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
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
,
p
p
.
408
~
415
I
SS
N:
2252
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
1
4
.i
1
.
p
p
4
0
8
-
4
1
5
408
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Autom
a
tic
dia
be
t
es predic
tion wi
th
ex
pla
ina
ble
ma
c
hine
lea
rning
t
ech
niqu
es
Adib
a
H
a
qu
e,
Sa
njida
I
s
la
m
,
Nus
ra
t
Ra
him
M
im
,
Sa
brina
M
a
nn
a
n M
ee
m
,
Ana
ny
a
Sa
ha
,
Ria
s
a
t
K
ha
n
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
mp
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
N
o
r
t
h
S
o
u
t
h
U
n
i
v
e
r
si
t
y
,
D
h
a
k
a
,
B
a
n
g
l
a
d
e
s
h
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
22
,
2
0
2
4
R
ev
is
ed
J
u
l
7
,
2
0
2
4
Acc
ep
ted
J
u
l
26
,
2
0
2
4
Dia
b
e
tes
is
a
m
e
tab
o
li
c
d
iso
rd
e
r
c
a
u
se
d
b
y
v
a
ri
o
u
s
g
e
n
e
ti
c
,
p
h
y
sio
l
o
g
ica
l
a
n
d
b
e
h
a
v
i
o
ra
l
fa
c
to
rs.
It
o
c
c
u
rs
d
u
e
to
a
n
imb
a
lan
c
e
in
th
e
b
o
d
y
’s
in
su
li
n
p
ro
c
e
ss
in
g
,
wh
ich
re
su
lt
s
i
n
e
lev
a
ted
b
l
o
o
d
s
u
g
a
r
lev
e
ls.
I
ts
e
a
rly
d
iag
n
o
si
s
c
a
n
a
ll
e
v
iate
th
e
risk
o
f
o
th
e
r
d
e
a
d
ly
d
ise
a
se
s.
Th
e
o
n
se
t
a
n
d
a
c
c
u
ra
te
d
e
tec
ti
o
n
o
f
d
ia
b
e
tes
c
a
n
d
e
c
re
a
s
e
th
e
p
ro
g
re
ss
io
n
o
f
d
iffere
n
t
c
o
m
p
li
c
a
ti
o
n
s
a
n
d
d
y
sfu
n
c
ti
o
n
o
f
ti
ss
u
e
s.
Th
e
p
rin
c
ip
a
l
o
b
jec
ti
v
e
o
f
th
is
a
rti
c
le
is
to
u
ti
li
z
e
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
e
s
to
p
re
d
ict
th
e
e
x
isten
c
e
o
f
d
iab
e
tes
in
fe
m
a
le
p
a
ti
e
n
ts
a
t
a
p
rima
ry
sta
g
e
.
M
u
lt
ip
le
m
a
c
h
in
e
lea
rn
in
g
,
i
n
c
lu
d
i
n
g
e
n
se
m
b
le
c
las
sifiers
with
th
e
P
ima
In
d
ian
d
a
tas
e
t
a
n
d
a
p
riv
a
te
d
a
tas
e
t
o
b
tain
e
d
fro
m
a
lo
c
a
l
Ba
n
g
la
d
e
sh
i
h
o
sp
it
a
l,
a
re
u
se
d
in
th
is
wo
r
k
.
We
e
m
p
l
o
y
e
d
fe
a
tu
re
sc
a
li
n
g
,
s
y
n
t
h
e
ti
c
o
v
e
rsa
m
p
li
n
g
tec
h
n
iq
u
e
(S
M
OTE)
,
a
n
d
h
y
p
e
r
p
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
wit
h
G
rid
S
e
a
rc
h
CV
to
g
e
t
t
h
e
b
e
st
p
e
rfo
r
m
a
n
c
e
fro
m
d
iffere
n
t
m
a
c
h
in
e
lea
rn
in
g
a
l
g
o
rit
h
m
s.
T
h
e
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM
)
with
th
e
S
M
OTE
fra
m
e
wo
rk
a
n
d
d
e
fa
u
lt
h
y
p
e
r
p
a
ra
m
e
ters
a
c
h
iev
e
d
th
e
a
c
c
u
ra
c
y
a
n
d
F
1
sc
o
re
o
f
8
7
%
a
n
d
9
1
%
,
re
sp
e
c
ti
v
e
ly
.
T
h
e
a
c
c
u
ra
c
y
a
n
d
F
1
sc
o
re
o
f
th
e
S
VM
m
o
d
e
l
imp
r
o
v
e
d
to
9
5
%
a
n
d
9
1
%
,
re
sp
e
c
ti
v
e
l
y
,
with
h
y
p
e
r
p
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
.
F
i
n
a
ll
y
,
e
x
p
lain
a
b
le
a
rti
ficia
l
in
tell
ig
e
n
c
e
wit
h
th
e
lo
c
a
l
in
terp
re
tab
le
m
o
d
e
l
-
a
g
n
o
stic
e
x
p
lan
a
ti
o
n
s
(LI
M
E)
is
e
m
p
lo
y
e
d
t
o
il
lu
stra
te
th
e
p
re
d
icta
b
il
it
y
o
f
th
e
S
VM
tec
h
n
i
q
u
e
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
Diab
etes
p
r
ed
ictio
n
E
x
p
l
a
i
n
a
b
l
e
a
r
ti
f
i
c
ia
l
i
n
te
l
li
g
e
n
c
e
Ma
ch
in
e
lear
n
in
g
M
etab
o
lic
d
is
o
r
d
er
S
y
n
t
h
e
t
i
c
o
v
e
r
s
a
m
p
l
i
n
g
t
ec
h
n
iq
u
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
:
R
iasat Kh
an
Dep
ar
tm
en
t o
f
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
in
ee
r
in
g
,
No
r
th
So
u
th
Un
iv
er
s
ity
Plo
t: 1
5
,
B
lo
ck
: B,
B
ash
u
n
d
h
a
r
a,
B
ar
id
h
ar
a,
D
h
ak
a
-
1
2
2
9
,
B
an
g
lad
esh
E
m
ail: r
iasat.k
h
an
@
n
o
r
th
s
o
u
t
h
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
W
h
en
th
e
b
o
d
y
’
s
in
s
u
lin
is
u
s
ed
in
ad
e
q
u
ately
,
an
d
co
n
s
e
q
u
en
tly
,
th
e
p
an
cr
ea
s
f
ails
to
g
en
er
ate
ad
eq
u
ate
in
s
u
lin
,
th
en
a
n
im
m
ed
icab
le
d
is
ea
s
e
o
cc
u
r
s
k
n
o
wn
as
d
iab
etes
[
1
]
.
T
h
e
r
e
a
r
e
d
if
f
er
e
n
t
ty
p
es
o
f
d
iab
etes
ch
ar
ac
ter
ized
b
y
h
y
p
e
r
g
ly
ce
m
ia,
f
o
r
in
s
tan
ce
,
ty
p
e
o
n
e,
ty
p
e
two
,
a
n
d
g
estatio
n
al
d
i
ab
etes.
Pre
d
iab
etes
is
also
co
n
s
id
er
ed
an
o
th
er
ty
p
e
o
f
d
ia
b
etes.
So
m
etim
es
p
eo
p
le
h
av
e
a
g
lu
co
s
e
lev
el
t
h
at
i
s
m
o
r
e
ex
ce
s
s
th
an
s
tan
d
ar
d
b
u
t
n
o
t
th
at
m
u
ch
ex
ce
s
s
to
ty
p
e
2
d
iab
etes.
T
h
is
c
o
n
d
itio
n
is
ca
lled
p
r
ed
ia
b
etes
[
2
]
.
W
o
r
ld
wid
e
5
3
7
m
illi
o
n
in
d
i
v
id
u
als
ag
e
d
f
r
o
m
2
0
to
7
9
y
ea
r
s
h
a
v
e
b
ee
n
af
f
e
cted
b
y
d
ia
b
etes,
ac
co
r
d
in
g
to
a
r
ep
o
r
t
b
y
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
p
u
b
lis
h
ed
in
2
0
2
1
.
T
h
e
in
f
o
r
m
atio
n
an
ticip
ated
th
at
b
y
2
0
3
0
an
d
2
0
4
5
,
th
e
r
ate
wo
u
ld
b
e
in
c
r
ea
s
ed
to
6
4
3
m
illi
o
n
an
d
7
8
3
m
illi
o
n
,
r
esp
ec
tiv
e
ly
[
2
]
.
I
n
2
0
1
9
,
ap
p
r
o
x
im
ately
8
.
