TELK
O
M
N
I
K
A
Te
l
e
c
ommu
n
i
c
at
i
on
,
C
omp
u
ti
n
g
,
El
e
c
t
r
on
i
c
s
an
d
C
on
tr
o
l
V
ol
.
18
,
N
o
.
2
,
A
pri
l
2020
,
p
p.
726
~
732
IS
S
N
:
1693
-
6930
,
a
c
c
r
e
di
t
e
d
F
i
rs
t
G
r
a
de
by
K
e
m
e
n
ri
s
t
e
kdi
k
t
i
,
D
e
c
r
e
e
N
o:
21
/
E
/
K
P
T
/
2
018
D
O
I:
10
.
129
28/
T
E
L
K
O
M
N
IK
A
.
v1
8i
2
.
1406
2
726
Jou
r
n
al
h
o
m
e
pa
ge
:
ht
t
p:
/
/
j
our
nal
.
uad
.
a
c
.
i
d/
i
nd
e
x
.
php
/
T
E
L
K
O
MNIKA
Pl
a
n
t
sp
e
c
i
e
s
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
a
sed
o
n
l
e
a
f
v
e
n
a
t
i
o
n
f
e
a
t
u
r
e
s usi
n
g
S
V
M
A
gu
s
A
mb
ar
w
a
r
i
1
,
Q
ad
h
l
i
Jafa
r
A
d
r
i
an
2
,
Y
e
n
i
H
e
r
d
i
ye
n
i
3
,
I
r
man
H
e
r
mad
i
4
1
D
e
pa
r
t
m
e
n
t
o
f
I
nf
o
r
m
a
t
i
c
s
E
ng
i
ne
e
r
i
ng
,
U
ni
v
e
r
s
i
t
a
s
T
e
kno
kr
a
t
I
nd
one
s
i
a
,
I
nd
one
s
i
a
1
D
e
pa
r
t
m
e
n
t
o
f
I
nf
o
r
m
a
t
i
c
s
M
a
na
g
e
m
e
n
t
,
P
o
l
i
t
e
kni
k
N
e
ge
r
i
L
a
m
pu
ng,
I
ndon
e
s
i
a
2
D
e
pa
r
t
m
e
n
t
o
f
I
nf
o
r
m
a
t
i
on
S
y
s
t
e
m
,
U
n
i
ve
r
s
i
t
a
s
T
e
k
nok
r
a
t
I
nd
one
s
i
a
,
I
ndo
ne
s
i
a
3
,4
D
e
p
a
r
t
m
e
n
t
of
C
o
m
pu
t
e
r
S
c
i
e
n
c
e
,
I
P
B
U
ni
v
e
r
s
i
t
y
,
I
nd
one
s
i
a
A
r
ti
c
l
e
I
n
fo
A
BS
TR
A
C
T
Ar
t
i
c
l
e
h
i
s
t
or
y
:
Re
c
e
i
v
e
d
S
e
p
7
,
20
19
Re
vi
s
e
d
D
e
c
2
6
,
20
19
A
c
c
e
pt
e
d
F
e
b
6
,
2020
T
he
pu
r
po
s
e
of
t
h
i
s
s
t
udy
i
s
t
o
i
de
n
t
i
f
y
pl
a
nt
s
p
e
c
i
e
s
us
i
ng
l
e
a
f
ve
na
t
i
on
f
e
a
t
u
r
e
s
.
L
e
a
f
ve
n
a
t
i
on
f
e
a
t
u
r
e
s
w
e
r
e
ob
t
a
i
n
e
d
t
hr
ough
t
h
e
e
x
t
r
a
c
t
i
on
of
l
e
a
f
ve
na
t
i
on
f
e
a
t
ur
e
s
.
T
he
l
e
a
f
i
m
a
ge
s
e
g
m
e
n
t
a
t
i
on
w
a
s
p
e
r
f
or
m
e
d
t
o
o
bt
a
i
n
t
he
b
i
na
r
y
i
m
a
ge
of
t
he
l
e
a
f
ve
n
a
t
i
on
w
h
i
c
h
i
s
t
h
e
n
de
t
e
r
m
i
n
e
d
t
h
e
br
a
n
c
h
i
ng
poi
n
t
a
nd
e
nd
i
ng
p
oi
nt
.
F
r
o
m
t
he
s
e
po
i
n
t
s
,
t
he
e
x
t
r
a
c
t
i
on
of
l
e
a
f
ve
na
t
i
on
f
e
a
t
u
r
e
w
a
s
pe
r
f
or
m
e
d
b
y
c
a
l
c
u
l
a
t
i
n
g
t
he
va
l
u
e
o
f
s
t
r
a
i
gh
t
n
e
s
s
,
a
di
f
f
e
r
e
nt
a
ngl
e
,
l
e
ng
t
h
r
a
t
i
o
,
s
c
a
l
e
pr
oj
e
c
t
i
o
n,
s
k
e
l
e
t
o
n
l
e
ng
t
h
,
nu
m
be
r
of
s
e
g
m
e
nt
s
,
t
o
t
a
l
s
ke
l
e
t
on
l
e
ngt
h,
nu
m
be
r
of
br
a
nc
h
i
ng
po
i
n
t
s
a
nd
nu
m
be
r
o
f
e
nd
i
ng
po
i
n
t
s
.
S
o
t
ha
t
f
r
o
m
t
h
e
e
x
t
r
a
c
t
i
o
n
of
l
e
a
f
ve
na
t
i
o
n
f
e
a
t
u
r
e
s
19
f
e
a
t
ur
e
s
w
e
r
e
ob
t
a
i
ne
d.
I
de
nt
i
f
i
c
a
t
i
on
of
pl
a
n
t
s
pe
c
i
e
s
w
a
s
c
a
r
r
i
e
d
ou
t
us
i
ng
S
upp
or
t
V
e
c
t
o
r
M
a
c
hi
n
e
(
S
V
M
)
w
i
t
h
R
B
F
k
e
r
n
e
l
.
T
he
l
e
a
r
ni
ng
m
ode
l
w
a
s
bu
i
l
t
us
i
ng
75
%
of
t
he
t
r
a
i
n
i
ng
d
a
t
a
.
T
h
e
t
e
s
t
i
ng
r
e
s
ul
t
s
us
i
n
g
25
%
o
f
t
he
da
t
a
on
t
h
e
t
r
a
i
n
i
ng
m
od
e
l
,
ob
t
a
i
ne
d
a
n
a
c
c
u
r
a
c
y
o
f
82
.
67
%
,
w
i
t
h
a
n
a
ve
r
a
ge
of
p
r
e
c
i
s
i
on
of
8
4%
a
nd
r
e
c
a
l
l
o
f
83
%
.
Ke
y
w
or
d
s
:
F
e
a
t
u
re
e
x
t
ra
c
t
i
on
L
e
a
f
v
e
n
a
t
i
on
SVM
T
hi
s
i
s
an
op
e
n
ac
c
e
s
s
ar
t
i
c
l
e
u
nde
r
t
he
C
C
B
Y
-
SA
l
i
c
e
n
s
e
.
Cor
r
e
s
pon
di
n
g
Au
t
h
or
:
A
gus
A
m
b
a
rw
a
r
i
,
D
e
pa
r
t
m
e
n
t
of
I
nfo
rm
a
t
i
c
s
E
ng
i
ne
e
ri
ng
,
U
ni
ve
rs
i
t
a
s
T
e
kno
kra
t
I
ndon
e
s
i
a
,
J
l
.
Z
a
i
n
a
l
A
bi
d
i
n
P
a
ga
r
A
l
a
m
N
o
.
9
-
11
,
K
e
d
a
t
o
n,
Ba
nda
r
L
a
m
pung
351
32,
Ind
one
s
i
a
.
E
m
a
i
l
:
a
m
ba
rw
a
ri
a
gus
@
t
e
knokr
a
t
.
a
c
.
i
d
1.
I
N
TR
O
D
U
C
TI
O
N
M
a
ny
s
t
ud
i
e
s
t
h
a
t
di
s
c
us
s
t
e
c
hni
que
s
or
m
e
t
h
ods
f
or
i
d
e
nt
i
fyi
ng
p
l
a
n
t
s
,
s
how
t
h
a
t
pl
a
n
t
i
de
nt
i
fi
c
a
t
i
on
i
s
i
m
port
a
n
t
.
T
h
e
s
t
u
dy
of
t
h
e
ph
ys
i
c
a
l
for
m
a
nd
s
t
ru
c
t
ure
of
pl
a
nt
bod
i
e
s
,
know
n
a
s
p
l
a
nt
m
orph
ol
og
y
[1]
.
P
l
a
nt
m
orpho
l
ogy
i
s
us
e
f
ul
for
vi
s
u
a
l
l
y
i
d
e
nt
i
fyi
ng
p
l
a
nt
s
,
s
o
t
h
a
t
p
l
a
n
t
di
v
e
rs
i
t
y
c
a
n
b
e
i
de
nt
i
fi
e
d,
c
l
a
s
s
i
fi
e
d
a
nd
g
i
v
e
n
t
he
ri
g
ht
na
m
e
for
e
a
c
h
grou
p
for
m
e
d.
In
a
dd
i
t
i
on
t
o
de
s
c
ri
bi
ng
t
h
e
s
h
a
pe
a
nd
c
om
pos
i
t
i
on
of
t
he
p
l
a
n
t
body
,
p
l
a
n
t
m
o
rpho
l
ogy
i
s
us
e
ful
f
or
de
t
e
r
m
i
ni
ng
t
h
e
func
t
i
o
n
of
e
a
c
h
pa
r
t
i
n
pl
a
nt
l
i
f
e
.
