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.
39
,
No
.
1
,
J
u
l
y
2
0
2
5
,
p
p
.
336
~
3
4
4
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
39
.i
1
.
p
p
3
3
6
-
3
4
4
336
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
An impro
v
ed e
ff
i
cientne
t
-
B5
f
o
r
cu
curbit
lea
f
id
enti
f
ica
tion
Q
ua
ng
H
un
g
H
a
1
,
T
ro
ng
-
M
inh
H
o
a
ng
2
,
M
inh
T
r
ien P
ha
m
1
1
F
a
c
u
l
t
y
o
f
A
g
r
i
c
u
l
t
u
r
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
V
N
U
U
n
i
v
e
r
si
t
y
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
H
a
n
o
i
,
V
i
e
t
n
a
m
2
F
a
c
u
l
t
y
of
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
s
N
o
1
,
P
o
s
t
s
a
n
d
Te
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
s I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
H
a
n
o
i
,
V
i
e
t
n
a
m
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
27
,
2
0
2
4
R
ev
is
ed
Mar
6
,
2
0
2
5
Acc
ep
ted
Mar
25
,
2
0
2
5
P
lan
t
d
ise
a
se
s
sig
n
if
ica
n
tl
y
imp
a
c
t
th
e
q
u
a
li
t
y
a
n
d
p
r
o
d
u
c
ti
v
it
y
o
f
c
ro
p
s
,
lea
d
in
g
t
o
s
u
b
sta
n
t
ial
e
c
o
n
o
m
ic
l
o
ss
e
s.
Th
is
p
a
p
e
r
i
n
tro
d
u
c
e
s
two
e
n
h
a
n
c
e
d
Eff
icie
n
tNe
t
-
B5
a
rc
h
i
tec
tu
re
s,
Eff
icie
n
tNe
tB5
-
sig
c
a
a
n
d
E
ffici
e
n
tNe
tB5
-
sig
b
i,
sp
e
c
ifi
c
a
ll
y
d
e
sig
n
e
d
to
d
e
t
e
c
t
a
n
d
c
las
sify
d
ise
a
se
s
in
c
u
c
u
r
b
it
lea
v
e
s.
We
e
m
p
lo
y
Eff
icie
n
tNe
t
-
B5
fo
r
f
e
a
tu
re
e
x
trac
ti
o
n
,
u
sin
g
a
4
5
6
×
4
5
6
×
3
i
n
p
u
t
a
n
d
o
m
it
ti
n
g
t
h
e
to
p
lay
e
r
t
o
g
e
n
e
ra
te
fe
a
tu
re
m
a
p
s
with
S
wish
a
c
ti
v
a
ti
o
n
.
A
g
lo
b
a
l
a
v
e
ra
g
e
p
o
o
li
n
g
2
D
la
y
e
r
re
p
lac
e
s
th
e
c
o
n
v
e
n
ti
o
n
a
l
f
u
ll
y
c
o
n
n
e
c
ted
lay
e
r,
p
r
o
d
u
c
in
g
a
flatten
e
d
v
e
c
t
o
r.
Th
is
is
f
o
ll
o
we
d
b
y
a
d
e
n
se
l
a
y
e
r
w
it
h
fo
u
r
o
u
tp
u
t
u
n
it
s,
L2
re
g
u
lariz
a
ti
o
n
,
a
n
d
sig
m
o
i
d
a
c
ti
v
a
ti
o
n
,
u
s
in
g
e
it
h
e
r
c
a
teg
o
rica
l
o
r
b
i
n
a
ry
c
r
o
ss
-
e
n
tro
p
y
a
s
th
e
lo
ss
f
u
n
c
ti
o
n
.
We
a
lso
d
e
v
e
lo
p
e
d
a
n
o
v
e
l
ima
g
e
d
a
tas
e
t
targ
e
ti
n
g
c
u
c
u
m
b
e
r
a
n
d
c
a
n
tal
o
u
p
e
lea
v
e
s,
in
c
lu
d
in
g
1
1
,
4
2
5
a
u
g
m
e
n
ted
ima
g
e
s
c
a
teg
o
rize
d
in
t
o
fo
u
r
d
ise
a
se
c
las
se
s:
a
n
th
ra
c
n
o
se
,
p
o
wd
e
r
y
m
il
d
e
w,
d
o
w
n
y
m
il
d
e
w,
a
n
d
fre
sh
lea
f
.
Ou
r
e
x
p
e
rime
n
ts
d
a
tas
e
t
d
e
m
o
n
stra
tes
th
a
t
t
h
e
Eff
icie
n
tNe
tB5
-
sig
b
i
a
c
h
ie
v
e
s
a
n
a
c
c
u
ra
c
y
o
f
9
7
.
0
7
%
,
m
a
rk
in
g
a
sig
n
ifi
c
a
n
t
imp
r
o
v
e
m
e
n
t
i
n
c
las
sify
in
g
sim
il
a
r
d
ise
a
se
s
in
c
u
c
u
rb
it
lea
v
e
s.
K
ey
w
o
r
d
s
:
C
u
cu
r
b
it d
ataset
C
u
cu
r
b
it d
is
ea
s
e
d
etec
tio
n
Dee
p
lear
n
in
g
E
f
f
icien
tNetB
5
L
ea
f
d
is
ea
s
es d
etec
tio
n
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
:
Min
h
T
r
ien
Ph
am
Facu
lty
o
f
Ag
r
ic
u
ltu
r
e
an
d
T
e
ch
n
o
lo
g
y
,
VNU
Un
iv
er
s
ity
o
f
E
n
g
in
ee
r
in
g
an
d
T
ec
h
n
o
lo
g
y
E
3
B
u
ild
in
g
,
1
4
4
Xu
a
n
T
h
u
y
Stre
et,
C
au
Giay
Dis
tr
ict,
Ha
n
o
i,
Vietn
am
E
m
ail: tr
ien
p
m
@
v
n
u
.
e
d
u
.
v
n
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
C
u
cu
r
b
itace
ae
f
am
ily
,
al
s
o
k
n
o
wn
as
th
e
g
o
u
r
d
o
r
c
u
cu
r
b
its
f
am
ily
,
en
co
m
p
ass
es
a
d
iv
er
s
e
r
an
g
e
o
f
ag
r
icu
ltu
r
ally
s
ig
n
if
ic
an
t
cr
o
p
s
,
in
clu
d
in
g
cu
cu
m
b
er
s
an
d
ca
n
talo
u
p
es,
wh
ich
ar
e
p
iv
o
tal
to
lo
ca
l
an
d
g
lo
b
al
f
o
o
d
ec
o
n
o
m
ies.
T
h
ese
cr
o
p
s
ar
e
r
ich
s
o
u
r
ce
s
o
f
n
u
tr
ien
ts
s
u
ch
as
ca
r
o
ten
o
id
s
,
ter
p
en
o
id
s
,
s
ap
o
n
in
s
,
an
d
p
h
y
to
ch
e
m
icals
[
1
]
.
As
we
d
elv
e
d
ee
p
e
r
in
to
t
h
e
ch
a
llen
g
es
co
n
f
r
o
n
tin
g
th
e
C
u
cu
r
b
itace
ae
f
am
ily
,
it
b
ec
o
m
es
cr
u
cial
to
s
p
o
tlig
h
t
t
h
e
d
is
ea
s
es
th
at
p
o
s
e
s
ig
n
if
ican
t
th
r
ea
ts
to
th
ese
ag
r
icu
ltu
r
ally
v
alu
ab
le
cr
o
p
s
.
Am
o
n
g
th
ese,
an
th
r
ac
n
o
s
e,
d
o
wn
y
m
ild
ew,
an
d
p
o
wd
e
r
y
m
ild
ew
ar
e
p
ar
ticu
lar
ly
d
etr
im
en
t
al,
ep
ito
m
izin
g
th
e
ar
r
ay
o
f
p
at
h
o
g
e
n
s
-
v
ir
u
s
es,
f
u
n
g
i,
an
d
b
ac
ter
ia
-
th
at
en
d
an
g
er
th
e
h
ea
lth
a
n
d
p
r
o
d
u
cti
v
ity
o
f
cu
cu
m
b
er
s
,
ca
n
talo
u
p
es,
an
d
th
eir
k
in
[
2
]
.
T
h
ese
d
is
ea
s
es
co
m
p
r
o
m
is
e
th
ese
cr
o
p
’
s
q
u
ality
a
n
d
y
i
eld
,
wh
ich
p
o
s
e
a
s
u
b
s
tan
tial
r
is
k
to
th
e
b
r
o
ad
er
ag
r
icu
ltu
r
al
ec
o
s
y
s
tem
.
Dea
lin
g
with
th
ese
th
r
ea
ts
ef
f
ec
tiv
ely
is
ess
en
tial
f
o
r
m
ain
tain
in
g
th
e
v
iab
ilit
y
an
d
s
u
s
tain
ab
ilit
y
o
f
cu
cu
m
b
er
s
,
c
an
talo
u
p
es,
an
d
th
e
en
tire
C
u
cu
r
b
itace
ae
f
am
ily
,
en
s
u
r
in
g
th
e
y
co
n
tin
u
e
to
p
lay
th
eir
cr
itical
r
o
le
in
g
lo
b
al
f
o
o
d
ec
o
n
o
m
ies an
d
n
u
tr
itio
n
al
s
e
cu
r
ity
.
T
h
e
wid
esp
r
ea
d
n
at
u
r
e
o
f
an
t
h
r
ac
n
o
s
e
[
3
]
,
d
o
wn
y
m
ild
ew
[
4
]
,
an
d
p
o
wd
er
y
m
ild
ew
[
5
]
with
in
th
e
C
u
cu
r
b
itace
ae
f
am
ily
u
n
d
er
l
i
n
es
th
e
n
ec
ess
ity
f
o
r
ea
r
ly
d
e
tectio
n
an
d
ac
cu
r
ate
d
ia
g
n
o
s
i
s
.
B
ased
o
n
m
an
u
al
in
s
p
ec
tio
n
an
d
e
x
p
er
t
an
aly
s
i
s
,
tr
ad
itio
n
al
d
is
ea
s
e
d
etec
tio
n
m
eth
o
d
s
ar
e
f
r
au
g
h
t
with
c
h
allen
g
es,
in
clu
d
in
g
tim
e
co
n
s
u
m
p
tio
n
,
la
b
o
r
in
ten
s
ity
,
an
d
t
h
e
p
o
ten
tial
f
o
r
s
u
b
jectiv
e
er
r
o
r
s
wh
ich
u
n
d
e
r
s
co
r
e
th
e
u
r
g
e
n
t
n
ee
d
f
o
r
in
n
o
v
ativ
e
s
o
lu
tio
n
s
in
th
e
ag
r
icu
ltu
r
al
s
ec
to
r
,
h
ig
h
lig
h
tin
g
th
e
p
o
ten
tial
o
f
m
ac
h
in
e
lear
n
in
g
an
d
o
th
er
ad
v
an
ce
d
tec
h
n
o
lo
g
ies
to
r
ev
o
lu
tio
n
ize
d
is
ea
s
e
d
etec
tio
n
a
n
d
m
an
a
g
em
en
t
in
th
ese
v
ital
cr
o
p
s
.
