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.
37
,
No
.
2
,
Feb
r
u
ar
y
20
25
,
p
p
.
1
1
40
~1
14
9
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
37.
i
2
.
p
p
1
1
40
-
1
14
9
1140
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Im
pro
v
ed Bi
-
G
R
U f
o
r
p
a
rki
nso
n
’
s
disea
se sev
erity a
na
ly
sis
M
a
la
t
hi Ar
un
a
cha
la
m
1
,
Ra
m
a
la
k
s
hm
i R
a
ma
r
2
,
Va
ibh
a
v
G
a
nd
hi
3
,
B
hu
v
a
nes
h Ana
n
t
ha
n
4
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
a
n
d
S
o
f
t
w
a
r
e
En
g
i
n
e
e
r
i
n
g
,
A
n
a
n
d
I
n
st
i
t
u
t
e
o
f
H
i
g
h
e
r
T
e
c
h
n
o
l
o
g
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
K
a
l
a
sa
l
i
n
g
a
m
A
c
a
d
e
m
y
o
f
R
e
se
a
r
c
h
a
n
d
E
d
u
c
a
t
i
o
n
,
K
r
i
s
h
n
a
n
k
o
i
l
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
D
e
si
g
n
E
n
g
i
n
e
e
r
i
n
g
a
n
d
M
a
t
h
e
m
a
t
i
c
s
,
M
i
d
d
l
e
s
e
x
U
n
i
v
e
r
si
t
y
,
Lo
n
d
o
n
,
U
n
i
t
e
d
K
i
n
g
d
o
m
4
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
P
S
N
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
T
i
r
u
n
e
l
v
e
l
i
,
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
Ap
r
22
,
2
0
2
4
R
ev
is
ed
Sep
21
,
2
0
2
4
Acc
ep
ted
Sep
30
,
2
0
2
4
P
a
rk
in
so
n
’
s
d
ise
a
se
(P
D)
is
a
c
o
m
m
o
n
n
e
u
ro
-
d
e
g
e
n
e
ra
ti
v
e
issu
e
,
e
v
a
lu
a
ted
v
ia
th
e
c
o
n
ti
n
u
o
u
s d
e
terio
ra
ti
o
n
o
f
m
o
to
r
f
u
n
c
ti
o
n
s o
v
e
r
ti
m
e
.
T
h
is co
n
d
i
ti
o
n
lea
d
s
to
a
g
ra
d
u
a
l
d
e
c
li
n
e
in
m
o
v
e
m
e
n
t
c
a
p
a
b
il
it
ies
.
F
o
r
d
iag
n
o
sin
g
c
li
n
ica
l
se
t
o
f
P
Ds
,
m
e
d
ica
l
e
x
p
e
rts
u
ti
li
z
e
m
e
d
ica
l
o
b
se
rv
a
ti
o
n
s.
Th
e
se
o
b
se
rv
a
ti
o
n
s
a
re
h
ig
h
ly
b
a
se
d
o
n
th
e
e
x
p
e
rt
’
s
e
x
p
e
rien
c
e
a
n
d
c
a
n
v
a
ry
a
m
o
n
g
c
li
n
icia
n
s
d
u
e
t
o
it
s
s
u
b
jec
ti
v
e
n
a
tu
re
,
lea
d
in
g
t
o
d
if
fe
re
n
c
e
s
in
e
v
a
lu
a
ti
o
n
.
Th
e
g
a
it
p
a
tt
e
rn
s
o
f
i
n
d
i
v
id
u
a
ls
with
P
D
t
y
p
ica
ll
y
e
x
h
i
b
it
d
isti
n
c
ti
o
n
s
fro
m
th
o
se
o
f
a
d
u
lt
s.
Ev
a
lu
a
t
i
n
g
t
h
e
se
g
a
it
m
a
lfo
rm
a
ti
o
n
s
n
o
t
o
n
l
y
a
id
s
in
d
iag
n
o
sin
g
P
D
b
u
t
c
a
n
a
lso
e
n
a
b
le
th
e
c
a
teg
o
r
iza
ti
o
n
o
f
se
v
e
rit
y
sta
g
e
s
with
re
sp
e
c
t
to
sy
m
p
to
m
s
o
f
m
o
t
o
r
m
o
v
e
m
e
n
t.
T
h
e
re
fo
re
,
th
is
p
a
p
e
r
in
tr
o
d
u
c
e
s
a
c
las
sifica
ti
o
n
o
f
g
a
i
t
m
o
d
e
l
b
a
se
d
o
n
th
e
o
p
ti
m
ize
d
d
e
e
p
lea
rn
in
g
(DL)
m
o
d
e
l
b
id
irec
ti
o
n
a
l
g
a
ted
re
c
u
rr
e
n
t
u
n
it
-
a
rti
ficia
l
h
u
m
m
in
g
b
ird
o
p
ti
m
ize
r
(BI
-
G
RU
-
A
HO
).
Th
e
trai
n
in
g
a
n
d
tes
ti
n
g
in
v
o
l
v
e
d
th
e
se
q
u
e
n
ti
a
l
se
g
m
e
n
tatio
n
o
f
t
h
e
rig
h
t
a
n
d
l
e
ft
in
sta
n
c
e
s
fro
m
th
e
si
g
n
a
ls
o
f
v
e
rti
c
a
l
g
ro
u
n
d
re
a
c
ti
o
n
f
o
rc
e
(VG
RF
)
b
a
se
d
o
n
t
h
e
id
e
n
t
ifi
e
d
g
a
it
c
y
c
le.
Th
e
o
u
tco
m
e
s
o
f
th
e
p
ro
p
o
se
d
BI
-
G
RU
-
AH
O
e
x
h
ib
it
s
re
li
a
b
le
a
n
d
a
c
c
u
ra
te
a
ss
e
ss
m
e
n
t
o
f
P
D
a
n
d
a
c
h
iev
e
d
b
e
tt
e
r
a
c
c
u
ra
c
y
o
f
9
8
.
7
%
.
Th
e
p
r
o
p
o
se
d
m
o
d
e
l
is
train
e
d
a
n
d
tes
ted
sa
ti
sf
a
c
to
ril
y
;
h
e
n
c
e
it
c
a
n
b
e
imp
lem
e
n
ted
i
n
a
re
a
l
-
ti
m
e
e
n
v
iro
n
m
e
n
t
b
y
i
n
teg
ra
ti
n
g
t
h
e
m
o
d
e
l
i
n
to
a
s
o
ftwa
re
a
p
p
li
c
a
ti
o
n
o
r
sy
ste
m
c
a
p
a
b
le o
f
re
c
e
iv
in
g
re
a
l
-
ti
m
e
d
a
ta fro
m
PD
p
a
ti
e
n
ts.
K
ey
w
o
r
d
s
:
Gait
p
atter
n
s
Op
tim
ized
d
ee
p
lear
n
in
g
Par
k
in
s
o
n
’
s
d
is
ea
s
e
Ver
tical
g
r
o
u
n
d
r
ea
ctio
n
f
o
r
ce
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
:
Ma
lath
i A
r
u
n
ac
h
alam
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
a
n
d
So
f
twar
e
E
n
g
in
ee
r
in
g
,
An
an
d
I
n
s
titu
te
o
f
Hig
h
er
T
ec
h
n
o
lo
g
y
6
0
3
1
0
3
C
h
en
n
ai,
T
am
il Na
d
u
,
I
n
d
ia
E
m
ail: m
alath
iar
u
n
ac
h
alam
8
3
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Gait
an
aly
s
is
p
lay
s
a
m
ajo
r
r
o
le
in
d
iag
n
o
s
in
g
v
ar
i
o
u
s
n
eu
r
o
d
eg
en
er
ati
v
e
co
n
d
itio
n
s
s
u
ch
as
p
ar
k
in
s
o
n
’
s
d
is
ea
s
e
(
PD)
,
d
em
en
tia
an
d
alzh
eim
er
.
Gait
an
aly
s
is
o
f
f
er
s
es
s
en
tial
i
n
s
ig
h
ts
in
to
jo
in
t
m
o
v
em
en
t,
s
p
atio
-
tem
p
o
r
al
f
e
atu
r
es,
an
d
th
e
tr
ea
tm
en
t
p
r
o
c
ess
[
1]
.
Of
r
ec
e
n
t
,
t
h
e
g
ait
p
att
er
n
s
h
av
e
p
r
o
v
e
d
to
b
e
v
alu
ab
le
m
eth
o
d
in
d
iag
n
o
s
in
g
PD.
T
h
er
e
is
s
ig
n
if
ican
t
ad
v
an
ce
m
e
n
t
in
g
ait
an
aly
s
is
m
eth
o
d
o
lo
g
ies,
d
r
iv
en
b
y
th
e
in
tr
o
d
u
ctio
n
o
f
s
o
p
h
is
ticated
an
aly
s
is
o
f
m
o
tio
n
m
o
d
els
[
2
]
.
Var
io
u
s
tec
h
n
iq
u
es
h
a
v
e
b
ee
n
em
p
lo
y
ed
f
o
r
th
e
g
ait
p
r
o
ce
s
s
in
clu
d
in
g
th
e
u
s
e
o
f
ca
m
er
a
s
f
o
r
ca
p
tu
r
in
g
m
o
tio
n
p
at
h
s
.
T
h
ese
in
n
o
v
atio
n
s
c
o
l
l
e
c
ti
v
e
l
y
c
o
n
t
r
i
b
u
t
e
t
o
a
c
o
m
p
r
e
h
e
n
s
i
v
e
u
n
d
e
r
s
t
a
n
d
i
n
g
o
f
h
u
m
a
n
g
a
i
t
w
i
t
h
o
u
t
d
u
p
l
i
ca
t
i
n
g
e
x
i
s
ti
n
g
c
o
n
t
e
n
t
[
3
]
.
C
u
r
r
en
tly
,
m
e
d
ical
ev
alu
atio
n
ap
p
r
o
ac
h
es
f
o
r
PD
p
atien
ts
c
o
n
tin
u
e
t
o
d
e
p
en
d
o
n
q
u
esti
o
n
n
air
es
an
d
s
elf
-
d
escr
ip
tio
n
s
lik
e
f
r
ee
zin
g
o
f
g
ait
q
u
esti
o
n
n
ai
r
e
(
FOG)
an
d
ass
ess
m
en
ts
o
f
d
aily
liv
in
g
(
ADL
)
[
4
]
.
E
x
p
er
ts
f
r
eq
u
e
n
tly
ass
ess
PD
s
ev
er
ity
in
s
p
ec
if
ic
cr
iter
ia
b
ased
o
n
t
h
e
p
atien
t
’
s
p
e
r
f
o
r
m
an
ce
i
n
q
u
esti
o
n
s
o
u
tlin
ed
i
n
q
u
esti
o
n
n
air
es.
Ho
wev
er
,
th
i
s
p
r
o
ce
s
s
tak
es
m
o
r
e
tim
e
an
d
p
r
o
v
id
es
in
ac
cu
r
ate
o
u
t
co
m
es,
lim
itin
g
its
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:
2
5
0
2
-
4
7
52
I
mp
r
o
ve
d
B
i
-
GR
U
fo
r
p
a
r
kin
s
o
n
’
s
d
is
ea
s
e
s
ev
erit
y
a
n
a
lysi
s
(
Ma
la
th
i A
r
u
n
a
c
h
a
la
m)
1141
ef
f
ec
tiv
en
ess
in
th
e
tr
ea
tm
en
t
an
d
s
cr
ee
n
in
g
o
f
PD.
Gait
p
r
o
ce
s
s
al
s
o
p
o
s
es
s
ev
er
al
ch
alle
n
g
es,
s
u
ch
as
h
ig
h
d
im
en
s
io
n
al
d
ata,
n
o
n
-
lin
ea
r
d
ep
en
d
e
n
cies a
n
d
in
tr
icate
co
r
r
elatio
n
s
am
o
n
g
s
p
atio
-
tem
p
o
r
al
f
ea
tu
r
es [
5
]
.
