I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
20
21
,
p
p
.
1
6
7
2
~
16
79
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
4
.i
3
.
pp
167
2
-
16
79
1672
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Cla
ss
ifying
clinic
a
lly
actio
na
ble genetic
m
u
tatio
ns u
sing
K
NN
a
nd SVM
Ro
hit
Chiv
u
k
u
la
1
,
T
.
J
a
y
a
L
a
k
s
h
m
i
2
,
Sa
n
k
u Sa
t
y
a
Uda
y
3
,
Sa
t
t
i Th
a
nu
j
a
P
a
v
a
ni
4
1
S
c
h
o
o
l
o
f
Co
m
p
u
ti
n
g
a
n
d
E
n
g
in
e
e
rin
g
,
Un
iv
e
rsit
y
o
f
Hu
d
d
e
rsf
iel
d
,
Hu
d
d
e
rsf
ield
,
Un
i
ted
Ki
n
g
d
o
m
2,
3,
4
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
S
R
M
Un
iv
e
rsity
,
A
n
d
h
ra
P
ra
d
e
sh
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
24
,
2
0
2
1
R
ev
i
s
ed
Oct
19
,
2
0
2
1
A
cc
ep
ted
Oct
2
7
,
2
0
2
1
Ca
n
c
e
r
is
o
n
e
o
f
th
e
m
a
jo
r
c
a
u
se
s
o
f
d
e
a
th
in
h
u
m
a
n
s.
Earl
y
d
i
a
g
n
o
sis
o
f
g
e
n
e
ti
c
m
u
tatio
n
s
th
a
t
c
a
u
se
c
a
n
c
e
r
tu
m
o
r
g
ro
w
th
lea
d
s
to
p
e
rso
n
a
li
z
e
d
m
e
d
icin
e
to
t
h
e
d
e
c
e
a
se
a
n
d
c
a
n
sa
v
e
th
e
li
f
e
o
f
m
a
jo
rit
y
o
f
p
a
ti
e
n
ts.
W
it
h
th
is
a
i
m
,
Ka
g
g
le
h
a
s
c
o
n
d
u
c
ted
a
c
o
m
p
e
ti
ti
o
n
to
c
las
sify
c
li
n
ica
ll
y
a
c
ti
o
n
a
b
le
g
e
n
e
m
u
tatio
n
s
b
a
se
d
o
n
c
li
n
ica
l
e
v
id
e
n
c
e
a
n
d
so
m
e
o
th
e
r
f
e
a
tu
re
s
re
late
d
to
g
e
n
e
m
u
tatio
n
s.
T
h
e
d
a
tas
e
t
c
o
n
tain
s
3
3
2
1
train
in
g
d
a
ta
p
o
i
n
ts
t
h
a
t
c
a
n
b
e
c
las
si
f
ied
in
to
9
c
las
se
s.
In
t
h
is
w
o
rk
,
a
n
a
t
te
m
p
t
is
m
a
d
e
to
c
las
sify
th
e
s
e
d
a
ta
p
o
i
n
ts
u
sin
g
K
-
n
e
a
re
st
n
e
i
g
h
b
o
rs
(KN
N)
a
n
d
li
n
e
a
r
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
(S
V
M
)
in
a
m
u
lt
i
c
las
s
e
n
v
iro
n
m
e
n
t.
A
s
th
e
f
e
a
tu
re
s
a
re
c
a
teg
o
rica
l,
o
n
e
h
o
t
e
n
c
o
d
i
n
g
a
s
w
e
ll
a
s
re
sp
o
n
se
c
o
d
in
g
a
re
a
p
p
l
i
e
d
to
m
a
k
e
th
e
m
su
it
a
b
l
e
to
th
e
c
las
sif
ier
s.
T
h
e
p
re
d
ictio
n
p
e
rf
o
rm
a
n
c
e
is
e
v
a
lu
a
ted
u
sin
g
lo
g
lo
ss
a
n
d
KN
N
h
a
s
p
e
rf
o
r
m
e
d
b
e
tt
e
r
w
it
h
a
lo
g
lo
ss
v
a
l
u
e
o
f
1
.
1
0
c
o
m
p
a
re
d
to
th
a
t
o
f
S
V
M
1
.
2
4
.
K
ey
w
o
r
d
s
:
Gen
etic
m
u
tatio
n
KNN
L
o
g
-
lo
s
s
Mu
lti
-
cla
s
s
clas
s
i
f
icatio
n
P
er
s
o
n
alize
d
ca
n
ce
r
tr
ea
t
m
en
t
P
r
o
b
lem
SVM
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
:
T
.
J
ay
a
L
a
k
s
h
m
i
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
,
S
R
M
U
n
iv
er
s
it
y
An
d
h
r
a
P
r
ad
esh
,
I
n
d
ia
E
m
ail:
j
a
y
a.
p
h
d
.
h
c
u
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
C
an
ce
r
is
o
n
e
o
f
t
h
e
lead
in
g
c
au
s
e
s
o
f
d
ea
th
i
n
h
u
m
an
s
.
T
h
e
m
ain
ca
u
s
e
o
f
ca
n
ce
r
is
g
e
n
e
m
u
tatio
n
s
w
it
h
i
n
ce
l
ls
.
T
h
e
s
u
r
v
iv
a
l
a
n
d
r
ec
o
v
er
y
o
f
a
ca
n
ce
r
p
atien
t
h
i
g
h
l
y
d
ep
en
d
s
o
n
d
iag
n
o
s
i
n
g
a
n
d
tr
ea
ti
n
g
it
at
an
ea
r
l
y
s
ta
g
e.
P
er
s
o
n
alize
d
tr
ea
tm
en
t
f
o
r
a
ca
n
ce
r
p
atien
t
ca
n
b
e
d
esig
n
ed
if
t
h
e
m
u
tatio
n
s
ar
e
u
n
d
er
s
to
o
d
in
ad
v
an
ce
[
1
]
.
T
h
o
u
g
h
th
er
e
ar
e
ad
v
an
ce
d
tr
ea
t
m
en
ts
f
o
r
ca
n
ce
r
,
th
e
u
n
d
er
s
tan
d
i
n
g
o
f
g
e
n
etic
m
u
tatio
n
s
i
s
li
m
ited
b
y
a
lar
g
e
a
m
o
u
n
t
o
f
m
an
u
al
w
o
r
k
[
2
]
.
Me
m
o
r
ial
Slo
an
Ketter
i
n
g
C
an
ce
r
(
MS
KC
C
)
h
as
co
m
e
u
p
w
it
h
an
e
x
p
er
t
k
n
o
w
led
g
e
b
ase
d
escr
ib
in
g
th
e
a
n
n
o
tatio
n
s
o
f
n
i
n
e
clas
s
es
o
f
cli
n
icall
y
ac
ti
o
n
ab
le
g
en
e
s
.
T
h
is
p
r
o
b
lem
ca
n
b
e
m
o
d
elled
as
a
m
u
lt
i
-
c
lass
cla
s
s
i
f
icat
io
n
p
r
o
b
lem
.
I
n
th
e
y
ea
r
2
0
1
7
,
MSKC
C
lau
n
c
h
ed
a
co
m
p
eti
tio
n
,
o
n
Kag
g
le
[
3
]
t
o
f
ac
ilit
ate
p
er
s
o
n
alize
d
ca
n
ce
r
tr
ea
tm
e
n
t
to
th
e
p
atien
ts
[
4
]
.
T
h
e
task
is
to
d
ev
elo
p
class
i
f
icatio
n
m
o
d
els
u
tili
zi
n
g
t
h
e
te
x
t
in
th
e
g
i
v
e
n
m
ed
ical
ar
ticle
s
t
h
at
ca
n
p
r
ed
ict
o
n
co
g
e
n
icit
y
a
n
d
m
u
tatio
n
ef
f
ec
t
o
f
th
e
g
en
e
s
s
p
ec
if
ied
in
th
e
co
n
ten
t.
I
n
th
is
ass
ess
m
e
n
t,
it
is
p
r
o
p
o
s
ed
to
u
n
d
er
s
ta
n
d
th
e
d
ata
an
d
to
ex
a
m
i
n
e
t
w
o
clas
s
i
f
icat
io
n
alg
o
r
it
h
m
s
o
n
t
h
e
d
ataset.
2.
P
RO
B
L
E
M
ST
AT
E
M
E
NT
2
.
1
.
P
ro
ble
m
s
t
a
t
e
m
ent
G
iv
e
n
a
s
et
o
f
g
en
e
ti
c
m
u
tat
i
o
n
s
w
i
th
th
e
i
r
a
s
s
o
c
i
at
e
d
f
e
a
t
u
r
e
s
,
o
n
e
f
e
a
tu
r
e
b
e
in
g
a
l
o
n
g
t
ex
t
r
e
p
r
e
s
en
t
in
g
th
e
c
li
n
i
c
a
l
ev
i
d
en
c
e
a
b
o
u
t
th
e
m
u
t
at
i
o
n
g
iv
en
b
y
an
e
x
p
e
r
t
,
an
d
l
a
b
e
l
l
e
d
w
ith
o
n
e
o
f
n
in
e
p
o
s
s
i
b
l
e
c
l
a
s
s
l
a
b
el
s
,
th
e
p
r
o
b
l
em
o
f
g
e
n
e
m
u
ta
t
i
o
n
c
la
s
s
if
i
ca
t
i
o
n
is
t
o
p
r
e
d
i
c
t
a
cl
a
s
s
la
b
e
l
f
r
o
m
1
t
o
9
f
o
r
a
g
en
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
la
s
s
i
fyin
g
clin
ica
lly
a
ctio
n
a
b
le
g
en
etic
mu
ta
tio
n
s
u
s
in
g
K
N
N
a
n
d
S
V
M
(
R
o
h
it C
h
ivu
ku
la
)
1673
m
u
t
at
i
o
n
in
s
t
an
c
e
w
ith
m
is
s
i
n
g
l
a
b
el
.
