I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
20
2
5
,
p
p
.
209
0
~
210
0
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
8
.
i
3
.
pp
209
0
-
2
1
0
0
2090
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Im
pro
v
ing
f
a
rming
by quickly
de
t
ecting mus
km
elo
n plan
t
disea
ses
using
adv
a
nced ensemble
lea
rning
and ca
ps
ule
networks
Dee
ba
K
a
nn
a
n
1
,
Na
g
a
m
uthu
K
rish
na
n Su
nd
a
ra
s
rin
iv
a
s
a
Sa
nk
a
ra
na
ra
y
a
na
n
2
,
Sh
a
nm
ug
a
s
un
da
ra
m
Venk
a
t
a
ra
j
a
n
3
,
Ra
s
him
a
M
a
ha
j
a
n
4
,
B
rindh
a
G
un
a
s
ek
a
ra
n
5
,
P
a
nd
i Ma
ha
ra
j
a
n M
uru
g
a
ma
ni
6
,
K
a
rt
hik
ey
a
n
Dha
nd
a
pa
ni
7
1
S
c
h
o
o
l
o
f
C
o
m
p
u
t
i
n
g
,
S
R
M
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
A
S
TR
A
D
e
e
m
e
d
t
o
b
e
U
n
i
v
e
r
si
t
y
S
R
C
,
K
u
m
b
a
k
o
n
a
m,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
EEE
,
S
o
n
a
C
o
l
l
e
g
e
o
f
Te
c
h
n
o
l
o
g
y
,
S
a
l
e
m,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
M
a
n
a
v
R
a
c
h
n
a
I
n
t
e
r
n
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
R
e
s
e
a
r
c
h
a
n
d
S
t
u
d
i
e
s,
F
a
r
i
d
a
b
a
d
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
t
.
J
o
se
p
h
’
s
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
C
h
e
n
n
a
i
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
D
h
a
a
n
i
sh
A
h
me
d
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
C
h
e
n
n
a
i
,
I
n
d
i
a
7
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
S
R
M
i
n
s
t
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
C
h
e
n
n
a
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
29
,
2
0
2
4
R
ev
is
ed
No
v
20
,
2
0
2
4
Acc
ep
ted
No
v
30
,
2
0
2
4
In
m
o
d
e
rn
a
g
ricu
lt
u
re
,
e
n
s
u
rin
g
p
lan
t
h
e
a
lt
h
is
e
ss
e
n
ti
a
l
fo
r
h
ig
h
c
r
o
p
y
iel
d
s
a
n
d
q
u
a
li
t
y
.
P
lan
t
d
ise
a
se
s
p
o
se
risk
s
to
e
c
o
n
o
m
ies
,
c
o
m
m
u
n
it
ies
,
a
n
d
th
e
e
n
v
iro
n
m
e
n
t,
m
a
k
i
n
g
e
a
rly
a
n
d
a
c
c
u
ra
te
d
iag
n
o
sis
c
ru
c
ial.
Th
e
i
n
tern
e
t
o
f
th
in
g
s
(I
o
T)
h
a
s
re
v
o
l
u
ti
o
n
ize
d
fa
rm
in
g
b
y
e
n
a
b
li
n
g
re
a
l
-
ti
m
e
c
ro
p
m
o
n
it
o
r
in
g
a
n
d
u
si
n
g
d
r
o
n
e
s
a
n
d
c
a
m
e
ra
s
fo
r
e
a
rly
d
ise
a
se
d
e
tec
ti
o
n
.
Th
is
tec
h
n
o
l
o
g
y
h
e
l
p
s
fa
rm
e
rs
a
d
d
re
ss
c
h
a
ll
e
n
g
e
s
with
p
re
c
is
io
n
a
n
d
su
sta
in
a
b
il
it
y
.
Th
is
re
se
a
rc
h
p
ro
p
o
se
s
a
n
e
n
se
m
b
le
lea
rn
i
n
g
m
o
d
e
l
in
c
o
rp
o
ra
ti
n
g
m
u
lt
i
-
c
las
s
c
a
p
su
le
n
e
two
r
k
s
(M
CCN)
a
n
d
o
t
h
e
r
p
re
-
train
e
d
m
o
d
e
l
with
m
a
jo
rit
y
v
o
ti
n
g
sy
ste
m
is
imp
lem
e
n
ted
t
o
p
re
d
ict
p
lan
t
d
ise
a
se
s
a
n
d
p
e
sts
e
a
rly
.
Th
e
re
se
a
rc
h
a
ims
to
d
e
v
e
l
o
p
a
r
o
b
u
st
M
C
CN
-
b
a
se
d
e
n
se
m
b
le
p
re
d
icti
o
n
m
o
d
e
l
fo
r
ti
m
e
ly
d
ise
a
se
id
e
n
ti
fica
ti
o
n
.
To
e
v
a
lu
a
te
t
h
e
p
e
rfo
rm
a
n
c
e
o
f
th
e
e
n
se
m
b
le
m
o
d
e
l,
v
a
rio
u
s
k
e
y
m
e
tri
c
s,
in
c
lu
d
i
n
g
a
c
c
u
ra
c
y
,
a
n
d
lo
ss
v
a
lu
e
,
a
re
a
ss
e
ss
e
d
.
F
u
rt
h
e
rm
o
re
,
a
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
is
c
o
n
d
u
c
ted
,
b
e
n
c
h
m
a
rk
in
g
t
h
e
M
CCN
m
o
d
e
l
a
g
a
in
st
o
t
h
e
r
w
e
ll
-
k
n
o
wn
p
re
-
train
e
d
m
o
d
e
ls
su
c
h
a
s
r
e
sid
u
a
l
n
e
two
rk
-
1
0
1
(
Re
sN
e
t1
0
1
)
,
v
isu
a
l
g
e
o
m
e
try
g
ro
u
p
-
1
9
(
VG
G
1
9
)
,
a
n
d
G
o
o
g
leN
e
t.
T
h
is
re
se
a
rc
h
si
g
n
ifi
e
s
a
su
b
sta
n
ti
a
l
stri
d
e
to
wa
rd
s
th
e
re
a
l
iza
ti
o
n
o
f
I
o
T
-
d
r
iv
e
n
p
re
c
isio
n
a
g
ricu
lt
u
re
,
wh
e
re
a
d
v
a
n
c
e
d
tec
h
n
o
l
o
g
y
a
n
d
m
a
c
h
in
e
lea
rn
in
g
c
o
n
tri
b
u
te
t
o
th
e
e
a
rly
d
e
tec
ti
o
n
a
n
d
m
it
ig
a
ti
o
n
o
f
p
lan
t
d
ise
a
se
s,
u
lt
ima
tely
e
n
h
a
n
c
i
n
g
c
ro
p
y
ield
a
n
d
e
n
v
iro
n
m
e
n
tal
su
sta
i
n
a
b
il
it
y
.
K
ey
w
o
r
d
s
:
C
ap
s
u
le
n
etwo
r
k
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Dee
p
lear
n
in
g
E
n
s
em
b
le
lear
n
in
g
Mu
lti
-
class
ca
p
s
u
le
n
etwo
r
k
s
Pre
cisi
o
n
ag
r
icu
ltu
r
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
:
Kar
th
ik
ey
an
Dh
a
n
d
ap
a
n
i
Dep
ar
tm
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ics E
n
g
in
ee
r
i
n
g
,
SR
M
I
n
s
titu
te
o
f
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
Kattan
k
u
lath
u
r
,
C
h
e
n
n
ai,
T
am
il Na
d
u
,
I
n
d
ia
E
m
ail:
k
ar
th
ip
n
cl@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
m
o
d
er
n
ag
r
icu
ltu
r
e,
p
lan
t
h
ea
lth
is
cr
u
cial
f
o
r
ac
h
iev
in
g
h
ig
h
cr
o
p
y
ield
s
,
im
p
ac
tin
g
b
o
th
q
u
ality
an
d
q
u
a
n
tity
.
Plan
t
in
f
ec
tio
n
s
ca
n
th
r
ea
ten
ec
o
n
o
m
ies,
co
m
m
u
n
ities
,
an
d
th
e
en
v
i
r
o
n
m
en
t,
h
ig
h
lig
h
tin
g
th
e
n
ee
d
f
o
r
ea
r
l
y
an
d
ac
cu
r
ate
d
is
ea
s
e
d
iag
n
o
s
is
.
I
n
co
n
tr
ast,
em
p
lo
y
in
g
au
to
m
ate
d
d
i
s
ea
s
e
s
eg
m
en
tatio
n
th
r
o
u
g
h
p
lan
t
leaf
im
ag
e
a
n
al
y
s
is
with
s
o
f
t
co
m
p
u
tin
g
tech
n
iq
u
es
p
r
esen
ts
a
m
o
r
e
ef
f
icie
n
t
alter
n
ativ
e
to
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
mp
r
o
vin
g
fa
r
min
g
b
y
q
u
ickly
d
etec
tin
g
mu
s
kme
lo
n
p
la
n
t d
is
ea
s
es u
s
in
g
…
(
Dee
b
a
K
a
n
n
a
n
)
2091
ex
is
tin
g
ap
p
r
o
ac
h
.
T
h
e
a
d
v
en
t
o
f
th
e
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
h
as
in
itiated
a
tr
a
n
s
f
o
r
m
ativ
e
er
a
in
a
g
r
icu
ltu
r
e
,
en
d
o
win
g
f
a
r
m
er
s
with
th
e
to
o
ls
f
o
r
p
r
ec
is
e
an
d
s
u
s
tain
a
b
le
f
ar
m
in
g
p
r
ac
tices
to
ad
d
r
ess
th
e
m
u
ltifa
ce
ted
ch
allen
g
es
in
th
e
ag
r
icu
ltu
r
al
lan
d
s
ca
p
e.
T
h
e
r
a
p
id
ev
o
l
u
tio
n
o
f
tech
n
o
lo
g
y
is
u
s
h
er
in
g
in
a
s
h
if
t
f
r
o
m
co
n
v
en
tio
n
al
p
r
ac
tices
to
war
d
s
cu
ttin
g
-
ed
g
e
m
eth
o
d
o
l
o
g
i
es.
T
h
e
au
to
m
atio
n
o
f
ea
r
l
y
-
s
tag
e
p
lan
t
d
is
ea
s
e
d
etec
tio
n
h
as
b
ec
o
m
e
im
p
er
at
iv
e,
n
o
t
o
n
ly
to
s
tr
ea
m
lin
e
d
e
tectio
n
p
r
o
ce
s
s
es,
en
h
a
n
ce
ac
cu
r
ac
y
,
b
u
t
also
t
o
en
s
u
r
e
co
n
s
is
ten
t
cr
o
p
y
ield
s
d
esp
ite
v
ar
iatio
n
s
in
clim
atic,
s
o
il,
an
d
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
.
Ma
n
u
al
p
ath
o
g
e
n
d
etec
tio
n
in
p
la
n
ts
is
b
u
r
d
e
n
ed
b
y
its
h
ig
h
c
o
s
ts
,
tim
e
in
ten
s
iv
en
ess
,
an
d
th
e
n
ec
ess
ity
f
o
r
s
p
ec
ialized
ex
p
er
tis
e.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
e
r
esear
ch
er
s
p
r
im
ar
ily
e
m
p
h
asize
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
f
o
r
e
x
tr
ac
tin
g
d
is
tin
ctiv
e
f
ea
tu
r
es,
r
ath
er
th
a
n
co
n
ce
n
tr
atin
g
o
n
c
lass
if
ier
s
y
s
tem
s
.
R
ec
o
g
n
izin
g
th
e
lim
itatio
n
s
o
f
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
,
th
e
r
esear
ch
d
ir
ec
tio
n
h
as
s
h
if
ted
to
war
d
s
d
ee
p
lear
n
i
n
g
alg
o
r
ith
m
s
.
Dee
p
lear
n
in
g
m
o
d
els
h
av
e
g
ain
ed
p
r
o
m
in
e
n
ce
in
im
ag
e
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
d
u
e
to
th
eir
a
b
ilit
y
to
au
to
m
atica
lly
ex
tr
ac
t
f
ea
tu
r
es
an
d
tr
ain
th
em
s
elv
es.
T
h
ey
h
a
v
e
d
em
o
n
s
tr
ated
s
ig
n
if
ican
tly
im
p
r
o
v
e
d
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
t
r
ad
itio
n
al
m
ac
h
i
n
e
class
if
icatio
n
m
o
d
els,
esp
ec
ially
in
task
s
lik
e
p
lan
t le
af
class
if
icatio
n
.