Ad
d
r
ess
in
g
th
e
h
ig
h
ly
n
o
n
-
lin
ea
r
n
atu
r
e
o
f
g
ait
p
atter
n
s
r
eq
u
ir
es
s
p
ec
ialized
an
d
ef
f
icien
t
ap
p
r
o
ac
h
es
f
o
r
f
in
d
in
g
th
e
s
ev
er
ity
s
tag
e
o
f
PD.
I
n
r
ec
en
t d
e
v
elo
p
m
en
ts
,
t
h
e
m
ac
h
in
e
lea
r
n
in
g
(
ML
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
m
o
d
els
h
av
e
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t
p
o
s
s
ib
ilit
ies
in
a
id
in
g
m
ed
ical
ex
p
er
t
s
[
6
]
.
T
h
ese
m
o
d
els
d
iag
n
o
s
e
th
e
o
cc
u
r
r
en
ce
o
f
P
D
th
r
o
u
g
h
g
ait
f
lex
ib
ilit
y
an
a
ly
s
is
an
d
class
if
y
th
e
s
tag
es
o
f
PD
b
ased
o
n
th
e
m
o
to
r
s
y
m
p
to
m
s
ex
h
ib
ite
d
b
y
in
d
iv
id
u
als.
L
ev
er
ag
in
g
DL
m
o
d
els
in
th
e
g
ait
p
r
o
ce
s
s
ca
n
m
ar
k
ed
ly
r
e
d
u
ce
th
e
tim
e
ass
o
ciate
d
with
th
e
p
r
o
ce
s
s
in
g
o
f
d
ata,
as
th
ese
alg
o
r
ith
m
s
p
o
s
s
ess
th
e
ab
ilit
y
to
id
e
n
tify
h
id
d
en
f
ea
tu
r
es
an
d
m
an
ag
e
h
u
g
e
d
atab
ases
[
7
]
.
T
h
is
,
in
tu
r
n
,
ca
n
s
ig
n
if
ican
tly
en
h
an
ce
th
e
tr
ea
tm
en
t
q
u
ality
r
ec
eiv
ed
b
y
p
atien
ts
an
d
ef
f
icien
tly
en
h
an
ce
clin
ical
r
e
s
u
lts
.
E
v
en
th
o
u
g
h
th
e
g
ait
p
r
o
ce
s
s
h
as
b
ee
n
ex
ten
s
iv
ely
an
aly
ze
d
f
o
r
PD
d
iag
n
o
s
is
,
a
m
o
r
e
th
o
r
o
u
g
h
in
v
esti
g
atio
n
o
f
h
i
d
d
en
g
ait
b
i
o
m
ar
k
er
s
is
n
ec
ess
ar
y
f
o
r
en
h
an
ce
d
id
en
tific
atio
n
a
n
d
q
u
an
titativ
e
e
v
alu
atio
n
o
f
s
y
m
p
to
m
s
o
f
PD.
Mo
r
eo
v
er
,
DL
m
o
d
els
h
av
e
t
h
e
p
o
ten
tial
to
s
u
r
p
ass
ML
m
o
d
el
s
wh
en
th
er
e
is
a
s
u
f
f
icien
t
am
o
u
n
t
o
f
d
ata,
a
f
ac
t
o
r
th
at
m
a
y
v
ar
y
b
ased
o
n
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
ad
o
p
ted
i
n
d
icatio
n
m
o
d
els.
So
m
e
o
f
th
e
DL
m
o
d
els
lik
e
r
ec
u
r
r
e
n
t
n
e
u
r
al
n
etwo
r
k
(
R
NN)
,
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
an
d
lo
n
g
s
h
o
r
t
ter
m
m
em
o
r
y
(
L
STM
)
.
T
h
is
p
ap
er
p
r
esen
ts
an
o
p
tim
ized
DL
m
o
d
el
to
m
o
d
el
t
h
e
g
ait
an
aly
s
is
o
f
PD
p
atien
ts
u
s
in
g
th
e
wea
r
a
b
le
s
en
s
o
r
d
ata.
Su
b
s
eq
u
en
tly
,
g
ait
cla
s
s
if
icatio
n
is
ac
h
iev
ed
u
s
i
n
g
g
ated
r
ec
u
r
r
e
n
t
u
n
it
-
ar
tific
ial
h
u
m
m
in
g
b
ir
d
o
p
tim
izer
(
BI
-
GR
U
-
AHO
)
an
d
VGRF
.
Sectio
n
2
p
r
esen
ts
r
e
ce
n
t
wo
r
k
s
o
f
liter
atu
r
e
b
ased
o
n
d
if
f
e
r
en
t
PD
m
o
d
els.
Sectio
n
3
p
r
esen
ts
th
e
PD m
o
d
el
an
d
s
ec
tio
n
4
d
is
cu
s
s
es th
e
an
aly
s
is
o
f
r
esu
lts
.
I
n
s
ec
tio
n
5
co
n
clu
d
es th
e
p
a
p
er
.
2.
RE
L
AT
E
D
WO
RK
S
Sig
ch
a
et
a
l.
[
8
]
d
e
v
elo
p
e
d
a
m
o
d
el
b
ased
o
n
th
e
R
NN
an
d
tr
i
-
ax
ial
ac
ce
ler
o
m
eter
f
o
r
e
n
h
an
cin
g
th
e
d
etec
tio
n
o
f
FOG.
T
h
e
ex
p
er
i
m
en
tatio
n
was d
em
o
n
s
tr
ated
b
y
th
e
cr
o
s
s
-
v
alid
atio
n
.
C
am
p
s
et
a
l.
[
9
]
d
e
v
elo
p
ed
au
to
m
ated
d
etec
tio
n
FOG)
u
tili
zin
g
DL
m
o
d
el
C
NN
a
n
d
d
ata
f
r
o
m
wea
r
ab
le
s
en
s
o
r
s
.
T
h
is
ap
p
r
o
ac
h
d
em
o
n
s
tr
ates su
p
er
io
r
p
er
f
o
r
m
an
ce
co
m
p
a
r
ed
to
e
x
is
tin
g
m
et
h
o
d
s
,
ac
h
iev
i
n
g
an
ac
cu
r
ac
y
le
v
el
o
f
9
0
%.
Vid
y
a
an
d
Sas
ik
u
m
ar
[
1
0
]
d
ev
elo
p
ed
a
m
eth
o
d
f
o
r
p
r
ed
i
ctin
g
PD
th
r
o
u
g
h
a
C
NN
with
L
STM
.
T
h
e
s
ig
n
als
o
f
VGRF
wer
e
ex
tr
ac
ted
b
y
th
e
E
MD
(
em
p
ir
i
ca
l
m
o
d
e
d
ec
o
m
p
o
s
itio
n
)
t
o
o
b
tain
th
e
s
ig
n
i
f
ican
t
in
tr
in
s
ic
f
ea
tu
r
es.
Acc
u
r
ac
y
ac
h
iev
ed
was
9
8
.
3
%
f
o
r
m
u
lti
-
class
if
icatio
n
.
C
NN
with
lo
ca
lly
weig
h
ted
r
an
d
o
m
f
o
r
es
t
(
L
W
R
F
)
was
in
tr
o
d
u
ce
d
b
y
Aşu
r
o
ğ
lu
an
d
Oğ
u
l
[
1
1
]
f
o
r
th
e
ca
teg
o
r
izatio
n
o
f
p
ar
k
in
s
o
n
’
s
d
is
ea
s
e.
T
h
e
L
W
R
F wa
s
u
tili
ze
d
to
id
en
tify
PD a
n
d
e
x
tr
ac
t lo
ca
l c
h
ar
ac
ter
is
tics
.
Xia
et
a
l.
[
1
2
]
p
r
esen
ted
C
NN
m
o
d
el
t
o
d
etec
t
FOG
in
PD
p
atien
ts
;
h
er
e,
th
e
d
is
cr
im
in
a
tiv
e
f
ea
tu
r
es
wer
e
an
aly
ze
d
u
s
in
g
m
u
lti
-
1
D
d
ata.
C
o
m
p
ar
ativ
e
an
aly
s
is
was
p
er
f
o
r
m
e
d
f
o
r
two
f
ea
tu
r
e
f
u
s
ed
m
o
d
els
lik
e
p
atien
t
d
ep
en
d
en
t
an
d
in
d
e
p
e
n
d
en
t
s
ettin
g
s
.
Fer
r
eir
a
et
a
l.
[
1
3
]
p
r
esen
ted
ML
ap
p
r
o
ac
h
e
s
to
d
etec
t
PD
with
r
esp
ec
t
to
s
p
atio
-
tem
p
o
r
al
f
ea
t
u
r
es.
Her
e,
th
e
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
v
alu
es
ac
h
iev
ed
o
f
8
4
%
an
d
9
2
.
3
%
r
esp
ec
tiv
ely
.
B
o
r
zì
et
a
l.
[
1
4
]
p
r
esen
ted
r
ea
l
tim
e
id
en
tific
atio
n
o
f
FOG
in
PD
u
s
in
g
s
en
s
o
r
a
n
d
m
u
lti
h
ea
d
C
NN.
T
h
e
p
er
f
o
r
m
an
ce
was
ca
r
r
ied
o
u
t
b
y
v
ar
y
in
g
th
r
esh
o
ld
v
al
u
es
o
f
0
,
0
.
4
an
d
0
.
7
o
n
th
r
e
e
d
atab
ases
.
Up
o
n
ev
alu
atin
g
th
is
ex
is
tin
g
ap
p
r
o
ac
h
u
s
in
g
t
h
e
6
MWT
d
atab
as
e,
a
d
ec
r
e
ase
i
n
s
en
s
itiv
ity
an
d
an
e
n
h
an
ce
m
en
t
in
s
p
ec
if
icity
wer
e
n
o
ted
.
Nilash
i
et
a
l.
[
1
5
]
d
ev
elo
p
ed
ea
r
ly
i
d
en
tific
atio
n
PD
u
s
in
g
DL
an
d
f
u
zz
y
m
o
d
els.
Fo
r
h
an
d
lin
g
m
ass
iv
e
d
atasets
ex
p
ec
tatio
n
m
ax
im
izatio
n
an
d
c
lu
s
ter
in
g
wer
e
u
tili
ze
d
.
T
h
e
n
,
f
o
r
r
em
o
v
in
g
th
e
no
is
e,
th
e
PC
A
(
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
aly
s
is
)
was
p
r
esen
ted
.
At
last
,
th
e
K
-
n
ea
r
est
n
eig
h
b
o
u
r
(
KNN
)
was
p
r
esen
ted
to
id
e
n
tify
PD.
An
ap
p
r
o
ac
h
t
o
PD
d
etec
tio
n
u
s
in
g
s
p
ee
ch
r
ec
o
g
n
itio
n
was
s
u
g
g
ested
b
y
Nis
s
ar
et
a
l.
[
1
6
]
.
T
h
e
y
ev
alu
ated
eig
h
t
d
if
f
er
e
n
t
cl
ass
if
ier
s
u
s
in
g
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
in
clu
d
in
g
m
in
im
u
m
r
ed
u
n
d
a
n
cy
m
ax
im
u
m
r
ele
v
an
ce
(
m
R
MR
)
an
d
r
ec
u
r
s
iv
e
f
ea
tu
r
e
elim
in
at
io
n
(
R
FE
)
.
An
ac
cu
r
ac
y
o
f
9
5
.
3
9
%
was
ac
h
iev
ed
b
y
co
m
b
in
in
g
R
FE
with
ex
tr
em
e
g
r
ad
ie
n
t
b
o
o
s
t
in
g
(
X
g
b
o
o
s
t
)
,
wh
ich
was
b
etter
t
h
an
p
r
ev
io
u
s
m
et
h
o
d
s
.
Usi
n
g
v
o
ice
d
ata
f
r
o
m
UC
I
,
Gu
n
d
u
z
[
1
7
]
p
r
esen
ted
a
C
N
N
-
b
ased
PD
clas
s
if
icatio
n
m
eth
o
d
.
