I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
2
,
A
p
r
il 2
0
2
6
,
p
p
.
1
3
1
6
~
1
3
2
6
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
3
1
6
-
1
3
2
6
1316
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
H
y
brid k
ernel
su
ppo
rt
v
ector
ma
chine wi
th
cu
cko
o
sea
rch
o
ptimiza
tion for
ma
la
ria
det
ection
f
ro
m blo
o
d smea
r ima
g
es
Sri H
un
ing
An
wa
rinin
g
s
ih
1
,
I
nd
ra
rini Dy
a
h Ira
wa
t
i
2
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
F
a
c
u
l
t
y
o
f
S
a
i
n
s,
Te
c
h
n
o
l
o
g
y
,
a
n
d
H
e
a
l
t
h
,
U
n
i
v
e
r
si
t
a
s
S
a
h
i
d
S
u
r
a
k
a
r
t
a
,
S
u
r
a
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
2
S
c
h
o
o
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
,
T
e
l
k
o
m
U
n
i
v
e
r
si
t
y
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
2
3
,
2
0
2
5
R
ev
is
ed
J
an
7
,
2
0
2
6
Acc
ep
ted
J
an
2
2
,
2
0
2
6
M
icro
sc
o
p
ic
ima
g
e
-
b
a
se
d
m
a
laria
d
e
tec
ti
o
n
stil
l
stru
g
g
les
t
o
c
a
p
tu
re
c
o
m
p
lex
fe
a
tu
re
s
d
u
e
t
o
v
a
riatio
n
s
in
li
g
h
ti
n
g
a
n
d
c
o
lo
r
.
T
h
e
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM
)
m
e
th
o
d
is
o
ften
u
se
d
i
n
m
e
d
ica
l
ima
g
e
d
e
tec
ti
o
n
,
b
u
t
i
ts
p
e
rfo
rm
a
n
c
e
d
e
p
e
n
d
s
h
e
a
v
il
y
o
n
t
h
e
se
lec
ti
o
n
o
f
o
p
ti
m
a
l
k
e
rn
e
l
a
n
d
h
y
p
e
r
p
a
ra
m
e
ters
(C
a
n
d
g
a
m
m
a
).
Co
n
v
e
n
t
io
n
a
l
a
p
p
ro
a
c
h
e
s,
with
si
n
g
le
k
e
rn
e
ls
a
n
d
m
a
n
u
a
l
tu
n
i
n
g
,
h
a
v
e
li
m
it
a
ti
o
n
s
i
n
c
a
p
tu
ri
n
g
b
o
t
h
sp
a
ti
a
l
in
fo
rm
a
ti
o
n
a
n
d
c
o
l
o
r
d
istri
b
u
ti
o
n
sim
u
lt
a
n
e
o
u
sly
.
T
h
e
re
fo
re
,
th
is
re
se
a
rc
h
p
ro
p
o
se
s
h
y
b
r
i
d
k
e
rn
e
l
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
-
c
u
c
k
o
o
se
a
rc
h
a
lg
o
r
it
h
m
(
HK
S
VM
-
CS
A
)
m
e
th
o
d
th
a
t
c
o
m
b
in
e
s
th
e
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
(
RBF
)
k
e
rn
e
l
a
n
d
h
isto
g
ra
m
i
n
ters
e
c
ti
o
n
fo
r
S
VM,
a
lo
n
g
with
h
y
p
e
r
p
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
u
sin
g
t
h
e
CS
A
.
T
h
e
d
a
tas
e
t
u
se
d
is
m
a
laria
c
e
ll
ima
g
e
s
,
wh
ich
c
o
n
tain
s
p
a
ra
siti
z
e
d
a
n
d
u
n
i
n
fe
c
ted
ima
g
e
s
o
f
b
l
o
o
d
c
e
ll
s.
Th
e
p
ro
p
o
se
d
m
e
th
o
d
c
o
m
p
rise
s
fiv
e
m
a
in
ste
p
s:
d
a
tas
e
t
p
re
p
a
ra
ti
o
n
,
fe
a
tu
re
e
x
trac
ti
o
n
,
HK
S
VM,
h
y
p
e
r
p
a
ra
m
e
ter
o
p
ti
m
i
z
a
ti
o
n
,
a
n
d
m
o
d
e
l
e
v
a
lu
a
ti
o
n
.
E
x
p
e
rime
n
ts
d
e
m
o
n
stra
te
th
a
t
th
e
p
r
o
p
o
se
d
m
o
d
e
l
a
c
h
iev
e
s
9
4
%
a
c
c
u
ra
c
y
,
9
3
%
se
n
siti
v
it
y
,
9
4
%
sp
e
c
if
icit
y
,
a
n
d
a
re
a
u
n
d
e
r
th
e
c
u
rv
e
(
AUC
)
o
f
0
.
9
8
,
wh
ich
is
sig
n
ifi
c
a
n
tl
y
b
e
tt
e
r
th
a
n
sta
n
d
a
r
d
S
VM
,
S
V
M
-
g
e
n
e
ti
c
a
lg
o
r
it
h
m
(
GA
)
,
a
n
d
k
-
n
e
a
re
st
n
e
ig
h
b
o
rs
(KN
N)
.
T
h
e
se
re
su
lt
s
sh
o
w
th
a
t
c
o
m
b
i
n
in
g
k
e
rn
e
l
a
n
d
CS
A
sig
n
ifi
c
a
n
tl
y
imp
ro
v
e
s
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
.
T
h
is
a
p
p
r
o
a
c
h
is
p
ro
m
isin
g
fo
r
ima
g
e
-
b
a
se
d
a
u
t
o
m
a
ti
c
sy
ste
m
s fo
r
in
fe
c
ti
o
u
s d
ise
a
se
d
iag
n
o
si
s.
K
ey
w
o
r
d
s
:
C
u
ck
o
o
s
ea
r
ch
alg
o
r
ith
m
His
to
g
r
am
in
ter
s
ec
tio
n
Hy
b
r
id
k
e
r
n
el
Ma
lar
ia
d
etec
tio
n
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sri
Hu
n
in
g
An
war
in
i
n
g
s
ih
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
Sain
s
,
T
ec
h
n
o
lo
g
y
,
a
n
d
Hea
lth
,
Un
iv
er
s
itas
Sah
id
Su
r
ak
ar
ta
St.
Ad
i Su
cip
to
,
No
1
5
4
,
J
ajar
,
Su
r
ak
ar
ta,
C
en
tr
al
J
av
a,
I
n
d
o
n
esia
E
m
ail:
h
u
n
in
g
1
7
0
6
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Ma
lar
ia
is
a
d
ea
d
ly
in
f
ec
tio
u
s
d
is
ea
s
e
th
at
is
ca
u
s
ed
b
y
p
r
o
to
zo
an
p
a
r
asit
es.
T
h
ese
p
r
o
to
zo
a
n
p
ar
asit
es
b
elo
n
g
t
o
th
e
g
en
u
s
P
la
s
mo
d
iu
m
an
d
ar
e
tr
a
n
s
m
itted
to
h
u
m
an
s
v
ia
th
e
b
ite
o
f
a
f
em
ale
A
n
o
p
h
eles
mo
s
q
u
ito
[
1
]
.
Sev
er
al
s
p
ec
ies
f
r
o
m
b
o
th
g
en
er
a
ar
e
r
esp
o
n
s
ib
le
f
o
r
m
alar
ia
tr
an
s
m
is
s
i
o
n
ac
r
o
s
s
d
if
f
er
en
t
en
d
em
ic
r
eg
i
o
n
s
,
th
at
is
,
P
la
s
mo
d
iu
m
o
va
le
,
P
.
ma
la
r
ia
e
,
P
.
fa
lcip
a
r
u
m
,
P
.
viva
x
,
an
d
P
.
k
n
o
w
lesi
[
2
]
.
T
h
e
W
H
O
p
r
e
d
i
c
t
s
2
3
0
m
i
l
l
io
n
m
a
l
ar
i
a
c
a
s
e
s
wo
r
l
d
w
id
e
in
2
0
2
3
.
T
h
i
s
i
s
e
q
u
i
v
a
l
en
t
t
o
6
0
.
4
c
a
s
e
s
p
e
r
1
,
0
0
0
in
d
iv
i
d
u
a
l
s
.
T
h
i
s
i
s
a
n
i
n
cr
e
a
s
e
c
o
m
p
ar
ed
t
o
2
0
2
2
,
w
h
en
t
h
e
r
e
w
er
e
5
8
.
6
c
a
s
e
s
p
e
r
1
,
0
0
0
i
n
d
i
v
id
u
a
l
s
.
I
n
2
0
2
3
,
a
p
p
r
o
x
i
m
a
t
e
ly
9
4
%
o
f
a
l
l
g
lo
b
a
l
c
a
s
e
s
w
e
r
e
r
ep
o
r
t
ed
i
n
A
f
r
i
c
a.
S
i
m
i
l
ar
l
y
,
9
5
%
o
f
t
h
e
p
r
o
je
c
t
e
d
5
9
7
,
0
0
0
g
lo
b
a
l
m
a
la
r
i
a
f
a
t
a
li
t
i
e
s
in
2
0
2
3
o
c
c
u
r
r
ed
in
t
h
e
A
f
r
i
c
a
n
R
e
g
i
o
n
[
3
]
.
M
a
l
ar
i
a
s
y
m
p
to
m
s
a
p
p
e
ar
w
h
en
t
h
e
P
l
a
s
m
o
d
iu
m
p
a
r
a
s
i
t
e
a
t
t
ac
k
s
a
n
d
m
u
l
t
ip
l
i
e
s
w
i
t
h
i
n
th
e
r
e
d
b
l
o
o
d
c
e
l
l
s
.
I
n
s
id
e
r
e
d
b
lo
o
d
c
e
l
l
s
,
t
h
e
P
l
a
s
m
o
d
i
u
m
p
ar
a
s
i
t
e
u
n
d
er
g
o
e
s
s
e
v
e
r
a
l
d
ev
e
l
o
p
m
en
t
a
l
s
t
a
g
e
s
.
I
n
i
t
i
a
l
l
y
,
in
i
t
s
r
i
n
g
f
o
r
m
,
i
t
d
ev
e
l
o
p
s
in
t
o
a
t
r
o
p
h
o
zo
i
t
e
a
n
d
u
l
t
i
m
a
te
l
y
f
o
r
m
s
a
s
c
h
i
zo
n
t
[
4
]
.
T
h
e
s
c
h
i
zo
n
t
d
iv
i
d
e
s
i
n
to
m
an
y
m
e
r
o
z
o
i
t
e
s
,
w
h
ic
h
a
r
e
r
e
l
e
a
s
e
d
wh
e
n
t
h
e
r
e
d
b
lo
o
d
c
e
l
l
b
u
r
s
t
s
,
i
n
f
e
c
t
in
g
o
th
e
r
c
e
l
l
s
a
n
d
i
n
i
t
i
a
t
in
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
ke
r
n
el
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
w
ith
cu
ck
o
o
s
ea
r
ch
o
p
timiz
a
tio
n
fo
r
…
(
S
r
i H
u
n
in
g
A
n
w
a
r
in
in
g
s
ih
)
1317
i
n
f
e
c
t
io
n
c
y
c
le
t
h
a
t
c
a
u
s
e
s
f
ev
e
r
.
T
h
i
s
cy
c
l
e
w
i
l
l
c
o
n
t
i
n
u
e
t
o
r
ep
e
a
t
[
5
]
.
T
h
e
in
v
a
s
io
n
o
f
m
a
l
a
r
i
a
p
ar
a
s
i
t
e
s
i
n
t
o
r
ed
b
l
o
o
d
c
e
l
l
s
a
l
t
er
s
th
e
m
o
r
p
h
o
l
o
g
y
a
n
d
s
t
r
u
c
tu
r
e
o
f
t
h
e
s
e
c
e
l
l
s
.
T
h
e
s
e
c
h
an
g
es
c
a
n
b
e
o
b
s
er
v
ed
m
i
c
r
o
s
co
p
ic
a
l
l
y
,
p
r
o
v
i
d
in
g
an
o
p
p
o
r
tu
n
i
ty
to
u
s
e
r
ed
b
lo
o
d
ce
l
l
i
m
a
g
e
s
f
o
r
t
h
e
au
t
o
m
a
t
i
c
d
e
t
e
c
t
io
n
o
f
m
a
l
a
r
i
a
i
n
f
e
c
t
i
o
n
s
[
6
]
.
