I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
3373
~
3
3
8
1
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
3
.
pp
3
3
7
3
-
3
3
8
1
3373
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Deep
lea
rni
ng
-
ba
sed sem
a
ntic
seg
menta
tion o
f
t
o
m
a
to lea
f
disea
ses
using
U
-
Net
a
nd
clas
sifica
tion o
f
blig
h
t
usin
g
ResNet
Ash
a
M
a
ng
a
la
Sh
a
nk
a
re
g
o
w
da
1
,
2,
3
,
Yo
g
is
h H
ull
uk
er
e
K
a
deg
o
wda
2
,3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
C
H
R
I
S
T
U
n
i
v
e
r
si
t
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
R
a
mai
a
h
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
R
a
mai
a
h
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
V
i
sv
e
sv
a
r
a
y
a
Te
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
,
B
e
l
a
g
a
v
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
2
3
,
2
0
2
4
R
ev
is
ed
J
an
3
0
,
2
0
2
5
Acc
ep
ted
Ma
r
3
,
2
0
2
5
Eff
e
c
ti
v
e
d
ise
a
se
c
o
n
tr
o
l
re
q
u
ire
s
th
e
e
a
rly
i
d
e
n
t
ifi
c
a
ti
o
n
a
n
d
d
i
a
g
n
o
sis
o
f
p
lan
t
d
ise
a
se
s,
e
sp
e
c
ially
th
o
se
a
ffe
c
ti
n
g
to
m
a
to
lea
v
e
s.
A
c
ru
c
ial
sta
g
e
in
th
is p
ro
c
e
ss
is
se
g
m
e
n
ti
n
g
ima
g
e
s
o
f
d
ise
a
se
d
lea
v
e
s,
b
u
t
th
is
c
a
n
b
e
d
iffi
c
u
lt
b
e
c
a
u
se
o
f
th
e
u
n
e
v
e
n
sh
a
p
e
s,
v
a
ried
siz
e
s,
v
ib
ra
n
t
c
o
l
o
rs,
a
n
d
f
re
q
u
e
n
tl
y
b
lu
rr
y
b
o
r
d
e
rs
o
f
t
h
e
a
ffe
c
ted
p
o
rti
o
n
s,
in
a
d
d
i
ti
o
n
t
o
t
h
e
m
e
ss
y
b
a
c
k
g
ro
u
n
d
s.
We
p
r
o
p
o
se
a
d
e
e
p
lea
rn
in
g
-
b
a
se
d
stra
teg
y
b
a
se
d
o
n
t
h
e
U
-
Ne
t
a
rc
h
it
e
c
tu
re
fo
r
a
d
d
re
ss
in
g
t
h
e
se
issu
e
s,
e
n
a
b
li
n
g
p
re
c
ise
se
g
m
e
n
tatio
n
a
n
d
ti
m
e
ly
id
e
n
ti
fica
ti
o
n
o
f
t
o
m
a
to
le
a
f
d
ise
a
se
s.
Wi
th
a
DICE
sc
o
re
o
f
0
.
9
3
a
n
d
a
n
a
c
c
u
ra
c
y
o
f
9
3
%
in
id
e
n
ti
fy
in
g
h
e
a
lt
h
y
fro
m
d
ise
a
se
d
l
o
c
a
ti
o
n
s,
t
h
is
tec
h
n
iq
u
e
sh
o
ws
p
r
o
m
ise
in
h
e
lp
i
n
g
fa
rm
e
rs
c
a
rry
o
u
t
fo
c
u
se
d
i
n
te
rv
e
n
ti
o
n
s.
F
u
rth
e
rm
o
re
,
th
e
Re
sN
e
t1
8
m
o
d
e
l
h
a
s
g
o
o
d
lev
e
ls
o
f
s
p
e
c
ifi
c
it
y
,
se
n
siti
v
it
y
,
a
n
d
a
c
c
u
ra
c
y
wh
e
n
u
se
d
t
o
c
las
sify
e
a
rly
a
n
d
late
b
l
ig
h
t.
T
h
e
se
o
u
tc
o
m
e
s
h
ig
h
li
g
h
t
th
e
wa
y
o
u
r
s
u
g
g
e
ste
d
m
o
d
e
ls
p
e
rfo
rm
in
a
c
tu
a
l
a
g
ricu
lt
u
ra
l
e
n
v
iro
n
m
e
n
ts.
S
u
b
se
q
u
e
n
t
re
se
a
rc
h
e
n
d
e
a
v
o
rs
will
c
e
n
ter
o
n
a
u
g
m
e
n
ti
n
g
th
e
m
o
d
e
l'
s
g
e
n
e
ra
li
z
a
b
il
it
y
i
n
v
a
ri
o
u
s
a
g
r
icu
lt
u
ra
l
se
tt
in
g
s
a
n
d
i
n
v
e
stig
a
ti
n
g
m
u
lt
i
-
m
o
d
a
l
ima
g
i
n
g
m
e
th
o
d
o
lo
g
ies
.
It
is
a
lso
in
ten
d
e
d
f
o
r
th
e
a
d
v
a
n
c
e
m
e
n
t
o
f
m
o
b
il
e
a
p
p
l
ica
ti
o
n
s
a
n
d
e
d
g
e
c
o
m
p
u
t
in
g
t
o
e
n
a
b
le
re
a
l
-
ti
m
e
d
ise
a
se
m
o
n
it
o
r
in
g
a
n
d
su
sta
in
a
b
le farm
in
g
m
e
th
o
d
s w
o
rld
wi
d
e
.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
Plan
t d
is
ea
s
e
d
etec
tio
n
R
esNet1
8
T
o
m
ato
leaf
d
is
ea
s
es
U
-
Net
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ash
a
Ma
n
g
ala
Sh
an
k
ar
e
g
o
wd
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
C
HR
I
ST
Un
iv
er
s
ity
B
en
g
alu
r
u
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail: a
s
h
ag
o
wd
a0
5
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
On
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
c
r
o
p
s
in
t
h
e
wo
r
ld
in
ter
m
s
o
f
e
co
n
o
m
ic
im
p
ac
t
is
th
e
to
m
ato
(
S
o
l
a
n
u
m
Lyco
p
ers
ico
n
)
,
wh
ich
ad
d
s
v
ital
n
u
tr
ien
ts
an
d
tast
es
to
a
w
id
e
r
an
g
e
o
f
d
iets
.
T
o
m
ato
p
lan
ts
ar
e
p
r
o
n
e
to
a
n
u
m
b
er
o
f
illn
ess
es,
th
o
u
g
h
,
a
n
d
th
is
ca
n
n
eg
ativ
el
y
af
f
ec
t
g
r
o
wer
s
'
p
r
o
f
its
,
p
r
o
d
u
ctiv
it
y
,
a
n
d
q
u
ality
.
T
o
m
ato
m
o
s
aic
v
ir
u
s
,
p
o
wd
er
y
m
ild
e
w,
ea
r
ly
an
d
late
b
lig
h
t,
b
ac
ter
ial
s
p
o
t,
an
d
to
m
ato
b
lig
h
t a
r
e
am
o
n
g
th
e
co
m
m
o
n
d
is
ea
s
es
th
at
h
ar
m
to
m
ato
leav
es
[
1
]
–
[
3
]
.
T
h
e
s
ig
n
s
o
f
th
e
s
e
d
is
ea
s
e
s
in
clu
d
e
lesi
o
n
s
,
s
p
o
ts
,
d
is
co
lo
r
atio
n
,
wiltin
g
,
an
d
d
ef
o
r
m
ities
o
n
t
h
e
leav
es.
E
v
en
tu
ally
,
th
ese
co
n
d
itio
n
s
r
esu
lt
in
a
d
ec
r
ea
s
e
in
p
h
o
to
s
y
n
th
etic
ca
p
ab
ilit
y
an
d
h
am
p
e
r
ed
f
r
u
it
d
ev
elo
p
m
en
t
[
4
]
–
[
7
]
.
E
ar
ly
d
etec
tio
n
an
d
m
an
a
g
em
en
t
o
f
th
ese
d
is
ea
s
e
s
ar
e
p
ar
am
o
u
n
t
f
o
r
m
ain
tain
in
g
th
e
h
ea
lth
an
d
p
r
o
d
u
ctiv
ity
o
f
t
o
m
ato
c
r
o
p
s
.
T
im
ely
i
n
ter
v
en
tio
n
s
tr
ateg
ies,
s
u
c
h
as
tar
g
eted
p
esti
cid
e
ap
p
licatio
n
,
c
r
o
p
r
o
tatio
n
,
an
d
r
esis
tan
t
cu
ltiv
ar
s
elec
tio
n
,
ca
n
m
iti
g
ate
th
e
s
p
r
ea
d
an
d
s
ev
er
ity
o
f
d
is
ea
s
es,
th
er
eb
y
m
in
im
izin
g
y
ield
l
o
s
s
es a
n
d
en
s
u
r
in
g
f
o
o
d
s
ec
u
r
ity
.
I
n
r
ec
e
n
t
y
ea
r
s
,
ad
v
a
n
ce
m
en
ts
in
ar
tific
ial
in
tellig
en
ce
,
p
ar
ticu
lar
l
y
d
ee
p
lear
n
in
g
,
h
a
v
e
r
ev
o
lu
tio
n
ize
d
v
ar
io
u
s
f
ield
s
,
in
clu
d
in
g
co
m
p
u
ter
v
is
io
n
an
d
ag
r
icu
ltu
r
e.
Dee
p
lear
n
in
g
tech
n
iq
u
es,
esp
ec
ially
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
3
7
3
-
3
3
8
1
3374
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs),
h
av
e
s
h
o
wn
r
em
ar
k
ab
le
p
er
f
o
r
m
a
n
ce
in
im
ag
e
r
ec
o
g
n
itio
n
,
o
b
ject
d
etec
tio
n
,
an
d
s
em
an
tic
s
eg
m
en
tatio
n
task
s
.
Sem
an
tic
s
eg
m
en
tatio
n
,
a
p
ix
el
-
lev
el
cla
s
s
if
icatio
n
m
eth
o
d
,
ass
ig
n
s
ea
ch
p
ix
el
in
a
n
im
ag
e
to
a
s
p
ec
if
ic
class
lab
el,
en
a
b
l
in
g
d
etailed
u
n
d
e
r
s
tan
d
in
g
a
n
d
an
aly
s
is
o
f
v
is
u
al
d
ata
[
8
]
–
[
1
6
]
.
Am
o
n
g
C
NN
-
b
ased
a
r
ch
itectu
r
es,
U
-
Net
h
as
em
er
g
ed
as
a
p
o
wer
f
u
l
to
o
l
f
o
r
s
em
an
tic
s
eg
m
en
tatio
n
task
s
,
p
ar
ticu
lar
ly
in
b
io
m
ed
ic
al
im
ag
in
g
an
d
ag
r
ic
u
ltu
r
al
ap
p
licatio
n
s
.