F
ur
t
he
r
m
or
e
,
t
he
o
ri
g
i
n
a
nd
c
o
m
pos
i
t
i
on
of
t
h
e
pl
a
nt
body
c
a
n
be
k
now
n
[2
]
.
Info
rm
a
t
i
on
a
bout
pl
a
nt
m
orp
hol
o
gy
i
s
n
e
e
d
e
d
t
o
und
e
rs
t
a
nd
e
vo
l
ut
i
on
,
e
c
ol
ogy,
ge
og
ra
ph
i
c
a
l
d
i
s
t
ri
but
i
on
,
c
ons
e
rva
t
i
o
n,
l
i
f
e
c
y
c
l
e
,
a
nd
s
pe
c
i
e
s
de
f
i
ni
t
i
o
n
[3]
.
P
a
rt
s
of
pl
a
n
t
s
t
ha
t
ha
ve
d
i
ffe
r
e
n
t
c
h
a
ra
c
t
e
ri
s
t
i
c
s
fr
om
e
a
c
h
p
l
a
n
t
a
n
d
c
o
m
m
onl
y
us
e
d
for
p
l
a
n
t
i
de
n
t
i
f
i
c
a
t
i
on
a
r
e
l
e
a
ve
s
[4
-
5]
.
L
e
a
ve
s
ha
ve
a
n
i
m
por
t
a
n
t
r
o
l
e
for
pl
a
nt
s
t
o
a
d
a
pt
t
o
t
he
i
r
e
nvi
ronm
e
n
t
[6]
.
T
he
m
a
i
n
f
e
a
t
ur
e
s
o
n
l
e
a
ve
s
t
h
a
t
c
a
n
di
s
t
i
ng
ui
s
h
e
a
c
h
p
l
a
nt
s
p
e
c
i
e
s
i
n
c
l
u
de
s
ha
p
e
[7
-
9]
,
t
e
xt
ur
e
[10
-
1
3]
,
c
ol
or
[1
4]
,
a
nd
l
e
a
f
v
e
na
t
i
o
n
[
15
-
18]
a
re
c
a
l
l
e
d
l
e
a
f
bi
o
m
e
t
ri
c
s
[1
9]
.
A
m
ong
t
hos
e
fe
a
t
ur
e
s
,
t
ha
t
h
a
v
e
uni
q
ue
di
ve
rs
i
t
y
a
nd
c
a
n
de
s
c
ri
b
e
pl
a
nt
c
ha
r
a
c
t
e
r
i
s
t
i
c
s
i
n
m
ore
d
e
t
a
i
l
i
s
l
e
a
f
v
e
na
t
i
o
n,
a
l
t
hough
t
he
r
e
a
r
e
s
o
m
e
s
p
e
c
i
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
P
l
an
t
s
p
e
c
i
e
s
i
d
e
nt
i
f
i
c
a
t
i
on
bas
e
d
on
l
e
a
f
v
e
nat
i
on
f
e
at
ur
e
s
u
s
i
ng
S
V
M
(
A
gus
A
m
bar
war
i
)
727
of
p
l
a
n
t
s
t
h
a
t
h
a
ve
v
a
gu
e
pa
t
t
e
rns
t
h
a
t
a
re
no
t
ve
r
y
c
l
e
a
r
[
20]
.
T
o
ob
t
a
i
n
l
e
a
f
v
e
n
a
t
i
on
pa
t
t
e
rns
,
i
t
c
a
n
b
e
don
e
us
i
ng
f
e
a
t
ure
e
x
t
ra
c
t
i
on
t
e
c
hn
i
que
s
t
hro
ugh
d
i
gi
t
a
l
i
m
a
ge
p
roc
e
s
s
i
n
g
[21
-
22]
,
s
o
t
ha
t
l
e
a
f
ve
na
t
i
on
fe
a
t
ur
e
s
a
re
obt
a
i
ne
d
.
E
xt
r
a
c
t
i
on
of
l
e
a
f
ve
n
a
t
i
on
f
e
a
t
ure
c
a
n
be
done
by
i
m
pl
e
m
e
nt
i
ng
S
e
l
f
-
Inva
ri
a
nt
F
e
a
t
ure
T
ra
ns
form
(S
IF
T
)
[23]
,
F
our
i
e
r
a
n
d
B
-
S
pl
i
n
e
m
ode
l
i
ng
[15]
.
H
ow
e
ve
r
,
t
he
r
e
s
ul
t
s
of
s
e
gm
e
nt
a
t
i
on
a
re
l
e
s
s
t
ha
n
opt
i
m
a
l
be
c
a
us
e
t
he
y
on
l
y
r
e
a
c
h
s
e
c
ond
a
ry
ve
n
a
t
i
on
.
In
a
dd
i
t
i
on,
m
a
ny
pa
r
t
s
of
l
e
a
f
v
e
n
a
t
i
on
a
re
not
s
e
gm
e
n
t
e
d
.
T
he
m
e
t
ho
d
i
s
t
h
e
n
i
m
prove
d
us
i
ng
t
he
H
e
s
s
i
a
n
m
a
t
ri
x
[24]
,
w
hi
c
h
i
s
b
y
i
m
p
l
e
m
e
n
t
i
n
g
a
ve
s
s
e
l
m
e
a
s
ur
e
b
a
s
e
d
on
t
he
e
i
g
e
nv
a
l
u
e
s
of
t
h
e
H
e
s
s
i
a
n
m
a
t
ri
x
.
T
h
e
re
s
u
l
t
i
s
t
ha
t
t
he
s
ys
t
e
m
c
a
n
s
e
gm
e
n
t
l
e
a
f
v
e
na
t
i
o
n
t
o
t
e
rt
i
a
ry
ve
na
t
i
o
n.
In
P
ra
s
t
ya
'
s
s
t
udy
[25]
,
t
h
e
bi
n
a
ry
v
e
na
t
i
on
i
m
a
ge
o
f
t
h
e
e
x
t
ra
c
t
e
d
l
e
a
v
e
s
w
a
s
c
a
l
c
ul
a
t
e
d
f
or
t
h
e
va
l
ue
of
s
t
ra
i
ght
ne
s
s
,
a
d
i
ffe
r
e
n
t
a
ng
l
e
,
l
e
ng
t
h
r
a
t
i
o,
a
nd
s
c
a
l
e
pr
o
j
e
c
t
i
o
n.
T
h
e
s
e
v
a
l
u
e
s
a
r
e
t
h
e
n
us
e
d
a
s
a
m
a
rk
e
r
of
l
e
a
f
ve
n
a
t
i
on
.
O
t
he
r
s
t
ud
i
e
s
c
o
nduc
t
e
d
by
A
m
ba
rw
a
ri
e
t
a
l
.
[1
6]
,
w
ho
pe
r
form
e
d
a
n
a
na
l
ys
i
s
of
l
e
a
f
v
e
na
t
i
on
de
ns
i
t
y
fe
a
t
u
re
s
t
o
obt
a
i
n
t
he
m
os
t
i
m
port
a
nt
fe
a
t
ur
e
s
,
w
h
i
c
h
c
a
n
di
s
t
i
ng
ui
s
h
t
ype
s
of
l
e
a
f
v
e
na
t
i
o
n.
T
he
s
e
fe
a
t
ure
s
by
A
m
b
a
rw
a
r
i
e
t
al
.
[
26]
i
s
us
e
d
t
o
i
d
e
n
t
i
fy
pl
a
n
t
s
b
a
s
e
d
on
t
h
e
t
yp
e
of
v
e
n
a
t
i
on.
H
ow
e
ve
r
,
f
rom
s
om
e
of
t
h
e
s
e
s
t
ud
i
e
s
,
n
o
o
ne
ha
s
i
d
e
nt
i
fi
e
d
t
h
e
pl
a
nt
s
pe
c
i
e
s
.
In
t
h
i
s
s
t
udy
,
i
de
n
t
i
fy
i
ng
pl
a
nt
s
p
e
c
i
e
s
us
i
ng
t
he
l
e
a
f
ve
n
a
t
i
on
fe
a
t
ur
e
.
L
e
a
f
ve
na
t
i
on
fe
a
t
ur
e
s
w
e
r
e
obt
a
i
ne
d
t
h
rough
fe
a
t
u
re
e
x
t
ra
c
t
i
on
.
L
e
a
f
v
e
na
t
i
o
n
f
e
a
t
ure
e
xt
r
a
c
t
i
o
n
w
i
l
l
produ
c
e
s
e
v
e
ra
l
f
e
a
t
ur
e
s
,
i
nc
l
udi
n
g
s
t
r
a
i
gh
t
n
e
s
s
,
a
di
ff
e
r
e
nt
a
ng
l
e
,
l
e
ng
t
h
r
a
t
i
o,
s
c
a
l
e
proj
e
c
t
i
on
[
25]
,
t
o
t
al
s
k
e
l
e
t
on
l
e
ng
t
h
,
num
b
e
r
of
br
anc
hi
ng
poi
nt
s
and
num
b
e
r
of
e
ndi
ng
poi
nt
s
[27]
.
T
h
i
s
l
e
a
f
ve
na
t
i
o
n
fe
a
t
ur
e
w
a
s
us
e
d
t
o
i
d
e
n
t
i
fy
p
l
a
n
t
s
pe
c
i
e
s
by
c
l
a
s
s
i
f
i
c
a
t
i
on
t
e
c
hn
i
que
s
.
T
he
c
l
a
s
s
i
f
i
c
a
t
i
on
t
e
c
hn
i
que
us
e
d
i
s
t
he
S
u
ppor
t
V
e
c
t
o
r
M
a
c
h
i
ne
(S
V
M
).
