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.
1
5
,
No
.
2
,
A
p
r
il 2
0
2
6
,
p
p
.
1
7
8
3
~
1
7
8
9
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
7
8
3
-
1
7
8
9
1783
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
H
y
brid ma
chi
ne l
ea
rning
f
o
r imba
l
a
nced let
tuce
dise
a
se
cla
ss
ificatio
n
F
a
zlur
I
hza
nu
ra
hm
a
n,
Wa
y
a
n F
irda
us
M
a
hm
ud
y
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
c
s
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
B
r
a
w
i
j
a
y
a
U
n
i
v
e
r
si
t
y
,
M
a
l
a
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
2
8
,
2
0
2
4
R
ev
is
ed
Feb
9
,
2
0
2
6
Acc
ep
ted
Ma
r
5
,
2
0
2
6
Th
is
stu
d
y
i
n
v
e
sti
g
a
tes
a
h
y
b
r
id
m
a
c
h
in
e
lea
rn
in
g
fra
m
e
wo
rk
c
o
m
b
in
i
n
g
Eff
icie
n
tNe
t
-
B3
fe
a
tu
re
e
x
trac
ti
o
n
wit
h
c
las
sic
a
l
c
las
sifier
s
f
o
r
lettu
c
e
d
ise
a
se
c
las
sific
a
ti
o
n
u
n
d
e
r
c
o
n
d
it
io
n
s
o
f
e
x
trem
e
c
las
s
imb
a
la
n
c
e
.
Th
e
sy
ste
m
u
ti
li
z
e
s
Eff
icie
n
tNe
t
-
B
3
to
e
x
trac
t
h
i
g
h
-
d
ime
n
sio
n
a
l
fe
a
tu
re
e
m
b
e
d
d
in
g
s
fro
m
2
,
3
3
7
ima
g
e
s,
wh
ich
a
re
su
b
se
q
u
e
n
tl
y
c
las
sified
u
sin
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM),
r
a
n
d
o
m
fo
re
st
(R
F
),
a
n
d
k
-
n
e
a
re
st
n
e
ig
h
b
o
rs
(KN
N).
Alth
o
u
g
h
th
e
p
ro
p
o
se
d
S
VM
-
b
a
se
d
m
o
d
e
l
a
c
h
ie
v
e
s
a
h
i
g
h
o
v
e
ra
ll
a
c
c
u
ra
c
y
o
f
9
4
.
0
1
%
,
e
x
p
e
rime
n
t
a
l
re
su
lt
s
re
v
e
a
l
a
su
b
sta
n
ti
a
l
p
e
rfo
rm
a
n
c
e
d
isc
re
p
a
n
c
y
c
o
m
p
a
re
d
t
o
th
e
m
a
c
ro
F1
-
sc
o
re
o
f
3
7
.
9
4
%
.
T
h
is
c
rit
ica
l
g
a
p
in
d
ica
tes
th
a
t
wh
il
e
t
h
e
m
o
d
e
l
su
c
c
e
ss
fu
ll
y
id
e
n
ti
fies
th
e
m
a
jo
rit
y
c
las
se
s,
it
fa
il
s
to
re
c
o
g
n
ize
ra
re
d
ise
a
se
c
a
teg
o
ries
with
li
m
it
e
d
sa
m
p
les
.
Th
e
o
re
ti
c
a
l
a
n
a
ly
sis
su
g
g
e
sts
t
h
a
t
wh
il
e
S
V
M
h
a
n
d
les
h
ig
h
-
d
ime
n
si
o
n
a
l
fe
a
t
u
re
sp
a
c
e
s
m
o
re
e
ffe
c
ti
v
e
ly
t
h
a
n
RF
a
n
d
K
NN
,
th
e
d
e
e
p
fe
a
tu
re
s
e
x
trac
ted
a
re
b
ias
e
d
to
wa
rd
m
a
jo
rit
y
c
las
s
c
h
a
ra
c
teristics
.
Th
e
se
fin
d
in
g
s
h
i
g
h
li
g
h
t
th
e
se
v
e
re
lim
it
a
ti
o
n
s
o
f
a
c
c
u
ra
c
y
-
c
e
n
tri
c
e
v
a
lu
a
ti
o
n
i
n
a
g
ricu
lt
u
ra
l
d
iag
n
o
stics
a
n
d
d
e
m
o
n
stra
te
t
h
a
t
d
e
e
p
fe
a
tu
re
e
x
trac
ti
o
n
a
lo
n
e
is
i
n
su
ff
icie
n
t
t
o
g
u
a
ra
n
tee
ro
b
u
st
d
e
tec
ti
o
n
f
o
r
m
i
n
o
rit
y
p
a
t
h
o
l
o
g
ies
.
Th
e
st
u
d
y
c
o
n
c
lu
d
e
s
th
a
t
re
ly
in
g
o
n
a
g
g
re
g
a
te
a
c
c
u
ra
c
y
c
a
n
m
a
sk
d
iag
n
o
stic
fa
il
u
re
s,
e
m
p
h
a
siz
in
g
t
h
e
u
rg
e
n
t
n
e
e
d
fo
r
p
e
r
-
c
las
s
p
e
rfo
rm
a
n
c
e
a
n
a
ly
sis
a
n
d
d
a
ta
-
lev
e
l
m
it
i
g
a
ti
o
n
stra
teg
ies
in
fu
tu
re
re
se
a
rc
h
.
K
ey
w
o
r
d
s
:
Dee
p
f
ea
tu
r
e
e
x
tr
ac
tio
n
E
f
f
icien
tNet
-
B3
Hy
b
r
id
m
ac
h
in
e
lear
n
i
n
g
L
ettu
ce
d
is
ea
s
e
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
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
:
W
ay
an
Fird
au
s
Ma
h
m
u
d
y
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
C
o
m
p
u
te
r
Scien
ce
,
B
r
awijay
a
Un
iv
er
s
ity
St.
Vete
r
an
No
.
1
0
-
1
1
,
Keta
wa
n
g
g
ed
e
,
L
o
wo
k
war
u
,
Ma
lan
g
6
5
1
4
5
,
I
n
d
o
n
esia
E
m
ail: w
ay
an
f
m
@
u
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Ag
r
icu
ltu
r
al
p
r
o
d
u
ctiv
ity
is
o
f
ten
co
m
p
r
o
m
is
ed
b
y
p
lan
t
d
i
s
ea
s
es,
wh
ich
n
eg
ativ
ely
af
f
ec
t
b
o
th
th
e
q
u
ality
an
d
q
u
a
n
tity
o
f
cr
o
p
y
ield
s
.
L
ettu
ce
(
La
ctu
ca
s
a
tiva
L.
)
,
in
p
ar
ticu
lar
,
is
h
ig
h
ly
s
u
s
ce
p
tib
le
to
a
r
a
n
g
e
o
f
p
ath
o
g
en
s
,
in
clu
d
in
g
b
ac
te
r
ia,
f
u
n
g
i,
a
n
d
v
ir
u
s
es
[
1
]
.
T
h
ese
in
f
ec
tio
n
s
ca
n
r
esu
lt
in
s
u
b
s
tan
tial
f
in
an
cial
lo
s
s
es
f
o
r
f
ar
m
er
s
an
d
p
o
s
e
b
r
o
ad
er
r
is
k
s
to
ag
r
icu
ltu
r
al
s
ec
to
r
.
As
s
u
ch
,
th
e
a
b
ilit
y
to
d
etec
t
p
lan
t
d
is
ea
s
es
ea
r
ly
an
d
ac
c
u
r
ately
is
ess
en
tial to
ef
f
ec
tiv
ely
m
a
n
ag
e
th
ei
r
s
p
r
ea
d
an
d
r
ed
u
ce
ass
o
ciate
d
d
am
ag
es
[
2
]
.
R
ec
en
t
ad
v
an
ce
m
en
ts
in
m
ac
h
in
e
lear
n
in
g
an
d
im
ag
e
p
r
o
c
ess
in
g
h
av
e
o
p
en
ed
u
p
n
ew
p
o
s
s
ib
ilit
ie
s
f
o
r
au
t
o
m
atin
g
p
lan
t
d
is
ea
s
e
d
etec
tio
n
,
with
e
n
co
u
r
ag
in
g
o
u
tco
m
es
[
3
]
.
T
h
ese
tech
n
i
q
u
es
ar
e
ca
p
a
b
le
o
f
h
an
d
lin
g
lar
g
e
d
atasets
an
d
co
n
d
u
ctin
g
in
tr
icate
an
aly
s
es
to
u
n
co
v
e
r
p
atter
n
s
th
at
ar
e
o
f
ten
u
n
d
etec
tab
le
b
y
h
u
m
an
o
b
s
er
v
atio
n
.
Am
o
n
g
t
h
e
v
ar
io
u
s
ap
p
r
o
ac
h
es,
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
s
tan
d
o
u
t
as
h
ig
h
ly
ef
f
ec
tiv
e
f
o
r
im
ag
e
c
lass
if
icatio
n
[
4
]
,
[
5
]
.
C
NNs
ex
ce
l
at
au
to
n
o
m
o
u
s
ly
lear
n
i
n
g
im
ag
e
f
ea
tu
r
es
th
r
o
u
g
h
s
tack
ed
co
n
v
o
l
u
tio
n
al
lay
er
s
,
wh
ich
m
ak
es
th
e
m
p
a
r
ticu
lar
ly
well
-
s
u
ited
f
o
r
task
s
in
v
o
lv
in
g
p
atter
n
r
ec
o
g
n
itio
n
an
d
v
is
u
al
ca
teg
o
r
izatio
n
[
6
]
,
[
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.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
7
8
3
-
1
7
8
9
1784
Alth
o
u
g
h
C
NN
ar
e
h
ig
h
ly
ef
f
ec
tiv
e,
th
eir
class
if
icatio
n
ac
cu
r
ac
y
ca
n
b
e
en
h
a
n
ce
d
b
y
c
o
m
b
in
in
g
th
em
with
co
n
v
en
tio
n
al
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
lik
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SV
M
)
,
r
an
d
o
m
f
o
r
ests
(
R
F)
,
an
d
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN
)
[
8
]
.
SVM
aim
s
to
co
n
s
tr
u
ct
an
o
p
tim
al
h
y
p
er
p
lan
e
th
at
s
ep
ar
ates
d
ata
p
o
in
ts
b
elo
n
g
in
g
to
d
if
f
er
e
n
t
class
es,
an
d
it
h
as
s
h
o
wn
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
n
u
m
er
o
u
s
class
if
icatio
n
task
s
[
9
]
,
[
1
0
]
.
