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
.
1
,
Feb
r
u
ar
y
20
26
,
p
p
.
756
~
765
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
1
.
p
p
7
5
6
-
7
6
5
756
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Intellig
ent
plant d
isea
se detec
tion u
sing
t
win at
ten
tion o
ptima
l
co
nv
o
lutiona
l neural network
P
ra
m
ee
t
ha
P
a
i
1
,
Na
m
it
ha
S
.
J
.
1
,
So
wm
y
a
T
.
1
,
Am
utha
S
.
2
,
Nis
a
rg
a
G
o
nd
i
1
1
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
,
B
.
M
.
S
.
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
B
e
n
g
a
l
u
r
u
,
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
,
D
a
y
a
n
a
n
d
a
S
a
g
a
r
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
B
e
n
g
a
l
u
r
u
,
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
Dec
14
,
2
0
2
4
R
ev
is
ed
No
v
17
,
2
0
2
5
Acc
ep
ted
Dec
15
,
2
0
2
5
F
a
rm
in
g
is
o
n
e
o
f
th
e
m
o
st
im
p
o
rtan
t
wa
y
s
f
o
r
p
e
o
p
le
i
n
In
d
ia
t
o
m
a
k
e
a
li
v
in
g
.
Rice
is
a
sta
p
le
fo
o
d
,
a
n
d
wh
e
n
fa
rm
e
rs
su
c
c
e
ss
fu
ll
y
h
a
rv
e
st
rice
c
ro
p
s,
p
e
sts
o
fte
n
a
tt
a
c
k
th
e
m
,
w
h
ich
c
o
sts
a
g
ricu
lt
u
re
a
lo
t
o
f
m
o
n
e
y
.
T
h
e
re
a
re
n
o
w
a
l
o
t
o
f
n
e
w
AI
-
b
a
se
d
wa
y
s
to
h
e
lp
with
t
h
is
p
r
o
b
lem
i
n
r
ice
p
lan
ts.
Bu
t
t
h
o
se
wa
y
s
d
o
n
’
t
w
o
rk
v
e
r
y
we
ll
b
e
c
a
u
se
th
e
y
ta
k
e
a
l
o
n
g
ti
m
e
a
n
d
m
a
k
e
m
istak
e
s
wh
e
n
so
r
ti
n
g
t
h
i
n
g
s.
Th
is
a
rti
c
le
talk
s
a
b
o
u
t
a
n
e
w
h
y
b
ri
d
d
e
e
p
lea
rn
i
n
g
(DL)
m
e
th
o
d
fo
r
fin
d
in
g
lea
f
d
ise
a
se
s
in
rice
p
l
a
n
ts.
T
h
is
p
ro
c
e
ss
h
a
s
f
o
u
r
m
a
in
ste
p
s
:
p
re
-
p
r
o
c
e
ss
in
g
,
se
g
m
e
n
tatio
n
,
fe
a
tu
re
e
x
trac
ti
o
n
,
a
n
d
c
las
sifica
ti
o
n
.
A
h
y
b
ri
d
DL
-
b
a
se
d
twin
a
tt
e
n
ti
o
n
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(
C
NN
)
m
o
d
e
l
c
las
sifies
se
g
m
e
n
ted
i
m
a
g
e
s in
to
h
e
a
lt
h
y
a
n
d
u
n
h
e
a
lt
h
y
lea
v
e
s.
Bu
t
th
is
m
e
th
o
d
h
a
s
th
e
p
r
o
b
lem
o
f
o
v
e
rfit
ti
n
g
.
An
o
p
ti
m
iza
ti
o
n
m
e
t
h
o
d
b
a
se
d
o
n
c
h
a
o
t
ic
slim
e
m
o
u
ld
(CS
M
)
so
lv
e
s
th
is
p
r
o
b
lem
.
T
h
e
p
r
o
p
o
se
d
m
e
th
o
d
is
c
o
m
p
a
re
d
wit
h
bi
d
irec
ti
o
n
a
l
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(Bi
-
LS
T
M
),
re
c
u
rre
n
t
n
e
u
ra
l
n
e
two
r
k
(R
NN
),
d
e
e
p
n
e
u
ra
l
n
e
two
rk
(DN
N),
a
n
d
d
e
e
p
b
e
li
e
f
n
e
two
r
k
(DBN
).
Th
e
su
g
g
e
ste
d
m
e
th
o
d
h
a
s
a
n
o
v
e
ra
ll
a
c
c
u
ra
c
y
o
f
9
9
.
5
6
%
,
a
n
F
-
m
e
a
su
re
o
f
9
9
.
2
1
%
,
a
se
n
siti
v
it
y
o
f
9
9
.
1
6
%
,
a
sp
e
c
ifi
c
it
y
o
f
9
8
.
5
6
%
,
a
p
re
c
isio
n
o
f
9
9
.
2
6
%
,
a
m
e
a
n
a
b
so
lu
te
e
rro
r
(
M
AE)
o
f
0
.
0
0
4
,
a
m
e
a
n
sq
u
a
re
d
e
rro
r
(
MSE
)
o
f
0
.
0
0
4
,
a
n
d
a
ro
o
t
m
e
a
n
sq
u
a
re
e
rro
r
(RM
S
E)
o
f
0
.
0
6
.
K
ey
w
o
r
d
s
:
C
h
a
o
t
i
c
s
l
i
m
e
m
o
u
l
d
o
p
t
i
m
i
z
a
t
i
o
n
Dee
p
lear
n
in
g
I
m
p
r
o
v
ed
Gau
s
s
ian
f
ilter
in
g
Neu
r
al
n
etwo
r
k
R
ice
p
lan
t le
af
d
is
ea
s
e
T
win
atten
tio
n
-
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
So
wm
y
a
T
.
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
B
.
M.
S.
C
o
lleg
e
o
f
E
n
g
i
n
ee
r
in
g
B
u
ll T
em
p
le
R
o
ad
,
B
asav
an
g
u
d
i,
B
en
g
alu
r
u
1
9
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail: so
wm
y
at.
cse@
b
m
s
ce
.
a
c.
in
1.
I
NT
RO
D
UCT
I
O
N
At
f
ir
s
t,
a
s
p
ec
ialis
t
d
id
p
lan
t
d
is
ea
s
e
m
o
n
ito
r
in
g
an
d
an
al
y
s
is
b
y
h
an
d
[
1
]
–
[
5
]
.
T
h
is
tak
es
a
lo
t
o
f
tim
e
an
d
wo
r
k
to
g
et
th
r
o
u
g
h
.
T
h
e
s
ig
n
s
o
f
d
is
ea
s
e
ca
n
u
s
u
ally
b
e
s
ee
n
o
n
th
e
f
r
u
its
,
leav
es,
an
d
s
tem
s
.
T
h
e
p
lan
t
leaf
s
h
o
ws
th
e
s
ig
n
s
o
f
th
e
d
is
ea
s
e,
wh
ich
is
h
o
w
th
e
illn
ess
is
f
o
u
n
d
[
6
]
,
[
7
]
.
I
t
i
s
h
ar
d
to
f
ig
u
r
e
o
u
t
wh
at'
s
wr
o
n
g
with
a
p
lan
t.
On
e
n
ee
d
s
to
lo
o
k
at
th
e
leav
e
s
an
d
s
ee
wh
at
th
ey
lo
o
k
lik
e
.
B
ec
au
s
e
o
f
th
is
co
m
p
lex
ity
an
d
th
e
m
a
n
y
p
lan
ts
th
at
ar
e
g
r
o
wn
an
d
th
eir
cu
r
r
en
t
p
h
y
to
-
p
at
h
o
lo
g
ic
al
p
r
o
b
lem
s
,
ev
en
ex
p
er
ien
ce
d
ag
r
o
n
o
m
is
ts
an
d
p
lan
t
p
ath
o
lo
g
is
ts
o
f
ten
m
is
s
s
o
m
e
d
is
ea
s
es.
T
h
is
r
esu
lts
in
er
r
o
n
eo
u
s
co
n
clu
s
io
n
s
an
d
tr
ea
tm
e
n
ts
[
8
]
,
[
9
]
.
A
n
au
t
o
m
ated
co
m
p
u
tatio
n
al
s
y
s
tem
f
o
r
id
e
n
tify
in
g
a
n
d
d
iag
n
o
s
in
g
p
lan
t
d
is
ea
s
es
wo
u
ld
g
r
ea
tly
ass
is
t
ag
r
o
n
o
m
is
ts
task
ed
with
s
u
ch
d
iag
n
o
s
es
th
r
o
u
g
h
leaf
ex
am
in
atio
n
[
1
0
]
.
Als
o
,
th
e
tech
n
o
lo
g
y
co
u
ld
b
e
u
s
ed
with
s
elf
-
d
r
iv
in
g
f
ar
m
v
e
h
ic
les
o
n
b
ig
f
ar
m
s
to
q
u
ick
ly
a
n
d
ac
cu
r
ately
f
in
d
p
lan
t d
is
ea
s
es in
th
e
f
ield
s
b
y
t
ak
in
g
p
ictu
r
es a
ll th
e
tim
e
[
1
1
]
.
R
esear
ch
er
s
,
esp
ec
ially
th
o
s
e
f
r
o
m
d
ev
elo
p
in
g
co
u
n
tr
ies,
ar
e
in
cr
ea
s
in
g
ly
co
n
ce
n
tr
ati
n
g
o
n
th
e
id
en
tific
atio
n
o
f
p
lan
t
d
is
ea
s
es.
An
o
th
er
ar
ea
o
f
r
esear
ch
th
at
lo
o
k
s
p
r
o
m
is
in
g
is
f
in
d
in
g
p
lan
t
d
is
ea
s
es
ea
r
ly
[
1
2
]
.
B
ac
ter
ia,
f
u
n
g
i,
an
d
v
ir
u
s
es
ar
e
ju
s
t
a
f
ew
o
f
th
e
th
in
g
s
th
at
ca
n
m
ak
e
p
lan
ts
s
ick
.
T
h
ese
d
is
ea
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
I
n
tellig
en
t p
la
n
t
d
is
ea
s
e
d
etec
tio
n
u
s
in
g
tw
in
a
tten
tio
n
o
p
tim
a
l c
o
n
vo
l
u
tio
n
a
l
n
eu
r
a
l
…
(
P
r
a
mee
th
a
P
a
i
)
757
ca
n
also
h
u
r
t
t
h
e
wo
r
ld
ec
o
n
o
m
y
,
s
o
ciety
,
an
d
en
v
ir
o
n
m
en
t.
B
ec
au
s
e
o
f
th
is
,
th
er
e
is
a
n
ee
d
to
f
in
d
q
u
ick
a
n
d
ac
cu
r
ate
way
s
to
f
in
d
p
lan
t
d
is
ea
s
es
r
ig
h
t
awa
y
.
I
n
th
e
p
ast,
d
if
f
er
en
t
wa
y
s
h
av
e
b
ee
n
u
s
e
d
to
f
in
d
an
d
s
to
p
p
lan
t d
is
ea
s
es in
o
r
d
er
to
cu
t d
o
wn
o
n
c
r
o
p
lo
s
s
es [
1
3
]
.
B
ac
ter
ia,
v
ir
u
s
es,
an
d
f
u
n
g
i
ar
e
s
o
m
e
o
f
th
e
m
o
s
t
c
o
m
m
o
n
th
in
g
s
th
at
h
u
r
t
c
r
o
p
s
.
T
h
is
ca
n
b
e
s
to
p
p
ed
with
p
lan
t
d
is
ea
s
e
d
etec
tio
n
s
y
s
tem
s
[
1
4
]
.
T
h
e
f
ar
m
er
p
ick
s
th
e
r
ig
h
t
cr
o
p
b
ased
o
n
th
e
wea
th
er
,
th
e
s
o
il
ty
p
e,
an
d
h
o
w
m
u
c
h
m
o
n
ey
it
will
m
ak
e.
Ag
r
icu
ltu
r
al
b
u
s
in
ess
es
s
tar
ted
lo
o
k
in
g
f
o
r
n
ew
way
s
to
g
r
o
w
m
o
r
e
f
o
o
d
b
ec
au
s
e
th
e
wea
th
er
was
ch
an
g
in
g
,
th
e
p
o
p
u
latio
n
was
g
r
o
win
g
,
a
n
d
p
o
liti
cs
wer
e
u
n
s
tab
le.
So
,
s
cien
tis
t
s
ar
e
lo
o
k
in
g
f
o
r
n
ew
tech
n
o
lo
g
ies
th
at
ar
e
b
o
th
p
r
e
cise
an
d
ef
f
icien
t
to
b
o
o
s
t
p
r
o
d
u
ctiv
ity
[
1
5
]
,
[
1
6
]
.
