I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
39
,
No
.
3
,
Sep
tem
b
er
2
0
2
5
,
p
p
.
1
7
3
6
~
1
744
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
39
.i
3
.
p
p
1
7
3
6
-
1
7
4
4
1736
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Predic
tion o
f
Par
kinso
n's dis
ea
se u
sing
f
ea
ture
selec
t
io
n and
ensem
ble learn
in
g
t
echniqu
es
Sh
a
ra
n T
.
D
.,
Su
j
a
t
a
J
o
s
hi
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
N
i
t
t
e
M
e
e
n
a
k
sh
i
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
13
,
2
0
2
4
R
ev
is
ed
Ap
r
3
,
2
0
2
5
Acc
ep
ted
J
u
l
2
,
2
0
2
5
P
a
rk
in
so
n
'
s
d
ise
a
se
(P
D)
is
a
p
r
o
g
re
ss
iv
e
n
e
u
ro
d
e
g
e
n
e
ra
ti
v
e
d
is
o
rd
e
r
t
h
a
t
sig
n
ifi
c
a
n
t
ly
imp
a
c
ts
q
u
a
li
t
y
o
f
li
fe
a
n
d
h
e
a
lt
h
c
a
re
sy
ste
m
s.
Early
d
e
tec
ti
o
n
is
c
ru
c
ial
fo
r
ti
m
e
ly
i
n
terv
e
n
ti
o
n
s
th
a
t
c
a
n
m
it
ig
a
te
d
ise
a
se
p
ro
g
r
e
ss
io
n
a
n
d
imp
ro
v
e
p
a
ti
e
n
t
o
u
tc
o
m
e
s.
Th
is
s
tu
d
y
le
v
e
ra
g
e
s
a
d
v
a
n
c
e
d
m
a
c
h
i
n
e
lea
rn
in
g
(M
L)
tec
h
n
iq
u
e
s
to
d
e
tec
t
P
D
u
sin
g
s
p
e
e
c
h
fe
a
tu
re
s
a
s
n
o
n
-
in
v
a
siv
e
b
io
m
a
rk
e
rs.
A
d
a
tas
e
t
c
o
n
tain
in
g
7
5
4
fe
a
t
u
re
s
d
e
riv
e
d
fr
o
m
su
sta
in
e
d
v
o
we
l
p
h
o
n
a
ti
o
n
s
o
f
2
5
2
in
d
iv
i
d
u
a
ls
(
1
8
8
P
D
p
a
ti
e
n
ts,
6
4
h
e
a
lt
h
y
c
o
n
tro
ls)
wa
s
a
n
a
ly
z
e
d
.
Th
e
d
a
tas
e
t,
o
rig
i
n
a
l
ly
c
o
ll
e
c
ted
b
y
Ista
n
b
u
l
U
n
iv
e
rsity
a
n
d
p
u
b
li
c
ly
h
o
ste
d
v
ia t
h
e
UCI
ML
re
p
o
sito
r
y
,
wa
s a
c
c
e
ss
e
d
th
ro
u
g
h
Ka
g
g
le fo
r
p
re
p
ro
c
e
ss
in
g
a
n
d
a
n
a
ly
sis
.
To
id
e
n
ti
f
y
th
e
m
o
st
p
re
d
ictiv
e
fe
a
tu
re
s,
we
e
m
p
lo
y
e
d
re
c
u
rsiv
e
fe
a
t
u
re
e
li
m
in
a
ti
o
n
(R
F
E),
ra
n
d
o
m
fo
re
st
i
m
p
o
rtan
c
e
,
las
so
re
g
r
e
ss
io
n
,
a
n
d
th
e
Bo
ru
ta
a
lg
o
rit
h
m
—
e
n
su
ri
n
g
ro
b
u
st
fe
a
tu
re
se
lec
ti
o
n
wh
il
e
re
d
u
c
in
g
d
ime
n
s
io
n
a
li
t
y
.
Th
e
XG
Bo
o
st
m
o
d
e
l,
o
p
ti
m
ise
d
u
sin
g
th
e
sy
n
th
e
ti
c
m
in
o
rit
y
o
v
e
rsa
m
p
li
n
g
tec
h
n
i
q
u
e
(S
M
OTE)
fo
r
c
las
s
b
a
lan
c
in
g
,
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
9
6
.
6
9
%
,
a
re
c
a
ll
o
f
9
6
%
,
a
n
d
a
n
F
1
-
sc
o
re
o
f
9
8
%
.
M
o
d
e
l
ro
b
u
st
n
e
ss
wa
s
v
a
li
d
a
ted
t
h
ro
u
g
h
5
-
f
o
l
d
c
ro
ss
-
v
a
li
d
a
ti
o
n
,
y
ield
i
n
g
a
n
a
v
e
ra
g
e
a
c
c
u
ra
c
y
o
f
8
9
.
5
4
%
.
Th
e
se
fi
n
d
i
n
g
s
e
sta
b
l
ish
a
sc
a
lab
le,
c
o
st
-
e
ffe
c
ti
v
e
,
a
n
d
n
o
n
-
i
n
v
a
siv
e
fra
m
e
wo
rk
fo
r
e
a
rly
P
D
d
e
tec
ti
o
n
,
d
e
m
o
n
stra
ti
n
g
th
e
p
o
ten
ti
a
l
o
f
sp
e
e
c
h
a
n
a
ly
sis
a
n
d
ML
in
n
e
u
ro
d
e
g
e
n
e
ra
ti
v
e
d
ise
a
se
m
a
n
a
g
e
m
e
n
t.
K
ey
w
o
r
d
s
:
Featu
r
e
s
elec
tio
n
Par
k
in
s
o
n
’
s
d
is
ea
s
e
SMOT
E
Sp
ee
ch
b
io
m
ar
k
er
s
XGBo
o
s
t
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
:
Sh
ar
an
T
.
D.
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Nitte
M
ee
n
ak
s
h
i
I
n
s
titu
te
o
f
T
ec
h
n
o
l
o
g
y
Yela
h
an
k
a,
B
en
g
alu
r
u
,
I
n
d
ia
E
m
ail:
s
h
r
n
2
8
2
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Par
k
in
s
o
n
'
s
d
is
ea
s
e
(
PD)
is
a
p
r
o
g
r
ess
iv
e
n
eu
r
o
d
eg
e
n
er
ati
v
e
d
is
o
r
d
e
r
af
f
ec
tin
g
ap
p
r
o
x
im
ately
1
0
m
illi
o
n
in
d
iv
id
u
als
wo
r
ld
wi
d
e
[
1
]
.
I
t
p
r
im
ar
ily
im
p
air
s
th
e
ce
n
tr
al
n
er
v
o
u
s
s
y
s
tem
,
lead
in
g
to
m
o
t
o
r
d
y
s
f
u
n
ctio
n
s
s
u
ch
as tr
em
o
r
s
,
s
tiff
n
ess
,
b
r
ad
y
k
in
esia,
an
d
p
o
s
tu
r
al
in
s
tab
ilit
y
[
2
]
-
[
4
]
.
A
d
d
it
io
n
ally
,
n
o
n
-
m
o
to
r
s
y
m
p
to
m
s
,
in
clu
d
in
g
co
g
n
itiv
e
d
ec
lin
e,
s
p
ee
ch
im
p
air
m
en
ts
,
s
le
ep
d
is
tu
r
b
a
n
ce
s
,
an
d
d
ep
r
ess
io
n
,
s
ig
n
if
ican
tly
im
p
ac
t p
atien
ts
'
q
u
ality
o
f
life
an
d
p
o
s
e
c
h
allen
g
es f
o
r
ca
r
eg
i
v
er
s
an
d
h
e
alth
ca
r
e
s
y
s
tem
s
[
5
]
-
[
7
]
.
E
ar
ly
d
iag
n
o
s
is
o
f
PD
i
s
cr
u
cial
to
in
itiate
tim
ely
th
er
ap
eu
tic
in
ter
v
en
tio
n
s
,
m
itig
ate
s
y
m
p
to
m
p
r
o
g
r
ess
io
n
,
a
n
d
p
r
o
lo
n
g
f
u
n
ctio
n
al
in
d
ep
e
n
d
en
ce
[
8
]
-
[9
]
.
Ho
wev
er
,
tr
ad
itio
n
al
d
iag
n
o
s
tic
m
eth
o
d
s
r
ely
h
ea
v
ily
o
n
s
u
b
jectiv
e
clin
ica
l
ass
es
s
m
en
ts
,
lead
in
g
to
in
ter
-
o
b
s
er
v
e
r
v
ar
iab
ilit
y
an
d
l
ate
-
s
tag
e
d
etec
tio
n
[
1
0
]
-
[
1
2
]
.
T
h
is
u
n
d
er
s
co
r
es
th
e
n
ee
d
f
o
r
o
b
jectiv
e
,
s
ca
lab
le,
an
d
ea
r
ly
d
ia
g
n
o
s
tic
m
et
h
o
d
o
lo
g
ies.
Sp
ee
ch
an
aly
s
is
h
as
em
er
g
e
d
as
a
p
r
o
m
is
in
g
n
on
-
in
v
asiv
e
b
io
m
ar
k
e
r
f
o
r
PD
d
iag
n
o
s
is
[
1
3
]
-
[
1
6
]
.
T
h
e
d
is
ea
s
e
af
f
ec
ts
p
h
o
n
at
o
r
y
an
d
m
o
to
r
co
n
tr
o
l
s
y
s
tem
s
,
lead
in
g
to
s
u
b
tle
alter
atio
n
s
in
j
itter
,
s
h
im
m
er
,
an
d
h
ar
m
o
n
icity
,
wh
ic
h
o
f
ten
p
r
ec
ed
e
o
v
er
t
m
o
t
o
r
s
y
m
p
to
m
s
[
1
7
]
,
[
1
8
]
.
R
ec
en
t
ad
v
an
ce
m
en
ts
in
m
ac
h
in
e
lear
n
i
n
g
(
ML
)
an
d
d
ee
p
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
r
ed
ictio
n
o
f
P
a
r
kin
s
o
n
's
d
is
ea
s
e
u
s
in
g
fea
tu
r
e
s
elec
tio
n
a
n
d
en
s
emb
le
lea
r
n
in
g
tech
n
iq
u
es
(
S
h
a
r
a
n
T.
D.
)
1737
lear
n
in
g
(
DL
)
e
n
ab
le
au
to
m
at
ed
an
aly
s
is
an
d
in
ter
p
r
etab
ilit
y
o
f
th
ese
s
p
ee
ch
f
ea
tu
r
es,
o
f
f
er
in
g
a
p
ath
way
f
o
r
r
o
b
u
s
t a
n
d
co
n
s
is
ten
t PD
p
r
ed
i
ctio
n
[
1
9
]
-
[
2
1
].
T
h
is
p
ap
er
p
r
o
p
o
s
es
an
ML
-
b
ased
PD
d
etec
tio
n
f
r
am
ewo
r
k
u
tili
zin
g
th
e
f
u
ll
“P
ar
k
i
n
s
o
n
’
s
d
is
ea
s
e
s
p
ee
ch
f
ea
tu
r
es
”
d
ataset,
o
r
ig
in
ally
co
llected
b
y
th
e
Dep
a
r
tm
en
t
o
f
Neu
r
o
lo
g
y
at
I
s
tan
b
u
l
Un
iv
er
s
ity
an
d
h
o
s
ted
v
ia
th
e
UC
I
ML
r
ep
o
s
ito
r
y
[
2
2
]
.
