I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Ro
bo
t
ics a
nd
Aut
o
m
a
t
io
n
(
I
J
RA)
Vo
l.
14
,
No
.
3
,
Sep
tem
b
er
20
25
,
p
p
.
40
7
~
41
7
I
SS
N:
2722
-
2
5
8
6
,
DOI
:
1
0
.
1
1
5
9
1
/i
jr
a
.
v
14
i
3
.
pp
40
7
-
41
7
4
0
7
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
a
.
ia
esco
r
e.
co
m
Disea
se dete
ction
o
n coco
nut
t
ree
u
sing
go
lden j
a
cka
l
o
ptimiza
tion a
lg
o
rithm
Arun
Ra
m
a
ia
h
1
,
M
uthus
a
m
y
Sh
un
m
ug
a
t
ha
m
ma
l
2
,
H
a
ri
K
rish
na
K
a
lid
in
di
3
,
Ani
s
h P
o
n Ya
m
ini
K
um
a
re
s
o
n
4
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
P
.
S
.
R
.
En
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
,
S
i
v
a
k
a
si
,
V
i
r
u
d
h
u
n
a
g
a
r
,
T
a
m
i
l
n
a
d
u
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
S
R
M
I
n
s
t
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
R
a
m
a
p
u
r
a
m
,
C
h
e
n
n
a
i
,
T
a
mi
l
N
a
d
u
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
R
K
R
E
n
g
i
n
e
e
r
i
n
g
C
o
l
l
e
g
e
(
A
)
,
B
h
i
ma
v
a
r
a
m,
C
h
i
n
a
m
i
r
a
m
R
u
r
a
l
,
A
n
d
h
r
a
P
r
a
d
e
s
h
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
V
e
l
Te
c
h
R
a
n
g
a
r
a
j
a
n
D
r
.
S
a
g
u
n
t
h
a
l
a
R
&D
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
A
v
a
d
i
,
C
h
e
n
n
a
i
,
Ta
m
i
l
N
a
d
u
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
2
3
,
2
0
2
4
R
ev
is
ed
J
u
n
3
,
2
0
2
5
Acc
ep
ted
J
u
l 1
0
,
2
0
2
5
M
il
li
o
n
s
o
f
p
e
o
p
le
d
e
p
e
n
d
o
n
c
o
c
o
n
u
t
p
a
lms
f
o
r
th
e
ir
fo
o
d
a
n
d
li
v
e
li
h
o
o
d
s,
m
a
k
in
g
th
e
m
o
n
e
o
f
th
e
m
o
st
e
ss
e
n
ti
a
l
c
ro
p
s
in
tro
p
ica
l
c
o
u
n
tr
ies
.
Ho
we
v
e
r,
Dise
a
se
s
m
a
y
sig
n
ifi
c
a
n
t
ly
re
d
u
c
e
th
e
o
u
tp
u
t
o
f
c
o
c
o
n
u
t
tree
s
a
n
d
p
o
ss
ib
l
y
re
su
lt
in
t
h
e
ir
d
e
a
t
h
.
T
o
o
v
e
r
c
o
m
e
th
is,
a
n
o
v
e
l
g
o
ld
e
n
jac
k
a
l
o
p
ti
m
ize
d
d
ise
a
se
d
e
tec
ti
o
n
in
COCO
n
u
t
t
re
e
(G
OD
-
C
OCO
)
h
a
s
b
e
e
n
p
r
o
p
o
se
d
fo
r
d
e
tec
ti
n
g
d
ise
a
se
s
in
c
o
c
o
n
u
t
tre
e
s.
F
irst,
t
h
e
in
p
u
t
d
a
tas
e
t
ima
g
e
s
a
re
p
re
-
p
ro
c
e
ss
e
d
in
p
re
-
p
r
o
c
e
ss
in
g
im
a
g
e
ro
tatio
n
,
ima
g
e
re
sc
a
li
n
g
,
a
n
d
ima
g
e
re
siz
in
g
,
a
n
d
t
h
e
e
n
h
a
n
c
e
d
ima
g
e
s
a
re
g
a
th
e
re
d
.
Th
e
e
n
h
a
n
c
e
d
i
m
a
g
e
s
a
re
se
g
m
e
n
ted
u
sin
g
t
h
e
P
S
P
-
Ne
t.
F
r
o
m
th
e
se
g
m
e
n
ted
ima
g
e
s,
th
e
fe
a
tu
re
s
a
re
e
x
trac
ted
u
sin
g
t
h
e
De
n
se
-
Ne
t.
T
h
e
n
t
h
e
fe
a
tu
re
s
n
e
e
d
e
d
a
re
se
lec
ted
u
si
n
g
th
e
g
o
ld
e
n
jac
k
a
l
o
p
ti
m
iza
ti
o
n
a
lg
o
rit
h
m
(G
JO
A).
F
in
a
ll
y
,
t
h
e
d
e
e
p
b
e
li
e
f
n
e
two
rk
(DBN
)
c
las
sifier
c
las
sifies
wh
e
th
e
r
it
is
n
o
rm
a
l
o
r
a
b
n
o
rm
a
l.
Th
e
e
x
p
e
rime
n
tal
a
n
a
l
y
sis
o
f
th
e
p
r
o
p
o
se
d
G
OD
-
COC
h
a
s
b
e
e
n
e
v
a
l
u
a
ted
u
si
n
g
th
e
P
lan
t
P
a
th
o
lo
g
y
d
a
tas
e
ts
b
a
se
d
o
n
th
e
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
a
n
d
re
c
a
ll
sta
n
d
a
rd
s.
B
y
t
h
is,
t
h
e
p
r
o
p
o
se
d
G
O
D
-
COCO
a
c
h
iev
e
s
a
n
a
c
c
u
ra
c
y
ra
te
o
f
9
9
.
3
1
%
a
n
d
it
a
c
h
iev
e
s
a
n
o
v
e
ra
ll
a
c
c
u
ra
c
y
ra
te
o
f
0
.
7
7
%
,
0
.
3
1
%
a
n
d
1
.
1
7
%
b
y
th
e
e
x
isti
n
g
m
e
th
o
d
s
s
u
c
h
a
s
AIE
-
CTDDC,
DL
-
WDM
,
a
n
d
CL
S
.
S
imilarly
,
th
e
p
ro
p
o
se
d
G
OD
-
CO
CO
m
o
d
e
l
tak
e
s
les
s
ti
m
e
,
1
.
1
3
m
i
ll
ise
c
o
n
d
s
to
d
e
tec
t
th
e
d
ise
a
se
,
th
a
n
th
e
e
x
is
ti
n
g
m
e
th
o
d
s,
wh
ic
h
tak
e
3
.
0
4
,
2
.
5
,
a
n
d
2
.
6
7
m
il
li
se
c
o
n
d
s,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
C
o
co
n
u
t d
is
ea
s
e
Dee
p
b
elief
n
etwo
r
k
Den
s
e
-
Net
Go
ld
en
jack
al
o
p
tim
izatio
n
Plan
t p
ath
o
lo
g
y
d
atasets
PSP
-
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
:
Ar
u
n
R
am
aiah
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
P.S.R E
n
g
in
ee
r
in
g
C
o
lleg
e
Siv
ak
asi,
Vir
u
d
h
u
n
a
g
ar
,
T
am
i
l
Nad
u
,
I
n
d
ia
E
m
ail:
ar
u
n
.
r
@
p
s
r
.
ed
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
Glo
b
ally
,
co
co
n
u
t
tr
ee
s
g
r
o
w
ex
ten
s
iv
ely
an
d
p
r
o
v
id
e
a
s
ig
n
if
ican
t
s
o
u
r
ce
o
f
i
n
co
m
e
f
o
r
n
u
m
er
o
u
s
in
d
iv
id
u
als
in
tr
o
p
ical
p
lace
s
.
Am
o
n
g
v
ar
io
u
s
tr
o
p
ical
d
ev
el
o
p
in
g
co
u
n
tr
ies
an
d
o
th
er
Pacif
ic
I
s
lan
d
n
atio
n
s
,
th
e
co
co
n
u
t
tr
ee
h
as
s
ig
n
if
ican
t
ec
o
lo
g
ical
a
n
d
ec
o
n
o
m
ic
b
en
ef
its
[
1
]
,
[
2
]
.
T
h
ese
co
co
n
u
t
tr
ee
s
h
av
e
s
u
f
f
e
r
ed
f
r
o
m
n
u
m
er
o
u
s
d
is
ea
s
es
in
r
e
ce
n
t
y
ea
r
s
[
3
]
,
[
4
]
.
T
h
e
co
co
n
u
t
tr
ee
is
n
o
t
o
n
ly
g
o
r
g
eo
u
s
b
u
t
also
in
c
r
ed
ib
ly
p
r
ac
tical
[
5
]
,
[
6
]
.
Ma
n
y
k
in
d
s
o
f
p
r
o
b
lem
s
with
co
co
n
u
t
tr
ee
s
co
u
ld
p
r
ev
en
t
th
is
tr
ee
f
r
o
m
g
r
o
win
g
h
ea
lth
ily
[
7
]
,
[
8
]
.
T
h
er
ef
o
r
e,
f
o
r
a
co
c
o
n
u
t tr
ee
to
f
lo
u
r
is
h
,
p
r
o
p
er
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t o
f
p
r
o
b
le
m
s
ar
e
ess
en
tial
[
9
]
,
[
1
0
]
.
A
v
ar
iety
o
f
p
ests
f
r
eq
u
e
n
tly
in
f
lict ser
io
u
s
h
ar
m
to
co
c
o
n
u
t tr
ee
s
[
1
1
]
,
[
1
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
40
7
-
41
7
408
I
n
f
estatio
n
s
an
d
d
is
ea
s
es
th
at
af
f
lict
co
co
n
u
t
tr
ee
s
m
o
s
t
f
r
eq
u
en
tly
i
n
th
e
ce
n
tr
al
Ph
ilip
p
in
es
in
clu
d
e
y
ello
win
g
,
f
lacc
id
ity
,
leaf
let
d
r
y
in
g
,
ca
ter
p
illar
s
,
an
d
leaf
lets
[
1
3
]
,
[
1
4
]
.
T
h
e
c
o
co
n
u
t
tr
ee
'
s
leav
es
ca
n
b
e
u
s
ed
to
d
etec
t n
u
tr
ien
t
d
ef
icits
b
ased
o
n
c
o
lo
r
ch
a
n
g
es
[
1
5
]
,
[
1
6
]
.
T
h
e
m
ajo
r
ity
o
f
f
ar
m
er
s
ar
e
u
n
ab
le
to
id
en
tif
y
th
e
d
is
ea
s
e
as
lo
n
g
as
s
ev
er
al
p
la
n
ts
an
d
i
d
en
tical
s
y
m
p
t
o
m
s
a
r
e
p
r
esen
t
in
m
u
ltip
le
n
u
tr
itio
n
al
s
h
o
r
tag
es
[
1
7
]
.
Sin
ce
s
ev
er
al
f
er
tili
ze
r
s
o
n
th
e
m
ar
k
et
co
n
tain
m
o
r
e
n
u
tr
ien
ts
th
an
o
th
e
r
s
,
ch
o
o
s
in
g
t
h
e
r
i
g
h
t
f
e
r
tili
ze
r
is
also
cr
u
cial.
