I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
3
3
1
8
~
3
3
2
5
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
4
.
p
p
3
3
1
8
-
3
3
2
5
3318
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Andro
id
-
ba
sed
to
ma
to lea
f
disea
se
cla
ss
ificatio
n usin
g
a
lig
htweight Mo
bil
eNet
V2
co
nv
o
lutiona
l neural net
wo
rk
Andi
Ria
n
s
y
a
h
1
,
I
rf
a
n E
k
a
M
a
hd
y
1
,
M
o
cha
m
a
d Abdu
l
B
a
s
ir
2
,
No
o
rm
ins
ha
h A.
I
a
h
a
d
3
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
I
n
d
u
st
r
i
a
l
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
a
s
I
sl
a
m Su
l
t
a
n
A
g
u
n
g
,
S
e
m
a
r
a
n
g
,
I
n
d
o
n
e
si
a
2
M
a
t
h
e
ma
t
i
c
s E
d
u
c
a
t
i
o
n
S
t
u
d
y
P
r
o
g
r
a
m,
F
a
c
u
l
t
y
o
f
T
e
a
c
h
e
r
Tr
a
i
n
i
n
g
a
n
d
E
d
u
c
a
t
i
o
n
,
U
n
i
v
e
r
si
t
a
s
I
sl
a
m S
u
l
t
a
n
A
g
u
n
g
,
S
e
mara
n
g
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
me
n
t
o
f
A
p
p
l
i
e
d
C
o
m
p
u
t
i
n
g
a
n
d
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
i
n
g
,
U
n
i
v
e
r
si
t
i
Te
k
n
o
l
o
g
i
M
a
l
a
y
s
i
a
,
Jo
h
o
r
B
a
h
r
u
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
25
,
2
0
2
5
R
ev
is
ed
J
u
n
5
,
2
0
2
6
Acc
ep
ted
J
u
l
9
,
2
0
2
6
Early
sc
re
e
n
in
g
o
f
to
m
a
to
le
a
f
d
ise
a
se
s
is
i
m
p
o
rtan
t
b
e
c
a
u
se
fo
li
a
r
sy
m
p
to
m
s
c
a
n
re
d
u
c
e
p
lan
t
v
i
g
o
r
a
n
d
d
e
lay
a
p
p
r
o
p
r
iate
c
ro
p
m
a
n
a
g
e
m
e
n
t.
Th
is
stu
d
y
d
e
v
e
lo
p
s
a
n
An
d
ro
i
d
-
b
a
se
d
to
m
a
to
lea
f
d
ise
a
se
c
la
ss
ifi
c
a
ti
o
n
sy
ste
m
u
sin
g
M
o
b
il
e
Ne
tV2
a
s
a
li
g
h
twe
ig
h
t
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(CNN
)
a
rc
h
it
e
c
tu
re
.
Th
e
c
o
n
tri
b
u
ti
o
n
o
f
th
is wo
r
k
is t
h
e
i
n
teg
ra
ti
o
n
o
f
m
o
d
e
l
train
in
g
,
in
d
e
p
e
n
d
e
n
t
tes
ti
n
g
,
a
n
d
o
n
-
d
e
v
ice
An
d
ro
i
d
d
e
p
l
o
y
m
e
n
t
th
a
t
su
p
p
o
rts
c
a
m
e
ra
a
n
d
g
a
ll
e
ry
in
p
u
ts
with
o
u
t
re
ly
in
g
o
n
se
rv
e
r
-
sid
e
c
o
m
p
u
tati
o
n
.
Th
e
d
a
tas
e
t
c
o
n
sist
e
d
o
f
1
,
2
0
0
b
a
lan
c
e
d
to
m
a
to
lea
f
ima
g
e
s
fro
m
fiv
e
c
las
se
s:
b
a
c
teria
l
sp
o
t,
late
b
li
g
h
t,
targ
e
t
sp
o
t,
t
o
m
a
to
y
e
ll
o
w
lea
f
c
u
rl
v
iru
s,
a
n
d
h
e
a
lt
h
y
lea
f.
Im
a
g
e
s
we
re
re
siz
e
d
,
n
o
rm
a
li
z
e
d
,
a
u
g
m
e
n
ted
fo
r
train
in
g
,
a
n
d
d
i
v
id
e
d
in
t
o
trai
n
in
g
,
v
a
li
d
a
ti
o
n
,
a
n
d
in
d
e
p
e
n
d
e
n
t
tes
ti
n
g
su
b
se
ts.
T
h
e
m
o
d
e
l
o
b
tain
e
d
9
4
.
1
2
%
train
in
g
a
c
c
u
ra
c
y
,
9
3
.
0
0
%
v
a
li
d
a
ti
o
n
a
c
c
u
ra
c
y
,
a
n
d
8
9
.
0
0
%
in
d
e
p
e
n
d
e
n
t
tes
t
a
c
c
u
ra
c
y
.
Th
e
c
o
n
fu
si
o
n
m
a
tri
x
sh
o
we
d
t
h
a
t
to
m
a
to
y
e
ll
o
w
lea
f
c
u
rl
v
ir
u
s
wa
s
c
las
sified
with
o
u
t
e
rro
r
,
wh
e
re
a
s
b
a
c
teria
l
sp
o
t,
late
b
li
g
h
t,
targ
e
t
s
p
o
t
,
a
n
d
h
e
a
lt
h
y
lea
v
e
s
p
ro
d
u
c
e
d
se
v
e
ra
l
m
isc
las
sific
a
ti
o
n
s
b
e
c
a
u
se
o
f
sim
il
a
r
les
io
n
a
n
d
d
is
c
o
lo
ra
ti
o
n
p
a
tt
e
rn
s.
T
h
e
re
su
lt
s
sh
o
w
th
a
t
M
o
b
il
e
Ne
tV2
is
su
it
a
b
le
fo
r
li
g
h
twe
ig
h
t
m
o
b
il
e
d
ise
a
se
sc
re
e
n
in
g
,
a
lt
h
o
u
g
h
larg
e
r
f
ield
d
a
tas
e
ts,
c
ro
ss
-
v
a
li
d
a
ti
o
n
,
m
o
d
e
l
c
o
m
p
a
ris
o
n
,
a
n
d
e
x
p
lai
n
a
b
il
it
y
a
n
a
l
y
sis
a
re
sti
ll
n
e
e
d
e
d
f
o
r
b
ro
a
d
e
r
d
e
p
lo
y
m
e
n
t.
K
ey
w
o
r
d
s
:
An
d
r
o
id
a
p
p
licatio
n
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Mo
b
ileNetV2
Plan
t d
is
ea
s
e
clas
s
if
icatio
n
T
o
m
ato
leaf
d
is
ea
s
e
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
:
An
d
i Ri
an
s
y
ah
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics E
n
g
in
ee
r
in
g
,
Facu
lty
o
f
I
n
d
u
s
tr
ial
T
ec
h
n
o
lo
g
y
,
Un
i
v
er
s
itas
I
s
lam
Su
ltan
Ag
u
n
g
St.
R
ay
a
Kalig
awe
Km
.
4
,
Sem
ar
an
g
5
0
1
1
2
,
I
n
d
o
n
esia
E
m
ail:
an
d
i@
u
n
is
s
u
la.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
o
m
ato
h
as
s
tr
ateg
ic
v
alu
e
as
a
h
o
r
ticu
ltu
r
al
cr
o
p
b
ec
a
u
s
e
it
is
co
n
s
u
m
ed
f
r
esh
,
p
r
o
ce
s
s
ed
in
to
f
o
o
d
p
r
o
d
u
cts,
an
d
cu
ltiv
ated
wid
ely
in
m
an
y
a
g
r
icu
ltu
r
al
a
r
ea
s
.
I
n
d
o
n
esian
p
r
o
d
u
ctio
n
d
at
a
s
h
o
w
th
at
to
m
ato
f
ar
m
in
g
c
o
v
er
e
d
ap
p
r
o
x
im
ate
ly
6
3
,
3
6
9
h
ec
tar
es
an
d
p
r
o
d
u
ce
d
ab
o
u
t
1
,
1
6
8
,
7
4
4
t
o
n
s
in
2
0
2
2
[
1
]
–
[
3
]
.
T
h
is
p
r
o
d
u
ctio
n
p
o
ten
tial
n
ee
d
s
t
o
b
e
p
r
o
tecte
d
b
ec
au
s
e
co
n
s
u
m
er
d
em
a
n
d
co
n
tin
u
es
to
g
r
o
w,
wh
ile
leaf
d
is
ea
s
es
ca
n
r
e
d
u
ce
p
h
o
to
s
y
n
th
etic
ca
p
ac
ity
,
wea
k
en
p
la
n
t
d
e
v
elo
p
m
en
t,
an
d
lo
we
r
h
ar
v
est
q
u
ality
.
B
ac
ter
ial,
f
u
n
g
al,
an
d
v
ir
al
s
y
m
p
to
m
s
o
n
lea
v
es
o
f
ten
ap
p
ea
r
b
ef
o
r
e
s
ev
er
e
y
ie
ld
lo
s
s
o
cc
u
r
s
.
C
o
n
s
eq
u
en
tly
,
f
ast
an
d
ac
ce
s
s
ib
le
d
is
ea
s
e
s
cr
ee
n
in
g
h
as
b
ec
o
m
e
an
im
p
o
r
tan
t
r
e
q
u
ir
em
en
t
in
p
r
ec
is
io
n
a
g
r
icu
ltu
r
e
an
d
s
m
ar
t
cr
o
p
m
an
ag
em
en
t
[
4
]
–
[
7
]
.
T
h
e
r
esear
ch
p
r
o
b
lem
a
d
d
r
ess
ed
in
th
is
wo
r
k
is
th
e
au
t
o
m
a
tic
class
if
icat
io
n
o
f
to
m
ato
leaf
im
ag
es
in
to
d
is
ea
s
e
ca
teg
o
r
ies.
T
h
e
i
n
p
u
t
is
a
leaf
im
ag
e,
wh
ile
th
e
o
u
tp
u
t
is
o
n
e
o
f
f
iv
e
la
b
els:
b
ac
ter
ial
s
p
o
t,
late
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
d
r
o
id
-
b
a
s
ed
to
ma
to
le
a
f d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
a
lig
h
tw
eig
h
t Mo
b
ileN
etV
2
…
(
A
n
d
i R
ia
n
s
ya
h
)
3319
b
lig
h
t,
tar
g
et
s
p
o
t,
t
o
m
ato
y
ell
o
w
leaf
cu
r
l
v
ir
u
s
,
o
r
h
ea
lth
y
l
ea
f
.