T
h
eir
c
o
m
b
in
e
d
u
s
e
o
f
f
ea
tu
r
es
an
d
m
o
d
els
r
es
u
lted
in
a
n
8
6
.
0
p
er
ce
n
t
m
o
d
el
-
lev
el
ac
cu
r
ac
y
.
B
y
c
o
m
b
i
n
in
g
B
AT
with
th
e
PD
class
if
icatio
n
d
ataset
f
r
o
m
UC
I
,
Oliv
ar
es
et
a
l.
[
1
8
]
cr
ea
te
d
a
m
eth
o
d
f
o
r
PD
d
iag
n
o
s
is
.
T
h
ey
wer
e
ab
le
to
attain
a
9
6
.
7
4
p
er
ce
n
t a
cc
u
r
ac
y
with
a
3
.
2
7
% lo
s
s
b
y
f
ee
d
i
n
g
2
3
c
h
ar
ac
ter
is
tics
in
to
th
e
m
o
d
el
’
s
in
p
u
t la
y
er
.
As
a
m
ea
n
s
o
f
p
r
e
-
d
iag
n
o
s
is
f
o
r
PD,
L
av
alle
an
d
R
o
m
er
o
[
1
9
]
s
u
g
g
ested
u
s
in
g
v
o
ice
d
ata.
T
h
ey
u
s
ed
KNN,
r
an
d
o
m
f
o
r
est
(
RF
)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SV
M
)
,
an
d
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
MLP
)
class
if
ier
s
to
ch
o
o
s
e
f
ea
tu
r
es
an
d
class
if
y
th
em
.
W
ith
a
p
r
ec
is
io
n
o
f
9
4
.
7
%,
th
e
SVM
-
R
B
F
c
lass
if
ier
was
a
s
u
cc
es
s
.
T
o
id
en
tify
PD,
Yam
an
et
a
l.
[
2
0
]
r
elied
o
n
v
o
wels.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
class
if
icatio
n
,
KNN
a
n
d
SVM
class
if
ier
s
wer
e
u
s
ed
af
ter
R
elief
F
wa
s
u
s
ed
to
ex
tr
ac
t
ac
o
u
s
tic
f
ea
tu
r
es
f
r
o
m
th
e
d
ataset.
A
9
1
.
2
5
%
s
u
cc
es
s
r
ate
was
attain
ed
with
th
e
SVM
class
if
ier
.
An
ML
-
b
ased
s
y
s
tem
f
o
r
p
ar
k
in
s
o
n
’
s
d
is
ea
s
e
d
iag
n
o
s
is
u
s
in
g
ch
o
s
en
f
ea
tu
r
es,
R
FE,
an
d
f
ea
tu
r
e
im
p
o
r
tan
ce
was
p
r
o
v
en
b
y
Sen
t
u
r
k
[
2
1
]
.
T
h
ey
u
s
ed
R
FE
an
d
SVM
class
if
ier
s
in
co
n
ju
n
ctio
n
with
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANNs
)
an
d
r
eg
r
ess
io
n
tr
ee
s
to
g
et
a
9
3
.
8
% a
cc
u
r
ac
y
r
ate.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
1
1
40
-
1
14
9
1142
I
n
th
eir
2
0
1
9
s
tu
d
y
,
Aich
et
a
l.
[
2
2
]
u
tili
ze
d
a
d
ataset
f
r
o
m
Ma
x
L
ittl
e
Un
iv
er
s
ity
,
Ox
f
o
r
d
,
to
ca
teg
o
r
ize
th
e
PD
g
r
o
u
p
u
s
in
g
p
r
i
n
cip
al
c
o
m
p
o
n
en
t
a
n
aly
s
is
(
PC
A)
an
d
o
n
lin
e
f
ea
tu
r
e
s
elec
tio
n
b
ased
o
n
r
eg
r
ess
io
n
(
OFS)
n
o
n
-
lin
ea
r
f
ea
tu
r
e
s
.
T
h
eir
m
eth
o
d
o
l
o
g
y
u
s
ed
n
o
n
lin
ea
r
class
if
ier
s
,
b
ag
g
in
g
class
if
icatio
n
,
r
eg
r
ess
io
n
tr
ee
s
,
R
F,
an
d
R
PAR
T
,
wh
ich
allo
wed
th
em
t
o
g
et
a
9
6
.
8
3
p
er
ce
n
t
ac
cu
r
ac
y
r
ate
wh
en
R
F
was
co
m
b
in
ed
with
PC
A.
W
h
en
it
co
m
es
to
PD
p
r
ed
ictio
n
,
R
u
s
tem
p
asic
an
d
C
an
[
2
3
]
h
ig
h
l
i
g
h
ted
b
io
m
ed
ical
v
o
ice
an
al
y
s
is
.
T
h
ey
wer
e
ab
l
e
to
ac
q
u
ir
e
a
s
en
s
itiv
ity
o
f
7
5
.
3
4
%,
a
s
p
ec
if
icity
o
f
4
5
.
6
3
%,
an
d
an
ac
c
u
r
ac
y
o
f
6
8
.
0
4
%
u
s
in
g
p
atter
n
r
ec
o
g
n
itio
n
an
d
f
u
zz
y
c
-
m
ea
n
s
(
FC
M)
clu
s
ter
in
g
to
f
o
r
ec
ast
PD
f
r
o
m
p
atien
ts
’
s
p
ee
ch
.
R
esear
ch
er
s
Sil
v
eir
a
e
t
a
l.
[
2
4
]
ad
m
in
is
ter
ed
th
e
p
en
n
s
y
lv
an
ia
s
m
ell
id
e
n
tific
atio
n
te
s
t
(
UPSIT
)
-
4
0
an
d
s
n
if
f
in
’
s
s
tick
s
1
6
-
item
s
m
ell
test
s
to
m
em
b
er
s
o
f
th
e
B
r
az
ilian
p
o
p
u
latio
n
.
Fo
r
ev
er
y
attr
ib
u
te,
lo
g
is
tic
r
eg
r
ess
io
n
was
u
s
ed
.
T
h
e
s
p
ec
if
icity
an
d
s
en
s
itiv
ity
lev
els
f
o
r
s
n
if
f
in
s
tick
s
wer
e
8
9
.
0
%
an
d
8
1
.
1
%,
r
esp
ec
tiv
ely
,
wh
er
ea
s
f
o
r
UP
SIT
-
4
0
th
e
y
wer
e
8
3
.
5
%
an
d
8
2
.
1
%.
T
h
e
s
leep
b
e
h
av
io
r
d
i
s
o
r
d
er
q
u
esti
o
n
n
air
e
an
d
th
e
o
lf
ac
to
r
y
im
p
air
m
en
t
s
ca
le
(
UPSIT
)
wer
e
u
s
ed
b
y
P
r
ash
an
th
et
a
l
.
[
2
5
]
.
A
s
en
s
itiv
ity
lev
el
o
f
9
0
.
5
%
an
d
a
n
ac
cu
r
ac
y
o
f
8
5
.
4
%
w
er
e
th
e
o
u
tco
m
es
o
f
tr
ain
in
g
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
an
d
class
if
icatio
n
tr
ee
s
.
Fro
m
th
e
d
et
ailed
liter
atu
r
e
r
e
v
iew,
th
e
f
o
llo
win
g
r
esear
ch
g
ap
s
ar
e
id
en
tifie
d
.
Data
s
ca
r
city
an
d
q
u
ality
−
Data
im
b
alan
ce
:
ex
is
tin
g
d
atasets
m
ay
b
e
im
b
alan
ce
d
,
with
m
o
r
e
d
ata
f
o
r
ce
r
tain
s
ev
er
it
y
lev
els,
lead
in
g
to
b
iased
m
o
d
el
p
er
f
o
r
m
an
ce
.
Dev
elo
p
in
g
tech
n
iq
u
es
to
h
a
n
d
le
im
b
alan
ce
d
d
ata
in
t
h
e
B
i
-
GR
U
m
o
d
el
is
a
g
ap
wo
r
t
h
ex
p
l
o
r
in
g
.
Featu
r
e
e
n
g
in
ee
r
i
n
g
−
Ad
v
an
ce
d
f
ea
tu
r
e
ex
tr
ac
tio
n
:
th
er
e
m
ig
h
t
b
e
a
lack
o
f
ad
v
a
n
ce
d
f
ea
tu
r
e
en
g
i
n
ee
r
in
g
tailo
r
ed
s
p
ec
if
ically
f
o
r
PD,
s
u
ch
as
ex
tr
ac
tin
g
n
o
n
-
lin
ea
r
p
atter
n
s
f
r
o
m
tim
e
-
s
e
r
ies
d
ata.
R
esear
ch
co
u
ld
f
o
cu
s
o
n
id
en
tify
in
g
o
r
cr
ea
tin
g
n
o
v
el
f
ea
tu
r
es th
at
en
h
an
ce
th
e
B
i
-
GR
U
’
s
ab
ilit
y
to
d
etec
t su
b
tle
ch
an
g
es in
d
is
ea
s
e
s
ev
er
ity
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
Fig
u
r
e
1
s
h
o
ws
th
e
b
lo
ck
d
i
ag
r
am
o
f
th
e
p
r
o
p
o
s
ed
g
ait
p
atter
n
an
aly
s
is
in
PD.
T
h
is
ap
p
r
o
a
ch
lev
er
ag
es
o
p
tim
ized
DL
m
o
d
el
an
d
in
c
o
r
p
o
r
ates
th
e
ca
p
ab
ilit
y
o
f
p
h
y
s
io
n
et
d
ataset
[
8
]
.
T
h
e
o
p
tim
ized
DL
m
o
d
el
B
I
-
GR
U
-
AHO
is
p
r
ese
n
ted
an
d
th
e
d
ataset
is
co
llected
u
s
in
g
VGRF
.
Fig
u
r
e
1
.
Fra
m
ewo
r
k
o
f
th
e
p
r
o
p
o
s
ed
g
ait
p
atter
n
an
al
y
s
is
in
PD
3
.
1
.
Da
t
a
ba
s
e
T
h
e
d
ata
b
ase
co
n
s
id
er
e
d
is
p
h
y
s
io
n
et
[
7
]
an
d
in
clu
d
es
g
ai
t
m
ea
s
u
r
em
en
ts
f
r
o
m
7
3
n
o
r
m
al
p
eo
p
le
(
av
er
ag
e
a
g
e
is
6
6
.
3
y
ea
r
s
)
an
d
9
3
p
e
o
p
le
(
a
v
er
ag
e
a
g
e
is
6
6
.
3
y
ea
r
s
)
with
id
i
o
p
ath
ic
PD
.
T
h
e
d
atab
ase
h
as
VGRF
in
s
tan
ce
s
o
f
in
d
iv
id
u
als
walk
in
g
o
n
lev
e
l
te
r
r
ain
f
o
r
ab
o
u
t
two
m
in
u
tes
at
th
eir
ty
p
ical,
s
elf
-
d
eter
m
in
ed
p
ac
e.
E
ig
h
t
s
en
s
o
r
s
in
th
e
r
ig
h
t
an
d
lef
t
f
o
o
t
tr
ac
k
f
o
r
ce
o
v
er
tim
e
an
d
it
is
c
o
m
p
u
ted
b
y
New
to
n
’
s
.
T
h
e
s
am
p
lin
g
f
r
eq
u
e
n
cy
is
1
0
0
Hz
an
d
th
e
o
u
tco
m
e
f
r
o
m
t
h
e
s
ix
teen
s
en
s
o
r
s
is
d
ig
italized
a
n
d
s
to
r
e
d
.
T
wo
s
ig
n
als
th
at
r
ep
r
esen
t
t
h
e
to
tal
o
f
t
h
e
o
u
tco
m
es
f
r
o
m
ev
er
y
eig
h
t
s
en
s
o
r
s
f
o
r
ev
e
r
y
f
o
o
t
a
r
e
also
in
clu
d
ed
i
n
th
e
in
s
tan
ce
s
.
