I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
,
p
p
.
85
~
92
IS
SN: 2
2
5
2
-
8814
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
aa
s
.
v
9
.
i
2
.
p
p
85
-
92
85
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Disea
se predic
tio
n in big da
ta
hea
l
thcare using
ex
te
nded
co
nv
o
lutiona
l neural netw
o
rk
t
ec
hn
iques
Asa
di Srin
iv
a
s
ulu
,
A
s
a
di P
u
s
hp
a
Da
ta
A
n
a
l
y
ti
c
s Re
se
a
rc
h
L
a
b
o
ra
to
ry
,
S
re
e
V
id
y
a
n
ik
e
th
a
n
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
3
,
2
0
1
9
R
ev
i
s
ed
Feb
2
,
2
0
20
A
cc
ep
ted
Mar
14
,
2
0
20
Dia
b
e
tes
M
e
ll
it
u
s
is
o
n
e
o
f
th
e
g
ro
w
in
g
f
a
tal
d
ise
a
se
s
a
ll
o
v
e
r
t
h
e
w
o
rld
.
It
lea
d
s
to
c
o
m
p
li
c
a
ti
o
n
s
th
a
t
in
c
l
u
d
e
h
e
a
rt
d
ise
a
se
,
stro
k
e
,
a
n
d
n
e
rv
e
d
ise
a
s
e
,
k
id
n
e
y
d
a
m
a
g
e
.
S
o
,
M
e
d
ica
l
P
ro
f
e
s
sio
n
a
ls
w
a
n
t
a
re
li
a
b
le
p
re
d
ictio
n
sy
ste
m
to
d
iag
n
o
se
Dia
b
e
tes
.
T
o
p
re
d
ict
th
e
d
iab
e
tes
a
t
e
a
rli
e
r
sta
g
e
,
d
if
fe
re
n
t
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
a
re
u
se
f
u
l
f
o
r
e
x
a
m
in
in
g
th
e
d
a
ta
f
ro
m
d
iff
e
re
n
t
so
u
rc
e
s
a
n
d
v
a
lu
a
b
le
k
n
o
w
led
g
e
is
s
y
n
o
p
siz
e
d
.
S
o
,
m
in
in
g
th
e
d
ia
b
e
tes
d
a
ta
in
a
n
e
f
f
ici
e
n
t
w
a
y
is
a
c
ru
c
ial
c
o
n
c
e
rn
.
In
t
h
is
p
r
o
jec
t,
a
m
e
d
ica
l
d
a
tas
e
t
h
a
s
b
e
e
n
a
c
c
o
m
p
li
sh
e
d
to
p
re
d
ict
t
h
e
d
iab
e
tes
.
T
h
e
R
-
S
tu
d
io
a
n
d
P
y
p
a
rk
so
f
t
w
a
r
e
w
a
s
e
m
p
lo
y
e
d
a
s
a
sta
ti
stica
l
c
o
m
p
u
ti
n
g
to
o
l
f
o
r
d
iag
n
o
si
n
g
d
iab
e
tes
.
T
h
e
P
IM
A
In
d
ian
d
a
tab
a
se
w
a
s
a
c
q
u
ired
f
ro
m
UCI
re
p
o
sito
ry
w
i
ll
b
e
u
se
d
f
o
r
a
n
a
l
y
sis.
T
h
e
d
a
tas
e
t
wa
s
s
tu
d
ie
d
a
n
d
a
n
a
ly
z
e
d
to
b
u
il
d
a
n
e
ff
e
c
ti
v
e
m
o
d
e
l
th
a
t
p
re
d
icts a
n
d
d
iag
n
o
se
s
th
e
d
iab
e
tes
d
ise
a
se
e
a
rli
e
r.
K
ey
w
o
r
d
s
:
C
NN,
Diab
etes,
Neu
r
al
n
et
w
o
r
k
s
,
R
NN
SVM,
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
:
Asad
i Sr
in
i
v
as
u
l
u
,
Data
An
al
y
tic
s
R
esear
c
h
L
ab
o
r
ato
r
y
,
Sre
e
Vid
y
an
i
k
et
h
a
n
E
n
g
in
ee
r
i
n
g
C
o
lleg
e,
Sre
e
Sain
at
h
Na
g
ar
,
T
ir
u
p
ati,
An
d
h
r
a
P
r
ad
esh
5
1
7
1
0
2
,
I
n
d
ia
.
E
m
ail:
s
r
i
n
u
.
asad
i
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
As
w
e
k
n
o
w
t
h
at
th
e
g
r
o
w
t
h
in
tech
n
o
lo
g
y
h
elp
s
t
h
e
co
m
p
u
ter
s
to
p
r
o
d
u
ce
h
u
g
e
a
m
o
u
n
t
o
f
d
ata.
A
d
d
itio
n
al
l
y
,
s
u
c
h
ad
v
a
n
ce
m
en
ts
a
n
d
i
n
n
o
v
atio
n
s
in
th
e
m
ed
ical
d
atab
ase
m
an
a
g
e
m
e
n
t
s
y
s
te
m
s
g
en
er
ate
lar
g
e
v
o
l
u
m
e
s
o
f
m
ed
ical
d
ata.
Hea
lth
ca
r
e
in
d
u
s
tr
y
co
n
tai
n
s
v
er
y
lar
g
e
a
n
d
s
en
s
iti
v
e
d
ata.
T
h
is
d
ata
n
ee
d
s
to
b
e
tr
ea
ted
v
er
y
ca
r
ef
u
l
to
g
et
b
en
ef
itted
f
r
o
m
it.
Diab
etic
Me
llit
u
s
is
a
s
et
o
f
ass
o
ciate
d
d
is
ea
s
es
in
w
h
ic
h
th
e
h
u
m
an
b
o
d
y
is
u
n
ab
le
to
co
n
tr
o
l
th
e
q
u
an
ti
t
y
o
f
s
u
g
ar
in
th
e
b
lo
o
d
.
I
t
r
esu
lts
in
h
ig
h
s
u
g
ar
l
ev
els
i
n
b
lo
o
d
,
m
a
y
b
e
as
t
h
e
b
o
d
y
d
o
es
n
o
t
p
r
o
d
u
ce
s
u
f
f
icie
n
t
in
s
u
lin
,
o
r
m
a
y
b
ec
au
s
e
ce
lls
d
o
n
o
t
r
ea
ct
to
th
e
p
r
o
d
u
ce
d
in
s
u
li
n
.
T
h
e
f
o
cu
s
is
to
d
ev
elo
p
th
e
p
r
ed
ictio
n
m
o
d
els
b
y
u
s
in
g
ce
r
tai
n
m
ac
h
i
n
e
le
ar
n
in
g
al
g
o
r
ith
m
s
.
T
h
e
Ma
ch
in
e
L
ea
r
n
i
n
g
is
a
n
ap
p
li
ca
tio
n
o
f
ar
tif
icia
l
in
te
lli
g
en
ce
as
it
h
elp
s
th
e
co
m
p
u
ter
to
lear
n
o
n
its
o
w
n
.
T
h
e
t
w
o
cla
s
s
i
f
icat
io
n
o
f
M
L
ar
e
s
u
p
er
v
is
ed
a
n
d
u
n
s
u
p
er
v
i
s
ed
.
T
h
e
Su
p
er
v
i
s
ed
lear
n
i
n
g
ca
lcu
latio
n
u
tili
ze
s
th
e
p
ast
ex
p
er
ien
ce
to
in
f
lu
e
n
ce
ex
p
ec
tatio
n
s
o
n
n
e
w
o
r
in
co
n
s
p
ic
u
o
u
s
i
n
f
o
r
m
atio
n
w
h
ile
u
n
s
u
p
er
v
i
s
ed
ca
lcu
latio
n
s
to
ca
n
d
r
a
w
d
er
i
v
atio
n
s
f
r
o
m
d
ataset
s
.
Ma
ch
i
n
e
lear
n
in
g
al
g
o
r
ith
m
s
ar
e:
S
u
p
ervis
ed
lea
r
n
in
g
tech
n
iq
u
e
s
:
C
la
s
s
i
fica
tio
n
T
h
e
p
r
o
ce
d
u
r
e
o
f
f
in
d
in
g
th
e
o
b
s
cu
r
e
in
f
o
r
m
atio
n
o
f
t
h
e
class
n
a
m
e
w
h
ic
h
is
u
tili
zi
n
g
r
ec
e
n
t
k
n
o
w
n
in
f
o
r
m
atio
n
is
ca
lled
as
cla
s
s
m
ar
k
w
h
ich
i
s
i
n
ter
n
ca
lle
d
as
class
i
f
icatio
n
.
