I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
24
,
p
p
.
6
3
2
2
~
6
3
3
1
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
6
3
2
2
-
6
3
3
1
6322
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Suppo
rt
v
ec
tor m
a
chine met
ho
d f
o
r clas
sify
ing
sev
er
ity o
f
Alzheimer's
ba
se
d on hippo
ca
mpu
s o
bject us
ing
ma
g
netic
reso
na
nce ima
g
ing
mo
da
lities
Ret
no
Su
priy
a
nti
1
,
Arif
P
ujo
Riy
a
nto
1
,
Yo
g
i R
a
m
a
dh
a
ni
1
,
M
uh
a
m
m
a
d Sy
a
if
ul Aliim
1
,
M
uh
a
m
m
a
d Irha
m
Ak
ba
r
1
,
H
a
ris B
ud
i
Wido
do
2
,
M
u
ha
m
m
a
d Alqa
a
f
3
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
Je
n
d
e
r
a
l
S
o
e
d
i
r
ma
n
U
n
i
v
e
r
si
t
y
,
P
u
r
b
a
l
i
n
g
g
a
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
D
e
n
t
i
st
r
y
,
F
a
c
u
l
t
y
o
f
M
e
d
i
c
a
l
,
J
e
n
d
e
r
a
l
S
o
e
d
i
r
ma
n
U
n
i
v
e
r
s
i
t
y
,
P
u
r
b
a
l
i
n
g
g
a
,
I
n
d
o
n
e
si
a
3
G
r
a
d
u
a
t
e
S
c
h
o
o
l
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
N
a
r
a
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
I
k
o
m
a
,
Ja
p
a
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
3
,
2
0
2
4
R
ev
is
ed
J
u
l 1
2
,
2
0
2
4
Acc
ep
ted
J
u
l 1
7
,
2
0
2
4
Alz
h
e
ime
r'
s
d
ise
a
se
is
a
d
e
g
e
n
e
ra
ti
v
e
b
ra
in
c
o
n
d
it
i
o
n
t
h
a
t
c
a
u
se
s
p
r
o
g
re
ss
iv
e
d
e
c
li
n
e
in
se
v
e
ra
l
a
sp
e
c
ts.
S
tart
in
g
fr
o
m
m
e
m
o
ry
,
c
o
g
n
it
iv
e
o
r
th
in
k
i
n
g
a
b
il
it
ies
,
s
p
e
a
k
in
g
a
b
il
it
ies
,
a
n
d
b
e
h
a
v
i
o
r.
C
u
rre
n
tl
y
,
Alz
h
e
ime
r'
s
d
iag
n
o
si
s
u
se
s
so
m
e
m
e
th
o
d
s,
su
c
h
a
s
b
lo
o
d
tes
ts,
sc
a
n
n
in
g
with
c
o
m
p
u
teriz
e
d
to
m
o
g
ra
p
h
y
sc
a
n
(CT
sc
a
n
),
o
r
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
ima
g
in
g
(M
RI).
As
a
re
fe
re
n
c
e
fo
r
d
e
term
in
in
g
t
h
e
le
v
e
l
o
f
se
v
e
rit
y
,
d
o
c
t
o
rs
u
su
a
ll
y
u
se
c
li
n
ica
l
d
e
m
e
n
ti
a
ra
ti
n
g
(CDR)
.
CDR
i
s
a
n
u
m
e
rica
l
sc
a
l
e
u
se
d
to
m
e
a
su
re
th
e
se
v
e
rit
y
o
f
d
e
m
e
n
ti
a
sy
m
p
to
m
s.
Th
e
d
o
c
t
o
r
will
m
a
n
u
a
ll
y
c
o
m
p
a
re
th
e
p
a
ti
e
n
t'
s
c
o
n
d
it
io
n
wi
th
th
o
se
sta
ted
o
n
t
h
e
CDR.
Th
is
c
o
n
d
it
io
n
will
tak
e
q
u
it
e
a
lo
n
g
ti
m
e
,
a
n
d
s
o
m
e
ti
m
e
s
h
u
m
a
n
e
rro
r
will
o
c
c
u
r
.
As
tec
h
n
o
lo
g
y
a
n
d
sc
ien
c
e
d
e
v
e
lo
p
,
d
o
c
to
rs
c
a
n
a
ss
ist
in
m
a
n
u
a
ll
y
d
e
tec
ti
n
g
Alz
h
e
ime
r'
s
u
sin
g
c
las
sifica
ti
o
n
a
lg
o
r
it
h
m
s.
M
a
n
y
m
e
th
o
d
s
c
a
n
b
e
u
se
d
t
o
c
las
sify
,
in
c
lu
d
in
g
th
e
CDR
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
m
e
th
o
d
.
Un
f
o
rtu
n
a
tely
,
t
h
is
m
e
th
o
d
is
u
su
a
ll
y
o
n
l
y
u
se
d
to
c
las
sify
two
c
las
se
s.
Th
is
tec
h
n
o
lo
g
y
a
ll
o
ws
th
e
c
las
sifica
ti
o
n
p
ro
c
e
ss
to
b
e
c
a
rried
o
u
t
a
u
to
m
a
ti
c
a
ll
y
a
n
d
q
u
ic
k
l
y
.
On
t
h
e
o
th
e
r
h
a
n
d
,
w
h
e
n
u
si
n
g
CDR
t
o
c
las
sify
Alz
h
e
ime
r'
s
se
v
e
rit
y
,
th
e
re
a
re
se
v
e
ra
l
sc
a
les
,
n
o
t
ju
st
two
c
las
se
s.
S
o
,
i
n
t
h
is
re
se
a
rc
h
,
we
m
o
d
ifi
e
d
th
e
u
se
o
f
S
VM
t
o
c
las
sify
t
h
re
e
lev
e
ls
o
f
se
v
e
rit
y
,
n
a
m
e
ly
sc
a
le
0
fo
r
n
o
r
m
a
l,
sc
a
le
1
f
o
r
m
il
d
c
o
n
d
it
i
o
n
s,
a
n
d
sc
a
le
2
f
o
r
m
o
d
e
ra
te
c
o
n
d
it
io
n
s.
T
h
e
e
x
p
e
rime
n
ts
we
c
a
rried
o
u
t
p
ro
v
id
e
d
a
n
a
c
c
u
ra
c
y
o
f
9
0
.
9
%
.
K
ey
w
o
r
d
s
:
Alzh
eim
er
C
las
s
if
icatio
n
C
lin
ical
d
em
en
tia
r
atin
g
M
ag
n
etic
r
eso
n
an
ce
im
a
g
in
g
m
o
d
alities
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
:
R
etn
o
Su
p
r
iy
an
ti
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
J
en
d
er
al
So
ed
i
r
m
an
Un
i
v
er
s
ity
B
later
C
am
p
u
s
,
Ma
y
jen
d
Su
n
g
k
o
n
o
s
tr
ee
t
KM
5
,
B
later
,
Pu
r
b
alin
g
g
a,
I
n
d
o
n
esia
E
m
ail:
r
etn
o
_
s
u
p
r
iy
an
ti@
u
n
s
o
ed
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Alzh
eim
er
'
s
i
s
th
e
m
o
s
t
co
m
m
o
n
n
e
u
r
o
d
eg
en
e
r
ativ
e
d
is
ea
s
e
an
d
is
th
e
m
o
s
t
co
m
m
o
n
f
o
r
m
o
f
d
em
en
tia.
T
h
e
e
x
ac
t
ca
u
s
e
o
f
Alzh
eim
er
'
s
is
n
o
t
f
u
lly
u
n
d
er
s
to
o
d
,
b
u
t
th
e
p
ath
o
lo
g
ical
p
r
o
ce
s
s
in
v
o
lv
es
th
e
f
o
r
m
atio
n
o
f
am
y
l
o
id
-
b
eta
p
la
q
u
es in
th
e
b
r
ain
an
d
th
e
ac
cu
m
u
latio
n
o
f
n
eu
r
o
f
ib
r
illar
y
tan
g
les.
T
h
ese
p
laq
u
es
an
d
tan
g
les
d
is
r
u
p
t
c
o
m
m
u
n
icatio
n
b
etwe
en
n
er
v
e
ce
lls
an
d
ca
u
s
e
n
er
v
e
ce
ll
d
am
a
g
e
an
d
d
ea
th
.
Alzh
eim
er
'
s
s
y
m
p
to
m
s
in
v
o
lv
e
p
r
o
g
r
ess
iv
e
co
g
n
itiv
e
d
ec
lin
e,
s
u
ch
as
m
em
o
r
y
l
o
s
s
,
d
if
f
icu
lty
th
in
k
in
g
,
an
d
b
eh
a
v
io
r
al
ch
an
g
es.
Patien
ts
with
Alzh
ei
m
er
'
s
m
ay
h
av
e
tr
o
u
b
le
p
er
f
o
r
m
in
g
ev
er
y
d
ay
task
s
,
r
ec
o
g
n
izin
g
p
eo
p
le
th
ey
k
n
o
w,
o
r
o
r
g
a
n
izin
g
th
eir
t
h
o
u
g
h
ts
.
C
u
r
r
e
n
tly
,
th
e
r
e
is
n
o
cu
r
e
f
o
r
Alzh
eim
e
r
'
s
,
b
u
t
th
er
e
ar
e
s
y
m
p
to
m
atic
tr
ea
tm
en
ts
an
d
m
an
a
g
em
en
t
s
tr
ateg
ies
th
at
ca
n
h
el
p
s
lo
w
t
h
e
p
r
o
g
r
ess
o
f
th
e
d
is
ea
s
e
an
d
i
m
p
r
o
v
e
th
e
p
atien
t'
s
q
u
ality
o
f
life
.
Peo
p
le
with
Al
zh
eim
er
'
s
th
r
o
u
g
h
o
u
t
th
e
wo
r
l
d
ar
e
in
cr
ea
s
in
g
r
a
p
id
ly
.
C
u
r
r
e
n
tly
,
it
is
esti
m
ated
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
meth
o
d
fo
r
cla
s
s
ifyin
g
s
ev
erit
y
o
f
A
lz
h
eime
r
's
b
a
s
ed
o
n
…
(
R
etn
o
S
u
p
r
iya
n
ti)
6323
th
at
clo
s
e
to
4
6
.
8
o
r
5
0
m
illi
o
n
p
e
o
p
le
ar
e
d
iag
n
o
s
ed
with
d
em
en
tia
in
th
e
wo
r
ld
an
d
2
0
.
9
m
illi
o
n
in
Asi
a
Pacif
ic.
T
h
er
e
a
r
e
ar
o
u
n
d
1
0
m
illi
o
n
n
ew
ca
s
es
ev
er
y
y
e
ar
.
I
n
I
n
d
o
n
esia,
it
is
esti
m
at
ed
th
at
th
e
r
e
wer
e
ar
o
u
n
d
1
.
2
m
illi
o
n
p
eo
p
le
wi
th
d
em
en
tia
i
n
2
0
1
6
,
wh
ich
will
in
cr
ea
s
e
to
2
m
illi
o
n
in
2
0
3
0
an
d
4
m
illi
o
n
p
eo
p
le
i
n
2
0
5
0
[
1
]
.
Diag
n
o
s
is
o
f
Alzh
eim
er
'
s
is
o
f
ten
a
co
m
p
lex
p
r
o
ce
s
s
an
d
r
e
q
u
ir
es
a
th
o
r
o
u
g
h
ass
ess
m
en
t
b
y
an
ex
p
er
ien
ce
d
h
ea
lth
ca
r
e
p
r
o
f
ess
io
n
al.
