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
.
4
,
A
u
g
u
s
t 2
0
2
6
,
p
p
.
3
6
3
7
~
3
6
4
5
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
4
.
p
p
3
6
3
7
-
3
6
4
5
3637
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Co
ntext
-
a
wa
re
A
g
riBo
t
using
dual
intent
and en
tit
y
trans
former a
nd
hy
brid deep
learn
ing
mo
del
B
ino
d De
k
a
1
,
Ridip
Dev
Cho
ud
hu
ry
1
,
Ut
pa
l Ba
rm
a
n
2
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
,
K
r
i
sh
n
a
K
a
n
t
a
H
a
n
d
i
q
u
i
S
t
a
t
e
O
p
e
n
U
n
i
v
e
r
si
t
y
,
G
u
w
a
h
a
t
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
A
ssa
m Sk
i
l
l
U
n
i
v
e
r
s
i
t
y
,
M
a
n
g
a
l
d
o
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
Ma
y
3
1
,
2
0
2
5
R
ev
is
ed
Ma
y
1
5
,
2
0
2
6
Acc
ep
ted
J
u
n
1
9
,
2
0
2
6
Th
e
a
g
ricu
lt
u
re
se
c
to
r
h
a
s
g
o
n
e
th
ro
u
g
h
v
a
st
tec
h
n
o
l
o
g
ica
l
imp
ro
v
e
m
e
n
t,
lea
d
in
g
to
in
c
re
a
se
d
p
r
o
d
u
c
ti
v
i
ty
a
n
d
su
sta
i
n
a
b
il
i
ty
.
Th
is
re
se
a
rc
h
in
tro
d
u
c
e
s
Ag
riBo
t,
a
c
o
n
tex
t
-
a
wa
re
v
ir
tu
a
l
a
ss
istan
t
(VA
)
t
h
a
t
h
e
l
p
s
fa
rm
e
rs
in
r
ice
c
u
lt
iv
a
ti
o
n
a
n
d
i
d
e
n
ti
f
ies
d
ise
a
se
s
wh
il
e
p
ro
v
id
i
n
g
i
n
sta
n
t
su
g
g
e
stio
n
s
f
o
r
su
b
se
q
u
e
n
t
tas
k
.
Us
in
g
t
h
e
RAS
A
fra
m
e
wo
rk
,
A
g
riBo
t
h
a
s
b
e
e
n
d
e
sig
n
e
d
t
o
u
n
d
e
rsta
n
d
t
h
e
fa
rm
e
r'
s
q
u
e
ries
.
Du
a
l
in
ten
t
a
n
d
e
n
t
it
y
t
ra
n
sfo
rm
e
r
(DIET
)
c
las
sifier
h
a
s
b
e
e
n
u
se
d
fo
r
e
n
ti
ty
c
las
sifica
ti
o
n
,
a
c
h
ie
v
in
g
train
in
g
a
n
d
tes
ti
n
g
a
c
c
u
ra
c
y
o
f
u
p
t
o
9
8
%
a
n
d
9
7
%
,
re
sp
e
c
ti
v
e
l
y
.
Ad
d
it
i
o
n
a
ll
y
,
th
e
sy
ste
m
in
c
o
r
p
o
ra
tes
m
a
c
h
i
n
e
l
e
a
rn
in
g
(M
L)
m
o
d
e
ls
f
o
r
ric
e
d
ise
a
se
d
e
tec
ti
o
n
,
u
ti
l
izin
g
a
d
a
tas
e
t
o
f
4
,
6
2
4
ima
g
e
s
c
o
v
e
rin
g
t
h
re
e
m
a
jo
r
rice
d
ise
a
se
s:
b
a
c
teria
l
b
li
g
h
t,
b
ro
w
n
sp
o
t,
a
n
d
b
las
t
.
Am
o
n
g
t
h
e
tes
ted
m
o
d
e
ls
—
n
e
u
ra
l
n
e
tw
o
rk
(NN
),
ra
n
d
o
m
fo
re
st
(RF
),
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
a
n
d
n
a
iv
e
Ba
y
e
s
(NB)
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
u
p
t
o
9
9
.
9
%
,
d
e
m
o
n
stra
ti
n
g
e
x
c
e
ll
e
n
t
c
las
sifica
ti
o
n
p
e
rf
o
rm
a
n
c
e
.
Us
in
g
te
x
t
-
b
a
se
d
q
u
e
ry
h
a
n
d
li
n
g
wi
th
ima
g
e
-
b
a
se
d
d
ise
a
se
id
e
n
ti
fica
ti
o
n
a
n
d
i
n
sta
n
t
su
g
g
e
stio
n
m
a
k
e
s
it
a
m
o
re
ro
b
u
st su
p
p
o
rt
sy
ste
m
fo
r
th
e
fa
r
m
e
rs.
K
ey
w
o
r
d
s
:
Ag
r
iB
o
t
D
u
a
l
i
n
t
e
n
t
a
n
d
e
n
t
i
t
y
t
r
a
n
s
f
o
r
m
e
r
c
l
a
s
s
i
f
i
e
r
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
R
ice
d
is
ea
s
e
d
etec
tio
n
T
r
an
s
f
er
lear
n
i
n
g
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
:
B
in
o
d
Dek
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Kr
is
h
n
a
Kan
ta
Han
d
iq
u
i
State
Op
en
Un
iv
er
s
ity
Gu
wah
ati,
Ass
am
,
I
n
d
ia
E
m
ail:
b
in
o
d
d
e
k
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Ov
er
th
e
p
ast
f
ew
d
ec
ad
es,
th
e
ag
r
icu
ltu
r
al
in
d
u
s
tr
y
h
as
u
n
d
er
g
o
n
e
s
ig
n
if
ican
t
tec
h
n
o
lo
g
ical
ch
an
g
es,
e
v
en
in
u
r
b
a
n
en
v
i
r
o
n
m
en
ts
.
No
t
o
n
ly
d
o
es
t
h
e
im
p
lem
en
tatio
n
o
f
ar
tific
ia
l
in
tellig
en
ce
(
A
I
)
s
y
s
tem
s
an
d
th
e
u
s
e
o
f
a
d
v
an
ce
d
to
o
ls
r
ed
u
ce
th
e
lab
o
r
r
e
q
u
ir
em
en
ts
o
f
f
a
r
m
er
s
,
b
u
t
it
al
s
o
en
ab
les
th
e
m
to
ac
h
iev
e
th
e
ex
p
ec
ted
y
ield
le
v
els
[
1
]
.
Un
m
an
n
ed
air
v
eh
icle
s
ca
n
co
n
tin
u
o
u
s
ly
m
o
n
ito
r
cr
o
p
h
ea
lth
,
e
n
ab
lin
g
th
e
u
s
e
o
f
p
esti
cid
es
in
h
az
ar
d
o
u
s
ar
ea
s
an
d
allo
win
g
f
o
r
tar
g
eted
ap
p
licatio
n
with
h
ig
h
p
r
ec
is
io
n
.
Similar
ly
,
ag
r
ar
ian
s
ar
e
p
r
o
tecte
d
f
r
o
m
h
ea
lth
r
is
k
s
as r
o
b
o
tic
ap
p
a
r
atu
s
es u
n
d
er
tak
e
h
az
a
r
d
o
u
s
task
s
[
2
]
.
T
h
e
ad
v
e
n
t
o
f
m
o
b
ile
p
latf
o
r
m
s
with
an
ag
r
icu
ltu
r
al
o
r
ien
tatio
n
an
d
v
ir
t
u
al
ass
is
tan
t
(
VA)
tech
n
o
lo
g
ies
h
as
b
r
o
u
g
h
t
s
ig
n
if
ican
t
b
en
ef
its
to
f
ar
m
er
s
in
v
ar
io
u
s
f
ield
s
,
in
clu
d
i
n
g
m
eteo
r
o
lo
g
ical
f
o
r
ec
asti
n
g
,
p
h
y
to
p
at
h
o
lo
g
ica
l
d
iag
n
o
s
is
,
an
d
cr
o
p
m
an
ag
e
m
en
t.
Su
ch
in
v
e
n
tio
n
s
also
m
ak
e
f
ar
m
er
s
m
o
r
e
awa
r
e
o
f
s
u
p
p
ly
-
c
h
ain
d
y
n
a
m
ics
an
d
v
ar
io
u
s
g
o
v
e
r
n
m
e
n
t
p
r
o
g
r
am
s
,
m
o
s
t
o
f
ten
tr
a
n
s
lated
in
to
n
ativ
e
lan
g
u
ag
es
[
3
]
–
[
6
]
.
VA
s
,
s
u
ch
as
C
h
atGPT
,
Alex
a,
Siri,
an
d
Gem
in
i,
h
av
e
b
ec
o
m
e
ess
en
tial
p
ar
ts
o
f
d
aily
o
p
er
atio
n
s
,
ac
ce
ler
atin
g
r
o
u
ti
n
e
p
r
o
ce
s
s
es
an
d
p
r
o
v
id
in
g
i
n
f
o
r
m
atio
n
q
u
ick
l
y
,
wh
ich
in
cr
ea
s
es
p
r
o
d
u
ctiv
ity
in
g
en
er
al.
I
n
th
e
ag
r
icu
ltu
r
al
d
o
m
ain
,
AI
,
in
clu
d
in
g
VA
s
an
d
co
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs),
h
as
b
ee
n
wid
ely
ap
p
lied
to
s
u
p
p
o
r
t
f
ar
m
er
s
.
Ho
wev
er
,
a
g
ap
r
e
m
ain
s
in
d
ev
elo
p
in
g
u
s
er
-
f
r
i
en
d
ly
s
y
s
tem
s
th
at
s
ea
m
less
ly
in
teg
r
ate
tex
tu
al
a
n
d
im
ag
e
-
b
ased
d
ata
f
o
r
p
lan
t
d
is
ea
s
e
d
etec
tio
n
th
r
o
u
g
h
C
NNs
in
to
a
u
n
if
ied
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
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
6
3
7
-
3
6
4
5
3638
p
latf
o
r
m
with
r
ea
s
o
n
a
b
le
ac
c
u
r
ac
y
.
Su
ch
a
s
y
s
tem
s
h
o
u
l
d
p
r
io
r
itize
ac
ce
s
s
ib
ilit
y
f
o
r
f
a
r
m
er
s
an
d
in
tu
itiv
e
in
ter
f
ac
es
to
b
r
id
g
e
th
e
d
ig
ital
d
iv
id
e
an
d
s
im
p
lify
co
m
p
le
x
task
s
.
T
h
e
r
esear
ch
u
s
in
g
Ag
r
iB
o
t
f
ills
th
is
g
ap
with
g
r
ea
t a
cc
u
r
ac
y
an
d
an
ea
s
y
-
to
-
u
s
e
u
n
if
ied
in
ter
f
ac
e.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
T
h
e
latest
d
ev
elo
p
m
en
ts
in
th
e
f
ield
o
f
d
ee
p
-
lea
r
n
in
g
m
eth
o
d
s
h
av
e
p
r
o
d
u
ce
d
s
ig
n
if
ican
t
ac
h
iev
em
en
ts
in
ag
r
icu
ltu
r
e
-
b
ased
r
esear
ch
an
d
im
p
lem
e
n
tatio
n
.
Su
ch
ap
p
licatio
n
s
a
s
u
n
m
an
n
ed
ae
r
ial
v
eh
icles,
th
e
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
,
n
o
t
o
n
ly
allo
w
d
etec
t
in
g
an
d
m
itig
atin
g
cr
o
p
d
is
ea
s
es
ea
r
ly
,
b
u
t
also
s
u
p
p
o
r
t
a
clo
s
er
i
n
ter
ac
tio
n
b
etwe
en
f
ar
m
er
s
an
d
em
er
g
i
n
g
tech
n
o
lo
g
ies
[
7
]
,
[
8
]
.
Ko
o
p
m
an
et
a
l.
[
9
]
in
tr
o
d
u
ce
d
Ag
Ask
,
a
co
n
v
er
s
atio
n
al
ag
r
icu
ltu
r
al
in
f
o
r
m
ati
o
n
r
etr
ie
v
al
s
y
s
tem
d
esig
n
ed
to
an
s
wer
f
ar
m
e
r
s
’
n
atu
r
al
lan
g
u
a
g
e
q
u
er
ies
b
y
e
x
tr
ac
tin
g
r
elev
an
t
in
f
o
r
m
atio
n
f
r
o
m
s
cien
tific
d
o
cu
m
en
ts
u
s
in
g
ad
v
an
ce
d
n
eu
r
al
r
an
k
in
g
tech
n
iq
u
es.
