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.
1
6
,
No
.
4
,
A
u
g
u
s
t
20
2
6
,
p
p
.
1
876
~
1
8
8
4
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
4
.
pp
1
8
7
6
-
1
8
84
1876
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
A comp
a
ra
tive st
udy
of
ba
seline
co
nv
o
lutiona
l neural network
a
nd ResNe
t50
f
o
r
ima
g
e
-
ba
sed
tom
a
to
lea
f
disea
se cl
a
ss
ificatio
n
Su
m
a
na
B
ud
s
a
bo
k
,
Wa
chira
po
rn
P
o
lpa
nu
m
a
s
,
P
iy
a
na
n
K
ho
ng
ph
a
i
F
a
c
u
l
t
y
o
f
B
u
s
i
n
e
ss A
d
m
i
n
i
st
r
a
t
i
o
n
a
n
d
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
R
a
j
a
ma
n
g
a
l
a
U
n
i
v
e
r
s
i
t
y
o
f
T
e
c
h
n
o
l
o
g
y
S
u
v
a
r
n
a
b
h
u
mi
,
P
h
r
a
N
a
k
h
o
n
S
i
A
y
u
t
t
h
a
y
a
,
T
h
a
i
l
a
n
d
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
7
,
2
0
2
6
R
ev
is
ed
Ap
r
1
2
,
2
0
2
6
Acc
ep
ted
Ap
r
2
6
,
2
0
2
6
Im
a
g
e
-
b
a
se
d
tec
h
n
i
q
u
e
s
a
re
wid
e
ly
u
se
d
i
n
p
lan
t
d
ise
a
se
c
las
sifica
ti
o
n
to
su
p
p
o
rt
a
g
ricu
lt
u
ra
l
p
ro
d
u
c
ti
v
it
y
a
n
d
fa
c
il
it
a
te
e
a
rly
d
e
tec
ti
o
n
.
Th
is
st
u
d
y
p
re
se
n
ts
a
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
b
e
twe
e
n
a
b
a
se
li
n
e
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(CNN
)
a
n
d
a
Re
sN
e
t5
0
-
b
a
se
d
tran
sfe
r
lea
rn
in
g
m
o
d
e
l
f
o
r
to
m
a
to
lea
f
d
ise
a
se
c
l
a
ss
ifi
c
a
ti
o
n
.
A
p
u
b
li
c
l
y
a
v
a
il
a
b
le
d
a
tas
e
t
c
o
n
tai
n
in
g
fiv
e
c
a
teg
o
ries
—
to
m
a
to
b
a
c
teria
l
sp
o
t,
t
o
m
a
to
late
b
li
g
h
t,
t
o
m
a
to
se
p
to
ria
lea
f
sp
o
t,
t
o
m
a
to
y
e
ll
o
w
lea
f
c
u
r
l
v
i
ru
s,
a
n
d
h
e
a
lt
h
y
lea
v
e
s
—
wa
s
u
s
e
d
i
n
t
h
e
e
x
p
e
rime
n
ts.
M
o
d
e
l
p
e
rfo
rm
a
n
c
e
wa
s
e
v
a
lu
a
ted
u
sin
g
se
v
e
ra
l
sta
n
d
a
rd
c
las
sifica
ti
o
n
m
e
tri
c
s,
with
e
m
p
h
a
sis
o
n
o
v
e
ra
ll
a
c
c
u
ra
c
y
.
Th
e
b
a
s
e
li
n
e
CNN
a
c
h
iev
e
d
a
n
a
c
c
u
ra
c
y
o
f
9
7
.
0
%
,
wh
e
re
a
s
th
e
Re
sN
e
t5
0
m
o
d
e
l
re
a
c
h
e
d
9
9
.
6
%
.
Th
e
re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
t
h
e
Re
sN
e
t5
0
m
o
d
e
l
p
ro
d
u
c
e
s
m
o
re
sta
b
le
a
n
d
re
li
a
b
le
p
re
d
ictio
n
s,
p
a
rti
c
u
larly
w
h
e
n
d
isti
n
g
u
is
h
in
g
b
e
twe
e
n
v
isu
a
ll
y
sim
il
a
r
d
ise
a
se
c
las
se
s.
Th
e
se
fin
d
i
n
g
s
c
o
n
firm t
h
a
t
t
ra
n
sfe
r
lea
rn
in
g
c
a
n
e
ffe
c
ti
v
e
ly
imp
ro
v
e
c
las
sifica
ti
o
n
p
e
rf
o
rm
a
n
c
e
in
p
lan
t
d
ise
a
se
re
c
o
g
n
it
i
o
n
tas
k
s.
K
ey
w
o
r
d
s
:
C
o
m
p
u
ter
v
is
io
n
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
R
esNet5
0
Dee
p
lear
n
in
g
I
m
ag
e
class
if
icatio
n
Plan
t d
is
ea
s
e
r
ec
o
g
n
itio
n
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
:
W
ac
h
ir
ap
o
r
n
Po
lp
a
n
u
m
as
Facu
lty
o
f
B
u
s
in
ess
Ad
m
in
is
tr
atio
n
an
d
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
R
ajam
an
g
ala
U
n
iv
er
s
ity
o
f
T
ec
h
n
o
lo
g
y
Su
v
ar
n
ab
h
u
m
i
Ph
r
a
Nak
h
o
n
Si Ay
u
tth
ay
a,
T
h
ailan
d
E
m
ail: w
ac
h
ir
a.
p
@
r
m
u
ts
b
.
ac
.
t
h
1.
I
NT
RO
D
UCT
I
O
N
Plan
t
d
is
ea
s
es
p
o
s
e
s
er
io
u
s
ch
allen
g
es
to
ag
r
icu
ltu
r
al
p
r
o
d
u
ctiv
ity
,
f
o
o
d
s
ec
u
r
ity
,
a
n
d
ec
o
n
o
m
ic
s
tab
ilit
y
in
m
an
y
r
eg
io
n
s
.
I
n
to
m
ato
p
r
o
d
u
ctio
n
,
co
n
d
itio
n
s
s
u
ch
as
b
ac
ter
ial
s
p
o
t,
late
b
lig
h
t,
s
ep
to
r
ia
leaf
s
p
o
t,
an
d
v
ir
al
in
f
ec
tio
n
s
ca
n
s
ig
n
if
ican
tly
r
ed
u
ce
b
o
th
y
ield
an
d
cr
o
p
q
u
ality
,
p
a
r
ticu
lar
l
y
wh
en
th
ey
a
r
e
n
o
t
d
etec
ted
in
a
tim
ely
m
an
n
er
.
C
o
n
v
en
tio
n
al
d
iag
n
o
s
tic
p
r
a
ctice
s
co
m
m
o
n
ly
d
ep
en
d
o
n
ex
p
er
t
-
b
ased
v
is
u
al
in
s
p
ec
tio
n
,
wh
ic
h
is
o
f
ten
tim
e
-
in
ten
s
iv
e
an
d
m
ay
r
esu
lt
in
i
n
co
n
s
is
ten
t
ev
alu
atio
n
s
.
C
o
n
s
eq
u
en
tly
,
th
er
e
is
an
in
cr
ea
s
in
g
n
ee
d
f
o
r
m
o
r
e
ef
f
icien
t
an
d
r
eliab
le
au
to
m
ated
ap
p
r
o
ac
h
es
to
s
u
p
p
o
r
t
ac
cu
r
ate
p
lan
t
d
is
ea
s
e
d
etec
tio
n
[
1
]
–
[
6
]
.
R
ec
en
t
d
ev
elo
p
m
e
n
ts
in
co
m
p
u
ter
v
is
io
n
an
d
d
ee
p
lear
n
i
n
g
h
a
v
e
s
ig
n
if
ican
tl
y
ad
v
an
c
ed
im
ag
e
-
b
ased
p
lan
t
d
is
ea
s
e
class
if
ica
tio
n
.
I
n
p
a
r
ticu
lar
,
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
h
av
e
d
em
o
n
s
tr
ated
s
tr
o
n
g
ca
p
ab
ilit
y
in
ex
tr
ac
tin
g
m
ea
n
in
g
f
u
l
v
is
u
al
f
ea
tu
r
es
f
r
o
m
p
lan
t
im
ag
es,
s
u
ch
as
v
ar
iatio
n
s
in
co
lo
r
,
s
h
ap
e,
an
d
tex
tu
r
e.
Mo
r
e
o
v
er
,
tr
an
s
f
er
lear
n
in
g
m
eth
o
d
s
th
at
u
tili
ze
p
r
e
-
tr
ain
e
d
m
o
d
els
—
in
clu
d
in
g
R
esNet,
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
(
VG
G)
,
an
d
E
f
f
icien
tNet
—
h
av
e
b
ee
n
wid
ely
ad
o
p
ted
t
o
im
p
r
o
v
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
b
y
lev
e
r
ag
in
g
k
n
o
wled
g
e
f
r
o
m
la
r
g
e
-
s
ca
le
d
atasets
.
Am
o
n
g
th
ese
ap
p
r
o
a
ch
es,
R
esNet
h
as
r
ec
eiv
ed
co
n
s
id
er
a
b
le
atten
tio
n
d
u
e
to
its
r
esid
u
al
lear
n
in
g
f
r
am
ewo
r
k
,
wh
ich
f
ac
ilit
ates
m
o
r
e
s
tab
le
tr
ain
in
g
in
d
ee
p
n
etwo
r
k
a
r
ch
itectu
r
es
[
7
]
–
[1
8
]
.
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
A
co
mp
a
r
a
tive
s
tu
d
y
o
f
b
a
s
elin
e
co
n
vo
l
u
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
a
n
d
…
(
S
u
ma
n
a
B
u
d
s
a
b
o
k
)
1877
Desp
ite
th
ese
d
ev
elo
p
m
en
ts
,
m
an
y
s
tu
d
ies
f
o
c
u
s
o
n
ac
h
ie
v
in
g
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
u
s
in
g
co
m
p
lex
d
ee
p
lear
n
in
g
m
o
d
els,
with
lim
ited
atten
tio
n
g
iv
en
to
f
air
co
m
p
ar
is
o
n
s
u
n
d
er
co
n
s
is
ten
t
ex
p
er
im
en
tal
c
o
n
d
itio
n
s
.
