I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
,
p
p
.
1
0
1
3
~
1
0
22
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
1
3
.
i
4
.
pp
1
0
1
3
-
1
0
22
1013
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Enha
nced U
-
Ne
t
mo
dels with
enco
der and a
ug
men
t
a
tion for
phy
topla
nkton se
g
menta
tion
O
v
ide D
ec
ro
ly
Wis
nu
Ard
hi
1
,
2
,
7
,
T
ri
Ret
na
nin
g
s
ih So
epr
o
bo
wa
t
i
3
,
4
,
6
,
K
us
wo
ro
Adi
3
,
5
,
E
s
a
P
ra
k
a
s
a
7
,
Arie
f
Ra
chm
a
n
8
1
D
o
c
t
o
r
a
l
o
f
I
n
f
o
r
ma
t
i
o
n
S
y
st
e
m
P
r
o
g
r
a
m,
S
c
h
o
o
l
o
f
P
o
st
g
r
a
d
u
a
t
e
S
t
u
d
i
e
s,
U
n
i
v
e
r
si
t
a
s
D
i
p
o
n
e
g
o
r
o
,
S
e
m
a
r
a
n
g
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
V
o
c
a
t
i
o
n
a
l
S
c
h
o
o
l
,
U
n
i
v
e
r
s
i
t
a
s Se
b
e
l
a
s
M
a
r
e
t
,
S
u
r
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
3
S
c
h
o
o
l
o
f
P
o
st
g
r
a
d
u
a
t
e
S
t
u
d
i
e
s,
U
n
i
v
e
r
si
t
a
s Di
p
o
n
e
g
o
r
o
,
S
e
mara
n
g
,
I
n
d
o
n
e
si
a
4
D
e
p
a
r
t
me
n
t
o
f
B
i
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
o
f
M
a
t
h
e
ma
t
i
c
s,
U
n
i
v
e
r
s
i
t
a
s D
i
p
o
n
e
g
o
r
o
,
S
e
mara
n
g
,
I
n
d
o
n
e
s
i
a
5
D
e
p
a
r
t
me
n
t
o
f
P
h
y
si
c
s,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
o
f
M
a
t
h
e
m
a
t
i
c
s,
U
n
i
v
e
r
si
t
a
s D
i
p
o
n
e
g
o
r
o
,
S
e
m
a
r
a
n
g
,
I
n
d
o
n
e
si
a
6
C
l
u
st
e
r
f
o
r
P
a
l
e
o
l
i
m
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
a
s D
i
p
o
n
e
g
o
r
o
,
S
e
mar
a
n
g
,
I
n
d
o
n
e
s
i
a
7
R
e
s
e
a
r
c
h
C
e
n
t
e
r
f
o
r
D
a
t
a
a
n
d
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
,
N
a
t
i
o
n
a
l
R
e
s
e
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
o
n
A
g
e
n
c
y
(
B
R
I
N
)
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
si
a
8
R
e
s
e
a
r
c
h
C
e
n
t
e
r
f
o
r
O
c
e
a
n
o
g
r
a
p
h
y
,
N
a
t
i
o
n
a
l
R
e
se
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
o
n
A
g
e
n
c
y
(
B
R
I
N
)
,
Ja
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
3
0
,
2
0
2
3
R
ev
is
ed
Ma
y
1
9
,
2
0
2
4
Acc
ep
ted
Sep
9
,
2
0
2
4
Th
is
stu
d
y
c
o
m
p
re
h
e
n
siv
e
ly
a
n
a
ly
z
e
s
U
-
Ne
t
m
o
d
e
ls
fo
r
se
m
a
n
ti
c
se
g
m
e
n
tatio
n
i
n
p
h
y
to
p
lan
k
to
n
i
m
a
g
e
re
c
o
g
n
it
i
o
n
,
lev
e
ra
g
in
g
e
n
c
o
d
e
rs
su
c
h
a
s
Eff
icie
n
tNe
t
-
B5
,
M
o
b
il
e
N
e
tV2
,
Re
s
N
e
t5
0
,
a
n
d
Re
s
N
e
X
t5
0
a
n
d
e
m
p
lo
y
i
n
g
th
e
A
d
a
m
o
p
ti
m
ize
r.
Th
e
re
se
a
rc
h
h
ig
h
li
g
h
ts
t
h
e
U
-
Ne
t
M
o
b
i
leN
e
tV2
m
o
d
e
l
wi
th
o
p
ti
c
a
l
d
isto
rt
io
n
,
wh
ich
a
c
h
iev
e
s
n
o
tab
le
tes
t
sc
o
re
s
with
9
3
.
6
9
%
Dic
e
,
8
8
.
1
4
%
i
n
ters
e
c
ti
o
n
o
v
e
r
u
n
io
n
(
I
o
U
)
,
9
9
.
8
9
%
P
re
c
isio
n
,
a
n
d
1
0
0
%
Re
c
a
ll
,
u
n
d
e
rsc
o
rin
g
th
e
e
ffica
c
y
o
f
th
e
a
p
p
li
e
d
a
u
g
m
e
n
tatio
n
stra
teg
ies
,
in
c
l
u
d
i
n
g
g
e
o
m
e
tri
c
a
n
d
d
ist
o
rti
o
n
tran
sf
o
rm
s,
a
n
d
c
o
lo
r
a
n
d
b
l
u
r
tec
h
n
i
q
u
e
s
.
Th
e
U
-
Ne
t
Re
sN
e
t5
0
m
o
d
e
l
wit
h
m
i
x
tran
sf
o
rm
c
o
n
siste
n
tl
y
d
e
m
o
n
stra
tes
h
ig
h
a
c
c
u
ra
c
y
in
c
rit
ica
l
m
e
tri
c
s,
o
u
tp
e
rfo
rm
in
g
o
th
e
rs,
wh
i
le
Eff
icie
n
tNe
t
-
B5
wit
h
b
l
u
r
su
g
g
e
sts
in
c
re
a
se
d
m
o
d
e
l
se
n
siti
v
it
y
with
imp
r
o
v
e
d
re
c
a
ll
.
T
h
e
s
e
re
su
lt
s
u
n
d
e
rsc
o
re
th
e
c
ru
c
ial
ro
le
o
f
e
n
c
o
d
e
r
-
a
u
g
m
e
n
tatio
n
sy
n
e
r
g
y
i
n
m
o
d
e
l
p
e
rfo
rm
a
n
c
e
.
Train
in
g
a
n
d
tes
t
in
g
ti
m
e
s
a
c
ro
ss
m
o
d
e
ls
h
a
v
e
re
m
a
in
e
d
u
n
d
e
r
2
5
0
se
c
o
n
d
s,
re
flec
ti
n
g
m
e
th
o
d
o
lo
g
ica
l
e
fficie
n
c
y
.
Ov
e
ra
ll
,
th
e
se
re
s
u
lt
s
d
e
m
o
n
stra
te
t
h
e
m
o
d
e
l'
s
e
x
c
e
l
len
t
p
e
rfo
rm
a
n
c
e
fo
r
t
h
e
se
m
a
n
ti
c
se
g
m
e
n
tatio
n
tas
k
.
K
ey
w
o
r
d
s
:
Au
g
m
en
tatio
n
E
n
co
d
er
Ph
y
to
p
lan
k
t
o
n
r
ec
o
g
n
itio
n
Sem
an
tic
s
eg
m
en
tatio
n
U
-
Net
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
:
Ov
id
e
Dec
r
o
ly
W
is
n
u
Ar
d
h
i
Do
cto
r
al
o
f
I
n
f
o
r
m
atio
n
Sy
s
te
m
Pro
g
r
am
,
Sch
o
o
l
o
f
Po
s
tg
r
a
d
u
ate
Stu
d
ies,
Un
iv
er
s
itas
Dip
o
n
eg
o
r
o
I
m
am
B
ar
d
jo
SH
St.
No
.
5
,
R
T
.
0
0
2
,
Pleb
u
r
an
,
Sem
ar
an
g
,
I
n
d
o
n
esia
E
m
ail:
o
v
id
e@
s
taf
f
.
u
n
s
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
o
n
esia
is
o
n
e
th
e
m
eg
ad
iv
e
r
s
ity
co
u
n
tr
ies
an
d
co
n
tain
s
p
a
r
t
o
f
‘
th
e
h
ea
r
t
o
f
co
r
al
tr
ian
g
le’
,
wh
ich
is
well
k
n
o
wn
f
o
r
its
h
ig
h
d
iv
er
s
ity
lev
el
o
f
co
r
al
r
ee
f
a
n
d
r
ee
f
f
is
h
s
p
ec
ies,
wh
ich
co
n
s
is
t
s
o
f
m
an
y
en
d
em
ic
s
p
ec
ies
[
1
]
.
Similar
to
co
r
al
r
ee
f
s
an
d
r
ee
f
f
is
h
es,
it
is
ass
u
m
ed
th
at
p
h
y
to
p
lan
k
to
n
co
m
m
u
n
ities
with
in
I
n
d
o
n
esian
m
ar
in
e
ec
o
s
y
s
tem
s
ex
h
ib
it
co
n
s
id
er
ab
ly
h
ig
h
d
iv
er
s
ity
,
with
s
o
m
e
s
p
ec
ies
p
o
ten
tially
en
d
em
i
c.
Alth
o
u
g
h
n
o
ac
cu
r
ate
o
f
f
icial
r
ec
o
r
d
s
ex
is
t,
v
ar
io
u
s
s
tu
d
ies
h
av
e
d
o
cu
m
en
ted
b
etwe
en
1
5
0
to
4
0
0
s
p
ec
ies
o
f
m
ar
in
e
p
h
y
to
p
lan
k
to
n
i
n
I
n
d
o
n
esia,
with
s
o
m
e
s
p
ec
ies
s
u
s
p
ec
ted
to
b
e
en
d
e
m
ic,
n
ew
r
ec
o
r
d
s
,
o
r
n
ew
s
p
ec
ies
[
2
]
–
[
6
]
.
As
a
f
u
n
d
am
en
tal
c
o
m
p
o
n
en
t
o
f
h
ig
h
l
y
p
r
o
d
u
ct
iv
e
tr
o
p
ical
m
ar
i
n
e
ec
o
s
y
s
tem
s
,
p
h
y
to
p
lan
k
to
n
co
m
m
u
n
ities
p
er
f
o
r
m
v
ital
ec
o
lo
g
ical
f
u
n
ctio
n
s
as
th
e
p
r
im
ar
y
p
r
o
d
u
ce
r
s
,
ess
en
tial
lin
k
s
in
en
er
g
y
tr
an
s
f
er
,
an
d
s
tab
ilizer
s
o
f
th
e
b
io
d
i
v
er
s
ity
an
d
en
v
i
r
o
n
m
e
n
tal
b
alan
ce
in
t
h
e
ec
o
s
y
s
tem
[
7
]
–
[
9
]
.
Fu
r
th
er
m
o
r
e,
p
h
y
to
p
la
n
k
to
n
co
m
m
u
n
ities
a
ls
o
d
r
iv
e
th
e
aq
u
atic
b
i
o
g
eo
c
h
em
ical
cy
cles,
wh
ich
in
f
l
u
en
c
e
th
e
en
tire
m
a
r
in
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
1
0
1
3
-
1
0
22
1014
f
o
o
d
web
wh
ile
also
p
r
o
d
u
cin
g
o
x
y
g
e
n
an
d
r
e
g
u
latin
g
th
e
r
eg
io
n
al
an
d
g
lo
b
al
o
ce
an
tem
p
er
atu
r
e.
Du
e
to
th
e
q
u
ick
r
esp
o
n
s
e
o
f
p
h
y
to
p
lan
k
to
n
co
m
m
u
n
ities
to
war
d
s
ch
an
g
es
in
wate
r
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
,
th
ey
ar
e
r
eg
ar
d
e
d
as
ex
ce
ll
en
t b
io
in
d
ic
ato
r
s
an
d
o
f
ten
u
s
ed
as
p
r
o
x
ie
s
f
o
r
ec
o
l
o
g
ical
m
o
n
ito
r
in
g
to
d
etec
t
an
o
m
alies
o
r
d
is
tu
r
b
an
ce
s
,
s
u
ch
as e
u
tr
o
p
h
i
ca
tio
n
o
r
p
o
llu
tio
n
,
with
in
th
e
co
astal e
co
s
y
s
tem
[
7
]
,
[
9
]
–
[
1
1
]
.
I
n
r
ec
en
t
d
ec
ad
es,
aq
u
atic
e
co
lo
g
ical
p
r
o
b
lem
s
,
s
u
ch
as
h
ar
m
f
u
l
alg
al
b
lo
o
m
s
(
HABs
)
,
h
av
e
in
cr
ea
s
ed
in
m
an
y
tr
o
p
ical
co
u
n
tr
ies,
in
clu
d
in
g
I
n
d
o
n
esia
[
1
2
]
,
d
r
i
v
en
b
y
in
c
r
ea
s
ed
h
u
m
a
n
ac
tiv
ity
co
m
b
in
ed
with
th
e
ef
f
ec
t
o
f
clim
ate
ch
a
n
g
e.
T
h
e
c
o
m
b
in
e
d
im
p
ac
t
o
f
clim
ate
ch
an
g
e
an
d
a
n
th
r
o
p
o
g
en
ic
ac
tiv
ities
h
av
e
ch
an
g
ed
th
e
e
n
v
ir
o
n
m
en
tal
c
o
n
d
itio
n
s
,
p
r
o
v
id
e
d
m
o
r
e
co
m
p
etitiv
e
ad
v
an
tag
es,
p
r
o
m
o
t
ed
to
x
in
p
r
o
d
u
ce
r
s
,
an
d
in
cr
ea
s
ed
s
o
m
e
HAB
s
p
e
cies
'
b
io
m
ass
p
r
o
d
u
ctio
n
[
1
3
]
,
[
1
4
]
.
Fro
m
2
0
0
5
to
2
0
2
1
,
at
least
5
8
d
if
f
er
en
t
s
tu
d
ies
h
av
e
r
ep
o
r
ted
ca
s
es
o
f
HABs
in
o
th
er
co
astal
ar
ea
s
in
I
n
d
o
n
esia,
s
u
ch
as
L
am
p
u
n
g
B
ay
,
J
ak
ar
ta
B
ay
,
an
d
Am
b
o
n
B
ay
[
1
4
]
.
