I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l
I
nte
llig
ence
(
I
J
-
AI)
Vo
l.
10
,
No
.
2
,
J
u
n
e
2021
,
p
p
.
438
~
4
4
5
I
SS
N:
2
2
5
2
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
10
.i
2
.
p
p
4
3
8
-
445
438
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Acute
sinus
itis
da
ta cla
ss
ificatio
n u
sing
grey
w
o
lf
o
pti
m
i
z
a
tion
-
ba
sed supp
o
rt
v
ec
tor
m
a
chine
Aj
eng
M
a
ha
ra
ni P
utr
i
1
,
Z
uh
er
m
a
n R
us
t
a
m
2
,
J
a
cub P
a
nd
ela
k
i
3
,
I
ls
y
a
Wira
s
a
t
i
4
,
Sri H
a
rt
ini
5
1,
2
,
4,
5
De
p
a
rtm
e
n
t
o
f
M
a
th
e
m
a
ti
c
s,
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
,
De
p
o
k
,
I
n
d
o
n
e
sia
3
De
p
a
rtme
n
t
o
f
Ra
d
io
lo
g
y
,
Cip
to
M
a
n
g
u
n
k
u
su
m
o
Ho
sp
it
a
l,
Ja
k
a
rta,
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
Ma
r
1
1
,
2
0
20
R
ev
i
s
ed
Mar
12
,
2
0
21
A
cc
ep
ted
A
pr
13
,
2
0
21
A
c
u
te
sin
u
siti
s
is
t
h
e
m
o
st
c
o
m
m
o
n
f
o
rm
o
f
sin
u
siti
s,
a
n
d
it
c
a
u
se
s
sw
e
ll
in
g
a
n
d
in
f
lam
m
a
ti
o
n
w
it
h
in
t
h
e
n
o
se
.
T
h
e
m
a
in
th
in
g
t
h
a
t
c
a
n
c
a
u
se
s
sin
u
siti
s
is
p
ro
b
a
b
ly
d
u
e
to
v
iru
se
s,
a
n
d
a
lso
c
a
n
b
e
c
a
u
se
d
b
y
o
th
e
r
f
a
c
to
r
s,
n
a
m
e
l
y
b
a
c
teria
,
f
u
n
g
i,
irri
tatio
n
,
d
u
st,
a
n
d
a
ll
e
rg
e
n
s.
I
n
t
h
is
re
se
a
rc
h
,
th
e
CT
sc
a
n
d
a
ta
a
tt
rib
u
tes
w
il
l
b
e
u
se
d
f
o
r
c
las
si
f
ica
ti
o
n
a
n
d
g
re
y
w
o
l
f
o
p
t
im
iz
a
ti
o
n
-
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(GW
O
-
S
V
M
)
w
il
l
b
e
t
h
e
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
u
se
d
,
w
h
e
re
th
e
GWO
tec
h
n
iq
u
e
w
il
l
b
e
u
se
d
to
tu
n
e
d
th
e
p
a
ra
m
e
ters
in
S
V
M
.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
m
e
th
o
d
s
w
a
s
a
n
a
ly
z
e
d
u
sin
g
th
e
p
y
th
o
n
p
ro
g
ra
m
m
in
g
lan
g
u
a
g
e
w
it
h
d
if
f
e
r
e
n
t
p
e
rc
e
n
tag
e
s
o
f
train
in
g
d
a
ta,
w
h
ich
sta
rted
f
ro
m
1
0
%
to
9
0
%
.
T
h
e
GW
O
-
S
V
M
m
e
th
o
d
p
ro
p
o
se
d
p
ro
v
id
e
s
b
e
tt
e
r
a
c
c
u
ra
c
y
th
a
n
u
sin
g
S
V
M
w
it
h
o
u
t
GW
O.
K
ey
w
o
r
d
s
:
A
c
u
te
s
i
n
u
s
it
is
Gr
e
y
w
o
l
f
o
p
ti
m
izatio
n
Me
ta
-
h
eu
r
i
s
tic
Su
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
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
:
Z
u
h
er
m
an
R
u
s
ta
m
Dep
ar
t
m
en
t o
f
Ma
th
e
m
at
ics
Un
i
v
er
s
it
y
o
f
I
n
d
o
n
e
s
ia
Dep
o
k
1
6
4
2
4
,
I
n
d
o
n
esia
E
m
ail: r
u
s
ta
m
@
u
i.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
A
c
u
te
s
in
u
s
i
tis
i
s
th
e
m
o
s
t
c
o
m
m
o
n
f
o
r
m
o
f
s
i
n
u
s
i
tis
,
a
n
d
it
ca
u
s
es
s
w
elli
n
g
an
d
i
n
f
l
a
m
m
atio
n
w
it
h
i
n
th
e
n
o
s
e
[
1
]
.
T
h
e
m
ai
n
t
h
i
n
g
t
h
at
ca
n
ca
u
s
e
s
s
in
u
s
itis
i
s
p
r
o
b
ab
l
y
d
u
e
to
v
ir
u
s
e
s
,
an
d
a
ls
o
ca
n
b
e
ca
u
s
ed
b
y
o
th
er
f
ac
to
r
s
,
n
a
m
el
y
b
ac
ter
ia,
f
u
n
g
i,
ir
r
itat
io
n
,
d
u
s
t,
a
n
d
aller
g
en
s
[
2
]
.
I
n
d
i
ag
n
o
s
in
g
,
t
h
er
e
ar
e
s
ev
er
al
cr
iter
ia
th
at
ca
n
b
e
co
n
s
id
er
ed
,
s
u
c
h
as
n
asal
o
b
s
tr
u
ctio
n
,
f
ac
ial
p
ain
,
f
e
v
er
,
an
d
o
th
er
s
.
So
m
e
o
f
th
e
th
i
n
g
s
m
e
n
tio
n
ed
ea
r
lier
ar
e
i
n
clu
d
ed
in
t
h
e
m
aj
o
r
cr
iter
ia,
w
h
ile
t
h
er
e
ar
e
also
m
i
n
o
r
cr
iter
ia
s
u
c
h
as
d
en
tal
p
ain
,
h
ea
d
ac
h
e,
f
ati
g
u
e,
co
u
g
h
,
a
n
d
o
th
er
s
[
3
]
.
T
h
er
e
a
r
e
s
ev
er
al
m
et
h
o
d
s
i
n
d
iag
n
o
s
in
g
s
i
n
u
s
iti
s
i.e
.
co
m
p
u
ted
to
m
o
g
r
ap
h
y
s
ca
n
n
in
g
(
C
T
s
ca
n
)
,
n
a
s
al
en
d
o
s
c
o
p
y
,
n
asal
a
n
d
s
i
n
u
s
c
u
lt
u
r
e,
aller
g
y
te
s
t
a
n
d
m
ag
n
etic
r
eso
n
an
ce
i
m
a
g
in
g
(
MRI)
[
4
]
.
I
n
th
is
r
esear
ch
,
th
e
C
T
s
ca
n
d
ata
attr
ib
u
tes
w
i
ll
b
e
u
s
ed
f
o
r
class
i
f
icatio
n
m
et
h
o
d
s
.
T
h
e
p
r
ev
io
u
s
r
esear
ch
o
n
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
w
as
p
r
o
p
o
s
ed
to
p
r
o
ce
s
s
th
is
d
ata
[
4
]
.