RF
,
a
ty
p
e
o
f
en
s
em
b
le
m
eth
o
d
,
lev
er
a
g
es
m
u
ltip
le
d
ec
is
io
n
tr
ee
s
to
en
h
an
ce
ac
cu
r
ac
y
an
d
m
in
im
ize
o
v
er
f
itti
n
g
,
o
f
f
er
in
g
a
r
o
b
u
s
t
s
o
lu
tio
n
f
o
r
class
if
ic
atio
n
p
r
o
b
lem
s
[
1
1
]
.
Me
an
wh
ile,
KNN
cla
s
s
if
ie
s
d
ata
b
ased
o
n
th
e
p
r
o
x
im
ity
o
f
n
eig
h
b
o
r
in
g
in
s
tan
ce
s
an
d
is
wid
ely
ad
o
p
ted
d
u
e
to
its
ea
s
e
o
f
im
p
lem
en
tatio
n
an
d
ef
f
ec
tiv
e
n
ess
[
1
2
]
.
Nu
m
er
o
u
s
C
NN
ar
ch
itectu
r
es
h
av
e
b
ee
n
d
ev
elo
p
ed
,
ea
ch
tailo
r
ed
to
o
f
f
er
s
p
ec
if
ic
ad
v
an
tag
es
in
im
ag
e
class
if
icatio
n
task
s
.
E
f
f
icien
tNet
ar
ch
itectu
r
es
h
av
e
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
in
v
ar
io
u
s
p
lan
t
d
is
ea
s
e
class
if
icatio
n
task
s
,
s
u
ch
as
in
p
o
tato
an
d
m
an
g
o
c
r
o
p
s
[
1
3
]
.
Mo
tiv
ated
b
y
th
is
s
u
cc
ess
,
th
is
r
esear
ch
in
v
esti
g
ates
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
E
f
f
icien
tNet
-
B
3
m
o
d
el
in
co
m
b
i
n
atio
n
with
th
r
ee
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
—
SV
M,
RF
,
an
d
KNN
—
f
o
r
d
is
ea
s
e
d
et
ec
tio
n
in
lettu
ce
p
lan
ts
.
E
f
f
icien
tNet
r
ep
r
esen
ts
a
m
o
d
er
n
C
NN
d
esig
n
t
h
at
b
a
lan
ce
s
co
m
p
u
tatio
n
al
co
s
t
a
n
d
p
r
e
d
ictiv
e
ac
c
u
r
ac
y
b
y
em
p
lo
y
in
g
co
m
p
o
u
n
d
s
ca
lin
g
,
wh
ich
s
im
u
ltan
eo
u
s
l
y
ad
ju
s
ts
th
e
m
o
d
el’
s
d
e
p
th
,
wid
th
,
an
d
in
p
u
t
r
eso
lu
tio
n
[
1
4
]
.
T
h
r
o
u
g
h
th
is
h
y
b
r
id
a
p
p
r
o
ac
h
,
th
e
s
tu
d
y
ai
m
s
to
d
eter
m
in
e
wh
eth
er
th
e
in
teg
r
ated
m
o
d
el
d
eliv
er
s
s
u
p
er
io
r
class
if
icatio
n
p
er
f
o
r
m
an
ce
co
m
p
a
r
ed
to
u
s
in
g
E
f
f
icien
tNet
-
B
3
alo
n
e.
T
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
in
te
n
d
ed
to
s
u
p
p
o
r
t
th
e
ad
v
an
ce
m
e
n
t
o
f
m
o
r
e
ac
cu
r
at
e
an
d
ef
f
icien
t
tech
n
i
q
u
es
f
o
r
d
etec
tin
g
p
lan
t
d
is
ea
s
es.
Mo
r
e
o
v
er
,
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
h
o
ld
s
p
o
ten
tial
f
o
r
p
r
ac
tical
ap
p
licatio
n
in
ag
r
icu
ltu
r
e,
o
f
f
er
in
g
a
to
o
l
th
at
co
u
l
d
ass
is
t
f
ar
m
er
s
in
m
o
n
ito
r
in
g
cr
o
p
h
ea
lth
a
n
d
im
p
r
o
v
in
g
d
is
ea
s
e
m
an
ag
em
e
n
t stra
teg
ies
[
1
5
]
,
[
1
6
]
.
Sev
er
al
r
ec
en
t
s
tu
d
ies
h
av
e
h
i
g
h
lig
h
ted
th
e
p
o
ten
tial
o
f
co
m
b
in
in
g
E
f
f
icien
tNet
with
ad
v
a
n
ce
d
d
ee
p
lear
n
in
g
s
tr
ateg
ies
to
en
h
an
ce
th
e
p
r
ec
is
io
n
o
f
p
lan
t
d
is
ea
s
e
d
etec
tio
n
[
1
7
]
,
[
1
8
]
.
E
x
ten
s
iv
e
p
r
io
r
wo
r
k
also
s
u
p
p
o
r
ts
th
e
ef
f
ec
tiv
en
ess
o
f
C
NN
-
b
ased
m
o
d
els
f
o
r
th
is
ta
s
k
[
1
9
]
.
C
NNs
h
av
e
b
ee
n
b
r
o
ad
ly
ad
o
p
ted
in
th
e
class
if
icatio
n
o
f
p
lan
t
d
is
ea
s
e
s
,
p
ar
ticu
lar
ly
u
s
in
g
leaf
im
a
g
er
y
as
th
e
p
r
im
ar
y
in
p
u
t.
R
ev
iews
in
th
e
f
ield
co
n
s
is
ten
tly
s
h
o
w
th
at
C
NNs
o
u
tp
er
f
o
r
m
tr
a
d
itio
n
al
class
if
icatio
n
tech
n
iq
u
es,
lar
g
ely
b
ec
au
s
e
o
f
th
eir
s
u
p
er
io
r
ca
p
a
b
ilit
y
to
ca
p
t
u
r
e
i
n
tr
icate
p
atter
n
s
an
d
f
ea
tu
r
es f
r
o
m
im
ag
es
[
1
4
]
.
A
r
c
h
i
t
e
ct
u
r
e
s
s
u
c
h
as
V
GG
1
6
,
R
es
N
e
t
,
a
n
d
E
f
f
i
c
ie
n
t
N
e
t
h
av
e
b
e
e
n
w
i
d
e
l
y
u
ti
l
iz
e
d
i
n
p
l
an
t
d
i
s
e
ase
c
l
a
s
s
i
f
ic
a
t
i
o
n
t
as
k
s
.
W
h
i
l
e
VG
G
1
6
a
n
d
R
e
s
N
e
t
a
r
e
r
e
c
o
g
n
i
z
e
d
f
o
r
t
h
e
i
r
h
i
g
h
c
l
a
s
s
i
f
i
c
at
i
o
n
a
c
c
u
r
a
c
y
,
t
h
e
i
r
i
m
p
l
e
m
e
n
t
a
ti
o
n
o
f
t
e
n
d
e
m
a
n
d
s
c
o
n
s
i
d
e
r
a
b
l
e
c
o
m
p
u
t
a
ti
o
n
a
l
p
o
w
e
r
[
2
0
]
.
In
c
o
n
t
r
a
s
t
,
E
f
f
i
ci
e
n
t
N
e
t
p
r
es
e
n
ts
a
m
o
r
e
r
e
s
o
u
r
c
e
-
e
f
f
i
c
i
e
n
t
a
l
te
r
n
at
i
v
e
.
R
e
c
e
n
t
s
t
u
d
i
es
h
a
v
e
a
l
s
o
s
h
o
w
n
t
h
a
t
c
o
m
b
i
n
i
n
g
E
f
f
i
c
i
e
n
t
N
e
t
w
it
h
a
t
t
e
n
ti
o
n
m
e
c
h
a
n
i
s
m
s
c
a
n
f
u
r
t
h
e
r
e
n
h
a
n
c
e
b
o
t
h
a
c
c
u
r
a
c
y
a
n
d
i
n
t
e
r
p
r
e
t
a
b
i
l
it
y
i
n
p
la
n
t
d
is
e
as
e
d
e
t
ec
t
i
o
n
t
as
k
s
[
2
1
]
.
B
y
u
t
i
l
i
zi
n
g
c
o
m
p
o
u
n
d
s
c
a
l
i
n
g
t
o
a
d
j
u
s
t
n
e
tw
o
r
k
d
i
m
e
n
s
i
o
n
s
i
n
a
b
a
l
a
n
c
e
d
m
a
n
n
e
r
,
E
f
f
i
c
i
e
n
t
Ne
t a
c
h
i
e
v
e
s
i
m
p
r
o
v
e
d
p
e
r
f
o
r
m
a
n
c
e
i
n
t
e
r
m
s
o
f
b
o
t
h
ef
f
i
c
i
e
n
c
y
a
n
d
a
c
c
u
r
a
c
y
c
o
m
p
a
r
e
d
t
o
e
a
r
l
i
e
r
C
NN
m
o
d
e
l
s
[
1
5
]
.
T
h
e
ap
p
licatio
n
o
f
E
f
f
icien
tN
et
in
p
lan
t
d
is
ea
s
e
id
en
tific
atio
n
h
as
s
h
o
wn
co
n
s
is
ten
tly
h
ig
h
lev
els
o
f
ac
cu
r
ac
y
ac
r
o
s
s
v
ar
io
u
s
s
tu
d
ie
s
[
2
2
]
.
On
e
n
o
ta
b
le
ex
am
p
le
is
its
u
s
e
in
class
if
y
in
g
ap
p
le
l
ea
f
d
is
ea
s
es,
wh
er
e
it
d
em
o
n
s
tr
ated
ex
ce
p
tio
n
al
p
er
f
o
r
m
a
n
ce
,
f
u
r
th
e
r
v
alid
atin
g
its
r
eliab
ilit
y
an
d
s
u
itab
ilit
y
f
o
r
d
is
ea
s
e
d
etec
tio
n
in
ag
r
ic
u
ltu
r
al
c
o
n
tex
ts
[
2
3
]
,
[
2
4
]
.
Fu
r
th
er
m
o
r
e,
a
r
ec
en
t
s
tu
d
y
d
e
m
o
n
s
tr
ated
th
at
E
f
f
i
cien
tNet
p
er
f
o
r
m
ed
r
o
b
u
s
tly
in
m
u
lti
-
cr
o
p
d
is
ea
s
e
class
if
icatio
n
s
ce
n
ar
io
s
,
h
ig
h
li
g
h
tin
g
its
s
ca
lab
ilit
y
an
d
ac
cu
r
ac
y
ac
r
o
s
s
d
iv
er
s
e
p
lan
t ty
p
es
[
2
5
]
.
