I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
26
,
p
p
.
1
6
9
1
~
1
7
0
0
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
6
9
1
-
1
7
0
0
1691
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Enha
nced
V
G
G
-
19
mo
del f
o
r ric
e p
la
nt
disea
se de
tec
tion a
nd
cla
ss
ificatio
n
Ay
e
T
hid
a
Win
1
,
K
hin
M
a
r
So
e
2
,
M
y
int
M
y
int
L
w
in
3
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
,
P
o
l
y
t
e
c
h
n
i
c
U
n
i
v
e
r
si
t
y
(
K
y
a
i
n
g
To
n
g
)
,
K
y
a
i
n
g
To
n
g
,
M
y
a
n
mar
2
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
y
o
f
C
o
m
p
u
t
e
r
S
t
u
d
i
e
s,
Y
a
n
g
o
n
,
M
y
a
n
mar
3
F
a
c
u
l
t
y
o
f
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
Y
a
n
g
o
n
,
M
y
a
n
mar
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
28
,
2
0
2
5
R
ev
is
ed
J
an
20
,
2
0
2
6
Acc
ep
ted
Feb
6
,
2
0
2
6
Rice
is
th
e
m
a
in
sta
p
le
f
o
o
d
a
n
d
rice
fa
rm
in
g
p
lay
s
a
c
ru
c
ial
r
o
le
i
n
t
h
e
a
g
ricu
lt
u
re
se
c
to
r
o
f
M
y
a
n
m
a
r.
It
is
a
lso
a
n
e
ss
e
n
ti
a
l
p
il
lar
i
n
g
e
n
e
ra
ti
n
g
fo
re
ig
n
i
n
c
o
m
e
.
Ho
we
v
e
r,
rice
d
i
se
a
se
s
se
rio
u
sly
re
d
u
c
e
d
t
h
e
rice
p
ro
d
u
c
ti
o
n
a
n
d
q
u
a
li
t
y
.
Early
d
e
tec
ti
o
n
o
f
ri
c
e
d
ise
a
se
s
is
o
n
e
o
f
th
e
e
ffe
c
ti
v
e
wa
y
s
to
re
d
u
c
e
t
h
e
d
ise
a
se
sp
re
a
d
in
g
a
n
d
i
n
c
re
a
se
y
ield
s.
M
o
st
M
y
a
n
m
a
r
fa
rm
e
rs
d
e
tec
t
rice
d
ise
a
se
s
b
a
se
d
o
n
v
is
u
a
l
ju
d
g
m
e
n
t
a
n
d
t
h
e
ir
e
x
p
e
rien
c
e
,
wh
ich
lea
d
s
to
d
e
lay
i
n
tak
i
n
g
e
fficie
n
t
a
c
ti
o
n
.
T
o
o
v
e
rc
o
m
e
th
is
c
h
a
ll
e
n
g
e
,
we
in
ten
d
t
o
p
ro
p
o
se
a
n
e
n
h
a
n
c
e
d
r
ice
p
lan
t
d
ise
a
se
c
las
sifica
ti
o
n
m
o
d
e
l
t
h
a
t
c
o
n
tri
b
u
tes
a
s
a
rti
ficia
l
in
telli
g
e
n
c
e
(AI)
in
M
y
a
n
m
a
r
a
g
ricu
lt
u
re
s
e
c
to
r.
Th
e
p
ro
p
o
se
d
m
o
d
e
l
e
n
h
a
n
c
e
s
o
ri
g
in
a
l
v
isu
a
l
g
e
o
m
e
try
g
ro
u
p
1
9
(
VGG
-
19
)
b
y
in
teg
ra
ti
n
g
th
e
a
lg
o
rit
h
m
s:
m
ix
t
u
re
o
f
G
a
u
ss
ian
s
2
(
M
OG
2
),
G
ra
b
Cu
t
,
a
n
d
re
lev
a
n
c
e
e
stim
a
ti
o
n
with
li
n
e
a
r
fe
a
tu
re
(
REL
IEF
)
f
o
r
c
las
sifica
ti
o
n
.
It
wa
s
train
e
d
o
n
6
,
3
2
6
rice
p
lan
t
ima
g
e
s
o
f
Ka
g
g
le
a
n
d
Eas
tern
S
h
a
n
S
tate
a
n
d
v
a
li
d
a
ted
u
sin
g
5
-
fo
l
d
n
e
ste
d
c
ro
ss
-
v
a
li
d
a
ti
o
n
.
Th
e
trai
n
in
g
a
n
d
tes
ti
n
g
o
f
p
ro
p
o
se
d
m
o
d
e
l
a
re
fo
l
lo
we
d
a
s
8
0
:2
0
.
Th
e
p
r
o
p
o
se
d
m
o
d
e
l
e
x
p
e
rime
n
tal
re
su
lt
is
(9
8
.
3
%
)
a
n
d
lo
we
st
sta
n
d
a
rd
d
e
v
iati
o
n
(0
.
0
0
4
)
a
c
ro
ss
se
v
e
n
c
las
se
s
th
a
n
t
h
e
o
ri
g
in
a
l
VG
G
-
19
,
M
o
b
il
e
Ne
t,
Eff
icie
n
t
Ne
t
,
a
n
d
Re
stNe
t5
0
re
sp
e
c
ti
v
e
ly
.
F
u
t
u
re
wo
r
k
wil
l
e
x
p
a
n
d
d
a
tas
e
t
d
iv
e
rsity
,
e
n
h
a
n
c
e
e
a
rly
-
sta
g
e
d
ise
a
se
p
re
d
ictio
n
,
a
n
d
su
p
p
o
rt
m
o
b
il
e
d
iag
n
o
stics
fo
r
re
a
l
-
wo
rld
a
g
ricu
lt
u
ra
l
a
p
p
li
c
a
ti
o
n
.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
Gr
ab
C
u
t
Mix
tu
r
e
o
f
Ga
u
s
s
ian
s
2
R
elev
an
ce
esti
m
atio
n
with
lin
ea
r
f
ea
tu
r
e
VGG
-
19
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
:
Ay
e
T
h
id
a
W
in
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Scien
ce
,
Po
ly
tech
n
ic
Un
i
v
er
s
ity
(
Ky
ain
g
T
o
n
g
)
Ky
ain
g
T
o
n
g
,
My
a
n
m
ar
E
m
ail:
ay
eth
id
awin
@
u
csk
t.e
d
u
.
m
m
1.
I
NT
RO
D
UCT
I
O
N
R
ice
is
th
e
h
ea
r
t
o
f
My
an
m
ar
’
s
ec
o
n
o
m
y
,
f
o
o
d
s
u
f
f
icien
cy
an
d
a
m
ajo
r
s
o
u
r
ce
o
f
f
o
r
ei
g
n
in
co
m
e.
I
t
ac
co
u
n
ts
f
o
r
o
v
er
6
0
%
o
f
t
h
e
co
u
n
tr
y
’
s
ag
r
icu
ltu
r
al
g
r
o
s
s
d
o
m
esti
c
p
r
o
d
u
ct
(
GDP)
,
s
u
p
p
o
r
ts
m
illi
o
n
s
o
f
liv
elih
o
o
d
s
,
an
d
p
r
o
v
id
es
ec
o
n
o
m
ic
s
tab
ilit
y
.
Sh
an
State
is
o
n
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
r
ice
-
g
r
o
win
g
r
eg
io
n
s
in
My
an
m
ar
.
Ho
wev
er
,
r
ice
p
r
o
d
u
ctio
n
f
ac
es
s
er
io
u
s
th
r
ea
ts
s
u
ch
as
b
r
o
wn
s
p
o
t,
leaf
s
m
u
t,
s
h
ea
th
r
o
t,
s
tem
r
o
t,
tu
n
g
r
o
,
an
d
b
ac
ter
ial
leaf
b
lig
h
t,
wh
ich
r
ed
u
ce
y
ield
s
b
y
u
p
to
3
0
%
an
n
u
ally
.
R
ice
d
is
ea
s
es
th
r
ea
ten
n
o
t
o
n
ly
d
o
m
esti
c
f
o
o
d
s
u
f
f
icien
cy
b
u
t
also
r
ice
q
u
ality
.
Mo
r
e
o
v
er
,
M
y
an
m
ar
f
a
r
m
er
s
in
r
em
o
te
ar
ea
s
ar
e
ex
p
er
ien
cin
g
u
n
n
ec
ess
ar
y
lo
s
s
es
in
r
ice
cu
l
tiv
atio
n
d
u
e
to
th
eir
in
ab
ilit
y
to
id
en
tify
r
ice
d
is
ea
s
es
ac
cu
r
ately
o
r
to
co
n
n
ec
t
with
ag
r
icu
ltu
r
al
ex
p
er
ts
.
Du
e
to
th
e
r
ar
e
o
f
s
k
illed
ag
r
ic
u
ltu
r
al
p
r
o
f
ess
io
n
als,
m
o
s
t
f
ar
m
er
s
in
My
an
m
ar
d
etec
t
an
d
class
if
y
th
e
r
ice
d
is
ea
s
es
b
ased
o
n
v
is
u
al
in
s
p
ec
tio
n
an
d
t
h
eir
o
wn
e
x
p
er
ien
ce
.
As
a
co
n
s
eq
u
en
ce
,
th
e
f
ar
m
er
s
d
elay
to
co
n
tr
o
l
t
h
e
s
p
r
ea
d
o
f
r
ice
d
is
ea
s
es
in
tim
ely
an
d
r
ice
d
is
ea
s
es
ca
u
s
e
s
ev
er
e
d
am
ag
e
t
o
r
ice
f
ield
s
.
E
ar
ly
r
ice
p
lan
t
d
is
ea
s
es
d
etec
tio
n
an
d
d
ia
g
n
o
s
is
ca
n
s
ig
n
if
ican
tly
r
e
d
u
ce
lo
s
s
es.
No
wad
ay
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
6
9
1
-
1
7
0
0
1692
as
tech
n
o
lo
g
y
d
e
v
elo
p
s
,
m
o
d
er
n
tech
n
o
lo
g
ies
s
u
ch
as
d
ee
p
lear
n
in
g
,
m
ac
h
in
e
lear
n
i
n
g
ar
e
b
ein
g
u
s
ed
in
th
e
ag
r
icu
ltu
r
al
s
ec
to
r
.
I
n
My
an
m
ar
,
th
er
e
is
a
n
ee
d
f
o
r
s
y
s
tem
s
th
at
ca
n
ea
s
ily
d
ete
ct
an
d
class
if
y
r
ice
d
is
ea
s
es
au
to
m
atica
lly
to
h
elp
f
ar
m
er
s
.
Acc
o
r
d
in
g
to
th
e
U
n
ited
States
Dep
ar
tm
en
t
o
f
Ag
r
icu
ltu
r
e
(
USDA)
r
ice
ar
ea
esti
m
atio
n
,
Sh
an
State
is
th
e
f
o
u
r
th
lar
g
est
r
ice
-
g
r
o
win
g
r
eg
i
o
n
i
n
My
a
n
m
ar
[
1
]
.
H
o
wev
er
,
au
to
m
ated
r
ice
d
is
ea
s
es
m
o
n
ito
r
in
g
,
d
etec
tio
n
an
d
clas
s
if
icatio
n
s
y
s
tem
s
ar
e
n
o
t
y
et
in
u
tili
ze
d
i
n
Sh
an
State’
s
f
ar
m
in
g
.
R
ice
p
lan
t
d
is
ea
s
e
id
en
tific
ati
o
n
is
a
k
ey
to
s
u
s
tain
ab
le
cr
o
p
p
r
o
d
u
ctio
n
an
d
g
lo
b
al
f
o
o
d
p
r
o
d
u
ctio
n
.
E
ar
ly
d
etec
tio
n
o
f
r
ice
p
lan
t
d
is
ea
s
es
ca
n
s
ig
n
if
ican
tly
i
m
p
r
o
v
e
cr
o
p
y
ield
an
d
q
u
ali
ty
.
Sar
i
et
a
l
.
[
2
]
in
v
esti
g
ated
th
e
ap
p
licatio
n
o
f
R
esNet5
0
d
ee
p
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
DC
NN)
f
o
r
a
u
to
m
atic
d
etec
tio
n
o
f
f
o
u
r
r
ice
leaf
d
is
ea
s
es
u
s
in
g
d
ig
ital
im
ag
e
an
aly
s
is
.