Far
m
er
s
ca
n
u
s
e
p
r
ec
is
io
n
ag
r
i
cu
ltu
r
e
in
I
T
to
g
et
th
e
d
ata
an
d
in
f
o
r
m
atio
n
th
ey
n
ee
d
to
m
a
k
e
th
e
b
est ch
o
ices
f
o
r
g
ettin
g
th
e
m
o
s
t
c
r
o
p
s
.
AI
ap
p
licatio
n
s
r
elate
d
t
o
m
ac
h
in
e
lear
n
in
g
(
ML
)
h
av
e
g
r
o
wn
a
lo
t
in
th
e
last
f
ew
y
ea
r
s
b
ec
au
s
e
o
f
t
h
e
g
r
o
wth
o
f
co
m
p
u
tatio
n
al
s
y
s
tem
s
,
esp
ec
ially
g
r
ap
h
ical
p
r
o
ce
s
s
in
g
u
n
its
(
GPU)
,
wh
ich
lead
s
to
th
e
cr
ea
tio
n
o
f
n
ew
m
eth
o
d
s
an
d
m
o
d
els
lik
e
d
ee
p
lear
n
in
g
(
DL
)
[
1
7
]
.
D
L
e
m
p
l
o
y
s
a
r
t
i
f
i
c
i
al
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
A
NN
)
c
h
a
r
a
c
t
e
r
iz
e
d
b
y
m
u
l
t
i
p
l
e
p
r
o
c
e
s
s
i
n
g
l
a
y
e
r
s
,
d
i
s
t
i
n
g
u
is
h
i
n
g
i
t
f
r
o
m
t
h
e
“
s
wa
l
l
o
w
e
r
”
t
o
p
o
l
o
g
i
es
u
t
i
l
i
z
e
d
i
n
m
o
r
e
p
r
e
v
a
l
e
n
t
n
eu
r
a
l
n
e
t
w
o
r
k
m
e
t
h
o
d
o
l
o
g
i
e
s
[
1
8
]
.
DL
m
e
t
h
o
d
s
i
n
a
g
r
i
c
u
l
tu
r
e
,
e
s
p
e
ci
a
l
l
y
f
o
r
f
i
g
u
r
i
n
g
o
u
t
w
h
a
t
d
i
s
ea
s
es
’
p
l
an
t
s
h
a
v
e
,
a
r
e
s
t
il
l
n
e
w
a
n
d
h
a
v
en
’
t
b
e
e
n
a
r
o
u
n
d
f
o
r
v
e
r
y
l
o
n
g
[
1
9
]
,
[
2
0
]
.
I
t
tak
es
a
lo
n
g
tim
e
an
d
is
b
o
r
in
g
to
f
ig
u
r
e
o
u
t
wh
o
s
o
m
eo
n
e
is
b
y
l
o
o
k
in
g
at
t
h
em
.
A
co
m
p
u
ter
ized
s
cr
ee
n
in
g
s
y
s
tem
was
cr
ea
te
d
to
m
a
k
e
t
h
in
g
s
ea
s
ier
at
wo
r
k
.
T
h
is
s
y
s
tem
a
u
to
m
atica
lly
ch
ec
k
s
th
e
p
lan
ts
’
h
ea
lth
an
d
lo
o
k
s
f
o
r
d
is
ea
s
es.
T
h
e
m
ain
g
o
al
o
f
p
r
o
p
o
s
ed
m
eth
o
d
is
to
s
h
o
w
a
n
ew
way
to
u
s
e
DL
to
class
if
y
r
ice
p
lan
t
d
is
ea
s
es
in
to
h
ea
lt
h
y
an
d
u
n
h
ea
lth
y
g
r
o
u
p
s
u
s
in
g
twin
atten
tio
n
-
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(TA
-
C
NN)
.
I
t a
ls
o
s
u
g
g
ests
way
to
o
p
tim
ize
u
s
in
g
ch
a
o
tic
s
lim
e
m
o
u
ld
(
C
SM)
to
r
ed
u
ce
l
o
s
s
an
d
o
v
er
f
itti
n
g
.
A
th
o
r
o
u
g
h
a
n
d
c
o
m
p
r
e
h
en
s
iv
e
ex
am
in
atio
n
o
f
th
e
liter
atu
r
e
r
eg
ar
d
in
g
c
o
n
tem
p
o
r
ar
y
s
y
s
tem
s
was
co
n
d
u
cte
d
.
T
h
e
s
u
r
v
e
y
was
d
o
n
e
to
f
in
d
o
u
t
w
h
at
th
e
c
u
r
r
e
n
t
ef
f
o
r
ts
ca
n
an
d
ca
n
’
t
d
o
,
wh
at
th
e
p
r
o
b
lem
s
a
r
e,
an
d
wh
at
h
as
wo
r
k
e
d
.
T
a
b
le
1
s
h
o
ws
s
o
m
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
s
y
s
tem
s
th
at
wer
e
s
tu
d
i
ed
,
alo
n
g
with
th
eir
p
r
o
b
lem
s
an
d
u
n
i
q
u
e
f
ea
t
u
r
es.
T
h
ese
s
y
s
tem
s
ar
e
th
e
m
o
s
t im
p
o
r
tan
t
to
th
e
o
b
jectiv
es o
f
t
h
is
wo
r
k
.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
ex
is
tin
g
w
o
r
k
R
e
f
e
r
e
n
c
e
s
M
e
t
h
o
d
s
F
e
a
t
u
r
e
s
C
h
a
l
l
e
n
g
e
s
H
a
ssan
e
t
a
l
.
[
2
1
]
C
N
N
Th
e
t
i
me
f
o
r
t
r
a
i
n
i
n
g
p
r
o
c
e
ss
i
s
l
e
ss
S
o
me
t
i
m
e
s
t
h
e
i
ma
g
e
s
h
a
v
e
n
o
i
s
e
a
n
d
l
e
a
d
s
t
o
mi
scl
a
ssi
f
i
c
a
t
i
o
n
F
e
r
e
n
t
i
n
o
s [2
2
]
C
N
N
Th
i
s
m
o
d
e
l
h
a
s
a
c
h
i
e
v
e
d
a
n
a
c
c
u
r
a
c
y
o
f
9
9
.
5
3
%
a
n
d
i
t
w
a
s
m
o
r
e
r
o
b
u
s
t
i
n
r
e
a
l
l
i
f
e
a
p
p
l
i
c
a
t
i
o
n
Th
i
s
mo
d
e
l
d
o
e
s
n
o
t
i
d
e
n
t
i
f
y
t
h
e
e
x
i
st
i
n
g
p
l
a
n
t
d
i
s
e
a
s
e
.
K
a
m
a
l
[
2
3
]
D
e
p
t
h
w
i
se
se
p
a
r
a
b
l
e
c
o
n
v
o
l
u
t
i
o
n
Th
i
s
m
o
d
e
l
s
h
o
w
e
d
e
f
f
i
c
i
e
n
t
t
r
a
d
e
-
o
f
f
a
mo
n
g
a
c
c
u
r
a
c
y
a
n
d
l
a
t
e
n
c
y
W
h
e
n
t
h
e
p
a
r
a
me
t
e
r
s
w
e
r
e
i
n
c
r
e
a
s
e
d
,
t
h
e
c
o
st
o
f
c
o
m
p
u
t
a
t
i
o
n
a
l
s
o
i
n
c
r
e
a
s
e
d
.
Ta
k
e
s m
o
r
e
t
i
me
f
o
r
l
a
r
g
e
d
a
t
a
A
sh
t
a
g
i
e
t
a
l
.
[
2
4
]
H
y
b
r
i
d
C
N
N
+
R
F
,
C
N
N
+
S
V
M
w
i
t
h
P
S
O
H
y
b
r
i
d
f
u
s
i
o
n
o
f
DL
a
n
d
M
L
i
mp
r
o
v
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
;
P
S
O
-
b
a
s
e
d
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
e
n
h
a
n
c
e
s
d
i
scri
m
i
n
a
t
i
v
e
p
o
w
e
r
.
C
N
N
+
R
F
a
c
h
i
e
v
e
d
9
5
%
a
c
c
u
r
a
c
y
,
C
N
N
+
S
V
M
a
c
h
i
e
v
e
d
9
3
%
a
c
c
u
r
a
c
y
H
i
g
h
e
r
c
o
m
p
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
;
r
e
q
u
i
r
e
s
c
a
r
e
f
u
l
p
a
r
a
met
e
r
t
u
n
i
n
g
a
n
d
q
u
a
l
i
t
y
d
a
t
a
se
t
s
f
o
r
o
p
t
i
ma
l
g
e
n
e
r
a
l
i
z
a
t
i
o
n
A
t
i
l
a
e
t
a
l
.
[
2
5
]
Ef
f
i
c
i
e
n
t
N
e
t
A
c
h
i
e
v
e
d
b
e
t
t
e
r
a
c
c
u
r
a
c
y
Ex
e
c
u
t
i
o
n
t
i
me
i
s
l
a
r
g
e
w
h
e
n
c
o
m
p
a
r
e
d
t
o
t
h
e
b
a
se
l
i
n
e
m
o
d
e
l
s.
P
a
n
i
g
r
a
h
i
e
t
a
l
.
[
2
6
]
M
L
m
o
d
e
l
s
Th
i
s
mo
d
e
l
w
a
s
m
o
r
e
h
e
l
p
f
u
l
f
o
r
f
o
r
mers
t
o
f
i
n
d
t
h
e
d
i
s
e
a
s
e
s
a
t
e
a
r
l
y
st
a
g
e
Th
i
s
m
o
d
e
l
ma
y
n
o
t
b
e
s
u
i
t
a
b
l
e
f
o
r
a
l
l
d
a
t
a
b
a
s
e
2.
M
E
T
H
O
D
DL
is
m
o
v
in
g
q
u
ick
l
y
,
s
o
it
ca
n
n
o
w
f
in
d
p
lan
t
d
is
ea
s
es
o
n
it
i
s
o
wn
.
T
h
is
h
elp
s
in
f
i
n
d
in
g
s
ick
p
lan
ts
an
d
f
ig
u
r
e
o
u
t w
h
at
’
s
wr
o
n
g
with
th
em
b
y
lo
o
k
in
g
at
d
ig
ital p
h
o
to
s
.
T
h
is
wo
r
k
s
h
o
ws a
DL
s
y
s
tem
th
at
ca
n
au
to
m
atica
lly
tell d
if
f
er
en
ce
b
etwe
en
p
ictu
r
es
o
f
h
ea
lth
y
an
d
s
ick
p
lan
t
leav
es.
T
h
e
f
ir
s
t
s
tep
in
g
ettin
g
a
n
im
ag
e
r
ea
d
y
f
o
r
p
r
o
ce
s
s
in
g
is
to
g
et
r
id
o
f
n
o
is
e,
ad
d
t
o
it,
a
n
d
ch
an
g
e
it
i
s
s
ize.
T
h
e
im
p
r
o
v
ed
G
au
s
s
ian
f
ilter
(
I
GF)
g
ets
r
id
o
f
th
e
n
o
is
e
in
t
h
e
p
ictu
r
e.
T
h
is
m
ak
es
th
e
co
lo
r
s
s
tan
d
o
u
t
m
o
r
e
an
d
m
ak
es th
e
p
ictu
r
e
clea
r
er
.
Data
ca
n
b
e
ad
d
e
d
to
th
e
p
ict
u
r
e
b
y
r
o
tatin
g
,
clip
p
in
g
,
an
d
f
lip
p
in
g
it
to
o
b
tain
as
m
an
y
p
ictu
r
es
as
p
o
s
s
ib
le
af
ter
th
e
n
o
is
e
is
g
o
n
e.
Nex
t,
th
e
im
ag
e
n
ee
d
s
to
b
e
r
esized
s
o
th
at
it
wo
r
k
s
with
th
e
DL
m
o
d
el.
T
o
g
et
a
h
ig
h
lev
el
o
f
d
is
ea
s
e
d
etec
tio
n
ac
cu
r
ac
y
,
it
i
s
im
p
o
r
ta
n
t
to
b
r
ea
k
th
e
i
n
p
u
t
i
m
ag
e
in
t
o
s
m
aller
p
ar
ts
b
e
f
o
r
e
ex
tr
ac
tin
g
th
e
f
ea
tu
r
es.
T
o
d
o
th
is
,
b
in
ar
y
th
r
esh
o
ld
s
eg
m
e
n
t
atio
n
(
B
T
S)
is
u
s
ed
to
s
ep
ar
at
e
th
e
im
ag
e
o
f
th
e
leaf
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
.
Ne
x
t,
f
ea
tu
r
e
e
x
tr
ac
tio
n
is
d
is
cu
s
s
ed
,
wh
ich
is
a
v
er
y
im
p
o
r
tan
t
p
ar
t
o
f
id
e
n
tify
in
g
p
lan
t
d
is
ea
s
es.
