I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
26
,
p
p
.
11
32
~
11
42
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
11
32
-
11
42
1132
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Autom
a
ted
ba
cte
ria
and fung
i
cla
ss
ificatio
n using
co
nv
o
lutiona
l
neura
l net
wo
rk
on
embedd
ed sy
ste
m
T
a
rik
B
o
ug
a
ns
s
a
1
,
M
a
ry
em
Ait
M
o
ula
y
2
,
Sa
m
a
r
Aa
r
a
bi
3
,
Abdela
li
L
a
s
f
a
r
2
,
Abdel
la
t
if
E
l
Af
ia
1
1
La
b
o
r
a
t
o
r
y
S
m
a
r
t
S
y
s
t
e
m
,
EN
S
I
A
S
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
s
i
t
y
,
R
a
b
a
t
,
M
o
r
o
c
c
o
2
La
b
o
r
a
t
o
r
y
S
y
st
e
ms
A
n
a
l
y
s
i
s
a
n
d
I
n
f
o
r
mat
i
o
n
P
r
o
c
e
ssi
n
g
a
n
d
I
n
d
u
st
r
i
a
l
M
a
n
a
g
e
me
n
t
,
H
i
g
h
S
c
h
o
o
l
of
Te
c
h
n
o
l
o
g
y
S
A
LE,
M
o
h
a
mm
a
d
i
a
S
c
h
o
o
l
of
E
n
g
i
n
e
e
r
i
n
g
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
s
i
t
y
,
R
a
b
a
t
,
M
o
r
o
c
c
o
3
M
a
t
e
r
i
a
l
s
,
E
n
e
r
g
y
a
n
d
A
c
o
u
st
i
c
s
Te
a
m
,
H
i
g
h
S
c
h
o
o
l
of
Te
c
h
n
o
l
o
g
y
S
A
LE
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
si
t
y
,
R
a
b
a
t
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
12
,
2
0
2
4
R
ev
is
ed
J
an
7
,
2
0
2
6
Acc
ep
ted
J
an
25
,
2
0
2
6
In
th
is
st
u
d
y
,
we
c
re
a
ted
a
n
d
a
p
p
li
e
d
n
o
v
e
l
c
o
n
c
e
p
ts
fo
r
h
a
rd
wa
re
-
b
a
se
d
ima
g
e
id
e
n
ti
fica
ti
o
n
a
n
d
c
a
teg
o
ri
z
a
ti
o
n
.
F
o
r
a
rti
ficia
l
in
telli
g
e
n
c
e
(
AI
)
a
n
d
ima
g
e
re
c
o
g
n
it
io
n
a
p
p
li
c
a
ti
o
n
s
,
th
is
in
c
l
u
d
e
s
p
u
t
ti
n
g
a
l
g
o
ri
th
m
s
fo
r
re
c
o
g
n
izin
g
c
o
lo
rs
,
te
x
tu
re
s,
a
n
d
sh
a
p
e
s
in
t
o
p
ra
c
ti
c
e
.
O
u
r
c
o
n
tri
b
u
ti
o
n
u
se
s
an
e
m
b
e
d
d
e
d
d
e
v
ice
wit
h
a
c
a
m
e
ra
a
n
d
a
m
icr
o
c
o
m
p
u
ter
(Ra
sp
b
e
rry
-
P
i
4
ty
p
e
)
to
re
p
lac
e
th
e
o
p
t
ica
l
a
ss
e
ss
m
e
n
t
of
P
e
tri
d
ish
e
s.
O
u
r
o
b
jec
t
re
c
o
g
n
it
i
o
n
s
y
ste
m
p
ro
c
e
ss
e
s
im
a
g
e
s
e
fficie
n
tl
y
by
u
si
n
g
a
sta
te
-
of
-
th
e
-
a
rt
k
e
rn
e
l
f
u
n
c
ti
o
n
a
n
d
a
n
e
w
n
e
ig
h
b
o
rh
o
o
d
a
rc
h
it
e
c
tu
re
.
Us
in
g
t
h
e
w
e
ll
-
k
n
o
wn
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(C
NN
)
a
rc
h
it
e
c
tu
re
,
YO
LO
v
8
,
as
a
p
re
-
train
e
d
m
o
d
e
l,
we
e
v
a
l
u
a
ted
t
h
e
p
r
o
p
o
se
d
CNN
-
b
a
se
d
m
e
th
o
d
f
o
r
o
b
jec
t
r
e
c
o
g
n
it
i
o
n
in
a
n
u
m
b
e
r
of
d
e
m
a
n
d
i
n
g
sc
e
n
a
rio
s.
S
e
v
e
ra
l
P
e
tri
p
late
s,
u
n
c
o
n
tro
ll
e
d
se
tt
in
g
s,
a
n
d
d
iffere
n
t
b
a
c
k
g
ro
u
n
d
s
a
n
d
il
lu
m
in
a
ti
o
n
we
re
u
se
d
to
e
v
a
lu
a
te
th
e
tec
h
n
o
lo
g
y
.
Ou
r
d
y
n
a
m
ic
m
o
d
e
in
te
g
ra
tes
a
CNN
n
e
two
r
k
with
an
a
tt
e
n
ti
o
n
m
a
sk
to
h
ig
h
li
g
h
t
t
h
e
tr
a
it
s
of
b
a
c
teria
a
n
d
f
u
n
g
i,
e
n
s
u
ri
n
g
r
o
b
u
st
re
c
o
g
n
it
i
o
n
.
We
imp
lem
e
n
ted
our
a
lg
o
rit
h
m
on
a
Ra
sp
b
e
rry
Pi
4
0
0
,
c
o
n
n
e
c
ted
to
a
CM
OS
3
.
0
c
a
m
e
ra
se
n
so
r
a
n
d
a
h
u
m
a
n
-
m
a
c
h
in
e
in
terfa
c
e
(HMI
)
fo
r
i
n
sta
n
t
d
isp
lay
of
re
su
lt
s.
K
ey
w
o
r
d
s
:
B
ac
ter
ia
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
E
m
b
ed
d
e
d
s
y
s
tem
Mic
r
o
b
io
lo
g
y
YOL
Ov
8
T
h
is
is
an
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC
BY
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
ar
ik
B
o
u
g
an
s
s
a
L
ab
o
r
ato
r
y
Sm
ar
t Sy
s
tem
,
E
N
SIA
S
,
Mo
h
am
m
ed
V
Un
iv
e
r
s
ity
R
ab
at,
Mo
r
o
cc
o
E
m
ail:
tar
ik
.
b
o
u
g
an
s
s
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
B
ac
ter
ial
in
f
ec
tio
n
s
p
o
s
e
an
im
p
o
r
tan
t
d
an
g
er
to
m
icr
o
b
io
lo
g
y
la
b
s
an
d
h
ea
lth
ca
r
e
in
s
titu
tio
n
s
wo
r
ld
wid
e.
C
o
n
s
eq
u
en
tly
,
tim
ely
an
d
p
r
ec
is
e
id
en
tific
atio
n
of
b
ac
te
r
ia
an
d
f
u
n
g
i
is
ess
en
tial
f
o
r
d
iag
n
o
s
in
g
an
d
ap
p
r
o
p
r
iately
m
an
a
g
in
g
d
is
ea
s
es
[
1
]
.
T
h
is
d
etec
tio
n
h
as
h
is
to
r
ically
b
ee
n
d
o
n
e
m
a
n
u
ally
,
wh
ich
tak
es
tim
e
an
d
is
in
ef
f
ec
tiv
e.
Petr
i
d
is
h
es
ar
e
wid
esp
r
ea
d
an
d
e
f
f
ec
tiv
e
to
o
ls
co
m
m
o
n
ly
u
s
ed
by
r
esear
ch
er
s
to
co
llect
d
ata
on
s
am
p
les
d
u
r
i
n
g
m
icr
o
b
io
lo
g
ical
s
tu
d
ies.
T
h
ey
ar
e
g
en
er
ally
e
q
u
ip
p
ed
with
a
lu
m
p
len
s
to
clar
if
y
v
is
io
n
,
th
e
Petr
i
d
is
h
es
illu
s
tr
ated
in
Fig
u
r
e
1
d
ep
lo
y
e
d
in
m
icr
o
b
io
l
o
g
y
lab
o
r
ato
r
ies
h
av
e
in
n
o
v
ated
in
th
e
f
ield
of
r
esear
ch
on
b
ac
ter
i
a
an
d
f
u
n
g
i
[
2
]
.
I
n
th
is
co
n
tex
t
o
f
o
b
ject
d
etec
tio
n
o
b
ject
s
p
ec
ially
b
ac
ter
ia
an
d
f
u
n
g
i
d
etec
tio
n
,
th
er
e
ar
e
two
ty
p
es
o
f
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etw
o
r
k
(
C
NN)
alg
o
r
ith
m
s
d
esig
n
ed
to
ac
ce
le
r
ate
o
b
ject
d
etec
tio
n
m
o
d
els
a
n
d
ac
h
iev
e
h
ig
h
ac
c
u
r
ac
y
r
eg
io
n
-
b
ased
c
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
R
-
C
NN)
an
d
y
o
u
o
n
l
y
lo
o
k
o
n
ce
(
YOL
O)
[
3
]
.
I
n
th
is
f
ield
,
m
a
n
y
s
tu
d
ies
h
av
e
b
ee
n
p
u
b
lis
h
e
d
[
4
]
,
to
id
en
tif
y
an
d
q
u
a
n
tify
tilap
ia
lar
v
ae
u
s
in
g
th
e
Fas
ter
R
-
C
NN
R
5
0
-
FP
N
2
X
an
d
Gr
id
R
-
C
NN
-
X1
0
1
-
3
2
X4
d
-
FP
N
2
X
m
o
d
els
g
av
e
t
h
e
g
r
ea
test
o
u
tco
m
es,
with
a
m
ea
n
ac
cu
r
ac
y
5
0
o
f
9
7
.
3
0
%.
an
d
[
5
]
u
s
es a
d
ig
ital twin
-
b
ased
in
tellig
en
t h
ea
lth
s
y
s
t
em
with
a
ca
s
ca
d
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
b
a
cteria
a
n
d
fu
n
g
i
cla
s
s
ifica
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
n
etw
o
r
k
o
n
…
(
Ta
r
ik
B
o
u
g
a
n
s
s
a
)
1133
r
ec
u
r
r
en
t
co
n
v
o
lu
tio
n
al
n
e
u
r
a
l
n
etwo
r
k
ar
ch
itectu
r
e
to
id
e
n
tify
C
OVI
D
-
1
9
f
r
o
m
X
-
r
a
y
im
ag
es.
T
h
e
m
o
d
el
ac
h
iev
ed
an
av
er
a
g
e
ac
cu
r
ac
y
o
f
0
.
9
4
.
Mo
r
eo
v
er
,
in
s
ev
e
r
al
r
esear
ch
p
r
o
jects
lik
e
Ah
m
ed
et
a
l.
[
6
]
u
s
es
m
u
lti
-
s
ca
le
p
er
ce
p
tu
al
(
MSP)
-
YOL
O
f
o
r
th
e
d
iag
n
o
s
is
o
f
v
a
g
in
itis
an
d
ac
h
iev
es
s
en
s
itiv
ities
o
f
0
.
7
0
6
f
o
r
k
ey
ce
lls
an
d
0
.
9
1
0
f
o
r
Tr
ich
o
mo
n
a
s
,
o
u
t
p
er
f
o
r
m
in
g
th
e
r
e
f
er
e
n
ce
m
o
d
el
b
y
0
.
2
1
8
an
d
0
.