T
h
e
ex
p
er
im
en
tal
r
esu
lts
s
h
o
wed
th
at
th
e
8
5
:1
5
r
atio
h
ad
th
e
h
i
g
h
est
ac
cu
r
ac
y
o
f
8
1
.
4
8
%,
in
d
icatin
g
th
at
R
esNet5
0
p
r
o
v
id
es
r
eliab
le
p
er
f
o
r
m
a
n
ce
f
o
r
r
ice
d
is
ea
s
e
class
if
icatio
n
wh
en
ap
p
r
o
p
r
ia
te
d
ata
an
aly
s
is
s
tr
ateg
ies
ar
e
u
s
ed
.
Vijay
an
a
n
d
C
h
o
w
d
h
a
r
y
[
3
]
p
r
esen
ted
a
h
y
b
r
id
o
p
tim
izatio
n
f
r
am
ewo
r
k
th
at
co
m
b
in
es
th
e
wh
ale
o
p
tim
izatio
n
alg
o
r
ith
m
(
W
OA)
with
ad
ap
tiv
e
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
APSO)
to
en
h
an
ce
im
ag
e
s
eg
m
en
tatio
n
an
d
f
ea
t
u
r
e
s
elec
tio
n
.
T
h
e
s
elec
ted
f
ea
tu
r
es
wer
e
th
e
n
class
if
ied
u
s
in
g
a
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN)
,
r
esu
ltin
g
in
a
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
7
.
5
%.
R
o
d
r
ig
o
et
a
l
.
[
4
]
p
r
esen
ted
a
li
g
h
tweig
h
t
tr
a
n
s
f
er
-
lear
n
i
n
g
m
o
d
el
b
u
ilt
o
n
th
e
Mo
b
ileViT
V2
_
0
5
0
ar
c
h
itectu
r
e
with
I
m
ag
eNe
t
-
1
k
p
r
e
-
tr
ai
n
ed
weig
h
ts
.
T
h
e
m
o
d
el
ef
f
e
ctiv
ely
m
er
g
es
th
e
lo
ca
l
f
ea
tu
r
e
lear
n
in
g
ca
p
ab
il
ity
o
f
C
NN
s
wi
th
th
e
g
lo
b
al
co
n
tex
tu
al
u
n
d
er
s
tan
d
in
g
o
f
v
is
io
n
tr
an
s
f
o
r
m
er
s
u
s
in
g
a
s
ep
ar
a
b
le
s
elf
-
atten
tio
n
m
ec
h
an
is
m
.
I
ts
ef
f
icien
c
y
m
ak
es
it
s
u
itab
le
f
o
r
d
ep
l
o
y
m
en
t
i
n
m
o
b
ile
en
v
ir
o
n
m
en
ts
.
So
b
u
j
et
a
l
.
[
5
]
in
v
esti
g
ated
th
e
ef
f
ec
t o
f
in
c
o
r
p
o
r
atin
g
a
d
d
itio
n
al
f
ea
tu
r
e
e
x
t
r
ac
tio
n
tech
n
i
q
u
es
in
to
th
e
p
r
e
-
tr
ain
ed
E
f
f
icie
n
tNet
-
B
7
ar
ch
itectu
r
e.
B
y
in
t
eg
r
atin
g
h
is
to
g
r
am
o
f
o
r
ien
t
ed
g
r
ad
ien
ts
an
d
g
r
ad
ien
t
-
weig
h
ted
class
ac
tiv
atio
n
m
ap
p
in
g
(
Gr
ad
-
C
AM
)
,
th
eir
en
h
an
ce
d
m
o
d
el
ac
h
ie
v
ed
an
ac
cu
r
ac
y
o
f
9
7
%.
Misb
a
et
a
l
.
[
6
]
in
tr
o
d
u
ce
d
a
r
ice
leaf
d
is
ea
s
e
class
if
i
ca
tio
n
ap
p
r
o
ac
h
b
ased
o
n
a
C
NN
en
h
an
ce
d
with
tr
an
s
f
er
lear
n
in
g
u
s
in
g
th
e
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
(
VGG
)
-
1
6
ar
ch
itectu
r
e
.
T
h
eir
co
m
p
ar
ativ
e
ev
alu
atio
n
d
em
o
n
s
tr
ated
t
h
at
th
e
tr
a
n
s
f
er
lear
n
in
g
–
b
ased
m
o
d
el
ac
h
iev
ed
9
2
.
4
6
%
ac
c
u
r
ac
y
,
s
u
b
s
tan
tially
o
u
tp
er
f
o
r
m
i
n
g
th
e
C
NN
tr
ain
ed
f
r
o
m
s
cr
atch
,
wh
ich
attain
ed
7
4
%
ac
cu
r
ac
y
.
Go
g
o
i
et
a
l
.
[
7
]
p
r
o
p
o
s
ed
a
th
r
ee
-
s
tag
e
C
NN
f
r
am
ewo
r
k
th
at
en
h
a
n
ce
s
cla
s
s
if
icatio
n
p
er
f
o
r
m
an
ce
th
r
o
u
g
h
th
e
u
s
e
o
f
a
p
ar
am
et
r
ic
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
f
u
n
ctio
n
.
T
r
ain
ed
o
n
8
,
8
8
3
im
ag
es
ac
r
o
s
s
f
iv
e
class
es,
th
e
m
o
d
el
ac
h
ie
v
ed
an
ac
cu
r
ac
y
o
f
9
4
%.
Ak
y
o
l
[
8
]
p
r
esen
ted
a
r
ice
leaf
d
is
ea
s
e
class
if
icatio
n
m
eth
o
d
b
ased
o
n
h
y
p
er
co
l
u
m
n
d
ee
p
f
ea
tu
r
es
ex
tr
ac
ted
at
s
alien
t
in
ter
est
p
o
in
ts
.
E
x
p
er
im
en
tal
r
esu
lts
in
d
icate
d
th
at
th
e
r
a
n
d
o
m
f
o
r
est
class
if
ier
ef
f
ec
tiv
ely
u
tili
ze
d
th
ese
f
ea
tu
r
es,
ac
h
ie
v
in
g
an
ac
c
u
r
ac
y
o
f
9
3
.
0
6
%.
Kir
atir
atan
ap
r
u
k
et
a
l
.
[
9
]
p
r
o
p
o
s
ed
a
r
ice
lea
f
d
is
ea
s
e
d
etec
tio
n
ap
p
r
o
ac
h
th
at
in
teg
r
ates
C
NN
-
b
ased
o
b
ject
d
etec
tio
n
with
an
im
a
g
e
tili
n
g
s
tr
ateg
y
g
u
id
e
d
b
y
au
to
m
atica
lly
esti
m
ated
leaf
wid
th
s
.
Usi
n
g
an
1
8
-
lay
er
R
esNet
m
o
d
el
ev
alu
ated
o
n
4
,
9
6
0
im
ag
es
co
v
er
in
g
eig
h
t d
is
ea
s
e
ca
teg
o
r
ies,
th
eir
m
eth
o
d
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
1
.
1
4
%.
Yak
k
u
n
d
im
ath
et
a
l.
[
1
0
]
c
o
n
d
u
cted
a
co
m
p
ar
ativ
e
s
tu
d
y
o
f
VGG
-
16
an
d
Go
o
g
leNe
t
f
o
r
r
ice
d
is
ea
s
e
class
if
icatio
n
u
s
in
g
1
,
2
0
0
im
ag
es
r
ep
r
esen
tin
g
f
u
n
g
al,
b
ac
ter
ial,
an
d
v
i
r
al
in
f
ec
tio
n
s
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
VGG
-
16
ac
h
iev
ed
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
,
attain
in
g
9
2
.
2
4
% a
cc
u
r
ac
y
co
m
p
ar
ed
to
9
1
.
2
8
% f
o
r
Go
o
g
leNe
t.
Sen
th
il
an
d
Kh
atwa
l
[
1
1
]
in
t
r
o
d
u
ce
d
a
n
o
v
el
h
y
b
r
i
d
m
u
lti
-
c
lass
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
MCS
VM
)
-
d
ee
p
n
e
u
r
al
n
etwo
r
k
(
DNN)
a
r
ch
itectu
r
e
f
o
r
ac
c
u
r
ate
r
ice
l
ea
f
d
is
ea
s
e
p
r
ed
ictio
n
.
T
h
e
MCS
VM
co
m
p
o
n
en
t
f
o
cu
s
es
o
n
f
ea
tu
r
e
o
p
tim
izatio
n
af
ter
tr
ain
in
g
,
wh
ile
th
e
DNN
co
m
p
o
n
en
t
en
a
b
les
d
y
n
am
ic
u
p
d
atin
g
o
f
f
ea
tu
r
es
to
h
an
d
le
co
m
p
lex
a
n
d
d
iv
er
s
e
s
y
m
p
to
m
s
.
I
t
ac
h
i
ev
ed
ac
cu
r
ac
y
o
f
9
5
.
2
%.
R
ith
ar
s
o
n
et
a
l.
[
1
2
]
d
ev
elo
p
e
d
a
cu
s
to
m
ized
VGG
-
16
-
b
ased
f
r
am
ewo
r
k
th
at
lev
er
ag
es
d
ee
p
lear
n
i
n
g
an
d
t
r
an
s
f
er
lear
n
in
g
t
o
class
if
y
r
ice
leaf
d
is
ea
s
e
s
.
T
h
eir
ap
p
r
o
ac
h
s
u
cc
ess
f
u
lly
r
ec
o
g
n
ized
n
i
n
e
d
is
tin
ct
d
is
ea
s
e
ca
teg
o
r
ies
an
d
ac
h
iev
ed
a
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
9
.
9
4
%.
Ma
h
a
d
ev
an
et
a
l
.
[
1
3
]
in
t
r
o
d
u
ce
d
a
co
m
p
r
eh
e
n
s
iv
e
r
ice
leaf
d
is
ea
s
e
d
etec
tio
n
f
r
am
e
wo
r
k
ce
n
ter
ed
o
n
a
d
ee
p
s
p
ec
tr
al
g
en
er
ativ
e
ad
v
er
s
ar
ial
n
etwo
r
k
(
DS
-
GAN
)
o
p
tim
ized
u
s
in
g
an
im
p
r
o
v
ed
ar
tific
ial
p
lan
t
o
p
tim
izatio
n
s
tr
ateg
y
.
T
h
e
ap
p
r
o
ac
h
im
p
r
o
v
es
im
ag
e
q
u
ality
th
r
o
u
g
h
an
en
h
an
ce
d
t
h
r
esh
o
l
d
-
b
ased
n
e
u
r
al
n
etwo
r
k
,
ap
p
li
es
m
u
ltis
ca
le
n
eu
r
al
s
licin
g
f
o
r
s
eg
m
en
tatio
n
,
an
d
em
p
lo
y
s
s
p
ec
tr
al
f
ea
tu
r
e
s
elec
tio
n
co
m
b
in
ed
with
s
o
cial
s
p
id
er
–
b
ased
weig
h
t
o
p
tim
izat
io
n
to
id
en
tif
y
th
e
m
o
s
t
d
is
cr
im
in
ativ
e
f
e
atu
r
es
.
L
i
et
a
l
.
[
1
4
]
d
ev
elo
p
e
d
a
Dee
p
L
a
b
V3
+
-
b
ased
s
em
an
tic
s
eg
m
en
tatio
n
f
r
am
ewo
r
k
f
o
r
r
ice
leaf
d
is
ea
s
e
an
aly
s
is
,
lev
er
ag
i
n
g
a
n
en
c
o
d
er
–
d
ec
o
d
er
d
esig
n
with
atr
o
u
s
co
n
v
o
lu
tio
n
an
d
s
p
atial
p
y
r
am
id
p
o
o
lin
g
to
en
h
an
ce
s
eg
m
en
tatio
n
q
u
alit
y
.
T
h
e
ap
p
r
o
ac
h
was
v
alid
ated
o
n
a
d
ataset
co
m
p
r
is
in
g
f
o
u
r
r
ice
leaf
d
is
e
ase
class
e
s
u
s
in
g
m
ea
n
in
ter
s
ec
tio
n
o
v
er
u
n
io
n
(
mIoU
)
a
n
d
p
ix
el
ac
cu
r
ac
y
as
ev
alu
atio
n
m
ea
s
u
r
es.