T
h
e
d
atab
ase
h
a
s
s
ev
er
ity
r
atin
g
s
o
f
h
ea
lth
y
,
s
ev
er
ity
2
,
2
.
5
,
an
d
3
.
3
.
2
.
P
re
pa
ring
da
t
a
s
a
m
ples
T
h
e
g
ait
o
b
s
er
v
e
d
o
n
r
eg
u
lar
walk
in
g
f
o
r
t
h
e
lo
we
r
leg
o
n
t
h
e
lef
t
o
r
r
ig
h
t
ex
h
i
b
its
a
q
u
asi
-
p
er
io
d
ic
m
o
d
el.
T
h
er
ef
o
r
e,
f
o
r
e
f
f
ec
tiv
e
m
o
d
ellin
g
an
d
u
n
d
er
s
tan
d
in
g
o
f
th
e
in
h
er
en
t
b
eh
av
i
o
u
r
o
f
g
ait,
it
is
ad
v
is
ab
le
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:
2
5
0
2
-
4
7
52
I
mp
r
o
ve
d
B
i
-
GR
U
fo
r
p
a
r
kin
s
o
n
’
s
d
is
ea
s
e
s
ev
erit
y
a
n
a
lysi
s
(
Ma
la
th
i A
r
u
n
a
c
h
a
la
m)
1143
to
s
eg
m
en
t
g
ait
d
ata
b
ased
o
n
walk
cy
cles.
T
o
ac
h
iev
e
th
is
,
th
e
wo
r
k
em
p
lo
y
ed
th
e
o
v
er
all
f
o
r
ce
f
o
r
id
en
tify
in
g
t
h
e
walk
cy
cles
f
o
r
th
e
r
esp
ec
tiv
e
lo
wer
leg
.
T
h
e
cy
cle
f
o
r
g
ait
in
th
e
s
in
g
le
lo
wer
leg
is
d
elin
ea
ted
as
th
e
d
u
r
atio
n
f
r
o
m
th
e
in
itial
in
s
tan
ce
wh
e
n
th
e
r
esp
ec
tiv
e
f
o
o
t
m
ak
es
a
s
et
with
th
e
f
l
o
o
r
to
th
e
co
n
clu
d
in
g
m
o
tio
n
if
th
e
f
o
o
t
lifts
o
f
f
th
e
f
lo
o
r
.
E
m
p
l
o
y
in
g
a
th
r
esh
o
ld
p
r
o
ce
s
s
en
ab
les
th
e
d
etec
tio
n
o
f
th
e
ze
r
o
-
cr
o
s
s
ed
p
o
in
t,
f
ac
ilit
atin
g
th
e
s
eg
m
en
tatio
n
o
f
t
h
e
g
ait
cy
cle.
Utilizin
g
th
e
id
en
tifie
d
g
ait
cy
cle,
th
e
m
u
ltip
le
r
an
g
es
o
f
VGRF
d
ata
ar
e
s
p
lit
to
d
if
f
er
en
t
s
am
p
les
o
f
d
ata
to
tr
ain
an
d
tr
ain
th
e
class
if
ier
.
T
h
e
ze
r
o
-
p
ad
d
i
n
g
ap
p
r
o
ac
h
is
u
tili
ze
d
f
o
r
m
a
k
in
g
e
v
er
y
i
d
en
tifie
d
g
ait
cy
cle
with
an
e
q
u
al
len
g
th
o
f
1
4
0
.
3
.
3
.
G
a
it
cla
s
s
if
ica
t
io
n
Fo
r
m
o
d
ellin
g
t
h
e
lef
t
an
d
r
ig
h
t
g
aits
,
th
e
DL
m
o
d
el
B
I
-
GR
U
-
AHO
is
p
r
esen
ted
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
R
NN
h
as
b
ee
n
d
em
o
n
s
tr
ated
in
p
r
o
ce
s
s
es
lik
e
s
ig
n
al
an
d
lan
g
u
ag
e
r
ec
o
g
n
itio
n
.
Ho
wev
e
r
,
th
e
co
n
v
e
n
tio
n
al
R
NN
en
co
u
n
ter
ch
allen
g
es
s
u
ch
as
g
r
ad
ien
t
v
an
is
h
in
g
,
esp
ec
ially
with
in
cr
ea
s
in
g
in
p
u
t
d
ata.
Ad
d
r
ess
in
g
th
ese
ch
allen
g
es,
an
L
STM
is
d
ev
elo
p
ed
a
n
d
b
ec
a
u
s
e
o
f
its
g
atin
g
m
o
d
el,
L
STM
ca
n
ef
f
ec
tiv
ely
u
tili
ze
f
o
r
s
to
r
in
g
an
d
ac
ce
s
s
in
g
u
s
ef
u
l
f
ea
tu
r
es.
I
n
th
e
ad
v
an
ce
d
m
o
d
el
o
f
L
STM
,
p
r
ev
io
u
s
wo
r
k
s
in
d
icate
th
at
GR
U
o
u
tp
er
f
o
r
m
s
L
S
T
M
in
v
ar
io
u
s
d
o
m
ain
s
.
I
n
th
is
wo
r
k
,
O
-
GR
U
h
as
th
e
g
ates
lik
e
u
p
d
ate
g
a
te
an
d
r
eset
g
ate
as sh
o
wn
in
Fig
u
r
e
2
.
=
(
+
h
−
1
+
)
(
1
)
=
(
+
h
−
1
+
)
(
2
)
=
h
(
+
h
−
1
+
)
(
3
)
h
=
(
1
−
)
h
−
1
+
(
4
)
W
h
er
e
,
,
,
h
an
d
ar
e
th
e
s
ig
m
o
id
,
in
p
u
t
v
ec
to
r
,
h
id
d
en
p
h
a
s
e
an
d
s
to
r
ag
e
m
ed
i
u
m
.
,
,
,
an
d
,
,
ar
e
th
e
weig
h
tin
g
m
atr
ices a
n
d
,
,
ar
e
th
e
b
ias v
alu
es.
B
u
t,
th
e
GR
U
n
etwo
r
k
c
o
n
s
id
er
s
th
e
in
p
u
t
s
er
ies
in
o
n
ly
o
n
e
d
ir
ec
tio
n
,
lim
itin
g
its
ab
ilit
y
to
lear
n
th
e
r
ep
r
esen
tatio
n
o
f
th
e
f
e
atu
r
e.
C
o
n
s
eq
u
en
tly
,
th
e
B
i
-
GR
U
m
o
d
el
h
as
b
ee
n
d
e
v
is
ed
to
ad
d
r
ess
th
is
lim
itatio
n
b
y
g
en
er
atin
g
a
s
er
ies o
f
in
p
u
ts
f
r
o
m
b
o
th
f
o
r
war
d
an
d
b
ac
k
war
d
d
ir
ec
tio
n
s
.
T
h
e
f
o
r
m
u
latio
n
o
f
th
e
Bi
-
GR
U
m
o
d
el
in
b
o
th
d
ir
ec
ti
o
n
s
is
p
r
esen
ted
b
elo
w:
h
→
=
→
(
,
h
−
1
)
(
5
)
h
←
=
←
(
,
h
−
1
)
(
6
)
At
last
,
th
e
last
o
u
tco
m
es o
f
th
e
B
i
-
GR
U
m
o
d
el
ar
e
g
iv
en
as
(
7
)
.
=
[
h
→
,
h
←
]
(
7
)
T
h
en
,
f
o
r
o
p
tim
izin
g
th
e
p
a
r
am
eter
s
o
f
B
i
-
GR
U
m
o
d
el,
th
e
o
p
tim
izer
AHA
is
p
r
es
en
ted
.
HB
(
h
u
m
m
in
g
b
ir
d
s
)
ass
ess
th
e
ch
ar
ac
ter
is
tics
o
f
f
o
o
d
s
o
u
r
ce
s
,
in
clu
d
in
g
th
e
co
n
te
x
t
an
d
q
u
ali
ty
o
f
h
o
n
ey
s
p
ec
if
ic
f
lo
wer
s
,
th
e
r
ate
o
f
h
o
n
ey
p
r
o
d
u
ctio
n
,
an
d
th
e
tim
e
elap
s
ed
s
in
ce
t
h
eir
f
in
al
v
is
it
to
a
f
lo
wer
.
T
h
e
f
o
r
ag
in
g
b
e
h
av
io
u
r
en
c
o
m
p
ass
es
th
r
ee
s
tr
ateg
ies
g
u
id
e
d
,
r
elo
ca
tio
n
,
a
n
d
ter
r
ito
r
ial
f
o
r
ag
in
g
.
T
h
ese
th
r
ee
f
o
r
ag
in
g
b
e
h
av
io
u
r
s
ar
e
p
r
ese
n
ted
b
elo
w.
Fig
u
r
e
2
.
B
i
-
GR
U
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
1
1
40
-
1
14
9
1144
I
n
itializatio
n
:
t
h
e
p
o
p
u
latio
n
o
f
HB
is
k
ep
t
in
a
r
a
n
d
o
m
ize
d
m
an
n
e
r
o
n
th
e
s
o
u
r
ce
o
f
f
o
o
d
an
d
it
is
g
iv
en
as
(
8
)
.
=
+
×
(
−
)
(
8
)
W
h
er
e
,
,
is
th
e
u
p
p
e
r
,
an
d
lo
we
r
b
o
u
n
d
s
an
d
is
th
e
r
an
d
o
m
n
u
m
b
er
.
Gu
id
in
g
f
o
r
ag
i
n
g
:
HB
in
d
iv
id
u
ally
n
a
v
ig
ates
to
war
d
s
th
e
n
e
ctar
s
o
u
r
ce
co
n
tain
in
g
t
h
e
h
i
g
h
est
n
ec
tar
co
n
ten
t.
T
h
ese
b
ir
d
s
u
tili
ze
th
r
ee
d
is
tin
ct
f
lig
h
t
m
o
d
es:
ax
ia
l,
d
iag
o
n
al,
a
n
d
o
m
n
id
ir
ec
tio
n
al.
T
h
e
a
x
ial
f
lig
h
t
is
g
iv
en
as
(
9
)
.
(
)
=
{
1
h
=
0
h
(
9
)
T
h
e
d
iag
o
n
al
f
lig
h
t is g
iv
e
n
as
(
1
0
)
.
(
)
=
{
1
h
=
(
)
0
h
(
1
0
)
W
h
er
e
,
=
(
)
,
is
th
e
r
an
d
o
m
p
e
r
m
u
t
atio
n
.
T
h
e
o
m
n
i
d
ir
ec
tio
n
al
f
lig
h
t is g
iv
en
as
(
1
1
)
.
(
)
=
1
(
1
1
)
T
h
e
f
o
r
a
g
in
g
c
h
ar
ac
ter
is
tic
is
m
ath
em
atica
lly
ex
p
r
ess
ed
as
(
1
2
)
.
(
+
1
)
=
,
(
)
+
×
×
(
(
)
−
,
(
)
)
(
1
2
)
W
h
er
e
,
(
)
is
th
e
h
HB
p
o
s
itio
n
o
f
f
o
o
d
s
o
u
r
ce
an
d
is
th
e
g
u
id
in
g
t
er
m
.
T
h
e
h
HB
p
o
s
itio
n
o
f
f
o
o
d
s
o
u
r
ce
is
g
iv
en
as:
(
+
1
)
=
{
(
)
(
(
(
)
)
≤
(
+
1
)
)
(
+
1
)
(
(
(
)
)
>
(
+
1
)
)
(
1
3
)
W
h
en
th
e
f
o
o
d
s
o
u
r
ce
o
f
ca
n
d
id
ate
’
s
h
o
n
ey
f
ill
r
atio
n
is
lar
g
er
th
an
th
e
p
r
esen
t
s
o
u
r
ce
o
f
f
o
o
d
,
th
e
HB
av
o
id
s
th
e
p
r
esen
t so
u
r
ce
o
f
f
o
o
d
.
Fig
u
r
e
3
s
h
o
ws th
e
f
lo
wch
ar
t o
f
th
e
AHA.