T
h
e
U
-
Net
ar
ch
itec
tu
r
e
co
m
p
r
is
es
an
en
co
d
er
-
d
ec
o
d
er
f
r
a
m
ewo
r
k
with
s
y
m
m
etr
ic
co
n
tr
ac
tin
g
a
n
d
ex
p
a
n
s
iv
e
p
ath
way
s
,
f
ea
tu
r
in
g
s
k
ip
co
n
n
ec
tio
n
s
th
at
b
r
id
g
e
c
o
r
r
esp
o
n
d
in
g
lay
er
s
o
f
th
e
en
c
o
d
er
a
n
d
d
ec
o
d
e
r
.
T
h
is
d
esig
n
f
ac
ilit
ates
th
e
p
r
o
p
ag
atio
n
o
f
h
ig
h
-
r
eso
lu
tio
n
f
ea
tu
r
e
m
ap
s
f
r
o
m
th
e
en
c
o
d
er
to
th
e
d
ec
o
d
e
r
,
e
n
ab
lin
g
p
r
ec
is
e
l
o
ca
lizatio
n
a
n
d
s
eg
m
e
n
tatio
n
o
f
o
b
jects in
im
ag
es
[
1
7
]
,
[
1
8
]
.
Dee
p
r
esid
u
al
lear
n
in
g
is
u
s
ed
b
y
R
esNet1
8
,
a
r
esid
u
al
n
etwo
r
k
(
R
esNet
)
ar
ch
itectu
r
al
v
ar
iatio
n
,
to
h
elp
in
th
e
t
r
ain
in
g
o
f
e
x
tr
e
m
ely
d
ee
p
n
eu
r
al
n
etwo
r
k
s
.
I
t
u
s
es
r
esid
u
al
b
lo
ck
s
an
d
h
as
eig
h
teen
lay
er
s
,
in
clu
d
in
g
c
o
n
v
o
lu
tio
n
al,
p
o
o
l
in
g
,
an
d
f
u
lly
co
n
n
ec
ted
lay
e
r
s
.
A
s
h
o
r
tcu
t
lin
k
t
h
at
s
k
ip
s
o
n
e
o
r
m
o
r
e
lev
els
an
d
a
s
et
o
f
co
n
v
o
l
u
tio
n
al
la
y
er
s
ar
e
p
r
esen
t
in
ev
e
r
y
r
esid
u
al
b
lo
ck
.
B
y
p
er
m
itti
n
g
g
r
a
d
ie
n
ts
to
p
ass
s
tr
aig
h
t
th
r
o
u
g
h
t
h
e
n
etwo
r
k
,
th
is
s
h
o
r
tcu
t,
also
k
n
o
wn
as
a
s
k
i
p
lin
k
,
s
o
lv
es
t
h
e
v
an
is
h
in
g
g
r
a
d
ien
t
is
s
u
e
an
d
p
r
eser
v
es
s
ig
n
al
s
tr
en
g
th
wh
ile
en
h
an
cin
g
tr
ain
i
n
g
ef
f
ec
t
iv
en
ess
.
T
h
e
ar
ch
itectu
r
e’
s
a
b
ilit
y
to
m
ain
tain
p
er
f
o
r
m
an
ce
i
n
d
ee
p
n
etwo
r
k
s
with
o
u
t
d
eg
r
a
d
atio
n
is
p
r
im
ar
ily
attr
ib
u
ted
to
th
ese
r
e
s
id
u
al
co
n
n
e
ctio
n
s
,
en
ab
lin
g
R
esNet1
8
to
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
o
n
co
m
p
lex
im
ag
e
r
ec
o
g
n
itio
n
task
s
wh
ile
r
em
ain
in
g
co
m
p
u
tatio
n
ally
ef
f
icien
t
[
1
9
]
–
[
2
5
]
.
Ou
r
ap
p
r
o
ac
h
ac
h
iev
es
g
r
ea
t
p
r
ec
is
io
n
an
d
ac
cu
r
ac
y
b
y
ac
cu
r
ately
s
eg
m
en
tin
g
f
atig
u
ed
r
eg
io
n
s
in
to
m
ato
leaf
im
ag
es
u
s
in
g
a
U
-
Net
ar
ch
itectu
r
e.
I
t
en
s
u
r
es
h
i
g
h
s
p
ec
if
icity
an
d
s
en
s
itiv
ity
b
y
class
if
y
in
g
ea
r
ly
an
d
late
b
lig
h
t
u
s
in
g
th
e
R
esNet1
8
m
o
d
el.
T
h
is
m
et
h
o
d
im
p
r
o
v
es
s
u
s
tain
ab
le
f
ar
m
in
g
p
r
ac
tices
b
y
h
elp
in
g
f
ar
m
er
s
tr
ea
t d
is
ea
s
es in
a
tim
ely
an
d
f
o
cu
s
ed
m
a
n
n
er
.
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
T
h
e
d
ataset
u
s
ed
,
co
m
p
r
is
es
im
ag
es
o
f
to
m
ato
leav
es
ex
h
ib
itin
g
v
ar
io
u
s
d
is
ea
s
e
s
y
m
p
to
m
s
.
A
to
tal
o
f
2
8
0
9
im
ag
es
wer
e
co
llected
,
ca
p
tu
r
in
g
a
d
iv
er
s
e
r
an
g
e
o
f
d
is
ea
s
e
m
an
if
estatio
n
s
,
in
clu
d
in
g
lesi
o
n
s
,
s
p
o
ts
,
d
is
co
lo
r
atio
n
,
a
n
d
d
ef
o
r
m
ities
.
T
h
ese
im
ag
es
wer
e
o
b
tain
ed
f
r
o
m
a
Ka
g
g
le
c
h
allen
g
e
.
E
ac
h
im
a
g
e
in
t
h
e
d
ataset
is
ac
co
m
p
an
ie
d
b
y
a
co
r
r
esp
o
n
d
i
n
g
g
r
o
u
n
d
tr
u
t
h
m
ask
d
elin
ea
tin
g
th
e
u
n
h
ea
lth
y
r
e
g
io
n
s
o
n
t
h
e
to
m
ato
leav
es.
T
h
ese
m
ask
s
wer
e
m
an
u
all
y
an
n
o
tated
.
T
h
e
a
n
n
o
tatio
n
p
r
o
ce
s
s
in
v
o
lv
ed
m
eticu
lo
u
s
in
s
p
ec
tio
n
an
d
la
b
elin
g
o
f
d
is
e
ase
s
y
m
p
to
m
s
,
en
s
u
r
in
g
co
m
p
r
eh
en
s
iv
e
co
v
er
ag
e
o
f
all
af
f
ec
ted
r
eg
io
n
s
.
Fo
r
tr
ain
in
g
th
e
s
eg
m
e
n
tatio
n
m
o
d
el,
2
,
8
0
9
im
ag
es
f
r
o
m
th
e
d
ataset
wer
e
u
tili
ze
d
,
with
th
eir
r
esp
ec
tiv
e
g
r
o
u
n
d
tr
u
t
h
m
as
k
s
s
er
v
in
g
as
t
h
e
tar
g
et
lab
e
ls
f
o
r
s
u
p
e
r
v
is
ed
lear
n
in
g
.
T
h
e
tr
ain
in
g
d
ataset
in
clu
d
es
a
b
alan
ce
d
d
is
tr
ib
u
tio
n
o
f
im
ag
es
co
n
tain
in
g
d
if
f
e
r
en
t
d
is
ea
s
e
ty
p
es
an
d
s
ev
er
it
y
lev
els,
ac
co
u
n
tin
g
f
o
r
r
o
b
u
s
t
m
o
d
el
tr
ain
in
g
an
d
g
en
er
aliza
tio
n
.
T
o
ev
alu
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
eg
m
en
tatio
n
m
o
d
el,
a
s
ep
ar
ate
test
s
et
co
n
s
is
t
in
g
o
f
1
0
0
im
ag
es
was
cu
r
ated
.
T
h
es
e
test
im
ag
es
wer
e
s
elec
ted
to
en
co
m
p
ass
a
wid
e
r
an
g
e
o
f
d
is
ea
s
e
s
ce
n
ar
io
s
en
co
u
n
ter
ed
in
p
r
ac
tical
ag
r
icu
lt
u
r
al
s
ettin
g
s
,
in
clu
d
in
g
c
o
m
m
o
n
d
is
ea
s
es
s
u
ch
as
b
ac
ter
ial
s
p
o
t,
ea
r
l
y
b
lig
h
t
an
d
late
b
lig
h
t.
T
h
e
co
r
r
esp
o
n
d
i
n
g
g
r
o
u
n
d
tr
u
th
m
ask
s
f
o
r
t
h
e
test
s
et
wer
e
also
p
r
o
v
id
e
d
to
ass
ess
th
e
m
o
d
el'
s
ac
cu
r
ac
y
a
n
d
g
e
n
er
aliza
tio
n
c
ap
ab
ilit
ies o
n
u
n
s
ee
n
d
ata.
T
h
e
d
ataset
u
n
d
e
r
g
o
es
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
to
en
s
u
r
e
c
o
n
s
is
ten
cy
an
d
c
o
m
p
atib
ilit
y
with
th
e
s
eg
m
en
tatio
n
m
o
d
el.
T
h
is
in
clu
d
es
r
esizin
g
all
im
ag
es
to
a
u
n
if
o
r
m
r
eso
lu
tio
n
o
f
2
5
6
×
2
5
6
p
i
x
els,
n
o
r
m
aliza
tio
n
to
s
tan
d
a
r
d
ize
p
ix
el
in
ten
s
ity
v
alu
es,
an
d
a
u
g
m
en
tatio
n
tech
n
iq
u
es
s
u
ch
a
s
r
an
d
o
m
r
o
tatio
n
s
,
f
lip
s
,
an
d
s
ca
lin
g
to
en
h
an
ce
th
e
d
iv
er
s
ity
o
f
tr
ain
in
g
s
am
p
les
an
d
im
p
r
o
v
e
m
o
d
el
r
o
b
u
s
tn
ess
.
T
h
e
d
ataset
u
tili
ze
d
f
o
r
class
if
icatio
n
o
f
b
lig
h
t
in
th
is
s
tu
d
y
is
ca
teg
o
r
iz
ed
in
to
two
d
is
tin
ct
class
es,
ea
r
ly
b
lig
h
t
an
d
late
b
lig
h
t,
co
n
s
is
tin
g
o
f
9
2
9
im
ag
es
o
f
ea
r
ly
b
lig
h
t
an
d
1
,
7
8
0
im
ag
es
o
f
late
b
lig
h
t.