T
h
e
f
ield
o
f
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
A
n
imp
r
o
ve
d
efficien
tn
et
-
B
5
fo
r
cu
cu
r
b
it lea
f id
en
tifi
ca
tio
n
(
Qu
a
n
g
Hu
n
g
Ha
)
337
m
ac
h
in
e
lear
n
i
n
g
,
a
d
v
an
ce
m
en
ts
in
co
m
p
u
ter
v
is
io
n
[
6
]
,
an
d
a
r
tific
ial
in
tellig
en
ce
h
av
e
s
ig
n
if
ican
tly
p
r
o
p
elled
th
e
d
ev
elo
p
m
en
t
o
f
ca
p
ab
ilit
ies
in
d
iag
n
o
s
in
g
p
lan
t
d
is
ea
s
es
an
d
c
r
ea
tin
g
a
u
to
m
ated
s
o
lu
tio
n
s
.
T
h
ey
h
av
e
b
ec
o
m
e
a
p
o
p
u
l
ar
m
eth
o
d
f
o
r
p
lan
t
d
is
e
ase
r
ec
o
g
n
itio
n
,
ac
co
m
m
o
d
atin
g
th
e
c
h
allen
g
e
o
f
id
en
tify
in
g
m
u
ltip
le
d
is
ea
s
es
o
n
a
s
in
g
le
leaf
b
y
co
n
s
id
er
i
n
g
a
r
an
g
e
o
f
f
ea
tu
r
es,
in
clu
d
in
g
co
l
o
r
,
tex
tu
r
e,
an
d
s
h
ap
e
[
6
]
.
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
s
tan
d
o
u
t
as
a
f
o
u
n
d
atio
n
al
n
etwo
r
k
s
tr
u
ctu
r
e
in
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
,
en
ab
lin
g
th
e
au
to
m
atic
lear
n
in
g
o
f
k
e
y
f
ea
tu
r
es
d
ir
ec
tly
f
r
o
m
d
ata
an
d
elim
in
atin
g
th
e
n
ee
d
f
o
r
m
an
u
al
f
ea
tu
r
e
ex
t
r
a
ctio
n
[
7
]
.
C
NNs
h
av
e
b
ee
n
e
f
f
ec
tiv
ely
u
s
ed
in
co
m
p
lex
ta
s
k
s
s
u
ch
as
im
ag
e
class
if
icatio
n
,
s
em
an
tic
s
eg
m
en
tat
io
n
,
an
d
p
atter
n
r
ec
o
g
n
iti
o
n
.
T
h
e
ev
o
lu
tio
n
o
f
d
ee
p
lear
n
in
g
class
if
icatio
n
m
eth
o
d
s
h
as
s
ee
n
th
e
d
ev
el
o
p
m
en
t
o
f
C
NN
-
b
ased
ar
ch
itectu
r
es
lik
e
Alex
Net
[
8
]
,
VGGN
et
[
9
]
,
an
d
Mo
b
ileNet
[
1
0
]
.
T
h
ese
ar
ch
it
ec
tu
r
es
h
av
e
ac
h
iev
ed
h
ei
g
h
t
en
ed
ac
cu
r
ac
y
t
h
r
o
u
g
h
n
etwo
r
k
d
ep
th
an
d
wid
th
in
n
o
v
atio
n
s
an
d
o
p
tim
izin
g
m
o
d
el
p
a
r
am
eter
s
.
Ho
war
d
e
t
a
l.
[
1
0
]
in
tr
o
d
u
ce
d
Mo
b
ile
Net,
a
n
ew
s
er
ies
o
f
ef
f
icien
t
m
o
d
els
d
is
tin
g
u
is
h
ed
b
y
th
eir
u
s
e
o
f
d
e
p
th
-
wis
e
s
ep
ar
ab
l
e
co
n
v
o
lu
tio
n
s
.
T
h
is
tech
n
iq
u
e
e
f
f
ec
tiv
el
y
d
iv
id
es
s
tan
d
ar
d
co
n
v
o
lu
tio
n
s
in
to
d
e
p
th
-
wis
e
an
d
p
o
in
twis
e
co
n
v
o
s
,
en
h
an
cin
g
m
o
d
el
ef
f
icien
cy
.
E
f
f
icien
tNet,
in
tr
o
d
u
ce
d
b
y
T
an
an
d
L
e
[
1
1
]
,
e
n
h
an
ce
s
m
o
d
el
’
s
p
r
ec
is
io
n
an
d
o
p
er
at
io
n
al
ef
f
icien
c
y
b
y
m
in
im
izin
g
t
h
eir
s
ize
an
d
th
e
n
u
m
b
er
o
f
f
lo
atin
g
-
p
o
in
t
o
p
er
atio
n
s
with
o
u
t
co
m
p
r
o
m
is
in
g
m
o
d
el
q
u
ality
.
T
h
is
ar
ch
itectu
r
e
was
d
e
v
elo
p
ed
th
r
o
u
g
h
a
m
eth
o
d
k
n
o
w
n
as
n
eu
r
al
a
r
ch
itectu
r
e
s
ea
r
c
h
[
1
2
]
,
en
a
b
lin
g
t
h
e
s
ca
lin
g
o
f
th
e
b
ase
m
o
d
el
to
p
r
o
d
u
ce
v
ar
io
u
s
E
f
f
icien
tNet
v
a
r
ian
ts
.
Dee
p
lear
n
in
g
h
as
th
u
s
b
ec
o
m
e
a
v
ital
to
o
l
in
p
lan
t d
is
ea
s
e
i
m
ag
e
r
ec
o
g
n
itio
n
,
with
s
tu
d
ie
s
u
s
in
g
th
e
wid
ely
u
s
ed
Plan
tVillag
e
d
at
aset
[
1
3
]
,
[
1
4
]
.
W
ith
d
ata
co
llected
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
,
th
e
f
aster
R
-
C
NN
m
o
d
el
is
r
ec
o
r
d
e
d
with
an
av
e
r
ag
e
p
r
ec
i
s
io
n
s
co
r
e
o
f
8
7
.
0
1
%
f
o
r
r
ec
o
g
n
izin
g
d
is
ea
s
e
o
n
to
m
ato
leav
es
[
1
5
]
,
o
r
d
is
ea
s
e
d
etec
tio
n
[
1
6
]
.
Ma
et
a
l.
[
1
7
]
d
ev
elo
p
ed
a
d
atas
et
co
n
s
is
tin
g
o
f
1
,
1
8
4
im
ag
es
f
o
r
f
o
u
r
c
u
cu
m
b
er
d
is
ea
s
es
an
d
ap
p
lied
a
d
ee
p
C
NN
,
d
em
o
n
s
tr
atin
g
a
s
ig
n
if
ican
t
p
er
f
o
r
m
a
n
ce
im
p
r
o
v
e
m
en
t
co
m
p
ar
ed
to
tr
ad
itio
n
al
class
if
ier
s
lik
e
r
an
d
o
m
f
o
r
est
an
d
s
u
p
p
o
r
t
v
e
cto
r
m
ac
h
in
es
(
SVM
)
,
ac
h
iev
in
g
a
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
o
f
9
3
.
4
%,
s
im
ilar
ly
,
Z
h
an
g
et
a
l.
[
1
8
]
in
tr
o
d
u
ce
d
a
m
eth
o
d
u
tili
zin
g
a
g
lo
b
al
p
o
o
lin
g
d
ilated
C
NN
f
o
r
i
d
en
tify
in
g
s
ix
co
m
m
o
n
cu
cu
m
b
er
d
is
ea
s
es,
r
ea
ch
in
g
a
n
ac
cu
r
ac
y
r
ate
o
f
o
v
er
9
4
%.
Fu
r
th
er
a
d
v
an
ci
n
g
t
h
e
f
ield
,
Z
h
a
n
g
et
a
l.
[
1
9
]
ex
p
l
o
r
ed
th
e
u
s
e
o
f
tr
an
s
f
er
lear
n
in
g
with
E
f
f
icie
n
tNet
f
o
r
class
i
f
y
in
g
f
o
u
r
ty
p
es
o
f
cu
cu
m
b
er
d
is
ea
s
es,
ac
h
iev
in
g
an
im
p
r
ess
iv
e
ac
cu
r
ac
y
o
f
9
7
%,
with
E
f
f
icien
tNet
-
B
4
b
ein
g
id
en
tifie
d
as
th
e
m
o
s
t
ef
f
ec
tiv
e
m
o
d
el
f
o
r
th
eir
s
tu
d
y
.
T
h
e
ab
o
v
e
s
tu
d
ies
s
h
o
w
th
at
d
ee
p
lear
n
in
g
m
o
d
els
i
n
cr
ea
s
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
with
v
a
r
io
u
s
p
r
o
c
ess
in
g
tech
n
iq
u
es.
Ho
wev
er
,
d
esp
ite
th
e
n
u
m
er
o
u
s
s
tu
d
ies
an
d
d
iv
er
s
e
m
eth
o
d
o
l
o
g
ies
d
ev
elo
p
ed
t
o
d
etec
t
p
lan
t
d
is
ea
s
es,
m
o
s
t
o
f
t
h
ese
in
v
esti
g
atio
n
s
f
o
c
u
s
o
n
s
p
ec
if
ic
d
is
ea
s
es
o
r
in
d
iv
id
u
al
cr
o
p
ty
p
es,
o
f
ten
n
ee
d
in
g
m
o
r
e
ac
cu
r
ac
y
a
n
d
ar
e
u
n
av
ailab
le
f
o
r
v
ar
io
u
s
p
lan
ts
.
I
n
s
u
m
m
ar
y
,
th
e
m
ain
co
n
tr
ib
u
tio
n
s
o
f
th
is
s
tu
d
y
ar
e
as f
o
llo
ws:
−
A
n
ew
cu
c
u
r
b
it
leav
es
d
atas
et,
s
p
ec
if
ically
cu
c
u
m
b
er
an
d
ca
n
talo
u
p
e,
h
as
b
ee
n
d
e
v
elo
p
ed
f
o
r
d
is
ea
s
e
class
if
icatio
n
.
T
h
is
d
ata
s
et
v
i
s
u
ally
r
ep
r
esen
ts
th
e
ap
p
ea
r
an
ce
o
f
cu
cu
r
b
it
d
is
ea
s
es
th
r
o
u
g
h
v
is
ib
le
lig
h
t
im
ag
es.
I
t
is
ca
teg
o
r
ized
in
t
o
f
o
u
r
class
es
:
an
t
h
r
ac
n
o
s
e,
p
o
wd
er
y
m
ild
ew,
d
o
wn
y
m
ild
e
w,
an
d
f
r
esh
l
ea
f
.
T
h
e
d
ataset
in
itially
co
n
s
is
ted
o
f
2
,
2
7
5
o
r
ig
i
n
al
p
h
o
to
s
co
ll
ec
ted
f
r
o
m
r
ea
l
f
ield
s
u
n
d
er
n
atu
r
al
wea
th
er
co
n
d
itio
n
s
with
in
co
n
s
is
ten
t
lig
h
tin
g
.
Af
ter
p
r
e
p
r
o
ce
s
s
in
g
a
n
d
au
g
m
e
n
tatio
n
,
th
e
d
ataset
n
o
w
co
m
p
r
is
es
1
1
,
4
2
5
im
ag
es.