I
n
2
0
1
5
,
Kaw
asak
i
et
a
l.
[
1
]
in
tr
o
d
u
ce
d
a
th
r
ee
-
lay
e
r
ed
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
s
tr
u
ctu
r
e
d
esig
n
ed
to
d
etec
t
cu
cu
m
b
er
leaf
d
is
ea
s
es,
ac
h
iev
in
g
an
im
p
r
ess
iv
e
ac
cu
r
ac
y
r
ate
o
f
9
4
.
9
%.
Similar
ly
,
L
ee
et
a
l.
[
2
]
p
r
esen
ted
a
f
iv
e
-
lay
er
C
NN
m
o
d
el
in
2
0
1
5
f
o
r
ca
teg
o
r
izin
g
4
4
d
i
f
f
e
r
en
t p
lan
t sp
ec
ies.
T
h
is
m
o
d
el
was
test
ed
u
s
in
g
2
,
8
1
6
im
a
g
es
f
r
o
m
th
e
Ma
l
ay
aKe
w
(
MK
)
d
ataset,
s
o
u
r
ce
d
f
r
o
m
th
e
R
o
y
al
B
o
tan
ic
Gar
d
en
s
in
New
E
n
g
l
an
d
,
an
d
ac
h
iev
ed
a
r
em
ar
k
a
b
l
e
ac
cu
r
ac
y
o
f
9
9
.
7
%.
I
n
2
0
1
6
,
Mo
h
an
ty
et
a
l.
[
3
]
co
n
d
u
cte
d
ex
p
er
i
m
en
ts
th
at
ex
p
lo
r
ed
t
h
e
s
tate
-
of
-
th
e
-
a
r
t
tech
n
iq
u
es
in
p
lan
t
d
is
ea
s
e
id
en
tific
atio
n
an
d
class
if
icatio
n
,
m
ar
k
in
g
a
s
ig
n
if
ican
t
ad
v
an
ce
m
en
t
in
th
is
f
ield
.
T
h
eir
r
esear
c
h
em
p
lo
y
ed
Alex
Net
an
d
Go
o
g
leNe
t
as
in
teg
r
al
co
m
p
o
n
en
ts
.
T
h
e
d
ataset
was
d
iv
i
d
ed
in
to
th
r
ee
d
is
tin
ct
ca
teg
o
r
ies:
o
r
ig
in
al
co
lo
r
im
ag
es,
g
r
ay
s
ca
le
im
ag
es,
an
d
s
eg
m
en
ted
im
ag
es.
T
h
e
m
o
d
el
u
n
d
er
wen
t
tr
ain
i
n
g
u
s
in
g
ea
ch
o
f
th
ese
im
ag
e
s
ets,
with
th
e
h
ig
h
est
p
er
f
o
r
m
an
ce
o
b
s
er
v
e
d
in
th
e
m
o
d
el
tr
ain
ed
o
n
t
h
e
o
r
ig
i
n
al
co
lo
r
im
ag
es.
I
m
p
r
ess
iv
ely
,
th
e
p
r
o
p
o
s
ed
s
y
s
tem
ac
h
iev
e
d
an
av
er
ag
e
ac
cu
r
ac
y
r
ate
o
f
9
9
.
5
3
%.
T
r
an
s
f
er
lear
n
i
n
g
,
a
p
r
ev
ale
n
t
tech
n
iq
u
e
in
d
ee
p
lear
n
in
g
,
in
v
o
lv
es
th
e
u
tili
za
tio
n
o
f
p
r
e
-
tr
ain
ed
m
o
d
els
as
a
f
o
u
n
d
atio
n
al
s
tar
tin
g
p
o
i
n
t,
f
o
llo
wed
b
y
f
in
e
-
t
u
n
in
g
th
r
o
u
g
h
a
class
if
icatio
n
alg
o
r
ith
m
.
Sev
er
al
r
esear
ch
s
tu
d
ies
h
av
e
s
u
cc
ess
f
u
lly
ap
p
lied
th
is
ap
p
r
o
ac
h
in
co
n
ju
n
ctio
n
with
s
p
ec
if
ic
alg
o
r
ith
m
s
to
class
if
y
p
lan
t
d
is
ea
s
es.
R
am
ch
ar
an
et
a
l.
[
4
]
em
p
lo
y
ed
an
I
n
ce
p
ti
o
n
V
3
p
r
e
-
tr
ai
n
ed
m
o
d
el
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
co
u
p
led
with
a
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
class
if
ier
f
o
r
class
if
icatio
n
p
u
r
p
o
s
es.
T
h
ey
tr
ain
ed
th
e
m
o
d
el
u
s
in
g
1
1
,
6
7
0
i
n
f
ec
ted
ca
s
s
av
a
leav
es
f
r
o
m
im
ag
e
d
atasets
,
a
ch
iev
in
g
a
r
em
ar
k
a
b
le
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
8
%.
Similar
ly
,
in
2
0
1
7
,
Sh
ijie
et
a
l.
[
5
]
im
p
lem
en
ted
a
tech
n
iq
u
e
m
er
g
in
g
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
-
16
(
VGG1
6
)
with
SVM
f
o
r
to
m
a
to
leaf
d
is
ea
s
e
id
en
tific
atio
n
,
attain
in
g
an
ac
cu
r
ac
y
o
f
8
9
%
in
test
s
co
n
d
u
cted
with
4
4
0
in
f
ec
ted
im
ag
es,
s
p
a
n
n
in
g
1
1
d
i
f
f
er
en
t c
lass
lab
els.
Z
h
an
g
et
a
l.
[
6
]
in
2
0
1
8
p
r
o
p
o
s
ed
an
im
p
r
o
v
is
ed
Go
o
g
L
eN
et
m
o
d
el
an
d
C
if
er
1
0
m
o
d
el
f
o
r
m
aize
leaf
d
is
ea
s
e
class
if
icat
io
n
to
p
id
en
tific
atio
n
ac
cu
r
ac
y
o
f
ab
o
u
t
9
8
%.
T
h
e
r
esear
ch
b
y
Sin
g
h
et
a
l.
[
7
]
in
2
0
1
9
p
r
o
p
o
s
ed
a
m
u
lti
-
lay
er
C
NN
s
tr
u
ctu
r
e
f
o
r
id
e
n
tific
atio
n
o
f
m
an
g
o
leav
es
af
f
ec
te
d
b
y
th
e
an
th
r
ac
n
o
s
e
f
u
n
g
al
in
f
ec
tio
n
.
I
n
th
is
wo
r
k
,
th
ey
h
av
e
co
n
d
u
cted
a
r
ig
o
r
o
u
s
ev
al
u
atio
n
u
s
in
g
a
r
ea
l
-
tim
e
d
ataset
co
llected
at
Sh
r
i
Ma
ta
Vaish
n
o
Dev
i
Un
iv
er
s
it
y
,
Katr
a,
J
am
m
u
an
d
Kash
m
i
r
,
I
n
d
ia.
T
h
is
d
ataset
co
m
p
r
is
es
a
to
tal
o
f
1
,
0
7
0
im
ag
es
d
ep
ictin
g
th
e
leav
es
o
f
m
an
g
o
tr
ee
s
.
I
t
en
co
m
p
ass
es
a
d
iv
er
s
e
r
an
g
e
o
f
im
a
g
es,
in
clu
d
in
g
th
o
s
e
o
f
b
o
th
h
ea
lth
y
leav
es
a
n
d
leav
es
th
at
h
a
v
e
b
ee
n
in
f
ec
ted
b
y
v
a
r
io
u
s
d
is
ea
s
es.
T
h
e
o
u
tc
o
m
es
o
f
th
eir
s
tu
d
y
d
em
o
n
s
tr
ate
a
n
o
ta
b
le
im
p
r
o
v
em
en
t
in
class
if
icatio
n
ac
cu
r
ac
y
ac
h
iev
e
d
b
y
th
e
m
u
lti
-
l
ay
er
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
MCNN
)
m
o
d
el
in
co
m
p
ar
is
o
n
to
ex
is
tin
g
s
t
ate
-
of
-
th
e
-
a
r
t a
p
p
r
o
ac
h
es.
Su
n
et
a
l.
[
8
]
in
2
0
2
0
u
s
ed
an
im
p
r
o
v
is
ed
R
PN
m
o
d
el
f
o
r
d
etec
tio
n
o
f
n
o
r
t
h
er
n
m
aize
lea
f
b
lig
h
t
in
ch
allen
g
in
g
f
ield
co
n
d
itio
n
s
a
n
d
ac
h
iev
e
d
an
ac
cu
r
ac
y
o
f
9
1
.
8
%
af
ter
6
,
0
0
0
iter
atio
n
s
.
I
n
2
0
2
0
,
Hu
et
a
l.
[
9
]
,
in
tr
o
d
u
ce
th
e
m
u
ltid
im
en
s
io
n
al
f
ea
tu
r
e
co
m
p
en
s
atio
n
r
e
s
id
u
al
n
eu
r
al
n
etwo
r
k
(
MD
FC
-
R
e
s
Net)
m
o
d
el
d
esig
n
ed
f
o
r
p
r
e
cise d
is
ea
s
e
id
en
tific
atio
n
with
in
th
e
s
y
s
tem
.
Z
in
o
n
o
s
et
a
l.
[
1
0
]
in
2
0
2
1
,
p
r
esen
ts
th
e
p
r
ac
tical
o
u
tco
m
es
o
f
a
co
m
b
in
ed
lo
n
g
r
an
g
e
(
L
o
R
a
)
an
d
d
ee
p
lear
n
in
g
-
p
o
wer
ed
co
m
p
u
ter
v
is
io
n
s
y
s
tem
,
d
esig
n
e
d
f
o
r
e
f
f
icien
t
id
e
n
tific
atio
n
o
f
g
r
ap
e
lea
f
d
is
ea
s
es
u
tili
zin
g
lo
w
-
r
eso
lu
tio
n
im
ag
es.
I
n
th
is
r
esear
ch
,
th
e
y
e
m
p
lo
y
t
h
e
g
r
ad
-
C
AM
m
eth
o
d
to
v
is
u
alize
th
e
ju
d
g
m
en
ts
m
ad
e
b
y
th
e
C
NN
’
s
o
u
tp
u
t
lay
er
.
T
h
e
v
is
u
aliza
t
io
n
r
esu
lts
h
ig
h
lig
h
t
s
ig
n
if
ica
n
t
ac
tiv
atio
n
in
th
e
d
is
ea
s
e
’
s
af
f
ec
ted
r
eg
io
n
,
elu
cid
atin
g
h
o
w
th
e
n
etwo
r
k
ef
f
ec
tiv
ely
d
is
cr
im
in
ates
b
etwe
en
v
ar
io
u
s
g
r
a
p
e
leaf
d
is
ea
s
es.
A
co
m
p
r
eh
en
s
iv
e
ev
alu
atio
n
was
co
n
d
u
cted
u
s
in
g
a
to
tal
o
f
1
,
2
9
6
b
ea
n
leaf
im
ag
es
b
y
E
lf
atim
i
et
a
l.
[
1
1
]
in
2
0
2
2
.
T
h
e
r
esu
lts
o
b
tain
ed
th
r
o
u
g
h
th
is
ap
p
r
o
ac
h
d
em
o
n
s
tr
ated
th
e
r
em
ar
k
ab
le
p
er
f
o
r
m
an
ce
o
f
o
u
r
Mo
b
ileN
et
m
o
d
el
in
class
if
y
in
g
b
ea
n
leaf
d
is
ea
s
es.
Sp
ec
if
ically
,
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
ex
h
ib
ited
im
p
r
ess
iv
e
av
er
a
g
e
class
if
icatio
n
ac
cu
r
ac
y
,
s
u
r
p
a
s
s
in
g
9
7
%
o
n
th
e
tr
ain
in
g
d
ataset
an
d
ex
ce
ed
in
g
9
2
%
o
n
th
e
test
d
ataset,
en
co
m
p
ass
in
g
th
e
two
u
n
h
ea
lth
y
class
es
an
d
o
n
e
h
ea
lth
y
cla
s
s
.
T
h
ese
f
in
d
in
g
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
20
2
5
:
2
0
9
0
-
210
0
2092
u
n
d
er
s
co
r
e
th
e
p
o
ten
tial
o
f
d
ee
p
lear
n
in
g
tech
n
iq
u
es
in
th
e
r
ea
lm
o
f
b
ea
n
leaf
d
is
ea
s
e
d
etec
tio
n
an
d
class
if
icatio
n
,
o
f
f
er
in
g
r
o
b
u
s
t a
n
d
ac
cu
r
ate
r
esu
lts
.