On
e
wa
y
to
s
u
p
p
o
r
t
th
e
d
iag
n
o
s
is
o
f
Alzh
ei
m
er
'
s
d
is
ea
s
e
is
t
o
ca
r
r
y
o
u
t a
b
r
ai
n
s
ca
n
,
esp
ec
ia
lly
to
s
ee
th
e
co
n
d
itio
n
o
f
th
e
h
ip
p
o
ca
m
p
u
s
an
d
v
en
tr
icle
ar
e
as.
Me
d
ical
im
ag
e
p
r
o
ce
s
s
in
g
th
r
o
u
g
h
th
e
m
a
g
n
etic
r
eso
n
an
ce
i
m
ag
in
g
(
MRI)
m
o
d
ality
h
as e
x
p
er
ien
ce
d
s
ig
n
if
ican
t
d
ev
el
o
p
m
en
ts
with
tech
n
o
l
o
g
ical
ad
v
an
ce
s
a
n
d
t
h
e
d
e
v
elo
p
m
e
n
t
o
f
im
ag
e
an
al
y
s
is
m
eth
o
d
s
.
So
m
e
r
esear
ch
th
at
u
s
es
d
ig
ital
im
a
g
e
p
r
o
ce
s
s
in
g
tech
n
o
lo
g
y
in
Alzh
eim
er
'
s
ca
s
es
is
a
s
f
o
llo
ws.
Dar
a
et
a
l
.
[
2
]
co
n
d
u
cte
d
a
co
m
p
a
r
ativ
e
s
tu
d
y
o
f
m
o
r
e
th
an
ei
g
h
ty
p
u
b
licatio
n
s
o
n
Alzh
eim
er
'
s
d
ia
g
n
o
s
is
th
at
u
tili
ze
m
ac
h
in
e
lear
n
in
g
an
d
m
o
r
e
t
h
an
f
if
ty
p
ap
e
r
s
th
at
d
is
cu
s
s
ap
p
r
o
ac
h
es
with
a
p
ar
ticu
lar
ar
ch
itectu
r
e.
T
h
e
co
n
clu
s
io
n
h
e
ca
m
e
to
was
th
at
all
th
e
tech
n
o
lo
g
y
th
at
was
alr
ea
d
y
in
u
s
e
n
ee
d
ed
im
p
r
o
v
em
en
t
to
b
ec
o
m
e
b
etter
.
Pra
s
ath
et
a
l
.
[
3
]
s
tu
d
ied
th
e
n
ee
d
f
o
r
s
tr
ateg
ies
in
m
ed
ical
im
ag
e
p
r
o
ce
s
s
in
g
an
d
an
aly
s
is
f
o
r
Alzh
eim
er
'
s
d
iag
n
o
s
is
.
Z
h
ao
e
t a
l
.
[
4
]
s
tu
d
ied
th
e
u
s
e
o
f
d
ee
p
lear
n
in
g
in
im
p
r
o
v
in
g
th
e
q
u
ality
an
d
ef
f
icien
cy
o
f
m
a
g
n
etic
r
eso
n
an
ce
im
ag
i
n
g
o
r
Po
s
itro
n
em
is
s
io
n
t
o
m
o
g
r
ap
h
y
in
d
iag
n
o
s
in
g
Alzh
eim
er
'
s
.
Vin
h
an
d
B
y
eo
n
[
5
]
s
tu
d
ie
d
d
ee
p
lear
n
i
n
g
,
esp
ec
ially
th
e
y
o
u
o
n
ly
l
o
o
k
o
n
ce
(
YOL
O)
a
r
ch
itectu
r
e,
in
n
eu
r
o
im
ag
in
g
an
d
m
ac
h
i
n
e
lear
n
i
n
g
f
o
r
Al
zh
eim
er
'
s
d
iag
n
o
s
is
.
Alg
h
am
ed
y
et
a
l
.
[
6
]
u
s
ed
m
ac
h
in
e
lear
n
in
g
in
m
ed
ical
im
ag
e
-
b
ased
Alzh
eim
e
r
'
s
clas
s
if
icatio
n
.
I
n
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
,
th
ey
u
s
e
th
e
c
o
n
tr
ast
-
lim
ited
ad
ap
tiv
e
h
is
to
g
r
am
eq
u
aliza
tio
n
(
C
L
AHE
)
alg
o
r
ith
m
to
im
p
r
o
v
e
im
a
g
e
q
u
ality
;
th
en
,
class
if
icatio
n
is
ca
r
r
ied
o
u
t
u
s
in
g
m
ac
h
in
e
lear
n
in
g
.
Sh
ar
m
a
et
a
l
.
[
7
]
r
esear
ch
ed
r
etin
al
o
p
tics
u
s
in
g
o
p
tical
co
h
er
en
ce
t
o
m
o
g
r
a
p
h
y
(
OC
T
)
im
ag
es
in
Alzh
eim
er
'
s
p
atien
t
s
.
T
h
is
OC
T
an
aly
s
is
is
u
s
ed
to
id
en
tify
th
e
th
ick
n
ess
o
f
th
e
r
etin
al
lay
e
r
s
an
d
ch
an
g
es
in
th
e
r
atio
,
wh
ich
ca
n
b
e
u
s
ed
as
m
ar
k
er
s
f
o
r
t
h
e
s
ev
er
ity
o
f
Alzh
eim
er
'
s
.
Sh
astri
et
a
l
.
[
8
]
u
s
ed
a
12
-
lay
er
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
co
n
s
is
tin
g
o
f
4
co
n
v
u
ls
io
n
lay
er
s
,
f
o
u
r
co
n
v
o
l
u
tio
n
al,
two
p
o
o
lin
g
,
two
f
latten
ed
,
o
n
e
d
e
n
s
e,
an
d
th
r
ee
ac
tiv
atio
n
f
u
n
c
tio
n
s
to
ca
r
r
y
o
u
t
MRI
im
ag
e
-
b
ased
Alzh
eim
er
'
s
class
if
icatio
n
.
Xin
g
et
a
l
.
[
9
]
co
n
v
e
r
ted
3
D
im
ag
es
in
to
2
D
f
u
s
ed
im
ag
es
u
s
in
g
th
e
lear
n
ab
le
weig
h
ted
p
o
o
lin
g
(
L
W
P)
m
eth
o
d
to
i
m
p
r
o
v
e
tr
ain
in
g
e
f
f
icien
cy
a
n
d
m
ai
n
tain
m
o
d
el
p
er
f
o
r
m
a
n
ce
in
Alzh
eim
er
'
s
d
iag
n
o
s
is
.
C
u
i
et
a
l
.
[
1
0
]
co
n
d
u
cted
a
n
in
-
d
e
p
th
r
e
v
iew
o
f
th
e
in
teg
r
atio
n
o
f
d
ee
p
lear
n
in
g
tech
n
iq
u
es
i
n
m
ed
ical
im
ag
e
r
ec
o
g
n
itio
n
ac
r
o
s
s
a
r
an
g
e
o
f
s
p
ec
if
ic
ap
p
r
o
a
ch
es,
in
clu
d
in
g
v
ar
io
u
s
m
o
d
al
ities
f
o
r
ap
p
licatio
n
to
Alzh
eim
er
'
s
d
iag
n
o
s
is
.
B
a
m
b
er
an
d
Vis
h
v
ak
ar
m
a
[
1
1
]
d
ev
elo
p
ed
a
m
o
d
el
f
o
r
d
ia
g
n
o
s
in
g
an
d
tr
ac
k
in
g
t
h
e
p
r
o
g
r
ess
io
n
o
f
Alzh
eim
er
'
s
s
ev
er
ity
u
s
in
g
a
C
NN
b
ased
o
n
a
s
h
allo
w
co
n
v
o
lu
tio
n
la
y
er
.
Na
et
a
l.
[
1
2
]
an
aly
ze
d
h
ea
r
in
g
ch
a
n
g
es
in
Alzh
eim
er
'
s
p
atien
ts
u
s
in
g
tr
a
n
s
g
en
ic
am
y
l
o
id
o
s
is
with
m
ic
e.
T
h
ey
co
n
clu
d
e
d
th
at
th
e
h
ea
r
in
g
ch
an
g
es
co
r
r
elate
d
with
am
y
lo
id
d
e
p
o
s
its
in
th
e
au
d
ito
r
y
b
r
ain
s
tem
an
d
wer
e
in
itially
r
ev
er
s
ib
le
th
r
o
u
g
h
i
n
cr
ea
s
ed
c
h
o
lin
er
g
ic
s
ig
n
als.
T
h
ese
r
esu
lts
ca
n
p
o
ten
tially
b
e
u
s
ed
as
an
ea
r
ly
b
i
o
m
ar
k
e
r
f
o
r
Alzh
eim
er
'
s
d
iag
n
o
s
is
.
Z
h
u
o
et
a
l
.
[
1
3
]
u
s
ed
an
Ultr
awe
ek
b
io
p
h
o
to
n
im
ag
in
g
s
y
s
tem
an
d
s
y
n
a
p
to
s
o
m
es
p
r
ep
ar
e
d
b
y
a
m
o
d
if
ied
Per
c
o
ll
m
eth
o
d
.
T
h
is
m
eth
o
d
e
v
a
lu
ates
f
u
n
ctio
n
al
ch
a
n
g
es
in
s
y
n
ap
s
es
an
d
n
er
v
e
n
etwo
r
k
s
in
p
eo
p
le
with
Alzh
eim
er
'
s
an
d
v
ascu
lar
d
em
en
tia.
Fra
n
cis
an
d
Pan
d
ian
[
1
4
]
co
m
b
in
e
th
e
Xce
p
tio
n
,
I
n
ce
p
tio
n
V3
,
an
d
Mo
b
ileNet
lay
er
alg
o
r
ith
m
s
th
at
h
av
e
p
r
ev
io
u
s
ly
b
ee
n
tr
ain
ed
.
T
h
is
alg
o
r
ith
m
was
test
ed
b
ased
o
n
T
1
weig
h
ts
o
n
Alzh
eim
er
'
s
MRI
im
ag
es.
L
iu
an
d
W
an
g
[
1
5
]
u
s
ed
th
e
Pit
t
d
at
aset
in
Alzh
eim
er
'
s
d
etec
tio
n
with
a
b
alan
ce
d
n
u
m
b
er
o
f
g
en
d
er
s
an
d
a
g
es.
T
h
e
f
ir
s
t
b
id
i
r
ec
tio
n
al
e
n
co
d
e
r
r
ep
r
esen
tatio
n
o
f
th
e
tr
ain
ed
tr
an
s
f
o
r
m
er
m
o
d
el
is
u
s
ed
to
o
b
tain
th
e
wo
r
d
v
ec
t
o
r
.
T
h
en
,
two
ch
an
n
els
ar
e
b
u
ilt
in
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
la
y
er
:
a
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
a
n
d
lo
n
g
-
an
d
s
h
o
r
t
-
ter
m
m
em
o
r
y
m
o
d
els
to
ex
tr
ac
t
l
o
ca
l
an
d
g
lo
b
al
f
ea
t
u
r
es,
wh
ich
will
b
e
u
s
ed
in
class
if
icatio
n
.