A
s
th
e
p
r
e
d
i
c
ti
o
n
i
s
n
o
t
b
i
n
a
r
y
,
b
u
t
am
o
n
g
1
t
o
9
,
th
is
is
a
m
u
l
t
i
-
c
l
as
s
class
i
f
icatio
n
p
r
o
b
lem
.
2
.
2
.
Da
t
a
s
et
des
cr
iptio
n
T
h
e
co
m
p
etitio
n
lau
n
c
h
er
[
3
]
p
r
o
v
id
ed
a
s
ep
ar
ate
tr
ain
an
d
test
s
ets
co
n
s
i
s
ti
n
g
o
f
t
h
e
g
en
e
tic
in
f
o
r
m
atio
n
o
f
ea
ch
i
n
s
ta
n
ce
i
s
s
p
an
n
ed
o
v
er
t
w
o
d
i
f
f
er
e
n
t f
i
les
as
:
−
tr
ain
i
n
g
_
v
ar
ian
t
s
(
I
D,
g
en
e,
v
ar
iatio
n
s
,
an
d
clas
s
)
:
C
o
n
tain
s
th
e
in
f
o
r
m
at
io
n
ab
o
u
t
th
e
g
e
n
etic
m
u
ta
tio
n
s
s
u
c
h
as
g
en
e,
v
ar
iatio
n
a
n
d
class
to
w
h
ic
h
t
h
is
m
u
tatio
n
b
elo
n
g
s
to
.
−
tr
ain
i
n
g
_
te
x
t
(
I
D,
tex
t
)
:
C
o
n
tain
s
a
lo
n
g
tex
t
d
escr
ib
in
g
th
e
clin
ical
ev
id
en
ce
th
at
h
u
m
a
n
ex
p
er
ts
u
s
e
to
class
i
f
y
th
e
g
en
e
tic
m
u
t
atio
n
s
.
−
B
o
th
th
ese
d
ata
f
iles
h
av
e
a
co
m
m
o
n
co
lu
m
n
ca
lled
I
D
th
r
o
u
g
h
w
h
ic
h
t
h
e
y
ca
n
b
e
j
o
in
ed
.
Si
m
i
lar
l
y
,
t
w
o
f
iles
f
o
r
test
in
g
w
it
h
s
i
m
ilar
i
n
f
o
r
m
atio
n
ar
e
p
r
o
v
id
ed
.
Gen
etic
m
u
tat
io
n
s
ar
e
class
i
f
ied
in
to
n
in
e
d
if
f
er
e
n
t
class
e
s
.
T
h
e
c
o
m
p
eti
tio
n
lau
n
c
h
er
p
r
o
v
id
ed
a
s
ep
ar
ate
tr
ain
an
d
test
s
ets.
An
ex
a
m
p
le
d
ata
p
o
in
t
in
th
e
tr
ain
i
n
g
v
ar
ian
t
s
is
s
h
o
w
n
i
n
T
ab
le
1
.
T
h
er
e
ar
e
3
,
3
2
1
tr
ain
in
g
i
n
s
tan
ce
s
an
d
5
,
6
6
7
test
in
g
in
s
ta
n
c
es i
n
t
h
e
d
ataset.
T
ab
le
1
.
E
x
am
p
le
d
ata
p
o
in
t
F
i
l
e
Ex
a
mp
l
e
d
a
t
a
p
o
i
n
t
t
r
a
i
n
i
n
g
_
v
a
r
i
a
n
t
s
(
I
D
,
G
e
n
e
,
V
a
r
i
a
t
i
o
n
,
C
l
a
ss)
0
,
F
A
M
5
8
A
,
T
r
u
n
c
a
t
i
n
g
M
u
t
a
t
i
o
n
s,
1
t
r
a
i
n
i
n
g
_
t
e
x
t
(
I
D
,
Te
x
t
)
0
|
|
<
l
o
n
g
t
e
x
t
d
e
scri
b
i
n
g
a
b
s
t
r
a
c
t
o
f
c
l
i
n
i
c
a
l
>
2
.
3
.
E
x
plo
ra
t
o
ry
da
t
a
a
na
l
y
s
is
P
er
f
o
r
m
i
n
g
ex
p
lo
r
ato
r
y
d
ata
an
al
y
s
is
o
n
d
atase
t
h
e
lp
s
i
n
u
n
d
er
s
tan
d
i
n
g
th
e
d
ata
in
d
ep
th
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
i
n
s
ta
n
ce
s
o
v
er
9
class
es
in
t
h
e
tr
ain
i
n
g
s
et
i
s
s
h
o
w
n
i
n
Fig
u
r
e
1
.
Fro
m
th
e
h
is
to
g
r
a
m
,
C
las
s
7
h
as
h
ig
h
es
t
n
u
m
b
er
o
f
i
n
s
tan
ce
s
co
n
tai
n
in
g
2
8
.
6
%
o
f
to
tal
tr
ain
in
g
d
ataset
a
n
d
class
8
w
it
h
lo
w
es
t
n
u
m
b
er
(
0
.
5
6
%).
Fo
r
a
class
if
icatio
n
task
,
ex
p
lo
r
ato
r
y
d
ata
an
al
y
s
is
(
E
D
A
)
f
u
r
th
er
h
elp
s
i
n
d
eter
m
in
i
n
g
w
h
ich
f
ea
t
u
r
es a
r
e
u
s
e
f
u
l f
o
r
th
e
m
ac
h
in
e
lear
n
i
n
g
ta
s
k
.
Fig
u
r
e
1
.
Dis
tr
ib
u
tio
n
o
f
i
n
s
ta
n
ce
s
o
v
er
9
class
e
s
2
.
4
.
E
v
a
lua
t
i
o
n
m
ea
s
ure
s
T
h
e
f
o
llo
w
i
n
g
e
v
al
u
atio
n
m
etr
ics ar
e
u
s
ed
in
t
h
i
s
w
o
r
k
.
−
L
o
g
lo
s
s
[
5
]
,
[
6
]
:
L
o
g
lo
s
s
m
etr
ic
is
co
m
m
o
n
l
y
u
s
ed
in
m
u
lti
-
clas
s
cla
s
s
i
f
icatio
n
p
r
o
b
lem
s
.
T
h
is
m
e
tr
ic
co
n
s
id
er
s
t
h
e
p
r
o
b
ab
ilit
ies
o
f
ea
c
h
p
r
o
b
le
m
i
n
s
ta
n
ce
b
el
o
n
g
i
n
g
to
ea
c
h
clas
s
a
n
d
s
u
m
s
u
p
.
As
t
h
e
p
r
o
b
a
b
ilit
ies
ar
e
clo
s
u
r
e
to
th
e
tr
u
e
clas
s
m
e
m
b
er
s
h
ip
,
th
e
b
etter
w
ill
b
e
th
e
v
al
u
e
o
f
lo
g
lo
s
s
.
I
t
is
a
m
ea
s
u
r
e
o
f
u
n
ce
r
tain
t
y
,
s
o
a
l
o
w
lo
g
lo
s
s
m
ea
n
s
a
lo
w
u
n
c
er
tain
t
y
.
T
h
e
id
ea
l
v
al
u
e
o
f
lo
g
lo
s
s
is
0
f
o
r
a
s
tr
o
n
g
cla
s
s
i
f
ier
.
I
n
th
e
g
e
n
e
m
u
tatio
n
d
ata
s
et,
f
o
r
ea
ch
I
D
i
n
t
h
e
tes
t
s
et,
t
h
e
class
i
f
icat
io
n
al
g
o
r
ith
m
m
u
s
t
p
r
ed
ic
t
a
p
r
o
b
a
b
ilit
y
f
o
r
ea
ch
o
f
th
e
9
class
es
a
g
en
et
ic
m
u
tatio
n
c
an
b
e
class
i
f
ied
o
n
.
Ma
n
y
o
f
th
e
clas
s
if
icatio
n
p
r
o
b
lem
s
e
v
alu
ate
t
h
eir
p
er
f
o
r
m
an
ce
u
s
i
n
g
ac
cu
r
ac
y
.
A
cc
u
r
ac
y
ca
n
b
e
s
o
m
eti
m
e
m
is
lead
i
n
g
i
f
th
e
d
atase
t
is
i
m
b
alan
ce
d
.
C
o
n
f
u
s
io
n
m
atr
i
x
g
iv
es
a
b
et
ter
p
ictu
r
e
w
h
er
e
th
e
ch
o
s
en
clas
s
i
f
icatio
n
m
o
d
el
is
p
er
f
o
r
m
i
n
g
w
ell
an
d
w
h
at
t
y
p
e
s
o
f
er
r
o
r
s
it is
m
ak
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
3
,
Dec
em
b
er
20
21
:
1
6
7
2
-
16
79
1674
−
C
o
n
f
u
s
io
n
m
atr
ix
:
A
co
n
f
u
s
i
o
n
m
atr
ix
f
o
r
a
n
-
cla
s
s
p
r
o
b
l
e
m
w
ill
b
e
an
n
X
n
m
atr
i
x
,
w
h
er
e
co
lu
m
n
s
co
r
r
esp
o
n
d
to
th
e
p
r
ed
icted
class
lab
els
an
d
th
e
r
o
w
s
co
r
r
esp
o
n
d
s
to
th
e
ac
tu
al
[
7
]
-
[
9
]
.