B
i
an
d
W
an
g
[
1
5
]
p
r
o
p
o
s
ed
an
att
en
tio
n
-
en
h
an
ce
d
d
o
u
b
le
-
b
r
an
ch
DC
NN
f
o
r
r
ice
d
is
ea
s
e
clas
s
if
icatio
n
.
T
h
eir
ex
p
er
im
en
tal
r
esu
lts
s
h
o
wed
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
o
u
tp
er
f
o
r
m
ed
s
ev
er
al
well
-
k
n
o
wn
C
NN
ar
ch
itectu
r
e
s
,
ac
h
iev
in
g
a
h
ig
h
e
r
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
8
.
7
3
%
co
m
p
ar
ed
with
ex
is
tin
g
m
eth
o
d
s
.
Up
ad
h
y
ay
an
d
Ku
m
ar
[
1
6
]
in
tr
o
d
u
ce
d
an
ef
f
icien
t
r
ice
p
lan
t
d
is
ea
s
e
d
etec
tio
n
m
eth
o
d
u
s
in
g
a
C
NN
m
o
d
el
an
d
Ots
u
’
s
g
lo
b
al
t
h
r
e
s
h
o
ld
in
g
.
T
h
eir
r
esear
c
h
f
o
c
u
s
ed
o
n
th
r
e
e
m
ajo
r
r
ice
d
is
ea
s
es
an
d
o
b
tain
e
d
th
e
ac
h
iev
em
en
t
a
h
ig
h
ac
cu
r
ac
y
o
f
9
9
.
7
%.
De
n
g
et
a
l
.
[
1
7
]
p
r
o
p
o
s
ed
en
s
em
b
le
m
o
d
el
co
m
b
i
n
in
g
Den
s
eNe
t
-
1
2
1
,
SE
-
R
esNet
-
5
0
,
R
e
s
NeSt
-
5
0
,
R
esNet
-
5
0
,
an
d
R
esNeX
t
-
5
0
f
o
r
r
ice
d
is
ea
s
e
d
iag
n
o
s
is
ac
r
o
s
s
s
ix
d
is
ea
s
e
cla
s
s
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
h
a
n
ce
d
V
GG
-
1
9
mo
d
el
fo
r
r
ice
p
la
n
t d
is
ea
s
e
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
(
A
ye
Th
id
a
Wi
n
)
1693
o
n
3
,
3
0
2
im
ag
es.
T
h
eir
en
s
e
m
b
le
ap
p
r
o
ac
h
ac
h
iev
es
an
o
v
er
all
ac
cu
r
ac
y
o
f
9
1
%.
Sh
iv
am
an
d
Ku
m
ar
[
1
8
]
in
v
esti
g
ated
p
r
e
-
tr
ain
ed
C
NN
m
o
d
els
s
u
ch
as
VGG
-
1
9
,
L
e
Net5
,
an
d
Mo
b
ileNet
-
V2
to
i
d
en
tify
in
f
ec
ted
r
ice
p
lan
ts
.
T
h
ey
s
tu
d
ied
two
cl
ass
es
(
in
f
ec
ted
leav
es
an
d
h
ea
lth
y
)
u
s
in
g
2
2
1
2
im
ag
es.
T
h
eir
ex
p
e
r
im
en
ts
ac
h
iev
ed
7
7
.
0
9
%,
7
6
.
6
3
%,
a
n
d
7
6
.
9
2
%
ac
cu
r
ac
y
f
o
r
VGG
-
1
9
,
L
eNe
t5
,
a
n
d
M
o
b
ileNet
-
V2
,
r
esp
ec
tiv
ely
.
Sh
ah
et
a
l
.
[
1
9
]
co
m
p
ar
e
d
t
h
e
p
e
r
f
o
r
m
an
ce
o
f
d
ee
p
lear
n
in
g
m
o
d
els,
i
n
clu
d
in
g
I
n
ce
p
tio
n
v
3
,
VGG
-
16
,
VGG
-
19
,
C
NN,
an
d
R
es
Net5
0
,
o
n
2
,
0
0
0
im
ag
es
f
o
r
r
ice
d
i
s
ea
s
e
cla
s
s
if
icatio
n
.
T
h
eir
an
aly
s
is
d
em
o
n
s
tr
ated
th
at
VGG
-
19
h
a
d
h
ig
h
est
ac
h
i
ev
em
en
t
an
ac
cu
r
ac
y
o
f
9
8
.
5
6
%.
I
q
b
al
et
a
l
.
[
2
0
]
f
o
cu
s
ed
o
n
th
e
ea
r
ly
d
etec
tio
n
o
f
r
ice
d
is
ea
s
es
u
s
in
g
I
n
ce
p
tio
n
v
3
an
d
VGG
-
19
m
o
d
els.
T
h
eir
r
esear
ch
ac
h
iev
ed
an
im
p
r
ess
iv
e
ac
cu
r
ac
y
o
f
9
7
.
9
4
%
with
VGG
-
19
.
L
win
a
n
d
Htwe
[
2
1
]
a
p
p
lied
Alex
Net
f
o
r
r
ice
leaf
d
is
ea
s
e
class
if
ica
tio
n
an
d
co
m
p
ar
ed
with
VGG
-
1
6
.
I
n
th
eir
a
n
aly
s
is
,
th
e
o
p
en
d
ataset
g
o
t
th
e
h
ig
h
est
ac
c
u
r
ac
y
.
W
an
g
et
a
l
.
[
2
2
]
p
r
o
p
o
s
ed
a
lig
h
tweig
h
t
en
s
em
b
le
d
ee
p
lear
n
in
g
m
o
d
el
u
s
in
g
atten
tio
n
-
en
h
an
ce
d
E
f
f
icien
tNet
with
s
tack
ed
lo
g
is
tic
r
eg
r
ess
io
n
f
o
r
class
if
y
in
g
f
iv
e
r
ice
d
is
ea
s
es,
ac
h
iev
in
g
9
6
.
1
0
%
ac
c
u
r
ac
y
wh
ile
o
u
tp
e
r
f
o
r
m
in
g
VGG
-
16
,
R
esNet1
0
1
,
an
d
Den
s
eNe
t2
0
1
with
lo
w
co
m
p
u
tatio
n
al
co
s
t.
Pen
g
et
a
l
.
[
2
3
]
p
r
o
p
o
s
ed
a
m
u
tu
al
in
f
o
r
m
atio
n
–
b
ased
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
u
s
in
g
th
e
m
in
im
al
-
r
ed
u
n
d
an
cy
–
m
ax
im
al
-
r
ele
v
an
ce
(
m
R
MR)
cr
iter
io
n
,
wh
ic
h
en
h
an
ce
s
class
if
icatio
n
p
er
f
o
r
m
an
ce
b
y
s
elec
tin
g
f
ea
tu
r
es
th
at
m
ax
im
ize
r
elev
an
ce
an
d
m
in
i
m
ize
r
e
d
u
n
d
an
cy
.
Prity
et
a
l
.
[
2
4
]
p
r
o
p
o
s
e
d
a
n
eu
r
al
n
etwo
r
k
ap
p
r
o
ac
h
f
o
r
r
ice
leaf
d
is
ea
s
e
r
ec
o
g
n
itio
n
u
s
in
g
f
ea
tu
r
e
ex
tr
ac
tio
n
,
d
im
en
s
io
n
ality
r
ed
u
ct
io
n
,
an
d
s
elec
tio
n
with
an
ex
tr
em
e
lear
n
in
g
m
a
ch
in
e
class
if
ier
o
n
3
,
8
2
9
im
a
g
es,
s
h
o
win
g
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
o
v
er
d
ir
ec
t
im
ag
e
-
b
ased
m
eth
o
d
s
,
with
Gr
ad
-
C
AM
en
h
an
cin
g
in
ter
p
r
et
ab
ilit
y
.
Pen
g
et
a
l
.
[
2
5
]
in
tr
o
d
u
ce
d
R
iceD
R
A
-
Net,
a
r
esid
u
al
d
ee
p
lear
n
in
g
ar
ch
it
ec
tu
r
e
d
esig
n
e
d
f
o
r
r
ice
leaf
d
is
ea
s
e
r
ec
o
g
n
itio
n
.
T
h
e
m
o
d
el
was
ev
alu
ated
o
n
b
o
th
s
im
p
le
an
d
co
m
p
lex
b
ac
k
g
r
o
u
n
d
d
atasets
,
wh
er
e
it
ac
c
u
r
ately
class
if
ied
f
o
u
r
r
ice
lea
f
d
is
ea
s
e
ca
teg
o
r
ies
an
d
ac
h
iev
e
d
r
ec
o
g
n
itio
n
r
ates o
f
9
9
.
7
1
% a
n
d
9
7
.
8
6
%,
r
esp
e
ctiv
ely
.
Acc
o
r
d
in
g
t
o
o
u
r
s
tu
d
y
,
m
o
s
t
r
esear
ch
er
s
f
o
c
u
s
ed
o
n
o
n
l
y
r
ice
leav
es
d
is
ea
s
es
an
d
u
p
t
o
f
iv
e
r
ice
d
is
ea
s
es.
T
h
ey
ap
p
lied
C
NN,
th
e
o
r
ig
in
al
VGG
m
o
d
els
o
r
en
s
em
b
le
m
o
d
el
to
tr
ain
Kag
g
le
d
ataset.
T
h
ey
u
tili
ze
d
th
e
clea
n
im
ag
es
o
r
alr
ea
d
y
s
eg
m
en
ted
im
ag
es
to
tr
ain
in
g
m
o
d
el.
So
m
e
class
if
icatio
n
m
o
d
els
ca
n
h
an
d
le
o
n
ly
s
in
g
le
b
ac
k
g
r
o
u
n
d
im
ag
es.
T
h
ey
ev
alu
ated
t
h
eir
m
o
d
els
with
th
e
s
p
ec
if
ic
co
n
d
itio
n
s
s
u
ch
as
s
in
g
le
b
ac
k
g
r
o
u
n
d
im
a
g
es
o
r
co
m
p
lex
b
ac
k
g
r
o
u
n
d
im
a
g
e
s
.
T
h
er
ef
o
r
e,
o
u
r
r
esear
ch
ta
r
g
ets
to
d
etec
t
an
d
class
if
y
s
ev
en
class
e
s
o
f
r
ice
d
is
ea
s
es
in
clu
d
in
g
h
ea
lth
y
cla
s
s
.
Ou
r
p
r
o
p
o
s
ed
m
o
d
el
h
an
d
l
es
r
ice
d
is
ea
s
es
n
o
t
o
n
ly
o
n
leav
es
b
u
t
also
o
n
wh
o
le
p
lan
t
in
clu
d
in
g
r
ice
s
ee
d
s
.
I
t
m
o
d
if
ies
th
e
o
r
ig
i
n
al
VGG
-
1
9
m
o
d
el
th
at
is
tr
ain
ed
with
th
e
co
m
b
in
atio
n
o
f
Kag
g
le
an
d
o
wn
d
ataset.
Ou
r
m
o
d
el
ca
n
m
a
n
ip
u
late
th
e
c
o
m
p
lex
b
ac
k
g
r
o
u
n
d
im
ag
es
b
y
u
tili
za
tio
n
o
f
im
a
g
e
s
eg
m
en
tatio
n
alg
o
r
ith
m
s
;
m
ix
tu
r
e
o
f
Gau
s
s
ian
s
2
(
MO
G2
)
an
d
Gr
a
b
C
u
t
.
Mo
r
eo
v
er
,
in
th
e
p
r
o
p
o
s
ed
m
o
d
el,
r
elev
an
ce
esti
m
atio
n
with
lin
ea
r
f
ea
t
u
r
e
(
R
E
L
I
E
F)
is
in
teg
r
ated
to
th
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
th
at
ca
n
g
en
er
ate
th
e
m
o
s
t
r
elev
an
t
f
ea
tu
r
es
th
an
th
e
f
ea
tu
r
es
g
en
er
ated
f
r
o
m
th
e
o
r
ig
in
al
VGG
-
19
m
o
d
el.
T
h
e
r
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
m
o
d
el
o
f
f
er
s
a
r
o
b
u
s
t,
r
eliab
le
an
d
ef
f
ec
tiv
e
s
o
lu
tio
n
f
o
r
r
ice
d
is
ea
s
e
class
if
icatio
n
an
d
h
elp
f
a
r
m
er
s
to
p
r
o
tect
th
eir
cr
o
p
s
an
d
in
cr
ea
s
e
y
ield
s
.