T
h
e
f
o
llo
w
i
n
g
ar
e
P
o
p
u
lar
C
las
s
i
f
icatio
n
A
l
g
o
r
it
h
m
s
:
R
an
d
o
m
f
o
r
est
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8814
I
n
t J
A
d
v
A
p
p
l Sci
,
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
:
85
–
92
86
SVM
K
-
Nea
r
est
n
ei
g
h
b
o
r
s
Dec
is
io
n
tr
ee
Naïv
e
B
a
y
es
R
eg
r
ess
io
n
A
s
u
p
er
v
i
s
ed
lear
n
in
g
alg
o
r
it
h
m
s
u
c
h
as
class
if
icatio
n
w
h
i
ch
f
i
n
d
s
th
e
r
elatio
n
s
h
ip
b
etw
ee
n
s
o
m
e
in
d
ep
en
d
en
t
v
ar
iab
le
s
w
i
th
s
o
m
e
d
ep
en
d
en
t
v
ar
iab
les
is
n
ca
lled
R
eg
r
ess
io
n
.
T
h
e
p
o
p
u
lar
R
eg
r
ess
io
n
alg
o
r
ith
m
s
ar
e:
Si
m
p
le
L
i
n
ea
r
R
e
g
r
ess
io
n
Mu
ltip
le
L
i
n
ea
r
R
eg
r
e
s
s
io
n
L
o
g
i
s
tic
R
eg
r
es
s
io
n
P
o
ly
n
o
m
ial
R
eg
r
e
s
s
io
n
L
i
n
ea
r
Dis
cr
i
m
i
n
an
t
An
al
y
s
is
(
L
D
A
)
Un
s
u
p
ervis
ed
Lea
r
n
in
g
tech
n
i
q
u
es:
C
lu
s
ter
in
g
T
h
e
p
r
o
ce
s
s
w
h
ic
h
class
i
f
ie
s
t
h
e
s
i
m
ilar
o
b
j
ec
ts
in
to
g
r
o
u
p
s
ca
lled
as
clu
s
ter
in
g
m
ec
h
a
n
i
s
m
.
So
m
e
o
f
th
e
cl
u
s
ter
i
n
g
tech
n
iq
u
e
s
ar
e:
K
-
m
ea
n
s
clu
s
ter
i
n
g
Hier
ar
ch
ical
clu
s
ter
i
n
g
R
s
tu
d
io
An
I
n
te
g
r
ated
De
v
elo
p
m
e
n
t
E
n
v
ir
o
n
m
e
n
t
(
I
DE
)
f
o
r
R
p
r
o
g
r
a
m
m
i
n
g
lan
g
u
ag
e
w
h
ic
h
was
f
o
u
n
d
ed
b
y
J
j
allair
e
is
ca
lled
as
R
Stu
d
io
.
T
h
e
co
m
m
a
n
d
lin
e
t
h
at
R
Stu
d
io
u
s
e
s
is
in
ter
p
r
eter
.
R
s
tu
d
io
u
s
ed
f
o
r
s
tatis
t
ical
co
m
p
u
tin
g
a
n
d
g
r
ap
h
ics.
R
St
u
d
io
is
h
av
i
n
g
m
a
n
y
b
u
ilt
-
i
n
p
ac
k
ag
e
s
s
o
it
ca
n
m
a
n
ip
u
late
h
u
g
e
d
ataset
f
o
r
an
al
y
s
i
s
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
e
u
s
a
g
e
o
f
b
ig
d
ata
f
o
r
p
r
ed
ictin
g
d
iab
etes
h
as
b
ee
n
co
n
d
u
cted
i
n
m
an
y
r
e
s
ea
r
ch
e
s
.
T
ab
le
1
d
is
p
la
y
r
esear
ch
es
i
n
th
e
f
ield
an
d
also
cr
itiq
u
e
g
iv
e
n
f
o
r
ea
ch
r
esear
ch
p
ap
er
s
.
C
o
n
s
id
er
i
n
g
t
h
e
cr
itiq
u
e
an
d
n
o
tes
o
f
ea
ch
p
u
b
lis
h
ed
r
ese
ar
ch
,
th
i
s
r
esear
ch
w
ill
p
r
o
p
o
s
e
a
n
e
w
m
o
d
el
f
o
r
r
eso
l
v
i
n
g
p
r
o
b
le
m
s
f
r
o
m
p
r
ev
io
u
s
r
esear
ch
.
T
ab
el
1
.
R
ev
ie
w
o
f
r
elate
d
r
esear
ch
N
o
.
P
a
p
e
r
A
u
t
h
o
r
(
s)
N
a
me
o
f
t
h
e
Jo
u
r
n
a
l
M
e
t
h
o
d
s
F
i
n
d
i
n
g
s
N
o
t
e
s/
C
r
i
t
i
q
u
e
1.
P
r
e
d
i
c
t
i
n
g
D
i
a
b
e
t
e
s
i
n
M
e
d
i
c
a
l
D
a
t
a
se
t
s
U
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
T
e
c
h
n
i
q
u
e
s
U
sw
a
A
l
i
Z
i
a
,
D
r
.
N
a
e
e
m
K
h
a
n
.
I
n
t
e
r
n
a
t
i
o
n
a
l
Jo
u
r
n
a
l
o
f
S
c
i
e
n
t
i
f
i
c
&
En
g
i
n
e
e
r
i
n
g
R
e
se
a
r
c
h
(
I
JS
ER
)
.
B
o
o
t
st
r
a
p
p
i
n
g
r
e
samp
l
i
n
g
t
e
c
h
n
i
q
u
e
t
o
e
n
h
a
n
c
e
t
h
e
a
c
c
u
r
a
c
y
a
n
d
t
h
e
n
a
p
p
l
y
i
n
g
i.
N
a
i
v
e
B
a
y
e
s,
i
i
.
D
e
c
i
s
i
o
n
T
r
e
e
s
i
i
i
.
k
-
N
e
a
r
e
st
N
e
i
g
h
b
o
r
s
(k
-
NN)
A
f
t
e
r
B
o
o
t
st
r
a
p
p
i
n
g
A
c
c
u
r
a
c
y
:
i
.
N
a
i
v
e
B
a
y
e
s
-
7
4
.
8
9
%
i
i
.
D
e
c
i
s
i
o
n
T
r
e
e
s
-
9
4
.
4
4
%
i
i
i
.
k
-
N
N
(
f
o
r
k
=
1
)
9
3
.
7
9
%
4
.
k
-
N
N
(
f
o
r
k
=
3
)
-
7
6
.
7
9
%
i
.
P
l
a
n
t
o
u
se
f
u
r
t
h
e
r
mo
r
e
a
d
v
a
n
c
e
d
c
l
a
ssi
f
i
e
r
s
su
c
h
a
s
N
e
u
r
a
l
N
e
t
w
o
r
k
s.
i
i
.
I
t
sh
o
u
l
d
c
o
n
si
d
e
r
so
me
o
t
h
e
r
i
mp
o
r
t
a
n
t
f
a
c
t
o
r
s t
h
a
t
a
r
e
r
e
l
a
t
e
d
t
o
g
e
st
a
t
i
o
n
a
l
d
i
a
b
e
t
e
s,
l
i
k
e
me
t
a
b
o
l
i
c
sy
n
d
r
o
me
,
f
a
mi
l
y
h
i
st
o
r
y
,
h
a
b
i
t
o
f
smo
k
i
n
g
,
l
a
z
y
r
o
u
t
i
n
e
s,
so
me
d
i
e
t
a
r
y
p
a
t
t
e
r
n
s e
t
c
.
2.
P
r
e
d
i
c
t
i
o
n
o
f
D
i
a
b
e
t
e
s
U
si
n
g
D
a
t
a
M
i
n
i
n
g
T
e
c
h
n
i
q
u
e
s
F
i
k
i
r
t
e
G
i
r
ma,
W
o
l
d
e
mi
c
h
a
e
l
,
S
u
mi
t
r
a
M
e
n
a
r
i
a
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
T
r
e
n
d
s
i
n
El
e
c
t
r
o
n
i
c
s
a
n
d
I
n
f
o
r
mat
i
c
s
(
I
C
O
E
I
)
i
.
B
a
c
k
P
r
o
p
a
g
a
t
i
o
n
A
l
g
o
r
i
t
h
m
i
i
.
J
4
8
A
l
g
o
r
i
t
h
m
i
i
i
.
N
a
ï
v
e
B
a
y
e
s
C
l
a
ssi
f
i
e
r
i
v
.
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
.
B
a
c
k
P
r
o
p
a
g
a
t
i
o
n
A
l
g
o
r
i
t
h
m
h
a
s
A
c
c
u
r
a
c
y
-
8
3
.
1
1
%
S
e
n
si
t
i
v
i
t
y
-
8
6
.
5
3
%
S
p
e
c
i
f
i
c
i
t
y
-
76%
i
.
I
n
c
r
e
me
n
t
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
a
l
g
o
r
i
t
h
ms.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
d
v
A
p
p
l Sci
I
SS
N:
2
2
5
2
-
8814
Dis
ea
s
e
p
r
ed
ictio
n
in
b
ig
d
a
ta
h
ea
lth
ca
r
e
u
s
in
g
ex
ten
d
ed
co
n
vo
lu
tio
n
a
l n
eu
r
a
l n
etw
o
r
k…
(
A
s
a
d
i S
r
in
iva
s
u
lu
)
87
Ta
b
le
co
n
tin
u
e
d
3.