0
5
1
.
Als
o
,
C
h
en
et
a
l.
[
7
]
a
p
p
lied
d
ef
o
r
m
ab
le
co
n
v
o
lu
tio
n
n
etwo
r
k
(
DC
N
)
-
YOL
Ov
5
,
with
a
DC
N
,
ca
n
d
etec
t
o
b
jects,
k
ey
p
o
i
n
ts
an
d
tr
ac
k
th
e
Op
leg
n
a
th
u
s
p
u
n
cta
tu
s
’s
ac
tio
n
s
in
an
a
m
m
o
n
ia
-
r
ic
h
en
v
ir
o
n
m
e
n
t.
T
h
is
m
o
d
el
s
h
o
wed
im
p
r
o
v
e
d
p
er
f
o
r
m
an
ce
o
v
er
t
h
e
o
r
ig
in
al
YOL
Ov
5
,
ac
h
iev
i
n
g
m
AP@
0
.
5
o
f
9
3
.
7
1
%
an
d
m
AP@
0
.
5
:0
.
9
5
o
f
5
7
.
4
5
%.
I
n
th
e
s
am
e
co
n
tex
t
o
f
o
b
ject
d
etec
tio
n
,
J
u
b
ay
er
e
t
a
l.
[
8
]
ap
p
lied
YOL
Ov
5
f
o
r
d
etec
tin
g
m
o
ld
o
n
f
o
o
d
s
u
r
f
ac
es
an
d
YOL
Ov
5
p
er
f
o
r
m
ed
ex
ce
p
tio
n
ally
well,
ac
h
iev
in
g
9
8
.
1
0
%
ac
cu
r
ac
y
,
1
0
0
%
r
ec
all,
an
d
9
9
.
6
0
% a
v
er
ag
e
p
r
ec
is
io
n
(
AP
)
,
o
u
tp
e
r
f
o
r
m
in
g
v
er
s
io
n
s
YOL
Ov
3
an
d
YOL
Ov
4
.
Ou
r
co
n
tr
ib
u
tio
n
in
v
o
l
v
es r
ep
lacin
g
th
e
v
is
u
al
in
s
p
ec
tio
n
o
f
Petr
i d
is
h
es w
ith
an
o
n
b
o
ar
d
s
y
s
tem
th
at
u
s
es
th
e
YOL
Ov
8
m
o
d
el
f
o
r
o
b
ject
d
etec
tio
n
.
T
h
is
s
y
s
tem
em
p
lo
y
s
a
ca
m
er
a
an
d
a
p
r
o
ce
s
s
in
g
ca
r
d
in
th
e
f
o
r
m
o
f
a
m
icr
o
co
m
p
u
ter
to
p
r
o
ce
s
s
im
ag
es
ib
n
r
ea
l
-
tim
e
an
d
au
to
m
ate
th
e
i
n
s
p
ec
tio
n
.
T
h
is
ap
p
r
o
ac
h
n
o
t
o
n
ly
m
in
im
izes
h
u
m
an
in
ter
f
er
en
ce
d
u
r
in
g
d
ata
co
llectio
n
b
u
t
also
p
r
o
v
id
es
v
alu
a
b
l
e
v
is
u
al
d
ata
th
at
r
esear
ch
er
s
ca
n
u
s
e
to
b
etter
u
n
d
er
s
tan
d
b
ac
ter
ial
ev
o
lu
tio
n
i
n
s
am
p
les
[
9
]
.
Fig
u
r
e
1
.
Petr
i
d
is
h
es
2.
T
H
E
I
M
P
O
RT
ANC
E
O
F
P
E
T
R
I
DI
SH
E
S
I
N
T
H
E
L
A
B
O
RATOR
Y
Petr
i
d
is
h
es
ar
e
s
u
p
er
f
icial
an
d
cy
lin
d
r
ical
co
n
tain
er
s
m
ad
e
of
g
lass
or
p
last
ic
th
at
ar
e
u
s
e
d
to
g
r
o
w
b
ac
ter
ia,
f
u
n
g
i,
an
d
o
th
er
m
icr
o
o
r
g
an
is
m
s
on
s
p
ec
if
ic
n
u
tr
ien
t
m
e
d
ia
[
1
0
]
.
T
h
ey
ar
e
n
ec
ess
ar
y
in
m
icr
o
b
io
lo
g
y
la
b
o
r
ato
r
ies
f
o
r
p
r
o
d
u
cin
g
an
d
s
tu
d
y
in
g
m
ic
r
o
o
r
g
a
n
is
m
s
.
O
f
f
er
in
g
a
c
o
n
t
r
o
lled
en
v
ir
o
n
m
en
t
th
at
m
in
im
izes
co
n
tam
in
atio
n
[
1
1
]
.
Petr
i
d
is
h
es
h
av
e
g
r
o
wn
to
be
am
o
n
g
th
e
m
o
s
t
f
r
eq
u
e
n
t
ly
u
tili
ze
d
lab
s
u
p
p
lies
b
ec
a
u
s
e
of
its
s
im
p
licity
an
d
u
s
ab
ilit
y
[
1
2
]
a
Petr
i
d
is
h
is
m
ad
e
up
of
a
tr
an
s
lu
ce
n
t
b
ase
an
d
a
s
q
u
ar
e
or
cir
c
u
lar
,
lo
o
s
e
-
f
itti
n
g
co
v
er
t
h
at
is
in
ten
d
ed
to
s
h
ield
s
am
p
les
f
r
o
m
o
u
ts
id
e
co
n
tam
in
atio
n
.
Ad
d
itio
n
ally
,
th
ey
ar
e
ess
en
tial
to
th
e
p
r
o
ce
s
s
of
ass
ess
in
g
an
tib
io
tic
s
u
s
ce
p
tib
ili
ty
,
wh
ich
estab
lis
h
es
how
well
an
tib
io
tics
wo
r
k
ag
ain
s
t
d
if
f
er
en
t
s
tr
ain
s
of
b
ac
ter
ia
[
1
3
]
.
Als
o
,
L
a
n
d
is
et
a
l.
[
1
4
]
d
e
m
o
n
s
tr
ates
th
e
b
en
e
f
its
of
th
e
lar
g
e
s
u
r
f
ac
e
ar
ea
to
v
o
lu
m
e
r
atio
of
Petr
i
p
lates,
wh
ich
can
h
elp
o
r
g
a
n
is
m
s
s
u
ch
as
B
r
etta
n
o
myc
es
b
r
u
xe
llen
s
is
g
r
o
w
an
d
p
r
o
d
u
ce
m
o
r
e
m
etab
o
lites
u
n
d
er
ae
r
o
b
ic
cir
c
u
m
s
tan
ce
s
.
To
f
in
d
n
ew
d
is
ea
s
es
an
d
h
elp
m
icr
o
b
io
l
o
g
is
ts
in
th
e
lab
o
r
ato
r
y
p
r
ec
is
ely
co
u
n
t
an
d
an
aly
ze
m
icr
o
b
ial
co
n
te
n
t
.
I
t
is
cr
itical
to
id
en
tify
th
e
b
ac
ter
ia
a
n
d
f
u
n
g
i
g
r
o
win
g
on
Petr
i
d
is
h
es.
To
do
t
h
is
,
we
h
av
e
im
p
lem
en
ted
a
m
o
d
el
th
at
m
a
k
es
u
s
e
of
an
ex
ten
s
iv
e
d
ataset
to
en
h
an
ce
th
e
id
en
tific
atio
n
an
d
ca
teg
o
r
izatio
n
of
m
icr
o
o
r
g
a
n
is
m
s
,
h
en
ce
f
ac
i
litatin
g
more
ac
cu
r
ate
an
d
i
n
s
ig
h
tf
u
l
m
icr
o
b
io
lo
g
ical
ev
alu
at
io
n
s
.
3.
M
AT
E
R
I
AL
A
ND
M
E
T
H
O
DS
3
.
1
.
Co
m
pu
t
er
v
is
io
n
a
nd
co
nv
o
lutio
na
l
neura
l
net
wo
rk
s
Ar
tific
ial
in
tellig
en
ce
(
AI
)
[
1
5
]
was
f
ir
s
t
d
escr
ib
ed
in
1
9
5
0
[
1
6
]
.
Ma
c
h
in
e
lear
n
in
g
,
a
p
o
r
ti
o
n
of
AI
,
allo
ws
m
ac
h
in
es
to
ac
q
u
ir
e
k
n
o
wled
g
e
f
r
o
m
d
ata
an
d
ad
v
an
ce
with
o
u
t
th
e
n
ee
d
f
o
r
e
x
p
licit
p
r
o
g
r
a
m
m
in
g
[
1
7
]
.
On
e
s
u
b
f
ield
of
m
ac
h
in
e
lear
n
in
g
ca
lled
“
d
ee
p
lea
r
n
i
n
g
(
DL
)
”
m
o
d
els
d
if
f
icu
lt
d
at
a
u
s
in
g
d
ee
p
n
e
u
r
al
n
etwo
r
k
s
,
d
u
e
to
its
ab
ilit
y
to
id
en
tify
o
b
jects
in
im
ag
es,
DL
ar
ch
itectu
r
es
h
a
v
e
attr
ac
ted
a
lo
t
of
atten
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
11
32
-
11
42
1134
As
a
r
esu
lt,
th
ey
h
av
e
b
ee
n
ap
p
lied
to
m
ed
ical
im
ag
in
g
to
p
er
f
o
r
m
task
s
s
u
ch
as
o
r
g
an
d
etec
tio
n
an
d
s
eg
m
en
tatio
n
[
1
7
]
.
A
s
p
ec
if
ic
DL
ar
ch
itectu
r
e
cr
ea
ted
to
ef
f
e
ctiv
ely
p
r
o
ce
s
s
v
is
u
al
d
ata
is
th
e
C
NN.
C
o
m
p
u
ter
v
is
io
n
is
an
o
th
er
s
u
b
s
et
of
AI
t
h
at
allo
ws
co
m
p
u
ter
s
to
s
ee
an
d
u
n
d
e
r
s
tan
d
[
1
8
]
by
tr
ai
n
in
g
th
em
to
i
d
en
tify
a
n
d
in
te
r
p
r
et
th
e
c
o
n
ten
t
of
im
ag
es
an
d
v
id
e
o
s
.
Sin
ce
th
ey
a
r
e
clo
s
ely
r
elate
d
to
each
o
th
er
,
ad
v
a
n
ce
s
in
DL
in
r
ec
en
t
y
ea
r
s
h
av
e
also
led
to
ex
ce
p
tio
n
al
s
u
cc
ess
es
in
th
e
f
ield
of
co
m
p
u
ter
v
is
io
n
.
Ap
p
licatio
n
s
f
o
r
co
m
p
u
ter
v
is
io
n
in
clu
d
e
r
ea
l
-
tim
e
s
p
o
r
ts
,
au
to
n
o
m
o
u
s
ca
r
s
,
o
b
ject
id
en
tific
atio
n
,
an
d
f
ac
ial
r
ec
o
g
n
itio
n
.
C
NNs
[
1
9
]
,
wh
ich
wer
e
f
ir
s
t
in
tr
o
d
u
ce
d
in
th
e
L
eNe
t
-
5
a
r
c
h
itectu
r
e
[
2
0
]
by
Yan
n
L
eCu
n
et
a
l.
in
1998,
r
ec
eiv
e
d
m
u
ch
atten
tio
n
af
ter
th
e
r
elea
s
e
of
Alex
n
et
in
2
0
1
2
[
3
]
.