T
h
ese
ca
teg
o
r
ies
ar
e
v
is
u
ally
r
ep
r
esen
ted
b
y
d
if
f
er
en
ce
s
in
lesi
o
n
s
h
ap
e,
s
p
o
t
d
is
tr
ib
u
tio
n
,
co
lo
r
d
e
g
r
ad
at
io
n
,
an
d
tex
tu
r
e
.
A
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN
)
is
ap
p
r
o
p
r
iate
f
o
r
th
is
task
b
ec
au
s
e
it
ca
n
lear
n
d
is
cr
im
in
ativ
e
v
is
u
al
p
atter
n
s
d
ir
ec
tly
f
r
o
m
im
ag
e
p
ix
els.
Mo
b
ileNetV2
was
ad
o
p
ted
as
co
r
e
m
o
d
el
b
ec
a
u
s
e
its
d
ep
th
wis
e
s
ep
ar
ab
le
c
o
n
v
o
lu
tio
n
s
an
d
in
v
e
r
te
d
r
esid
u
al
s
tr
u
ctu
r
e
r
e
d
u
ce
co
m
p
u
tatio
n
al
co
m
p
lex
ity
wh
ile
p
r
eser
v
in
g
f
ea
t
u
r
e
ex
tr
ac
tio
n
ca
p
ab
ilit
y
[
8
]
–
[
1
1
]
.
I
n
an
id
ea
l
f
ield
s
itu
atio
n
,
f
a
r
m
er
s
an
d
ex
ten
s
io
n
o
f
f
icer
s
s
h
o
u
ld
b
e
a
b
le
to
id
en
tify
lea
f
d
is
ea
s
e
s
q
u
ick
ly
,
c
o
n
s
is
ten
tly
,
an
d
n
ea
r
th
e
cu
ltiv
atio
n
s
ite.
Ho
wev
er
,
id
en
tific
atio
n
is
co
m
m
o
n
ly
b
ased
o
n
m
a
n
u
al
o
b
s
er
v
atio
n
,
wh
ic
h
is
in
f
lu
en
ce
d
b
y
ex
p
er
ien
ce
,
im
a
g
e
co
n
d
itio
n
s
,
d
is
ea
s
e
s
tag
e,
an
d
s
im
ilar
ity
am
o
n
g
s
y
m
p
to
m
s
.
Sp
o
t
-
lik
e
lesi
o
n
s
,
y
ello
win
g
,
n
ec
r
o
tic
ar
ea
s
,
a
n
d
u
n
e
v
en
lig
h
tin
g
m
ay
ca
u
s
e
in
co
r
r
ec
t
p
r
elim
in
ar
y
d
iag
n
o
s
is
.
L
ab
o
r
ato
r
y
ex
am
in
atio
n
an
d
ex
p
e
r
t
co
n
s
u
ltatio
n
ar
e
m
o
r
e
r
eliab
le,
b
u
t
th
e
y
m
a
y
b
e
c
o
s
tly
,
s
lo
w,
o
r
u
n
av
ailab
le
in
s
m
all
f
ar
m
in
g
co
m
m
u
n
ities
.
T
h
is
co
n
d
itio
n
cr
ea
tes
a
p
r
ac
tical
g
a
p
f
o
r
a
s
m
ar
tp
h
o
n
e
-
b
ased
s
y
s
tem
th
at
ca
n
s
u
p
p
o
r
t e
ar
ly
s
cr
ee
n
in
g
b
ef
o
r
e
f
u
r
th
er
ex
p
e
r
t c
o
n
f
ir
m
atio
n
is
p
er
f
o
r
m
ed
.
Deep
lear
n
in
g
ap
p
r
o
ac
h
es
h
a
v
e
b
ee
n
wid
ely
e
x
p
lo
r
ed
f
o
r
p
l
an
t
d
is
ea
s
e
r
ec
o
g
n
itio
n
,
in
clu
d
in
g
C
NN
v
ar
ian
ts
an
d
lig
h
tweig
h
t
m
o
d
els
f
o
r
m
o
b
ile
o
r
lo
w
-
r
eso
u
r
c
e
en
v
ir
o
n
m
en
ts
[
1
2
]
–
[
1
7
]
.
Alth
o
u
g
h
th
ese
s
tu
d
ies
d
em
o
n
s
tr
ate
th
e
ca
p
ab
ilit
y
o
f
n
eu
r
al
n
etwo
r
k
s
in
r
ec
o
g
n
izin
g
v
is
u
al
d
is
ea
s
e
f
ea
tu
r
es,
s
ev
er
al
lim
itatio
n
s
r
em
ain
.
Ma
n
y
wo
r
k
s
em
p
h
a
s
ize
b
en
ch
m
ar
k
ac
cu
r
ac
y
b
u
t
p
r
o
v
id
e
less
d
etail
ab
o
u
t
d
ata
p
r
ep
a
r
atio
n
,
au
g
m
en
tatio
n
s
tr
ateg
y
,
h
y
p
e
r
p
ar
am
eter
c
h
o
ices,
an
d
th
e
r
ep
r
o
d
u
cib
ilit
y
o
f
th
e
ex
p
er
i
m
en
tal
p
ip
elin
e.
I
n
ad
d
itio
n
,
s
o
m
e
s
tu
d
ies
s
to
p
a
t
m
o
d
el
ev
alu
atio
n
an
d
d
o
n
o
t
ex
p
lain
th
e
tr
an
s
itio
n
f
r
o
m
tr
ain
ed
m
o
d
el
to
An
d
r
o
id
-
b
ased
u
s
e.
T
h
e
r
em
a
in
in
g
g
ap
is
th
er
ef
o
r
e
a
co
m
p
ac
t
f
r
am
ewo
r
k
t
h
at
lin
k
s
Mo
b
ileNetV2
tr
ain
in
g
,
in
d
ep
en
d
en
t te
s
tin
g
,
m
o
b
ile
in
teg
r
atio
n
,
an
d
er
r
o
r
a
n
aly
s
is
f
o
r
to
m
ato
leaf
d
is
ea
s
e
r
ec
o
g
n
iti
o
n
.
T
h
e
g
ap
is
im
p
o
r
tan
t
b
ec
a
u
s
e
m
o
b
ile
d
ep
l
o
y
m
en
t
c
h
an
g
es
th
e
v
alu
e
o
f
a
class
if
icatio
n
m
o
d
el
f
r
o
m
lab
o
r
ato
r
y
ev
alu
atio
n
to
p
r
ac
tical
d
ec
is
io
n
s
u
p
p
o
r
t.
Fro
m
an
ac
ad
em
ic
p
er
s
p
ec
tiv
e,
th
e
s
tu
d
y
clar
if
ies
h
o
w
a
lig
h
tweig
h
t
C
NN
ca
n
b
e
p
r
ep
ar
ed
,
test
ed
,
an
d
em
b
ed
d
e
d
in
a
n
An
d
r
o
i
d
wo
r
k
f
lo
w.
Fro
m
a
p
r
ac
tical
p
er
s
p
ec
tiv
e,
th
e
ap
p
licatio
n
ca
n
ass
is
t
f
ar
m
er
s
,
s
tu
d
en
ts
,
an
d
ag
r
icu
ltu
r
al
f
ield
o
f
f
icer
s
in
o
b
tain
in
g
an
in
itial
d
is
ea
s
e
in
d
icatio
n
f
r
o
m
ca
m
er
a
o
r
g
aller
y
im
ag
es
with
o
u
t
s
er
v
er
-
s
id
e
p
r
o
ce
s
s
in
g
.
W
ith
o
u
t
th
is
ty
p
e
o
f
im
p
lem
en
tatio
n
,
im
ag
e
-
b
ased
p
lan
t
d
is
ea
s
e
r
ec
o
g
n
itio
n
m
ay
r
em
ain
d
if
f
icu
lt
to
u
s
e
in
lo
ca
tio
n
s
with
lim
ited
ac
ce
s
s
to
ex
p
er
ts
,
u
n
s
tab
le
co
n
n
ec
tiv
ity
,
o
r
l
o
w
co
m
p
u
tatio
n
a
l r
eso
u
r
ce
s
.
Acc
o
r
d
in
g
ly
,
th
is
s
tu
d
y
aim
s
to
d
e
v
elo
p
an
d
ev
al
u
ate
an
An
d
r
o
id
-
b
ased
to
m
ato
le
af
d
is
ea
s
e
class
if
icatio
n
s
y
s
tem
u
s
in
g
M
o
b
ileNetV2
.
T
h
e
o
b
jects
an
aly
ze
d
wer
e
to
m
ato
lea
f
im
ag
e
s
r
ep
r
esen
tin
g
f
o
u
r
d
is
ea
s
e
ca
teg
o
r
ies
an
d
o
n
e
h
ea
lth
y
ca
teg
o
r
y
.
T
h
e
s
tu
d
y
e
x
am
in
ed
th
e
r
elatio
n
s
h
ip
b
et
wee
n
im
ag
e
in
p
u
t,
p
r
ep
r
o
ce
s
s
in
g
co
n
f
ig
u
r
atio
n
,
m
o
d
el
tr
ain
i
n
g
,
an
d
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
.
T
h
e
e
x
p
ec
t
ed
co
n
tr
ib
u
tio
n
is
a
lig
h
tweig
h
t
class
if
icatio
n
m
o
d
el
th
at
ca
n
b
e
em
b
ed
d
ed
in
an
An
d
r
o
id
a
p
p
licatio
n
an
d
u
s
ed
f
o
r
p
r
elim
in
ar
y
d
is
ea
s
e
s
cr
ee
n
in
g
.
T
h
e
s
tu
d
y
also
p
r
o
v
id
es
a
b
asis
f
o
r
f
u
t
u
r
e
d
e
v
elo
p
m
en
t
in
v
o
lv
in
g
la
r
g
er
f
ield
d
atasets
,
k
-
f
o
l
d
v
ali
d
a
ti
o
n
,
e
x
p
lai
n
ab
le
ar
t
if
ici
al
i
n
tel
li
g
e
n
c
e
,
a
n
d
c
o
m
p
a
r
is
o
n
w
it
h
alt
er
n
a
ti
v
e
li
g
h
tw
eig
h
t
a
r
ch
ite
ct
u
r
es.
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
T
h
is
s
tu
d
y
u
s
ed
th
e
s
eg
m
en
t
ed
v
er
s
io
n
o
f
a
p
u
b
licly
av
ai
lab
le
Kag
g
le
t
o
m
ato
leaf
d
is
e
ase
im
ag
e
d
ataset.
