T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
19
,
No
.
6
,
Dec
em
b
er
2
0
2
1
,
p
p
.
1
8
65
~1
8
71
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
9
i6
.
2
1
5
9
4
1865
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Co
mpa
riso
n
o
f
th
e f
ea
tu
re sele
ction
alg
o
r
ithm in
ed
u
ca
tiona
l
da
ta mining
Ag
un
g
T
ria
y
ud
i,
I
s
k
a
nd
a
r
F
it
ri
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
,
Un
i
v
e
rsitas
Na
sio
n
a
l,
Ja
k
a
rta,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
1
1
,
2
0
2
0
R
ev
is
ed
Ap
r
3
0
,
2
0
2
1
Acc
ep
ted
May
1
5
,
2
0
21
S
tu
d
e
n
t
a
c
a
d
e
m
ic
a
c
c
o
m
p
li
sh
m
e
n
t
is
t
h
e
f
o
re
m
o
st
f
o
c
u
s
o
f
e
v
e
ry
e
d
u
c
a
ti
o
n
a
l
in
stit
u
ti
o
n
.
In
d
e
v
e
lo
p
in
g
stu
d
e
n
t
a
c
h
iev
e
m
e
n
t
in
e
d
u
c
a
ti
o
n
a
l
in
stit
u
ti
o
n
s,
th
e
re
se
a
rc
h
e
rs
fin
a
ll
y
c
re
a
ted
a
n
e
w
re
se
a
rc
h
a
re
a
,
n
a
m
e
ly
e
d
u
c
a
ti
o
n
a
l
d
a
ta
m
in
in
g
(EDM
).
H
o
w
th
e
fe
a
tu
re
se
lec
ti
o
n
(
FS)
a
l
g
o
rit
h
m
wo
rk
s
is
b
y
re
m
o
v
in
g
u
n
re
late
d
d
a
ta
fro
m
e
d
u
c
a
ti
o
n
a
l
d
a
tas
e
ts;
th
e
re
fo
re
,
t
h
is
a
lg
o
rit
h
m
c
a
n
imp
ro
v
e
t
h
e
c
las
sifica
ti
o
n
p
e
rfo
rm
a
n
c
e
m
a
n
a
g
e
d
in
EDM
tec
h
n
iq
u
e
s.
T
h
is
re
s
e
a
rc
h
p
re
se
n
ts an
a
n
a
ly
sis
o
f
t
h
e
p
e
rfo
rm
a
n
c
e
o
f
t
h
e
FS
a
lg
o
rit
h
m
fro
m
th
e
stu
d
e
n
t
d
a
tas
e
t.
Th
e
re
su
lt
s
re
c
e
iv
e
d
fro
m
o
t
h
e
r
F
S
a
lg
o
rit
h
m
s
a
n
d
c
las
sifiers
will
h
e
lp
o
t
h
e
r
re
se
a
rc
h
e
rs
to
g
a
in
so
m
e
b
e
st
c
o
m
b
in
a
ti
o
n
re
g
a
rd
in
g
FS
a
lg
o
rit
h
m
s
a
n
d
th
e
c
las
sifica
ti
o
n
.
S
e
lec
ti
n
g
fe
a
tu
re
s
th
a
t
a
re
re
lev
a
n
t
fo
r
stu
d
e
n
t
f
o
re
c
a
st
m
o
d
e
ls
is
a
s
e
n
siti
v
e
p
ro
b
lem
to
sta
k
e
h
o
ld
e
rs
in
e
d
u
c
a
ti
o
n
b
e
c
a
u
se
th
e
y
m
u
st
m
a
k
e
d
e
c
isio
n
s
b
a
se
d
o
n
th
e
re
su
lt
s
o
f
t
h
e
p
re
d
ictio
n
m
o
d
e
ls.
F
o
r
t
h
e
fu
t
u
re
,
o
u
r
p
a
p
e
r
s
e
e
k
s
to
p
lay
a
d
e
c
isiv
e
p
a
rt
wh
il
e
d
e
v
e
lo
p
i
n
g
q
u
a
li
t
y
c
o
n
c
e
rn
i
n
g
e
d
u
c
a
ti
o
n
,
a
s
we
ll
a
s
g
u
id
in
g
d
iffere
n
t
re
se
a
rc
h
e
rs
in
c
o
n
d
u
c
ti
n
g
e
d
u
c
a
ti
o
n
a
l
in
ter
v
e
n
ti
o
n
s
.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
Dec
is
io
n
E
d
u
ca
tio
n
al
d
ata
m
in
in
g
Featu
r
e
s
elec
tio
n
alg
o
r
ith
m
Stu
d
en
t a
ca
d
em
ic
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
:
Ag
u
n
g
T
r
iay
u
d
i
Dep
ar
tm
en
t
o
f
I
n
f
o
r
m
atic
Un
iv
er
s
itas
Nasio
n
al
J
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail:
ag
u
n
g
tr
ia
y
u
d
i@
civ
itas
.
u
n
as.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
o
s
t
im
p
o
r
tan
t
asp
ec
ts
o
f
b
u
ild
in
g
a
s
tr
o
n
g
s
eg
m
en
t
o
f
civ
ilizatio
n
ar
e
im
p
r
o
v
e
m
en
t
with
in
th
e
q
u
ality
o
f
e
d
u
ca
tio
n
[
1
]
.
Dat
a
s
to
r
ed
u
n
d
e
r
r
ep
o
s
ito
r
ies
o
f
ed
u
ca
tio
n
al
in
s
titu
tio
n
s
p
la
y
a
cr
u
cial
p
ar
t
i
n
ex
tr
ac
tin
g
d
ee
p
a
n
d
u
n
u
s
u
al
tr
i
m
s
to
h
elp
ea
ch
s
t
ak
eh
o
ld
er
o
f
an
ed
u
ca
tio
n
al
m
a
n
n
er
[
2
]
.
Se
v
er
al
m
eth
o
d
s
wer
e
ex
p
ec
tin
g
to
esti
m
ate
s
tu
d
e
n
ts
'
ed
u
ca
tio
n
al
ac
co
m
p
lis
h
m
en
ts
b
y
cr
ea
tin
g
a
b
r
ig
h
t
f
u
tu
r
e
f
o
r
th
eir
s
tu
d
en
ts
[
3
]
,
[
4
]
.
Pre
d
ictin
g
s
tu
d
en
t
p
e
r
f
o
r
m
an
ce
h
as
co
n
tin
u
ed
to
a
to
p
ic
th
at
is
q
u
ite
h
o
t
wit
h
in
th
e
s
co
p
e
o
f
ed
u
ca
tio
n
al
d
ata
m
in
in
g
(
E
D
M)
.
Data
m
in
in
g
is
th
e
b
est
ch
o
ice
u
s
ed
b
y
r
esear
ch
e
r
s
to
an
aly
ze
s
tu
d
en
t
p
er
f
o
r
m
an
ce
[
5
]
.
Data
m
in
in
g
tech
n
iq
u
es
th
at
m
ar
e
o
f
ten
u
s
e
d
in
th
e
p
r
o
ce
s
s
in
g
o
f
ed
u
ca
tio
n
al
d
ata
to
d
ay
ar
e
n
am
ed
E
D
M
[
2
]
.
E
DM
s
ea
r
ch
es
e
d
u
ca
tio
n
al
d
ata
to
f
u
lly
r
ec
o
g
n
ize
s
tu
d
en
t
c
o
m
p
letio
n
p
r
o
b
lem
s
b
y
ad
o
p
tin
g
a
v
ar
iety
o
f
d
ata
m
in
in
g
tech
n
iq
u
es
[
6
]
.
T
o
ass
is
t
ed
u
ca
tio
n
al
in
s
titu
tio
n
s
to
o
r
g
an
is
e
ed
u
ca
tio
n
p
o
licies
to
in
cr
ea
s
e
th
e
v
ar
iety
o
f
ed
u
ca
tio
n
,
E
DM
u
s
es e
d
u
ca
tio
n
al
d
at
a
m
an
ip
u
lati
o
n
tech
n
iq
u
es [
7
]
.
On
e
o
f
th
e
f
o
r
em
o
s
t
f
ield
s
o
f
E
DM
is
f
o
r
esig
h
t.
Fo
r
esi
g
h
t
an
d
a
n
aly
s
is
o
f
s
tu
d
en
t
ed
u
ca
tio
n
al
ac
h
iev
em
en
t
a
r
e
r
eq
u
ir
e
d
to
s
tu
d
en
t
e
d
u
ca
tio
n
al
m
ajo
r
ity
.
I
d
en
tific
atio
n
o
f
d
eter
m
in
a
n
ts
t
h
at
af
f
ec
t
s
tu
d
en
ts
'
ed
u
ca
tio
n
al
ac
co
m
p
lis
h
m
e
n
t
i
s
a
r
ea
s
o
n
a
b
ly
tr
ick
y
an
aly
s
is
jo
b
[
8
]
.
Un
iq
u
e
ed
u
ca
tio
n
al
d
ata
in
clu
d
es
a
lo
t
o
f
u
n
r
elate
d
d
ata,
in
cl
u
d
in
g
r
ed
u
n
d
an
cy
.
R
ed
u
n
d
an
cy
d
ata
ca
n
af
f
ec
t th
e
r
esu
lts
o
f
p
r
ed
ictio
n
s
.
