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.
3
6
,
No
.
1
,
Octo
b
er
20
24
,
p
p
.
64
~
73
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
1
.
pp
64
-
73
64
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Alzheimer
’
s
p
r
ed
iction v
ia
CNN
-
S
VM
on
cha
tbot
pl
a
tf
o
rm
wit
h
M
RI
M
uh
a
m
m
a
d
Sy
a
eka
r
K
a
da
f
i
1
,
Ahm
a
d K
ha
lil Ya
qu
bi
2
,
P
urba
nd
i
ni
3
,
Su
ry
a
ni Dy
a
h A
s
t
uti
4
1
D
e
p
a
r
t
me
n
t
o
f
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
A
d
v
a
n
c
e
d
a
n
d
M
u
l
t
i
d
i
sc
i
p
l
i
n
a
r
y
Te
c
h
n
o
l
o
g
y
,
A
i
r
l
a
n
g
g
a
U
n
i
v
e
r
s
i
t
y
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
2
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
A
i
r
l
a
n
g
g
a
U
n
i
v
e
r
si
t
y
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
s
i
a
3
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
A
i
r
l
a
n
g
g
a
U
n
i
v
e
r
si
t
y
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
s
i
a
4
D
e
p
a
r
t
me
n
t
o
f
P
h
y
s
i
c
s,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
A
i
r
l
a
n
g
g
a
U
n
i
v
e
r
si
t
y
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
12
,
2
0
2
4
R
ev
is
ed
Ma
y
13
,
2
0
2
4
Acc
ep
ted
J
u
n
5
,
2
0
2
4
Artifi
c
ial
in
tell
ig
e
n
c
e
(AI)
,
c
o
n
si
stin
g
o
f
m
o
d
e
ls
a
n
d
a
l
g
o
rit
h
m
s
c
a
p
a
b
le
o
f
c
o
n
c
lu
d
in
g
d
a
ta
t
o
p
ro
d
u
c
e
f
u
tu
r
e
p
re
d
icti
o
n
s,
h
a
s
re
v
o
l
u
ti
o
n
a
ry
p
o
ten
ti
a
l
in
v
a
rio
u
s
a
s
p
e
c
ts
o
f
h
u
m
a
n
l
ife.
On
e
a
p
p
li
c
a
ti
o
n
is
a
n
Alz
h
e
ime
r
’
s
d
ise
a
se
(AD
)
p
re
d
ictio
n
c
h
a
t
ro
b
o
t
(
c
h
a
tb
o
t
)
.
On
l
y
n
o
w
h
a
s
a
m
e
t
h
o
d
p
r
o
v
id
e
d
v
e
ry
a
c
c
u
ra
te
fin
d
in
g
s
a
n
d
re
c
o
m
m
e
n
d
a
ti
o
n
s
re
g
a
rd
i
n
g
th
e
e
a
rly
d
e
tec
t
io
n
o
f
AD
u
sin
g
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
ima
g
i
n
g
(
M
RI
)
.
T
h
e
re
fo
re
,
t
h
is
re
se
a
rc
h
a
ims
to
m
e
a
su
re
AD
p
re
d
ictio
n
p
e
rfo
rm
a
n
c
e
in
fo
u
r
sta
g
e
c
las
se
s,
n
a
m
e
ly
v
e
ry
m
il
d
d
e
m
e
n
ted
,
m
il
d
d
e
m
e
n
ted
,
m
o
d
e
ra
te
d
e
m
e
n
ted
,
a
n
d
n
o
n
-
d
e
m
e
n
ted
,
u
si
n
g
b
ra
in
M
RI
ima
g
e
s
train
e
d
in
t
h
e
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
r
k
(
CNN
)
-
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
(
S
VM
)
m
o
d
e
l.
T
h
e
re
se
a
rc
h
in
v
o
lv
e
d
n
in
e
c
o
m
b
in
a
ti
o
n
sc
h
e
m
e
s
o
f
d
a
tas
e
t
p
ro
p
o
rti
o
n
s
a
n
d
p
re
p
r
o
c
e
ss
in
g
in
th
e
CNN
-
SV
M
m
o
d
e
l.
E
v
a
lu
a
ti
o
n
sh
o
ws
th
a
t
sc
h
e
m
e
1
p
r
o
d
u
c
e
s
th
e
h
ig
h
e
st ac
c
u
ra
c
y
,
p
re
c
isio
n
,
re
c
a
ll
,
a
n
d
F
1
-
s
c
o
re
,
n
a
m
e
ly
9
8
%
,
9
9
%
,
9
8
%
,
a
n
d
9
8
%
.
T
h
e
c
h
a
tb
o
t,
trai
n
e
d
u
sin
g
CNN
,
a
c
h
iev
e
d
9
9
.
3
4
%
a
c
c
u
ra
c
y
in
q
u
e
stio
n
re
sp
o
n
se
s,
a
n
d
wa
s
th
e
n
c
o
m
b
in
e
d
with
AD
p
re
d
icti
o
n
m
o
d
e
ls
fo
r
imp
ro
v
e
d
a
c
c
u
ra
c
y
.
Th
e
tes
t
re
su
lt
s
s
h
o
w
t
h
a
t
t
h
e
c
h
a
tb
o
t
fu
n
c
ti
o
n
a
li
ty
ru
n
s
we
ll
fo
r
e
a
c
h
tran
siti
o
n
,
with
a
f
u
n
c
ti
o
n
a
li
ty
sc
o
re
re
a
c
h
in
g
9
9
.
6
4
p
o
in
ts
o
u
t
o
f
1
0
0
.
0
0
.
T
h
is
su
c
c
e
ss
sh
o
ws
e
x
c
e
ll
e
n
t
p
o
ten
ti
a
l
fo
r
e
a
rl
y
d
e
tec
ti
o
n
o
f
AD
.
Th
is
re
se
a
rc
h
b
ri
n
g
s
n
e
w
h
o
p
e
i
n
p
re
v
e
n
t
in
g
AD
t
h
ro
u
g
h
AI,
wi
th
p
o
ten
ti
a
l
p
o
siti
v
e
imp
a
c
ts o
n
h
u
m
a
n
h
e
a
lt
h
a
n
d
q
u
a
li
t
y
o
f
li
fe
.
K
ey
w
o
r
d
s
:
Alzh
eim
er
d
is
ea
s
e
C
h
at
r
o
b
o
t
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Ma
g
n
etic
r
eso
n
an
ce
im
a
g
in
g
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Su
r
y
an
i D
y
ah
Ast
u
ti
Dep
ar
tm
en
t o
f
Ph
y
s
ics,
Facu
lty
o
f
Scien
ce
a
n
d
T
ec
h
n
o
lo
g
y
,
Air
lan
g
g
a
Un
iv
e
r
s
ity
Su
r
ab
ay
a,
I
n
d
o
n
esia
E
m
ail: su
r
y
an
id
y
a
h
@
f
s
t.u
n
air
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Ar
tific
ial
in
tellig
en
ce
(
AI
)
in
m
ed
icin
e
p
r
o
life
r
ates,
p
r
o
v
i
d
in
g
p
h
y
s
ician
s
with
n
ew
to
o
ls
to
o
f
f
er
b
etter
p
atien
t
ca
r
e
r
ec
o
m
m
en
d
atio
n
s
,
d
iag
n
o
s
tic
ass
is
tan
ce
,
tr
ea
tm
en
t
s
u
g
g
esti
o
n
s
,
an
d
th
e
latest
m
ed
ical
k
n
o
wled
g
e
[
1
]
.
AI
,
wh
ich
c
o
n
s
is
t
s
o
f
m
o
d
els
an
d
al
g
o
r
ith
m
s
ca
p
ab
le
o
f
co
n
cl
u
d
in
g
ex
is
tin
g
d
ata
to
p
r
o
d
u
ce
f
u
tu
r
e
p
r
e
d
ictio
n
s
[
2
]
,
h
as
th
e
p
o
ten
tial
to
r
ev
o
lu
tio
n
ize
m
an
y
asp
ec
ts
o
f
o
u
r
liv
es
[
3
]
.
AI
-
d
r
iv
en
m
eth
o
d
s
ca
n
p
o
ten
tially
en
h
a
n
ce
th
e
p
r
o
g
n
o
s
is
an
d
tr
ea
tm
en
t
o
f
Alzh
eim
er
’
s
d
is
ea
s
e
(
AD)
.
E
n
h
an
ci
n
g
e
ar
ly
id
en
tific
atio
n
o
f
AD
m
ay
im
p
r
o
v
e
p
atien
t
o
u
tco
m
es
an
d
q
u
ality
o
f
li
f
e
b
y
u
s
in
g
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
an
d
in
co
r
p
o
r
atin
g
c
h
at
r
o
b
o
t
(
C
h
atb
o
ts
)
.
T
o
f
u
lly
f
u
lf
ill
AI
’
s
p
r
o
m
is
e
in
tack
lin
g
th
is
u
r
g
e
n
t
h
ea
lth
ca
r
e
is
s
u
e,
h
o
wev
er
,
f
u
tu
r
e
r
esear
c
h
m
u
s
t
c
o
n
ce
n
tr
ate
o
n
v
alid
atio
n
,
l
o
n
g
itu
d
in
al
s
tu
d
ies,
eth
ical
is
s
u
es,
u
s
er
ex
p
er
ien
ce
,
an
d
m
u
ltid
is
cip
lin
ar
y
c
o
o
p
e
r
a
tio
n
.
C
h
atb
o
t,
o
n
e
o
f
th
e
m
an
y
ap
p
licatio
n
s
o
f
AI
,
is
a
v
ir
tu
al
co
n
v
er
s
atio
n
al
ag
en
t
th
at
allo
ws
u
s
er
s
to
e
n
g
ag
e
with
AI
-
b
ased
co
m
p
u
t
er
p
r
o
g
r
am
s
t
h
r
o
u
g
h
v
o
ice
o
r
wr
itin
g
[
4
]
,
[
5
]
.
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
A
lz
h
eime
r
’
s
p
r
ed
ictio
n
via
C
N
N
-
S
V
M o
n
ch
a
tb
o
t p
la
tfo
r
m
w
ith
MRI
(
Mu
h
a
mma
d
S
ya
ek
a
r
K
a
d
a
fi
)
65
R
ec
en
tly
,
ch
atb
o
ts
h
av
e
b
ee
n
lau
n
ch
ed
in
v
a
r
io
u
s
f
ield
s
,
in
clu
d
in
g
b
u
s
in
ess
,
r
etail,
an
d
s
er
v
ices
s
u
ch
as
h
ea
lth
ca
r
e
[
6
]
–
[
9
]
.
E
x
is
tin
g
r
e
s
ea
r
ch
h
as
d
em
o
n
s
tr
ated
th
e
e
f
f
ec
tiv
en
ess
o
f
m
ed
ical
ch
atb
o
ts
in
ac
tiv
ities
s
u
ch
as
e
n
s
u
r
in
g
p
r
o
p
er
m
ed
icatio
n
ad
h
er
en
ce
.
C
an
ce
r
p
atien
t
s
atis
f
ac
tio
n
h
as
b
ee
n
s
h
o
w
n
to
i
n
cr
ea
s
e
af
ter
co
n
v
er
s
atio
n
s
with
ch
atb
o
ts
.
I
n
ter
ac
tin
g
with
an
em
p
ath
et
ic
ch
atb
o
t
h
as
a
m
itig
atin
g
im
p
ac
t
o
n
p
atien
ts
’
m
en
tal
h
ea
lth
[
9
]
.
I
n
ter
ac
tio
n
s
with
m
ed
ical
ch
atb
o
ts
r
e
d
u
ce
d
s
y
m
p
to
m
s
o
f
h
o
p
eless
n
ess
an
d
an
x
iety
[
1
0
]
,
wh
ile
m
ed
ical
ch
atb
o
ts
co
r
r
ec
tly
id
en
tifie
d
m
o
r
e
th
a
n
9
6
%
o
f
in
f
ec
ted
p
atien
ts
d
u
r
i
n
g
th
e
C
OVI
D
-
19
p
an
d
em
ic
[
1
1
]
.
T
h
e
b
u
r
d
en
o
n
h
ea
lth
ca
r
e
p
r
ac
titi
o
n
er
s
c
an
b
e
r
e
d
u
ce
d
an
d
s
im
p
lifie
d
with
th
e
h
elp
o
f
m
ed
i
ca
l c
h
atb
o
ts
[
1
2
]
,
s
u
c
h
as AD
p
r
ed
ictio
n
c
h
atb
o
ts
.
AD
is
a
d
eg
en
er
ativ
e
b
r
ai
n
d
is
ea
s
e
th
at
ca
u
s
es
m
em
o
r
y
lo
s
s
an
d
co
g
n
itiv
e
im
p
air
m
e
n
t,
in
clu
d
in
g
d
if
f
icu
lty
s
p
ea
k
in
g
,
th
in
k
in
g
,
an
d
co
m
p
letin
g
task
s
.
AD
wa
s
n
am
ed
af
ter
Alo
is
Alzh
eim
e
r
,
wh
o
d
is
co
v
er
e
d
it
f
ir
s
t
in
1
9
0
6
[
1
3
]
.
AD
ca
u
s
es
6
0
–
8
0
%
o
f
all
d
em
en
tia
ca
s
es
[
1
4
]
.
I
n
2
0
2
0
,
ap
p
r
o
x
im
ately
5
7
.
4
m
illi
o
n
p
eo
p
le
wer
e
d
iag
n
o
s
ed
with
d
em
en
ti
a
[
1
5
]
.
I
n
o
th
er
wo
r
d
s
,
2
o
u
t
o
f
3
p
eo
p
le
with
d
e
m
en
tia
h
a
v
e
AD.
T
h
e
in
cr
ea
s
e
in
th
e
n
u
m
b
er
o
f
AD
s
u
f
f
er
er
s
is
esti
m
ated
to
r
ea
ch
1
5
2
m
illi
o
n
b
y
2
0
5
0
[
1
6
]
.
I
n
d
i
v
id
u
a
ls
af
f
ec
ted
b
y
AD
ex
p
er
ien
ce
a
s
ev
er
e
d
ec
lin
e
in
co
g
n
itiv
e
f
u
n
ctio
n
,
an
d
th
is
h
as
a
s
ig
n
if
ican
t
im
p
ac
t
o
n
th
eir
q
u
ality
o
f
life
an
d
g
en
er
al
h
ea
lth
[
1
4
]
.
I
n
ad
d
itio
n
,
th
e
av
er
ag
e
life
s
p
a
n
o
f
Alz
h
eim
er
’
s
s
u
f
f
er
er
s
af
t
er
d
ia
g
n
o
s
is
is
7
.
6
y
ea
r
s
an
d
5
.
8
y
ea
r
s
[
1
7
]
.
Mild
co
g
n
itiv
e
im
p
air
m
en
t
(
MCI)
is
a
p
r
o
m
is
in
g
s
tag
e
b
ec
au
s
e
it
is
s
ti
ll
in
th
e
p
r
ec
lin
ical
s
tag
es
o
f
AD,
s
er
v
i
n
g
as
a
n
ic
h
e
tar
g
et
f
o
r
ea
r
ly
tr
ea
tm
en
t
with
th
e
p
o
ten
tial
to
s
to
p
o
r
s
l
o
w
th
e
p
r
o
g
r
ess
io
n
o
f
AD
[
1
8
]
.