T
o
f
ac
ilit
ate
r
o
b
u
s
t
ev
alu
atio
n
,
a
test
s
et
was
m
eticu
lo
u
s
ly
cu
r
ated
,
co
m
p
r
is
in
g
1
0
0
im
a
g
es,
with
an
eq
u
al
r
ep
r
esen
tatio
n
o
f
5
0
im
ag
es
f
r
o
m
ea
ch
class
.
Als
o
in
th
is
s
tu
d
y
ev
alu
atio
n
,
a
ca
r
ef
u
lly
s
elec
ted
test
s
et
d
ata
f
o
r
b
o
th
p
o
tato
a
n
d
m
aize
leav
es we
r
e
also
u
s
ed
.
2
.
2
.
Net
w
o
rk
a
rc
hite
ct
ure
T
h
e
d
ee
p
lear
n
in
g
ar
c
h
itectu
r
e
u
s
ed
in
th
is
s
tu
d
y
is
th
e
s
tan
d
ar
d
U
-
Net,
a
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
p
ec
if
ically
d
esig
n
e
d
f
o
r
s
em
an
tic
s
eg
m
en
tatio
n
task
s
.
U
-
Net
ar
ch
itectu
r
e
c
ap
tu
r
es
co
n
te
x
tu
al
in
f
o
r
m
atio
n
wh
ile
p
r
eser
v
in
g
s
p
atial
d
etails.
T
h
e
U
-
N
et
ar
ch
itectu
r
e
co
m
p
r
is
es
an
en
co
d
er
-
d
ec
o
d
er
f
r
am
ewo
r
k
with
s
k
ip
co
n
n
ec
ti
o
n
s
,
as sh
o
wn
in
Fig
u
r
e
1
.
T
h
e
en
co
d
er
r
o
u
te
is
m
a
d
e
u
p
o
f
a
s
er
ies
o
f
co
n
v
o
lu
tio
n
al
a
n
d
p
o
o
lin
g
lay
er
s
th
at
m
i
n
im
ize
s
p
atial
d
im
en
s
io
n
s
wh
ile
ca
p
tu
r
i
n
g
h
i
er
ar
ch
ical
ch
ar
ac
te
r
is
tics
.
R
ep
air
ed
lin
ea
r
u
n
it
(
R
eL
U)
ac
tiv
atio
n
f
u
n
ctio
n
s
tr
ail
ea
ch
co
n
v
o
lu
tio
n
al
lay
er
,
en
ab
lin
g
n
o
n
-
lin
ea
r
tr
a
n
s
f
o
r
m
at
io
n
s
.
T
h
e
d
ec
o
d
er
r
o
u
te,
wh
i
ch
co
n
s
is
ts
o
f
u
p
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dee
p
lea
r
n
in
g
-
b
a
s
ed
s
ema
n
tic
s
eg
men
ta
tio
n
o
f to
m
a
to
lea
f d
is
ea
s
es
…
(
A
s
h
a
Ma
n
g
a
la
S
h
a
n
ka
r
eg
o
w
d
a
)
3375
co
n
v
o
l
u
tio
n
al
lay
er
s
to
g
r
ad
u
ally
r
eg
ain
s
p
atial
r
eso
lu
tio
n
,
s
y
m
m
etr
ically
m
ir
r
o
r
s
th
e
e
n
co
d
er
.
B
y
c
r
ea
tin
g
s
k
ip
lin
k
s
b
etwe
en
th
e
en
co
d
er
an
d
d
ec
o
d
er
'
s
ap
p
r
o
p
r
iat
e
lay
er
s
,
f
ea
tu
r
e
m
ap
s
m
ay
f
lo
w
d
ir
ec
tly
ac
r
o
s
s
d
if
f
er
en
t
r
eso
lu
tio
n
lev
els.
T
h
ese
s
k
ip
co
n
n
ec
tio
n
s
ar
e
ess
e
n
tial
f
o
r
en
ab
lin
g
ac
c
u
r
ate
o
b
j
ec
t
lo
ca
lizatio
n
an
d
s
eg
m
en
tatio
n
b
y
f
u
s
in
g
t
h
e
en
co
d
er
'
s
h
ig
h
-
r
eso
lu
tio
n
f
ea
tu
r
e
m
ap
s
with
t
h
e
d
ec
o
d
er
'
s
lo
w
-
r
eso
lu
tio
n
f
ea
tu
r
e
m
ap
s
.
I
n
th
e
co
n
tex
t
o
f
U
-
Net
ar
ch
itectu
r
e,
“
co
p
y
a
n
d
cr
o
p
”
r
ef
er
s
t
o
th
e
p
r
o
ce
s
s
o
f
c
o
p
y
in
g
,
cr
o
p
p
in
g
,
an
d
co
n
ca
ten
atin
g
f
ea
tu
r
e
m
ap
s
f
r
o
m
th
e
co
n
tr
ac
tin
g
(
d
o
wn
s
am
p
lin
g
)
p
ath
with
f
ea
tu
r
e
m
a
p
s
f
r
o
m
th
e
ex
p
a
n
d
in
g
(
u
p
s
am
p
lin
g
)
p
ath
.
B
y
p
r
eser
v
in
g
s
p
atial
in
f
o
r
m
atio
n
an
d
co
m
b
in
in
g
h
ig
h
-
lev
el
d
ata
f
r
o
m
later
lay
er
s
with
lo
w
-
lev
el
ch
ar
ac
ter
is
tics
f
r
o
m
ea
r
lier
lay
er
s
,
th
is
im
p
r
o
v
es seg
m
en
tatio
n
ac
c
u
r
ac
y
.
Fig
u
r
e1
.
U
-
Net
ar
c
h
itectu
r
e
T
o
f
in
e
-
tu
n
e
an
d
lo
ca
lize
th
e
s
eg
m
en
ted
o
b
jects,
th
e
co
n
ca
t
en
ated
f
ea
tu
r
e
m
a
p
s
g
o
th
r
o
u
g
h
f
u
r
t
h
er
co
n
v
o
l
u
tio
n
al
p
r
o
ce
s
s
es
an
d
ac
tiv
atio
n
f
u
n
ctio
n
s
at
ea
ch
d
ec
o
d
in
g
p
h
ase.
W
h
ile
d
r
o
p
o
u
t
lay
e
r
s
m
ay
b
e
in
s
er
ted
to
r
ed
u
ce
o
v
e
r
f
itti
n
g
an
d
en
h
an
ce
m
o
d
el
g
en
e
r
aliza
tio
n
,
b
atch
n
o
r
m
aliza
tio
n
l
ay
er
s
ar
e
in
clu
d
ed
th
r
o
u
g
h
o
u
t t
h
e
n
etwo
r
k
to
s
tab
ilize
an
d
s
p
ee
d
u
p
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
.
T
h
e
last
lay
er
in
t
h
e
U
-
Net
ar
ch
itectu
r
e
c
r
ea
tes
p
ix
el
-
wis
e
p
r
o
b
ab
ilit
y
m
a
p
s
b
y
u
s
in
g
a
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ctio
n
to
s
h
o
w
h
o
w
lik
ely
it
is
th
at
ea
c
h
p
i
x
el
is
p
ar
t
o
f
th
e
tar
g
et
class
(
e.
g
.
,
h
ea
lth
y
o
r
s
ick
p
atch
es
o
n
to
m
ato
leav
es).
T
h
r
o
u
g
h
t
r
ain
in
g
,
th
e
m
o
d
el
c
o
m
p
ar
es
th
e
p
r
ed
icted
p
r
o
b
ab
ilit
y
m
ap
s
with
th
e
g
r
o
u
n
d
tr
u
th
m
ask
s
in
o
r
d
er
to
lear
n
h
o
w
t
o
m
in
im
ize
a
p
r
e
d
eter
m
in
ed
lo
s
s
f
u
n
ctio
n
,
s
u
c
h
as
DI
C
E
lo
s
s
was
ca
lcu
lated
u
s
in
g
(
1
)
an
d
(
2
)
as d
ep
icted
b
el
o
w.
=
−
1
∑
(
l
og
(
)
+
(
1
−
)
l
og
(
1
−
)
)
=
1
(
1
)
W
h
er
e
n
is
th
e
n
u
m
b
er
o
f
p
ix
e
ls
,
is
th
e
g
r
o
u
n
d
tr
u
th
lab
el
f
o
r
p
ix
el
I
(
0
o
r
1
f
o
r
b
in
ar
y
s
eg
m
en
tatio
n
)
,
is
th
e
p
r
ed
icted
p
r
o
b
ab
ilit
y
f
o
r
p
i
x
el
i
.
=
1
−
∑
=
1
∑
+
∑
=
1
=
1
(
2
)
W
h
er
e
is
th
e
g
r
o
u
n
d
tr
u
th
f
o
r
p
ix
el
,
is
th
e
p
r
ed
icted
v
al
u
e
f
o
r
p
ix
el
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
3
7
3
-
3
3
8
1
3376
Fig
u
r
e
2
r
ep
r
esen
tatio
n
o
f
th
e
R
esNet1
8
ar
ch
itectu
r
e
s
h
o
ws
i
ts
1
8
lay
e
r
s
-
co
n
v
o
lu
tio
n
al,
p
o
o
lin
g
,
a
n
d
f
u
lly
lin
k
ed
lay
er
s
-
ar
r
a
n
g
ed
in
to
a
s
eq
u
en
ce
o
f
r
esid
u
al
b
lo
c
k
s
.
I
n
R
esNet1
8
,
ea
ch
r
esid
u
al
b
lo
ck
is
c
o
m
p
o
s
e
d
o
f
two
co
n
v
o
l
u
tio
n
al
lay
er
s
,
b
atch
n
o
r
m
aliza
tio
n
,
an
d
a
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
e
id
en
tity
s
h
o
r
tcu
t
co
n
n
ec
tio
n
s
th
at
allo
w
th
e
in
p
u
t
to
b
y
p
ass
o
n
e
o
r
m
o
r
e
le
v
els
an
d
b
e
ad
d
ed
d
ir
ec
tly
to
th
e
o
u
tp
u
t
ar
e
wh
at
m
ak
e
th
ese
b
lo
ck
s
s
p
ec
ial.
B
ec
au
s
e
th
e
g
r
ad
ien
ts
m
ay
tr
av
el
th
r
o
u
g
h
th
e
id
en
tity
c
o
n
n
ec
ti
o
n
s
d
ir
ec
tly
d
u
r
in
g
b
ac
k
p
r
o
p
ag
atio
n
,
th
is
b
y
p
as
s
in
g
m
eth
o
d
s
u
b
s
tan
tially
m
itig
ates
th
e
v
an
is
h
in
g
g
r
a
d
ien
t
p
r
o
b
lem
.
T
h
is
p
r
eser
v
es th
e
s
ig
n
al
in
ten
s
ity
a
n
d
m
ak
es it e
asier
to
tr
ain
ev
e
n
d
ee
p
er
n
etwo
r
k
s
.
Fig
u
r
e
2
.