Fro
m
th
e
ten
ca
teg
o
r
i
es in
th
e
o
r
ig
in
al
d
ataset,
f
iv
e
class
es
wer
e
s
elec
ted
f
o
r
th
e
e
x
p
er
im
en
t: b
ac
te
r
ial
s
p
o
t,
late
b
lig
h
t,
tar
g
et
s
p
o
t
,
to
m
ato
y
ello
w
lea
f
cu
r
l
v
ir
u
s
,
an
d
h
ea
lth
y
leaf
.
E
ac
h
class
co
n
tr
ib
u
ted
2
4
0
im
ag
es,
s
o
th
e
to
tal
d
ataset
co
n
tain
ed
1
,
2
0
0
im
ag
es.
T
h
e
im
ag
es
wer
e
ar
r
an
g
ed
in
a
b
alan
ce
d
co
m
p
o
s
itio
n
co
n
s
is
tin
g
o
f
9
0
0
tr
ain
in
g
im
ag
es,
2
0
0
v
ali
d
atio
n
im
ag
es,
an
d
1
0
0
in
d
ep
en
d
en
t
test
in
g
im
ag
es.
T
h
e
test
in
g
s
et
was
n
o
t
in
v
o
l
v
ed
in
tr
ain
in
g
o
r
m
o
d
el
s
elec
tio
n
a
n
d
was
u
s
ed
o
n
ly
f
o
r
f
in
al
ev
alu
atio
n
th
r
o
u
g
h
th
e
co
n
f
u
s
io
n
m
atr
ix
.
All
im
ag
es
wer
e
r
esized
to
2
2
4
×
2
2
4
p
ix
els
b
e
f
o
r
e
b
ei
n
g
p
r
o
ce
s
s
ed
b
y
Mo
b
ileNet
V2
.
Pix
el
in
ten
s
ities
wer
e
s
ca
led
in
to
th
e
r
an
g
e
o
f
0
to
1
to
m
a
k
e
th
e
i
n
p
u
t
d
is
tr
ib
u
tio
n
m
o
r
e
s
tab
le
d
u
r
in
g
o
p
tim
izatio
n
.
Au
g
m
en
tatio
n
was
ap
p
lied
o
n
ly
to
th
e
tr
ain
in
g
s
u
b
s
et
th
r
o
u
g
h
r
o
tatio
n
,
h
o
r
iz
o
n
tal
f
lip
p
in
g
,
zo
o
m
in
g
,
b
r
ig
h
tn
ess
v
ar
iatio
n
,
an
d
s
m
all
s
p
atial
s
h
if
ts
.
T
h
e
v
alid
atio
n
an
d
test
in
g
s
u
b
s
ets
r
ec
eiv
ed
o
n
ly
r
esizin
g
an
d
n
o
r
m
aliza
tio
n
t
o
av
o
id
ar
tific
i
ally
ch
an
g
i
n
g
th
e
ev
alu
atio
n
d
ata.
A
f
ix
e
d
r
an
d
o
m
s
ee
d
w
as
u
s
ed
d
u
r
i
n
g
d
ata
s
p
litt
in
g
s
o
th
at
th
e
ex
p
er
i
m
en
t c
an
b
e
r
e
p
ea
ted
with
th
e
s
am
e
s
u
b
s
et
co
m
p
o
s
itio
n
.
2
.
2
.
Co
nv
o
lutio
na
l neura
l net
wo
rk
Fig
u
r
e
1
p
r
esen
ts
th
e
p
r
o
p
o
s
e
d
C
NN
-
b
ased
class
if
icatio
n
p
i
p
elin
e.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
with
a
to
m
ato
leaf
im
ag
e,
f
o
llo
wed
b
y
p
r
e
p
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
an
d
class
p
r
ed
ictio
n
.
C
NN
lay
er
s
lear
n
v
is
u
al
r
ep
r
esen
tatio
n
s
p
r
o
g
r
ess
iv
ely
,
b
eg
in
n
in
g
f
r
o
m
lo
ca
l
f
ea
tu
r
es
s
u
ch
as
e
d
g
es,
c
o
lo
r
b
o
u
n
d
ar
ies,
an
d
tex
tu
r
e
p
atter
n
s
an
d
m
o
v
i
n
g
to
war
d
h
ig
h
er
-
lev
el
d
is
ea
s
e
ch
ar
ac
ter
is
tics
[
1
3
]
–
[
1
5
]
.
Mo
b
ileNetV2
was
ch
o
s
en
b
ec
au
s
e
its
lig
h
tweig
h
t
ar
ch
itectu
r
e
is
s
u
itab
le
f
o
r
An
d
r
o
id
d
ev
ices
wh
ile
s
ti
ll
m
ain
tain
in
g
s
u
f
f
icien
t
r
ep
r
esen
tatio
n
ca
p
ac
ity
f
o
r
leaf
d
is
ea
s
e
im
ag
es
[
1
6
]
,
[
1
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
26
:
3
3
1
8
-
3
3
2
5
3320
Fig
u
r
e
1
.
Pro
ce
s
s
f
lo
w
o
f
th
e
C
NN
m
eth
o
d
Du
r
in
g
f
ea
tu
r
e
ex
tr
ac
tio
n
,
th
e
Mo
b
ileNetV2
b
ac
k
b
o
n
e
tr
an
s
f
o
r
m
s
th
e
p
r
e
p
r
o
ce
s
s
ed
i
m
ag
e
in
to
co
m
p
ac
t
f
ea
tu
r
e
m
a
p
s
.
T
h
ese
f
ea
tu
r
e
m
ap
s
ar
e
th
en
p
r
o
ce
s
s
ed
b
y
th
e
class
if
icatio
n
h
ea
d
,
wh
ich
p
r
o
d
u
ce
s
p
r
o
b
a
b
ilit
y
s
co
r
es
f
o
r
all
tar
g
et
class
es
th
r
o
u
g
h
th
e
s
o
f
t
m
ax
lay
er
[
1
8
]
,
[
1
9
]
.
T
h
e
la
b
el
with
th
e
lar
g
est
p
r
o
b
a
b
ilit
y
is
s
elec
ted
as
th
e
p
r
ed
ictio
n
r
esu
lt.
T
h
is
ar
ch
itectu
r
e
was
s
elec
ted
b
ec
au
s
e
it
s
u
p
p
o
r
ts
ef
f
icien
t
in
f
er
en
ce
a
n
d
ca
n
b
e
co
n
v
er
te
d
f
o
r
u
s
e
in
s
id
e
an
An
d
r
o
id
ap
p
licatio
n
.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
was
co
n
d
u
cted
f
o
r
3
0
ep
o
ch
s
u
s
in
g
s
to
ch
asti
c
g
r
ad
ien
t
d
escen
t
(
SGD)
,
a
lea
r
n
i
n
g
r
at
e
o
f
0
.
0
0
0
1
,
an
d
a
b
at
c
h
s
ize
o
f
1
6
.
T
h
is
s
m
al
l le
ar
n
i
n
g
r
a
te
was
s
ele
cte
d
t
o
k
ee
p
p
ar
am
ete
r
u
p
d
ates
g
r
ad
u
al,
wh
ile
th
e
b
atch
s
ize
was
ch
o
s
en
to
b
ala
n
ce
m
em
o
r
y
u
s
ag
e
a
n
d
g
r
ad
ien
t
s
tab
ilit
y
.
T
h
e
co
n
f
ig
u
r
atio
n
was
d
eter
m
in
ed
b
y
m
o
n
ito
r
in
g
th
e
tr
ain
in
g
an
d
v
alid
atio
n
cu
r
v
es
an
d
s
elec
tin
g
th
e
s
ettin
g
th
at
p
r
o
d
u
ce
d
s
tab
le
co
n
v
er
g
e
n
ce
with
lo
w
v
alid
atio
n
lo
s
s
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
p
r
o
ce
d
u
r
e,
s
p
lit
r
a
tio
,
ep
o
ch
n
u
m
b
e
r
,
o
p
tim
izer
,
lear
n
i
n
g
r
ate,
an
d
b
atch
s
ize
wer
e
k
ep
t c
o
n
s
is
ten
t a
cr
o
s
s
ex
p
er
im
en
ts
to
im
p
r
o
v
e
r
ep
r
o
d
u
cib
ilit
y
.
2
.
3
.
M
o
bil
e
a
pp
lica
t
io
n wo
r
k
f
lo
w
T
h
e
o
v
er
all
wo
r
k
f
lo
w
o
f
m
o
b
ile
ap
p
licatio
n
u
s
ed
in
th
is
s
tu
d
y
is
illu
s
tr
ated
in
Fig
u
r
e
2
[
2
0
]
–
[
2
2
]
.
T
h
e
f
lo
wch
ar
t
d
escr
ib
es
th
e
s
eq
u
en
ce
o
f
p
r
o
ce
s
s
es
s
tar
tin
g
f
r
o
m
u
s
er
in
ter
ac
tio
n
to
i
m
ag
e
class
if
icatio
n
o
u
tp
u
t.
User
s
ca
n
ca
p
t
u
r
e
im
a
g
es
u
s
in
g
th
e
ca
m
er
a
o
r
s
elec
t
im
ag
es
f
r
o
m
th
e
g
aller
y
,
af
te
r
wh
ich
t
h
e
s
y
s
tem
au
to
m
atica
lly
p
er
f
o
r
m
s
d
is
ea
s
e
class
if
icatio
n
an
d
d
is
p
lay
s
th
e
r
esu
lts
[
2
3
]
.
Fig
u
r
e
2
.
Mo
b
ile
ap
p
licatio
n
f
lo
wch
ar
t
I
n
th
e
i
m
p
l
em
e
n
te
d
wo
r
k
f
lo
w,
th
e
ap
p
li
ca
tio
n
f
ir
s
t
d
ir
e
ct
s
u
s
er
s
to
th
e
m
ain
p
ag
e,
wh
er
e
i
m
ag
e
in
p
u
t
c
an
b
e
s
e
le
ct
ed
.
On
ce
an
i
m
ag
e
is
p
r
o
v
id
e
d
,
th
e
s
y
s
t
em
co
n
v
er
t
s
i
t
in
to
t
h
e
r
eq
u
ir
ed
in
p
u
t
s
iz
e
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
d
r
o
id
-
b
a
s
ed
to
ma
to
le
a
f d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
a
lig
h
tw
eig
h
t Mo
b
ileN
etV
2
…
(
A
n
d
i R
ia
n
s
ya
h
)
3321
f
o
r
m
a
t
b
ef
o
r
e
r
u
n
n
i
n
g
o
n
-
d
ev
ic
e
c
la
s
s
if
ic
at
io
n
.