In
m
a
n
y
c
a
s
e
s
s
u
c
h
a
s
pa
t
t
e
rn
r
e
c
og
ni
t
i
on
,
S
V
M
e
rr
or
r
a
t
e
s
w
h
e
n
t
e
s
t
i
ng
da
t
a
a
re
s
i
gn
i
fi
c
a
nt
l
y
be
t
t
e
r
t
h
a
n
ot
h
e
r
m
e
t
ho
ds
[28
]
.
2.
R
ES
EA
R
C
H
M
ET
H
O
D
2.
1
.
Le
af
i
mag
e
ac
q
u
i
s
i
ti
on
T
he
s
t
a
ge
s
i
n
t
h
i
s
s
t
u
dy
c
ons
i
s
t
e
d
of
s
i
x
s
t
a
g
e
s
a
s
s
how
n
i
n
F
i
gure
1
.
L
e
a
f
i
m
a
g
e
d
a
t
a
us
e
d
a
r
e
F
l
a
v
i
a
da
t
a
s
e
t
[29
]
w
i
t
h
6
s
p
e
c
i
e
s
w
e
r
e
t
a
k
e
n
,
n
a
m
e
l
y
A
e
s
c
ul
us
c
h
i
ne
ns
i
s
,
L
age
r
s
t
r
o
e
m
i
a
i
n
di
c
a
(L
.
)
P
e
r
s
.
,
Ci
nnam
om
um
j
apon
i
c
um
Si
e
b
.
,
C
hi
m
on
ant
hus
pr
ae
c
ox
L
.
,
Il
e
x
m
ac
r
o
c
ar
pa
O
l
i
v
.
,
a
n
d
Ko
e
l
r
e
ut
e
r
i
a
pa
ni
c
ul
a
t
a
L
ax
m
.
T
h
e
num
be
r
of
l
e
a
v
e
s
i
n
e
a
c
h
s
pe
c
i
e
s
i
s
50
l
e
a
f
i
m
a
g
e
s
.
L
e
a
f
i
m
a
ge
s
a
m
p
l
e
s
a
r
e
s
how
n
i
n
F
i
gure
2
.
F
i
gure
1
.
S
t
a
g
e
s
of
re
s
e
a
r
c
h
(a
)
(b)
(c
)
(d)
(e
)
(f)
F
i
gure
2
.
L
e
a
f
i
m
a
g
e
d
a
t
a
,
(
a
)
A
e
s
c
u
l
us
c
hi
n
e
ns
i
s
,
(
b)
L
a
ge
rs
t
roe
m
i
a
i
nd
i
c
a
(
L
.
)
P
e
rs
,
(c
)
C
i
nna
m
o
m
u
m
j
a
pon
i
c
um
S
i
e
b,
(d)
Ch
i
m
o
na
n
t
hus
pra
e
c
o
x
L
,
(
e
)
I
l
e
x
m
a
c
ro
c
a
rp
a
O
l
i
v
,
(f)
K
oe
l
re
u
t
e
r
i
a
p
a
ni
c
ul
a
t
a
l
a
x
m
2.
2
.
S
e
gm
e
n
tat
i
on
Im
a
g
e
s
e
gm
e
nt
a
t
i
on
i
s
t
h
e
pr
oc
e
s
s
of
s
e
p
a
r
a
t
i
ng
i
m
a
ge
s
i
nt
o
hom
og
e
ne
ous
p
a
rt
s
a
nd
e
xt
r
a
c
t
i
ng
t
he
s
e
pa
rt
s
i
nt
o
obj
e
c
t
s
t
h
a
t
w
i
l
l
be
o
bs
e
rv
e
d
s
o
t
ha
t
t
h
e
r
e
gi
o
n
of
i
nt
e
re
s
t
i
s
ob
t
a
i
ne
d
[30]
.
F
rom
t
h
e
a
c
qu
i
s
i
t
i
on
of
l
e
a
f
i
m
a
ge
da
t
a
,
t
h
e
n
i
m
a
g
e
s
e
g
m
e
nt
a
t
i
on
w
a
s
pe
rf
orm
e
d
us
i
ng
t
he
H
e
s
s
i
a
n
m
a
t
r
i
x
[
24]
t
o
ob
t
a
i
n
t
he
l
e
a
f
ve
na
t
i
o
n
s
ha
p
e
.
L
e
a
f
i
m
a
ge
d
a
t
a
fro
m
s
e
g
m
e
nt
a
t
i
on
re
s
u
l
t
s
i
n
t
h
e
for
m
of
l
e
a
f
ve
n
a
t
i
on
b
i
na
ry
i
m
a
g
e
d
a
t
a
s
how
n
i
n
F
i
g
ure
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
1693
-
6930
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
,
V
ol
.
18
,
N
o.
2
,
A
pri
l
2
020:
726
-
7
32
728
(a
)
(b)
(c
)
(d)
(e
)
(f)
F
i
gure
3
.
B
i
na
ry
ve
n
a
t
i
on
l
e
a
f
i
m
a
g
e
da
t
a
,
(
a
)
A
e
s
c
u
l
us
c
h
i
n
e
ns
i
s
,
(b)
L
a
g
e
rs
t
ro
e
m
i
a
i
n
di
c
a
(L
.
)
P
e
rs
.
,
(c
)
Ci
nna
m
o
m
u
m
j
a
po
ni
c
um
S
i
e
b,
(d)
Ch
i
m
ona
n
t
hus
pra
e
c
ox
L
,
(e
)
Il
e
x
m
a
c
r
oc
a
rpa
O
l
i
v
,
(f
)
K
o
e
l
r
e
ut
e
ri
a
pa
ni
c
ul
a
t
a
l
a
xm
2.
3
.
Ext
r
ac
ti
on
of
l
e
af
v
e
n
ati
o
n
f
e
atu
r
e
T
he
l
e
a
f
v
e
n
a
t
i
on
i
m
a
g
e
da
t
a
fro
m
t
h
e
s
e
g
m
e
n
t
a
t
i
on
r
e
s
ul
t
s
,
t
h
e
n
e
xr
a
c
t
i
on
o
f
t
he
l
e
a
f
ve
n
a
t
i
on
fe
a
t
ure
.
L
e
a
f
v
e
na
t
i
o
n
f
e
a
t
ure
e
x
t
r
a
c
t
i
on
w
a
s
o
bt
a
i
n
e
d
fr
om
t
h
e
c
a
l
c
u
l
a
t
i
on
of
t
h
e
v
a
l
ue
of
s
t
ra
i
ght
n
e
s
s
,
di
ff
e
re
nt
a
ng
l
e
,
l
e
ng
t
h
r
a
t
i
o
a
nd
s
c
a
l
e
proj
e
c
t
i
o
n
[25]
,
i
n
o
rde
r
t
o
c
a
l
c
ul
a
t
e
t
he
s
e
va
l
ue
s
fi
rs
t
,
t
he
de
t
e
c
t
i
on
of
br
a
n
c
h
po
i
nt
s
a
nd
en
d
poi
n
t
s
.
Il
l
us
t
r
a
t
i
on
of
l
e
a
f
ve
n
a
t
i
on
fe
a
t
u
re
e
x
t
ra
c
t
i
on
i
s
s
how
n
i
n
F
i
gure
4
.
F
i
gure
4
.
I
l
l
us
t
ra
t
i
on
of
l
e
a
f
v
e
na
t
i
o
n
f
e
a
t
ure
e
xt
r
a
c
t
i
o
n
[1
6]
T
he
no
t
a
t
i
on
of
F
i
gur
e
4
i
s
pr
e
s
e
n
t
e
d
b
e
l
ow
:
x,
y
=
p
i
xe
l
c
oor
di
n
a
t
e
l
j
=
l
e
ng
t
h
of
t
h
e
j
s
e
gm
e
nt
t
h
a
t
r
e
pre
s
e
nt
e
d
by
t
h
e
n
um
b
e
r
of
t
he
p
i
x
e
l
s
d
j
=
d
i
s
t
a
nc
e
b
e
t
w
e
e
n
p
i
xe
l
c
oord
i
n
a
t
e
s
(x
s
,
y
s
)
a
nd
(x
e
,
y
e
)
S
t
ra
i
g
ht
n
e
s
s
i
s
a
m
e
a
s
ure
m
e
n
t
of
t
he
a
l
i
gnm
e
nt
v
a
l
u
e
of
a
s
e
gm
e
nt
.
F
rom
F
i
g
ure
4
,
t
he
s
t
r
a
i
gh
t
n
e
s
s
va
l
u
e
i
s
c
a
l
c
u
l
a
t
e
d
us
i
n
g
(
1).
s
t
r
ai
ght
ne
s
s
=
l
j
d
j
(1)
D
i
ffe
r
e
nt
a
n
gl
e
(
δ
1
)
i
s
a
m
e
a
s
ur
e
m
e
nt
of
t
h
e
a
ngl
e
d
i
ff
e
re
nc
e
be
t
w
e
e
n
c
o
i
nc
i
d
e
nt
s
e
g
m
e
n
t
s
.
F
rom
F
i
gu
re
4
,
di
ffe
r
e
n
t
a
ngl
e
va
l
ue
s
a
r
e
c
a
l
c
ul
a
t
e
d
us
i
ng
t
h
e
(2
).
δ
1
=
|
α
i
-
α
j
|
(2)
i
j
m
k
l
δ
1
δ
2
δ
3
(
x
s
i
,
y
s
i
)
d
j
l
j
P
i
,
j
(
x
s
j
,
y
s
j
)
(
x
e
i,
j
,
y
e
i,
j
)
δ
4
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
P
l
an
t
s
p
e
c
i
e
s
i
d
e
nt
i
f
i
c
a
t
i
on
bas
e
d
on
l
e
a
f
v
e
nat
i
on
f
e
at
ur
e
s
u
s
i
ng
S
V
M
(
A
gus
A
m
bar
war
i
)
729
L
e
ng
t
h
ra
t
i
o
(
R
i
)
i
s
m
e
a
s
ur
e
d
by
c
o
m
p
a
ri
ng
t
he
l
e
ngt
h
o
f
e
a
c
h
s
e
gm
e
nt
w
i
t
h
t
h
e
m
a
xi
m
um
l
e
ng
t
h
of
t
he
s
e
g
m
e
n
t
i
n
a
l
e
a
f
v
e
na
t
i
on
i
m
a
ge
.
