I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
6
,
Decem
b
er
20
25
,
p
p
.
5
5
8
4
~
5
5
9
3
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
6
.
pp
5
5
8
4
-
5
5
9
3
5584
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Exploring
fea
ture
select
io
n
metho
d
fo
r microa
rray
cl
a
ss
ificatio
n
M
uh
a
m
m
a
d Z
a
k
y
H
a
k
i
m
A
k
ma
l,
Dev
i F
it
ria
na
h
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
D
e
p
a
r
t
m
e
n
t
,
B
i
n
u
s
G
r
a
d
u
a
t
e
P
r
o
g
r
a
m
–
M
a
s
t
e
r
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
B
i
n
a
N
u
sa
n
t
a
r
a
U
n
i
v
e
r
si
t
y
,
Ja
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
9
,
2
0
2
5
R
ev
is
ed
J
u
l 1
6
,
2
0
2
5
Acc
ep
ted
Sep
1
4
,
2
0
2
5
Eff
e
c
ti
v
e
ly
se
lec
ti
n
g
fe
a
tu
re
s
fr
o
m
h
i
g
h
-
d
ime
n
sio
n
a
l
m
icro
a
rra
y
d
a
ta
is
e
ss
e
n
ti
a
l
fo
r
a
c
c
u
ra
te
c
a
n
c
e
r
d
e
te
c
ti
o
n
.
Th
is
stu
d
y
e
x
p
lo
re
s
t
h
e
p
i
v
o
tal
ro
le
o
f
fe
a
tu
re
se
lec
ti
o
n
i
n
imp
r
o
v
i
n
g
th
e
a
c
c
u
ra
c
y
o
f
c
las
sify
in
g
m
icro
a
rra
y
d
a
ta
fo
r
o
v
a
rian
c
a
n
c
e
r
d
e
tec
ti
o
n
.
U
ti
li
z
in
g
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
s
a
n
d
m
icro
a
rra
y
tec
h
n
o
lo
g
y
,
t
h
e
re
se
a
rc
h
a
ims
t
o
i
d
e
n
ti
f
y
su
b
tl
e
g
e
n
e
e
x
p
re
ss
io
n
p
a
tt
e
rn
s
th
a
t
i
n
d
ica
te
o
v
a
rian
c
a
n
c
e
r.
Th
e
re
se
a
rc
h
e
x
p
lo
re
s
th
e
u
ti
li
z
a
ti
o
n
o
f
p
rin
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
l
y
sis
(
P
CA)
fo
r
d
ime
n
sio
n
a
li
t
y
re
d
u
c
ti
o
n
a
n
d
c
o
m
p
a
re
s
th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
fe
a
tu
re
se
lec
ti
o
n
tec
h
n
i
q
u
e
s
su
c
h
a
s
a
rti
ficia
l
b
e
e
c
o
lo
n
y
(ABC)
a
n
d
se
q
u
e
n
ti
a
l
fo
rwa
rd
f
lo
a
ti
n
g
se
lec
ti
o
n
(
S
F
F
S
).
Th
e
d
a
tas
e
t
u
se
d
in
th
is
stu
d
y
c
o
m
p
rise
s
o
f
1
5
,
1
5
4
g
e
n
e
s,
2
5
3
i
n
sta
n
c
e
s,
a
n
d
2
c
las
se
s
re
lat
e
d
to
o
v
a
rian
c
a
n
c
e
r.
Th
ro
u
g
h
a
c
o
m
p
re
h
e
n
siv
e
a
n
a
ly
sis,
th
e
stu
d
y
a
ims
to
o
p
ti
m
ize
th
e
c
las
sifica
ti
o
n
p
r
o
c
e
ss
a
n
d
imp
r
o
v
e
th
e
e
a
rly
d
e
tec
ti
o
n
o
f
o
v
a
rian
c
a
n
c
e
r.
M
o
r
e
o
v
e
r,
t
h
e
st
u
d
y
p
re
se
n
ts
t
h
e
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
re
su
lt
s
o
b
tai
n
e
d
b
y
P
CA,
ABC,
a
n
d
S
F
F
S
.
Wh
il
e
P
CA
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
9
6
%
a
n
d
S
F
F
S
y
iel
d
e
d
a
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
9
8
%
,
ABC
d
e
m
o
n
stra
ted
t
h
e
h
ig
h
e
st
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
1
0
0
%
.
Th
e
se
fin
d
in
g
s
u
n
d
e
rsc
o
re
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
ABC
a
s
th
e
p
re
fe
rre
d
c
h
o
ice
f
o
r
fe
a
tu
re
se
lec
ti
o
n
i
n
imp
ro
v
i
n
g
th
e
c
l
a
ss
ifi
c
a
ti
o
n
a
c
c
u
ra
c
y
o
f
o
v
a
ri
a
n
c
a
n
c
e
r
d
e
tec
ti
o
n
u
sin
g
m
icro
a
rra
y
d
a
ta.
K
ey
w
o
r
d
s
:
C
an
ce
r
d
etec
tio
n
E
v
o
lu
tio
n
a
r
y
alg
o
r
ith
m
Featu
r
e
s
elec
tio
n
Ma
ch
in
e
lear
n
in
g
Mic
r
o
ar
r
ay
d
ata
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
:
Mu
h
am
m
ad
Z
ak
y
Ha
k
im
Ak
m
al
C
o
m
p
u
ter
Scien
ce
Dep
ar
tm
e
n
t
,
B
in
u
s
Gr
ad
u
ate
Pro
g
r
a
m
-
M
aster
o
f
C
o
m
p
u
ter
Scien
ce
,
B
in
a
Nu
s
an
tar
a
Un
iv
er
s
ity
Ky
ai
H.
Sy
ah
d
an
9
Stre
et
,
Ke
m
an
g
g
is
an
,
Palm
er
a
h
,
J
ak
ar
ta
B
ar
at,
Dae
r
ah
Kh
u
s
u
s
I
b
u
k
o
ta
1
1
4
8
0
,
J
ak
ar
ta
E
m
ail:
m
u
h
am
m
a
d
.
ak
m
al0
0
3
@
b
in
u
s
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
an
ce
r
is
o
n
e
o
f
th
e
n
u
m
b
er
o
n
e
ca
u
s
es
o
f
d
ea
th
in
t
h
e
wo
r
ld
,
wh
ich
m
a
y
a
p
p
ea
r
in
v
ar
io
u
s
p
ar
ts
o
f
th
e
h
u
m
an
b
o
d
y
,
s
u
c
h
as
th
e
lu
n
g
s
,
h
ea
r
t,
p
an
c
r
ea
s
,
an
d
m
an
y
o
th
er
o
r
g
an
s
an
d
tis
s
u
es.
C
an
ce
r
m
ay
s
tar
t
f
o
r
m
in
g
d
u
e
t
o
ab
n
o
r
m
al
ce
ll
g
r
o
wth
th
at
will
s
p
r
ea
d
to
o
t
h
er
o
r
g
an
s
an
d
tis
s
u
es
in
th
e
b
o
d
y
.
Yo
u
ca
n
g
et
ca
n
ce
r
b
y
s
m
o
k
in
g
,
d
r
in
k
in
g
alco
h
o
l,
b
ein
g
o
l
d
er
,
ce
r
tain
t
y
p
es
o
f
in
f
ec
tio
n
s
,
an
d
y
o
u
c
an
ev
en
g
et
ca
n
ce
r
ju
s
t
b
y
g
ettin
g
o
ld
er
.
T
h
e
r
ea
s
o
n
is
b
ec
au
s
e
o
f
th
e
m
u
tatio
n
s
o
f
th
e
tis
s
u
e,
an
d
s
o
m
e
o
f
th
ese
m
u
tatio
n
s
m
ay
co
n
tr
ib
u
te
to
th
e
b
ir
t
h
o
f
c
an
c
er
s
[
1
]
.
Acc
o
r
d
in
g
to
th
e
wo
r
ld
wid
e
ca
n
ce
r
r
esear
ch
f
u
n
d
i
n
t
er
n
atio
n
al
,
ca
n
ce
r
r
em
ain
s
a
co
n
ce
r
n
wo
r
ld
wid
e,
th
er
e
will
b
e
an
esti
m
ate
o
f
1
8
.
1
m
illi
o
n
ca
n
ce
r
ca
s
es
in
th
e
wo
r
ld
in
2
0
2
0
alo
n
e.
Am
o
n
g
th
ese
ca
s
es,
th
e
m
o
s
t
co
m
m
o
n
ca
n
ce
r
s
th
at
p
eo
p
le
m
ay
h
a
v
e
ar
e
b
r
ea
s
t
an
d
lu
n
g
ca
n
ce
r
,
wh
ile
p
an
cr
ea
tic
an
d
o
v
ar
ian
ca
n
ce
r
ar
e
co
n
s
id
er
ed
ty
p
es
o
f
ca
n
ce
r
s
th
at
ar
e
h
ar
d
to
d
etec
t
u
n
til
th
ey
h
av
e
r
e
ac
h
ed
an
ad
v
an
ce
d
s
tag
e.
Ov
ar
ian
ca
n
ce
r
is
co
n
s
id
er
ed
o
n
e
o
f
th
e
d
ea
d
lies
t
ca
n
ce
r
s
,
ch
allen
g
in
g
to
d
etec
t
in
its
p
r
elim
in
ar
y
s
tag
es,
lead
in
g
t
o
d
elay
ed
d
i
ag
n
o
s
es
an
d
p
o
ten
tially
p
o
o
r
er
o
u
tco
m
es.
T
h
e
tr
ic
k
y
p
r
o
g
r
ess
io
n
o
f
o
v
ar
ia
n
ca
n
ce
r
u
n
d
er
s
co
r
es
th
e
cr
itical
n
ee
d
f
o
r
im
p
r
o
v
ed
d
iag
n
o
s
tic
m
eth
o
d
s
ca
p
ab
le
o
f
id
e
n
tify
in
g
th
e
d
is
ea
s
e
at
an
ea
r
lier
s
tag
e
wh
en
t
r
ea
tm
en
t
o
p
tio
n
s
ar
e
m
o
s
t
ef
f
ec
tiv
e.
T
r
a
d
itio
n
al
d
iag
n
o
s
tic
ap
p
r
o
ac
h
es
,
in
clu
d
in
g
p
h
y
s
ical
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
xp
lo
r
in
g
fea
tu
r
e
s
elec
tio
n
meth
o
d
fo
r
micro
a
r
r
a
y
cla
s
s
ific
a
tio
n
(
Mu
h
a
mma
d
Za
ky
Ha
ki
m
A
kma
l
)
5585
ex
am
in
atio
n
s
,
ca
n
ce
r
s
cr
ee
n
i
n
g
s
,
b
lo
o
d
test
s
,
an
d
la
b
o
r
at
o
r
y
a
n
aly
s
es,
m
ay
n
o
t
alwa
y
s
b
e
s
u
f
f
icien
t
i
n
d
etec
tin
g
o
v
ar
ian
ca
n
ce
r
,
g
iv
en
its
ten
d
en
cy
to
m
an
if
est
with
v
ag
u
e
o
r
n
o
n
s
p
ec
if
ic
s
y
m
p
to
m
s
u
n
til
it
h
as
r
ea
ch
ed
an
ad
v
a
n
ce
d
s
tag
e.
F
u
r
th
er
m
o
r
e,
o
v
ar
ian
ca
n
ce
r
p
o
s
es
a
s
ig
n
if
ican
t
ch
allen
g
e
in
ea
r
ly
d
etec
tio
n
a
n
d
tr
ea
tm
en
t
d
u
e
to
its
elu
s
iv
e
s
y
m
p
to
m
s
u
n
til
it
r
ea
ch
es
ad
v
a
n
ce
d
s
tag
es.
Ma
ch
in
e
lear
n
in
g
t
ec
h
n
iq
u
es
co
u
p
led
with
m
icr
o
ar
r
a
y
tech
n
o
lo
g
y
o
f
f
er
a
p
r
o
m
is
in
g
ap
p
r
o
ac
h
to
ad
d
r
ess
th
is
ch
allen
g
e.
B
y
an
aly
zin
g
g
e
n
e
ex
p
r
ess
io
n
p
atter
n
s
f
r
o
m
m
i
cr
o
ar
r
ay
d
ata,
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
ca
n
id
en
tify
s
u
b
tle
s
ig
n
atu
r
es
in
d
icativ
e
o
f
o
v
ar
ian
ca
n
ce
r
.
B
y
lev
er
ag
in
g
m
ac
h
in
e
lear
n
i
n
g
,
r
esear
ch
e
r
s
ca
n
g
o
th
r
o
u
g
h
m
ass
iv
e
d
atasets
to
id
en
tify
m
o
lecu
lar
s
ig
n
at
u
r
es
o
f
o
v
ar
ia
n
ca
n
ce
r
,
ev
e
n
in
its
ea
r
lies
t
s
tag
es.
T
h
is
ap
p
r
o
ac
h
h
elp
s
d
o
cto
r
s
u
n
d
er
s
tan
d
th
e
d
is
ea
s
e
b
ette
r
an
d
tr
ea
t
it
s
o
o
n
er
.
Als
o
,
co
m
b
i
n
in
g
m
ac
h
i
n
e
lear
n
in
g
with
m
icr
o
ar
r
ay
tech
n
o
lo
g
y
m
ea
n
s
d
o
ct
o
r
s
ca
n
g
iv
e
tr
ea
tm
en
ts
th
at
f
it
ea
c
h
p
er
s
o
n
’
s
u
n
iq
u
e
s
itu
atio
n
,
m
ak
in
g
tr
ea
tm
en
ts
wo
r
k
b
etter
a
n
d
ca
u
s
in
g
f
ewe
r
p
r
o
b
lem
s
.
T
h
er
e
ar
e
n
u
m
er
o
u
s
s
tu
d
ies
r
e
lated
to
p
r
ed
ictin
g
o
v
ar
ian
ca
n
ce
r
u
s
in
g
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
es,
s
u
ch
as
XG
B
o
o
s
t
[
2
]
,
s
o
f
tm
ax
d
is
cr
im
in
an
t
alg
o
r
ith
m
(
SDA)
[
3
]
,
an
d
g
r
ad
ien
t
b
o
o
s
tin
g
d
ec
is
io
n
tr
ee
[
4
]
.
All
th
r
ee
jo
u
r
n
als
u
tili
ze
o
v
ar
ian
c
an
ce
r
m
icr
o
ar
r
ay
d
ata
lab
ele
d
as
‘
n
o
r
m
al’
an
d
‘
ca
n
ce
r
’
.
Mic
r
o
ar
r
ay
tec
h
n
o
lo
g
y
is
a
p
o
wer
f
u
l
to
o
l
u
s
ed
b
y
s
ci
en
tis
ts
to
s
tu
d
y
g
en
e
ac
tiv
ity
b
y
co
m
p
a
r
in
g
h
u
n
d
r
ed
s
o
r
e
v
en
th
o
u
s
an
d
s
o
f
g
en
e
p
r
o
f
iles
b
etwe
en
d
if
f
er
en
t
co
n
d
itio
n
s
,
s
u
ch
as
h
ea
lth
y
tis
s
u
e
an
d
ca
n
ce
r
o
u
s
tis
s
u
e.