W
ith
th
e
a
v
ailab
ilit
y
of
lar
g
e
d
atasets
,
C
NNs
ar
e
ab
le
to
au
t
o
m
atica
lly
d
etec
t
im
p
o
r
tan
t
f
ea
tu
r
es,
m
ak
e
h
ig
h
ly
ac
cu
r
ate
p
r
e
d
ic
tio
n
s
,
an
d
p
er
f
o
r
m
co
m
p
u
ter
v
is
io
n
task
s
th
at
wer
e
p
r
ev
i
o
u
s
ly
im
p
o
s
s
ib
le.
Un
lik
e
th
e
class
ic
n
eu
r
al
n
etwo
r
k
with
f
u
lly
co
n
n
ec
ted
lay
e
r
s
,
C
NN
h
as
a
u
n
iq
u
e
ar
c
h
itectu
r
e
as
s
h
o
wn
in
Fig
u
r
e
2
th
at
g
e
n
er
ally
in
cl
u
d
es
th
r
ee
ty
p
es
of
lay
er
s
:
co
n
v
o
l
u
tio
n
al
lay
er
,
p
o
o
lin
g
lay
er
,
an
d
f
u
lly
c
o
n
n
ec
te
d
lay
er
.
Fig
u
r
e
2
.
Sch
em
atic
illu
s
tr
atio
n
of
a
C
NN
ar
ch
itectu
r
e
T
h
e
YO
L
O
m
o
d
e
l
f
a
m
i
ly
wa
s
p
r
o
p
o
s
ed
by
R
ed
m
o
n
et
a
l
.
[
2
1
]
in
2015,
as
a
s
ta
te
-
of
-
t
h
e
-
ar
t
r
e
al
-
tim
e
o
b
je
ct
d
e
tec
t
io
n
s
y
s
t
em
.
It
is
an
o
b
je
ct
r
ec
o
g
n
i
ti
o
n
an
d
lo
c
al
iz
at
io
n
al
g
o
r
i
th
m
b
a
s
e
d
on
a
d
e
ep
n
e
u
r
a
l
n
et
wo
r
k
.
It
i
s
b
e
s
t
f
e
atu
r
e
is
th
a
t
it
wo
r
k
s
v
er
y
f
a
s
t.
F
o
r
e
x
am
p
l
e,
if
you
en
te
r
an
im
ag
e,
th
e
s
y
s
t
em
w
il
l
d
i
s
p
l
ay
th
e
o
b
je
ct
s
it
co
n
t
ain
s
an
d
th
e
p
o
s
i
tio
n
of
ea
c
h
o
b
j
ec
t
(
th
e
r
ec
tan
g
u
la
r
f
r
am
e
co
n
ta
in
in
g
th
e
o
b
je
ct)
[
2
2
]
.
YO
L
O
is
an
o
u
t
s
tan
d
in
g
ac
co
m
p
li
s
h
m
en
t
in
o
b
je
ct
d
ete
ct
io
n
,
a
lb
e
it
r
e
s
tr
ic
ted
to
a
s
in
g
l
e
d
et
ec
tio
n
wi
th
in
a
p
ict
u
r
e.
A
f
t
er
w
ar
d
s
,
n
u
m
er
o
u
s
f
u
r
th
e
r
it
er
a
tio
n
s
,
r
an
g
in
g
f
r
o
m
YO
L
O
v
1
to
Y
OL
O
v
7
[
2
3
]
,
we
r
e
in
tr
o
d
u
ce
d
w
ith
ad
v
an
ce
m
en
t
s
in
s
eg
m
en
ta
t
io
n
,
m
u
lt
i
-
o
b
je
ct
i
d
en
tif
ic
at
io
n
in
a
s
in
g
l
e
f
r
am
e,
ac
c
u
r
a
cy
,
an
d
ex
ac
t
lo
c
al
iza
t
io
n
[
2
4
]
.
T
h
e
m
o
d
el
w
as
im
p
r
o
v
ed
w
ith
b
a
tch
n
o
r
m
a
li
za
tio
n
,
an
ch
o
r
b
o
x
es
,
an
d
d
im
en
s
io
n
clu
s
t
er
s
in
YO
L
Ov
2
,
wh
i
ch
wa
s
r
e
le
as
ed
in
2
0
1
6
.
YO
L
Ov
3
,
wh
ich
was
r
el
ea
s
ed
in
2
0
1
8
,
en
h
an
c
ed
p
er
f
o
r
m
an
c
e
by
e
m
p
lo
y
in
g
s
p
at
ia
l
p
y
r
am
id
p
o
o
l
in
g
an
d
a
m
o
r
e
ef
f
ec
tiv
e
b
ac
k
b
o
n
e
n
et
wo
r
k
.
W
ith
th
e
r
el
ea
s
e
of
Y
OL
Ov
4
,
wh
ich
d
eb
u
t
ed
in
2
0
2
0
,
ad
d
it
io
n
a
l
f
ea
tu
r
e
s
l
ik
e
an
ch
o
r
-
f
r
ee
d
e
te
ct
in
g
h
ea
d
a
n
d
m
o
s
ai
c
d
ata
au
g
m
en
ta
tio
n
wer
e
ad
d
ed
.
W
it
h
in
t
eg
r
a
ted
ex
p
er
i
m
en
t
tr
ac
k
in
g
an
d
h
y
p
er
p
ar
am
e
ter
ad
ju
s
tm
en
t,
YO
L
Ov
5
im
p
r
o
v
ed
th
e
m
o
d
e
l
ev
en
f
u
r
th
e
r
.
Au
to
n
o
m
o
u
s
d
el
iv
er
y
r
o
b
o
t
s
em
p
lo
y
Y
OL
O
v
6
[
2
5
]
,
wh
ich
was
m
ad
e
o
p
en
-
s
o
u
r
c
e
in
2
0
2
2
,
w
h
il
e
Y
OL
Ov
7
in
tr
o
d
u
ce
d
p
o
s
e
es
t
im
a
tio
n
f
ea
tu
r
es
.
T
h
e
m
o
s
t
r
ec
en
t
Ul
tr
a
ly
ti
cs
v
er
s
io
n
,
Y
OL
Ov
8
[
2
6
]
,
p
r
o
v
i
d
es
im
p
r
o
v
ed
p
er
f
o
r
m
a
n
ce
an
d
ad
ap
tab
i
li
ty
f
o
r
ap
p
l
ica
t
io
n
s
r
el
at
ed
to
tr
a
ck
in
g
,
s
eg
m
en
ta
tio
n
,
an
d
d
et
ec
tio
n
.
Y
OL
Ov
9
[
2
7
]
p
r
e
s
en
t
s
p
r
o
g
r
am
m
ab
l
e
g
r
ad
i
en
t
in
f
o
r
m
at
io
n
(
P
GI
)
an
d
th
e
g
en
er
al
iz
ed
ef
f
ic
ie
n
t
lay
er
a
g
g
r
eg
a
tio
n
n
e
two
r
k
(
GE
L
A
N)
,
th
e
F
ig
u
r
e
3
i
l
lu
s
tr
at
e
s
v
ar
io
u
s
v
er
s
i
o
n
s
of
YO
L
O
alg
o
r
i
th
m
s
.
YOL
O
wo
r
k
s
in
th
at
we
tak
e
an
im
ag
e
an
d
d
iv
id
e
it
in
to
an
S
×
S
g
r
id
,
in
ea
ch
o
f
th
e
g
r
id
s
we
tak
e
N
b
o
u
n
d
in
g
b
o
x
es.
Fo
r
ea
ch
o
f
t
h
e
b
o
u
n
d
in
g
b
o
x
es,
th
e
n
etwo
r
k
g
en
er
ates
a
class
p
r
o
b
ab
ilit
y
an
d
o
f
f
s
et
v
alu
es
f
o
r
th
e
b
o
u
n
d
in
g
b
o
x
.
B
o
u
n
d
i
n
g
b
o
x
p
r
ed
ictio
n
:
An
ch
o
r
b
o
x
es
ar
e
m
ad
e
o
f
d
im
en
s
io
n
clu
s
ter
s
b
y
th
e
YOL
O
alg
o
r
ith
m
to
an
ticip
ate
b
o
u
n
d
in
g
b
o
x
es.
Fo
r
e
v
er
y
b
o
u
n
d
i
n
g
b
o
x
,
it
is
n
etwo
r
k
p
r
ed
ict
s
f
o
u
r
c
o
o
r
d
i
n
ates:
tx
,
ty
,
tw,
an
d
th
.
T
h
e
p
r
e
d
ictio
n
s
m
atch
Fig
u
r
e
4
if
th
e
ce
ll
is
o
f
f
s
et
f
r
o
m
th
e
u
p
p
er
lef
t
c
o
r
n
er
o
f
th
e
im
a
g
e
b
y
(
cx
,
cy
)
an
d
t
h
e
wid
th
an
d
h
eig
h
t o
f
th
e
p
r
ev
io
u
s
b
o
u
n
d
in
g
b
o
x
ar
e
p
w,
p
h
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
b
a
cteria
a
n
d
fu
n
g
i
cla
s
s
ifica
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
n
etw
o
r
k
o
n
…
(
Ta
r
ik
B
o
u
g
a
n
s
s
a
)
1135
Fig
u
r
e
3.
Ver
s
io
n
s
of
YOL
O
a
lg
o
r
ith
m
Fig
u
r
e
4
.
YOL
O
b
o
u
n
d
in
g
b
o
x
p
r
ed
ictio
n
[
9
]
3
.
2
.
YO
L
O
v
8
a
lg
o
rit
hm
YOL
Ov
8
,
i
t
is
a
r
ea
l
-
tim
e
o
b
ject
d
etec
tin
g
s
y
s
tem
th
at
r
ep
r
esen
ts
YOL
O,
wa
s
u
s
ed
as
a
p
r
ev
io
u
s
ly
tr
ain
ed
m
o
d
el
in
t
h
is
p
r
o
ject
.
C
o
m
p
ar
ed
to
o
t
h
er
d
etec
ti
o
n
s
y
s
tem
s
[
2
8
]
,
YOL
Ov
8
is
f
aster
an
d
m
o
r
e
ac
cu
r
ate,
also
YOL
Ov
8
can
r
ec
o
g
n
ize
s
m
all,
f
o
r
b
id
d
e
n
o
b
jects
with
v
ar
io
u
s
o
cc
lu
s
io
n
s
wh
ile
s
tr
ik
in
g
an
im
p
r
ess
iv
e
b
alan
ce
b
etwe
en
e
f
f
icien
cy
an
d
d
etec
tio
n
ac
cu
r
ac
y
.
Fo
r
th
is
r
ea
s
o
n
,
YOL
Ov
8
is
ex
tr
e
m
ely
f
ast
th
an
Fas
t
R
-
C
NN
[
2
9
]
.
T
h
e
ar
ch
itectu
r
e
of
y
o
lo
v
8
s
tr
ik
es
a
co
m
p
r
o
m
is
e
b
etwe
en
s
p
ee
d
an
d
p
r
ec
is
io
n
to
s
o
lv
e
th
e
s
h
o
r
tco
m
in
g
s
of
ea
r
lier
Y
OL
O
iter
atio
n
s
[
3
]
.
O
n
e
clea
r
im
p
r
o
v
em
e
n
t
is
YOL
Ov
8
’
s
s
c
alab
le
an
d
m
o
d
u
lar
ar
ch
itectu
r
e.
T
h
e
th
r
ee
m
ai
n
p
ar
ts
of
th
e
m
o
d
el
ar
e
t
h
e
h
ea
d
,
n
ec
k
,
an
d
b
ac
k
b
o
n
e.