A
l
s
o
,
m
an
y
r
esear
ch
es
b
ef
o
r
e
u
s
i
n
g
o
t
h
er
m
et
h
o
d
s
o
f
clas
s
i
f
icatio
n
f
o
r
class
i
f
y
in
g
d
is
ea
s
e
d
ata,
s
u
c
h
as
b
i
n
ar
y
lo
g
is
tic
r
eg
r
ess
io
n
f
o
r
o
v
ar
ia
n
ca
n
ce
r
class
i
f
icatio
n
[
5
]
,
f
ast
f
u
zz
y
c
lu
s
ter
i
n
g
f
o
r
b
r
ea
s
t
ca
n
ce
r
d
at
a
[
6
]
,
n
aiv
e
b
a
y
e
s
class
i
f
ier
f
o
r
p
r
ed
ictin
g
co
lo
n
ca
n
ce
r
[
7
]
,
r
an
d
o
m
f
o
r
est cla
s
s
if
ier
f
o
r
p
r
ed
ictin
g
p
r
o
s
tate
c
an
ce
r
[
8
]
,
an
d
m
an
y
m
o
r
e.
T
h
er
ef
o
r
e,
in
th
i
s
r
esea
r
ch
,
g
r
e
y
w
o
l
f
o
p
ti
m
izatio
n
-
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
GW
O
-
SVM)
w
il
l
b
e
th
e
m
ac
h
i
n
e
lear
n
i
n
g
tec
h
n
iq
u
e
u
s
ed
,
w
h
er
e
t
h
e
GW
O
tech
n
iq
u
e
w
ill b
e
u
s
ed
to
tu
n
ed
th
e
p
ar
am
eter
s
i
n
SVM.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
A
cu
te
s
in
u
s
itis
d
a
ta
cla
s
s
ifica
t
io
n
u
s
in
g
g
r
ey
w
o
lf o
p
timiz
a
tio
n
-
b
a
s
ed
… (
A
jen
g
Ma
h
a
r
a
n
i
P
u
tr
i
)
439
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
A
c
u
te
s
in
u
s
i
tis
d
ata
f
r
o
m
t
h
e
Dep
ar
t
m
en
t
o
f
R
ad
io
lo
g
y
at
C
ip
to
Ma
n
g
u
n
k
u
s
u
m
o
Ho
s
p
ital
at
J
ak
ar
ta
in
I
n
d
o
n
e
s
ia,
w
as
u
s
ed
in
t
h
i
s
s
tu
d
y
.
T
h
e
d
ata
s
ets
h
as
2
0
0
r
o
w
s
w
i
th
t
w
o
c
lass
e
s
n
a
m
ed
ac
u
te
s
i
n
u
s
i
tis
a
n
d
n
o
n
-
ac
u
te
s
i
n
u
s
iti
s
,
r
esp
ec
ti
v
el
y
.
F
u
r
th
er
m
o
r
e,
th
i
s
d
ataset
co
n
tain
s
f
iv
e
v
ar
iab
les,
w
h
i
ch
o
n
e
o
f
th
e
m
is
d
ep
en
d
en
t
an
d
th
e
r
est
o
f
t
h
e
m
ar
e
i
n
d
ep
en
d
en
t.
T
h
e
d
ep
en
d
en
t
v
ar
iab
le
is
a
clas
s
o
f
w
h
e
th
er
t
h
e
p
atie
n
t
h
as
ac
u
te
s
i
n
u
s
iti
s
m
ar
k
ed
0
o
r
n
o
n
-
ac
u
te
s
i
n
u
s
it
is
m
ar
k
ed
1
.
W
h
ile,
th
e
in
d
ep
en
d
e
n
t
v
ar
iab
le
s
a
r
e
g
en
d
er
(
0
f
o
r
m
ale,
1
f
o
r
f
e
m
ale)
,
a
g
e,
air
ca
v
it
y
,
an
d
h
o
u
n
s
f
ield
u
n
it (
H
U)
.
W
h
er
e,
h
o
u
n
s
f
ield
u
n
it i
s
a
r
elativ
e
q
u
a
n
ti
tati
v
e
m
ea
s
u
r
e
m
e
n
t
o
f
r
ad
io
d
en
s
it
y
u
tili
ze
d
b
y
r
ad
io
lo
g
is
ts
w
it
h
i
n
th
e
i
n
ter
p
r
etatio
n
o
f
co
m
p
u
te
d
to
m
o
g
r
ap
h
y
(
C
T
)
p
ictu
r
es
[
9
]
.
T
h
e
s
e
v
ar
iab
les
ar
e
u
s
ed
to
d
iag
n
o
s
e
th
e
ac
u
t
e
s
in
u
s
iti
s
.
T
ab
le
1
s
h
o
w
n
co
n
tai
n
s
th
r
ee
r
o
w
s
o
f
d
ata.
T
ab
le
1
.
E
x
am
p
le
o
f
s
in
u
s
itis
d
ata
G
e
n
d
e
r
A
g
e
H
U
(
H
o
u
n
sf
i
e
l
d
u
n
i
t
s
)
A
i
r
C
a
v
i
t
y
D
i
a
g
n
o
si
s
1
76
1
3
8
-
1
0
2
0
1
0
20
38
-
9
6
7
0
1
57
27
-
9
9
9
0
2
.
2
.
G
re
y
w
o
lf
o
pti
m
iza
t
io
n
(
G
WO
)
Gr
e
y
w
o
l
f
o
p
ti
m
izatio
n
(
GW
O)
is
o
n
e
o
f
r
ec
en
t
m
eta
-
h
eu
r
is
tics
m
e
th
o
d
s
w
h
ich
i
n
s
p
ir
e
d
b
y
g
r
e
y
w
o
l
v
es
(
C
a
n
is
Lu
p
u
s
)
,
p
r
o
p
o
s
ed
b
y
Mir
j
alili
et
a
l.
[
1
0
]
.
T
h
e
GW
O
alg
o
r
ith
m
s
i
m
u
l
ates
th
e
lead
er
s
h
ip
b
eh
av
io
r
an
d
h
u
n
ti
n
g
m
ec
h
a
n
is
m
u
n
d
er
t
h
e
g
r
e
y
w
o
l
f
h
i
er
ar
ch
y
i
n
ter
m
o
f
m
o
v
e
m
e
n
t
s
tr
ateg
y
o
f
s
ea
r
ch
ag
en
t
s
[
1
1
]
.
T
h
e
r
ea
s
o
n
w
h
y
GW
O
is
u
s
ed
in
t
h
is
r
esear
ch
is
b
ec
a
u
s
e
b
a
s
ed
o
n
s
ev
er
al
s
tu
d
ie
s
,
t
h
e
GW
O
alg
o
r
ith
m
p
r
o
d
u
ce
s
b
etter
r
esu
lts
w
h
e
n
co
m
p
ar
ed
to
o
th
er
m
etah
eu
r
i
s
tic
m
et
h
o
d
s
.
I
n
m
o
d
elin
g
t
h
e
g
r
e
y
w
o
lf
le
ad
er
s
h
ip
h
ier
ar
ch
y
,
alp
h
a
(
)
w
il
l
b
e
co
n
s
id
er
ed
as
th
e
m
o
s
t
s
u
itab
le
s
o
lu
tio
n
,
th
e
n
b
eta
(
)
an
d
d
elta
(
)
w
ill
b
e
co
n
s
id
er
ed
as
th
e
s
ec
o
n
d
an
d
th
ir
d
b
est
s
o
lu
tio
n
s
.
An
d
o
m
eg
a
(
)
w
i
ll
b
e
co
n
s
id
er
ed
as
t
h
e
r
e
m
ain
in
g
s
o
l
u
tio
n
.
T
h
e
o
p
t
i
m
izatio
n
m
o
d
el
t
h
at
w
i
ll
b
e
f
o
r
m
ed
is
a
r
ep
r
esen
tatio
n
o
f
th
e
h
u
n
t
in
g
b
eh
av
io
r
o
f
t
h
e
g
r
e
y
w
o
l
v
es
alp
h
a,
b
eta,
an
d
d
elta,
w
h
er
e
as
o
m
e
g
a
w
ill
o
n
l
y
f
o
llo
w
in
g
t
h
ese
g
r
o
u
p
s
[
1
2
]
.