T
h
is
s
u
g
g
ests
th
at
MCI
is
an
ef
f
ec
tiv
e
ea
r
ly
-
s
tag
e
in
ter
v
en
tio
n
to
r
ev
er
s
e
o
r
h
alt
th
e
p
ath
o
lo
g
ical
p
r
o
g
r
ess
io
n
o
f
AD.
Ma
g
n
etic
r
eso
n
an
ce
im
ag
in
g
(
MRI)
ca
n
p
r
o
v
i
d
e
co
m
p
r
eh
en
s
iv
e
3
D
im
ag
es
o
f
in
ter
n
al
b
o
d
y
co
m
p
o
n
en
ts
s
u
ch
as
th
e
b
r
ain
[
1
9
]
.
MRI
h
as
b
ee
n
wid
ely
u
s
ed
t
o
u
n
d
er
s
tan
d
m
o
r
p
h
o
lo
g
ical
a
n
d
f
u
n
ctio
n
al
b
r
ai
n
ch
an
g
es
in
v
iv
o
,
in
clu
d
in
g
AD
[
20
]
,
s
ch
iz
o
p
h
r
e
n
ia
[
2
1
]
,
an
d
o
th
e
r
s
.
T
h
er
ef
o
r
e,
s
tr
u
ctu
r
e
d
MRI
ca
n
p
r
o
v
id
e
i
n
f
o
r
m
atio
n
ab
o
u
t
th
e
b
r
ain
’
s
an
ato
m
ical
s
tr
u
ctu
r
e,
aid
in
g
in
d
etec
tin
g
an
d
m
ea
s
u
r
in
g
AD
b
r
ain
s
h
r
in
k
ag
e
p
atter
n
s
[
2
2
]
.
T
h
is
wo
r
k
ex
p
an
d
s
o
n
ea
r
lier
s
tu
d
ies
th
at
u
s
ed
b
r
ain
MRI
i
m
ag
in
g
an
d
m
ac
h
i
n
e
lear
n
in
g
to
f
o
r
ec
ast
th
e
o
n
s
et
o
f
AD
.
Fo
r
im
p
r
o
v
ed
p
r
e
d
ictio
n
ac
cu
r
ac
y
,
it
c
o
m
b
in
es
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN
)
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM
)
alg
o
r
ith
m
s
in
a
n
o
v
el
way
in
s
id
e
a
ch
atb
o
t
p
latf
o
r
m
.
I
t
also
lo
o
k
s
at
h
o
w
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
af
f
ec
t
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el.
I
n
g
en
er
al,
it
ad
v
an
ce
s
th
e
ar
ea
o
f
AI
in
h
ea
lth
ca
r
e
b
y
in
v
esti
g
atin
g
cu
ttin
g
-
ed
g
e
m
et
h
o
d
s
f
o
r
im
p
r
o
v
in
g
p
atien
t
c
ar
e
an
d
ea
r
ly
AD
d
iag
n
o
s
is
.
T
h
e
s
tu
d
y
r
ec
o
m
m
e
n
d
s
in
v
e
s
tig
atin
g
o
th
er
d
ata
m
o
d
alities
b
esid
es
M
R
I
im
ag
es
to
i
m
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
a
n
d
c
o
m
p
r
e
h
en
d
th
e
co
u
r
s
e
o
f
AD.
Pre
d
ictiv
e
m
o
d
els
m
ay
b
e
im
p
r
o
v
ed
,
an
d
ea
r
ly
b
io
m
a
r
k
er
s
ca
n
b
e
f
o
u
n
d
th
r
o
u
g
h
lo
n
g
itu
d
in
al
r
esear
ch
.
I
t
is
ess
en
tial
to
v
al
id
ate
th
e
m
o
d
el
o
n
v
a
r
io
u
s
d
a
tasets
an
d
en
h
an
ce
its
in
ter
p
r
etab
ilit
y
.
I
n
teg
r
atin
g
p
atien
t
v
iewp
o
in
ts
an
d
ad
d
r
e
s
s
in
g
eth
ical
is
s
u
es
ar
e
es
s
en
tial
f
o
r
tr
an
s
latio
n
in
to
th
er
ap
eu
tic
p
r
ac
tice.
T
o
ad
v
an
ce
r
esear
ch
o
n
A
D
p
r
ed
ict
io
n
an
d
en
h
an
ce
p
atien
t
o
u
tco
m
es,
in
ter
d
is
cip
lin
ar
y
co
o
p
er
atio
n
,
an
d
f
in
an
cin
g
ar
e
cr
u
cial.
T
h
e
p
o
s
s
ib
ilit
y
o
f
f
o
r
ec
asti
n
g
th
e
co
u
r
s
e
o
f
AD
b
y
co
m
b
in
in
g
b
r
ain
MRI
im
a
g
e
p
r
o
ce
s
s
in
g
with
a
C
NN
-
SVM
m
o
d
el
is
s
h
o
wn
in
th
is
s
tu
d
y
.
T
h
e
m
o
d
el
attain
s
g
o
o
d
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
m
etr
ics,
esp
ec
ially
wh
en
r
esizin
g
an
d
r
escalin
g
MRI
im
ag
es,
b
y
ass
ess
in
g
d
if
f
er
en
t
p
r
ep
r
o
c
ess
in
g
p
r
o
ce
d
u
r
es
an
d
d
ataset
p
r
o
p
o
r
tio
n
s
.
Fo
r
p
e
o
p
le
lo
o
k
i
n
g
f
o
r
in
f
o
r
m
ati
o
n
ab
o
u
t
AD,
in
teg
r
atin
g
th
is
p
ar
ad
i
g
m
in
t
o
a
ch
atb
o
t
p
la
tf
o
r
m
im
p
r
o
v
es
ac
ce
s
s
ib
ilit
y
an
d
u
s
ab
ilit
y
.
No
n
eth
eless
,
m
o
r
e
v
er
if
icatio
n
an
d
m
o
r
al
d
elib
er
atio
n
s
a
r
e
r
eq
u
i
r
ed
t
o
g
u
ar
an
tee
th
e
m
o
d
el
’
s
d
ep
e
n
d
ab
ilit
y
an
d
m
o
r
al
u
s
e
i
n
th
e
m
ed
ical
f
ield
.
T
h
is
s
tu
d
y
em
p
h
asizes
h
o
w
cr
u
cial
AI
-
d
r
i
v
en
m
eth
o
d
s
ar
e
f
o
r
ea
r
l
y
AD
d
iag
n
o
s
is
an
d
p
atien
t
tr
ea
tm
en
t.
T
h
is
s
tu
d
y
aim
ed
to
ass
ess
th
e
u
tili
ty
o
f
m
ac
h
in
e
le
ar
n
in
g
(
ML
)
-
b
ased
class
if
icatio
n
alg
o
r
ith
m
s
in
o
v
er
co
m
in
g
lim
itin
g
f
ac
to
r
s
ass
o
ciate
d
with
th
e
p
at
h
o
lo
g
ical
d
i
f
f
er
en
tiatio
n
o
f
t
h
e
v
ar
io
u
s
s
tag
es
in
v
o
lv
ed
in
t
h
e
AD
d
ev
elo
p
m
en
tal
p
r
o
ce
s
s
.
ML
an
d
m
u
ltiv
ar
iate
p
atter
n
an
aly
s
is
ar
e
p
o
wer
f
u
l
co
n
v
en
tio
n
al
to
o
ls
f
o
r
b
u
ild
in
g
im
ag
e
-
b
ased
p
r
e
d
ictiv
e
m
o
d
els
in
co
m
p
u
ter
-
ass
is
ted
d
iag
n
o
s
tics
[
2
3
].
T
h
e
r
esear
ch
u
s
es
a
Kag
g
le
d
ataset
an
d
a
co
llectio
n
o
f
ch
atb
o
t
q
u
er
ies
f
o
r
AD
p
r
ed
ictio
n
.
T
h
e
ass
ess
m
en
t
p
r
o
ce
d
u
r
e
in
clu
d
es
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es,
s
ev
er
al
d
ata
d
iv
is
io
n
s
,
an
d
b
lack
b
o
x
test
in
g
.
T
h
e
im
p
licatio
n
s
s
u
g
g
est
f
u
r
th
er
r
esear
ch
in
to
o
p
tim
izatio
n
,
eth
ical
co
n
ce
r
n
s
,
an
d
p
o
s
s
ib
le
th
er
ap
eu
tic
ap
p
licatio
n
s
.
T
h
is
r
esear
ch
d
esig
n
b
e
g
in
s
with
im
p
lem
en
tin
g
an
ML
alg
o
r
it
h
m
th
at
r
ec
eiv
es
b
r
ain
MRI
d
ata
f
r
o
m
p
atien
ts
d
iag
n
o
s
ed
with
AD
an
d
b
r
ai
n
MRI
d
ata
f
r
o
m
h
ea
lth
y
p
a
tien
ts
.
Af
ter
th
at,
ML
p
r
ep
r
o
ce
s
s
es
th
e
d
ata
to
id
en
tify
th
e
m
o
s
t
s
ig
n
if
ican
t
f
ea
tu
r
e
d
if
f
er
e
n
ce
s
b
etwe
en
th
e
two
p
atien
t
g
r
o
u
p
s
.
T
h
e
n
e
x
t
s
tep
is
to
in
teg
r
ate
th
e
ch
atb
o
t
with
ML
alg
o
r
ith
m
s
,
allo
win
g
th
e
ch
atb
o
t
to
p
r
ed
ict
a
p
er
s
o
n
’
s
lik
elih
o
o
d
o
f
d
ev
elo
p
in
g
AD
b
ased
o
n
b
r
ain
MRI
d
ata
p
r
o
v
i
d
ed
b
y
th
e
u
s
er
.
2.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
DS
T
h
is
r
esear
ch
u
tili
ze
s
th
e
Alzh
eim
er
’
s
d
ataset
(
4
class
es o
f
I
m
ag
es)
f
r
o
m
Ka
g
g
le,
co
n
s
is
tin
g
o
f
6
,
4
0
0
MRI
im
ag
es
as
X1
.
T
h
e
d
atas
et
in
clu
d
es
t
h
e
f
o
u
r
in
itial
s
ta
g
es
o
f
AD
in
th
e
f
o
r
m
o
f
1
-
s
lice
co
r
o
n
al
o
r
a
x
ial
im
ag
es,
co
m
p
r
is
in
g
n
o
n
-
d
em
en
ted
,
v
er
y
m
ild
d
em
e
n
ted
,
m
ild
d
em
en
ted
,
an
d
m
o
d
er
at
e
d
em
e
n
ted
s
tag
es.
Deta
iled
in
f
o
r
m
atio
n
r
eg
ar
d
in
g
th
is
r
esear
ch
m
ater
ial
ca
n
b
e
f
o
u
n
d
in
T
a
b
le
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
64
-
73
66
T
h
e
Kag
g
le
Alzh
eim
er
’
s
d
ataset,
wh
ich
co
n
s
is
ts
o
f
6
,
4
0
0
MRI
p
ictu
r
es
d
iv
id
ed
in
to
f
o
u
r
s
tag
es
o
f
AD,
is
u
s
ed
in
th
e
ex
p
er
im
en
tal
s
etu
p
.
T
h
er
e
is
a
4
0
-
item
ch
atb
o
t
q
u
esti
o
n
lis
t
d
iv
id
e
d
i
n
to
s
ix
ca
teg
o
r
ies.
T
h
r
ee
ap
p
r
o
ac
h
es
ar
e
u
s
ed
to
ev
alu
ate
th
e
AD
p
r
ed
ictio
n
alg
o
r
ith
m
,
with
d
ata
d
iv
is
io
n
an
d
p
r
e
p
ar
atio
n
d
if
f
er
en
ce
s
.
T
h
er
e
ar
e
n
in
e
d
if
f
er
en
t
ass
ess
m
en
t
s
ch
em
es
u
s
ed
.
B
lack
b
o
x
test
in
g
ev
alu
ates
th
e
ch
atb
o
t
’
s
f
u
n
ctio
n
ality
u
s
in
g
th
e
s
tate
tr
an
s
itio
n
ap
p
r
o
ac
h
.
T
h
is
th
o
r
o
u
g
h
tech
n
iq
u
e
aim
s
to
co
m
p
r
eh
e
n
d
ch
atb
o
t
r
eliab
ilit
y
an
d
alg
o
r
ith
m
ic
m
o
d
el
p
er
f
o
r
m
an
ce
in
AD
p
r
ed
ic
tio
n
.
A
cu
r
ated
q
u
esti
o
n
lis
t
is
g
en
er
ated
f
o
r
th
e
ch
atb
o
t,
in
cl
u
d
in
g
m
an
y
AD
-
r
elate
d
s
u
b
jects.
T
h
e
alg
o
r
ith
m
’
s
p
er
f
o
r
m
a
n
ce
is
m
ea
s
u
r
ed
u
s
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
m
etr
ics,
with
ass
ess
m
en
t
d
o
n
e
v
ia
m
u
ltip
le
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es
an
d
d
a
t
a
s
et
p
r
o
p
o
r
t
i
o
n
s
.
T
h
e
d
a
t
ase
t
’
s
d
i
s
t
r
i
b
u
t
i
o
n
a
n
d
t
h
e
q
u
e
s
t
io
n
s
’
c
l
as
s
i
f
i
c
at
i
o
n
a
r
e
d
e
s
c
r
i
b
ed
i
n
T
a
b
l
es
1
a
n
d
2,
r
esp
ec
tiv
ely
.
Data
f
o
r
a
q
u
esti
o
n
lis
t
is
also
n
ee
d
ed
t
o
d
e
v
elo
p
a
ch
at
b
o
t
tex
t
-
p
r
o
ce
s
s
in
g
m
o
d
el.
T
h
e
ch
atb
o
t
q
u
esti
o
n
lis
t
co
n
s
is
ts
o
f
s
ix
s
ec
tio
n
s
,
in
v
o
lv
in
g
d
ialo
g
u
e,
ess
en
tial,
r
is
k
,
d
iet,
k
ee
p
i
n
g
ac
tiv
e,
an
d
o
th
e
r
m
ed
ical,
with
4
0
q
u
esti
o
n
s
.
T
h
e
last
f
iv
e
s
ec
tio
n
s
o
f
t
h
is
q
u
esti
o
n
n
air
e
a
r
e
s
o
u
r
ce
d
f
r
o
m
[
2
4
]
,
[2
5
]
.
E
v
alu
atio
n
o
f
th
e
f
o
u
r
m
ain
m
etr
ics in
clas
s
if
icatio
n
,
n
am
ely
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
will b
e
ca
r
r
ied
o
u
t
s
ee
in
T
ab
le
2
.
T
ab
le
1
.
R
esear
ch
m
ater
ials
S
t
a
g
e
s
o
f
A
D
N
u
mb
e
r
o
f
i
m
a
g
e
s
N
o
n
-
d
e
m
e
n
t
e
d
3
,
2
0
0
V
e
r
y
m
i
l
d
d
e
m
e
n
t
e
d
2
,
2
4
0
M
i
l
d
d
e
me
n
t
e
d
8
9
6
M
o
d
e
r
a
t
e
d
e
me
n
t
e
d
64
To
t
a
l
6
,
4
0
0
T
ab
le
2
.