I
t
is
o
f
ten
u
n
clea
r
wh
et
h
er
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
e
n
ts
ar
e
d
u
e
to
m
o
d
el
a
r
ch
itectu
r
e
o
r
d
if
f
e
r
en
ce
s
in
d
atasets
an
d
ev
alu
atio
n
s
ettin
g
s
[
8
]
,
[
1
2
]
,
[
1
3
]
,
[
1
5
]
,
[
1
6
]
,
[
1
9
]
–
[
2
1
]
.
T
o
ad
d
r
ess
th
e
id
en
tifie
d
r
es
ea
r
ch
g
ap
,
th
is
s
tu
d
y
f
o
cu
s
es
o
n
co
m
p
ar
in
g
a
b
aselin
e
C
NN
an
d
a
R
esNet5
0
-
b
ased
tr
an
s
f
er
lear
n
in
g
m
o
d
el
f
o
r
to
m
ato
le
af
d
is
ea
s
e
class
if
icatio
n
.
B
o
th
m
o
d
els
wer
e
im
p
lem
en
ted
u
s
in
g
id
e
n
tical
ex
p
er
im
en
tal
s
ettin
g
s
to
en
s
u
r
e
a
f
air
co
m
p
ar
is
o
n
.
T
h
eir
ef
f
ec
tiv
en
ess
was
ev
alu
ated
th
r
o
u
g
h
m
u
ltip
le
ass
es
s
m
en
t
ap
p
r
o
ac
h
es,
co
n
s
id
er
in
g
o
v
e
r
all
p
r
ed
ictio
n
ac
cu
r
ac
y
alo
n
g
with
ad
d
itio
n
al
p
e
r
f
o
r
m
an
ce
i
n
d
ic
ato
r
s
.
I
n
a
d
d
itio
n
,
a
c
o
n
f
u
s
i
o
n
m
atr
ix
was
em
p
lo
y
ed
to
ex
am
in
e
class
-
wis
e
p
r
ed
ictio
n
o
u
tco
m
es a
n
d
to
id
en
tify
p
atter
n
s
o
f
m
is
class
if
ica
tio
n
ac
r
o
s
s
d
if
f
er
e
n
t c
ateg
o
r
ie
s
.
T
h
is
wo
r
k
m
ak
es
th
r
ee
k
ey
co
n
tr
ib
u
tio
n
s
.
First,
a
lig
h
tweig
h
t
b
aselin
e
C
NN
an
d
a
d
ee
p
er
R
esNet5
0
-
b
ased
m
o
d
el
ar
e
d
esig
n
e
d
a
n
d
ev
alu
ate
d
u
n
d
er
th
e
s
am
e
d
ata
an
d
ex
p
e
r
im
en
tal
c
o
n
d
itio
n
s
to
e
n
s
u
r
e
a
f
air
co
m
p
ar
is
o
n
.
Seco
n
d
,
a
d
etai
led
co
m
p
a
r
is
o
n
is
ca
r
r
ied
o
u
t
to
ex
am
i
n
e
h
o
w
m
o
d
el
co
m
p
lex
ity
a
f
f
ec
ts
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
ir
d
,
th
e
s
tu
d
y
p
r
o
v
id
es
p
r
ac
t
ical
g
u
id
an
ce
o
n
s
elec
tin
g
s
u
itab
le
d
ee
p
lear
n
in
g
m
o
d
els
f
o
r
ag
r
icu
ltu
r
al
im
ag
e
an
aly
s
is
,
esp
ec
ially
f
o
r
r
ea
l
-
wo
r
ld
p
la
n
t
d
is
ea
s
e
d
etec
tio
n
task
s
wh
er
e
b
o
th
p
r
ed
ictiv
e
ac
cu
r
ac
y
an
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
ar
e
cr
itical
.
2.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
DS
T
h
is
s
ec
tio
n
d
escr
ib
es
th
e
m
eth
o
d
o
lo
g
ical
f
r
am
ewo
r
k
ad
o
p
ted
f
o
r
to
m
ato
leaf
d
is
ea
s
e
class
if
icatio
n
u
s
in
g
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es.
T
h
e
wo
r
k
f
lo
w
co
n
s
is
ts
o
f
s
ev
er
al
k
ey
s
tag
es,
in
clu
d
in
g
d
ataset
p
r
ep
ar
atio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
m
o
d
el
d
ev
elo
p
m
en
t,
tr
ain
in
g
,
an
d
ev
alu
atio
n
,
as p
r
esen
ted
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
T
h
e
m
ain
w
o
r
k
f
l
o
w
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
f
o
r
t
o
m
ato
leaf
d
is
ea
s
e
class
if
icatio
n
,
wh
ich
co
n
s
is
ts
o
f
d
ataset
p
r
ep
ar
atio
n
,
p
r
e
p
r
o
ce
s
s
in
g
,
m
o
d
el
d
ev
elo
p
m
en
t,
tr
ai
n
in
g
,
a
n
d
ev
al
u
atio
n
s
tag
es
2
.
1
.
Da
t
a
s
et
des
cr
iptio
n
A
p
u
b
licly
av
ailab
le
to
m
ato
leaf
im
ag
e
d
ataset
d
er
iv
ed
f
r
o
m
th
e
wid
ely
r
ec
o
g
n
ized
Plan
tVillag
e
d
ataset
was
u
tili
ze
d
to
ass
ess
th
e
p
er
f
o
r
m
an
ce
o
f
d
ee
p
lear
n
in
g
m
o
d
els
f
o
r
p
lan
t
d
is
ea
s
e
class
if
icatio
n
.
T
h
is
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.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
1
8
7
6
-
1
8
84
1878
d
ataset
is
well
estab
lis
h
ed
in
ag
r
icu
ltu
r
al
im
ag
e
an
aly
s
is
an
d
is
f
r
eq
u
en
tly
u
s
ed
as
a
r
ef
er
en
ce
b
en
ch
m
ar
k
f
o
r
ev
alu
atin
g
p
lan
t d
is
ea
s
e
r
ec
o
g
n
itio
n
m
o
d
els.
T
h
e
d
ataset
co
m
p
r
is
es
f
iv
e
ca
teg
o
r
ies:
to
m
ato
b
ac
ter
ial
s
p
o
t,
to
m
ato
late
b
lig
h
t,
to
m
ato
s
ep
to
r
ia
leaf
s
p
o
t,
to
m
ato
y
ello
w
leaf
cu
r
l
v
ir
u
s
,
an
d
h
ea
lth
y
leav
es.
I
m
ag
e
s
am
p
les
wer
e
o
b
tain
ed
u
n
d
er
co
n
tr
o
lled
en
v
ir
o
n
m
en
tal
s
ettin
g
s
,
ca
p
tu
r
in
g
v
ar
iatio
n
s
in
leaf
s
h
ap
e,
tex
tu
r
e,
co
lo
r
,
an
d
d
is
ea
s
e
s
ev
er
ity
.
Su
ch
d
iv
er
s
ity
p
r
o
v
id
es su
f
f
icien
t v
is
u
al
in
f
o
r
m
atio
n
f
o
r
ef
f
ec
tiv
e
m
o
d
el
tr
ain
in
g
an
d
ev
alu
atio
n
.
T
h
e
d
ataset
was
d
iv
id
ed
in
to
th
r
ee
s
u
b
s
ets:
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
in
g
,
to
en
s
u
r
e
a
r
eliab
le
ev
alu
atio
n
p
r
o
ce
s
s
.
T
h
e
tr
ain
in
g
s
u
b
s
et
was
u
s
ed
to
lear
n
m
o
d
el
p
ar
am
eter
s
,
wh
ile
th
e
v
alid
atio
n
s
u
b
s
et
h
elp
ed
o
p
tim
ize
p
er
f
o
r
m
an
ce
an
d
p
r
ev
en
t
o
v
er
f
itti
n
g
.
T
h
e
test
in
g
s
u
b
s
et
was
u
s
ed
to
ass
ess
th
e
f
in
al
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
e
u
s
e
o
f
a
p
u
b
licly
av
ailab
le
d
ataset
also
en
h
an
ce
s
r
ep
r
o
d
u
cib
ilit
y
an
d
en
ab
les
f
air
co
m
p
ar
is
o
n
with
ex
is
tin
g
s
tu
d
ies
in
p
lan
t
d
is
ea
s
e
class
if
icatio
n
[
2
]
,
[
8
]
,
[
1
9
]
.
T
h
e
d
etailed
d
is
tr
ib
u
tio
n
o
f
im
ag
e
s
am
p
les f
o
r
ea
ch
ca
teg
o
r
y
ac
r
o
s
s
th
ese
th
r
ee
s
u
b
s
ets is
o
u
tlin
ed
in
T
ab
le
1
.
T
ab
le
1
.
Su
m
m
a
r
y
o
f
to
m
ato
leaf
im
ag
e
s
am
p
les ac
r
o
s
s
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
in
g
s
u
b
s
ets
C
l
a
s
s
Tr
a
i
n
i
n
g
V
a
l
i
d
a
t
i
o
n
Te
st
i
n
g
To
t
a
l
To
ma
t
o
b
a
c
t
e
r
i
a
l
sp
o
t
1
,
7
0
1
2
1
3
2
1
3
2
,
1
2
7
To
ma
t
o
_
La
t
e
_
b
l
i
g
h
t
1
,
5
2
7
1
9
1
1
9
1
1
,
9
0
9
To
ma
t
o
se
p
t
o
r
i
a
l
e
a
f
s
p
o
t
1
,
4
1
6
1
7
7
1
7
8
1
,
7
7
1
To
ma
t
o
y
e
l
l
o
w
l
e
a
f
c
u
r
l
v
i
r
u
s
4
,
2
8
5
5
3
6
5
3
6
5
,
3
5
7
To
ma
t
o
h
e
a
l
t
h
y
1
,
2
7
2
1
5
9
1
6
0
1
,
5
9
1
To
t
a
l
1
0
,
2
0
1
1
,
2
7
6
1
,
2
7
8
1
2
,
7
5
5
2
.
2
.