Fo
r
th
is
s
tep
,
a
r
ed
g
r
ee
n
b
lu
e
(
R
GB
)
h
is
to
g
r
am
an
d
a
g
r
e
y
lev
el
co
-
o
cc
u
r
r
e
n
ce
m
atr
ix
(
GL
C
M)
ar
e
u
s
ed
.
T
h
e
last
s
tep
is
class
if
icatio
n
p
r
o
ce
s
s
,
wh
ich
u
s
es
th
e
twin
atten
tio
n
o
p
tim
al
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
T
AO
-
C
NN)
to
f
ig
u
r
e
o
u
t
if
th
e
p
lan
t
leaf
is
s
ick
o
r
h
ea
lth
y
.
T
h
e
C
SM
alg
o
r
ith
m
is
u
s
ed
h
er
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
756
-
7
6
5
758
to
f
ix
t
h
e
T
AO
-
C
NN
’
s
lo
s
s
.
T
h
e
T
AO
-
C
NN
m
o
d
el
th
at
w
as
s
u
g
g
ested
is
a
g
o
o
d
way
t
o
d
o
DL
th
at
h
elp
s
with
o
v
er
f
itti
n
g
a
n
d
m
a
k
es th
e
class
if
icatio
n
m
o
r
e
ac
cu
r
ate.
T
h
ese
s
tep
s
ar
e
r
ep
r
esen
ted
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
2
.
1
.
P
re
-
pro
ce
s
s
ing
T
h
e
r
aw
d
ataset
im
ag
es
h
a
v
e
a
lo
t
o
f
n
o
is
e
in
t
h
em
,
w
h
ich
m
ak
es
th
em
less
ac
cu
r
ate.
I
t
i
s
n
ec
ess
ar
y
to
g
et
r
id
o
f
th
e
n
o
is
e.
Peo
p
l
e
h
av
e
u
s
ed
Gau
s
s
ian
f
ilter
in
g
[
2
7
]
,
b
u
t
it
h
as
a
lo
t
o
f
f
al
s
e
p
o
s
itiv
es
in
g
r
ey
v
alu
es
(
0
–
2
5
5
)
an
d
m
is
tak
es
in
p
ix
els
th
at
h
av
e
h
ad
n
o
is
e
r
ed
u
ce
d
,
wh
ich
m
ak
es
it
h
a
r
d
to
r
esto
r
e
im
ag
es.
T
h
is
p
r
o
b
lem
is
s
o
lv
ed
b
y
t
h
e
I
GF
m
eth
o
d
.
T
h
is
m
eth
o
d
ca
n
ch
ec
k
th
e
n
o
is
e
d
en
s
i
ty
an
d
u
s
e
im
ag
e
th
r
esh
o
ld
in
g
to
m
ak
e
m
is
tak
e
s
less
lik
ely
.
I
t
ca
n
also
m
ak
e
th
e
win
d
o
w
b
ig
g
er
t
o
h
elp
f
in
d
th
in
g
s
.
L
et
’
s
lo
o
k
at
th
e
p
ictu
r
e
with
th
e
p
ix
el
P(x
,
y
)
an
d
th
e
g
r
ey
lev
el
G(
x
,
y
)
.
T
h
e
I
GF
lo
o
k
s
at
th
e
g
r
ey
lev
els
o
f
th
e
p
ix
els
to
d
ec
id
e
wh
ich
o
n
es
ar
e
n
o
is
y
.
I
f
G(
x
,
y
)
eq
u
als
0
o
r
2
5
5
,
I
G
F
b
eliev
es
th
at
p
ix
el
i
s
n
o
is
y
.
I
GF
d
o
esn
’
t
th
in
k
it
i
s
th
e
n
o
is
y
p
ix
el
if
G(
x
,
y
)
is
n
’
t
0
o
r
2
5
5
.
B
u
t
in
m
an
y
ca
s
es,
th
e
s
u
g
g
ested
I
GF
m
eth
o
d
g
ets
th
e
g
r
ey
lev
el
o
f
0
to
2
5
5
wr
o
n
g
an
d
th
in
k
s
t
h
e
y
ar
e
n
o
is
e
-
f
r
ee
p
ix
els,
wh
ich
m
ak
es
th
e
p
ictu
r
e
lo
o
k
b
lu
r
r
y
.
T
h
is
also
m
ak
es
it
h
ar
d
to
tell
h
o
w
lo
u
d
th
e
n
o
is
e
is
,
wh
ich
ca
u
s
es
a
lo
t
o
f
f
alse a
lar
m
s
.
T
h
e
GF
h
as
a
b
etter
v
ar
ian
ce
co
m
p
o
n
e
n
t
th
at
m
ak
es
th
e
n
o
is
e
r
em
o
v
al
p
r
o
ce
s
s
wo
r
k
b
etter
.
T
h
e
I
G
F
m
eth
o
d
u
s
es
a
f
ix
e
d
weig
h
ted
m
ea
n
f
ilter
in
g
win
d
o
w
to
f
in
d
all
th
e
n
o
is
y
p
ix
els.
GF
ch
o
o
s
es
th
e
weig
h
ts
b
ased
o
n
wh
ich
o
n
e
h
as
m
o
r
e
v
ar
iatio
n
.
Her
e
is
th
e
co
m
p
lete
lis
t o
f
s
tep
s
to
g
e
t r
id
o
f
n
o
is
e:
L
et
’
s
s
ay
th
at
α
is
th
e
w
×
w
f
ilter
in
g
win
d
o
w
th
at
is
p
u
t
at
P(x
,
y
)
f
o
r
t
h
e
n
o
is
e
p
ix
el
P(
x
,
y
)
.
Ma
k
e
w
eq
u
al
to
9
.
Fin
d
th
e
n
ew
s
et
V
af
ter
tak
in
g
o
u
t
th
e
n
o
is
e
p
ix
e
ls
in
α
th
at
h
av
e
p
ix
el
v
alu
es
b
etwe
en
0
an
d
2
5
5
.
T
h
e
g
r
e
y
lev
el
R
(
x
,
y
)
o
f
P(
x
,
y
)
th
at
was
f
o
u
n
d
f
in
d
s
th
e
w
eig
h
ted
p
i
x
el
m
ea
n
in
V.
T
h
i
s
ca
n
b
e
e
x
p
r
ess
ed
m
ath
em
atica
lly
as
:
(
,
)
=
∑
(
,
)
(
,
)
(
,
)
∈
∑
(
,
)
(
,
)
∈
(
1
)
Fo
r
th
is
ca
s
e,
G(
u
,
v
)
a
n
d
β(u
,
v
)
ar
e
th
e
g
r
ey
le
v
el
an
d
wei
g
h
t
o
f
P(x
,
y
)
.
T
h
e
e
n
h
an
ce
d
Gau
s
s
ian
f
u
n
ctio
n
is
r
ep
r
esen
ted
m
ath
e
m
atica
lly
b
y
th
e
weig
h
t β(
u
,
v
)
,
wh
ich
is
:
(
,
)
=
(
−
(
−
)
2
+
(
−
)
2
2
2
)
(
2
)
I
n
th
is
ca
s
e,
(
x
,
y
)
an
d
(
u
,
v
)
ar
e
th
e
co
o
r
d
in
ates
f
o
r
th
e
p
ix
el
s
P(x
,
y
)
an
d
P(u
,
v
)
th
at
ar
e
n
e
x
t
to
ea
ch
o
th
er
in
th
e
wh
o
le
p
ictu
r
e
.
T
h
e
p
ar
am
e
ter
σ
ca
n
also
b
e
c
o
n
s
id
er
ed
as:
=
0
.
2
+
(
3
)
T
h
e
n
o
is
e
d
en
s
ity
is
th
e
n
u
m
b
er
o
f
p
ix
els
th
at
m
ak
e
u
p
th
e
n
o
is
e
d
iv
id
ed
b
y
th
e
to
tal
n
u
m
b
er
o
f
p
ix
els
in
th
e
im
ag
e.
Data
au
g
m
en
tatio
n
h
el
p
s
a
lo
t
with
o
v
er
f
itti
n
g
p
r
o
b
lem
s
an
d
m
a
k
es
ac
cu
r
ac
y
b
etter
.
Du
r
in
g
d
ata
au
g
m
en
tatio
n
,
th
e
im
ag
e
with
th
e
n
o
is
e
r
em
o
v
ed
is
r
a
n
d
o
m
l
y
m
o
v
ed
alo
n
g
th
e
h
o
r
iz
o
n
tal
an
d
v
er
tical
ax
es
b
y
a
v
alu
e
b
etwe
en
−4
5
an
d
4
5
.
T
h
e
en
h
an
ce
d
Gau
s
s
ian
f
ilter
wo
r
k
s
well
to
g
et
r
id
o
f
n
o
is
e
b
y
f
ig
u
r
in
g
o
u
t
h
o
w
d
en
s
e
it
is
af
ter
th
ese
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
.
T
h
en
,
th
r
esh
o
ld
in
g
is
u
s
ed
to
g
et
r
id
o
f
all
b
u
t
th
e
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
I
n
tellig
en
t p
la
n
t
d
is
ea
s
e
d
etec
tio
n
u
s
in
g
tw
in
a
tten
tio
n
o
p
tim
a
l c
o
n
vo
l
u
tio
n
a
l
n
eu
r
a
l
…
(
P
r
a
mee
th
a
P
a
i
)
759
m
o
s
t
im
p
o
r
ta
n
t
p
i
x
el
d
ata.
So
,
th
e
p
ictu
r
es
th
at
co
m
e
o
u
t
ar
e
clea
r
er
.
I
m
ag
es
th
at
wer
e
p
r
e
-
p
r
o
ce
s
s
ed
th
is
way
wo
r
k
m
u
c
h
b
etter
i
n
later
s
tep
s
,
s
u
ch
as c
lass
if
icatio
n
,
s
eg
m
en
tatio
n
,
an
d
d
etec
tio
n
.
2
.
2
.
Seg
m
ent
a
t
i
o
n us
ing
bin
a
ry
t
hresh
o
ldi
ng
a
pp
ro
a
ch
Af
ter
th
at,
th
e
im
ag
e
g
o
es to
th
e
s
eg
m
en
tatio
n
s
tag
e,
wh
er
e
th
e
s
ick
p
ar
t is cu
t o
u
t o
f
th
e
b
ac
k
g
r
o
u
n
d
im
ag
e.
T
h
e
b
in
ar
y
th
r
esh
o
ld
i
n
g
m
eth
o
d
(
B
T
S)
is
em
p
lo
y
ed
to
p
er
f
o
r
m
th
e
s
eg
m
en
tatio
n
.
B
y
s
ettin
g
th
r
esh
o
ld
v
alu
e,
th
e
B
T
S
m
eth
o
d
ca
n
r
e
m
o
v
e
u
n
wan
ted
b
ac
k
g
r
o
u
n
d
r
eg
io
n
s
.
At
f
ir
s
t,
th
e
p
ix
el
in
p
i
ctu
r
e
th
at
is
b
elo
w
th
e
th
r
esh
o
ld
g
ets a
v
alu
e
o
f
0
.
A
p
ix
el
in
an
im
ag
e
g
ets a
v
al
u
e
o
f
1
if
it
i
s
v
alu
e
is
h
ig
h
er
t
h
an
th
e
th
r
esh
o
ld
.
T
h
e
b
est
th
r
esh
o
ld
f
o
r
ea
ch
i
m
ag
e
is
d
if
f
er
en
t
b
ec
au
s
e
th
e
p
ix
el
d
is
tr
ib
u
tio
n
f
o
r
ea
ch
p
ix
el
v
alu
e
is
d
if
f
er
en
t.
I
f
all
o
f
th
e
test
i
m
ag
es
h
av
e
th
e
s
am
e
th
r
esh
o
ld
,
th
e
r
an
d
o
m
th
r
esh
o
ld
m
ig
h
t
n
o
t
h
u
r
t
t
h
e
p
er
f
o
r
m
an
ce
.
T
h
e
lin
e
s
ea
r
ch
m
eth
o
d
c
an
n
o
t
id
en
tif
y
th
e
b
e
s
t
th
r
esh
o
ld
f
o
r
ea
ch
im
a
g
e
d
u
e
to
t
h
e
u
n
k
n
o
wn
im
ag
e
ty
p
es
in
th
e
test
in
g
s
e
t.
T
h
is
m
ea
n
s
th
at
lab
elled
d
ata
f
o
r
tr
ain
in
g
,
v
alid
atio
n
,
a
n
d
test
in
g
ar
e
n
o
t
av
ailab
le.
Du
r
in
g
tr
ain
in
g
,
th
is
p
r
o
b
lem
ca
n
b
e
m
itig
ated
b
y
s
ea
r
ch
in
g
f
o
r
th
e
b
est v
alu
e.
2
.