Fig
u
r
e
1
d
escr
ib
es
th
e
d
is
ea
s
e
s
th
at
af
f
ec
t
co
co
n
u
t
tr
ee
s
in
v
ar
io
u
s
co
u
n
tr
ies.
Fin
ally
,
th
e
d
is
cu
s
s
io
n
will h
ig
h
lig
h
t th
e
m
o
d
el'
s
im
p
licatio
n
s
f
o
r
d
etec
tin
g
d
is
ea
s
es
in
co
co
n
u
t tr
ee
s
.
−
H
o
w
c
a
n
c
o
c
o
n
u
t
t
r
e
e
d
is
e
as
e
s
b
e
a
c
c
u
r
a
t
el
y
d
e
t
e
ct
e
d
a
n
d
c
l
as
s
i
f
i
e
d
u
s
i
n
g
a
d
v
a
n
c
e
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
?
−
W
h
a
t
a
r
e
t
h
e
i
m
p
a
c
ts
o
f
f
e
a
t
u
r
e
s
e
le
c
t
i
o
n
u
s
i
n
g
t
h
e
g
o
l
d
e
n
j
ac
k
a
l
o
p
t
i
m
i
za
t
i
o
n
al
g
o
r
i
t
h
m
(
GJ
O
A
)
o
n
d
is
e
ase
c
l
a
s
s
i
f
ic
a
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
?
−
H
o
w
d
o
e
s
t
h
e
p
r
o
p
o
s
e
d
GO
D
-
C
OC
O
m
eth
o
d
im
p
r
o
v
e
tim
e
ef
f
icien
cy
co
m
p
ar
ed
to
ex
is
tin
g
ap
p
r
o
ac
h
es?
I
n
th
is
,
th
e
tr
ee
s
af
f
ec
te
d
b
y
th
e
co
co
n
u
t
tr
ee
s
ar
e
in
cr
ea
s
in
g
y
ea
r
b
y
y
ea
r
in
v
ar
i
o
u
s
way
s
.
T
h
is
wo
r
k
'
s
p
r
im
ar
y
c
o
n
tr
ib
u
tio
n
h
as
b
ee
n
s
u
cc
ess
f
u
lly
co
m
p
leted
b
y
:
−
A
n
o
v
e
l
G
OD
-
C
O
C
O
h
a
s
b
e
en
p
r
o
p
o
s
e
d
f
o
r
d
e
t
e
c
t
i
n
g
d
i
s
ea
s
es
o
n
c
o
c
o
n
u
t
t
r
e
e
s
w
h
e
t
h
e
r
i
t
is
n
o
r
m
a
l
o
r
a
b
n
o
r
m
a
l
.
−
F
i
r
s
t
,
t
h
e
i
n
p
u
t
d
a
t
a
s
et
i
m
a
g
es
a
r
e
p
r
e
-
p
r
o
c
e
s
s
e
d
t
o
i
m
a
g
e
r
o
ta
t
i
o
n
,
i
m
a
g
e
r
e
s
c
al
i
n
g
,
a
n
d
i
m
a
g
e
r
e
s
i
z
i
n
g
,
a
n
d
t
h
e
e
n
h
a
n
c
e
d
i
m
a
g
e
s
a
r
e
g
a
t
h
e
r
e
d
.
−
T
h
e
e
n
h
a
n
c
e
d
i
m
a
g
e
s
a
r
e
s
e
g
m
e
n
t
e
d
u
s
i
n
g
t
h
e
PS
P
-
N
et
.
Fr
o
m
t
h
e
s
e
g
m
e
n
t
e
d
i
m
a
g
e
s
,
th
e
f
e
a
t
u
r
e
s
a
r
e
e
x
t
r
a
c
t
e
d
u
s
i
n
g
t
h
e
D
e
n
s
e
-
Net
.
−
T
h
e
n
t
h
e
f
e
a
t
u
r
es
n
e
e
d
e
d
a
r
e
s
e
l
e
ct
e
d
u
s
i
n
g
t
h
e
G
J
OA
.
F
i
n
a
l
l
y
,
t
h
e
d
ee
p
b
elief
n
etwo
r
k
(
DB
N)
c
l
a
s
s
i
f
i
e
r
c
l
a
s
s
i
f
ie
s
w
h
et
h
e
r
i
t
i
s
n
o
r
m
a
l
o
r
a
b
n
o
r
m
a
l
.
T
h
e
f
o
r
m
a
t
f
o
r
t
h
e
r
e
m
a
i
n
d
e
r
o
f
t
h
e
s
t
u
d
y
r
e
p
o
r
t
w
as
as
f
o
l
l
o
w
s
.
S
e
c
t
i
o
n
2
p
r
o
v
i
d
e
s
a
n
o
v
e
r
v
i
e
w
a
n
d
a
f
u
l
l
s
u
m
m
a
r
y
o
f
t
h
e
r
el
e
v
a
n
t
wo
r
k
s
.
A
t
h
o
r
o
u
g
h
d
e
s
c
r
i
p
t
i
o
n
o
f
t
h
e
p
r
o
p
o
s
e
d
G
O
D
-
C
OC
O
s
y
s
t
e
m
f
o
r
i
d
e
n
t
i
f
y
i
n
g
c
o
c
o
n
u
t
t
r
e
e
d
i
s
e
as
es
is
p
r
o
v
i
d
e
d
i
n
S
e
c
t
i
o
n
3
.
S
ec
t
i
o
n
4
c
o
n
ta
i
n
s
d
is
c
u
s
s
i
o
n
a
n
d
e
x
p
e
r
i
m
e
n
ta
l
f
a
l
l
o
u
ts
.
S
e
ct
i
o
n
5
c
o
n
c
l
u
d
e
s
w
it
h
s
o
m
e
t
h
o
u
g
h
ts
f
o
r
f
u
t
u
r
e
d
e
v
e
l
o
p
m
e
n
t
.
Fig
u
r
e
1
.
Dis
ea
s
es a
f
f
ec
ted
co
co
n
u
t tr
ee
s
in
v
ar
io
u
s
co
u
n
tr
ie
s
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Kad
eth
an
k
ar
et
a
l.
[
1
8
]
p
r
o
p
o
s
ed
an
ex
h
a
u
s
tiv
e
p
ip
elin
e
f
o
r
id
en
tify
in
g
a
s
p
ec
if
ic
in
s
ec
t
i
n
co
co
n
u
t
tr
ee
s
.
T
h
e
p
r
im
a
r
y
g
o
al
is
to
r
e
co
g
n
ize
an
d
d
i
f
f
er
en
tiate
e
v
er
y
s
in
g
le
tr
ee
cr
o
wn
f
r
o
m
an
im
ag
e
th
at
m
ig
h
t
h
av
e
u
p
to
th
ir
ty
cr
o
wn
s
.
C
o
n
v
o
lu
ti
o
n
n
eu
r
al
n
etwo
r
k
(
C
NN)
-
b
ase
d
alg
o
r
i
th
m
s
h
av
e
s
ev
er
al
p
r
o
b
lem
s
wh
en
it
co
m
es
to
u
n
m
an
n
ed
ae
r
ial
v
eh
icle
(
UAV)
n
av
ig
atio
n
an
d
im
a
g
e
p
r
o
ce
s
s
in
g
in
wo
o
d
e
d
r
eg
io
n
s
.
Sin
g
h
et
a
l.
[
1
9
]
p
r
o
p
o
s
ed
th
e
id
en
tific
atio
n
o
f
n
u
tr
itio
n
al
d
ef
icits
an
d
in
s
ec
t
i
n
f
estatio
n
s
in
t
h
e
c
o
co
n
u
t
leav
es.
C
o
co
n
u
t
leav
es
h
av
e
b
ee
n
s
ee
n
ap
p
ly
in
g
th
e
n
ewe
s
t
tech
n
iq
u
es
in
im
ag
e
p
r
o
ce
s
s
in
g
an
d
m
ac
h
i
n
e
lear
n
in
g
f
o
llo
win
g
th
e
ap
p
licatio
n
o
f
p
esti
cid
es
an
d
f
er
tili
ze
r
s
.
I
t
is
n
o
t
p
o
s
s
ib
le
to
en
h
an
ce
th
is
s
y
s
tem
b
y
ad
d
i
n
g
o
th
er
f
ea
tu
r
es
lik
e
wate
r
lev
el
an
d
s
o
il
ty
p
e
,
th
is
is
o
n
e
o
f
th
e
m
ajo
r
d
r
awb
ac
k
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
Dis
ea
s
e
d
etec
tio
n
o
n
co
c
o
n
u
t t
r
ee
u
s
in
g
g
o
ld
en
ja
ck
a
l
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
(
A
r
u
n
R
a
ma
i
a
h
)
409
Ma
r
ay
et
a
l.
[
2
0
]
s
u
g
g
ested
th
e
AI
E
-
C
T
DDC
co
n
ce
p
t
f
o
r
in
tellig
en
t
f
ar
m
in
g
,
wh
ich
is
an
ar
tific
ial
in
tellig
en
ce
-
en
ab
led
m
et
h
o
d
f
o
r
id
en
tify
in
g
an
d
ca
teg
o
r
izin
g
co
co
n
u
t
tr
ee
illn
ess
es.
I
t
id
en
tifie
s
d
is
ea
s
e
s
th
at
af
f
ec
t
co
co
n
u
t
tr
ee
s
i
n
an
in
t
ellig
en
t
f
ar
m
in
g
s
ettin
g
to
in
cr
e
ase
cr
o
p
o
u
tp
u
t.
T
h
e
m
ai
n
d
r
awb
ac
k
o
f
th
is
ap
p
r
o
ac
h
is
th
at
it d
o
es n
o
t h
el
p
to
en
s
u
r
e
th
e
i
n
d
u
s
tr
y
'
s
s
u
s
ta
in
ab
ilit
y
.
I
n
2
0
2
2
,
B
an
er
jee
et
a
l.
[
2
1
]
d
ev
elo
p
ed
a
m
eth
o
d
f
o
r
id
e
n
tify
in
g
an
d
c
ateg
o
r
izin
g
th
e
d
eg
r
ee
s
o
f
c
o
c
o
n
u
t
leaf
y
ello
win
g
d
is
ea
s
e
u
s
i
n
g
C
NN
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
.
I
n
o
r
d
er
to
r
ec
o
g
n
ize
an
d
class
if
y
th
e
v
ar
io
u
s
d
eg
r
ee
s
o
f
s
ev
er
ity
o
f
th
e
co
co
n
u
t
leaf
y
ello
win
g
illn
ess
,
th
e
s
u
g
g
este
d
C
NN
an
d
SVM
m
eth
o
d
o
l
o
g
y
is
a
v
iab
le
an
d
ef
f
icien
t te
ch
n
iq
u
e.
Kav
ith
am
an
i
an
d
Ma
h
eswar
i
[
2
2
]
in
tr
o
d
u
ce
d
th
e
d
ee
p
lear
n
in
g
-
ass
is
ted
wh
itef
ly
d
etec
ti
o
n
m
o
d
el
(
DL
-
W
DM
)
a
m
o
d
el
ef
f
ec
tiv
e
in
f
in
d
in
g
illn
ess
es
o
f
co
co
n
u
t
tr
ee
s
lik
e
in
s
ec
t
in
f
estatio
n
,
d
ir
ty
b
lad
es,
a
n
d
b
leed
in
g
r
o
o
ts
.