Am
id
t
h
e
h
u
n
t
i
n
g
p
r
o
ce
s
s
,
th
e
g
r
e
y
w
o
l
v
es
s
u
r
r
o
u
n
d
th
eir
p
r
e
y
.
Nu
m
er
icall
y
,
t
h
e
m
o
d
el
o
f
s
u
r
r
o
u
n
d
in
g
b
eh
a
v
io
r
is
m
o
d
el
ed
b
y
th
e
(
1
)
an
d
(
2
)
[
1
3
]
:
⃗
⃗
=
.
(
)
−
(
)
(1
)
(
+
1
)
=
(
)
−
.
⃗
⃗
(
2
)
w
h
er
e
t =
cu
r
r
en
t iter
atio
n
;
⃗
⃗
=
s
u
r
r
o
u
n
d
i
n
g
p
r
e
y
v
ec
to
r
;
,
=
co
ef
f
icien
t v
ec
to
r
;
=
a
g
r
e
y
w
o
l
f
’
s
p
o
s
itio
n
v
ec
to
r
;
=
th
e
p
r
ey
’
s
p
o
s
itio
n
v
ec
to
r
.
T
h
e
f
o
llo
w
i
n
g
(
3
)
an
d
(
4
)
is
h
o
w
t
h
e
v
ec
to
r
s
an
d
ar
e
d
eter
m
i
n
ed
[
1
0
]
:
=
2
.
1
⃗
⃗
⃗
−
(
3
)
=
2
.
2
⃗
⃗
⃗
(
4
)
w
h
er
e
1
⃗
⃗
⃗
,
2
⃗
⃗
⃗
ar
e
r
an
d
o
m
v
ec
to
r
s
b
et
w
ee
n
[
0
,
1
]
an
d
co
m
p
o
n
en
t
s
ar
e
lin
ea
r
l
y
r
ed
u
ce
d
f
r
o
m
2
to
0
d
u
r
in
g
th
e
iter
atio
n
s
[
1
0
]
.
T
o
s
im
u
late
t
h
e
h
u
n
t
in
g
b
eh
a
v
io
r
o
f
g
r
e
y
w
o
l
v
es
in
m
at
h
e
m
atic
s
,
s
u
p
p
o
s
e
alp
h
a
(
ca
n
d
id
ate
s
o
lu
t
io
n
th
at
th
e
m
o
s
t
s
u
i
tab
le)
,
b
eta
a
n
d
d
elta
ar
e
t
h
e
ex
p
er
t
i
n
k
n
o
w
led
g
e
p
er
tain
in
g
to
th
e
p
r
e
y
’
s
lo
ca
tio
n
.
Hen
ce
,
d
u
r
in
g
th
e
iter
atio
n
s
,
t
h
e
th
r
e
e
b
est
s
o
lu
tio
n
s
w
ill
b
e
r
ec
o
r
d
ed
,
an
d
f
o
r
th
e
n
ex
t
iter
atio
n
ca
lcu
latio
n
w
i
ll
b
e
u
p
d
ated
b
ased
o
n
th
e
p
r
ev
io
u
s
t
h
r
ee
b
est
s
o
lu
tio
n
s
(
o
r
also
ca
lled
th
e
b
est
s
ea
r
c
h
a
g
en
ts
p
o
s
i
tio
n
)
.
T
h
e
f
o
r
m
u
las d
ef
in
ed
b
y
(
5
)
-
(
7
)
[
1
0
]
,
[
1
2
]
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
20
21
:
4
3
8
–
445
440
⃗
⃗
=
|
1
.
−
|
,
⃗
⃗
=
|
2
.
−
|
,
⃗
⃗
=
|
3
.
−
|
(
5
)
1
=
−
1
.
(
⃗
⃗
)
,
2
=
−
2
.
(
⃗
⃗
)
,
3
=
−
3
.
(
⃗
⃗
)
(6
)
(
+
1
)
=
⃗
1
+
⃗
2
+
⃗
3
3
(
7
)
T
h
e
iter
atio
n
ter
m
in
atio
n
o
f
th
e
g
r
e
y
w
o
l
f
o
p
ti
m
izatio
n
(
GW
O)
ca
lcu
latio
n
is
b
a
s
e
d
o
n
th
e
co
n
v
er
g
e
n
ce
o
f
t
h
e
o
p
ti
m
al
s
o
lu
tio
n
r
eq
u
ir
ed
.
T
h
e
b
est
s
o
lu
t
io
n
i
s
o
b
tain
ed
f
r
o
m
ca
lc
u
lati
n
g
t
h
e
alp
h
a
s
co
r
e,
an
d
th
e
p
ar
am
e
ter
th
at
w
ill
b
e
u
s
ed
in
th
e
n
e
x
t
ca
lcu
la
tio
n
o
r
n
ex
t
s
tep
is
th
e
v
al
u
e
o
f
th
e
alp
h
a
p
o
s
itio
n
th
at
h
as
b
ee
n
o
b
tai
n
ed
.
I
f
th
e
p
r
o
b
le
m
d
o
es
n
o
t
h
a
v
e
a
n
y
co
n
s
t
r
ain
t
tag
th
e
n
to
g
et
t
h
e
s
o
l
u
ti
o
n
b
y
s
to
p
p
in
g
th
e
iter
atio
n
p
r
o
ce
s
s
b
y
s
etti
n
g
th
e
m
ax
i
m
u
m
iter
atio
n
(
t)
at
th
e
b
eg
in
n
i
n
g
o
f
t
h
e
co
m
p
u
ta
tio
n
p
r
o
ce
s
s
[
1
4
]
.
2
.
3
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chine
(
SVM
)
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SV
M)
is
a
class
if
icatio
n
m
eth
o
d
in
tr
o
d
u
ce
d
b
y
B
o
s
er
,
Gu
y
o
n
,
an
d
Vap
n
i
k
in
1
9
9
2
.
T
h
e
SVM
m
et
h
o
d
is
ex
ten
s
i
v
el
y
u
s
ed
i
n
b
io
in
f
o
r
m
atics
b
ec
au
s
e
o
f
its
h
i
g
h
ac
c
u
r
ac
y
,
an
d
i
s
ab
le
to
h
an
d
le
d
ata
w
it
h
h
i
g
h
d
i
m
e
n
s
i
o
n
s
[
1
5
]
.
SVM
aim
s
to
f
i
n
d
a
h
y
p
er
p
lan
e
b
et
w
ee
n
t
w
o
tar
g
e
t
class
es
i
n
t
h
e
d
ata
an
d
m
a
x
i
m
ize
th
e
m
ar
g
in
[
1
6
]
.
T
h
e
lin
ea
r
m
o
d
el
f
o
r
h
y
p
er
p
lan
e
is
i
n
(
8
)
[
1
7
]
.
(
)
=
(
+
)
(
8
)
W
h
er
e,
=
w
e
ig
h
t
v
ec
to
r
;
=
b
ias
ter
m
;
=
in
p
u
t v
ec
to
r
.
T
h
e
f
o
llo
w
i
n
g
Fig
u
r
e
1
is
a
r
ep
r
esen
tatio
n
o
f
th
e
S
VM
m
et
h
o
d
[
1
8
]
.
Fig
u
r
e
1
.
A
r
ep
r
esen
tatio
n
o
f
SVM
Giv
e
n
a
d
ataset
{
(
,
)
|
∈
,
∈
{
−
1
,
+
1
}
,
=
1
,
2
,
…
,
}
,
th
e
SVM
o
p
ti
m
izatio
n
p
r
o
b
lem
is
in
(
9
)
[
1
7
]
:
m
i
n
.
