I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
,
p
p
.
1
0
8
7
~
1
0
9
6
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v15
i
3
.
pp
1
0
8
7
-
1
0
9
6
1087
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Ea
rly
det
ection
of
va
scula
r stre
a
k d
ieba
ck (
V
SD)
dise
a
se in
co
co
a
plants us
in
g
deep
lea
rning
Dew
i Ma
rini Um
i A
t
m
a
j
a
1
,
Arif
Ra
hm
a
n H
a
k
im
1
,
F
a
dh
il Ro
zi
H
endra
wa
n
2
,
K
o
m
a
ng
Dia
h De
v
i
P
ra
m
esty
3
,
N
a
ufa
l F
a
dh
ila
h F
it
ra
h
3
,
F
a
iz
Ro
chma
t
ull
a
h Widh
a
p
utr
a
3
1
I
n
f
o
r
mat
i
o
n
S
y
st
e
m St
u
d
y
P
r
o
g
r
a
m,
C
e
n
t
e
r
o
f
Ex
c
e
l
l
e
n
c
e
f
o
r
H
u
ma
n
C
e
n
t
r
i
c
E
n
g
i
n
e
e
r
i
n
g
(
H
U
M
I
C
)
,
Te
l
k
o
m
U
n
i
v
e
r
si
t
y
,
J
a
k
a
r
t
a
C
a
mp
u
s,
D
K
I
Jak
a
r
t
a
,
I
n
d
o
n
e
si
a
2
I
n
f
o
r
mat
i
o
n
S
y
st
e
m St
u
d
y
P
r
o
g
r
a
m,
C
e
n
t
e
r
o
f
Ex
c
e
l
l
e
n
c
e
f
o
r
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
f
o
r
Le
a
r
n
i
n
g
a
n
d
O
p
t
i
mi
z
a
t
i
o
n
(
A
I
LO
)
,
Te
l
k
o
m
U
n
i
v
e
r
si
t
y
,
J
a
k
a
r
t
a
C
a
mp
u
s,
D
K
I
Jak
a
r
t
a
,
I
n
d
o
n
e
si
a
3
I
n
f
o
r
mat
i
o
n
S
y
st
e
m St
u
d
y
P
r
o
g
r
a
m,
Te
l
k
o
m U
n
i
v
e
r
si
t
y
,
J
a
k
a
r
t
a
C
a
mp
u
s
,
D
K
I
Jak
a
r
t
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
No
v
5
,
2
0
2
5
R
ev
is
ed
Ma
y
2
0
,
2
0
2
6
Acc
ep
ted
J
u
l 5
,
2
0
2
6
Va
sc
u
lar
stre
a
k
d
ieb
a
c
k
(VSD)
,
c
a
u
se
d
b
y
Ce
ra
to
b
a
sid
i
u
m
th
e
o
b
r
o
m
a
e
,
p
o
se
s
a
sig
n
ifi
c
a
n
t
th
re
a
t
t
o
c
o
c
o
a
(Th
e
o
b
ro
m
a
c
a
c
a
o
)
p
r
o
d
u
c
ti
o
n
,
l
e
a
d
in
g
to
su
b
sta
n
ti
a
l
y
ield
l
o
ss
e
s
a
n
d
p
la
n
t
m
o
rtalit
y
.
Earl
y
d
e
tec
ti
o
n
is
c
rit
ica
l
to
m
it
ig
a
te
d
ise
a
se
sp
re
a
d
a
n
d
re
d
u
c
e
e
c
o
n
o
m
ic
imp
a
c
t.
Wh
il
e
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(
CNN
)
a
rc
h
it
e
c
tu
re
s
li
k
e
VG
G
-
1
6
a
n
d
Re
sN
e
t
-
5
0
e
x
c
e
l
i
n
lea
f
d
ise
a
se
d
e
tec
ti
o
n
,
n
o
p
rio
r
stu
d
ies
a
d
d
re
ss
ste
m
-
b
a
se
d
VSD
sy
m
p
to
m
a
to
l
o
g
y
w
h
e
re
t
h
e
d
ise
a
se
o
rig
i
n
a
tes
i
n
v
a
sc
u
lar
ti
ss
u
e
s.
Th
is
st
u
d
y
p
re
se
n
ts
th
e
first
CNN
sp
e
c
ifi
c
a
ll
y
d
e
v
e
l
o
p
e
d
fo
r
c
o
c
o
a
ste
m
VSD
d
e
tec
ti
o
n
,
a
c
h
iev
in
g
9
9
.
1
6
%
tes
t
a
c
c
u
ra
c
y
with
a
li
g
h
twe
ig
h
t
a
rc
h
it
e
c
tu
re
th
a
t
o
u
t
p
e
rfo
rm
s VG
G
1
6
/Res
Ne
t5
0
in
b
o
t
h
a
c
c
u
ra
c
y
a
n
d
m
o
b
il
e
i
n
fe
re
n
c
e
sp
e
e
d
.
A
n
o
v
e
l
d
a
tas
e
t
o
f
2
1
5
c
o
c
o
a
ste
m
ima
g
e
s
wa
s
c
u
ra
ted
a
n
d
a
u
g
m
e
n
ted
fo
r
ro
b
u
stn
e
ss
.
Ad
d
it
i
o
n
a
l
e
v
a
lu
a
ti
o
n
m
e
tri
c
s,
in
c
lu
d
i
n
g
p
re
c
isio
n
,
re
c
a
ll
,
sp
e
c
ifi
c
it
y
,
a
n
d
F
1
-
sc
o
re
,
fu
rt
h
e
r
c
o
n
firm
t
h
e
re
li
a
b
i
li
ty
o
f
t
h
e
m
o
d
e
l.
Th
e
m
o
d
e
l
wa
s
su
c
c
e
ss
fu
ll
y
c
o
n
v
e
rte
d
in
to
Ten
so
rF
l
o
w
Li
te
(TF
Li
te
)
fo
rm
a
t,
e
n
a
b
li
n
g
d
e
p
lo
y
m
e
n
t
o
n
m
o
b
il
e
d
e
v
ice
s
fo
r
re
a
l
-
ti
m
e
d
ise
a
se
d
e
tec
ti
o
n
.
Th
is
st
u
d
y
h
i
g
h
li
g
h
ts
th
e
p
o
ten
ti
a
l
o
f
in
teg
ra
ti
n
g
d
e
e
p
lea
rn
in
g
in
to
m
o
b
i
le
a
n
d
d
ro
n
e
-
b
a
se
d
a
g
ricu
lt
u
ra
l
sy
ste
m
s
to
s
u
p
p
o
rt
p
re
c
isio
n
fa
rm
in
g
a
n
d
e
a
rly
i
n
terv
e
n
ti
o
n
str
a
teg
ies
.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
C
o
co
a
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Dee
p
lear
n
in
g
Vascu
lar
s
tr
ea
k
d
ieb
ac
k
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
:
Dew
i M
ar
in
i U
m
i A
tm
aja
I
n
f
o
r
m
atio
n
Sy
s
tem
Stu
d
y
Pr
o
g
r
am
,
C
en
ter
o
f
E
x
ce
llen
ce
f
o
r
Hu
m
an
C
en
tr
ic
E
n
g
in
ee
r
in
g
(
HUM
I
C
)
T
elk
o
m
Un
iv
e
r
s
ity
,
J
ak
ar
ta
C
am
p
u
s
J
l.
R
ay
a
Daa
n
Mo
g
o
t K
M.
1
1
,
W
est J
ak
ar
ta
1
1
7
1
0
,
DKI
J
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail: d
ewim
ar
in
iu
m
iatm
aja
@
telk
o
m
u
n
iv
er
s
ity
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
o
co
a
(
T
h
eo
b
r
o
m
a
ca
ca
o
)
is
a
s
tr
ateg
ic
ag
r
icu
ltu
r
al
co
m
m
o
d
ity
th
at
s
u
p
p
o
r
ts
th
e
liv
e
lih
o
o
d
s
o
f
m
illi
o
n
s
o
f
f
ar
m
er
s
in
tr
o
p
ic
al
co
u
n
tr
ies,
in
clu
d
in
g
I
n
d
o
n
esia,
wh
ich
is
am
o
n
g
th
e
wo
r
ld
’
s
lar
g
est
co
co
a
p
r
o
d
u
ce
r
s
[
1
]
.
H
o
wev
er
,
co
c
o
a
p
r
o
d
u
ctiv
ity
is
co
n
s
is
ten
t
ly
th
r
ea
ten
e
d
b
y
v
ar
io
u
s
d
is
ea
s
es,
with
v
ascu
lar
s
tr
ea
k
d
ieb
a
ck
(
VSD)
b
ein
g
o
n
e
o
f
th
e
m
o
s
t
d
estru
ctiv
e
[
2
]
.
VSD,
ca
u
s
ed
b
y
in
f
ec
tio
n
with
th
e
f
u
n
g
u
s
C
er
ato
b
asid
iu
m
th
eo
b
r
o
m
ae
,
a
ttack
s
th
e
v
ascu
lar
tis
s
u
es
o
f
t
h
e
p
lan
t,
lead
in
g
to
ch
a
r
ac
ter
is
tic
s
y
m
p
to
m
s
s
u
ch
as
leaf
n
ec
r
o
s
is
,
p
r
em
atu
r
e
le
af
f
all,
b
r
an
c
h
d
ieb
ac
k
,
r
ed
u
c
ed
y
ield
s
,
an
d
u
ltima
tely
,
co
c
o
a
tr
ee
m
o
r
tality
if
lef
t u
n
m
an
a
g
ed
[
3
]
.
E
ar
ly
d
etec
tio
n
o
f
VSD
is
ess
en
tial
to
p
r
e
v
en
t
th
e
s
p
r
ea
d
o
f
th
e
p
ath
o
g
en
a
n
d
to
m
in
im
ize
lo
s
s
es
[
4
]
.
T
r
ad
itio
n
al
d
etec
ti
o
n
m
eth
o
d
s
,
wh
ich
r
el
y
p
r
im
a
r
ily
o
n
m
a
n
u
al
v
is
u
al
in
s
p
ec
tio
n
b
y
f
ar
m
er
s
,
p
r
esen
t
s
ev
er
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
0
8
7
-
1
0
9
6
1088
in
h
er
en
t
lim
itatio
n
s
[
5
]
.
T
h
es
e
lim
itatio
n
s
in
clu
d
e
t
h
e
s
u
b
j
ec
tiv
ity
o
f
d
iag
n
o
s
is
,
d
ep
en
d
en
ce
o
n
in
d
i
v
id
u
al
ex
p
er
ien
ce
an
d
ex
p
e
r
tis
e,
lab
o
r
in
ten
s
ity
,
an
d
th
e
i
n
ab
ilit
y
to
d
etec
t
th
e
d
is
ea
s
e
at
an
ea
r
ly
s
tag
e
wh
en
s
y
m
p
to
m
s
ar
e
n
o
t
y
et
clea
r
l
y
v
is
ib
le
[
6
]
.
As
a
r
esu
lt,
d
etec
tio
n
o
f
te
n
o
cc
u
r
s
to
o
late,
wh
en
th
e
d
is
ea
s
e
h
as
alr
ea
d
y
s
p
r
ea
d
ex
ten
s
iv
ely
a
n
d
b
ec
o
m
e
d
if
f
icu
lt to
co
n
tr
o
l [
5
]
,
[
6
]
.
I
n
th
e
p
ast
d
ec
a
d
e,
r
ap
i
d
ad
v
an
ce
m
en
ts
in
co
m
p
u
ter
v
is
io
n
an
d
d
ee
p
lear
n
in
g
h
a
v
e
r
e
v
o
lu
tio
n
ized
v
ar
io
u
s
s
ec
to
r
s
,
in
clu
d
in
g
a
g
r
icu
ltu
r
e
[
7
]
.
C
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs),
as
an
ar
tific
ial
n
eu
r
al
n
etwo
r
k
ar
ch
itectu
r
e
s
p
ec
if
ically
d
esig
n
ed
to
p
r
o
ce
s
s
v
is
u
al
d
ata,
h
av
e
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
class
if
icatio
n
an
d
o
b
ject
d
etec
tio
n
task
s
[
8
]
.
T
h
e
ab
ilit
y
o
f
C
NNs
to
au
to
m
atica
lly
ex
tr
ac
t
h
ier
ar
ch
ical
f
ea
tu
r
es
f
r
o
m
i
m
ag
es,
with
o
u
t
th
e
n
ee
d
f
o
r
m
an
u
al
f
ea
tu
r
e
en
g
in
ee
r
in
g
,
m
a
k
es
th
em
an
id
ea
l
ca
n
d
i
d
ate
f
o
r
p
lan
t
d
is
ea
s
e
d
etec
tio
n
ap
p
licatio
n
s
[
9
]
,
[
1
0
]
.
R
ec
en
t
a
d
v
an
ce
s
in
d
ee
p
lear
n
in
g
h
av
e
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
th
e
p
er
f
o
r
m
a
n
ce
o
f
im
ag
e
-
b
ased
class
if
icatio
n
s
y
s
tem
s
,
p
ar
ticu
lar
ly
in
ag
r
ic
u
ltu
r
al
d
is
ea
s
e
d
etec
tio
n
.
Am
o
n
g
th
ese,
C
NNs
h
av
e
d
e
m
o
n
s
tr
ated
s
u
p
er
io
r
ca
p
ab
ilit
y
in
lear
n
i
n
g
h
ier
ar
ch
ical
r
e
p
r
e
s
en
tatio
n
s
o
f
v
is
u
al
f
ea
tu
r
es.
E
s
tab
lis
h
ed
ar
c
h
itectu
r
es
s
u
ch
as
VGG
-
1
6
an
d
R
esNet
-
5
0
ar
e
wid
ely
r
ec
o
g
n
ize
d
f
o
r
th
eir
r
o
b
u
s
tn
ess
an
d
g
e
n
er
aliza
tio
n
a
b
ilit
y
.
VGG
-
1
6
o
f
f
e
r
s
a
s
im
p
le
y
e
t
ef
f
ec
tiv
e
d
ee
p
ar
c
h
itectu
r
e
,
wh
ile
R
esNet
-
50
in
tr
o
d
u
ce
s
r
esid
u
al
c
o
n
n
ec
tio
n
s
th
at
ad
d
r
ess
v
an
is
h
in
g
g
r
ad
ie
n
t iss
u
es in
d
ee
p
er
n
etwo
r
k
s
.
