I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
,
p
p
.
4
8
6
6
~
4
8
7
2
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
6
.
p
p
4
8
6
6
-
4872
4866
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
RB
-
b
a
y
es a
lg
o
rith
m
f
o
r
the
p
redic
tion o
f
dia
be
tic
in “PIM
A India
n
da
tas
et”
Ra
j
ni
1
,
A
m
a
n
deep
2
1
S
c
h
o
o
l
o
f
Co
m
p
u
ter A
p
p
li
c
a
ti
o
n
,
L
o
v
e
l
y
P
ro
f
e
ss
io
n
a
l
Un
iv
e
rsit
y
,
In
d
ia
2
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter A
p
p
li
c
a
ti
o
n
,
L
o
v
e
l
y
P
ro
f
e
ss
io
n
a
l
Un
iv
e
rsity
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
8
,
2
0
1
8
R
ev
i
s
ed
A
p
r
11
,
2
0
1
9
A
cc
ep
ted
J
u
n
27
,
2
0
1
9
Dia
b
e
tes
is
a
m
a
jo
r
c
o
n
c
e
rn
a
ll
o
v
e
r
th
e
w
o
rld
.
It
is
i
n
c
re
a
sin
g
a
t
a
f
a
st
p
a
c
e
.
P
e
o
p
le
c
a
n
a
v
o
i
d
d
ia
b
e
tes
a
t
a
n
e
a
rl
y
sta
g
e
w
it
h
o
u
t
a
n
y
tes
t.
T
h
e
g
o
a
l
o
f
th
is
p
a
p
e
r
is
to
p
re
d
ict
t
h
e
p
r
o
b
a
b
il
it
y
o
f
w
h
e
th
e
r
th
e
p
e
rso
n
h
a
s
a
risk
o
f
d
iab
e
tes
o
r
n
o
t
a
t
a
n
e
a
rly
sta
g
e
.
T
h
is
wo
u
l
d
lea
d
to
h
a
v
in
g
a
g
re
a
t
im
p
a
c
t
o
n
th
e
ir
q
u
a
li
ty
o
f
h
u
m
a
n
li
f
e
.
T
h
e
d
a
tas
e
ts
a
re
P
im
a
In
d
ian
s
d
iab
e
tes
a
n
d
Clev
e
lan
d
c
o
ro
n
a
ry
il
ln
e
ss
a
n
d
c
o
n
sist
o
f
7
6
8
re
c
o
r
d
s.
T
h
o
u
g
h
th
e
re
a
re
a
n
u
m
b
e
r
o
f
so
lu
ti
o
n
s
a
v
a
il
a
b
le
f
o
r
in
f
o
rm
a
ti
o
n
e
x
trac
ti
o
n
f
ro
m
a
h
u
g
e
d
a
tas
e
ts
a
n
d
to
p
re
d
ict
th
e
p
o
ss
ib
il
i
ty
o
f
h
a
v
in
g
d
iab
e
tes
,
b
u
t
t
h
e
a
c
c
u
ra
c
y
o
f
th
e
ir
m
in
in
g
p
ro
c
e
ss
is f
a
r
f
ro
m
a
c
c
u
ra
te.
F
o
r
a
c
h
iev
in
g
h
ig
h
e
st ac
c
u
ra
c
y
,
th
e
issu
e
o
f
z
e
ro
p
ro
b
a
b
il
it
y
w
h
ich
is
g
e
n
e
ra
ll
y
fa
c
e
d
b
y
n
a
ïv
e
b
a
y
e
s
a
n
a
l
y
sis
n
e
e
d
s
to
b
e
a
d
d
re
ss
e
d
su
it
a
b
ly
.
T
h
e
p
ro
p
o
s
e
d
f
ra
m
e
w
o
rk
RB
-
Ba
y
e
s
a
i
m
s
to
e
x
trac
t
th
e
re
q
u
ired
i
n
f
o
rm
a
ti
o
n
w
it
h
h
ig
h
a
c
c
u
ra
c
y
th
a
t
c
o
u
ld
su
rv
iv
e
th
e
p
ro
b
lem
o
f
z
e
ro
p
ro
b
a
b
il
it
y
a
n
d
a
lso
c
o
n
f
ig
u
re
a
c
c
u
ra
c
y
w
it
h
o
th
e
r
m
e
th
o
d
s
li
k
e
S
u
p
p
o
rt
V
e
c
t
o
r
M
a
c
h
i
n
e
,
Na
iv
e
Ba
y
e
s,
a
n
d
K
Ne
a
re
st
Ne
ig
h
b
o
r.
W
e
c
a
lcu
late
d
m
e
a
n
to
h
a
n
d
le
m
issin
g
d
a
ta
a
n
d
c
a
lcu
late
d
p
ro
b
a
b
il
it
y
f
o
r
y
e
s
(p
o
siti
v
e
)
a
n
d
n
o
(n
e
g
a
ti
v
e
).
T
h
e
h
ig
h
e
st
v
a
lu
e
b
e
tw
e
e
n
y
e
s
a
n
d
n
o
d
e
c
i
d
e
th
e
v
a
lu
e
f
o
r
th
e
tu
p
le
.
It
is
m
o
st
ly
u
se
d
in
tex
t
c
la
ss
i
f
ica
ti
o
n
.
T
h
e
o
u
tco
m
e
s
o
n
P
im
a
In
d
ian
d
iab
e
tes
d
a
tas
e
t
d
e
m
o
n
stra
te
th
a
t
th
e
p
ro
p
o
se
d
m
e
th
o
d
o
l
o
g
y
e
n
h
a
n
c
e
s
th
e
p
re
c
isio
n
a
s
a
c
o
n
tras
t
w
it
h
o
th
e
r
re
g
u
late
d
p
ro
c
e
d
u
re
s.
T
h
e
a
c
c
u
ra
c
y
o
f
th
e
p
ro
p
o
se
d
m
e
th
o
d
o
l
o
g
y
lar
g
e
d
a
tas
e
t
is
7
2
.
9
%
.
K
ey
w
o
r
d
s
:
A
cc
u
r
ac
y
B
ay
e
s
m
et
h
o
d
C
r
o
s
s
-
v
al
id
atio
n
P
I
MA
I
n
d
ian
d
ata
-
s
et
SVM
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Am
a
n
d
ee
p
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
A
p
p
licatio
n
,
L
o
v
el
y
P
r
o
f
ess
io
n
al
U
n
iv
er
s
it
y
,
P
h
ag
w
ar
a,
P
u
n
j
ab
,
I
n
d
ia.
E
m
ail:
a
m
an
d
ee
p
.
b
ag
g
a@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Diab
etes
is
a
d
is
ea
s
e
in
w
h
ic
h
b
lo
o
d
s
u
g
ar
lev
el
is
v
er
y
h
i
g
h
.
T
h
er
e
ar
e
tw
o
k
i
n
d
s
o
f
d
iab
etes.
I
N
T
y
p
e1
d
iab
etes
th
e
b
o
d
y
d
o
es
n
o
t
d
eliv
er
i
n
s
u
li
n
.
A
p
p
r
o
x
i
m
atel
y
1
0
%
o
f
all
ca
s
es
ar
e
T
y
p
e1
.
I
n
T
y
p
e
-
2
b
o
d
y
d
o
es
n
o
t
cr
ea
te
en
o
u
g
h
i
n
s
u
lin
.
R
o
u
g
h
l
y
9
0
%
o
f
all
i
n
s
tan
ce
s
o
f
d
iab
etes
w
o
r
ld
w
id
e
o
f
th
is
k
i
n
d
[
1
]
.
P
im
a
C
o
u
n
t
y
i
s
a
r
eg
io
n
i
n
t
h
e
s
o
u
t
h
f
o
ca
l
d
is
tr
ict
o
f
th
e
U.
S.
p
r
o
v
in
ce
o
f
A
r
izo
n
a.
P
I
MA
is
a
s
ta
n
d
o
u
t
a
m
o
n
g
s
t
th
e
m
o
s
t
s
t
u
d
ied
p
o
p
u
latio
n
w
it
h
r
esp
ec
t
to
d
iab
etes,
n
o
t
j
u
s
t
a
m
o
n
g
Nat
iv
e
Am
er
ican
s
y
e
t
ar
o
u
n
d
th
e
g
lo
b
e
[
2
]
.