T
h
e
a
u
th
o
r
s
s
h
o
w
th
at
th
e
ass
i
s
tan
t
is
ca
p
ab
le
o
f
an
s
wer
in
g
q
u
esti
o
n
s
ab
o
u
t
f
er
tili
ze
r
s
,
p
esti
cid
es
,
an
d
o
p
tim
al
ir
r
i
g
atio
n
r
eg
im
es
to
a
n
ac
ce
p
tab
le
d
eg
r
ee
,
r
ea
ch
in
g
8
6
%
wh
en
u
s
in
g
Sen
2
Vec
an
d
W
o
r
d
2
Vec
em
b
ed
d
in
g
s
.
Similar
to
th
is
,
An
ek
ar
et
a
l.
[
1
0
]
d
esig
n
ed
a
r
eg
io
n
al
-
lan
g
u
ag
e
VA
th
at
p
r
o
d
u
ce
s
s
p
ee
ch
an
d
p
r
o
v
id
es
cr
o
p
-
a
n
d
f
er
tili
ze
r
-
r
elate
d
s
u
g
g
esti
o
n
s
b
ased
o
n
t
h
e
wea
th
er
an
d
s
o
il
p
r
o
p
er
ties
.
T
h
eir
ap
p
licatio
n
b
r
i
n
g
s
an
ac
c
u
r
ac
y
o
f
a
m
a
x
im
u
m
o
f
7
1
%.
T
em
n
ir
an
r
at
et
a
l.
[
1
1
]
f
o
cu
s
ed
o
n
o
p
tim
izin
g
s
er
v
ices
p
r
o
v
id
ed
to
r
ice
f
a
r
m
er
s
an
d
a
g
r
o
n
o
m
is
ts
.
T
h
e
r
esear
ch
er
s
ca
m
e
u
p
with
a
d
ed
icate
d
c
h
atb
o
t
th
at
ca
n
d
etec
t
r
ice
d
is
ea
s
es
an
d
it
is
ab
le
to
d
o
th
is
b
y
u
s
in
g
an
o
b
ject
-
d
etec
tio
n
s
y
s
t
em
to
d
if
f
er
en
tiate
b
etwe
en
f
i
v
e
s
ig
n
if
ican
t
d
is
ea
s
e
p
h
en
o
ty
p
es
n
am
ely
,
b
last
,
b
lig
h
t,
b
r
o
w
n
s
p
o
t,
n
ar
r
o
w
-
b
r
o
wn
s
p
o
t
,
an
d
s
tr
ip
e.
T
h
e
a
v
er
ag
e
tr
u
e
-
p
o
s
itiv
e
r
ate
in
cr
ea
s
ed
b
y
9
1
.
1
to
9
5
.
6
%.
C
o
m
p
ar
is
o
n
with
R
etin
aNe
t,
Ma
s
k
r
eg
io
n
-
b
ased
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
R
-
C
NN
)
,
an
d
Fas
ter
R
-
C
NN
also
co
n
f
ir
m
e
d
th
at
th
e
YOL
Ov
3
s
o
lv
er
h
as
b
etter
p
e
r
f
o
r
m
an
ce
.
Nay
a
k
et
a
l.
[
1
2
]
p
r
esen
ted
a
r
esear
c
h
p
a
p
er
th
at
d
ev
elo
p
e
d
a
VA
to
ass
is
t
f
ar
m
er
s
.
T
h
is
VA
p
r
o
v
id
e
d
k
n
o
wled
g
e
o
n
v
ar
i
o
u
s
ag
r
icu
l
tu
r
al
p
r
ac
tices,
s
o
il
ch
ar
ac
ter
is
tics
,
an
d
m
o
d
e
r
n
t
o
o
ls
u
s
ed
in
ag
r
icu
ltu
r
e.
T
h
e
r
e
s
ea
r
ch
er
s
u
s
ed
t
h
e
L
e
v
en
s
h
tie
n
d
is
tan
ce
f
o
r
m
u
la
,
th
e
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
ap
p
r
o
ac
h
,
to
ca
lcu
late
s
en
ten
ce
s
im
ilar
ity
.
T
h
e
c
h
atb
o
t
au
to
m
atica
lly
r
ed
ir
ec
ted
a
n
y
u
n
an
s
wer
ed
q
u
esti
o
n
s
th
r
o
u
g
h
em
ail
to
th
e
ag
r
icu
ltu
r
al
ex
p
e
r
ts
o
r
a
d
m
i
n
is
tr
ato
r
s
.
T
h
is
VA
r
ea
ch
ed
a
n
ac
c
u
r
ac
y
lev
el
o
f
9
6
%.
Mo
r
e
o
v
er
,
th
is
s
tu
d
y
test
ed
a
d
e
ep
c
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
D
C
NN)
b
ased
o
n
I
n
ce
p
tio
n
R
esNetV2
with
tr
an
s
f
er
lear
n
in
g
f
o
r
r
ice
d
is
ea
s
e
class
if
icatio
n
.
Mo
m
ay
a
et
a
l.
[
1
3
]
cr
ea
ted
th
e
ch
atb
o
t
Kr
u
s
h
i,
wh
ich
u
s
es
th
e
W
h
atsAp
p
m
ess
ag
in
g
n
etwo
r
k
'
s
NL
P
tech
n
o
lo
g
y
to
d
eliv
er
f
ar
m
er
s
ag
r
icu
ltu
r
al
in
f
o
r
m
atio
n
,
wea
th
er
f
o
r
ec
asts
,
an
d
g
o
v
er
n
m
en
t
p
r
o
g
r
am
s
.
T
h
is
s
o
f
twar
e
aim
s
to
s
av
e
ag
r
icu
ltu
r
al
o
p
er
atio
n
s
ex
p
e
n
s
es
an
d
b
o
o
s
t
cr
o
p
o
u
tp
u
t
am
o
n
g
i
n
d
iv
id
u
al
f
a
r
m
er
s
.
I
t
h
ad
a
n
o
u
ts
tan
d
in
g
o
v
er
al
l
ac
cu
r
ac
y
o
f
9
6
.
1
%
an
d
r
eso
lv
ed
7
0
%
o
f
th
e
q
u
esti
o
n
s
ask
ed
th
r
o
u
g
h
th
e
h
elp
lin
e
n
u
m
b
e
r
o
f
Kis
an
C
all
C
en
ter
(
K
C
C
)
,
wh
ich
we
n
t
b
ey
o
n
d
wh
at
co
n
tact
ce
n
ter
s
er
v
ice
co
u
ld
d
o
p
r
esen
tly
.
Kr
u
s
h
i,
cr
ea
ted
u
s
i
n
g
R
ASA
X,
h
elp
ed
u
n
d
er
r
e
p
r
esen
ted
g
r
o
u
p
s
b
y
ad
d
r
ess
in
g
is
s
u
es
r
eg
ar
d
in
g
ag
r
icu
ltu
r
e
an
d
h
o
r
ticu
ltu
r
e,
an
im
al
h
u
s
b
an
d
r
y
,
f
is
h
er
ies
an
d
m
ar
k
et
p
r
ices.
Fam
ilies
wh
o
wis
h
ed
to
k
n
o
w
m
o
r
e
ab
o
u
t
th
ese
s
p
ec
if
ic
ar
ea
s
wer
e
p
r
o
v
id
ed
with
th
is
ch
at
b
o
t
f
o
r
k
n
o
wled
g
e
ac
q
u
is
itio
n
an
d
f
u
r
th
e
r
s
tu
d
y
.
J
ain
et
a
l.
[
1
4
]
in
v
esti
g
ated
th
e
class
if
icat
io
n
o
f
f
ar
m
er
s
b
ased
o
n
th
eir
liter
ac
y
lev
els,
ca
teg
o
r
izin
g
th
em
as
lo
w,
s
em
i,
an
d
h
ig
h
liter
ac
y
u
s
er
s
.
Fo
r
th
o
s
e
with
lo
w
liter
ac
y
,
th
e
u
s
er
in
te
r
f
ac
e
is
d
es
ig
n
ed
to
p
r
i
o
r
itize
v
is
u
als o
v
er
tex
t.
Ad
d
itio
n
ally
,
th
e
s
tu
d
y
in
co
r
p
o
r
ates a
u
d
io
an
d
au
d
io
-
p
lu
s
-
tex
t
-
b
ased
VA
s
.
T
h
e
r
esu
lts
s
h
o
w
th
at
s
y
s
tem
s
f
ea
tu
r
in
g
m
o
r
e
v
is
u
al
elem
en
ts
ar
e
ea
s
ier
to
u
n
d
er
s
tan
d
an
d
m
o
r
e
u
s
er
-
f
r
ie
n
d
ly
f
o
r
th
is
tar
g
et
g
r
o
u
p
.
I
B
M
W
atso
n
is
em
p
lo
y
ed
to
an
aly
ze
q
u
er
ies th
at
a
r
e
s
u
b
m
itted
th
r
o
u
g
h
th
e
ch
at
b
o
t.
Usi
p
et
a
l.
[
1
5
]
f
o
cu
s
ed
o
n
d
ev
elo
p
in
g
a
cu
s
to
m
ized
m
o
b
i
le
ch
atb
o
t
d
esig
n
ed
f
o
r
cr
o
p
f
ar
m
er
s
in
Uy
o
.
C
h
atb
o
t
tr
ain
in
g
d
ata
was
co
llected
f
r
o
m
th
e
Ak
w
a
I
b
o
m
State
Min
is
tr
y
o
f
Ag
r
icu
ltu
r
e
an
d
lo
ca
l
f
ar
m
er
s
u
s
in
g
q
u
esti
o
n
n
air
es,
an
d
in
ter
v
iews.
T
o
r
e
p
r
esen
t
th
e
d
ataset
ef
f
ec
tiv
ely
,
th
e
c
h
atb
o
t
em
p
l
o
y
ed
an
o
n
to
lo
g
y
-
b
ased
ap
p
r
o
ac
h
em
p
lo
y
in
g
a
h
y
b
r
id
m
ac
h
in
e
lear
n
in
g
(
ML
)
m
eth
o
d
co
n
s
is
tin
g
o
f
wo
r
d
p
er
m
u
tatio
n
co
m
b
in
ed
with
th
e
J
ac
q
u
ar
d
Similar
ity
alg
o
r
ith
m
.
C
o
n
s
eq
u
en
tly
,
it
o
p
er
ates
lik
e
a
k
n
o
wled
g
e
ce
n
ter
wh
er
e
f
ar
m
er
s
ca
n
g
et
h
elp
f
u
l
r
esp
o
n
s
es,
in
f
o
r
m
atio
n
,
an
d
p
er
s
o
n
alize
d
s
u
g
g
esti
o
n
s
r
eg
ar
d
in
g
th
eir
u
n
iq
u
e
f
ar
m
in
g
q
u
esti
o
n
s
.
C
h
an
d
o
lik
ar
et
a
l.
[
1
6
]
d
em
o
n
s
tr
ate
th
at
Ag
r
o
B
o
t
s
u
cc
ess
f
u
lly
p
r
o
v
id
es
r
ea
l
-
tim
e
r
esp
o
n
s
es
to
f
ar
m
er
q
u
er
ies
r
elate
d
to
c
r
o
p
co
n
d
itio
n
s
,
wea
th
e
r
f
o
r
ec
asts
,
s
o
il
r
eq
u
ir
em
en
ts
,
f
e
r
tili
ze
r
s
,
an
d
m
ar
k
et
p
r
ices.
I
t h
elp
s
f
ar
m
er
s
p
lan
th
eir
ac
ti
v
ities
b
y
p
r
ed
ictin
g
f
u
tu
r
e
cr
o
p
p
r
ices.
I
n
2
0
1
8
,
a
f
e
w
r
e
s
e
a
r
ch
er
s
d
e
v
e
lo
p
e
d
Ag
r
o
n
o
m
o
B
o
t
,
a
c
h
a
t
b
o
t
cr
e
a
t
ed
to
o
b
t
a
in
an
d
d
i
s
p
l
a
y
i
n
f
o
r
m
a
t
io
n
f
r
o
m
a
w
ir
e
l
e
s
s
s
e
n
s
o
r
n
e
t
wo
r
k
.
T
h
e
b
o
t
c
an
in
t
e
r
a
c
t
w
i
t
h
s
e
n
s
o
r
d
a
t
a
an
d
g
e
n
er
a
t
e
r
e
p
o
r
t
s
i
n
v
a
r
io
u
s
f
o
r
m
a
t
s
a
s
th
e
u
s
er
r
eq
u
i
r
e
s
.