T
h
is
d
ataset
is
p
u
b
licly
a
v
ailab
le
to
th
e
r
esear
ch
co
m
m
u
n
ity
.
−
T
h
e
E
f
f
icien
tNet
-
B
5
m
o
d
el
h
as
b
ee
n
en
h
an
ce
d
b
y
r
ep
lac
in
g
tr
ad
itio
n
al
f
u
lly
co
n
n
ec
te
d
lay
er
s
with
a
g
lo
b
al
a
v
er
ag
e
p
o
o
li
n
g
2
D
lay
er
,
wh
ich
av
e
r
ag
es
ac
r
o
s
s
s
p
atial
d
im
en
s
io
n
s
t
o
p
r
o
d
u
ce
a
f
l
atten
ed
v
ec
t
o
r
.
A
d
en
s
e
lay
er
w
ith
f
o
u
r
o
u
tp
u
t
u
n
its
in
co
r
p
o
r
ates
L
2
r
eg
u
l
ar
izatio
n
an
d
a
s
ig
m
o
id
ac
tiv
a
tio
n
f
u
n
ctio
n
to
p
r
ev
en
t
o
v
e
r
f
itti
n
g
.
I
t
em
p
lo
y
s
eith
er
ca
teg
o
r
ical
o
r
b
in
a
r
y
cr
o
s
s
-
en
tr
o
p
y
as
lo
s
s
f
u
n
ctio
n
s
,
en
h
an
cin
g
r
o
b
u
s
tn
ess
an
d
g
en
e
r
aliza
tio
n
ac
r
o
s
s
d
iv
er
s
e
d
atasets
.
T
h
e
b
as
e
m
o
d
el,
with
a
4
5
6
×
4
5
6
×
3
in
p
u
t
s
ize,
u
s
es
a
Swis
h
ac
tiv
atio
n
f
u
n
ctio
n
.
Ou
r
m
o
d
el
o
u
tp
er
f
o
r
m
s
p
r
ev
i
o
u
s
p
r
o
p
o
s
als
o
n
p
u
b
lic
d
atasets
an
d
o
u
r
ac
tu
al
-
wo
r
ld
d
ataset.
Acc
o
r
d
in
g
to
e
x
p
er
im
en
ts
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
h
as
9
8
.
2
%
class
if
icatio
n
ac
cu
r
ac
y
o
n
th
e
tr
ain
in
g
s
et
an
d
9
7
.
5
% o
n
th
e
v
alid
atio
n
s
et.
T
h
e
s
tr
u
ctu
r
e
o
f
th
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws:
s
ec
tio
n
2
p
r
esen
ts
th
e
m
eth
o
d
with
an
ex
p
er
im
en
tal
d
esig
n
to
co
lle
ct
th
e
d
ataset
an
d
m
o
d
if
ied
m
o
d
els.
I
n
s
ec
tio
n
3
d
is
cu
s
s
es
th
e
ex
p
e
r
im
en
tal
m
etr
ics an
d
th
e
r
esu
lts
o
b
tain
e
d
.
L
astl
y
,
th
e
co
n
clu
s
io
n
s
ar
e
s
h
o
wn
in
s
ec
tio
n
4
.
2.
M
E
T
H
O
D
2
.
1
.
I
ma
g
e
da
t
a
s
et
T
h
e
im
ag
e
d
ataset
o
f
cu
cu
r
b
it
leaf
d
is
ea
s
es,
p
ar
ticu
lar
l
y
f
o
r
ca
n
talo
u
p
e,
is
r
ar
ely
av
ailab
le,
h
ig
h
lig
h
tin
g
a
s
ig
n
if
ican
t
g
ap
in
th
e
r
eso
u
r
ce
s
n
ee
d
e
d
f
o
r
ef
f
ec
tiv
e
d
is
ea
s
e
d
etec
tio
n
.
T
o
ad
d
r
ess
th
is
,
we
p
r
o
p
o
s
ed
a
n
o
v
el
cu
cu
r
b
it
d
at
aset
aim
ed
at
p
r
ec
is
e
o
b
ject
d
e
tectio
n
an
d
lo
ca
lizatio
n
o
f
d
is
ea
s
es
o
n
th
e
leav
es.
T
h
e
d
ataset
co
m
p
r
is
es
s
ev
er
al
in
f
ec
ted
leav
es
co
llected
f
r
o
m
f
o
u
r
d
is
tin
ct
lo
ca
tio
n
s
:
cu
cu
m
b
er
s
f
r
o
m
a
g
r
ee
n
h
o
u
s
e
at
th
e
Vietn
am
Natio
n
al
Un
iv
er
s
ity
o
f
Ag
r
ic
u
ltu
r
e,
Gia
L
am
Dis
tr
ict,
Ha
n
o
i
C
ity
,
Vi
etn
am
(
cu
cu
m
b
e
r
s
)
;
f
ield
s
in
Hai
Ph
o
n
g
C
ity
,
Vietn
am
;
Gen
Xa
n
h
Far
m
in
Da
n
Ph
u
o
n
g
Di
s
tr
ict,
Han
o
i
C
ity
,
Vietn
am
;
an
d
ca
n
talo
u
p
es
f
r
o
m
a
g
r
ee
n
h
o
u
s
e
in
L
o
n
g
B
ien
Dis
tr
ict,
Han
o
i
C
ity
,
Vietn
am
.
T
h
e
cu
cu
m
b
e
r
s
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.
39
,
No
.
1
,
J
u
ly
20
25
:
336
-
3
4
4
338
wer
e
cu
ltiv
ated
in
n
u
tr
ien
t
-
r
ich
lo
am
y
s
o
il,
r
e
n
o
wn
e
d
f
o
r
th
eir
ex
ce
llen
t
wate
r
r
ete
n
tio
n
a
n
d
ae
r
atio
n
p
r
o
p
er
ties
.
I
n
c
o
n
tr
ast,
th
e
c
an
talo
u
p
es
wer
e
g
r
o
w
n
in
a
s
an
d
y
lo
am
m
ix
ed
with
co
co
n
u
t
co
ir
,
wh
ic
h
co
m
b
in
es
th
e
d
r
ain
ag
e
an
d
ae
r
atio
n
ad
v
an
tag
es
o
f
s
an
d
y
lo
am
with
th
e
m
o
is
tu
r
e
r
et
en
tio
n
an
d
o
r
g
an
ic
en
r
ich
m
en
t
b
e
n
ef
its
o
f
co
c
o
n
u
t
co
ir
.
Fig
u
r
e
1
p
r
esen
ts
v
is
u
al
r
ep
r
esen
tatio
n
s
o
f
th
e
ex
p
er
im
en
tal
en
v
ir
o
n
m
en
ts
f
r
o
m
wh
ich
d
at
a
wer
e
g
ath
er
ed
.
On
th
e
lef
t,
th
e
f
ield
s
in
Hai
Ph
o
n
g
a
r
e
ill
u
s
tr
ated
,
wh
ile
th
e
r
ig
h
t
s
id
e
f
ea
tu
r
es
th
e
g
r
ee
n
h
o
u
s
e
in
L
o
n
g
B
ien
.
T
h
is
d
a
taset
co
n
tain
s
2
,
2
7
5
o
r
ig
in
al
p
h
o
to
s
as
s
h
o
wn
in
Fig
u
r
e
2
,
ca
teg
o
r
ized
in
to
f
o
u
r
ty
p
es
o
f
d
is
ea
s
es:
a
n
th
r
ac
n
o
s
e
(
Fig
u
r
e
2
(
a
)
)
,
d
o
wn
y
m
ild
ew
(
Fig
u
r
e
2
(
b
)
)
,
p
o
wd
er
y
m
ild
ew
(
Fig
u
r
e
2
(
c
)
)
,
an
d
f
r
esh
leaf
(
Fig
u
r
e
2
(
d
)
)
.
W
e
also
d
iv
id
ed
it
in
to
tr
ain
in
g
an
d
test
s
ets
at
an
8
0
:2
0
r
atio
.
T
h
e
im
ag
es
wer
e
ca
p
tu
r
e
d
u
s
in
g
an
iPh
o
n
e
XS
Ma
x
with
a
r
eso
lu
tio
n
o
f
3
,
0
2
4
×
4
,
0
3
2
p
ix
els,
a
f
o
ca
l
len
g
th
o
f
2
6
m
m
,
an
a
p
e
r
tu
r
e
o
f
f
/
1
.
8
,
a
n
d
a
s
h
u
tter
s
p
ee
d
o
f
1
/5
0
s
.
T
o
en
h
an
ce
th
e
d
ataset,
we
ap
p
lied
d
ata
au
g
m
en
tatio
n
tech
n
iq
u
es
s
u
ch
as
r
o
tatio
n
at
6
0
d
e
g
r
ee
s
,
zo
o
m
in
g
to
0
.
5
tim
es,
a
n
d
ad
ju
s
tin
g
b
r
ig
h
tn
ess
to
1
.
2
tim
es.
Fro
m
2
,
2
7
5
o
r
ig
in
al
im
ag
es,
we
r
ec
ei
v
ed
1
1
,
4
2
5
a
u
g
m
e
n
ted
im
ag
es.
T
h
e
p
r
o
p
o
r
tio
n
s
o
f
an
th
r
ac
n
o
s
e,
d
o
wn
y
m
ild
ew,
p
o
wd
e
r
y
m
ild
ew,
an
d
f
r
esh
leaf
a
r
e
2
6
.
8
%,
2
0
.
3
%,
3
1
.
8
%,
an
d
2
1
.
1
%
,
r
esp
ec
tiv
ely
as sh
o
wn
in
T
a
b
le
1
.
Fig
u
r
e
1
.
R
ea
l c
u
cu
m
b
er
s
in
H
ai
Ph
o
n
g
(
le
f
t)
an
d
ca
n
talo
u
p
e
s
in
th
e
f
ield
in
Han
o
i,
Vietn
a
m
(
r
ig
h
t)
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
Sam
p
le
im
a
g
es f
o
r
e
ac
h
class
in
th
e
d
ataset: (
a)
an
t
h
r
ac
n
o
s
e,
(
b
)
d
o
wn
y
m
ild
ew,
(
c)
p
o
wd
e
r
y
m
ild
ew,
an
d
(
d
)
f
r
esh
leaf
T
ab
le
1
.
Statis
tics
o
f
th
e
cu
cu
r
b
it d
ataset
D
a
t
a
s
e
t
C
l
a
s
ses
O
r
i
g
i
n
a
l
i
ma
g
e
s
A
u
g
m
e
n
t
e
d
i
ma
g
e
s
Tr
a
i
n
i
n
g
A
n
t
h
r
a
c
n
o
se
4
9
0
2
,
9
4
0
D
o
w
n
y
m
i
l
d
e
w
3
7
1
2
,
2
2
6
P
o
w
d
e
r
y
m
i
l
d
e
w
5
8
3
3
,
4
9
8
F
r
e
sh
l
eaf
3
8
6
2
,
3
1
6
Te
st
i
n
g
A
n
t
h
r
a
c
n
o
se
1
2
3
1
2
3
D
o
w
n
y
m
i
l
d
e
w
93
93
P
o
w
d
e
r
y
m
i
l
d
e
w
1
3
3
1
3
3
F
r
e
sh
l
eaf
96
96
O
v
e
r
a
l
l
2
,
2
7
5
1
1
,
4
2
5
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
A
n
imp
r
o
ve
d
efficien
tn
et
-
B
5
fo
r
cu
cu
r
b
it lea
f id
en
tifi
ca
tio
n
(
Qu
a
n
g
Hu
n
g
Ha
)
339
2
.
