I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
3
8
,
No
.
1
,
A
p
r
il
20
2
5
,
p
p
.
303
~
311
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs
.v
3
8
.
i
1
.
pp
303
-
3
1
1
303
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Ens
e
m
bl
e learnin
g
w
eig
hted
a
v
erag
e
m
e
ta
-
cla
ss
ifier
for pa
l
m
disea
ses
ident
i
fica
tion
So
f
ia
ne
Abden,
M
o
s
t
ef
a
B
en
dji
m
a
,
So
u
m
ia
B
en
k
ra
m
a
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
mat
i
c
s
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
L
a
b
o
r
a
t
o
r
y
o
f
I
n
f
o
r
mat
i
o
n
P
r
o
c
e
ssi
n
g
a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
s (L
TI
T)
,
T
a
h
r
i
M
o
h
a
me
d
U
n
i
v
e
r
si
t
y
o
f
B
e
c
h
a
r
,
B
e
c
h
a
r
,
A
l
g
e
r
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
9
,
2
0
2
4
R
ev
i
s
ed
Oct
18
,
2
0
2
4
A
cc
ep
ted
Oct
28
,
2
0
2
4
Cro
p
d
ise
a
se
s
lea
d
to
sig
n
if
ica
n
t
lo
ss
e
s
f
o
r
fa
r
m
e
rs
a
n
d
th
re
a
ten
th
e
g
lo
b
a
l
f
o
o
d
su
p
p
ly
.
T
h
e
d
a
te
p
a
l
m
,
v
a
l
u
e
d
f
o
r
it
s
n
u
tri
ti
o
n
a
l
b
e
n
e
f
it
s
a
n
d
d
r
o
u
g
h
t
re
sista
n
c
e
in
d
e
se
rt
c
li
m
a
tes
,
is
a
v
it
a
l
e
x
p
o
rt
c
ro
p
f
o
r
m
a
n
y
c
o
u
n
tr
ies
in
t
h
e
M
id
d
le
Eas
t
a
n
d
No
r
th
A
f
rica
,
se
c
o
n
d
o
n
ly
to
h
y
d
ro
c
a
rb
o
n
s.
Ho
w
e
v
e
r,
v
a
rio
u
s
d
ise
a
se
s
p
o
se
a
t
h
re
a
t
to
t
h
is
im
p
o
rtan
t
p
lan
t.
T
h
e
re
fo
re
,
e
a
rly
d
ise
a
se
p
re
d
ictio
n
u
si
n
g
d
e
e
p
lea
rn
in
g
(DL
)
is
e
ss
e
n
ti
a
l
to
p
r
e
v
e
n
t
th
e
d
e
terio
ra
ti
o
n
o
f
d
a
te
p
a
lm
c
ro
p
s.
T
h
e
a
i
m
o
f
th
is
p
a
p
e
r
is
to
a
p
p
l
y
a
ro
b
u
st
e
n
se
m
b
le
m
e
th
o
d
(EL
)
c
o
m
b
in
in
g
tree
tran
sf
e
r
lea
rn
in
g
(
TL
)
m
o
d
e
ls
Re
sn
e
t5
0
,
De
n
se
Ne
t2
0
1
,
a
n
d
I
n
c
e
p
ti
o
n
V3
,
a
n
d
c
o
m
p
a
re
s
it
s
p
e
rf
o
r
m
a
n
c
e
w
it
h
th
e
CNN
-
S
V
M
m
o
d
e
l
a
n
d
th
e
tree
T
L
m
o
d
e
ls
m
e
n
ti
o
n
e
d
p
re
v
io
u
sly
.
T
h
e
m
o
d
e
ls
we
re
a
p
p
li
e
d
to
a
d
a
te
p
a
l
m
d
a
tas
e
t
c
o
n
tain
in
g
th
re
e
c
las
se
s:
W
h
it
e
sc
a
le
,
b
ro
w
n
sp
o
t,
a
n
d
h
e
a
lt
h
y
le
a
f
.
T
h
e
train
in
g
a
n
d
v
a
li
d
a
ti
o
n
se
ts
w
e
r
e
a
p
p
li
e
d
to
a
p
u
b
li
c
d
a
tas
e
t,
w
h
il
e
th
e
tes
ti
n
g
se
t
wa
s
a
p
p
li
e
d
to
a
lo
c
a
l
d
a
tas
e
t
c
a
p
tu
re
d
m
a
n
u
a
ll
y
to
c
h
e
c
k
th
e
m
o
d
e
l’s
p
e
rf
o
r
m
a
n
c
e
.
A
s
a
re
su
lt
,
w
e
c
o
n
sid
e
re
d
t
h
a
t
t
h
e
e
n
se
m
b
le
m
e
th
o
d
g
a
v
e
v
e
r
y
s
a
ti
s
f
a
c
to
ry
r
e
su
lt
s
c
o
m
p
a
re
d
to
o
th
e
r
m
e
th
o
d
s.
Ou
r
h
y
b
rid
m
o
d
e
l
re
a
c
h
e
d
a
tes
ti
n
g
a
c
c
u
ra
c
y
o
f
9
8
%
w
h
il
e
a
c
h
iev
in
g
a
n
a
m
a
z
in
g
train
in
g
a
n
d
v
a
li
d
a
ti
o
n
a
c
c
u
ra
c
y
o
f
9
9
.
9
4
%
a
n
d
9
8
.
1
4
%
,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
i
n
tel
lig
e
n
ce
C
las
s
i
f
icatio
n
Ma
ch
i
n
e
lear
n
i
n
g
P
alm
d
is
ea
s
es
S
m
ar
t a
g
r
icu
lt
u
r
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
So
f
ia
n
e
A
b
d
en
Dep
ar
t
m
en
t o
f
Ma
th
e
m
at
ics a
n
d
C
o
m
p
u
ter
Scien
ce
,
L
ab
o
r
ato
r
y
o
f
I
n
f
o
r
m
atio
n
P
r
o
ce
s
s
i
n
g
an
d
T
elec
o
m
m
u
n
icatio
n
s
(
L
T
I
T
)
,
T
ah
r
i M
o
h
a
m
ed
Un
i
v
er
s
it
y
o
f
B
ec
h
ar
I
n
d
ep
en
d
en
ce
R
o
ad
B
.
P
4
1
7
,
B
ec
h
ar
,
A
l
g
er
ia
E
m
ail:
ab
d
an
.
s
o
u
f
y
a
n
e@
u
n
i
v
-
b
ec
h
ar
.
d
z
1.
I
NT
RO
D
UCT
I
O
N
P
lan
ts
ar
e
a
p
r
im
ar
y
s
o
u
r
ce
o
f
f
o
o
d
f
o
r
th
e
g
lo
b
al
p
o
p
u
latio
n
[
1
]
.
A
g
r
ic
u
lt
u
r
e
is
r
eg
ar
d
ed
as
a
cr
u
cial
se
cto
r
w
it
h
s
i
g
n
i
f
ican
t
e
f
f
ec
t
s
o
n
lif
e
a
n
d
ec
o
n
o
m
ic
i
n
s
e
v
er
al
n
atio
n
s
.
D
u
e
to
th
e
s
u
b
s
tan
t
ial
p
o
p
u
latio
n
g
r
o
w
t
h
,
m
ee
ti
n
g
p
eo
p
le’
s
d
i
etar
y
n
ee
d
s
a
n
d
i
m
p
r
o
v
i
n
g
th
e
q
u
alit
y
a
n
d
q
u
an
ti
t
y
o
f
cr
o
p
s
h
as
g
ai
n
ed
s
ig
n
i
f
ica
n
t
i
m
p
o
r
tan
ce
.
T
h
e
tr
an
s
itio
n
to
s
m
ar
t
ag
r
ic
u
lt
u
r
e
h
as
b
ec
o
m
e
in
e
v
itab
le
to
ac
h
iev
e
f
o
o
d
s
ec
u
r
it
y
g
o
als
[
2
]
,
w
h
ile
th
e
u
s
e
o
f
tr
ad
itio
n
al
m
et
h
o
d
s
a
n
d
i
m
p
r
o
p
er
m
an
a
g
e
m
en
t
lead
s
to
t
h
e
lo
s
s
o
f
a
g
r
ic
u
lt
u
r
al
p
r
o
d
u
cts
[
3
]
.
A
cc
o
r
d
in
g
to
a
r
ep
o
r
t
b
y
th
e
f
o
o
d
an
d
ag
r
ic
u
ltu
r
e
o
r
g
a
n
izatio
n
(
F
A
O)
,
it
i
s
esti
m
ated
t
h
at
t
h
e
p
o
p
u
latio
n
o
f
th
e
w
h
o
le
w
o
r
ld
w
ill ap
p
r
o
x
i
m
atel
y
r
is
e
u
p
to
9
b
illi
o
n
i
n
a
f
e
w
y
ea
r
s
.
Ho
w
e
v
er
,
th
e
p
r
o
d
u
ctio
n
w
it
h
i
n
t
h
e
a
g
r
ic
u
lt
u
r
al
s
ec
to
r
n
ee
d
s
to
b
e
i
m
p
r
o
v
ed
to
at
le
ast
7
0
%
i
n
o
r
d
er
to
s
atis
f
y
t
h
e
f
o
o
d
d
e
m
an
d
s
o
f
h
u
m
a
n
b
ein
g
s
[
4
]
.
S
w
ee
t
an
d
p
alata
b
le,
ea
ten
a
s
a
m
ai
n
co
u
r
s
e,
t
h
e
d
ate
p
al
m
o
r
P
h
o
en
ix
d
ac
t
y
li
f
er
a
L
,
is
o
n
e
o
f
t
h
e
ea
r
lies
t
p
lan
t
s
k
n
o
w
n
to
h
u
m
a
n
s
i
n
p
r
e
-
Sa
h
ar
an
a
n
d
Sa
h
ar
an
r
eg
io
n
s
.
I
t
b
elo
n
g
s
to
t
h
e
A
r
ecaceae
f
a
m
il
y
a
n
d
h
as
b
ee
n
cu
l
tiv
a
ted
s
i
n
ce
an
c
ien
t
ti
m
e
s
[
5
]
.
Date
cu
lti
v
ati
o
n
h
a
s
h
ad
a
s
ig
n
i
f
ica
n
t
i
m
p
ac
t
o
n
t
h
is
r
e
g
io
n
'
s
h
is
to
r
y
.
I
n
t
h
is
h
ar
s
h
d
eser
t
cli
m
ate,
d
ates
ar
e
ess
en
tial
f
o
r
th
e
s
u
r
v
i
v
al
o
f
a
s
izab
le
h
u
m
a
n
p
o
p
u
latio
n
.
T
h
ey
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
A
p
r
il
20
2
5
:
3
0
3
-
311
304
h
o
ld
s
p
ec
ial
s
ig
n
i
f
ica
n
ce
as
a
s
y
m
b
o
l
o
f
f
ec
u
n
d
it
y
a
n
d
f
er
tili
t
y
,
li
n
k
ed
to
s
o
cieta
l
v
al
u
es,
tr
ad
itio
n
s
,
a
n
d
r
itu
als
[
6
]
t
h
at
h
av
e
b
ee
n
i
n
h
er
ited
b
y
n
u
m
er
o
u
s
g
e
n
er
atio
n
s
[
7
]
.
E
x
te
n
s
i
v
el
y
,
d
ates
ar
e
u
s
ed
i
n
t
h
e
f
o
o
d
p
r
o
ce
s
s
in
g
in
d
u
s
tr
y
f
o
r
m
a
k
i
n
g
j
u
ice,
j
am
,
j
ell
y
,
a
n
d
s
y
r
u
p
,
o
r
b
ein
g
co
n
s
u
m
ed
alo
n
e
as
s
u
ch
i
n
t
h
eir
f
r
e
s
h
o
r
d
r
ied
f
o
r
m
s
.
B
esid
es,
lo
ca
l
citi
ze
n
s
m
a
y
r
el
y
o
n
th
i
s
f
r
u
it,
th
a
t
is
r
ich
in
n
u
tr
ie
n
t
s
lik
e
ca
r
b
o
h
y
d
r
ates,
p
r
o
tein
s
,
v
ita
m
i
n
s
,
lip
id
s
a
n
d
m
in
er
al
s
th
at
ar
e
es
s
en
tial
f
o
r
h
u
m
a
n
h
ea
lth
[
5
]
.
E
v
er
y
co
m
p
o
n
en
t
is
u
tili
ze
d
,
i
n
cl
u
d
in
g
th
e
tr
u
n
k
an
d
lea
v
es,
w
h
ich
a
r
e
em
p
lo
y
ed
in
a
n
cien
t
b
u
ild
i
n
g
m
et
h
o
d
s
an
d
b
as
k
etr
y
[
8
]
.
Date
p
al
m
i
n
m
a
n
y
n
atio
n
s
i
n
th
e
M
id
d
le
E
ast
an
d
No
r
th
Af
r
ica,
h
a
s
a
b
ig
i
m
p
ac
t
o
n
th
e
e
n
v
ir
o
n
m
e
n
t,
s
o
ci
et
y
,
an
d
ec
o
n
o
m
y
.
T
h
is
cr
o
p
is
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
o
n
e
i
n
A
l
g
er
ian
Sa
h
ar
a
ag
r
i
cu
lt
u
r
e,
af
f
ec
ti
n
g
j
o
b
s
,
s
ed
en
t
ar
i
z
atio
n
o
f
p
eo
p
le,
an
d
p
r
o
d
u
cts.
I
t
is
p
r
o
j
ec
te
d
to
co
n
s
is
t
o
f
ar
o
u
n
d
8
0
0
s
p
ec
ies
an
d
o
v
er
1
7
m
illi
o
n
p
al
m
tr
e
es
[
9
]
.
r
an
k
s
f
o
u
r
th
g
lo
b
all
y
i
n
d
ate
p
r
o
d
u
ctio
n
,
y
ield
in
g
1
,
1
3
1
,
6
0
5
m
etr
ic
to
n
s
an
n
u
all
y
ac
r
o
s
s
1
6
9
,
3
8
0
h
ec
tar
es.
Date
s
ar
e
also
A
l
g
er
ia
’
s
m
o
s
t
v
alu
ab
le
a
g
r
ic
u
lt
u
r
al
p
r
o
d
u
ct
ex
p
o
r
t,
w
it
h
1
5
,
0
0
0
to
n
n
es e
x
p
o
r
ted
an
n
u
all
y
[
9
]
,
[
1
0
]
.