T
h
is
r
esear
ch
ex
p
l
o
r
es
th
e
i
n
teg
r
atio
n
o
f
th
e
E
f
f
icien
tNe
t
-
B
3
ar
ch
itectu
r
e
with
th
r
ee
tr
ad
itio
n
al
class
if
icatio
n
alg
o
r
ith
m
s
SVM,
RF
,
an
d
KNN
,
to
ass
ess
p
o
ten
tial
g
ain
s
in
class
if
icati
o
n
ac
cu
r
ac
y
.
T
h
ese
m
eth
o
d
s
ar
e
wid
ely
em
p
lo
y
ed
in
m
ac
h
in
e
lear
n
in
g
f
o
r
th
eir
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
.
SVM
f
u
n
ctio
n
s
b
y
co
n
s
tr
u
ctin
g
a
n
o
p
tim
al
d
ec
is
i
o
n
b
o
u
n
d
ar
y
to
d
is
tin
g
u
is
h
b
e
twee
n
class
es
[
9
]
.
RF
,
wh
ich
ag
g
r
eg
ates
m
u
ltip
le
d
ec
is
io
n
tr
ee
s
,
is
ef
f
ec
tiv
e
in
b
o
o
s
tin
g
ac
cu
r
ac
y
an
d
m
iti
g
atin
g
o
v
e
r
f
itti
n
g
is
s
u
es
[
1
1
]
.
I
t
h
as
also
b
ee
n
p
r
ev
io
u
s
ly
a
p
p
lied
in
p
la
n
t
d
is
ea
s
e
clas
s
if
icatio
n
,
s
er
v
in
g
as
a
s
o
lid
b
en
ch
m
ar
k
f
o
r
ev
alu
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
m
o
r
e
r
ec
en
t
m
o
d
els
lik
e
E
f
f
icien
tNet
[
2
6
]
.
Me
an
wh
ile,
KNN
d
eter
m
i
n
e
s
class
m
em
b
er
s
h
ip
b
ased
o
n
p
r
o
x
im
ity
to
n
eig
h
b
o
r
in
g
s
am
p
les
an
d
r
em
ain
s
a
s
tr
aig
h
tf
o
r
war
d
y
et
ef
f
e
ctiv
e
tech
n
iq
u
e
f
o
r
class
if
icatio
n
task
s
[
1
2
]
.
Desp
ite
th
e
wid
esp
r
ea
d
ad
o
p
tio
n
o
f
C
NN
-
b
ased
m
o
d
els
f
o
r
p
lan
t
d
is
ea
s
e
class
if
icat
io
n
,
m
o
s
t
ex
is
tin
g
s
tu
d
ies
r
ely
o
n
b
alan
ce
d
d
atasets
an
d
em
p
h
asize
o
v
er
all
ac
cu
r
ac
y
,
with
lim
ited
atten
tio
n
to
m
i
n
o
r
it
y
d
is
ea
s
e
class
e
s
.
C
o
n
s
eq
u
en
tly
,
th
e
r
eliab
ilit
y
o
f
th
ese
m
o
d
els
in
r
ea
l
-
wo
r
ld
,
h
ig
h
l
y
im
b
alan
ce
d
ag
r
ic
u
ltu
r
al
s
ce
n
ar
io
s
r
em
ain
s
in
s
u
f
f
icien
tly
ex
p
lo
r
ed
.
C
u
r
r
en
t
liter
atu
r
e
o
f
ten
o
v
er
lo
o
k
s
th
e
r
is
k
th
at
h
ig
h
ac
cu
r
ac
y
m
etr
ics m
ay
m
ask
th
e
m
o
d
el'
s
co
m
p
lete
f
ailu
r
e
in
d
etec
tin
g
r
ar
e
b
u
t c
r
itical
p
ath
o
lo
g
ies.
T
h
is
s
tu
d
y
p
r
o
v
id
es
an
em
p
ir
i
ca
l
an
aly
s
is
o
f
th
e
lim
itat
io
n
s
o
f
h
y
b
r
id
d
ee
p
f
ea
tu
r
e
ex
tr
ac
tio
n
m
o
d
els
wh
en
ap
p
lied
to
h
ig
h
l
y
im
b
a
lan
ce
d
lettu
ce
d
is
ea
s
e
d
atase
ts
.
I
t
o
f
f
er
s
cr
itical
in
s
ig
h
ts
in
to
th
e
m
is
m
atch
b
etwe
en
r
e
p
o
r
ted
ac
cu
r
ac
y
a
n
d
ac
tu
al
d
iag
n
o
s
tic
r
eliab
ilit
y
.
Sp
ec
if
ically
,
it
e
v
alu
ates
t
h
e
p
e
r
f
o
r
m
an
ce
o
f
E
f
f
icien
tNet
-
B
3
f
ea
tu
r
es
co
m
b
in
ed
with
SVM,
RF
,
an
d
KNN
cla
s
s
if
ier
s
,
an
aly
zin
g
h
o
w
ex
tr
em
e
class
im
b
alan
ce
d
is
to
r
ts
ev
alu
atio
n
m
etr
ics an
d
af
f
ec
ts
th
e
d
e
cisi
o
n
b
o
u
n
d
ar
ies o
f
d
if
f
e
r
en
t c
lass
ical
alg
o
r
ith
m
s
.
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
Hyb
r
id
ma
ch
in
e
lea
r
n
in
g
fo
r
imb
a
la
n
ce
d
lettu
ce
d
is
ea
s
e
cla
s
s
ifica
tio
n
(
F
a
z
lu
r
I
h
z
a
n
u
r
a
h
ma
n
)
1785
2.
M
E
T
H
O
D
T
h
is
s
tu
d
y
em
p
lo
y
s
th
e
E
f
f
ici
en
tNet
-
B
3
ar
ch
itectu
r
e
as
a
f
e
atu
r
e
ex
tr
ac
to
r
,
wh
ic
h
is
th
en
in
teg
r
ated
with
th
r
ee
class
ical
m
ac
h
in
e
l
ea
r
n
in
g
class
if
ier
s
SVM,
RF
,
an
d
KNN
to
co
n
s
tr
u
ct
h
y
b
r
id
m
o
d
els.
A
s
tr
atif
ied
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
s
ch
em
e
is
u
s
ed
to
en
s
u
r
e
th
at
th
e
p
r
o
p
o
r
tio
n
al
d
is
tr
ib
u
tio
n
o
f
clas
s
es
is
p
r
eser
v
ed
in
ev
er
y
f
o
ld
.
T
h
is
ap
p
r
o
ac
h
r
ed
u
ce
s
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
a
n
d
p
r
o
v
id
es
a
m
o
r
e
r
eliab
le
esti
m
atio
n
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
,
p
ar
ticu
lar
ly
g
iv
e
n
th
e
im
b
alan
ce
d
n
atu
r
e
o
f
th
e
d
ataset.
2
.
1
.
Da
t
a
s
et
T
h
is
s
t
u
d
y
u
ti
liz
e
d
t
h
e
let
tu
ce
d
is
e
ase
d
atas
et
s
o
u
r
ce
d
f
r
o
m
K
a
g
g
le
,
w
h
ic
h
i
n
cl
u
d
es
a
d
iv
e
r
s
e
co
l
le
cti
o
n
o
f
im
a
g
es
r
e
p
r
es
en
t
in
g
b
o
t
h
h
ea
lt
h
y
a
n
d
d
is
e
ase
d
lett
u
c
e
l
ea
v
es
.
T
h
e
d
a
tase
t
c
o
n
tai
n
s
2
,
3
3
7
i
m
a
g
es
o
f
let
tu
ce
d
is
ea
s
es
ca
te
g
o
r
i
ze
d
i
n
t
o
ei
g
h
t
class
es:
h
e
alt
h
y
(
1
,
1
2
3
im
a
g
es
)
,
S
h
ep
h
e
r
d
’
s
p
u
r
s
e
w
ee
d
s
(
1
,
1
0
6
)
,
d
o
wn
y
m
i
ld
ew
o
n
l
ett
u
c
e
(
3
0
)
,
b
a
ct
er
i
al
in
f
e
cti
o
n
(
2
0
)
,
s
ep
t
o
r
i
a
b
li
g
h
t
(
1
9
)
,
p
o
w
d
er
y
m
il
d
e
w
(
1
8
)
,
v
i
r
a
l
in
f
e
cti
o
n
(
1
5
)
,
a
n
d
wilt
a
n
d
le
af
b
l
ig
h
t
(
6
)
.
T
h
e
d
is
tr
i
b
u
ti
o
n
i
s
h
i
g
h
l
y
i
m
b
al
an
ce
d
,
wi
th
tw
o
class
es
a
cc
o
u
n
ti
n
g
f
o
r
m
o
r
e
th
a
n
9
5
%
o
f
all
s
a
m
p
les
,
w
h
il
e
s
e
v
e
r
al
d
is
ea
s
e
c
at
eg
o
r
ies
c
o
n
tai
n
f
ew
er
th
a
n
2
0
i
m
a
g
es.
T
h
is
im
b
al
an
ce
i
n
t
r
o
d
u
ce
s
a
s
i
g
n
i
f
ica
n
t
r
is
k
o
f
b
iase
d
l
ea
r
n
i
n
g
,
w
h
e
r
e
m
o
d
els
m
ay
ac
h
i
ev
e
h
i
g
h
ac
c
u
r
a
cy
b
y
p
r
io
r
i
tiz
in
g
m
aj
o
r
i
ty
c
lass
es
wh
i
le
p
er
f
o
r
m
i
n
g
p
o
o
r
l
y
o
n
m
i
n
o
r
i
ty
d
is
e
ase
ca
te
g
o
r
i
es.
T
h
e
d
a
tase
t
i
n
cl
u
d
es
v
a
r
i
ati
o
n
s
i
n
le
af
t
e
x
t
u
r
e,
li
g
h
ti
n
g
,
a
n
d
b
a
c
k
g
r
o
u
n
d
c
o
n
d
i
ti
o
n
s
,
f
u
r
th
er
i
n
c
r
e
asi
n
g
co
m
p
le
x
i
ty
o
f
cl
ass
i
f
ic
ati
o
n
.
2
.
2
.
P
re
pro
ce
s
s
ing
All
im
ag
es
wer
e
r
esized
to
2
2
4
×2
2
4
p
i
x
els
to
m
atch
E
f
f
icien
tNet
-
B
3
in
p
u
t
r
e
q
u
ir
em
en
ts
an
d
n
o
r
m
alize
d
to
a
[
0
,
1
]
r
an
g
e.