D
i
a
b
e
t
e
s
D
i
se
a
se
P
r
e
d
i
c
t
i
o
n
U
si
n
g
D
a
t
a
M
i
n
i
n
g
D
e
e
r
a
j
S
h
e
t
t
y
,
K
i
sh
o
r
R
i
t
,
S
o
h
a
i
l
S
h
a
i
k
h
,
N
i
k
i
t
a
P
a
t
i
l
s
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
I
n
n
o
v
a
t
i
o
n
s
i
n
I
n
f
o
r
mat
i
o
n
,
Emb
e
d
d
e
d
a
n
d
C
o
mm
u
n
i
c
a
t
i
o
n
S
y
st
e
ms (
I
C
I
I
EC
S
)
.
i.
N
a
ï
v
e
B
a
y
e
s
ii.
k
-
NN
a
l
g
o
r
i
t
h
ms
p
r
e
d
i
c
t
i
o
n
o
f
t
h
e
d
i
se
a
se
w
i
l
l
b
e
d
o
n
e
w
i
t
h
t
h
e
h
e
l
p
o
f
B
a
y
e
si
a
n
a
l
g
o
r
i
t
h
m
a
n
d
K
N
N
a
l
g
o
r
i
t
h
m
a
n
d
a
n
a
l
y
z
e
t
h
e
m
b
y
t
a
k
i
n
g
v
a
r
i
o
u
s
a
t
t
r
i
b
u
t
e
s
o
f
d
i
a
b
e
t
e
s.
i
.
I
n
c
r
e
me
n
t
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
a
l
g
o
r
i
t
h
ms.
i
i
.
S
o
W
o
r
k
i
n
g
o
n
so
me
mo
r
e
a
t
t
r
i
b
u
t
e
s
w
h
i
c
h
i
s
u
se
d
t
o
t
a
c
k
l
e
t
h
e
d
i
a
b
e
t
e
s
e
v
e
n
mo
r
e
.
4.
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
D
i
a
b
e
t
i
c
P
a
t
i
e
n
t
s
b
y
u
si
n
g
Ef
f
i
c
i
e
n
t
P
r
e
d
i
c
t
i
o
n
f
r
o
m
B
i
g
D
a
t
a
u
si
n
g
R
S
t
u
d
i
o
K
.
S
h
a
r
mi
l
a
,
D
r
.
S
.
A
.
V
e
t
h
a
M
a
n
i
c
k
a
m
I
n
t
e
r
n
a
t
i
o
n
a
l
Jo
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
En
g
i
n
e
e
r
i
n
g
R
e
se
a
r
c
h
a
n
d
S
c
i
e
n
c
e
(
I
J
A
ER
S
)
.
D
e
c
i
si
o
n
t
r
e
e
i
.
U
si
n
g
R
,
t
h
e
d
a
t
a
se
t
i
s
a
n
a
l
y
z
e
d
a
n
d
t
h
e
c
o
r
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
f
o
r
t
w
o
a
t
t
r
i
b
u
t
e
s
i
s
c
a
l
c
u
l
a
t
e
d
.
i
i
.
D
e
c
i
si
o
n
T
r
e
e
i
s
u
se
d
t
o
p
r
e
d
i
c
t
t
h
e
t
y
p
e
o
f
D
i
a
b
e
t
e
s.
P
o
ssi
b
i
l
i
t
y
o
f
d
e
v
e
l
o
p
i
n
g
e
f
f
i
c
i
e
n
t
p
r
e
d
i
c
t
i
v
e
mo
d
e
l
s
u
si
n
g
t
h
e
i
n
f
o
r
mat
i
o
n
f
r
o
m
t
h
e
a
n
a
l
y
si
s
wh
i
c
h
i
s
a
l
r
e
a
d
y
c
a
r
r
i
e
d
o
u
t
.
5.
D
i
a
g
n
o
si
s
o
f
d
i
a
b
e
t
e
s
u
si
n
g
C
l
a
ssi
f
i
c
a
t
i
o
n
mi
n
i
n
g
T
e
c
h
n
i
q
u
e
s
A
i
s
w
a
r
y
a
I
y
e
r
,
S
.
Je
y
a
l
a
t
h
a
a
n
d
R
o
n
a
k
S
u
mb
a
l
y
I
n
t
e
r
n
a
t
i
o
n
a
l
Jo
u
r
n
a
l
o
f
D
a
t
a
M
i
n
i
n
g
&
K
n
o
w
l
e
d
g
e
M
a
n
a
g
e
me
n
t
P
r
o
c
e
ss
(
I
JD
K
P
)
.
D
e
c
i
si
o
n
t
r
e
e
N
a
ï
v
e
B
a
y
e
s.
J4
8
C
r
o
ss
v
a
l
i
d
a
t
i
o
n
-
7
4
.
8
6
9
8
%
J4
8
P
e
r
c
e
n
t
a
g
e
S
p
l
i
t
-
7
6
.
9
5
6
5
%
N
a
i
v
e
B
a
y
e
s
-
7
9
.
5
6
5
2
%
i
.
I
n
f
u
t
u
r
e
t
h
e
w
o
r
k
,
p
l
a
n
n
e
d
t
o
b
e
g
a
t
h
e
r
i
n
g
t
h
e
i
n
f
o
r
mat
i
o
n
f
r
o
m
d
i
f
f
e
r
e
n
t
l
o
c
a
l
e
s
o
v
e
r
t
h
e
w
o
r
l
d
.
i
i
.
T
h
i
s
w
o
r
k
c
a
n
b
e
i
mp
r
o
v
e
d
a
n
d
e
x
t
e
n
d
e
d
f
o
r
t
h
e
a
u
t
o
mat
i
o
n
o
f
d
i
a
b
e
t
e
s
a
n
a
l
y
si
s.
6.
A
n
D
i
se
a
se
D
i
a
g
n
o
si
s
u
si
n
g
D
a
t
a
M
i
n
i
n
g
T
e
c
h
n
i
q
u
e
s
A
n
d
Em
p
i
r
i
c
a
l
st
u
d
y
.
M
.
D
e
e
p
i
k
a
,
D
r
.
K
.
K
a
l
a
i
se
l
v
i
T
h
e
2
nd
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
I
n
v
e
n
t
i
v
e
C
o
mm
u
n
i
c
a
t
i
o
n
a
n
d
C
o
mp
u
t
a
t
i
o
n
a
l
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
I
C
C
T
)
.
i
.
A
r
t
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
i
i
.
D
e
c
i
s
i
o
n
T
r
e
e
i
i
i
.
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
i
v
.
N
a
ï
v
e
B
a
y
e
s
v.
S
V
M
A
r
t
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
:
7
3
.
2
3
%
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
:
7
6
.
1
3
%
D
e
c
i
si
o
n
T
r
e
e
:
7
7
.
8
7
%
Ef
f
i
c
i
e
n
t
a
n
d
A
c
c
u
r
a
t
e
c
l
a
ssi
f
i
e
r
c
a
n
b
e
d
e
v
e
l
o
p
e
d
.
3.
P
RO
P
O
SE
D
SYS
T
E
M
W
e
p
r
o
p
o
s
e
a
clas
s
if
icatio
n
m
o
d
el
w
it
h
b
o
o
s
ted
ac
cu
r
ac
y
to
p
r
ed
ict
th
e
d
iab
etic
p
atie
n
t.
I
n
t
h
is
m
o
d
el,
w
e
h
a
v
e
e
m
p
lo
y
ed
d
if
f
er
en
t
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
ar
e
u
s
i
n
g
lik
e
clas
s
i
f
icat
io
n
,
r
eg
r
ess
io
n
a
n
d
clu
s
ter
i
n
g
.
T
h
e
m
aj
o
r
f
o
cu
s
i
s
to
in
cr
ea
s
e
t
h
e
ac
cu
r
ac
y
b
y
u
s
i
n
g
r
e
s
a
m
p
le
tec
h
n
iq
u
e
o
n
a
b
en
ch
m
ar
k
w
ell
r
en
o
w
n
ed
P
I
MA
d
iab
etes
d
ataset
th
at
w
a
s
ac
q
u
ir
ed
f
r
o
m
UC
I
m
ac
h
i
n
e
lear
n
i
n
g
r
ep
o
s
ito
r
y
,
h
av
i
n
g
eig
h
t
attr
ib
u
tes a
n
d
o
n
e
cla
s
s
lab
el.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
i
s
s
h
o
w
n
in
Fi
g
u
r
e
1
.
T
h
e
d
escr
ip
ti
o
n
o
f
ea
c
h
p
h
a
s
e
is
m
en
tio
n
ed
.
3
.
1
.
Da
t
a
s
elec
t
io
n
Data
s
elec
tio
n
is
a
p
r
o
ce
s
s
i
n
w
h
ic
h
t
h
e
m
o
s
t
r
ele
v
an
t
d
ata
is
s
elec
ted
f
r
o
m
a
s
p
ec
i
f
ic
d
o
m
ai
n
to
d
er
iv
e
v
alu
e
s
th
a
t
ar
e
in
f
o
r
m
a
tiv
e
an
d
f
ac
ilit
ate
lear
n
in
g
.