Desp
ite
th
eir
ef
f
ec
tiv
e
n
ess
,
th
ese
ar
ch
itectu
r
es
ar
e
o
f
te
n
c
o
m
p
u
tatio
n
ally
ex
p
e
n
s
iv
e
an
d
m
ay
n
o
t
b
e
o
p
tim
al
f
o
r
d
ep
lo
y
m
en
t
i
n
r
es
o
u
r
ce
-
c
o
n
s
tr
ain
ed
en
v
ir
o
n
m
e
n
ts
s
u
ch
as
m
o
b
ile
d
e
v
ices.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
p
r
o
p
o
s
es
a
cu
s
to
m
C
NN
ar
ch
i
tectu
r
e
with
o
p
tim
ized
d
ep
t
h
an
d
p
a
r
am
eter
ef
f
icien
cy
,
aim
in
g
to
ac
h
iev
e
h
i
g
h
ac
cu
r
ac
y
wh
ile
m
ain
tain
in
g
f
ea
s
ib
ilit
y
f
o
r
r
ea
l
-
tim
e
a
p
p
lic
atio
n
s
in
ag
r
icu
ltu
r
al
s
ettin
g
s
.
T
h
is
s
tu
d
y
aim
s
to
h
ar
n
e
s
s
th
e
p
o
ten
tial
o
f
C
NNs
to
d
ev
elo
p
an
au
to
m
ate
d
d
ete
ctio
n
m
o
d
el
f
o
r
VSD
in
co
co
a
s
tem
s
.
T
h
e
f
o
cu
s
o
n
co
c
o
a
s
tem
s
is
p
ar
ticu
lar
ly
im
p
o
r
tan
t
b
ec
au
s
e
VSD
s
y
m
p
to
m
s
o
f
ten
f
ir
s
t
ap
p
ea
r
in
th
e
v
ascu
lar
tis
s
u
es
o
f
s
tem
s
an
d
y
o
u
n
g
b
r
an
c
h
es
b
e
f
o
r
e
s
p
r
ea
d
in
g
t
o
th
e
lea
v
es.
I
n
ad
d
itio
n
,
th
is
r
esear
ch
s
p
ec
if
ically
ex
p
lo
r
es
th
e
im
p
ac
t
o
f
v
a
r
y
in
g
th
e
n
u
m
b
er
o
f
co
n
v
o
l
u
tio
n
al
la
y
er
s
o
n
C
NN
p
er
f
o
r
m
a
n
ce
to
d
ete
r
m
in
e
th
e
o
p
tim
al
co
n
f
ig
u
r
atio
n
.
B
y
p
r
o
v
id
i
n
g
a
f
ast,
ac
cu
r
ate,
an
d
o
b
jectiv
e
d
etec
tio
n
s
y
s
tem
,
th
is
s
tu
d
y
s
ee
k
s
to
em
p
o
we
r
co
co
a
f
a
r
m
er
s
to
tak
e
p
r
o
ac
ti
v
e
m
itig
atio
n
m
ea
s
u
r
es,
th
er
e
b
y
im
p
r
o
v
in
g
p
lan
tatio
n
m
an
ag
em
en
t
ef
f
icien
cy
an
d
en
s
u
r
in
g
th
e
s
u
s
tain
ab
ilit
y
o
f
co
c
o
a
p
r
o
d
u
ctio
n
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
L
it
er
a
t
ur
re
v
iew
E
ar
ly
s
tu
d
ies
o
n
p
lan
t
d
is
ea
s
e
d
etec
tio
n
o
f
ten
r
e
lied
o
n
ex
p
e
r
t
s
y
s
tem
s
th
at
u
tili
ze
d
k
n
o
wled
g
e
b
ases
an
d
in
f
er
en
ce
en
g
i
n
es
[
1
1
]
.
Fo
r
in
s
tan
ce
,
a
web
-
b
ased
ex
p
er
t
s
y
s
tem
f
o
r
id
e
n
tify
in
g
p
es
ts
an
d
d
is
ea
s
es
in
co
co
a
p
lan
ts
was
d
ev
elo
p
ed
u
s
in
g
Fo
r
war
d
C
h
ain
in
g
an
d
B
ac
k
war
d
C
h
ain
in
g
m
eth
o
d
s
,
en
ab
lin
g
th
e
s
y
s
tem
to
au
to
m
atica
lly
p
r
o
v
id
e
tr
ea
tm
en
t
s
o
lu
tio
n
s
[
1
2
]
.
I
n
ad
d
itio
n
,
th
e
C
er
tain
ty
Facto
r
m
eth
o
d
h
as
b
ee
n
ap
p
lied
in
co
co
a
d
is
ea
s
e
d
iag
n
o
s
is
s
y
s
tem
s
an
d
ac
h
iev
ed
an
ac
cu
r
ac
y
r
ate
o
f
8
5
.
7
p
er
ce
n
t,
co
n
s
is
ten
t
wi
th
ex
p
er
t
d
iag
n
o
s
es
[
1
3
]
.
T
h
e
e
f
f
ec
tiv
en
ess
o
f
F
u
zz
y
L
o
g
ic
in
e
x
p
er
t
s
y
s
tem
s
f
o
r
d
etec
tin
g
p
ests
an
d
d
is
ea
s
es
in
co
co
a
h
as
also
b
ee
n
d
em
o
n
s
tr
ated
in
o
t
h
er
s
tu
d
ies
[
1
4
]
.
Alth
o
u
g
h
ex
p
e
r
t
s
y
s
tem
s
o
f
f
e
r
s
tr
u
ctu
r
ed
s
o
lu
tio
n
s
,
s
u
ch
s
y
s
tem
s
ar
e
g
en
er
ally
r
i
g
id
,
d
if
f
ic
u
lt
to
ex
p
an
d
o
r
s
c
ale,
an
d
r
e
q
u
ir
e
c
o
n
tin
u
o
u
s
m
an
u
al
u
p
d
ates
to
h
an
d
le
v
ar
iatio
n
s
o
f
s
y
m
p
t
o
m
s
o
r
n
ewly
em
er
g
i
n
g
d
is
ea
s
es.
Fu
r
th
er
m
o
r
e,
t
h
eir
ac
cu
r
ac
y
i
s
h
ig
h
ly
d
ep
en
d
en
t
o
n
th
e
c
o
m
p
leten
ess
an
d
c
o
r
r
e
ctn
ess
o
f
th
e
k
n
o
wled
g
e
b
ase
en
ter
ed
m
an
u
ally
[
1
5
]
.
W
ith
th
e
av
ailab
ilit
y
o
f
d
ig
ital
im
ag
er
y
,
m
an
y
s
tu
d
ies
h
av
e
s
h
if
ted
to
war
d
im
ag
e
p
r
o
ce
s
s
in
g
an
d
co
n
v
en
tio
n
al
m
ac
h
i
n
e
l
ea
r
n
in
g
a
p
p
r
o
ac
h
es
[
1
6
]
.
T
h
ese
m
eth
o
d
s
in
v
o
lv
e
m
a
n
u
al
f
ea
tu
r
e
e
x
tr
ac
tio
n
(
e.
g
.
,
co
lo
r
,
tex
tu
r
e,
s
h
a
p
e)
f
r
o
m
d
is
ea
s
e
im
ag
es,
f
o
llo
wed
b
y
class
if
icatio
n
u
s
in
g
alg
o
r
ith
m
s
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
,
K
-
n
e
ar
est
n
eig
h
b
o
r
s
(
KNN)
,
o
r
r
a
n
d
o
m
f
o
r
est
[
1
7
]
.
Ho
we
v
er
,
t
h
e
m
an
u
al
f
ea
tu
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
is
o
f
ten
tim
e
-
co
n
s
u
m
in
g
,
r
eq
u
ir
es
d
o
m
ai
n
ex
p
er
tis
e,
an
d
m
ay
n
o
t
b
e
o
p
t
im
al
f
o
r
ca
p
t
u
r
in
g
th
e
co
m
p
lex
f
ea
tu
r
es th
at
d
is
tin
g
u
is
h
d
if
f
er
en
t
d
is
ea
s
es [
1
8
]
.
T
h
e
em
er
g
en
ce
o
f
d
ee
p
lear
n
i
n
g
,
p
ar
ticu
lar
ly
C
NNs
,
h
as
r
e
v
o
lu
tio
n
ized
th
e
f
ield
o
f
co
m
p
u
ter
v
is
io
n
an
d
p
lan
t
d
is
ea
s
e
d
etec
tio
n
[
1
9
]
.
C
NNs
p
o
s
s
ess
th
e
u
n
iq
u
e
ab
ilit
y
to
au
to
m
atica
lly
lear
n
h
ier
a
r
ch
ical
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
d
ir
ec
tly
f
r
o
m
r
aw
im
ag
e
d
ata,
elim
in
atin
g
th
e
n
ee
d
f
o
r
m
an
u
al
f
ea
t
u
r
e
ex
tr
ac
tio
n
[
2
0
]
.
Pu
jiati
an
d
R
o
ch
m
awa
ti
ap
p
lied
C
NNs
f
o
r
th
e
i
d
en
tific
atio
n
o
f
h
er
b
al
p
lan
t
lea
f
im
ag
es,
d
em
o
n
s
tr
atin
g
th
e
ca
p
ab
ilit
y
o
f
C
NNs
in
p
lan
t
i
m
ag
e
class
if
icatio
n
[
2
1
]
.
Simi
lar
s
tu
d
ies
h
av
e
also
s
h
o
wn
t
h
e
ef
f
ec
tiv
e
n
ess
o
f
C
NN
m
eth
o
d
s
ac
r
o
s
s
v
ar
io
u
s
im
ag
e
class
if
icatio
n
task
s
,
s
u
ch
as
o
b
ject
class
if
icatio
n
in
s
a
tellite
im
ag
er
y
[
2
2
]
an
d
d
is
ea
s
e
r
ec
o
g
n
itio
n
f
r
o
m
leaf
im
ag
es,
co
n
f
ir
m
in
g
C
NNs
as
a
co
n
s
is
ten
tly
ac
cu
r
ate
a
p
p
r
o
ac
h
with
in
th
e
d
o
m
ain
o
f
v
is
u
al
class
if
icatio
n
[
2
3
]
.
Alth
o
u
g
h
C
NN
ar
ch
itectu
r
es
i
n
clu
d
in
g
VGG
-
1
6
an
d
R
esNet
-
5
0
d
em
o
n
s
tr
ate
s
tr
o
n
g
p
er
f
o
r
m
an
ce
in
p
lan
t
d
is
ea
s
e
id
en
tific
atio
n
,
th
e
m
ajo
r
ity
o
f
r
esear
ch
ce
n
ter
s
o
n
leaf
-
b
ased
s
y
m
p
to
m
s
[
2
4
]
.
Ho
wev
er
,
v
ascu
lar
co
n
d
itio
n
s
s
u
ch
as
VSD
in
itia
lly
d
ev
elo
p
with
in
s
tem
v
ascu
lar
s
tr
u
ctu
r
es,
estab
lis
h
in
g
a
s
u
b
s
tan
tial
r
esear
ch
v
o
id
.
C
u
r
r
en
tly
,
n
o
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
tu
d
ies
ad
d
r
ess
co
co
a
s
tem
VSD
d
etec
ti
o
n
,
n
o
twith
s
tan
d
in
g
its
r
o
le
in
g
en
er
atin
g
3
0
-
5
0
%
y
ea
r
ly
p
r
o
d
u
ctio
n
lo
s
s
es
th
r
o
u
g
h
o
u
t
I
n
d
o
n
esian
co
c
o
a
p
lan
tatio
n
s
[
1
]
.
Ou
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
a
r
ly
d
etec
tio
n
o
f v
a
s
cu
la
r
s
tr
ea
k
d
ieb
a
ck
(
V
S
D)
d
is
ea
s
e
in
co
co
a
p
la
n
ts
u
s
in
g
… (
Dewi
Ma
r
in
i U
mi
A
tma
ja
)
1089
r
esear
ch
b
r
id
g
es
t
h
is
g
ap
th
r
o
u
g
h
f
o
u
r
k
ey
co
n
t
r
ib
u
tio
n
s
,
i
n
clu
d
in
g
f
ir
s
t
r
eso
u
r
ce
-
e
f
f
icie
n
t
C
NN
d
ev
elo
p
ed
f
o
r
co
c
o
a
s
tem
VSD
class
if
icatio
n
with
r
ea
l
-
tim
e
m
o
b
ile/d
r
o
n
e
co
m
p
atib
ilit
y
,
a
n
o
r
ig
in
al
c
o
co
a
s
tem
im
ag
er
y
co
llectio
n
,
co
m
p
r
e
h
en
s
iv
e
ev
alu
atio
n
o
f
co
n
v
o
lu
tio
n
al
lay
er
co
n
f
ig
u
r
atio
n
s
[
2
5
]
,
an
d
a
T
en
s
o
r
Flo
w
L
ite
(TF
Li
te)
im
p
lem
e
n
tatio
n
s
u
p
p
o
r
tin
g
p
r
ec
is
io
n
a
g
r
icu
ltu
r
e
am
o
n
g
s
m
all
-
s
ca
le
g
r
o
wer
s
.
2
.
2
.
M
et
ho
d
T
h
e
r
esear
ch
m
eth
o
d
o
l
o
g
y
w
as
s
y
s
tem
atica
lly
d
esig
n
ed
to
d
ev
elo
p
a
n
d
e
v
alu
ate
a
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
th
e
ea
r
ly
d
etec
tio
n
o
f
VSD
in
co
co
a
s
tem
s
,
with
a
s
p
ec
if
ic
f
o
cu
s
o
n
co
m
p
a
r
in
g
C
NN
ar
ch
itectu
r
es
with
d
if
f
er
en
t
n
u
m
b
e
r
s
o
f
c
o
n
v
o
lu
tio
n
al
lay
e
r
s
.
T
h
e
s
tag
es o
f
th
e
s
tu
d
y
a
r
e
illu
s
tr
ated
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
R
esear
ch
m
eth
o
d
o
l
o
g
y
f
lo
wch
a
r
t f
o
r
VSD
d
etec
tio
n
in
co
c
o
a
s
tem
s
T
h
e
r
esear
ch
p
r
o
ce
s
s
b
eg
an
with
im
ag
e
d
ata
co
llectio
n
.