No
ag
g
r
ess
iv
e
au
g
m
en
tatio
n
was
ap
p
lied
to
av
o
i
d
cr
ea
tin
g
u
n
r
ea
lis
tic
s
am
p
les
f
o
r
m
in
o
r
ity
class
es.
I
n
s
tead
,
d
ata
b
alan
cin
g
was h
an
d
led
th
r
o
u
g
h
c
r
o
s
s
-
v
alid
atio
n
a
n
d
clas
s
weig
h
ts
.
2
.
3
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
E
f
f
icien
tNet
-
B
3
was
u
s
ed
as
a
f
ix
ed
f
ea
tu
r
e
ex
t
r
ac
to
r
.
T
h
e
m
o
d
el
was
l
o
ad
ed
with
I
m
ag
eNe
t
weig
h
ts
,
an
d
all
lay
e
r
s
wer
e
f
r
o
ze
n
.
T
h
e
o
u
tp
u
t
was
tak
en
f
r
o
m
th
e
f
in
al
co
n
v
o
lu
tio
n
al
b
lo
ck
f
o
llo
wed
b
y
g
lo
b
al
av
e
r
ag
e
p
o
o
lin
g
,
r
esu
lti
n
g
in
a
1
,
5
3
6
-
d
im
en
s
io
n
al
f
ea
tu
r
e
v
ec
to
r
f
o
r
ea
ch
im
ag
e.
T
h
ese
f
ea
tu
r
e
v
ec
to
r
s
wer
e
th
en
n
o
r
m
alize
d
u
s
in
g
Stan
d
ar
d
Scaler
b
ef
o
r
e
b
ein
g
f
o
r
war
d
ed
in
to
t
h
e
class
if
icatio
n
m
o
d
els.
2
.
4
.
H
y
brid
cla
s
s
if
ica
t
io
n mo
dels
(
SVM
,
RF
,
a
nd
K
NN)
T
h
r
ee
class
ical
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
wer
e
in
teg
r
at
ed
with
E
f
f
icien
tNet
-
B
3
f
ea
t
u
r
es:
SVM
(
r
ad
ial
b
asis
f
u
n
ctio
n
o
r
R
B
F
k
er
n
el)
,
R
F
(
2
0
0
tr
ee
s
,
m
a
x
i
m
u
m
d
e
p
th
=
n
o
n
e
)
,
an
d
KN
N
(
k
=
5
,
E
u
cli
d
ea
n
d
is
tan
ce
)
.
T
h
e
im
p
lem
en
tati
o
n
was
co
n
d
u
cted
u
s
in
g
t
h
e
Scik
it
-
lear
n
lib
r
ar
y
in
Py
th
o
n
to
en
s
u
r
e
r
ep
r
o
d
u
cib
ilit
y
.
T
h
ese
m
o
d
e
ls
wer
e
s
elec
ted
d
u
e
to
th
eir
ab
ilit
y
to
h
an
d
le
h
ig
h
-
d
im
en
s
io
n
al
f
ea
tu
r
e
em
b
ed
d
in
g
s
an
d
p
r
o
v
i
d
e
s
tr
o
n
g
b
aselin
e
p
er
f
o
r
m
a
n
ce
with
lim
ited
tr
ain
in
g
d
ata.
2
.
5
.
H
a
nd
lin
g
da
t
a
s
et
im
ba
l
a
nce
T
o
m
itig
ate
th
e
im
p
ac
t
o
f
s
ev
er
e
class
im
b
alan
ce
,
s
tr
atif
ied
s
am
p
lin
g
was
ap
p
lied
in
all
tr
ain
in
g
an
d
v
alid
atio
n
s
p
lits
to
p
r
eser
v
e
t
h
e
o
r
ig
in
al
lab
el
d
is
tr
ib
u
tio
n
.
W
eig
h
ted
lo
s
s
f
u
n
ctio
n
s
wer
e
im
p
lem
en
ted
f
o
r
SVM
,
an
d
class
-
b
alan
ce
d
s
am
p
lin
g
was
u
s
ed
d
u
r
in
g
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
is
s
tr
ateg
y
en
s
u
r
es
th
at
m
in
o
r
it
y
class
es c
o
n
tr
ib
u
te
p
r
o
p
o
r
tio
n
al
ly
d
u
r
in
g
tr
ain
in
g
an
d
ev
alu
ati
o
n
.
2
.
6
.
Str
a
t
if
ied 5
-
f
o
ld
cr
o
s
s
-
v
a
lid
a
t
io
n
A
s
tr
atif
ied
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
p
r
o
ce
d
u
r
e
was
im
p
lem
e
n
ted
to
en
s
u
r
e
f
air
an
d
r
o
b
u
s
t
ev
alu
atio
n
.
I
n
ea
ch
f
o
ld
,
8
0
%
o
f
t
h
e
d
ata
was
u
s
ed
f
o
r
tr
ain
i
n
g
an
d
2
0
%
f
o
r
test
in
g
,
p
r
eser
v
in
g
th
e
d
is
tr
ib
u
tio
n
o
f
ea
ch
class
.
No
im
ag
e
f
r
o
m
th
e
s
am
e
class
s
u
b
s
et
was
allo
wed
to
ap
p
ea
r
in
b
o
t
h
tr
ain
in
g
a
n
d
test
in
g
p
ar
titi
o
n
s
,
p
r
ev
en
tin
g
d
ata
leak
a
g
e.
Mo
d
el
p
er
f
o
r
m
an
ce
was r
ep
o
r
ted
a
s
m
ea
n
an
d
s
tan
d
a
r
d
d
e
v
iatio
n
ac
r
o
s
s
all
f
o
ld
s
.
2
.
7
.
E
v
a
lua
t
i
o
n
m
et
rics
Du
e
to
th
e
h
ig
h
ly
im
b
alan
ce
d
d
ataset,
m
u
ltip
le
ev
alu
atio
n
m
etr
ics
wer
e
u
s
ed
,
in
clu
d
in
g
ac
cu
r
ac
y
,
m
ac
r
o
F1
,
a
n
d
weig
h
ted
F1
.
Acc
u
r
ac
y
alo
n
e
is
in
s
u
f
f
icien
t
f
o
r
im
b
alan
ce
d
d
atasets
b
ec
au
s
e
it
m
ay
b
e
d
o
m
in
ated
b
y
m
ajo
r
ity
class
es.
Ma
cr
o
F1
tr
ea
ts
all
class
e
s
eq
u
ally
an
d
is
th
er
e
f
o
r
e
a
m
o
r
e
r
eliab
le
in
d
icato
r
o
f
p
er
f
o
r
m
a
n
ce
o
n
m
in
o
r
ity
d
i
s
ea
s
e
ca
teg
o
r
ies.
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
in
d
icate
th
at
SVM
ac
h
iev
es
th
e
h
ig
h
est
p
er
f
o
r
m
an
ce
am
o
n
g
th
e
th
r
ee
class
if
ier
s
,
b
ased
o
n
b
o
th
ac
cu
r
ac
y
an
d
F1
-
s
co
r
e.
Ho
wev
er
,
a
s
u
b
s
tan
tial
d
is
cr
ep
an
cy
is
o
b
s
er
v
ed
b
etwe
en
ac
cu
r
ac
y
an
d
m
ac
r
o
F1
-
s
co
r
es
ac
r
o
s
s
all
m
o
d
els,
h
ig
h
lig
h
tin
g
th
e
s
tr
o
n
g
im
p
ac
t
o
f
class
im
b
alan
ce
with
in
th
e
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.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
7
8
3
-
1
7
8
9
1786
d
ataset.
C
o
n
s
eq
u
en
tly
,
th
e
in
ter
p
r
etatio
n
o
f
r
esu
lts
em
p
h
asizes
n
o
t
o
n
ly
ac
cu
r
ac
y
b
u
t
also
class
-
lev
el
p
er
f
o
r
m
an
ce
,
s
u
p
p
o
r
te
d
b
y
co
n
f
u
s
io
n
m
atr
ices a
n
d
d
etailed
F1
-
s
co
r
e
an
aly
s
is
.
3
.
1
.
E
f
f
icient
Net
-
B
3
f
e
a
t
ure
ex
t
ra
ct
io
n r
esu
lt
E
f
f
icien
tNet
-
B
3
s
u
cc
ess
f
u
lly
ex
tr
ac
ted
1
,
5
3
6
-
d
im
en
s
io
n
al
f
ea
tu
r
e
v
ec
to
r
s
f
o
r
ea
ch
o
f
2
,
3
3
7
im
ag
es.
T
h
e
em
b
ed
d
in
g
s
ca
p
t
u
r
ed
lea
f
tex
tu
r
e,
c
o
lo
r
v
ar
iatio
n
,
an
d
lesi
o
n
p
atter
n
s
,
f
o
r
m
in
g
a
r
o
b
u
s
t
r
ep
r
esen
tatio
n
f
o
r
d
o
wn
s
tr
ea
m
class
if
icatio
n
.
Af
ter
n
o
r
m
aliza
tio
n
u
s
in
g
Stan
d
ar
d
Scaler
,
th
e
f
ea
tu
r
e
d
is
tr
ib
u
tio
n
s
ac
r
o
s
s
f
o
ld
s
wer
e
co
n
s
is
ten
t,
in
d
icatin
g
th
at
E
f
f
icien
tNet
-
B
3
p
r
o
v
id
ed
s
tab
le
h
ig
h
-
lev
el
r
ep
r
esen
tatio
n
s
r
eg
ar
d
less
o
f
d
ata
s
p
lit.
T
h
is
f
ea
tu
r
e
ex
tr
ac
tio
n
ap
p
r
o
ac
h
r
ed
u
ce
d
tr
ain
in
g
tim
e
s
ig
n
if
ican
tly
wh
ile
m
ain
tain
in
g
th
e
ex
p
r
ess
iv
e
p
o
wer
o
f
d
ee
p
co
n
v
o
lu
tio
n
al
e
n
co
d
er
s
.
3
.
2
.
P
er
f
o
r
m
a
nce
co
m
pa
riso
n a
cr
o
s
s
hy
brid m
o
dels
T
h
e
h
y
b
r
i
d
class
if
ier
s
S
VM
,
R
F,
an
d
KNN
wer
e
ev
alu
ated
u
s
in
g
5
-
f
o
ld
s
tr
atif
ied
cr
o
s
s
-
v
alid
atio
n
to
en
s
u
r
e
a
f
ai
r
ass
ess
m
en
t
o
n
t
h
e
h
ig
h
ly
im
b
ala
n
ce
d
d
ataset.