R
esNet1
8
ar
ch
itectu
r
e
f
o
r
class
if
y
in
g
b
lig
h
t
T
h
e
ar
c
h
itectu
r
e
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws:
th
e
in
itial
lay
e
r
is
a
7
×
7
co
n
v
o
lu
tio
n
al
lay
er
with
6
4
f
ilter
s
an
d
a
s
tr
id
e
o
f
2
,
f
o
llo
wed
b
y
a
3
×
3
m
ax
-
p
o
o
lin
g
lay
e
r
with
a
s
tr
id
e
o
f
2
.
Su
b
s
eq
u
en
tly
,
th
er
e
ar
e
f
o
u
r
s
tag
es,
ea
ch
co
n
tain
in
g
two
r
esid
u
al
b
lo
ck
s
.
T
h
e
f
ir
s
t
s
tag
e
in
clu
d
es
two
b
lo
ck
s
with
6
4
f
ilter
s
,
t
h
e
s
ec
o
n
d
s
tag
e
h
as
two
b
lo
ck
s
with
1
2
8
f
ilter
s
,
th
e
th
ir
d
s
tag
e
co
n
tain
s
two
b
lo
ck
s
with
2
5
6
f
ilter
s
,
an
d
th
e
f
o
u
r
th
s
tag
e
co
n
s
is
ts
o
f
two
b
lo
c
k
s
with
5
1
2
f
ilter
s
.
T
o
d
ec
r
ea
s
e
th
e
s
p
atial
d
im
en
s
io
n
s
o
f
th
e
f
ea
tu
r
e
m
ap
s
,
th
e
in
itial
co
n
v
o
lu
tio
n
in
th
e
r
esid
u
al
b
l
o
ck
h
as
a
s
tr
id
e
o
f
2
in
p
h
ases
wh
er
e
th
e
n
u
m
b
er
o
f
f
ilter
s
r
is
es.
A
f
u
ll
y
lin
k
e
d
lay
e
r
with
So
f
tMa
x
ac
tiv
atio
n
f
o
r
class
if
icatio
n
an
d
a
g
lo
b
al
av
er
ag
e
p
o
o
lin
g
lay
er
c
o
m
p
lete
th
e
n
et
wo
r
k
.
T
h
e
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
is
u
s
ed
f
o
r
th
e
class
if
icatio
n
task
s
in
th
is
s
tu
d
y
i
n
o
r
d
er
to
d
if
f
e
r
en
tiate
b
etwe
en
ea
r
ly
a
n
d
late
b
lig
h
t
in
to
m
ato
leav
es.
So
f
tMa
x
is
u
s
ed
to
tr
an
s
f
o
r
m
th
e
o
u
tp
u
t
lo
g
its
in
to
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
s
s
o
th
at
th
e
m
o
d
el
ca
n
f
o
r
ec
ast th
e
class
with
th
e
h
ig
h
est p
r
o
b
a
b
i
lity
.
T
h
is
r
esid
u
al
lear
n
in
g
f
r
am
ewo
r
k
allo
ws
R
esNet1
8
to
m
ain
tain
h
ig
h
p
er
f
o
r
m
an
ce
ev
en
with
in
cr
ea
s
ed
d
e
p
th
,
as
th
e
r
esid
u
al
co
n
n
ec
tio
n
s
p
r
o
v
id
e
a
d
ir
e
ct
p
ath
f
o
r
th
e
g
r
a
d
ien
t
f
lo
w,
th
u
s
en
h
a
n
cin
g
th
e
co
n
v
er
g
en
ce
r
ate
a
n
d
ac
c
u
r
a
cy
o
f
th
e
m
o
d
el.
T
h
ese
ar
c
h
itectu
r
al
ad
v
a
n
ce
s
ar
e
u
tili
ze
d
in
th
is
s
tu
d
y
'
s
ap
p
licatio
n
o
f
R
esNet1
8
to
p
r
o
v
id
e
ef
f
ec
tiv
e
an
d
p
r
ec
is
e
p
ictu
r
e
class
if
icatio
n
,
with
a
s
p
ec
if
ic
f
o
c
u
s
o
n
d
if
f
er
en
tiatin
g
b
etwe
en
ea
r
l
y
an
d
late
b
lig
h
t
in
p
la
n
t
p
h
o
to
s
.
T
h
e
n
etwo
r
k
is
a
g
o
o
d
f
it
f
o
r
th
is
ch
allen
g
i
n
g
class
if
icatio
n
task
b
ec
au
s
e
o
f
its
r
esil
ien
ce
an
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
ef
f
ec
tiv
en
ess
.
2
.
3
.
T
ra
ini
ng
m
et
ho
ds
T
h
e
U
-
Net
m
o
d
el
was
tr
ain
ed
f
o
r
1
0
0
ep
o
ch
s
.
Du
r
in
g
tr
ain
in
g
,
th
e
DI
C
E
lo
s
s
f
u
n
ctio
n
was
em
p
lo
y
ed
as
th
e
l
o
s
s
f
u
n
ctio
n
.
T
h
e
DI
C
E
l
o
s
s
q
u
an
tifie
s
th
e
s
im
ilar
ity
b
etwe
en
p
r
ed
icte
d
an
d
g
r
o
u
n
d
tr
u
th
s
eg
m
en
tatio
n
m
ask
s
,
g
u
i
d
in
g
t
h
e
m
o
d
el
to
wa
r
d
s
p
r
ec
is
e
s
eg
m
en
tatio
n
o
f
d
is
ea
s
ed
ar
ea
s
o
n
to
m
ato
leav
es.
T
o
o
p
tim
ize
th
e
m
o
d
el
p
ar
a
m
eter
s
,
th
e
Ad
am
o
p
tim
izer
was u
s
ed
.
5
0
ep
o
c
h
s
wer
e
u
s
ed
to
tr
ain
th
e
R
esNet
m
o
d
el.
T
h
e
lo
s
s
f
u
n
ctio
n
th
at
was
em
p
lo
y
ed
was
b
in
ar
y
cr
o
s
s
en
tr
o
p
y
lo
s
s
.
Star
tin
g
in
th
e
4
0
th
ep
o
ch
,
ea
r
ly
s
to
p
p
in
g
was
in
s
titu
ted
.
T
h
e
3
5
th
p
er
io
d
p
r
o
d
u
ce
d
th
e
b
est
m
o
d
el.
Alth
o
u
g
h
th
is
o
p
tim
ized
m
o
d
el
was
in
itially
tr
a
in
ed
o
n
t
o
m
ato
leav
es,
its
ef
f
ec
tiv
en
ess
was
s
u
b
s
eq
u
en
tly
ass
ess
ed
o
n
th
e
p
o
tato
an
d
m
aize
leaf
d
atasets
.
3.
RE
SU
L
T
S
Fig
u
r
e
3
s
h
o
ws
th
e
ev
o
lu
tio
n
o
f
th
e
lo
s
s
cu
r
v
e
o
v
er
1
0
0
tr
ain
in
g
ep
o
c
h
s
,
illu
s
tr
atin
g
th
e
U
-
Net
s
eg
m
en
tatio
n
m
o
d
el'
s
tr
ain
in
g
p
r
o
ce
s
s
f
o
r
to
m
ato
leaf
d
is
ea
s
e
d
etec
tio
n
.
T
h
e
lo
s
s
f
u
n
cti
o
n
s
tead
ily
d
ec
r
ea
s
es
as
th
e
lo
s
s
cu
r
v
e
d
is
p
lay
s
th
e
d
is
tin
ctiv
e
“
L
”
s
h
ap
e,
wh
ich
is
co
n
s
is
ten
t
wi
th
th
e
g
en
er
a
l
tr
en
d
s
ee
n
d
u
r
i
n
g
d
ee
p
lear
n
in
g
m
o
d
el
tr
ai
n
in
g
as
s
h
o
wn
in
Fig
u
r
e
3
.
T
h
e
DI
C
E
s
co
r
e
an
d
ac
cu
r
ac
y
ar
e
th
e
ass
e
s
s
m
en
t
m
etr
ic
s
th
at
ar
e
u
s
ed
to
ev
alu
ate
th
e
s
eg
m
en
tatio
n
m
o
d
el'
s
p
er
f
o
r
m
an
ce
.
T
h
ese
m
ea
s
u
r
em
en
ts
s
h
ed
in
s
ig
h
t
in
to
h
o
w
well
th
e
alg
o
r
ith
m
d
is
tin
g
u
is
h
es si
ck
ar
ea
s
o
n
to
m
ato
leav
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dee
p
lea
r
n
in
g
-
b
a
s
ed
s
ema
n
tic
s
eg
men
ta
tio
n
o
f to
m
a
to
lea
f d
is
ea
s
es
…
(
A
s
h
a
Ma
n
g
a
la
S
h
a
n
ka
r
eg
o
w
d
a
)
3377
Fig
u
r
e
3
.
L
o
s
s
cu
r
v
e
T
ab
le
1
s
u
m
m
ar
izes
th
e
s
eg
m
en
tatio
n
m
o
d
el'
s
ac
cu
r
ac
y
,
wh
ich
was
9
2
.
5
%,
an
d
its
D
I
C
E
s
co
r
e,
wh
ich
was 0
.
9
3
.
W
h
ile
th
e
DI
C
E
s
co
r
e
m
ea
s
u
r
es th
e
o
v
er
lap
b
etwe
en
th
e
an
ticip
ated
a
n
d
g
r
o
u
n
d
tr
u
th
m
ask
s
,
o
f
f
er
in
g
a
r
eliab
le
in
d
icato
r
o
f
s
eg
m
en
tatio
n
ac
cu
r
ac
y
,
th
e
a
cc
u
r
ac
y
m
etr
ic
s
h
o
ws
th
e
p
r
o
p
o
r
tio
n
o
f
p
r
o
p
e
r
ly
id
en
tifie
d
p
ix
els in
th
e
s
eg
m
en
tatio
n
m
ask
s
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
m
etr
ics
f
o
r
T
o
m
ato
d
ataset
M
e
t
r
i
c
V
a
l
u
e
A
c
c
u
r
a
c
y
9
2
.
5
%
D
I
C
E
s
c
o
r
e
0
.
9
3
A
test
s
et
o
f
1
0
0
im
ag
es,
e
q
u
ally
r
ep
r
esen
ted
b
y
5
0
im
ag
es
f
r
o
m
ea
c
h
class
,
was
u
s
ed
to
ass
es
s
th
e
R
esNet1
8
m
o
d
el's
ef
f
ec
tiv
en
ess
in
d
if
f
er
en
tiatin
g
b
etwe
en
ea
r
ly
an
d
late
b
lig
h
t.