4
0
m
illi
o
n
ad
u
lts
h
ad
d
iab
etes
in
B
an
g
lad
esh
,
w
h
ich
is
an
ticip
ated
to
ex
p
a
n
d
t
o
alm
o
s
t
1
5
m
illi
o
n
b
y
2
0
4
5
.
3
.
8
0
m
illi
o
n
p
eo
p
le
wer
e
ex
p
ec
ted
to
h
av
e
p
r
e
d
iab
etes
in
2
0
1
9
.
8
.
2
%
o
f
r
u
r
al
wo
m
en
an
d
1
2
.
9
%
o
f
f
em
ale
s
in
u
r
b
an
ar
ea
s
o
f
B
an
g
lad
esh
ar
e
a
f
f
ec
ted
b
y
g
estatio
n
al
d
iab
etes
m
ellitu
s
[
3
]
.
T
h
e
tr
ea
tm
en
t
o
f
d
iab
etes
v
ar
ies
in
s
tep
s
,
with
wh
at
am
o
u
n
t
o
f
in
s
u
lin
t
h
e
b
o
d
y
m
ak
es
an
d
h
o
w
p
r
o
p
er
ly
t
h
e
b
o
d
y
ca
n
u
s
e
av
ailab
le
in
s
u
lin
.
Diab
etes
is
n
o
t
cu
r
ab
le,
y
et
it
is
co
n
tr
o
llab
le.
Diab
etes
ca
r
e
is
ass
o
ciate
d
wit
h
ad
o
p
tin
g
a
h
ea
lth
y
life
s
ty
le,
r
estr
icted
d
iet,
weig
h
t
co
n
tr
o
l a
n
d
r
e
g
u
lar
p
h
y
s
ical
a
ctiv
ity
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
tic
d
ia
b
etes p
r
ed
ictio
n
w
ith
ex
p
la
in
a
b
le
m
a
ch
in
e
le
a
r
n
in
g
tech
n
i
q
u
es
(
A
d
i
b
a
Ha
q
u
e
)
409
Acc
u
r
ate
an
d
p
r
o
m
p
t
p
r
ed
icti
o
n
o
f
d
iab
etes
is
a
co
n
ce
r
n
.
No
tab
le
wo
r
k
s
h
av
e
b
ee
n
d
o
n
e
o
n
th
e
au
to
m
atic
id
en
tific
atio
n
o
f
d
ia
b
etes
u
tili
zin
g
v
a
r
io
u
s
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es.
T
h
e
au
to
m
ated
p
r
ed
ictio
n
o
f
th
ese
wo
r
k
s
is
ex
p
ec
te
d
to
co
m
e
u
p
with
a
h
elp
f
u
l
r
e
f
er
e
n
cin
g
to
o
l
an
d
p
r
elim
in
ar
y
ju
d
g
m
en
t
f
o
r
clin
ician
s
to
p
r
e
d
ict
d
iab
etes
ea
r
ly
o
n
an
d
r
ed
u
ce
t
h
e
wo
r
k
lo
ad
o
f
h
ea
lt
h
ca
r
e
p
r
o
f
ess
io
n
als.
So
m
e
s
ig
n
if
ican
t
wo
r
k
s
b
ased
o
n
d
iab
etes p
r
ed
ictio
n
h
av
e
b
e
en
d
escr
ib
ed
b
r
ief
ly
i
n
th
e
f
o
llo
win
g
p
ar
a
g
r
ap
h
s
.
Ma
n
y
o
f
th
ese
s
tu
d
ies
u
s
ed
d
i
f
f
er
en
t
o
p
en
-
s
o
u
r
ce
d
atasets
,
p
ar
ticu
lar
ly
th
e
Pima
I
n
d
ian
d
ataset.
Fo
r
in
s
tan
ce
,
Ab
d
u
lh
ad
i
an
d
Al
-
M
o
u
s
a
[
4
]
co
n
d
u
cted
m
ac
h
in
e
le
ar
n
in
g
ap
p
r
o
ac
h
es
to
d
eter
m
in
e
ty
p
e
2
d
iab
etes
in
f
em
ales
at
th
e
p
r
im
ar
y
s
tag
e.
T
h
e
au
th
o
r
s
u
s
ed
th
e
Pima
I
n
d
ian
d
ataset
co
n
tain
in
g
7
6
8
i
n
s
tan
ce
s
with
n
in
e
attr
ib
u
tes,
b
u
t
th
er
e
we
r
e
m
a
n
y
m
is
s
in
g
v
alu
es
f
r
o
m
s
ev
er
al
ca
s
es.
Hen
ce
th
e
n
u
ll
v
alu
es
wer
e
r
esto
r
ed
with
th
e
m
ea
n
v
al
u
e,
an
d
th
e
d
ataset
was
s
tan
d
ar
d
ized
u
s
in
g
a
s
tan
d
ar
d
s
ca
lar
.
T
h
e
au
th
o
r
s
test
ed
d
if
f
er
en
t
class
if
ier
s
an
d
r
an
d
o
m
f
o
r
est
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
8
2
%,
m
ak
in
g
it
th
e
m
o
s
t
ef
f
icien
t
m
o
d
el.
Hasan
et
a
l.
[
5
]
u
s
ed
v
ar
io
u
s
f
ea
tu
r
e
s
elec
tio
n
ap
p
r
o
ac
h
es
to
cr
ea
te
a
tr
ee
-
b
ased
p
r
ed
ictio
n
m
o
d
el
f
o
r
t
h
e
ea
r
ly
d
etec
tio
n
o
f
d
iab
etes
in
f
em
ale
p
atien
ts
.
T
h
e
au
th
o
r
s
u
s
ed
s
ev
er
al
s
tep
s
f
o
r
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
i.e
.
,
h
an
d
lin
g
m
is
s
in
g
v
alu
es,
f
ea
tu
r
e
s
elec
tio
n
,
o
v
er
s
am
p
lin
g
,
an
d
f
ea
tu
r
e
s
ca
lin
g
.
T
h
e
au
t
h
o
r
s
u
s
ed
d
ec
is
io
n
tr
ee
,
r
an
d
o
m
f
o
r
est
,
ex
tr
a
tr
ee
s
,
an
d
ad
a
p
tiv
e
b
o
o
s
tin
g
(
AB
)
f
r
am
ewo
r
k
s
.
T
h
e
ex
tr
a
tr
ee
s
m
o
d
el
p
r
o
v
id
ed
t
h
e
h
ig
h
est ac
cu
r
ac
y
an
d
F1
s
co
r
e
o
f
8
8
.
3
p
er
ce
n
t
an
d
0
.
8
7
7
,
r
esp
ec
tiv
ely
.
Kh
an
am
a
n
d
Fo
o
[
6
]
a
p
p
lied
d
if
f
e
r
en
t
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
an
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
A
NN)
o
n
th
e
Pima
I
n
d
ian
d
at
aset
to
p
r
ed
ict
d
iab
etes.
T
h
e
au
th
o
r
ap
p
lied
t
h
e
tr
ad
itio
n
al
d
ata
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
u
s
in
g
th
e
W
E
KA
to
o
l a
n
d
th
e
K
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
tech
n
iq
u
e.
ANN
o
b
tain
ed
th
e
m
ax
im
u
m
ac
cu
r
a
cy
o
f
8
6
%
am
o
n
g
all
th
e
p
r
o
p
o
s
ed
m
o
d
els.
C
h
an
g
et
a
l
.
[
7
]
o
b
s
er
v
ed
th
e
r
an
d
o
m
f
o
r
est
m
o
d
el
to
o
b
tain
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
7
9
.
5
7
%
i
n
p
r
ed
ictin
g
wh
et
h
er
t
h
e
p
atien
t
is
d
iab
etic
o
r
n
o
n
-
d
iab
etic.
B
an
o
a
n
d
h
is
team
[
8
]
ap
p
lied
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
,
ANN,
d
ec
is
io
n
tr
ee
,
lo
g
is
tic
r
eg
r
ess
io
n
,
an
d
f
ar
th
est
f
ir
s
t
cl
u
s
ter
in
g
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
o
n
th
e
Pima
I
n
d
ian
d
ataset
to
p
r
ed
ict
d
iab
etes
with
b
etter
ac
cu
r
ac
y
.
T
h
e
au
th
o
r
s
p
r
ep
r
o
ce
s
s
ed
d
ata
b
y
a
p
p
ly
in
g
ef
f
icien
t
f
ea
tu
r
e
s
elec
tio
n
m
o
d
alities
an
d
also
s
p
lit
th
e
d
ataset
in
to
tr
ain
an
d
test
d
ata.
Fin
ally
,
af
ter
a
p
p
ly
in
g
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
to
th
e
p
r
e
p
r
o
ce
s
s
ed
d
ataset,
th
ey
g
o
t th
e
b
est ac
cu
r
ac
y
o
f
alm
o
s
t 9
0
% f
r
o
m
th
e
f
ar
th
est f
ir
s
t a
p
p
r
o
ac
h
.