I
n
o
u
r
p
r
e
v
io
u
s
r
esear
ch
[
1
6
]
–
[
1
8
]
we
d
ev
elo
p
ed
a
s
y
s
tem
f
o
r
Alzh
eim
er
'
s
class
i
f
icatio
n
b
ased
o
n
lo
w
-
r
eso
lu
tio
n
MRI
im
ag
es.
Ho
wev
e
r
,
in
th
is
r
esear
ch
,
o
u
r
f
o
cu
s
was
o
n
l
y
o
n
co
r
o
n
al
c
r
o
s
s
-
s
ec
tio
n
s
,
ev
en
th
o
u
g
h
MRI
im
ag
es
h
av
e
t
h
r
ee
t
y
p
e
s
o
f
cr
o
s
s
-
s
ec
tio
n
s
:
co
r
o
n
al,
s
ag
ittal,
an
d
ax
ial.
He
n
ce
,
th
e
r
esu
lts
we
g
o
t
in
p
r
ev
io
u
s
r
esear
ch
co
u
ld
h
a
v
e
b
ee
n
m
o
r
e
o
p
tim
al.
T
h
e
m
ain
g
o
al
o
f
c
o
n
d
u
ctin
g
th
is
r
esear
ch
is
to
o
b
tain
in
teg
r
ated
in
f
o
r
m
atio
n
f
r
o
m
th
r
ee
ax
ial,
s
ag
ittal a
n
d
co
r
o
n
al
cr
o
s
s
-
s
ec
tio
n
s
to
s
u
p
p
o
r
t c
atar
ac
t d
iag
n
o
s
is
b
ased
o
n
th
e
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
e
(
SVM)
m
eth
o
d
.
I
n
th
is
p
ap
er
,
we
m
ak
e
im
p
r
o
v
em
en
ts
b
y
e
x
tr
ac
tin
g
f
ea
tu
r
e
s
o
n
th
e
t
h
r
ee
cr
o
s
s
-
s
ec
tio
n
s
to
m
a
k
e
th
e
r
esu
ltin
g
class
if
icatio
n
m
o
r
e
co
m
p
r
e
h
en
s
iv
e.
I
n
t
h
is
p
a
p
er
,
we
will
d
is
cu
s
s
h
o
w
t
o
ap
p
l
y
th
e
SVM
class
if
icatio
n
alg
o
r
ith
m
to
th
e
class
if
icatio
n
o
f
Alzh
eim
er
'
s
b
r
ain
im
ag
e
o
b
jects
b
ased
o
n
an
e
x
ten
s
iv
e
h
ip
p
o
ca
m
p
u
s
d
ataset
o
n
co
r
o
n
al,
ax
ial,
an
d
s
ag
ittal
im
ag
e
s
,
as
well
as
ca
lcu
latin
g
th
e
ac
cu
r
ac
y
lev
el
o
f
class
if
icatio
n
o
f
Alzh
eim
er
'
s
b
r
ain
im
ag
e
o
b
jects u
s
in
g
th
e
S
VM
m
eth
o
d
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
I
n
th
is
r
esear
ch
,
we
m
o
d
if
ied
th
e
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
m
eth
o
d
to
ca
r
r
y
o
u
t
m
u
ltil
ev
el
class
if
icatio
n
.
T
h
e
s
y
s
tem
we
d
ev
elo
p
e
d
b
eg
in
s
b
y
en
ter
i
n
g
th
e
im
ag
e
d
ata
to
b
e
test
ed
in
to
th
e
s
y
s
tem
;
th
en
,
th
e
test
im
ag
e
will
b
e
s
eg
m
e
n
ted
to
o
b
tain
th
e
r
eq
u
ir
ed
o
b
j
ec
ts
.
T
h
e
s
eg
m
en
tatio
n
r
esu
lts
will
d
eter
m
in
e
th
e
ar
ea
o
f
th
e
o
b
ject
in
t
h
e
im
a
g
e
b
ein
g
test
ed
.
Af
ter
th
e
tes
t
im
ag
e
d
ata
h
as
b
ee
n
o
b
tai
n
ed
,
th
e
d
ata
will
b
e
co
m
p
ar
ed
with
th
e
ex
is
tin
g
d
ataset
to
ca
lcu
late
th
e
p
r
o
b
ab
ilit
y
.
SVM
clas
s
if
icatio
n
c
an
o
n
ly
b
e
u
s
ed
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
3
2
2
-
6
3
3
1
6324
class
if
y
two
class
es.
T
h
er
ef
o
r
e,
we
u
s
e
m
u
ltil
ev
el
SVM
class
if
icatio
n
to
b
e
a
b
le
to
class
if
y
m
o
r
e
th
an
two
class
es.
I
n
o
u
r
s
y
s
tem
,
in
itial
lev
el
class
if
icatio
n
class
if
ies
MRI
im
ag
e
p
ar
am
eter
d
ata
o
f
th
e
h
ip
p
o
ca
m
p
u
s
b
r
ain
s
u
f
f
e
r
in
g
f
r
o
m
Azh
ei
m
er
'
s
d
is
ea
s
e
an
d
n
o
r
m
al
(
n
o
t
s
u
f
f
er
in
g
f
r
o
m
Azh
eim
er
'
s
d
is
ea
s
e)
.
I
f
SVM
id
en
tifie
s
th
e
test
d
ata
as
s
u
f
f
er
in
g
f
r
o
m
Alzh
eim
er
'
s
,
th
e
d
ata
will
p
r
o
c
ee
d
to
ad
v
a
n
ce
d
class
if
icatio
n
.
Ho
wev
er
,
if
th
e
d
ata
is
id
en
t
if
ied
as
n
o
t
s
u
f
f
er
in
g
f
r
o
m
Alzh
eim
er
'
s
,
th
e
s
y
s
tem
will
i
m
m
ed
iately
s
h
o
w
a
clin
ical
d
em
en
tia
r
atin
g
(
C
DR
)
r
esu
lt
o
f
0
,
m
ea
n
in
g
i
t
d
o
es
n
o
t
s
u
f
f
er
f
r
o
m
Alz
h
eim
er
'
s
.
Ad
v
an
ce
d
class
if
icatio
n
:
Data
th
at
h
as
u
n
d
er
g
o
n
e
in
itial
class
if
icatio
n
an
d
th
e
r
esu
lts
o
f
id
en
tify
in
g
t
h
e
d
ata
as
s
u
f
f
er
in
g
f
r
o
m
Alzh
eim
er
'
s
will
g
o
th
r
o
u
g
h
an
ad
v
a
n
ce
d
class
if
icatio
n
p
r
o
ce
s
s
.
T
h
is
ad
v
an
ce
d
class
if
icatio
n
wil
l
d
eter
m
in
e
th
e
s
ev
er
ity
le
v
el
o
f
p
e
o
p
le
with
Alzh
eim
er
'
s
b
ased
o
n
C
DR
1
(
m
ild
)
a
n
d
C
DR
2
(
m
o
d
er
ate)
class
es.
3.
M
E
T
H
O
D
3
.
1
.
I
np
ut
i
m
a
g
e
Alzh
eim
er
'
s
d
i
s
ea
s
e
is
an
ir
r
ev
er
s
ib
le
an
d
p
r
o
g
r
ess
iv
e
b
r
ain
d
is
o
r
d
er
ass
o
ciate
d
with
c
h
an
g
es
in
n
er
v
e
ce
lls
,
ca
u
s
in
g
b
r
ain
ce
l
l
d
ea
th
.
Alzh
eim
er
'
s
d
is
ea
s
e
o
cc
u
r
s
g
r
ad
u
ally
,
is
n
o
t
p
a
r
t
o
f
th
e
n
o
r
m
al
ag
in
g
p
r
o
ce
s
s
,
an
d
is
th
e
m
o
s
t
c
o
m
m
o
n
ca
u
s
e
o
f
d
e
m
en
tia
[
1
9
]
.
Me
an
wh
ile,
t
h
e
C
DR
is
a
s
ca
le
f
o
r
ev
alu
atin
g
d
em
en
tia
s
ev
er
ity
,
esp
ec
ially
f
o
r
Alzh
eim
er
'
s
.
T
h
is
r
esear
ch
u
s
ed
th
r
ee
s
ev
er
ity
s
ca
les:
a
s
ca
le
o
f
0
to
in
d
icate
n
o
r
m
al
co
n
d
itio
n
s
,
a
s
ca
le
o
f
1
f
o
r
m
ild
co
n
d
itio
n
s
,
an
d
a
s
ca
le
o
f
2
f
o
r
m
o
d
er
ate
co
n
d
itio
n
s
[
2
0
]
.
T
h
is
r
esear
ch
u
s
es
im
ag
e
d
ata
f
r
o
m
o
p
en
a
cc
ess
s
er
ies
im
ag
in
g
s
tu
d
ies
(
OASI
S
)
.
T
h
e
in
itial
d
ata
co
n
s
is
ted
o
f
cr
o
s
s
-
s
ec
tio
n
al
d
ata
co
llectio
n
f
r
o
m
4
1
6
s
u
b
jects
ag
ed
1
8
to
9
6
y
ea
r
s
.
On
e
h
u
n
d
r
e
d
s
u
b
jects
ag
ed
o
v
er
6
0
y
ea
r
s
h
av
e
b
ee
n
clin
ically
d
iag
n
o
s
ed
with
Alzh
eim
er
'
s
d
is
ea
s
e
in
th
e
m
ild
to
m
o
d
er
ate
ca
teg
o
r
y
[
2
1
]
.
Fig
u
r
e
s
1
(
a)
to
(
c)
s
h
o
w
a
n
ex
am
p
le
o
f
th
r
ee
cr
o
s
s
-
s
ec
tio
n
al
MRI
im
ag
es
(
ax
ial,
co
r
o
n
al,
a
n
d
s
ag
ittal)
u
s
ed
in
th
is
s
tu
d
y
.
(
a)
(
b
)
(
c)
Fig
u
r
e
1
.
An
ex
am
p
le
o
f
th
r
ee
cr
o
s
s
-
s
ec
tio
n
al
MRI
in
p
u
t im
ag
es
,
(
a)
ax
ial,
(
b
)
c
o
r
o
n
al
an
d
(
c)
s
ag
ittal
3
.
2
.
I
m
a
g
e
p
ro
ce
s
s
ing
I
m
ag
e
p
r
o
ce
s
s
in
g
is
p
r
o
ce
s
s
in
g
im
ag
es
to
im
p
r
o
v
e
th
e
q
u
ali
ty
,
ex
p
licitly
u
s
in
g
co
m
p
u
ter
ass
is
tan
ce
.
I
n
im
ag
e
p
r
o
ce
s
s
in
g
,
th
e
r
e
is
a
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
ca
lled
s
eg
m
en
tatio
n
.
I
m
ag
e
s
eg
m
e
n
tatio
n
aim
s
to
s
ep
ar
ate
o
b
jects
th
at
will
b
e
n
ee
d
ed
to
o
b
tain
th
eir
ch
a
r
ac
ter
is
tics
f
r
o
m
o
b
jects
th
at
will
b
e
lef
t
alo
n
e.
Gen
er
ally
,
t
h
e
o
u
tp
u
t
o
f
im
a
g
e
s
eg
m
en
tatio
n
r
esu
lts
is
a
b
in
ar
y
im
ag
e
with
th
e
d
esire
d
o
b
ject
b
ein
g
wh
ite
(
1
)
wh
ile
th
e
u
n
wan
ted
o
b
ject
is
b
lack
(
0
)
.