Fig
u
r
e
3
.
Flo
w
-
ch
a
r
t o
f
t
h
e
A
HA
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:
2
5
0
2
-
4
7
52
I
mp
r
o
ve
d
B
i
-
GR
U
fo
r
p
a
r
kin
s
o
n
’
s
d
is
ea
s
e
s
ev
erit
y
a
n
a
lysi
s
(
Ma
la
th
i A
r
u
n
a
c
h
a
la
m)
1145
T
er
r
ito
r
ial
f
o
r
a
g
in
g
:
t
h
e
m
ath
e
m
atica
l
eq
u
atio
n
b
elo
w
o
u
tlin
es
th
e
lo
ca
l
f
o
r
ag
e
p
r
o
ce
s
s
em
p
lo
y
ed
b
y
HB
an
d
d
ef
in
es a
p
r
o
p
er
s
o
u
r
c
e
o
f
f
o
o
d
with
in
t
h
eir
ter
r
ito
r
ial
f
o
r
ag
in
g
m
o
d
el.
(
+
1
)
=
(
)
+
×
×
(
)
(
1
4
)
W
h
er
e
is
th
e
ter
r
ito
r
ial
ter
m
.
R
elo
ca
tio
n
f
o
r
ag
in
g
:
t
h
e
r
elo
c
atio
n
o
f
a
HB
,
tr
an
s
itio
n
in
g
f
r
o
m
th
e
h
o
n
e
y
s
o
u
r
ce
with
th
e
less
r
ef
ill
r
atio
to
a
r
a
n
d
o
m
l
y
g
en
e
r
ated
n
ew
s
o
u
r
ce
,
ca
n
b
e
elu
ci
d
ated
as
(
1
5
)
.
(
+
1
)
=
+
×
(
−
)
(
1
5
)
W
h
er
e
is
th
e
s
o
u
r
ce
o
f
f
o
o
d
h
av
in
g
less
r
ef
ill r
atio
.
4.
RE
SU
L
T
S AN
A
L
YS
I
S
T
o
ass
ess
all
cla
s
s
if
icatio
n
m
o
d
els,
a
s
tr
atif
ied
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
ap
p
r
o
ac
h
is
em
p
lo
y
ed
.
I
n
itially
,
th
e
o
r
ig
in
al
d
ata
b
ase
is
s
p
lit
in
to
1
0
s
ep
ar
ate
f
o
ld
v
alu
es.
Nin
e
o
u
t o
f
th
e
ten
f
o
ld
s
ar
e
in
teg
r
ated
a
n
d
u
tili
ze
d
as
a
tr
ain
m
o
d
el,
wh
il
e
th
e
r
est
f
o
ld
s
s
er
v
ed
as
a
test
m
o
d
el.
E
ac
h
tr
ai
n
m
o
d
el
u
n
d
er
wen
t
r
esam
p
lin
g
an
d
r
esizin
g
u
s
in
g
th
e
SMO
T
E
alg
o
r
ith
m
to
en
s
u
r
e
a
m
o
r
e
b
alan
ce
d
d
is
tr
ib
u
tio
n
o
f
in
s
tan
ce
s
ac
r
o
s
s
all
class
es.
T
ab
le
1
d
ef
in
es
th
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
co
n
s
id
er
e
d
in
th
is
wo
r
k
.
T
h
ese
m
etr
ic
s
ar
e
ev
alu
ated
u
s
in
g
f
o
u
r
cr
iter
ia
lik
e
,
,
,
an
d
as
tr
u
e
p
o
s
itiv
e,
f
alse
n
eg
ativ
e,
f
alse
p
o
s
itiv
e
an
d
f
alse
n
eg
at
iv
e
r
esp
ec
tiv
ely
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
m
etr
ics
M
e
t
r
i
c
s
Ex
p
r
e
ssi
o
n
s
A
c
c
u
r
a
c
y
+
+
+
+
P
r
e
c
i
s
i
o
n
+
S
e
n
s
i
t
i
v
i
t
y
+
S
p
e
c
i
f
i
c
i
t
y
+
4
.
1
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
Fo
llo
win
g
s
ec
tio
n
d
ef
in
es
co
m
p
ar
is
o
n
o
f
ac
c
u
r
ac
y
b
y
v
ar
y
in
g
d
if
f
er
en
t
iter
atio
n
s
,
co
n
f
u
s
io
n
m
atr
ix
,
r
eg
io
n
o
f
ch
ar
ac
ter
is
tics
(
R
o
C
)
an
d
co
m
p
ar
ativ
e
an
aly
s
is
ar
e
g
iv
en
.
Fig
u
r
e
4
s
tates
th
e
a
cc
u
r
ac
y
b
y
v
ar
y
i
n
g
d
if
f
er
en
t
iter
atio
n
s
f
r
o
m
1
to
1
4
,
0
0
0
.
Acc
u
r
ac
y
p
e
r
f
o
r
m
an
c
e
is
ca
r
r
ied
o
u
t
b
y
v
ar
y
in
g
l
o
s
s
v
alu
es
f
r
o
m
1
=
1
0
−
5
,
1
=
1
0
−
4
,
1
=
1
0
−
3
,
an
d
1
=
1
0
−
2
.
I
t
is
o
b
s
er
v
ed
th
at
w
h
en
th
e
iter
atio
n
is
in
cr
ea
s
ed
,
t
h
e
ac
cu
r
ac
y
v
alu
e
is
also
in
cr
ea
s
ed
.
Mo
r
e
o
v
er
,
th
e
v
alu
e
o
f
ac
cu
r
ac
y
is
h
ig
h
at
1
=
1
0
−
5
an
d
v
alu
e
o
f
a
cc
u
r
ac
y
i
s
lo
w
at
1
=
1
0
−
2
.
Fig
u
r
e
4
.
Acc
u
r
ac
y
at
d
if
f
er
en
t iter
atio
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
1
1
40
-
1
14
9
1146
Fig
u
r
e
5
p
r
esen
ts
th
e
co
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
p
r
o
p
o
s
ed
D
L
m
o
d
el
B
I
-
GR
U
-
AHO
with
r
esp
ec
t
to
f
o
u
r
class
es
as
h
ea
lth
y
,
s
ev
er
i
ty
2
,
2
.
5
,
an
d
3
.
I
t
is
n
o
ted
t
h
at
th
e
p
r
o
p
o
s
ed
B
I
-
GR
U
-
AHO
class
if
ied
9
9
.
9
6
%
s
am
p
les
as
h
ea
lth
y
,
9
7
.
0
2
%
s
am
p
les
as
s
ev
er
ity
2
,
9
6
.
5
9
%
s
am
p
les
as
s
ev
er
ity
2
.
5
an
d
9
9
.
7
4
%
s
am
p
les
as
s
ev
er
ity
3
.
Fig
u
r
e
6
p
r
esen
t
s
th
e
r
ec
eiv
er
o
p
er
atin
g
ch
a
r
ac
ter
is
tic
(
R
OC
)
o
f
th
e
p
r
o
p
o
s
ed
DL
m
o
d
el
BI
-
GR
U
-
AHO
w
ith
r
esp
ec
t
t
o
f
o
u
r
class
es
lik
e
h
ea
lth
y
,
s
ev
er
ity
2
,
2
.
5
,
a
n
d
3
.
T
h
e
ar
ea
u
n
d
er
t
h
e
cu
r
v
e
(
AUC)
v
alu
e
ac
h
iev
ed
b
y
th
e
h
ea
lth
y
,
s
ev
er
ity
2
,
2
.
5
,
a
n
d
3
ar
e
0
.
9
7
7
,
0
.
9
6
1
,
0
.
9
6
3
,
an
d
0
.
9
7
.
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
Fig
u
r
e
6
.
R
OC
cu
r
v
e
o
f
th
e
s
e
v
er
ity
s
tag
es
T
ab
le
2
d
ep
icts
th
e
c
o
m
p
ar
a
tiv
e
an
aly
s
is
o
f
d
if
f
er
e
n
t
ap
p
r
o
ac
h
es
lik
e
R
NN,
L
STM
,
B
i
-
L
STM
,
GR
U,
B
i
-
G
R
U
,
an
d
th
e
p
r
o
p
o
s
ed
B
I
-
GR
U
-
AHO.
T
h
e
p
er
f
o
r
m
an
ce
is
ca
r
r
ied
o
u
t
b
y
v
ar
y
i
n
g
th
e
h
ea
lth
y
an
d
s
ev
er
ity
v
alu
es.
I
n
a
ll
c
o
m
p
ar
ativ
e
p
er
f
o
r
m
a
n
ce
th
e
p
r
o
p
o
s
ed
B
I
-
GR
U
-
AHO
o
u
tp
er
f
o
r
m
ed
th
e
co
n
v
en
tio
n
a
l
DL
m
o
d
el
an
d
s
u
itab
le
f
o
r
g
ai
t a
n
aly
s
is
.
T
h
e
p
r
ac
tical
im
p
ac
ts
o
f
u
s
in
g
i
m
p
r
o
v
ed
B
i
-
GR
U
f
o
r
PD
s
e
v
er
ity
an
aly
s
is
ca
n
b
e
s
u
b
s
tan
tial
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
,
p
ar
ticu
lar
l
y
i
n
h
ea
lth
ca
r
e,
p
atien
t c
ar
e,
a
n
d
r
esear
ch
.
Her
e
ar
e
s
o
m
e
o
f
t
h
e
k
ey
im
p
ac
ts
:
E
n
h
an
ce
d
d
iag
n
o
s
tic
ac
cu
r
ac
y
−
I
m
p
r
o
v
ed
ea
r
ly
d
etec
tio
n
:
th
e
Bi
-
GR
U
m
o
d
el,
with
its
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
lex
tem
p
o
r
a
l
d
ep
en
d
en
cies
in
s
eq
u
en
tial
d
ata,
ca
n
s
ig
n
if
i
ca
n
tly
en
h
a
n
ce
th
e
ac
cu
r
ac
y
o
f
ea
r
ly
d
etec
tio
n
o
f
PD
.
T
h
i
s
lead
s
to
tim
ely
in
ter
v
en
tio
n
s
,
p
o
ten
tially
s
lo
win
g
d
is
ea
s
e
p
r
o
g
r
ess
io
n
.
−
Pre
cisi
o
n
in
s
ev
er
ity
class
if
icatio
n
:
b
y
ac
c
u
r
ately
class
if
y
in
g
th
e
s
ev
er
ity
o
f
PD
s
y
m
p
t
o
m
s
,
th
e
m
o
d
el
en
ab
les
m
o
r
e
tailo
r
e
d
tr
ea
tm
e
n
t
p
lan
s
.
T
h
is
p
r
ec
is
io
n
is
cr
itical
in
m
an
ag
in
g
th
e
d
is
ea
s
e
ef
f
ec
tiv
ely
an
d
ad
ju
s
tin
g
th
er
ap
ies as n
ee
d
e
d
.
C
lin
ical
d
ec
is
io
n
s
u
p
p
o
r
t
−
Su
p
p
o
r
tin
g
clin
ician
s
:
th
e
m
o
d
el
ca
n
s
er
v
e
as
a
d
ec
is
io
n
s
u
p
p
o
r
t
to
o
l
f
o
r
clin
ician
s
,
p
r
o
v
id
in
g
d
ata
-
d
r
iv
e
n
in
s
ig
h
ts
in
to
th
e
s
ev
er
ity
o
f
a
p
atien
t
’
s
co
n
d
itio
n
.
T
h
is
ca
n
a
s
s
is
t
in
m
ak
in
g
i
n
f
o
r
m
ed
d
ec
i
s
io
n
s
r
eg
ar
d
i
n
g
tr
ea
tm
en
t o
p
tio
n
s
a
n
d
in
ter
v
en
tio
n
s
.