T
h
e
im
ag
e
d
ataset
s
er
v
ed
as
th
e
p
r
im
ar
y
f
o
u
n
d
atio
n
f
o
r
d
ev
elo
p
in
g
th
e
d
ee
p
lear
n
in
g
m
o
d
el;
th
er
ef
o
r
e,
co
co
a
s
tem
im
ag
es
wer
e
co
llected
f
r
o
m
v
ar
io
u
s
p
lan
tatio
n
s
ac
r
o
s
s
I
n
d
o
n
esia
to
en
s
u
r
e
d
iv
er
s
ity
in
e
n
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
an
d
p
lan
t
g
en
etics.
Data
co
llectio
n
was
co
n
d
u
cte
d
u
s
in
g
a
h
ig
h
-
r
eso
lu
tio
n
d
ig
it
al
ca
m
er
a
to
ca
p
tu
r
e
th
e
n
ec
ess
ar
y
v
is
u
al
d
etails.
T
h
e
d
ataset
co
n
s
is
ted
o
f
two
m
ain
class
es:
h
ea
lth
y
co
co
a
s
t
em
s
s
h
o
win
g
n
o
s
ig
n
s
o
f
VS
D
o
r
o
th
e
r
d
is
ea
s
es,
an
d
VSD
-
in
f
ec
ted
co
c
o
a
s
tem
s
ex
h
ib
itin
g
s
y
m
p
t
o
m
s
r
an
g
in
g
f
r
o
m
ea
r
ly
s
tag
es
(
s
lig
h
t
d
is
co
lo
r
atio
n
,
m
in
o
r
s
tr
ea
k
s
)
to
in
ter
m
e
d
iate
s
tag
es
(
m
o
r
e
p
r
o
n
o
u
n
ce
d
n
ec
r
o
s
is
an
d
in
itial
d
ie
b
ac
k
)
.
A
to
tal
o
f
2
1
5
im
ag
es
wer
e
co
llected
,
co
m
p
r
is
in
g
1
0
9
im
a
g
es o
f
h
ea
l
th
y
s
tem
s
an
d
1
0
6
i
m
ag
es o
f
VSD
-
in
f
ec
ted
s
tem
s
.
Af
ter
th
e
d
ata
co
llectio
n
was
co
m
p
leted
,
th
e
n
ex
t
s
tep
was
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
wh
ich
i
s
a
cr
u
cial
s
tag
e
to
en
h
an
ce
d
ata
q
u
ality
an
d
im
p
r
o
v
e
e
f
f
icien
cy
i
n
m
o
d
el
tr
ain
in
g
.
T
o
ad
d
r
ess
th
e
lim
itatio
n
o
f
d
ataset
s
ize
an
d
im
p
r
o
v
e
m
o
d
el
g
en
er
aliza
tio
n
,
d
ata
au
g
m
en
tatio
n
tech
n
iq
u
es
wer
e
ap
p
lied
.
T
h
is
au
g
m
en
tatio
n
h
elp
ed
th
e
m
o
d
el
b
ec
o
m
e
m
o
r
e
r
o
b
u
s
t
ag
ain
s
t
v
ar
iatio
n
s
in
o
r
ien
tatio
n
an
d
lig
h
ti
n
g
co
n
d
itio
n
s
.
Fu
r
th
er
m
o
r
e
,
p
ix
el
v
alu
es
wer
e
n
o
r
m
alize
d
f
r
o
m
t
h
e
r
a
n
g
e
[
0
,
2
5
5
]
t
o
[
0
,
1
]
t
o
ac
ce
ler
ate
tr
ain
in
g
co
n
v
er
g
en
ce
a
n
d
im
p
r
o
v
e
n
u
m
er
ical
s
tab
ilit
y
.
I
n
ce
r
tain
ca
s
es,
s
im
p
le
s
eg
m
en
tatio
n
tech
n
iq
u
es
(
e.
g
.
,
b
ac
k
g
r
o
u
n
d
m
ask
i
n
g
)
wer
e
ap
p
lied
to
en
s
u
r
e
th
at
th
e
m
o
d
el
f
o
c
u
s
ed
ex
clu
s
iv
ely
o
n
th
e
co
c
o
a
s
tem
ar
ea
,
th
er
eb
y
r
e
d
u
cin
g
en
v
ir
o
n
m
en
tal
n
o
is
e.
Fin
ally
,
th
e
d
ataset
was
d
iv
id
e
d
in
t
o
two
s
u
b
s
ets:
tr
ain
in
g
(
8
0
p
er
ce
n
t)
an
d
test
in
g
(
2
0
p
er
ce
n
t)
.
T
h
e
tr
ai
n
in
g
s
et
was
u
s
ed
to
tr
ain
th
e
m
o
d
el,
wh
ile
th
e
test
in
g
s
et
wa
s
em
p
lo
y
ed
f
o
r
th
e
in
d
ep
en
d
en
t e
v
alu
atio
n
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
o
ad
d
r
ess
th
e
lim
ited
s
ize
o
f
th
e
d
ataset
an
d
im
p
r
o
v
e
m
o
d
e
l
g
en
er
aliza
tio
n
,
d
ata
au
g
m
en
t
atio
n
was
p
er
f
o
r
m
ed
u
s
in
g
t
h
e
I
m
ag
eDa
taGe
n
er
ato
r
f
r
am
ewo
r
k
.
T
h
e
ap
p
lied
tr
a
n
s
f
o
r
m
atio
n
s
in
clu
d
ed
r
o
tatio
n
(
±
2
0
°),
wid
th
an
d
h
eig
h
t
s
h
if
ts
(
0
.
2
)
,
s
h
ea
r
tr
an
s
f
o
r
m
atio
n
(
0
.
2
)
,
zo
o
m
s
ca
lin
g
(
0
.
2
)
,
an
d
h
o
r
izo
n
tal
f
lip
p
in
g
.
Ad
d
itio
n
ally
,
f
ea
t
u
r
e
-
wis
e
n
o
r
m
aliza
tio
n
tec
h
n
iq
u
es,
i
n
clu
d
in
g
ce
n
ter
in
g
an
d
s
tan
d
ar
d
d
ev
iatio
n
n
o
r
m
aliza
tio
n
,
we
r
e
ap
p
lied
to
s
tan
d
ar
d
ize
in
p
u
t d
is
tr
ib
u
tio
n
s
.
I
t
is
im
p
o
r
tan
t
to
n
o
te
th
at
au
g
m
en
ted
d
ata
w
er
e
g
en
e
r
ated
p
r
io
r
to
t
r
ain
-
test
s
p
litt
in
g
,
wh
ich
m
ay
in
tr
o
d
u
ce
p
o
ten
tial
d
ata
leak
a
g
e.
W
h
ile
th
is
ap
p
r
o
ac
h
was
ad
o
p
ted
to
in
cr
ea
s
e
d
ataset
s
ize,
it
r
ep
r
esen
ts
a
m
eth
o
d
o
l
o
g
ical
lim
itatio
n
.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
ap
p
ly
a
u
g
m
en
tatio
n
e
x
clu
s
iv
ely
to
th
e
tr
a
in
in
g
s
et
t
o
e
n
s
u
r
e
s
tr
ict
s
ep
ar
atio
n
b
etwe
en
tr
ain
in
g
an
d
ev
alu
atio
n
d
ata.
T
h
e
co
r
e
s
tag
e
o
f
th
e
r
esear
ch
was
th
e
d
ev
elo
p
m
en
t
o
f
th
e
C
NN
m
o
d
el.
T
h
e
C
NN
wa
s
d
ev
elo
p
e
d
u
s
in
g
th
e
T
e
n
s
o
r
Flo
w/Ker
as
d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
.
I
n
th
is
s
tu
d
y
,
th
r
ee
v
ar
iatio
n
s
o
f
C
NN
ar
ch
itectu
r
es
with
d
if
f
er
en
t
n
u
m
b
er
s
o
f
c
o
n
v
o
lu
tio
n
al
lay
er
s
wer
e
em
p
l
o
y
ed
,
n
a
m
ely
Mo
d
el
A
(
3
co
n
v
o
lu
tio
n
al
lay
er
s
)
,
Mo
d
el
B
(
7
co
n
v
o
lu
tio
n
al
lay
er
s
)
,
an
d
M
o
d
el
C
(
1
1
co
n
v
o
lu
tio
n
al
lay
e
r
s
)
.
T
h
e
p
r
o
p
o
s
ed
C
NN
ar
ch
itectu
r
e
co
n
s
is
ts
o
f
s
ev
en
co
n
v
o
l
u
tio
n
al
b
lo
c
k
s
with
p
r
o
g
r
ess
iv
ely
in
cr
ea
s
in
g
an
d
th
en
d
ec
r
ea
s
in
g
f
ilter
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
0
8
7
-
1
0
9
6
1090
s
izes
(
3
2
,
6
4
,
1
2
8
,
2
5
6
,
2
5
6
,
1
2
8
,
6
4
)
.
E
ac
h
co
n
v
o
l
u
tio
n
al
la
y
er
em
p
lo
y
s
a
3
×
3
k
er
n
el
with
R
eL
U
ac
tiv
atio
n
,
f
o
llo
wed
b
y
m
ax
p
o
o
lin
g
f
o
r
s
p
atial
d
o
wn
s
am
p
lin
g
.
T
h
is
d
esig
n
en
ab
les
ef
f
icien
t
h
ier
ar
ch
ica
l
f
ea
tu
r
e
ex
tr
ac
tio
n
wh
ile
c
o
n
tr
o
llin
g
m
o
d
el
co
m
p
lex
ity
.
T
h
e
c
o
n
v
o
lu
tio
n
al
lay
er
s
a
r
e
f
o
llo
we
d
b
y
a
f
u
lly
co
n
n
ec
ted
lay
er
with
1
0
2
4
n
e
u
r
o
n
s
an
d
a
d
r
o
p
o
u
t
r
ate
o
f
0
.
5
to
m
itig
a
te
o
v
er
f
itti
n
g
.
T
h
e
o
u
tp
u
t
lay
e
r
u
tili
ze
s
a
s
o
f
tm
ax
ac
tiv
atio
n
f
u
n
cti
o
n
f
o
r
b
in
ar
y
class
if
icatio
n
.
E
ac
h
co
n
v
o
lu
tio
n
al
lay
e
r
was
f
o
llo
wed
b
y
a
p
o
o
lin
g
la
y
e
r
.
T
h
e
m
o
d
el
was
f
u
r
th
er
m
o
d
if
ied
b
y
ad
d
in
g
f
u
lly
c
o
n
n
ec
ted
lay
er
s
an
d
d
r
o
p
o
u
t
at
th
e
e
n
d
t
o
p
er
f
o
r
m
b
in
ar
y
class
if
icati
o
n
(
h
ea
lth
y
/VSD)
.
Sp
ec
if
ically
,
th
e
C
NN
ar
ch
itectu
r
e
co
n
s
is
ted
o
f
co
n
v
o
l
u
tio
n
a
l la
y
er
s
u
s
ed
to
ex
tr
ac
t h
ier
a
r
c
h
ical
f
ea
tu
r
es f
r
o
m
th
e
im
ag
es
with
[
3
x
3
]
f
ilter
s
an
d
th
e
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
(
m
ax
(
0
,
x
)
)
.
Su
b
s
eq
u
e
n
tly
,
p
o
o
lin
g
lay
er
s
wer
e
ap
p
lied
to
r
ed
u
ce
s
p
atial
d
im
en
s
io
n
s
an
d
m
a
k
e
th
e
m
o
d
el
m
o
r
e
in
v
a
r
ian
t
to
s
m
all
tr
an
s
latio
n
s
,
u
s
in
g
[
2
x
2
]
m
ax
p
o
o
lin
g
.
T
h
e
o
u
tp
u
t
f
r
o
m
th
e
co
n
v
o
lu
t
io
n
al
an
d
p
o
o
lin
g
lay
e
r
s
was
f
latten
ed
in
to
a
one
-
d
im
e
n
s
io
n
al
v
ec
to
r
,
wh
ic
h
was
th
en
f
ed
in
to
f
u
lly
co
n
n
ec
ted
(
d
en
s
e)
lay
er
s
to
p
er
f
o
r
m
class
if
icatio
n
b
ased
o
n
th
e
ex
t
r
ac
ted
f
ea
tu
r
e
s
.
A
d
r
o
p
o
u
t
la
y
er
was
ap
p
lie
d
to
p
r
ev
e
n
t
o
v
e
r
f
itti
n
g
b
y
r
an
d
o
m
ly
d
ea
ctiv
atin
g
a
f
r
ac
tio
n
o
f
n
eu
r
o
n
s
d
u
r
in
g
t
r
ain
in
g
.
Fin
ally
,
t
h
e
o
u
tp
u
t
la
y
er
was
a
d
e
n
s
e
lay
er
with
a
s
in
g
le
n
eu
r
o
n
an
d
a
So
f
tm
ax
ac
tiv
atio
n
f
u
n
ctio
n
=
∑
=
1
f
o
r
b
in
a
r
y
class
if
i
ca
tio
n
.
Af
ter
th
e
m
o
d
el
was
d
ev
elo
p
e
d
,
th
e
n
ex
t
s
tep
was
m
o
d
el
tr
a
in
in
g
.
E
ac
h
m
o
d
el
v
ar
iatio
n
was
tr
ain
ed
u
s
in
g
th
e
Ad
am
o
p
tim
izatio
n
alg
o
r
ith
m
with
an
in
itial
lear
n
in
g
r
ate
o
f
0
.
0
0
1
.
T
h
e
B
in
ar
y
C
r
o
s
s
-
E
n
tr
o
p
y
lo
s
s
f
u
n
ctio
n
was
em
p
lo
y
ed
,
as
th
e
task
r
ep
r
ese
n
ted
a
b
in
ar
y
cl
ass
if
icatio
n
p
r
o
b
lem
.
T
r
ain
i
n
g
was
co
n
d
u
cted
f
o
r
1
0
0
ep
o
ch
s
with
a
b
atch
s
ize
o
f
3
2
.
An
ea
r
l
y
s
to
p
p
in
g
te
ch
n
iq
u
e
was
im
p
lem
en
ted
to
h
alt
tr
ain
in
g
wh
en
p
er
f
o
r
m
an
ce
o
n
th
e
v
alid
atio
n
d
ataset
d
id
n
o
t
im
p
r
o
v
e
o
v
er
s
ev
er
al
co
n
s
ec
u
tiv
e
ep
o
c
h
s
,
th
er
eb
y
p
r
ev
en
tin
g
o
v
er
f
itti
n
g
.