T
h
e
s
u
g
g
ested
DL
-
W
DM
ac
h
iev
es
an
ac
cu
r
ac
y
r
ate
o
f
9
5
.
7
1
%.
On
e
o
f
th
e
m
ain
d
is
ad
v
an
tag
e
s
co
u
ld
b
e
th
e
d
if
f
icu
lt
y
in
co
m
p
ilin
g
a
lar
g
e
d
ataset
co
v
er
in
g
a
v
ar
iety
o
f
illn
ess
es
af
f
ec
tin
g
co
co
n
u
t
tr
ee
s
.
I
n
2
0
2
3
B
r
ar
et
a
l
.
[
2
3
]
s
u
g
g
ested
a
d
ee
p
lear
n
in
g
(
DL
)
-
b
ased
v
er
s
io
n
o
f
R
esNex
t5
0
f
o
r
th
e
co
co
n
u
t
s
ec
to
r
.
T
h
e
s
y
s
tem
ac
h
iev
es a
9
1
.
7
7
% o
v
er
all
ac
cu
r
ac
y
r
ate
in
co
r
r
ec
tly
i
d
en
tify
in
g
a
u
to
m
atic
d
etec
tio
n
an
d
class
if
icatio
n
o
f
C
L
S
d
is
ea
s
e.
T
h
e
s
u
g
g
est
ed
ap
p
r
o
ac
h
h
as
p
r
o
m
is
es
f
o
r
g
r
ea
tly
en
h
an
ci
n
g
th
e
ef
f
icac
y
an
d
p
r
ec
is
io
n
o
f
d
etec
tin
g
an
d
tr
ac
k
in
g
C
L
S d
is
ea
s
e.
Yo
g
ab
alaje
e
an
d
Kaliap
p
a
n
[
2
4
]
p
r
o
p
o
s
ed
th
at
MCo
n
v
n
ex
tV
2
u
tili
ze
s
a
Swin
o
p
tim
izer
to
d
etec
t
an
d
class
if
y
co
co
n
u
t
tr
ee
leaf
d
is
ea
s
es
to
en
ab
le
p
r
ec
is
io
n
f
ar
m
in
g
.
T
h
e
p
r
i
n
cip
al
aim
o
f
th
is
s
tu
d
y
is
to
p
r
o
m
o
te
s
u
s
tain
ab
le
ag
r
icu
ltu
r
al
m
eth
o
d
s
b
y
u
s
in
g
cu
ttin
g
-
ed
g
e
te
ch
n
o
lo
g
ies
to
ac
c
u
r
ately
clas
s
if
y
p
lan
t
d
is
ea
s
es.
Ap
p
ly
in
g
a
s
wim
o
p
tim
izer
th
e
p
r
o
p
o
s
ed
MCo
n
v
n
e
x
tV2
ac
h
iev
es 9
9
% a
cc
u
r
ac
y
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
is
r
esear
ch
p
r
o
p
o
s
es
a
n
o
v
el
GOD
-
C
OC
O
h
as
b
ee
n
p
r
o
p
o
s
ed
f
o
r
d
etec
tin
g
d
is
ea
s
es
o
n
co
co
n
u
t
tr
ee
s
,
wh
eth
er
it
is
n
o
r
m
al
o
r
ab
n
o
r
m
al.
First,
th
e
in
p
u
t
d
a
taset
im
ag
es
ar
e
p
r
e
-
p
r
o
ce
s
s
ed
in
p
r
e
-
p
r
o
ce
s
s
in
g
im
ag
e
r
o
tatio
n
,
im
ag
e
r
escali
n
g
,
an
d
im
ag
e
r
esizin
g
,
an
d
th
e
en
h
a
n
ce
d
im
ag
es
ar
e
g
ath
er
ed
.
T
h
e
en
h
a
n
ce
d
im
ag
es
ar
e
s
eg
m
e
n
ted
u
s
in
g
t
h
e
PS
P
-
Net.
Fro
m
t
h
e
s
eg
m
e
n
ted
im
ag
es,
th
e
f
ea
tu
r
es
a
r
e
ex
tr
ac
ted
u
s
in
g
th
e
Den
s
e
-
Net.
T
h
en
t
h
e
f
ea
tu
r
es
n
ee
d
ed
ar
e
s
elec
ted
u
s
in
g
t
h
e
GJOA.
Fin
ally
,
th
e
DB
N
class
if
ier
class
if
ies
wh
eth
er
it is
n
o
r
m
al
o
r
ab
n
o
r
m
al.
Fig
u
r
e
2
illu
s
tr
ates th
e
g
e
n
er
al
p
r
o
ce
d
u
r
e
o
f
t
h
e
GOD
-
C
OC
O
m
eth
o
d
.
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
am
o
f
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
eth
o
d
3
.
1
.
P
re
-
p
ro
ce
s
s
ing
T
h
e
im
ag
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
ar
e
as f
o
llo
ws.
a.
I
m
ag
e
r
o
tatio
n
:
I
m
ag
e
r
o
tati
o
n
is
a
r
u
d
im
e
n
tar
y
im
a
g
e
p
r
o
ce
s
s
in
g
m
eth
o
d
t
h
at
m
o
d
if
ies
th
e
im
ag
e
o
r
ien
tatio
n
b
y
a
p
r
ed
eter
m
in
e
d
an
g
le.
T
h
e
ten
d
e
n
cy
o
f
th
e
m
o
d
el
to
g
en
er
alize
an
d
id
en
ti
f
y
p
atter
n
s
m
o
r
e
p
r
ec
is
ely
ca
n
b
e
e
n
h
an
ce
d
b
y
r
o
tatin
g
im
ag
es
t
o
b
etter
alig
n
t
h
e
ch
ar
ac
te
r
is
tics
in
s
id
e
th
em
with
th
e
m
o
d
el'
s
lear
n
in
g
o
b
jectiv
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
40
7
-
41
7
410
b.
I
m
ag
e
r
e
-
s
ca
lin
g
:
R
esizin
g
in
v
o
lv
es
eith
er
ex
p
an
d
in
g
o
r
d
ec
r
ea
s
in
g
th
e
d
im
e
n
s
io
n
s
o
f
t
h
e
i
m
ag
es
is
k
n
o
wn
as
im
ag
e
r
e
-
sc
alin
g
.
T
o
en
s
u
r
e
th
at
m
o
d
els
ca
n
h
a
n
d
le
im
ag
es
o
f
d
if
f
er
e
n
t
d
im
en
s
io
n
s
ef
f
icien
tly
,
s
tan
d
ar
d
ize
in
p
u
ts
,
an
d
r
e
d
u
ce
co
m
p
u
tatio
n
al
co
m
p
le
x
ity
,
r
e
s
ca
lin
g
is
ess
en
tial.
c.
I
m
ag
e
r
e
-
s
izin
g
:
I
m
ag
e
r
esizin
g
is
a
b
asic
im
ag
e
p
r
o
ce
s
s
in
g
t
ec
h
n
iq
u
e
th
at
e
n
tails
ad
ju
s
tin
g
th
e
d
im
en
s
io
n
s
o
f
im
a
g
es.
T
h
is
alter
atio
n
m
o
d
if
ies
th
e
im
ag
e'
s
p
ix
el
co
u
n
t,
ca
u
s
in
g
it
to
eith
er
g
et
s
m
aller
o
r
lar
g
e
r
.
R
esizin
g
p
h
o
to
s
also
aid
s
i
n
th
e
cr
ea
tio
n
o
f
co
n
s
is
ten
t
d
atase
ts
,
m
ak
in
g
it
ea
s
ier
to
t
r
ain
a
n
d
u
s
e
p
r
ed
ictiv
e
alg
o
r
ith
m
s
o
n
a
v
ar
iety
o
f
im
a
g
e
in
p
u
ts
.
3
.
2
.
Seg
m
ent
a
t
i
o
n
Par
titi
o
n
in
g
th
e
im
ag
e
in
to
m
ea
n
in
g
f
u
l
p
a
r
ts
o
r
o
b
jects
f
o
r
an
aly
s
is
an
d
co
m
p
r
eh
en
s
io
n
is
k
n
o
wn
as
s
eg
m
en
tatio
n
.
Seg
m
e
n
tin
g
an
im
ag
e
f
ac
ilit
ates
an
aly
s
is
an
d
m
ak
es
it
ea
s
ier
to
r
etr
iev
e
im
p
o
r
tan
t
in
f
o
r
m
atio
n
.
I
n
th
is
,
th
e
p
r
e
-
p
r
o
ce
s
s
ed
im
ag
es a
r
e
im
ag
e
d
atasets
ar
e
s
eg
m
en
ted
u
s
in
g
t
h
e
PS
P
-
Net.
3
.
2
.
1
.
P
SP
-
Net
A
m
u
lti
-
s
ca
le
n
etwo
r
k
is
u
s
ed
in
th
e
PS
P
-
Net
p
y
r
am
id
s
ce
n
e
p
r
o
ce
s
s
in
g
s
y
s
tem
.
T
h
e
p
y
r
am
id
p
o
o
lin
g
m
o
d
u
le
is
u
s
ed
in
th
e
s
em
an
ti
c
s
eg
m
en
tatio
n
ar
ea
to
in
cr
ea
s
e
s
eg
m
en
tatio
n
ac
cu
r
ac
y
an
d
ef
f
ec
tiv
ely
lear
n
th
e
g
lo
b
al
co
n
tex
t
o
f
th
e
s
ce
n
e.
T
h
e
PS
P
-
Net
ac
q
u
ir
es
a
b
ac
k
g
r
o
u
n
d
p
r
io
r
ity
an
d
en
r
ic
h
es
s
em
an
tic
s
eg
m
en
tatio
n
with
co
n
tex
t
in
f
o
r
m
atio
n
.
T
h
is
PS
P
-
Net
n
etwo
r
k
m
o
d
el
m
ea
s
u
r
es
th
e
tr
ain
in
g
er
r
o
r
as
th
e
av
er
ag
e
o
f
th
e
to
tal
o
f
th
e
o
u
tp
u
t
er
r
o
r
s
f
o
r
ea
ch
p
i
x
el
in
th
e
s
am
p
le
im
ag
e
.
B
y
e
m
p
lo
y
in
g
p
o
o
lin
g
of
v
ar
io
u
s
s
izes
an
d
h
av
in
g
th
e
ab
ilit
y
to
in
cr
ea
s
e
th
e
n
etwo
r
k
's
r
ea
l
r
ec
ep
tiv
e
f
ield
,
th
e
s
p
ati
al
p
y
r
am
id
p
o
o
lin
g
m
o
d
u
le
s
u
cc
ess
f
u
lly
m
itig
ates
th
is
is
s
u
e.
T
h
e
PS
P
-
Net
n
etwo
r
k
u
s
es th
is
b
en
ef
it to
its
f
u
ll p
o
ten
tial.
Fig
u
r
e
3
d
ep
icts
its
n
etwo
r
k
s
tr
u
ctu
r
e.
Fig
u
r
e
3
.
Ar
c
h
itectu
r
e
o
f
PS
P
-
Net
3
.