T
h
e
r
esear
ch
b
y
Vis
h
n
o
i
et
a
l.
[
1
2
]
in
2
0
2
3
,
p
r
o
p
o
s
ed
an
im
p
r
o
v
is
ed
C
NN
m
o
d
el
f
o
r
d
ete
ctin
g
ap
p
le
leaf
d
is
ea
s
es
an
d
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
8
%.
I
n
th
e
s
am
e
y
ea
r
,
Far
ah
et
a
l.
[
1
3
]
,
p
r
o
p
o
s
ed
a
tr
an
s
f
e
r
lear
n
in
g
b
ased
VGG1
9
m
o
d
e
l
f
o
r
class
if
icatio
n
o
f
s
o
y
b
ea
n
leaf
d
is
ea
s
es
an
d
ac
h
iev
ed
an
ac
cu
r
ac
y
u
p
to
9
4
.
1
6
%.
Fo
r
a
co
m
p
r
eh
e
n
s
iv
e
o
v
er
v
iew
o
f
ex
is
tin
g
r
esear
c
h
in
leaf
d
is
ea
s
e
id
en
tific
atio
n
u
s
in
g
d
ee
p
lear
n
in
g
alg
o
r
it
h
m
s
,
p
lease
r
ef
er
to
T
a
b
le
1
,
s
u
m
m
ar
izin
g
th
e
r
ec
e
n
t
ef
f
o
r
ts
o
f
v
ar
i
o
u
s
r
esear
ch
er
s
in
t
h
is
f
ield
f
r
o
m
th
e
y
ea
r
2
0
2
0
[
1
4
]
,
[
1
5
]
.
T
ab
le
1
.
Pre
v
i
o
u
s
s
tu
d
ies co
n
d
u
cted
b
y
d
iv
er
s
e
r
esear
ch
e
r
s
o
n
leaf
d
is
ea
s
e
r
ec
o
g
n
itio
n
u
tili
zin
g
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
f
r
o
m
th
e
y
ea
r
2
0
2
0
A
u
t
h
o
r
A
l
g
o
r
i
t
h
m
u
s
e
d
D
a
t
a
s
e
t
P
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
Te
t
i
l
a
e
t
a
l
.
[1
4
]
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
(
DNN
)
w
i
t
h
f
i
n
e
t
u
r
n
e
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
U
A
V
i
ma
g
e
s
o
f
s
o
y
b
e
a
n
9
9
.
0
4
%
Li
e
t
a
l
.
[1
5
]
F
a
st
e
r
r
e
c
u
r
r
e
n
t
-
C
N
N
(
R
C
N
N
)
S
e
a
c
u
c
u
m
b
e
r
v
i
d
e
o
s
9
9
%
Li
u
e
t
a
l
.
[1
6
]
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sari
a
l
n
e
t
w
o
r
k
(
GAN
)
b
a
s
e
d
X
c
e
p
t
i
o
n
n
e
t
w
o
r
k
8
,
1
2
4
i
ma
g
e
s
o
f
g
r
a
p
e
l
e
a
v
e
s
9
8
.
7
0
%
Ze
n
g
e
t
a
l
.
[1
7
]
G
A
N
b
a
se
d
d
e
e
p
C
N
N
mo
d
e
l
1
4
,
0
5
6
i
ma
g
e
s
o
f
c
i
t
r
u
s
l
e
a
v
e
s
9
2
.
6
0
%
Ai
e
t
a
l
.
[
18
]
I
n
c
e
p
t
i
o
n
-
R
e
sN
e
t
-
v2
2
7
d
i
se
a
se
i
ma
g
e
s
o
f
1
0
c
r
o
p
s
8
6
.
1
%
P
h
a
m
e
t
a
l
.
[
19
]
En
h
a
n
c
e
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
4
5
0
i
ma
g
e
s
o
f
ma
n
g
o
l
e
a
v
e
s
Up
t
o
8
9
.
4
1
%
Zh
o
u
e
t
a
l
.
[2
0
]
R
e
st
r
u
c
t
u
r
e
d
d
e
e
p
r
e
s
i
d
u
a
l
d
e
n
s
e
n
e
t
w
o
r
k
A
I
c
h
a
l
l
e
n
g
e
r
2
0
1
8
d
a
t
a
se
t
s fo
r
to
m
a
t
o
l
e
a
f
d
i
se
a
ses
9
5
%
Zh
o
u
e
t
a
l
.
[2
1
]
F
i
n
e
g
r
a
i
n
e
d
-
G
A
N
w
i
t
h
R
e
sN
e
t
1
,
5
0
0
i
ma
g
e
s
o
f
g
r
a
p
e
l
e
a
v
e
s
9
6
.
2
7
%
Zi
n
o
n
o
s
e
t
a
l
.
[
10
]
Lo
R
a
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
G
r
a
p
e
l
e
a
v
es
-
H
a
ssan
a
n
d
M
a
j
i
[2
2
]
C
N
N
w
i
t
h
i
n
c
e
p
t
i
o
n
l
a
y
e
r
a
n
d
r
e
si
d
u
a
l
c
o
n
n
e
c
t
i
o
n
P
l
a
n
t
v
i
l
l
a
g
e
d
a
t
a
se
t
r
i
c
e
d
i
sea
s
e
d
a
t
a
s
e
t
c
a
ssa
v
a
d
a
t
a
se
t
9
9
.
3
9
%
,
9
9
.
6
6
%
,
a
n
d
7
6
.
5
9
%
r
e
s
p
e
c
t
i
v
e
l
y
A
mi
n
e
t
a
l
.
[2
3
]
R
e
sN
e
t
1
5
2
a
n
d
I
n
c
e
p
t
i
o
n
V
3
1
5
,
4
0
8
i
ma
g
e
s
o
f
c
o
r
n
l
eaf
9
8
.
3
7
%
a
n
d
9
6
.
2
6
%
r
e
sp
e
c
t
i
v
e
l
y
C
h
e
n
e
t
a
l
.
[2
4
]
Li
g
h
t
w
e
i
g
h
t
M
-
I
n
c
e
p
t
i
o
n
P
l
a
n
t
V
i
l
l
a
g
e
d
a
t
a
se
t
9
9
.
2
1
%
Li
u
a
n
d
Z
h
a
n
g
[2
5
]
P
i
TLi
D
b
a
se
d
I
n
c
e
p
t
i
o
n
-
V3
A
p
p
l
e
l
e
a
f
i
m
a
g
s
9
8
.
6
5
%
M
a
s
o
o
d
e
t
a
l
.
[2
6
]
M
a
i
z
e
N
e
t
2
,
1
1
2
i
ma
g
e
s
o
f
mi
z
e
l
e
a
f
9
7
.
8
9
%
H
o
sn
y
e
t
a
l
.
[
27
]
C
N
N
b
a
se
d
o
n
l
o
c
a
l
b
i
n
a
r
y
p
a
t
t
e
r
n
(
LB
P
)
A
p
p
l
e
l
e
a
f
,
t
o
m
a
t
o
l
e
a
f
,
a
n
d
g
r
a
p
e
l
e
a
f
9
8
.
8
%,
9
6
.
5
%
,
a
n
d
9
8
.
3
%
r
e
s
p
e
c
t
i
v
e
l
y
A
l
h
a
r
b
i
e
t
a
l
.
[
28
]
Ef
f
i
c
i
e
n
t
N
e
t
C
G
I
A
R
d
a
t
a
se
t
9
8
.
5
%
A
b
i
n
a
y
a
e
t
a
l
.
[
29
]
R
e
si
d
u
a
l
U
-
n
et
5
4
,
3
0
3
i
ma
g
e
s
o
f
c
o
r
n
l
e
a
f
9
5
.
2
6
%
F
a
r
a
h
e
t
a
l
.
[
13
]
Tr
a
n
sf
e
r
l
e
a
r
n
i
n
g
b
a
se
d
V
G
G
1
6
mo
d
e
l
6
,
4
1
0
i
ma
g
e
s
s
o
y
b
e
a
n
l
e
a
v
e
s
9
4
.
1
6
%
Pre
s
en
tly
,
th
er
e
is
a
n
o
tab
le
s
ca
r
city
o
f
s
y
s
tem
s
f
o
r
m
o
n
i
to
r
in
g
an
d
f
o
r
ec
asti
n
g
c
r
o
p
c
o
n
d
itio
n
s
.
Mu
s
k
m
elo
n
,
a
lu
cr
ativ
e
cr
o
p
,
h
in
g
es
its
p
r
o
d
u
ctiv
ity
o
n
o
p
tim
al
f
ar
m
in
g
p
r
ac
tices,
ca
r
ef
u
l
m
an
ag
em
en
t,
a
n
d
d
is
ea
s
e
-
f
r
ee
p
lan
t
g
r
o
wth
.
W
ith
a
r
elativ
ely
s
h
o
r
t
life
s
p
an
o
f
5
5
to
6
5
d
a
y
s
,
an
y
d
is
ea
s
e
o
u
tb
r
ea
k
d
u
r
in
g
t
h
is
p
er
io
d
r
esu
lts
in
co
m
p
lete
lo
s
s
es
f
o
r
f
ar
m
er
s
.
Mo
r
eo
v
e
r
,
th
er
e
is
a
d
ea
r
th
o
f
co
m
p
r
e
h
en
s
iv
e
in
f
o
r
m
atio
n
o
n
f
in
e
-
g
r
ain
e
d
p
lan
t
d
is
ea
s
e
p
r
e
d
ictio
n
th
at
in
co
r
p
o
r
ates a
d
d
itio
n
al
d
ee
p
lear
n
in
g
lay
er
s
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
is
r
esear
ch
p
r
o
p
o
s
es
an
e
n
s
em
b
le
lear
n
in
g
m
o
d
el
i
n
co
r
p
o
r
atin
g
m
u
lti
-
class
ca
p
s
u
le
n
etwo
r
k
s
(
MCC
N)
an
d
o
th
er
p
r
e
-
tr
ain
e
d
m
o
d
el
with
m
ajo
r
ity
v
o
tin
g
s
y
s
tem
is
im
p
lem
en
ted
to
p
r
ed
ict
p
lan
t
d
is
ea
s
es
an
d
p
ests
ea
r
ly
.
T
h
e
r
esear
ch
aim
s
to
d
ev
elo
p
a
r
o
b
u
s
t
MCC
N
-
b
ased
en
s
em
b
le
p
r
e
d
ictio
n
m
o
d
el
f
o
r
tim
ely
d
is
ea
s
e
id
en
tific
atio
n
.
T
h
e
ar
c
h
itectu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
is
s
h
o
wn
in
Fig
u
r
e
1
.
3
.
1
.
Ca
ps
ule
n
et
wo
rk
A
ca
p
s
u
le
is
lik
e
a
g
r
o
u
p
o
f
s
p
ec
ialized
n
eu
r
o
n
s
,
wh
e
r
e
ea
c
h
n
eu
r
o
n
is
tu
n
ed
to
r
ec
o
g
n
iz
e
d
if
f
er
e
n
t
ch
ar
ac
ter
is
tics
o
f
an
o
b
ject,
lik
e
its
p
o
s
itio
n
,
s
ize,
o
r
co
lo
r
.
C
ap
s
u
le
n
etwo
r
k
s
aim
to
p
r
e
d
ict
th
ese
f
ea
tu
r
es,
in
clu
d
in
g
th
e
o
b
ject
’
s
o
r
ien
tat
io
n
,
b
ased
o
n
th
e
in
f
o
r
m
atio
n
th
ey
r
ec
eiv
e
.
T
h
is
lo
s
s
o
f
s
p
at
ial
in
f
o
r
m
atio
n
ca
n
b
e
d
etr
im
e
n
tal
wh
e
n
d
ea
lin
g
with
d
is
ea
s
es
in
p
lan
ts
,
wh
ich
r
eq
u
ir
e
p
r
eser
v
in
g
e
v
en
m
o
r
e
i
n
f
o
r
m
atio
n
.
T
o
ad
d
r
ess
th
is
is
s
u
e,
ca
p
s
u
le
n
etwo
r
k
s
ar
e
u
s
ed
f
o
r
i
n
f
ec
ti
o
n
class
if
icatio
n
in
leaf
im
ag
es,
as
th
ey
m
ain
tain
m
o
r
e
s
p
atial
in
f
o
r
m
atio
n
,
lea
d
in
g
to
im
p
r
o
v
e
d
ac
cu
r
ac
y
.