Nu
m
b
er
o
f
q
u
esti
o
n
s
D
i
a
l
o
g
B
a
si
c
R
i
s
k
D
i
e
t
K
e
e
p
i
n
g
a
c
t
i
v
e
O
t
h
e
r
m
e
d
i
c
a
l
12
8
2
10
2
6
T
h
e
AD
p
r
ed
ictio
n
alg
o
r
ith
m
s
y
s
tem
will
b
e
ev
alu
ated
th
r
o
u
g
h
th
r
ee
d
if
f
er
en
t
m
et
h
o
d
s
.
First,
th
e
alg
o
r
ith
m
m
o
d
el
will
b
e
e
v
alu
ated
with
o
u
t
p
r
ep
r
o
ce
s
s
in
g
.
Seco
n
d
,
ev
alu
atio
n
will
b
e
ca
r
r
ied
o
u
t
o
n
t
h
e
alg
o
r
ith
m
m
o
d
el
with
f
ir
s
t
-
o
r
d
er
p
r
ep
r
o
ce
s
s
in
g
,
n
am
ely
r
e
s
izin
g
an
d
r
esc
alin
g
.
Fin
ally
,
alg
o
r
ith
m
m
o
d
el
s
with
s
ec
o
n
d
-
o
r
d
er
p
r
ep
r
o
ce
s
s
in
g
,
n
am
ely
r
esc
alin
g
a
n
d
r
e
s
izin
g
,
will
also
b
e
ev
alu
ate
d
.
Var
iatio
n
s
in
th
e
p
r
o
p
o
r
tio
n
o
f
tr
ain
in
g
:
test
in
g
d
ata
d
iv
is
io
n
,
n
am
ely
6
0
%:2
0
%,
4
5
%:4
0
%,
an
d
3
7
.
5
%:5
0
%,
will
b
e
ex
p
lo
r
ed
in
th
e
ev
alu
atio
n
.
I
t
is
h
o
p
ed
th
at
th
e
r
esu
lts
o
f
th
is
s
y
s
tem
ev
alu
atio
n
ca
n
p
r
o
v
id
e
leg
i
tim
ac
y
to
th
e
r
eliab
i
lity
o
f
th
e
alg
o
r
ith
m
m
o
d
el
in
m
a
k
in
g
p
r
ed
ictio
n
s
r
elate
d
to
Alzh
eim
er
’
s
.
T
h
is
c
o
m
p
r
e
h
en
s
iv
e
ev
alu
atio
n
aim
s
t
o
p
r
o
v
id
e
ess
en
tial
in
s
ig
h
ts
in
to
th
e
p
er
f
o
r
m
an
ce
an
d
ef
f
ec
t
iv
en
ess
o
f
alg
o
r
ith
m
ic
m
o
d
els
in
th
e
co
n
tex
t
o
f
Alzh
eim
er
’
s
p
r
ed
i
ctio
n
.
I
n
ad
d
itio
n
,
a
ta
b
le
th
at
in
cl
u
d
es
th
e
m
o
d
el
e
v
alu
atio
n
s
ch
em
e
is
p
r
esen
ted
to
p
r
o
v
id
e
a
m
o
r
e
d
etailed
u
n
d
e
r
s
tan
d
in
g
.
T
ab
le
3
was
d
esig
n
ed
b
y
co
n
s
id
er
in
g
th
r
ee
d
ataset
p
r
o
p
o
r
t
io
n
s
an
d
p
r
ep
r
o
ce
s
s
es
u
s
ed
in
th
e
d
ata
p
r
o
ce
s
s
in
g
.
T
h
e
u
s
e
o
f
th
r
ee
p
r
o
p
o
r
tio
n
s
o
f
d
atasets
p
r
o
v
id
es
th
e
d
iv
er
s
ity
n
ec
ess
ar
y
to
tr
ai
n
,
test
,
a
n
d
v
alid
ate
th
e
m
o
d
el
well.
Me
an
wh
ile,
th
e
th
r
ee
p
r
ep
r
o
ce
s
s
in
g
s
tag
es
m
en
tio
n
ed
in
clu
d
e
cr
itical
s
tep
s
in
p
r
ep
ar
in
g
th
e
d
ata
b
ef
o
r
e
i
n
p
u
t
in
to
th
e
m
o
d
el.
B
y
d
etai
lin
g
th
e
m
o
d
el
e
v
alu
atio
n
s
c
h
em
e,
r
ea
d
e
r
s
ca
n
u
n
d
er
s
tan
d
t
h
at
th
e
ev
al
u
atio
n
r
esu
lts
ar
e
b
ased
o
n
a
t
h
o
r
o
u
g
h
an
d
a
p
p
r
o
p
r
iate
f
r
am
ewo
r
k
.
T
ab
le
3
.
L
is
t o
f
s
y
s
tem
ev
al
u
a
tio
n
s
ch
em
es
N
a
me
D
a
t
a
s
e
t
p
r
o
p
o
r
t
i
o
n
P
r
e
p
r
o
c
e
ss
S
c
h
e
me
1
Tr
a
i
n
6
0
%:
t
e
s
t
2
0
%
:
v
a
l
i
d
2
0
%
N
o
p
r
e
p
r
o
c
e
ssi
n
g
S
c
h
e
me
2
Tr
a
i
n
4
5
%:
t
e
s
t
4
0
%
:
v
a
l
i
d
1
5
%
S
c
h
e
me
3
Tr
a
i
n
3
7
.
5
%:
t
e
s
t
5
0
%
:
v
a
l
i
d
1
2
.
5
%
S
c
h
e
me
4
Tr
a
i
n
6
0
%:
t
e
s
t
2
0
%
:
v
a
l
i
d
2
0
%
P
r
e
p
r
o
c
e
ss
1
:
r
e
s
c
a
l
e
(
0
-
1
)
a
n
d
r
e
si
z
e
(
1
5
0
×
1
5
0
)
S
c
h
e
me
5
Tr
a
i
n
4
5
%:
t
e
s
t
4
0
%
:
v
a
l
i
d
1
5
%
S
c
h
e
me
6
Tr
a
i
n
3
7
.
5
%:
t
e
s
t
5
0
%
:
v
a
l
i
d
1
2
.
5
%
S
c
h
e
me
7
Tr
a
i
n
6
0
%:
t
e
s
t
2
0
%
:
v
a
l
i
d
2
0
%
P
r
e
p
r
o
c
e
ss
2
:
r
e
s
i
z
e
(
1
5
0
×
1
5
0
)
a
n
d
r
e
sca
l
e
(0
-
1)
S
c
h
e
me
8
Tr
a
i
n
4
5
%:
t
e
s
t
4
0
%
:
v
a
l
i
d
1
5
%
S
c
h
e
me
9
Tr
a
i
n
3
7
.
5
%:
t
e
s
t
5
0
%
:
v
a
l
i
d
1
2
.
5
%
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
A
lz
h
eime
r
’
s
p
r
ed
ictio
n
via
C
N
N
-
S
V
M o
n
ch
a
tb
o
t p
la
tfo
r
m
w
ith
MRI
(
Mu
h
a
mma
d
S
ya
ek
a
r
K
a
d
a
fi
)
67
I
n
ad
d
itio
n
,
test
s
co
m
m
o
n
l
y
u
s
ed
in
Alzh
eim
er
’
s
p
r
ed
ictio
n
ch
atb
o
t
s
y
s
tem
s
,
esp
ec
ially
b
lack
b
o
x
test
in
g
,
will
b
e
ca
r
r
ied
o
u
t.
T
h
is
test
in
g
p
h
ase
ex
p
lo
r
es
th
e
c
h
atb
o
t
’
s
b
e
n
ef
its
,
d
r
aw
b
ac
k
s
,
an
d
s
ig
n
if
ica
n
ce
to
en
s
u
r
e
its
q
u
ality
an
d
r
eliab
ilit
y
.
T
esti
n
g
will
ad
o
p
t
th
e
s
tat
e
tr
an
s
itio
n
tech
n
iq
u
e,
wh
ich
in
v
o
lv
es
p
r
o
v
id
in
g
in
p
u
t
in
im
a
g
es
an
d
te
x
t
to
o
b
s
er
v
e
th
e
ch
at
b
o
t
’
s
b
e
h
av
io
u
r
.
Fu
r
th
er
ex
p
lan
atio
n
is
s
h
o
w
n
in
T
ab
le
4
,
a
test
tab
le
b
ased
o
n
t
h
e
s
tate
tr
an
s
itio
n
d
iag
r
am
.
T
h
is
t
r
an
s
itio
n
(
T
)
t
ab
le
will
o
u
tlin
e
th
e
r
e
s
u
lts
o
f
o
b
s
er
v
atio
n
s
an
d
an
aly
s
is
r
eg
ar
d
i
n
g
th
e
c
h
atb
o
t
’
s
r
esp
o
n
s
e
to
ea
ch
tr
an
s
itio
n
,
allo
win
g
f
o
r
a
d
etailed
ev
alu
atio
n
o
f
th
e
ch
atb
o
t
’
s
p
er
f
o
r
m
a
n
ce
in
v
a
r
i
o
u
s
co
n
tex
ts
an
d
in
ter
ac
tio
n
s
.
T
ab
le
4
.
T
esti
n
g
b
ased
o
n
s
tate
tr
an
s
itio
n
d
iag
r
am
T
D
o
ma
i
n
A
c
t
i
o
n
O
b
j
e
c
t
i
v
e
M
a
r
k
T1
En
t
e
r
C
l
i
c
k
l
o
g
i
n
En
t
e
r
h
o
m
e
p
a
g
e
1
0
0
p
o
i
n
t
s
i
f
a
c
t
i
o
n
a
n
d
g
o
a
l
m
a
t
c
h
.
0
p
o
i
n
t
s
i
f
a
c
t
i
o
n
a
n
d
g
o
a
l
d
o
n
o
t
ma
t
c
h
.
T2
S
e
a
r
c
h
C
l
i
c
k
se
a
r
c
h
,
t
y
p
e
“
A
L
C
H
A
”
,
C
l
i
c
k
A
L
C
H
A
En
t
e
r
C
h
a
t
b
o
t
T3
H
o
me
p
a
g
e
C
l
i
c
k
s
t
a
r
t
En
t
e
r
h
o
m
e
T4
I
d
e
n
t
i
t
y
Ty
p
e
“
I
d
e
n
t
i
t
y
”
D
i
sp
l
a
y
i
d
e
n
t
i
t
y
T5
O
r
d
e
r
Ty
p
e
“
C
o
mm
a
n
d
”
Th
e
c
o
mm
a
n
d
l
i
s
t
a
p
p
e
a
r
s
T6
S
e
r
v
i
c
e
C
l
i
c
k
l
o
g
o
u
t
Q
u
i
t
C
h
a
t
b
o
t
s a
n
d
T
e
l
e
g
r
a
m
T7
S
e
r
v
i
c
e
S
e
n
d
t
e
x
t
A
n
sw
e
r
o
r
t
e
x
t
C
h
a
t
b
o
t
m
o
d
e
l
a
c
c
u
r
a
c
y
T8
S
e
n
d
p
i
c
t
u
r
e
D
i
a
g
n
o
se
o
r
r
e
sp
o
n
d
t
o
i
ma
g
e
A
c
c
u
r
a
c
y
o
f
A
D
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
s
tu
d
y
co
m
b
in
e
d
th
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
ca
p
a
b
ilit
ies
o
f
C
NN
w
ith
th
e
d
is
cr
im
in
ativ
e
p
o
wer
o
f
SVM
to
cr
ea
te
a
h
y
b
r
id
C
NN
-
SVM
m
o
d
el
f
o
r
AD
p
r
e
d
ictio
n
.
I
n
o
r
d
er
t
o
p
r
e
p
ar
e
th
e
d
at
a,
th
e
in
itial
d
ataset
was
th
en
r
an
d
o
m
ly
d
iv
id
e
d
in
to
th
r
ee
m
ain
p
a
r
ts
:
tr
ain
i
n
g
d
ata,
test
in
g
d
ata,
a
n
d
v
alid
atin
g
d
ata.
T
h
e
p
r
o
ce
s
s
aim
s
to
en
s
u
r
e
th
at
th
e
d
ev
el
o
p
ed
m
o
d
el
ca
n
lear
n
f
r
o
m
lar
g
e
am
o
u
n
ts
o
f
d
ata.
T
h
e
m
o
d
el
is
test
ed
o
n
d
ata
u
n
s
ee
n
d
u
r
i
n
g
tr
ain
in
g
an
d
v
e
r
if
ied
o
n
a
s
m
all
p
o
r
tio
n
o
f
th
e
d
ata
u
s
ed
f
o
r
v
alid
atio
n
.
I
n
t
h
i
s
s
tep
,
b
y
d
ef
au
lt,
2
5
%
o
f
th
e
tr
ai
n
in
g
d
ata
is
t
ak
en
to
f
o
r
m
v
ali
d
atin
g
d
ata.
T
h
e
e
n
tire
p
r
o
ce
s
s
o
f
d
iv
id
i
n
g
th
is
d
ataset
was
ca
r
r
ied
o
u
t c
ar
ef
u
lly
to
en
s
u
r
e
s
u
f
f
icien
t r
ep
r
esen
tatio
n
o
f
ea
ch
s
tag
e
o
f
AD
in
ea
c
h
d
ata
g
r
o
u
p
.
T
h
r
e
e
p
r
e
p
r
o
c
e
s
s
i
n
g
s
t
r
at
e
g
i
es
w
e
r
e
i
n
v
e
s
ti
g
a
t
e
d
,
c
o
n
s
is
ti
n
g
o
f
n
o
p
r
e
p
r
o
c
e
s
s
i
n
g
,
p
r
e
p
r
o
c
e
s
s
in
g
1
,
a
n
d
p
r
e
p
r
o
c
e
s
s
i
n
g
2
.
T
h
e
r
es
i
z
i
n
g
an
d
r
e
s
c
a
l
i
n
g
o
f
b
r
a
i
n
i
m
a
g
es
s
ig
n
i
f
i
c
a
n
t
l
y
i
m
p
r
o
v
e
d
t
h
e
m
o
d
el
’
s
p
e
r
f
o
r
m
a
n
c
e
.
I
n
p
r
e
p
a
r
i
n
g
t
o
t
r
a
i
n
a
m
o
d
e
l
f
o
r
a
n
A
l
z
h
e
i
m
e
r
’
s
p
r
e
d
i
c
t
i
o
n
ta
s
k
u
s
i
n
g
a
h
y
b
r
i
d
C
N
N
-
S
V
M
,
i
t
i
s
c
r
u
c
i
al
t
o
i
n
v
o
l
v
e
e
v
e
r
y
s
t
e
p
o
f
d
a
ta
p
r
o
c
e
s
s
i
n
g
.