3
.
F
e
a
t
ure
e
x
t
r
a
ct
io
n
Featu
r
e
ex
tr
ac
tio
n
is
th
e
m
eth
o
d
o
f
id
en
tif
y
in
g
a
n
d
r
em
o
v
i
n
g
r
elev
an
t
p
atter
n
s
o
r
ch
ar
ac
te
r
is
tics
f
r
o
m
v
is
u
al
d
ata
s
o
th
at
it
ca
n
b
e
e
x
p
r
ess
ed
s
u
cc
in
ctly
an
d
u
n
a
m
b
i
g
u
o
u
s
ly
.
Sev
er
al
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
u
s
e
th
e
co
llected
f
ea
tu
r
es
as
th
e
b
a
s
is
f
o
r
m
o
r
e
co
m
p
le
x
ev
alu
atio
n
an
d
an
aly
s
is
.
Fro
m
t
h
e
s
eg
m
en
ted
im
ag
e
d
ataset,
th
e
f
ea
tu
r
es a
r
e
e
x
tr
ac
ted
u
s
in
g
th
e
Den
s
e
-
N
et
m
eth
o
d
.
3
.
3
.
1
.
Dense
-
Net
Den
s
eNe
t
is
an
in
n
o
v
ativ
e,
p
ar
am
eter
-
lig
h
t
v
er
s
io
n
o
f
t
h
e
C
NN
ar
ch
itectu
r
e
f
o
r
v
is
u
al
o
b
ject
r
ec
o
g
n
itio
n
.
Den
s
eNe
t
an
d
R
e
s
Net
ar
e
r
elativ
ely
s
im
ilar
,
with
a
f
ew
k
e
y
d
if
f
er
en
ce
s
.
I
t
c
an
im
p
r
o
v
e
f
ea
t
u
r
e
m
ap
p
r
o
p
ag
atio
n
,
less
en
th
e
n
u
m
b
er
o
f
p
ar
am
eter
s
r
eq
u
ir
e
d
,
an
d
s
o
lv
e
th
e
v
an
is
h
in
g
-
g
r
ad
i
en
t p
r
o
b
lem
.
Dir
ec
t
co
n
n
ec
tio
n
s
f
r
o
m
an
y
lay
er
t
o
an
y
f
o
llo
win
g
lay
e
r
ar
e
a
n
o
v
el
co
n
n
ec
tiv
ity
p
atter
n
in
th
e
Den
s
eNe
t
m
o
d
el
co
m
p
ar
ed
to
p
r
e
v
io
u
s
C
NNs,
a
n
d
th
e
y
ca
n
s
ig
n
if
ica
n
tly
e
n
h
a
n
ce
th
e
in
f
o
r
m
atio
n
f
lo
w
ac
r
o
s
s
lay
er
s
.
T
h
e
r
ef
o
r
e
,
th
e
f
ea
tu
r
e
m
a
p
s
o
f
e
v
er
y
p
r
ev
io
u
s
lay
er
ar
e
tr
a
n
s
m
itted
to
th
e
ℓ
ℎ
lay
er
,
an
d
(
1
)
is
co
m
p
u
ted
:
ℓ
=
ℳ
ℓ
[
(
0
,
1
,
…
…
.
.
ℓ
−
1
)
]
(
1
)
w
h
er
e
1
in
d
icate
s
th
e
ℓ
ℎ
lay
er
'
s
o
u
tp
u
t
an
d
ℓ
in
d
icate
s
th
e
lay
er
.
[
0
,
1
,
…
…
.
ℓ
−
1
]
d
en
o
tes
th
e
jo
in
in
g
o
f
f
ea
tu
r
e
m
ap
s
m
a
d
e
in
lay
e
r
s
0
,
1
,
2
.
.
.
l
−
1
.
Ad
d
itio
n
ally
,
ℳ
1
m
a
y
b
e
a
co
m
b
in
atio
n
o
f
v
a
r
io
u
s
u
s
es
an
id
e
n
tity
f
u
n
ctio
n
-
b
ased
s
k
ip
-
c
o
n
n
ec
tio
n
to
cir
cu
m
v
en
t th
e
n
o
n
-
lin
ea
r
tr
an
s
f
o
r
m
atio
n
s
.
ℓ
=
ℳ
ℓ
(
ℓ
)
+
ℓ
−
1
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
Dis
ea
s
e
d
etec
tio
n
o
n
co
c
o
n
u
t t
r
ee
u
s
in
g
g
o
ld
en
ja
ck
a
l
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
(
A
r
u
n
R
a
ma
i
a
h
)
411
T
h
e
m
o
d
el
Den
s
eNe
t2
0
1
(
T
T
A)
in
d
icate
s
th
at
th
e
test
s
et
h
as
b
ee
n
ex
p
an
d
e
d
wh
ile
th
e
tr
ain
in
g
s
et
s
till
u
s
e
s
th
e
Den
s
eNe
t2
0
1
m
o
d
el.
T
o
o
b
tain
s
u
f
f
icien
t
d
iv
er
s
ity
in
s
a
m
p
les
an
d
d
er
iv
e
a
d
ee
p
n
etw
o
r
k
f
r
o
m
th
e
im
ag
es,
d
ata
au
g
m
e
n
tatio
n
is
an
ess
en
tial p
h
ase.
3
.
4
.
F
e
a
t
ure
s
elec
t
io
n
Featu
r
e
s
elec
tio
n
in
clu
d
es
d
ete
r
m
in
in
g
th
e
m
o
s
t
r
elev
a
n
t
an
d
u
s
ef
u
l
ch
ar
ac
te
r
is
tics
f
r
o
m
t
h
e
ex
tr
ac
ted
im
ag
e
co
llectio
n
in
o
r
d
er
t
o
e
n
h
an
ce
th
e
m
o
d
el'
s
ef
f
icac
y
a
n
d
p
er
f
o
r
m
an
ce
.
I
t
is
a
cr
itica
l
p
r
o
ce
s
s
in
g
s
tep
in
d
is
ea
s
e
d
etec
tio
n
o
n
c
o
co
n
u
t t
r
ee
s
b
y
id
e
n
tify
in
g
an
d
r
etain
i
n
g
o
n
ly
th
e
m
o
s
t r
elev
an
t
attr
ib
u
tes f
r
o
m
th
e
d
ata.
T
h
e
d
etec
tio
n
s
y
s
tem
h
as
th
e
ab
ilit
y
to
f
o
cu
s
o
n
s
p
ec
ial
v
is
u
a
l
p
atter
n
s
an
d
b
io
m
ar
k
er
s
th
at
ar
e
s
y
m
p
to
m
ati
c
o
f
p
ar
ticu
lar
d
is
ea
s
es o
f
co
co
n
u
ts
.
I
n
th
is
,
th
e
r
eq
u
ir
e
d
f
ea
tu
r
es a
r
e
s
elec
ted
f
r
o
m
t
h
e
im
ag
e
d
a
taset u
s
in
g
GJOA
.
3
.
4
.
1
.
G
o
lden
j
a
c
k
a
l o
pti
m
iz
a
t
io
n a
lg
o
ri
t
hm
T
h
e
GJO
alg
o
r
ith
m
is
a
m
eta
-
h
eu
r
is
tic
o
p
tim
izatio
n
tech
n
i
q
u
e
th
at
is
b
ased
o
n
g
o
ld
en
jac
k
al
h
u
n
tin
g
b
eh
av
io
r
.
T
h
ese
cr
af
t
y
p
r
ed
ato
r
s
ar
e
k
n
o
w
n
f
o
r
th
eir
ab
ilit
y
to
ad
a
p
t
to
a
v
ar
iety
o
f
e
n
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
an
d
th
is
alg
o
r
ith
m
attem
p
ts
to
m
im
ic
th
eir
h
u
n
tin
g
a
p
p
r
o
ac
h
.
E
q
u
atio
n
(
3
)
illu
s
tr
ates
h
o
w
th
e
GJO
is
a
p
o
p
u
latio
n
-
b
ased
m
eth
o
d
th
at
,
lik
e
o
th
er
m
eta
-
h
e
u
r
is
tics
,
s
tar
ts
with
a
r
a
n
d
o
m
ize
d
d
is
tr
ib
u
tio
n
o
f
th
e
f
ir
s
t
an
s
wer
o
v
er
th
e
s
ea
r
ch
s
p
ac
e.
0
=
+
∗
−
(
3
)
w
h
er
e
is
th
e
Up
p
er
lim
it
an
d
is
th
e
lo
wer
lim
it,
an
d
r
an
d
in
d
icate
s
th
at
a
co
n
s
i
s
ten
tly
r
an
d
o
m
n
u
m
b
er
is
co
n
tain
ed
in
[
0
,
1
]
.
An
o
b
je
ctiv
e
f
u
n
ctio
n
d
ete
r
m
in
es
ea
ch
p
r
ey
'
s
f
itn
ess
v
alu
e
th
r
o
u
g
h
o
u
t
th
e
o
p
tim
izatio
n
p
h
ase.
T
h
e
f
itn
ess
v
alu
e
is
f
o
u
n
d
in
th
e
f
o
llo
win
g
(
4
)
.
=
[
ℱ
(
1
,
1
1
,
2
⋯
1
.
)
ℱ
(
2
,
1
2
,
2
⋯
2
,
)
⋮
ℱ
(
,
1
⋮
,
2
⋮
⋮
⋯
,
)
]
(
4
)
T
h
e
f
itn
ess
v
alu
es o
f
ev
er
y
p
r
ey
ar
e
co
llected
in
a
m
atr
ix
,
w
ith
th
e
F m
atr
ix
s
to
r
in
g
th
e
f
it
n
ess
v
alu
es
o
f
ea
ch
p
r
e
y
,
as
ex
p
lain
ed
i
n
(
4
)
.
,
d
en
o
tes
th
e
ℎ
d
im
en
s
io
n
v
al
u
e
o
f
th
e
ℎ
p
r
ey
.
T
h
e
m
ale
g
o
ld
en
jack
al
is
r
eg
ar
d
ed
as
th
e
m
o
s
t
s
u
ited
p
r
ey
in
its
h
u
n
tin
g
tactics,
with
th
e
f
e
m
ale
jack
al
co
m
in
g
i
n
s
ec
o
n
d
.
T
h
e
jack
al
p
air
o
b
tain
s
th
e
p
r
ey
'
s
p
lace
m
en
ts
b
y
in
s
tr
u
ctio
n
s
.
3
.
4
.
2
.
E
x
plo
ra
t
io
n
p
ha
s
e
I
n
GJO,
th
e
p
r
o
ce
s
s
o
f
ex
p
lo
r
in
g
is
ac
co
m
p
lis
h
ed
b
y
im
itatin
g
th
e
m
o
v
em
e
n
ts
o
f
a
p
ac
k
o
f
g
o
ld
e
n
jack
als
lo
o
k
in
g
f
o
r
f
o
o
d
in
an
u
n
k
n
o
wn
ter
r
ito
r
y
.
Alth
o
u
g
h
j
ac
k
als
ar
e
ca
p
ab
le
o
f
s
ee
in
g
a
n
d
s
in
g
in
g
th
eir
p
r
ey
,
th
e
p
r
e
y
o
cc
asio
n
ally
m
an
ag
e
s
to
escap
e
ca
p
tu
r
e
.