T
h
is
m
eth
o
d
allo
ws
r
esear
ch
er
s
to
s
im
u
ltan
eo
u
s
ly
m
o
n
ito
r
,
id
en
tif
y
,
a
n
d
u
n
d
er
s
tan
d
th
o
u
s
an
d
s
o
r
ev
en
m
illi
o
n
s
o
f
g
en
e
p
atter
n
s
in
a
s
in
g
le
ex
p
er
im
e
n
t.
Ho
w
ev
er
,
th
e
a
b
u
n
d
an
ce
o
f
g
en
e
s
an
aly
ze
d
in
m
icr
o
ar
r
ay
d
at
a
r
esu
lts
in
h
ig
h
-
d
im
en
s
io
n
al
d
atasets
,
wh
ich
ca
n
p
o
s
e
ch
allen
g
es
f
o
r
an
al
y
s
is
d
u
e
to
co
m
p
u
tatio
n
al
in
s
tab
ilit
y
an
d
wh
at
is
k
n
o
wn
as th
e
“
c
u
r
s
e
o
f
d
im
en
s
io
n
ality
.”
T
o
ad
d
r
ess
th
ese
ch
allen
g
es,
a
d
im
en
s
io
n
ality
r
e
d
u
ctio
n
tech
n
iq
u
e
is
u
s
ed
to
r
ed
u
ce
th
e
h
ig
h
-
d
im
en
s
io
n
al
d
ata
an
d
to
r
e
d
u
ce
co
m
p
u
tatio
n
al
in
s
tab
ilit
y
.
On
e
co
m
m
o
n
l
y
u
s
ed
tech
n
iq
u
e
is
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
,
wh
ich
aim
s
to
r
ed
u
ce
th
e
d
im
en
s
io
n
ality
o
f
th
e
d
ata
wh
ile
p
r
e
s
er
v
in
g
its
ess
en
tial
f
ea
tu
r
es.
I
n
th
e
r
esear
ch
f
r
o
m
[
5
]
–
[
8
]
,
PC
A
is
u
tili
ze
d
to
t
ac
k
le
th
e
c
u
r
s
e
o
f
d
im
en
s
io
n
ality
in
m
icr
o
a
r
r
ay
d
ata
.
T
h
ese
ex
p
e
r
im
en
ts
o
b
t
ain
ed
p
o
o
r
v
al
u
es
g
e
n
er
ated
b
y
PC
A
co
m
p
a
r
ed
to
o
th
e
r
f
ea
tu
r
e
r
ed
u
ctio
n
tech
n
iq
u
es.
T
h
e
r
ef
o
r
e
,
th
is
s
tu
d
y
will
em
p
lo
y
a
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
th
at
ca
n
c
h
o
o
s
e
im
p
o
r
tan
t
f
ea
t
u
r
es
b
ased
o
n
th
e
e
v
alu
atio
n
m
o
d
el
to
b
e
in
clu
d
e
d
in
th
e
class
if
icatio
n
u
s
in
g
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
.
R
esear
ch
er
s
ex
p
lo
r
ed
alter
n
ati
v
e
ap
p
r
o
ac
h
es
t
o
d
im
e
n
s
io
n
al
ity
r
ed
u
ctio
n
a
n
d
f
ea
tu
r
e
s
elec
tio
n
in
t
h
e
co
n
tex
t
o
f
m
icr
o
ar
r
ay
d
ata
an
aly
s
is
.
On
e
o
f
th
e
tech
n
iq
u
es
is
ar
tifi
cial
b
ee
co
lo
n
y
(
AB
C
)
f
ea
tu
r
e
s
elec
tio
n
f
r
o
m
th
e
[
9
]
–
[
1
1
]
r
esear
ch
,
wh
ich
s
elec
ts
p
r
o
m
in
e
n
t
f
ea
tu
r
es
b
ased
o
n
a
co
lo
n
y
c
o
n
ce
p
t,
m
im
ick
i
n
g
th
e
b
e
h
av
io
r
o
f
r
ea
l
-
life
h
o
n
ey
b
ee
s
co
llectin
g
f
o
o
d
.
T
h
e
o
th
er
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
is
s
eq
u
e
n
tial
f
o
r
war
d
f
lo
atin
g
s
elec
tio
n
(
SF
FS
)
,
as
a
co
m
p
ar
is
o
n
f
o
r
AB
C
,
will
b
e
im
p
lem
en
ted
in
th
is
r
esear
ch
.
SF
FS
h
as
g
ain
ed
atten
tio
n
as
an
ef
f
ec
tiv
e
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
f
o
r
h
an
d
lin
g
h
i
g
h
-
d
im
en
s
io
n
al
m
ic
r
o
ar
r
a
y
d
ata,
as
s
ee
n
in
th
e
jo
u
r
n
als
[
1
2
]
–
[
1
4
]
.
I
n
th
is
r
esear
ch
,
th
e
au
th
o
r
s
s
u
g
g
e
s
ted
co
m
p
ar
i
n
g
th
e
p
er
f
o
r
m
an
ce
o
f
PC
A
f
o
r
d
im
en
s
io
n
ality
r
ed
u
ctio
n
an
d
co
m
p
ar
in
g
th
e
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
o
f
AB
C
an
d
SF
F
S
u
s
in
g
an
o
v
ar
ia
n
ca
n
ce
r
d
ataset
s
o
u
r
ce
d
f
r
o
m
[
1
5
]
.
T
h
is
d
ataset
co
n
s
is
ted
o
f
1
5
,
1
5
4
g
en
es,
2
5
3
i
n
s
tan
ce
s
,
an
d
2
class
es,
p
r
o
v
id
i
n
g
a
r
o
b
u
s
t f
o
u
n
d
atio
n
f
o
r
e
v
alu
atin
g
th
e
ef
f
ec
tiv
e
n
ess
o
f
d
if
f
er
e
n
t
ap
p
r
o
ac
h
es
in
th
e
co
n
tex
t
o
f
ca
n
ce
r
d
etec
tio
n
.
B
y
co
m
p
a
r
in
g
th
es
e
m
eth
o
d
s
,
th
e
s
tu
d
y
aim
s
to
id
en
tify
th
e
m
o
s
t
ef
f
ec
tiv
e
s
tr
a
teg
y
f
o
r
o
p
tim
izin
g
th
e
an
aly
s
is
o
f
m
icr
o
a
r
r
ay
d
at
a.
2.
RE
L
AT
E
D
WO
RK
S
C
an
ce
r
is
a
co
m
p
lex
a
n
d
m
u
lt
if
ac
eted
d
is
ea
s
e
ch
ar
ac
ter
ize
d
b
y
th
e
u
n
co
n
tr
o
lled
g
r
o
wth
a
n
d
s
p
r
ea
d
o
f
ab
n
o
r
m
al
ce
lls
in
t
h
e
b
o
d
y
.
T
h
ese
ab
n
o
r
m
al
ce
lls
,
k
n
o
w
n
as
ca
n
ce
r
ce
lls
,
h
a
v
e
th
e
a
b
ilit
y
to
in
v
ad
e
an
d
d
estro
y
s
u
r
r
o
u
n
d
i
n
g
tis
s
u
es
an
d
o
r
g
a
n
s
.
C
an
ce
r
ca
n
ar
is
e
in
v
ir
tu
ally
an
y
p
ar
t
o
f
th
e
b
o
d
y
an
d
ca
n
m
an
i
f
est
in
v
ar
io
u
s
f
o
r
m
s
,
d
ep
e
n
d
in
g
o
n
th
e
t
y
p
e
o
f
ce
lls
af
f
ec
te
d
a
n
d
th
e
lo
ca
tio
n
o
f
th
e
t
u
m
o
r
.
W
h
ile
th
e
m
o
s
t
tu
m
o
r
o
u
s
lesi
o
n
s
ar
e
ty
p
icall
y
ca
teg
o
r
ized
as
eith
er
“b
en
ig
n
”
o
r
“m
alig
n
a
n
t,”
th
e
class
if
icatio
n
o
f
o
v
ar
ian
tu
m
o
r
s
f
o
llo
ws
a
m
o
r
e
n
u
a
n
ce
d
ca
teg
o
r
izatio
n
,
in
clu
d
i
n
g
“b
en
ig
n
,
”
“b
o
r
d
er
lin
e,
”
o
r
“m
ali
g
n
an
t”
d
is
tin
ctio
n
s
.
Ov
ar
ian
tu
m
o
r
s
en
co
m
p
ass
a
s
p
ec
tr
u
m
o
f
g
r
o
wth
s
r
an
g
in
g
f
r
o
m
n
o
n
ca
n
ce
r
o
u
s
(
b
en
ig
n
)
to
p
o
ten
tially
ca
n
ce
r
o
u
s
(
m
alig
n
a
n
t)
,
with
s
o
m
e
f
allin
g
in
an
in
ter
m
ed
i
ate
ca
teg
o
r
y
r
e
f
er
r
e
d
to
as
b
o
r
d
er
li
n
e
tu
m
o
r
s
.
C
o
m
p
ar
ed
to
b
en
ig
n
o
v
ar
ian
tu
m
o
r
s
,
m
alig
n
an
t
o
v
ar
ian
ca
n
ce
r
s
ar
e
r
elativ
ely
r
ar
e,
t
h
o
u
g
h
th
ey
p
o
s
e
a
s
ig
n
if
ican
t
h
ea
lth
r
is
k
d
u
e
to
t
h
eir
p
o
ten
tial
to
s
p
r
ea
d
to
o
th
e
r
p
ar
ts
o
f
th
e
b
o
d
y
.
B
o
r
d
e
r
lin
e
tu
m
o
r
s
,
wh
ile
less
co
m
m
o
n
th
an
b
en
ig
n
tu
m
o
r
s
,
also
p
r
esen
t
u
n
iq
u
e
ch
all
en
g
es
in
d
iag
n
o
s
is
an
d
tr
ea
t
m
en
t
d
u
e
t
o
th
eir
am
b
ig
u
o
u
s
n
atu
r
e,
e
x
h
ib
itin
g
f
ea
tu
r
es
th
at
lie
b
etwe
en
b
en
i
g
n
a
n
d
m
alig
n
an
t
tu
m
o
r
s
[
1
6
]
.
A
Stu
d
y
f
r
o
m
[
1
7
]
f
o
u
n
d
th
at
ag
e
an
d
o
v
ar
ian
tu
m
o
r
s
ite
wer
e
s
ig
n
if
ican
tly
c
o
r
r
elate
d
with
p
atien
t
s
u
r
v
iv
a
l
in
o
v
ar
ian
ca
n
ce
r
(
OC
)
.
T
h
e
s
tu
d
y
also
id
en
tifie
d
clin
ical
f
ac
to
r
s
s
u
ch
as
Am
e
r
ican
I
n
d
ian
,
Af
r
ican
Am
er
ica
n
,
p
atien
t
ag
e,
an
d
ca
n
ce
r
s
tag
e
s
tatu
s
as
a
s
s
o
ciat
ed
with
a
s
ig
n
if
ican
tly
h
ig
h
er
r
is
k
o
f
d
ea
th
with
in
5
y
ea
r
s
in
OC
.
Patien
ts
with
lef
t
-
s
id
ed
tu
m
o
r
s
in
t
h
e
o
v
a
r
y
h
ad
a
lo
wer
r
is
k
o
f
d
ea
th
.
T
h
e
s
tu
d
y
p
r
o
v
id
es
s
tr
o
n
g
ev
id
e
n
ce
th
at
th
ese
g
en
es
ar
e
im
p
o
r
ta
n
t
p
r
o
g
n
o
s
tic
in
d
ic
ato
r
s
o
f
p
atien
t
s
u
r
v
iv
al
an
d
g
iv
e
clu
es
to
b
io
lo
g
ical
p
r
o
ce
s
s
es
u
n
d
er
ly
in
g
OC
p
r
o
g
r
ess
io
n
an
d
m
o
r
tality
.
T
h
e
s
tu
d
y
id
en
tifie
d
s
ev
er
al
g
en
es,
in
clu
d
in
g
T
L
R
4
,
B
SC
L
2
,
C
DH1
,
E
R
B
B
2
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
5
8
4
-
5
5
9
3
5586
SC
G
B
2
A1
,
an
d
B
R
C
A2
,
th
at
wer
e
in
d
ep
en
d
en
tly
r
elate
d
to
s
u
r
v
iv
al
in
OC
p
atien
ts
.
T
h
ese
g
en
es
wer
e
f
o
u
n
d
to
b
e
im
p
o
r
tan
t
p
r
o
g
n
o
s
tic
in
d
icato
r
s
o
f
p
atien
t
s
u
r
v
iv
al
an
d
p
r
o
v
id
e
d
m
ec
h
an
is
tic
an
d
p
r
e
d
ictiv
e
in
f
o
r
m
atio
n
in
ad
d
itio
n
to
cli
n
ical
tr
aits
.
Ag
e
an
d
o
v
ar
ian
t
u
m
o
r
s
ite
wer
e
s
ig
n
if
ican
tly
co
r
r
elate
d
with
p
atien
t
s
u
r
v
iv
al
in
OC
.
Ad
d
itio
n
ally
,
clin
ical
f
ac
to
r
s
s
u
ch
as
Am
er
ican
I
n
d
ian
,
Af
r
ican
Am
er
ican
,
p
atien
t
ag
e,
an
d
ca
n
ce
r
s
tag
e
s
tatu
s
wer
e
ass
o
ciate
d
with
a
h
ig
h
er
r
is
k
o
f
d
ea
th
with
in
5
y
ea
r
s
in
OC
.
An
o
th
e
r
s
tu
d
y
f
r
o
m
[
1
8
]
c
o
n
d
u
cted
a
r
esear
ch
wh
er
e
th
ey
i
d
en
tifie
d
s
ig
n
if
ican
t
g
en
e
ex
p
r
ess
io
n
p
atter
n
s
ass
o
ciate
d
with
o
v
ar
ian
ca
n
ce
r
,
with
s
o
m
e
o
f
th
e
f
in
d
i
n
g
s
ar
e:
s
ev
en
s
ig
n
if
ican
t
g
en
es
wer
e
id
en
tifie
d
in
th
e
co
n
tex
t
o
f
o
v
ar
ian
ca
n
ce
r
:
E
2
F1
,
ME
F2
C
,
HPN,
KR
AS,
E
R
B
B
2
,
T
P5
3
,
T
L
R
4
,
PAR
K2
,
B
R
C
A1
;
Gen
e
On
to
lo
g
y
te
r
m
s
an
d
b
io
lo
g
ical
p
ath
wa
y
s
ass
o
ciate
d
with
th
ese
s
ig
n
if
ican
t
g
en
es
wer
e
d
eter
m
in
ed
,
s
u
ch
as
p
o
s
itiv
e
r
eg
u
latio
n
o
f
tr
an
s
cr
ip
tio
n
,
d
eo
x
y
r
ib
o
n
u
cleic
ac
id
(
DN
A
)
s
y
n
th
esis
in
v
o
l
v
ed
in
DNA
r
ep
air
,
a
n
d
ce
llu
lar
r
esp
o
n
s
e
to
s
p
ec
if
ic
co
m
p
o
u
n
d
s
;
Su
r
v
iv
al
p
atter
n
s
f
o
r
alter
ed
an
d
u
n
alter
ed
g
en
e
ex
p
r
ess
io
n
g
r
o
u
p
s
wer
e
esti
m
ated
,
with
s
p
ec
if
ic
g
en
es
lik
e
T
P5
3
s
h
o
win
g
d
i
f
f
er
en
tial
s
u
r
v
iv
al
p
atter
n
s
.