F
r
om
F
i
gur
e
4
,
t
h
e
l
e
n
gt
h
r
a
t
i
o
va
l
ue
i
s
c
a
l
c
ul
a
t
e
d
us
i
ng
(3)
R
i
=
l
i
max
(
l
⃗
)
(3)
S
c
a
l
e
P
roj
e
c
t
i
o
n
(
P
i,
j
)
i
s
a
m
e
a
s
ure
m
e
nt
of
proj
e
c
t
i
o
n
l
e
ngt
h
be
t
w
e
e
n
c
o
i
nc
i
de
n
t
s
e
gm
e
nt
s
.
In
F
i
gure
4
,
t
he
pro
j
e
c
t
e
d
l
e
n
gt
h
be
t
w
e
e
n
s
e
g
m
e
n
t
s
i
a
nd
j
i
s
c
a
l
c
u
l
a
t
e
d
u
s
i
ng
(4
)
a
nd
(5)
.
P
i
,
j
=
i
⃗
⋅
j
⃗
(
m
a
x
(
|
i
|
,
|
j
|
)
)
2
(4)
P
i
,
j
=
(
x
e
i
-
x
s
i
)
(
x
e
j
-
x
s
j
)
+
(
y
e
i
-
y
s
i
)
(
y
e
j
-
y
s
j
)
(
max
(
d
i
,
d
j
)
)
2
(5)
T
hi
s
l
e
a
f
v
e
n
a
t
i
on
fe
a
t
ure
e
xt
r
a
c
t
i
on
produ
c
e
s
s
e
v
e
r
a
l
fe
a
t
ur
e
s
,
i
n
c
l
u
di
ng
s
t
ra
i
ght
ne
s
s
,
d
i
ffe
re
n
t
a
ng
l
e
,
l
e
ng
t
h
ra
t
i
o,
s
c
a
l
e
pro
j
e
c
t
i
on
,
s
k
e
l
e
t
on
l
e
ng
t
h,
s
e
g
m
e
nt
,
t
ot
a
l
s
ke
l
e
t
on,
nu
m
be
r
of
br
a
nc
hi
ng
po
i
nt
s
a
nd
nu
m
b
e
r
of
e
ndi
n
g
p
oi
n
t
s
.
2.
4
.
S
V
M
c
l
as
s
i
fi
c
at
i
on
T
he
m
o
de
l
w
a
s
bui
l
t
u
s
i
ng
t
h
e
S
V
M
c
l
a
s
s
i
fi
e
r
w
i
t
h
t
w
o
ke
rne
l
fun
c
t
i
ons
,
t
h
e
RBF
a
nd
L
i
n
e
a
r
k
e
rne
l
s
.
In
t
he
RBF
ke
r
ne
l
func
t
i
on,
p
a
r
a
m
e
t
e
rs
C
a
n
d
ga
m
m
a
(
γ
).
C
i
s
a
p
a
r
a
m
e
t
e
r
t
o
d
e
t
e
r
m
i
n
e
t
h
e
a
m
oun
t
of
p
e
na
l
t
y
due
t
o
a
n
e
rror
i
n
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
on
of
t
r
a
i
n
i
ng
d
a
t
a
,
w
h
i
l
e
γ
i
s
a
pa
r
a
m
e
t
e
r
c
ont
r
ol
l
i
ng
t
he
w
i
dt
h
of
t
h
e
G
a
us
s
i
a
n
func
t
i
on
v
a
ri
a
nt
.
T
he
p
a
ra
m
e
t
e
r
C
va
l
ue
t
ha
t
w
a
s
t
e
s
t
e
d
w
a
s
[1,
10
,
100
,
1000]
a
nd
t
he
p
a
ra
m
e
t
e
r
va
l
ue
γ
t
h
a
t
w
a
s
t
e
s
t
e
d
w
a
s
[1
e
-
1
,
1
e
-
2
,
1
e
-
3
,
1e
-
4]
.
T
h
e
s
e
a
r
c
h
for
t
h
e
b
e
s
t
p
a
r
a
m
e
t
e
r
v
a
l
ue
s
i
s
d
one
us
i
ng
a
gr
i
d
s
e
a
r
c
h
w
i
t
h
5
-
fol
d
c
ros
s
-
v
a
l
i
da
t
i
on
i
n
t
he
t
r
a
i
n
i
ng
d
a
t
a
.
T
h
e
b
e
s
t
pa
i
r
of
C
a
nd
γ
v
a
l
u
e
s
a
re
o
bt
a
i
n
e
d
b
a
s
e
d
o
n
t
he
gre
a
t
e
s
t
a
c
c
u
ra
c
y
v
a
l
ue
a
t
t
he
t
i
m
e
o
f
t
ra
i
ni
n
g
t
he
da
t
a
.
T
he
s
t
a
ge
s
of
t
h
e
S
V
M
c
l
a
s
s
i
fi
c
a
t
i
o
n
pr
oc
e
s
s
a
r
e
s
how
n
i
n
F
i
g
ure
5
.
F
i
gure
5
.
S
t
a
g
e
s
of
t
h
e
S
V
M
c
l
a
s
s
i
f
i
c
a
t
i
on
pro
c
e
s
s
3.
R
ES
U
LTS
A
N
D
A
N
A
LY
S
I
S
T
he
F
l
a
vi
a
da
t
a
s
e
t
[28]
us
e
d
i
n
t
h
i
s
m
e
t
hod
w
a
s
c
hos
e
n
ba
s
e
d
on
t
h
e
e
xt
r
a
c
t
i
on
of
t
he
l
e
a
f
ve
n
a
t
i
on
fe
a
t
ure
.
T
he
F
l
a
vi
a
d
a
t
a
s
e
t
c
ons
i
s
t
s
of
32
s
pe
c
i
e
s
,
t
h
e
r
e
a
r
e
s
o
m
e
s
p
e
c
i
e
s
w
hi
c
h
t
h
e
l
e
a
f
ve
n
a
t
i
on
fe
a
t
ure
s
c
a
nno
t
be
e
xt
r
a
c
t
e
d.
T
h
i
s
i
s
be
c
a
us
e
t
h
e
p
a
t
t
e
rn
of
l
e
a
f
ve
na
t
i
on
w
a
s
not
c
l
e
a
r
l
y
vi
s
i
b
l
e
,
s
o
on
l
y
l
e
a
f
ve
n
a
t
i
on
t
h
a
t
ha
s
a
c
l
e
a
r
pa
t
t
e
rn
w
a
s
c
hos
e
n
.
T
he
n
fr
om
t
hi
s
d
a
t
a
s
e
t
,
e
x
t
r
a
c
t
i
on
of
t
he
l
e
a
f
ve
na
t
i
on
f
e
a
t
ur
e
w
a
s
pe
rfo
r
m
e
d
.
D
a
t
a
re
s
ul
t
i
ng
fro
m
t
h
e
e
xt
ra
c
t
i
on
of
l
e
a
f
ve
n
a
t
i
on
fe
a
t
ur
e
c
ons
i
s
t
of
19
f
e
a
t
ur
e
s
,
i
nc
l
ud
i
ng
m
e
a
n
,
v
a
ri
a
nc
e
,
s
t
a
nda
rd
de
vi
a
t
i
on
(
of
s
t
r
a
i
g
ht
n
e
s
s
,
a
d
i
ffe
r
e
n
t
a
ngl
e
,
l
e
ngt
h
ra
t
i
o
,
s
c
a
l
e
pro
j
e
c
t
i
on,
a
n
d
l
e
ng
t
h)
,
t
o
t
a
l
s
k
e
l
e
t
on
,
e
ndpo
i
nt
,
bra
nc
h
p
oi
n
t
,
a
nd
s
e
gm
e
n
t
.
T
he
va
l
ue
of
t
he
s
e
f
e
a
t
ure
s
h
a
s
a
di
ff
e
r
e
nt
r
a
nge
of
v
a
l
u
e
s
s
o
t
h
a
t
i
t
i
s
n
orm
a
l
i
z
e
d
us
i
ng
M
i
n
-
M
a
x
nor
m
a
l
i
z
a
t
i
o
n.
T
he
da
t
a
i
s
t
he
n
di
v
i
de
d
i
n
t
o
t
ra
i
n
i
ng
d
a
t
a
a
nd
t
e
s
t
i
ng
d
a
t
a
w
i
t
h
75%
port
i
on
of
t
ra
i
ni
ng
d
a
t
a
(
225
da
t
a
)
a
n
d
2
5%
of
t
e
s
t
i
ng
da
t
a
(75
d
a
t
a
).
In
t
h
e
t
ra
i
ni
ng
d
a
t
a
,
t
h
e
b
e
s
t
pa
r
a
m
e
t
e
r
s
e
a
r
c
h
w
a
s
p
e
rfor
m
e
d
t
o
bui
l
d
a
t
ra
i
ni
ng
m
od
e
l
by
a
pp
l
yi
n
g
a
g
ri
d
s
e
a
rc
h
w
i
t
h
5
-
f
ol
d
c
ros
s
-
va
l
i
d
a
t
i
on
.
T
h
e
b
e
s
t
p
a
ra
m
e
t
e
r
s
e
a
rc
h
r
e
s
ul
t
s
a
re
do
ne
by
p
a
i
r
i
ng
t
h
e
pa
ra
m
e
t
e
rs
t
ha
t
h
a
ve
be
e
n
pre
p
a
re
d.