P
I
MA
d
iab
etes
d
ataset
h
av
in
g
8
attr
ib
u
tes
th
a
t
ar
e
u
s
ed
to
p
r
ed
ict
th
e
d
iab
etes a
t e
ar
lier
s
tag
e.
T
h
is
d
ataset
is
o
b
tain
ed
f
r
o
m
U
C
I
r
ep
o
s
ito
r
y
.
3
.
2
.
Da
t
a
pre
-
pro
ce
s
s
ing
Data
p
r
e
-
p
r
o
ce
s
s
in
g
i
s
a
Ma
c
h
in
e
L
ea
r
n
i
n
g
tech
n
iq
u
e
th
at
i
n
clu
d
e
s
ch
a
n
g
in
g
cr
u
d
e
in
f
o
r
m
atio
n
in
to
r
ea
s
o
n
ab
le
co
n
f
i
g
u
r
atio
n
.
I
t
in
clu
d
es
Da
ta
C
lea
n
i
n
g
,
Data
I
n
teg
r
atio
n
,
Data
T
r
an
s
f
o
r
m
atio
n
,
a
n
d
Data
Dis
cr
etiza
tio
n
.
3
.
3
.
F
ea
t
ure
ex
t
ra
ct
io
n t
hro
ug
h
princip
le
co
m
po
nent
a
na
ly
s
i
s
Featu
r
e
E
x
tr
ac
tio
n
o
n
th
e
d
a
taset
to
d
eter
m
i
n
e
t
h
e
m
o
s
t
s
u
itab
le
s
et
o
f
a
ttrib
u
te
s
th
a
t
ca
n
h
e
lp
ac
h
iev
e
b
etter
class
if
ica
tio
n
.
T
h
e
s
et
o
f
attr
ib
u
tes
s
u
g
g
e
s
ted
b
y
t
h
e
P
C
A
ar
e
te
r
m
ed
as
f
ea
tu
r
e
v
ec
to
r
.
Featu
r
e
r
ed
u
ct
io
n
o
r
d
i
m
en
s
io
n
alit
y
r
ed
u
ctio
n
w
il
l
b
e
b
en
ef
itted
u
s
b
y
r
ed
u
ci
n
g
th
e
co
m
p
u
tat
io
n
a
n
d
s
p
ac
e
co
m
p
le
x
it
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8814
I
n
t J
A
d
v
A
p
p
l Sci
,
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
:
85
–
92
88
3
.
4
.
Resa
m
pli
ng
F
ilte
r
T
h
e
s
u
p
er
v
i
s
ed
R
e
s
a
m
p
le
f
ilt
er
is
ap
p
lied
to
t
h
e
p
r
e
-
p
r
o
ce
s
s
ed
d
ataset.
R
e
-
s
a
m
p
li
n
g
is
a
s
er
ies
o
f
m
et
h
o
d
s
u
s
ed
to
r
ec
o
n
s
tr
u
c
t
y
o
u
r
s
a
m
p
le
d
ata
s
ets,
i
n
cl
u
d
in
g
tr
ain
i
n
g
s
ets
a
n
d
v
alid
atio
n
s
ets.
I
n
t
h
is
s
tu
d
y
,
B
o
o
t stra
p
p
in
g
r
esa
m
p
li
n
g
tec
h
n
iq
u
e
to
en
h
an
ce
t
h
e
ac
cu
r
ac
y
.
Fig
u
r
e
1
.
P
r
o
p
o
s
ed
s
y
s
te
m
f
o
r
d
iab
etes p
r
ed
ictio
n
s
y
s
te
m
4.
M
ACH
I
NE
LE
AR
NIN
G
T
E
CH
NIQU
E
S
4
.
1
.
Cla
s
s
if
ica
t
io
n
4
.
1
.
1
.
Ra
nd
o
m
f
o
re
s
t
T
h
e
o
u
tf
it
lear
n
i
n
g
tec
h
n
iq
u
e
u
s
ed
f
o
r
th
e
clas
s
if
icatio
n
an
d
r
eg
r
ess
io
n
t
h
at
o
p
er
ates
b
y
c
o
n
s
tr
u
ct
in
g
th
e
m
u
ltit
u
d
e
o
f
d
ec
is
io
n
tr
ee
s
at
tr
ai
n
i
n
g
ti
m
e
a
n
d
o
u
tp
u
tti
n
g
th
e
clas
s
i.e
m
o
d
e
o
f
t
h
e
cla
s
s
es
o
r
th
e
r
eg
r
ess
io
n
o
f
t
h
e
in
d
i
v
id
u
al
tr
ee
s
.
I
r
r
eg
u
lar
ch
o
ice
w
o
o
d
s
r
ig
h
t
f
o
r
ch
o
ice
tr
ee
s
p
r
o
p
e
n
s
it
y
w
h
ich
i
s
u
s
e
d
f
o
r
o
v
er
f
itti
n
g
o
n
to
th
eir
p
r
ep
ar
atio
n
s
et.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
d
v
A
p
p
l Sci
I
SS
N:
2
2
5
2
-
8814
Dis
ea
s
e
p
r
ed
ictio
n
in
b
ig
d
a
ta
h
ea
lth
ca
r
e
u
s
in
g
ex
ten
d
ed
co
n
vo
lu
tio
n
a
l n
eu
r
a
l n
etw
o
r
k…
(
A
s
a
d
i S
r
in
iva
s
u
lu
)
89
4
.
1
.
2
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chine
(
S
V
M
)
SVM
is
a
d
i
v
is
io
n
o
f
S
u
p
er
v
is
ed
L
ea
r
n
i
n
g
A
l
g
o
r
ith
m
.
T
h
e
s
tr
ate
g
y
u
s
ed
to
p
er
f
o
r
m
r
eg
r
ess
io
n
,
class
i
f
icatio
n
a
n
d
o
u
t
lier
d
etec
tio
n
o
f
d
ata.
SVM
w
ill
b
e
g
r
o
u
p
in
g
th
e
i
n
f
o
r
m
atio
n
d
ep
en
d
e
n
t t
h
at
o
n
th
e
h
y
p
er
p
lan
e.
T
h
e
h
y
p
er
p
la
n
e
i
s
u
s
e
d
to
to
tall
y
is
o
late
t
h
e
t
w
o
cl
ass
es
i
n
t
h
e
b
es
t
w
a
y
a
n
d
t
h
e
m
o
s
t
e
x
tr
e
m
e
ed
g
e
h
y
p
er
p
lan
e
o
u
g
h
t
to
b
e
p
ick
ed
as
a
b
est
s
ep
ar
ato
r
.
T
h
e
tw
o
t
y
p
e
s
SVM
C
las
s
i
f
ier
s
t
h
at
ar
e
b
ee
n
u
s
ed
ar
e
u
s
ed
ar
e:
L
i
n
ea
r
C
la
s
s
i
f
ier
a
n
d
No
n
-
L
i
n
ea
r
C
la
s
s
i
f
ier
.
4
.
1
.
3
.
Dec
is
io
n t
re
e
T
h
e
alg
o
r
ith
m
w
h
ich
is
m
ai
n
l
y
u
s
ed
to
p
r
o
d
u
ce
a
clas
s
i
f
icatio
n
o
n
tr
ai
n
in
g
d
ata
an
d
r
eg
r
es
s
io
n
m
o
d
e
l
i
n
to
a
tr
ee
s
tr
u
ctu
r
e
is
ca
lled
as
Dec
is
io
n
tr
ee
alg
o
r
ith
m
,
it
is
b
ased
o
n
p
r
ev
io
u
s
d
ata
to
class
if
y
/p
r
ed
ict
class
o
r
tar
g
et
v
ar
iab
les
o
f
f
u
t
u
r
e/n
e
w
d
ata
w
it
h
th
e
h
elp
o
f
d
ec
is
io
n
r
u
les
o
r
d
ec
is
io
n
tr
ee
s
.
Dec
is
io
n
tr
ee
ca
n
b
e
u
s
ef
u
l
f
o
r
b
o
th
n
u
m
er
ical
an
d
ca
teg
o
r
ical
d
ata.
T
h
e
tr
ee
in
w
h
ic
h
th
e
r
o
o
t
n
o
d
e
in
ea
ch
lev
el
is
a
s
tar
ti
n
g
p
o
in
t
o
r
th
e
b
est
s
p
litt
in
g
attr
ib
u
te
in
t
h
at
p
o
s
itio
n
w
h
ic
h
h
elp
s
to
test
o
n
an
attr
ib
u
te
i
s
ca
lled
as
co
m
p
let
e
d
ec
is
io
n
tr
ee
.
T
h
e
y
ield
o
f
t
h
e
test
w
ill
cr
ea
te
b
r
an
ch
es.