3
.
2
.
Arc
hite
ct
ure
o
f
m
ulti
-
cl
a
s
s
ca
ps
ule net
wo
rk
W
e
h
av
e
m
ad
e
a
n
o
tab
le
ch
an
g
e
b
y
elim
in
atin
g
th
e
s
tan
d
ar
d
m
ax
-
p
o
o
lin
g
lay
e
r
s
th
at
u
s
u
al
ly
f
o
llo
w
ea
ch
co
n
v
o
lu
tio
n
al
lay
er
.
Fu
r
th
er
m
o
r
e
,
we
’
v
e
ad
ap
ted
th
e
lo
s
s
f
u
n
ctio
n
with
in
th
e
ca
p
s
u
le
n
etwo
r
k
t
o
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
mp
r
o
vin
g
fa
r
min
g
b
y
q
u
ickly
d
etec
tin
g
mu
s
kme
lo
n
p
la
n
t d
is
ea
s
es u
s
in
g
…
(
Dee
b
a
K
a
n
n
a
n
)
2093
m
u
lti
-
class
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
,
wh
ich
is
tailo
r
ed
to
id
en
tify
a
n
etwo
r
k
with
s
ix
d
is
tin
ct
class
e
s
.
I
n
th
is
s
etu
p
,
o
n
e
class
s
ig
n
if
ies
a
h
ea
lth
y
co
n
d
itio
n
,
wh
ile
th
e
r
e
m
ain
in
g
f
iv
e
class
es
r
ep
r
esen
t
d
if
f
er
en
t
d
is
ea
s
e
lab
els.
T
h
e
ar
ch
itectu
r
e
o
f
t
h
e
MCC
N
is
illu
s
tr
ated
in
Fig
u
r
e
2
.
T
h
is
co
m
p
r
eh
en
s
iv
e
s
tr
u
ct
u
r
e
co
m
p
r
is
es
ten
co
n
v
o
l
u
tio
n
al
la
y
er
s
f
o
r
e
x
tr
a
ctin
g
ess
en
tial
f
ea
tu
r
es,
f
o
llo
wed
b
y
a
s
in
g
le
p
r
im
ar
y
ca
p
s
u
le
lay
er
an
d
a
s
in
g
le
d
is
ea
s
e
ca
p
s
u
le
lay
er
r
esp
o
n
s
ib
le
f
o
r
th
e
class
if
icatio
n
p
r
o
ce
s
s
.
I
n
ad
d
itio
n
,
th
er
e
ar
e
th
r
ee
f
u
lly
co
n
n
ec
ted
lay
er
s
,
wh
ich
p
lay
a
r
o
le
in
d
e
co
d
in
g
th
e
im
ag
e
s
eg
m
en
ts
an
d
ar
e
cr
u
cial
f
o
r
r
ec
o
n
s
tr
u
ctin
g
th
e
lo
s
s
f
u
n
ctio
n
.
T
h
is
r
ec
o
n
s
tr
u
ctio
n
p
r
o
ce
s
s
m
ea
s
u
r
es h
o
w
ef
f
ec
tiv
ely
t
h
e
al
g
o
r
ith
m
m
o
d
els th
e
p
r
o
v
id
e
d
d
ata.
T
h
e
p
r
o
ce
s
s
o
f
f
ea
tu
r
e
e
x
tr
ac
tio
n
f
r
o
m
th
e
i
n
p
u
t
im
ag
e
is
ac
h
iev
ed
th
r
o
u
g
h
co
n
v
o
lu
tio
n
al
lay
er
s
.
I
n
o
u
r
p
r
o
p
o
s
ed
s
tr
u
ctu
r
e,
t
h
er
e
ar
e
a
to
tal
o
f
ten
c
o
n
v
o
lu
tio
n
al
lay
er
s
.
T
o
f
ac
ilit
ate
a
m
ea
n
in
g
f
u
l c
o
m
p
a
r
ativ
e
an
aly
s
is
with
th
e
b
en
ch
m
ar
k
e
d
d
ataset,
th
e
in
p
u
t
im
ag
e
is
r
esized
to
2
5
6
×
2
5
6
p
ix
els.
I
t
’
s
wo
r
th
n
o
tin
g
t
h
at
th
e
b
en
c
h
m
ar
k
e
d
d
ataset
f
o
r
co
m
p
a
r
is
o
n
is
th
e
Plan
tVillag
e
d
ataset,
wh
er
e
all
im
ag
es
s
h
ar
e
th
e
s
am
e
d
im
en
s
io
n
s
o
f
2
5
6
×
2
5
6
p
ix
els.
Fig
u
r
e
1
.
Ar
c
h
itectu
r
e
o
f
en
s
e
m
b
le
m
o
d
el
p
r
ed
ictio
n
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
o
f
MCC
N
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
20
2
5
:
2
0
9
0
-
210
0
2094
3
.
3
.
Ca
ps
ule
la
y
er
T
h
e
p
r
im
ar
y
ca
p
s
u
le
lay
er
c
o
n
tain
s
a
to
tal
o
f
5
3
,
0
8
,
6
7
2
lea
r
n
ab
le
p
ar
a
m
eter
s
,
an
d
th
ese
p
ar
am
eter
s
ar
e
th
en
p
ass
ed
o
n
to
th
e
d
is
ea
s
e
ca
p
s
u
le
lay
er
,
s
er
v
in
g
as th
e
h
ig
h
er
ca
p
s
u
le
lay
er
.
I
n
th
e
t
r
an
s
itio
n
,
th
e
3
,
2
0
0
eig
h
t
-
d
im
en
s
io
n
al
v
ec
to
r
s
ar
e
m
eticu
lo
u
s
ly
m
ap
p
e
d
in
t
o
th
e
d
is
ea
s
e
ca
p
s
u
le
lay
er
,
r
esu
ltin
g
in
3
,
2
0
0
ca
p
s
u
les,
ea
ch
co
m
p
r
is
in
g
eig
h
t n
eu
r
o
n
s
ar
r
an
g
ed
i
n
a
1
×
1
s
tr
u
ctu
r
e,
as d
escr
ib
e
d
in
r
e
f
er
e
n
ce
[
3
0
].
T
h
ese
eig
h
t
-
d
im
en
s
io
n
al
v
ec
t
o
r
s
ar
e
f
u
r
th
er
tr
a
n
s
f
o
r
m
e
d
in
t
o
s
ix
class
lab
el
s
,
ex
p
an
d
in
g
t
h
eir
v
ec
to
r
s
ize
to
s
ix
teen
d
im
en
s
io
n
s
.
T
h
ese
s
ix
class
lab
el
s
r
ep
r
esen
t
f
iv
e
d
is
tin
ct
d
is
ea
s
e
ca
teg
o
r
ies
an
d
o
n
e
f
o
r
th
e
ca
teg
o
r
y
o
f
h
ea
lth
y
leav
es.
T
h
e
lin
k
weig
h
ts
co
n
n
ec
tin
g
th
e
Dis
iC
ap
s
lay
er
with
th
e
p
r
ec
ed
in
g
lay
er
en
co
m
p
ass
two
v
ital
p
ar
am
et
er
s
:
C
ij
,
wh
ich
p
e
r
tain
s
to
ea
c
h
ca
p
s
u
le
’
s
c
o
n
n
ec
tio
n
to
all
s
ix
class
lab
els,
an
d
W
ij
,
wh
ich
s
ig
n
if
ies th
e
co
n
n
e
ctio
n
b
etwe
en
s
p
ec
if
ic
n
e
u
r
o
n
s
in
th
e
o
u
tp
u
t la
y
er
.
T
h
e
to
tal
n
u
m
b
e
r
o
f
lear
n
a
b
le
C
ij
p
ar
am
eter
s
am
o
u
n
ts
to
1
9
,
2
0
0
p
ar
a
m
eter
s
(
3
,
2
0
0
ca
p
s
u
l
es
×
6
clas
s
lab
els).
Similar
ly
,
th
e
to
tal
n
u
m
b
er
o
f
lear
n
a
b
le
W
ij
p
ar
am
et
er
s
s
tan
d
s
at
2
4
,
5
7
,
6
0
0
p
ar
am
eter
s
(
8
d
im
e
n
s
io
n
s
×
1
6
d
im
e
n
s
io
n
s
×
32
,
0
0
ca
p
s
u
les
×
6
class
lab
els).
I
n
th
is
s
etu
p
,
th
e
p
r
im
ar
y
ca
p
s
u
le
lay
e
r
co
n
s
is
ts
o
f
eig
h
t
ca
p
s
u
les
lab
eled
as
u
i
,
an
d
th
ese
ca
p
s
u
les
ar
e
in
ter
co
n
n
e
cted
with
s
ix
teen
ca
p
s
u
les
la
b
eled
as
v
j
in
th
e
Dis
i
C
ap
s
lay
er
.
A
s
q
u
ash
in
g
f
u
n
ctio
n
,
as
d
escr
ib
ed
in
[
3
1
]
,
[
3
2
]
,
is
ap
p
lied
to
en
s
u
r
e
th
at
th
e
o
u
t
p
u
t
f
alls
with
in
th
e
r
an
g
e
o
f
ze
r
o
to
o
n
e.
T
h
e
f
in
al
s
tep
en
tails
ass
e
s
s
in
g
th
e
r
esu
lts
f
r
o
m
b
o
th
l
o
w
-
lev
el
ca
p
s
u
les
an
d
h
ig
h
-
lev
el
ca
p
s
u
les an
d
m
ak
i
n
g
an
y
r
eq
u
ir
e
d
ad
ju
s
tm
en
ts
.
3
.
4
.
F
ina
l
la
y
er
s
T
h
is
p
r
o
ce
s
s
g
en
er
ates
a
v
ec
t
o
r
with
d
im
en
s
io
n
s
o
f
1
6
×
5
1
2
,
wh
er
e
1
6
c
o
r
r
esp
o
n
d
s
to
th
e
d
im
en
s
io
n
o
f
th
e
Dis
iC
ap
s
lay
er
.
Su
b
s
eq
u
en
tly
,
th
e
f
u
lly
co
n
n
ec
te
d
lay
er
is
f
u
r
th
er
ex
ten
d
e
d
to
en
co
m
p
ass
1
,
0
2
4
n
eu
r
o
n
s
,
u
tili
zin
g
th
e
r
ec
tifi
ed
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
f
u
n
ctio
n
.
E
v
en
t
u
ally
,
t
h
is
ex
p
an
d
e
d
f
u
lly
co
n
n
ec
ted
lay
e
r
co
n
tain
s
7
8
4
n
eu
r
o
n
s
,
alig
n
i
n
g
with
th
e
in
p
u
t
d
im
en
s
io
n
s
o
f
t
h
e
last
C
NN
lay
er
,
wh
ich
m
ea
s
u
r
es 2
8
×
2
8
p
ix
els.
3
.
4
.
1
.
VG
G
1
9
VGG1
9
d
er
iv
es
its
n
am
e
f
r
o
m
its
s
tr
u
ctu
r
e,
co
n
s
is
tin
g
o
f
1
9
lay
e
r
s
,
in
clu
d
in
g
1
6
co
n
v
o
lu
tio
n
al
lay
er
s
an
d
3
f
u
lly
c
o
n
n
ec
ted
lay
er
s
.
T
h
e
r
e
p
ea
ted
p
atter
n
o
f
s
m
all
-
s
ized
k
er
n
els (
3
×
3
)
f
o
r
c
o
n
v
o
lu
ti
o
n
al
lay
er
s
co
n
tr
ib
u
tes
to
its
d
is
tin
ctiv
e
d
esig
n
.
W
h
ile
VG
G1
9
ex
h
ib
its
r
em
ar
k
ab
le
p
er
f
o
r
m
an
ce
,
its
m
ain
d
r
awb
ac
k
lies
in
its
r
eso
u
r
ce
-
i
n
ten
s
iv
e
n
atu
r
e
d
u
e
to
a
lar
g
e
n
u
m
b
er
o
f
p
ar
am
eter
s
.
T
h
is
ca
n
lead
to
ch
all
en
g
es
in
d
ep
lo
y
in
g
th
e
m
o
d
el
o
n
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
d
ev
ices.
3
.
4
.
2
.