Ne
g
ativ
e
im
p
ac
ts
,
in
clu
d
in
g
m
ass
f
is
h
m
o
r
tality
an
d
f
atal
p
ar
al
y
tic
s
h
ellf
is
h
p
o
is
o
n
in
g
(
PS
P)
d
is
ea
s
e
in
h
u
m
an
s
,
h
av
e
b
ee
n
r
ep
o
r
ted
f
r
o
m
m
an
y
HAB
-
af
f
ec
ted
ar
ea
s
,
p
ar
ticu
la
r
ly
in
C
ir
eb
o
n
[
1
4
]
.
Giv
en
th
at,
at
least 2
0
0
o
u
t o
f
th
e
5
,
0
0
0
k
n
o
wn
p
h
y
to
p
lan
k
to
n
s
p
ec
ies p
r
o
d
u
ce
to
x
in
s
h
ar
m
f
u
l to
h
u
m
an
s
[
1
4
]
an
d
at
least
1
0
o
u
t
o
f
1
7
m
o
s
t c
o
m
m
o
n
HABs
ca
u
s
ativ
e
s
p
ec
ies
in
I
n
d
o
n
esia
wer
e
to
x
in
p
r
o
d
u
ce
r
s
[
1
4
]
,
r
ap
id
an
d
ac
cu
r
ate
g
en
u
s
o
r
s
p
ec
ies lev
el
id
en
tific
a
tio
n
h
av
e
b
ec
o
m
e
ess
en
tial to
id
en
tify
an
d
m
itig
ate
th
e
ef
f
ec
ts
o
f
th
eir
b
lo
o
m
s
o
n
m
ar
i
n
e
ec
o
s
y
s
tem
s
an
d
co
astal c
o
m
m
u
n
ities
.
So
f
ar
,
lig
h
t
m
icr
o
s
co
p
y
co
n
t
in
u
es
to
b
e
th
e
p
r
ef
er
r
ed
m
eth
o
d
f
o
r
p
h
y
to
p
lan
k
to
n
i
d
en
tif
icatio
n
in
I
n
d
o
n
esia
d
esp
ite
its
lab
o
r
-
i
n
te
n
s
iv
e
n
atu
r
e
,
s
u
s
ce
p
tib
ilit
y
to
er
r
o
r
s
,
a
n
d
lim
itatio
n
s
im
p
o
s
ed
b
y
h
u
m
an
p
h
y
s
io
lo
g
ical
an
d
p
s
y
ch
o
lo
g
ical
f
ac
to
r
s
[
1
4
]
.
Misid
en
tif
icatio
n
is
a
co
m
m
o
n
is
s
u
e,
o
f
ten
d
u
e
to
th
e
m
o
r
p
h
o
lo
g
ical
s
im
ilar
ities
b
etwe
en
d
if
f
er
e
n
t
p
lan
k
to
n
s
p
ec
ies
[
1
4
]
.
Ho
wev
er
,
m
ac
h
in
e
lear
n
in
g
(
ML
)
m
eth
o
d
s
u
s
in
g
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
h
av
e
b
ee
n
u
s
ed
an
d
s
h
o
wn
ex
ce
ll
en
t
p
er
f
o
r
m
an
ce
in
id
en
tify
in
g
v
ar
io
u
s
p
h
y
t
o
p
lan
k
to
n
s
p
ec
ies
in
r
ec
e
n
t
y
ea
r
s
[
1
5
]
.
I
n
p
h
y
t
o
p
lan
k
t
o
n
r
esear
ch
,
th
e
s
u
b
s
tan
tial
v
ar
iab
ilit
y
in
im
ag
e
s
izes
an
d
q
u
ality
p
o
s
es
a
s
ig
n
if
ican
t
c
h
allen
g
e
f
o
r
co
n
v
en
tio
n
al
C
NN
-
b
ased
class
if
ier
s
,
wh
ic
h
ty
p
ically
r
e
q
u
ir
e
u
n
if
o
r
m
-
s
ized
in
p
u
t
im
ag
es
[
1
6
]
.
T
h
is
n
ec
ess
ity
f
o
r
r
esizin
g
,
a
p
r
o
ce
s
s
t
h
at
eith
e
r
d
is
r
eg
ar
d
s
[
1
7
]
,
[
1
8
]
o
r
p
r
eser
v
es
th
e
im
ag
e'
s
asp
ec
t
r
atio
[
8
]
,
[
1
9
]
,
[
2
0
]
,
co
m
es
with
its
s
et
o
f
ad
v
a
n
tag
es
an
d
d
is
ad
v
an
tag
es.
W
h
ile
ig
n
o
r
in
g
th
e
asp
ec
t
r
atio
ca
n
d
is
to
r
t
im
ag
es
an
d
p
o
ten
tially
af
f
ec
t f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
lear
n
in
g
o
u
tco
m
es,
p
r
eser
v
in
g
it,
esp
ec
ially
wh
en
alig
n
i
n
g
with
th
e
im
ag
e'
s
b
ac
k
g
r
o
u
n
d
co
lo
r
,
h
as
p
r
o
d
u
ce
d
o
p
tim
al
r
esu
lts
o
n
im
ag
in
g
Flo
wC
y
to
b
o
t (
I
FC
B
)
d
ata
[
2
1
]
.
Ho
wev
er
,
r
esizin
g
in
ev
itab
ly
l
ea
d
s
to
s
o
m
e
lo
s
s
o
f
d
etail
an
d
in
f
o
r
m
atio
n
,
esp
e
cially
co
n
ce
r
n
i
n
g
p
h
y
to
p
lan
k
to
n
s
ize.
T
h
is
is
s
u
e
is
s
o
m
ewh
at
m
itig
ated
b
y
in
clu
d
in
g
im
ag
e
s
ize
in
f
o
r
m
at
io
n
as
m
etad
ata
[2
2]
.
Mo
r
e
o
v
er
,
th
e
v
ar
iab
ilit
y
in
im
a
g
e
q
u
ality
with
in
th
ese
d
atasets
n
ec
es
s
itates
em
p
lo
y
in
g
v
ar
io
u
s
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
to
en
h
an
ce
class
if
icatio
n
ac
cu
r
ac
y
[
1
6
]
.
Stra
teg
ies
s
u
ch
as
d
is
ca
r
d
in
g
lo
w
-
q
u
ality
im
ag
es
[
2
3
]
,
s
eg
m
en
tatio
n
[
2
4
]
,
a
n
d
d
e
n
o
is
in
g
[
2
5
]
,
alo
n
g
with
ad
v
an
ce
m
e
n
ts
lik
e
C
NN
-
b
as
ed
s
u
p
er
-
r
eso
lu
tio
n
tech
n
i
q
u
e
s
,
h
av
e
b
ee
n
p
r
o
p
o
s
ed
to
r
e
f
in
e
im
ag
e
q
u
ality
,
th
o
u
g
h
th
e
ef
f
ec
tiv
e
n
ess
o
f
th
ese
ap
p
r
o
ac
h
es
i
n
im
p
r
o
v
in
g
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
war
r
an
ts
f
u
r
th
er
in
v
esti
g
atio
n
[
2
6
]
.
T
h
e
U
-
Net
a
r
ch
itectu
r
e,
wh
ic
h
em
p
h
asizes
en
co
d
er
-
d
ec
o
d
e
r
m
eth
o
d
s
,
r
ep
r
esen
ts
n
o
tab
le
p
r
o
g
r
e
s
s
in
ad
d
r
ess
in
g
s
em
an
tic
s
eg
m
en
ta
tio
n
d
if
f
icu
lties
[
2
7
]
.
T
h
e
o
b
je
ctiv
e
o
f
th
is
d
esig
n
is
to
r
ed
u
c
e
n
o
is
e
at
d
if
f
e
r
en
t
s
ca
les
in
o
r
d
er
to
en
h
a
n
ce
p
e
r
f
o
r
m
an
ce
b
y
em
p
lo
y
in
g
a
co
m
p
r
eh
en
s
iv
e
r
ef
in
in
g
m
eth
o
d
o
lo
g
y
[
2
8
]
.
A
n
o
v
el
m
eth
o
d
o
l
o
g
y
h
as
b
ee
n
d
ev
elo
p
ed
th
at
co
m
b
in
es
co
n
v
en
ti
o
n
al
n
eu
r
al
d
if
f
er
en
tial
eq
u
atio
n
s
with
th
e
s
tr
u
ctu
r
al
f
r
am
ewo
r
k
o
f
U
-
Net
to
d
elin
e
ate
ce
ll
r
eg
i
o
n
s
ac
cu
r
ately
[
2
9
]
.
T
h
e
u
s
e
o
f
U
-
Net
in
m
icr
o
s
co
p
ic
s
eg
m
e
n
tatio
n
is
v
er
y
ef
f
ec
tiv
e,
s
o
it
h
as
b
e
en
p
u
t
to
g
eth
er
i
n
d
if
f
e
r
en
t
w
ay
s
to
g
et
b
etter
r
esu
lts
[
3
0
]
.
T
h
e
p
u
r
p
o
s
e
o
f
th
e
en
v
ir
o
n
m
en
tal
m
icr
o
o
r
g
an
is
m
d
ata
s
et
f
if
th
v
er
s
io
n
(
E
MD
S
-
5
)
d
ataset
is
to
ev
alu
ate
an
d
co
m
p
ar
e
th
e
U
-
Net
m
eth
o
d
f
o
r
d
iv
id
in
g
n
u
m
er
o
u
s
o
b
jects
in
im
a
g
es
[
3
1
]
.
A
s
an
alter
n
ativ
e,
th
e
lo
w
-
c
o
s
t
U
-
Net
(
L
C
U)
was
cr
ea
ted
,
wh
ich
b
u
ild
s
o
n
th
e
b
asic
U
-
Net
m
o
d
el
to
m
ak
e
it
ea
s
ier
to
s
ep
ar
ate
im
ag
es
o
f
m
icr
o
o
r
g
an
is
m
s
th
at
liv
e
in
th
e
en
v
ir
o
n
m
en
t
wh
il
e
also
tr
y
in
g
to
u
s
e
as
litt
le
m
em
o
r
y
as
p
o
s
s
ib
le
[
3
2
]
.
Ac
co
r
d
in
g
to
p
r
ev
io
u
s
r
esear
ch
,
th
e
U
-
Net+
+
v
ar
iati
o
n
wo
r
k
s
b
etter
th
an
r
eg
u
la
r
p
atch
-
lev
el
s
eg
m
e
n
tatio
n
m
eth
o
d
s
th
at
u
s
e
v
is
u
al
tr
an
s
f
o
r
m
er
s
to
g
et
ac
cu
r
ate
d
ata
o
n
m
icr
o
o
r
g
a
n
is
m
s
in
th
e
en
v
ir
o
n
m
en
t a
t th
e
p
ix
el
lev
el
[
3
3
]
.
Pre
v
io
u
s
r
esear
ch
f
o
c
u
s
ed
o
n
m
o
d
if
y
in
g
th
e
U
-
Net
ar
ch
ite
ctu
r
e
f
o
r
s
em
an
tic
s
eg
m
en
tati
o
n
b
u
t
d
i
d
n
o
t
ex
p
licitly
d
is
cu
s
s
th
e
in
f
lu
en
ce
o
f
th
e
e
n
co
d
e
r
o
n
t
h
e
U
-
Net
ar
ch
itectu
r
e
an
d
i
m
ag
e
au
g
m
e
n
tatio
n
tech
n
iq
u
es.
T
h
is
p
ap
e
r
p
r
o
p
o
s
es
an
im
p
r
o
v
em
en
t
o
f
th
e
U
-
Net
ar
ch
itectu
r
e,
s
ev
er
al
e
n
co
d
er
a
n
d
d
ec
o
d
er
n
etwo
r
k
s
h
av
e
b
ee
n
in
teg
r
ate
d
with
th
e
U
-
Net.
Var
io
u
s
i
m
ag
e
au
g
m
en
tatio
n
ap
p
r
o
ac
h
es
ar
e
im
p
lem
en
ted
,
s
u
ch
as
g
eo
m
etr
ic,
d
is
to
r
tio
n
,
co
lo
r
,
an
d
b
lu
r
tr
an
s
f
o
r
m
atio
n
ty
p
es,
to
elev
ate
th
e
alg
o
r
ith
m
's
r
eliab
ili
ty
.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
o
f
t
h
is
s
tu
d
y
i
s
to
ass
ess
th
e
in
teg
r
atio
n
o
f
th
e
en
c
o
d
er
with
in
th
e
U
-
Net
ar
ch
itectu
r
e
f
o
r
s
em
an
tic
s
eg
m
en
tatio
n
o
f
tr
an
s
p
ar
en
t
p
h
y
t
o
p
lan
k
t
o
n
im
ag
es.
Ad
d
itio
n
ally
,
th
e
r
esear
ch
ex
p
lo
r
es
d
if
f
er
en
t
s
tr
ateg
ies
f
o
r
en
h
an
cin
g
th
e
i
m
ag
es.
T
h
e
p
u
r
p
o
s
e
o
f
t
h
is
s
tu
d
y
is
t
o
s
h
o
wc
ase
th
e
r
em
a
r
k
ab
le
ca
p
ab
ilit
y
o
f
U
-
Net
in
d
etec
tin
g
a
n
d
u
tili
zin
g
f
ea
tu
r
es
f
r
o
m
im
ag
es
th
at
ex
h
ib
it
s
u
b
s
tan
tial
v
ar
iatio
n
s
in
ter
m
s
o
f
s
ize,
s
h
ap
e
,
an
d
clar
ity
.
Mo
r
eo
v
e
r
,
it
d
o
es
a
co
m
p
ar
ativ
e
a
n
aly
s
is
o
f
th
e
co
llab
o
r
atio
n
b
etwe
en
th
e
en
co
d
er
an
d
d
ec
o
d
er
u
s
in
g
v
ar
io
u
s
au
g
m
e
n
tatio
n
tech
n
iq
u
es,
th
er
eb
y
f
ac
ilit
a
tin
g
th
e
im
p
lem
en
tatio
n
o
f
en
s
em
b
le
lear
n
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
n
h
a
n
ce
d
U
-
N
et
mo
d
els w
ith
en
co
d
er a
n
d
a
u
g
men
ta
tio
n
fo
r
p
h
yto
p
l
a
n
kto
n
…
(
Ovid
e
Dec
r
o
ly
Wis
n
u
A
r
d
h
i
)
1015
m
eth
o
d
o
l
o
g
ies.