L
ea
f
h
u
b
w
ill
g
o
ab
o
u
t
as
a
last
c
lass
m
ar
k
o
r
tar
g
et
v
ar
iab
le
to
ch
ar
ac
ter
ize/f
o
r
ese
e
th
e
n
e
w
i
n
f
o
r
m
atio
n
.
A
r
r
a
n
g
e
m
en
t r
u
les ar
e
attr
ac
ted
f
r
o
m
r
o
o
t to
leaf
.
4
.
1
.
4
.
Na
ïv
e
b
a
y
es
T
h
e
alg
o
r
ith
m
p
er
f
o
r
m
s
clas
s
if
icatio
n
ta
s
k
s
i
n
t
h
e
f
ie
ld
o
f
ML
ar
e
ca
lled
a
s
Na
ïv
e
B
a
y
es
.
I
t
ca
n
p
er
f
o
r
m
cla
s
s
i
f
ica
tio
n
v
er
y
well
o
n
th
e
d
atase
t
ev
e
n
it
h
as
h
u
g
e
r
ec
o
r
d
s
w
it
h
m
u
lti
clas
s
an
d
b
in
ar
y
c
las
s
class
i
f
icatio
n
p
r
o
b
lem
s
.
T
h
e
ap
p
licatio
n
o
f
Nai
v
e
B
a
y
es
i
s
m
ai
n
l
y
to
tex
t
an
al
y
s
is
a
n
d
Natu
r
al
L
an
g
u
ag
e
P
r
o
ce
s
s
in
g
.
I
t
w
o
r
k
s
b
ased
o
n
co
n
d
it
io
n
al
p
r
o
b
ab
ilit
y
.
I
t c
a
n
b
e
r
ep
r
esen
ted
(
1
)
.
(
|
)
=
(
|
)
(
)
(
)
(
1
)
Her
e
M
an
d
N
ar
e
t
w
o
ev
e
n
ts
an
d
,
P
(
M|
N
)
is
th
e
co
n
d
itio
n
a
l
p
r
o
b
a
b
ilit
y
o
f
M
g
iven
N
.
P
(
M)
is
t
h
e
p
r
o
b
ab
ilit
y
o
f
M.
P
(
N)
is
th
e
p
r
o
b
ab
ilit
y
o
f
N
.
P
(
N
|
M)
i
s
th
e
co
n
d
itio
n
a
l p
r
o
b
a
b
ilit
y
of
N
g
iven
M.
4
.
1
.
5
.
K
-
nea
re
s
t
neig
hb
o
rs
T
h
e
s
u
p
er
v
i
s
ed
class
if
ier
w
h
i
ch
is
a
b
est
c
h
o
ice
f
o
r
K
-
N
N
is
ca
l
led
as
k
-
Nea
r
est
Ne
i
g
h
b
o
r
.
I
t
is
a
b
est c
h
o
ice
f
o
r
th
e
clas
s
i
f
ica
tio
n
o
f
k
-
NN
k
i
n
d
o
f
p
r
o
b
lem
s
.
I
n
o
r
d
er
to
p
r
ed
ict
th
e
tar
g
et
lab
el
o
f
a
te
s
t d
ata,
KNN
w
h
ich
f
i
n
d
s
d
is
tan
ce
b
e
t
w
ee
n
n
ea
r
est
tr
ai
n
i
n
g
d
ata
cl
ass
lab
els
a
n
d
n
e
w
tes
t
d
ata
p
o
in
t
i
n
t
h
e
p
r
esen
ce
o
f
K
v
al
u
e?
KNN
u
s
es
K
v
ar
ia
b
le
v
alu
e
b
et
w
ee
n
0
to
1
0
n
o
r
m
all
y
.
4
.
2
.
Reg
re
s
s
io
n
4
.
2
.
1
.
Si
m
ple l
inea
r
re
g
re
s
s
io
n
T
h
e
lin
ea
r
R
eg
r
ess
io
n
alg
o
r
ith
m
w
h
ic
h
ex
p
lai
n
s
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
in
d
ep
en
d
en
t
an
d
d
ep
en
d
en
t
v
ar
iab
les
to
p
r
ed
ict
th
e
v
al
u
e
s
o
f
t
h
e
d
ep
en
d
en
t
v
ar
iab
le
is
ca
lled
as
Si
m
p
le
L
i
n
ea
r
R
e
g
r
ess
io
n
alg
o
r
ith
m
.
Si
m
p
le
r
eg
r
ess
io
n
u
s
e
s
o
n
e
in
d
ep
en
d
en
t
v
a
r
iab
le.
Th
e
s
i
m
p
le
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el
is
r
ep
r
esen
ted
(
2
)
.
y
=
(
b
0
+b
1
x)
(
2
)
Her
e,
x
(
in
d
ep
en
d
e
n
t
v
ar
iab
le)
an
d
y
(
d
ep
en
d
an
t
v
ar
iab
le)
a
r
e
t
w
o
f
ac
to
r
s
in
v
o
l
v
ed
i
n
s
i
m
p
le
li
n
ea
r
r
eg
r
ess
io
n
an
al
y
s
i
s
.
A
ls
o
,
b
0
is
th
e
Y
-
in
ter
ce
p
t a
n
d
b
1
is
t
h
e
S
lo
p
e.
4
.
2
.
2
.
M
ultiple
lin
ea
r
re
g
re
s
s
io
ns
I
t
ex
p
lain
s
t
h
e
r
elatio
n
s
h
ip
b
e
t
w
ee
n
t
w
o
o
r
m
o
r
e
i
n
d
ep
en
d
en
t
v
ar
iab
les
a
n
d
a
d
ep
en
d
en
t
v
ar
iab
le
to
p
r
ed
ict
th
e
v
a
lu
e
s
o
f
t
h
e
d
ep
en
d
en
t
v
ar
iab
le.
I
t
u
s
e
s
t
w
o
o
r
m
o
r
e
in
d
ep
en
d
e
n
t
v
ar
iab
les.
Dep
en
d
en
t
v
ar
iab
le
h
as
a
co
n
ti
n
u
o
u
s
a
n
d
in
d
ep
en
d
e
n
t
v
ar
iab
le
h
as
d
is
cr
ete
o
r
co
n
tin
u
o
u
s
v
al
u
es.
T
h
e
m
u
ltip
l
e
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el
i
s
r
ep
r
esen
ted
as
(
3
)
y
=
(
p
0
+p
1
x
1
+p
2
x
2
+…+
p
n
x
n
)
(
3
)
Her
e
x
1,
x
2
...
x
n
(
in
d
ep
en
d
e
n
t
v
ar
iab
le)
an
d
y
(
d
ep
en
d
an
t
v
ar
iab
le)
ar
e
tw
o
f
ac
to
r
s
i
n
v
o
lv
ed
in
m
u
ltip
le
li
n
ea
r
r
eg
r
ess
io
n
an
al
y
s
i
s
.
A
ls
o
b
0
is
th
e
y
-
in
ter
ce
p
t
an
d
p
1
, p
2
…
p
n
is
th
e
s
lo
p
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8814
I
n
t J
A
d
v
A
p
p
l Sci
,
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
:
85
–
92
90
4
.
2
.
3
.
L
o
g
is
t
ic
re
g
re
s
s
io
n
T
h
e
p
r
e
d
ictiv
e
an
al
y
s
is
w
h
ic
h
is
u
s
ed
f
o
r
th
e
d
ep
en
d
en
t
v
ar
iab
le
is
ca
teg
o
r
ical
ca
lled
as
L
o
g
i
s
tical
R
eg
r
es
s
io
n
.
L
o
g
is
tical
R
eg
r
e
s
s
io
n
e
x
p
lai
n
s
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
o
n
e
d
ep
en
d
en
t
v
ar
iab
le
an
d
o
n
e
o
r
m
o
r
e
in
d
ep
en
d
en
t
v
ar
iab
les.
T
h
e
v
a
r
io
u
s
t
y
p
es o
f
L
o
g
is
tic
R
e
g
r
es
s
io
n
ar
e:
Mu
lti
n
o
m
ial
L
o
g
is
tic
R
e
g
r
ess
i
o
n
(
m
an
y
)
B
in
ar
y
L
o
g
is
tic
R
e
g
r
ess
io
n
(
t
w
o
)
Or
d
in
al
L
o
g
is
t
ic
R
e
g
r
ess
io
n
(
1)
T
h
e
ca
teg
o
r
ical
r
esp
o
n
s
e
h
a
s
o
n
l
y
t
w
o
p
o
s
s
ib
le
o
u
tco
m
es
.
Mu
lti
n
o
m
ial
L
o
g
is
t
ic
R
e
g
r
ess
io
n
h
a
s
th
r
ee
o
r
m
o
r
e
o
u
tco
m
es
w
it
h
o
u
t
o
r
d
er
in
g
w
h
er
ea
s
Or
d
i
n
al
L
o
g
i
s
tic
R
e
g
r
es
s
io
n
h
as
t
h
r
ee
o
r
m
o
r
e
o
u
tco
m
e
s
w
it
h
o
r
d
er
in
g
.