T
h
e
p
r
e
d
ic
ted
c
la
s
s
i
s
t
h
en
s
h
o
wn
o
n
t
h
e
ap
p
li
ca
tio
n
in
t
er
f
a
ce
to
g
e
th
er
w
i
th
th
e
cl
as
s
if
ica
ti
o
n
in
f
o
r
m
at
io
n
.
T
h
e
a
p
p
l
ic
at
io
n
is
in
ten
d
ed
f
o
r
p
r
el
im
in
ar
y
s
cr
ee
n
in
g
in
ag
r
i
cu
ltu
r
al
en
v
ir
o
n
m
en
t
s
;
th
er
ef
o
r
e
,
ex
p
er
t
co
n
f
ir
m
a
tio
n
r
em
ain
s
n
ec
es
s
ar
y
f
o
r
cr
it
ic
al
tr
e
atm
en
t
d
e
ci
s
io
n
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
T
ra
ini
ng
a
nd
v
a
lid
a
t
io
n
T
h
e
ex
p
er
im
en
t
u
s
ed
a
b
alan
c
ed
s
p
lit
o
f
1
,
2
0
0
im
ag
es.
A
t
o
tal
o
f
9
0
0
im
ag
es
wer
e
u
s
ed
f
o
r
tr
ain
in
g
,
2
0
0
im
ag
es
f
o
r
v
alid
atio
n
,
a
n
d
1
0
0
im
ag
es
f
o
r
in
d
e
p
en
d
en
t
test
in
g
.
E
ac
h
class
h
ad
th
e
s
am
e
n
u
m
b
e
r
o
f
s
am
p
les
in
ev
er
y
s
u
b
s
et
to
r
ed
u
ce
th
e
p
o
s
s
ib
ilit
y
o
f
d
o
m
in
an
ce
b
y
a
p
a
r
ticu
lar
d
is
ea
s
e
ca
teg
o
r
y
.
T
h
e
v
alid
atio
n
d
ata
wer
e
u
s
ed
to
o
b
s
er
v
e
lear
n
in
g
s
tab
ilit
y
d
u
r
i
n
g
tr
ain
in
g
,
wh
er
ea
s
th
e
test
in
g
d
ata
wer
e
r
eser
v
ed
f
o
r
th
e
f
i
n
al
p
er
f
o
r
m
an
ce
ass
ess
m
en
t.
Fig
u
r
e
3
d
is
p
lay
s
th
e
ac
cu
r
ac
y
t
r
en
d
o
v
er
3
0
e
p
o
ch
s
.
T
h
e
tr
ai
n
in
g
ac
cu
r
ac
y
in
cr
ea
s
ed
g
r
a
d
u
all
y
,
an
d
th
e
v
alid
atio
n
ac
cu
r
ac
y
f
o
llo
wed
a
s
im
ilar
p
atter
n
.
T
h
e
clo
s
en
ess
b
etwe
en
th
e
two
cu
r
v
es
in
d
ic
ates
th
at
th
e
m
o
d
el
lear
n
ed
r
elev
an
t
d
is
ea
s
e
f
ea
tu
r
es
with
o
u
t
s
h
o
win
g
a
s
tr
o
n
g
o
v
er
f
itti
n
g
p
atter
n
.
Fig
u
r
e
4
p
r
esen
ts
th
e
lo
s
s
cu
r
v
es
f
o
r
tr
ain
in
g
an
d
v
alid
atio
n
.
B
o
th
cu
r
v
es
d
ec
r
ea
s
ed
d
u
r
in
g
tr
ain
in
g
,
s
h
o
win
g
th
at
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
r
ed
u
ce
d
class
if
icatio
n
er
r
o
r
.
T
h
e
s
tab
le
v
alid
atio
n
lo
s
s
al
s
o
s
u
g
g
ests
th
at
th
e
s
elec
ted
co
n
f
ig
u
r
atio
n
p
r
o
d
u
ce
d
ac
ce
p
ta
b
le
g
en
er
aliza
tio
n
o
n
u
n
s
ee
n
v
alid
atio
n
im
ag
es.
T
h
e
f
in
a
l
co
n
f
ig
u
r
atio
n
u
s
ed
SGD,
a
lear
n
in
g
r
ate
o
f
0
.
0
0
0
1
,
a
b
atch
s
ize
o
f
1
6
an
d
3
0
ep
o
ch
s
.
T
h
is
co
n
f
ig
u
r
atio
n
was
r
etain
ed
b
ec
a
u
s
e
it
p
r
o
d
u
ce
d
c
o
n
s
is
ten
t
co
n
v
er
g
en
ce
in
th
e
a
cc
u
r
ac
y
a
n
d
lo
s
s
cu
r
v
es.
E
v
en
s
o
,
th
e
ev
alu
atio
n
r
em
ain
s
co
n
s
tr
ain
ed
b
y
th
e
l
im
ited
d
ataset
s
ize
an
d
th
e
u
s
e
o
f
a
s
in
g
le
tr
ain
-
v
alid
atio
n
-
test
s
p
lit.
Fu
tu
r
e
ex
p
er
im
en
ts
s
h
o
u
ld
ap
p
ly
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
a
n
d
in
clu
d
e
lar
g
e
r
im
a
g
es
co
llected
d
ir
ec
tly
f
r
o
m
f
a
r
m
s
to
in
cr
ea
s
e
th
e
r
eliab
ilit
y
o
f
t
h
e
f
in
d
in
g
s
.
At
th
e
en
d
o
f
t
r
ain
in
g
,
t
h
e
m
o
d
el
o
b
tain
ed
a
t
r
ain
in
g
ac
c
u
r
ac
y
o
f
9
4
.
1
2
% with
a
lo
s
s
v
alu
e
o
f
0
.
1
5
0
3
.
T
h
e
v
alid
atio
n
ac
cu
r
ac
y
r
ea
c
h
ed
9
3
.
0
0
%,
wh
ile
th
e
v
alid
a
tio
n
lo
s
s
was
0
.
0
7
9
7
.
T
h
ese
r
esu
lts
in
d
icate
th
at
Mo
b
ileNetV2
was
ab
le
to
ex
t
r
ac
t
u
s
ef
u
l
d
is
ea
s
e
-
r
elate
d
v
is
u
al
p
atter
n
s
f
r
o
m
th
e
s
elec
ted
d
ataset.
Ho
wev
er
,
th
ese
v
alu
es
s
h
o
u
ld
n
o
t
b
e
in
ter
p
r
eted
alo
n
e
b
ec
au
s
e
v
a
lid
atio
n
im
ag
es
m
ay
n
o
t
f
u
l
ly
r
ep
r
esen
t
f
ield
v
ar
iatio
n
; th
er
ef
o
r
e,
t
h
e
in
d
e
p
en
d
en
t te
s
t r
esu
lt p
r
o
v
id
es a
m
o
r
e
r
ea
lis
tic
p
er
f
o
r
m
an
ce
in
d
ic
atio
n
[
2
4
]
–
[2
7
]
.
Fig
u
r
e
3
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
cu
r
v
es
Fig
u
r
e
4
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
lo
s
s
cu
r
v
es
3
.
2
.
T
esting
Fig
u
r
e
5
s
h
o
ws
th
e
co
n
f
u
s
io
n
m
atr
ix
o
b
tain
ed
f
r
o
m
1
0
0
in
d
ep
en
d
en
t
test
im
ag
es,
co
n
s
is
tin
g
o
f
2
0
im
ag
es
f
o
r
ea
ch
class
.
T
h
e
m
atr
ix
was
u
s
ed
to
d
e
r
iv
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
as
well
as
to
o
b
s
er
v
e
wh
ich
ca
teg
o
r
ies
wer
e
co
n
f
u
s
ed
b
y
th
e
class
if
ier
[
1
8
]
,
[
2
8
]
.
T
h
is
ev
alu
atio
n
was
s
ep
ar
ated
f
r
o
m
tr
ain
in
g
an
d
v
alid
atio
n
to
p
r
o
v
id
e
an
in
d
e
p
en
d
e
n
t m
ea
s
u
r
em
en
t o
f
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
T
h
e
co
n
f
u
s
io
n
m
atr
i
x
in
d
ica
tes
th
at
all
to
m
at
o
y
ello
w
l
ea
f
cu
r
l
v
ir
u
s
im
ag
es
wer
e
class
if
ied
co
r
r
ec
tly
.
T
h
e
r
em
ain
in
g
er
r
o
r
s
m
ain
ly
in
v
o
lv
ed
b
ac
ter
ial
s
p
o
t,
h
ea
lth
y
leaf
,
late
b
lig
h
t,
an
d
tar
g
et
s
p
o
t.
T
h
is
r
esu
lt
s
u
g
g
ests
th
at
s
y
m
p
to
m
o
v
er
lap
,
esp
ec
ially
s
p
o
t
-
lik
e
l
esio
n
s
an
d
c
o
lo
r
d
eg
r
a
d
atio
n
,
s
till
af
f
ec
ts
m
o
d
el
d
ec
is
io
n
s
.
T
h
e
in
d
ep
en
d
en
t
te
s
t
p
r
o
d
u
ce
d
an
o
v
er
all
ac
cu
r
a
cy
o
f
8
9
.
0
0
%,
a
n
d
th
e
d
etailed
class
-
lev
el
r
esu
lts
ar
e
p
r
esen
ted
in
T
ab
le
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
26
:
3
3
1
8
-
3
3
2
5
3322
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
th
e
in
d
e
p
en
d
e
n
t te
s
t su
b
s
et
T
ab
le
1
.
C
lass
if
icatio
n
p
er
f
o
r
m
an
ce
o
n
th
e
in
d
e
p
en
d
e
n
t te
s
t su
b
s
et
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
B
a
c
t
e
r
i
a
l
sp
o
t
0
.
8
9
0
.
8
5
0
.
8
7
H
e
a
l
t
h
y
l
e
a
f
0
.
8
5
0
.
8
5
0
.
8
5
L
a
t
e
b
l
i
g
h
t
0
.
8
9
0
.
8
5
0
.
8
7
T
a
r
g
e
t
s
p
o
t
0
.
8
2
0
.
9
0
0
.
8
6
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
M
a
c
r
o
0
.
8
9
0
.
8
9
0
.
8
9
O
v
e
r
a
l
l
a
c
c
u
r
a
c
y
0
.