Ho
wev
er
,
we
ca
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
6
,
Dec
em
b
e
r
2
0
2
1
:
18
65
-
18
71
1866
d
ec
r
ea
s
e
s
o
m
e
r
e
d
u
n
d
an
cy
an
d
in
cr
ea
s
e
th
e
r
elev
a
n
cy
o
f
p
o
in
ts
with
o
u
t
a
n
y
waste
r
e
g
ar
d
in
g
im
p
o
r
tan
t
d
ata
with
th
e
f
ea
tu
r
e
s
elec
tio
n
(
FS
)
m
eth
o
d
[
9
]
.
T
h
e
em
b
e
d
d
ed
m
eth
o
d
is
a
u
n
iq
u
e
m
eth
o
d
f
o
r
s
ev
er
al
lear
n
i
n
g
alg
o
r
ith
m
s
g
iv
e
n
,
an
d
th
is
m
eth
o
d
is
also
ca
r
r
ied
o
u
t
in
t
h
e
tr
ain
i
n
g
p
r
o
c
ess
in
class
if
icatio
n
.
T
h
e
f
ilter
m
eth
o
d
d
ep
en
d
s
o
n
th
e
c
o
m
m
o
n
f
ea
tu
r
es
o
f
th
e
p
r
ac
tice
d
ata,
an
d
th
is
m
eth
o
d
is
ca
r
r
ie
d
o
u
t
at
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
a
n
d
d
o
es
n
o
t
d
ep
e
n
d
o
n
t
h
e
ed
u
ca
tio
n
al
alg
o
r
ith
m
.
T
h
e
w
r
ap
p
er
m
eth
o
d
u
s
es
an
ed
u
ca
t
io
n
al
alg
o
r
ith
m
to
e
v
alu
ate
f
e
atu
r
es
[
1
0
]
.
Featu
r
e
se
lectio
n
(
FS
)
is
o
n
e
o
f
th
e
m
o
s
t
p
r
o
d
u
ctiv
e
an
d
v
er
y
d
y
n
a
m
ic
f
ield
s
o
f
th
e
an
aly
s
is
f
ield
in
m
ac
h
in
e
lear
n
in
g
an
d
d
ata
m
in
in
g
.
T
h
e
p
r
im
ar
y
p
u
r
p
o
s
e
o
f
th
is
FS
is
to
s
elec
t
a
s
u
b
s
et
th
r
o
u
g
h
p
ass
in
g
v
a
r
iab
le
d
ata.
Als
o
,
th
at
ca
n
im
p
r
o
v
e
s
o
m
e
e
f
f
icien
cy
o
f
p
r
e
d
ictio
n
s
a
n
d
r
ed
u
ce
th
e
co
m
p
lex
ity
o
f
t
h
e
d
ec
is
io
n
s
ac
q
u
ir
ed
.
I
n
c
o
n
n
ec
tio
n
with
th
e
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e,
t
h
e
ef
f
ec
ti
v
en
ess
o
f
s
tu
d
en
t
ac
h
iev
em
e
n
t
f
o
r
ec
ast
m
o
d
e
ls
ca
n
b
e
im
p
r
o
v
ed
.
FS
T
ec
h
n
iq
u
es c
an
b
e
g
r
o
u
p
i
n
to
th
r
ee
ass
o
ciatio
n
s
,
n
am
el
y
:
em
b
ed
d
e
d
,
f
ilter
s
,
an
d
wr
ap
p
er
m
o
d
els
[
1
1
]
.
Pre
v
io
u
s
ly
,
m
u
ch
w
o
r
k
was
ar
r
an
g
e
d
to
d
iv
in
e
s
tu
d
e
n
t
ac
h
i
ev
em
en
t
u
s
in
g
s
ep
ar
ate
FS
tech
n
iq
u
es.
Me
an
wh
ile,
th
e
latest
r
esear
c
h
,
th
e
r
esear
ch
er
s
u
s
ed
d
if
f
er
en
t
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
an
d
class
if
icatio
n
co
m
b
in
atio
n
s
to
cr
ea
te
m
o
r
e
e
f
f
ec
tiv
e
f
o
r
ec
ast
m
o
d
els
[
1
2
]
.
T
h
e
an
aly
s
is
is
n
ee
d
ed
to
r
ec
o
g
n
ize
p
er
f
o
r
m
an
ce
r
ev
iews
in
ter
m
s
o
f
p
r
ed
ictiv
e
ef
f
icien
cy
in
co
n
ju
n
ctio
n
with
o
th
er
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
s
am
o
n
g
d
if
f
er
e
n
t
class
if
icatio
n
s
[
1
3
]
.
T
h
is
p
ap
er
is
a
s
tep
to
war
d
s
r
ec
o
g
n
i
zin
g
th
is
f
o
r
ec
ast
ef
f
icien
cy
o
f
v
a
r
io
u
s
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
s
av
ailab
le
in
t
h
e
m
e
an
in
g
o
f
th
e
class
if
icatio
n
ad
o
p
ted
in
ed
u
ca
tio
n
al
d
ata.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
p
u
r
p
o
s
e
o
b
jectiv
e
o
f
th
is
an
aly
s
is
i
s
to
as
s
es
s
th
e
ac
h
iev
em
en
t
o
f
o
th
er
f
ea
tu
r
e
s
elec
t
io
n
alg
o
r
ith
m
s
o
n
v
a
r
io
u
s
class
if
icatio
n
alg
o
r
ith
m
s
u
s
in
g
e
d
u
ca
tio
n
al
d
atasets
.
T
h
e
ass
o
ciatio
n
b
etwe
en
v
ar
io
u
s
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
s
g
i
v
es
ed
u
ca
tio
n
al
d
ata
m
in
er
s
a
d
ee
p
in
s
ig
h
t
in
to
th
e
co
m
p
leti
o
n
o
f
s
ev
er
al
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
s
to
war
d
ed
u
ca
tio
n
al
d
ata.
T
h
er
ef
o
r
e,
th
e
o
b
jectiv
es
r
eg
a
r
d
in
g
th
is
a
n
aly
s
is
ca
n
b
e
ac
h
iev
ed
,
th
e
ed
u
ca
tio
n
al
d
ataset
is
o
b
ta
in
ed
f
r
o
m
a
c
r
ed
ib
le
s
o
u
r
ce
;
f
u
r
th
er
m
o
r
e,
a
n
o
th
er
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
is
ap
p
lied
to
th
e
d
ataset,
wh
ich
is
n
o
t
u
s
ed
in
th
e
d
ataset.
Sev
e
r
al
class
if
icatio
n
alg
o
r
ith
m
s
ar
e
im
p
lem
en
ted
u
tili
zin
g
th
e
ch
o
s
en
f
ea
tu
r
e
s
el
ec
tio
n
alg
o
r
ith
m
,
th
en
d
ec
id
e
d
to
c
h
ec
k
th
e
m
o
s
t
r
eliab
le
p
er
f
o
r
m
an
ce
am
o
n
g
s
t
all
co
m
b
in
atio
n
s
im
p
lem
e
n
ted
to
t
h
e
e
d
u
ca
tio
n
al
d
ataset.
T
h
e
f
o
r
em
o
s
t
ac
tio
n
s
o
f
th
is
r
e
s
ea
r
ch
will
th
en
b
e
ex
p
lain
ed
b
elo
w
.
2
.
1
.
Descript
io
n o
f
t
he
da
t
a
s
et
T
h
e
d
ataset
u
s
ed
in
th
is
s
tu
d
y
co
n
s
is
ted
o
f
4
3
9
s
tu
d
en
ts
a
n
d
n
in
e
attr
ib
u
tes
in
o
n
lin
e
a
n
d
d
is
tan
ce
(
ODL
)
Un
iv
er
s
ity
.
I
n
th
is
p
a
p
er
,
th
e
p
r
im
a
r
y
p
u
r
p
o
s
e
o
f
u
tili
zin
g
th
e
d
ataset
is
to
d
is
tin
g
u
is
h
th
e
m
o
s
t su
itab
le
co
m
b
in
atio
n
r
eg
ar
d
in
g
th
e
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
a
n
d
c
lass
if
icatio
n
to
r
ec
o
g
n
ize
ea
ch
m
ain
s
p
ec
ial
p
ar
ts
co
n
ce
r
n
in
g
ed
u
ca
tio
n
al
ac
h
iev
em
en
t.
I
n
th
is
p
ap
er
,
th
e
p
r
im
a
r
y
p
u
r
p
o
s
e
o
f
u
tili
zin
g
th
e
d
ata
s
et
is
to
d
is
tin
g
u
is
h
th
e
m
o
s
t
s
u
itab
le
co
m
b
i
n
atio
n
r
eg
ar
d
i
n
g
th
e
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
an
d
class
if
icatio
n
to
r
ec
o
g
n
ize
ea
ch
m
ain
s
p
ec
ial
p
ar
ts
co
n
ce
r
n
in
g
ed
u
ca
tio
n
al
ac
h
ie
v
em
en
t.
2
.
2
.
E
x
perim
ent
a
l set
up
W
aik
ato
en
v
ir
o
n
m
en
t
f
o
r
k
n
o
wled
g
e
an
aly
s
is
(
W
E
KA
)
u
tili
ze
d
ess
en
tially
a
to
o
l
f
o
r
d
at
a
m
in
in
g
tech
n
iq
u
es.
W
E
KA
o
wn
s
m
a
n
y
s
o
u
r
ce
s
o
f
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
.