4
.
2
.
4
.
P
o
ly
no
m
ia
l
r
eg
re
s
s
io
n
T
h
e
f
o
r
m
o
f
r
eg
r
es
s
io
n
a
n
al
y
s
is
w
h
ic
h
ex
p
lai
n
s
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
in
d
ep
en
d
e
n
t
v
ar
iab
l
e
an
d
d
ep
en
d
en
t
v
ar
iab
le
a
s
a
n
n
t
h
d
e
g
r
ee
p
o
l
y
n
o
m
ial
is
ca
l
led
as
p
o
l
y
n
o
m
ial
r
e
g
r
ess
io
n
.
I
t
f
its
a
n
o
n
-
li
n
ea
r
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
v
a
lu
e
o
f
i
n
d
ep
en
d
en
t
v
ar
iab
le
a
n
d
co
n
d
itio
n
al
m
ea
n
o
f
d
ep
en
d
en
t
v
ar
iab
le.
I
t
is
r
ep
r
esen
ted
as
(
4
)
.
x
=
a
+
b
*
y
^
n
(
4
)
Her
e
p
is
Dep
en
d
en
t V
ar
iab
le,
q
is
I
n
d
ep
en
d
en
t V
ar
iab
le
an
d
n
is
De
g
r
ee
.
I
t
is
u
s
ed
to
f
it
t
h
e
d
ata
v
er
y
w
ell
w
h
e
n
th
e
d
ata
is
b
el
o
w
a
n
d
ab
o
v
e
t
h
e
r
eg
r
e
s
s
io
n
m
o
d
el.
I
t
m
i
n
i
m
izes t
h
e
co
s
t
f
u
n
ctio
n
a
n
d
p
r
o
v
id
es o
p
tim
u
m
r
es
u
lt o
n
th
e
r
eg
r
es
s
io
n
.
4
.
2
.
5
.
L
inea
r
di
s
cr
i
m
i
na
nt
a
na
ly
s
is
T
h
e
p
r
o
ce
s
s
o
f
u
s
in
g
v
ar
io
u
s
d
ata
ite
m
s
an
d
ap
p
l
y
in
g
d
i
f
f
er
en
t
f
u
n
ctio
n
s
to
t
h
at
s
et
t
o
an
al
y
ze
class
es
o
f
o
b
j
ec
ts
o
r
item
s
s
ep
ar
at
el
y
is
ca
lled
L
in
ea
r
Dis
cr
i
m
in
a
n
t
An
al
y
s
i
s
.
I
m
ag
e
R
ec
o
g
n
i
tio
n
a
n
d
P
r
ed
ictiv
e
an
al
y
tic
s
u
s
e
t
h
is
L
i
n
ea
r
Dis
cr
i
m
i
n
an
t
An
al
y
s
i
s
4.3.
Clus
t
er
ing
4
.
3
.
1
.
K
-
m
ea
ns
cl
us
t
er
ing
T
h
e
u
n
s
u
p
er
v
i
s
ed
m
ac
h
in
e
l
ea
r
n
in
g
al
g
o
r
ith
m
w
h
ich
i
s
u
s
ed
to
s
o
lv
e
cl
u
s
ter
i
n
g
p
r
o
b
le
m
s
b
y
class
i
f
y
in
g
th
e
d
ataset
i
n
to
a
n
u
m
b
er
o
f
clu
s
ter
s
k
(
g
r
o
u
p
o
f
s
i
m
ilar
o
b
j
ec
ts
)
,
w
h
ic
h
d
ef
in
es
t
h
e
n
u
m
b
er
o
f
clu
s
ter
s
w
h
ic
h
i
s
ass
u
m
ed
b
ef
o
r
e
class
if
y
i
n
g
t
h
e
d
ataset.
4
.
3
.
2
.
H
iera
rc
hica
l
clus
t
er
ing
T
h
e
ty
p
e
o
f
clu
s
ter
i
n
g
al
g
o
r
ith
m
w
h
ic
h
is
u
s
ed
to
b
u
ild
a
h
ier
ar
c
h
y
o
f
cl
u
s
ter
s
i
s
ca
lled
h
ier
ar
ch
ical
clu
s
ter
i
n
g
.
T
h
e
t
w
o
t
y
p
es o
f
H
ier
ar
ch
ical
C
l
u
s
ter
i
n
g
ar
e:
4
.
3
.
3
.
Ag
g
lo
m
er
a
t
iv
e
clus
t
er
ing
I
t
is
u
s
ed
to
g
r
o
u
p
o
b
j
ec
ts
in
t
o
clu
s
ter
s
b
ased
o
n
th
e
ir
s
i
m
il
ar
it
y
.
T
h
e
r
es
u
lt
o
b
tai
n
ed
at
la
s
t
is
a
tr
e
e
r
ep
r
esen
tatio
n
o
f
o
b
j
ec
ts
c
alled
Den
d
r
o
g
r
a
m
.
4
.
3
.
4
.
Div
is
iv
e
a
na
ly
s
is
T
h
is
is
a
b
est
d
o
w
n
m
et
h
o
d
o
lo
g
y
w
h
er
e
all
p
er
ce
p
tio
n
s
b
eg
in
in
o
n
e
b
u
n
c
h
,
an
d
p
ar
ts
ar
e
p
er
f
o
r
m
ed
r
ec
u
r
s
iv
e
l
y
a
s
o
n
e
m
o
v
es
d
o
w
n
t
h
e
p
ec
k
i
n
g
o
r
d
er
.
A
h
ier
ar
ch
ical
c
lu
s
t
er
in
g
i
s
o
f
t
en
r
ep
r
esen
ted
as
a
d
en
d
r
o
g
r
am
.
E
ac
h
clu
s
ter
w
i
ll b
e
r
ep
r
esen
tin
g
w
it
h
ce
n
tr
o
i
d
s
.
Dis
tan
ce
w
i
ll b
e
ca
lcu
lated
b
y
u
s
i
n
g
lin
k
a
g
e.
5.
RE
SU
L
T
S
AND
AN
AL
Y
SI
S
I
n
d
ian
d
iab
etes
d
ataset
n
a
m
e
d
PIM
A
w
er
e
u
s
ed
f
o
r
an
al
y
s
i
s
f
o
r
th
is
s
tu
d
y
.
I
t
co
n
s
i
s
t
s
o
f
eig
h
t
in
d
ep
en
d
en
t
attr
ib
u
te
s
a
n
d
o
n
e
in
d
ep
en
d
en
t
cla
s
s
at
tr
ib
u
te.
T
h
e
s
tu
d
y
w
as
i
m
p
le
m
e
n
ted
b
y
R
p
r
o
g
r
a
m
m
i
n
g
lan
g
u
a
g
e
u
s
i
n
g
R
St
u
d
io
.
Ma
c
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
li
k
e
class
i
f
icatio
n
(
Dec
i
s
io
n
T
r
ee
,
Naïv
e
B
a
y
es,
k
-
NN
an
d
R
a
n
d
o
m
Fo
r
est),
r
eg
r
es
s
io
n
(
li
n
ea
r
,
m
u
ltip
le,
lo
g
is
ti
c,
L
D
A
)
a
n
d
clu
s
ter
in
g
(
k
-
m
ea
n
s
,
h
ier
ar
ch
ica
l
ag
g
lo
m
er
ati
v
e)
ar
e
u
s
ed
to
p
r
ed
ict
th
e
d
iab
etics
d
is
ea
s
e
in
ea
r
l
y
s
ta
g
es
as
s
h
o
w
n
i
n
T
ab
le
1
.
Me
asu
r
e
P
er
f
o
r
m
a
n
ce
m
o
d
el
b
y
u
s
i
n
g
a
cc
u
r
ac
y
as
s
h
o
w
n
in
Fig
u
r
e
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
d
v
A
p
p
l Sci
I
SS
N:
2
2
5
2
-
8814
Dis
ea
s
e
p
r
ed
ictio
n
in
b
ig
d
a
ta
h
ea
lth
ca
r
e
u
s
in
g
ex
ten
d
ed
co
n
vo
lu
tio
n
a
l n
eu
r
a
l n
etw
o
r
k…
(
A
s
a
d
i S
r
in
iva
s
u
lu
)
91
T
ab
le
1
.
P
r
ed
ictiv
e
an
al
y
s
is
o
f
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
S
.
N
o
A
l
g
o
r
i
t
h
m
A
c
c
u
r
a
c
y
1
R
a
n
d
o
m fo
r
e
st
8
3
%
2.
D
e
c
i
si
o
n
t
r
e
e
7
7
%
3.
S
V
M
9
2
%
4.
N
a
ï
v
e
B
a
y
e
s
8
6
%
5.
K
-
NN
9
1
%
6.
S
i
mp
l
e
l
i
n
e
a
r
r
e
g
r
e
ssi
o
n
9
8
%
7.
L
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
8
8
%
8.
L
D
A
8
8
%
9.
k
-
M
e
a
n
s
8
1
%
1
0
.