I
n
g
en
e
r
a
l,
a
m
ale
jack
al
lead
s
th
e
h
u
n
t,
with
th
e
f
em
ale
f
o
llo
win
g
in
h
is
wak
e:
1
(
ℎ
)
=
(
ℎ
)
−
|
(
ℎ
)
−
∗
(
ℎ
)
|
(
5
)
2
(
ℎ
)
=
(
ℎ
)
−
|
(
ℎ
)
−
∗
(
ℎ
)
|
(
6
)
wh
er
e
th
e
p
o
s
itio
n
v
ec
to
r
is
in
d
icate
d
b
y
p
r
e
y
(
ℎ
)
,
th
e
p
r
esen
t
ite
r
atio
n
s
ar
e
r
e
p
r
esen
ted
b
y
ℎ
,
an
d
th
e
m
ale
a
n
d
f
em
ale
jack
als'
lo
ca
tio
n
s
wi
th
in
th
e
s
ea
r
ch
ar
ea
ar
e
d
e
n
o
ted
b
y
(
ℎ
)
an
d
(
ℎ
)
r
esp
ec
tiv
ely
.
is
ca
lcu
lated
u
s
in
g
(
7
)
,
wh
ich
is
th
e
p
r
ey
'
s
escap
e
en
er
g
y
.
=
1
∗
0
(
7
)
wh
er
e
0
an
d
1
s
y
m
b
o
lize
th
e
b
eg
in
n
in
g
a
n
d
d
ec
r
ea
s
in
g
en
er
g
y
l
ev
els o
f
th
e
p
r
ey
,
r
esp
ec
tiv
ely
.
0
=
2
∗
−
1
(
8
)
1
=
1
∗
(
1
−
ℎ
|
)
(
9
)
T
h
e
r
a
n
d
o
m
n
u
m
b
e
r
i
n
t
h
i
s
c
a
s
e
i
s
b
e
tw
e
e
n
[
0
,
1
]
.
a
n
d
ℎ
a
n
d
s
t
a
n
d
f
o
r
t
h
e
c
u
r
r
e
n
t
i
t
e
r
a
t
i
o
n
a
n
d
m
a
x
i
m
u
m
i
t
e
r
at
i
o
n
,
r
es
p
e
c
t
i
v
ely
.
1
i
s
t
h
e
c
o
n
s
t
a
n
t
,
w
it
h
a
v
al
u
e
o
f
1
.
5
.
1
g
r
a
d
u
a
l
l
y
d
r
o
p
s
t
h
r
o
u
g
h
o
u
t
t
h
e
c
o
u
r
s
e
o
f
t
h
e
i
t
e
r
a
ti
o
n
s
,
f
r
o
m
1
.
5
t
o
0
.
E
v
e
n
t
u
a
l
l
y
,
t
h
e
g
o
l
d
e
n
j
a
c
k
al'
s
m
o
s
t
r
e
c
e
n
t
l
o
c
a
t
i
o
n
is
es
t
a
b
li
s
h
e
d
t
o
b
e
(
1
0
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
40
7
-
41
7
412
(
ℎ
+
1
)
=
1
(
ℎ
)
+
2
(
ℎ
)
2
(
1
0
)
E
q
u
a
t
i
o
n
(
1
1
)
r
e
p
r
e
s
e
n
t
s
t
h
e
m
a
l
e
a
n
d
f
e
m
a
l
e
ja
c
k
a
ls
'
m
o
s
t
r
ec
e
n
t
p
o
s
i
ti
o
n
s
b
as
e
d
o
n
t
h
e
a
v
er
a
g
e
s
o
f
(
6
)
a
n
d
(
7
)
.
3
.
4
.
3
.
E
x
plo
it
a
t
io
n
p
ha
s
e
T
h
e
p
r
ey
f
o
u
n
d
in
t
h
e
p
r
ev
io
u
s
p
h
ase
is
s
u
r
r
o
u
n
d
ed
b
y
th
e
jack
al
c
o
u
p
les
f
o
llo
win
g
th
ei
r
ab
ilit
y
t
o
f
lee.
T
h
e
y
s
u
r
r
o
u
n
d
t
h
eir
v
ictim
,
th
en
ju
m
p
o
n
it
to
ea
t
it.
T
o
g
et
h
er
with
th
e
m
ale
a
n
d
f
em
ale
jack
als,
th
e
m
ath
em
atica
l e
x
p
r
ess
io
n
f
o
r
t
h
is
h
u
n
tin
g
ac
tiv
ity
is
:
1
(
ℎ
)
=
(
ℎ
)
−
.
|
.
(
ℎ
)
−
(
ℎ
)
|
(
1
1
)
2
(
ℎ
)
=
(
ℎ
)
−
.
|
.
(
ℎ
)
−
(
ℎ
)
|
(
1
2
)
I
n
o
r
d
er
to
em
p
h
asize
ex
p
l
o
r
a
tio
n
an
d
p
r
ev
e
n
t
lo
ca
l
o
p
tim
u
m
,
th
e
g
o
al
o
f
in
(
1
1
)
a
n
d
(
1
2
)
ar
e
to
g
e
n
er
ate
r
an
d
o
m
b
eh
a
v
io
u
r
d
u
r
i
n
g
th
e
ex
p
lo
itatio
n
p
h
ase.
3
.
5
.
Cla
s
s
if
ica
t
io
n
T
h
e
p
r
o
ce
s
s
o
f
ca
te
g
o
r
izatio
n
en
tails
th
e
ar
r
an
g
em
e
n
t
o
f
d
a
ta
p
o
in
ts
in
to
d
is
cr
ete
g
r
o
u
p
s
o
r
class
es
ac
co
r
d
in
g
to
s
p
ec
if
ic
f
ea
tu
r
e
s
o
r
attr
ib
u
tes.
C
o
co
n
u
t
tr
ee
d
is
ea
s
e
class
if
icatio
n
in
v
o
lv
e
s
ca
teg
o
r
izatio
n
o
f
v
ar
io
u
s
d
is
ea
s
es a
f
f
ec
tin
g
co
c
o
n
u
t tr
ee
s
b
ased
o
n
v
is
u
al
s
y
m
p
to
m
s
.
I
n
th
is
class
if
icatio
n
p
r
o
ce
s
s
,
th
e
d
is
ea
s
es
o
n
th
e
co
co
n
u
t
tr
ee
s
ar
e
class
if
ied
b
y
th
e
DB
N
class
if
ier
.
I
t
im
p
r
o
v
es
r
ec
o
g
n
itio
n
p
er
f
o
r
m
an
ce
b
y
h
a
n
d
lin
g
co
m
p
lex
,
n
o
n
lin
ea
r
d
ata
a
n
d
r
ed
u
cin
g
class
if
icatio
n
er
r
o
r
s
in
co
co
n
u
t d
is
ea
s
e
d
etec
tio
n
ta
s
k
s
.
3
.
5
.
1
.
DB
N
A
p
ar
ticu
lar
s
o
r
t o
f
g
e
n
er
ativ
e
m
o
d
el
ca
lled
a
d
ee
p
b
elief
n
etwo
r
k
(
DB
N)
m
a
k
es u
s
e
in
cl
u
d
es sev
er
al
p
r
o
ce
s
s
in
g
lay
er
s
to
ex
tr
ac
t in
t
r
icate
s
tr
u
ctu
r
es a
n
d
ab
s
tr
ac
tio
n
s
f
r
o
m
in
p
u
t.
A
s
tack
o
f
m
u
lt
ip
le
in
d
ep
en
d
en
tly
tr
ain
ed
r
estricte
d
B
o
ltzm
an
n
m
ac
h
in
es
(
R
B
Ms)
m
ak
es
u
p
t
h
e
s
y
s
tem
.
T
h
e
n
etwo
r
k
'
s
v
is
ib
le
lay
er
(
)
is
f
o
r
m
e
d
u
p
o
f
a
n
en
o
r
m
o
u
s
n
u
m
b
er
o
f
o
b
s
er
v
a
b
le
en
titi
es
(
1
,
2
,
…
…
.
)
,
wh
ich
ar
e
tau
g
h
t
u
s
in
g
th
e
u
n
lab
ele
d
p
atter
n
s
tr
u
ctu
r
es
th
at
wer
e
p
r
o
v
id
ed
to
it,
an
d
s
ev
e
r
al
in
v
is
ib
le
b
ein
g
s
(
1
,
2
…
…
)
.
Netwo
r
k
n
o
d
es
th
at
ar
e
n
o
t
v
is
ib
le
h
a
v
e
b
in
ar
y
v
alu
es
an
d
ca
n
r
e
b
u
ild
p
atter
n
s
b
y
r
e
ce
iv
in
g
in
f
o
r
m
atio
n
f
r
o
m
v
is
ib
le
n
o
d
es
(
)
.
As
a
two
-
way
weig
h
t
m
atr
ix
t
h
at
is
s
y
m
m
etr
ic
(
)
,
all
th
e
o
b
v
io
u
s
n
o
d
es
co
m
m
u
n
icate
with
all
t
h
e
o
th
e
r
o
b
v
io
u
s
n
o
d
es in
ad
d
itio
n
to
t
h
e
p
r
ee
x
i
s
tin
g
b
iases
(
)
an
d
(
).
(
,
)
=
∑
(
−
)
2
2
2
−
∈
∑
∈
−
∑
(
1
3
)
wh
er
e
λ
is
th
e
Gau
s
s
ian
n
o
is
e
d
is
p
er
s
io
n
in
t
h
e
ℎ
v
is
ib
le
d
im
e
n
s
io
n
.
I
f
b
o
th
th
e
ex
p
o
s
ed
an
d
h
id
d
e
n
u
n
its
ar
e
Gau
s
s
ian
s
,
th
e
lear
n
in
g
g
r
a
d
ie
n
t m
ig
h
t in
cr
ea
s
e.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Plan
t
p
ath
o
lo
g
y
f
r
o
m
Kag
g
le
d
atasets
[
2
5
]
p
r
o
v
id
e
a
wid
e
s
elec
tio
n
o
f
e
x
ce
llen
t
im
ag
es
d
ep
ictin
g
p
lan
t
leav
es
with
v
ar
i
o
u
s
d
is
e
ases
.
T
h
ese
d
atab
ases
ar
e
ess
en
tial
f
o
r
c
r
ea
tin
g
a
n
d
r
ef
in
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
th
at
au
to
m
ate
p
la
n
t
d
is
ea
s
e
id
en
tific
atio
n
an
d
d
iag
n
o
s
is
.
Fig
u
r
e
4
d
escr
ib
es
th
e
ex
p
er
im
en
tal
class
if
icatio
n
r
esu
lt o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
eth
o
d
.
C
o
lu
m
n
1
d
escr
ib
es th
e
in
p
u
t i
m
ag
e.
T
h
e
en
h
an
ce
d
im
ag
es
o
f
t
h
e
co
c
o
n
u
t
tr
ee
a
r
e
d
is
p
lay
ed
in
c
o
lu
m
n
2
.
T
h
e
s
eg
m
en
ted
im
ag
es
if
t
h
e
co
c
o
n
u
t
tr
ee
is
s
h
o
wn
in
co
lu
m
n
3
.