8
9
T
ab
le
1
s
u
m
m
ar
izes
th
e
class
-
lev
el
test
p
er
f
o
r
m
a
n
ce
.
T
h
e
m
ac
r
o
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
wer
e
all
0
.
8
9
,
in
d
icatin
g
r
elativ
ely
b
alan
ce
d
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
class
es.
T
h
e
y
ello
w
leaf
cu
r
l
v
ir
u
s
class
ac
h
iev
ed
th
e
b
est
r
esu
lt,
with
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
all
eq
u
a
l
to
1
.
0
0
.
B
ac
ter
ial
s
p
o
t
a
n
d
l
ate
b
lig
h
t
o
b
tain
ed
s
im
ilar
F1
-
s
co
r
es
o
f
0
.
8
7
,
wh
i
le
th
e
h
ea
lth
y
class
r
ea
ch
ed
a
n
F1
-
s
co
r
e
o
f
0
.
8
5
.
T
ar
g
et
s
p
o
t
ac
h
iev
ed
a
r
ec
all
o
f
0
.
9
0
b
u
t
a
lo
wer
p
r
ec
is
io
n
o
f
0
.
8
2
,
m
ea
n
in
g
th
at
s
ev
er
al
im
ag
es
f
r
o
m
o
th
er
class
es
we
r
e
ass
ig
n
ed
to
th
is
ca
teg
o
r
y
.
T
h
ese
f
in
d
i
n
g
s
s
h
o
w
th
at
Mo
b
ileNetV2
p
er
f
o
r
m
ed
well,
alth
o
u
g
h
s
y
m
p
t
o
m
s
im
ilar
ity
s
till
ca
u
s
ed
class
if
icatio
n
am
b
ig
u
ity
.
Fig
u
r
e
6
p
r
esen
ts
th
e
An
d
r
o
id
in
ter
f
ac
e
d
ev
el
o
p
ed
f
o
r
to
m
ato
leaf
d
is
ea
s
e
class
if
icatio
n
.
T
h
e
in
ter
f
ac
e
d
em
o
n
s
tr
ates
th
e
in
teg
r
atio
n
o
f
th
e
tr
ain
ed
Mo
b
ileNetV2
m
o
d
el
in
to
a
m
o
b
ile
ap
p
licatio
n
.
User
s
ca
n
p
r
o
v
id
e
an
in
p
u
t
im
a
g
e
f
r
o
m
t
h
e
ca
m
er
a
o
r
g
aller
y
,
an
d
th
e
ap
p
l
icatio
n
r
etu
r
n
s
th
e
p
r
ed
icted
d
is
ea
s
e
ca
teg
o
r
y
d
ir
ec
tly
o
n
th
e
d
ev
ice.
Fig
u
r
e
6
.
An
d
r
o
id
ap
p
licatio
n
in
ter
f
ac
e
f
o
r
to
m
ato
lea
f
d
is
ea
s
e
class
if
icat
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
d
r
o
id
-
b
a
s
ed
to
ma
to
le
a
f d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
a
lig
h
tw
eig
h
t Mo
b
ileN
etV
2
…
(
A
n
d
i R
ia
n
s
ya
h
)
3323
T
h
e
An
d
r
o
id
im
p
lem
en
tatio
n
ex
ten
d
s
th
e
co
n
tr
i
b
u
tio
n
o
f
th
is
wo
r
k
b
ey
o
n
d
m
o
d
el
t
r
ain
in
g
.
B
y
em
b
ed
d
in
g
th
e
class
if
ier
in
to
a
m
o
b
ile
w
o
r
k
f
l
o
w,
th
e
s
y
s
t
em
ca
n
s
u
p
p
o
r
t
p
r
elim
in
ar
y
d
is
ea
s
e
r
ec
o
g
n
itio
n
with
o
u
t c
o
n
tin
u
o
u
s
in
ter
n
et
ac
ce
s
s
o
r
s
er
v
er
-
s
id
e
co
m
p
u
tatio
n
.
T
h
is
im
p
lem
en
tatio
n
o
f
f
e
r
s
a
p
r
ac
tical
p
ath
f
o
r
u
s
e
b
y
f
ar
m
e
r
s
,
ag
r
icu
ltu
r
al
ex
ten
s
io
n
o
f
f
icer
s
,
s
tu
d
en
ts
,
an
d
c
r
o
p
-
m
o
n
ito
r
in
g
team
s
.
I
t
also
d
em
o
n
s
tr
ates
h
o
w
a
lig
h
tweig
h
t CNN c
an
b
e
co
n
n
ec
ted
to
a
s
im
p
le
u
s
er
i
n
ter
f
ac
e
f
o
r
f
ield
-
o
r
ien
ted
s
cr
ee
n
in
g
.
Mo
b
ileNetV2
is
n
o
t
in
tr
o
d
u
c
ed
as
a
n
ew
ar
ch
itectu
r
e
in
t
h
is
s
tu
d
y
;
r
ath
er
,
it
is
u
s
ed
b
ec
au
s
e
its
co
m
p
u
tatio
n
al
e
f
f
icien
cy
is
s
u
itab
le
f
o
r
m
o
b
ile
ag
r
ic
u
ltu
r
a
l
ap
p
licatio
n
s
.
T
h
e
m
ain
c
o
n
t
r
ib
u
tio
n
lies
in
th
e
in
teg
r
atio
n
o
f
a
li
g
h
tweig
h
t
c
lass
if
ier
,
in
d
ep
en
d
e
n
t
test
in
g
,
an
d
An
d
r
o
i
d
-
b
ased
d
ep
lo
y
m
en
t
f
o
r
to
m
ato
lea
f
d
is
ea
s
e
s
cr
ee
n
in
g
.
Nev
er
th
ele
s
s
,
th
e
cu
r
r
en
t
wo
r
k
d
o
es
n
o
t
y
et
co
m
p
a
r
e
Mo
b
ileNetV2
with
E
f
f
icien
tNet,
Den
s
eNe
t
,
o
r
tr
an
s
f
o
r
m
er
-
b
a
s
ed
v
is
io
n
m
o
d
els.
Su
ch
c
o
m
p
ar
is
o
n
s
ar
e
n
ee
d
e
d
to
d
eter
m
in
e
wh
eth
e
r
Mo
b
ileNetV2
p
r
o
v
i
d
es th
e
m
o
s
t a
p
p
r
o
p
r
iate
ac
c
u
r
ac
y
-
e
f
f
icie
n
cy
tr
ad
e
-
o
f
f
f
o
r
th
is
ap
p
licatio
n
.
Fo
r
wid
er
d
ep
lo
y
m
en
t,
th
e
s
y
s
tem
s
h
o
u
ld
b
e
test
ed
u
n
d
er
m
o
r
e
d
iv
er
s
e
f
ield
co
n
d
itio
n
s
.
L
ig
h
tin
g
v
ar
iatio
n
,
b
ac
k
g
r
o
u
n
d
clu
tter
,
leaf
o
r
ien
tatio
n
,
d
is
ea
s
e
s
tag
e,
an
d
ca
m
er
a
q
u
ality
ca
n
in
f
l
u
en
ce
class
if
icatio
n
r
esu
lts
in
r
ea
l
f
a
r
m
s
.
T
h
e
a
p
p
licatio
n
m
a
y
also
b
e
e
x
p
an
d
ed
b
y
co
m
b
i
n
in
g
im
ag
e
class
if
icatio
n
with
en
v
ir
o
n
m
en
tal
d
ata
f
r
o
m
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
s
en
s
o
r
s
,
s
u
ch
as
h
u
m
id
ity
,
tem
p
e
r
atu
r
e,
an
d
s
o
il
m
o
is
tu
r
e.
Fu
tu
r
e
v
er
s
io
n
s
s
h
o
u
ld
in
clu
d
e
f
ar
m
-
ac
q
u
ir
ed
d
atasets
,
ex
p
lain
ab
ilit
y
m
eth
o
d
s
s
u
ch
a
s
g
r
ad
ien
t
-
weig
h
ted
class
ac
tiv
atio
n
m
ap
p
in
g
(
Gr
ad
-
C
AM
)
o
r
s
alien
cy
m
ap
s
,
an
d
a
r
ch
itectu
r
e
c
o
m
p
ar
is
o
n
s
to
im
p
r
o
v
e
tr
an
s
p
ar
en
cy
a
n
d
s
ca
lab
ilit
y
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
esig
n
ed
an
An
d
r
o
id
-
b
ased
to
m
ato
leaf
d
is
ea
s
e
class
if
icatio
n
s
y
s
tem
u
s
in
g
a
li
g
h
tweig
h
t
Mo
b
ileNetV2
C
NN.
T
h
e
m
o
d
el
ac
h
iev
ed
9
4
.
1
2
%
tr
ain
in
g
ac
cu
r
ac
y
,
9
3
.
0
0
%
v
alid
at
io
n
ac
cu
r
ac
y
,
a
n
d
8
9
.
0
0
%
ac
cu
r
ac
y
o
n
t
h
e
in
d
e
p
en
d
en
t
test
s
u
b
s
et.
T
h
ese
r
e
s
u
lts
in
d
icate
th
at
Mo
b
ileNetV2
ca
n
p
r
o
v
id
e
a
r
ea
s
o
n
ab
le
b
ala
n
ce
b
etwe
en
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
an
d
m
o
b
ile
d
ep
lo
y
m
en
t
ef
f
icie
n
cy
.
T
h
e
An
d
r
o
id
im
p
lem
en
tatio
n
allo
ws
u
s
er
s
to
class
if
y
to
m
ato
leaf
im
ag
es
th
r
o
u
g
h
ca
m
er
a
o
r
g
aller
y
in
p
u
t,
m
ak
in
g
th
e
f
r
am
ewo
r
k
u
s
ef
u
l
as
an
ea
r
ly
s
cr
ee
n
in
g
to
o
l
in
ag
r
icu
ltu
r
al
s
ettin
g
s
.
