e
r,
2
0
1
2
,
p
p
.
4
1
5
–
4
6
3
.
[5
]
E.
F
e
rsin
i
,
E.
M
e
ss
in
a
,
a
n
d
F
.
A
.
P
o
z
z
i,
“
S
e
n
t
im
e
n
t
a
n
a
l
y
sis:
Ba
y
e
sia
n
e
n
se
m
b
le
lea
rn
in
g
,
”
D
e
c
is.
S
u
p
p
o
r
t
S
y
st.
,
v
o
l.
6
8
,
p
p
.
2
6
–
3
8
,
2
0
1
4
.
[6
]
D.
E.
G
o
ld
b
e
rg
a
n
d
J.
H.
Ho
ll
a
n
d
,
“
G
e
n
e
ti
c
a
lg
o
rit
h
m
s
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
”
M
a
c
h
.
L
e
a
r
n
.
,
v
o
l.
3
,
n
o
.
2
,
p
p
.
95
–
9
9
,
1
9
8
8
.
[7
]
K.
P
.
M
u
rp
h
y
,
M
a
c
h
in
e
L
e
a
r
n
in
g
:
A
Pro
b
a
b
il
isti
c
Per
sp
e
c
ti
v
e
.
2
0
1
2
.
[8
]
R.
F
e
ld
m
a
n
a
n
d
J.
S
a
n
g
e
r,
“
T
h
e
tex
t
m
in
in
g
h
a
n
d
b
o
o
k
:
a
d
v
a
n
c
e
d
a
p
p
ro
a
c
h
e
s
in
a
n
a
ly
z
in
g
u
n
stru
c
t
u
re
d
d
a
ta,”
Ima
g
i
n
e
,
v
o
l.
3
4
,
p
.
4
1
0
,
2
0
0
7
.
[9
]
Z.
F
.
A
lf
ik
ri
a
n
d
A
.
P
u
rw
a
rian
ti
,
“
De
tailed
A
n
a
l
y
sis
o
f
Ex
tri
n
sic
P
lag
iaris
m
De
te
c
ti
o
n
S
y
ste
m
Us
in
g
M
a
c
h
in
e
L
e
a
rn
in
g
A
p
p
ro
a
c
h
(Na
iv
e
Ba
y
e
s
a
n
d
S
V
M
)
,
”
T
EL
KOM
NIKA
In
d
o
n
e
s.
J
.
El
e
c
tr.
En
g
.
,
v
o
l.
1
2
,
n
o
.
1
1
,
p
p
.
7
8
8
4
–
7
8
9
4
,
2
0
1
4
.
[1
0
]
I.
Rish
,
“
A
n
e
m
p
iri
c
a
l
stu
d
y
o
f
th
e
n
a
iv
e
Ba
y
e
s
c
l
a
ss
i
f
ier,”
in
IJ
CAI
2
0
0
1
w
o
rk
sh
o
p
o
n
e
mp
irica
l
me
th
o
d
s
in
a
rtif
icia
l
in
telli
g
e
n
c
e
,
2
0
0
1
,
v
o
l.
3
,
n
o
.
2
2
,
p
p
.
4
1
–
4
6
.
[1
1
]
L
.
Du
a
n
,
P
.
Di,
a
n
d
A
.
L
i,
“
A
N
e
w
Na
iv
e
Ba
y
e
s
Tex
t
Clas
sif
i
c
a
t
io
n
A
lg
o
rit
h
m
,
”
T
EL
KOM
NIKA
In
d
o
n
e
s.
J
.
El
e
c
tr.
En
g
.
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
9
4
7
–
9
5
2
,
2
0
1
4
.
[1
2
]
L
.
D
e
y
,
S
.
Ch
a
k
ra
b
o
rty
,
A
.
Bis
w
a
s,
B.
Bo
se
,
a
n
d
S
.