T
h
e
co
m
p
ar
is
o
n
ab
o
v
e
n
o
t
o
n
ly
u
n
d
e
r
s
co
r
es
th
e
v
er
s
atility
o
f
U
-
Net
in
ter
m
s
o
f
v
a
r
io
u
s
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
b
u
t a
ls
o
its
ab
ilit
y
to
en
h
an
c
e
th
e
r
o
b
u
s
tn
ess
an
d
p
r
ec
is
io
n
o
f
s
eg
m
en
tatio
n
o
u
tc
o
m
es.
2.
M
E
T
H
O
D
T
h
e
p
r
esen
t
s
tu
d
y
in
v
o
lv
ed
t
h
e
d
ev
elo
p
m
en
t
o
f
a
s
eg
m
e
n
tatio
n
m
o
d
el
f
o
r
tr
an
s
p
ar
e
n
t
im
ag
es
o
f
p
h
y
to
p
la
n
k
to
n
.
T
h
e
U
-
Net
ar
ch
itectu
r
e
was
em
p
lo
y
ed
in
s
i
d
e
a
r
esear
ch
wo
r
k
f
lo
w,
as
d
ep
icted
in
Fig
u
r
e
1
.
T
h
is
s
tu
d
y
h
as
th
r
ee
p
r
im
ar
y
p
h
ases
:
p
r
ep
a
r
atio
n
,
p
r
o
ce
s
s
in
g
,
a
n
d
m
o
d
el
im
p
lem
en
tatio
n
.
Du
r
in
g
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e,
th
e
im
ag
e
was
an
n
o
tated
with
s
p
ec
ies
n
am
es,
an
d
s
u
b
s
eq
u
en
tly
,
th
e
i
m
ag
e
was
r
esized
to
d
im
en
s
io
n
s
o
f
2
2
4
×
2
2
4
p
i
x
els.
Su
b
s
eq
u
en
tly
,
s
ev
er
al
au
g
m
en
tatio
n
tech
n
iq
u
es
ar
e
em
p
lo
y
ed
to
g
e
n
er
ate
s
u
p
p
lem
en
tar
y
p
h
o
to
s
.
T
h
e
tr
ea
ted
im
ag
es
ar
e
p
ar
titi
o
n
ed
i
n
to
s
ev
er
al
d
atasets
f
o
r
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
in
g
p
u
r
p
o
s
es.
T
h
is
s
tag
e
is
co
m
m
o
n
l
y
r
ef
e
r
r
ed
t
o
as
p
r
o
ce
s
s
in
g
.
T
h
e
u
tili
za
tio
n
o
f
d
ata
s
ep
a
r
atio
n
f
ac
ilit
ates
th
e
p
r
o
ce
s
s
o
f
tr
ain
in
g
,
v
alid
atin
g
,
an
d
test
in
g
f
o
u
r
d
is
tin
ct
U
-
Net
a
r
ch
itectu
r
e
s
.
T
h
ese
n
etwo
r
k
s
in
clu
d
e
s
ev
er
al
e
n
co
d
e
r
s
an
d
ar
e
tr
ain
ed
u
s
in
g
im
a
g
es
o
b
ta
in
ed
f
r
o
m
v
ar
io
u
s
a
u
g
m
en
tati
o
n
tech
n
iq
u
es.
T
h
e
f
in
al
s
tag
e
is
ass
es
s
in
g
an
d
co
n
tr
asti
n
g
th
e
ef
f
icac
y
o
f
all
t
h
e
m
o
d
els g
en
e
r
ated
.
Fig
u
r
e
1
.
R
esear
ch
wo
r
k
f
lo
w
o
f
p
h
y
to
p
lan
k
to
n
s
em
a
n
tic
s
eg
m
en
tatio
n
2
.
1
.
E
x
perim
ent
env
iro
n
m
e
nt
T
h
e
m
o
d
el
was
b
u
ilt
an
d
u
tili
ze
d
with
Py
T
o
r
ch
,
a
wid
ely
u
s
ed
m
ac
h
in
e
lear
n
i
n
g
f
r
a
m
ewo
r
k
an
d
p
r
o
g
r
a
m
m
in
g
lan
g
u
ag
e
Py
th
o
n
3
+.
Ou
r
e
x
p
er
im
en
tal
s
etu
p
was
ca
r
r
ied
o
u
t
o
n
Go
o
g
le
C
o
lab
Pro
+,
wh
ich
o
f
f
er
ed
v
ar
y
in
g
GPU
s
p
ec
if
ic
atio
n
s
,
s
u
ch
as
K8
0
,
T
4
,
P1
0
0
,
an
d
5
2
GB
o
f
R
AM
.
T
h
is
r
e
s
ea
r
ch
u
tili
ze
s
h
ig
h
-
r
eso
lu
tio
n
m
icr
o
s
co
p
y
HAB
s
d
ata
f
r
o
m
th
e
p
h
y
to
p
la
n
k
to
n
im
ag
e
d
atab
ase
(
cPI
D
)
,
h
o
u
s
ed
at
th
e
Oce
an
o
g
r
ap
h
ic
R
esear
ch
C
en
t
er
,
Natio
n
al
R
esear
ch
a
n
d
I
n
n
o
v
atio
n
A
g
en
cy
(
R
C
O
-
B
R
I
N)
[
2
]
.
T
h
e
d
ata
u
s
ed
in
th
is
s
tu
d
y
wer
e
co
llected
d
u
r
i
n
g
a
r
esear
ch
ex
p
e
d
itio
n
s
p
an
n
i
n
g
f
r
o
m
2
0
1
1
to
2
0
1
9
,
en
co
m
p
ass
in
g
1
8
lo
ca
tio
n
s
in
I
n
d
o
n
esian
wat
er
s
.
2
.
2
.
Da
t
a
prepro
ce
s
s
ing
a
nd
a
ug
m
ent
a
t
io
n
Fo
r
th
is
wo
r
k
,
we
u
tili
ze
d
th
e
L
ab
elM
e
ap
p
licatio
n
[
3
4
]
to
an
n
o
tate
im
ag
es
f
r
o
m
th
e
d
ata
b
ase.
T
h
is
s
tu
d
y
p
ar
titi
o
n
s
th
e
d
ata
in
a
7
0
:2
0
:1
0
%
r
atio
an
d
em
p
lo
y
s
v
ar
io
u
s
d
ata
au
g
m
en
tatio
n
te
ch
n
iq
u
es
to
ad
d
r
ess
d
ata
s
ca
r
city
.
T
h
e
Alb
u
m
en
t
atio
n
s
lib
r
ar
y
in
Py
to
r
ch
,
k
n
o
wn
f
o
r
its
ef
f
icien
cy
in
im
ag
e
tr
an
s
f
o
r
m
atio
n
,
s
u
p
p
o
r
ts
th
is
p
r
o
ce
s
s
[
3
5
]
.
T
ab
le
1
lis
ts
th
e
au
g
m
en
tatio
n
ty
p
es
u
s
ed
to
e
n
r
ich
th
e
i
m
ag
e
d
ataset
[
3
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
1
0
1
3
-
1
0
22
1016
Au
g
m
en
tatio
n
tec
h
n
iq
u
es
ar
e
ty
p
ically
ca
teg
o
r
ize
d
in
to
f
o
u
r
g
r
o
u
p
s
:
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
,
d
is
to
r
tio
n
tr
an
s
f
o
r
m
atio
n
,
co
lo
r
tr
a
n
s
f
o
r
m
atio
n
,
an
d
b
lu
r
a
n
d
s
m
o
o
t
h
in
g
.
Geo
m
etr
ic
tr
a
n
s
f
o
r
m
atio
n
s
,
s
u
ch
as
s
h
if
t
s
ca
le
r
o
tat
io
n
,
a
r
e
u
tili
ze
d
to
ch
a
n
g
e
im
ag
es
th
r
o
u
g
h
ac
tio
n
s
s
u
c
h
as
m
o
v
em
en
t,
zo
o
m
i
n
g
,
a
n
d
s
p
in
n
in
g
.
On
th
e
o
th
er
h
an
d
,
r
an
d
o
m
r
o
tat
io
n
i
s
em
p
lo
y
ed
to
r
o
tate
im
ag
es
at
in
ter
v
als
o
f
9
0
°
.
T
h
e
im
ag
es
ar
e
f
lip
p
ed
u
s
in
g
p
r
o
b
a
b
ilit
ies
in
th
e
v
er
tical
f
lip
an
d
h
o
r
izo
n
tal
f
lip
f
u
n
ctio
n
s
.
Dif
f
er
en
t
d
is
to
r
tio
n
tr
an
s
f
o
r
m
atio
n
s
,
s
u
ch
as
o
p
tical
d
is
to
r
tio
n
,
g
r
id
d
is
to
r
t
io
n
,
an
d
elastic
tr
an
s
f
o
r
m
,
ar
e
em
p
lo
y
ed
to
in
tr
o
d
u
ce
a
r
a
n
g
e
o
f
o
p
tical
an
d
wav
e
-
lik
e
d
is
to
r
tio
n
s
.
R
an
d
o
m
b
r
ig
h
tn
ess
an
d
c
o
lo
r
jitt
er
a
r
e
u
tili
ze
d
to
r
an
d
o
m
ly
m
o
d
if
y
th
e
b
r
ig
h
tn
ess
an
d
v
ar
io
u
s
o
th
er
attr
ib
u
tes
o
f
co
lo
r
s
.
T
h
e
ap
p
licatio
n
o
f
a
b
l
u
r
r
in
g
ef
f
ec
t
to
im
ag
es
f
ac
ilit
ates
th
e
p
r
o
ce
s
s
o
f
au
g
m
en
tatio
n
.
T
ab
le
1
.
Au
g
m
en
tatio
n
tec
h
n
i
q
u
es
G
e
o
me
t
r
i
c
t
r
a
n
sf
o
r
ms
D
i
st
o
r
t
i
o
n
t
r
a
n
sf
o
r
ms
C
o
l
o
r
t
r
a
n
sf
o
r
ms
B
l
u
r
a
n
d
sm
o
o
t
h
i
n
g
S
h
i
f
t
sc
a
l
e
r
o
t
a
t
e
O
p
t
i
c
a
l
d
i
s
t
o
r
t
i
o
n
R
a
n
d
o
m
b
r
i
g
h
t
n
e
ss
B
l
u
r
R
a
n
d
o
m
r
o
t
a
t
e
G
r
i
d
d
i
s
t
o
r
t
i
o
n
C
o
l
o
r
j
i
t
t
e
r
V
e
r
t
i
c
a
l
f
l
i
p
El
a
s
t
i
c
t
r
a
n
sf
o
r
m
H
u
e
s
a
t
u
r
a
t
i
o
n
H
o
r
i
z
o
n
t
a
l
f
l
i
p
2
.
3
.
M
o
del a
rc
hite
ct
ures
T
o
im
p
r
o
v
e
s
eg
m
e
n
tatio
n
p
er
f
o
r
m
an
ce
,
th
is
s
tu
d
y
em
p
lo
y
s
t
r
an
s
f
er
lear
n
i
n
g
with
e
n
co
d
e
r
s
th
at
h
av
e
b
ee
n
p
r
e
-
tr
ain
ed
,
a
m
eth
o
d
p
r
o
v
en
to
e
n
h
an
ce
m
o
d
el
p
er
f
o
r
m
an
ce
[
3
7
]
.
T
h
is
ex
p
er
im
en
t
u
s
es
en
co
d
er
s
f
r
o
m
th
e
R
esNet5
0
,
R
e
s
NeX
t,
Mo
b
ileNetV2
,
an
d
E
f
f
icien
tNet
V2
B
5
ar
ch
itectu
r
es.
T
h
is
s
tu
d
y
u
tili
ze
s
ad
v
an
ce
d
d
ee
p
-
lear
n
i
n
g
m
o
d
els
f
o
r
im
a
g
e
an
aly
s
is
.
R
esNet,
a
s
ig
n
if
ican
t
ad
v
an
ce
m
en
t
o
v
er
Alex
Net
an
d
VGGN
et,
u
s
es
a
r
esid
u
al
lay
er
a
n
d
g
lo
b
al
av
er
ag
e
p
o
o
lin
g
t
o
p
r
o
ce
s
s
2
2
4
×2
2
4
-
p
ix
el
im
a
g
es
ef
f
i
cien
tly
.
R
esNeXt,
ex
ten
d
in
g
R
esNet,
in
tr
o
d
u
ce
s
"c
ar
d
in
ality
"
with
m
u
ltip
le
tr
a
n
s
f
o
r
m
atio
n
p
ath
s
,
b
alan
cin
g
l
ea
r
n
in
g
a
b
ilit
y
an
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
[
3
8
]
.
Mo
b
ileNetV2
,
an
ar
ch
itectu
r
e
d
esig
n
ed
s
p
ec
if
ically
f
o
r
m
o
b
ile
an
d
em
b
ed
d
ed
ap
p
licatio
n
s
,
in
co
r
p
o
r
ates
d
e
p
th
wis
e
s
ep
ar
ab
le
co
n
v
o
lu
tio
n
s
ac
r
o
s
s
its
5
4
lay
er
s
[
3
9
]
.
E
f
f
icien
tNet
s
ca
les
m
o
d
el
d
im
e
n
s
io
n
s
u
s
in
g
a
co
m
p
o
u
n
d
v
a
r
iab
le
an
d
m
o
b
ile
i
n
v
er
ted
b
o
ttlen
ec
k
c
o
n
v
o
lu
tio
n
(
MBC
o
n
v
)
b
lo
c
k
s
,
ac
h
iev
in
g
o
p
tim
al
p
er
f
o
r
m
an
ce
o
n
th
e
I
m
a
g
eNe
t
d
ataset
with
its
co
m
p
ac
t
an
d
f
ast
-
co
n
v
er
g
in
g
a
r
ch
i
tectu
r
e
[
4
0
]
.
2
.
4
.
T
ra
ini
ng
a
nd
e
v
a
lua
t
io
n
Ou
r
r
esear
ch
u
s
ed
a
7
0
:
2
0
:1
0
%
d
ata
s
p
lit
r
atio
to
d
e
v
elo
p
a
n
d
ex
te
n
s
iv
ely
an
al
y
ze
th
e
o
p
t
im
al
C
N
N
m
o
d
el.
T
h
r
o
u
g
h
o
u
t
th
e
tr
ain
in
g
p
h
ase,
im
ag
es
wer
e
g
r
o
u
p
ed
in
to
'
m
in
i
b
atch
es'
o
f
1
6
d
u
e
to
m
em
o
r
y
co
n
s
tr
ain
ts
.