T
h
e
s
e
f
in
d
in
g
s
co
n
tr
ib
u
te
to
a
b
ett
er
u
n
d
er
s
tan
d
in
g
to
a
b
etter
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
m
o
lecu
lar
m
e
ch
an
is
m
s
in
v
o
lv
ed
in
o
v
ar
ia
n
ca
n
c
er
p
r
o
g
r
ess
io
n
an
d
m
a
y
h
av
e
im
p
licatio
n
s
f
o
r
th
e
d
ev
elo
p
m
en
t o
f
tar
g
eted
th
er
a
p
ies an
d
p
er
s
o
n
alize
d
tr
ea
tm
en
t a
p
p
r
o
ac
h
es.
DNA
m
icr
o
ar
r
ay
is
a
tech
n
o
lo
g
y
th
at
is
u
s
ed
to
d
etec
t
a
n
d
c
o
m
p
ar
e
th
o
u
s
an
d
s
o
f
g
en
e
p
r
o
f
iles
at
th
e
s
am
e
tim
e.
T
h
e
p
r
in
cip
le
is
b
ased
o
n
th
e
h
y
b
r
id
izatio
n
o
f
n
u
cleic
ac
id
s
eq
u
en
ce
s
,
allo
win
g
r
esear
ch
er
s
to
s
im
u
ltan
eo
u
s
ly
an
aly
ze
th
e
e
x
p
r
ess
io
n
lev
els
o
f
th
o
u
s
an
d
s
o
f
g
en
es
o
r
d
etec
t
s
p
ec
if
ic
g
en
o
m
ic
s
eq
u
en
ce
s
.
T
h
e
d
im
e
n
s
io
n
ality
o
f
m
icr
o
a
r
r
ay
d
ata
o
f
ten
p
o
s
es
ch
allen
g
es
in
th
e
d
ev
el
o
p
m
en
t
o
f
m
ac
h
in
e
lear
n
i
n
g
an
d
ev
en
d
ee
p
lear
n
i
n
g
m
o
d
els
.
Ma
n
y
r
esear
ch
h
as
d
is
cu
s
s
ed
v
ar
io
u
s
tech
n
i
q
u
es
f
o
r
ad
d
r
ess
in
g
d
ata
d
im
en
s
io
n
ality
in
m
icr
o
ar
r
a
y
s
,
em
p
lo
y
i
n
g
m
eth
o
d
s
s
u
ch
as
f
ea
tu
r
e
s
elec
tio
n
an
d
d
im
en
s
io
n
ality
r
ed
u
ctio
n
.
I
n
p
r
ev
io
u
s
s
tu
d
ies
[
6
]
,
a
co
m
b
i
n
atio
n
o
f
th
e
U
-
Net
n
eu
r
al
n
e
two
r
k
an
d
u
n
s
u
p
er
v
is
ed
PC
A
alg
o
r
ith
m
s
is
u
s
ed
f
o
r
th
e
s
eg
m
en
tatio
n
o
f
ca
n
ce
r
n
ests
f
r
o
m
h
y
p
e
r
s
p
ec
tr
al
im
ag
es
o
f
b
r
ea
s
t
ca
n
ce
r
tis
s
u
e
m
icr
o
ar
r
ay
s
am
p
les.
T
h
e
PC
A
tech
n
iq
u
e
in
t
h
is
jo
u
r
n
al
aim
s
to
r
e
d
u
ce
c
o
m
p
u
tatio
n
al
co
m
p
lex
ity
a
n
d
e
n
h
an
ce
ac
cu
r
ac
y
in
th
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
.
An
o
th
e
r
jo
u
r
n
al
[
1
9
]
,
ex
p
lo
r
es
an
a
n
a
ly
tical
p
latf
o
r
m
f
o
r
g
astric
ca
n
ce
r
u
s
in
g
s
u
r
f
ac
e
-
en
h
an
ce
d
R
am
an
s
ca
tter
in
g
(
SERS
)
an
d
PC
A
-
two
-
lay
er
n
ea
r
est
n
eig
h
b
o
r
.
T
h
e
co
m
b
in
ed
P
C
A
m
o
d
el
y
ield
ed
an
ac
cu
r
ac
y
o
f
9
7
.
5
%,
s
en
s
itiv
ity
ex
ce
ed
in
g
9
0
%,
an
d
s
p
ec
if
icity
o
f
9
6
.
7
%.
I
n
th
e
th
ir
d
jo
u
r
n
al
[
2
0
]
,
PC
A
tech
n
iq
u
es
ar
e
d
is
cu
s
s
ed
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
g
astric
ca
n
ce
r
p
r
ed
ictio
n
an
d
id
e
n
tify
p
atter
n
s
an
d
d
if
f
er
en
ce
s
in
s
am
p
les f
r
o
m
p
atien
ts
with
an
d
with
o
u
t g
astri
c
ca
n
ce
r
.
PC
A
h
as
b
ec
o
m
e
o
n
e
o
f
th
e
m
o
s
t
wid
ely
u
s
ed
d
im
en
s
io
n
ality
r
ed
u
ctio
n
tech
n
i
q
u
es.
Ho
wev
er
,
wh
en
d
ea
lin
g
with
m
icr
o
a
r
r
ay
d
ata,
wh
ich
ty
p
ically
in
v
o
lv
es
a
v
as
t
n
u
m
b
er
o
f
f
ea
t
u
r
es,
alter
n
ati
v
e
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
s
u
ch
as
AB
C
an
d
SFFS
ar
e
p
ar
ticu
la
r
ly
a
d
v
an
ta
g
e
o
u
s
.
T
h
e
p
r
im
ar
y
ch
allen
g
e
w
ith
m
icr
o
a
r
r
ay
d
ata
is
th
e
cu
r
s
e
o
f
d
im
e
n
s
io
n
ality
,
wh
er
e
t
h
e
h
i
g
h
n
u
m
b
e
r
o
f
f
ea
tu
r
es
ca
n
s
ev
er
el
y
im
p
ac
t
th
e
p
er
f
o
r
m
a
n
ce
o
f
tr
ad
itio
n
al
m
eth
o
d
s
.
AB
C
,
a
b
io
-
in
s
p
ir
ed
o
p
tim
iza
tio
n
alg
o
r
ith
m
,
ex
ce
ls
in
ex
p
lo
r
in
g
lar
g
e
an
d
co
m
p
le
x
s
ea
r
ch
s
p
ac
es,
m
ak
in
g
it
h
ig
h
ly
ef
f
ec
tiv
e
f
o
r
s
elec
tin
g
r
elev
an
t
f
ea
tu
r
e
s
u
b
s
ets
in
h
ig
h
-
d
im
en
s
io
n
al
d
atasets
.
I
ts
ab
ilit
y
to
o
p
tim
ize
class
if
icatio
n
ac
cu
r
a
cy
wh
ile
r
ed
u
cin
g
r
ed
u
n
d
an
c
y
m
ak
es
it
a
r
o
b
u
s
t
ch
o
ice
f
o
r
m
icr
o
ar
r
ay
an
aly
s
is
.
J
o
u
r
n
al
f
r
o
m
[
2
1
]
ex
p
lain
s
t
h
at
th
e
AB
C
alg
o
r
ith
m
h
as
e
n
o
r
m
o
u
s
p
o
ten
tial
an
d
ca
n
b
e
im
p
lem
en
ted
as
an
ev
o
lu
tio
n
ar
y
s
tr
u
ctu
r
e
th
at
in
teg
r
ates
th
e
p
ar
am
eter
s
o
f
v
ar
io
u
s
tr
ad
itio
n
al
o
r
m
o
d
er
n
h
e
u
r
is
tic
alg
o
r
ith
m
s
.
On
e
o
f
th
o
s
e
p
o
ten
tials
is
ex
p
lain
ed
in
[
2
2
]
,
wh
e
r
e
it
u
s
es
t
h
e
ex
p
l
o
r
atio
n
f
ea
tu
r
es
o
f
t
h
e
AB
C
alg
o
r
ith
m
an
d
u
s
es
th
e
attac
k
in
g
f
ea
tu
r
e
o
f
a
n
o
th
er
alg
o
r
ith
m
n
a
m
ed
t
h
e
W
h
ale
Op
tim
izatio
n
Alg
o
r
ith
m
.
An
o
th
e
r
e
x
am
p
le
is
wh
er
e
[
2
3
]
p
r
o
p
o
s
es
an
in
teg
r
ated
s
tan
d
ar
d
er
r
o
r
-
b
ased
s
o
lu
tio
n
s
ea
r
ch
in
to
th
e
o
r
ig
i
n
al
AB
C
alg
o
r
ith
m
.
B
ased
o
n
th
e
v
ar
io
u
s
s
tu
d
ie
s
,
th
e
s
y
n
er
g
y
b
etwe
en
th
e
AB
C
alg
o
r
ith
m
an
d
o
th
er
h
eu
r
is
tic
ap
p
r
o
ac
h
es
em
er
g
es
as
a
p
o
ten
t
s
tr
ateg
y
f
o
r
tack
lin
g
th
e
lar
g
e
d
im
e
n
s
io
n
s
o
f
DNA
m
icr
o
ar
r
ay
d
atasets
an
d
th
e
cu
r
s
e
o
f
d
im
en
s
io
n
ality
.
Similar
ly
,
SF
FS
d
y
n
am
ically
b
alan
ce
s
th
e
in
clu
s
io
n
an
d
ex
clu
s
io
n
o
f
f
ea
tu
r
es
th
r
o
u
g
h
it
s
iter
ativ
e
p
r
o
ce
s
s
,
ad
ap
tin
g
to
th
e
co
m
p
lex
in
ter
ac
tio
n
s
b
etwe
en
f
ea
tu
r
es.
T
h
is
ad
ap
tab
ilit
y
e
n
s
u
r
es
th
at
th
e
s
elec
ted
f
ea
tu
r
e
s
et
p
r
o
v
id
es
o
p
tim
a
l
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
wh
ich
is
o
f
ten
n
o
t
ac
h
ie
v
ab
le
with
m
o
r
e
s
tr
aig
h
tf
o
r
war
d
m
et
h
o
d
s
.
I
n
s
tu
d
y
[
1
4
]
,
SF
FS
is
d
is
cu
s
s
ed
as
a
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
in
th
e
m
o
d
elin
g
p
r
o
ce
s
s
.
B
y
s
elec
tin
g
r
elev
a
n
t
f
ea
tu
r
e
s
u
b
s
ets
f
r
o
m
th
e
av
ailab
le
s
et,
SF
FS
h
elp
s
ac
h
iev
e
th
e
g
o
al
o
f
co
n
s
tr
u
ctin
g
a
m
iR
NA
b
io
m
a
r
k
er
p
a
n
el
th
at
ca
n
s
er
v
e
as
an
in
d
icato
r
f
o
r
b
r
ea
s
t
ca
n
ce
r
.
T
h
e
jo
u
r
n
al
[
2
4
]
ex
p
lo
r
es
v
ar
io
u
s
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es,
in
cl
u
d
in
g
f
ilter
s
,
wr
ap
p
er
s
,
an
d
em
b
ed
d
ed
ap
p
r
o
ac
h
es
.
SF
FS
f
alls
u
n
d
er
th
e
w
r
ap
p
er
ap
p
r
o
ac
h
,
an
d
th
e
s
elec
ted
f
ea
tu
r
es
ar
e
o
n
ly
co
n
s
id
er
e
d
wh
en
ac
c
u
r
ac
y
ex
ce
ed
s
8
0
%.
T
h
e
d
ata
u
s
ed
in
th
is
jo
u
r
n
a
l
is
s
o
u
r
ce
d
f
r
o
m
th
e
UC
I
m
ac
h
in
e
lear
n
in
g
m
ed
ical
d
a
ta.
An
o
th
er
jo
u
r
n
al
ad
d
r
ess
in
g
f
ilter
s
,
wr
ap
p
er
s
,
a
n
d
em
b
e
d
d
ed
ap
p
r
o
ac
h
es
an
d
u
tili
zin
g
SF
FS
as
o
n
e
o
f
its
tech
n
iq
u
es
is
[
1
3
]
.
I
n
th
is
jo
u
r
n
al,
n
o
t
o
n
ly
is
m
icr
o
ar
r
ay
d
ata
u
s
ed
,
b
u
t
th
e
a
p
p
r
o
ac
h
is
also
ap
p
lied
to
tex
t
an
aly
s
is
,
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
,
an
d
s
tr
ea
m
d
ata
an
al
y
s
is
.
T
h
e
r
esear
c
h
er
s
in
th
is
jo
u
r
n
al
p
r
o
p
o
s
e
a
n
o
v
el
ap
p
r
o
ac
h
in
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
f
o
r
h
ea
lth
ca
r
e,
g
o
v
er
n
m
en
t
s
ec
to
r
s
,
n
etwo
r
k
attac
k
p
r
e
d
ictio
n
s
,
an
d
o
th
e
r
d
o
m
ain
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
xp
lo
r
in
g
fea
tu
r
e
s
elec
tio
n
meth
o
d
fo
r
micro
a
r
r
a
y
cla
s
s
ific
a
tio
n
(
Mu
h
a
mma
d
Za
ky
Ha
ki
m
A
kma
l
)
5587
3.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
p
r
o
v
id
es
a
co
m
p
r
eh
en
s
iv
e
o
v
er
v
iew
o
f
th
e
d
e
ep
lear
n
i
n
g
al
g
o
r
ith
m
,
f
ea
t
u
r
e
s
elec
tio
n
tech
n
iq
u
es,
an
d
d
im
en
s
io
n
alit
y
r
ed
u
ctio
n
m
eth
o
d
s
em
p
lo
y
e
d
in
th
e
s
tu
d
y
.
T
h
e
p
r
im
ar
y
ai
m
is
to
id
en
tify
th
e
m
o
s
t
ef
f
ec
tiv
e
c
o
m
b
in
atio
n
a
m
o
n
g
th
e
c
h
o
s
en
tec
h
n
iq
u
es
to
ac
h
iev
e
o
p
tim
al
ac
cu
r
ac
y
i
n
ca
n
ce
r
d
etec
tio
n
.
E
ac
h
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
u
n
d
er
g
o
es
a
s
tan
d
ar
d
ized
p
r
o
ce
s
s
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
,
en
s
u
r
in
g
co
n
s
is
ten
cy
an
d
c
o
m
p
ar
a
b
ilit
y
ac
r
o
s
s
all
ap
p
r
o
ac
h
es.
All
f
ea
tu
r
es
s
elec
tio
n
u
n
d
er
g
o
es
id
en
tical
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
to
p
r
e
p
ar
e
th
e
d
ata
f
o
r
an
a
ly
s
is
.
T
h
is
in
clu
d
es
d
ata
clea
n
in
g
,
n
o
r
m
a
lizatio
n
,
an
d
tr
a
n
s
f
o
r
m
atio
n
t
o
en
s
u
r
e
u
n
if
o
r
m
ity
an
d
ac
cu
r
ac
y
in
s
u
b
s
eq
u
en
t
an
aly
s
es.
T
h
e
d
ataset
is
d
iv
i
d
ed
in
to
a
tr
ain
in
g
s
et
(
8
0
%)
an
d
a
test
in
g
s
et
(
2
0
%)
u
s
in
g
th
eir
r
esp
ec
tiv
e
m
eth
o
d
s
.
T
h
e
tr
ain
in
g
s
ets
a
r
e
th
en
u
s
ed
to
tr
ain
an
A
NN
class
if
ier
s
p
ec
if
ic
to
ea
c
h
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e.