Ho
wev
er
,
th
e
s
tu
d
y
is
s
till
l
im
ited
b
y
th
e
d
ataset
s
ize,
th
e
u
s
e
o
f
a
s
in
g
le
s
p
lit,
th
e
ab
s
en
ce
o
f
a
r
ch
itectu
r
e
co
m
p
a
r
is
o
n
,
an
d
t
h
e
lack
o
f
v
is
u
al
ex
p
lain
ab
ilit
y
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
u
s
e
lar
g
e
r
f
ield
d
atasets
,
ap
p
ly
k
-
f
o
l
d
v
a
lid
atio
n
,
co
m
p
a
r
e
Mo
b
ileNetV2
with
o
th
er
lig
h
t
weig
h
t
an
d
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els,
in
teg
r
ate
Gr
ad
-
C
AM
o
r
s
alien
cy
m
ap
s
,
an
d
co
m
b
in
e
im
ag
e
-
b
ased
p
r
e
d
ictio
n
s
with
I
o
T
-
b
ased
en
v
ir
o
n
m
en
tal
m
o
n
ito
r
in
g
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
ex
p
r
ess
th
eir
s
in
ce
r
e
g
r
atitu
d
e
to
th
e
C
en
ter
f
o
r
I
n
d
u
s
tr
ial
I
n
tellig
en
ce
Stu
d
ies,
Un
iv
er
s
itas
I
s
lam
Su
ltan
Ag
u
n
g
,
f
o
r
t
h
e
ac
ad
em
ic
s
u
p
p
o
r
t,
f
ac
ilit
ies,
an
d
r
esear
ch
en
v
ir
o
n
m
e
n
t
p
r
o
v
id
ed
d
u
r
in
g
th
e
co
m
p
letio
n
o
f
th
is
s
tu
d
y
.
T
h
e
a
u
th
o
r
s
also
ap
p
r
ec
iate
th
e
co
n
s
tr
u
ctiv
e
in
p
u
t
r
ec
eiv
ed
d
u
r
in
g
th
e
d
ev
elo
p
m
e
n
t
o
f
t
h
e
An
d
r
o
id
-
b
ased
to
m
ato
leaf
d
is
ea
s
e
class
if
icatio
n
s
y
s
tem
an
d
th
e
p
r
ep
ar
atio
n
o
f
t
h
is
m
an
u
s
cr
ip
t.
T
h
is
s
u
p
p
o
r
t c
o
n
tr
ib
u
ted
to
th
e
s
u
cc
ess
f
u
l c
o
m
p
l
etio
n
o
f
th
e
r
esear
ch
.
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
An
d
i Ri
an
s
y
ah
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
I
r
f
an
E
k
a
Ma
h
d
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
Mo
ch
am
ad
Ab
d
u
l Bas
ir
✓
✓
✓
✓
✓
✓
✓
✓
No
o
r
m
in
s
h
ah
A.
I
ah
a
d
✓
✓
✓
✓
✓
✓
✓
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
4
,
Au
g
u
s
t
20
26
:
3
3
1
8
-
3
3
2
5
3324
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
er
e
ar
e
n
o
f
in
an
cial,
p
er
s
o
n
al,
p
r
o
f
ess
io
n
al,
o
r
n
o
n
-
f
in
an
cial
c
o
n
f
licts
o
f
in
ter
est
th
at
co
u
ld
h
av
e
in
f
lu
en
ce
d
th
e
r
esear
ch
p
r
o
ce
s
s
,
r
esu
lts
,
in
ter
p
r
etatio
n
,
o
r
m
an
u
s
cr
ip
t
p
r
ep
ar
atio
n
.
T
h
e
au
th
o
r
s
also
co
n
f
ir
m
th
at
n
o
co
m
p
etin
g
in
ter
ests
ar
e
ass
o
ciate
d
with
th
is
wo
r
k
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
u
s
ed
in
th
is
s
tu
d
y
we
r
e
d
er
i
v
ed
f
r
o
m
a
p
u
b
licly
a
v
a
ilab
le
to
m
ato
leaf
d
is
ea
s
e
im
ag
e
d
ataset.
T
h
e
p
r
o
ce
s
s
ed
s
u
b
s
et,
ex
p
e
r
im
en
tal
co
n
f
i
g
u
r
atio
n
,
an
d
ev
alu
atio
n
r
esu
lts
ar
e
r
etain
e
d
b
y
th
e
a
u
th
o
r
s
an
d
m
ay
b
e
m
ad
e
av
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
[
AR
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
es
t
f
o
r
ac
ad
em
ic
an
d
r
ep
r
o
d
u
cib
ilit
y
p
u
r
p
o
s
es.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
R
i
a
n
s
y
a
h
,
S
.
M
u
l
y
o
n
o
,
a
n
d
M
.
R
o
i
c
h
a
n
i
,
“
A
p
p
l
y
i
n
g
f
u
z
z
y
p
r
o
p
o
r
t
i
o
n
a
l
i
n
t
e
g
r
a
l
d
e
r
i
v
a
t
i
v
e
o
n
in
t
e
r
n
e
t
o
f
t
h
i
n
g
s
f
o
r
f
i
g
s
g
r
e
e
n
h
o
u
se
,
”
I
AE
S
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
5
3
6
–
5
4
4
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
0
.
i
3
.
p
p
5
3
6
-
5
4
4
.
[
2
]
L.
X
u
,
Y
.
D
o
n
g
,
Y
.
Z
h
a
n
g
,
P
.
X
u
,
Z
.
C
a
i
,
a
n
d
J
.
Zh
a
o
,
“
M
LSA
:
a
m
u
l
t
i
-
h
e
a
d
l
a
t
e
n
t
a
n
d
s
e
l
f
-
a
t
t
e
n
t
i
o
n
d
e
e
p
l
e
a
r
n
i
n
g
n
e
t
w
o
r
k
f
o
r
t
o
m
a
t
o
l
e
a
f
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
S
m
a
rt
Ag
r
i
c
u
l
t
u
ra
l
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
t
e
c
h
.
2
0
2
5
.
1
0
1
6
0
4
.
[
3
]
A
.
M
a
r
w
a
n
t
o
,
A
.
R
i
a
n
s
y
a
h
,
a
n
d
M
.
K
.
A
n
w
a
r
,
“
A
n
i
m
p
r
o
v
e
m
e
n
t
o
f
a
p
p
l
e
l
e
a
f
d
i
s
e
a
s
e
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
me
t
h
o
d
s
b
a
se
d
o
n
m
o
b
i
l
e
s
y
s
t
e
ms,
”
i
n
2
0
2
4
1
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
c
s (E
EC
S
I
)
,
S
e
p
.
2
0
2
4
,
p
p
.
4
4
0
–
4
4
7
.
d
o
i
:
1
0
.
1
1
0
9
/
EE
C
S
I
6
3
4
4
2
.
2
0
2
4
.
1
0
7
7
6
3
4
5
.
[
4
]
M
.
G
u
p
t
a
,
S
.
G
a
r
g
,
N
.
D
e
b
,
a
n
d
P
.
P
a
n
d
e
y
,
“
C
S
-
D
:
a
d
a
t
a
set
f
o
r
d
i
s
e
a
s
e
i
n
t
e
a
l
e
a
f
(
C
a
m
e
l
l
i
a
s
i
n
e
n
si
s
)
f
r
o
m
A
ssam,
”
D
a
t
a
i
n
Bri
e
f
,
v
o
l
.
6
3
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
i
b
.
2
0
2
5
.
1
1
2
2
5
1
.
[
5
]
A
.
A
r
o
r
a
a
n
d
V
.
G
a
u
t
a
m,
“
P
l
a
n
t
l
e
a
v
e
s
d
i
sea
se
d
e
t
e
c
t
i
o
n
i
n
c
o
m
p
l
e
x
b
a
c
k
g
r
o
u
n
d
u
si
n
g
a
u
t
o
m
a
t
i
c
se
g
me
n
t
a
t
i
o
n
a
n
d
i
m
p
r
o
v
e
d
mu
l
t
i
-
sc
a
l
e
f
e
a
t
u
r
e
f
u
si
o
n
n
e
t
w
o
r
k
,
”
S
y
st
e
m
s
a
n
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
8
,
Ju
n
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sas
c
.
2
0
2
5
.
2
0
0
4
3
4
.
[
6
]
D
.
K
.
S
a
h
a
,
M
.
R
.
A
h
me
d
,
T
.
D
.
N
a
t
h
,
R
.
I
.
B
o
b
y
,
M
.
J
.
H
o
ss
e
n
,
a
n
d
M
.
F
.
M
r
i
d
h
a
,
“
F
u
si
n
g
e
x
p
l
a
i
n
a
b
l
e
d
e
e
p
l
e
a
r
n
i
n
g
e
n
s
e
mb
l
e
s
a
n
d
LL
M
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
f
o
r
r
e
a
l
-
t
i
me
p
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
d
i
a
g
n
o
s
i
s,
”
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
8
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sw
a
.
2
0
2
5
.
2
0
0
5
9
6
.
[
7
]
M
.
M
.
B
i
l
l
a
h
,
S
.
S
a
g
o
r
,
a
n
d
M
.
S
.
U
d
d
i
n
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
c
o
m
b
i
n
e
d
d
a
t
a
s
e
t
o
n
h
i
b
i
s
c
u
s
a
n
d
t
e
a
p
l
a
n
t
l
e
a
f
d
i
sea
s
e
i
ma
g
e
s
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
s
,
”
D
a
t
a
i
n
Br
i
e
f
,
v
o
l
.
6
4
,
F
e
b
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
i
b
.
2
0
2
5
.
1
1
2
3
5
7
.
[
8
]
N
.
D
e
b
a
n
d
T.
R
a
h
m
a
n
,
“
L
i
g
h
t
w
e
i
g
h
t
C
N
N
a
n
d
M
o
b
i
l
e
N
e
t
V
2
w
i
t
h
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
e
x
p
l
a
i
n
a
b
l
e
A
I
f
o
r
e
f
f
i
c
i
e
n
t
i
n
s
e
c
t
d
e
t
e
c
t
i
o
n
i
n
p
o
t
a
t
o
p
l
a
n
t
s,
”
J
o
u
rn
a
l
o
f
Ag
r
i
c
u
l
t
u
re
a
n
d
F
o
o
d
R
e
se
a
rc
h
,
v
o
l
.
2
5
,
F
e
b
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
f
r
.
2
0
2
5
.
1
0
2
6
0
4
.
[
9
]
V
.
P
.
R
a
j
,
K
.
R
a
d
h
a
,
S
.
H
.
G
o
p
a
l
a
n
,
C
.
V
e
n
k
a
t
a
r
a
m
a
n
a
n
,
R
.
D
h
a
n
a
p
a
l
,
a
n
d
A
.
M
a
n
i
k
a
n
d
a
n
,
“
C
O
A
-
S
S
D
:
a
n
o
v
e
l
c
h
a
o
t
i
c
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
e
n
h
a
n
c
e
m
e
n
t
o
f
r
e
a
l
-
t
i
me
v
i
d
e
o
su
r
v
e
i
l
l
a
n
c
e
i
mag
e
s
u
s
i
n
g
si
n
g
l
e
s
h
o
t
d
e
t
e
c
t
o
r
w
i
t
h
M
o
b
i
l
e
N
e
t
V
2
,
”
S
y
s
t
e
m
s
a
n
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sas
c
.