T
h
e
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
an
d
ac
cu
r
ac
y
o
f
th
e
m
o
d
el'
s
p
r
ed
ictio
n
s
wer
e
ass
ess
ed
,
an
d
f
o
r
ea
ch
o
f
th
e
th
r
ee
d
atasets
,
a
co
n
f
u
s
io
n
m
atr
ix
an
d
r
ec
eiv
e
r
o
p
e
r
atin
g
ch
a
r
ac
ter
is
tic
(
R
O
C
)
cu
r
v
e
wer
e
u
s
e
d
to
v
is
u
alize
th
e
r
esu
lts
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
,
d
ep
icted
in
Fig
u
r
e
4
,
s
u
m
m
ar
izes
th
e
class
if
icatio
n
o
u
tco
m
es.
T
h
e
m
o
d
el
co
r
r
ec
tly
i
d
en
t
if
ied
4
7
o
u
t
o
f
5
0
ea
r
ly
b
lig
h
t
ca
s
es
an
d
4
8
o
u
t
o
f
5
0
late
b
lig
h
t
ca
s
es
f
r
o
m
T
o
m
ato
leaf
d
ataset.
T
h
e
co
n
f
u
s
i
o
n
m
atr
ix
,
d
ep
icted
in
Fig
u
r
e
5
(
a)
,
s
u
m
m
a
r
izes
th
e
class
if
icatio
n
o
u
tco
m
es.
T
h
e
m
o
d
el
co
r
r
ec
tly
id
en
tifie
d
4
4
o
u
t
o
f
5
0
ea
r
ly
b
lig
h
t
ca
s
es
an
d
4
5
o
u
t
o
f
5
0
late
b
lig
h
t
ca
s
es
f
r
o
m
Po
tato
leaf
d
ataset.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
,
d
ep
icted
in
Fig
u
r
e
5
(
b
)
,
s
u
m
m
ar
izes
th
e
class
if
icatio
n
o
u
tco
m
es.
T
h
e
m
o
d
el
co
r
r
ec
tly
id
e
n
tifie
d
4
1
o
u
t
o
f
5
0
ea
r
ly
b
lig
h
t
ca
s
es a
n
d
4
2
o
u
t o
f
5
0
late
b
li
g
h
t c
ases
f
r
o
m
Ma
ize
leaf
d
ata
s
et.
T
h
e
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
,
o
r
tr
u
e
p
o
s
itiv
e
an
d
tr
u
e
n
eg
ativ
e
r
ates,
wer
e
co
m
p
u
ted
f
r
o
m
th
e
co
n
f
u
s
io
n
m
atr
ix
.
9
6
%
o
f
r
ea
l la
te
b
lig
h
t
in
s
tan
ce
s
wer
e
f
o
u
n
d
to
b
e
s
u
cc
ess
f
u
lly
d
etec
ted
,
wh
ich
is
k
n
o
wn
as
th
e
s
en
s
itiv
ity
.
9
4
%
o
f
tr
u
e
ea
r
ly
b
lig
h
t
ca
s
es
wer
e
s
u
cc
ess
f
u
lly
r
ec
o
g
n
ized
,
ac
c
o
r
d
i
n
g
to
th
e
s
p
ec
if
icity
.
Usi
n
g
th
e
T
o
m
ato
L
ea
f
d
ataset,
th
e
m
o
d
el'
s
o
v
er
all
ac
c
u
r
ac
y
-
wh
ich
is
m
ea
s
u
r
e
d
as
t
h
e
p
er
ce
n
tag
e
o
f
p
r
o
p
e
r
ly
id
en
tifie
d
o
cc
u
r
r
en
ce
s
am
o
n
g
all
in
s
tan
ce
s
-
was
9
5
%.
T
h
e
ac
cu
r
ac
y
,
s
p
ec
if
icity
,
an
d
s
en
s
itiv
ity
f
o
r
th
r
ee
d
is
tin
ct
d
atasets
ar
e
s
h
o
wn
in
Fig
u
r
e
6
.
T
h
e
R
OC
cu
r
v
e
f
o
r
T
o
m
ato
le
af
d
ataset,
s
h
o
wn
in
Fig
u
r
e
7
,
illu
s
tr
ates
th
e
m
o
d
el'
s
d
iag
n
o
s
tic
ab
ilit
y
.
AUC
was
ca
lcu
lated
to
b
e
0
.
9
5
,
in
d
icatin
g
a
h
ig
h
lev
el
o
f
d
i
s
cr
im
in
ativ
e
p
o
wer
b
etwe
en
t
h
e
two
class
es.
T
h
e
R
OC
cu
r
v
e
d
em
o
n
s
tr
ates th
at
th
e
m
o
d
el
p
er
f
o
r
m
s
co
n
s
is
ten
tly
well
ac
r
o
s
s
v
ar
io
u
s
th
r
esh
o
l
d
lev
els.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
3
7
3
-
3
3
8
1
3378
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
ea
r
ly
b
lig
h
t a
n
d
late
b
lig
h
t T
o
m
ato
d
ataset
(
a)
(
b
)
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
ea
r
ly
b
lig
h
t a
n
d
late
b
lig
h
t f
o
r
(
a)
Po
tato
d
ataset
an
d
(
b
)
Ma
ize
d
ataset
Fig
u
r
e
6
.
Sen
s
itiv
ity
,
s
p
ec
if
ici
ty
an
d
ac
c
u
r
ac
y
p
lo
ts
f
o
r
v
ar
io
u
s
leaf
d
atasets
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dee
p
lea
r
n
in
g
-
b
a
s
ed
s
ema
n
tic
s
eg
men
ta
tio
n
o
f to
m
a
to
lea
f d
is
ea
s
es
…
(
A
s
h
a
Ma
n
g
a
la
S
h
a
n
ka
r
eg
o
w
d
a
)
3379
Fig
u
r
e
7
.
AUC an
d
R
OC
cu
r
v
e
4.
DIS
CU
SS
I
O
N
T
h
e
u
tili
za
tio
n
o
f
th
e
U
-
Net
ar
ch
itectu
r
e
in
th
is
s
tu
d
y
h
as
s
h
o
wed
p
r
o
m
is
in
g
o
u
tco
m
es
f
o
r
ea
r
l
y
d
etec
tio
n
an
d
p
r
ec
is
e
m
ap
p
in
g
o
f
to
m
ato
leaf
d
is
ea
s
es.
W
i
th
an
ac
cu
r
ac
y
o
f
9
2
.
5
%
an
d
a
DI
C
E
s
co
r
e
o
f
0
.
9
3
,
th
e
m
o
d
el
ef
f
ec
tiv
ely
d
is
tin
g
u
is
h
ed
b
etwe
en
h
ea
lth
y
a
n
d
d
is
ea
s
ed
r
eg
io
n
s
,
d
em
o
n
s
tr
atin
g
its
p
o
ten
tial
to
ai
d
f
ar
m
er
s
in
im
p
lem
en
tin
g
tar
g
eted
in
ter
v
en
tio
n
s
tr
ateg
ies.
T
h
is
ap
p
licatio
n
o
f
d
e
ep
lear
n
in
g
-
b
ase
d
s
eg
m
en
tatio
n
tech
n
i
q
u
es
h
o
ld
s
s
ig
n
if
ican
t
im
p
licatio
n
s
f
o
r
s
u
s
tain
ab
le
ag
r
icu
ltu
r
e,
em
p
o
wer
in
g
f
ar
m
e
r
s
with
tim
ely
in
f
o
r
m
atio
n
to
o
p
tim
iz
e
r
eso
u
r
ce
u
tili
za
tio
n
a
n
d
m
iti
g
ate
y
ield
lo
s
s
es.
T
h
e
a
s
s
e
s
s
m
e
n
t
f
i
n
d
i
n
g
s
s
h
o
w
t
h
a
t
t
h
e
R
es
N
et
1
8
m
o
d
e
l
p
e
r
f
o
r
m
s
w
e
ll
a
c
r
o
s
s
t
h
r
e
e
d
a
t
as
e
ts
:
t
o
m
at
o
,
p
o
t
a
t
o
,
a
n
d
m
a
i
z
e
l
e
a
v
es
,
f
o
r
b
o
t
h
t
h
e
e
a
r
l
y
b
l
i
g
h
t
a
n
d
l
at
e
b
l
ig
h
t
c
l
a
s
s
i
f
i
ca
t
i
o
n
t
as
k
s
.
W
it
h
r
e
s
p
e
c
t
t
o
t
h
e
t
o
m
a
t
o
l
e
a
f
d
a
t
a
s
e
t
,
t
h
e
m
o
d
e
l
a
c
h
i
e
v
ed
a
9
5
%
a
c
c
u
r
a
c
y
r
a
t
e
b
y
a
c
c
u
r
a
t
e
l
y
i
d
e
n
t
i
f
y
i
n
g
4
7
o
u
t
o
f
5
0
e
a
r
l
y
b
l
i
g
h
t
p
h
o
t
o
s
a
n
d
4
8
o
u
t
o
f
5
0
la
t
e
b
l
i
g
h
t
i
m
a
g
e
s
.
T
h
is
h
i
g
h
a
c
c
u
r
a
c
y
r
a
t
e
s
h
o
w
s
t
h
at
t
h
e
m
o
d
e
l
c
a
n
g
e
n
e
r
a
l
i
z
e
e
f
f
e
c
t
i
v
el
y
t
o
n
e
w
,
u
n
o
b
s
e
r
v
e
d
d
a
t
a
,
w
h
i
c
h
m
a
k
e
s
i
t
a
u
s
e
f
u
l
t
o
o
l
f
o
r
r
e
a
l
-
w
o
r
l
d
p
l
a
n
t
d
i
s
ea
s
e
d
e
te
c
t
i
o
n
a
p
p
l
i
c
a
t
i
o
n
s
.
T
h
e
m
o
d
e
l
'
s
a
b
i
li
t
y
t
o
a
c
c
u
r
at
e
l
y
i
d
e
n
t
i
f
y
c
a
s
es
o
f
l
a
t
e
b
l
i
g
h
t
,
w
h
ic
h
i
s
e
s
s
e
n
ti
a
l
t
o
s
t
o
p
p
i
n
g
t
h
e
s
p
r
e
a
d
o
f
t
h
i
s
m
o
r
e
a
g
g
r
e
s
s
i
v
e
b
li
g
h
t
t
y
p
e
,
i
s
d
e
m
o
n
s
t
r
a
t
e
d
b
y
i
t
s
s
e
n
s
it
i
v
it
y
o
f
0
.
9
6
.
S
i
m
i
l
a
r
l
y
,
t
h
e
s
p
e
ci
f
i
c
it
y
o
f
0
.