C
o
lu
m
n
4
d
is
p
lay
s
th
e
f
ea
t
u
r
e
e
x
tr
ac
ted
im
a
g
e
a
n
d
f
i
n
ally
th
e
class
if
icatio
n
r
e
s
u
lt
o
f
th
e
co
co
n
u
t
tr
ee
d
is
ea
s
e
ar
e
s
h
o
wn
in
co
l
u
m
n
4.
4
.
1
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
T
h
e
ev
alu
atio
n
m
et
r
ics
m
en
tio
n
ed
p
r
ev
io
u
s
ly
d
escr
ib
ed
ca
n
b
e
g
en
er
ate
d
with
s
im
p
le
p
ar
am
eter
s
s
u
ch
as
tr
u
e
p
o
s
itiv
e
(
)
,
tr
u
e
n
e
g
ativ
e
(
)
,
f
alse p
o
s
itiv
e
(
)
,
an
d
f
alse n
eg
ativ
e
(
).
=
+
+
+
+
×
100
(
1
4
)
=
+
(
1
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
Dis
ea
s
e
d
etec
tio
n
o
n
co
c
o
n
u
t t
r
ee
u
s
in
g
g
o
ld
en
ja
ck
a
l
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
(
A
r
u
n
R
a
ma
i
a
h
)
413
=
+
(
1
6
)
T
h
e
ef
f
ec
tiv
e
n
ess
ev
alu
atio
n
o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
in
clu
d
in
g
n
o
r
m
al
an
d
a
b
n
o
r
m
al
is
d
escr
ib
ed
in
th
e
T
a
b
le
1
.
Acc
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
ar
e
u
s
ed
to
ca
lcu
late
p
e
r
f
o
r
m
an
ce
.
T
h
e
p
r
o
p
o
s
ed
GOD
-
C
O
C
O
ar
ch
iv
es
an
ac
cu
r
ac
y
r
ate
o
f
9
9
.
3
4
%
in
th
e
n
o
r
m
al
class
es
an
d
9
9
.
2
8
%
in
th
e
ab
n
o
r
m
al
class
es.
Ad
d
itio
n
ally
,
th
e
p
r
o
p
o
s
ed
G
OD
-
C
OC
O
ar
ch
iv
es a
p
r
ec
is
io
n
an
d
r
ec
all
r
ate
o
f
9
8
.
6
3
% a
n
d
9
9
.
1
9
% in
n
o
r
m
al
class
es
an
d
9
8
.
5
7
%
an
d
9
9
.
0
8
%
in
th
e
ab
n
o
r
m
al
cl
ass
es.
T
h
e
p
er
f
o
r
m
an
ce
ev
alu
atio
n
o
f
th
e
p
r
o
p
o
s
ed
GOD
C
OC
O
ap
p
r
o
ac
h
is
s
h
o
wn
i
n
Fig
u
r
e
5
.
T
h
e
d
etec
tio
n
ac
c
u
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
o
d
el
with
1
0
0
tr
ain
in
g
ep
o
ch
s
was 9
9
.
4
8
,
an
d
it h
ad
a
l
o
w
r
ate
o
f
er
r
o
r
s
.
Fig
u
r
e
4
.
Simu
latio
n
r
esu
lt o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
e
th
o
d
T
ab
le
1
.
E
v
alu
atio
n
o
u
tco
m
e
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
C
l
a
s
ses
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
N
o
r
mal
9
9
.
3
4
%
9
8
.
6
3
%
9
9
.
1
9
%
A
b
n
o
r
ma
l
9
9
.
2
8
%
9
8
.
5
7
%
9
9
.
0
8
%
Fig
u
r
e
5
.
Per
f
o
r
m
an
c
e
ev
alu
at
io
n
o
f
t
h
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
40
7
-
41
7
414
I
n
Fig
u
r
e
6
,
th
e
ac
cu
r
ac
y
g
r
ap
h
was
g
en
er
ated
u
s
in
g
1
0
0
ep
o
ch
s
an
d
an
ac
cu
r
ac
y
r
a
n
g
e.
T
h
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
s
im
ilar
ly
im
p
r
o
v
es
as
th
e
n
u
m
b
er
o
f
ep
o
ch
s
r
is
es.
Fig
u
r
e
7
d
escr
ib
es
th
e
ep
o
ch
an
d
lo
s
s
g
r
ap
h
o
f
th
e
p
r
o
p
o
s
ed
GOD
C
OC
O
m
eth
o
d
.
T
o
ac
h
iev
e
o
p
tim
al
ac
cu
r
ac
y
f
o
r
test
in
g
in
th
is
s
tu
d
y
.
T
h
e
d
etec
tio
n
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
o
d
el
with
1
0
0
tr
ain
in
g
ep
o
ch
s
was
9
9
.
4
8
,
an
d
it
h
a
d
a
l
o
w
r
ate
o
f
er
r
o
r
s
.
Fig
u
r
e
6
.
Acc
u
r
ac
y
g
r
ap
h
o
f
t
h
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
eth
o
d
Fig
u
r
e
7
.
L
o
s
s
o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
O
C
O
m
eth
o
d
4
.
1
.
1
.
T
im
e
ef
f
iciency
T
im
e
tak
en
to
d
etec
t
th
e
d
is
ea
s
e
in
th
e
co
co
n
u
t
tr
ee
u
s
in
g
b
o
th
th
e
p
r
o
p
o
s
ed
an
d
th
e
ex
is
tin
g
m
eth
o
d
s
is
d
escr
ib
ed
in
Fig
u
r
e
8
.
T
h
e
p
er
f
o
r
m
a
n
ce
lev
els
ar
e
in
d
icate
d
o
n
th
e
v
er
tical
ax
is
,
wh
ile
th
e
ev
alu
ated
m
eth
o
d
s
ar
e
p
r
esen
ted
o
n
th
e
h
o
r
izo
n
tal
ax
is
.
T
h
e
p
r
o
p
o
s
ed
GOD
-
C
O
C
O
m
eth
o
d
tak
en
less
tim
e
f
o
r
co
co
n
u
t
tr
ee
d
is
ea
s
e
d
etec
tio
n
th
a
n
t
h
e
e
x
is
tin
g
te
ch
n
iq
u
es.
I
t
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
o
d
el
t
ak
es
less
tim
e
1
.
1
3
m
illi
s
ec
o
n
d
s
to
d
etec
t
th
e
d
is
ea
s
e
th
an
t
h
e
e
x
is
tin
g
m
eth
o
d
s
wh
ich
tak
e
3
.
0
4
,
2
.
5
a
n
d
2
.
6
7
m
illi
s
ec
o
n
d
s
to
d
etec
t
th
e
d
is
ea
s
e.
Fig
u
r
e
8
.
C
o
m
p
a
r
is
o
n
o
f
tim
e
ef
f
icien
cy
4
.
1
.
2
.
Co
m
pa
r
a
t
iv
e
a
na
ly
s
is
T
h
e
co
m
p
ar
is
o
n
a
n
aly
s
is
o
f
e
x
is
tin
g
m
eth
o
d
s
with
t
h
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
is
d
escr
ib
ed
in
th
e
T
a
b
le
2
.
T
h
e
ac
cu
r
ac
y
r
atin
g
o
f
9
9
.
3
1
%
ac
h
iev
ed
b
y
th
e
s
u
g
g
ested
GOD
-
C
OC
O
is
h
ig
h
er
th
an
th
at
o
f
th
e
cu
r
r
en
t
tech
n
iq
u
es.
I
n
t
h
is
,
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
ac
h
iev
es
an
o
v
er
all
ac
cu
r
ac
y
r
ate
o
f
0
.
7
7
%,
0
.
3
1
%
an
d
1
.
1
7
%
o
v
er
th
e
e
x
is
tin
g
m
eth
o
d
s
s
u
ch
as AI
E
-
C
T
DDC,
DL
-
W
DM
an
d
C
L
S,
r
esp
ec
tiv
ely
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
Dis
ea
s
e
d
etec
tio
n
o
n
co
c
o
n
u
t t
r
ee
u
s
in
g
g
o
ld
en
ja
ck
a
l
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
(
A
r
u
n
R
a
ma
i
a
h
)
415
4
.
2
.
Dis
cus
s
io
n
I
n
th
is
s
ec
tio
n
,
th
e
co
m
p
ar
is
o
n
ev
alu
atio
n
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
n
r
esu
lts
is
d
escr
ib
ed
.
Fig
u
r
e
1
d
escr
ib
es
th
e
d
is
ea
s
es
th
at
af
f
ec
t
co
co
n
u
t
tr
ee
s
in
v
a
r
io
u
s
c
o
u
n
tr
ies.
T
h
e
ex
p
e
r
im
en
tal
cl
ass
if
icatio
n
r
esu
lt
o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
m
eth
o
d
is
d
escr
ib
ed
in
Fig
u
r
e
4
.
Fig
u
r
e
5
d
escr
ib
es
t
h
e
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
o
f
th
e
p
r
o
p
o
s
ed
GOD
C
OC
O
m
eth
o
d
.
T
h
e
ac
cu
r
ac
y
an
d
lo
s
s
g
r
ap
h
with
1
0
0
tr
ai
n
in
g
ep
o
ch
s
attain
h
ig
h
est
ac
cu
r
ac
y
o
f
9
9
.
4
8
%.
T
h
e
tim
e
ef
f
icien
cy
co
m
p
ar
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
in
b
o
th
th
e
p
r
o
p
o
s
ed
a
n
d
th
e
ex
is
tin
g
m
eth
o
d
s
is
d
escr
ib
ed
in
Fig
u
r
e
8
.
Fin
ally
,
th
e
co
m
p
ar
is
o
n
an
aly
s
is
o
f
ex
is
tin
g
m
eth
o
d
s
with
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
i
s
d
esc
r
ib
ed
in
th
e
T
ab
le
2
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
ex
is
tin
g
m
eth
o
d
with
p
r
o
p
o
s
ed
m
eth
o
d
M
e
t
h
o
d
s
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
A
I
E
-
C
TD
D
C
[
2
0
]
9
8
.
5
4
%
9
7
.
4
8
%
9
7
.
2
1
%
DL
-
W
D
M
[
2
2
]
9
9
.
0
0
%
9
8
.
1
9
%
9
8
.
8
2
%
C
LS [
2
3
]
9
8
.
1
4
%
9
7
.
5
7
%
9
7
.
4
9
%
GOD
-
C
O
C
O
(
P
r
o
p
o
se
d
met
h
o
d
)
9
9
.
3
1
%
9
8
.
6
1
%
9
9
.
1
3
%
5.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
e
r
,
a
n
o
v
el
g
o
ld
en
j
ac
k
al
o
p
tim
ized
d
is
ea
s
e
d
etec
tio
n
in
C
OC
On
u
t
tr
ee
(
GOD
-
C
OC
O)
h
as
b
ee
n
p
r
o
p
o
s
ed
f
o
r
d
etec
tin
g
d
i
s
ea
s
es
in
co
co
n
u
t tr
ee
s
.
First,
t
h
e
in
p
u
t d
ataset
im
ag
es a
r
e
p
r
e
-
p
r
o
ce
s
s
ed
in
p
r
e
-
p
r
o
ce
s
s
in
g
im
ag
e
r
o
tatio
n
,
im
ag
e
r
escalin
g
,
an
d
im
ag
e
r
esizin
g
,
an
d
th
e
en
h
an
ce
d
im
a
g
e
s
ar
e
g
ath
er
ed
.