3
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
T
h
e
p
r
o
ce
s
s
o
f
ex
tr
ac
tin
g
f
ea
tu
r
es
h
as
two
m
ain
s
tep
s
:
g
et
tin
g
co
lo
r
f
ea
tu
r
es
an
d
g
ettin
g
GL
C
M
f
ea
tu
r
es.
T
o
g
et
th
e
im
p
o
r
tan
t
r
ed
(
R
)
,
g
r
ee
n
(
G)
,
an
d
b
lu
e
(
B
)
co
lo
r
f
ea
tu
r
es
f
r
o
m
t
h
e
p
ictu
r
e
o
f
th
e
s
ick
r
ice
p
lan
t,
an
R
GB
h
is
to
g
r
am
is
u
s
ed
.
T
h
is
R
GB
h
is
to
g
r
am
is
g
r
ea
t
b
ec
au
s
e
it
is
u
s
ed
a
lo
t
in
T
Vs,
m
o
n
ito
r
s
,
ca
m
er
as,
an
d
o
th
er
d
e
v
ices
to
tell
th
e
d
if
f
er
en
ce
b
etwe
en
c
h
an
n
els.
On
e
o
f
th
e
wo
r
d
s
u
s
ed
to
g
et
leaf
c
o
lo
r
f
ea
tu
r
es
f
r
o
m
th
e
in
p
u
t
s
am
p
les
is
“
R
GB
h
i
s
to
g
r
am
”
.
I
n
m
o
s
t
o
f
th
e
in
p
u
t
s
am
p
les,
th
e
b
lu
e
ch
a
n
n
el
h
as
f
ewe
r
f
ea
tu
r
es
th
an
th
e
r
ed
ch
an
n
el.
A
h
is
to
g
r
am
is
a
p
ictu
r
e
m
ad
e
u
p
o
f
p
ix
els
th
at
h
av
e
th
e
s
am
e
f
r
eq
u
en
c
y
.
I
t
h
elp
s
id
en
tify
p
ix
els
th
at
ar
e
d
if
f
er
en
t
at
ea
ch
f
ea
t
u
r
e
p
o
in
t
.
T
h
e
m
o
s
t
im
p
o
r
ta
n
t
th
in
g
th
e
h
is
to
g
r
am
d
o
es
is
g
et
co
lo
r
s
f
r
o
m
th
e
R
GB
ch
an
n
els.
Du
r
in
g
ex
tr
ac
tin
g
f
ea
tu
r
es,
th
in
k
o
f
R
GB
as
th
e
h
ar
d
p
ar
t
th
at
th
e
h
is
to
g
r
am
is
b
r
o
k
e
n
u
p
i
n
to
d
if
f
er
en
t
b
in
s
.
R
GB
alwa
y
s
h
as
2
5
7
ch
a
n
n
els,
an
d
ea
c
h
R
GB
cu
m
u
lativ
e
v
ec
to
r
h
as 7
6
8
b
in
s
.
2
.
4
.
Cla
s
s
if
ica
t
io
n us
ing
t
win a
t
t
ent
io
n
-
co
nv
o
lutio
na
l ne
ura
l net
wo
rk
t
ec
hn
iqu
e
N
e
x
t
,
th
e
f
e
a
t
u
r
e
s
th
a
t
w
er
e
r
e
m
o
v
e
d
a
r
e
s
en
t
to
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
s
t
a
g
e,
w
h
er
e
th
ey
a
r
e
s
o
r
t
e
d
i
n
to
p
i
c
t
u
r
e
s
o
f
th
e
s
i
c
k
r
i
c
e
p
l
an
t
t
h
a
t
ar
e
h
e
a
l
th
y
a
n
d
u
n
h
e
a
l
t
h
y
.
T
h
e
r
e
ar
e
b
l
o
ck
s
f
o
r
b
o
th
s
p
a
t
i
a
l
an
d
s
p
e
c
tr
a
l
a
t
t
e
n
t
i
o
n
i
n
t
h
e
p
r
o
p
o
s
e
d
t
w
in
a
t
te
n
t
io
n
ar
c
h
i
t
ec
t
u
r
e
.
T
h
e
in
p
u
t
p
a
t
ch
,
w
h
i
ch
i
s
1
1
×
11
×
1
3
,
i
s
s
p
l
i
t
i
n
to
t
wo
s
t
r
e
a
m
s
s
o
th
a
t
t
h
e
d
e
e
p
f
ea
t
u
r
e
s
ca
n
b
e
p
u
l
l
ed
o
u
t
o
f
t
h
e
in
p
u
t
s
a
m
p
le
s
.
T
h
i
s
i
s
h
o
w
th
e
s
u
g
g
e
s
t
ed
TA
-
C
N
N
m
o
d
e
l
i
s
s
e
t
u
p
.
T
h
e
a
r
c
h
i
t
e
c
tu
r
e
in
c
l
u
d
e
s
a
s
u
r
f
a
c
e
m
u
l
t
i
-
la
y
er
f
e
a
tu
r
e
ex
t
r
a
ct
o
r
,
a
m
ax
p
o
o
l
i
n
g
l
a
y
e
r
,
s
p
e
c
t
r
a
l
a
t
t
en
t
i
o
n
b
l
o
ck
s
,
an
d
m
u
l
t
i
-
r
e
s
i
d
u
a
l
b
l
o
ck
s
.
T
o
s
t
a
r
t,
m
u
l
t
i
-
l
a
y
er
c
o
n
v
o
l
u
t
io
n
b
lo
c
k
s
a
r
e
u
s
e
d
t
o
g
e
t
r
i
d
o
f
t
h
e
d
e
e
p
f
e
at
u
r
e
s
t
h
a
t
ar
e
b
a
s
ed
o
n
th
e
s
u
r
f
a
c
e
.
T
h
e
f
e
a
tu
r
e
c
a
n
b
e
o
b
s
er
v
ed
in
t
h
e
m
id
d
le
c
h
a
n
n
e
l
s
w
i
th
th
e
s
p
ec
t
r
a
l
a
t
te
n
t
i
o
n
b
l
o
ck
.
T
h
e
m
ax
p
o
o
l
i
n
g
l
ay
e
r
a
l
s
o
s
h
r
i
n
k
s
th
e
s
i
z
e
o
f
t
h
e
f
ea
t
u
r
e
s
.
T
h
e
m
u
l
t
i
-
r
e
s
i
d
u
a
l
b
lo
ck
i
s
u
s
ed
t
o
f
in
d
th
e
m
o
s
t
i
m
p
o
r
t
a
n
t
p
a
r
t
s
.
T
h
e
la
s
t
s
t
e
p
i
s
w
h
e
n
t
h
e
m
u
l
t
i
-
r
e
s
i
d
u
a
l
b
l
o
ck
s
a
n
d
s
p
e
c
t
r
a
l
a
t
t
en
t
i
o
n
b
l
o
ck
s
g
e
t
t
h
e
d
ee
p
f
e
a
tu
r
e
s
th
a
t
w
er
e
t
ak
e
n
o
u
t
s
o
t
h
ey
c
an
g
e
t
h
i
er
a
r
c
h
i
ca
l
d
e
e
p
f
ea
t
u
r
e
s
.
I
n
th
e
s
e
c
o
n
d
s
t
r
e
a
m
,
s
p
a
t
i
a
l
a
t
t
e
n
ti
o
n
b
lo
ck
s
a
r
e
u
s
ed
to
lo
o
k
f
o
r
d
ee
p
s
p
a
t
i
a
l
f
e
a
t
u
r
e
s
b
y
l
o
o
k
i
n
g
a
t
d
e
ep
f
e
a
tu
r
e
s
.
T
h
e
s
p
e
c
tr
a
l
a
t
t
e
n
t
i
o
n
b
l
o
c
k
a
n
d
th
e
m
ax
p
o
o
l
in
g
l
ay
e
r
a
r
e
b
u
i
l
t
a
f
t
er
t
h
e
c
o
n
v
o
lu
t
i
o
n
l
a
y
e
r
.
T
h
e
d
en
s
e
l
a
y
er
g
e
t
s
th
e
f
l
a
t
te
n
ed
f
ea
t
u
r
e
s
,
a
n
d
t
h
e
f
l
a
t
t
en
l
a
y
e
r
f
l
a
t
t
e
n
s
th
e
d
e
e
p
f
e
a
t
u
r
e
s
th
a
t
w
er
e
t
a
k
en
o
u
t.
T
h
e
So
f
t
M
ax
la
y
er
th
e
n
f
in
d
s
o
u
t
wh
a
t
th
e
f
i
n
a
l
an
s
w
e
r
i
s
.
F
i
g
u
r
e
2
s
h
o
w
s
t
h
e
w
h
o
l
e
s
tr
u
c
tu
r
e
o
f
t
h
e
p
r
o
p
o
s
e
d
T
A
-
C
N
N
.
2
.
4
.
1
.
T
win
a
t
t
ent
io
n
m
ec
ha
nis
m
T
h
e
C
NN
’
s
atten
tio
n
b
l
o
ck
is
b
ased
o
n
h
o
w
th
e
h
u
m
a
n
b
r
ain
u
s
es
p
s
y
ch
o
lo
g
ical
A
M
to
f
in
d
im
p
o
r
tan
t
d
ee
p
f
ea
tu
r
es
in
s
tead
o
f
o
n
es
th
at
ar
en
’
t
u
s
ef
u
l
.
T
h
e
s
u
g
g
ested
AM
wo
r
k
s
b
y
u
s
in
g
s
p
ec
tr
al
-
tem
p
o
r
al
an
d
s
p
atial
-
tem
p
o
r
al
d
ata
f
r
o
m
in
p
u
t sam
p
les to
s
o
r
t r
ice
d
is
ea
s
es.
T
h
e
in
p
u
t f
ea
tu
r
e
m
ap
g
o
es to
th
e
co
n
v
o
l
u
tio
n
b
lo
c
k
.
T
h
e
k
er
n
e
l
s
ize
(
x
,
y
)
is
alm
o
s
t
th
e
s
am
e
as
th
e
in
p
u
t
f
ea
tu
r
e
’
s
len
g
th
an
d
wid
th
.
T
h
e
o
u
tco
m
e
f
ea
tu
r
e
m
ap
is
1
×
1
×
f
,
wh
er
e
f
is
th
e
n
u
m
b
er
o
f
f
il
ter
s
.
T
h
e
o
u
t
p
u
t
f
r
o
m
t
h
e
c
u
r
r
e
n
t
l
a
y
e
r
i
s
c
h
a
n
g
e
d
a
n
d
s
e
n
t
t
o
t
h
e
m
u
lt
i
-
l
a
y
e
r
p
e
r
ce
p
t
r
o
n
(
M
L
P
)
.
T
h
e
M
L
P
h
a
s
tw
o
d
e
n
s
e
l
a
y
e
r
s
w
it
h
n
e
u
r
o
n
s
o
f
d
i
f
f
e
r
e
n
t
s
i
ze
s
.
T
h
er
e
ar
e
a
lo
t
f
ewe
r
n
eu
r
o
n
s
in
th
e
f
ir
s
t
an
d
s
ec
o
n
d
lay
er
s
b
ec
au
s
e
o
f
th
e
n
ew
f
ea
tu
r
es.
B
ef
o
r
e
th
e
in
p
u
t
f
ea
tu
r
e
m
a
p
is
m
u
ltip
lie
d
with
th
e
e
x
tr
ac
ted
f
ea
t
u
r
es,
a
s
ep
ar
ab
le
co
n
v
o
lu
ti
o
n
lay
e
r
is
ap
p
lied
to
ea
ch
in
p
u
t
d
ata.
T
h
e
s
ep
ar
a
b
le
co
n
v
o
lu
tio
n
la
y
er
m
u
ltip
lies
th
e
f
ir
s
t
s
tr
ea
m
’
s
o
u
tp
u
t.
T
o
d
o
th
is
,
p
o
in
t
-
wis
e
an
d
d
ep
th
-
wis
e
co
n
v
o
lu
tio
n
a
r
e
u
s
ed
.
T
h
e
p
r
o
p
o
s
ed
s
p
atial
A
M
is
d
ef
in
e
d
b
y
f
ea
tu
r
e
m
ap
s
th
at
s
h
o
w
a
m
id
d
le
g
r
o
u
n
d
r
elatio
n
s
h
ip
.
I
t
is
th
e
s
am
e
as
th
e
s
p
ec
tr
al
AM
b
ec
au
s
e
it
o
n
ly
k
ee
p
s
th
e
m
o
s
t
im
p
o
r
tan
t
p
ar
ts
o
f
th
e
in
p
u
t
f
ea
tu
r
e
m
a
p
.
Af
ter
th
at,
th
e
in
p
u
t
f
ea
tu
r
e
m
a
p
is
tu
r
n
ed
in
to
a
co
n
v
o
lu
tio
n
b
lo
ck
with
a
k
er
n
el
s
ize
o
f
(
x
,
y
)
an
d
o
n
ly
o
n
e
k
e
r
n
el
f
o
r
co
n
v
o
l
u
tio
n
an
d
p
ad
d
in
g
.