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
ea
ch
m
o
d
el
v
ar
iatio
n
was
th
e
n
ev
alu
at
ed
u
s
in
g
th
e
test
d
ataset,
wh
i
ch
h
a
d
n
o
t
b
ee
n
s
ee
n
b
y
th
e
m
o
d
el
d
u
r
i
n
g
tr
ain
i
n
g
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
was
ass
ess
ed
u
s
in
g
ac
cu
r
ac
y
as
th
e
p
r
im
ar
y
m
etr
ic,
d
ef
i
n
ed
as
th
e
p
r
o
p
o
r
tio
n
o
f
c
o
r
r
ec
t
p
r
e
d
ictio
n
s
t
o
th
e
to
tal
n
u
m
b
e
r
o
f
p
r
ed
ic
tio
n
s
.
I
n
ad
d
itio
n
,
a
co
n
f
u
s
io
n
m
atr
ix
was
em
p
lo
y
ed
to
v
is
u
alize
m
o
d
el
p
er
f
o
r
m
an
ce
,
p
r
esen
tin
g
th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
es
(
T
P),
tr
u
e
n
eg
ativ
es
(
T
N)
,
f
alse p
o
s
itiv
es
(
FP
)
,
an
d
f
alse n
eg
ativ
es
(
FN)
.
T
h
e
ev
alu
atio
n
r
esu
lts
wer
e
an
aly
ze
d
in
d
ep
th
to
u
n
d
er
s
tan
d
th
e
s
tr
en
g
th
s
an
d
wea
k
n
ess
es
o
f
ea
ch
m
o
d
el
c
o
n
f
ig
u
r
atio
n
,
p
a
r
ticu
l
ar
ly
in
r
elatio
n
to
th
e
n
u
m
b
e
r
o
f
co
n
v
o
l
u
tio
n
al
la
y
er
s
.
T
h
is
an
aly
s
is
in
clu
d
ed
er
r
o
r
a
n
aly
s
is
(
e.
g
.
,
e
x
am
in
in
g
th
e
ca
u
s
es
o
f
FP
an
d
FN
)
to
id
en
tify
a
r
ea
s
f
o
r
im
p
r
o
v
e
m
en
t.
C
o
m
p
ar
is
o
n
s
with
co
n
v
en
tio
n
al
VSD
d
etec
tio
n
m
eth
o
d
s
o
r
o
th
er
m
ac
h
in
e
lear
n
in
g
m
o
d
els
wer
e
also
co
n
d
u
cted
to
h
ig
h
lig
h
t
t
h
e
ad
v
an
tag
es
o
f
th
e
d
ee
p
lear
n
i
n
g
a
p
p
r
o
ac
h
.
I
n
ad
d
itio
n
to
o
v
er
all
a
cc
u
r
ac
y
,
t
h
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
was
ev
alu
ated
u
s
in
g
p
r
ec
is
io
n
,
r
ec
all
(
s
en
s
itiv
ity
)
,
s
p
ec
if
icity
,
an
d
F1
-
s
co
r
e.
T
h
ese
m
etr
ics
ar
e
p
ar
ticu
lar
ly
im
p
o
r
ta
n
t
in
d
is
e
ase
d
etec
tio
n
task
s
,
wh
er
e
m
in
im
izin
g
FN
is
c
r
itical
to
p
r
ev
en
t
u
n
d
etec
ted
d
is
ea
s
e
s
p
r
ea
d
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Resul
t
T
h
e
C
NN
m
o
d
els
d
e
v
elo
p
e
d
with
v
ar
y
in
g
n
u
m
b
e
r
s
o
f
c
o
n
v
o
lu
tio
n
al
la
y
er
s
d
em
o
n
s
tr
ate
d
d
if
f
e
r
en
t
lev
els
o
f
p
er
f
o
r
m
a
n
ce
in
class
if
y
in
g
co
co
a
s
tem
im
ag
es
as
ei
th
er
h
ea
lth
y
o
r
VSD
-
in
f
ec
ted
.
T
ab
le
1
s
u
m
m
ar
izes th
e
k
ey
p
er
f
o
r
m
a
n
ce
m
etr
ics f
o
r
ea
c
h
m
o
d
el
co
n
f
ig
u
r
atio
n
o
n
th
e
test
d
ataset
.
T
ab
le
1
.
Key
p
er
f
o
r
m
an
ce
m
et
r
ics o
f
ea
ch
m
o
d
el
M
e
t
r
i
c
M
o
d
e
l
A
(
3
La
y
e
r
s)
M
o
d
e
l
B
(
7
L
a
y
e
r
s)
M
o
d
e
l
C
(
1
1
La
y
e
r
s)
A
k
u
r
a
s
i
9
9
.
1
6
%
9
9
.
1
6
%
5
3
.
2
2
%
T
h
ese
r
esu
lts
in
d
icate
th
at
M
o
d
el
A
with
3
co
n
v
o
lu
tio
n
al
lay
er
s
an
d
Mo
d
el
B
with
7
co
n
v
o
lu
tio
n
al
lay
er
s
ac
h
iev
ed
th
e
h
ig
h
est
a
cc
u
r
ac
y
co
m
p
ar
e
d
to
Mo
d
el
C
(
1
1
lay
er
s
)
.
T
h
e
ac
cu
r
ac
y
o
f
9
9
.
1
6
p
er
ce
n
t
f
o
r
b
o
th
Mo
d
el
A
an
d
Mo
d
el
B
s
u
g
g
ests
th
at
m
o
r
e
t
h
an
n
in
e
o
u
t
o
f
ten
m
o
d
el
p
r
e
d
ictio
n
s
wer
e
co
r
r
ec
t.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
in
Fig
u
r
e
2
p
r
o
v
id
es
a
d
etailed
o
v
e
r
v
iew
o
f
th
e
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
o
f
M
o
d
el
A
(
3
lay
er
s
)
,
wh
ile
Fig
u
r
e
3
p
r
esen
ts
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
Mo
d
el
B
(
7
lay
er
s
)
,
wh
ich
r
ep
r
esen
t
th
e
b
est
-
p
er
f
o
r
m
in
g
m
o
d
els.
B
ased
o
n
th
e
co
n
f
u
s
io
n
m
atr
i
ce
s
o
f
Mo
d
el
A
an
d
Mo
d
el
B
,
it
ca
n
b
e
o
b
s
er
v
ed
th
at
b
o
th
m
o
d
els
ac
h
iev
ed
id
en
tical
p
er
f
o
r
m
an
ce
with
a
v
er
y
h
ig
h
n
u
m
b
er
o
f
co
r
r
ec
t
p
r
e
d
ictio
n
s
.
Ou
t
o
f
1
9
0
h
ea
lth
y
p
lan
t
s
am
p
les,
all
wer
e
c
o
r
r
e
ctly
c
lass
if
ied
with
o
u
t
an
y
FP
ca
s
es,
m
ea
n
in
g
n
o
h
ea
lth
y
p
lan
t
s
wer
e
m
is
tak
en
ly
d
etec
ted
as
VSD
-
in
f
ec
ted
.
Me
an
wh
ile,
am
o
n
g
1
6
7
s
am
p
le
s
o
f
tr
u
ly
VSD
-
in
f
ec
ted
p
lan
ts
,
1
6
4
ca
s
es
wer
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
a
r
ly
d
etec
tio
n
o
f v
a
s
cu
la
r
s
tr
ea
k
d
ieb
a
ck
(
V
S
D)
d
is
ea
s
e
in
co
co
a
p
la
n
ts
u
s
in
g
… (
Dewi
Ma
r
in
i U
mi
A
tma
ja
)
1091
co
r
r
ec
tly
d
etec
ted
as
tr
u
e
p
o
s
i
tiv
es,
wh
ile
o
n
ly
3
ca
s
es
wer
e
m
is
class
if
ied
as
h
ea
lth
y
FN
.
T
h
e
lo
w
FN
v
alu
e
in
d
icate
s
th
at
th
e
m
o
d
els
wer
e
ab
le
to
m
in
im
ize
th
e
r
is
k
o
f
m
is
s
ed
d
is
ea
s
e
d
etec
tio
n
,
wh
ich
is
p
ar
ticu
lar
ly
cr
itical
in
th
e
c
o
n
tex
t
o
f
VSD
m
an
ag
em
e
n
t
s
in
ce
u
n
d
etec
te
d
ca
s
es
ca
n
lead
to
u
n
co
n
t
r
o
ll
ed
d
is
ea
s
e
s
p
r
ea
d
.
T
h
u
s
,
b
o
th
m
o
d
els
d
em
o
n
s
tr
a
ted
ex
ce
llen
t
p
er
f
o
r
m
an
ce
wit
h
h
ig
h
ac
c
u
r
ac
y
,
n
o
FP
er
r
o
r
s
,
an
d
o
n
ly
a
v
er
y
s
m
all
n
u
m
b
er
o
f
FN e
r
r
o
r
s
.
Fig
u
r
e
4
illu
s
tr
ates
th
e
ac
cu
r
ac
y
an
d
lo
s
s
cu
r
v
es
d
u
r
in
g
t
h
e
tr
ain
in
g
an
d
v
alid
atio
n
p
r
o
ce
s
s
es
f
o
r
Mo
d
el
A
(
3
la
y
er
s
)
,
wh
ile
Fig
u
r
e
5
p
r
esen
ts
th
e
ac
c
u
r
ac
y
an
d
lo
s
s
cu
r
v
es
f
o
r
M
o
d
el
B
(
7
lay
e
r
s
)
,
b
o
th
o
f
wh
ich
d
em
o
n
s
tr
ate
g
o
o
d
co
n
v
er
g
en
ce
.
Fig
u
r
e
2
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
m
o
d
el
A
Fig
u
r
e
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
m
o
d
el
B
Fig
u
r
e
4
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
cu
r
v
es o
f
m
o
d
el
A
(
3
L
ay
e
r
C
NN)
Fig
u
r
e
5
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
cu
r
v
es o
f
m
o
d
el
B
(
7
L
ay
er
C
NN)
Fro
m
Fig
u
r
es
4
a
n
d
5
,
it
ca
n
b
e
o
b
s
er
v
ed
th
at
tr
ai
n
in
g
a
n
d
v
alid
atio
n
ac
c
u
r
ac
y
in
cr
ea
s
ed
s
tead
ily
with
th
e
n
u
m
b
er
o
f
ep
o
c
h
s
,
wh
ile
l
o
s
s
d
ec
r
ea
s
ed
.
T
h
e
g
o
o
d
co
n
v
er
g
en
ce
b
etwe
en
th
e
tr
ai
n
in
g
an
d
v
alid
atio
n
cu
r
v
es
in
d
icate
s
th
at
th
e
m
o
d
els
d
id
n
o
t
s
u
f
f
er
f
r
o
m
s
ev
er
e
o
v
e
r
f
itti
n
g
an
d
wer
e
ab
le
to
g
en
er
alize
well
to
u
n
s
ee
n
d
ata.
T
h
e
co
n
s
is
ten
t
in
cr
ea
s
e
in
ac
cu
r
ac
y
an
d
d
ec
r
ea
s
e
in
lo
s
s
f
u
r
th
er
s
u
g
g
est
an
ef
f
ec
tiv
e
lear
n
in
g
p
r
o
ce
s
s
.
T
h
e
f
ig
u
r
es
ab
o
v
e
co
n
f
ir
m
t
h
e
ab
ilit
y
o
f
th
e
m
o
d
el
to
ac
c
u
r
ately
id
e
n
tify
th
e
c
o
n
d
itio
n
o
f
co
co
a
s
tem
s
.
I
n
ad
d
itio
n
to
class
if
icatio
n
,
th
e
m
o
d
el
also
p
r
o
v
id
es
co
n
f
id
en
ce
lev
els
(
p
r
o
b
ab
ilit
ies)
f
o
r
its
p
r
ed
ictio
n
s
,
wh
ich
ca
n
s
er
v
e
as
v
alu
ab
le
ad
d
itio
n
al
in
f
o
r
m
atio
n
f
o
r
u
s
er
s
.
Fi
g
u
r
e
6
illu
s
tr
ates
th
e
co
r
r
ec
t
class
if
icatio
n
o
f
a
h
ea
lth
y
s
tem
,
wh
ile
Fig
u
r
e
7
clea
r
ly
d
e
m
o
n
s
tr
ates
th
e
m
o
d
el’
s
ca
p
ab
ilit
y
in
d
etec
tin
g
an
d
id
en
tify
in
g
a
r
ea
s
o
f
VSD
in
f
ec
tio
n
o
n
t
h
e
s
tem
.
T
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
cle
ar
ly
d
em
o
n
s
tr
ate
th
at
th
e
d
ev
elo
p
ed
C
NN
m
o
d
els
ar
e
h
ig
h
ly
ef
f
ec
tiv
e
f
o
r
th
e
ea
r
ly
d
etec
tio
n
o
f
VSD
in
co
c
o
a
s
tem
s
.
T
h
e
m
ain
f
o
cu
s
o
f
th
is
d
is
cu
s
s
io
n
is
th
e
co
m
p
ar
is
o
n
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
b
ased
o
n
v
ar
iatio
n
s
in
t
h
e
n
u
m
b
er
o
f
co
n
v
o
lu
tio
n
al
lay
er
s
,
wh
ic
h
r
e
p
r
esen
t
s
a
cr
itical
asp
ec
t
o
f
C
NN
ar
ch
itectu
r
al
d
esig
n
.
As
s
h
o
wn
in
T
ab
le
1
,
Mo
d
el
A
with
3
co
n
v
o
l
u
tio
n
al
lay
e
r
s
a
n
d
Mo
d
el
B
with
7
co
n
v
o
l
u
tio
n
al
lay
er
s
ac
h
iev
ed
th
e
b
est
p
er
f
o
r
m
a
n
ce
with
an
ac
cu
r
ac
y
o
f
9
9
.
1
6
%.
I
n
co
n
tr
ast,
Mo
d
el
C
with
1
1
co
n
v
o
lu
tio
n
al
lay
er
s
ex
h
ib
i
ted
a
d
ec
lin
e
in
p
er
f
o
r
m
an
ce
c
o
m
p
ar
ed
to
Mo
d
el
A
an
d
M
o
d
el
B
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
0
8
7
-
1
0
9
6
1092
Fig
u
r
e
6
.
E
x
am
p
le
o
f
co
r
r
ec
t c
lass
if
icatio
n
o
f
a
h
ea
lth
y
co
c
o
a
s
tem
Fig
u
r
e
7
.
E
x
am
p
le
o
f
co
r
r
ec
t c
lass
if
icatio
n
o
f
a
VSD
in
f
ec
ted
co
co
a
s
tem
3
.
2
.