T
h
ese
class
if
ier
s
ar
e
o
p
tim
ized
to
r
ec
o
g
n
ize
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
with
in
th
e
d
ata,
en
h
an
cin
g
th
eir
p
r
e
d
ictiv
e
ca
p
a
b
ilit
ies.
Me
an
wh
ile,
th
e
test
in
g
s
ets
m
ir
r
o
r
th
e
s
elec
ted
f
ea
tu
r
es
f
r
o
m
th
eir
c
o
r
r
esp
o
n
d
in
g
tr
ain
in
g
s
ets
an
d
ar
e
u
s
ed
to
ev
alu
ate
ea
ch
m
eth
o
d
’
s
p
er
f
o
r
m
a
n
ce
.
T
h
e
ac
cu
r
ac
y
r
e
s
u
lts
ar
e
u
s
ed
f
o
r
co
m
p
ar
is
o
n
.
B
y
ass
ess
in
g
ac
cu
r
ac
y
ac
r
o
s
s
d
if
f
er
en
t
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
r
esear
ch
e
r
s
ca
n
d
eter
m
in
e
t
h
e
s
u
p
er
io
r
f
ea
t
u
r
e
s
elec
tio
n
m
et
h
o
d
f
o
r
ca
n
ce
r
d
etec
tio
n
.
Fig
u
r
e
1
.
R
esear
ch
f
r
am
ewo
r
k
3
.
1
.
P
re
-
pro
ce
s
s
ing
T
h
e
d
ataset
u
s
ed
in
t
h
is
r
esear
ch
co
n
s
is
ts
o
f
2
5
3
in
s
tan
ce
s
o
f
d
ata
p
o
i
n
ts
f
o
r
ea
ch
p
ati
en
t.
Af
ter
u
n
d
er
g
o
in
g
clea
n
in
g
a
n
d
d
at
a
clea
n
s
in
g
p
r
o
ce
s
s
es
(
ch
ec
k
in
g
f
o
r
m
is
s
in
g
v
alu
es
a
n
d
d
u
p
licate
d
ata
)
,
n
o
p
r
o
b
lem
atic
d
ata
was
id
en
tifie
d
.
I
n
th
is
p
r
e
p
r
o
ce
s
s
in
g
s
tag
e,
th
e
tar
g
et
f
ea
tu
r
e
is
e
n
co
d
e
d
b
y
tr
an
s
f
o
r
m
in
g
th
e
lab
el
‘
No
r
m
al’
in
to
0
an
d
‘
C
an
ce
r
’
in
to
1
.
Mo
r
e
o
v
er
,
n
o
n
-
ess
en
tial
f
ea
tu
r
es
s
u
ch
as
p
ati
en
t
I
D
will
n
o
t
b
e
u
tili
ze
d
in
t
h
e
m
o
d
ellin
g
,
s
o
ir
r
elev
an
t
f
ea
t
u
r
es
ar
e
d
r
o
p
p
e
d
.
Data
n
o
r
m
aliza
tio
n
is
p
er
f
o
r
m
ed
o
n
th
e
tr
ain
in
g
d
ata
with
th
e
aim
o
f
aid
in
g
th
e
co
n
v
e
r
g
en
ce
o
f
m
o
d
ellin
g
alg
o
r
ith
m
s
m
o
r
e
q
u
ick
ly
a
n
d
g
en
er
atin
g
a
b
etter
m
o
d
el
[
2
5
]
.
T
h
e
n
o
r
m
aliza
tio
n
s
tep
em
p
lo
y
s
th
e
Stan
d
a
r
d
S
ca
ler
(
1
)
,
wh
ich
u
tili
ze
s
s
tan
d
ar
d
d
e
v
iatio
n
f
o
r
t
h
e
d
ata
af
ter
th
e
tr
ai
n
-
test
s
p
lit p
h
ase.
=
−
(
1
)
3
.
2
.
T
ra
in
-
t
est
s
pli
t
T
r
ain
-
test
s
p
lit
is
a
f
u
n
d
am
en
tal
tech
n
iq
u
e
in
m
ac
h
in
e
lear
n
in
g
th
at
is
u
s
ed
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
p
r
ed
ictiv
e
m
o
d
els.
I
t
in
v
o
lv
es
d
i
v
id
in
g
a
d
a
taset
in
to
two
s
u
b
s
ets:
o
n
e
f
o
r
tr
ain
in
g
th
e
m
o
d
el
an
d
th
e
o
th
er
f
o
r
test
in
g
its
p
er
f
o
r
m
an
ce
with
a
r
atio
o
f
8
:2
.
B
y
allo
ca
tin
g
a
m
aj
o
r
ity
o
f
th
e
d
ata
t
o
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
5
8
4
-
5
5
9
3
5588
tr
ain
in
g
s
et,
th
e
m
o
d
el
s
ee
s
m
an
y
d
i
f
f
er
en
t
ex
am
p
les,
wh
ich
h
elp
s
it
lear
n
p
atter
n
s
,
co
n
n
ec
tio
n
,
an
d
r
elatio
n
s
h
ip
in
th
e
d
ata.
A
tr
ain
-
test
s
p
lit
is
cr
u
cial
f
o
r
as
s
ess
in
g
a
m
o
d
el’
s
a
b
ilit
y
to
g
en
er
alize
to
n
ew,
u
n
s
ee
n
d
ata.
I
t
h
elp
s
d
etec
t
o
v
er
f
itti
n
g
,
wh
er
e
th
e
m
o
d
el
m
em
o
r
izes
th
e
tr
ain
in
g
d
ata
t
o
th
e
ex
ten
t
th
at
it
p
er
f
o
r
m
s
p
o
o
r
ly
o
n
n
ew,
u
n
s
e
en
s
am
p
les.
T
r
ain
-
test
s
p
lit
o
f
f
er
s
a
r
o
b
u
s
t
m
ec
h
an
is
m
f
o
r
g
au
g
in
g
t
h
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
,
m
ir
r
o
r
in
g
its
ef
f
ec
tiv
en
ess
in
m
ak
i
n
g
p
r
ed
ictio
n
s
o
n
d
ata
p
o
in
ts
.
Fu
r
th
er
m
o
r
e
,
th
is
tech
n
iq
u
e
f
u
r
n
is
h
es
an
u
n
b
iased
esti
m
ate
o
f
th
e
m
o
d
el’
s
p
e
r
f
o
r
m
an
ce
,
f
r
ee
f
r
o
m
t
h
e
b
iases
th
at
m
ay
ar
is
e
f
r
o
m
tr
ain
in
g
a
n
d
test
in
g
o
n
th
e
s
am
e
d
ataset.
3
.
3
.
P
CA
PC
A
is
a
tech
n
iq
u
e
u
s
ed
in
s
t
atis
tics
an
d
m
ac
h
in
e
lear
n
in
g
f
o
r
d
im
en
s
io
n
ality
r
ed
u
ctio
n
a
n
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
I
ts
g
o
al
is
to
tr
an
s
f
o
r
m
a
h
i
g
h
-
d
im
e
n
s
io
n
al
d
ataset
in
to
a
lo
wer
-
d
im
en
s
io
n
al
s
p
ac
e
wh
ile
r
etain
i
n
g
as
f
ew
co
m
p
o
n
en
ts
as
p
o
s
s
ib
le.
PC
A
ac
h
iev
es
th
is
b
y
tr
im
m
in
g
to
k
ee
p
th
e
h
ig
h
-
v
alu
e
d
ata
an
d
g
et
r
id
o
f
th
e
r
est;
th
is
will
g
iv
e
a
s
en
s
e
o
f
c
o
m
p
lex
ity
in
th
e
d
ataset.
Utili
zin
g
PC
A
f
o
r
d
im
e
n
s
io
n
ality
r
ed
u
ctio
n
d
ec
r
ea
s
es
th
e
co
m
p
lex
ity
o
f
d
im
en
s
io
n
s
b
y
allo
win
g
th
e
m
icr
o
ar
r
ay
d
ata
to
d
er
iv
e
its
f
ea
tu
r
es
f
r
o
m
eig
en
v
ec
to
r
s
an
d
eig
en
v
alu
es
ac
q
u
ir
ed
d
u
r
in
g
th
e
p
r
o
ce
s
s
[
2
6
]
.
PC
A
is
als
o
f
lex
ib
le
a
n
d
ca
n
an
aly
ze
d
atasets
th
at
co
n
tain
m
is
s
in
g
v
alu
es,
ca
teg
o
r
ical
d
at
a,
an
d
u
n
s
p
ec
if
ic
m
ea
s
u
r
em
e
n
ts
[
7
]
.
3
.
4
.
AB
C
AB
C
is
a
p
o
p
u
latio
n
-
b
ased
m
etah
eu
r
is
tic
in
s
p
ir
ed
b
y
th
e
m
etap
h
o
r
o
f
f
o
r
a
g
in
g
b
eh
av
io
r
o
f
h
o
n
ey
b
ee
s
in
th
eir
q
u
est
f
o
r
f
o
o
d
.
T
h
is
alg
o
r
ith
m
en
ca
p
s
u
lates
th
e
ess
en
ce
o
f
co
llab
o
r
atio
n
o
b
s
e
r
v
ed
i
n
th
e
n
atu
r
al
wo
r
ld
,
p
a
r
ticu
lar
ly
a
m
o
n
g
b
ee
s
,
to
tack
le
th
e
in
tr
icac
ies
o
f
s
o
lv
i
n
g
c
o
m
p
lex
p
r
o
b
le
m
s
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
.
At
th
e
h
ea
r
t
o
f
th
e
A
B
C
alg
o
r
ith
m
is
its
iter
ativ
e
n
atu
r
e,
wh
er
e
a
s
er
ies
o
f
p
h
ases
o
cc
u
r
to
g
r
ad
u
ally
o
p
tim
ize
p
o
s
s
ib
le
s
o
lu
tio
n
s
an
d
ac
h
iev
e
th
e
o
p
tim
al
r
esu
lt.
T
h
e
p
r
o
ce
s
s
b
eg
i
n
s
with
an
in
itializatio
n
p
h
ase.
I
n
th
is
p
h
ase,
th
e
alg
o
r
ith
m
s
ets
th
e
s
tag
e
b
y
in
itializin
g
a
p
o
p
u
latio
n
o
f
s
o
lu
tio
n
s
,
s
im
ilar
to
s
tar
tin
g
a
h
o
n
ey
b
ee
co
lo
n
y
.
T
h
en
,
t
h
e
em
p
lo
y
ed
p
h
ase
b
eg
in
s
,
wh
er
e
b
ee
s
ac
tiv
ely
e
x
p
lo
r
e
th
e
s
o
lu
tio
n
s
p
ac
e
a
n
d
u
s
e
lo
ca
l
s
ea
r
ch
m
ec
h
a
n
is
m
s
to
f
in
d
p
r
o
m
is
in
g
s
o
lu
tio
n
s
.
Fo
llo
win
g
th
e
em
p
lo
y
ed
p
h
ase,
th
e
o
n
lo
o
k
er
p
h
ase
tak
es
ce
n
ter
s
tag
e,
r
ef
lectin
g
th
e
co
llectiv
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
o
b
s
er
v
ed
as
b
y
s
tan
d
er
b
ee
s
ev
al
u
a
te
an
d
s
elec
t
s
o
lu
tio
n
s
b
ased
o
n
th
eir
q
u
ality
an
d
s
u
itab
ilit
y
.
T
h
is
p
h
ase
em
b
o
d
ies
th
e
ess
en
ce
o
f
in
f
o
r
m
ati
o
n
s
h
ar
in
g
an
d
co
llab
o
r
atio
n
,
as
o
n
lo
o
k
e
r
b
ee
s
ex
ch
an
g
e
v
al
u
ab
le
in
s
ig
h
ts
to
g
u
id
e
th
e
co
llectiv
e
p
u
r
s
u
it
o
f
o
p
tim
al
s
o
lu
tio
n
s
.
Af
ter
th
at,
th
e
AB
C
alg
o
r
ith
m
in
co
r
p
o
r
ates
th
e
s
co
u
tin
g
p
h
a
s
e
wh
er
e
th
e
s
co
u
t
b
ee
s
p
lay
a
k
ey
r
o
le
in
id
en
tify
i
n
g
an
d
r
ep
lacin
g
s
o
lu
tio
n
s
th
at
h
av
e
r
ea
c
h
ed
s
tag
n
atio
n
o
r
n
o
lo
n
g
er
h
o
ld
p
r
o
m
is
e.
T
h
i
s
p
h
ase
ad
d
s
d
y
n
am
ic
elem
en
t
s
to
th
e
alg
o
r
ith
m
,
en
s
u
r
in
g
ad
a
p
tab
ilit
y
an
d
r
esi
lien
ce
in
th
e
f
ac
e
o
f
ev
o
lv
in
g
p
r
o
b
lem
s
itu
atio
n
s
.
B
y
s
ea
m
less
ly
co
o
r
d
in
atin
g
th
ese
p
h
ases
o
f
in
itializatio
n
,
em
p
l
o
y
m
en
t,
o
n
lo
o
k
er
,
an
d
s
co
u
tin
g
,
AB
C
s
tr
ik
es
th
e
b
alan
ce
b
etwe
en
ex
p
lo
r
atio
n
an
d
ex
p
lo
itatio
n
,
g
lo
b
al
an
d
lo
ca
l
s
ea
r
ch
,
an
d
u
ltima
tely
d
eliv
er
s
u
n
p
ar
alleled
q
u
ality
.
T
h
r
o
u
g
h
th
e
iter
ativ
e
p
r
o
ce
s
s
o
f
e
x
p
lo
r
atio
n
,
ex
p
lo
itatio
n
,
an
d
in
f
o
r
m
atio
n
s
h
ar
in
g
,
AB
C
co
n
v
er
g
es
to
war
d
s
o
p
tim
al
s
o
lu
tio
n
s
b
y
b
ala
n
cin
g
lo
ca
l a
n
d
g
lo
b
al
s
ea
r
ch
[
2
1
]
.
3
.
5
.
SFF
S
SF
FS
is
a
wr
ap
p
er
f
ea
t
u
r
e
s
el
ec
tio
n
m
eth
o
d
t
h
at
will
ad
d
o
n
e
f
ea
tu
r
e
at
a
tim
e
to
th
e
s
elec
ted
s
et
o
f
f
ea
tu
r
es.
At
ea
ch
iter
atio
n
,
th
e
p
er
f
o
r
m
an
ce
is
ev
alu
ate
d
u
s
in
g
a
ch
o
s
en
e
v
alu
atio
n
m
et
h
o
d
th
r
o
u
g
h
cr
o
s
s
-
v
alid
atio
n
o
r
an
o
t
h
er
v
alid
ati
o
n
m
eth
o
d
.
T
h
e
f
ea
tu
r
e
with
th
e
h
ig
h
est
p
er
f
o
r
m
a
n
ce
will
b
e
ad
d
ed
to
th
e
s
elec
ted
s
et
[
2
7
]
.
Du
r
in
g
ea
c
h
iter
atio
n
,
SF
FS
id
en
tifie
s
t
h
e
f
ea
tu
r
es
th
at
y
ield
th
e
g
r
ea
test
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
e
n
t
wh
en
ad
d
e
d
to
t
h
e
s
elec
ted
f
ea
tu
r
e
s
et.