9
4
d
e
m
o
n
s
t
r
a
t
es
t
h
e
m
o
d
e
l
'
s
e
f
f
e
c
t
i
v
e
n
ess
i
n
a
c
c
u
r
a
t
e
l
y
d
e
t
e
c
ti
n
g
e
a
r
l
y
b
l
i
g
h
t
,
t
h
e
r
e
b
y
r
e
d
u
c
i
n
g
f
a
l
s
e
p
o
s
i
t
i
v
e
s
a
n
d
e
n
s
u
r
i
n
g
t
h
a
t
h
e
a
l
t
h
y
p
l
a
n
ts
a
r
e
n
o
t
m
i
s
ta
k
en
l
y
t
r
e
a
t
e
d
f
o
r
l
a
te
b
l
i
g
h
t
.
T
h
e
R
OC
c
u
r
v
e
a
n
d
t
h
e
c
o
r
r
e
s
p
o
n
d
i
n
g
A
U
C
o
f
0
.
9
5
f
u
r
t
h
e
r
c
o
r
r
o
b
o
r
a
t
e
t
h
e
m
o
d
el'
s
e
x
c
e
l
le
n
t
d
is
c
r
i
m
i
n
a
t
i
v
e
ca
p
a
b
i
l
i
ti
e
s
.
T
h
e
R
OC
c
u
r
v
e
i
l
l
u
s
t
r
a
t
es
t
h
a
t
t
h
e
R
es
N
e
t
1
8
m
o
d
e
l
m
a
i
n
t
a
i
n
s
a
h
i
g
h
t
r
u
e
p
o
s
i
t
i
v
e
r
a
t
e
w
h
i
l
e
k
e
e
p
i
n
g
t
h
e
f
a
l
s
e
p
o
s
i
ti
v
e
r
a
t
e
lo
w
a
c
r
o
s
s
d
i
f
f
e
r
e
n
t
t
h
r
e
s
h
o
l
d
s
et
t
i
n
g
s
,
w
h
i
c
h
is
es
s
e
n
t
i
a
l
f
o
r
m
a
k
i
n
g
r
e
l
ia
b
l
e
p
r
e
d
ic
t
i
o
n
s
i
n
v
a
r
y
i
n
g
o
p
e
r
a
ti
o
n
a
l
s
ce
n
a
r
i
o
s
.
Similar
r
esu
lts
wer
e
o
b
tain
ed
f
o
r
th
e
p
o
tato
lea
f
d
ataset,
w
h
er
e
th
e
m
o
d
el
ac
h
iev
ed
a
n
a
cc
u
r
ac
y
o
f
8
9
%
b
y
ac
c
u
r
ately
id
e
n
tify
in
g
4
4
o
u
t
o
f
5
0
ea
r
ly
b
lig
h
t
p
h
o
to
s
an
d
4
5
o
u
t
o
f
5
0
late
b
lig
h
t
im
ag
es.
T
h
e
R
OC
AUC
o
f
0
.
8
9
f
o
r
t
h
is
d
ataset
also
s
h
o
ws
th
e
s
en
s
it
iv
ity
an
d
s
p
ec
if
icity
,
s
u
g
g
esti
n
g
s
tr
o
n
g
p
e
r
f
o
r
m
an
ce
in
d
if
f
er
en
tiatin
g
b
etwe
en
ea
r
ly
an
d
late
b
lig
h
t.
B
ec
au
s
e
o
f
its
g
r
ea
t
ac
c
u
r
ac
y
,
th
e
m
o
d
el
m
a
y
also
b
e
tr
u
s
ted
to
id
en
tify
p
o
tato
lea
f
b
lig
h
t,
h
e
n
ce
ass
is
tin
g
d
is
ea
s
e
co
n
tr
o
l
i
n
itiativ
es.
Fo
r
th
e
m
aize
leaf
d
ataset,
th
e
m
o
d
el
co
r
r
ec
tly
id
en
tifie
d
4
1
o
u
t
o
f
5
0
ea
r
ly
b
lig
h
t
im
ag
es
an
d
4
2
o
u
t
o
f
5
0
late
b
lig
h
t
im
ag
es,
ac
h
iev
in
g
a
n
ac
cu
r
ac
y
o
f
8
3
%.
T
h
e
R
OC
AUC
o
f
0
.
8
3
,
w
h
ile
s
lig
h
tly
l
o
wer
th
an
th
e
o
th
er
d
atasets
,
s
till
s
ig
n
if
ies
a
s
o
lid
p
er
f
o
r
m
an
ce
i
n
d
if
f
er
en
tiatin
g
b
etwe
en
th
e
ty
p
es
o
f
b
lig
h
t.
T
h
e
m
o
d
el’
s
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
cr
o
p
s
s
h
o
wca
s
es
its
v
er
s
atility
an
d
r
o
b
u
s
tn
ess
in
p
lan
t
d
is
ea
s
e
d
etec
tio
n
,
m
ak
in
g
it
a
v
alu
ab
le
ass
et
f
o
r
ag
r
icu
ltu
r
al
d
is
ea
s
e
m
an
ag
em
en
t.
T
h
ese
r
esu
lts
u
n
d
e
r
s
co
r
e
th
e
m
o
d
el'
s
o
v
er
all
r
eliab
ilit
y
a
n
d
ef
f
ec
tiv
en
ess
,
d
em
o
n
s
tr
atin
g
i
ts
p
o
ten
tial
f
o
r
b
r
o
ad
a
p
p
licatio
n
i
n
ag
r
i
cu
ltu
r
al
d
is
ea
s
e
d
etec
tio
n
an
d
m
an
ag
e
m
en
t.
Mo
v
in
g
f
o
r
w
ar
d
,
f
u
tu
r
e
r
esear
c
h
en
d
ea
v
o
r
s
co
u
ld
ex
p
lo
r
e
a
v
en
u
es
to
en
h
an
ce
m
o
d
el
g
e
n
er
a
lizatio
n
ac
r
o
s
s
d
iv
er
s
e
ag
r
icu
l
tu
r
al
co
n
tex
ts
an
d
in
teg
r
ate
m
u
lti
-
m
o
d
al
im
ag
i
n
g
tech
n
iq
u
es
f
o
r
co
m
p
r
eh
e
n
s
iv
e
d
is
ea
s
e
d
iag
n
o
s
is
.
T
h
e
ad
o
p
tio
n
o
f
th
ese
tech
n
o
lo
g
ies
co
u
l
d
b
e
f
u
r
th
er
ac
ce
ler
ated
b
y
ef
f
o
r
ts
to
d
ev
e
lo
p
m
o
b
ile
an
d
ed
g
e
c
o
m
p
u
tin
g
s
o
lu
tio
n
s
f
o
r
in
-
th
e
-
f
ield
r
ea
l
-
tim
e
d
is
ea
s
e
m
o
n
ito
r
in
g
(
s
u
c
h
as
d
r
o
n
e
-
b
as
ed
m
o
n
ito
r
in
g
s
y
s
tem
s
)
,
w
h
ich
wo
u
l
d
u
ltima
tely
s
tr
en
g
th
en
an
d
s
u
s
tain
ag
r
icu
lt
u
r
al
s
y
s
tem
s
ac
r
o
s
s
th
e
g
lo
b
e.
5.
CO
NCLU
SI
O
N
T
h
is
wo
r
k
d
em
o
n
s
tr
ates
th
e
ef
f
ec
tiv
en
ess
o
f
d
ee
p
lea
r
n
in
g
m
o
d
els
in
ea
r
ly
d
ete
ctio
n
an
d
ca
teg
o
r
izatio
n
o
f
to
m
at
o
,
p
o
t
ato
,
an
d
m
aize
leaf
d
is
ea
s
es.
Pre
cise
id
en
tific
atio
n
o
f
af
f
l
icted
lo
ca
tio
n
s
was
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
3
7
3
-
3
3
8
1
3380
m
ad
e
p
o
s
s
ib
le
b
y
th
e
U
-
Net
ar
ch
itectu
r
e'
s
ex
ce
llen
t
ac
cu
r
ac
y
an
d
DI
C
E
s
co
r
es.
I
m
p
r
ess
iv
e
s
en
s
i
tiv
ity
,
s
p
ec
if
icity
,
an
d
o
v
er
all
ac
cu
r
a
cy
wer
e
d
em
o
n
s
tr
ated
b
y
t
h
e
R
esNet1
8
m
o
d
el
in
its
class
if
i
ca
tio
n
o
f
ea
r
l
y
an
d
late
b
lig
h
t a
cr
o
s
s
all
th
r
ee
d
ata
s
ets.
Fo
r
to
m
ato
leav
es,
th
e
m
o
d
el
ac
h
iev
e
d
9
5
% a
cc
u
r
ac
y
,
with
a
s
en
s
itiv
ity
o
f
0
.
9
6
a
n
d
s
p
ec
if
icity
o
f
0
.
9
4
.
Fo
r
p
o
tato
leav
es,
th
e
m
o
d
el
r
esu
lted
in
8
9
%
ac
cu
r
ac
y
an
d
an
R
OC
AU
C
o
f
0
.
8
9
.
Ab
o
u
t
m
aize
leav
es,
th
e
m
o
d
el'
s
ac
cu
r
ac
y
was
8
3
%
,
an
d
its
R
OC
AUC
was
0
.
8
3
.
T
h
ese
f
i
n
d
in
g
s
d
em
o
n
s
tr
ate
h
o
w
th
ese
m
o
d
el
s
,
wh
ich
o
f
f
er
ac
cu
r
ate
a
n
d
d
e
p
en
d
ab
le
d
is
ea
s
e
d
etec
tio
n
a
n
d
class
if
icatio
n
f
o
r
m
an
y
c
r
o
p
s
,
m
ig
h
t
e
n
h
an
ce
ag
r
icu
ltu
r
al
d
is
ea
s
e
co
n
tr
o
l
s
t
r
ateg
ies.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
co
n
ce
n
tr
ate
o
n
en
h
an
cin
g
m
o
d
el
g
e
n
er
aliza
tio
n
ac
r
o
s
s
v
ar
io
u
s
c
r
o
p
s
a
n
d
u
s
in
g
cu
ttin
g
-
ed
g
e
im
ag
in
g
te
ch
n
iq
u
es
to
f
u
r
th
er
m
ax
im
ize
r
ea
l
-
tim
e,
in
-
f
ield
d
i
s
ea
s
e
m
o
n
ito
r
in
g
an
d
in
ter
v
en
tio
n
.
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
Ash
a
Ma
n
g
ala
Sh
an
k
ar
eg
o
wd
a
✓
✓
✓
✓
✓
Yo
g
is
h
Hu
llu
k
er
e
Kad
eg
o
wd
a
✓
✓
✓
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.
I
NF
O
RM
E
D
CO
NS
E
N
T
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
all
d
ata
u
s
ed
in
th
is
s
tu
d
y
,
i
n
c
lu
d
in
g
im
ag
es
o
f
to
m
ato
lea
v
es,
wer
e
p
u
b
licly
av
ailab
le.