Acc
u
r
ate
ea
r
ly
d
etec
tio
n
o
f
m
alar
ia
in
f
ec
tio
n
is
cr
u
cial
b
ec
au
s
e
it
in
f
o
r
m
s
d
ec
is
io
n
s
o
n
wh
en
to
ad
m
in
is
ter
tr
ea
tm
en
t,
th
er
eb
y
r
ed
u
cin
g
t
h
e
r
is
k
o
f
d
is
ea
s
e
tr
an
s
m
is
s
io
n
.
Gen
er
ally
,
m
alar
ia
in
f
ec
tio
n
d
etec
tio
n
r
elies
o
n
tr
ad
itio
n
al
m
eth
o
d
s
,
in
clu
d
in
g
r
a
p
id
d
iag
n
o
s
tic
test
s
(
R
DT
s
)
an
d
m
icr
o
s
co
p
y
.
Ho
wev
er
,
th
ese
m
eth
o
d
s
h
av
e
lim
itatio
n
s
,
in
clu
d
in
g
th
e
n
ee
d
f
o
r
ex
p
e
r
t
s
k
ills
,
v
ar
iatio
n
s
in
in
ter
p
r
etatio
n
r
esu
lts
,
an
d
th
e
in
ab
ilit
y
to
au
to
m
ate
[
7
]
,
[
8
]
.
R
ec
en
t
r
esear
ch
h
as
d
em
o
n
s
tr
ated
th
at
m
ac
h
in
e
lea
r
n
in
g
an
d
co
m
p
u
ter
v
is
io
n
ca
n
id
en
tify
m
alar
ia
in
b
l
o
o
d
s
m
ea
r
im
ag
es a
u
to
m
atica
lly
[
9
]
,
[
1
0
]
.
Ov
er
th
e
p
ast
d
ec
a
d
e,
m
a
n
y
a
u
to
m
atic
d
etec
tio
n
m
eth
o
d
s
f
o
r
m
alar
ia
p
ar
asit
es
b
ased
o
n
b
l
o
o
d
s
m
ea
r
im
ag
es
h
av
e
b
ee
n
d
ev
elo
p
ed
.
So
m
e
tr
ad
itio
n
al
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es,
s
u
ch
as
th
r
esh
o
ld
in
g
[
1
1
]
,
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
[
1
2
]
,
an
d
s
eg
m
en
tatio
n
t
o
is
o
late
in
f
ec
ted
ce
lls
[
1
3
]
ar
e
u
s
ed
b
e
f
o
r
e
class
if
icatio
n
.
Ho
wev
er
,
th
ese
m
eth
o
d
s
s
tr
u
g
g
le
to
h
a
n
d
le
v
a
r
iatio
n
s
in
s
tain
in
g
,
lig
h
tin
g
,
an
d
ce
ll
m
o
r
p
h
o
lo
g
y
,
lead
i
n
g
to
in
co
n
s
is
ten
t p
er
f
o
r
m
an
ce
in
r
e
al
-
wo
r
ld
ap
p
licatio
n
s
.
Ma
ch
in
e
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
es
h
a
v
e
d
em
o
n
s
tr
ated
th
e
ab
ilit
y
to
tack
le
th
ese
ch
allen
g
es.
Sev
er
al
co
n
v
en
tio
n
al
class
if
ier
s
,
in
clu
d
in
g
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
d
ec
is
io
n
tr
ee
s
,
an
d
n
aiv
e
B
ay
es,
h
av
e
b
ee
n
wid
ely
u
s
ed
in
v
a
r
io
u
s
s
tu
d
ies.
Ho
wev
er
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
ese
co
n
v
en
tio
n
a
l
m
eth
o
d
s
ten
d
s
to
d
ec
lin
e
wh
en
f
ac
i
n
g
h
i
g
h
-
d
im
en
s
io
n
al
f
ea
tu
r
e
s
p
ac
es a
n
d
o
v
er
lap
p
in
g
class
es f
o
r
n
o
n
-
lin
ea
r
d
ata
[
1
3
]
.
Am
o
n
g
v
ar
i
o
u
s
class
if
ier
s
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
h
as
d
em
o
n
s
tr
ated
s
u
p
er
io
r
o
r
co
m
p
ar
ab
le
p
er
f
o
r
m
an
ce
to
o
th
e
r
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
,
p
ar
ticu
lar
l
y
in
d
is
ea
s
e
d
iag
n
o
s
is
an
d
p
r
o
g
n
o
s
is
.
T
h
e
u
s
e
o
f
k
er
n
el
f
u
n
ctio
n
s
(
e.
g
.
,
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F
)
an
d
p
o
ly
n
o
m
ials
)
ca
n
ef
f
icien
tly
h
an
d
l
e
h
ig
h
-
d
im
en
s
io
n
al
f
ea
tu
r
e
s
p
ac
es
an
d
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
in
m
ed
ical
d
ata,
m
ak
in
g
it
p
ar
ticu
lar
ly
u
s
ef
u
l
f
o
r
lar
g
e
-
s
ca
le
ap
p
licatio
n
s
[
1
3
]
.
SVMs
p
er
f
o
r
m
well
o
n
d
atasets
with
a
s
m
all
n
u
m
b
er
o
f
s
am
p
les
an
d
a
lar
g
e
n
u
m
b
er
o
f
f
ea
tu
r
es (
e.
g
.
,
m
icr
o
a
r
r
ay
g
en
e
d
ata)
,
wh
er
e
tr
ad
itio
n
al
m
o
d
e
ls
m
ay
s
tr
u
g
g
le
d
u
e
to
o
v
er
f
itt
in
g
[
1
4
]
.
T
h
e
SVM
m
eth
o
d
h
as
b
ee
n
wid
ely
u
s
ed
to
en
h
an
ce
th
e
a
cc
u
r
ac
y
o
f
m
alar
ia
d
is
ea
s
e
d
etec
tio
n
an
d
class
if
icatio
n
[
1
5
]
–
[
1
7
]
.
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
an
d
o
th
er
d
ee
p
lea
r
n
i
n
g
alg
o
r
ith
m
s
h
a
v
e
p
r
o
v
e
n
m
o
r
e
e
f
f
ec
tiv
e
at
class
if
y
in
g
m
alar
ia
ce
lls
[
1
8
]
–
[
2
0
]
.
Ho
wev
er
,
d
ee
p
lear
n
in
g
m
eth
o
d
s
r
e
q
u
ir
e
n
o
t
o
n
ly
lar
g
e
am
o
u
n
ts
o
f
a
n
n
o
tat
ed
d
ata
b
u
t
also
s
ig
n
if
ican
t
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
.
T
h
is
lim
its
th
eir
p
r
ac
tical
ap
p
licatio
n
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
en
v
ir
o
n
m
en
ts
.
I
n
co
n
tr
a
s
t,
u
s
in
g
an
SVM
co
m
b
in
e
d
with
d
im
en
s
io
n
ality
r
ed
u
ctio
n
tec
h
n
iq
u
es
h
as p
r
o
v
en
b
o
th
h
elp
f
u
l a
n
d
c
o
m
p
u
tatio
n
ally
ef
f
icien
t
[
1
7
]
.
Ho
wev
er
,
u
s
in
g
a
s
in
g
le
k
er
n
el,
s
u
ch
as
th
e
R
B
F
k
er
n
el,
in
SVM
o
f
ten
m
ak
es
it
in
s
u
f
f
icien
t
f
o
r
ca
p
tu
r
in
g
th
e
f
u
ll
d
iv
er
s
ity
o
f
v
is
u
al
p
atter
n
s
in
b
lo
o
d
ce
ll
im
ag
es.
Ad
d
itio
n
ally
,
SV
M’
s
p
er
f
o
r
m
an
ce
is
in
f
lu
en
ce
d
b
y
h
y
p
er
p
ar
am
ete
r
s
(
C
an
d
g
a
m
m
a)
th
at
a
f
f
ec
t
ac
cu
r
ac
y
[
2
1
]
.
Gen
er
ally
,
b
o
th
p
a
r
am
eter
s
ar
e
d
eter
m
in
ed
th
r
o
u
g
h
m
an
u
al
t
u
n
in
g
o
r
g
r
id
s
ea
r
ch
.
B
o
th
m
eth
o
d
s
r
eq
u
ir
e
a
h
ig
h
co
m
p
u
tatio
n
al
tim
e
an
d
d
o
n
o
t g
u
a
r
an
tee
o
p
tim
al
v
alu
es.
C
o
n
s
id
er
in
g
th
ese
lim
itatio
n
s
,
th
is
r
esear
ch
p
r
o
p
o
s
es
an
im
p
r
o
v
e
d
SVM
f
r
am
ewo
r
k
th
at
in
teg
r
ates
R
B
F
an
d
h
is
to
g
r
a
m
in
ter
s
ec
tio
n
k
e
r
n
els
with
in
a
h
y
b
r
id
k
e
r
n
el
d
esig
n
.
Su
p
er
io
r
ity
h
y
b
r
i
d
k
er
n
els
allo
w
th
e
class
if
ier
to
ca
p
tu
r
e
b
o
th
lo
ca
l
an
d
g
lo
b
al
s
tr
u
ctu
r
es
in
th
e
d
ata
b
y
co
m
b
in
in
g
m
u
ltip
le
s
im
ilar
ity
m
ea
s
u
r
es
[
2
2
]
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
will
u
tili
ze
a
h
y
b
r
id
k
er
n
el
a
n
d
ap
p
ly
th
e
cu
ck
o
o
s
ea
r
ch
alg
o
r
ith
m
(
C
SA)
to
d
eter
m
in
e
th
e
C
an
d
g
a
m
m
a
p
ar
am
eter
s
,
th
er
eb
y
o
b
tain
in
g
t
h
e
o
p
tim
al
p
ar
am
eter
s
f
o
r
u
s
e
in
th
e
SVM
m
o
d
el.
T
h
e
C
SA
m
eth
o
d
p
r
o
p
o
s
ed
b
y
Yan
g
a
n
d
Deb
[
2
3
]
h
as
s
ev
er
al
ad
v
an
tag
es,
in
clu
d
in
g
a
s
im
p
le
s
tr
u
ctu
r
e,
g
lo
b
al
s
ea
r
ch
ca
p
ab
ilit
ies
v
ia
L
ev
y
f
lig
h
ts
,
an
d
h
ig
h
co
n
v
er
g
en
ce
ef
f
icien
cy
.
Pre
v
io
u
s
s
tu
d
ies
h
av
e
s
h
o
wn
th
at
C
SA
p
er
f
o
r
m
s
well
ac
r
o
s
s
d
iv
er
s
e
o
p
tim
izatio
n
p
r
o
b
le
m
s
[
2
4
]
.
B
y
co
m
b
in
in
g
th
e
ad
v
an
tag
es
o
f
m
u
ltip
le
k
er
n
el
f
u
n
ctio
n
s
with
th
e
g
lo
b
al
s
ea
r
ch
ca
p
ab
ilit
ies
o
f
C
SA,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
v
e
r
co
m
es
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
SVMs,
th
er
eb
y
a
ch
iev
in
g
h
ig
h
er
ac
c
u
r
ac
y
wh
ile
m
ain
tain
in
g
c
o
m
p
u
tatio
n
al
e
f
f
icien
cy
.
T
h
is
s
tu
d
y
ai
m
s
to
d
etec
t
m
a
lar
ia
b
y
class
if
y
in
g
m
icr
o
s
co
p
ic
b
lo
o
d
s
m
ea
r
im
a
g
es
in
to
p
ar
asit
ized
an
d
u
n
in
f
ec
ted
ce
ll
ca
teg
o
r
ie
s
b
ased
o
n
v
is
u
al
f
ea
tu
r
es.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
was
t
ested
o
n
th
e
p
u
b
lic
m
alar
ia
ce
ll im
ag
e
d
ataset
an
d
co
m
p
ar
e
d
with
th
e
b
aselin
e
p
er
f
o
r
m
a
n
ce
o
f
s
tan
d
ar
d
SVM,
SVM
o
p
tim
ized
b
y
a
g
en
etic
alg
o
r
ith
m
(
GA)
,
an
d
th
e
KNN
cla
s
s
if
ier
.
T
h
e
m
o
d
el
p
ip
elin
e
in
clu
d
es
th
e
im
ag
e
p
r
ep
r
o
ce
s
s
in
g
,
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
,
th
e
h
y
b
r
id
k
er
n
el
-
b
ased
SVM
class
if
icatio
n
,
th
e
h
y
p
e
r
p
ar
am
eter
o
p
ti
m
izatio
n
v
ia
C
SA,
an
d
th
e
m
o
d
el
ev
alu
atio
n
.