1
2
|
|
|
|
2
(
9
)
Su
b
j
ec
t to
:
[
+
]
≥
1
(
1
0
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
A
cu
te
s
in
u
s
itis
d
a
ta
cla
s
s
ifica
t
io
n
u
s
in
g
g
r
ey
w
o
lf o
p
timiz
a
tio
n
-
b
a
s
ed
… (
A
jen
g
Ma
h
a
r
a
n
i
P
u
tr
i
)
441
I
f
th
e
cla
s
s
i
f
icatio
n
s
ee
m
s
to
h
av
e
an
er
r
o
r
to
ler
an
ce
,
th
e
SV
M
o
p
tim
izatio
n
i
s
b
ased
o
n
(
1
1
)
[
1
7
]
:
m
i
n
.
1
2
|
|
|
|
2
+
∑
=
1
(
1
1
)
Su
b
j
ec
t to
:
{
[
+
]
≥
1
−
≥
0
(
1
2
)
W
h
en
t
h
e
p
r
o
b
lem
ca
n
n
o
t
b
e
s
ep
ar
ated
lin
ea
r
l
y
i
n
th
e
i
n
p
u
t
s
p
ac
e,
th
e
s
tr
ateg
y
i
s
to
ap
p
ly
k
er
n
el
f
u
n
ctio
n
i
n
SVM.
T
h
e
k
er
n
el
f
u
n
ctio
n
d
ef
in
ed
in
(
1
3
)
.
(
,
)
=
〈
(
)
,
(
)
〉
(
1
3
)
W
h
e
r
e
(
)
d
en
o
tes
th
e
in
p
u
t
d
ata
’
s
m
ap
p
ed
f
ea
tu
r
e
s
p
ac
e,
a
n
d
in
th
e
h
i
g
h
-
d
i
m
en
s
io
n
al
f
e
atu
r
e
s
p
ac
e
,
(
,
)
is
th
e
k
er
n
e
l
f
u
n
ct
io
n
th
at
i
s
eq
u
al
to
th
e
in
n
er
p
r
o
d
u
ct
o
f
tw
o
v
ec
to
r
s
[
1
9
]
.
T
h
u
s
,
th
e
k
e
r
n
el
SV
M
f
o
r
m
u
la
is
i
n
t
h
e
(
1
4
)
[
2
0
]
.
min
,
1
2
+
∑
=
1
(
1
4)
Su
b
j
ec
t to
:
{
(
(
)
+
)
≥
1
−
≥
0
,
∀
(
1
5
)
W
e
ca
n
g
et
th
e
SVM
k
er
n
el
o
p
ti
m
izatio
n
ex
p
r
ess
ed
i
n
ter
m
s
o
f
v
ar
iab
les
[
2
1
]
:
ma
x
(
∑
=
1
−
1
2
∑
(
,
)
=
1
(
1
6
)
Su
b
j
ec
t to
:
{
∑
=
1
0
≤
≤
(
1
7
)
I
n
th
e
n
ex
t a
l
g
o
r
ith
m
,
t
h
e
k
er
n
el
f
u
n
ctio
n
th
a
t
w
ill b
e
u
s
ed
i
s
R
B
F k
er
n
el
w
h
er
e
(
,
)
=
e
xp
(
−
‖
−
‖
2
)
(
1
8
)
2
.
4
.
O
ptim
izi
ng
SVM
p
a
ra
m
et
er
s
us
i
ng
G
WO
a
lg
o
rit
hm
SVM
h
a
s
b
ee
n
u
s
ed
s
u
cc
es
s
f
u
ll
y
in
s
o
l
v
i
n
g
m
a
n
y
cla
s
s
i
f
i
ca
tio
n
p
r
o
b
lem
s
.
SVM
p
er
f
o
r
m
an
ce
i
s
af
f
ec
ted
b
y
th
e
ch
o
ice
o
f
k
er
n
el
f
u
n
ctio
n
ch
o
s
e
n
an
d
t
h
eir
p
ar
a
m
eter
v
alu
e
s
[
2
2
]
.
As
w
e
k
n
o
w
,
t
h
e
ac
c
u
r
ac
y
o
f
p
r
ed
ictio
n
o
f
th
e
SVM
m
o
d
el
is
r
elate
d
to
th
e
co
r
r
ec
t
p
a
r
a
m
eter
s
.
T
o
m
ax
i
m
ize
t
h
e
SVM
p
er
f
o
r
m
a
n
ce
th
e
p
ar
am
eter
s
m
u
s
t
b
e
tu
n
ed
;
th
e
er
r
o
r
p
en
alt
y
C
an
d
th
e
k
er
n
e
l
p
ar
am
eter
s
.
T
o
ad
j
u
s
t
th
e
p
ar
a
m
eter
s
(
,
)
,
th
e
tr
ain
i
n
g
d
ata
w
a
s
u
s
ed
.
T
h
er
ef
o
r
e,
th
is
m
eta
-
h
e
u
r
is
tic
te
ch
n
iq
u
e
ca
n
b
e
u
s
e
to
f
in
d
th
e
f
ea
s
ib
le
SVM
p
ar
am
eter
s
as
w
r
itte
n
o
n
r
ev
ie
w
f
r
o
m
Far
is
,
A
lj
ar
ah
,
A
l
-
B
etar
an
d
Mir
j
alili
[
2
3
]
.
Fig
u
r
e
2
d
ep
icts
th
e
p
r
o
ce
s
s
f
lo
w
ch
ar
t o
f
t
h
e
GW
O
-
SVM
alg
o
r
ith
m
[
2
4
]
,
[
2
5
]
.
2
.
5
.
P
er
f
o
rm
a
nce
m
ea
s
ure
ment
T
o
ev
alu
ate
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
clas
s
i
f
icatio
n
m
o
d
el
s
,
t
h
e
s
co
r
e
o
f
ac
cu
r
ac
y
w
ill
b
e
u
s
ed
.
C
o
m
p
u
te
th
e
ac
cu
r
ac
y
s
co
r
e
u
s
i
n
g
th
e
f
o
r
m
u
la
(
1
9
)
w
it
h
T
P
T
N
FN F
P
b
ased
o
n
T
ab
le
2
.
A
cc
u
r
ac
y
=
+
+
+
+
(
1
9
)
W
h
er
e
T
P
is
n
u
m
b
er
o
f
test
s
ar
e
h
av
in
g
ac
u
te
s
in
u
s
i
tis
an
d
ac
cu
r
atel
y
d
iag
n
o
s
ed
h
av
i
n
g
ac
u
te
s
i
n
u
s
iti
s
an
d
T
N
is
n
u
m
b
er
o
f
test
s
ar
e
n
o
n
-
ac
u
te
s
in
u
s
itis
a
n
d
ac
cu
r
atel
y
d
iag
n
o
s
ed
b
elo
n
g
i
n
g
n
o
n
-
ac
u
te
s
in
u
s
it
is
.
W
h
ile
FN
is
n
u
m
b
er
o
f
te
s
ts
w
i
th
ac
u
te
s
i
n
u
s
it
i
s
b
u
t
in
ac
c
u
r
atel
y
c
lass
i
f
ied
as
n
o
n
-
ac
u
te
s
i
n
u
s
iti
s
an
d
FP
is
n
u
m
b
er
o
f
test
s
ar
e
n
o
n
-
ac
u
te
s
in
u
s
itis
b
u
t in
ac
c
u
r
atel
y
cla
s
s
i
f
ied
as
h
av
i
n
g
ac
u
te
s
i
n
u
s
iti
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
20
21
:
4
3
8
–
445
442
T
ab
le
2
.
C
o
n
f
u
s
io
n
m
atr
i
x
P
r
e
d
i
c
t
i
o
n
A
c
u
t
e
C
l
a
ss
N
o
n
-
a
c
u
t
e
C
l
a
ss
A
c
t
u
a
l
A
c
u
t
e
C
l
a
ss
T
r
u
e
P
o
si
t
i
v
e
(
T
P
)
F
a
l
s
e
N
e
g
a
t
i
v
e
(
F
N
)
N
o
n
-
a
c
u
t
e
C
l
a
ss
F
a
l
s
e
P
o
si
t
i
v
e
(
F
P
)
T
r
u
e
N
e
g
a
t
i
v
e
(
T
N
)
Fig
u
r
e
2
.