T
h
e
d
ataset
in
clu
d
es
7
5
4
ex
tr
ac
ted
f
ea
tu
r
es
f
r
o
m
s
u
s
tain
ed
v
o
wel
p
h
o
n
atio
n
r
ec
o
r
d
in
g
s
o
f
2
5
2
in
d
iv
id
u
als
(
1
8
8
PD
p
atie
n
ts
an
d
6
4
h
ea
lth
y
c
o
n
tr
o
ls
)
,
co
v
er
in
g
d
iv
e
r
s
e
d
em
o
g
r
a
p
h
ic
b
ac
k
g
r
o
u
n
d
s
.
B
y
ad
d
r
ess
in
g
ch
alle
n
g
es
lik
e
h
ig
h
-
d
im
e
n
s
io
n
ality
,
class
im
b
alan
ce
,
a
n
d
m
o
d
el
in
ter
p
r
etab
ilit
y
,
th
is
wo
r
k
in
teg
r
ates
m
u
lti
-
m
eth
o
d
f
ea
tu
r
e
s
el
ec
tio
n
,
en
s
em
b
le
lear
n
in
g
tech
n
iq
u
es,
an
d
in
ter
p
r
etab
le
AI
to
d
eliv
er
a
r
o
b
u
s
t,
s
ca
lab
le,
an
d
clin
ically
r
elev
an
t so
lu
tio
n
f
o
r
ea
r
l
y
PD d
etec
tio
n
.
2.
RE
L
AT
E
D
WO
RK
Go
v
in
d
u
a
n
d
Palwe
[
2
3
]
a
p
p
l
ied
SVM,
KNN,
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
an
d
r
an
d
o
m
f
o
r
e
s
t
(
R
F)
t
o
t
h
e
MD
VP
au
d
io
d
ataset
f
o
r
PD
class
if
icatio
n
.
T
h
eir
RF
m
o
d
el
ac
h
ie
v
ed
9
1
.
8
3
%
ac
cu
r
ac
y
,
b
u
t
th
e
s
m
all
d
ataset
(
3
0
p
atien
ts
)
in
cr
e
ased
s
u
s
ce
p
tib
ilit
y
to
o
v
er
f
itti
n
g
,
lim
itin
g
g
en
er
alis
ab
ilit
y
.
M
a
k
a
r
i
o
u
s
e
t
a
l
.
[
2
4
]
d
e
v
e
l
o
p
e
d
a
m
u
l
t
i
-
m
o
d
a
l
i
t
y
M
L
m
o
d
e
l
i
n
t
e
g
r
a
t
i
n
g
P
PM
I
a
n
d
P
D
B
P
d
a
t
a
s
et
s
,
u
t
i
l
is
i
n
g
R
F
,
S
V
M
,
a
n
d
DL
t
ec
h
n
i
q
u
e
s
.
T
h
e
i
r
m
o
d
e
l
i
n
i
t
i
al
ly
a
c
h
i
e
v
e
d
a
n
A
U
C
o
f
8
9
.
7
2
%
,
l
a
t
e
r
o
p
t
i
m
is
e
d
t
o
8
5
.
0
3
%
.
H
o
w
e
v
e
r
,
w
h
il
e
t
h
ei
r
a
p
p
r
o
a
c
h
i
n
c
o
r
p
o
r
a
t
e
d
g
e
n
e
t
i
c,
t
r
a
n
s
c
r
i
p
t
o
m
i
c
,
a
n
d
cl
i
n
i
c
al
m
a
r
k
e
r
s
,
i
ts
r
el
i
a
n
c
e
o
n
o
m
i
c
s
-
b
a
s
e
d
te
s
ti
n
g
a
n
d
i
m
a
g
i
n
g
d
a
t
a
r
e
d
u
c
e
s
a
cc
e
s
s
i
b
il
i
ty
f
o
r
r
e
a
l
-
w
o
r
l
d
c
l
i
n
i
ca
l
u
s
e
.
Z
h
an
g
et
a
l.
[
2
5
]
c
o
m
p
ar
e
d
d
ec
is
io
n
tr
ee
(
DT
)
,
KNN,
Naïv
e
B
ay
es,
R
F,
SVM,
an
d
XGB
o
o
s
t
o
n
th
e
PP
MI
d
ataset.
T
h
eir
p
en
alis
ed
LR
m
o
d
el
r
ea
ch
ed
an
AUC
o
f
0
.
9
4
,
wh
ile
XGBo
o
s
t
ac
h
iev
ed
0
.
9
2
.
Alth
o
u
g
h
th
eir
s
tu
d
y
ca
te
g
o
r
is
ed
PD
r
is
k
f
ac
to
r
s
b
ased
o
n
co
s
t
an
d
a
cc
ess
ib
ilit
y
,
it
lack
ed
ex
p
licit
class
b
alan
cin
g
an
d
ex
ter
n
al
v
alid
atio
n
b
ey
o
n
d
th
e
d
ata
s
et
co
n
s
tr
ain
ts
.
W
an
g
et
a
l.
[
2
0
]
d
ev
elo
p
ed
a
d
ee
p
lear
n
in
g
(
DNN)
an
d
ML
-
b
ased
PD c
lass
if
icat
io
n
s
y
s
tem
u
s
in
g
th
e
PP
MI
d
ataset
(
5
8
4
in
d
iv
id
u
al
s
:
4
0
1
ea
r
ly
PD,
1
8
3
h
ea
lth
y
co
n
tr
o
ls
)
.
T
h
ei
r
DNN
m
o
d
el
ac
h
iev
ed
9
6
.
6
8
%
ac
cu
r
ac
y
.
Ho
wev
er
,
th
e
lack
o
f
ex
p
licit
f
ea
tu
r
e
s
elec
tio
n
m
ad
e
th
e
m
o
d
el
p
r
o
n
e
to
o
v
er
f
itti
n
g
an
d
less
in
ter
p
r
etab
le
f
o
r
clin
ical
ap
p
licatio
n
s
.
Als
h
am
m
r
i
et
a
l.
[
2
6
]
a
p
p
lied
KNN,
SVM,
DT
,
R
F,
an
d
m
u
lti
-
lay
er
p
er
ce
p
t
r
o
n
(
ML
P)
t
o
th
e
UC
I
v
o
ice
d
ataset
(
1
9
5
s
p
ee
ch
s
a
m
p
les).
T
h
eir
ML
P
m
o
d
el
o
u
tp
er
f
o
r
m
ed
SVM
(
9
5
%)
with
an
ac
cu
r
ac
y
o
f
9
8
.
3
1
%.
Ho
we
v
er
,
as
th
eir
s
tu
d
y
r
elied
s
o
lely
o
n
s
p
ee
c
h
f
ea
tu
r
es,
it
f
ailed
to
co
n
s
id
er
n
o
n
-
m
o
to
r
PD
s
y
m
p
to
m
s
,
lim
itin
g
its
r
ea
l
-
wo
r
ld
ap
p
licab
ilit
y
.
Saee
d
et
a
l.
[
2
7
]
ap
p
lied
KN
N,
SVM,
Naïv
e
B
ay
es,
R
F,
an
d
ML
P
o
n
a
UC
I
v
o
ice
d
a
taset
(
2
4
0
r
ec
o
r
d
in
g
s
,
4
6
f
ea
t
u
r
es),
u
s
in
g
f
ilter
-
b
ased
(
PC
A,
I
G)
an
d
wr
ap
p
e
r
-
b
ased
(
PS
O,
Gr
ee
d
y
Step
wis
e)
f
ea
tu
r
e
s
elec
tio
n
.
T
h
eir
b
est m
o
d
el
(
K
NN
with
wr
ap
p
er
s
elec
tio
n
)
ac
h
iev
ed
8
8
.
3
3
% a
cc
u
r
ac
y
.
Ho
wev
er
,
th
eir
s
m
aller
d
ataset
an
d
f
ea
tu
r
e
s
et
lim
ited
g
en
er
aliza
b
ilit
y
.
Nah
ar
et
a
l.
[
2
8
]
in
v
esti
g
ated
f
ea
tu
r
e
s
elec
tio
n
-
b
ased
class
if
icatio
n
f
o
r
ea
r
ly
PD
d
etec
tio
n
,
ap
p
ly
in
g
B
o
r
u
ta,
R
FE,
RF
,
XG
B
o
o
s
t,
B
ag
g
in
g
,
an
d
E
x
tr
a
T
r
ee
s
C
las
s
if
ier
o
n
th
e
UC
I
d
ataset.
T
h
eir
b
est
m
o
d
el
(
B
ag
g
in
g
)
ac
h
ie
v
ed
8
2
.
3
5
%
ac
cu
r
ac
y
,
b
u
t
th
e
s
m
all
d
ata
s
et
(
8
0
p
ar
ticip
an
ts
)
an
d
f
o
c
u
s
o
n
s
p
ee
ch
-
o
n
ly
f
ea
tu
r
es r
ed
u
ce
d
its
b
r
o
a
d
er
cl
in
ical
u
tili
ty
.
Ali
et
a
l.
[
2
9
]
p
r
o
p
o
s
ed
an
e
n
s
em
b
le
lear
n
in
g
m
o
d
el
(
E
O
FS
C
)
in
teg
r
atin
g
d
ee
p
n
eu
r
al
n
etwo
r
k
s
(
DNN)
with
f
ea
tu
r
e
s
elec
tio
n
.
T
h
eir
ap
p
r
o
ac
h
,
f
o
cu
s
ed
o
n
m
u
ltip
le
v
o
wel
p
h
o
n
atio
n
s
,
ac
h
iev
ed
9
5
%
ac
cu
r
ac
y
.
Ho
wev
er
,
th
eir
r
elia
n
ce
o
n
p
h
o
n
atio
n
-
s
p
ec
if
ic
f
ea
tu
r
es
an
d
m
ajo
r
ity
v
o
tin
g
lim
ited
in
ter
p
r
etab
ilit
y
an
d
f
ea
tu
r
e
g
en
e
r
aliza
tio
n
.
Var
g
h
ese
et
a
l.
[
3
0
]
ap
p
lied
SVM,
DT
s
,
l
in
ea
r
r
eg
r
ess
io
n
,
an
d
su
p
p
o
r
t
v
ec
t
o
r
r
eg
r
ess
io
n
(
SVR
)
o
n
th
e
UC
I
Par
k
in
s
o
n
’
s
T
elem
o
n
ito
r
in
g
d
ataset
to
p
r
ed
ict
m
o
to
r
an
d
to
tal
UPDR
S
s
co
r
es.
T
h
eir
m
o
d
el
ac
h
ie
v
ed
an
R
MSE
o
f
7
.
4
9
f
o
r
T
o
tal
U
PDR
S
an
d
6
.
0
6
f
o
r
Mo
to
r
UP
DR
S,
d
em
o
n
s
tr
atin
g
ef
f
ec
tiv
e
s
ev
er
ity
p
r
ed
ictio
n
r
ath
er
th
an
d
ir
e
ct
PD c
lass
if
icatio
n
.
Srin
iv
asan
et
a
l.
[
3
1
]
p
r
o
p
o
s
ed
a
m
u
lticlas
s
class
if
icatio
n
ap
p
r
o
ac
h
f
o
r
PD
d
etec
tio
n
u
s
in
g
v
o
ice
s
ig
n
als,
co
m
p
ar
in
g
KNN,
KSVM,
DT
,
R
F,
an
d
f
ee
d
-
f
o
r
wa
r
d
n
eu
r
al
n
etwo
r
k
(
FNN)
o
n
th
e
UC
I
d
ataset
(
3
1
p
atien
ts
,
1
9
5
v
o
ice
s
am
p
les).
