Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
,
p
p
.
3
6
9
~
3
7
6
I
SS
N:
2722
-
3
2
2
1
,
DOI
:
1
0
.
1
1
5
9
1
/csi
t
.
v
7
i
3
.
p
3
6
9
-
3
7
6
369
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
O
ptimi
zing
dee
p l
ea
rning
mo
dels fo
r plant l
ea
f
disea
s
e
cla
ss
ificatio
n usin
g
nature
-
inspi
red
a
lg
o
rithms
Av
ines
h C
ull
o
o
,
Av
ina
s
h B
h
un
j
un
,
G
ee
ris
h Sud
du
l
D
e
p
a
r
t
me
n
t
o
f
B
u
si
n
e
ss
I
n
f
o
r
mat
i
c
s
a
n
d
S
o
f
t
w
a
r
e
En
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
I
n
n
o
v
a
t
i
v
e
Te
c
h
n
o
l
o
g
i
e
s
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
o
f
Te
c
h
n
o
l
o
g
y
,
M
a
u
r
i
t
i
u
s (
U
TM
)
,
P
o
r
t
Lo
u
i
s,
M
a
u
r
i
t
i
u
s
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
27
,
2
0
2
6
R
ev
is
ed
J
u
l
2
,
2
0
2
6
Acc
ep
ted
J
u
l
13
,
2
0
2
6
P
lan
t
d
ise
a
se
s
g
re
a
tl
y
a
ffe
c
t
a
g
ric
u
lt
u
ra
l
p
r
o
d
u
c
ti
o
n
,
e
sp
e
c
ially
i
n
d
e
v
e
lo
p
i
n
g
c
o
u
n
tr
ies
,
wh
e
re
p
r
o
m
p
t
d
iag
n
o
sis
c
a
n
b
e
q
u
it
e
c
h
a
ll
e
n
g
i
n
g
d
u
e
to
th
e
li
m
it
e
d
a
v
a
il
a
b
il
it
y
o
f
e
x
p
e
rts
i
n
re
a
l
-
ti
m
e
.
De
e
p
lea
rn
in
g
tec
h
n
iq
u
e
s
fo
r
ima
g
e
a
n
a
ly
sis
is
g
a
i
n
in
g
p
o
p
u
l
a
rit
y
a
n
d
a
re
in
c
re
a
sin
g
l
y
c
o
n
s
id
e
re
d
a
n
a
lt
e
rn
a
ti
v
e
to
trad
it
i
o
n
a
l
m
a
n
u
a
l
i
n
sp
e
c
ti
o
n
o
f
p
lan
ts.
Th
is
re
se
a
rc
h
p
re
se
n
ts
th
e
e
v
a
l
u
a
ti
o
n
o
f
p
lan
t
lea
f
d
ise
a
se
d
e
tec
ti
o
n
sy
ste
m
b
a
se
d
o
n
a
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(
CNN
)
o
p
ti
m
ize
d
with
d
iffere
n
t
n
a
t
u
re
-
in
sp
ired
a
lg
o
rit
h
m
s
.
T
h
e
b
a
c
k
b
o
n
e
m
o
d
e
l
is
b
a
se
d
o
n
t
h
e
Eff
icie
n
tNe
t
-
B0
p
re
train
e
d
o
n
Im
a
g
e
Ne
t.
Th
e
re
f
o
re
,
tran
sfe
r
lea
rn
in
g
is
u
se
d
t
o
a
d
a
p
t
th
e
m
o
d
e
l
to
a
n
u
p
d
a
ted
P
lan
t
V
i
ll
a
g
e
d
a
tas
e
t.
Ex
p
e
rime
n
ts
h
a
v
e
b
e
e
n
c
o
n
d
u
c
ted
with
m
u
lt
i
p
le
n
a
t
u
re
-
in
s
p
ired
a
lg
o
rit
h
m
s
to
imp
ro
v
e
g
e
n
e
ra
li
s
a
ti
o
n
a
n
d
train
in
g
e
fficie
n
c
y
o
f
th
e
p
re
d
ictio
n
m
o
d
e
l.
Diffe
re
n
t
d
a
ta
p
re
p
a
ra
ti
o
n
tec
h
n
iq
u
e
s
h
a
v
e
b
e
e
n
c
a
re
fu
ll
y
a
p
p
li
e
d
t
o
th
e
d
a
tas
e
t,
c
re
a
ti
n
g
a
u
n
ifi
e
d
a
p
p
ro
a
c
h
t
o
e
n
s
u
re
c
o
n
siste
n
c
y
in
th
e
p
re
p
r
o
c
e
ss
in
g
p
ip
e
l
in
e
fo
r
th
e
train
in
g
,
v
a
li
d
a
ti
o
n
,
a
n
d
tes
ti
n
g
p
h
a
se
s.
O
u
r
e
x
p
e
rime
n
ts
i
n
d
ica
te
th
a
t
a
p
p
l
ica
ti
o
n
o
f
th
e
g
re
y
wo
lf
o
p
ti
m
ize
r
(G
WO)
fo
r
t
u
n
in
g
k
e
y
h
y
p
e
rp
a
ra
m
e
te
rs
o
f
t
h
e
m
o
d
e
l,
in
c
l
u
d
i
n
g
d
ro
p
o
u
t,
lea
rn
in
g
ra
tes
,
a
n
d
we
ig
h
t
d
e
c
a
y
p
r
o
d
u
c
e
d
th
e
b
e
s
t
re
su
lt
s,
with
a
n
a
c
c
u
r
a
c
y
a
ro
u
n
d
9
9
.
4
5
%
.
K
ey
w
o
r
d
s
:
C
o
m
p
u
ter
v
is
io
n
L
ea
f
d
is
ea
s
e
class
if
icatio
n
Natu
r
e
-
in
s
p
ir
ed
alg
o
r
ith
m
Op
tim
izatio
n
T
r
an
s
f
er
lear
n
i
n
g
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
:
Gee
r
is
h
Su
d
d
u
l
Dep
ar
tm
en
t o
f
B
u
s
in
ess
I
n
f
o
r
m
atics a
n
d
So
f
twar
e
E
n
g
in
ee
r
in
g
,
Sch
o
o
l
o
f
I
n
n
o
v
ativ
e
T
ec
h
n
o
lo
g
ies
Un
iv
er
s
ity
o
f
T
ec
h
n
o
lo
g
y
,
Ma
u
r
itiu
s
(
UT
M)
L
a
T
o
u
r
K
o
en
ig
,
Po
i
n
te
-
au
x
-
Sab
les,
Po
r
t L
o
u
is
,
Ma
u
r
itiu
s
E
m
ail: g
.
s
u
d
d
u
l@
u
tm
.
ac
.
m
u
1.
I
NT
RO
D
UCT
I
O
N
Ag
r
icu
ltu
r
e
r
em
ain
s
a
v
ital
s
ec
to
r
f
o
r
en
s
u
r
in
g
f
o
o
d
s
ec
u
r
ity
an
d
ec
o
n
o
m
ic
s
u
s
tain
ab
ilit
y
,
p
ar
ticu
lar
ly
in
d
ev
el
o
p
in
g
an
d
is
lan
d
n
atio
n
s
s
u
ch
as
Ma
u
r
itiu
s
.
I
m
p
r
o
v
in
g
ag
r
icu
ltu
r
a
l
p
r
o
d
u
ctiv
ity
a
n
d
cr
o
p
h
ea
lth
is
th
er
ef
o
r
e
ess
en
tial
to
s
u
p
p
o
r
t
g
l
o
b
al
i
n
itia
tiv
es
s
u
ch
as
t
h
e
Un
ited
Natio
n
s
Su
s
tain
ab
le
Dev
elo
p
m
en
t
G
o
al
2
,
wh
ich
f
o
cu
s
es
o
n
en
s
u
r
in
g
f
o
o
d
s
ec
u
r
ity
,
en
c
o
u
r
a
g
in
g
s
u
s
tain
ab
le
ag
r
icu
ltu
r
e
an
d
en
d
in
g
h
u
n
g
er
[
1
]
.
Ho
wev
er
,
cr
o
p
p
r
o
d
u
ctio
n
is
f
r
eq
u
e
n
tly
af
f
ec
ted
b
y
p
lan
t
d
is
ea
s
es,
wh
ich
ca
n
s
ig
n
if
ican
tly
r
ed
u
ce
y
ield
an
d
q
u
ality
if
n
o
t
id
en
tifie
d
at
an
ea
r
ly
s
tag
e
.
I
n
m
a
n
y
ag
r
icu
ltu
r
al
s
ettin
g
s
,
d
is
ea
s
e
d
iag
n
o
s
is
r
elies
o
n
m
a
n
u
al
e
x
am
in
atio
n
o
f
th
e
p
lan
t
b
y
f
ar
m
er
s
o
r
e
x
p
er
ts
in
ag
r
icu
ltu
r
e.
T
h
is
p
r
o
ce
s
s
is
o
f
ten
tim
e
co
n
s
u
m
in
g
,
s
u
b
jectiv
e,
an
d
n
o
t
alwa
y
s
ac
c
ess
ib
le
to
s
m
all
h
o
ld
er
f
a
r
m
er
s
,
esp
ec
ially
in
r
em
o
te
o
r
r
eso
u
r
ce
-
lim
ited
en
v
ir
o
n
m
en
ts
[
2
]
,
[
3
]
.
W
ith
r
ec
en
t
ad
v
an
ce
s
in
ar
tifi
cial
in
tellig
en
ce
,
c
o
m
p
u
te
r
v
is
io
n
h
as
em
er
g
e
d
as
a
p
r
o
m
is
in
g
to
o
l
f
o
r
s
u
p
p
o
r
tin
g
ag
r
icu
ltu
r
al
d
ec
is
io
n
m
a
k
in
g
.
I
m
a
g
e
-
b
ased
d
is
ea
s
e
d
etec
tio
n
s
y
s
tem
s
allo
w
p
lan
t
h
ea
lth
to
b
e
ass
es
s
ed
d
ir
ec
tly
f
r
o
m
leaf
im
ag
es,
m
in
im
is
in
g
th
e
n
ee
d
f
o
r
m
a
n
u
al
in
s
p
ec
tio
n
.
C
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
d
em
o
n
s
tr
ate
th
e
ab
ilit
y
to
au
to
m
atica
ll
y
lear
n
r
elev
an
t
f
ea
tu
r
es
f
r
o
m
r
aw
im
ag
e
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
6
9
-
376
370
in
d
icatin
g
its
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
in
co
m
p
u
te
r
v
is
io
n
task
s
.
Pre
v
io
u
s
s
tu
d
ies
s
h
o
w
th
at
C
NN
-
b
ased
m
o
d
els
ca
n
ef
f
ec
tiv
el
y
id
e
n
tify
d
is
ea
s
e
s
y
m
p
to
m
s
s
u
ch
as
d
is
co
lo
r
a
tio
n
,
lesi
o
n
s
,
an
d
ir
r
eg
u
lar
lea
f
tex
tu
r
es
m
ak
in
g
th
em
a
s
u
itab
le
ap
p
r
o
ac
h
f
o
r
t
h
e
p
lan
t le
af
d
is
ea
s
e
d
etec
tio
n
[
4
]
–
[
9
]
.