ResNet
1
0
1
W
h
ile
R
es
Net1
0
1
ad
d
r
ess
es
ch
allen
g
es
r
elate
d
t
o
tr
ain
in
g
d
ee
p
n
etwo
r
k
s
,
its
co
m
p
u
tatio
n
al
co
m
p
lex
ity
m
ay
p
o
s
e
ch
allen
g
es
f
o
r
d
ep
l
o
y
m
en
t
o
n
r
es
o
u
r
ce
-
c
o
n
s
tr
ain
ed
d
e
v
ices.
Mo
d
el
co
m
p
r
ess
io
n
tech
n
iq
u
es a
r
e
o
f
ten
ex
p
lo
r
e
d
to
m
itig
ate
th
is
is
s
u
e.
3
.
4
.
3
.
G
o
o
g
leNe
t
T
h
e
s
tan
d
o
u
t
f
ea
tu
r
e
o
f
Go
o
g
leNe
t
is
th
e
u
s
e
o
f
th
e
in
ce
p
tio
n
m
o
d
u
le,
wh
ich
em
p
lo
y
s
m
u
ltip
le
co
n
v
o
l
u
tio
n
al
f
ilter
s
o
f
d
if
f
er
en
t
s
izes
(
1
×
1
,
3
×
3
,
a
n
d
5
×
5
)
an
d
a
p
o
o
lin
g
lay
e
r
in
p
ar
all
el.
T
h
is
allo
ws
th
e
n
etwo
r
k
to
ca
p
tu
r
e
f
ea
tu
r
es a
t
v
ar
io
u
s
s
p
atial
s
ca
les with
in
th
e
s
am
e
lay
er
.
3
.
4
.
4
.
Da
t
a
s
et
d
escript
io
n
Fo
r
o
u
r
ex
p
er
im
en
tal
w
o
r
k
,
w
e
’
v
e
ass
em
b
led
a
r
ea
l
-
tim
e
d
at
aset
co
m
p
r
is
in
g
s
ix
d
is
tin
ct
class
lab
els.
T
h
is
d
ataset
en
co
m
p
ass
es
v
ar
i
o
u
s
ca
teg
o
r
ies,
s
p
ec
if
ically
,
“
Dis
in
f
ec
ted
leaf
,
”
“
E
ar
ly
B
lig
h
t,
”
“
Mo
s
aic
v
ir
u
s
,
”
“
L
ea
f
s
p
o
t,
”
“
B
ac
ter
ial
Sp
o
t,
”
an
d
“
Po
wd
e
r
y
Mild
ew.
”
O
u
r
r
esear
ch
p
r
im
a
r
ily
f
o
c
u
s
es
o
n
ad
d
r
ess
in
g
th
e
f
iv
e
m
o
s
t
co
m
m
o
n
d
is
ea
s
es
th
at
ty
p
ically
af
f
lict
m
u
s
k
m
elo
n
p
l
an
ts
.
T
h
e
im
ag
es
u
tili
ze
d
in
t
h
is
s
tu
d
y
h
a
v
e
b
ee
n
s
o
u
r
ce
d
f
r
o
m
a
o
n
e
-
ac
r
e
a
g
r
ic
u
ltu
r
al
p
lo
t
s
itu
ated
in
Sath
ap
p
ad
i
Villag
e,
Attu
r
T
alu
k
,
Salem
Dis
tr
ict,
T
am
il
Nad
u
.
T
h
is
lo
ca
tio
n
’
s
g
eo
g
r
ap
h
ic
co
o
r
d
in
ates
ar
e
ap
p
r
o
x
im
a
tely
1
1
°
3
5
’
5
3
.
2
1
7
6
’’
N
f
o
r
l
atitu
d
e
an
d
7
8
°
3
5
’
4
8
.
4
8
7
2
’’
E
f
o
r
lo
n
g
itu
d
e
[3
0
]
,
[3
2
]
.
Mu
s
k
m
elo
n
,
k
n
o
wn
f
o
r
its
p
r
o
f
itab
ilit
y
,
h
as
a
r
elativ
ely
s
h
o
r
t
life
s
p
an
,
ty
p
ically
ar
o
u
n
d
6
5
d
a
y
s
.
Du
r
in
g
t
h
is
b
r
ief
p
er
i
o
d
,
an
y
o
u
tb
r
ea
k
o
f
d
is
ea
s
e
ca
n
h
a
v
e
a
d
ev
astatin
g
im
p
ac
t
o
n
th
e
e
n
tire
cr
o
p
,
lea
d
in
g
to
s
ig
n
if
ican
t
y
ield
lo
s
s
es.
C
o
n
s
eq
u
en
tly
,
t
h
er
e
is
a
p
r
ess
in
g
n
ee
d
f
o
r
t
h
e
d
e
v
elo
p
m
e
n
t
o
f
an
ea
r
l
y
d
is
ea
s
e
p
r
ed
ictio
n
s
y
s
tem
to
m
itig
ate
th
ese
r
is
k
s
.
Fro
m
t
h
is
v
ast
r
ep
o
s
ito
r
y
,
we
ex
tr
ac
ted
im
ag
es
r
elev
an
t
to
th
e
f
i
v
e
m
ajo
r
d
is
ea
s
es
th
at
co
m
m
o
n
ly
af
f
ec
t
p
lan
ts
,
an
d
th
ese
im
ag
e
s
wer
e
em
p
lo
y
ed
as
a
b
en
ch
m
ar
k
d
ataset
f
o
r
o
u
r
d
is
ea
s
e
class
if
icatio
n
ef
f
o
r
ts
.
As
a
s
tan
d
a
r
d
p
r
ac
tice,
all
th
e
im
ag
es
in
th
is
d
ataset
h
a
v
e
b
ee
n
u
n
if
o
r
m
ly
r
esized
to
d
im
en
s
io
n
s
o
f
2
5
6
×
256.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
mp
r
o
vin
g
fa
r
min
g
b
y
q
u
ickly
d
etec
tin
g
mu
s
kme
lo
n
p
la
n
t d
is
ea
s
es u
s
in
g
…
(
Dee
b
a
K
a
n
n
a
n
)
2095
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
is
e
v
alu
ated
u
s
in
g
a
r
an
g
e
o
f
k
ey
m
etr
ics,
f
o
cu
s
in
g
o
n
ac
c
u
r
ac
y
an
d
l
o
s
s
.
Du
r
in
g
5
0
e
p
o
ch
s
,
tr
ai
n
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
ies
an
d
lo
s
s
v
alu
es
ar
e
r
ec
o
r
d
ed
f
o
r
ea
ch
m
o
d
el.
Af
ter
tr
ain
in
g
,
m
o
d
els
ar
e
test
ed
o
n
3
0
%
o
f
th
e
u
n
u
s
ed
d
ataset
to
m
ea
s
u
r
e
th
eir
ac
cu
r
ac
y
.
Fo
r
p
r
ed
ictio
n
s
,
an
en
s
em
b
le
lear
n
in
g
m
o
d
el
is
u
s
ed
with
m
ajo
r
ity
v
o
tin
g
t
o
s
elec
t
th
e
m
o
s
t
ac
cu
r
ate
m
o
d
e
l.
T
h
e
tr
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
f
u
n
ctio
n
o
f
R
esNet1
0
1
is
s
h
o
wn
in
Fig
u
r
e
3
.
T
h
e
tr
ain
i
n
g
ac
cu
r
ac
y
o
f
t
h
e
R
esNet1
0
1
m
o
d
el
ex
h
i
b
its
a
p
r
o
g
r
ess
iv
e
in
cr
ea
s
e
f
r
o
m
a
n
in
itial
ac
cu
r
ac
y
o
f
6
2
.
5
3
%
to
a
p
ea
k
o
f
9
8
.
5
9
%.
T
h
e
v
alid
atio
n
ac
cu
r
ac
y
o
f
th
e
R
esNet1
0
1
m
o
d
el
f
o
llo
ws
a
s
im
ilar
in
cr
ea
s
in
g
tr
en
d
,
s
tar
tin
g
at
6
6
.
4
1
%
an
d
r
ea
ch
in
g
9
2
.
3
7
% in
th
e
f
i
n
al
e
p
o
ch
.
Fig
u
r
e
3
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
v
alu
es
R
esNet1
0
1
T
h
e
tr
ain
in
g
an
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
f
u
n
ctio
n
o
f
VGG1
9
is
s
h
o
wn
in
Fig
u
r
e
4
.
T
h
e
tr
ain
in
g
ac
cu
r
ac
y
o
f
th
e
VGG1
9
m
o
d
el
s
tead
ily
in
cr
ea
s
ed
with
ea
c
h
ep
o
ch
,
r
ea
ch
in
g
a
p
ea
k
o
f
9
8
.
5
7
%
in
th
e
f
in
al
ep
o
ch
.
T
h
e
v
alid
atio
n
ac
cu
r
a
cy
o
f
th
e
VGG1
9
m
o
d
el
f
o
l
lo
wed
a
s
im
ilar
p
o
s
itiv
e
tr
ajec
to
r
y
.
Star
tin
g
at
6
6
.
4
1
%,
th
e
ac
cu
r
ac
y
s
tead
il
y
in
cr
ea
s
ed
a
n
d
r
ea
ch
ed
9
6
.
9
5
%
in
th
e
f
i
n
al
ep
o
c
h
.
T
h
is
alig
n
m
en
t
with
th
e
tr
ain
in
g
ac
cu
r
ac
y
d
e
m
o
n
s
tr
ate
s
th
e
m
o
d
el
’
s
ab
ilit
y
to
g
en
er
a
lize
well
to
d
ata
it h
as n
o
t seen
d
u
r
i
n
g
tr
ain
i
n
g
.
Fig
u
r
e
4
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
v
alu
es VG
G1
9
T
h
e
tr
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
a
n
d
lo
s
s
f
u
n
ctio
n
o
f
Go
o
g
leNe
t
is
s
h
o
wn
in
Fig
u
r
e
5
.
T
h
e
tr
ain
in
g
ac
cu
r
ac
y
o
f
th
e
Go
o
g
leNe
t
m
o
d
el
ex
h
ib
its
a
p
r
o
g
r
ess
iv
e
in
c
r
ea
s
e
f
r
o
m
a
n
in
itial
ac
cu
r
ac
y
o
f
6
2
.
5
3
%
to
a
p
ea
k
o
f
9
8
.
1
3
%.
T
h
e
v
alid
atio
n
ac
cu
r
ac
y
o
f
t
h
e
Go
o
g
leNe
t
m
o
d
el
f
o
llo
ws
a
s
im
ilar
in
cr
ea
s
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
20
2
5
:
2
0
9
0
-
210
0
2096
tr
en
d
,
s
tar
tin
g
at
6
6
.
4
1
%
an
d
r
ea
ch
in
g
9
2
.
3
7
%
in
th
e
f
in
al
ep
o
ch
.
T
h
e
tr
ain
in
g
an
d
v
alid
atio
n
ac
cu
r
ac
y
a
n
d
lo
s
s
f
u
n
ctio
n
o
f
MCC
N
is
s
h
o
wn
in
Fig
u
r
e
6
.
T
h
e
MCC
N
ex
h
ib
ited
n
o
tewo
r
th
y
p
e
r
f
o
r
m
an
ce
d
u
r
in
g
b
o
th
tr
ain
in
g
an
d
v
alid
atio
n
p
h
ases
,
as
d
ep
icted
b
y
th
e
ev
o
lv
in
g
ac
c
u
r
ac
y
v
alu
es
o
v
er
th
e
c
o
u
r
s
e
o
f
5
0
ep
o
c
h
s
.
T
h
e
tr
ain
in
g
ac
cu
r
ac
y
co
n
s
is
ten
tly
im
p
r
o
v
e
d
th
r
o
u
g
h
o
u
t
th
e
ep
o
ch
s
,
s
tar
tin
g
at
8
5
.
9
9
7
%
an
d
r
ea
ch
in
g
a
n
im
p
r
ess
iv
e
9
9
.
1
%.
T
h
is
p
r
o
g
r
ess
iv
e
in
cr
ea
s
e
u
n
d
er
s
co
r
es
th
e
m
o
d
el
’
s
ca
p
ab
ilit
y
to
ef
f
ec
tiv
ely
lear
n
an
d
ad
ap
t
to
th
e
co
m
p
le
x
ities
o
f
th
e
d
ataset.