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:
2
5
0
2
-
4
7
52
I
mp
r
o
ve
d
B
i
-
GR
U
fo
r
p
a
r
kin
s
o
n
’
s
d
is
ea
s
e
s
ev
erit
y
a
n
a
lysi
s
(
Ma
la
th
i A
r
u
n
a
c
h
a
la
m)
1147
−
R
ed
u
cin
g
d
iag
n
o
s
tic
v
ar
iab
ilit
y
:
b
y
p
r
o
v
id
i
n
g
co
n
s
is
ten
t
an
d
o
b
jectiv
e
s
ev
er
ity
ass
ess
m
en
ts
,
th
e
i
m
p
r
o
v
e
d
Bi
-
GR
U
r
ed
u
ce
s
th
e
v
ar
i
ab
ilit
y
in
d
iag
n
o
s
es
th
at
ca
n
o
cc
u
r
d
u
e
to
s
u
b
jectiv
e
j
u
d
g
m
e
n
t,
l
ea
d
in
g
to
m
o
r
e
s
tan
d
ar
d
ized
ca
r
e.
T
h
ese
p
r
ac
tical
im
p
ac
ts
h
ig
h
lig
h
t
th
e
p
o
ten
tial
o
f
t
h
e
i
m
p
r
o
v
e
d
B
i
-
GR
U
m
o
d
el
to
r
ev
o
lu
tio
n
ize
th
e
m
an
ag
em
en
t
an
d
u
n
d
er
s
tan
d
i
n
g
o
f
PD
,
lead
in
g
to
b
etter
p
atie
n
t
o
u
tco
m
es
an
d
m
o
r
e
ef
f
icien
t
h
ea
lth
ca
r
e
s
y
s
tem
s
.
T
ab
le
2
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
C
l
a
s
s
M
e
t
h
o
d
A
c
c
u
r
a
c
y
S
e
n
s
i
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
P
r
e
c
i
s
i
o
n
H
e
a
l
t
h
y
R
N
N
9
0
.
2
9
1
.
2
9
1
.
7
8
9
.
3
LSTM
9
1
.
3
9
2
.
4
9
3
.
9
9
0
.
4
Bi
-
LST
M
9
4
.
3
9
4
.
9
9
4
.
5
9
3
.
2
G
R
U
9
4
.
7
9
5
.
1
9
5
.
6
9
4
.
8
Bi
-
G
R
U
9
5
.
6
9
5
.
9
9
6
.
9
9
5
.
3
P
r
o
p
o
se
d
9
8
.
7
9
7
.
7
9
7
.
2
9
6
.
9
2
R
N
N
9
4
.
2
9
1
.
9
9
1
.
4
9
0
.
3
LSTM
9
4
.
3
9
2
.
3
9
5
.
9
9
0
.
5
Bi
-
LST
M
9
5
.
3
9
4
.
1
9
4
.
9
9
3
.
4
G
R
U
9
5
.
7
9
5
.
5
9
6
.
7
9
4
.
1
Bi
-
G
R
U
9
5
.
9
9
4
.
9
9
7
.
8
9
5
.
9
P
r
o
p
o
se
d
9
6
.
7
9
7
.
3
9
7
.
8
9
9
.
9
2
.
5
R
N
N
9
0
.
4
9
1
.
2
9
0
.
1
8
9
.
6
LSTM
9
1
.
3
9
2
.
4
9
2
.
2
9
0
.
7
Bi
-
LST
M
9
4
.
3
9
4
.
9
9
4
.
7
9
3
.
4
G
R
U
9
4
.
7
9
5
.
1
9
5
.
8
9
4
.
9
Bi
-
G
R
U
9
5
.
6
9
5
.
9
9
6
.
2
9
6
.
2
P
r
o
p
o
se
d
9
8
.
5
9
6
.
7
9
7
.
9
9
8
.
9
3
R
N
N
9
0
.
6
9
1
.
6
9
1
.
9
9
0
.
3
LSTM
9
1
.
5
9
1
.
4
9
4
.
9
9
1
.
4
Bi
-
LST
M
9
3
.
1
9
5
.
8
9
5
.
5
9
3
.
5
G
R
U
9
4
.
4
9
5
.
4
9
5
.
2
9
4
.
6
Bi
-
G
R
U
9
5
.
2
9
5
.
8
9
6
.
1
9
5
.
2
P
r
o
p
o
se
d
9
8
.
1
9
7
.
6
9
7
.
4
9
7
.
1
5.
CO
NCLU
SI
O
N
Sig
n
als
in
g
ait
ty
p
ically
ex
h
ib
it
p
er
io
d
ic
an
d
r
e
p
etitiv
e
p
a
tter
n
s
.
T
h
er
ef
o
r
e
,
th
e
ev
alu
ati
o
n
o
f
g
ait
ab
n
o
r
m
alities
p
r
o
v
es
ef
f
ec
tiv
e
in
d
is
tin
g
u
is
h
in
g
b
etwe
en
n
o
r
m
al
an
d
PD
in
d
i
v
id
u
als.
Me
d
ical
ex
p
er
ts
tr
ad
itio
n
ally
r
ely
o
n
m
u
ltip
le
p
h
y
s
ical,
n
eu
r
o
l
o
g
ical
an
d
p
h
y
s
io
lo
g
ical
an
aly
s
es
f
o
r
an
ac
cu
r
ate
PD
d
iag
n
o
s
is
.
Ho
wev
er
,
th
is
ap
p
r
o
ac
h
h
ea
v
i
ly
r
elies
o
n
th
e
ex
p
er
tis
e
an
d
lead
s
to
in
ac
cu
r
ac
ies.
T
h
e
wo
r
k
p
r
esen
ted
i
n
th
is
p
ap
er
(
DL
m
o
d
el
B
I
-
GR
U
-
AHO)
was
s
u
b
s
eq
u
en
tly
u
tili
ze
d
to
an
aly
ze
th
e
g
ait
p
atter
n
s
o
n
th
e
VGRF
p
atter
n
.
T
h
e
p
r
o
p
o
s
ed
B
I
-
GR
U
-
AHO
was
tr
ain
ed
u
s
in
g
a
1
0
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
an
d
ac
h
ie
v
ed
b
etter
ac
cu
r
ac
ies
o
f
9
8
.
7
%
(
h
ea
lth
y
)
,
9
6
.
7
%
(
s
ev
e
r
ity
2
)
,
9
8
.
5
%
(
(
s
ev
er
ity
2
.
5
)
,
an
d
9
8
.
1
%
(
s
ev
er
ity
3
)
r
esp
ec
t
iv
ely
.
T
h
e
f
in
d
in
g
s
s
u
g
g
est th
at
th
e
p
r
o
p
o
s
ed
B
I
-
GR
U
-
AHO,
wh
en
tr
ain
ed
with
a
lar
g
er
d
atab
ase
o
f
g
ait
d
ata,
h
as th
e
p
o
ten
tial to
o
f
f
er
im
p
r
o
v
ed
ass
ess
m
en
ts
o
f
p
atien
ts
with
PD.
T
h
is
ca
p
a
b
ilit
y
ca
n
b
e
p
ar
ticu
l
ar
ly
v
alu
a
b
le
f
o
r
clin
ician
s
in
f
o
r
m
u
latin
g
m
o
r
e
ef
f
ec
tiv
e
r
e
h
ab
ilit
atio
n
p
r
o
g
r
am
s
.
Fu
tu
r
e
r
esear
ch
co
u
ld
f
o
c
u
s
o
n
v
alid
atin
g
th
e
i
m
p
r
o
v
e
d
Bi
-
GR
U
m
o
d
el
ac
r
o
s
s
m
u
lti
p
le
an
d
d
i
v
er
s
e
d
atasets
.
T
h
is
wo
u
ld
en
s
u
r
e
th
e
m
o
d
e
l
’
s
r
o
b
u
s
tn
ess
an
d
g
en
er
aliza
b
ilit
y
,
m
ak
in
g
it
ap
p
licab
le
to
d
if
f
er
en
t
p
o
p
u
latio
n
s
an
d
en
v
ir
o
n
m
en
ts
.
I
n
v
est
ig
atin
g
m
eth
o
d
s
to
ad
ap
t
th
e
B
i
-
GR
U
m
o
d
el
to
n
ew
d
atasets
with
m
in
im
al
r
etr
ain
in
g
co
u
l
d
en
h
a
n
ce
its
u
s
ab
ilit
y
in
d
if
f
er
en
t
clin
ical
s
ettin
g
s
,
r
ed
u
cin
g
th
e
n
ee
d
f
o
r
ex
ten
s
iv
e
d
ata
co
llect
io
n
an
d
m
o
d
el
r
etr
ain
in
g
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
Au
th
o
r
with
a
d
ee
p
s
en
s
e
o
f
g
r
atitu
d
e
wo
u
ld
th
a
n
k
th
e
s
u
p
er
v
is
o
r
f
o
r
h
is
g
u
id
an
ce
an
d
co
n
s
tan
t
s
u
p
p
o
r
t r
e
n
d
er
e
d
d
u
r
in
g
t
h
is
r
esear
ch
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
B
a
l
a
k
r
i
s
h
n
a
n
,
J.
M
e
d
i
k
o
n
d
a
,
P
.
K
.
N
a
m
b
o
o
t
h
i
r
i
,
a
n
d
M
.
N
a
t
a
r
a
j
a
n
,
“
R
o
l
e
o
f
w
e
a
r
a
b
l
e
se
n
s
o
r
s
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
i
n
g
a
i
t
a
n
a
l
y
s
i
s
f
o
r
p
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
a
ssess
me
n
t
:
a
r
e
v
i
e
w
,
”
En
g
i
n
e
e
re
d
S
c
i
e
n
ce
,
v
o
l
.
1
9
,
p
p
.
5
–
1
9
,
2
0
2
2
,
d
o
i
:
1
0
.
3
0
9
1
9
/
e
s8
e
6
2
2
.
[
2
]
B
.
G
.
M
u
ñ
o
z
-
M
a
t
a
,
G
.
D
o
r
a
n
t
e
s
-
M
é
n
d
e
z
,
a
n
d
O
.
P
i
ñ
a
-
R
a
m
í
r
e
z
,
“
S
t
a
c
k
e
d
sp
a
t
i
a
l
a
n
d
t
e
mp
o
r
a
l
d
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
s
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
u
si
n
g
g
a
i
t
si
g
n
a
l
s
,
”
i
n
I
FM
BE
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
8
6
,
2
0
2
3
,
p
p
.
1
1
9
–
1
2
6
.
[
3
]
B
.
L
i
,
Y
.
S
u
n
,
Z.
Y
a
o
,
J.
W
a
n
g
,
S
.
W
a
n
g
,
a
n
d
X
.
Y
a
n
g
,
“
I
mp
r
o
v
e
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
t
o
d
e
t
e
c
t
f
r
e
e
z
i
n
g
o
f
g
a
i
t
i
n
p
a
r
k
i
n
so
n
’
s
d
i
se
a
se
b
a
s
e
d
o
n
w
e
a
r
a
b
l
e
s
e
n
s
o
r
s,
”
El
e
c
t
ro
n
i
c
s
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
9
,
n
o
.
1
1
,
p
p
.
1
–
2
0
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s9
1
1
1
9
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
1
1
40
-
1
14
9
1148
[
4
]
B
.
E.
,
B
.
D
.
,
a
n
d
B
.
R
.
,
“
S
u
p
e
r
v
i
se
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
g
a
i
t
c
l
a
ssi
f
i
c
a
t
i
o
n
sy
s
t
e
m
f
o
r
e
a
r
l
y
d
e
t
e
c
t
i
o
n
a
n
d
st
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
P
a
r
k
i
n
so
n
’
s
d
i
s
e
a
s
e
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
J
o
u
rn
a
l
,
v
o
l
.
9
4
,
p
.
1
0
6
4
9
4
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
0
.
1
0
6
4
9
4
.
[
5
]
B
.
F
i
l
t
j
e
n
s,
A
.
N
i
e
u
w
b
o
e
r
,
N
.
D
’
c
r
u
z
,
J.
S
p
i
l
d
o
o
r
e
n
,
P
.