Alth
o
u
g
h
C
NN
-
b
ased
m
o
d
els
h
av
e
d
em
o
n
s
tr
ated
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
,
s
ev
er
al
ch
allen
g
es
r
em
ain
.
Dee
p
l
ea
r
n
in
g
m
o
d
els
r
eq
u
ir
e
lar
g
e
am
o
u
n
ts
o
f
lab
ele
d
d
ata
f
o
r
ef
f
ec
tiv
e
tr
ain
in
g
an
d
m
ay
b
e
p
r
o
n
e
to
o
v
er
f
itti
n
g
,
p
ar
ticu
lar
ly
wh
e
n
tr
ain
ed
o
n
d
at
asets
u
n
d
er
co
n
tr
o
lled
co
n
d
itio
n
s
.
T
o
m
itig
at
e
th
ese
lim
itatio
n
s
,
tech
n
iq
u
es
s
u
ch
as
tr
a
n
s
f
er
l
ea
r
n
in
g
an
d
o
p
tim
is
atio
n
ap
p
r
o
ac
h
es
h
av
e
b
ee
n
u
tili
s
ed
to
en
h
a
n
ce
m
o
d
e
l
g
en
er
aliza
tio
n
a
n
d
tr
ain
in
g
e
f
f
icien
cy
.
Ad
d
itio
n
ally
,
d
ata
p
r
ep
ar
atio
n
an
d
p
r
ep
r
o
ce
s
s
in
g
ar
e
ess
en
tial
f
o
r
co
m
p
u
ter
v
is
io
n
s
y
s
tem
s
,
as th
ese
s
tep
s
p
lay
a
cr
itical
r
o
le
in
d
eter
m
in
in
g
o
v
e
r
all
m
o
d
el
p
e
r
f
o
r
m
a
n
ce
[
1
0
]
.
T
h
e
Plan
tVillag
e
d
ataset
[
1
1
]
is
co
m
m
o
n
ly
u
s
ed
in
d
i
g
ital
ag
r
icu
ltu
r
e
f
o
r
th
e
au
to
m
atio
n
o
f
p
lan
t
d
is
ea
s
e
p
r
ed
ictio
n
co
n
s
is
tin
g
o
f
1
4
cr
o
p
ca
teg
o
r
ies
an
d
2
6
d
is
ea
s
es.
W
e
f
o
cu
s
ed
o
n
a
s
u
b
s
et
o
f
th
e
d
ataset,
k
n
o
wn
as
th
e
‘
p
lan
t
v
illag
e
d
ataset
(
u
p
d
ated
)
’
f
r
o
m
Kag
g
le
[
1
2
]
,
co
m
p
r
is
in
g
o
f
n
in
e
m
ain
cr
o
p
s
p
ec
ies,
n
am
ely
ap
p
le,
b
ell
p
ep
p
e
r
,
c
h
er
r
y
,
g
r
a
p
e,
p
ea
c
h
,
s
tr
awb
er
r
y
,
to
m
at
o
,
p
o
tato
,
a
n
d
c
o
r
n
(
m
aize
)
.
E
ac
h
cr
o
p
ca
teg
o
r
y
co
n
tain
s
m
u
ltip
le
cl
ass
es
r
ep
r
esen
tin
g
eith
er
s
p
ec
if
ic
p
lan
t
d
is
ea
s
es
o
r
h
ea
lth
y
p
lan
t
co
n
d
itio
n
s
.
T
h
e
p
r
o
b
lem
is
th
er
ef
o
r
e
a
class
if
icatio
n
task
with
m
u
ltip
le
class
e
s
,
wh
er
e
ea
ch
im
ag
e
is
as
s
ig
n
ed
to
its
co
r
r
e
s
p
o
n
d
in
g
class
lab
el
s
u
ch
as
to
m
o
t
o
_
b
ac
ter
ial
_
s
p
o
t,
to
m
ato
_
ea
r
l
y
_
b
lig
h
t,
to
m
a
to
_
late_
b
lig
h
t,
an
d
to
m
ato
_
h
ea
lth
y
.
Ou
r
p
r
o
p
o
s
ed
m
eth
o
d
co
m
b
in
es
a
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
with
o
p
tim
is
atio
n
t
ec
h
n
iq
u
es
in
s
p
ir
ed
b
y
n
at
u
r
al
p
r
o
ce
s
s
es
to
en
h
a
n
ce
m
o
d
el
p
er
f
o
r
m
a
n
c
e.
Ad
d
itio
n
ally
,
s
tan
d
ar
d
ized
p
r
ep
r
o
ce
s
s
in
g
an
d
ev
alu
atio
n
s
tr
ateg
ies
ar
e
em
p
lo
y
ed
to
ass
ess
clas
s
if
icatio
n
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
Stan
d
ar
d
p
e
r
f
o
r
m
an
ce
m
etr
ics,
alo
n
g
with
co
m
p
a
r
a
tiv
e
ex
p
er
im
e
n
ts
,
ar
e
ad
o
p
te
d
to
a
n
aly
s
e
th
e
ef
f
ec
tiv
en
es
s
o
f
th
e
p
r
o
p
o
s
e
d
ap
p
r
o
ac
h
.
T
h
e
p
r
im
ar
y
co
n
tr
i
b
u
tio
n
s
o
f
th
is
wo
r
k
ar
e
f
ir
s
tly
th
e
ap
p
licatio
n
o
f
m
etah
eu
r
is
tic
alg
o
r
ith
m
s
f
o
r
h
y
p
er
p
ar
am
eter
tu
n
in
g
o
f
th
e
m
o
d
el
an
d
s
ec
o
n
d
ly
,
a
co
m
p
r
eh
en
s
iv
e
ev
alu
atio
n
an
d
co
m
p
ar
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
u
s
in
g
b
e
n
c
h
m
ar
k
d
atasets
.
T
h
e
r
est
o
f
th
is
p
ap
e
r
is
o
r
g
a
n
is
ed
as
:
s
ec
tio
n
2
s
h
o
ws
th
e
m
eth
o
d
s
u
s
ed
in
th
is
s
tu
d
y
,
i
n
clu
d
in
g
th
e
C
NN
ar
ch
itectu
r
e,
o
p
tim
is
ati
o
n
s
tr
ateg
y
,
d
ataset
p
r
ep
a
r
atio
n
,
an
d
e
v
alu
atio
n
m
etr
ics.
T
h
e
ex
p
er
im
e
n
tal
r
esu
lts
an
d
d
is
cu
s
s
io
n
ar
e
p
r
e
s
en
ted
in
s
ec
tio
n
3
.
Sec
tio
n
4
,
co
n
clu
d
es
with
th
e
p
a
p
er
an
d
o
u
tlin
es
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
wo
r
k
.
2.
M
E
T
H
O
D
T
h
is
r
esear
ch
in
tr
o
d
u
ce
s
a
d
ee
p
lear
n
i
n
g
f
r
am
ewo
r
k
f
o
r
th
e
ca
teg
o
r
is
atio
n
o
f
p
la
n
t
d
is
ea
s
es,
co
m
b
in
in
g
a
C
NN
w
ith
n
atu
r
e
-
in
s
p
ir
ed
o
p
tim
is
atio
n
alg
o
r
i
th
m
s
.
T
h
e
o
b
jectiv
e
is
to
f
in
d
o
u
t
wh
ich
n
atu
r
e
-
in
s
p
ir
ed
alg
o
r
ith
m
p
er
f
o
r
m
s
b
est
f
o
r
im
p
r
o
v
i
n
g
d
ee
p
lear
n
i
n
g
m
o
d
els
th
at
ar
e
u
s
ed
to
i
d
e
n
tify
p
lan
t
d
is
ea
s
es
in
im
ag
es.
T
h
ese
alg
o
r
ith
m
s
ar
e
s
p
ec
if
ically
u
tili
s
ed
t
o
en
h
an
ce
h
y
p
er
p
a
r
am
eter
t
u
n
in
g
an
d
m
o
d
el
g
en
er
aliza
tio
n
[
1
3
]
,
[
1
4
]
.
T
h
e
m
eth
o
d
o
l
o
g
y
is
d
iv
i
d
ed
in
to
f
o
u
r
m
ai
n
p
ar
ts
,
as
d
ep
icted
i
n
Fig
u
r
e
1
.
First
a
C
NN
is
u
s
ed
as
th
e
m
ain
m
o
d
el
f
o
r
im
ag
e
class
if
icatio
n
.
Seco
n
d
,
a
s
et
o
f
alg
o
r
ith
m
s
b
ased
o
n
n
atu
r
e
is
u
s
ed
to
f
in
d
th
e
b
est
v
alu
es
f
o
r
th
e
m
o
s
t
im
p
o
r
tan
t
h
y
p
er
p
ar
am
e
ter
s
o
f
th
e
d
ee
p
lear
n
i
n
g
m
o
d
el.
T
h
ir
d
,
th
e
s
tep
s
f
o
r
g
ettin
g
th
e
d
ataset
r
ea
d
y
w
ith
s
p
ec
if
ic
p
r
e
-
p
r
o
ce
s
s
in
g
s
tep
s
ar
e
p
er
f
o
r
m
e
d
to
en
s
u
r
e
th
e
d
ata
is
s
tr
o
n
g
an
d
co
n
s
is
ten
t
d
u
r
in
g
tr
ain
in
g
.
Fin
ally
,
we
u
s
e
s
tan
d
ar
d
p
er
f
o
r
m
an
ce
ev
alu
atio
n
m
etr
ics
to
test
an
d
co
m
p
ar
e
th
e
s
u
g
g
ested
o
p
tim
is
atio
n
s
tr
ateg
ies.
2
.
1
.
Co
nv
o
lutio
na
l
neura
l net
wo
rk
C
NNs
ar
e
u
s
ed
f
r
e
q
u
en
tly
f
o
r
im
ag
e
class
if
icatio
n
task
s
g
iv
en
th
eir
ca
p
ac
ity
to
in
d
ep
e
n
d
e
n
tly
lear
n
s
p
atial
an
d
s
tr
u
ctu
r
al
f
ea
tu
r
es
f
r
o
m
r
aw
im
ag
e
d
ata
[
1
5
]
.
T
r
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
d
ep
en
d
o
n
f
ea
tu
r
es
th
at
ar
e
d
esig
n
e
d
m
a
n
u
ally
,
b
u
t
C
NNs
d
o
b
o
th
f
e
atu
r
e
ex
tr
ac
tio
n
a
n
d
class
if
icatio
n
f
r
o
m
s
tar
t
to
f
in
is
h
.
T
h
is
m
ak
es
th
em
well
s
u
ited
f
o
r
p
lan
t
d
is
ea
s
e
id
en
tific
atio
n
,
wh
er
e
v
is
u
al
s
y
m
p
t
o
m
s
s
u
ch
as
s
p
o
ts
,
lesi
o
n
s
,
an
d
co
lo
r
v
a
r
iatio
n
s
ap
p
ea
r
at
d
if
f
e
r
en
t
s
p
atial
s
ca
les
o
n
leaf
im
ag
es.