T
h
e
b
e
s
t
pa
r
a
m
e
t
e
rs
a
re
de
t
e
r
m
i
ne
d
ba
s
e
d
on
t
h
e
h
i
gh
e
s
t
a
c
c
ur
a
c
y
.
T
he
p
a
ra
m
e
t
e
r
s
e
a
rc
h
r
e
s
ul
t
s
us
i
ng
t
he
gr
i
d
s
e
a
r
c
h
a
r
e
s
h
ow
n
i
n
T
a
bl
e
1
.
Ba
s
e
d
on
T
a
bl
e
1
ob
t
a
i
ne
d
t
he
hi
ghe
s
t
a
c
c
ura
c
y
of
7
7.
8
%
us
i
ng
t
h
e
RBF
k
e
rn
e
l
.
T
h
e
b
e
s
t
pa
r
a
m
e
t
e
rs
w
e
re
s
e
l
e
c
t
e
d
ba
s
e
d
on
t
he
a
c
c
u
ra
c
y,
t
h
a
t
i
s
t
he
p
a
ra
m
e
t
e
r
v
a
l
u
e
s
C
=
1000
a
n
d
g
a
m
m
a
(
γ
)
=
0
.
1
.
T
hi
s
c
om
b
i
n
a
t
i
on
of
k
e
rn
e
l
a
nd
p
a
ra
m
e
t
e
rs
w
a
s
us
e
d
t
o
bu
i
l
d
t
he
S
V
M
l
e
a
r
ni
ng
m
od
e
l
.
T
he
n
t
h
e
re
s
u
l
t
s
of
t
e
s
t
s
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
1693
-
6930
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
,
V
ol
.
18
,
N
o.
2
,
A
pri
l
2
020:
726
-
7
32
730
c
ondu
c
t
e
d
on
t
h
e
m
o
de
l
t
ha
t
ha
s
b
e
e
n
bu
i
l
t
a
r
e
di
s
pl
a
y
e
d
i
n
t
he
for
m
of
a
c
onfus
i
on
m
a
t
r
i
x.
T
he
r
e
s
ul
t
s
o
f
t
he
c
o
nfus
i
on
m
a
t
ri
x
on
t
h
e
t
e
s
t
i
ng
d
a
t
a
a
ga
i
ns
t
t
h
e
S
V
M
l
e
a
r
ni
ng
m
od
e
l
a
re
s
how
n
i
n
F
i
gur
e
6
.
T
a
b
l
e
1
.
S
e
a
r
c
h
r
e
s
ul
t
s
of
p
a
ra
m
e
t
e
rs
us
i
n
g
t
he
gr
i
d
s
e
a
r
c
h
K
e
rn
e
l
C
G
a
m
m
a
(γ
)
A
c
c
u
ra
c
y
rb
f
1
0
.
1
0
.
6
0
0
rb
f
1
0
.
0
1
0
.
4
1
3
rb
f
1
0
.
0
0
1
0
.
4
1
3
rb
f
1
0
.
0
0
0
1
0
.
4
1
3
rb
f
10
0
.
1
0
.
7
4
2
rb
f
10
0
.
0
1
0
.
5
9
6
rb
f
10
0
.
0
0
1
0
.
4
1
3
rb
f
10
0
.
0
0
0
1
0
.
4
1
3
rb
f
100
0
.
1
0
.
7
5
1
rb
f
100
0
.
0
1
0
.
7
3
8
rb
f
100
0
.
0
0
1
0
.
6
0
0
rb
f
100
0
.
0
0
0
1
0
.
4
1
3
r
b
f
1000
0
.
1
0
.
7
7
8
rb
f
1000
0
.
0
1
0
.
7
5
1
rb
f
1000
0
.
0
0
1
0
.
7
3
8
rb
f
1000
0
.
0
0
0
1
0
.
6
0
0
l
i
n
e
a
r
1
-
0
.
7
1
1
l
i
n
e
a
r
10
-
0
.
7
6
4
l
i
n
e
a
r
100
-
0
.
7
6
0
l
i
n
e
a
r
1000
-
0
.
7
6
4
F
i
gure
6
.
C
onfus
i
o
n
m
a
t
ri
x
Ba
s
e
d
on
t
he
c
onf
us
i
on
m
a
t
r
i
x
F
i
g
ure
6
i
t
c
a
n
be
s
e
e
n
t
h
a
t
of
t
he
s
i
x
s
p
e
c
i
e
s
t
e
s
t
e
d
onl
y
K
oe
l
re
u
t
e
ri
a
pa
ni
c
ul
a
t
a
L
a
x
m
.
s
p
e
c
i
e
s
,
w
h
e
re
a
l
l
t
h
e
da
t
a
i
s
c
orr
e
c
t
l
y
c
l
a
s
s
i
fi
e
d.
W
h
e
re
a
s
t
he
ot
h
e
r
s
pe
c
i
e
s
o
n
a
v
e
ra
ge
h
a
ve
m
i
s
c
l
a
s
s
i
f
i
e
d
be
t
w
e
e
n
2
t
o
3
m
i
s
c
l
a
s
s
i
fi
e
d
d
a
t
a
.
O
v
e
r
a
l
l
,
t
he
a
v
e
r
a
ge
a
c
c
ur
a
c
y
o
bt
a
i
n
e
d
i
n
t
e
s
t
i
ng
d
a
t
a
i
s
82.
67
%.
T
h
i
s
a
c
c
ur
a
c
y
v
a
l
u
e
i
s
f
a
r
b
e
t
t
e
r
t
h
a
n
i
de
nt
i
fyi
ng
l
e
a
ve
s
b
a
s
e
d
on
t
he
t
yp
e
of
l
e
a
f
ve
n
a
t
i
on
d
one
by
A
m
ba
rw
a
ri
e
t
a
l
.
[16
]
.
In
t
he
r
e
s
e
a
rc
h
of
A
m
b
a
rw
a
r
i
e
t
a
l
.
[
1
6]
t
he
h
i
gh
e
s
t
a
c
c
ur
a
c
y
w
a
s
obt
a
i
n
e
d
a
t
77
.
57%
.
O
ne
re
a
s
on
for
t
h
e
s
m
a
l
l
a
c
c
ur
a
c
y
i
s
t
he
a
m
ount
o
f
da
t
a
t
h
a
t
i
s
no
t
t
h
e
s
a
m
e
i
n
e
a
c
h
c
a
t
e
gory
.
In
a
ddi
t
i
on
,
t
he
t
ype
of
l
e
a
f
ve
n
a
t
i
on
c
ons
i
s
t
s
of
s
e
ve
ra
l
di
ff
e
r
e
nt
s
p
e
c
i
e
s
,
s
o
i
t
i
s
pos
s
i
b
l
e
h
a
ve
di
ff
e
r
e
nt
f
e
a
t
ur
e
s
of
l
e
a
f
ve
na
t
i
o
n.
D
e
t
a
i
l
e
d
r
e
s
ul
t
s
of
t
h
e
S
V
M
c
l
a
s
s
i
f
i
c
a
t
i
on
a
r
e
s
h
ow
n
i
n
T
a
b
l
e
2.
Be
s
i
d
e
s
a
c
c
ura
c
y
,
t
o
s
e
e
t
he
p
e
rfor
m
a
n
c
e
of
a
c
l
a
s
s
i
fi
e
r
w
e
ne
e
d
pre
c
i
s
i
o
n
a
nd
re
c
a
l
l
v
a
l
u
e
s
.
B
a
s
e
d
on
T
a
b
l
e
2
i
t
c
a
n
b
e
s
e
e
n
t
h
a
t
t
h
e
s
pe
c
i
e
s
of
A
e
s
c
ul
us
c
hi
n
e
n
s
i
s
a
nd
L
a
g
e
rs
t
ro
e
m
i
a
i
ndi
c
a
(
L
.
)
P
e
rs
.
w
hi
c
h
ha
s
pre
c
i
s
i
on
a
nd
re
c
a
l
l
va
l
ue
s
be
l
ow
80%
.
T
h
i
s
m
e
a
ns
t
ha
t
t
h
e
d
a
t
a
of
t
he
t
w
o
s
p
e
c
i
e
s
a
ff
e
c
t
t
he
d
e
c
r
e
a
s
e
s
of
a
c
c
ura
c
y
.
E
v
e
n
s
o
,
t
h
e
a
v
e
r
a
ge
p
re
c
i
s
i
o
n
a
nd
re
c
a
l
l
ob
t
a
i
ne
d
w
e
re
q
ui
t
e
h
i
gh,
na
m
e
l
y
84
%
for
t
he
v
a
l
u
e
of
pre
c
i
s
i
on
a
nd
8
3%
for
t
he
va
l
ue
of
re
c
a
l
l
.
T
h
i
s
re
s
u
l
t
i
s
v
e
ry
s
m
a
l
l
c
o
m
p
a
re
d
t
o
t
he
s
t
udy
of
W
a
ng
e
t
al
.
[29
],
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
P
l
an
t
s
p
e
c
i
e
s
i
d
e
nt
i
f
i
c
a
t
i
on
bas
e
d
on
l
e
a
f
v
e
nat
i
on
f
e
at
ur
e
s
u
s
i
ng
S
V
M
(
A
gus
A
m
bar
war
i
)
731
w
ho
us
e
d
t
he
l
e
a
f
s
ha
p
e
fe
a
t
ur
e
for
pl
a
nt
i
de
n
t
i
f
i
c
a
t
i
on
.