W
ek
a
is
an
o
p
en
-
s
o
u
r
ce
s
o
f
twar
e
d
ev
elo
p
e
d
with
t
h
e
J
AVA
p
r
o
g
r
am
m
in
g
lan
g
u
a
g
e
,
w
h
ich
p
r
o
v
id
es
f
ac
ilit
ies
d
u
r
i
n
g
i
m
p
r
o
v
i
n
g
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es f
o
r
d
ata
m
in
in
g
wo
r
k
,
p
r
o
d
u
ce
d
b
y
th
e
U
n
iv
er
s
ity
o
f
W
aik
ato
in
New
Z
ea
lan
d
[
1
4
]
.
2
.
3
.
F
e
a
t
ure
s
elec
t
io
n a
lg
o
ri
t
hm
a
nd
cla
s
s
if
ica
t
io
n
T
h
is
p
ap
er
u
s
in
g
s
ix
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
s
h
av
e
b
ee
n
test
ed
b
ef
o
r
e,
t
h
er
e
ar
e
C
f
s
s
u
b
s
et
ev
al
[
1
5
]
,
C
h
i
s
q
u
ar
e
d
attr
ib
u
te
ev
al
[
1
6
]
,
f
ilter
e
d
attr
ib
u
te
ev
al
[
1
7
]
,
g
ain
r
atio
attr
ib
u
te
ev
al
[
1
8
]
,
p
r
in
ci
p
al
co
m
p
o
n
en
ts
[
1
9
]
,
a
n
d
r
elief
at
tr
ib
u
te
ev
al
[
2
0
]
.
T
h
is
p
ap
er
al
s
o
u
s
es
1
5
d
if
f
er
en
t
class
if
icat
io
n
alg
o
r
ith
m
s
th
at
h
av
e
b
ee
n
test
ed
th
r
o
u
g
h
e
d
u
c
atio
n
al
d
atasets
,
s
p
ec
if
ically
B
ay
es
n
et,
Naïv
e
B
ay
es,
Naiv
e
B
ay
es
u
p
d
ate
ab
le
,
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
,
s
im
p
le
lo
g
is
tic
,
SMO,
d
ec
is
io
n
t
r
ee
,
J
R
ip
,
On
eR,
PA
R
T
,
d
ec
is
io
n
s
t
u
m
p
,
J
4
8
,
r
an
d
o
m
f
o
r
est,
r
an
d
o
m
tr
ee
,
an
d
R
E
P
t
r
ee
[
2
1
]
-
[
2
3
]
.
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
h
is
an
aly
s
is
co
n
ce
n
tr
ates
a
b
o
u
t
th
e
co
m
p
letio
n
r
eg
a
r
d
i
n
g
s
ev
er
al
f
ea
t
u
r
e
s
elec
tio
n
alg
o
r
ith
m
s
f
o
r
war
d
with
th
e
class
if
icatio
n
m
eth
o
d
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
th
is
alg
o
r
ith
m
is
in
clu
d
e
d
with
in
th
e
v
alu
e
s
o
f
F
-
m
ea
s
u
r
e,
r
ec
all,
p
r
ec
is
io
n
,
a
n
d
f
o
r
ec
ast
ef
f
icien
c
y
(
ex
am
p
l
es
with
th
e
co
r
r
ec
t
class
if
icati
o
n
)
[
2
4
]
,
[
2
5
]
.
T
h
e
co
m
p
letio
n
o
f
th
e
s
ix
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
im
p
lem
en
ted
to
th
e
1
5
class
if
icatio
n
s
is
d
escr
ib
e
d
in
T
ab
le
s
1
-
6
.
All
th
e
tab
les
ar
e
m
ad
e
d
ef
in
itely
f
o
r
th
e
s
ix
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es,
a
n
d
th
en
e
v
er
y
ta
b
le
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
C
o
mp
a
r
is
o
n
o
f th
e
fea
tu
r
e
s
elec
tio
n
a
lg
o
r
ith
m
in
e
d
u
ca
tio
n
a
l d
a
ta
min
i
n
g
(
A
g
u
n
g
Tr
ia
yu
d
i
)
1867
co
m
p
r
is
es
f
o
u
r
c
o
lu
m
n
s
.
T
h
e
co
lu
m
n
s
p
r
esen
t
th
e
n
a
m
e
o
f
t
h
e
class
if
icatio
n
alg
o
r
ith
m
,
th
e
F
-
m
ea
s
u
r
e
v
alu
e,
th
e
r
ec
all
v
alu
e,
a
n
d
th
e
p
r
ec
is
io
n
v
alu
e
u
tili
zin
g
th
e
f
ea
t
u
r
e
s
elec
tio
n
alg
o
r
ith
m
.
3
.
1
.
Cf
s
s
ub
s
et
ev
a
l
c
la
s
s
C
f
s
s
u
b
s
et
ev
al
class
p
r
ed
icts
th
e
r
elev
an
ce
o
f
a
s
u
b
s
et
o
f
p
o
in
ts
b
y
co
n
s
id
er
in
g
th
e
u
n
iq
u
e
o
m
in
o
u
s
s
tr
en
g
th
o
f
ea
ch
p
o
in
t
o
n
war
d
b
y
th
e
le
v
el
o
f
r
ed
u
n
d
an
c
y
wit
h
in
th
em
.
T
ab
le
1
d
is
p
lay
s
th
e
v
alu
es
o
f
F
-
m
ea
s
u
r
e
,
r
ec
all,
an
d
p
r
ec
is
io
n
f
o
r
ev
e
r
y
o
n
e
o
f
th
e
1
5
class
if
icatio
n
s
u
s
ed
in
C
f
s
s
u
b
s
et
ev
al
.
Fig
u
r
e
1
is
a
d
iag
r
am
m
ati
c
illu
s
tr
atio
n
o
f
T
ab
le
1
.
T
h
e
r
esu
lts
f
r
o
m
T
ab
le
1
s
h
o
w
th
at
th
e
p
r
ec
is
io
n
v
al
u
e
is
alw
ay
s
h
ig
h
e
r
th
a
n
th
e
re
ca
ll
an
d
F
-
m
ea
s
u
r
e
v
alu
es.
B
esid
es,
th
er
e
wer
e
n
o
s
ig
n
if
ican
t
ch
an
g
es
in
th
e
r
esu
lts
o
f
all
clas
s
if
icatio
n
s
u
s
ed
to
g
eth
er
with
C
f
s
s
u
b
s
et
ev
al
,
b
u
t
th
e
r
an
d
o
m
tr
e
e
class
if
icatio
n
s
h
o
wed
th
e
lo
west
p
er
f
o
r
m
an
ce
in
th
e
F
-
m
e
asu
r
e,
p
r
ec
is
io
n
,
an
d
r
ec
all
r
u
les
u
tili
s
in
g
th
e
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
.
Fig
u
r
e
2
s
h
o
ws
th
e
r
esu
lts
o
f
ea
ch
m
eth
o
d
in
g
r
ap
h
ical
f
o
r
m
,
b
ased
o
n
th
r
ee
s
tan
d
a
r
d
s
F
-
m
ea
s
u
r
e,
p
r
ec
is
io
n
,
an
d
r
ec
all
r
u
les u
s
in
g
th
e
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
ev
alu
ati
o
n
o
f
C
f
s
s
u
b
s
et
ev
al
class
C
l
a
s
si
f
i
c
a
t
i
o
n
A
l
g
o
r
i
t
h
m
F
-
M
e
a
s
u
r
e
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
B
a
y
e
s
N
e
t
0
.
7
0
6
0
.
7
0
8
0
.
7
8
9
N
a
i
v
e
B
a
y
e
s
0
.
7
2
8
0
.
7
3
1
0
.
8
2
2
N
a
i
v
e
B
a
y
e
s
U
p
d
a
t
e
a
b
l
e
0
.
7
2
8
0
.
7
3
1
0
.
8
2
2
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
0
.
7
3
4
0
.
7
3
1
0
.
7
4
2
S
i
mp
l
e
Lo
g
i
st
i
c
0
.
7
2
1
0
.
7
2
4
0
.
8
1
9
S
M
O
0
.
7
2
3
0
.
7
2
7
0
.
8
2
7
D
e
c
i
s
i
o
n
Tr
e
e
0
.
7
1
9
0
.
7
2
2
0
.
8
1
4
JR
i
p
0
.
7
2
0
.
7
2
4
0
.
8
2
2
O
n
e
R
0
.
7
2
3
0
.
7
2
7
0
.
8
2
7
P
A
R
T
0
.
7
2
7
0
.
7
2
4
0
.
7
4
4
D
e
c
i
s
i
o
n
S
t
u
mp
0
.
7
2
3
0
.
7
2
7
0
.
8
2
7
J4
8
0
.
7
6
3
0
.
7
6
1
0
.
7
8
5
R
a
n
d
o
m
F
o
r
e
s
t
0
.
7
3
2
0
.
7
3
1
0
.
7
3
2
R
a
n
d
o
m
Tr
e
e
0
.
6
9
7
0
.
6
9
7
0
.
6
9
7
R
EP
t
r
e
e
0
.
7
1
1
0
.
7
0
8
0
.
7
4
Fig
u
r
e
1
.
F
-
m
ea
s
u
r
e
,
r
ec
all,
an
d
p
r
ec
is
io
n
f
o
r
C
f
s
s
u
b
s
et
ev
al
class
3
.
2
.
Chi sq
ua
re
d a
t
t
ribute
ev
a
l
cla
s
s
C
h
i
s
q
u
ar
ed
attr
ib
u
te
ev
al
clas
s
d
eter
m
in
es
th
e
attr
ib
u
te
b
y
m
ea
s
u
r
in
g
th
e
ch
i
-
s
q
u
ar
e
d
s
tatis
tical
v
alu
e
ass
o
ciate
d
with
an
ex
is
tin
g
cl
ass
.