T
h
eir
FNN
m
o
d
el
ac
h
iev
e
d
9
9
.
1
1
%
ac
c
u
r
ac
y
b
u
t
r
elied
en
ti
r
ely
o
n
DL
,
m
ak
in
g
it c
o
m
p
u
tatio
n
ally
e
x
p
en
s
iv
e
a
n
d
h
ar
d
er
to
in
ter
p
r
et
f
o
r
clin
i
ca
l d
ep
lo
y
m
e
n
t.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
Ou
r
p
r
o
p
o
s
ed
m
o
d
el
in
teg
r
ate
s
ad
v
an
ce
d
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es,
d
ata
b
alan
cin
g
m
eth
o
d
s
,
an
d
o
p
tim
is
ed
ML
alg
o
r
ith
m
s
to
ac
h
iev
e
r
o
b
u
s
t
PD
d
etec
tio
n
.
T
h
e
UC
I
Par
k
in
s
o
n
’
s
Sp
ee
ch
Data
s
et,
wh
ich
in
clu
d
es
2
5
2
p
a
r
ticip
an
ts
(
1
8
8
PD,
6
4
h
ea
lth
y
co
n
tr
o
ls
)
,
is
u
s
ed
to
t
r
ain
th
e
m
o
d
el.
Un
li
k
e
p
r
e
v
io
u
s
s
tu
d
ies
(
T
ab
le
1
)
t
h
at
r
ely
s
o
lely
o
n
s
p
ee
ch
f
ea
tu
r
es,
o
u
r
a
p
p
r
o
ac
h
in
co
r
p
o
r
ates
a
co
m
b
in
ati
o
n
o
f
s
p
ee
c
h
an
d
s
y
m
p
to
m
-
b
ased
f
ea
t
u
r
es
to
im
p
r
o
v
e
ac
cu
r
ac
y
an
d
r
ea
l
-
wo
r
ld
ap
p
licab
ilit
y
.
XGBo
o
s
t,
o
p
tim
is
ed
v
ia
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
3
6
-
1
7
4
4
1738
R
an
d
o
m
is
ed
Sear
ch
C
V,
is
e
m
p
lo
y
ed
as
th
e
p
r
im
ar
y
class
if
icatio
n
m
o
d
el,
ac
h
iev
in
g
9
6
.
6
9
%
ac
cu
r
ac
y
.
T
h
e
f
lo
wch
ar
t o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
as in
Fig
u
r
e
1
.
T
ab
le
1
.
Su
m
m
a
r
y
o
f
r
elate
d
wo
r
k
A
u
t
h
o
r
s
B
e
st
me
t
h
o
d
Ty
p
e
o
f
m
o
d
a
l
l
i
t
y
P
e
r
f
o
r
ma
n
c
e
V
o
l
u
me
o
f
d
a
t
a
s
e
t
G
o
v
i
n
d
u
a
n
d
P
a
l
w
e
[
2
3
]
R
a
n
d
o
m F
o
r
e
s
t
(
R
F
)
M
D
V
P
a
u
d
i
o
D
a
t
a
9
1
.
8
3
%
3
1
p
e
o
p
l
e
M
a
k
a
r
i
o
u
s
e
t
a
l
.
[
2
4
]
D
e
e
p
Le
a
r
n
i
n
g
(
D
L)
P
P
M
I
,
P
D
B
P
8
3
.
9
5
%
7
5
6
p
e
o
p
l
e
Zh
a
n
g
e
t
a
l
.
[
2
5
]
P
e
n
a
l
i
z
e
d
L
R
P
P
M
I
A
U
C
o
f
0
.
9
4
7
4
7
p
e
o
p
l
e
(
mi
ss
i
n
g
v
a
l
u
e
s
g
r
e
a
t
e
r
t
h
a
n
1
0
e
x
c
l
u
d
e
d
)
W
a
n
g
e
t
a
l
.
[
2
0
]
D
e
e
p
N
e
u
r
a
l
N
e
t
w
o
r
k
P
P
M
I
9
6
.
6
8
%
5
8
4
i
n
d
i
v
i
d
u
a
l
s
A
l
sh
a
mm
r
i
e
t
a
l
.
[
2
6
]
M
u
l
t
i
-
La
y
e
r
P
e
r
c
e
p
t
r
o
n
(
M
LP)
U
C
I
d
a
t
a
set
9
8
.
3
1
%
1
9
5
r
e
c
o
r
d
s
o
f
v
o
i
c
e
s
i
g
n
a
l
f
e
a
t
u
r
e
s
S
a
e
e
d
e
t
a
l
.
[2
7
]
K
N
N
+
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
K
a
g
g
l
e
8
8
.
3
3
%
2
4
0
r
e
c
o
r
d
i
n
g
s fr
o
m
8
0
P
D
p
a
t
i
e
n
t
s
N
a
h
a
r
e
t
a
l
.
[
2
8
]
B
a
g
g
i
n
g
C
l
a
ssi
f
i
e
r
U
C
I
d
a
t
a
set
8
2
.
3
5
%
8
0
p
a
r
t
i
c
i
p
a
n
t
s
A
l
i
e
t
a
l
.
[
2
9
]
D
e
e
p
Le
a
r
n
i
n
g
+
F
S
c
o
r
e
M
u
l
t
i
-
t
y
p
e
v
o
w
e
l
p
h
o
n
a
t
i
o
n
s
d
a
t
a
se
t
9
5
%
1
6
0
s
u
b
j
e
c
t
s
V
a
r
g
h
e
se
e
t
a
l
.
[3
0
]
S
u
p
p
o
r
t
V
e
c
t
o
r
R
e
g
r
e
ssi
o
n
U
C
I
M
L
r
e
p
o
si
t
o
r
y
R
M
S
E
7
.
4
9
(
U
P
D
R
S
)
4
2
c
a
n
d
i
d
a
t
e
s
S
r
i
n
i
v
a
s
a
n
e
t
a
l
.
[
3
1
]
F
e
e
d
-
F
o
r
w
a
r
d
N
e
u
r
a
l
N
e
t
w
o
r
k
U
C
I
M
L
R
e
p
o
s
i
t
o
r
y
9
9
.
1
1
%
3
1
p
e
o
p
l
e
Fig
u
r
e
1
.
Flo
wch
ar
t
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
r
ed
ictio
n
o
f
P
a
r
kin
s
o
n
's
d
is
ea
s
e
u
s
in
g
fea
tu
r
e
s
elec
tio
n
a
n
d
en
s
emb
le
lea
r
n
in
g
tech
n
iq
u
es
(
S
h
a
r
a
n
T.
D.
)
1739
3
.
1
.
Da
t
a
s
et
co
llect
i
o
n
T
h
e
d
ataset
u
s
ed
i
n
th
is
s
tu
d
y
co
m
p
r
is
es
7
5
6
s
am
p
les
an
d
7
5
4
ex
tr
ac
te
d
f
ea
tu
r
es,
s
o
u
r
ce
d
f
r
o
m
s
u
s
tain
ed
p
h
o
n
ati
o
n
r
ec
o
r
d
i
n
g
s
o
f
th
e
v
o
wel
s
o
u
n
d
“/a/.
”
I
t
co
n
tain
s
d
ata
f
r
o
m
2
5
2
in
d
iv
id
u
als:
1
8
8
PD
p
atien
ts
(
1
0
7
m
ales,
8
1
f
e
m
ales)
an
d
6
4
h
ea
lth
y
co
n
tr
o
ls
(
2
3
m
ales,
4
1
f
em
ales)
.
Par
ticip
an
ts
r
an
g
ed
i
n
ag
e
f
r
o
m
3
3
to
8
7
y
ea
r
s
(
m
ea
n
a
g
e:
6
5
.
1
±
1
0
.
9
f
o
r
PD,
6
1
.
1
±
8
.
9
f
o
r
co
n
tr
o
ls
)
.
T
h
e
d
at
aset
was
o
r
ig
in
ally
co
llected
b
y
th
e
Dep
a
r
tm
en
t
o
f
Ne
u
r
o
lo
g
y
,
C
er
r
a
h
p
aşa
Facu
lty
o
f
Me
d
icin
e,
I
s
tan
b
u
l
Un
iv
er
s
ity
,
u
n
d
er
ph
y
s
ician
s
u
p
er
v
is
io
n
,
a
n
d
m
a
d
e
p
u
b
licly
a
v
ailab
le
v
ia
th
e
UC
I
ML
r
ep
o
s
ito
r
y
[
2
2
]
.
Fo
r
an
aly
s
is
p
u
r
p
o
s
es,
it
was
ac
ce
s
s
ed
th
r
o
u
g
h
Kag
g
le
,
wh
ich
m
ir
r
o
r
s
th
e
o
r
ig
in
al
d
ataset.
Du
r
in
g
d
ata
c
o
llectio
n
,
p
ar
ticip
an
ts
wer
e
in
s
tr
u
cted
to
s
u
s
tain
th
e
p
h
o
n
atio
n
o
f
th
e
v
o
wel
“a
”
i
n
th
r
ee
r
ep
etitio
n
s
,
r
ec
o
r
d
e
d
u
s
in
g
a
s
tan
d
ar
d
m
icr
o
p
h
o
n
e
at
a
s
am
p
lin
g
r
at
e
o
f
4
4
.
1
k
Hz.
All
d
ata
p
ar
ti
cip
an
ts
in
T
ab
le
2
is
d
e
-
id
e
n
t
if
ied
an
d
eth
ically
clea
r
ed
f
o
r
r
esear
ch
u
s
e.
T
ab
le
2
.
Data
s
et
s
u
m
m
ar
y
D
a
t
a
s
e
t
a
t
t
r
i
b
u
t
e
D
e
scri
p
t
i
o
n
To
t
a
l
P
a
r
t
i
c
i
p
a
n
t
s
2
5
2
P
D
P
a
t
i
e
n
t
s
1
8
8
(
1
0
7
mal
e
s,
8
1
f
e
mal
e
s)
H
e
a
l
t
h
y
C
o
n
t
r
o
l
s
6
4
(
2
3
m
a
l
e
s,
4
1
f
e
m
a
l
e
s)
To
t
a
l
F
e
a
t
u
r
e
s
7
5
4
S
a
mp
l
i
n
g
R
a
t
e
4
4
.
1
k
H
z
D
a
t
a
C
o
l
l
e
c
t
i
o
n
S
u
st
a
i
n
e
d
p
h
o
n
a
t
i
o
n
o
f
v
o
w
e
l
/
a
/
3
.
2
.
P
re
-
pro
ce
s
s
ing
T
h
e
Par
k
in
s
o
n
’
s
Sp
ee
ch
Data
s
et
co
n
tain
s
7
5
4
f
ea
tu
r
e
s
ex
tr
ac
ted
f
r
o
m
s
u
s
tain
ed
p
h
o
n
atio
n
r
ec
o
r
d
in
g
s
,
p
r
esen
tin
g
a
h
ig
h
-
d
im
en
s
io
n
al
an
d
p
o
ten
tiall
y
r
ed
u
n
d
an
t
f
ea
tu
r
e
s
p
ac
e.
T
o
ad
d
r
ess
th
is
,
we
ap
p
lied
f
i
v
e
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es:
RF
I
m
p
o
r
ta
n
c
e,
r
ec
u
r
s
i
v
e
f
ea
tu
r
e
elim
in
atio
n
(
R
FE)
,
L
ASSO
R
eg
r
ess
io
n
,
B
o
r
u
ta,
an
d
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
.