Naz
a
n
d
Ah
u
ja
[
9
]
u
s
ed
t
h
e
Pima
I
n
d
ian
d
ataset
an
d
d
ep
l
o
y
ed
s
ev
er
al
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
.
Fo
r
b
etter
p
r
ed
icti
o
n
,
th
e
a
u
th
o
r
s
u
s
ed
s
y
n
th
etic
o
v
er
s
am
p
lin
g
a
n
d
r
a
p
id
m
in
in
g
s
tu
d
io
f
o
r
p
r
ep
r
o
c
ess
in
g
an
d
r
u
d
im
en
ta
r
y
p
r
e
d
ic
tio
n
.
T
h
e
o
b
tain
e
d
ac
cu
r
ac
ies
f
o
r
d
if
f
er
e
n
t
m
o
d
el
s
r
an
g
ed
f
r
o
m
0
.
9
0
to
0
.
9
8
.
A
NN
-
b
ased
d
ee
p
lea
r
n
in
g
tech
n
iq
u
e
ac
h
ie
v
ed
th
e
b
est
r
esu
lt
with
0
.
9
8
ac
c
u
r
ac
y
.
Ku
m
ar
i
et
a
l.
[
1
0
]
a
p
p
lied
an
en
s
em
b
le
lear
n
in
g
tech
n
i
q
u
e
with
a
s
o
f
t
v
o
te
class
if
ier
to
b
o
o
s
t
th
e
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
.
T
h
e
au
t
h
o
r
s
p
r
ep
r
o
ce
s
s
ed
v
ar
io
u
s
f
ea
tu
r
es in
th
e
p
u
b
lic
d
ataset
u
s
in
g
en
co
d
in
g
la
b
els
an
d
m
i
n
-
m
ax
n
o
r
m
aliza
tio
n
ap
p
r
o
ac
h
es.
T
h
e
s
o
f
t
v
o
tin
g
e
n
s
em
b
le
tec
h
n
iq
u
e
p
r
o
d
u
ce
d
th
e
b
est
p
er
f
o
r
m
a
n
ce
s
:
an
F1
s
co
r
e
o
f
0
.
8
0
6
,
a
p
r
ec
is
io
n
o
f
0
.
7
3
4
8
,
0
.
7
1
4
5
r
ec
all
,
a
n
d
0
.
9
7
0
2
class
if
icatio
n
ac
cu
r
ac
y
.
B
u
tt
et
a
l
.
[
1
1
]
u
s
ed
v
ar
i
o
u
s
m
ac
h
in
e
lea
r
n
in
g
an
d
tr
ee
-
b
ased
en
s
em
b
le
al
g
o
r
ith
m
s
to
class
if
y
d
iab
etes.
Mu
ltil
ay
er
p
e
r
ce
p
tr
o
n
(
ML
P)
was
f
i
n
e
-
tu
n
e
d
b
e
ca
u
s
e
o
f
o
u
tp
er
f
o
r
m
in
g
o
t
h
er
alg
o
r
ith
m
s
with
a
n
ac
cu
r
ac
y
o
f
8
6
.
0
8
%.
So
m
e
o
f
th
e
ar
ticles
em
p
lo
y
ed
cu
s
to
m
d
atasets
co
llected
f
r
o
m
v
ar
i
o
u
s
s
o
u
r
ce
s
.
I
s
lam
et
a
l
.
[
1
2
]
in
tr
o
d
u
ce
d
two
latest
tech
n
iq
u
es
to
d
e
r
iv
e
im
p
o
r
ta
n
t
f
ea
tu
r
e
s
f
r
o
m
th
e
o
r
al
g
lu
c
o
s
e
to
ler
a
n
ce
test
.
I
d
en
tify
in
g
th
e
b
est
s
eg
m
en
ts
an
d
m
o
s
t
cr
itical
r
is
k
f
ac
to
r
s
th
at
ac
co
u
n
t
f
o
r
th
e
f
u
r
th
er
ad
v
a
n
ce
m
en
t
o
f
d
iab
etes
is
a
cr
u
cial
co
n
tr
ib
u
tio
n
o
f
t
h
e
au
th
o
r
s
.
T
h
e
au
th
o
r
s
u
s
ed
d
ata
f
r
o
m
s
an
a
n
to
n
io
h
ea
r
t
s
tu
d
y
(
SAHS).
T
h
e
ar
ith
m
etica
l
m
ea
n
o
f
th
e
ap
p
r
o
p
r
iate
v
ar
iab
le
was
u
s
ed
to
f
ill
in
m
is
s
in
g
v
alu
es
i
n
th
e
r
aw
d
ataset.
T
h
e
em
p
lo
y
e
d
m
ac
h
in
e
lear
n
in
g
m
o
d
els
wer
e
tr
ain
e
d
an
d
test
ed
u
s
in
g
a
1
0
-
f
o
ld
C
V
ap
p
r
o
ac
h
.
T
h
e
p
r
o
b
ab
ilit
y
o
f
a
p
er
s
o
n
h
a
v
in
g
ty
p
e
2
d
iab
etes
in
th
e
u
p
c
o
m
in
g
7
-
8
y
ea
r
s
is
p
r
ed
icted
b
y
th
e
n
aïv
e
B
ay
es
ap
p
r
o
ac
h
with
a
n
ac
cu
r
ac
y
o
f
9
5
.
9
4
%.
Pu
s
to
ze
r
o
v
et
a
l.
[
1
3
]
u
s
ed
th
e
ir
u
n
iq
u
e
d
ataset
co
llected
f
r
o
m
a
R
u
s
s
ian
m
ed
ical
r
esear
ch
ce
n
ter
.
T
h
e
d
ataset
in
clu
d
es
3
,
2
4
0
m
ea
l
r
ec
o
r
d
in
g
s
an
d
th
eir
r
elate
d
p
o
s
tp
r
a
n
d
ia
l
g
ly
ce
m
ic
r
esp
o
n
s
es
(
PP
GR
)
f
r
o
m
p
atien
ts
.
T
h
e
au
th
o
r
s
em
p
lo
y
ed
g
r
ad
ien
t
b
o
o
s
tin
g
m
o
d
els
f
o
r
p
r
ed
ictio
n
,
tr
ain
ed
with
h
y
p
er
p
ar
a
m
eter
tu
n
in
g
an
d
cr
o
s
s
-
v
alid
atio
n
.
T
h
e
m
o
s
t
im
p
o
r
ta
n
t
f
ac
to
r
s
in
f
lu
e
n
cin
g
t
h
e
PP
GR
ar
e
f
o
u
n
d
to
b
e
g
ly
ce
m
ic
lo
ad
,
ca
r
b
o
h
y
d
r
ate
co
u
n
t,
an
d
m
ea
l
s
ty
le.
W
h
en
th
e
m
o
d
el
d
id
n
o
t
u
s
e
d
ata
o
n
t
h
e
cu
r
r
en
t
g
lu
c
o
s
e
lev
el,
th
e
v
alu
e
f
o
r
a
p
er
s
o
n
’
s
co
r
r
elatio
n
was
0
.
6
3
1
,
an
d
th
e
m
ea
n
ab
s
o
lu
te
er
r
o
r
was
0
.
3
7
3
m
m
o
lL
-
1
.
W
h
en
th
e
m
o
d
el
u
s
ed
d
ata
o
n
t
h
e
cu
r
r
en
t
g
l
u
co
s
e
lev
el,
th
e
v
al
u
e
f
o
r
a
p
e
r
s
o
n
’
s
co
r
r
elatio
n
was
0
.
6
4
4
,
an
d
th
e
m
ea
n
f
u
n
d
am
en
tal
er
r
o
r
was
0
.
3
7
1
m
m
o
lL
-
1
.
W
h
en
th
e
m
o
d
el
u
tili
ze
d
d
ata
o
n
c
o
n
tin
u
al
b
lo
o
d
g
lu
c
o
s
e
tr
en
d
s
b
ef
o
r
e
th
e
m
ea
l,
th
e
v
alu
e
f
o
r
a
p
er
s
o
n
’
s
c
o
r
r
elatio
n
was
0
.
7
0
4
,
an
d
th
e
m
ea
n
a
b
s
o
lu
te
er
r
o
r
was
0
.
3
4
1
m
m
o
lL
-
1
.
Azb
eg
et
a
l
.
