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.
15
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
3429
~
3
4
3
8
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
3
.
pp
3
4
2
9
-
3
4
3
8
3429
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
O
ptimi
zing
rice
le
a
f
disea
se cla
ss
ific
a
tion throug
h con
v
o
lutiona
l
neura
l net
wo
rk a
rchitec
tural mo
di
ficatio
n and
aug
menta
tion
techniqu
es
M
o
ha
m
a
d F
irda
us
1
,
K
us
rini
2
,
I
M
a
de
Art
ha
Ag
a
s
t
y
a
3
,
R
o
drig
o
M
a
rt
ínez
-
B
éj
a
r
4,
5
1
I
n
f
o
r
mat
i
c
s,
F
a
c
u
l
t
y
o
f
Te
c
h
n
i
c
,
I
n
st
i
t
u
t
T
e
k
n
o
l
o
g
i
d
a
n
K
e
se
h
a
t
a
n
M
a
h
a
r
d
i
k
a
,
C
i
r
e
b
o
n
,
I
n
d
o
n
e
si
a
2
I
n
f
o
r
mat
i
c
s,
P
o
s
t
g
r
a
d
u
a
t
e
P
r
o
g
r
a
m,
U
n
i
v
e
r
si
t
a
s
A
mi
k
o
m
Y
o
g
y
a
k
a
r
t
a
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
3
I
n
f
o
r
mat
i
c
s,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s
A
m
i
k
o
m
Y
o
g
y
a
k
a
r
t
a
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
4
I
n
f
o
r
mat
i
c
s,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
y
o
f
M
u
r
c
i
a
,
M
u
r
c
i
a
,
S
p
a
i
n
5
F
u
n
d
a
c
i
ó
n
p
a
r
a
l
a
I
n
v
e
s
t
i
g
a
c
i
ó
n
y
D
e
sarr
o
l
l
o
Te
c
n
o
l
ó
g
i
c
o
d
e
l
a
S
o
c
i
e
d
a
d
d
e
l
C
o
n
o
c
i
mi
e
n
t
o
,
M
u
r
c
i
a
,
S
p
a
i
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
2
1
,
2
0
2
4
R
ev
is
ed
Dec
1
6
,
2
0
2
4
Acc
ep
ted
J
an
1
6
,
2
0
2
5
Th
is
re
se
a
rc
h
f
o
c
u
se
s
o
n
a
d
v
a
n
c
in
g
t
h
e
a
c
c
u
ra
c
y
o
f
rice
lea
f
d
ise
a
se
c
las
sifica
ti
o
n
b
y
in
teg
ra
t
in
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
s
(CNN
)
a
n
d
d
e
e
p
lea
rn
in
g
m
o
d
e
ls.
Wi
t
h
I
n
d
o
n
e
si
a
ra
n
k
in
g
th
ir
d
i
n
g
lo
b
a
l
rice
p
ro
d
u
c
ti
o
n
,
e
ffe
c
ti
v
e
c
ro
p
m
a
n
a
g
e
m
e
n
t
is
c
r
u
c
ial
fo
r
s
u
sta
in
i
n
g
a
g
ricu
l
tu
ra
l
o
u
tp
u
t
.
T
h
is
stu
d
y
e
m
p
l
o
y
s
i
n
n
o
v
a
ti
v
e
d
a
ta
a
u
g
m
e
n
tati
o
n
tec
h
n
iq
u
e
s,
in
c
lu
d
in
g
ra
n
d
o
m
z
o
o
m
a
n
d
o
th
e
rs,
to
e
n
h
a
n
c
e
m
o
d
e
l
train
i
n
g
ro
b
u
st
n
e
ss
.
T
h
e
e
x
p
e
rime
n
tatio
n
in
v
o
lv
e
s
e
ig
h
t
sc
e
n
a
rio
s
wit
h
v
a
ri
e
d
a
rc
h
it
e
c
tu
ra
l
c
o
n
fig
u
ra
ti
o
n
s
a
p
p
l
ied
to
a
re
sid
u
a
l
n
e
two
r
k
(Re
sN
e
t)5
0
lay
e
r
m
o
d
e
l
to
o
p
ti
m
ize
d
ise
a
se
c
la
ss
ifi
c
a
ti
o
n
p
e
rfo
rm
a
n
c
e
.
F
e
a
tu
rin
g
Ra
n
d
o
m
z
o
o
m
with
o
u
t
th
e
m
u
lt
i
lay
e
r
p
e
rc
e
p
tro
n
(M
LP
)
c
o
m
p
o
n
e
n
t,
it
e
m
e
rg
e
s
a
s
th
e
m
o
st
e
ffe
c
ti
v
e
,
d
e
m
o
n
stra
ti
n
g
su
p
e
rio
r
a
c
c
u
ra
c
y
a
n
d
p
e
rf
o
rm
a
n
c
e
m
e
tri
c
s.
A
g
rid
se
a
rc
h
is
c
o
n
d
u
c
ted
t
o
o
p
ti
m
ize
M
LP
lay
e
rs,
re
v
e
a
li
n
g
a
th
re
e
-
la
y
e
r
c
o
n
fi
g
u
ra
ti
o
n
a
s
th
e
m
o
st
e
ff
e
c
ti
v
e
.
We
fo
u
n
d
t
h
a
t
d
a
ta
a
u
g
m
e
n
tati
o
n
a
n
d
th
e
M
LP
la
y
e
r
c
a
n
in
c
re
a
se
th
e
a
c
c
u
ra
c
y
o
f
t
h
e
d
ise
a
se
c
las
sifica
ti
o
n
tas
k
.
Th
e
m
e
th
o
d
p
r
o
p
o
se
d
i
n
th
is
s
tu
d
y
will
li
k
e
ly
h
a
v
e
a
m
u
c
h
h
i
g
h
e
r
p
ro
p
o
rti
o
n
o
f
c
o
rre
c
t
d
ise
a
se
c
las
sifi
c
a
ti
o
n
b
y
c
o
m
b
in
i
n
g
M
L
P
a
n
d
z
o
o
m
a
u
g
m
e
n
tatio
n
.
S
p
e
c
ifi
c
a
ll
y
,
t
h
e
m
o
d
e
l
with
th
re
e
M
LP
lay
e
rs
a
n
d
z
o
o
m
a
u
g
m
e
n
tatio
n
d
e
m
o
n
stra
ted
sig
n
ifi
c
a
n
t
ly
h
i
g
h
e
r
a
c
c
u
ra
c
y
,
a
c
h
iev
in
g
tes
t
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
re
c
a
ll
,
a
n
d
F
1
-
sc
o
r
e
o
f
0
.
9
2
,
0
.
9
4
,
0
.
9
2
,
a
n
d
0
.
9
2
,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
Data
au
g
m
en
tatio
n
Mu
ltil
ay
er
p
er
ce
p
tr
o
n
R
esNet5
0
R
ice
leaf
d
is
ea
s
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
:
Ku
s
r
in
i
Ma
g
is
ter
o
f
I
n
f
o
r
m
atics E
n
g
i
n
ee
r
in
g
,
Un
iv
e
r
s
itas
Am
ik
o
m
Yo
g
y
ak
ar
ta
J
l.
R
in
g
r
o
ad
Utar
a
C
o
n
d
o
n
g
C
atu
r
Dep
o
k
Slem
an
Yo
g
y
ak
ar
t
a
I
n
d
o
n
esia
E
m
ail:
k
u
s
r
in
i@
am
ik
o
m
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
R
ice
cu
ltiv
atio
n
[
1
]
is
p
iv
o
ta
l
in
g
lo
b
al
ag
r
icu
lt
u
r
e,
s
er
v
i
n
g
as
a
p
r
im
ar
y
f
o
o
d
s
o
u
r
ce
f
o
r
d
iv
e
r
s
e
p
o
p
u
latio
n
s
wo
r
ld
wid
e.
I
n
d
o
n
esia,
r
an
k
in
g
th
ir
d
in
g
lo
b
al
r
ice
p
r
o
d
u
ctio
n
b
eh
in
d
C
h
in
a
an
d
I
n
d
ia,
p
lay
s
a
s
ig
n
if
ican
t
r
o
le
in
s
u
s
tain
in
g
t
h
is
cr
u
cial
ag
r
icu
ltu
r
al
o
u
tp
u
t
[
2
]
.
A
k
ey
f
o
cu
s
is
e
f
f
ec
tiv
e
cr
o
p
m
an
ag
em
e
n
t,
p
ar
ticu
lar
ly
d
is
ea
s
e
an
d
p
est
co
n
tr
o
l,
to
en
s
u
r
e
c
o
n
tin
u
e
d
h
i
g
h
p
r
o
d
u
ctio
n
lev
els.
Un
ch
ec
k
ed
d
is
ea
s
es
p
o
s
e
a
s
u
b
s
tan
tial
th
r
ea
t
to
b
o
th
f
o
o
d
s
ec
u
r
ity
an
d
ec
o
n
o
m
ic
s
tab
ilit
y
.
Ad
d
r
ess
in
g
th
ese
ch
alle
n
g
es
h
as
p
r
o
m
p
ted
r
esear
ch
er
s
to
ex
p
lo
r
e
in
n
o
v
a
tiv
e
s
o
lu
tio
n
s
,
p
ar
ticu
lar
ly
lev
er
ag
in
g
ad
v
an
ce
m
e
n
ts
in
d
ig
ital
im
ag
e
an
aly
s
is
.
Stu
d
ies
h
av
e
in
v
esti
g
ated
th
e
ap
p
licatio
n
o
f
s
o
p
h
is
ticated
alg
o
r
ith
m
s
,
in
clu
d
in
g
d
ee
p
lear
n
in
g
tech
n
i
q
u
es
lik
e
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
[
3
]
–
[
6
]
.
T
h
ese
alg
o
r
it
h
m
s
h
av
e
b
ee
n
a
p
p
lied
to
ac
c
u
r
ately
id
en
tify
a
n
d
class
if
y
v
ar
io
u
s
r
ice
leaf
d
is
ea
s
es th
at
h
in
d
er
o
p
tim
al
c
r
o
p
g
r
o
wth
an
d
y
ield
.
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
4
2
9
-
3
4
3
8
3430
A
n
o
tab
le
ar
ea
o
f
ex
p
lo
r
atio
n
in
v
o
lv
es
u
tili
zin
g
th
ese
ad
v
a
n
ce
d
tech
n
o
l
o
g
ies
to
ca
teg
o
r
i
ze
d
is
tin
ct
r
ice
leaf
d
is
ea
s
es,
s
u
ch
as
b
r
o
wn
s
p
o
t,
leaf
b
last
,
leaf
b
lig
h
t,
an
d
leaf
s
m
u
t,
d
is
tin
g
u
is
h
in
g
th
em
f
r
o
m
a
h
ea
lth
y
leaf
[
7
]
–
[
9
]
.
R
esear
ch
er
s
h
av
e
c
o
n
d
u
cted
ex
te
n
s
iv
e
an
aly
s
es
u
s
in
g
d
atasets
f
r
o
m
r
ep
u
ta
b
le
s
o
u
r
ce
s
lik
e
Kag
g
le
o
r
t
h
e
Un
iv
e
r
s
ity
o
f
C
alif
o
r
n
ia
I
r
v
in
e
(
UC
I
)
Ma
ch
in
e
L
ea
r
n
in
g
R
ep
o
s
ito
r
y
,
co
n
tain
i
n
g
d
iv
er
s
e
im
ag
es
o
f
d
is
ea
s
ed
r
ice
p
lan
t
s
f
o
r
m
o
d
el
tr
ain
in
g
.
I
n
a
d
d
itio
n
to
d
ataset
s
elec
tio
n
,
a
u
g
m
en
tatio
n
tech
n
iq
u
es
h
av
e
em
e
r
g
ed
as
cr
itical
f
ac
to
r
s
in
r
e
f
in
in
g
th
e
ac
cu
r
ac
y
a
n
d
r
eliab
ilit
y
o
f
d
is
ea
s
e
class
if
icatio
n
m
o
d
els.
Data
au
g
m
en
tatio
n
[
3
]
,
[
6
]
,
[
1
0
]
,
[
1
1
]
aim
s
to
en
h
a
n
ce
t
h
e
d
i
v
er
s
ity
o
f
tr
ain
in
g
d
ata,
en
a
b
lin
g
t
h
e
d
ev
elo
p
m
e
n
t
o
f
m
o
r
e
r
o
b
u
s
t
an
d
v
er
s
atile
m
o
d
els.
Mo
r
eo
v
e
r
,
th
ey
also
ex
p
lo
r
ed
v
ar
iatio
n
s
in
m
o
d
el
ar
ch
itectu
r
es
b
y
ex
p
er
im
en
tin
g
with
d
if
f
er
e
n
t
lay
er
s
,
ac
tiv
atio
n
f
u
n
ctio
n
s
,
an
d
n
etwo
r
k
s
tr
u
ctu
r
es,
in
cl
u
d
in
g
alter
atio
n
s
in
C
NN
an
d
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
ML
P)
c
o
n
f
ig
u
r
atio
n
s
to
o
p
tim
ize
p
er
f
o
r
m
an
ce
a
n
d
ac
h
i
ev
e
h
ig
h
e
r
ac
cu
r
ac
y
r
ates in
d
is
ea
s
e
class
if
ica
tio
n
.
I
n
L
u
et
a
l.
[
1
2
]
’
s
in
v
esti
g
atio
n
,
C
NNs
ar
e
tr
ain
e
d
o
n
a
d
ataset
o
f
5
0
0
im
ag
es
f
r
o
m
a
r
ice
ex
p
er
im
en
tal
f
ield
,
ac
h
ie
v
in
g
9
5
.
4
8
%
ac
cu
r
ac
y
in
id
en
tify
in
g
ten
co
m
m
o
n
r
ice
d
is
ea
s
es
.
Z
h
an
g
et
a
l.