T
h
e
v
alid
atio
n
ac
cu
r
ac
y
m
ir
r
o
r
ed
th
e
tr
ain
in
g
ac
cu
r
ac
y
tr
en
d
,
d
em
o
n
s
tr
atin
g
a
p
ar
allel
in
cr
ea
s
e
f
r
o
m
an
in
itial
7
2
.
9
5
%
to
a
p
ea
k
o
f
9
8
.
7
4
%.
T
h
is
s
y
n
ch
r
o
n
izatio
n
in
d
icate
s
th
at
th
e
m
o
d
el
n
o
t
o
n
l
y
p
e
r
f
o
r
m
ed
well
o
n
th
e
tr
ain
in
g
s
et
b
u
t
also
m
ain
tain
ed
its
ef
f
ec
tiv
e
n
ess
wh
en
co
n
f
r
o
n
te
d
with
p
r
ev
i
o
u
s
ly
u
n
s
ee
n
d
ata
d
u
r
in
g
v
alid
atio
n
.
T
h
e
co
n
s
is
ten
t
r
is
e
in
v
alid
atio
n
ac
cu
r
ac
y
s
ig
n
if
ies
th
e
r
o
b
u
s
tn
ess
o
f
th
e
MCC
N
in
m
ak
in
g
ac
cu
r
ate
p
r
ed
ictio
n
s
o
n
d
iv
er
s
e
d
ata,
r
ein
f
o
r
ci
n
g
its
p
o
ten
tial f
o
r
r
ea
l
-
wo
r
l
d
ap
p
licatio
n
s
.
T
h
e
test
in
g
ac
cu
r
ac
y
o
f
th
e
m
o
d
els
is
s
h
o
wn
in
T
ab
le
2.
T
h
e
ex
p
er
im
e
n
tal
r
esu
lts
u
n
eq
u
i
v
o
ca
lly
d
e
m
o
n
s
tr
ate
th
e
s
u
p
er
io
r
ity
o
f
th
e
MCC
N
-
b
ased
en
s
em
b
le
lear
n
in
g
m
o
d
el.
T
h
is
m
o
d
el
s
u
r
p
a
s
s
es
its
co
u
n
ter
p
ar
ts
,
ac
h
iev
in
g
an
o
u
ts
tan
d
in
g
ac
cu
r
ac
y
r
ate
o
f
9
9
.
5
4
%.
Fig
u
r
e
5
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
v
alu
es Go
o
g
leNe
t
Fig
u
r
e
6
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
v
alu
es M
C
C
N
T
ab
le
2
.
T
esti
n
g
ac
c
u
r
ac
y
o
f
d
if
f
er
en
t
m
o
d
els
M
o
d
e
l
s
R
e
sN
e
t
1
0
1
V
G
G
1
9
G
o
o
g
l
e
N
e
t
M
C
C
N
En
se
mb
l
e
m
o
d
e
l
Te
st
i
n
g
a
c
c
u
r
a
c
y
9
8
.
6
7
%
9
8
.
7
3
%
9
8
.
3
6
%
9
9
.
2
5
%
9
9
.
5
4
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
mp
r
o
vin
g
fa
r
min
g
b
y
q
u
ickly
d
etec
tin
g
mu
s
kme
lo
n
p
la
n
t d
is
ea
s
es u
s
in
g
…
(
Dee
b
a
K
a
n
n
a
n
)
2097
5.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
p
r
esen
ts
an
en
s
em
b
le
lear
n
in
g
m
o
d
el
co
m
b
i
n
in
g
MCC
N
wi
th
p
r
e
-
tr
ain
ed
m
o
d
els an
d
a
v
o
tin
g
s
y
s
tem
f
o
r
ea
r
ly
d
ete
ctio
n
o
f
p
lan
t
d
is
ea
s
es
an
d
p
ests
,
ac
h
iev
in
g
an
im
p
r
ess
iv
e
9
9
.
5
4
%
ac
cu
r
ac
y
.
T
h
e
m
o
d
el
s
u
r
p
ass
es
estab
li
s
h
ed
ar
ch
itectu
r
es
lik
e
R
esNe
t1
0
1
,
VGG1
9
,
an
d
Go
o
g
leN
et,
p
r
o
m
o
tin
g
I
o
T
-
d
r
iv
en
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
to
en
h
an
ce
cr
o
p
y
ield
s
an
d
e
n
v
ir
o
n
m
e
n
tal
s
u
s
tain
ab
ilit
y
.
Fu
tu
r
e
wo
r
k
i
n
clu
d
es
f
ield
tr
ials
to
v
alid
ate
r
ea
l
-
wo
r
ld
ap
p
licab
ilit
y
,
o
p
tim
izin
g
t
h
e
MCC
N
ar
ch
itectu
r
e,
an
d
in
teg
r
atin
g
a
d
d
itio
n
al
d
ata
s
o
u
r
ce
s
lik
e
m
eteo
r
o
lo
g
i
ca
l
an
d
s
o
il
in
f
o
r
m
atio
n
.
Scal
ab
ilit
y
f
o
r
lar
g
e
-
s
ca
le
f
ar
m
in
g
an
d
co
m
p
atib
ilit
y
with
I
o
T
s
y
s
tem
s
ar
e
k
ey
a
r
ea
s
f
o
r
p
r
ac
tical
d
ep
l
o
y
m
en
t.
T
h
is
ap
p
r
o
ac
h
aim
s
to
r
e
v
o
lu
tio
n
ize
p
r
o
ac
tiv
e
d
is
ea
s
e
co
n
tr
o
l in
ag
r
icu
ltu
r
e.
F
U
N
DI
N
G
I
N
F
O
RM
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
.
A
U
T
H
O
R
C
O
NT
R
I
B
UT
I
O
N
S
ST
AT
E
M
E
NT
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Dee
b
a
Kan
n
an
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Nag
am
u
th
u
Kr
is
h
n
a
n
Su
n
d
ar
asrin
iv
asa
San
k
ar
an
ar
a
y
an
an
✓
✓
✓
✓
✓
✓
✓
Sh
an
m
u
g
asu
n
d
ar
am
Ven
k
atar
ajan
✓
✓
✓
✓
✓
✓
✓
R
ash
im
a
Ma
h
ajan
✓
✓
✓
✓
✓
B
r
in
d
h
a
Gu
n
asek
ar
a
n
✓
✓
✓
✓
✓
Pan
d
i M
ah
ar
ajan
Mu
r
u
g
am
a
n
i
✓
✓
✓
✓
✓
Kar
th
ik
ey
an
Dh
an
d
ap
an
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
tu
a
li
z
a
ti
o
n
M
:
M
e
th
o
d
o
l
o
g
y
So
:
So
ftwa
re
Va
:
Va
li
d
a
ti
o
n
Fo
:
Fo
rm
a
l
a
n
a
ly
sis
I
:
I
n
v
e
stig
a
ti
o
n
R
:
R
e
so
u
rc
e
s
D
:
D
a
ta Cu
ra
ti
o
n
O
:
Wr
it
in
g
-
O
r
ig
i
n
a
l
Dra
ft
E
:
Wr
it
in
g
-
Re
v
iew
&
E
d
it
in
g
Vi
:
Vi
su
a
li
z
a
ti
o
n
Su
:
Su
p
e
rv
isio
n
P
:
P
ro
jec
t
a
d
m
in
istrati
o
n
Fu
:
Fu
n
d
in
g
a
c
q
u
isit
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
Data
av
ailab
ilit
y
is
n
o
t
a
p
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
c
r
ea
ted
o
r
an
al
y
ze
d
in
t
h
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
Y
.
K
a
w
a
s
a
k
i
,
H
.
U
g
a
,
S
.
K
a
g
i
w
a
d
a
,
a
n
d
H
.
I
y
a
t
o
m
i
,
“
B
a
si
c
s
t
u
d
y
o
f
a
u
t
o
ma
t
e
d
d
i
a
g
n
o
si
s
o
f
v
i
r
a
l
p
l
a
n
t
d
i
sea
s
e
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
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
su
b
s
e
ri
e
s
L
e
c
t
u
r
e
N
o
t
e
s
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
9
4
7
5
,
2
0
1
5
,
p
p
.
6
3
8
–
6
4
5
.
[
2
]
S
.
H
.
L
e
e
,
C
.
S
.
C
h
a
n
,
P
.
W
i
l
k
i
n
,
a
n
d
P
.
R
e
m
a
g
n
i
n
o
,
“
D
e
e
p
-
p
l
a
n
t
:
p
l
a
n
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
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
s
,
”
i
n
2
0
1
5
I
E
E
E
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
P
r
o
c
e
s
s
i
n
g
(
I
C
I
P
)
,
S
e
p
.
2
0
1
5
,
p
p
.
4
5
2
–
4
5
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
P
.
2
0
1
5
.
7
3
5
0
8
3
9
.
[
3
]
S
.
P
.
M
o
h
a
n
t
y
,
D
.
P
.
H
u
g
h
e
s,
a
n
d
M
.
S
a
l
a
t
h
é
,
“
U
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
m
a
g
e
-
b
a
s
e
d
p
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
,
”
F
ro
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
7
,
S
e
p
.
2
0
1
6
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
1
6
.
0
1
4
1
9
.
[
4
]
A
.
R
a
mc
h
a
r
a
n
,
K
.
B
a
r
a
n
o
w
s
k
i
,
P
.
M
c
C
l
o
s
k
e
y
,
B
.
A
h
m
e
d
,
J.
Le
g
g
,
a
n
d
D
.
P
.
H
u
g
h
e
s
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
ma
g
e
-
b
a
se
d
c
a
ss
a
v
a
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
,
”
Fr
o
n
t
i
e
rs i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
8
,
O
c
t
.
2
0
1
7
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
1
7
.
0
1
8
5
2
.
[
5
]
J.
S
h
i
j
i
e
,
J.
P
e
i
y
i
,
H
.
S
i
p
i
n
g
,
a
n
d
S
l
.
H
a
i
b
o
,
“
A
u
t
o
m
a
t
i
c
d
e
t
e
c
t
i
o
n
o
f
t
o
ma
t
o
d
i
s
e
a
s
e
s
a
n
d
p
e
st
s
b
a
se
d
o
n
l
e
a
f
i
ma
g
e
s
,
”
i
n
2
0
1
7
C
h
i
n
e
se
Au
t
o
m
a
t
i
o
n
C
o
n
g
ress
(
C
A
C
)
,
O
c
t
.
2
0
1
7
,
v
o
l
.
2
0
1
7
-
Ja
n
u
a
,
p
p
.
2
5
3
7
–
2
5
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
C
A
C
.
2
0
1
7
.
8
2
4
3
3
8
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
3
,
J
u
n
e
20
2
5
:
2
0
9
0
-
210
0
2098
[
6
]
X
.
Z
h
a
n
g
,
Y
.
Q
i
a
o
,
F
.
M
e
n
g
,
C
.
F
a
n
,
a
n
d
M
.
Z
h
a
n
g
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
m
a
i
z
e
l
e
a
f
d
i
s
e
a
se
s
u
si
n
g
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
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
6
,
p
p
.
3
0
3
7
0
–
3
0
3
7
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
8
.
2
8
4
4
4
0
5
.
[
7
]
U
.
P
.
S
i
n
g
h
,
S
.
S
.
C
h
o
u
h
a
n
,
S
.
J
a
i
n
,
a
n
d
S
.
J
a
i
n
,
“
M
u
l
t
i
l
a
y
e
r
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
f
m
a
n
g
o
l
e
a
v
e
s
i
n
f
e
c
t
e
d
b
y
a
n
t
h
r
a
c
n
o
s
e
d
i
s
e
a
s
e
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
7
,
p
p
.
43721
–
4
3
7
2
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
1
9
.
2
9
0
7
3
8
3
.
[
8
]
J.
S
u
n
,
Y
.
Y
a
n
g
,
X
.
H
e
,
a
n
d
X
.
W
u
,
“
N
o
r
t
h
e
r
n
ma
i
z
e
l
e
a
f
b
l
i
g
h
t
d
e
t
e
c
t
i
o
n
u
n
d
e
r
c
o
m
p
l
e
x
f
i
e
l
d
e
n
v
i
r
o
n
me
n
t
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
3
3
6
7
9
–
3
3
6
8
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
7
3
6
5
8
.
[
9
]
W.
-
J.
H
u
,
J
.
F
a
n
,
Y
.
-
X
.
D
u
,
B
.
-
S
.
L
i
,
N
.
X
i
o
n
g
,
a
n
d
E
.