L
ik
e
th
e
im
ag
e
q
u
ality
im
p
r
o
v
em
en
t
p
r
o
ce
s
s
,
th
e
im
ag
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
is
also
ex
p
er
im
en
tal,
s
u
b
jectiv
e,
an
d
d
ep
e
n
d
s
o
n
th
e
g
o
als
to
ac
h
iev
e
[
2
2
]
.
T
h
e
s
eg
m
e
n
tatio
n
m
eth
o
d
ap
p
lied
in
th
is
r
esear
ch
is
ac
tiv
e
co
n
to
u
r
.
T
h
is
r
esear
ch
u
s
ed
m
ag
n
etic
r
eso
n
an
ce
im
ag
in
g
(
MRI)
d
at
a
f
r
o
m
Azh
eim
er
'
s
b
r
ain
im
a
g
e
with
th
e
jo
in
t
p
h
o
to
g
r
ap
h
ic
ex
p
e
r
ts
’
g
r
o
u
p
(
jp
g
)
ex
ten
s
io
n
.
MRI
im
ag
e
d
ata
is
d
iv
id
ed
in
to
th
r
ee
ty
p
es
o
f
p
lan
es:
ax
ial,
co
r
o
n
a
l,
an
d
s
ag
ittal.
B
ased
o
n
ea
ch
ar
ea
o
f
th
e
MRI
im
ag
e
o
f
th
e
b
r
ain
,
p
ar
t
o
f
th
e
h
ip
p
o
ca
m
p
u
s
will
b
e
v
is
ib
le,
wh
ich
is
th
e
o
b
ject
o
f
s
eg
m
en
tatio
n
to
b
e
u
s
ed
as
a
p
ar
am
eter
to
d
eter
m
in
e
th
e
s
ev
er
ity
o
f
p
e
o
p
le
liv
in
g
with
Alzh
eim
er
'
s
.
T
h
e
r
esu
lts
o
f
cu
ttin
g
o
r
c
r
o
p
p
in
g
th
e
h
ip
p
o
c
am
p
u
s
in
th
e
b
r
ain
MRI
im
ag
e
th
en
en
ter
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
s
tag
e.
T
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
s
tag
e
aim
s
to
e
x
t
r
ac
t
s
p
ec
if
ic
v
alu
es
o
r
v
ar
iab
les
th
at
ar
e
u
n
iq
u
e
c
h
ar
ac
ter
is
tics
o
f
an
o
b
ject.
T
h
e
s
e
v
alu
es
o
r
v
ar
iab
les
ar
e
u
s
e
d
to
class
if
y
o
b
jects
in
to
p
ar
ticu
lar
ca
te
g
o
r
ies o
r
class
es wi
th
s
im
ilar
o
r
th
e
s
am
e
ch
ar
ac
ter
is
tics
as sev
er
al
av
ailab
le
class
es.
3
.
3
.
Cla
s
s
if
ica
t
io
n
C
las
s
if
icatio
n
is
th
e
g
r
o
u
p
in
g
o
f
an
o
b
ject
in
to
o
n
e
o
f
th
e
p
r
e
d
eter
m
in
ed
ca
teg
o
r
ies.
T
h
e
tar
g
et
f
u
n
ctio
n
lear
n
in
g
p
r
o
ce
s
s
(
class
if
icatio
n
m
o
d
el)
will
m
a
p
ea
ch
s
et
o
f
attr
ib
u
tes
(
in
p
u
t)
to
o
n
e
o
f
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
meth
o
d
fo
r
cla
s
s
ifyin
g
s
ev
erit
y
o
f
A
lz
h
eime
r
's
b
a
s
ed
o
n
…
(
R
etn
o
S
u
p
r
iya
n
ti)
6325
p
r
ev
io
u
s
ly
d
ef
in
e
d
class
es.
I
n
p
u
t
is
a
tr
ain
i
n
g
d
ata
s
et
with
class
attr
ib
u
tes
in
th
is
d
ata.
B
ased
o
n
th
e
class
attr
ib
u
tes,
a
class
if
icatio
n
m
o
d
el
will
b
e
d
ete
r
m
in
ed
to
o
b
t
ain
a
class
if
icatio
n
m
o
d
el.
C
lass
if
icatio
n
m
o
d
els
ar
e
u
s
u
ally
u
s
ed
t
o
s
ep
ar
ate
o
b
jects
with
th
e
s
am
e
ch
ar
ac
ter
is
tics
in
to
th
e
s
am
e
class
,
wh
ile
o
b
jects
with
d
if
f
er
en
t
f
ac
t
o
r
s
will
b
e
g
r
o
u
p
ed
in
to
v
a
r
io
u
s
class
es.
I
n
th
is
r
esear
ch
,
we
u
s
e
th
e
SVM
class
if
icatio
n
m
eth
o
d
.
I
n
s
im
p
le
ter
m
s
,
th
e
co
n
ce
p
t
o
f
SVM
is
to
f
in
d
th
e
b
est
h
y
p
er
p
lan
e
th
at
f
u
n
ctio
n
s
to
s
ep
ar
ate
two
class
e
s
in
th
e
in
p
u
t.
T
h
e
b
asic
p
r
in
ci
p
le
o
f
SVM
is
a
l
in
ea
r
class
if
ier
,
wh
ich
was
f
u
r
th
er
d
ev
elo
p
e
d
to
wo
r
k
o
n
n
o
n
-
lin
ea
r
p
r
o
b
lem
s
.
T
h
e
b
est
way
to
s
ep
ar
ate
th
e
h
y
p
e
r
p
lan
e
b
etwe
en
two
class
es
ca
n
b
e
d
eter
m
in
e
d
b
y
m
ea
s
u
r
in
g
th
e
m
ar
g
in
o
f
th
e
h
y
p
er
p
lan
e.
T
h
e
m
ar
g
in
is
th
e
d
is
tan
ce
b
etwe
en
th
e
h
y
p
er
p
l
an
e
an
d
th
e
clo
s
est
p
atter
n
f
r
o
m
ea
ch
class
[
2
3
]
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
r
esear
ch
,
we
u
s
e
p
o
ly
g
o
n
cu
ttin
g
.
Po
ly
g
o
n
c
u
ttin
g
w
as
ch
o
s
en
b
ec
au
s
e
it
ca
n
ad
ju
s
t
th
e
s
h
ap
e
o
f
th
e
h
ip
p
o
ca
m
p
u
s
q
u
ite
well
s
o
th
at
a
n
ea
t
cu
ttin
g
s
h
ap
e
is
o
b
tain
e
d
an
d
is
ce
n
ter
ed
o
n
ly
o
n
th
e
h
ip
p
o
ca
m
p
u
s
.
Fig
u
r
es
2
,
3
,
a
n
d
4
s
h
o
w
ex
am
p
les
o
f
cr
o
p
p
in
g
s
tag
es
u
s
ed
to
o
b
tain
h
i
p
p
o
ca
m
p
u
s
o
b
jects
in
MRI
b
r
ain
im
ag
es
b
y
cu
ttin
g
p
o
ly
g
o
n
s
in
th
e
s
ag
ittal,
a
x
ial,
an
d
co
r
o
n
al
p
lan
es.
T
h
e
f
o
llo
win
g
p
r
o
ce
s
s
f
ea
tu
r
es e
x
tr
ac
tio
n
af
ter
th
e
cr
o
p
p
in
g
s
tag
e
is
ca
r
r
ied
o
u
t p
r
o
p
er
ly
u
n
til th
e
d
esire
d
test
o
b
ject
is
o
b
tain
ed
.
T
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
ed
in
th
is
r
esear
ch
is
im
ag
e
s
eg
m
en
tatio
n
u
s
in
g
th
e
ac
tiv
e
co
n
to
u
r
m
eth
o
d
.
Activ
e
co
n
to
u
r
u
s
es
th
e
p
r
in
cip
le
o
f
m
in
im
izin
g
en
e
r
g
y
,
wh
ich
d
et
ec
ts
ce
r
tain
f
ea
tu
r
es
in
th
e
im
ag
e
an
d
is
a
f
lex
i
b
le
cu
r
v
e
th
at
ca
n
ad
ap
t
d
y
n
a
m
ica
lly
to
war
d
th
e
d
esire
d
ed
g
e
b
o
u
n
d
ar
y
o
r
o
b
ject
[
2
4
]
.
Fig
u
r
e
2
.
C
r
o
p
p
in
g
s
tag
es in
th
e
s
ag
ittal p
lan
e
with
p
o
ly
g
o
n
s
Fig
u
r
e
3
.
C
r
o
p
p
in
g
s
tag
es in
th
e
ax
ial
p
lan
e
with
p
o
ly
g
o
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
3
2
2
-
6
3
3
1
6326
Fig
u
r
e
4
.
C
r
o
p
p
in
g
s
tag
es in
co
r
o
n
al
p
lan
e
with
p
o
ly
g
o
n
s
Fro
m
th
e
s
eg
m
en
tatio
n
r
es
u
lts
,
th
e
ch
ar
ac
ter
is
tic
p
ar
am
eter
s
o
f
th
e
o
b
ject
r
esu
ltin
g
f
r
o
m
h
ip
p
o
ca
m
p
u
s
MRI
b
r
ain
im
a
g
e
cr
o
p
p
in
g
ar
e
o
b
tain
ed
in
t
h
e
f
o
r
m
o
f
ar
ea
,
d
iam
eter
,
an
d
p
er
im
ete
r
v
al
u
es.
T
h
ese
ch
ar
ac
ter
is
tic
p
ar
am
ete
r
s
ar
e
u
s
ed
as
tr
ain
in
g
an
d
te
s
t
d
ata
at
th
e
class
if
icatio
n
s
tag
e.
Fig
u
r
es
5
to
7
s
h
o
w
ex
am
p
les
o
f
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
s
tag
es
o
b
tain
ed
f
r
o
m
ax
ial,
s
ag
ittal,
an
d
co
r
o
n
a
l
MRI
b
r
ain
im
ag
e
s
ec
tio
n
s
.
I
n
Fig
u
r
e
5
,
th
e
ar
ea
p
ar
am
eter
v
al
u
e
is
4
2
4
,
th
e
av
er
ag
e
d
iam
eter
is
2
3
.
3
2
3
4
7
,
a
n
d
th
e
p
e
r
im
eter
is
8
2
.
6
6
9
.
I
t
is
class
if
ied
in
th
e
C
DR
ca
teg
o
r
y
0
.
I
n
Fig
u
r
e
6
,
th
e
ar
ea
p
ar
am
eter
v
alu
e
is
2
1
4
,
th
e
a
v
er
ag
e
d
iam
eter
is
1
6
.
5
0
6
8
,
an
d
t
h
e
p
er
im
eter
is
9
6
.
3
2
5
9
,
class
if
ied
in
th
e
C
DR
ca
teg
o
r
y
1
.
I
n
Fig
u
r
e
7
,
th
e
ar
ea
p
ar
am
eter
v
al
u
e
is
1
9
9
,
th
e
a
v
er
ag
e
d
iam
eter
is
1
5
.
9
1
7
7
,
an
d
th
e
p
er
im
eter
is
7
9
.
2
5
4
8
,
class
if
ied
in
C
DR
ca
teg
o
r
y
2
.
T
h
e
s
eg
m
en
tatio
n
r
esu
lts
in
ch
ar
ac
ter
is
tic
p
ar
a
m
eter
s
ar
e
th
en
s
to
r
ed
t
o
f
o
r
m
a
d
ata
s
et,
wh
ich
will
later
b
e
u
s
ed
as
tr
ain
in
g
an
d
test
d
ata
in
t
h
e
SVM
class
if
icatio
n
m
eth
o
d
.