T
h
e
en
h
an
ce
d
im
a
g
es
ar
e
s
eg
m
en
ted
u
s
in
g
th
e
PS
P
-
Net.
Fro
m
t
h
e
s
eg
m
en
ted
im
ag
es,
th
e
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
u
s
in
g
th
e
Den
s
e
-
Net.
T
h
en
th
e
f
ea
tu
r
es
n
ee
d
ed
ar
e
s
elec
ted
u
s
in
g
th
e
Go
ld
en
J
ac
k
al
Op
tim
izatio
n
alg
o
r
ith
m
.
Fin
ally
,
th
e
DB
N
class
if
ier
class
if
ies
wh
eth
er
it
is
n
o
r
m
al
o
r
a
b
n
o
r
m
al.
T
h
e
ex
p
e
r
im
en
tal
an
aly
s
is
o
f
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
h
as
b
ee
n
ev
alu
ated
u
s
in
g
th
e
Plan
t
p
at
h
o
lo
g
y
d
atasets
b
ased
o
n
th
e
a
cc
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
p
r
ec
is
io
n
s
tan
d
ar
d
s
.
B
y
th
is
,
th
e
p
r
o
p
o
s
ed
GOD
-
C
OC
O
ac
h
iev
es
an
ac
cu
r
ac
y
r
at
e
o
f
9
9
.
3
1
%
an
d
it
ac
h
iev
es
an
o
v
er
all
ac
cu
r
ac
y
r
ate
o
f
0
.
7
7
%,
0
.
3
1
%,
a
n
d
1
.
1
7
%
b
y
th
e
ex
is
tin
g
m
eth
o
d
s
s
u
c
h
as
AI
E
-
C
T
DDC,
DL
-
W
DM
,
an
d
C
L
S.
Fu
tu
r
e
r
e
s
ea
r
ch
an
d
d
ev
elo
p
m
en
t
ef
f
o
r
t
s
s
h
o
u
ld
b
e
g
u
id
e
d
b
y
an
e
v
alu
atio
n
o
f
t
h
e
m
o
d
el'
s
im
p
ac
t o
n
c
o
co
n
u
t f
ar
m
in
g
m
e
th
o
d
s
an
d
its
p
o
te
n
tial to
co
n
tr
ib
u
te
to
th
e
in
d
u
s
tr
y
'
s
s
u
s
tain
a
b
ilit
y
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
w
o
u
ld
lik
e
to
ex
p
r
ess
h
is
h
ea
r
tf
elt
g
r
atitu
d
e
to
th
e
s
u
p
er
v
is
o
r
f
o
r
h
is
g
u
i
d
an
ce
an
d
u
n
wav
er
in
g
s
u
p
p
o
r
t d
u
r
in
g
t
h
is
r
esear
ch
f
o
r
h
is
g
u
id
an
ce
an
d
s
u
p
p
o
r
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
Fin
an
cial
s
u
p
p
o
r
t.
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
Ar
u
n
R
am
aiah
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Mu
th
u
s
am
y
Sh
u
n
m
u
g
at
h
am
m
al
✓
✓
✓
✓
✓
✓
✓
✓
Har
i K
r
is
h
n
a
Kalid
in
d
i
✓
✓
✓
✓
✓
✓
✓
✓
An
is
h
Po
n
Yam
in
i
Ku
m
ar
eso
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
T
h
e
au
t
h
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
e
p
o
r
te
d
in
t
h
is
p
ap
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
14
,
No
.
3
,
Sep
tem
b
er
20
25
:
40
7
-
41
7
416
I
NF
O
RM
E
D
CO
NS
E
N
T
I
ce
r
tify
th
at
I
h
av
e
ex
p
lain
ed
t
h
e
n
atu
r
e
an
d
p
u
r
p
o
s
e
o
f
th
is
s
tu
d
y
to
th
e
ab
o
v
e
-
n
am
ed
in
d
iv
id
u
al,
an
d
I
h
av
e
d
is
cu
s
s
ed
th
e
p
o
ten
tial
b
en
ef
its
o
f
th
is
s
tu
d
y
p
ar
ticip
a
tio
n
.
T
h
e
q
u
esti
o
n
s
th
e
in
d
i
v
id
u
al
h
a
d
ab
o
u
t
th
is
s
tu
d
y
h
av
e
b
ee
n
a
n
s
wer
ed
,
an
d
we
will a
lway
s
b
e
av
ailab
le
to
ad
d
r
ess
f
u
tu
r
e
q
u
esti
o
n
s
.
E
T
H
I
CAL AP
P
RO
V
AL
My
r
esear
ch
g
u
id
e
r
e
v
iewe
d
a
n
d
eth
ically
ap
p
r
o
v
ed
th
is
m
a
n
u
s
cr
ip
t f
o
r
p
u
b
lis
h
in
g
in
th
is
jo
u
r
n
al
.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
s
h
ar
in
g
is
n
o
t
ap
p
licab
l
e
to
th
is
ar
ticle
as
n
o
d
atasets
we
r
eg
en
er
ated
o
r
an
aly
ze
d
d
u
r
in
g
th
e
cu
r
r
en
t stu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
S
a
n
t
h
i
a
n
d
S
.
M
.
Ti
r
t
h
a
,
“
D
e
s
i
g
n
a
n
d
d
e
v
e
l
o
p
me
n
t
o
f
c
o
c
o
n
u
t
t
r
e
e
d
i
sea
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
s
i
n
En
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
(
I
J
A
EM
)
,
v
o
l
.
5
,
n
o
.
6
,
p
.
3
1
9
,
2
0
2
3
,
d
o
i
:
1
0
.
3
5
6
2
9
/
5
2
5
2
-
0
5
0
6
3
1
9
3
2
4
.
[
2
]
N
.
B
h
a
v
a
n
a
,
M
.
M
.
K
o
d
a
b
a
g
i
,
B
.
M
.
K
u
m
a
r
,
P
.
A
j
a
y
,
N
.
M
u
t
h
u
k
u
m
a
r
a
n
,
a
n
d
A
.
A
h
i
l
a
n
,
“
P
O
T
-
Y
O
LO
:
r
e
a
l
-
t
i
me
r
o
a
d
p
o
t
h
o
l
e
s
d
e
t
e
c
t
i
o
n
u
si
n
g
e
d
g
e
se
g
me
n
t
a
t
i
o
n
b
a
sed
Y
o
l
o
V
8
n
e
t
w
o
r
k
,
”
I
E
EE
S
e
n
s
o
rs
J
o
u
r
n
a
l
,
v
o
l
.
2
4
,
n
o
.
1
5
,
p
p
.
2
4
8
0
2
–
2
4
8
0
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
4
.
3
3
9
9
0
0
8
.
[
3
]
P
.
R
.
D
e
S
i
l
v
a
,
C
.
N
.
P
e
r
e
r
a
,
B
.
W
.
B
a
h
d
e
r
,
a
n
d
R
.
N
.
A
t
t
a
n
a
y
a
k
e
,
“
N
e
s
t
e
d
P
C
R
-
b
a
s
e
d
r
a
p
i
d
d
e
t
e
c
t
i
o
n
o
f
p
h
y
t
o
p
l
a
sm
a
l
e
a
f
w
i
l
t
d
i
s
e
a
se
o
f
c
o
c
o
n
u
t
i
n
S
r
i
La
n
k
a
a
n
d
sy
s
t
e
m
i
c
m
o
v
e
me
n
t
o
f
t
h
e
p
a
t
h
o
g
e
n
,
”
P
a
t
h
o
g
e
n
s
,
v
o
l
.
1
2
,
n
o
.
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
p
a
t
h
o
g
e
n
s
1
2
0
2
0
2
9
4
.
[
4
]
S
.
C
a
r
o
l
i
n
e
,
V
.
S
r
i
,
a
n
d
L.
H
a
r
s
h
i
t
h
a
,
“
D
e
e
p
-
F
i
r
:
d
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
b
u
t
t
e
r
f
l
y
o
p
t
i
mi
z
e
d
r
e
g
r
e
ss
i
o
n
n
e
t
w
o
r
k
f
o
r
f
a
s
t
i
ma
g
e
r
e
t
r
i
e
v
a
l
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
a
t
a
S
c
i
e
n
c
e
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
D
S
AI
)
,
v
o
l
.
0
2
.
[
5
]
B
.
M
.
K
u
mar
a
n
d
T.
K
.
K
u
n
h
a
mu
,
“
N
a
t
u
r
e
-
b
a
se
d
s
o
l
u
t
i
o
n
s
i
n
a
g
r
i
c
u
l
t
u
r
e
:
A
r
e
v
i
e
w
o
f
t
h
e
c
o
c
o
n
u
t
(
C
o
c
o
s
n
u
c
i
f
e
r
a
L.
)
-
b
a
s
e
d
f
a
r
mi
n
g
s
y
s
t
e
ms
i
n
K
e
r
a
l
a
,
‘
t
h
e
l
a
n
d
o
f
c
o
c
o
n
u
t
t
r
e
e
s,’”
N
a
t
u
re
-
B
a
se
d
S
o
l
u
t
i
o
n
s
,
v
o
l
.
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
b
sj
.
2
0
2
2
.
1
0
0
0
1
2
.
[
6
]
P
.
J.
S
h
e
r
m
i
l
a
,
A
.
A
h
i
l
a
n
,
A
.
J.
G
.
M
a
l
a
r
,
a
n
d
R
.
J
o
t
h
i
n
,
“
M
D
E
EPF
I
C
:
F
o
o
d
i
t
e
m
c
l
a
ss
i
f
i
c
a
t
i
o
n
w
i
t
h
c
a
l
o
r
i
e
c
a
l
c
u
l
a
t
i
o
n
u
si
n
g
mo
d
i
f
i
e
d
d
r
a
g
o
n
f
l
y
d
e
e
p
l
e
a
r
n
i
n
g
n
e
t
w
o
r
k
,
”
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
a
n
d
F
u
zzy
S
y
s
t
e
m
s
,
v
o
l
.
4
5
,
n
o
.
2
,
p
p
.
3
1
3
7
–
3
1
4
8
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
3
3
/
JI
F
S
-
2
3
0
1
9
3
.
[
7
]
S
.
T
h
i
t
e
,
Y
.
S
u
r
y
a
w
a
n
s
h
i
,
K
.
P
a
t
i
l
,
a
n
d
P
.
C
h
u
mc
h
u
,
“
C
o
c
o
n
u
t
(
C
o
c
o
s
n
u
c
i
f
e
r
a
)
t
r
e
e
d
i
s
e
a
s
e
d
a
t
a
s
e
t
:
A
d
a
t
a
s
e
t
f
o
r
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s,
”
D
a
t
a
i
n
Bri
e
f
,
v
o
l
.
5
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
i
b
.
2
0
2
3
.
1
0
9
6
9
0
.
[
8
]
E.
F
e
n
i
l
,
G
.
M
a
n
o
g
a
r
a
n
,
G
.
N
.
V
i
v
e
k
a
n
a
n
d
a
,
T
.