Ou
r
f
in
al
f
ea
tu
r
e
s
et
was
d
er
iv
ed
u
s
in
g
a
co
n
s
en
s
u
s
-
b
ased
s
tr
ateg
y
,
wh
er
e
f
ea
tu
r
es
co
n
s
is
ten
tly
id
en
tifie
d
b
y
at
least
two
o
u
t
o
f
th
e
f
o
u
r
p
r
im
ar
y
tech
n
iq
u
es
(
R
F,
R
FE,
L
ASSO,
B
o
r
u
ta)
wer
e
r
etain
ed
.
T
h
i
s
ap
p
r
o
ac
h
b
alan
ce
s
d
im
en
s
io
n
ality
r
ed
u
ctio
n
an
d
in
ter
p
r
etab
ilit
y
wh
ile
r
ed
u
cin
g
m
eth
o
d
-
s
p
ec
if
ic
b
ias.
PC
A
was
u
s
ed
s
o
lely
f
o
r
co
m
p
a
r
is
o
n
an
d
n
o
t
f
o
r
f
in
al
f
ea
tu
r
e
s
elec
tio
n
d
u
e
to
its
lack
o
f
in
te
r
p
r
etab
ilit
y
.
3
.
2
.
1
.
F
ea
t
ure
s
elec
t
io
n t
ec
h
niq
ue
s
T
o
im
p
r
o
v
e
m
o
d
el
ef
f
icien
cy
an
d
ac
cu
r
ac
y
,
s
ev
er
al
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
wer
e
ap
p
lied
to
id
en
tify
th
e
m
o
s
t r
elev
an
t f
ea
t
u
r
es f
o
r
PD
class
if
icatio
n
.
RF
Featu
r
e
I
m
p
o
r
tan
ce
was
u
s
ed
to
r
an
k
f
ea
tu
r
es
b
ased
o
n
th
eir
co
n
tr
ib
u
tio
n
to
class
if
icatio
n
,
d
eter
m
in
ed
th
r
o
u
g
h
Gin
i
im
p
u
r
ity
r
ed
u
ctio
n
.
A
R
F
m
o
d
el
with
3
0
esti
m
ato
r
s
was
tr
ain
e
d
,
id
en
tify
in
g
en
er
g
y
an
d
f
r
e
q
u
en
c
y
-
b
ased
s
p
ee
c
h
m
ar
k
er
s
as
k
ey
i
n
d
icato
r
s
o
f
Par
k
in
s
o
n
ian
s
p
ee
ch
i
m
p
a
i
r
m
e
n
t
s
.
T
h
es
e
h
i
g
h
-
r
a
n
k
i
n
g
f
e
a
t
u
r
e
s
p
l
a
y
e
d
a
c
r
u
c
ia
l
r
o
l
e
i
n
r
e
f
i
n
i
n
g
t
h
e
d
at
a
s
e
t
f
o
r
c
l
a
s
s
i
f
i
ca
t
i
o
n
as
s
h
o
w
n
i
n
T
ab
l
e
3
.
T
ab
le
3
.
T
o
p
f
ea
tu
r
es selecte
d
b
y
RF
F
e
a
t
u
r
e
I
mp
o
r
t
a
n
c
e
sc
o
r
e
st
d
_
d
e
l
t
a
_
d
e
l
t
a
_
l
o
g
_
e
n
e
r
g
y
0
.
0
2
8
5
t
q
w
t
_
e
n
t
r
o
p
y
_
l
o
g
_
d
e
c
_
1
2
0
.
0
1
6
0
t
q
w
t
_
e
n
e
r
g
y
_
d
e
c
_
2
7
0
.
0
1
3
6
t
q
w
t
_
e
n
t
r
o
p
y
_
s
h
a
n
n
o
n
_
d
e
c
_
1
2
0
.
0
1
3
0
st
d
_
6
t
h
_
d
e
l
t
a
_
d
e
l
t
a
0
.
0
1
2
7
R
FE
,
wi
th
LR
a
s
th
e
b
ase
esti
m
ato
r
,
iter
ativ
ely
r
em
o
v
e
d
less
s
ig
n
if
ican
t
f
ea
tu
r
es
to
r
etain
th
e
m
o
s
t
d
is
cr
im
in
ativ
e
o
n
es.
T
h
e
to
p
f
iv
e
s
elec
ted
f
ea
tu
r
es
wer
e:
tq
wt_
en
tr
o
p
y
_
lo
g
_
d
ec
_
1
8
,
tq
wt_
en
tr
o
p
y
_
lo
g
_
d
ec
_
2
0
,
t
q
wt_
en
tr
o
p
y
_
lo
g
_
d
ec
_
2
4
,
tq
wt
_
en
tr
o
p
y
_
lo
g
_
d
ec
_
2
5
,
tq
wt_
e
n
tr
o
p
y
_
lo
g
_
d
ec
_
2
8
.
L
ass
o
R
eg
r
ess
io
n
(
L
1
R
eg
u
lar
izatio
n
)
f
u
r
th
er
r
e
d
u
ce
d
d
im
e
n
s
io
n
ality
b
y
s
h
r
in
k
i
n
g
ir
r
elev
a
n
t
f
ea
tu
r
e
weig
h
ts
to
ze
r
o
wh
ile
p
r
eser
v
in
g
cr
u
cial
p
r
e
d
icto
r
s
.
A
L
ass
o
C
V
m
o
d
el
with
f
iv
e
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
was
u
s
ed
to
id
e
n
tify
t
h
e
m
o
s
t
s
ig
n
if
ica
n
t
f
ea
tu
r
es.
No
tab
ly
,
th
e
to
p
1
0
s
elec
ted
f
ea
tu
r
es
s
h
o
wed
s
tr
o
n
g
o
v
e
r
lap
with
th
o
s
e
id
en
tifie
d
b
y
R
F
an
d
R
FE,
r
ein
f
o
r
cin
g
th
e
ir
p
r
ed
ictiv
e
s
tr
en
g
th
.
T
h
ese
f
ea
tu
r
es
in
cl
u
d
e
d
s
td
_
d
elta_
d
elta_
lo
g
_
en
er
g
y
,
tq
wt_
k
u
r
to
s
is
Valu
e_
d
ec
_
3
1
,
tq
wt_
en
tr
o
p
y
_
lo
g
_
d
ec
_
2
8
,
s
t
d
_
7
th
_
d
elta_
d
elta,
s
td
_
6
th
_
d
elta_
d
elta,
tq
wt_
en
tr
o
p
y
_
l
o
g
_
d
ec
_
2
6
,
tq
wt_
k
u
r
to
s
is
Valu
e_
d
ec
_
2
7
,
tq
wt_
k
u
r
t
o
s
is
Valu
e_
d
ec
_
3
3
,
tq
wt_
m
ax
Valu
e_
d
ec
_
2
5
,
tq
wt
_
en
tr
o
p
y
_
lo
g
_
d
ec
_
3
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
3
6
-
1
7
4
4
1740
B
o
r
u
ta
Featu
r
e
Selectio
n
,
a
wr
ap
p
er
-
b
ased
tech
n
iq
u
e
u
s
in
g
RF
,
v
alid
ated
th
e
im
p
o
r
tan
ce
o
f
j
itter
,
s
h
im
m
er
,
an
d
p
er
io
d
-
b
ased
f
e
atu
r
es,
wh
ich
a
r
e
wid
ely
r
ec
o
g
n
ized
i
n
Par
k
in
s
o
n
’
s
s
p
ee
ch
p
ath
o
l
o
g
y
.
T
h
ese
f
ea
tu
r
es,
co
m
m
o
n
ly
lin
k
ed
t
o
p
h
o
n
at
o
r
y
an
d
ac
o
u
s
tic
ch
an
g
es,
in
clu
d
ed
m
ea
n
Per
i
o
d
Pu
ls
es,
lo
cPct
J
itter
,
lo
cAb
s
J
itter
,
r
ap
J
itter
,
p
p
q
5
J
itter
,
d
d
p
J
itt
er
,
ap
q
1
1
Sh
im
m
er
.
Ad
d
itio
n
ally
,
PC
A
was
ex
p
lo
r
ed
to
tr
an
s
f
o
r
m
th
e
d
ataset
in
to
5
0
p
r
in
cip
al
c
o
m
p
o
n
en
ts
,
en
ab
lin
g
f
aster
co
m
p
u
tatio
n
.
Ho
wev
er
,
PC
A
was
n
o
t
u
s
ed
in
th
e
f
i
n
al
s
elec
tio
n
,
as
d
ir
ec
t
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
(
R
F,
R
FE,
L
as
s
o
,
an
d
B
o
r
u
ta)
p
r
o
v
i
d
ed
b
etter
class
if
icatio
n
p
er
f
o
r
m
an
ce
an
d
in
ter
p
r
etab
i
lity
.
B
y
co
m
b
in
in
g
th
ese
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es,
we
m
ad
e
s
u
r
e
th
at
o
n
ly
th
e
m
o
s
t
r
elev
an
t
f
ea
tu
r
es
wer
e
k
ep
t
in
th
e
d
ataset,
in
cr
ea
s
in
g
m
o
d
el
ac
cu
r
ac
y
wh
ile
lo
wer
in
g
co
m
p
u
tatio
n
a
l
co
s
t
an
d
r
ed
u
n
d
a
n
cy
.
T
a
b
l
e
4
h
ig
h
lig
h
ts
th
e
co
m
p
ar
ativ
e
r
esu
lts
o
f
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es.
T
h
e
f
in
al
f
ea
tu
r
e
s
u
b
s
et
was
d
er
iv
ed
th
r
o
u
g
h
a
co
n
s
en
s
u
s
-
b
ased
ap
p
r
o
ac
h
,
s
elec
tin
g
f
ea
tu
r
es
id
en
tifie
d
b
y
at
least
two
o
f
t
h
e
f
o
u
r
tech
n
iq
u
es:
RF
,
R
FE,
L
ASSO,
an
d
B
o
r
u
ta.
T
h
is
m
eth
o
d
e
n
s
u
r
ed
th
at
o
n
ly
th
e
m
o
s
t
co
n
s
is
ten
tly
r
an
k
ed
an
d
b
io
lo
g
ically
r
ele
v
an
t
f
ea
t
u
r
es
wer
e
r
etain
ed
,
im
p
r
o
v
in
g
m
o
d
el
r
o
b
u
s
tn
ess
an
d
i
n
ter
p
r
etab
ilit
y
.
T
ab
le
4
ex
p
licitly
h
ig
h
lig
h
ts
th
ese
s
elec
ted
f
ea
tu
r
es,
wh
ich
in
clu
d
e
k
ey
b
io
m
ar
k
e
r
s
lik
e
s
td
_
d
elta_
d
el
ta_
lo
g
_
en
e
r
g
y
,
s
td
_
6
th
_
d
elta_
d
elta,
an
d
tq
wt_
en
tr
o
p
y
_
lo
g
_
d
ec
_
2
8
,
co
m
m
o
n
ly
ass
o
ciate
d
with
Par
k
in
s
o
n
ian
v
o
ca
l im
p
air
m
e
n
ts
.
T
ab
le
4
.
C
o
m
p
a
r
ativ
e
f
ea
tu
r
e
s
elec
tio
n
r
esu
lts
F
e
a
t
u
r
e
R
a
n
d
o
m
f
o
r
e
st
r
a
n
k
R
F
E
sel
e
c
t
e
d
La
sso
c
o
e
f
f
i
c
i
e
n
t
B
o
r
u
t
a
sel
e
c
t
e
d
S
e
l
e
c
t
e
d
i
n
f
i
n
a
l
su
b
s
e
t
st
d
_
d
e
l
t
a
_
d
e
l
t
a
_
l
o
g
_
e
n
e
r
g
y
1
Y
e
s
0
.