A
C
NN
u
s
u
ally
co
n
s
is
ts
o
f
co
n
v
o
l
u
tio
n
al
lay
er
s
,
ac
tiv
atio
n
f
u
n
ctio
n
s
,
p
o
o
li
n
g
lay
er
s
,
a
n
d
f
u
lly
co
n
n
ec
ted
la
y
er
s
[
1
6
]
.
I
n
a
co
n
v
o
lu
tio
n
al
lay
er
,
lear
n
a
b
le
f
ilter
s
ar
e
ap
p
l
ied
to
th
e
in
p
u
t
im
ag
e
t
o
r
etr
ie
v
e
lo
ca
l
p
atter
n
s
.
T
h
e
co
n
v
o
lu
tio
n
o
p
e
r
atio
n
ca
n
b
e
ex
p
r
ess
ed
as:
{
(
)
}
=
{
(
)
}
∗
+
{
(
)
}
(
1
)
wh
er
e
x
d
e
n
o
tes
th
e
in
p
u
t
im
ag
e,
w⁽
ᵏ⁾
r
e
p
r
esen
ts
th
e
k
-
th
c
o
n
v
o
lu
ti
o
n
al
f
ilter
,
b
⁽
ᵏ⁾
is
th
e
b
ias
ter
m
,
a
n
d
z⁽
ᵏ
⁾
d
en
o
tes
th
e
r
esu
ltin
g
f
ea
t
u
r
e
m
ap
p
r
o
d
u
c
ed
b
y
th
e
co
n
v
o
l
u
tio
n
o
p
er
atio
n
.
T
h
e
s
y
m
b
o
l
(
*
)
r
ep
r
esen
ts
th
e
co
n
v
o
l
u
tio
n
o
p
e
r
ato
r
.
A
n
ac
ti
v
atio
n
f
u
n
ctio
n
is
u
s
ed
af
ter
co
n
v
o
lu
ti
o
n
to
m
ak
e
th
e
n
etwo
r
k
n
o
n
-
lin
ea
r
.
T
h
is
s
tu
d
y
u
s
es
th
e
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U)
b
ec
au
s
e
it
is
s
im
p
le
an
d
wo
r
k
s
well
in
d
ee
p
n
e
u
r
al
n
etwo
r
k
s
[
1
7
]
.
I
t is d
ef
in
ed
as:
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Op
timiz
in
g
d
ee
p
lea
r
n
in
g
mo
d
els fo
r
p
la
n
t le
a
f d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
…
(
A
vi
n
esh
C
u
llo
o
)
371
f
(
z
)
=
ma
x
(
0
,
z
)
(
2
)
As
th
e
n
etwo
r
k
d
ep
th
in
c
r
ea
s
es,
co
n
v
o
lu
ti
o
n
al
an
d
p
o
o
lin
g
lay
er
s
p
r
o
g
r
ess
iv
ely
ex
tr
ac
t
h
i
g
h
er
-
lev
e
l
f
ea
tu
r
e
r
e
p
r
esen
tatio
n
s
.
Af
ter
th
at,
th
ese
f
ea
tu
r
es
ar
e
co
m
p
r
ess
ed
an
d
s
en
t
to
f
u
lly
c
o
n
n
ec
ted
lay
e
r
s
f
o
r
class
if
icatio
n
.
T
h
e
f
in
al
o
u
tp
u
t
lay
er
ap
p
lies
th
e
s
o
f
tm
ax
f
u
n
ctio
n
to
tr
an
s
f
o
r
m
th
e
n
etwo
r
k
o
u
tp
u
ts
in
to
class
p
r
o
b
a
b
ilit
ies,
en
s
u
r
in
g
t
h
at
th
e
p
r
ed
icted
p
r
o
b
ab
ilit
ies
ac
r
o
s
s
all
d
is
ea
s
e
class
es
s
u
m
to
o
n
e
[
1
6
]
.
T
h
is
en
ab
les
m
u
lti
-
class
p
lan
t d
is
ea
s
e
clas
s
i
f
icatio
n
b
y
s
elec
tin
g
t
h
e
class
with
th
e
h
ig
h
est p
r
e
d
icted
p
r
o
b
ab
ilit
y
.
E
f
f
icien
tNet
is
a
g
r
o
u
p
o
f
C
NN
ar
ch
itectu
r
es
th
at
u
s
e
s
a
co
m
p
o
u
n
d
s
ca
lin
g
s
tr
ateg
y
to
s
ca
le
th
e
d
ep
th
,
wid
th
,
an
d
in
p
u
t
r
eso
l
u
tio
n
o
f
th
e
n
etwo
r
k
in
a
b
alan
ce
d
way
[1
8
]
.
T
h
is
d
esig
n
en
ab
les
E
f
f
icien
tNet
m
o
d
els
to
ac
h
iev
e
s
tr
o
n
g
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
wh
ile
m
ain
tain
in
g
co
m
p
u
tatio
n
al
ef
f
icien
cy
.
Am
o
n
g
th
e
d
if
f
er
en
t
v
ar
ian
ts
,
E
f
f
icien
tN
et
-
B
0
r
ep
r
esen
ts
th
e
b
aselin
e
ar
ch
itectu
r
e
an
d
p
r
o
v
i
d
es
an
ef
f
ec
tiv
e
tr
ad
e
-
o
f
f
b
etwe
en
ac
cu
r
ac
y
an
d
m
o
d
el
co
m
p
lex
ity
,
m
ak
in
g
it
s
u
itab
le
f
o
r
p
lan
t
d
is
ea
s
e
class
if
icatio
n
task
s
u
s
in
g
im
ag
es
.
I
n
th
is
s
tu
d
y
,
E
f
f
icien
tNet
-
B
0
p
r
etr
ain
ed
o
n
th
e
I
m
ag
eNe
t
d
ataset
[1
9
]
is
em
p
lo
y
ed
as
th
e
C
NN
b
ac
k
b
o
n
e
as
it
h
as
a
g
o
o
d
b
a
lan
ce
b
etwe
en
class
if
icatio
n
ac
cu
r
ac
y
a
n
d
c
o
m
p
u
tatio
n
al
ef
f
icien
cy
.
T
r
an
s
f
er
lear
n
in
g
is
u
s
ed
b
y
,
f
ir
s
tly
,
f
r
e
ez
in
g
th
e
p
r
etr
ain
ed
lay
e
r
s
an
d
tr
ain
i
n
g
th
e
class
if
ier
h
ea
d
t
o
m
ak
e
th
e
m
o
d
el
f
it
th
e
tar
g
et
d
ataset.
Su
b
s
eq
u
en
tl
y
,
all
lay
er
s
ar
e
u
n
f
r
o
ze
n
an
d
f
in
e
-
tu
n
ed
u
s
in
g
a
s
m
aller
lear
n
in
g
r
ate
to
f
u
r
th
er
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
a
n
d
g
e
n
er
alis
atio
n
o
n
p
la
n
t
d
is
ea
s
e
im
ag
es.
P
o
o
lin
g
lay
er
s
ar
e
o
f
ten
u
s
ed
in
C
NN
ar
ch
itectu
r
es
to
k
ee
p
im
p
o
r
t
an
t
in
f
o
r
m
atio
n
wh
ile
lo
we
r
in
g
th
e
s
p
atial
r
eso
lu
tio
n
o
f
f
ea
tu
r
e
m
ap
s
.
T
h
is
o
p
er
atio
n
im
p
r
o
v
es
t
h
e
c
o
m
p
u
tin
g
a
n
d
m
ak
es
it
less
lik
ely
th
at
tr
a
n
s
latio
n
s
will
ch
an
g
e
th
e
r
esu
lts
.
Po
o
lin
g
o
p
er
atio
n
s
ar
e
b
u
ilt
in
to
t
h
e
n
etwo
r
k
b
lo
c
k
s
in
E
f
f
icien
tNet
,
wh
ich
h
elp
s
with
ef
f
ec
tiv
e
f
ea
tu
r
e
ab
s
tr
ac
tio
n
.
Du
r
in
g
tr
ai
n
in
g
,
th
e
C
NN'
s
p
ar
am
eter
s
ar
e
lear
n
ed
b
y
m
in
im
is
in
g
a
class
if
icatio
n
lo
s
s
f
u
n
ctio
n
th
r
o
u
g
h
g
r
ad
ien
t
-
b
ased
o
p
tim
is
atio
n
.
T
h
is
s
tu
d
y
em
p
lo
y
s
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
alo
n
g
s
id
e
b
ac
k
p
r
o
p
a
g
atio
n
to
u
p
d
ate
th
e
n
etwo
r
k
weig
h
ts
,
f
ac
ilit
atin
g
t
h
e
ac
q
u
is
itio
n
o
f
d
is
cr
im
in
ativ
e
f
ea
tu
r
es b
y
t
h
e
m
o
d
el,
f
o
r
b
e
tter
class
if
icatio
n
.
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
f
o
r
p
lan
t d
is
ea
s
e
d
etec
tio
n
u
s
in
g
n
at
u
r
e
in
s
p
ir
ed
alg
o
r
ith
m
2
.
2
.
Na
t
ure
ins
pired o
ptim
is
a
t
io
n a
lg
o
ri
t
hm
s
T
h
e
im
p
ac
t
o
f
m
etah
eu
r
is
tic
o
p
tim
izatio
n
ap
p
r
o
ac
h
o
n
C
NN
p
er
f
o
r
m
an
ce
is
ass
ess
ed
u
s
in
g
a
d
iv
er
s
e
s
et
o
f
n
atu
r
e
-
in
s
p
ir
ed
alg
o
r
ith
m
s
,
en
co
m
p
ass
in
g
b
o
th
e
v
o
lu
tio
n
ar
y
a
n
d
s
war
m
in
tellig
en
c
e
ap
p
r
o
ac
h
es.
E
ac
h
alg
o
r
ith
m
d
if
f
er
s
in
its
ex
p
lo
r
atio
n
-
ex
p
lo
itatio
n
s
tr
ateg
ie
s
an
d
s
ea
r
ch
d
y
n
am
ics,
en
ab
lin
g
a
th
o
r
o
u
g
h
co
m
p
ar
is
o
n
o
f
th
eir
ef
f
ec
tiv
e
n
ess
in
h
y
p
er
p
ar
a
m
eter
s
f
o
r
p
lan
t
d
is
ea
s
e
class
if
icatio
n
.
T
h
e
s
elec
ted
n
atu
r
e
-
in
s
p
ir
ed
alg
o
r
ith
m
s
ar
e:
−
Dif
f
er
en
tial
ev
o
lu
tio
n
(
DE
)
[
20
]
−
Par
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
[
21
]
−
Gr
ey
wo
lf
o
p
tim
izer
(
GW
O)
[
22
]
−
B
at
alg
o
r
ith
m
(
B
A)
[
23
]
−
Fire
f
ly
alg
o
r
ith
m
(
FA)
[
24
]
−
C
u
ck
o
o
s
ea
r
c
h
(
C
S)
[
25
]
−
C
o
r
al
r
ee
f
o
p
tim
izatio
n
(
C
R
O
)
[
26
]
−
Ar
tific
ial
b
ee
co
lo
n
y
(
AB
C
)
[
27
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
6
9
-
376
372
DE
an
d
PS
O
ar
e
o
f
te
n
u
tili
z
ed
to
s
o
l
v
e
p
r
o
b
lem
s
t
h
a
t
n
e
ed
to
b
e
o
p
tim
ized
,
s
u
ch
as
tu
n
in
g
t
h
e
lear
n
in
g
r
ate
an
d
weig
h
t
d
ec
ay
in
d
ee
p
l
ea
r
n
in
g
.