T
h
e
m
a
in
d
iag
o
n
al
g
iv
e
s
th
e
co
r
r
ec
t
p
r
e
d
ictio
n
s
.
T
h
at
is
,
th
e
ca
s
es
w
h
er
e
th
e
a
ctu
al
v
al
u
es
an
d
th
e
m
o
d
el
p
r
ed
ictio
n
s
ar
e
th
e
s
a
m
e.
I
n
th
i
s
p
r
o
b
lem
,
th
e
m
at
r
ix
is
o
f
s
ize
9
X
9
.
E
ac
h
ce
ll
[
i,j
]
r
e
p
r
esen
ts
n
u
m
b
er
o
f
p
o
in
ts
o
f
class
i
ar
e
p
r
ed
icted
to
b
elo
n
g
to
class
j
.
T
h
e
id
ea
l v
alu
e
o
f
co
n
f
u
s
io
n
m
atr
i
x
C
ca
n
b
e
C
[
i,j
]
=
0
if
i≠
j
=
Nu
m
b
er
o
f
in
s
tan
ce
s
o
f
clas
s
i(
o
r
j)
if
i=j
−
P
r
ec
is
io
n
m
a
tr
ix
:
P
r
ec
is
io
n
is
th
e
f
r
ac
tio
n
o
f
co
r
r
ec
tly
p
r
ed
icted
in
s
tan
ce
s
o
u
t
o
f
to
tal
p
r
ed
ictio
n
s
f
o
r
a
g
iv
e
n
cla
s
s
[
8
]
,
[
9
]
.
P
r
ec
is
io
n
is
g
o
o
d
if
co
s
t o
f
w
r
o
n
g
b
elo
n
g
in
g
n
e
s
s
p
r
ed
ictio
n
to
a
class
.
−
R
ec
all
m
atr
i
x
:
R
ec
all
is
t
h
e
ca
p
tu
r
e
o
f
co
r
r
ec
t
p
r
e
d
ictio
n
s
am
o
n
g
to
tal
in
s
ta
n
ce
s
b
elo
n
g
in
g
to
th
e
class
[
8
]
,
[
9
]
.
R
ec
all
is
g
o
o
d
if
co
s
t
o
f
i
d
en
tify
i
n
g
an
in
s
tan
ce
w
h
ich
is
a
m
e
m
b
er
o
f
th
e
class
.
I
f
a
p
atien
t
w
h
o
is
ca
n
ce
r
o
u
s
i
s
n
o
t p
r
ed
icted
,
it is
a
h
u
g
e
lo
s
s
to
th
e
p
atien
t.
3.
RE
L
AT
E
D
L
I
T
E
RA
T
UR
E
Ma
ch
i
n
e
lear
n
i
n
g
ca
n
aid
ca
n
ce
r
d
iag
n
o
s
is
e
f
f
ic
ien
t
l
y
[
1
0
]
.
C
li
n
ic
al
r
esear
ch
d
ata
r
elate
d
to
g
en
eti
c
d
etail
ca
n
p
r
o
v
id
e
im
p
o
r
tan
t
i
n
s
i
g
h
ts
o
n
ca
n
ce
r
[
1
1
]
.
Dif
f
er
en
t
t
y
p
es
o
f
ca
n
ce
r
s
h
a
v
e
b
ee
n
class
i
f
ied
u
tili
zi
n
g
th
e
g
en
e
ex
p
r
ess
io
n
s
in
[
1
2
]
.
T
h
e
ar
ticles
o
n
b
io
m
ed
ical
d
ata
ac
t
as
a
s
tr
o
n
g
s
o
u
r
ce
f
o
r
t
h
e
clas
s
i
f
icatio
n
o
f
clin
icall
y
ac
tio
n
ab
le
g
e
n
etic
m
u
tatio
n
s
[
1
3
]
.
T
o
u
tili
ze
th
e
k
n
o
w
led
g
e
b
ase
av
ailab
le
i
n
th
e
f
o
r
m
o
f
d
o
cu
m
e
n
ts
at
P
u
b
Me
d
d
atab
ase,
a
co
m
p
eti
tio
n
h
as
b
ee
n
la
u
n
ch
ed
at
Kag
g
le
i
n
w
h
ic
h
a
d
at
aset
o
f
o
n
co
g
e
n
es,
t
h
eir
r
elat
ed
m
u
tatio
n
s
w
it
h
ar
ticles.
T
h
e
ai
m
o
f
t
h
e
co
m
p
etitio
n
ca
n
b
e
b
asicall
y
v
ie
w
e
d
as
tex
t
clas
s
if
icatio
n
,
b
u
t
i
t
i
s
m
o
r
e
ch
alle
n
g
in
g
th
an
t
h
at.
Z
h
an
g
et
a
l
.,
ar
e
th
e
r
u
n
n
er
s
o
f
th
e
co
m
p
etitio
n
an
d
h
a
v
e
d
o
cu
m
e
n
ted
t
h
eir
s
o
lu
tio
n
in
[
1
4
]
.
T
h
e
p
r
im
ar
y
p
r
o
b
le
m
t
h
e
y
h
av
e
f
ac
ed
in
cla
s
s
i
f
icatio
n
i
s
t
h
at
t
w
o
g
en
e
s
ca
n
h
av
e
s
a
m
e
cl
in
ical
ev
id
e
n
ce
,
w
it
h
d
if
f
er
e
n
t
m
u
tatio
n
s
(
clas
s
lab
e
l)
.
T
h
er
ef
o
r
e,
th
e
au
t
h
o
r
s
o
f
[
1
4
]
f
elt
th
at
tex
t
clas
s
i
f
icatio
n
alo
n
e
ca
n
n
o
t
s
o
l
v
e
th
e
p
r
o
b
lem
.
Z
h
a
n
g
et
a
l
.,
p
er
f
o
r
m
ed
a
n
o
v
el
f
ea
tu
r
e
en
g
i
n
e
er
in
g
f
o
r
o
b
tain
in
g
th
r
ee
t
y
p
e
s
o
f
f
ea
t
u
r
es.
First
b
ein
g
d
o
cu
m
e
n
t
f
ea
tu
r
es
d
er
iv
ed
f
r
o
m
clin
ical
e
v
id
en
ce
d
o
cu
m
e
n
ts
;
s
ec
o
n
d
th
e
en
tit
y
f
ea
tu
r
es
ar
e
d
er
iv
ed
f
r
o
m
m
u
tat
io
n
s
a
n
d
clin
ical
e
v
id
en
ce
an
d
f
in
a
ll
y
t
h
ir
d
ar
e
n
a
m
e
f
ea
t
u
r
es
ex
tr
ac
ted
f
r
o
m
m
u
tatio
n
,
ev
id
en
ce
u
s
i
n
g
w
o
r
d
e
m
b
ed
d
in
g
m
o
d
el.
T
h
e
au
th
o
r
s
o
f
[
1
5
]
ap
p
ly
o
n
e
h
o
t
en
co
d
in
g
o
n
g
e
n
es
a
n
d
th
eir
m
u
tatio
n
s
to
co
n
v
er
t
th
e
f
ea
tu
r
e
s
to
n
u
m
er
ic
an
d
TF
-
I
DF
m
ec
h
a
n
i
s
m
to
ex
tr
ac
t
f
ea
t
u
r
es
f
r
o
m
clin
ical
ev
id
en
ce
.
Gan
g
m
i
n
et
a
l
.,
[
1
6
]
u
s
e
TF
-
I
DF
tech
n
iq
u
e
to
ex
tr
ac
t te
x
t
f
e
atu
r
es
f
r
o
m
cli
n
ical
ev
id
en
ce
d
ata.
T
h
e
w
o
r
k
at
[
1
7
]
u
s
es
w
o
r
d
e
m
b
ed
d
i
n
g
tech
n
iq
u
es
a
n
d
tr
ai
n
t
h
eir
m
o
d
el
u
s
in
g
co
n
v
o
l
u
ti
o
n
al
n
e
u
r
al
ne
t
w
o
r
k
(
C
NN)
alg
o
r
it
h
m
to
class
i
f
y
ca
n
ce
r
liter
at
u
r
e
b
ase
d
o
n
ca
n
ce
r
h
all
m
ar
k
s
.
Dee
p
lear
n
in
g
al
g
o
r
ith
m
s
s
ee
m
to
w
o
r
k
e
f
f
icie
n
t
i
n
t
h
is
d
o
m
ai
n
.
A
co
m
p
r
e
h
en
s
iv
e
r
e
v
ie
w
o
f
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es
is
g
i
v
en
i
n
[
1
8
]
.
E
r
r
o
r
s
in
s
u
ch
s
e
n
s
i
tiv
e
p
r
o
b
le
m
s
ca
n
b
e
v
er
y
co
s
tl
y
.
An
i
n
ter
esti
n
g
co
s
t
s
e
n
s
iti
v
e
ap
p
r
o
ac
h
f
o
r
m
u
lti
-
clas
s
p
r
o
b
lem
h
as
b
ee
n
d
is
c
u
s
s
ed
i
n
[
1
9
]
,
w
h
ic
h
p
en
alize
s
th
e
m
i
s
class
if
ica
tio
n
s
to
im
p
r
o
v
e
lea
r
n
in
g
in
t
h
e
m
o
d
el.
T
h
er
ef
o
r
e,
th
er
e
is
a
s
tr
o
n
g
n
e
ed
o
f
m
o
r
e
ef
f
ic
ien
t
m
o
d
els i
n
f
u
t
u
r
e.