T
h
a
n
j
a
i
v
a
d
i
v
e
l
,
S
.
Jee
v
a
,
a
n
d
A
.
A
h
i
l
a
n
,
“
R
e
a
l
t
i
m
e
v
i
o
l
e
n
c
e
d
e
t
e
c
t
i
o
n
f
r
a
mew
o
r
k
f
o
r
f
o
o
t
b
a
l
l
s
t
a
d
i
u
m
c
o
m
p
r
i
s
i
n
g
o
f
b
i
g
d
a
t
a
a
n
a
l
y
s
i
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
h
r
o
u
g
h
b
i
d
i
r
e
c
t
i
o
n
a
l
LST
M
,
”
C
o
m
p
u
t
e
r
N
e
t
w
o
r
k
s
,
v
o
l
.
1
5
1
,
p
p
.
1
9
1
–
2
0
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mn
e
t
.
2
0
1
9
.
0
1
.
0
2
8
[
9
]
D
.
M
.
N
.
S
.
D
i
ssa
n
a
y
a
k
a
,
D
.
K
.
R
.
P
.
L.
D
i
ss
a
n
a
y
a
k
e
,
S
.
S
.
U
d
u
ma
n
n
,
T
.
D
.
N
u
w
a
r
a
p
a
k
s
h
a
,
a
n
d
A
.
J
.
A
t
a
p
a
t
t
u
,
“
A
g
r
o
f
o
r
e
st
r
y
—
a
k
e
y
t
o
o
l
i
n
t
h
e
c
l
i
ma
t
e
-
sm
a
r
t
a
g
r
i
c
u
l
t
u
r
e
c
o
n
t
e
x
t
:
a
r
e
v
i
e
w
o
n
c
o
c
o
n
u
t
c
u
l
t
i
v
a
t
i
o
n
i
n
S
r
i
La
n
k
a
,
”
Fr
o
n
t
i
e
rs
i
n
A
g
ro
n
o
m
y
,
v
o
l
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
a
g
r
o
.
2
0
2
3
.
1
1
6
2
7
5
0
.
[
1
0
]
D
.
N
e
sara
j
a
n
,
L
.
K
u
n
a
l
a
n
,
M
.
L
o
g
e
sw
a
r
a
n
,
S
.
K
a
s
t
h
u
r
i
a
r
a
c
h
c
h
i
,
a
n
d
D
.
Lu
n
g
a
l
a
g
e
,
“
C
o
c
o
n
u
t
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
s
y
st
e
m
u
si
n
g
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
i
n
4
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
m
a
g
e
Pr
o
c
e
ssi
n
g
,
Ap
p
l
i
c
a
t
i
o
n
s
a
n
d
S
y
st
e
m
s
,
I
PA
S
2
0
2
0
,
2
0
2
0
,
p
p
.
2
1
2
–
2
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
P
A
S
5
0
0
8
0
.
2
0
2
0
.
9
3
3
4
9
3
4
.
[
1
1
]
P
.
B
a
l
a
m
u
r
u
g
a
n
a
n
d
R
.
R
a
j
e
s
h
,
“
N
e
u
r
a
l
n
e
t
w
o
r
k
b
a
s
e
d
s
y
st
e
m
f
o
r
t
h
e
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
l
e
a
f
r
o
t
d
i
se
a
se
i
n
C
o
c
o
s
N
u
c
i
f
e
r
a
Tr
e
e
l
e
a
v
e
s
,
”
Eu
r
o
p
e
a
n
J
o
u
rn
a
l
o
f
S
c
i
e
n
t
i
f
i
c
Re
s
e
a
rc
h
,
v
o
l
.
8
8
,
n
o
.
1
,
p
p
.
1
3
7
–
1
4
5
,
2
0
1
2
.
[
1
2
]
A
.
S
h
a
r
ma
,
N
.
K
.
Tr
i
v
e
d
i
,
a
n
d
A
.
K
.
S
h
a
r
ma
,
“
D
i
s
e
a
s
e
c
a
t
e
g
o
r
i
z
a
t
i
o
n
a
n
d
e
a
r
l
y
d
e
t
e
c
t
i
o
n
i
n
c
o
c
o
n
u
t
l
e
a
v
e
s
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
,
p
p
.
1
5
6
–
1
6
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
3
2
7
0
0
5
0
2
-
2
5
.
[
1
3
]
S
.
S
u
b
b
a
i
a
n
,
A
.
B
a
l
a
s
u
b
r
a
ma
n
i
a
n
,
M
.
M
a
r
i
mu
t
h
u
,
S
.
C
h
a
n
d
r
a
se
k
a
r
a
n
,
a
n
d
G
.
M
u
t
h
u
sar
a
v
a
n
a
n
,
“
D
e
t
e
c
t
i
o
n
o
f
c
o
c
o
n
u
t
l
e
a
f
d
i
se
a
ses
u
si
n
g
e
n
h
a
n
c
e
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
J
o
u
rn
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
a
n
d
Fu
z
zy
S
y
s
t
e
m
s
,
v
o
l
.
4
6
,
n
o
.
2
,
p
p
.
5
0
3
3
–
5
0
4
5
,
2
0
2
4
,
d
o
i
:
1
0
.
3
2
3
3
/
JI
F
S
-
2
3
3
8
3
1
.
[
1
4
]
S
.
B
h
a
r
a
t
h
i
,
a
n
d
P
.
H
a
r
i
n
i
,
"
E
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
d
i
sea
s
e
s i
n
c
o
c
o
n
u
t
t
r
e
e
l
e
a
v
e
s
,"
I
n
2
0
2
0
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s (I
C
AC
C
S
)
,
p
p
.
1
2
6
5
-
1
2
6
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
C
S
4
8
7
0
5
.
2
0
2
0
.
9
0
7
4
3
5
7
[
1
5
]
X
.
H
u
a
n
g
,
M
.
M
.
A
l
o
b
a
e
d
y
,
Y
.
F
a
z
e
a
,
S
.
B
.
G
o
y
a
l
,
a
n
d
Z
.
D
e
n
g
,
"
D
i
se
a
s
e
i
n
f
e
c
t
i
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
c
o
c
o
n
u
t
t
r
e
e
b
a
se
d
o
n
a
n
e
n
h
a
n
c
e
d
v
i
su
a
l
g
e
o
met
r
y
g
r
o
u
p
m
o
d
e
l
,"
P
r
o
c
e
sses,
v
o
l
.
13
,
n
o
.
3
,
p
p.
689
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
p
r
1
3
0
3
0
6
8
9
[
1
6
]
D
.
R
.
R
a
m
j
i
,
C
.
A
.
P
a
l
a
g
a
n
,
A
.
N
i
t
h
y
a
,
A
.
A
p
p
a
t
h
u
r
a
i
,
a
n
d
E.
J.
A
l
e
x
,
“
S
o
f
t
c
o
m
p
u
t
i
n
g
b
a
se
d
c
o
l
o
r
i
ma
g
e
d
e
mo
s
a
i
c
i
n
g
f
o
r
me
d
i
c
a
l
I
mag
e
p
r
o
c
e
ss
i
n
g
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
7
9
,
n
o
.
1
5
–
1
6
,
p
p
.
1
0
0
4
7
–
1
0
0
6
3
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
1
9
-
0
8
0
9
1
-
1.
[
1
7
]
A
.
A
p
p
a
t
h
u
r
a
i
,
R
.
S
u
n
d
a
r
a
s
e
k
a
r
,
C
.
R
a
j
a
,
E.
J.
A
l
e
x
,
C
.
A
.
P
a
l
a
g
a
n
,
a
n
d
A
.
N
i
t
h
y
a
,
“
A
n
e
f
f
i
c
i
e
n
t
o
p
t
i
ma
l
n
e
u
r
a
l
n
e
t
w
o
r
k
-
b
a
s
e
d
mo
v
i
n
g
v
e
h
i
c
l
e
d
e
t
e
c
t
i
o
n
i
n
t
r
a
f
f
i
c
v
i
d
e
o
s
u
r
v
e
i
l
l
a
n
c
e
s
y
st
e
m,”
C
i
rc
u
i
t
s,
S
y
st
e
m
s,
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
,
v
o
l
.
3
9
,
n
o
.
2
,
p
p
.
7
3
4
–
7
5
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
0
3
4
-
019
-
0
1
2
2
4
-
9.
[
1
8
]
A
.
K
a
d
e
t
h
a
n
k
a
r
,
N
.
S
i
n
h
a
,
A
.
B
u
r
m
a
n
,
a
n
d
V
.
H
e
g
d
e
,
"
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
d
e
t
e
c
t
i
o
n
o
f
r
h
i
n
o
c
e
r
o
s
b
e
e
t
l
e
i
n
f
e
st
a
t
i
o
n
i
n
c
o
c
o
n
u
t
t
r
e
e
s
u
s
i
n
g
d
r
o
n
e
i
m
a
g
e
r
y
,
"
I
n
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
Vi
s
i
o
n
a
n
d
I
m
a
g
e
Pro
c
e
ss
i
n
g
,
p
p
.
4
6
3
-
4
7
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
1
0
8
6
-
8
_
4
1
[
1
9
]
P
.
S
i
n
g
h
,
A
.
V
e
r
m
a
,
a
n
d
J.S.
R
.
A
l
e
x
,
"
D
i
sea
s
e
a
n
d
p
e
st
i
n
f
e
c
t
i
o
n
d
e
t
e
c
t
i
o
n
i
n
c
o
c
o
n
u
t
t
r
e
e
t
h
r
o
u
g
h
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
"
C
o
m
p
u
t
e
rs
a
n
d
e
l
e
c
t
r
o
n
i
c
s i
n
a
g
ri
c
u
l
t
u
re
,
v
o
l
.
1
8
2
,
p
p
.
1
0
5
9
8
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
1
.
1
0
5
9
8
6
.
[
2
0
]
M
.
M
a
r
a
y
,
A
.
A
.
A
l
b
r
a
i
k
a
n
,
S
.
S
.
A
l
o
t
a
i
b
i
,
R
.
A
l
a
b
d
a
n
,
M
.
A
l
D
u
h
a
y
y
i
m,
a
n
d
W
.
K
.
A
l
-
A
z
z
a
w
i
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
e
n
a
b
l
e
d
c
o
c
o
n
u
t
t
r
e
e
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
mo
d
e
l
f
o
r
smar
t
a
g
r
i
c
u
l
t
u
r
e
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
2
.
1
0
8
3
9
9
.
[
2
1
]
D
.
B
a
n
e
r
j
e
e
,
V
.
K
u
k
r
e
j
a
,
S
.
V
a
t
s
,
V
.
Jai
n
,
a
n
d
B
.
G
o
y
a
l
,
“
En
h
a
n
c
i
n
g
a
c
c
u
r
a
c
y
o
f
y
e
l
l
o
w
i
n
g
d
i
s
e
a
se
se
v
e
r
i
t
y
l
e
v
e
l
d
e
t
e
c
t
i
o
n
i
n
c
o
c
o
n
u
t
p
a
l
ms
w
i
t
h
S
V
M
r
e
g
u
l
a
r
i
z
a
t
i
o
n
a
n
d
C
N
N
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
”
i
n
I
C
S
C
C
C
2
0
2
3
-
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
e
c
u
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.