T
h
er
e
ar
e
s
ev
er
al
co
n
tr
ib
u
tio
n
s
f
r
o
m
t
h
is
s
tu
d
y
,
n
am
ely
:
i
)
p
r
o
p
o
s
in
g
a
n
ew
f
r
am
ewo
r
k
o
f
SVM
th
at
in
te
g
r
ates
m
u
lti
-
k
er
n
el,
n
am
ely
R
B
F
an
d
h
is
to
g
r
am
in
ter
s
ec
tio
n
,
s
o
th
at
it
ca
n
ca
p
tu
r
e
b
o
th
tex
tu
r
e
an
d
co
lo
r
f
ea
tu
r
es
i
n
b
l
o
o
d
s
m
ea
r
im
ag
es,
ii
)
d
eter
m
in
in
g
th
e
o
p
ti
m
al
p
ar
am
eter
s
o
f
C
an
d
g
am
m
a
in
SVM
a
u
to
m
atica
lly
u
s
in
g
C
SA
,
an
d
iii
)
co
m
b
in
e
c
o
lo
r
h
is
to
g
r
am
an
d
te
x
tu
r
e
-
b
ased
f
ea
tu
r
es
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
e
p
ap
er
is
o
r
g
an
ize
d
as
f
o
llo
ws.
Sectio
n
2
o
u
tlin
es
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
Sectio
n
3
p
r
esen
ts
th
e
d
ataset
an
d
ex
p
e
r
im
en
tal
r
esu
l
ts
.
Sectio
n
4
co
n
clu
d
es th
e
p
a
p
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
3
1
6
-
1
3
2
6
1318
2.
M
E
T
H
O
D
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
a
f
r
am
e
wo
r
k
,
h
y
b
r
i
d
k
e
r
n
el
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
HKSVM
)
-
C
SA,
f
o
r
an
im
p
r
o
v
e
d
SVM
m
o
d
el
th
at
in
t
eg
r
ates
a
h
y
b
r
id
k
er
n
el
f
u
n
ctio
n
an
d
h
y
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
v
ia
th
e
C
SA
to
en
h
an
ce
class
if
icatio
n
p
er
f
o
r
m
an
ce
f
o
r
m
alar
ia
-
in
f
ec
ted
r
ed
b
lo
o
d
ce
lls
in
m
icr
o
s
co
p
ic
im
ag
es.
T
h
e
m
eth
o
d
o
l
o
g
ical
p
ip
elin
e
co
m
p
r
is
es
f
iv
e
k
ey
s
tag
es:
d
ataset
p
r
ep
ar
atio
n
,
f
ea
tu
r
e
ex
t
r
ac
tio
n
,
co
n
s
tr
u
ctio
n
o
f
a
HKSVM
,
C
S
A
-
b
ased
h
y
p
e
r
p
ar
am
eter
tu
n
i
n
g
,
an
d
co
m
p
r
eh
en
s
iv
e
m
o
d
el
ev
alu
atio
n
.
T
h
e
o
v
er
all
f
r
am
ewo
r
k
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
s
h
o
wn
in
Fig
u
r
e
1
.
D
a
t
a
P
r
e
p
a
r
a
t
i
o
n
F
e
a
t
u
r
e
Ex
t
r
a
c
t
i
o
n
(
G
LC
M
a
n
d
C
o
l
o
r
H
i
s
t
o
g
r
a
m
)
H
y
b
r
i
d
-
K
e
r
n
e
l
S
V
M
(
R
B
F
a
n
d
H
i
s
t
o
g
r
a
m
I
n
t
e
r
s
e
c
t
i
o
n
)
H
y
p
e
r
p
a
r
a
m
e
t
e
r
O
p
t
i
m
i
z
a
t
i
o
n
(
C
S
A
)
M
o
d
e
l
E
v
a
l
u
a
t
i
o
n
(
A
c
c
u
r
a
c
y
,
S
e
n
s
i
t
i
v
i
t
y
,
S
p
e
c
i
f
i
c
a
t
i
o
n
,
A
U
C
)
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
2
.
1
.
Da
t
a
prepa
ra
t
i
o
n
T
h
is
s
tu
d
y
u
s
ed
a
s
u
b
s
et
o
f
t
h
e
p
u
b
licly
av
ailab
le
m
alar
ia
ce
ll
im
ag
es
d
ataset
f
r
o
m
Ka
g
g
le
[
2
5
]
.
Fro
m
th
e
2
7
,
5
5
8
im
a
g
es,
th
is
s
tu
d
y
u
s
es
o
n
ly
3
,
0
0
0
im
a
g
es
p
er
class
(
p
ar
asit
ized
an
d
u
n
i
n
f
ec
ted
)
t
o
cr
ea
te
a
b
alan
ce
d
,
co
m
p
u
tatio
n
ally
m
a
n
ag
ea
b
le
d
ataset
(
Fig
u
r
e
2
)
.
T
h
is
s
u
b
s
et
s
ize
p
r
o
v
id
es
s
u
f
f
icien
t
v
ar
iab
ilit
y
f
o
r
r
eliab
le
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
class
if
icatio
n
wh
ile
k
ee
p
in
g
th
e
C
SA
-
b
ased
h
y
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
co
m
p
u
tatio
n
ally
f
ea
s
ib
le.
T
h
e
im
ag
es
wer
e
ch
o
s
en
b
ased
o
n
th
eir
o
r
d
er
in
th
e
d
atase
t
d
ir
ec
to
r
y
,
as
th
e
p
r
im
ar
y
o
b
jectiv
e
at
th
is
s
tag
e
was
to
estab
lis
h
a
co
n
s
is
ten
t,
r
ep
r
esen
tativ
e
s
u
b
s
et
f
o
r
in
itial
ex
p
er
im
en
tatio
n
.
T
o
en
s
u
r
e
co
n
s
is
ten
cy
an
d
r
ed
u
ce
co
m
p
u
tatio
n
al
lo
a
d
,
s
ev
er
al
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
wer
e
a
p
p
lied
.
E
ac
h
im
ag
e
was
s
ca
led
to
1
2
8
×1
2
8
p
ix
els
b
ef
o
r
e
f
u
r
th
er
p
r
o
ce
s
s
in
g
.
C
o
lo
r
in
f
o
r
m
atio
n
is
p
r
eser
v
ed
in
th
e
R
GB
f
o
r
m
at
f
o
r
co
lo
r
-
b
ased
f
ea
tu
r
e
ex
tr
ac
tio
n
,
wh
ile
a
g
r
ay
s
ca
le
v
er
s
io
n
is
also
g
en
er
ated
f
o
r
tex
tu
r
e
an
aly
s
is
.
No
ad
d
itio
n
al
d
en
o
is
in
g
o
r
c
o
n
tr
ast
en
h
a
n
ce
m
en
t
is
a
p
p
li
ed
,
en
s
u
r
i
n
g
th
at
th
e
n
atu
r
al
ch
ar
ac
ter
o
f
b
l
o
o
d
s
m
ea
r
s
am
p
les is
m
ain
tain
ed
.
Fig
u
r
e
2
s
h
o
ws
th
e
v
is
u
al
ap
p
ea
r
an
ce
o
f
b
lo
o
d
s
m
ea
r
im
a
g
es;
Fig
u
r
e
2
(
a)
d
is
p
lay
s
a
p
ar
asit
ized
im
ag
e,
a
r
ed
b
l
o
o
d
ce
ll
c
o
n
tai
n
in
g
m
alar
ia
p
ar
asit
es
(
P
la
s
mo
d
iu
m
)
,
m
ar
k
e
d
b
y
s
m
all
co
lo
r
ed
s
tr
u
ctu
r
es.
T
h
is
s
m
all
s
tr
u
ctu
r
e
o
f
ten
ap
p
ea
r
s
as
a
r
in
g
/b
an
d
/cr
escen
t
(
d
ep
e
n
d
in
g
o
n
th
e
s
tag
e
o
f
d
ev
elo
p
m
en
t)
.
Fig
u
r
e
2
(
b
)
s
h
o
ws
an
u
n
in
f
ec
ted
im
a
g
e
o
f
a
h
ea
lth
y
,
n
o
r
m
al
r
e
d
b
lo
o
d
ce
ll,
g
en
er
ally
u
n
if
o
r
m
i
n
b
i
co
n
ca
v
e
d
is
k
s
h
ap
e
an
d
s
h
o
win
g
n
o
f
o
r
eig
n
s
tr
u
ct
u
r
es o
r
d
e
f
o
r
m
ities
.
(
a)
(
b
)
Fig
u
r
e
2
.
B
lo
o
d
s
m
ea
r
im
ag
es
of
(
a)
p
ar
asit
ized
im
ag
e
a
n
d
(
b
)
u
n
in
f
ec
ted
im
ag
e
2
.
2
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
u
s
es
a
co
m
b
in
atio
n
o
f
co
lo
r
h
is
to
g
r
am
f
ea
tu
r
es
an
d
tex
tu
r
e
-
b
ase
d
f
ea
tu
r
es
o
b
tain
ed
f
r
o
m
th
e
g
r
ay
-
lev
el
co
-
o
cc
u
r
r
e
n
ce
m
at
r
ix
(
GL
C
M)
.
T
h
e
co
m
b
in
atio
n
o
f
th
e
two
m
et
h
o
d
s
was
ch
o
s
en
to
ca
p
tu
r
e
th
e
ch
r
o
m
a
tic
an
d
s
tr
u
ctu
r
al
v
ar
iatio
n
s
th
at
in
d
icate
P
la
s
mo
d
iu
m
in
f
e
ctio
n
.
T
h
e
s
tep
s
o
f
f
ea
tu
r
e
ex
t
r
ac
tio
n
a
r
e
s
h
o
wn
i
n
Fig
u
r
e
3
.
I
n
ex
tr
ac
tin
g
th
e
co
lo
r
h
is
to
g
r
am
f
ea
tu
r
e,
th
e
i
n
p
u
t
R
GB
im
ag
e
is
s
p
lit in
to
th
r
ee
ch
an
n
els (
R
,
G,
an
d
B
)
.
E
ac
h
ch
a
n
n
el
is
th
en
ca
lcu
lated
an
d
n
o
r
m
alize
d
to
3
2
b
in
s
,
r
esu
ltin
g
in
a
to
tal
o
f
9
6
co
lo
r
f
ea
t
u
r
es.
B
ased
o
n
th
ese
co
lo
r
f
ea
t
u
r
e
s
,
s
tain
in
g
p
atter
n
s
,
a
n
d
cy
to
p
lasmic
ch
an
g
es
in
in
f
ec
ted
ce
lls
,
in
f
ec
ted
ce
lls
will b
e
id
en
tifie
d
,
as r
ef
lecte
d
in
th
e
g
lo
b
al
i
n
ten
s
ity
d
is
tr
ib
u
tio
n
.
Me
an
wh
ile,
in
th
e
tex
tu
r
e
f
ea
tu
r
e
ex
tr
ac
tio
n
s
tep
,
th
e
in
p
u
t
im
ag
e
is
co
n
v
er
ted
to
g
r
ay
s
c
ale.
T
h
en
,
th
e
GL
C
M
is
ca
lcu
lated
with
a
p
ix
el
d
is
tan
ce
o
f
1
an
d
an
an
g
u
lar
d
ir
ec
tio
n
o
f
0
°,
u
s
in
g
t
h
e
f
ea
tu
r
e
d
escr
ip
to
r
s
co
n
tr
ast,
co
r
r
elatio
n
,
en
er
g
y
,
an
d
h
o
m
o
g
e
n
eity
.
T
h
ese
f
o
u
r
f
ea
tu
r
es
will
p
r
o
v
id
e
a
co
m
p
r
eh
en
s
iv
e
o
v
e
r
v
iew
o
f
th
e
lo
ca
l
s
tr
u
ctu
r
e'
s
tex
tu
r
e.
T
h
e
co
m
b
in
atio
n
o
f
th
e
t
wo
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
p
r
o
d
u
ce
s
a
f
in
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
ke
r
n
el
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
w
ith
cu
ck
o
o
s
ea
r
ch
o
p
timiz
a
tio
n
fo
r
…
(
S
r
i H
u
n
in
g
A
n
w
a
r
in
in
g
s
ih
)
1319
f
ea
tu
r
e
v
ec
to
r
with
1
0
0
d
im
e
n
s
io
n
s
,
co
n
s
is
tin
g
o
f
9
6
c
o
lo
r
s
f
r
o
m
th
e
f
ea
t
u
r
e
c
o
lo
r
h
is
to
g
r
am
s
tag
e
an
d
f
o
u
r
tex
tu
r
es
f
r
o
m
th
e
te
x
tu
r
e
f
ea
tu
r
e
ex
tr
ac
tio
n
s
tag
e.