Mo
s
t
o
f
th
e
r
esear
ch
o
n
d
iab
etes
d
id
u
s
e
P
im
a
I
n
d
ian
d
ataset.
T
h
e
d
ataset
c
o
n
tain
s
a
r
ec
o
r
d
o
f
th
o
s
e
d
iab
etic
p
atien
ts
t
h
at
i
n
s
in
u
ate
d
is
cr
ete
t
y
p
e
2
p
o
s
itiv
e
an
d
n
e
g
ati
v
e
ca
s
es.
T
h
e
co
u
r
s
e
f
o
r
a
d
iab
etes
p
atien
t
to
l
iv
e
w
it
h
t
h
is
ill
n
es
s
is
to
k
ee
p
th
e
g
l
u
co
s
e
as
t
y
p
ical
as
g
r
ea
t
w
it
h
o
u
t
g
en
u
i
n
e
h
i
g
h
o
r
lo
w
b
lo
o
d
s
u
g
ar
s
.
T
h
er
e
ar
e
a
n
u
m
b
er
o
f
w
a
y
s
th
r
o
u
g
h
w
h
ic
h
p
er
s
o
n
ca
n
s
u
r
v
i
v
e
w
it
h
t
h
i
s
d
is
ea
s
e
if
h
e/
s
h
e
is
u
s
in
g
co
r
r
ec
t
r
o
u
tin
e
li
f
e.
L
i
k
e,
m
a
n
ag
e
y
o
u
r
w
eig
h
t,
ex
er
ci
s
i
n
g
,
ea
tin
g
a
b
alan
ce
d
h
ea
lt
h
y
d
i
et,
li
m
iti
n
g
alco
h
o
l
in
ta
k
e,
co
n
tr
o
llin
g
b
lo
o
d
p
r
ess
u
r
e
o
r
u
s
in
g
a
k
i
n
d
o
f
in
s
u
li
n
[
3
]
.
A
cc
o
r
d
in
g
to
I
DF
(
I
n
ter
n
atio
n
al
Diab
etes
Fed
er
atio
n
)
,
d
iab
etes
p
er
s
o
n
is
in
cr
ea
s
i
n
g
d
a
y
b
y
d
a
y
[
4
]
.
I
t
h
as
r
e
ac
h
ed
3
8
2
m
illi
o
n
in
2
0
1
3
.
W
h
en
t
h
e
p
atien
t
is
d
iab
etic
an
d
h
a
v
in
g
s
tr
ess
al
s
o
th
i
s
lead
s
to
m
icr
o
v
asc
u
lar
d
a
m
ag
e
[
5
]
,
u
n
h
ea
lt
h
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
RB
-
b
a
ye
s
a
lg
o
r
ith
m
fo
r
th
e
p
r
ed
ictio
n
o
f d
i
a
b
etic
in
“PI
MA
I
n
d
ia
n
d
a
ta
s
et” (
R
a
jn
i)
4867
ch
o
lest
er
o
l
lev
el
a
ls
o
.
T
o
m
a
k
e
li
f
e
b
etter
,
w
e
n
ee
d
to
r
ec
o
r
d
h
is
to
r
y
ab
o
u
t
th
e
p
atie
n
t
,
s
o
th
at
it
w
il
l
h
elp
th
e
d
o
cto
r
s
to
tak
e
th
e
b
est
d
e
cisi
o
n
f
o
r
p
atien
t’
s
h
ea
lth
.
T
h
e
m
aj
o
r
g
o
al
o
f
th
is
p
ap
er
is
to
cr
ea
te
s
u
ch
an
al
g
o
r
ith
m
th
at
cr
ea
tes
a
g
r
o
u
p
o
f
p
atter
n
s
an
d
n
atu
r
al
l
y
s
et
tle
o
n
ch
o
ice
in
li
g
h
t
o
f
p
r
ep
ar
in
g
in
f
o
r
m
atio
n
[
6
]
.
T
o
ch
ec
k
v
alid
atio
n
o
f
t
h
e
alg
o
r
ith
m
,
w
e
ar
e
test
i
n
g
o
n
t
h
e
r
ea
l
-
ti
m
e
d
atas
et.
T
h
is
ca
n
b
e
ca
lled
s
u
p
er
v
is
ed
lear
n
i
n
g
.
T
r
ain
in
g
d
ata
ar
e
k
n
o
w
n
a
s
t
h
o
s
e
d
ata.
T
h
e
p
r
ep
ar
atio
n
in
f
o
r
m
atio
n
i
n
cl
u
d
es
a
co
u
r
s
e
o
f
a
ctio
n
o
f
tr
ai
n
in
g
ca
s
es.
A
s
u
p
er
v
is
ed
le
ar
n
i
n
g
co
m
p
u
tatio
n
s
ep
ar
ates
th
e
ar
r
a
n
g
e
m
e
n
t d
ata
a
n
d
p
r
o
d
u
ce
s
an
ass
e
m
b
led
li
m
it,
w
h
ic
h
ca
n
b
e
u
s
ed
f
o
r
m
ap
p
i
n
g
n
e
w
d
eli
n
ea
tio
n
s
.
A
p
er
f
ec
t
s
i
tu
atio
n
w
ill
ta
k
e
i
n
to
co
n
s
id
er
atio
n
t
h
e
ca
lcu
la
tio
n
to
p
r
ec
is
el
y
c
h
o
o
s
e
th
e
cla
s
s
m
ar
k
s
f
o
r
th
e
u
n
s
ee
n
t
u
p
le.
T
h
is
r
eq
u
ir
es
th
e
tak
in
g
o
f
c
o
m
p
u
tatio
n
n
to
w
h
o
le
u
p
f
r
o
m
t
h
e
p
r
ep
ar
atio
n
in
f
o
r
m
atio
n
to
a
n
u
n
s
ee
n
t
u
p
le
in
a
"
s
en
s
ib
le"
w
a
y
.
A
l
th
o
u
g
h
u
n
s
u
p
er
v
is
ed
tech
n
iq
u
es
h
av
e
b
ee
n
u
s
ed
i
n
d
iag
n
o
s
t
ic
m
a
n
y
d
i
s
ea
s
es
[
7
]
.
On
e
u
n
s
u
p
er
v
i
s
ed
tech
n
iq
u
e
i
s
clu
s
ter
i
n
g
[8
-
12]
.
B
o
th
s
u
p
er
v
is
ed
an
d
u
n
s
u
p
er
v
is
ed
tech
n
iq
u
e
s
h
as e
m
er
g
ed
a
s
th
e
m
o
s
t u
s
e
f
u
l
w
a
y
to
ex
tr
a
ct
r
elev
an
t
in
f
o
r
m
atio
n
f
r
o
m
h
u
g
e
d
atase
ts
.
T
h
o
u
g
h
th
er
e
ar
e
n
u
m
b
er
o
f
s
o
lu
tio
n
s
a
v
ailab
le
f
o
r
i
n
f
o
r
m
atio
n
e
x
tr
ac
tio
n
,
b
u
t
th
e
ac
c
u
r
ac
y
o
f
th
e
m
i
n
i
n
g
p
r
o
ce
s
s
is
f
ar
f
r
o
m
ac
c
u
r
ate.
Fo
r
ac
h
iev
i
n
g
h
i
g
h
est
ac
c
u
r
a
c
y
,
th
e
i
s
s
u
e
o
f
ze
r
o
p
r
o
b
a
b
ilit
y
,
w
h
ic
h
is
g
e
n
er
all
y
f
ac
ed
b
y
Naiv
e
B
a
y
e
s
an
al
y
s
i
s
,
n
ee
d
s
to
ad
d
r
ess
es
s
u
ita
b
ly
.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
ai
m
s
to
ex
tr
ac
t t
h
e
r
eq
u
ir
ed
in
f
o
r
m
a
tio
n
w
it
h
h
ig
h
ac
cu
r
ac
y
th
at
co
u
ld
s
u
r
v
i
v
e
t
h
e
p
r
o
b
lem
o
f
ze
r
o
p
r
o
b
a
b
ilit
y
.
T
h
is
tech
n
iq
u
e
is
s
u
r
e
to
b
e
an
ef
f
ec
t
iv
e
alter
n
ati
v
e
to
n
aïv
e
b
a
y
es
b
ec
au
s
e
o
f
o
v
er
co
m
i
n
g
th
e
p
r
o
b
lem
o
f
ze
r
o
f
r
eq
u
en
c
y
.