I
t
also
ac
h
iev
ed
th
e
h
ig
h
ac
cu
r
ac
y
th
an
o
th
er
p
r
e
v
io
u
s
r
esear
ch
es.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
o
n
e
o
f
th
e
ar
tific
ial
in
te
llig
en
ce
s
(
AI
)
p
lu
s
ag
r
icu
ltu
r
e
to
o
ls
to
im
p
r
o
v
e
th
e
r
ice
p
r
o
d
u
ctio
n
o
f
E
aster
n
Sh
an
State.
M
o
r
eo
v
er
,
it
is
also
a
f
u
lf
illme
n
t
o
f
th
e
g
ap
b
etwe
en
t
h
e
ag
r
icu
ltu
r
e
s
ec
to
r
an
d
f
ar
m
er
s
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
tr
ain
ed
b
y
u
s
in
g
th
e
c
o
m
b
in
ati
o
n
o
f
two
d
ata
s
o
u
r
ce
s
:
Kag
g
le
d
ataset
an
d
o
wn
d
ataset.
T
h
e
o
wn
d
ataset
is
m
an
u
ally
co
llected
f
r
o
m
E
a
s
ter
n
Sh
an
State,
My
an
m
ar
a
n
d
v
alid
ated
b
y
th
e
Ag
r
icu
ltu
r
al
R
esear
ch
Dep
ar
t
m
en
t
o
f
Ky
ain
g
T
o
n
g
.
T
h
e
im
ag
es
wer
e
tak
e
n
u
n
d
e
r
r
ea
l
-
wo
r
ld
c
o
n
d
itio
n
s
with
d
if
f
er
en
t
b
ac
k
g
r
o
u
n
d
s
an
d
lig
h
tin
g
.
T
h
e
d
ataset
co
n
s
is
ts
o
f
s
ix
r
ice
d
is
ea
s
es
o
f
d
if
f
er
e
n
t
ty
p
es
an
d
h
ea
lth
y
p
lan
ts
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
c
an
h
an
d
le
b
o
th
c
o
m
p
le
x
b
ac
k
g
r
o
u
n
d
an
d
s
in
g
le
b
ac
k
g
r
o
u
n
d
im
ag
es.
T
h
e
d
etail
in
f
o
r
m
atio
n
o
f
d
ataset
is
d
escr
ib
ed
in
T
ab
le
1
.
T
ab
le
1
.
Data
d
is
tr
ib
u
tio
n
in
r
i
ce
p
lan
t d
is
ea
s
e
d
atasets
No
Ty
p
e
s
o
f
d
i
s
e
a
s
e
s
N
u
mb
e
r
o
f
i
m
a
g
e
s
K
a
g
g
l
e
d
a
t
a
se
t
Ea
st
e
r
n
-
S
h
a
n
S
t
a
t
e
d
a
t
a
se
t
1
Le
a
f
sm
u
t
40
30
10
2
B
r
o
w
n
s
p
o
t
1
,
6
1
0
1
,
0
6
0
5
5
0
3
S
h
e
a
t
h
r
o
t
1
0
0
70
30
4
S
t
e
m r
o
t
6
9
4
4
0
0
2
9
4
5
Tu
n
g
r
o
1
,
2
9
8
1
,
0
0
0
2
9
8
6
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
1
,
5
8
4
1
,
0
0
0
5
8
4
7
H
e
a
l
t
h
y
1
,
0
0
0
5
0
0
5
0
0
To
t
a
l
6
,
3
2
6
4
,
0
6
0
2
,
2
6
6
T
h
e
im
ag
es
o
f
s
ix
c
o
m
m
o
n
r
ice
d
is
ea
s
es
ar
e
s
h
o
w
n
in
F
ig
u
r
e
1
.
B
r
o
wn
s
p
o
t
d
is
ea
s
e,
s
h
o
wn
in
Fig
u
r
e
1
(
a)
,
is
ch
a
r
ac
ter
ized
b
y
s
m
all
to
m
ed
iu
m
cir
c
u
la
r
o
r
o
v
al
lesi
o
n
s
with
d
ar
k
b
r
o
wn
ce
n
te
r
s
an
d
y
ello
wis
h
h
alo
s
th
at
m
a
y
co
al
esce
an
d
lead
t
o
ex
ten
s
iv
e
leaf
n
ec
r
o
s
is
.
Fig
u
r
e
1
(
b
)
s
h
o
ws
s
h
ea
th
r
o
t
d
is
ea
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
6
9
1
-
1
7
0
0
1694
af
f
ec
tin
g
th
e
leaf
s
h
ea
th
n
ea
r
th
e
p
an
icle,
ch
a
r
ac
ter
ized
b
y
ir
r
eg
u
lar
b
r
o
wn
to
d
ar
k
r
ed
d
is
h
lesi
o
n
s
with
tis
s
u
e
s
o
f
ten
in
g
th
at
ca
n
h
in
d
e
r
n
o
r
m
al
p
a
n
icle
em
er
g
en
ce
.
S
tem
r
o
t d
is
ea
s
e,
s
h
o
wn
in
Fig
u
r
e
1
(
c)
,
af
f
ec
ts
th
e
b
asal
s
tem
an
d
lo
wer
leaf
s
h
e
ath
,
p
r
esen
tin
g
d
ar
k
b
r
o
wn
t
o
b
lack
lesi
o
n
s
,
tis
s
u
e
d
ec
ay
,
a
n
d
s
tem
wea
k
en
in
g
th
at
m
ay
ca
u
s
e
lo
d
g
in
g
in
s
ev
er
e
ca
s
es.
Fig
u
r
e
1
(
d
)
il
lu
s
tr
ates
t
u
n
g
r
o
d
is
ea
s
e,
wh
ich
is
m
ar
k
e
d
b
y
y
ello
w
-
to
-
o
r
a
n
g
e
leaf
d
is
co
lo
r
atio
n
in
itiatin
g
at
t
h
e
leaf
ti
p
s
an
d
m
ar
g
in
s
,
as
well
as
s
tu
n
ted
g
r
o
wth
an
d
d
ec
r
ea
s
ed
till
er
in
g
.
Fig
u
r
e
1
(
e
)
s
h
o
ws
b
ac
ter
ial
leaf
b
lig
h
t,
c
h
ar
ac
ter
ized
b
y
lo
n
g
,
lin
ea
r
wate
r
-
s
o
ak
ed
lesi
o
n
s
f
r
o
m
th
e
leaf
m
a
r
g
in
s
to
th
e
m
id
r
ib
th
at
t
u
r
n
y
ello
wis
h
-
wh
ite
as
th
e
d
is
ea
s
e
p
r
o
g
r
ess
es.
L
ea
f
s
m
u
t
d
is
ea
s
e,
s
h
o
wn
in
Fig
u
r
e
1
(
f
)
,
is
id
en
tifie
d
b
y
n
ar
r
o
w,
elo
n
g
ated
d
ar
k
b
r
o
wn
to
b
lac
k
s
tr
ea
k
s
alo
n
g
th
e
leaf
v
ein
s
,
wh
ich
ar
e
s
lig
h
tly
r
aised
a
n
d
d
is
tin
ct
f
r
o
m
cir
cu
lar
lesi
o
n
s
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(f)
Fig
u
r
e
1
.
Sam
p
le
im
a
g
es f
o
r
d
if
f
er
en
t
ty
p
es
o
f
r
ice
p
lan
t d
is
ea
s
es
f
o
r
(
a)
b
r
o
wn
s
p
o
t,
(
b
)
s
h
ea
th
r
o
t,
(
c)
s
tem
r
o
t,
(
d
)
tu
n
g
r
o
,
(
e)
b
a
cter
ial
leaf
b
lig
h
t,
an
d
(
f
)
leaf
s
m
u
t
2.
M
E
T
H
O
D
No
wad
ay
s
,
My
an
m
ar
’
s
Ag
r
i
T
ec
h
s
ec
to
r
is
im
p
r
o
v
e
d
b
y
u
s
in
g
AI
tech
n
o
l
o
g
y
t
o
im
p
r
o
v
e
f
ar
m
i
n
g
p
r
ac
tices,
en
h
an
ce
ef
f
icien
cy
,
an
d
p
r
o
m
o
te
s
u
s
tain
ab
ilit
y
ac
r
o
s
s
th
e
f
o
o
d
s
u
p
p
ly
ch
ain
.
I
t
i
n
clu
d
es
m
an
y
ar
ea
s
lik
e
p
r
ed
ictio
n
in
f
a
r
m
in
g
,
d
a
ta
an
aly
tics
,
au
to
m
atic
d
etec
ti
o
n
an
d
class
if
icatio
n
f
o
r
d
is
ea
s
es.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
u
s
es
a
5
-
f
o
ld
n
ested
cr
o
s
s
-
v
alid
atio
n
tech
n
iq
u
e,
with
ea
ch
f
o
ld
u
s
in
g
8
0
%
o
f
t
h
e
d
ata
f
o
r
tr
ain
in
g
(
ap
p
r
o
x
im
ately
5
,
0
6
0
im
ag
es
)
an
d
2
0
%
f
o
r
test
in
g
(
ap
p
r
o
x
im
ately
1
,
2
6
6
im
ag
es),
en
s
u
r
in
g
r
eliab
le
m
o
d
el
ev
alu
atio
n
an
d
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
em
en
t.
T
h
is
r
esear
ch
in
ten
d
s
to
co
n
tr
ib
u
te
to
th
e
Ag
r
iTe
ch
s
e
cto
r
b
y
im
p
lem
en
tin
g
th
e
r
i
ce
d
is
ea
s
e
s
class
if
icatio
n
m
o
d
el
wh
ich
u
tili
ze
s
th
e
d
ee
p
lear
n
in
g
.
I
t
s
u
p
p
o
r
ts
f
o
r
im
p
r
o
v
in
g
f
ar
m
in
g
p
r
ac
tices
an
d
ef
f
icien
cy
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
b
ased
o
n
th
e
o
r
ig
i
n
al
VGG
-
19
m
o
d
el
th
at
i
n
clu
d
es
th
r
ee
s
tep
s
:
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
e
x
tr
ac
t
io
n
,
an
d
class
if
icatio
n
.
W
e
in
teg
r
ate
th
e
im
ag
e
s
eg
m
en
tati
o
n
to
p
r
ep
r
o
ce
s
s
in
g
s
tep
an
d
f
ea
tu
r
e
s
elec
tio
n
is
ad
d
ed
b
etwe
en
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
class
if
icatio
n
s
tep
.
T
h
e
co
m
p
lete
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
is
s
h
o
wn
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
Pro
p
o
s
ed
s
y
s
tem
f
o
r
r
ice
p
lan
t d
is
ea
s
es c
lass
if
icati
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
h
a
n
ce
d
V
GG
-
1
9
mo
d
el
fo
r
r
ice
p
la
n
t d
is
ea
s
e
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
(
A
ye
Th
id
a
Wi
n
)
1695
2
.
1
.
P
re
pro
ce
s
s
ing
T
h
i
s
s
t
a
g
e
i
s
p
e
r
f
o
r
m
e
d
t
o
e
n
s
u
r
e
d
a
t
a
q
u
a
l
i
t
y
a
n
d
u
p
g
r
a
d
e
t
h
e
a
c
c
u
r
a
c
y
o
f
t
r
a
i
n
i
n
g
m
o
d
e
l
.
I
t
i
n
c
l
u
d
e
s
i
m
a
g
e
r
e
s
i
z
i
n
g
t
o
t
r
a
n
s
f
o
r
m
t
h
e
s
a
m
e
d
i
m
e
n
s
i
o
n
s
(
2
2
4
×
2
2
4
)
o
f
a
l
l
i
n
p
u
t
i
m
a
g
e
s
,
n
o
r
m
a
l
i
z
a
t
i
o
n
,
a
u
g
m
e
n
t
a
t
i
o
n
s
u
c
h
a
s
f
l
i
p
p
i
n
g
,
r
e
s
c
a
l
i
n
g
,
z
o
o
m
i
n
g
,
r
o
t
a
t
i
o
n
t
o
i
m
p
r
o
v
e
m
o
d
e
l
g
e
n
e
r
a
l
i
z
a
t
i
o
n
,
c
o
l
o
r
c
h
a
n
n
e
l
s
t
a
n
d
a
r
d
i
z
a
t
i
o
n
,
a
n
d
t
r
a
n
s
f
o
r
m
a
t
i
o
n
s
t
o
g
e
t
t
h
e
c
o
m
p
a
t
i
b
l
e
f
o
r
m
a
t
o
f
t
e
n
s
o
r
.