T
h
e
f
i
n
al
f
ea
tu
r
e
v
ec
to
r
will
later
s
er
v
e
as
th
e
in
p
u
t
to
t
h
e
SVM
class
if
ier
.
R
G
B
I
m
a
g
e
H
i
s
to
g
r
a
m
R
G
B
G
r
a
y
s
c
a
l
e
i
m
a
g
e
Fin
a
l
Fe
a
t
u
r
e
I
n
d
e
x
G
L
C
M
M
a
t
r
ix
C
o
n
tr
a
s
t
C
o
r
r
e
l
a
ti
o
n
E
n
er
g
y
H
o
m
o
g
en
ei
ty
T
e
x
tu
r
e
F
e
a
tu
r
e
s
V
ec
to
r
G
LC
M
M
a
tr
i
x
C
o
lo
r
Fe
a
t
u
r
e
V
e
c
t
o
r
(
9
6
d
im
)
Fig
u
r
e
3
.
Step
o
f
f
ea
tu
r
e
ex
tr
a
ctio
n
2
.
3
.
H
y
brid k
er
nel su
pp
o
rt
v
ec
t
o
r
m
a
chine
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
e
m
p
lo
y
s
a
h
y
b
r
i
d
k
er
n
el
f
u
n
ctio
n
th
at
in
teg
r
ates
th
e
R
B
F
an
d
h
is
to
g
r
am
in
ter
s
ec
tio
n
k
er
n
els,
as
s
h
o
w
n
in
Fig
u
r
e
4
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
s
tar
ts
with
th
e
f
in
al
f
ea
tu
r
e
in
d
ex
v
alu
es
o
b
tain
ed
f
r
o
m
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
s
tag
e,
wh
ich
will
b
e
u
s
ed
in
th
e
R
B
F
k
er
n
el
an
d
th
e
h
is
to
g
r
am
in
ter
s
ec
tio
n
k
er
n
el.
T
h
e
r
esu
lt
s
o
f
b
o
th
will th
e
n
b
e
c
o
m
b
in
e
d
to
o
b
tai
n
a
k
er
n
el
co
m
b
in
ati
o
n
.
Fin
a
l
Fe
a
t
u
r
e
I
n
d
e
x
R
B
F
K
e
r
n
e
l
H
is
t
o
g
r
a
m
I
n
t
e
r
s
e
c
t
io
n
k
e
r
n
e
l
W
e
i
g
h
t
e
d
c
o
m
b
in
a
t
io
n
C
o
m
b
in
e
d
k
e
r
n
e
l
Fig
u
r
e
4
.
Step
o
f
HKSVM
T
h
e
f
in
al
f
ea
tu
r
e
v
ec
to
r
r
esu
lt
in
g
f
r
o
m
th
e
p
r
e
v
io
u
s
s
tep
will
s
er
v
e
as
th
e
in
p
u
t
f
o
r
ca
lc
u
latin
g
ea
ch
k
er
n
el.
T
h
e
R
B
F
k
er
n
el
will
b
e
ca
lcu
lated
u
s
in
g
(
1
)
wh
ile
th
e
k
er
n
el
h
is
to
g
r
a
m
in
ter
s
ec
tio
n
will
b
e
ca
lcu
lated
u
s
in
g
(
2
)
.
T
h
e
r
esu
lts
o
f
th
e
two
ca
lcu
latio
n
s
will
th
en
b
e
co
m
b
in
ed
u
s
in
g
(
3
)
,
wh
ich
e
m
p
lo
y
s
a
weig
h
ted
co
m
b
in
atio
n
a
p
p
r
o
ac
h
.
T
h
e
p
r
o
p
o
r
tio
n
s
o
f
th
e
weig
h
ts
o
f
b
o
th
a
r
e
eq
u
al
to
en
h
a
n
ce
th
e
d
is
cr
im
in
ativ
e
ca
p
ac
ity
o
f
SVM
class
if
ier
s
.
C
o
m
b
in
in
g
th
e
two
k
er
n
els r
esu
lts
in
a
s
in
g
le
k
er
n
el.
(
,
)
=
(
−
‖
−
‖
2
)
(
1
)
(
,
)
=
∑
(
,
)
=
1
(
2
)
W
h
er
e
,
∈
ℝ
ar
e
f
ea
tu
r
e
v
ec
to
r
s
an
d
γ
is
th
e
k
er
n
el
wid
t
h
p
ar
am
ete
r
o
p
tim
ized
u
s
in
g
th
e
C
SA.
ℎ
(
,
)
=
.
(
,
)
+
(
1
−
)
.
(
,
)
(
3
)
W
h
e
r
e
∈
[
0
,
1
]
i
s
w
e
i
g
h
t
c
o
e
f
f
i
c
i
e
n
t
,
α
,
s
e
t
t
o
0
.
5
f
o
r
e
a
c
h
k
e
r
n
e
l
,
i
n
d
i
c
a
t
i
n
g
t
h
a
t
e
a
c
h
k
e
r
n
e
l
c
o
n
t
r
i
b
u
t
e
s
e
q
u
a
l
l
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
3
1
6
-
1
3
2
6
1320
2
.
4
.
H
y
perpa
ra
m
e
t
er
o
ptim
i
za
t
io
n
I
n
th
is
s
tu
d
y
,
th
e
C
SA
is
u
s
ed
to
o
p
tim
ize
th
e
SVM
h
y
p
e
r
p
ar
am
eter
s
(
C
an
d
g
am
m
a)
.
T
h
e
s
tep
s
p
er
f
o
r
m
ed
at
th
is
s
tag
e
ar
e
p
r
esen
ted
in
Fig
u
r
e
5
.
T
h
e
f
ir
s
t
s
tep
is
th
e
in
itializat
io
n
o
f
t
h
e
n
est,
wh
er
e
th
e
s
o
lu
tio
n
s
o
u
g
h
t
is
a
p
air
o
f
p
a
r
am
eter
v
alu
es
C
an
d
g
am
m
a.
T
h
e
f
itn
ess
v
alu
e
will
th
en
b
e
ca
lcu
lated
.
I
f
th
e
f
itn
ess
v
alu
e
is
wo
r
s
e,
th
en
C
SA
will
u
p
d
ate
t
h
em
v
ia
L
év
y
f
lig
h
ts
a
n
d
r
ep
lace
th
e
w
o
r
s
t
s
o
lu
tio
n
s
u
s
in
g
a
d
is
co
v
er
y
p
r
o
b
ab
ilit
y
m
ec
h
an
is
m
[
2
3
]
.
T
h
is
p
r
o
ce
s
s
will
b
e
r
ep
ea
ted
u
n
til
th
e
o
p
tim
al
s
o
lu
tio
n
is
ac
h
iev
ed
,
s
p
ec
if
ically
,
th
e
b
est C
an
d
g
a
m
m
a
v
alu
e
p
air
s
.
T
h
e
o
b
jectiv
e
f
itn
ess
f
u
n
ctio
n
is
th
e
SVM
m
o
d
el'
s
clas
s
if
icatio
n
ac
cu
r
ac
y
o
n
th
e
v
alid
atio
n
d
ata.
E
ac
h
s
o
lu
tio
n
p
air
(
C
an
d
g
am
m
a)
will
b
e
tr
ain
ed
o
n
th
e
tr
ain
in
g
d
ata,
an
d
its
ac
cu
r
ac
y
in
th
e
v
alid
atio
n
d
ata
will
th
en
b
e
ca
lcu
lated
as
a
f
itn
ess
v
alu
e.
Acc
u
r
ac
y
d
eter
m
in
atio
n
is
a
n
o
b
jectiv
e
f
u
n
c
tio
n
th
at
d
eter
m
in
es
h
y
p
er
p
ar
am
eter
v
alu
es
b
ased
o
n
th
e
m
o
d
el'
s
g
en
er
aliza
tio
n
ca
p
ab
ilit
ies.
T
h
e
o
b
jectiv
e
f
u
n
ctio
n
is
ex
p
r
ess
ed
as
(
4
)
.
I
n
th
is
s
tu
d
y
,
C
SA w
as r
u
n
with
1
5
n
ests
,
a
d
is
co
v
er
y
r
ate
o
f
0
.
2
5
,
an
d
1
0
iter
atio
n
s
.
(
,
)
=
1
∑
(
̂
=
)
=
1
(
4
)
W
h
er
e
N
d
en
o
tes
th
e
n
u
m
b
er
o
f
v
alid
atio
n
s
am
p
les,
̂
is
th
e
p
r
ed
icted
lab
el,
is
th
e
ac
tu
al
lab
el,
an
d
δ(
.
)
is
th
e
Kr
o
n
ec
k
er
d
elta
f
u
n
ctio
n
,
wh
ich
r
etu
r
n
s
1
if
th
e
co
n
d
itio
n
is
tr
u
e
a
n
d
0
o
th
er
wis
e.
T
h
is
f
u
n
ctio
n
d
ir
ec
tly
esti
m
ates c
la
s
s
if
icatio
n
ac
cu
r
ac
y
,
g
u
i
d
in
g
th
e
C
SA in
s
ea
r
ch
in
g
f
o
r
o
p
tim
al
p
ar
am
eter
v
alu
es.
I
n
it
ia
l
N
e
s
t
s
L
e
v
y
F
li
g
h
t
Fi
t
n
e
s
s
E
v
a
lu
a
t
io
n
Se
le
c
t
io
n
a
n
d
R
e
p
la
c
e
m
e
n
t
B
e
s
t
So
lu
t
io
n
Fig
u
r
e
5
.
Step
o
f
h
y
p
er
p
ar
am
e
ter
o
p
tim
izatio
n
2
.
5
.
M
o
del e
v
a
lua
t
i
o
n
Af
ter
th
e
o
p
tim
al
h
y
p
er
p
ar
a
m
eter
s
ar
e
id
en
tifie
d
v
ia
C
S
A,
th
e
i
m
p
r
o
v
ed
SVM
m
o
d
e
l
is
tr
ain
ed
u
s
in
g
th
e
en
tire
tr
ain
in
g
s
et.
T
h
e
m
o
d
el
is
th
en
ev
alu
ate
d
o
n
a
h
o
ld
-
o
u
t
test
s
et
u
s
in
g
s
tan
d
ar
d
m
etr
ics
[
2
6
]
,
n
am
ely
ac
cu
r
ac
y
,
s
en
s
itiv
ity
/r
ec
all,
s
p
ec
if
icity
,
an
d
th
e
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
AUC).
Sen
s
it
iv
ity
is
th
e
r
atio
o
f
tr
u
e
-
p
o
s
itiv
e
p
r
e
d
ictio
n
s
to
th
e
to
tal
n
u
m
b
er
o
f
tr
u
e
-
p
o
s
itiv
e
s
am
p
les;
in
o
th
er
wo
r
d
s
,
it
m
ea
s
u
r
es
th
e
m
o
d
el'
s
ab
ilit
y
to
ac
cu
r
ately
i
d
en
tify
p
ar
asit
ized
ce
lls
.
Sen
s
itiv
ity
ca
n
b
e
ca
lcu
lated
u
s
in
g
(
5
)
.
=
+
(
5
)
Sp
ec
if
icity
is
th
e
r
atio
o
f
tr
u
e
-
n
eg
ativ
e
p
r
ed
ictio
n
s
to
t
h
e
n
u
m
b
er
o
f
tr
u
ly
n
eg
ativ
e
s
am
p
le
s
.
I
n
o
th
er
wo
r
d
s
,
s
p
ec
if
icity
m
ea
s
u
r
es
th
e
m
o
d
el'
s
ab
ilit
y
to
co
r
r
ec
tly
id
en
tify
u
n
i
n
f
ec
ted
ce
lls
.
Sp
ec
if
icity
ca
n
b
e
ca
lcu
lated
u
s
in
g
(
6
)
.
=
+
(
6
)
Acc
u
r
ac
y
r
ef
e
r
s
to
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tl
y
d
etec
ted
p
o
s
itiv
e
an
d
n
e
g
ativ
e
r
esu
lts
.
Acc
u
r
ac
y
s
er
v
es
as
a
b
en
ch
m
ar
k
f
o
r
ev
alu
atin
g
an
d
co
m
p
ar
in
g
d
iag
n
o
s
tic
m
eth
o
d
s
.