R
ef
er
e
n
ce
[
2
0
]
an
d
[
2
1
]
d
is
cu
s
s
th
e
u
s
a
g
e
o
f
m
eta
h
e
u
r
is
ti
c
alg
o
r
ith
m
s
a
f
ter
f
u
zz
y
m
o
d
ellin
g
t
h
e
p
r
o
b
lem
.
A
b
asi
et
al
d
ev
elo
p
a
clu
s
ter
-
b
ased
ap
p
r
o
ac
h
f
o
r
tex
t
d
o
cu
m
en
ts
b
y
tr
ea
ti
n
g
te
x
t
d
o
cu
m
e
n
t
clu
s
ter
i
n
g
as
d
is
cr
ete
o
p
ti
m
iz
atio
n
p
r
o
b
lem
[
2
2
]
.
R
u
s
ta
m
e
t
al
p
r
o
p
o
s
e
a
n
e
w
f
ea
t
u
r
e
s
el
ec
tio
n
m
e
th
o
d
an
d
u
s
e
K
-
m
ea
n
s
cl
u
s
ter
i
n
g
a
s
t
h
e
class
i
f
ier
u
s
i
n
g
r
ad
ial
b
asis
f
u
n
ctio
n
an
d
p
o
l
y
n
o
m
ial
k
e
r
n
el
f
u
n
ctio
n
[
2
3
]
.
K
-
m
ea
n
s
clu
s
ter
i
n
g
i
s
s
e
n
s
iti
v
e
to
th
e
p
ar
am
eter
k
.
S
u
d
h
a
et
al
p
r
o
p
o
s
e
a
n
o
v
el
m
o
d
elli
n
g
o
f
clu
s
ter
in
g
to
g
et
o
p
tim
u
m
n
u
m
b
er
o
f
clu
s
ter
s
[
2
4
]
.
4.
P
RO
P
O
SE
D
AP
P
RO
ACH
An
y
m
ac
h
in
e
lear
n
in
g
tas
k
,
th
e
ap
p
r
o
ac
h
in
th
is
w
o
r
k
also
f
o
llo
w
s
s
tep
s
s
u
ch
as
p
er
f
o
r
m
in
g
ex
p
lo
r
ato
r
y
d
ata
a
n
al
y
s
i
s
,
p
r
ep
r
o
ce
s
s
in
g
,
th
e
n
tr
ai
n
i
n
g
th
e
class
i
f
icat
io
n
m
o
d
el
w
it
h
t
r
ain
d
ata
an
d
th
e
n
ev
alu
a
tin
g
t
h
e
p
er
f
o
r
m
a
n
ce
u
s
i
n
g
p
er
f
o
r
m
an
ce
m
etr
ic.
B
u
t
f
ea
tu
r
e
e
n
g
i
n
ee
r
i
n
g
,
p
r
ep
r
o
ce
s
s
in
g
an
d
class
i
f
icatio
n
p
ar
a
m
eter
s
v
ar
y
f
o
r
d
if
f
er
e
n
t d
ataset
s
.
T
h
e
ap
p
r
o
ac
h
is
s
u
m
m
ar
ized
in
F
ig
u
r
e
2.
4
.
1
.
P
re
-
pro
ce
s
s
ing
T
h
e
m
ac
h
i
n
e
lear
n
in
g
al
g
o
r
ith
m
s
t
h
at
ar
e
in
ten
d
ed
to
u
s
e
i
n
th
is
w
o
r
k
r
eq
u
ir
e
th
e
i
n
p
u
t
an
d
o
u
tp
u
t
v
ar
iab
les
as
n
u
m
er
ic.
T
h
er
ef
o
r
e,
th
e
ca
teg
o
r
ical
f
ea
tu
r
e
s
m
u
s
t
b
e
e
n
co
d
ed
to
n
u
m
b
er
s
.
T
w
o
en
co
d
i
n
g
s
ar
e
u
s
ed
i
n
th
is
w
o
r
k
:
o
n
e
h
o
t
en
co
d
in
g
[
2
5
]
an
d
r
esp
o
n
s
e
co
d
in
g
[
2
6
]
.
I
n
o
n
e
h
o
t
e
n
co
d
in
g
,
t
h
e
f
ea
tu
r
e
i
s
r
ep
r
esen
ted
as
a
v
ec
to
r
o
f
s
ize
n
if
th
er
e
ar
e
n
d
is
tin
c
t
n
u
m
b
er
o
f
ca
teg
o
r
ies,
w
it
h
a
1
/0
s
h
o
w
i
n
g
p
r
ese
n
ce
o
r
ab
s
en
ce
o
f
t
h
at
v
alu
e.
Usi
n
g
r
esp
o
n
s
e
co
d
in
g
,
a
d
ata
p
o
i
n
t
i
s
r
ep
r
esen
ted
as
a
v
ec
to
r
s
h
o
w
i
n
g
t
h
e
p
r
o
b
ab
ilit
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
la
s
s
i
fyin
g
clin
ica
lly
a
ctio
n
a
b
le
g
en
etic
mu
ta
tio
n
s
u
s
in
g
K
N
N
a
n
d
S
V
M
(
R
o
h
it C
h
ivu
ku
la
)
1675
o
f
th
e
d
ata
p
o
in
t b
elo
n
g
i
n
g
to
a
s
p
ec
if
ic
c
lass
g
i
v
e
n
a
ca
te
g
o
r
y
.
Fo
r
a
k
-
cla
s
s
cla
s
s
i
f
ica
tio
n
p
r
o
b
lem
,
t
h
er
e
w
il
l
b
e
k
n
e
w
f
ea
tu
r
es
w
h
ic
h
e
m
b
e
d
th
e
p
r
o
b
a
b
ilit
y
o
f
th
e
d
atap
o
in
t
b
elo
n
g
in
g
to
ea
ch
clas
s
b
ased
o
n
th
e
v
al
u
e
o
f
ca
teg
o
r
ical
d
ata.
Gen
e
a
n
d
v
ar
iatio
n
f
ea
t
u
r
es
ar
e
o
n
e
h
o
t
e
n
co
d
ed
an
d
cli
n
ical
e
v
id
en
ce
f
ea
t
u
r
e
i
s
en
c
o
d
ed
u
s
in
g
r
esp
o
n
s
e
co
d
in
g
.
Ge
n
e
an
d
v
a
r
iatio
n
f
ea
t
u
r
es
ar
e
en
co
d
ed
u
s
in
g
o
n
e
h
o
t
en
co
d
in
g
to
m
a
k
e
th
en
s
u
i
tab
le
f
o
r
m
ac
h
in
e
lear
n
in
g
tas
k
.
C
li
n
ic
al
ev
id
en
ce
f
ea
t
u
r
es,
w
h
ich
i
s
a
lo
n
g
tex
t
co
n
tai
n
s
s
e
v
er
al
s
to
p
w
o
r
d
s
,
s
p
ec
ial
ch
ar
ac
ter
s
an
d
s
p
ac
es.
I
n
th
e
f
ir
s
t
s
tep
,
all
th
ese
ar
e
r
em
o
v
e
d
.
L
ater
,
a
v
ec
to
r
o
f
d
is
tin
ct
w
o
r
d
s
is
b
u
ilt
alo
n
g
w
it
h
th
e
co
u
n
t
o
f
ea
ch
w
o
r
d
in
th
e
in
s
tan
ce
.
R
e
tain
ed
o
n
l
y
th
o
s
e
w
o
r
d
s
w
h
ich
o
cc
u
r
m
o
r
e
th
an
3
ti
m
es
an
d
f
ilter
ed
all
o
th
er
s
.
T
h
en
cr
ea
te
d
t
w
o
s
ep
ar
ate
en
co
d
ed
v
ec
to
r
s
,
o
n
e
u
s
in
g
o
n
e
h
o
t
en
co
d
in
g
an
d
th
e
o
th
er
w
i
t
h
r
esp
o
n
s
e
co
d
in
g
.
T
h
en
t
h
e
v
ec
to
r
s
ar
e
n
o
r
m
alize
d
.
Af
ter
t
h
e
t
w
o
t
y
p
es o
f
en
co
d
i
n
g
s
,
t
h
e
n
u
m
b
er
o
f
f
ea
t
u
r
es is
s
h
o
w
n
in
t
h
e
T
ab
l
e
2
.
Fig
u
r
e
2
.
P
r
o
p
o
s
ed
a
p
p
r
o
ac
h
T
ab
le
2
.
T
o
tal
f
ea
tu
r
es a
f
ter
e
n
co
d
in
g
En
c
o
d
i
n
g
G
e
n
e
V
a
r
i
a
t
i
o
n
C
l
i
n
i
c
a
l
Ev
i
d
e
n
c
e
T
o
t
a
l
n
o
.
o
f
f
e
a
t
u
r
e
s
O
n
e
H
o
t
e
n
c
o
d
i
n
g
2
2
9
1
,
9
6
0
5
4
,
8
5
0
5
7
,
0
2
9
R
e
sp
o
n
se
c
o
d
i
n
g
9
9
9
27
4
.
2
.
M
a
chine
lea
rning
a
lg
o
ri
t
h
m
s
−
R
an
d
o
m
m
o
d
el:
I
n
a
r
an
d
o
m
Mo
d
el,
w
e
g
en
er
ate
t
h
e
NI
N
E
class
p
r
o
b
ab
ilit
ies
r
an
d
o
m
l
y
s
u
c
h
t
h
at
th
e
y
s
u
m
to
1
f
o
r
ea
ch
test
d
ata
p
o
in
t.
−
K
-
n
ea
r
est
n
ei
g
h
b
o
r
s
[
2
7
]
:
B
as
ed
o
n
th
e
n
e
ig
h
b
o
r
s
o
f
th
e
test
d
ata
p
o
in
t,
b
ased
o
n
s
o
m
e
d
is
tan
ce
m
ea
s
u
r
e.