[
1
4
]
em
p
lo
y
e
d
Pima
I
n
d
ian
d
ataset
an
d
a
u
n
i
q
u
e
d
iab
etes
d
ata
b
ase
f
r
o
m
th
e
Fra
n
k
f
u
r
t
Ger
m
an
y
Ho
s
p
ital
to
d
ev
elo
p
a
n
o
v
el
s
tr
ateg
y
f
o
r
ef
f
ec
tiv
ely
p
r
e
d
i
ctin
g
d
iab
etes.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el’
s
ac
cu
r
ac
y
was
9
9
.
5
%
f
o
r
th
e
Fra
n
k
f
u
r
t
d
ataset,
9
9
.
5
%
f
o
r
t
h
e
Pima
I
n
d
ian
d
ataset,
an
d
9
9
.
8
%
f
o
r
th
e
co
m
b
in
e
d
d
ataset,
all
b
a
s
ed
o
n
an
ad
a
p
tiv
e
r
an
d
o
m
f
o
r
est
m
eth
o
d
.
Fo
r
s
ec
u
r
e
d
ata
co
llectio
n
a
n
d
ar
ch
iv
a
l,
th
e
au
t
h
o
r
s
co
m
b
in
ed
in
ter
p
l
an
etar
y
f
ile
s
y
s
tem
(
I
PF
S
)
d
is
tr
ib
u
ted
f
r
am
ewo
r
k
an
d
b
l
o
ck
ch
ain
with
I
o
T
m
ed
ical
d
ev
ices,
s
tr
en
g
th
e
n
in
g
an
d
im
p
r
o
v
i
n
g
th
e
m
ec
h
an
is
m
’
s
co
n
s
is
ten
cy
.
Fro
m
th
e
ab
o
v
e
p
ar
ag
r
ap
h
s
,
we
ca
n
d
ec
ip
h
er
th
at
ex
te
n
s
iv
e
r
esear
ch
h
as
b
ee
n
d
o
n
e
o
n
au
to
m
atic
d
iab
etes
p
r
ed
ictio
n
.
Var
io
u
s
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
wer
e
ap
p
lied
in
th
ese
wo
r
k
s
to
p
r
ed
ict
d
iab
etes
ac
cu
r
ately
.
T
h
e
m
aj
o
r
ity
o
f
th
e
s
e
s
tu
d
ies
u
s
ed
d
if
f
er
en
t
o
p
e
n
-
s
o
u
r
ce
d
atasets
with
o
u
t
u
s
in
g
a
n
y
co
m
p
r
eh
en
s
ib
le
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
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
408
-
4
1
5
410
ar
tific
ial
in
tellig
en
ce
tech
n
iq
u
es
to
an
aly
ze
th
e
p
r
ed
ictio
n
s
m
ad
e
b
y
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
As
a
r
esu
lt,a
co
m
b
in
atio
n
o
f
o
p
en
-
s
o
u
r
ce
a
n
d
cu
s
to
m
d
atasets
an
d
ex
p
lain
ab
le
ar
tific
ial
in
tellig
en
ce
ap
p
r
o
ac
h
es
h
av
e
b
ee
n
p
r
o
p
o
s
ed
in
th
is
wo
r
k
.
T
h
is
ar
ticle
u
s
ed
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
t
o
p
r
ed
ict
th
e
p
o
s
s
ib
le
p
r
esen
ce
o
f
t
y
p
e
2
d
iab
etes
at
an
ea
r
ly
s
tag
e.
T
h
e
s
ig
n
if
ica
n
t c
o
n
tr
ib
u
tio
n
o
f
th
is
wo
r
k
ca
n
b
e
lis
ted
as:
−
A
cu
s
to
m
d
ataset
o
f
f
em
ale
d
ia
b
etes
p
atien
ts
co
llected
f
r
o
m
a
lo
ca
l
m
ed
ical
ce
n
ter
in
B
an
g
la
d
esh
h
as
b
ee
n
in
tr
o
d
u
ce
d
to
th
e
s
cien
tific
co
m
m
u
n
ity
.
T
h
is
d
ataset
h
as
b
ee
n
co
m
b
in
e
d
with
th
e
p
u
b
li
c
Pima
I
n
d
ian
d
ataset.
−
Me
an
im
p
u
tatio
n
,
in
ter
q
u
ar
tile
r
an
g
e
(
I
QR
)
-
b
ased
o
u
tlier
d
et
ec
tio
n
an
d
s
y
n
th
etic
o
v
er
s
am
p
lin
g
tech
n
iq
u
e
(
SMOT
E
)
tech
n
iq
u
es h
a
v
e
b
e
en
u
s
ed
in
th
e
d
ata
p
r
ep
r
o
ce
s
s
in
g
s
tag
e.
−
Gr
id
Sear
ch
C
V
h
y
p
er
p
a
r
am
ete
r
o
p
tim
izatio
n
m
et
h
o
d
h
as
b
ee
n
ap
p
lied
f
o
r
v
a
r
io
u
s
m
ac
h
i
n
e
lear
n
in
g
an
d
en
s
em
b
le
ap
p
r
o
ac
h
es.
−
E
x
p
lain
ab
le
ar
tific
ial
in
tellig
en
ce
lib
r
ar
y
lo
ca
l
in
ter
p
r
etab
le
m
o
d
el
-
ag
n
o
s
tic
ex
p
lan
atio
n
s
(
L
I
ME
)
is
u
tili
ze
d
to
in
ter
p
r
et
th
e
r
esu
lt
s
an
d
d
eter
m
in
e
th
e
m
ain
c
o
n
tr
ib
u
tin
g
f
ac
to
r
s
th
at
im
p
ac
t
th
e
p
r
ed
ictio
n
p
r
o
ce
s
s
,
m
ak
in
g
th
is
r
esear
ch
m
o
r
e
r
eliab
le
.
T
h
e
n
o
v
elty
o
f
th
is
wo
r
k
is
th
e
ap
p
licatio
n
o
f
ex
p
lain
ab
le
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es
o
n
a
u
n
iq
u
e
lo
ca
l d
ataset
o
f
f
em
ale
p
atien
ts
o
f
B
an
g
lad
esh
.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
illu
s
tr
ate
s
th
e
d
at
aset
u
s
ed
,
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es,
ap
p
lied
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els,
an
d
o
v
e
r
all
wo
r
k
in
g
s
eq
u
en
ce
s
o
f
th
e
p
r
o
p
o
s
ed
au
to
m
atic
d
i
ab
etes id
en
tific
atio
n
s
y
s
tem
.
T
h
e
wo
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
d
iab
etes
p
r
ed
ictio
n
s
y
s
tem
s
tar
t
s
wit
h
th
e
m
er
g
in
g
o
f
th
e
Pima
I
n
d
ian
d
ataset
an
d
a
p
r
iv
ate
d
ataset
f
r
o
m
C
h
o
to
Go
b
r
a
C
o
m
m
u
n
it
y
C
lin
ic
o
f
T
an
g
ail,
B
an
g
lad
esh
,
f
o
llo
wed
b
y
d
ataset
p
r
ep
r
o
c
ess
in
g
an
d
d
ata
s
p
lit
in
to
tr
ain
in
g
an
d
test
s
ets.
T
h
e
tr
ain
in
g
d
ata
u
n
d
e
r
g
o
es
SMOT
E
f
o
r
b
alan
cin
g
an
d
is
f
ed
in
to
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
m
o
d
els with
h
y
p
er
p
ar
am
eter
tu
n
in
g
ap
p
r
o
ac
h
es
.
2
.
1
.
Da
t
a
s
et
T
h
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
h
as
b
ee
n
tr
ain
ed
an
d
test
ed
u
s
in
g
a
m
er
g
ed
d
ataset
wh
ich
in
clu
d
ed
th
e
Pima
I
n
d
ian
d
ataset
[
1
5
]
an
d
a
cu
s
to
m
lo
ca
l d
ataset.
T
h
e
p
r
iv
ate
d
ataset
h
as b
ee
n
co
llected
f
r
o
m
C
h
o
to
Go
b
r
a
C
o
m
m
u
n
ity
C
lin
ic
o
f
T
an
g
ail,
B
an
g
lad
esh
.
T
h
e
d
ataset
in
cl
u
d
es
9
5
in
s
tan
ce
s
o
f
f
em
ale
p
atien
ts
.
I
t
co
m
p
r
is
es
v
ar
io
u
s
attr
ib
u
tes,
i.e
.
,
weig
h
t,
h
eig
h
t,
b
lo
o
d
p
r
ess
u
r
e,
g
l
u
c
o
s
e,
ag
e
a
n
d
n
u
m
b
e
r
o
f
p
r
eg
n
an
cies.
T
h
e
Pima
I
n
d
ian
d
ataset
co
n
tain
s
8
6
3
ca
s
es,
s
ep
ar
ated
in
to
two
cla
s
s
es
wi
th
eig
h
t
d
is
tin
ct
attr
ib
u
tes.