Y
OL
Ov
8
’
s
b
ac
k
b
o
n
e,
wh
ich
co
n
s
is
ts
of
C
SP
Dar
k
n
et5
3
an
d
E
f
f
icien
tDet,
is
ac
co
u
n
tab
le
f
o
r
T
ak
in
g
o
u
t
f
ea
tu
r
es
f
r
o
m
th
e
in
p
u
t
im
ag
e.
T
h
e
f
u
s
i
o
n
of
c
h
a
r
a
c
te
r
i
s
ti
c
s
d
e
p
e
n
d
s
on
t
h
e
n
e
c
k
,
w
h
i
c
h
c
o
n
n
e
c
ts
t
h
e
h
ea
d
a
n
d
b
a
ck
b
o
n
e
.
As
s
h
o
w
n
in
F
i
g
u
r
e
5
,
t
h
e
h
e
a
d
p
r
e
d
i
c
ts
b
o
u
n
d
i
n
g
b
o
x
e
s
,
i
t
e
m
c
l
ass
i
f
i
c
at
i
o
n
s
,
a
n
d
c
o
n
f
i
d
e
n
c
e
r
a
t
i
n
g
s
.
Fig
u
r
e
5.
YOL
Ov
8
ar
ch
itectu
r
e
[
3
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
11
32
-
11
42
1136
3
.
3
.
T
he
m
a
in
cr
it
er
ia
of
t
he
pro
po
s
ed
em
bedd
ed
ha
rd
w
a
re
s
o
lutio
n
T
h
e
o
b
jectiv
es
to
be
ac
h
ie
v
ed
f
o
r
th
e
r
e
co
g
n
itio
n
an
d
class
if
icatio
n
of
b
ac
ter
ia,
with
in
th
e
f
r
am
ewo
r
k
of
th
is
d
o
cu
m
e
n
t,
m
u
s
t
m
ee
t
th
e
f
o
llo
win
g
cr
iter
ia:
−
Pro
v
id
es
s
tab
le
p
er
f
o
r
m
an
ce
in
an
e
n
v
ir
o
n
m
en
t
with
o
u
t
co
n
s
tr
ain
ts
s
u
ch
as
lig
h
tin
g
co
n
d
itio
n
s
,
b
ac
k
g
r
o
u
n
d
in
h
o
m
o
g
en
eity
,
p
o
s
itio
n
an
d
o
r
ien
tatio
n
of
b
ac
ter
ia,
s
tain
s
an
d
,
m
o
s
t
im
p
o
r
ta
n
tly
,
d
if
f
er
en
tiatio
n
b
etwe
en
a
f
u
n
g
u
s
an
d
b
ac
ter
ia.
−
Ach
iev
es
v
er
y
h
ig
h
r
ec
o
g
n
iti
o
n
r
ates,
d
em
o
n
s
tr
atin
g
th
e
r
eliab
ilit
y
of
th
e
alg
o
r
ith
m
'
s
r
ec
o
g
n
itio
n
an
d
id
en
tific
atio
n
r
esu
lts
.
−
Sin
ce
m
o
s
t
f
u
t
u
r
e
a
p
p
licatio
n
s
will
be
r
ea
l
-
tim
e,
ex
ec
u
tio
n
tim
e
is
also
a
c
r
u
cial
m
etr
ic
to
ev
alu
ate
th
e
r
ec
o
g
n
itio
n
ar
c
h
itectu
r
e
im
p
le
m
en
ted
on
an
em
b
ed
d
e
d
s
y
s
tem
.
On
a
R
asp
b
er
r
y
Pi
4,
f
o
r
in
s
tan
ce
,
th
e
s
y
s
tem
is
ex
p
ec
ted
to
ac
h
iev
e
in
f
er
en
ce
laten
cy
of
ap
p
r
o
x
im
ately
200
–
3
0
0
ms
p
er
im
ag
e,
m
ain
tain
m
em
o
r
y
u
s
ag
e
u
n
d
e
r
1
GB
,
an
d
s
u
s
tain
a
f
r
am
e
r
ate
of
3
–
5
FPS
d
ep
en
d
in
g
on
im
ag
e
r
eso
lu
tio
n
an
d
m
o
d
el
co
m
p
lex
ity
[
3
0
]
.
−
All
th
e
to
o
ls
ch
o
s
en
ar
e
f
r
ee
,
s
u
ch
as
th
e
Py
th
o
n
lan
g
u
ag
e
an
d
th
e
R
asp
b
ian
o
p
er
atin
g
s
y
s
tem
.
It
is
an
em
b
ed
d
e
d
GNU/L
in
u
x
o
p
er
at
in
g
s
y
s
tem
co
m
p
atib
le
with
R
asp
b
er
r
y
Pi
m
icr
o
co
m
p
u
ter
s
as
p
r
esen
ted
in
th
e
Fig
u
r
e
6
.
Fig
u
r
e
6
.
R
asp
b
er
r
y
Pi
4
v
e
r
s
io
n
4
0
0
3
.
4
.
M
et
ho
do
lo
g
y
a
do
pte
d
Ou
r
s
tu
d
y
in
clu
d
ed
a
n
u
m
b
e
r
of
cr
u
cial
p
r
o
ce
d
u
r
es
to
id
en
tify
b
ac
ter
ia
an
d
f
u
n
g
u
s
.
Sin
ce
our
o
r
ig
in
al
d
ataset
was
litt
le,
we
u
s
ed
i
n
ten
s
iv
e
d
ata
au
g
m
en
t
atio
n
to
d
ig
itally
e
n
lar
g
e
it
in
s
tead
of
c
o
llectin
g
more
Petr
i
d
is
h
p
h
o
to
g
r
ap
h
s
.
Usi
n
g
ad
v
an
ce
d
tech
n
i
q
u
es
lik
e
m
o
s
aic,
m
ix
u
p
,
an
d
co
p
y
-
p
aste
to
in
cr
ea
s
e
m
o
d
el
r
o
b
u
s
tn
ess
,
as
well
as
f
lip
p
in
g
,
r
o
tatio
n
,
s
ca
lin
g
,
an
d
b
r
ig
h
tn
ess
m
o
d
if
icat
io
n
s
,
au
g
m
e
n
tatio
n
p
r
o
ce
d
u
r
es
r
ep
licated
r
ea
l
-
wo
r
ld
f
lu
ctu
atio
n
s
in
illu
m
i
n
atio
n
,
o
r
ien
tatio
n
,
a
n
d
s
ca
le.
To
p
r
o
d
u
ce
th
e
lab
eled
d
ataset,
L
ab
elI
m
g
was
u
s
ed
to
a
n
n
o
tate
two
class
es:
“
b
ac
”
(
b
a
cter
ia)
an
d
“
ch
am
p
”
(
f
u
n
g
i)
.
To
ac
h
iev
e
r
o
b
u
s
t
ev
alu
atio
n
in
s
p
ite
of
th
e
s
m
all
s
am
p
le
s
ize,
we
em
p
lo
y
ed
f
iv
e
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
with
tr
ain
/
v
alid
atio
n
/tes
t
s
p
lits
.
T
h
is
ap
p
r
o
a
ch
p
r
o
d
u
ce
d
p
r
ec
is
e
p
er
f
o
r
m
a
n
ce
esti
m
ates
f
o
r
a
r
an
g
e
of
d
ata
s
u
b
s
ets.
T
h
e
Ad
am
W
o
p
tim
izer
f
o
r
s
tab
le
g
en
er
aliza
tio
n
on
s
h
o
r
t
d
atasets
,
a
lear
n
in
g
r
ate
of
0
.
0
0
5
with
co
s
in
e
s
ch
ed
u
lin
g
to
en
h
an
ce
co
n
v
er
g
en
ce
,
a
n
d
an
im
ag
e
s
ize
of
9
6
0
×
9
6
0
p
ix
els
to
ca
p
t
u
r
e
f
in
e
b
ac
ter
ial
an
d
f
u
n
g
al
f
ea
tu
r
es
wer
e
am
o
n
g
th
e
ca
r
ef
u
lly
ch
o
s
en
h
y
p
er
p
a
r
am
eter
s
u
s
ed
to
tr
ain
t
h
e
Y
OL
Ov
8
m
o
d
el.
By
b
alan
cin
g
ac
c
u
r
ac
y
,
s
tab
ilit
y
,
an
d
c
o
m
p
u
tatio
n
ef
f
icien
c
y
,
th
is
s
etu
p
tak
es
in
to
ac
c
o
u
n
t
b
o
th
r
ea
lis
tic
d
ep
lo
y
m
e
n
t
asp
ec
ts
an
d
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
.
Fig
u
r
e
7
ill
u
s
tr
ates
how
v
a
r
io
u
s
co
m
b
in
a
tio
n
s
im
p
r
o
v
ed
th
e
ac
cu
r
ac
y
an
d
s
tab
ilit
y
of
d
etec
tio
n
.
3
.
5
.
I
m
ple
m
ent
a
t
io
n det
a
ils
W
e
u
s
ed
a
Kag
g
le
n
o
teb
o
o
k
e
n
v
ir
o
n
m
en
t
to
tr
ain
an
d
ev
al
u
ate
th
e
m
o
d
el.
T
h
e
d
ataset
was
s
ep
ar
ated
in
to
tr
ain
,
v
alid
atio
n
,
an
d
test
s
u
b
s
ets
to
en
s
u
r
e
r
e
liab
le
p
er
f
o
r
m
an
ce
esti
m
atio
n
s
,
an
d
f
iv
e
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
was
em
p
lo
y
e
d
to
less
en
b
ias
r
e
s
u
ltin
g
f
r
o
m
th
e
s
m
all
s
am
p
le
s
ize.
T
h
e
Y
OL
Ov
8
m
o
d
el
was
d
ev
elo
p
e
d
u
s
in
g
th
e
Py
T
o
r
ch
DL
p
latf
o
r
m
.
Fo
r
s
tab
le
o
p
tim
izatio
n
,
th
e
m
o
d
el
was
tr
ain
ed
f
o
r
3
0
0
ep
o
c
h
s
u
s
in
g
co
s
in
e
s
ch
e
d
u
lin
g
with
an
in
itial
lear
n
in
g
r
ate
o
f
0
.
0
0
5
.
B
ased
o
n
p
r
elim
in
ar
y
e
x
p
er
im
en
ts
a
n
d
b
est
p
r
ac
tices,
th
ese
h
y
p
er
p
ar
am
et
er
s
wer
e
ca
r
ef
u
lly
s
elec
ted
.
A
d
v
an
ce
d
d
ata
au
g
m
en
tatio
n
li
k
e
f
lip
p
in
g
,
r
o
tatio
n
,
s
ca
lin
g
,
co
p
y
-
p
aste,
m
o
s
aic,
m
ix
u
p
,
an
d
b
r
i
g
h
tn
ess
ad
ju
s
t
m
en
t
was
u
s
ed
to
im
p
r
o
v
e
m
o
d
el
g
e
n
er
aliza
tio
n
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
b
a
cteria
a
n
d
fu
n
g
i
cla
s
s
ifica
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
n
etw
o
r
k
o
n
…
(
Ta
r
ik
B
o
u
g
a
n
s
s
a
)
1137
an
d
th
e
s
ize
o
f
th
e
im
ag
e
h
ad
b
ee
n
cu
s
to
m
ized
to
9
6
0
×
9
6
0
p
ix
els
to
ca
p
tu
r
e
f
in
e
b
ac
ter
ial
an
d
f
u
n
g
al
d
etails,
all
d
etails ar
e
s
h
o
wn
in
T
ab
le
1
.
Fig
u
r
e
7.