T
h
i
s
c
h
a
tb
o
t
u
s
e
d
T
e
le
g
r
am
ap
p
l
ic
a
t
i
o
n
p
r
o
g
r
a
m
m
in
g
i
n
t
er
f
ac
e
(
A
P
I
)
t
o
co
m
m
u
n
i
c
a
t
e
w
i
t
h
u
s
e
r
s
a
n
d
c
ap
t
u
r
e
in
f
o
r
m
a
t
i
o
n
f
r
o
m
e
K
o
f
ie
l
d
s
e
n
s
o
r
s
.
T
h
i
s
c
h
a
t
b
o
t
p
l
a
t
f
o
r
m
e
m
b
r
a
c
e
d
I
B
M
W
a
t
s
o
n
co
g
n
it
i
o
n
s
er
v
i
ce
s
t
o
e
n
h
an
c
e
u
s
e
r
e
x
p
er
i
e
n
c
e
th
r
o
u
g
h
n
a
tu
r
a
l
l
an
g
u
a
g
e
i
n
t
er
a
c
t
io
n
a
n
d
id
en
t
i
f
y
u
s
er
i
n
t
en
t
[
1
7
]
.
A
r
o
r
a
e
t
a
l
.
[
1
8
]
wo
r
k
o
n
A
g
r
i
B
o
t
,
wh
i
c
h
u
s
e
s
m
u
l
t
i
l
a
y
e
r
ed
l
o
n
g
s
h
o
r
t
-
t
er
m
m
e
m
o
r
y
(
L
S
T
M
)
to
a
n
s
w
er
f
ar
m
er
s
'
q
u
er
i
e
s
an
d
u
s
es
C
N
N
f
o
r
d
i
s
e
a
s
e
d
e
t
e
c
t
io
n
.
A
f
t
er
tr
a
i
n
in
g
,
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
C
o
n
text
-
a
w
a
r
e
A
g
r
iBo
t u
s
in
g
d
u
a
l in
ten
t
a
n
d
en
tity tra
n
s
fo
r
mer a
n
d
h
yb
r
id
d
ee
p
lea
r
n
in
g
…
(
B
in
o
d
Dek
a
)
3639
9
8
%
a
c
cu
r
a
cy
w
a
s
ac
h
i
ev
e
d
f
o
r
co
n
v
e
r
s
a
t
io
n
a
l
s
y
s
t
em
m
o
d
u
l
e
o
n
t
r
a
in
i
n
g
d
a
t
a
an
d
9
4
%
f
o
r
d
i
s
ea
s
e
d
e
t
e
c
t
io
n
m
o
d
u
l
e
o
n
t
e
s
t
d
a
t
a
.
T
h
e
Fo
u
r
C
r
o
p
Net
f
r
a
m
ewo
r
k
is
a
n
ew
d
ee
p
-
lear
n
in
g
m
o
d
el
th
at
ca
n
d
etec
t
m
u
lti
-
cr
o
p
p
la
n
t
d
is
ea
s
es
in
co
tto
n
,
g
r
ap
e,
s
o
y
b
ea
n
,
a
n
d
co
r
n
,
as
p
r
o
p
o
s
ed
b
y
Kh
an
d
ag
ale
et
a
l.
[
1
9
]
.
T
h
e
a
r
ch
it
ec
tu
r
e
u
s
es
r
esid
u
al
b
lo
ck
s
to
im
p
r
o
v
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
atten
tio
n
to
em
p
h
a
s
ize
th
e
d
is
ea
s
ed
ar
ea
s
,
an
d
co
m
p
ac
t
lay
er
s
t
o
m
ain
tain
th
e
co
m
p
u
tatio
n
al
co
s
t.
Fo
u
r
C
r
o
p
Net
ac
h
iev
es
ex
ce
llen
t
r
esu
lts
with
m
u
lti
-
cr
o
p
d
ata
with
a
m
ax
im
u
m
ac
cu
r
ac
y
o
f
9
9
.
7
%
with
g
r
a
p
e
a
n
d
9
9
.
5
%
with
c
o
r
n
.
Alh
ass
an
et
a
l.
[
2
0
]
cr
ea
t
e
a
n
ew
ML
-
b
ased
Ar
ab
ic
ch
atb
o
t
to
r
eso
lv
e
tech
n
ical
p
r
o
b
lem
s
an
d
d
etec
t
p
r
o
b
lem
s
b
y
tr
o
u
b
lesh
o
o
tin
g
th
r
o
u
g
h
th
e
cr
ea
tio
n
o
f
a
ch
atb
o
t.
T
h
e
d
atasets
ar
e
c
o
m
p
iled
u
s
in
g
web
ex
tr
ac
tio
n
an
d
th
is
is
s
u
p
p
lem
e
n
ted
with
an
o
p
en
-
s
o
u
r
ce
co
r
p
u
s
ca
lled
MA
DR
A
PR
OJEC
T
th
at
s
p
ec
ializes
in
t
h
e
Sau
d
i
d
ialec
t
,
h
en
ce
m
a
k
in
g
it
lin
g
u
is
tically
r
elev
an
t a
n
d
r
ich
.
As
a
h
y
b
r
id
AI
m
o
d
el,
Hasan
et
a
l.
[
2
1
]
u
s
e
a
DC
NN
w
ith
a
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
i
n
e
(
SVM)
to
id
en
tify
a
n
d
d
if
f
er
e
n
tiate
n
in
e
m
ajo
r
d
is
ea
s
es
in
r
ice
p
lan
ts
.
W
ith
th
is
m
eth
o
d
,
th
e
p
r
ed
icti
o
n
ac
c
u
r
ac
y
o
n
th
e
test
s
et
is
f
o
u
n
d
t
o
b
e
h
ig
h
,
at
9
7
.
5
%
,
wh
ich
p
r
o
v
es
th
e
ef
f
ec
tiv
en
ess
o
f
co
m
b
in
in
g
d
ee
p
lear
n
in
g
o
f
r
ep
r
esen
tatio
n
s
with
class
ical
ML
m
eth
o
d
s
.
Dan
iy
a
an
d
V
ig
n
esh
war
i
[
2
2
]
in
t
r
o
d
u
ce
a
d
ee
p
lear
n
in
g
-
b
ased
s
ch
em
e
o
f
d
etec
tin
g
r
ice
p
lan
t
d
is
ea
s
es,
wh
ich
u
tili
ze
s
s
tatis
tical,
tex
tu
r
al
(
L
OOP)
,
a
n
d
C
NN
ch
ar
ac
ter
is
tics
.
T
h
e
ap
p
r
o
ac
h
will
in
v
o
lv
e
im
ag
e
p
r
e
-
p
r
o
ce
s
s
in
g
an
d
s
eg
m
e
n
tatio
n
u
s
in
g
Seg
Net,
an
d
cla
s
s
if
icatio
n
u
s
in
g
a
d
ee
p
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
(
D
R
NN)
th
at
h
as
b
ee
n
tr
ain
ed
u
s
in
g
R
id
eSp
id
er
wate
r
wav
e
(
R
SW
)
alg
o
r
ith
m
.
T
h
e
en
d
p
e
r
f
o
r
m
an
ce
m
ea
s
u
r
e
s
ar
e
9
0
.
5
%
ac
cu
r
ac
y
,
8
4
.
9
%
s
en
s
itiv
ity
,
an
d
9
5
.
2
%
s
p
ec
if
i
city
,
wh
ich
s
tr
ess
es
th
e
ef
f
icien
cy
o
f
th
e
s
u
g
g
ested
p
ip
elin
e.
3.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
r
esear
ch
in
te
g
r
ated
th
e
R
ASA
f
r
am
ewo
r
k
as
an
o
p
en
-
s
o
u
r
ce
to
o
l
th
at
o
p
tim
izes
f
lex
ib
ilit
y
f
o
r
c
u
s
to
m
izatio
n
s
,
ad
ap
tiv
en
ess
,
an
d
ea
s
e
o
f
d
a
ta
p
r
o
ce
s
s
in
g
u
s
in
g
n
atu
r
al
lan
g
u
ag
e
.
R
ASA
is
co
m
p
o
s
ed
o
f
two
c
o
r
e
c
o
m
p
o
n
en
ts
:
n
atu
r
al
lan
g
u
ag
e
u
n
d
er
s
tan
d
in
g
(
NL
U)
a
n
d
R
ASA
c
o
r
e.
T
h
is
f
r
am
ewo
r
k
b
eg
in
s
with
th
e
s
tep
o
f
u
s
er
to
k
en
izatio
n
,
wh
ich
clu
s
ter
s
u
s
er
u
tter
an
ce
s
in
to
d
is
cr
ete
u
s
er
to
k
en
s
.
T
h
is
is
f
o
llo
wed
b
y
t
h
e
u
s
er
in
f
o
r
m
a
tio
n
tex
t
f
r
ag
m
e
n
tatio
n
,
r
ef
er
r
ed
to
as
en
tity
ex
tr
ac
tio
n
.
T
h
e
f
r
a
m
ewo
r
k
th
e
n
co
n
v
er
ts
th
e
to
k
en
s
an
d
e
x
tr
ac
ted
en
titi
es
in
to
n
u
m
er
ic
v
alu
es.
T
h
is
tr
an
s
f
o
r
m
atio
n
is
ter
m
ed
as
th
e
f
ea
tu
r
izatio
n
o
f
th
e
tex
t.
Fin
a
lly
,
b
ased
o
n
th
e
n
u
m
er
ical
f
ea
tu
r
es
o
f
th
e
u
s
er
tex
t,
th
e
f
r
am
ewo
r
k
class
if
ies
u
s
er
in
ten
t,
d
ec
o
d
in
g
th
e
d
ata
u
s
in
g
th
e
R
ASA
NL
U
co
m
p
o
n
en
t.
C
o
n
s
id
er
in
g
th
e
ab
o
v
e
s
tep
s
,
as
a
VA
,
Ag
r
iB
o
t
is
em
p
o
w
er
ed
to
u
n
d
er
s
tan
d
t
h
e
u
s
er
s
’
tex
t
an
d
,
wh
en
n
ec
ess
ar
y
,
p
r
o
v
id
e
u
s
er
co
n
tex
tu
al
r
esp
o
n
s
es.
Fig
u
r
e
1
illu
s
tr
ates
an
d
ca
p
tu
r
es
t
h
e
o
v
er
all
s
y
s
tem
wo
r
k
f
lo
w
an
d
ar
ch
itectu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
.
T
h
is
f
ig
u
r
e
d
escr
ib
es th
e
en
tire
p
r
o
ce
s
s
in
g
f
r
am
ewo
r
k
,
f
r
o
m
th
e
in
p
u
t
o
f
a
u
s
er
q
u
er
y
,
th
r
o
u
g
h
th
e
R
ASA
f
r
am
ewo
r
k
o
f
NL
P
,
an
d
th
e
ex
t
r
ac
tio
n
o
f
u
s
er
in
ten
ts
an
d
en
titi
es
f
o
r
th
e
g
en
er
atio
n
o
f
th
e
f
in
al
s
y
s
tem
r
esp
o
n
s
e.
G
o
o
g
le
T
r
a
n
s
lato
r
an
d
th
e
Op
e
n
W
ea
th
er
API
ar
e
u
tili
ze
d
to
s
u
p
p
o
r
t
r
e
g
io
n
al
la
n
g
u
ag
es
an
d
r
etr
iev
e
wea
th
er
co
n
d
itio
n
s
b
ased
o
n
th
e
l
o
ca
tio
n
p
r
o
v
id
ed
b
y
th
e
f
ar
m
er
to
a
n
s
wer
th
e
q
u
er
ies.
Fig
u
r
e
1
.
Ov
e
r
all
p
r
o
ce
s
s
f
o
r
d
ev
elo
p
in
g
th
e
Ag
r
iB
o
t f
o
r
r
ice
f
ar
m
in
g
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
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
6
3
7
-
3
6
4
5
3640
3
.
1
.
Da
t
a
s
et
us
ed
T
h
e
p
r
o
p
o
s
ed
Ag
r
iB
o
t
was
d
e
v
elo
p
ed
u
s
in
g
th
e
d
ata
c
o
llected
f
r
o
m
th
e
KC
C
Gu
wah
ati
c
all
ce
n
t
er
,
wh
ich
p
r
o
v
id
ed
v
alu
ab
le
c
o
n
tex
t
f
o
r
d
esig
n
in
g
th
e
c
o
n
v
er
s
atio
n
f
lo
w.
I
n
ad
d
iti
o
n
to
tex
t
u
al
d
ata
co
llected
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
,
in
clu
d
in
g
KC
C
Gu
wah
ati,
a
d
ata
s
et
f
o
r
r
ice
d
is
ea
s
e,
n
am
ely
b
ac
ter
ial
b
lig
h
t,
b
r
o
wn
s
p
o
t
,
an
d
b
last
,
h
ad
also
b
ee
n
co
llected
f
r
o
m
th
e
f
iel
d
u
s
in
g
m
o
b
ile
d
ev
ices
with
v
ar
y
in
g
illu
m
in
atio
n
an
d
class
if
ied
with
th
e
h
el
p
o
f
ex
p
er
ts
to
tr
ain
th
e
s
am
e
in
an
ML
m
o
d
el.