A
l
g
o
r
ith
m
o
f
GW
O
-
SVM
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
SVM
R
B
F
Ker
n
el
an
d
GW
O
-
SV
M
R
B
F
Ker
n
el
w
as
a
n
al
y
ze
d
u
s
i
n
g
t
h
e
p
y
t
h
o
n
p
r
o
g
r
am
m
i
n
g
la
n
g
u
a
g
e
w
it
h
d
if
f
er
e
n
t
p
er
ce
n
tag
e
s
o
f
tr
ai
n
in
g
d
ata,
w
h
ic
h
s
tar
ted
f
r
o
m
1
0
%
to
9
0
%.
T
h
e
p
ar
am
eter
s
o
b
tain
ed
th
r
o
u
g
h
GW
O
-
SVM
f
o
r
ea
ch
p
er
ce
n
t
ag
e
o
f
tr
ai
n
in
g
d
ata
ar
e
s
h
o
w
n
i
n
T
ab
le
3
,
an
d
SVM
R
B
F
Ker
n
el
a
n
d
GW
O
-
SVM
R
B
F
Ker
n
e
l
r
es
u
lt
s
s
h
o
w
n
i
n
T
ab
le
4
an
d
T
ab
le
5
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
co
m
p
ar
ati
v
e
an
al
y
s
i
s
f
o
r
ac
cu
r
ac
y
o
f
SV
M
an
d
GW
O
-
SVM
.
T
h
e
r
esu
lt
s
h
o
w
ed
th
at
b
y
o
p
ti
m
izi
n
g
t
h
e
SVM
class
i
f
ier
’
s
i
n
p
u
t p
ar
a
m
eter
s
,
th
e
p
r
o
p
o
s
ed
GW
O
-
SVM
s
o
lu
t
io
n
o
u
tp
er
f
o
r
m
ed
t
h
e
SVM
al
g
o
r
ith
m
.
no
y
es
t
=
t
+
1
S
t
a
r
t
I
n
i
t
i
a
l
i
z
a
t
i
o
n
g
r
e
y
w
o
l
f
p
o
p
u
l
a
t
i
o
n
(
=
1
,
2
,
…
,
)
a
n
d
max
i
m
u
m
i
t
e
r
a
t
i
o
n
T
r
a
i
n
i
n
g
D
a
t
a
F
i
t
n
e
ss e
v
a
l
u
a
t
i
o
n
U
p
d
a
t
e
p
o
s
i
t
i
o
n
o
f
t
h
e
w
o
l
f
w
i
t
h
o
n
(5
)
-
(
7)
U
p
d
at
e
α,
d
a
n
I
t
e
r
a
t
i
o
n
h
a
s
r
e
a
c
h
e
d
i
t
e
r
max
?
O
p
t
i
mi
z
e
d
p
a
r
a
me
t
e
r
s
(
,
)
S
V
M
p
r
e
d
i
c
t
i
o
n
T
e
st
i
n
g
d
a
t
a
En
d
C
a
l
c
u
l
a
t
e
,
,
D
a
t
a
se
t
O
u
t
p
u
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
A
cu
te
s
in
u
s
itis
d
a
ta
cla
s
s
ifica
t
io
n
u
s
in
g
g
r
ey
w
o
lf o
p
timiz
a
tio
n
-
b
a
s
ed
… (
A
jen
g
Ma
h
a
r
a
n
i
P
u
tr
i
)
443
T
ab
le
3
.
T
h
e
p
ar
am
eter
s
o
b
tain
ed
th
r
o
u
g
h
GW
O
-
S
VM
W
ith
2
0
s
ea
r
ch
ag
en
t
s
an
d
5
I
ter
atio
n
s
T
r
a
i
n
i
n
g
D
a
t
a
(
%)
C
10
7
.
0
0
4
4
4
5
5
3
6
3
4
4
2
9
7
6
.
4
7
6
8
4
3
9
4
3
3
0
2
9
3
4
20
8
.
7
3
1
7
3
7
5
2
7
8
9
8
4
5
5
1
.
3
5
9
4
7
4
5
4
0
6
3
2
6
5
2
30
40
50
60
70
80
90
4
.
3
0
3
5
9
7
3
9
7
5
4
1
8
1
7
4
.
4
4
4
6
1
2
8
6
5
0
0
0
7
3
.
4
3
2
2
1
9
1
7
3
8
4
2
4
5
6
3
2
.
0
7
6
0
2
0
5
9
6
0
5
8
3
4
1
5
6
.
0
5
5
9
7
3
9
8
3
2
4
7
8
3
8
5
7
.
5
4
7
3
1
7
9
4
2
2
8
3
0
1
5
6
.
8
9
9
7
1
6
7
9
8
2
3
7
9
2
6
6
.
2
8
1
4
6
2
9
0
2
9
9
7
2
6
6
1
.
0
8
2
7
8
9
4
1
0
1
7
8
0
8
0
6
2
.
1
0
1
7
9
8
7
9
8
2
0
5
3
0
4
6
2
.
3
7
2
3
9
6
8
0
1
6
5
2
1
6
8
2
.
6
5
6
1
4
1
0
1
4
2
0
5
0
1
1
7
3
.
4
7
2
1
7
1
2
2
6
0
8
5
1
9
9
3
2
.
5
1
8
0
0
0
9
9
3
5
4
2
0
6
6
6
T
ab
le
4
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
S
VM
R
B
F
k
er
n
el
T
r
a
i
n
i
n
g
D
a
t
a
(
%)
A
c
c
u
r
a
c
y
(
%)
10
9
6
.
1
1
20
9
3
.
1
2
30
40
50
60
70
80
90
8
8
.
5
7
9
8
.
3
3
9
8
.
0
0
9
7
.
5
0
9
6
.
6
7
9
7
.
5
0
9
5
.
0
0
T
ab
le
5
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
GW
O
-
SVM
R
B
F
k
er
n
el
T
r
a
i
n
i
n
g
D
a
t
a
(
%)
A
c
c
u
r
a
c
y
(
%)
10
1
0
0
20
1
0
0
30
40
50
60
70
80
90
9
9
.
2
8
9
9
.
1
7
1
0
0
9
8
.
7
5
9
8
.
3
3
1
0
0
1
0
0
Fig
u
r
e
3
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
SVM
R
B
F Ke
r
n
el
a
n
d
GW
O
-
SV
M
R
B
F Ke
r
n
e
l
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
b
eg
i
n
s
w
it
h
ac
u
te
s
in
u
s
itis
d
ata,
w
h
ic
h
m
o
d
eled
b
y
p
r
o
p
o
s
ed
m
e
th
o
d
G
W
O
-
SV
M
R
B
F
Ker
n
el
an
d
SVM
R
B
F
Ker
n
el
as
a
co
m
p
ar
is
o
n
,
an
d
th
e
GW
O
tech
n
iq
u
e
u
s
e
d
to
o
p
tim
iz
in
g
th
e
p
ar
am
eter
s
i
n
SV
M.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
p
r
o
d
u
ce
th
e
lo
w
e
s
t a
cc
u
r
ac
y
o
f
9
8
.
3
3
%
w
h
en
d
ata
tr
ain
i
n
g
at
7
0
%
an
d
ac
h
ie
v
ed
th
e
h
i
g
h
est
ac
c
u
r
ac
y
o
f
1
0
0
%
w
h
e
n
d
ata
tr
ain
i
n
g
at
1
0
%,
2
0
%,
5
0
%,
8
0
%
an
d
9
0
%.