2
.
M
et
ho
ds
Af
ter
co
m
p
ar
i
n
g
class
if
icatio
n
p
er
f
o
r
m
an
ce
s
u
s
in
g
o
u
r
d
ataset
am
o
n
g
v
ar
io
u
s
E
f
f
icie
n
tNet
an
d
Mo
b
ileNet
m
o
d
els
u
s
in
g
th
e
s
tu
d
y
d
ataset,
E
f
f
icie
n
tNet
-
B
5
h
ad
th
e
b
est
p
er
f
o
r
m
an
ce
a
n
d
was
s
elec
ted
f
o
r
f
u
r
th
er
o
p
tim
izatio
n
as
s
h
o
wn
in
T
ab
le
2
.
I
n
itially
,
we
d
i
s
ca
r
d
ed
th
e
p
r
e
-
tr
ain
e
d
weig
h
ts
to
allo
w
a
m
o
r
e
tailo
r
ed
ad
ap
tatio
n
to
o
u
r
d
a
taset,
f
o
cu
s
in
g
o
n
cu
c
u
r
b
it
d
is
ea
s
es
[
2
0
]
.
W
e
r
ep
lace
d
th
e
tr
ad
itio
n
al
f
u
lly
co
n
n
ec
ted
lay
er
with
a
g
lo
b
al
av
er
ag
e
p
o
o
lin
g
2
D
lay
er
,
s
im
p
lify
in
g
th
e
m
o
d
el
’
s
ar
c
h
itectu
r
e
b
y
av
er
a
g
in
g
th
e
s
p
atial
d
im
e
n
s
io
n
s
o
f
wi
d
th
a
n
d
h
eig
h
t
in
to
a
f
latten
ed
v
ec
t
o
r
w
h
ile
p
r
eser
v
in
g
t
h
e
d
e
p
th
.
T
h
is
s
tep
en
h
an
ce
s
th
e
m
o
d
el
’
s
ca
p
ab
il
ity
to
m
an
ag
e
s
p
atial
h
ier
ar
c
h
ies
ef
f
ec
tiv
ely
.
Fo
llo
win
g
th
e
p
o
o
lin
g
la
y
er
,
we
in
co
r
p
o
r
ated
a
d
en
s
e
lay
er
co
n
f
ig
u
r
e
d
with
f
o
u
r
o
u
tp
u
t
u
n
i
ts
co
r
r
esp
o
n
d
i
n
g
to
o
u
r
class
if
icatio
n
ca
teg
o
r
ies,
en
s
u
r
in
g
alig
n
m
en
t
with
o
u
r
s
p
ec
if
ic
class
if
icatio
n
o
b
jectiv
es.
T
h
is
d
en
s
e
lay
er
em
p
lo
y
s
L
2
r
eg
u
lar
izatio
n
with
a
f
ac
to
r
o
f
0
.
0
1
to
m
itig
ate
o
v
er
f
itti
n
g
,
m
ain
tain
in
g
m
in
im
al
m
o
d
e
l
weig
h
ts
to
f
o
s
ter
b
etter
g
en
er
aliza
tio
n
.
A
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ctio
n
is
also
u
s
ed
to
p
r
o
d
u
ce
p
r
o
b
ab
ilit
y
o
u
tp
u
ts
f
o
r
ea
ch
class
,
wh
ich
is
cr
u
cial
f
o
r
ef
f
ec
tiv
e
m
u
lti
-
lab
el
c
lass
if
icatio
n
.
T
h
e
s
ig
m
o
id
f
u
n
ctio
n
[
2
1
]
is
:
(
)
=
1
1
+
−
(
1
)
T
h
e
b
ase
m
o
d
el,
E
f
f
icien
tNet
-
B
5
,
o
p
er
ates
with
o
u
t
its
to
p
la
y
er
an
d
s
er
v
es
as
a
f
ea
tu
r
e
ex
tr
ac
to
r
,
p
r
o
d
u
cin
g
a
s
et
o
f
f
ea
tu
r
e
m
ap
s
.
T
h
ese
f
ea
tu
r
e
m
ap
s
ar
e
ac
tiv
ated
b
y
a
Swis
h
ac
tiv
atio
n
f
u
n
ctio
n
,
en
h
an
cin
g
th
e
n
o
n
-
lin
ea
r
ity
o
f
th
e
p
r
o
ce
s
s
in
g
an
d
p
o
ten
tially
im
p
r
o
v
in
g
th
e
m
o
d
el
’
s
lear
n
in
g
ca
p
ab
ilit
y
.
T
h
e
Swis
h
ac
tiv
atio
n
f
o
r
m
u
la
[
2
1
]
is
:
ℎ
(
)
=
∗
(
∗
)
(
2
)
wh
er
e
α
is
a
tr
ain
ab
le
p
ar
am
et
er
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
1
0
ten
k
in
d
s
o
f
class
if
icatio
n
n
etwo
r
k
s
N
e
t
w
o
r
k
A
c
c
u
r
a
c
y
(
%
)
N
o
p
r
e
-
t
r
a
i
n
e
d
w
e
i
g
h
t
s
I
mag
e
N
e
t
w
e
i
g
h
t
s
P
l
a
n
t
V
i
l
l
a
g
e
w
e
i
g
h
t
s
Ef
f
i
c
i
e
n
t
N
e
t
-
B4
7
2
.
1
3
%
2
0
.
2
2
%
7
7
.
5
3
%
E
f
f
i
c
i
e
n
t
N
e
t
-
B5
8
2
.
2
5
%
6
1
.
1
2
%
8
2
.
2
5
%
Ef
f
i
c
i
e
n
t
N
e
t
V
2
-
B0
2
4
.
9
4
%
2
1
.
5
7
%
2
1
.
5
7
%
Ef
f
i
c
i
e
n
t
N
e
t
V
2
-
B1
2
3
.
6
0
%
1
9
.
3
3
%
2
7
.
6
4
%
Ef
f
i
c
i
e
n
t
N
e
t
V
2
-
B2
2
1
.
5
7
%
2
1
.
5
7
%
2
1
.
5
7
%
Ef
f
i
c
i
e
n
t
N
e
t
V
2
-
B3
1
6
.
8
5
%
2
8
.
7
6
%
2
6
.
2
9
%
Ef
f
i
c
i
e
n
t
N
e
t
V
2
-
S
1
5
.
2
8
%
3
2
.
8
1
%
1
7
.
5
3
%
M
o
b
i
l
e
N
e
t
V
2
7
8
.
6
5
%
7
9
.
7
8
%
7
6
.
1
8
%
M
o
b
i
l
e
N
e
t
V
3
-
La
r
g
e
2
1
.
5
7
%
2
9
.
8
9
%
2
7
.
6
4
%
M
o
b
i
l
e
N
e
t
V
3
-
S
mal
l
1
9
.
7
8
%
1
8
.
8
8
%
2
1
.
5
7
%
R
elate
d
to
th
e
lo
s
s
f
u
n
ctio
n
s
,
we
h
av
e
cr
ea
ted
two
s
ep
ar
ate
m
o
d
el
v
ar
iatio
n
s
to
ca
ter
to
d
is
tin
ct
class
if
icatio
n
r
eq
u
ir
em
en
ts
:
−
E
f
f
icien
tNetB
5
-
s
ig
ca
:
u
tili
ze
s
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
as
th
e
lo
s
s
f
u
n
ctio
n
,
s
u
itab
le
f
o
r
m
u
lti
-
class
class
if
icatio
n
task
s
.
T
h
e
s
tan
d
ar
d
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
f
u
n
ctio
n
[
2
2
]
is
:
=
−
1
∑
∑
l
og
(
ℎ
(
,
)
)
=
1
=
1
(
3
)
−
E
f
f
icien
tNetB
5
-
s
ig
b
i:
em
p
lo
y
s
b
in
ar
y
cr
o
s
s
-
en
tr
o
p
y
as
th
e
lo
s
s
f
u
n
ctio
n
,
o
p
tim
ized
f
o
r
b
in
ar
y
class
if
icatio
n
task
s
.
T
h
e
s
tan
d
ar
d
b
in
a
r
y
cr
o
s
s
-
en
tr
o
p
y
f
u
n
ct
io
n
[
2
2
]
is
g
iv
en
as:
=
−
1
∑
[
l
og
(
ℎ
(
)
)
+
(
1
−
)
l
og
(
1
−
ℎ
(
)
)
]
=
1
(
4
)
T
h
ese
ad
ap
tatio
n
s
p
r
o
v
i
d
e
tar
g
eted
s
o
lu
tio
n
s
to
d
if
f
e
r
en
t
class
if
icatio
n
ch
allen
g
es,
en
h
an
cin
g
th
e
‘
m
o
d
el
’
s
ac
cu
r
ac
y
an
d
e
f
f
ici
en
cy
ac
r
o
s
s
d
iv
er
s
e
s
ce
n
ar
io
s
.
I
n
(
3
)
,
s
ig
n
if
ies
th
e
to
tal
co
u
n
t
o
f
t
r
ain
in
g
ex
am
p
les,
with
in
d
icatin
g
th
e
d
is
tin
ct
n
u
m
b
er
o
f
class
es
i
n
v
o
lv
e
d
.
T
h
e
ex
p
r
ess
io
n
is
d
ef
in
ed
as
th
e
tar
g
et
lab
el
f
o
r
th
e
ℎ
tr
ain
in
g
e
x
am
p
le
s
p
ec
if
ic
to
th
e
class
,
wh
ile
is
th
e
in
p
u
t
co
r
r
esp
o
n
d
in
g
to
th
e
ℎ
ex
am
p
le.
He
r
e,
ℎ
r
ep
r
esen
ts
th
e
m
o
d
el
s
tr
u
ctu
r
e
d
b
y
t
h
e
n
e
u
r
al
n
etwo
r
k
weig
h
ts
.
Fo
r
(
4
)
,
d
en
o
tes
th
e
n
u
m
b
er
o
f
tr
ain
in
g
s
am
p
les,
wh
er
e
is
th
e
tar
g
et
lab
el
f
o
r
e
ac
h
tr
ain
in
g
ex
a
m
p
le
in
d
ex
ed
b
y
,
an
d
is
th
e
r
esp
ec
tiv
e
in
p
u
t
f
o
r
th
at
ex
am
p
le.
T
h
e
m
o
d
el,
s
y
m
b
o
lized
b
y
ℎ
,
is
d
ef
in
ed
b
y
th
e
n
e
u
r
al
n
e
two
r
k
weig
h
ts
.
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.
39
,
No
.
1
,
J
u
ly
20
25
:
336
-
3
4
4
340
T
h
e
f
u
n
ctio
n
∗
l
og
(
ℎ
(
)
)
is
in
co
r
p
o
r
ated
to
m
in
im
ize
t
h
e
o
cc
u
r
r
e
n
ce
o
f
p
r
o
b
a
b
ilis
tic
f
alse
n
eg
ativ
es
d
u
r
in
g
th
e
m
o
d
el
tr
ain
in
g
p
h
as
e.