W
h
en
R
B
-
B
a
y
es
w
er
e
ap
p
lie
d
o
n
th
is
P
I
MA
I
n
d
ian
d
atase
t,
th
e
r
esu
lts
ar
r
iv
ed
at
g
a
v
e
a
n
ac
cu
r
ac
y
o
f
7
2
.
9
%.I
t
ca
n
b
e
co
n
cl
u
d
ed
th
at
R
B
-
B
ay
e
s
al
g
o
r
ith
m
p
r
o
d
u
ce
d
m
o
r
e
ac
cu
r
ate
r
esu
l
ts
th
an
t
h
e
e
x
is
t
in
g
clas
s
i
f
icatio
n
alg
o
r
ith
m
.
R
est
s
o
f
s
ec
tio
n
s
ar
e
s
o
r
ted
o
u
t
a
s
f
o
llo
w
s
.
I
n
S
ec
tio
n
2
w
e
s
p
ea
k
to
th
e
r
ela
ted
w
o
r
k
.
I
n
S
ec
tio
n
3
d
ep
ictin
g
t
h
e
ex
a
m
i
n
atio
n
s
t
r
ateg
y
a
n
d
all
tech
n
iq
u
es
j
o
in
ed
to
th
e
p
r
o
p
o
s
ed
tech
n
i
q
u
e
ar
e
clar
if
ied
.
I
n
S
ec
tio
n
4
,
ex
ec
u
tio
n
a
n
d
r
esu
lt
s
ar
e
talk
ed
ab
o
u
t.
Sectio
n
5
s
p
ea
k
in
g
to
a
co
n
clu
s
io
n
a
n
d
f
u
t
u
r
e
w
o
r
k
.
2.
RE
L
AT
E
D
WO
RK
A
n
u
m
b
er
o
f
m
et
h
o
d
s
h
av
e
b
ee
n
u
s
ed
f
o
r
d
iab
etes
cla
s
s
i
f
i
ca
tio
n
.
[
1
3
]
u
s
ed
d
is
cr
i
m
i
n
a
n
t
an
al
y
s
i
s
,
SVM
an
d
1
0
f
o
ld
cr
o
s
s
v
al
id
atio
n
f
o
r
class
i
f
icat
io
n
a
n
d
to
ch
ec
k
ac
c
u
r
ac
y
an
d
it
ac
h
ie
v
e
8
2
.
0
5
%.
[
1
4
]
u
s
ed
a
g
en
er
al
r
eg
r
es
s
io
n
n
eu
r
al
n
et
w
o
r
k
f
o
r
d
iab
etes
class
i
f
i
ca
tio
n
[
1
5
]
.
Pr
o
p
o
s
ed
a
m
eth
o
d
f
o
r
d
iab
etes
class
i
f
icatio
n
i
s
g
en
et
ic
p
r
o
g
r
a
m
m
in
g
.
T
o
ch
ec
k
t
h
e
ac
c
u
r
ac
y
o
f
t
h
e
m
o
d
el,
[
1
6
]
au
t
h
o
r
t
est
h
y
b
r
id
m
o
d
el
o
n
t
w
o
d
atasets
.
O
n
e
o
f
t
h
e
m
i
s
a
P
i
m
a
I
n
d
ian
d
ataset
an
d
th
e
s
ec
o
n
d
o
n
e
i
s
c
lev
er
lan
d
h
ea
r
t
d
is
ea
s
e.
T
h
e
r
es
u
l
t
o
f
ac
c
u
r
ac
y
f
o
r
b
o
th
o
f
th
e
m
o
d
el
is
8
4
.
2
4
%
an
d
8
6
.
8
%.
Usi
n
g
L
i
n
ea
r
d
is
cr
i
m
i
n
an
t
an
a
l
y
s
i
s
a
n
d
Ne
u
r
o
-
f
u
zz
y
s
y
s
te
m
[
1
6
]
i
n
tell
ig
e
n
t d
iag
n
o
s
is
s
y
s
te
m
w
a
s
d
ev
elo
p
ed
f
o
r
class
i
f
icatio
n
.
T
h
e
ac
cu
r
ac
y
was 8
4
.
6
1
%.
A
n
o
th
er
in
telli
g
e
n
t
m
e
th
o
d
w
a
s
p
r
o
p
o
s
ed
to
class
if
y
d
iab
etes
t
h
at
b
ased
o
n
[
1
7
]
Sm
al
l
-
W
o
r
ld
Feed
Fo
r
w
ar
d
ANN.
T
h
is
m
et
h
o
d
h
av
i
n
g
t
h
e
h
ig
h
est
ac
c
u
r
ac
y
i.e
.
9
1
.
6
6
%.Se
t
o
f
f
u
zz
y
r
u
le
s
ex
tr
ac
ted
f
o
r
class
if
icatio
n
o
f
d
iab
etes
[
1
8
]
.
B
y
u
s
i
n
g
th
i
s
m
et
h
o
d
th
e
au
th
o
r
ac
h
ie
v
ed
a
n
ac
cu
r
ac
y
o
f
8
4
.
2
4
%.
Fo
r
d
i
ab
etes
class
i
f
icat
io
n
au
th
o
r
d
id
a
co
m
p
ar
ativ
e
s
t
u
d
y
o
f
d
iab
etes.
T
h
e
y
u
s
ed
[
1
9
]
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
al
g
o
r
ith
m
a
n
d
p
r
o
b
ab
ilis
tic
NN
f
o
r
d
iab
etes
class
i
f
icatio
n
.
C
alis
ir
u
s
ed
[
2
0
]
Mo
r
let
W
a
v
elet
S
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
alo
n
g
w
it
h
L
i
n
ea
r
d
is
cr
i
m
i
n
an
t
an
a
l
y
s
is
f
o
r
d
iab
etes
class
i
f
ica
tio
n
.
T
h
eir
ac
h
iev
ed
cla
s
s
i
f
icat
io
n
ac
c
u
r
ac
y
o
f
8
9
.
7
4
%.Fo
r
class
i
f
icatio
n
o
n
e
o
f
s
u
p
er
v
i
s
ed
p
o
w
er
f
u
l
tech
n
iq
u
es
n
aï
v
e
b
a
y
e
s
ca
n
al
s
o
b
e
u
s
ed
f
o
r
p
r
ed
ictio
n
o
f
d
iab
etes.N
aiv
e
b
a
y
es
a
lr
ea
d
y
u
s
ed
f
o
r
p
r
ed
ictio
n
o
f
m
o
b
ile
p
h
o
n
e
[
2
1
]
.
Ot
h
er
p
o
w
er
f
u
l
d
ata
m
i
n
in
g
alg
o
r
ith
m
s
h
a
v
e
b
ee
n
u
s
ed
f
o
r
p
r
ed
ictio
n
o
f
h
ea
r
d
is
ea
s
es
[
2
2
]
.
3.
RE
S
E
ARCH
M
E
T
H
O
DO
L
O
G
Y
C
o
n
ce
n
tr
atin
g
o
n
e
x
p
ec
tatio
n
an
d
clas
s
i
f
icatio
n
o
f
d
is
ea
s
es,
th
e
p
r
ese
n
t
s
tu
d
y
u
s
es
R
B
-
B
a
y
e
s
alg
o
r
ith
m
b
ased
o
n
t
h
e
B
a
y
e
s
m
et
h
o
d
an
d
d
id
a
co
m
p
ar
i
s
o
n
w
it
h
n
a
iv
e
B
a
y
e
s
,
SVM,
an
d
d
ec
is
io
n
tr
ee
.
T
h
e
g
en
er
al
s
y
s
te
m
o
f
p
r
o
p
o
s
ed
d
em
o
n
s
tr
ate
ap
p
ea
r
s
in
Fi
g
u
r
e
1
.
W
e
p
r
o
p
o
s
e
an
o
th
er
cla
s
s
i
f
icatio
n
m
et
h
o
d
f
o
r
d
iab
etes
class
i
f
icatio
n
.
Firstl
y
to
h
an
d
le
m
is
s
i
n
g
d
ata,
w
e
r
ep
lace
v
al
u
es
w
i
th
m
ea
n
.
An
ex
p
la
n
atio
n
o
f
m
et
h
o
d
o
lo
g
ies is
g
iv
e
n
i
n
F
i
g
u
r
e
1
.