No
h
u
m
an
p
ar
ticip
an
ts
o
r
p
e
r
s
o
n
al
d
ata
w
er
e
in
v
o
lv
e
d
in
th
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
e
au
th
o
r
s
af
f
ir
m
th
at
th
e
r
esear
ch
was
co
n
d
u
cted
in
ac
co
r
d
an
ce
with
eth
ical
s
tan
d
ar
d
s
an
d
in
s
titu
tio
n
al
g
u
id
elin
es
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
en
ly
av
ailab
le
in
Kag
g
le
at
h
ttp
s
:
//w
w
w
.
ka
g
g
le.
co
m/d
a
ta
s
ets/
ch
a
r
u
ch
a
u
d
h
r
y/p
la
n
tvilla
g
e
-
to
ma
to
-
lea
f
-
d
a
ta
s
et
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
S
i
g
a
l
a
,
A
.
B
e
e
r
,
L
.
H
o
d
g
so
n
,
a
n
d
A
.
O
’
C
o
n
n
o
r
,
B
i
g
d
a
t
a
f
o
r
m
e
a
su
ri
n
g
t
h
e
i
m
p
a
c
t
o
f
t
o
u
r
i
sm
e
c
o
n
o
m
i
c
d
e
v
e
l
o
p
m
e
n
t
p
ro
g
r
a
m
m
e
s:
A
p
r
o
c
e
ss
a
n
d
q
u
a
l
i
t
y
c
ri
t
e
r
i
a
f
r
a
m
e
w
o
rk
f
o
r
u
si
n
g
b
i
g
d
a
t
a
.
2
0
1
9
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
13
-
6
3
3
9
-
9
_
4
.
[
2
]
G
.
N
g
u
y
e
n
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
s a
n
d
l
i
b
r
a
r
i
e
s
f
o
r
l
a
r
g
e
-
sc
a
l
e
d
a
t
a
mi
n
i
n
g
:
A
s
u
r
v
e
y
,
”
Ar
t
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
2
,
n
o
.
1
,
p
p
.
7
7
–
1
2
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
1
8
-
0
9
6
7
9
-
z.
[
3
]
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
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
0
1
9
-
0
1
9
7
-
0.
[
4
]
R
.
V
i
n
a
y
a
k
u
m
a
r
,
M
.
A
l
a
z
a
b
,
K
.
P
.
S
o
ma
n
,
P
.
P
o
o
r
n
a
c
h
a
n
d
r
a
n
,
A
.
A
l
-
N
e
mr
a
t
,
a
n
d
S
.
V
e
n
k
a
t
r
a
m
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
i
n
t
e
l
l
i
g
e
n
t
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
4
1
5
2
5
–
4
1
5
5
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
8
9
5
3
3
4
.
[
5
]
K
.
S
i
v
a
r
a
ma
n
,
R
.
M
.
V
.
K
r
i
s
h
n
a
n
,
B
.
S
u
n
d
a
r
r
a
j
,
a
n
d
S
.
S
r
i
G
o
w
t
h
e
m,
“
N
e
t
w
o
r
k
f
a
i
l
u
r
e
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
s
i
s
b
y
a
n
a
l
y
z
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Dee
p
lea
r
n
in
g
-
b
a
s
ed
s
ema
n
tic
s
eg
men
ta
tio
n
o
f to
m
a
to
lea
f d
is
ea
s
es
…
(
A
s
h
a
Ma
n
g
a
la
S
h
a
n
ka
r
eg
o
w
d
a
)
3381
sy
sl
o
g
a
n
d
S
N
S
d
a
t
a
:
A
p
p
l
y
i
n
g
b
i
g
d
a
t
a
a
n
a
l
y
s
i
s
t
o
n
e
t
w
o
r
k
o
p
e
r
a
t
i
o
n
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Ex
p
l
o
ri
n
g
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
8
,
n
o
.
9
S
p
e
c
i
a
l
I
ssu
e
3
,
p
p
.
8
8
3
–
8
8
7
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
3
5
9
4
0
/
i
j
i
t
e
e
.
I
3
1
8
7
.
0
7
8
9
S
3
1
9
.
[
6
]
A
.
D
.
D
w
i
v
e
d
i
,
G
.
S
r
i
v
a
s
t
a
v
a
,
S
.
D
h
a
r
,
a
n
d
R
.
S
i
n
g
h
,
“
A
d
e
c
e
n
t
r
a
l
i
z
e
d
p
r
i
v
a
c
y
-
p
r
e
ser
v
i
n
g
h
e
a
l
t
h
c
a
r
e
b
l
o
c
k
c
h
a
i
n
f
o
r
I
o
T,
”
S
e
n
s
o
rs
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
9
,
n
o
.
2
,
p
p
.
1
–
1
7
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
0
2
0
3
2
6
.
[
7
]
F
.
A
l
-
Tu
r
j
ma
n
,
H
.
Za
h
ma
t
k
e
sh
,
a
n
d
L.
M
o
s
t
a
r
d
a
,
“
Q
u
a
n
t
i
f
y
i
n
g
u
n
c
e
r
t
a
i
n
t
y
i
n
i
n
t
e
r
n
e
t
o
f
me
d
i
c
a
l
t
h
i
n
g
s
a
n
d
b
i
g
-
d
a
t
a
ser
v
i
c
e
s
u
si
n
g
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
1
5
7
4
9
–
1
1
5
7
5
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
3
1
6
3
7
.
[
8
]
L.
M
.
A
n
g
,
K
.
P
.
S
e
n
g
,
G
.
K
.
I
j
e
m
a
r
u
,
a
n
d
A
.
M
.
Z
u
n
g
e
r
u
,
“
D
e
p
l
o
y
m
e
n
t
o
f
I
o
V
f
o
r
smar
t
c
i
t
i
e
s
:
A
p
p
l
i
c
a
t
i
o
n
s,
a
r
c
h
i
t
e
c
t
u
r
e
,
a
n
d
c
h
a
l
l
e
n
g
e
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
6
4
7
3
–
6
4
9
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
8
.
2
8
8
7
0
7
6
.
[
9
]
S
.
K
u
mar
a
n
d
M
.
S
i
n
g
h
,
“
B
i
g
d
a
t
a
a
n
a
l
y
t
i
c
s
f
o
r
h
e
a
l
t
h
c
a
r
e
i
n
d
u
s
t
r
y
:
I
mp
a
c
t
,
a
p
p
l
i
c
a
t
i
o
n
s,
a
n
d
t
o
o
l
s,
”
Bi
g
D
a
t
a
M
i
n
i
n
g
a
n
d
An
a
l
y
t
i
c
s
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
4
8
–
5
7
,
2
0
1
9
,
d
o
i
:
1
0
.
2
6
5
9
9
/
B
D
M
A
.
2
0
1
8
.
9
0
2
0
0
3
1
.
[
1
0
]
B
.
P
.
L.
La
u
e
t
a
l
.
,
“
A
s
u
r
v
e
y
o
f
d
a
t
a
f
u
s
i
o
n
i
n
smar
t
c
i
t
y
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
n
f
o
rm
a
t
i
o
n
F
u
s
i
o
n
,
v
o
l
.
5
2
,
n
o
.
Ja
n
u
a
r
y
,
p
p
.
3
5
7
–
3
7
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s.
2
0
1
9
.
0
5
.
0
0
4
.
[
1
1
]
Y
.
W
u
e
t
a
l
.
,
“
L
a
r
g
e
s
c
a
l
e
i
n
c
r
e
m
e
n
t
a
l
l
e
a
r
n
i
n
g
,
”
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
si
o
n
a
n
d
Pa
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
2
0
1
9
-
Ju
n
e
,
p
p
.
3
7
4
–
3
8
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
9
.
0
0
0
4
6
.
[
1
2
]
A
.
M
o
s
a
v
i
,
S
.
S
h
a
msh
i
r
b
a
n
d
,
E
.
S
a
l
w
a
n
a
,
K
.
w
i
n
g
C
h
a
u
,
a
n
d
J.
H
.
M
.
T
a
h
,
“
P
r
e
d
i
c
t
i
o
n
o
f
m
u
l
t
i
-
i
n
p
u
t
s
b
u
b
b
l
e
c
o
l
u
m
n
r
e
a
c
t
o
r
u
si
n
g
a
n
o
v
e
l
h
y
b
r
i
d
m
o
d
e
l
o
f
c
o
mp
u
t
a
t
i
o
n
a
l
f
l
u
i
d
d
y
n
a
mi
c
s
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
E
n
g
i
n
e
e
ri
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
Fl
u
i
d
M
e
c
h
a
n
i
c
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
4
8
2
–
4
9
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
1
9
9
4
2
0
6
0
.
2
0
1
9
.
1
6
1
3
4
4
8
.
[
1
3
]
V
.
P
a
l
a
n
i
s
a
m
y
a
n
d
R
.
T
h
i
r
u
n
a
v
u
k
a
r
a
s
u
,
“
I
m
p
l
i
c
a
t
i
o
n
s
o
f
b
i
g
d
a
t
a
a
n
a
l
y
t
i
c
s
i
n
d
e
v
e
l
o
p
i
n
g
h
e
a
l
t
h
c
a
r
e
f
r
a
m
e
w
o
r
k
s
–
A
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
r
s
i
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
1
,
n
o
.
4
,
p
p
.
4
1
5
–
4
2
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
1
7
.
1
2
.
0
0
7
.
[
1
4
]
J.
S
a
d
o
w
s
k
i
,
“
W
h
e
n
d
a
t
a
i
s
c
a
p
i
t
a
l
:
d
a
t
a
f
i
c
a
t
i
o
n
,
a
c
c
u
mu
l
a
t
i
o
n
,
a
n
d
e
x
t
r
a
c
t
i
o
n
,
”
Bi
g
D
a
t
a
a
n
d
S
o
c
i
e
t
y
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
1
–
1
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
7
7
/
2
0
5
3
9
5
1
7
1
8
8
2
0
5
4
9
.
[
1
5
]
J.
R
.
S
a
u
r
a
,
B
.
R
.
H
e
r
r
a
e
z
,
a
n
d
A
.
R
e
y
e
s
-
M
e
n
e
n
d
e
z
,
“
C
o
m
p
a
r
i
n
g
a
t
r
a
d
i
t
i
o
n
a
l
a
p
p
r
o
a
c
h
f
o
r
f
i
n
a
n
c
i
a
l
b
r
a
n
d
c
o
mm
u
n
i
c
a
t
i
o
n
a
n
a
l
y
si
s
w
i
t
h
a
b
i
g
d
a
t
a
a
n
a
l
y
t
i
c
s t
e
c
h
n
i
q
u
e
,
”
I
EE
E
A
c
c
e
s
s
,
v
o
l
.
7
,
p
p
.
3
7
1
0
0
–
3
7
1
0
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ES
S
.
2
0
1
9
.
2
9
0
5
3
0
1
.
[
1
6
]
D
.
N
a
l
l
a
p
e
r
u
ma
e
t
a
l
.