T
h
e
d
etailed
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
o
f
th
ese
m
o
d
els
is
p
r
esen
ted
in
T
ab
l
e
1
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
SVM
o
u
tp
er
f
o
r
m
ed
b
o
th
R
F
an
d
KNN.
T
h
eo
r
etica
lly
,
th
is
ca
n
b
e
attr
ib
u
ted
to
th
e
n
atu
r
e
o
f
th
e
h
i
g
h
-
d
im
e
n
s
io
n
al
f
ea
tu
r
e
s
p
ac
e
(
1
,
5
3
6
d
im
en
s
io
n
s
)
g
en
er
ated
b
y
E
f
f
icien
tNet
-
B
3
.
SVM
i
s
p
ar
ticu
lar
ly
ef
f
ec
tiv
e
in
s
u
ch
s
ce
n
ar
io
s
b
ec
au
s
e
it
co
n
s
tr
u
cts
o
p
tim
al
h
y
p
er
p
lan
es
th
at
m
ax
im
ize
th
e
m
ar
g
in
b
etwe
en
class
es,
all
o
win
g
it
to
h
a
n
d
le
h
ig
h
-
d
im
e
n
s
io
n
al
d
ata
with
o
u
t
s
u
cc
u
m
b
in
g
ea
s
ily
to
o
v
er
f
itti
n
g
.
I
n
c
o
n
tr
ast,
KNN
s
h
o
wed
th
e
lo
west
p
er
f
o
r
m
an
ce
,
lik
el
y
d
u
e
to
th
e
"c
u
r
s
e
o
f
d
im
en
s
io
n
ality
,
"
w
h
er
e
d
is
t
an
ce
m
etr
ics (
s
u
ch
as E
u
clid
ea
n
d
is
tan
ce
)
lo
s
e
th
eir
d
is
cr
im
i
n
ativ
e
p
o
wer
as th
e
v
o
lu
m
e
o
f
th
e
s
p
ac
e
in
cr
ea
s
es,
m
ak
in
g
m
in
o
r
ity
s
am
p
les
in
d
is
tin
g
u
is
h
ab
le
f
r
o
m
th
e
m
ajo
r
ity
n
eig
h
b
o
r
s
.
Similar
ly
,
R
F
s
tr
u
g
g
led
b
ec
au
s
e,
in
th
e
p
r
esen
ce
o
f
ex
tr
em
e
im
b
alan
ce
,
th
e
in
d
iv
id
u
al
d
ec
is
io
n
tr
ee
s
ten
d
to
b
e
b
iased
to
war
d
th
e
m
ajo
r
ity
class
to
m
in
im
ize
o
v
er
all
im
p
u
r
ity
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
m
o
d
els o
n
im
b
alan
ce
d
d
atasets
C
l
a
s
si
f
i
c
a
t
i
o
n
me
t
h
o
d
A
c
c
u
r
a
c
y
W
e
i
g
h
t
e
d
F
1
M
a
c
r
o
F
1
S
V
M
9
4
.
0
1
%
±
0
.
0
0
7
8
9
3
.
9
1
%
±
0
.
0
0
9
7
3
7
.
9
4
%
±
0
.
0
3
0
9
RF
8
8
.
7
9
%
±
0
.
0
1
6
3
8
7
.
1
9
%
±
0
.
0
1
5
8
3
2
.
1
8
%
±
0
.
0
5
5
1
K
N
N
8
7
.
9
3
%
±
0
.
0
0
9
5
8
6
.
6
2
%
±
0
.
0
0
9
8
2
9
.
3
9
%
±
0
.
0
4
1
6
3
.
3
.
Acc
ura
cy
ma
cr
o
F
1
dis
cr
epa
ncy
a
nd
cla
s
s
im
ba
la
nce
A
s
u
b
s
tan
tial
d
is
cr
ep
an
cy
a
p
p
ea
r
s
b
etwe
en
ac
cu
r
ac
y
(
9
4
%)
an
d
m
ac
r
o
F1
(
o
n
ly
3
7
%).
T
h
i
s
b
eh
av
io
r
is
ex
p
ec
ted
g
iv
en
th
e
ex
tr
e
m
e
class
im
b
alan
ce
in
th
e
d
ataset:
−
Hea
lth
y
: 1
,
1
2
3
im
ag
es
−
Sh
ep
h
er
d
’
s
p
u
r
s
e:
1
,
1
0
6
im
a
g
es
−
Min
o
r
ity
class
es: 6
–
3
0
im
ag
es
p
er
class
Acc
u
r
ac
y
is
,
th
er
e
f
o
r
e
,
m
is
lead
in
g
,
as
a
class
if
ier
ca
n
ac
h
ie
v
e
h
ig
h
ac
cu
r
ac
y
b
y
p
r
ed
ictin
g
m
ajo
r
ity
class
es
co
r
r
ec
tly
wh
ile
f
ailin
g
alm
o
s
t
en
tire
ly
o
n
r
ar
e
d
is
ea
s
e
ca
teg
o
r
ies.
Ma
cr
o
F1
,
wh
ich
weig
h
ts
all
class
es
eq
u
ally
,
r
e
v
ea
ls
th
is
wea
k
n
ess
clea
r
ly
.
3
.
4
.
Co
nfusi
o
n
m
a
t
rix
a
na
l
y
s
is
Fig
u
r
e
1
illu
s
tr
ates
th
e
c
o
m
b
i
n
ed
5
-
f
o
l
d
c
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
th
e
SVM
class
if
ier
.
T
h
e
m
a
tr
ix
clea
r
ly
s
h
o
ws:
−
Hea
lth
y
(
1
,
1
0
7
/1
,
1
2
3
)
an
d
Sh
ep
h
er
d
’
s
p
u
r
s
e
(
1
,
0
9
2
/1
,
1
0
6
)
a
r
e
d
etec
ted
with
n
ea
r
-
p
er
f
ec
t p
r
ec
is
io
n
.
−
Min
o
r
ity
d
is
ea
s
es
s
u
ch
as
wilt
an
d
leaf
b
lig
h
t,
v
ir
al
,
p
o
wd
er
y
m
ild
ew,
an
d
s
ep
to
r
ia
b
lig
h
t
ex
h
ib
it
s
ev
er
e
m
is
class
if
icatio
n
,
m
o
s
tly
p
r
ed
i
cted
as th
e
two
m
ajo
r
ity
class
es.
−
Dis
ea
s
e
s
with
f
ewe
r
th
an
2
0
s
am
p
les
s
h
o
w
alm
o
s
t
ze
r
o
d
i
ag
o
n
al
in
ten
s
ity
,
c
o
n
f
ir
m
i
n
g
f
ailu
r
e
to
lear
n
d
is
cr
im
in
ativ
e
p
atter
n
s
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
as
s
h
o
w
n
in
Fig
u
r
e
1
p
r
o
v
id
es
d
ee
p
er
in
s
ig
h
t
in
to
th
e
class
if
icatio
n
f
ailu
r
es.
I
t
r
ev
ea
ls
th
at
m
in
o
r
ity
d
is
ea
s
e
s
am
p
les
(
e.
g
.
,
wilt,
v
ir
al
,
s
ep
t
o
r
ia)
ar
e
f
r
eq
u
en
tly
m
is
class
if
ied
as
"
h
ea
lth
y
"
o
r
"
wee
d
s
.
"
T
h
is
s
u
g
g
ests
th
at
wh
ile
E
f
f
icien
tNet
-
B
3
s
u
cc
ess
f
u
lly
ex
tr
ac
ts
r
o
b
u
s
t
v
is
u
al
f
ea
t
u
r
es
f
o
r
g
en
er
al
leaf
s
tr
u
ctu
r
es
(
tex
tu
r
e,
s
h
ap
e
)
,
it
f
ails
to
ca
p
tu
r
e
th
e
s
u
b
tle,
f
in
e
-
g
r
ain
ed
v
is
u
al
p
atter
n
s
r
eq
u
ir
ed
to
d
is
tin
g
u
is
h
r
ar
e
d
is
ea
s
es.
T
h
is
is
n
o
t
m
er
e
ly
a
class
if
ier
f
ailu
r
e
b
u
t
a
d
at
a
d
is
tr
ib
u
tio
n
is
s
u
e;
th
e
f
ea
tu
r
e
ex
tr
ac
to
r
lear
n
s
to
p
r
io
r
itize
th
e
v
is
u
al
ch
ar
ac
ter
i
s
tics
o
f
th
e
m
ajo
r
ity
class
es.
C
o
n
s
eq
u
en
tly
,
th
e
d
ec
is
io
n
b
o
u
n
d
ar
ies
f
o
r
m
ed
b
y
th
e
class
if
ier
s
ar
e
o
v
er
wh
elm
ed
b
y
th
e
d
e
n
s
ity
o
f
th
e
m
aj
o
r
ity
class
f
ea
tu
r
es.
As
s
h
o
wn
in
th
e
c
o
n
f
u
s
io
n
m
atr
ix
,
m
in
o
r
ity
class
es su
ch
as
v
ir
al
an
d
wilt
y
ield
ed
n
ea
r
l
y
ze
r
o
c
o
r
r
ec
t p
r
ed
ictio
n
s
,
r
es
u
ltin
g
in
an
F1
-
s
co
r
e
o
f
~0
.
0
f
o
r
th
ese
ca
teg
o
r
ies.
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
Hyb
r
id
ma
ch
in
e
lea
r
n
in
g
fo
r
imb
a
la
n
ce
d
lettu
ce
d
is
ea
s
e
cla
s
s
ifica
tio
n
(
F
a
z
lu
r
I
h
z
a
n
u
r
a
h
ma
n
)
1787
Fig
u
r
e
1
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
th
e
SVM
class
if
ier
3
.
4
.
Why
SVM
o
utper
f
o
rm
s
RF
a
nd
K
NN
SVM
o
u
tp
er
f
o
r
m
ed
R
F
an
d
K
NN
b
ec
au
s
e
E
f
f
icien
tNet
-
B
3
f
ea
tu
r
es
ar
e
h
ig
h
-
d
im
en
s
io
n
al
(
1
5
3
6
-
D)
.
SVM
with
an
R
B
F
k
er
n
el
is
k
n
o
wn
to
p
er
f
o
r
m
well
in
s
u
ch
s
p
ac
es
b
y
lear
n
in
g
f
lex
i
b
le
n
o
n
lin
ea
r
d
ec
is
io
n
b
o
u
n
d
ar
ies.