3
.
1
.
Da
t
a
s
et
T
h
e
d
ataset
is
a
g
a
th
er
i
n
g
o
f
Nativ
e
Am
er
ica
n
s
l
iv
i
n
g
i
n
a
z
o
n
e
co
m
p
r
is
i
n
g
o
f
w
h
at
i
s
p
r
esen
tl
y
f
o
ca
l
an
d
s
o
u
t
h
er
n
A
r
izo
n
a.
I
n
d
ia
n
in
d
i
v
id
u
a
ls
w
h
o
ar
e
lea
v
i
n
g
i
n
P
i
m
a
h
a
v
in
g
d
if
f
er
e
n
t
ec
o
lo
g
icall
y
b
ased
m
ed
ical
p
r
o
b
le
m
s
id
en
ti
f
ied
w
it
h
t
h
e
d
ec
r
ea
s
e
in
t
h
eir
co
n
v
en
t
io
n
al
ec
o
n
o
m
y
an
d
c
u
lti
v
atin
g
.
T
h
e
y
h
a
v
e
t
h
e
m
o
s
t
n
o
te
w
o
r
t
h
y
p
er
v
asi
v
e
n
e
s
s
o
f
t
y
p
e
2
d
iab
etes
o
n
th
e
p
lan
et,
co
n
s
id
er
ab
l
y
m
o
r
e
th
a
n
is
s
ee
n
in
d
if
f
er
en
t
U.
S.
p
o
p
u
lace
.
W
h
ile
t
h
e
y
d
o
n
'
t
h
av
e
a
m
o
r
e
s
er
io
u
s
h
az
ar
d
th
an
d
if
f
er
en
t
clan
s
,
t
h
e
P
im
a
i
n
d
iv
id
u
als
h
a
v
e
b
ee
n
th
e
s
u
b
j
ec
t
o
f
a
co
n
ce
n
tr
ated
in
v
est
ig
at
io
n
o
f
d
iab
etes.
T
h
er
e
is
an
a
g
g
r
e
g
ate
o
f
7
6
8
p
r
e
p
ar
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
:
4
8
6
6
-
4
8
7
2
4868
o
cc
u
r
r
en
ce
s
in
co
r
p
o
r
ated
in
to
th
is
i
n
f
o
r
m
atio
n
al
i
n
d
ex
.
E
a
ch
p
r
ep
ar
atio
n
ev
en
t
h
a
s
8
h
ig
h
lig
h
t
s
an
d
class
v
ar
iab
le
th
at
g
iv
e
s
th
e
n
a
m
e
t
o
th
at
p
r
ep
ar
atio
n
c
ase
as
s
h
o
w
ed
u
p
i
n
Fi
g
u
r
e
2
.
T
h
e
class
v
ar
iab
le
co
n
s
is
t
s
o
f
t
w
o
v
a
lu
e
s
eith
er
0
o
r
1
th
at
in
d
icatin
g
w
h
et
h
er
a
p
er
s
o
n
is
h
ea
lt
h
y
o
r
h
a
v
in
g
d
iab
etes.0
m
ea
n
s
th
e
p
er
s
o
n
i
s
n
o
t d
iab
etic
1
m
ea
n
s
t
h
e
p
er
s
o
n
is
d
iab
etic.
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
f
o
r
p
r
ed
ictio
n
Fig
u
r
e
2
.
Descr
ip
tio
n
o
f
P
I
MA
I
n
d
ia
n
d
ataset
3
.
2
.
H
a
nd
lin
g
m
is
s
ing
da
t
a
Han
d
lin
g
m
i
s
s
i
n
g
d
ata
is
a
n
i
m
p
o
r
tan
t
s
tep
b
ef
o
r
e
ap
p
l
y
in
g
th
e
m
o
d
el
.
I
f
w
e
d
elete
tu
p
le
t
h
at
co
n
s
is
ts
o
f
m
i
s
s
i
n
g
d
ata.
T
h
is
is
al
s
o
a
b
ad
id
ea
b
ec
au
s
e
m
i
g
h
t
p
o
s
s
ib
le
th
a
t
tu
p
le
co
n
s
i
s
ts
o
f
i
m
p
o
r
ta
n
t
in
f
o
r
m
atio
n
.
So
,
to
h
a
n
d
le
m
i
s
s
i
n
g
d
ata,
w
e
ar
e
h
av
in
g
t
w
o
ch
o
ices
e
ith
er
to
ca
lcu
la
te
t
h
e
m
ea
n
o
r
m
ed
ian
.
I
n
o
u
r
p
ap
er
,
w
e
ar
e
r
ep
lacin
g
m
is
s
i
n
g
v
al
u
es
w
it
h
m
ea
n
.
3
.
3
.
Cro
s
s
-
v
a
lid
a
t
io
ns
T
o
av
o
id
th
e
p
r
o
b
lem
o
f
o
v
er
f
itti
n
g
d
ata,
w
e
p
er
f
o
r
m
t
h
is
m
eth
o
d
o
n
o
u
r
d
ataset
b
ef
o
r
e
f
i
n
alizi
n
g
it
.
So
m
eti
m
es
o
u
r
m
o
d
el
d
o
es
n
o
t
p
er
f
o
r
m
li
k
e
th
e
w
a
y
w
e
e
x
p
ec
t
b
ec
au
s
e
w
e
ar
e
n
o
t
r
eser
v
i
n
g
p
ar
t
o
f
th
e
d
ataset
o
n
w
h
ich
y
o
u
d
o
n
o
t
t
r
ain
t
h
e
m
o
d
el
f
o
r
test
i
n
g
.
C
r
o
s
s
-
v
alid
atio
n
i
s
a
s
tati
s
tical
s
tr
ateg
y
t
h
at
i
n
th
i
s
ex
a
m
in
at
io
n
is
u
t
ilized
f
o
r
ex
ec
u
tio
n
as
s
es
s
m
e
n
t
o
f
lear
n
i
n
g
m
et
h
o
d
o
lo
g
y
an
d
ex
ec
u
tio
n
o
f
a
p
r
ed
icted
m
o
d
el
o
n
an
u
n
s
ee
n
d
ataset.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
RB
-
b
a
ye
s
a
lg
o
r
ith
m
fo
r
th
e
p
r
ed
ictio
n
o
f d
i
a
b
etic
in
“PI
MA
I
n
d
ia
n
d
a
ta
s
et” (
R
a
jn
i)
4869
T
h
u
s
,
u
t
ilizi
n
g
cr
o
s
s
-
v
al
id
atio
n
,
th
e
in
f
o
r
m
a
tio
n
al
co
llect
io
n
s
u
t
ilized
a
s
a
p
ar
t o
f
th
i
s
e
x
p
l
o
r
atio
n
ar
e
is
o
lated
in
to
s
ev
er
all
y
s
i
m
ila
r
l
y
m
ea
s
u
r
ed
s
u
b
s
ets.
T
h
e
r
esear
ch
er
m
u
s
t
e
n
s
u
r
e
t
h
at
t
h
er
e
ar
e
s
u
f
f
icie
n
t
tr
ain
i
n
g
e
x
a
m
p
le
s
to
tak
e
i
n
t
h
e
m
o
d
els.
W
e
ar
e
u
s
i
n
g
t
h
e
t
r
ain
_
test
_
s
p
lit
m
et
h
o
d
o
f
clas
s
cr
o
s
s
-
v
alid
atio
n
in
p
y
t
h
o
n
f
o
r
d
iv
id
in
g
t
h
e
d
ata
in
to
p
r
ep
a
r
in
g
an
d
te
s
ti
n
g
p
ar
t.
3
.
4
.
P
ro
po
s
ed
RB
-
B
a
y
es a
l
g
o
rit
h
m
RB
-
B
a
y
e
s
is
o
n
e
o
f
s
i
m
p
lest
s
u
p
er
v
is
ed
tec
h
n
iq
u
e.
I
t
is
a
class
i
f
icatio
n
s
y
s
te
m
i
n
li
g
h
t
o
f
B
ay
e
s
th
eo
r
e
m
.
I
t
is
m
o
s
tl
y
u
s
ed
in
tex
t
class
if
ica
tio
n
.
Naiv
e
B
a
y
e
s
is
also
b
as
ed
o
n
th
e
B
ay
es
t
h
eo
r
e
m
.