T
ab
le
2
p
r
esen
ts
th
e
r
esu
lts
o
f
F
-
m
ea
s
u
r
e,
r
ec
all,
an
d
p
r
ec
is
io
n
to
war
d
1
5
class
if
icatio
n
s
ac
co
m
p
an
y
in
g
C
h
i
s
q
u
ar
ed
attr
ib
u
te
ev
al
.
Fig
u
r
e
2
is
a
d
iag
r
am
m
atic
illu
s
tr
a
tio
n
o
f
T
ab
le
2
.
T
h
e
r
esu
lts
ar
e
p
r
esen
te
d
in
T
ab
le
2
,
an
d
Fig
u
r
e
2
illu
s
tr
ates
th
e
ML
P
class
if
icatio
n
th
at
h
as
th
e
lo
west
p
er
f
o
r
m
an
c
e
in
ed
u
ca
tio
n
al
d
ata
s
ets u
s
in
g
C
h
i
s
q
u
ar
ed
at
tr
ib
u
te
e
v
al
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
ev
alu
ati
o
n
o
f
C
f
s
s
u
b
s
et
ev
al
class
C
l
a
s
si
f
i
c
a
t
i
o
n
A
l
g
o
r
i
t
h
m
F
-
M
e
a
s
u
r
e
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
B
a
y
e
s
N
e
t
0
.
7
5
4
0
.
7
5
2
0
.
7
7
N
a
i
v
e
B
a
y
e
s
0
.
7
2
9
0
.
7
2
7
0
.
7
6
4
N
a
i
v
e
B
a
y
e
s
U
p
d
a
t
e
a
b
l
e
0
.
7
2
9
0
.
7
2
7
0
.
7
6
4
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
0
.
6
9
7
0
.
6
9
5
0
.
7
S
i
mp
l
e
Lo
g
i
st
i
c
0
.
7
1
2
0
.
7
1
1
0
.
7
6
S
M
O
0
.
7
0
9
0
.
7
1
1
0
.
7
8
7
D
e
c
i
s
i
o
n
Tr
e
e
0
.
7
5
9
0
.
7
5
6
0
.
7
7
7
JR
i
p
0
.
7
7
7
0
.
7
7
4
0
.
7
9
7
O
n
e
R
0
.
7
2
3
0
.
7
2
7
0
.
8
2
7
P
A
R
T
0
.
7
2
0
.
7
2
0
.
7
2
D
e
c
i
s
i
o
n
S
t
u
mp
0
.
7
2
3
0
.
7
2
7
0
.
8
2
7
J4
8
0
.
7
5
4
0
.
7
5
4
0
.
7
5
4
R
a
n
d
o
m
F
o
r
e
s
t
0
.
7
5
1
0
.
7
4
9
0
.
7
5
3
R
a
n
d
o
m
Tr
e
e
0
.
7
0
5
0
.
7
0
4
0
.
7
0
7
R
EP
t
r
e
e
0
.
7
4
9
0
.
7
4
7
0
.
7
5
4
Fig
u
r
e
2
.
F
-
m
ea
s
u
r
e
,
r
ec
all,
an
d
p
r
ec
is
io
n
o
f
C
h
i
s
q
u
ar
ed
attr
ib
u
te
e
v
al
class
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
6
,
Dec
em
b
e
r
2
0
2
1
:
18
65
-
18
71
1868
3
.
3
.
F
ilte
re
d
a
t
t
ribute
ev
a
l c
la
s
s
T
ab
le
3
an
d
Fig
u
r
e
3
p
r
esen
t
t
h
e
r
esu
lts
o
f
th
e
class
if
icatio
n
,
wh
ich
is
u
s
ed
in
ed
u
ca
tio
n
al
d
ata
u
tili
s
in
g
th
e
f
ilter
ed
attr
ib
u
te
ev
al
class
.
T
h
e
r
esu
lts
p
r
o
v
e
th
at
ML
P
g
iv
es
r
elativ
ely
d
ee
p
v
al
u
es
o
f
F
-
m
ea
s
u
r
e,
r
ec
all,
an
d
p
r
ec
is
io
n
as
in
th
e
p
r
ev
io
u
s
m
e
th
o
d
.
W
h
ile
J
R
ip
'
s
o
f
f
er
in
g
is
r
elativ
ely
m
o
r
e
r
eliab
le
th
an
o
th
er
class
if
icatio
n
s
u
tili
s
in
g
f
ilter
ed
attr
ib
u
te
ev
al
class
.
T
ab
le
3
.
Per
f
o
r
m
an
ce
ev
alu
ati
o
n
o
f
f
ilter
ed
attr
ib
u
te
ev
al
class
C
l
a
s
si
f
i
c
a
t
i
o
n
A
l
g
o
r
i
t
h
m
F
-
M
e
a
s
u
r
e
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
B
a
y
e
s
N
e
t
0
.
7
5
4
0
.
7
5
2
0
.
7
7
N
a
i
v
e
B
a
y
e
s
0
.
7
2
9
0
.
7
2
7
0
.
7
6
4
N
a
i
v
e
B
a
y
e
s
U
p
d
a
t
e
a
b
l
e
0
.
7
2
9
0
.
7
2
7
0
.
7
6
4
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
0
.
6
9
7
0
.
6
9
5
0
.
7
S
i
mp
l
e
Lo
g
i
st
i
c
0
.
7
1
2
0
.
7
1
1
0
.
7
6
S
M
O
0
.
7
0
9
0
.
7
1
1
0
.
7
8
7
D
e
c
i
s
i
o
n
Tr
e
e
0
.
7
5
9
0
.
7
5
6
0
.
7
7
7
JR
i
p
0
.
7
7
7
0
.
7
7
4
0
.
7
9
7
O
n
e
R
0
.
7
2
3
0
.
7
2
7
0
.
8
2
7
P
A
R
T
0
.
7
2
0
.
7
2
0
.
7
2
D
e
c
i
s
i
o
n
S
t
u
mp
0
.
7
2
3
0
.
7
2
7
0
.
8
2
7
J4
8
0
.
7
5
4
0
.
7
5
4
0
.
7
5
4
R
a
n
d
o
m
F
o
r
e
s
t
0
.
7
5
1
0
.
7
4
9
0
.
7
5
3
R
a
n
d
o
m
Tr
e
e
0
.
7
0
7
0
.
7
0
4
0
.
7
0
5
R
EP
t
r
e
e
0
.
7
5
4
0
.
7
4
7
0
.
7
4
9
Fig
u
r
e
3
.
F
-
m
ea
s
u
r
e
,
r
ec
all,
an
d
p
r
ec
is
io
n
o
f
f
ilter
ed
attr
ib
u
te
ev
al
class
3
.
4
.
G
a
in ra
t
io
a
t
t
ribute
ev
a
l c
la
s
s
Gain
r
atio
attr
ib
u
te
ev
al
class
is
a
n
o
n
-
s
y
m
m
etr
ical
d
e
v
ice
th
at
was
ad
d
ed
to
r
ec
o
m
p
e
n
s
e
f
o
r
th
e
p
r
ef
er
en
ce
(
d
e
v
iatio
n
)
o
f
k
n
o
wled
g
e
ac
q
u
is
itio
n
[
1
7
]
.
T
ab
l
e
4
an
d
Fig
u
r
e
4
s
h
o
w
th
at
u
s
in
g
a
class
if
icatio
n
g
ain
r
atio
attr
ib
u
te
ev
al
class
p
er
f
o
r
m
a
n
ce
,
wh
ich
is
q
u
ite
lo
w
co
m
p
ar
ed
to
o
th
e
r
class
if
icatio
n
s
.
T
ab
le
4
.
Per
f
o
r
m
an
ce
ev
alu
ati
o
n
o
f
g
ain
r
atio
attr
ib
u
te
ev
al
class
C
l
a
s
si
f
i
c
a
t
i
o
n
A
l
g
o
r
i
t
h
m
F
-
M
e
a
s
u
r
e
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
B
a
y
e
s
N
e
t
0
.
6
4
4
0
.
7
0
8
0
.
6
8
4
N
a
i
v
e
B
a
y
e
s
0
.
6
2
0
.
6
8
3
0
.
6
3
1
N
a
i
v
e
B
a
y
e
s
U
p
d
a
t
e
a
b
l
e
0
.
6
2
0
.
6
8
3
0
.
6
3
1
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
0
.
6
3
2
0
.
6
6
3
0
.
6
2
4
S
i
mp
l
e
Lo
g
i
st
i
c
0
.
6
3
0
.
6
9
5
0
.
6
5
4
S
M
O
0
.
5
7
8
0
.
6
7
4
0
.
5
7
4
D
e
c
i
s
i
o
n
Tr
e
e
0
.
6
4
6
0
.
7
0
4
0
.
6
7
3
JR
i
p
0
.
6
0
7
0
.
6
6
7
0
.
6
0
4
O
n
e
R
0
.
5
7
0
.
6
3
8
0
.
5
4
7
P
A
R
T
0
.
6
1
4
0
.
6
4
7
0
.
6
0
3
D
e
c
i
s
i
o
n
S
t
u
mp
0
.
5
7
7
0
.
6
7
9
0
.
5
8
J4
8
0
.
6
4
8
0
.
6
7
0
.
6
4
1
R
a
n
d
o
m
F
o
r
e
s
t
0
.
6
0
5
0
.
6
3
6
0
.
5
9
3
R
a
n
d
o
m
Tr
e
e
0
.
6
0
6
0
.
6
0
4
0
.
