I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
25
,
No
.
2
,
Feb
r
u
ar
y
20
22
,
p
p
.
995
~
1
0
0
2
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijeecs.v
25
.i
2
.
pp
995
-
1
0
0
2
995
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
I
nterne
t
o
f
things
a
nd multi
-
cla
ss
d
eep f
ea
ture
-
fusio
n bas
ed
cla
ss
ificatio
n of t
o
ma
to lea
f
disea
se
Rina
M
a
ha
k
ud
1
,
B
ino
d K
um
a
r
P
a
t
t
a
na
y
a
k
1
,
B
ibu
dh
en
du
P
a
t
i
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
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
i
k
s
h
a
'O
' A
n
u
sa
n
d
h
a
n
D
e
e
me
d
t
o
b
e
U
n
i
v
e
r
si
t
y
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
i
c
a
l
E
d
u
c
a
t
i
o
n
a
n
d
R
e
se
a
r
c
h
,
B
h
u
b
a
n
e
sw
a
r
,
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
,
R
a
ma
D
e
v
i
W
o
m
e
n
’
s Un
i
v
e
r
si
t
y
,
B
h
u
b
a
n
e
sw
a
r
,
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
Sep
1
7
,
2
0
2
1
R
ev
is
ed
Dec
20
,
2
0
2
1
Acc
ep
ted
Dec
24
,
2
0
2
1
A
d
e
e
p
tran
sfe
r
lea
rn
i
n
g
(
d
eep
-
T
L)
c
las
sifica
ti
o
n
m
o
d
e
l
h
a
s
b
e
e
n
p
r
o
p
o
se
d
to
d
iag
n
o
se
to
m
a
to
lea
f
d
ise
a
se
.
Th
e
m
a
in
c
h
a
ll
e
n
g
e
o
f
in
a
c
c
u
ra
te
c
las
sifica
ti
o
n
o
f
a
c
o
n
v
o
l
u
ti
o
n
n
e
u
ra
l
n
e
two
rk
(
CNN
)
m
o
d
e
l
wa
s
th
e
a
v
a
il
a
b
il
it
y
o
f
t
h
e
sm
a
ll
-
siz
e
d
d
a
tas
e
t.
Th
is
m
o
d
e
l
d
e
a
ls
with
th
e
c
h
a
ll
e
n
g
e
s
li
k
e
a
v
a
il
a
b
il
it
y
o
f
sm
a
ll
-
siz
e
d
a
n
d
imb
a
lan
c
e
d
d
a
tas
e
ts.
Th
e
p
r
o
p
o
se
d
Ale
x
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM
)
f
u
se
d
h
y
b
rid
c
las
sifica
ti
o
n
(A
S
F
H
C)
m
o
d
e
l
is b
a
se
d
o
n
fu
ll
y
fu
si
o
n
tec
h
n
o
l
o
g
y
th
a
t
a
v
o
i
d
s o
v
e
rfit
ti
n
g
to
c
las
sif
y
th
e
ty
p
e
o
f
d
ise
a
se
in
t
o
m
a
to
lea
v
e
s.
Th
e
p
r
o
p
o
se
d
m
o
d
e
l
a
c
h
iev
e
s
th
e
b
e
st
p
e
rfo
rm
a
n
c
e
in
term
s
o
f
a
c
c
u
ra
c
y
b
y
d
a
ta
a
u
g
m
e
n
tati
o
n
o
f
th
e
train
in
g
d
a
ta
.
It
u
se
s
a
p
re
-
trai
n
e
d
n
e
two
r
k
fo
r
fe
a
tu
re
e
x
trac
ti
o
n
wi
th
th
e
m
o
d
if
ica
ti
o
n
o
f
a
rc
h
it
e
c
tu
re
b
y
c
o
n
c
a
ten
a
ti
n
g
t
wo
lay
e
rs
F
C6
a
n
d
F
C7
(
fu
ll
y
c
o
n
n
e
c
ted
lay
e
r),
p
l
u
s
a
li
n
e
a
r
S
VM
c
las
sifier
fo
r
c
las
sifica
ti
o
n
o
f
t
h
e
d
ise
a
se
.
Th
e
u
n
i
q
u
e
n
e
ss
o
f
th
e
re
se
a
rc
h
is
a
lt
h
o
u
g
h
th
e
d
a
tas
e
t
is
n
o
t
b
a
lan
c
e
d
,
t
h
e
p
e
rfo
rm
a
n
c
e
o
f
t
h
e
m
o
d
e
l
h
a
s
a
c
h
iev
e
d
th
e
m
a
x
imu
m
.
Co
m
p
a
re
d
with
VG
G
1
6
a
n
d
VG
G
1
9
,
t
h
e
p
ro
p
o
se
d
m
o
d
e
l
(ASF
HC)
h
a
s
b
e
e
n
e
v
a
lu
a
ted
u
sin
g
d
iffere
n
t
m
e
a
su
rin
g
p
a
ra
m
e
ters
,
in
d
ica
ti
n
g
re
m
a
rk
a
b
le
c
o
m
p
u
tati
o
n
ti
m
e
f
o
r
imp
lem
e
n
tatio
n
in
th
e
i
n
tern
e
t
o
f
th
i
n
g
s
(
I
o
T
)
d
o
m
a
in
.
Th
e
o
v
e
ra
l
l
a
c
c
u
ra
c
y
a
tt
a
in
e
d
b
y
t
h
e
m
o
d
e
l
is 9
9
.
6
2
%
.
K
ey
w
o
r
d
s
:
Alex
Net
C
NNs
SVM
T
o
m
ato
leaf
d
is
ea
s
e
id
en
tific
atio
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
:
R
in
a
Ma
h
ak
u
d
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
,
Sik
s
h
a
'
O'
An
u
s
an
d
h
an
Dee
m
ed
to
b
e
Un
iv
er
s
ity
I
n
s
titu
te
o
f
T
ec
h
n
ical
E
d
u
ca
ti
o
n
an
d
R
esear
ch
B
h
u
b
an
eswar
,
I
n
d
ia
E
m
ail
:
r
in
am
ah
ak
u
d
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
o
m
ato
is
a
u
s
ef
u
l
v
eg
etab
le
th
at
is
r
ich
in
v
itam
in
C
,
p
o
ta
s
s
iu
m
,
f
o
late,
an
d
v
itam
in
K.
T
h
is
p
lan
t
h
as
s
o
m
e
m
ed
icin
al
v
alu
es.
I
t
is
ad
v
is
ab
le
to
co
n
s
u
m
e
in
o
r
d
er
to
r
ed
u
ce
th
e
r
is
k
o
f
h
ea
r
t
d
is
ea
s
e
an
d
ca
n
ce
r
.
I
n
2
0
2
0
,
w
o
r
l
d
p
r
o
ce
s
s
in
g
to
m
ato
co
u
n
cil
(
WP
TC
)
wo
r
ld
esti
m
ate
o
f
to
m
ato
p
r
o
d
u
ctio
n
is
ar
o
u
n
d
3
9
.
2
m
illi
o
n
m
etr
ic
to
n
s
,
m
ai
n
ly
d
u
e
t
o
th
e
in
cr
ea
s
e
o
f
th
e
C
h
in
ese
f
o
r
ec
ast
to
5
.
6
m
il
lio
n
to
n
es
[
1
]
.
T
h
e
g
r
o
wth
cy
cle
o
f
th
e
to
m
at
o
p
lan
t
is
r
elativ
ely
s
h
o
r
t,
th
at
is
ab
o
u
t
th
r
ee
to
f
i
v
e
m
o
n
t
h
s
with
an
a
v
er
ag
e
tem
p
er
atu
r
e
1
0
to
2
0
d
eg
r
ee
s
[
2
]
.
I
t is v
er
y
d
if
f
icu
lt f
o
r
a
f
ar
m
er
to
id
en
tify
th
e
d
is
ea
s
es in
to
m
ato
p
lan
ts
f
r
o
m
th
eir
p
ast
e
x
p
er
ien
ce
b
ec
a
u
s
e
o
f
clim
ate
c
h
an
g
e.
I
n
th
e
m
an
u
al
ca
s
e
o
f
cu
ltiv
atio
n
,
th
e
p
r
o
ce
s
s
is
lab
o
r
-
in
ten
s
iv
e,
co
s
t
-
ef
f
ec
tiv
e
an
d
ti
m
e
-
co
n
s
u
m
in
g
.
So
,
th
e
y
n
ee
d
d
o
m
ain
e
x
p
er
t
v
is
it
to
th
e
f
ield
,
wh
ich
is
co
s
tly
.
I
t
is
ch
allen
g
in
g
to
p
r
o
tect
h
e
alth
y
p
lan
ts
f
r
o
m
d
is
ea
s
es
to
p
r
o
v
id
e
q
u
ality
an
d
q
u
an
titativ
e
p
r
o
d
u
cts
in
th
e
m
ar
k
et.
T
h
e
r
ef
o
r
e
,
if
d
is
ea
s
es
ar
e
ap
p
r
o
p
r
iately
d
ia
g
n
o
s
ed
,
th
en
p
r
ec
au
tio
n
s
ca
n
b
e
tak
en
.
T
o
r
ep
lace
th
e
ex
p
er
t’
s
ad
v
ice
in
tr
ad
itio
n
al
m
eth
o
d
o
f
cu
ltiv
atio
n
,
it
is
v
er
y
m
u
c
h
o
f
n
ec
ess
ar
y
to
a
u
to
m
ate
th
e
d
is
ea
s
e
id
en
tific
atio
n
p
r
o
ce
s
s
at
v
er
y
ea
r
ly
s
tag
e
[
3
]
.
T
h
e
t
y
p
e
o
f
le
af
d
is
ea
s
e
class
if
icatio
n
b
y
v
is
u
al
o
b
s
er
v
ati
o
n
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
2
,
Feb
r
u
a
r
y
20
22
:
9
9
5
-
1
0
0
2
996
p
r
o
n
e
t
o
e
r
r
o
r
d
u
e
t
o
e
n
v
i
r
o
n
m
e
n
t
a
l
s
t
i
m
u
li
s
u
c
h
a
s
s
h
a
d
o
ws
,
r
e
f
l
e
c
t
i
o
n
s
o
f
s
u
n
s
h
i
n
e
,
f
o
g
,
a
n
d
h
i
g
h
h
u
m
i
d
i
t
y
[
4
]
.
R
ec
en
tly
ad
v
an
ce
m
e
n
t
in
c
o
m
p
u
tatio
n
al
to
o
ls
s
u
ch
as
im
ag
e
p
r
o
ce
s
s
in
g
,
r
em
o
te
s
en
s
in
g
,
ar
tific
ial
in
tellig
en
ce
an
d
d
ee
p
lear
n
in
g
h
elp
ed
t
o
ac
h
iev
e
s
u
cc
ess
f
u
l
ap
p
licatio
n
.
I
n
last
1
0
y
ea
r
s
,
d
ee
p
lear
n
i
n
g
(
DL
)
h
ad
b
ee
n
a
p
p
lied
in
v
ar
io
u
s
f
ield
s
lik
e
v
id
eo
class
if
icatio
n
,
o
b
ject
d
etec
tio
n
,
an
d
h
u
m
an
ac
tio
n
r
ec
o
g
n
itio
n
.