T
h
e
m
o
d
if
ied
E
f
f
icien
tNet
-
B
5
ar
ch
itectu
r
e
is
in
Fig
u
r
e
3.
Fig
u
r
e
3
.
T
h
e
ar
ch
itectu
r
e
o
f
m
o
d
if
ied
E
f
f
icien
t
-
B5
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n m
et
rics
I
n
th
is
s
tu
d
y
,
th
e
d
ata
wer
e
p
ar
titi
o
n
ed
in
to
tr
ain
i
n
g
an
d
te
s
t
s
et
s
at
an
8
0
:2
0
r
atio
,
as
d
etailed
in
T
ab
le
1
.
Su
b
s
eq
u
en
t
ex
p
er
im
en
tal
an
aly
s
es
wer
e
co
n
d
u
cted
u
s
in
g
th
e
Ma
tp
l
o
tlib
s
o
f
twar
e
en
v
ir
o
n
m
en
t
[
2
3
]
o
n
a
lab
o
r
ato
r
y
co
m
p
u
ter
eq
u
ip
p
ed
with
a
2
0
8
0
T
i
Nv
id
ia
GeFo
r
ce
g
r
ap
h
ics
ca
r
d
,
3
2
Gb
R
AM
,
an
d
I
n
tel®
Xeo
n
®
Pro
ce
s
s
o
r
E
5
-
2
6
8
0
.
T
h
e
h
y
p
er
p
ar
a
m
eter
s
,
illu
s
tr
ated
in
Fig
u
r
e
3
,
wer
e
co
n
s
is
ten
t
ac
r
o
s
s
b
o
th
p
r
o
p
o
s
ed
m
o
d
els
an
d
i
n
clu
d
e
d
a
b
atch
s
ize
o
f
8
,
a
lear
n
i
n
g
r
ate
o
f
0
.
0
0
1
,
an
d
a
d
u
r
atio
n
o
f
5
0
e
p
o
ch
s
.
T
h
e
ev
alu
atio
n
m
etr
ics
em
p
lo
y
ed
in
th
is
r
esear
ch
in
clu
d
ed
ac
c
u
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
an
d
F1
-
s
co
r
e
[
2
4
]
wer
e
an
aly
ze
d
i
n
co
n
j
u
n
ctio
n
with
a
co
n
f
u
s
io
n
m
atr
ix
with
r
e
ce
iv
er
-
o
p
e
r
atin
g
c
h
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
es
to
ass
es
s
m
o
d
el
p
er
f
o
r
m
a
n
ce
[
3
]
co
m
p
r
eh
e
n
s
iv
ely
.
T
h
ese
m
etr
i
cs
allo
wed
u
s
to
m
ea
s
u
r
e
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
m
o
d
els
in
i
d
en
tify
in
g
tr
u
e
p
o
s
itiv
es,
tr
u
e
n
e
g
ativ
es,
f
a
ls
e
p
o
s
itiv
es,
an
d
f
alse
n
e
g
ativ
es,
u
l
tim
ately
en
ab
lin
g
a
r
o
b
u
s
t a
n
aly
s
is
o
f
th
e
class
if
ier
’
s
p
er
f
o
r
m
an
ce
ac
r
o
s
s
v
ar
io
u
s
th
r
esh
o
ld
s
.
3
.
2
.
Resul
t
s
a
nd
d
is
cu
s
s
io
n
T
h
is
s
tu
d
y
in
v
esti
g
ated
t
h
e
ef
f
ec
ts
o
f
two
m
o
d
if
icatio
n
s
to
th
e
E
f
f
icien
tNetB
5
m
o
d
el
f
o
r
cu
c
u
r
b
it
leaf
d
is
ea
s
e
d
etec
tio
n
.
W
h
ile
ea
r
lier
s
tu
d
ies
h
av
e
ex
p
lo
r
e
d
v
ar
io
u
s
d
ee
p
lear
n
in
g
tech
n
iq
u
es
f
o
r
p
lan
t
d
is
ea
s
e
r
ec
o
g
n
itio
n
,
th
e
y
h
av
e
n
o
t
ex
p
licitly
ad
d
r
ess
ed
th
e
i
n
f
lu
en
ce
o
f
in
co
r
p
o
r
atin
g
a
s
ig
m
o
i
d
ac
tiv
atio
n
f
u
n
ctio
n
co
m
b
in
ed
with
a
b
in
ar
y
cr
o
s
s
-
e
n
tr
o
p
y
lo
s
s
o
n
m
o
d
el
s
tab
ilit
y
an
d
o
v
er
all
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
d
iv
er
s
e
ev
alu
atio
n
m
etr
ics.
Ou
r
e
x
p
er
im
en
ts
r
ev
ea
led
th
at
b
o
th
p
r
o
p
o
s
ed
m
o
d
i
f
icatio
n
s
d
em
o
n
s
t
r
ated
a
co
n
tin
u
o
u
s
u
p
war
d
tr
e
n
d
in
ac
cu
r
ac
y
d
u
r
i
n
g
tr
ain
in
g
an
d
v
alid
atio
n
.
No
tab
ly
,
E
f
f
icien
tNetB
5
-
s
ig
b
i
s
h
o
wed
a
m
o
r
e
s
tab
le
p
er
f
o
r
m
an
ce
,
as
ev
id
en
ce
d
b
y
Fig
u
r
e
4
,
wh
ich
illu
s
tr
ates
th
e
co
n
s
is
ten
t
in
cr
ea
s
e
in
a
cc
u
r
ac
y
,
r
ec
all,
an
d
p
r
ec
is
io
n
.
E
f
f
icien
tNetB
5
-
s
ig
b
i
ac
h
iev
ed
a
s
tab
le
r
ec
all
o
f
9
8
.
0
2
%
a
n
d
m
ain
tain
e
d
a
v
ali
d
atio
n
p
r
ec
is
io
n
o
f
9
7
.
5
%,
wh
ile
E
f
f
icien
tNetB
5
-
s
ig
ca
ex
h
ib
ited
f
lu
ctu
atio
n
s
(
f
o
r
ex
am
p
le,
a
r
ec
all
d
ip
to
7
0
.
6
8
%
at
ep
o
c
h
7
b
ef
o
r
e
r
ec
o
v
er
in
g
to
9
2
.
7
%).
Fu
r
th
er
an
aly
s
is
u
s
in
g
th
e
co
n
f
u
s
io
n
m
atr
ices Fig
u
r
e
5
an
d
F
ig
u
r
e
6
s
h
o
ws
R
O
C
cu
r
v
es
f
o
r
E
f
f
icien
tNetB
5
-
s
ig
ca
in
Fig
u
r
e
6
(
a
)
an
d
E
f
f
ic
ien
t
NetB5
-
s
ig
b
i
in
Fig
u
r
e
6
(
b
)
co
n
f
i
r
m
ed
th
ese
o
b
s
er
v
atio
n
s
,
an
d
a
n
F1
-
s
co
r
e
co
m
p
ar
is
o
n
s
u
m
m
a
r
ized
i
n
T
ab
le
3
in
d
icate
d
th
at
E
f
f
icien
tNetB
5
-
s
ig
b
i
(
9
6
.
4
2
%)
o
u
t
p
er
f
o
r
m
ed
E
f
f
ici
en
tNetB
5
-
s
ig
ca
(
8
0
.
7
3
%).
Ou
r
f
in
d
in
g
s
s
u
g
g
est
th
at
th
e
in
teg
r
atio
n
o
f
th
e
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ctio
n
an
d
b
i
n
a
r
y
cr
o
s
s
-
en
tr
o
p
y
l
o
s
s
in
E
f
f
icien
tNetB
5
-
s
ig
b
i
s
ig
n
if
ican
tly
en
h
a
n
ce
s
m
o
d
el
p
r
ec
is
io
n
a
n
d
s
tab
ilit
y
.
W
h
en
co
m
p
ar
ed
with
p
r
ev
io
u
s
s
tu
d
ies
in
T
ab
le
4
-
s
u
ch
as
th
o
s
e
b
y
Z
h
an
g
et
a
l.
[
1
9
]
an
d
o
th
er
s
u
s
in
g
E
f
f
icie
n
tNetB
4
-
R
an
g
er
o
r
Mo
b
ileNetV2
[
2
5
]
-
th
e
s
u
p
e
r
io
r
p
er
f
o
r
m
a
n
ce
m
etr
ics
o
f
E
f
f
icien
tNetB
5
-
s
ig
b
i
h
ig
h
lig
h
t
its
r
o
b
u
s
tn
ess
an
d
im
p
r
o
v
e
d
g
e
n
er
aliza
tio
n
ac
r
o
s
s
u
n
s
ee
n
d
ata,
m
ar
k
in
g
a
cle
ar
ad
v
a
n
ce
m
en
t
in
th
e
d
etec
tio
n
o
f
cu
c
u
r
b
it
leaf
d
is
ea
s
es.
Desp
ite
th
ese
p
r
o
m
is
in
g
r
esu
lts
,
th
e
s
tu
d
y
h
as
ce
r
tain
lim
itati
o
n
s
.
T
h
e
cu
r
ate
d
d
at
aset,
co
n
s
is
tin
g
o
f
1
1
,
4
2
5
im
ag
es
ac
r
o
s
s
f
o
u
r
d
i
s
ea
s
e
ca
teg
o
r
ies,
was
l
im
ited
to
cu
cu
r
b
it
leav
es.
As
a
r
esu
lt,
q
u
esti
o
n
s
r
em
ain
r
eg
ar
d
in
g
th
e
m
o
d
el
’
s
ad
ap
tab
ilit
y
to
o
th
er
p
lan
t
s
p
ec
ies
an
d
v
ar
y
in
g
en
v
ir
o
n
m
en
tal
c
o
n
d
it
io
n
s
.
T
h
ese
f
ac
to
r
s
co
u
ld
p
o
ten
tially
im
p
ac
t th
e
g
en
er
aliza
b
ilit
y
o
f
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
an
d
war
r
a
n
t f
u
r
t
h
er
in
v
esti
g
atio
n
.
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
A
n
imp
r
o
ve
d
efficien
tn
et
-
B
5
fo
r
cu
cu
r
b
it lea
f id
en
tifi
ca
tio
n
(
Qu
a
n
g
Hu
n
g
Ha
)
341
Fig
u
r
e
4
.
Acc
u
r
ac
y
,
r
ec
all,
an
d
p
r
ec
is
io
n
r
esu
lts
o
n
th
e
tr
ain
in
g
s
et
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
E
f
f
icien
tNetB
5
-
s
ig
ca
(
lef
t)
an
d
E
f
f
icien
tNetB
5
-
s
ig
b
i (
r
ig
h
t)
(
a)
(
b
)
Fig
u
r
e
6
.
R
OC
cu
r
v
e
o
f
(
a)
E
f
f
icien
tNetB
5
-
s
ig
ca
an
d
(
b
)
an
d
E
f
f
icien
tNetB
5
-
s
ig
b
i
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.
39
,
No
.
1
,
J
u
ly
20
25
:
336
-
3
4
4
342
Ou
r
s
tu
d
y
lay
s
t
h
e
g
r
o
u
n
d
wo
r
k
f
o
r
f
u
tu
r
e
r
esear
ch
av
e
n
u
es.