[
1
3
]
u
s
ed
2
-
D
s
p
ec
tr
al
im
ag
es
an
d
1
-
D
s
p
ec
tr
a,
em
p
lo
y
in
g
C
NNs,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
S
VM
)
,
r
an
d
o
m
f
o
r
est
(
R
F),
an
d
p
ar
tial
least
s
q
u
ar
es
-
d
is
cr
im
in
an
t
an
aly
s
is
(
PLS
-
DA)
,
ac
h
iev
in
g
h
i
g
h
ac
cu
r
ac
y
.
R
ith
ar
s
o
n
et
a
l.
[
1
4
]
p
r
o
p
o
s
ed
tailo
r
ed
C
NN
m
o
d
els,
o
u
tp
er
f
o
r
m
in
g
tr
an
s
f
er
lear
n
in
g
ap
p
r
o
ac
h
es
with
9
9
.
9
4
%
ac
cu
r
ac
y
.
I
n
J
esie
et
a
l.
[
1
5
]
’
s
ex
p
er
im
en
t
r
esu
lt,
a
h
y
b
r
id
C
NN
m
o
d
el
id
en
tifie
s
f
iv
e
p
a
d
d
y
leaf
d
i
s
ea
s
es,
s
u
r
p
ass
in
g
p
r
ev
io
u
s
m
et
h
o
d
s
.
C
u
i
an
d
T
an
[
1
6
]
co
m
p
ar
ed
YOL
Ov
3
with
tr
ad
itio
n
al
C
NN
m
o
d
els,
ac
h
iev
in
g
im
p
r
o
v
ed
r
ec
all,
p
r
ec
is
io
n
,
F1
-
s
co
r
e,
a
n
d
ac
c
u
r
ac
y
f
o
r
r
ice
d
is
ea
s
e
class
if
icatio
n
.
L
u
et
a
l.
[
5
]
c
o
m
b
in
ed
C
NN
an
d
b
id
ir
ec
tio
n
al
g
ated
r
ec
u
r
r
en
t
u
n
it
(
B
iGR
U)
m
o
d
u
les,
r
ea
ch
in
g
9
8
.
2
1
%
ac
cu
r
ac
y
in
id
en
tify
in
g
f
o
u
r
r
ice
d
is
ea
s
es,
o
f
f
er
in
g
a
r
eliab
le
r
e
co
g
n
itio
n
m
eth
o
d
.
I
n
Gu
p
ta
et
a
l.
[
1
7
]
’s
r
esea
r
ch
,
h
y
p
er
p
a
r
am
eter
s
o
f
E
f
f
i
cien
tNetV2
ar
e
f
in
e
-
tu
n
e
d
f
o
r
h
ig
h
e
r
ac
cu
r
ac
y
in
d
etec
tin
g
p
lan
t
d
is
ea
s
es.
T
h
e
Plan
t
Dis
ea
s
es
Data
s
et
with
3
8
class
es
is
u
s
ed
,
in
ten
tio
n
ally
ex
p
o
s
in
g
n
eu
r
al
n
etwo
r
k
s
to
a
n
o
is
y
tr
ain
in
g
d
ataset.
Petch
iam
m
al
et
a
l.
[
1
8
]
in
tr
o
d
u
ce
d
Pad
d
y
Net,
a
1
7
-
lay
er
m
o
d
el
ac
h
iev
i
n
g
9
8
.
9
9
%
ac
cu
r
ac
y
in
p
a
d
d
y
leaf
d
is
ea
s
e
d
et
ec
tio
n
u
s
in
g
a
d
ataset
o
f
1
6
,
2
2
5
s
am
p
les.
Z
h
an
g
et
a
l.
[
1
9
]
r
eso
lv
e
d
th
e
p
r
o
b
le
m
o
f
s
ig
n
if
ican
t
C
NN
m
o
d
el
p
ar
am
eter
s
b
y
p
r
o
p
o
s
in
g
a
m
u
lt
i
-
s
ca
le
co
n
v
o
l
u
tio
n
m
o
d
u
le
with
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
(
VGG)
,
ac
h
iev
i
n
g
9
7
.
1
%
test
ac
cu
r
ac
y
an
d
2
6
.
1
M
m
em
o
r
y
r
e
q
u
ir
em
e
n
t.
Pra
th
im
a
et
a
l.
[
4
]
f
av
o
r
ed
r
e
s
id
u
al
n
etwo
r
k
-
5
0
(
R
esNet5
0
)
o
v
er
Alex
Net
f
o
r
m
o
b
ile
ap
p
licatio
n
s
d
u
e
to
a
s
m
aller
m
o
d
el
s
ize
wi
th
co
m
p
ar
ab
le
ac
cu
r
ac
y
.
Do
g
r
a
et
a
l.
[
2
0
]
p
r
o
p
o
s
ed
a
VGG1
9
m
o
d
el
with
tr
an
s
f
er
lear
n
in
g
,
ac
h
iev
in
g
9
3
.
0
%
ac
cu
r
ac
y
i
n
r
ice
leaf
d
is
ea
s
e
id
en
tific
atio
n
.
Ah
a
d
et
a
l.
[
3
]
c
o
m
p
ar
ed
s
ix
C
NN
ar
ch
itectu
r
es,
h
ig
h
lig
h
tin
g
an
en
s
em
b
le
m
o
d
el
with
9
8
%
ac
cu
r
ac
y
u
s
in
g
tr
a
n
s
f
er
lear
n
i
n
g
.
Simh
ad
r
i
et
a
l.
[
2
1
]
em
p
lo
y
ed
tr
an
s
f
er
lear
n
i
n
g
o
n
1
5
C
NN
m
o
d
els,
with
I
n
ce
p
tio
n
V3
o
u
t
p
er
f
o
r
m
in
g
o
th
er
s
with
9
9
.
6
4
%
ac
cu
r
ac
y
.
Kh
a
n
et
a
l.
[
2
2
]
p
r
o
p
o
s
ed
a
m
o
d
el
ac
h
iev
in
g
1
0
0
% a
cc
u
r
ac
y
in
test
in
g
s
am
p
les,
d
em
o
n
s
tr
atin
g
h
ig
h
co
n
f
id
en
ce
in
d
iag
n
o
s
in
g
r
ice
leaf
d
is
ea
s
es f
o
r
ag
r
icu
ltu
r
al
s
u
p
p
o
r
t.
L
iu
et
a
l.
[
2
3
]
in
v
esti
g
ated
r
ice
b
last
,
f
alse
s
m
u
t,
an
d
b
a
cter
ial
wilt,
ex
p
an
d
in
g
th
e
d
ataset
an
d
o
p
tim
izin
g
a
n
ew
d
ee
p
-
lea
r
n
i
n
g
m
o
d
el.
I
n
itial
m
o
d
el
ac
cu
r
ac
y
is
in
s
u
f
f
icien
t,
lead
i
n
g
t
o
a
co
m
p
r
eh
en
s
iv
e
an
aly
s
is
o
f
p
ar
am
ete
r
s
(
e.
g
.
,
it
er
atio
n
tim
es,
b
atch
s
ize,
lear
n
in
g
r
ate,
an
d
o
p
tim
izatio
n
al
g
o
r
ith
m
)
.
Usi
n
g
th
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
ev
alu
ati
o
n
,
th
e
o
p
tim
ize
d
m
o
d
el
ac
h
iev
es
9
8
.
6
4
%
ac
cu
r
ac
y
,
ef
f
e
ctiv
ely
id
en
tify
i
n
g
d
is
ea
s
es.
Dix
it
et
a
l.
[
2
4
]
p
r
o
p
o
s
ed
a
h
y
b
r
id
m
o
d
el,
d
is
tu
r
b
an
ce
s
to
r
m
tim
e
(
DST)
,
co
m
b
in
i
n
g
d
ilated
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
(
DC
NN)
,
SVM,
an
d
tr
a
n
s
f
er
lear
n
in
g
to
d
etec
t
r
ice
p
lan
t
d
is
ea
s
e.
T
h
e
DST
m
o
d
el
attain
s
9
5
%
tr
ain
in
g
an
d
8
5
%
v
alid
atio
n
ac
cu
r
ac
y
,
o
f
f
er
in
g
co
n
s
is
ten
t
r
esu
lts
ac
r
o
s
s
m
u
ltip
le
d
atasets
.
Pan
d
i
et
a
l.
[
2
5
]
s
tu
d
ied
p
lan
t
leaf
d
is
ea
s
e
d
etec
tio
n
u
s
in
g
d
ee
p
lear
n
in
g
an
d
d
ev
elo
p
ed
a
DC
NN
wi
th
g
lo
b
al
av
er
ag
e
p
o
o
lin
g
(
GAP)
t
o
ad
d
r
ess
co
m
p
u
tatio
n
al
ch
allen
g
es
.
Hasan
et
a
l.
[
2
6
]
d
ev
elo
p
ed
a
DC
NN
with
GAP
th
at
o
u
tp
e
r
f
o
r
m
s
class
ic
C
NN
with
a
5
.
4
9
%
im
p
r
o
v
em
en
t
i
n
tr
ain
in
g
ac
c
u
r
ac
y
,
s
h
o
wca
s
in
g
ef
f
ec
tiv
en
ess
in
class
if
y
in
g
b
ac
ter
ial
b
lig
h
t,
b
last
,
b
r
o
wn
s
p
o
t,
a
n
d
T
u
n
g
r
o
.
Ou
r
s
tu
d
y
in
v
esti
g
ates
th
e
in
f
lu
en
ce
o
f
d
ata
au
g
m
en
tatio
n
,
em
p
lo
y
in
g
zo
o
m
,
co
n
tr
ast
ad
ju
s
tm
en
t,
r
o
tatio
n
,
an
d
f
lip
tech
n
iq
u
es,
o
n
au
g
m
en
tin
g
th
e
ac
cu
r
ac
y
o
f
d
is
ea
s
e
clas
s
if
icatio
n
m
o
d
els
in
r
ice
p
lan
ts
.
W
h
ile
p
r
ev
io
u
s
r
esear
ch
h
as
ex
am
in
ed
th
e
b
r
o
ad
ef
f
ec
ts
o
f
d
ata
au
g
m
e
n
tatio
n
o
n
a
s
p
ec
ts
lik
e
o
v
er
all
ac
cu
r
ac
y
an
d
m
o
d
el
r
o
b
u
s
tn
e
s
s
,
it
h
a
s
n
o
t
ex
p
licitly
an
aly
ze
d
th
e
p
er
f
o
r
m
an
ce
o
f
in
d
iv
id
u
al
au
g
m
en
tatio
n
m
eth
o
d
s
.
C
o
n
s
eq
u
en
tly
,
th
e
r
e
is
a
r
esear
ch
g
ap
co
n
ce
r
n
in
g
th
e
d
is
tin
ct
co
n
tr
ib
u
ti
o
n
s
o
f
ea
ch
d
ata
au
g
m
en
tatio
n
tech
n
iq
u
e
to
wa
r
d
en
h
an
ci
n
g
ac
cu
r
ac
y
.
B
r
id
g
in
g
th
is
g
ap
co
u
l
d
y
ield
v
al
u
ab
le
in
s
ig
h
ts
in
to
r
ef
in
in
g
a
u
g
m
e
n
tatio
n
s
tr
ateg
i
es f
o
r
m
o
r
e
ef
f
icien
t
d
is
ea
s
e
m
an
ag
em
en
t i
n
r
ice
cu
ltiv
atio
n
.
T
h
is
p
ap
er
is
d
iv
id
e
d
in
to
s
ev
er
al
s
ec
tio
n
s
,
ea
ch
s
er
v
in
g
a
d
is
tin
ct
p
u
r
p
o
s
e.
T
h
e
in
t
r
o
d
u
ctio
n
p
r
o
v
id
es
a
n
o
v
er
v
iew
o
f
t
h
e
t
o
p
ic
an
d
o
u
tlin
es
th
e
m
o
tiv
atio
n
f
o
r
th
e
s
tu
d
y
.
Fu
r
th
e
r
m
o
r
e,
Sectio
n
2
d
escr
ib
es
th
e
m
eth
o
d
o
lo
g
y
o
r
ap
p
r
o
ac
h
u
s
ed
in
o
u
r
r
esear
ch
.
T
h
e
f
o
llo
win
g
s
ec
tio
n
p
r
esen
ts
th
e
r
esu
lts
,
d
is
cu
s
s
io
n
,
an
d
co
m
p
r
eh
e
n
s
iv
e
an
aly
s
is
an
d
i
n
ter
p
r
etatio
n
.
T
h
e
s
ec
tio
n
in
c
o
r
p
o
r
ates
tab
les,
g
r
ap
h
s
,
o
r
f
i
g
u
r
es
th
at
f
ac
ilit
ate
co
m
p
ar
is
o
n
s
with
p
r
e
v
io
u
s
s
tu
d
ies
o
r
t
h
eo
r
etica
l
f
r
am
e
wo
r
k
s
to
en
h
a
n
ce
t
h
e
d
is
cu
s
s
io
n
.
L
astl
y
,
th
e
co
n
clu
s
io
n
s
u
m
m
a
r
izes th
e
k
e
y
r
esu
lts
an
d
d
is
cu
s
s
es th
eir
im
p
licatio
n
s
.
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
Op
timiz
in
g
r
ice
lea
f d
is
ea
s
e
cla
s
s
ifica
tio
n
th
r
o
u
g
h
co
n
vo
lu
ti
o
n
a
l n
e
u
r
a
l n
etw
o
r
k
…
(
Mo
h
a
ma
d
F
ir
d
a
u
s
)
3431
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
T
h
e
r
ice
leaf
d
is
ea
s
e
d
ataset
[
2
7
]
was
s
o
u
r
ce
d
f
r
o
m
th
e
Kag
g
le
r
e
p
o
s
ito
r
y
.
T
h
e
d
ataset
co
m
p
r
is
ed
6
,
0
3
4
im
ag
es
m
eticu
l
o
u
s
ly
p
ar
titi
o
n
ed
i
n
to
th
r
ee
s
u
b
s
e
ts
(
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
in
g
d
ata)
.