M
eth
o
d
o
lo
g
y
a
d
o
p
te
d
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
We
s
u
cc
ess
f
u
lly
ap
p
lied
our
m
eth
o
d
to
i
d
en
tify
b
ac
ter
ia
a
n
d
f
u
n
g
i
in
Petr
i
d
is
h
es
d
esp
i
te
wo
r
k
in
g
with
a
co
m
p
ar
ativ
ely
s
m
all
d
a
taset.
W
ith
o
v
er
all
s
co
r
es
of
p
r
ec
is
io
n
s
0
.
8
6
4
,
r
ec
all
0
.
7
7
9
,
a
n
d
m
AP@
5
0
0
.
8
5
9
ac
r
o
s
s
all
class
es,
th
e
YOL
Ov
8
m
o
d
el
s
h
o
wed
e
x
ce
llen
t
p
er
f
o
r
m
an
ce
in
r
ec
o
g
n
izin
g
s
m
al
l
o
b
jects
as
s
h
o
wn
in
T
ab
le
1
.
I
n
te
r
m
s
o
f
in
d
i
v
id
u
al
class
es,
th
e
“c
h
a
m
p
”
class
,
wh
ich
h
ad
1
6
p
h
o
to
s
with
4
4
2
in
s
tan
ce
s
,
ac
h
iev
ed
a
p
r
ec
is
io
n
o
f
0
.
8
3
9
,
r
ec
all
o
f
0
.
9
1
9
,
an
d
m
AP@
5
0
o
f
0
.
9
4
1
,
wh
ile
th
e
“b
ac
”
cl
ass
,
wh
ich
co
n
s
is
ted
o
f
2
3
im
ag
es
with
5
7
9
in
s
tan
ce
s
,
ac
h
iev
ed
a
p
r
ec
is
io
n
o
f
0
.
8
8
9
,
r
ec
all
o
f
0
.
6
3
9
,
an
d
m
AP@
5
0
o
f
0
.
7
7
6
.
T
h
ese
r
esu
lts
ar
e
illu
s
tr
ated
i
n
Fig
u
r
es
8
an
d
9
,
with
Fig
u
r
e
1
0
s
h
o
win
g
th
e
p
r
ec
is
io
n
-
co
n
f
id
e
n
ce
c
u
r
v
e
,
wh
ich
d
em
o
n
s
tr
ates m
o
d
el
p
r
e
cisi
o
n
ac
r
o
s
s
all
class
e
s
as a
f
u
n
ctio
n
o
f
p
r
e
d
ictio
n
co
n
f
id
en
c
e
lev
els.
T
ab
le
1
.
Per
f
o
r
m
an
ce
m
etr
ics
an
d
m
o
d
el
d
etails
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
0
5
R
u
n
n
i
n
g
t
i
me
0
.
1
4
9
h
o
u
r
s
G
P
U
u
se
d
P
1
0
0
M
o
d
e
l
s
i
z
e
2
2
.
0
1
Mo
Ep
o
c
h
s
3
0
0
P
r
e
c
i
s
i
o
n
8
6
.
4
%
mA
P
@
5
0
0.
85
Fig
u
r
e
8
.
R
ec
o
g
n
itio
n
o
f
b
ac
te
r
ia
an
d
f
u
n
g
i
Alth
o
u
g
h
,
Fig
u
r
e
1
1
co
n
f
u
s
io
n
m
atr
ix
d
em
o
n
s
tr
ates
th
e
s
u
g
g
ested
m
o
d
el’
s
ex
ce
llen
t
d
is
cr
im
in
ativ
e
p
o
wer
ac
r
o
s
s
all
th
r
ee
class
es.
E
x
ce
llen
t
class
s
ep
ar
ab
ilit
y
w
as
co
n
f
ir
m
ed
b
y
th
e
ch
a
m
p
(
f
u
n
g
u
s
)
class
,
wh
ic
h
h
ad
th
e
b
est
ac
cu
r
ac
y
with
3
9
3
co
r
r
ec
t
p
r
ed
ictio
n
s
.
W
ith
3
4
2
tr
u
e
p
o
s
itiv
es,
th
e
b
ac
(
b
ac
ter
ia)
class
also
d
em
o
n
s
tr
ated
s
tr
o
n
g
r
ec
o
g
n
iti
o
n
,
p
r
o
v
in
g
s
u
cc
ess
f
u
l b
ac
ter
ial
id
en
tific
atio
n
in
s
p
ite
o
f
s
ig
n
if
ican
t b
ac
k
g
r
o
u
n
d
r
eg
io
n
c
o
n
f
u
s
io
n
.
T
h
e
p
r
im
a
r
y
ca
u
s
e
o
f
m
is
class
if
icatio
n
s
b
etwe
en
b
ac
ter
ia
a
n
d
b
ac
k
g
r
o
u
n
d
was
v
is
u
al
s
im
ilar
ity
in
tex
tu
r
e
an
d
illu
m
in
atio
n
,
b
u
t
th
ey
wer
e
s
till
with
in
to
ler
ab
le
b
o
u
n
d
s
.
Ov
er
all,
th
e
co
n
f
u
s
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
11
32
-
11
42
1138
m
atr
ix
co
n
f
ir
m
s
th
e
m
o
d
el’
s
ca
p
ab
ilit
y
f
o
r
r
ea
l
-
tim
e
b
ac
ter
ial
an
d
f
u
n
g
al
class
if
icatio
n
o
n
em
b
e
d
d
ed
h
ar
d
war
e
lik
e
t
h
e
R
asp
b
er
r
y
P
i a
n
d
p
r
o
v
es its
r
o
b
u
s
t a
n
d
d
e
p
en
d
ab
le
p
e
r
f
o
r
m
an
ce
.
Fig
u
r
e
9
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
illu
s
tr
ated
b
y
th
e
p
r
ec
is
io
n
-
r
ec
all
cu
r
v
e
Fig
u
r
e
1
0
.
T
h
e
lin
k
b
etwe
en
p
r
ed
ictio
n
s
elf
-
ass
u
r
an
ce
an
d
a
cc
u
r
ac
y
Fig
u
r
e
11
.
C
o
n
f
u
s
io
n
m
atr
ix
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
b
a
cteria
a
n
d
fu
n
g
i
cla
s
s
ifica
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
n
etw
o
r
k
o
n
…
(
Ta
r
ik
B
o
u
g
a
n
s
s
a
)
1139
Pre
-
tr
ain
ed
m
o
d
el
(
YOL
Ov
8
)
:
alth
o
u
g
h
th
e
o
r
ig
in
al
YOL
O
m
o
d
el
can
d
etec
t,
c
o
u
n
t,
a
n
d
r
ec
o
g
n
ize
s
ev
er
al
co
m
m
o
n
ty
p
es
of
b
ac
t
er
ia,
it
m
ay
co
n
f
u
s
e
s
o
m
e
u
n
k
n
o
wn
s
p
ec
ies,
r
esu
ltin
g
in
lo
w
er
m
o
d
el
ac
c
u
r
ac
y
an
d
more
m
an
u
al
wo
r
k
ca
r
r
i
ed
out
by
t
h
e
r
esear
ch
er
s
as
p
r
esen
ted
in
Fig
u
r
e
1
2
.
YOL
Ov
8
can
co
u
n
t
an
d
class
if
y
s
ev
er
al
b
ac
ter
ia
p
r
ese
n
t
in
a
s
in
g
le
im
ag
e.
As
you
can
s
ee
in
Fig
u
r
e
1
2
,
it
illu
s
tr
ates
th
e
n
u
m
b
er
of
b
ac
ter
ia
(
b
ac
)
a
n
d
f
u
n
g
i
(
ch
am
p
)
p
r
esen
t
in
each
im
ag
e
.
Fig
u
r
e
1
2
.
C
o
u
n
tin
g
s
ev
e
r
al
b
ac
ter
ia
R
ef
i
n
e
d
m
o
d
e
l
(
r
es
u
l
t)
:
to
ev
al
u
at
e
t
h
e
m
o
d
e
l,
p
h
o
to
s
o
f
Pet
r
i
d
is
h
es
ta
k
en
b
y
d
o
c
t
o
r
al
s
t
u
d
e
n
ts
i
n
t
h
e
m
ic
r
o
b
io
lo
g
y
l
ab
o
r
at
o
r
y
at
C
NR
ST
we
r
e
u
s
e
d
as
a
test
s
et
to
w
h
i
ch
t
h
e
tr
ai
n
e
d
m
o
d
e
l
is
ap
p
li
e
d
.
T
h
e
r
esu
lts
ill
u
s
tr
at
e
t
h
at
th
e
DL
m
o
d
el
was
ab
le
t
o
d
e
tec
t,
r
ec
o
g
n
iz
e
,
an
d
l
o
ca
liz
e
m
u
lt
ip
le
b
ac
t
er
ia
an
d
d
if
f
e
r
en
tia
te
b
et
we
en
b
a
cte
r
i
a
(
s
m
a
ll
s
i
ze
s
wit
h
th
e
s
a
m
e
co
lo
r
s
)
a
n
d
f
u
n
g
i
(
la
r
g
e
r
s
iz
es
a
n
d
d
if
f
e
r
e
n
t
c
o
l
o
r
s
)
v
ia
C
MO
S
3
.
0
ca
m
e
r
a
i
m
a
g
es
wi
th
g
r
ea
t
p
r
e
c
is
io
n
.
E
a
ch
i
d
en
ti
f
ie
d
o
b
j
ec
t
w
ill
b
e
s
u
r
r
o
u
n
d
e
d
b
y
a
b
o
u
n
d
i
n
g
b
o
x
an
d
l
ab
ele
d
wit
h
i
ts
s
p
ec
i
es
a
n
d
o
r
d
er
n
u
m
b
er
[
3
1
]
.
P
r
a
cti
ca
l
ly
s
p
e
a
k
i
n
g
,
t
h
is
m
et
h
o
d
m
a
y
b
e
i
m
m
ed
iat
el
y
u
s
ed
i
n
m
ic
r
o
b
io
lo
g
i
ca
l
la
b
s
t
o
h
el
p
r
ese
ar
c
h
e
r
s
a
u
t
o
m
ate
m
o
r
p
h
o
l
o
g
ic
al
c
h
a
r
a
ct
er
i
za
ti
o
n
,
c
o
l
o
n
y
co
u
n
ti
n
g
,
an
d
b
a
cte
r
i
al
a
n
d
f
u
n
g
al
d
is
ti
n
c
ti
o
n
,
g
r
ea
t
ly
m
in
im
i
zi
n
g
m
a
n
u
al
la
b
o
r
a
n
d
h
u
m
an
e
r
r
o
r
.
T
h
is
k
i
n
d
o
f
c
o
n
n
ec
ti
o
n
co
u
l
d
im
p
r
o
v
e
th
e
r
e
p
ea
t
ab
ilit
y
o
f
m
i
cr
o
b
i
o
l
o
g
ic
al
test
s
a
n
d
ex
p
e
d
i
te
la
b
o
r
at
o
r
y
p
r
o
c
e
d
u
r
es.
Nev
er
t
h
el
ess
,
s
e
v
e
r
a
l
r
es
tr
ict
i
o
n
s
w
er
e
n
o
t
ed
.
T
h
e
p
r
o
p
o
s
e
d
m
o
d
el
m
a
y
n
o
t
b
e
as
g
en
e
r
aliz
a
b
le
t
o
lar
g
er
m
ic
r
o
b
io
lo
g
i
ca
l
co
n
t
ex
ts
b
e
ca
u
s
e
it
w
as
tr
ai
n
e
d
a
n
d
v
ali
d
ate
d
o
n
a
s
m
all
d
a
tase
t
wit
h
li
ttl
e
s
p
e
ci
es
v
a
r
i
et
y
.