T
h
e
p
r
e
p
r
o
c
e
s
s
e
d
i
m
a
g
e
s
a
r
e
d
e
s
c
r
i
b
e
d
i
n
F
i
g
u
r
e
3
.
O
n
e
o
f
t
h
e
m
o
s
t
i
m
p
o
r
t
a
n
t
s
t
e
p
s
i
n
t
h
e
p
r
e
p
r
o
c
e
s
s
i
n
g
o
f
t
h
e
r
i
c
e
p
l
a
n
t
d
i
s
e
a
s
e
i
s
r
e
m
o
v
i
n
g
i
r
r
e
l
e
v
a
n
t
b
a
c
k
g
r
o
u
n
d
.
H
o
w
e
v
e
r
,
r
e
m
o
v
i
n
g
f
o
r
e
g
r
o
u
n
d
a
n
d
b
a
c
k
g
r
o
u
n
d
p
r
o
c
e
s
s
e
s
i
s
n
o
t
p
r
o
v
i
d
e
d
i
n
t
h
e
o
r
i
g
i
n
a
l
V
G
G
-
19
m
o
d
e
l
.
F
o
r
i
m
a
g
e
s
e
g
m
e
n
t
a
t
i
o
n
o
f
t
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l
,
M
O
G
2
a
n
d
G
r
a
b
C
u
t
a
l
g
o
r
i
t
h
m
s
a
r
e
e
m
b
e
d
d
e
d
i
n
t
h
e
p
r
e
p
r
o
c
e
s
s
i
n
g
s
t
a
g
e
t
o
h
a
n
d
l
e
t
h
e
c
o
m
p
l
e
x
b
a
c
k
g
r
o
u
n
d
i
m
a
g
e
s
,
t
o
o
b
t
a
i
n
t
h
e
m
e
a
n
i
n
g
f
u
l
r
e
g
i
o
n
s
o
r
s
e
g
m
e
n
t
s
,
t
o
e
n
a
b
l
e
m
o
r
e
d
e
t
a
i
l
e
d
a
n
a
l
y
s
i
s
,
t
o
u
n
d
e
r
s
t
a
n
d
t
h
e
i
m
a
g
e
c
o
n
t
e
n
t
a
n
d
d
i
s
e
a
s
e
r
e
g
i
o
n
s
.
T
h
e
y
o
f
f
e
r
t
h
e
d
e
t
a
i
l
a
n
a
l
y
s
i
s
o
f
i
m
a
g
e
c
o
n
t
e
n
t
s
f
r
o
m
t
h
e
i
m
a
g
e
s
h
a
s
b
a
c
k
g
r
o
u
n
d
n
o
i
s
e
a
n
d
f
o
r
e
g
r
o
u
n
d
n
o
i
s
e
t
h
a
t
c
o
n
f
u
s
e
s
t
h
e
m
o
d
e
l
w
h
e
n
s
t
a
n
d
a
r
d
i
z
e
t
h
e
i
n
p
u
t
i
m
a
g
e
s
.
M
O
G
2
i
s
a
n
a
d
a
p
t
i
v
e
b
a
c
k
g
r
o
u
n
d
s
u
b
t
r
a
c
t
i
o
n
m
e
t
h
o
d
t
h
a
t
e
f
f
i
c
i
e
n
t
l
y
h
a
n
d
l
e
s
n
o
i
s
e
,
l
i
g
h
t
i
n
g
c
h
a
n
g
e
s
,
a
n
d
s
h
a
d
o
w
s
,
m
a
k
i
n
g
i
t
s
u
i
t
a
b
l
e
f
o
r
i
m
a
g
e
s
w
i
t
h
c
o
m
p
l
e
x
o
r
u
n
c
o
n
t
r
o
l
l
e
d
b
a
c
k
g
r
o
u
n
d
s
,
w
h
i
l
e
G
r
a
b
C
u
t
r
e
f
i
n
e
s
f
o
r
e
g
r
o
u
n
d
e
x
t
r
a
c
t
i
o
n
i
t
e
r
a
t
i
v
e
l
y
t
o
r
e
m
o
v
e
i
r
r
e
l
e
v
a
n
t
i
n
f
o
r
m
a
t
i
o
n
a
n
d
p
r
o
d
u
c
e
c
l
e
a
n
,
f
o
c
u
s
e
d
i
m
a
g
e
s
t
h
a
t
e
n
h
a
n
c
e
t
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l
’
s
p
e
r
f
o
r
m
a
n
c
e
;
t
h
e
p
r
e
p
r
o
c
e
s
s
e
d
o
u
t
p
u
t
s
a
r
e
s
h
o
w
n
i
n
F
i
g
u
r
e
4
.
Fig
u
r
e
3
.
E
x
am
p
les o
f
au
g
m
e
n
ted
im
ag
es
Fig
u
r
e
4
.
C
o
m
p
a
r
is
o
n
o
f
r
esu
l
ted
im
ag
es a
f
ter
b
ac
k
g
r
o
u
n
d
r
em
o
v
al,
f
o
r
eg
r
o
u
n
d
ex
tr
ac
tio
n
,
an
d
f
ea
t
u
r
e
s
elec
tio
n
p
r
o
ce
s
s
2
.
2
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
T
h
e
VGG
-
19
m
o
d
el,
p
r
e
-
tr
ai
n
ed
o
n
th
e
I
m
a
g
eNe
t
d
ataset,
ca
n
b
e
u
s
ed
f
o
r
f
ea
tu
r
e
e
x
t
r
ac
tio
n
b
y
ex
tr
ac
tin
g
f
ea
tu
r
es
f
r
o
m
in
ter
m
ed
iate
lay
er
s
o
f
th
e
n
etwo
r
k
.
T
h
is
ap
p
r
o
ac
h
allo
ws
th
e
m
o
d
el
to
lev
er
ag
e
th
e
lear
n
ed
r
ep
r
esen
tatio
n
s
o
f
th
e
m
o
d
el
with
o
u
t
n
ee
d
in
g
to
r
etr
ain
th
e
en
tire
n
etwo
r
k
.
T
h
ese
ex
tr
ac
ted
f
ea
tu
r
es
s
er
v
e
as
h
ig
h
-
lev
el
im
ag
e
d
e
s
cr
ip
to
r
s
th
at
im
p
r
o
v
e
th
e
cl
ass
if
icatio
n
ac
cu
r
ac
y
o
f
r
ice
p
lan
t
d
is
ea
s
es
an
d
r
ed
u
ce
co
m
p
u
tatio
n
al
co
s
t.
2
.
3
.
F
e
a
t
ure
s
elec
t
io
n
T
o
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
VGG
-
19
m
o
d
el
an
d
r
ed
u
ce
d
im
en
s
io
n
ality
,
f
ea
tu
r
e
s
elec
tio
n
s
tep
is
ad
d
ed
to
th
e
o
r
ig
in
al
VGG
-
19
m
o
d
el
b
ec
a
u
s
e
it
is
n
o
t
s
u
p
p
o
r
ted
in
th
e
o
r
ig
in
al
VGG
-
19
m
o
d
el.
T
h
er
e
ar
e
m
an
y
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
s
s
u
ch
as
m
u
tu
al
in
f
o
r
m
ati
o
n
,
an
al
y
s
is
o
f
v
ar
ian
ce
(
ANOVA
)
,
least
ab
s
o
lu
te
s
h
r
in
k
ag
e
an
d
s
elec
tio
n
o
p
er
a
to
r
(
L
ASSO
),
an
d
R
E
L
I
E
F
to
f
in
d
th
e
b
est
s
et
o
f
f
ea
tu
r
es
th
at
allo
ws
o
n
e
to
b
u
ild
o
p
tim
ized
th
e
class
if
icatio
n
m
o
d
el.
T
ab
le
2
illu
s
tr
ates
th
e
n
u
m
b
er
o
f
s
elec
ted
f
ea
tu
r
es
f
o
r
ea
ch
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e.
Acc
o
r
d
in
g
to
th
e
ex
p
er
im
en
tal
r
esu
lts
o
f
f
ea
tu
r
e
s
elec
tio
n
,
th
e
VG
G
-
19
m
o
d
el
alo
n
e
ex
tr
ac
ts
th
e
h
ig
h
est n
u
m
b
er
o
f
f
ea
tu
r
es (
3
0
,
3
6
0
)
,
wh
ile
ap
p
ly
in
g
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
s
r
ed
u
ce
s
th
e
f
ea
tu
r
e
co
u
n
t
s
ig
n
if
ican
tly
.
Am
o
n
g
th
ese,
VGG
-
19
+L
ASSO
s
elec
ts
th
e
f
ewe
s
t
f
ea
tu
r
es
(
2
4
,
2
0
0
)
,
f
o
llo
wed
clo
s
ely
b
y
VGG
-
19
+
R
E
L
I
E
F
(
2
5
,
3
0
0
)
,
d
em
o
n
s
tr
atin
g
th
eir
ef
f
ec
tiv
en
e
s
s
in
r
ed
u
cin
g
d
im
e
n
s
io
n
ality
.
T
h
is
r
ed
u
ctio
n
ca
n
lead
to
m
o
r
e
ef
f
icie
n
t
an
d
s
ca
lab
le
class
if
icatio
n
m
o
d
els
with
o
u
t
s
u
b
s
tan
tial
lo
s
s
o
f
i
n
f
o
r
m
atio
n
,
h
ig
h
lig
h
tin
g
th
e
ad
v
an
ta
g
e
o
f
c
o
m
b
in
i
n
g
V
GG
-
19
with
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
6
9
1
-
1
7
0
0
1696
T
ab
le
2
.
Nu
m
b
er
o
f
s
elec
ted
f
ea
tu
r
es
C
o
m
b
i
n
a
t
i
o
n
o
f
m
o
d
e
l
a
n
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
met
h
o
d
N
u
mb
e
r
o
f
se
l
e
c
t
e
d
f
e
a
t
u
r
e
s
sh
a
p
e
VGG
-
19
3
0
,
3
6
0
VGG
-
1
9
+
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
s
i
s (P
C
A
)
2
8
,
3
6
0
VGG
-
1
9
+
R
ELI
EF
2
5
,
3
0
0
VGG
-
1
9
+
M
u
t
u
a
l
2
6
,
8
0
0
VGG
-
1
9
+
A
N
O
V
A
2
7
,
6
0
0
VGG
-
1
9
+
LA
S
S
O
2
4
,
2
0
0
B
ased
o
n
th
e
all
-
ex
p
e
r
im
en
ta
l
r
esu
lts
,
f
in
ally
o
u
r
p
r
o
p
o
s
e
d
m
o
d
el
u
tili
ze
s
R
E
L
I
E
F
alg
o
r
ith
m
f
o
r
f
ea
tu
r
e
s
elec
tio
n
.
I
t
e
v
alu
ates
ea
ch
f
ea
tu
r
e
b
y
h
o
w
well
it
d
i
s
tin
g
u
is
h
es
b
etwe
en
n
ea
r
in
s
ta
n
ce
s
(
n
eig
h
b
o
r
s
)
o
f
th
e
s
am
e
class
an
d
d
if
f
er
en
t
class
es.
Fo
r
ea
ch
in
s
tan
ce
,
it
i
d
en
tifie
s
th
e
n
ea
r
est
h
it
(
s
am
e
class
)
an
d
n
ea
r
est
m
is
s
(
d
if
f
er
en
t
class
)
,
u
p
d
atin
g
f
ea
tu
r
e
weig
h
ts
to
h
ig
h
lig
h
t
s
ig
n
if
ican
t
f
ea
tu
r
es
an
d
d
is
ca
r
d
less
im
p
o
r
ta
n
t
o
n
es.
I
t w
o
r
k
s
f
o
r
n
o
is
y
an
d
r
e
d
u
n
d
a
n
t d
ata
b
ec
a
u
s
e
it f
o
cu
s
e
s
o
n
lo
ca
l d
if
f
e
r
en
ce
s
.
2
.
4
.
Cla
s
s
if
ica
t
io
n
T
h
e
s
elec
ted
f
ea
tu
r
es a
r
e
u
s
ed
to
class
if
y
th
e
d
if
f
er
en
t ty
p
es o
f
r
ice
p
lan
t
d
is
ea
s
es.