Fre
s
h
ly
DL
h
as
also
b
ee
n
s
u
c
ce
s
s
f
u
lly
ap
p
lied
i
n
ag
r
icu
ltu
r
al
s
ec
to
r
f
o
r
d
i
s
ea
s
e
id
en
tific
a
tio
n
an
d
p
r
ed
ictio
n
o
f
d
i
s
e
a
s
e
[
5
]
,
[
6
]
.
I
n
t
h
e
p
a
s
t
d
e
c
a
d
e
,
t
h
e
c
l
a
s
s
i
f
i
c
at
i
o
n
a
l
g
o
r
i
t
h
m
s
u
c
h
a
s
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
(
S
V
M
)
[
7
]
,
k
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN)
[
8
]
,
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
AN
N)
[
9
]
,
p
ar
ticle
s
war
m
o
p
tim
iz
atio
n
[
1
0
]
,
r
an
d
o
m
f
o
r
est
(
R
F)
[
1
1
]
an
d
s
o
o
n
wer
e
u
s
ed
f
o
r
p
lan
t
d
is
ea
s
e
id
en
tific
atio
n
.
SVM
is
a
p
o
p
u
lar
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
class
if
ier
u
s
ed
f
o
r
s
o
lv
in
g
b
o
th
b
in
ar
y
an
d
m
u
lti
class
cla
s
s
if
icat
io
n
p
r
o
b
lem
.
T
h
u
s
,
p
r
e
-
tr
ain
e
d
c
o
n
v
o
l
u
tio
n
n
e
u
r
al
n
etwo
r
k
(
C
NN
)
n
etwo
r
k
with
SVM
clas
s
if
ier
im
p
r
o
v
es th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el.
T
h
e
m
ain
wo
r
k
o
f
th
is
p
ap
er
i
s
r
ev
o
lv
ed
ar
o
u
n
d
th
e
v
eg
etab
le
to
m
ato
.
T
h
is
is
a
v
eg
etab
le
wh
ich
ca
n
b
e
cu
ltiv
ated
th
r
o
u
g
h
o
u
t
t
h
e
y
ea
r
.
T
h
e
clim
ate
ch
an
g
in
g
f
a
cto
r
s
th
at
ar
e
h
u
m
id
ity
,
h
ea
v
y
r
ain
,
g
lo
b
al
r
ad
iatio
n
,
a
n
d
tem
p
er
atu
r
e
.
T
h
at
ca
n
a
f
f
ec
t
th
e
g
r
o
wth
o
f
t
h
e
cr
o
p
[
1
2
]
an
d
d
u
e
to
th
ese
f
ac
to
r
s
’
p
lan
ts
g
o
t
af
f
ec
ted
b
y
th
e
d
is
ea
s
es.
So
,
th
er
e
ar
e
a
lo
t
o
f
r
esear
c
h
wo
r
k
u
n
d
e
r
tak
en
b
y
th
e
r
esear
ch
e
r
f
o
r
leaf
d
i
s
ea
s
es
id
en
tific
atio
n
o
f
th
e
to
m
ato
p
lan
t
u
s
in
g
v
ar
io
u
s
m
o
d
els.
A
co
n
v
o
lu
tio
n
n
eu
r
al
n
etwo
r
k
(
C
NN)
m
o
d
el
was
p
r
o
p
o
s
ed
in
[
1
3
]
f
o
r
th
e
to
m
a
to
p
lan
t'
s
leaf
-
b
ased
class
if
ica
tio
n
.
I
n
th
is
C
NN
Mo
d
el,
1
4
0
0
leaf
im
ag
es
h
ad
b
ee
n
tr
ain
ed
in
s
u
g
g
ested
8
lay
er
s
an
d
9
8
.
4
%
o
f
ac
cu
r
ac
y
was
o
b
tain
ed
.
Ver
m
a
et
a
l
.
[
1
4
]
d
ev
elo
p
ed
a
C
NN
ar
ch
itectu
r
es
-
b
ased
m
o
d
el
wh
ich
wo
r
k
s
in
two
d
if
f
e
r
en
t
m
o
d
es
f
o
r
ex
tr
ac
tin
g
th
e
f
ea
tu
r
es
an
d
th
en
th
e
ex
tr
ac
ted
f
ea
tu
r
e
s
et
was
tr
ain
ed
in
a
m
u
lticlas
s
SVM
to
g
et
th
e
f
in
al
o
u
tp
u
t.
T
h
e
a
u
th
o
r
co
m
p
ar
e
d
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
Alex
Net
m
o
d
el
with
o
th
er
two
n
etwo
r
k
s
Sq
u
ee
ze
Net
an
d
I
n
ce
p
tio
n
V3
.
T
h
e
Alex
Net
r
esu
ltin
g
th
e
h
ig
h
est
ac
cu
r
ac
y
in
tr
an
s
f
er
lear
n
in
g
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
ap
p
r
o
ac
h
es
8
9
.
6
9
%
an
d
9
3
.
4
%,
r
esp
ec
tiv
el
y
f
o
r
to
m
at
o
late
b
lig
h
t
d
is
ea
s
e.
Ash
q
ar
an
d
Ab
u
-
Naser
[
1
5
]
p
r
esen
ted
a
f
u
ll
-
co
lo
r
n
eu
r
al
n
etwo
r
k
m
o
d
el
to
ex
tr
ac
t
f
ea
tu
r
es
in
two
s
u
b
s
ec
tio
n
s
.
T
h
e
f
ir
s
t
s
ec
tio
n
o
f
th
e
m
o
d
el
is
f
ea
tu
r
e
ex
tr
ac
tio
n
wh
ich
co
n
s
is
ts
o
f
4
lay
er
s
o
f
co
n
v
o
l
u
tio
n
al
lay
er
s
,
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
u
)
an
d
m
ax
p
o
o
lin
g
la
y
er
.
T
h
e
s
ec
o
n
d
s
ec
tio
n
o
f
th
e
m
o
d
el
is
f
latten
ed
lay
er
b
y
u
s
in
g
two
d
en
s
e
lay
er
s
f
o
r
b
o
th
ap
p
r
o
ac
h
es.
L
u
n
a
et
a
l
.
[
1
6
]
d
ev
elo
p
e
d
a
p
r
e
-
tr
ain
ed
d
ee
p
lear
n
in
g
Alex
Net
ar
ch
itectu
r
e
to
id
en
tify
th
e
th
r
ee
to
m
ato
leaf
d
is
ea
s
es.
T
h
e
au
th
o
r
u
til
izes
th
e
m
o
d
el
Alex
Net
b
o
th
an
o
m
aly
d
etec
tio
n
a
n
d
d
is
ea
s
e
d
etec
tio
n
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
h
ad
an
ac
cu
r
ac
y
o
f
9
1
.
6
p
e
r
ce
n
t b
ase
d
o
n
3
6
s
am
p
les.
Fer
en
tin
o
s
[
1
7
]
d
ev
el
o
p
ed
a
n
opt
im
al
d
ee
p
lear
n
in
g
m
o
d
el
an
d
u
s
ed
d
ataset
co
n
tain
s
8
7
,
8
4
8
in
f
ec
ted
im
ag
es
an
d
h
ea
lt
h
y
le
av
es
o
u
t
o
f
2
5
p
lan
t
s
p
ec
ies
f
r
o
m
o
p
e
n
d
atasets
.
T
h
e
au
th
o
r
c
o
n
clu
d
e
d
th
at
th
e
b
est
p
er
f
o
r
m
a
n
ce
g
iv
en
b
y
V
GG
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etw
o
r
k
with
9
9
.
5
3
%
o
f
s
u
cc
ess
r
ate
in
th
e
cla
s
s
if
icat
io
n
in
co
m
p
a
r
is
o
n
to
Alex
Net
o
n
e
weir
d
tr
ick
b
atch
(
Alex
NetOWT
B
n
)
w
ith
9
9
.
4
9
%
o
f
s
u
cc
ess
r
ate.
Has
s
an
ien
et
al
.
[
1
8
]
p
r
o
p
o
s
ed
a
m
ath
em
atica
l
m
o
d
el
m
o
th
-
f
lam
e
o
p
tim
izatio
n
(
MFO)
an
d
r
o
u
g
h
s
et
(
MFORS
F
S)
ap
p
r
o
ac
h
to
au
t
o
m
atic
ally
d
etec
t
p
o
wd
e
r
y
m
ild
ew
an
d
ea
r
ly
b
lig
h
t
o
f
to
m
ato
d
is
ea
s
e.
T
ex
tu
r
al
p
atter
n
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
b
y
u
s
in
g
Gab
o
r
tr
a
n
s
f
o
r
m
o
f
d
is
ea
s
ed
to
m
ato
leav
es.
Her
e
au
th
o
r
r
ep
r
esen
ted
a
c
o
m
p
ar
is
o
n
b
etwe
en
p
ar
ti
cle
s
war
m
o
p
tim
izatio
n
an
d
g
en
et
ic
alg
o
r
ith
m
s
with
r
o
u
g
h
s
ets
f
r
o
m
wh
ic
h
r
o
u
g
h
s
et
p
r
o
v
id
e
b
etter
r
esu
lts
.
MF
OR
S
-
b
ased
class
if
icatio
n
o
f
f
e
r
s
a
9
1
.
5
%
r
esu
lt
as
co
m
p
ar
ed
to
m
ax
im
u
m
r
ele
v
a
n
ce
m
in
im
u
m
r
ed
u
n
d
an
c
y
(
m
R
MR)
b
ased
m
eth
o
d
.
A
T
r
an
s
f
er
lear
n
in
g
ap
p
r
o
ac
h
is
p
r
o
p
o
s
ed
in
th
is
p
r
esen
t
wo
r
k
to
id
en
tify
an
d
class
if
y
th
e
ty
p
e
o
f
d
is
ea
s
e
in
r
ea
l
tim
e.
Fo
r
im
p
lem
en
tatio
n
o
f
th
e
m
o
d
el
a
p
r
e
tr
ain
ed
n
etwo
r
k
is
u
s
ed
with
t
h
e
m
o
d
if
icatio
n
o
f
ar
ch
itectu
r
e.
T
h
e
p
r
o
s
ed
f
u
s
e
d
h
y
b
r
i
d
m
o
d
el
is
a
class
if
ica
tio
n
m
o
d
el
b
ased
o
n
d
ee
p
C
NN
m
o
d
el.
T
h
e
m
ai
n
co
n
tr
ib
u
tio
n
s
o
f
th
is
wo
r
k
ar
e
f
o
llo
ws:
−
A
f
u
s
ed
h
y
b
r
id
m
o
d
el
is
p
r
o
p
o
s
ed
,
wh
ich
ca
n
p
r
o
v
id
e
b
ette
r
ac
cu
r
ac
y
with
f
aster
ex
ec
u
ti
o
n
tim
e
with
an
im
b
alan
ce
d
d
ataset
b
y
u
s
in
g
f
ield
im
ag
es
as
well
as
s
tan
d
ar
d
d
ataset
to
ac
h
iev
e
a
u
s
e
f
u
l
d
etec
tio
n
o
f
to
m
ato
p
lan
t
d
is
ea
s
e.