Fig
u
r
e
2
p
r
es
en
ts
r
ep
r
esen
tativ
e
s
am
p
le
im
ag
es
f
r
o
m
th
e
r
ice
d
is
ea
s
e
im
ag
e
d
ata
s
et
u
s
ed
in
t
h
is
s
tu
d
y
.
T
h
e
f
ig
u
r
e
in
clu
d
es
v
is
u
al
ex
am
p
les
o
f
th
r
ee
m
ajo
r
r
ice
d
is
ea
s
es,
n
a
m
ely
b
ac
ter
ial
b
lig
h
t
(
1
,
5
8
4
im
ag
es)
as
s
h
o
wn
in
Fig
u
r
e
2
(
a)
,
b
r
o
wn
s
p
o
t
(
1
,
6
0
0
im
ag
es)
as
s
h
o
wn
in
Fig
u
r
e
2
(
b
)
,
a
n
d
b
last
(
1
,
4
4
0
im
ag
es)
as
s
h
o
wn
i
n
Fig
u
r
e
2
(
c)
,
wh
ich
wer
e
co
llected
an
d
v
alid
ated
with
ex
p
er
t
ass
is
tan
ce
.
T
h
ese
im
ag
es
d
em
o
n
s
tr
ate
th
e
v
is
u
al
v
ar
iatio
n
s
in
co
lo
r
,
tex
tu
r
e,
an
d
lesi
o
n
p
atter
n
s
th
a
t a
r
e
cr
itical
f
o
r
e
f
f
ec
tiv
e
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
ac
c
u
r
ate
d
is
e
ase
class
if
icat
io
n
.
F
ield
sa
m
p
le A
F
ield
sa
m
p
le B
F
ield
sa
m
p
le A
F
ield
sa
m
p
le B
(
a)
(
b
)
F
ield
sa
m
p
le A
F
ield
sa
m
p
le B
(
c)
Fig
u
r
e
2
.
T
h
e
r
ice
d
is
ea
s
e
im
a
g
e
d
ataset
u
s
ed
f
o
r
tr
ain
in
g
an
d
ev
alu
atio
n
o
f
th
e
p
r
o
p
o
s
ed
Ag
r
iB
o
t sy
s
tem
:
(
a)
b
ac
ter
ial
b
lig
h
t
,
(
b
)
b
r
o
wn
s
p
o
t
,
an
d
(
c
)
b
last
T
h
e
r
esear
ch
co
n
d
u
cted
al
o
n
g
s
id
e
th
e
d
ev
el
o
p
m
en
t
o
f
th
e
A
g
r
iB
o
t
also
en
ab
led
th
e
id
e
n
tif
icatio
n
o
f
r
ice
leaf
d
is
ea
s
es
b
ased
o
n
s
y
m
p
to
m
s
d
escr
ib
ed
i
n
th
e
q
u
er
y
.
Ad
d
itio
n
ally
,
th
e
Ag
r
iB
o
t
p
r
o
v
id
e
d
n
ec
ess
ar
y
s
u
g
g
esti
o
n
s
f
o
r
m
an
ag
in
g
th
e
cr
o
p
s
.
All
th
e
in
ter
ac
tio
n
s
w
er
e
s
to
r
ed
in
a
MY
SQL
d
atab
ase
u
s
in
g
a
tr
ac
k
er
s
to
r
e
to
m
o
n
ito
r
an
d
t
r
ac
k
th
e
co
n
v
er
s
atio
n
s
b
etwe
en
t
h
e
f
ar
m
er
s
an
d
th
e
c
h
atb
o
t.
T
wo
d
a
tasets
wer
e
u
s
ed
in
th
is
r
esear
ch
:
i
)
tex
tu
al
d
ata
f
o
r
Ag
r
iB
o
t
to
h
an
d
le
f
ar
m
e
r
s
'
q
u
er
ies,
an
d
ii
)
im
a
g
es
o
f
r
i
ce
leav
es
to
d
etec
t
d
is
ea
s
e.
I
n
th
e
f
ir
s
t
ca
s
e,
th
e
d
u
al
in
ten
t
an
d
en
tity
tr
a
n
s
f
o
r
m
er
(
DI
E
T
)
c
lass
if
ier
was
u
s
ed
to
ac
cu
r
ately
id
en
tify
in
ten
t
a
n
d
e
n
tity
,
i.
e.
,
f
o
r
r
esp
o
n
s
e
s
elec
tio
n
s
.
W
ith
an
i
m
ag
e
d
ataset,
r
an
d
o
m
f
o
r
est
(
R
F),
SVM,
n
aiv
e
B
ay
es
(
NB
)
,
an
d
n
eu
r
al
n
etwo
r
k
s
(
NNs)
wer
e
u
s
ed
to
id
en
tify
th
e
ty
p
e
o
f
r
ice
d
is
ea
s
es.
Af
ter
ev
alu
atin
g
th
e
m
o
d
el,
it
was
in
teg
r
ated
with
th
e
ac
tio
n
s
er
v
er
R
ASA
f
r
am
ewo
r
k
,
i.e
.
,
Ag
r
iB
o
t,
to
p
r
ed
ict
th
e
d
is
ea
s
e
.
3
.
2
.
M
a
chine
lea
rning
a
lg
o
ri
t
hm
s
f
o
r
rice
dis
ea
s
e
det
ec
t
io
n
Fig
u
r
e
3
d
ep
icts
th
e
co
m
p
lete
p
r
o
ce
s
s
f
lo
w
f
o
r
r
ice
d
is
ea
s
e
d
etec
tio
n
im
p
lem
en
ted
in
th
e
p
r
o
p
o
s
e
d
s
y
s
tem
.
T
h
e
f
ig
u
r
e
s
h
o
ws
th
e
k
ey
s
tag
es,
in
clu
d
i
n
g
im
a
g
e
ac
q
u
is
itio
n
,
r
esizin
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
in
g
Sq
u
ee
ze
Net,
an
d
class
if
icatio
n
u
s
in
g
d
if
f
er
en
t
ML
m
o
d
els.
I
t
clea
r
ly
illu
s
tr
ates
h
o
w
th
e
ex
t
r
ac
ted
f
ea
tu
r
es
ar
e
p
r
o
ce
s
s
ed
an
d
ev
al
u
ated
to
id
en
tify
th
e
m
o
s
t
ac
cu
r
ate
m
o
d
el
f
o
r
r
ice
d
is
ea
s
e
p
r
ed
ictio
n
.
All
th
e
im
ag
e
d
ata
s
ets
ar
e
r
esized
to
3
0
0
×
3
0
0
f
o
r
f
u
r
th
e
r
p
r
o
ce
s
s
in
g
.
R
F,
SVM,
NB
,
an
d
NN
,
ML
m
o
d
els
wer
e
u
s
ed
f
o
r
d
is
ea
s
e
id
en
tific
atio
n
with
p
ar
a
m
eter
s
s
h
o
wn
in
T
ab
le
1
ag
ain
s
t e
ac
h
m
o
d
el.
I
n
o
r
d
er
to
d
if
f
er
en
tiate
a
m
o
n
g
p
ar
ticu
lar
d
is
ea
s
es
af
f
lic
tin
g
r
ice
p
lan
ts
,
th
e
c
o
lo
r
,
s
h
ap
e,
an
d
tex
tu
r
e
ap
p
ea
r
an
ce
o
f
r
ice
lea
v
es
wer
e
s
tu
d
ied
.
A
d
ee
p
-
lear
n
in
g
m
o
d
el
was
u
s
ed
to
ex
tr
a
ct
f
ea
tu
r
es
b
ased
o
n
Sq
u
ee
ze
Net
an
d
f
u
r
th
er
m
ac
h
in
e
-
b
ased
m
eth
o
d
s
wer
e
u
s
ed
to
tr
ain
t
h
e
m
o
d
el.
T
h
e
r
e
s
u
lt
o
f
th
is
p
r
o
ce
s
s
was
a
s
et
o
f
2
0
4
8
e
x
tr
ac
ted
f
ea
tu
r
es.
T
h
e
d
ata
we
r
e
p
a
r
titi
o
n
ed
in
to
th
r
ee
s
ep
a
r
ate
s
u
b
s
ets,
in
clu
d
in
g
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
C
o
n
text
-
a
w
a
r
e
A
g
r
iBo
t u
s
in
g
d
u
a
l in
ten
t
a
n
d
en
tity tra
n
s
fo
r
mer a
n
d
h
yb
r
id
d
ee
p
lea
r
n
in
g
…
(
B
in
o
d
Dek
a
)
3641
tr
ain
in
g
(
8
0
%
o
f
th
e
to
tal
d
ata
s
et)
,
test
in
g
(
1
0
%
o
f
th
e
t
o
tal
d
ataset)
,
an
d
v
alid
atio
n
(
1
0
%
o
f
th
e
t
o
tal
d
ataset)
af
ter
p
r
ep
a
r
atio
n
.
Fig
u
r
e
3
.
W
o
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
r
ice
d
is
ea
s
e
d
etec
tio
n
a
n
d
ev
alu
atio
n
p
ip
elin
e
T
ab
le
1
g
i
v
es
a
d
etailed
o
v
er
v
iew
o
f
th
e
ML
m
o
d
els
u
s
e
d
to
d
etec
t
th
e
d
is
ea
s
e
in
r
ic
e
with
th
e
co
r
r
esp
o
n
d
in
g
h
y
p
e
r
p
ar
am
ete
r
s
.
T
h
e
tab
le
p
r
esen
ts
ac
cu
r
at
e,
m
o
d
el
-
s
p
ec
if
ic
s
ettin
g
s
-
tr
ee
d
ep
th
in
th
e
ca
s
e
o
f
RF
,
ch
o
ices
o
f
k
e
r
n
el
p
a
r
a
m
eter
s
in
th
e
ca
s
e
o
f
SVM,
an
d
ar
ch
itectu
r
al
h
y
p
er
p
ar
a
m
eter
s
in
th
e
ca
s
e
o
f
NN
s
,
alo
n
g
with
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
m
et
h
o
d
s
u
s
ed
.
T
h
is
ca
r
ef
u
l
s
p
ec
if
icatio
n
o
f
p
ar
am
eter
s
m
ak
es
it
ea
s
ier
to
r
ep
r
o
d
u
ce
th
e
ex
p
e
r
im
en
tal
p
r
o
t
o
co
l,
an
d
also
m
a
k
es
it
e
asy
to
h
a
v
e
a
s
o
u
n
d
a
n
d
f
air
co
m
p
ar
is
o
n
o
f
th
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
th
r
o
u
g
h
o
u
t th
e
s
tu
d
y
.
T
ab
le
1
.
ML
m
o
d
els an
d
p
ar
a
m
eter
s
f
o
r
r
ice
d
is
ea
s
e
d
etec
tio
n
M
o
d
e
l
u
se
d
RF
S
V
M
NN
NB
M
o
d
e
l
p
a
r
a
m
e
t
e
r
N
o
o
f
t
r
e
e
s:
1
0
R
e
p
l
i
c
a
b
l
e
t
r
a
i
n
i
n
g
:
N
o
Tr
e
e
d
e
p
t
h
:
u
n
l
i
m
i
t
e
d
M
i
n
i
m
u
m
i
n
st
a
n
c
e
s
p
e
r
n
o
d
e
t
o
c
o
n
t
i
n
u
e
sp
l
i
t
t
i
n
g
:
5
M
o
d
e
l
t
y
p
e
:
s
t
a
n
d
a
r
d
S
V
M
R
e
g
u
l
a
r
i
z
a
t
i
o
n
c
o
n
st
a
n
t
(
C
)
:
1
.
0
Ep
si
l
o
n
(
ε)
:
0
.
1
K
e
r
n
e
l
s
u
se
d
:
S
i
g
mo
i
d
,
Ta
n
h
w
i
t
h
a
u
t
o
x
·
y
+
1
.
0
m
a
p
p
i
n
g
To
l
e
r
a
n
c
e
f
o
r
n
u
mer
i
c
a
l
p
r
e
c
i
si
o
n
:
0
.
0
0
1
M
a
x
i
m
u
m
i
t
e
r
a
t
i
o
n
s
:
1
0
0
H
i
d
d
e
n
l
a
y
e
r
s:
1
0
0
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
:
R
e
L
u
O
p
t
i
mi
z
e
r
:
A
d
a
m
Le
a
r
n
i
n
g
r
a
t
e
(
α)
:
0
.