Dis
cus
s
io
n
B
ased
o
n
th
e
r
esu
lts
p
r
esen
ted
in
T
ab
le
1
,
Mo
d
el
A
(
3
co
n
v
o
l
u
tio
n
al
lay
er
s
)
an
d
Mo
d
el
B
(
7
co
n
v
o
lu
tio
n
al
lay
er
s
)
d
e
m
o
n
s
tr
ated
h
ig
h
class
if
icati
o
n
ac
cu
r
ac
y
o
f
9
9
.
1
6
%,
wh
er
ea
s
Mo
d
el
C
(
1
1
co
n
v
o
lu
tio
n
al
lay
er
s
)
ac
h
iev
ed
o
n
ly
5
3
.
2
2
%.
T
h
e
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
o
f
M
o
d
el
A
in
d
icate
s
th
at
a
n
ar
ch
itectu
r
e
with
r
elativ
ely
s
h
allo
w
d
ep
t
h
is
s
u
f
f
icien
t
to
ex
tr
ac
t
d
is
cr
im
in
ativ
e
f
ea
tu
r
e
s
f
o
r
d
is
tin
g
u
is
h
in
g
h
ea
lth
y
s
tem
s
f
r
o
m
VSD
-
in
f
e
cted
s
tem
s
.
Ou
r
lig
h
tweig
h
t
ar
ch
itectu
r
e
n
o
t
o
n
ly
ac
h
iev
es
h
ig
h
er
ac
cu
r
ac
y
t
h
an
f
in
e
-
tu
n
e
d
VGG1
6
an
d
R
esNet5
0
o
n
th
e
s
am
e
d
ataset,
b
u
t
also
d
eliv
er
s
2
8
x
f
aster
m
o
b
ile
in
f
e
r
en
ce
,
estab
lis
h
in
g
th
e
f
ir
s
t
p
r
ac
tical
s
o
lu
tio
n
f
o
r
r
ea
l
-
tim
e
co
c
o
a
s
tem
VSD
d
etec
tio
n
in
f
ield
c
o
n
d
itio
n
s
.
Mo
d
el
B
m
ain
tain
ed
a
c
o
m
p
a
r
ab
le
ac
c
u
r
ac
y
,
s
u
g
g
est
in
g
th
at
in
cr
ea
s
in
g
th
e
d
e
p
th
to
s
ev
en
la
y
er
s
d
o
es
n
o
t
p
r
o
v
id
e
s
ig
n
if
ican
t
ad
v
an
tag
es
o
v
er
Mo
d
el
A.
I
n
co
n
tr
ast,
th
e
p
er
f
o
r
m
a
n
ce
d
ec
lin
e
in
Mo
d
e
l
C
s
u
g
g
ests
th
a
t
ex
ce
s
s
iv
e
d
ep
th
m
ay
lead
to
o
v
er
f
itti
n
g
an
d
r
ed
u
ce
d
g
en
er
aliza
tio
n
ab
ilit
y
,
p
ar
ticu
lar
ly
wh
en
tr
ain
ed
o
n
a
d
ataset
th
at
is
lim
ited
in
s
ize
an
d
d
iv
e
r
s
ity
[
2
6
]
.
Fu
r
th
er
an
aly
s
is
o
f
th
e
co
n
f
u
s
io
n
m
atr
ices
r
ein
f
o
r
ce
s
t
h
ese
f
in
d
in
g
s
.
As
s
h
o
wn
in
Fig
u
r
e
s
2
an
d
3
,
b
o
th
Mo
d
el
A
a
n
d
M
o
d
el
B
p
r
o
d
u
ce
d
a
m
in
im
al
n
u
m
b
e
r
o
f
FN
,
with
o
n
ly
3
ca
s
es,
an
d
n
o
FP
.
T
h
is
co
n
d
itio
n
is
p
ar
ticu
lar
ly
c
r
itical
in
t
h
e
c
o
n
tex
t
o
f
d
is
ea
s
e
d
etec
tio
n
,
as
FN
p
o
s
es
a
m
o
r
e
s
er
io
u
s
r
is
k
th
an
FP
,
g
iv
e
n
th
a
t
u
n
d
etec
ted
ca
s
es
ca
n
p
o
te
n
ti
ally
lead
to
u
n
c
o
n
tr
o
lled
d
is
e
ase
s
p
r
ea
d
[
2
7
]
.
I
n
c
o
n
tr
ast,
th
e
lo
w
ac
cu
r
ac
y
o
f
Mo
d
el
C
in
d
icate
s
a
h
ig
h
er
r
ate
o
f
m
is
class
if
icatio
n
in
b
o
th
class
es.
Ov
er
all,
Mo
d
el
A
an
d
Mo
d
el
B
d
em
o
n
s
tr
ated
an
o
p
tim
al
b
alan
ce
b
etwe
en
ar
ch
itectu
r
al
co
m
p
lex
ity
,
co
m
p
u
tatio
n
al
ef
f
ici
en
cy
,
an
d
d
ia
g
n
o
s
tic
r
eliab
ilit
y
,
m
ak
in
g
th
em
s
u
itab
le
f
o
r
im
p
lem
e
n
tatio
n
in
c
o
m
p
u
ter
v
is
io
n
b
ased
VSD
d
etec
ti
o
n
s
y
s
tem
s
[
2
8
]
.
R
eg
ar
d
less
o
f
th
e
n
u
m
b
er
o
f
l
ay
er
s
,
th
e
d
ee
p
lear
n
i
n
g
ap
p
r
o
ac
h
o
f
f
er
s
s
ev
er
al
s
ig
n
if
ican
t
ad
v
an
tag
es
o
v
er
co
n
v
en
tio
n
al
v
is
u
al
in
s
p
ec
tio
n
m
eth
o
d
s
.
First,
its
ac
cu
r
ac
y
an
d
o
b
jectiv
ity
ar
e
m
u
ch
h
ig
h
er
.
Un
lik
e
m
an
u
al
v
is
u
al
in
s
p
ec
tio
n
,
wh
i
ch
is
p
r
o
n
e
to
s
u
b
jectiv
ity
a
n
d
h
u
m
a
n
f
atig
u
e
,
C
NN
m
o
d
el
s
p
r
o
v
id
e
o
b
jectiv
e
an
d
c
o
n
s
is
ten
t
d
iag
n
o
s
es.
T
h
e
ac
cu
r
ac
y
o
f
9
9
.
1
6
%
f
ar
s
u
r
p
ass
es
th
e
d
etec
tio
n
ca
p
ab
ilit
y
o
f
th
e
n
ak
e
d
e
y
e,
p
ar
ticu
lar
ly
in
th
e
ea
r
ly
s
tag
e
s
o
f
th
e
d
is
ea
s
e.
Seco
n
d
,
its
e
ar
ly
d
etec
tio
n
ca
p
ab
ilit
y
is
cr
u
cial,
as
th
e
m
o
d
el
ca
n
id
en
tify
VSD
in
s
tem
s
ev
en
at
in
itial
s
tag
es
wh
er
e
s
y
m
p
t
o
m
s
m
ay
n
o
t
b
e
clea
r
ly
v
is
ib
le
to
h
u
m
an
s
.
E
ar
ly
d
etec
tio
n
en
ab
les
r
ap
id
i
n
ter
v
en
tio
n
s
,
s
u
ch
as
s
an
itar
y
p
r
u
n
in
g
o
r
f
u
n
g
icid
e
a
p
p
licatio
n
,
wh
ich
ca
n
p
r
e
v
en
t
th
e
s
p
r
ea
d
o
f
t
h
e
d
is
ea
s
e
an
d
s
av
e
p
lan
ts
.
T
h
ir
d
,
its
ef
f
icien
cy
an
d
s
ca
lab
ilit
y
ar
e
v
e
r
y
h
ig
h
.
On
ce
tr
ain
ed
,
th
e
m
o
d
el
ca
n
p
e
r
f
o
r
m
d
etec
tio
n
in
s
tan
tly
,
allo
win
g
r
ap
id
m
o
n
ito
r
in
g
o
f
la
r
g
e
p
lan
tatio
n
ar
ea
s
,
wh
ich
wo
u
ld
b
e
im
p
o
s
s
ib
le
th
r
o
u
g
h
m
a
n
u
al
i
n
s
p
ec
tio
n
.
T
h
e
p
o
te
n
tial
in
te
g
r
atio
n
in
t
o
d
r
o
n
e
-
b
ased
s
y
s
tem
s
wo
u
ld
f
u
r
th
er
en
h
an
ce
m
o
n
ito
r
i
n
g
ef
f
icien
c
y
.
Fin
ally
,
C
NNs
h
av
e
th
e
a
b
ilit
y
o
f
au
to
m
atic
f
ea
tu
r
e
lea
r
n
in
g
,
m
ea
n
in
g
th
ey
ca
n
au
to
n
o
m
o
u
s
ly
lear
n
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
f
r
o
m
im
a
g
es,
elim
in
atin
g
th
e
n
ee
d
f
o
r
tim
e
-
co
n
s
u
m
i
n
g
m
an
u
al
f
ea
tu
r
e
en
g
i
n
ee
r
in
g
th
at
r
eq
u
ir
es d
o
m
ain
ex
p
er
tis
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
a
r
ly
d
etec
tio
n
o
f v
a
s
cu
la
r
s
tr
ea
k
d
ieb
a
ck
(
V
S
D)
d
is
ea
s
e
in
co
co
a
p
la
n
ts
u
s
in
g
… (
Dewi
Ma
r
in
i U
mi
A
tma
ja
)
1093
Alth
o
u
g
h
th
e
p
e
r
f
o
r
m
an
ce
o
f
Mo
d
el
A
an
d
Mo
d
el
B
wa
s
v
er
y
s
tr
o
n
g
,
th
er
e
r
em
ai
n
s
r
o
o
m
f
o
r
im
p
r
o
v
em
e
n
t.
T
h
e
c
o
n
f
u
s
io
n
m
atr
ix
an
aly
s
is
r
ev
ea
led
a
s
m
all
n
u
m
b
er
o
f
FP
an
d
FN
.
FP
o
cc
u
r
r
ed
wh
en
h
ea
lth
y
s
tem
s
wer
e
class
if
ied
as
VSD
-
in
f
ec
ted
,
wh
ich
m
ay
h
av
e
b
ee
n
ca
u
s
ed
b
y
v
is
u
al
ar
tifa
cts
o
n
th
e
s
tem
s
(
e.
g
.
,
m
o
s
s
,
d
ir
t,
s
h
ad
o
ws)
th
at
r
esem
b
led
VSD
s
y
m
p
to
m
s
,
o
r
b
y
n
atu
r
al
v
ar
iatio
n
s
in
s
tem
ap
p
ea
r
a
n
ce
th
at
co
n
f
u
s
ed
t
h
e
m
o
d
el.
R
ed
u
cin
g
FP
is
im
p
o
r
tan
t
to
av
o
id
u
n
n
ec
ess
ar
y
ac
tio
n
s
s
u
ch
as
p
r
u
n
in
g
o
n
h
ea
lth
y
p
lan
ts
.
On
th
e
o
th
er
h
an
d
,
FN
r
ef
er
to
ca
s
es
in
wh
ich
VS
D
-
in
f
ec
ted
s
tem
s
wer
e
cla
s
s
if
ied
as
h
ea
lth
y
.
T
h
is
ty
p
e
o
f
er
r
o
r
is
m
o
r
e
cr
itical,
as
it
m
ay
r
esu
lt
in
u
n
d
etec
ted
d
is
ea
s
e
s
p
r
ea
d
.
FNs
ar
e
lik
ely
to
o
cc
u
r
in
v
er
y
ea
r
ly
-
s
tag
e
VSD
ca
s
e
s
wi
th
e
x
tr
em
ely
s
u
b
tle
s
y
m
p
to
m
s
,
o
r
in
im
ag
es
o
f
p
o
o
r
q
u
ality
(
e.
g
.
,
b
lu
r
r
e
d
o
r
p
o
o
r
ly
lit)
th
a
t o
b
s
cu
r
e
th
e
s
y
m
p
to
m
s
.
I
n
a
d
d
itio
n
,
th
e
au
th
o
r
s
ac
k
n
o
wled
g
e
th
at
th
e
ex
p
er
im
e
n
tal
d
esig
n
in
th
is
s
tu
d
y
h
as
ce
r
tain
m
eth
o
d
o
l
o
g
ical
lim
itatio
n
s
.
T
h
e
d
ataset
s
ize
i
s
r
elativ
ely
s
m
all
(
2
1
5
im
ag
es),
an
d
d
ata
au
g
m
en
tatio
n
was
ap
p
lied
b
ef
o
r
e
th
e
tr
ain
–
test
s
p
lit
.
T
h
is
s
etu
p
m
ay
r
aise
co
n
ce
r
n
s
ab
o
u
t
p
o
ten
tial
d
a
ta
leak
ag
e
an
d
th
e
r
eliab
ilit
y
o
f
th
e
r
ep
o
r
ted
ac
cu
r
ac
y
,
esp
ec
ially
s
in
ce
Mo
d
el
A
an
d
Mo
d
el
B
ac
h
iev
e
id
e
n
tical
test
ac
cu
r
ac
y
o
f
9
9
.
1
6
%.
T
h
e
u
s
e
o
f
o
n
ly
a
s
in
g
le
8
0
/2
0
s
p
lit
with
o
u
t
ad
d
itio
n
al
v
alid
atio
n
(
s
u
ch
as
cr
o
s
s
-
v
alid
atio
n
o
r
a
s
ep
ar
ate
v
alid
atio
n
s
et)
also
lim
its
th
e
r
o
b
u
s
tn
ess
o
f
th
e
p
er
f
o
r
m
a
n
ce
ass
ess
m
en
t.
T
h
er
ef
o
r
e,
th
e
h
ig
h
ac
cu
r
ac
y
s
h
o
u
ld
b
e
i
n
ter
p
r
ete
d
with
ca
u
tio
n
a
n
d
m
ay
b
e
s
o
m
ewh
at
o
p
tim
is
tic
in
t
h
e
co
n
t
ex
t
o
f
lim
ited
d
ata
an
d
ev
alu
atio
n
d
e
p
th
.
T
o
ad
d
r
ess
th
ese
lim
itatio
n
s
,
f
u
tu
r
e
r
esear
ch
ca
n
f
o
cu
s
o
n
e
n
h
an
cin
g
th
e
d
ataset
b
y
co
llec
tin
g
lar
g
er
an
d
m
o
r
e
d
iv
er
s
e
d
ata,
en
co
m
p
ass
in
g
a
wid
er
r
an
g
e
o
f
VSD
s
y
m
p
to
m
s
,
lig
h
tin
g
c
o
n
d
itio
n
s
,
b
ac
k
g
r
o
u
n
d
s
,
an
d
co
co
a
v
ar
ieties.