T
o
m
ai
n
tain
co
n
s
is
ten
cy
b
etwe
en
th
e
two
d
atasets
,
we
h
a
v
e
u
s
ed
th
e
s
h
ar
ed
f
iv
e
f
ea
tu
r
es,
p
r
eg
n
a
n
cy
,
g
l
u
co
s
e,
b
lo
o
d
p
r
e
s
s
u
r
e,
b
o
d
y
m
ass
in
d
ex
(
B
MI
)
an
d
ag
e
.
T
ab
le
1
illu
s
tr
ates
th
e
d
if
f
er
en
t
f
ea
tu
r
es
an
d
o
u
t
co
m
es
o
f
th
e
m
er
g
ed
d
ataset
u
s
ed
in
th
is
wo
r
k
.
As
th
e
tab
le
in
d
icate
s
,
th
e
co
m
b
i
n
ed
d
ataset
h
as
f
iv
e
f
ea
tu
r
es
an
d
h
as
an
o
u
tp
u
t
th
at
s
h
o
ws wh
eth
er
th
e
p
er
s
o
n
h
as
d
iab
etes (
Yes)
o
r
n
o
t (
No
)
.
T
ab
le
1
.
C
h
ar
ac
ter
is
tics
o
f
th
e
m
er
g
ed
d
ataset
u
s
ed
in
th
is
wo
r
k
F
e
a
t
u
r
e
D
e
scri
p
t
i
o
n
N
u
mb
e
r
o
f
r
e
c
o
r
d
s
(
p
u
b
l
i
c
)
7
6
8
N
u
mb
e
r
o
f
r
e
c
o
r
d
s
(
p
r
i
v
a
t
e
)
95
To
t
a
l
N
u
m
b
e
r
o
f
r
e
c
o
r
d
s (m
e
r
g
e
d
)
8
6
3
To
t
a
l
n
u
m
b
e
r
o
f
a
t
t
r
i
b
u
t
e
s
5
A
t
t
r
i
b
u
e
s
1
:
P
r
e
g
n
a
n
c
i
e
s
R
a
n
g
e
:
0
t
o
1
7
A
t
t
r
i
b
u
e
s
2
:
G
l
u
c
o
se
(
mg
/
d
L)
R
a
n
g
e
:
0
t
o
1
9
9
A
t
t
r
i
b
u
e
s
3
:
B
l
o
o
d
p
r
e
ss
u
r
e
(
mm
H
g
)
R
a
n
g
e
:
0
t
o
1
2
2
A
t
t
r
i
b
u
e
s
4
:
B
M
I
R
a
n
g
e
s:
0
t
o
6
7
.
1
0
A
t
t
r
i
b
u
e
s
5
:
A
g
e
(
y
e
a
r
s)
R
a
n
g
e
:
2
1
t
o
8
1
O
u
t
c
o
m
e
C
a
t
e
g
o
r
i
c
a
l
:
Y
e
s (D
i
a
b
e
t
e
s)
,
N
o
(
H
e
a
l
t
h
y
)
2
.
2
.
Da
t
a
s
et
prepro
ce
s
s
ing
Me
d
ical
d
ata
in
th
e
ac
t
u
al
wo
r
ld
is
in
co
h
e
r
en
t,
b
iza
r
r
e,
an
d
co
m
p
lex
.
I
t
m
ay
h
av
e
n
u
ll
v
alu
es,
in
co
m
p
lete
d
ata,
an
d
o
u
tlier
s
.
Data
p
r
ep
r
o
ce
s
s
in
g
is
o
n
e
elem
en
t
th
at
af
f
ec
ts
an
y
class
if
icatio
n
s
y
s
tem
’
s
p
er
f
o
r
m
an
ce
.
C
lass
if
icatio
n
in
ac
cu
r
ac
y
will b
e
elev
ate
d
if
th
e
d
ata
q
u
ality
is
n
o
t
f
ac
ilit
ated
[
1
6
]
.
I
n
th
is
wo
r
k
,
we
h
a
v
e
attem
p
ted
to
h
a
n
d
le
th
e
d
ata
as
ef
f
ic
ien
tly
as
p
o
s
s
ib
le.
As
a
r
esu
lt,
we
wen
t
th
r
o
u
g
h
v
ar
io
u
s
ef
f
icien
t
p
r
ep
r
o
ce
s
s
in
g
p
r
o
ce
s
s
es.
I
n
th
e
m
e
r
g
ed
d
ataset,
s
o
m
e
v
alu
es
wer
e
m
is
s
in
g
f
o
r
s
ev
er
al
in
s
tan
ce
s
.
Fo
r
in
s
tan
ce
,
it
m
ak
es
n
o
s
en
s
e
to
h
av
e
ze
r
o
b
lo
o
d
p
r
ess
u
r
e.
T
h
e
d
ataset
h
as
a
r
elativ
ely
s
m
all
n
u
m
b
er
o
f
ca
s
es.
As
a
r
esu
lt,
we
d
id
n
o
t
ex
clu
d
e
an
y
in
s
tan
ce
s
with
n
u
ll
v
alu
es
an
d
in
s
tead
u
s
ed
th
e
m
ea
n
im
p
u
tatio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
tic
d
ia
b
etes p
r
ed
ictio
n
w
ith
ex
p
la
in
a
b
le
m
a
ch
in
e
le
a
r
n
in
g
tech
n
i
q
u
es
(
A
d
i
b
a
Ha
q
u
e
)
411
m
eth
o
d
.
Ag
ain
,
t
h
e
m
a
x
im
u
m
v
alu
es
in
t
h
e
s
am
p
le
a
p
p
ea
r
e
d
to
b
e
to
o
h
ig
h
,
e.
g
.
,
a
m
ax
i
m
u
m
B
MI
o
f
6
7
.
1
0
ca
n
b
e
co
n
s
id
er
e
d
an
o
u
tlier
.
W
e
u
s
ed
I
QR
tech
n
i
q
u
es
to
s
o
lv
e
th
is
p
r
o
b
lem
o
f
o
u
tlier
d
etec
tio
n
.
W
e
also
ap
p
lied
f
ea
tu
r
e
s
ca
lin
g
in
th
is
wo
r
k
.
T
h
e
p
r
o
ce
s
s
o
f
n
o
r
m
aliz
in
g
th
e
in
d
ep
en
d
en
t f
ea
t
u
r
e
v
a
lu
es with
in
a
g
iv
en
r
an
g
e
is
k
n
o
wn
as
f
ea
tu
r
e
s
ca
l
in
g
.
Featu
r
e
s
ca
lin
g
is
o
n
e
o
f
t
h
e
m
o
s
t
im
p
o
r
ta
n
t
d
ata
p
r
e
p
r
o
ce
s
s
in
g
s
tep
s
[
1
7
]
.
T
h
e
d
ataset
h
ad
to
b
e
s
tan
d
a
r
d
ized
s
in
ce
it
h
ad
v
ar
ied
s
ca
les.
T
h
e
v
alu
es
o
f
co
r
r
elatio
n
b
etwe
en
d
if
f
er
e
n
t
attr
ib
u
tes an
d
f
in
al
o
u
tco
m
e
(
c
lass
)
o
f
th
e
co
m
b
i
n
ed
d
ataset,
wh
ich
r
an
g
e
f
r
o
m
0
to
1
,
a
r
e
s
h
o
wn
in
T
a
b
le
2
.
T
ab
le
2
.
Valu
es o
f
co
r
r
elatio
n
o
f
v
ar
i
o
u
s
f
ea
tu
r
es a
n
d
o
u
tc
o
m
e
o
f
th
e
m
er
g
e
d
d
ataset
P
r
e
g
n
a
n
c
i
e
s
G
l
u
c
o
s
e
BP
B
M
I
A
g
e
O
u
t
p
u
t
P
r
e
g
n
a
n
c
i
e
s
1
.
0
0
0
.
1
2
9
0
.
1
4
1
0
.
0
1
8
0
.
5
4
4
0
.
2
2
2
G
l
u
c
o
s
e
0
.
1
2
9
1
.
0
0
0
.
1
5
3
0
.
2
2
1
0
.
2
6
3
0
.
4
6
7
BP
0
.
1
4
1
0
.
1
5
3
1
.
0
0
0
.
2
8
2
0
.
2
3
9
0
.
0
6
5
B
M
I
0
.
0
1
7
0
.
2
2
1
0
.
2
8
2
1
.
0
0
0
.
0
3
6
0
.
2
9
2
A
g
e
0
.
5
4
4
0
.
2
6
4
0
.
2
3
9
0
.
0
3
6
1
.