−
A
Pre
-
tr
ain
ed
tr
an
s
f
er
lear
n
in
g
ar
ch
itectu
r
e
b
ased
o
n
f
u
s
io
n
c
o
n
ce
p
t
is
u
s
ed
to
a
n
aly
ze
to
m
ato
leaf
d
is
ea
s
e
ch
ar
ac
ter
is
tics
,
with
th
e
m
o
d
if
icatio
n
o
f
co
n
ca
ten
atin
g
two
l
ay
er
s
FC
6
an
d
FC
7
(
f
u
lly
c
o
n
n
ec
ted
lay
er
)
.
2.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
D
T
h
e
class
if
icatio
n
o
f
th
e
d
is
ea
s
e
id
en
tific
atio
n
in
to
m
ato
p
la
n
t
is
s
h
o
wn
in
Fig
u
r
e
1
.
I
n
th
i
s
s
ec
tio
n
,
d
etail
o
f
im
ag
e
d
ataset
cr
ea
tio
n
f
r
o
m
i
n
ter
n
et
o
f
th
i
n
g
s
(
I
o
T
)
m
o
d
u
le
an
d
im
p
lem
en
t
atio
n
o
f
s
u
g
g
ested
class
if
icatio
n
o
f
th
e
d
is
ea
s
e
m
o
d
els
ar
e
elab
o
r
ated
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
b
r
o
ad
ly
d
iv
id
ed
in
to
th
r
ee
u
n
its
s
u
ch
as
d
ata
ac
q
u
is
itio
n
(
I
o
T
m
o
d
u
les
s
en
s
ed
th
e
im
ag
e
d
at
a)
,
p
r
o
ce
s
s
in
g
u
n
it
(
u
s
in
g
C
NN)
an
d
class
if
icatio
n
u
n
it
ar
e
d
escr
ib
e
d
in
s
u
b
s
eq
u
e
n
t su
b
s
ec
tio
n
.
2
.1
.
I
ma
g
e
da
t
a
s
et
Sen
s
o
r
s
ar
e
p
lace
d
in
th
e
f
iel
d
to
ca
p
tu
r
e
im
ag
es
at
r
e
g
u
lar
in
ter
v
als
d
u
r
in
g
cr
o
p
g
r
o
wth
in
o
r
d
er
t
o
m
o
n
ito
r
f
o
r
in
f
ec
tio
n
.
T
h
is
p
r
o
p
o
s
ed
m
o
d
el
is
co
m
p
r
is
ed
o
f
a
d
ev
ice
k
n
o
wn
as
th
e
R
asb
er
r
y
PI,
wh
ich
is
a
q
u
ad
-
c
o
r
e
6
4
-
b
it
ad
v
a
n
ce
d
r
e
d
u
ce
d
i
n
s
tr
u
ctio
n
s
et
co
m
p
u
tin
g
(
R
I
SC
)
m
ac
h
i
n
es
(
AR
M)
p
r
o
ce
s
s
o
r
r
u
n
n
i
n
g
at
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
tern
et
o
f th
in
g
s
a
n
d
mu
lti
-
cl
a
s
s
d
ee
p
fea
tu
r
e
-
fu
s
io
n
b
a
s
ed
cla
s
s
ifica
tio
n
o
f to
ma
to
lea
f …
(
R
in
a
Ma
h
a
ku
d
)
997
1
.
2
GHz
.
T
h
e
we
b
ca
m
er
a
is
lin
k
ed
to
th
e
p
r
o
ce
s
s
o
r
d
ev
ice
.
Her
e,
a
d
ig
ital
ca
m
e
r
a,
web
ca
m
er
a,
o
r
clo
s
ed
-
cir
cu
it
telev
is
io
n
(
C
C
T
V)
ca
n
b
e
lin
k
ed
to
th
e
p
r
o
ce
s
s
o
r
to
co
n
tin
u
o
u
s
ly
ca
p
tu
r
e
im
a
g
es
o
f
leav
es
an
d
g
en
er
ate
a
d
atab
ase
o
f
t
h
e
leav
es.
All
th
e
m
o
d
u
les
ar
e
co
n
n
ec
ted
th
r
o
u
g
h
I
o
T
n
etwo
r
k
.
B
u
t
in
th
e
p
r
o
p
o
s
ed
I
o
T
b
ased
d
is
ea
s
e
id
en
tific
atio
n
s
ch
em
e,
th
e
d
ataset
is
co
ll
ec
ted
f
r
o
m
‘
Plan
t
v
illag
e’
d
at
ab
ase.
T
h
e
d
ataset
co
n
tain
s
a
to
tal
o
f
6
6
6
0
im
ag
e
s
,
o
u
t
o
f
w
h
ich
6
5
7
8
im
a
g
es
a
r
e
d
is
ea
s
ed
to
m
ato
leaf
im
a
g
e
s
ca
u
s
ed
b
y
y
ello
w
leaf
cu
r
l
v
ir
u
s
a
n
d
m
o
s
aic
v
ir
u
s
,
an
d
8
2
o
f
wh
ich
ar
e
h
ea
lt
h
y
to
m
ato
leaf
im
ag
es.
All
t
h
e
im
ag
es
ar
e
p
r
e
-
p
r
o
ce
s
s
ed
f
o
r
r
esized
to
227x227x3
.
T
h
e
d
ataset
co
n
tain
s
to
m
ato
leaf
im
ag
es
wh
ich
ar
e
g
r
o
u
p
ed
i
n
to
th
r
e
e
class
es
a
s
to
m
ato
m
o
s
aic
v
ir
u
s
,
to
m
ato
y
ello
w
leaf
cu
r
l,
an
d
to
m
ato
h
ea
lth
y
is
s
h
o
wn
in
Fi
g
u
r
e
2
.
T
h
ese
th
r
ee
class
es
ar
e
s
h
o
wn
in
Fig
u
r
e
s
2
(
a
)
-
(
c
)
r
esp
ec
tiv
ely
.
W
e
h
ad
tak
en
8
0
%
an
d
2
0
%
o
f
th
e
s
am
p
les
f
o
r
tr
ain
in
g
an
d
test
in
g
p
u
r
p
o
s
e
r
esp
ec
tiv
e
ly
.
T
h
e
s
am
p
les ar
e
c
h
o
s
en
b
y
th
e
m
o
d
el
r
an
d
o
m
ly
f
o
r
ea
ch
ex
ec
u
tio
n
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
o
f
p
r
o
p
o
s
ed
m
o
d
el
f
o
r
id
en
tific
atio
n
o
f
to
m
ato
leaf
d
is
ea
s
es
(
a)
(
b
)
(
c)
Fig
u
r
e
2
.
Sam
p
le
im
a
g
es o
f
to
m
ato
leaf
:
(
a)
to
m
ato
m
o
s
aic
v
ir
u
s
,
(
b
)
to
m
ato
y
ello
w
leaf
cu
r
l
,
an
d
(
c)
to
m
ato
h
ea
lth
y
2
.2
.
Da
t
a
a
ug
m
ent
a
t
io
n
Data
au
g
m
en
tatio
n
is
a
m
an
ip
u
latin
g
tech
n
iq
u
e
wh
ich
is
d
o
n
e
b
y
s
im
p
le
r
o
tatio
n
o
f
im
a
g
es
(
i.e
.
,
9
0
d
eg
r
ee
s
r
ig
h
t
an
d
lef
t
r
o
tatio
n
an
d
1
8
0
d
e
g
r
ee
s
r
o
tatio
n
)
an
d
f
lip
p
in
g
o
p
er
atio
n
(
i.e
.
,
v
er
tical
f
lip
p
in
g
an
d
h
o
r
izo
n
tal
f
lip
p
i
n
g
)
to
o
v
e
r
co
m
e
th
e
p
r
o
b
lem
o
f
o
v
er
f
itti
n
g
,
we
ap
p
lied
d
ata
au
g
m
en
tatio
n
.
B
y
au
g
m
en
tatio
n
,
th
e
n
u
m
b
er
o
f
s
am
p
le
im
a
g
es
ar
e
in
cr
ea
s
es
to
s
ix
tim
es
to
th
e
n
u
m
b
er
o
f
im
ag
es
to
th
e
ap
p
lied
au
g
m
en
tatio
n
im
ag
es.
As
a
r
esu
lt,
th
e
ch
an
ce
to
lear
n
th
e
ap
p
r
o
p
r
iate
f
e
atu
r
e
is
in
cr
ea
s
ed
f
o
r
th
e
n
et
wo
r
k
[
1
9
]
.
T
ab
le
1
p
r
esen
ts
th
e
d
etail
o
f
ea
c
h
class
o
f
to
m
ato
leaf
d
is
ea
s
e
u
s
ed
d
u
r
in
g
th
e
ex
p
e
r
im
en
tatio
n
.
T
ab
le
1
.
Deta
ils
o
f
im
ag
e
d
ata
s
et
f
o
r
to
m
ato
leaf
d
is
ea
s
e
u
s
ed
in
th
e
s
tu
d
y
Le
a
f
d
i
s
e
a
s
e
s
N
u
mb
e
r
o
f
i
m
a
g
e
s
(
o
r
i
g
i
n
a
l
)
N
u
mb
e
r
o
f
i
m
a
g
e
s
u
se
d
f
o
r
(
a
u
g
m
e
n
t
a
t
i
o
n
)
N
u
mb
e
r
o
f
i
m
a
g
e
s
u
se
d
f
o
r
(
Tr
a
i
n
i
n
g
)
N
u
mb
e
r
o
f
i
m
a
g
e
s
u
se
d
f
o
r
(
Te
s
t
i
n
g
)
To
ma
t
o
m
o
sa
i
c
v
i
r
u
s
(
To
M
V
)
1
1
1
0
9
1
0
5
4
6
0
2
0
0
To
ma
t
o
y
e
l
l
o
w
l
e
a
f
c
u
r
l
v
i
r
u
s (
TY
L
C
V
)
5
4
6
8
5
2
6
8
3
1
6
0
8
2
0
0
To
t
a
l
6
5
7
8
6
1
7
8
3
7
0
6
8
4
0
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
2
,
Feb
r
u
a
r
y
20
22
:
9
9
5
-
1
0
0
2
998
3.
M
E
T
H
O
D
Gen
er
ally
,
tr
a
n
s
f
er
lear
n
in
g
is
th
e
ap
p
r
o
ac
h
o
f
d
ee
p
lea
r
n
in
g
,
wh
ich
is
u
s
ed
f
o
r
d
e
ep
f
ea
tu
r
e
ex
tr
ac
tio
n
.
I
n
t
h
is
m
o
d
el,
we
i
n
clu
d
e
t
h
r
ee
p
r
e
-
tr
ain
e
d
m
o
d
e
l
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
I
n
th
is
wo
r
k
,
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
is
d
o
n
e
th
r
o
u
g
h
c
o
n
ca
ten
atin
g
two
f
u
lly
c
o
n
n
e
cted
lay
er
s
(
FC
L
)
an
d
f
r
o
m
th
e
f
u
lly
co
n
n
ec
te
d
lay
er
s
o
f
(
FC
6
an
d
FC
7
)
,
ex
tr
ac
ted
f
ea
tu
r
es
ar
e
f
ee
d
to
th
e
lin
ea
r
SVM
clas
s
if
ier
f
o
r
class
if
y
th
e
d
is
ea
s
e
d
u
r
in
g
tr
ain
in
g
th
e
m
o
d
el.
Pro
ce
s
s
in
v
o
lv
es
in
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
t
h
e
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
ap
p
lied
in
th
is
m
o
d
e
l,
in
v
o
lv
es
in
two
p
r
o
ce
s
s
th
at
ar
e
i
)
f
ea
t
u
r
e
ex
tr
ac
tio
n
an
d
ii
)
class
if
icatio
n
.