6
0
8
R
EP
t
r
e
e
0
.
6
2
1
0
.
6
6
7
0
.
6
1
7
Fig
u
r
e
4
.
F
-
m
ea
s
u
r
e
,
r
ec
all,
an
d
p
r
ec
is
io
n
o
f
g
ain
r
atio
attr
ib
u
te
ev
al
class
3
.
5
.
P
rincipa
l c
o
m
po
nent
cla
s
s
T
ab
le
5
p
r
esen
t
th
e
ap
p
ea
r
an
c
e
o
f
th
e
p
r
in
cip
al
c
o
m
p
o
n
en
ts
u
tili
s
in
g
1
5
class
if
icatio
n
s
,
wh
ich
ar
e
1
5
ex
is
t
in
th
e
W
E
KA
o
p
en
-
s
o
u
r
ce
d
ata
m
in
in
g
ap
p
licatio
n
.
Fig
u
r
e
5
is
a
g
r
ap
h
illu
s
tr
atio
n
o
f
T
ab
le
5
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
B
ay
es
n
et
class
if
icatio
n
h
as
r
elativ
ely
b
etter
p
er
f
o
r
m
an
ce
,
wh
ile
r
an
d
o
m
tr
ee
s
h
o
ws
lo
w
p
er
f
o
r
m
a
n
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
C
o
mp
a
r
is
o
n
o
f th
e
fea
tu
r
e
s
elec
tio
n
a
lg
o
r
ith
m
in
e
d
u
ca
tio
n
a
l d
a
ta
min
i
n
g
(
A
g
u
n
g
Tr
ia
yu
d
i
)
1869
3
.
6
.
Relief
a
t
t
ribute
ev
a
l c
l
a
s
s
T
h
is
ev
alu
ates
th
e
im
p
o
r
ta
n
ce
o
f
attr
ib
u
tes
with
ex
am
p
les
th
a
t
ar
e
tak
e
n
r
e
p
ea
ted
ly
.
T
h
e
o
u
t
co
m
es
ar
e
s
h
o
wn
in
T
ab
le
6
p
r
esen
t
th
e
r
esu
lts
o
f
th
e
r
elief
atr
ib
u
te
e
v
al
ev
alu
atio
n
o
n
th
e
class
if
icatio
n
s
h
o
wn
in
th
e
cla
s
s
if
icatio
n
o
n
th
e
class
if
icatio
n
o
f
r
elief
atr
ib
u
te
e
v
al
o
n
th
e
class
if
icatio
n
s
h
o
wn
in
T
ab
le
6
d
if
f
er
en
tly
.
Fig
u
r
e
6
is
a
g
r
ap
h
r
e
p
r
esen
ta
tio
n
o
f
T
ab
le
6
.
T
h
e
r
esu
lts
o
f
th
e
r
elief
attr
ib
u
te
e
v
al
ev
al
u
atio
n
h
av
e
r
esu
lts
s
im
ilar
to
th
e
g
ain
r
atio
attr
ib
u
t
e
ev
al
ev
alu
atio
n
.
T
h
e
r
esu
lts
d
ep
ict
th
at
th
e
B
ay
es
n
et
clas
s
if
icatio
n
h
as b
etter
p
er
f
o
r
m
an
ce
th
a
n
th
e
o
th
er
cl
ass
if
icatio
n
s
,
b
u
t
On
eR
s
h
o
ws
th
e
lo
w
p
e
r
f
o
r
m
an
ce
w
h
en
u
s
in
g
r
elief
attr
ib
u
te
ev
al
o
n
th
e
s
tu
d
en
t d
ataset.
T
ab
le
5
.
Per
f
o
r
m
an
ce
ev
alu
ati
o
n
o
f
p
r
in
ci
p
al
co
m
p
o
n
en
ts
class
C
l
a
s
si
f
i
c
a
t
i
o
n
A
l
g
o
r
i
t
h
m
F
-
M
e
a
s
u
r
e
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
B
a
y
e
s
N
e
t
0
.
6
4
8
0
.
7
1
1
0
.
6
8
9
N
a
i
v
e
B
a
y
e
s
0
.
6
3
0
.
6
8
8
0
.
6
4
2
N
a
i
v
e
B
a
y
e
s
U
p
d
a
t
e
a
b
l
e
0
.
6
3
0
.
6
8
8
0
.
6
4
2
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
0
.
5
9
8
0
.
6
2
2
0
.
5
8
6
S
i
mp
l
e
Lo
g
i
st
i
c
0
.
6
3
2
0
.
6
9
7
0
.
6
5
8
S
M
O
0
.
5
7
0
.
6
7
9
0
.
5
6
D
e
c
i
s
i
o
n
Tr
e
e
0
.
6
1
8
0
.
6
9
9
0
.
6
6
8
JR
i
p
0
.
5
9
4
0
.
6
7
7
0
.
6
0
2
O
n
e
R
0
.
5
7
0
.
6
3
8
0
.
5
4
7
P
A
R
T
0
.
6
2
4
0
.
6
3
3
0
.
6
1
8
D
e
c
i
s
i
o
n
S
t
u
mp
0
.
5
7
7
0
.
6
7
9
0
.
5
8
J4
8
0
.
6
1
3
0
.
6
3
8
0
.
6
0
2
R
a
n
d
o
m
F
o
r
e
s
t
0
.
6
1
2
0
.
6
4
0
.
6
R
a
n
d
o
m
Tr
e
e
0
.
5
6
4
0
.
5
5
8
0
.
5
7
R
EP
t
r
e
e
0
.
6
1
4
0
.
6
7
2
0
.
6
1
5
T
ab
le
6
.
Per
f
o
r
m
an
ce
ev
alu
ati
o
n
o
f
r
elief
attr
ib
u
te
ev
al
class
C
l
a
s
si
f
i
c
a
t
i
o
n
A
l
g
o
r
i
t
h
m
F
-
M
e
a
s
u
r
e
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
B
a
y
e
s
N
e
t
0
.
6
4
8
0
.
7
1
1
0
.
6
8
9
N
a
i
v
e
B
a
y
e
s
0
.
6
4
0
.
6
9
0
.
6
4
9
N
a
i
v
e
B
a
y
e
s
U
p
d
a
t
e
a
b
l
e
0
.
6
4
0
.
6
9
0
.
6
4
9
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
0
.
6
4
5
0
.
6
7
7
0
.
6
4
1
S
i
mp
l
e
Lo
g
i
st
i
c
0
.
6
2
9
0
.
6
9
7
0
.
6
5
8
S
M
O
0
.
5
7
8
0
.
6
7
4
0
.
5
7
4
D
e
c
i
s
i
o
n
Tr
e
e
0
.
6
1
8
0
.
6
9
9
0
.
6
6
8
JR
i
p
0
.
5
9
2
0
.
6
6
7
0
.
5
8
8
O
n
e
R
0
.
5
7
0
.
6
3
8
0
.
5
4
7
P
A
R
T
0
.
6
2
6
0
.
6
4
2
0
.
6
1
7
D
e
c
i
s
i
o
n
S
t
u
mp
0
.
5
7
7
0
.
6
7
9
0
.
5
8
J4
8
0
.
6
1
8
0
.
6
4
2
0
.
6
0
7
R
a
n
d
o
m
F
o
r
e
s
t
0
.
6
2
8
0
.
6
4
7
0
.
6
1
9
R
a
n
d
o
m
Tr
e
e
0
.
6
2
1
0
.
6
2
4
0
.
6
1
9
R
EP
t
r
e
e
0
.
6
3
7
0
.
6
7
4
0
.
6
3
4
Fig
u
r
e
5
.
F
-
m
ea
s
u
r
e
,
r
ec
all,
an
d
p
r
ec
is
io
n
o
f
p
r
in
cip
al
co
m
p
o
n
e
n
ts
class
Fig
u
r
e
6
.
F
-
m
ea
s
u
r
e
,
r
ec
all,
an
d
p
r
ec
is
io
n
o
f
r
elief
attr
ib
u
te
ev
al
class
T
ab
le
7
p
r
esen
ts
th
e
v
al
u
es
o
f
ev
er
y
f
ea
t
u
r
e
s
elec
tio
n
alg
o
r
ith
m
with
v
ar
io
u
s
class
if
icatio
n
s
.
Fin
ally
,
th
e
m
ea
n
an
d
th
e
v
ar
ia
n
ce
o
f
ev
er
y
f
ea
t
u
r
e
s
elec
tio
n
ar
e
u
s
ed
to
ch
ec
k
v
a
r
iatio
n
s
in
th
e
ap
p
ea
r
an
ce
o
f
th
e
f
ea
tu
r
e
s
elec
t
io
n
alg
o
r
ith
m
a
m
o
n
g
s
ep
ar
ate
class
if
icatio
n
m
eth
o
d
s
.
T
h
e
d
ec
is
io
n
tr
e
e
(
D
T
)
class
if
icatio
n
h
as
b
etter
p
er
f
o
r
m
an
ce
wh
en
u
s
ed
o
n
t
h
e
FS
alg
o
r
ith
m
,
an
d
t
h
e
r
an
d
o
m
tr
ee
(
R
T
)
class
if
icatio
n
h
as
th
e
lo
west
p
er
f
o
r
m
an
ce
am
o
n
g
o
th
er
clas
s
if
icatio
n
s
.
T
h
e
r
esu
lts
with
in
Fig
u
r
e
7
an
d
Fig
u
r
e
8
p
r
esen
t
th
e
m
ea
n
an
d
th
e
v
ar
ian
ce
i
n
th
e
ch
o
s
en
f
ea
tu
r
e
s
elec
tio
n
(
FS
)
alg
o
r
ith
m
.