I
t
en
co
m
p
ass
es
f
iv
e
d
is
tin
ct
ca
teg
o
r
ies:
B
ac
ter
ial
leaf
b
lig
h
t,
b
r
o
wn
s
p
o
t,
b
last
,
tu
n
g
r
o
,
an
d
n
o
r
m
al
,
as
s
h
o
wn
in
Fig
u
r
e
1
.
B
ased
o
n
a
s
tu
d
y
[
2
8
]
,
b
ac
ter
ial
leaf
b
lig
h
t
,
as
in
Fig
u
r
e
1
(
a)
ca
u
s
es
wate
r
-
s
o
ak
ed
lesi
o
n
s
o
n
leav
es
th
at
tu
r
n
y
ello
wis
h
an
d
b
r
o
w
n
.
Mo
r
eo
v
er
,
th
e
b
r
o
wn
s
p
o
t
,
s
h
o
wn
in
Fig
u
r
e
1
(
b
)
ap
p
ea
r
s
as
s
m
all,
d
ar
k
-
b
r
o
wn
lesi
o
n
s
with
a
y
ello
wis
h
h
alo
o
n
th
e
leav
es.
T
h
er
e
f
o
r
e,
b
last
lik
e
in
Fig
u
r
e
1
(
c
)
f
ea
tu
r
es
a
r
e
s
p
in
d
le
-
s
h
ap
e
d
o
r
d
iam
o
n
d
-
s
h
ap
ed
leaf
lesi
o
n
s
.
T
u
n
g
r
o
d
is
ea
s
e
in
Fig
u
r
e
1
(
d
)
[
2
8
]
lead
s
to
s
tu
n
ted
g
r
o
wth
,
y
ello
win
g
o
f
leav
es
,
an
d
r
ed
u
ce
d
till
er
in
g
.
“
No
r
m
a
l
”
in
Fig
u
r
e
1
(
e
)
r
ef
e
r
s
to
h
ea
lth
y
,
d
is
ea
s
e
-
f
r
ee
r
ice
p
lan
ts
ex
h
ib
itin
g
v
ig
o
r
o
u
s
g
r
o
wth
an
d
p
r
o
d
u
ci
n
g
a
g
o
o
d
y
ield
o
f
g
r
ain
s
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
1
.
T
h
e
r
ice
p
la
n
t
d
is
ea
s
e
in
(
a)
b
ac
ter
ial
leaf
b
lig
h
t,
(
b
)
b
r
o
wn
s
p
o
t,
(
c
)
b
last
,
(
d
)
tu
n
g
r
o
,
an
d
(
e)
n
o
r
m
al
Acc
o
r
d
in
g
to
C
aa
s
i
et
a
l.
[
2
9
]
,
ex
ten
s
iv
e
f
ield
ass
e
s
s
m
en
ts
co
n
d
u
cte
d
in
I
n
d
o
n
esia
h
av
e
h
ig
h
lig
h
ted
th
e
f
o
u
r
m
o
s
t
p
r
ev
ale
n
t
r
ice
d
is
ea
s
es
th
at
s
ig
n
if
ican
tly
im
p
ac
t
cr
o
p
y
ield
s
.
T
h
e
f
ir
s
t
b
l
ast
is
ca
u
s
ed
b
y
th
e
f
u
n
g
u
s
P
yricu
la
r
ia
o
r
yza
e
,
wh
ich
is
n
o
to
r
io
u
s
f
o
r
in
f
lictin
g
s
ev
er
e
d
am
ag
e
a
n
d
lead
i
n
g
to
s
u
b
s
tan
tial
y
ield
lo
s
s
es.
T
h
e
s
ec
o
n
d
is
b
r
o
wn
s
p
o
t
,
a
d
is
ea
s
e
attr
ib
u
ted
to
th
e
f
u
n
g
u
s
C
o
ch
lio
b
o
lu
s
miya
b
e
a
n
u
s
,
d
is
tin
g
u
is
h
ed
b
y
th
e
ap
p
ea
r
a
n
ce
o
f
b
r
o
wn
lesi
o
n
s
o
n
th
e
r
ice
leav
es,
u
ltima
tely
wea
k
en
in
g
th
e
p
lan
t
an
d
r
ed
u
cin
g
p
r
o
d
u
ctiv
ity
.
T
h
e
th
i
r
d
m
ajo
r
th
r
ea
t
is
tu
n
g
r
o
,
a
v
ir
al
d
is
ea
s
e
tr
an
s
m
itted
b
y
g
r
ee
n
leaf
h
o
p
p
er
s
in
r
ice.
T
h
is
d
is
ea
s
e
is
p
ar
ticu
lar
ly
d
etr
im
en
tal
as
it
r
esu
lts
in
leaf
y
ello
win
g
,
s
tu
n
ted
g
r
o
wth
,
ab
n
o
r
m
al
p
o
d
d
e
v
elo
p
m
e
n
t,
an
d
a
m
ar
k
e
d
r
e
d
u
ctio
n
in
y
i
eld
.
L
astl
y
,
b
ac
ter
ial
leaf
b
lig
h
t
,
ca
u
s
ed
b
y
th
e
p
ath
o
g
en
X
a
n
th
o
mo
n
a
s
o
r
yza
e
,
m
an
if
ests
th
r
o
u
g
h
wate
r
-
s
o
ak
ed
s
p
o
ts
th
at
s
p
r
ea
d
alo
n
g
th
e
leaf
v
ein
s
,
co
m
p
r
o
m
is
in
g
th
e
p
lan
t
’
s
s
tr
u
ctu
r
al
in
teg
r
ity
an
d
v
itality
.
T
h
ese
d
is
ea
s
es
p
o
s
e
s
ig
n
if
ican
t
ch
allen
g
es
to
r
ice
cu
ltiv
atio
n
an
d
n
ec
ess
itate
v
ig
ilan
t
m
o
n
ito
r
in
g
an
d
m
a
n
ag
em
en
t
to
m
itig
ate
th
eir
im
p
ac
t
o
n
a
g
r
icu
ltu
r
al
o
u
tp
u
t.
T
h
e
im
p
o
r
tan
ce
o
f
m
an
ag
i
n
g
th
ese
d
is
ea
s
es
is
u
n
d
er
s
co
r
ed
b
y
Azz
am
et
a
l.
[
2
8
]
,
w
h
o
h
i
g
h
lig
h
ted
th
e
r
ec
en
t
a
d
v
an
ce
m
e
n
ts
in
b
r
ee
d
i
n
g
r
ice
v
ar
ieties
r
esis
tan
t
to
tu
n
g
r
o
,
a
d
d
r
ess
in
g
a
cr
itical
n
ee
d
f
o
r
c
o
n
tr
o
l
m
ea
s
u
r
es
in
tr
o
p
ical
Asi
a,
wh
er
e
s
u
ch
v
ir
al
d
is
ea
s
es
ar
e
p
ar
ticu
lar
ly
d
estru
ctiv
e.
I
n
b
r
ief
,
T
ab
le
1
d
e
p
icts
f
iv
e
tar
g
et
class
if
icatio
n
class
es
with
th
eir
r
esp
ec
tiv
e
d
ataset
q
u
an
titi
es.
T
h
e
d
ataset
in
clu
d
es
4
7
9
im
ag
e
d
ata
f
o
r
b
ac
ter
ial
leaf
b
lig
h
t,
1
,
0
8
8
f
o
r
tu
n
g
r
o
,
1
,
7
6
4
f
o
r
n
o
r
m
al,
9
6
5
f
o
r
b
r
o
wn
s
p
o
t,
an
d
1
,
7
3
8
f
o
r
b
last
.
T
h
e
s
elec
tio
n
o
f
th
e
n
u
m
b
er
a
n
d
ty
p
es
o
f
r
ice
lea
f
d
is
ea
s
es
is
b
ased
o
n
r
ec
en
t
s
t
u
d
ies
th
at
ass
e
s
s
th
e
p
r
ev
alen
ce
an
d
im
p
ac
t
o
f
th
ese
d
is
ea
s
es
in
I
n
d
o
n
esia
an
d
So
u
th
ea
s
t A
s
ia.
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
4
2
9
-
3
4
3
8
3432
T
ab
le
1
.
Deta
il o
f
d
ataset
C
l
a
s
s Nam
e
To
t
a
l
N
u
m
b
e
r
o
f
I
mag
e
s
B
a
c
t
e
r
i
a
l
l
e
a
f
b
l
i
g
h
t
4
7
9
Tu
n
g
r
o
1
,
0
8
8
N
o
r
mal
1
,
7
6
4
B
r
o
w
n
s
p
o
t
9
6
5
B
l
a
s
t
1
,
7
3
8
T
o
t
a
l
6
,
0
3
4
2.
2
.
Da
t
a
a
ug
m
ent
a
t
io
n
A
p
iv
o
tal
s
tag
e
in
v
o
lv
ed
ex
p
er
im
en
tatio
n
with
d
iv
er
s
e
d
at
a
au
g
m
en
tatio
n
tech
n
iq
u
es.
T
h
e
s
tu
d
y
ex
p
lo
r
ed
m
et
h
o
d
o
lo
g
ies
s
u
ch
as
r
an
d
o
m
zo
o
m
,
r
a
n
d
o
m
b
r
ig
h
tn
ess
,
h
o
r
izo
n
tal
f
lip
,
v
e
r
tical
f
lip
,
an
d
th
eir
v
ar
io
u
s
c
o
m
b
in
atio
n
s
to
au
g
m
en
t
th
e
d
ataset.
T
h
e
s
p
ec
if
ic
au
g
m
e
n
tatio
n
p
ar
am
eter
s
p
lay
a
p
iv
o
tal
r
o
l
e
in
en
h
a
n
cin
g
th
e
d
i
v
er
s
ity
o
f
th
e
tr
ai
n
in
g
d
ataset.
T
h
ese
p
ar
am
eter
s
a
r
e
ca
r
ef
u
lly
s
el
ec
ted
to
in
tr
o
d
u
ce
v
ar
iatio
n
s
th
at
e
n
ab
le
th
e
m
o
d
el
to
g
en
er
alize
e
f
f
ec
tiv
ely
ac
r
o
s
s
d
if
f
er
en
t
co
n
d
itio
n
s
.
T
h
e
f
ir
s
t
p
a
r
am
eter
,
zo
o
m
r
an
g
e
=
[
1
.
5
,
2
.
0
]
,
is
in
teg
r
al
f
o
r
co
n
t
r
o
llin
g
th
e
lev
el
o
f
zo
o
m
ap
p
lied
to
im
ag
es
d
u
r
in
g
tr
ain
in
g
.
T
h
is
p
ar
am
eter
allo
ws
th
e
m
o
d
el
to
lear
n
f
r
o
m
im
ag
es
a
t
v
ar
y
in
g
s
ca
les,
with
v
alu
es
b
etwe
en
1
.
5
an
d
2
.
0
,
in
d
icatin
g
th
at
th
e
i
m
ag
es
m
ay
b
e
m
a
g
n
if
ied
to
d
if
f
er
e
n
t
ex
ten
ts
.
T
h
e
s
ec
o
n
d
p
ar
am
ete
r
,
b
r
ig
h
tn
ess
r
an
g
e
=
[
1
.
2
,
2
.
0
]
,
is
cr
u
cial
f
o
r
ad
ju
s
tin
g
t
h
e
b
r
ig
h
tn
ess
o
f
im
ag
es
with
in
a
s
p
e
cif
ied
r
an
g
e.
T
h
e
p
ar
am
eter
in
tr
o
d
u
ce
s
v
ar
iab
ili
ty
in
b
r
ig
h
tn
ess
lev
els
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
T
h
e
th
ir
d
s
et
o
f
p
ar
am
eter
s
,
v
er
tical
f
lip
=
tr
u
e
an
d
h
o
r
izo
n
t
al
f
lip
=
tr
u
e,
co
n
tr
ib
u
tes
to
th
e
au
g
m
en
tatio
n
m
eth
o
d
o
lo
g
y
b
y
allo
win
g
th
e
m
o
d
el
to
lear
n
f
r
o
m
v
er
tically
an
d
h
o
r
izo
n
tally
f
lip
p
e
d
v
er
s
io
n
s
o
f
th
e
im
ag
es.
T
h
e
a
u
g
m
e
n
ted
d
ata
ca
n
aid
in
im
p
r
o
v
in
g
th
e
m
o
d
el
’
s
r
o
b
u
s
t
n
ess
to
d
if
f
er
en
t
o
r
ien
tatio
n
s
.
B
y
in
teg
r
atin
g
th
ese
a
u
g
m
en
t
atio
n
tech
n
iq
u
es
in
to
th
e
tr
ain
in
g
p
r
o
ce
s
s
,
th
e
m
eth
o
d
o
lo
g
y
ar
tific
ially
d
iv
er
s
if
ies
th
e
d
ataset,
e
x
p
o
s
in
g
th
e
m
o
d
el
to
a
b
r
o
ad
e
r
r
an
g
e
o
f
s
ce
n
ar
i
o
s
.
T
h
is
a
p
p
r
o
ac
h
e
n
h
an
ce
s
th
e
m
o
d
el
’
s
ab
ilit
y
t
o
h
a
n
d
le
r
ea
l
-
wo
r
ld
v
ar
iatio
n
s
,
in
cl
u
d
in
g
c
h
an
g
es
in
s
ca
le,
lig
h
tin
g
co
n
d
itio
n
s
,
an
d
im
ag
e
o
r
ien
tatio
n
s
.
T
h
e
m
eth
o
d
o
lo
g
y
,
r
o
o
ted
i
n
th
e
ju
d
icio
u
s
a
p
p
li
ca
tio
n
o
f
au
g
m
en
tatio
n
p
ar
am
eter
s
,
aim
s
to
f
o
s
ter
a
m
o
r
e
r
esil
ien
t
an
d
ad
ap
tab
l
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
f
o
r
p
r
ac
tical
a
p
p
licatio
n
s
,
p
a
r
ticu
lar
ly
in
co
m
p
u
ter
v
is
io
n
task
s
.