T
h
e
o
u
tco
m
e
f
ea
tu
r
e
m
ap
h
as
a
s
ize
o
f
x
×
y
×
1
.
T
h
e
ML
P
g
ets
th
e
n
ew
r
esu
lt
f
r
o
m
th
e
lay
er
th
at
is
cu
r
r
e
n
tly
ac
tiv
e.
I
t
h
as
two
f
u
lly
co
n
v
o
lu
te
d
(
FC
)
lay
er
s
,
ea
ch
with
n
eu
r
o
n
s
o
f
d
if
f
er
e
n
t
s
izes.
T
h
er
e
ar
e
a
lo
t
f
ewe
r
n
eu
r
o
n
s
in
th
e
f
ir
s
t
lay
er
th
an
th
er
e
wer
e
b
ef
o
r
e.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
756
-
7
6
5
760
s
ec
o
n
d
FC
lay
er
ch
an
g
es
h
o
w
all
th
e
f
ea
tu
r
es
lo
o
k
,
an
d
th
e
s
ep
ar
ab
le
co
n
v
o
lu
tio
n
lay
e
r
is
u
s
ed
o
n
ea
ch
in
p
u
t
d
ata
b
ef
o
r
e
th
e
in
p
u
t f
ea
tu
r
e
m
ap
an
d
ex
tr
ac
ted
f
ea
tu
r
es a
r
e
m
u
ltip
lied
.
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
twin
atten
tio
n
-
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
m
o
d
e
2
.
4
.
2
.
Co
nv
o
lutio
n la
y
er
T
h
e
co
n
v
o
lu
tio
n
lay
e
r
is
th
e
m
o
s
t
im
p
o
r
tan
t
p
ar
t
o
f
a
C
NN
n
etwo
r
k
f
o
r
g
ettin
g
h
ier
a
r
ch
i
ca
l
f
ea
tu
r
es
f
r
o
m
th
e
in
p
u
t
s
am
p
les.
T
h
e
co
n
v
o
lu
tio
n
lay
er
au
to
m
atica
lly
s
p
lits
th
e
s
p
atial
an
d
s
p
ec
tr
al
f
ea
tu
r
es.
Ma
th
em
atica
lly
,
th
e
co
n
v
o
lu
ti
o
n
lay
er
'
s
m
ain
jo
b
ca
n
b
e
u
n
d
er
s
to
o
d
as
:
=
(
−
1
)
+
(
4
)
I
n
th
is
ca
s
e,
β
is
th
e
ac
t
iv
atio
n
f
u
n
ctio
n
,
w
is
th
e
weig
h
ted
tem
p
lates,
B
M
i
s
th
e
b
ias
v
ec
to
r
,
an
d
M
is
th
e
to
tal
n
u
m
b
er
o
f
la
y
er
s
.
T
h
e
o
u
tp
u
t
o
f
th
e
lth
f
ea
tu
r
e
m
a
p
at
th
e
s
p
atial
co
o
r
d
in
ates (
r
,
s
)
ca
n
b
e
e
x
p
r
ess
ed
as
:
,
=
(
,
+
∑
∑
∑
,
,
(
+
)
(
+
)
−
1
,
−
1
=
0
−
1
=
0
)
(
5
)
T
h
is
tim
e,
C
is
th
e
f
ea
t
u
r
e
c
u
b
e
th
at
was
co
m
b
in
ed
with
th
e
cu
r
r
e
n
t
f
ea
tu
r
e
cu
b
e
a
n
d
is
th
e
(
M
–
1
)
th
lay
er
.
T
h
e
f
ilter
’
s
len
g
th
is
X,
an
d
t
h
e
f
ilter
’
s
wid
t
h
is
Y.
Usi
n
g
t
h
e
r
esid
u
al
an
d
m
u
ltip
le
s
ca
lin
g
b
lo
ck
s
ca
n
m
ak
e
th
e
n
etwo
r
k
m
o
d
el
wo
r
k
b
etter
an
d
h
elp
a
lo
t to
s
to
p
g
r
a
d
ien
t in
s
u
f
f
icien
cy
.
W
h
en
a
r
ice
p
lan
t
lo
s
es
it
i
s
f
u
n
ctio
n
,
it
’
s
h
ar
d
to
tell
wh
at
k
in
d
o
f
d
is
ea
s
e
it
h
as.
T
h
e
m
u
lti
-
f
ea
tu
r
e
s
y
s
tem
wo
r
k
s
well
b
ec
au
s
e
t
h
e
T
A
-
C
NN
lo
s
s
f
u
n
ctio
n
is
lo
wer
.
T
h
e
lo
s
s
f
u
n
cti
o
n
al
way
s
lo
o
k
s
at
th
e
n
eg
ativ
e
f
r
am
es,
wh
ich
lo
wer
s
th
e
tr
u
e
p
o
s
itiv
e
r
ate.
Du
r
in
g
tr
ain
in
g
,
th
er
e
will
b
e
a
s
m
all
d
if
f
er
en
ce
in
h
o
w
th
e
wh
o
le
n
etwo
r
k
is
h
an
d
led
.
T
h
is
im
b
alan
ce
ca
u
s
es
th
e
ex
tr
a
f
ac
to
r
to
c
r
o
s
s
th
e
o
r
ig
in
al
p
ar
am
eter
th
at
h
as
g
o
n
e
b
ad
.
T
h
e
lo
s
s
ca
n
b
ea
t th
e
g
r
ad
ien
t
o
f
im
ag
es th
at
a
r
en
'
t e
v
en
ly
s
p
ac
ed
.
Input
e
xt
ra
c
t
e
d
fe
a
t
ure
s
Cl
a
s
s
i
fi
e
d he
a
l
t
hy
/
U
nhe
a
l
t
hy c
l
a
s
s
e
s
D
e
e
p fe
a
t
ure
e
xt
ra
c
t
i
on i
n S
pa
t
i
a
l
a
t
t
e
nt
i
on bl
oc
k
D
e
e
p fe
a
t
ure
e
xt
ra
c
t
i
on i
n S
pe
c
t
ra
l
a
t
t
e
nt
i
on bl
oc
k
2
D
-
M
a
x pool
i
ng
K
e
rne
l
s
i
z
e
-
3
x
3
F
l
a
t
t
e
ne
d l
a
ye
r
F
C l
a
ye
r
Re
L
U
a
c
t
i
va
t
i
on
func
t
i
on
D
ropout
-
0
.
1
S
oft
m
a
x
l
a
ye
r
2
D
-
c
onvol
ut
i
on l
a
ye
r
K
e
rne
l
s
i
z
e
-
7
x
7
Re
L
u a
c
t
i
va
t
i
on fun
c
t
i
on
Ba
t
c
h norm
a
l
i
z
a
t
i
on
2
D
-
c
onvol
ut
i
on l
a
ye
r
K
e
rne
l
s
i
z
e
-
5
x
5
Re
L
u a
c
t
i
va
t
i
on fun
c
t
i
on
Ba
t
c
h norm
a
l
i
z
a
t
i
on
2
D
-
c
onvol
ut
i
on l
a
ye
r
K
e
rn
e
l
s
i
z
e
-
3
x
3
Re
L
u a
c
t
i
va
t
i
on fun
c
t
i
on
Ba
t
c
h norm
a
l
i
z
a
t
i
on
S
pe
c
t
ra
l
a
t
t
e
nt
i
on
bl
oc
k
S
pa
t
i
a
l
a
t
t
e
nt
i
on
bl
oc
k
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
I
n
tellig
en
t p
la
n
t
d
is
ea
s
e
d
etec
tio
n
u
s
in
g
tw
in
a
tten
tio
n
o
p
tim
a
l c
o
n
vo
l
u
tio
n
a
l
n
eu
r
a
l
…
(
P
r
a
mee
th
a
P
a
i
)
761
2
.
4
.
3
.
L
o
s
s
f
un
ct
io
n r
educt
io
n us
ing
cha
o
t
ic
s
lim
e
m
o
uld
o
ptim
iza
t
io
n t
ec
hn
iqu
e
T
h
e
lo
s
s
es
in
T
A
-
C
N
N
m
ak
e
ac
cu
r
ac
y
p
er
f
o
r
m
a
n
ce
m
u
c
h
wo
r
s
e.
T
h
at
’
s
wh
y
th
is
s
tu
d
y
s
u
g
g
ests
th
e
C
SM
o
p
tim
izatio
n
m
eth
o
d
.
T
h
e
s
tan
d
ar
d
s
lim
e
m
o
u
ld
(
SM
)
m
eth
o
d
[
2
8
]
d
ep
e
n
d
s
o
n
h
o
w
SM
m
o
v
es
b
ac
k
an
d
f
o
r
th
.
A
m
ath
em
atica
l
s
tu
d
y
f
in
d
s
th
e
b
est
way
to
f
in
d
f
o
o
d
th
at
h
as
a
lo
t
o
f
r
o
o
m
to
e
x
p
lo
r
e
a
n
d
u
s
e.
B
u
t
th
is
m
eth
o
d
ta
k
es
lo
n
g
e
r
to
r
ea
ch
a
s
o
lu
tio
n
an
d
is
m
o
r
e
lik
ely
to
g
et
s
tu
ck
in
lo
ca
l
o
p
tim
a.
C
o
m
b
in
in
g
ch
ao
tic
m
ap
p
i
n
g
with
SM
o
p
ti
m
izatio
n
s
p
ee
d
s
u
p
t
h
e
s
ea
r
ch
an
d
m
ak
es b
etter
u
s
e
o
f
l
o
ca
lized
s
o
lu
tio
n
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
f
o
cu
s
s
es
o
n
d
is
ea
s
e
class
if
icat
io
n
u
s
in
g
an
I
n
d
ian
d
ataset
[
2
9
]
co
llec
ted
f
r
o
m
Gan
d
h
in
ag
a
r
,
Gu
jar
at,
co
n
tai
n
in
g
ar
o
u
n
d
1
2
0
u
n
h
ea
lth
y
c
lass
es.
B
ec
au
s
e
th
e
d
ataset
o
n
ly
h
as
u
n
h
ea
lth
y
class
es,
a
p
u
b
licly
av
ailab
le
r
ice
leaf
d
ataset
[
3
0
]
with
4
,
0
0
0
h
ea
lth
y
class
es
was
m
ad
e.
T
h
e
class
if
icatio
n
p
r
o
ce
s
s
u
s
es
4
,
1
2
0
class
es
in
th
e
en
d
.
So
m
e
o
f
th
ese
class
es
ar
e
h
ea
lth
y
,
an
d
s
o
m
e
ar
e
n
o
t.
T
h
e
h
y
p
er
p
ar
am
eter
s
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
ar
e
s
h
o
wn
in
T
ab
le
2
.
T
ab
le
2
.
Hy
p
er
p
a
r
am
eter
s
o
f
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
H
y
p
e
r
p
a
r
a
m
e
t
e
r
s
V
a
l
u
e
s
O
p
t
i
mi
z
e
r
C
S
M
o
p
t
i
mi
z
e
r
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
0
1
Ep
o
c
h
s
1
0
0
Lo
ss f
u
n
c
t
i
o
n
B
i
n
a
r
y
c
r
o
ss
e
n
t
r
o
p
y
B
a
t
c
h
si
z
e
60
D
r
o
p
o
u
t
0
.
3
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
’
s
co
n
f
u
s
io
n
m
atr
ix
is
s
h
o
wn
in
Fig
u
r
e
3
.
A
to
tal
o
f
1
1
6
s
am
p
les
is
ex
am
in
ed
f
o
r
th
e
h
ea
lth
y
ca
teg
o
r
ies.
T
h
e
r
e
a
r
e
1
1
5
s
am
p
l
es
t
h
a
t a
r
e
c
o
r
r
e
ctl
y
i
d
en
ti
f
ie
d
as h
e
alt
h
y
cla
s
s
es
a
n
d
o
n
e
t
h
at
is
in
c
o
r
r
ec
tl
y
i
d
en
ti
f
ie
d
as
a
n
u
n
h
e
alt
h
y
class
.
T
h
e
r
e
a
r
e
1
1
5
s
am
p
les
i
n
th
e
u
n
h
e
alt
h
y
c
lass
es.
All
1
1
5
s
a
m
p
les
ar
e
co
r
r
ec
tly
p
u
t in
to
th
e
u
n
h
e
alth
y
class
es in
th
is
ca
s
e.
Fig
u
r
e
4
s
h
o
ws
h
o
w
lo
n
g
it
tak
es
f
o
r
ea
ch
m
eth
o
d
to
wo
r
k
.
T
h
e
g
r
ap
h
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
ta
k
es
less
tim
e
th
an
c
u
r
r
en
t
m
eth
o
d
s
.