B
u
t
u
n
ab
le
to
h
an
d
le
th
e
p
r
o
b
le
m
o
f
th
e
l
ik
eli
h
o
o
d
o
f
ze
r
o
p
o
s
s
ib
ilit
y
.
R
B
-
B
a
y
e
s
is
p
r
o
p
o
s
ed
to
s
o
lv
e
th
is
p
r
o
b
le
m
[
2
3
]
.
RB
-
B
a
y
e
s
alg
o
r
it
h
m
p
r
o
v
id
es
a
w
a
y
o
f
c
alc
u
lati
n
g
p
r
ed
ictio
n
.
L
o
o
k
at
E
q
u
at
io
n
(
1
)
.
=
∗
(
+
⋯
…
…
…
…
.
+
∗
)
(
1
)
Af
ter
co
m
p
air
i
n
g
th
e
v
al
u
e
o
f
P
y
f
a
n
d
P
n
f
,
p
r
eid
ctio
n
ca
n
b
e
d
o
n
e
w
h
e
th
er
p
er
s
o
n
is
d
iab
etic
o
r
n
o
t.
RB
-
B
a
y
e
s
cla
s
s
i
f
ier
h
as
a
m
i
n
i
m
u
m
er
r
o
r
r
ate
as
co
m
p
ar
e
d
to
o
th
er
al
g
o
r
ith
m
s
.
A
ll
f
ac
to
r
s
ar
e
tak
e
n
in
to
co
n
s
id
er
atio
n
.
4.
RE
SU
L
T
S AN
D
CO
M
P
ARIS
O
N
O
F
M
E
T
H
O
DS
I
m
p
le
m
e
n
tatio
n
an
d
co
n
s
eq
u
e
n
ce
s
o
f
t
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
o
n
r
ea
l
-
w
o
r
ld
d
ata
s
ets
ar
e
clar
if
ied
in
th
is
ar
ea
.
4
.
1
.
Na
iv
e
B
a
y
es e
v
a
lua
t
io
n
I
n
th
i
s
ex
p
lo
r
atio
n
,
Naï
v
e
B
a
y
es
i
s
co
n
n
ec
ted
o
n
t
h
e
tes
t
d
ataset
in
e
x
ce
l
s
h
ee
t.
Naï
v
e
B
a
y
e
s
class
i
f
ier
o
f
f
er
s
a
b
asic
a
n
d
i
n
ten
s
e
m
a
n
ag
ed
c
h
ar
ac
ter
izatio
n
tech
n
iq
u
e.
T
h
e
p
ec
u
liar
it
y
o
f
t
h
is
m
o
d
el
is
t
h
at
it
ex
p
ec
ts
all
i
n
f
o
r
m
atio
n
attr
ib
u
tes
to
b
e
o
f
eq
u
i
v
ale
n
t
i
m
p
o
r
tan
ce
an
d
f
r
ee
o
f
o
n
e
a
n
o
th
er
.
Nai
v
e
B
a
y
es
b
ased
o
n
B
ay
es t
h
eo
r
e
m
.
B
a
y
es h
y
p
o
t
h
esi
s
ca
n
b
e
ex
p
r
es
s
e
d
as
E
q
u
atio
n
(
2
)
[
2
4
]
.
(
|
)
=
(
|
)
(
)
(
)
(
2
)
w
h
er
e
D
an
d
E
ar
e
ev
en
t
s
an
d
P
(
E
)
≠
0
.
A
p
p
l
y
m
o
d
el
ap
p
lies
a
m
o
d
el
to
th
e
r
ea
l
-
w
o
r
ld
d
ataset.
A
m
o
d
el
is
f
ir
s
t
p
r
ep
ar
ed
o
n
an
E
x
a
m
p
le
Se
t
b
y
an
o
t
h
er
Op
er
ato
r
,
w
h
ich
is
f
r
eq
u
en
tl
y
a
lear
n
in
g
ca
lc
u
lati
o
n
.
Su
b
s
eq
u
en
tl
y
,
th
i
s
m
o
d
el
ca
n
b
e
co
n
n
ec
ted
to
an
o
th
er
E
x
a
m
p
le
Set.
Or
d
in
ar
i
l
y
,
th
e
o
b
j
ec
tiv
e
is
to
g
et
an
e
x
p
ec
tatio
n
o
n
co
n
ce
aled
i
n
f
o
r
m
atio
n
o
r
to
ch
an
g
e
in
f
o
r
m
atio
n
b
y
ap
p
l
y
i
n
g
a
p
r
e
-
p
r
o
ce
s
s
i
n
g
m
o
d
el.
P
er
f
o
r
m
a
n
ce
clas
s
i
f
icatio
n
o
p
er
ato
r
to
ch
ec
k
th
e
ac
c
u
r
ac
y
o
f
th
e
m
et
h
o
d
.
A
cc
u
r
ac
y
w
it
h
Naïv
e
B
a
y
es i
s
6
7
.
7
1
%.
4
.
2
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chine
A
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
is
a
d
is
cr
i
m
i
n
ati
v
e
clas
s
if
ier
f
o
r
m
all
y
p
o
r
tr
a
y
ed
b
y
a
s
ec
lu
d
in
g
h
y
p
er
p
lan
e.
I
n
a
m
a
n
n
er
o
f
s
p
ea
k
in
g
,
g
iv
e
n
n
a
m
ed
g
etti
n
g
r
ea
d
y
d
ata
(
co
n
tr
o
lled
tak
in
g
i
n
)
,
th
e
co
m
p
u
tatio
n
y
ield
s
a
p
er
f
ec
t
h
y
p
er
p
lan
e
wh
ich
ar
r
an
g
es
n
e
w
o
u
tli
n
es.
T
h
e
ac
cu
r
ac
y
o
f
SV
M
is
w
h
e
n
ap
p
lied
t
o
a
r
ea
l
-
w
o
r
ld
d
ataset
as s
h
o
w
n
i
n
T
ab
le
1
.
T
ab
le
1
.
P
er
f
o
r
m
a
n
ce
class
if
ic
atio
n
u
s
in
g
SV
M
A
c
c
u
r
a
c
y
:
7
0
.
9
0
%
t
r
u
e
1
t
r
u
e
0
p
r
e
d
.
1
2
0
p
r
e
d
.
0
39
93
c
l
a
ss re
c
a
l
l
4
.
8
8
%
1
0
0
.
0
0
%
4
.
3
.
Dec
is
io
n t
re
e
e
v
a
lua
t
io
n
I
n
th
e
c
h
o
ice
e
x
a
m
in
a
tio
n
,
a
ch
o
ice
tr
ee
ca
n
b
e
u
s
ed
to
ap
p
ar
en
tl
y
a
n
d
ex
p
lici
tl
y
ad
d
r
ess
d
ec
is
io
n
s
an
d
f
u
n
d
a
m
en
tal
i
n
itia
tiv
e.
A
s
th
e
n
a
m
e
g
o
es,
it
u
s
e
s
a
tr
ee
-
l
ik
e
m
o
d
el
o
f
ch
o
ice.
A
d
ec
is
io
n
tr
ee
is
ap
p
lied
to
th
e
ex
p
er
i
m
en
ta
l
d
ataset
as
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
Set
r
o
le
o
p
er
ato
r
u
s
ed
to
d
ef
in
e
th
e
r
o
le
o
f
an
o
p
er
ato
r
.
T
h
e
p
ar
t
o
f
an
A
ttrib
u
te
d
ep
icts
h
o
w
d
i
f
f
er
en
t
Op
er
ato
r
s
h
a
n
d
le
th
i
s
Attr
ib
u
te.
T
h
e
d
ef
au
l
t
p
ar
t
is
co
n
s
is
ten
t,
d
if
f
er
e
n
t
p
ar
ts
ar
e
n
a
m
ed
s
p
ec
ial.
An
E
x
a
m
p
le
Set
ca
n
h
a
v
e
n
u
m
er
o
u
s
s
p
ec
ial
Attr
ib
u
tes,
y
et
ev
er
y
ex
tr
ao
r
d
in
ar
y
p
ar
t
ca
n
j
u
s
t
s
h
o
w
u
p
o
n
ce
.