GW
O
is
well
k
n
o
wn
f
o
r
m
ain
tain
in
g
a
b
alan
ce
b
etwe
en
ex
p
lo
r
atio
n
an
d
ex
p
lo
itatio
n
.
Oth
er
ap
p
r
o
ac
h
es,
in
clu
d
i
n
g
B
A,
FA,
an
d
C
S,
ar
e
ca
p
ab
le
o
f
p
r
ev
e
n
tin
g
p
r
em
atu
r
e
c
o
n
v
e
r
g
en
ce
a
n
d
r
e
d
u
ce
th
e
r
is
k
o
f
b
ein
g
tr
ap
p
ed
in
th
e
lo
ca
l
o
p
tim
a.
C
R
O
p
r
o
m
o
tes
co
m
p
etitiv
e
r
ep
r
o
d
u
ctio
n
m
ec
h
a
n
is
m
s
b
y
in
cr
ea
s
in
g
p
o
p
u
latio
n
d
iv
e
r
s
ity
.
Fin
ally
,
AB
C
is
a
b
i
o
-
in
s
p
ir
ed
,
m
u
lti
-
ag
en
t
p
r
o
b
a
b
ilis
tic
s
ea
r
ch
alg
o
r
ith
m
th
at
em
p
lo
y
s
a
m
etap
h
o
r
b
ase
d
o
n
th
e
f
o
r
ag
i
n
g
i
n
tellig
en
ce
o
f
h
o
n
ey
b
ee
s
war
m
s
.
T
h
e
m
etah
eu
r
is
tic
alg
o
r
ith
m
s
wer
e
im
p
lem
en
te
d
u
s
in
g
th
e
NiaPy
f
r
am
ewo
r
k
a
n
d
co
m
b
in
e
d
with
th
e
E
f
f
icien
tNet
-
B
0
m
o
d
el
f
o
r
t
h
e
h
y
p
er
p
ar
am
eter
tu
n
i
n
g
.
T
h
e
co
m
p
ar
ativ
e
p
e
r
f
o
r
m
an
ce
o
f
ea
ch
alg
o
r
ith
m
is
an
aly
s
ed
in
s
ec
tio
n
3.
2
.
3
.
Da
t
a
s
et
T
h
e
p
lan
t
v
illag
e
u
p
d
ated
d
at
aset
co
n
s
is
t
s
o
f
a
m
ix
tu
r
e
o
f
h
ea
lth
y
an
d
d
is
ea
s
ed
leav
es
ac
r
o
s
s
n
in
e
d
if
f
er
en
t
cr
o
p
s
f
o
r
a
to
tal
o
f
6
7
,
1
1
8
h
ig
h
q
u
ality
p
lan
t
leav
e
s
,
as
li
s
ted
in
T
ab
le
1
.
T
h
e
d
at
aset
is
o
r
g
an
ized
in
s
u
ch
a
way
th
at
ea
ch
cr
o
p
is
s
to
r
ed
in
its
o
wn
f
o
ld
er
a
n
d
th
e
n
s
p
lit
in
to
tr
ain
,
test
,
an
d
v
alid
atio
n
s
ets.
W
ith
in
ea
ch
s
p
lit,
th
e
leaf
p
ictu
r
es
ar
e
class
if
ied
in
to
d
if
f
er
en
t
f
o
l
d
er
s
n
am
ed
af
ter
th
e
d
is
ea
s
e
with
an
ad
d
itio
n
al
f
o
ld
er
c
o
n
tain
in
g
th
e
h
ea
lth
y
l
ea
v
es.
T
h
e
f
o
ld
er
s
ar
e
ar
r
an
g
e
d
to
allo
w
th
e
l
o
ad
in
g
o
f
t
h
e
d
ataset
in
a
s
tan
d
ar
d
way
wh
ich
is
p
r
ac
tical
f
o
r
th
e
m
ac
h
in
e
lear
n
in
g
.
Fig
u
r
e
2
s
h
o
ws
an
ex
am
p
le
o
f
to
m
at
o
s
am
p
le
im
ag
es
ac
r
o
s
s
s
ix
class
e
s
in
th
e
tr
ain
in
g
s
p
lit
wh
ich
th
e
m
o
d
el
n
ee
d
s
to
t
r
ain
f
r
o
m
.
T
ab
le
1
.
Dis
tr
ib
u
tio
n
o
f
p
lan
t
d
is
ea
s
e
im
ag
es a
cr
o
s
s
d
if
f
er
en
t c
r
o
p
ca
teg
o
r
ies with
s
p
lit r
atio
C
r
o
p
Tr
a
i
n
V
a
l
i
d
a
t
i
o
n
Te
st
To
t
a
l
S
p
l
i
t
r
a
t
i
o
(
t
r
a
i
n
/
v
a
l
/
t
e
st
)
A
p
p
l
e
7
,
7
7
1
1
,
7
4
7
1
9
6
9
,
7
1
4
8
0
.
0
0
%
/
1
7
.
9
8
%
/
2
.
0
2
%
B
e
l
l
P
e
p
p
e
r
3
,
9
0
1
8
7
7
98
4
,
8
7
6
8
0
.
0
0
%
/
1
7
.
9
9
%
/
2
.
0
1
%
C
h
e
r
r
y
3
,
5
0
9
7
8
8
89
4
,
3
8
6
8
0
.
0
0
%
/
1
7
.
9
7
%
/
2
.
0
3
%
C
o
r
n
(
M
a
i
z
e
)
7
,
3
1
6
1
,
6
4
5
1
8
8
9
,
1
4
9
7
9
.
9
7
%
/
1
7
.
9
8
%
/
2
.
0
5
%
G
r
a
p
e
7
,
2
2
2
1
,
6
2
3
1
8
2
9
,
0
2
7
8
0
.
0
0
%
/
1
7
.
9
8
%
/
2
.
0
2
%
P
e
a
c
h
3
,
5
6
6
8
0
1
90
4
,
4
5
7
8
0
.
0
1
%
/
1
7
.
9
7
%
/
2
.
0
2
%
P
o
t
a
t
o
5
,
7
0
2
1
,
2
8
2
1
4
4
7
,
1
2
8
7
9
.
9
9
%
/
1
7
.
9
9
%
/
2
.
0
2
%
S
t
r
a
w
b
e
r
r
y
3
,
5
9
8
8
0
9
91
4
,
4
9
8
7
9
.
9
9
%
/
1
7
.
9
9
%
/
2
.
0
2
%
To
ma
t
o
1
1
,
1
0
8
2
,
4
9
5
2
8
0
1
3
,
8
8
3
8
0
.
0
1
%
/
1
7
.
9
7
%
/
2
.
0
2
%
To
t
a
l
5
3
,
6
9
3
1
2
,
0
6
7
1
,
3
5
8
6
7
,
1
1
8
Fig
u
r
e
2
.
Vis
u
al
d
if
f
e
r
en
ce
s
o
f
th
e
tr
ain
in
g
s
am
p
les f
o
r
to
m
at
o
leav
es a
cr
o
s
s
s
ix
d
if
f
er
e
n
t c
lass
es (
s
tar
t
in
g
f
r
o
m
lef
t:
b
ac
te
r
ial
s
p
o
t,
ea
r
ly
b
lig
h
t,
h
ea
lth
y
,
late
b
lig
h
t,
s
ep
to
r
ia
leaf
s
p
o
t
an
d
y
ello
w
leaf
cu
r
l v
ir
u
s
)
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Op
timiz
in
g
d
ee
p
lea
r
n
in
g
mo
d
els fo
r
p
la
n
t le
a
f d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
…
(
A
vi
n
esh
C
u
llo
o
)
373
2
.
4
.
Da
t
a
prepro
ce
s
s
ing
T
h
e
lo
ad
i
n
g
o
f
t
h
e
d
ata
is
s
tan
d
ar
d
is
ed
s
o
th
at
th
e
m
o
d
e
l
alwa
y
s
u
s
es
th
e
s
am
e
ty
p
e
o
f
in
p
u
t.
T
h
e
d
ata
p
r
e
p
r
o
ce
s
s
in
g
p
ip
el
in
e
is
k
ep
t
s
im
p
le
an
d
c
o
n
s
is
ten
t
f
o
r
th
e
m
o
d
el
test
in
g
a
n
d
v
alid
atio
n
.
E
ac
h
im
ag
e
in
p
u
t to
th
e
co
m
p
u
ter
v
is
io
n
m
o
d
el
is
f
ir
s
t c
o
n
v
er
ted
to
a
3
-
ch
an
n
el
g
r
ay
s
ca
led
im
ag
e
th
en
tr
an
s
f
o
r
m
e
d
in
to
ten
s
o
r
s
an
d
th
e
I
m
ag
e
Net
m
ea
n
an
d
s
tan
d
ar
d
d
e
v
iatio
n
is
u
s
ed
f
o
r
n
o
r
m
alis
in
g
th
e
in
p
u
t
.
T
h
is
p
r
ep
r
o
ce
s
s
in
g
s
tep
is
f
u
n
d
am
en
tal
to
k
ee
p
in
g
th
e
tr
ain
i
n
g
s
tab
le
s
in
ce
th
e
E
f
f
icien
tNet
-
B
0
b
ac
k
b
o
n
e
wer
e
tr
ain
ed
o
n
I
m
ag
eNe
t.
Fo
r
tr
ain
in
g
o
f
th
e
m
o
d
el,
t
h
e
s
am
e
co
r
e
s
tep
s
f
r
o
m
th
e
d
ata
p
r
ep
r
o
ce
s
s
in
g
ar
e
a
p
p
lied
with
ad
d
itio
n
al
im
a
g
e
a
u
g
m
en
tati
o
n
to
im
p
r
o
v
e
g
e
n
er
alis
atio
n
.
I
n
s
tead
o
f
u
s
in
g
a
f
ix
ed
r
esize,
th
e
im
ag
e
is
r
an
d
o
m
l
y
r
esized
ar
o
u
n
d
2
2
4
p
ix
els
an
d
r
an
d
o
m
ly
c
r
o
p
p
e
d
with
a
lo
wer
b
o
u
n
d
o
f
0
.
8
an
d
u
p
p
e
r
b
o
u
n
d
o
f
1
.
0
.
T
h
is
allo
ws
th
e
m
o
d
el
to
l
ea
r
n
s
m
all
ch
an
g
es
in
th
e
im
a
g
e
f
r
am
e
wh
ile
k
ee
p
in
g
p
ar
t
o
f
th
e
im
ag
e
v
is
ib
le.