Da
t
a
s
et
prepro
ce
s
s
ing
B
ef
o
r
e
tr
ain
in
g
,
all
im
ag
es
wer
e
p
r
ep
ar
ed
to
m
ain
tain
co
n
s
is
ten
cy
an
d
en
s
u
r
e
co
m
p
atib
ilit
y
with
th
e
d
ee
p
lear
n
in
g
m
o
d
els.
E
ac
h
im
ag
e
was
ad
ju
s
ted
to
a
u
n
if
o
r
m
s
ize
o
f
2
2
4
×
2
2
4
p
ix
els
to
m
atch
th
e
in
p
u
t
r
eq
u
ir
em
en
ts
o
f
th
e
R
esNet5
0
ar
ch
itectu
r
e.
I
n
ad
d
itio
n
,
p
ix
el
v
alu
es
wer
e
s
ca
led
to
im
p
r
o
v
e
n
u
m
er
ical
s
tab
ilit
y
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
Fo
r
th
e
b
aselin
e
C
NN
m
o
d
el,
p
ix
el
v
alu
es
wer
e
s
ca
led
to
th
e
r
an
g
e
[
0
,
1
]
.
I
n
co
n
tr
ast,
im
ag
es
u
s
ed
f
o
r
th
e
R
esNet5
0
m
o
d
el
wer
e
p
r
ep
r
o
ce
s
s
ed
u
s
in
g
th
e
p
r
ep
r
o
ce
s
s
_
in
p
u
t
f
u
n
ctio
n
,
wh
ich
ap
p
lies
ch
an
n
el
-
wis
e
n
o
r
m
aliza
tio
n
b
ased
o
n
th
e
I
m
ag
eNe
t
d
ataset
[
7
]
.
T
h
is
p
r
ep
r
o
ce
s
s
in
g
s
tep
is
ess
en
tial
to
f
u
lly
lev
er
ag
e
th
e
b
en
ef
its
o
f
tr
an
s
f
er
lear
n
in
g
with
p
r
e
-
tr
ain
ed
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
.
2
.
3
.
B
a
s
eline
CNN
a
rc
hite
ct
ure
T
h
e
b
aselin
e
C
NN
was
d
ev
elo
p
ed
as
a
r
ef
er
en
ce
m
o
d
el
f
o
r
p
er
f
o
r
m
an
ce
co
m
p
ar
is
o
n
.
T
h
e
ar
ch
itectu
r
e
is
co
m
p
o
s
ed
o
f
th
r
ee
co
n
v
o
lu
tio
n
al
s
tag
es,
ea
ch
d
esig
n
ed
to
p
r
o
g
r
ess
iv
ely
ca
p
tu
r
e
s
p
atial
f
ea
tu
r
es
f
r
o
m
th
e
in
p
u
t
im
ag
es.
E
ac
h
s
tag
e
in
clu
d
es
a
co
n
v
o
lu
tio
n
al
lay
er
f
o
llo
wed
b
y
a
m
ax
-
p
o
o
lin
g
o
p
er
atio
n
to
r
ed
u
ce
f
ea
tu
r
e
m
ap
d
im
en
s
io
n
s
.
T
h
e
f
ir
s
t stag
e
u
tili
ze
s
3
2
f
ilter
s
with
a
k
er
n
el
s
ize
o
f
3
×
3
an
d
em
p
lo
y
s
th
e
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
.
T
h
is
is
f
o
llo
wed
b
y
a
m
ax
-
p
o
o
lin
g
lay
er
with
a
p
o
o
lin
g
s
ize
o
f
2
×
2
.
I
n
th
e
s
ec
o
n
d
s
tag
e,
th
e
n
u
m
b
er
o
f
f
ilter
s
is
in
cr
ea
s
ed
to
6
4
wh
ile
m
ain
tain
in
g
th
e
s
am
e
k
er
n
el
s
ize
an
d
ac
tiv
atio
n
f
u
n
ctio
n
,
f
o
llo
wed
ag
ain
b
y
a
2
×
2
m
ax
-
p
o
o
lin
g
lay
er
.
T
h
e
th
ir
d
s
tag
e
f
u
r
th
er
ex
p
an
d
s
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
ca
p
ac
ity
b
y
u
s
in
g
1
2
8
f
ilter
s
with
a
3
×
3
k
er
n
el,
also
f
o
llo
wed
b
y
m
ax
-
p
o
o
lin
g
to
f
u
r
th
er
r
ed
u
ce
s
p
atial
r
eso
lu
tio
n
.
Af
ter
f
ea
tu
r
e
ex
tr
ac
tio
n
,
th
e
r
esu
ltin
g
f
ea
tu
r
e
m
ap
s
ar
e
f
latten
ed
an
d
p
ass
ed
to
a
f
u
lly
co
n
n
ec
ted
lay
er
co
n
s
is
tin
g
o
f
1
2
8
n
eu
r
o
n
s
with
R
eL
U
ac
tiv
atio
n
.
A
d
r
o
p
o
u
t
lay
er
with
a
r
ate
o
f
0
.
5
is
ap
p
lied
to
m
itig
ate
o
v
er
f
itti
n
g
.
Fin
ally
,
a
So
f
tMa
x
lay
er
is
u
s
ed
to
p
r
o
d
u
ce
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
s
ac
r
o
s
s
th
e
f
iv
e
to
m
ato
leaf
class
es.
Ov
er
all,
th
e
p
r
o
p
o
s
ed
b
aselin
e
ar
ch
itectu
r
e
is
d
esig
n
ed
to
b
alan
ce
co
m
p
u
tatio
n
al
ef
f
icien
cy
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
ca
p
ab
ilit
y
,
m
ak
in
g
it
s
u
itab
le
f
o
r
co
m
p
ar
is
o
n
with
m
o
r
e
ad
v
an
ce
d
d
ee
p
lear
n
in
g
m
o
d
els
[
2
2
]
,
[
2
3
]
.
2
.
4
.
ResNet
5
0
-
ba
s
ed
t
ra
ns
f
er
lea
rning
m
o
del
T
o
im
p
r
o
v
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
tr
an
s
f
er
lear
n
in
g
was
im
p
lem
en
ted
u
s
in
g
th
e
R
esNet5
0
ar
ch
itectu
r
e
p
r
e
-
tr
ain
ed
o
n
th
e
I
m
ag
eNe
t d
ataset.
T
h
e
o
r
ig
in
al
f
u
lly
co
n
n
ec
ted
lay
er
s
wer
e
r
em
o
v
ed
,
allo
win
g
th
e
m
o
d
el
to
f
u
n
ctio
n
as
a
f
ea
tu
r
e
ex
tr
ac
to
r
.
Du
r
in
g
tr
ain
in
g
,
th
e
co
n
v
o
lu
tio
n
al
b
ase
was
r
etain
ed
to
p
r
eser
v
e
lear
n
ed
r
ep
r
esen
tatio
n
s
wh
ile
r
ed
u
cin
g
co
m
p
u
tatio
n
al
co
s
t.
All
in
p
u
t
im
ag
es
wer
e
r
esized
to
2
2
4
×
224
×
3
to
en
s
u
r
e
co
m
p
atib
ilit
y
with
th
e
m
o
d
el
in
p
u
t
r
eq
u
ir
em
en
ts
.
A
g
lo
b
al
av
er
ag
e
p
o
o
lin
g
(
GAP)
lay
er
was
ap
p
lied
to
r
ed
u
ce
th
e
s
p
atial
d
im
en
s
io
n
s
o
f
th
e
f
ea
tu
r
e
m
ap
s
,
f
o
llo
wed
b
y
a
f
u
lly
co
n
n
ec
ted
lay
er
with
2
5
6
n
eu
r
o
n
s
u
s
in
g
R
eL
U
ac
tiv
atio
n
to
ca
p
tu
r
e
h
ig
h
er
-
lev
el
f
ea
tu
r
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
A
co
mp
a
r
a
tive
s
tu
d
y
o
f
b
a
s
elin
e
co
n
vo
l
u
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
a
n
d
…
(
S
u
ma
n
a
B
u
d
s
a
b
o
k
)
1879
T
o
m
itig
ate
o
v
er
f
itti
n
g
,
a
d
r
o
p
o
u
t
lay
er
with
a
r
ate
o
f
0
.
3
was
in
tr
o
d
u
ce
d
.
T
h
e
f
in
al
class
if
icatio
n
lay
er
u
s
es a
So
f
tMa
x
f
u
n
ctio
n
to
g
en
er
ate
class
p
r
o
b
ab
ilit
ies.
Fo
r
tr
ain
in
g
,
th
e
Ad
am
o
p
tim
izer
was e
m
p
lo
y
ed
with
a
lear
n
in
g
r
ate
o
f
0
.
0
0
0
1
,
an
d
s
p
ar
s
e
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
was
u
s
ed
as
th
e
lo
s
s
f
u
n
ctio
n
.
T
h
is
ar
ch
itectu
r
e
en
ab
les
ef
f
icien
t
f
ea
tu
r
e
ex
tr
ac
tio
n
wh
ile
lev
er
ag
in
g
th
e
s
tr
en
g
th
s
o
f
d
ee
p
r
esid
u
al
lear
n
in
g
to
en
h
an
ce
class
if
icatio
n
p
er
f
o
r
m
an
ce
[
1
1
]
,
[
1
9
]
.
2
.
5
.
T
ra
ini
ng
co
nfig
ura
t
io
n
T
h
e
m
o
d
els
wer
e
tr
ain
ed
u
s
in
g
th
e
Ad
am
o
p
tim
izer
with
an
in
itial
lear
n
in
g
r
ate
o
f
0
.
0
0
0
1
an
d
a
b
atch
s
ize
o
f
3
2
.
T
h
e
class
if
icatio
n
task
was
o
p
tim
ized
u
s
in
g
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
as
th
e
lo
s
s
f
u
n
ctio
n
.
T
r
ain
in
g
was
co
n
d
u
cted
f
o
r
a
m
ax
im
u
m
o
f
3
0
ep
o
ch
s
,
with
ea
r
ly
s
to
p
p
in
g
ap
p
lied
b
ased
o
n
v
alid
atio
n
p
er
f
o
r
m
an
ce
to
p
r
ev
en
t
o
v
er
f
itti
n
g
.