T
h
e
co
m
p
ar
is
o
n
r
esu
lt
ab
o
v
e
ill
u
s
t
r
ate
th
e
ef
f
ec
ti
v
en
e
s
s
o
f
u
s
in
g
GW
O
to
tu
n
e
d
th
e
p
ar
a
m
eter
s
in
SVM
clas
s
i
f
ier
.
Ho
w
e
v
er
,
th
e
d
i
f
f
er
e
n
ce
i
n
ac
cu
r
ac
y
r
es
u
lt
s
ar
e
n
o
t
v
er
y
s
i
g
n
i
f
ican
t,
b
ec
au
s
e
u
s
i
n
g
SVM
w
it
h
o
u
t
GW
O
alo
n
e
p
r
o
v
id
es
g
o
o
d
ac
cu
r
ac
y
r
e
s
u
l
t
s
.
Fo
r
f
u
t
u
r
e
r
esear
ch
,
th
i
s
m
e
th
o
d
ca
n
b
e
u
s
ed
f
o
r
o
th
er
d
at
a
w
ith
ex
p
ec
tatio
n
th
at
th
e
ac
c
u
r
ac
y
o
f
th
e
cla
s
s
i
f
icatio
n
r
esu
l
ts
o
b
tain
ed
is
b
etter
th
an
j
u
s
t
u
s
in
g
co
n
v
en
t
io
n
a
l
m
eth
o
d
s
,
an
d
also
if
it st
ill u
s
e
t
h
e
SVM
clas
s
i
f
ie
r
,
o
th
er
k
er
n
el
f
u
n
ctio
n
s
ca
n
b
e
u
s
ed
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esear
ch
f
u
ll
s
u
p
p
o
r
ted
f
in
an
c
iall
y
b
y
U
n
iv
er
s
it
y
o
f
I
n
d
o
n
esia,
w
it
h
a
P
UT
I
Q
2
2
0
2
0
r
esear
ch
g
r
an
t
s
ch
e
m
e
.
82,
00%
84,
00%
86,
00%
88,
00%
90,
00%
92,
00%
94,
00%
96,
00%
98,
00%
100
,
00%
102
,
00%
10
20
30
40
50
60
70
80
90
Ac
c
u
r
ac
y
Dat
a
T
r
ain
in
g
(
%)
S
V
M
and
G
WO
-
SV
M
S
V
M
GW
O-
S
VM
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
20
21
:
4
3
8
–
445
444
RE
F
E
R
E
NC
E
S
[1
]
A
.
S
.
A
ro
ra
a
n
d
J.
S
in
g
h
,
“
A
F
ra
m
e
w
o
rk
f
o
r
En
c
h
a
n
c
in
g
t
h
e
T
h
e
rm
o
g
r
a
p
h
ic
Ev
a
lu
a
t
io
n
o
n
Ch
a
ra
c
teristic
A
r
e
a
s
f
o
r
P
ra
n
a
sa
l
S
in
u
siti
s
De
tec
ti
o
n
,
”
In
In
fra
re
d
P
h
y
sic
s
&
T
e
c
h
n
o
lo
g
y
,
v
o
l.
8
5
,
p
p
.
4
5
7
-
4
6
4
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/
j.
in
f
ra
re
d
.
2
0
1
7
.
0
8
.
0
1
1
.
[2
]
B.
F
e
ld
t
,
“
A
c
u
te
S
in
u
siti
s
,
”
i
n
S
o
u
t
h
e
rn
M
e
d
ica
l
J
o
u
r
n
a
l
,
v
o
l.
1
0
6
,
n
o
.
1
0
,
p
p
.
5
7
7
-
5
8
1
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
9
7
/sm
j.
0
0
0
0
0
0
0
0
0
0
0
0
0
0
0
2
.
[3
]
R.
M
.
Ro
se
n
f
e
ld
,
“
A
c
u
te
S
in
u
siti
s
in
A
d
u
lt
s
,
”
in
T
h
e
Ne
w
En
g
l
a
n
d
J
o
u
rn
a
l
o
f
M
e
d
icin
e
,
3
7
5
:
9
6
2
-
970
,
2
0
1
6
.
d
o
i:
1
0
.
1
0
5
6
/NEJ
M
c
p
1
6
0
1
7
4
9
.
[4
]
J.
A
r
f
ian
i
e
t
a
l
,
.
“
Ke
rn
e
l
S
p
h
e
rica
l
K
-
M
e
a
n
s
a
n
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
f
o
r
A
c
u
te
S
in
u
siti
s
Cla
ss
if
ic
a
ti
o
n
,
”
i
n
IOP
Co
n
fer
e
n
c
e
S
e
rie
s
M
a
ter
ia
ls
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
5
4
6
0
5
2
0
1
1
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
5
4
6
/
5
/0
5
2
0
1
1
.
[5
]
T
.
L
.
Oc
tav
ian
i
e
t
a
l.
,
“
Ov
a
rian
Ca
n
c
e
r
Clas
sif
ic
a
ti
o
n
u
sin
g
Ba
y
e
si
a
n
L
o
g
ic
Re
g
re
ss
io
n
,
”
in
IOP
Co
n
fer
e
n
c
e
S
e
rie
s
M
a
ter
ia
ls S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
5
4
6
0
5
2
0
4
9
,
2
0
1
9
.
d
o
i:
1
0
.
1
0
8
8
/1
7
5
7
-
8
9
9
X
/
5
4
6
/5
/
0
5
2
0
4
9
.
[6
]
Z.
Ru
sta
m
a
n
d
S
.
Ha
rti
n
i
“
Clas
sif
ica
ti
o
n
o
f
Bre
a
st
Ca
n
c
e
r
u
sin
g
F
a
st
F
u
z
z
y
Clu
ste
rin
g
b
a
se
d
o
n
Ke
rn
e
l
,
”
in
in
IOP
Co
n
fer
e
n
c
e
S
e
rie
s M
a
ter
ia
ls
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
5
4
6
5
2
0
6
7
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/5
4
6
/
5
/0
5
2
0
6
7
.
[7
]
N.
S
a
l
m
i
a
n
d
Z.
Ru
sta
m
.
“
Na
iv
e
Ba
y
e
s
Clas
si
f
ier
f
o
r
P
re
d
ictin
g
th
e
Co
lo
n
Ca
n
c
e
r”
in
IOP
Co
n
fer
e
n
c
e
S
e
rie
s
M
a
ter
ia
ls S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
5
4
6
0
5
2
0
6
8
,
2
0
1
9
.
d
o
i:
1
0
.
1
0
8
8
/1
7
5
7
-
8
9
9
X
/
5
4
6
/5
/
0
5
2
0
6
8
.
[8
]
M
.
Hu
lj
a
n
a
h
e
t
a
l.
,
”
F
e
a
tu
re
S
e
l
e
c
ti
o
n
u
si
n
g
Ra
n
d
o
m
F
o
re
st
Cla
ss
if
ier
f
o
r
P
re
d
icti
n
g
P
r
o
sta
te
Ca
n
c
e
r
,
”
in
IOP
Co
n
fer
e
n
c
e
S
e
rie
s M
a
ter
ia
ls
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
5
4
6
0
5
2
0
3
1
,
2
0
1
9
.
d
o
i:
1
0
.
1
0
8
8
/1
7
5
7
-
8
9
9
X
/
5
4
6
/5
/
0
5
2
0
3
1
.
[9
]
T
.
D.
De
n
Otter a
n
d
J.
S
c
h
u
b
e
rt.
“
Ho
u
n
sf
il
e
d
Un
i
t” i
n
S
tat
P
e
a
rls
P
u
b
li
sh
i
n
g
,
2
0
1
9
.
[1
0
]
S.
M
irj
a
li
li
e
t
a
l.