Featu
r
e
ex
tr
ac
tio
n
p
r
o
c
ess
es
ca
n
b
e
ca
r
r
ied
o
u
t
with
s
ev
er
al
co
n
v
o
l
u
tio
n
lay
er
s
ad
d
e
d
with
m
ax
-
p
o
o
lin
g
lay
er
s
an
d
o
u
tp
u
t
o
f
co
n
v
o
lu
tio
n
la
y
er
s
ar
e
co
n
n
ec
ted
to
R
eL
u
[
2
0
]
as
a
n
o
n
-
l
in
ea
r
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
e
co
n
v
o
lu
tio
n
la
y
er
in
v
o
lv
e
s
in
th
e
p
r
o
ce
s
s
ca
n
b
e
lear
n
ed
in
s
u
p
e
r
v
is
ed
o
r
u
n
s
u
p
er
v
is
ed
m
an
n
er
co
n
tain
s
a
s
et
o
f
f
ilter
s
.
I
t
ap
p
lies
th
e
co
n
v
o
lu
tio
n
o
p
er
atio
n
o
n
th
e
in
p
u
t
im
ag
e,
th
en
th
e
r
esu
lt
will
b
e
ap
p
lied
to
th
e
n
ex
t
lay
er
.
I
n
co
n
v
o
l
u
tio
n
lay
er
,
it
is
ca
lcu
lated
b
y
u
s
in
g
th
e
f
o
r
m
u
la
as g
i
v
en
in
(
1
)
.
=
+
2
−
+
1
(
1
)
W
h
er
e,
n
=im
ag
e
s
ize
h
av
in
g
h
eig
h
t
an
d
wid
th
,
p
is
ze
r
o
p
a
d
d
in
g
,
d
is
th
e
f
ilter
s
ize
an
d
s
is
th
e
s
ize
o
f
th
e
s
tr
id
e.
T
h
e
p
o
o
lin
g
lay
er
is
u
s
ed
to
r
ed
u
ce
th
e
d
im
en
s
io
n
s
o
f
th
e
f
ea
tu
r
e
m
ap
d
u
e
t
o
wh
ich
it
s
u
m
m
ar
izes
th
e
f
ea
tu
r
es
g
en
e
r
ated
b
y
c
o
n
v
o
lu
tio
n
lay
er
s
to
m
ak
es
th
e
m
o
d
el
m
o
r
e
r
o
b
u
s
t
.
Gen
er
ally
,
two
ty
p
es
o
f
poo
lin
g
a
r
e
tak
en
in
to
th
e
co
n
s
id
er
atio
n
th
at
ar
e
a
v
er
ag
e
a
n
d
m
ax
p
o
o
lin
g
.
I
n
ca
s
e
o
f
a
v
er
ag
e
p
o
llin
g
,
th
e
av
er
ag
e
elem
e
n
ts
ar
e
ca
lcu
la
ted
with
in
th
e
r
ec
ep
tiv
e
f
ield
to
s
en
d
t
h
e
o
u
tp
u
t
a
r
r
ay
.
B
u
t
in
m
a
x
p
o
o
lin
g
m
ax
im
u
m
n
u
m
b
er
o
f
elem
e
n
ts
s
elec
ted
f
r
o
m
t
h
e
r
e
g
io
n
i
n
t
h
e
f
ea
tu
r
e
m
ap
.
T
h
u
s
,
m
ax
p
o
o
lin
g
p
r
o
v
id
es
m
o
s
t
p
r
o
m
in
e
n
t f
ea
tu
r
es in
t
h
e
r
eg
i
o
n
.
I
n
th
is
wo
r
k
,
we
p
r
o
p
o
s
e
tr
an
s
f
er
lear
n
in
g
ap
p
r
o
ac
h
to
ex
tr
ac
t
th
e
d
ee
p
f
ea
tu
r
es
th
at
ar
e
t
h
e
ab
s
tr
ac
t
f
ea
tu
r
es.
Fro
m
th
e
r
elate
d
ca
s
e
s
tu
d
ies
o
f
a
m
eth
o
d
o
l
o
g
y
b
a
s
ed
o
n
d
ee
p
lear
n
in
g
Din
g
et
a
l
.
[
19
]
f
o
cu
s
ed
o
n
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
clas
s
if
icatio
n
.
Du
r
in
g
ex
p
er
im
en
t
atio
n
,
it
was
f
o
u
n
d
th
at
th
e
f
u
lly
co
n
n
ec
ted
lay
e
r
FC
6
is
p
r
o
v
id
in
g
h
i
g
h
er
ac
cu
r
ac
y
in
class
if
icatio
n
th
an
FC
7
.
Seth
y
et
a
l
.
[
21
]
,
d
escr
ib
e
d
an
in
-
d
ep
th
f
ea
t
u
r
e
-
b
ased
leaf
d
is
ea
s
e
id
en
tific
atio
n
m
o
d
el.
Fro
m
t
h
er
e
e
x
p
er
i
m
en
tal
s
tu
d
y
,
th
e
a
u
th
o
r
s
co
n
clu
d
ed
t
h
at
FC
6
an
d
FC
7
g
iv
e
b
etter
r
esu
lt
as
co
m
p
ar
ed
to
FC
8
.
I
n
t
h
e
p
r
o
p
o
s
ed
m
o
d
el,
we
h
av
e
tak
en
t
h
o
s
e
d
ee
p
f
ea
tu
r
es
a
n
d
d
o
th
e
co
n
ca
ten
atio
n
(
i.e
.
,
c
o
n
c
a
ten
atio
n
f
o
r
FC
6
an
d
FC
7
)
.
So
,
h
er
e
i
n
th
is
wo
r
k
th
e
d
ee
p
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
FC
6
an
d
FC
7
is
co
n
s
id
er
ed
.
Fro
m
FC
6
4
0
9
6
n
u
m
b
er
o
f
f
ea
tu
r
es
ar
e
e
x
tr
ac
ted
an
d
s
im
ilar
ly
f
r
o
m
FC
7
also
4
0
9
6
n
u
m
b
er
o
f
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
.
T
h
en
th
e
ex
tr
ac
t
ed
f
ea
tu
r
es
f
r
o
m
FC
6
an
d
FC
7
ar
e
f
u
s
ed
to
g
eth
er
to
en
h
an
ce
th
e
d
im
en
s
io
n
o
f
f
ea
tu
r
es.
T
h
e
f
ea
tu
r
es
f
u
s
io
n
p
r
o
ce
s
s
is
d
o
n
e
b
y
co
n
ca
ten
ati
o
n
th
e
two
f
ea
tu
r
es
i.e
,
FC
6
an
d
F
C
7
to
f
o
r
m
a
h
ig
h
d
im
en
s
io
n
al
f
ea
tu
r
e
.
Her
e
th
e
d
im
en
s
io
n
o
f
th
e
f
ea
tu
r
es
is
ad
d
ed
to
p
r
o
v
id
e
4096
+
4096
=
8192
.
W
ith
co
n
s
id
er
atio
n
o
f
th
is
n
u
m
b
er
o
f
f
ea
t
u
r
es
th
e
lin
er
SVM
class
if
y
in
g
th
r
e
e
v
ar
ieties
o
f
to
m
ato
d
is
ea
s
e
s
u
ch
as
t
o
m
ato
m
o
s
aic
v
ir
u
s
(
T
o
MV
)
,
t
o
m
ato
y
ello
w
leaf
cu
r
l
v
ir
u
s
(
T
YL
C
V)
,
an
d
to
m
ato
h
ea
lth
y.
Said
et
a
l
.
[
2
2
]
s
u
g
g
ested
f
o
r
im
ag
e
class
if
icat
io
n
in
m
ac
h
i
n
e
lear
n
in
g
m
o
s
t
p
r
ef
er
ab
le
cl
ass
if
ier
is
SVM.
T
h
is
cla
s
s
if
ier
s
ep
ar
at
es
th
e
d
atap
o
in
t
u
s
in
g
a
lin
e
o
f
h
y
p
e
r
p
lan
e
f
o
r
d
ataset
lab
ellin
g
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
f
o
r
to
m
ato
le
af
d
is
ea
s
e.
I
n
th
is
p
ap
er
lin
ea
r
-
SVM
is
u
s
ed
f
o
r
d
is
ea
s
e
class
if
ica
tio
n
b
ased
o
n
d
ee
p
f
ea
tu
r
es
o
f
p
r
e
-
tr
ain
e
d
m
o
d
el
Alex
n
et
.
“
T
o
tr
ain
th
e
S
VM
,
th
e
f
u
n
ctio
n
'
f
it
class
er
r
o
r
-
co
r
r
ec
tin
g
o
u
tp
u
t
co
d
es
(
f
itcec
o
c)
'
was
u
s
ed
.
T
h
is
f
u
n
ctio
n
r
etu
r
n
s
f
u
ll
tr
ain
ed
m
u
lticlas
s
er
r
o
r
-
co
r
r
ec
tin
g
o
u
tp
u
t
o
f
th
e
m
o
d
el.
T
h
e
f
u
n
ctio
n
‘
f
itcec
o
c
’
u
s
es
K(
K
-
1
)
/2
,
b
i
n
ar
y
SVM
m
o
d
e
l,
u
s
in
g
one
-
vs
-
all
co
d
in
g
d
e
s
ig
n
.
Her
e,
K
is
a
u
n
iq
u
e
class
lab
el.
B
ec
au
s
e
o
f
er
r
o
r
co
r
r
ec
ti
n
g
o
u
tp
u
t
co
d
es
an
d
one
-
vs
-
all
co
d
in
g
d
e
s
ig
n
o
f
SVM,
th
e
p
er
f
o
r
m
an
ce
o
f
class
if
icatio
n
m
o
d
els
was
en
h
an
ce
d
[
21
]
.
”
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
in
v
o
lv
e
d
th
e
f
o
llo
win
g
s
tep
s
ar
e
g
iv
en
i
n
Alg
o
r
ith
m
1
.
Alg
o
r
ith
m
1
:
Step
-
I: Input: Diseased leaf images.
Step
-
II
:
Pr
e
-
processing:
Resize
Images
to
22
7x227x3
dimensions
Step
-
III: Image augmentation
Step
-
IV: Concatenate FC6 and FC7
layers of the CNN model.
Step
-
V: Classification using linear SVM
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
r
esear
ch
m
o
d
el,
C
NN
b
ased
tr
an
s
f
er
lear
n
in
g
is
u
s
ed
to
id
en
tify
to
m
ato
leaf
d
is
ea
s
e
with
g
iv
in
g
im
p
o
r
ta
n
t
to
th
e
ef
f
ici
en
cy
o
f
th
e
m
o
d
el
in
class
if
icatio
n
an
d
ex
ec
u
ti
o
n
tim
e
ta
k
en
b
y
th
e
m
o
d
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
tern
et
o
f th
in
g
s
a
n
d
mu
lti
-
cl
a
s
s
d
ee
p
fea
tu
r
e
-
fu
s
io
n
b
a
s
ed
cla
s
s
ifica
tio
n
o
f to
ma
to
lea
f …
(
R
in
a
Ma
h
a
ku
d
)
999
MA
T
L
AB
2
0
2
0
a
with
ad
d
o
n
as
d
ee
p
lean
in
g
is
u
s
ed
f
o
r
ex
p
er
im
e
n
tal
s
tu
d
y
with
th
e
s
y
s
tem
h
av
in
g
,
co
n
f
ig
u
r
atio
n
I
n
tel
i7
9
th
g
en
er
atio
n
p
r
o
ce
s
s
o
r
,
1
6
GB
DD
R
4
R
AM
,
2
5
0
GB
SS
D
&
4
T
B
HDD,
NVI
DA
1
0
5
0
T
i
4
GB
DDR5
GPU
wit
h
NVI
DA
cu
d
a_
1
1
.