T
h
is
f
ea
tu
r
e
is
in
teg
r
ated
in
to
th
e
s
et
an
d
in
cr
ea
s
es
it
s
u
n
iq
u
e
n
ess
.
SF
FS
th
en
d
y
n
am
ically
ev
alu
ates
th
e
p
er
f
o
r
m
an
ce
im
p
ac
t
o
f
f
ea
t
u
r
e
r
em
o
v
al.
E
x
clu
d
i
n
g
p
r
ev
io
u
s
ly
s
elec
ted
f
ea
tu
r
es
im
p
r
o
v
es
p
e
r
f
o
r
m
an
ce
,
a
n
d
S
FF
S
s
e
lectiv
ely
r
em
o
v
es
f
ea
tu
r
es
if
th
ey
in
d
icate
r
ed
u
n
d
an
cy
o
r
n
o
is
e
in
th
e
f
ea
tu
r
e
s
et.
T
h
is
iter
ativ
e
p
r
o
ce
s
s
co
n
tin
u
es
u
n
til
n
o
f
u
r
th
er
im
p
r
o
v
em
en
t
in
p
er
f
o
r
m
an
ce
is
o
b
s
er
v
ed
o
r
a
p
r
ed
ef
in
ed
s
to
p
p
i
n
g
cr
iter
io
n
is
m
et.
B
y
s
y
s
tem
atica
lly
ex
p
lo
r
in
g
th
e
f
ea
tu
r
e
s
p
ac
e
in
th
is
way
,
S
FF
S
id
en
ti
f
ies th
e
m
o
s
t in
f
o
r
m
ativ
e
an
d
d
is
cr
im
in
ato
r
y
s
u
b
s
et
o
f
f
ea
tu
r
es f
o
r
a
g
iv
en
task
,
th
er
eb
y
m
a
x
im
izin
g
p
r
ed
ictio
n
ac
cu
r
ac
y
an
d
o
th
er
p
er
f
o
r
m
a
n
ce
m
etr
ics.
T
h
e
p
u
r
p
o
s
e
is
th
at.
3
.
6
.
ANN
-
c
la
s
s
if
ier
ANN
is
o
n
e
o
f
th
e
m
o
s
t
u
s
e
d
co
m
p
u
tatio
n
al
m
o
d
els
o
f
d
ee
p
lear
n
in
g
th
at
is
in
s
p
ir
ed
b
y
th
e
way
n
er
v
e
ce
lls
wo
r
k
in
t
h
e
b
r
ain
.
Dee
p
l
ea
r
n
in
g
au
to
m
atica
lly
lear
n
s
th
e
d
ata
f
ea
t
u
r
es
to
f
in
d
co
m
p
lex
p
atter
n
s
u
s
in
g
m
u
ltip
le
h
id
d
en
lay
e
r
s
o
f
a
n
eu
r
al
n
etwo
r
k
to
m
o
d
el
an
d
s
o
lv
e
co
m
p
lex
p
r
o
b
lem
s
[
2
8
]
.
ANN
co
n
s
is
ts
o
f
n
o
d
es
th
at
o
f
te
n
co
n
v
er
g
e
i
n
to
lay
er
s
.
T
h
e
lay
er
s
ty
p
ically
in
clu
d
e
an
in
p
u
t
lay
e
r
,
o
n
e
o
r
m
u
ltip
le
h
id
d
en
lay
er
s
,
an
d
an
o
u
tp
u
t
lay
er
.
Data
will
th
en
en
ter
th
e
in
p
u
t
la
y
er
an
d
m
ay
p
ass
th
r
o
u
g
h
th
e
h
id
d
en
lay
er
u
n
til
it
r
ea
ch
es
th
e
o
u
t
p
u
t
lay
er
[
2
9
]
.
Gr
id
s
ea
r
ch
,
r
a
n
d
o
m
s
ea
r
ch
,
a
n
d
K
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
ar
e
s
o
m
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
m
eth
o
d
s
to
b
e
u
s
ed
to
f
in
d
th
e
b
est n
u
m
b
e
r
o
f
u
n
its
in
an
ANN
h
id
d
e
n
lay
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
xp
lo
r
in
g
fea
tu
r
e
s
elec
tio
n
meth
o
d
fo
r
micro
a
r
r
a
y
cla
s
s
ific
a
tio
n
(
Mu
h
a
mma
d
Za
ky
Ha
ki
m
A
kma
l
)
5589
4.
E
XP
E
R
I
M
E
N
T
AND
R
E
SU
L
T
S
4
.
1
.
E
x
perim
ent
u
s
ing
P
CA
T
h
e
PC
A
an
aly
s
is
b
eg
in
s
b
y
ap
p
ly
in
g
t
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
d
etailed
in
th
e
m
eth
o
d
o
lo
g
y
s
ec
tio
n
.
On
ce
th
e
d
ata
h
as
b
ee
n
s
tan
d
ar
d
ized
th
r
o
u
g
h
th
e
s
tan
d
ar
d
s
ca
ler
,
th
e
s
ca
led
d
ataset
is
u
tili
ze
d
to
d
eter
m
in
e
th
e
o
p
tim
al
n
u
m
b
e
r
o
f
co
m
p
o
n
en
ts
u
s
in
g
PC
A’
s
ex
p
lain
ed
v
a
r
ian
ce
r
atio
.
B
y
p
l
o
ttin
g
th
e
c
u
m
u
lativ
e
ex
p
lain
ed
v
ar
ian
ce
r
atio
a
g
ain
s
t
th
e
n
u
m
b
er
o
f
c
o
m
p
o
n
en
ts
,
th
e
an
aly
s
is
id
en
tifie
s
a
t
h
r
esh
o
ld
w
h
er
e
th
e
cu
r
v
e
s
tar
ts
to
lev
el
o
f
f
.
T
h
is
in
f
lectio
n
p
o
in
t
in
d
icate
s
th
e
o
p
tim
al
n
u
m
b
e
r
o
f
co
m
p
o
n
en
ts
to
r
etain
.
Su
b
s
eq
u
en
tly
,
th
is
ch
o
s
en
n
u
m
b
er
o
f
co
m
p
o
n
en
ts
is
p
i
n
p
o
in
ted
u
s
in
g
a
th
r
esh
o
ld
,
en
s
u
r
in
g
th
e
m
o
s
t
in
f
o
r
m
ativ
e
f
ea
tu
r
es a
r
e
ca
p
tu
r
ed
f
o
r
f
u
r
th
er
a
n
aly
s
is
.
T
h
e
T
h
r
esh
o
ld
th
at
is
co
m
m
o
n
ly
u
s
ed
f
o
r
PC
A
r
an
g
es
f
r
o
m
9
5
%
to
9
9
%
to
d
eter
m
in
e
th
e
lev
el
o
f
v
ar
ian
ce
to
r
etain
in
th
e
t
r
a
n
s
f
o
r
m
ed
d
ata.
I
n
th
is
s
tu
d
y
,
a
9
5
%
th
r
esh
o
l
d
is
em
p
lo
y
ed
,
r
esu
ltin
g
in
2
4
co
m
p
o
n
en
ts
f
o
r
m
ed
b
y
PC
A
as
th
e
n
ew
f
ea
tu
r
es
f
o
r
m
o
d
e
lin
g
,
ju
s
t
as
s
h
o
wn
in
Fig
u
r
e
2
.
T
h
is
th
r
esh
o
l
d
s
elec
tio
n
p
r
o
ce
s
s
is
u
s
ed
to
all
o
w
f
o
r
th
e
r
ed
u
ctio
n
o
f
th
e
o
r
i
g
in
al
d
ataset,
c
o
n
s
is
tin
g
o
f
ap
p
r
o
x
im
ately
1
5
,
1
5
4
g
en
es,
to
2
4
g
en
es
th
at
ca
n
r
ep
r
esen
t
th
e
o
r
ig
in
al
1
5
,
1
5
4
g
en
es.
T
h
e
im
p
lem
en
tatio
n
o
f
PC
A
f
ac
ilit
ates
th
e
d
ataset
wh
ile
r
etain
in
g
th
e
ess
en
tial
in
f
o
r
m
atio
n
n
ec
ess
ar
y
f
o
r
m
o
d
elin
g
.
Af
ter
t
h
at,
K
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
is
th
en
u
s
ed
to
f
in
d
th
e
o
p
tim
al
n
u
m
b
er
o
f
u
n
its
in
th
e
ANN
class
if
ier
,
wh
ich
in
clu
d
es
o
n
e
h
id
d
en
lay
er
.
T
h
is
tech
n
iq
u
e
en
a
b
les
th
e
m
o
s
t
s
u
itab
le
ar
ch
itectu
r
e
f
o
r
th
e
A
NN
m
o
d
el,
en
h
an
cin
g
its
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
.
T
h
e
o
p
tim
al
co
n
f
ig
u
r
atio
n
o
b
tain
ed
f
r
o
m
K
f
o
ld
cr
o
s
s
-
v
ali
d
atio
n
is
th
en
u
tili
ze
d
in
th
e
ANN
clas
s
if
ier
an
d
u
ltima
tely
y
ield
s
a
test
ac
cu
r
ac
y
o
f
9
6
.
0
8
%
an
d
a
test
lo
s
s
o
f
0
.
1
3
7
8
.
T
h
ese
p
er
f
o
r
m
a
n
ce
m
etr
ics
s
ig
n
if
y
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
PC
A
-
b
ased
d
im
en
s
io
n
ality
r
ed
u
cti
o
n
a
p
p
r
o
ac
h
in
f
ac
ilit
atin
g
th
e
ac
c
u
r
ate
class
if
icatio
n
o
f
th
e
o
v
ar
ian
ca
n
ce
r
d
ataset.
Fig
u
r
e
2
.
PC
A
n
u
m
b
e
r
o
f
co
m
p
o
n
en
ts
4
.
2
.
E
x
perim
ent
u
s
ing
AB
C
T
h
e
AB
C
ex
p
er
im
en
t
aim
s
to
p
er
f
o
r
m
f
ea
t
u
r
e
s
elec
tio
n
o
n
o
v
ar
ian
ca
n
ce
r
d
ata
u
s
in
g
v
ar
y
in
g
p
ar
am
eter
s
,
s
p
ec
if
ically
n
C
o
lo
n
y
v
alu
es
o
f
1
0
,
2
0
,
an
d
3
0
,
with
5
0
an
d
1
0
0
iter
atio
n
s
f
o
r
ea
ch
n
C
o
lo
n
y
s
ettin
g
,
as
s
h
o
wn
in
T
ab
le
1
.
Ap
p
r
o
x
im
ately
5
0
%
-
8
7
%
o
f
th
e
f
ea
tu
r
es
ar
e
s
elec
ted
f
r
o
m
th
e
o
r
ig
in
al
d
ataset
co
n
tain
in
g
1
5
,
1
5
4
f
ea
tu
r
es.
T
h
e
ex
p
e
r
im
en
t
o
n
AB
C
was
co
n
d
u
cte
d
in
two
s
tag
es;
s
tag
e
1
with
5
0
iter
atio
n
s
an
d
s
tag
e
2
with
1
0
0
iter
atio
n
s
.
W
h
en
u
s
in
g
5
0
iter
atio
n
s
,
co
lo
n
ies
o
f
1
0
,
2
0
,
an
d
3
0
wer
e
f
o
r
m
ed
,
ea
ch
r
esu
ltin
g
in
d
if
f
er
e
n
t
s
elec
ted
f
ea
tu
r
es.
I
n
th
e
1
0
t
h
co
lo
n
y
,
1
3
,
3
0
0
f
ea
tu
r
es
wer
e
s
elec
ted
o
u
t
o
f
1
5
,
1
5
4
,
m
ak
in
g
it
th
e
h
ig
h
est
f
ea
tu
r
e
s
s
elec
ted
.
I
n
th
e
2
0
th
co
lo
n
y
,
7
,
4
9
8
f
ea
tu
r
es
wer
e
s
elec
ted
,
b
ein
g
th
e
lo
west
f
ea
tu
r
es
o
u
t
o
f
all
th
e
iter
atio
n
s
.
W
h
ile
in
th
e
3
0
th
co
lo
n
y
,
o
n
ly
7
,
6
3
7
f
ea
tu
r
es
wer
e
s
elec
ted
.
W
h
en
1
0
0
iter
atio
n
s
wer
e
u
s
ed
in
th
e
A
B
C
ex
p
er
im
en
t
o
n
th
e
d
ata,
th
e
1
0
th
co
l
o
n
y
y
ield
ed
th
e
f
ew
est
s
elec
ted
f
ea
tu
r
es
co
m
p
ar
ed
to
o
th
er
co
lo
n
ies
in
its
iter
atio
n
,
to
talin
g
7
,
5
8
0
.
W
h
ile
th
e
2
0
th
co
lo
n
y
y
ield
e
d
th
e
m
o
s
t
s
elec
ted
f
ea
tu
r
es
co
m
p
a
r
ed
t
o
o
t
h
er
co
lo
n
ies
in
its
iter
atio
n
,
t
o
talin
g
7
,
6
5
8
,
t
h
e
3
0
th
c
o
lo
n
y
y
ield
ed
a
to
tal
o
f
7
,
5
9
3
s
elec
ted
f
ea
tu
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
5
8
4
-
5
5
9
3
5590
Fo
r
n
C
o
lo
n
y
1
0
p
ar
a
m
eter
s
with
b
o
th
iter
atio
n
s
,
b
o
th
g
av
e
te
s
t
ac
cu
r
ac
y
o
f
ar
o
u
n
d
9
6
%
an
d
test
lo
s
s
o
f
0
.
3
2
6
5
an
d
0
.
1
0
5
0
,
r
esp
ec
t
iv
ely
.
Fo
r
n
C
o
lo
n
y
2
0
,
b
o
th
it
er
atio
n
s
ac
h
iev
ed
1
0
0
%
ac
cu
r
ac
y
,
with
test
lo
s
s
0
.
0
0
0
3
an
d
0
.
0
0
0
2
.
Fin
ally
,
f
o
r
n
C
o
lo
n
y
3
0
,
th
e
5
0
iter
atio
n
r
u
n
ac
h
iev
es
9
8
%
ac
cu
r
ac
y
with
a
test
lo
s
s
o
f
0
.
0
8
8
5
,
wh
ile
th
e
1
0
0
iter
atio
n
r
u
n
m
ain
tain
s
1
0
0
%
ac
cu
r
a
cy
with
a
m
in
im
al
test
lo
s
s
o
f
0
.
0
0
0
0
1
.
B
ased
o
n
T
ab
le
I
,
it
ca
n
b
e
in
f
er
r
ed
th
at
a
h
ig
h
er
n
u
m
b
e
r
o
f
iter
atio
n
s
an
d
n
C
o
lo
n
y
g
en
e
r
ally
r
esu
lt
s
in
b
etter
ac
c
u
r
ac
y
an
d
lo
s
s
s
co
r
es.
Ho
we
v
er
,
t
h
e
r
e
is
an
e
x
ce
p
tio
n
wh
er
e
f
o
r
it
er
atio
n
5
0
,
a
n
n
C
o
lo
n
y
o
f
3
0
h
as
r
elativ
ely
wo
r
s
e
r
esu
lts
co
m
p
ar
ed
t
o
n
C
o
lo
n
y
o
f
2
0
,
s
in
ce
n
C
o
lo
n
y
o
f
3
0
r
e
q
u
ir
ed
m
o
r
e
iter
atio
n
s
to
y
iel
d
b
etter
r
esu
lts
th
an
n
C
o
lo
n
y
o
f
2
0
.