T
h
e
d
ate
p
alm
is
s
e
v
er
e
l
y
li
m
ited
b
y
en
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
s
u
c
h
as
s
ali
n
e
s
o
il,
lo
n
g
-
ter
m
d
r
o
u
g
h
t
s
,
h
ig
h
te
m
p
er
at
u
r
es,
d
eser
ti
f
ic
atio
n
[
8
]
.
Ho
w
e
v
er
,
th
e
s
e
s
a
m
e
co
n
d
itio
n
s
a
ls
o
en
co
u
r
ag
e
th
e
e
x
is
ten
ce
o
f
m
icr
o
o
r
g
an
i
s
m
s
w
h
ich
co
n
tr
i
b
u
tes
to
th
e
o
cc
u
r
r
en
ce
o
f
p
es
ts
an
d
d
is
ea
s
e
s
.
I
n
g
e
n
er
al,
a
v
ar
iet
y
o
f
d
is
ea
s
es,
in
cl
u
d
in
g
B
a
y
o
u
d
,
lea
f
s
m
u
t,
r
ed
p
alm
w
ee
v
il,
m
ea
l
y
b
u
g
s
,
an
d
m
i
tes,
ca
n
af
f
lic
t
d
ate
p
al
m
tr
ee
s
[
1
0
]
,
[
1
1
]
.
I
t
h
as
a
d
ev
as
tatin
g
e
f
f
ec
t
o
n
p
al
m
tr
ee
s
;
in
j
u
s
t
o
n
e
ce
n
tu
r
y
,
a
d
is
ea
s
e
li
k
e
B
a
y
o
u
d
(
Fu
s
ar
iu
m
o
x
y
s
p
o
r
iu
m
f
.
alb
ed
in
is
)
h
a
s
k
illed
t
h
r
ee
m
i
llio
n
tr
ee
s
in
s
o
u
t
h
w
e
s
ter
n
Alg
er
ia
[
1
2
]
.
T
h
e
n
atu
r
e
an
d
s
y
m
p
to
m
s
o
f
t
h
ese
d
is
ea
s
es
v
a
r
y
i
n
t
h
eir
f
o
r
m
,
o
f
ten
ap
p
ea
r
in
g
o
n
t
h
e
lea
v
es
[
7
]
.
C
o
n
v
e
n
tio
n
al
ap
p
r
o
ac
h
es
f
o
r
id
en
tify
i
n
g
p
lan
t
d
is
ea
s
es,
w
h
ic
h
in
v
o
l
v
e
o
b
s
er
v
in
g
th
e
d
is
ea
s
e
w
i
th
t
h
e
u
n
a
id
ed
e
y
e
o
r
u
s
i
n
g
s
k
il
led
lab
o
r
ato
r
y
p
r
o
ce
d
u
r
es,
tak
e
ti
m
e
a
n
d
n
ec
e
s
s
itate
o
n
g
o
in
g
p
la
n
t
o
b
s
er
v
atio
n
[
1
3
]
.
Far
m
er
s
o
f
ten
g
r
ap
p
le
w
it
h
t
h
e
ch
a
llen
g
e
o
f
n
o
t
s
eizin
g
t
h
e
o
p
p
o
r
tu
n
it
y
to
p
r
ev
en
t
th
e
s
e
ill
n
ess
e
s
.
W
h
ile
u
s
i
n
g
m
o
d
er
n
ap
p
r
o
ac
h
es
wo
u
ld
h
elp
to
av
o
id
d
is
ea
s
es
i
n
g
e
n
er
al
an
d
in
ca
s
e
o
f
p
al
m
tr
ee
s
in
p
ar
tic
u
lar
an
d
tak
e
n
ec
e
s
s
ar
y
m
ea
s
u
r
e
s
i
n
ti
m
e
s
av
in
g
co
s
ts
an
d
lab
o
r
er
’
s
,
th
er
e
is
s
till
a
n
ee
d
to
w
o
r
k
o
n
a
p
r
ac
tical
an
d
ef
f
ic
ien
t
m
et
h
o
d
o
f
ad
d
r
ess
in
g
th
e
s
e
is
s
u
es.
E
as
y
to
u
s
e
a
n
d
co
n
v
e
n
ie
n
t
v
ia
a
m
o
b
ile
ap
p
w
o
u
ld
m
a
k
e
it
h
e
lp
f
u
l
to
d
ate
p
al
m
f
ar
m
er
s
[
1
4
]
.
Sev
er
al
m
ac
h
in
e
lear
n
in
g
(
ML
)
an
d
D
L
tech
n
i
q
u
es,
u
s
ed
b
y
r
esear
ch
er
s
to
ca
teg
o
r
ize
an
d
r
ec
o
g
n
ize
p
alm
i
m
a
g
es,
i
n
clu
d
i
n
g
d
ate
p
alm
d
is
ea
s
es a
n
d
d
ate
f
r
u
it,
ar
e
p
r
esen
ted
in
t
h
is
s
ec
tio
n
.
No
u
tf
ia
an
d
R
o
p
ele
w
s
k
a
[
5
]
ai
m
s
to
ca
teg
o
r
ize
f
iv
e
d
ate
p
alm
f
r
u
it
v
ar
ietie
s
u
s
i
n
g
M
L
alg
o
r
ith
m
s
b
y
ex
tr
ac
ti
n
g
te
x
t
u
r
e
f
ea
t
u
r
es
f
r
o
m
f
r
u
it
i
m
a
g
es.
T
h
e
m
o
d
els,
i
n
clu
d
i
n
g
co
m
b
in
ed
te
x
t
u
r
es
s
elec
ted
f
r
o
m
all
1
2
co
lo
r
s
ch
an
n
els,
ac
h
iev
ed
a
n
av
er
ag
e
ac
c
u
r
ac
y
o
f
9
8
%.
I
n
th
e
s
t
u
d
y
f
r
o
m
Al
-
Sh
a
lo
u
t
et
a
l.
[
7
]
,
c
o
n
v
o
lu
tio
n
n
eu
r
al
n
et
w
o
r
k
(
C
NN)
a
n
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM
)
alg
o
r
ith
m
s
ar
e
s
u
g
g
ested
to
d
etec
t
d
ate
p
al
m
d
is
ea
s
es.
T
h
e
r
esu
lts
s
h
o
w
t
h
a
t
C
NN
i
s
m
o
r
e
e
f
f
ec
ti
v
e,
ac
h
i
ev
in
g
a
n
ac
c
u
r
ac
y
o
f
9
9
.
8
7
%
w
h
e
n
th
e
s
ize
o
f
th
e
d
ataset
in
cr
ea
s
e
s
.
E
m
p
lo
y
i
n
g
i
m
a
g
e
au
g
m
e
n
tatio
n
tech
n
o
lo
g
y
.
T
h
e
s
t
u
d
y
w
as
ap
p
lied
to
f
o
u
r
co
m
m
o
n
d
is
ea
s
es
d
atase
t:
b
ac
ter
ial
b
lig
h
t,
b
r
o
w
n
s
p
o
ts
,
lea
f
s
m
u
t,
a
n
d
w
h
ite
s
ca
les
[
1
1
]
.
B
u
ilt
a
f
r
a
m
e
w
o
r
k
t
h
at
u
s
e
s
ML
tec
h
n
iq
u
es
(
SVM,
KNN
)
an
d
E
L
m
et
h
o
d
s
(
lig
h
t
g
r
a
d
ien
t
b
o
o
s
tin
g
m
ac
h
in
e,
r
an
d
o
m
f
o
r
est
(
R
F))
to
class
i
f
y
t
h
e
s
tag
e
s
o
f
i
n
f
estati
o
n
b
y
w
h
i
te
s
ca
le
d
is
ea
s
e
i
n
d
ate
p
al
m
tr
ee
s
b
ased
o
n
t
h
eir
l
ea
f
let
i
m
a
g
es.
T
h
e
f
r
a
m
e
w
o
r
k
ex
tr
ac
ts
t
e
x
t
u
r
e
f
e
atu
r
es
f
r
o
m
i
m
a
g
es.
T
h
e
b
est
p
er
f
o
r
m
a
n
ce
ac
cu
r
ac
y
o
f
9
8
.
2
9
%
ac
h
iev
ed
b
y
SVM
[
1
2
]
.
A
p
p
lied
a
s
u
p
er
v
i
s
ed
ML
tech
n
iq
u
es
(
KNN,
S
V
M,
Naiv
e
B
a
y
e
s
,
a
n
d
A
d
aB
o
o
s
t)
to
r
ec
o
g
n
ize
th
e
g
en
d
er
o
f
d
ate
p
a
l
m
s
at
t
h
e
s
e
ed
lin
g
s
ta
g
e
u
s
i
n
g
a
n
i
m
a
g
e
o
f
i
n
f
ec
ted
d
ate
p
al
m
leav
e
s
b
y
d
u
b
as
in
s
ec
ts
,
t
he
SVM
al
g
o
r
ith
m
y
ie
ld
ed
th
e
m
o
s
t
ac
cu
r
ate
r
es
u
lts
w
it
h
9
7
%
ac
cu
r
ac
y
[
1
3
]
.
D
e
v
elo
p
ed
a
f
r
a
m
e
w
o
r
k
f
o
r
d
ate
r
ec
o
g
n
itio
n
b
ased
o
n
co
lo
r
,
s
h
ap
e,
an
d
s
ize
f
ea
tu
r
es,
t
h
e
y
e
m
p
lo
y
ed
C
NN
to
t
h
r
ee
t
y
p
es
o
f
d
ates:
Aseel,
Ku
p
r
o
,
an
d
Kar
b
alain
,
ac
q
u
ir
ed
9
7
.
2
%
ac
cu
r
ac
y
.
Ah
m
ed
a
n
d
A
h
m
ed
[
1
5
]
u
s
ed
T
L
o
f
in
ce
p
tio
n
an
d
R
e
s
Net
o
n
a
2
,
6
3
1
to
tal
v
ar
ied
s
izes
i
m
ag
e
s
,
ac
h
iev
in
g
ac
c
u
r
ac
y
o
f
9
9
.
6
2
%
an
d
1
0
0
%,
r
esp
ec
tiv
el
y
,
to
clas
s
i
f
y
t
h
r
ee
class
es
o
f
p
al
m
d
i
s
ea
s
e.
Ma
g
s
i
et
a
l.
[
1
6
]
im
p
le
m
e
n
ted
a
C
NN
to
r
ec
o
g
n
ize
p
al
m
d
is
ea
s
e
at
d
if
f
er
e
n
t
s
tag
e
s
,
in
1
,
2
0
0
d
ate
p
alm
leav
e
s
d
is
e
ase
i
m
a
g
es
h
a
v
e
b
ee
n
co
llecte
d
m
a
n
u
all
y
,
ac
h
ie
v
ed
an
ac
c
u
r
ac
y
o
f
8
9
.
4
%.
T
h
e
ex
p
er
i
m
e
n
tal
r
es
u
lts
d
i
s
c
u
s
s
e
d
in
th
e
p
ap
er
[
1
7
]
ar
e
b
ased
o
n
f
i
v
e
s
ta
g
es
u
s
i
n
g
a
d
atase
t
o
f
2
7
d
ate
class
es
w
it
h
3
,
2
2
8
im
a
g
e
s
.
T
h
e
f
ir
s
t
s
tag
e
ap
p
lied
ML
al
g
o
r
ith
m
s
.
T
h
e
s
ec
o
n
d
s
tag
e,
a
De
n
s
e
N
et
T
L
w
as
ap
p
lied
,
an
d
in
t
h
e
s
ta
g
e
tr
ee
an
d
f
o
u
r
,
f
in
e
-
t
u
n
ed
w
a
s
ap
p
lied
to
ac
h
iev
e
t
h
e
b
est
m
o
d
el
’
s
cla
s
s
i
f
icatio
n
.
I
n
th
e
f
i
f
t
h
s
tag
e,
r
eg
u
lar
izatio
n
w
as
i
m
p
le
m
e
n
ted
,
ac
h
ie
v
in
g
a
v
a
lid
atio
n
ac
cu
r
ac
y
o
f
9
7
.
2
1
%,
an
d
a
test
ac
cu
r
ac
y
o
f
9
5
.
2
1
%.
A
b
u
-
za
n
o
n
a
et
a
l.
[
1
8
]
s
u
g
g
ested
C
NN
m
o
d
el
ap
p
l
ied
in
a
d
ataset
co
n
tai
n
tr
ee
p
al
m
lea
v
es
d
is
ea
s
es
ac
h
iev
e
s
an
ac
c
u
r
ac
y
o
f
9
9
.
1
0
%,
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
ev
al
u
ated
an
d
co
m
p
ar
ed
ag
ain
s
t
VGG
-
1
6
an
d
Mo
b
ileNet.
Kh
r
ij
i
et
a
l.
[
1
9
]
th
r
ee
d
if
f
er
en
t
ML
tec
h
n
iq
u
es,
SVM,
ar
ti
f
ici
al
n
eu
r
al
n
et
w
o
r
k
s
(
A
NN)
,
an
d
K
-
Nea
r
est
n
ei
g
h
b
o
r
(
KNN)
h
av
e
b
ee
n
e
m
p
lo
y
e
d
f
o
r
class
if
icat
io
n
b
ased
o
n
co
lo
r
,
s
h
ap
e
an
d
s
ize
f
ea
t
u
r
es.
ap
p
lied
to
s
ix
d
ate
f
r
u
it
v
ar
ieties
in
O
m
an
,
T
h
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
o
f
9
9
.
2
0
%
ac
h
iev
ed
b
y
t
h
e
A
N
N
class
i
f
ier
.
I
n
[
2
0
]
th
is
w
o
r
k
t
w
o
clas
s
i
f
ier
s
w
er
e
u
tili
ze
d
to
class
i
f
y
t
h
r
ee
d
is
ea
s
e
s
.
VGG
to
d
if
f
er
e
n
tiate
b
et
w
ee
n
leaf
s
p
o
ts
a
n
d
b
lig
h
t
s
p
o
ts
,
an
d
SVM
f
o
r
r
ed
p
a
l
m
w
ee
v
il
p
est.
T
h
e
r
esu
lts
f
o
r
VGG
an
d
SVM
s
h
o
w
ed
a
s
u
cc
e
s
s
r
ate
o
f
ac
cu
r
ac
y
9
7
.