0
2
8
5
Y
e
s
Y
e
s
t
q
w
t
_
e
n
t
r
o
p
y
_
l
o
g
_
d
e
c
_
1
2
2
No
0
.
0
1
6
0
No
No
t
q
w
t
_
e
n
e
r
g
y
_
d
e
c
_
2
7
3
No
0
.
0
1
3
6
No
No
t
q
w
t
_
e
n
t
r
o
p
y
_
s
h
a
n
n
o
n
_
d
e
c
_
1
2
4
No
0
.
0
1
3
0
No
No
st
d
_
6
t
h
_
d
e
l
t
a
_
d
e
l
t
a
5
Y
e
s
0
.
0
1
2
7
Y
e
s
Y
e
s
3
.
2
.
2
.
M
o
del t
ra
ini
ng
a
nd
o
ptim
iza
t
io
n
Af
ter
s
elec
tin
g
th
e
m
o
s
t
r
elev
an
t
f
ea
tu
r
es,
th
e
n
e
x
t
s
tep
i
n
v
o
lv
es
tr
ain
i
n
g
an
d
o
p
tim
izin
g
th
e
ML
m
o
d
el
f
o
r
PD
class
if
icatio
n
.
W
e
em
p
lo
y
ed
XGBo
o
s
t
as
th
e
p
r
im
ar
y
class
if
icatio
n
al
g
o
r
i
th
m
d
u
e
to
its
h
ig
h
ac
cu
r
ac
y
,
r
o
b
u
s
tn
ess
ag
ain
s
t
im
b
alan
ce
d
d
atasets
,
an
d
ef
f
icien
cy
in
h
an
d
lin
g
h
ig
h
-
d
i
m
en
s
io
n
al
d
ata.
T
o
o
p
tim
ize
th
e
XGBo
o
s
t
m
o
d
el,
R
an
d
o
m
ized
Sear
ch
C
r
o
s
s
-
Valid
atio
n
(
C
V)
wa
s
u
s
e
d
to
f
in
e
-
tu
n
e
k
ey
h
y
p
er
p
ar
am
eter
s
,
im
p
r
o
v
in
g
g
en
er
ali
za
tio
n
an
d
r
ed
u
ci
n
g
o
v
er
f
itti
n
g
.
Af
ter
5
0
iter
atio
n
s
,
th
e
b
est
h
y
p
er
p
ar
am
eter
s
wer
e
d
eter
m
i
n
ed
an
d
wer
e
t
h
en
u
s
ed
in
t
h
e
f
in
al
XGB
o
o
s
t
m
o
d
el
tr
ain
in
g
.
T
ab
le
5
c
o
n
tain
s
th
e
b
est h
y
p
e
r
p
ar
am
eter
s
af
ter
5
0
iter
atio
n
s
.
On
ce
th
e
b
est
h
y
p
er
p
a
r
am
eter
s
wer
e
s
elec
ted
,
th
e
f
in
al
XG
B
o
o
s
t
m
o
d
el
was
tr
ain
ed
o
n
th
e
b
alan
ce
d
d
ataset
(
af
ter
SMOT
E
was
a
p
p
lied
)
.
T
o
e
n
s
u
r
e
t
h
e
r
o
b
u
s
tn
ess
an
d
r
eliab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el,
5
-
f
o
l
d
s
tr
atif
ied
cr
o
s
s
-
v
alid
atio
n
wa
s
p
er
f
o
r
m
e
d
,
allo
win
g
f
o
r
a
n
u
n
b
iased
ev
al
u
atio
n
ac
r
o
s
s
d
if
f
er
en
t
d
ata
s
p
lits
.
T
h
e
m
o
d
el
ac
h
iev
ed
a
m
ea
n
a
cc
u
r
ac
y
o
f
8
9
.
5
4
%,
d
em
o
n
s
tr
atin
g
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
an
d
g
e
n
er
aliza
b
ilit
y
in
d
is
tin
g
u
is
h
in
g
PD
f
r
o
m
h
ea
lth
y
co
n
tr
o
ls
.
B
y
in
teg
r
atin
g
R
an
d
o
m
ized
Sear
ch
C
V
f
o
r
h
y
p
er
p
a
r
am
et
er
tu
n
in
g
,
SMOT
E
f
o
r
class
b
alan
cin
g
,
an
d
a
r
ef
i
n
ed
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
,
th
e
f
in
al
XGBo
o
s
t
m
o
d
el
ac
h
iev
ed
an
o
v
er
all
ac
c
u
r
ac
y
o
f
9
6
.
6
9
%,
r
ei
n
f
o
r
ci
n
g
its
ef
f
ec
tiv
en
ess
as
a
h
ig
h
ly
r
eliab
l
e
an
d
in
ter
p
r
etab
le
s
o
lu
tio
n
f
o
r
PD
class
if
icatio
n
.
T
ab
le
5
.
Fin
al
o
p
tim
ized
m
o
d
el
p
ar
am
eter
s
H
y
p
e
r
p
a
r
a
me
t
e
r
O
p
t
i
mi
s
e
d
v
a
l
u
e
s
n
_
e
st
i
ma
t
o
r
s
3
0
0
max
_
d
e
p
t
h
7
l
e
a
r
n
i
n
g
_
r
a
t
e
0
.
1
su
b
s
a
m
p
l
e
0
.
8
c
o
l
sam
p
l
e
_
b
y
t
r
e
e
0
.
8
mi
n
_
c
h
i
l
d
_
w
e
i
g
h
t
1
g
a
mm
a
0
.
1
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
o
ev
alu
ate
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
XGBo
o
s
t
m
o
d
el,
its
p
er
f
o
r
m
an
ce
was
co
m
p
ar
ed
with
RF
,
L
ig
h
tGB
M
(
L
GB
M)
,
an
d
a
Vo
tin
g
C
lass
if
ier
.
R
F
w
as
u
s
ed
as
a
b
aselin
e
f
o
r
f
ea
tu
r
e
s
elec
tio
n
b
u
t
s
tr
u
g
g
led
with
o
v
er
f
itti
n
g
an
d
in
ef
f
icien
c
y
in
h
i
g
h
-
d
im
en
s
io
n
al
d
ata.
L
GB
M,
a
g
r
ad
ie
n
t
-
b
o
o
s
tin
g
m
o
d
el,
was
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
r
ed
ictio
n
o
f
P
a
r
kin
s
o
n
's
d
is
ea
s
e
u
s
in
g
fea
tu
r
e
s
elec
tio
n
a
n
d
en
s
emb
le
lea
r
n
in
g
tech
n
iq
u
es
(
S
h
a
r
a
n
T.
D.
)
1741
o
p
tim
ized
f
o
r
s
p
ee
d
an
d
m
em
o
r
y
ef
f
icien
cy
,
m
a
k
in
g
it
s
u
it
ab
le
f
o
r
lar
g
e
d
atasets
.
T
o
e
n
h
an
ce
r
o
b
u
s
tn
ess
,
a
Vo
tin
g
c
lass
if
ier
co
m
b
in
in
g
X
GB
o
o
s
t
an
d
L
GB
M
was
im
p
lem
en
ted
to
im
p
r
o
v
e
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
T
ab
le
6
s
h
o
ws th
e
m
o
d
els p
er
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
.
T
ab
le
6
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
c
o
m
p
ar
is
o
n
M
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
(
P
D
-
1)
R
e
c
a
l
l
(
H
e
a
l
t
h
y
-
0)
F
1
S
c
o
r
e
R
a
n
d
o
m F
o
r
e
s
t
8
4
.
1
%
8
2
%
9
6
%
5
2
%
8
3
%
Li
g
h
t
G
B
M
8
8
.
9
%
8
5
%
9
7
%
6
7
%
8
8
%
V
o
t
i
n
g
C
l
a
ssi
f
i
e
r
9
0
.
7
%
9
5
%
9
9
%
6
9
%
9
0
%
X
G
B
o
o
st
(
O
p
t
i
m
i
se
d
)
9
6
.
6
9
%
9
9
%
9
6
%
9
7
%
9
8
%
T
h
e
r
esu
lts
clea
r
ly
d
em
o
n
s
tr
ate
th
at
th
e
XGBo
o
s
t
m
o
d
el
a
ch
iev
es
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
ev
alu
atio
n
m
etr
ics,
with
an
a
cc
u
r
ac
y
o
f
9
6
.
6
9
%,
p
r
ec
is
io
n
o
f
9
9
%,
an
d
an
F1
-
s
co
r
e
o
f
9
8
%.
U
n
lik
e
th
e
b
aselin
e
m
o
d
els,
XGBo
o
s
t
m
ain
tain
s
h
ig
h
r
ec
all
ac
r
o
s
s
b
o
th
class
es
(
PD:
9
6
%,
Hea
lth
y
:
9
7
%),
in
d
icatin
g
ex
ce
llen
t
s
en
s
itiv
ity
an
d
s
p
ec
i
f
icity
.
I
n
co
n
tr
ast,
RF
ex
h
i
b
ited
s
ig
n
if
ican
t
class
im
b
alan
ce
b
ias,
as
r
ef
lecte
d
in
its
r
ec
all
d
is
p
ar
ity
(
9
6
%
v
s
.
5
2
%).
L
ig
h
tGB
M
an
d
th
e
Vo
tin
g
C
lass
if
ier
s
h
o
wed
im
p
r
o
v
e
d
b
alan
ce
b
u
t
f
ailed
to
m
atch
th
e
o
v
er
all
d
is
cr
im
in
ativ
e
p
o
wer
o
f
XGBo
o
s
t.
T
h
ese
m
etr
ics
(
Fig
u
r
e
2
)
u
n
d
e
r
s
co
r
e
XGBo
o
s
t’
s
r
o
b
u
s
tn
ess
,
p
ar
ticu
lar
ly
in
h
an
d
lin
g
h
i
g
h
-
d
im
e
n
s
io
n
al,
i
m
b
alan
ce
d
d
ata
s
ce
n
ar
i
o
s
co
m
m
o
n
i
n
clin
ical
ap
p
licatio
n
s
.
Fig
u
r
e
2
.
T
o
p
-
r
a
n
k
ed
f
ea
tu
r
es
b
y
XGBo
o
s
t’
s
b
u
ilt
-
in
im
p
o
r
tan
ce
m
etr
ic,
h
ig
h
lig
h
tin
g
th
e
k
ey
ac
o
u
s
tic
m
ar
k
er
s
u
s
ed
in
Par
k
in
s
o
n
’
s
cl
ass
if
icatio
n
SHap
ley
Ad
d
itiv
e
ex
Plan
atio
n
s
(
SHA
P
)
an
aly
s
is
was
co
n
d
u
cted
to
en
h
an
ce
m
o
d
el
tr
an
s
p
a
r
en
cy
an
d
in
ter
p
r
etab
ilit
y
.
Fig
u
r
e
3
illu
s
t
r
ates
h
o
w
in
d
iv
id
u
al
f
ea
tu
r
es
co
n
tr
ib
u
te
t
o
class
if
icatio
n
o
u
t
co
m
es,
q
u
an
tif
y
in
g
ea
ch
f
ea
tu
r
e’
s
im
p
ac
t
o
n
th
e
f
in
al
p
r
ed
ictio
n
.