T
h
e
test
d
ata
p
o
in
t
is
as
s
ig
n
e
d
to
th
e
m
o
s
t
co
m
m
o
n
clas
s
a
m
o
n
g
th
e
K
-
n
ea
r
es
t
n
ei
g
h
b
o
r
s
.
P
ick
in
g
t
h
e
v
alu
e
o
f
k
is
c
h
alle
n
g
e
i
n
th
i
s
alg
o
r
ith
m
.
H
y
p
er
p
ar
am
e
ter
tu
n
i
n
g
w
ill
b
e
p
er
f
o
r
m
ed
b
y
m
an
y
w
h
ic
h
is
to
test
v
ar
io
u
s
v
al
u
es
f
o
r
k
a
n
d
f
i
x
t
h
e
b
est
o
n
e
t
h
at
g
i
v
es
b
etter
p
r
ed
ictio
n
ac
cu
r
ac
y
[
2
8
]
.
I
n
th
i
s
w
o
r
k
,
d
if
f
er
e
n
t
v
al
u
es
r
an
g
in
g
f
r
o
m
5
to
1
0
0
h
av
e
b
ee
n
ex
p
er
i
m
en
ted
,
th
e
b
etter
lo
g
l
o
s
s
v
alu
e
h
as
b
ee
n
o
b
tain
ed
f
o
r
k
=1
5
.
T
h
e
h
y
p
er
p
ar
am
eter
t
u
n
in
g
h
a
s
b
ee
n
s
h
o
w
n
n
Fig
u
r
e
3
.
K
-
n
ea
r
est
n
ei
g
h
b
o
r
s
(
KNN
)
is
lo
ca
l
m
eth
o
d
an
d
m
o
d
el
n
ee
d
n
o
t b
e
b
u
ilt in
ad
v
a
n
ce
.
B
u
t it
is
less
s
u
s
ce
p
tib
le
f
o
r
n
o
is
e.
−
L
i
n
ea
r
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
[
2
9
]
:
A
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
f
o
r
b
in
ar
y
clas
s
if
i
ca
tio
n
p
r
o
b
le
m
is
b
ased
o
n
th
e
id
ea
o
f
f
in
d
in
g
a
h
y
p
er
p
lan
e
th
at
n
est
s
ep
ar
ated
th
e
d
ata
p
o
in
ts
b
elo
n
g
in
g
to
t
w
o
class
es
.
I
n
a
m
u
lti
clas
s
clas
s
i
f
icatio
n
p
r
o
b
lem
w
it
h
n
cla
s
s
es,
a
o
n
e
v
s
o
n
e
ap
p
r
o
ac
h
is
u
s
ed
.
I
n
th
is
ap
p
r
o
ac
h
,
n
*
(
n
-
1
)
/2
n
u
m
b
er
o
f
b
in
ar
y
cl
ass
i
f
ier
s
ar
e
b
u
ilt
f
o
r
ea
ch
p
air
o
f
class
es.
T
h
e
tar
g
et
class
o
f
th
e
test
d
ata
p
o
in
t
is
ch
o
s
en
b
y
m
aj
o
r
it
y
v
o
tin
g
.
T
h
e
r
eg
u
lar
izatio
n
p
ar
am
eter
is
tu
n
ed
ex
p
er
i
m
en
ted
b
et
w
ee
n
0
.
0
0
0
0
1
an
d
1
0
0
an
d
o
b
tain
ed
a
lo
w
er
lo
g
lo
s
s
f
o
r
0
.
0
1
.
T
h
er
ef
o
r
e,
a
r
eg
u
lar
izatio
n
p
ar
a
m
eter
o
f
0
.
0
1
is
u
s
ed
in
f
i
n
al
ex
p
er
i
m
en
ta
tio
n
.
T
h
e
r
eg
u
lar
izatio
n
p
ar
a
m
e
ter
tu
n
in
g
[
3
0
]
is
s
h
o
w
n
i
n
Fi
g
u
r
e
4.
Af
ter
tr
ain
i
n
g
a
class
i
f
icat
io
n
m
o
d
el
o
n
tr
ai
n
i
n
g
d
ata,
th
e
p
e
r
f
o
r
m
an
ce
i
s
to
b
e
ev
alu
ated
o
n
a
test
s
et.
A
s
it
i
s
clea
r
l
y
s
ee
n
f
r
o
m
Fig
u
r
e
1
th
a
t
class
d
i
s
tr
ib
u
tio
n
is
n
o
t
b
ala
n
ce
d
.
T
h
er
ef
o
r
e,
s
tr
atif
ied
s
a
m
p
lin
g
i
s
p
er
f
o
r
m
e
d
o
n
tr
ain
i
n
g
s
et
to
f
o
r
m
te
s
t a
s
w
ell
a
s
cr
o
s
s
v
a
lid
atio
n
s
et
s
to
m
ain
tain
t
h
e
s
i
m
i
lar
d
is
tr
ib
u
ti
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
3
,
Dec
em
b
er
20
21
:
1
6
7
2
-
16
79
1676
Fig
u
r
e
3
.
Hy
p
er
p
a
r
am
eter
tu
n
i
n
g
f
o
r
KNN
Fig
u
r
e
4
.
Hy
p
er
p
a
r
am
eter
tu
n
i
n
g
f
o
r
SVM
5.
RE
SU
L
T
S
T
h
e
class
if
icatio
n
r
esu
lt
s
o
f
l
o
g
lo
s
s
ev
al
u
atio
n
m
etr
ic
f
o
r
g
en
e
m
u
tatio
n
d
ataset
ar
e
ta
b
u
lated
in
T
ab
le
3
.
I
t
ca
n
b
e
o
b
s
er
v
ed
th
at
KNN
h
as
s
h
o
w
n
m
o
r
e
p
r
ed
ictio
n
ac
cu
r
ac
y
co
m
p
ar
ed
to
lin
ea
r
SVM
in
ter
m
s
o
f
lo
g
lo
s
s
.
A
s
alr
ea
d
y
h
av
e
m
en
tio
n
ed
,
th
e
less
t
h
e
lo
g
lo
s
s
v
a
lu
e,
b
etter
t
h
e
p
r
ed
ictio
n
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
KNN
h
as b
ee
n
d
o
u
b
led
co
m
p
a
r
ed
to
r
an
d
o
m
p
r
ed
ictio
n
an
d
in
cr
ea
s
ed
s
li
g
h
tl
y
t
h
a
n
p
er
f
o
r
m
an
ce
o
f
SVM.
KNN
is
laz
y
clas
s
if
ier
,
an
d
n
o
m
o
d
el
n
ee
d
s
to
b
e
b
u
ilt
i
n
ad
v
an
ce
.
I
t
is
a
lo
ca
l
m
et
h
o
d
an
d
w
o
r
k
s
b
ased
o
n
n
ea
r
est
n
eig
h
b
o
r
s
.
T
h
e
tr
ain
in
g
ti
m
e
f
o
r
SVM
is
h
ig
h
.
T
h
e
co
n
f
u
s
io
n
m
atr
i
x
,
p
r
ec
is
io
n
an
d
r
ec
all
m
atr
ices
ar
e
g
iv
e
n
i
n
Fi
g
u
r
e
s
5
to
7
.
T
h
e
d
iag
o
n
al
v
al
u
e
co
r
r
esp
o
n
d
in
g
to
a
clas
s
in
co
n
f
u
s
io
n
m
atr
i
x
g
iv
e
s
th
e
id
ea
ab
o
u
t th
e
p
r
ed
ictio
n
.
T
h
e
d
iag
o
n
al
en
tr
y
,
p
r
ec
is
io
n
an
d
r
ec
all
f
o
r
class
7
,
9
,
3
an
d
8
o
f
KNN
class
i
f
ier
ar
e
g
iv
e
n
in
T
ab
le
4
.
T
ab
le
3
.
L
o
g
g
lo
s
s
r
es
u
lt
s
S
.
N
o
C
l
a
ssi
f
i
e
r
L
o
g
L
o
ss
N
u
mb
e
r
o
f
mi
scl
a
ss
i
f
i
e
d
p
o
i
n
t
s
1
R
a
n
d
o
m
2
.
5
3
2
.
5
0
2
K
N
N
1
.
1
0
0
.
3
9
3
S
V
M
1
.
2
4
0
.
3
9
T
ab
le
4
.
A
n
al
y
s
i
s
o
f
clas
s
7
,
9
,
3
an
d
8
o
b
tain
ed
u
s
i
n
g
KN
N
C
l
a
ss
%
o
f
T
e
st
d
a
t
a
p
o
i
n
t
s
D
i
a
g
o
n
a
l
v
a
l
u
e
i
n
C
o
n
f
u
s
i
o
n
ma
t
r
i
x
P
r
e
c
i
si
o
n
R
e
c
a
l
l
7
2
8
.
7
%
1
1
9
0
.
6
8
0
.
7
7
9
1%
3
1
0
.
5
3
2
.
7
%
1
0
0
8
0
.
6
%
0
0
0
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
KNN
class
if
ier
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
la
s
s
i
fyin
g
clin
ica
lly
a
ctio
n
a
b
le
g
en
etic
mu
ta
tio
n
s
u
s
in
g
K
N
N
a
n
d
S
V
M
(
R
o
h
it C
h
ivu
ku
la
)
1677
Fig
u
r
e
6
.
P
r
ec
is
io
n
m
atr
ix
o
f
KNN
Fig
u
r
e
7
.