I
n
ad
d
itio
n
,
th
e
im
a
g
e
is
r
an
d
o
m
ly
h
o
r
iz
o
n
tally
f
lip
p
ed
with
a
p
r
o
b
a
b
ilit
y
o
f
5
0
%
an
d
r
a
n
d
o
m
ly
r
o
tated
with
a
r
an
g
e
o
f
d
e
g
r
ee
s
b
etwe
en
-
1
5
an
d
+1
5
.
On
to
p
o
f
th
ese
r
an
d
o
m
f
lip
p
in
g
an
d
r
o
tatio
n
,
to
m
im
ic
n
atu
r
al
v
ar
iatio
n
s
in
lig
h
tin
g
an
d
ca
m
er
a
co
n
d
itio
n
s
,
th
e
b
r
ig
h
tn
ess
an
d
th
e
co
n
tr
ast ar
e
ea
ch
jitt
er
ed
b
y
0
.
1
5
.
Sin
ce
in
th
e
d
ata
p
r
e
p
r
o
ce
s
s
in
g
s
tep
,
th
e
im
ag
e
is
co
n
v
e
r
ted
to
g
r
ay
s
c
ale,
th
e
jitt
er
is
lim
ited
to
co
n
t
r
ast
an
d
b
r
ig
h
tn
ess
o
n
ly
t
o
b
e
co
n
s
is
ten
t.
T
h
r
o
u
g
h
th
ese
p
r
ep
r
o
ce
s
s
in
g
an
d
d
at
a
au
g
m
e
n
tatio
n
,
th
e
v
ar
iety
o
f
tr
ain
in
g
ex
a
m
p
les
h
av
e
b
ee
n
u
s
ed
,
with
o
u
t
c
h
an
g
in
g
t
h
e
u
n
d
er
l
y
in
g
class
es.
T
h
ese
d
ata
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es
ar
e
ex
p
ec
ted
to
r
ed
u
ce
t
h
e
o
v
e
r
f
itti
n
g
a
n
d
a
ls
o
im
p
r
o
v
in
g
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
el
o
n
u
n
s
ee
n
test
im
ag
es [
28
].
2
.
5
.
P
er
f
o
r
m
a
nce
m
e
t
rics
T
o
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el,
m
etr
ics ar
e
u
s
ed
wh
ich
ar
e
d
escr
ib
e
d
as:
−
Acc
u
r
ac
y
:
th
e
p
er
f
o
r
m
an
ce
m
etr
ic
th
at
m
ea
s
u
r
es
th
e
p
r
o
p
o
r
tio
n
o
f
c
o
r
r
ec
t
p
r
ed
ictio
n
s
th
e
m
o
d
el
m
ak
es
ac
r
o
s
s
th
e
en
tire
test
s
et.
=
(
+
)
(
+
+
+
)
(
3
)
−
Pre
cisi
o
n
:
th
e
p
r
o
p
o
r
tio
n
o
f
c
ases
th
e
m
o
d
el
lab
els
as
p
o
s
i
tiv
e
th
at
ar
e
ac
tu
ally
p
o
s
itiv
e
.
I
t
s
h
o
ws
h
o
w
well
th
e
m
o
d
el
r
ed
u
ce
s
f
alse p
o
s
itiv
es (
th
at
is
,
av
o
id
s
f
alse a
lar
m
s
)
.
=
(
+
)
(
4
)
−
R
ec
all/
s
en
s
itiv
ity
(
tr
u
e
p
o
s
itiv
e
r
ate)
:
th
e
p
er
ce
n
tag
e
o
f
r
ea
l
p
o
s
itiv
es
th
at
h
av
e
b
ee
n
id
en
tifie
d
co
r
r
ec
tly
.
I
t sh
o
ws th
e
ex
ten
t to
wh
ic
h
th
e
m
o
d
el
f
in
d
s
all
th
e
r
ig
h
t
ca
s
es a
n
d
d
o
esn
'
t m
is
s
an
y
(
f
alse n
eg
ativ
es).
=
(
+
)
(
5
)
−
F1
-
s
co
r
e:
th
e
av
er
ag
e
o
f
p
r
e
cisi
o
n
an
d
r
ec
all.
I
t
is
esp
ec
ially
h
elp
f
u
l
wh
en
class
f
r
e
q
u
en
cies
ar
e
n
o
t
p
er
f
ec
tly
b
alan
ce
d
b
ec
a
u
s
e
it
r
ewa
r
d
s
m
o
d
els
th
at
f
in
d
a
g
o
o
d
b
alan
ce
b
etwe
en
p
r
ec
i
s
io
n
an
d
r
ec
all
in
s
tead
o
f
ju
s
t o
p
tim
is
in
g
o
n
e
o
f
th
em
.
1
=
2
∗
(
∗
)
(
+
)
(
6
)
w
h
er
e
T
P is
tr
u
e
p
o
s
itiv
e,
T
N
is
tr
u
e
n
eg
ativ
e,
FN is f
alse n
e
g
ativ
e,
an
d
FP
is
f
alse p
o
s
itiv
e.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
ab
le
2
p
r
esen
ts
th
e
s
u
m
m
ar
y
o
f
th
e
r
esu
lts
f
o
r
all
th
e
co
m
b
in
atio
n
s
o
f
m
etah
e
u
r
is
tic
with
C
NN
ex
p
er
im
en
ts
p
er
f
o
r
m
e
d
in
th
is
s
tu
d
y
.
T
h
e
s
am
e
E
f
f
icien
tNet
-
B
0
(
p
r
etr
ain
e
d
)
b
ac
k
b
o
n
e
wa
s
u
s
ed
th
r
o
u
g
h
o
u
t
an
d
th
e
m
etah
eu
r
is
tics
wer
e
ap
p
lied
to
tu
n
e
k
ey
tr
ain
in
g
h
y
p
er
p
ar
am
eter
s
(
d
r
o
p
o
u
t,
lear
n
in
g
r
ates,
a
n
d
weig
h
t
d
ec
ay
)
u
s
in
g
v
alid
atio
n
Ma
cr
o
-
F1
as
th
e
o
b
jectiv
e.
Ov
er
all,
all
ap
p
r
o
ac
h
es
ac
h
iev
e
d
v
er
y
s
tr
o
n
g
p
e
r
f
o
r
m
an
ce
(
ab
o
v
e
9
9
%
ac
r
o
s
s
th
e
m
ain
m
etr
ics).
T
h
is
d
em
o
n
s
tr
ates
th
at
tr
an
s
f
er
lear
n
i
n
g
with
E
f
f
ici
en
tNet
-
B
0
is
h
ig
h
ly
ef
f
ec
tiv
e
f
o
r
th
is
Plan
tVillag
e
class
if
icatio
n
s
etu
p
.
Firstl
y
,
DE
p
r
o
d
u
ce
d
a
s
tr
o
n
g
b
aselin
e
with
9
9
.
2
1
%
ac
cu
r
ac
y
an
d
a
9
9
.
2
1
%
Ma
cr
o
-
F1
s
co
r
e,
co
m
p
letin
g
in
ap
p
r
o
x
im
ately
3
2
.
9
7
m
in
u
tes.
B
u
ild
in
g
o
n
th
is
,
PS
O
d
eliv
er
ed
a
n
o
ticea
b
le
im
p
r
o
v
e
m
en
t,
r
ea
ch
in
g
9
9
.
3
7
%
ac
cu
r
ac
y
an
d
9
9
.
3
6
%
Ma
cr
o
-
F1
,
wh
ile
a
ls
o
b
ein
g
o
n
e
o
f
th
e
m
o
s
t
tim
e
-
ef
f
icien
t
r
u
n
s
a
t
ar
o
u
n
d
2
9
.
1
5
m
i
n
u
tes.
Fu
r
t
h
e
r
m
o
r
e,
th
e
GW
O
ac
h
iev
ed
th
e
b
est
o
v
er
all
r
esu
lts
in
T
a
b
le
2
,
r
ec
o
r
d
in
g
th
e
h
ig
h
est
ac
cu
r
ac
y
(
9
9
.
4
5
%)
an
d
Ma
cr
o
-
F1
(
9
9
.
4
6
%),
wh
ich
in
d
icate
s
th
e
m
o
s
t
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
class
es,
wi
th
a
to
tal
r
u
n
tim
e
o
f
r
o
u
g
h
ly
3
1
.
1
9
m
in
u
tes.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
6
9
-
376
374
Mo
r
eo
v
er
,
b
o
th
t
h
e
B
A
an
d
C
S
a
ch
iev
ed
v
er
y
s
im
ilar
m
id
-
r
an
g
e
p
er
f
o
r
m
a
n
ce
(
ab
o
u
t
9
9
.
2
9
%
ac
cu
r
ac
y
a
n
d
9
9
.
2
8
%
Ma
cr
o
-
F1
)
,
alth
o
u
g
h
B
A
was
s
lig
h
tly
f
aster
o
v
er
all
(
2
9
.
9
3
m
in
u
tes)
co
m
p
ar
e
d
with
C
S
(
3
2
.
2
9
m
in
u
tes).
T
h
e
AB
C
d
eliv
er
ed
r
esu
lts
co
m
p
ar
a
b
le
to
th
e
DE
b
aselin
e
(
ar
o
u
n
d
9
9
.
2
1
%
ac
cu
r
ac
y
an
d
9
9
.
2
0
%
Ma
cr
o
-
F1
)
with
a
t
o
t
al
tim
e
o
f
3
0
.
3
5
m
in
u
tes.
I
n
c
o
n
tr
ast,
th
e
FA
p
r
o
d
u
ce
d
th
e
l
o
west
Ma
cr
o
-
F1
in
T
ab
le
2
(
9
9
.
1
8
%)
a
n
d
r
eq
u
ir
e
d
a
lo
n
g
er
to
tal
r
u
n
tim
e
(
3
4
.
1
5
m
in
u
tes),
s
u
g
g
esti
n
g
t
h
at
u
n
d
er
th
e
s
am
e
tu
n
in
g
b
u
d
g
et
it wa
s
less
ef
f
ec
tiv
e
at
lo
ca
t
in
g
th
e
b
est h
y
p
er
p
ar
am
e
ter
r
eg
io
n
.
Fin
ally
,
th
e
C
R
O
ap
p
r
o
ac
h
a
ch
iev
ed
p
er
f
o
r
m
an
ce
th
at
was
v
er
y
clo
s
e
to
PS
O
(
9
9
.
3
6
%
Ma
cr
o
-
F1
)
b
u
t
at
a
s
u
b
s
tan
tially
h
ig
h
er
co
m
p
u
tatio
n
al
co
s
t
(
4
5
.
6
6
m
i
n
u
tes),
m
ak
in
g
it
a
less
p
r
ac
tical
ch
o
ice
wh
en
r
u
n
tim
e
is
a
co
n
ce
r
n
.