T
h
e
b
r
a
i
n
i
m
a
g
e
o
f
A
D
p
at
i
e
n
t
s
’
n
e
e
d
s
t
o
b
e
r
e
s
i
z
e
d
u
s
i
n
g
lin
e
a
r
i
n
t
e
r
p
o
l
at
i
o
n
,
w
h
i
c
h
c
o
n
n
e
c
ts
tw
o
d
a
t
a
p
o
i
n
ts
wi
t
h
a
s
t
r
ai
g
h
t
li
n
e
.
B
y
s
e
l
e
ct
i
n
g
a
n
a
p
p
r
o
p
r
i
a
t
e
X
3
p
r
e
p
r
o
c
e
s
s
o
r
,
t
h
e
m
o
d
e
l
is
h
o
p
e
d
t
o
o
b
t
a
i
n
b
e
t
t
e
r
r
e
p
r
e
s
e
n
t
a
t
i
o
n
,
i
m
p
r
o
v
e
p
e
r
f
o
r
m
a
n
c
e
,
an
d
m
a
k
e
l
e
a
r
n
i
n
g
e
a
s
ie
r
.
T
h
e
h
y
b
r
i
d
m
o
d
e
l
ex
h
ib
i
t
e
d
ad
a
p
t
ab
i
l
i
t
y
a
n
d
r
o
b
u
s
t
p
e
r
f
o
r
m
a
n
c
e
a
c
r
o
s
s
d
i
f
f
e
r
en
t
d
a
ta
p
r
o
p
o
r
t
io
n
s
a
n
d
p
r
e
p
r
o
c
e
s
s
i
n
g
m
e
t
h
o
d
s
.
H
y
b
r
id
C
N
N
-
S
V
M
w
i
t
h
T
e
n
s
o
r
F
l
o
w
h
a
s
p
r
o
v
e
n
to
b
e
a
p
o
w
e
r
f
u
l
co
m
b
in
a
t
io
n
i
n
d
a
t
a
an
a
l
y
s
i
s
f
o
r
i
m
ag
e
c
la
s
s
i
f
i
c
a
t
i
o
n
.
T
h
e
h
y
b
r
id
t
e
c
h
n
i
q
u
e
in
t
en
d
s
t
o
co
m
b
i
n
e
th
e
f
ea
t
u
r
e
e
x
tr
a
c
t
i
o
n
c
a
p
ab
i
l
i
t
i
e
s
o
f
C
N
N
an
d
th
e
d
i
s
c
r
i
m
in
a
t
i
v
e
p
o
w
e
r
o
f
S
VM
t
o
p
r
o
d
u
c
e
a
r
o
b
u
s
t
m
o
d
e
l.
T
h
e
m
o
d
e
l
co
n
s
i
s
t
s
o
f
t
w
o
co
n
v
o
lu
t
i
o
n
l
a
y
er
s
w
i
t
h
m
a
x
-
p
o
o
l
in
g
,
a
f
l
a
t
t
en
ed
l
a
y
er
,
a
n
d
a
d
e
n
s
e
l
a
y
e
r
d
e
s
i
g
n
e
d
t
o
ex
t
r
a
c
t
f
e
a
t
u
r
e
s
f
r
o
m
i
m
ag
e
s
h
ie
r
ar
ch
i
c
a
l
l
y
.
C
l
a
s
s
i
f
i
c
a
t
i
o
n
u
s
e
s
r
an
d
o
m
f
o
u
r
i
e
r
f
e
a
tu
r
e
s
t
o
r
e
p
la
c
e
t
h
e
S
V
M
o
u
t
p
u
t
l
a
y
e
r
w
i
t
h
a
r
ad
i
a
l
b
a
s
i
s
f
u
n
c
t
i
o
n
(
R
B
F
)
k
er
n
e
l.
T
h
e
f
o
l
lo
w
i
n
g
i
s
a
d
i
a
g
r
a
m
o
f
t
h
e
AD
p
r
ed
i
c
t
i
o
n
m
o
d
e
l
s
h
o
w
n
i
n
F
ig
u
r
e
1
.
Fig
u
r
e
1
.
AD
p
r
ed
ictio
n
m
o
d
e
l d
iag
r
am
B
y
in
teg
r
atin
g
t
h
e
AD
p
r
ed
ict
io
n
m
o
d
el,
tex
t
p
r
o
ce
s
s
in
g
m
o
d
el,
an
d
q
u
esti
o
n
n
air
e
d
ataset
th
r
o
u
g
h
a
T
eleg
r
am
b
o
t,
s
m
o
o
th
co
m
m
u
n
icatio
n
was
e
n
ab
led
,
im
p
r
o
v
i
n
g
th
e
s
h
ar
in
g
o
f
in
f
o
r
m
atio
n
.
T
h
e
u
s
e
o
f
r
an
d
o
m
f
o
u
r
ier
f
ea
t
u
r
es
in
th
e
m
o
d
el
a
r
ch
itectu
r
e
s
h
o
ws
th
e
in
teg
r
atio
n
o
f
SVM
in
to
th
e
C
NN
m
o
d
el.
T
h
is
f
ea
tu
r
e
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
64
-
73
68
u
s
ed
as
an
SVM
r
ep
r
esen
tatio
n
with
a
R
B
F
k
er
n
el,
allo
win
g
th
e
m
o
d
el
to
ca
p
t
u
r
e
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
b
etwe
en
f
ea
tu
r
es
in
t
h
e
d
ata.
T
r
ad
itio
n
ally
,
SVM
is
o
f
ten
u
s
ed
f
o
r
class
if
icatio
n
b
ec
au
s
e
o
f
its
ab
ilit
y
to
h
an
d
le
n
o
n
-
lin
ea
r
p
r
o
b
lem
s
[
2
6
]
.
W
ith
th
e
r
an
d
o
m
f
o
u
r
ier
f
ea
tu
r
es
lay
er
,
th
e
m
o
d
el
attem
p
ts
to
ap
p
r
o
x
im
ate
co
m
p
lex
n
o
n
-
lin
ea
r
m
ap
p
in
g
wh
ile
r
etain
in
g
th
e
ad
v
a
n
tag
e
s
o
f
C
NN
in
ex
tr
ac
tin
g
f
ea
tu
r
es
f
r
o
m
im
ag
e
d
ata.
T
h
e
C
NN
-
SVM
h
y
b
r
id
in
n
o
v
atio
n
r
ef
lects
a
h
o
lis
tic
ap
p
r
o
ac
h
b
y
co
m
b
in
in
g
th
e
ad
v
an
tag
es
o
f
two
ML
p
ar
ad
ig
m
s
.
T
h
is
allo
ws th
e
m
o
d
el
to
h
a
n
d
le
co
m
p
lex
c
h
allen
g
es with
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
[
2
7
]
.
L
ev
er
ag
in
g
th
e
ad
v
an
tag
es
o
f
SVM
wh
ile
s
til
l
u
tili
zin
g
th
e
p
o
wer
o
f
h
ier
ar
c
h
ical
lear
n
in
g
f
ea
tu
r
es
f
r
o
m
C
NN,
im
p
lem
en
tin
g
th
e
ea
r
ly
s
to
p
p
in
g
ca
llb
ac
k
s
h
o
ws
an
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
d
u
r
i
n
g
m
o
d
el
tr
ain
in
g
.
C
allb
ac
k
s
r
ef
lect
an
ef
f
o
r
t
to
en
s
u
r
e
th
e
m
o
d
el
f
its
th
e
tr
ain
in
g
d
ata
to
g
e
n
er
alize
u
n
s
ee
n
d
ata
well.
B
y
p
r
o
v
id
in
g
a
p
atien
ce
lim
it o
f
5
,
th
e
m
o
d
el
will a
u
to
m
atica
lly
s
to
p
t
r
ain
in
g
if
th
er
e
is
n
o
im
p
r
o
v
em
e
n
t
in
th
e
ac
cu
r
ac
y
o
f
th
e
v
alid
ati
o
n
d
ata
af
ter
r
ea
ch
in
g
th
e
p
atien
ce
lim
it.
T
h
ey
wer
e
f
o
llo
wed
b
y
m
o
d
el
tr
ain
in
g
f
o
r
1
0
0
ep
o
ch
s
,
with
ea
ch
ep
o
ch
co
m
p
letin
g
th
e
tr
ain
i
n
g
d
at
a
p
r
o
ce
s
s
in
g
.
Pre
p
r
o
ce
s
s
in
g
p
lay
ed
a
c
r
itical
r
o
le
in
b
o
o
s
tin
g
m
o
d
el
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
p
ar
ticu
lar
ly
in
h
an
d
lin
g
n
o
n
-
li
n
ea
r
r
elatio
n
s
h
ip
s
in
AD
p
r
ed
i
ctio
n
.
Af
ter
th
e
tr
ain
in
g
p
r
o
ce
s
s
i
s
co
m
p
lete,
th
e
n
ex
t
s
tep
is
to
ev
alu
ate
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
th
e
AD
p
r
e
d
ictio
n
s
y
s
tem
m
o
d
el
t
h
r
o
u
g
h
d
ata
an
aly
s
is
o
f
im
ag
es
th
at
wer
e
n
o
t
s
ee
n
d
u
r
i
n
g
t
h
e
t
r
ain
in
g
a
n
d
v
alid
atio
n
s
tag
es.
T
h
e
f
o
llo
win
g
is
th
e
m
o
d
el
ev
alu
atio
n
r
esu
lts
f
o
r
th
r
ee
d
ata
p
r
o
p
o
r
tio
n
s
ch
em
es
an
d
th
r
ee
p
r
e
p
r
o
ce
s
s
in
g
s
ch
e
m
es
.
T
ab
le
5
p
r
esen
ts
th
e
r
esu
lts
o
f
th
e
ev
alu
atio
n
with
o
u
t
p
r
e
p
r
o
ce
s
s
in
g
,
wh
ile
T
ab
le
6
d
is
p
lay
s
th
e
o
u
tco
m
es
o
f
p
r
ep
r
o
ce
s
s
ev
alu
atio
n
1
,
a
n
d
T
ab
le
7
s
h
o
wca
s
es th
e
f
in
d
in
g
s
o
f
p
r
e
p
r
o
ce
s
s
ev
alu
atio
n
2.
T
ab
le
5
.
E
v
alu
atio
n
with
o
u
t p
r
ep
r
o
ce
s
s
in
g
N
a
me
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
c
h
e
me
1
2
6
%
2
6
%
3
0
%
2
2
%
S
c
h
e
me
2
2
4
%
2
4
%
2
2
%
2
0
%
S
c
h
e
me
3
7
7
%
6
6
%
7
1
%
6
2
%
T
ab
le
6
.
Pre
p
r
o
ce
s
s
e
v
alu
atio
n
1
N
a
me
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
c
h
e
me
4
9
8
%
9
9
%
9
8
%
9
8
%
S
c
h
e
me
5
9
5
%
9
5
%
9
5
%
9
5
%
S
c
h
e
me
6
8
9
%
9
2
%
8
7
%
8
9
%
T
ab
le
7
.
Pre
p
r
o
ce
s
s
e
v
alu
atio
n
2
N
a
me
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
c
h
e
me
7
9
7
%
9
8
%
9
5
%
9
7
%
S
c
h
e
me
8
9
3
%
8
4
%
9
1
%
8
6
%
S
c
h
e
me
9
9
0
%
9
2
%
8
7
%
9
0
%
B
ased
o
n
T
ab
le
5
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
AD
s
tag
e
p
r
ed
ic
tio
n
m
o
d
el
s
h
o
ws
a
s
tag
n
an
t
ten
d
en
cy
in
v
ar
io
u
s
d
ata
p
r
o
p
o
r
tio
n
s
ch
em
es o
f
m
o
r
e
th
a
n
6
0
%.
T
h
is
p
h
e
n
o
m
en
o
n
o
cc
u
r
s
d
u
e
t
o
p
r
e
p
r
o
ce
s
s
in
g
n
ee
d
in
g
t
o
b
e
ap
p
lied
.
H
o
wev
er
,
in
cr
ea
s
i
n
g
m
o
d
el
co
m
p
le
x
ity
im
p
ac
ts
ac
cu
r
ac
y
b
y
3
%
to
8
0
%
f
o
r
a
d
ataset
p
r
o
p
o
r
tio
n
o
f
3
7
.
5
%:5
0
%
with
o
u
t
p
r
ep
r
o
ce
s
s
in
g
.
I
n
ad
d
itio
n
,
th
e
m
o
d
el
p
r
o
d
u
ce
s
an
ac
cu
r
ac
y
o
f
8
9
%
an
d
8
8
%
f
o
r
a
d
ataset
p
r
o
p
o
r
tio
n
o
f
3
7
.
5
%:5
0
%
with
p
r
e
p
r
o
ce
s
s
o
n
e
an
d
a
d
ataset
p
r
o
p
o
r
tio
n
o
f
3
7
.
5
%:5
0
%
with
p
r
ep
r
o
ce
s
s
2
.
T
h
er
ef
o
r
e,
a
m
o
r
e
co
m
p
lex
m
o
d
el
is
lik
ely
s
u
it
ab
le
f
o
r
p
r
ep
r
o
ce
s
s
in
g
1
.
On
th
e
o
th
er
h
an
d
,
wh
en
th
e
im
ag
e
is
n
o
t
r
esized
,
t
h
e
m
o
d
el
h
as
d
if
f
ic
u
lty
h
a
n
d
lin
g
t
h
e
s
p
atial
s
tr
u
ctu
r
e
o
f
th
e
2
0
8
×1
7
6
-
p
ix
el
im
ag
e.
R
esizin
g
th
e
im
a
g
e
t
o
s
m
aller
d
im
en
s
io
n
s
a
n
d
s
ca
lin
g
p
ix
el
v
alu
es
to
a
s
m
aller
r
an
g
e
a
r
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
th
at
h
elp
tr
ain
an
d
b
e
tter
co
n
v
e
r
g
e
m
o
r
e
e
f
f
icien
tly
.
Af
ter
ca
r
r
y
in
g
o
u
t
t
h
e
r
escale
an
d
r
esizin
g
p
r
o
c
ess
o
n
th
e
im
ag
e,
th
e
m
o
d
el
ev
alu
atio
n
r
esu
lts
s
h
o
w
a
co
n
s
is
ten
t
in
cr
ea
s
e
in
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
f
o
r
ea
c
h
d
ata
p
r
o
p
o
r
tio
n
s
ch
em
e,
as
d
ep
icted
in
T
ab
le
s
6
an
d
7
.
Sp
ec
if
ically
,
th
e
ab
s
en
ce
o
f
s
ca
lin
g
an
d
r
esi
zin
g
in
th
e
im
a
g
e
n
eg
ativ
ely
im
p
ac
ts
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
wh
ich
is
o
n
ly
ar
o
u
n
d
2
0
% to
3
0
% o
n
t
r
ain
in
g
d
ata
o
f
m
o
r
e
th
a
n
3
7
.
5
%.
L
ar
g
e
p
ix
el
v
alu
es
tr
ig
g
er
s
ig
n
if
ican
t
weig
h
t
d
if
f
er
e
n
ce
s
d
u
r
in
g
tr
ain
in
g
i
f
th
e
im
ag
e
is
n
o
t
s
ca
led
.
T
h
is
r
esu
lts
in
u
n
s
tab
le
co
n
v
e
r
g
en
ce
a
n
d
o
v
er
f
itti
n
g
.