I
n
th
e
e
v
e
n
t
t
h
at
a
s
p
ec
ial
r
o
le
is
a
s
s
i
g
n
ed
o
u
t
to
in
e
x
ce
s
s
o
f
o
n
e
A
ttrib
u
te,
all
p
ar
ts
w
i
ll
b
e
ch
an
g
ed
to
r
eg
u
lar
as
id
e
f
r
o
m
t
h
e
last
Attr
ib
u
te.
O
n
e
attr
ib
u
t
e
w
i
ll
b
e
ass
i
g
n
ed
a
lab
el
attr
ib
u
te.
P
er
f
o
r
m
a
n
ce
cl
ass
i
f
icatio
n
o
p
er
ato
r
ev
alu
ates
th
e
ac
cu
r
ac
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
:
4
8
6
6
-
4
8
7
2
4870
Fig
u
r
e
3
.
C
lass
if
y
i
n
g
d
iab
etes
u
s
i
n
g
a
d
ec
is
io
n
tr
ee
4
.
4
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n o
f
RB
-
B
a
y
es a
lg
o
rit
h
m
T
h
is
ar
ea
g
iv
e
s
t
h
e
test
co
n
s
eq
u
en
ce
s
o
f
d
iab
etes
i
n
f
ec
ti
o
n
g
r
o
u
p
i
n
g
w
i
th
p
r
o
p
o
s
ed
R
B
-
B
a
y
e
s
tech
n
iq
u
e
i
n
li
g
h
t
o
f
B
a
y
e
s
h
y
p
o
t
h
esi
s
.
Fu
r
t
h
er
m
o
r
e,
li
k
e
w
i
s
e,
ex
a
m
i
n
atio
n
w
it
h
v
ar
i
o
u
s
s
tr
ate
g
ies
a
ls
o
p
er
f
o
r
m
ed
a
n
d
th
eir
ac
cu
r
ac
y
is
also
ev
al
u
ated
.
I
n
th
is
s
t
u
d
y
,
f
ir
s
tl
y
m
i
s
s
i
n
g
d
ata
ar
e
h
an
d
led
b
y
ca
lcu
la
tin
g
m
ea
n
a
n
d
m
is
s
in
g
v
al
u
e
s
ar
e
r
ep
lace
d
b
y
m
ea
n
v
a
lu
e
s
.
B
ef
o
r
e
ap
p
ly
in
g
r
ea
l
-
w
o
r
ld
d
ataset
to
m
o
d
el,
w
e
s
p
lit
th
e
d
ataset
i
n
to
tr
ain
i
n
g
an
d
test
in
g
.
B
y
d
o
in
g
th
is
,
w
e
ar
e
av
o
id
in
g
t
h
e
p
r
o
b
lem
o
f
o
v
er
f
it
tin
g
a
l
s
o
.
So
m
eti
m
es
w
e
d
o
n
’
t
g
et
t
h
e
e
x
p
ec
ted
r
esu
l
t
i
f
w
e
te
s
t
d
ata
s
et
o
n
tr
ai
n
i
n
g
d
ata
.
O
v
er
f
itti
n
g
p
r
o
b
lem
ar
i
s
es
a
n
d
s
o
m
eti
m
es
d
o
n
’
t
g
et
th
e
ex
p
ec
ted
r
esu
lt.
I
t
'
s
b
etter
w
h
e
n
e
v
er
w
e
w
r
ite
a
n
y
n
e
w
s
o
f
t
w
ar
e,
s
ep
ar
ate
th
e
d
ataset
in
to
p
r
ep
ar
in
g
an
d
test
i
n
g
.
C
r
o
s
s
-
Va
lid
atio
n
o
p
er
ato
r
is
u
s
e
d
to
u
tili
zin
g
to
is
o
late
in
f
o
r
m
atio
n
a
l
co
llectio
n
in
to
p
r
ep
ar
in
g
a
n
d
test
i
n
g
.
W
e
ca
lcu
lated
a
v
al
u
e
f
o
r
th
e
p
r
o
b
ab
ilit
y
o
f
y
e
s
(
P
y
f
)
an
d
t
h
e
p
r
o
b
a
b
ilit
y
o
f
n
o
(
P
n
f
)
.
Hig
h
es
t
v
al
u
e
w
i
ll
d
ec
i
d
e
th
e
v
a
lu
e
f
o
r
t
h
e
lab
el
.
T
o
ch
e
ck
p
r
ec
is
io
n
w
e
tall
y
an
in
ce
n
tiv
e
f
o
r
f
alse
p
o
s
itiv
e,
g
e
n
u
in
e
p
o
s
iti
v
e,
g
e
n
u
i
n
e
n
eg
at
iv
e
a
n
d
f
alse
n
e
g
a
tiv
e.
T
h
e
r
esu
lt
is
s
h
o
w
n
in
Fi
g
u
r
e
4
.
T
h
is
s
h
o
w
s
th
e
e
f
f
ec
ti
v
en
e
s
s
o
f
co
n
s
o
lid
atin
g
cr
o
s
s
-
v
alid
atio
n
an
d
R
B
-
B
a
y
es
ca
lc
u
lat
io
n
f
o
r
t
h
e
o
r
d
er
p
r
ec
is
io
n
o
f
d
iab
etes illn
es
s
.
T
h
e
ex
ec
u
t
io
n
o
f
class
i
f
ier
s
t
h
at
w
er
e
co
n
tr
a
s
ted
an
d
o
u
r
s
tr
ateg
y
ap
p
ea
r
s
in
T
ab
le
2
.
Fig
u
r
e
4
.
A
cc
u
r
ac
y
ev
a
lu
at
io
n
o
f
R
B
-
B
a
y
e
s
alg
o
r
it
h
m
T
ab
le
2
.
C
o
r
r
elatio
n
o
f
p
r
o
p
o
s
ed
s
tr
ateg
y
w
i
th
d
i
f
f
er
e
n
t c
las
s
if
ier
s
f
o
r
P
im
a
I
n
d
ian
M
e
t
h
o
d
A
c
c
u
r
a
c
y
N
a
i
v
e
B
a
y
e
s
6
7
.
7
1
%
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
7
0
.
9
0
%
D
e
c
i
si
o
n
t
r
e
e
6
8
.
1
8
%
RB
-
B
a
y
e
s(
P
r
o
p
o
se
d
me
t
h
o
d
i
n
t
h
i
s
st
u
d
y
)
7
2
.
9
%
5.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
w
e
p
r
o
p
o
s
e
a
n
o
th
er
p
r
o
ce
d
u
r
e
in
lig
h
t
o
f
B
ay
e
s
h
y
p
o
t
h
esi
s
f
o
r
d
iab
etes
s
ick
n
es
s
ar
r
an
g
e
m
en
t
u
tili
zi
n
g
m
ac
h
i
n
e
lear
n
in
g
m
et
h
o
d
s
.
W
e
ca
lcu
lated
m
ea
n
to
h
an
d
le
m
is
s
in
g
d
ata
an
d
ca
lcu
lated
p
r
o
b
a
b
ilit
y
f
o
r
y
e
s
(
p
o
s
iti
v
e)
an
d
n
o
(
n
e
g
ati
v
e)
.
T
h
e
h
i
g
h
es
t
v
al
u
e
b
et
w
ee
n
y
e
s
a
n
d
n
o
d
ec
id
e
th
e
v
al
u
e
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
RB
-
b
a
ye
s
a
lg
o
r
ith
m
fo
r
th
e
p
r
ed
ictio
n
o
f d
i
a
b
etic
in
“PI
MA
I
n
d
ia
n
d
a
ta
s
et” (
R
a
jn
i)
4871
th
e
t
u
p
le
.
Kee
p
i
n
g
i
n
m
i
n
d
t
h
e
e
n
d
g
o
al
to
i
n
v
e
s
ti
g
ate
th
e
ad
eq
u
ac
y
o
f
t
h
e
p
r
o
p
o
s
ed
s
tr
ateg
y
an
d
ap
p
r
o
v
e
th
e
f
r
a
m
e
w
o
r
k
,
a
f
e
w
e
x
a
m
i
n
atio
n
s
d
ir
ec
ted
o
n
P
im
a
I
n
d
ian
in
f
o
r
m
atio
n
al
co
llectio
n
.
T
h
e
d
ataset
w
as
tak
e
n
f
r
o
m
k
a
g
g
le.