W
e
em
p
lo
y
ed
a
n
Ad
am
o
p
tim
izer
f
o
r
o
p
ti
m
izatio
n
,
ad
ju
s
tin
g
C
NN
p
a
r
am
eter
s
with
a
0
.
9
m
o
m
en
tu
m
[
4
1
]
an
d
a
lear
n
in
g
r
ate
o
f
0
.
0
0
0
1
[
4
2
]
.
L
2
r
eg
u
lar
izatio
n
with
a
f
ac
to
r
o
f
0
.
0
0
0
1
was
ap
p
lied
t
o
m
itig
ate
o
v
er
f
itti
n
g
[
4
3
]
.
T
h
is
s
tu
d
y
em
p
lo
y
ed
th
e
Ad
am
o
p
t
im
izer
,
ch
o
s
en
f
o
r
its
d
em
o
n
s
tr
ated
ef
f
ec
tiv
e
n
ess
in
p
r
ac
tical
s
ce
n
ar
io
s
as
d
o
c
u
m
en
ted
i
n
p
r
i
o
r
r
esear
c
h
[
4
4
]
.
Fo
llo
win
g
ea
ch
tr
ai
n
in
g
ep
o
ch
,
t
h
e
m
o
d
el's
ad
v
an
ce
m
e
n
t
was
ev
alu
ated
u
s
in
g
th
e
v
alid
atio
n
s
et.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
wo
u
ld
ter
m
in
ate
if
n
o
im
p
r
o
v
em
e
n
ts
wer
e
o
b
s
er
v
ed
o
v
er
t
h
e
last
f
iv
e
ep
o
ch
s
o
r
u
p
o
n
r
ea
ch
in
g
5
0
to
tal
ep
o
ch
s
.
T
h
e
tr
ain
in
g
s
et
u
n
d
er
wen
t
s
h
u
f
f
lin
g
at
th
e
b
eg
in
n
in
g
o
f
ea
c
h
ep
o
c
h
to
i
n
ject
d
iv
er
s
ity
.
T
o
e
v
alu
ate
t
h
e
p
er
f
o
r
m
an
ce
o
f
d
if
f
er
en
t
m
o
d
els,
we
u
s
e
a
r
an
g
e
o
f
m
etr
ics
to
e
x
am
in
e
th
e
s
eg
m
en
tatio
n
r
esu
lts
in
o
u
r
s
tu
d
y
.
O
u
r
ass
ess
m
en
t
in
co
r
p
o
r
ates
th
e
Dice
co
ef
f
icien
t
[
4
5
]
,
J
ac
ca
r
d
in
d
ex
(
also
k
n
o
wn
as
in
ter
s
ec
tio
n
o
v
e
r
u
n
io
n
o
r
I
o
U)
,
p
i
x
el
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
[
4
6
]
,
r
ep
r
esen
te
d
b
y
(
1
)
-
(
5
)
.
=
2
×
(
2
×
)
+
+
(
1
)
=
∑
(
)
=
1
(
2)
=
(
3
)
=
+
(
4
)
=
+
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
n
h
a
n
ce
d
U
-
N
et
mo
d
els w
ith
en
co
d
er a
n
d
a
u
g
men
ta
tio
n
fo
r
p
h
yto
p
l
a
n
kto
n
…
(
Ovid
e
Dec
r
o
ly
Wis
n
u
A
r
d
h
i
)
1017
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
p
r
esen
ts
an
an
aly
s
i
s
o
f
t
h
e
p
er
f
o
r
m
an
ce
o
f
v
a
r
io
u
s
m
o
d
els
i
n
r
ec
o
g
n
izin
g
p
h
y
t
o
p
lan
k
to
n
im
ag
es,
with
a
f
o
cu
s
o
n
s
em
an
tic
s
eg
m
en
tin
g
p
h
y
to
p
lan
k
t
o
n
.
T
h
e
r
esear
c
h
in
c
o
r
p
o
r
ate
s
th
e
U
-
Net
m
o
d
el
co
m
b
in
ed
with
f
o
u
r
d
is
tin
ct
en
co
d
er
s
:
E
f
f
icien
tNet
-
B5
,
Mo
b
ile
N
etV2
,
R
es
N
et5
0
,
an
d
R
es
N
e
X
t5
0
.
T
h
e
ev
alu
atio
n
em
p
l
o
y
s
s
e
v
er
al
m
etr
ics,
s
u
ch
as
Dice
,
J
ac
ca
r
d
,
p
r
ec
is
io
n
av
er
ag
e
(
PA)
,
p
r
ec
i
s
io
n
(
P),
an
d
r
ec
all
(
R
)
,
to
g
au
g
e
th
e
m
o
d
els'
ef
f
ec
tiv
en
ess
o
n
b
o
th
tr
ain
in
g
a
n
d
test
d
atasets
.
W
e
f
o
u
n
d
th
at
th
e
U
-
Net
Mo
b
ileNetV2
m
o
d
el,
ap
p
ly
in
g
o
p
tical
d
is
to
r
tio
n
tr
an
s
f
o
r
m
atio
n
,
ac
h
ie
v
e
d
th
e
h
ig
h
est
s
co
r
es
o
n
th
e
test
s
et
f
o
r
ea
ch
ev
alu
atio
n
m
etr
ic:
a
Dice
s
co
r
e
o
f
9
3
.
6
9
%,
a
J
ac
ca
r
d
(
I
o
U
)
s
co
r
e
o
f
8
8
.
1
4
%,
p
r
ec
is
io
n
at
9
9
.
8
9
%,
an
d
r
ec
all
at
1
0
0
%.
T
h
i
s
p
er
f
o
r
m
a
n
ce
m
ar
k
s
a
s
ig
n
if
ican
t
ad
v
an
ce
m
e
n
t
co
m
p
ar
ed
to
t
h
e
tr
ain
in
g
s
et
s
co
r
es.
Oth
er
m
o
d
els,
in
cl
u
d
in
g
U
-
Net+
R
es
N
et5
0
an
d
U
-
Net
+
R
es
N
e
X
t5
0
,
also
d
em
o
n
s
tr
ated
c
o
m
m
en
d
ab
le
p
er
f
o
r
m
an
ce
s
(
T
a
b
le
2
)
.
Ho
wev
er
,
th
e
U
-
Net
M
o
b
ileNe
tV2
m
o
d
el
n
o
tab
ly
ex
ce
lled
in
all
ass
es
s
ed
m
etr
ics
(
T
ab
le
2
)
.
T
h
e
co
m
p
lete
to
p
f
iv
e
m
o
d
els'
p
er
f
o
r
m
an
ce
m
etr
ics
f
o
r
te
s
t
Dice
,
I
o
U
,
p
r
ec
is
io
n
,
an
d
r
ec
all
ar
e
d
is
p
lay
ed
in
T
a
b
le
2
.
Ou
r
f
in
d
in
g
s
s
h
o
w
th
at
U
-
Net
Mo
b
ileNetV2
with
o
p
ti
ca
l
d
is
to
r
tio
n
ex
ce
ls
in
p
h
y
to
p
lan
k
to
n
s
eg
m
en
tatio
n
.
Fig
u
r
e
2
s
h
o
ws
th
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
o
f
p
r
ec
is
io
n
,
r
ec
all,
Dice
v
alu
e,
I
o
U
,
p
ix
el
ac
cu
r
ac
y
,
an
d
tim
e.
As
s
h
o
wn
b
y
th
e
ef
f
ec
tiv
en
ess
o
f
p
r
ec
is
io
n
an
d
r
ec
all
(
Fig
u
r
e
2
(
a)
an
d
(
b
)
)
.
I
n
co
n
tr
ast,
th
e
U
-
Net
R
esNet5
0
m
o
d
el
with
m
ix
tr
an
s
f
o
r
m
co
n
s
is
ten
tly
d
em
o
n
s
tr
ated
h
ig
h
Dice
s
co
r
es,
o
u
tp
er
f
o
r
m
in
g
Mo
b
ileNetV2
m
o
d
els,
wh
ich
s
h
o
wed
m
o
r
e
s
ig
n
if
ica
n
t
s
co
r
e
v
ar
iab
ilit
y
,
in
d
icatin
g
o
v
e
r
f
i
ttin
g
r
is
k
s
(
Fig
u
r
e
2
(
b
)
)
.
Fig
u
r
e
2
(
c
)
h
i
g
h
lig
h
ts
th
e
U
-
Net
R
esNet5
0
m
o
d
el'
s
co
n
s
is
ten
tly
h
ig
h
I
o
U
p
er
f
o
r
m
an
ce
,
co
n
t
r
asti
n
g
with
th
e
v
ar
iab
ilit
y
s
ee
n
in
m
o
d
els
u
s
in
g
elastic
tr
an
s
f
o
r
m
an
d
g
r
id
d
is
to
r
tio
n
.
Fig
u
r
e
2
(
d
)
r
ev
ea
ls
R
e
s
Net5
0
's
co
n
s
is
ten
t
p
ix
el
ac
cu
r
ac
y
co
m
p
a
r
ed
to
Mo
b
ileNetV2
'
s
f
lu
ctu
atin
g
r
esu
lts
.
Fig
u
r
e
s
2(
e
)
an
d
(
f
)
s
h
o
w
th
e
U
-
Net
Mo
b
ileNetV2
m
o
d
el
m
ain
tain
in
g
tr
ain
in
g
an
d
test
in
g
t
im
es
u
n
d
er
2
5
0
s
ec
o
n
d
s
,
u
n
a
f
f
ec
ted
b
y
d
if
f
er
e
n
t
au
g
m
en
tatio
n
s
.
T
h
is
s
tu
d
y
i
n
v
esti
g
ates
a
c
o
m
p
r
eh
e
n
s
iv
e
s
et
o
f
U
-
Net
m
o
d
els
u
s
i
n
g
m
u
ltip
le
e
n
c
o
d
er
s
an
d
au
g
m
en
tatio
n
s
.
Ho
wev
e
r
,
ad
d
itio
n
al
r
esear
ch
m
ay
b
e
r
eq
u
ir
ed
to
co
n
f
ir
m
th
e
r
eliab
ilit
y
o
f
th
ese
m
o
d
els.
I
n
-
d
ep
th
s
tu
d
ies
ar
e
p
a
r
ticu
lar
ly
n
ee
d
ed
r
e
g
ar
d
i
n
g
th
eir
p
er
f
o
r
m
an
ce
o
n
d
if
f
er
e
n
t
ty
p
es
o
f
p
h
y
to
p
lan
k
to
n
im
a
g
es
an
d
in
v
ar
io
u
s
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
Ou
r
r
esear
ch
s
h
o
ws
th
at
th
e
U
-
Net
Mo
b
ileNetV2
with
o
p
tical
d
is
to
r
tio
n
is
m
o
r
e
r
e
s
ilien
t
an
d
ef
f
ec
tiv
e
in
s
eg
m
en
tin
g
p
h
y
t
o
p
lan
k
to
n
th
an
o
th
e
r
m
o
d
els
.
Fu
tu
r
e
r
esear
ch
m
ay
lo
o
k
in
to
m
o
r
e
d
iv
e
r
s
e
au
g
m
en
tatio
n
s
tr
ateg
ies
an
d
p
r
ac
tical
m
eth
o
d
s
f
o
r
f
u
r
th
er
e
n
h
an
cin
g
s
eg
m
en
tatio
n
ac
cu
r
ac
y
.
E
x
p
lo
r
in
g
th
e
u
s
e
o
f
atten
tio
n
m
ec
h
an
is
m
s
an
d
v
is
io
n
tr
a
n
s
f
o
r
m
er
s
(
ViT
)
with
g
en
er
ativ
e
ad
v
er
s
ar
ial
n
etwo
r
k
s
(
GAN)
to
au
g
m
en
t
lim
ited
d
atasets
co
u
ld
p
r
o
v
id
e
ad
d
itio
n
al
in
s
ig
h
t
s
.
Mo
r
eo
v
er
,
ex
p
e
r
im
en
tin
g
w
ith
th
e
YOL
O
v8
b
ac
k
b
o
n
e
to
cr
ea
te
a
n
ew
U
-
N
et
ar
ch
itectu
r
e
is
an
ex
citin
g
a
v
en
u
e
f
o
r
f
u
tu
r
e
i
n
v
esti
g
atio
n
.
A
tr
ip
ar
tite
ar
r
an
g
em
e
n
t
lin
k
ed
to
th
e
s
em
an
tic
s
eg
m
en
ta
tio
n
o
f
th
e
p
h
y
to
p
la
n
k
to
n
r
e
co
g
n
itio
n
p
r
o
ce
d
u
r
e
is
d
ep
icted
in
Fig
u
r
e
s
3
-
5
.
Fig
u
r
e
3
s
h
o
wca
s
es
a
co
llectio
n
o
f
o
r
ig
in
al
p
h
y
to
p
la
n
k
to
n
in
p
u
t
im
ag
es
o
f
d
if
f
er
en
t
s
izes
an
d
s
h
ap
es
.
T
h
e
im
a
g
es'
b
in
ar
y
r
e
p
r
esen
t
atio
n
s
o
f
t
h
e
r
elev
a
n
t
p
h
y
to
p
lan
k
to
n
r
eg
io
n
s
ar
e
d
is
p
lay
ed
in
Fig
u
r
e
4
as
in
p
u
t
m
ask
s
.
Fig
u
r
e
5
s
h
o
ws
th
e
p
r
o
jecte
d
m
ask
s
o
f
th
e
d
ee
p
lear
n
in
g
n
etwo
r
k
,
illu
s
tr
atin
g
its
at
tem
p
t
to
is
o
l
ate
an
d
h
ig
h
lig
h
t
th
e
p
h
y
to
p
l
an
k
to
n
p
atch
es.
T
h
e
m
o
d
el'
s
ab
ilit
y
to
ac
cu
r
ately
r
ec
o
g
n
ize
an
d
s
ep
ar
ate
p
h
y
to
p
lan
k
to
n
f
r
o
m
th
e
im
ag
e
b
a
ck
g
r
o
u
n
d
is
s
h
o
wca
s
ed
b
y
co
m
p
ar
in
g
th
e
in
p
u
t
an
d
p
r
ed
icted
m
ask
s
.
T
ab
l
e
2
.