9
%
an
d
9
2
.
8
%
r
esp
ec
tiv
el
y
.
T
h
e
r
esear
ch
er
s
p
r
ese
n
ted
in
[
2
1
]
a
h
y
b
r
id
m
o
d
el
th
at
co
m
b
in
e
s
t
h
e
e
f
f
i
cien
t
c
h
an
n
el
at
ten
t
io
n
n
et
w
o
r
k
(
E
C
A
-
Net)
w
it
h
De
n
s
e
Net
2
0
1
an
d
R
esNet5
0
th
o
u
g
h
T
L
,
ac
h
iev
i
n
g
r
e
m
ar
k
a
b
le
ac
cu
r
ac
y
r
ates o
f
9
9
.
5
4
% f
o
r
tr
ain
in
g
a
n
d
9
8
.
6
7
% f
o
r
v
alid
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
E
n
s
emb
le
lea
r
n
in
g
w
eig
h
ted
a
ve
r
a
g
e
meta
-
cla
s
s
ifier
fo
r
p
a
lm
d
is
ea
s
es
…
(
S
o
fia
n
e
A
b
d
en
)
305
T
h
e
g
o
al
o
f
t
h
is
s
t
u
d
y
i
s
to
le
v
er
ag
e
ar
ti
f
icial
in
telli
g
en
ce
(
A
I
)
,
p
ar
ticu
lar
l
y
M
L
a
n
d
D
L
,
to
en
h
a
n
ce
ag
r
icu
l
tu
r
e
b
y
u
s
in
g
i
m
ag
e
s
o
f
in
f
ec
ted
p
al
m
lea
v
es
to
id
en
ti
f
y
t
w
o
co
m
m
o
n
d
is
ea
s
es
(
w
h
i
te
s
ca
le
an
d
b
r
o
w
n
s
p
o
ts
)
,
w
i
th
a
th
ir
d
clas
s
co
n
t
ain
i
n
g
h
ea
lt
h
y
lea
v
es.
U
n
li
k
e
p
r
ev
io
u
s
w
o
r
k
,
w
h
ic
h
lar
g
el
y
f
o
cu
s
ed
o
n
M
L
o
r
T
L
m
o
d
els
i
n
d
i
v
id
u
all
y
w
it
h
p
u
b
lic
d
atasets
,
th
i
s
s
t
u
d
y
ad
d
r
ess
es
a
g
ap
b
y
in
tr
o
d
u
c
in
g
E
L
co
m
b
i
n
i
n
g
p
r
etr
ain
ed
C
NNs
o
n
a
lo
ca
l
d
ataset.
Sev
er
al
c
h
alle
n
g
es
w
er
e
e
n
co
u
n
ter
ed
d
u
r
in
g
t
h
is
s
tu
d
y
,
in
c
l
u
d
i
n
g
a
s
h
o
r
tag
e
o
f
s
p
ec
ialis
t
s
i
n
p
al
m
tr
ee
d
i
s
ea
s
e
i
n
th
e
B
ec
h
a
r
r
eg
io
n
o
f
A
l
g
er
ia,
w
h
ic
h
m
ad
e
it
d
i
f
f
ic
u
lt
to
d
iag
n
o
s
i
s
an
d
co
llect
i
m
a
g
es
f
o
r
a
lo
ca
l
p
alm
tr
ee
d
ataset.
Mo
r
eo
v
er
,
th
e
s
ca
r
city
o
f
i
n
f
o
r
m
atio
n
o
n
p
al
m
d
is
ea
s
es
co
m
p
ar
ed
to
o
th
er
p
l
an
t
d
i
s
e
ases
is
li
k
el
y
d
u
e
to
th
eir
o
cc
u
r
r
en
ce
in
s
p
ec
i
f
ic
g
eo
g
r
ap
h
ical
ar
ea
s
.
T
h
e
m
ai
n
co
n
tr
ib
u
tio
n
s
o
f
t
h
is
p
a
p
er
in
clu
d
e
th
e
ap
p
licatio
n
o
f
a
h
y
b
r
id
m
et
h
o
d
co
m
b
in
i
n
g
C
NN
-
SVM,
T
L
o
n
R
es
N
et5
0
,
Den
s
e
N
et2
0
1
,
an
d
in
ce
p
tio
n
V3
.
ad
d
itio
n
all
y
,
o
u
r
p
r
o
p
o
s
al
o
f
E
L
o
n
t
h
e
s
a
m
e
T
L
m
o
d
els.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
p
r
o
p
o
s
ed
E
L
,
b
ased
o
n
a
w
ei
g
h
ted
av
e
r
ag
e
m
eta
-
clas
s
i
f
ier
,
w
a
s
co
m
p
ar
ed
w
it
h
th
e
T
L
an
d
C
NN
-
SV
M
r
esu
l
ts
u
s
i
n
g
a
lo
ca
l te
s
t d
ataset
f
r
o
m
t
h
e
B
ec
h
ar
r
eg
io
n
.
T
h
e
p
a
p
er
'
s
r
e
m
ain
in
g
s
ec
tio
n
is
ar
r
an
g
ed
as
f
o
llo
w
s
:
s
ec
tio
n
2
d
ea
ls
w
i
th
t
h
e
d
ataset,
th
e
p
r
o
p
o
s
ed
m
o
d
el
a
n
d
th
e
m
et
h
o
d
o
lo
g
y
th
at
h
a
s
b
ee
n
u
s
ed
to
s
o
lv
e
th
e
p
r
o
b
lem
.
Sectio
n
3
d
ea
ls
w
it
h
ex
p
er
i
m
e
n
t
s
p
er
f
o
r
m
ed
to
o
n
th
e
g
iv
e
n
p
r
o
b
lem
a
n
d
r
esu
lt
s
o
b
tain
ed
f
o
r
th
e
s
a
m
e,
a
n
d
a
co
m
p
ar
is
o
n
b
et
w
ee
n
d
i
f
f
er
e
n
t
m
o
d
el
s
.
Fi
n
al
l
y
,
T
h
e
co
n
cl
u
s
i
o
n
an
d
th
e
f
u
tu
r
e
s
co
p
e
in
s
ec
t
io
n
4
.
2.
M
E
T
H
O
D
Ou
r
w
o
r
k
f
lo
w
,
s
h
o
w
n
in
Fi
g
u
r
e
1
,
r
ep
r
esen
ts
a
r
o
b
u
s
t
en
s
e
m
b
le
m
et
h
o
d
w
ith
a
w
ei
g
h
t
ed
av
er
ag
e
m
eta
-
clas
s
i
f
ier
,
co
m
b
in
i
n
g
t
h
r
ee
T
L
m
o
d
els,
R
es
Net5
0
,
Den
s
eNe
t2
0
1
,
an
d
I
n
ce
p
tio
n
V3
to
id
en
ti
f
y
lea
f
p
al
m
d
is
ea
s
es,
an
d
its
p
er
f
o
r
m
an
ce
w
as
co
m
p
ar
ed
w
it
h
C
NN
-
S
VM
an
d
in
d
iv
id
u
al
T
L
m
o
d
e
ls
u
s
in
g
a
lo
ca
l
test
d
ataset
f
r
o
m
t
h
e
B
ec
h
ar
r
eg
io
n
in
Alg
er
ia.
Fig
u
r
e
1
.
P
r
o
p
o
s
ed
w
o
r
k
f
lo
w
d
iag
r
a
m
2
.
1
.
Da
t
a
s
et
des
cr
iptio
n
T
h
e
p
r
e
s
e
n
t
e
d
m
o
d
e
l
is
t
r
a
in
ed
a
n
d
a
s
s
ess
e
d
u
s
in
g
a
p
u
b
l
i
c
d
a
t
e
p
a
lm
d
a
t
as
e
t
f
r
o
m
K
ag
g
l
e
[
1
]
,
T
h
e
d
a
t
a
s
et
is
c
o
n
ta
in
in
g
a
t
o
t
al
o
f
2
,
6
3
1
l
a
b
e
l
l
e
d
d
a
t
e
p
a
lm
l
e
af
le
t
s
f
o
r
3
c
la
s
s
e
s
(
h
e
a
lt
h
y
,
b
r
o
w
n
s
p
o
ts
,
an
d
w
h
i
te
s
c
a
l
e
)
.
F
o
r
th
e
p
u
r
p
o
s
e
o
f
im
ag
e
-
b
as
e
d
i
d
e
n
t
if
i
c
at
i
o
n
w
h
i
ch
i
n
cl
u
d
es
,
t
r
a
in
in
g
an
d
e
v
al
u
a
t
io
n
p
h
as
e
w
h
e
r
e
t
h
e
p
e
r
f
o
r
m
an
c
e
o
f
c
la
s
s
if
ic
a
t
i
o
n
a
l
g
o
r
ith
m
s
is
e
v
a
lu
a
t
e
d
,
i
t
is
n
e
c
ess
a
r
y
t
o
h
av
e
h
u
g
e
d
a
t
ase
t
s
t
o
r
e
c
e
iv
e
b
e
tt
e
r
r
e
s
u
l
ts
.
T
o
e
n
h
an
c
e
th
e
d
a
t
as
et
an
d
in
c
r
e
as
e
th
e
c
r
e
d
i
b
i
li
ty
o
f
th
e
p
e
r
f
o
r
m
an
c
e
ev
a
lu
a
ti
o
n
,
a
d
d
i
t
i
o
n
a
l
im
ag
es
w
e
r
e
c
a
p
tu
r
e
d
l
o
c
al
ly
an
d
c
o
m
b
i
n
e
d
w
ith
th
e
p
u
b
l
ic
d
a
t
as
e
t
.
R
es
u
l
t
in
g
in
a
t
o
t
a
l
o
f
4
3
0
s
am
p
l
es
f
o
r
t
es
t
in
g
th
e
m
o
d
e
ls
.
T
h
e
p
u
b
l
i
c
d
at
a
s
e
t
,
w
h
ic
h
h
a
s
b
e
en
d
iv
i
d
e
d
in
t
o
t
r
a
in
in
g
an
d
v
a
l
i
d
a
ti
o
n
im
ag
es
f
o
r
th
e
s
u
g
g
es
t
e
d
m
o
d
e
ls
.
T
h
e
d
is
t
r
i
b
u
t
i
o
n
o
f
th
e
d
a
t
e
p
a
lm
l
e
af
d
is
e
as
e
im
ag
e
s
i
s
p
r
e
s
e
n
t
e
d
in
T
a
b
l
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
A
p
r
il
20
2
5
:
3
0
3
-
311
306
T
ab
le
1
.
Dis
tr
ib
u
tio
n
o
f
d
atase
t c
ateg
o
r
ies
C
a
t
e
g
o
r
i
e
s
N
u
mb
e
r
o
f
sam
p
l
e
s
B
r
o
w
n
sp
o
t
s
4
7
0
W
h
i
t
e
sca
l
e
9
5
8
H
e
a
l
t
h
y
1
2
0
3
T
o
t
a
l
2
6
3
1
T
h
e
v
alid
atio
n
s
et
co
n
tain
s
2
0
%
o
f
th
e
to
tal
p
al
m
leaf
p
h
o
to
s
,
w
h
er
ea
s
th
e
tr
ain
in
g
s
et
h
a
s
8
0
%
o
f
th
e
en
tire
leaf
d
ataset
i
m
a
g
es
[
2
1
]
.
E
ac
h
s
et
in
clu
d
e
s
an
u
n
i
n
f
e
cted
class
an
d
t
w
o
i
n
f
ec
ted
class
es
o
f
d
ate
p
al
m
leaf
d
i
s
ea
s
es.
Fi
g
u
r
e
2
p
r
esen
t
s
a
s
elec
tio
n
o
f
s
a
m
p
le
i
m
a
g
es
f
r
o
m
t
h
e
d
ataset
s
u
s
ed
i
n
th
i
s
s
tu
d
y
,
s
h
o
w
ca
s
i
n
g
h
ea
lt
h
y
an
d
d
is
ea
s
ed
lea
v
es
f
r
o
m
b
o
th
p
u
b
lic
an
d
lo
ca
l
d
atasets
.
Sp
ec
i
f
icall
y
,
Fig
u
r
e
2
(
a)
d
is
p
la
y
s
a
h
ea
lth
y
leaf
s
a
m
p
le,
a
n
d
Fi
g
u
r
e
2
(
b
)
s
h
o
w
s
a
s
a
m
p
le
i
m
a
g
e
o
f
w
h
ite
s
ca
le
d
is
ea
s
e
f
r
o
m
t
h
e
p
u
b
lic
d
ataset.
Fi
g
u
r
e
2
(
c)
illu
s
tr
ates
a
s
a
m
p
le
o
f
b
r
o
w
n
s
p
o
t
d
is
ea
s
e
f
r
o
m
t
h
e
p
u
b
lic
d
ataset,
w
h
ile
Fi
g
u
r
e
2
(
d
)
d
ep
i
cts
an
o
t
h
er
ex
a
m
p
le
o
f
b
r
o
w
n
s
p
o
t d
is
ea
s
e
ca
p
t
u
r
e
d
f
r
o
m
o
u
r
lo
ca
l d
ataset.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
Sa
m
p
les
f
o
r
ea
ch
p
alm
clas
s
in
o
r
d
er
: (
a)
h
ea
lth
y
le
af
,
(
b
)
w
h
i
te
s
ca
le
lea
f
d
is
ea
s
e
,
(
c)
b
r
o
w
n
s
p
o
ts
leaf
d
is
ea
s
e
f
r
o
m
t
h
e
Ka
g
g
le
d
ataset
,
an
d
(
d
)
b
r
o
w
n
s
p
o
ts
d
is
ea
s
e
ca
p
tu
r
ed
lo
ca
ll
y
2
.
2
.
CNN
-
SV
M
m
o
del
T
h
e
C
NN
-
SVM
m
o
d
el
is
a
h
y
b
r
id
ap
p
r
o
ac
h
th
at
co
m
b
in
es
th
e
s
tr
e
n
g
t
h
s
o
f
C
NN
w
it
h
SVM
to
i
m
p
r
o
v
e
class
i
f
icat
io
n
ac
cu
r
ac
y
.
SVM
is
a
s
u
p
er
v
i
s
ed
lear
n
in
g
alg
o
r
it
h
m
t
h
at
atte
m
p
ts
to
f
in
d
a
b
est
s
ep
ar
atin
g
h
y
p
er
p
la
n
e
th
at
i
s
e
m
b
ed
d
ed
in
to
t
h
e
g
i
v
e
n
f
ea
t
u
r
e
s
p
ac
es.