T
iw
a
ri,
“
S
e
n
ti
m
e
n
t
A
n
a
l
y
sis
o
f
Re
v
ie
w
Da
tas
e
ts
Us
in
g
Na
iv
e
Ba
y
e
s an
d
K
-
NN
Clas
si
f
ier
,
”
a
rXiv P
re
p
r.
a
rXiv1
6
1
0
.
0
9
9
8
2
,
2
0
1
6
.
[1
3
]
L
.
F
a
n
,
X
.
H
u
a
n
g
,
a
n
d
L
.
Yi,
“
F
a
u
lt
Dia
g
n
o
sis
f
o
r
F
u
e
l
Ce
ll
Ba
se
d
o
n
Na
iv
e
Ba
y
e
si
a
n
Clas
sif
ica
ti
o
n
,
”
T
EL
KOM
NIKA
In
d
o
n
e
s.
J
.
El
e
c
t
r.
En
g
.
,
v
o
l
.
1
1
,
n
o
.
1
2
,
p
p
.
7
6
6
4
–
7
6
7
0
,
2
0
1
3
.
[1
4
]
M
.
S
o
k
o
l
o
v
a
a
n
d
G
.
L
a
p
a
l
m
e
,
“
A
s
y
ste
m
a
ti
c
a
n
a
l
y
sis
o
f
p
e
r
f
o
rm
a
n
c
e
m
e
a
su
re
s
f
o
r
c
la
ss
i
f
ica
ti
o
n
tas
k
s,”
In
f.
Pro
c
e
ss
.
M
a
n
a
g
.
,
v
o
l
.
4
5
,
n
o
.
4
,
p
p
.
4
2
7
–
4
3
7
,
2
0
0
9
.
[1
5
]
D.
M
.
W
.
P
OW
ERS
,
“
Ev
a
lu
a
ti
o
n
:
F
r
o
m
P
re
c
isio
n
,
Re
c
a
ll
a
n
d
F
-
M
e
a
su
re
T
o
Ro
c
,
I
n
f
o
rm
e
d
n
e
ss
,
M
a
rk
e
d
n
e
ss
&
Co
rre
latio
n
,
”
J
.
M
a
c
h
.
L
e
a
rn
.
T
e
c
h
n
o
l
.
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
3
7
–
6
3
,
2
0
1
1
.
[1
6
]
K.
M
.
T
in
g
,
“
S
e
n
si
ti
v
it
y
a
n
d
S
p
e
c
if
icit
y
,
”
in
En
c
y
c
lo
p
e
d
i
a
o
f
M
a
c
h
in
e
L
e
a
r
n
in
g
,
C
.
S
a
m
m
u
t
a
n
d
G
.
.
W
e
b
b
,
Ed
s.
Bo
st
o
n
,
M
A
:
S
p
ri
n
g
e
r,
2
0
1
1
.
[1
7
]
M
.
Ho
ss
i
n
a
n
d
M
.
N.
S
u
laim
a
n
,
“
a
Re
v
ie
w
o
n
Ev
a
lu
a
ti
o
n
M
e
tri
c
s
f
o
r
Da
ta
Clas
sif
ic
a
ti
o
n
Ev
a
lu
a
ti
o
n
s,”
In
t
.
J
.
Da
ta
M
in
.
Kn
o
wl.
M
a
n
a
g
.
Pro
c
e
ss
,
v
o
l.
5
,
n
o
.
2
,
p
p
.
1
–
1
1
,
2
0
1
5
.
[1
8
]
C.
X
.
L
in
g
,
J.
Hu
a
n
g
,
a
n
d
H.
Zh
a
n
g
,
“
A
UC:
A
sta
ti
stica
ll
y
c
o
n
siste
n
t
a
n
d
m
o
re
d
isc
ri
m
in
a
ti
n
g
m
e
a
su
re
th
a
n
a
c
c
u
ra
c
y
,
”
in
IJ
CAI
In
ter
n
a
ti
o
n
a
l
J
o
in
t
Co
n
fer
e
n
c
e
o
n
Art
if
icia
l
In
t
e
ll
ig
e
n
c
e
,
2
0
0
3
,
p
p
.
5
1
9
–
5
2
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.