C
f
s
s
u
b
s
et
ev
al
(
C
SE)
,
C
h
i
s
q
u
ar
ed
attr
ib
u
te
ev
al
(
C
SAE)
,
f
ilter
ed
attr
ib
u
te
ev
a
l
(
FAE)
,
g
ain
r
atio
attr
ib
u
te
ev
al
(
GR
AE
)
,
p
r
in
cip
al
co
m
p
o
n
e
n
ts
(
P
C
)
,
an
d
r
elief
attr
ib
u
te
ev
al
(
R
AE
)
.
B
ay
es
n
et
(
B
N)
,
Naïv
e
B
ay
es
(
NB
)
,
Naiv
e
B
ay
es
upda
te
ab
le
(
NB
U)
,
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
MP)
,
s
im
p
le
lo
g
is
tic
(
SL)
,
SMO,
d
ec
is
io
n
tr
ee
(
DT
)
,
J
R
ip
,
On
eR,
PAR
T
,
d
ec
is
io
n
s
tu
m
p
(
DS)
,
J
4
8
,
r
a
n
d
o
m
f
o
r
est
(
R
F)
,
r
an
d
o
m
t
r
ee
(
R
T
)
,
an
d
R
E
P
tr
ee
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
19
,
No
.
6
,
Dec
em
b
e
r
2
0
2
1
:
18
65
-
18
71
1870
T
ab
le
7
.
E
v
alu
atio
n
o
f
p
e
r
f
o
r
m
an
ce
alg
o
r
ith
m
s
f
ea
tu
r
e
s
ele
ctio
n
in
co
n
tex
t w
ith
co
r
r
ec
tly
class
if
ied
in
s
tan
ce
s
FS
C
o
r
r
e
c
t
l
y
C
l
a
ss
i
f
i
e
d
I
n
st
a
n
c
e
s (
%)
M
e
a
n
V
a
r
i
a
n
c
e
BN
NB
N
B
U
MP
SL
S
M
O
DT
JR
i
p
C
S
E
7
0
.
8
7
3
.
1
7
3
.
1
7
3
.
1
7
2
.
4
3
7
2
.
6
6
7
2
.
2
7
2
.
4
3
7
2
.
4
9
0
.
0
0
0
1
8
6
C
S
A
E
7
4
.
4
7
3
.
3
7
3
.
3
7
1
.
2
7
1
.
0
7
7
1
.
0
7
7
5
.
6
2
7
6
.
3
7
3
.
8
0
0
.
0
0
0
3
9
4
F
A
E
7
5
.
1
7
2
.
6
7
2
.
6
6
9
.
4
7
1
.
0
7
7
1
.
0
7
7
5
.
6
2
7
7
.
4
4
7
3
.
1
9
0
.
0
0
0
4
7
6
GAE
7
0
.
8
6
8
.
3
6
8
.
3
6
6
.
2
6
9
.
4
7
6
7
.
4
2
7
0
.
3
8
6
6
.
7
4
6
6
.
7
8
0
.
0
0
0
7
2
3
PC
7
1
.
1
6
8
.
7
6
8
.
7
6
2
.
1
6
9
.
7
6
7
.
8
8
6
9
.
9
3
6
7
.
6
5
6
6
.
1
2
0
.
0
0
1
4
7
4
R
A
E
7
1
.
1
6
9
.
0
6
9
.
0
6
7
.
6
6
9
.
7
6
7
.
4
2
6
9
.
9
3
6
6
.
7
4
6
7
.
0
1
0
.
0
0
0
6
2
9
O
n
e
R
P
A
R
T
DS
J4
8
RF
RT
R
EP
t
r
e
e
C
S
E
7
2
.
6
6
7
2
.
4
3
7
2
.
6
6
7
6
.
0
8
7
3
.
1
2
6
9
.
7
7
0
.
8
4
7
2
.
4
9
0
.
0
0
0
1
8
6
C
S
A
E
7
2
.
6
6
7
4
.
9
4
7
2
.
6
6
7
7
.
4
4
7
5
.
8
5
7
1
.
7
5
7
5
.
1
7
7
3
.
8
0
0
.
0
0
0
3
9
4
F
A
E
7
2
.
6
6
7
1
.
9
8
7
2
.
6
6
7
5
.
3
9
7
4
.
9
4
7
0
.
3
8
7
4
.
7
1
7
3
.
1
9
0
.
0
0
0
4
7
6
GAE
6
3
.
7
8
6
4
.
6
9
6
7
.
8
8
6
6
.
9
7
6
3
.
5
5
6
0
.
3
6
6
6
.
7
4
6
6
.
7
8
0
.
0
0
0
7
2
3
PC
6
3
.
7
8
6
3
.
3
2
6
7
.
8
8
6
3
.
7
8
64
5
5
.
8
6
7
.
1
9
6
6
.
1
2
0
.
0
0
1
4
7
4
R
A
E
6
3
.
7
8
6
4
.
2
3
6
7
.
8
8
6
4
.
2
3
6
4
.
6
9
6
2
.
4
1
6
7
.
4
2
6
7
.
0
1
0
.
0
0
0
6
2
9
Fig
u
r
e
7
.
Av
e
r
ag
e
FS
alg
o
r
ith
m
Fig
u
r
e
8
.
Var
ian
ce
FS
alg
o
r
ith
m
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
d
if
f
e
r
en
t
alg
o
r
ith
m
s
h
av
e
b
ee
n
ass
ess
ed
an
d
an
aly
ze
d
th
e
FS
alg
o
r
ith
m
.
T
h
e
r
esu
lts
in
th
e
ed
u
ca
tio
n
al
d
ataset
s
h
o
w
th
at
th
er
e
is
n
o
im
p
o
r
tan
t
ch
an
g
e
in
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
FS
alg
o
r
ith
m
in
th
e
W
E
KA
ap
p
licatio
n
.
B
u
t
am
o
n
g
all
av
ailab
le
FS
m
eth
o
d
s
,
th
e
p
r
in
cip
al
co
m
p
o
n
en
ts
m
eth
o
d
s
h
o
ws
b
etter
r
esu
lts
wh
en
u
s
in
g
FS
with
B
ay
es
n
et
(
B
N)
class
if
icatio
n
.
T
h
is
p
ap
er
also
s
h
o
ws
th
at
th
e
d
ec
is
io
n
t
r
ee
(
DT
)
class
if
icatio
n
p
er
f
o
r
m
s
b
etter
th
an
th
e
o
th
er
class
if
icatio
n
s
in
th
e
s
tu
d
en
t
d
ataset,
an
d
th
e
r
an
d
o
m
t
r
ee
(
R
T
)
class
if
icatio
n
is
th
e
lo
west
-
p
er
f
o
r
m
in
g
class
am
o
n
g
th
e
o
th
e
r
class
if
icatio
n
s
.
T
h
e
r
esu
lts
r
ep
r
esen
t th
at
th
er
e
is
a
n
ee
d
to
a
d
ju
s
t
co
m
p
lex
p
ar
a
m
eter
s
with
th
e
FS
m
eth
o
d
,
to
ac
h
iev
e
b
etter
p
e
r
f
o
r
m
an
ce
.
F
o
r
th
e
f
u
tu
r
e
FS
an
d
its
v
ar
io
u
s
m
ix
t
u
r
es,
an
d
ed
u
c
atio
n
al
d
atasets
o
f
v
ar
io
u
s
ar
e
as c
an
also
b
e
u
tili
ze
d
f
o
r
ev
al
u
atio
n
.
ACK
NO
WL
E
DG
M
E
N
T
T
h
is
r
esear
ch
is
th
e
r
e
s
u
lt
o
f
th
e
b
asic
r
esear
ch
s
c
h
em
e
o
f
th
e
I
n
d
o
n
esian
Dik
ti
g
r
an
t
B
/1
1
2
/E3
/R
A.
0
0
/2
0
2
1
.
RE
F
E
R
E
NC
E
S
[1
]
A.
Tri
a
y
u
d
i,
W.
O.
W
id
y
a
rto
,
a
n
d
V.
Ro
sa
li
n
a
,
"
CLG
Clu
ste
rin
g
fo
r
M
a
p
p
i
n
g
P
a
tt
e
rn
A
n
a
ly
sis
o
f
S
tu
d
e
n
t
Ac
a
d
e
m
ic
Ac
h
iev
e
m
e
n
t,
"
ICIC
Ex
p
re
ss
L
e
tt
e
rs
,
v
o
l.
1
4
,
n
o
.
1
2
,
p
p
.
1
2
2
5
-
1
2
3
4
,
2
0
2
0
,
d
o
i
:
1
0
.
2
4
5
0
7
/i
c
ice
l.
1
4
.
1
2
.
1
2
2
5
.
[2
]
E.
Os
m
a
n
b
e
g
o
v
ić,
M
.
S
u
l
ji
ć
,
a
n
d
H.
Ag
ić,
De
ter
min
in
g
Do
mi
n
a
n
t
Fa
c
to
r
F
o
r
S
tu
d
e
n
ts
Per
f
o
rm
a
n
c
e
Pre
d
ictio
n
By
Us
in
g
D
a
ta
M
i
n
i
n
g
Cla
ss
if
ic
a
ti
o
n
Al
g
o
rith
ms
,
Tran
z
icija,
v
o
l.
1
6
,
p
p
.
1
4
7
-
1
5
8
,
2
0
1
5
.