S
l
a
e
t
s
,
a
n
d
B
.
V
a
n
r
u
mst
e
,
“
A
d
a
t
a
-
d
r
i
v
e
n
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
g
a
i
t
e
v
e
n
t
s
d
u
r
i
n
g
t
u
r
n
i
n
g
i
n
p
e
o
p
l
e
w
i
t
h
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
a
n
d
f
r
e
e
z
i
n
g
o
f
g
a
i
t
,
”
G
a
i
t
a
n
d
P
o
s
t
u
r
e
,
v
o
l
.
8
0
,
p
p
.
1
3
0
–
1
3
6
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
a
i
t
p
o
st
.
2
0
2
0
.
0
5
.
0
2
6
.
[
6
]
O
.
M
.
B
e
i
g
i
,
L.
R
.
N
ó
b
r
e
g
a
,
S
.
H
o
u
g
h
t
e
n
,
A
.
A
.
P
e
r
e
i
r
a
,
a
n
d
A
.
d
e
O
l
i
v
e
i
r
a
A
n
d
r
a
d
e
,
“
F
r
e
e
z
i
n
g
o
f
g
a
i
t
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
:
C
l
a
s
si
f
i
c
a
t
i
o
n
u
s
i
n
g
c
o
m
p
u
t
a
t
i
o
n
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
Bi
o
S
y
s
t
e
m
s
,
v
o
l
.
2
3
2
,
p
.
1
0
5
0
0
6
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
s
y
st
e
ms.
2
0
2
3
.
1
0
5
0
0
6
.
[
7
]
J.
H
a
u
sd
o
r
f
f
,
“
G
a
i
t
i
n
p
a
r
k
i
n
s
o
n
’
s d
i
s
e
a
se
,
”
Ph
y
si
o
n
e
t
,
2
0
0
8
.
h
t
t
p
s:
/
/
p
h
y
s
i
o
n
e
t
.
o
r
g
/
c
o
n
t
e
n
t
/
g
a
i
t
p
d
b
/
1
.
0
.
0
/
.
[
8
]
L.
S
i
g
c
h
a
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
d
e
t
e
c
t
i
n
g
f
r
e
e
z
i
n
g
o
f
g
a
i
t
i
n
p
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
p
a
t
i
e
n
t
s
t
h
r
o
u
g
h
o
n
-
b
o
d
y
a
c
c
e
l
e
r
a
t
i
o
n
s
e
n
so
r
s,
”
S
e
n
s
o
rs (S
w
i
t
ze
rl
a
n
d
)
,
v
o
l
.
2
0
,
n
o
.
7
,
p
.
1
8
9
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
0
7
1
8
9
5
.
[
9
]
J.
C
a
m
p
s
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
f
r
e
e
z
i
n
g
o
f
g
a
i
t
d
e
t
e
c
t
i
o
n
i
n
P
a
r
k
i
n
so
n
’
s
d
i
s
e
a
se
p
a
t
i
e
n
t
s
i
n
t
h
e
i
r
h
o
mes
u
si
n
g
a
w
a
i
s
t
-
w
o
r
n
i
n
e
r
t
i
a
l
mea
su
r
e
me
n
t
u
n
i
t
,
”
K
n
o
w
l
e
d
g
e
-
Ba
s
e
d
S
y
st
e
m
s
,
v
o
l
.
1
3
9
,
p
p
.
1
1
9
–
1
3
1
,
Ja
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
1
7
.
1
0
.
0
1
7
.
[
1
0
]
B
.
V
i
d
y
a
a
n
d
P
.
S
a
si
k
u
mar,
“
P
a
r
k
i
n
so
n
’
s
d
i
se
a
se
d
i
a
g
n
o
si
s
a
n
d
s
t
a
g
e
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
g
a
i
t
s
i
g
n
a
l
a
n
a
l
y
s
i
s
u
s
i
n
g
E
M
D
a
n
d
C
N
N
–
LST
M
n
e
t
w
o
r
k
,
”
E
n
g
i
n
e
e
r
i
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
1
4
,
p
.
1
0
5
0
9
9
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
2
.
1
0
5
0
9
9
.
[
1
1
]
T.
A
ş
u
r
o
ğ
l
u
a
n
d
H
.
O
ğ
u
l
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
p
a
r
k
i
n
s
o
n
’
s
d
i
sea
se
se
v
e
r
i
t
y
a
ssessm
e
n
t
,
”
H
e
a
l
t
h
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
n
o
.
5
,
p
p
.
9
4
3
–
9
5
3
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
5
5
3
-
0
2
2
-
0
0
6
9
8
-
z.
[
1
2
]
Y
.
X
i
a
,
J
.
Z
h
a
n
g
,
Q
.
Y
e
,
N
.
C
h
e
n
g
,
Y
.
Lu
,
a
n
d
D
.
Zh
a
n
g
,
“
E
v
a
l
u
a
t
i
o
n
o
f
d
e
e
p
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
s
f
o
r
d
e
t
e
c
t
i
o
n
o
f
f
r
e
e
z
i
n
g
o
f
g
a
i
t
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
sea
se
p
a
t
i
e
n
t
s,”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pro
c
e
ssi
n
g
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
4
6
,
p
p
.
2
2
1
–
2
3
0
,
S
e
p
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
1
8
.
0
7
.
0
1
5
.
[
1
3
]
M
.
I
.
A
.
S
.
N
.
F
e
r
r
e
i
r
a
,
F
.
A
.
B
a
r
b
i
e
r
i
,
V
.
C
.
M
o
r
e
n
o
,
T
.
P
e
n
e
d
o
,
a
n
d
J.
M
.
R
.
S
.
Ta
v
a
r
e
s,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
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
a
n
d
st
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
se
d
o
n
sp
a
t
i
a
l
-
t
e
mp
o
r
a
l
g
a
i
t
p
a
r
a
m
e
t
e
r
s,”
G
a
i
t
a
n
d
Po
st
u
r
e
,
v
o
l
.
9
8
,
p
p
.
4
9
–
5
5
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
a
i
t
p
o
st
.
2
0
2
2
.
0
8
.
0
1
4
.
[
1
4
]
L.
B
o
r
z
ì
,
L.
S
i
g
c
h
a
,
D
.
R
o
d
r
í
g
u
e
z
-
M
a
r
t
í
n
,
a
n
d
G
.
O
l
m
o
,
“
R
e
a
l
-
t
i
me
d
e
t
e
c
t
i
o
n
o
f
f
r
e
e
z
i
n
g
o
f
g
a
i
t
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
u
si
n
g
mu
l
t
i
-
h
e
a
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
s
a
n
d
a
si
n
g
l
e
i
n
e
r
t
i
a
l
se
n
so
r
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
M
e
d
i
c
i
n
e
,
v
o
l
.
1
3
5
,
p
.
1
0
2
4
5
9
,
Jan
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
t
m
e
d
.
2
0
2
2
.
1
0
2
4
5
9
.
[
1
5
]
M
.
N
i
l
a
s
h
i
e
t
a
l
.
,
“
E
a
r
l
y
d
i
a
g
n
o
si
s
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
:
A
c
o
mb
i
n
e
d
met
h
o
d
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
n
e
u
r
o
-
f
u
z
z
y
t
e
c
h
n
i
q
u
e
s
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
Bi
o
l
o
g
y
a
n
d
C
h
e
m
i
st
r
y
,
v
o
l
.
1
0
2
,
p
.
1
0
7
7
8
8
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
b
i
o
l
c
h
e
m.
2
0
2
2
.
1
0
7
7
8
8
.
[
1
6
]
I
.
N
i
ssar,
W
.
A
.
M
i
r
,
I
z
h
a
r
u
d
d
i
n
,
a
n
d
T.
A
.
S
h
a
i
k
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
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
s
i
s
o
f
p
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
-
a
r
e
v
i
e
w
,
”
2
0
2
1
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s,
I
C
AC
C
S
2
0
2
1
,
p
p
.
8
9
8
–
9
0
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
C
S
5
1
4
3
0
.
2
0
2
1
.
9
4
4
1
8
8
5
.
[
1
7
]
H
.
G
u
n
d
u
z
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
p
a
r
k
i
n
so
n
’
s
d
i
se
a
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
v
o
c
a
l
f
e
a
t
u
r
e
se
t
s,”
I
E
EE
Ac
c
e
s
s
,
v
o
l
.
7
,
p
p
.
1
1
5
5
4
0
–
1
1
5
5
5
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
3
6
5
6
4
.
[
1
8
]
D
.
O
l
i
v
a
r
e
s
e
t
a
l
.
,
“
N
-
M
e
t
h
y
l
D
-
A
sp
a
r
t
a
t
e
(
N
M
D
A
)
r
e
c
e
p
t
o
r
a
n
t
a
g
o
n
i
st
s
a
n
d
me
ma
n
t
i
n
e
t
r
e
a
t
m
e
n
t
f
o
r
a
l
z
h
e
i
mer’
s
d
i
s
e
a
s
e
,
v
a
s
c
u
l
a
r
d
e
me
n
t
i
a
a
n
d
p
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se,
”
C
u
rre
n
t
Al
z
h
e
i
m
e
r
Re
se
a
rc
h
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
7
4
6
–
7
5
8
,
2
0
1
3
,
d
o
i
:
1
0
.
2
1
7
4
/
1
5
6
7
2
0
5
1
2
8
0
1
3
2
2
5
6
4
.
[
1
9
]
G
.
S
.
La
v
a
l
l
e
a
n
d
R
.
R
.
R
o
mer
o
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
P
P
M
I
M
R
I
sca
n
s
w
i
t
h
v
o
x
e
l
-
b
a
se
d
mo
r
p
h
o
m
e
t
r
y
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
o
a
ssi
s
t
i
n
t
h
e
d
i
a
g
n
o
s
i
s
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
ra
m
s
i
n
Bi
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
9
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
mp
b
.
2
0
2
0
.
1
0
5
7
9
3
.
[
2
0
]
O
.
Y
a
ma
n
,
F
.
Er
t
a
m,
a
n
d
T.
Tu
n
c
e
r
,
“
A
u
t
o
ma
t
e
d
P
a
r
k
i
n
so
n
’
s
d
i
s
e
a
se
r
e
c
o
g
n
i
t
i
o
n
b
a
s
e
d
o
n
st
a
t
i
st
i
c
a
l
p
o
o
l
i
n
g
me
t
h
o
d
u
si
n
g
a
c
o
u
s
t
i
c
f
e
a
t
u
r
e
s,
”
M
e
d
i
c
a
l
H
y
p
o
t
h
e
s
e
s
,
v
o
l
.
1
3
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
h
y
.
2
0
1
9
.
1
0
9
4
8
3
.
[
2
1
]
Z.
K
.
S
e
n
t
u
r
k
,
“
Ea
r
l
y
d
i
a
g
n
o
si
s
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
a
l
g
o
r
i
t
h
ms,
”
Me
d
i
c
a
l
H
y
p
o
t
h
e
s
e
s
,
v
o
l
.
1
3
8
,
p
.
1
0
9
6
0
3
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
h
y
.
2
0
2
0
.
1
0
9
6
0
3
.
[
2
2
]
S
.
A
i
c
h
,
H
.
-
C
.
K
i
m,
K
.
Y
o
u
n
g
a
,
K
.
L
.
H
u
i
,
A
.
A
.
A
l
-
A
b
si
,
a
n
d
M
.
S
a
i
n
,
“
A
su
p
e
r
v
i
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
u
s
i
n
g
d
i
f
f
e
r
e
n
t
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
o
n
v
o
i
c
e
d
a
t
a
s
e
t
s
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
p
a
r
k
i
n
s
o
n
’
s
d
i
sea
s
e
,
”
i
n
2
0
1
9
2
1
st
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
AC
T
)
,
F
e
b
.
2
0
1
9
,
v
o
l
.
2
0
1
9
-
F
e
b
r
u
,
p
p
.
1
1
1
6
–
1
1
2
1
,
d
o
i
:
1
0
.
2
3
9
1
9
/
I
C
A
C
T.