T
h
e
f
in
al
lay
er
s
o
f
VGG
-
19
u
s
ed
th
e
s
elec
ted
f
e
atu
r
es
to
en
s
u
r
e
th
e
ac
cu
r
ac
y
o
f
class
if
icatio
n
o
f
s
ix
r
ice
d
is
ea
s
es
an
d
h
ea
lth
y
p
lan
ts
.
T
h
is
p
r
o
c
ess
en
h
an
ce
s
th
e
g
en
er
aliza
b
ilit
y
o
f
t
h
e
m
o
d
el
ac
r
o
s
s
d
if
f
er
en
t
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
an
d
co
m
p
lex
b
ac
k
g
r
o
u
n
d
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
o
p
r
o
v
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
,
it
is
test
ed
o
n
th
e
m
an
y
ex
p
e
r
im
en
t
s
s
u
ch
as
p
ar
am
eter
tu
r
n
in
g
,
f
ea
tu
r
e
ex
t
r
ac
tio
n
,
f
ea
tu
r
e
s
elec
tio
n
an
d
m
o
d
el
s
elec
tio
n
to
class
if
y
th
e
r
ice
d
is
ea
s
es.
T
h
ey
ar
e
test
ed
o
n
Go
o
g
le
C
o
lab
u
s
in
g
th
e
s
am
e
d
atasets
wh
ich
i
s
alr
ea
d
y
m
en
tio
n
ed
.
T
h
e
f
ir
s
t
ex
p
er
im
e
n
t
s
h
o
ws
th
e
tr
ain
in
g
an
d
v
alid
atio
n
l
o
s
s
o
f
p
r
o
p
o
s
ed
m
o
d
el
wh
ic
h
af
f
ec
ts
t
h
e
ac
c
u
r
ac
y
o
f
th
e
m
o
d
el.
T
h
e
b
est
p
ar
am
eter
s
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
ar
e
1
0
ep
o
ch
s
an
d
a
b
atch
s
ize
o
f
3
2
an
d
th
e
ex
p
e
r
im
en
tal
r
esu
lts
ar
e
s
h
o
wn
in
Fig
u
r
e
5
.
Fig
u
r
e
5
.
C
o
m
p
a
r
is
o
n
o
f
th
e
tr
ain
in
g
lo
s
s
an
d
v
alid
atio
n
lo
s
s
o
f
VGG
-
19
with
R
E
L
I
E
F
a
n
d
VGG
-
19
+PC
A
T
h
e
s
ec
o
n
d
ex
p
er
im
en
t
ev
alu
ates
th
e
g
en
e
r
aliza
tio
n
ca
p
ab
il
ity
o
f
VGG
-
19
co
m
b
i
n
ed
with
PC
A
an
d
R
E
L
I
E
F
f
ea
tu
r
e
s
elec
tio
n
.
T
h
e
r
esu
lts
s
h
o
w
th
at
b
o
th
tr
ain
in
g
an
d
v
alid
atio
n
lo
s
s
es
g
r
a
d
u
ally
d
ec
lin
e
a
n
d
co
n
v
er
g
e,
d
em
o
n
s
tr
atin
g
s
tab
l
e
lear
n
in
g
b
eh
av
io
r
.
T
h
e
clo
s
e
alig
n
m
en
t
b
etwe
en
th
e
two
lo
s
s
cu
r
v
es
in
d
icate
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
h
a
n
ce
d
V
GG
-
1
9
mo
d
el
fo
r
r
ice
p
la
n
t d
is
ea
s
e
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
(
A
ye
Th
id
a
Wi
n
)
1697
ef
f
ec
tiv
e
g
en
er
aliza
tio
n
to
u
n
s
ee
n
d
ata
an
d
co
n
f
i
r
m
s
th
at
th
e
m
o
d
els
d
o
n
o
t
s
u
f
f
er
f
r
o
m
o
v
er
f
itti
n
g
.
T
h
ey
ar
e
s
h
o
wn
in
Fig
u
r
e
s
6
an
d
7
.
T
h
e
VGG
-
19
with
R
E
L
I
E
F
h
as sm
aller
g
ap
th
a
n
VGG
-
19
with
PC
A.
Fig
u
r
e
6
.
Mo
d
el
g
en
e
r
aliza
tio
n
o
f
VGG
-
19
with
PC
A
Fig
u
r
e
7
.
Mo
d
el
g
en
e
r
aliza
tio
n
o
f
VGG
-
1
9
+REL
I
E
F
T
h
e
ex
p
er
im
e
n
tal
r
esu
lt
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
ev
alu
ated
with
n
ested
cr
o
s
s
-
v
alid
atio
n
m
eth
o
d
f
o
r
ea
ch
class
is
d
escr
ib
ed
in
T
ab
l
e
3
.
Of
th
e
s
ev
en
test
class
es,
t
h
e
b
r
o
w
n
s
p
o
t a
n
d
b
ac
ter
ial
b
l
ig
h
t a
r
e
lo
wer
th
a
n
th
e
o
th
er
r
esu
lts
.
T
h
e
ex
p
e
r
im
en
tal
r
esu
lt
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
f
o
r
ea
ch
class
is
d
escr
ib
ed
in
T
ab
le
3
.
T
h
e
f
in
al
ex
p
e
r
im
en
tal
r
esu
lt
is
o
b
tain
ed
b
y
co
m
p
ar
in
g
with
th
e
o
r
ig
in
al
VGG
-
1
9
,
i
n
teg
r
atio
n
o
f
VGG
-
1
9
wit
h
o
th
er
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
Mo
b
ileNetV3
,
E
f
f
icien
tNet
an
d
R
estNet5
0
.
T
h
e
r
esu
lts
o
f
th
ese
m
o
d
els
ar
e
s
h
o
wn
in
T
ab
le
4
.
T
ab
le
3
.
E
x
p
er
im
en
tal
r
esu
lt o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
(
VGG
-
19
+
R
E
L
I
E
F
)
f
o
r
ea
c
h
class
C
l
a
s
s
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
H
e
a
l
t
h
0
.
9
9
5
0
.
9
9
5
0
.
9
9
5
Le
a
f
sm
u
t
0
.
9
9
0
0
.
9
8
5
0
.
9
8
8
S
h
e
a
t
h
r
o
t
0
.
9
9
0
0
.
9
8
5
0
.
9
8
8
S
t
e
m r
o
t
0
.
9
8
5
0
.
9
8
5
0
.
9
8
5
Tu
n
g
r
o
0
.
9
8
0
0
.
9
8
0
0
.
9
8
0
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
0
.
9
7
0
0
.
9
7
5
0
.
9
7
2
B
r
o
w
n
s
p
o
t
0
.
9
7
5
0
.
9
7
0
0
.
9
7
2
M
a
c
r
o
a
v
e
r
a
g
e
0
.
9
8
4
0
.
9
8
2
0
.
9
8
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
6
9
1
-
1
7
0
0
1698
T
h
e
ex
p
e
r
im
en
tal
r
esu
lts
s
h
o
w
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
(
VGG
-
1
9
+REL
I
E
F)
ac
h
iev
ed
th
e
h
ig
h
est
r
esu
lt
o
f
0
.
9
8
3
,
wh
ile
E
f
f
icien
tNet
attain
ed
a
co
m
p
ar
ab
le
r
e
s
u
lt
o
f
0
.
9
7
7
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
co
n
s
id
er
ed
s
u
p
er
io
r
d
u
e
to
its
co
m
b
in
atio
n
o
f
h
ig
h
r
esu
lt
an
d
th
e
lo
west
s
tan
d
ar
d
d
ev
iatio
n
,
in
d
icatin
g
s
tab
le
an
d
r
eliab
le
p
er
f
o
r
m
an
ce
.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
at
th
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
o
u
tp
e
r
f
o
r
m
s
th
e
ex
is
tin
g
m
o
d
el
in
b
o
th
f
ea
tu
r
e
s
elec
tio
n
,
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
m
o
d
el
s
tab
ilit
y
an
d
r
eliab
ilit
y
.
T
ab
le
4
.
E
x
p
er
im
en
tal
r
esu
lt o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
(
VGG
-
19
+
R
E
L
I
E
F
)
an
d
o
t
h
er
m
o
d
els
M
o
d
e
l
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
M
o
b
i
l
e
N
e
t
V
3
0
.
9
5
2
0
.
9
6
7
0
.
9
5
6
0
.
0
0
6
Ef
f
i
c
i
e
n
t
N
e
t
0
.
9
7
6
0
.
9
8
1
0
.
9
7
7
0
.
0
0
5
R
e
st
N
e
t
5
0
0
.
9
7
3
0
.
9
8
1
0
.
9
7
6
0
.
0
0
4
VGG
-
1
9
+
R
ELI
EF+M
O
G
2
0
.
9
6
5
0
.
9
6
2
0
.
9
6
4
0
.
0
0
6
VGG
-
1
9
+
R
ELI
EF+G
r
a
b
C
u
t
0
.
9
7
1
0
.
9
6
9
0
.
9
7
4
0
.
0
0
5
VGG
-
1
9
+
M
u
t
u
a
l
+
M
O
G
2
+
G
r
a
b
C
u
t
0
.
9
7
2
0
.
9
6
9
0
.
9
8
4
0
.
0
0
5
VGG
-
1
9
+
A
N
O
V
A
+
M
O
G
2
+
G
r
a
b
C
u
t
0
.
9
6
6
0
.
9
6
3
0
.
9
7
1
0
.
0
0
7
VGG
-
1
9
+
LA
S
S
O
+
M
O
G
2
+
G
r
a
b
C
u
t
0
.
9
8
0
0
.
9
6
7
0
.
9
7
3
0
.
0
0
7
P
r
o
p
o
se
d
m
o
d
e
l
0
.
9
8
4
0
.
9
8
2
0
.
9
8
3
0
.
0
0
4
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
co
n
tr
ib
u
tes
Ag
r
i
-
T
ec
h
b
y
o
f
f
er
in
g
a
r
o
b
u
s
t
a
n
d
co
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
f
o
r
r
ice
p
lan
t
d
is
ea
s
e
ty
p
es,
u
ltima
tely
im
p
r
o
v
in
g
p
r
o
d
u
ctiv
ity
,
a
n
d
en
s
u
r
i
n
g
b
etter
c
r
o
p
h
ea
lth
.
W
e
ex
p
lo
r
ed
t
h
e
p
o
wer
o
f
d
ee
p
lear
n
i
n
g
an
d
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
f
o
r
r
ice
p
lan
t
d
is
ea
s
es
d
etec
tio
n
an
d
class
if
icatio
n
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
b
ased
o
n
a
DC
NN
(
VGG
-
19
)
.
I
t
is
in
t
eg
r
ated
th
e
im
ag
e
s
eg
m
en
tat
io
n
alg
o
r
ith
m
s
in
p
r
ep
r
o
ce
s
s
in
g
s
tep
an
d
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
af
ter
f
ea
tu
r
in
g
ex
tr
ac
tio
n
s
tep
.
I
t
also
p
r
o
v
id
es
th
e
co
m
p
r
eh
e
n
s
iv
e
class
if
icatio
n
an
d
h
elp
s
ea
r
ly
d
iag
n
o
s
is
.
I
t s
u
p
p
o
r
ts
th
e
im
p
r
o
v
em
en
t o
f
cr
o
p
m
an
ag
em
e
n
t a
n
d
p
r
ev
en
tio
n
o
f
s
ev
e
r
e
o
u
tb
r
ea
k
s
.
Mo
r
eo
v
er
,
it
ca
n
ac
cu
r
ately
id
en
tify
s
ix
d
if
f
er
e
n
t
ty
p
es
o
f
r
ice
p
lan
t
d
is
ea
s
es.
Acc
o
r
d
in
g
to
t
h
e
p
er
f
o
r
m
an
ce
an
aly
s
is
,
o
u
r
p
r
o
p
o
s
ed
m
o
d
el
is
a
r
o
b
u
s
t
m
o
d
el
f
o
r
r
ice
p
lan
t
d
is
ea
s
es
d
etec
tio
n
an
d
class
if
icatio
n
an
d
h
as
th
e
h
ig
h
est
r
esu
lt
o
f
9
8
.
3
%.
I
m
p
o
r
ta
n
tly
,
th
e
in
teg
r
ati
o
n
o
f
VGG
-
19
with
th
e
R
E
L
I
E
F
alg
o
r
ith
m
ac
h
ie
v
es
th
e
h
ig
h
est
class
if
icatio
n
ac
cu
r
ac
y
,
h
ig
h
lig
h
tin
g
th
e
e
f
f
ec
tiv
en
ess
o
f
th
e
o
p
tim
al
f
ea
tu
r
e
s
elec
tio
n
.