R
F,
o
n
th
e
o
th
er
h
an
d
,
s
tr
u
g
g
les
with
s
p
ar
s
e
an
d
h
ig
h
-
d
im
en
s
io
n
al
f
ea
tu
r
e
d
i
s
tr
ib
u
tio
n
s
,
lead
in
g
to
o
v
e
r
f
itti
n
g
o
n
m
ajo
r
ity
class
es
an
d
u
n
d
e
r
f
itti
n
g
o
n
r
ar
e
o
n
es.
KNN
s
u
f
f
er
s
f
r
o
m
th
e
cu
r
s
e
o
f
d
im
en
s
io
n
ality
,
wh
e
r
e
d
is
tan
c
e
m
etr
ics
lo
s
e
d
is
cr
im
in
ativ
e
p
o
wer
,
m
a
k
in
g
m
in
o
r
ity
class
s
am
p
les
ef
f
ec
tiv
ely
in
d
is
tin
g
u
is
h
ab
le
in
f
ea
tu
r
e
s
p
ac
e.
T
h
e
r
ef
o
r
e
,
SVM
r
em
ai
n
s
th
e
m
o
s
t
ap
p
r
o
p
r
iate
ch
o
ice
f
o
r
h
y
b
r
id
d
ee
p
f
ea
tu
r
e
ag
r
ic
u
ltu
r
al
d
is
ea
s
e
class
if
icatio
n
.
3
.
5
.
Co
m
pa
riso
n
wit
h pre
v
io
us
s
t
ud
ie
s
Pre
v
io
u
s
C
NN
-
b
ased
s
tu
d
ies,
s
u
ch
as
th
e
wo
r
k
b
y
L
iu
et
a
l.
[
2
3
]
o
n
ap
p
le
leaf
d
is
ea
s
es
an
d
Su
n
il
et
a
l.
[
2
4
]
o
n
ca
r
d
am
o
m
p
lan
ts
r
ep
o
r
ted
ac
cu
r
ac
ies
ex
ce
ed
in
g
9
5
%
u
s
in
g
en
d
-
to
-
en
d
d
ee
p
lear
n
i
n
g
m
o
d
els.
W
h
ile
h
i
g
h
ly
ac
cu
r
at
e,
th
ese
m
et
h
o
d
s
t
y
p
ically
r
eq
u
ir
e
s
u
b
s
tan
tial
c
o
m
p
u
tatio
n
al
p
o
wer
f
o
r
g
r
ad
ie
n
t
u
p
d
ates
ac
r
o
s
s
all
lay
e
r
s
an
d
o
f
te
n
r
ely
o
n
b
ala
n
ce
d
d
a
tasets
.
I
n
co
n
tr
ast,
th
is
s
tu
d
y
p
r
esen
ts
a
h
y
b
r
id
ap
p
r
o
ac
h
th
at
u
tili
ze
s
E
f
f
icien
tNet
-
B
3
s
o
lely
as
a
f
ix
ed
f
ea
t
u
r
e
ex
tr
ac
t
o
r
co
m
b
in
ed
with
SVM.
T
h
is
m
eth
o
d
ac
h
iev
ed
co
m
p
ar
ab
le
ac
cu
r
a
cy
(
9
4
.
0
1
%)
to
f
u
lly
tr
ain
e
d
m
o
d
els
b
u
t
with
s
ig
n
if
ican
tly
lo
wer
tr
ain
in
g
co
m
p
lex
ity
.
T
h
is
h
ig
h
lig
h
ts
th
e
s
tr
en
g
th
o
f
c
o
m
b
in
in
g
d
ee
p
f
ea
tu
r
e
ex
t
r
ac
tio
n
with
class
ic
al
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
as
an
ef
f
icien
t
al
ter
n
ativ
e
p
i
p
elin
e
f
o
r
l
o
w
-
r
e
s
o
u
r
ce
ag
r
icu
ltu
r
al
e
n
v
ir
o
n
m
en
ts
wh
er
e
lar
g
e,
b
alan
ce
d
d
atasets
ar
e
u
n
a
v
aila
b
le.
3
.
6
.
L
im
it
a
t
io
ns
a
nd
f
uture
wo
rk
T
h
e
p
r
im
ar
y
lim
itatio
n
o
f
th
i
s
s
tu
d
y
is
th
e
ex
tr
em
ely
im
b
alan
ce
d
d
ataset,
wh
er
e
s
ev
er
al
d
is
ea
s
e
class
es
h
av
e
f
ewe
r
th
a
n
2
0
s
a
m
p
les.
T
h
is
r
estricts
th
e
m
o
d
e
l’
s
ab
ilit
y
to
g
en
er
alize
m
in
o
r
i
ty
d
is
ea
s
e
p
atter
n
s
.
Fu
tu
r
e
ef
f
o
r
ts
s
h
o
u
ld
in
co
r
p
o
r
ate
s
y
n
th
etic
o
v
er
s
am
p
lin
g
(
e.
g
.
,
s
y
n
t
h
etic
m
in
o
r
ity
o
v
er
s
am
p
lin
g
tech
n
iq
u
e
(
SMOT
E
)
)
,
f
o
ca
l
lo
s
s
,
g
en
er
ativ
e
au
g
m
en
tatio
n
,
o
r
a
d
d
iti
o
n
al
f
ield
d
ata
ac
q
u
is
itio
n
to
ad
d
r
ess
th
is
is
s
u
e.
Fu
r
th
er
im
p
r
o
v
e
m
en
ts
ca
n
a
ls
o
b
e
ac
h
ie
v
ed
b
y
ex
p
lo
r
in
g
en
d
to
en
d
f
in
e
tu
n
in
g
o
f
E
f
f
icien
tNet
-
B
3
,
h
ier
ar
ch
ical
class
if
icatio
n
,
o
r
e
n
s
em
b
le
h
y
b
r
id
ar
c
h
itectu
r
es to
en
h
a
n
ce
r
ar
e
d
is
ea
s
e
d
etec
tio
n
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ated
th
at
co
m
b
in
in
g
E
f
f
icien
tNet
-
B
3
f
ea
tu
r
e
ex
tr
ac
tio
n
with
class
ical
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
p
r
o
v
id
es
an
ef
f
ec
tiv
e
an
d
co
m
p
u
tat
io
n
ally
ef
f
icien
t
ap
p
r
o
ac
h
f
o
r
lettu
ce
d
is
ea
s
e
class
if
icatio
n
.
E
f
f
icien
tNet
-
B
3
s
u
cc
ess
f
u
lly
ex
tr
ac
ted
h
i
g
h
-
d
im
e
n
s
io
n
al
r
e
p
r
esen
tatio
n
s
th
at
ca
p
tu
r
ed
ess
en
tial
v
is
u
al
ch
ar
ac
ter
is
tic
s
o
f
th
e
leav
es,
wh
ile
th
e
SVM
ac
h
iev
ed
th
e
b
est
o
v
e
r
all
p
er
f
o
r
m
an
ce
with
9
4
%
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.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
7
8
3
-
1
7
8
9
1788
ac
cu
r
ac
y
an
d
9
3
.
9
%
weig
h
ted
F1
-
s
co
r
e
ac
r
o
s
s
f
iv
e
f
o
ld
s
.
Ho
wev
er
,
th
e
lo
w
m
ac
r
o
F1
-
s
co
r
e
(
3
7
.
9
%)
an
d
th
e
co
n
f
u
s
io
n
m
atr
ix
a
n
aly
s
is
r
ev
ea
led
th
at
th
e
m
o
d
el
s
tr
u
g
g
l
ed
to
r
ec
o
g
n
ize
m
in
o
r
ity
d
is
ea
s
e
class
e
s
d
u
e
to
ex
tr
em
e
d
ataset
im
b
alan
ce
.
T
h
ese
f
in
d
i
n
g
s
h
i
g
h
lig
h
t
th
a
t
ac
cu
r
ac
y
alo
n
e
is
in
s
u
f
f
icien
t
f
o
r
e
v
alu
atin
g
im
b
alan
ce
d
ag
r
icu
ltu
r
al
d
atasets
an
d
th
at
m
ac
r
o
F1
an
d
p
e
r
-
class
p
er
f
o
r
m
an
ce
ar
e
cr
itic
al
f
o
r
ass
ess
in
g
tr
u
e
m
o
d
el
r
eliab
ilit
y
.
Alth
o
u
g
h
t
h
e
h
y
b
r
id
ap
p
r
o
ac
h
p
er
f
o
r
m
e
d
well
f
o
r
d
o
m
in
an
t
class
es
s
u
ch
as
h
ea
lth
y
an
d
Sh
ep
h
er
d
’
s
p
u
r
s
e
wee
d
s
,
it
r
e
m
ain
s
lim
ited
in
d
etec
tin
g
r
ar
e
d
is
ea
s
es
with
f
ewe
r
av
aila
b
le
s
am
p
les.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
im
p
r
o
v
in
g
m
in
o
r
ity
class
r
ec
o
g
n
itio
n
th
r
o
u
g
h
s
y
n
th
etic
o
v
er
s
am
p
lin
g
,
a
d
v
an
ce
d
au
g
m
en
tatio
n
s
tr
ateg
ies,
o
r
a
cq
u
ir
in
g
a
d
d
itio
n
al
f
ield
d
ata
.
Fu
r
th
er
ex
p
l
o
r
atio
n
o
f
en
d
-
to
-
en
d
f
in
e
-
tu
n
in
g
,
im
b
alan
ce
-
awa
r
e
lo
s
s
f
u
n
ctio
n
s
,
an
d
lar
g
er
-
s
ca
le
b
en
ch
m
a
r
k
s
m
ay
also
en
h
an
ce
g
en
er
ali
za
tio
n
.
Ov
er
all,
th
is
s
tu
d
y
estab
lis
h
es
a
s
tr
o
n
g
b
aselin
e
f
o
r
lig
h
tweig
h
t
ag
r
icu
ltu
r
al
d
is
ea
s
e
class
if
icatio
n
u
s
in
g
d
ee
p
f
ea
t
u
r
e
ex
tr
ac
tio
n
co
m
b
in
ed
with
class
ical
clas
s
if
ier
s
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
t
o
t
h
an
k
th
e
Facu
lty
o
f
C
o
m
p
u
t
er
Scien
ce
,
B
r
awijay
a
Un
iv
e
r
s
ity
,
f
o
r
p
r
o
v
id
i
n
g
th
e
f
ac
ilit
ies an
d
s
u
p
p
o
r
t
n
ec
ess
ar
y
to
co
n
d
u
ct
th
i
s
r
esear
ch
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
d
id
n
o
t
r
ec
eiv
e
d
ir
ec
t
f
in
an
cial
s
u
p
p
o
r
t
f
r
o
m
an
y
f
u
n
d
in
g
ag
en
c
y
.