F
u
r
th
e
r
m
o
r
e
,
th
e
m
o
d
er
ate
r
e
ca
l
l
r
a
te
s
u
g
g
ests
t
h
at
s
o
m
e
b
ac
t
e
r
ia
l
c
o
l
o
n
ies
a
r
e
s
t
ill
o
v
er
lo
o
k
e
d
d
u
r
i
n
g
d
et
ec
ti
o
n
.
F
u
t
u
r
e
r
ese
ar
c
h
wi
ll
c
o
n
ce
n
t
r
a
te
o
n
e
x
a
m
i
n
i
n
g
ad
v
a
n
ce
d
a
r
c
h
it
ec
tu
r
es
li
k
e
v
is
io
n
t
r
a
n
s
f
o
r
m
e
r
s
(
Vi
T
s
)
f
o
r
m
o
r
e
p
r
e
cise
d
e
tec
tio
n
o
f
s
m
al
l
a
n
d
v
is
u
a
ll
y
s
im
ila
r
m
i
cr
o
b
i
al
o
b
j
ec
ts
,
a
p
p
l
y
i
n
g
t
r
a
n
s
f
er
lea
r
n
i
n
g
f
r
o
m
la
r
g
e
-
s
ca
le
b
i
o
m
ed
ica
l
i
m
a
g
e
d
at
asets
t
o
i
m
p
r
o
v
e
f
ea
t
u
r
e
g
en
e
r
al
iza
ti
o
n
,
a
n
d
b
r
o
a
d
e
n
i
n
g
t
h
e
d
atas
et
t
o
in
c
lu
d
e
a
g
r
ea
te
r
v
ar
iet
y
o
f
m
i
cr
o
b
ia
l s
p
e
cies
i
n
o
r
d
e
r
to
g
et
ar
o
u
n
d
t
h
es
e
l
im
i
tat
io
n
s
.
5.
CO
NCLU
SI
O
N
T
h
i
s
p
r
o
j
e
c
t
a
i
m
s
t
o
tr
a
i
n
an
a
l
g
o
r
i
t
h
m
ca
p
ab
l
e
o
f
p
r
o
c
e
s
s
in
g
a
n
d
l
a
b
e
l
i
n
g
d
a
t
a
f
r
o
m
P
e
tr
i
e
d
i
s
h
e
s
w
i
t
h
t
h
e
n
u
m
b
e
r
,
t
y
p
e
,
a
n
d
l
o
c
a
t
i
o
n
o
f
b
a
c
te
r
i
a
a
n
d
f
u
n
g
i
.
C
a
p
tu
r
e
d
h
u
g
e
a
n
d
l
ab
o
r
i
o
u
s
i
m
a
g
e
s
in
a
n
a
u
t
o
m
a
t
i
c
w
ay
t
h
a
t
r
e
s
ea
r
ch
er
s
w
e
r
e
wo
r
k
i
n
g
b
y
ap
p
ly
i
n
g
a
Y
O
L
O
v
8
-
b
a
s
e
d
o
b
j
ec
t
d
e
t
ec
t
i
o
n
.
C
o
m
p
a
r
ed
to
o
t
h
er
a
t
te
m
p
t
s
a
t
a
u
to
m
a
t
ic
b
a
c
t
e
r
ia
r
e
co
g
n
i
t
i
o
n
,
t
h
i
s
p
r
o
j
e
c
t
s
t
r
iv
e
s
to
f
u
r
t
h
er
f
a
c
i
l
i
tat
e
t
h
e
p
r
o
c
e
s
s
an
d
r
e
d
u
c
e
t
h
e
h
u
m
a
n
ef
f
o
r
t
r
e
q
u
ir
e
d
b
y
p
r
o
v
i
d
in
g
s
u
r
r
o
u
n
d
in
g
b
o
u
n
d
i
n
g
b
o
x
e
s
,
p
er
f
o
r
m
in
g
r
ea
l
-
t
i
m
e
r
e
c
o
g
n
i
t
io
n
,
an
d
ad
d
in
g
b
a
c
te
r
i
a
th
a
t
c
a
n
b
e
au
t
o
m
a
t
i
c
a
l
ly
id
e
n
t
if
i
e
d
.
T
h
i
s
r
e
s
e
a
r
c
h
ad
d
r
e
s
s
e
s
m
a
jo
r
d
a
t
a
i
s
s
u
e
s
b
y
c
r
ea
t
i
n
g
a
m
i
c
r
o
b
io
l
o
g
i
c
a
l
r
ec
o
g
n
i
t
io
n
m
o
d
e
l
.
W
e
u
s
e
d
t
h
e
Y
O
L
Ov
8
o
b
je
c
t
d
e
t
e
c
t
i
o
n
t
e
ch
n
iq
u
e
a
s
t
h
e
p
r
e
-
t
r
a
i
n
ed
m
o
d
e
l
u
s
i
n
g
t
r
an
s
f
e
r
l
ea
r
n
i
n
g
.
E
v
e
n
w
i
th
a
r
a
th
e
r
s
m
a
l
l
i
m
ag
e
d
a
ta
b
as
e
,
w
e
w
e
r
e
ab
l
e
t
o
i
d
e
n
t
if
y
f
u
n
g
i
an
d
b
a
c
te
r
i
a
in
P
e
t
r
i
d
i
s
h
e
s
.
T
h
e
m
o
d
e
l’
s
e
x
c
e
l
l
en
t
ac
c
u
r
a
c
y
i
n
r
e
c
o
g
n
iz
i
n
g
a
n
d
lo
c
a
l
i
z
in
g
b
a
c
t
e
r
ia
wa
s
a
ch
i
ev
e
d
w
i
th
ad
d
i
t
io
n
a
l
r
e
f
in
e
m
e
n
t
u
s
i
n
g
b
e
t
te
r
d
a
ta
th
a
t
w
a
s
f
i
r
s
t
a
n
n
o
t
a
t
ed
b
y
m
i
c
r
o
b
i
o
lo
g
y
p
r
o
f
e
s
s
i
o
n
a
l
s
.
T
h
i
s
i
l
lu
s
t
r
a
t
e
s
th
e
s
u
c
c
e
s
s
o
f
Y
OL
O
a
lg
o
r
i
t
h
m
s
i
n
t
h
e
s
e
a
p
p
l
i
c
a
t
io
n
s
a
n
d
h
e
l
p
s
a
l
le
v
i
a
t
e
t
h
e
w
o
r
k
l
o
a
d
f
r
o
m
h
u
m
an
f
o
r
t
a
s
k
s
s
u
ch
as
r
e
c
o
g
n
i
t
io
n
a
n
d
co
u
n
t
i
n
g
.
I
n
o
r
d
er
t
o
e
n
h
an
c
e
t
h
e
p
er
f
o
r
m
a
n
c
e
a
n
d
a
c
cu
r
a
cy
i
n
d
e
t
e
c
t
i
o
n
,
e
s
p
e
c
i
a
l
ly
f
o
r
s
m
a
l
l
o
b
j
e
c
t
s
,
t
h
e
f
u
t
u
r
e
wo
r
k
w
i
l
l
f
o
cu
s
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
26
:
11
32
-
11
42
1140
d
e
s
i
g
n
in
g
p
o
w
e
r
f
u
l
a
l
g
o
r
i
th
m
s
w
h
i
ch
ap
p
ly
i
n
g
h
ig
h
p
er
f
o
r
m
a
n
c
e
C
P
U
a
n
d
ex
t
en
d
in
g
t
h
e
p
l
at
e
ty
p
e
s
a
s
w
e
l
l
a
s
v
ar
i
e
ty
o
f
b
a
c
t
er
i
a
co
ll
e
c
t
i
o
n
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
ex
p
r
ess
th
eir
th
a
n
k
s
to
Mo
h
am
m
ed
V
Un
iv
e
r
s
ity
,
Facu
lty
of
Scien
ce
s
an
d
C
NR
ST
L
ab
o
r
ato
r
y
f
o
r
f
u
r
th
er
g
u
id
an
c
e
an
d
p
r
o
v
i
d
in
g
n
ec
ess
ar
y
in
f
o
r
m
atio
n
on
th
is
r
esear
ch
to
p
ic
d
o
cto
r
al
ab
o
u
t
th
e
b
ac
ter
ial
an
d
f
u
n
g
al
id
e
n
tific
atio
n
in
Petr
i
d
is
h
es.
T
h
e
a
u
th
o
r
s
also
th
an
k
all
th
o
s
e
wh
o
h
e
lp
ed
with
tech
n
ical
ass
is
tan
ce
or
ad
v
ice.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
ar
e
g
r
ate
f
u
l
to
t
h
e
in
s
titu
tio
n
f
o
r
s
u
p
p
o
r
t.
No
s
p
ec
if
ic
g
r
a
n
t,
f
u
n
d
i
n
g
o
r
g
a
n
izatio
n
or
f
in
an
cial
s
u
p
p
o
r
t
was
r
ec
eiv
ed
f
o
r
th
is
s
tu
d
y
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS
ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
T
ar
ik
B
o
u
g
an
s
s
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ma
r
y
em
Ait M
o
u
lay
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sam
ar
Aar
ab
i
✓
✓
✓
✓
Ab
d
elali
L
asfa
r
✓
✓
✓
✓
✓
✓
✓
Ab
d
ellatif
E
l A
f
ia
✓
✓
✓
✓
✓
✓
✓
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
OF
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
af
f
ir
m
th
at
th
e
r
e
ar
e
no
k
n
o
wn
f
i
n
an
cial,
p
e
r
s
o
n
al,
or
p
r
o
f
ess
io
n
al
ties
th
at
c
o
u
ld
h
av
e
af
f
ec
ted
th
e
f
i
n
d
in
g
s
or
in
ter
p
r
etatio
n
s
o
f
f
er
ed
in
th
is
s
tu
d
y
in
o
r
d
e
r
to
m
ai
n
tain
o
b
jectiv
ity
an
d
tr
an
s
p
a
r
en
cy
.
DATA
AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
t
h
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
of
t
h
is
s
tu
d
y
ar
e
av
ailab
l
e
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
M
.
A
n
sari
,
N
.
B
i
s
h
t
,
T.
S
i
n
g
h
,
a
n
d
P
.
S
.
C
h
a
u
h
a
n
,
“
S
y
m
p
h
o
n
y
o
f
s
u
r
v
i
v
a
l
:
i
n
s
i
g
h
t
s
i
n
t
o
c
r
o
ss
-
t
a
l
k
me
c
h
a
n
i
sms
i
n
p
l
a
n
t
s
,
b
a
c
t
e
r
i
a
,
a
n
d
f
u
n
g
i
f
o
r
st
r
e
n
g
t
h
e
n
i
n
g
p
l
a
n
t
i
m
mu
n
e
r
e
s
p
o
n
ses
,
”
Mi
c
r
o
b
i
o
l
o
g
i
c
a
l
R
e
se
a
rc
h
,
v
o
l
.
2
8
5
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
i
c
r
e
s
.
2
0
2
4
.
1
2
7
7
6
2
.
[
2
]
M
.
W
i
l
l
i
e
t
a
l
.
,
“
I
d
e
n
t
i
f
y
i
n
g
a
n
i
m
a
l
s
p
e
c
i
e
s
i
n
c
a
mera
t
r
a
p
i
ma
g
e
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
c
i
t
i
z
e
n
sc
i
e
n
c
e
,
”
Me
t
h
o
d
s
i
n
E
c
o
l
o
g
y
a
n
d
Ev
o
l
u
t
i
o
n
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
8
0
–
9
1
,
Ja
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
1
1
/
2
0
4
1
-
2
1
0
X
.