No
tab
l
y
,
s
td
_
d
elta_
lo
g
_
en
er
g
y
an
d
tq
wt_
en
tr
o
p
y
_
lo
g
_
d
ec
_
1
2
ex
h
ib
ited
t
h
e
h
ig
h
est
SHAP
v
alu
es,
r
ein
f
o
r
cin
g
th
eir
s
tatu
s
as
d
o
m
in
a
n
t
p
r
ed
icto
r
s
.
T
h
ese
f
ea
tu
r
es
co
r
r
esp
o
n
d
to
v
ar
iab
ilit
y
an
d
e
n
tr
o
p
y
in
f
r
eq
u
en
c
y
-
m
o
d
u
lated
s
p
ee
ch
p
atter
n
s
,
wh
ich
ar
e
k
n
o
wn
to
d
eter
io
r
ate
ea
r
ly
in
PD
p
atien
ts
d
u
e
to
p
h
o
n
ato
r
y
m
u
s
cle
co
n
tr
o
l
lo
s
s
.
B
y
elu
cid
atin
g
th
e
m
o
d
el’
s
d
ec
is
io
n
p
r
o
ce
s
s
,
SHAP
en
ab
les
clin
ician
s
to
tr
ac
e
p
r
ed
ictio
n
s
b
ac
k
to
e
x
p
lain
ab
le
ac
o
u
s
tic
b
io
m
ar
k
er
s
,
th
er
eb
y
b
r
id
g
in
g
th
e
g
a
p
b
etwe
en
AI
o
u
tp
u
t
an
d
clin
ic
al
in
tu
itio
n
.
T
h
is
in
ter
p
r
eta
b
ilit
y
is
ess
en
tial
f
o
r
clin
ical
tr
u
s
t
an
d
r
eg
u
lato
r
y
v
alid
atio
n
o
f
AI
-
ass
is
ted
d
iag
n
o
s
tic
s
y
s
tem
s
.
s
y
s
tem
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
3
6
-
1
7
4
4
1742
Fig
u
r
e
3
.
SHAP su
m
m
ar
y
p
lo
t
s
h
o
win
g
th
e
m
a
r
g
in
al
c
o
n
tr
ib
u
tio
n
o
f
ea
ch
f
ea
t
u
r
e
to
war
d
m
o
d
el
p
r
e
d
ictio
n
s
.
Featu
r
es with
h
ig
h
er
SHAP v
a
lu
es c
o
n
tr
ib
u
te
m
o
r
e
s
ig
n
if
ica
n
tly
to
class
if
icatio
n
d
ec
is
io
n
s
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ts
a
ML
-
b
a
s
ed
ap
p
r
o
ac
h
f
o
r
PD
d
etec
tio
n
,
u
tili
zin
g
s
p
ee
ch
b
io
m
a
r
k
er
s
ex
tr
ac
ted
f
r
o
m
th
e
UC
I
Par
k
in
s
o
n
’
s
Sp
ee
ch
Data
s
et.
B
y
in
te
g
r
atin
g
f
ea
tu
r
e
s
elec
tio
n
tec
h
n
iq
u
es,
d
ata
b
alan
cin
g
u
s
in
g
SMOT
E
,
an
d
h
y
p
e
r
p
ar
am
e
ter
o
p
tim
izatio
n
th
r
o
u
g
h
R
an
d
o
m
ized
Sear
ch
C
V,
an
XGBo
o
s
t
-
b
ased
class
if
icatio
n
m
o
d
el
was
d
ev
e
lo
p
ed
,
ac
h
iev
in
g
9
6
.
6
9
%
ac
cu
r
ac
y
with
h
ig
h
r
ec
all
an
d
p
r
ec
is
io
n
ac
r
o
s
s
b
o
th
PD
an
d
h
ea
lth
y
class
e
s
.
A
co
m
p
ar
ativ
e
an
aly
s
is
ag
ain
s
t
RF
,
L
ig
h
tGB
M,
an
d
an
en
s
em
b
le
Vo
tin
g
C
las
s
if
ier
d
em
o
n
s
tr
ated
th
at
XGBo
o
s
t
o
u
tp
er
f
o
r
m
s
tr
ad
itio
n
al
class
if
ier
s
,
m
ak
in
g
it
th
e
m
o
s
t
ef
f
ec
tiv
e
m
o
d
el
f
o
r
PD
class
if
icatio
n
.
T
h
e
f
ea
tu
r
e
i
m
p
o
r
tan
ce
an
aly
s
is
em
p
h
asized
th
e
s
ig
n
if
ican
ce
o
f
en
er
g
y
-
b
ased
an
d
tim
e
-
f
r
eq
u
e
n
cy
s
p
ee
ch
f
ea
tu
r
es,
r
ei
n
f
o
r
cin
g
th
e
r
o
le
o
f
ac
o
u
s
tic
b
io
m
a
r
k
e
r
s
in
PD
s
cr
ee
n
in
g
.
T
h
e
ap
p
licatio
n
o
f
SHAP
ex
p
lain
ab
ilit
y
tech
n
iq
u
es
f
u
r
th
er
en
h
an
ce
d
t
h
e
m
o
d
el’
s
in
ter
p
r
etab
ilit
y
,
in
cr
ea
s
i
n
g
its
p
o
ten
tial
f
o
r
clin
ical
d
ep
lo
y
m
e
n
t
an
d
in
te
g
r
atio
n
in
to
d
e
cisi
o
n
-
s
u
p
p
o
r
t
s
y
s
tem
s
.
Desp
ite
th
e
p
r
o
m
is
in
g
r
esu
lts
,
th
er
e
ar
e
s
ev
er
al
ar
ea
s
f
o
r
f
u
tu
r
e
im
p
r
o
v
em
en
t.
On
e
k
ey
lim
itatio
n
is
th
e
d
ataset
s
ize,
wh
ich
,
wh
ile
s
u
f
f
icien
t
f
o
r
in
itial
v
alid
atio
n
,
r
eq
u
ir
es
f
u
r
th
er
e
x
p
an
s
io
n
an
d
ex
ter
n
al
v
alid
a
tio
n
o
n
lar
g
er
,
m
o
r
e
d
iv
e
r
s
e,
an
d
m
u
lti
-
ce
n
te
r
d
atasets
.
Fu
tu
r
e
s
tu
d
ies
s
h
o
u
ld
f
o
c
u
s
o
n
in
teg
r
atin
g
m
u
ltimo
d
al
b
io
m
ar
k
e
r
s
,
in
co
r
p
o
r
atin
g
m
o
to
r
-
b
ase
d
f
ea
tu
r
es
(
e.
g
.
,
h
a
n
d
wr
itin
g
p
at
ter
n
s
,
g
ait
an
aly
s
is
)
,
clin
ical
s
y
m
p
to
m
s
,
an
d
wea
r
a
b
le
s
en
s
o
r
d
ata
to
d
ev
elo
p
a
m
o
r
e
c
o
m
p
r
e
h
en
s
iv
e
d
iag
n
o
s
tic
m
o
d
el.
Ad
d
itio
n
ally
,
d
ee
p
lear
n
in
g
a
r
ch
itectu
r
es,
s
u
c
h
as
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
o
r
T
r
an
s
f
o
r
m
e
r
-
b
ased
m
o
d
els,
c
o
u
ld
b
e
ex
p
l
o
r
ed
t
o
ca
p
tu
r
e
co
m
p
lex
p
atter
n
s
in
v
o
ice
d
ata
m
o
r
e
ef
f
ec
tiv
ely
.
T
o
f
ac
ilit
ate
r
ea
l
-
wo
r
ld
clin
ic
al
d
ep
lo
y
m
e
n
t,
f
u
tu
r
e
r
esear
c
h
s
h
o
u
ld
f
o
cu
s
o
n
d
ev
elo
p
in
g
r
ea
l
-
tim
e
Par
k
in
s
o
n
’
s
d
etec
tio
n
s
y
s
tem
s
,
in
teg
r
atin
g
th
e
m
o
d
el
in
to
m
o
b
ile
ap
p
licatio
n
s
o
r
telem
ed
icin
e
p
latf
o
r
m
s
.
Su
c
h
ad
v
an
ce
m
e
n
ts
co
u
ld
e
n
ab
le
r
e
m
o
te
p
atien
t
m
o
n
ito
r
in
g
,
ea
r
l
y
in
ter
v
en
tio
n
,
a
n
d
co
n
tin
u
o
u
s
d
is
ea
s
e
p
r
o
g
r
ess
io
n
tr
ac
k
in
g
,
en
h
a
n
cin
g
th
e
m
a
n
ag
em
en
t
o
f
PD
.
Fu
r
th
e
r
m
o
r
e
,
im
p
r
o
v
in
g
m
o
d
el
g
en
er
aliza
tio
n
an
d
r
o
b
u
s
tn
ess
th
r
o
u
g
h
f
ed
e
r
ated
lear
n
in
g
c
o
u
ld
allo
w
s
ec
u
r
e
c
o
llab
o
r
ati
o
n
ac
r
o
s
s
d
if
f
er
e
n
t
h
ea
lth
ca
r
e
in
s
titu
tio
n
s
wh
ile
p
r
eser
v
in
g
p
atien
t
p
r
iv
ac
y
.
Ov
er
all,
th
is
s
tu
d
y
d
em
o
n
s
tr
at
es
th
e
p
o
ten
tial
o
f
AI
-
d
r
i
v
en
,
n
on
-
in
v
asiv
e
PD
s
cr
ee
n
in
g
to
o
ls
,
p
av
in
g
th
e
way
f
o
r
f
u
tu
r
e
a
d
v
an
ce
m
e
n
ts
in
ML
-
b
ased
n
e
u
r
o
d
e
g
en
e
r
ativ
e
d
is
ea
s
e
d
iag
n
o
s
tics
.
B
y
ex
p
a
n
d
in
g
d
ataset
d
iv
er
s
ity
,
in
teg
r
atin
g
m
u
ltimo
d
al
f
ea
tu
r
es,
a
n
d
d
ep
lo
y
in
g
r
e
al
-
tim
e
d
etec
tio
n
s
y
s
tem
s
,
AI
-
b
ased
Par
k
in
s
o
n
’
s
d
etec
tio
n
ca
n
b
ec
o
m
e
a
m
o
r
e
r
eliab
le,
ac
ce
s
s
ib
le,
an
d
clin
ically
u
s
ef
u
l
to
o
l
f
o
r
ea
r
ly
d
iag
n
o
s
is
an
d
im
p
r
o
v
e
d
p
atien
t
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
P
r
ed
ictio
n
o
f
P
a
r
kin
s
o
n
's
d
is
ea
s
e
u
s
in
g
fea
tu
r
e
s
elec
tio
n
a
n
d
en
s
emb
le
lea
r
n
in
g
tech
n
iq
u
es
(
S
h
a
r
a
n
T.
D.
)
1743
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Sh
ar
an
T
.
D.
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Su
jata
J
o
s
h
i
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
is
n
o
t
ap
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
H
a
a
h
r
,
H
.
G
r
o
o
s,
a
n
d
D
.
S
ø
r
e
n
s
e
n
,
“
‘
S
t
r
i
v
i
n
g
f
o
r
n
o
r
mal
i
t
y
’
w
h
e
n
c
o
p
i
n
g
w
i
t
h
P
a
r
k
i
n
so
n
’
s
d
i
sea
se
i
n
e
v
e
r
y
d
a
y
l
i
f
e
:
A
met
a
s
y
n
t
h
e
s
i
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
N
u
rs
i
n
g
S
t
u
d
i
e
s
,
v
o
l
.