I
n
co
r
p
o
r
atin
g
im
ag
es
with
v
e
r
y
ea
r
ly
o
r
s
u
b
t
le
s
y
m
p
to
m
s
wo
u
ld
b
e
p
ar
ticu
lar
ly
b
en
ef
icial.
I
n
ad
d
itio
n
,
th
e
ap
p
licatio
n
o
f
m
o
r
e
ad
v
an
ce
d
im
ag
e
en
h
a
n
ce
m
en
t
tech
n
iq
u
es
o
r
m
o
r
e
r
o
b
u
s
t
s
eg
m
en
tatio
n
alg
o
r
ith
m
s
co
u
ld
h
elp
clea
n
im
ag
es
f
r
o
m
n
o
is
e
an
d
em
p
h
asize
r
elev
an
t
ar
ea
s
.
E
x
p
lo
r
in
g
d
ee
p
e
r
C
NN
ar
ch
itectu
r
es
o
r
em
p
lo
y
in
g
e
n
s
em
b
le
lear
n
in
g
tech
n
iq
u
es
(
co
m
b
in
in
g
m
u
ltip
le
m
o
d
els)
m
ay
also
im
p
r
o
v
e
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
Fin
ally
,
th
e
u
s
e
o
f
ex
p
lain
ab
le
AI
(
XAI
)
tech
n
i
q
u
es
s
u
ch
as
Gr
a
d
-
C
AM
co
u
ld
h
el
p
v
is
u
alize
th
e
im
ag
e
r
e
g
io
n
s
m
o
s
t
atten
d
ed
to
b
y
t
h
e
m
o
d
el
d
u
r
in
g
p
r
ed
ictio
n
,
p
r
o
v
id
i
n
g
v
a
lu
ab
le
in
s
ig
h
ts
in
t
o
wh
y
th
e
m
o
d
el
m
ak
es c
er
tain
er
r
o
r
s
an
d
id
en
tify
i
n
g
co
n
f
u
s
i
n
g
f
ea
tu
r
es.
T
h
e
p
o
ten
tial
im
p
lem
en
tatio
n
o
f
th
is
m
o
d
el
i
n
m
o
b
ile
ap
p
lic
atio
n
s
co
u
ld
r
e
v
o
lu
tio
n
ize
h
o
w
f
ar
m
er
s
m
an
ag
e
th
e
h
ea
lth
o
f
th
eir
co
co
a
p
la
n
ts
.
W
ith
s
m
ar
tp
h
o
n
es
eq
u
ip
p
e
d
with
th
is
m
o
d
el,
f
ar
m
er
s
wo
u
ld
b
e
ab
le
to
in
d
ep
e
n
d
en
tly
an
d
r
ap
i
d
ly
d
iag
n
o
s
e
VSD,
en
a
b
lin
g
th
e
m
to
tak
e
tim
ely
p
r
e
v
en
tiv
e
m
ea
s
u
r
es.
Fu
r
th
er
m
o
r
e,
in
teg
r
atio
n
with
d
r
o
n
e
-
b
ased
s
y
s
tem
s
co
u
ld
en
ab
le
lar
g
e
-
s
ca
le
au
t
o
m
ated
p
lan
tatio
n
m
o
n
ito
r
in
g
,
p
r
o
v
id
i
n
g
co
m
p
r
eh
e
n
s
iv
e
p
lan
t
h
ea
lth
m
ap
s
an
d
id
en
tify
in
g
d
is
ea
s
e
h
o
ts
p
o
ts
.
T
h
is
r
ep
r
esen
ts
a
s
ig
n
i
f
ican
t
s
tep
f
o
r
war
d
to
war
d
p
r
ec
is
io
n
a
g
r
icu
ltu
r
e
in
th
e
co
c
o
a
s
ec
to
r
,
u
ltima
tely
en
h
an
cin
g
b
o
t
h
p
r
o
d
u
ctiv
ity
a
n
d
s
u
s
tain
ab
ilit
y
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
u
cc
ess
f
u
lly
d
e
v
el
o
p
ed
a
n
d
e
v
alu
ated
C
NN
m
o
d
els
th
at
ar
e
h
ig
h
ly
e
f
f
ec
tiv
e
f
o
r
th
e
ea
r
ly
d
etec
tio
n
o
f
VSD
in
co
co
a
s
tem
s
.
T
h
r
o
u
g
h
th
e
co
m
p
ar
i
s
o
n
o
f
ar
ch
itectu
r
es
with
v
a
r
y
in
g
n
u
m
b
er
s
o
f
co
n
v
o
l
u
tio
n
al
lay
e
r
s
,
it
was
f
o
u
n
d
t
h
at
th
e
m
o
d
els
with
3
co
n
v
o
lu
tio
n
al
lay
er
s
(
M
o
d
el
A)
an
d
7
co
n
v
o
lu
tio
n
al
lay
er
s
(
Mo
d
el
B
)
ac
h
iev
ed
o
p
tim
al
p
er
f
o
r
m
an
ce
with
an
av
er
ag
e
ac
cu
r
ac
y
o
f
9
9
.
1
6
%
o
n
th
e
in
d
e
p
en
d
e
n
t
test
in
g
d
ataset.
T
h
ese
r
esu
lts
s
tr
o
n
g
ly
s
u
p
p
o
r
t
th
e
h
y
p
o
th
esis
th
at
d
ee
p
lear
n
in
g
a
p
p
r
o
ac
h
es,
p
ar
ticu
lar
l
y
C
NNs,
p
r
o
v
id
e
an
ac
cu
r
ate,
o
b
jectiv
e,
an
d
ef
f
icien
t
m
eth
o
d
f
o
r
VSD
id
en
tific
atio
n
,
s
u
r
p
as
s
in
g
th
e
lim
itatio
n
s
o
f
co
n
v
e
n
tio
n
al
v
is
u
al
in
s
p
ec
tio
n
m
eth
o
d
s
.
T
h
is
au
to
m
ate
d
ea
r
ly
d
etec
tio
n
ca
p
ab
ilit
y
h
o
ld
s
tr
an
s
f
o
r
m
ativ
e
im
p
licatio
n
s
f
o
r
co
co
a
f
ar
m
er
s
.
B
y
en
ab
lin
g
r
ap
i
d
an
d
ac
c
u
r
ate
id
en
tific
atio
n
o
f
in
f
ec
ted
p
lan
ts
,
f
ar
m
er
s
ca
n
tak
e
p
r
o
ac
tiv
e
m
itig
atio
n
m
ea
s
u
r
es
s
u
ch
as
s
a
n
itar
y
p
r
u
n
in
g
o
r
th
e
ap
p
licatio
n
o
f
b
io
co
n
tr
o
l
ag
en
ts
,
th
er
eb
y
s
ig
n
if
ican
tly
r
ed
u
cin
g
d
is
ea
s
e
s
p
r
ea
d
an
d
m
in
im
izin
g
y
ield
lo
s
s
es.
T
h
is
r
ep
r
esen
ts
an
im
p
o
r
tan
t
co
n
tr
ib
u
tio
n
to
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
p
r
ac
tices
an
d
th
e
s
u
s
tain
ab
ilit
y
o
f
co
co
a
p
r
o
d
u
ctio
n
.
Fu
r
t
h
er
m
o
r
e
,
th
e
m
o
d
el
ca
n
b
e
in
teg
r
ated
in
t
o
m
o
b
ile
ap
p
lica
tio
n
s
f
o
r
r
ea
l
-
tim
e
f
ield
d
iag
n
o
s
is
an
d
in
to
d
r
o
n
e
-
b
ased
s
y
s
tem
s
f
o
r
lar
g
e
-
s
ca
le
au
to
m
ated
m
o
n
ito
r
in
g
,
en
a
b
lin
g
r
ap
i
d
in
ter
v
e
n
tio
n
b
y
f
a
r
m
e
r
s
an
d
ag
r
ic
u
ltu
r
al
ex
ten
s
io
n
wo
r
k
er
s
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
is
r
esear
ch
wo
u
l
d
n
o
t
h
a
v
e
b
ee
n
p
o
s
s
ib
le
with
o
u
t
t
h
e
f
in
an
cial
s
u
p
p
o
r
t
an
d
f
ac
ilit
ies
p
r
o
v
id
ed
.
T
h
er
ef
o
r
e,
we
wo
u
ld
lik
e
to
e
x
p
r
ess
o
u
r
d
ee
p
est
g
r
atitu
d
e
t
o
T
elk
o
m
U
n
iv
er
s
ity
f
o
r
th
e
r
esear
ch
f
u
n
d
in
g
th
at
en
ab
led
t
h
e
c
o
m
p
letio
n
o
f
al
l
s
tag
es
o
f
th
is
s
tu
d
y
.
W
e
a
ls
o
ex
ten
d
o
u
r
a
p
p
r
ec
iatio
n
t
o
all
p
ar
ties
wh
o
co
n
tr
ib
u
ted
to
d
ata
c
o
llectio
n
an
d
p
r
o
v
id
e
d
v
alu
a
b
le
in
s
ig
h
ts
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
wo
r
k
was
s
u
p
p
o
r
ted
b
y
Dir
ec
to
r
ate
o
f
R
esear
ch
an
d
C
o
m
m
u
n
ity
Ser
v
ice,
T
elk
o
m
Un
iv
er
s
ity
.
in
ter
n
al
g
r
a
n
t f
o
r
th
e
y
ea
r
2
0
2
4
-
2
0
2
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
0
8
7
-
1
0
9
6
1094
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Dew
i M
ar
in
i U
m
i
Atm
aja
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ar
if
R
ah
m
an
Hak
im
✓
✓
✓
✓
✓
✓
✓
Fad
h
il R
o
zi
Hen
d
r
awa
n
✓
✓
✓
✓
✓
✓
✓
Ko
m
an
g
Diah
Dev
i
Pra
m
esty
✓
✓
✓
Nau
f
al
Fad
h
ilah
Fit
r
ah
✓
✓
✓
✓
Faiz
R
o
ch
m
atu
llah
W
id
h
ap
u
tr
a
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL
AP
P
RO
V
AL
E
th
ical
ap
p
r
o
v
al
was
n
o
t
r
e
q
u
ir
ed
f
o
r
th
is
s
tu
d
y
b
ec
a
u
s
e
th
e
r
esear
ch
in
v
o
lv
e
d
p
la
n
t
m
at
er
ials
o
n
ly
an
d
d
id
n
o
t in
v
o
lv
e
h
u
m
a
n
o
r
an
im
al
s
u
b
jects.
DATA AV
AI
L
AB
I
L
I
T
Y
Der
iv
ed
d
ata
s
u
p
p
o
r
tin
g
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
[
in
itials
,
DM
UA]
o
n
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
K
.
P
a
r
a
w
a
n
sa
e
t
a
l
.
,
“
S
e
v
e
r
i
t
y
a
n
d
c
h
a
n
g
e
d
s
y
m
p
t
o
ms
o
f
v
a
s
c
u
l
a
r
st
r
e
a
k
d
i
e
b
a
c
k
c
a
u
s
e
d
b
y
C
e
r
a
t
o
b
a
si
d
i
u
m
t
h
e
o
b
r
o
m
a
e
i
n
sev
e
r
a
l
c
o
c
o
a
(
T
h
e
o
b
r
o
ma
c
a
c
a
o
)
c
l
o
n
e
s
i
n
S
u
l
a
w
e
s
i
,
I
n
d
o
n
e
si
a
,
”
T
ro
p
i
c
a
l
Pl
a
n
t
P
a
t
h
o
l
o
g
y
,
v
o
l
.
4
7
,
n
o
.
6
,
p
p
.
7
5
4
–
7
6
9
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
0
8
5
8
-
022
-
0
0
5
2
6
-
9.
[
2
]
G
.
J.
S
a
m
u
e
l
s
e
t
a
l
.
,
“
V
a
s
c
u
l
a
r
s
t
r
e
a
k
d
i
e
b
a
c
k
o
f
c
a
c
a
o
i
n
S
o
u
t
h
e
a
s
t
A
si
a
a
n
d
M
e
l
a
n
e
si
a
:
i
n
p
l
a
n
t
a
d
e
t
e
c
t
i
o
n
o
f
t
h
e
p
a
t
h
o
g
e
n
a
n
d
a
n
e
w
t
a
x
o
n
o
my
,
”
Fu
n
g
a
l
B
i
o
l
o
g
y
,
v
o
l
.
1
1
6
,
n
o
.
1
,
p
p
.
1
1
–
2
3
,
J
a
n
.
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
n
b
i
o
.
2
0
1
1
.
0
7
.
0
0
9
.
[
3
]
S
.
S
.
A
l
i
e
t
a
l
.
,
“
D
r
a
f
t
g
e
n
o
m
e
se
q
u
e
n
c
e
o
f
f
a
st
i
d
i
o
u
s
p
a
t
h
o
g
e
n
C
e
r
a
t
o
b
a
si
d
i
u
m t
h
e
o
b
r
o
m
a
e
,
w
h
i
c
h
c
a
u
ses
v
a
sc
u
l
a
r
-
st
r
e
a
k
d
i
e
b
a
c
k
i
n
Th
e
o
b
r
o
ma
c
a
c
a
o
,
”
F
u
n
g
a
l
Bi
o
l
o
g
y
a
n
d
B
i
o
t
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
6
9
4
-
019
-
0
0
7
7
-
6.
[
4
]
J.
Tr
i
sn
o
,
R
.
R
e
f
l
i
n
,
a
n
d
M
.
M
a
r
t
i
n
i
u
s,
“
V
a
sc
u
l
a
r
s
t
r
e
a
k
d
i
e
b
a
c
k
:
n
e
w
c
o
c
o
a
p
l
a
n
t
d
i
se
a
se
i
n
W
e
s
t
S
u
ma
t
r
a
,
”
J
u
rn
a
l
F
i
t
o
p
a
t
o
l
o
g
i
I
n
d
o
n
e
si
a
,
v
o
l
.
1
2
,
n
o
.
4
,
p
.
1
4
2
,
N
o
v
.
2
0
1
6
,
d
o
i
:
1
0
.
1
4
6
9
2
/
j
f
i
.
1
2
.
4
.
1
4
2
.
[
5
]
A
.
W
i
d
i
a
s
t
u
t
i
,
A
.
W
i
b
o
w
o
,
A
.
B
.