E
x
p
a
n
d
in
g
th
e
d
ataset
to
en
c
o
m
p
ass
a
wid
er
r
an
g
e
o
f
d
is
ea
s
e
ty
p
es
an
d
en
v
ir
o
n
m
e
n
tal
s
ce
n
ar
io
s
co
u
ld
en
h
an
ce
m
o
d
el
r
o
b
u
s
tn
ess
.
Ad
d
itio
n
ally
,
f
u
tu
r
e
s
tu
d
ies
m
ig
h
t
e
x
p
lo
r
e
th
e
r
ea
l
-
tim
e
d
ep
l
o
y
m
en
t
o
f
E
f
f
icien
tNetB
5
-
s
ig
b
i
o
n
ed
g
e
d
e
v
ices
f
o
r
ag
r
icu
ltu
r
al
m
o
n
ito
r
in
g
.
I
n
te
g
r
atin
g
h
y
p
er
s
p
ec
tr
al
o
r
m
u
ltis
p
ec
tr
al
im
ag
in
g
also
p
r
esen
ts
a
p
r
o
m
is
in
g
o
p
p
o
r
tu
n
ity
to
im
p
r
o
v
e
ea
r
ly
-
s
tag
e
d
is
ea
s
e
d
etec
tio
n
f
u
r
th
er
,
b
r
id
g
i
n
g
th
e
g
ap
b
etwe
en
lab
o
r
ato
r
y
p
er
f
o
r
m
an
ce
an
d
p
r
ac
tical,
f
ie
ld
-
lev
el
ap
p
licatio
n
s
.
I
n
co
n
cl
u
s
io
n
,
th
e
r
esu
lts
f
r
o
m
Fig
u
r
e
s
4
to
6
,
alo
n
g
with
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
d
eta
iled
in
T
ab
le
3
p
r
o
v
id
e
co
n
c
lu
s
iv
e
ev
id
en
ce
th
at
E
f
f
icien
t
NetB5
-
s
ig
b
i
o
f
f
er
s
s
tate
-
of
-
th
e
-
ar
t
p
e
r
f
o
r
m
an
ce
i
n
cu
cu
r
b
it
leaf
d
is
ea
s
e
d
etec
tio
n
.
T
h
e
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
ad
v
an
ce
d
im
ag
e
s
eg
m
en
tatio
n
tech
n
i
q
u
es,
wh
en
co
m
b
i
n
ed
with
a
p
p
r
o
p
r
ia
te
ac
tiv
atio
n
an
d
lo
s
s
f
u
n
ct
io
n
s
,
s
ig
n
if
ican
tly
en
h
an
ce
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
ese
f
in
d
in
g
s
n
o
t
o
n
ly
o
u
tp
e
r
f
o
r
m
p
r
e
v
io
u
s
m
eth
o
d
o
lo
g
ies
b
u
t
also
p
av
e
t
h
e
way
f
o
r
f
u
tu
r
e
i
n
n
o
v
atio
n
s
in
ag
r
icu
ltu
r
al
d
is
ea
s
e
m
an
ag
e
m
en
t.
T
ab
le
3
.
C
o
m
p
a
r
is
o
n
o
f
p
er
f
o
r
m
an
ce
b
etwe
en
E
f
f
icien
tNet
-
B
5
v
er
s
io
n
s
N
e
t
w
o
r
k
A
c
c
u
r
a
c
y
(
%
)
R
e
c
a
l
l
(
%
)
P
r
e
c
i
s
i
o
n
(
%
)
F1
-
sc
o
r
e
Ef
f
i
c
i
e
n
t
N
e
t
-
B
5
[
1
1
]
8
2
.
2
5
%
9
1
.
8
0
%
8
2
.
5
4
%
8
2
.
1
7
%
Ef
f
i
c
i
e
n
t
N
e
t
B
5
-
si
g
c
a
8
8
.
5
4
%
9
4
.
6
1
%
7
0
.
4
%
8
0
.
7
3
%
Ef
f
i
c
i
e
n
t
N
e
t
B
5
-
si
g
b
i
9
7
.
0
7
%
9
8
.
0
2
%
9
5
.
7
8
%
9
6
.
4
2
%
T
ab
le
4
.
C
o
m
p
a
r
in
g
E
f
f
icien
t
NetB5
-
s
ig
b
i w
ith
o
th
er
r
elev
a
n
t stu
d
ies
S
t
u
d
y
N
u
mb
e
r
o
f
l
a
y
e
r
s
O
r
i
g
i
n
a
l
d
a
t
a
N
e
t
w
o
r
k
Te
st
a
c
c
u
r
a
c
y
Th
e
i
r
d
a
t
a
O
u
r
d
a
t
a
M
i
a
e
t
a
l
.
[
2
5
]
7
5
2
5
M
o
b
i
l
e
N
e
t
V
2
9
3
.
2
3
%
8
9
.
6
6
%
Zh
a
n
g
e
t
a
l
.
[
1
9
]
4
2
8
1
6
Ef
f
i
c
i
e
n
t
N
e
t
B
4
-
R
a
n
g
e
r
9
6
.
3
9
%
9
6
.
5
6
%
Th
i
s
st
u
d
y
4
2
2
7
5
Ef
f
i
c
i
e
n
t
N
e
t
B
5
-
si
g
b
i
-
9
7
.
0
7
%
4.
CO
NCLU
SI
O
N
Ou
r
s
tu
d
y
estab
lis
h
es
a
r
o
b
u
s
t
f
o
u
n
d
atio
n
f
o
r
d
etec
tin
g
an
d
d
if
f
er
en
tiatin
g
p
lan
t
d
i
s
ea
s
es
in
co
n
tr
o
lled
en
v
ir
o
n
m
e
n
ts
,
s
ig
n
if
ican
tly
co
n
tr
ib
u
tin
g
to
th
e
f
ield
.
W
e
h
av
e
d
ev
elo
p
ed
a
n
o
v
e
l
d
ataset
f
ea
tu
r
in
g
1
1
,
4
2
5
a
u
g
m
en
te
d
im
ag
es
o
f
cu
cu
m
b
er
an
d
ca
n
talo
u
p
e
p
lan
ts
,
ca
teg
o
r
ized
in
to
f
o
u
r
d
is
e
ase
class
if
icatio
n
s
:
an
th
r
ac
n
o
s
e,
p
o
wd
er
y
m
ild
ew
,
d
o
wn
y
m
ild
ew,
an
d
f
r
esh
le
af
.
W
e
p
r
o
v
id
e
a
p
u
b
licly
av
a
ilab
le
r
eso
u
r
ce
th
at
h
as
th
e
p
o
ten
tial
to
d
r
iv
e
f
u
t
u
r
e
r
esear
c
h
a
n
d
i
n
n
o
v
atio
n
in
p
lan
t
d
is
ea
s
e
m
an
ag
e
m
en
t
.
Ad
d
itio
n
al
ly
,
we
in
tr
o
d
u
ce
d
an
e
n
h
an
ce
d
class
if
icatio
n
m
o
d
el,
t
h
e
E
f
f
icien
t
NetB5
-
s
ig
b
i,
wh
ich
u
tili
ze
s
th
e
E
f
f
icien
tNet
-
B
5
ar
ch
itectu
r
e
f
in
e
-
tu
n
ed
with
a
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ctio
n
an
d
b
in
ar
y
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
,
ac
h
iev
in
g
an
im
p
r
ess
iv
e
ac
cu
r
ac
y
o
f
9
7
.
0
7
%,
d
em
o
n
s
tr
a
tin
g
its
ca
p
ab
ilit
y
f
o
r
p
r
ec
is
e
d
is
ea
s
e
id
en
tific
atio
n
an
d
class
if
icatio
n
.
Ho
wev
er
,
th
e
s
co
p
e
o
f
th
is
r
esear
ch
ex
ten
d
s
b
ey
o
n
d
its
im
m
ed
iate
r
esu
lts
.
T
h
e
d
ataset
n
ee
d
s
to
b
e
ex
p
an
d
ed
to
in
cl
u
d
e
m
o
r
e
d
ata
f
r
o
m
a
wid
e
r
r
an
g
e
o
f
s
p
ec
ies
with
in
th
e
C
u
cu
r
b
itace
a
e
f
am
ily
.
W
h
ile
th
e
cu
r
r
en
t
d
ataset
f
o
c
u
s
es
o
n
cu
cu
m
b
er
an
d
ca
n
talo
u
p
e
p
lan
t
s
,
o
th
er
s
ig
n
if
ican
t
cr
o
p
s
in
t
h
e
f
am
ily
,
s
u
ch
as
wate
r
m
elo
n
,
s
q
u
ash
,
p
u
m
p
k
in
,
an
d
zu
cc
h
in
i,
s
h
o
u
l
d
b
e
in
co
r
p
o
r
ated
to
in
cr
ea
s
e
d
iv
er
s
ity
a
n
d
m
ak
e
th
e
m
o
d
el
ap
p
licab
le
to
a
b
r
o
ad
er
s
p
ec
tr
u
m
o
f
c
u
cu
r
b
it
d
is
ea
s
es.
Fu
r
th
er
m
o
r
e,
co
llectin
g
d
ata
u
n
d
er
v
a
r
y
in
g
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
s
u
ch
as
d
if
f
er
en
t
h
u
m
id
it
y
lev
els,
tem
p
er
atu
r
es,
an
d
lig
h
t
ex
p
o
s
u
r
es,
will
en
h
a
n
ce
th
e
m
o
d
el
’
s
r
o
b
u
s
tn
ess
an
d
ad
ap
tab
ilit
y
to
r
ea
l
-
wo
r
ld
s
c
en
ar
io
s
.
I
n
clu
d
i
n
g
im
a
g
es
o
f
p
lan
ts
at
d
if
f
e
r
en
t
g
r
o
wth
s
tag
es
an
d
v
ar
y
in
g
s
e
v
er
ities
o
f
d
is
ea
s
e
s
y
m
p
to
m
s
will
also
allo
w
th
e
m
o
d
el
to
id
en
tify
ea
r
l
y
-
s
tag
e
in
f
ec
tio
n
s
an
d
p
r
o
v
id
e
a
m
o
r
e
g
r
an
u
lar
class
if
icatio
n
.
E
x
p
an
d
in
g
t
h
e
d
ataset
to
in
cl
u
d
e
h
y
p
e
r
s
p
ec
tr
al
an
d
m
u
ltis
p
ec
t
r
al
im
ag
in
g
co
u
l
d
en
h
an
ce
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
an
d
en
a
b
le
ea
r
ly
-
s
tag
e
d
is
ea
s
e
d
etec
tio
n
,
ad
d
r
ess
in
g
a
p
r
ess
in
g
n
ee
d
in
r
ea
l
-
wo
r
ld
ag
r
icu
ltu
r
al
s
ce
n
ar
i
o
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Qu
an
g
Hu
n
g
Ha
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
T
r
o
n
g
-
Min
h
Ho
a
n
g
✓
✓
✓
Min
h
T
r
ien
Ph
am
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
A
n
imp
r
o
ve
d
efficien
tn
et
-
B
5
fo
r
cu
cu
r
b
it lea
f id
en
tifi
ca
tio
n
(
Qu
a
n
g
Hu
n
g
Ha
)
343
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Der
iv
ed
d
ata
s
u
p
p
o
r
ti
n
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
i
n
g
au
th
o
r
M.T.P
o
n
r
e
q
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
B
.