T
o
im
p
r
o
v
e
m
o
d
el
r
o
b
u
s
tn
ess
an
d
g
en
er
aliza
tio
n
,
s
ev
er
al
d
ata
au
g
m
en
tatio
n
tech
n
iq
u
es
wer
e
ap
p
lied
,
in
clu
d
in
g
h
o
r
izo
n
tal
an
d
v
er
tical
f
lip
p
in
g
,
s
lig
h
t
r
o
tatio
n
s
(
±
1
5
°),
an
d
b
r
ig
h
tn
ess
ad
ju
s
tm
en
ts
.
2
.
6
.
E
v
a
lua
t
io
n m
et
rics
T
h
e
p
er
f
o
r
m
an
ce
o
f
b
o
th
th
e
b
aselin
e
C
NN
an
d
R
esNet5
0
m
o
d
els
was
ex
am
in
ed
u
s
in
g
m
u
ltip
le
ev
alu
atio
n
m
etr
ics
to
o
b
tain
a
co
m
p
r
eh
en
s
iv
e
an
aly
s
is
.
Ov
er
all
class
if
icatio
n
ac
cu
r
ac
y
s
er
v
ed
as
th
e
m
ain
in
d
icato
r
o
f
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
,
wh
ile
ad
d
itio
n
al
m
etr
ics
wer
e
ap
p
lied
to
ass
ess
class
-
lev
el
b
eh
av
io
r
an
d
m
o
d
el
co
n
s
is
ten
cy
.
I
n
ad
d
itio
n
,
a
co
n
f
u
s
io
n
m
atr
ix
was
u
s
ed
to
ev
alu
ate
class
if
icatio
n
o
u
tco
m
es
ac
r
o
s
s
in
d
iv
id
u
al
class
es
an
d
to
id
en
tify
m
is
class
if
icatio
n
tr
en
d
s
.
T
o
g
eth
er
,
th
ese
m
etr
ics
o
f
f
er
in
s
ig
h
ts
in
to
th
e
ef
f
ec
tiv
en
ess
an
d
r
o
b
u
s
tn
ess
o
f
ea
ch
m
o
d
el
in
to
m
ato
leaf
d
is
ea
s
e
class
if
icatio
n
task
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
ex
p
er
im
e
n
tal
r
esu
lts
a
n
d
co
r
r
esp
o
n
d
in
g
an
aly
s
is
o
f
th
e
p
r
o
p
o
s
ed
to
m
ato
le
af
d
is
ea
s
e
class
if
icatio
n
m
o
d
els
ar
e
p
r
es
en
ted
in
th
is
s
ec
tio
n
.
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
b
o
th
t
h
e
b
aselin
e
C
NN
an
d
R
esNet5
0
m
o
d
els
is
ex
am
in
ed
u
s
in
g
s
ta
n
d
ar
d
ev
alu
ati
o
n
m
etr
ics,
f
o
c
u
s
in
g
o
n
o
v
er
all
p
r
e
d
ictio
n
a
cc
u
r
ac
y
an
d
class
-
lev
el
p
er
f
o
r
m
an
ce
.
3
.
1
.
P
er
f
o
r
m
a
nce
o
f
t
he
ba
s
eline
CNN
m
o
del
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
b
aselin
e
C
NN
m
o
d
el
was
ev
alu
ated
u
s
in
g
th
e
test
d
ataset
d
escr
ib
ed
in
Sectio
n
2
.
1
.
T
h
e
m
o
d
el
ac
h
iev
ed
an
o
v
er
all
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
7
.
0
%,
in
d
icatin
g
s
tr
o
n
g
b
aselin
e
p
er
f
o
r
m
an
ce
f
o
r
to
m
ato
leaf
d
is
ea
s
e
class
if
icatio
n
.
T
ab
le
2
s
u
m
m
ar
izes
th
e
class
if
icatio
n
r
esu
lts
o
f
th
e
b
aselin
e
C
NN
ac
r
o
s
s
all
ca
teg
o
r
ies.
T
h
e
m
o
d
el
p
er
f
o
r
m
s
well
o
n
v
is
u
ally
d
is
tin
ct
class
es,
s
u
ch
as
to
m
ato
y
ello
w
leaf
cu
r
l
v
ir
u
s
an
d
h
ea
lth
y
leav
es,
wh
er
e
p
r
ed
ictio
n
ac
cu
r
ac
y
is
co
n
s
is
ten
tly
h
ig
h
.
Ho
wev
er
,
r
elativ
ely
lo
wer
p
er
f
o
r
m
an
ce
is
o
b
s
er
v
ed
in
to
m
ato
late
b
lig
h
t
an
d
to
m
ato
s
ep
to
r
ia
leaf
s
p
o
t
,
with
F1
-
s
co
r
es
o
f
0
.
9
6
an
d
0
.
9
7
,
r
esp
ec
tiv
ely
.
T
h
is
r
ed
u
ctio
n
in
p
er
f
o
r
m
an
ce
m
ay
b
e
ass
o
ciate
d
with
s
im
ilar
ities
in
v
is
u
al
ch
ar
ac
ter
is
tics
am
o
n
g
th
ese
d
is
ea
s
e
class
es.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
p
r
esen
ted
in
Fig
u
r
e
2
s
h
o
ws
th
at
m
is
class
if
icatio
n
s
p
r
im
ar
ily
o
cc
u
r
b
etwe
en
class
es
with
s
im
ilar
v
is
u
al
p
atter
n
s
,
p
ar
ticu
lar
ly
in
ter
m
s
o
f
tex
tu
r
e
an
d
co
lo
r
d
is
tr
ib
u
tio
n
.
T
h
ese
o
b
s
er
v
atio
n
s
s
u
g
g
est
th
at
wh
ile
th
e
b
aselin
e
C
NN
ca
n
ca
p
tu
r
e
f
u
n
d
am
en
tal
v
is
u
al
f
ea
tu
r
es,
it
h
as
lim
itatio
n
s
in
d
is
tin
g
u
is
h
in
g
s
u
b
tle
d
if
f
er
en
ce
s
b
etwe
en
clo
s
ely
r
elate
d
class
es.
Ov
er
all,
th
e
b
aselin
e
C
NN
m
o
d
el
s
h
o
ws s
tab
le
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
class
es,
with
co
n
s
is
ten
tly
h
ig
h
class
if
icatio
n
r
esu
lts
.
Sev
er
al
d
is
ea
s
e
ca
teg
o
r
ies
ac
h
iev
e
n
ea
r
-
p
er
f
ec
t
p
r
ed
ictio
n
s
,
r
ef
lectin
g
th
e
m
o
d
el’
s
ab
ilit
y
to
ca
p
tu
r
e
im
p
o
r
tan
t
v
is
u
al
ch
ar
ac
ter
is
tics
.
I
n
ca
s
es
wh
er
e
class
es
s
h
ar
e
s
im
ilar
v
is
u
al
p
atter
n
s
,
s
lig
h
t
d
if
f
er
en
ce
s
in
p
er
f
o
r
m
an
ce
ca
n
b
e
o
b
s
er
v
ed
;
h
o
wev
er
,
th
e
m
o
d
el
s
till
m
ain
tain
s
r
eliab
le
an
d
co
n
s
is
ten
t
class
if
icatio
n
o
u
tco
m
es.
T
ab
le
2
.
p
r
o
v
i
d
es a
s
u
m
m
ar
y
o
f
th
e
b
aselin
e
C
NN
m
o
d
el’
s
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
n
th
e
to
m
ato
leaf
d
is
ea
s
e
d
at
aset
C
l
a
s
s
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
u
p
p
o
r
t
To
ma
t
o
b
a
c
t
e
r
i
a
l
sp
o
t
0
.
9
9
0
.
9
1
0
.
9
5
2
1
3
To
ma
t
o
l
a
t
e
b
l
i
g
h
t
0
.
9
9
0
.
9
3
0
.
9
6
1
9
1
To
ma
t
o
se
p
t
o
r
i
a
l
e
a
f
s
p
o
t
0
.
9
4
1
.
0
0
0
.
9
7
1
7
8
To
ma
t
o
y
e
l
l
o
w
l
e
a
f
c
u
r
l
v
i
r
u
s
0
.
9
7
1
.
0
0
0
.
9
8
5
3
6
To
ma
t
o
h
e
a
l
t
h
y
1
.
0
0
1
.
0
0
1
.
0
0
1
6
0
Ov
e
r
a
l
l
a
c
c
u
r
a
c
y
0
.
9
7
1
2
7
8
M
a
c
r
o
a
v
e
r
a
g
e
0
.
9
8
0
.
9
7
0
.
9
7
12
78
We
i
g
h
t
e
d
a
v
e
r
a
g
e
0
.
9
8
0
.
9
7
0.
97
1
2
7
8
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.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
1
8
7
6
-
1
8
84
1880
Fig
u
r
e
2
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
t
h
e
b
aselin
e
C
NN
m
o
d
el
in
to
m
ato
leaf
d
is
ea
s
e
class
if
ic
atio
n
.
T
h
e
d
iag
o
n
al
v
alu
es c
o
r
r
esp
o
n
d
t
o
co
r
r
ec
tly
p
r
ed
icted
s
am
p
les,
w
h
er
ea
s
th
e
o
f
f
-
d
iag
o
n
al
v
alu
es
r
ep
r
esen
t
m
is
class
if
icatio
n
s
,
r
ef
lectin
g
c
o
n
f
u
s
io
n
b
etwe
en
class
es with
s
im
ilar
v
is
u
al
ch
ar
ac
ter
is
tics
3
.
2
.
P
er
f
o
r
m
a
nce
o
f
t
he
ResNet
5
0
mo
del
T
h
e
R
esNet5
0
-
b
ased
tr
an
s
f
er
lear
n
in
g
m
o
d
el
was
ev
alu
ated
u
s
in
g
th
e
s
am
e
d
ataset
an
d
ex
p
er
im
en
tal
s
etu
p
to
m
ain
tain
a
co
n
s
is
ten
t
co
m
p
ar
is
o
n
.