Ou
r
co
n
tr
ib
u
tio
n
ac
ts
as a
n
as
s
is
ta
n
t f
o
r
My
an
m
a
r
f
ar
m
er
s
an
d
o
f
f
er
s
a
s
ig
n
if
ican
tly
im
p
r
o
v
em
e
n
t to
My
a
n
m
ar
a
g
r
icu
ltu
r
al
s
ec
to
r
.
ACK
NO
WL
E
DG
M
E
N
T
S
W
e
ar
e
g
r
atef
u
l f
o
r
th
e
v
alu
ab
le
s
u
p
p
o
r
t a
n
d
r
eso
u
r
ce
s
p
r
o
v
i
d
ed
b
y
th
e
Natu
r
al
L
an
g
u
ag
e
Pro
ce
s
s
in
g
L
ab
o
f
th
e
U
n
iv
er
s
ity
o
f
C
o
m
p
u
ter
Stu
d
ies,
Ya
n
g
o
n
,
My
an
m
ar
.
W
e
wo
u
ld
lik
e
to
th
a
n
k
Dr
.
T
h
in
n
T
h
u
Nain
g
,
R
ec
to
r
o
f
Po
ly
tech
n
i
c
Un
iv
er
s
ity
(
Ky
ain
g
T
o
n
g
)
f
o
r
h
er
in
v
al
u
ab
le
en
co
u
r
ag
em
en
t
an
d
s
u
p
p
o
r
t
th
r
o
u
g
h
o
u
t
th
is
r
esear
c
h
e
n
d
e
av
o
r
.
W
e
s
in
ce
r
ely
ex
ten
d
o
u
r
h
ea
r
tf
elt
ap
p
r
ec
iatio
n
to
e
v
er
y
o
n
e
wh
o
s
u
p
p
o
r
ted
th
e
s
u
cc
ess
f
u
l c
o
m
p
letio
n
o
f
t
h
is
wo
r
k
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
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
Ay
e
T
h
id
a
W
in
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Kh
in
Ma
r
So
e
✓
✓
✓
✓
✓
✓
✓
My
in
t M
y
in
t L
win
✓
✓
✓
✓
✓
✓
✓
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
n
h
a
n
ce
d
V
GG
-
1
9
mo
d
el
fo
r
r
ice
p
la
n
t d
is
ea
s
e
d
etec
tio
n
a
n
d
cla
s
s
ifica
tio
n
(
A
ye
Th
id
a
Wi
n
)
1699
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
t
h
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
e
p
o
r
te
d
in
t
h
is
p
ap
er
.
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
T
h
is
s
tu
d
y
d
o
es
n
o
t
i
n
v
o
lv
e
h
u
m
an
p
a
r
ticip
an
ts
o
r
p
e
r
s
o
n
al
d
ata.
T
h
er
e
f
o
r
e,
i
n
f
o
r
m
ed
co
n
s
en
t
was
n
o
t r
eq
u
ir
ed
f
o
r
th
is
r
esear
ch
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
r
esear
ch
u
s
es
r
ice
leaf
im
ag
e
d
atasets
an
d
d
o
es
n
o
t
in
v
o
l
v
e
h
u
m
an
o
r
an
im
al
s
u
b
jects.
T
h
er
ef
o
r
e,
eth
ical
ap
p
r
o
v
al
f
r
o
m
an
in
s
titu
tio
n
al
r
ev
iew
b
o
ar
d
o
r
eth
ics co
m
m
ittee
was n
o
t
r
eq
u
ir
ed
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
u
s
ed
in
th
is
s
tu
d
y
wer
e
o
b
tain
ed
f
r
o
m
two
s
o
u
r
ce
s
:
a
p
u
b
licly
av
ailab
le
Kag
g
le
r
ice
leaf
d
is
ea
s
e
d
ataset
an
d
an
o
wn
d
a
taset
co
llected
f
r
o
m
r
ice
f
ield
s
in
E
aster
n
Sh
an
State,
My
an
m
ar
.
T
h
e
co
llected
d
ataset
was
o
b
tain
ed
with
p
er
m
is
s
io
n
f
r
o
m
th
e
r
ice
f
ield
o
wn
er
s
an
d
v
alid
ated
b
y
th
e
Ag
r
icu
ltu
r
al
R
esear
ch
Dep
ar
tm
en
t
o
f
Ky
ain
g
T
o
n
g
,
My
an
m
a
r
.
T
h
e
Kag
g
le
d
at
aset
is
p
u
b
licly
av
ailab
le
th
r
o
u
g
h
th
e
Kag
g
le
r
ep
o
s
ito
r
y
.
T
h
e
o
w
n
d
ataset
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
is
av
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
i
n
g
au
t
h
o
r
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est d
u
e
t
o
u
s
ag
e
p
er
m
is
s
io
n
s
an
d
lo
ca
l
d
ata
co
llectio
n
r
estrictio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
A
D
P
C
,
Ri
c
e
m
a
p
a
n
d
a
re
a
e
st
i
m
a
t
e
s
o
f
r
i
c
e
c
u
l
t
i
v
a
t
i
o
n
f
o
r
t
h
e
m
o
n
so
o
n
se
a
so
n
o
f
2
0
2
1
:
My
a
n
m
a
r
a
g
r
i
c
u
l
t
u
r
a
l
c
ro
p
y
i
e
l
d
e
st
i
m
a
t
i
o
n
p
r
o
j
e
c
t
,
M
y
a
n
mar
:
A
si
a
n
D
i
sast
e
r
P
r
e
p
a
r
e
d
n
e
ss
C
e
n
t
e
r
,
2
0
2
2
.
[
2
]
R
.
S
a
r
i
,
H
.
L
.
A
sb
u
d
i
,
a
n
d
F
.
E.
S
u
s
i
l
a
w
a
t
i
,
“
U
t
i
l
i
z
i
n
g
R
e
sN
e
t
-
5
0
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
r
i
c
e
l
e
a
f
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
,
”
Bri
l
l
i
a
n
c
e
:
Re
se
a
rc
h
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
1
2
5
8
–
1
2
6
8
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
4
7
7
0
9
/
b
r
i
l
l
i
a
n
c
e
.
v
5
i
2
.
7
4
2
5
.
[
3
]
S
.
V
i
j
a
y
a
n
a
n
d
C
.
L
.
C
h
o
w
d
h
a
r
y
,
“
H
y
b
r
i
d
f
e
a
t
u
r
e
o
p
t
i
mi
z
e
d
C
N
N
f
o
r
r
i
c
e
c
r
o
p
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
5
-
9
2
6
4
6
-
w.
[
4
]
K
.
U
.
K
.
R
o
d
r
i
g
o
,
J
.
H
.
H
.
S
.
M
a
r
c
i
a
l
,
S
.
C
.
B
r
i
l
l
o
,
K
.
E
.
M
a
t
a
,
a
n
d
J.
C
.
M
o
r
a
n
o
,
“
A
n
e
n
h
a
n
c
e
m
e
n
t
o
f
C
N
N
a
l
g
o
r
i
t
h
m
f
o
r
r
i
c
e
l
e
a
f
d
i
se
a
se
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
m
o
b
i
l
e
a
p
p
l
i
c
a
t
i
o
n
s
,
”
J
o
u
rn
a
l
o
f
I
n
f
o
r
m
a
t
i
o
n
S
y
st
e
m
s
E
n
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
1
0
,
n
o
.
6
s,
p
p
.
2
7
2
–
2
8
1
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
5
2
7
8
3
/
j
i
sem
.
v
1
0
i
6
s.
7
2
0
.
[
5
]
M
.
S
.
I
.
S
o
b
u
j
,
M
.
I
.
H
o
sse
n
,
M
.
F
.
M
a
h
m
u
d
,
a
n
d
M
.
U
.
I
.
K
h
a
n
,
“
L
e
v
e
r
a
g
i
n
g
p
r
e
-
t
r
a
i
n
e
d
C
N
N
s
f
o
r
e
f
f
i
c
i
e
n
t
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
i
n
r
i
c
e
l
e
a
f
d
i
sea
se
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
2
0
2
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
,
El
e
c
t
ri
c
a
l
,
a
n
d
S
m
a
r
t
S
y
s
t
e
m
s (
i
C
A
C
C
ES
S
)
,
M
a
r
.
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
C
A
C
C
ESS
6
1
7
3
5
.
2
0
2
4
.
1
0
4
9
9
6
0
3
.
[
6
]
M
.
M
i
s
b
a
,
A
.
V
i
v
e
k
,
R
.
R
a
t
h
e
e
s
h
,
C
.
A
s
l
i
n
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
b
a
s
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
d
i
se
a
ses
f
o
r
r
i
c
e
l
e
a
f
u
si
n
g
C
N
N
mo
d
e
l
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
c
i
e
n
t
i
f
i
c
I
n
n
o
v
a
t
i
o
n
s
i
n
S
c
i
e
n
c
e
,
T
e
c
h
n
o
l
o
g
y
,
a
n
d
M
a
n
a
g
e
m
e
n
t
(
N
G
C
ES
l
-
2
0
2
3
)
,
A
u
g
.
2
0
2
3
,
p
p
.
3
0
8
-
3
1
6
,
d
o
i
:
1
0
.
5
9
5
4
4
/
X
V
TU
7
5
4
5
/
N
G
C
ESI
2
3
P
3
7
.
[
7
]
M
.
G
o
g
o
i
,
V
.
K
u
mar
,
S
.
B
e
g
u
m,
N
.
S
h
a
r
m
a
,
a
n
d
S
.
K
a
n
t
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
o
f
r
i
c
e
d
i
se
a
ses
u
si
n
g
a
3
-
st
a
g
e
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
A
g
ri
c
u
l
t
u
r
e
,
v
o
l
.
1
3
,
n
o
.
8
,
J
u
l
.
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
8
1
5
0
5
.
[
8
]
K
.
A
k
y
o
l
,
“
H
a
n
d
l
i
n
g
h
y
p
e
r
c
o
l
u
m
n
d
e
e
p
f
e
a
t
u
r
e
s
i
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
r
i
c
e
l
e
a
f
d
i
sea
s
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
2
,
n
o
.
1
3
,
p
p
.
1
9
5
0
3
–
1
9
5
2
0
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
022
-
1
4
3
1
8
-
5.
[
9
]
K
.
K
i
r
a
t
i
r
a
t
a
n
a
p
r
u
k
,
P
.
T
e
m
n
i
r
a
n
r
a
t
,
W
.
S
i
n
t
h
u
p
i
n
y
o
,
S
.
M
a
r
u
k
a
t
a
t
,
a
n
d
S
.
P
a
t
a
r
a
p
u
w
a
d
o
l
,
“
A
u
t
o
ma
t
i
c
d
e
t
e
c
t
i
o
n
o
f
r
i
c
e
d
i
se
a
se
i
n
i
ma
g
e
s
o
f
v
a
r
i
o
u
s
l
e
a
f
si
z
e
s,
”
I
ET
I
m
a
g
e
Pro
c
e
ss
i
n
g
,
v
o
l
.
1
9
,
n
o
.
1
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
4
9
/
i
p
r
2
.
1
3
3
0
1
.
[
1
0
]
R
.
Y
a
k
k
u
n
d
i
m
a
t
h
,
G
.
S
a
u
n
s
h
i
,
B
.
A
n
a
m
i
,
a
n
d
S
.
P
a
l
a
i
a
h
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
r
i
c
e
d
i
s
e
a
se
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
mo
d
e
l
s
,
”
J
o
u
r
n
a
l
o
f
T
h
e
I
n
st
i
t
u
t
i
o
n
o
f
En
g
i
n
e
e
rs
,
v
o
l
.
1
0
3
,
n
o
.
4
,
p
p
.
1
0
4
7
–
1
0
5
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
0
3
1
-
0
2
1
-
0
0
7
0
4
-
4.
[
1
1
]
R
.
S
e
n
t
h
i
l
a
n
d
R
.