B
y
m
a
x
i
m
izin
g
t
h
e
m
ar
g
i
n
b
et
w
ee
n
th
e
d
is
s
i
m
ilar
clas
s
es,
SVM
ai
m
s
to
r
ed
u
ce
th
e
n
u
m
b
er
o
f
m
i
s
cl
ass
i
f
icatio
n
s
[
2
2
]
.
T
h
e
h
y
b
r
id
C
NN
-
SVM
m
o
d
el
ap
p
lies
th
e
SVM
m
o
d
el
i
n
p
lace
o
f
th
e
co
n
v
e
n
tio
n
al
So
f
t
M
ax
ac
tiv
at
io
n
f
u
n
ctio
n
f
o
u
n
d
in
th
e
la
s
t
la
y
er
o
f
a
C
NN.
T
h
is
k
i
n
d
o
f
ad
j
u
s
t
m
en
ts
g
i
v
es
a
ch
a
n
ce
f
o
r
th
e
C
N
N
to
au
to
m
atica
ll
y
e
x
tr
ac
t
f
ea
tu
r
es
f
r
o
m
th
e
i
n
p
u
t
d
ata,
w
h
ic
h
ar
e
f
i
n
all
y
clas
s
i
f
ied
b
y
th
e
S
VM
[
2
3
]
.
Du
r
in
g
tr
ain
i
n
g
in
t
h
is
s
tu
d
y
,
v
ar
i
o
u
s
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
ar
e
u
s
ed
to
en
h
an
ce
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
Fo
r
i
n
s
tan
ce
,
r
esca
le
p
ar
a
m
eter
s
e
t
to
1
/2
5
5
n
o
r
m
alize
p
ix
el
v
alu
e
s
i
n
to
[
0
,
1
]
to
s
p
ee
d
u
p
co
n
v
er
g
e
n
ce
.
I
n
p
u
t
i
m
a
g
es
ar
e
r
esized
to
2
2
4
×
2
2
4
p
ix
els.
A
b
atc
h
s
ize
o
f
3
2
en
s
u
r
e
s
a
b
ala
n
ce
b
et
w
ee
n
co
m
p
u
tatio
n
al
e
f
f
icie
n
c
y
an
d
p
er
f
o
r
m
a
n
ce
.
T
h
e
m
o
d
el
u
s
es
a
s
q
u
ar
ed
h
i
n
g
e
lo
s
s
f
u
n
ctio
n
f
o
r
m
u
l
ti
-
clas
s
cl
ass
i
f
icatio
n
o
n
an
S
VM
o
u
tp
u
t
la
y
er
.
2
.
3
.
T
ra
ns
f
er
lea
rning
(
T
L
)
T
L
is
a
M
L
tec
h
n
iq
u
e
t
h
at
e
m
p
lo
y
s
k
n
o
w
led
g
e
f
r
o
m
a
p
r
io
r
m
o
d
el
to
tack
le
a
n
e
w
r
e
lated
p
r
o
b
lem
.
A
p
p
l
y
in
g
s
u
c
h
T
L
m
et
h
o
d
,
d
em
o
n
s
tr
ate
o
n
e
’
s
k
n
o
w
led
g
e
f
r
o
m
a
b
ig
-
lab
elled
d
ataset
li
k
e
I
m
ag
eNe
t to
a
p
lan
t
d
is
ea
s
e
class
i
f
icat
io
n
tas
k
.
I
n
f
o
tr
an
s
f
er
r
i
n
g
i
s
a
p
ar
t
o
f
n
ar
r
o
w
in
g
d
o
w
n
th
e
g
e
n
er
aliza
tio
n
er
r
o
r
an
d
s
h
o
r
ten
i
n
g
t
h
e
n
et
w
o
r
k
tr
ai
n
i
n
g
ti
m
e
b
y
u
tili
zi
n
g
t
h
e
m
o
d
e
l
w
h
ich
is
alr
ea
d
y
d
e
v
elo
p
ed
as
a
n
e
w
to
o
l.
T
h
is
o
u
tco
m
e
is
a
ttrib
u
tab
l
e
to
th
e
f
ac
t
t
h
at
T
L
h
elp
s
u
s
tr
ai
n
DL
m
o
d
els
f
ir
s
tl
y
w
h
e
n
d
o
n
e
m
o
r
e
q
u
ick
l
y
an
d
ac
cu
r
atel
y
b
ec
au
s
e
k
n
o
w
led
g
e
an
d
p
atter
n
s
in
a
p
ar
ticu
lar
d
o
m
a
in
ar
e
tr
an
s
f
er
r
ed
to
th
e
o
th
er
o
n
e
[
2
4
]
,
[
2
5
]
.
T
h
e
m
u
ltit
u
d
e
o
f
C
NN
m
o
d
el
s
alr
ea
d
y
p
r
e
-
tr
ain
ed
ar
e
a
h
u
g
e
n
u
m
b
er
av
ailab
le
f
o
r
u
s
e.
T
o
p
th
r
ee
p
r
e
-
tr
ain
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
E
n
s
emb
le
lea
r
n
in
g
w
eig
h
ted
a
ve
r
a
g
e
meta
-
cla
s
s
ifier
fo
r
p
a
lm
d
is
ea
s
es
…
(
S
o
fia
n
e
A
b
d
en
)
307
C
NNs
m
o
d
el
s
:
I
n
ce
p
tio
n
V3
,
R
esNet5
0
,
De
n
s
eNe
t2
0
1
h
as
b
ee
n
s
elec
ted
d
u
e
to
t
h
eir
u
n
i
q
u
e
ad
v
a
n
ta
g
es
a
n
d
co
m
p
le
m
e
n
tar
y
ca
p
ab
ilit
ie
s
in
f
ea
tu
r
e
e
x
tr
ac
tio
n
a
n
d
i
m
a
g
e
class
i
f
icatio
n
.
E
ac
h
m
o
d
el
w
as
tr
ain
ed
f
o
r
te
n
ep
o
ch
s
w
it
h
co
n
s
i
s
te
n
t
p
ar
a
m
eter
s
,
in
cl
u
d
i
n
g
a
d
en
s
e
la
y
e
r
w
i
th
5
1
2
u
n
i
ts
,
R
e
L
U
ac
ti
v
atio
n
,
a
n
i
n
p
u
t
s
h
ap
e
o
f
2
2
4
×
224
×
3
,
an
d
a
d
r
o
p
o
u
t
r
ate
o
f
0
.
3
to
av
o
id
o
v
er
f
itti
n
g
.
T
o
p
r
eser
v
e
lear
n
ed
f
ea
t
u
r
es,
t
h
e
in
itial
te
n
la
y
er
s
o
f
ea
ch
m
o
d
el
w
er
e
f
r
o
ze
n
.
A
f
ter
th
e
tr
ain
in
g
an
d
v
alid
atio
n
s
tag
e,
t
h
ese
T
L
m
o
d
els
w
a
s
te
s
ted
o
n
o
u
r
lo
ca
l d
ataset.
T
h
e
m
o
d
el
s
ar
e
d
ef
in
ed
i
n
th
e
f
o
llo
w
i
n
g
s
ec
tio
n
.
2
.
3
.
1
.
I
ncept
io
nV3
P
r
o
p
o
s
ed
b
y
Sze
g
ed
y
e
t
a
l.,
is
a
d
ee
p
C
NN
ar
ch
itect
u
r
e
th
at
d
e
m
o
n
s
tr
ated
its
p
er
f
o
r
m
an
ce
an
d
w
o
n
th
e
f
ir
s
t
p
lace
in
th
e
2
0
1
4
L
ar
g
e
-
s
ca
le
I
m
a
g
eNe
t
v
i
s
u
al
r
ec
o
g
n
i
tio
n
ch
al
len
g
e
(
I
L
SV
R
C
)
.
I
n
ce
p
tio
n
-
v
3
tak
e
s
in
i
n
p
u
t
S
h
ap
e
o
f
2
4
4
b
y
2
4
4
p
ix
els,
Un
iq
u
e
ele
m
e
n
ts
o
f
t
h
is
m
o
d
el
i
n
cl
u
d
e
th
e
f
u
ll
y
co
n
n
ec
ted
(
F
C
)
la
y
er
,
b
atch
n
o
r
m
a
lizatio
n
,
a
n
d
co
n
v
o
l
u
tio
n
a
l
la
y
er
s
,
w
h
ich
m
ea
n
s
it
is
d
i
f
f
er
en
t
t
h
a
n
it
s
p
r
ed
ec
ess
o
r
s
[
2
6
]
.
2
.
3
.
2
.
Resnet
5
0
He
et
a
l.
(
2
0
1
6
)
in
v
en
ted
th
e
s
h
o
r
t
f
o
r
m
r
esid
u
al
n
et
w
o
r
k
(
R
esNet)
,
a
DL
ar
ch
itect
u
r
e
f
r
eq
u
en
tl
y
u
s
ed
f
o
r
i
m
a
g
e
clas
s
i
f
icatio
n
ap
p
licatio
n
s
.
T
h
eir
ar
ch
itect
u
r
e
u
s
e
s
s
k
ip
co
n
n
ec
tio
n
s
,
allo
w
i
n
g
t
h
e
g
r
ad
ie
n
t
to
s
k
ip
s
o
m
e
la
y
er
s
i
n
b
et
w
ee
n
an
d
f
lo
w
d
ir
ec
tl
y
f
r
o
m
t
h
e
i
n
p
u
t
to
t
h
e
o
u
tp
u
t,
w
h
ic
h
co
n
s
is
ts
o
f
5
0
la
y
er
s
,
to
ad
d
r
ess
th
e
is
s
u
es
o
f
v
an
i
s
h
in
g
g
r
ad
ien
t
s
an
d
n
et
w
o
r
k
d
eg
r
ad
atio
n
in
D
L
.
I
n
f
o
r
m
a
tio
n
is
p
r
o
p
ag
ated
th
r
o
u
g
h
th
e
n
et
w
o
r
k
u
s
i
n
g
r
esid
u
al
b
lo
ck
s
,
w
h
ich
i
m
p
r
o
v
es p
r
ed
ictio
n
ac
cu
r
ac
y
[
2
7
]
.
2
.
3
.
3
.
Densenet
2
0
1
Den
s
e
n
et2
0
1
I
s
a
s
o
p
h
i
s
ticate
d
DL
ar
ch
itect
u
r
e
d
esig
n
ed
to
tack
le
s
th
e
v
a
n
i
s
h
i
n
g
g
r
ad
ie
n
t
p
r
o
b
lem
an
d
is
a
p
ar
t
o
f
t
h
e
De
n
s
eN
et
f
a
m
il
y
.
W
ith
2
0
1
la
y
er
s
,
i
t
s
u
r
p
as
s
es
t
h
e
o
r
ig
i
n
al
s
tr
u
c
tu
r
e
in
co
m
p
lex
it
y
.
Den
s
e
n
et2
0
1
is
co
m
p
o
s
ed
o
f
s
tiff
d
en
s
e
b
lo
ck
s
w
it
h
ti
g
h
tl
y
p
ac
k
ed
lay
er
s
.
E
v
er
y
la
y
er
f
o
cu
s
es
o
n
ta
k
i
n
g
i
n
in
f
o
r
m
atio
n
f
r
o
m
t
h
e
la
y
er
s
b
ef
o
r
e
it,
m
ap
p
in
g
t
h
e
r
es
u
lti
n
g
f
ea
tu
r
es.
T
h
is
m
e
th
o
d
p
r
o
m
o
te
s
f
ea
tu
r
e
r
e
u
s
e
an
d
m
ak
e
s
s
m
o
o
th
g
r
ad
ien
t p
r
o
p
ag
atio
n
ea
s
ier
,
w
h
ic
h
ev
e
n
t
u
all
y
i
m
p
r
o
v
e
s
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
[
2
4
]
.
2
.
4
.
E
ns
e
m
ble
lea
rn
ing
(
E
L
)
W
ith
t
h
e
h
elp
o
f
f
u
s
io
n
m
et
h
o
d
s
,
d
if
f
er
e
n
t
m
o
d
els
ar
e
m
er
g
ed
in
en
s
e
m
b
le
s
m
o
d
ellin
g
i
n
o
r
d
er
to
r
ea
ch
th
e
h
i
g
h
er
-
le
v
el
p
r
ed
ictio
n
co
n
f
id
e
n
ce
an
d
b
etter
g
en
e
r
aliza
tio
n
in
M
L
d
o
m
ain
.
No
t
w
it
h
s
tan
d
i
n
g
,
s
in
ce
s
in
g
le
m
o
d
el
er
r
o
r
s
n
ex
t
to
o
t
h
er
m
o
d
els
ca
n
b
e
co
r
r
ec
ted
,
t
h
e
tea
m
's
s
co
r
e
b
ec
o
m
es
m
u
c
h
b
etter
th
an
th
at
o
f
a
n
y
g
i
v
e
n
m
o
d
e
l
a
l
o
n
e
.
T
h
e
t
h
r
e
e
p
r
i
m
a
r
y
t
y
p
e
s
o
f
E
L
t
e
c
h
n
i
q
u
e
s
a
r
e
b
o
o
s
t
i
n
g
,
s
t
a
c
k
i
n
g
,
a
n
d
b
a
g
g
i
n
g
[
2
5
]
,
[
2
8
]
.
I
n
th
is
s
tu
d
y
th
r
ee
T
L
m
o
d
els
:
R
esNet5
0
,
I
n
ce
p
tio
n
V3
,
an
d
Den
s
eNe
t2
0
1
,
w
er
e
co
m
b
in
e
d
to
d
ev
elo
p
ed
an
E
L
m
o
d
el.
T
h
e
f
i
n
al
p
r
ed
ictio
n
s
w
er
e
m
ad
e
u
s
i
n
g
a
w
e
i
g
h
ted
a
v
er
ag
e
m
eta
-
clas
s
i
f
ier
.
P
r
e
d
ictio
n
s
w
er
e
co
llected
f
r
o
m
ea
ch
o
f
t
h
e
tr
ain
ed
b
ase
m
o
d
els
a
n
d
s
to
r
ed
in
an
.
h
5
f
ile.