T
h
e
m
o
d
el
ac
h
iev
ed
an
o
v
er
all
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
9
.
6
%,
in
d
icatin
g
im
p
r
o
v
ed
p
er
f
o
r
m
an
ce
o
v
er
b
aselin
e
C
NN.
As
p
r
esen
ted
in
T
ab
le
3
,
th
e
R
esNet5
0
m
o
d
el
d
em
o
n
s
tr
ates
s
tr
o
n
g
class
if
icatio
n
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
to
m
ato
leaf
ca
teg
o
r
ies.
Mo
s
t
p
r
ed
ictio
n
s
ar
e
h
ig
h
ly
ac
cu
r
ate,
with
p
ar
ticu
lar
ly
s
tr
o
n
g
r
esu
lts
o
b
s
er
v
ed
in
to
m
ato
b
ac
ter
ial
s
p
o
t
an
d
to
m
ato
y
ello
w
leaf
cu
r
l
v
ir
u
s
.
T
h
ese
r
esu
lts
h
ig
h
lig
h
t th
e
m
o
d
el’
s
ef
f
ec
tiv
en
ess
in
d
is
tin
g
u
is
h
in
g
b
etwe
en
v
is
u
ally
d
is
tin
ct
d
is
ea
s
e
class
es.
T
ab
le
3
.
C
lass
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
t
h
e
R
esNet5
0
m
o
d
el
o
n
th
e
t
o
m
ato
leaf
d
is
ea
s
e
test
d
ataset
C
l
a
s
s
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
u
p
p
o
r
t
To
ma
t
o
b
a
c
t
e
r
i
a
l
sp
o
t
1
.
0
0
1
.
0
0
1
.
0
0
2
1
3
To
ma
t
o
_
La
t
e
_
b
l
i
g
h
t
1
.
0
0
0
.
9
9
0
.
9
9
1
9
1
To
ma
t
o
se
p
t
o
r
i
a
l
e
a
f
s
p
o
t
0
.
9
9
0
.
9
8
0
.
9
9
1
7
8
To
ma
t
o
y
e
l
l
o
w
l
e
a
f
c
u
r
l
v
i
r
u
s
1
.
0
0
1
.
0
0
1
.
0
0
5
3
6
To
ma
t
o
h
e
a
l
t
h
y
0
.
9
8
1
.
0
0
0
.
9
9
1
6
0
O
v
e
r
a
l
l
a
c
c
u
r
a
c
y
0
.
9
9
1
2
7
8
M
a
c
r
o
a
v
e
r
a
g
e
0
.
9
9
0
.
9
9
0
.
9
9
1
2
7
8
W
e
i
g
h
t
e
d
a
v
e
r
a
g
e
1
.
0
0
1
.
0
0
1
.
0
0
1
2
7
8
T
h
e
R
esNet5
0
m
o
d
el
s
h
o
ws
s
tr
o
n
g
class
if
icatio
n
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
ca
teg
o
r
ies,
with
r
esu
lts
co
n
s
is
ten
tly
clo
s
e
to
o
p
tim
al
v
alu
es.
Mo
s
t
class
es
ac
h
iev
e
n
ea
r
-
p
er
f
ec
t
p
r
ed
ictio
n
s
,
r
ef
lectin
g
th
e
m
o
d
el’
s
ab
ilit
y
to
ex
tr
ac
t
m
ea
n
in
g
f
u
l
f
ea
tu
r
es
f
r
o
m
th
e
in
p
u
t
im
ag
es.
T
h
e
r
esu
lts
also
in
d
icate
th
at
th
e
R
esNet5
0
ar
ch
itectu
r
e
p
r
o
v
id
es
r
eliab
le
an
d
co
n
s
is
ten
t
class
if
icatio
n
ac
r
o
s
s
d
if
f
er
en
t
d
is
ea
s
e
ca
teg
o
r
ies.
W
h
en
co
m
p
ar
ed
with
th
e
b
aselin
e
C
NN
m
o
d
el,
th
e
R
esNet5
0
m
o
d
el
d
eliv
er
s
m
o
r
e
s
tab
le
an
d
im
p
r
o
v
ed
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
3
.
3
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
o
f
ba
s
eline
CNN
a
nd
ResNet
5
0
A
co
m
p
ar
is
o
n
b
etwe
en
th
e
b
aselin
e
C
NN
an
d
th
e
R
esNet5
0
m
o
d
els
was
co
n
d
u
cted
u
n
d
er
id
en
tical
ex
p
er
im
en
tal
co
n
d
itio
n
s
.
T
ab
le
4
p
r
esen
ts
th
e
o
v
er
all
p
er
f
o
r
m
an
ce
o
f
b
o
th
m
o
d
els
ac
r
o
s
s
m
u
ltip
le
ev
alu
atio
n
asp
ec
ts
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
R
esNet5
0
m
o
d
el
d
eliv
er
s
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
th
e
b
aselin
e
C
NN,
r
ef
lectin
g
its
s
tr
o
n
g
er
ca
p
ab
ilit
y
in
lear
n
in
g
m
o
r
e
d
is
cr
im
in
ativ
e
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
.
T
h
is
s
tr
o
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
A
co
mp
a
r
a
tive
s
tu
d
y
o
f
b
a
s
elin
e
co
n
vo
l
u
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
a
n
d
…
(
S
u
ma
n
a
B
u
d
s
a
b
o
k
)
1881
ca
p
ab
ilit
y
is
ev
id
en
ce
d
b
y
th
e
m
in
im
al
m
is
class
if
icatio
n
s
s
h
o
wn
in
th
e
R
esNet5
0
co
n
f
u
s
io
n
m
atr
ix
,
as
d
ep
icted
in
Fig
u
r
e
3
.
T
h
e
im
p
r
o
v
em
en
t
is
p
ar
ticu
lar
ly
n
o
ticea
b
le
in
d
is
ea
s
e
class
es
with
s
im
ilar
v
is
u
al
ch
ar
ac
ter
is
tics
,
s
u
ch
as
to
m
ato
late
b
lig
h
t
an
d
to
m
ato
s
ep
to
r
ia
leaf
s
p
o
t.
W
h
ile
th
e
b
aselin
e
C
NN
s
h
o
ws
s
o
m
e
co
n
f
u
s
io
n
b
etwe
en
th
ese
class
es,
th
e
R
esNet5
0
m
o
d
el
is
ab
le
to
p
r
o
v
id
e
m
o
r
e
co
n
s
is
ten
t
an
d
ac
cu
r
ate
class
if
icatio
n
r
esu
lts
.
T
h
e
co
m
p
ar
is
o
n
p
r
esen
ted
in
T
ab
le
4
h
ig
h
lig
h
ts
th
e
o
v
er
all
p
er
f
o
r
m
an
ce
d
if
f
er
en
ce
b
etwe
en
th
e
b
aselin
e
C
NN
an
d
R
esNet5
0
m
o
d
els
o
n
th
e
to
m
ato
leaf
d
is
ea
s
e
test
d
ataset.
T
h
e
R
esNet5
0
m
o
d
el
ac
h
iev
es
h
ig
h
er
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
ev
alu
atio
n
asp
ec
ts
,
r
ef
lectin
g
its
s
tr
o
n
g
er
ca
p
ab
ilit
y
in
ca
p
tu
r
in
g
co
m
p
lex
v
is
u
al
f
ea
tu
r
es th
r
o
u
g
h
d
ee
p
r
esid
u
al
lear
n
in
g
.
T
ab
le
4
.
C
o
m
p
a
r
ativ
e
p
er
f
o
r
m
an
ce
o
f
b
aselin
e
C
NN
an
d
R
es
Net5
0
m
o
d
els
M
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
(
a
v
g
)
R
e
c
a
l
l
(
a
v
g
)
F1
-
sc
o
r
e
(
a
v
g
)
B
a
sel
i
n
e
C
N
N
0
.
9
7
0
.
9
8
0
.
9
7
0
.
9
7
R
e
sN
e
t
5
0
0
.
9
9
0
.
9
9
0
.
9
9
0
.
9
9
Fig
u
r
e
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
R
esNet5
0
m
o
d
el
f
o
r
to
m
at
o
leaf
d
is
ea
s
e
class
if
icatio
n
.
T
h
e
m
atr
ix
s
h
o
ws
f
ewe
r
m
is
class
if
icatio
n
s
co
m
p
ar
ed
to
b
aselin
e
C
NN,
in
d
icati
n
g
im
p
r
o
v
ed
d
is
cr
im
in
ativ
e
ca
p
ab
ilit
y
an
d
b
etter
g
en
er
aliza
tio
n
to
u
n
s
ee
n
d
ata
3
.
4
.
Dis
cus
s
io
n
T
h
e
p
er
f
o
r
m
an
ce
o
f
b
o
th
th
e
b
aselin
e
C
NN
an
d
R
esNet5
0
m
o
d
els
was
an
aly
ze
d
u
s
in
g
m
u
ltip
le
ev
alu
atio
n
m
etr
ics
to
o
b
tain
a
co
m
p
r
eh
en
s
iv
e
u
n
d
er
s
tan
d
in
g
o
f
th
eir
ef
f
ec
tiv
en
ess
.
T
h
e
an
aly
s
is
was
co
n
d
u
cted
b
ased
o
n
th
e
to
m
ato
leaf
d
is
ea
s
e
test
d
ataset.
T
h
e
r
esu
lts
o
f
th
e
b
aselin
e
C
NN
m
o
d
el
in
d
icate
an
o
v
er
all
class
if
icatio
n
ac
cu
r
ac
y
o
f
0
.
9
7
,
with
s
tr
o
n
g
p
er
f
o
r
m
an
ce
o
b
s
er
v
ed
ac
r
o
s
s
m
o
s
t
class
es.
Ho
wev
er
,
s
o
m
e
m
is
class
if
icatio
n
s
o
cc
u
r
,
p
ar
ticu
lar
ly
in
d
is
ea
s
e
ca
teg
o
r
ies
with
s
im
ilar
v
is
u
al
ch
ar
ac
ter
is
tics
,
s
u
ch
as
to
m
ato
s
ep
to
r
ia
leaf
s
p
o
t
an
d
to
m
ato
late
b
lig
h
t.