,
“
O
n
l
i
n
e
i
n
c
r
e
me
n
t
a
l
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
p
l
a
t
f
o
r
m
f
o
r
b
i
g
d
a
t
a
-
d
r
i
v
e
n
sm
a
r
t
t
r
a
f
f
i
c
m
a
n
a
g
e
me
n
t
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
t
e
l
l
i
g
e
n
t
T
r
a
n
s
p
o
rt
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
2
0
,
n
o
.
1
2
,
p
p
.
4
6
7
9
–
4
6
9
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
TS.2
0
1
9
.
2
9
2
4
8
8
3
.
[
1
7
]
S
.
S
c
h
u
l
z
,
M
.
B
e
c
k
e
r
,
M
.
R
.
G
r
o
sec
l
o
se
,
S
.
S
c
h
a
d
t
,
a
n
d
C
.
H
o
p
f
,
“
A
d
v
a
n
c
e
d
M
A
LD
I
mass
s
p
e
c
t
r
o
m
e
t
r
y
i
ma
g
i
n
g
i
n
p
h
a
r
mac
e
u
t
i
c
a
l
r
e
s
e
a
r
c
h
a
n
d
d
r
u
g
d
e
v
e
l
o
p
m
e
n
t
,
”
C
u
rre
n
t
O
p
i
n
i
o
n
i
n
B
i
o
t
e
c
h
n
o
l
o
g
y
,
v
o
l
.
5
5
,
p
p
.
5
1
–
5
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
p
b
i
o
.
2
0
1
8
.
0
8
.
0
0
3
.
[
1
8
]
C
.
S
h
a
n
g
a
n
d
F
.
Y
o
u
,
“
D
a
t
a
a
n
a
l
y
t
i
c
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
smar
t
p
r
o
c
e
ss ma
n
u
f
a
c
t
u
r
i
n
g
:
R
e
c
e
n
t
a
d
v
a
n
c
e
s
a
n
d
p
e
r
sp
e
c
t
i
v
e
s
i
n
t
h
e
b
i
g
d
a
t
a
e
r
a
,
”
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
,
n
o
.
6
,
p
p
.
1
0
1
0
–
1
0
1
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
.
2
0
1
9
.
0
1
.
0
1
9
.
[
1
9
]
Y
.
Y
u
,
M
.
Li
,
L.
L
i
u
,
Y
.
Li
,
a
n
d
J
.
W
a
n
g
,
“
C
l
i
n
i
c
a
l
b
i
g
d
a
t
a
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
:
A
p
p
l
i
c
a
t
i
o
n
s
,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
f
u
t
u
r
e
o
u
t
l
o
o
k
s
,”
Bi
g
D
a
t
a
M
i
n
i
n
g
a
n
d
A
n
a
l
y
t
i
c
s
,
v
o
l
.
2
,
n
o
.
4
,
p
p
.
2
8
8
–
3
0
5
,
2
0
1
9
,
d
o
i
:
1
0
.
2
6
5
9
9
/
B
D
M
A
.
2
0
1
9
.
9
0
2
0
0
0
7
.
[
2
0
]
M
.
H
u
a
n
g
,
W
.
L
i
u
,
T.
W
a
n
g
,
H
.
S
o
n
g
,
X
.
L
i
,
a
n
d
A
.
L
i
u
,
“
A
q
u
e
u
i
n
g
d
e
l
a
y
u
t
i
l
i
z
a
t
i
o
n
s
c
h
e
me
f
o
r
o
n
-
p
a
t
h
ser
v
i
c
e
a
g
g
r
e
g
a
t
i
o
n
i
n
serv
i
c
e
s
-
o
r
i
e
n
t
e
d
c
o
m
p
u
t
i
n
g
n
e
t
w
o
r
k
s
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
2
3
8
1
6
–
2
3
8
3
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
8
9
9
4
0
2
.
[
2
1
]
G
.
X
u
,
Y
.
S
h
i
,
X
.
S
u
n
,
a
n
d
W
.
S
h
e
n
,
“
I
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
i
n
m
a
r
i
n
e
e
n
v
i
r
o
n
me
n
t
mo
n
i
t
o
r
i
n
g
:
A
r
e
v
i
e
w
,
”
S
e
n
so
rs
(
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
9
,
n
o
.
7
,
p
p
.
1
–
2
1
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
0
7
1
7
1
1
.
[
2
2
]
M
.
A
q
i
b
,
R
.
M
e
h
mo
o
d
,
A
.
A
l
z
a
h
r
a
n
i
,
I
.
K
a
t
i
b
,
A
.
A
l
b
e
s
h
r
i
,
a
n
d
S
.
M
.
A
l
t
o
w
a
i
j
r
i
,
S
m
a
rt
e
r
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
b
i
g
d
a
t
a
,
i
n
-
m
e
m
o
ry
c
o
m
p
u
t
i
n
g
,
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
g
p
u
s
,
v
o
l
.
1
9
,
n
o
.
9
.
2
0
1
9
.
d
o
i
:
1
0
.
3
3
9
0
/
s1
9
0
9
2
2
0
6
.
[
2
3
]
S
.
Le
o
n
e
l
l
i
a
n
d
N
.
Te
m
p
i
n
i
,
D
a
t
a
j
o
u
rn
e
y
s i
n
t
h
e
s
c
i
e
n
c
e
s
.
2
0
2
0
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
3
7
1
7
7
-
7.
[
2
4
]
N
.
S
t
y
l
o
s
a
n
d
J.
Zw
i
e
g
e
l
a
a
r
,
Bi
g
d
a
t
a
a
s
a
g
a
m
e
c
h
a
n
g
e
r:
H
o
w
d
o
e
s
i
t
s
h
a
p
e
b
u
si
n
e
ss
i
n
t
e
l
l
i
g
e
n
c
e
w
i
t
h
i
n
a
t
o
u
r
i
sm
a
n
d
h
o
s
p
i
t
a
l
i
t
y
i
n
d
u
s
t
ry
c
o
n
t
e
x
t
?
2
0
1
9
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
13
-
6
3
3
9
-
9
_
1
1
.
[
2
5
]
Q
.
S
o
n
g
,
H
.
G
e
,
J.
C
a
v
e
r
l
e
e
,
a
n
d
X
.
H
u
,
“
T
e
n
s
o
r
c
o
m
p
l
e
t
i
o
n
a
l
g
o
r
i
t
h
ms
i
n
b
i
g
d
a
t
a
a
n
a
l
y
t
i
c
s,
”
AC
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
D
i
sco
v
e
r
y
f
ro
m
D
a
t
a
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
–
4
8
,
Ja
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
4
5
/
3
2
7
8
6
0
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
As
h
a
Ma
n
g
a
l
a
S
h
a
n
k
a
r
e
g
o
wd
a
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
CHRIS
T
(De
e
m
e
d
to
b
e
Un
i
v
e
rsity
)
Ba
n
g
a
lo
re
.
S
h
e
re
c
e
iv
e
d
h
e
r
B.
E.
d
e
g
re
e
in
IS
E
fr
o
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
,
Be
lg
a
u
m
a
n
d
M
.
Tec
h
.
d
e
g
re
e
in
CCT
fro
m
M
y
s
o
re
Un
iv
e
rsit
y
.
S
h
e
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
h
e
r
Ph
.
D
.
a
t
Visv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
U
n
iv
e
rsit
y
(VTU),
Be
lg
a
u
m
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
ima
g
e
p
ro
c
e
ss
in
g
a
n
d
d
e
e
p
lea
rn
in
g
,
wh
e
re
s
h
e
a
c
ti
v
e
l
y
e
x
p
lo
re
s
a
d
v
a
n
c
e
m
e
n
ts
i
n
th
e
se
field
s.
Wi
t
h
a
stro
n
g
a
c
a
d
e
m
ic
b
a
c
k
g
r
o
u
n
d
a
n
d
a
p
a
ss
io
n
f
o
r
tea
c
h
i
n
g
,
sh
e
c
o
n
tr
ib
u
tes
sig
n
ifi
c
a
n
t
ly
to
b
o
th
re
se
a
rc
h
a
n
d
e
d
u
c
a
ti
o
n
in
c
o
m
p
u
ter
sc
ien
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
sh
a
g
o
wd
a
0
5
@g
m
a
il
.
c
o
m
.
Yo
g
ish
H
u
ll
u
k
e
r
e
K
a
d
e
g
o
wd
a
is
wo
r
k
in
g
a
s
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
re
c
e
iv
e
d
B.
E.
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
,
fr
o
m
P
E
S
CE,
M
a
n
d
y
a
,
M
y
s
o
re
Un
i
v
e
rsity
,
M
.
Tec
h
.
d
e
g
re
e
fro
m
S
JCE
M
y
so
re
,
VTU
Be
lag
a
v
i
i
n
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
.
P
h
.
D.
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Bh
a
ra
th
iar
Un
i
v
e
rsit
y
a
n
d
P
G
DCLCF
-
P
o
st
G
ra
d
u
a
te
Dip
lo
m
a
in
c
y
b
e
r
law
a
n
d
c
y
b
e
r
fo
re
n
sic
s
-
NLS
IU
(Na
ti
o
n
a
l
Law
S
c
h
o
o
l
o
f
I
n
d
ia
n
Un
i
v
e
rsity
)
–
Be
n
g
a
l
u
ru
.
P
r
o
d
u
c
e
d
F
o
u
r
P
h
.
D
.
,
a
n
d
c
u
rre
n
tl
y
g
u
i
d
in
g
6
sc
h
o
lars
fo
r
t
h
e
ir
P
h
.
D.
i
n
VTU.
P
u
b
l
ish
e
d
a
n
d
p
re
se
n
ted
1
0
3
p
a
p
e
rs
a
t
Na
ti
o
n
a
l/
In
tern
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
s/Jo
u
r
n
a
ls
a
m
o
n
g
2
5
p
a
p
e
rs
we
re
In
d
e
x
e
d
b
y
S
COPU
S
/W
e
b
o
f
S
c
ien
c
e
,
1
6
IEE
E
a
n
d
t
h
re
e
p
a
p
e
rs
in
DBLP
.
Two
p
a
ten
ts
a
n
d
o
n
e
c
o
p
y
ri
g
h
t
in
h
is
c
re
d
it
.
S
u
c
c
e
ss
fu
ll
y
g
u
id
e
d
fiv
e
P
h
Ds
a
n
d
g
u
id
in
g
6
P
h
D
S
c
h
o
lars
u
n
d
e
r
VTU.
F
iv
e
Bo
o
k
C
h
a
p
ters
F
e
tch
e
s
F
u
n
d
s
fro
m
M
OD
ROBS
-
AICTE
(
1
2
L
a
k
h
s),
DS
T
7
lak
h
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
y
o
g
ish
h
k
@g
m
a
il
.
c
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.