T
h
e
b
ase
m
o
d
el
s
w
er
e
tr
ain
ed
o
n
a
p
u
b
licl
y
av
ailab
le
p
al
m
d
atas
et.
A
cc
u
r
ac
y
,
F1
-
s
co
r
e,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
o
t
h
er
p
er
f
o
r
m
an
ce
m
etr
ics
w
er
e
u
s
ed
to
ass
es
s
ea
ch
b
ase
m
o
d
el's
ef
f
ec
ti
v
en
e
s
s
u
s
i
n
g
a
lo
ca
l
test
in
g
d
ataset
ca
p
tu
r
ed
in
B
ac
h
ar
r
eg
io
n
.
E
ac
h
m
o
d
el
w
a
s
g
i
v
en
a
w
ei
g
h
t
ac
c
o
r
d
in
g
to
h
o
w
w
ell
it
p
er
f
o
r
m
ed
;
m
o
d
els
w
it
h
lar
g
er
w
ei
g
h
t
s
p
er
f
o
r
m
ed
b
etter
.
T
h
e
f
in
al
p
r
ed
ictio
n
s
a
n
d
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
w
ei
g
h
ted
a
v
er
ag
e
E
L
w
er
e
o
b
tain
ed
u
s
i
n
g
t
h
e
lo
ca
l d
ataset.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
E
x
peri
m
ent
a
l set
up
T
o
p
e
r
f
o
r
m
th
e
n
ec
e
s
s
ar
y
ex
p
er
im
e
n
t
s
,
t
h
e
s
t
u
d
y
w
as
i
m
p
le
m
en
ted
th
r
o
u
g
h
P
y
t
h
o
n
s
cr
ip
ts
an
d
ex
ec
u
ted
o
n
Go
o
g
le
C
o
lab
o
r
ato
r
y
(
Go
o
g
le
C
o
lab
)
,
lev
er
ag
i
n
g
its
ac
ce
s
s
to
g
r
ap
h
ics
p
r
o
c
ess
i
n
g
u
n
it
s
(
GP
Us)
an
d
T
en
s
o
r
P
r
o
ce
s
s
in
g
U
n
it
s
(
T
P
Us)
ca
p
ab
ilit
ies
u
p
to
1
2
G
B
o
f
R
AM
.
T
h
e
d
ate
p
al
m
d
at
aset
w
a
s
u
p
lo
ad
ed
to
Go
o
g
le
Dr
iv
e
a
n
d
i
m
p
o
r
ted
in
to
t
h
e
C
o
lab
en
v
ir
o
n
m
en
t
u
s
in
g
a
la
p
to
p
eq
u
ip
p
ed
w
it
h
a
n
I
n
te
l
i5
p
r
o
ce
s
s
o
r
an
d
r
u
n
n
in
g
W
in
d
o
w
s
1
0
.
T
h
e
al
g
o
r
ith
m
s
w
er
e
d
e
v
elo
p
ed
u
s
i
n
g
s
ev
er
al
lib
r
ar
ies,
s
u
ch
a
s
Sc
ik
it
-
lear
n
,
Seab
o
r
n
,
Nu
m
P
y
,
P
an
d
as,
an
d
Ma
tp
lo
tlib
.
Go
o
g
le
C
o
lab
w
a
s
s
elec
ted
f
o
r
its
e
f
f
icie
n
c
y
an
d
ea
s
e
o
f
u
s
e,
o
f
f
er
i
n
g
a
r
eliab
le
an
d
s
p
ee
d
y
p
latf
o
r
m
f
o
r
DL
m
o
d
els tr
ai
n
i
n
g
a
n
d
an
al
y
s
i
s
.
3
.
2
.
E
v
a
lua
t
i
o
n
m
et
rics
A
cc
u
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
F
1
-
s
co
r
e,
an
d
co
n
f
u
s
io
n
m
atr
i
x
ar
e
th
e
p
er
f
o
r
m
a
n
ce
e
v
al
u
ati
o
n
m
etr
ic
s
u
s
ed
f
o
r
an
al
y
zin
g
th
e
M
L
m
o
d
els.
Fo
r
a
g
iv
en
cla
s
s
,
ac
cu
r
ac
y
i
s
d
ef
in
ed
as
th
e
r
ate
o
f
co
r
r
ec
tly
id
en
ti
f
ie
d
s
a
m
p
les o
u
t o
f
t
h
e
to
tal
n
u
m
b
er
o
f
s
a
m
p
les i
n
t
h
at
clas
s
.
T
h
is
m
etr
ic
i
s
d
ef
i
n
ed
w
i
th
t
h
e
(
1
)
.
A
c
c
ura
c
y
=
+
+
+
+
(
1
)
tp
: tr
u
e
p
o
s
itiv
e
s
,
tn
: tr
u
e
n
e
g
a
tiv
es,
fp
:
f
alse p
o
s
iti
v
es,
fn
:
f
al
s
e
n
e
g
ati
v
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
A
p
r
il
20
2
5
:
3
0
3
-
311
308
P
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
ar
e
esti
m
ated
u
t
ilizi
n
g
t
h
e
m
a
th
e
m
atica
l (
2
)
–
(
4
)
r
esp
ec
tiv
ely
.
=
+
(
2
)
=
+
(
3
)
1
−
=
2
(
p
r
e
cis
i
o
n
∗
r
ecal
l
)
p
r
e
cis
i
o
n
+
r
ecal
l
(
4
)
Hig
h
p
r
ec
is
io
n
i
n
d
icate
s
th
a
t
ev
er
y
p
r
ed
icted
i
m
a
g
e
i
s
a
p
al
m
lea
f
clas
s
,
r
eg
ar
d
les
s
o
f
t
h
e
n
u
m
b
er
o
f
m
is
c
lass
if
ied
p
al
m
d
is
ea
s
es.
On
th
e
o
th
er
h
a
n
d
,
g
o
o
d
r
ec
all
o
r
(
s
en
s
itiv
i
t
y
)
r
ep
r
esen
t
t
h
e
m
ea
s
u
r
e
o
f
th
e
p
r
o
p
o
r
tio
n
o
f
th
e
ac
tu
al
p
o
s
iti
v
e
p
al
m
lea
f
clas
s
t
h
at
w
er
e
cl
ass
i
f
ied
co
r
r
ec
tly
,
r
eg
ar
d
les
s
o
f
h
o
w
m
an
y
t
h
in
g
s
w
er
e
i
n
co
r
r
ec
tl
y
c
lass
if
ied
.
T
h
e
F1
-
s
co
r
e
is
t
h
e
h
ar
m
o
n
ic
m
ea
s
u
r
e
o
f
p
r
ec
is
io
n
a
n
d
r
ec
all.
Ulti
m
atel
y
,
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
v
ar
io
u
s
M
L
m
o
d
els
u
n
d
er
in
v
e
s
ti
g
atio
n
w
a
s
in
ter
p
r
eted
u
s
i
n
g
co
n
f
u
s
io
n
m
atr
ice
s
.
3
.
3
.
Resul
t
s
a
na
ly
s
is
a
nd
dis
cus
s
io
n
T
h
is
s
tu
d
y
u
ti
lized
v
ar
io
u
s
o
f
M
L
m
o
d
els
to
ca
teg
o
r
ize
d
ate
p
al
m
leaf
i
m
a
g
es.
F
u
r
th
e
r
m
o
r
e,
th
e
b
en
ef
it
o
f
th
e
s
u
g
g
e
s
ted
ap
p
r
o
ac
h
is
th
at
p
al
m
p
lan
t
ill
n
es
s
es
ca
n
b
e
r
ec
o
g
n
ized
at
an
e
ar
l
y
s
ta
g
e.
Fo
r
th
i
s
p
u
r
p
o
s
e,
E
L
,
C
NN
-
SVM
a
n
d
th
r
ee
T
L
m
o
d
els,
r
u
n
o
n
p
alm
d
ataset
co
n
tai
n
i
n
g
2
,
6
3
1
i
m
ag
e
s
d
iv
id
ed
o
n
3
class
es
test
ed
in
o
u
r
lo
ca
l
d
at
aset
co
n
tai
n
i
n
g
4
3
0
i
m
a
g
es.
Mo
r
eo
v
er
,
th
er
e
is
a
lack
o
f
s
tu
d
ie
s
f
o
cu
s
i
n
g
o
n
ap
p
ly
i
n
g
E
L
to
lo
ca
l
p
al
m
d
atasets
,
w
h
ic
h
ar
e
es
s
en
t
ial
f
o
r
en
h
a
n
ci
n
g
ac
cu
r
ac
y
i
n
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
w
it
h
E
L
.
B
y
co
m
b
in
in
g
s
e
v
er
al
T
L
m
o
d
els
to
i
m
p
r
o
v
e
p
al
m
d
is
e
ase
ca
teg
o
r
izatio
n
,
t
h
is
w
o
r
k
clo
s
es
th
e
g
ap
.
T
h
e
f
o
llo
w
in
g
d
is
c
u
s
s
io
n
p
r
o
v
id
es
a
co
m
p
r
eh
e
n
s
iv
e
e
v
al
u
atio
n
o
f
th
ese
m
o
d
el
s
’
p
er
f
o
r
m
an
ce
.
T
r
a
i
n
i
n
g
a
C
N
N
u
s
in
g
a
SV
M
c
l
ass
if
i
e
r
d
em
o
n
s
t
r
a
te
d
s
ig
n
if
i
c
an
t
ef
f
i
ci
en
cy
in
p
a
lm
d
is
e
ase
c
l
a
s
s
if
ic
a
t
i
o
n
.
T
h
is
a
p
p
r
o
a
ch
y
i
e
l
d
e
d
a
c
o
m
m
en
d
a
b
l
e
t
r
a
in
i
n
g
a
c
cu
r
a
cy
o
f
9
5
.
8
3
%
an
d
a
v
ali
d
a
t
i
o
n
a
c
cu
r
a
cy
o
f
9
4
.
1
7
%
.
H
o
w
ev
e
r
,
w
h
en
t
e
s
te
d
o
n
th
e
l
o
c
a
l
d
at
a
s
e
t
,
T
h
e
C
N
N
-
S
VM
a
ch
ie
v
e
d
th
e
l
o
w
e
r
t
e
s
tin
g
a
c
cu
r
a
cy
o
f
9
4
%
,
w
h
ic
h
w
a
s
th
e
l
o
w
est
am
o
n
g
al
l
m
o
d
el
s
ev
a
lu
at
ed
.
T
L
em
p
l
o
y
in
g
p
r
e
-
t
r
ai
n
e
d
m
o
d
e
l
s
s
u
ch
a
s
I
n
c
e
p
ti
o
n
V
3
,
D
en
s
e
N
et
2
0
1
,
an
d
R
es
N
e
t
5
0
,
w
a
s
a
ls
o
as
s
e
s
s
e
d
.
V
e
r
y
a
c
ce
p
t
a
b
l
e
r
e
s
u
lt
s
w
e
r
e
y
i
e
l
d
e
d
b
y
th
e
I
n
c
e
p
ti
o
n
V
3
m
o
d
e
l
:
th
e
t
r
a
in
i
n
g
a
n
d
v
a
l
i
d
at
i
o
n
a
cc
u
r
a
cy
w
e
r
e
9
9
.
8
6
%
,
9
7
.
3
5
%
,
r
es
p
ec
t
iv
e
ly
.
T
h
e
t
es
ti
n
g
a
c
c
u
r
ac
y
c
o
m
p
r
is
e
d
9
7
%
.
T
h
e
D
e
s
n
e
N
et
2
0
1
a
n
d
R
es
-
N
e
t5
0
a
r
c
h
i
t
e
ct
u
r
e
s
s
h
o
w
e
d
n
o
t
b
a
d
o
u
t
c
o
m
e
s
t
o
o
:
9
9
.
8
2
%
a
n
d
9
9
.
0
1
%
,
9
6
.
6
1
%
a
n
d
9
7
.
4
4
%
,
9
6
%
a
n
d
9
7
%
f
o
r
t
r
a
in
in
g
,
v
al
i
d
a
ti
o
n
an
d
t
e
s
t
in
g
a
c
cu
r
a
cy
,
r
e
s
p
e
c
t
iv
ely
.
T
h
e
E
L
t
e
ch
n
i
q
u
e
w
as
th
e
m
o
s
t
im
p
r
e
s
s
iv
e
in
t
h
is
s
es
s
i
o
n
,
u
t
il
i
z
in
g
a
w
e
ig
h
t
e
d
av
e
r
ag
e
m
e
t
a
-
c
l
a
s
s
if
ie
r
,
c
o
m
b
in
e
d
p
r
e
d
i
ct
i
o
n
s
f
r
o
m
th
e
p
r
ev
i
o
u
s
ly
m
en
tio
n
e
d
T
L
m
e
th
o
d
s
.
B
y
ass
ig
n
in
g
w
e
ig
h
ts
b
a
s
e
d
o
n
e
a
c
h
m
o
d
e
l’
s
p
e
r
f
o
r
m
an
ce
,
E
L
a
ch
i
ev
e
d
t
h
e
h
ig
h
es
t
p
e
r
f
o
r
m
a
n
c
e
am
o
n
g
a
ll
m
o
d
e
ls
.
th
e
p
er
f
o
r
m
an
c
e
a
n
aly
s
i
s
,
i
n
t
e
r
m
s
o
f
t
r
a
i
n
i
n
g
a
n
d
v
a
l
i
d
a
t
i
o
n
a
c
c
u
r
a
c
y
,
p
r
e
c
i
s
i
o
n
,
r
e
c
a
l
l
a
n
d
F
1
s
c
o
r
e
o
f
a
l
l
m
o
d
e
l
s
,
i
s
i
l
l
u
s
t
r
a
t
e
d
i
n
T
a
b
l
e
2
.
E
L
a
ch
i
e
v
e
d
a
t
r
a
in
in
g
a
c
cu
r
ac
y
o
f
9
9
.
9
4
%
a
n
d
a
v
a
li
d
a
t
i
o
n
a
c
c
u
r
a
cy
o
f
9
8
.
1
4
%
af
t
e
r
t
en
e
p
o
c
h
s
,
as
s
h
o
w
n
in
F
ig
u
r
e
3
,
w
i
th
a
t
es
t
in
g
a
c
cu
r
a
cy
o
f
9
8
%
,
in
d
ic
a
t
in
g
it
s
r
o
b
u
s
tn
es
s
in
c
la
s
s
if
y
in
g
l
o
c
a
l
s
am
p
le
s
,
a
l
l
E
L
p
r
e
d
i
ct
i
o
n
r
e
s
u
l
ts
o
n
th
e
t
e
s
t
d
a
t
as
e
t
h
a
v
e
b
e
e
n
il
lu
s
t
r
a
t
e
d
in
Fi
g
u
r
es
4
.