I
n
s
u
m
m
ar
y
,
GW
O
p
r
o
v
id
ed
t
h
e
b
est o
v
er
all
p
r
ed
ictiv
e
p
e
r
f
o
r
m
an
ce
in
th
is
s
tu
d
y
,
wh
ile
PS
O
o
f
f
er
ed
a
v
er
y
co
m
p
etitiv
e
alter
n
ativ
e
with
ex
ce
llen
t
r
esu
lts
an
d
th
e
m
o
s
t
ef
f
icien
t
r
u
n
tim
e
am
o
n
g
th
e
to
p
-
p
er
f
o
r
m
i
n
g
m
eth
o
d
s
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
E
f
f
icien
tNet
-
B
0
co
m
b
i
n
ed
with
d
if
f
er
en
t n
at
u
r
e
-
in
s
p
i
r
ed
o
p
tim
is
atio
n
alg
o
r
ith
m
s
M
o
d
e
l
C
o
m
p
u
t
a
t
i
o
n
a
l
(
mi
n
)
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
(
P
o
si
t
i
v
e
p
r
e
d
i
c
t
e
d
v
a
l
u
e
)
R
e
c
a
l
l
/
s
e
n
s
i
t
i
v
i
t
y
(
Tr
u
e
p
o
si
t
i
v
e
r
a
t
e
)
F1
-
S
c
o
r
e
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
D
E
3
2
.
9
7
0
.
9
9
2
1
0
.
9
9
2
4
0
.
9
9
2
0
0
.
9
9
2
1
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
P
S
O
2
9
.
1
5
0
.
9
9
3
7
0
.
9
9
4
0
0
.
9
9
3
4
0
.
9
9
3
6
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
G
W
O
3
1
.
1
9
0
.
9
9
4
5
0
.
9
9
4
9
0
.
9
9
4
4
0
.
9
9
4
6
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
B
A
2
9
.
9
3
0
.
9
9
2
9
0
.
9
9
2
9
0
.
9
9
2
7
0
.
9
9
2
8
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
F
A
3
4
.
1
5
0
.
9
9
2
1
0
.
9
9
2
5
0
.
9
9
1
5
0
.
9
9
1
8
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
C
S
3
2
.
2
9
0
.
9
9
2
9
0
.
9
9
2
9
0
.
9
9
2
7
0
.
9
9
2
8
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
C
R
O
4
5
.
6
6
0
.
9
9
3
7
0
.
9
9
3
8
0
.
9
9
3
5
0
.
9
9
3
6
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
A
B
C
3
0
.
3
5
0
.
9
9
2
1
0
.
9
9
2
1
0
.
9
9
2
1
0
.
9
9
2
0
3
.
1
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
Acc
o
r
d
in
g
to
th
e
r
esu
lts
in
T
a
b
le
3
,
o
u
r
s
u
g
g
ested
E
f
f
icien
t
Net
-
B
0
m
o
d
el
with
m
etah
eu
r
i
s
tic
tu
n
in
g
GW
O
h
as
th
e
b
est
o
v
er
all
p
er
f
o
r
m
an
ce
,
with
a
test
ac
cu
r
ac
y
o
f
9
9
.
4
5
%.
T
h
is
s
h
o
ws
th
at
th
e
s
elec
ted
m
o
d
el
wo
r
k
s
b
etter
th
an
o
th
er
m
eth
o
d
s
f
o
r
d
etec
tin
g
p
lan
t
d
is
ea
s
es
f
r
o
m
im
a
g
es wh
en
it c
o
m
es to
class
if
y
in
g
th
em
.
T
ab
le
3
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
ex
is
tin
g
m
o
d
els
R
e
f
e
r
e
n
c
e
A
r
c
h
i
t
e
c
t
u
r
e
A
c
c
u
r
a
c
y
m
e
t
r
i
c
(
%)
S
l
a
d
o
j
e
v
i
c
e
t
a
l
.
[
4
]
C
a
f
f
e
N
e
t
(
M
o
d
i
f
i
e
d
A
l
e
x
N
e
t
)
9
6
.
3
0
M
o
h
a
n
t
y
e
t
a
l
.
[
5
]
G
o
o
g
l
e
Le
N
e
t
9
9
.
3
5
P
i
c
o
n
e
t
a
l
.
[
6
]
D
e
e
p
r
e
si
d
u
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
M
o
d
i
f
i
e
d
R
e
sN
e
t
-
50)
9
6
.
0
Zh
a
n
g
e
t
a
l
.
[
7
]
G
P
D
C
N
N
(
M
o
d
i
f
i
e
d
A
l
e
x
N
e
t
)
9
4
.
6
5
F
u
e
n
t
e
s
e
t
a
l
.
[
8
]
F
a
st
e
r
R
-
C
N
N
(
w
i
t
h
V
G
G
-
1
6
)
8
3
.
0
(
mA
P
)
O
u
r
h
y
b
r
i
d
m
o
d
e
l
Ef
f
i
c
i
e
n
t
N
e
t
-
B
0
+
G
W
O
9
9
.
4
5
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
h
o
ws
th
at
n
atu
r
e
-
i
n
s
p
ir
ed
o
p
tim
izatio
n
alg
o
r
ith
m
s
h
av
e
s
tr
o
n
g
p
o
ten
tial
to
s
u
p
p
o
r
t
p
lan
t
d
is
ea
s
e
d
etec
tio
n
.
T
h
is
in
t
u
r
n
ca
n
ass
is
t
in
im
p
r
o
v
in
g
cr
o
p
h
ea
lth
an
d
p
r
o
d
u
ctiv
i
ty
in
Sm
all
I
s
lan
d
Dev
elo
p
m
en
t
States
.
B
y
en
a
b
lin
g
f
aster
an
d
m
o
r
e
ac
ce
s
s
ib
le
d
iag
n
o
s
is
f
r
o
m
im
a
g
es
with
o
u
t
alwa
y
s
r
ely
in
g
o
n
ex
p
e
r
t
in
s
p
ec
tio
n
,
s
u
c
h
s
y
s
tem
s
ca
n
h
elp
f
ar
m
er
s
r
esp
o
n
d
ea
r
lier
,
r
ed
u
ce
u
n
n
e
ce
s
s
ar
y
lo
s
s
es,
an
d
p
o
ten
tially
im
p
r
o
v
e
p
r
o
f
itab
ilit
y
.
I
n
a
wid
er
c
o
n
tex
t,
t
h
is
d
ir
ec
tio
n
alig
n
s
well
with
UN
SDG
2
(
Z
er
o
Hu
n
g
er
)
b
y
co
n
t
r
ib
u
tin
g
to
m
o
r
e
r
esil
ien
t a
n
d
ef
f
icien
t a
g
r
ic
u
ltu
r
al
p
r
ac
tices.
T
h
e
m
o
s
t
ef
f
ec
tiv
e
co
n
f
ig
u
r
at
io
n
am
o
n
g
s
t
all
ev
alu
ated
ap
p
r
o
ac
h
es
was
th
e
E
f
f
icien
tNet
-
B
0
p
air
ed
with
th
e
GW
O
to
tu
n
e
k
ey
h
y
p
er
p
a
r
am
eter
s
,
in
clu
d
in
g
d
r
o
p
o
u
t,
lear
n
in
g
r
ates,
an
d
weig
h
t
d
ec
ay
.
T
h
e
test
p
er
f
o
r
m
an
ce
ac
h
iev
ed
is
a
s
tr
o
n
g
i
n
d
icatio
n
t
h
at
u
s
i
n
g
m
etah
e
u
r
is
tic
-
d
r
iv
en
tu
n
i
n
g
ap
p
r
o
ac
h
es
ca
n
s
ig
n
if
ican
tly
im
p
r
o
v
e
m
o
d
el
g
en
er
aliza
tio
n
.
I
n
a
d
d
itio
n
to
u
s
in
g
n
at
u
r
e
i
n
s
p
ir
ed
al
g
o
r
ith
m
f
o
r
h
y
p
er
p
ar
am
ete
r
f
in
e
tu
n
in
g
,
th
e
p
r
e
p
r
o
ce
s
s
in
g
s
tr
ateg
y
wi
th
im
a
g
e
r
esizin
g
,
f
lip
p
in
g
,
r
o
tatin
g
,
g
r
a
y
s
ca
lin
g
an
d
jitt
er
in
g
im
p
r
o
v
e
d
th
e
r
o
b
u
s
tn
ess
o
f
t
h
e
m
o
d
el
t
o
v
ar
iatio
n
s
in
v
ie
wp
o
in
t
an
d
lea
f
o
r
ie
n
tatio
n
.
T
h
is
b
etter
r
ef
lects
r
ea
lwo
r
ld
co
n
d
itio
n
s
wh
er
e
im
ag
in
g
en
v
ir
o
n
m
en
ts
ar
e
d
if
f
icu
lt to
co
n
tr
o
l.
T
o
f
u
r
t
h
er
a
d
v
an
ce
t
h
e
p
lan
t
d
is
ea
s
e
clas
s
if
icatio
n
m
o
d
el,
f
u
tu
r
e
wo
r
k
s
m
u
s
t
f
o
cu
s
o
n
im
p
r
o
v
in
g
th
e
r
o
b
u
s
tn
ess
o
f
t
h
e
m
o
d
el
ag
ai
n
s
t
a
b
r
o
a
d
r
a
n
g
e
o
f
c
r
o
p
s
,
d
is
ea
s
e
ty
p
es,
as
well
as
u
n
d
er
d
iv
er
s
e
im
a
g
in
g
co
n
d
itio
n
s
s
u
ch
as
clu
tter
ed
b
ac
k
g
r
o
u
n
d
,
m
o
tio
n
b
lu
r
an
d
v
ar
y
i
n
g
ca
m
er
a
q
u
ality
.
C
u
r
r
en
tly
,
th
e
m
o
d
el
was
tr
ain
ed
o
n
a
d
ataset
with
a
lim
ited
n
in
e
p
lan
t
s
p
ec
ies,
wh
ich
ca
n
b
e
ex
p
an
d
ed
f
u
r
th
er
to
in
c
lu
d
e
m
o
r
e
s
p
ec
ies.
Als
o
,
m
o
r
e
d
iv
er
s
e
f
ield
im
a
g
es
will
m
ak
e
th
e
m
o
d
el
m
o
r
e
d
ep
en
d
ab
le
in
r
ea
l
-
w
o
r
ld
s
ettin
g
s
.
Mo
r
eo
v
er
,
f
u
r
th
er
r
esear
ch
ca
n
also
ex
p
lo
r
e
d
e
p
lo
y
m
e
n
t
s
tr
ateg
ies,
p
ar
ticu
lar
ly
lig
h
tweig
h
t
in
f
er
en
ce
s
f
o
r
m
o
b
ile
d
ev
ices.
C
lear
u
s
er
d
o
cu
m
en
ta
tio
n
an
d
g
u
id
elin
es m
u
s
t a
ls
o
b
e
d
ev
elo
p
ed
to
b
u
ild
tr
u
s
t a
n
d
s
u
p
p
o
r
t a
d
o
p
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
Op
timiz
in
g
d
ee
p
lea
r
n
in
g
mo
d
els fo
r
p
la
n
t le
a
f d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
…
(
A
vi
n
esh
C
u
llo
o
)
375
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
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
Av
in
esh
C
u
llo
o
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Av
in
ash
B
h
u
n
ju
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Gee
r
is
h
Su
d
d
u
l
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
is
n
o
t
ap
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
U
n
i
t
e
d
N
a
t
i
o
n
s,
T
r
a
n
sf
o
rm
i
n
g
o
u
r
w
o
rl
d
:
t
h
e
2
0
3
0
a
g
e
n
d
a
f
o
r
s
u
st
a
i
n
a
b
l
e
d
e
v
e
l
o
p
m
e
n
t
,
A
/
R
ES/
7
0
/
1
.