Fin
ally
,
as
f
o
r
th
e
n
u
m
b
er
o
f
s
elec
ted
f
ea
t
u
r
es,
it
ca
n
b
e
s
ee
n
th
at
an
n
C
o
lo
n
y
o
f
1
0
is
to
o
litt
le
as
it
s
elec
ted
1
3
3
0
0
f
ea
t
u
r
es
in
th
e
5
0
th
iter
atio
n
c
o
m
p
ar
ed
to
th
e
7
5
8
0
f
ea
tu
r
es
in
th
e
1
0
0
th
iter
atio
n
.
T
h
is
s
h
o
ws
th
at
an
n
C
o
lo
n
y
th
at
is
to
o
s
m
all
m
ay
p
o
ten
tially
r
esu
lt
in
to
o
m
a
n
y
ir
r
ele
v
an
t
f
ea
tu
r
es
b
ein
g
s
elec
ted
.
Me
an
wh
ile,
in
n
C
o
l
o
n
y
2
0
an
d
3
0
,
it
ca
n
b
e
o
b
s
er
v
ed
th
at
b
etwe
en
th
e
5
0
th
an
d
1
0
0
t
h
iter
atio
n
,
wh
er
e
th
e
n
u
m
b
e
r
o
f
s
elec
ted
f
ea
tu
r
es
h
as
b
ar
ely
ch
an
g
ed
,
wh
ich
m
ea
n
s
th
at
it
is
alr
ea
d
y
v
er
y
clo
s
e
to
th
e
o
p
tim
al
n
u
m
b
er
o
f
f
ea
tu
r
es.
T
ab
le
1
.
AB
C
f
ea
tu
r
e
s
elec
ted
I
t
e
r
a
t
i
o
n
50
1
0
0
n
C
o
l
o
n
y
10
20
30
10
20
30
S
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
1
3
3
0
0
7
4
9
8
7
6
3
7
7
5
8
0
7
6
5
8
7
5
9
3
A
c
c
u
r
a
c
y
(
%)
96
1
0
0
98
96
1
0
0
1
0
0
Lo
ss
0
.
3
2
6
5
0
.
0
0
0
3
0
.
0
8
8
5
0
.
1
0
5
0
0
.
0
0
0
2
0
.
0
0
0
0
1
4
.
3
.
E
x
perim
ent
u
s
ing
SFF
S
Similar
to
th
e
A
B
C
ex
p
er
im
en
t,
th
e
SF
F
S a
p
p
r
o
ac
h
u
tili
ze
s
o
v
ar
ian
ca
n
ce
r
d
ata
f
o
r
f
ea
tu
r
e
s
elec
tio
n
.
Ho
wev
er
,
u
n
lik
e
AB
C
,
SF
FS
d
o
es
n
o
t
em
p
lo
y
n
C
o
lo
n
y
b
u
t r
elies
o
n
a
class
if
ier
alo
n
e
as
i
ts
esti
m
ato
r
.
I
n
th
is
s
tu
d
y
,
lo
g
is
tic
r
eg
r
ess
io
n
is
u
tili
ze
d
in
s
tead
o
f
an
ANN,
as
th
e
Ker
as
lay
er
m
o
d
el
is
n
o
t
co
m
p
atib
le
with
SF
FS
.
Ad
d
itio
n
ally
,
to
en
s
u
r
e
co
m
p
atib
ilit
y
with
SF
FS
,
th
e
y
tr
ain
d
ata
is
f
latten
ed
u
s
in
g
th
e
Nu
m
Py
r
a
v
el
f
u
n
ctio
n
;
th
is
is
d
o
n
e
s
o
th
at
t
h
e
d
ata
f
o
r
ea
c
h
elem
e
n
t
o
f
th
e
d
ata
c
o
r
r
esp
o
n
d
s
t
o
a
s
in
g
le
f
ea
tu
r
e,
m
a
k
in
g
it
ea
s
ier
to
ev
alu
ate
an
d
s
elec
t
t
h
e
f
ea
tu
r
e.
Ho
we
v
er
,
it
is
n
o
te
d
th
at
t
h
e
f
latten
e
d
tr
ain
is
o
n
ly
u
s
ed
to
f
i
n
d
th
e
f
ea
tu
r
e
o
f
th
e
o
v
ar
ian
d
ataset,
an
d
it
is
n
o
t
u
s
ed
f
o
r
tr
ain
in
g
.
On
th
e
o
th
er
h
a
n
d
,
th
e
o
r
ig
in
a
l
y
tr
ain
is
u
s
ed
as
th
e
tr
ain
in
g
in
s
tead
o
f
th
e
f
latten
ed
tr
ain
.
As
a
r
esu
lt
o
f
t
h
is
ex
p
er
im
en
t,
SF
FS
r
esu
lted
i
n
an
ac
cu
r
ac
y
o
f
9
8
.
0
4
%,
with
SF
FS
s
u
cc
es
s
f
u
lly
s
elec
tin
g
a
to
tal
o
f
7
,
5
7
7
f
ea
tu
r
es.
T
h
e
test
lo
s
s
is
r
ec
o
r
d
ed
at
0
.
0
4
7
3
,
in
d
icatin
g
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
s
elec
ted
f
ea
tu
r
es in
ac
cu
r
ately
class
if
y
in
g
o
v
ar
ia
n
ca
n
ce
r
d
ata.
T
ab
le
2
illu
s
tr
ates
th
e
r
e
m
ar
k
ab
le
p
er
f
o
r
m
an
ce
m
etr
ics
o
f
v
ar
io
u
s
f
ea
tu
r
e
s
elec
tio
n
tech
n
i
q
u
es,
with
th
e
ar
tific
ial
b
ee
co
lo
n
y
(
AB
C
)
m
eth
o
d
ac
h
ie
v
in
g
th
e
h
ig
h
es
t
ac
cu
r
ac
y
am
o
n
g
all
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
th
at
wer
e
ex
am
in
ed
.
No
tab
ly
,
AB
C
at
tain
ed
an
o
u
ts
tan
d
in
g
ac
cu
r
ac
y
o
f
1
0
0
%,
s
u
r
p
ass
in
g
b
o
th
PC
A
an
d
SF
FS
,
wh
ich
ac
h
iev
ed
ac
cu
r
ac
ies
o
f
9
6
%
an
d
9
8
%
r
esp
e
ctiv
ely
.
T
h
is
r
em
ar
k
ab
le
r
esu
lt
u
n
d
er
s
co
r
es
th
e
ef
f
ec
tiv
en
ess
o
f
AB
C
in
d
is
ce
r
n
in
g
c
r
u
cial
g
e
n
e
ex
p
r
ess
io
n
p
atter
n
s
in
d
icativ
e
o
f
o
v
ar
i
an
ca
n
ce
r
.
Fu
r
th
e
r
an
aly
s
is
r
ev
ea
ls
th
at
th
e
ex
ce
p
tio
n
al
ac
cu
r
ac
y
o
f
AB
C
ca
n
b
e
attr
ib
u
ted
to
s
p
ec
if
ic
p
ar
am
e
ter
co
n
f
ig
u
r
atio
n
s
.
I
n
p
ar
ticu
lar
,
AB
C
iter
atio
n
s
at
5
0
an
d
1
0
0
,
with
co
l
o
n
y
s
ize
s
o
f
1
0
,
2
0
,
an
d
3
0
,
wer
e
ex
p
l
o
r
ed
.
I
n
tr
ig
u
i
n
g
ly
,
th
e
co
n
f
ig
u
r
atio
n
th
at
y
ield
ed
th
e
1
0
0
%
ac
cu
r
ac
y
co
m
p
r
is
ed
AB
C
iter
atio
n
s
a
t
5
0
an
d
1
0
0
,
with
co
lo
n
y
s
ize
s
o
f
2
0
a
n
d
3
0
,
r
esp
ec
tiv
ely
.
T
h
ese
f
in
d
in
g
s
h
ig
h
lig
h
t
th
e
cr
i
tical
r
o
le
o
f
p
a
r
am
eter
o
p
tim
i
za
tio
n
in
ac
h
iev
in
g
o
p
tim
al
p
er
f
o
r
m
a
n
ce
with
AB
C
an
d
h
ig
h
lig
h
t
th
e
im
p
o
r
tan
ce
o
f
f
in
e
-
tu
n
in
g
p
ar
a
m
eter
s
to
m
a
x
im
ize
ac
cu
r
ac
y
.
T
h
e
ex
ce
p
tio
n
al
ac
cu
r
ac
y
ac
h
iev
ed
b
y
AB
C
n
o
t
o
n
ly
u
n
d
er
s
co
r
es
its
p
o
ten
tial
as
a
r
o
b
u
s
t
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
b
u
t
also
s
ig
n
if
ies
its
u
til
ity
in
en
h
an
cin
g
th
e
class
if
icatio
n
p
r
o
ce
s
s
in
m
icr
o
ar
r
ay
-
b
ased
ca
n
ce
r
d
etec
tio
n
.
Su
ch
in
s
ig
h
t
s
g
lean
ed
f
r
o
m
t
h
is
s
tu
d
y
co
n
tr
ib
u
te
s
ig
n
if
ican
tly
to
th
e
o
n
g
o
in
g
ef
f
o
r
ts
aim
ed
at
ad
v
an
cin
g
ea
r
ly
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t
s
tr
ateg
ies
f
o
r
o
v
ar
ian
ca
n
ce
r
p
atien
ts
,
u
lti
m
ately
lead
in
g
to
im
p
r
o
v
e
d
clin
ical
o
u
tc
o
m
es a
n
d
p
atien
t c
ar
e
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
r
esu
lt
M
e
t
h
o
d
F
e
a
t
u
r
e
S
e
l
e
c
t
e
d
A
c
c
u
r
a
c
y
(
%)
Lo
ss
P
C
A
24
96
0
.
1
3
7
8
A
B
C
(
5
0
,
1
0
)
1
3
3
0
0
96
0
.
3
2
6
5
A
B
C
(
5
0
,
2
0
)
7
4
9
8
1
0
0
0
.
0
0
0
3
A
B
C
(
5
0
,
3
0
)
7
6
3
7
98
0
.
0
8
8
5
A
B
C
(
1
0
0
,
1
0
)
7
5
8
0
96
0
.
1
0
5
A
B
C
(
1
0
0
,
2
0
)
7
6
5
8
1
0
0
0
.
0
0
0
2
A
B
C
(
1
0
0
,
3
0
)
7
5
9
3
1
0
0
0
.
0
0
0
0
1
SFFS
7
5
7
7
98
0
.
0
4
7
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
xp
lo
r
in
g
fea
tu
r
e
s
elec
tio
n
meth
o
d
fo
r
micro
a
r
r
a
y
cla
s
s
ific
a
tio
n
(
Mu
h
a
mma
d
Za
ky
Ha
ki
m
A
kma
l
)
5591
C
o
m
p
ar
ativ
e
an
al
y
s
is
o
f
PC
A,
AB
C
,
an
d
SF
FS
r
ev
ea
ls
d
is
t
in
ct
ap
p
r
o
ac
h
es
to
f
ea
tu
r
e
s
el
ec
tio
n
an
d
m
o
d
ellin
g
in
t
h
e
co
n
tex
t
o
f
o
v
ar
ian
ca
n
ce
r
d
etec
tio
n
.
B
ased
o
n
Fig
u
r
es
3
an
d
4
,
PC
A
d
em
o
n
s
tr
ates
its
ef
f
ec
tiv
en
ess
b
y
r
e
d
u
cin
g
th
e
d
ataset’
s
d
im
en
s
io
n
ality
to
2
4
co
m
p
o
n
en
ts
wh
ile
m
ain
tain
i
n
g
a
h
i
g
h
ac
c
u
r
ac
y
o
f
9
6
.
0
8
%
th
r
o
u
g
h
ANN
m
o
d
ellin
g
.
C
o
n
v
er
s
ely
,
AB
C
,
with
its
f
lex
ib
le
p
a
r
am
eter
tu
n
in
g
an
d
f
ea
tu
r
e
s
elec
tio
n
ca
p
ab
ilit
ies,
ac
h
iev
e
s
r
em
ar
k
ab
le
r
esu
lts
,
n
o
tab
ly
attain
in
g
a
p
e
r
f
ec
t
1
0
0
%
ac
cu
r
ac
y
u
n
d
er
o
p
tim
al
co
n
f
ig
u
r
atio
n
s
.
Me
a
n
wh
ile,
S
FF
S,
alth
o
u
g
h
u
tili
zin
g
L
o
g
is
tic
R
eg
r
ess
io
n
d
u
e
to
co
m
p
at
ib
ilit
y
co
n
s
tr
ain
ts
,
ef
f
icien
tly
s
elec
ts
7
,
5
7
7
f
ea
tu
r
es
with
a
h
ig
h
ac
cu
r
ac
y
o
f
9
8
.
0
4
%.
Ho
wev
er
,
it’s
im
p
o
r
tan
t
to
n
o
te
th
at
SF
FS
h
ad
th
e
lo
n
g
est
r
u
n
n
in
g
c
o
m
p
u
tatio
n
al
tim
e
am
o
n
g
t
h
e
th
r
ee
m
eth
o
d
s
,
wh
ich
r
e
q
u
ir
ed
m
o
r
e
th
an
a
d
a
y
to
f
in
is
h
its
co
m
p
u
tatio
n
,
wh
er
e
as
PC
A
an
d
AB
C
b
o
th
to
o
k
less
th
an
8
h
o
u
r
s
co
m
b
in
ed
.
Desp
ite
th
is
,
ea
ch
m
eth
o
d
s
h
o
wca
s
es
u
n
iq
u
e
s
tr
en
g
th
s
:
PC
A
o
f
f
er
s
s
im
p
lici
ty
an
d
ef
f
icien
t
d
im
e
n
s
io
n
ality
r
ed
u
ctio
n
,
AB
C
ex
ce
ls
in
f
in
e
-
tu
n
in
g
p
ar
am
et
er
co
n
f
ig
u
r
atio
n
s
f
o
r
o
p
tim
al
f
ea
tu
r
e
s
elec
tio
n
,
an
d
SF
FS
ef
f
icien
tly
s
elec
ts
f
ea
tu
r
es
with
h
ig
h
ac
cu
r
ac
y
,
alb
eit
with
lo
n
g
er
co
m
p
u
tatio
n
al
tim
e.
T
h
e
s
elec
tio
n
am
o
n
g
th
ese
a
p
p
r
o
ac
h
es
d
ep
en
d
s
o
n
s
ev
er
al
f
ac
to
r
s
,
in
clu
d
in
g
th
e
c
h
ar
ac
ter
is
tics
o
f
th
e
d
ataset,
av
ailab
le
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
,
an
d
th
e
s
p
ec
if
ic
o
b
jectiv
es
o
f
th
e
an
aly
s
is
.
R
esear
ch
er
s
m
u
s
t
ca
r
ef
u
lly
weig
h
th
ese
co
n
s
id
er
atio
n
s
to
ch
o
o
s
e
th
e
m
o
s
t
s
u
itab
le
m
eth
o
d
th
at
alig
n
s
with
th
eir
r
esear
ch
g
o
als
an
d
co
n
s
tr
ain
ts
.