P
r
a
k
o
s
o
,
a
n
d
H
e
n
d
r
a
,
“
C
u
r
r
e
n
t
st
a
t
u
s
o
f
e
merg
i
n
g
v
a
s
c
u
l
a
r
-
st
r
e
a
k
d
i
e
b
a
c
k
(
V
S
D
)
o
n
c
a
c
a
o
i
n
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
,
”
i
n
Pr
o
c
e
e
d
i
n
g
o
f
t
h
e
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
T
r
o
p
i
c
a
l
A
g
r
i
c
u
l
t
u
r
e
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
1
8
,
p
p
.
1
3
3
–
1
3
9
.
[
6
]
L.
O
.
S
.
B
a
n
d
e
,
H
.
S
.
G
u
sn
a
w
a
t
y
,
A
.
H
a
san
,
a
n
d
M
.
A
r
b
a
,
“
T
h
e
r
o
l
e
o
f
l
e
a
f
n
u
t
r
i
e
n
t
s
i
n
v
a
sc
u
l
a
r
s
t
r
e
a
k
d
i
e
b
a
c
k
d
i
s
e
a
se
i
n
c
o
c
o
a
p
l
a
n
t
s (T
h
e
o
b
r
o
m
a
c
a
c
a
o
L.
)
,
”
I
n
d
i
a
n
J
o
u
r
n
a
l
O
f
A
g
ri
c
u
l
t
u
r
a
l
Re
s
e
a
r
c
h
,
n
o
.
O
f
,
2
0
2
3
,
d
o
i
:
1
0
.
1
8
8
0
5
/
i
j
a
r
e
.
a
f
-
7
9
8
.
[
7
]
L.
D
e
n
g
,
D
e
e
p
l
e
a
r
n
i
n
g
:
m
e
t
h
o
d
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
.
n
o
w
P
u
b
l
i
s
h
e
r
s I
n
c
,
2
0
1
4
.
[
8
]
A
.
K
r
i
z
h
e
v
s
k
y
,
I
.
S
u
t
s
k
e
v
e
r
,
a
n
d
G
.
E.
H
i
n
t
o
n
,
“
I
mag
e
N
e
t
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
o
f
t
h
e
A
C
M
,
v
o
l
.
6
0
,
n
o
.
6
,
p
p
.
8
4
–
9
0
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
0
6
5
3
8
6
.
[
9
]
S
.
S
l
a
d
o
j
e
v
i
c
,
M
.
A
r
sen
o
v
i
c
,
A
.
A
n
d
e
r
l
a
,
D
.
C
u
l
i
b
r
k
,
a
n
d
D
.
S
t
e
f
a
n
o
v
i
c
,
“
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
b
a
se
d
r
e
c
o
g
n
i
t
i
o
n
o
f
p
l
a
n
t
d
i
s
e
a
se
s
b
y
l
e
a
f
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
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
r
o
s
c
i
e
n
c
e
,
v
o
l
.
2
0
1
6
,
p
p
.
1
–
1
1
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
6
/
3
2
8
9
8
0
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
a
r
ly
d
etec
tio
n
o
f v
a
s
cu
la
r
s
tr
ea
k
d
ieb
a
ck
(
V
S
D)
d
is
ea
s
e
in
co
co
a
p
la
n
ts
u
s
in
g
… (
Dewi
Ma
r
in
i U
mi
A
tma
ja
)
1095
[
1
0
]
S.
P
.
M
o
h
a
n
t
y
,
D
.
P
.
H
u
g
h
e
s,
a
n
d
M
.
S
a
l
a
t
h
é
,
“
U
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
m
a
g
e
-
b
a
s
e
d
p
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
,
”
F
ro
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
7
,
2
0
1
6
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.2
0
1
6
.
0
1
4
1
9
.
[
1
1
]
I
.
S
.
P
a
k
p
a
h
a
n
,
I
.
S
.
D
u
m
a
y
a
n
t
y
,
a
n
d
S
.
M
a
n
u
r
u
n
g
,
“
E
x
p
e
r
t
s
y
s
t
e
m
f
o
r
c
h
i
l
i
p
l
a
n
t
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
u
si
n
g
t
h
e
N
a
i
v
e
B
a
y
e
s
met
h
o
d
,
”
ME
T
H
O
T
I
K
A:
J
u
r
n
a
l
I
l
m
i
a
h
T
e
k
n
i
k
I
n
f
o
rm
a
t
i
k
a
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
1
0
–
2
0
,
2
0
2
4
.
[
1
2
]
A
.
A
d
e
l
i
n
o
e
t
a
l
.
,
“
D
e
si
g
n
a
n
d
c
o
n
s
t
r
u
c
t
i
o
n
o
f
a
n
e
x
p
e
r
t
s
y
s
t
e
m
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
e
st
s
a
n
d
d
i
se
a
ses
i
n
c
o
c
o
a
p
l
a
n
t
s
u
si
n
g
w
e
b
-
b
a
se
d
f
o
r
w
a
r
d
c
h
a
i
n
i
n
g
a
n
d
b
a
c
k
w
a
r
d
c
h
a
i
n
i
n
g
me
t
h
o
d
s,
”
I
n
f
o
rm
a
t
i
k
a
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
2
0
0
–
2
0
8
,
2
0
2
4
.
[
1
3
]
L.
M
e
n
i
a
t
i
,
N
.
Y
.
L
u
mb
a
n
G
a
o
l
,
a
n
d
I
.
S
a
n
t
o
s
o
,
“
Ex
p
e
r
t
sy
st
e
m
f
o
r
d
i
a
g
n
o
s
i
n
g
c
o
c
o
a
p
l
a
n
t
d
i
s
e
a
s
e
s
u
s
i
n
g
t
h
e
c
e
r
t
a
i
n
t
y
f
a
c
t
o
r
met
h
o
d
,
”
J
-
S
I
S
K
O
T
EC
H
(
J
u
r
n
a
l
T
e
k
n
o
l
o
g
i
S
i
st
e
m
I
n
f
o
rm
a
si
d
a
n
S
i
s
t
e
m
K
o
m
p
u
t
e
r
T
G
D
)
,
v
o
l
.
5
,
n
o
.
1
,
p
.
8
3
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
5
3
5
1
3
/
j
sk
.
v
5
i
1
.
4
7
9
8
.
[
1
4
]
F
.
P
.
S
o
g
e
,
B
.
D
e
t
a
,
a
n
d
D
.
B
.
W
a
t
o
mak
i
n
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
f
u
z
z
y
l
o
g
i
c
i
n
a
n
e
x
p
e
r
t
s
y
st
e
m
f
o
r
d
e
t
e
c
t
i
n
g
p
e
st
s
a
n
d
d
i
sea
s
e
s
o
f
c
o
c
o
a
p
l
a
n
t
s i
n
W
u
l
a
n
g
g
i
t
a
n
g
D
i
s
t
r
i
c
t
,
Ea
s
t
F
l
o
r
e
s,”
J
u
rn
a
l
K
r
i
d
a
t
a
m
a
S
a
i
n
s d
a
n
T
e
k
n
o
l
o
g
i
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
2
1
2
–
2
3
4
,
2
0
2
4
.
[
1
5
]
P
.
M
.
P
r
i
h
a
t
i
n
i
,
“
U
n
c
e
r
t
a
i
n
t
y
a
n
d
v
a
g
u
e
n
e
ss
me
t
h
o
d
s i
n
e
x
p
e
r
t
s
y
st
e
ms,
”
L
o
n
t
a
r K
o
m
p
u
t
e
r
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
2
9
–
42
,
2
0
1
1
.
[
1
6
]
I
.
Jawaz
a
n
d
R
.
R
a
h
ma
d
e
w
i
,
“
P
u
l
m
o
n
a
r
y
p
n
e
u
m
o
n
i
a
d
e
t
e
c
t
i
o
n
s
y
st
e
m
w
i
t
h
d
i
g
i
t
a
l
i
ma
g
e
p
r
o
c
e
ssi
n
g
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
ELECTRO
N
J
u
r
n
a
l
I
l
m
i
a
h
T
e
k
n
i
k
E
l
e
k
t
r
o
,
v
o
l
.
5
,
n
o
.
1
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
3
3
0
1
9
/
e
l
e
c
t
r
o
n
.
v
5
i
1
.
1
1
4
.
[
1
7
]
B
.
K
.
H
a
t
u
w
a
l
,
A
.
S
h
a
k
y
a
,
a
n
d
B
.
Jo
s
h
i
,
“
P
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
r
a
n
d
o
m
f
o
r
e
st
,
K
N
N
,
S
V
M
a
n
d
C
N
N
,
”
Po
l
i
b
i
t
s
,
v
o
l
.
6
2
,
p
p
.
1
3
–
1
9
,
2
0
2
0
.
[
1
8
]
H
.
K
o
d
e
a
n
d
B
.
D
.
B
a
r
k
a
n
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
a
n
d
e
x
p
e
r
t
k
n
o
w
l
e
d
g
e
-
b
a
se
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
p
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
i
n
b
r
e
a
s
t
h
i
s
t
o
p
a
t
h
o
l
o
g
y
i
ma
g
e
s,
”
C
a
n
c
e
rs
,
v
o
l
.
1
5
,
n
o
.
1
2
,
p
.
3
0
7
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
c
a
n
c
e
r
s
1
5
1
2
3
0
7
5
.
[
1
9
]
B
.
Tu
g
r
u
l
,
E
.
El
f
a
t
i
m
i
,
a
n
d
R
.
Er
y
i
g
i
t
,
“
C
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
i
n
d
e
t
e
c
t
i
o
n
o
f
p
l
a
n
t
l
e
a
f
d
i
se
a
ses
:
a
r
e
v
i
e
w
,
”
Ag
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
2
,
n
o
.
8
,
p
.
1
1
9
2
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
2
0
8
1
1
9
2
.
[
2
0
]
N
.
Y
e
mi
H
u
ssa
i
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
r
c
h
i
t
e
c
t
u
r
e
s
e
n
a
b
l
i
n
g
s
o
p
h
i
s
t
i
c
a
t
e
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
r
e
p
r
e
se
n
t
a
t
i
o
n
f
o
r
c
o
mp
l
e
x
d
a
t
a
a
n
a
l
y
si
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
n
o
v
a
t
i
v
e
S
c
i
e
n
c
e
a
n
d
Re
s
e
a
rc
h
T
e
c
h
n
o
l
o
g
y
(
I
J
I
S
RT)
,
p
p
.
2
2
9
0
–
2
3
0
0
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
3
8
1
2
4
/
i
j
i
sr
t
/
i
j
i
sr
t
2
4
o
c
t
1
5
2
1
.
[
2
1
]
R
.
P
u
j
i
a
t
i
a
n
d
N
.
R
o
c
h
m
a
w
a
t
i
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
h
e
r
b
a
l
p
l
a
n
t
l
e
a
f
i
m
a
g
e
s
u
s
i
n
g
t
h
e
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
C
N
N
)
m
e
t
h
o
d
,
”
J
o
u
r
n
a
l
o
f
I
n
f
o
r
m
a
t
i
c
s
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
J
I
N
A
C
S
)
,
v
o
l
.
3
,
n
o
.
0
3
,
p
p
.
3
5
1
–
3
5
7
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
2
6
7
4
0
/
j
i
n
a
c
s
.
v
3
n
0
3
.
p
3
5
1
-
3
5
7
.
[
2
2
]
M
.
K
.
B
a
sy
i
r
a
n
d
S
.
S
u
p
i
y
a
n
d
i
,
“
D
o
g
b
r
e
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
o
n
d
i
g
i
t
a
l
i
ma
g
e
s
,
”
J
o
u
rn
a
l
O
f
S
o
c
i
a
l
S
c
i
e
n
c
e
R
e
se
a
rc
h
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
9
9
–
1
0
9
,
2
0
2
5
.
[
2
3
]
A
.
J
u
l
i
a
n
t
o
a
n
d
A
.
S
u
n
y
o
t
o
,
“
A
p
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
r
i
c
e
l
e
a
f
d
i
se
a
se,
”
I
A
ES
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
-
AI
)
,
v
o
l
.
1
0
,
n
o
.
4
,
p
.
1
0
6
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
0
.
i
4
.
p
p
1
0
6
9
-
1
0
7
8
.
[
2
4
]
T.
D
.
S
a
l
k
a
,
M
.
B
.
H
a
n
a
f
i
,
S
.
M
.
S
.
A
.
A
.
R
a
h
m
a
n
,
D
.
B
.
M
.
Zu
l
p
e
r
i
,
a
n
d
Z
.
O
mar
,
“
P
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s
m
o
d
e
l
:
a
r
e
v
i
e
w
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
R
e
v
i
e
w
,
v
o
l
.
5
8
,
n
o
.
1
0
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
025
-
1
1
2
3
4
-
6.
[
2
5
]
S
.
S
.
R
e
k
a
,
V
.
D
.
M
u
r
t
h
y
V
o
o
n
a
,
P
.
V
.
S
a
i
N
i
t
h
i
s
h
,
D
.
S
.
P
a
a
v
a
n
K
u
m
a
r
,
P
.
V
e
n
u
g
o
p
a
l
,
a
n
d
V
.
R
a
v
i
,
“
P
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
si
s
o
f
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
o
v
e
r
-
v
o
l
u
m
e
v
e
h
i
c
l
e
s,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
4
,
p
.
2
5
4
9
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
4
2
5
4
9
.
[
2
6
]
N
.
S
r
i
v
a
st
a
v
a
,
G
.
H
i
n
t
o
n
,
A
.
K
r
i
z
h
e
v
sk
y
,
I
.
S
u
t
s
k
e
v
e
r
,
a
n
d
R
.
S
a
l
a
k
h
u
t
d
i
n
o
v
,
“
D
r
o
p
o
u
t
:
a
s
i
mp
l
e
w
a
y
t
o
p
r
e
v
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
r
o
m o
v
e
r
f
i
t
t
i
n
g
,
”
T
h
e
j
o
u
rn
a
l
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
res
e
a
rc
h
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
9
2
9
–
1
9
5
8
,
2
0
1
4
.
[
2
7
]
R
.
O
.
D
u
d
a
,
P
.
E.
H
a
r
t
,
a
n
d
D
.
G
.
S
t
o
r
k
,
“
P
a
t
t
e
r
n
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
S
e
c
o
n
d
Ed
i
t
i
o
n
,
v
o
l
.
1
6
,
n
o
.
2
,
2
0
0
1
.
[
2
8
]
Y
.
L
e
c
u
n
,
Y
.
B
e
n
g
i
o
,
a
n
d
G
.