Fig
u
r
e
2
illu
s
tr
ates
th
e
s
am
p
l
e
im
ag
es
p
r
o
d
u
ce
d
b
y
th
e
a
u
g
m
en
tatio
n
tec
h
n
iq
u
es
e
m
p
lo
y
ed
in
th
is
s
tu
d
y
.
Fig
u
r
e
2
(
a
)
in
d
icat
es
a
n
o
r
ig
i
n
al
im
ag
e
f
r
o
m
th
e
d
at
aset.
Fig
u
r
e
2
(
b
)
r
esu
lts
f
r
o
m
au
g
m
en
tatio
n
u
s
in
g
th
e
r
an
d
o
m
z
o
o
m
tech
n
i
q
u
e.
Fig
u
r
e
2
(
c)
r
esu
lts
f
r
o
m
au
g
m
en
tatio
n
u
s
in
g
th
e
r
an
d
o
m
b
r
ig
h
tn
ess
tech
n
iq
u
e.
Fig
u
r
e
2
(
d
)
is
g
en
er
ated
f
r
o
m
th
e
v
er
tical
f
lip
au
g
m
en
tatio
n
tech
n
iq
u
e.
Fin
ally
,
Fig
u
r
e
3
(
e
)
is
g
en
er
ated
u
s
in
g
th
e
h
o
r
izo
n
tal
f
lip
au
g
m
en
tati
o
n
tech
n
i
q
u
e.
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
2
.
T
h
e
s
am
p
le
o
f
(
a)
o
r
ig
in
al
im
ag
e
an
d
au
g
m
en
ted
i
m
ag
es
wh
ich
ar
e
(
b
)
r
a
n
d
o
m
z
o
o
m
,
(
c
)
r
an
d
o
m
b
r
ig
h
tn
ess
,
(
d
)
v
er
tical
f
lip
,
an
d
(
e)
h
o
r
izo
n
tal
f
lip
2.
3
.
E
x
perim
ent
s
ce
na
rio
T
h
e
r
esear
ch
er
s
em
p
lo
y
e
d
two
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
ar
ch
itectu
r
es
in
th
e
ex
p
er
im
en
t
to
s
tu
d
y
r
ice
leaf
d
is
ea
s
e
class
if
icatio
n
.
T
h
e
f
ir
s
t
ar
ch
itectu
r
e
is
ca
lled
“
v
an
illa
R
esNet5
0
,
”
an
d
t
h
e
s
ec
o
n
d
is
lab
eled
“
R
esNet5
0
-
ML
P.
”
T
h
e
ter
m
“
v
an
illa
”
im
p
lies
th
at
it
is
th
e
s
tan
d
ar
d
o
r
o
r
i
g
in
al
v
er
s
io
n
o
f
th
e
R
esNet5
0
ar
ch
itectu
r
e
with
o
u
t
ad
d
itio
n
al
m
o
d
if
icatio
n
s
o
r
co
m
p
o
n
en
ts
.
Fig
u
r
e
3
d
ep
icts
th
e
v
is
u
al
r
ep
r
esen
tatio
n
o
r
d
iag
r
a
m
o
f
th
e
v
an
illa
R
esNet5
0
ar
ch
itectu
r
e,
s
h
o
wca
s
in
g
th
e
C
NN
m
o
d
el
’
s
lay
er
s
,
co
n
n
ec
tio
n
s
,
an
d
o
v
er
all
s
tr
u
c
tu
r
e.
R
esNet5
0
is
a
s
p
ec
if
ic
v
ar
ian
t
o
f
th
e
R
esNet
ar
ch
itectu
r
e
th
at
c
o
n
s
is
ts
o
f
5
0
lay
er
s
an
d
is
k
n
o
w
n
f
o
r
its
ef
f
ec
tiv
en
ess
in
im
ag
e
class
if
icatio
n
task
s
.
On
th
e
o
th
er
h
a
n
d
,
Fig
u
r
e
4
illu
s
tr
ates
th
e
R
es
Net5
0
-
ML
P
ar
ch
itectu
r
e.
“
MLP
”
in
th
e
n
am
e
in
d
icate
s
th
at
th
is
ar
ch
itectu
r
e
in
co
r
p
o
r
ates
a
n
ML
P
co
m
p
o
n
en
t
alo
n
g
with
th
e
s
tan
d
ar
d
R
esNet5
0
s
tr
u
ctu
r
e.
ML
P
is
an
ar
tific
ial
n
eu
r
al
n
etwo
r
k
with
m
u
ltip
le
lay
er
s
,
o
f
t
en
u
s
ed
to
en
h
a
n
ce
th
e
m
o
d
el
’
s
ab
ilit
y
to
ca
p
tu
r
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
Op
timiz
in
g
r
ice
lea
f d
is
ea
s
e
cla
s
s
ifica
tio
n
th
r
o
u
g
h
co
n
vo
lu
ti
o
n
a
l n
e
u
r
a
l n
etw
o
r
k
…
(
Mo
h
a
ma
d
F
ir
d
a
u
s
)
3433
co
m
p
lex
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
in
d
ata.
B
y
u
tili
zin
g
b
o
th
v
a
n
illa
R
esNet5
0
a
n
d
R
esNet5
0
-
ML
P
ar
ch
itectu
r
es,
th
e
r
esear
ch
er
s
aim
to
co
m
p
ar
e
a
n
d
e
v
alu
ate
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
ese
m
o
d
e
ls
in
th
e
co
n
te
x
t
o
f
class
if
y
in
g
r
ice
leaf
d
is
ea
s
es.
I
t
allo
ws
th
em
to
a
n
aly
ze
t
h
e
im
p
ac
t
o
f
ad
d
in
g
a
n
ML
P
co
m
p
o
n
e
n
t
to
th
e
s
tan
d
ar
d
R
esNet5
0
ar
ch
itectu
r
e
o
n
th
e
ac
c
u
r
ac
y
a
n
d
e
f
f
ec
tiv
en
ess
o
f
d
is
ea
s
e
class
if
icatio
n
.
Fig
u
r
e
3
.
Ar
c
h
itectu
r
e
o
f
R
esNet5
0
Fig
u
r
e
4
.
Ar
c
h
itectu
r
e
o
f
R
esNet5
0
-
MLP
T
h
e
p
r
o
v
id
ed
tab
le
u
n
v
eils
a
co
m
p
r
eh
e
n
s
iv
e
s
er
ies
o
f
ex
p
er
im
en
tal
s
ce
n
ar
io
s
;
ea
ch
in
tr
icate
ly
en
twin
ed
with
d
is
tin
ctiv
e
ar
c
h
itectu
r
al
co
n
f
ig
u
r
atio
n
s
an
d
au
g
m
en
tatio
n
tech
n
i
q
u
es
ap
p
l
ied
to
a
R
esNet5
0
lay
er
m
o
d
el.
T
h
ese
s
ce
n
ar
io
s
,
d
en
o
ted
b
y
lab
els
S1
to
S
8
,
en
co
m
p
ass
a
r
ig
o
r
o
u
s
ex
p
lo
r
atio
n
s
ee
k
in
g
t
o
o
p
tim
ize
th
e
class
if
icatio
n
o
f
r
ice
p
lan
t
d
is
ea
s
es,
a
s
s
h
o
w
n
in
T
ab
le
2
.
E
ac
h
ex
p
er
im
e
n
tal
s
ce
n
ar
io
test
s
v
ar
io
u
s
co
m
b
in
atio
n
s
o
f
ar
ch
itectu
r
e
co
n
f
ig
u
r
atio
n
s
an
d
a
u
g
m
en
tatio
n
tech
n
i
q
u
es
o
n
t
h
e
R
esNet5
0
lay
er
m
o
d
el.
T
h
e
n
u
m
b
er
in
g
o
f
s
ce
n
ar
io
s
f
r
o
m
S1
to
S8
r
ef
l
ec
ts
a
m
eticu
lo
u
s
ex
p
lo
r
atio
n
to
o
p
tim
ize
th
e
class
if
icatio
n
o
f
r
ice
p
lan
t
d
is
ea
s
es.
An
aly
zin
g
th
e
r
esu
lts
o
f
ea
ch
s
ce
n
ar
io
will
p
r
o
v
id
e
v
alu
ab
le
in
s
ig
h
ts
f
o
r
d
ev
elo
p
in
g
m
o
r
e
ef
f
ec
tiv
e
m
o
d
els f
o
r
ad
d
r
ess
in
g
r
ice
p
lan
t
h
ea
lth
is
s
u
es.
T
ab
le
2
.
T
h
e
ex
p
e
r
im
en
t scen
ar
io
s
A
r
c
h
i
t
e
c
t
u
r
e
S
c
e
n
a
r
i
o
R
e
sN
e
t
5
0
l
a
y
e
r
s
S1
R
e
sN
e
t
5
0
l
a
y
e
r
s
+
r
a
n
d
o
m z
o
o
m
S2
R
e
sN
e
t
5
0
l
a
y
e
r
s
–
M
LP
S3
R
e
sN
e
t
5
0
l
a
y
e
r
s
–
M
LP +
r
a
n
d
o
m
z
o
o
m
S4
R
e
sN
e
t
5
0
l
a
y
e
r
s
–
M
LP +
r
a
n
d
o
m
b
r
i
g
h
t
n
e
ss
S5
R
e
sN
e
t
5
0
l
a
y
e
r
s
–
M
LP +
h
o
r
i
z
o
n
t
a
l
f
l
i
p
S6
R
e
sN
e
t
5
0
l
a
y
e
r
s
–
M
LP +
v
e
r
t
i
c
a
l
f
l
i
p
S7
R
e
sN
e
t
5
0
l
a
y
e
r
s
–
M
LP +
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
(
r
a
n
d
o
m
z
o
o
m,
r
a
n
d
o
m
b
r
i
g
h
t
n
e
ss,
v
e
r
t
i
c
a
l
f
l
i
p
,
h
o
r
i
z
o
n
t
a
l
f
l
i
p
)
S8
I
n
Scen
ar
io
1
(
S1
)
,
t
h
e
s
tu
d
y
in
itiates
b
y
em
p
lo
y
in
g
th
e
R
esNet5
0
lay
er
ar
ch
itectu
r
e,
estab
lis
h
in
g
a
f
u
n
d
am
e
n
tal
b
en
c
h
m
ar
k
to
c
o
m
p
r
eh
e
n
d
th
e
m
o
d
el
’
s
b
aselin
e
p
er
f
o
r
m
an
ce
in
d
is
ea
s
e
class
if
icatio
n
.
T
h
e
R
esNet5
0
h
as
p
r
o
v
en
to
b
e
r
o
b
u
s
t
an
d
wid
ely
u
s
ed
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
ar
c
h
itectu
r
e
in
v
ar
i
o
u
s
co
m
p
u
ter
v
is
io
n
task
s
,
in
clu
d
in
g
im
ag
e
class
if
icatio
n
.
I
ts
d
ee
p
s
tr
u
ctu
r
e,
f
ea
tu
r
in
g
s
k
ip
o
r
r
esid
u
al
co
n
n
ec
tio
n
s
,
en
ab
les
p
r
ac
tical
tr
ain
in
g
o
f
d
ee
p
n
etwo
r
k
s
w
h
ile
m
itig
atin
g
th
e
v
an
is
h
in
g
g
r
ad
ien
t
p
r
o
b
lem
.
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
4
2
9
-
3
4
3
8
3434
T
h
e
R
esNet5
0
ar
ch
itectu
r
e
also
b
alan
ce
s
m
o
d
el
c
o
m
p
lex
ity
an
d
co
m
p
u
tatio
n
al
ef
f
icie
n
cy
,
m
ak
in
g
it
s
u
itab
le
f
o
r
ap
p
licatio
n
s
with
lim
ited
c
o
m
p
u
tatio
n
al
r
eso
u
r
ce
s
.
Scen
ar
io
2
(
S2
)
ex
ten
d
s
th
e
R
esNet5
0
lay
er
a
r
ch
itectu
r
e
b
y
in
teg
r
atin
g
r
an
d
o
m
z
o
o
m
au
g
m
en
tatio
n
,
aim
in
g
to
ass
ess
th
e
im
p
ac
t
o
f
th
is
tech
n
iq
u
e
o
n
th
e
m
o
d
el
’
s
d
is
ea
s
e
class
if
icatio
n
ac
cu
r
ac
y
.
C
o
n
v
er
s
ely
,
Scen
ar
io
3
(
S3
)
ex
p
er
im
en
ts
b
y
ex
clu
d
i
n
g
th
e
ML
P
co
m
p
o
n
en
t
f
r
o
m
th
e
a
r
ch
itectu
r
e,
p
r
o
b
in
g
th
e
ef
f
ec
ts
o
f
th
is
alter
atio
n
o
n
d
is
ea
s
e
cla
s
s
if
icatio
n
p
er
f
o
r
m
a
n
ce
.
Fu
r
th
er
n
u
an
ce
d
in
v
esti
g
atio
n
s
u
n
f
o
ld
in
Scen
ar
io
s
4
(
S4
)
th
r
o
u
g
h
7
(
S7
)
.
E
ac
h
s
ce
n
ar
io
ex
am
in
es th
e
is
o
lated
ef
f
ec
ts
o
f
s
p
ec
if
ic
au
g
m
en
tatio
n
tech
n
iq
u
es:
r
an
d
o
m
zo
o
m
,
r
a
n
d
o
m
b
r
ig
h
t
n
ess
,
h
o
r
izo
n
tal
f
lip
,
a
n
d
v
er
tical
f
l
ip
.
T
h
ese
tech
n
iq
u
es
ar
e
a
p
p
lied
alo
n
g
s
id
e
th
e
R
esNet5
0
lay
er
ar
ch
itectu
r
e
with
th
e
ML
P
co
m
p
o
n
en
t.
T
h
e
aim
o
f
th
ese
s
ce
n
ar
io
s
is
to
d
i
s
ce
r
n
th
e
in
d
iv
id
u
al
in
f
lu
en
ce
s
o
f
th
ese
au
g
m
e
n
tatio
n
m
eth
o
d
s
o
n
th
e
m
o
d
el
’
s
c
lass
if
icatio
n
ac
cu
r
ac
y
an
d
ef
f
i
ca
cy
.