B
ased
o
n
T
ab
le
s
6
to
7
,
th
e
d
if
f
er
en
ce
in
p
r
e
p
r
o
ce
s
s
in
g
o
r
d
er
d
o
es
n
o
t
h
av
e
a
s
ig
n
if
ican
t
ef
f
ec
t,
n
am
ely
1
%.
No
p
r
e
p
r
o
ce
s
s
in
g
s
ig
n
if
ica
n
tly
im
p
ac
ts
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
is
is
b
ec
au
s
e
b
o
th
s
eq
u
en
ce
s
ess
en
tial
ly
d
o
th
e
s
am
e
th
in
g
,
n
a
m
ely
,
c
h
an
g
in
g
th
e
s
ize
a
n
d
s
ca
le
o
f
th
e
d
ata.
B
o
th
o
p
er
ati
o
n
s
h
av
e
a
s
im
ilar
g
o
al:
ad
ju
s
tin
g
th
e
d
ata
to
s
u
it
th
e
m
o
d
el
’
s
n
ee
d
s
.
Sin
ce
th
e
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
A
lz
h
eime
r
’
s
p
r
ed
ictio
n
via
C
N
N
-
S
V
M o
n
ch
a
tb
o
t p
la
tfo
r
m
w
ith
MRI
(
Mu
h
a
mma
d
S
ya
ek
a
r
K
a
d
a
fi
)
69
r
esu
lts
o
f
th
e
two
p
r
e
p
r
o
ce
s
s
es
ar
e
v
er
y
s
im
ilar
,
th
er
e
is
n
o
s
ig
n
if
ican
t
d
if
f
e
r
en
ce
in
t
h
e
f
in
al
r
esu
lts
.
T
h
e
h
y
b
r
id
C
NN
-
SVM
m
o
d
el
is
less
s
en
s
i
tiv
e
to
s
m
all
r
esize
an
d
r
esale
p
r
ep
r
o
ce
s
s
in
g
ch
an
g
es.
T
h
e
m
o
d
el
ca
n
ad
a
p
t
to
th
e
n
u
m
er
ical
r
ep
r
esen
tatio
n
s
g
en
er
ated
f
r
o
m
b
o
th
p
r
ep
r
o
ce
s
s
es,
an
d
its
im
p
ac
t
o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
is
in
s
ig
n
if
ican
t.
I
t
is
i
m
p
o
r
tan
t
to
n
o
te
th
at
n
o
ess
en
tial
ch
an
g
es
o
cc
u
r
to
t
h
e
d
ata
af
ter
ap
p
ly
in
g
th
ese
two
p
r
ep
r
o
ce
s
s
es.
T
h
is
m
ea
n
s
th
at
n
o
tr
an
s
f
o
r
m
atio
n
s
af
f
ec
t f
ea
tu
r
e
ex
tr
ac
tio
n
o
r
th
e
m
o
d
el
’
s
d
ee
p
u
n
d
er
s
tan
d
in
g
o
f
th
e
d
ata.
T
h
er
ef
o
r
e,
d
if
f
er
e
n
ce
s
in
p
r
ep
r
o
ce
s
s
in
g
o
r
d
er
h
a
v
e
a
m
in
im
al
im
p
ac
t
o
n
th
e
f
i
n
al
r
esu
lts
o
f
m
o
d
el
a
cc
u
r
ac
y
.
B
ased
o
n
th
e
d
ata
p
r
o
p
o
r
tio
n
s
ch
em
e
an
d
p
r
e
p
r
o
ce
s
s
in
g
,
t
h
e
b
est
m
o
d
el
is
a
m
o
d
el
wi
th
a
d
ata
p
r
o
p
o
r
tio
n
s
ch
em
e
o
f
6
0
%:2
0
%
an
d
p
r
e
p
r
o
ce
s
s
in
g
1
with
9
8
%
ac
cu
r
ac
y
,
9
9
%
p
r
ec
is
io
n
,
9
8
%
r
ec
all,
an
d
9
8
%
F1
-
s
co
r
e.
O
n
th
e
o
th
er
h
an
d
,
th
e
ac
c
u
r
ac
y
,
p
r
ec
is
i
o
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
r
esu
lts
f
o
r
ea
ch
d
ata
p
r
o
p
o
r
tio
n
s
ch
em
e
in
p
r
ep
r
o
c
ess
in
g
s
ch
em
e
1
s
h
o
w
s
lig
h
tly
b
etter
r
esu
lts
th
an
in
p
r
ep
r
o
ce
s
s
in
g
s
ch
em
e
2
.
T
h
e
m
o
d
el
r
esu
lts
in
cr
ea
s
e
wi
th
ea
ch
in
c
r
ea
s
e
in
th
e
am
o
u
n
t
o
f
tr
ain
i
n
g
d
ata.
T
h
e
an
aly
s
i
s
r
esu
lts
in
T
ab
le
8
s
h
o
w
th
at
p
r
ep
r
o
ce
s
s
in
g
p
lay
s
an
ess
en
tial
r
o
le
in
im
p
r
o
v
in
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
AD
m
o
d
el.
Mo
d
el
p
er
f
o
r
m
an
ce
ca
n
b
e
s
tag
n
an
t
an
d
n
o
t
o
p
tim
al
with
o
u
t
o
p
tim
al
p
r
ep
r
o
ce
s
s
in
g
,
esp
ec
ially
r
escalin
g
an
d
r
esizin
g
,
m
is
tr
ea
ted
b
y
th
e
ev
alu
atio
n
r
esu
lts
in
T
ab
le
6
.
T
h
e
f
o
llo
win
g
is
a
d
etailed
tab
le
ev
alu
atin
g
th
e
b
est
m
o
d
el
.
T
ab
le
8
.
Deta
ils
o
f
b
est s
ch
em
e
test
d
ata
ev
alu
atio
n
S
t
a
g
e
s
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
A
mo
u
n
t
o
f
d
a
t
a
M
i
l
d
d
e
me
n
t
e
d
9
7
.
7
4
%
9
8
.
8
7
%
9
7
.
2
2
%
9
8
.
0
4
%
1
8
0
M
o
d
e
r
a
t
e
d
e
me
n
t
e
d
1
0
0
%
1
0
0
%
1
0
0
%
13
N
o
n
-
d
e
m
e
n
t
e
d
9
7
.
0
8
%
9
8
.
5
9
%
9
7
.
8
3
%
6
4
0
V
e
r
y
m
i
l
d
d
e
m
e
n
t
e
d
9
8
.
1
9
%
9
6
.
6
5
%
9
7
.
4
1
%
4
4
8
M
a
c
r
o
a
v
e
r
a
g
e
9
8
.
5
3
%
9
8
.
1
2
%
9
8
.
3
2
%
1
,
2
8
1
W
e
i
g
h
t
e
d
a
v
e
r
a
g
e
9
7
.
7
5
%
9
7
.
7
4
%
9
7
.
7
4
%
1
,
2
8
1
T
h
e
m
o
d
el
ev
alu
atio
n
p
er
f
o
r
m
s
ex
ce
llen
tly
f
o
r
v
ar
io
u
s
class
e
s
in
th
e
b
est
m
o
d
e
l
s
ch
em
e.
T
h
e
“m
o
d
er
ate
d
e
m
en
ted
”
class
s
tan
d
s
o
u
t
with
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
an
F1
-
s
co
r
e
th
at
r
ea
c
h
es
1
0
0
%.
Me
an
w
h
ile,
th
e
“m
ild
d
em
en
ted
,
”
“n
o
n
-
d
em
en
ted
,
”
an
d
“v
er
y
m
ild
d
em
en
te
d
”
c
lass
es
al
s
o
s
h
o
wed
ex
ce
llen
t p
er
f
o
r
m
an
ce
,
with
a
cc
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
m
etr
ics in
th
e
r
a
n
g
e
o
f
9
7
.
8
5
%
-
9
9
.
3
6
%.
A
tex
t
p
r
o
ce
s
s
in
g
m
o
d
el
was
d
e
v
elo
p
e
d
to
e
n
h
an
ce
u
s
er
in
t
er
ac
tio
n
,
ef
f
ec
tiv
ely
p
r
o
ce
s
s
in
g
q
u
e
r
ies
an
d
p
r
o
v
id
in
g
r
elev
an
t
r
esp
o
n
s
es.
T
h
ese
s
ch
em
es
p
r
o
v
id
e
a
s
o
lid
b
asis
f
o
r
ev
alu
atin
g
m
o
d
el
p
er
f
o
r
m
an
ce
i
n
p
r
ed
ictin
g
a
n
d
class
if
y
in
g
AD
s
tag
es
in
b
r
ain
MRI
im
ag
es.
Ap
ar
t
f
r
o
m
th
at,
q
u
esti
o
n
lis
t
d
ata
is
also
n
ee
d
ed
in
d
ev
el
o
p
in
g
a
ch
atb
o
t
tex
t
p
r
o
ce
s
s
in
g
m
o
d
el.
T
r
u
s
ted
i
n
f
o
r
m
atio
n
s
o
u
r
ce
s
f
r
o
m
Alzh
ei
m
er
’
s
r
esear
ch
UK
’
s
in
f
o
r
m
atio
n
s
er
v
ices
ad
d
v
al
u
e
to
th
e
c
h
atb
o
t
s
er
v
ice,
e
n
s
u
r
in
g
u
s
er
s
r
ec
eiv
e
ac
cu
r
a
te
an
d
u
p
-
to
-
d
ate
in
f
o
r
m
atio
n
.
Af
ter
cr
ea
tin
g
a
lis
t
o
f
q
u
esti
o
n
s
,
th
e
n
ex
t
s
tep
is
m
o
d
ellin
g
th
e
tex
t
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
.
Alg
o
r
ith
m
m
o
d
ellin
g
aim
s
to
en
ab
le
th
e
ch
atb
o
t
to
p
r
o
v
i
d
e
th
e
co
r
r
ec
t
an
s
wer
b
ased
o
n
th
e
lev
el
o
f
s
im
ilar
ity
o
f
th
e
u
s
er
’
s
q
u
esti
o
n
to
th
e
lis
t
o
f
p
r
ev
io
u
s
ly
co
m
p
ile
d
q
u
esti
o
n
s
.
I
n
th
is
co
n
tex
t,
if
th
e
p
r
o
b
a
b
ilit
y
o
f
s
im
ilar
ity
b
etwe
en
th
e
u
s
er
’
s
q
u
esti
o
n
an
d
th
e
lis
t
o
f
q
u
esti
o
n
s
is
les
s
th
an
2
5
%,
th
e
ch
atb
o
t
will
tak
e
th
e
an
s
wer
f
r
o
m
th
e
C
h
atGPT
m
o
d
el.
T
h
is
m
o
d
ellin
g
p
r
o
ce
s
s
in
v
o
lv
es
p
r
o
ce
s
s
in
g
th
e
i
n
ten
ts
in
th
e
d
ataset,
wh
er
e
ea
ch
in
ten
t
r
ep
r
esen
ts
a
p
u
r
p
o
s
e
o
r
to
p
ic
o
f
co
n
v
er
s
atio
n
.
Fig
u
r
e
2
s
h
o
ws
a
d
iag
r
am
o
f
th
e
tex
t
p
r
o
ce
s
s
in
g
m
o
d
el
.
T
h
e
m
o
d
el
m
ea
s
u
r
es
th
e
s
im
ilar
ity
b
etwe
en
tex
ts
.
T
h
is
p
r
o
ce
s
s
allo
ws
th
e
ch
atb
o
t
to
p
r
o
v
id
e
m
o
r
e
r
elev
an
t
an
s
wer
s
to
th
e
u
s
er
’
s
q
u
esti
o
n
s
.
Usi
n
g
th
e
in
ten
t
i
n
f
o
r
m
atio
n
in
th
e
d
ataset,
th
e
s
y
s
tem
ca
n
m
atch
th
e
u
s
er
’
s
q
u
esti
o
n
in
ten
t
with
t
h
e
lis
t
o
f
q
u
esti
o
n
s
an
d
p
r
o
v
id
e
an
ap
p
r
o
p
r
iate
r
esp
o
n
s
e.
T
h
is
s
tep
in
v
o
lv
es
ex
tr
ac
tin
g
th
e
wo
r
d
p
atter
n
s
o
f
ea
ch
in
ten
t,
a
n
d
th
e
r
esu
lts
a
r
e
o
r
g
a
n
ized
d
u
r
in
g
m
o
d
el
tr
ai
n
in
g
an
d
,
b
ased
o
n
Fig
u
r
e
2
,
f
o
r
m
i
n
g
an
d
tr
ain
in
g
a
n
eu
r
al
n
etwo
r
k
(
NN)
m
o
d
el
u
s
in
g
Ker
as.
First,
th
e
s
eq
u
en
tial
NN
m
o
d
el
is
b
u
ilt s
eq
u
en
tially
with
ap
p
r
o
p
r
iate
lay
er
s
,
s
tar
tin
g
with
an
in
p
u
t la
y
er
wit
h
1
2
8
n
eu
r
o
n
s
.
T
h
en
,
a
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
f
u
n
ctio
n
is
ap
p
lied
,
f
o
llo
wed
b
y
a
d
r
o
p
o
u
t
lay
er
to
r
ed
u
ce
o
v
e
r
f
itti
n
g
b
y
r
an
d
o
m
ly
s
ettin
g
s
ev
er
al
n
eu
r
o
n
s
to
0
d
u
r
in
g
tr
ain
in
g
.
Nex
t,
a
h
i
d
d
en
lay
er
with
6
4
n
eu
r
o
n
s
an
d
a
R
eL
U
ac
tiv
atio
n
f
u
n
ct
io
n
is
ad
d
ed
,
f
o
llo
wed
b
y
a
n
o
th
er
d
r
o
p
o
u
t
la
y
er
.
T
h
e
p
r
o
ce
s
s
o
f
m
o
d
el
f
o
r
m
atio
n
an
d
tr
ain
in
g
co
n
tin
u
es.
T
h
e
o
u
tp
u
t
lay
er
is
ad
d
e
d
with
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
ac
co
r
d
in
g
to
th
e
n
u
m
b
er
o
f
class
es
an
d
th
e
So
f
tm
ax
ac
tiv
atio
n
f
u
n
ctio
n
.
Af
ter
th
at,
th
e
m
o
d
el
is
co
n
f
ig
u
r
ed
with
th
e
p
r
ev
io
u
s
ly
cr
ea
ted
s
to
c
h
asti
c
g
r
ad
ien
t
d
escen
t
(
SGD)
o
p
tim
izer
,
u
s
in
g
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
as
th
e
lo
s
s
f
u
n
ctio
n
an
d
ac
cu
r
ac
y
as
th
e
m
o
n
ito
r
in
g
m
etr
ic.
Fin
ally
,
th
e
m
o
d
el
is
tr
ain
ed
u
s
in
g
t
r
a
in
in
g
d
ata
f
o
r
2
0
0
ep
o
ch
s
with
a
b
atc
h
s
ize
o
f
5
.
T
h
ese
s
tep
s
f
o
r
m
a
n
eu
r
al
n
etwo
r
k
m
o
d
el
t
h
at
ca
n
b
e
u
s
e
d
f
o
r
class
if
icatio
n
with
an
ac
cu
r
ac
y
o
f
u
p
to
9
9
%.