Sp
e
c
i
f
i
c
a
lly
,
Fi
g
u
r
e
4
(
a
)
r
e
p
r
e
s
en
ts
th
e
c
l
as
s
i
f
i
c
a
ti
o
n
t
e
s
t
r
e
p
o
r
t
,
w
h
i
l
e
F
ig
u
r
e
4
(
b
)
s
h
o
w
s
th
e
E
L
c
o
n
f
u
s
i
o
n
m
at
r
ix
w
ith
d
is
e
a
s
e
l
a
b
e
ls
.
T
ab
le
2
.
Mo
d
el’
s
p
er
f
o
r
m
a
n
ce
in
ter
m
s
o
f
ev
a
lu
at
io
n
m
etr
ics
M
o
d
e
l
s
Ev
a
l
u
a
t
i
o
n
me
t
r
i
c
s
B
r
o
w
n
sp
o
t
s
H
e
a
l
t
h
y
W
h
i
t
e
sca
l
e
T
r
a
i
n
i
n
g
a
c
c
u
r
a
c
y
V
a
l
i
d
a
t
i
o
n
a
c
c
u
r
a
c
y
C
N
N
-
S
V
M
P
r
e
c
i
si
o
n
0
.
9
8
0
.
9
2
0
.
9
2
0
.
9
5
8
3
0
.
9
4
1
7
R
e
c
a
l
l
0
.
9
7
0
.
9
3
0
.
9
3
F1
-
S
c
o
r
e
0
.
9
7
0
.
9
2
0
.
9
2
TL
I
n
c
e
p
t
i
o
n
V
3
P
r
e
c
i
si
o
n
1
.
0
0
0
.
9
5
0
.
9
5
0
.
9
9
8
6
0
.
9
7
3
5
R
e
c
a
l
l
0
.
9
6
1
.
0
0
1
.
0
0
F1
-
S
c
o
r
e
0
.
9
8
0
.
9
7
0
.
9
7
TL
D
e
n
se
N
e
t
2
0
1
P
r
e
c
i
si
o
n
0
.
9
7
0
.
9
6
0
.
9
6
0
.
9
9
8
2
0
.
9
6
6
1
R
e
c
a
l
l
0
.
9
6
0
.
9
7
0
.
9
7
F1
-
S
c
o
r
e
0
.
9
7
0
.
9
7
0
.
9
7
TL
R
e
sN
e
t
5
0
P
r
e
c
i
si
o
n
1
.
0
0
0
.
9
5
0
.
9
5
0
.
9
9
0
1
0
.
9
7
4
4
R
e
c
a
l
l
0
.
9
5
0
.
9
9
0
.
9
9
F1
-
S
c
o
r
e
0
.
9
7
0
.
9
7
0
.
9
7
En
se
mb
l
e
l
e
a
r
n
i
n
g
P
r
e
c
i
si
o
n
0
.
9
7
0
.
9
9
0
.
9
9
0
.
9
9
9
4
0
.
9
8
1
4
R
e
c
a
l
l
1
.
0
0
0
.
9
6
0
.
9
6
F1
-
S
c
o
r
e
0
.
9
9
0
.
9
8
0
.
9
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
E
n
s
emb
le
lea
r
n
in
g
w
eig
h
ted
a
ve
r
a
g
e
meta
-
cla
s
s
ifier
fo
r
p
a
lm
d
is
ea
s
es
…
(
S
o
fia
n
e
A
b
d
en
)
309
Fig
u
r
e
3
.
T
r
ain
in
g
an
d
v
a
lid
ati
o
n
ac
cu
r
ac
y
u
s
i
n
g
en
s
e
m
b
le
m
eth
o
d
(
a)
(
b
)
Fig
u
r
e
4
.
E
L
m
o
d
el
p
er
f
o
r
m
a
n
ce
o
n
test
d
ataset
(
a)
E
L
c
las
s
i
f
icatio
n
r
ep
o
r
t
an
d
(
b
)
E
L
c
o
n
f
u
s
io
n
m
atr
i
x
C
o
m
p
ar
ed
to
p
r
io
r
s
tu
d
ies
as
s
h
o
w
n
i
n
T
ab
le
3
,
o
u
r
ap
p
r
o
ac
h
n
o
t
o
n
l
y
d
e
m
o
n
s
tr
ates
s
u
p
er
io
r
ac
cu
r
ac
y
b
u
t
al
s
o
ad
d
r
ess
es
t
h
e
c
h
alle
n
g
e
s
o
f
w
o
r
k
i
n
g
w
i
t
h
a
lo
ca
ll
y
co
llected
d
ataset,
u
n
l
ik
e
s
t
u
d
ies
[
1
5
]
,
[
1
8
]
,
an
d
[
2
0
]
,
w
h
ich
p
r
i
m
ar
il
y
r
el
y
o
n
p
u
b
lic
d
atas
et.
M
o
r
eo
v
er
,
o
n
l
y
a
f
e
w
s
t
u
d
ies,
s
u
c
h
a
s
[
1
1
]
,
h
av
e
e
m
p
lo
y
ed
E
L
,
b
u
t
t
h
e
y
to
o
w
er
e
r
estricte
d
to
p
u
b
lic
d
atasets
.
T
h
e
w
ei
g
h
ted
av
er
ag
e
m
et
a
-
clas
s
i
f
ier
an
d
th
e
b
ase
p
r
etr
ain
ed
m
o
d
els
u
s
ed
in
o
u
r
E
L
d
i
s
ti
n
g
u
is
h
e
s
o
u
r
w
o
r
k
f
r
o
m
o
th
er
s
,
o
f
f
er
in
g
a
n
o
v
el
m
et
h
o
d
f
o
r
lev
er
ag
i
n
g
th
e
s
tr
en
g
t
h
s
o
f
m
u
ltip
le
c
h
o
s
en
m
o
d
els
to
ac
h
i
ev
e
b
etter
r
esu
lt
s
.
A
n
d
p
r
o
v
i
d
es
a
m
o
r
e
r
o
b
u
s
t
s
o
lu
tio
n
,
en
h
a
n
ci
n
g
o
v
er
all
p
e
r
f
o
r
m
an
ce
a
n
d
r
ed
u
cin
g
t
h
e
r
is
k
o
f
m
is
cla
s
s
i
f
icatio
n
.
T
h
is
f
i
n
d
in
g
s
u
p
p
o
r
ts
o
u
r
h
y
p
o
t
h
esi
s
th
at
E
L
w
o
u
ld
o
u
tp
er
f
o
r
m
i
n
d
iv
id
u
al
m
o
d
el
s
,
p
ar
ticu
lar
l
y
w
h
en
ap
p
lied
to
lo
ca
l
d
atasets
,
as
d
em
o
n
s
tr
ated
i
n
s
tu
d
ie
s
[
7
]
an
d
[
1
6
]
.
A
d
d
itio
n
all
y
,
th
e
r
e
s
u
lts
in
d
icate
th
at
in
te
g
r
ati
n
g
d
iv
er
s
e
m
o
d
el
s
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
ca
n
s
i
g
n
if
ic
an
tl
y
i
m
p
r
o
v
e
cla
s
s
i
f
icatio
n
o
u
tco
m
e
s
.
T
ab
le
3
.
A
cc
u
r
ac
y
co
m
p
ar
is
o
n
o
f
o
u
r
p
r
o
p
o
s
ed
s
tu
d
y
w
it
h
s
i
m
ilar
liter
at
u
r
e
s
t
u
d
ies
R
e
f
/
Y
e
a
r
A
p
p
r
o
a
c
h
P
a
l
m l
e
a
f
d
a
t
a
se
t
c
l
a
sse
s
D
a
t
a
se
t
so
u
r
c
e
B
e
st
a
c
c
u
r
a
c
y
[
7
]
/
2
0
2
0
C
N
N
,
S
V
M
B
r
o
w
n
sp
o
t
s,
W
h
i
t
e
sc
a
l
e
,
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
,
L
e
a
f
smu
t
,
H
e
a
l
t
h
y
K
a
g
g
l
e
,
Jo
r
d
a
n
v
a
l
l
e
y
9
9
%.
[
1
1
]
/
2
0
2
0
S
V
M
,
K
N
N
,
a
n
d
EL
:
R
F
,
L
i
g
h
t
G
B
M
.
H
e
a
l
t
h
y
,
W
h
i
t
e
sca
l
e
K
a
g
g
l
e
9
8
.
2
9
%
[
1
5
]
/
2
0
2
3
R
e
sn
e
t
a
n
d
TL
:
I
n
c
e
p
t
i
o
n
B
r
o
w
n
sp
o
t
s,
H
e
a
l
t
h
y
,
W
h
i
t
e
sca
l
e
K
a
g
g
l
e
9
9
.
6
2
%
[
1
6
]
/
2
0
2
0
C
N
N
S
u
d
d
e
n
d
e
c
l
i
n
e
sy
n
d
r
o
me
C
o
l
l
e
c
t
e
d
man
u
a
l
l
y
8
9
.
4
0
%
[
1
8
]
/
2
0
2
2
C
N
N
,
V
G
G
-
1
6
a
n
d
M
o
b
i
l
e
N
e
t
.
B
r
o
w
n
sp
o
t
s,
W
h
i
t
e
sc
a
l
e
,
B
a
c
t
e
r
i
a
l
b
l
i
g
h
t
,
L
e
a
f
smu
t
,
H
e
a
l
t
h
y
K
a
g
g
l
e
9
9
.
1
0
%
[
2
0
]
/
2
0
2
0
V
G
G
,
S
V
M
B
l
i
g
h
t
S
p
o
t
s
,
L
e
a
f
S
p
o
t
s,
R
e
d
p
a
l
m
w
e
e
v
i
l
K
a
g
g
l
e
9
7
.
9
0
%
[
2
1
]
/
2
0
2
4
TL
:
R
e
sN
e
t
5
0
,
D
e
n
se
N
e
t
2
0
1
D
u
b
a
s,
B
u
g
,
H
e
a
l
t
h
y
,
H
o
n
e
y
K
a
g
g
l
e
9
8
.
6
7
%
-
9
9
.
5
4
%
O
u
r
mo
d
e
l
EL
:
TL
(
R
e
sN
e
t
5
0
,
I
n
c
e
p
t
i
o
n
V
3
,
D
e
n
sn
e
t
2
0
1
)
B
r
o
w
n
sp
o
t
s,
H
e
a
l
t
h
y
,
W
h
i
t
e
sca
l
e
K
a
g
g
l
e
,
L
o
c
a
l
-
c
a
p
t
u
r
e
d
d
a
t
a
se
t
9
8
.
1
4
%
-
9
9
.
9
4
%
T
h
e
im
p
lica
tio
n
s
o
f
t
h
is
r
esea
r
ch
ex
te
n
d
b
e
y
o
n
d
t
h
e
s
p
ec
if
i
c
ca
s
e
o
f
p
al
m
d
is
ea
s
e
clas
s
i
f
icatio
n
.
T
h
e
s
u
cc
ess
o
f
th
e
E
L
m
o
d
el
s
u
g
g
est
s
th
at
s
i
m
ilar
E
L
co
u
ld
b
e
ap
p
lied
to
o
th
er
ag
r
icu
lt
u
r
al
ch
alle
n
g
es,
p
o
ten
tiall
y
tr
an
s
f
o
r
m
i
n
g
d
is
e
ase
m
an
a
g
e
m
e
n
t
p
r
ac
tices.
F
u
tu
r
e
r
esear
ch
m
a
y
ex
p
lo
r
e
t
h
e
d
ev
e
lo
p
m
en
t
o
f
m
o
b
ile
ap
p
licatio
n
s
an
d
w
eb
-
b
ased
p
latf
o
r
m
s
t
h
at
lev
er
a
g
e
th
ese
m
o
d
els
f
o
r
r
ea
l
-
ti
m
e
d
etec
tio
n
,
m
a
k
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
8
,
No
.
1
,
A
p
r
il
20
2
5
:
3
0
3
-
311
310
th
ese
ad
v
a
n
ce
d
tech
n
iq
u
e
s
ea
s
y
to
u
s
e
b
y
f
ar
m
er
s
.
A
d
d
itio
n
all
y
,
e
x
p
an
d
i
n
g
t
h
e
r
esear
ch
to
in
clu
d
e
a
w
id
er
v
ar
iet
y
o
f
p
lan
t
d
i
s
ea
s
e
s
an
d
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
co
u
ld
f
u
r
th
er
e
n
h
a
n
ce
t
h
e
m
o
d
el
’
s
u
ti
lit
y
an
d
r
o
b
u
s
tn
es
s
.
Giv
e
n
t
h
at
p
al
m
tr
ee
s
ta
k
e
m
an
y
y
ea
r
s
to
b
ea
r
f
r
u
it,
n
e
g
lecti
n
g
to
i
m
p
le
m
en
t
e
f
f
ec
ti
v
e
d
is
ea
s
e
d
etec
tio
n
m
e
th
o
d
s
,
s
u
c
h
as
th
o
s
e
p
r
o
p
o
s
ed
in
t
h
is
s
t
u
d
y
,
co
u
ld
lead
to
s
ig
n
i
f
ica
n
t
ag
r
icu
ltu
r
al
lo
s
s
e
s
,
p
ar
ticu
lar
l
y
in
d
eser
t
r
eg
io
n
s
w
h
er
e
p
al
m
c
u
lti
v
atio
n
is
ec
o
n
o
m
ical
l
y
v
i
tal.
T
h
e
i
n
teg
r
at
i
o
n
o
f
ad
v
an
ce
d
ML
m
o
d
el
s
,
esp
ec
iall
y
t
h
r
o
u
g
h
E
L
,
o
f
f
er
s
a
p
r
o
m
is
i
n
g
ap
p
r
o
a
ch
to
i
m
p
r
o
v
in
g
t
h
e
ac
c
u
r
ac
y
an
d
e
f
f
icie
n
c
y
o
f
d
is
ea
s
e
d
etec
tio
n
i
n
a
g
r
icu
l
tu
r
e,
p
r
o
v
id
in
g
s
u
b
s
ta
n
tial
b
e
n
e
f
its
f
o
r
b
o
th
f
ar
m
er
s
an
d
t
h
e
b
r
o
ad
er
ag
r
icu
ltu
r
al
in
d
u
s
tr
y
.