R
ec
all
m
atr
i
x
o
f
KN
N
I
n
th
e
d
ataset,
class
7
is
m
a
j
o
r
class
w
it
h
2
8
%
o
f
d
ata
p
o
in
ts
.
KNN
class
i
f
ier
h
a
s
ac
q
u
ir
ed
a
p
r
ec
is
io
n
v
al
u
e
o
f
0
.
6
8
an
d
r
ec
all
o
f
0
.
7
7
f
o
r
class
7
in
d
icatin
g
th
a
t
6
8
%
o
f
th
e
d
ata
p
o
in
ts
i
n
t
h
e
p
r
ed
icted
an
d
7
7
%
in
ac
t
u
al
p
o
in
ts
co
r
r
ec
tly
.
T
h
e
t
w
o
clas
s
i
f
ier
s
KNN
as
w
ell
a
s
SVM
f
aile
d
in
p
r
ed
ictin
g
t
h
e
in
s
ta
n
ce
s
o
f
clas
s
3
an
d
8
w
it
h
ze
r
o
p
r
ec
is
io
n
an
d
r
ec
all.
C
lass
3
an
d
8
h
av
e
least
n
u
m
b
er
o
f
d
ata
p
o
in
ts
in
th
e
d
ataset.
I
g
u
es
s
t
h
i
s
is
b
ec
au
s
e
th
e
s
ta
n
d
ar
d
class
i
f
ier
s
ar
e
d
esig
n
ed
f
o
r
b
alan
ce
d
d
atasets
.
Fu
r
t
h
er
in
v
e
s
ti
g
atio
n
is
n
ee
d
ed
f
o
r
an
a
l
y
zi
n
g
t
h
e
p
r
ed
ictio
n
ac
cu
r
ac
y
f
o
r
class
3
an
d
8
.
C
o
m
p
in
g
to
class
9
co
n
tain
i
n
g
1
%
o
f
te
s
t
i
n
s
tan
ce
s
,
KNN
co
u
ld
o
b
tain
a
n
id
ea
l
p
r
ec
is
io
n
o
f
1
an
d
r
ec
all
o
f
0
.
5
.
T
h
is
m
ea
n
s
,
w
h
ate
v
er
t
h
e
in
s
ta
n
ce
s
th
a
t
KNN
cla
s
s
i
f
ied
in
to
clas
s
9
ar
e
ac
cu
r
ate,
b
u
t
i
t
co
u
ld
p
r
ed
ict
o
n
l
y
h
al
f
t
h
e
e
x
is
t
i
n
g
i
n
s
ta
n
ce
s
o
f
class
9
.
T
h
is
o
b
s
er
v
atio
n
i
n
d
i
ca
tes
th
at
p
r
ec
is
io
n
o
r
r
ec
all
alo
n
e
ca
n
n
o
t
b
e
tak
e
n
in
to
c
o
n
s
id
er
atio
n
w
h
ile
an
al
y
z
in
g
.
6.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
A
p
er
s
o
n
alize
d
tr
ea
t
m
e
n
t
f
o
r
c
an
ce
r
ca
n
b
e
ef
f
icien
t
l
y
d
esi
g
n
ed
if
th
e
m
ed
ical
ex
p
er
ts
h
av
e
th
e
p
r
e
in
f
o
r
m
atio
n
o
f
g
e
n
etic
m
u
tati
o
n
s
.
Ma
c
h
i
n
e
lear
n
in
g
m
et
h
o
d
s
ca
n
b
e
e
f
f
ec
ti
v
el
y
u
s
ed
to
class
i
f
y
t
h
e
g
en
e
tic
m
u
tatio
n
s
b
ased
o
n
clin
ical
l
y
ac
tio
n
ab
le
d
ata.
I
n
th
is
w
o
r
k
,
K
-
n
ea
r
es
t
n
ei
g
h
b
o
r
s
an
d
li
n
ea
r
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
ar
e
ap
p
lied
o
n
t
h
e
p
u
b
lic
d
ataset
av
ailab
le
at
Ka
g
g
le
co
m
p
et
itio
n
.
K
NN
i
s
f
o
u
n
d
to
ac
h
iev
e
a
b
etter
class
i
f
icatio
n
ac
cu
r
ac
y
o
v
er
L
in
ea
r
SVM
in
ter
m
s
o
f
lo
g
lo
s
s
.
I
n
f
u
t
u
r
e,
it
is
in
ten
d
ed
to
u
s
e
th
e
ef
f
icie
n
t
tex
t
ex
tr
ac
tio
n
f
ea
t
u
r
es
li
k
e
TF
-
I
DF
an
d
d
o
c2
v
ec
an
d
tr
ain
t
h
e
m
o
d
els
u
s
i
n
g
en
s
e
m
b
le
f
r
a
m
e
w
o
r
k
.
A
s
t
h
i
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
3
,
Dec
em
b
er
20
21
:
1
6
7
2
-
16
79
1678
p
r
o
b
lem
is
i
m
b
ala
n
ce
d
,
clas
s
b
alan
cin
g
m
ec
h
an
i
s
m
s
s
u
c
h
a
s
u
n
d
er
s
a
m
p
lin
g
,
o
v
er
s
a
m
p
l
in
g
ca
n
b
e
u
s
ed
to
o
b
tain
m
o
r
e
ac
cu
r
ate
r
esu
lt
s
.
Dee
p
lear
n
in
g
m
et
h
o
d
s
s
ee
m
t
o
w
o
r
k
ef
f
icie
n
t
o
n
tex
t
p
r
o
ce
s
s
i
n
g
.
I
n
f
u
t
u
r
e,
w
e
w
o
u
ld
w
o
r
k
o
n
d
ee
p
lear
n
in
g
t
ec
h
n
iq
u
es o
n
t
h
e
d
ataset.
RE
F
E
R
E
NC
E
S
[1
]
L
.
Ch
in
,
J.
N.
A
n
d
e
rse
n
,
a
n
d
P
.
A
.
F
u
trea
l
,
“
Ca
n
c
e
r
g
e
n
o
m
ics
:
f
r
o
m
d
isc
o
v
e
r
y
sc
ien
c
e
to
p
e
rso
n
a
l
ize
d
m
e
d
icin
e
,
”
Na
tu
re
me
d
icin
e
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
2
9
7
-
3
0
3
,
2
0
1
1
,
d
o
i:
1
0
.
1
0
3
8
/n
m
.
2
3
2
3
.
[2
]
T
.
Ch
e
n
g
a
n
d
X
.
Z
h
a
n
,
“
P
a
tt
e
r
n
re
c
o
g
n
it
i
o
n
f
o
r
p
re
d
ictiv
e
,
p
re
v
e
n
ti
v
e
,
a
n
d
p
e
rso
n
a
li
z
e
d
m
e
d
ic
in
e
in
c
a
n
c
e
r
,”
EP
M
A
J
o
u
rn
a
l,
vol
.
8
,
n
o
.
1
,
p
p
.
5
1
-
6
0
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
0
7
/s1
3
1
6
7
-
0
1
7
-
0
0
8
3
-
9
.
[3
]
Ka
g
g
l
e
,
P
e
rso
n
a
li
z
e
d
M
e
d
i
c
in
e
:
Re
d
e
f
in
in
g
Ca
n
c
e
r
T
re
a
t
m
e
n
t,
2
0
1
8
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/www
.
k
a
g
g
l
e
.
c
o
m
/
c
/
m
sk
-
r
e
d
e
f
in
in
g
-
c
a
n
c
e
r
-
trea
t
m
e
n
t/
o
v
e
rv
i
e
ws
d
[4
]
NIP
S
2
0
1
7
Co
m
p
e
ti
ti
o
n
T
ra
c
k
,
2
0
1
7
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
n
ip
s.c
c
/Co
n
f
e
re
n
c
e
s/2
0
1
7
/Co
m
p
e
ti
ti
o
n
T
ra
c
k
[5
]
C
.
F
e
rri
,
J
.
He
rn
á
n
d
e
z
-
Ora
ll
o
,
a
n
d
R
.
M
o
d
ro
i
u
,
“
A
n
e
x
p
e
rim
e
n
tal
c
o
m
p
a
riso
n
o
f
p
e
rf
o
rm
a
n
c
e
m
e
a
su
re
s
f
o
r
c
las
si
f
ica
ti
o
n
,”
Pa
tt
e
r
n
Rec
o
g
n
it
i
o
n
L
e
tt
e
rs
,
v
o
l.
3
0
,
n
o
.
1
,
p
p
.
2
7
-
3
8
,
2
0
0
9
,
d
o
i:
1
0
.
1
0
1
6
/
j.
p
a
trec
.
2
0
0
8
.
0
8
.
0
1
0
.
[6
]
J.
Re
a
d
,
B.
P
f
a
h
rin
g
e
r,
G
.
Ho
l
m
e
s,
a
n
d
E.
F
ra
n
k
,
“
Clas
sif
ier
c
h
a
in
s
f
o
r
m
u
lt
i
-
lab
e
l
c
las
sif
ic
a
ti
o
n
,
”
M
a
c
h
in
e
lea
rn
in
g
,
v
o
l
.
8
5
n
o
.
3
,
p
p
.
3
3
3
-
3
5
9
,
2
0
1
1
,
d
o
i:
1
0
.
1
0
0
7
/s1
0
9
9
4
-
0
1
1
-
5
2
5
6
-
5
.
[7
]
J.
T
.
T
o
w
n
se
n
d
,
“
T
h
e
o
re
ti
c
a
l
a
n
a
ly
sis
o
f
a
n
a
lp
h
a
b
e
ti
c
c
o
n
f
u
sio
n
m
a
tri
x
,”
Per
c
e
p
ti
o
n
&
Ps
y
c
h
o
p
h
y
sic
s,
v
o
l.