N
e
w
Y
o
r
k
,
N
Y
:
U
n
i
t
e
d
N
a
t
i
o
n
s,
2
0
1
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
d
o
c
u
m
e
n
t
s.
u
n
.
o
r
g
/
d
o
c
/
u
n
d
o
c
/
g
e
n
/
n
1
5
/
2
9
1
/
8
9
/
p
d
f
/
n
1
5
2
9
1
8
9
.
p
d
f
[
2
]
F
A
O
,
I
F
A
D
,
U
N
I
C
EF,
W
F
P
,
a
n
d
W
H
O
,
T
h
e
s
t
a
t
e
o
f
f
o
o
d
se
c
u
ri
t
y
a
n
d
n
u
t
ri
t
i
o
n
i
n
t
h
e
w
o
r
l
d
2
0
1
7
:
b
u
i
l
d
i
n
g
re
si
l
i
e
n
c
e
f
o
r
p
e
a
c
e
a
n
d
f
o
o
d
s
e
c
u
ri
t
y
.
R
o
me
:
F
A
O
,
2
0
1
7
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
f
a
o
.
o
r
g
/
3
/
I
7
6
9
5
EN
/
i
7
6
9
5
e
n
.
p
d
f
[
3
]
S
.
S
a
v
a
r
y
,
A
.
F
i
c
k
e
,
J.
N
.
A
u
b
e
r
t
o
t
,
a
n
d
C
.
H
o
l
l
i
e
r
,
“
P
l
a
n
t
d
i
sea
s
e
s
a
n
d
f
o
o
d
se
c
u
r
i
t
y
:
c
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s
,
”
Pl
a
n
t
Pa
t
h
o
l
o
g
y
,
v
o
l
.
6
1
,
n
o
.
1
,
p
p
.
3
–
1
6
,
2
0
1
2
.
[
4
]
S
.
S
l
a
d
o
j
e
v
i
c
,
M
.
A
r
sen
o
v
i
c
,
A
.
A
n
d
e
r
l
a
,
D
.
C
u
l
i
b
r
k
,
a
n
d
D
.
S
t
e
f
a
n
o
v
i
c
,
“
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
b
a
se
d
r
e
c
o
g
n
i
t
i
o
n
o
f
p
l
a
n
t
d
i
s
e
a
se
s
b
y
l
e
a
f
i
m
a
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
2
0
1
6
,
n
o
.
1
,
p
p
.
1
–
1
1
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
6
/
3
2
8
9
8
0
1
.
[
5
]
S
.
P
.
M
o
h
a
n
t
y
,
D
.
P
.
H
u
g
h
e
s,
a
n
d
M
.
S
a
l
a
t
h
é
,
“
U
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
m
a
g
e
-
b
a
s
e
d
p
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
,
”
F
ro
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
7
,
p
.
1
4
1
9
,
S
e
p
.
2
0
1
6
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
1
6
.
0
1
4
1
9
.
[
6
]
A
.
P
i
c
o
n
,
A
.
A
l
v
a
r
e
z
-
G
i
l
a
,
M
.
S
e
i
t
z
,
A
.
O
r
t
i
z
-
B
a
r
r
e
d
o
,
J
.
Ec
h
a
z
a
r
r
a
,
a
n
d
A
.
Jo
h
a
n
n
e
s
,
“
D
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
mo
b
i
l
e
c
a
p
t
u
r
e
d
e
v
i
c
e
-
b
a
s
e
d
c
r
o
p
d
i
sea
s
e
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
t
h
e
w
i
l
d
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ro
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
re
,
v
o
l
.
1
6
1
,
p
p
.
2
8
0
–
2
9
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
1
8
.
0
4
.
0
0
2
.
[
7
]
S
.
Z
h
a
n
g
,
S
.
Z
h
a
n
g
,
C
.
Z
h
a
n
g
,
X
.
W
a
n
g
,
a
n
d
Y
.
S
h
i
,
“
C
u
c
u
mb
e
r
l
e
a
f
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
w
i
t
h
g
l
o
b
a
l
p
o
o
l
i
n
g
d
i
l
a
t
e
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
o
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
1
6
2
,
p
p
.
4
2
2
–
4
3
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
1
9
.
0
3
.
0
1
2
.
[
8
]
A
.
F
u
e
n
t
e
s,
S
.
Y
o
o
n
,
S
.
C
.
K
i
m,
a
n
d
D
.
S
.
P
a
r
k
,
“
A
r
o
b
u
s
t
d
e
e
p
-
l
e
a
r
n
i
n
g
-
b
a
s
e
d
d
e
t
e
c
t
o
r
f
o
r
r
e
a
l
-
t
i
m
e
t
o
ma
t
o
p
l
a
n
t
d
i
s
e
a
ses
a
n
d
p
e
s
t
s re
c
o
g
n
i
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
1
7
,
n
o
.
9
,
p.
2
0
2
2
,
2
0
1
7
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
7
0
9
2
0
2
2
.
[
9
]
E.
C
.
T
o
o
,
L.
Y
u
j
i
a
n
,
S
.
N
j
u
k
i
,
a
n
d
L.
Y
i
n
g
c
h
u
n
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
f
i
n
e
-
t
u
n
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
f
o
r
p
l
a
n
t
d
i
s
e
a
s
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
o
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
re
,
v
o
l
.
1
6
1
,
p
p
.
2
7
2
–
2
7
9
,
J
u
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
1
8
.
0
3
.
0
3
2
.
[
1
0
]
S
.
J.
P
a
n
a
n
d
Q
.
Y
a
n
g
,
“
A
su
r
v
e
y
o
n
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
I
EE
E
T
r
a
n
sa
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
2
,
n
o
.
1
0
,
p
p
.
1
3
4
5
–
1
3
5
9
,
O
c
t
.
2
0
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E.
2
0
0
9
.
1
9
1
.
[
1
1
]
D
.
P
.
H
u
g
h
e
s
a
n
d
M
.
S
a
l
a
t
h
é
,
“
A
n
o
p
e
n
a
c
c
e
ss
r
e
p
o
si
t
o
r
y
o
f
i
ma
g
e
s
o
n
p
l
a
n
t
h
e
a
l
t
h
t
o
e
n
a
b
l
e
t
h
e
d
e
v
e
l
o
p
me
n
t
o
f
mo
b
i
l
e
d
i
s
e
a
s
e
d
i
a
g
n
o
st
i
c
s,
”
a
rX
i
v
:
1
5
1
1
.
0
8
0
6
0
,
2
0
1
5
.
[
1
2
]
T.
S
h
a
r
ma,
“
P
l
a
n
t
v
i
l
l
a
g
e
d
a
t
a
s
e
t
(
U
p
d
a
t
e
d
)
.
”
K
a
g
g
l
e
.
A
c
c
e
sse
d
J
a
n
.
27
,
2
0
2
6
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
t
u
sh
a
r
5
h
a
r
ma
/
p
l
a
n
t
-
v
i
l
l
a
g
e
-
d
a
t
a
se
t
-
u
p
d
a
t
e
d
[
1
3
]
G
.
S
u
d
d
u
l
,
K
.
D
o
o
k
h
i
t
r
a
m,
a
n
d
K
.
Ta
mesw
a
r
,
“
O
p
t
i
m
i
z
i
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
w
i
t
h
n
a
t
u
r
e
-
i
n
s
p
i
r
e
d
a
l
g
o
r
i
t
h
ms
f
o
r
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
2
0
2
6
,
p
p
.
2
4
5
–
2
5
5
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
96
-
5
5
8
9
-
2
_
2
5
.
[
1
4
]
K
.
T
a
mesw
a
r
,
G
.
S
u
d
d
u
l
,
a
n
d
K
.
D
o
o
k
h
i
t
r
a
m
,
“
A
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
w
i
t
h
g
e
n
e
t
i
c
a
n
d
c
o
r
a
l
r
e
e
f
s
met
a
h
e
u
r
i
s
t
i
c
s
f
o
r
e
n
h
a
n
c
e
d
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
i
n
s
o
f
t
w
a
r
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
M
a
n
a
g
e
m
e
n
t
D
a
t
a
I
n
si
g
h
t
s
,
v
o
l
.
2
,
n
o
.
2
,
p.
1
0
0
1
0
5
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
j
i
me
i
.
2
0
2
2
.
1
0
0
1
0
5
.
[
1
5
]
A
.
K
r
i
z
h
e
v
sk
y
,
I
.
S
u
t
s
k
e
v
e
r
,
a
n
d
G
.
E
.
H
i
n
t
o
n
,
“
I
mag
e
N
e
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
w
i
t
h
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
i
n
A
d
v
a
n
c
e
s i
n
N
e
u
ra
l
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
S
y
s
t
e
m
s (Ne
u
rI
PS
/
N
I
PS
2
0
1
2
)
,
2
0
1
2
,
p
p
.
1
0
9
7
–
1
1
0
5
.
[
1
6
]
I
.
G
o
o
d
f
e
l
l
o
w
,
Y
.
B
e
n
g
i
o
,
a
n
d
A
.
C
o
u
r
v
i
l
l
e
,
D
e
e
p
l
e
a
r
n
i
n
g
,
1
s
t
e
d
.
C
a
mb
r
i
d
g
e
,
M
A
:
M
I
T
P
r
e
ss
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
3
,
No
v
em
b
er
20
26
:
3
6
9
-
376
376
[
1
7
]
V
.
N
a
i
r
a
n
d
G
.
E
.
H
i
n
t
o
n
,
“
R
e
c
t
i
f
i
e
d
l
i
n
e
a
r
u
n
i
t
s
i
mp
r
o
v
e
r
e
s
t
r
i
c
t
e
d
B
o
l
t
z
man
n
m
a
c
h
i
n
e
s
,
”
i
n
I
C
ML
2
0
1
0
-
Pr
o
c
e
e
d
i
n
g
s
,
2
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
2
0
1
0
,
p
p
.
8
0
7
–
8
1
4
.
[
18
]
M
.
T
a
n
a
n
d
Q
.
L
e
,
“
Ef
f
i
c
i
e
n
t
N
e
t
:
r
e
t
h
i
n
k
i
n
g
m
o
d
e
l
s
c
a
l
i
n
g
f
o
r
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
2
0
1
9
,
p
p
.
6
1
0
5
–
6
1
1
4
.
[
19
]
J.
D
e
n
g
,
W
.
D
o
n
g
,
R
.
S
o
c
h
e
r
,
L.
J.
Li
,
K
.
L
i
,
a
n
d
L
.
F
e
i
-
F
e
i
,
“
I
mag
e
N
e
t
:
a
l
a
r
g
e
-
sca
l
e
h
i
e
r
a
r
c
h
i
c
a
l
i
m
a
g
e
d
a
t
a
b
a
se,
”
i
n
I
EEE
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
Pa
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
(
C
VP
R
2
0
0
9
)
,
2
0
0
9
,
p
p
.