[O
n
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
s:/
/co
re
.
a
c
.
u
k
/d
o
wn
l
o
a
d
/p
d
f/
3
3
2
7
3
9
1
6
.
p
d
f
[3
]
A.
Tri
a
y
u
d
i
a
n
d
I
.
F
i
tri
,
“
A
n
e
w
a
g
g
l
o
m
e
ra
ti
v
e
h
iera
rc
h
ica
l
c
lu
ste
ri
n
g
t
o
m
o
d
e
l
st
u
d
e
n
t
a
c
ti
v
it
y
i
n
o
n
li
n
e
lea
rn
i
n
g
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l
,
v
o
l.
17
,
n
o
.
3
,
p
p
.
1
2
2
6
-
1
2
3
5
,
2
0
1
9
,
doi
:
1
0
.
1
2
9
2
8
/t
e
lk
o
m
n
i
k
a
.
v
1
7
i
3
.
9
4
2
5
.
[4
]
A.
Tri
a
y
u
d
i
,
S
u
m
iati,
S.
Dw
i
y
a
t
n
o
,
D.
Ka
ry
a
n
in
g
sih
,
a
n
d
S
u
sila
wa
ti
,
"
M
e
a
su
re
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
in
f
o
rm
a
ti
o
n
sy
ste
m
s with
th
e
n
a
ïv
e
b
a
y
e
s c
las
sifier m
e
th
o
d
,
"
IAE
S
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Art
if
icia
l
In
tell
ig
e
n
c
e
,
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
4
1
4
-
4
2
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jai.
v
1
0
.
i2
.
p
p
4
1
4
-
4
2
0
.
[5
]
A.
M
.
S
h
a
h
iri
a
n
d
W.
Hu
sa
in
,
“
A
re
v
iew
o
n
p
re
d
ictin
g
stu
d
e
n
t
'
s
p
e
rfo
rm
a
n
c
e
u
sin
g
d
a
ta
m
in
in
g
tec
h
n
iq
u
e
s
,”
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ie
n
c
e
,
v
o
l.
7
2
,
p
p
.
4
1
4
-
4
2
2
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
p
r
o
c
s.2
0
1
5
.
1
2
.
1
5
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
C
o
mp
a
r
is
o
n
o
f th
e
fea
tu
r
e
s
elec
tio
n
a
lg
o
r
ith
m
in
e
d
u
ca
tio
n
a
l d
a
ta
min
i
n
g
(
A
g
u
n
g
Tr
ia
yu
d
i
)
1871
[6
]
A.
M
ish
ra
,
R.
Ba
n
sa
l
,
a
n
d
S
.
N.
S
in
g
h
,
“
Ed
u
c
a
ti
o
n
a
l
d
a
ta
m
in
in
g
a
n
d
lea
rn
i
n
g
a
n
a
l
y
sis,
”
2
0
1
7
7
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Clo
u
d
C
o
mp
u
ti
n
g
,
D
a
ta
S
c
ien
c
e
&
En
g
in
e
e
r
in
g
-
Co
n
fl
u
e
n
c
e
,
2
0
1
7
,
p
p
.
4
9
1
-
4
9
4
,
d
o
i:
1
0
.
1
1
0
9
/CONFL
U
ENCE.
2
0
1
7
.
7
9
4
3
2
0
1
.
[7
]
N.
Hid
a
y
a
t,
R.
Ward
o
y
o
,
a
n
d
S
.
Az
h
a
ri,
“
Ed
u
c
a
ti
o
n
a
l
Da
ta
M
in
in
g
(ED
M
)
a
s
a
M
o
d
e
l
fo
r
S
tu
d
e
n
t
s'
Ev
a
lu
a
ti
o
n
i
n
Lea
rn
in
g
E
n
v
ir
o
n
m
e
n
t
,
”
2
0
1
8
T
h
ird
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
fo
rm
a
t
ics
a
n
d
C
o
mp
u
ti
n
g
(ICIC)
,
2
0
1
8
,
p
p
.
1
-
4
,
d
o
i:
1
0
.
1
1
0
9
/IAC.
2
0
1
8
.
8
7
8
0
4
5
9
.
[8
]
A.
M
u
e
e
n
,
B.
Zafa
r
,
a
n
d
U.
M
a
n
z
o
o
r,
“
M
o
d
e
li
n
g
a
n
d
P
re
d
icti
n
g
S
t
u
d
e
n
ts'
Ac
a
d
e
m
ic
P
e
rfo
rm
a
n
c
e
Us
i
n
g
Da
ta
M
i
n
in
g
Tec
h
n
iq
u
e
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
M
o
d
e
rn
Ed
u
c
a
ti
o
n
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
8
,
p
.
3
6
,
2
0
1
6
,
doi
:
1
0
.
5
8
1
5
/
ij
m
e
c
s.2
0
1
6
.
1
1
.
0
5
.
[9
]
W.
P
u
n
l
u
m
jea
k
a
n
d
N.
Ra
c
h
b
u
r
e
e
,
“
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
f
fe
a
tu
re
se
lec
ti
o
n
tec
h
n
i
q
u
e
s
fo
r
c
las
sify
stu
d
e
n
t
p
e
rfo
rm
a
n
c
e
,
”
2
0
1
5
7
th
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
a
n
d
El
e
c
trica
l
En
g
i
n
e
e
rin
g
(ICIT
EE
)
,
2
0
1
5
,
p
p
.
4
2
5
-
4
2
9
,
d
o
i:
1
0
.
1
1
0
9
/I
CITE
ED.
2
0
1
5
.
7
4
0
8
9
8
4
.
[1
0
]
W.
Z
h
a
n
g
a
n
d
S
.
Qi
n
,
“
A
b
rief
a
n
a
ly
sis
o
f
th
e
k
e
y
tec
h
n
o
l
o
g
ie
s
a
n
d
a
p
p
li
c
a
ti
o
n
s
o
f
e
d
u
c
a
ti
o
n
a
l
d
a
ta
m
in
in
g
o
n
o
n
li
n
e
lea
rn
in
g
p
latf
o
rm
,”
2
0
1
8
IEE
E
3
r
d
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Bi
g
Da
t
a
A
n
a
lys
is
(ICBDA
)
,
2
0
1
8
,
p
p
.
8
3
-
8
6
,
d
o
i
:
1
0
.
1
1
0
9
/ICBDA.
2
0
1
8
.
8
3
6
7
6
5
5
.
[1
1
]
C.
Ja
lo
ta
a
n
d
R.
Ag
ra
wa
l,
“
An
a
ly
sis
o
f
E
d
u
c
a
ti
o
n
a
l
D
a
ta
M
in
in
g
u
sin
g
Clas
sifica
ti
o
n
,
”
2
0
1
9
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
r
n
in
g
,
Bi
g
D
a
ta
,
C
lo
u
d
a
n
d
P
a
ra
ll
e
l
C
o
mp
u
t
in
g
(CO
M
IT
Co
n
)
,
2
0
1
9
,
p
p
.
2
4
3
-
2
4
7
,
d
o
i:
1
0
.
1
1
0
9
/CO
M
ITCo
n
.
2
0
1
9
.
8
8
6
2
2
1
4
.
[1
2
]
H.
M
.
Ha
rb
a
n
d
M
.
A.
M
o
u
sta
f
a
,
“
S
e
lec
ti
n
g
o
p
ti
m
a
l
s
u
b
se
t
o
f
f
e
a
tu
re
s
fo
r
stu
d
e
n
t
p
e
rfo
rm
a
n
c
e
m
o
d
e
l,
”
IJ
CS
I
In
t
e
rn
a
t
io
n
a
l
J
o
u
rn
a
l
Co
m
p
u
t
er
S
c
i
e
n
c
e
,
v
o
l.
9
,
n
o
.
5
,
p
p
.
2
5
3
-
2
6
2
,
2
0
1
2
.
[On
l
in
e
].
Av
a
il
a
b
le:
h
tt
p
s:/
/www
.
ij
c
si.o
r
g
/p
a
p
e
rs/IJCS
I
-
9
-
5
-
1
-
2
5
3
-
2
6
2
.
p
d
f
[1
3
]
A.
F
ig
u
e
ira,
"
P
re
d
ictin
g
G
ra
d
e
s
b
y
P
ri
n
c
ip
a
l
C
o
m
p
o
n
e
n
t
A
n
a
ly
sis:
A
Da
ta
M
in
in
g
Ap
p
ro
a
c
h
to
Lea
rn
i
n
g
An
a
ly
ics
,
"
2
0
1
6
IEE
E
1
6
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
L
e
a
rn
i
n
g
T
e
c
h
n
o
l
o
g
ies
(ICAL
T
)
,
2
0
1
6
,
p
p
.
4
6
5
-
4
6
7
,
d
o
i:
1
0
.
1
1
0
9
/ICALT
.
2
0
1
6
.
1
0
3
.
[1
4
]
A.
K.
P
a
n
d
e
y
,
D.
S
.
Ra
j
p
o
o
t
,
a
n
d
D.
S
.
Ra
jp
o
o
t,
"
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
f
c
las
sific
a
ti
o
n
tec
h
n
iq
u
e
s
b
y
u
ti
l
izin
g
WE
KA
,
"
2
0
1
6
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
S
ig
n
a
l
Pr
o
c
e
ss
in
g
a
n
d
Co
mm
u
n
ica
ti
o
n
(ICS
C)
,
2
0
1
6
,
p
p
.
2
1
9
-
2
2
4
,
d
o
i:
1
0
.
1
1
0
9
/IC
S
P
Co
m
.
2
0
1
6
.
7
9
8
0
5
7
9
.