A
h
ig
h
ac
c
u
r
a
cy
v
alu
e
in
d
icate
s
th
at
th
e
m
o
d
el
is
h
ig
h
ly
ef
f
ec
tiv
e
in
class
if
icatio
n
[
2
6
]
.
Acc
u
r
ac
y
ca
n
b
e
ca
lcu
lated
u
s
in
g
(
7
)
.
=
+
+
+
+
(
7
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
ke
r
n
el
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
w
ith
cu
ck
o
o
s
ea
r
ch
o
p
timiz
a
tio
n
fo
r
…
(
S
r
i H
u
n
in
g
A
n
w
a
r
in
in
g
s
ih
)
1321
W
h
er
e
T
P
in
d
icat
es
co
r
r
ec
t
p
o
s
itiv
e
p
r
ed
ictio
n
s
,
FP
d
e
n
o
tes
in
co
r
r
ec
t
p
o
s
itiv
e
p
r
ed
icti
o
n
s
,
FN
r
ep
r
esen
ts
m
is
s
ed
p
o
s
itiv
e
ca
s
es,
an
d
T
N
in
d
icate
s
co
r
r
ec
t
n
eg
ativ
e
p
r
ed
ictio
n
s
.
AUC
is
a
wid
ely
u
s
ed
m
etr
ic
f
o
r
ev
alu
atin
g
b
in
ar
y
class
if
icatio
n
m
o
d
els,
r
ef
lectin
g
t
h
e
tr
ad
e
-
o
f
f
b
etwe
en
th
e
tr
u
e
p
o
s
itiv
e
r
at
e
(
T
PR
)
an
d
t
h
e
f
alse p
o
s
itiv
e
r
ate
(
FP
R
)
in
d
is
tin
g
u
is
h
in
g
p
o
s
itiv
e
an
d
n
eg
at
iv
e
class
es
[
2
7
]
.
Ad
d
itio
n
ally
,
co
n
f
u
s
io
n
m
atr
i
ce
s
an
d
r
ec
eiv
er
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
(
R
O
C
)
cu
r
v
es
ar
e
p
lo
tted
to
p
r
o
v
id
e
v
is
u
al
in
s
ig
h
ts
in
to
class
if
icat
io
n
p
er
f
o
r
m
a
n
ce
.
All
ev
alu
atio
n
s
ar
e
co
n
d
u
c
ted
u
n
d
er
id
en
tical
co
n
d
itio
n
s
to
en
s
u
r
e
a
f
air
co
m
p
ar
is
o
n
with
th
e
b
aselin
e
m
o
d
el.
T
h
e
b
aselin
e
class
if
ier
e
m
p
lo
y
ed
in
th
is
s
tu
d
y
is
an
R
B
F
-
SVM
with
s
cik
i
t
-
lear
n
’
s
d
ef
au
lt
p
ar
am
eter
s
(
C
=1
.
0
,
γ
=
‘
s
ca
le’
)
im
p
l
em
en
ted
th
r
o
u
g
h
a
Stan
d
ar
d
Scaler
–
SVM
p
ip
elin
e.
Oth
er
b
aselin
e
m
o
d
els
in
cl
u
d
e
a
KNN
class
if
ier
(
=3
)
an
d
SVM
-
GA,
b
o
th
im
p
lem
en
ted
th
r
o
u
g
h
Stan
d
ar
d
Scaler
–
b
ased
p
ip
elin
es.
T
h
e
GA
u
s
ed
a
p
o
p
u
latio
n
o
f
1
5
,
1
0
g
en
er
atio
n
s
,
an
d
a
m
u
tatio
n
r
ate
o
f
0
.
1
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
s
et
des
cr
iptio
n
T
h
is
s
tu
d
y
u
tili
ze
s
6
,
0
0
0
R
GB
im
ag
es
f
r
o
m
t
h
e
m
alar
i
a
ce
ll
im
ag
es
d
ataset
d
e
v
elo
p
ed
b
y
th
e
Natio
n
al
L
ib
r
ar
y
o
f
Me
d
icin
e.
T
h
e
d
ataset
is
ev
en
ly
s
p
lit
in
t
o
two
class
es,
n
am
ely
p
ar
asit
i
ze
d
an
d
u
n
i
n
f
ec
ted
.
E
ac
h
im
ag
e
is
1
2
8
×1
2
8
p
ix
els
in
s
ize
an
d
was c
ap
tu
r
e
d
u
s
in
g
s
tan
d
ar
d
lig
h
t m
icr
o
s
co
p
y
.
3
.
2
.
E
x
perim
ent
a
l set
up
All
ex
p
er
im
en
tal
p
r
o
ce
d
u
r
es
wer
e
co
n
d
u
cted
i
n
Py
th
o
n
3
.
1
2
.
0
an
d
th
e
s
cik
it
-
lear
n
an
d
Op
en
C
V
lib
r
ar
ies.
T
h
e
f
o
llo
win
g
r
esu
lts
wer
e
o
b
tain
ed
o
n
a
PC
with
an
I
n
tel
C
o
r
e
i5
-
8
2
5
0
U
C
PU
r
u
n
n
in
g
at
1
.
8
0
GHz
,
8
GB
DDR4
R
AM
,
an
d
an
NVI
DI
A
GeFo
r
ce
9
3
0
MX
GPU.
T
h
e
d
ataset
was
r
an
d
o
m
ly
s
p
lit
in
to
tr
ain
in
g
an
d
test
in
g
s
ets
at
an
8
0
:2
0
r
atio
.
Ad
d
itio
n
ally
,
2
0
%
o
f
th
e
tr
ain
in
g
s
et
was
f
u
r
th
er
d
iv
id
ed
i
n
to
a
v
alid
atio
n
s
et
f
o
r
h
y
p
er
p
ar
am
e
ter
o
p
tim
izatio
n
u
s
in
g
C
SA.
B
ef
o
r
e
ex
tr
ac
tin
g
f
ea
t
u
r
es,
im
ag
es we
r
e
u
n
if
o
r
m
ly
r
esized
to
1
2
8
×1
2
8
p
ix
els.
T
h
e
C
SA w
as c
o
n
f
ig
u
r
ed
with
f
o
llo
win
g
p
ar
am
eter
s
,
as sh
o
wn
in
T
ab
le
1
.
T
ab
le
1
.
C
SA’
s
p
ar
am
eter
s
P
a
r
a
me
t
e
r
s
V
a
l
u
e
N
u
mb
e
r
o
f
n
e
st
s
(
n
)
15
D
i
sco
v
e
r
y
r
a
t
e
(
p
a
)
0
.
2
5
N
u
mb
e
r
o
f
i
t
e
r
a
t
i
o
n
s
10
S
e
a
r
c
h
b
o
u
n
d
s
f
o
r
C
[
0
.
1
…
1
0
0
0
]
S
e
a
r
c
h
b
o
u
n
d
s
f
o
r
γ
[
1
0
-
5
.
.
.
1
]
3
.
3
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
T
o
v
alid
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
,
a
co
m
p
ar
ativ
e
a
n
aly
s
is
was
co
n
d
u
cte
d
b
etwe
en
th
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
th
e
co
m
p
ar
ato
r
m
eth
o
d
(
th
e
b
aselin
e
s
tan
d
ar
d
SVM
u
s
in
g
an
R
B
F
k
er
n
el,
KNN,
an
d
SVM
-
GA)
.
T
h
e
p
er
f
o
r
m
an
ce
m
etr
ics
u
s
ed
in
th
is
co
m
p
ar
is
o
n
in
cl
u
d
e
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
an
d
AUC.
Sen
s
iti
v
ity
r
ep
r
esen
ts
th
e
ab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
to
ac
c
u
r
ately
id
en
tify
ce
lls
in
f
ec
ted
with
m
alar
ia.
Sp
ec
if
icity
ev
alu
ates
th
e
ca
p
ab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
to
ac
cu
r
ately
class
if
y
u
n
in
f
ec
ted
ce
lls
.
AUC
i
s
a
m
etr
ic
th
at
r
ef
lects
h
o
w
ef
f
ec
tiv
ely
a
m
o
d
el
d
if
f
er
e
n
tiates
b
etwe
en
p
o
s
itiv
e
an
d
n
eg
ativ
e
class
es.
AUC
v
alu
es
r
an
g
e
f
r
o
m
0
to
1
,
with
h
ig
h
er
v
alu
es
co
r
r
esp
o
n
d
in
g
t
o
b
etter
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
A
v
alu
e
u
n
d
e
r
0
.
5
in
d
icate
s
p
o
o
r
p
er
f
o
r
m
an
ce
.
Ad
d
itio
n
ally
,
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
test
in
g
was
p
er
f
o
r
m
ed
to
e
v
alu
ate
m
o
d
el
p
er
f
o
r
m
an
ce
,
s
p
ec
if
ically
to
ass
es
s
s
tab
ili
ty
an
d
en
s
u
r
e
th
at
th
e
p
er
f
o
r
m
an
c
e
esti
m
ates w
er
e
m
o
r
e
r
ep
r
esen
t
ativ
e
o
f
th
e
o
v
er
all
d
ata.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
em
p
l
o
y
ed
a
h
y
b
r
id
k
e
r
n
el
(
R
B
F
an
d
h
is
to
g
r
am
in
ter
s
ec
tio
n
k
e
r
n
els),
with
α
=0
.
5
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
was
tr
ain
ed
an
d
test
ed
o
n
th
e
s
am
e
d
ata
s
p
lit.
T
h
e
co
m
p
a
r
ativ
e
p
er
f
o
r
m
an
ce
b
etwe
en
th
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
th
e
co
m
p
ar
at
o
r
m
eth
o
d
s
(
SVM
s
tan
d
ar
d
,
SVM
-
GA,
an
d
KNN)
f
o
r
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
is
p
r
esen
ted
i
n
T
ab
le
2
.
T
ab
le
2
.
C
o
m
p
a
r
ativ
e
p
er
f
o
r
m
an
ce
an
aly
s
is
b
etwe
en
th
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
co
m
p
ar
ato
r
m
eth
o
d
s
M
o
d
e
l
A
c
c
u
r
a
c
y
S
e
n
s
i
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
AUC
S
V
M
s
t
a
n
d
a
r
d
0
.
9
2
0
.
9
4
0
.
9
1
0
.
9
7
K
N
N
0
.
8
4
0
.
8
4
0
.
8
4
0
.
9
0
S
V
M
-
GA
0
.
7
4
0
.
5
4
0
.
9
5
0
.
8
3
Th
e
p
r
o
p
o
s
e
d
me
t
h
o
d
(
H
K
S
V
M
-
C
S
A
)
0
.
9
4
0
.
9
3
0
.
9
4
0
.
9
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
3
1
6
-
1
3
2
6
1322
T
ab
le
2
s
u
m
m
ar
izes
th
e
co
m
p
ar
ativ
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
(
HKSVM
-
C
S
A)
an
d
t
h
e
co
m
p
ar
ato
r
m
eth
o
d
s
o
n
f
o
u
r
k
ey
p
er
f
o
r
m
a
n
ce
m
etr
ics:
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
s
p
ec
if
ici
ty
,
an
d
AUC.
T
h
e
ex
p
er
im
en
tal
f
in
d
i
n
g
s
s
h
o
we
d
im
p
r
o
v
e
d
p
er
f
o
r
m
an
ce
f
o
r
th
e
HKSVM
-
C
SA
class
if
icati
o
n
c
o
m
p
ar
e
d
t
o
th
e
co
m
p
ar
ato
r
m
o
d
el.
HKSVM
-
C
SA
ac
h
iev
es
9
4
%
ac
cu
r
ac
y
,
s
ig
n
if
ican
tly
o
u
t
p
er
f
o
r
m
in
g
th
e
b
aselin
e.
T
h
is
d
em
o
n
s
tr
ates
th
at
in
teg
r
atin
g
h
y
b
r
id
k
er
n
el
f
u
n
ctio
n
s
with
C
SA
-
b
ased
h
y
p
er
p
a
r
a
m
eter
o
p
tim
izatio
n
s
ig
n
if
ican
tly
en
h
a
n
ce
s
th
e
class
if
icatio
n
ca
p
ab
ilit
ies o
f
b
lo
o
d
s
m
ea
r
im
ag
es.
B
ased
o
n
th
e
s
en
s
itiv
ity
m
ea
s
u
r
em
en
t,
HKSVM
-
C
SA
ac
h
iev
ed
a
0
.
9
3
,
s
u
r
p
ass
in
g
SV
M
-
GA
an
d
KNN.