2
4
8
–
255
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
0
9
.
5
2
0
6
8
4
8
.
[
20
]
R
.
S
t
o
r
n
a
n
d
K
.
P
r
i
c
e
,
“
D
i
f
f
e
r
e
n
t
i
a
l
e
v
o
l
u
t
i
o
n
–
a
s
i
mp
l
e
a
n
d
e
f
f
i
c
i
e
n
t
h
e
u
r
i
st
i
c
f
o
r
g
l
o
b
a
l
o
p
t
i
m
i
z
a
t
i
o
n
o
v
e
r
c
o
n
t
i
n
u
o
u
s
s
p
a
c
e
s,
”
J
o
u
rn
a
l
o
f
G
l
o
b
a
l
O
p
t
i
m
i
z
a
t
i
o
n
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
3
4
1
–
3
5
9
,
1
9
9
7
,
d
o
i
:
1
0
.
1
0
2
3
/
A
:
1
0
0
8
2
0
2
8
2
1
3
2
8
.
[
21
]
J.
K
e
n
n
e
d
y
a
n
d
R
.
E
b
e
r
h
a
r
t
,
“
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
I
C
N
N
’
9
5
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
N
e
u
r
a
l
N
e
t
w
o
rks
,
1
9
9
5
,
p
p
.
1
9
4
2
–
1
9
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
N
N
.
1
9
9
5
.
4
8
8
9
6
8
.
[
22
]
S
.
M
i
r
j
a
l
i
l
i
,
S
.
M
.
M
i
r
j
a
l
i
l
i
,
a
n
d
A
.
L
e
w
i
s,
“
G
r
e
y
w
o
l
f
o
p
t
i
m
i
z
e
r
,
”
A
d
v
a
n
c
e
s
i
n
E
n
g
i
n
e
e
r
i
n
g
S
o
f
t
w
a
r
e
,
v
o
l
.
6
9
,
p
p
.
4
6
–
6
1
,
M
a
r
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
v
e
n
g
s
o
f
t
.
2
0
1
3
.
1
2
.
0
0
7
.
[
23
]
X
.
-
S
.
Y
a
n
g
,
“
A
n
e
w
me
t
a
h
e
u
r
i
st
i
c
b
a
t
-
i
n
s
p
i
r
e
d
a
l
g
o
r
i
t
h
m
,
”
i
n
N
a
t
u
re
I
n
s
p
i
r
e
d
C
o
o
p
e
ra
t
i
v
e
S
t
r
a
t
e
g
i
e
s
f
o
r
O
p
t
i
m
i
za
t
i
o
n
(
N
I
C
S
O
2
0
1
0
)
,
J
.
R
.
G
o
n
z
á
l
e
z
,
D
.
A
.
P
e
l
t
a
,
C
.
C
r
u
z
,
G
.
T
e
r
r
a
z
a
s
,
a
n
d
N
.
K
r
a
sn
o
g
o
r
,
Ed
s
.
,
B
e
r
l
i
n
,
H
e
i
d
e
l
b
e
r
g
:
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
1
0
,
p
p
.
6
5
–
74
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
1
2
5
3
8
-
6
_
6
.
[
24
]
X
.
-
S
.
Y
a
n
g
,
“
F
i
r
e
f
l
y
a
l
g
o
r
i
t
h
ms
f
o
r
mu
l
t
i
mo
d
a
l
o
p
t
i
m
i
z
a
t
i
o
n
,
”
i
n
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
S
t
o
c
h
a
st
i
c
Al
g
o
ri
t
h
m
s:
Fo
u
n
d
a
t
i
o
n
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s (S
AG
A
2
0
0
9
)
,
2
0
0
9
,
p
p
.
1
69
–
1
7
8
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
0
4
9
4
4
-
6
_
1
4
.
[
25
]
X
.
-
S
.
Y
a
n
g
a
n
d
S
.
D
e
b
,
“
C
u
c
k
o
o
s
e
a
r
c
h
v
i
a
Lé
v
y
f
l
i
g
h
t
s,
”
i
n
2
0
0
9
W
o
rl
d
C
o
n
g
r
e
ss
o
n
N
a
t
u
re
a
n
d
Bi
o
l
o
g
i
c
a
l
l
y
I
n
s
p
i
r
e
d
C
o
m
p
u
t
i
n
g
(
N
ABIC
2
0
0
9
)
,
2
0
0
9
,
p
p
.
2
1
0
–
214
,
d
o
i
:
1
0
.
1
1
0
9
/
N
A
B
I
C
.
2
0
0
9
.
5
3
9
3
6
9
0
.
[
26
]
S
.
S
a
l
c
e
d
o
-
S
a
n
z
,
J
.
D
.
S
e
r
,
I
.
L
a
n
d
a
-
To
r
r
e
s,
S
.
G
i
l
-
L
ó
p
e
z
,
a
n
d
J
.
A
.
P
o
r
t
i
l
l
a
-
F
i
g
u
e
r
a
s,
“
T
h
e
c
o
r
a
l
r
e
e
f
s
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m:
a
n
o
v
e
l
m
e
t
a
h
e
u
r
i
st
i
c
a
l
g
o
r
i
t
h
m
f
o
r
s
o
l
v
i
n
g
o
p
t
i
mi
z
a
t
i
o
n
p
r
o
b
l
e
ms
,
”
S
c
i
e
n
t
i
f
i
c
Wo
r
l
d
J
o
u
r
n
a
l
,
v
o
l
.
2
0
1
4
,
n
o
.
1
,
p.
7
3
9
7
6
8
,
2
0
1
4
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
4
/
7
3
9
7
6
8
.
[
27
]
D
.
K
a
r
a
b
o
g
a
,
“
A
n
i
d
e
a
b
a
s
e
d
o
n
h
o
n
e
y
b
e
e
sw
a
r
m
f
o
r
n
u
meri
c
a
l
o
p
t
i
mi
z
a
t
i
o
n
,
”
Te
c
h
n
i
c
a
l
R
e
p
o
r
t
(
TR
0
6
)
,
2
0
0
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
a
b
c
.
e
r
c
i
y
e
s
.
e
d
u
.
t
r
/
p
u
b
/
t
r
0
6
_
2
0
0
5
.
p
d
f
[
28
]
C
.
S
h
o
r
t
e
n
a
n
d
T.
M
.
K
h
o
s
h
g
o
f
t
a
a
r
,
“
A
su
r
v
e
y
o
n
i
ma
g
e
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
,
”
J
o
u
r
n
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
6
,
n
o
.
1
,
p.
1
8
1
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
1
9
-
0
1
9
7
-
0.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Av
in
e
sh
Cul
l
o
o
is
c
u
rre
n
t
ly
p
u
rsu
in
g
h
is
m
a
ste
r’s
d
e
g
re
e
in
th
e
M
AIML
P
ro
g
ra
m
m
e
a
t
th
e
Un
iv
e
rsity
o
f
Tec
h
n
o
lo
g
y
,
M
a
u
rit
iu
s,
w
h
il
e
wo
rk
i
n
g
a
s
a
n
Ap
p
li
c
a
ti
o
n
De
v
e
lo
p
e
r
a
t
Da
y
fo
rc
e
M
a
u
rit
iu
s.
He
is
c
e
rti
fied
in
M
icr
o
so
ft
AI
F
u
n
d
a
m
e
n
tals
a
n
d
is
a
lso
a
n
AWS
Ce
rti
fied
Clo
u
d
P
ra
c
ti
ti
o
n
e
r.
His
re
se
a
rc
h
a
n
d
p
ro
jec
t
i
n
tere
sts
in
c
l
u
d
e
m
a
c
h
in
e
le
a
rn
in
g
,
d
e
e
p
lea
rn
i
n
g
,
a
n
d
g
e
n
e
ra
ti
v
e
AI,
a
n
d
h
e
h
a
s
wo
rk
e
d
o
n
se
v
e
ra
l
p
r
o
jec
ts
in
th
e
se
a
re
a
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
v
in
e
sh
c
u
ll
o
o
@g
m
a
il
.
c
o
m
.
Av
in
a
sh
Bh
u
n
j
u
n
h
o
l
d
s
a
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
fr
o
m
th
e
Un
iv
e
rsity
o
f
M
a
u
ri
ti
u
s
a
n
d
a
P
o
stg
ra
d
u
a
te
Dip
l
o
m
a
in
Web
a
n
d
M
o
b
i
le
Ap
p
li
c
a
ti
o
n
De
v
e
lo
p
m
e
n
t
fro
m
th
e
O
p
e
n
Un
iv
e
rsity
.
He
wo
r
k
s
a
s
a
n
A
n
a
ly
st
a
n
d
De
v
e
lo
p
e
r
i
n
a
tex
t
il
e
c
o
m
p
a
n
y
,
sp
e
c
ializin
g
in
ERP
sy
ste
m
s
a
n
d
d
ig
it
a
l
s
o
lu
t
io
n
s.
He
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
n
M
.
S
c
.
in
Artifi
c
ial
I
n
telli
g
e
n
c
e
with
M
a
c
h
in
e
Lea
rn
in
g
a
t
th
e
Un
iv
e
rsit
y
o
f
Tec
h
n
o
lo
g
y
,
M
a
u
rit
i
u
s,
a
n
d
h
a
s
e
x
p
e
rien
c
e
wo
rk
i
n
g
o
n
m
a
c
h
in
e
lea
rn
in
g
p
ro
jec
ts.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
v
ib
h
u
n
ju
n
@g
m
a
il
.
c
o
m
.
G
e
e
r
ish
S
u
d
d
u
l
re
c
e
iv
e
d
h
is
P
h
.
D.
fro
m
t
h
e
Un
iv
e
rsit
y
o
f
Tec
h
n
o
l
o
g
y
,
M
a
u
r
it
iu
s
(UTM
).
He
is
c
u
rre
n
tl
y
a
se
n
i
o
r
lec
tu
re
r
a
t
th
e
UTM
,
i
n
th
e
De
p
a
rtme
n
t
o
f
B
u
sin
e
ss
In
fo
rm
a
ti
c
s
a
n
d
S
o
f
twa
re
En
g
i
n
e
e
rin
g
u
n
d
e
r
t
h
e
S
c
h
o
o
l
o
f
I
n
n
o
v
a
t
iv
e
Tec
h
n
o
lo
g
ies
a
n
d
En
g
i
n
e
e
rin
g
.
He
h
a
s
b
e
e
n
a
c
ti
v
e
l
y
in
v
o
l
v
e
d
i
n
re
se
a
rc
h
a
n
d
tea
c
h
i
n
g
sin
c
e
2
0
0
5
,
a
n
d
c
u
rre
n
tl
y
h
is
re
se
a
rc
h
wo
rk
fo
c
u
se
s
o
n
d
if
fe
r
e
n
t
a
sp
e
c
ts
o
f
m
a
c
h
in
e
lea
rn
in
g
su
c
h
a
s
c
o
m
p
u
ter
v
isi
o
n
a
n
d
n
a
t
u
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
.
s
u
d
d
u
l@
u
tm.a
c
.
m
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.