T
h
e
r
esu
lt
d
em
o
n
s
tr
ated
th
at
t
h
e
p
r
o
p
o
s
ed
R
B
-
B
a
y
es
s
tr
ate
g
y
u
s
ed
to
ac
q
u
ir
e
g
o
o
d
class
i
f
icatio
n
ac
cu
r
ac
y
a
n
d
r
em
o
v
e
t
h
e
p
r
o
b
lem
o
f
t
h
e
p
o
s
s
ib
ilit
y
o
f
li
k
eli
h
o
o
d
o
f
ze
r
o
p
r
o
b
lem
s
th
at
e
x
is
t
in
Naiv
e
B
a
y
es.
T
h
e
m
aj
o
r
ity
o
f
t
h
e
m
et
h
o
d
o
lo
g
ies,
u
tili
ze
d
as
a
p
ar
t
o
f
th
is
i
n
v
est
ig
atio
n
,
m
a
y
li
k
e
w
i
s
e
b
e
p
er
tin
en
t
to
o
th
er
ar
r
an
g
e
m
e
n
t
is
s
u
es.
S
u
b
s
eq
u
e
n
tl
y
,
in
o
u
r
f
u
tu
r
e
ex
a
m
i
n
atio
n
,
w
e
in
ten
d
to
ass
ess
t
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
o
n
e
x
tr
a
d
atasets
a
n
d
s
p
ec
i
f
icall
y
o
n
s
u
b
s
tan
tial
d
atasets
to
d
e
m
o
n
s
tr
ate
th
e
ad
eq
u
ac
y
o
f
th
e
s
tr
ate
g
y
.
RE
F
E
R
E
NC
E
S
[1
]
M
.
Nilas
h
i,
e
t
a
l
.
,
“
A
c
c
u
ra
c
y
I
m
p
ro
v
e
m
e
n
t
f
o
r
Dia
b
e
tes
Dise
a
se
Clas
si
f
ica
ti
o
n
:
A
C
a
se
o
n
a
P
u
b
l
ic
M
e
d
ica
l
Da
tas
e
t,
”
Fu
zz
y
In
f.
En
g
.
,
v
o
l.
9
,
p
p
.
3
4
5
-
3
5
7
,
2
0
1
7
.
[2
]
W
.
C.
Kn
o
w
ler,
e
t
a
l
.
,
“
Dia
b
e
tes
m
e
ll
it
u
s
in
th
e
P
im
a
In
d
ian
s:
g
e
n
e
ti
c
a
n
d
e
v
o
lu
ti
o
n
a
ry
c
o
n
sid
e
ra
ti
o
n
s.,
”
Am.
J
.
P
h
y
s.
An
th
ro
p
o
l
.
,
v
o
l
.
6
2
,
p
p
.
1
0
7
-
1
4
,
1
9
8
3
.
[3
]
B.
A
.
Ha
m
b
u
rg
a
n
d
G
.
E.
In
o
f
f
,
“
Re
latio
n
sh
i
p
s
b
e
tw
e
e
n
b
e
h
a
v
io
ra
l
f
a
c
to
rs
a
n
d
d
ia
b
e
ti
c
c
o
n
tr
o
l
i
n
c
h
il
d
re
n
a
n
d
a
d
o
les
c
e
n
ts:
a
c
a
m
p
stu
d
y
,
”
Psy
c
h
o
so
m M
e
d
,
v
o
l.
4
4
,
p
p
.
3
2
1
-
3
3
9
,
1
9
8
2
.
[4
]
V
.
A
.
Ku
m
a
ri
a
n
d
R
.
Ch
it
ra
,
“
Cl
a
ss
if
ic
a
ti
o
n
Of
Dia
b
e
tes
Dise
a
se
U
sin
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
,
”
I
n
t.
J
.
En
g
.
Res
.
Ap
p
l
.
www.i
jer
a
.
c
o
m
,
v
o
l
.
3
,
p
p
.
1
7
9
7
-
1
8
0
1
,
2
0
1
3
.
[5
]
N.
H.
Ba
ra
k
a
t,
e
t
a
l
.
,
“
In
telli
g
ib
l
e
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
f
o
r
d
iag
n
o
sis
o
f
d
iab
e
tes
m
e
ll
it
u
s.,
”
IEE
E
T
ra
n
s.
I
n
f.
T
e
c
h
n
o
l
.
Bi
o
me
d
.
, v
o
l.
1
4
,
p
p
.
1
1
1
4
-
1
1
2
0
,
2
0
1
0
.
[6
]
R.
Bh
a
ll
a
,
“
Op
in
io
n
m
in
in
g
f
ra
m
e
w
o
rk
u
sin
g
p
ro
p
o
se
d
RB
-
Ba
y
e
s
,
”
In
t.
J
.
El
e
c
tr.
Co
mp
u
t.
En
g
.
,
v
o
l.
9,
p
p
.
1
-
1
2
,
2
0
1
8
.
[7
]
E.
R.
Hru
sc
h
k
a
a
n
d
N.
F
.
F
.
E
b
e
c
k
e
n
,
“
Ex
tra
c
ti
n
g
ru
les
f
ro
m
m
u
lt
il
a
y
e
r
p
e
rc
e
p
tr
o
n
s
in
c
las
sif
ic
a
ti
o
n
p
ro
b
lem
s:
A
c
lu
ste
rin
g
-
b
a
se
d
a
p
p
ro
a
c
h
,
”
Ne
u
ro
c
o
mp
u
ti
n
g
,
v
o
l.
7
0
,
p
p
.
3
8
4
-
3
9
7
,
2
0
0
6
.
[8
]
C.
H.
Ch
e
n
,
“
A
h
y
b
rid
in
telli
g
e
n
t
m
o
d
e
l
o
f
a
n
a
l
y
z
in
g
c
li
n
ica
l
b
re
a
st
c
a
n
c
e
r
d
a
ta
u
sin
g
c
lu
ste
rin
g
tec
h
n
iq
u
e
s
w
it
h
f
e
a
tu
re
se
lec
ti
o
n
,
”
Ap
p
l.
S
o
ft
C
o
mp
u
t.
J
.
,
v
o
l
.
2
0
,
p
p
.
4
-
1
4
,
2
0
1
4
.
[9
]
K.
P
o
lat,
“
Clas
sif
ica
ti
o
n
o
f
P
a
rk
in
so
n
’s
d
ise
a
se
u
sin
g
fe
a
tu
re
w
e
ig
h
ti
n
g
m
e
th
o
d
o
n
t
h
e
b
a
sis
o
f
fu
z
z
y
C
-
m
e
a
n
s
c
lu
ste
rin
g
,
”
In
t.
J
.
S
y
st.
S
c
i.
,
v
o
l.
4
3
,
p
p
.
5
9
7
-
6
0
9
,
2
0
1
2
.
[1
0
]
M
.
Nilas
h
i,
e
t
a
l
.
,
“
A
so
f
t
c
o
m
p
u
ti
n
g
a
p
p
r
o
a
c
h
f
o
r
d
iab
e
tes
d
ise
a
se
c
las
s
i
f
ica
ti
o
n
,
”
He
a
lt
h
In
f
o
rm
a
ti
c
s J
.
,
2
0
1
6
.
[1
1
]
M
.
Nilas
h
i,
e
t
a
l
.
,
“
A
c
c
u
ra
c
y
I
m
p
ro
v
e
m
e
n
t
f
o
r
P
re
d
ictin
g
P
a
rk
in
so
n
’s
Dise
a
se
P
ro
g
re
ss
io
n
,
”
S
c
i.
Rep
.
,
v
o
l.
6,
p
p
.
1
-
1
8
,
2
0
1
6
.
[1
2
]
M
.
Nilas
h
i,
e
t
a
l
.
,
“
A
k
n
o
w
led
g
e
-
b
a
se
d
s
y
ste
m
f
o
r
b
re
a
st
c
a
n
c
e
r
c
l
a
ss
if
i
c
a
ti
o
n
u
sin
g
f
u
z
z
y
lo
g
ic
m
e
t
h
o
d
,
”
T
e
lem
a
t.
In
fo
rm
a
t
ics
,
v
o
l.
3
4
,
p
p
.
1
3
3
-
1
4
4
,
2
0
1
7
.
[1
3
]
K.
P
o
lat,
e
t
a
l
.
,
“
A
c
a
sc
a
d
e
le
a
rn
in
g
sy
st
e
m
f
o
r
c
las
si
f
ica
ti
o
n
o
f
d
iab
e
tes
d
ise
a
se
:
G
e
n
e
ra
li
z
e
d
Disc
rim
in
a
n
t
A
n
a
l
y
si
s a
n
d
L
e
a
st S
q
u
a
re
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
,
”
Exp
e
rt S
y
st.