Ho
wev
er
,
th
e
r
esear
ch
was
f
u
lly
s
u
p
p
o
r
te
d
th
r
o
u
g
h
f
ac
ilit
ies
an
d
in
f
r
astru
ctu
r
e
p
r
o
v
id
ed
b
y
th
e
I
n
tellig
en
t
Sy
s
tem
s
L
ab
o
r
ato
r
y
,
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
,
B
r
awijay
a
Un
iv
er
s
ity
.
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
Fazlu
r
I
h
za
n
u
r
ah
m
a
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
W
a
y
a
n
F
i
r
d
a
u
s
M
a
h
m
u
d
y
✓
✓
✓
✓
✓
✓
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
o
p
en
ly
av
ailab
le
in
Kag
g
le
at
h
ttp
s
://www.
k
ag
g
le.
co
m
/d
atasets
/ash
is
h
j
s
tar
/lettu
ce
-
d
is
ea
s
e
s
/d
ata.
RE
F
E
R
E
NC
E
S
[
1
]
L
.
H
u
a
n
g
,
G
.
L
i
u
,
Y
.
W
a
n
g
,
H
.
Y
u
a
n
,
a
n
d
T
.
C
h
e
n
,
“
F
i
r
e
d
e
t
e
c
t
i
o
n
i
n
v
i
d
e
o
s
u
r
v
e
i
l
l
a
n
c
e
s
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
s
a
n
d
w
a
v
e
l
e
t
t
r
a
n
s
f
o
r
m
,
”
E
n
g
i
n
e
e
r
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
1
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
2
.
1
0
4
7
3
7
.
[
2
]
T.
K
a
l
a
i
s
e
l
v
i
,
S
.
T.
P
a
d
m
a
p
r
i
y
a
,
K
.
S
o
mas
u
n
d
a
r
a
m,
a
n
d
S
.
P
r
a
v
e
e
n
k
u
mar,
“
E
-
T
a
n
h
:
a
n
o
v
e
l
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
f
o
r
i
ma
g
e
p
r
o
c
e
ss
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
s
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
4
,
n
o
.
1
9
,
p
p
.
1
6
5
6
3
–
1
6
5
7
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
022
-
0
7
2
4
5
-
x.
[
3
]
P
.
Tr
i
p
a
t
h
i
,
N
.
K
u
mar,
M
.
R
a
i
,
a
n
d
A
.
K
h
a
n
,
“
A
p
p
l
i
c
a
t
i
o
n
s o
f
d
e
e
p
l
e
a
r
n
i
n
g
i
n
a
g
r
i
c
u
l
t
u
r
e
,
”
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
A
p
p
l
i
c
a
t
i
o
n
s
i
n
Ag
r
i
c
u
l
t
u
re
a
n
d
F
o
o
d
Q
u
a
l
i
t
y
I
m
p
r
o
v
e
m
e
n
t
,
2
0
2
2
,
p
p
.
1
7
–
28
,
d
o
i
:
1
0
.
4
0
1
8
/
9
7
8
-
1
-
6
6
8
4
-
5
1
4
1
-
0
.
c
h
0
0
2
.
[
4
]
O
.
A
.
D
.
A
mm
a
r
e
t
a
l
.
,
“
P
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
e
n
s
e
mb
l
e
l
e
a
r
n
i
n
g
a
n
d
e
x
p
l
a
i
n
a
b
l
e
A
I
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
5
6
0
3
8
–
1
5
6
0
4
9
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
8
4
5
7
4
.
[
5
]
S
.
M
.
H
a
ss
a
n
,
A
.
K
.
M
a
j
i
,
M
.
J
a
si
ń
sk
i
,
Z.
Le
o
n
o
w
i
c
z
,
a
n
d
E.
J
a
si
ń
s
k
a
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
l
a
n
t
-
l
e
a
f
d
i
s
e
a
s
e
s
u
s
i
n
g
C
N
N
a
n
d
t
r
a
n
sf
e
r
-
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
0
,
n
o
.
1
2
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
0
1
2
1
3
8
8
.
[
6
]
L.
L
i
u
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
a
u
t
o
ma
t
i
c
m
u
l
t
i
c
l
a
ss
w
i
l
d
p
e
st
mo
n
i
t
o
r
i
n
g
a
p
p
r
o
a
c
h
u
si
n
g
h
y
b
r
i
d
g
l
o
b
a
l
a
n
d
l
o
c
a
l
a
c
t
i
v
a
t
e
d
f
e
a
t
u
r
e
s,
”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
ri
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
7
,
n
o
.
1
1
,
p
p
.
7
5
8
9
–
7
5
9
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
I
.
2
0
2
0
.
2
9
9
5
2
0
8
.
[
7
]
A
.
S
h
a
r
ma
,
U
.
S
.
A
sw
a
l
,
A
.
R
a
n
a
,
V
.
D
.
V
a
n
i
,
A
.
S
a
n
k
h
y
a
n
,
a
n
d
S
h
e
k
h
a
r
,
“
R
e
a
l
t
i
me
p
l
a
n
t
d
i
sea
se
d
e
t
e
c
t
i
o
n
m
o
d
e
l
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
3
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
t
e
m
p
o
r
a
r
y
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
I
C
3
I
)
,
N
a
g
a
r
,
I
n
d
i
a
,
2
0
2
3
,
p
p
.
2
6
9
5
–
2
6
9
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
I
5
9
1
1
7
.
2
0
2
3
.
1
0
3
9
8
0
7
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
Hyb
r
id
ma
ch
in
e
lea
r
n
in
g
fo
r
imb
a
la
n
ce
d
lettu
ce
d
is
ea
s
e
cla
s
s
ifica
tio
n
(
F
a
z
lu
r
I
h
z
a
n
u
r
a
h
ma
n
)
1789
[
8
]
R
.
A
sh
t
a
g
i
,
“
F
u
s
i
o
n
o
f
A
I
t
e
c
h
n
i
q
u
e
s:
a
h
y
b
r
i
d
a
p
p
r
o
a
c
h
f
o
r
p
r
e
c
i
se
p
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
S
y
s
t
e
m
s
,
v
o
l
.
2
0
,
n
o
.
1
s,
p
p
.
8
5
0
–
8
6
1
,
2
0
2
4
,
d
o
i
:
1
0
.
5
2
7
8
3
/
j
e
s
.
8
3
6
.
[
9
]
L.
D
.
A
.
-
V
a
l
e
n
c
i
a
a
n
d
S
.
D
.
F
a
ss
o
i
s,
“
N
a
t
u
r
a
l
v
i
b
r
a
t
i
o
n
r
e
s
p
o
n
se
b
a
s
e
d
d
a
ma
g
e
d
e
t
e
c
t
i
o
n
f
o
r
a
n
o
p
e
r
a
t
i
n
g
w
i
n
d
t
u
r
b
i
n
e
v
i
a
r
a
n
d
o
m
c
o
e
f
f
i
c
i
e
n
t
l
i
n
e
a
r
p
a
r
a
me
t
e
r
v
a
r
y
i
n
g
A
R
mo
d
e
l
l
i
n
g
,
”
J
o
u
rn
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
6
2
8
,
n
o
.
1
,
p
p
.
2
7
3
–
2
9
7
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
6
2
8
/
1
/
0
1
2
0
7
3
.
[
1
0
]
J.
Y
a
o
,
S
.
N
.
Tr
a
n
,
S
.
S
a
w
y
e
r
,
a
n
d
S
.
G
a
r
g
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
l
e
a
f
d
i
s
e
a
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
:
d
a
t
a
,
t
e
c
h
n
i
q
u
e
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
6
,
n
o
.
s
3
,
p
p
.
3
5
7
1
–
3
6
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
2
3
-
1
0
6
1
0
-
4.
[
1
1
]
Z.
Ji
n
,
J.
S
h
a
n
g
,
Q
.
Z
h
u
,
C
.
Li
n
g
,
W
.
X
i
e
,
a
n
d
B
.
Q
i
a
n
g
,
“
R
F
R
S
F
:
e
m
p
l
o
y
e
e
t
u
r
n
o
v
e
r
p
r
e
d
i
c
t
i
o
n
b
a
s
e
d
o
n
r
a
n
d
o
m
f
o
r
e
s
t
s
a
n
d
su
r
v
i
v
a
l
a
n
a
l
y
s
i
s
,
”
i
n
W
e
b
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
E
n
g
i
n
e
e
r
i
n
g
–
WIS
E
2
0
2
0
,
C
h
a
m
,
S
w
i
t
z
e
r
l
a
n
d
:
S
p
r
i
n
g
e
r
,
2
0
2
0
,
p
p
.
5
0
3
–
5
1
5
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
6
2
0
0
8
-
0
_
3
5
.
[
1
2
]
T.
M
.
C
o
v
e
r
a
n
d
P
.
E
.
H
a
r
t
,
“
N
e
a
r
e
st
n
e
i
g
h
b
o
r
p
a
t
t
e
r
n
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
f
o
rm
a
t
i
o
n
T
h
e
o
r
y
,
v
o
l
.
13
,
n
o
.
1
,
p
p
.
2
2
-
2
7
,
1
9
6
7
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
T.
1
9
6
7
.
1
0
5
3
9
6
4
.
[
1
3
]
U
.
M
i
s
h
r
a
,
A
.
P
a
n
d
e
y
,
G
.
L
o
g
e
sw
a
r
i
,
a
n
d
K
.
Ta
m
i
l
a
r
a
si
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
i
n
p
o
t
a
t
o
a
n
d
man
g
o
l
e
a
v
e
s:
a
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
C
N
N
,
A
l
e
x
N
e
t
,
R
e
sN
e
t
,
a
n
d
Ef
f
i
c
i
e
n
t
N
e
t
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
p
p
.
1
–
2
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
025
-
3
2
6
0
7
-
5.
[
1
4
]
J.
A
n
d
r
e
w
,
J.
Eu
n
i
c
e
,
D
.
E
.
P
o
p
e
s
c
u
,
M
.
K
.
C
h
o
w
d
a
r
y
,
a
n
d
J
.
H
e
ma
n
t
h
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
l
e
a
f
d
i
se
a
se
d
e
t
e
c
t
i
o
n
i
n
c
r
o
p
s
u
si
n
g
i
m
a
g
e
s f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
a
p
p
l
i
c
a
t
i
o
n
s
,
”
Ag
r
o
n
o
m
y
,
v
o
l
.
1
2
,
n
o
.
1
0
,
p
p
.