9
,
n
o
.
1
,
p
p
.
4
0
-
5
0
,
1
9
7
1
,
d
o
i:
1
0
.
3
7
5
8
/
BF
0
3
2
1
3
0
2
6
.
[8
]
D.
M
.
W
.
P
o
w
e
rs,
“
Ev
a
lu
a
ti
o
n
:
F
ro
m
P
re
c
isio
n
,
Re
c
a
ll
a
n
d
F
-
M
e
a
su
re
T
o
Ro
c
,
In
f
o
rm
e
d
n
e
ss
,
M
a
rk
e
d
n
e
ss
&
Co
rre
latio
n
,”
J
o
u
r
n
a
l
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
o
lo
g
ies
,
v
o
l.
2
,
n
o
.
1
,
p
p
.
3
7
–
6
3
,
2
0
1
1
.
[9
]
K.
M
.
T
in
g
,
“
Co
n
f
u
sio
n
M
a
tri
x
,
”
En
c
y
c
lo
p
a
e
d
i
a
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
a
n
d
Da
ta
M
in
in
g
,
p
p
.
2
6
0
,
Bo
sto
n
,
USA
:
S
p
r
i
n
g
e
r
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
0
7
/9
7
8
-
1
-
4
8
9
9
-
7
6
8
7
-
1
_
5
0
.
[1
0
]
J.
G
o
e
c
k
s,
V
.
Ja
li
l
i,
L
.
M
.
He
ise
r,
a
n
d
J.
W
.
G
ra
y
,
“
Ho
w
m
a
c
h
in
e
lea
rn
in
g
w
il
l
tran
sf
o
rm
b
io
m
e
d
i
c
in
e
,
”
Ce
ll
,
v
o
l.
1
8
1
,
n
o
.
1
,
p
p
.
9
2
-
1
0
1
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/
j.
c
e
ll
.
2
0
2
0
.
0
3
.
0
2
2
.
[1
1
]
T
.
C.
Ca
rter
a
n
d
M
.
M
.
He
,
“
Ch
a
ll
e
n
g
e
s
o
f
id
e
n
ti
fy
in
g
c
li
n
ica
ll
y
a
c
ti
o
n
a
b
le
g
e
n
e
ti
c
v
a
rian
ts
f
o
r
p
re
c
isio
n
m
e
d
icin
e
,”
J
o
u
rn
a
l
o
f
h
e
a
lt
h
c
a
re
e
n
g
in
e
e
rin
g
,
v
o
l
.
2
0
1
6
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
5
5
/2
0
1
6
/3
6
1
7
5
7
2
.
[1
2
]
G
.
C.
Ca
w
le
y
a
n
d
N.
L
.
C.
T
a
lb
o
t,
“
G
e
n
e
se
lec
ti
o
n
i
n
c
a
n
c
e
r
c
la
ss
if
ic
a
ti
o
n
u
sin
g
sp
a
rse
lo
g
isti
c
r
e
g
re
ss
io
n
w
it
h
Ba
y
e
sia
n
re
g
u
lariz
a
ti
o
n
,”
Bi
o
i
n
fo
rm
a
ti
c
s
,
v
o
l.
2
2
,
n
o
.
1
9
,
p
p
.
2
3
4
8
-
2
3
5
5
,
2
0
0
6
,
d
o
i:
1
0
.
1
0
9
3
/b
io
i
n
f
o
rm
a
ti
c
s/b
tl
3
8
6
.
[1
3
]
N.
P
e
n
g
,
H.
P
o
o
n
,
C.
Qu
irk
,
K.
T
o
u
tan
o
v
a
,
a
n
d
W
.
Yih
,
“
Cro
s
s
-
se
n
ten
c
e
n
-
a
r
y
re
latio
n
e
x
trac
ti
o
n
w
it
h
g
ra
p
h
lstm
s
,”
T
ra
n
sa
c
ti
o
n
s
o
f
t
h
e
Asso
c
ia
ti
o
n
fo
r
Co
m
p
u
t
a
ti
o
n
a
l
L
in
g
u
isti
c
s,
v
o
l.
5
,
p
p
.
1
0
1
-
1
1
5
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
6
2
/
tac
l_
a
_
0
0
0
4
9
.
[1
4
]
X
.
Z
h
a
n
g
,
e
t
a
l
.
,
“
M
u
lt
i
-
v
iew
e
n
se
m
b
le
c
las
sif
i
c
a
ti
o
n
f
o
r
c
li
n
ic
a
ll
y
a
c
ti
o
n
a
b
le
g
e
n
e
ti
c
m
u
tatio
n
s
,”
T
h
e
NIPS
'1
7
Co
mp
e
ti
ti
o
n
:
Bu
il
d
i
n
g
I
n
telli
g
e
n
t
S
y
ste
ms
,
p
p
.
7
9
-
9
9
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
9
4
0
4
2
-
7
_
5
.
[1
5
]
R.
N.
W
a
y
k
o
le
a
n
d
A
.
D.
T
h
a
k
a
re
,
“
In
telli
g
e
n
t
Clas
sif
ic
a
ti
o
n
o
f
Cli
n
ica
ll
y
A
c
ti
o
n
a
b
le
G
e
n
e
ti
c
M
u
tatio
n
s
Ba
se
d
o
n
Cli
n
ica
l
Ev
i
d
e
n
c
e
s,”
2
0
1
8
F
o
u
rth
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ti
n
g
Co
mm
u
n
ica
ti
o
n
C
o
n
tr
o
l
a
n
d
Au
to
m
a
ti
o
n
(
ICCUBEA
)
,
2
0
1
8
,
p
p
.
1
-
4
,
d
o
i:
1
0
.
1
1
0
9
/ICCUBEA
.
2
0
1
8
.
8
6
9
7
3
9
5
.
[1
6
]
G
.
L
i
a
n
d
B.
Ya
o
,
“
Clas
sif
ica
ti
o
n
o
f
G
e
n
e
ti
c
M
u
tatio
n
s
f
o
r
Ca
n
c
e
r
T
re
a
t
m
e
n
t
w
it
h
M
a
c
h
in
e
L
e
a
rn
in
g
A
p
p
ro
a
c
h
e
s
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
De
sig
n
,
An
a
lys
is
a
n
d
T
o
o
ls
fo
r
In
te
g
ra
te
d
Circ
u
i
ts
a
n
d
S
y
ste
ms
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
63
-
6
7
,
2
0
1
8
.
[1
7
]
N.
A
li
,
A
.
H.
A
b
u
El
-
A
tt
a
,
a
n
d
H.
H
.
Zay
e
d
,
“
En
h
a
n
c
i
n
g
th
e
p
e
rf
o
rm
a
n
c
e
o
f
c
a
n
c
e
r
tex
t
c
la
ss
i
f
ica
ti
o
n
m
o
d
e
l
b
a
se
d
o
n
c
a
n
c
e
r
h
a
ll
m
a
rk
s
,
”
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
,
vol
.
1
0
,
n
o
.
2
,
p
p
.
3
1
6
-
323
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jai.
v
1
0
.
i
2
.
p
p
3
1
6
-
3
2
3
.
[1
8
]
C.
M
is
h
ra
a
n
d
D
.
L
.
G
u
p
ta,
“
D
e
e
p
m
a
c
h
in
e
lea
rn
in
g
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
s:
A
n
o
v
e
rv
iew
,
”
IAE
S
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
,
v
o
l.
6
,
n
o
.
2
,
p
p
.
66
-
73
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jai.
v
6
.
i
2
.
p
p
6
6
-
73
.
[1
9
]
M
.
A
.
F
e
b
rian
t
o
n
o
,
S
.
H.
P
ra
m
o
n
o
,
Ra
h
m
a
d
w
a
ti
,
a
n
d
G
.
Na
g
h
d
y
,
“
Cl
a
ss
i
f
ica
ti
o
n
o
f
m
u
lt
icla
ss
i
m
b
a
lan
c
e
d
d
a
ta
u
sin
g
c
o
st
-
se
n
siti
v
e
d
e
c
isio
n
tree
C5
.
0
,
”
IAE
S
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Arti
fi
c
ia
l
In
tell
ig
e
n
c
e
,
v
o
l.
9
,
n
o
.
1
,
p
p
.
6
5
-
72
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
a
i.
v
9
.
i
1
.
p
p
6
5
-
72
.
[2
0
]
M
.
S
.
N
o
rd
i
n
e
t
a
l
.
,
“
A
c
o
m
p
a
r
a
ti
v
e
a
n
a
ly
sis
o
f
m
e
tah
e
u
risti
c
a
lg
o
rit
h
m
s
in
f
u
z
z
y
m
o
d
e
ll
in
g
f
o
r
p
h
ish
i
n
g
a
tt
a
c
k
d
e
tec
ti
o
n
,
”
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
2
3
,
n
o
.
2
,
p
p
.
1
1
4
6
-
1
1
5
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
2
3
.
i
2
.
p
p
1
1
4
6
-
1
1
5
8
.
[2
1
]
S
.
S
.
M
.
A
li
,
A
.
H.
A
lsa
e
e
d
i,
D.
A
l
-
S
h
a
m
m
a
r
y
,
H.
H.
A
lsa
e
e
d
i,
a
n
d
H.
W
.
A
b
id
,
“
Eff
icie
n
t
in
telli
g
e
n
t
s
y
ste
m
f
o
r
d
iag
n
o
sis
p
n
e
u
m
o
n
ia
(S
A
RS
-
COV
ID1
9
)
in
X
-
ra
y
i
m
a
g
e
s
e
m
p
o
we
re
d
w
it
h
in
it
ial
c
lu
ste
ri
n
g
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
2
2
,
n
o
.