T
h
e
d
is
tin
c
tiv
e
d
ata
r
esu
ltin
g
f
r
o
m
MRI
im
ag
e
e
x
tr
ac
tio
n
o
f
th
e
b
r
ain
i
n
th
e
h
i
p
p
o
ca
m
p
u
s
was th
en
class
if
ied
b
ased
o
n
C
DR
clas
s
u
s
in
g
th
e
SVM
class
if
icatio
n
m
eth
o
d
.
Fig
u
r
e
5
.
Featu
r
e
ex
tr
ac
tio
n
i
n
ax
ial
cr
o
s
s
-
s
ec
tio
n
SVM
r
eq
u
ir
es
tr
ain
in
g
b
y
s
to
r
in
g
th
e
s
u
p
p
o
r
t
v
ec
t
o
r
r
esu
lt
s
to
b
e
u
s
ed
ag
ain
d
u
r
in
g
p
r
e
d
ictio
n
o
r
test
in
g
.
SVM
is
n
o
t a
f
f
ec
ted
b
y
h
ig
h
d
ata
d
im
en
s
io
n
s
,
s
o
it h
as n
o
r
ed
u
ctio
n
p
r
o
ce
s
s
.
T
h
e
m
em
o
r
y
in
an
SVM
is
in
f
lu
en
ce
d
b
y
th
e
am
o
u
n
t
o
f
d
ata,
n
o
t
t
h
e
s
ize
o
f
t
h
e
d
ata
d
im
en
s
io
n
s
.
I
n
th
e
in
it
ial
s
tag
e
o
f
SVM
class
if
icatio
n
tr
ain
in
g
an
d
p
r
e
d
ictio
n
ex
p
er
im
en
ts
,
t
h
e
tr
ain
i
n
g
d
ata
is
4
4
d
ata
o
b
jects
co
n
s
is
tin
g
o
f
3
cu
ttin
g
p
lan
es
(
co
r
o
n
al,
s
ag
ittal,
an
d
ax
ial)
,
s
o
th
e
to
tal
im
ag
e
d
ata
u
s
ed
is
1
3
2
f
r
o
m
4
4
o
b
jects.
T
h
e
m
ix
tu
r
e
o
f
Alzh
eim
er
'
s
b
r
ain
M
R
I
im
ag
e
d
ata
co
n
s
is
ts
o
f
2
8
clas
s
0
d
ata
an
d
1
6
class
1
d
ata.
C
la
s
s
1
d
ata
is
M
R
I
im
ag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
meth
o
d
fo
r
cla
s
s
ifyin
g
s
ev
erit
y
o
f
A
lz
h
eime
r
's
b
a
s
ed
o
n
…
(
R
etn
o
S
u
p
r
iya
n
ti)
6327
d
ata
o
f
b
r
ain
s
th
at
ar
e
d
etec
ted
to
b
e
s
u
f
f
er
in
g
f
r
o
m
Alzh
ei
m
er
'
s
at
b
o
th
C
DR
1
an
d
C
D
R
2
lev
els.
A
t
th
e
in
itial
class
if
icatio
n
p
r
ed
ictio
n
s
tag
e,
th
e
s
y
s
tem
will
id
en
tif
y
d
ata
th
at
s
u
f
f
er
s
f
r
o
m
Alzh
e
im
er
'
s
an
d
av
er
ag
e
d
ata
(
n
o
t
s
u
f
f
e
r
in
g
f
r
o
m
Alzh
eim
er
'
s
)
.
Nex
t,
we
s
ep
ar
ate
cl
ass
1
d
ata
f
o
r
tr
ain
in
g
d
ata
f
o
r
ad
v
a
n
ce
d
SVM
class
if
icatio
n
p
r
ed
ictio
n
s
.
T
h
is
ad
v
an
ce
d
SVM
class
if
icatio
n
d
ata
co
n
s
is
ts
o
f
MRI
im
ag
es
o
f
b
r
ain
s
p
r
e
d
icted
to
s
u
f
f
er
f
r
o
m
Alzh
eim
e
r
'
s
lev
el
C
DR
1
an
d
C
DR
2
f
r
o
m
3
MRI
p
lan
es:
ax
ial,
co
r
o
n
a
l,
an
d
s
ag
ittal.
W
e
ca
r
r
ied
o
u
t
SVM
class
if
icatio
n
test
in
g
u
s
in
g
a
s
y
s
tem
th
at
we
h
av
e
d
e
v
elo
p
ed
.
T
h
e
aim
is
to
d
eter
m
in
e
h
o
w
ac
cu
r
ate
th
e
SVM
m
eth
o
d
is
f
o
r
class
if
y
in
g
Alzh
eim
er
'
s
o
b
jects
b
ased
o
n
b
r
ain
MRI
im
ag
e
d
ata
t
h
at
w
e
o
b
tain
ed
f
r
o
m
th
e
OASI
S
d
at
ab
ase.
T
h
e
test
u
s
es
3
MRI
i
m
ag
e
-
cu
ttin
g
p
lan
es:
ax
ial,
c
o
r
o
n
al,
an
d
s
ag
ittal.
T
h
e
ch
a
r
ac
ter
is
tic
d
ata
o
f
th
e
th
r
ee
cu
ttin
g
p
la
n
es
is
class
if
ied
in
to
s
p
ec
if
ic
class
es
b
ased
o
n
th
e
C
DR
v
alu
e
u
s
in
g
th
e
SVM
alg
o
r
ith
m
th
a
t
h
as
b
ee
n
cr
ea
ted
.
T
h
e
in
itial
s
tag
e
u
s
es
ac
tiv
e
co
n
to
u
r
s
eg
m
en
tatio
n
to
tak
e
ch
ar
ac
ter
is
tic
d
ata
f
r
o
m
3
MRI
f
ield
s
with
th
e
s
am
e
o
b
ject
—
f
ea
tu
r
e
ex
tr
ac
tio
n
.
Fig
u
r
e
6
.
Featu
r
e
ex
tr
ac
tio
n
i
n
co
r
o
n
al
c
r
o
s
s
-
s
ec
tio
n
Fig
u
r
e
7
.
Featu
r
e
ex
tr
ac
tio
n
i
n
s
ag
ittal c
r
o
s
s
-
s
ec
tio
n
Featu
r
e
ex
tr
ac
tio
n
is
u
s
ed
to
o
b
tain
ch
ar
ac
ter
is
tic
v
alu
es
f
r
o
m
test
d
ata
in
SVM
clas
s
if
ic
atio
n
.
T
h
e
lar
g
e
-
s
ca
le
im
ag
e
is
c
u
t
o
r
tak
en
f
r
o
m
th
e
h
ip
p
o
ca
m
p
u
s
as
a
class
if
icatio
n
o
b
ject.
T
h
e
h
ip
p
o
ca
m
p
u
s
is
p
ar
t
o
f
th
e
lim
b
ic
s
y
s
tem
.
T
h
e
lim
b
ic
s
y
s
tem
is
th
e
p
ar
t
o
f
th
e
b
r
ain
in
v
o
lv
ed
in
b
eh
av
io
r
al
an
d
em
o
tio
n
al
r
esp
o
n
s
es.
T
h
e
p
r
im
ar
y
f
u
n
ctio
n
o
f
th
e
h
ip
p
o
ca
m
p
u
s
is
lear
n
in
g
an
d
lo
n
g
-
ter
m
m
em
o
r
y
s
to
r
ag
e.
T
h
e
r
ef
o
r
e,
i
f
s
o
m
eo
n
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
3
2
2
-
6
3
3
1
6328
ex
p
er
ien
ce
s
Alzh
eim
er
'
s
,
th
e
h
ip
p
o
ca
m
p
u
s
will
s
h
r
in
k
,
b
ec
o
m
in
g
s
m
aller
th
an
o
r
d
in
ar
y
p
eo
p
le'
s
[
2
5
]
.
T
h
e
ch
ar
ac
ter
is
tic
v
ar
iab
les
tak
en
f
r
o
m
th
e
h
ip
p
o
ca
m
p
u
s
s
lic
e
im
ag
e
o
f
th
e
b
r
ain
ar
e
th
e
p
ix
el
s
ize
o
f
th
e
h
ip
p
o
ca
m
p
u
s
ar
ea
,
th
e
p
er
im
e
ter
,
an
d
th
e
d
iam
eter
o
f
th
e
h
i
p
p
o
ca
m
p
u
s
.
Peo
p
le
liv
in
g
with
Alzh
eim
er
'
s
will
h
av
e
s
m
aller
p
ix
el
v
alu
es
o
f
th
e
h
ip
p
o
ca
m
p
u
s
ar
ea
co
m
p
ar
ed
to
o
r
d
i
n
ar
y
p
e
o
p
le.
T
h
ese
ch
ar
ac
ter
is
tic
v
ar
iab
les
ar
e
p
r
o
ce
s
s
ed
u
s
in
g
ac
tiv
e
co
n
t
o
u
r
s
eg
m
en
tatio
n
.
T
h
e
f
o
llo
win
g
is
th
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
d
ata
o
b
tain
ed
f
r
o
m
6
6
MRI
im
ag
e
s
,
co
n
s
is
tin
g
o
f
2
2
MRI
im
ag
es
in
th
e
ax
ial
p
lan
e,
2
2
in
th
e
co
r
o
n
al
p
lan
e,
an
d
2
2
in
th
e
s
ag
ittal
p
lan
e
.
T
h
e
r
e
s
u
lts
o
f
all
test
d
ata
ar
e
a
co
m
b
in
atio
n
b
ased
o
n
th
e
r
esu
lts
o
f
th
e
class
if
icatio
n
p
r
ed
ictio
n
d
ata
in
th
e
t
h
r
ee
ar
e
as o
f
th
e
b
r
ai
n
MRI
im
ag
e
th
at
we
d
is
p
lay
in
T
ab
le
1
.
T
ab
le
1
.