1
3
0
9
9
.
[
3
]
M
.
A
.
M
o
u
l
a
y
,
A
.
S
a
l
b
i
,
I
.
B
o
u
g
a
n
s
sa,
M
.
-
S
.
M
a
sm
o
u
d
i
,
a
n
d
A
.
La
sf
a
r
,
“
A
n
i
n
n
o
v
a
t
i
v
e
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
b
u
i
l
d
i
n
g
s
a
n
d
c
o
n
st
r
u
c
t
i
o
n
a
n
o
m
a
l
i
e
s
i
n
z
e
n
a
t
a
c
i
t
y
,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
2
7
0
3
-
2
7
1
2
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
3
.
p
p
2
7
0
3
-
2
7
1
2
.
[
4
]
C
.
S
.
C
o
s
t
a
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
l
i
e
d
i
n
f
i
sh
r
e
p
r
o
d
u
c
t
i
o
n
f
o
r
c
o
u
n
t
i
n
g
l
a
r
v
a
e
i
n
i
ma
g
e
s
c
a
p
t
u
r
e
d
b
y
smar
t
p
h
o
n
e
,
”
Aq
u
a
c
u
l
t
u
r
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
7
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
q
u
a
e
n
g
.
2
0
2
2
.
1
0
2
2
2
5
.
[
5
]
I
.
A
h
med
,
M
.
A
h
m
a
d
,
a
n
d
G
.
Je
o
n
,
“
I
n
t
e
g
r
a
t
i
n
g
d
i
g
i
t
a
l
t
w
i
n
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
me
d
i
c
a
l
i
ma
g
e
a
n
a
l
y
si
s
i
n
t
h
e
e
r
a
o
f
c
o
v
i
d
-
1
9
,
”
Vi
r
t
u
a
l
Re
a
l
i
t
y
&
I
n
t
e
l
l
i
g
e
n
t
H
a
r
d
w
a
re
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
2
9
2
–
3
0
5
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
v
r
i
h
.
2
0
2
2
.
0
3
.
0
0
2
.
[
6
]
X
.
C
h
e
n
,
H
.
Z
h
e
n
g
,
H
.
T
a
n
g
,
a
n
d
F
.
Li
,
“
M
u
l
t
i
-
sca
l
e
p
e
r
c
e
p
t
u
a
l
y
o
l
o
f
o
r
a
u
t
o
m
a
t
i
c
d
e
t
e
c
t
i
o
n
o
f
c
l
u
e
c
e
l
l
s
a
n
d
t
r
i
c
h
o
m
o
n
a
s
i
n
f
l
u
o
r
e
sc
e
n
c
e
mi
c
r
o
s
c
o
p
i
c
i
m
a
g
e
s,”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
7
5
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
b
i
o
me
d
.
2
0
2
4
.
1
0
8
5
0
0
.
[
7
]
J.
Li
,
W
.
C
h
e
n
,
Y
.
Zh
u
,
K
.
X
u
a
n
,
H
.
Li
,
a
n
d
N
.
Z
e
n
g
,
“
I
n
t
e
l
l
i
g
e
n
t
d
e
t
e
c
t
i
o
n
a
n
d
b
e
h
a
v
i
o
r
t
r
a
c
k
i
n
g
u
n
d
e
r
a
mm
o
n
i
a
n
i
t
r
o
g
e
n
st
r
e
ss,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
5
5
9
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
2
3
.
1
2
6
8
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
b
a
cteria
a
n
d
fu
n
g
i
cla
s
s
ifica
tio
n
u
s
in
g
co
n
vo
lu
tio
n
a
l n
eu
r
a
l
n
etw
o
r
k
o
n
…
(
Ta
r
ik
B
o
u
g
a
n
s
s
a
)
1141
[
8
]
F
.
Ju
b
a
y
e
r
e
t
a
l
.
,
“
D
e
t
e
c
t
i
o
n
o
f
m
o
l
d
o
n
t
h
e
f
o
o
d
s
u
r
f
a
c
e
u
si
n
g
Y
O
LO
v
5
,
”
C
u
rre
n
t
Re
s
e
a
r
c
h
i
n
F
o
o
d
S
c
i
e
n
c
e
,
v
o
l
.
4
,
p
p
.
7
2
4
–
7
2
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
r
f
s.2
0
2
1
.
1
0
.
0
0
3
.
[
9
]
S
.
S
c
h
n
e
i
d
e
r
,
G
.
W
.
T
a
y
l
o
r
,
a
n
d
S
.
K
r
e
m
e
r
,
“
D
e
e
p
l
e
a
r
n
i
n
g
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
met
h
o
d
s
f
o
r
e
c
o
l
o
g
i
c
a
l
c
a
m
e
r
a
t
r
a
p
d
a
t
a
,
”
i
n
2
0
1
8
1
5
t
h
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
Ro
b
o
t
V
i
si
o
n
(
C
RV)
,
I
EEE,
M
a
y
2
0
1
8
,
p
p
.
3
2
1
–
3
2
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
R
V
.
2
0
1
8
.
0
0
0
5
2
.
[
1
0
]
S
.
A
a
r
a
b
i
,
O
.
C
h
a
u
i
y
a
k
h
,
T
.
B
o
u
g
a
n
s
sa,
E.
E
.
F
a
h
i
m
e
,
a
n
d
A
.
Et
-
t
a
h
i
r
,
“
B
i
o
a
c
c
u
mu
l
a
t
i
o
n
o
f
h
e
a
v
y
met
a
l
s
i
n
f
i
v
e
s
p
e
c
i
e
s
o
f
f
i
s
h
o
b
t
a
i
n
e
d
f
r
o
m
t
h
e
e
s
t
u
a
r
y
o
f
r
a
b
a
t
,
mo
r
o
c
c
o
,
”
T
r
o
p
i
c
a
l
J
o
u
r
n
a
l
o
f
N
a
t
u
r
a
l
Pr
o
d
u
c
t
R
e
se
a
rc
h
,
v
o
l
.
8
,
n
o
.
4
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
2
6
5
3
8
/
t
j
n
p
r
/
v
8
i
4
.
3
.
[
1
1
]
Q
.
Y
a
o
,
X
.
Z
h
e
n
g
,
G
.
Z
h
o
u
,
a
n
d
J.
Z
h
a
n
g
,
“
S
G
R
-
y
o
l
o
:
a
me
t
h
o
d
f
o
r
d
e
t
e
c
t
i
n
g
s
e
e
d
g
e
r
mi
n
a
t
i
o
n
r
a
t
e
i
n
w
i
l
d
r
i
c
e
,
”
F
ro
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
4
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
2
3
.
1
3
0
5
0
8
1
.
[
1
2
]
D
.
D
o
h
e
r
t
y
e
t
a
l
.
,
“
A
ssess
i
n
g
t
h
e
v
i
a
b
i
l
i
t
y
o
f
3
d
-
p
r
i
n
t
e
d
p
o
l
y
(
l
a
c
t
i
c
a
c
i
d
)
p
e
t
r
i
d
i
s
h
e
s:
a
su
s
t
a
i
n
a
b
l
e
a
l
t
e
r
n
a
t
i
v
e
f
o
r
l
a
b
o
r
a
t
o
r
y
u
se,
”
S
u
st
a
i
n
a
b
l
e
M
a
t
e
r
i
a
l
s
a
n
d
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
4
0
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
u
sm
a
t
.
2
0
2
4
.
e
0
0
8
9
9
.
[
1
3
]
Q
.
W
u
e
t
a
l
.
,
“
Th
e
s
c
r
e
e
n
i
n
g
a
n
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
s
i
x
c
o
mm
o
n
l
y
u
s
e
d
a
n
t
i
b
i
o
t
i
c
s
i
n
sw
i
n
e
k
i
d
n
e
y
b
y
a
m
i
c
r
o
b
i
o
l
o
g
i
c
a
l
i
n
h
i
b
i
t
i
o
n
met
h
o
d
,
”
Mi
c
r
o
c
h
e
m
i
c
a
l
J
o
u
rn
a
l
,
v
o
l
.
1
6
1
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mi
c
r
o
c
.
2
0
2
0
.
1
0
5
7
9
6
.
[
1
4
]
E.
A
.
La
n
d
i
s
,
E.
F
o
g
a
r
t
y
,
J
.
C
.
Ed
w
a
r
d
s,
O
.
P
o
p
a
,
A
.
M
.
Er
e
n
,
a
n
d
B
.
E.
W
o
l
f
e
,
“
M
i
c
r
o
b
i
a
l
d
i
v
e
r
s
i
t
y
a
n
d
i
n
t
e
r
a
c
t
i
o
n
s
p
e
c
i
f
i
c
i
t
y
i
n
k
o
m
b
u
c
h
a
t
e
a
f
e
r
m
e
n
t
a
t
i
o
n
s,”
m
S
y
st
e
m
s
,
v
o
l
.
7
,
n
o
.
3
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
2
8
/
ms
y
st
e
ms.
0
0
1
5
7
-
2
2
.
[
1
5
]
N
.
R
.
M
a
n
n
u
r
u
e
t
a
l
.
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
d
e
v
e
l
o
p
i
n
g
c
o
u
n
t
r
i
e
s
:
t
h
e
i
m
p
a
c
t
o
f
g
e
n
e
r
a
t
i
v
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
(
AI
)
t
e
c
h
n
o
l
o
g
i
e
s
f
o
r
d
e
v
e
l
o
p
m
e
n
t
,
”
I
n
f
o
r
m
a
t
i
o
n
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
4
1
,
n
o
.
3
,
p
p
.
1
0
3
6
–
1
0
5
4
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
7
7
/
0
2
6
6
6
6
6
9
2
3
1
2
0
0
6
2
8
.
[
1
6
]
R
.
B
u
n
o
d
,
E.
A
u
g
s
t
b
u
r
g
e
r
,
E.
B
r
a
s
n
u
,
A
.
L
a
b
b
e
,
a
n
d
C
.
B
a
u
d
o
u
i
n
,
“
I
n
t
e
l
l
i
g
e
n
c
e
a
r
t
i
f
i
c
i
e
l
l
e
e
t
g
l
a
u
c
o
me
:
u
n
e
r
e
v
u
e
d
e
l
a
l
i
t
t
é
r
a
t
u
r
e
,
”
J
o
u
rn
a
l
Fr
a
n
ç
a
i
s
d
’
O
p
h
t
a
l
m
o
l
o
g
i
e
,
v
o
l
.
4
5
,
n
o
.
2
,
p
p
.
2
1
6
–
2
3
2
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
f
o
.
2
0
2
1
.
1
1
.
0
0
2
.
[
1
7
]
J.
K
i
m
e
t
a
l
.
,
“
A
n
o
v
e
l
d
e
e
p
l
e
a
r
n
i
n
g
–
b
a
se
d
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
sy
s
t
e
m
f
o
r
i
n
t
e
r
p
r
e
t
i
n
g
u
r
o
l
i
t
h
i
a
si
s
i
n
c
o
m
p
u
t
e
d
t
o
mo
g
r
a
p
h
y
,
”
Eu
r
o
p
e
a
n
U
r
o
l
o
g
y
Fo
c
u
s
,
v
o
l
.
1
0
,
n
o
.
6
,
p
p
.
1
0
4
9
–
1
0
5
4
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
u
f
.
2
0
2
4
.
0
7
.
0
0
3
.
[
1
8
]
J.
Te
r
v
e
n
,
D
.
M
.