T
h
is
im
p
r
o
v
em
en
t
is
cr
u
cial
in
m
e
d
ical
d
ia
g
n
o
s
is
,
wh
er
e
f
ailu
r
e
to
d
etec
t p
o
s
itiv
e
c
ases
h
as
a
p
r
o
f
o
u
n
d
im
p
ac
t
o
n
p
atien
t
ca
r
e.
I
n
th
e
s
p
ec
if
icity
m
ea
s
u
r
em
en
t,
H
KSVM
-
C
SA
ac
h
iev
ed
0
.
9
4
,
in
d
icatin
g
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
ef
f
ec
tiv
el
y
r
ed
u
ce
s
f
alse
p
o
s
itiv
es
an
d
th
er
eb
y
m
in
im
izes
th
e
r
is
k
o
f
m
is
d
iag
n
o
s
in
g
h
ea
lth
y
in
d
iv
id
u
als as in
f
ec
ted
.
Ad
d
itio
n
ally
,
in
t
h
e
AUC
m
et
r
ic,
HKSVM
-
C
SA
ac
h
iev
ed
0
.
9
8
,
o
u
tp
e
r
f
o
r
m
in
g
KNN
an
d
SVM
-
GA
wh
ile
co
m
p
ar
ab
le
with
SVM
s
tan
d
ar
d
(
Fig
u
r
e
6
)
.
An
AU
C
v
alu
e
o
f
0
.
9
8
i
n
d
icate
s
ex
c
ellen
t
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
in
d
icatin
g
th
at
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
ca
n
e
f
f
ec
t
iv
ely
d
is
tin
g
u
is
h
b
etwe
en
im
a
g
es
o
f
in
f
ec
ted
a
n
d
u
n
in
f
ec
ted
r
ed
b
lo
o
d
ce
lls
at
v
ar
io
u
s
d
ec
is
io
n
th
r
esh
o
l
d
s
.
T
h
e
AUC
r
esu
lts
f
u
r
th
er
v
alid
a
te
th
e
s
u
p
er
i
o
r
ity
o
f
th
e
HKSVM
-
C
SA
m
eth
o
d
.
B
ased
o
n
p
er
f
o
r
m
an
ce
m
ea
s
u
r
e
m
en
ts
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
r
em
ain
s
s
u
p
er
io
r
b
ec
au
s
e
it
o
f
f
er
s
a
m
o
r
e
b
al
an
ce
d
s
en
s
itiv
ity
–
s
p
ec
if
icity
t
r
ad
e
-
o
f
f
,
y
ield
s
h
ig
h
e
r
ac
cu
r
ac
y
,
ex
h
ib
its
lo
wer
f
o
ld
-
to
-
f
o
ld
v
ar
ia
b
ilit
y
,
an
d
b
en
e
f
its
f
r
o
m
ad
a
p
tiv
e
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
v
ia
C
SA.
T
h
ese
ch
ar
ac
ter
is
tics
m
ak
e
it m
o
r
e
r
e
liab
le
f
o
r
r
ea
l
-
w
o
r
ld
m
alar
ia
d
etec
tio
n
task
s
.
Fig
u
r
e
6
.
R
OC
cu
r
v
e
co
m
p
ar
i
s
o
n
B
ased
o
n
th
e
m
ea
n
R
OC
ac
r
o
s
s
all
f
o
ld
s
(
Fig
u
r
e
6
)
,
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
'
s
cu
r
v
e
is
at
th
e
to
p
f
o
r
alm
o
s
t
th
e
en
tire
r
an
g
e
o
f
f
alse
-
p
o
s
itiv
e
r
ates.
T
h
e
AUC
is
v
er
y
h
ig
h
,
with
a
n
av
er
a
g
e
a
cc
u
r
ac
y
o
f
0
.
9
8
1
5
ac
r
o
s
s
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
an
d
a
s
tan
d
ar
d
d
ev
iatio
n
o
f
0
.
0
0
4
6
.
T
h
e
r
esu
lts
co
n
f
ir
m
th
a
t
th
e
m
o
d
el
s
h
o
ws
r
o
b
u
s
t
s
tab
ilit
y
an
d
is
n
o
t
s
ig
n
if
ican
tly
af
f
ec
ted
b
y
ch
a
n
g
es
in
th
e
d
ata.
T
h
e
n
ar
r
o
west
s
h
a
d
ed
ar
ea
s
h
o
ws
th
at
th
e
f
o
ld
s
ar
e
v
er
y
s
tab
le.
I
n
co
n
tr
ast,
SVM
-
GA
s
h
o
ws
a
wid
e
r
an
g
e
o
f
s
h
a
d
in
g
,
i
n
d
ic
atin
g
h
ig
h
v
ar
ian
ce
ac
r
o
s
s
f
o
ld
s
(
s
o
m
etim
es
g
o
o
d
an
d
s
o
m
etim
es
b
a
d
)
.
B
ased
o
n
t
h
e
m
ea
n
R
OC
v
alu
e,
HKSVM
-
C
SA
d
em
o
n
s
tr
ates
th
e
s
tr
o
n
g
est
d
i
s
cr
im
in
ativ
e
ab
ilit
y
,
with
th
e
h
ig
h
est
m
ea
n
AUC
an
d
th
e
s
m
allest
f
o
ld
-
to
-
f
o
ld
v
ar
ian
ce
,
in
d
icatin
g
r
o
b
u
s
t a
n
d
co
n
s
is
ten
t p
er
f
o
r
m
an
ce
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
,
as
s
h
o
wn
in
Fig
u
r
e
7
,
ca
n
s
h
o
w
th
e
co
m
p
ar
is
o
n
o
f
tr
u
e
p
o
s
itiv
e
,
f
alse
p
o
s
itiv
e
,
f
alse
n
eg
ativ
e
,
an
d
tr
u
e
n
eg
ativ
e
v
alu
es
b
etwe
en
th
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
th
e
co
m
p
ar
ato
r
m
eth
o
d
s
(
SVM
s
tan
d
ar
d
in
Fig
u
r
e
7
(
a
)
,
KNN
in
Fig
u
r
e
7
(
b
)
,
an
d
SVM
-
GA
in
Fig
u
r
e
7
(
c)
)
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
(
Fig
u
r
e
7
(
d
)
)
s
h
o
we
d
a
s
ig
n
if
i
ca
n
t
in
cr
ea
s
e
in
th
e
tr
u
e
p
o
s
itiv
ity
an
d
tr
u
e
n
eg
ativ
e
v
alu
es.
T
h
is
in
d
icate
s
th
at,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
ke
r
n
el
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
w
ith
cu
ck
o
o
s
ea
r
ch
o
p
timiz
a
tio
n
fo
r
…
(
S
r
i H
u
n
in
g
A
n
w
a
r
in
in
g
s
ih
)
1323
co
m
p
ar
ed
to
th
e
o
th
er
,
HKS
VM
-
C
SA
i
s
m
o
r
e
ac
cu
r
ate
in
d
etec
tin
g
ca
s
es
o
f
m
alar
ia
th
at
ar
e
tr
u
ly
in
f
ec
ted
(
p
ar
asit
ized
)
an
d
th
o
s
e
th
at
a
r
e
co
m
p
letely
u
n
i
n
f
ec
ted
.
Ad
d
itio
n
ally
,
th
er
e
was
a
s
ig
n
if
ic
an
t
d
ec
r
ea
s
e
i
n
th
e
f
alse
p
o
s
itiv
e
an
d
f
alse
n
eg
ativ
e
v
alu
es.
T
h
is
d
em
o
n
s
tr
ates
th
at
HKSVM
-
C
SA
is
h
ig
h
ly
r
o
b
u
s
t
an
d
r
eliab
le
in
class
if
icatio
n
co
m
p
ar
ed
to
th
e
s
tan
d
ar
d
SVM.
T
h
is
p
er
f
o
r
m
an
ce
im
p
r
o
v
e
m
en
t
en
s
u
r
es
th
at
m
alar
ia
ca
s
es
ar
e
ac
cu
r
ately
d
etec
ted
w
h
ile
m
in
i
m
izin
g
th
e
r
is
k
o
f
m
is
d
iag
n
o
s
is
in
u
n
in
f
ec
ted
in
d
iv
id
u
als.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
7
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
(
a)
SVM
s
tan
d
ar
d
,
(
b
)
KNN,
(
c
)
SVM
-
GA,
an
d
(
d
)
HKSVM
-
C
SA
T
h
is
s
tu
d
y
also
co
n
d
u
cted
s
tatis
tical
tes
tin
g
u
s
in
g
th
e
p
air
e
d
t
-
test
(
T
ab
le
3
)
.
B
o
th
we
r
e
u
s
ed
to
test
th
e
s
tatis
tical
s
ig
n
if
ican
ce
o
f
d
if
f
er
en
ce
s
in
p
er
f
o
r
m
an
ce
b
e
twee
n
m
o
d
els.
T
h
is
s
tu
d
y
als
o
co
m
p
a
r
es
tr
ain
in
g
an
d
test
in
g
tim
es
ac
r
o
s
s
all
m
o
d
els
(
T
ab
le
4
)
.
I
n
a
p
air
e
d
t
-
t
est,
th
e
t
-
v
al
u
e
in
d
icate
s
th
e
d
if
f
er
en
ce
in
a
v
er
ag
e
p
er
f
o
r
m
an
ce
b
etwe
en
two
m
o
d
els.
T
h
e
lar
g
e
r
th
e
t
-
v
al
u
e,
th
e
m
o
r
e
s
ig
n
if
ican
tly
d
if
f
e
r
en
t
th
e
two
m
o
d
els'
p
er
f
o
r
m
an
ce
.
A
p
o
s
itiv
e
t
-
v
alu
e
m
ea
n
s
th
e
f
ir
s
t
m
o
d
el
p
er
f
o
r
m
s
b
etter
th
an
th
e
s
ec
o
n
d
,
wh
ile
a
n
eg
ativ
e
t
-
v
alu
e
in
d
icate
s
th
e
o
p
p
o
s
ite.
Me
an
wh
ile,
th
e
p
-
v
alu
e
in
d
ica
tes
th
e
lik
elih
o
o
d
th
at
th
e
d
if
f
er
en
ce
o
cc
u
r
r
ed
b
y
ch
an
ce
.
A
p
-
v
alu
e
less
th
an
0
.
0
5
in
d
icate
s
th
at
th
e
d
if
f
er
en
ce
is
s
tat
is
tical
ly
s
ig
n
if
ican
t,
s
u
g
g
esti
n
g
it
is
u
n
lik
ely
d
u
e
to
r
an
d
o
m
f
lu
ctu
atio
n
s
.
C
o
n
v
er
s
ely
,
a
p
-
v
alu
e
ab
o
v
e
0
.
0
5
i
n
d
icate
s
th
at
th
e
o
b
s
er
v
ed
d
if
f
e
r
en
c
e
is
n
o
t statis
tica
lly
s
ig
n
if
ican
t,
an
d
b
o
t
h
m
o
d
els ca
n
b
e
s
aid
t
o
p
er
f
o
r
m
s
im
ilar
ly
[
2
8
]
.
T
ab
le
3
.
Statis
tical
test
in
g
u
s
i
n
g
th
e
p
air
ed
t
-
test
M
o
d
e
l
1
M
o
d
e
l
2
t
_
s
t
a
t
p
-
v
a
l
u
e
H
K
S
V
M
-
C
S
A
S
V
M
s
t
a
n
d
a
r
d
4
.
6
1
9
0
.
0
1
0
H
K
S
V
M
-
C
S
A
S
V
M
-
GA
2
.
9
7
4
0
.
0
4
1
H
K
S
V
M
-
C
S
A
K
N
N
2
1
.
5
0
0
0
.
0
0
0
S
V
M
-
s
t
a
n
d
a
r
d
S
V
M
-
GA
2
.
7
6
0
0
.
0
5
1
S
V
M
-
s
t
a
n
d
a
r
d
K
N
N
1
4
.
8
6
4
0
.
0
0
0
1
S
V
M
-
GA
K
N
N
-
1
.
5
5
5
0
.
1
9
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
3
1
6
-
1
3
2
6
1324
B
ased
o
n
T
ab
le
3
,
a
s
ig
n
if
ican
t
s
tatis
tical
d
if
f
er
en
ce
ex
is
ts
b
etwe
en
HKS
VM
-
C
S
A
an
d
th
e
co
m
p
ar
is
o
n
m
eth
o
d
s
.
A
p
o
s
itiv
e
t
-
v
alu
e
in
d
icate
s
th
at
HK
SVM
-
C
S
A
h
as
a
h
ig
h
er
av
er
ag
e
p
er
f
o
r
m
an
ce
.