C
lass
if
icatio
n
r
esu
lt
No
I
mag
e
C
l
a
s
si
f
i
c
a
t
i
o
n
R
e
su
l
t
Ta
r
g
e
t
I
n
f
o
r
mat
i
o
n
1
O
A
S
1
_
0
0
0
2
_
M
R
1
_
m
p
r
_
n
4
.
b
mp
C
D
R
0
0
mat
c
h
i
n
g
2
O
A
S
1
_
0
0
1
3
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
0
0
mat
c
h
i
n
g
3
O
A
S
1
_
0
0
2
0
_
M
R
1
_
m
p
r
_
n
3
.
j
p
g
C
D
R
0
0
mat
c
h
i
n
g
4
O
A
S
1
_
0
1
5
7
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
0
0
mat
c
h
i
n
g
5
O
A
S
1
_
0
0
4
4
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
0
0
mat
c
h
i
n
g
6
O
A
S
1
_
0
1
3
0
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
0
0
mat
c
h
i
n
g
7
O
A
S
1
_
0
1
3
5
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
0
0
mat
c
h
i
n
g
8
O
A
S
1
_
0
1
6
5
_
M
R
1
_
m
p
r
_
n
3
.
j
p
g
C
D
R
0
0
mat
c
h
i
n
g
9
O
A
S
1
_
0
1
6
9
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
0
n
o
t
m
a
t
c
h
10
O
A
S
1
_
0
1
7
0
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
0
0
mat
c
h
i
n
g
11
O
A
S
1
_
0
3
0
8
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
2
2
mat
c
h
i
n
g
12
O
A
S
1
_
0
3
0
8
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
2
2
mat
c
h
i
n
g
13
O
A
S
1
_
0
3
5
1
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
2
2
mat
c
h
i
n
g
14
O
A
S
1
_
0
0
5
2
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
1
mat
c
h
i
n
g
15
O
A
S
1
_
0
0
7
3
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
1
mat
c
h
i
n
g
16
O
A
S
1
_
0
3
5
1
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
1
mat
c
h
i
n
g
17
O
A
S
1
_
0
0
7
3
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
1
mat
c
h
i
n
g
18
O
A
S
1
_
0
1
8
4
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
0
1
n
o
t
m
a
t
c
h
19
O
A
S
1
_
0
1
8
5
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
1
mat
c
h
i
n
g
20
O
A
S
1
_
0
0
3
5
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
1
mat
c
h
i
n
g
21
O
A
S
1
_
0
2
7
8
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
1
mat
c
h
i
n
g
22
O
A
S
1
_
0
2
9
1
_
M
R
1
_
m
p
r
_
n
4
.
j
p
g
C
D
R
1
1
mat
c
h
i
n
g
B
ased
o
n
th
e
d
ata
in
T
ab
le
1
,
MRI
im
ag
es
wer
e
test
ed
in
3
ax
ial
p
lan
es,
co
r
o
n
al
s
ag
ittal,
with
2
2
d
ata,
co
n
s
is
tin
g
o
f
1
0
C
DR
0
d
ata,
9
C
DR
1
d
ata,
a
n
d
3
C
DR
2
d
ata.
T
h
e
p
r
ed
icted
d
ata
is
th
en
co
m
p
a
r
ed
with
th
e
ac
tu
al
tar
g
et
v
alu
e
b
a
s
ed
o
n
d
ata
f
r
o
m
OASI
S;
it
ca
n
b
e
s
ee
n
t
h
at
th
e
v
alu
es
in
th
e
p
r
ed
ictio
n
r
esu
lts
o
f
2
0
d
ata
ar
e
b
y
th
e
d
esire
d
tar
g
et
C
DR
,
wh
ile
2
d
ata
ar
e
n
o
t
b
y
th
e
tar
g
et.
Data
o
n
o
b
ject
n
u
m
b
e
r
9
(
OA
S
1
_
0
1
6
9
_
MR1
_
mp
r
_
n
4
.
jp
g
)
an
d
o
b
ject
n
u
m
b
er
1
8
(
OA
S
1
_
0
1
8
4
_
MR1
_
mp
r
_
n
4
.
jp
g
)
ar
e
n
o
t
class
if
ied
ac
co
r
d
in
g
to
th
e
ta
r
g
et
d
ata.
I
n
th
e
OA
S
1
_
0
1
6
9
_
MR1
_
mp
r
_
n
4
.
jp
g
d
ata
class
if
ied
at
C
DR
1
,
it
s
h
o
u
ld
b
e
C
DR
0
,
wh
ile
th
e
OA
S
1
_
0
1
8
4
_
MR1
_
mp
r
_
n
4
.
jp
g
d
ata
class
if
ied
at
C
D
R
0
s
h
o
u
ld
b
e
C
D
R
1
.
T
h
is
co
n
d
itio
n
ca
n
h
a
p
p
en
b
ec
a
u
s
e
it
is
n
o
t
a
cc
u
r
ate
wh
e
n
cu
ttin
g
th
e
ar
ea
o
f
th
e
ed
g
e
o
f
t
h
e
h
ip
p
o
ca
m
p
u
s
,
s
o
th
e
test
d
ata
class
if
icatio
n
r
esu
lts
d
o
n
o
t
g
et
an
ap
p
r
o
p
r
iate
v
alu
e.
B
ased
o
n
th
e
ac
cu
r
ac
y
an
d
er
r
o
r
c
alcu
latio
n
s
,
it
ca
n
b
e
s
ee
n
th
at
th
e
tes
t
r
esu
lts
h
av
e
an
ac
cu
r
ac
y
p
er
ce
n
tag
e
o
f
9
0
.
9
%
an
d
an
er
r
o
r
p
er
ce
n
tag
e
o
f
9
.
0
9
%.
T
h
e
r
esu
lts
o
f
test
in
g
th
e
class
if
ica
tio
n
s
y
s
tem
u
s
in
g
SVM
s
h
o
w
ex
ce
llen
t
ac
cu
r
ac
y
.
E
r
r
o
r
s
o
cc
u
r
b
ec
au
s
e
th
e
im
ag
e
q
u
ality
d
o
es
n
o
t
m
ee
t
s
tan
d
a
r
d
s
,
s
o
th
e
h
ip
p
o
ca
m
p
u
s
ar
ea
ca
n
n
o
t
b
e
s
eg
m
en
te
d
p
r
o
p
er
ly
.
T
h
is
co
n
d
itio
n
ca
u
s
es th
e
class
if
icatio
n
p
r
o
ce
s
s
to
ex
p
er
ien
ce
m
is
tak
es,
as lis
ted
in
T
ab
le
1
.
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
's
ac
cu
r
ac
y
lev
el
r
ea
ch
ed
9
0
.
9
%
in
test
in
g
with
b
r
ain
MRI
im
ag
e
p
lan
es
(
ax
ial,
co
r
o
n
al,
s
ag
ittal)
with
ch
ar
ac
ter
is
tic
p
ar
am
eter
s
r
esu
ltin
g
f
r
o
m
h
i
p
p
o
ca
m
p
u
s
im
ag
e
s
eg
m
en
tatio
n
u
s
in
g
th
e
ac
tiv
e
co
n
to
u
r
an
d
p
o
ly
g
o
n
c
u
ttin
g
m
eth
o
d
s
.
T
h
e
m
o
r
e
tr
ai
n
in
g
d
ata
in
th
e
SVM
will
in
cr
ea
s
e
th
e
ch
an
ce
s
o
f
b
etter
p
r
ed
ictio
n
s
b
ec
a
u
s
e
th
e
m
e
m
o
r
y
in
th
e
SVM
d
ep
en
d
s
o
n
th
e
am
o
u
n
t
o
f
d
ata,
n
o
t
o
n
th
e
s
ize
o
f
th
e
d
im
en
s
io
n
s
o
f
th
e
tr
ain
in
g
d
at
a.
T
h
e
cu
ttin
g
s
tag
e
o
f
th
e
h
ip
p
o
ca
m
p
u
s
in
th
e
MRI
im
ag
e
o
f
th
e
b
r
ain
b
ec
o
m
es
v
er
y
im
p
o
r
tan
t;
th
e
n
ea
ter
an
d
m
o
r
e
ac
cu
r
ate
th
e
h
i
p
p
o
ca
m
p
u
s
is
cu
t,
th
e
m
o
r
e
p
r
ec
is
e
th
e
s
eg
m
en
tatio
n
ch
ar
ac
ter
is
tic
d
ata
will
b
e.
T
h
e
SVM
clas
s
if
icatio
n
m
eth
o
d
ca
n
b
e
d
ev
elo
p
ed
b
y
ad
d
in
g
tr
ain
in
g
an
d
test
d
ata
to
o
b
tai
n
e
x
ac
t
ac
cu
r
ac
y
v
al
u
es.
T
h
e
s
y
s
tem
ca
n
b
e
cr
ea
ted
an
d
c
o
m
p
ar
e
d
with
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
in
g
m
eth
o
d
s
o
th
er
th
an
ac
tiv
e
co
n
to
u
r
an
d
cu
ttin
g
tech
n
iq
u
es.
Fo
r
f
u
r
th
er
r
esear
ch
,
it
is
n
ec
ess
ar
y
to
co
n
s
id
er
u
s
in
g
im
ag
e
q
u
ality
th
at
m
ee
ts
th
e
r
eq
u
i
r
em
en
ts
f
o
r
im
ag
e
-
b
ased
class
if
icatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
meth
o
d
fo
r
cla
s
s
ifyin
g
s
ev
erit
y
o
f
A
lz
h
eime
r
's
b
a
s
ed
o
n
…
(
R
etn
o
S
u
p
r
iya
n
ti)
6329
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
r
esear
ch
was
f
u
n
d
ed
b
y
Natio
n
al
R
esear
ch
an
d
I
n
n
o
v
a
tio
n
Ag
en
cy
o
r
B
ad
an
R
is
et
d
an
I
n
o
v
asi
Nasio
n
al
(
B
R
I
N)
th
r
o
u
g
h
th
e
“
R
is
et
I
n
o
va
s
i
u
n
tu
k
I
n
d
o
n
e
s
ia
Ma
ju
S
ch
eme
2
0
2
3
”
wit
h
co
n
tr
ac
t
n
u
m
b
er
3
9
/I
V/KS/0
5
/2
0
2
3
an
d
T
/5
9
9
/
UN2
3
.
1
8
/HK/0
6
.
0
0
/2
0
2
3
.
RE
F
E
R
E
NC
E
S
[
1
]
A
l
z
h
e
i
m
e
r
’
s
I
n
d
o
n
e
s
i
a
,
“
S
t
a
t
i
st
i
c
o
f
d
e
m
e
n
t
i
a
,
”
A
l
z
h
e
i
m
e
r
I
n
d
o
n
e
s
i
a
,
h
t
t
p
s:
/
/
a
l
z
i
.
o
r
.
i
d
/
s
t
a
t
i
st
i
k
-
t
e
n
t
a
n
g
-
d
e
m
e
n
s
i
a
/
A
c
c
e
sse
d
:
J
a
n
.
2
4
,
2
0
2
4
.
[
2
]
O
.
A
.
D
a
r
a
,
J.
M
.
L
o
p
e
z
-
G
u
e
d
e
,
H
.
I
.
R
a
h
e
e
m
,
J
.
R
a
h
e
b
i
,
E
.
Z
u
l
u
e
t
a
,
a
n
d
U
.
F
e
r
n
a
n
d
e
z
-
G
a
mi
z
,
“
A
l
z
h
e
i
m
e
r
’
s
d
i
s
e
a
se
d
i
a
g
n
o
si
s
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
A
s
u
r
v
e
y
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
1
4
8
2
9
8
.
[
3
]
P
.
T
a
n
d
S
.
V
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
A
l
z
h
e
i
m
e
r
’
s
d
i
s
e
a
s
e
b
y
i
ma
g
i
n
g
:
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
En
v
i
r
o
n
m
e
n
t
a
l
R
e
se
a
rc
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
2
0
,
n
o
.
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
2
0
0
2
1
2
7
3
.
[
4
]
Y
.
Z
h
a
o
e
t
a
l
.
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
A
l
z
h
e
i
m
e
r
’
s d
i
s
e
a
se
i
n
P
E
T/
M
R
i
ma
g
i
n
g
,
”
Bi
o
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
,
n
o
.
1
0
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
e
n
g
i
n
e
e
r
i
n
g
1
0
1
0
1
1
2
0
.
[
5
]
T.
Q
.
V
i
n
h
a
n
d
H
.
B
y
e
o
n
,
“
E
n
h
a
n
c
i
n
g
A
l
z
h
e
i
m
e
r
’
s
d
i
s
e
a
s
e
d
i
a
g
n
o
s
i
s:
Th
e
e
f
f
i
c
a
c
y
o
f
t
h
e
Y
O
LO
a
l
g
o
r
i
t
h
m
m
o
d
e
l
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
1
1
,
p
p
.