H
i
e
r
a
r
c
h
i
c
a
l
a
g
g
l
o
me
r
a
t
i
v
e
7
4
%
Fig
u
r
e
2
.
C
o
m
p
ar
is
o
n
o
f
ac
c
u
r
ac
y
o
f
v
ar
io
u
s
al
g
o
r
ith
m
s
6.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
Dee
p
L
ea
r
n
i
n
g
a
n
d
Data
m
in
i
n
g
p
la
y
s
an
i
m
p
o
r
tan
t
r
o
le
in
v
ar
io
u
s
f
ie
ld
s
s
u
ch
as
A
r
ti
f
icia
l
I
n
telli
g
en
ce
(
A
I
)
an
d
Ma
c
h
in
e
L
ea
r
n
i
n
g
(
ML
)
,
Data
b
ase
S
y
s
te
m
s
a
n
d
m
o
r
e.
T
h
e
co
r
e
o
b
j
e
ctiv
e
is
to
en
h
a
n
ce
th
e
ac
c
u
r
ac
y
o
f
p
r
ed
icti
v
e
m
o
d
el
.
T
h
is
P
I
MA
d
ata
s
et
w
i
ll
i
n
cr
ea
s
e
t
h
e
ac
c
u
r
ac
y
o
f
al
m
o
s
t
all
al
g
o
r
ith
m
s
b
u
t
th
e
S
VM
a
n
d
lin
ea
r
r
e
g
r
ess
io
n
lead
s
o
v
er
o
th
er
s
.
I
n
f
u
tu
r
e
m
an
y
ad
v
an
ce
d
d
ee
p
lear
n
in
g
tech
n
iq
u
e
s
w
il
l
b
e
u
s
ed
to
in
cr
ea
s
i
n
g
th
e
ac
c
u
r
ac
y
o
f
t
h
e
alg
o
r
it
h
m
s
.
RE
F
E
R
E
NC
E
S
[1
]
Us
m
a
Ni
y
a
z
e
t
a
l,
“
A
d
v
a
n
c
e
s
in
De
e
p
L
e
a
rn
in
g
Tec
h
n
iq
u
e
s
f
o
r
M
e
d
ica
l
Im
a
g
e
A
n
a
l
y
sis”
5
th
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
P
a
ra
ll
e
l,
Distri
b
u
ted
a
n
d
Gr
id
Co
mp
u
ti
n
g
(
PDGC
-
2
0
1
8
),
9
7
8
-
1
-
5
3
8
6
-
6
0
2
6
-
3
/1
8
/$
3
1
©2
0
1
8
I
EE
E,
20
-
2
2
De
c
,
2
0
1
8
,
S
o
la
n
,
I
n
d
ia.
[2
]
Y.
L
e
Cu
n
,
L
.
B
o
tt
o
u
,
Y.
Be
n
g
io
a
n
d
P
.
Ha
ff
n
e
r,
“
G
r
a
d
ien
t
-
Ba
se
d
L
e
a
rn
in
g
A
p
p
li
e
d
to
Do
c
u
m
e
n
t
Re
c
o
g
n
it
io
n
,
”
Pro
c
e
e
d
in
g
s
o
f
IE
EE
,
v
o
l
.
8
6
,
p
p
.
2
2
7
8
-
2
3
2
4
.
[3
]
L
e
slie
N.
S
m
it
h
,
“
C
y
c
li
c
a
l
L
e
a
r
n
in
g
Ra
tes
f
o
r
T
ra
in
in
g
Ne
u
ra
l
Ne
tw
o
rk
s,”
2
0
1
7
IEE
E
W
in
ter
Co
n
fer
e
n
c
e
o
n
Ap
p
l
ic
a
ti
o
n
s
o
f
Co
m
p
u
ter
V
isio
n
(
W
ACV
),
p
p
.
4
6
4
–
4
7
2
,
2
0
1
7
.
[4
]
J.
W
a
n
g
,
L
.
P
e
re
z
,
“
T
h
e
Eff
e
c
ti
v
e
n
e
ss
o
f
Da
ta
A
u
g
m
e
n
tatio
n
i
n
Im
a
g
e
Clas
si
f
ica
ti
o
n
u
sin
g
D
e
e
p
L
e
a
rn
in
g
,
”
Co
mp
u
t
in
g
Res
e
a
rc
h
Rep
o
sit
o
ry
(Co
RR
)
-
a
r
X
iv
,
2
0
1
7
.
[5
]
N.
S
riv
a
sta
v
a
,
G
.
Hin
to
n
,
A
.
Kriz
h
e
v
sk
y
a
n
d
I.
S
u
tsk
e
v
e
r
a
n
d
R.
S
a
lak
h
u
td
i
n
o
v
,
“
Dro
p
o
u
t:
A
S
im
p
le
Wa
y
to
P
re
v
e
n
t
Ne
u
ra
l
Ne
tw
o
rk
s
f
ro
m
Ov
e
r
f
it
ti
n
g
,
”
J
o
u
rn
a
l
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
Res
e
a
rc
h
(J
M
L
R)
,
v
o
l.
1
5
,
p
p
.
1
9
2
9
-
1
9
5
8
,
2
0
1
4
.
[6
]
M
.
S
.
A
l
-
tara
w
n
e
h
,
“
L
u
n
g
Ca
n
c
e
r
De
tec
ti
o
n
Us
in
g
I
m
a
g
e
P
ro
c
e
ss
in
g
T
e
c
h
n
iq
u
e
s,”
L
e
o
n
a
rd
o
El
e
c
tro
n
ic
J
o
u
r
n
a
l
o
f
Pra
c
ti
c
e
s a
n
d
T
e
c
h
n
o
l
o
g
ies
(
L
EJPT
)
,
n
o
.
2
0
,
p
p
.
1
4
7
–
1
5
8
,
2
0
1
2
.
[7
]
A
b
h
ish
e
k
S
.
S
a
m
b
y
a
l,
As
h
a
T
.
,
“
Kn
o
w
led
g
e
A
b
stra
c
ti
o
n
f
ro
m
T
e
x
tu
ra
l
F
e
a
tu
re
s
o
f
Bra
in
M
RI
Im
a
g
e
s
f
o
r
Dia
g
n
o
sin
g
Bra
in
T
u
m
o
r
u
si
n
g
S
tatisti
c
a
l
T
e
c
h
n
iq
u
e
s
a
n
d
A
s
so
c
iativ
e
Clas
si
f
ica
ti
o
n
,
”
2
0
1
6
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
y
ste
ms
in
M
e
d
ici
n
e
a
n
d
B
io
l
o
g
y
,
IIT
Kh
a
ra
g
p
u
r
,
2
0
1
6
.
[8
]
A
.
Kriz
h
e
v
s
k
y
,
I.
S
u
tsk
e
v
e
r
a
n
d
G
.
E.
Hin
t
o
n
,
“
Im
a
g
e
Ne
t
Cl
a
ss
if
i
c
a
ti
o
n
w
it
h
De
e
p
Co
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s,”
NIPS
’1
2
Pr
o
c
e
e
d
in
g
s
o
f
th
e
2
5
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ne
u
ra
l
I
n
fo
rm
a
ti
o
n
Pro
c
e
ss
in
g
S
y
ste
ms
,
v
o
l.
1
,
p
p
.
1
0
9
7
–
1
1
0
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8814
I
n
t J
A
d
v
A
p
p
l Sci
,
Vo
l.
9
,
No
.
2
,
J
u
n
e
2020
:
85
–
92
92
[9
]
K.
S
im
o
n
y
a
n
a
n
d
A
.
Zi
ss
e
r
m
a
n
,
“
V
e
ry
De
e
p
Co
n
v
o
lu
t
io
n
a
l
Ne
tw
o
rk
f
o
r
L
a
r
g
e
-
S
c
a
l
e
I
m
a
g
e
Re
c
o
g
n
it
io
n
,
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
L
e
a
rn
in
g
Rep
re
se
n
ta
ti
o
n
s (
ICL
R)
,
2
0
1
5
.
[1
0
]
C.
S
z
e
g
e
d
y
,
W
.
L
iu
,
Y.
Jia
,
P
.
S
e
r
m
a
n
e
t,
S
.
Re
e
d
,
D.
A
n
g
u
e
lo
v
,
D.
Erh
a
n
,
V.
V
a
n
h
o
u
c
k
e
,
A
.
Ra
b
in
o
v
ich
,
“
G
o
in
g
d
e
e
p
e
r
w
it
h
c
o
n
v
o
lu
ti
o
n
s
,
”
2
0
1
5
IEE
E
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
Vi
sio
n
a
n
d
Pa
tt
e
rn
Rec
o
g
n
it
io
n
(
CVP
R
),
p
p
.
1
–
9
,
2
0
1
5
.
[1
1
]
K.
He
,
X.
Z
h
a
n
g
,
S
.
Re
n
,
J
.