1
–
2
0
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
m
y
1
2
1
0
2
3
9
5
.
[
1
5
]
M
.
T
a
n
a
n
d
Q
.
V
.
L
e
,
“
Ef
f
i
c
i
e
n
t
N
e
t
:
r
e
t
h
i
n
k
i
n
g
m
o
d
e
l
sca
l
i
n
g
f
o
r
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
i
n
3
6
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
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
,
I
C
ML 2
0
1
9
,
2
0
1
9
,
p
p
.
1
0
6
9
1
–
1
0
7
0
0
.
[
1
6
]
M
.
H
.
S
a
l
e
e
m,
J
.
P
o
t
g
i
e
t
e
r
,
a
n
d
K
.
M
.
A
r
i
f
,
“
A
p
e
r
f
o
r
ma
n
c
e
-
o
p
t
i
m
i
z
e
d
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
p
l
a
n
t
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
h
o
r
t
i
c
u
l
t
u
r
a
l
c
r
o
p
s
o
f
N
e
w
Z
e
a
l
a
n
d
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
8
9
7
9
8
–
8
9
8
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
2
0
1
1
0
4
.
[
1
7
]
A
.
L
a
k
s
h
m
a
n
a
r
a
o
,
M
.
R
.
B
a
b
u
,
a
n
d
T.
S
.
R
.
K
i
r
a
n
,
“
P
l
a
n
t
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
a
n
d
c
l
a
s
si
f
i
c
a
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
C
o
n
v
N
e
t
s,”
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
Ma
c
h
i
n
e
V
i
si
o
n
(
AI
MV
)
,
G
a
n
d
h
i
n
a
g
a
r
,
I
n
d
i
a
,
2
0
2
1
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
M
V
5
3
3
1
3
.
2
0
2
1
.
9
6
7
0
9
1
8
.
[
1
8
]
G
.
S
a
n
g
a
r
a
n
d
V
.
R
a
j
a
se
k
a
r
,
“
O
p
t
i
m
i
z
e
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
p
o
t
a
t
o
l
e
a
f
d
i
se
a
se
u
si
n
g
Ef
f
i
c
i
e
n
t
N
e
t
-
LI
TE
a
n
d
K
E
-
S
V
M
i
n
d
i
v
e
r
se
e
n
v
i
r
o
n
m
e
n
t
s,
”
Fr
o
n
t
i
e
rs
i
n
P
l
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
6
,
n
o
.
M
a
y
,
p
p
.
1
–
1
7
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s.
2
0
2
5
.
1
4
9
9
9
0
9
.
[
1
9
]
J.
O
.
A
d
e
o
l
a
,
J.
D
e
g
i
l
a
,
a
n
d
M
.
Ze
n
n
a
r
o
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
s
i
n
p
l
a
n
t
d
i
sea
ses
d
e
t
e
c
t
i
o
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
s
o
l
u
t
i
o
n
f
o
r
d
e
v
e
l
o
p
i
n
g
c
o
u
n
t
r
i
e
s,
”
i
n
2
0
2
2
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
m
a
r
t
C
o
m
p
u
t
i
n
g
,
S
MA
RT
C
O
MP
2
0
2
2
,
2
0
2
2
,
p
p
.
3
7
4
–
3
8
0
,
d
o
i
:
1
0
.
1
1
0
9
/
S
M
A
R
TC
O
M
P
5
5
6
7
7
.
2
0
2
2
.
0
0
0
8
3
.
[
2
0
]
R
.
C
h
e
n
,
H
.
Q
i
,
Y
.
L
i
a
n
g
,
a
n
d
M
.
Y
a
n
g
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
l
a
n
t
l
e
a
f
d
i
s
e
a
ses
b
y
d
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
o
n
c
h
a
n
n
e
l
a
t
t
e
n
t
i
o
n
a
n
d
c
h
a
n
n
e
l
p
r
u
n
i
n
g
,
”
Fr
o
n
t
i
e
rs
i
n
Pl
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
13
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s
.
2
0
2
2
.
1
0
2
3
5
1
5
.
[
2
1
]
A
.
G
.
-
B
r
i
o
n
e
s,
S
.
L
.
F
l
o
r
e
z
,
P
.
C
h
a
mo
s
o
,
L
.
F
.
C
a
st
i
l
l
o
-
O
ssa
,
a
n
d
E.
S
.
C
o
r
c
h
a
d
o
,
“
En
h
a
n
c
i
n
g
p
l
a
n
t
d
i
sea
se
d
e
t
e
c
t
i
o
n
:
i
n
c
o
r
p
o
r
a
t
i
n
g
a
d
v
a
n
c
e
d
c
n
n
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
b
e
t
t
e
r
a
c
c
u
r
a
c
y
a
n
d
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
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
S
y
st
e
m
s
,
v
o
l
.
1
8
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
4
1
9
6
-
0
2
5
-
0
0
8
3
5
-
2.
[
2
2
]
L.
L
i
,
S
.
Z
h
a
n
g
,
a
n
d
B
.
W
a
n
g
,
“
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
b
y
d
e
e
p
l
e
a
r
n
i
n
g
-
a
r
e
v
i
e
w
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
5
6
6
8
3
–
5
6
6
9
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
6
9
6
4
6
.
[
2
3
]
B
.
Li
u
,
Y
.
Z
h
a
n
g
,
D
.
J.
H
e
,
a
n
d
Y
.
Li
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
a
p
p
l
e
l
e
a
f
d
i
s
e
a
ses
b
a
se
d
o
n
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,
”
S
y
m
m
e
t
ry
,
v
o
l
.
1
0
,
n
o
.
1
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m
1
0
0
1
0
0
1
1
.
[
2
4
]
C
.
K
.
S
u
n
i
l
,
C
.
D
.
J
a
i
d
h
a
r
,
a
n
d
N
.
P
a
t
i
l
,
“
C
a
r
d
a
m
o
m
p
l
a
n
t
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
u
s
i
n
g
Ef
f
i
c
i
e
n
t
N
e
t
V
2
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
7
8
9
–
8
0
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
3
8
9
2
0
.
[
2
5
]
A
.
B.
S
i
d
h
i
q
u
e
,
A
.
G
o
p
a
k
u
m
a
r
,
a
n
d
A
.
R
.
B
u
sh
a
r
a
,
“
Ef
f
i
c
i
e
n
t
n
e
t
-
b
a
sed
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
a
c
c
u
r
a
t
e
p
l
a
n
t
d
i
se
a
se
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
d
i
a
g
n
o
s
i
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
i
e
n
c
e
a
n
d
Re
s
e
a
r
c
h
Ar
c
h
i
v
e
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
1
2
6
4
–
1
2
7
0
,
2
0
2
5
,
d
o
i
:
1
0
.
3
0
5
7
4
/
i
j
sr
a
.
2
0
2
5
.
1
4
.
1
.
0
1
7
0
.
[
2
6
]
J.
Li
u
,
F
.
L
v
,
a
n
d
D
.
P
e
n
g
h
u
i
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
s
u
n
f
l
o
w
e
r
l
e
a
f
d
i
s
e
a
se
s b
a
s
e
d
o
n
r
a
n
d
o
m f
o
r
e
s
t
a
l
g
o
r
i
t
h
m
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
1
9
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
,
A
u
t
o
m
a
t
i
o
n
a
n
d
S
y
st
e
m
s
,
I
C
I
C
A
S
2
0
1
9
,
2
0
1
9
,
v
o
l
.
1
1
,
p
p
.
4
5
9
–
4
6
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
A
S
4
8
5
9
7
.
2
0
1
9
.
0
0
1
0
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Fa
z
lu
r
Ihza
n
u
r
a
h
m
a
n
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r'
s
d
e
g
re
e
in
Eco
n
o
m
ics
fr
o
m
th
e
De
p
a
rtme
n
t
o
f
De
v
e
lo
p
m
e
n
t
Ec
o
n
o
m
ics
,
Un
iv
e
rsitas
G
a
jay
a
n
a
M
a
lan
g
,
in
2
0
2
2
.
He
o
b
tain
e
d
h
is
m
a
ste
r'
s d
e
g
re
e
in
Co
m
p
u
ter S
c
ien
c
e
fro
m
th
e
F
a
c
u
lt
y
o
f
C
o
m
p
u
ter S
c
ien
c
e
,
Bra
wijay
a
Un
iv
e
rsity
,
in
2
0
2
5
.
He
is
c
u
rre
n
t
ly
a
c
ti
v
e
i
n
re
se
a
rc
h
in
th
e
field
s
o
f
c
o
m
p
u
ter
v
isio
n
,
d
e
e
p
lea
rn
in
g
,
a
n
d
d
a
ta
sc
ien
c
e
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
i
g
it
a
l
ima
g
e
p
ro
c
e
ss
in
g
,
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
r
k
(CNN
)
-
b
a
se
d
c
las
sifica
ti
o
n
,
a
n
d
t
h
e
a
p
p
li
c
a
ti
o
n
o
f
a
rti
ficia
l
in
telli
g
e
n
c
e
in
a
g
ric
u
lt
u
re
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
fa
z
lu
ri
h
z
a
@s
tu
d
e
n
t
.
u
b
.
a
c
.
id
.
Wa
y
a
n
Fi
r
d
a
u
s
Ma
h
m
u
d
y
o
b
tai
n
e
d
a
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
d
e
g
re
e
fro
m
th
e
De
p
a
rtme
n
t
of
M
a
th
e
m
a
ti
c
s,
Bra
wijay
a
Un
iv
e
rsity
i
n
1
9
9
5
.
His
m
a
ste
r
in
In
fo
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
d
e
g
re
e
wa
s
o
b
tain
e
d
fro
m
th
e
In
stit
u
t
Tek
n
o
l
o
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r
,
S
u
ra
b
a
y
a
i
n
1
9
9
9
wh
il
e
a
Ph
.
D
.
i
n
M
a
n
u
fa
c
tu
ri
n
g
En
g
in
e
e
r
in
g
wa
s
o
b
tain
e
d
fro
m
t
h
e
Un
iv
e
r
sity
o
f
S
o
u
th
A
u
stra
li
a
in
2
0
1
4
.
He
is
a
p
ro
fe
ss
o
r
a
t
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s
En
g
in
e
e
rin
g
,
Bra
wijay
a
Un
iv
e
rsit
y
,
I
n
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
o
p
ti
m
iz
a
ti
o
n
o
f
c
o
m
b
in
a
t
o
rial
p
ro
b
lem
s
a
n
d
m
a
c
h
i
n
e
lea
rn
i
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
wa
y
a
n
fm
@u
b
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.