[1
5
]
E.
A.
Am
rieh
,
T
.
Ha
m
ti
n
i
,
a
n
d
I.
Aljara
h
,
“
M
in
i
n
g
Ed
u
c
a
ti
o
n
a
l
Da
t
a
to
P
re
d
ict
S
tu
d
e
n
t’s
a
c
a
d
e
m
ic
P
e
rfo
rm
a
n
c
e
u
sin
g
En
se
m
b
le
M
e
th
o
d
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Da
t
a
b
a
se
T
h
e
o
ry
a
n
d
A
p
p
li
c
a
ti
o
n
,
v
o
l
.
9
,
n
o
.
8
,
p
p
.
1
1
9
-
1
3
6
,
2
0
1
6
,
d
o
i:
1
0
.
1
4
2
5
7
/
ij
d
ta.
2
0
1
6
.
9
.
8
.
1
3
.
[
On
li
n
e
].
A
v
a
il
a
b
le:
h
ttp
://ar
ticle.
n
ad
iap
u
b
.
co
m
/I
J
DT
A/v
o
l9
_
n
o
8
/1
3
.
p
d
f
[1
6
]
S
.
M
.
Ajib
a
d
e
,
N.
B
.
Ah
m
a
d
,
a
n
d
S
.
M
.
S
h
a
m
su
d
d
in
,
"
An
He
u
risti
c
F
e
a
tu
re
S
e
lec
ti
o
n
Alg
o
rit
h
m
to
E
v
a
lu
a
te
Ac
a
d
e
m
ic
P
e
rfo
rm
a
n
c
e
o
f
S
tu
d
e
n
ts,"
2
0
1
9
IEE
E
1
0
th
C
o
n
tr
o
l
a
n
d
S
y
ste
m
Gr
a
d
u
a
te
Res
e
a
rc
h
Co
ll
o
q
u
iu
m
(ICS
GRC)
,
2
0
1
9
,
p
p
.
1
1
0
-
1
1
4
,
d
o
i:
1
0
.
1
1
0
9
/ICS
G
RC.2
0
1
9
.
8
8
3
7
0
6
7
.
[1
7
]
T.
Ve
lmu
ru
g
a
n
a
n
d
C
.
An
u
ra
d
h
a
,
“
P
e
rfo
rm
a
n
c
e
Ev
a
l
u
a
ti
o
n
o
f
F
e
a
tu
re
S
e
lec
ti
o
n
Alg
o
ri
t
h
m
s
in
Ed
u
c
a
ti
o
n
a
l
Da
ta
M
in
i
n
g
,
”
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Da
ta
M
in
i
n
g
T
e
c
h
n
i
q
u
e
s
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
v
ol
.
5
,
n
o
.
2
,
p
p
.
1
3
1
-
1
3
9
,
2
0
1
6
,
d
o
i:
1
0
.
2
0
8
9
4
/IJDMT
A.
1
0
2
.
0
0
5
.
0
0
2
.
0
0
7
.
[1
8
]
M.
P
e
k
e
r
,
A
.
Ars
lan
,
B.
Ş
e
n
,
F
.
V.
Çe
leb
i
,
a
n
d
A.
Bu
t,
"
A
n
o
v
e
l
h
y
b
ri
d
m
e
th
o
d
fo
r
d
e
term
in
i
n
g
th
e
d
e
p
t
h
o
f
a
n
e
sth
e
sia
lev
e
l:
Co
m
b
i
n
i
n
g
Re
li
e
fF
fe
a
tu
re
se
lec
ti
o
n
a
n
d
ra
n
d
o
m
fo
re
st
a
lg
o
rit
h
m
(Re
li
e
fF
+
R
F
),
"
2
0
1
5
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m
o
n
I
n
n
o
v
a
ti
o
n
s
i
n
In
telli
g
e
n
t
S
y
sTem
s
a
n
d
Ap
p
li
c
a
ti
o
n
s
(INIS
T
A)
,
2
0
1
5
,
p
p
.
1
-
8
,
d
o
i:
1
0
.
1
1
0
9
/INI
S
TA.
2
0
1
5
.
7
2
7
6
7
3
7
.
[1
9
]
C.
An
u
ra
d
h
a
a
n
d
T.
Ve
lmu
r
u
g
a
n
,
“
F
e
a
tu
re
S
e
lec
ti
o
n
Tec
h
n
i
q
u
e
s
t
o
An
a
ly
se
S
tu
d
e
n
t
Ac
a
d
a
m
ic
P
e
rfo
rm
a
n
c
e
u
sin
g
Na
ïv
e
Ba
y
e
s Clas
sifier
,”
in
T
h
e
3
rd
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
ma
ll
&
M
e
d
iu
m B
u
sin
e
ss
,
2
0
1
6
,
p
p
.
3
4
5
-
3
5
0
.
[2
0
]
J.
No
v
a
k
o
v
ić,
P
.
S
tr
b
a
c
,
a
n
d
D
.
Bu
lato
v
i
ć
,
“
To
wa
rd
o
p
t
ima
l
fe
a
tu
re
se
lec
ti
o
n
u
sin
g
ra
n
k
in
g
m
e
th
o
d
s
a
n
d
c
las
sifica
ti
o
n
a
lg
o
rit
h
m
s,”
Y
u
g
o
sla
v
J
o
u
rn
a
l
o
f
Op
e
ra
ti
o
n
s
Res
e
a
rc
h
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
1
1
9
-
1
3
5
,
2
0
1
6
,
d
o
i:
1
0
.
2
2
9
8
/
YJ
OR1
1
0
1
1
1
9
N.
[2
1
]
S
.
T.
Ah
m
e
d
,
R.
Al
-
Ha
m
d
a
n
i
,
a
n
d
M
.
S
.
Cr
o
o
c
k
,
“
De
v
e
lo
p
e
d
t
h
ir
d
it
e
ra
ti
v
e
d
ich
o
to
m
ize
r
b
a
se
d
o
n
fe
a
tu
re
d
e
c
isiv
e
v
a
lu
e
s
fo
r
e
d
u
c
a
ti
o
n
a
l
d
a
ta
m
in
i
n
g
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
18
,
n
o
.
1
,
p
p
.
2
0
9
-
2
1
7
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
8
.
i1
.
p
p
2
0
9
-
2
1
7
.
[2
2
]
C.
R
o
m
e
ro
a
n
d
S
.
Ve
n
t
u
ra
,
“
Ed
u
c
a
ti
o
n
a
l
d
a
ta
m
in
i
n
g
a
n
d
l
e
a
rn
i
n
g
a
n
a
ly
t
ics
:
An
u
p
d
a
ted
su
rv
e
y
,
”
W
il
e
y
In
ter
d
isc
ip
li
n
a
ry
Rev
iews
:
Da
t
a
M
in
i
n
g
a
n
d
K
n
o
wle
d
g
e
Disc
o
v
e
ry
,
v
o
l
.
10
,
n
o
.
3
,
d
o
i:
1
0
.
1
0
0
2
/wid
m
.
1
3
5
5
.
[2
3
]
Y.
S
.
M
it
r
o
fa
n
o
v
a
,
A.
A.
S
h
e
rsto
b
it
o
v
a
,
a
n
d
O.
A.
F
il
ip
p
o
v
a
,
“
M
o
d
e
li
n
g
sm
a
rt
lea
rn
i
n
g
p
r
o
c
e
ss
e
s
b
a
se
d
o
n
e
d
u
c
a
ti
o
n
a
l
d
a
ta
m
in
i
n
g
t
o
o
ls
,”
In
S
m
a
rt
E
d
u
c
a
ti
o
n
a
n
d
e
-
L
e
a
rn
i
n
g
2
0
1
9
,
p
p
.
5
6
1
-
5
7
1
,
2
0
1
9
,
d
o
i
:1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
13
-
8
2
6
0
-
4
_
4
9
[2
4
]
R.
Ah
u
ja
,
A.
Jh
a
,
R.
M
a
u
r
y
a
,
a
n
d
R.
S
ri
v
a
sta
v
a
,
“
An
a
l
y
sis
o
f
E
d
u
c
a
ti
o
n
a
l
Da
ta
M
i
n
in
g
,”
I
n
:
Ya
d
a
v
N.,
Ya
d
a
v
A.
,
Ba
n
sa
l
J.,
De
e
p
K.,
Kim
J.
(e
d
s)
Ha
rm
o
n
y
S
e
a
rc
h
a
n
d
Na
tu
re
I
n
sp
ired
O
p
ti
m
iza
ti
o
n
Alg
o
rit
h
m
s.
Ad
v
a
n
c
e
s
i
n
In
telli
g
e
n
t
S
y
ste
ms
a
n
d
Co
mp
u
ti
n
g
,
v
o
l
.
7
4
1
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
13
-
0
7
6
1
-
4
_
8
5
[2
5
]
M.
Tsiak
m
a
k
i,
G.
Ko
st
o
p
o
u
l
o
s,
S
.
Ko
tsian
t
is
,
a
n
d
O.
Ra
g
o
s,
“
Im
p
l
e
m
e
n
ti
n
g
A
u
to
M
L
in
e
d
u
c
a
ti
o
n
a
l
d
a
ta m
in
i
n
g
fo
r
p
re
d
ictio
n
tas
k
s
,
”
Ap
p
li
e
d
S
c
ien
c
e
s
,
v
o
l.
10
,
n
o
.
1
,
p
.
9
0
,
2
0
2
0
,
d
o
i
:1
0
.
3
3
9
0
/ap
p
1
0
0
1
0
0
9
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.