T
h
e
f
o
llo
win
g
is
a
d
iag
r
am
o
f
m
o
d
el
ac
cu
r
ac
y
an
d
lo
s
s
ag
ain
s
t
ep
o
ch
.
Fig
u
r
e
3
d
is
p
lay
s
a
g
r
ap
h
ic
r
e
p
r
esen
tatio
n
o
f
th
e
tex
t p
r
o
ce
s
s
in
g
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
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
64
-
73
70
Fig
u
r
e
2
.
T
e
x
t p
r
o
ce
s
s
in
g
m
o
d
el
d
iag
r
am
Fig
u
r
e
3
.
Gr
a
p
h
ic
o
f
tex
t p
r
o
c
ess
in
g
m
o
d
el
Af
ter
co
m
p
letin
g
th
e
d
e
v
elo
p
m
en
t
o
f
t
h
e
AD
p
r
e
d
ictio
n
m
o
d
el
f
o
r
d
ata
an
aly
s
is
,
th
e
tex
t
p
r
o
ce
s
s
in
g
m
o
d
el
f
o
r
ch
atb
o
t
d
esig
n
,
an
d
th
e
q
u
esti
o
n
n
ai
r
e
d
ataset
f
o
r
d
ata
co
llectio
n
,
th
e
n
ex
t
s
tep
is
to
in
teg
r
ate
all
th
ese
co
m
p
o
n
e
n
ts
v
ia
a
T
eleg
r
am
b
o
t.
T
h
e
in
teg
r
atio
n
en
a
b
les
a
s
ea
m
les
s
f
lo
w
o
f
in
f
o
r
m
atio
n
b
etwe
en
th
e
AD
p
r
ed
ictio
n
m
o
d
els,
tex
t
p
r
o
ce
s
s
in
g
m
o
d
els,
an
d
q
u
esti
o
n
n
air
e
d
atasets
,
cr
ea
tin
g
a
r
eliab
le
an
d
r
es
p
o
n
s
iv
e
ch
atb
o
t.
T
o
ac
h
iev
e
th
is
,
test
in
g
n
ee
d
s
to
b
e
ca
r
r
ied
o
u
t
to
p
r
o
v
id
e
an
in
-
d
ep
th
e
x
p
lan
atio
n
o
f
th
e
r
esu
lts
o
b
tain
ed
r
eg
ar
d
i
n
g
ch
at
b
o
t
f
u
n
ctio
n
ality
b
y
r
ef
er
r
in
g
to
t
h
e
test
tab
le
in
T
ab
le
4
.
T
h
i
s
tab
le
p
r
o
v
id
es
a
n
u
n
d
er
s
tan
d
i
n
g
o
f
t
h
e
s
itu
atio
n
o
r
co
n
d
itio
n
s
b
ein
g
test
ed
,
m
a
k
in
g
it
ea
s
ier
to
in
ter
p
r
et
th
e
t
est
r
esu
lts
.
C
o
lu
m
n
T
(
tr
an
s
itio
n
)
in
T
ab
le
6
d
esc
r
ib
es
th
e
t
r
an
s
itio
n
n
u
m
b
e
r
c
o
r
r
esp
o
n
d
i
n
g
to
th
e
tr
a
n
s
itio
n
co
lu
m
n
in
T
ab
le
4
,
clea
r
ly
id
en
tif
y
in
g
th
e
tr
an
s
itio
n
s
tep
b
ein
g
test
ed
.
I
n
th
e
co
n
te
x
t
o
f
r
esu
lts
in
ter
p
r
etatio
n
,
th
e
o
u
tp
u
t
co
l
u
m
n
p
r
o
v
id
es
a
d
etailed
d
escr
ip
ti
o
n
o
f
th
e
r
esu
lts
o
f
th
e
s
ce
n
ar
io
tr
an
s
itio
n
test
.
Nex
t,
th
e
s
ce
n
ar
io
co
lu
m
n
d
escr
ib
es th
e
s
ce
n
ar
io
s
d
esig
n
ed
f
o
r
test
in
g
.
T
ab
le
9
p
r
esen
t
s
th
e
r
esu
lts
o
f
th
e
ch
atb
o
t f
u
n
ctio
n
alit
y
test
in
g
.
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
A
lz
h
eime
r
’
s
p
r
ed
ictio
n
via
C
N
N
-
S
V
M o
n
ch
a
tb
o
t p
la
tfo
r
m
w
ith
MRI
(
Mu
h
a
mma
d
S
ya
ek
a
r
K
a
d
a
fi
)
71
T
ab
le
9
.
C
h
atb
o
t
f
u
n
ctio
n
ality
test
in
g
T
S
c
e
n
a
r
i
o
O
u
t
p
u
t
M
a
r
k
T1
U
ser l
o
g
s
i
n
t
o
t
h
e
i
r
Te
l
e
g
r
a
m
a
c
c
o
u
n
t
U
ser su
c
c
e
ssf
u
l
l
y
l
o
g
s
i
n
t
o
T
e
l
e
g
r
a
m
a
c
c
o
u
n
t
1
0
0
.
0
T2
U
ser se
a
r
c
h
e
s fo
r
A
LC
H
A
U
sers d
i
sc
o
v
e
r
e
d
A
L
C
H
A
1
0
0
.
0
T3
U
sers st
a
r
t
u
si
n
g
A
L
C
H
A
U
sers g
e
t
b
a
si
c
i
n
f
o
r
m
a
t
i
o
n
1
0
0
.
0
T4
U
ser t
y
p
e
s “
/
I
d
e
n
t
i
t
y
”
U
ser g
e
t
s A
LC
H
A
i
d
e
n
t
i
t
y
1
0
0
.
0
T5
U
ser t
y
p
e
s “
/
C
o
mm
a
n
d
”
U
sers g
e
t
s
e
r
v
i
c
e
i
n
f
o
r
mat
i
o
n
1
0
0
.
0
T6
U
ser se
n
d
t
e
x
t
U
sers g
e
t
I
n
f
o
r
m
a
t
i
o
n
9
9
.
3
4
T7
U
sers se
n
d
p
h
o
t
o
s
U
sers c
a
n
e
st
i
ma
t
e
A
D
9
7
.
7
4
T8
U
ser l
o
g
s
o
u
t
o
f
Te
l
e
g
r
a
m
a
c
c
o
u
n
t
U
ser su
c
c
e
ssf
u
l
l
y
l
o
g
s
o
u
t
o
f
T
e
l
e
g
r
a
m a
c
c
o
u
n
t
1
0
0
.
0
To
t
a
l
7
9
7
.
08
C
h
atb
o
t
f
u
n
ctio
n
ality
ca
n
b
e
m
ea
s
u
r
ed
m
ath
em
atica
lly
b
ased
o
n
th
e
tech
n
ical
tr
an
s
itio
n
v
alu
es.
T
h
e
f
o
llo
win
g
is
th
e
ca
lcu
latio
n
.
F
ungsion
a
l
ita
s
=
∑
7
=
1
=
7
97
,
08
8
=
99
.
64
T
h
ese
r
esu
lts
in
d
icate
th
at
t
h
e
ch
atb
o
t
ca
n
r
esp
o
n
d
an
d
h
an
d
le
v
ar
io
u
s
s
ce
n
ar
io
s
ef
f
ec
tiv
ely
,
m
ee
tin
g
ex
p
ec
ted
p
er
f
o
r
m
an
ce
ex
p
ec
tatio
n
s
with
a
f
u
n
ctio
n
ality
s
c
o
r
e
r
ea
c
h
in
g
9
9
.
6
4
p
o
i
n
ts
o
u
t
o
f
1
0
0
.
Su
cc
ess
in
ea
ch
s
ce
n
ar
io
p
r
o
v
id
es
a
p
o
s
itiv
e
p
ictu
r
e
o
f
t
h
e
ch
atb
o
t
’
s
ab
ilit
y
to
p
r
o
v
id
e
ap
p
r
o
p
r
iate
an
d
ac
c
u
r
ate
r
esp
o
n
s
es to
q
u
esti
o
n
s
o
r
s
itu
atio
n
s
s
u
b
m
itted
b
y
t
h
e
u
s
er
.
L
ar
g
e
-
s
ca
le
v
alid
atio
n
s
tu
d
ies
m
ay
b
e
ca
r
r
ied
o
u
t
in
th
e
f
u
t
u
r
e
to
v
alid
ate
th
e
ef
f
icac
y
o
f
AI
m
o
d
els
in
ac
tu
al
clin
ical
s
ettin
g
s
,
b
u
ild
in
g
o
n
t
h
ese
r
esu
lts
.
C
lin
ical
tr
ials
as
s
ess
in
g
th
e
ef
f
ec
t
o
f
AI
-
d
r
iv
en
t
h
er
ap
ies
o
n
p
atien
t
o
u
tco
m
es
an
d
lo
n
g
i
tu
d
in
al
s
tu
d
ies
f
o
llo
win
g
p
eo
p
le
o
v
er
tim
e
ar
e
cr
u
cial.
Fu
r
th
er
m
o
r
e,
to
ad
v
an
ce
AI
-
d
r
iv
en
h
ea
lth
ca
r
e
s
o
lu
tio
n
s
f
o
r
AD
p
r
ed
ictio
n
,
m
u
ltid
is
cip
lin
ar
y
co
o
p
er
atio
n
,
u
s
er
e
x
p
er
ien
ce
r
esear
ch
,
co
m
p
ar
is
o
n
s
v
er
s
u
s
co
n
v
en
tio
n
al
d
iag
n
o
s
tic
tech
n
iq
u
es,
an
d
eth
ical
im
p
licatio
n
s
m
u
s
t b
e
e
x
p
lo
r
ed
.
4.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
e
x
p
lo
r
es
n
in
e
c
o
m
b
in
atio
n
s
ch
em
es
b
etwe
en
3
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
a
n
d
3
d
ataset
p
r
o
p
o
r
tio
n
s
in
th
e
C
NN
-
SV
M
m
o
d
e
l.
T
h
e
th
r
ee
p
r
e
p
r
o
ce
s
s
in
g
m
eth
o
d
s
a
r
e
with
o
u
t
p
r
ep
r
o
ce
s
s
in
g
o
n
e
a
n
d
p
r
ep
r
o
ce
s
s
in
g
2
.
T
h
e
ev
alu
ati
o
n
r
esu
lts
s
h
o
w
th
at
th
e
b
est
p
er
f
o
r
m
a
n
ce
is
o
b
tain
ed
in
th
e
m
o
d
el
with
s
ch
em
e
f
o
u
r
b
ased
o
n
ac
c
u
r
ac
y
,
p
r
e
cisi
o
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
,
r
ea
ch
in
g
v
alu
es
o
f
9
8
%
,
9
9
%,
9
8
%,
an
d
9
8
%,
r
esp
ec
tiv
ely
.
I
n
o
th
er
wo
r
d
s
,
th
e
b
est
p
r
ep
r
o
ce
s
s
in
g
m
ec
h
a
n
is
m
am
o
n
g
th
e
th
r
ee
s
ch
em
es
s
tu
d
ied
in
v
o
lv
es
r
esizin
g
th
e
im
ag
e
to
a
s
ize
o
f
1
5
0
p
ix
els×1
5
0
p
ix
els,
f
o
l
lo
wed
b
y
r
escalin
g
th
e
im
ag
e
to
a
r
a
n
g
e
o
f
0
-
1
.
T
h
e
ch
o
ice
o
f
th
is
p
r
ep
r
o
ce
s
s
in
g
s
ch
em
e
in
d
icate
s
th
at
th
e
s
p
ec
if
ic
s
tep
s
im
p
lem
en
ted
in
p
r
ep
r
o
ce
s
s
in
g
o
n
e
p
o
s
itiv
ely
co
n
tr
ib
u
tes
to
th
e
m
o
d
el
’
s
p
e
r
f
o
r
m
an
ce
.
R
esizin
g
im
ag
es
t
o
s
m
aller
d
im
en
s
io
n
s
an
d
r
escalin
g
to
ch
an
g
e
p
ix
el
v
al
u
es
to
a
m
o
r
e
co
n
ce
n
tr
ate
d
r
a
n
g
e
h
av
e
im
p
r
o
v
ed
th
e
m
o
d
el
’
s
ab
ilit
y
to
e
x
tr
ac
t
f
ea
tu
r
es
a
n
d
u
n
d
er
s
tan
d
b
r
ain
MRI
im
a
g
e
p
atter
n
s
.
On
th
e
o
th
er
h
an
d
,
th
e
ch
atb
o
t
h
as
d
em
o
n
s
tr
ated
ex
ce
llen
t
f
u
n
ctio
n
ality
in
p
r
o
v
id
in
g
A
D
-
r
elate
d
r
esp
o
n
s
es
af
ter
tr
an
s
itio
n
test
in
g
,
with
a
f
u
n
ctio
n
ality
s
co
r
e
r
ea
ch
in
g
9
9
.
6
4
p
o
in
ts
o
u
t o
f
1
0
0
.
RE
F
E
R
E
NC
E
S
[
1
]
P
.
Le
e
,
S
.
B
u
b
e
c
k
,
a
n
d
J
.
P
e
t
r
o
,
“
B
e
n
e
f
i
t
s
,
l
i
mi
t
s,
a
n
d
r
i
s
k
s
o
f
G
P
T
-
4
a
s
a
n
A
I
C
h
a
t
b
o
t
f
o
r
m
e
d
i
c
i
n
e
,
”
N
e
w
E
n
g
l
a
n
d
J
o
u
r
n
a
l
o
f
Me
d
i
c
i
n
e
,
v
o
l
.
3
8
8
,
n
o
.
1
3
,
p
p
.
1
2
3
3
–
1
2
3
9
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
5
6
/
n
e
j
msr
2
2
1
4
1
8
4
.
[
2
]
Ş
.
Y
a
şar,
C
.
Ç
o
l
a
k
,
a
n
d
S
.
Y
o
l
o
ğ
l
u
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
b
a
s
e
d
p
r
e
d
i
c
t
i
o
n
o
f
C
O
V
I
D
-
19
sev
e
r
i
t
y
o
n
t
h
e
r
e
su
l
t
s
o
f
p
r
o
t
e
i
n
p
r
o
f
i
l
i
n
g
,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
r
a
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
2
0
2
,
p
.
1
0
5
9
9
6
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
2
1
.
1
0
5
9
9
6
.
[
3
]
C
.
W
a
n
g
,
T.
S
.
H
.
T
e
o
,
a
n
d
M
.
J
a
n
ss
e
n
,
“
P
u
b
l
i
c
a
n
d
p
r
i
v
a
t
e
v
a
l
u
e
c
r
e
a
t
i
o
n
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
:
a
n
e
mp
i
r
i
c
a
l
s
t
u
d
y
o
f
A
I
v
o
i
c
e
r
o
b
o
t
u
s
e
r
s
i
n
C
h
i
n
e
se
p
u
b
l
i
c
sec
t
o
r
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
6
1
,
p
.
1
0
2
4
0
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
i
n
f
o
m
g
t
.
2
0
2
1
.
1
0
2
4
0
1
.