0
0
0
1
M
a
x
i
t
e
r
a
t
i
o
n
s:
2
0
0
R
e
p
l
i
c
a
b
l
e
t
r
a
i
n
i
n
g
:
Tr
u
e
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
met
h
o
d
:
h
i
s
t
o
g
r
a
m
o
f
o
r
i
e
n
t
e
d
g
r
a
d
i
e
n
t
s
(HOG)
3
.
3
.
E
x
perim
ent
a
l
s
et
up
T
o
d
ev
elo
p
th
e
p
r
o
p
o
s
ed
Ag
r
iB
o
t
s
y
s
tem
,
Py
th
o
n
3
.
6
an
d
R
ASA
's
o
p
en
-
s
o
u
r
ce
co
n
v
er
s
atio
n
al
AI
f
r
am
ewo
r
k
was
u
s
ed
.
T
h
e
c
o
n
v
er
s
atio
n
al
m
o
d
u
le
u
s
ed
th
e
DI
E
T
class
if
ier
as
b
o
th
an
in
t
en
t
class
if
ier
an
d
an
en
tity
r
ec
o
g
n
izer
.
C
u
s
to
m
ac
tio
n
s
wer
e
b
u
ilt
u
s
in
g
th
e
R
AS
A
SDK
f
o
r
r
esp
o
n
s
e
g
en
er
atio
n
an
d
r
ice
d
is
ea
s
e
id
en
tific
atio
n
.
R
ice
leaf
im
ag
es
wer
e
co
llected
in
th
e
f
ield
.
T
h
ese
im
ag
es
wer
e
p
r
o
ce
s
s
ed
an
d
r
esized
,
an
d
th
e
f
ea
tu
r
es
wer
e
ex
tr
ac
te
d
an
d
c
lass
if
ied
.
Fo
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
tr
a
n
s
f
er
lear
n
i
n
g
was
u
s
e
d
,
an
d
th
e
e
x
tr
ac
ted
f
ea
tu
r
es
wer
e
class
if
ied
u
s
in
g
NN,
R
F,
SVM,
an
d
NB
c
lass
if
ier
s
.
T
h
e
as
s
ess
m
en
t
w
as
co
n
d
u
cted
u
s
in
g
4
,
6
2
4
r
ice
leaf
im
ag
es
ca
p
t
u
r
i
n
g
b
ac
ter
ial
b
lig
h
t,
b
r
o
wn
s
p
o
t,
an
d
b
last
d
is
ea
s
e
s
,
alo
n
g
with
tex
tu
al
d
atasets
co
llected
f
r
o
m
in
te
r
ac
tio
n
s
w
ith
f
ar
m
er
s
.
T
h
e
d
ataset
was
d
iv
id
ed
in
th
e
r
atio
8
0
:
1
0
:1
0
to
c
r
ea
te
tr
ain
in
g
,
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
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
6
3
7
-
3
6
4
5
3642
v
alid
atio
n
,
an
d
test
in
g
d
atas
ets.
T
h
e
s
y
s
tem
u
s
ed
an
I
n
tel
C
o
r
e
i5
p
r
o
ce
s
s
o
r
with
1
6
GB
o
f
R
AM
o
n
W
in
d
o
ws
1
1
.
T
h
e
im
p
lem
en
tatio
n
o
f
th
e
s
y
s
tem
u
s
ed
T
en
s
o
r
Flo
w,
Op
en
C
V,
Nu
m
Py
,
an
d
Scik
it
-
lear
n
lib
r
ar
ies.
T
h
e
s
y
s
tem
was
ev
al
u
ated
b
ased
o
n
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
th
e
F1
-
s
co
r
e,
an
d
th
e
ar
ea
u
n
d
er
t
h
e
cu
r
v
e
(
AUC)
.
T
h
e
o
v
er
all
s
y
s
t
em
an
d
th
e
ex
p
er
im
e
n
tal
p
r
o
c
ess
ar
e
s
h
o
wn
in
Fig
u
r
es 1
to
3.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
ab
le
2
r
ep
o
r
ts
th
e
e
v
alu
atio
n
r
esu
lts
o
f
t
h
e
DI
E
T
class
if
ier
u
s
ed
f
o
r
in
ten
t
an
d
en
tity
r
ec
o
g
n
itio
n
in
th
e
Ag
r
iB
o
t
s
y
s
tem
.
T
h
e
ta
b
le
p
r
esen
ts
tr
ain
in
g
a
n
d
te
s
tin
g
ac
cu
r
ac
y
,
F1
-
s
co
r
e,
an
d
p
r
ec
is
io
n
v
alu
es,
p
r
o
v
id
i
n
g
a
co
m
p
r
e
h
en
s
iv
e
v
i
ew
o
f
th
e
m
o
d
el’
s
p
er
f
o
r
m
a
n
ce
.
T
h
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
e
r
o
b
u
s
tn
ess
an
d
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
o
f
t
h
e
co
n
v
er
s
atio
n
al
c
o
m
p
o
n
en
t
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
.
R
ASA
ch
atb
o
t
h
as
a
tr
ain
in
g
ac
cu
r
ac
y
o
f
9
8
%,
wh
ich
m
ea
n
s
th
at
th
e
m
o
d
el
h
as
s
to
ch
asti
ca
lly
lear
n
ed
th
e
p
atter
n
s
an
d
ch
a
r
ac
ter
is
tics
o
f
th
e
tr
ain
in
g
co
r
p
u
s
.
T
h
e
s
lig
h
tly
r
ed
u
ce
d
test
ac
cu
r
ac
y
o
f
9
7
%,
m
ar
g
in
ally
lo
wer
test
ac
cu
r
ac
y
p
r
o
v
es
th
at
th
e
m
o
d
el
is
we
ll
-
g
en
er
alize
d
to
s
itu
atio
n
s
it
h
as
n
ev
er
en
co
u
n
ter
e
d
b
ef
o
r
e,
wh
ich
s
e
r
v
es
as
ev
id
en
ce
o
f
th
e
f
ac
t
th
at
th
e
m
o
d
el
is
well
-
p
er
f
o
r
m
in
g
o
u
ts
id
e
o
f
th
e
tr
ain
in
g
s
et.
T
h
e
s
lig
h
t
d
ec
r
ea
s
in
g
in
ac
cu
r
ac
y
in
d
icate
s
th
at
th
e
o
v
er
f
itti
n
g
is
m
in
im
al
a
n
d
h
en
ce
im
p
r
o
v
es
r
eliab
ilit
y
o
f
th
e
s
y
s
tem
in
its
f
u
n
ctio
n
in
g
.
T
h
e
F1
-
s
co
r
e
o
f
t
r
ain
in
g
o
f
8
2
%
v
er
s
u
s
th
e
test
F1
-
s
co
r
e
o
f
6
4
%
ex
p
lain
s
th
e
tr
ad
eo
f
f
b
etwe
en
p
r
ec
is
io
n
an
d
r
ec
all
o
f
th
e
m
o
d
el.
W
h
en
th
e
tr
ain
in
g
F1
-
s
co
r
e
is
h
ig
h
,
it su
g
g
ests
th
at
th
e
m
o
d
el
h
as b
ee
n
ab
le
to
ca
p
tu
r
e
th
e
p
r
ec
is
io
n
an
d
r
ec
all
wh
en
u
s
in
g
th
e
tr
ain
in
g
d
ata
as
an
in
d
icato
r
o
f
g
o
o
d
p
er
f
o
r
m
a
n
ce
.
On
th
e
o
th
er
h
a
n
d
,
th
e
test
F1
-
s
co
r
e
i
s
r
elativ
ely
lo
w
to
s
h
o
w
th
at
t
h
is
b
alan
ce
m
ig
h
t
b
e
in
jeo
p
ar
d
y
wh
en
u
s
in
g
n
ew
d
ata.
T
h
e
p
r
ec
is
io
n
o
f
th
e
tr
ain
in
g
th
at
is
8
1
%
with
test
ac
cu
r
ac
y
o
f
6
6
%
also
in
d
ic
ates
a
d
ec
r
ea
s
e
in
o
p
tim
is
tic
p
r
ed
ictio
n
s
wh
e
n
te
s
ted
o
n
u
n
s
ee
n
ca
s
es.
T
o
a
d
d
r
ess
th
is
s
h
o
r
tco
m
in
g
,
f
u
tu
r
e
s
t
u
d
ies
will
ex
am
in
e
r
eg
u
lar
izatio
n
s
ch
em
es,
cr
o
s
s
-
v
alid
atio
n
,
an
d
lar
g
er
d
ata
-
au
g
m
en
tatio
n
.
W
ith
in
th
e
f
r
a
m
e
wo
r
k
o
f
r
ice
d
is
ea
s
e
id
en
tific
atio
n
,
th
e
g
e
n
er
ated
d
ataset
was
te
s
ted
with
th
e
h
elp
o
f
th
e
R
F,
SVM,
NB
,
an
d
NN
class
if
ier
s
,
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
was
im
p
le
m
en
ted
with
th
e
l
o
ca
l
Sq
u
ee
ze
Net
ar
ch
itectu
r
e.
All
o
f
th
e
s
am
p
les
y
ield
ed
2
,
0
4
8
f
ea
tu
r
es a
s
s
h
o
wn
i
n
T
a
b
le
2
.
T
ab
le
2
.
E
n
tity
ev
alu
atio
n
r
esu
lts
(
en
ti
ty
ex
tr
ac
to
r
: D
I
E
T
C
lass
if
ier
)
D
a
t
a
s
e
t
A
c
c
u
r
a
c
y
(
%)
F1
-
sc
o
r
e
(
%)
P
r
e
c
i
s
i
o
n
(
%)
Tr
a
i
n
98
82
81
Te
st
97
64
66
T
h
e
co
m
p
ar
ativ
e
p
er
f
o
r
m
an
c
e
o
f
v
ar
io
u
s
ML
alg
o
r
ith
m
s
em
p
lo
y
ed
f
o
r
r
ice
d
is
ea
s
e
d
e
tectio
n
is
p
r
esen
ted
in
T
ab
le
3
.
T
h
is
tab
le
r
ep
o
r
ts
k
ey
ev
al
u
atio
n
m
etr
ics,
in
clu
d
in
g
AUC,
clas
s
if
icatio
n
ac
cu
r
ac
y
,
F1
-
s
co
r
e,
p
r
ec
is
io
n
,
an
d
r
ec
al
l
f
o
r
ea
ch
m
o
d
el.
T
h
e
r
esu
lts
clea
r
ly
in
d
icate
t
h
at
th
e
NN
a
n
d
R
F
ap
p
r
o
ac
h
es
ac
h
iev
e
co
n
s
is
ten
tly
b
etter
p
er
f
o
r
m
a
n
ce
th
an
th
e
SVM
an
d
NB
clas
s
if
ier
s
.
NN
s
(
0
.
9
9
9
)
an
d
R
F
(
0
.
9
8
4
)
ac
h
iev
ed
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
,
s
h
o
win
g
th
e
p
r
ed
i
ctio
n
ac
cu
r
ac
y
o
f
th
o
s
e
m
o
d
els.
As
p
r
ev
io
u
s
ly
d
is
cu
s
s
ed
,
NNs
an
d
R
F
o
u
t
p
er
f
o
r
m
b
o
th
SVM
a
n
d
NB
,
ac
h
iev
in
g
h
ig
h
v
alu
es
o
f
AUC,
class
if
icat
io
n
ac
cu
r
ac
y
,
F1
-
s
co
r
e,
p
r
ec
is
io
n
,
an
d
r
ec
all.
A
b
ala
n
ce
o
f
p
r
ec
i
s
io
n
an
d
r
ec
all
m
ak
es
th
e
m
s
u
itab
le
f
o
r
u
s
e
ca
s
es
th
at
h
av
e
co
n
s
tr
ain
ts
o
n
f
alse
p
o
s
itiv
es
an
d
f
alse
n
eg
ativ
es.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
th
e
f
o
u
r
class
if
ier
s
was
g
en
er
ated
in
o
r
d
er
to
ass
ess
th
e
b
est p
er
f
o
r
m
in
g
m
o
d
els.
T
ab
le
3
.
R
esu
lts
o
f
th
e
d
if
f
er
e
n
t
ML
alg
o
r
ith
m
s
f
o
r
r
ice
d
is
ea
s
e
d
etec
tio
n
M
o
d
e
l
AUC
A
c
c
u
r
a
c
y
F1
-
sc
o
r
e
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
NN
1
0
.
9
9
9
0
.
9
9
9
0
.
9
9
9
0
.
9
9
9
S
V
M
0
.
6
6
7
0
.
4
7
4
0
.
4
5
7
0
.
4
7
5
0
.
4
7
4
RF
0
.