T
h
e
c
u
r
r
e
n
t
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
B
i
-
L
STM
)
,
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
(
R
NN)
,
d
ee
p
n
eu
r
al
n
etwo
r
k
(
DNN)
,
an
d
p
r
o
p
o
s
ed
m
o
d
el
tak
e
4
0
1
.
2
3
,
4
2
1
.
3
6
,
3
9
9
.
4
1
,
4
1
3
.
5
2
,
an
d
2
5
1
.
3
2
m
s
,
r
esp
ec
tiv
ely
.
T
h
e
cu
r
r
en
t
m
eth
o
d
s
tak
e
a
lo
n
g
tim
e
b
ec
au
s
e
th
ey
d
o
n
'
t
wo
r
k
well
with
b
ig
d
atase
ts
wh
en
t
h
ey
’
r
e
b
ein
g
tr
ain
ed
.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
i
d
m
eth
o
d
y
ield
s
in
tr
ig
u
in
g
r
esu
lts
with
m
in
im
al
tim
e
co
m
p
lex
ity
.
I
t
also
s
h
o
ws
p
er
f
o
r
m
an
ce
th
at
is
alm
o
s
t
th
e
s
am
e
wh
en
th
e
am
o
u
n
t
o
f
t
r
ain
in
g
d
ata
in
cr
ea
s
es.
Fig
u
r
e
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
Fig
u
r
e
4
.
T
im
e
co
m
p
le
x
ity
u
n
d
er
d
if
f
e
r
en
t m
eth
o
d
s
Fig
u
r
es
5
s
h
o
w
h
o
w
well
th
e
p
r
ed
ictio
n
s
an
d
th
e
m
is
tak
es wo
r
k
ed
.
Fig
u
r
e
5
(
a)
s
h
o
ws
th
e
p
r
ed
ictio
n
-
b
ased
p
er
f
o
r
m
an
ce
,
wh
ile
Fig
u
r
e
5
(
b
)
s
h
o
ws
th
e
er
r
o
r
p
e
r
f
o
r
m
a
n
ce
s
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
s
u
g
g
ested
m
eth
o
d
wo
r
k
s
well
to
tell
th
e
d
if
f
er
e
n
ce
b
etwe
en
h
ea
lth
y
an
d
u
n
h
ea
lth
y
g
r
o
u
p
s
.
T
ab
le
3
s
h
o
ws
h
o
w
well
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
756
-
7
6
5
762
d
if
f
er
en
t
m
eth
o
d
s
wo
r
k
e
d
b
y
u
s
in
g
p
er
f
o
r
m
an
ce
m
etr
ics,
an
d
T
a
b
le
4
s
h
o
ws
h
o
w
wel
l
d
if
f
er
e
n
t
m
etr
ics
wo
r
k
ed
with
d
if
f
er
en
t
b
atch
s
i
ze
s
.
(
a)
(
b
)
Fig
u
r
e
5
.
Per
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
u
n
d
er
:
(
a)
p
r
ed
ictio
n
-
b
ased
p
er
f
o
r
m
an
ce
an
d
(
b
)
e
r
r
o
r
p
er
f
o
r
m
a
n
ce
s
T
ab
le
3
.
Ob
tain
e
d
o
u
tc
o
m
e
o
f
d
if
f
er
en
t te
ch
n
iq
u
es u
n
d
er
p
er
f
o
r
m
an
ce
m
etr
ics
M
e
t
r
i
c
s
M
e
t
h
o
d
s
Bi
-
LST
M
R
N
N
DNN
D
B
N
P
r
o
p
o
se
d
A
c
c
u
r
a
c
y
9
9
.
1
3
9
8
.
2
6
9
7
.
4
0
9
6
.
5
3
9
9
.
5
6
F
-
mea
su
r
e
9
8
.
7
9
9
7
.
9
2
9
7
.
0
5
9
6
.
2
1
9
9
.
2
1
S
e
n
s
i
t
i
v
i
t
y
9
8
.
7
3
9
7
.
8
7
97
9
6
.
1
4
9
9
.
1
6
S
p
e
c
i
f
i
c
i
t
y
9
8
.
1
4
9
7
.
2
7
9
6
.
4
1
9
5
.
5
8
9
8
.
5
6
P
r
e
c
i
s
i
o
n
9
8
.
8
4
9
7
.
9
7
9
7
.
1
9
6
.
2
8
9
9
.
2
6
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
(
M
A
E)
0
.
0
0
8
6
0
.
0
1
7
0
.
0
2
5
0
.
0
3
4
0
.
0
0
4
3
M
e
a
n
sq
u
a
r
e
d
e
r
r
o
r
(
M
S
E)
0
.
0
0
8
6
0
.
0
1
7
0
.
0
2
5
0
.
0
3
4
0
.
0
0
4
3
R
o
o
t
me
a
n
sq
u
a
r
e
e
r
r
o
r
(
R
M
S
E)
0
.
0
9
3
0
.
1
3
0
.
1
6
0
.
1
8
0
.
0
6
5
T
ab
le
4
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
th
e
b
atch
s
ize
u
n
d
er
d
if
f
er
e
n
t m
etr
ics
M
o
d
e
l
s
B
a
t
c
h
si
z
e
A
c
c
u
r
a
c
y
(
%)
F
1
sc
o
r
e
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
S
p
e
c
i
f
i
c
i
t
y
(
%)
P
r
o
p
o
se
d
20
9
6
.
5
9
6
.
3
2
9
6
.
3
9
6
.
5
6
9
6
.
7
40
9
7
.
3
97
9
6
.
5
9
7
.
3
9
7
.
1
5
60
9
9
.
3
9
8
.
4
5
9
8
.
3
5
9
8
.
5
9
9
.
0
1
80
9
8
.
3
9
7
.
3
9
7
.
1
3
97
9
8
.
3
1
0
0
9
7
.
9
9
6
.
2
1
9
6
.
8
9
6
.
3
9
7
.
6
BI
-
LSTM
20
9
5
.
9
9
4
.
4
9
5
.
8
9
4
.
7
9
4
.
3
40
9
5
.
6
9
5
.
1
1
9
5
.
2
1
9
6
.
1
9
5
.
2
60
9
7
.
3
9
6
.
5
2
9
7
.
1
5
9
7
.
7
5
9
5
.
3
5
80
9
5
.
2
9
4
.
2
9
4
.
2
4
9
4
.
1
4
9
4
.
5
1
0
0
94
9
3
.
6
9
4
.
1
2
9
3
.
2
9
2
.
6
R
N
N
20
9
3
.
8
9
5
.
6
9
3
.
5
9
3
.
7
9
4
.
6
40
9
4
.
3
9
6
.
4
9
5
.
1
4
9
4
.
4
9
5
.
4
60
9
5
.
6
9
7
.
3
6
9
5
.
2
6
9
5
.
1
6
9
6
.
1
6
80
9
4
.
2
9
4
.
4
94
9
4
.
4
9
4
.
4
1
0
0
9
3
.
5
9
2
.
1
4
9
2
.
4
9
2
.
8
9
3
.
3
DNN
20
9
2
.
5
9
3
.
3
6
9
2
.
2
9
2
.
5
9
3
.
4
40
9
3
.
2
9
4
.
5
9
3
.
5
9
3
.
6
9
4
.
4
60
9
5
.
2
9
6
.
2
9
5
.
8
9
4
.
5
9
5
.
5
1
80
9
4
.
6
9
3
.
1
6
9
4
.
1
6
9
2
.
1
6
9
3
.
1
6
1
0
0
9
3
.
3
9
3
.
2
8
9
4
.
2
3
92
9
2
.
4
5
4.
CO
NCLU
SI
O
N
T
h
e
ex
is
ten
ce
o
f
a
n
a
u
to
m
ated
co
m
p
u
tatio
n
al
s
y
s
tem
f
o
r
d
et
ec
tin
g
r
ice
p
lan
t d
is
ea
s
es
is
s
i
g
n
if
ican
tly
in
f
lu
en
ce
d
b
y
f
l
u
ctu
atin
g
e
n
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
an
d
tem
p
o
r
al
co
m
p
lex
ities
.
T
h
is
s
tu
d
y
p
r
esen
ts
an
in
n
o
v
ativ
e
h
y
b
r
id
DL
m
eth
o
d
o
lo
g
y
f
o
r
th
e
class
if
icatio
n
o
f
r
ice
p
lan
t
leaf
d
is
ea
s
es.
T
h
e
s
u
g
g
ested
m
eth
o
d
h
as a
n
o
v
er
all
ac
cu
r
ac
y
o
f
9
9
.
5
6
%,
an
F
-
m
ea
s
u
r
e
o
f
9
9
.
2
1
%,
a
s
en
s
itiv
ity
o
f
9
9
.
1
6
%,
a
s
p
ec
if
icity
o
f
9
8
.
5
6
%,
a
p
r
ec
is
io
n
o
f
9
9
.
2
6
%,
a
MA
E
o
f
0
.
0
0
4
,
a
MSE
o
f
0
.
0
0
4
,
a
n
d
a
R
MSE
o
f
0
.
0
6
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
v
er
y
h
elp
f
u
l
f
o
r
f
in
d
in
g
d
is
ea
s
es
i
n
m
an
y
cr
o
p
s
,
an
d
it
d
o
esn
'
t
tak
e
lo
n
g
.
B
u
t
th
e
s
u
g
g
ested
m
eth
o
d
d
o
esn
'
t
s
ay
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
I
n
tellig
en
t p
la
n
t
d
is
ea
s
e
d
etec
tio
n
u
s
in
g
tw
in
a
tten
tio
n
o
p
tim
a
l c
o
n
vo
l
u
tio
n
a
l
n
eu
r
a
l
…
(
P
r
a
mee
th
a
P
a
i
)
763
h
o
w
b
ad
th
e
d
is
ea
s
e
is
f
o
r
th
e
r
ice
cr
o
p
.
T
h
e
r
esear
ch
e
r
s
n
ee
d
to
f
in
d
b
etter
way
s
to
f
ig
u
r
e
o
u
t
h
o
w
b
ad
th
e
d
is
ea
s
e
is
th
at
af
f
ec
ts
th
e
leav
es
o
f
r
ice
p
lan
ts
in
th
e
f
u
tu
r
e
.
T
h
e
p
r
o
p
o
s
ed
wo
r
k
n
ee
d
s
to
b
e
b
etter
in
o
r
d
er
to
f
in
d
m
o
r
e
p
lan
t
d
is
ea
s
es a
n
d
s
ee
h
o
w
well
th
e
m
o
d
el
wo
r
k
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
ass
er
t
th
at
th
ey
d
id
n
o
t
r
ec
eiv
e
an
y
f
in
an
cial
co
m
p
en
s
atio
n
,
g
r
an
ts
,
o
r
ass
is
tan
ce
d
u
r
i
n
g
th
e
co
m
p
o
s
itio
n
o
f
th
is
p
a
p
er
.
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
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
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
Pra
m
ee
th
a
Pai
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Nam
ith
a
S
.
J
.
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
S
o
w
m
y
a
T
.
✓
✓
✓
✓
✓
✓
✓
✓
✓
Am
u
th
a
S
.
✓
✓
✓
✓
✓
✓
✓
Nis
ar
g
a
Go
n
d
i
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
claim
th
at
th
er
e
a
r
e
n
o
co
n
f
licts
o
f
in
ter
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
T
h
i
s
s
t
u
d
y
d
id
n
o
t
i
n
v
o
lv
e
i
n
d
i
v
id
u
a
l
s
o
r
an
y
p
e
r
s
o
n
al
i
d
e
n
t
if
i
c
a
t
i
o
n
i
n
f
o
r
m
a
t
io
n
r
e
q
u
i
r
in
g
i
n
f
o
r
m
ed
co
n
s
en
t
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
is
p
ap
er
d
o
es
n
o
t
in
cl
u
d
e
in
d
iv
id
u
als
o
r
an
im
als;
th
er
e
h
as
b
ee
n
n
o
r
esear
ch
in
v
o
lv
i
n
g
h
u
m
an
s
u
b
jects.
T
h
e
au
th
o
r
s
d
id
n
o
t seek
ap
p
r
o
v
al
f
r
o
m
a
n
y
in
s
titu
t
io
n
al
r
ev
iew
b
o
ar
d
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
a
t
a
t
h
a
t
s
u
p
p
o
r
t
t
h
e
r
e
s
u
lt
s
o
f
t
h
is
s
t
u
d
y
w
e
r
e
g
a
t
h
e
r
e
d
f
r
o
m
p
u
b
l
i
c
l
y
a
v
a
i
l
a
b
l
e
r
e
p
o
s
i
to
r
i
e
s
a
n
d
u
s
e
d
t
o
t
r
a
i
n
a
n
d
t
es
t
t
h
e
s
u
g
g
e
s
t
e
d
T
A
O
-
C
NN
f
o
r
d
e
te
c
t
i
n
g
p
l
a
n
t
d
is
e
as
es
.