1
,
p
p
.
2
4
1
-
2
5
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
2
2
.
i
1
.
p
p
2
4
1
-
251
.
[2
2
]
A
.
K.
A
b
a
si,
A
.
T
.
Kh
a
d
e
r,
M
.
A
.
A
l
-
Be
tar,
S
.
Na
im
,
M
.
A
.
Aw
a
d
a
ll
a
h
,
a
n
d
O.
A
.
A
lo
m
a
ri
,
“
T
e
x
t
d
o
c
u
m
e
n
ts
c
lu
ste
rin
g
u
si
n
g
m
o
d
if
ied
m
u
lt
i
-
v
e
rse
o
p
ti
m
ize
r”
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
t
e
r
En
g
in
e
e
rin
g
,
v
o
l.
1
0
,
n
o
.
6
,
p
p
.
6
3
6
1
-
6
3
6
9
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
e
c
e
.
v
1
0
i6
.
p
p
6
3
6
1
-
6
3
6
9
.
[2
3
]
Z.
Ru
sta
m
a
n
d
S
.
Ha
rti
n
i,
“
Ne
w
f
e
a
tu
re
se
le
c
ti
o
n
b
a
se
d
o
n
k
e
rn
e
l
,
”
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
In
fo
rm
a
t
ics
,
v
o
l.
9
,
n
o
.
4
,
p
p
.
1
5
6
9
-
1
5
7
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/ee
i.
v
9
i4
.
1
9
5
9
.
[2
4
]
V
.
S
u
d
h
a
a
n
d
H.
A
.
G
iri
ja
m
m
a
,
“
No
v
e
l
m
o
d
e
ll
in
g
o
f
c
lu
ste
rin
g
f
o
r
e
n
h
a
n
c
e
d
c
las
sif
ica
ti
o
n
p
e
rf
o
rm
a
n
c
e
o
n
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
t
e
r
En
g
in
e
e
rin
g
,
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
2
0
8
8
-
8
7
0
8
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
0
i
2
.
p
p
2
0
6
0
-
2
0
6
8
.
[2
5
]
J.
Co
h
e
n
,
P
.
Co
h
e
n
,
S
.
G
.
W
e
st,
a
n
d
L
.
S
.
A
ik
e
n
,
Ap
p
li
e
d
M
u
lt
i
p
l
e
Reg
re
ss
io
n
.
Ne
w
Yo
rk
,
USA
:
Ro
u
tl
e
d
g
e
,
2
0
1
3
,
d
o
i:
1
0
.
4
3
2
4
/9
7
8
0
2
0
3
7
7
4
4
4
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
la
s
s
i
fyin
g
clin
ica
lly
a
ctio
n
a
b
le
g
en
etic
mu
ta
tio
n
s
u
s
in
g
K
N
N
a
n
d
S
V
M
(
R
o
h
it C
h
ivu
ku
la
)
1679
[2
6
]
K.
W
ieg
a
n
d
a
n
d
E.
W
a
sc
h
e
r,
“
Re
sp
o
n
se
c
o
d
in
g
i
n
th
e
S
im
o
n
tas
k
,”
Psy
c
h
o
lo
g
ica
l
Res
e
a
rc
h
,
v
o
l.
7
1
,
n
o
.
4
,
p
p
.
401
-
4
1
0
,
2
0
0
7
,
d
o
i:
1
0
.
1
0
0
7
/s0
0
4
2
6
-
0
0
5
-
0
0
2
7
-
1
.
[2
7
]
T
.
Ha
stie,
R
.
T
ib
sh
ira
n
i,
a
n
d
J
.
F
ried
m
a
n
,
T
h
e
e
lem
e
n
ts
o
f
st
a
ti
stica
l
lea
rn
i
n
g
:
d
a
ta
mi
n
in
g
,
i
n
fer
e
n
c
e
,
a
n
d
p
re
d
ict
io
n
.
USA
:
S
p
r
in
g
e
r,
2
0
0
9
.
[2
8
]
S
.
Z
h
a
n
g
,
X
.
L
i,
M
.
Z
o
n
g
,
X
.
Zh
u
,
a
n
d
D.
C
h
e
n
g
,
“
L
e
a
rn
in
g
k
f
o
r
k
n
n
c
las
sif
ic
a
ti
o
n
,”
ACM
T
ra
n
sa
c
ti
o
n
s
o
n
In
telli
g
e
n
t
S
y
ste
ms
a
n
d
T
e
c
h
n
o
lo
g
y
(
T
IS
T
),
v
o
l
.
8
,
n
o
.
3
,
p
p
.
1
-
1
9
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
4
5
/
2
9
9
0
5
0
8
.
[2
9
]
D.
A
.
P
is
n
e
r
a
n
d
D
.
M
.
S
c
h
n
y
e
r
,
“
S
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
,”
M
a
c
h
in
e
L
e
a
rn
i
n
g
,
p
p
1
0
1
-
1
2
1
,
C
a
m
b
rid
g
e
,
UK
:
A
c
a
d
e
m
ic P
re
ss
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/B
9
7
8
-
0
-
12
-
8
1
5
7
3
9
-
8
.
0
0
0
0
6
-
7
.
[3
0
]
L
.
W
a
n
g
,
S
u
p
p
o
rt ve
c
to
r ma
c
h
i
n
e
s: t
h
e
o
ry
a
n
d
a
p
p
li
c
a
ti
o
n
s
,
USA
:
S
p
rin
g
e
r
,
2
0
0
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ro
h
it
Ch
i
v
u
k
u
la
is
M
a
ste
rs
stu
d
e
n
t
i
n
Co
m
p
u
ti
n
g
w
it
h
Un
iv
e
rsity
o
f
Hu
d
d
e
rsf
ield
,
Hu
d
d
e
rsf
ield
,
U
n
it
e
d
Kin
g
d
o
m
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
M
a
c
h
in
e
L
e
a
rn
in
g
,
Da
ta
A
n
a
l
y
ti
c
s
a
n
d
Na
tu
ra
l
L
a
n
g
u
a
g
e
Co
m
p
u
ti
n
g
He
h
a
s
a
c
q
u
ired
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
C
o
m
p
u
t
e
r
S
c
ie
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
f
r
o
m
Ja
w
a
h
a
r
l
a
l
Ne
h
r
u
T
e
c
h
n
o
l
o
g
i
c
a
l
U
n
iv
e
rs
i
ty
,
Ka
k
i
n
a
d
a
,
A
n
d
h
r
a
P
r
a
d
e
s
h
,
I
n
d
i
a
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
r
o
h
i
t
.
c
h
i
v
u
k
u
l
a
.
k
i
n
g
d
o
m
@g
m
a
i
l
.
c
o
m
.
T.
J
a
y
a
La
k
s
h
m
i
is
w
o
rk
in
g
a
s
a
n
A
ss
i
sta
n
t
P
r
o
f
e
ss
o
r
in
th
e
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
S
RM
Un
iv
e
rsit
y
,
Am
a
ra
v
a
th
i,
A
P
,
In
d
ia.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
.
D.
De
g
re
e
f
o
r
h
e
r
w
o
rk
o
n
"
L
in
k
P
r
e
d
ictio
n
i
n
He
tero
g
e
n
e
o
u
s
S
o
c
ial
Ne
tw
o
rk
s"
f
ro
m
th
e
S
c
h
o
o
l
o
f
Co
m
p
u
ter
a
n
d
I
n
f
o
rm
a
ti
o
n
S
c
ien
c
e
s,
Un
iv
e
rsity
o
f
H
y
d
e
ra
b
a
d
,
In
d
ia
i
n
2
0
1
9
.
S
h
e
is
re
v
ie
w
e
r
o
f
re
p
u
ted
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls.
S
h
e
h
a
s
a
o
v
e
ra
ll
tea
c
h
in
g
e
x
p
e
rien
c
e
o
f
2
2
y
e
a
r
s.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
g
ra
p
h
m
in
in
g
,
re
c
o
m
m
e
n
d
e
r
sy
ste
m
s,
Na
tu
ra
l
L
a
n
g
u
a
g
e
P
r
o
c
e
ss
in
g
a
n
d
se
c
u
rit
y
a
n
a
ly
ti
c
s
.
Sh
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ja
y
a
.
p
h
d
.
h
c
u
@g
m
a
il
.
c
o
m
)
S
a
n
k
u
S
a
ty
a
U
d
a
y
is
Ba
c
h
e
lo
r
s
stu
d
e
n
t
i
n
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
w
it
h
S
RM
Un
iv
e
rsit
y
.
,
A
n
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
M
a
c
h
in
e
L
e
a
rn
in
g
,
Da
ta
A
n
a
l
y
ti
c
s
a
n
d
Na
tu
ra
l
L
a
n
g
u
a
g
e
Co
m
p
u
ti
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
n
k
u
_
sa
ty
a
@s
r
m
a
p
.
e
d
u
.
in
.
S
a
tti
Th
a
n
u
j
a
Pa
v
a
n
i
is
Ba
c
h
e
lo
rs
stu
d
e
n
t
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
w
it
h
S
RM
Un
iv
e
rsit
y
,
A
n
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
M
a
c
h
in
e
L
e
a
rn
in
g
,
Da
ta
A
n
a
l
y
ti
c
s
a
n
d
Na
tu
ra
l
L
a
n
g
u
a
g
e
Co
m
p
u
ti
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
tt
i_
th
a
n
u
ja@
srm
a
p
.
e
d
u
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.