I
n
co
m
p
ar
is
o
n
,
th
e
R
esNet5
0
m
o
d
el
d
em
o
n
s
tr
ates
h
ig
h
er
o
v
er
all
class
if
icatio
n
ac
cu
r
ac
y
an
d
m
o
r
e
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
class
es.
T
h
e
im
p
r
o
v
ed
r
esu
lts
s
u
g
g
est
th
at
th
e
R
esNet5
0
m
o
d
el
is
m
o
r
e
ef
f
ec
tiv
e
in
ca
p
tu
r
in
g
co
m
p
lex
v
is
u
al
f
ea
tu
r
es,
lead
in
g
to
m
o
r
e
r
eliab
le
class
if
icatio
n
o
u
tco
m
es.
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.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
1
8
7
6
-
1
8
84
1882
T
h
e
co
n
f
u
s
io
n
m
atr
ices
in
Fig
u
r
e
2
p
r
o
v
id
e
ad
d
itio
n
al
in
s
ig
h
t
in
to
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
b
o
th
m
o
d
els.
B
aselin
e
C
NN
s
h
o
ws
m
in
o
r
co
n
f
u
s
io
n
b
etwe
en
v
is
u
ally
s
im
ilar
d
is
ea
s
e
class
es,
wh
ile
th
e
R
esNet5
0
m
o
d
el
d
em
o
n
s
tr
ates
f
ewe
r
m
is
class
if
icatio
n
s
,
with
m
o
s
t
p
r
ed
ictio
n
s
co
r
r
ec
tly
alig
n
ed
alo
n
g
th
e
d
iag
o
n
al.
T
ab
le
4
s
u
m
m
ar
izes
th
e
o
v
er
all
p
er
f
o
r
m
an
ce
co
m
p
ar
is
o
n
b
etwe
en
th
e
two
m
o
d
els.
T
h
e
R
esNet5
0
m
o
d
el
co
n
s
is
ten
tly
ac
h
iev
es
h
ig
h
er
class
if
icatio
n
p
er
f
o
r
m
an
ce
th
an
th
e
b
aselin
e
C
NN
ac
r
o
s
s
all
ev
alu
atio
n
m
etr
ics.
T
h
ese
r
esu
lts
in
d
icate
th
at
in
teg
r
atin
g
tr
an
s
f
er
lear
n
in
g
with
d
ee
p
r
esid
u
al
n
etwo
r
k
s
en
h
an
ce
s
th
e
m
o
d
el’
s
ca
p
ab
ilit
y
to
ca
p
tu
r
e
m
o
r
e
co
m
p
lex
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
.
Ov
er
all,
th
e
ex
p
er
im
en
tal
f
in
d
in
g
s
co
n
f
ir
m
th
at
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
d
eliv
er
s
r
eliab
le
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
ev
alu
atio
n
cr
iter
ia.
T
h
e
m
o
d
el
ef
f
ec
tiv
ely
ex
tr
ac
ts
m
ea
n
in
g
f
u
l
f
ea
tu
r
es,
en
ab
lin
g
im
p
r
o
v
ed
d
if
f
er
en
tiatio
n
b
etwe
en
d
is
ea
s
e
class
es.
I
n
ad
d
itio
n
,
co
n
s
is
ten
t
r
esu
lts
ac
r
o
s
s
ev
alu
atio
n
s
h
ig
h
lig
h
t
its
p
o
ten
tial f
o
r
p
r
ac
tical
ap
p
licatio
n
s
in
p
lan
t d
is
ea
s
e
class
if
icatio
n
task
s
.
T
h
e
im
p
r
o
v
ed
p
er
f
o
r
m
an
ce
o
f
th
e
R
esNet5
0
m
o
d
el
ca
n
b
e
attr
ib
u
ted
to
its
d
ee
p
ar
ch
itectu
r
e
an
d
th
e
u
s
e
o
f
p
r
e
-
tr
ain
ed
weig
h
ts
f
r
o
m
th
e
I
m
ag
eNe
t
d
ataset.
T
h
is
en
ab
les
th
e
m
o
d
el
to
lear
n
m
o
r
e
r
ep
r
esen
tativ
e
an
d
h
ier
ar
ch
ical
f
ea
tu
r
es,
in
clu
d
in
g
s
u
b
tle
v
ar
iatio
n
s
in
tex
tu
r
e,
co
lo
r
d
is
tr
ib
u
tio
n
,
an
d
lesi
o
n
p
atter
n
s
,
wh
ich
ar
e
im
p
o
r
tan
t
f
o
r
d
is
tin
g
u
is
h
in
g
b
etwe
en
d
if
f
er
en
t
p
lan
t
d
is
ea
s
es.
Alth
o
u
g
h
th
e
m
o
d
el
ac
h
iev
es
h
ig
h
o
v
er
all
p
er
f
o
r
m
an
ce
,
m
in
o
r
m
is
class
if
icatio
n
s
ar
e
s
till
o
b
s
er
v
ed
,
p
ar
ticu
lar
ly
b
etwe
en
v
is
u
ally
s
im
ilar
class
es
s
u
ch
as
to
m
ato
s
ep
to
r
ia
leaf
s
p
o
t
an
d
to
m
ato
late
b
lig
h
t.
T
h
ese
class
es
s
h
ar
e
o
v
er
lap
p
in
g
v
is
u
al
ch
ar
ac
ter
is
tics
,
in
clu
d
in
g
ir
r
eg
u
lar
d
ar
k
lesi
o
n
s
an
d
s
im
ilar
tex
tu
r
e
p
atter
n
s
,
wh
ich
ca
n
m
ak
e
class
if
icatio
n
ch
allen
g
in
g
ev
en
f
o
r
d
ee
p
lear
n
in
g
m
o
d
els.
T
h
is
o
b
s
er
v
atio
n
em
p
h
asizes
th
e
im
p
o
r
tan
ce
o
f
f
ea
tu
r
e
r
ep
r
esen
tatio
n
in
h
an
d
lin
g
in
ter
-
class
s
im
ilar
ity
.
I
n
co
n
tr
ast,
th
e
b
aselin
e
C
NN
m
o
d
el,
alth
o
u
g
h
co
m
p
u
tatio
n
ally
ef
f
icien
t,
s
h
o
ws
r
elativ
ely
lo
wer
p
er
f
o
r
m
an
ce
,
wh
ich
ca
n
b
e
attr
ib
u
ted
to
its
lim
ited
d
ep
th
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
ca
p
ab
ilit
y
.
T
h
e
m
o
d
el
ten
d
s
to
ca
p
tu
r
e
b
asic
v
is
u
al
p
atter
n
s
s
u
ch
as
ed
g
es
an
d
s
im
p
le
tex
tu
r
es,
wh
ich
m
ay
n
o
t
b
e
s
u
f
f
icien
t
f
o
r
d
is
tin
g
u
is
h
in
g
m
o
r
e
co
m
p
lex
d
is
ea
s
e
ch
ar
ac
ter
is
tics
,
r
esu
ltin
g
in
co
n
f
u
s
io
n
b
etwe
en
v
is
u
ally
s
im
ilar
class
es.
T
h
e
n
ea
r
-
p
er
f
ec
t
ac
cu
r
ac
y
ac
h
iev
ed
b
y
th
e
R
esNet5
0
m
o
d
el
in
d
icate
s
th
at
th
e
d
ataset
is
well
-
s
tr
u
ctu
r
ed
an
d
co
n
tain
s
clea
r
v
is
u
al
d
is
tin
ctio
n
s
am
o
n
g
class
es.
Ho
wev
er
,
th
is
m
ay
also
r
aise
co
n
ce
r
n
s
r
eg
ar
d
in
g
th
e
m
o
d
el’
s
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
in
r
ea
l
-
wo
r
ld
co
n
d
itio
n
s
,
wh
er
e
im
ag
es
ca
n
b
e
in
f
lu
en
ce
d
b
y
v
ar
y
in
g
lig
h
tin
g
,
b
ac
k
g
r
o
u
n
d
s
,
an
d
n
o
is
e.
T
h
er
ef
o
r
e,
f
u
r
th
er
ev
alu
atio
n
u
s
in
g
m
o
r
e
d
iv
er
s
e
an
d
r
ea
lis
tic
d
atasets
is
n
ec
ess
ar
y
to
b
etter
ass
ess
th
e
r
o
b
u
s
tn
ess
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
Fu
tu
r
e
s
tu
d
ies
m
ay
co
n
s
id
er
em
p
lo
y
in
g
m
o
r
e
ad
v
an
ce
d
v
alid
atio
n
s
tr
ateg
ies,
s
u
ch
as
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
,
to
en
h
an
ce
th
e
r
eliab
ilit
y
an
d
r
o
b
u
s
tn
ess
o
f
th
e
r
esu
lts
.
T
h
is
m
eth
o
d
en
ab
les
th
e
d
ataset
to
b
e
p
ar
titi
o
n
ed
in
to
m
u
ltip
le
s
u
b
s
ets,
allo
win
g
all
s
am
p
les
to
b
e
ef
f
ec
tiv
ely
u
tili
ze
d
d
u
r
in
g
b
o
th
tr
ain
in
g
an
d
v
alid
atio
n
.
Ad
d
itio
n
ally
,
in
ter
p
r
etab
ilit
y
tech
n
iq
u
es,
s
u
ch
as
g
r
ad
ien
t
-
weig
h
ted
class
ac
tiv
atio
n
m
ap
p
in
g
(
Gr
ad
-
C
AM
)
,
ca
n
b
e
u
tili
ze
d
to
id
en
tify
im
p
o
r
tan
t
r
eg
io
n
s
th
at
in
f
lu
en
ce
th
e
m
o
d
el’
s
p
r
ed
ictio
n
s
.
T
h
is
im
p
r
o
v
es m
o
d
el
tr
an
s
p
ar
en
cy
an
d
s
u
p
p
o
r
ts
its
p
r
ac
tical
u
s
e
in
r
ea
l
-
wo
r
ld
ag
r
icu
ltu
r
al
ap
p
licatio
n
s
.