Mo
r
eo
v
er
,
f
u
r
th
er
ex
p
l
o
r
atio
n
a
n
d
ex
p
er
im
en
tatio
n
m
ay
b
e
wa
r
r
an
ted
to
f
u
lly
u
n
d
er
s
tan
d
th
e
n
u
an
ce
s
an
d
tr
a
d
e
-
o
f
f
s
ass
o
ciate
d
with
ea
ch
tech
n
iq
u
e,
e
n
s
u
r
in
g
r
o
b
u
s
t a
n
d
r
eliab
le
r
esu
lts
in
th
e
co
n
te
x
t
o
f
o
v
a
r
ian
ca
n
ce
r
d
etec
tio
n
an
d
b
ey
o
n
d
.
Fig
u
r
e
3
.
Acc
u
r
ac
y
in
c
o
r
p
o
r
at
ed
with
ANN
d
iag
r
am
Fig
u
r
e
4
.
L
o
s
s
in
co
r
p
o
r
ated
w
ith
ANN
d
iag
r
am
5.
CO
NCLU
SI
O
N
I
n
co
n
clu
s
io
n
,
th
e
r
esear
ch
u
n
d
er
s
co
r
es th
e
cr
itical
r
o
le
o
f
f
e
atu
r
e
s
elec
tio
n
in
n
o
t o
n
ly
en
h
an
cin
g
th
e
ac
cu
r
ac
y
b
u
t
also
o
p
tim
izin
g
th
e
ef
f
icie
n
cy
o
f
m
icr
o
a
r
r
ay
d
a
ta
class
if
icatio
n
f
o
r
ca
n
ce
r
d
et
ec
tio
n
,
p
ar
ticu
lar
l
y
in
th
e
c
h
allen
g
in
g
co
n
tex
t
o
f
o
v
ar
ian
ca
n
ce
r
d
etec
tio
n
.
B
y
em
p
lo
y
in
g
ad
v
an
ce
d
tech
n
i
q
u
es
an
d
c
o
m
p
ar
in
g
th
em
,
s
u
ch
as
PC
A
f
o
r
d
im
en
s
io
n
ality
r
ed
u
ctio
n
a
n
d
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
s
lik
e
AB
C
an
d
SF
FS
,
th
e
s
tu
d
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
5
8
4
-
5
5
9
3
5592
d
em
o
n
s
tr
ates
th
e
p
o
ten
tial
f
o
r
o
p
tim
izin
g
th
e
class
if
icatio
n
p
r
o
ce
s
s
in
th
e
m
icr
o
ar
r
a
y
d
ataset.
Fro
m
o
b
s
er
v
i
n
g
th
e
ac
cu
r
ac
y
,
lo
s
s
,
an
d
r
u
n
ti
m
e
v
alu
es
d
u
r
in
g
m
u
ltip
le
ex
p
er
im
en
ts
,
it
b
ec
o
m
es
ev
id
en
t
th
at
AB
C
p
r
o
v
id
es
m
o
r
e
o
p
tim
al
r
esu
lts
co
m
p
ar
e
d
to
PC
A
an
d
SF
FS
.
AB
C
,
w
ith
its
ap
p
r
o
ac
h
in
s
p
ir
ed
b
y
t
h
e
b
eh
a
v
io
r
o
f
r
ea
l
b
ee
s
in
s
ea
r
ch
o
f
f
o
o
d
s
o
u
r
ce
s
,
ac
h
iev
es
a
r
em
ar
k
ab
le
ac
cu
r
ac
y
o
f
1
0
0
%
wh
en
u
s
in
g
n
C
o
l
o
n
y
s
ize
o
f
2
0
a
n
d
d
em
o
n
s
tr
ates
a
m
in
im
u
m
lo
s
s
o
f
0
.
0
0
0
3
.
M
o
r
eo
v
e
r
,
th
e
r
u
n
tim
e
f
o
r
im
p
lem
en
tin
g
AB
C
r
eq
u
ir
es
a
m
an
ag
ea
b
le
r
u
n
tim
e,
r
a
n
g
in
g
ar
o
u
n
d
1
to
3
h
o
u
r
s
f
o
r
ea
ch
o
f
its
ex
p
er
im
en
ts
.
On
th
e
o
t
h
e
r
h
an
d
,
PC
A,
wh
ile
s
er
v
in
g
as
a
wid
ely
u
s
ed
m
eth
o
d
f
o
r
d
im
en
s
io
n
ality
r
ed
u
ctio
n
,
y
ield
s
r
elativ
ely
lo
w
er
ac
cu
r
ac
y
r
esu
lts
co
m
p
ar
ed
to
AB
C
,
em
p
h
asizi
n
g
th
e
n
ee
d
f
o
r
m
o
r
e
s
o
p
h
is
ticated
f
ea
tu
r
e
s
elec
tio
n
ap
p
r
o
a
ch
es
in
m
icr
o
a
r
r
ay
d
ata
an
aly
s
is
.
Similar
ly
,
SF
FS
ex
h
ib
its
a
s
ig
n
if
ican
tly
l
o
n
g
e
r
r
u
n
tim
e,
r
e
n
d
er
in
g
it
in
e
f
f
icien
t
f
o
r
m
icr
o
ar
r
ay
d
ata
u
s
ag
e
in
its
cu
r
r
en
t
co
m
p
u
tati
o
n
al
en
v
ir
o
n
m
e
n
t.
Ho
wev
er
,
i
t
is
n
o
ted
th
at
SF
FS
h
as
th
e
p
o
ten
tial
to
g
en
er
ate
b
etter
o
u
tco
m
es
wh
e
n
em
p
l
o
y
ed
o
n
a
m
o
r
e
p
o
wer
f
u
l
c
o
m
p
u
tin
g
d
e
v
ice,
i
n
d
icatin
g
th
e
im
p
o
r
ta
n
ce
o
f
co
n
s
id
er
in
g
h
ar
d
war
e
ca
p
ab
ili
ties
wh
en
s
elec
tin
g
f
ea
tu
r
e
s
e
lectio
n
m
eth
o
d
s
f
o
r
c
o
m
p
lex
d
atasets
.
Giv
en
its
iter
ativ
e
n
atu
r
e
an
d
co
m
p
u
ta
tio
n
al
d
em
a
n
d
s
o
f
SF
FS
,
it
b
en
ef
its
f
r
o
m
en
h
an
ce
d
p
r
o
c
ess
in
g
p
o
wer
a
n
d
m
em
o
r
y
r
eso
u
r
ce
s
,
p
o
ten
tiall
y
u
n
lo
c
k
in
g
its
f
u
ll
ca
p
ab
ilit
i
es
in
u
n
co
v
er
in
g
s
u
b
tle
g
e
n
e
ex
p
r
ess
io
n
p
atter
n
s
ass
o
ciate
d
with
o
v
ar
ian
ca
n
ce
r
.
T
h
ese
f
in
d
in
g
s
u
n
d
e
r
s
co
r
e
th
e
s
ig
n
if
ican
ce
o
f
h
ar
n
ess
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
an
d
m
icr
o
a
r
r
ay
te
ch
n
o
lo
g
y
to
u
n
c
o
v
er
s
u
b
tle
g
en
e
ex
p
r
ess
io
n
p
atter
n
s
ass
o
ciate
d
with
o
v
ar
ian
ca
n
ce
r
.
Su
ch
en
d
ea
v
o
r
s
h
o
ld
im
m
en
s
e
p
o
ten
tial
f
o
r
ad
v
a
n
cin
g
ea
r
ly
d
etec
tio
n
a
n
d
tr
e
atm
en
t
s
tr
ateg
ies
in
ca
n
ce
r
r
esear
ch
,
u
ltima
tely
le
ad
in
g
to
im
p
r
o
v
ed
p
atien
t
o
u
tco
m
es
an
d
c
o
n
tr
ib
u
tin
g
to
th
e
b
r
o
a
d
er
ef
f
o
r
t
o
f
co
m
b
atin
g
co
m
p
lex
d
is
ea
s
es.
B
y
co
n
tin
u
ally
r
ef
in
in
g
an
d
o
p
tim
izin
g
h
o
w
co
m
p
u
ter
s
an
aly
ze
d
ata
an
d
u
n
d
er
s
tan
d
i
n
g
h
o
w
o
u
r
b
o
d
ie
s
wo
r
k
,
r
esear
ch
er
s
ca
n
p
av
e
th
e
way
f
o
r
tr
an
s
f
o
r
m
ativ
e
b
r
ea
k
th
r
o
u
g
h
s
in
th
e
f
ig
h
t a
g
ain
s
t c
an
ce
r
an
d
o
th
er
co
m
p
lex
,
d
ev
astatin
g
illn
ess
es,
b
r
in
g
i
n
g
h
o
p
e
to
m
illi
o
n
s
ar
o
u
n
d
th
e
wo
r
ld
.
RE
F
E
R
E
NC
E
S
[
1
]
E.
L
a
c
o
n
i
,
F
.
M
a
r
o
n
g
i
u
,
a
n
d
J
.
D
e
G
r
e
g
o
r
i
,
“
C
a
n
c
e
r
a
s
a
d
i
s
e
a
s
e
o
f
o
l
d
a
g
e
:
c
h
a
n
g
i
n
g
mu
t
a
t
i
o
n
a
l
a
n
d
mi
c
r
o
e
n
v
i
r
o
n
m
e
n
t
a
l
l
a
n
d
s
c
a
p
e
s
,
”
Bri
t
i
s
h
j
o
u
r
n
a
l
o
f
c
a
n
c
e
r
,
v
o
l
.
1
2
2
,
n
o
.
7
,
p
p
.
9
4
3
–
9
5
2
,
2
0
2
0
.
[
2
]
N
.
B
.
S
h
a
n
n
o
n
e
t
a
l
.
,
“
A
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
i
d
e
n
t
i
f
y
p
r
e
d
i
c
t
i
v
e
m
o
l
e
c
u
l
a
r
mar
k
e
r
s
f
o
r
c
i
s
p
l
a
t
i
n
c
h
e
m
o
se
n
s
i
t
i
v
i
t
y
f
o
l
l
o
w
i
n
g
s
u
r
g
i
c
a
l
r
e
s
e
c
t
i
o
n
i
n
o
v
a
r
i
a
n
c
a
n
c
e
r
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
rt
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
.
1
6
8
2
9
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
021
-
9
6
0
7
2
-
6.
[
3
]
M
.
K
a
l
a
i
y
a
r
a
si
a
n
d
H
.
R
a
j
a
g
u
r
u
,
“
P
e
r
f
o
r
man
c
e
a
n
a
l
y
si
s
o
f
o
v
a
r
i
a
n
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
m
i
c
r
o
a
r
r
a
y
g
e
n
e
d
a
t
a
,”
Bi
o
Me
d
Re
se
a
r
c
h
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
2
0
2
2
,
n
o
.
1
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
6
7
5
0
4
5
7
.
[
4
]
K
.
C
h
e
n
e
t
a
l
.
,
“
I
n
t
e
g
r
a
t
i
o
n
a
n
d
i
n
t
e
r
p
l
a
y
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
b
i
o
i
n
f
o
r
mat
i
c
s
a
p
p
r
o
a
c
h
t
o
i
d
e
n
t
i
f
y
g
e
n
e
t
i
c
i
n
t
e
r
a
c
t
i
o
n
r
e
l
a
t
e
d
t
o
o
v
a
r
i
a
n
c
a
n
c
e
r
c
h
e
m
o
r
e
si
s
t
a
n
c
e
,
”
B
ri
e
f
i
n
g
s
i
n
B
i
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
2
,
n
o
.
6
,
p
p
.
1
–
1
1
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
9
3
/
b
i
b
/
b
b
a
b
1
0
0
.
[
5
]
E.
L
o
t
f
i
a
n
d
A
.
K
e
s
h
a
v
a
r
z
,
“
G
e
n
e
e
x
p
r
e
ssi
o
n
m
i
c
r
o
a
r
r
a
y
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
P
C
A
–
B
EL,
”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
5
4
,
p
p
.
1
8
0
–
1
8
7
,
N
o
v
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
m
e
d
.
2
0
1
4
.
0
9
.
0
0
8
.
[
6
]
J.
W
a
n
g
e
t
a
l
.
,
“
P
C
A
-
U
-
N
e
t
b
a
se
d
b
r
e
a
st
c
a
n
c
e
r
n
e
st
se
g
m
e
n
t
a
t
i
o
n
f
r
o
m
mi
c
r
o
a
r
r
a
y
h
y
p
e
r
sp
e
c
t
r
a
l
i
ma
g
e
s,”
Fu
n
d
a
m
e
n
t
a
l
Re
se
a
rc
h
,
v
o
l
.
1
,
n
o
.
5
,
p
p
.
6
3
1
–
6
4
0
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
mr
e
.
2
0
2
1
.
0
6
.
0
1
3
.
[
7
]
B
.
M
.
S
a
l
i
h
H
a
sa
n
a
n
d
A
.
M
.
A
b
d
u
l
a
z
e
e
z
,
“
A
r
e
v
i
e
w
o
f
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
s
i
s
a
l
g
o
r
i
t
h
m
f
o
r
d
i
me
n
s
i
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
a
n
d
D
a
t
a
Mi
n
i
n
g
,
v
o
l
.
0
2
,
n
o
.
0
1
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
0
8
8
0
/
j
s
c
d
m
.
2
0
2
1
.
0
2
.
0
1
.
0
0
3
.
[
8
]
E.
N
a
z
a
r
i
,
M
.
A
g
h
e
m
i
r
i
,
A
.
A
v
a
n
,
A
.
M
e
h
r
a
b
i
a
n
,
a
n
d
H
.
Ta
b
e
s
h
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
o
l
o
r
e
c
t
a
l
c
a
n
c
e
r
w
i
t
h
a
n
d
w
i
t
h
o
u
t
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
d
o
n
m
i
c
r
o
a
r
r
a
y
d
a
t
a
,
”
G
e
n
e
R
e
p
o
r
t
s
,
v
o
l
.
2
5
,
p
.
1
0
1
4
1
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
e
n
r
e
p
.
2
0
2
1
.
1
0
1
4
1
9
.
[
9
]
R
.
M
.
A
z
i
z
,
“
N
a
t
u
r
e
-
i
n
s
p
i
r
e
d
m
e
t
a
h
e
u
r
i
st
i
c
s
mo
d
e
l
f
o
r
g
e
n
e
s
e
l
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
b
i
o
m
e
d
i
c
a
l
m
i
c
r
o
a
r
r
a
y
d
a
t
a
,
”
M
e
d
i
c
a
l
& Bi
o
l
o
g
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
\
&
C
o
m
p
u
t
i
n
g
,
v
o
l
.
6
0
,
n
o
.
6
,
p
p
.
1
6
2
7
–
1
6
4
6
,
2
0
2
2
.
[
1
0
]
E.
H
.
H
o
u
sse
i
n
,
D
.
S
.
A
b
d
e
l
mi
n
a
a
m,
H
.
N
.
H
a
ss
a
n
,
M
.
M
.
A
l
-
S
a
y
e
d
,
a
n
d
E.
N
a
b
i
l
,
“
A
h
y
b
r
i
d
b
a
r
n
a
c
l
e
s
mat
i
n
g
o
p
t
i
m
i
z
e
r
a
l
g
o
r
i
t
h
m
w
i
t
h
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
f
o
r
g
e
n
e
s
e
l
e
c
t
i
o
n
o
f
mi
c
r
o
a
r
r
a
y
c
a
n
c
e
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
6
4
8
9
5
–
6
4
9
0
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
7
5
9
4
2
.
[
1
1
]
A
.