2
0
2
5
.
2
0
0
4
1
7
.
[
1
0
]
M
.
S
.
A
.
M
.
A
l
-
G
a
a
sh
a
n
i
,
A
.
S
.
B
.
M
a
h
e
l
,
a
n
d
A
.
M
u
t
h
a
n
n
a
,
“
Tr
u
n
c
a
t
e
d
M
o
b
i
l
e
N
e
t
V
2
s
p
a
r
se
v
i
si
o
n
g
r
a
p
h
a
t
t
e
n
t
i
o
n
m
o
d
e
l
f
o
r
e
x
p
l
a
i
n
a
b
l
e
m
o
n
k
e
y
p
o
x
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
K
n
o
w
l
e
d
g
e
-
Ba
s
e
d
S
y
st
e
m
s
,
v
o
l
.
3
3
0
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s
.
2
0
2
5
.
1
1
4
5
0
3
.
[
1
1
]
M
.
C
h
i
l
a
k
a
r
a
o
,
S
.
K
.
B
e
h
e
r
a
,
K
.
P
.
R
a
j
u
,
P
.
P
.
D
a
s
h
,
P
.
K
.
S
e
t
h
y
,
a
n
d
A
.
N
a
n
t
h
a
a
m
o
r
n
p
h
o
n
g
,
“
D
o
ma
i
n
-
a
l
i
g
n
e
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
w
i
t
h
M
o
b
i
l
e
n
e
t
v
2
-
G
R
L
a
n
d
K
N
N
f
o
r
w
h
e
a
t
l
e
a
f
d
i
se
a
se
d
e
t
e
c
t
i
o
n
,
”
Re
su
l
t
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
8
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
n
e
n
g
.
2
0
2
5
.
1
0
8
1
1
8
.
[
1
2
]
P
.
Y
u
a
n
,
Z
.
C
h
e
n
,
Q
.
J
i
n
,
Y
.
X
u
,
a
n
d
H
.
X
u
,
“
Li
g
h
t
w
e
i
g
h
t
l
o
t
u
s
p
h
e
n
o
t
y
p
e
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
M
o
b
i
l
e
N
e
t
V
2
-
S
E
w
i
t
h
r
e
l
i
a
b
l
e
p
se
u
d
o
-
l
a
b
e
l
s
,
”
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
.
2
3
2
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
5
.
1
1
0
0
8
0
.
[
1
3
]
Y.
-
C
.
C
h
e
n
,
J.
-
C
.
W
a
n
g
,
M
.
-
H
.
Le
e
,
A
.
-
C
.
Li
u
,
a
n
d
J.
-
A
.
Ji
a
n
g
,
“
En
h
a
n
c
e
d
d
e
t
e
c
t
i
o
n
o
f
ma
n
g
o
l
e
a
f
d
i
se
a
ses
i
n
f
i
e
l
d
e
n
v
i
r
o
n
me
n
t
s
u
si
n
g
M
S
M
P
-
C
N
N
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
o
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
2
2
7
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
4
.
1
0
9
6
3
6
.
[
1
4
]
W
.
Ji
a
o
,
C
.
P
e
r
s
e
l
l
o
,
a
n
d
G
.
V
o
ss
e
l
man
,
“
P
o
l
y
R
-
C
N
N
:
R
-
C
N
N
f
o
r
e
n
d
-
to
-
e
n
d
p
o
l
y
g
o
n
a
l
b
u
i
l
d
i
n
g
o
u
t
l
i
n
e
e
x
t
r
a
c
t
i
o
n
,
”
I
S
PR
S
J
o
u
rn
a
l
o
f
Ph
o
t
o
g
r
a
m
m
e
t
r
y
a
n
d
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
2
1
8
,
p
p
.
3
3
–
4
3
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s
p
r
sj
p
r
s.
2
0
2
4
.
1
0
.
0
0
6
.
[
1
5
]
U
.
A
t
h
i
y
a
h
,
S
.
R
u
st
a
d
,
M
.
A
.
S
o
e
l
e
man
,
M
.
M
u
l
j
o
n
o
,
M
.
A
k
r
o
m
,
a
n
d
R
.
A
.
K
o
n
o
r
a
l
ma
,
“
D
a
t
a
e
n
h
a
n
c
e
me
n
t
t
o
i
m
p
r
o
v
e
C
N
N
a
c
c
u
r
a
c
y
f
o
r
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
c
o
l
o
r
e
c
t
a
l
c
a
n
c
e
r
,
”
Arra
y
,
v
o
l
.
2
8
,
D
e
c
.
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
5
8
1
.
[
1
6
]
L.
N
a
n
n
i
a
n
d
S
.
B
r
a
h
n
a
m
,
“
V
e
c
t
o
r
t
o
mat
r
i
x
r
e
p
r
e
se
n
t
a
t
i
o
n
f
o
r
C
N
N
n
e
t
w
o
r
k
s
f
o
r
c
l
a
ss
i
f
y
i
n
g
a
st
r
o
n
o
m
i
c
a
l
d
a
t
a
,
”
As
t
r
o
n
o
m
y
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
4
9
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
c
o
m.
2
0
2
4
.
1
0
0
8
6
4
.
[
1
7
]
R
.
T.
A
.
G
u
n
a
,
O
.
K
.
S
i
k
h
a
,
a
n
d
R
.
B
e
n
i
t
e
z
,
“
I
n
t
e
r
p
r
e
t
i
n
g
C
N
N
p
r
e
d
i
c
t
i
o
n
s
u
s
i
n
g
c
o
n
d
i
t
i
o
n
a
l
g
e
n
e
r
a
t
i
v
e
a
d
v
e
r
sari
a
l
n
e
t
w
o
r
k
s
,”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
s
t
e
m
s
,
v
o
l
.
3
0
2
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
2
4
.
1
1
2
3
4
0
.
[
1
8
]
B
.
B
.
G
u
p
t
a
,
S
.
-
H
.
P
a
n
,
A
.
G
a
u
r
a
v
,
V
.
A
r
y
a
,
W
.
A
l
h
a
l
a
b
i
,
a
n
d
K
.
T.
C
h
u
i
,
“
O
p
t
i
mi
z
e
d
h
y
b
r
i
d
C
N
N
-
LST
M
-
G
R
U
mo
d
e
l
f
o
r
c
y
b
e
r
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
u
si
n
g
a
d
a
p
t
i
v
e
e
q
u
i
l
i
b
r
i
u
m
o
p
t
i
m
i
z
a
t
i
o
n
,
”
I
C
T
E
x
p
ress
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
3
2
4
–
3
2
9
,
A
p
r
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
c
t
e
.
2
0
2
5
.
0
9
.
0
0
6
.
[
1
9
]
S
.
L
i
u
,
W
.
W
a
n
g
,
L.
D
e
n
g
,
a
n
d
H
.
X
u
,
“
C
N
N
-
t
r
a
n
s
m
o
d
e
l
:
a
p
a
r
a
l
l
e
l
d
u
a
l
-
b
r
a
n
c
h
n
e
t
w
o
r
k
f
o
r
f
u
n
d
u
s
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pr
o
c
e
s
si
n
g
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
9
6
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
4
.
1
0
6
6
2
1
.
[
2
0
]
I
.
G
r
i
j
a
l
v
a
,
H
.
B
.
A
d
a
ms,
a
n
d
B
.
M
c
C
o
r
n
a
c
k
,
“
A
f
i
n
e
-
t
u
n
e
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
d
e
t
e
c
t
i
n
g
J
a
p
a
n
e
se
b
e
e
t
l
e
s i
n
so
y
b
e
a
n
s u
si
n
g
u
n
m
a
n
n
e
d
a
i
r
c
r
a
f
t
sy
s
t
e
ms
(
U
A
S
)
a
n
d
mo
b
i
l
e
i
m
a
g
i
n
g
,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
1
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
l
w
a
.
2
0
2
5
.
1
0
0
7
1
1
.
[
2
1
]
C
.
S
.
-
L
ó
p
e
z
,
“
M
a
z
e
s
o
l
v
i
n
g
mo
b
i
l
e
r
o
b
o
t
b
a
s
e
d
o
n
i
m
a
g
e
p
r
o
c
e
ssi
n
g
a
n
d
s
t
a
n
d
a
r
d
n
o
d
a
l
a
n
a
l
y
si
s
,
”
Fr
a
n
k
l
i
n
O
p
e
n
,
v
o
l
.
1
2
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
r
a
o
p
e
.
2
0
2
5
.
1
0
0
3
5
7
.
[
2
2
]
J.
W
e
n
e
t
a
l
.
,
“
A
c
c
u
r
a
c
y
a
n
d
c
l
i
n
i
c
a
l
a
p
p
l
i
c
a
t
i
o
n
p
r
o
sp
e
c
t
s
o
f
m
o
b
i
l
e
l
o
w
-
f
i
e
l
d
s
t
r
e
n
g
t
h
m
a
g
n
e
t
i
c
r
e
s
o
n
a
n
c
e
i
ma
g
i
n
g
i
n
t
h
e
d
i
a
g
n
o
si
s
o
f
h
y
d
r
o
c
e
p
h
a
l
u
s
:
a
r
e
t
r
o
s
p
e
c
t
i
v
e
c
o
h
o
r
t
st
u
d
y
,
”
Bra
i
n
Re
s
e
a
r
c
h
Bu
l
l
e
t
i
n
,
v
o
l
.
2
3
2
,
N
o
v
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
r
a
i
n
r
e
s
b
u
l
l
.
2
0
2
5
.
1
1
1
5
8
5
.
[
2
3
]
M
.
H
u
a
n
g
a
n
d
J
.
Z
h
u
,
“
A
f
a
s
t
i
m
a
g
e
r
e
c
o
g
n
i
t
i
o
n
me
t
h
o
d
o
f
m
o
b
i
l
e
p
o
i
n
t
r
a
d
i
o
a
c
t
i
v
e
s
o
u
r
c
e
b
a
s
e
d
o
n
se
q
u
e
n
t
i
a
l
b
a
y
e
s
i
a
n
a
n
a
l
y
si
s
,
”
Ra
d
i
a
t
i
o
n
P
h
y
s
i
c
s
a
n
d
C
h
e
m
i
st
ry
,
v
o
l
.
2
3
7
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
a
d
p
h
y
s
c
h
e
m.
2
0
2
5
.