4.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
T
h
is
s
tu
d
y
in
v
esti
g
ates
th
e
p
er
f
o
r
m
an
ce
o
f
a
b
aselin
e
C
NN
an
d
a
R
esNet5
0
-
b
ased
tr
an
s
f
er
lear
n
in
g
m
o
d
el
f
o
r
to
m
ato
leaf
d
is
ea
s
e
class
if
icatio
n
u
s
in
g
th
e
s
am
e
ex
p
er
im
en
tal
s
etu
p
.
B
aselin
e
C
NN
ac
h
iev
ed
an
o
v
er
all
ac
cu
r
ac
y
o
f
9
7
.
0
%,
in
d
icatin
g
its
ca
p
ab
ilit
y
to
ex
tr
ac
t
ess
en
tial
v
is
u
al
f
ea
tu
r
es.
B
y
co
m
p
ar
is
o
n
,
th
e
R
esNet5
0
m
o
d
el
r
ea
ch
ed
an
ac
cu
r
ac
y
o
f
9
9
.
6
%,
co
r
r
esp
o
n
d
in
g
to
an
im
p
r
o
v
em
en
t
o
f
ap
p
r
o
x
im
ately
2
.
6
%.
T
h
e
ad
v
an
tag
e
o
f
th
e
R
esNet5
0
m
o
d
el
is
p
ar
ticu
lar
ly
n
o
ticea
b
le
in
v
is
u
ally
s
im
ilar
d
is
ea
s
e
ca
teg
o
r
ies,
wh
er
e
it
p
r
o
d
u
ce
s
m
o
r
e
co
n
s
is
ten
t
p
r
ed
ictio
n
s
co
m
p
ar
ed
to
th
e
b
aselin
e
C
NN,
wh
ich
s
h
o
ws
o
cc
asio
n
al
m
is
class
if
icatio
n
.
Ov
er
all,
th
e
f
in
d
in
g
s
s
h
o
w
th
at
co
m
b
in
in
g
d
ee
p
r
esid
u
al
lear
n
in
g
with
tr
an
s
f
er
lear
n
in
g
im
p
r
o
v
es
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
e
R
esNet
50
m
o
d
el
is
well
s
u
ited
f
o
r
p
r
ac
tical
ag
r
icu
ltu
r
al
ap
p
licatio
n
s
,
as
it
p
r
o
v
id
es
s
tab
le
an
d
co
n
s
is
ten
t
p
r
ed
ictio
n
r
esu
lts
,
esp
ec
ially
in
m
o
r
e
co
m
p
lex
class
if
icatio
n
task
s
.
Alth
o
u
g
h
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
s
h
o
ws
s
tr
o
n
g
p
er
f
o
r
m
an
ce
,
s
o
m
e
lim
itatio
n
s
s
h
o
u
ld
b
e
co
n
s
id
er
ed
.
T
h
e
ex
p
er
im
en
ts
wer
e
co
n
d
u
cted
u
s
in
g
a
s
in
g
le
d
ataset
u
n
d
er
co
n
tr
o
lled
co
n
d
itio
n
s
,
wh
ich
m
ay
n
o
t
f
u
lly
r
ep
r
esen
t
r
ea
l
-
wo
r
ld
ag
r
icu
ltu
r
al
en
v
ir
o
n
m
en
ts
.
I
n
p
r
ac
tice,
f
ac
to
r
s
s
u
ch
as
tem
p
er
atu
r
e,
h
u
m
id
ity
,
an
d
v
ar
y
in
g
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
m
ay
af
f
ec
t m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
er
ef
o
r
e,
f
u
r
th
er
ev
alu
atio
n
u
s
in
g
m
o
r
e
d
iv
er
s
e
d
atasets
an
d
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
is
r
ec
o
m
m
en
d
ed
to
im
p
r
o
v
e
th
e
m
o
d
el’
s
g
en
er
aliza
b
ilit
y
an
d
r
o
b
u
s
tn
ess
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
is
r
esear
ch
was
co
n
d
u
cted
with
p
er
s
o
n
al
f
u
n
d
in
g
.
T
h
e
a
u
th
o
r
s
wo
u
l
d
lik
e
to
th
an
k
R
ajam
an
g
ala
Un
iv
er
s
ity
o
f
T
ec
h
n
o
lo
g
y
Su
v
ar
n
ab
h
u
m
i f
o
r
s
u
p
p
o
r
tin
g
t
h
is
r
esear
ch
.
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
A
co
mp
a
r
a
tive
s
tu
d
y
o
f
b
a
s
elin
e
co
n
vo
l
u
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
a
n
d
…
(
S
u
ma
n
a
B
u
d
s
a
b
o
k
)
1883
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
Su
m
an
a
B
u
d
s
ab
o
k
✓
✓
✓
✓
✓
✓
✓
✓
W
ac
h
ir
ap
o
r
n
Po
lp
an
u
m
as
✓
✓
✓
✓
✓
✓
✓
Piy
an
an
Kh
o
n
g
p
h
ai
✓
✓
✓
✓
✓
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
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
p
u
b
licly
av
ailab
le
in
th
e
Plan
tVilla
g
e
d
ataset,
wh
ich
ca
n
b
e
ac
ce
s
s
ed
o
n
lin
e.
RE
F
E
R
E
NC
E
S
[
1
]
K
.
P
.
F
e
r
e
n
t
i
n
o
s
,
“
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
se
a
se
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
si
s,
”
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
r
e
,
v
o
l
.
1
4
5
,
p
p
.
3
1
1
–
3
1
8
,
F
e
b
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
1
8
.
0
1
.
0
0
9
.
[
2
]
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
,
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
.
[
3
]
A
.
U
p
a
d
h
y
a
y
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
n
d
c
o
m
p
u
t
e
r
v
i
si
o
n
i
n
p
l
a
n
t
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
:
a
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
t
e
c
h
n
i
q
u
e
s
,
mo
d
e
l
s
,
a
n
d
t
r
e
n
d
s
i
n
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
R
e
v
i
e
w
,
v
o
l
.
5
8
,
n
o
.
3
,
p
.
9
2
,
Ja
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
2
4
-
1
1
1
0
0
-
x.
[
4
]
T.
N
y
a
w
o
se,
R
.
C
.
M
a
sw
a
n
g
a
n
y
i
,
a
n
d
P
.
K
h
u
m
a
l
o
,
“
A
r
e
v
i
e
w
o
n
t
h
e
d
e
t
e
c
t
i
o
n
o
f
p
l
a
n
t
d
i
s
e
a
s
e
u
si
n
g
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
a
p
p
r
o
a
c
h
e
s,
”
J
o
u
r
n
a
l
o
f
I
m
a
g
i
n
g
,
v
o
l
.
1
1
,
n
o
.
1
0
,
p
.
3
2
6
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
j
i
ma
g
i
n
g
1
1
1
0
0
3
2
6
.
[
5
]
J.
Zh
a
o
e
t
a
l
.
,
“
A
r
e
v
i
e
w
o
f
p
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
y
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
Fr
o
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
6
,
A
u
g
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
2
5
.
1
6
3
7
2
4
1
.
[
6
]
P
.
K
.
D
a
s
,
S
.
S
.
R
u
p
a
,
S
.
P
u
mr
i
n
,
U
.
C
.
D
a
s,
a
n
d
M
.
K
.
H
o
sse
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
p
l
a
n
t
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
A
sy
st
e
ma
t
i
c
a
n
a
l
y
si
s
a
n
d
r
e
v
i
e
w
,
”
C
u
rr
e
n
t
Ap
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
5
7
,
p
.
e
0
2
5
9
0
1
6
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
5
5
0
0
3
/
c
a
s
t
.
2
0
2
4
.
2
5
9
0
1
6
.
[
7
]
K
.
H
e
,
X
.
Z
h
a
n
g
,
S
.
R
e
n
,
a
n
d
J
.
S
u
n
,
“
D
e
e
p
r
e
si
d
u
a
l
l
e
a
r
n
i
n
g
f
o
r
i
ma
g
e
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
2
0
1
6
I
EEE
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
si
o
n
a
n
d
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
(
C
V
P
R)
,
Ju
n
.
2
0
1
6
,
v
o
l
.
2
0
1
6
-
D
e
c
e
m
,
p
p
.
7
7
0
–
7
7
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
6
.
9
0
.
[
8
]
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
r
e
,
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
.
[
9
]
N
.
S
a
g
a
r
e
t
a
l
.
,
“
P
r
e
c
i
s
i
o
n
d
e
t
e
c
t
i
o
n
o
f
g
r
a
p
e
v
i
n
e
d
o
w
n
y
a
n
d
p
o
w
d
e
r
y
mi
l
d
e
w
d
i
s
e
a
s
e
d
l
e
a
v
e
s
a
n
d
f
r
u
i
t
s
u
si
n
g
e
n
h
a
n
c
e
d
R
e
sN
e
t
5
0
w
i
t
h
b
a
t
c
h
n
o
r
ma
l
i
z
a
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
r
o
n
i
c
s
i
n
Ag
r
i
c
u
l
t
u
re
,
v
o
l
.
2
3
2
,
p
.
1
1
1
4
0
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
5
.
1
1
0
1
4
4
.
[
1
0
]
J.
L
i
a
n
g
a
n
d
W
.
Ji
a
n
g
,
“
A
R
e
sN
e
t
5
0
-
D
P
A
mo
d
e
l
f
o
r
t
o
m
a
t
o
l
e
a
f
d
i
sea
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
Fr
o
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s
.
2
0
2
3
.
1
2
5
8
6
5
8
.
[
1
1
]
W
.
S
h
a
f
i
k
,
A
.
T
u
f
a
i
l
,
C
.
D
e
S
i
l
v
a
L
i
y
a
n
a
g
e
,
a
n
d
R
.
A
.
A
.
H
.
M
.
A
p
o
n
g
,
“
U
si
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
-
b
a
s
e
d
p
l
a
n
t
d
i
se
a
s
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
f
o
r
s
u
s
t
a
i
n
a
b
l
e
a
g
r
i
c
u
l
t
u
r
e
,
”
B
M
C
P
l
a
n
t
B
i
o
l
o
g
y
,
v
o
l
.
2
4
,
n
o
.
1
,
p
.
1
3
6
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
8
7
0
-
024
-
04825
-
y.