8
1
4
–
8
2
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
3
.
0
1
4
1
1
8
2
.
[
6
]
F
.
H
.
A
l
g
h
a
me
d
y
,
M
.
S
h
a
f
i
q
,
L.
Li
u
,
A
.
Y
a
si
n
,
R
.
A
.
K
h
a
n
,
a
n
d
H
.
S
.
M
o
h
a
mm
e
d
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
sed
m
u
l
t
i
m
o
d
e
l
c
o
m
p
u
t
i
n
g
f
o
r
m
e
d
i
c
a
l
i
ma
g
i
n
g
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
o
f
A
l
z
h
e
i
mer
d
i
s
e
a
se
,
”
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
a
n
d
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
9
2
1
1
4
7
7
.
[
7
]
S
.
N
.
S
h
a
r
ma,
J
.
W
.
M
a
r
s
h
,
M
.
S
.
Ts
i
p
u
r
sk
y
,
a
n
d
S
.
A
.
B
o
p
p
a
r
t
,
“
R
a
t
i
o
me
t
r
i
c
a
n
a
l
y
si
s
o
f
i
n
v
i
v
o
o
p
t
i
c
a
l
c
o
h
e
r
e
n
c
e
t
o
m
o
g
r
a
p
h
y
r
e
t
i
n
a
l
l
a
y
e
r
t
h
i
c
k
n
e
ss
e
s
f
o
r
d
e
t
e
c
t
i
o
n
o
f
c
h
a
n
g
e
s
i
n
A
l
z
h
e
i
m
e
r
’
s
d
i
s
e
a
s
e
,
”
T
ra
n
s
l
a
t
i
o
n
a
l
Bi
o
p
h
o
t
o
n
i
c
s
,
v
o
l
.
5
,
n
o
.
3
–
4
,
p
p
.
1
–
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
2
/
t
b
i
o
.
2
0
2
3
0
0
0
0
3
.
[
8
]
S
.
S
.
S
h
a
st
r
i
,
A
.
B
h
a
d
r
a
s
h
e
t
t
y
,
a
n
d
S
.
K
u
l
k
a
r
n
i
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
A
l
z
h
e
i
m
e
r
’
s
d
i
s
e
a
s
e
b
y
e
mp
l
o
y
i
n
g
C
N
N
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
5
,
n
o
.
2
,
p
p
.
1
4
–
2
2
,
2
0
2
3
,
d
o
i
:
1
0
.
5
8
1
5
/
i
j
i
sa.
2
0
2
3
.
0
2
.
0
2
.
[
9
]
X
.
X
i
n
g
e
t
a
l
.
,
“
Ef
f
i
c
i
e
n
t
t
r
a
i
n
i
n
g
o
n
A
l
z
h
e
i
m
e
r
’
s
d
i
s
e
a
s
e
d
i
a
g
n
o
si
s
w
i
t
h
l
e
a
r
n
a
b
l
e
w
e
i
g
h
t
e
d
p
o
o
l
i
n
g
f
o
r
3
D
P
ET
b
r
a
i
n
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
El
e
c
t
r
o
n
i
c
s (S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
1
–
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
0
2
0
4
6
7
.
[
1
0
]
H
.
C
u
i
,
L
.
H
u
,
a
n
d
L.
C
h
i
,
“
A
d
v
a
n
c
e
s
i
n
c
o
mp
u
t
e
r
-
a
i
d
e
d
me
d
i
c
a
l
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
1
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
1
2
7
0
7
9
.
[
1
1
]
S
.
S
.
B
a
m
b
e
r
a
n
d
T.
V
i
s
h
v
a
k
a
r
ma,
“
M
e
d
i
c
a
l
i
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
f
o
r
A
l
z
h
e
i
mer’
s
u
si
n
g
a
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
A
p
p
l
i
e
d
S
c
i
e
n
c
e
,
v
o
l
.
7
0
,
n
o
.
1
,
p
p
.
1
–
1
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
4
1
4
7
-
0
2
3
-
0
0
2
1
1
-
x.
[
1
2
]
D
.
N
a
e
t
a
l
.
,
“
I
n
c
r
e
a
sed
c
e
n
t
r
a
l
a
u
d
i
t
o
r
y
g
a
i
n
i
n
5
x
F
A
D
A
l
z
h
e
i
m
e
r
’
s
d
i
s
e
a
s
e
m
i
c
e
a
s
a
n
e
a
r
l
y
b
i
o
ma
r
k
e
r
c
a
n
d
i
d
a
t
e
f
o
r
A
l
z
h
e
i
m
e
r
’
s
d
i
s
e
a
se
d
i
a
g
n
o
si
s,
”
F
ro
n
t
i
e
r
s
i
n
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
7
,
n
o
.
M
a
y
,
p
p
.
1
–
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s
.
2
0
2
3
.
1
1
0
6
5
7
0
.
[
1
3
]
Z.
W
a
n
g
e
t
a
l
.
,
“
R
e
d
u
c
e
d
b
i
o
p
h
o
t
o
n
i
c
a
c
t
i
v
i
t
i
e
s
a
n
d
sp
e
c
t
r
a
l
b
l
u
e
s
h
i
f
t
i
n
A
l
z
h
e
i
mer’
s
d
i
sea
s
e
a
n
d
v
a
s
c
u
l
a
r
d
e
me
n
t
i
a
m
o
d
e
l
s
w
i
t
h
c
o
g
n
i
t
i
v
e
i
m
p
a
i
r
m
e
n
t
,
”
Fr
o
n
t
i
e
rs
i
n
A
g
i
n
g
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
S
e
p
t
e
mb
e
r
,
p
p
.
1
–
1
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
a
g
i
.
2
0
2
3
.
1
2
0
8
2
7
4
.
[
1
4
]
A
.
F
r
a
n
c
i
s
a
n
d
I
.
A
.
P
a
n
d
i
a
n
,
“
En
s
e
mb
l
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
m
u
l
t
i
-
c
l
a
ss
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
A
l
z
h
e
i
m
e
r
’
s
st
a
g
e
s
u
s
i
n
g
m
a
g
n
e
t
i
c
r
e
so
n
a
n
c
e
i
m
a
g
i
n
g
,
”
T
e
l
k
o
m
n
i
k
a
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
ro
l
)
,
v
o
l
.
2
1
,
n
o
.
2
,
p
p
.
3
7
4
–
3
8
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
2
9
2
8
/
T
EL
K
O
M
N
I
K
A
.
v
2
1
i
2
.
2
3
3
5
2
.
[
1
5
]
N
.
Li
u
a
n
d
L.
W
a
n
g
,
“
A
n
a
p
p
r
o
a
c
h
f
o
r
a
ss
i
st
i
n
g
d
i
a
g
n
o
s
i
s
o
f
A
l
z
h
e
i
mer’
s
d
i
s
e
a
s
e
b
a
s
e
d
o
n
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ss
i
n
g
,
”
Fro
n
t
i
e
rs
i
n
A
g
i
n
g
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
a
g
i
.
2
0
2
3
.
1
2
8
1
7
2
6
.
[
1
6
]
R
.
S
u
p
r
i
y
a
n
t
i
,
A
.
R
.
S
u
b
h
i
,
Y
.
R
a
m
a
d
h
a
n
i
,
a
n
d
H
.
B
.
W
i
d
o
d
o
,
“
C
o
r
o
n
a
l
s
l
i
c
e
s
se
g
me
n
t
a
t
i
o
n
o
f
mr
i
i
ma
g
e
s
u
si
n
g
a
c
t
i
v
e
c
o
n
t
o
u
r
met
h
o
d
o
n
i
n
i
t
i
a
l
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
l
z
h
e
i
m
e
r
sev
e
r
i
t
y
l
e
v
e
l
b
a
se
d
o
n
c
l
i
n
i
c
a
l
d
e
m
e
n
t
i
a
r
a
t
i
n
g
(
C
D
R
)
,
”
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
3
,
2
0
1
9
.
[
1
7
]
R
.
S
u
p
r
i
y
a
n
t
i
,
A
.
K
.
M
a
r
c
h
e
l
,
Y
.
R
a
m
a
d
h
a
n
i
,
a
n
d
H
.
B
.
W
i
d
o
d
o
,
“
C
o
r
o
n
a
l
sl
i
c
e
se
g
me
n
t
a
t
i
o
n
u
si
n
g
a
w
a
t
e
r
sh
e
d
met
h
o
d
f
o
r
e
a
r
l
y
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
e
o
p
l
e
w
i
t
h
A
l
z
h
e
i
m
e
r
’
s,”
T
e
l
k
o
m
n
i
k
a
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
ro
n
i
c
s
a
n
d
C
o
n
t
ro
l
)
,
v
o
l
.
1
9
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
2
9
2
8
/
TEL
K
O
M
N
I
K
A
.
V
1
9
I
1
.
1
5
1
4
2
.
[
1
8
]
R
.
S
u
p
r
i
y
a
n
t
i
,
A
.
R
.
S
u
b
h
i
,
E.
J.
A
s
h
a
r
i
,
F
.
A
h
ma
d
,
Y
.
R
a
ma
d
h
a
n
i
,
a
n
d
H
.
B
.
W
i
d
o
d
o
,
“
S
i
m
p
l
e
c
l
a
s
si
f
i
c
a
t
i
o
n
o
f
t
h
e
A
l
z
h
e
i
mer’
s
sev
e
r
i
t
y
i
n
s
u
p
p
o
r
t
i
n
g
st
r
e
n
g
t
h
e
n
i
n
g
t
h
e
d
i
a
g
n
o
s
i
s
o
f
p
a
t
i
e
n
t
s
b
a
se
d
o
n
R
O
C
d
i
a
g
r
a
m,
”
i
n
I
O
P
C
o
n
f
e
r
e
n
c
e
S
e
ri
e
s:
Ma
t
e
r
i
a
l
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
2
0
2
0
,
v
o
l
.
9
8
2
,
n
o
.
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
9
8
2
/
1
/
0
1
2
0
0
7
.
[
1
9
]
H
o
sp
i
t
a
l
A
u
t
h
o
r
i
t
y
,
“
S
mar
t
p
a
t
i
e
n
t
d
i
m
e
n
si
a
(
D
i
me
n
t
i
a
)
,
”
H
o
sp
i
t
a
l
A
u
t
h
o
ri
t
y
,
h
t
t
p
s:
/
/
w
w
w
2
1
.
h
a
.
o
r
g
.
h
k
/
s
martp
a
t
i
e
n
t
/
E
M
/
i
d
-
i
d
/
H
o
m
e
/
(a
c
c
e
sse
d
N
o
v
.
2
9
,
2
0
2
3
)
.
[
2
0
]
J.
M
o
r
r
i
s,
“
C
l
i
n
i
c
a
l
d
e
m
e
n
t
i
a
r
a
t
i
n
g
:
a
r
e
l
i
a
b
l
e
a
n
d
v
a
l
i
d
d
i
a
g
n
o
st
i
c
a
n
d
s
t
a
g
i
n
g
m
e
a
s
u
r
e
f
o
r
d
e
m
e
n
t
i
a
o
f
t
h
e
A
l
z
h
e
i
mer
t
y
p
e
,
”
I
n
t
Psy
c
h
o
g
e
ri
a
t
r
.