A
d
o
p
tin
g
th
e
s
e
m
e
th
o
d
s
is
cr
u
cial
f
o
r
en
s
u
r
i
n
g
s
u
s
t
ain
ab
le
ag
r
ic
u
lt
u
r
al
p
r
ac
tices.
4.
C
O
N
C
L
U
SIO
N
T
h
is
s
t
u
d
y
ex
p
lo
r
ed
th
r
ee
M
L
tech
n
iq
u
es
to
cla
s
s
i
f
y
p
al
m
le
af
d
is
ea
s
e
d
atase
t:
C
NN
-
SV
M
,
T
L
u
s
in
g
(
Den
s
eNe
t2
0
1
,
I
n
ce
p
tio
n
V3
a
n
d
R
es
Net5
0
)
,
an
d
E
L
.
T
h
e
o
u
tco
m
e
s
ill
u
s
tr
ate
th
e
p
o
ten
tia
l
o
f
th
e
s
e
m
o
d
el
s
to
ass
is
t
f
ar
m
er
s
i
n
p
r
ed
ictin
g
an
d
m
a
n
ag
i
n
g
p
al
m
d
is
ea
s
es,
th
er
eb
y
co
n
tr
ib
u
ti
n
g
to
m
o
r
e
e
f
f
ec
ti
v
e
an
d
s
u
s
tai
n
ab
le
ag
r
ic
u
lt
u
r
al
p
r
ac
ti
ce
s
.
C
N
N
-
SVM
ac
h
ie
v
ed
a
d
ec
en
t
te
s
ti
n
g
ac
c
u
r
ac
y
o
f
9
4
%,
in
co
m
p
ar
i
s
o
n
,
T
L
m
o
d
el
s
s
h
o
w
ed
h
ig
h
er
test
i
n
g
ac
cu
r
ac
ies,
w
it
h
De
n
s
eNe
t
2
0
1
,
I
n
ce
p
tio
n
V3
an
d
R
esNe
t5
0
r
ea
ch
in
g
9
6
%,
9
7
%,
an
d
9
7
%,
r
esp
ec
tiv
el
y
.
No
tab
l
y
,
o
u
r
E
L
m
o
d
el,
e
m
p
lo
y
i
n
g
a
W
eig
h
ted
A
v
er
a
g
e
m
eta
-
c
lass
if
ier
,
ac
h
iev
ed
th
e
h
i
g
h
est
test
i
n
g
ac
cu
r
ac
y
o
f
9
8
%.
S
h
o
w
ca
s
i
n
g
it
s
ab
ilit
y
to
e
n
h
an
ce
ac
cu
r
ac
y
b
y
co
m
b
in
i
n
g
m
u
ltip
le
h
i
g
h
-
p
er
f
o
r
m
in
g
c
las
s
if
ier
s
.
T
h
is
r
esu
lt
ali
g
n
s
w
it
h
an
d
e
x
te
n
d
s
p
r
ev
io
u
s
r
esear
c
h
,
h
ig
h
li
g
h
ti
n
g
t
h
e
b
en
ef
it
s
o
f
e
n
s
e
m
b
le
tec
h
n
iq
u
es
i
n
a
g
r
icu
lt
u
r
al
ap
p
licatio
n
s
.
I
m
p
o
r
tan
tl
y
,
o
u
r
s
t
u
d
y
’
s
E
l
m
o
d
el,
ap
p
lied
to
a
lo
ca
ll
y
ca
p
tu
r
ed
p
al
m
d
ataset,
r
ep
r
esen
ts
a
s
ig
n
i
f
ica
n
t
ad
v
a
n
ce
m
e
n
t
i
n
p
al
m
d
is
ea
s
e
clas
s
if
icatio
n
,
esp
ec
iall
y
g
iv
e
n
t
h
e
ch
all
e
n
g
es
o
f
li
m
ite
d
lo
ca
l
d
ata
an
d
co
m
p
lex
d
is
e
ases
id
en
ti
f
icat
io
n
.
Fu
tu
r
e
r
es
ea
r
ch
s
h
o
u
ld
f
o
cu
s
o
n
r
ef
in
i
n
g
th
e
s
e
m
o
d
els
an
d
d
ev
elo
p
in
g
p
r
ac
tical
to
o
ls
,
s
u
ch
as
a
m
o
b
ile
ap
p
s
,
f
o
r
r
ea
l
-
ti
m
e
p
al
m
d
is
ea
s
e
id
en
ti
f
icatio
n
.
A
d
d
itio
n
a
ll
y
,
e
x
ten
d
i
n
g
th
is
ap
p
r
o
ac
h
t
o
o
th
er
p
lan
t
d
is
ea
s
es
a
n
d
en
v
ir
o
n
m
en
t
co
u
ld
f
u
r
t
h
er
i
m
p
r
o
v
e
its
ap
p
licab
ilit
y
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
E
.
H
.
C
h
o
w
d
h
u
r
y
e
t
a
l
.
,
“
A
u
t
o
mat
i
c
a
n
d
r
e
l
i
a
b
l
e
l
e
a
f
d
i
se
a
se
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
t
e
c
h
n
i
q
u
e
s
,”
A
g
ri
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
2
9
4
–
3
1
2
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
e
n
g
i
n
e
e
r
i
n
g
3
0
2
0
0
2
0
.
[
2
]
M
.
A
l
t
a
l
a
k
,
M
.
A
mm
a
d
u
d
d
i
n
,
A
.
A
l
a
j
mi
,
a
n
d
A
.
R
i
z
g
,
“
S
mart
a
g
r
i
c
u
l
t
u
r
e
a
p
p
l
i
c
a
t
i
o
n
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
o
l
o
g
i
e
s:
a
su
r
v
e
y
,”
Ap
p
l
.
S
c
i
.
,
v
o
l
.
1
2
,
n
o
.
1
2
,
p
.
5
9
1
9
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
2
5
9
1
9
.
[
3
]
M
.
I
.
H
o
ssai
n
,
S
.
Ja
h
a
n
,
M
.
R
.
A
l
A
si
f
,
M
.
S
a
msu
d
d
o
h
a
,
a
n
d
K
.
A
h
me
d
,
“
D
e
t
e
c
t
i
n
g
t
o
ma
t
o
l
e
a
f
d
i
se
a
se
s
b
y
i
mag
e
p
r
o
c
e
ssi
n
g
t
h
r
o
u
g
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
s,”
S
m
a
rt
A
g
r
i
c
u
l
t
u
r
a
l
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
5
,
n
o
.
4
,
p
.
1
0
0
3
0
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
e
c
h
.
2
0
2
3
.
1
0
0
3
0
1
.
[
4
]
T
.
D
a
sz
k
i
e
w
i
c
z
,
“
F
o
o
d
p
r
o
d
u
c
t
i
o
n
i
n
t
h
e
c
o
n
t
e
x
t
o
f
g
l
o
b
a
l
d
e
v
e
l
o
p
me
n
t
a
l
c
h
a
l
l
e
n
g
e
s
,”
Ag
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
2
,
n
o
.
6
,
p
.
8
3
2
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
2
0
6
0
8
3
2
.
[
5
]
Y
.
N
o
u
t
f
i
a
a
n
d
E.
R
o
p
e
l
e
w
sk
a
,
“
I
n
n
o
v
a
t
i
v
e
mo
d
e
l
s
b
u
i
l
t
b
a
se
d
o
n
i
mag
e
t
e
x
t
u
r
e
s
u
si
n
g
t
r
a
d
i
t
i
o
n
a
l
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
d
i
st
i
n
g
u
i
s
h
i
n
g
d
i
f
f
e
r
e
n
t
v
a
r
i
e
t
i
e
s o
f
mo
r
o
c
c
a
n
d
a
t
e
p
a
l
m fr
u
i
t
(
P
h
o
e
n
i
x
d
a
c
t
y
l
i
f
e
r
a
L
.
)
,
”
Ag
ri
c
u
l
t
u
r
e
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
2
6
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
3
0
1
0
0
2
6
.
[
6
]
C
.
T
.
C
h
a
o
a
n
d
R
.
R
.
K
r
u
e
g
e
r
,
“
T
h
e
da
t
e
p
a
l
m
(
P
h
o
e
n
i
x
d
a
c
t
y
l
i
f
e
r
a
L
.
)
:
O
v
e
r
v
i
e
w
o
f
b
i
o
l
o
g
y
,
u
se
s,
a
n
d
c
u
l
t
i
v
a
t
i
o
n
,”
H
o
rt
S
c
i
e
n
c
e
,
v
o
l
.
4
2
,
n
o
.
5
,
p
p
.
1
0
7
7
–
1
0
8
2
,
2
0
0
7
,
d
o
i
:
1
0
.
2
1
2
7
3
/
H
O
R
T
S
C
I
.
4
2
.
5
.
1
0
7
7
.
[
7
]
M
.
A
l
-
S
h
a
l
o
u
t
,
K
.
M
a
n
so
u
r
,
K
.
E.
A
l
-
Q
a
w
a
smi,
a
n
d
M
.
R
a
sm
i
,
“
C
l
a
ss
i
f
y
i
n
g
d
a
t
e
p
a
l
m
t
r
e
e
d
i
s
e
a
se
s
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
2
I
n
t
e
rn
a
t
i
o
n
a
l
E
n
g
i
n
e
e
r
i
n
g
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
r
i
c
a
l
,
En
e
rg
y
,
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
EI
C
E
EAI)
,
2
0
2
2
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
EI
C
EEA
I
5
6
3
7
8
.
2
0
2
2
.
1
0
0
5
0
4
2
6
.
[
8
]
J.
M
.
A
l
-
K
h
a
y
r
i
,
S
.
M
.
Jai
n
,
a
n
d
D
.
V
.
Jo
h
n
so
n
,
D
a
t
e
Pa
l
m
G
e
n
e
t
i
c
Re
s
o
u
r
c
e
s a
n
d
U
t
i
l
i
za
t
i
o
n
,
Ja
n
u
a
r
y
2
0
1
6
.
D
o
r
d
r
e
c
h
t
:
S
p
r
i
n
g
e
r
N
e
t
h
e
r
l
a
n
d
s,
2
0
1
5
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
94
-
0
1
7
-
9
6
9
4
-
1.
[
9
]
S
.
K
h
i
r
a
n
i
,
H
.
B
o
u
t
a
j
,
C
.
El
M
o
d
a
f
a
r
,
a
n
d
A
.
O
.
E.
K
h
e
l
i
l
,
“
A
r
b
u
scu
l
a
r
m
y
c
o
r
r
h
i
z
a
l
f
u
n
g
i
a
sso
c
i
a
t
e
d
w
i
t
h
d
a
t
e
p
a
l
m
i
n
O
u
a
r
g
l
a
r
e
g
i
o
n
(
S
o
u
t
h
e
a
s
t
e
r
n
A
l
g
e
r
i
a
)
,
”
Pl
a
n
t
C
e
l
l
B
i
o
t
e
c
h
n
o
l
o
g
y
An
d
M
o
l
e
c
u
l
a
r B
i
o
l
o
g
y
,
v
o
l
.
2
1
,
n
o
.
4
5
–
4
6
,
p
p
.
1
5
–
2
8
,
2
0
2
0
.
[
1
0
]
H
.
R
h
i
n
a
n
e
,
A
.
B
a
n
n
a
r
i
,
M
.
M
a
a
n
a
n
,
a
n
d
N
.
A
d
e
r
d
o
u
r
,
“
P
a
l
m
t
r
e
e
s
c
r
o
w
n
d
e
t
e
c
t
i
o
n
a
n
d
d
e
l
i
n
e
a
t
i
o
n
f
r
o
m
v
e
r
y
h
i
g
h
sp
a
t
i
a
l
r
e
so
l
u
t
i
o
n
i
mag
e
s
u
si
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
(U
-
N
e
t
)
,
”
2
0
2
1
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
G
e
o
s
c
i
e
n
c
e
a
n
d
Re
m
o
t
e
S
e
n
si
n
g
S
y
m
p
o
si
u
m
I
G
ARS
S
,
2
0
2
1
,
p
p
.
6
5
1
6
–
6
5
1
9
.
d
o
i
:
1
0
.
1
1
0
9
/
I
G
A
R
S
S
4
7
7
2
0
.
2
0
2
1
.
9
5
5
4
4
7
0
.
[
1
1
]
A
.
H
e
ssan
e
,
A
.
El
Y
o
u
sse
f
i
,
Y
.
F
a
r
h
a
o
u
i
,
B
.
A
g
h
o
u
t
a
n
e
a
n
d
F
.
A
mo
u
n
a
s
,
"
A
mac
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
f
r
a
me
w
o
r
k
f
o
r
a
st
a
g
e
-
w
i
se
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
d
a
t
e
p
a
l
m
w
h
i
t
e
sc
a
l
e
d
i
se
a
se
,
"
i
n
B
i
g
D
a
t
a
Mi
n
i
n
g
a
n
d
An
a
l
y
t
i
c
s
,
v
o
l
.
6
,
n
o
.
3
,
p
p
.
2
6
3
-
2
7
2
,
2
0
2
3
,
d
o
i
:
1
0
.
2
6
5
9
9
/
B
D
M
A
.
2
0
2
2
.
9
0
2
0
0
2
2
.
[
1
2
]
A
.
B
i
n
N
a
e
e
m
e
t
a
l
.
,
“
Ea
r
l
y
g
e
n
d
e
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
d
a
t
e
p
a
l
m
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
i
n
g
&
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
4
,
n
o
.
2
,
2
0
2
3.
[
1
3
]
A
.
M
a
g
si
,
J
.
A
h
me
d
M
a
h
a
r
,
a
n
d
S
.
H
.
D
a
n
w
a
r
,
“
D
a
t
e
f
r
u
i
t
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
a
n
d
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,”
I
n
d
i
a
n
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
n
o
.
3
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
7
4
8
5
/
i
j
st
/
2
0
1
9
/
v
1
2
i
3
2
/
1
4
6
4
4
1
.
[
1
4
]
M
.
L
i
,
G
.
Z
h
o
u
,
A
.
C
h
e
n
,
L
.