Ap
p
l
.
,
v
o
l.
3
4
,
p
p
.
4
8
2
-
4
8
7
,
2
0
0
8
.
[1
4
]
K.
Ka
y
a
e
r
a
n
d
T
.
Yild
iri
m
,
“
M
e
d
ica
l
Dia
g
n
o
sis
o
n
P
im
a
In
d
ian
Dia
b
e
tes
Us
in
g
G
e
n
e
ra
l
Re
g
re
ss
io
n
Ne
u
ra
l
Ne
tw
o
rk
s,”
Iter
n
a
ti
o
n
a
l
C
o
n
f.
Art
if
.
Ne
u
ra
l
Ne
two
rk
s Ne
u
ra
l
In
f.
P
ro
c
e
ss
.
,
p
p
.
1
8
1
-
1
8
4
,
2
0
0
3
.
[1
5
]
M
.
W
.
A
sla
m
,
e
t
a
l
.
,
“
F
e
a
tu
re
g
e
n
e
ra
ti
o
n
u
si
n
g
g
e
n
e
ti
c
p
r
o
g
ra
m
m
in
g
w
it
h
c
o
m
p
a
ra
ti
v
e
p
a
rtn
e
r
se
lec
ti
o
n
f
o
r
d
iab
e
tes
c
las
sif
ic
a
ti
o
n
,
”
Exp
e
rt
S
y
st.
Ap
p
l.
,
v
o
l.
4
0
,
p
p
.
5
4
0
2
-
5
4
1
2
,
2
0
1
3
.
[1
6
]
H.
Ka
h
ra
m
a
n
li
a
n
d
N.
A
ll
a
h
v
e
rd
i,
“
De
sig
n
o
f
a
h
y
b
rid
sy
st
e
m
f
o
r
th
e
d
iab
e
tes
a
n
d
h
e
a
rt
d
ise
a
s
e
s
,
”
Exp
e
rt
S
y
st.
Ap
p
l
.
,
v
o
l.
3
5
,
p
p
.
8
2
-
8
9
,
2
0
0
8
.
[1
7
]
O.
Erk
a
y
m
a
z
a
n
d
M
.
Oz
e
r,
“
I
m
p
a
c
t
o
f
s
m
a
ll
-
w
o
rld
n
e
tw
o
rk
to
p
o
l
o
g
y
o
n
th
e
c
o
n
v
e
n
ti
o
n
a
l
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
th
e
d
iag
n
o
sis
o
f
d
iab
e
tes
,
”
Ch
a
o
s,
S
o
l
it
o
n
s a
n
d
Fra
c
ta
ls
,
v
o
l.
8
3
,
p
p
.
1
7
8
-
1
8
5
,
2
0
1
6
.
[1
8
]
M
.
F
.
G
a
n
ji
a
n
d
M
.
S
.
A
b
a
d
e
h
,
“
A
f
u
z
z
y
c
las
si
f
ica
ti
o
n
s
y
ste
m
b
a
se
d
o
n
A
n
t
Co
lo
n
y
Op
ti
m
i
z
a
ti
o
n
f
o
r
d
iab
e
tes
d
ise
a
se
d
iag
n
o
sis,”
Exp
e
rt S
y
st.
A
p
p
l.
,
v
o
l.
3
8
,
p
p
.
1
4
6
5
0
-
1
4
6
5
9
,
2
0
1
1
.
[1
9
]
H.
T
e
m
u
rtas
,
e
t
a
l
.
,
“
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
n
d
iab
e
tes
d
ise
a
se
d
iag
n
o
sis
u
si
n
g
n
e
u
ra
l
n
e
tw
o
rk
s,”
Ex
p
e
rt
S
y
st.
Ap
p
l.
,
v
o
l.
3
6
,
p
p
.
8
6
1
0
-
8
6
1
5
,
2
0
0
9
.
[2
0
]
D.
Ça
li
şir
a
n
d
E.
Do
g
a
n
tek
in
,
“
A
n
e
w
in
telli
g
e
n
t
h
e
p
a
ti
ti
s
d
iag
n
o
sis
s
y
ste
m
:
P
CA
-
L
S
S
V
M
,
”
Exp
e
rt
S
y
st.
Ap
p
l.
,
v
o
l.
3
8
,
p
p
.
1
0
7
0
5
-
1
0
7
0
8
,
2
0
1
1
.
[2
1
]
R.
Bh
a
ll
a
a
n
d
A
.
Am
a
n
d
e
e
p
,
“
A
Co
m
p
a
ra
ti
v
e
A
n
a
l
y
sis o
f
F
a
c
to
r
Eff
e
c
ti
n
g
th
e
Bu
y
in
g
Ju
d
g
e
m
e
n
t
o
f
S
m
a
rt
P
h
o
n
e
,
”
In
t.
J
.
El
e
c
tr.
Co
mp
u
t.
En
g
.
,
v
o
l.
8
,
p
p
.
3
0
5
7
-
3
0
6
9
,
2
0
1
8
.
[2
2
]
M
.
A
b
d
a
r,
e
t
a
l
.
,
“
Co
m
p
a
rin
g
P
e
r
f
o
r
m
a
n
c
e
o
f
Da
ta
M
in
in
g
A
lg
o
rit
h
m
s
in
P
re
d
icti
o
n
He
a
rt
D
ise
a
se
s,
”
In
t.
J
.
El
e
c
tr.
Co
mp
u
t
.
E
n
g
.
,
v
o
l.
5
,
p
p
.
1
5
6
9
-
1
5
7
6
,
2
0
1
5
.
[2
3
]
R.
Bh
a
ll
a
a
n
d
A
.
Ba
g
g
a
,
“
Op
in
io
n
m
in
in
g
f
ra
m
e
w
o
rk
u
sin
g
p
ro
p
o
se
d
RB
-
b
a
y
e
s
m
o
d
e
l
f
o
r
tex
t
c
las
sic
a
ti
o
n
,
”
In
t.
J
.
El
e
c
tr.
Co
mp
u
t.
E
n
g
.
,
v
o
l
.
9
,
p
p
.
4
7
7
-
4
8
5
,
2
0
1
9
.
[2
4
]
S
.
Ru
ss
e
ll
a
n
d
P
.
No
rv
ig
,
“
A
rti
f
ic
ial
In
telli
g
e
n
c
e
A
M
o
d
e
rn
A
p
p
r
o
a
c
h
,”
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
:
4
8
6
6
-
4
8
7
2
4872
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ra
jn
i
B
h
a
ll
a
is
p
u
rsu
in
g
P
HD
f
ro
m
lo
v
e
l
y
p
ro
f
e
ss
io
n
a
l
Un
iv
e
rsi
ty
.
S
h
e
is
w
o
r
k
in
g
a
s
a
ss
istan
t
p
ro
f
e
ss
o
r
in
L
o
v
e
ly
P
ro
f
e
ss
io
n
a
l
u
n
iv
e
rsity
.
S
h
e
is
i
n
tere
ste
d
i
n
d
a
ta
m
in
in
g
,
d
a
ta
a
n
a
ly
sis,
f
e
a
tu
re
e
x
trac
ti
o
n
,
p
re
d
ictio
n
a
n
d
c
lu
ste
ri
n
g
tec
h
n
iq
u
e
s.
A
m
a
n
d
e
e
p
B
a
g
g
a
is
a
n
A
ss
o
c
ia
ted
P
r
o
f
e
ss
o
r
in
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
a
t
L
o
v
e
ly
P
r
o
f
e
ss
io
n
a
l
u
n
iv
e
rsity
,
In
d
ia.
S
h
e
h
a
s
c
o
m
p
lete
d
h
is
stu
d
ies
f
o
r
B.
C.
A
,
M
.
C.
A
,
P
h
.
D.
f
ro
m
L
P
U.He
r
re
se
a
rc
h
in
tere
st i
n
c
lu
d
e
c
lo
u
d
c
o
m
p
u
ti
n
g
,
se
c
u
rit
y
,
n
e
t
w
o
rk
se
c
u
rit
y
a
n
d
c
ry
p
to
g
ra
phy
Evaluation Warning : The document was created with Spire.PDF for Python.