S
a
l
e
h
i
e
t
a
l
.
,
“
C
u
c
u
r
b
i
t
s
p
l
a
n
t
s:
a
k
e
y
e
m
p
h
a
s
i
s
t
o
i
t
s
p
h
a
r
mac
o
l
o
g
i
c
a
l
p
o
t
e
n
t
i
a
l
,
”
M
o
l
e
c
u
l
e
s
,
v
o
l
.
2
4
,
n
o
.
1
0
,
p
.
1
8
5
4
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
m
o
l
e
c
u
l
e
s
2
4
1
0
1
8
5
4
.
[
2
]
A
.
B
u
t
e
,
S
.
A
m
b
ă
r
u
ş,
C
.
B
r
e
z
e
a
n
u
,
M
.
C
ă
l
i
n
,
a
n
d
M
.
B
r
e
z
e
a
n
u
,
“
Th
e
st
u
d
y
o
f
t
o
l
e
r
a
n
c
e
o
f
s
o
m
e
s
p
e
c
i
e
s
a
n
d
v
a
r
i
e
t
i
e
s
o
f
c
u
c
u
r
b
i
t
a
c
e
a
e
t
o
t
h
e
a
t
t
a
c
k
o
f
p
a
t
h
o
g
e
n
s
,
”
S
c
i
e
n
t
i
f
i
c
S
t
u
d
i
e
s
&
Re
se
a
r
c
h
.
S
e
ri
e
s
Bi
o
l
o
g
y
,
v
o
l
.
2
9
,
n
o
.
2
,
p
.
2
8
,
2
0
2
0
.
[
3
]
H
.
M
a
t
s
u
o
,
M
.
S
u
g
i
y
a
ma,
a
n
d
Y
.
Y
o
sh
i
o
k
a
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
n
e
w
so
u
r
c
e
o
f
r
e
si
s
t
a
n
c
e
t
o
a
n
t
h
r
a
c
n
o
se
i
n
c
u
c
u
mb
e
r
i
n
Ja
p
a
n
,
”
H
o
rt
i
c
u
l
t
u
r
e
J
o
u
rn
a
l
,
v
o
l
.
9
1
,
n
o
.
1
,
p
p
.
4
9
–
5
7
,
2
0
2
2
,
d
o
i
:
1
0
.
2
5
0
3
/
h
o
r
t
j
.
U
T
D
-
3
2
2
.
[
4
]
Z.
S
u
n
,
S
.
Y
u
,
Y
.
H
u
,
a
n
d
Y
.
W
e
n
,
“
B
i
o
l
o
g
i
c
a
l
c
o
n
t
r
o
l
o
f
t
h
e
c
u
c
u
m
b
e
r
d
o
w
n
y
m
i
l
d
e
w
p
a
t
h
o
g
e
n
p
s
e
u
d
o
p
e
r
o
n
o
sp
o
r
a
c
u
b
e
n
s
i
s,
”
H
o
rt
i
c
u
l
t
u
r
a
e
,
v
o
l
.
8
,
n
o
.
5
,
p
.
4
1
0
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
h
o
r
t
i
c
u
l
t
u
r
a
e
8
0
5
0
4
1
0
.
[
5
]
A
.
L
e
b
e
d
a
,
E
.
K
ř
í
st
k
o
v
á
,
B
.
M
i
e
sl
e
r
o
v
á
,
N
.
P
.
S
.
D
h
i
l
l
o
n
,
a
n
d
J
.
D
.
M
c
C
r
e
i
g
h
t
,
“
S
t
a
t
u
s
,
g
a
p
s
a
n
d
p
e
r
sp
e
c
t
i
v
e
s
o
f
p
o
w
d
e
r
y
mi
l
d
e
w
r
e
si
st
a
n
c
e
r
e
s
e
a
r
c
h
a
n
d
b
r
e
e
d
i
n
g
i
n
c
u
c
u
r
b
i
t
s,”
C
ri
t
i
c
a
l
Re
v
i
e
w
s
i
n
Pl
a
n
t
S
c
i
e
n
c
e
s
,
v
o
l
.
4
3
,
n
o
.
4
,
p
p
.
2
1
1
–
2
9
0
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
0
/
0
7
3
5
2
6
8
9
.
2
0
2
4
.
2
3
1
5
7
1
0
.
[
6
]
S
.
P
.
M
o
h
a
n
t
y
,
D
.
P
.
H
u
g
h
e
s,
a
n
d
M
.
S
a
l
a
t
h
é
,
“
U
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
m
a
g
e
-
b
a
s
e
d
p
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
,
”
F
ro
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
7
,
n
o
.
S
e
p
t
e
m
b
e
r
,
S
e
p
.
2
0
1
6
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
1
6
.
0
1
4
1
9
.
[
7
]
M
.
M
.
G
h
a
z
i
,
B
.
Y
a
n
i
k
o
g
l
u
,
a
n
d
E.
A
p
t
o
u
l
a
,
“
P
l
a
n
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
v
i
a
o
p
t
i
m
i
z
a
t
i
o
n
o
f
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
p
a
r
a
m
e
t
e
r
s,”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
2
3
5
,
p
p
.
2
2
8
–
2
3
5
,
A
p
r
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
7
.
0
1
.
0
1
8
.
[
8
]
A
.
K
r
i
z
h
e
v
s
k
y
,
I
.
S
u
t
s
k
e
v
e
r
,
a
n
d
G
.
E.
H
i
n
t
o
n
,
“
I
mag
e
N
e
t
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
o
f
t
h
e
A
C
M
,
v
o
l
.
6
0
,
n
o
.
6
,
p
p
.
8
4
–
9
0
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
0
6
5
3
8
6
.
[
9
]
K
.
S
i
m
o
n
y
a
n
a
n
d
A
.
Zi
ss
e
r
ma
n
,
“
V
e
r
y
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
s
f
o
r
l
a
r
g
e
-
s
c
a
l
e
i
ma
g
e
r
e
c
o
g
n
i
t
i
o
n
,
”
3
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
L
e
a
rn
i
n
g
Re
p
res
e
n
t
a
t
i
o
n
s
,
I
C
L
R
2
0
1
5
-
C
o
n
f
e
re
n
c
e
T
r
a
c
k
P
ro
c
e
e
d
i
n
g
s
,
2
0
1
5
.
[
1
0
]
H
.
A
.
A
.
G
.
H
o
w
a
r
d
,
M
.
Z
h
u
,
B
.
C
h
e
n
,
D
.
K
a
l
e
n
i
c
h
e
n
k
o
,
W
.
W
a
n
g
,
T
.
W
e
y
a
n
d
,
M
.
A
n
d
r
e
e
t
t
o
,
“
M
o
b
i
l
e
N
e
t
s:
e
f
f
i
c
i
e
n
t
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
mo
b
i
l
e
v
i
s
i
o
n
a
p
p
l
i
c
a
t
i
o
n
s,”
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
5
3
–
5
7
,
2
0
0
9
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
1
7
0
4
.
0
4
8
6
1
.
[
1
1
]
M
.
T
a
n
a
n
d
Q
.
V
.
L
e
,
“
Ef
f
i
c
i
e
n
t
N
e
t
:
r
e
t
h
i
n
k
i
n
g
m
o
d
e
l
s
c
a
l
i
n
g
f
o
r
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,”
3
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
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
,
I
C
ML
2
0
1
9
,
v
o
l
.
2
0
1
9
-
Ju
n
e
,
p
p
.
1
0
6
9
1
–
1
0
7
0
0
,
2
0
1
9
.
[
1
2
]
B
.
Z
o
p
h
a
n
d
Q
.
V
.
L
e
,
“
N
e
u
r
a
l
a
r
c
h
i
t
e
c
t
u
r
e
se
a
r
c
h
w
i
t
h
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
,
”
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
L
e
a
r
n
i
n
g
Re
p
r
e
se
n
t
a
t
i
o
n
s
,
I
C
L
R
2
0
1
7
-
C
o
n
f
e
r
e
n
c
e
T
r
a
c
k
Pr
o
c
e
e
d
i
n
g
s
,
2
0
1
7
.
[
1
3
]
H
.
A
h
me
d
,
M
.
A
.
H
o
ss
a
i
n
,
I
.
H
o
ss
a
i
n
,
S
.
S
.
A
k
h
i
,
a
n
d
I
.
J
.
Li
m
a
,
“
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
p
l
a
n
t
d
i
se
a
ses
i
n
l
e
a
v
e
s
t
h
r
o
u
g
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
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
ri
n
g
a
n
d
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
(
I
J
E
EC
S
)
,
v
o
l
.
2
8
,
n
o
.
3
,
p
p
.
1
6
7
6
–
1
6
8
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
8
.
i
3
.
p
p
1
6
7
6
-
1
6
8
3
.
[
1
4
]
P
.
S
.
Th
a
k
u
r
,
T.
S
h
e
o
r
e
y
,
a
n
d
A
.
O
j
h
a
,
“
V
G
G
-
I
C
N
N
:
A
Li
g
h
t
w
e
i
g
h
t
C
N
N
mo
d
e
l
f
o
r
c
r
o
p
d
i
sea
s
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
2
,
n
o
.
1
,
p
p
.
4
9
7
–
5
2
0
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
022
-
1
3
1
4
4
-
z.
[
1
5
]
Y
.
W
a
n
g
,
P
.
Z
h
a
n
g
,
a
n
d
S
.
T
i
a
n
,
“
T
o
ma
t
o
l
e
a
f
d
i
se
a
se
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
a
t
t
e
n
t
i
o
n
mec
h
a
n
i
sm
a
n
d
m
u
l
t
i
-
sc
a
l
e
f
e
a
t
u
r
e
f
u
s
i
o
n
,
”
F
r
o
n
t
i
e
r
s
i
n
P
l
a
n
t
S
c
i
e
n
c
e
v
o
l
.
1
5
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s
.
2
0
2
4
.
1
3
8
2
8
0
2
.
[
1
6
]
G
.
L.
G
r
i
n
b
l
a
t
,
L.
C
.
U
z
a
l
,
M
.
G
.
La
r
e
se,
a
n
d
P
.
M
.
G
r
a
n
i
t
t
o
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
p
l
a
n
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
si
n
g
v
e
i
n
,
”
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
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
2
7
,
p
p
.
4
1
8
–
4
2
4
,
S
e
p
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
1
6
.
0
7
.
0
0
3
.
[
1
7
]
J.
M
a
,
K
.
D
u
,
F
.
Z
h
e
n
g
,
L
.
Z
h
a
n
g
,
Z
.
G
o
n
g
,
a
n
d
Z.
S
u
n
,
“
A
r
e
c
o
g
n
i
t
i
o
n
me
t
h
o
d
f
o
r
c
u
c
u
m
b
e
r
d
i
s
e
a
ses
u
s
i
n
g
l
e
a
f
sy
m
p
t
o
m i
ma
g
e
s
b
a
s
e
d
o
n
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
,
”
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
5
4
,
p
p
.
1
8
–
2
4
,
N
o
v
.
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
4
8
.
[
18]
S
.
Z
h
a
n
g
,
S
.
Z
h
a
n
g
,
C
.
Z
h
a
n
g
,
X
.
W
a
n
g
,
a
n
d
Y
.