1
1
8
,
p
.
1
0
3
9
2
3
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
n
u
r
st
u
.
2
0
2
1
.
1
0
3
9
2
3
.
[
2
]
J.
M
o
i
n
i
,
A
.
L
o
g
a
l
b
o
,
a
n
d
J.
G
.
S
c
h
n
e
l
l
m
a
n
n
,
“
P
h
a
r
m
a
c
o
l
o
g
y
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
,
”
i
n
N
e
u
r
o
p
sy
c
h
o
p
h
a
rm
a
c
o
l
o
g
y
,
E
l
se
v
i
e
r
,
2
0
2
3
,
p
p
.
2
5
7
–
2
7
4
.
[
3
]
G
.
S
ö
d
e
r
b
o
m,
“
S
t
a
t
u
s
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s
o
f
c
l
i
n
i
c
a
l
t
r
i
a
l
s
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
sea
s
e
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
R
e
v
i
e
w
o
f
N
e
u
ro
b
i
o
l
o
g
y
,
v
o
l
.
1
5
4
,
El
s
e
v
i
e
r
,
2
0
2
0
,
p
p
.
1
5
3
–
1
8
8
.
[
4
]
S
.
Y
.
K
i
m
,
T.
M
.
Je
i
t
n
e
r
,
a
n
d
P
.
M
.
S
t
e
i
n
e
r
t
,
“
Tr
a
n
s
g
l
u
t
a
m
i
n
a
ses
i
n
d
i
se
a
se
,
”
N
e
u
r
o
c
h
e
m
i
st
r
y
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
4
0
,
n
o
.
1
,
p
p
.
8
5
–
1
0
3
,
Ja
n
.
2
0
0
2
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
1
9
7
-
0
1
8
6
(
0
1
)
0
0
0
6
4
-
X.
[
5
]
P
.
A
.
Le
W
i
t
t
a
n
d
K
.
R
.
C
h
a
u
d
h
u
r
i
,
“
U
n
m
e
t
n
e
e
d
s
i
n
P
a
r
k
i
n
s
o
n
d
i
se
a
se
:
M
o
t
o
r
a
n
d
n
o
n
-
mo
t
o
r
,
”
Pa
r
k
i
n
s
o
n
i
sm
a
n
d
Re
l
a
t
e
d
D
i
so
r
d
e
rs
,
v
o
l
.
8
0
,
p
p
.
S
7
–
S
1
2
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
r
k
r
e
l
d
i
s.
2
0
2
0
.
0
9
.
0
2
4
.
[
6
]
A
.
To
d
o
r
o
v
a
,
P
.
Je
n
n
e
r
,
a
n
d
K
.
R
a
y
C
h
a
u
d
h
u
r
i
,
“
N
o
n
-
m
o
t
o
r
p
a
r
k
i
n
so
n
’
s
:
I
n
t
e
g
r
a
l
t
o
m
o
t
o
r
p
a
r
k
i
n
s
o
n
’
s
,
y
e
t
o
f
t
e
n
n
e
g
l
e
c
t
e
d
,
”
Pra
c
t
i
c
a
l
N
e
u
r
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
5
,
p
p
.
3
1
0
–
3
2
2
,
A
p
r
.
2
0
1
4
,
d
o
i
:
1
0
.
1
1
3
6
/
p
r
a
c
t
n
e
u
r
o
l
-
2
0
1
3
-
0
0
0
7
4
1
.
[
7
]
L.
A
.
U
e
b
e
l
a
c
k
e
r
,
G
.
E
p
s
t
e
i
n
-
L
u
b
o
w
,
T.
Le
w
i
s,
M
.
K
.
B
r
o
u
g
h
t
o
n
,
a
n
d
J
.
H
.
F
r
i
e
d
m
a
n
,
“
A
s
u
r
v
e
y
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
p
a
t
i
e
n
t
s
:
M
o
s
t
b
o
t
h
e
r
s
o
me
s
y
mp
t
o
ms
a
n
d
c
o
p
i
n
g
p
r
e
f
e
r
e
n
c
e
s
,
”
J
o
u
r
n
a
l
o
f
Pa
r
k
i
n
s
o
n
’
s
D
i
s
e
a
s
e
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
7
1
7
–
7
2
3
,
2
0
1
4
,
d
o
i
:
1
0
.
3
2
3
3
/
JP
D
-
1
4
0
4
4
6
.
[
8
]
M
.
O
.
O
y
o
v
w
i
,
K
.
H
.
B
a
b
a
w
a
l
e
,
E
.
Jer
o
h
,
a
n
d
B
.
B
e
n
-
A
z
u
,
“
E
x
p
l
o
r
i
n
g
t
h
e
r
o
l
e
o
f
n
e
u
r
o
m
o
d
u
l
a
t
i
o
n
i
n
n
e
u
r
o
d
e
g
e
n
e
r
a
t
i
v
e
d
i
s
o
r
d
e
r
s:
I
n
si
g
h
t
s
f
r
o
m
A
l
z
h
e
i
m
e
r
’
s
a
n
d
P
a
r
k
i
n
so
n
’
s
d
i
sea
s
e
s,
”
B
ra
i
n
D
i
so
r
d
e
rs
,
v
o
l
.
1
7
,
p
.
1
0
0
1
8
7
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
s
c
b
.
2
0
2
5
.
1
0
0
1
8
7
.
[
9
]
X
.
Li
,
Z.
Y
.
D
o
n
g
,
M
.
D
o
n
g
,
a
n
d
L.
C
h
e
n
,
“
E
a
r
l
y
d
o
p
a
m
i
n
e
r
g
i
c
r
e
p
l
a
c
e
men
t
t
r
e
a
t
m
e
n
t
i
n
i
t
i
a
t
i
o
n
b
e
n
e
f
i
t
s
m
o
t
o
r
s
y
mp
t
o
ms
i
n
p
a
t
i
e
n
t
s wi
t
h
P
a
r
k
i
n
so
n
’
s
d
i
s
e
a
s
e
,
”
Fr
o
n
t
i
e
rs
i
n
H
u
m
a
n
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
1
8
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
h
u
m.
2
0
2
4
.
1
3
2
5
3
2
4
.
[
1
0
]
R
.
P
r
a
t
i
h
a
r
a
n
d
R
.
S
a
n
k
a
r
,
“
A
d
v
a
n
c
e
men
t
s
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
d
i
a
g
n
o
s
i
s:
a
c
o
m
p
r
e
h
e
n
si
v
e
s
u
r
v
e
y
o
n
b
i
o
m
a
r
k
e
r
i
n
t
e
g
r
a
t
i
o
n
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
1
3
,
n
o
.
1
1
,
p
.
2
9
3
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
e
r
s
1
3
1
1
0
2
9
3
.
[
1
1
]
A
.
J.
Es
p
a
y
e
t
a
l
.
,
“
T
e
c
h
n
o
l
o
g
y
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
:
C
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s
,
”
M
o
v
e
m
e
n
t
D
i
s
o
r
d
e
rs
,
v
o
l
.
3
1
,
n
o
.
9
,
p
p
.
1
2
7
2
–
1
2
8
2
,
S
e
p
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
0
2
/
md
s.
2
6
6
4
2
.
[
1
2
]
L.
S
i
g
c
h
a
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
n
d
w
e
a
r
a
b
l
e
se
n
so
r
s
f
o
r
t
h
e
d
i
a
g
n
o
s
i
s
a
n
d
m
o
n
i
t
o
r
i
n
g
o
f
P
a
r
k
i
n
so
n
’
s
d
i
sea
se:
A
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
2
9
,
p
.
1
2
0
5
4
1
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
0
5
4
1
.
[
1
3
]
S
.
M
o
r
a
d
i
,
L.
T
a
p
a
k
,
a
n
d
S
.
A
f
s
h
a
r
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
n
o
v
e
l
n
o
n
i
n
v
a
s
i
v
e
d
i
a
g
n
o
st
i
c
s
b
i
o
mar
k
e
r
s
i
n
t
h
e
p
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
s
a
nd
i
mp
r
o
v
i
n
g
t
h
e
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
B
i
o
Me
d
R
e
se
a
rc
h
I
n
t
e
rn
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
/
5
0
0
9
8
9
2
.
[
1
4
]
A
.
R
a
t
n
a
k
a
r
,
“
E
v
a
l
u
a
t
i
n
g
s
p
e
e
c
h
a
n
a
l
y
si
s
t
e
c
h
n
i
q
u
e
s fo
r
P
a
r
k
i
n
s
o
n
s
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
:
a
c
o
m
p
a
r
i
so
n
o
f
mac
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
a
l
g
o
r
i
t
h
ms,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
Re
s
e
a
rc
h
,
v
o
l
.
1
2
,
n
o
.
0
5
,
p
p
.
1
1
1
8
–
1
1
3
7
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
2
1
4
7
4
/
i
j
a
r
0
1
/
1
8
8
2
7
.
[
1
5
]
K
.
P
.
S
w
a
i
n
e
t
a
l
.
,
“
T
o
w
a
r
d
s
e
a
r
l
y
i
n
t
e
r
v
e
n
t
i
o
n
:
d
e
t
e
c
t
i
n
g
P
a
r
k
i
n
so
n
’
s d
i
s
e
a
se
t
h
r
o
u
g
h
v
o
i
c
e
a
n
a
l
y
s
i
s
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
T
h
e
O
p
e
n
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
J
o
u
r
n
a
l
,
v
o
l
.
1
8
,
n
o
.
1
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
2
1
7
4
/
0
1
1
8
7
4
1
2
0
7
2
9
4
0
5
6
2
4
0
3
2
2
0
7
5
6
0
2
.
[
1
6
]
J
.
R
u
s
z
,
P
.
K
r
a
c
k
,
a
n
d
E.
Tr
i
p
o
l
i
t
i
,
“
F
r
o
m
p
r
o
d
r
o
ma
l
st
a
g
e
s
t
o
c
l
i
n
i
c
a
l
t
r
i
a
l
s
:
T
h
e
p
r
o
m
i
se
o
f
d
i
g
i
t
a
l
sp
e
e
c
h
b
i
o
mar
k
e
r
s
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
,
”
N
e
u
r
o
sc
i
e
n
c
e
a
n
d
B
i
o
b
e
h
a
v
i
o
r
a
l
Re
v
i
e
w
s
,
v
o
l
.
1
6
7
,
p
.
1
0
5
9
2
2
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
b
i
o
r
e
v
.
2
0
2
4
.
1
0
5
9
2
2
.
[
17
]
A
.
F
a
v
a
r
o
e
t
a
l
.
,
“
M
u
l
t
i
l
i
n
g
u
a
l
e
v
a
l
u
a
t
i
o
n
o
f
i
n
t
e
r
p
r
e
t
a
b
l
e
b
i
o
mar
k
e
r
s
t
o
r
e
p
r
e
s
e
n
t
l
a
n
g
u
a
g
e
a
n
d
sp
e
e
c
h
p
a
t
t
e
r
n
s
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
,
”
Fr
o
n
t
i
e
rs i
n
N
e
u
r
o
l
o
g
y
,
v
o
l
.
1
4
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
e
u
r
.
2
0
2
3
.
1
1
4
2
6
4
2
.
[
1
8
]
Q
.
C
.
N
g
o
,
M
.
A
.
M
o
t
i
n
,
N
.
D
.
P
a
h
,
P
.
D
r
o
t
á
r
,
P
.
K
e
m
p
st
e
r
,
a
n
d
D
.