,
“
G
re
y
w
o
lf
o
p
ti
m
iz
e
r
,
”
Ad
v
En
g
S
o
ft
w
,
6
9
:
4
6
–
61
,
2
0
1
4
.
d
o
i:
1
0
.
1
0
1
6
/j
.
a
d
v
e
n
g
so
f
t.
2
0
1
3
.
1
2
.
0
0
7
.
[1
1
]
T
.
R.
Bi
y
a
n
to
e
t
a
l.
,
“
Op
ti
m
i
z
a
ti
o
n
o
f
Ac
id
Ga
s
S
w
e
e
ten
in
g
P
la
n
t
Ba
se
d
o
n
L
e
a
st
S
q
u
a
re
s
-
S
u
p
p
o
rt
V
e
c
t
o
r
M
a
c
h
i
n
e
(L
S
-
S
V
M
)
M
o
d
e
l
a
n
d
G
re
y
Wo
lf
Op
ti
m
ize
r
(
GW
O)
”
in
In
ter
n
a
ti
o
n
a
l
S
e
min
a
r
o
n
S
e
n
so
rs
,
I
n
stru
me
n
ta
ti
o
n
,
M
e
a
su
re
me
n
t
a
n
d
M
e
tro
lo
g
y
(
IS
S
IM
M
),
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/IS
S
IM
M
2
0
1
6
.
7
8
0
3
7
1
1
.
[1
2
]
Z.
M
u
sta
f
f
a
,
M
.
H.
S
u
laim
a
n
a
n
d
M
.
N.
M
.
Ka
h
a
r
.
“
LS
-
S
VM
H
y
p
e
r
-
p
a
ra
m
e
ters
Op
ti
m
iza
ti
o
n
b
a
se
d
o
n
G
W
O
A
l
g
o
rit
h
m
f
o
r
T
i
m
e
S
e
ries
F
o
re
c
a
stin
g
,
”
in
In
ter
n
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
S
o
ft
w
a
re
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
te
r
S
y
ste
ms
(
ICS
ECS
)
,
2
0
1
5
,
d
o
i:
1
0
.
1
1
0
9
/ICS
ECS
.
2
0
1
5
.
7
3
3
3
1
0
7
.
[1
3
]
A
.
H.
S
w
e
id
a
n
e
t
a
l.
,
“
W
a
ter
Qu
a
li
ty
Clas
si
f
ic
a
ti
o
n
A
p
p
ro
a
c
h
b
a
s
e
d
o
n
Bi
o
-
in
s
p
ired
G
ra
y
W
o
lf
O
p
ti
m
iza
ti
o
n
,
”
i
n
7
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
f
S
o
ft
Co
mp
u
ti
n
g
a
n
d
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
(
S
o
CPa
R
),
2
0
1
5
,
d
o
i:
1
0
.
1
1
0
9
/
S
OC
P
A
R.
2
0
1
5
.
7
4
9
2
7
7
7
.
[1
4
]
S
.
Esw
a
ra
m
o
o
rth
y
,
“
G
re
y
W
o
l
f
Op
ti
m
iza
ti
o
n
Ba
se
d
P
a
ra
m
e
ter
S
e
l
e
c
ti
o
n
f
o
r
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s”
,
in
T
h
e
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
f
o
r
Co
mp
u
ta
ti
o
n
a
n
d
M
a
th
e
ma
t
ics
in
El
e
c
tr
ica
l
a
n
d
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
,
v
o
l.
3
5
,
n
o
.
5
,
p
p
.
1
5
1
3
-
1
5
2
3
,
2
0
1
6
.
d
o
i:
1
0
.
1
1
0
8
/COM
P
EL
-
09
-
2
0
1
5
-
0
3
3
7
.
[1
5
]
B.
S
c
h
ӧ
lk
o
p
f
,
K.
T
su
d
a
a
n
d
J.
P
.
V
e
rt.
“
Ke
rn
e
l
M
e
t
h
o
d
s
in
C
o
m
p
u
tatio
n
a
l
Bio
l
o
g
y
,
”
in
M
IT
P
re
ss
se
rie
s
o
n
Co
mp
u
t
a
ti
o
n
a
l
M
o
lec
u
l
a
r B
i
o
lo
g
y
,
2
0
0
4
.
[1
6
]
A
.
Be
n
h
u
r
a
n
d
J.
W
e
sto
n
,
“
A
u
se
r’s
g
u
id
e
t
o
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
s
,
”
in
M
e
th
o
d
s
in
M
o
lec
u
la
r
b
i
o
lo
g
y
,
v
o
l.
6
0
9
,
p
p
.
2
2
3
-
2
3
9
,
2
0
1
0
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
6
0
3
2
7
-
2
4
1
-
4
_
1
3
.
[1
7
]
N
.
Cristi
a
n
in
i
a
n
d
J
.
S
.
T
a
y
lo
r
,
“
A
n
In
tro
d
u
c
ti
o
n
t
o
S
u
p
p
o
rt
V
e
c
t
o
r
M
a
c
h
in
e
s
a
n
d
Oth
e
r
Ke
rn
e
l
-
Ba
se
d
Lea
rn
in
g
M
e
th
o
d
s
”
in
Ca
m
b
rid
g
e
P
re
ss
Un
iv
e
rsit
y
,
2
0
0
0
,
d
o
i:
1
0
.
1
0
1
7
/CBO
9
7
8
0
5
1
1
8
0
1
3
8
9
.
[1
8
]
S
.
R.
Na
g
a
n
n
a
a
n
d
P
.
C
.
De
k
a
.
,
“
S
u
p
p
o
r
t
v
e
c
to
r
m
a
c
h
in
e
a
p
p
li
c
a
ti
o
n
s
i
n
t
h
e
f
ield
o
f
h
y
d
ro
l
o
g
y
:
A
re
v
ie
w
,
”
in
Ap
p
li
e
d
S
o
ft
Co
mp
u
ti
n
g
,
v
o
l.
1
9
,
p
p
.
3
7
2
-
386
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
1
4
.
0
2
.
0
0
2
.
[1
9
]
X.
-
Q.
Bia
n
e
t
a
l
.
,
“
P
re
d
icti
o
n
o
f
S
u
lf
u
r
S
o
lu
b
il
it
y
in
S
u
p
e
rc
rit
ica
l
S
o
u
r
G
a
se
s
U
sin
g
G
r
e
y
W
o
lf
O
p
ti
m
ize
r
-
Ba
s
e
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
,
”
i
n
J
o
u
rn
a
l
o
f
M
o
lec
u
la
r
L
i
q
u
id
s
,
v
o
l.
2
6
1
,
p
p
.
4
3
1
–
438
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/
j.
m
o
ll
iq
.
2
0
1
8
.
0
4
.
0
7
0
.
[2
0
]
M
.
Aw
a
d
a
n
d
R.
Kh
a
n
n
a
.
“
Eff
ici
e
n
t
L
e
a
rn
in
g
M
a
c
h
in
e
,
”
in
S
p
rin
g
e
r S
c
ien
c
e
+
Bu
sin
e
ss
M
e
d
ia
Ne
w
Y
o
rk
,
p
3
9
-
55
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
4
3
0
2
-
5
9
9
0
-
9
.
[2
1
]
J.
X
iao
a
n
d
R.
Z
h
u
o
,
"
Re
se
a
rc
h
o
n
M
o
to
r
R
o
ll
i
n
g
Be
a
rin
g
F
a
u
lt
Clas
sif
ic
a
ti
o
n
M
e
th
o
d
Ba
se
d
o
n
CEE
M
DA
N
a
n
d
GW
O
-
S
V
M
,
"
2
0
1
8
2
n
d
I
EE
E
A
d
v
a
n
c
e
d
I
n
f
o
rm
a
ti
o
n
M
a
n
a
g
e
me
n
t,
C
o
mm
u
n
ica
tes
,
El
e
c
tro
n
ic
a
n
d
Au
t
o
ma
ti
o
n
Co
n
tro
l
Co
n
fer
e
n
c
e
(
IM
CEC)
,
2
0
1
8
,
p
p
.