H
ow
e
ve
r,
t
he
l
e
a
f
v
e
n
a
t
i
on
fe
a
t
ur
e
c
a
n
be
us
e
d
t
o
ob
t
a
i
n
i
nfor
m
a
t
i
on
r
e
l
a
t
e
d
t
o
pl
a
nt
a
n
a
t
o
m
y
s
uc
h
a
s
t
h
e
l
o
c
a
t
i
on
of
pl
a
n
t
s
gr
ow
t
a
nd
e
nvi
ro
nm
e
nt
a
l
c
ondi
t
i
ons
[16]
.
T
a
b
l
e
2
.
D
e
t
a
i
l
e
d
re
s
u
l
t
s
of
t
he
S
V
M
c
l
a
s
s
i
fi
c
a
t
i
on
S
p
e
c
i
e
s
P
re
c
i
s
i
o
n
Re
c
a
l
l
F1
-
s
c
o
re
S
u
p
p
o
rt
A
e
s
c
u
l
u
s
c
h
i
n
e
n
s
i
s
0
.
6
0
0
.
7
5
0
.
6
7
12
L
a
g
e
r
s
t
r
o
e
m
i
a
i
n
d
i
c
a
(L
.
)
P
e
r
s
.
0
.
7
1
0
.
7
7
0
.
7
4
13
Ci
n
n
a
m
o
m
u
m
j
a
p
o
n
i
c
u
m
S
i
e
b
.
0
.
9
2
0
.
8
5
0
.
8
8
13
Ch
i
m
o
n
a
n
t
h
u
s
p
r
a
e
c
o
x
L
.
0
.
9
2
0
.
9
2
0
.
9
2
12
Il
e
x
m
a
c
r
o
c
a
r
p
a
O
l
i
v
.
0
.
9
0
0
.
6
9
0
.
7
8
13
Ko
e
l
r
e
u
t
e
r
i
a
p
a
n
i
c
u
l
a
t
a
L
a
x
m
.
1
.
0
0
1
.
0
0
1
.
0
0
12
A
v
e
ra
g
e
/
t
o
t
a
l
0
.
8
4
0
.
8
3
0
.
8
3
75
4.
C
O
N
C
LU
S
I
O
N
Ide
nt
i
fi
c
a
t
i
o
n
of
pl
a
n
t
s
pe
c
i
e
s
b
a
s
e
d
on
l
e
a
f
ve
n
a
t
i
on
f
e
a
t
ure
s
w
a
s
c
a
rr
i
e
d
out
us
i
ng
t
he
S
V
M
c
l
a
s
s
i
f
i
e
r.
T
he
a
pp
l
i
c
a
t
i
on
of
RBF
k
e
rn
e
l
w
i
t
h
p
a
ra
m
e
t
e
rs
C
a
nd
ga
m
m
a
(
γ
)
i
n
S
V
M
,
i
s
a
bl
e
t
o
c
l
a
s
s
i
fy
pl
a
nt
s
w
i
t
h
a
n
a
c
c
ura
c
y
of
82
.
67
%.
In
a
dd
i
t
i
on
t
o
a
c
c
ur
a
c
y
,
p
e
rfor
m
a
n
c
e
on
S
V
M
i
s
a
l
s
o
m
e
a
s
ure
d
by
a
n
a
v
e
ra
ge
of
pre
c
i
s
i
on
a
nd
r
e
c
a
l
l
w
hi
c
h
i
s
84
%
f
or
pre
c
i
s
i
o
n
a
nd
83%
fo
r
re
c
a
l
l
.
T
h
e
us
e
of
l
e
a
f
ve
n
a
t
i
on
a
s
a
fe
a
t
ur
e
i
n
t
he
i
de
nt
i
fi
c
a
t
i
on
of
p
l
a
n
t
s
p
e
c
i
e
s
c
a
n
be
us
e
d
a
s
a
n
a
l
t
e
rn
a
t
i
ve
w
h
e
n
t
he
l
e
a
ve
s
of
p
l
a
n
t
s
h
a
ve
s
i
m
i
l
a
r
s
h
a
pe
s
a
nd
t
e
xt
u
re
s
.
A
s
for
s
ugg
e
s
t
i
ons
on
s
t
ud
i
e
s
r
e
l
a
t
e
d
t
o
p
l
a
n
t
i
de
nt
i
fi
c
a
t
i
on
,
t
he
pro
c
e
s
s
of
i
de
n
t
i
f
i
c
a
t
i
on
us
i
ng
t
he
f
e
a
t
ure
of
l
e
a
f
v
e
n
a
t
i
on
re
qui
r
e
s
qui
t
e
a
l
on
g
t
i
m
e
,
e
s
pe
c
i
a
l
l
y
a
t
t
h
e
s
e
g
m
e
nt
a
t
i
on
s
t
a
ge
.
T
h
e
dur
a
t
i
on
of
l
e
a
f
s
e
gm
e
n
t
a
t
i
on
i
s
due
t
o
t
h
e
m
a
nu
a
l
l
y
d
e
t
e
rm
i
ne
d
t
h
re
s
ho
l
d
va
l
u
e
,
m
e
a
n
i
ng
t
h
a
t
e
a
c
h
l
e
a
f
t
hre
s
ho
l
d
v
a
l
u
e
i
s
di
ffe
r
e
n
t
.
O
n
t
h
e
o
t
he
r
h
a
nd
,
i
nfor
m
a
t
i
on
r
e
g
a
rdi
ng
l
e
a
f
ve
na
t
i
on
fe
a
t
ur
e
s
c
a
n
b
e
obt
a
i
n
e
d.
In
a
ddi
t
i
on
,
i
f
t
he
foc
us
of
re
s
e
a
r
c
h
i
s
on
i
d
e
nt
i
fyi
ng
a
nd
not
c
a
ri
n
g
a
bout
pl
a
nt
c
ondi
t
i
o
ns
,
a
no
t
he
r
m
e
t
hod
t
h
a
t
c
a
n
b
e
a
ppl
i
e
d
for
p
l
a
nt
i
d
e
n
t
i
fi
c
a
t
i
on
i
s
t
h
e
c
on
vol
u
t
i
o
na
l
n
e
ur
a
l
n
e
t
w
o
rk
(CN
N
)
.
In
t
e
r
m
s
o
f
s
p
e
e
d
i
s
s
upe
r
i
or
,
but
t
he
s
pe
c
i
f
i
c
a
t
i
ons
o
f
t
he
de
vi
c
e
s
us
e
d
a
r
e
a
l
s
o
hi
ghe
r
.
A
C
K
N
O
WL
ED
G
E
M
EN
TS
T
he
a
u
t
ho
rs
t
h
a
nk
t
h
e
D
i
r
e
c
t
or
a
t
e
of
R
e
s
e
a
rc
h
a
n
d
Co
m
m
uni
t
y
S
e
rv
i
c
e
,
t
he
D
i
r
e
c
t
ora
t
e
G
e
n
e
ra
l
of
Re
s
e
a
r
c
h
a
nd
T
e
c
hno
l
ogy
S
t
re
ng
t
h
e
ni
ng
a
n
d
D
e
v
e
l
o
pm
e
nt
of
t
he
M
i
n
i
s
t
ry
of
Re
s
e
a
r
c
h
,
T
e
c
hnol
o
gy
a
nd
H
i
ghe
r
E
d
uc
a
t
i
on
o
f
t
he
Re
p
ubl
i
c
of
Indon
e
s
i
a
t
h
a
t
prov
i
d
i
ng
r
e
s
e
a
rc
h
gr
a
nt
s
t
hro
ugh
t
he
201
8
R
e
s
e
a
rc
h
a
nd
Com
m
un
i
t
y
S
e
r
vi
c
e
P
rogr
a
m
.
R
EF
ER
EN
C
ES
[
1]
R
.
F
.
E
ve
r
t
a
nd
S
.
E
.
E
i
c
hho
r
n
,
“
R
a
ve
n
B
i
o
l
og
y
o
f
P
l
a
nt
s
,
”
8t
h
e
d.
N
e
w
Y
o
r
k
(
U
S
)
:
P
e
t
e
r
M
a
r
s
h
a
l
l
,
2013
.
[
2]
G
.
T
j
i
t
r
os
o
e
po
m
o
,
“
M
or
f
o
l
og
i
T
u
m
buh
a
n
,”
Y
ogy
a
ka
r
t
a
(
I
D
)
:
G
a
dj
a
h
M
a
d
a
U
n
i
v
e
r
s
i
t
y
P
r
e
s
s
,
201
6.
[
3]
B
.
D
oua
i
hy
e
t
a
l
.
,
“
M
o
r
ph
ol
ogi
c
a
l
ve
r
s
u
s
m
ol
e
c
u
l
a
r
m
a
r
ke
r
s
t
o
de
s
c
r
i
be
v
a
r
i
a
b
i
l
i
t
y
i
n
J
un
i
p
e
r
u
s
e
x
c
e
l
s
a
s
ub
s
p
.
e
xc
e
l
s
a
(
C
up
r
e
s
s
a
c
e
a
e
)
,
”
A
oB
P
L
A
N
T
S
,
20
12
.
[
4]
T
.
L
.
L
e
,
D
.
T
.
T
r
a
n
,
a
nd
V
.
N
.
H
oa
n
g,
“
F
ul
l
y
a
u
t
o
m
a
t
i
c
l
e
a
f
-
b
a
s
e
d
p
l
a
n
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n,
a
pp
l
i
c
a
t
i
on
f
o
r
V
i
e
t
na
m
e
s
e
m
e
d
i
c
i
n
a
l
p
l
a
n
t
s
e
a
r
c
h
,
”
i
n
T
he
F
i
f
t
h
Sy
m
po
s
i
um
o
n
I
nf
or
m
a
t
i
on
and
C
om
m
uni
c
at
i
on
T
e
c
hn
ol
o
gy
-
So
I
C
T
’
14
,
H
a
no
i
,
V
i
e
t
N
a
m
,
pp
.
1
46
–
1
54
,
2
014
.