1
1
3
0
6
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
n
d
r
o
id
-
b
a
s
ed
to
ma
to
le
a
f d
is
ea
s
e
cla
s
s
ifica
tio
n
u
s
in
g
a
lig
h
tw
eig
h
t Mo
b
ileN
etV
2
…
(
A
n
d
i R
ia
n
s
ya
h
)
3325
[
2
4
]
M
.
M
.
Y
a
p
i
c
i
,
“
A
n
o
v
e
l
i
ma
g
e
b
a
s
e
d
a
p
p
r
o
a
c
h
f
o
r
m
o
b
i
l
e
a
n
d
r
o
i
d
ma
l
w
a
r
e
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
s
t
e
m
s
,
v
o
l
.
3
2
3
,
Ju
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
2
5
.
1
1
3
8
5
5
.
[
2
5
]
D
.
K
.
N
.
H
o
e
t
a
l
.
,
“
M
i
t
i
g
a
t
i
n
g
e
r
r
o
r
s
i
n
mo
b
i
l
e
-
b
a
s
e
d
d
i
e
t
a
r
y
a
ss
e
ssm
e
n
t
s:
e
f
f
e
c
t
s
o
f
a
d
a
t
a
m
o
d
i
f
i
c
a
t
i
o
n
p
r
o
c
e
s
s
o
n
t
h
e
v
a
l
i
d
i
t
y
o
f
a
n
i
ma
g
e
-
a
ssi
s
t
e
d
f
o
o
d
a
n
d
n
u
t
r
i
t
i
o
n
a
p
p
,
”
N
u
t
ri
t
i
o
n
,
v
o
l
.
1
1
6
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
u
t
.
2
0
2
3
.
1
1
2
2
1
2
.
[
2
6
]
S
.
Ti
t
o
u
n
i
e
t
a
l
.
,
“
H
y
b
r
i
d
C
N
N
-
a
u
t
o
e
n
c
o
d
e
r
mo
d
e
l
f
o
r
a
c
c
u
r
a
t
e
a
n
d
e
f
f
i
c
i
e
n
t
f
a
u
l
t
d
i
a
g
n
o
s
i
s
i
n
g
r
i
d
-
c
o
n
n
e
c
t
e
d
p
h
o
t
o
v
o
l
t
a
i
c
sy
st
e
ms,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
P
o
w
e
r &
En
e
r
g
y
S
y
s
t
e
m
s
,
v
o
l
.
1
7
3
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
e
p
e
s
.
2
0
2
5
.
1
1
1
4
5
4
.
[
2
7
]
T.
P
.
T.
N
g
u
y
e
n
,
T
.
T.
N
g
u
y
e
n
,
H
.
Q
.
N
g
u
y
e
n
,
T.
D
.
N
g
u
y
e
n
,
C
.
K
.
N
g
u
y
e
n
,
a
n
d
N
.
G
.
C
u
,
“
A
n
e
n
h
a
n
c
e
d
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
mo
d
e
l
b
a
se
d
o
n
g
r
a
p
h
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
su
p
e
r
p
i
x
e
l
-
d
e
r
i
v
e
d
C
N
N
f
e
a
t
u
r
e
s
f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
d
a
t
a
se
t
s,
”
C
o
m
p
u
t
e
rs,
Ma
t
e
r
i
a
l
s
&
C
o
n
t
i
n
u
a
,
v
o
l
.
8
5
,
n
o
.
3
,
p
p
.
4
8
9
9
–
4
9
2
0
,
2
0
2
5
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc
.
2
0
2
5
.
0
6
7
7
0
7
.
[
2
8
]
J.
S
.
T
h
a
n
g
a
P
u
r
n
i
a
n
d
M
.
B
r
a
v
e
e
n
,
“
U
n
i
f
i
e
d
A
R
P
-
V
i
T
-
C
N
N
s
y
st
e
m:
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
seg
m
e
n
t
i
n
g
a
n
d
c
l
a
ss
i
f
y
i
n
g
mu
l
t
i
p
l
e
sk
i
n
c
a
n
c
e
r
l
e
s
i
o
n
s,”
Ar
ra
y
,
v
o
l
.
2
8
,
D
e
c
.
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
5
1
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
And
i
Ria
n
sy
a
h
is a l
e
c
tu
re
r
in
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s E
n
g
in
e
e
rin
g
,
F
a
c
u
l
ty
o
f
In
d
u
strial
Tec
h
n
o
lo
g
y
,
Un
iv
e
rsit
a
s
Isla
m
S
u
lt
a
n
Ag
u
n
g
,
S
e
m
a
ra
n
g
,
I
n
d
o
n
e
sia
.
He
p
rima
ry
e
x
p
e
rti
se
is
in
In
f
o
rm
a
ti
c
s,
p
a
rti
c
u
larly
a
rti
f
icia
l
in
tell
ig
e
n
c
e
,
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
c
o
m
p
u
ter
v
isio
n
fo
r
p
lan
t
d
ise
a
se
d
e
tec
ti
o
n
a
n
d
m
e
d
ica
l
d
iag
n
o
sis
.
He
a
lso
d
e
v
e
lo
p
s
a
rti
ficia
l
in
telli
g
e
n
c
e
-
b
a
se
d
c
h
a
t
b
o
ts
a
n
d
a
n
a
ly
z
e
s
p
u
b
l
ic
o
p
i
n
io
n
th
r
o
u
g
h
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
.
His
wo
rk
in
c
lu
d
e
s
Io
T,
f
u
z
z
y
lo
g
ic,
p
u
b
li
c
a
ti
o
n
s
,
a
n
d
p
a
te
n
ts
b
e
n
e
fit
i
n
g
h
e
a
lt
h
c
a
re
,
a
g
ricu
lt
u
re
,
a
n
d
S
M
Es.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
d
i@u
n
issu
l
a
.
a
c
.
id
.
Ir
fa
n
Ek
a
Ma
h
d
y
is
a
d
a
ta
a
n
d
m
a
c
h
in
e
lea
rn
in
g
e
n
t
h
u
sia
st
fr
o
m
S
e
m
a
ra
n
g
a
n
d
a
g
ra
d
u
a
te
o
f
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
c
s
En
g
in
e
e
ri
n
g
,
F
a
c
u
lt
y
o
f
I
n
d
u
strial
Tec
h
n
o
lo
g
y
,
Un
iv
e
rsitas
Isla
m
S
u
lt
a
n
Ag
u
n
g
,
S
e
m
a
ra
n
g
,
I
n
d
o
n
e
sia
.
His
i
n
te
re
sts
in
c
lu
d
e
d
a
ta
a
n
a
ly
sis,
m
a
c
h
in
e
lea
rn
in
g
,
An
d
ro
i
d
a
p
p
li
c
a
ti
o
n
s,
a
n
d
we
b
tec
h
n
o
l
o
g
ies
.
He
d
e
v
e
lo
p
s
d
a
ta
-
d
ri
v
e
n
we
b
p
latfo
rm
s
to
c
re
a
te
in
telli
g
e
n
t,
sc
a
lab
le
so
l
u
ti
o
n
s
fo
r
re
a
l
-
wo
rld
b
u
si
n
e
ss
a
n
d
so
c
ial
c
h
a
ll
e
n
g
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
irfa
n
e
k
a
m
@g
m
a
il
.
c
o
m
.
Mo
c
h
a
m
a
d
Abd
u
l
Ba
sir
i
s
a
lec
tu
re
r
i
n
th
e
M
a
th
e
m
a
ti
c
s
Ed
u
c
a
ti
o
n
S
tu
d
y
P
ro
g
ra
m
,
F
a
c
u
lt
y
o
f
Tea
c
h
e
r
Train
in
g
a
n
d
E
d
u
c
a
ti
o
n
,
U
n
iv
e
rsitas
Isla
m
S
u
lt
a
n
Ag
u
n
g
,
S
e
m
a
ra
n
g
.
His
e
x
p
e
rti
se
fo
c
u
se
s
o
n
m
a
th
e
m
a
ti
c
s
e
d
u
c
a
ti
o
n
,
n
u
m
e
ra
c
y
li
tera
c
y
,
a
lg
e
b
ra
ic
re
a
so
n
in
g
,
a
n
d
m
a
th
e
m
a
ti
c
s
a
n
x
iety
in
lea
rn
i
n
g
.
He
is
a
lso
a
c
ti
v
e
in
d
e
v
e
l
o
p
i
n
g
lea
rn
in
g
in
n
o
v
a
ti
o
n
s,
writi
n
g
sc
ien
ti
fic
p
u
b
li
c
a
ti
o
n
s
a
n
d
te
x
tb
o
o
k
s,
a
n
d
se
rv
in
g
a
s
a
p
e
e
r
re
v
iew
e
r
i
n
se
v
e
ra
l
a
c
a
d
e
m
ic fi
e
ld
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
b
d
u
l
b
a
sir@u
n
issu
la.ac
.
i
d
.
No
o
r
m
i
n
sha
h
A.
Ia
h
a
d
is
a
n
a
c
a
d
e
m
ic
a
t
th
e
De
p
a
rtme
n
t
o
f
Ap
p
li
e
d
Co
m
p
u
ti
n
g
a
n
d
Art
ifi
c
ial
I
n
telli
g
e
n
c
e
,
F
a
c
u
lt
y
o
f
C
o
m
p
u
t
in
g
,
Un
i
v
e
rsiti
Tek
n
o
lo
g
i
M
a
lay
sia
,
J
o
h
o
r
Ba
h
ru
,
M
a
lay
sia
.
S
h
e
is
a
re
c
o
g
n
ize
d
d
i
g
it
a
l
lea
d
e
r
a
n
d
wa
s
o
n
e
o
f
3
3
0
p
a
rti
c
i
p
a
n
ts
se
lec
ted
n
a
ti
o
n
a
ll
y
t
o
c
o
m
p
lete
th
e
Di
g
it
a
l
Lea
d
e
rsh
ip
Ex
p
e
rien
c
e
P
ro
g
ra
m
o
rg
a
n
ize
d
b
y
t
h
e
M
a
lay
sia
Co
m
m
u
n
ica
ti
o
n
s
a
n
d
M
u
lt
ime
d
ia
Co
m
m
issio
n
a
n
d
Hu
a
we
i.
S
h
e
c
u
rre
n
tl
y
se
rv
e
s
a
s
p
re
sid
e
n
t
o
f
th
e
As
so
c
iati
o
n
fo
r
I
n
fo
rm
a
ti
o
n
S
y
ste
m
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
in
sh
a
h
@u
tm.m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.