0
0
0
.
2
3
8
O
u
t
p
u
t
0
.
2
2
1
0
.
4
6
7
0
.
0
6
5
0
.
2
9
2
0
.
2
3
9
1
.
0
0
2
.
3
.
P
re
pa
ring
m
a
chine le
a
r
nin
g
m
o
dels
W
e
h
av
e
u
s
ed
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
in
th
is
r
esear
ch
.
B
ef
o
r
e
ap
p
ly
in
g
d
if
f
er
e
n
t
m
o
d
els,
we
em
p
lo
y
e
d
a
f
ew
way
s
to
g
et
th
e
b
est
r
esu
lts
o
u
t
o
f
ea
ch
m
o
d
el.
W
e
ap
p
lied
SMOT
E
,
h
y
p
er
p
a
r
am
eter
o
p
tim
izatio
n
with
Gr
id
Sear
ch
C
V,
an
d
e
x
p
lain
ab
le
ar
tific
ial
in
tellig
en
ce
ap
p
r
o
ac
h
es
to
g
e
t
th
e
b
est
ac
cu
r
ac
y
o
u
t o
f
t
h
e
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
.
‒
SMOT
E
:
T
h
e
SMOT
E
cr
ea
te
s
n
ew
s
y
n
th
etic
o
b
s
er
v
atio
n
s
f
o
r
t
h
e
m
i
n
o
r
ity
ca
teg
o
r
y
s
am
p
les
f
r
o
m
th
e
n
ea
r
est
n
eig
h
b
o
r
s
in
its
co
r
r
esp
o
n
d
in
g
f
ea
tu
r
e
s
p
ac
e
[
1
8
]
.
T
h
e
p
r
im
ar
y
p
u
r
p
o
s
e
o
f
th
is
ap
p
r
o
a
ch
is
to
s
o
lv
e
p
r
o
b
lem
s
th
at
o
cc
u
r
wh
en
u
s
in
g
an
im
b
alan
ce
d
d
ataset.
I
t
is
an
im
p
r
o
v
ed
v
er
s
io
n
o
f
t
h
e
tr
ad
itio
n
al
o
v
er
s
am
p
lin
g
tech
n
iq
u
e.
T
h
e
a
p
p
r
o
p
r
iate
way
o
f
ap
p
ly
in
g
SMOT
E
d
ir
ec
tly
o
n
th
e
tr
ain
in
g
d
ata
s
et
in
s
tead
o
f
th
e
v
alid
atio
n
s
et.
Ap
p
ly
in
g
SMOT
E
d
ir
ec
tly
o
n
th
e
e
n
tire
d
ataset
cr
ea
tes
n
ew
s
am
p
les
t
h
at
wo
u
ld
also
ap
p
ea
r
in
t
h
e
v
alid
atio
n
o
r
test
in
g
d
ata
s
et,
g
iv
in
g
u
s
m
is
lead
in
g
r
esu
lts
.
‒
Gr
id
Sear
ch
C
V:
Fo
r
an
y
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
we
aim
f
o
r
th
e
h
ig
h
est
le
v
el
o
f
ac
c
u
r
ac
y
an
d
o
p
tim
al
h
y
p
er
p
ar
am
eter
s
.
I
n
th
is
wo
r
k
,
we
h
a
v
e
u
s
ed
h
y
p
e
r
p
ar
am
eter
tu
n
in
g
with
Gr
id
Sear
ch
C
V.
A
h
y
p
er
p
ar
am
eter
f
r
o
m
Gr
id
Sear
ch
C
V
is
u
s
ed
to
f
in
e
-
tu
n
e
th
e
m
o
d
el
in
th
e
s
p
ec
if
ied
r
an
g
e
o
f
all
p
o
s
s
ib
l
e
co
m
b
in
atio
n
s
o
f
v
a
r
io
u
s
h
y
p
er
p
ar
am
eter
s
[
1
9
]
.
W
h
en
t
h
er
e
a
r
e
m
an
y
p
ar
am
eter
s
to
tu
n
e,
a
n
d
th
e
d
ataset
is
m
o
r
e
ex
ten
s
iv
e
th
an
its
cr
ea
ted
co
m
p
u
tatio
n
al
is
s
u
es
an
d
R
an
d
o
m
ized
Sear
ch
C
V
lib
r
ar
y
is
u
s
ed
.
Sin
ce
we
h
av
e
a
s
m
all
d
ataset,
ap
p
ly
in
g
Gr
id
Sear
ch
C
V
h
elp
ed
to
o
b
tain
ac
cu
r
ate
a
n
d
r
o
b
u
s
t r
esu
l
ts
.
‒
E
x
p
lain
ab
le
a
r
tific
ial
in
tellig
e
n
ce
:
T
h
e
th
r
ee
k
ey
co
m
p
o
n
e
n
ts
o
f
e
x
p
lain
ab
le
ar
tific
ial
i
n
tellig
en
ce
ar
e
f
o
r
ec
asti
n
g
ac
c
u
r
ac
y
,
d
ec
is
io
n
u
n
d
er
s
tan
d
in
g
,
an
d
tr
ac
ea
b
ilit
y
.
Mo
d
el
-
ag
n
o
s
tic
in
ter
p
r
etab
ilit
y
r
ef
er
s
t
o
th
e
ab
ilit
y
o
f
L
I
ME
to
ex
p
lain
wh
y
a
m
ac
h
i
n
e
lear
n
in
g
m
o
d
el
p
r
o
d
u
ce
s
a
p
ar
ticu
lar
r
esu
lt
(
o
u
tco
m
e
)
f
o
r
a
g
iv
en
in
p
u
t
[
2
0
]
.
T
h
e
L
I
M
E
in
ter
p
r
eta
b
le
ar
tific
ial
in
tell
ig
en
ce
m
eth
o
d
h
elp
s
illu
m
in
a
te
a
m
ac
h
i
n
e
lear
n
in
g
m
o
d
el
an
d
m
ak
e
p
r
ed
ictio
n
s
u
n
d
er
s
tan
d
a
b
ly
.
2
.
4
.
Appl
ied m
a
chine le
a
rning
m
o
dels
T
h
e
f
o
llo
win
g
p
ar
a
g
r
ap
h
s
d
ep
ict
b
r
ief
d
escr
ip
tio
n
s
o
f
th
e
em
p
lo
y
ed
m
o
d
els in
th
is
wo
r
k
.
‒
SVM
:
SVM
b
elo
n
g
s
to
th
e
f
ir
s
t
o
f
th
ese
th
r
ee
ca
teg
o
r
ies,
i.e
.
,
s
u
p
er
v
is
ed
lear
n
in
g
[
2
1
]
.
C
lass
if
y
in
g
o
b
jects
is
o
n
e
o
f
th
e
m
o
s
t
b
asic
m
ac
h
in
e
lear
n
in
g
p
r
o
b
lem
s
,
an
d
SVM
is
o
n
e
o
f
th
e
b
est
class
if
ica
tio
n
m
eth
o
d
s
.
T
h
is
m
o
d
el
o
u
tp
er
f
o
r
m
s
o
t
h
er
tech
n
iq
u
es
lik
e
n
eu
r
al
n
e
two
r
k
s
in
ter
m
s
o
f
p
r
o
ce
s
s
in
g
s
p
ee
d
a
n
d
p
er
f
o
r
m
an
ce
.
I
t
tr
an
s
f
o
r
m
s
d
a
ta
u
s
in
g
k
er
n
el
tr
ick
s
.
I
t
ca
lc
u
lates
th
e
id
ea
l
b
o
u
n
d
ar
y
b
et
wee
n
p
r
o
b
ab
le
o
u
tp
u
t th
r
o
u
g
h
th
is
p
r
o
ce
s
s
.
‒
R
an
d
o
m
f
o
r
est:
r
an
d
o
m
f
o
r
est
is
a
co
llectio
n
o
f
m
o
d
els
th
at
wo
r
k
to
g
eth
e
r
as
an
en
s
em
b
le.
R
an
d
o
m
f
o
r
est
is
a
m
u
ltifu
n
ctio
n
al
m
ac
h
in
e
-
l
ea
r
n
in
g
m
eth
o
d
.
I
t
h
as
b
ee
n
u
s
ed
in
th
is
ar
ticle
to
p
r
e
d
ict
d
i
ab
etes
an
d
its
ef
f
ec
tiv
en
ess
[
2
2
]
.
R
an
d
o
m
f
o
r
est
,
u
n
lik
e
th
e
d
ec
is
io
n
tr
ee
m
eth
o
d
,
g
e
n
er
ates a
lar
g
e
n
u
m
b
er
o
f
d
ec
is
io
n
tr
ee
s
.