T
h
e
P
la
n
t
V
il
l
ag
e
d
a
t
a
s
e
t
,
w
h
i
c
h
is
p
u
b
l
i
c
l
y
a
v
a
i
la
b
l
e
,
w
a
s
u
s
e
d
i
n
t
h
i
s
s
t
u
d
y
.
T
o
e
n
h
a
n
c
e
m
o
d
e
l'
s
p
e
r
f
o
r
m
a
n
c
e
,
a
d
d
i
ti
o
n
a
l
d
a
ta
w
e
r
e
i
n
c
o
r
p
o
r
a
t
e
d
,
i
m
a
g
e
s
i
z
es
we
r
e
a
d
j
u
s
t
e
d
,
a
n
d
t
h
e
d
a
t
as
e
t
w
as
s
t
a
n
d
a
r
d
i
ze
d
.
T
h
e
c
o
r
r
e
s
p
o
n
d
i
n
g
a
u
t
h
o
r
,
[
P
P
]
,
ca
n
p
r
o
v
i
d
e
a
l
l
s
c
r
i
p
ts
u
s
e
d
f
o
r
d
a
t
a
p
r
e
p
a
r
at
io
n
a
n
d
m
o
d
e
l
t
r
a
i
n
i
n
g
,
al
o
n
g
w
i
t
h
t
r
ai
n
e
d
m
o
d
e
l
w
e
i
g
h
ts
a
n
d
e
v
a
l
u
a
t
i
o
n
r
es
u
l
ts
,
u
p
o
n
r
e
q
u
e
s
t
.
T
h
e
s
e
m
a
te
r
i
a
ls
a
r
e
i
n
t
e
n
d
e
d
s
o
l
el
y
f
o
r
r
e
s
e
a
r
c
h
t
h
a
t
is
n
o
t
f
o
r
s
c
h
o
o
l
o
r
b
u
s
i
n
es
s
.
RE
F
E
R
E
NC
E
S
[
1
]
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.
[
2
]
Y
.
B
o
r
h
a
n
i
,
J.
K
h
o
r
a
m
d
e
l
,
a
n
d
E.
N
a
j
a
f
i
,
“
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
a
u
t
o
ma
t
e
d
p
l
a
n
t
d
i
se
a
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
v
i
s
i
o
n
t
r
a
n
sf
o
r
mer,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
022
-
1
5
1
6
3
-
0.
[
3
]
V
.
K
.
S
h
r
i
v
a
s
t
a
v
a
,
M
.
K
.
P
r
a
d
h
a
n
,
a
n
d
M
.
P
.
T
h
a
k
u
r
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
p
r
e
-
t
r
a
i
n
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
f
o
r
r
i
c
e
p
l
a
n
t
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
m
a
r
t
S
y
st
e
m
s,
I
C
AI
S
2
0
2
1
,
2
0
2
1
,
p
p
.
1
0
2
3
–
1
0
3
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
S
5
0
9
3
0
.
2
0
2
1
.
9
3
9
5
8
1
3
.
[
4
]
M
.
S
h
a
r
m
a
,
C
.
J
.
K
u
mar,
a
n
d
A
.
D
e
k
a
,
“
E
a
r
l
y
d
i
a
g
n
o
s
i
s
o
f
r
i
c
e
p
l
a
n
t
d
i
s
e
a
se
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
Ar
c
h
i
v
e
s
o
f
Ph
y
t
o
p
a
t
h
o
l
o
g
y
a
n
d
Pl
a
n
t
Pro
t
e
c
t
i
o
n
,
v
o
l
.
5
5
,
n
o
.
3
,
p
p
.
2
5
9
–
2
8
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
0
3
2
3
5
4
0
8
.
2
0
2
1
.
2
0
1
5
8
6
6
.
[
5
]
T.
S
.
P
o
o
r
n
a
p
p
r
i
y
a
a
n
d
R
.
G
o
p
i
n
a
t
h
,
“
R
i
c
e
p
l
a
n
t
d
i
s
e
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
si
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
p
p
r
o
a
c
h
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
1
,
n
o
.
1
0
,
p
p
.
3
9
2
–
4
0
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
7
6
0
5
/
O
S
F
.
I
O
/
R
5
J
X
A
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
20
26
:
756
-
7
6
5
764
[
6
]
S
.
B
a
b
u
,
M
.
M
a
r
a
v
a
r
ma
n
,
a
n
d
R
.
P
i
t
c
h
a
i
,
“
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
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
J
o
u
rn
a
l
o
f
M
o
b
i
l
e
Mu
l
t
i
m
e
d
i
a
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
7
5
7
–
7
7
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
3
0
5
2
/
j
mm
1
5
5
0
-
4
6
4
6
.
1
8
3
1
4
.
[
7
]
J.
C
h
e
n
,
W
.
C
h
e
n
,
A
.
Ze
b
,
S
.
Y
a
n
g
,
a
n
d
D
.
Zh
a
n
g
,
“
Li
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 fo
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
s
e
a
se
s,”
I
EEE
S
e
n
s
o
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
,
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
.
[
8
]
J.
C
h
e
n
,
D
.
Z
h
a
n
g
,
A
.
Z
e
b
,
a
n
d
Y
.
A
.
N
a
n
e
h
k
a
r
a
n
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
r
i
c
e
p
l
a
n
t
d
i
s
e
a
se
s
u
s
i
n
g
l
i
g
h
t
w
e
i
g
h
t
a
t
t
e
n
t
i
o
n
n
e
t
w
o
r
k
s,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
6
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
0
.
1
1
4
5
1
4
.
[
9
]
Y
.
W
a
n
g
,
H
.
W
a
n
g
,
a
n
d
Z.
P
e
n
g
,
“
R
i
c
e
d
i
s
e
a
s
e
s
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
a
t
t
e
n
t
i
o
n
b
a
s
e
d
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
B
a
y
e
si
a
n
o
p
t
i
m
i
z
a
t
i
o
n
,
”
E
x
p
e
rt
S
y
st
e
m
s w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
1
.
1
1
4
7
7
0
.
[
1
0
]
T.
T
o
sawa
d
i
,
T.
K
a
se
t
k
a
sem
,
W
.
L
a
u
n
g
n
a
r
u
t
a
i
,
T.
P
h
a
t
r
a
p
o
m
n
a
n
t
,
a
n
d
I
.
K
u
ma
z
a
w
a
,
“
A
u
t
o
ma
t
i
c
r
i
c
e
p
l
a
n
t
d
i
sea
s
e
e
v
a
l
u
a
t
i
o
n
met
h
o
d
b
a
se
d
o
n
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
E
C
T
I
-
C
O
N
2
0
2
1
-
2
0
2
1
1
8
t
h
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
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
/
E
l
e
c
t
r
o
n
i
c
s
,
C
o
m
p
u
t
e
r
,
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
:
S
m
a
r
t
El
e
c
t
r
i
c
a
l
S
y
s
t
e
m
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
2
1
,
p
p
.
9
0
0
–
9
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
E
C
T
I
-
C
O
N
5
1
8
3
1
.
2
0
2
1
.
9
4
5
4
7
3
7
.
[
1
1
]
K
.
K
u
mar K
a
n
d
E.
K
a
n
n
a
n
,
“
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
u
si
n
g
A
da
B
o
o
st
S
V
M
c
l
a
ss
i
f
i
e
r
,
”
A
g
r
o
n
o
m
y
J
o
u
r
n
a
l
,
v
o
l
.
1
1
4
,
n
o
.
4
,
p
p
.
2
2
1
3
–
2
2
2
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
a
g
j
2
.
2
1
0
7
0
.
[
1
2
]
N
.
K
r
i
sh
n
a
mo
o
r
t
h
y
,
L
.
V
.
N
.
P
r
a
sa
d
,
C
.
S
.
P
.
K
u
m
a
r
,
B
.
S
u
b
e
d
i
,
H
.
B
.
A
b
r
a
h
a
,
a
n
d
V
.
E.
S
a
t
h
i
sh
k
u
mar,
“
R
i
c
e
l
e
a
f
d
i
s
e
a
ses
p
r
e
d
i
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
s
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
En
v
i
r
o
n
m
e
n
t
a
l
Re
s
e
a
rc
h
,
v
o
l
.
1
9
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
v
r
e
s
.
2
0
2
1
.
1
1
1
2
7
5
.
[
1
3
]
B
.
R
.
P
u
s
h
p
a
,
A
.
A
sh
o
k
,
a
n
d
A
.
V
.
S
.
H
a
r
i
,
“
P
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
v
e
n
t
i
v
e
Re
se
a
r
c
h
i
n
C
o
m
p
u
t
i
n
g
Ap
p
l
i
c
a
t
i
o
n
s
,
I
C
I
RC
A
2
0
2
1
,
2
0
2
1
,
p
p
.
1
2
8
5
–
1
2
9
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
R
C
A
5
1
5
3
2
.
2
0
2
1
.
9
5
4
4
7
2
9
.
[
1
4
]
B
.
P
a
t
e
l
a
n
d
A
.
S
h
a
r
a
f
f
,
“
R
i
c
e
c
r
o
p
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
g
ri
c
u
l
t
u
r
a
l
a
n
d
En
v
i
r
o
n
m
e
n
t
a
l
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
1
2
,
n
o
.
4
,
2
0
2
1
,
d
o
i
:
1
0
.
4
0
1
8
/
I
JA
E
I
S
.
2
0
2
1
1
0
0
1
.
o
a
5
.
[
1
5
]
B
.
S
.
B
a
r
i
e
t
a
l
.
,
“
A
r
e
a
l
-
t
i
m
e
a
p
p
r
o
a
c
h
o
f
d
i
a
g
n
o
s
i
n
g
r
i
c
e
l
e
a
f
d
i
sea
s
e
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
f
a
st
e
r
R
-
C
N
N
f
r
a
mew
o
r
k
,
”
Pe
e
r
J
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
2
0
2
1
,
d
o
i
:
1
0
.
7
7
1
7
/
P
E
ER
J
-
C
S
.
4
3
2
.
[
1
6
]
R
.
S
o
w
my
a
l
a
k
s
h
m
i
e
t
a
l
.
,
“
A
n
o
p
t
i
m
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
mo
d
e
l
f
o
r
r
i
c
e
p
l
a
n
t
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
,
”
C
o
m
p
u
t
e
rs,
M
a
t
e
ri
a
l
s a
n
d
C
o
n
t
i
n
u
a
,
v
o
l
.
6
8
,
n
o
.
2
,
p
p
.
1
7
5
1
–
1
7
6
7
,
2
0
2
1
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc
.
2
0
2
1
.
0
1
6
8
2
5
.
[
1
7
]
R
.
S
h
a
r
ma
,
V
.
K
u
k
r
e
j
a
,
a
n
d
V
.
K
a
d
y
a
n
,
“
H
i
s
p
a
r
i
c
e
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
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
,
”
i
n
2
0
2
1
3
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
PS
C
2
0
2
1
,
2
0
2
1
,
p
p
.
3
7
7
–
3
8
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
P
C
5
1
3
5
1
.
2
0
2
1
.
9
4
5
1
8
0
0
.
[
1
8
]
K
.
K
.
Je
n
a
,
S
.
K
.
B
h
o
i
,
D
.
M
o
h
a
p
a
t
r
a
,
C
.
M
a
l
l
i
c
k
,
a
n
d
P
.
S
w
a
i
n
,
“
R
i
c
e
d
i
sea
se
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
su
p
e
r
v
i
s
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
i
n
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
-
S
MA
C
(
I
o
T
i
n
S
o
c
i
a
l
,
Mo
b
i
l
e
,
A
n
a
l
y
t
i
c
s
a
n
d
C
l
o
u
d
)
,
I
-
S
M
AC
2
0
2
1
,
2
0
2
1
,
p
p
.
3
2
8
–
333
,
d
o
i
:
1
0
.
1
1
0
9
/
I
-
S
M
A
C
5
2
3
3
0
.
2
0
2
1
.
9
6
4
1
0
5
4
.
[
1
9
]
S
.
A
g
g
a
r
w
a
l
e
t
a
l
.
,
“
R
i
c
e
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
u
si
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
t
o
i
mp
r
o
v
i
se
a
g
r
o
-
b
u
s
i
n
e
ss,
”
S
c
i
e
n
t
i
f
i
c
Pro
g
r
a
m
m
i
n
g
,
v
o
l
.
2
0
2
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
1
7
5
7
8
8
8
.
[
2
0
]
T.
D
a
n
i
y
a
a
n
d
S
.
V
i
g
n
e
s
h
w
a
r
i
,
“
A
mal
g
a
m
a
t
i
o
n
o
f
r
i
c
e
p
l
a
n
t
d
i
sea
se
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
w
i
t
h
KNN
a
n
d
b
u
t
t
e
r
f
l
y
a
l
g
o
r
i
t
h
m,
”
I
n
n
o
v
a
t
i
o
n
s
i
n
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
ri
n
g
,
2
0
2
2
,
p
p
.