T
h
is
an
aly
s
is
f
ac
ilit
ates u
n
d
er
s
tan
d
in
g
th
e
o
p
tim
al
co
m
b
in
atio
n
o
f
au
g
m
e
n
tatio
n
s
f
o
r
im
p
r
o
v
ed
p
e
r
f
o
r
m
an
ce
.
Scen
ar
io
8
(
S8
)
ex
p
lo
r
es
co
m
p
r
eh
en
s
iv
ely
b
y
a
m
alg
am
at
in
g
m
u
ltip
le
au
g
m
en
tatio
n
te
ch
n
iq
u
es:
r
an
d
o
m
zo
o
m
,
r
a
n
d
o
m
b
r
i
g
h
t
n
ess
,
v
er
tical
f
lip
,
a
n
d
h
o
r
iz
o
n
tal
f
lip
with
t
h
e
R
esNet5
0
lay
er
ar
c
h
itectu
r
e,
ex
clu
d
in
g
th
e
ML
P
co
m
p
o
n
en
t.
T
h
is
co
m
p
r
eh
en
s
iv
e
s
ce
n
ar
io
aim
s
to
e
v
alu
ate
th
e
c
o
llectiv
e
im
p
ac
t
o
f
d
iv
er
s
e
au
g
m
e
n
tatio
n
s
tr
ateg
ie
s
o
n
th
e
m
o
d
el
’
s
d
is
ea
s
e
class
i
f
icatio
n
ca
p
ab
ilit
ies.
T
h
is
co
m
p
r
e
h
en
s
iv
e
b
r
ea
k
d
o
wn
co
r
r
elate
s
s
p
ec
if
ic
ar
ch
itectu
r
al
s
etu
p
s
an
d
au
g
m
en
tatio
n
ap
p
r
o
ac
h
es
with
th
eir
r
esp
e
ctiv
e
ex
p
er
im
e
n
tal
s
ce
n
ar
io
s
.
I
t
f
ac
ilit
ates
a
d
etailed
ex
am
in
atio
n
o
f
th
eir
s
ep
ar
ate
an
d
co
m
b
i
n
ed
im
p
ac
t
s
o
n
th
e
m
o
d
el
’
s
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es
an
d
co
m
p
u
tatio
n
al
e
f
f
ec
tiv
en
ess
.
E
ac
h
s
ce
n
ar
io
r
ep
r
esen
ts
a
d
is
tin
ctiv
e
co
m
b
i
n
atio
n
o
f
ar
ch
itec
tu
r
al
ad
ju
s
tm
en
ts
a
n
d
a
u
g
m
en
tatio
n
m
eth
o
d
s
,
en
r
ich
in
g
o
u
r
co
m
p
r
eh
e
n
s
io
n
o
f
h
o
w
th
ese
ch
a
n
g
es
in
f
l
u
en
ce
th
e
m
o
d
el
’
s
ab
ilit
y
t
o
class
if
y
d
is
ea
s
es
in
r
ice
p
lan
t
im
ag
es.
Su
ch
n
u
a
n
ce
d
i
n
s
ig
h
ts
ar
e
ess
en
tial
f
o
r
p
r
o
g
r
es
s
in
g
ag
r
icu
ltu
r
al
tech
n
o
l
o
g
y
a
n
d
en
h
an
cin
g
cr
o
p
m
an
ag
em
en
t
m
eth
o
d
o
lo
g
ies.
2.
4
.
E
v
a
lua
t
io
n
T
h
e
m
o
d
el
’
s
ef
f
icac
y
was
test
ed
in
th
is
p
h
ase
b
y
p
r
esen
tin
g
n
ew,
u
n
s
ee
n
r
ice
p
lan
t
im
ag
e
d
ata
co
m
p
r
is
in
g
2
5
test
s
am
p
les.
T
h
e
ev
alu
atio
n
s
tag
e
i
n
v
o
lv
e
d
th
e
m
o
d
el
g
en
er
atin
g
o
u
tp
u
t
f
r
o
m
th
e
test
in
g
p
h
ase.
T
h
is
ass
ess
m
en
t
u
tili
ze
d
th
e
co
n
f
u
s
io
n
m
atr
ix
m
eth
o
d
,
an
aly
zi
n
g
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
m
etr
ics
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e,
b
ased
o
n
t
h
e
2
5
test
im
ag
es.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
G
rid
s
ea
rc
h f
o
r
o
ptim
izing
t
he
M
L
P
la
y
er
s
I
n
th
e
co
n
d
u
cte
d
g
r
id
s
ea
r
ch
to
o
p
tim
ize
th
e
ML
P
m
o
d
el,
d
if
f
er
en
t
co
n
f
ig
u
r
atio
n
s
o
f
M
L
P
lay
er
s
wer
e
ex
p
lo
r
ed
,
a
n
d
t
h
e
r
esu
lts
ar
e
p
r
esen
ted
in
th
e
T
ab
le
3
.
T
h
e
o
b
jectiv
e
was
to
id
en
tif
y
th
e
b
est
ar
ch
itectu
r
e
f
o
r
th
e
g
i
v
en
task
,
as
in
d
icate
d
b
y
v
a
r
io
u
s
ev
alu
atio
n
m
etr
i
cs,
in
clu
d
in
g
test
ac
cu
r
ac
y
,
F
1
-
s
co
r
e,
p
r
ec
is
io
n
,
an
d
r
ec
all
.
W
e
s
elec
ted
th
e
o
n
e
with
th
e
n
u
m
b
e
r
o
f
lay
e
r
s
3
as
it
ac
h
iev
ed
th
e
h
ig
h
est
ac
c
u
r
ac
y
,
as
s
h
o
wn
in
T
ab
le
3
.
T
ab
le
3
.
T
h
e
g
r
id
s
ea
r
ch
r
esu
lt
N
u
mb
e
r
o
f
l
a
y
e
r
s
Te
st
a
c
c
u
r
a
c
y
F1
-
S
c
o
r
e
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
1
0
.
7
2
0
.
7
1
0
.
7
8
0
.
7
2
3
0
.
9
2
0
.
9
2
0
.
9
4
0
.
9
2
5
0
.
8
8
0
.
8
8
0
.
8
9
0
.
8
8
3
.
2
.
Scena
rio
s
perf
o
rm
a
nces c
o
mp
a
riso
n
As
s
h
o
wn
in
T
a
b
le
4
,
th
e
r
esu
lts
f
r
o
m
th
e
ex
p
e
r
im
en
tal
s
ce
n
ar
io
s
(
S1
t
o
S8
)
r
ev
ea
l
a
d
iv
e
r
s
e
s
p
ec
tr
u
m
o
f
p
er
f
o
r
m
a
n
ce
m
e
tr
ics
co
n
ce
r
n
in
g
th
e
class
if
icatio
n
o
f
r
ice
p
la
n
t
d
is
ea
s
es
u
s
in
g
th
e
R
esNet5
0
lay
er
s
m
o
d
el
with
v
a
r
y
in
g
ar
ch
itectu
r
al
co
n
f
ig
u
r
atio
n
s
an
d
au
g
m
en
tatio
n
tec
h
n
iq
u
e
s
.
Scen
ar
io
4
(
S4
)
em
er
g
es
as
th
e
m
o
s
t
n
o
tab
le
p
er
f
o
r
m
er
in
th
is
ex
p
lo
r
atio
n
,
s
h
o
w
-
co
v
er
in
g
t
h
e
h
ig
h
est
ac
cu
r
ac
y
r
ate
o
f
0
.
9
2
alo
n
g
s
id
e
r
o
b
u
s
t
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
,
all
at
0
.
9
4
,
0
.
9
2
,
an
d
0
.
9
2
,
r
esp
ec
tiv
ely
.
T
h
is
s
ce
n
ar
io
,
f
ea
tu
r
in
g
th
e
R
esNet5
0
lay
er
ar
ch
itectu
r
e
with
o
u
t
th
e
ML
P
co
m
p
o
n
e
n
t
b
u
t
in
co
r
p
o
r
atin
g
r
an
d
o
m
z
o
o
m
au
g
m
en
tatio
n
,
d
em
o
n
s
tr
ates
s
u
p
er
io
r
ca
p
a
b
ilit
ies
in
ac
cu
r
ately
id
en
tify
in
g
an
d
class
if
y
in
g
r
ice
p
lan
t d
is
ea
s
es.
C
o
n
v
er
s
ely
,
s
ce
n
ar
i
o
s
em
p
lo
y
in
g
s
in
g
u
lar
au
g
m
e
n
tatio
n
tech
n
iq
u
es,
s
u
ch
as
r
an
d
o
m
z
o
o
m
(
S2
)
,
r
an
d
o
m
b
r
ig
h
t
n
ess
(
S5
)
,
h
o
r
i
zo
n
tal
f
lip
(
S6
)
,
an
d
v
er
tical
f
lip
(
S7
)
,
ex
h
ib
it
m
o
d
er
ate
p
er
f
o
r
m
an
ce
with
co
n
s
is
ten
t
ac
cu
r
ac
y
r
ates
ar
o
u
n
d
0
.
8
4
an
d
co
r
r
esp
o
n
d
in
g
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
with
in
a
s
im
ilar
r
an
g
e.
W
h
ile
ef
f
ec
tiv
e
to
a
d
e
g
r
ee
,
th
ese
s
ce
n
ar
io
s
d
em
o
n
s
tr
ate
r
elativ
ely
co
m
p
ar
a
b
le
b
u
t
m
o
d
er
ate
s
u
cc
ess
in
d
is
ea
s
e
clas
s
if
icatio
n
co
m
p
ar
ed
to
th
e
s
tan
d
o
u
t
p
er
f
o
r
m
er
.
Scen
ar
io
3
(
S3
)
,
ex
clu
d
in
g
th
e
ML
P
co
m
p
o
n
en
t
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
Op
timiz
in
g
r
ice
lea
f d
is
ea
s
e
cla
s
s
ifica
tio
n
th
r
o
u
g
h
co
n
vo
lu
ti
o
n
a
l n
e
u
r
a
l n
etw
o
r
k
…
(
Mo
h
a
ma
d
F
ir
d
a
u
s
)
3435
f
r
o
m
th
e
R
esNet5
0
lay
er
ar
c
h
itectu
r
e,
d
is
p
lay
s
a
n
o
tewo
r
th
y
im
p
r
o
v
em
en
t
i
n
p
e
r
f
o
r
m
an
c
e
co
m
p
ar
e
d
to
t
h
e
b
aselin
e
s
ce
n
ar
io
(
S1
)
,
with
an
ac
cu
r
ac
y
r
ate
o
f
0
.
8
8
.
T
h
i
s
alter
atio
n
h
ig
h
lig
h
ts
th
e
p
o
ten
tial
in
f
lu
en
ce
o
f
ar
ch
itectu
r
al
co
m
p
o
n
e
n
ts
o
n
th
e
m
o
d
el
’
s
d
is
ea
s
e
class
if
i
ca
tio
n
ca
p
ab
ilit
ies.
Scen
ar
io
8
(
S8
)
in
v
o
lv
es
a
co
m
p
r
eh
e
n
s
iv
e
am
alg
am
atio
n
o
f
m
u
ltip
le
au
g
m
en
tatio
n
tech
n
iq
u
es
with
th
e
R
esNet5
0
lay
er
ar
ch
itectu
r
e,
d
ev
o
id
o
f
th
e
ML
P
co
m
p
o
n
e
n
t,
with
a
b
alan
ce
d
ac
cu
r
ac
y
r
ate
o
f
0
.
7
6
.
W
h
ile
n
o
t
th
e
h
i
g
h
est
p
er
f
o
r
m
er
,
it
d
em
o
n
s
tr
ates
co
m
p
etitiv
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
ar
o
u
n
d
0
.
8
2
,
0
.
7
6
,
an
d
0
.
7
8
,
r
esp
ec
tiv
ely
,
in
d
icatin
g
a
r
elativ
ely
ef
f
ec
tiv
e
al
b
eit
n
o
t
th
e
m
o
s
t su
p
er
io
r
p
er
f
o
r
m
a
n
c
e.
T
ab
le
4
.
T
h
e
ex
p
e
r
im
en
t scen
ar
io
’
s
r
esu
lt
S
c
e
n
a
r
i
o
Ti
me
p
e
r
st
e
p
A
c
c
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S1
4
5
7
m
s
0
.
8
0
.
8
6
0
.
8
0
.
8
S
2
R
a
n
d
o
m
z
o
o
m
7
7
8
m
s
0
.
8
4
0
.
8
7
0
.
8
4
0
.
8
4
S
3
M
LP
4
7
7
m
s
0
.
8
8
0
.
9
0
.
8
8
0
.
8
8
S
4
M
LP
+
z
o
o
m
7
8
7
m
s
0
.
9
2
0
.
9
4
0
.
9
2
0
.
9
2
S5
5
8
9
m
s
0
.
8
4
0
.
8
8
0
.
8
4
0
.
8
2
S6
4
5
7
m
s
0
.
7
6
0
.
8
0
.
7
6
0
.
7
5
S7
9
7
5
m
s
0
.
8
4
0
.
8
8
0
.
8
4
0
.
8
5
S8
1
,
0
0
0
m
s
0
.
7
6
0
.
8
2
0
.
7
6
0
.
7
8
T
h
e
en
h
a
n
ce
d
p
e
r
f
o
r
m
an
ce
ac
h
iev
ed
b
y
ap
p
l
y
in
g
r
a
n
d
o
m
zo
o
m
d
ata
au
g
m
e
n
tatio
n
s
tan
d
s
o
u
t
co
m
p
ar
ed
t
o
alter
n
ativ
e
tech
n
iq
u
es.
T
h
is
s
u
p
er
io
r
ity
ca
n
b
e
ascr
ib
ed
to
th
e
in
cr
ea
s
ed
d
et
ail
in
tr
o
d
u
ce
d
in
t
o
th
e
im
ag
e
d
ata.