E
v
er
y
tr
ee
in
th
e
r
an
d
o
m
f
o
r
est
g
iv
es
ca
teg
o
r
izatio
n
o
u
tp
u
t
a
n
d
‘
v
o
te
’
wh
en
th
e
r
a
n
d
o
m
f
o
r
est
is
ex
p
ec
tin
g
a
n
ew
o
b
ject
b
ased
o
n
s
o
m
e
c
h
ar
ac
ter
is
tics
.
T
h
e
f
o
r
est’s
f
in
al
o
u
tp
u
t
will
b
e
th
e
m
o
s
t
s
ig
n
if
ican
t
n
u
m
b
er
in
tax
o
n
o
m
y
.
‒
Dec
is
io
n
tr
ee
:
d
ec
is
io
n
tr
ee
is
th
e
m
o
s
t
ef
f
ec
tiv
e
a
n
d
ex
ten
s
i
v
ely
u
s
ed
ca
teg
o
r
izatio
n
a
n
d
p
r
ed
ictio
n
t
o
o
l
[
2
3
]
.
On
e
o
f
th
e
m
o
s
t
co
m
m
o
n
tech
n
iq
u
es
f
o
r
r
eg
r
ess
io
n
a
n
d
class
if
icatio
n
is
th
e
d
ec
is
i
o
n
tr
ee
.
I
n
th
is
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
a
cla
s
s
lab
el
i
s
s
to
r
ed
b
y
ea
ch
leaf
n
o
d
e,
an
d
a
test
r
esu
lt is
r
ep
r
esen
ted
b
y
ea
ch
b
r
an
ch
.
T
h
e
d
ec
is
io
n
tr
ee
m
o
d
el’
s
tr
ee
s
tr
u
ctu
r
e
ca
n
b
e
u
ti
lized
to
ex
p
lain
t
h
e
p
r
o
ce
s
s
o
f
ca
teg
o
r
izin
g
in
s
tan
ce
s
b
ased
o
n
th
e
im
p
u
r
it
y
ca
lcu
latio
n
o
f
ea
ch
f
ea
tu
r
e.
‒
K
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN
)
:
KNN
is
o
n
e
o
f
th
e
m
o
s
t
s
tr
aig
h
tf
o
r
war
d
class
if
ier
s
f
o
r
s
o
lv
in
g
class
if
icatio
n
p
r
o
b
lem
s
[
2
4
]
.
T
h
is
is
a
lazy
lear
n
er
alg
o
r
ith
m
an
d
a
n
o
n
-
p
a
r
am
etr
ic
m
eth
o
d
.
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
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
408
-
4
1
5
412
‒
XGBo
o
s
t
c
la
s
s
if
ier
:
XG
B
o
o
s
t
is
an
u
p
g
r
ad
ed
v
er
s
io
n
o
f
g
r
ad
ien
t
b
o
o
s
tin
g
th
at
s
tan
d
s
f
o
r
m
ax
im
u
m
g
r
ad
ien
t
b
o
o
s
tin
g
[
2
5
]
.
T
h
is
alg
o
r
ith
m
’
s
p
r
im
a
r
y
g
o
al
is
to
im
p
r
o
v
e
c
o
m
p
etitio
n
c
o
n
s
is
ten
cy
an
d
m
o
d
e
l
p
er
f
o
r
m
an
ce
.
I
t h
as sev
er
al
f
e
atu
r
es.
‒
Ad
aBo
o
s
t
c
lass
if
ier
:
T
h
e
m
o
s
t
wid
ely
u
s
ed
b
o
o
s
tin
g
te
ch
n
iq
u
e
f
o
r
b
in
a
r
y
class
if
icatio
n
is
ca
lled
Ad
aBo
o
s
t.
I
t
is
a
s
eq
u
en
tial
lea
r
n
in
g
p
r
o
ce
s
s
th
at
m
ea
n
s
o
n
e
tr
ee
is
a
p
r
ev
io
u
s
ly
d
ep
en
d
en
t
tr
ee
.
I
f
m
u
ltip
le
m
o
d
els
ar
e
im
p
lem
en
te
d
s
eq
u
en
tially
as
M1
,
M2
,
an
d
M3
,
i
t
h
as
a
p
r
o
ce
s
s
o
f
ass
em
b
lin
g
,
th
en
M2
will
d
ep
en
d
o
n
M1
;
s
im
ilar
ly
,
M3
will
d
ep
en
d
o
n
M2
.
Her
e
all
th
e
m
o
d
els
ar
e
d
ep
e
n
d
en
t
o
n
ea
ch
o
th
er
.
I
n
Ad
aBo
o
s
t,
tr
ee
s
ar
e
n
o
t
f
u
lly
g
r
o
wn
;
th
ey
c
o
n
s
is
t
o
f
o
n
e
r
o
o
t
an
d
two
leav
es,
r
ef
e
r
r
ed
to
as
s
tu
m
p
s
.
I
t
is
ad
v
an
tag
e
o
u
s
to
co
m
b
in
e
s
ev
e
r
al
wea
k
class
if
ier
s
in
to
o
n
e
s
tr
o
n
g
class
if
ier
.
A
m
e
r
g
e
d
d
at
aset
h
as
b
e
e
n
u
s
ed
i
n
t
h
is
w
o
r
k
c
o
m
b
i
n
i
n
g
t
h
e
Pi
m
a
I
n
d
ia
n
a
n
d
o
u
r
c
o
ll
ec
t
e
d
d
at
asets
,
ill
u
s
tr
at
ed
in
Fi
g
u
r
e
1
.
N
ec
ess
ar
y
p
r
e
p
r
o
c
ess
i
n
g
te
c
h
n
iq
u
es
h
a
v
e
b
ee
n
p
e
r
f
o
r
m
e
d
i
n
t
h
e
m
er
g
e
d
d
a
tase
t,
e.
g
.
,
m
ea
n
i
m
p
u
tati
o
n
f
o
r
m
is
s
in
g
e
n
t
r
ies
,
f
ea
t
u
r
e
s
c
al
i
n
g
wit
h
m
in
-
m
ax
n
o
r
m
a
liz
er
,
a
n
d
I
QR
-
b
as
ed
o
u
tli
er
d
et
ec
t
i
o
n
.
Nex
t,
a
s
t
r
at
if
ie
d
h
o
l
d
o
u
t
v
al
i
d
at
io
n
ap
p
r
o
ac
h
w
it
h
a
9
:
1
r
at
io
w
as
u
s
e
d
t
o
d
iv
id
e
t
h
e
d
ata
s
et
i
n
t
o
t
r
ai
n
i
n
g
a
n
d
test
s
am
p
l
es.
W
e
a
p
p
lie
d
s
y
n
t
h
et
ic
o
v
e
r
s
am
p
li
n
g
a
n
d
G
r
i
d
S
ea
r
c
h
C
V
h
y
p
e
r
p
ar
am
ete
r
o
p
t
i
m
iz
ati
o
n
ap
p
r
o
ac
h
es
o
n
t
r
ai
n
d
a
ta
.
A
f
te
r
t
h
at,
we
ap
p
li
ed
d
if
f
e
r
e
n
t
m
ac
h
i
n
e
lea
r
n
i
n
g
t
ec
h
n
iq
u
es
t
o
c
r
e
at
e
a
u
t
o
m
ati
c
p
r
e
d
i
cti
o
n
m
o
d
e
ls
.
W
e
e
v
a
lu
at
ed
e
ac
h
m
o
d
el
’
s
p
r
ed
i
cti
v
e
p
e
r
f
o
r
m
a
n
c
e
u
s
i
n
g
d
i
f
f
e
r
e
n
t
e
v
a
lu
ati
o
n
p
ar
am
ete
r
s
.
T
h
e
b
es
t
-
p
er
f
o
r
m
i
n
g
m
o
d
els’
p
r
e
d
ic
ti
o
n
p
e
r
f
o
r
m
a
n
c
e
h
as
b
ee
n
r
e
p
r
ese
n
te
d
u
s
i
n
g
e
x
p
lai
n
ab
le
a
r
ti
f
i
cia
l i
n
t
ell
ig
e
n
c
e
.
Fig
u
r
e
1
.
W
o
r
k
i
n
g
p
r
o
ce
s
s
o
f
t
h
e
p
r
o
p
o
s
ed
d
ia
b
etes p
r
ed
ictio
n
s
y
s
tem
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
r
esear
c
h
,
we
u
s
ed
s
ev
e
n
m
ac
h
in
e
lear
n
in
g
a
p
p
r
o
ac
h
es
in
th
e
c
o
m
b
in
e
d
d
ataset
o
f
8
6
3
in
s
tan
ce
s
(
Pima
I
n
d
ian
an
d
c
u
s
to
m
d
atasets
)
an
d
f
iv
e
f
ea
tu
r
es.