S
u
n
,
“
De
e
p
Re
sid
u
a
l
L
e
a
rn
in
g
f
o
r
Im
a
g
e
Re
c
o
g
n
it
io
n
,
”
2
0
1
6
IEE
E
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ter
V
isio
n
a
n
d
Pa
t
ter
n
Rec
o
g
n
it
io
n
(
CVP
R),
p
p
.
7
7
0
-
7
7
8
,
2
0
1
6
.
[1
2
]
O.
Ro
n
n
e
b
e
rg
e
r,
P
.
F
isc
h
e
r,
a
n
d
T
.
Bro
x
,
“
U
-
Ne
t:
Co
n
v
o
lu
ti
o
n
a
l
Ne
tw
o
rk
s
f
o
r
Bio
m
e
d
ica
l
I
m
a
g
e
S
e
g
m
e
n
tatio
n
,
”
M
ICCAI
2
0
1
5
,
p
p
.
2
3
4
?
2
4
1
,
2
0
1
5
.
[1
3
]
F
.
M
il
leta
ri,
N.
Na
v
a
b
,
a
n
d
S
.
A
.
A
h
m
a
d
i,
“
V
-
Ne
t:
F
u
ll
y
Co
n
v
o
lu
ti
o
n
a
l
Ne
tw
o
rk
s
f
o
r
V
o
l
u
m
e
tri
c
M
e
d
ica
l
Im
a
g
e
S
e
g
m
e
n
tatio
n
,
”
2
0
1
6
F
o
u
rt
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
3
D
Vi
sio
n
,
p
p
.
5
6
5
-
5
7
1
,
2
0
1
6
.
[1
4
]
E.
G
ib
so
n
,
W
.
L
i,
C.
S
u
d
re
,
L
.
F
i
d
o
n
,
D.
I.
S
h
a
k
ir,
G
.
W
a
n
g
Z.
Eat
o
n
-
Ro
se
n
,
R.
G
ra
y
,
T
.
Do
e
l,
Y.
Hu
,
T
.
W
h
y
n
ti
e
,
P
.
Na
c
h
e
v
,
M
.
M
o
d
a
t
D.
C.
Ba
rr
a
tt
,
S
.
Ou
rse
li
n
,
M
.
Jo
rg
e
Ca
rd
o
so
a
n
d
T
.
V
e
rc
a
u
tere
n
,
“
Nif
ty
Ne
t:
a
d
e
e
p
-
lea
rn
i
n
g
p
latf
o
rm
f
o
r
m
e
d
ica
l
i
m
a
g
in
g
,
”
C
o
mp
u
ter
M
e
th
o
d
s
a
n
d
Pro
g
ra
ms
i
n
Bi
o
me
d
ici
ne
,
v
o
l.
1
5
8
,
p
p
.
1
1
3
-
1
2
2
,
2
0
1
8
.
[1
5
]
S
.
Jg
o
u
,
M
.
Dro
z
d
z
a
l,
D.
V
z
q
u
e
z
,
A
.
Ro
m
e
ro
,
a
n
d
Y.
Be
n
g
i
o
,
“
T
h
e
On
e
Hu
n
d
re
d
L
a
y
e
rs
T
ira
m
isu
:
F
u
ll
y
Co
n
v
o
l
u
ti
o
n
a
l
De
n
se
Ne
ts f
o
r
S
e
m
a
n
ti
c
S
e
g
m
e
n
tatio
n
,
”
a
rXiv
:1
6
1
1
.
0
9
3
2
6
v
2
[
c
s.C
V]
,
2
0
1
6
.
[1
6
]
W
.
Ch
e
n
,
Y.
Zh
a
n
g
,
J.
H
e
,
Y.
Qia
o
,
Y.
Ch
e
n
,
H.
S
h
i,
X
.
T
a
n
g
,
“
W
-
n
e
t:
Brid
g
e
d
U
-
n
e
t
f
o
r
2
D
M
e
d
ica
l
I
m
a
g
e
S
e
g
m
e
n
tatio
n
,
”
a
rX
iv
:
1
8
0
7
.
0
4
4
5
9
v
1
[
c
s.CV] 1
2
Ju
l
2
0
1
8
.
[1
7
]
G
.
Ya
n
g
,
H.
Jin
g
,
“
M
u
lt
ip
le
C
o
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
f
o
r
F
e
a
tu
re
Ex
trac
ti
o
n
,
”
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
In
telli
g
e
n
t
Co
m
p
u
t
in
g
(
I
CIC)
,
2
0
1
5
.
[1
8
]
J.
Din
g
,
A
.
L
i,
Z.
Hu
,
a
n
d
L
.
Wan
g
,
“
Ac
c
u
ra
te
P
u
lm
o
n
a
ry
No
d
u
le
De
tec
ti
o
n
in
Co
m
p
u
ted
T
o
m
o
g
ra
p
h
y
I
m
a
g
e
s
Us
in
g
De
e
p
Co
n
v
o
l
u
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s,”
Co
mp
u
ti
n
g
Res
e
a
rc
h
Rep
o
sito
ry
(
Co
RR
)
-
a
r
X
iv
,
2
0
1
7
.
[1
9
]
Q.
S
o
n
g
,
L
.
Z
h
a
o
,
X
.
L
u
o
,
a
n
d
X
.
Do
u
,
“
Us
in
g
D
e
e
p
L
e
a
rn
in
g
f
o
r
Clas
sif
ica
ti
o
n
o
f
L
u
n
g
No
d
u
le
s
o
n
Co
m
p
u
ted
T
o
m
o
g
ra
p
h
y
I
m
a
g
e
s,”
J
o
u
rn
a
l
o
f
He
a
lt
h
c
a
re
E
n
g
i
n
e
e
rin
g
,
v
o
l.
2
0
1
7
,
2
0
1
7
.
[2
0
]
H.
Ch
o
u
g
ra
d
,
H.
Zo
u
a
k
i,
O.
A
l
h
e
y
a
n
e
“
Co
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s
f
o
r
Bre
a
st
Ca
n
c
e
r
S
c
r
e
e
n
in
g
:
T
ra
n
s
f
e
r
L
e
a
rn
in
g
w
it
h
Ex
p
o
n
e
n
ti
a
l
De
c
a
y
,
”
-
a
rX
iv
,
2
0
1
7
.
[2
1
]
A
.
Este
v
a
,
B.
Ku
p
re
l,
R.
A
.
No
v
o
a
,
J.
Ko
,
S
.
M
.
S
w
e
tt
e
r,
H.
M
.
Blau
&
S
.
T
h
ru
n
,
“
De
rm
a
to
lo
g
ist
-
lev
e
l
c
las
si
f
ica
ti
o
n
o
f
sk
in
c
a
n
c
e
r
w
it
h
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
s,”
Na
tu
re
,
v
o
l.
5
4
2
,
p
p
.
1
1
5
–
1
1
8
,
2
0
1
7
.
[2
2
]
E.
S
e
rt,
S
.
Ert
e
k
in
,
U.
Ha
li
c
i,
“
En
se
m
b
le
o
f
Co
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
t
w
o
rk
s
f
o
r
Cla
ss
i
f
ica
ti
o
n
o
f
Bre
a
st
M
icro
c
a
lcif
ica
ti
o
n
f
ro
m
M
a
m
m
o
g
ra
m
s,”
2
0
1
7
3
9
th
A
n
n
u
a
l
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
f
th
e
IEE
E
En
g
i
n
e
e
rin
g
i
n
M
e
d
icin
e
a
n
d
Bi
o
lo
g
y
S
o
c
iety
(
EM
BC)
,
p
p
.
6
8
9
–
6
9
2
,
2
0
1
7
.
[2
3
]
N.
C.
F
.
C
o
d
e
ll
a
,
Q.
B
.
Ng
u
y
e
n
,
S
.
P
a
n
k
a
n
ti
,
D.
G
u
tma
n
,
B.
He
lb
a
,
A
.
Ha
lp
e
rn
,
J.
R.
S
m
it
h
,
“
De
e
p
lea
rn
in
g
e
n
se
m
b
les
f
o
r
m
e
lan
o
m
a
re
c
o
g
n
it
io
n
in
d
e
rm
o
sc
o
p
y
i
m
a
g
e
s,”
Co
mp
u
ti
n
g
Res
e
a
rc
h
Rep
o
sit
o
ry
(
Co
RR
)
,
v
o
l.
a
b
s/1
6
1
0
.
0
4
6
6
2
,
2
0
1
6
.
[24]
K.
J.
G
e
ra
s,
S
.
W
o
lf
so
n
,
Y.
S
h
e
n
,
S
.
G
e
n
e
Kim
,
L
.
M
o
y
,
K.
Ch
o
,
“
Hig
h
-
Re
so
lu
ti
o
n
Bre
a
st
Ca
n
c
e
r
S
c
re
e
n
in
g
w
it
h
M
u
lt
i
-
V
iew
De
e
p
Co
n
v
o
l
u
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s,”
Co
mp
u
ti
n
g
Re
se
a
rc
h
Rep
o
sit
o
ry
(
Co
RR
)
-
a
r
X
i
v
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.