[
5]
S
.
S
.
C
ha
k
ka
r
a
va
r
t
hy
,
G
.
S
a
j
e
e
v
a
n
,
E
.
K
a
m
a
l
a
na
ba
n
a
nd
K
.
V
.
K
u
m
a
r
,
"
A
u
t
o
m
a
t
i
c
l
e
a
f
ve
i
n
f
e
a
t
ur
e
e
x
t
r
a
c
t
i
on
f
or
f
i
r
s
t
de
gr
e
e
ve
i
n
s
,
"
I
n
A
d
v
anc
e
s
i
n
Si
g
na
l
P
r
oc
e
s
s
i
n
g
a
nd
I
n
t
e
l
l
i
g
e
nt
R
e
c
ogni
t
i
on
Sy
s
t
e
m
s
,
p
p.
58
1
-
5
92
,
2
016
.
[
6]
J
.
Y
a
ng
e
t
al
.
,
“
L
e
a
f
f
o
r
m
-
c
l
i
m
a
t
e
r
e
l
a
t
i
ons
hi
ps
on
t
he
gl
oba
l
s
t
a
ge
:
a
n
e
ns
e
m
bl
e
of
c
h
a
r
a
c
t
e
r
s
:
G
l
oba
l
l
e
a
f
f
or
m
a
n
d
c
l
i
m
a
t
e
r
e
l
a
t
i
ons
h
i
p
s
,
”
G
l
ob
al
E
c
o
l
o
gy
and
B
i
oge
ogr
aph
y
,
vo
l
.
2
4,
no.
10
,
pp
.
1113
–
112
5,
O
c
t
.
20
15
.
[
7]
S
.
S
i
n
gh
a
n
d
M
.
S
.
B
ha
m
r
a
h
,
“
L
e
a
f
I
de
nt
i
f
i
c
a
t
i
on
U
s
i
ng
F
e
a
t
ur
e
E
xt
r
a
c
t
i
o
n
a
nd
N
e
ur
a
l
N
e
t
w
or
k,
”
I
O
SR
J
o
ur
n
al
o
f
E
l
e
c
t
r
oni
c
s
an
d
C
om
m
uni
c
a
t
i
o
n
E
ng
i
ne
e
r
i
ng
(
I
O
SR
-
J
E
C
E
)
,
vo
l
.
1
0
,
no.
5
,
pp
.
134
–
140
,
2015
.
[
8]
A
.
B
a
kh
s
h
i
pou
r
a
n
d
A
.
J
a
f
a
r
i
,
“
E
va
l
u
a
t
i
on
o
f
s
uppo
r
t
ve
c
t
o
r
m
a
c
h
i
n
e
a
nd
a
r
t
i
f
i
c
i
a
l
n
e
ur
a
l
ne
t
w
or
k
s
i
n
w
e
e
d
de
t
e
c
t
i
on
us
i
n
g
s
ha
pe
f
e
a
t
ur
e
s
,
”
C
om
pu
t
e
r
s
and
E
l
e
c
t
r
on
i
c
s
i
n
A
gr
i
c
u
l
t
ur
e
,
v
ol
.
1
45,
p
p.
15
3
–
16
0,
F
e
br
u
a
r
y
2
018
.
[
9]
A
.
A
.
P
a
t
i
l
a
nd
K
.
S
.
B
ha
ga
t
,
"
P
l
a
n
t
i
de
n
t
i
f
i
c
a
t
i
on
b
y
l
e
a
f
s
ha
pe
r
e
c
ogn
i
t
i
o
n:
a
r
e
vi
e
w
,
"
I
nt
e
r
n
at
i
on
al
J
ou
r
na
l
o
f
E
ngi
n
e
e
r
i
n
g
T
r
e
n
ds
and
T
e
c
hn
ol
og
y
,
vo
l
.
35
,
no
.
8,
20
16.
[
10]
J
.
S
.
C
ope
,
P
.
R
e
m
a
g
ni
n
o,
S
.
B
a
r
m
a
n
,
a
nd
P
.
W
i
l
k
i
n
,
“
P
l
a
n
t
t
e
x
t
u
r
e
c
l
a
s
s
i
f
i
c
a
t
i
on
us
i
ng
ga
b
or
c
o
-
oc
c
ur
r
e
n
c
e
s
,
”
i
n
A
dv
an
c
e
s
i
n
V
i
s
ua
l
C
om
put
i
n
g:
6
t
h
I
n
t
e
r
na
t
i
o
na
l
S
y
m
po
s
i
um
,
I
S
V
C
201
0
,
B
e
r
l
i
n
(
D
E
)
,
p
p.
66
9
-
6
67
,
2
010
.
[
11]
D
.
T
om
a
r
a
nd
S
.
A
g
a
r
w
a
l
,
“
L
e
a
f
R
e
c
ogn
i
t
i
on
f
or
P
l
a
n
t
C
l
a
s
s
i
f
i
c
a
t
i
o
n
U
s
i
ng
D
i
r
e
c
t
A
c
yc
l
i
c
G
r
a
ph
B
a
s
e
d
M
u
l
t
i
-
C
l
a
s
s
L
e
a
s
t
S
qua
r
e
s
T
w
i
n
S
up
po
r
t
V
e
c
t
o
r
M
a
c
h
i
ne
,
”
I
nt
e
r
na
t
i
ona
l
J
ou
r
n
al
of
I
m
age
an
d
G
r
aph
i
c
s
,
vo
l
.
16,
n
o.
3
,
2016
.
[
12]
F
.
R
.
F
.
P
a
d
a
o
a
nd
E
.
A
.
M
a
r
a
vi
l
l
a
s
,
“
U
s
i
ng
N
a
ï
ve
B
a
ye
s
i
a
n
m
e
t
h
o
d
f
o
r
pl
a
nt
l
e
a
f
c
l
a
s
s
i
f
i
c
a
t
i
on
ba
s
e
d
on
s
h
a
pe
a
n
d
t
e
x
t
u
r
e
f
e
a
t
u
r
e
s
,
”
2015
I
n
t
e
r
na
t
i
ona
l
C
on
f
e
r
e
n
c
e
o
n
H
um
an
o
i
d,
N
ano
t
e
c
hno
l
og
y
,
I
n
f
o
r
m
at
i
on
T
e
c
hno
l
og
y
C
om
m
uni
c
at
i
on
a
nd
C
on
t
r
o
l
,
E
n
v
i
r
onm
e
nt
a
nd
M
a
nag
e
m
e
n
t
(
H
N
I
C
E
M
)
,
pp
.
1
-
5,
201
5.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
1693
-
6930
T
E
L
K
O
M
N
IK
A
T
e
l
e
c
om
m
un
Co
m
put
E
l
Con
t
rol
,
V
ol
.
18
,
N
o.
2
,
A
pri
l
2
020:
726
-
7
32
732
[
13]
A
.
A
m
b
a
r
w
a
r
i
,
Y
.
H
e
r
d
i
y
e
ni
a
nd
T
.
D
j
a
t
n
a
,
"
C
o
m
b
i
na
t
i
on
of
r
e
l
i
e
f
f
e
a
t
ur
e
s
e
l
e
c
t
i
on
a
nd
f
uz
z
y
K
-
ne
a
r
e
s
t
ne
i
ghb
or
f
or
p
l
a
n
t
s
p
e
c
i
e
s
i
de
nt
i
f
i
c
a
t
i
on
,
"
2016
I
nt
e
r
n
at
i
on
al
C
on
f
e
r
e
n
c
e
o
n
A
d
v
an
c
e
d
C
om
p
ut
e
r
Sc
i
e
n
c
e
an
d
I
n
f
or
m
a
t
i
on
Sy
s
t
e
m
s
(
I
C
A
C
S
I
S)
,
pp
.
315
-
32
0,
20
16
.
[
14]
B
.
V
i
j
a
ya
L
a
ks
h
m
i
a
nd
V
.
M
oha
n,
“
K
e
r
ne
l
-
ba
s
e
d
P
S
O
a
nd
F
R
V
M
:
A
n
a
ut
o
m
a
t
i
c
pl
a
nt
l
e
a
f
t
ype
de
t
e
c
t
i
on
us
i
ng
t
e
x
t
u
r
e
,
s
ha
p
e
,
a
nd
c
o
l
or
f
e
a
t
u
r
e
s
,
”
C
om
p
ut
e
r
s
a
nd
E
l
e
c
t
r
on
i
c
s
i
n
A
gr
i
c
ul
t
u
r
e
,
vol
.
125
,
pp
.
99
–
1
12
,
J
ul
y
2016
.
[
15]
R
.
M
a
nd
Y
.
H
e
r
d
i
y
e
n
i
,
“
S
ha
p
e
a
nd
v
e
i
n
e
xt
r
a
c
t
i
on
o
n
pl
a
nt
l
e
a
f
i
m
a
ge
s
us
i
ng
f
our
i
e
r
a
n
d
B
-
S
p
l
i
ne
m
ode
l
i
ng
,
”
A
F
I
T
A
I
n
t
e
r
na
t
i
o
nal
C
on
f
e
r
e
n
c
e
,
t
he
Q
ua
l
i
t
y
I
n
f
o
r
m
at
i
on
f
or
C
om
pe
t
i
t
i
v
e
A
gr
i
c
u
l
t
ur
a
l
B
as
e
d
P
r
odu
c
t
i
o
n
S
y
s
t
e
m
a
nd
C
om
m
e
r
c
e
,
pp
.
306
–
310
,
201
0.
[
16]
A
.
A
m
b
a
r
w
a
r
i
,
Y
.
H
e
r
d
i
y
e
ni
,
a
nd
I
.