B
e
k
k
e
r
i
n
g
,
“
M
D
F
C
–
R
e
sN
e
t
:
a
n
a
g
r
i
c
u
l
t
u
r
a
l
i
o
t
s
y
s
t
e
m
t
o
a
c
c
u
r
a
t
e
l
y
r
e
c
o
g
n
i
z
e
c
r
o
p
d
i
s
e
a
s
e
s,
”
I
EEE
Ac
c
e
s
s
,
v
o
l
.
8
,
p
p
.
1
1
5
2
8
7
–
1
1
5
2
9
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
1
2
3
7
.
[
1
0
]
Z.
Zi
n
o
n
o
s,
S
.
G
k
e
l
i
o
s
,
A
.
F
.
K
h
a
l
i
f
e
h
,
D
.
G
.
H
a
d
j
i
mi
t
si
s,
Y
.
S
.
B
o
u
t
a
l
i
s,
a
n
d
S
.
A
.
C
h
a
t
z
i
c
h
r
i
st
o
f
i
s
,
“
G
r
a
p
e
l
e
a
f
d
i
s
e
a
s
e
s
i
d
e
n
t
i
f
i
c
a
t
i
o
n
s
y
s
t
e
m
u
si
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
a
n
d
L
o
R
a
t
e
c
h
n
o
l
o
g
y
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
2
2
–
1
3
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
3
8
0
5
0
.
[
1
1
]
E.
El
f
a
t
i
mi
,
R
.
Er
y
i
g
i
t
,
a
n
d
L.
El
f
a
t
i
mi
,
“
B
e
a
n
s
l
e
a
f
d
i
se
a
ses
c
l
a
s
si
f
i
c
a
t
i
o
n
u
si
n
g
M
o
b
i
l
e
N
e
t
m
o
d
e
l
s
,
”
I
EEE
Ac
c
e
s
s
,
v
o
l
.
1
0
,
p
p
.
9
4
7
1
–
9
4
8
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
4
2
8
1
7
.
[
1
2
]
V
.
K
.
V
i
s
h
n
o
i
,
K
.
K
u
mar,
B
.
K
u
m
a
r
,
S
.
M
o
h
a
n
,
a
n
d
A
.
A
.
K
h
a
n
,
“
D
e
t
e
c
t
i
o
n
o
f
a
p
p
l
e
p
l
a
n
t
d
i
s
e
a
s
e
s
u
si
n
g
l
e
a
f
i
m
a
g
e
s
t
h
r
o
u
g
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
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
6
5
9
4
–
6
6
0
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
3
2
9
1
7
.
[
1
3
]
N
.
F
a
r
a
h
,
N
.
D
r
a
c
k
,
H
.
D
a
w
e
l
,
a
n
d
R
.
B
u
e
t
t
n
e
r
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
t
h
e
d
e
t
e
c
t
i
o
n
o
f
i
n
f
e
st
e
d
so
y
b
e
a
n
l
e
a
v
e
s
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
9
9
6
7
0
–
9
9
6
7
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
1
3
9
7
8
.
[
1
4
]
E.
C
.
T
e
t
i
l
a
e
t
a
l
.
,
“
A
u
t
o
ma
t
i
c
r
e
c
o
g
n
i
t
i
o
n
o
f
s
o
y
b
e
a
n
l
e
a
f
d
i
se
a
ses
u
si
n
g
U
A
V
i
ma
g
e
s
a
n
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
s
,
”
I
EE
E
G
e
o
sc
i
e
n
c
e
a
n
d
R
e
m
o
t
e
S
e
n
si
n
g
L
e
t
t
e
r
s
,
v
o
l
.
1
7
,
n
o
.
5
,
p
p
.
9
0
3
–
9
0
7
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
LG
R
S
.
2
0
1
9
.
2
9
3
2
3
8
5
.
[
1
5
]
J.
L
i
,
C
.
X
u
,
L
.
J
i
a
n
g
,
Y
.
X
i
a
o
,
L
.
D
e
n
g
,
a
n
d
Z.
H
a
n
,
“
D
e
t
e
c
t
i
o
n
a
n
d
a
n
a
l
y
si
s
o
f
b
e
h
a
v
i
o
r
t
r
a
j
e
c
t
o
r
y
f
o
r
s
e
a
c
u
c
u
mb
e
r
s
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
8
8
3
2
–
1
8
8
4
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
6
2
8
2
3
.
[1
6
]
B
.
L
i
u
,
C
.
Ta
n
,
S
.
Li
,
J
.
H
e
,
a
n
d
H
.
W
a
n
g
,
“
A
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
m
e
t
h
o
d
b
a
s
e
d
o
n
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sari
a
l
n
e
t
w
o
r
k
s
f
o
r
g
r
a
p
e
l
e
a
f
d
i
s
e
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
0
2
1
8
8
–
1
0
2
1
9
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
8
8
3
9
.
[1
7
]
Q
.
Ze
n
g
,
X
.
M
a
,
B
.
C
h
e
n
g
,
E.
Z
h
o
u
,
a
n
d
W
.
P
a
n
g
,
“
GANs
-
b
a
s
e
d
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
f
o
r
c
i
t
r
u
s
d
i
s
e
a
s
e
se
v
e
r
i
t
y
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
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
7
2
8
8
2
–
1
7
2
8
9
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
2
5
1
9
6
.
[
18
]
Y
.
A
i
,
C
.
S
u
n
,
J.
Ti
e
,
a
n
d
X
.
C
a
i
,
“
R
e
s
e
a
r
c
h
o
n
r
e
c
o
g
n
i
t
i
o
n
mo
d
e
l
o
f
c
r
o
p
d
i
s
e
a
s
e
s
a
n
d
i
n
s
e
c
t
p
e
st
s
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
i
n
h
a
r
s
h
e
n
v
i
r
o
n
m
e
n
t
s
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
7
1
6
8
6
–
1
7
1
6
9
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
2
5
3
2
5
.
[
19
]
T
.
N
.
P
h
a
m,
L.
V
a
n
T
r
a
n
,
a
n
d
S
.
V
.
T
.
D
a
o
,
“
Ea
r
l
y
d
i
s
e
a
se
c
l
a
s
si
f
i
c
a
t
i
o
n
o
f
man
g
o
l
e
a
v
e
s
u
si
n
g
f
e
e
d
-
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
h
y
b
r
i
d
m
e
t
a
h
e
u
r
i
st
i
c
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
,
”
I
E
EE
Ac
c
e
s
s
,
v
o
l
.
8
,
p
p
.
1
8
9
9
6
0
–
1
8
9
9
7
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
0
.
3
0
3
1
9
1
4
.
[2
0
]
C
.
Zh
o
u
,
S
.
Z
h
o
u
,
J.
X
i
n
g
,
a
n
d
J.
S
o
n
g
,
“
To
m
a
t
o
l
e
a
f
d
i
sea
s
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
y
r
e
st
r
u
c
t
u
r
e
d
d
e
e
p
r
e
s
i
d
u
a
l
d
e
n
s
e
n
e
t
w
o
r
k
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
2
8
8
2
2
–
2
8
8
3
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
5
8
9
4
7
.
[2
1
]
C
.
Z
h
o
u
,
Z.
Z
h
a
n
g
,
S
.
Z
h
o
u
,
J.
X
i
n
g
,
Q
.
W
u
,
a
n
d
J.
S
o
n
g
,
“
G
r
a
p
e
l
e
a
f
s
p
o
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
n
d
e
r
l
i
m
i
t
e
d
s
a
m
p
l
e
s
b
y
f
i
n
e
g
r
a
i
n
e
d
-
GAN,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
0
0
4
8
0
–
1
0
0
4
8
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
9
7
0
5
0
.
[
2
2
]
S
.
M
.
H
a
ss
a
n
a
n
d
A
.
K
.
M
a
j
i
,
“
P
l
a
n
t
d
i
s
e
a
s
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
si
n
g
a
n
o
v
e
l
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
EE
E
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
5
3
9
0
–
5
4
0
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
4
1
3
7
1
.
[
2
3
]
H
.
A
mi
n
,
A
.
D
a
r
w
i
s
h
,
A
.
E.
H
a
ssa
n
i
e
n
,
a
n
d
M
.
S
o
l
i
m
a
n
,
“
En
d
-
to
-
e
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
c
o
r
n
l
e
a
f
d
i
se
a
s
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
3
1
1
0
3
–
3
1
1
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
5
9
6
7
8
.
[
2
4
]
J.
C
h
e
n
,
W
.
C
h
e
n
,
A
.
Ze
b
,
S
.
Y
a
n
g
,
a
n
d
D
.
Z
h
a
n
g
,
“
L
i
g
h
t
w
e
i
g
h
t
i
n
c
e
p
t
i
o
n
n
e
t
w
o
r
k
s
f
o
r
t
h
e
r
e
c
o
g
n
i
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
o
f
r
i
c
e
p
l
a
n
t
d
i
se
a
se
s,
”
I
EE
E
S
e
n
so
rs
J
o
u
r
n
a
l
,
v
o
l
.
2
2
,
n
o
.
1
4
,
p
p
.
1
4
6
2
8
–
1
4
6
3
8
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
2
.
3
1
8
2
3
0
4
.
[
2
5
]
K
.
Li
u
a
n
d
X
.
Z
h
a
n
g
,
“
P
i
TL
i
D
:
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
l
a
n
t
d
i
se
a
se
f
r
o
m
l
e
a
f
i
ma
g
e
s
b
a
se
d
o
n
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
EEE/
A
C
M
T
r
a
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
B
i
o
l
o
g
y
a
n
d
Bi
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
0
,
n
o
.
2
,
p
p
.
1
2
7
8
–
1
2
8
8
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
B
B
.
2
0
2
2
.
3
1
9
5
2
9
1
.
[
2
6
]
M
.
M
a
so
o
d
e
t
a
l
.
,
“
M
a
i
z
e
N
e
t
:
a
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
e
f
f
e
c
t
i
v
e
r
e
c
o
g
n
i
t
i
o
n
o
f
ma
i
z
e
p
l
a
n
t
l
e
a
f
d
i
se
a
ses
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
5
2
8
6
2
–
5
2
8
7
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
0
2
6
0
.
[
2
7
]
K
.
M
.
H
o
sn
y
,
W
.
M
.
El
-
H
a
d
y
,
F
.
M
.
S
a
my
,
E
.
V
r
o
c
h
i
d
o
u
,
a
n
d
G
.
A
.
P
a
p
a
k
o
s
t
a
s
,
“
M
u
l
t
i
-
c
l
a
ss
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
p
l
a
n
t
l
e
a
f
d
i
se
a
ses
u
si
n
g
f
e
a
t
u
r
e
f
u
si
o
n
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
a
n
d
l
o
c
a
l
b
i
n
a
r
y
p
a
t
t
e
r
n
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
6
2
3
0
7
–
6
2
3
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
6
7
3
0
.
[
2
8
]
A
.
A
l
h
a
r
b
i
,
M
.
U
.
G
.
K
h
a
n
,
a
n
d
B
.
Ta
y
y
a
b
a
,
“
W
h
e
a
t
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
c
o
n
t
i
n
u
a
l
l
e
a
r
n
i
n
g
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
9
0
0
1
6
–
9
0
0
2
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
0
4
3
5
8
.
[
2
9
]
S
.
A
b
i
n
a
y
a
,
K
.
U
.
K
u
ma
r
,
a
n
d
A
.
S
.
A
l
p
h
o
n
se
,
“
C
a
sc
a
d
i
n
g
a
u
t
o
e
n
c
o
d
e
r
w
i
t
h
a
t
t
e
n
t
i
o
n
r
e
si
d
u
a
l
U
-
n
e
t
f
o
r
mu
l
t
i
-
c
l
a
s
s
p
l
a
n
t
l
e
a
f
d
i
s
e
a
se
seg
men
t
a
t
i
o
n
a
n
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
9
8
1
5
3
–
9
8
1
7
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
3
.
3
3
1
2
7
1
8
.
[3
0
]
M
.
A
.
La
t
i
f
e
t
a
l
.
,
“
En
h
a
n
c
e
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
o
f
f
e
e
l
e
a
f
b
i
o
t
i
c
st
r
e
ss
b
y
sy
n
e
r
g
i
z
i
n
g
f
e
a
t
u
r
e
c
o
n
c
a
t
e
n
a
t
i
o
n
a
n
d
d
i
me
n
s
i
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
0
0
8
8
7
–
1
0
0
9
0
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
1
4
5
9
0
.
[3
1
]
Y
.