9
9
9
0
.
9
8
4
0
.
9
8
4
0
.
9
8
4
0
.
9
8
4
NB
0
.
8
7
9
0
.
7
6
4
0
.
7
6
4
0
.
7
6
4
0
.
7
6
4
T
ab
le
4
p
r
o
v
i
d
es
a
d
etailed
co
n
f
u
s
io
n
m
atr
i
x
an
aly
s
is
f
o
r
th
e
r
ice
d
is
ea
s
e
clas
s
if
icatio
n
task
u
s
in
g
NN,
SVM,
R
F,
an
d
NB
m
o
d
els.
T
h
e
tab
le
illu
s
tr
ates
th
e
d
is
tr
ib
u
tio
n
o
f
co
r
r
ec
tly
an
d
i
n
co
r
r
ec
tly
class
if
ied
in
s
tan
ce
s
ac
r
o
s
s
th
e
th
r
ee
d
i
s
ea
s
e
ca
teg
o
r
ies,
o
f
f
er
in
g
in
s
ig
h
ts
in
to
class
-
wis
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
is
r
ep
r
esen
tatio
n
en
a
b
les
a
clea
r
ev
alu
atio
n
o
f
m
is
class
if
ica
tio
n
tr
en
d
s
an
d
co
n
f
ir
m
s
th
e
r
eliab
ilit
y
o
f
th
e
b
est
-
p
er
f
o
r
m
in
g
class
if
ier
s
in
d
is
tin
g
u
is
h
in
g
b
etwe
en
v
is
u
a
lly
s
im
ilar
r
ice
d
is
ea
s
es.
All
co
n
f
u
s
io
n
m
atr
ices
ar
e
r
o
w
-
n
o
r
m
alize
d
a
n
d
v
alu
e
s
ar
e
ex
p
r
ess
ed
in
p
e
r
ce
n
tag
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
C
o
n
text
-
a
w
a
r
e
A
g
r
iBo
t u
s
in
g
d
u
a
l in
ten
t
a
n
d
en
tity tra
n
s
fo
r
mer a
n
d
h
yb
r
id
d
ee
p
lea
r
n
in
g
…
(
B
in
o
d
Dek
a
)
3643
A
p
er
f
o
r
m
a
n
ce
co
m
p
a
r
is
o
n
b
etwe
en
th
e
p
r
o
p
o
s
ed
m
o
d
el
a
n
d
r
elate
d
s
tu
d
ies
is
p
r
o
v
id
ed
in
T
ab
le
5
.
T
h
e
tab
le
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
ac
h
iev
es
h
ig
h
er
ac
cu
r
ac
y
th
a
n
m
o
s
t
ex
is
tin
g
m
eth
o
d
s
.
T
h
is
d
em
o
n
s
tr
ates
th
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
ad
o
p
ted
tr
an
s
f
er
lear
n
i
n
g
s
tr
ateg
y
.
I
t
ca
n
b
e
s
ee
n
th
at
b
o
th
NNs
an
d
R
F
m
o
d
els
h
av
e
ac
cu
r
ately
d
etec
ted
r
ice
d
is
ea
s
e.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
ac
h
iev
e
d
b
etter
ac
cu
r
ac
y
u
s
in
g
tr
an
s
f
er
lear
n
in
g
(
Sq
u
ee
ze
Net)
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
T
ab
le
4
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
t
h
e
d
if
f
er
e
n
t c
lass
if
ier
s
f
o
r
r
ice
d
is
ea
s
e
d
etec
tio
n
M
o
d
e
l
A
c
t
u
a
l
P
r
e
d
i
c
t
e
d
D
i
sea
s
e
s
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
(
%)
B
l
a
s
t
(
%)
B
r
o
w
n
s
p
o
t
(
%)
NN
A
c
t
u
a
l
d
a
t
a
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
9
9
.
9
0
.
0
0
0
.
1
B
l
a
s
t
0
.
0
0
9
9
.
8
0
.
2
B
r
o
w
n
s
p
o
t
0
.
0
0
0
.
0
1
9
9
.
8
S
V
M
A
c
t
u
a
l
d
a
t
a
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
5
3
.
2
2
3
.
7
2
3
.
1
B
l
a
s
t
2
7
.
5
43
2
9
.
5
B
r
o
w
n
s
p
o
t
1
9
.
3
1
7
.
6
63
RF
A
c
t
u
a
l
d
a
t
a
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
9
8
.
0
1
.
4
0
0
.
1
B
l
a
s
t
1
.
5
9
7
.
9
0
.
7
B
r
o
w
n
s
p
o
t
0
.
4
0
.
7
9
9
.
2
NB
A
c
t
u
a
l
d
a
t
a
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
7
8
.
7
1
6
.
9
4
.
7
B
l
a
s
t
1
3
.
9
7
1
.
3
1
4
.
8
B
r
o
w
n
s
p
o
t
7
.
5
1
3
.
7
7
8
.
8
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
wo
r
k
d
o
n
e
with
o
u
r
r
esear
c
h
m
o
d
el
R
e
f
e
r
e
n
c
e
M
o
d
e
l
A
c
c
u
r
a
c
y
(
%)
H
a
s
s
a
n
e
t
a
l
.
[
2
3
]
C
N
N
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
(
I
n
c
e
p
t
i
o
n
V
3
)
9
8
.
4
2
Al
-
G
a
a
s
h
a
n
i
e
t
a
l
.
[
2
4
]
S
e
l
f
-
a
t
t
e
n
t
i
o
n
n
e
t
w
o
r
k
(
S
A
N
ET)
b
a
se
d
o
n
t
h
e
R
e
sN
e
t
5
0
9
8
.
7
1
B
i
j
l
w
a
n
e
t
a
l
.
[
2
5
]
Ef
f
i
c
i
e
n
t
N
e
t
B
7
9
9
.
7
2
P
r
o
p
o
se
d
w
o
r
k
S
q
u
e
e
z
e
N
e
t
-
b
a
se
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
w
i
t
h
c
l
a
ss
i
c
a
l
ML
c
l
a
ss
i
f
i
e
r
s
9
9
.
9
0
5.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
p
r
esen
ts
a
c
o
n
t
ex
t
-
s
en
s
itiv
e
Ag
r
iB
o
t,
wh
ich
is
d
esig
n
ed
to
ass
is
t
r
ice
f
ar
m
er
s
with
a
co
m
b
in
atio
n
o
f
co
n
v
er
s
atio
n
a
l
in
tellig
en
ce
an
d
au
to
m
ated
d
is
ea
s
e
d
etec
tio
n
.
T
h
e
s
y
s
tem
was
d
ev
elo
p
ed
o
n
th
e
R
ASA
f
r
am
ewo
r
k
u
s
in
g
a
DI
E
T
class
if
ier
with
co
m
p
e
ten
t
in
ten
t
an
d
en
tity
r
ec
o
g
n
itio
n
with
a
tr
ai
n
in
g
an
d
test
ac
cu
r
ac
y
o
f
9
8
%
an
d
9
7
%
,
r
esp
ec
tiv
ely
.
A
NN
m
o
d
el
was
b
etter
at
r
ice
d
is
ea
s
e
d
etec
tio
n
,
with
an
ac
cu
r
ac
y
o
f
u
p
to
9
9
.
9
%,
th
a
n
o
th
er
class
if
ier
s
,
s
u
ch
as
th
e
RF
,
SVM,
an
d
NB
,
d
u
e
to
t
h
e
ef
f
ec
tiv
e
f
ea
tu
r
e
ex
tr
ac
tio
n
ac
h
iev
e
d
th
r
o
u
g
h
tr
an
s
f
er
lear
n
in
g
with
th
e
h
el
p
o
f
Sq
u
ee
ze
Net.
Ag
r
iB
o
t
is
a
v
iab
le
d
ec
is
io
n
s
u
p
p
o
r
t
s
o
lu
tio
n
th
at
will
a
d
d
r
ess
th
e
lan
g
u
ag
e
a
n
d
lit
er
ac
y
b
a
r
r
ier
b
y
co
m
b
in
in
g
tex
t
-
b
ased
q
u
er
y
m
an
ag
em
en
t
with
im
ag
e
-
b
ased
d
is
ea
s
e
d
iag
n
o
s
tics
to
en
co
u
r
ag
e
th
e
a
d
o
p
tio
n
o
f
AI
-
d
r
iv
en
s
o
lu
tio
n
s
i
n
m
o
d
er
n
r
ice
p
r
o
d
u
ctio
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
r
ec
ei
v
ed
n
o
s
p
ec
if
ic
g
r
an
t
f
r
o
m
an
y
f
u
n
d
in
g
ag
en
c
y
in
th
e
p
u
b
lic,
co
m
m
er
cial,
o
r
not
-
f
o
r
-
p
r
o
f
it secto
r
s
.
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
B
in
o
d
Dek
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
id
ip
Dev
C
h
o
u
d
h
u
r
y
✓
✓
✓
✓
Utp
al
B
ar
m
an
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
6
3
7
-
3
6
4
5
3644
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
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
[
BD
],
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
K
.
J
h
a
,
A
.
D
o
s
h
i
,
P
.
P
a
t
e
l
,
a
n
d
M
.
S
h
a
h
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
n
a
u
t
o
m
a
t
i
o
n
i
n
a
g
r
i
c
u
l
t
u
r
e
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
2
,
p
p
.
1
–
1
2
,
J
u
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
a
.
2
0
1
9
.
0
5
.
0
0
4
.
[
2
]
A
.
S
h
a
r
m
a
a
n
d
P
.
Tr
i
p
a
t
h
i
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
a
g
r
i
c
u
l
t
u
r
e
:
a
l
i
t
e
r
a
t
u
r
e
s
u
r
v
e
y
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Al
l
Re
se
a
r
c
h
Ed
u
c
a
t
i
o
n
a
n
d
S
c
i
e
n
t
i
f
i
c
M
e
t
h
o
d
s
,
v
o
l
.
9
,
n
o
.
8
,
p
p
.
2
4
5
5
–
6
2
1
1
,
2
0
2
1
.
[
3
]
J.
M
e
n
d
e
s
e
t
a
l
.
,
“
S
mart
p
h
o
n
e
a
p
p
l
i
c
a
t
i
o
n
s
t
a
r
g
e
t
i
n
g
p
r
e
c
i
s
i
o
n
a
g
r
i
c
u
l
t
u
r
e
p
r
a
c
t
i
c
e
s
—
a
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
,
”
A
g
ro
n
o
m
y
,
v
o
l
.
1
0
,
n
o
.
6
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
my
1
0
0
6
0
8
5
5
.
[
4
]
P
.
K
.
M
a
d
u
r
i
,
P
.
D
h
i
ma
n
,
M
.
R
.
S
h
u
k
l
a
,
S
.
A
n
a
n
d
,
a
n
d
S
.
P
.
S
i
n
g
h
,
“
F
a
r
mers
a
g
r
i
c
u
l
t
u
r
e
a
ssi
s
t
a
n
c
e
C
h
a
t
b
o
t
,
”
i
n
2
0
2
1
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
C
o
n
t
r
o
l
a
n
d
N
e
t
w
o
rki
n
g
(
I
C
A
C
3
N
)
,
D
e
c
.
2
0
2
1
,
p
p
.
1
8
8
4
–
1
8
8
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
3
N
5
3
5
4
8
.
2
0
2
1
.
9
7
2
5
6
3
4
.
[
5
]
U
.
K
i
r
u
t
h
i
k
a
,
S
.
K
.
S
.
R
a
j
a
,
V
.
B
a
l
a
j
i
,
a
n
d
C
.
J.
R
a
m
a
n
,
“
E
-
a
g
r
i
c
u
l
t
u
r
e
f
o
r
d
i
r
e
c
t
mar
k
e
t
i
n
g
o
f
f
o
o
d
c
r
o
p
s
u
s
i
n
g
c
h
a
t
b
o
t
s
,
”
i
n
2
0
2
0
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
P
o
w
e
r,
En
e
rg
y
,
C
o
n
t
r
o
l
a
n
d
T
r
a
n
sm
i
ssi
o
n
S
y
st
e
m
s
(
I
C
PE
C
T
S
)
,
D
e
c
.
2
0
2
0
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
EC
TS4
9
1
1
3
.
2
0
2
0
.
9
3
3
7
0
2
4
.
[
6
]
C
.
W
.
O
k
o
n
k
w
o
a
n
d
A
.
A
.
I
b
i
j
o
l
a
,
“
C
h
a
t
b
o
t
s
a
p
p
l
i
c
a
t
i
o
n
s
i
n
e
d
u
c
a
t
i
o
n
:
a
sy
st
e
mat
i
c
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
d
u
c
a
t
i
o
n
:
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
a
e
a
i
.