1
.
0
_
4
5
6
.
4
3
_
win
1
0
.
T
h
e
class
if
icatio
n
m
o
d
el'
s
p
er
f
o
r
m
an
ce
is
ev
alu
ated
th
r
o
u
g
h
ac
cu
r
ac
y
.
T
o
g
et
m
ax
im
u
m
ac
cu
r
ac
y
s
ev
er
al
iter
atio
n
s
to
b
e
p
er
f
o
r
m
e
d
an
d
s
o
m
e
tr
ain
in
g
tim
e
wi
ll
b
e
r
e
q
u
ir
e
d
f
o
r
th
e
p
e
r
f
o
r
m
an
ce
.
I
n
th
is
tr
an
s
f
er
lear
n
in
g
a
p
p
r
o
ac
h
,
th
e
ex
p
e
r
im
en
t
is
ca
r
r
ied
o
u
t in
two
p
h
ases
i.e
.
tr
ain
in
g
p
h
ase
an
d
test
in
g
p
h
as
e.
Fro
m
s
u
b
s
ec
tio
n
3
.
1
,
it
was
n
o
ticed
th
at
p
r
o
p
o
s
ed
m
o
d
el
p
e
r
f
o
r
m
s
well
in
th
e
FC
6
a
n
d
F
C
7
lay
er
f
o
r
c
lass
if
icatio
n
.
Fro
m
th
is
o
b
s
er
v
atio
n
we
in
clu
d
e
d
th
o
s
e
d
ee
p
f
ea
tu
r
es
an
d
c
o
n
ca
ten
ate
th
ese
f
u
lly
co
n
n
ec
ted
lay
er
s
to
p
er
f
o
r
m
b
etter
r
esu
lts
.
I
n
th
is
s
ec
tio
n
,
we
ex
p
er
im
e
n
ted
a
tr
an
s
f
er
lear
n
in
g
p
r
e
-
tr
a
in
ed
m
o
d
els
b
ase
d
o
n
C
NN.
T
h
e
h
y
p
er
p
ar
am
et
er
s
u
s
ed
in
tr
an
s
f
er
lear
n
in
g
m
eth
o
d
s
ar
e
s
to
ch
asti
c
g
r
a
d
ie
n
t
d
escen
t
(
SGD)
,
0
.
0
0
1
f
o
r
th
e
in
itial
lear
n
in
g
r
ate,
5
0
f
o
r
th
e
n
u
m
b
er
o
f
ep
o
ch
s
,
0
.
9
f
o
r
m
o
m
en
tu
m
,
0
.
2
f
o
r
d
r
o
p
o
u
t,
an
d
1
6
f
o
r
th
e
m
in
i
b
atch
s
ca
le.
T
h
e
m
in
ib
atch
s
ize
ca
n
b
e
8
,
1
6
,
3
2
,
6
4
,
1
2
8
o
r
2
5
6
,
d
e
p
e
n
d
i
n
g
o
n
th
e
GPU'
s
ab
ili
ty
.
T
h
e
s
im
u
lated
r
esu
lt o
f
p
r
o
p
o
s
ed
(
ASFHC
)
m
o
d
el,
VGG
1
6
,
VGG
1
9
class
if
icatio
n
m
o
d
el’
s
is
r
ep
r
esen
ted
b
y
co
n
f
u
s
io
n
m
atr
i
x
g
iv
en
in
Fi
g
u
r
e
3
.
Fig
u
r
e
3
(
a)
s
h
o
ws
th
e
b
etter
class
if
icatio
n
r
esu
lt
in
ca
m
p
ar
is
io
n
to
Fig
u
r
e
s
3
(
b
)
a
n
d
(
c
).
(
a)
(
b
)
(
c)
Fig
u
r
e
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
th
e
(
a)
ASFHC
,
(
b
)
VGG
1
6
,
an
d
(
c
)
VGG
1
9
I
n
th
is
ab
o
v
e
co
n
f
u
s
io
n
m
atr
ix
,
ea
ch
r
o
ws
r
e
p
r
esen
t
th
e
ac
t
u
al
class
an
d
ea
c
h
co
l
u
m
n
r
e
p
r
esen
t
th
e
p
r
ed
ictio
n
class
wh
er
ea
s
d
iag
o
n
al
v
alu
es
r
e
p
r
esen
t
ea
ch
leaf
class
es
co
r
r
ec
tly
ca
lcu
lated
s
h
o
wn
in
g
r
ee
n
co
lo
r
o
th
er
v
alu
es sh
o
w
n
in
p
i
n
k
co
l
o
r
m
is
class
if
ied
.
I
n
th
e
p
r
o
p
o
s
ed
ASFHC
m
o
d
el,
f
ir
s
t r
o
w
th
e
co
n
f
u
s
io
n
m
atr
ix
co
n
tain
s
to
tal
1
0
9
4
i
n
s
tan
ts
o
u
t
o
f
w
h
ich
1
0
9
2
in
s
tan
ts
co
r
r
ec
tly
class
if
ied
as
T
YL
C
V
an
d
o
n
ly
2
in
s
tan
ts
wer
e
wr
o
n
g
ly
class
if
ied
as
T
o
MV
is
s
h
o
wn
as
er
r
o
r
.
I
n
s
ec
o
n
d
r
o
w
2
1
9
co
r
r
ec
tly
class
if
ie
d
as
T
o
MV
a
n
d
3
in
s
tan
ts
wer
e
m
is
clas
s
if
ied
a
s
T
YL
C
V.
I
n
th
ir
d
r
o
w
all
1
6
in
s
tan
ts
ar
e
class
if
ied
as
h
ea
lth
y
.
T
h
u
s
,
th
e
p
er
f
o
r
m
an
ce
m
ea
s
u
r
es
o
f
to
m
ato
d
is
ea
s
e
p
lan
t a
r
e
g
iv
e
n
in
T
ab
le
2
.
T
ab
le
2
.
Me
asu
r
em
e
n
t p
ar
am
e
ter
s
o
f
C
NN
m
o
d
els with
d
ee
p
f
ea
tu
r
es
N
e
t
w
o
r
k
A
S
F
H
C
(
p
r
o
p
o
se
d
m
o
d
e
l
)
V
G
G
1
6
V
G
G
1
9
D
i
sea
s
e
C
l
a
s
s
-
1
C
l
a
s
s
-
2
C
l
a
s
s
-
3
C
l
a
s
s
-
1
C
l
a
s
s
-
2
C
l
a
s
s
-
3
C
l
a
s
s
-
1
C
l
a
s
s
-
2
C
l
a
s
s
-
3
A
c
c
u
r
a
c
y
o
f
si
n
g
l
e
0
.
9
9
8
1
7
0
.
9
8
6
4
9
1
0
.
9
9
9
0
9
0
.
9
5
9
4
6
1
1
0
.
9
5
9
4
6
1
Er
r
o
r
o
f
si
n
g
l
e
0
.
0
0
1
8
2
8
2
0
.
0
1
3
5
1
4
0
0
.
0
0
0
9
1
4
1
0
.
0
4
0
5
4
1
0
0
0
.
0
4
0
5
4
1
0
A
c
c
u
r
a
c
y
i
n
t
o
t
a
l
0
.
8
1
9
8
2
0
.
1
6
4
4
1
0
.
0
1
2
0
1
2
0
.
8
2
0
5
7
0
.
1
5
9
9
1
0
.
0
1
2
0
1
2
0
.
8
2
1
3
2
0
.
1
5
9
9
1
0
.
0
1
2
0
1
2
Er
r
o
r
i
n
t
o
t
a
l
0
.
0
0
2
2
5
2
3
0
.
0
0
1
5
0
1
5
0
0
.
0
0
6
7
5
6
8
0
.
0
0
0
7
5
0
8
0
0
.
0
0
6
7
5
6
8
0
0
S
e
n
s
i
t
i
v
i
t
y
0
.
9
9
8
1
7
0
.
9
8
6
4
9
1
0
.
9
9
9
0
9
0
.
9
5
9
4
6
1
1
0
.
9
5
9
4
6
1
S
p
e
c
i
f
i
c
i
t
y
0
.
9
8
7
3
9
0
.
9
9
8
2
1
0
.
9
6
2
1
8
0
.
9
9
9
1
1
0
.
9
6
2
1
8
1
1
P
r
e
c
i
s
i
o
n
0
.
9
9
7
2
6
0
.
9
9
0
9
5
1
0
.
9
9
1
8
3
0
.
9
9
5
3
3
1
0
.
9
9
1
8
4
1
1
F
a
l
se
p
o
s
i
t
i
v
e
r
a
t
e
0
.
0
1
2
6
0
5
0
.
0
0
1
8
0
1
8
0
0
.
0
3
7
8
1
5
0
.
0
0
0
9
0
0
9
0
0
.
0
3
7
8
1
5
0
0
F
1
_
s
c
o
r
e
0
.
9
9
7
7
2
0
.
9
8
8
7
1
1
0
.
9
9
5
4
5
0
.
9
7
7
0
6
1
0
.
9
9
5
9
0
.
9
7
9
3
1
1
*
To
mat
o
_
mo
s
a
i
c
_
v
i
r
u
s=
>
c
l
a
ss1
,
T
o
mat
o
_
Y
e
l
l
o
w
_
Le
a
f
_
C
u
r
l
_
V
i
r
u
s
=
>
c
l
a
ss
-
2
,
To
m
a
t
o
_
h
e
a
l
t
h
y
=
>
c
l
a
ss
-
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
2
,
Feb
r
u
a
r
y
20
22
:
9
9
5
-
1
0
0
2
1000
Fro
m
T
ab
le
2
th
e
p
er
f
o
r
m
an
c
e
m
ea
s
u
r
in
g
p
a
r
am
eter
s
o
f
ea
c
h
d
is
ea
s
e
in
clu
d
in
g
h
ea
lth
y
to
m
ato
p
lan
t
was
in
d
icate
d
.
T
h
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
n
o
t
o
n
ly
id
en
tifie
d
th
e
d
is
ea
s
e
b
u
t
also
d
is
tin
g
u
is
h
e
s
th
e
s
p
ec
if
ic
t
y
p
es
o
f
d
is
ea
s
es.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
p
r
o
v
id
es o
v
er
all
p
er
f
o
r
m
a
n
ce
is
g
iv
en
in
T
ab
le
3
.
T
ab
le
3
.
O
v
e
r
all
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
N
e
t
w
o
r
k
A
c
c
u
r
a
c
y
Er
r
o
r
S
e
n
s
i
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
P
r
e
c
i
s
i
o
n
FPR
F
1
_
s
c
o
r
e
Ex
e
c
u
t
i
o
n
t
i
m
e
(
se
c
)
A
S
F
H
C
(
p
r
o
p
o
se
d
m
o
d
e
l
)
0
.