Y
.
B
a
y
d
i
l
l
i
a
n
d
Ü
.
A
t
i
l
a
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
w
h
i
t
e
b
l
o
o
d
c
e
l
l
s
u
s
i
n
g
c
a
p
su
l
e
n
e
t
w
o
r
k
s,
”
C
o
m
p
u
t
e
r
i
ze
d
M
e
d
i
c
a
l
I
m
a
g
i
n
g
a
n
d
G
ra
p
h
i
c
s
,
v
o
l
.
8
0
,
p
.
1
0
1
6
9
9
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
m
e
d
i
ma
g
.
2
0
2
0
.
1
0
1
6
9
9
.
[3
2
]
S
.
S
a
b
o
u
r
,
N
.
F
r
o
ss
t
,
a
n
d
G
.
E
.
H
i
n
t
o
n
,
“
D
y
n
a
m
i
c
r
o
u
t
i
n
g
b
e
t
w
e
e
n
c
a
p
s
u
l
e
s,
”
a
rX
i
v
p
re
p
r
i
n
t
1
7
1
0
.
0
9
8
2
9
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
I
mp
r
o
vin
g
fa
r
min
g
b
y
q
u
ickly
d
etec
tin
g
mu
s
kme
lo
n
p
la
n
t d
is
ea
s
es u
s
in
g
…
(
Dee
b
a
K
a
n
n
a
n
)
2099
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
De
e
b
a
K
a
n
n
a
n
is
a
n
a
ss
is
tan
t
p
ro
fe
ss
o
r
a
t
S
RM
I
n
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
Ch
e
n
n
a
i,
Tam
il
n
a
d
u
,
In
d
ia.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
.
D
.
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
ri
n
g
,
Ch
e
n
n
a
i,
Tam
il
n
a
d
u
,
I
n
d
ia
in
2
0
2
1
He
r
re
se
a
rc
h
a
re
a
is
in
I
o
T,
d
e
e
p
lea
rn
in
g
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
h
a
s
2
0
i
n
tern
a
ti
o
n
a
l
jo
u
r
n
a
l
p
u
b
l
ica
ti
o
n
s
a
n
d
a
lso
p
u
b
li
sh
e
d
two
p
a
ten
ts.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
e
e
b
a
k
@s
rm
ist.
e
d
u
.
i
n
.
Dr
.
Na
g
a
m
u
th
u
K
r
ish
n
a
n
S
u
n
d
a
r
a
sr
in
i
v
a
sa
S
a
n
k
a
r
a
n
a
r
a
y
a
n
a
n
h
a
s
m
o
re
th
a
n
2
5
y
e
a
rs
o
f
e
x
p
e
rien
c
e
wi
th
a
stro
n
g
p
ro
fe
ss
io
n
a
l
re
c
o
rd
in
tea
c
h
in
g
,
re
se
a
rc
h
a
n
d
a
d
m
in
istratio
n
.
He
is
c
u
rre
n
tl
y
se
rv
in
g
with
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
S
AS
TRA
De
e
m
e
d
to
b
e
U
n
i
v
e
rsity
,
S
RC
K
u
m
b
a
k
o
n
a
m
,
Tam
il
N
a
d
u
.
P
ri
o
r
t
o
jo
in
i
n
g
th
is
in
stit
u
ti
o
n
,
h
e
h
a
s
w
o
rk
e
d
wi
th
R
V
C
o
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
Ba
n
g
a
l
o
re
.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
t
h
a
n
3
0
re
se
a
rc
h
p
a
p
e
rs/b
o
o
k
c
h
a
p
ters
in
p
e
e
r
re
v
iew
e
d
in
ter
n
a
ti
o
n
a
l
jo
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
.
He
h
a
s b
e
e
n
a
m
e
m
b
e
r
o
f
th
e
tec
h
n
ica
l
p
ro
g
ra
m
c
o
m
m
it
tee
o
f
m
a
n
y
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
.
He
b
e
li
e
v
e
s
in
u
p
sk
il
li
n
g
a
n
d
h
a
s
e
a
rn
e
d
a
fe
w
o
n
li
n
e
c
e
rti
fica
ti
o
n
s
i
n
th
e
f
ield
o
f
n
e
two
rk
a
n
d
c
y
b
e
rse
c
u
rit
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
a
g
a
m
u
th
u
k
ris
h
n
a
n
@s
rc
.
sa
stra
.
e
d
u
.
Dr
.
S
h
a
n
m
u
g
a
su
n
d
a
r
a
m
Ve
n
k
a
ta
r
a
j
a
n
is
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
o
f
EE
E
D
e
p
a
rtme
n
t
i
n
S
o
n
a
Co
ll
e
g
e
o
f
Tec
h
n
o
lo
g
y
,
S
a
lem
,
Tam
il
N
a
d
u
,
In
d
ia.
He
h
a
s
p
u
b
li
sh
e
d
6
2
p
a
p
e
rs
i
n
v
a
rio
u
s
p
e
e
r
re
v
iew
e
d
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
re
c
e
iv
e
d
th
e
re
se
a
rc
h
e
x
c
e
ll
e
n
c
e
a
w
a
rd
o
n
t
h
e
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
f
o
r
M
o
d
e
r
n
Tren
d
s
i
n
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(IJMT
S
T)
a
n
d
y
o
u
n
g
re
se
a
rc
h
e
r
a
wa
rd
2
0
2
0
o
n
F
e
b
ru
a
ry
2
0
2
1
.
He
wa
s
p
u
b
l
ish
e
d
fiv
e
b
o
o
k
s
i
n
th
e
f
ield
o
f
e
l
e
c
tri
c
m
o
b
il
it
y
,
sm
a
rt
g
ri
d
,
n
e
two
rk
a
n
a
ly
sis
a
n
d
sy
n
t
h
e
sis,
e
lec
tri
c
d
riv
e
s
a
n
d
m
icro
p
ro
c
e
ss
o
r
,
a
n
d
p
o
we
r
sy
ste
m
o
p
e
ra
ti
o
n
a
n
d
c
o
n
tr
o
l
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
so
f
t
c
o
m
p
u
ti
n
g
tec
h
n
iq
u
e
s
a
p
p
li
e
d
i
n
p
o
we
r
sy
ste
m
s
a
n
d
p
o
we
r
e
lec
tro
n
ics
a
p
p
li
c
a
ti
o
n
s,
re
n
e
wa
b
le
e
n
e
rg
y
sy
ste
m
s,
e
n
e
rg
y
st
o
ra
g
e
tec
h
n
o
l
o
g
ies
,
e
n
e
rg
y
m
a
n
a
g
e
m
e
n
t
a
n
d
a
u
d
i
ti
n
g
,
sm
a
rt
g
rid
s
a
n
d
e
lec
tri
c
m
o
b
il
it
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
a
n
m
u
g
a
su
n
d
a
ra
m
@s
o
n
a
tec
h
.
a
c
.
in
.
Dr
.
Ra
shi
m
a
M
a
h
a
ja
n
h
a
s
m
o
re
th
a
n
1
7
y
e
a
rs
o
f
e
x
p
e
ri
e
n
c
e
with
stro
n
g
p
ro
fe
ss
io
n
a
l
re
c
o
rd
i
n
tea
c
h
in
g
,
re
se
a
rc
h
a
n
d
a
d
m
in
istratio
n
a
t
u
n
i
v
e
rsiti
e
s
o
f
re
p
u
te
a
n
d
d
e
d
ica
ted
re
se
a
rc
h
c
e
n
ters
li
k
e
NBRC
(Na
ti
o
n
a
l
Bra
in
Re
se
a
rc
h
Ce
n
tre)
M
a
n
e
sa
r.
S
h
e
is
wo
rk
i
n
g
with
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
M
a
n
a
v
Ra
c
h
n
a
In
tern
a
ti
o
n
a
l
In
sti
tu
te
o
f
Re
se
a
rc
h
a
n
d
S
tu
d
ies
,
F
a
rid
a
b
a
d
.
P
ri
o
r
t
o
jo
i
n
in
g
t
h
is
in
sti
tu
te,
s
h
e
h
a
s
wo
rk
e
d
wit
h
G
D
G
o
e
n
k
a
Un
iv
e
rsity
a
n
d
Ap
e
e
jay
S
ty
a
Un
iv
e
rsity
,
G
u
rg
a
o
n
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
7
5
re
se
a
rc
h
p
a
p
e
rs/b
o
o
k
c
h
a
p
ters
in
p
e
e
r
re
v
i
e
we
d
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
.
S
h
e
is
a
u
t
h
o
r
o
f
a
b
o
o
k
wit
h
E
lse
v
ier
’
s:
t
it
le
-
E
EG
b
a
se
d
b
ra
in
c
o
m
p
u
ter
in
terfa
c
e
s:
c
o
g
n
it
i
v
e
a
n
a
ly
sis
a
n
d
c
o
n
tro
l
a
p
p
li
c
a
ti
o
n
s
,
M
a
rc
h
2
0
1
9
.
S
h
e
h
a
s
8
p
a
ten
ts
p
u
b
li
sh
e
d
to
h
e
r
c
re
d
it
.
S
h
e
is
a
re
v
iew
e
r
o
f
in
tern
a
t
io
n
a
l
jo
u
rn
a
ls
o
f
re
p
u
te
in
c
l
u
d
i
n
g
I
EE
E
Tran
sa
c
ti
o
n
s
o
n
Bio
m
e
d
ica
l
E
n
g
i
n
e
e
rin
g
,
IEE
E
Jo
u
rn
a
l
o
f
Bio
m
e
d
ica
l
a
n
d
He
a
lt
h
In
fo
rm
a
ti
c
s,
IE
T
S
c
ien
c
e
,
M
e
a
su
r
e
m
e
n
t
a
n
d
Tec
h
n
o
l
o
g
y
,
I
n
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
(S
p
ri
n
g
e
r
P
u
b
li
sh
e
rs
).
S
h
e
h
a
s
c
h
a
ired
m
a
n
y
tec
h
n
ica
l
se
ss
io
n
s
a
n
d
is
a
m
e
m
b
e
r
o
f
th
e
tec
h
n
ica
l
p
r
o
g
ra
m
c
o
m
m
it
tee
o
f
m
a
n
y
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
.
S
h
e
b
e
li
e
v
e
s
i
n
re
g
u
lar sk
il
l
e
n
h
a
n
c
e
m
e
n
t,
e
a
rn
e
d
m
u
lt
ip
le
o
n
l
in
e
c
e
rti
fica
ti
o
n
s
in
t
h
e
field
o
f
d
a
ta sc
ien
c
e
a
n
d
AI.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
sh
ima
m
a
h
a
jan
2
4
@g
m
a
il
.
c
o
m
.
Br
in
d
h
a
G
u
n
a
se
k
a
r
a
n
re
c
e
iv
e
d
th
e
B.
E.
d
e
g
re
e
in
e
lec
tro
n
ics
a
n
d
in
stru
m
e
n
tati
o
n
e
n
g
i
n
e
e
rin
g
fro
m
An
n
a
Un
i
v
e
rsity
o
f
In
sti
tu
ti
o
n
S
t.
Jo
se
p
h
’
s
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
C
h
e
n
n
a
i
,
Tam
il
N
a
d
u
i
n
th
e
y
e
a
r
2
0
0
5
a
n
d
M
.
E.
d
e
g
re
e
in
e
lec
tro
n
ics
a
n
d
c
o
n
tro
l
e
n
g
i
n
e
e
rin
g
fr
o
m
S
a
th
y
a
b
a
m
a
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Ch
e
n
n
a
i,
Tam
il
N
a
d
u
in
th
e
y
e
a
r
2
0
1
1
.
Re
c
e
iv
e
d
P
h
.
D.
d
e
g
re
e
in
e
lec
tro
n
ics
e
n
g
in
e
e
rin
g
a
t
S
a
th
y
a
b
a
m
a
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
C
h
e
n
n
a
i,
Tam
il
N
a
d
u
in
t
h
e
y
e
a
r
2
0
2
0
.
S
h
e
is
in
tere
ste
d
in
re
se
a
rc
h
o
n
b
io
M
EM
S
,
b
io
l
o
g
ica
l
tec
h
n
iq
u
e
s
,
i
n
teg
ra
ted
c
ir
c
u
it
lay
o
u
t,
la
b
-
on
-
a
-
c
h
ip
,
m
icro
flu
id
ics
b
io
c
h
ip
s
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
ri
n
d
h
a
g
s3
0
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.