T
o
p
5
m
o
d
els o
f
test
Dice
,
I
o
U
,
p
r
ec
is
io
n
,
a
n
d
r
ec
al
l
No
M
o
d
e
l
N
a
me
P
e
r
f
o
r
ma
n
c
e
M
e
t
r
i
c
s
D
i
c
e
(
%)
I
o
U
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
1
U
-
N
e
t
M
o
b
i
l
e
N
e
t
V
2
(
O
p
t
i
c
a
l
D
i
st
o
r
t
i
o
n
)
9
3
.
6
9
8
8
.
1
4
9
9
.
8
9
1
0
0
.
0
0
2
U
-
N
e
t
R
e
sN
e
t
5
0
(
V
e
r
t
i
c
a
l
F
l
i
p
)
9
2
.
6
8
8
6
.
3
8
9
9
.
7
6
9
9
.
9
9
3
U
-
N
e
t
M
o
b
i
l
e
N
e
t
V
2
(
V
e
r
t
i
c
a
l
F
l
i
p
)
9
2
.
0
3
8
5
.
2
7
9
9
.
6
8
9
9
.
9
9
4
U
-
N
e
t
M
o
b
i
l
e
N
e
t
V
2
(
B
l
u
r
)
9
1
.
7
5
8
4
.
7
8
9
9
.
1
9
9
9
.
9
9
5
U
-
N
e
t
R
e
sN
e
t
5
0
(
H
u
e
S
a
t
u
r
a
t
i
o
n
)
9
0
.
6
9
8
2
.
9
9
9
9
.
1
0
9
9
.
9
6
T
h
e
r
esu
lts
s
h
o
w
th
at
o
u
r
ar
c
h
itectu
r
e,
wh
ic
h
u
s
es
m
a
n
y
en
co
d
er
s
an
d
a
u
g
m
e
n
tatio
n
m
eth
o
d
s
in
th
e
U
-
Net
m
o
d
el,
ca
n
im
p
r
o
v
e
p
h
y
to
p
lan
k
t
o
n
s
p
ec
ies
s
eg
m
en
tatio
n
.
T
h
e
U
-
Net
Mo
b
ileNetV2
(
o
p
tical
d
is
to
r
tio
n
)
m
o
d
el
h
as
h
ig
h
er
Dice
(
9
3
.
6
9
%),
I
o
U
(
8
8
.
1
4
%),
p
r
ec
is
io
n
(
9
9
.
8
9
%),
a
n
d
r
ec
all
(
1
0
0
%)
v
alu
es
th
an
p
r
ev
io
u
s
m
o
d
els.
Ma
n
y
m
icr
o
o
r
g
an
is
m
s
’
s
p
ec
ies
'
s
eg
m
en
tatio
n
p
er
f
o
r
m
a
n
ce
im
p
r
o
v
es
with
s
o
p
h
is
ticated
m
eth
o
d
s
.
Fo
r
ex
am
p
le,
th
e
L
C
U
-
Net
a
r
ch
itectu
r
al
m
o
d
el
ac
h
iev
e
d
a
Dice
s
co
r
e
p
er
f
o
r
m
an
ce
o
f
8
7
.
1
3
%,
a
J
ac
ca
r
d
in
d
ex
p
er
f
o
r
m
a
n
ce
o
f
7
9
.
7
4
%,
a
p
r
ec
is
io
n
p
er
f
o
r
m
a
n
ce
o
f
9
0
.
1
4
%,
an
d
a
r
ec
all
p
er
f
o
r
m
a
n
ce
o
f
8
7
.
1
2
%
with
lo
w
p
r
o
ce
s
s
in
g
r
eso
u
r
ce
s
[
3
2
]
.
T
h
e
n
ew
d
ataset
E
MD
S
-
5
u
s
es
U
-
Net
f
o
r
m
u
lti
-
o
b
ject
p
h
o
to
s
eg
m
en
tatio
n
,
s
h
o
win
g
Dice
,
J
ac
ca
r
d
,
a
n
d
r
e
ca
ll
m
etr
ics
o
f
8
5
.
2
4
%,
7
7
.
4
1
%,
an
d
8
2
.
2
8
%
r
e
s
p
ec
tiv
ely
[
3
1
]
.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
we
s
h
o
u
ld
e
x
am
in
e
U
-
Net
d
esig
n
ch
an
g
es
to
in
cr
ea
s
e
s
eg
m
en
tatio
n
p
er
f
o
r
m
an
ce
.
Mo
r
e
r
esear
ch
in
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
1
0
1
3
-
1
0
22
1018
p
r
e
-
p
r
o
ce
s
s
in
g
an
d
au
g
m
en
ta
t
io
n
s
tr
ateg
ies
is
n
ee
d
ed
.
Usi
n
g
atten
tio
n
m
ec
h
an
is
m
s
[
4
7
]
a
n
d
ViT
with
GAN
s
to
au
g
m
en
t
lim
ited
d
atasets
[
3
2
]
an
d
e
x
p
er
im
e
n
tin
g
with
th
e
YOL
O
v
8
b
ac
k
b
o
n
e
[
4
8
]
to
c
r
ea
te
a
n
ew
U
-
Net
ar
ch
itectu
r
e
ar
e
p
r
o
m
is
in
g
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
(
a)
(
b
)
(
c
)
(
d
)
(
e
)
(
f
)
Fig
u
r
e
2
.
Me
tr
ics p
er
f
o
r
m
a
n
ce
of
(
a
)
p
r
ec
is
io
n
,
(
b
)
r
ec
all
,
(
c
)
Dice
s
co
r
e,
(
d
)
I
o
U
, (
e
)
p
ix
el
ac
cu
r
ac
y
,
a
n
d
(
f
)
tim
e
-
co
n
s
u
m
in
g
Fig
u
r
e
3
.
R
esu
lt o
f
p
h
y
to
p
lan
k
to
n
s
em
an
tic
s
eg
m
en
tatio
n
o
f
t
h
e
in
p
u
t im
a
g
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
n
h
a
n
ce
d
U
-
N
et
mo
d
els w
ith
en
co
d
er a
n
d
a
u
g
men
ta
tio
n
fo
r
p
h
yto
p
l
a
n
kto
n
…
(
Ovid
e
Dec
r
o
ly
Wis
n
u
A
r
d
h
i
)
1019
Fig
u
r
e
4
.
R
esu
lt o
f
p
h
y
to
p
lan
k
to
n
s
em
an
tic
s
eg
m
en
tatio
n
o
f
t
h
e
in
p
u
t
m
ask
Fig
u
r
e
5
.
R
esu
lt o
f
p
h
y
to
p
lan
k
to
n
s
em
an
tic
s
eg
m
en
tatio
n
o
f
t
h
e
p
r
ed
icted
m
ask
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
en
h
an
ci
n
g
th
e
p
er
f
o
r
m
an
ce
o
f
s
em
a
n
tic
s
eg
m
en
tatio
n
m
o
d
els
b
y
in
teg
r
atin
g
m
u
ltip
le
en
co
d
e
r
s
an
d
Ad
am
o
p
tim
izer
s
in
to
th
e
U
-
Net
ar
ch
itectu
r
e.
R
ec
en
t
o
b
s
er
v
atio
n
s
in
d
icate
th
at
th
e
p
ix
el
ac
c
u
r
ac
y
o
f
th
e
U
-
Net
R
esNet5
0
m
o
d
el
with
in
teg
r
ated
tr
an
s
f
o
r
m
atio
n
s
is
c
o
n
s
is
ten
tly
h
ig
h
.
Ou
r
f
in
d
in
g
s
o
f
f
er
d
ef
in
itiv
e
p
r
o
o
f
th
at
in
teg
r
atin
g
Mo
b
ileNet
V2
with
o
p
tical
d
is
to
r
tio
n
attain
s
a
h
ig
h
lev
el
o
f
p
r
ec
is
io
n
,
r
at
h
er
t
h
an
b
ein
g
ca
u
s
ed
b
y
in
cr
ea
s
ed
q
u
an
ti
ties
o
f
tr
ai
n
in
g
d
ata.
T
h
e
o
u
tc
o
m
es
o
f
ev
alu
atin
g
d
iv
er
s
e
U
-
Net
m
o
d
els
with
s
ev
er
al
en
c
o
d
er
s
a
n
d
au
g
m
en
tatio
n
s
d
em
o
n
s
tr
ate
ex
ce
p
tio
n
al
ac
cu
r
ac
y
in
s
em
an
tic
s
eg
m
en
tatio
n
p
er
f
o
r
m
an
ce
.
Pro
p
e
r
ly
s
elec
tin
g
an
en
co
d
er
a
n
d
au
g
m
en
tatio
n
s
tr
ateg
y
s
ig
n
if
ican
tly
im
p
a
cts
th
e
p
er
f
o
r
m
an
ce
o
f
a
m
o
d
el.
Usi
n
g
E
f
f
icien
tNet
-
B5
with
B
lu
r
au
g
m
en
tatio
n
d
em
o
n
s
tr
ates
en
h
an
ce
d
r
ec
all,
th
u
s
au
g
m
en
tin
g
t
h
e
m
o
d
el'
s
s
en
s
itiv
ity
.
T
h
e
ex
p
er
im
en
ts
co
n
clu
s
iv
ely
illu
s
tr
ate
th
e
m
o
d
el's
ex
ce
p
tio
n
al
ef
f
icien
cy
an
d
p
e
r
f
o
r
m
an
ce
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
r
esear
ch
,
p
ar
t
o
f
a
d
eg
r
ee
b
y
R
esear
ch
a
t
t
h
e
Nati
o
n
al
R
esear
ch
a
n
d
I
n
n
o
v
atio
n
Ag
en
cy
(
B
R
I
N)
,
r
ec
eiv
ed
f
u
n
d
in
g
f
r
o
m
th
e
R
esear
ch
an
d
I
n
n
o
v
atio
n
f
o
r
Ad
v
an
ce
d
I
n
d
o
n
esia
(
R
I
I
M)
Pro
g
r
am
-
I
n
d
o
n
esia E
n
d
o
wm
e
n
t Fu
n
d
f
o
r
E
d
u
ca
tio
n
Ag
en
c
y
(
L
PDP
)
at
Ph
ase
3
an
d
th
e
Do
ct
o
r
al
Dis
s
er
tatio
n
R
esear
ch
(
PDD)
at
Un
iv
er
s
itas
Se
b
elas
Ma
r
et,
with
g
r
an
t
n
u
m
b
er
s
B
-
8
3
8
/I
I
.
7
.
5
/FR
.
0
6
/5
/2
0
2
3
an
d
B
-
4
9
0
5
/I
I
I
.
6
/KS.0
0
/5
/2
0
2
3
f
o
r
(
R
I
I
M
an
d
L
PDP),
an
d
2
2
8
/UN2
7
.
2
2
/PT.
0
1
.
0
3
/2
0
2
3
f
o
r
PDD
-
UNS.
T
h
e
f
u
n
d
er
s
d
i
d
n
o
t
in
f
lu
en
ce
th
e
ex
p
er
im
en
tal
d
esig
n
,
d
ata
co
llectio
n
an
d
an
al
y
s
is
,
p
u
b
l
icatio
n
d
ec
is
io
n
,
o
r
m
an
u
s
cr
ip
t p
r
e
p
ar
atio
n
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
R
.
A
l
l
e
n
,
“
C
o
n
ser
v
a
t
i
o
n
h
o
t
sp
o
t
s
o
f
b
i
o
d
i
v
e
r
s
i
t
y
a
n
d
e
n
d
e
mi
sm
f
o
r
i
n
d
o
‐
p
a
c
i
f
i
c
c
o
r
a
l
r
e
e
f
f
i
s
h
e
s
,
”
Aq
u
a
t
.
C
o
n
ser
v
.
Ma
r
.
Fre
sh
w
.
Ec
o
sy
st
.
,
v
o
l
.
1
8
,
n
o
.
5
,
p
p
.
5
4
1
–
5
5
6
,
Ju
l
.
2
0
0
8
,
d
o
i
:
1
0
.
1
0
0
2
/
a
q
c
.
8
8
0
.
[
2
]
A
.
R
a
c
h
m
a
n
,
A
.
S
.
S
u
w
a
r
n
o
,
a
n
d
S
.
N
u
r
d
j
a
ma
n
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
d
e
e
p
(
m
a
c
h
i
n
e
)
l
e
a
r
n
i
n
g
f
o
r
p
h
y
t
o
p
l
a
n
k
t
o
n
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
mi
c
r
o
sc
o
p
y
i
m
a
g
e
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
7
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
B
i
o
l
o
g
i
c
a
l
S
c
i
e
n
c
e
(
I
C
B
S
2
0
2
1
)
,
A
t
l
a
n
t
i
s
P
r
e
s
s
I
n
t
e
r
n
a
t
i
o
n
a
l
B
.
V
.
,
2
0
2
2
.
d
o
i
:
1
0
.
2
9
9
1
/
a
b
sr
.
k
.
2
2
0
4
0
6
.
0
3
2
.
[3
]
E.
P
r
a
k
a
sa,
A
.
R
a
c
h
ma
n
,
D
.
R
.
N
o
e
r
d
j
i
t
o
,
a
n
d
R
.
W
a
r
d
o
y
o
,
“
D
e
v
e
l
o
p
me
n
t
o
f
s
e
g
m
e
n
t
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
d
e
t
e
r
m
i
n
i
n
g
p
l
a
n
k
t
o
n
i
c
o
b
j
e
c
t
s
f
r
o
m
m
i
c
r
o
sc
o
p
i
c
i
ma
g
e
s,”
I
O
P
C
o
n
f
.
S
e
r
.
E
a
rt
h
En
v
i
r
o
n
.
S
c
i
.
,
v
o
l
.
9
4
4
,
n
o
.
1
,
p
.
0
1
2
0
2
5
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
5
-
1
3
1
5
/
9
4
4
/
1
/
0
1
2
0
2
5
.
[
4
]
A
.
R
a
c
h
m
a
n
,
“
C
h
e
c
k
l
i
s
t
a
n
d
e
st
i
ma
t
i
o
n
o
f
t
o
t
a
l
n
u
m
b
e
r
o
f
p
h
y
t
o
p
l
a
n
k
t
o
n
s
p
e
c
i
e
s
i
n
P
a
r
i
,
T
i
d
u
n
g
,
a
n
d
P
a
y
u
n
g
I
sl
a
n
d
s,
I
n
d
o
n
e
si
a
,
”
Bi
o
d
i
v
e
rs
i
t
a
s
J
.
Bi
o
l
.
D
i
v
e
rs
.
,
v
o
l
.
2
1
,
n
o
.