[
1
2
]
S
.
G
.
P
a
u
l
e
t
a
l
.
,
“
A
r
e
a
l
-
t
i
me
a
p
p
l
i
c
a
t
i
o
n
-
b
a
se
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
a
p
p
r
o
a
c
h
f
o
r
t
o
ma
t
o
l
e
a
f
d
i
sea
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Arra
y
,
v
o
l
.
1
9
,
p
.
1
0
0
3
1
3
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
r
a
y
.
2
0
2
3
.
1
0
0
3
1
3
.
[
1
3
]
M
.
M
u
sl
i
h
a
n
d
A
.
D
.
K
r
i
smaw
a
n
,
“
T
o
ma
t
o
l
e
a
f
d
i
s
e
a
ses
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
w
i
t
h
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
R
e
s
n
e
t
-
5
0
,
”
K
i
n
e
t
i
k
:
G
a
m
e
T
e
c
h
n
o
l
o
g
y
,
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
,
C
o
m
p
u
t
e
r
N
e
t
w
o
r
k
,
C
o
m
p
u
t
i
n
g
,
El
e
c
t
ro
n
i
c
s,
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
4
9
–
1
5
8
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
2
2
2
1
9
/
k
i
n
e
t
i
k
.
v
9
i
2
.
1
9
3
9
.
[
1
4
]
M
.
S
.
A
.
M
.
A
l
-
G
a
a
sh
a
n
i
e
t
a
l
.
,
“
D
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
w
i
t
h
g
r
a
v
i
t
a
t
i
o
n
a
l
s
e
a
r
c
h
a
l
g
o
r
i
t
h
m
f
o
r
e
n
h
a
n
c
e
d
p
l
a
n
t
d
i
sea
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
7
,
p
.
e
2
8
9
6
7
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
2
8
9
6
7
.
[
1
5
]
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
ma
g
e
c
l
a
s
si
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
ro
s
c
i
e
n
c
e
,
v
o
l
.
2
0
1
6
,
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
.
[
1
6
]
J.
S
h
a
r
m
a
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
e
n
sem
b
l
e
m
o
d
e
l
f
o
r
a
c
c
u
r
a
t
e
t
o
m
a
t
o
l
e
a
f
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
b
y
l
e
v
e
r
a
g
i
n
g
R
e
sN
e
t
5
0
a
n
d
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.
1
6
,
No
.
4
,
Au
g
u
s
t
20
2
6
:
1
8
7
6
-
1
8
84
1884
M
o
b
i
l
e
N
e
t
V
2
a
r
c
h
i
t
e
c
t
u
r
e
s
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
1
3
9
0
4
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
9
8
0
1
5
-
x.
[
1
7
]
J.
G
.
A
.
B
a
r
b
e
d
o
,
“
A
r
e
v
i
e
w
o
n
t
h
e
mai
n
c
h
a
l
l
e
n
g
e
s
i
n
a
u
t
o
m
a
t
i
c
p
l
a
n
t
d
i
sea
s
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
a
se
d
o
n
v
i
si
b
l
e
r
a
n
g
e
i
ma
g
e
s
,
”
Bi
o
s
y
st
e
m
s E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
4
4
,
p
p
.
5
2
–
6
0
,
A
p
r
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
s
y
st
e
mse
n
g
.
2
0
1
6
.
0
1
.
0
1
7
.
[
1
8
]
B
.
S
a
m
b
a
n
a
e
t
a
l
.
,
“
A
n
e
f
f
i
c
i
e
n
t
p
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
u
si
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
1
9
0
8
2
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
025
-
0
2
2
7
1
-
w.
[
1
9
]
J.
G
.
A
.
B
a
r
b
e
d
o
,
“
I
mp
a
c
t
o
f
d
a
t
a
s
e
t
si
z
e
a
n
d
v
a
r
i
e
t
y
o
n
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
p
l
a
n
t
d
i
s
e
a
s
e
c
l
a
ss
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
r
e
,
v
o
l
.
1
5
3
,
p
p
.
4
6
–
5
3
,
O
c
t
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
1
8
.
0
8
.
0
1
3
.
[
2
0
]
M
.
R
.
A
.
R
a
s
h
i
d
e
t
a
l
.
,
“
A
n
e
n
sem
b
l
e
l
e
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
w
i
t
h
e
x
p
l
a
i
n
a
b
l
e
A
I
f
o
r
p
l
a
n
t
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
,
”
Arra
y
,
v
o
l
.
2
6
,
p
.
1
0
0
3
8
6
,
J
u
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
r
a
y
.
2
0
2
5
.
1
0
0
3
8
6
.
[
2
1
]
M
.
B
.
Y
i
l
d
i
z
,
M
.
F
.
H
a
f
i
f
,
E.
K
.
K
o
k
s
o
y
,
a
n
d
R
.
K
u
r
su
n
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
d
i
s
e
a
se
s
i
n
t
o
m
a
t
o
l
e
a
v
e
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
met
h
o
d
s,
”
I
n
t
e
l
l
i
g
e
n
t
Me
t
h
o
d
s I
n
E
n
g
i
n
e
e
ri
n
g
S
c
i
e
n
c
e
s
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
2
2
–
3
6
,
2
0
2
4
,
d
o
i
:
1
0
.
5
8
1
9
0
/
i
mi
e
n
s
.
2
0
2
4
.
8
4
.
[
2
2
]
A
.
K
r
i
z
h
e
v
s
k
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
ssi
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
,
”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
o
f
t
h
e
A
C
M
,
v
o
l
.
6
0
,
n
o
.
6
,
p
p
.
8
4
–
9
0
,
M
a
y
2
0
1
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
0
6
5
3
8
6
.
[
2
3
]
Y
.
Le
C
u
n
,
Y
.
B
e
n
g
i
o
,
a
n
d
G
.
H
i
n
t
o
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
,
”
N
a
t
u
re
,
v
o
l
.
5
2
1
,
n
o
.
7
5
5
3
,
p
p
.
4
3
6
–
4
4
4
,
M
a
y
2
0
1
5
,
d
o
i
:
1
0
.
1
0
3
8
/
n
a
t
u
r
e
1
4
5
3
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
u
m
a
n
a
B
u
d
sa
b
o
k
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
i
n
fo
rm
a
ti
o
n
sy
ste
m
s
a
n
d
m
a
ste
r’s
d
e
g
re
e
in
e
d
u
c
a
ti
o
n
a
l
tec
h
n
o
l
o
g
y
.
S
h
e
is
c
u
rre
n
tl
y
p
u
rsu
in
g
a
P
h
.
D
.
in
e
n
g
in
e
e
rin
g
a
n
d
tec
h
n
o
lo
g
y
m
a
n
a
g
e
m
e
n
t
a
t
Ra
jam
a
n
g
a
la
Un
iv
e
rsity
o
f
Tec
h
n
o
l
o
g
y
Kru
n
g
t
h
e
p
,
T
h
a
il
a
n
d
.
S
h
e
is
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
th
e
F
a
c
u
lt
y
o
f
Bu
si
n
e
ss
Ad
m
i
n
istratio
n
a
n
d
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
Ra
jam
a
n
g
a
la
Un
i
v
e
rsity
o
f
Tec
h
n
o
lo
g
y
S
u
v
a
rn
a
b
h
u
m
i.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
e
e
p
lea
rn
in
g
,
c
o
m
p
u
ter
v
isi
o
n
,
a
n
d
AI
a
p
p
l
ica
ti
o
n
s
i
n
a
g
ric
u
lt
u
re
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
m
a
n
a
.
p
@rm
u
tsb
.
a
c
.
t
h
.
Wa
c
h
ira
p
o
r
n
Po
l
p
a
n
u
m
a
s
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
th
e
F
a
c
u
lt
y
o
f
Bu
si
n
e
s
s
Ad
m
in
istratio
n
a
n
d
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
Ra
jam
a
n
g
a
la
Un
iv
e
rsity
o
f
Tec
h
n
o
l
o
g
y
S
u
v
a
r
n
a
b
h
u
m
i,
T
h
a
il
a
n
d
.
S
h
e
sp
e
c
ialize
s
in
in
fo
rm
a
ti
o
n
sy
ste
m
s
a
n
d
d
ig
it
a
l
in
n
o
v
a
ti
o
n
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
i
n
fo
r
m
a
ti
o
n
s
y
ste
m
s,
d
a
ta
a
n
a
ly
ti
c
s,
b
i
g
d
a
ta
a
n
a
ly
ti
c
s,
a
n
d
a
p
p
li
e
d
a
rti
ficia
l
in
telli
g
e
n
c
e
.
S
h
e
is
c
u
rre
n
tl
y
i
n
v
o
lv
e
d
in
re
se
a
rc
h
o
n
imm
e
rsiv
e
tec
h
n
o
lo
g
y
t
o
su
p
p
o
rt
t
o
u
rism
p
r
o
m
o
ti
o
n
i
n
h
is
to
rica
l
h
e
rit
a
g
e
sites
in
P
h
ra
Na
k
h
o
n
S
i
Ay
u
tt
h
a
y
a
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
wa
c
h
ira.
p
@rm
u
tsb
.
a
c
.
th
.
Pi
y
a
n
a
n
K
h
o
n
g
p
h
a
i
is
a
lec
t
u
re
r
a
t
t
h
e
F
a
c
u
lt
y
o
f
Bu
si
n
e
ss
A
d
m
in
istratio
n
a
n
d
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
Ra
jam
a
n
g
a
la
Un
i
v
e
rsity
o
f
Tec
h
n
o
l
o
g
y
S
u
v
a
rn
a
b
h
u
m
i
,
Th
a
il
a
n
d
.
S
h
e
h
o
l
d
s
a
d
o
c
t
o
ra
l
d
e
g
re
e
a
n
d
h
e
r
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
i
n
fo
rm
a
ti
o
n
s
y
ste
m
s
a
n
d
d
i
g
it
a
l
tec
h
n
o
l
o
g
y
a
p
p
li
c
a
ti
o
n
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
iy
a
n
a
n
.
k
@rm
u
tsb
.
a
c
.
th
.
Evaluation Warning : The document was created with Spire.PDF for Python.