B
y
allo
win
g
f
o
r
r
an
d
o
m
v
a
r
iatio
n
s
in
zo
o
m
lev
els,
th
e
m
o
d
el
g
ain
s
ac
ce
s
s
to
a
m
o
r
e
d
iv
er
s
e
an
d
in
tr
icate
s
et
o
f
f
ea
tu
r
es,
m
ak
in
g
th
e
d
ata
m
o
r
e
in
f
o
r
m
ativ
e
an
d
co
n
d
u
ci
v
e
to
i
m
p
r
o
v
e
d
lear
n
in
g
.
A
n
o
tewo
r
th
y
asp
ec
t
co
n
tr
ib
u
tin
g
to
th
e
s
u
cc
ess
o
f
r
an
d
o
m
zo
o
m
in
g
is
th
e
p
o
ten
tial
f
o
r
ad
v
a
n
tag
eo
u
s
p
r
ec
is
io
n
.
W
h
en
th
e
au
g
m
en
t
atio
n
p
r
o
ce
s
s
h
ap
p
en
s
to
alig
n
with
th
e
in
h
er
en
t
ch
ar
ac
ter
i
s
tics
o
f
th
e
d
ata,
th
e
m
o
d
el
is
ex
p
o
s
ed
to
p
ar
ticu
la
r
ly
b
en
ef
icial
in
s
tan
ce
s
.
T
h
is
ac
cid
en
tal
alig
n
m
en
t
ca
n
lead
to
a
m
o
r
e
r
ef
in
ed
lear
n
in
g
ex
p
er
ien
ce
,
aid
in
g
t
h
e
m
o
d
el
in
h
o
n
i
n
g
its
ac
cu
r
ac
y
lev
els.
Ho
wev
er
,
it
is
cr
u
cial
to
ac
k
n
o
wled
g
e
th
at
th
e
ad
v
an
tag
es
ass
o
ciate
d
with
r
an
d
o
m
zo
o
m
m
ay
n
o
t
u
n
iv
er
s
ally
ap
p
ly
to
all
ca
s
es
o
r
s
ce
n
ar
io
s
.
T
h
e
ef
f
ec
tiv
e
n
ess
o
f
th
is
au
g
m
en
tatio
n
tech
n
i
q
u
e
d
ep
e
n
d
s
o
n
th
e
n
atu
r
e
o
f
th
e
d
ata
an
d
th
e
s
p
e
cif
ic
lear
n
in
g
task
at
h
an
d
.
As
s
u
ch
,
co
n
s
id
er
atio
n
s
s
h
o
u
ld
b
e
m
ad
e
r
eg
ar
d
i
n
g
th
e
ap
p
r
o
p
r
iaten
ess
o
f
em
p
l
o
y
in
g
r
an
d
o
m
zo
o
m
b
ased
o
n
th
e
d
ataset
’
s
c
h
ar
ac
ter
is
tics
an
d
th
e
m
o
d
el
’
s
o
b
jectiv
es.
Ov
er
all,
th
e
o
u
tco
m
es
u
n
d
er
s
co
r
e
th
e
s
ig
n
if
ican
ce
o
f
a
r
ch
itectu
r
al
co
n
f
ig
u
r
atio
n
s
a
n
d
au
g
m
en
tatio
n
tech
n
iq
u
es in
s
h
ap
in
g
th
e
R
esNet5
0
lay
er
m
o
d
el
’
s
p
r
o
f
icien
cy
i
n
class
if
y
in
g
r
ice
p
lan
t d
is
ea
s
es.
Scen
ar
io
4
(
S4
)
n
o
tab
ly
s
tan
d
s
o
u
t
as
th
e
m
o
s
t
ef
f
ec
tiv
e
c
o
n
f
ig
u
r
atio
n
,
em
p
h
asizin
g
th
e
p
o
ten
tial
im
p
ac
t
o
f
r
an
d
o
m
zo
o
m
au
g
m
en
tatio
n
o
n
en
h
a
n
cin
g
t
h
e
m
o
d
el
’
s
ac
cu
r
ac
y
a
n
d
o
v
er
all
d
is
ea
s
e
class
if
icatio
n
ca
p
ab
ilit
ies.
T
ab
le
5
s
h
o
ws
th
e
co
m
p
ar
is
o
n
o
f
p
er
f
o
r
m
a
n
ce
m
etr
ics
f
o
r
d
if
f
er
e
n
t
m
eth
o
d
s
in
r
ice
leaf
d
is
ea
s
e
class
if
icatio
n
.
Do
g
r
a
et
a
l
.
[
2
0
]
with
th
eir
VGG1
9
m
o
d
el
with
tr
an
s
f
er
lear
n
in
g
ac
h
iev
ed
an
ac
c
u
r
ac
y
o
f
9
3
.
0
%,
w
h
ile
Dix
it
an
d
Ver
m
a
[
2
4
]
r
e
p
o
r
ted
a
s
lig
h
tly
lo
w
er
ac
cu
r
ac
y
o
f
8
5
%
f
o
r
DST
.
On
th
e
o
th
er
h
an
d
,
DC
NN
with
GAP
b
y
Pan
d
i
et
a
l.
[
2
5
]
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
am
o
n
g
th
e
r
ef
er
en
ce
d
s
tu
d
ies,
with
9
6
.
5
%.
I
n
co
n
tr
ast,
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
,
in
tr
o
d
u
ce
d
in
2
0
2
4
,
attain
ed
an
ac
cu
r
ac
y
o
f
9
2
%.
W
h
ile
D
C
NN
with
GAP
[
2
5
]
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
,
o
u
r
m
eth
o
d
d
em
o
n
s
tr
ates
co
m
p
etitiv
e
p
er
f
o
r
m
a
n
ce
,
f
allin
g
s
lig
h
tly
b
eh
in
d
b
u
t sti
ll m
ain
tain
in
g
a
h
i
g
h
lev
el
o
f
ac
cu
r
ac
y
in
r
ice
leaf
d
is
ea
s
e
class
if
icati
o
n
.
T
ab
le
5
.
T
h
e
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
with
ex
is
tin
g
r
esear
ch
M
e
t
h
o
d
Y
e
a
r
A
c
c
u
r
a
c
y
V
G
G
1
9
m
o
d
e
l
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
[
2
0
]
2
0
2
3
9
3
.
0
%
D
S
T
[
2
4
]
2
0
2
3
85
.0
%
D
C
N
N
w
i
t
h
GAP
[
2
5
]
2
0
2
3
9
6
.
5
%
P
r
o
p
o
se
d
m
e
t
h
o
d
2
0
2
4
92
.0
%
T
h
is
s
tu
d
y
ex
p
lo
r
ed
a
co
m
p
r
eh
en
s
iv
e
an
al
y
s
is
o
f
d
is
ea
s
e
class
if
icatio
n
in
r
ice
p
la
n
ts
u
s
in
g
th
e
R
esNet5
0
lay
er
m
o
d
el
with
v
ar
io
u
s
ar
ch
itectu
r
al
c
o
n
f
ig
u
r
atio
n
s
an
d
au
g
m
en
tatio
n
tec
h
n
iq
u
es.
Ho
wev
e
r
,
f
u
r
th
er
an
d
in
-
d
e
p
th
s
tu
d
ie
s
m
ay
b
e
n
ee
d
e
d
to
co
n
f
i
r
m
its
ef
f
icac
y
ac
r
o
s
s
d
if
f
er
en
t
d
atasets
an
d
en
v
ir
o
n
m
en
tal
c
o
n
d
itio
n
s
,
esp
ec
ially
r
eg
ar
d
in
g
its
g
en
er
aliz
ab
ilit
y
an
d
r
o
b
u
s
tn
ess
in
r
ea
l
-
wo
r
ld
ag
r
icu
ltu
r
al
s
ettin
g
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
4
2
9
-
3
4
3
8
3436
4.
CO
NCLU
SI
O
N
I
n
s
u
m
m
ar
y
,
th
is
r
esear
c
h
a
d
d
r
ess
es
th
e
cr
itical
r
o
le
o
f
r
ice
cu
ltiv
atio
n
in
g
lo
b
al
a
g
r
icu
ltu
r
e,
p
ar
ticu
lar
ly
in
I
n
d
o
n
esia,
t
h
e
th
ir
d
-
lar
g
est
g
l
o
b
al
r
ice
p
r
o
d
u
ce
r
.
R
ec
en
t
ex
p
e
r
im
en
ts
s
u
g
g
est
th
at
in
n
o
v
ativ
e
d
ig
ital
im
ag
e
an
al
y
s
is
s
o
lu
tio
n
s
ca
n
ac
h
iev
e
ef
f
ec
tiv
e
cr
o
p
m
an
ag
em
en
t
f
o
r
s
u
s
tain
ed
p
r
o
d
u
ctio
n
lev
els.
B
y
h
ar
n
ess
in
g
ad
v
an
c
ed
alg
o
r
ith
m
s
s
u
ch
as
C
N
Ns,
r
esear
ch
er
s
en
d
ea
v
o
r
to
p
r
ec
is
ely
id
en
tify
an
d
class
if
y
r
ice
leaf
d
is
ea
s
es,
wh
ich
p
o
s
e
s
ig
n
if
ican
t
th
r
ea
ts
to
cr
o
p
g
r
o
wth
an
d
y
ield
.
Utilizin
g
a
c
o
m
p
r
e
h
en
s
iv
e
d
ataset
f
r
o
m
r
ep
u
tab
le
r
ep
o
s
ito
r
ies
lik
e
K
ag
g
le,
th
e
s
tu
d
y
co
n
d
u
cts
tr
ain
in
g
an
d
test
in
g
o
f
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els.
C
en
tr
al
to
th
is
p
r
o
ce
s
s
ar
e
d
a
ta
au
g
m
e
n
tatio
n
tec
h
n
iq
u
es,
i
n
clu
d
in
g
r
an
d
o
m
zo
o
m
a
n
d
o
th
er
s
,
wh
ich
p
lay
a
cr
u
cial
r
o
le
in
d
iv
er
s
if
y
in
g
th
e
tr
ain
in
g
d
ataset
an
d
b
o
ls
ter
in
g
m
o
d
el
r
o
b
u
s
tn
ess
ac
r
o
s
s
v
ar
ied
co
n
d
itio
n
s
.
T
h
e
p
a
p
er
i
n
tr
o
d
u
ce
s
eig
h
t
ex
p
er
im
e
n
tal
s
ce
n
ar
io
s
,
ea
ch
co
m
b
in
in
g
d
is
tin
ctiv
e
ar
ch
itectu
r
al
co
n
f
ig
u
r
atio
n
s
a
n
d
a
u
g
m
e
n
tatio
n
m
eth
o
d
o
l
o
g
ies
ap
p
lied
to
a
R
esNet5
0
lay
e
r
m
o
d
el.
No
tab
ly
,
Scen
a
r
io
4
,
wh
ich
in
co
r
p
o
r
ates
r
an
d
o
m
zo
o
m
au
g
m
e
n
tatio
n
with
o
u
t
th
e
ML
P
co
m
p
o
n
e
n
t,
em
er
g
es
as
th
e
m
o
s
t
ef
f
ec
tiv
e,
ac
h
iev
in
g
th
e
h
ig
h
est
ac
cu
r
ac
y
an
d
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
m
etr
ics.
T
h
e
s
tu
d
y
also
in
clu
d
es
a
g
r
id
s
ea
r
ch
to
o
p
tim
ize
th
e
ML
P
lay
er
s
,
r
ev
ea
lin
g
th
e
ef
f
ec
tiv
en
ess
o
f
a
t
h
r
ee
-
lay
er
c
o
n
f
ig
u
r
atio
n
.
Ov
e
r
all,
th
ese
f
in
d
in
g
s
u
n
d
er
s
co
r
e
t
h
e
s
ig
n
if
ican
ce
o
f
ar
ch
itectu
r
al
c
o
n
f
ig
u
r
atio
n
s
an
d
au
g
m
en
tatio
n
tech
n
i
q
u
es
in
d
ev
elo
p
in
g
ac
cu
r
ate
m
o
d
els
f
o
r
class
if
y
in
g
r
ice
p
lan
t
d
is
ea
s
es,
co
n
tr
ib
u
tin
g
v
alu
a
b
le
in
s
ig
h
ts
to
im
p
r
o
v
e
f
o
o
d
s
ec
u
r
ity
th
r
o
u
g
h
tim
ely
d
is
ea
s
e
d
etec
ti
o
n
an
d
in
ter
v
e
n
tio
n
s
tr
ateg
ies.
Ou
r
s
tu
d
y
s
h
o
ws
th
at
zo
o
m
au
g
m
en
tatio
n
an
d
ML
P
lay
er
s
af
f
ec
t
d
is
ea
s
e
class
if
icatio
n
ac
cu
r
ac
y
.
Fu
tu
r
e
r
esear
ch
c
o
u
ld
e
x
p
lo
r
e
in
teg
r
atin
g
e
x
p
lain
ab
le
A
I
(
XAI
)
tech
n
iq
u
es
f
o
r
m
o
d
el
in
ter
p
r
etab
ilit
y
an
d
test
in
g
th
e
m
o
d
el
’
s
tr
a
n
s
f
er
ab
i
lity
to
d
if
f
er
e
n
t
r
e
g
io
n
s
a
n
d
r
i
ce
v
ar
ieties.
R
ea
l
-
tim
e
m
o
n
ito
r
in
g
s
y
s
tem
s
in
th
e
f
ield
co
u
ld
e
n
ab
le
a
d
ap
tiv
e
r
e
s
p
o
n
s
es
to
ch
a
n
g
in
g
d
is
ea
s
e
p
atter
n
s
.
C
o
llab
o
r
atio
n
b
etwe
e
n
ex
p
er
ts
co
u
ld
lea
d
to
u
s
er
-
f
r
ien
d
ly
ap
p
licatio
n
s
f
o
r
ea
r
ly
d
is
ea
s
e
d
etec
tio
n
.