S
h
i
,
“
C
u
c
u
mb
e
r
l
e
a
f
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
w
i
t
h
g
l
o
b
a
l
p
o
o
l
i
n
g
d
i
l
a
t
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
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
r
o
n
i
c
s
i
n
Ag
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
6
2
,
p
p
.
4
2
2
–
4
3
0
,
Ju
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
1
9
.
0
3
.
0
1
2
.
[
1
9
]
P
.
Z
h
a
n
g
,
L
.
Y
a
n
g
,
a
n
d
D
.
L
i
,
“
Ef
f
i
c
i
e
n
t
N
e
t
-
B4
-
R
a
n
g
e
r
:
a
n
o
v
e
l
m
e
t
h
o
d
f
o
r
g
r
e
e
n
h
o
u
se
c
u
c
u
m
b
e
r
d
i
sea
s
e
r
e
c
o
g
n
i
t
i
o
n
u
n
d
e
r
n
a
t
u
r
a
l
c
o
m
p
l
e
x
e
n
v
i
r
o
n
m
e
n
t
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ro
n
i
c
s
i
n
Ag
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
7
6
,
p
.
1
0
5
6
5
2
,
S
e
p
.
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
6
5
2
.
[
2
0
]
W
.
Z
h
a
n
g
,
L.
S
h
e
n
,
a
n
d
C
.
S
.
F
o
o
,
“
R
e
t
h
i
n
k
i
n
g
t
h
e
r
o
l
e
o
f
p
r
e
-
t
r
a
i
n
e
d
n
e
t
w
o
r
k
s
i
n
s
o
u
r
c
e
-
f
r
e
e
d
o
ma
i
n
a
d
a
p
t
a
t
i
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
E
EE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
p
p
.
1
8
7
9
5
–
1
8
8
0
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
V
5
1
0
7
0
.
2
0
2
3
.
0
1
7
2
7
.
[
2
1
]
A
.
A
p
i
c
e
l
l
a
,
F
.
D
o
n
n
a
r
u
mm
a
,
F
.
I
sg
r
ò
,
a
n
d
R
.
P
r
e
v
e
t
e
,
“
A
s
u
r
v
e
y
o
n
m
o
d
e
r
n
t
r
a
i
n
a
b
l
e
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s,”
N
e
u
ra
l
N
e
t
w
o
rks
,
v
o
l
.
1
3
8
,
p
p
.
1
4
–
3
2
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
2
1
.
0
1
.
0
2
6
.
[
2
2
]
Y
.
H
o
a
n
d
S
.
W
o
o
k
e
y
,
“
T
h
e
r
e
a
l
-
w
o
r
l
d
-
w
e
i
g
h
t
c
r
o
ss
-
e
n
t
r
o
p
y
l
o
ss
f
u
n
c
t
i
o
n
:
m
o
d
e
l
i
n
g
t
h
e
c
o
s
t
s
o
f
m
i
s
l
a
b
e
l
i
n
g
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
4
8
0
6
–
4
8
1
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
6
2
6
1
7
.
[
2
3
]
J.
D
.
H
u
n
t
e
r
,
“
M
a
t
p
l
o
t
l
i
b
:
a
2
D
g
r
a
p
h
i
c
s
e
n
v
i
r
o
n
m
e
n
t
,
”
C
o
m
p
u
t
i
n
g
i
n
S
c
i
e
n
c
e
&
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
,
n
o
.
3
,
p
p
.
9
0
–
9
5
,
2
0
0
7
,
d
o
i
:
1
0
.
1
1
0
9
/
M
C
S
E.
2
0
0
7
.
5
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.
39
,
No
.
1
,
J
u
ly
20
25
:
336
-
3
4
4
344
[
2
4
]
D
.
M
.
W
.
P
o
w
e
r
s
,
“
E
v
a
l
u
a
t
i
o
n
:
f
r
o
m
p
r
e
c
i
si
o
n
,
r
e
c
a
l
l
a
n
d
F
-
mea
s
u
r
e
t
o
R
O
C
,
i
n
f
o
r
m
e
d
n
e
ss
,
mar
k
e
d
n
e
ss
a
n
d
c
o
r
r
e
l
a
t
i
o
n
,
”
2
0
2
0
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
2
0
1
0
.
1
6
0
6
1
.
[
2
5
]
M
.
J
.
M
i
a
,
S
.
K
.
M
a
r
i
a
,
S
.
S
.
T
a
k
i
,
a
n
d
A
.
A
.
B
i
sw
a
s,
“
C
u
c
u
m
b
e
r
d
i
se
a
se
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
B
u
l
l
e
t
i
n
o
f
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
0
,
n
o
.
6
,
p
p
.
3
4
3
2
–
3
4
4
3
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
0
i
6
.
3
0
9
6
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Qu
a
n
g
H
u
n
g
H
a
is
c
u
rre
n
t
l
y
p
u
rsu
in
g
a
d
e
g
re
e
i
n
a
g
ricu
lt
u
ra
l
tec
h
n
o
lo
g
y
a
t
VN
U
Un
iv
e
rsity
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
.
He
is
i
n
th
e
se
v
e
n
th
se
m
e
ste
r
o
f
h
is
st
u
d
ies
,
with
a
fo
c
u
s
o
n
p
re
c
isio
n
a
g
ricu
lt
u
re
a
n
d
re
se
a
rc
h
a
c
ti
v
it
ies
with
th
e
Di
g
it
a
l
Ag
ric
u
lt
u
ra
l
Tec
h
n
o
l
o
g
y
Lab
o
ra
to
r
y
.
He
is
a
c
ti
v
e
ly
e
n
g
a
g
e
d
i
n
e
x
p
lo
r
in
g
in
n
o
v
a
ti
v
e
a
g
r
icu
lt
u
ra
l
tec
h
n
o
l
o
g
ies
t
o
imp
r
o
v
e
fa
rm
in
g
e
fficie
n
c
y
a
n
d
s
u
sta
in
a
b
i
li
ty
.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
h
u
n
g
h
a
1
5
1
2
3
@g
m
a
il
.
c
o
m
.
Tr
o
n
g
-
Mi
n
h
H
o
a
n
g
(S
e
n
i
o
r
M
e
m
b
e
r,
IEE
E)
re
c
e
iv
e
d
a
b
a
c
h
e
lo
r
’
s
d
e
g
re
e
in
p
h
y
sic
s
e
n
g
in
e
e
rin
g
(1
9
9
4
)
a
n
d
e
lec
tro
n
ic
a
n
d
tele
c
o
m
m
u
n
ica
ti
o
n
e
n
g
i
n
e
e
rin
g
(
1
9
9
9
)
fr
o
m
Ha
n
o
i
U
n
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
,
a
m
a
ste
r
’
s
d
e
g
re
e
i
n
e
lec
tro
n
ic
a
n
d
tele
c
o
m
m
u
n
ica
ti
o
n
e
n
g
i
n
e
e
rin
g
(2
0
0
3
),
a
n
d
th
e
P
h
.
D.
d
e
g
r
e
e
in
tele
c
o
m
m
u
n
ica
ti
o
n
e
n
g
in
e
e
rin
g
(
2
0
1
4
)
fr
o
m
P
o
sts
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
s
In
sti
tu
te
o
f
Tec
h
n
o
lo
g
y
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
th
e
Tele
c
o
m
m
u
n
ica
ti
o
n
F
a
c
u
lt
y
o
f
P
o
sts
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
s
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
.
He
is
t
h
e
h
e
a
d
o
f
th
e
Tele
c
o
m
m
u
n
ica
ti
o
n
Ne
two
rk
De
p
a
rtme
n
t
a
n
d
t
h
e
h
e
a
d
o
f
th
e
In
telli
g
e
n
t
Co
n
n
e
c
ted
Ne
two
rk
s
Lab
o
ra
t
o
ry
.
He
h
a
s
b
e
e
n
wo
rk
i
n
g
o
n
t
h
e
issu
e
s
su
rro
u
n
d
in
g
th
e
p
e
rf
o
rm
a
n
c
e
o
f
wire
les
s
n
e
two
rk
s.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
n
e
two
r
k
p
e
rfo
rm
a
n
c
e
a
n
d
se
c
u
ri
ty
issu
e
s
i
n
e
d
g
e
c
o
m
p
u
ti
n
g
,
wire
les
s
m
o
b
il
e
n
e
two
rk
s,
a
n
d
5
G
/6
G
n
e
two
rk
s.
He
is
a
m
e
m
b
e
r
o
f
th
e
IEE
E
a
n
d
IEE
E
Circu
it
s
a
n
d
S
y
ste
m
s
S
o
c
iety
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
o
a
n
g
tro
n
g
m
i
n
h
@
p
ti
t.
e
d
u
.
v
n
.
Mi
n
h
Tr
ien
Ph
a
m
o
b
tain
e
d
h
is
Ba
c
h
e
lo
r
’
s
a
n
d
M
a
ste
r
’
s
d
e
g
r
e
e
s
in
e
lec
tro
n
ics
a
n
d
tele
c
o
m
m
u
n
ica
ti
o
n
fr
o
m
VN
U
Un
iv
e
rsity
o
f
En
g
in
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
(VN
U
-
UET)
in
2
0
0
3
a
n
d
2
0
0
7
,
re
sp
e
c
ti
v
e
l
y
,
a
n
d
a
P
h
.
D
.
i
n
e
lec
tri
c
a
l
e
n
g
i
n
e
e
rin
g
fro
m
Ch
u
n
g
b
u
k
Na
ti
o
n
a
l
Un
iv
e
rsity
(Ko
re
a
)
in
2
0
1
1
.
H
e
is
a
Lec
tu
re
r
a
t
VN
U
Un
iv
e
rsity
o
f
En
g
in
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
,
Vie
tn
a
m
Na
ti
o
n
a
l
Un
iv
e
rsity
Ha
n
o
i
,
Vie
tn
a
m
.
His
re
se
a
rc
h
a
re
a
s
a
r
e
o
p
ti
m
iza
ti
o
n
a
l
g
o
ri
th
m
s,
e
d
g
e
c
o
m
p
u
ti
n
g
,
ro
b
o
t
ics
,
a
n
d
i
n
telli
g
e
n
t
sy
ste
m
s.
He
is
t
h
e
d
irec
to
r
o
f
th
e
Dig
it
a
l
A
g
ricu
lt
u
re
Lab
a
t
th
e
F
a
c
u
lt
y
o
f
Ag
ricu
l
tu
re
Tec
h
n
o
lo
g
y
.
He
h
a
s
fil
e
d
se
v
e
ra
l
p
a
ten
ts
a
n
d
i
n
d
u
strial
d
e
si
g
n
s
fo
r
h
is
in
n
o
v
a
ti
o
n
s.
He
is
a
lso
a
n
a
u
th
o
r
/co
-
a
u
t
h
o
r
o
f
se
v
e
ra
l
b
o
o
k
s,
re
se
a
rc
h
p
ro
jec
ts,
a
n
d
n
u
m
e
ro
u
s
r
e
se
a
rc
h
p
a
p
e
rs
p
u
b
li
s
h
e
d
i
n
d
o
m
e
stic
a
n
d
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls an
d
c
o
n
fe
re
n
c
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
tri
e
n
p
m
@v
n
u
.
e
d
u
.
v
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.