1
1
2
3
-
1
1
2
9
,
d
o
i:
1
0
.
1
1
0
9
/I
M
CEC.
2
0
1
8
.
8
4
6
9
2
7
6
.
[2
2
]
A
.
L
.
D.
Ro
ss
i
a
n
d
A
.
C.
P
.
L
.
F
.
Ca
rv
a
lh
o
.
“
Bio
-
in
sp
ire
d
Op
ti
m
iza
ti
o
n
T
e
c
h
n
iq
u
e
s
f
o
r
S
V
M
P
a
ra
m
e
ter
T
u
n
in
g
”
in
1
0
t
h
Bra
zi
li
a
n
S
y
mp
o
siu
m
o
n
Ne
u
ra
l
Ne
tw
o
rk
s
,
2
0
0
8
,
d
o
i:
1
0
.
1
1
0
9
/S
BRN.2
0
0
8
.
2
8
.
[2
3
]
H.
F
a
ris,
e
t
a
l.
"
G
re
y
W
o
lf
Op
ti
m
iz
e
r:
A
Re
v
i
e
w
o
f
Re
c
e
n
t
V
a
ri
a
n
ts
a
n
d
A
p
p
li
c
a
ti
o
n
s”
in
Ne
u
ra
l
Co
mp
u
ti
n
g
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/
s0
0
5
2
1
-
0
1
7
-
3
2
7
2
-
5
.
[2
4
]
X.
-
Q.
Bia
n
,
e
t
a
l.
,
“
A
g
re
y
w
o
l
f
o
p
ti
m
ize
r
-
b
a
se
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
f
o
r
th
e
so
lu
b
il
i
ty
o
f
a
ro
m
a
ti
c
c
o
m
p
o
u
n
d
s
in
su
p
e
rc
rit
ica
l
c
a
rb
o
n
d
io
x
id
e
,
”
i
n
Ch
e
mic
a
l
En
g
in
e
e
rin
g
Res
e
a
rc
h
An
d
De
sig
n
,
v
o
l.
1
2
3
,
p
p
.
2
8
4
–
294
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
c
h
e
rd
.
2
0
1
7
.
0
5
.
0
0
8
.
[2
5
]
S
.
Jia
n
g
,
e
t
a
l.
,
“
H
y
b
rid
G
e
n
e
ti
c
G
re
y
W
o
lf
A
l
g
o
rit
h
m
f
o
r
Larg
e
-
S
c
a
le
G
lo
b
a
l
Op
ti
m
iza
ti
o
n
,
”
in
Co
mp
e
x
it
y
,
v
o
l.
2
0
1
9
,
2
0
1
9
,
A
rt
.
n
o
.
2
6
5
3
5
1
2
,
d
o
i
:
1
0
.
1
1
5
5
/2
0
1
9
/2
6
5
3
5
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
A
cu
te
s
in
u
s
itis
d
a
ta
cla
s
s
ifica
t
io
n
u
s
in
g
g
r
ey
w
o
lf o
p
timiz
a
tio
n
-
b
a
s
ed
… (
A
jen
g
Ma
h
a
r
a
n
i
P
u
tr
i
)
445
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Aje
n
g
M
a
h
a
r
a
n
i
Pu
tr
i
is
a
s
e
n
io
r
stu
d
e
n
t
a
t
th
e
Un
iv
e
rsity
o
f
In
d
o
n
e
sia
’s
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s.
M
s.
A
j
e
n
g
is p
a
ss
io
n
a
tely
stu
d
y
in
g
d
a
ta m
in
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
Zu
h
e
r
m
a
n
R
u
st
a
m
is
a
n
A
s
so
c
iate
P
ro
f
e
ss
o
r
a
n
d
a
lec
tu
re
r
in
in
telli
g
e
n
c
e
c
o
m
p
u
tatio
n
a
t
th
e
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
’s
De
p
a
rtm
e
n
t
o
f
M
a
th
e
m
a
ti
c
s.
H
e
re
c
e
i
v
e
d
h
is
M
a
ste
r
o
f
S
c
ien
c
e
in
in
f
o
rm
a
ti
c
s
f
ro
m
P
a
ris
Did
e
ro
t
Un
iv
e
rsit
y
in
1
9
8
9
,
a
n
d
h
is
P
h
.
D.
in
c
o
m
p
u
ter
sc
ien
c
e
f
ro
m
th
e
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
i
n
2
0
0
6
.
A
ss
o
c
.
P
ro
f
.
Dr.
R
u
sta
m
is
a
n
IEE
E
m
e
m
b
e
r
w
h
o
is
a
c
ti
v
e
l
y
re
se
a
rc
h
in
g
a
rti
f
ici
a
l
in
telli
g
e
n
c
e
,
n
e
u
ra
l
n
e
tw
o
rk
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
p
a
tt
e
r
n
re
c
o
g
n
it
i
o
n
.
J
a
c
u
b
Pa
n
d
e
l
a
k
i
i
s
a
n
a
c
a
d
e
m
i
c
se
n
a
te
a
n
d
lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
.
He
e
a
rn
e
d
h
is
m
e
d
ica
l
d
o
c
t
o
r
a
te
f
ro
m
th
e
F
a
c
u
lt
y
o
f
M
e
d
icin
e
,
Un
iv
e
rsity
o
f
In
d
o
n
e
sia
in
1
9
8
9
a
n
d
h
is
P
h
.
D.
f
ro
m
th
e
sa
m
e
u
n
iv
e
rsity
in
2
0
1
0
.
Dr
.
d
r.
Ja
c
u
b
P
a
n
d
e
lak
i,
S
p
.
Ra
d
is
a
d
o
c
to
r
a
n
d
th
e
c
h
a
ir
o
f
th
e
In
ter
n
a
ti
o
n
a
l
Ra
d
io
lo
g
y
Div
isio
n
a
t
th
e
De
p
a
rtm
e
n
t
o
f
Ra
d
io
lo
g
y
a
t
Cip
to
M
a
g
u
n
k
u
su
m
o
Ho
sp
it
a
l
in
In
d
o
n
e
sia
.
Ilsy
a
W
ira
sa
ti
is
a
f
in
a
l
y
e
a
r
stu
d
e
n
t
a
t
th
e
U
n
iv
e
rsity
o
f
In
d
o
n
e
si
a
’s
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s
,
w
h
o
is
c
u
rre
n
tl
y
w
o
rk
in
g
o
n
h
e
r
th
e
sis.
He
r
re
se
a
rc
h
is
f
ir
m
l
y
a
b
o
u
t
a
p
p
l
ied
m
a
th
e
m
a
ti
c
s
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
in
m
e
d
ica
l
f
iel
d
.
M
s.
Ilsy
a
’s
sp
e
c
i
a
lt
ies
in
re
se
a
rc
h
a
re
m
o
stl
y
a
b
o
u
t
m
a
c
h
in
e
lea
rn
in
g
,
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
li
n
g
,
a
n
d
d
a
ta m
in
in
g
.
S
r
i
H
a
r
ti
n
i
is
a
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
f
ro
m
th
e
De
p
a
rt
m
e
n
t
o
f
M
a
th
e
m
a
ti
c
s,
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
.
M
s.
Ha
rti
n
i
is
a
m
a
c
h
i
n
e
lea
rn
in
g
,
c
o
m
p
u
ter
v
isio
n
,
n
e
u
ra
l
n
e
tw
o
rk
s,
a
n
d
d
e
e
p
lea
rn
i
n
g
re
se
a
rc
h
e
r
w
h
o
w
o
rk
s in
a
n
u
m
b
e
r
o
f
f
ield
s.
Evaluation Warning : The document was created with Spire.PDF for Python.