C
.
Es
p
a
r
z
a
,
a
n
d
J.
A
.
R
.
G
o
n
z
á
l
e
z
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
y
o
l
o
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
l
o
v
1
t
o
y
o
l
o
v
8
a
n
d
y
o
l
o
-
n
a
s,
”
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
K
n
o
w
l
e
d
g
e
E
x
t
ra
c
t
i
o
n
,
v
o
l
.
5
,
n
o
.
4
,
p
p
.
1
6
8
0
–
1
7
1
6
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
k
e
5
0
4
0
0
8
3
.
[
1
9
]
K
.
A
l
o
mar,
H
.
I
.
A
y
s
e
l
,
a
n
d
X
.
C
a
i
,
“
C
N
N
s,
r
n
n
s
a
n
d
t
r
a
n
sf
o
r
mers
i
n
h
u
man
a
c
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
:
a
s
u
r
v
e
y
a
n
d
a
h
y
b
r
i
d
mo
d
e
l
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
8
,
n
o
.
1
2
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
2
5
-
1
1
3
8
8
-
3.
[
2
0
]
I
.
B
o
u
g
a
n
s
s
a
,
H
.
B
e
n
r
a
d
i
,
A
.
S
a
l
b
i
,
M
.
S
b
i
h
i
,
a
n
d
A
.
L
a
s
f
a
r
,
“
E
m
b
e
d
d
e
d
f
p
g
a
h
a
r
d
w
a
r
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
a
p
r
e
p
r
o
c
e
s
s
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
s
u
r
v
e
i
l
l
a
n
c
e
i
m
a
g
e
s
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
a
n
d
A
p
p
l
i
e
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
1
,
n
o
.
1
9
,
p
p
.
6
0
0
1
–
6
0
1
2
,
2
0
2
3
.
[
2
1
]
J.
R
e
d
m
o
n
,
S
.
D
i
v
v
a
l
a
,
R
.
G
i
r
s
h
i
c
k
,
a
n
d
A
.
F
a
r
h
a
d
i
,
“
Y
o
u
o
n
l
y
l
o
o
k
o
n
c
e
:
u
n
i
f
i
e
d
,
r
e
a
l
-
t
i
me
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
,
”
2
0
1
6
I
E
E
E
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
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
(
C
VP
R)
,
L
a
s
V
e
g
a
s,
N
V
,
U
S
A,
2
0
1
6
,
p
p
.
7
7
9
-
7
8
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
6
.
9
1
.
[
2
2
]
C
.
M
.
B
a
d
g
u
j
a
r
,
A
.
P
o
u
l
o
se,
a
n
d
H
.
G
a
n
,
“
A
g
r
i
c
u
l
t
u
r
a
l
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
w
i
t
h
y
o
u
o
n
l
y
l
o
o
k
o
n
c
e
(
y
o
l
o
)
a
l
g
o
r
i
t
h
m:
a
b
i
b
l
i
o
m
e
t
r
i
c
a
n
d
s
y
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
o
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
r
e
,
v
o
l
.
2
2
3
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
4
.
1
0
9
0
9
0
.
[
2
3
]
Z.
C
a
i
,
Y
.
Zh
a
n
g
,
J.
L
i
,
J.
Z
h
a
n
g
,
a
n
d
X
.
L
i
,
“
S
y
n
c
h
r
o
n
o
u
s
d
e
t
e
c
t
i
o
n
o
f
i
n
t
e
r
n
a
l
a
n
d
e
x
t
e
r
n
a
l
d
e
f
e
c
t
s
o
f
c
i
t
r
u
s
b
y
st
r
u
c
t
u
r
e
d
-
i
l
l
u
m
i
n
a
t
i
o
n
r
e
f
l
e
c
t
a
n
c
e
i
m
a
g
i
n
g
c
o
u
p
l
i
n
g
w
i
t
h
i
m
p
r
o
v
e
d
Y
O
LO
v
7
,
”
Po
s
t
h
a
rv
e
st
Bi
o
l
o
g
y
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
2
7
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
o
st
h
a
r
v
b
i
o
.
2
0
2
5
.
1
1
3
5
7
6
.
[
2
4
]
S
a
n
d
h
y
a
a
n
d
A
.
K
a
s
h
y
a
p
,
“
A
n
o
v
e
l
met
h
o
d
f
o
r
r
e
a
l
-
t
i
m
e
o
b
j
e
c
t
-
b
a
s
e
d
c
o
p
y
-
m
o
v
e
t
a
m
p
e
r
i
n
g
l
o
c
a
l
i
z
a
t
i
o
n
i
n
v
i
d
e
o
s
u
s
i
n
g
f
i
n
e
-
t
u
n
e
d
Y
O
LO
v
8
,
”
F
o
re
n
si
c
S
c
i
e
n
c
e
I
n
t
e
rn
a
t
i
o
n
a
l
:
D
i
g
i
t
a
l
I
n
v
e
s
t
i
g
a
t
i
o
n
,
v
o
l
.
4
8
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
s
i
d
i
.
2
0
2
3
.
3
0
1
6
6
3
.
[
2
5
]
P
.
J
i
a
n
g
,
D
.
Er
g
u
,
F
.
L
i
u
,
Y
.
C
a
i
,
a
n
d
B
.
M
a
,
“
A
r
e
v
i
e
w
o
f
Y
O
LO
a
l
g
o
r
i
t
h
m
d
e
v
e
l
o
p
me
n
t
s,”
P
ro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
9
9
,
p
p
.
1
0
6
6
–
1
0
7
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
2
.
0
1
.
1
3
5
.
[
2
6
]
H
.
C
h
e
n
a
n
d
J.
Ta
o
,
“
U
t
i
l
i
z
i
n
g
i
m
p
r
o
v
e
d
y
o
l
o
v
8
b
a
se
d
o
n
SPD
-
B
R
S
A
-
A
F
P
N
f
o
r
u
l
t
r
a
so
n
i
c
p
h
a
s
e
d
a
r
r
a
y
n
o
n
-
d
e
st
r
u
c
t
i
v
e
t
e
st
i
n
g
,
”
U
l
t
r
a
so
n
i
c
s
,
v
o
l
.
1
4
2
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
u
l
t
r
a
s.
2
0
2
4
.
1
0
7
3
8
2
.
[
2
7
]
C
.
C
h
e
n
,
H
.
Le
e
,
a
n
d
M
.
C
h
e
n
,
“
S
t
e
e
l
su
r
f
a
c
e
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
met
h
o
d
b
a
s
e
d
o
n
i
mp
r
o
v
e
d
Y
O
LO
v
9
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
1
0
6
4
7
-
1.
[
2
8
]
S
.
S
u
n
,
B
.
M
o
,
J.
X
u
,
D
.
L
i
,
J
.
Z
h
a
o
,
a
n
d
S
.
H
a
n
,
“
M
u
l
t
i
-
Y
O
LO
v
8
:
a
n
i
n
f
r
a
r
e
d
m
o
v
i
n
g
sma
l
l
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
mo
d
e
l
b
a
se
d
o
n
Y
O
LO
v
8
f
o
r
a
i
r
v
e
h
i
c
l
e
,
”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
5
8
8
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
2
4
.
1
2
7
6
8
5
.
[
2
9
]
A
.
S
.
M
.
M
.
H
a
sa
n
,
D
.
D
i
e
p
e
v
e
e
n
,
H
.
La
g
a
,
M
.
G
.
K
.
J
o
n
e
s
,
a
n
d
F
.
S
o
h
e
l
,
“
O
b
j
e
c
t
-
l
e
v
e
l
b
e
n
c
h
mar
k
f
o
r
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
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
w
e
e
d
s
p
e
c
i
e
s
,
”
C
r
o
p
Pr
o
t
e
c
t
i
o
n
,
v
o
l
.
1
7
7
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
r
o
p
r
o
.
2
0
2
3
.
1
0
6
5
6
1
.
[
3
0
]
H
.
B
e
n
r
a
d
i
,
I
.
B
o
u
g
a
n
ssa,
A
.
C
h
a
t
e
r
,
a
n
d
A
.
L
a
sf
a
r
,
“
D
i
s
c
r
i
mi
n
a
t
i
v
e
a
p
p
r
o
a
c
h
l
u
n
g
d
i
se
a
ses
a
n
d
c
o
v
i
d
-
1
9
f
r
o
m c
h
e
s
t
x
-
r
a
y
i
ma
g
e
s
u
si
n
g
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
p
r
o
m
i
si
n
g
a
p
p
r
o
a
c
h
f
o
r
a
c
c
u
r
a
t
e
d
i
a
g
n
o
s
i
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
O
n
l
i
n
e
and
Bi
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
9
,
n
o
.
1
4
,
p
p
.
1
3
1
–
1
4
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
9
9
1
/
i
j
o
e
.
v
1
9
i
1
4
.
4
2
7
2
5
.
[
3
1
]
J.
D
i
n
g
,
J
.
Z
h
a
n
g
,
Z.
Z
h
a
n
,
X
.
Ta
n
g
,
a
n
d
X
.
W
a
n
g
,
“
A
p
r
e
c
i
si
o
n
e
f
f
i
c
i
e
n
t
m
e
t
h
o
d
f
o
r
c
o
l
l
a
p
s
e
d
b
u
i
l
d
i
n
g
d
e
t
e
c
t
i
o
n
i
n
p
o
s
t
-
e
a
r
t
h
q
u
a
k
e
u
a
v
i
m
a
g
e
s
b
a
s
e
d
o
n
t
h
e
i
mp
r
o
v
e
d
N
M
S
a
l
g
o
r
i
t
h
m
a
n
d
f
a
st
e
r
R
-
C
N
N
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
4
,
n
o
.
3
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
4
0
3
0
6
6
3
.
B
I
O
G
RAP
H
I
E
S
OF
AUTH
O
RS
Ta
r
ik
B
o
u
g
a
n
ss
a
re
c
e
iv
e
d
h
is
Ph
.
D
.
st
u
d
e
n
t
in
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
a
n
d
En
g
i
n
e
e
rin
g
S
c
ien
c
e
s
o
p
ti
o
n
:
A
p
p
li
e
d
M
a
t
h
e
m
a
ti
c
s
a
n
d
Artifi
c
i
a
l
In
telli
g
e
n
c
e
,
Lab
o
ra
to
r
y
:
S
m
a
rt
S
y
ste
m
s
Lab
o
ra
to
r
y
(
S
S
L
)
at
t
h
e
Na
ti
o
n
a
l
S
c
h
o
o
l
of
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
S
y
ste
m
s
An
a
ly
sis
(ENS
IAS)
,
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
of
Ra
b
a
t.
M
a
ste
r
of
Re
se
a
rc
h
in
M
a
th
e
m
a
ti
c
s
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
(2
0
2
1
)
o
p
ti
o
n
:
d
a
ta
sc
ien
c
e
a
n
d
b
i
g
d
a
ta
at
th
e
Na
ti
o
n
a
l
S
c
h
o
o
l
of
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
S
y
ste
m
s
An
a
ly
sis
(ENS
IAS),
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
of
Ra
b
a
t.
Ba
c
h
e
lo
r
of
F
u
n
d
a
m
e
n
tal
S
tu
d
ie
s
(2
0
0
9
)
in
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s
a
n
d
Co
m
p
u
ter
S
c
ie
n
c
e
(S
M
I)
at
th
e
F
a
c
u
lt
y
of
S
c
ien
c
e
s
of
Ra
b
a
t
F
S
R,
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
Ra
b
a
t
-
Ag
d
a
l.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
tarik
.
b
o
u
g
a
n
ss
a
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.