K
h
a
t
w
a
l
,
“
A
n
e
f
f
e
c
t
i
v
e
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
a
n
a
l
y
si
s
o
n
r
i
c
e
l
e
a
v
e
s
u
s
i
n
g
h
y
b
r
i
d
M
C
S
V
M
-
D
N
N
p
r
e
d
i
c
t
o
r
a
r
c
h
i
t
e
c
t
u
r
e
,
”
Re
m
o
t
e
S
e
n
si
n
g
i
n
Ea
r
t
h
S
y
s
t
e
m
s
S
c
i
e
n
c
e
s
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
8
4
–
9
7
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
9
7
6
-
0
2
4
-
0
0
1
7
5
-
3.
[
1
2
]
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
se
a
se
s
u
b
t
y
p
e
s,
”
Ar
t
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
re
,
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
3
]
K
.
M
a
h
a
d
e
v
a
n
,
A
.
P
u
n
i
t
h
a
,
a
n
d
J
.
S
u
r
e
sh
,
“
A
u
t
o
m
a
t
i
c
r
e
c
o
g
n
i
t
i
o
n
o
f
r
i
c
e
p
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
i
m
p
r
o
v
e
d
t
h
r
e
s
h
o
l
d
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
e
-
Pri
m
e
-
A
d
v
a
n
c
e
s
i
n
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
El
e
c
t
ro
n
i
c
s
a
n
d
En
e
r
g
y
,
v
o
l
.
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
i
m
e
.
2
0
2
4
.
1
0
0
5
3
4
.
[
1
4
]
J.
L
i
,
Z
.
R
e
n
,
a
n
d
L.
Z
h
o
u
,
“
S
e
m
a
n
t
i
c
s
e
g
m
e
n
t
a
t
i
o
n
o
f
r
i
c
e
d
i
se
a
se
i
ma
g
e
s
b
a
se
d
o
n
D
e
e
p
La
b
V
3
+
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
3
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
I
m
a
g
e
,
Al
g
o
ri
t
h
m
s
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
C
I
A
AI
2
0
2
3
)
,
2
0
2
3
,
p
p
.
9
3
5
–
9
4
7
,
d
o
i
:
1
0
.
2
9
9
1
/
9
7
8
-
94
-
6
4
6
3
-
300
-
9
_
9
5
.
[
1
5
]
X
.
B
i
a
n
d
H
.
W
a
n
g
,
“
D
o
u
b
l
e
-
b
r
a
n
c
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
-
b
a
se
d
r
i
c
e
l
e
a
f
d
i
s
e
a
s
e
s
r
e
c
o
g
n
i
t
i
o
n
a
n
d
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
Ag
r
i
c
u
l
t
u
ra
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
5
,
n
o
.
1
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
4
0
8
1
/
j
a
e
.
2
0
2
3
.
1
5
4
4
.
[
1
6
]
S
.
K
.
U
p
a
d
h
y
a
y
a
n
d
A
.
K
u
mar,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
r
i
c
e
p
l
a
n
t
d
i
se
a
ses
c
l
a
ss
i
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
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
1
8
5
–
1
9
9
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
8
7
0
-
0
2
1
-
0
0
8
1
7
-
5.
[
1
7
]
R
.
D
e
n
g
e
t
a
l
.
,
“
A
u
t
o
ma
t
i
c
d
i
a
g
n
o
si
s
o
f
r
i
c
e
d
i
se
a
ses
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Fr
o
n
t
i
e
rs
i
n
P
l
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
2
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s
.
2
0
2
1
.
7
0
1
0
3
8
.
[
1
8
]
S
.
P
.
S
.
S
h
i
v
a
m
a
n
d
I
.
K
u
m
a
r
,
“
R
i
c
e
p
l
a
n
t
i
n
f
e
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
sy
s
t
e
ms
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
S
e
m
a
n
t
i
c
I
n
t
e
l
l
i
g
e
n
c
e
C
o
n
f
e
r
e
n
c
e
(
I
S
I
C
2
0
2
1
)
,
2
0
2
1
,
p
p
.
3
8
4
-
3
9
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
1
6
9
1
-
1
7
0
0
1700
[
1
9
]
S
.
R
.
S
h
a
h
,
S
.
Q
a
d
r
i
,
H
.
B
i
b
i
,
S
.
M
.
W
.
S
h
a
h
,
M
.
I
.
S
h
a
r
i
f
,
a
n
d
F
.
M
a
r
i
n
e
l
l
o
,
“
C
o
m
p
a
r
i
n
g
I
n
c
e
p
t
i
o
n
V
3
,
V
G
G
1
6
,
V
G
G
1
9
,
C
N
N
,
a
n
d
R
e
sN
e
t
5
0
:
a
c
a
se
s
t
u
d
y
o
n
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
a
r
i
c
e
d
i
sea
se
,
”
Ag
r
o
n
o
m
y
,
v
o
l
.
1
3
,
n
o
.
6
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
m
y
1
3
0
6
1
6
3
3
.
[
2
0
]
J.
I
q
b
a
l
,
I
.
H
u
ss
a
i
n
,
A
.
H
a
k
i
m,
S
.
U
l
l
a
h
,
a
n
d
H
.
M
.
Y
o
u
s
u
f
,
“
E
a
r
l
y
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
r
i
c
e
b
r
o
w
n
s
p
o
t
a
n
d
b
a
c
t
e
r
i
a
l
b
l
i
g
h
t
d
i
s
e
a
s
e
s
u
si
n
g
d
i
g
i
t
a
l
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
&
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
4
0
,
n
o
.
2
,
p
p
.
9
8
–
1
0
9
,
2
0
2
3
.
[
2
1
]
L.
Y
.
W
.
Lw
i
n
a
n
d
A
.
N
.
H
t
w
e
,
“
I
mag
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
r
i
c
e
l
e
a
f
d
i
s
e
a
se
u
s
i
n
g
A
l
e
x
N
e
t
m
o
d
e
l
,
”
i
n
2
0
2
3
I
EE
E
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s (I
C
C
A)
,
F
e
b
.
2
0
2
3
,
p
p
.
1
2
4
–
1
2
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
A
5
1
7
2
3
.
2
0
2
3
.
1
0
1
8
1
8
4
7
.
[
2
2
]
Z.
W
a
n
g
,
Y
.
W
e
i
,
C
.
M
u
,
Y
.
Z
h
a
n
g
,
a
n
d
X
.
Q
i
a
o
,
“
R
i
c
e
d
i
s
e
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
a
st
a
c
k
e
d
e
n
sem
b
l
e
o
f
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
7
,
n
o
.
1
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
7
0
1
0
1
2
4
.
[
2
3
]
H
.
P
e
n
g
,
F
.
Lo
n
g
,
a
n
d
C
.
D
i
n
g
,
“
F
e
a
t
u
r
e
se
l
e
c
t
i
o
n
b
a
s
e
d
o
n
m
u
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
c
r
i
t
e
r
i
a
o
f
ma
x
-
d
e
p
e
n
d
e
n
c
y
,
m
a
x
-
r
e
l
e
v
a
n
c
e
,
a
n
d
mi
n
-
r
e
d
u
n
d
a
n
c
y
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
Pa
t
t
e
rn
An
a
l
y
si
s
a
n
d
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
2
7
,
n
o
.
8
,
p
p
.
1
2
2
6
–
1
2
3
8
,
A
u
g
.
2
0
0
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TPA
M
I
.
2
0
0
5
.
1
5
9
.
[
2
4
]
F
.
S
.
P
r
i
t
y
,
M
.
R
a
q
u
i
b
,
S
.
A
.
M
u
r
a
d
,
M
.
J.
A
.
R
a
f
i
,
M
.
K
.
B
.
B
h
u
i
y
a
n
,
a
n
d
A
.
K
.
B
a
i
r
a
g
i
,
“
N
e
u
r
a
l
n
e
t
w
o
r
k
‐
b
a
s
e
d
st
u
d
y
f
o
r
r
i
c
e
l
e
a
f
d
i
sea
s
e
r
e
c
o
g
n
i
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
a
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
b
e
t
w
e
e
n
f
e
a
t
u
r
e
‐
b
a
se
d
m
o
d
e
l
a
n
d
d
i
r
e
c
t
i
m
a
g
i
n
g
mo
d
e
l
,
”
F
o
o
d
S
c
i
e
n
c
e
&
N
u
t
ri
t
i
o
n
,
v
o
l
.
1
3
,
n
o
.
1
2
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
2
/
f
s
n
3
.
7
1
3
5
0
.
[
2
5
]
J.
P
e
n
g
,
Y
.
W
a
n
g
,
P
.
J
i
a
n
g
,
R
.
Zh
a
n
g
,
a
n
d
H
.
C
h
e
n
,
“
R
i
c
e
D
R
A
-
N
e
t
:
p
r
e
c
i
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
r
i
c
e
l
e
a
f
d
i
se
a
s
e
s
w
i
t
h
c
o
mp
l
e
x
b
a
c
k
g
r
o
u
n
d
s
u
s
i
n
g
a
r
e
s
-
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
sm,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
8
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
8
4
9
2
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ay
e
Th
id
a
W
in
is
c
u
rre
n
tl
y
d
o
i
n
g
P
h
.
D.
re
se
a
rc
h
a
t
Un
iv
e
r
sity
o
f
C
o
m
p
u
ter
S
tu
d
ies
,
Ya
n
g
o
n
.
S
h
e
re
c
e
iv
e
d
h
e
r
m
a
ste
r
d
e
g
re
e
(M
.
C
.
S
c
.
)
in
C
o
m
p
u
ter
S
c
ien
c
e
fr
o
m
t
h
e
Un
iv
e
rsity
o
f
C
o
m
p
u
ter
S
tu
d
ies
,
Ya
n
g
o
n
.
S
h
e
p
re
se
n
ted
h
e
r
c
o
n
tri
b
u
ti
o
n
a
t
ICCR2
3
,
Ko
re
a
(2
3
-
2
4
Oc
to
b
e
r,
2
0
2
3
)
a
n
d
a
t
ICCA2
4
,
M
y
a
n
m
a
r
(1
6
M
a
rc
h
,
2
0
2
4
)
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
re
se
a
rc
h
o
n
d
e
e
p
lea
rn
in
g
,
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
Arg
i
-
Tec
h
,
m
a
c
h
in
e
lea
rn
in
g
,
ima
g
e
p
r
o
c
e
ss
in
g
,
a
n
d
fe
a
tu
re
re
c
o
g
n
it
i
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
a
y
e
th
id
a
win
@
u
c
sk
t.
e
d
u
.
m
m
.
Dr
.
K
h
in
Ma
r
S
o
e
re
c
e
iv
e
d
a
P
h
.
D.
(
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
)
d
e
g
re
e
fro
m
th
e
Un
iv
e
rsity
o
f
Co
m
p
u
ter
S
t
u
d
ies
,
Ya
n
g
o
n
,
M
y
a
n
m
a
r.
S
h
e
is
a
p
r
o
fe
ss
o
r
a
t
th
e
Un
i
v
e
rsity
o
f
Co
m
p
u
ter
S
t
u
d
ies
,
Ya
n
g
o
n
.
He
r
re
se
a
rc
h
in
tere
sts
a
re
in
th
e
a
re
a
s
o
f
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
p
a
rt
-
of
-
sp
e
e
c
h
tag
g
in
g
,
m
a
c
h
in
e
tra
n
sla
ti
o
n
,
a
n
d
M
y
a
n
m
a
r
n
a
m
e
e
n
ti
t
y
re
c
o
g
n
it
i
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
h
i
n
m
a
rso
e
@u
c
sy
.
e
d
u
.
m
m
.
Dr
.
My
in
t
My
i
n
t
Lwin
i
s
c
u
rre
n
tl
y
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
in
F
a
c
u
lt
y
o
f
In
fo
rm
a
ti
o
n
S
c
ien
c
e
o
f
U
n
iv
e
rsit
y
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
.
S
h
e
re
c
e
iv
e
d
P
h
.
D
.
d
e
g
re
e
in
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
fro
m
t
h
e
Un
iv
e
rsit
y
o
f
Co
m
p
u
ter
S
t
u
d
ies
,
Ya
n
g
o
n
.
He
r
re
se
a
rc
h
in
tere
sts
a
re
d
a
tab
a
se
m
a
n
a
g
e
m
e
n
t
sy
ste
m
,
d
a
ta
m
in
in
g
,
m
a
c
h
i
n
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
d
a
ta an
a
ly
ti
c
s.
S
h
e
c
a
n
b
e
c
o
n
tac
t
e
d
at
e
m
a
il
:
m
y
in
tm
y
in
tl
wi
n
@u
it
.
e
d
u
.
m
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.