L
i
,
a
n
d
Y
.
H
u
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
t
o
mat
o
l
e
a
f
d
i
se
a
se
s
b
a
se
d
o
n
L
M
B
R
N
e
t
,
”
En
g
i
n
e
e
r
i
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
2
3
,
p
.
1
0
6
1
9
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
3
.
1
0
6
1
9
5
.
[
1
5
]
M
.
A
h
me
d
a
n
d
A
.
A
h
me
d
,
“
P
a
l
m
t
r
e
e
d
i
se
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
u
si
n
g
r
e
si
d
u
a
l
n
e
t
w
o
r
k
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
o
f
i
n
c
e
p
t
i
o
n
R
e
sN
e
t
,
”
PL
o
S
O
n
e
,
v
o
l
.
1
8
,
n
o
.
3
,
p
.
e
0
2
8
2
2
5
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
2
2
5
0
.
[
1
6
]
A
.
M
a
g
si
,
J.
A
.
M
a
h
a
r
,
M
.
A
.
R
a
z
z
a
q
,
a
n
d
S
.
H
.
G
i
l
l
,
“
D
a
t
e
p
a
l
m
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
i
o
n
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
2
0
2
0
I
EEE
2
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
M
u
l
t
i
t
o
p
i
c
C
o
n
f
e
re
n
c
e
(
I
N
MI
C
)
,
2
0
2
0
,
v
o
l
.
1
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
N
M
I
C
5
0
4
8
6
.
2
0
2
0
.
9
3
1
8
1
5
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
E
n
s
emb
le
lea
r
n
in
g
w
eig
h
ted
a
ve
r
a
g
e
meta
-
cla
s
s
ifier
fo
r
p
a
lm
d
is
ea
s
es
…
(
S
o
fia
n
e
A
b
d
en
)
311
[
1
7
]
A
.
A
l
si
r
h
a
n
i
,
M
.
H
.
S
i
d
d
i
q
i
,
A
.
M
.
M
o
st
a
f
a
,
M
.
Ez
z
,
a
n
d
A
.
A
.
M
a
h
mo
u
d
,
“
A
n
o
v
e
l
c
l
a
ssi
f
i
c
a
t
i
o
n
mo
d
e
l
o
f
d
a
t
e
f
r
u
i
t
d
a
t
a
se
t
u
si
n
g
d
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
1
2
,
n
o
.
3
,
p
.
6
6
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
0
3
0
6
6
5
.
[
1
8
]
M
.
A
b
u
-
z
a
n
o
n
a
,
S
.
El
a
i
w
a
t
,
S
.
Y
o
u
n
i
s,
N
.
I
n
n
a
b
,
a
n
d
M
.
M
.
K
a
mr
u
z
z
a
man
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
p
a
l
m
t
r
e
e
s
d
i
se
a
se
s
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
,”
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
,
n
o
.
6
,
p
p
.
9
4
3
–
9
4
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
J
A
C
S
A
.
2
0
2
2
.
0
1
3
0
6
1
1
1
.
[
1
9
]
L
.
K
h
r
i
j
i
,
A
.
C
h
i
h
e
b
,
a
n
d
M
.
A
w
a
d
a
l
l
a
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
t
t
e
c
h
n
i
q
u
e
s
f
o
r
p
a
l
m
d
a
t
e
v
a
r
i
e
t
i
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
,”
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
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
1
,
n
o
.
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
J
A
C
S
A
.
2
0
2
0
.
0
1
1
0
9
5
8
.
[
2
0
]
H
.
A
l
a
a
,
K
.
W
a
l
e
e
d
,
M
.
S
a
m
i
r
,
M
.
T
a
r
e
k
,
H
.
S
o
b
e
a
h
,
a
n
d
M
.
A
.
S
a
l
a
m
,
“
A
n
i
n
t
e
l
l
i
g
e
n
t
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
p
a
l
m
t
r
e
e
s
d
i
se
a
se
s
u
si
n
g
i
mag
e
p
r
o
c
e
ssi
n
g
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s(
I
J
AC
S
A)
,
v
o
l
.
1
1
,
n
o
.
7
,
p
p
.
4
3
4
–
4
4
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
J
A
C
S
A
.
2
0
2
0
.
0
1
1
0
7
5
7
.
[
2
1
]
S
.
M
.
N
.
N
o
b
e
l
e
t
a
l
.
,
“
P
a
l
m
l
e
a
f
h
e
a
l
t
h
ma
n
a
g
e
me
n
t
:
a
h
y
b
r
i
d
a
p
p
r
o
a
c
h
f
o
r
a
u
t
o
ma
t
e
d
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
n
d
t
h
e
r
a
p
y
e
n
h
a
n
c
e
me
n
t
,
”
i
n
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
9
0
9
7
-
9
1
1
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
5
1
9
1
2
.
[
2
2
]
Z
.
L
i
,
S
.
D
e
n
g
,
Y
.
H
o
n
g
,
Z
.
W
e
i
,
a
n
d
L
.
C
a
i
,
“
A
n
o
v
e
l
h
y
b
r
i
d
C
N
N
–
S
V
M
me
t
h
o
d
f
o
r
l
i
t
h
o
l
o
g
y
i
d
e
n
t
i
f
i
c
a
t
i
o
n
i
n
sh
a
l
e
r
e
se
r
v
o
i
r
s
b
a
se
d
o
n
l
o
g
g
i
n
g
me
a
su
r
e
me
n
t
s
,
”
J
o
u
rn
a
l
o
f
A
p
p
l
i
e
d
G
e
o
p
h
y
s
i
c
s
,
p
.
1
0
5
3
4
6
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
p
p
g
e
o
.
2
0
2
4
.
1
0
5
3
4
6
.
[
2
3
]
K
.
S
.
V
a
i
d
y
a
,
P
.
M
.
P
a
t
i
l
,
a
n
d
M
.
A
l
a
g
i
r
i
s
a
my
,
“
H
y
b
r
i
d
C
N
N
-
S
V
M
c
l
a
s
s
i
f
i
e
r
f
o
r
h
u
m
a
n
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
R
O
I
e
x
t
r
a
c
t
i
o
n
a
n
d
f
e
a
t
u
r
e
f
u
s
i
o
n
,”
W
i
r
e
l
e
s
s
P
e
r
s
o
n
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
2
,
n
o
.
2
,
p
p
.
1
0
9
9
–
1
1
3
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
7
7
-
023
-
1
0
6
5
0
-
7.
[
2
4
]
A
.
N
.
S
e
t
t
y
,
R
.
T
.
M
a
t
h
a
d
,
K
.
S
h
e
n
t
h
a
r
,
a
n
d
L
i
k
h
i
t
h
,
“
Ev
a
l
u
a
t
i
o
n
o
f
f
i
l
t
e
r
i
n
g
a
n
d
c
o
n
t
r
a
st
i
n
X
-
r
a
y
a
n
d
c
o
mp
u
t
e
r
i
z
e
d
t
o
mo
g
r
a
p
h
y
sca
n
l
u
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
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
(
I
J
EE
C
S
)
,
v
o
l
.
3
3
,
n
o
.
3
,
p
p
.
1
7
1
5
–
1
7
2
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
3
3
.
i
3
.
p
p
1
7
1
5
-
1
7
2
5
.
[
2
5
]
W
.
P
r
a
st
i
w
i
n
a
r
t
i
,
M
.
K
.
D
e
l
i
may
a
n
t
i
,
H
.
K
u
r
n
i
a
w
a
n
,
Y
.
P
.
P
r
a
t
a
ma,
H
.
W
e
n
d
h
o
,
a
n
d
R
.
A
d
i
,
“
Ef
f
i
c
i
e
n
t
p
a
c
k
a
g
i
n
g
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
:
l
e
v
e
r
a
g
i
n
g
p
r
e
-
t
r
a
i
n
e
d
v
i
si
o
n
mo
d
e
l
s
t
h
r
o
u
g
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
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
(
I
J
EEC
S
)
,
v
o
l
.
3
4
,
n
o
.
3
,
p
p
.
2
0
9
6
–
2
1
0
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
3
4
.
i
3
.
p
p
2
0
9
6
-
2
1
0
6
.
[
2
6
]
S
.
B
.
G
o
t
t
i
p
a
t
i
a
n
d
G
.
T
h
u
mb
u
r
,
“
M
u
l
t
i
-
mo
d
a
l
f
u
si
o
n
d
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
a
c
c
u
r
a
t
e
b
r
a
i
n
t
u
mo
r
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
mag
n
e
t
i
c
r
e
so
n
a
n
c
e
i
mag
i
n
g
i
mag
e
s,”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
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
(
I
J
EE
C
S
)
,
v
o
l
.
3
4
,
n
o
.
2
,
p
p
.
8
2
5
–
8
3
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
3
4
.
i
2
.
p
p
8
2
5
-
8
3
4
.
[
2
7
]
Z
.
T
.
O
m
e
r
a
n
d
A
.
H
.
A
b
b
a
s,
“
I
mag
e
a
n
o
mal
i
e
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
o
f
r
e
sn
e
t
-
5
0
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
d
o
n
e
si
a
n
J
o
u
rn
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
(
I
J
EEC
S
)
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
1
9
8
–
2
0
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
2
7
.
i
1
.
p
p
1
9
8
-
2
0
5
.
[
2
8
]
H
.
L
i
,
Y
.
Ji
n
,
J.
Z
h
o
n
g
,
a
n
d
R
.
Z
h
a
o
,
“
A
f
r
u
i
t
t
r
e
e
d
i
se
a
se
d
i
a
g
n
o
si
s mo
d
e
l
b
a
se
d
o
n
st
a
c
k
i
n
g
e
n
se
mb
l
e
l
e
a
r
n
i
n
g
,
”
C
o
m
p
l
e
x
i
t
y
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
1
2
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
6
8
6
8
5
9
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
M
r
.
S
o
fia
n
e
Abd
e
n
H
e
stu
d
ied
c
o
m
p
u
ter
sc
ien
c
e
a
t
t
h
e
T
a
h
ri
M
o
h
a
m
m
e
d
u
n
iv
e
rsity
o
f
Be
c
h
a
r,
A
l
g
e
ria.
H
e
e
a
rn
e
d
a
m
a
ste
r
d
e
g
r
e
e
in
a
d
v
a
n
c
e
d
in
f
o
rm
a
ti
o
n
sy
ste
m
in
2
0
1
2
.
He
is
a
P
h
.
D.
st
u
d
e
n
t
i
n
T
a
h
ri
M
o
h
a
m
e
d
u
n
iv
e
rsity
o
f
Be
c
h
a
r.
Lab
o
ra
to
ry
o
f
In
f
o
rm
a
ti
o
n
P
ro
c
e
ss
in
g
a
n
d
T
e
le
c
o
m
m
u
n
ica
ti
o
n
s
(LT
I
T
).
His
re
s
e
a
rc
h
in
tere
sts
a
r
e
s
m
a
rt
a
g
ricu
lt
u
re
,
m
a
c
h
in
e
lea
rn
in
g
,
c
o
m
p
u
ter v
isio
n
a
n
d
ima
g
e
p
ro
c
e
ss
i
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
b
d
a
n
.
so
u
fy
a
n
e
@u
n
iv
-
b
e
c
h
a
r.
d
z
;
a
b
d
e
n
so
f
ian
e
0
8
@g
m
a
il
.
c
o
m
.
Dr
.
M
o
ste
fa
B
e
n
d
ji
m
a
i
s a
n
a
ss
o
c
iate
p
ro
f
e
ss
o
r
a
t
th
e
f
a
c
u
lt
y
o
f
e
x
a
c
t
s
c
ien
c
e
s
,
c
o
m
p
u
ter
sc
ien
c
e
d
e
p
a
rtm
e
n
t.
T
a
h
ri
M
o
h
a
m
e
d
Un
iv
e
rsity
o
f
Be
c
h
a
r.
He
re
c
e
iv
e
d
a
P
h
.
D
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
th
e
Un
iv
e
rsity
o
f
T
le
m
c
e
n
,
A
l
g
e
ria.
He
h
a
s
p
u
b
li
s
h
e
d
re
se
a
rc
h
p
a
p
e
rs
in
v
a
rio
u
s
c
o
n
f
e
r
e
n
c
e
s
a
n
d
j
o
u
r
n
a
ls.
His
m
a
in
re
se
a
rc
h
in
tere
st
is
W
irele
ss
S
e
n
so
r
Ne
tw
o
rk
s
(W
S
N),
s
m
a
rt
a
g
ricu
lt
u
re
,
d
a
ta
sc
ien
c
e
s
a
n
d
c
o
m
p
u
ter
n
e
tw
o
rk
in
g
,
m
o
b
il
e
a
g
e
n
ts,
s
m
a
rt
s
y
ste
m
s
a
n
d
c
o
m
m
u
n
ica
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
e
n
d
j
im
a
.
m
o
ste
f
a
@u
n
iv
-
b
e
c
h
a
r.
d
z
.
Dr
.
S
o
u
m
ia
B
e
n
k
r
a
m
a
i
s
c
u
rre
n
tl
y
a
n
a
ss
o
c
iate
p
ro
f
e
ss
o
r
a
t
th
e
f
a
c
u
lt
y
o
f
e
x
a
c
t
s
c
ien
c
e
s,
c
o
m
p
u
ter sc
ien
c
e
d
e
p
a
rtm
e
n
t,
Un
iv
e
rsit
y
Tah
ri
M
o
h
a
m
e
d
o
f
Be
c
h
a
r,
A
l
g
e
ria.
S
h
e
re
c
e
iv
e
d
a
m
a
ste
r
'
s
a
n
d
P
h
.
D
.
d
e
g
re
e
s
in
c
o
m
p
u
ter
sc
ien
c
e
a
t
th
e
Un
iv
e
rsity
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
M
o
h
a
m
e
d
Bo
u
d
i
a
f
,
Or
a
n
,
A
l
g
e
ria.
He
r
re
se
a
rc
h
a
r
e
a
s
a
r
e
i
m
a
g
e
p
ro
c
e
ss
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
p
a
tt
e
r
n
re
c
o
g
n
i
ti
o
n
,
a
n
d
c
o
m
p
u
tatio
n
a
l
in
telli
g
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
e
n
k
ra
m
a
.
so
u
m
ia@
u
n
iv
-
b
e
c
h
a
r.
d
z
.
Evaluation Warning : The document was created with Spire.PDF for Python.