6
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
3
0
5
7
/
b
i
o
d
i
v
/
d
2
1
0
6
1
6
.
[
5
]
S
.
Ta
n
g
,
A
.
R
a
c
h
m
a
n
,
N
.
F
i
t
r
i
a
,
H
.
Th
o
h
a
,
a
n
d
B
.
C
h
e
n
,
“
P
h
y
t
o
p
l
a
n
k
t
o
n
c
h
a
n
g
e
s
d
u
r
i
n
g
s
e
m
o
n
s
o
o
n
a
l
p
e
r
i
o
d
i
n
t
h
e
Le
m
b
e
h
S
t
r
a
i
t
o
f
N
o
r
t
h
S
u
l
a
w
e
si
,
I
n
d
o
n
e
si
a
,
f
r
o
m
2
0
1
2
t
o
2
0
1
5
,
”
A
c
t
a
O
c
e
a
n
o
l
.
S
i
n
.
,
v
o
l
.
3
7
,
n
o
.
1
2
,
p
p
.
9
–
1
7
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
1
3
1
-
0
1
8
-
1
2
8
3
-
4.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
1
0
1
3
-
1
0
22
1020
[
6
]
A
.
R
a
c
h
ma
n
,
A
.
P
u
r
w
a
n
d
a
n
a
,
a
n
d
N
.
F
i
t
r
i
y
a
,
“
P
h
y
t
o
p
l
a
n
k
t
o
n
c
o
mm
u
n
i
t
y
st
r
u
c
t
u
r
e
o
f
t
h
e
M
a
k
a
ssar
S
t
r
a
i
t
,
I
n
d
o
n
e
si
a
,
”
I
O
P
C
o
n
f
.
S
e
r.
E
a
rt
h
En
v
i
r
o
n
.
S
c
i
.
,
v
o
l
.
7
8
9
,
n
o
.
1
,
p
.
0
1
2
0
0
6
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
5
-
1
3
1
5
/
7
8
9
/
1
/
0
1
2
0
0
6
.
[
7
]
L.
Ta
r
a
f
d
a
r
e
t
a
l
.
,
“
R
e
s
p
o
n
s
e
s
o
f
p
h
y
t
o
p
l
a
n
k
t
o
n
c
o
mm
u
n
i
t
y
st
r
u
c
t
u
r
e
a
n
d
a
sso
c
i
a
t
i
o
n
t
o
v
a
r
i
a
b
i
l
i
t
y
i
n
e
n
v
i
r
o
n
m
e
n
t
a
l
d
r
i
v
e
r
s
i
n
a
t
r
o
p
i
c
a
l
c
o
a
s
t
a
l
l
a
g
o
o
n
,
”
S
c
i
.
T
o
t
a
l
En
v
i
r
o
n
.
,
v
o
l
.
7
8
3
,
p
.
1
4
6
8
7
3
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sci
t
o
t
e
n
v
.
2
0
2
1
.
1
4
6
8
7
3
.
[
8
]
P
.
G
o
n
z
á
l
e
z
,
A
.
C
a
st
a
ñ
o
,
E.
E.
P
e
a
c
o
c
k
,
J.
D
í
e
z
,
J
.
J.
D
e
l
C
o
z
,
a
n
d
H
.
M
.
S
o
si
k
,
“
A
u
t
o
mat
i
c
p
l
a
n
k
t
o
n
q
u
a
n
t
i
f
i
c
a
t
i
o
n
u
si
n
g
d
e
e
p
f
e
a
t
u
r
e
s,
”
J
.
P
l
a
n
k
t
o
n
Re
s.
,
v
o
l
.
4
1
,
n
o
.
4
,
p
p
.
4
4
9
–
4
6
3
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
9
3
/
p
l
a
n
k
t
/
f
b
z
0
2
3
.
[
9
]
D
.
A
.
H
e
mr
a
j
,
M
.
A
.
H
o
ss
a
i
n
,
Q
.
Y
e
,
J.
G
.
Q
i
n
,
a
n
d
S
.
C
.
L
e
t
e
r
me,
“
P
l
a
n
k
t
o
n
b
i
o
i
n
d
i
c
a
t
o
r
s
o
f
e
n
v
i
r
o
n
m
e
n
t
a
l
c
o
n
d
i
t
i
o
n
s
i
n
c
o
a
s
t
a
l
l
a
g
o
o
n
s,”
Est
u
a
r.
C
o
a
s
t
.
S
h
e
l
f
S
c
i
.
,
v
o
l
.
1
8
4
,
p
p
.
1
0
2
–
1
1
4
,
J
a
n
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
ss.
2
0
1
6
.
1
0
.
0
4
5
.
[
1
0
]
T.
R
.
S
o
e
p
r
o
b
o
w
a
t
i
,
N
.
L.
A
d
d
a
d
i
y
a
h
,
R
.
H
a
r
i
y
a
t
i
,
a
n
d
J.
J
u
mari
,
“
P
h
y
s
i
c
o
-
c
h
e
m
i
c
a
l
a
n
d
b
i
o
l
o
g
i
c
a
l
w
a
t
e
r
q
u
a
l
i
t
y
o
f
w
a
r
n
a
a
n
d
p
e
n
g
i
l
o
n
l
a
k
e
s,
d
i
e
n
g
,
c
e
n
t
r
a
l
j
a
v
a
,
”
J
.
Wa
t
e
r
L
.
D
e
v
.
,
v
o
l
.
5
1
,
n
o
.
X
–
X
I
I
,
p
p
.
3
8
–
4
9
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
2
4
4
2
5
/
j
w
l
d
.
2
0
2
1
.
1
3
9
0
1
3
.
[
1
1
]
F
a
k
h
r
u
r
r
o
z
i
,
T
.
R
.
S
o
e
p
r
o
b
o
w
a
t
i
,
a
n
d
J.
J
u
mari
,
“
T
h
e
w
a
t
e
r
q
u
a
l
i
t
y
i
n
d
e
x
a
n
d
p
h
y
t
o
p
l
a
n
k
t
o
n
c
o
mm
u
n
i
t
i
e
s
o
f
K
o
k
o
h
P
u
t
i
h
R
i
v
e
r
,
S
e
mb
a
l
u
n
,
Ea
s
t
L
o
mb
o
k
,
I
n
d
o
n
e
s
i
a
,
”
A
AC
L
B
i
o
f
l
u
x
,
v
o
l
.
1
5
,
n
o
.
4
,
2
0
2
2
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
b
i
o
f
l
u
x
.
c
o
m.ro
/
d
o
c
s/
2
0
2
2
.
2
0
2
5
-
2
0
4
0
.
p
d
f
[
1
2
]
G.
M
.
H
a
l
l
e
g
r
a
e
f
f
e
t
a
l
.
,
“
P
e
r
c
e
i
v
e
d
g
l
o
b
a
l
i
n
c
r
e
a
s
e
i
n
a
l
g
a
l
b
l
o
o
m
s
i
s
a
t
t
r
i
b
u
t
a
b
l
e
t
o
i
n
t
e
n
s
i
f
i
e
d
m
o
n
i
t
o
r
i
n
g
a
n
d
e
merg
i
n
g
b
l
o
o
m
i
mp
a
c
t
s,”
C
o
m
m
u
n
.
E
a
rt
h
E
n
v
i
r
o
n
.
,
v
o
l
.
2
,
n
o
.
1
,
p
.
1
1
7
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
3
2
4
7
-
0
2
1
-
0
0
1
7
8
-
8.
[
1
3
]
M
.
L.
W
e
l
l
s
e
t
a
l
.
,
“
F
u
t
u
r
e
h
a
b
s
c
i
e
n
c
e
:
d
i
r
e
c
t
i
o
n
s
a
n
d
c
h
a
l
l
e
n
g
e
s
i
n
a
c
h
a
n
g
i
n
g
c
l
i
ma
t
e
,
”
H
a
rm
f
u
l
Al
g
a
e
,
v
o
l
.
9
1
,
p
.
1
0
1
6
3
2
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
a
l
.
2
0
1
9
.
1
0
1
6
3
2
.
[
1
4
]
S
.
H
.
S
a
m
u
d
r
a
e
t
a
l
.
,
“
Th
e
p
h
e
n
o
me
n
o
n
o
f
h
a
r
mf
u
l
a
l
g
a
e
b
l
o
o
m
s
(
h
a
b
s)
b
a
s
e
d
o
n
l
i
t
e
r
a
t
u
r
e
s
t
u
d
y
i
n
I
n
d
o
n
e
s
i
a
s
e
a
w
a
t
e
r
s
f
r
o
m
2
0
0
5
-
2
0
2
1
,
”
I
O
P
C
o
n
f
.
S
e
r.
Ea
r
t
h
E
n
v
i
r
o
n
.
S
c
i
.
,
v
o
l
.
1
2
5
1
,
n
o
.
1
,
p
.
0
1
2
0
4
4
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
5
-
1
3
1
5
/
1
2
5
1
/
1
/
0
1
2
0
4
4
.
[
1
5
]
O
.
D
.
W
.
A
r
d
h
i
,
T.
R
.
S
o
e
p
r
o
b
o
w
a
t
i
,
K
.
A
d
i
,
E
.
P
r
a
k
a
sa
,
a
n
d
A
.
R
a
c
h
m
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
s
f
o
r
p
l
a
n
k
t
o
n
i
d
e
n
t
i
f
i
c
a
t
i
o
n
:
a
b
i
b
l
i
o
met
r
i
c
a
n
a
l
y
si
s
a
n
d
g
e
n
e
r
a
l
r
e
v
i
e
w
,
”
i
n
2
0
2
2
1
s
t
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
S
m
a
r
t
T
e
c
h
n
o
l
o
g
y
,
A
p
p
l
i
e
d
I
n
f
o
rm
a
t
i
c
s,
a
n
d
En
g
i
n
e
e
ri
n
g
(
APIC
S
)
,
I
EEE,
A
u
g
.
2
0
2
2
,
p
p
.
9
6
–
1
0
1
.
d
o
i
:
1
0
.
1
1
0
9
/
A
P
I
C
S
5
6
4
6
9
.
2
0
2
2
.
9
9
1
8
7
0
7
.
[
1
6
]
T.
E
e
r
o
l
a
e
t
a
l
.
,
“
S
u
r
v
e
y
o
f
a
u
t
o
mat
i
c
p
l
a
n
k
t
o
n
i
ma
g
e
r
e
c
o
g
n
i
t
i
o
n
:
c
h
a
l
l
e
n
g
e
s,
e
x
i
s
t
i
n
g
s
o
l
u
t
i
o
n
s
a
n
d
f
u
t
u
r
e
p
e
r
sp
e
c
t
i
v
e
s
,
”
Art
i
f
.
I
n
t
e
l
l
.
R
e
v
.
,
v
o
l
.
5
7
,
n
o
.
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
2
4
-
1
0
7
4
5
-
y.
[
1
7
]
C
.
S
á
n
c
h
e
z
,
N
.
V
á
l
l
e
z
,
G
.
B
u
e
n
o
,
a
n
d
G
.
C
r
i
s
t
ó
b
a
l
,
“
D
i
a
t
o
m
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
c
l
u
d
i
n
g
mo
r
p
h
o
l
o
g
i
c
a
l
a
d
a
p
t
a
t
i
o
n
s
u
si
n
g
C
N
N
s,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
S
p
r
i
n
g
e
r
,
C
h
a
m,
2
0
1
9
,
p
p
.
3
1
7
–
3
2
8
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
3
1
3
3
2
-
6
_
2
8
.
[
1
8
]
H
.
A
.
A
l
-
B
a
r
a
z
a
n
c
h
i
,
A
.
V
e
r
ma
,
a
n
d
S
.
W
a
n
g
,
“
P
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
h
y
b
r
i
d
C
N
N
f
o
r
s
i
p
p
e
r
p
l
a
n
k
t
o
n
i
m
a
g
e
c
a
l
ssi
f
i
c
a
t
i
o
n
,
”
i
n
2
0
1
5
T
h
i
r
d
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
I
m
a
g
e
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
s
si
n
g
(
I
C
I
I
P)
,
I
EEE,
D
e
c
.
2
0
1
5
,
p
p
.
5
5
1
–
5
5
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
I
P
.
2
0
1
5
.
7
4
6
0
2
6
2
.
[
1
9
]
J.
D
a
i
,
R
.
W
a
n
g
,
H
.
Z
h
e
n
g
,
G
.
J
i
,
a
n
d
X
.
Q
i
a
o
,
“
Zo
o
p
l
a
n
k
t
o
N
e
t
:
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
f
o
r
z
o
o
p
l
a
n
k
t
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
O
C
EAN
S
2
0
1
6
-
S
h
a
n
g
h
a
i
,
I
EEE,
A
p
r
.
2
0
1
6
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
O
C
EA
N
S
A
P
.
2
0
1
6
.
7
4
8
5
6
8
0
.
[
2
0
]
I
.
C
o
r
r
e
a
,
P
.
D
r
e
w
s,
S
.
B
o
t
e
l
h
o
,
M
.
S
.
d
e
S
o
u
z
a
,
a
n
d
V
.
M
.
Ta
v
a
n
o
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
mi
c
r
o
a
l
g
a
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
2
0
1
7
1
6
t
h
I
EEE
I
n
t
e
rn
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
r
n
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
(
I
C
MLA)
,
I
EEE,
D
e
c
.
2
0
1
7
,
p
p
.
2
0
–
2
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
LA
.
2
0
1
7
.
0
-
1
8
3
.
[
2
1
]
K
.
K
r
a
f
t
e
t
a
l
.
,
“
T
o
w
a
r
d
s
o
p
e
r
a
t
i
o
n
a
l
p
h
y
t
o
p
l
a
n
k
t
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
a
u
t
o
ma
t
e
d
h
i
g
h
-
t
h
r
o
u
g
h
p
u
t
i
ma
g
i
n
g
,
n
e
a
r
-
r
e
a
l
-
t
i
me
d
a
t
a
p
r
o
c
e
ss
i
n
g
,
a
n
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
Fr
o
n
t
.
M
a
r.
S
c
i
.
,
v
o
l
.
9
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
m
a
r
s.
2
0
2
2
.
8
6
7
6
9
5
.
[
2
2
]
J.
S
.
El
l
e
n
,
C
.
A
.
G
r
a
f
f
,
a
n
d
M
.
D
.