[
4
]
M
.
A
l
m
a
l
k
i
a
n
d
F
.
A
z
e
e
z
,
“
H
e
a
l
t
h
c
h
a
t
b
o
t
s
f
o
r
f
i
g
h
t
i
n
g
C
O
V
I
D
-
19
:
a
sc
o
p
i
n
g
r
e
v
i
e
w
,
”
A
c
t
a
I
n
f
o
rm
a
t
i
c
a
Me
d
i
c
a
,
v
o
l
.
2
8
,
n
o
.
4
,
p
p
.
2
4
1
–
2
4
7
,
2
0
2
0
,
d
o
i
:
1
0
.
5
4
5
5
/
A
I
M
.
2
0
2
0
.
2
8
.
2
4
1
-
2
4
7
.
[
5
]
J.
Z
h
a
n
g
,
Y
.
J.
O
h
,
P
.
L
a
n
g
e
,
Z.
Y
u
,
a
n
d
Y
.
F
u
k
u
o
k
a
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
c
h
a
t
b
o
t
b
e
h
a
v
i
o
r
c
h
a
n
g
e
m
o
d
e
l
f
o
r
d
e
s
i
g
n
i
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
c
h
a
t
b
o
t
s
t
o
p
r
o
mo
t
e
p
h
y
si
c
a
l
a
c
t
i
v
i
t
y
a
n
d
a
h
e
a
l
t
h
y
d
i
e
t
:
v
i
e
w
p
o
i
n
t
,
”
J
o
u
r
n
a
l
o
f
M
e
d
i
c
a
l
I
n
t
e
r
n
e
t
Re
se
a
rc
h
,
v
o
l
.
2
2
,
n
o
.
9
,
p
.
e
2
2
8
4
5
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
2
1
9
6
/
2
2
8
4
5
.
[
6
]
A
.
R
.
D
e
n
n
i
s,
A
.
K
i
m,
M
.
R
a
h
i
m
i
,
a
n
d
S
.
A
y
a
b
a
k
a
n
,
“
U
ser
r
e
a
c
t
i
o
n
s t
o
C
O
V
I
D
-
1
9
scre
e
n
i
n
g
c
h
a
t
b
o
t
s
f
r
o
m
r
e
p
u
t
a
b
l
e
p
r
o
v
i
d
e
r
s,”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
r
i
c
a
n
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
Ass
o
c
i
a
t
i
o
n
,
v
o
l
.
2
7
,
n
o
.
1
1
,
p
p
.
1
7
2
7
–
1
7
3
1
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
9
3
/
j
a
m
i
a
/
o
c
a
a
1
6
7
.
[
7
]
X
.
Lu
o
,
S
.
To
n
g
,
Z
.
F
a
n
g
,
a
n
d
Z.
Q
u
,
“
F
r
o
n
t
i
e
r
s:
ma
c
h
i
n
e
s
v
s.
h
u
ma
n
s
:
t
h
e
i
m
p
a
c
t
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
c
h
a
t
b
o
t
d
i
sc
l
o
s
u
r
e
o
n
c
u
s
t
o
m
e
r
p
u
r
c
h
a
ses,
”
Ma
r
k
e
t
i
n
g
S
c
i
e
n
c
e
,
v
o
l
.
3
8
,
n
o
.
6
,
p
p
.
9
3
7
–
9
4
7
,
S
e
p
.
2
0
1
9
,
d
o
i
:
1
0
.
1
2
8
7
/
m
k
sc.
2
0
1
9
.
1
1
9
2
.
[
8
]
A
.
R
e
s
e
,
L
.
G
a
n
st
e
r
,
a
n
d
D
.
B
a
i
e
r
,
“
C
h
a
t
b
o
t
s
i
n
r
e
t
a
i
l
e
r
s’
c
u
st
o
mer
c
o
mm
u
n
i
c
a
t
i
o
n
:
h
o
w
t
o
m
e
a
s
u
r
e
t
h
e
i
r
a
c
c
e
p
t
a
n
c
e
?
,
”
J
o
u
rn
a
l
o
f
Re
t
a
i
l
i
n
g
a
n
d
C
o
n
su
m
e
r
S
e
rvi
c
e
s
,
v
o
l
.
5
6
,
p
.
1
0
2
1
7
6
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
r
e
t
c
o
n
ser.
2
0
2
0
.
1
0
2
1
7
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
64
-
73
72
[
9
]
M
.
d
e
G
e
n
n
a
r
o
,
E
.
G
.
K
r
u
mh
u
b
e
r
,
a
n
d
G
.
L
u
c
a
s,
“
Ef
f
e
c
t
i
v
e
n
e
ss
o
f
a
n
e
mp
a
t
h
i
c
c
h
a
t
b
o
t
i
n
c
o
m
b
a
t
i
n
g
a
d
v
e
r
se
e
f
f
e
c
t
s
o
f
s
o
c
i
a
l
e
x
c
l
u
si
o
n
o
n
mo
o
d
,
”
Fr
o
n
t
i
e
rs
i
n
Psy
c
h
o
l
o
g
y
,
v
o
l
.
1
0
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
s
y
g
.
2
0
1
9
.
0
3
0
6
1
.
[
1
0
]
R
.
F
u
l
m
e
r
,
A
.
J
o
e
r
i
n
,
B
.
G
e
n
t
i
l
e
,
L
.
La
k
e
r
i
n
k
,
a
n
d
M
.
R
a
u
w
s,
“
U
s
i
n
g
p
sy
c
h
o
l
o
g
i
c
a
l
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
(
t
e
ss)
t
o
r
e
l
i
e
v
e
sy
m
p
t
o
ms
o
f
d
e
p
r
e
ss
i
o
n
a
n
d
a
n
x
i
e
t
y
:
R
a
n
d
o
m
i
z
e
d
c
o
n
t
r
o
l
l
e
d
t
r
i
a
l
,
”
J
M
I
R
Me
n
t
a
l
H
e
a
l
t
h
,
v
o
l
.
5
,
n
o
.
4
,
p
.
e
6
4
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
2
1
9
6
/
me
n
t
a
l
.
9
7
8
2
.
[
1
1
]
A
.
M
a
r
t
i
n
e
t
a
l
.
,
“
A
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
b
a
s
e
d
f
i
r
st
-
l
i
n
e
d
e
f
e
n
c
e
a
g
a
i
n
st
C
O
V
I
D
-
1
9
:
d
i
g
i
t
a
l
l
y
scre
e
n
i
n
g
c
i
t
i
z
e
n
s
f
o
r
r
i
s
k
s
v
i
a
a
c
h
a
t
b
o
t
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
.
1
9
0
1
2
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
0
-
7
5
9
1
2
-
x.
[
1
2
]
L.
X
u
,
L
.
S
a
n
d
e
r
s,
K
.
Li
,
a
n
d
J.
C
.
L
.
C
h
o
w
,
“
C
h
a
t
b
o
t
f
o
r
h
e
a
l
t
h
c
a
r
e
a
n
d
o
n
c
o
l
o
g
y
a
p
p
l
i
c
a
t
i
o
n
s
u
si
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
:
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
J
MIR
C
a
n
c
e
r
,
v
o
l
.
7
,
n
o
.
4
,
p
.
e
2
7
8
5
0
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
2
1
9
6
/
2
7
8
5
0
.
[
1
3
]
C
.
B
i
r
k
e
n
b
i
h
l
e
t
a
l
.
,
“
A
N
M
e
r
g
e
:
a
c
o
mp
r
e
h
e
n
s
i
v
e
a
n
d
a
c
c
e
ssi
b
l
e
A
l
z
h
e
i
mer’
s
d
i
s
e
a
s
e
p
a
t
i
e
n
t
-
l
e
v
e
l
d
a
t
a
s
e
t
,
”
J
o
u
rn
a
l
o
f
Al
zh
e
i
m
e
r’
s Dis
e
a
s
e
,
v
o
l
.
7
9
,
n
o
.
1
,
p
p
.
4
2
3
–
4
3
1
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
2
3
3
/
J
A
D
-
2
0
0
9
4
8
.
[
1
4
]
“
2
0
2
2
A
l
z
h
e
i
mer’
s
d
i
sea
s
e
f
a
c
t
s
a
n
d
f
i
g
u
r
e
s,”
A
l
zh
e
i
m
e
r’
s
a
n
d
D
e
m
e
n
t
i
a
,
v
o
l
.
1
8
,
n
o
.
4
,
p
p
.
7
0
0
–
7
8
9
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
a
l
z
.
1
2
6
3
8
.
[
1
5
]
E.
N
i
c
h
o
l
s
e
t
a
l
.
,
“
Es
t
i
m
a
t
i
o
n
o
f
t
h
e
g
l
o
b
a
l
p
r
e
v
a
l
e
n
c
e
o
f
d
e
me
n
t
i
a
i
n
2
0
1
9
a
n
d
f
o
r
e
c
a
st
e
d
p
r
e
v
a
l
e
n
c
e
i
n
2
0
5
0
:
a
n
a
n
a
l
y
s
i
s
f
o
r
t
h
e
G
l
o
b
a
l
B
u
r
d
e
n
o
f
D
i
s
e
a
s
e
S
t
u
d
y
2
0
1
9
,
”
T
h
e
L
a
n
c
e
t
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
e
1
0
5
–
e
1
2
5
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
S
2
4
6
8
-
2
6
6
7
(
2
1
)
0
0
2
4
9
-
8.
[
1
6
]
L.
Li
u
,
S
.
Z
h
a
o
,
H
.
C
h
e
n
,
a
n
d
A
.
W
a
n
g
,
“
A
n
e
w
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
f
o
r
i
d
e
n
t
i
f
y
i
n
g
A
l
z
h
e
i
m
e
r
’
s
d
i
sea
se
,
”
S
i
m
u
l
a
t
i
o
n
Mo
d
e
l
l
i
n
g
Pra
c
t
i
c
e
a
n
d
T
h
e
o
ry
,
v
o
l
.
9
9
,
p
.
1
0
2
0
2
3
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
si
mp
a
t
.
2
0
1
9
.
1
0
2
0
2
3
.
[
1
7
]
C
.
S
.
Li
a
n
g
e
t
a
l
.
,
“
M
o
r
t
a
l
i
t
y
r
a
t
e
s
i
n
A
l
z
h
e
i
m
e
r
’
s
d
i
sea
se
a
n
d
n
o
n
-
A
l
z
h
e
i
m
e
r
’
s
d
e
me
n
t
i
a
s
:
a
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
a
n
d
m
e
t
a
-
a
n
a
l
y
si
s
,
”
T
h
e
L
a
n
c
e
t
H
e
a
l
t
h
y
L
o
n
g
e
v
i
t
y
,
v
o
l
.
2
,
n
o
.
8
,
p
p
.
e
4
7
9
–
e
4
8
8
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
S
2
6
6
6
-
7
5
6
8
(
2
1
)
0
0
1
4
0
-
9.
[
1
8
]
L.
P
a
r
n
e
t
t
i
,
E.
C
h
i
p
i
,
N
.
S
a
l
v
a
d
o
r
i
,
K
.
D
’
A
n
d
r
e
a
,
a
n
d
P
.
E
u
se
b
i
,
“
P
r
e
v
a
l
e
n
c
e
a
n
d
r
i
s
k
o
f
p
r
o
g
r
e
ss
i
o
n
o
f
p
r
e
c
l
i
n
i
c
a
l
A
l
z
h
e
i
mer’
s
d
i
s
e
a
se
st
a
g
e
s:
a
s
y
s
t
e
m
a
t
i
c
r
e
v
i
e
w
a
n
d
me
t
a
-
a
n
a
l
y
s
i
s,
”
A
l
zh
e
i
m
e
r’
s
Re
se
a
rc
h
a
n
d
T
h
e
r
a
p
y
,
v
o
l
.
1
1
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
S
1
3
1
9
5
-
0
1
8
-
0
4
5
9
-
7
/
F
I
G
U
R
ES/
4
.
[
1
9
]
A
.
M
u
z
a
mi
l
,
S
.
D
.
A
s
t
u
t
i
,
K
a
m
e
l
i
a
,
a
n
d
S
u
h
a
r
i
n
i
n
g
si
h
,
“
F
a
t
su
p
p
r
e
ssi
o
n
s
p
e
c
t
r
a
l
a
d
i
a
b
a
t
i
c
i
n
v
e
r
si
o
n
r
e
c
o
v
e
r
y
(
S
P
A
I
R
)
t
o
o
p
t
i
m
i
z
e
t
h
e
q
u
a
l
i
t
y
o
f
M
R
I
p
e
l
v
i
s
i
m
a
g
e
,
”
M
a
l
a
y
s
i
a
n
J
o
u
r
n
a
l
o
f
M
e
d
i
c
i
n
e
a
n
d
H
e
a
l
t
h
S
c
i
e
n
c
e
s
,
v
o
l
.
1
7
,
p
p
.
7
4
–
7
7
,
2
0
2
1
.
[
2
0
]
A
.
C
h
a
n
d
r
a
,
G
.
D
e
r
v
e
n
o
u
l
a
s
,
a
n
d
M
.
P
o
l
i
t
i
s,
“
M
a
g
n
e
t
i
c
r
e
s
o
n
a
n
c
e
i
mag
i
n
g
i
n
A
l
z
h
e
i
mer’
s
d
i
s
e
a
s
e
a
n
d
m
i
l
d
c
o
g
n
i
t
i
v
e
i
mp
a
i
r
m
e
n
t
,
”
J
o
u
rn
a
l
o
f
N
e
u
ro
l
o
g
y
,
v
o
l
.
2
6
6
,
n
o
.
6
,
p
p
.
1
2
9
3
–
1
3
0
2
,
J
u
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
4
1
5
-
018
-
9
0
1
6
-
3.
[
2
1
]
Y
.
X
i
a
n
g
,
J.
W
a
n
g
,
G
.
Ta
n
,
F
.
X
.
W
u
,
a
n
d
J.
Li
u
,
“
S
c
h
i
z
o
p
h
r
e
n
i
a
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
mu
l
t
i
-
v
i
e
w
g
r
a
p
h
m
e
a
s
u
r
e
s
o
f
f
u
n
c
t
i
o
n
a
l
b
r
a
i
n
n
e
t
w
o
r
k
s,
”
Fr
o
n
t
i
e
rs
i
n
B
i
o
e
n
g
i
n
e
e
ri
n
g
a
n
d
B
i
o
t
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
b
i
o
e
.
2
0
1
9
.
0
0
4
7
9
.
[
2
2
]
A
.
Zu
h
r
i
y
a
h
,
A
.
M
u
z
z
a
mi
l
,
S
.
D
.
A
st
u
t
i
,
a
n
d
S
u
h
a
r
i
n
i
n
g
si
h
,
“
D
e
t
e
r
mi
n
a
t
i
o
n
t
h
e
i
s
c
h
e
m
i
c
st
r
o
k
e
o
f
b
r
a
i
n
M
R
I
b
a
se
d
o
n
a
p
p
a
r
e
n
t
d
i
f
f
u
s
i
o
n
c
o
e
f
f
i
c
i
e
n
t
(
A
D
C
)
w
i
t
h
b
v
a
l
u
e
v
a
r
i
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s
,
v
o
l
.