9
9
6
2
0
.
0
0
3
8
0
.
9
9
4
9
0
.
9
9
5
2
0
.
9
9
6
1
0
.
0
0
4
8
0
.
9
9
5
5
46
V
G
G
1
6
+
Li
n
e
a
r
S
V
M
0
.
9
9
2
5
0
.
0
0
7
5
0
.
9
8
6
2
0
.
9
8
7
1
0
.
9
9
5
7
0
.
0
1
2
9
0
.
9
9
0
8
1
7
5
V
G
G
1
9
+
Li
n
e
a
r
S
V
M
0
.
9
9
3
2
0
.
0
0
6
8
0
.
9
8
6
5
0
.
9
8
7
4
0
.
9
9
7
3
0
.
0
1
2
6
0
.
9
9
1
7
2
3
7
Fro
m
T
ab
le
3
,
it
was
o
b
s
er
v
e
d
th
at
b
y
u
s
in
g
f
u
s
ed
f
ea
t
u
r
es
o
f
FC
6
a
n
d
FC
7
,
t
h
e
ASFHC
ac
h
iev
es
h
ig
h
est
ac
cu
r
ac
y
wh
ich
is
in
d
icate
s
in
b
o
ld
.
All
th
e
m
ea
s
u
r
in
g
p
ar
a
m
eter
s
ar
e
o
b
tain
ed
th
e
m
ax
im
u
m
v
al
u
e.
B
u
t
as
th
is
m
o
d
el
is
im
p
lem
en
ted
in
I
o
T
d
o
m
ain
,
th
e
r
esp
o
n
s
e
o
f
th
e
m
o
d
el
s
h
o
u
l
d
b
e
f
a
s
ter
.
On
th
e
b
asis
o
f
ex
ec
u
tio
n
tim
e,
it
was
o
b
s
er
v
ed
th
at
ASFH
C
m
o
d
el
p
r
o
v
id
es
th
e
r
esu
lt
in
ju
s
t
4
6
s
ec
.
wh
er
ea
s
VGG
1
6
tak
es
1
7
5
s
ec
an
d
VGG
1
9
tak
es
2
3
7
s
ec
.
Hen
ce
,
th
e
ASFH
C
m
o
d
el
with
lin
ea
r
SVM
i
s
th
e
b
est
clas
s
if
ier
m
o
d
el
ca
n
b
e
co
n
s
id
er
ed
in
I
o
T
d
o
m
ain
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
c
o
m
p
ar
es
th
e
ac
cu
r
ac
y
with
ex
is
tin
g
m
o
d
el
ar
e
g
iv
e
n
in
T
ab
le
4
.
F
r
o
m
th
e
T
ab
le
4
it
ca
n
b
e
s
u
m
m
ar
ized
t
h
at
th
e
p
lan
t
v
i
llag
e
d
ataset
was
u
s
ed
b
y
m
o
s
t
o
f
th
e
au
th
o
r
s
.
I
t
co
n
tain
s
th
o
u
s
an
d
s
o
f
to
m
ato
leaf
im
ag
es.
Mo
s
t
o
f
th
e
ab
o
v
e
r
esear
ch
ap
p
r
o
ac
h
in
clu
d
es
SVM
class
if
ier
to
d
etec
t
th
e
d
is
ea
s
e
s
.
B
u
t
o
n
ly
Seth
y
et
a
l.
[
2
1
]
ab
le
to
p
r
o
v
id
e
c
o
m
p
u
tatio
n
tim
e
as
4
8
.
6
5
s
ec
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
i.e
.
,
Alex
SVM
f
u
s
ed
h
y
b
r
id
class
if
icatio
n
(
ASFHC
)
with
f
u
s
ed
f
ea
tu
r
es
(
FC
6
&
FC
7
)
an
d
lin
ea
r
SVM
is
th
e
ch
o
s
en
class
if
ier
to
class
if
y
an
d
id
en
ti
f
y
th
e
to
m
ato
leaf
d
is
ea
s
e
with
an
ac
cu
r
ac
y
o
f
9
9
.
6
2
%
in
co
m
p
u
tatio
n
tim
e
4
6
s
ec
wh
ich
ca
n
b
e
im
p
lem
en
ted
I
o
T
ap
p
licatio
n
d
o
m
ain
.
I
n
th
is
p
r
o
p
o
s
ed
m
o
d
el
m
ay
h
av
e
lim
itatio
n
s
,
th
at
it
will
p
r
o
v
id
es
m
o
r
e
ac
cu
r
ate
r
esu
lt
in
co
lo
r
im
ag
es
r
ath
er
th
an
g
r
a
y
s
ca
le
im
ag
es
b
ec
au
s
e
th
is
m
o
d
el
im
p
lem
en
ted
in
I
o
T
d
o
m
ain
wh
ich
co
llect
th
e
r
ea
l
tim
e
im
ag
es
at
n
o
r
m
al
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
v
ar
io
u
s
m
eth
o
d
s
with
p
r
o
p
o
s
ed
m
o
d
el
A
u
t
h
o
r
s
D
a
t
a
s
e
t
M
e
t
h
o
d
o
l
o
g
y
A
c
c
u
r
a
c
y
C
o
m
p
u
t
a
t
i
o
n
t
i
m
e
(
S
e
c
)
V
e
r
ma
e
t
a
l
.
[
1
4
]
P
l
a
n
t
v
i
l
l
a
g
e
d
a
t
a
s
e
t
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
(
i
.
e
.
,
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
n
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
)
+
mu
l
t
i
c
l
a
ss SV
M
9
3
.
4
%
--
S
e
t
h
y
e
t
a
l
.
[
2
1
]
h
t
t
p
:
/
/
b
c
c
h
.
a
h
n
w
.
g
o
v
.
c
n
/
R
i
g
h
t
.
a
sp
x
D
e
e
p
Le
a
r
n
i
n
g
+
S
V
M
9
7
.
6
2
%
4
8
.
6
5
B
r
a
h
i
mi
e
t
a
l
.
[
2
3
]
P
l
a
n
t
v
i
l
l
a
g
e
d
a
t
a
s
e
t
Pre
-
p
r
o
c
e
ssi
n
g
+
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
+
S
V
M
o
r
R
a
n
d
o
m F
o
r
e
s
t
9
8
.
6
6
0
%
N
o
t
S
p
e
c
i
f
i
e
d
b
u
t
w
a
n
t
t
o
r
e
d
u
c
e
c
o
m
p
u
t
a
t
i
o
n
t
i
m
e
D
u
r
mu
s
e
t
a
l
.
[
2
4
]
P
l
a
n
t
v
i
l
l
a
g
e
d
a
t
a
s
e
t
C
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
A
l
e
x
N
e
t
a
n
d
S
q
u
e
e
z
e
N
e
t
9
5
.
6
5
%
--
H
o
n
g
e
t
a
l
.
[
2
5
]
P
l
a
n
t
v
i
l
l
a
g
e
d
a
t
a
s
e
t
D
e
e
p
C
N
N
m
o
d
e
l
9
7
.
1
0
%
--
A
l
t
u
n
t
a
s
e
t
a
l
.
[
2
6
]
P
l
a
n
t
v
i
l
l
a
g
e
d
a
t
a
s
e
t
D
e
e
p
C
N
N
m
o
d
e
l
9
6
.
9
9
%
--
A
S
F
H
C
(
P
r
o
p
o
se
d
M
o
d
e
l
)
P
l
a
n
t
v
i
l
l
a
g
e
d
a
t
a
s
e
t
D
e
e
p
C
N
N
+
l
i
n
e
a
r
S
V
M
9
9
.
6
2
%
46
5.
CO
NCLU
SI
O
N
T
h
is
p
r
o
p
o
s
ed
m
o
d
el
f
o
cu
s
es
o
n
d
ee
p
-
C
NN
tr
an
s
f
er
lear
n
in
g
ap
p
r
o
ac
h
t
o
id
en
tify
to
m
ato
leaf
d
is
ea
s
e
with
h
ig
h
ac
cu
r
ac
y
o
f
9
9
.
6
2
%.
I
n
th
is
cu
r
r
en
t
r
esear
ch
,
we
ev
alu
ate
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
m
o
d
e
l
with
lin
ea
r
SVM.
T
h
e
m
ai
n
aim
o
f
t
h
is
r
esear
ch
wo
r
k
i
s
to
au
to
m
ate
th
e
d
is
ea
s
e
id
en
tific
atio
n
as
it
is
im
p
lem
en
ted
in
I
o
T
d
o
m
ai
n
.
Her
e,
we
ar
e
av
o
i
d
in
g
o
v
e
r
f
itti
n
g
b
y
c
o
n
ca
ten
atin
g
FC
6
an
d
FC
7
o
f
t
h
e
ar
ch
itectu
r
e
d
u
e
to
wh
ich
all
th
e
f
ea
tu
r
es
ar
e
g
ettin
g
co
n
ca
ten
ated
to
p
r
o
v
id
e
b
est
ex
ec
u
t
io
n
tim
e
ju
s
t
at
4
6
s
ec
.
T
h
ese
n
etwo
r
k
m
o
d
els
ar
e
ev
alu
ated
with
o
th
er
e
x
is
tin
g
m
o
d
els
o
u
t
o
f
wh
ich
ASFHC
m
o
d
el
p
er
f
o
r
m
s
b
est
ex
ec
u
tio
n
tim
e
as
co
m
p
a
r
ed
t
o
o
th
er
m
o
d
els,
wh
ich
f
its
to
b
e
im
p
lem
en
te
d
in
I
o
T
d
o
m
ain
.
T
h
is
r
esear
ch
ca
n
b
e
f
u
r
th
e
r
ca
r
r
ied
f
o
r
war
d
with
a
co
m
p
ar
ativ
e
a
n
aly
s
is
with
o
th
er
e
x
is
tin
g
m
eth
o
d
s
with
m
o
r
e
v
ar
iety
o
f
to
m
ato
d
is
ea
s
es to
ac
h
iev
e
b
et
ter
p
er
f
o
r
m
an
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
tern
et
o
f th
in
g
s
a
n
d
mu
lti
-
cl
a
s
s
d
ee
p
fea
tu
r
e
-
fu
s
io
n
b
a
s
ed
cla
s
s
ifica
tio
n
o
f to
ma
to
lea
f …
(
R
in
a
Ma
h
a
ku
d
)
1001
RE
F
E
R
E
NC
E
S
[
1
]
To
ma
t
o
n
e
w
s,
WPT
C
C
r
o
p
s
i
t
u
a
t
i
o
n
a
s
o
f
3
J
u
l
y
2
0
2
0
,
2
0
2
0
.
A
c
c
e
ss
e
d
:
M
a
r
.
2
7
,
2
0
2
0
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
w
w
w
.
t
o
ma
t
o
n
e
w
s
.
c
o
m/
e
n
/
w
p
t
c
-
c
r
o
p
-
s
i
t
u
a
t
i
o
n
-
as
-
of
-
3
-
j
u
l
y
-
2
0
2
0
_
2
_
1
0
7
2
.
h
t
ml
[
2
]
T
.
R
.
G
a
d
e
k
a
l
l
u
e
t
a
l
.