2
0
2
1
.
1
0
0
0
3
3
.
[
7
]
U
.
I
.
I
smai
l
,
H
.
N
.
C
h
u
a
,
R
.
N
o
r
d
i
n
,
a
n
d
M
.
K
.
A
h
me
d
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
r
i
c
e
d
i
sea
se
d
e
t
e
c
t
i
o
n
:
d
a
t
a
se
t
s,
me
t
h
o
d
o
l
o
g
i
e
s,
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s
,
”
S
m
a
r
t
A
g
ri
c
u
l
t
u
ra
l
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
1
,
A
u
g
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
e
c
h
.
2
0
2
5
.
1
0
0
9
7
6
.
[
8
]
G
.
D
h
a
n
u
s
h
,
N
.
K
h
a
t
r
i
,
S
.
K
u
m
a
r
,
a
n
d
P
.
K
.
S
h
u
k
l
a
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
m
a
c
h
i
n
e
v
i
s
i
o
n
sy
s
t
e
ms
a
n
d
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
l
g
o
r
i
t
h
ms
f
o
r
t
h
e
d
e
t
e
c
t
i
o
n
a
n
d
h
a
r
v
e
s
t
i
n
g
o
f
a
g
r
i
c
u
l
t
u
r
a
l
p
r
o
d
u
c
e
,
”
S
c
i
e
n
t
i
f
i
c
A
f
ri
c
a
n
,
v
o
l
.
2
1
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
c
i
a
f
.
2
0
2
3
.
e
0
1
7
9
8
.
[
9
]
B
.
K
o
o
p
m
a
n
e
t
a
l
.
,
“
A
g
A
s
k
:
a
n
a
g
e
n
t
t
o
h
e
l
p
a
n
sw
e
r
f
a
r
m
e
r
s’
q
u
e
st
i
o
n
s
f
r
o
m
sc
i
e
n
t
i
f
i
c
d
o
c
u
m
e
n
t
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
D
i
g
i
t
a
l
L
i
b
ra
r
i
e
s
,
v
o
l
.
2
5
,
n
o
.
4
,
p
p
.
5
6
9
–
5
8
4
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
7
9
9
-
0
2
3
-
0
0
3
6
9
-
y.
[
1
0
]
D
.
R
.
A
n
e
k
a
r
,
S
.
S
u
r
y
a
v
a
n
s
h
i
,
D
.
A
u
t
i
,
P
.
L
o
k
h
a
n
d
e
,
a
n
d
A
.
D
e
sh
m
u
k
h
,
“
F
a
r
mer’
s
a
ss
i
st
a
n
t
u
s
i
n
g
A
I
v
o
i
c
e
b
o
t
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Re
s
e
a
rc
h
i
n
S
c
i
e
n
c
e
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
2
2
4
–
2
3
0
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
4
8
1
7
5
/
I
JA
R
S
C
T
-
9
1
2
1
.
[
1
1
]
P
.
Te
m
n
i
r
a
n
r
a
t
,
K
.
K
i
r
a
t
i
r
a
t
a
n
a
p
r
u
k
,
A
.
K
i
t
v
i
m
o
n
r
a
t
,
W
.
S
i
n
t
h
u
p
i
n
y
o
,
a
n
d
S
.
P
a
t
a
r
a
p
u
w
a
d
o
l
,
“
A
sy
s
t
e
m fo
r
a
u
t
o
mat
i
c
r
i
c
e
d
i
se
a
se
d
e
t
e
c
t
i
o
n
f
r
o
m
r
i
c
e
p
a
d
d
y
i
ma
g
e
s
s
e
r
v
i
c
e
d
v
i
a
a
C
h
a
t
b
o
t
,
”
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
8
5
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
1
.
1
0
6
1
5
6
.
[
1
2
]
V
.
N
a
y
a
k
,
P
.
R
.
N
.
N
a
y
a
k
,
S
a
m
p
o
o
r
n
a
,
A
i
sh
w
a
r
y
a
,
a
n
d
N
.
H
.
S
o
w
my
a
,
“
A
g
r
o
x
p
e
r
t
-
f
a
r
mer
a
ssi
s
t
a
n
t
,
”
G
l
o
b
a
l
T
ra
n
si
t
i
o
n
s
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
5
0
6
–
5
1
2
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
l
t
p
.
2
0
2
1
.
0
8
.
0
1
6
.
[
1
3
]
M
.
M
o
m
a
y
a
,
A
.
K
h
a
n
n
a
,
J
.
S
a
d
a
v
a
r
t
e
,
a
n
d
M
.
S
a
n
k
h
e
,
“
K
r
u
s
h
i
–
t
h
e
f
a
r
m
e
r
C
h
a
t
b
o
t
,
”
i
n
2
0
2
1
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
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
n
f
o
r
m
a
t
i
o
n
,
a
n
d
C
o
m
p
u
t
i
n
g
T
e
c
h
n
o
l
o
g
y
(
I
C
C
I
C
T
)
,
J
u
n
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
I
C
T
5
0
8
0
3
.
2
0
2
1
.
9
5
1
0
0
4
0
.
[
1
4
]
M
.
Ja
i
n
,
P
.
K
u
mar,
I
.
B
h
a
n
s
a
l
i
,
Q
.
V
.
Li
a
o
,
K
.
Tr
u
o
n
g
,
a
n
d
S
.
P
a
t
e
l
,
“
F
a
r
mCh
a
t
:
a
c
o
n
v
e
r
sat
i
o
n
a
l
a
g
e
n
t
t
o
a
n
sw
e
r
f
a
r
mer q
u
e
r
i
e
s
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
A
C
M
o
n
I
n
t
e
r
a
c
t
i
v
e
,
M
o
b
i
l
e
,
W
e
a
ra
b
l
e
a
n
d
U
b
i
q
u
i
t
o
u
s
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
2
,
n
o
.
4
,
p
p
.
1
–
2
2
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
4
5
/
3
2
8
7
0
4
8
.
[
1
5
]
P
.
U
.
U
si
p
,
E.
N
.
U
d
o
,
D
.
E
.
A
su
q
u
o
,
a
n
d
O
.
R
.
J
a
mes
,
“
A
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
m
o
b
i
l
e
C
h
a
t
b
o
t
f
o
r
c
r
o
p
f
a
r
m
e
r
s,”
i
n
El
e
c
t
r
o
n
i
c
G
o
v
e
r
n
a
n
c
e
w
i
t
h
Em
e
r
g
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
(
EG
ETC
2
0
2
2
)
,
2
0
2
2
,
p
p
.
1
9
2
–
2
1
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
2
9
5
0
-
3
_
1
5
.
[
1
6
]
N
.
C
h
a
n
d
o
l
i
k
a
r
,
C
.
D
a
l
e
,
T.
K
o
l
i
,
M
.
S
i
n
g
h
,
a
n
d
T.
N
a
r
k
h
e
d
e
,
“
A
g
r
i
c
u
l
t
u
r
e
a
ss
i
st
a
n
t
C
h
a
t
b
o
t
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
(
I
C
AC
T
A)
,
M
a
r
.
2
0
2
2
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
TA
5
4
4
8
8
.
2
0
2
2
.
9
7
5
3
4
3
3
.
[
1
7
]
G
.
M
.
M
o
st
a
ç
o
,
Í
.
R
.
C
.
D.
S
o
u
z
a
,
L.
B
.
C
a
mp
o
s,
a
n
d
C
.
E
.
C
u
g
n
a
sc
a
,
“
A
g
r
o
n
o
m
o
B
o
t
:
a
sm
a
r
t
a
n
sw
e
r
i
n
g
C
h
a
t
b
o
t
a
p
p
l
i
e
d
t
o
a
g
r
i
c
u
l
t
u
r
a
l
s
e
n
s
o
r
n
e
t
w
o
r
k
s,”
i
n
1
4
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
Pr
e
c
i
si
o
n
A
g
ri
c
u
l
t
u
r
e
(
I
C
P
A)
,
2
0
1
8
,
p
p
.
1
-
1
3
.
[
1
8
]
B
.
A
r
o
r
a
,
D
.
S
.
C
h
a
u
d
h
a
r
y
,
M
.
S
a
t
s
a
n
g
i
,
M
.
Y
a
d
a
v
,
L.
S
i
n
g
h
,
a
n
d
P
.
S
.
S
u
d
h
i
sh
,
“
A
g
r
i
b
o
t
:
a
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
g
e
n
e
r
a
t
i
v
e
n
e
u
r
a
l
n
e
t
w
o
r
k
s
e
n
g
i
n
e
f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
a
p
p
l
i
c
a
t
i
o
n
s,”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
t
e
m
p
o
r
a
ry
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(
I
C
3
A)
,
F
e
b
.
2
0
2
0
,
p
p
.
2
8
–
33
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
A
4
8
9
5
8
.
2
0
2
0
.
2
3
3
2
6
3
.
[
1
9
]
H
.
P
.
K
h
a
n
d
a
g
a
l
e
,
“
D
e
s
i
g
n
a
n
d
i
mp
l
e
me
n
t
a
t
i
o
n
o
f
f
o
u
r
C
r
o
p
N
e
t
:
a
C
N
N
-
b
a
s
e
d
s
y
st
e
m
f
o
r
e
f
f
i
c
i
e
n
t
m
u
l
t
i
-
c
r
o
p
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
n
d
ma
n
a
g
e
m
e
n
t
,
”
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
E
n
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
1
0
,
n
o
.
7
s,
p
p
.
4
6
1
–
4
7
1
,
2
0
2
5
,
d
o
i
:
1
0
.
5
2
7
8
3
/
j
i
se
m.
v
1
0
i
7
s.
8
7
7
.
[
2
0
]
N
.
A
.
A
l
h
a
ssa
n
,
A
.
S
.
A
l
b
a
r
r
a
k
,
S
.
B
h
a
t
i
a
,
a
n
d
P
.
A
g
a
r
w
a
l
,
“
A
n
o
v
e
l
f
r
a
mew
o
r
k
f
o
r
A
r
a
b
i
c
d
i
a
l
e
c
t
c
h
a
t
b
o
t
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
sc
i
e
n
c
e
,
p
p
.
1
–
1
1
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
1
8
4
4
0
5
1
.
[
2
1
]
M
.
J.
H
a
s
a
n
,
S
.
M
a
h
b
u
b
,
M
.
S
.
A
l
o
m,
a
n
d
M
.
A
.
N
a
si
m
,
“
R
i
c
e
d
i
sea
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
y
i
n
t
e
g
r
a
t
i
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
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
2
0
1
9
1
s
t
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
S
c
i
e
n
c
e
,
En
g
i
n
e
e
ri
n
g
a
n
d
R
o
b
o
t
i
c
s Te
c
h
n
o
l
o
g
y
(
I
C
A
S
ERT)
,
M
a
y
2
0
1
9
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
S
ER
T.
2
0
1
9
.
8
9
3
4
5
6
8
.
[
2
2
]
T.
D
a
n
i
y
a
a
n
d
S
.
V
i
g
n
e
sh
w
a
r
i
,
“
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
d
i
sea
se
d
e
t
e
c
t
i
o
n
i
n
r
i
c
e
p
l
a
n
t
u
si
n
g
t
h
e
t
e
x
t
u
r
e
a
n
d
d
e
e
p
f
e
a
t
u
r
e
s,
”
T
h
e
C
o
m
p
u
t
e
r J
o
u
rn
a
l
,
v
o
l
.
6
5
,
n
o
.
7
,
p
p
.
1
8
1
2
–
1
8
2
5
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
9
3
/
c
o
mj
n
l
/
b
x
a
b
0
2
2
.
[
2
3
]
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
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
0
1
2
1
3
8
8
.
[
2
4
]
M
.
S
.
A
.
M
.
A
l
-
G
a
a
s
h
a
n
i
,
N
.
A
.
S
a
mee
,
R
.
A
l
n
a
s
h
w
a
n
,
M
.
K
h
a
y
y
a
t
,
a
n
d
M
.
S
.
A
.
M
u
t
h
a
n
n
a
,
“
U
s
i
n
g
a
R
e
sn
e
t
5
0
w
i
t
h
a
k
e
r
n
e
l
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
sm
f
o
r
r
i
c
e
d
i
se
a
se
d
i
a
g
n
o
si
s,
”
L
i
f
e
,
v
o
l
.
1
3
,
n
o
.
6
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
l
i
f
e
1
3
0
6
1
2
7
7
.
[
2
5
]
A
.
B
i
j
l
w
a
n
e
t
a
l
.