O
h
man
,
“
I
mp
r
o
v
i
n
g
p
l
a
n
k
t
o
n
i
ma
g
e
c
l
a
s
si
f
i
c
a
t
i
o
n
u
si
n
g
c
o
n
t
e
x
t
m
e
t
a
d
a
t
a
,
”
L
i
m
n
o
l
.
O
c
e
a
n
o
g
r.
Me
t
h
o
d
s
,
v
o
l
.
1
7
,
n
o
.
8
,
p
p
.
4
3
9
–
4
6
1
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
2
/
l
o
m
3
.
1
0
3
2
4
.
[
2
3
]
J.
R
a
i
t
o
h
a
r
j
u
e
t
a
l
.
,
“
D
a
t
a
e
n
r
i
c
h
me
n
t
i
n
f
i
n
e
-
g
r
a
i
n
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
a
q
u
a
t
i
c
mac
r
o
i
n
v
e
r
t
e
b
r
a
t
e
s,”
i
n
2
0
1
6
I
C
P
R
2
n
d
W
o
rks
h
o
p
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
f
o
r
A
n
a
l
y
s
i
s
o
f
U
n
d
e
rw
a
t
e
r Im
a
g
e
ry
(
C
VAU
I
)
,
I
EEE,
D
e
c
.
2
0
1
6
,
p
p
.
4
3
–
4
8
.
d
o
i
:
1
0
.
1
1
0
9
/
C
V
A
U
I
.
2
0
1
6
.
0
2
0
.
[
2
4
]
A
.
S
.
K
e
ç
e
l
i
,
A
.
K
a
y
a
,
a
n
d
S
.
U
.
K
e
ç
e
l
i
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
r
a
d
i
o
l
a
r
i
a
n
i
mag
e
s
w
i
t
h
h
a
n
d
-
c
r
a
f
t
e
d
a
n
d
d
e
e
p
f
e
a
t
u
r
e
s
,
”
C
o
m
p
u
t
.
G
e
o
sc
i
.
,
v
o
l
.
1
0
9
,
p
p
.
6
7
–
7
4
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
a
g
e
o
.
2
0
1
7
.
0
8
.
0
1
1
.
[
2
5
]
K
.
C
h
e
n
g
,
X
.
C
h
e
n
g
,
Y
.
W
a
n
g
,
H
.
B
i
,
a
n
d
M
.
C
.
B
e
n
f
i
e
l
d
,
“
E
n
h
a
n
c
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
f
o
r
p
l
a
n
k
t
o
n
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
e
n
u
mer
a
t
i
o
n
,
”
PL
o
S
O
n
e
,
v
o
l
.
1
4
,
n
o
.
7
,
p
.
e
0
2
1
9
5
7
0
,
Ju
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
1
9
5
7
0
.
[
2
6
]
W
.
M
a
e
t
a
l
.
,
“
S
u
p
e
r
-
r
e
s
o
l
u
t
i
o
n
f
o
r
i
n
si
t
u
p
l
a
n
k
t
o
n
i
ma
g
e
s,”
i
n
2
0
2
1
I
EE
E/
C
VF
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
si
o
n
Wo
r
k
sh
o
p
s (I
C
C
VW
)
,
I
EEE,
O
c
t
.
2
0
2
1
,
p
p
.
3
6
7
6
–
3
6
8
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
V
W
5
4
1
2
0
.
2
0
2
1
.
0
0
4
1
1
.
[
2
7
]
O
.
R
o
n
n
e
b
e
r
g
e
r
,
P
.
F
i
sc
h
e
r
,
a
n
d
T.
B
r
o
x
,
“
U
-
N
e
t
:
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
s
f
o
r
b
i
o
m
e
d
i
c
a
l
i
m
a
g
e
s
e
g
me
n
t
a
t
i
o
n
,
”
L
e
c
t
.
N
o
t
e
s
C
o
m
p
u
t
.
S
c
i
.
(
i
n
c
l
u
d
i
n
g
S
u
b
se
r.
L
e
c
t
.
N
o
t
e
s
Art
i
f
.
I
n
t
e
l
l
.
L
e
c
t
.
N
o
t
e
s
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
9
3
5
1
,
p
p
.
2
3
4
–
2
4
1
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
2
4
5
7
4
-
4
_
2
8
.
[
2
8
]
S
.
Le
e
,
M
.
N
e
g
i
s
h
i
,
H
.
U
r
a
k
u
b
o
,
H
.
K
a
s
a
i
,
a
n
d
S
.
I
sh
i
i
,
“
M
U
-
N
e
t
:
m
u
l
t
i
-
s
c
a
l
e
U
-
N
e
t
f
o
r
t
w
o
-
p
h
o
t
o
n
mi
c
r
o
s
c
o
p
y
i
m
a
g
e
d
e
n
o
i
si
n
g
a
n
d
r
e
s
t
o
r
a
t
i
o
n
,
”
N
e
u
ra
l
N
e
t
w
o
rks
,
v
o
l
.
1
2
5
,
p
p
.
9
2
–
1
0
3
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
2
0
.
0
1
.
0
2
6
.
[
2
9
]
D
.
L
i
e
t
a
l
.
,
“
R
o
b
u
s
t
b
l
o
o
d
c
e
l
l
i
m
a
g
e
se
g
me
n
t
a
t
i
o
n
me
t
h
o
d
b
a
se
d
o
n
n
e
u
r
a
l
o
r
d
i
n
a
r
y
d
i
f
f
e
r
e
n
t
i
a
l
e
q
u
a
t
i
o
n
s,
”
C
o
m
p
u
t
.
M
a
t
h
.
Me
t
h
o
d
s
M
e
d
.
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
1
1
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
5
5
9
0
1
8
0
.
[
3
0
]
R
.
A
z
a
d
e
t
a
l
.
,
“
M
e
d
i
c
a
l
i
ma
g
e
s
e
g
m
e
n
t
a
t
i
o
n
r
e
v
i
e
w
:
t
h
e
s
u
c
c
e
ss
o
f
U
-
N
e
t
,
”
I
EEE
T
r
a
n
s.
P
a
t
t
e
rn
An
a
l
.
M
a
c
h
.
I
n
t
e
l
l
.
,
p
p
.
1
–
2
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
TPA
M
I
.
2
0
2
4
.
3
4
3
5
5
7
1
.
[
3
1
]
Z.
L
i
e
t
a
l
.
,
“
E
M
D
S
-
5
:
e
n
v
i
r
o
n
m
e
n
t
a
l
mi
c
r
o
o
r
g
a
n
i
sm
i
m
a
g
e
d
a
t
a
se
t
f
i
f
t
h
v
e
r
si
o
n
f
o
r
mu
l
t
i
p
l
e
i
m
a
g
e
a
n
a
l
y
si
s
t
a
sk
s
,
”
PLo
S
O
n
e
,
v
o
l
.
1
6
,
n
o
.
5
,
p
.
e
0
2
5
0
6
3
1
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
5
0
6
3
1
.
[
3
2
]
J.
Z
h
a
n
g
e
t
a
l
.
,
“
L
C
U
-
n
e
t
:
a
n
o
v
e
l
l
o
w
-
c
o
st
U
-
N
e
t
f
o
r
e
n
v
i
r
o
n
me
n
t
a
l
mi
c
r
o
o
r
g
a
n
i
s
m i
ma
g
e
s
e
g
m
e
n
t
a
t
i
o
n
,
”
P
a
t
t
e
rn
R
e
c
o
g
n
i
t
.
,
v
o
l
.
1
1
5
,
p
.
1
0
7
8
8
5
,
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
1
.
1
0
7
8
8
5
.
[
3
3
]
H
.
Y
a
n
g
e
t
a
l
.
,
“
C
o
m
p
a
r
a
t
i
v
e
st
u
d
y
f
o
r
p
a
t
c
h
-
l
e
v
e
l
a
n
d
p
i
x
e
l
-
l
e
v
e
l
s
e
g
m
e
n
t
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
met
h
o
d
s
o
n
t
r
a
n
s
p
a
r
e
n
t
i
m
a
g
e
s
o
f
e
n
v
i
r
o
n
m
e
n
t
a
l
mi
c
r
o
o
r
g
a
n
i
sms
:
f
r
o
m 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
t
o
v
i
su
a
l
t
r
a
n
sf
o
r
mers
,
”
A
p
p
l
.
S
c
i
.
,
v
o
l
.
1
2
,
n
o
.
1
8
,
p
.
9
3
2
1
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
1
8
9
3
2
1
.
[
3
4
]
B
.
C
.
R
u
sse
l
l
,
A
.
T
o
r
r
a
l
b
a
,
K
.
P
.
M
u
r
p
h
y
,
a
n
d
W
.
T
.
F
r
e
e
ma
n
,
“
La
b
e
l
M
e
:
a
d
a
t
a
b
a
s
e
a
n
d
w
e
b
-
b
a
se
d
t
o
o
l
f
o
r
i
m
a
g
e
a
n
n
o
t
a
t
i
o
n
,
”
I
n
t
.
J
.
C
o
m
p
u
t
.
V
i
s.
,
v
o
l
.
7
7
,
n
o
.
1
–
3
,
p
p
.
1
5
7
–
1
7
3
,
M
a
y
2
0
0
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
2
6
3
-
007
-
0
0
9
0
-
8.
[
3
5
]
A
.
B
u
sl
a
e
v
,
V
.
I
.
I
g
l
o
v
i
k
o
v
,
E
.
K
h
v
e
d
c
h
e
n
y
a
,
A
.
P
a
r
i
n
o
v
,
M
.
D
r
u
z
h
i
n
i
n
,
a
n
d
A
.
A
.
K
a
l
i
n
i
n
,
“
A
l
b
u
me
n
t
a
t
i
o
n
s
:
f
a
st
a
n
d
f
l
e
x
i
b
l
e
i
ma
g
e
a
u
g
m
e
n
t
a
t
i
o
n
s,”
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
1
1
,
n
o
.
2
,
p
.
1
2
5
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
i
n
f
o
1
1
0
2
0
1
2
5
.
[
3
6
]
E.
A
n
d
e
r
sso
n
a
n
d
R
.
B
e
r
g
l
u
n
d
,
“
E
v
a
l
u
a
t
i
o
n
o
f
d
a
t
a
a
u
g
me
n
t
a
t
i
o
n
o
f
mr
i
mag
e
s
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
,
”
2
0
1
8
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
l
u
p
.
l
u
b
.
l
u
.
se/
l
u
u
r
/
d
o
w
n
l
o
a
d
?
f
i
l
e
O
I
d
=
8
9
5
2
7
4
8
&f
u
n
c
=
d
o
w
n
l
o
a
d
F
i
l
e
&r
e
c
o
r
d
O
I
d
=
8
9
5
2
7
4
7
[
3
7
]
A
.
Lu
m
i
n
i
a
n
d
L.
N
a
n
n
i
,
“
D
e
e
p
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
f
e
a
t
u
r
e
s
f
o
r
p
l
a
n
k
t
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Ec
o
l
.
I
n
f
o
rm
.
,
v
o
l
.
5
1
,
p
p
.
3
3
–
4
3
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
o
i
n
f
.
2
0
1
9
.
0
2
.
0
0
7
.
[
3
8
]
S
.
X
i
e
,
R
.
G
i
r
sh
i
c
k
,
P
.
D
o
l
l
a
r
,
Z.
T
u
,
a
n
d
K
.
H
e
,
“
A
g
g
r
e
g
a
t
e
d
r
e
si
d
u
a
l
t
r
a
n
sf
o
r
m
a
t
i
o
n
s
f
o
r
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
2
0
1
7
I
EEE
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
Pa
t
t
e
rn
R
e
c
o
g
n
i
t
i
o
n
(
C
V
PR)
,
I
EEE,
J
u
l
.
2
0
1
7
,
p
p
.
5
9
8
7
–
5
9
9
5
.
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
7
.
6
3
4
.
[
3
9
]
M
.
S
a
n
d
l
e
r
,
A
.
H
o
w
a
r
d
,
M
.
Zh
u
,
A
.
Zh
m
o
g
i
n
o
v
,
a
n
d
L
.
C
.
C
h
e
n
,
“
M
o
b
i
l
e
N
e
t
V
2
:
i
n
v
e
r
t
e
d
r
e
s
i
d
u
a
l
s
a
n
d
l
i
n
e
a
r
b
o
t
t
l
e
n
e
c
k
s,
”
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
n
h
a
n
ce
d
U
-
N
et
mo
d
els w
ith
en
co
d
er a
n
d
a
u
g
men
ta
tio
n
fo
r
p
h
yto
p
l
a
n
kto
n
…
(
Ovid
e
Dec
r
o
ly
Wis
n
u
A
r
d
h
i
)
1021
Pro
c
e
e
d
i
n
g
s o
f
t
h
e
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
si
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
I
EEE,
J
u
n
.
2
0
1
8
,
p
p
.
4
5
1
0
–
4
5
2
0
.
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
8
.
0
0
4
7
4
.
[
4
0
]
M
.
Ta
n
a
n
d
Q
.
V
.
Le
,
“
Ef
f
i
c
i
e
n
t
N
e
t
:
r
e
t
h
i
n
k
i
n
g
mo
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
,
”
a
rX
i
v
,
M
a
y
2
0
1
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
9
0
5
.
1
1
9
4
6
[
4
1
]
M
.
O
.
La
w
a
l
,
“
T
o
ma
t
o
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
m
o
d
i
f
i
e
d
Y
O
LO
v
3
f
r
a
mew
o
r
k
,
”
S
c
i
.
R
e
p
.
,
v
o
l
.
1
1
,
n
o
.
1
,
p
.
1
4
4
7
,
Jan
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
1
-
8
1
2
1
6
-
5.
[4
2]
Y
.
Li
,
C
.
W
e
i
,
a
n
d
T
.
M
a
,
“
To
w
a
r
d
s
e
x
p
l
a
i
n
i
n
g
t
h
e
r
e
g
u
l
a
r
i
z
a
t
i
o
n
e
f
f
e
c
t
o
f
i
n
i
t
i
a
l
l
a
r
g
e
l
e
a
r
n
i
n
g
r
a
t
e
i
n
t
r
a
i
n
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
a
rXi
v
,
Ju
l
.
2
0
1
9
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
9
0
7
.
0
4
5
9
5
.
[
4
3
]
Z.
H
a
o
,
Y
.
Ji
a
n
g
,
H
.
Y
u
,
a
n
d
H
.
-
D
.