Ja
h
w
a
r
a
n
d
N
.
A
h
m
e
d
,
“
S
w
a
r
m
i
n
t
e
l
l
i
g
e
n
c
e
a
l
g
o
r
i
t
h
ms
i
n
g
e
n
e
s
e
l
e
c
t
i
o
n
p
r
o
f
i
l
e
b
a
se
d
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
m
i
c
r
o
a
r
r
a
y
d
a
t
a
:
a
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
T
re
n
d
s
,
v
o
l
.
2
,
n
o
.
0
1
,
p
p
.
0
1
–
0
9
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
8
0
9
4
/
j
a
st
t
2
0
1
6
1
.
[
1
2
]
H
.
Y
o
u
n
i
s,
M
.
W
.
A
n
w
a
r
,
M
.
U
.
G
.
K
h
a
n
,
A
.
S
i
k
a
n
d
a
r
,
a
n
d
U
.
I
.
B
a
j
w
a
,
“
A
n
e
w
s
e
q
u
e
n
t
i
a
l
f
o
r
w
a
r
d
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
(
S
F
F
S
)
a
l
g
o
r
i
t
h
m
f
o
r
mi
n
i
n
g
b
e
s
t
t
o
p
o
l
o
g
i
c
a
l
a
n
d
b
i
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
t
o
p
r
e
d
i
c
t
p
r
o
t
e
i
n
c
o
m
p
l
e
x
e
s
f
r
o
m
p
r
o
t
e
i
n
--
p
r
o
t
e
i
n
i
n
t
e
r
a
c
t
i
o
n
n
e
t
w
o
r
k
s (P
P
I
N
s)
,
”
I
n
t
e
rd
i
sc
i
p
l
i
n
a
ry
S
c
i
e
n
c
e
s:
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
f
e
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
3
7
1
–
3
8
8
,
2
0
2
1
.
[
1
3
]
G
.
M
a
n
i
k
a
n
d
a
n
a
n
d
S
.
A
b
i
r
a
m
i
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
i
s
i
mp
o
r
t
a
n
t
:
st
a
t
e
-
of
-
t
h
e
-
a
r
t
m
e
t
h
o
d
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
d
o
mai
n
s
o
f
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
o
n
h
i
g
h
-
d
i
me
n
si
o
n
a
l
d
a
t
a
,
”
i
n
A
p
p
l
i
c
a
t
i
o
n
s
i
n
U
b
i
q
u
i
t
o
u
s
C
o
m
p
u
t
i
n
g
,
S
p
r
i
n
g
e
r
,
2
0
2
0
,
p
p
.
1
7
7
–
1
9
6
.
[
1
4
]
R
.
Zo
u
e
t
a
l
.
,
“
D
e
v
e
l
o
p
me
n
t
a
n
d
v
a
l
i
d
a
t
i
o
n
o
f
a
c
i
r
c
u
l
a
t
i
n
g
m
i
c
r
o
R
N
A
p
a
n
e
l
f
o
r
t
h
e
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
b
r
e
a
st
c
a
n
c
e
r
,
”
Bri
t
i
s
h
J
o
u
rn
a
l
o
f
C
a
n
c
e
r
,
v
o
l
.
1
2
6
,
n
o
.
3
,
p
p
.
4
7
2
–
4
8
1
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
4
1
6
-
0
2
1
-
0
1
5
9
3
-
6.
[
1
5
]
Z.
Zh
u
,
Y
.
-
S
.
O
n
g
,
a
n
d
M
.
D
a
s
h
,
“
M
a
r
k
o
v
b
l
a
n
k
e
t
-
e
m
b
e
d
d
e
d
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
f
o
r
g
e
n
e
s
e
l
e
c
t
i
o
n
,
”
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
,
v
o
l
.
4
0
,
n
o
.
1
1
,
p
p
.
3
2
3
6
–
3
2
4
8
,
N
o
v
.
2
0
0
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
0
7
.
0
2
.
0
0
7
.
[
1
6
]
M
.
A
k
a
z
a
w
a
a
n
d
K
.
H
a
s
h
i
m
o
t
o
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
o
v
a
r
i
a
n
c
a
n
c
e
r
d
i
a
g
n
o
si
s
,
”
A
n
t
i
c
a
n
c
e
r
R
e
se
a
rc
h
,
v
o
l
.
4
0
,
n
o
.
8
,
p
p
.
4
7
9
5
–
4
8
0
0
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
2
1
8
7
3
/
a
n
t
i
c
a
n
r
e
s
.
1
4
4
8
2
.
[
1
7
]
E.
S
.
P
a
i
k
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
o
n
o
f
s
u
r
v
i
v
a
l
o
u
t
c
o
mes
i
n
p
a
t
i
e
n
t
s
w
i
t
h
e
p
i
t
h
e
l
i
a
l
o
v
a
r
i
a
n
c
a
n
c
e
r
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
,
”
J
o
u
rn
a
l
o
f
G
y
n
e
c
o
l
o
g
i
c
O
n
c
o
l
o
g
y
,
v
o
l
.
3
0
,
n
o
.
4
,
2
0
1
9
,
d
o
i
:
1
0
.
3
8
0
2
/
j
g
o
.
2
0
1
9
.
3
0
.
e
6
5
.
[
1
8
]
M
.
A
.
H
o
ssa
i
n
,
S
.
M
.
S
a
i
f
u
l
I
sl
a
m,
J
.
M
.
W
.
Q
u
i
n
n
,
F
.
H
u
q
,
a
n
d
M
.
A
.
M
o
n
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
b
i
o
i
n
f
o
r
mat
i
c
s
m
o
d
e
l
s
t
o
i
d
e
n
t
i
f
y
g
e
n
e
e
x
p
r
e
ss
i
o
n
p
a
t
t
e
r
n
s
o
f
o
v
a
r
i
a
n
c
a
n
c
e
r
a
ss
o
c
i
a
t
e
d
w
i
t
h
d
i
sea
se
p
r
o
g
r
e
ss
i
o
n
a
n
d
m
o
r
t
a
l
i
t
y
,
”
J
o
u
r
n
a
l
o
f
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
0
0
,
p
.
1
0
3
3
1
3
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
.
2
0
1
9
.
1
0
3
3
1
3
.
[
1
9
]
D
.
C
a
o
e
t
a
l
.
,
“
P
C
A
-
TLN
N
-
b
a
se
d
S
ER
S
a
n
a
l
y
s
i
s
p
l
a
t
f
o
r
m
f
o
r
l
a
b
e
l
-
f
r
e
e
d
e
t
e
c
t
i
o
n
a
n
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
c
i
s
p
l
a
t
i
n
-
t
r
e
a
t
e
d
g
a
s
t
r
i
c
c
a
n
c
e
r
,
”
S
e
n
s
o
rs
a
n
d
Ac
t
u
a
t
o
rs
B:
C
h
e
m
i
c
a
l
,
v
o
l
.
3
7
5
,
p
.
1
3
2
9
0
3
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
n
b
.
2
0
2
2
.
1
3
2
9
0
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
xp
lo
r
in
g
fea
tu
r
e
s
elec
tio
n
meth
o
d
fo
r
micro
a
r
r
a
y
cla
s
s
ific
a
tio
n
(
Mu
h
a
mma
d
Za
ky
Ha
ki
m
A
kma
l
)
5593
[
2
0
]
L.
G
u
o
e
t
a
l
.
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
a
n
a
l
y
s
i
s
o
f
ser
u
m
s
a
mp
l
e
s
b
y
su
r
f
a
c
e
-
e
n
h
a
n
c
e
d
R
a
m
a
n
s
p
e
c
t
r
o
s
c
o
p
y
c
o
mb
i
n
e
d
w
i
t
h
c
h
a
r
a
c
t
e
r
i
s
t
i
c
r
a
t
i
o
me
t
h
o
d
a
n
d
P
C
A
f
o
r
g
a
st
r
i
c
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
v
e
O
p
t
i
c
a
l
H
e
a
l
t
h
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
0
2
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
4
2
/
S
1
7
9
3
5
4
5
8
1
9
5
0
0
0
3
2
.
[
2
1
]
A
.
S
h
a
r
ma,
A
.
S
h
a
r
ma,
S
.
C
h
o
u
d
h
a
r
y
,
R
.
K
.
P
a
c
h
a
u
r
i
,
A
.
S
h
r
i
v
a
s
t
a
v
a
,
a
n
d
D
.
K
u
m
a
r
,
“
A
r
e
v
i
e
w
o
n
a
r
t
i
f
i
c
i
a
l
b
e
e
c
o
l
o
n
y
a
n
d
i
t
’
s
e
n
g
i
n
e
e
r
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
,
”
J
o
u
r
n
a
l
o
f
C
ri
t
i
c
a
l
R
e
v
i
e
w
s
,
v
o
l
.
7
,
n
o
.
1
1
,
p
p
.
4
0
9
7
–
4
1
0
7
,
2
0
2
0
.
[
2
2
]
P
.
S
t
e
p
h
a
n
,
T.
S
t
e
p
h
a
n
,
R
.
K
a
n
n
a
n
,
a
n
d
A
.
A
b
r
a
h
a
m
,
“
A
h
y
b
r
i
d
a
r
t
i
f
i
c
i
a
l
b
e
e
c
o
l
o
n
y
w
i
t
h
w
h
a
l
e
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
i
mp
r
o
v
e
d
b
r
e
a
s
t
c
a
n
c
e
r
d
i
a
g
n
o
si
s,”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
3
,
n
o
.
2
0
,
p
p
.
1
3
6
6
7
–
1
3
6
9
1
,
2
0
2
1
.
[
2
3
]
K
.
H
a
n
b
a
y
,
“
A
n
e
w
st
a
n
d
a
r
d
e
r
r
o
r
b
a
sed
a
r
t
i
f
i
c
i
a
l
b
e
e
c
o
l
o
n
y
a
l
g
o
r
i
t
h
m
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s
i
n
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rs
i
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
4
,
n
o
.
7
,
p
p
.
4
5
5
4
–
4
5
6
7
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
su
c
i
.
2
0
2
1
.
0
4
.
0
1
0
.
[
2
4
]
S
.
B
a
sh
i
r
,
I
.
U
.
K
h
a
t
t
a
k
,
A
.
K
h
a
n
,
F
.
H
.
K
h
a
n
,
A
.
G
a
n
i
,
a
n
d
M
.
S
h
i
r
a
z
,
“
A
n
o
v
e
l
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
me
t
h
o
d
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
med
i
c
a
l
d
a
t
a
u
si
n
g
f
i
l
t
e
r
s
,
w
r
a
p
p
e
r
s,
a
n
d
e
mb
e
d
d
e
d
a
p
p
r
o
a
c
h
e
s,
”
C
o
m
p
l
e
x
i
t
y
,
v
o
l
.
2
0
2
2
,
n
o
.
1
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
8
1
9
0
8
1
4
.
[
2
5
]
D
.
S
i
n
g
h
a
n
d
B
.
S
i
n
g
h
,
“
I
n
v
e
s
t
i
g
a
t
i
n
g
t
h
e
i
m
p
a
c
t
o
f
d
a
t
a
n
o
r
ma
l
i
z
a
t
i
o
n
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
9
7
,
p
.
1
0
5
5
2
4
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
1
9
.
1
0
5
5
2
4
.
[
2
6
]
W
.
U
.
A
d
i
w
i
j
a
y
a
,
E.
Li
s
n
a
w
a
t
i
,
A
.
A
d
i
t
sa
n
i
a
,
D
.
S
.
K
u
s
u
m
o
,
a
n
d
o
t
h
e
r
s,
“
D
i
m
e
n
s
i
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
u
si
n
g
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
si
s
f
o
r
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
m
i
c
r
o
a
r
r
a
y
d
a
t
a
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
4
,
n
o
.
1
1
,
p
p
.
1
5
2
1
–
1
5
3
0
,
2
0
1
8
.
[
2
7
]
B
.
E
a
n
d
J.
A
k
p
a
j
a
r
o
,
“
G
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
w
i
t
h
b
a
g
g
i
n
g
f
o
r
d
n
a
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
s
I
n
S
i
g
n
a
l
a
n
d
I
m
a
g
e
S
c
i
e
n
c
e
s
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
3
1
–
3
9
,
2
0
2
1
,
d
o
i
:
1
0
.
2
9
2
8
4
/
I
JA
S
I
S
.
7
.
2
.
2
0
2
1
.
3
1
-
3
9
.
[
2
8
]
C
.
J
a
n
i
e
s
c
h
,
P
.
Zs
c
h
e
c
h
,
a
n
d
K
.
H
e
i
n
r
i
c
h
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
El
e
c
t
ro
n
i
c
m
a
rk
e
t
s
,
v
o
l
.
3
1
,
n
o
.
3
,
p
p
.
6
8
5
–
6
9
5
,
2
0
2
1
.
[
2
9
]
A
.
S
h
a
h
e
t
a
l
.
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
s
t
u
d
y
o
n
s
k
i
n
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
A
N
N
)
a
n
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
C
N
N
)
,
”
C
l
i
n
i
c
a
l
e
H
e
a
l
t
h
,
v
o
l
.
6
,
p
p
.
7
6
–
8
4
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
e
h
.
2
0
2
3
.
0
8
.
0
0
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mu
h
a
m
m
a
d
Z
a
k
y
H
a
k
im
Ak
m
a
l
a
stu
d
e
n
t
o
f
m
a
ste
r
c
o
m
p
u
t
e
r
sc
ien
c
e
in
Bin
a
Nu
sa
n
tara
Un
iv
e
rsit
y
.
His
re
se
a
rc
h
in
tere
st
is
in
m
a
c
h
in
e
lea
rn
i
n
g
a
n
d
d
e
e
p
lea
rn
i
n
g
.
His
e
m
a
il
c
a
n
b
e
c
o
n
tac
t
a
t
m
u
h
a
m
m
a
d
.
a
k
m
a
l0
0
3
@
b
in
u
s.a
c
.
id
.
De
v
i
Fi
tr
ia
n
a
h
re
c
e
iv
e
d
th
e
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Bin
a
Nu
sa
n
tara
Un
i
v
e
rsity
,
Ja
k
a
rta,
I
n
d
o
n
e
sia
,
i
n
2
0
0
0
,
a
n
d
th
e
m
a
ste
r
’s
d
e
g
re
e
i
n
i
n
f
o
rm
a
ti
o
n
t
e
c
h
n
o
l
o
g
y
a
n
d
P
h
.
D
d
e
g
re
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
fr
o
m
t
h
e
Un
iv
e
rsitas
In
d
o
n
e
sia
,
De
p
o
k
,
In
d
o
n
e
sia
,
in
2
0
0
8
a
n
d
2
0
1
5
,
r
e
sp
e
c
ti
v
e
ly
.
In
2
0
1
4
,
sh
e
h
a
d
a
sa
n
d
wic
h
p
r
o
g
ra
m
a
t
t
h
e
Lab
o
ra
to
r
y
f
o
r
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
a
n
d
ima
g
e
p
r
o
c
e
ss
in
g
a
n
d
G
IS
(P
RIP
G
IS
Lab
)
d
e
p
a
rtme
n
t
o
f
c
o
m
p
u
ter
sc
ien
c
e
,
M
ich
i
g
a
n
S
tate
Un
i
v
e
rsity
,
Eas
t
Lan
si
n
g
,
M
ich
ig
a
n
,
USA
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
e
v
i.
fit
ria
n
a
h
@b
in
u
s.a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.