Fin
ally
,
ap
p
ly
i
n
g
t
h
e
m
o
d
el
alo
n
g
s
id
e
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
a
n
d
s
u
s
tain
ab
le
f
ar
m
in
g
p
r
ac
tices c
o
u
ld
en
h
an
ce
lo
n
g
-
ter
m
cr
o
p
h
ea
lth
an
d
f
o
o
d
s
ec
u
r
ity
.
ACK
NO
WL
E
DG
M
E
N
T
T
h
e
au
th
o
r
s
ar
e
g
r
ate
f
u
l to
th
e
W
o
r
ld
o
m
eter
in
itiativ
e
f
o
r
p
r
o
v
id
in
g
clu
es to
th
e
s
tu
d
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
r
o
u
g
h
a
f
u
n
d
am
e
n
tal
r
esear
ch
g
r
an
t,
th
is
r
esear
ch
h
as
r
ec
eiv
ed
s
u
p
p
o
r
t
f
r
o
m
Un
i
v
er
s
itas
Am
ik
o
m
Yo
g
y
ak
ar
ta
(
g
r
a
n
t n
u
m
b
er
R
P
-
1
7
2
5
2
4
7
5
7
9
)
.
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
Mo
h
am
ad
Fird
a
u
s
✓
✓
✓
✓
✓
✓
✓
✓
Ku
s
r
in
i
✓
✓
✓
✓
✓
✓
I
Ma
d
e
Ar
th
a
Ag
asty
a
✓
✓
✓
✓
✓
✓
✓
R
o
d
r
ig
o
Ma
r
tín
ez
-
B
éjar
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
t
h
is
s
tu
d
y
ar
e
o
p
e
n
ly
av
ailab
le
in
Kag
g
le
r
ep
o
s
ito
r
y
at:
h
ttp
s
:
//ka
g
g
le.
co
m/co
mp
etitio
n
s
/p
a
d
d
y
-
d
is
ea
s
e
-
cla
s
s
ifica
tio
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
Op
timiz
in
g
r
ice
lea
f d
is
ea
s
e
cla
s
s
ifica
tio
n
th
r
o
u
g
h
co
n
vo
lu
ti
o
n
a
l n
e
u
r
a
l n
etw
o
r
k
…
(
Mo
h
a
ma
d
F
ir
d
a
u
s
)
3437
RE
F
E
R
E
NC
E
S
[
1
]
P
.
S
e
e
l
w
a
l
a
n
d
T.
R
.
R
o
h
i
l
l
a
,
“
O
p
t
i
m
i
z
e
d
l
i
g
h
t
-
w
e
i
g
h
t
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
r
i
c
e
d
i
s
e
a
s
e
i
d
e
n
t
i
f
i
c
a
t
i
o
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 i
n
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
2
,
n
o
.
2
s,
p
p
.
6
5
7
–
6
6
4
,
2
0
2
4
.
[
2
]
O
.
W
a
l
l
a
c
h
,
“
T
h
i
s
i
s
h
o
w
mu
c
h
r
i
c
e
i
s
p
r
o
d
u
c
e
d
a
r
o
u
n
d
t
h
e
w
o
r
l
d
-
a
n
d
t
h
e
c
o
u
n
t
r
i
e
s t
h
a
t
g
r
o
w
t
h
e
mo
s
t
,
”
Vi
su
a
l
C
a
p
i
t
a
l
i
s
t
.
2
0
2
4
.
A
c
c
e
ss
e
d
:
J
a
n
.
1
1
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
w
e
f
o
r
u
m
.
o
r
g
/
a
g
e
n
d
a
/
2
0
2
2
/
0
3
/
v
i
s
u
a
l
i
z
i
n
g
-
t
h
e
-
w
o
r
l
d
-
s
-
b
i
g
g
e
st
-
r
i
c
e
-
p
r
o
d
u
c
e
r
s
/
[
3
]
M
.
T
.
A
h
a
d
,
Y
.
Li
,
B
.
S
o
n
g
,
a
n
d
T.
B
h
u
i
y
a
n
,
“
C
o
mp
a
r
i
s
o
n
o
f
C
N
N
-
b
a
se
d
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
f
o
r
r
i
c
e
d
i
s
e
a
s
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
A
g
ri
c
u
l
t
u
r
e
,
v
o
l
.
9
,
p
p
.
2
2
–
3
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
a
.
2
0
2
3
.
0
7
.
0
0
1
.
[
4
]
S
.
P
r
a
t
h
i
m
a
,
N
.
G
.
P
r
a
v
e
e
n
a
,
K
.
S
i
v
a
c
h
a
n
d
a
r
,
S
.
S
.
N
a
t
h
,
a
n
d
B
.
S
a
r
a
l
a
,
“
G
e
n
e
r
i
c
p
a
d
d
y
p
l
a
n
t
d
i
sea
s
e
d
e
t
e
c
t
o
r
(
G
P
2
D
2
)
:
a
n
a
p
p
l
i
c
a
t
i
o
n
o
f
t
h
e
d
e
e
p
-
C
N
N
m
o
d
e
l
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
S
y
st
e
m
s
,
v
o
l
.
1
4
,
n
o
.
6
,
p
p
.
6
4
7
–
6
5
6
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
9
8
5
/
I
JEC
ES.
1
4
.
6
.
4
.
[
5
]
Y
.
Lu
,
X
.
W
u
,
P
.
L
i
u
,
H
.
L
i
,
a
n
d
W
.
Li
u
,
“
R
i
c
e
d
i
s
e
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
met
h
o
d
b
a
se
d
o
n
i
mp
r
o
v
e
d
C
N
N
-
B
i
G
R
U
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
9
,
p
p
.
1
0
0
–
1
0
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
a
.
2
0
2
3
.
0
8
.
0
0
5
.
[
6
]
C
.
R
.
R
a
h
m
a
n
e
t
a
l
.
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
o
f
r
i
c
e
d
i
s
e
a
ses
a
n
d
p
e
st
s
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,”
Bi
o
s
y
st
e
m
s
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
9
4
,
p
p
.
1
1
2
–
1
2
0
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
s
y
s
t
e
ms
e
n
g
.
2
0
2
0
.
0
3
.
0
2
0
.
[
7
]
J.
P
.
S
h
a
h
,
H
.
B
.
P
r
a
j
a
p
a
t
i
,
a
n
d
V
.
K
.
D
a
b
h
i
,
“
A
s
u
r
v
e
y
o
n
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
o
f
r
i
c
e
p
l
a
n
t
d
i
se
a
s
e
s,”
i
n
2
0
1
6
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
u
rren
t
T
r
e
n
d
s
i
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
(
I
C
C
T
A
C
)
,
M
a
r
.
2
0
1
6
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
TA
C
.
2
0
1
6
.
7
5
6
7
3
3
3
.
[
8
]
F
.
Ji
a
n
g
,
Y
.
Lu
,
Y
.
C
h
e
n
,
D
.
C
a
i
,
a
n
d
G
.
L
i
,
“
I
mag
e
r
e
c
o
g
n
i
t
i
o
n
o
f
f
o
u
r
r
i
c
e
l
e
a
f
d
i
s
e
a
s
e
s
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
ro
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
1
7
9
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
0
.
1
0
5
8
2
4
.
[
9
]
N
.
V
.
R
.
R
.
G
o
l
u
g
u
r
i
,
K
.
S
u
g
a
n
y
a
D
e
v
i
,
a
n
d
N
.
V
a
d
a
p
a
r
t
h
i
,
I
m
a
g
e
c
l
a
s
si
f
i
e
rs
a
n
d
i
m
a
g
e
d
e
e
p
l
e
a
r
n
i
n
g
c
l
a
s
si
f
i
e
rs
e
v
o
l
v
e
d
i
n
d
e
t
e
c
t
i
o
n
o
f
O
r
y
za
s
a
t
i
v
a
d
i
se
a
s
e
s:
s
u
rve
y
,
v
o
l
.
5
4
,
n
o
.
1
.
S
p
r
i
n
g
e
r
N
e
t
h
e
r
l
a
n
d
s
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
6
2
-
0
2
0
-
0
9
8
4
9
-
y.
[
1
0
]
B
.
S
.
B
a
r
i
e
t
a
l
.
,
“
A
r
e
a
l
-
t
i
m
e
a
p
p
r
o
a
c
h
o
f
d
i
a
g
n
o
s
i
n
g
r
i
c
e
l
e
a
f
d
i
sea
s
e
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
f
a
st
e
r
R
-
C
N
N
f
r
a
mew
o
r
k
,
”
Pe
e
r
J
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s.
4
3
2
.
[
1
1
]
P
.
K
.
S
e
t
h
y
,
N
.
K
.
B
a
r
p
a
n
d
a
,
A
.
K
.
R
a
t
h
,
a
n
d
S
.
K
.
B
e
h
e
r
a
,
“
D
e
e
p
f
e
a
t
u
r
e
b
a
s
e
d
r
i
c
e
l
e
a
f
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
ro
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
1
7
5
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
0
.
1
0
5
5
2
7
.
[
1
2
]
Y
.
L
u
,
S
.
Y
i
,
N
.
Z
e
n
g
,
Y
.
L
i
u
,
a
n
d
Y
.
Zh
a
n
g
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
r
i
c
e
d
i
s
e
a
se
s
u
si
n
g
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,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
2
6
7
,
p
p
.
3
7
8
–
3
8
4
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
1
7
.
0
6
.
0
2
3
.
[
1
3
]
J.
Zh
a
n
g
,
Y
.
Y
a
n
g
,
X
.
F
e
n
g
,
H
.
X
u
,
J.
C
h
e
n
,
a
n
d
Y
.
H
e
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
b
a
c
t
e
r
i
a
l
b
l
i
g
h
t
r
e
s
i
st
a
n
t
r
i
c
e
se
e
d
s
u
si
n
g
t
e
r
a
h
e
r
t
z
i
ma
g
i
n
g
a
n
d
h
y
p
e
r
sp
e
c
t
r
a
l
i
ma
g
i
n
g
c
o
mb
i
n
e
d
w
i
t
h
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
,
”
Fr
o
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
1
,
n
o
.
J
u
n
e
,
p
p
.
1
–
1
5
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
2
0
.
0
0
8
2
1
.
[
1
4
]
P
.
I
.
R
i
t
h
a
r
s
o
n
,
K
.
R
a
i
m
o
n
d
,
X
.
A
.
M
a
r
y
,
J.
E.
R
o
b
e
r
t
,
a
n
d
A
.
J,
“
D
e
e
p
R
i
c
e
:
A
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
f
e
a
t
u
r
e
b
a
sed
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
s
e
a
s
e
su
b
t
y
p
e
s,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
1
,
p
p
.
3
4
–
4
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
a
.
2
0
2
3
.
1
1
.
0
0
1
.
[
1
5
]
R
.
S
.
Jes
i
e
,
M
.
S
.
G
.
P
r
e
m
i
,
a
n
d
T.
J
a
r
i
n
,
“
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
p
a
d
d
y
l
e
a
f
d
i
se
a
ses
s
e
n
s
i
n
g
w
i
t
h
a
h
y
b
r
i
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
,
”
Me
a
s
u
reme
n
t
:
S
e
n
s
o
rs
,
v
o
l
.
3
1
,
n
o
.
N
o
v
e
m
b
e
r
2
0
2
3
,
p
.
1
0
0
9
6
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
se
n
.
2
0
2
3
.
1
0
0
9
6
6
.
[
1
6
]
J.
C
u
i
a
n
d
F
.
T
a
n
,
“
R
i
c
e
p
l
a
q
u
e
d
e
t
e
c
t
i
o
n
a
n
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
a
n
i
mp
r
o
v
e
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
A
g
ri
c
u
l
t
u
r
e
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
–
1
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
3
0
1
0
1
7
0
.
[
1
7
]
T.
G
u
p
t
a
,
Ti
t
u
n
a
t
h
,
a
n
d
V
.
Ja
i
n
,
“
P
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
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
S
u
st
a
i
n
a
b
l
e
C
o
m
p
u
t
i
n
g
a
n
d
S
m
a
r
t
S
y
st
e
m
s,
I
C
S
C
S
S
2
0
2
3
-
Pr
o
c
e
e
d
i
n
g
s
,
v
o
l
.
1
5
,
n
o
.
6
,
p
p
.
2
0
2
–
2
0
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
S
S
5
7
6
5
0
.
2
0
2
3
.
1
0
1
6
9
2
6
8
.
[
1
8
]
A
.
P
e
t
c
h
i
a
mm
a
l
,
D
.
M
u
r
u
g
a
n
,
a
n
d
K
.
S
.
B
r
i
sk
l
i
n
e
,
“
P
a
d
d
y
N
e
t
:
a
n
i
m
p
r
o
v
e
d
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
f
o
r
a
u
t
o
m
a
t
e
d
d
i
s
e
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
n
v
i
su
a
l
p
a
d
d
y
l
e
a
f
i
m
a
g
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
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
.
6
,
p
p
.
1
1
4
1
–
1
1
4
9
,
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
0
6
1
2
2
.
[
1
9
]
C
.
Z
h
a
n
g
,
R
.
N
i
,
Y
.
M
u
,
Y
.
S
u
n
,
a
n
d
T.
L.
Ty
a
si
,
“
Li
g
h
t
w
e
i
g
h
t
M
u
l
t
i
-
s
c
a
l
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
f
o
r
r
i
c
e
l
e
a
f
d
i
se
a
se
r
e
c
o
g
n
i
t
i
o
n
,
”
C
o
m
p
u
t
e
rs,
M
a
t
e
ri
a
l
s
a
n
d
C
o
n
t
i
n
u
a
,
v
o
l
.
7
4
,
n
o
.
1
,
p
p
.
9
8
3
–
9
9
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc
.
2
0
2
3
.
0
2
7
2
6
9
.
[
2
0
]
R
.
D
o
g
r
a
,
S
.
R
a
n
i
,
A
.
S
i
n
g
h
,
M
.
A
.
A
l
b
a
h
a
r
,
A
.
E.
B
a
r
r
e
r
a
,
a
n
d
A
.