,
“
A
n
o
v
e
l
P
C
A
–
w
h
a
l
e
o
p
t
i
m
i
z
a
t
i
o
n
-
b
a
se
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
t
o
ma
t
o
p
l
a
n
t
d
i
s
e
a
se
s
u
si
n
g
G
P
U
,”
J
o
u
r
n
a
l
o
f
Re
a
l
-
T
i
m
e
I
m
a
g
e
Pro
c
e
ss
i
n
g
,
v
o
l
.
1
8
,
p
p
.
1
3
8
3
-
1
3
9
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
5
5
4
-
0
2
0
-
0
0
9
8
7
-
8
.
[
3
]
G
.
G
e
e
t
h
a
,
S
.
S
a
mu
n
d
e
sw
a
r
i
,
G
.
S
a
r
a
n
y
a
,
K
.
M
e
e
n
a
k
s
h
i
,
a
n
d
M
.
N
i
t
h
y
a
,
“
P
l
a
n
t
Le
a
f
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
S
y
s
t
e
m
U
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
,”
J
o
u
r
n
a
l
o
f
Ph
y
s
i
c
s:
C
o
n
f
e
r
e
n
c
e
S
e
ri
e
s
,
v
o
l
.
1
7
1
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
7
1
2
/
1
/
0
1
2
0
1
2
.
[
4
]
I
.
A
h
mad
,
M
.
H
a
m
i
d
,
S
.
Y
o
u
saf,
S
.
T
.
S
h
a
h
,
a
n
d
M
.
O
.
A
h
ma
d
,
“
O
p
t
i
mi
z
i
n
g
p
r
e
t
r
a
i
n
e
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
t
o
ma
t
o
l
e
a
f
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
,
”
C
o
m
p
l
e
x
i
t
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
0
/
8
8
1
2
0
1
9
.
[
5
]
P
.
Tm
,
A
.
P
r
a
n
a
t
h
i
,
K
.
S
a
i
A
sh
r
i
t
h
a
,
N
.
B
.
C
h
i
t
t
a
r
a
g
i
,
a
n
d
S
.
G
.
K
o
o
l
a
g
u
d
i
,
“
To
m
a
t
o
Le
a
f
D
i
sea
s
e
D
e
t
e
c
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
s,
”
2
0
1
8
E
l
e
v
e
n
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
C
o
n
t
e
m
p
o
ra
ry
C
o
m
p
u
t
i
n
g
(
I
C
3
)
,
2
0
1
8
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
.
2
0
1
8
.
8
5
3
0
5
3
2
.
[
6
]
S
.
V
e
r
ma,
A
.
C
h
u
g
,
a
n
d
A
.
P
.
S
i
n
g
h
,
“
P
r
e
d
i
c
t
i
o
n
M
o
d
e
l
s
f
o
r
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
D
i
a
g
n
o
si
s
o
f
T
o
m
a
t
o
P
l
a
n
t
D
i
sea
s
e
s,”
2
0
1
8
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
s
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
I
C
A
C
C
I
)
,
2
0
1
8
,
p
p
.
1
5
5
7
-
1
5
6
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
C
I
.
2
0
1
8
.
8
5
5
4
8
4
2
.
[
7
]
L.
M
.
G
r
i
f
f
e
l
,
D
.
D
e
l
p
a
r
t
e
,
a
n
d
J.
E
d
w
a
r
d
s
,
“
U
si
n
g
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
o
d
i
f
f
e
r
e
n
t
i
a
t
e
s
p
e
c
t
r
a
l
si
g
n
a
t
u
r
e
s
o
f
p
o
t
a
t
o
p
l
a
n
t
s
i
n
f
e
c
t
e
d
w
i
t
h
P
o
t
a
t
o
V
i
r
u
s
Y
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
e
c
t
r
o
n
i
c
s
i
n
Ag
r
i
c
u
l
t
u
re,
v
o
l
.
1
5
3
,
p
p
.
318
-
3
2
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
1
8
.
0
8
.
0
2
.
[
8
]
D
.
K
.
B
e
h
e
r
a
,
M
.
D
a
s,
S
.
S
w
e
t
a
n
i
sh
a
,
a
n
d
P
.
K
.
S
e
t
h
y
,
“
H
y
b
r
i
d
m
o
d
e
l
f
o
r
mo
v
i
e
r
e
c
o
m
me
n
d
a
t
i
o
n
sy
s
t
e
m
u
si
n
g
c
o
n
t
e
n
t
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
a
n
d
r
e
st
r
i
c
t
e
d
b
o
l
t
z
m
a
n
n
m
a
c
h
i
n
e
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
,
v
o
l
.
2
3
,
n
o
.
1
,
pp
.
4
4
5
-
4
5
2
,
2
0
2
1
,
doi
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
2
3
.
i
1
.
p
p
4
4
5
-
4
5
2
.
[
9
]
K
.
G
a
n
g
a
d
h
a
r
a
n
,
G
.
R
.
N
.
K
u
m
a
r
i
,
D
.
D
h
a
n
a
s
e
k
a
r
a
n
,
a
n
d
K
.
M
a
l
a
t
h
i
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
v
a
r
i
o
u
s
p
e
st
a
t
t
a
c
k
s
a
n
d
i
n
f
e
c
t
i
o
n
o
n
p
l
a
n
t
s
u
s
i
n
g
R
B
P
N
w
i
t
h
G
A
b
a
se
d
P
S
O
a
l
g
o
r
i
t
h
m
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
1
2
7
8
-
1
2
8
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
0
.
i
3
.
p
p
1
2
7
8
-
1
2
8
8
.
[
1
0
]
S
.
S
e
n
g
u
p
t
a
a
n
d
A
.
K
.
D
a
s
,
“
P
a
r
t
i
c
l
e
S
w
a
r
m
O
p
t
i
m
i
z
a
t
i
o
n
b
a
se
d
i
n
c
r
e
men
t
a
l
c
l
a
ss
i
f
i
e
r
d
e
si
g
n
f
o
r
r
i
c
e
d
i
s
e
a
se
p
r
e
d
i
c
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
4
0
,
p
p
.
4
4
3
-
4
5
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
1
7
.
0
6
.
0
2
4
.
[
1
1
]
J.
K
o
d
o
v
s
k
y
,
J.
F
r
i
d
r
i
c
h
,
a
n
d
V
.
H
o
l
u
b
,
“
En
sem
b
l
e
C
l
a
ss
i
f
i
e
r
s
f
o
r
S
t
e
g
a
n
a
l
y
s
i
s
o
f
D
i
g
i
t
a
l
M
e
d
i
a
,
”
i
n
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
f
o
rm
a
t
i
o
n
F
o
re
n
si
c
s
a
n
d
S
e
c
u
ri
t
y
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
4
3
2
-
4
4
4
,
A
p
r
i
l
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
F
S
.
2
0
1
1
.
2
1
7
5
9
1
9
.
[
1
2
]
K
.
G
o
l
h
a
n
i
,
S
.
K
.
B
a
l
a
su
n
d
r
a
m,
G
.
V
a
d
a
m
a
l
a
i
,
a
n
d
B
.
P
r
a
d
h
a
n
,
“
A
r
e
v
i
e
w
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
s
i
n
p
l
a
n
t
d
i
sea
se
d
e
t
e
c
t
i
o
n
u
s
i
n
g
h
y
p
e
r
s
p
e
c
t
r
a
l
d
a
t
a
,”
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
5
,
n
o
.
3
,
p
p
.
354
-
3
7
1
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
p
a
.
2
0
1
8
.
0
5
.
0
0
2
.
[
1
3
]
M
.
A
g
a
r
w
a
l
,
S
.
Kr
.
G
u
p
t
a
,
a
n
d
K
.
K
.
B
i
sw
a
s
,
“
D
e
v
e
l
o
p
me
n
t
o
f
Ef
f
i
c
i
e
n
t
C
N
N
m
o
d
e
l
f
o
r
T
o
ma
t
o
c
r
o
p
d
i
s
e
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
S
u
s
t
a
i
n
a
b
l
e
C
o
m
p
u
t
i
n
g
:
I
n
f
o
rm
a
t
i
c
s
a
n
d
S
y
st
e
m
s
,
v
o
l
.
2
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
u
sc
o
m.
2
0
2
0
.
1
0
0
4
0
7
.
[
1
4
]
S
.
V
e
r
ma
,
A
.
C
h
u
g
,
a
n
d
A
.
P
.
S
i
n
g
h
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
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
e
v
a
l
u
a
t
i
o
n
o
f
d
i
se
a
se
s
e
v
e
r
i
t
y
i
n
t
o
m
a
t
o
p
l
a
n
t
,
”
J
o
u
rn
a
l
o
f
D
i
s
c
ret
e
M
a
t
h
e
m
a
t
i
c
a
l
S
c
i
e
n
c
e
s
a
n
d
C
ry
p
t
o
g
r
a
p
h
y
,
v
o
l
.
2
3
,
n
o
.
1,
p
p
.
2
7
3
-
2
8
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
9
7
2
0
5
2
9
.
2
0
2
0
.
1
7
2
1
8
9
0
.
[
1
5
]
B
.
A
.
M
.
A
s
h
q
a
r
a
n
d
S
.
S
.
A
b
u
-
N
a
s
e
r
,
“
I
mag
e
-
b
a
se
d
t
o
ma
t
o
l
e
a
v
e
s
d
i
se
a
se
s
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ac
a
d
e
m
i
c
E
n
g
i
n
e
e
ri
n
g
Re
s
e
a
rc
h
(
I
J
AER)
,
v
o
l
.
2
,
n
o
.
1
2
,
p
p
.
10
-
1
6
,
2
0
1
8
.
[
1
6
]
R
.
G
.
d
e
Lu
n
a
,
E
.
P
.
D
a
d
i
o
s,
a
n
d
A
.
A
.
B
a
n
d
a
l
a
,
“
A
u
t
o
m
a
t
e
d
I
mag
e
C
a
p
t
u
r
i
n
g
S
y
s
t
e
m
f
o
r
D
e
e
p
Le
a
r
n
i
n
g
-
b
a
s
e
d
To
mat
o
P
l
a
n
t
Le
a
f
D
i
s
e
a
s
e
D
e
t
e
c
t
i
o
n
a
n
d
R
e
c
o
g
n
i
t
i
o
n
,
”
T
EN
C
O
N
2
0
1
8
-
2
0
1
8
I
EEE
Re
g
i
o
n
1
0
C
o
n
f
e
re
n
c
e
,
2
0
1
8
,
p
p
.
1
4
1
4
-
1
4
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TEN
C
O
N
.
2
0
1
8
.
8
6
5
0
0
8
8
.
[
1
7
]
K
.
P
.
F
e
r
e
n
t
i
n
o
s
,
“
D
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
p
l
a
n
t
d
i
s
e
a
s
e
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
r
o
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
r
e
,
v
o
l
.
1
4
5
,
p
p
.
3
11
-
3
1
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
1
8
.
0
1
.
0
0
9
.
[
1
8
]
A
.
E.
H
a
ssa
n
i
e
n
,
T
.
G
a
b
e
r
,
U
.
M
o
k
h
t
a
r
,
a
n
d
H
.
H
e
f
n
y
,
“
A
n
i
m
p
r
o
v
e
d
mo
t
h
f
l
a
me
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
r
o
u
g
h
se
t
s
f
o
r
t
o
m
a
t
o
d
i
se
a
ses
d
e
t
e
c
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
ri
c
u
l
t
u
re
,
v
o
l
.