1
2
7
–
1
3
5
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
8987
-
1
_
1
4
.
[
2
1
]
S
.
M
.
H
a
ss
a
n
,
A
.
K
.
M
a
j
i
,
M
.
J
a
si
ń
sk
i
,
Z.
Le
o
n
o
w
i
c
z
,
a
n
d
E.
J
a
si
ń
s
k
a
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
l
a
n
t
-
l
e
a
f
d
i
s
e
a
s
e
s
u
s
i
n
g
C
N
N
a
n
d
t
r
a
n
sf
e
r
-
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
0
,
n
o
.
1
2
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
0
1
2
1
3
8
8
.
[
2
2
]
K
.
P
.
F
e
r
e
n
t
i
n
o
s
,
“
D
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
f
o
r
p
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
si
s,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ro
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
4
5
,
p
p
.
3
1
1
–
3
1
8
,
2
0
1
8
,
doi
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
1
8
.
0
1
.
0
0
9
.
[
2
3
]
K
.
C
.
K
a
ma
l
,
Z.
Y
i
n
,
M
.
W
u
,
a
n
d
Z.
W
u
,
“
D
e
p
t
h
w
i
s
e
se
p
a
r
a
b
l
e
c
o
n
v
o
l
u
t
i
o
n
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
p
l
a
n
t
d
i
se
a
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
r
o
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
6
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
1
9
.
1
0
4
9
4
8
.
[
2
4
]
R
.
A
s
h
t
a
g
i
,
S
.
M
.
Ja
y
b
h
a
y
e
,
S
.
M
o
h
i
t
e
,
V
.
M
u
s
a
l
e
,
S
.
C
h
i
n
c
h
ma
l
a
t
p
u
r
e
,
a
n
d
R
.
V
.
B
i
d
w
e
,
“
F
u
s
i
o
n
o
f
A
I
t
e
c
h
n
i
q
u
e
s:
a
h
y
b
r
i
d
a
p
p
r
o
a
c
h
f
o
r
p
r
e
c
i
s
e
p
l
a
n
t
l
e
a
f
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
S
y
st
e
m
s
,
v
o
l
.
2
0
,
n
o
.
1
s
,
p
p
.
8
5
0
–
8
6
1
,
2
0
2
4
,
d
o
i
:
1
0
.
5
2
7
8
3
/
j
e
s.
8
3
6
.
[
2
5
]
Ü
.
A
t
i
l
a
,
M
.
U
ç
a
r
,
K
.
A
k
y
o
l
,
a
n
d
E
.
U
ç
a
r
,
“
P
l
a
n
t
l
e
a
f
d
i
sea
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
e
f
f
i
c
i
e
n
t
n
e
t
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
Ec
o
l
o
g
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
6
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
o
i
n
f
.
2
0
2
0
.
1
0
1
1
8
2
.
[
2
6
]
K
.
P
.
P
a
n
i
g
r
a
h
i
,
H
.
D
a
s
,
A
.
K
.
S
a
h
o
o
,
a
n
d
S
.
C
.
M
o
h
a
r
a
n
a
,
“
M
a
i
z
e
l
e
a
f
d
i
se
a
s
e
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
A
d
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
1
1
9
,
p
p
.
6
5
9
–
6
6
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
15
-
2414
-
1_66.
[
2
7
]
J.
K
h
e
a
r
a
l
l
a
h
a
n
d
K
.
R
i
j
a
b
,
“
O
p
t
i
m
i
z
i
n
g
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
w
i
r
e
l
e
ss
se
n
so
r
n
e
t
w
o
r
k
b
a
se
d
o
n
s
o
f
t
w
a
r
e
d
e
f
i
n
e
d
n
e
t
w
o
r
k
a
n
d
g
a
u
ssi
a
n
f
i
l
t
e
r
,
”
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
J
o
u
r
n
a
l
,
v
o
l
.
4
0
,
n
o
.
2
,
p
p
.
3
7
9
–
3
8
5
,
2
0
2
2
,
d
o
i
:
1
0
.
3
0
6
8
4
/
e
t
j
.
v
4
0
i
2
.
2
2
2
1
.
[
2
8
]
S
.
L
i
,
H
.
C
h
e
n
,
M
.
W
a
n
g
,
A
.
A
.
H
e
i
d
a
r
i
,
a
n
d
S
.
M
i
r
j
a
l
i
l
i
,
“
S
l
i
me
mo
u
l
d
a
l
g
o
r
i
t
h
m:
a
n
e
w
met
h
o
d
f
o
r
st
o
c
h
a
st
i
c
o
p
t
i
mi
z
a
t
i
o
n
,
”
Fu
t
u
r
e
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
,
v
o
l
.
1
1
1
,
p
p
.
3
0
0
–
3
2
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
0
.
0
3
.
0
5
5
.
[
2
9
]
v
b
o
o
k
s
h
e
l
f
,
“
R
i
c
e
l
e
a
f
d
i
se
a
ses
d
a
t
a
se
t
,
”
K
a
g
g
l
e
,
A
c
c
e
ss
e
d
:
F
e
b
,
1
2
.
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
v
b
o
o
k
s
h
e
l
f
/
r
i
c
e
-
l
e
a
f
-
d
i
s
e
a
se
s
[
3
0
]
B
a
h
r
i
,
“
R
i
c
e
-
l
e
a
f,
”
K
a
g
g
l
e
,
A
c
c
e
sse
d
:
F
e
b
,
1
2
.
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
b
a
h
r
i
b
a
h
r
i
/
r
i
c
e
l
e
a
f
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Pra
m
e
e
th
a
P
a
i
h
o
l
d
s
a
m
a
ste
r’s
d
e
g
re
e
fro
m
B.
M
.
S
.
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
Ba
n
g
a
lo
re
a
n
d
a
b
a
c
h
e
l
o
r’s
d
e
g
re
e
fro
m
NMAM
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Ka
rk
a
la.
S
h
e
is
a
lso
p
u
rsu
i
n
g
h
e
r
re
se
a
rc
h
a
t
Da
y
a
n
a
n
d
a
S
a
g
a
r
Co
l
leg
e
o
f
En
g
i
n
e
e
rin
g
Ba
n
g
a
lo
re
wh
ich
is
a
ffil
iate
d
to
VTU
Be
lg
a
u
m
.
S
h
e
i
s
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
a
ss
istan
t
p
ro
fe
ss
o
r
in
t
h
e
D
e
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
B.
M
.
S
Co
ll
e
g
e
o
f
E
n
g
in
e
e
rin
g
,
Ba
n
g
a
l
o
re
.
S
h
e
h
a
s
o
v
e
r
1
2
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
S
h
e
h
a
s
a
b
o
u
t
1
0
p
u
b
li
c
a
ti
o
n
s
in
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
l.
He
r
a
re
a
o
f
re
se
a
rc
h
is
p
re
c
isio
n
a
g
ricu
lt
u
re
a
n
d
d
e
e
p
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
ra
m
e
e
th
a
p
a
i.
c
se
@b
m
sc
e
.
a
c
.
in
.
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
I
n
tellig
en
t p
la
n
t
d
is
ea
s
e
d
etec
tio
n
u
s
in
g
tw
in
a
tten
tio
n
o
p
tim
a
l c
o
n
vo
l
u
tio
n
a
l
n
eu
r
a
l
…
(
P
r
a
mee
th
a
P
a
i
)
765
Na
m
ith
a
S
.
J
.
h
o
ld
s
M
a
st
e
r
o
f
Tec
h
n
o
lo
g
y
i
n
C
o
m
p
u
ter
Ne
two
rk
i
n
g
a
n
d
En
g
i
n
e
e
rin
g
a
n
d
a
Ba
c
h
e
lo
r
o
f
E
n
g
i
n
e
e
rin
g
(B.
E.
)
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
S
h
e
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
ss
istan
t
p
r
o
fe
ss
o
r
in
th
e
d
e
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
,
B.
M
.
S
Co
ll
e
g
e
o
f
e
n
g
i
n
e
e
rin
g
,
Ba
n
g
a
lo
re
,
wit
h
o
v
e
r
1
2
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rien
c
e
,
h
e
r
fo
c
u
se
d
re
se
a
rc
h
e
d
field
s
a
re
c
o
m
p
u
ter
n
e
two
rk
s,
m
o
b
i
le
a
p
p
li
c
a
ti
o
n
d
e
v
e
lo
p
m
e
n
t
,
ima
g
e
p
r
o
c
e
ss
in
g
,
g
ra
p
h
t
h
e
o
r
y
,
a
c
ti
v
e
m
e
m
b
e
r
o
f
Th
e
In
stit
u
ti
o
n
o
f
En
g
in
e
e
rs
(In
d
ia)
(IE
I)
.
S
h
e
h
a
s
a
n
e
x
c
e
ll
e
n
t
k
n
o
wle
d
g
e
in
u
se
r
in
terfa
c
e
d
e
sig
n
tec
h
n
i
q
u
e
s
fo
r
a
g
o
o
d
we
b
d
e
sig
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
a
m
it
h
a
sj.cs
e
@b
m
sc
e
.
a
c
.
in
.
S
o
wm
y
a
T
.
h
o
l
d
s
a
m
a
ste
r’s
d
e
g
re
e
fro
m
Ba
n
g
a
lo
re
In
st
it
u
t
e
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
a
lo
re
a
n
d
a
b
a
c
h
e
lo
r’s
d
e
g
re
e
fro
m
Ba
n
g
a
lo
re
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
Ba
n
g
a
lo
re
.
S
h
e
is
a
lso
p
u
rsu
in
g
h
e
r
P
h
.
D.
a
t
BM
S
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
Ba
n
g
a
l
o
re
wh
ich
is
a
ffil
iate
d
with
VTU
Be
lg
a
u
m
.
He
r
re
se
a
r
c
h
in
tere
sts
a
re
c
y
b
e
r
se
c
u
rit
y
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
I
o
T.
S
h
e
h
a
s
in
d
u
stry
e
x
p
e
rien
c
e
o
f
3
y
e
a
rs
a
n
d
tea
c
h
in
g
e
x
p
e
rien
c
e
o
f
1
0
y
e
a
rs
a
n
d
is
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s
a
ss
istan
t
p
ro
fe
ss
o
r
in
th
e
De
p
a
rt
m
e
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
,
B.
M
.
S
.
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
.
S
h
e
c
a
n
b
e
c
o
n
ta
c
ted
a
t
e
m
a
il
:
so
wm
y
a
t.
c
se
@b
m
sc
e
.
a
c
.
in
.
Am
u
th
a
S
.
i
s
p
r
o
f
e
s
s
o
r
o
f
D
e
p
a
r
tm
e
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
,
D
a
y
a
n
a
n
d
a
S
a
g
a
r
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
B
e
n
g
a
l
u
r
u
.
S
h
e
o
b
t
a
i
n
e
d
h
e
r
P
h
.
D
.
d
e
g
r
e
e
f
r
o
m
V
T
U
U
n
i
v
e
r
s
i
t
y
.
S
h
e
h
a
s
m
o
r
e
t
h
a
n
2
6
y
e
a
r
s
o
f
t
e
a
c
h
i
n
g
e
x
p
e
r
i
e
n
c
e
.
S
h
e
h
a
s
p
u
b
l
i
s
h
e
d
i
n
2
7
j
o
u
r
n
a
l
s
a
n
d
c
o
n
f
e
r
e
n
c
e
s
.
He
r
r
e
s
e
a
r
c
h
in
t
e
r
e
s
t
s
i
n
c
l
u
d
e
d
a
t
a
a
n
a
l
y
t
i
c
s
,
c
o
m
p
u
t
e
r
v
i
s
i
o
n
,
a
n
d
c
l
o
u
d
c
o
m
p
u
t
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
a
m
u
t
h
a
-
c
s
@
d
a
y
a
n
a
n
d
a
s
a
g
a
r
.
e
d
u
.
Nisa
r
g
a
G
o
n
d
i
h
o
l
d
s
a
b
a
c
h
e
lo
r
d
e
g
re
e
fro
m
BM
S
C
o
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
,
Ba
n
g
a
lo
re
a
n
d
is
p
u
rsu
i
n
g
m
a
ste
r’s
d
e
g
re
e
fro
m
Ca
rn
e
g
ie
M
e
ll
o
n
Un
i
v
e
rsity
.
H
is
re
se
a
rc
h
in
tere
sts
a
re
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
a
n
d
in
f
o
rm
a
ti
o
n
se
c
u
r
it
y
.
He
h
a
s
o
n
e
p
u
b
li
c
a
ti
o
n
in
IEE
E
c
o
n
fe
re
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
isa
rg
a
g
o
n
d
i@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.