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
7
3
–
1
7
6
,
1
9
9
7
,
d
o
i
:
d
o
i
:
1
0
.
1
0
1
7
/
s
1
0
4
1
6
1
0
2
9
7
0
0
4
8
7
0
.
[
2
1
]
D
.
S
.
M
a
r
c
u
s,
T.
H
.
W
a
n
g
,
J.
P
a
r
k
e
r
,
J.
G
.
C
ser
n
a
n
s
k
y
,
J
.
C
.
M
o
r
r
i
s
,
a
n
d
R
.
L.
B
u
c
k
n
e
r
,
“
O
p
e
n
a
c
c
e
ss
ser
i
e
s
o
f
i
ma
g
i
n
g
st
u
d
i
e
s
(
O
A
S
I
S
)
:
C
r
o
ss
-
se
c
t
i
o
n
a
l
M
R
I
d
a
t
a
i
n
y
o
u
n
g
,
m
i
d
d
l
e
a
g
e
d
,
n
o
n
d
e
me
n
t
e
d
,
a
n
d
d
e
m
e
n
t
e
d
o
l
d
e
r
a
d
u
l
t
s,
”
J
o
u
r
n
a
l
o
f
C
o
g
n
i
t
i
v
e
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
9
,
n
o
.
9
,
p
p
.
1
4
9
8
–
1
5
0
7
,
2
0
0
7
,
d
o
i
:
1
0
.
1
1
6
2
/
j
o
c
n
.
2
0
0
7
.
1
9
.
9
.
1
4
9
8
.
[
2
2
]
R
a
f
a
e
l
G
o
n
z
a
l
e
z
a
n
d
R
i
c
h
a
r
d
W
o
o
d
s
,
D
i
g
i
t
a
l
i
m
a
g
e
p
ro
c
e
ss
i
n
g
,
4
t
h
e
d
.
,
v
o
l
.
1
.
N
e
w
Y
o
r
k
:
P
e
a
r
so
n
,
2
0
1
7
.
[
2
3
]
C
.
C
o
r
t
e
s
a
n
d
V
.
V
a
p
n
i
k
,
“
S
u
p
p
o
r
t
v
e
c
t
o
r
n
e
t
w
o
r
k
s
,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
2
7
3
–
2
9
7
,
1
9
9
5
.
[
2
4
]
H
.
Zi
a
,
A
.
N
i
a
z
,
a
n
d
K
.
N
.
C
h
o
i
,
“
A
c
t
i
v
e
c
o
n
t
o
u
r
mo
d
e
l
f
o
r
i
ma
g
e
s
e
g
m
e
n
t
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
2
As
i
a
C
o
n
f
e
r
e
n
c
e
o
n
Ad
v
a
n
c
e
d
R
o
b
o
t
i
c
s,
A
u
t
o
m
a
t
i
o
n
,
a
n
d
C
o
n
t
r
o
l
E
n
g
i
n
e
e
ri
n
g
,
ARAC
E
2
0
2
2
,
2
0
2
2
,
p
p
.
1
3
–
17
,
d
o
i
:
1
0
.
1
1
0
9
/
A
R
A
C
E5
6
5
2
8
.
2
0
2
2
.
0
0
0
1
1
.
[
2
5
]
Y
.
L.
R
a
o
,
B
.
G
a
n
a
r
a
j
a
,
B
.
V
.
M
u
r
l
i
man
j
u
,
a
n
d
E.
A
l
,
“
H
i
p
p
o
c
a
m
p
u
s
a
n
d
i
t
s
i
n
v
o
l
v
e
m
e
n
t
i
n
A
l
z
h
e
i
mer’
s
d
i
s
e
a
se
:
a
r
e
v
i
e
w
,
”
3
Bi
o
t
e
c
h
,
v
o
l
.
1
2
,
n
o
.
5
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
2
0
5
-
022
-
0
3
1
2
3
-
4.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
6
3
2
2
-
6
3
3
1
6330
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Re
tn
o
S
u
p
r
i
y
a
n
ti
is
a
p
ro
fe
ss
o
r
at
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
U
n
iv
e
rsit
y
,
In
d
o
n
e
sia
.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
D
in
M
a
rc
h
2
0
1
0
fr
o
m
Na
ra
In
sti
tu
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
Ja
p
a
n
.
Also
,
sh
e
re
c
e
iv
e
d
h
e
r
m
a
ste
r’s
d
e
g
re
e
a
n
d
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
2
0
0
1
a
n
d
1
9
9
8
,
re
sp
e
c
ti
v
e
l
y
,
fro
m
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
In
d
o
n
e
sia
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
ima
g
e
p
r
o
c
e
ss
in
g
,
c
o
m
p
u
ter
v
isi
o
n
,
p
a
tt
e
rn
re
c
o
g
n
it
io
n
,
b
io
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
,
e
-
h
e
a
lt
h
,
tele
-
h
e
a
lt
h
a
n
d
tele
m
e
d
icin
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
re
tn
o
_
s
u
p
ri
y
a
n
ti
@u
n
so
e
d
.
a
c
.
id
.
Ar
if
Pu
jo
Riy
a
n
to
re
c
e
iv
e
d
h
is
b
a
c
h
e
l
o
r’s
d
e
g
re
e
fro
m
E
lec
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
iv
e
rsity
I
n
d
o
n
e
sia
.
He
r
re
se
a
rc
h
is
in
tere
ste
d
i
n
t
h
e
ima
g
e
p
ro
c
e
s
sin
g
f
ield
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
rifp
u
j
o
9
1
@g
m
a
il
.
c
o
m
.
Yo
g
i
Ra
m
a
d
h
a
n
i
is
a
n
a
c
a
d
e
m
ic
sta
ff
a
t
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
i
v
e
rsity
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
h
is
M
S
G
a
d
jah
M
a
d
a
Un
iv
e
rsit
y
In
d
o
n
e
sia
,
a
n
d
h
is
b
a
c
h
e
l
o
r’s
d
e
g
re
e
fro
m
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
i
v
e
rsity
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
ter
n
e
two
r
k
,
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
,
tele
m
e
d
icin
e
a
n
d
m
e
d
ica
l
ima
g
in
g
.
He
c
a
n
b
e
c
o
n
ta
c
ted
a
t
e
m
a
il
:
y
o
g
i.
ra
m
a
d
h
a
n
i@u
n
so
e
d
.
a
c
.
i
d
.
Mu
h
a
m
m
a
d
S
y
a
if
u
l
Alii
m
is
lec
tu
re
r
sta
f
f
a
t
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
i
v
e
rsity
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
h
is
m
a
ste
r
’
s
d
e
g
re
e
i
n
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
fro
m
I
n
d
o
n
e
sia
Un
i
v
e
rsity
,
In
d
o
n
e
sia
fro
m
2
0
1
4
u
n
ti
l
2
0
1
6
,
a
n
d
h
is
b
a
c
h
e
l
o
r
’
s
d
e
g
re
e
a
lso
i
n
e
lec
tri
c
a
l
e
n
g
i
n
e
e
rin
g
fr
o
m
Je
n
d
e
ra
l
S
o
e
d
irma
n
U
n
i
v
e
rsity
,
I
n
d
o
n
e
sia
fro
m
2
0
0
8
u
n
ti
l
2
0
1
2
.
Be
f
o
re
wo
rk
in
g
a
s
lec
tu
re
r
,
he
w
o
rk
e
d
a
s
Ja
v
a
P
ro
g
ra
m
m
e
r
a
t
Ac
e
Glo
b
a
l
Co
n
su
l
ti
n
g
a
n
d
In
te
g
ra
ti
o
n
(IT
Co
n
su
l
ti
n
g
Co
m
p
a
n
y
wit
h
fo
c
u
s
e
d
o
n
Re
tail
I
n
d
u
stry
)
fr
o
m
2
0
1
3
u
n
ti
l
2
0
1
9
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
i
n
g
,
d
e
e
p
lea
rn
i
n
g
,
c
o
m
p
u
ter
v
isio
n
,
m
a
c
h
in
e
lea
rn
in
g
o
n
a
u
g
m
e
n
ted
re
a
li
ty
a
n
d
i
n
tern
e
t
o
f
t
h
i
n
g
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
u
h
a
m
m
a
d
.
sy
a
ifu
l.
a
li
im
@u
n
so
e
d
.
a
c
.
id
.
Mu
h
a
m
m
a
d
Ir
h
a
m
Akb
a
r
is
a
n
a
c
a
d
e
m
ic
sta
ff
a
t
El
e
c
t
rica
l
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
iv
e
rsit
y
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
h
is
M
S
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
In
d
o
n
e
sia
,
a
n
d
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
fr
o
m
Je
n
d
e
ra
l
S
o
e
d
irma
n
U
n
iv
e
rsit
y
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
c
o
m
p
u
ter
n
e
tw
o
rk
,
d
e
c
isio
n
su
p
p
o
rt
s
y
ste
m
,
d
a
ta
m
in
in
g
a
n
d
m
e
d
ica
l
ima
g
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
h
a
m
m
a
d
.
irh
a
m
@u
n
so
e
d
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
u
p
p
o
r
t v
ec
to
r
ma
ch
in
e
meth
o
d
fo
r
cla
s
s
ifyin
g
s
ev
erit
y
o
f
A
lz
h
eime
r
's
b
a
s
ed
o
n
…
(
R
etn
o
S
u
p
r
iya
n
ti)
6331
H
a
r
is
Bu
d
i
W
id
o
d
o
is
a
n
a
c
a
d
e
m
ic
sta
ff
a
t
P
u
b
li
c
He
a
lt
h
De
p
a
rtme
n
t,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
i
v
e
rsity
,
In
d
o
n
e
sia
.
He
re
c
e
iv
e
d
h
is
P
h
.
D
.
fr
o
m
Airlan
g
g
a
Un
i
v
e
rsity
I
n
d
o
n
e
sia
.
Also
,
He
re
c
e
iv
e
d
h
is
M
.
S
.
d
e
g
re
e
a
n
d
b
a
c
h
e
lo
r’s
d
e
g
re
e
fro
m
G
a
d
jah
M
a
d
a
Un
iv
e
rsit
y
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
st
i
n
c
lu
d
in
g
p
u
b
li
c
h
e
a
lt
h
,
e
-
h
e
a
lt
h
a
n
d
tele
m
e
d
icin
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
ris.
b
wid
o
d
o
@u
n
so
e
d
.
a
c
.
id
.
Mu
h
a
m
m
a
d
Alq
a
a
f
re
c
e
iv
e
d
h
is b
a
c
h
e
lo
r’s
d
e
g
re
e
fro
m
De
p
a
r
tme
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
,
Je
n
d
e
ra
l
S
o
e
d
irma
n
Un
i
v
e
rsity
,
In
d
o
n
e
sia
;
M
.
S
.
d
e
g
re
e
in
Na
ra
In
st
it
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
Ja
p
a
n
.
Cu
rre
n
tl
y
h
e
is
a
d
o
c
to
r
st
u
d
e
n
t
in
Na
ra
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
Ja
p
a
n
.
His
re
se
a
rc
h
in
tere
st
ima
g
e
p
ro
c
e
ss
in
g
fi
e
ld
a
n
d
b
io
i
n
fo
rm
a
ti
c
s.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
u
h
a
m
m
a
d
.
a
lq
a
a
f_
su
b
a
n
d
o
k
o
.
m
b
5
@is.
n
a
ist.
jp
.
Evaluation Warning : The document was created with Spire.PDF for Python.