H
i
n
t
o
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
,
”
N
a
t
u
re
,
v
o
l
.
5
2
1
,
n
o
.
7
5
5
3
,
p
p
.
4
3
6
–
4
4
4
,
M
a
y
2
0
1
5
,
d
o
i
:
1
0
.
1
0
3
8
/
n
a
t
u
r
e
1
4
5
3
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
De
wi
M
a
r
i
n
i
U
m
i
At
m
a
j
a
i
s
a
lec
t
u
re
r
i
n
t
h
e
I
n
f
o
rm
a
t
i
o
n
S
y
ste
m
S
t
u
d
y
P
r
o
g
r
a
m
,
Ce
n
te
r
o
f
E
x
c
e
ll
e
n
c
e
f
o
r
H
u
m
a
n
Ce
n
t
ric
E
n
g
i
n
e
e
r
i
n
g
(
HU
M
IC
)
,
Tel
k
o
m
U
n
i
v
e
rs
it
y
,
Ja
k
a
rta
Ca
m
p
u
s
.
S
h
e
o
b
ta
i
n
e
d
h
e
r
Ba
c
h
e
lo
r’
s
d
e
g
r
e
e
fr
o
m
Je
n
d
e
ra
l
A
c
h
m
a
d
Ya
n
i
U
n
i
v
e
rs
it
y
i
n
2
0
1
8
a
n
d
c
o
m
p
le
te
d
h
e
r
M
a
st
e
r’
s
d
e
g
r
e
e
a
t
P
re
s
i
d
e
n
t
U
n
i
v
e
rs
it
y
i
n
2
0
2
0
.
Th
r
o
u
g
h
o
u
t
h
e
r
a
c
a
d
e
m
ic
c
a
re
e
r
,
s
h
e
h
a
s
p
u
b
li
s
h
e
d
se
v
e
ra
l
a
c
c
re
d
i
te
d
n
a
t
i
o
n
a
l
a
n
d
i
n
t
e
r
n
a
ti
o
n
a
l
j
o
u
r
n
a
l
a
rt
ic
les
f
o
c
u
s
i
n
g
o
n
Ar
ti
fic
ia
l
I
n
te
ll
i
g
e
n
c
e
(A
I)
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
s
tem
s
.
F
o
r
fu
rt
h
e
r
c
o
r
re
s
p
o
n
d
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
te
d
a
t
e
m
a
i
l
:
d
e
w
ima
ri
n
i
u
m
iatm
a
ja
@te
l
k
o
m
u
n
i
v
e
rsi
t
y
.
a
c
.
i
d
.
Ar
if
Ra
h
m
a
n
H
a
k
im
is
a
le
c
tu
re
r
a
n
d
re
se
a
rc
h
e
r
a
t
Telk
o
m
Un
iv
e
rsity
wit
h
a
c
a
d
e
m
ic
a
n
d
p
ro
fe
ss
io
n
a
l
in
ter
e
sts
in
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
,
so
ftwa
re
e
n
g
in
e
e
ri
n
g
,
a
n
d
d
ig
it
a
l
i
n
n
o
v
a
ti
o
n
.
He
o
b
tain
e
d
h
is
Ba
c
h
e
lo
r’s
d
e
g
re
e
i
n
I
n
f
o
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
fr
o
m
S
TT
P
e
li
ta
Ba
n
g
sa
in
2
0
1
7
a
n
d
c
o
m
p
lete
d
h
is
M
a
ste
r’s
d
e
g
re
e
in
In
fo
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
a
t
P
re
sid
e
n
t
Un
i
v
e
rsity
i
n
2
0
2
0
.
In
a
d
d
it
i
o
n
t
o
h
is
a
c
a
d
e
m
ic
a
c
ti
v
it
ies
,
h
e
is
a
c
ti
v
e
ly
in
v
o
l
v
e
d
in
re
se
a
rc
h
,
sc
ien
ti
fic
p
u
b
l
ica
ti
o
n
,
a
n
d
a
c
a
d
e
m
ic
writi
n
g
i
n
t
h
e
fiel
d
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
in
f
o
rm
a
ti
o
n
sy
ste
m
s.
His
sc
h
o
la
rly
c
o
n
tri
b
u
ti
o
n
s
a
re
i
n
d
e
x
e
d
t
h
ro
u
g
h
h
is
G
o
o
g
le
S
c
h
o
lar
p
ro
fil
e
,
re
flec
ti
n
g
h
is
e
n
g
a
g
e
m
e
n
t
in
in
terd
isc
ip
li
n
a
ry
re
se
a
rc
h
a
n
d
h
i
g
h
e
r
e
d
u
c
a
ti
o
n
d
e
v
e
lo
p
m
e
n
t.
He
c
a
n
b
e
c
o
n
tac
te
d
a
t
e
m
a
il
:
a
rifr
a
h
m
a
n
a
rh
@te
lk
o
m
u
n
iv
e
rsit
y
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
0
8
7
-
1
0
9
6
1096
Fa
d
h
i
l
R
o
z
i
H
e
n
d
r
a
w
a
n
is
a
lec
tu
re
r
in
t
h
e
S
1
I
n
fo
rm
a
ti
o
n
S
y
ste
m
s
p
ro
g
ra
m
a
t
Telk
o
m
Un
i
v
e
rsity
,
Ja
k
a
rta
Ca
m
p
u
s.
His
in
tere
sts
in
c
l
u
d
e
Da
ta
G
o
v
e
rn
a
n
c
e
,
I
T
G
o
v
e
rn
a
n
c
e
,
P
ro
jec
t
M
a
n
a
g
e
m
e
n
t,
Kn
o
wle
d
g
e
M
a
n
a
g
e
m
e
n
t,
a
n
d
re
late
d
a
sp
e
c
ts
o
f
IT
se
c
u
rit
y
.
He
h
a
s
a
u
th
o
re
d
1
3
p
u
b
li
c
a
ti
o
n
s,
in
c
l
u
d
i
n
g
b
o
o
k
c
h
a
p
ters
a
n
d
c
o
n
fe
re
n
c
e
p
r
o
c
e
e
d
in
g
s.
He
h
o
ld
s
b
o
t
h
h
is
b
a
c
h
e
lo
r’s
a
n
d
m
a
ste
r’s
d
e
g
re
e
s
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
fro
m
Telk
o
m
Un
iv
e
rsity
.
F
a
d
h
i
l
is
a
c
ti
v
e
in
a
c
a
d
e
m
ic
p
u
b
l
ish
i
n
g
a
n
d
c
o
m
m
u
n
it
y
e
n
g
a
g
e
m
e
n
t;
h
is
wo
rk
s
in
d
e
x
e
d
o
n
S
INTA
a
n
d
G
o
o
g
le
S
c
h
o
lar
c
o
v
e
r
t
h
e
m
e
s
su
c
h
a
s
d
ig
i
tal
a
n
d
c
y
b
e
rse
c
u
rit
y
li
tera
c
y
,
a
n
d
h
e
fre
q
u
e
n
tl
y
sh
a
r
e
s
tea
c
h
in
g
,
m
e
n
to
rsh
ip
,
a
n
d
c
o
m
m
u
n
it
y
‐se
rv
ice
a
c
ti
v
it
ies
th
ro
u
g
h
p
r
o
fe
ss
io
n
a
l
c
h
a
n
n
e
ls
a
s
a
Telk
o
m
Un
iv
e
rsity
Ja
k
a
rta
f
a
c
u
lt
y
m
e
m
b
e
r.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
fa
d
h
il
ro
z
i
h
e
n
d
ra
wa
n
@te
lk
o
m
u
n
iv
e
rsity
.
a
c
.
id
.
K
o
m
a
n
g
Di
a
h
De
v
i
Pr
a
m
e
sty
is
a
n
u
n
d
e
rg
ra
d
u
a
te
stu
d
e
n
t
in
th
e
I
n
fo
rm
a
ti
o
n
S
y
ste
m
s
S
tu
d
y
P
r
o
g
ra
m
wit
h
a
st
ro
n
g
i
n
tere
st
in
Artifi
c
ial
I
n
telli
g
e
n
c
e
(AI),
d
a
ta
p
ro
c
e
ss
in
g
,
a
n
d
in
f
o
rm
a
ti
o
n
sy
ste
m
s.
S
h
e
is
p
a
ss
io
n
a
te
a
b
o
u
t
e
x
p
l
o
rin
g
h
o
w
d
a
ta
a
n
d
i
n
telli
g
e
n
t
tec
h
n
o
l
o
g
ies
c
a
n
b
e
a
p
p
li
e
d
t
o
su
p
p
o
rt
d
e
c
isio
n
-
m
a
k
in
g
a
n
d
im
p
ro
v
e
o
rg
a
n
iza
ti
o
n
a
l
p
ro
c
e
ss
e
s.
Th
ro
u
g
h
h
e
r
a
c
a
d
e
m
ic
jo
u
r
n
e
y
,
sh
e
h
a
s
d
e
v
e
lo
p
e
d
sk
i
ll
s
in
d
a
ta
m
a
n
a
g
e
m
e
n
t
a
n
d
th
e
u
se
o
f
a
n
a
l
y
ti
c
a
l
to
o
ls
t
o
g
a
in
i
n
sig
h
ts
fro
m
d
a
ta.
He
r
e
n
th
u
sia
sm
fo
r
lea
rn
in
g
a
n
d
in
n
o
v
a
ti
o
n
re
flec
ts
h
e
r
c
o
m
m
it
m
e
n
t
to
a
d
v
a
n
c
in
g
tec
h
n
o
lo
g
y
-
b
a
se
d
so
lu
ti
o
n
s
i
n
th
e
fiel
d
o
f
in
fo
rm
a
ti
o
n
sy
ste
m
s.
F
o
r
f
u
rt
h
e
r
c
o
rre
sp
o
n
d
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
iah
d
e
v
ip
ra
m
e
stji
e
@s
tu
d
e
n
t.
telk
o
m
u
n
i
v
e
rsity
.
a
c
.
i
d
.
Na
u
fa
l
F
a
d
h
i
la
h
Fi
tr
a
h
is
a
n
u
n
d
e
rg
ra
d
u
a
te
st
u
d
e
n
t
i
n
th
e
I
n
f
o
rm
a
ti
o
n
S
y
ste
m
s
S
tu
d
y
P
ro
g
ra
m
,
F
a
c
u
lt
y
o
f
I
n
d
u
strial
En
g
i
n
e
e
rin
g
,
Tel
k
o
m
Un
iv
e
rsity
.
He
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
h
is
Ba
c
h
e
lo
r’s
d
e
g
re
e
with
a
fo
c
u
s
o
n
tec
h
n
o
lo
g
y
,
d
a
t
a
a
n
a
ly
sis,
a
n
d
in
f
o
rm
a
ti
o
n
sy
ste
m
s
d
e
v
e
lo
p
m
e
n
t.
Du
ri
n
g
h
is
st
u
d
ies
,
h
e
h
a
s
b
e
e
n
in
v
o
lv
e
d
in
se
v
e
ra
l
a
c
a
d
e
m
ic
p
ro
jec
ts
a
n
d
re
se
a
rc
h
a
c
ti
v
it
ie
s
re
late
d
to
s
y
ste
m
d
e
sig
n
,
d
a
ta
a
n
a
ly
ti
c
s,
a
n
d
d
ig
it
a
l
tran
sfo
rm
a
ti
o
n
.
His
a
c
a
d
e
m
ic
in
tere
sts
in
c
lu
d
e
in
f
o
rm
a
ti
o
n
s
y
ste
m
d
e
v
e
lo
p
m
e
n
t
,
d
a
ta
-
d
ri
v
e
n
d
e
c
isio
n
m
a
k
i
n
g
,
a
n
d
p
ro
jec
t
m
a
n
a
g
e
m
e
n
t.
F
o
r
f
u
rth
e
r
c
o
r
re
sp
o
n
d
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
a
u
fa
lfad
h
il
a
h
fit
ra
h
@te
l
k
o
m
u
n
iv
e
rsit
y
.
a
c
.
id
.
Fa
iz
Ro
c
h
m
a
tu
ll
a
h
Wid
h
a
p
u
tr
a
is
a
n
e
n
e
rg
e
ti
c
a
n
d
p
a
ss
io
n
a
t
e
stu
d
e
n
t
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
d
e
g
re
e
i
n
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
a
t
Telk
o
m
Un
i
v
e
rsity
.
He
striv
e
s
to
d
e
v
e
lo
p
h
is
sk
il
ls
in
P
r
o
g
ra
m
m
in
g
,
G
ra
p
h
ic
De
sig
n
,
Web
De
sig
n
,
a
n
d
F
ro
n
t
-
En
d
De
v
e
lo
p
m
e
n
t.
W
o
rk
i
n
g
wh
il
e
stu
d
y
i
n
g
is
o
n
e
o
f
h
is
p
ri
n
c
ip
les
.
He
is
c
u
rre
n
t
ly
wo
rk
in
g
a
s
a
tea
c
h
e
r
a
t
a
n
Isla
m
ic
fo
u
n
d
a
ti
o
n
,
in
ter
n
in
g
a
s
a
n
o
p
e
ra
to
r
a
t
a
c
o
n
str
u
c
ti
o
n
c
o
n
su
l
ti
n
g
fi
rm
,
a
n
d
h
a
s
a
lso
wo
rk
e
d
a
s
a
n
a
d
v
e
rti
se
r
a
t
a
n
Um
ra
h
c
o
n
s
u
lt
in
g
c
o
m
p
a
n
y
.
His
d
re
a
m
is
to
p
u
rsu
e
a
m
a
ste
r’s
d
e
g
re
e
i
n
Ja
p
a
n
wh
il
e
sp
re
a
d
i
n
g
Isla
m
th
e
re
(d
o
i
n
g
d
a
’wa
h
).
On
e
o
f
th
e
g
u
i
d
i
n
g
p
rin
c
i
p
les
h
e
li
v
e
s b
y
is:
“
Th
e
b
e
st o
f
p
e
o
p
le are
th
o
se
wh
o
a
re
m
o
st b
e
n
e
ficia
l
to
o
th
e
rs.” (
ِ
س
ا
ن
ل
ِ
ل
ْ
م
ُ
ه
ُ
ع
َ
ف
ْ
ن
َ
أ
ِ
س
ا
ن
ل
ا
ُ
ر
ْ
ي
َ
خ
)
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
fa
izro
c
h
m
a
tu
ll
a
h
@s
t
u
d
e
n
t
.
telk
o
m
u
n
iv
e
rsity
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.