K
u
mar,
“
C
o
mp
u
t
e
r
i
z
e
d
a
n
a
l
y
s
i
s
o
f
s
p
e
e
c
h
a
n
d
v
o
i
c
e
f
o
r
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
:
A
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pro
g
ra
m
s
i
n
Bi
o
m
e
d
i
c
i
n
e
,
v
o
l
.
2
2
6
,
p
.
1
0
7
1
3
3
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
mp
b
.
2
0
2
2
.
1
0
7
1
3
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
39
,
No
.
3
,
Sep
tem
b
er
20
25
:
1
7
3
6
-
1
7
4
4
1744
[
1
9
]
M
.
A
.
I
sl
a
m,
M
.
Z.
H
a
sa
n
M
a
j
u
md
e
r
,
M
.
A
.
H
u
ss
e
i
n
,
K
.
M
.
H
o
ssa
i
n
,
a
n
d
M
.
S
.
M
i
a
h
,
“
A
r
e
v
i
e
w
o
f
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
a
l
g
o
r
i
t
h
ms
f
o
r
P
a
r
k
i
n
s
o
n
’
s
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
u
si
n
g
h
a
n
d
w
r
i
t
i
n
g
a
n
d
v
o
i
c
e
d
a
t
a
se
t
s,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
3
,
p
.
e
2
5
4
6
9
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
2
5
4
6
9
.
[
2
0
]
W
.
W
a
n
g
,
J.
Le
e
,
F
.
H
a
r
r
o
u
,
a
n
d
Y
.
S
u
n
,
“
Ea
r
l
y
d
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
4
7
6
3
5
–
1
4
7
6
4
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
1
6
0
6
2
.
[
2
1
]
C
.
D
.
P
r
i
t
h
v
i
A
c
h
a
r
,
M
.
P
.
A
n
v
e
s
h
,
A
.
K
o
d
i
p
a
l
l
i
,
a
n
d
T.
R
a
o
,
“
E
x
p
l
o
r
i
n
g
c
o
mp
u
t
a
t
i
o
n
a
l
m
o
d
e
l
s
f
o
r
P
a
r
k
i
n
s
o
n
’
s d
i
sea
s
e
d
i
a
g
n
o
s
i
s
:
u
n
v
e
i
l
i
n
g
i
n
s
i
g
h
t
s wit
h
LI
M
E
a
n
d
S
H
A
P
e
x
p
l
a
i
n
a
b
i
l
i
t
y
t
e
c
h
n
i
q
u
e
s,
”
i
n
2
0
2
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s,
I
C
K
E
C
S
2
0
2
4
,
A
p
r
.
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
K
EC
S
6
1
4
9
2
.
2
0
2
4
.
1
0
6
1
6
8
3
1
.
[
2
2
]
“
P
a
r
k
i
n
s
o
n
’
s
d
i
sea
s
e
c
l
a
ssi
f
i
c
a
t
i
o
n
-
U
C
I
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
r
e
p
o
s
i
t
o
r
y
.
”
h
t
t
p
s
:
/
/
a
r
c
h
i
v
e
.
i
c
s.
u
c
i
.
e
d
u
/
d
a
t
a
s
e
t
/
4
7
0
/
p
a
r
k
i
n
so
n
+
s+
d
i
s
e
a
se
+
c
l
a
ss
i
f
i
c
a
t
i
o
n
(
a
c
c
e
ss
e
d
A
p
r
.
0
2
,
2
0
2
5
)
.
[
2
3
]
A
.
G
o
v
i
n
d
u
a
n
d
S
.
P
a
l
w
e
,
“
E
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
,
v
o
l
.
2
1
8
,
p
p
.
2
4
9
–
2
6
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.2
0
2
3
.
0
1
.
0
0
7
.
[2
4
]
M
.
B
.
M
a
k
a
r
i
o
u
s
e
t
a
l
.
,
“
M
u
l
t
i
-
m
o
d
a
l
i
t
y
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
p
r
e
d
i
c
t
i
n
g
P
a
r
k
i
n
so
n
’
s d
i
s
e
a
s
e
,
”
n
p
j
Pa
r
k
i
n
s
o
n
’
s
D
i
se
a
se
,
v
o
l
.
8
,
n
o
.
1
,
p
.
3
5
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
3
1
-
0
2
2
-
0
0
2
8
8
-
w.
[
2
5
]
J.
Zh
a
n
g
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
met
h
o
d
s,
”
B
i
o
m
o
l
e
c
u
l
e
s
,
v
o
l
.
1
3
,
n
o
.
1
2
,
p
.
1
7
6
1
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
m1
3
1
2
1
7
6
1
.
[
2
6
]
R
.
A
l
s
h
a
mm
r
i
,
G
.
A
l
h
a
r
b
i
,
E
.
A
l
h
a
r
b
i
,
a
n
d
I
.
A
l
mu
b
a
r
k
,
“
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
t
o
i
d
e
n
t
i
f
y
P
a
r
k
i
n
so
n
’
s
d
i
s
e
a
se
u
s
i
n
g
v
o
i
c
e
si
g
n
a
l
f
e
a
t
u
r
e
s,
”
Fr
o
n
t
i
e
rs
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
6
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
r
a
i
.
2
0
2
3
.
1
0
8
4
0
0
1
.
[
2
7
]
F
.
S
a
e
e
d
e
t
a
l
.
,
“
E
n
h
a
n
c
i
n
g
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
m
e
t
h
o
d
s,”
C
o
m
p
u
t
e
rs,
Ma
t
e
r
i
a
l
s
a
n
d
C
o
n
t
i
n
u
a
,
v
o
l
.
7
1
,
n
o
.
2
,
p
p
.
5
6
3
9
–
5
6
5
7
,
2
0
2
2
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc.
2
0
2
2
.
0
2
3
1
2
4
.
[
2
8
]
N
.
N
a
h
a
r
,
F
.
A
r
a
,
M
.
A
.
I
.
N
e
l
o
y
,
A
.
B
i
sw
a
s,
M
.
S
.
H
o
ss
a
i
n
,
a
n
d
K
.
A
n
d
e
r
ss
o
n
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
b
a
s
e
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
o
i
mp
r
o
v
e
p
r
e
d
i
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
d
i
se
a
se,
”
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
ser
i
e
s
L
e
c
t
u
r
e
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
1
2
9
6
0
LN
A
I
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
sh
i
n
g
,
2
0
2
1
,
p
p
.
4
9
6
–
5
0
8
.
[
2
9
]
L.
A
l
i
,
C
.
C
h
a
k
r
a
b
o
r
t
y
,
Z.
H
e
,
W
.
C
a
o
,
Y
.
I
mr
a
n
a
,
a
n
d
J.
J
.
P
.
C
.
R
o
d
r
i
g
u
e
s,
“
A
n
o
v
e
l
s
a
mp
l
e
a
n
d
f
e
a
t
u
r
e
d
e
p
e
n
d
e
n
t
e
n
s
e
mb
l
e
a
p
p
r
o
a
c
h
f
o
r
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
d
e
t
e
c
t
i
o
n
,
”
N
e
u
ra
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
5
,
n
o
.
2
2
,
p
p
.
1
5
9
9
7
–
1
6
0
1
0
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
022
-
0
7
0
4
6
-
2.
[
3
0
]
B
.
K
.
V
a
r
g
h
e
se,
D
.
G
.
B
.
A
ma
l
i
,
a
n
d
K
.
S
.
U
.
D
e
v
i
,
“
P
r
e
d
i
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
o
n
sp
e
e
c
h
d
a
t
a
se
t
,
”
Re
se
a
rc
h
J
o
u
rn
a
l
o
f
P
h
a
rm
a
c
y
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
1
–
5
,
2
0
1
9
,
d
o
i
:
1
0
.
5
9
5
8
/
0
9
7
4
-
3
6
0
X
.
2
0
1
9
.
0
0
1
1
4
.
8
.
[
3
1
]
S
.
S
r
i
n
i
v
a
sa
n
,
P
.
R
a
ma
d
a
ss,
S
.
K
.
M
a
t
h
i
v
a
n
a
n
,
K
.
P
.
S
e
l
v
a
m,
B
.
D
.
S
h
i
v
a
h
a
r
e
,
a
n
d
M
.
A
.
S
h
a
h
,
“
D
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
d
i
s
e
a
s
e
u
si
n
g
m
u
l
t
i
c
l
a
ss
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
4
,
n
o
.
1
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
024
-
6
4
0
0
4
-
9.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
h
a
r
a
n
T
.
D
.
is
a
n
u
n
d
e
r
g
ra
d
u
a
te
stu
d
e
n
t
a
t
Nitt
e
M
e
e
n
a
k
sh
i
In
sti
tu
te
o
f
Tec
h
n
o
l
o
g
y
,
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
ri
n
g
(B.
E.
)
in
C
o
m
p
u
ter
S
c
ien
c
e
.
His
a
c
a
d
e
m
ic
in
tere
sts
li
e
in
th
e
d
o
m
a
in
s
o
f
m
a
c
h
i
n
e
lea
rn
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
c
o
m
p
u
tati
o
n
a
l
h
e
a
lt
h
c
a
re
.
P
a
ss
io
n
a
te
a
b
o
u
t
le
v
e
ra
g
in
g
d
a
ta
-
d
riv
e
n
a
p
p
ro
a
c
h
e
s
fo
r
m
e
d
ica
l
d
iag
n
o
stics
,
h
e
is
p
a
rti
c
u
larly
f
o
c
u
se
d
o
n
p
re
d
ictiv
e
m
o
d
e
li
n
g
a
n
d
fe
a
tu
re
se
lec
ti
o
n
tec
h
n
i
q
u
e
s
to
e
n
h
a
n
c
e
d
ise
a
se
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
rn
2
8
2
@g
m
a
il
.
c
o
m
.
Dr
.
S
u
ja
t
a
J
o
sh
i
is
c
u
rre
n
t
ly
wo
r
k
i
n
g
a
s
a
P
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
Nit
te
M
e
e
n
a
k
sh
i
In
st
it
u
te
o
f
Tec
h
n
o
lo
g
y
,
Ba
n
g
a
lo
re
,
In
d
ia.
S
h
e
h
a
s
c
o
m
p
lete
d
a
Ph
.
D
.
fro
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Ba
n
g
a
lo
re
.
S
h
e
h
a
s
a
u
th
o
re
d
a
n
d
c
o
-
a
u
th
o
re
d
se
v
e
ra
l
jo
u
rn
a
l
a
n
d
c
o
n
fe
re
n
c
e
p
a
p
e
rs
a
n
d
b
o
o
k
c
h
a
p
ters
.
S
h
e
h
a
s
g
u
id
e
d
m
a
n
y
stu
d
e
n
ts
f
o
r
th
e
ir
p
ro
jec
t
wo
r
k
a
n
d
stu
d
e
n
t
re
se
a
rc
h
p
u
b
li
c
a
ti
o
n
s.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
p
re
d
ict
iv
e
m
o
d
e
ll
i
n
g
,
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
p
a
rti
c
u
larly
in
t
h
e
m
e
d
ica
l
d
o
m
a
in
.
S
h
e
h
a
s
b
e
e
n
a
m
e
m
b
e
r
o
f
th
e
o
rg
a
n
izin
g
c
o
m
m
it
tee
fo
r
m
a
n
y
c
o
n
fe
re
n
c
e
s
a
n
d
a
lso
on
th
e
re
v
iew
c
o
m
m
it
tee
o
f
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
rn
a
ls.
Sh
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s
u
jata
.
j
o
sh
i@
n
m
it
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.