A
p
-
v
alu
e
o
f
less
th
an
0
.
0
5
m
ea
n
s
th
at
th
e
d
if
f
e
r
en
ce
is
v
er
y
u
n
lik
ely
t
o
h
a
v
e
h
ap
p
e
n
ed
b
y
ch
an
ce
.
T
h
is
s
h
o
ws
th
at
u
s
in
g
a
h
y
b
r
id
k
er
n
el
an
d
C
SA
-
b
ased
p
ar
am
ete
r
o
p
tim
izatio
n
p
r
o
v
id
es
a
s
ig
n
if
ica
n
t
im
p
r
o
v
em
en
t
o
v
e
r
s
tan
d
ar
d
SVM.
C
o
m
p
ar
ed
to
SVM
-
GA,
HK
SVM
-
C
SA
i
s
s
till
s
u
p
er
io
r
,
ev
en
th
o
u
g
h
b
o
t
h
u
s
e
m
etah
eu
r
is
tic
o
p
tim
izatio
n
.
C
SA
p
r
o
v
id
es
m
o
r
e
s
tab
le
ex
p
lo
itatio
n
-
ex
p
l
o
r
atio
n
th
an
GA,
en
a
b
lin
g
it
to
d
eter
m
in
e
m
o
r
e
o
p
tim
al
p
ar
am
eter
s
.
On
th
e
o
th
er
h
a
n
d
,
c
o
m
p
a
r
ed
to
KNN,
th
e
lar
g
e
t
-
v
alu
e
in
d
icate
s
a
s
ig
n
if
ican
t
p
er
f
o
r
m
an
ce
g
ap
b
etwe
en
HK
SVM
-
C
S
A
an
d
KNN.
K
NN
i
s
f
ar
b
eh
in
d
in
m
alar
ia
class
if
icatio
n
u
s
in
g
co
lo
r
an
d
GL
C
M
f
ea
tu
r
es.
T
ab
le
3
s
h
o
ws
th
at
HKSVM
-
C
SA
i
s
th
e
b
est
-
p
er
f
o
r
m
i
n
g
m
o
d
el,
with
p
er
f
o
r
m
a
n
ce
s
ig
n
if
ican
tly
b
etter
th
an
th
at
o
f
all
o
th
er
m
o
d
els.
Usi
n
g
C
SA
is
also
m
o
r
e
ef
f
ec
tiv
e
th
a
n
GA
f
o
r
o
p
tim
izin
g
SVM
h
y
p
er
p
ar
a
m
eter
s
.
Me
an
wh
ile,
b
ased
o
n
t
h
e
tr
ai
n
in
g
a
n
d
test
in
g
tim
e
test
s
(
T
ab
le
4
)
,
KNN
h
as
th
e
s
h
o
r
t
est
tr
ain
in
g
tim
e
(
0
.
0
1
s
ec
o
n
d
s
)
b
ec
au
s
e
it
d
o
es
n
o
t
in
v
o
lv
e
a
co
m
p
lex
t
r
ain
in
g
p
r
o
ce
s
s
.
SVM
s
tan
d
ar
d
s
h
o
ws
th
e
f
aste
s
t
test
tim
e
(
0
.
1
9
s
ec
o
n
d
s
)
b
ec
a
u
s
e
it
d
o
es
n
o
t
in
clu
d
e
an
o
p
t
im
izatio
n
p
r
o
ce
s
s
,
wh
ich
m
a
k
es
th
e
co
m
p
u
tatio
n
r
u
n
ef
f
icien
tly
.
Me
an
wh
ile,
H
KSVM
-
C
SA
h
ad
th
e
lo
n
g
est
t
im
e.
T
h
is
is
n
atu
r
al
b
ec
au
s
e
th
e
p
r
o
p
o
s
ed
m
eth
o
d
m
u
s
t
ex
tr
ac
t
f
ea
tu
r
es
u
s
in
g
t
wo
k
er
n
els,
wh
ich
m
a
k
es
it
co
m
p
u
tatio
n
ally
m
o
r
e
c
o
m
p
le
x
.
Ad
d
itio
n
ally
,
th
e
C
SA o
p
tim
izatio
n
p
r
o
ce
s
s
r
eq
u
ir
es m
o
r
e
iter
atio
n
s
to
d
eter
m
in
e
th
e
o
p
tim
al
SVM
p
ar
a
m
eter
s
.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
co
m
p
u
tatio
n
al
tim
e
f
o
r
tr
ain
in
g
an
d
test
in
g
M
o
d
e
l
Tr
a
i
n
i
n
g
t
i
me
(
s)
Te
st
i
n
g
t
i
m
e
(
s)
S
V
M
s
t
a
n
d
a
r
d
2
.
9
7
0
.
1
9
K
N
N
0
.
0
1
0
.
4
3
S
V
M
-
GA
5
.
7
2
0
.
3
9
Th
e
p
r
o
p
o
s
e
d
me
t
h
o
d
(
H
K
S
V
M
-
C
S
A
)
2
3
8
.
1
9
5
.
3
1
3
.
4
.
Dis
cus
s
io
n
T
h
e
ex
p
er
im
en
tal
r
esu
lts
p
r
e
s
en
ted
d
em
o
n
s
tr
ate
th
e
s
u
p
e
r
io
r
ity
o
f
th
e
HKSVM
-
C
SA
m
o
d
el
i
n
class
if
y
in
g
m
alar
ia
-
in
f
ec
ted
b
lo
o
d
ce
lls
.
HKSVM
-
C
S
A
i
n
teg
r
ates
a
h
y
b
r
id
k
e
r
n
el
(
R
B
F
an
d
h
is
to
g
r
am
in
ter
s
ec
tio
n
)
an
d
o
p
tim
izes
h
y
p
er
p
a
r
am
eter
s
u
s
in
g
th
e
C
SA.
T
h
e
R
B
F
k
er
n
el’
s
a
b
ilit
y
to
h
an
d
le
n
o
n
lin
ea
r
s
p
atial
f
ea
tu
r
es,
co
m
b
in
ed
wit
h
th
e
h
is
to
g
r
am
in
te
r
s
ec
tio
n
k
er
n
el’
s
s
en
s
itiv
ity
to
co
lo
r
d
is
tr
ib
u
tio
n
,
r
esu
lts
in
a
m
o
r
e
d
is
cr
im
in
ativ
e
f
ea
tu
r
e
s
p
ac
e.
T
h
e
HKSVM
-
C
SA
m
o
d
el
ac
h
iev
ed
9
4
%
ac
cu
r
ac
y
,
0
.
9
3
s
en
s
itiv
ity
,
0
.
9
4
s
p
ec
if
icity
,
a
n
d
a
n
AUC
o
f
0
.
9
8
,
s
ig
n
if
ican
tly
o
u
t
p
er
f
o
r
m
in
g
th
e
b
aselin
e
m
et
h
o
d
s
.
T
h
ese
r
esu
lts
co
n
f
ir
m
t
h
at
a
m
u
lti
-
k
er
n
el
f
u
n
ctio
n
is
s
u
f
f
icien
t
t
o
f
u
lly
r
ep
r
esen
t
th
e
co
m
p
le
x
v
is
u
a
l
ch
ar
ac
ter
is
tics
o
f
m
alar
ia
-
in
f
ec
ted
a
n
d
n
o
n
-
in
f
ec
ted
ce
lls
.
Mo
r
eo
v
e
r
,
h
y
p
er
p
ar
am
eter
o
p
tim
izatio
n
u
s
in
g
C
SA
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
p
e
r
f
o
r
m
an
ce
.
C
SA
ca
p
ab
ilit
y
en
a
b
led
t
h
e
m
o
d
el
to
ef
f
ec
tiv
ely
f
in
e
-
tu
n
e
its
d
e
cisi
o
n
b
o
u
n
d
ar
y
to
th
e
s
p
ec
if
ic
f
ea
tu
r
e
d
is
tr
ib
u
tio
n
in
th
e
m
alar
ia
ce
ll im
ag
es d
a
taset
.
Fro
m
a
clin
ical
p
er
s
p
ec
tiv
e,
a
h
ig
h
-
s
en
s
itiv
ity
au
to
m
ated
m
alar
ia
d
etec
tio
n
s
y
s
tem
r
ed
u
ce
s
th
e
lik
elih
o
o
d
o
f
f
alse
n
eg
ativ
es
,
th
er
eb
y
en
s
u
r
i
n
g
th
at
in
f
e
cted
in
d
iv
id
u
als
r
ec
eiv
e
tim
ely
tr
ea
tm
en
t.
T
h
e
b
alan
ce
d
s
p
ec
if
icity
also
m
in
im
izes
f
alse
p
o
s
itiv
es,
r
ed
u
cin
g
u
n
n
ec
ess
ar
y
tr
ea
tm
en
ts
an
d
ass
o
ciate
d
co
s
ts
.
Desp
ite
its
ad
v
an
tag
es,
th
e
cu
r
r
en
t
s
tu
d
y
h
as
s
ev
er
al
lim
itatio
n
s
.
T
h
e
ex
p
er
im
e
n
ts
wer
e
co
n
d
u
cted
u
s
in
g
a
s
in
g
le
d
ataset
u
n
d
er
c
o
n
tr
o
lle
d
im
ag
in
g
co
n
d
itio
n
s
.
Per
f
o
r
m
an
ce
m
a
y
v
a
r
y
w
h
en
a
p
p
lie
d
to
im
a
g
es
ca
p
tu
r
ed
f
r
o
m
d
if
f
e
r
en
t
s
o
u
r
ce
s
o
r
u
n
d
e
r
v
ar
y
in
g
lig
h
tin
g
an
d
s
tain
in
g
co
n
d
itio
n
s
.
Fu
r
th
er
m
o
r
e,
f
u
tu
r
e
r
esear
ch
s
h
o
u
ld
in
v
esti
g
ate
d
o
m
ain
ad
ap
tatio
n
tech
n
iq
u
es
to
en
h
an
ce
m
o
d
el
g
en
er
aliza
b
ilit
y
ac
r
o
s
s
d
a
tasets
f
r
o
m
v
ar
io
u
s
m
ed
ical
ce
n
ter
s
.
T
h
e
in
teg
r
at
io
n
o
f
d
ee
p
f
ea
tu
r
e
r
ep
r
esen
t
atio
n
s
—
s
u
ch
as
th
o
s
e
d
er
iv
e
d
f
r
o
m
p
r
e
-
tr
ain
ed
C
NNs
—
with
HK
SVMs
m
ay
f
u
r
th
er
e
n
h
an
ce
p
er
f
o
r
m
an
ce
.
Ad
d
itio
n
ally
,
d
e
v
elo
p
in
g
an
en
d
-
to
-
e
n
d
s
y
s
tem
th
at
in
clu
d
es
s
eg
m
en
tatio
n
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
class
if
icatio
n
,
an
d
r
ep
o
r
t
g
en
e
r
atio
n
wo
u
ld
o
f
f
er
g
r
ea
ter
p
r
ac
tical
v
alu
e.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ts
a
n
o
v
el,
co
m
p
u
tatio
n
ally
ef
f
icien
t
f
r
a
m
ewo
r
k
f
o
r
th
e
au
to
m
atic
d
etec
tio
n
o
f
m
alar
ia
-
in
f
ec
ted
r
e
d
b
lo
o
d
ce
l
ls
,
wh
ich
en
h
an
ce
s
th
e
SVM
m
eth
o
d
with
a
h
y
b
r
id
k
e
r
n
el
a
n
d
h
y
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
v
ia
th
e
C
SA.
T
h
e
in
teg
r
atio
n
o
f
th
e
RBF
an
d
h
is
to
g
r
am
in
ter
s
ec
tio
n
k
e
r
n
els
en
ab
led
th
e
m
o
d
el
to
ca
p
tu
r
e
b
o
th
s
p
atial
an
d
c
h
r
o
m
atic
im
a
g
e
c
h
ar
ac
ter
is
tics
.
At
th
e
s
am
e
tim
e,
C
SA
ef
f
ec
tiv
ely
tu
n
ed
th
e
class
if
ier
'
s
p
ar
am
eter
s
to
m
ax
im
ize
p
er
f
o
r
m
an
ce
.
E
x
p
e
r
i
m
en
tal
r
esu
lts
o
n
th
e
m
alar
ia
ce
ll
im
ag
es
d
atase
t
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t
im
p
r
o
v
em
en
ts
o
v
er
a
s
tan
d
ar
d
S
VM
,
with
th
e
p
r
o
p
o
s
ed
m
o
d
el
ac
h
iev
in
g
9
4
%
ac
cu
r
ac
y
,
0
.