,
“
E
n
h
a
n
c
i
n
g
r
i
c
e
d
i
s
e
a
se
a
n
d
i
n
s
e
c
t
-
p
e
s
t
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
a
u
g
me
n
t
e
d
d
e
e
p
l
e
a
r
n
i
n
g
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
S
m
a
r
t
A
g
ri
c
u
l
t
u
r
a
l
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
1
,
A
u
g
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
e
c
h
.
2
0
2
5
.
1
0
0
9
5
4
.
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
C
o
n
text
-
a
w
a
r
e
A
g
r
iBo
t u
s
in
g
d
u
a
l in
ten
t
a
n
d
en
tity tra
n
s
fo
r
mer a
n
d
h
yb
r
id
d
ee
p
lea
r
n
in
g
…
(
B
in
o
d
Dek
a
)
3645
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Bin
o
d
De
k
a
h
o
l
d
s a
n
M
.
S
c
.
fr
o
m
G
a
u
h
a
ti
Un
iv
e
rsity
,
As
sa
m
,
In
d
ia (2
0
0
6
)
a
n
d
a
n
M
.
Tec
h
.
fro
m
t
h
e
In
d
ia
n
In
stit
u
te
o
f
Tec
h
n
o
lo
g
y
G
u
wa
h
a
ti
(2
0
1
1
)
.
S
in
c
e
2
0
1
1
,
h
e
h
a
s
se
rv
e
d
a
s
a
sy
ste
m
a
n
a
ly
st
a
t
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Krish
n
a
Ka
n
ta
Ha
n
d
iq
u
i
S
tate
Op
e
n
Un
iv
e
rsity
(KK
HSOU)
,
In
d
ia
wh
e
re
h
e
a
p
p
li
e
s
h
is
1
4
y
e
a
rs
o
f
tec
h
n
ica
l
e
x
p
e
rti
se
.
Hi
s
a
c
a
d
e
m
ic
a
n
d
p
ro
fe
ss
io
n
a
l
re
se
a
rc
h
fo
c
u
se
s
o
n
v
irt
u
a
l
a
ss
istan
ts
a
n
d
ima
g
e
p
r
o
c
e
ss
in
g
,
fiel
d
s
in
wh
ich
h
e
h
a
s
c
o
n
tri
b
u
te
d
sig
n
ifi
c
a
n
tl
y
.
I
n
a
d
d
it
i
o
n
to
h
is
tec
h
n
ica
l
c
a
re
e
r,
h
e
b
rin
g
s
two
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
,
f
u
r
th
e
r
e
n
rich
i
n
g
h
is
i
n
terd
isc
ip
l
in
a
r
y
p
r
o
fil
e
.
He
wa
s
h
o
n
o
re
d
with
th
e
g
o
ld
m
e
d
a
l
a
wa
rd
in
“
I
n
n
o
v
a
ti
o
n
in
o
p
e
n
a
n
d
d
istan
c
e
l
e
a
rn
in
g
”
b
y
I
n
d
ira
G
a
n
d
h
i
Na
ti
o
n
a
l
Op
e
n
Un
iv
e
rsity
,
De
l
h
i,
i
n
A
p
ril
2
0
1
7
fo
r
d
e
v
e
l
o
p
i
n
g
a
m
o
b
il
e
a
p
p
l
ica
ti
o
n
to
e
n
h
a
n
c
e
lea
rn
e
r
su
p
p
o
rt
se
rv
ice
s
a
t
KK
HSOU
.
In
re
c
o
g
n
it
io
n
o
f
h
is
o
u
tsta
n
d
i
n
g
se
rv
ice
,
h
e
a
lso
re
c
e
iv
e
d
th
e
v
ice
c
h
a
n
c
e
ll
o
r'
s
e
x
c
e
ll
e
n
c
e
a
wa
rd
in
2
0
1
9
fro
m
th
e
KK
HSOU
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
i
n
o
d
d
e
k
a
@g
m
a
il
.
c
o
m
.
Dr
.
Rid
ip
De
v
Ch
o
u
d
h
u
r
y
i
s
c
u
rre
n
tl
y
se
rv
i
n
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
Krish
n
a
Ka
n
ta
Ha
n
d
iq
u
i
S
tate
Op
e
n
Un
i
v
e
rsity
(KK
HSOU),
G
u
wa
h
a
ti
,
In
d
ia
,
a
p
o
siti
o
n
h
e
h
a
s
h
e
l
d
sin
c
e
No
v
e
m
b
e
r
2
0
2
0
.
He
is
t
h
e
d
irec
to
r
(i/
c
)
o
f
th
e
Hira
n
y
a
Ch
a
n
d
ra
B
h
u
y
a
n
S
c
h
o
o
l
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
a
n
d
th
e
G
u
ru
P
ra
sa
d
d
a
s S
c
h
o
o
l
o
f
In
terd
isc
ip
l
in
a
ry
a
n
d
Vo
c
a
ti
o
n
a
l
S
tu
d
ies
a
t
KK
HSOU.
Ad
d
it
i
o
n
a
ll
y
,
h
e
h
a
s b
e
e
n
e
n
tru
ste
d
wit
h
th
e
ro
le
o
f
d
e
p
u
ty
d
irec
to
r
a
t
th
e
Ce
n
tre
fo
r
On
li
n
e
Ed
u
c
a
ti
o
n
.
He
is
a
n
a
c
ti
v
e
m
e
m
b
e
r
o
f
th
e
a
c
a
d
e
m
ic
c
o
u
n
c
il
,
re
se
a
rc
h
c
o
u
n
c
il
,
a
n
d
se
v
e
ra
l
o
th
e
r
k
e
y
c
o
m
m
it
tee
s
a
t
th
e
u
n
i
v
e
rsity
.
Be
fo
re
j
o
i
n
in
g
KK
H
S
OU
,
h
e
wo
rk
e
d
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
th
e
G
a
u
h
a
ti
Un
iv
e
rsity
Ce
n
tre fo
r
Dista
n
c
e
a
n
d
On
li
n
e
Ed
u
c
a
ti
o
n
(G
UCD
OE),
G
a
u
h
a
ti
Un
iv
e
rsity
,
As
sa
m
,
a
n
d
a
s
a
g
u
e
st
fa
c
u
lt
y
m
e
m
b
e
r
in
th
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
i
e
n
c
e
a
t
Ga
u
h
a
ti
Un
iv
e
rsit
y
.
He
h
o
l
d
s
b
o
t
h
a
P
h
.
D.
a
n
d
a
n
M
.
S
c
.
i
n
Co
m
p
u
ter
S
c
ien
c
e
fro
m
G
a
u
h
a
ti
Un
iv
e
rsity
.
Wi
th
1
9
y
e
a
rs
o
f
p
ro
fe
ss
io
n
a
l
a
n
d
tea
c
h
in
g
e
x
p
e
rien
c
e
,
h
is
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
e
Lea
rn
in
g
,
e
x
p
e
r
t
sy
ste
m
s,
a
n
d
ima
g
e
p
ro
c
e
ss
in
g
.
He
h
a
s
p
u
b
li
s
h
e
d
e
x
ten
siv
e
l
y
i
n
r
e
p
u
ted
in
ter
n
a
ti
o
n
a
l
j
o
u
r
n
a
ls
in
d
e
x
e
d
in
S
c
o
p
u
s
a
n
d
Web
o
f
S
c
ien
c
e
,
a
s
we
ll
a
s
in
n
u
m
e
ro
u
s
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
p
ro
c
e
e
d
i
n
g
s
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
rid
ip
g
u
2
0
1
0
@g
m
a
il
.
c
o
m
.
Dr
.
Utpa
l
Ba
r
m
a
n
is
a
n
a
c
c
o
m
p
li
sh
e
d
a
c
a
d
e
m
ic
lea
d
e
r
,
re
se
a
rc
h
e
r,
a
n
d
in
n
o
v
a
t
o
r
with
o
v
e
r
1
5
+
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
c
o
m
p
u
ter
sc
i
e
n
c
e
a
n
d
e
n
g
in
e
e
rin
g
.
He
c
u
rre
n
tl
y
se
rv
e
s
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
(AI
-
M
L
d
isc
ip
li
n
e
)
a
t
As
sa
m
S
k
i
ll
Un
i
v
e
rsity
(A
G
o
v
e
rn
m
e
n
t
o
f
As
sa
m
Un
iv
e
rsity
)
a
n
d
h
a
s
p
re
v
io
u
sly
h
e
l
d
k
e
y
ro
les
s
u
c
h
a
s
d
e
a
n
o
f
f
a
c
u
lt
y
a
t
As
sa
m
Do
w
n
T
o
wn
Un
i
v
e
rsity
,
d
e
a
n
o
f
re
se
a
rc
h
,
a
n
d
c
e
n
tre
h
e
a
d
o
f
t
h
e
Ce
n
tre
o
f
E
x
c
e
ll
e
n
c
e
in
Da
ta
S
c
ien
c
e
a
n
d
S
imu
lati
o
n
(COEDSS
)
a
t
Ka
z
iran
g
a
Un
i
v
e
rsity
.
He
h
a
s
s
u
c
c
e
ss
fu
ll
y
c
o
m
p
let
e
d
9
+
fu
n
d
e
d
re
se
a
rc
h
a
n
d
c
o
n
su
lt
a
n
c
y
p
ro
jec
ts
w
o
rth
o
v
e
r
₹
6
5
lak
h
s
fr
o
m
a
g
e
n
c
ies
su
c
h
a
s
AICTE,
CDB,
a
n
d
M
HRD
,
a
n
d
se
rv
e
s
a
s
Co
-
P
I
in
th
e
₹
4
.
8
5
c
ro
re
DST
NID
HI
i
-
TBI
p
ro
je
c
t.
He
h
a
s
g
u
id
e
d
5
P
h
.
D
.
sc
h
o
lars
,
o
f
w
h
ich
2
h
a
v
e
a
wa
rd
e
d
a
n
d
On
e
h
a
s
su
b
m
it
ted
th
e
sis.
He
h
a
s
a
lso
g
u
id
e
d
a
to
tal
o
f
1
5
+
M
.
Tec
h
.
th
e
se
s,
a
n
d
2
5
+
B.
T
e
c
h
.
p
ro
jec
ts,
a
n
d
h
o
l
d
s
th
re
e
p
a
t
e
n
ts
in
a
g
ri
-
in
f
o
rm
a
ti
c
s
.
His
re
se
a
rc
h
e
x
p
e
rti
se
sp
a
n
s
a
g
ri
-
i
n
f
o
rm
a
ti
c
s,
m
a
c
h
in
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
d
a
ta
sc
ien
c
e
,
a
n
d
c
o
m
p
u
ter
v
isi
o
n
.
Be
y
o
n
d
a
c
a
d
e
m
ia,
h
e
is
th
e
co
-
fo
u
n
d
e
r
a
n
d
a
d
v
i
so
r
o
f
S
o
m
a
d
h
a
n
A
g
riT
e
c
h
a
n
d
Ka
re
n
g
g
Tec
h
n
o
l
o
g
ies
.
T
h
e
S
o
m
a
d
h
a
n
is
a
sta
rtu
p
fu
n
d
e
d
b
y
AIC
Ne
a
tE
HU
B,
AA
U
-
Jo
rh
a
t.
He
h
a
s m
o
re
th
a
n
5
0
+
jo
u
rn
a
l
p
a
p
e
rs an
d
2
0
+
c
o
n
fe
re
n
c
e
p
a
p
e
rs an
d
b
o
o
k
c
h
a
p
ters
.
He
a
lso
c
o
n
tri
b
u
tes
g
lo
b
a
ll
y
a
s
a
n
a
ss
o
c
iate
e
d
it
o
r
fo
r
In
f
o
rm
a
ti
o
n
P
ro
c
e
ss
in
g
i
n
Ag
ricu
lt
u
re
(
El
se
v
ier
)
a
n
d
e
d
it
o
r
in
S
p
rin
g
e
r
Na
tu
re
,
a
n
d
JA
NS.
Driv
e
n
b
y
a
p
a
ss
io
n
fo
r
i
n
n
o
v
a
ti
o
n
a
n
d
in
terd
isc
ip
li
n
a
ry
c
o
ll
a
b
o
ra
ti
o
n
,
he
c
o
n
ti
n
u
e
s to
b
rid
g
e
re
se
a
rc
h
,
in
d
u
stry
,
a
n
d
e
n
tre
p
re
n
e
u
rsh
i
p
,
m
e
n
to
rin
g
t
h
e
n
e
x
t
g
e
n
e
ra
ti
o
n
o
f
tec
h
n
o
lo
g
y
p
r
o
fe
ss
io
n
a
ls
a
n
d
c
o
n
tri
b
u
ti
n
g
to
a
d
v
a
n
c
e
m
e
n
ts
in
AI an
d
Ag
ri
Tec
h
so
l
u
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
u
t
p
a
lb
e
lso
r@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.