1
5
0
5
,
n
o
.
1
,
p
.
0
1
2
0
4
1
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
5
0
5
/
1
/
0
1
2
0
4
1
.
[
2
3
]
S
.
N
a
m,
D
.
K
i
m
,
W
.
Ju
n
g
,
a
n
d
Y
.
Zh
u
,
“
U
n
d
e
r
st
a
n
d
i
n
g
t
h
e
r
e
se
a
r
c
h
l
a
n
d
s
c
a
p
e
o
f
d
e
e
p
l
e
a
r
n
i
n
g
i
n
b
i
o
med
i
c
a
l
s
c
i
e
n
c
e
:
sci
e
n
t
o
m
e
t
r
i
c
a
n
a
l
y
si
s
,
”
J
o
u
r
n
a
l
o
f
M
e
d
i
c
a
l
I
n
t
e
rn
e
t
Re
s
e
a
rc
h
,
v
o
l
.
2
4
,
n
o
.
4
,
p
.
e
2
8
1
1
4
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
2
1
9
6
/
2
8
1
1
4
.
[
2
4
]
“
A
l
z
h
e
i
mer’
s
r
e
s
e
a
r
c
h
U
K
’
s
i
n
f
o
r
ma
t
i
o
n
s
e
r
v
i
c
e
s
,
”
D
e
m
e
n
t
i
a
:
Y
o
u
r Q
u
e
st
i
o
n
s
A
n
sw
e
re
d
,
2
0
2
0
.
[
2
5
]
“
A
l
z
h
e
i
mer’
s
r
e
sea
r
c
h
U
K
’
s
i
n
f
o
r
ma
t
i
o
n
s
e
r
v
i
c
e
s
,
”
D
e
m
e
n
t
i
a
:
Y
o
u
r
Q
u
e
st
i
o
n
s
A
n
sw
e
re
d
,
2
0
2
2
.
h
t
t
p
s
:
/
/
w
w
w
.
a
l
z
h
e
i
mers
r
e
s
e
a
r
c
h
u
k
.
o
r
g
/
w
p
c
o
n
t
e
n
t
/
p
l
u
g
i
n
s/
m
o
f
_
b
l
_
0
.
2
.
9
/
d
o
w
n
l
o
a
d
s/
F
A
Q
_
1
2
2
0
_
1
2
2
2
_
W
EB
.
p
d
f
.
[
2
6
]
S
.
D
.
A
st
u
t
i
e
t
a
l
.
,
“
G
a
s
s
e
n
s
o
r
a
r
r
a
y
t
o
c
l
a
ss
i
f
y
t
h
e
c
h
i
c
k
e
n
m
e
a
t
w
i
t
h
E.
c
o
l
i
c
o
n
t
a
mi
n
a
n
t
b
y
u
si
n
g
r
a
n
d
o
m
f
o
r
e
st
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
,
”
B
i
o
s
e
n
so
rs
a
n
d
B
i
o
e
l
e
c
t
ro
n
i
c
s:
X
,
v
o
l
.
9
,
p
.
1
0
0
0
8
3
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
s
x
.
2
0
2
1
.
1
0
0
0
8
3
.
[
2
7
]
S
.
D
.
A
st
u
t
i
,
Y
.
M
u
k
h
a
mm
a
d
,
S
.
A
.
J
.
D
u
l
i
,
A
.
P
.
P
u
t
r
a
,
E
.
M
.
S
e
t
i
a
w
a
t
i
e
,
a
n
d
K
.
Tr
i
y
a
n
a
,
“
G
a
s se
n
s
o
r
a
r
r
a
y
s
y
st
e
m p
r
o
p
e
r
t
i
e
s fo
r
d
e
t
e
c
t
i
n
g
b
a
c
t
e
r
i
a
l
b
i
o
f
i
l
ms,
”
J
o
u
rn
a
l
o
f
Me
d
i
c
a
l
S
i
g
n
a
l
s
a
n
d
S
e
n
so
r
s
,
v
o
l
.
9
,
n
o
.
3
,
p
p
.
1
5
8
–
1
6
4
,
2
0
1
9
,
d
o
i
:
1
0
.
4
1
0
3
/
j
mss
.
JM
S
S
_
6
0
_
1
8
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Mu
h
a
m
m
a
d
S
y
a
e
k
a
r
K
a
d
a
fi
b
o
r
n
in
M
a
k
a
ss
a
r,
In
d
o
n
e
sia
,
o
n
De
c
e
m
b
e
r
2
3
,
2
0
0
2
,
h
e
e
m
b
a
rk
e
d
o
n
a
re
se
a
rc
h
jo
u
rn
e
y
m
a
rk
e
d
b
y
u
n
wa
v
e
rin
g
d
e
d
ica
ti
o
n
t
o
a
c
a
d
e
m
ic
a
c
h
iev
e
m
e
n
t.
Th
e
h
i
g
h
li
g
h
t
o
f
h
i
s
jo
u
r
n
e
y
wa
s
a
c
h
iev
in
g
a
Ba
c
h
e
lo
r'
s
d
e
g
re
e
i
n
Ro
b
o
ti
c
s
a
n
d
Artifi
c
ial
In
telli
g
e
n
c
e
En
g
i
n
e
e
rin
g
fro
m
Airlan
g
g
a
Un
iv
e
rsit
y
lo
c
a
ted
in
S
u
ra
b
a
y
a
,
Eas
t
Ja
v
a
,
In
d
o
n
e
sia
,
i
n
2
0
2
4
.
He
h
a
s
d
e
m
o
n
stra
ted
a
firm
c
o
m
m
it
m
e
n
t
to
a
d
v
a
n
c
in
g
k
n
o
wle
d
g
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
.
P
re
v
i
o
u
s
p
u
b
li
c
a
ti
o
n
s
i
n
c
lu
d
e
si
g
n
ifi
c
a
n
t
c
o
n
tr
i
b
u
t
io
n
s
t
o
Alz
h
e
ime
r'
s
Dise
a
se
P
re
d
ictio
n
u
si
n
g
M
a
c
h
i
n
e
Lea
rn
i
n
g
in
C
h
a
tb
o
ts.
C
u
rre
n
t
a
n
d
p
a
st
re
se
a
rc
h
i
n
tere
sts
in
c
lu
d
e
Alz
h
e
ime
r
’
s,
CNN
,
S
V
M
,
M
RI
,
a
n
d
Ch
a
tb
o
ts,
d
e
m
o
n
str
a
ti
n
g
c
o
n
t
in
u
e
d
d
e
d
ica
ti
o
n
to
sc
ien
ti
fic en
d
e
a
v
o
u
rs.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
sy
e
k
h
a
d
a
fi@g
m
a
il
.
c
o
m
.
Ahm
a
d
K
h
a
li
l
Ya
q
u
b
i
P
h
.
D
.
M
e
d
ica
l
P
h
y
sic
s,
M
.
Sc
.
Ex
p
e
ri
m
e
n
tal
Co
n
d
e
n
se
d
M
a
tt
e
r
P
h
y
sic
s
B
.
Sc
.
i
n
P
h
y
sic
s
a
n
d
M
a
th
e
m
a
ti
c
s,
h
e
h
a
s
1
1
p
u
b
l
ica
ti
o
n
i
n
sc
o
p
u
s
,
a
s
we
ll
a
s
c
e
rti
fica
tes
in
lea
d
e
rsh
ip
,
p
ro
jec
t
m
a
n
a
g
e
m
e
n
t,
re
se
a
rc
h
,
m
o
n
it
o
ri
n
g
a
n
d
d
a
ta an
a
ly
z
i
n
g
.
5
y
e
a
rs
o
f
d
i
v
e
rse
wo
rk
e
x
p
e
rien
c
e
in
h
u
m
a
n
re
so
u
rc
e
s,
p
r
o
jec
t
m
a
n
a
g
e
m
e
n
t,
su
p
e
r
v
isio
n
,
d
a
t
a
a
n
a
ly
z
in
g
a
n
d
fiel
d
v
isi
ts wi
th
v
a
rio
u
s i
n
tern
a
ti
o
n
a
l/
n
a
ti
o
n
a
l
o
r
g
a
n
i
z
a
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
te
d
at
e
m
a
il
:
a
h
m
a
d
.
k
h
a
li
l
.
y
a
q
u
b
i.
3
5
9
7
2
0
-
2
0
2
1
@fst.u
n
a
ir.
a
c
.
id
.
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
A
lz
h
eime
r
’
s
p
r
ed
ictio
n
via
C
N
N
-
S
V
M o
n
ch
a
tb
o
t p
la
tfo
r
m
w
ith
MRI
(
Mu
h
a
mma
d
S
ya
ek
a
r
K
a
d
a
fi
)
73
Pu
r
b
a
n
d
in
i
is
a
se
n
io
r
lec
tu
re
r
o
f
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
p
r
o
g
ra
m
stu
d
y
a
n
d
Ro
b
o
ti
c
s
a
n
d
Artif
icia
l
In
telli
g
e
n
c
e
En
g
in
e
e
rin
g
p
ro
g
ra
m
stu
d
y
a
t
Airlan
g
g
a
U
n
iv
e
rsit
y
,
wit
h
a
M
a
ste
r
o
f
Co
m
p
u
ter
(
M
.
Ko
m
)
in
I
n
fo
rm
a
ti
c
s
E
n
g
in
e
e
rin
g
fr
o
m
In
sti
tu
t
Tek
n
o
l
o
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
sia
,
in
2
0
0
6
.
S
h
e
o
b
tain
e
d
h
is
b
a
c
h
e
lo
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
in
In
stit
u
t
Tek
n
o
l
o
g
i
S
e
p
u
lu
h
N
o
p
e
m
b
e
r
S
u
ra
b
a
y
a
,
in
1
9
9
7
.
S
h
e
h
a
s
1
5
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
b
u
sin
e
ss
in
telli
g
e
n
c
e
a
n
d
c
o
m
p
u
ter
v
isio
n
.
He
r
sc
ien
ti
fic
p
ro
d
u
c
t
io
n
c
o
u
n
ts
o
v
e
r
1
4
a
rti
c
le
s
in
d
e
x
e
d
b
y
S
c
o
p
u
s,
8
a
rti
c
les
i
n
d
e
x
e
d
b
y
G
S
h
c
o
lar,
a
n
d
8
a
rti
c
les
in
d
e
x
e
d
b
y
W
o
S
.
S
h
e
p
ro
d
u
c
e
d
in
v
e
n
t
o
rs
o
f
1
p
a
ten
t
(
b
o
th
n
a
ti
o
n
a
l),
a
n
d
h
e
g
a
v
e
a
ro
u
n
d
ten
in
v
it
e
d
talk
s
a
t
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
In
p
ro
fe
ss
io
n
a
l
o
rg
a
n
iza
ti
o
n
s,
sh
e
h
a
s
r
e
c
e
n
tl
y
b
e
e
n
a
m
e
m
b
e
r
o
f
th
e
In
sti
tu
te
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
i
n
e
e
rs
(IE
EE
)
a
n
d
In
d
o
n
e
sia
n
I
n
fo
rm
a
ti
c
s
a
n
d
Co
m
p
u
ter
Hi
g
h
e
r
E
d
u
c
a
ti
o
n
As
so
c
iatio
n
(APT
IKO
M
).
He
r
c
u
rre
n
t
re
se
a
rc
h
in
c
lu
d
e
s
c
o
m
p
u
te
r
v
isio
n
,
d
a
ta
m
in
in
ig
,
a
rti
ficia
l
in
t
e
ll
ig
e
n
c
e
,
a
n
a
ly
z
e
se
n
ti
m
e
n
t,
a
n
d
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
p
u
r
b
a
n
d
in
i@fst.
u
n
a
ir
.
a
c
.
id
.
S
u
r
y
a
n
i
D
y
a
h
As
tu
ti
is
a
fu
ll
p
r
o
fe
ss
o
r
o
f
Bi
o
p
h
y
sic
s
a
t
Air
lan
g
g
a
Un
i
v
e
rsity
,
with
a
P
h
.
D
.
in
Bi
o
p
h
y
sic
s
fr
o
m
Un
i
v
e
rsitas
Airlan
g
g
a
,
In
d
o
n
e
si
a
,
in
2
0
1
1
.
S
h
e
o
b
tai
n
e
d
h
is
B.
S
c
.
in
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
a
n
d
M
.
S
c
.
i
n
Ba
n
d
u
n
g
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
In
d
o
n
e
sia
i
n
1
9
9
4
a
n
d
1
9
9
9
,
re
sp
e
c
ti
v
e
ly
.
S
h
e
h
a
s
1
5
y
e
a
rs
o
f
e
x
p
e
rie
n
c
e
in
P
h
o
to
d
y
n
a
m
ic
Th
e
ra
p
y
(P
DT)
,
m
e
d
ica
l
in
stru
m
e
n
tati
o
n
a
n
d
c
o
m
p
u
tatio
n
a
n
a
l
y
sis.
He
r
sc
ien
ti
fi
c
p
ro
d
u
c
ti
o
n
c
o
u
n
ts
o
v
e
r
2
7
7
p
a
p
e
rs,
8
4
o
f
w
h
ich
h
a
v
e
b
e
e
n
p
u
b
li
sh
e
d
in
p
e
e
r
-
re
v
iew
e
d
,
h
i
g
h
-
ra
n
k
i
n
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
.
S
h
e
p
r
o
d
u
c
e
d
i
n
v
e
n
to
rs
o
f
1
2
p
a
ten
ts
(b
o
th
n
a
ti
o
n
a
l)
,
a
n
d
h
e
g
a
v
e
a
ro
u
n
d
te
n
i
n
v
i
ted
tal
k
s
a
t
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
c
o
n
fe
r
e
n
c
e
s.
In
p
ro
fe
ss
io
n
a
l
o
rg
a
n
iza
ti
o
n
s,
sh
e
h
a
s
re
c
e
n
tl
y
b
e
e
n
a
m
e
m
b
e
r
o
f
th
e
P
h
isy
c
a
l
o
f
S
o
c
i
e
ty
In
d
o
n
e
sia
(P
S
I)
a
n
d
t
h
e
All
i
a
n
c
e
o
f
In
d
o
n
e
sia
n
M
e
d
ica
l
P
h
y
sic
ists
(AFIS
M
I).
He
r
c
u
rre
n
t
re
se
a
rc
h
in
c
lu
d
e
s
p
h
o
to
b
i
o
m
o
d
u
latio
n
,
p
h
o
to
se
n
siti
z
e
r
fo
r
P
DT,
o
z
o
n
e
tec
h
n
o
l
o
g
y
f
o
r
d
e
c
o
n
tam
in
a
ti
o
n
o
f
f
o
o
d
a
n
d
h
e
rb
a
l
m
e
d
icin
e
s,
d
ia
g
n
o
stic
a
n
d
th
e
ra
p
y
(M
RI,
CT
sc
a
n
,
Li
n
a
c
),
e
lec
tro
n
ic
n
o
se
tec
h
n
o
l
o
g
y
fo
r
fo
o
d
q
u
a
li
t
y
d
e
tec
ti
o
n
,
a
n
d
b
io
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
su
r
y
a
n
id
y
a
h
@fst.u
n
a
ir.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.