9
3
s
en
s
itiv
ity
,
0
.
9
4
s
p
ec
if
icity
,
an
d
an
AUC
o
f
0
.
9
8
.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
th
at
th
e
p
r
o
p
o
s
ed
HKSVM
-
C
SA
is
a
r
o
b
u
s
t
an
d
s
ca
lab
le
s
o
lu
tio
n
f
o
r
m
alar
ia
d
etec
tio
n
f
r
o
m
m
icr
o
s
co
p
i
c
im
ag
es.
Fu
r
th
e
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
ke
r
n
el
s
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
w
ith
cu
ck
o
o
s
ea
r
ch
o
p
timiz
a
tio
n
fo
r
…
(
S
r
i H
u
n
in
g
A
n
w
a
r
in
in
g
s
ih
)
1325
d
ev
elo
p
m
e
n
t
co
u
ld
i
n
clu
d
e
in
teg
r
atin
g
d
ee
p
lea
r
n
in
g
-
b
ased
f
ea
tu
r
es
an
d
ev
alu
atin
g
th
e
m
o
d
el
o
n
a
d
iv
er
s
e
d
ataset.
I
m
p
lem
en
tatio
n
o
n
m
o
b
ile
d
ev
ices
o
r
em
b
ed
d
ed
s
y
s
tem
s
ca
n
also
in
cr
ea
s
e
clin
ical
b
en
ef
its
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
r
e
g
io
n
s
.
ACK
NO
WL
E
DG
M
E
N
T
S
W
e
ar
e
v
er
y
g
r
atef
u
l
to
U
n
iv
er
s
itas
Sah
id
Su
r
ak
ar
ta
an
d
T
elk
o
m
Un
iv
er
s
ity
f
o
r
p
r
o
v
id
i
n
g
ex
ce
p
tio
n
al
s
u
p
p
o
r
t in
en
h
a
n
cin
g
o
u
r
r
esear
ch
co
m
p
ete
n
ce
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
is
co
llab
o
r
ativ
e,
with
f
u
n
d
in
g
s
h
a
r
ed
b
etwe
en
Un
iv
er
s
itas
Sah
id
Su
r
ak
ar
ta
a
n
d
T
elk
o
m
Un
iv
er
s
ity
B
an
d
u
n
g
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
S
r
i
H
u
n
i
n
g
A
n
w
a
r
i
n
i
n
g
s
i
h
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
I
n
d
r
ar
i
n
i D
y
ah
I
r
awa
ti
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
t
h
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
in
f
l
u
en
ce
d
th
e
wo
r
k
r
e
p
o
r
ted
in
th
is
p
ap
e
r
.
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
th
is
s
tu
d
y
ar
e
p
u
b
licly
av
ailab
le
in
Kag
g
le
at
h
ttp
s
://www.
k
ag
g
le.
co
m
/d
atasets
/iar
u
n
av
a/ce
ll
-
im
ag
es
-
f
o
r
-
d
etec
tin
g
-
m
alar
ia.
RE
F
E
R
E
NC
E
S
[
1
]
D
.
Đ
u
mi
ć
,
D
.
K
e
č
o
,
a
n
d
Z.
M
a
še
t
i
ć
,
“
A
u
t
o
m
a
t
i
z
a
t
i
o
n
o
f
mi
c
r
o
s
c
o
p
y
m
a
l
a
r
i
a
d
i
a
g
n
o
si
s
u
si
n
g
c
o
mp
u
t
e
r
v
i
si
o
n
a
n
d
r
a
n
d
o
m
f
o
r
e
st
met
h
o
d
,
”
I
FA
C
-
P
a
p
e
rsO
n
L
i
n
e
,
v
o
l
.
5
5
,
n
o
.
4
,
p
p
.
8
0
–
8
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
f
a
c
o
l
.
2
0
2
2
.
0
6
.
0
1
3
.
[
2
]
H.
-
I
.
S
h
i
n
e
t
a
l
.
,
“
2
0
2
3
w
o
r
l
d
mal
a
r
i
a
r
e
p
o
r
t
(
st
a
t
u
s
o
f
w
o
r
l
d
ma
l
a
r
i
a
i
n
2
0
2
2
)
,
”
Pu
b
l
i
c
H
e
a
l
t
h
We
e
k
l
y
Re
p
o
rt
,
v
o
l
.
1
7
,
n
o
.
3
2
,
p
p
.
1
3
5
1
–
1
3
7
7
,
2
0
2
4
,
d
o
i
:
1
0
.
5
6
7
8
6
/
P
H
W
R
.
2
0
2
4
.
1
7
.
3
2
.
1
.
[
3
]
P
.
V
e
n
k
a
t
e
sa
n
,
“
W
H
O
w
o
r
l
d
ma
l
a
r
i
a
r
e
p
o
r
t
2
0
2
4
,
”
T
h
e
L
a
n
c
e
t
Mi
c
r
o
b
e
,
v
o
l
.
6
,
n
o
.
4
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
l
a
n
mi
c
.
2
0
2
5
.
1
0
1
0
7
3
.
[
4
]
I
.
M
.
D
.
M
a
y
s
a
n
j
a
y
a
,
“
C
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
c
l
a
ss
i
f
i
c
a
t
i
o
n
me
t
h
o
d
o
n
d
i
a
g
n
o
si
s
o
f
p
l
a
sm
o
d
i
u
m
p
h
a
se
,
”
J
o
u
rn
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
1
5
1
6
,
n
o
.
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
5
1
6
/
1
/
0
1
2
0
2
1
.
[
5
]
B
.
M
.
C
o
o
k
e
,
N
.
M
o
h
a
n
d
a
s,
a
n
d
R
.
L.
C
o
p
p
e
l
,
“
T
h
e
mal
a
r
i
a
-
i
n
f
e
c
t
e
d
r
e
d
b
l
o
o
d
c
e
l
l
:
st
r
u
c
t
u
r
a
l
a
n
d
f
u
n
c
t
i
o
n
a
l
c
h
a
n
g
e
s,
”
i
n
Ad
v
a
n
c
e
s i
n
Pa
r
a
s
i
t
o
l
o
g
y
,
v
o
l
.
5
0
,
2
0
0
1
,
p
p
.
1
–
86
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
0
6
5
-
3
0
8
X
(
0
1
)
5
0
0
2
9
-
9.
[
6
]
A
.
Lo
d
d
o
,
C
.
D
i
R
u
b
e
r
t
o
,
a
n
d
M
.
K
o
c
h
e
r
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
s
o
f
m
a
l
a
r
i
a
p
a
r
a
s
i
t
e
s
d
e
t
e
c
t
i
o
n
s
y
st
e
ms
b
a
s
e
d
o
n
ma
t
h
e
ma
t
i
c
a
l
mo
r
p
h
o
l
o
g
y
,
”
S
e
n
s
o
rs
,
v
o
l
.
1
8
,
n
o
.
2
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
s1
8
0
2
0
5
1
3
.
[
7
]
M
.
L.
M
c
M
o
r
r
o
w
,
M
.
A
i
d
o
o
,
a
n
d
S
.
P
.
K
a
c
h
u
r
,
“
M
a
l
a
r
i
a
r
a
p
i
d
d
i
a
g
n
o
s
t
i
c
t
e
st
s
i
n
e
l
i
m
i
n
a
t
i
o
n
s
e
t
t
i
n
g
s
—
c
a
n
t
h
e
y
f
i
n
d
t
h
e
l
a
s
t
p
a
r
a
s
i
t
e
?
,
”
C
l
i
n
i
c
a
l
M
i
c
r
o
b
i
o
l
o
g
y
a
n
d
I
n
f
e
c
t
i
o
n
,
v
o
l
.
1
7
,
n
o
.
1
1
,
p
p
.
1
6
2
4
–
1
6
3
1
,
2
0
1
1
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
4
6
9
-
0
6
9
1
.
2
0
1
1
.
0
3
6
3
9
.
x
.
[
8
]
S
.
M
o
mč
i
l
o
v
i
ć
,
C
.
C
a
n
t
a
c
e
ss
i
,
V
.
A
.
-
A
r
s
e
n
i
j
e
v
i
ć
,
D
.
O
t
r
a
n
t
o
,
a
n
d
S
.
T
.
-
O
t
a
š
e
v
i
ć
,
“
R
a
p
i
d
d
i
a
g
n
o
s
i
s
o
f
p
a
r
a
s
i
t
i
c
d
i
s
e
a
s
e
s
:
c
u
r
r
e
n
t
sc
e
n
a
r
i
o
a
n
d
f
u
t
u
r
e
n
e
e
d
s
,
”
C
l
i
n
i
c
a
l
M
i
c
r
o
b
i
o
l
o
g
y
a
n
d
I
n
f
e
c
t
i
o
n
,
v
o
l
.
2
5
,
n
o
.
3
,
p
p
.
2
9
0
–
3
0
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
mi
.
2
0
1
8
.
0
4
.
0
2
8
.
[
9
]
K
.
Y
a
h
u
z
a
,
A
.
M
.
U
mar
,
S
.
D
.
B
a
h
a
’
u
d
d
e
e
n
,
E.
T.
A
t
a
l
a
b
i
,
G
.
L
.
M
u
k
h
t
a
r
,
a
n
d
B
.
A
b
d
u
l
k
a
d
i
r
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
men
t
s i
n
d
e
t
e
c
t
i
o
n
a
n
d
q
u
a
n
t
i
f
i
c
a
t
i
o
n
o
f
m
a
l
a
r
i
a
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
U
MYU
J
o
u
r
n
a
l
o
f
Mi
c
r
o
b
i
o
l
o
g
y
Re
s
e
a
r
c
h
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
1
–
2
1
,
2
0
2
4
,
d
o
i
:
1
0
.
4
7
4
3
0
/
u
j
mr
.
2
4
9
2
.
0
0
1
.
[
1
0
]
C
.
R
.
M
a
t
u
r
a
n
a
e
t
a
l
.
,
“
A
d
v
a
n
c
e
s
a
n
d
c
h
a
l
l
e
n
g
e
s
i
n
a
u
t
o
m
a
t
e
d
ma
l
a
r
i
a
d
i
a
g
n
o
s
i
s
u
si
n
g
d
i
g
i
t
a
l
m
i
c
r
o
s
c
o
p
y
i
ma
g
i
n
g
w
i
t
h
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
t
o
o
l
s:
a
r
e
v
i
e
w
,
”
Fr
o
n
t
i
e
r
s i
n
M
i
c
r
o
b
i
o
l
o
g
y
,
v
o
l
.
1
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
mi
c
b
.
2
0
2
2
.
1
0
0
6
6
5
9
.
[
1
1
]
Y
.
Z
h
o
n
g
e
t
a
l
.
,
“
E
f
f
i
c
i
e
n
t
m
a
l
a
r
i
a
p
a
r
a
s
i
t
e
d
e
t
e
c
t
i
o
n
f
r
o
m
d
i
v
e
r
s
e
i
m
a
g
e
s
o
f
t
h
i
c
k
b
l
o
o
d
sm
e
a
r
s
f
o
r
c
r
o
s
s
-
r
e
g
i
o
n
a
l
m
o
d
e
l
a
c
c
u
r
a
c
y
,
”
I
E
EE
O
p
e
n
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
r
i
n
g
i
n
M
e
d
i
c
i
n
e
a
n
d
B
i
o
l
o
g
y
,
v
o
l
.
4
,
p
p
.
2
2
6
–
2
3
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
O
J
E
M
B
.
2
0
2
3
.
3
3
2
8
4
3
5
.
[
1
2
]
C
.
D
i
R
u
b
e
r
t
o
,
A
.
D
e
m
p
st
e
r
,
S
.
K
h
a
n
,
a
n
d
B
.
Jarr
a
,
“
A
n
a
l
y
si
s
o
f
i
n
f
e
c
t
e
d
b
l
o
o
d
c
e
l
l
i
m
a
g
e
s
u
s
i
n
g
m
o
r
p
h
o
l
o
g
i
c
a
l
o
p
e
r
a
t
o
r
s
,
”
I
m
a
g
e
a
n
d
V
i
si
o
n
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
0
,
n
o
.
2
,
p
p
.
1
3
3
–
1
4
6
,
2
0
0
2
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
2
6
2
-
8
8
5
6
(
0
1
)
0
0
0
9
2
-
0.
Evaluation Warning : The document was created with Spire.PDF for Python.