1
3
6
,
p
p
.
86
-
9
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
1
7
.
0
2
.
0
2
6
.
[
1
9
]
L
.
D
i
n
g
,
H
.
Li
,
C
.
H
u
,
W
.
Zh
a
n
g
,
a
n
d
S
.
W
a
n
g
,
“
A
l
e
x
n
e
t
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
m
u
l
t
i
-
k
e
r
n
e
l
l
e
a
r
n
i
n
g
f
o
r
o
b
j
e
c
t
-
o
r
i
e
n
t
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
,”
I
n
t
.
Ar
c
h
.
P
h
o
t
o
g
r
a
m
m
.
Re
m
o
t
e
S
e
n
s.
S
p
a
t
.
I
n
f
.
S
c
i
,
p
p
.
2
7
7
-
2
8
1
,
2
0
1
8
,
d
o
i
:
1
0
.
5
1
9
4
/
i
s
p
r
s
-
a
r
c
h
i
v
e
s
-
X
LI
I
-
3
-
277
-
2
0
1
8
.
[
2
0
]
A
.
A
.
A
b
b
o
o
d
,
Q
.
M
.
S
h
a
l
l
a
l
,
a
n
d
M
.
A
.
F
a
d
h
e
l
,
“
A
u
t
o
mat
e
d
b
r
a
i
n
t
u
m
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
v
a
r
i
o
u
s
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
:
a
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
2
,
n
o
.
1
,
p
p
.
252
-
2
5
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
2
.
i
1
.
p
p
2
5
2
-
2
5
9
.
[
2
1
]
P
.
K
.
S
e
t
h
y
,
N
.
K
.
B
a
r
p
a
n
d
a
,
A
.
K
.
R
a
t
h
,
a
n
d
S
.
K
.
B
e
h
e
r
a
,
“
D
e
e
p
f
e
a
t
u
r
e
-
b
a
s
e
d
r
i
c
e
l
e
a
f
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
ro
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
1
7
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
0
.
1
0
5
5
2
7
.
[
2
2
]
N
.
S
.
M
.
S
a
i
d
,
H
.
M
a
d
z
i
n
,
S
.
K
.
A
l
i
,
a
n
d
N
.
S
.
B
e
n
g
,
“
C
o
mp
a
r
i
s
o
n
o
f
c
o
l
o
r
-
b
a
se
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s
i
n
b
a
n
a
n
a
l
e
a
f
d
i
s
e
a
se
s
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
S
V
M
a
n
d
K
-
NN
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
4
,
n
o
.
3
,
p
p
.
1
5
2
3
-
1
5
3
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
4
.
i
3
.
p
p
1
5
2
3
-
1
5
3
3
.
[
2
3
]
M
.
B
r
a
h
i
m
i
,
K
.
B
o
u
k
h
a
l
f
a
,
a
n
d
A
.
M
o
u
ss
a
o
u
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
t
o
ma
t
o
d
i
se
a
ses
:
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
s
y
m
p
t
o
ms
v
i
s
u
a
l
i
z
a
t
i
o
n
,
”
Ap
p
l
i
e
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
1
,
n
o
.
4
,
p
p
.
2
9
9
-
3
1
5
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
8
0
/
0
8
8
3
9
5
1
4
.
2
0
1
7
.
1
3
1
5
5
1
6
.
[
2
4
]
H
.
D
u
r
m
u
ş,
E.
O
.
G
ü
n
e
ş,
a
n
d
M
.
K
ı
r
c
ı
,
“
D
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
o
n
t
h
e
l
e
a
v
e
s
o
f
t
h
e
t
o
m
a
t
o
p
l
a
n
t
s
b
y
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
2
0
1
7
6
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
A
g
r
o
-
G
e
o
i
n
f
o
rm
a
t
i
c
s
,
2
0
1
7
,
p
p
.
1
-
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
g
r
o
-
G
e
o
i
n
f
o
r
ma
t
i
c
s.
2
0
1
7
.
8
0
4
7
0
1
6
.
[
2
5
]
H
.
H
o
n
g
,
J.
Li
n
,
a
n
d
F
.
H
u
a
n
g
,
“
T
o
m
a
t
o
D
i
s
e
a
se
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
b
y
D
e
e
p
Le
a
r
n
i
n
g
,
”
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
Bi
g
D
a
t
a
,
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
En
g
i
n
e
e
ri
n
g
(
I
C
BAIE)
,
2
0
2
0
,
p
p
.
2
5
-
2
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
B
A
I
E4
9
9
9
6
.
2
0
2
0
.
0
0
012
.
[
2
6
]
Y
.
A
l
t
u
n
t
a
s
a
n
d
A
.
F
.
K
o
c
a
m
a
z
,
“
D
e
e
p
F
e
a
t
u
r
e
Ex
t
r
a
c
t
i
o
n
f
o
r
D
e
t
e
c
t
i
o
n
o
f
To
m
a
t
o
P
l
a
n
t
D
i
se
a
ses
a
n
d
P
e
st
s
b
a
se
d
o
n
L
e
a
f
I
mag
e
s
,
”
C
e
l
a
l
Ba
y
a
r
U
n
i
v
e
rsi
t
y
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
1
4
5
-
15
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
8
4
6
6
/
c
b
a
y
a
r
f
b
e
.
8
1
2
3
7
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
2
,
Feb
r
u
a
r
y
20
22
:
9
9
5
-
1
0
0
2
1002
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Rin
a
M
a
h
a
k
u
d
h
a
s
c
o
m
p
lete
d
h
e
r
Ba
c
h
e
lo
r
i
n
El
e
c
tro
n
ics
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
En
g
g
.
a
n
d
M
a
ste
r
in
Na
tu
ra
l
la
n
g
u
a
g
e
p
r
o
c
e
ss
in
g
fro
m
Ut
k
a
l
Un
i
v
e
rsity
,
Od
ish
a
,
I
n
d
ia.
P
re
se
n
tl
y
sh
e
is
wo
rk
i
n
g
a
s
As
sista
n
t
P
r
o
fe
ss
o
r
in
De
p
t
o
f
El
e
c
tro
n
ics
a
n
d
Tele
c
o
m
m
En
g
g
.
a
t
Tri
d
e
n
t
Ac
a
d
e
m
y
o
f
Tec
h
n
o
lo
g
y
,
Bh
u
b
a
n
e
sw
a
r,
Od
is
h
a
,
I
n
d
ia.
S
h
e
h
a
s 1
3
y
e
a
rs
o
f
te
a
c
h
in
g
e
x
p
e
rien
c
e
a
n
d
p
u
b
li
sh
e
d
m
o
re
t
h
a
n
7
re
se
a
rc
h
p
a
p
e
rs
in
jo
u
rn
a
l
a
n
d
c
o
n
fe
re
n
c
e
s.
He
r
a
re
a
o
f
re
se
a
rc
h
in
tere
st
is
M
a
c
h
in
e
lea
rn
i
n
g
a
n
d
I
n
tern
e
t
o
f
T
h
in
g
s
a
n
d
g
u
i
d
e
d
n
u
m
e
ro
u
s
B.
Tec
h
P
r
o
jec
ts.
S
h
e
is
a
li
fe
ti
m
e
m
e
m
b
e
r
o
f
IS
TE
a
n
d
IE
TE
.
Sh
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ri
n
a
m
a
h
a
k
u
d
@g
m
a
il
.
c
o
m
.
Dr
.
Bin
o
d
K
u
m
a
r
P
a
tta
n
a
y
a
k
c
o
m
p
lete
d
h
is
M
.
S
.
i
n
C
o
m
p
u
ter
En
g
in
e
e
ri
n
g
fro
m
Kh
a
rk
o
v
P
o
l
y
tec
h
n
ic
In
st
i
tu
te,
Kh
a
rk
o
v
,
Uk
ra
i
n
e
in
th
e
y
e
a
r
1
9
9
2
a
n
d
P
h
.
D.
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
fr
o
m
S
ik
sh
a
‘O’
An
u
sa
n
d
h
a
n
Un
iv
e
rsit
y
,
Bh
u
b
a
n
e
sw
a
r,
Od
ish
a
,
In
d
ia
i
n
th
e
y
e
a
r
2
0
1
1
.
He
h
a
s
a
te
a
c
h
in
g
e
x
p
e
rien
c
e
o
f
2
1
y
e
a
rs
in
u
n
d
e
r
g
ra
d
u
a
te,
p
o
st
g
ra
d
u
a
te
a
n
d
P
h
.
D.
Lev
e
ls
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
.
He
h
a
s
su
c
c
e
ss
fu
ll
y
g
u
i
d
e
d
P
h
.
D
a
n
d
M
.
Tec
h
.
Lev
e
l
stu
d
e
n
ts.
He
is
c
u
rre
n
tl
y
P
r
o
f
e
ss
o
r
in
th
e
d
e
p
a
rtme
n
t
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
ri
n
g
i
n
I
n
stit
u
te
o
f
Tec
h
n
ica
l
Ed
u
c
a
ti
o
n
a
n
d
Re
se
a
rc
h
(IT
ER),
th
e
fa
c
u
lt
y
o
f
e
n
g
in
e
e
ri
n
g
o
f
S
.
O.A
(De
e
m
e
d
to
b
e
)
Un
iv
e
rsity
,
B
h
u
b
a
n
e
sw
a
r,
Od
ish
a
,
In
d
ia.
His
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
a
d
h
o
c
n
e
two
rk
s,
so
f
twa
re
e
n
g
in
e
e
rin
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
c
o
m
p
il
e
r
d
e
sig
n
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
in
o
d
p
a
tt
a
n
a
y
a
k
@s
o
a
.
a
c
.
in
.
Dr
.
Bib
u
d
h
e
n
d
u
P
a
ti
is
As
so
c
iate
P
ro
fe
ss
o
r
a
n
d
He
a
d
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
Ra
m
a
De
v
i
Wo
m
e
n
’s
Un
i
v
e
rsity
,
Bh
u
b
a
n
e
sw
a
r,
In
d
ia.
He
h
a
s
a
r
o
u
n
d
2
1
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
.
His
a
re
a
s
o
f
re
s
e
a
rc
h
in
tere
sts
in
c
lu
d
e
Wi
re
les
s
S
e
n
so
r
Ne
two
rk
s,
Cl
o
u
d
Co
m
p
u
ti
n
g
,
Big
Da
ta,
In
tern
e
t
o
f
Th
i
n
g
s,
a
n
d
Ad
v
a
n
c
e
d
Ne
two
rk
Tec
h
n
o
l
o
g
ies
.
He
c
o
m
p
lete
d
h
is
P
h
.
D.
fr
o
m
IIT
Kh
a
ra
g
p
u
r,
I
n
d
i
a
.
He
is
a
Li
fe
M
e
m
b
e
r
o
f
In
d
ian
S
o
c
iety
f
o
r
Tec
h
n
ica
l
Ed
u
c
a
ti
o
n
,
Co
m
p
u
ter
S
o
c
iety
o
f
In
d
ia
a
n
d
S
e
n
i
o
r
M
e
m
b
e
r
o
f
IEE
E.
He
a
lso
se
rv
e
d
a
s
G
u
e
st
E
d
it
o
r
o
f
IJCN
DS
a
n
d
IJCSE
jo
u
r
n
a
ls
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
a
ti
b
ib
u
d
h
e
n
d
u
@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.