C
h
i
a
n
g
,
“
A
d
a
p
t
i
v
e
l
e
a
r
n
i
n
g
r
a
t
e
a
n
d
m
o
me
n
t
u
m f
o
r
t
r
a
i
n
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
S
p
r
i
n
g
e
r
,
C
h
a
m,
2
0
2
1
,
p
p
.
3
8
1
–
3
9
6
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
8
6
5
2
3
-
8
_
2
3
.
[
4
4
]
D
.
P
.
K
i
n
g
ma
a
n
d
J.
B
a
,
“
A
d
a
m
:
a
m
e
t
h
o
d
f
o
r
s
t
o
c
h
a
s
t
i
c
o
p
t
i
m
i
z
a
t
i
o
n
,
”
a
rX
i
v
,
2
0
1
7
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
4
1
2
.
6
9
8
0
.
[
4
5
]
L.
R
.
D
i
c
e
,
“
M
e
a
s
u
r
e
s
o
f
t
h
e
a
m
o
u
n
t
o
f
e
c
o
l
o
g
i
c
a
ss
o
c
i
a
t
i
o
n
b
e
t
w
e
e
n
s
p
e
c
i
e
s
,
”
Ec
o
l
o
g
y
,
v
o
l
.
2
6
,
n
o
.
3
,
p
p
.
2
9
7
–
3
0
2
,
J
u
l
.
1
9
4
5
,
d
o
i
:
1
0
.
2
3
0
7
/
1
9
3
2
4
0
9
.
[
4
6
]
D
.
M
ü
l
l
e
r
,
I
.
S
o
t
o
-
R
e
y
,
a
n
d
F
.
K
r
a
m
e
r
,
“
To
w
a
r
d
s
a
g
u
i
d
e
l
i
n
e
f
o
r
e
v
a
l
u
a
t
i
o
n
me
t
r
i
c
s
i
n
me
d
i
c
a
l
i
ma
g
e
s
e
g
me
n
t
a
t
i
o
n
,
”
B
MC
Re
s
.
N
o
t
e
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
2
1
0
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
3
1
0
4
-
0
2
2
-
0
6
0
9
6
-
y.
[
4
7
]
A
.
K
u
mt
h
e
k
a
r
a
n
d
G
.
R
.
R
e
d
d
y
,
“
R
e
d
e
s
i
g
n
i
n
g
u
-
n
e
t
w
i
t
h
d
e
n
se
c
o
n
n
e
c
t
i
o
n
a
n
d
a
t
t
e
n
t
i
o
n
m
o
d
u
l
e
f
o
r
s
a
t
e
l
l
i
t
e
b
a
se
d
c
l
o
u
d
d
e
t
e
c
t
i
o
n
,
”
I
AE
S
I
n
t
.
J
.
Ar
t
i
f
.
I
n
t
e
l
l
.
,
v
o
l
.
1
1
,
n
o
.
2
,
p
.
6
9
9
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
1
.
i
2
.
p
p
6
9
9
-
7
0
8
.
[
4
8
]
J.
Te
r
v
e
n
a
n
d
D
.
C
o
r
d
o
v
a
-
E
sp
a
r
z
a
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
Y
O
LO
a
r
c
h
i
t
e
c
t
u
r
e
s
i
n
c
o
m
p
u
t
e
r
v
i
s
i
o
n
:
f
r
o
m
Y
O
LO
v
1
t
o
Y
O
LO
v
8
a
n
d
Y
O
LO
-
n
a
s
,
”
a
rX
i
v
,
2
0
2
4
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
3
0
4
.
0
0
5
0
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
O
v
id
e
De
c
r
o
ly
W
isn
u
Ar
d
h
i
o
b
tain
e
d
a
Ba
c
h
e
l
o
r
o
f
E
n
g
i
n
e
e
rin
g
(B
.
E
n
g
.
)
i
n
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
fr
o
m
th
e
Un
iv
e
rsitas
Isla
m
In
d
o
n
e
sia
in
2
0
0
8
.
He
t
h
e
n
p
u
rsu
e
d
a
M
a
ste
r
o
f
En
g
in
e
e
ri
n
g
(
M
.
E
n
g
.
)
with
a
sp
e
c
ializa
ti
o
n
in
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
fr
o
m
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
i
v
e
rsitas
G
a
d
jah
M
a
d
a
,
wh
ich
h
e
c
o
m
p
lete
d
i
n
2
0
1
2
.
He
is
p
u
rsu
in
g
a
P
h
D
i
n
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
a
t
th
e
S
c
h
o
o
l
o
f
P
o
st
g
ra
d
u
a
te
S
t
u
d
ies
,
Un
iv
e
rsitas
Dip
o
n
e
g
o
ro
.
As
i
d
e
f
ro
m
p
u
rs
u
in
g
h
is
d
o
c
t
o
ra
l
stu
d
i
e
s,
h
e
is
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
,
V
o
c
a
ti
o
n
a
l
S
c
h
o
o
l
a
t
Un
iv
e
rsitas
S
e
b
e
las
M
a
re
t,
S
u
ra
k
a
rta,
In
d
o
n
e
sia
.
He
is p
rima
ril
y
in
tere
ste
d
i
n
In
fo
rm
a
ti
o
n
S
y
st
e
m
s,
Artifi
c
ial
In
telli
g
e
n
c
e
,
M
a
c
h
in
e
Lea
rn
in
g
,
De
e
p
Lea
rn
in
g
,
a
n
d
Bio
i
n
fo
rm
a
ti
c
s.
C
o
n
tac
t
h
im
v
ia
e
m
a
il
a
t
o
v
i
d
e
@s
taff.u
n
s.a
c
.
i
d
o
r
o
v
id
e
@s
tu
d
e
n
ts.u
n
d
i
p
.
a
c
.
id
.
Pro
f.
Dr
.
Tr
i
Re
tn
a
n
in
g
sih
S
o
e
p
r
o
b
o
w
a
ti,
MA
p
p
S
c
a
p
ro
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
Bi
o
lo
g
y
,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
M
a
th
e
m
a
ti
c
s,
a
n
d
th
e
S
c
h
o
o
l
o
f
P
o
st
g
ra
d
u
a
te
S
tu
d
ies
a
t
Un
iv
e
rsitas
Dip
o
n
e
g
o
ro
,
S
e
m
a
ra
n
g
,
In
d
o
n
e
sia
,
o
b
tai
n
e
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
b
io
l
o
g
y
fro
m
U
n
iv
e
rsitas
G
a
d
jah
M
a
d
a
in
1
9
8
7
.
S
h
e
f
u
rth
e
re
d
h
e
r
e
d
u
c
a
ti
o
n
with
a
M
a
ste
r
o
f
Ap
p
li
e
d
S
c
ien
c
e
in
En
v
iro
n
m
e
n
tal
S
c
ien
c
e
fro
m
th
e
Un
i
v
e
rsity
o
f
Wes
tern
S
y
d
n
e
y
-
Ha
wk
e
sb
u
ry
,
NS
W,
Au
stra
li
a
,
in
1
9
9
6
.
S
h
e
c
o
m
p
lete
d
h
e
r
P
h
.
D.
i
n
En
v
iro
n
m
e
n
tal
S
c
ien
c
e
a
t
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
in
2
0
1
0
.
He
r
e
x
p
e
rti
se
p
rima
ril
y
li
e
s
in
E
n
v
ir
o
n
m
e
n
tal
S
c
ien
c
e
s
a
n
d
Eco
lo
g
y
,
E
n
g
in
e
e
rin
g
,
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
.
F
o
r
c
o
rre
sp
o
n
d
e
n
c
e
,
Co
n
tac
t
h
e
r
v
ia
e
m
a
il
a
t
trso
e
p
ro
b
o
wa
ti
@li
v
e
.
u
n
d
i
p
.
a
c
.
i
d
.
Pro
f.
Dr
.
K
u
sw
o
r
o
Adi
,
S
.
T.
,
M.
T.
a
p
r
o
fe
ss
o
r
in
th
e
fiel
d
o
f
In
str
u
m
e
n
tal
P
h
y
sic
s
a
t
t
h
e
De
p
a
rtme
n
t
o
f
P
h
y
sic
s,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
M
a
t
h
e
m
a
ti
c
s,
a
n
d
t
h
e
S
c
h
o
o
l
o
f
P
o
stg
ra
d
u
a
te
S
t
u
d
ies
a
t
Un
i
v
e
rsit
a
s
Dip
o
n
e
g
o
r
o
,
S
e
m
a
ra
n
g
,
I
n
d
o
n
e
sia
,
e
a
rn
e
d
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
p
h
y
sic
s
fro
m
U
n
iv
e
rsit
a
s
Dip
o
n
e
g
o
ro
i
n
1
9
9
6
.
He
o
b
ta
in
e
d
h
is
M
a
ste
r'
s
in
Im
a
g
e
P
ro
c
e
ss
in
g
fro
m
th
e
In
st
it
u
t
Te
k
n
o
lo
g
i
Ba
n
d
u
n
g
in
2
0
0
6
.
He
c
o
m
p
lete
d
h
is
P
h
.
D.
i
n
Im
a
g
in
g
a
n
d
Im
a
g
e
P
ro
c
e
ss
in
g
a
t
th
e
In
st
it
u
t
Tek
n
o
l
o
g
i
Ba
n
d
u
n
g
in
2
0
1
0
.
His
re
se
a
rc
h
i
n
tere
sts
a
re
fo
c
u
se
d
o
n
Artifi
c
ial
In
telli
g
e
n
c
e
a
n
d
C
o
m
p
u
ter
Visi
o
n
.
He
c
a
n
b
e
re
a
c
h
e
d
fo
r
c
o
rre
sp
o
n
d
e
n
c
e
v
ia em
a
il
a
t
k
u
sw
o
ro
a
d
i@lec
t
u
re
r.
u
n
d
ip
.
a
c
.
id
.
Dr
.
Esa
Pra
k
a
sa
,
S
.
T.
,
M.
T.
o
b
tain
e
d
h
is
Ba
c
h
e
l
o
r
o
f
E
n
g
i
n
e
e
rin
g
(
B
.
E
n
g
)
in
1
9
9
8
a
fter
c
o
m
p
leti
n
g
h
is
u
n
d
e
r
g
ra
d
u
a
te
stu
d
ies
i
n
N
u
c
lea
r
En
g
in
e
e
rin
g
a
t
Un
i
v
e
rsitas
G
a
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
.
Afte
r
o
b
tain
i
n
g
a
M
a
ste
r
o
f
En
g
in
e
e
rin
g
(
M
.
En
g
)
i
n
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
in
2
0
0
1
,
h
e
c
o
n
ti
n
u
e
d
h
is
a
c
a
d
e
m
ic
p
u
rs
u
it
s
a
t
t
h
e
sa
m
e
in
stit
u
ti
o
n
.
T
h
e
M
a
lay
sia
n
i
n
stit
u
ti
o
n
Un
iv
e
rsiti
Tek
n
o
l
o
g
i
P
E
TRONA
S
a
wa
rd
e
d
h
im
a
Do
c
to
r
o
f
P
h
il
o
so
p
h
y
(P
h
D)
i
n
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
E
n
g
i
n
e
e
rin
g
in
2
0
1
4
.
He
is
a
se
n
i
o
r
re
se
a
rc
h
e
r
a
t
th
e
Re
se
a
rc
h
Ce
n
ter
fo
r
Da
ta
a
n
d
I
n
fo
rm
a
ti
o
n
S
c
ien
c
e
s
o
f
th
e
Na
ti
o
n
a
l
Re
se
a
rc
h
a
n
d
In
n
o
v
a
ti
o
n
A
g
e
n
c
y
(BRIN).
His
re
se
a
rc
h
in
tere
sts
a
re
im
a
g
e
a
n
d
v
isu
a
l
d
a
ta
a
n
a
ly
sis,
p
a
tt
e
rn
re
c
o
g
n
it
io
n
,
a
n
d
c
o
m
p
u
ter v
isio
n
.
P
lea
se
e
m
a
il
h
im a
t
e
sa
p
0
0
1
@
b
ri
n
.
g
o
.
i
d
wit
h
a
n
y
in
q
u
iri
e
s o
r
c
o
rre
sp
o
n
d
e
n
c
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
1
0
1
3
-
1
0
22
1022
Ar
ief
Ra
c
h
m
a
n
,
M
.
Bio
l.
S
c
.
w
o
rk
s
a
s
a
re
se
a
rc
h
e
r
a
t
t
h
e
P
la
n
k
to
n
La
b
o
ra
to
r
y
,
a
p
a
rt
o
f
th
e
Re
se
a
rc
h
Ce
n
ter
fo
r
Oc
e
a
n
o
g
ra
p
h
y
u
n
d
e
r
th
e
Na
ti
o
n
a
l
Re
se
a
r
c
h
a
n
d
In
n
o
v
a
ti
o
n
Ag
e
n
c
y
(BRIN).
He
h
o
l
d
s
a
M
a
ste
r
o
f
Bi
o
lo
g
ica
l
S
c
ien
c
e
(
M
.
Bio
l.
S
c
.
)
.
He
sp
e
c
ialize
s
in
m
a
rin
e
p
h
y
t
o
p
la
n
k
t
o
n
,
p
a
C
o
n
v
o
lu
tio
n
al
Netwo
r
k
s
f
o
r
B
io
m
ed
ical
I
m
ag
e
Seg
m
en
tatio
n
rti
c
u
larl
y
stu
d
y
in
g
h
a
rm
fu
l
a
l
g
a
e
'
s
d
y
n
a
m
ic
a
n
d
e
c
o
l
o
g
ica
l
p
ro
p
e
rti
e
s.
F
u
rth
e
rm
o
re
,
h
e
is
a
c
c
o
u
n
tab
le
f
o
r
re
se
a
rc
h
in
g
t
h
e
se
field
s,
a
ss
e
ss
in
g
sa
m
p
les
a
n
d
d
a
ta,
a
n
d
p
ro
v
id
i
n
g
d
irec
ti
o
n
a
n
d
i
n
stru
c
ti
o
n
a
l
su
p
e
rv
isi
o
n
to
st
u
d
e
n
t
s
in
v
o
lv
e
d
in
lab
o
ra
to
ry
in
tern
sh
ip
s,
fi
n
a
l
p
r
o
jec
ts,
t
h
e
se
s,
o
r
d
isse
rtatio
n
s.
Ki
n
d
l
y
a
d
d
re
ss
a
ll
in
q
u
iri
e
s
a
n
d
c
o
m
m
e
n
ts
to
a
riefra
c
h
m
a
n
1
9
8
7
@
y
a
h
o
o
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.