A
l
k
h
a
y
y
a
t
,
“
D
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
d
e
t
e
c
t
i
o
n
o
f
b
r
o
w
n
s
p
o
t
r
i
c
e
l
e
a
f
d
i
se
a
se
w
i
t
h
sm
a
r
t
a
g
r
i
c
u
l
t
u
r
e
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
9
,
n
o
.
P
A
,
p
.
1
0
8
6
5
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
3
.
1
0
8
6
5
9
.
[
2
1
]
C
.
G
.
S
i
m
h
a
d
r
i
a
n
d
H
.
K
.
K
o
n
d
a
v
e
e
t
i
,
“
A
u
t
o
ma
t
i
c
r
e
c
o
g
n
i
t
i
o
n
o
f
r
i
c
e
l
e
a
f
d
i
se
a
ses
u
si
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
Ag
ro
n
o
m
y
,
v
o
l
.
1
3
,
n
o
.
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
m
y
1
3
0
4
0
9
6
1
.
[
2
2
]
A
.
R
.
K
h
a
n
,
I
.
A
b
u
n
a
d
i
,
B
.
A
l
g
h
o
f
a
i
l
y
,
H
.
A
l
i
,
a
n
d
T.
S
a
b
a
,
“
A
u
t
o
m
a
t
i
c
d
i
a
g
n
o
s
i
s
o
f
r
i
c
e
l
e
a
v
e
s
d
i
se
a
ses
u
si
n
g
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
4
1
8
–
4
2
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
2
7
2
0
/
j
a
i
t
.
1
4
.
3
.
4
1
8
-
4
2
5
.
[
2
3
]
H
.
Li
u
,
Y
.
C
u
i
,
J
.
W
a
n
g
,
a
n
d
H
.
Y
u
,
“
A
n
a
l
y
si
s
a
n
d
r
e
sea
r
c
h
o
n
r
i
c
e
d
i
sea
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
me
t
h
o
d
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
5
,
n
o
.
1
2
,
p
p
.
1
–
1
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
5
1
2
9
3
2
1
.
[
2
4
]
A
.
K
.
D
i
x
i
t
a
n
d
R
.
V
e
r
ma
,
“
A
d
v
a
n
c
e
d
h
y
b
r
i
d
m
o
d
e
l
f
o
r
m
u
l
t
i
p
a
d
d
y
d
i
sea
ses
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
EAI
En
d
o
rse
d
T
ra
n
s
a
c
t
i
o
n
s
o
n
Pe
r
v
a
si
v
e
H
e
a
l
t
h
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
–
8
,
2
0
2
3
,
d
o
i
:
1
0
.
4
1
0
8
/
e
e
t
p
h
t
.
9
.
4
4
8
1
.
[
2
5
]
S
.
S
.
P
a
n
d
i
,
A
.
S
e
n
t
h
i
l
s
e
l
v
i
,
J.
G
i
t
a
n
j
a
l
i
,
K
.
A
r
i
v
u
S
e
l
v
a
n
,
J.
G
o
p
a
l
,
a
n
d
J.
V
e
l
l
i
n
g
i
r
i
,
“
R
i
c
e
p
l
a
n
t
d
i
s
e
a
s
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
d
i
l
a
t
e
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
g
l
o
b
a
l
a
v
e
r
a
g
e
p
o
o
l
i
n
g
,
”
E
c
o
l
o
g
i
c
a
l
M
o
d
e
l
l
i
n
g
,
v
o
l
.
4
7
4
,
n
o
.
J
u
l
y
,
p
.
1
1
0
1
6
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
o
l
m
o
d
e
l
.
2
0
2
2
.
1
1
0
1
6
6
.
[
2
6
]
M
.
M
.
H
a
sa
n
,
A
.
F
.
M
.
S
.
U
d
d
i
n
,
M
.
R
.
A
k
h
o
n
d
,
M
.
J
.
U
d
d
i
n
,
M
.
A
.
H
o
ss
a
i
n
,
a
n
d
M
.
A
.
H
o
ssa
i
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
r
i
c
e
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
:
A
c
r
i
t
i
c
a
l
a
n
a
l
y
s
i
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
P
l
a
n
t
B
i
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
4
,
p
p
.
1
1
9
0
–
1
2
0
7
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
p
b
1
4
0
4
0
0
8
7
.
[
2
7
]
P
.
D
o
c
t
o
r
,
“
P
a
d
d
y
d
o
c
t
o
r
:
p
a
d
d
y
d
i
s
e
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
K
a
g
g
l
e
.
K
a
g
g
l
e
,
2
0
2
2
.
A
c
c
e
ss
e
d
:
J
u
n
.
0
1
,
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
k
a
g
g
l
e
.
c
o
m/
c
o
m
p
e
t
i
t
i
o
n
s/
p
a
d
d
y
-
d
i
sea
se
-
c
l
a
ss
i
f
i
c
a
t
i
o
n
[
2
8
]
O
.
A
z
z
a
m
a
n
d
T.
C
.
B
.
C
h
a
n
c
e
l
l
o
r
,
“
Th
e
b
i
o
l
o
g
y
,
e
p
i
d
e
m
i
o
l
o
g
y
,
a
n
d
m
a
n
a
g
e
m
e
n
t
o
f
r
i
c
e
t
u
n
g
r
o
d
i
s
e
a
se
i
n
A
si
a
,
”
Pl
a
n
t
D
i
se
a
se
,
v
o
l
.
8
6
,
n
o
.
2
,
p
p
.
8
8
–
1
0
0
,
F
e
b
.
2
0
0
2
,
d
o
i
:
1
0
.
1
0
9
4
/
P
D
I
S
.
2
0
0
2
.
8
6
.
2
.
8
8
.
[
2
9
]
O
.
C
a
a
s
i
,
C
.
H
o
n
g
o
,
A
.
S
u
r
y
a
n
i
n
g
si
h
,
S
.
W
i
y
o
n
o
,
K
.
H
o
mm
a
,
a
n
d
M
.
S
h
i
s
h
i
d
o
,
“
R
e
l
a
t
i
o
n
s
h
i
p
s
b
e
t
w
e
e
n
b
a
c
t
e
r
i
a
l
l
e
a
f
b
l
i
g
h
t
a
n
d
o
t
h
e
r
d
i
se
a
ses
b
a
s
e
d
o
n
f
i
e
l
d
a
ss
e
ssm
e
n
t
i
n
I
n
d
o
n
e
s
i
a
,
”
T
ro
p
i
c
a
l
A
g
ri
c
u
l
t
u
r
e
a
n
d
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
6
3
,
n
o
.
3
,
p
p
.
1
1
3
–
1
2
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
2
4
8
/
j
st
a
.
6
3
.
1
1
3
.
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.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
4
2
9
-
3
4
3
8
3438
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mo
h
a
m
a
d
F
irda
u
s
g
ra
d
u
a
t
e
d
fro
m
U
n
iv
e
rsitas
Am
ik
o
m
Y
o
g
y
a
k
a
rta
with
a
m
a
ste
r
’
s
d
e
g
re
e
in
th
e
P
o
stg
ra
d
u
a
te
S
tu
d
y
p
r
o
g
ra
m
.
At
th
e
e
n
d
o
f
2
0
2
3
,
h
e
b
e
g
a
n
h
is
c
a
re
e
r
a
s
a
lec
tu
re
r
a
t
In
stit
u
t
Tek
n
o
l
o
g
i
d
a
n
Ke
se
h
a
tan
M
a
h
a
rd
i
k
a
in
Cire
b
o
n
,
In
d
o
n
e
sia
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
m
o
h
a
m
a
d
.
1
2
2
1
@s
t
u
d
e
n
ts.am
ik
o
m
.
a
c
.
i
d
.
K
u
sr
in
i
is
a
p
r
o
fe
ss
o
r
fro
m
Un
iv
e
rsitas
Am
ik
o
m
Yo
g
y
a
k
a
rt
a
In
d
o
n
e
sia
.
S
h
e
fin
ish
e
d
h
e
r
d
o
c
t
o
ra
l
p
ro
g
ra
m
in
th
e
Co
m
p
u
ter
S
c
ie
n
c
e
S
tu
d
y
P
ro
g
ra
m
a
t
Un
i
v
e
rsitas
G
a
d
jah
M
a
d
a
,
Y
o
g
y
a
k
a
rta,
I
n
d
o
n
e
sia
,
in
2
0
1
0
.
S
h
e
is
in
tere
ste
d
in
e
x
p
l
o
rin
g
m
a
n
y
t
h
in
g
s
re
late
d
t
o
m
a
c
h
in
e
lea
rn
in
g
a
n
d
o
th
e
r
a
rti
fi
c
ial
in
telli
g
e
n
c
e
field
s.
S
h
e
a
lso
lo
v
e
s
re
se
a
rc
h
in
g
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
s
a
n
d
d
a
tab
a
se
s.
S
h
e
is
a
m
e
m
b
e
r
o
f
t
h
e
IE
EE
a
n
d
IE
EE
S
y
ste
m
s,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s
S
o
c
iety
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
k
u
srin
i@a
m
ik
o
m
.
a
c
.
id
.
h
e
r
p
ro
f
il
e
c
a
n
b
e
f
o
u
n
d
at
Web
site: h
t
tp
:/
/k
u
srin
i.
c
o
m
/.
I
Ma
d
e
Ar
th
a
Ag
a
st
y
a
e
a
rn
e
d
h
is
m
a
ste
r
’
s
d
e
g
re
e
i
n
i
n
fo
rm
a
ti
o
n
tec
h
n
o
lo
g
y
with
a
fo
c
u
s
o
n
p
a
tt
e
rn
re
c
o
g
n
it
io
n
a
n
d
d
a
ta
c
lu
ste
ri
n
g
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
i
n
2
0
1
7
.
He
su
b
se
q
u
e
n
tl
y
c
o
m
p
lete
d
h
is
P
h
D
in
c
o
m
p
u
ter
sc
ien
c
e
a
t
Tay
l
o
r
’
s
Un
iv
e
rsity
,
M
a
lay
sia
,
in
2
0
2
4
.
H
e
is
a
lec
tu
re
r
in
t
h
e
In
f
o
rm
a
ti
c
s
De
p
a
rtme
n
t
a
t
Un
i
v
e
rsitas
Am
ik
o
m
Yo
g
y
a
k
a
rta,
I
n
d
o
n
e
sia
.
He
h
a
s
b
e
e
n
a
c
ti
v
e
l
y
i
n
v
o
l
v
e
d
in
two
g
ra
n
t
p
ro
jec
ts
fu
n
d
e
d
b
y
t
h
e
M
in
istr
y
o
f
Ed
u
c
a
ti
o
n
,
C
u
lt
u
re
,
Re
se
a
rc
h
,
a
n
d
Tec
h
n
o
lo
g
y
,
In
d
o
n
e
sia
.
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
,
a
ffe
c
ti
v
e
c
o
m
p
u
ti
n
g
,
EE
G
sig
n
a
l
p
ro
c
e
ss
in
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
c
o
m
p
u
ter v
isio
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
a
rt
h
a
.
a
g
a
sty
a
@a
m
ik
o
m
.
a
c
.
id
.
Ro
d
r
ig
o
Ma
r
tí
n
e
z
-
Bé
ja
r
is
a
P
ro
fe
ss
o
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
i
n
th
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
a
t
t
h
e
Un
i
v
e
rsity
o
f
M
u
rc
ia
i
n
S
p
a
in
.
H
e
re
c
e
iv
e
d
h
is
m
a
ste
r
’
s
in
c
o
m
p
u
t
e
r
sc
ien
c
e
fro
m
th
e
Un
iv
e
rsit
y
o
f
M
a
lag
a
i
n
1
9
9
2
a
n
d
h
is
P
h
.
D.
fr
o
m
th
e
Un
iv
e
rsit
y
o
f
M
u
rc
ia
in
S
p
a
i
n
in
1
9
9
7
.
Als
o
,
h
e
h
o
l
d
s
a
m
a
ste
r
’
s
d
e
g
re
e
in
a
p
p
li
e
d
S
o
c
io
l
o
g
y
fro
m
th
e
Un
i
v
e
rsity
o
f
M
u
rc
ia.
He
h
a
s
h
e
ld
v
isit
in
g
p
o
siti
o
n
s
a
t
se
v
e
ra
l
Eu
ro
p
e
a
n
,
Au
stra
li
a
n
,
a
n
d
Latin
-
Am
e
rica
n
Un
iv
e
rsiti
e
s,
in
c
lu
d
i
n
g
th
e
Au
stra
li
a
n
Un
iv
e
rsiti
e
s
o
f
Ad
e
lai
d
e
a
n
d
Ne
w
S
o
u
t
h
Wale
s
a
n
d
th
e
F
re
n
c
h
U
n
iv
e
rsit
y
o
f
S
o
u
th
e
rn
P
a
ris.
He
h
a
s
se
rv
e
d
o
n
se
v
e
ra
l
E
d
it
o
rial
B
o
a
rd
s
a
n
d
c
o
-
a
u
th
o
re
d
m
o
re
th
a
n
1
0
0
sc
ie
n
ti
fic
p
u
b
li
c
a
ti
o
n
s,
m
o
st
o
f
th
e
m
in
p
e
e
r
-
re
v
iew
e
d
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
h
a
s
led
m
o
re
th
a
n
3
0
n
a
ti
o
n
a
l
o
r
in
tern
a
ti
o
n
a
l
c
o
m
p
e
ti
ti
v
e
g
ra
n
ts
a
n
d
re
se
a
rc
h
c
o
n
trac
ts
with
in
d
u
st
ry
.
I
n
2
0
0
6
,
h
e
b
e
c
a
m
e
th
e
He
a
d
o
f
a
n
in
stit
u
ti
o
n
a
l,
i
n
ter
-
d
isc
ip
li
n
a
ry
U
n
iv
e
rsit
y
re
se
a
rc
h
g
ro
u
p
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
ro
d
ri
g
o
@
u
m
.
e
s.
Evaluation Warning : The document was created with Spire.PDF for Python.