2
0
1
9
.
8
7
0
1
9
6
1
.
[
2
3
]
I
.
R
u
st
e
mp
a
si
c
a
n
d
M
.
C
a
n
,
“
D
i
a
g
n
o
s
i
s
o
f
p
a
r
k
i
n
s
o
n
’
s d
i
sea
se
u
si
n
g
f
u
z
z
y
c
-
mea
n
s
c
l
u
st
e
r
i
n
g
a
n
d
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
,
”
S
o
u
t
h
e
a
st
Eu
r
o
p
e
J
o
u
r
n
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
,
n
o
.
1
,
M
a
r
.
2
0
1
3
,
d
o
i
:
1
0
.
2
1
5
3
3
/
s
c
j
o
u
r
n
a
l
.
v
2
i
1
.
4
4
.
[
2
4
]
L.
S
i
l
v
e
i
r
a
-
M
o
r
i
y
a
m
a
e
t
a
l
.
,
“
T
h
e
u
s
e
o
f
sm
e
l
l
i
d
e
n
t
i
f
i
c
a
t
i
o
n
t
e
s
t
s
i
n
t
h
e
d
i
a
g
n
o
si
s
o
f
P
a
r
k
i
n
so
n
’
s
d
i
se
a
se
i
n
B
r
a
z
i
l
,
”
M
o
v
e
m
e
n
t
D
i
so
r
d
e
rs
,
v
o
l
.
2
3
,
n
o
.
1
6
,
p
p
.
2
3
2
8
–
2
3
3
4
,
2
0
0
8
,
d
o
i
:
1
0
.
1
0
0
2
/
md
s
.
2
2
2
4
1
.
[
2
5
]
R
.
P
r
a
sh
a
n
t
h
,
S
.
D
u
t
t
a
R
o
y
,
P
.
K
.
M
a
n
d
a
l
,
a
n
d
S
.
G
h
o
sh
,
“
A
u
t
o
m
a
t
i
c
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
f
o
r
e
a
r
l
y
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
d
i
a
g
n
o
si
s
f
r
o
m
S
P
EC
T
i
m
a
g
i
n
g
,
”
Ex
p
e
r
t
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
1
,
n
o
.
7
,
p
p
.
3
3
3
3
–
3
3
4
2
,
J
u
n
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
3
.
1
1
.
0
3
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ma
la
t
h
i
Ar
u
n
a
c
h
a
l
a
m
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
i
n
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
En
g
i
n
e
e
rin
g
,
u
n
d
e
r
An
a
n
d
In
stit
u
te
o
f
Hig
h
e
r
Tec
h
n
o
lo
g
y
,
Ka
z
h
ip
a
tt
u
r,
Ch
e
n
n
a
i
-
6
0
3
1
0
3
.
S
h
e
h
a
s
re
c
e
iv
e
d
h
e
r
B.
Tec
h
.
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
fro
m
S
RM
Eas
wa
ri
En
g
i
n
e
e
rin
g
Co
ll
e
g
e
i
n
2
0
0
4
.
M
.
Tec
h
.
i
n
C
o
m
p
u
t
e
r
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
fr
o
m
S
R
M
Un
iv
e
rsity
in
2
0
1
3
.
He
r
a
re
a
o
f
i
n
tere
st
a
re
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
d
e
e
p
lea
r
n
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
lath
iaru
n
a
c
h
a
lam
8
3
@g
m
a
il
.
c
o
m
.
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:
2
5
0
2
-
4
7
52
I
mp
r
o
ve
d
B
i
-
GR
U
fo
r
p
a
r
kin
s
o
n
’
s
d
is
ea
s
e
s
ev
erit
y
a
n
a
lysi
s
(
Ma
la
th
i A
r
u
n
a
c
h
a
la
m)
1149
Ra
m
a
la
k
sh
m
i
R
a
m
a
r
re
c
e
iv
e
d
h
e
r
Do
c
t
o
ra
l
d
e
g
re
e
a
n
d
M
a
st
e
r
o
f
En
g
in
e
e
ri
n
g
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ie
n
c
e
a
n
d
En
g
in
e
e
rin
g
.
S
h
e
h
a
s
b
e
e
n
wo
r
k
in
g
i
n
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
in
e
e
rin
g
a
t
Ka
las
a
li
n
g
a
m
Ac
a
d
e
m
y
o
f
Re
se
a
rc
h
a
n
d
Ed
u
c
a
ti
o
n
(P
re
v
io
u
sly
k
n
o
wn
a
s
Aru
lmig
u
K
a
las
a
li
n
g
a
m
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
)
si
n
c
e
2
0
0
1
.
S
h
e
h
a
s
m
o
re
th
a
n
2
4
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rien
c
e
.
S
h
e
is
a
m
e
m
b
e
r
o
f
CS
I,
I
S
TE
,
a
n
d
Ne
two
rk
Tec
h
n
o
l
o
g
y
g
r
o
u
p
o
f
TIF
AC
-
CORE
in
Ne
two
rk
En
g
in
e
e
rin
g
.
S
h
e
h
a
s p
u
b
li
sh
e
d
m
o
re
th
a
n
6
0
re
se
a
rc
h
a
rti
c
les
in
re
p
u
ted
jo
u
rn
a
ls
a
n
d
in
ter
n
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
.
S
h
e
h
a
s
re
c
e
iv
e
d
a
Yo
u
n
g
S
c
ien
ti
st
F
e
ll
o
ws
h
i
p
fro
m
t
h
e
Ta
m
il
n
a
d
u
S
tate
Co
u
n
c
il
fo
r
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
a
n
d
a
n
Aw
a
rd
o
f
E
x
c
e
ll
e
n
c
e
fro
m
S
AP
In
d
ia
P
v
t
.
Li
m
it
e
d
.
He
r
a
re
a
s
o
f
re
se
a
rc
h
in
c
lu
d
e
so
f
twa
re
d
e
fin
e
d
n
e
two
r
k
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
th
e
i
n
tern
e
t
o
f
th
in
g
s,
a
n
d
d
a
ta
a
n
a
l
y
ti
c
s
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
m
a
@k
lu
.
a
c
.
in
.
Va
ib
h
a
v
G
a
n
d
h
i
is
a
d
e
d
ica
ted
e
d
u
c
a
to
r
a
n
d
re
se
a
rc
h
e
r
a
t
M
id
d
les
e
x
Un
i
v
e
rsity
,
sp
e
c
ializin
g
in
Bra
in
-
Co
m
p
u
ter
In
terfa
c
e
a
n
d
a
ss
isti
v
e
ro
b
o
t
ics
.
Wi
th
a
p
a
ss
io
n
fo
r
e
m
p
o
we
rin
g
stu
d
e
n
ts,
h
e
c
u
lt
i
v
a
t
e
s
a
d
y
n
a
m
ic
lea
rn
in
g
e
n
v
iro
n
m
e
n
t
th
a
t
e
n
c
o
u
ra
g
e
s
c
rit
ica
l
th
in
k
in
g
a
n
d
p
ra
c
ti
c
a
l
a
p
p
li
c
a
t
io
n
o
f
k
n
o
wle
d
g
e
.
Va
i
b
h
a
v
’
s
e
x
p
e
rti
se
e
x
ten
d
s
to
t
h
e
e
x
p
lo
ra
ti
o
n
o
f
tec
h
n
o
l
o
g
y
’
s
imp
a
c
t
o
n
so
c
iet
y
,
p
a
rti
c
u
larl
y
in
a
re
a
s
su
c
h
a
s
b
i
o
m
e
d
ica
l
si
g
n
a
l
p
ro
c
e
ss
in
g
,
c
o
m
p
u
tat
io
n
a
l
n
e
u
r
o
sc
ien
c
e
,
a
n
d
u
se
r
-
c
e
n
tri
c
g
ra
p
h
i
c
a
l
u
se
r
in
terfa
c
e
s.
He
i
s
c
o
m
m
it
ted
to
a
d
v
a
n
c
in
g
a
c
a
d
e
m
ic
e
x
c
e
ll
e
n
c
e
th
r
o
u
g
h
in
n
o
v
a
t
iv
e
tea
c
h
in
g
m
e
th
o
d
s
a
n
d
c
o
ll
a
b
o
ra
ti
v
e
re
se
a
rc
h
in
it
iati
v
e
s.
As
a
re
sp
e
c
ted
m
e
m
b
e
r
o
f
th
e
u
n
iv
e
rsit
y
c
o
m
m
u
n
it
y
,
Va
ib
h
a
v
a
c
ti
v
e
l
y
c
o
n
tri
b
u
tes
to
in
terd
isc
ip
li
n
a
ry
p
r
o
jec
ts
a
n
d
fo
s
te
rs
p
a
rtn
e
rsh
ip
s
t
h
a
t
d
r
iv
e
p
o
siti
v
e
c
h
a
n
g
e
.
His
h
o
li
stic
a
p
p
ro
a
c
h
to
e
d
u
c
a
ti
o
n
a
n
d
re
se
a
rc
h
re
flec
ts
a
d
e
e
p
c
o
m
m
it
m
e
n
t
to
p
re
p
a
rin
g
stu
d
e
n
ts
f
o
r
s
u
c
c
e
ss
in
a
n
in
c
re
a
sin
g
l
y
d
ig
it
a
l
wo
rl
d
.
Th
ro
u
g
h
h
is
wo
r
k
,
Va
ib
h
a
v
in
sp
ires
b
o
t
h
stu
d
e
n
ts
a
n
d
c
o
ll
e
a
g
u
e
s
to
p
u
sh
th
e
b
o
u
n
d
a
ries
o
f
k
n
o
wle
d
g
e
a
n
d
m
a
k
e
m
e
a
n
in
g
fu
l
c
o
n
tri
b
u
ti
o
n
s t
o
t
h
e
ir
field
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
V.G
a
n
d
h
i@m
d
x
.
a
c
.
u
k
.
Bh
u
v
a
n
e
sh
Ana
n
t
h
a
n
re
c
e
i
v
e
d
th
e
B.
E.
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
s
En
g
i
n
e
e
rin
g
fr
o
m
An
n
a
Un
i
v
e
rsity
in
2
0
1
2
,
M
.
Tec
h
.
i
n
P
o
we
r
S
y
ste
m
En
g
i
n
e
e
rin
g
fr
o
m
Ka
las
a
li
n
g
a
m
Un
iv
e
rsity
i
n
2
0
1
4
a
n
d
P
h
.
D.
d
e
g
re
e
fro
m
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
o
f
An
n
a
Un
i
v
e
rsity
i
n
2
0
1
9
.
He
h
a
s
ten
y
e
a
rs
o
f
tea
c
h
in
g
a
n
d
re
se
a
rc
h
e
x
p
e
rien
c
e
s.
His
re
se
a
rc
h
in
tere
sts
a
re
in
p
o
we
r
sy
ste
m
s,
e
lec
tri
c
v
e
h
icle
s,
re
n
e
wa
b
le
e
n
e
rg
y
so
u
rc
e
s,
o
p
t
imiz
a
ti
o
n
tec
h
n
iq
u
e
s
a
n
d
a
rti
ficia
l
i
n
telli
g
e
n
c
e
.
He
is
n
o
w
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
,
P
S
N
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
Ti
ru
n
e
l
v
e
l
i,
Tam
il
Na
d
u
,
I
n
d
i
a
.
He
h
a
s
p
u
b
li
s
h
e
d
m
o
re
th
a
n
1
0
0
p
a
p
e
rs
in
r
e
p
u
ted
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls,
6
5
p
a
p
e
rs
in
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
2
0
b
o
o
k
s.
He
is
a
li
fe
t
ime
m
e
m
b
e
r
o
f
I
n
tern
a
ti
o
n
a
l
S
o
c
iet
y
fo
r
Re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
,
I
n
tern
a
ti
o
n
a
l
As
so
c
iati
o
n
o
f
En
g
i
n
e
e
rs.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
h
u
v
a
n
e
sh
.
a
n
a
n
t
h
a
n
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.