H
e
r
m
a
di
,
“
B
i
o
m
e
t
r
i
c
A
n
a
l
y
s
i
s
o
f
L
e
a
f
V
e
na
t
i
on
D
e
n
s
i
t
y
B
a
s
e
d
o
n
D
i
g
i
t
a
l
I
m
a
ge
,
”
T
E
L
K
O
M
N
I
K
A
(
T
e
l
e
c
om
m
uni
c
a
t
i
o
n
C
om
pu
t
i
ng
E
l
e
c
t
r
oni
c
s
an
d
C
on
t
r
o
l
)
,
vo
l
.
16
,
no
.
4
,
pp
.
17
35
–
1
744
,
A
ugus
t
2018
.
[
17]
G
.
L
.
G
r
i
nbl
a
t
,
L
.
C
.
U
z
a
l
,
M
.
G
.
L
a
r
e
s
e
a
nd
P
.
M
.
G
r
a
n
i
t
t
o
,
"
D
e
e
p
l
e
a
r
ni
ng
f
or
p
l
a
nt
i
de
nt
i
f
i
c
a
t
i
on
u
s
i
ng
v
e
i
n
m
o
r
pho
l
og
i
c
a
l
p
a
t
t
e
r
ns
,
"
C
om
put
e
r
s
and
E
l
e
c
t
r
o
ni
c
s
i
n
A
g
r
i
c
u
l
t
u
r
e
,
vo
l
.
12
7,
pp
.
4
18
-
424
,
S
e
p
t
e
m
b
e
r
201
6.
[
18]
J
.
W
.
T
a
n,
S
.
C
ha
ng,
S
.
B
i
nt
i
A
bdu
l
K
a
r
e
e
m
,
H
.
J
.
Y
a
p
a
nd
K
.
Y
o
ng,
"
D
e
e
p
L
e
a
r
ni
ng
f
o
r
P
l
a
n
t
S
pe
c
i
e
s
C
l
a
s
s
i
f
i
c
a
t
i
o
n
us
i
n
g
L
e
a
f
V
e
i
n
M
o
r
pho
m
e
t
r
i
c
,
"
i
n
I
E
E
E
/
A
C
M
T
r
ans
a
c
t
i
o
ns
on
C
o
m
put
a
t
i
ona
l
B
i
o
l
og
y
and
B
i
oi
nf
o
r
m
a
t
i
c
s
,
2
018
.
[
19]
H
.
F
.
E
i
d
a
nd
A
.
A
b
r
a
h
a
m
,
"
P
l
a
n
t
s
p
e
c
i
e
s
i
de
nt
i
f
i
c
a
t
i
on
u
s
i
ng
l
e
a
f
bi
om
e
t
r
i
c
s
a
n
d
s
w
a
r
m
opt
i
m
i
z
a
t
i
on:
A
h
ybr
i
d
P
S
O
,
G
W
O
,
S
V
M
m
od
e
l
,
"
I
n
t
e
r
na
t
i
o
nal
J
ou
r
nal
o
f
H
y
br
i
d
I
nt
e
l
l
i
ge
n
t
Sy
s
t
e
m
s
,
14
(
3
)
,
pp
.
1
55
-
165
,
2017
.
[
20]
A
.
W
a
hyu
m
i
ya
nt
o,
I
.
K
.
E
.
P
u
r
n
a
m
a
,
a
nd
C
hr
i
s
t
yow
i
d
i
a
s
m
or
o
,
“
I
d
e
nt
i
f
i
ka
s
i
t
u
m
bu
ha
n
be
r
da
s
a
r
ka
n
m
i
nu
t
i
a
e
t
u
l
a
n
g
da
un
m
e
ng
gun
a
ka
n
S
O
M
koho
ne
n
,
”
I
ns
t
i
t
u
t
T
e
kno
l
o
gi
S
e
pul
uh
N
o
pe
m
be
r
,
S
u
r
a
b
a
ya
(
I
D
)
,
20
1
1.
[
21]
Z
.
W
a
n
g,
H
.
L
i
,
Y
.
Z
hu
a
n
d
T
.
X
u
,
"
R
e
vi
e
w
of
pl
a
n
t
i
de
n
t
i
f
i
c
a
t
i
on
ba
s
e
d
on
i
m
a
ge
pr
oc
e
s
s
i
ng
,
"
A
r
c
h
i
v
e
s
of
C
om
put
at
i
ona
l
M
e
t
hod
s
i
n
E
ng
i
ne
e
r
i
ng
,
vo
l
.
24
,
pp
.
63
7
-
6
54,
J
ul
y
2
017.
[
22]
G
.
D
h
i
ng
r
a
,
V
.
K
u
m
a
r
a
nd
H
.
D
.
J
os
hi
,
"
S
t
udy
o
f
di
g
i
t
a
l
i
m
a
g
e
p
r
o
c
e
s
s
i
n
g
t
e
c
h
n
i
que
s
f
o
r
l
e
a
f
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
a
nd
c
l
a
s
s
i
f
i
c
a
t
i
on
,
"
M
u
l
t
i
m
e
d
i
a
T
o
ol
s
a
nd
A
pp
l
i
c
a
t
i
o
ns
,
vol
.
77
,
pp
.
199
51
-
2
0000
,
201
8.
[
23]
M
.
G
.
L
a
r
e
s
e
a
nd
P
.
M
.
G
r
a
n
i
t
t
o
,
"
F
i
n
di
ng
l
o
c
a
l
l
e
a
f
ve
i
n
pa
t
t
e
r
ns
f
or
l
e
gu
m
e
c
ha
r
a
c
t
e
r
i
z
a
t
i
on
a
nd
c
l
a
s
s
i
f
i
c
a
t
i
on
,
"
M
ac
hi
n
e
V
i
s
i
o
n
and
A
p
p
l
i
c
a
t
i
o
n
,
vo
l
.
27,
p
p.
7
09
-
720
,
2016
.
[
24]
A
.
S
a
l
i
m
a
,
Y
.
H
e
r
di
y
e
n
i
,
a
nd
S
.
D
ou
a
dy
,
“
L
e
a
f
v
e
i
n
s
e
g
m
e
n
t
a
t
i
o
n
of
m
e
d
i
c
i
na
l
p
l
a
nt
us
i
ng
he
s
s
i
a
n
m
a
t
r
i
x,
”
i
n
I
nt
e
r
n
at
i
on
al
C
on
f
e
r
e
n
c
e
on
A
d
v
anc
e
d
C
om
pu
t
e
r
Sc
i
e
n
c
e
and
I
nf
or
m
a
t
i
on
Sy
s
t
e
m
s
(
I
C
A
C
SI
S)
,
D
e
pok
(
I
D
)
,
pp.
27
5
–
27
9.
20
15
.
[
25]
A
.
D
.
P
r
a
s
t
y
a
,
“
E
ks
t
r
a
k
s
i
f
i
t
u
r
ve
n
a
s
i
da
un
t
u
m
buh
a
n
ob
a
t
be
r
b
a
s
i
s
g
e
o
m
e
t
r
i
,
”
I
ns
t
i
t
u
t
P
e
r
t
a
ni
a
n
B
og
or
,
B
ogor
(
I
D
)
,
201
6.
[
26]
A
.
A
m
b
a
r
w
a
r
i
,
Y
.
H
e
r
d
i
ye
ni
,
a
nd
I
.
H
e
r
m
a
d
i
,
“
I
de
n
t
i
f
i
c
a
t
i
o
n
of
V
e
na
t
i
o
n
T
ype
B
a
s
e
d
o
n
V
e
na
t
i
on
D
e
n
s
i
t
y
us
i
ng
D
i
gi
t
a
l
I
m
a
g
e
P
r
o
c
e
s
s
i
ng
,
”
J
u
r
na
l
T
e
k
n
oi
nf
o
,
vo
l
.
12
,
no
.
2,
pp
.
87
–
92,
20
18.
[
27]
J
.
B
ü
hl
e
r
e
t
a
l
.
,
“
P
he
n
ove
i
n
-
A
t
ool
f
o
r
l
e
a
f
ve
i
n
s
e
g
m
e
n
t
a
t
i
on
a
nd
a
na
l
y
s
i
s
,
”
P
l
ant
P
hy
s
i
o
l
og
y
,
vo
l
.
1
69
,
pp.
23
59
–
2
370
,
2015
.
[
28]
C
.
B
ur
g
e
s
,
“
A
t
u
t
or
i
a
l
on
s
u
ppo
r
t
ve
c
t
or
m
a
c
hi
n
e
s
f
or
pa
t
t
e
r
n
r
e
c
og
ni
t
i
o
n,
”
D
a
t
a
M
i
n
i
ng
a
nd
K
now
l
e
dg
e
D
i
s
c
ov
e
r
y
,
vol
.
2,
pp
.
121
–
167
,
J
u
ne
199
8.
[
29]
Z
.
W
a
ng
,
X
.
S
un
,
Y
.
Z
h
a
ng
,
a
n
d
Z
.
Y
i
n
g,
“
L
e
a
f
r
e
c
o
gn
i
t
i
on
ba
s
e
d
o
n
P
C
N
N
,
”
N
e
u
r
a
l
C
om
pu
t
&
A
ppl
i
c
,
v
ol
.
27
,
no.
4
,
pp.
8
99
–
9
08,
2
016
.
[
30]
R
.
G
on
z
a
l
e
z
,
R
.
W
ood
s
,
a
n
d
S
.
E
dd
i
n
s
,
“
D
i
gi
t
a
l
I
m
a
ge
P
r
oc
e
s
s
i
n
g
U
s
i
ng
M
A
T
L
A
B
,”
N
e
w
J
e
r
s
e
y
(
U
S
)
:
P
e
a
r
s
on
P
r
e
n
t
i
c
e
H
a
l
l
,
2004
.
Evaluation Warning : The document was created with Spire.PDF for Python.