T
ab
le
3
d
ep
icts
th
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
o
f
v
ar
io
u
s
class
if
ier
s
f
o
r
d
ef
au
lt
p
ar
am
eter
s
an
d
SMOT
E
tech
n
iq
u
e.
Acc
o
r
d
in
g
to
th
is
tab
le,
SVM
o
u
tp
er
f
o
r
m
s
all
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els with
8
7
% a
cc
u
r
ac
y
an
d
9
1
% F1
s
c
o
r
e.
T
ab
le
3
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
v
ar
i
o
u
s
class
if
ier
s
f
o
r
d
ef
au
lt p
ar
am
eter
s
an
d
SMOT
E
C
l
a
s
si
f
i
e
r
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F
1
S
c
o
r
e
(
%)
A
c
c
u
r
a
c
y
(
%)
S
V
M
91
91
91
87
R
a
n
d
o
m
f
o
r
e
s
t
73
60
66
78
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
66
78
72
74
D
e
c
i
s
i
o
n
t
r
e
e
56
56
56
70
K
N
N
69
45
55
73
X
G
B
o
o
st
66
62
64
79
A
d
a
B
o
o
st
69
42
52
74
T
ab
le
4
d
em
o
n
s
tr
ates
th
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
o
f
v
ar
io
u
s
class
if
ier
s
with
Gr
id
Sear
ch
C
V
h
y
p
er
p
ar
am
eter
o
p
tim
izatio
n
an
d
SMOT
E
.
I
t
s
tates
th
at
b
o
th
SVM
an
d
r
an
d
o
m
f
o
r
est
ac
h
iev
e
th
e
h
ig
h
est
p
r
ec
is
io
n
an
d
F1
s
co
r
e
o
f
9
1
%.
Ov
er
all,
th
e
SVM
m
o
d
el
d
em
o
n
s
tr
ated
th
e
b
est
p
er
f
o
r
m
a
n
ce
with
9
5
%
ac
c
u
r
ac
y
an
d
9
1
%
F1
co
ef
f
icien
t.
T
h
e
a
cc
u
r
ac
y
a
n
d
F1
s
co
r
e
im
p
r
o
v
e
d
with
an
a
v
er
ag
e
o
f
1
2
%
an
d
1
0
%,
r
esp
ec
tiv
ely
,
af
ter
u
s
in
g
th
e
o
p
tim
ized
h
y
p
e
r
p
ar
am
eter
s
.
Fig
u
r
e
2
s
h
o
ws
t
h
e
ac
cu
r
ac
y
o
f
th
e
m
ac
h
in
e
le
ar
n
in
g
m
o
d
els
in
th
e
f
o
r
m
o
f
a
b
a
r
g
r
ap
h
with
d
ef
au
lt
p
ar
am
eter
s
an
d
SMOT
E
tech
n
iq
u
e.
I
t
in
d
icate
s
th
at
SVM
h
as
th
e
b
est
ac
cu
r
ac
y
o
f
8
7
% f
o
r
th
e
m
er
g
e
d
d
ataset.
T
h
e
ac
cu
r
ac
y
o
f
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els
is
d
is
p
la
y
ed
in
Fig
u
r
e
3
as
a
b
a
r
c
h
ar
t
u
s
in
g
Gr
id
Sear
ch
C
V
an
d
SMOT
E
m
eth
o
d
s
.
Acc
o
r
d
i
n
g
to
th
is
f
ig
u
r
e,
th
e
ac
cu
r
ac
y
im
p
r
o
v
ed
f
o
r
al
l
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
Fig
u
r
e
4
p
r
esen
ts
an
illu
s
tr
atio
n
o
f
t
h
e
p
r
ed
ictio
n
i
n
ter
p
r
etatio
n
o
f
th
e
SVM
m
o
d
el
u
s
in
g
th
e
L
I
ME
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
tic
d
ia
b
etes p
r
ed
ictio
n
w
ith
ex
p
la
in
a
b
le
m
a
ch
in
e
le
a
r
n
in
g
tech
n
i
q
u
es
(
A
d
i
b
a
Ha
q
u
e
)
413
ex
p
lain
ab
le
ar
tific
ial
in
tellig
e
n
ce
f
r
am
ewo
r
k
.
Sin
ce
t
h
e
SVM
m
o
d
el
with
o
p
tim
ized
h
y
p
e
r
p
ar
am
eter
s
an
d
th
e
SMOT
E
ap
p
r
o
ac
h
p
er
f
o
r
m
e
d
th
e
b
est,
it
was
u
tili
ze
d
to
ev
alu
ate
th
e
L
I
ME
p
r
ed
ictio
n
f
in
d
in
g
s
.
Acc
o
r
d
in
g
to
th
is
f
ig
u
r
e,
th
e
SVM
m
o
d
el
p
r
ed
icted
d
iab
ete
s
(
lab
el:
1
)
f
o
r
th
e
in
d
iv
id
u
al
p
atien
t
with
9
6
%
co
n
f
id
en
ce
.
T
h
e
d
iab
etes
ca
s
e
is
an
ticip
ated
b
ec
au
s
e
o
f
th
e
a
g
e
o
f
less
th
an
2
4
,
g
lu
co
s
e
lev
el
g
r
ea
ter
th
an
1
0
0
m
g
/d
L
an
d
n
u
m
b
er
o
f
p
r
eg
n
a
n
cies
g
r
ea
ter
th
an
1
.
Diab
etes
ca
s
es
ar
e
an
ticip
ate
d
b
ec
au
s
e
t
h
e
ag
e
o
f
th
e
p
er
s
o
n
is
u
n
d
er
2
4
,
th
e
b
lo
o
d
g
lu
c
o
s
e
lev
el
is
g
r
ea
ter
t
h
an
1
0
0
m
g
/
d
L
,
an
d
th
er
e
h
as
b
ee
n
m
o
r
e
th
an
o
n
e
p
r
eg
n
an
cy
.
T
ab
le
5
co
m
p
ar
es
th
e
p
r
o
p
o
s
ed
a
u
to
m
atic
d
ia
b
et
es
p
r
ed
ictio
n
s
y
s
tem
with
ex
i
s
tin
g
wo
r
k
s
.
T
h
is
tab
le
s
h
o
ws
th
at
o
u
r
p
r
o
p
o
s
ed
m
o
d
el
h
as b
ee
n
p
r
o
v
en
to
b
e
h
ig
h
ly
ac
cu
r
ate
c
o
m
p
a
r
ed
to
o
t
h
er
wo
r
k
s
f
o
u
n
d
in
th
e
liter
atu
r
e.
T
ab
le
4
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
v
ar
i
o
u
s
class
if
ier
s
with
o
p
tim
ized
h
y
p
er
p
ar
a
m
eter
s
an
d
S
MO
T
E
C
l
a
s
si
f
i
e
r
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F
1
S
c
o
r
e
(
%)
A
c
c
u
r
a
c
y
(
%)
S
V
M
91
91
91
95
R
a
n
d
o
m
f
o
r
e
s
t
91
91
91
92
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
69
1
0
0
81
87
D
e
c
i
s
i
o
n
t
r
e
e
77
85
81
86
K
N
N
86
55
67
85
X
G
B
o
o
st
74
62
67
82
A
d
a
B
o
o
st
59
68
63
76
Fig
u
r
e
2
.
Valid
atio
n
ac
cu
r
ac
y
o
f
v
ar
i
o
u
s
em
p
lo
y
ed
m
ac
h
in
e
lear
n
in
g
m
o
d
els with
d
ef
au
lt
h
y
p
er
p
ar
am
eter
s
an
d
SMOT
E
tech
n
iq
u
e
Fig
u
r
e
3
.
Valid
atio
n
ac
cu
r
ac
y
o
f
v
ar
i
o
u
s
em
p
lo
y
ed
m
ac
h
in
e
lear
n
in
g
m
o
d
els with
h
y
p
er
p
ar
am
eter
tu
n
in
g
(
Gr
i
d
Sear
ch
C
V)
an
d
S
MO
T
E
tech
n
iq
u
e
Fig
u
r
e
4
.
SVM
m
o
d
el’
s
p
r
ed
ic
tio
n
in
ter
p
r
etatio
n
with
L
I
ME
ex
p
lain
ab
le
ar
tific
ial
in
tellig
en
ce
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
with
o
th
er
wo
r
k
s
R
e
f
e
r
e
n
c
e
D
a
t
a
s
e
t
A
c
c
u
r
a
c
y
a
n
d
b
e
s
t
-
p
e
r
f
o
r
me
d
m
o
d
e
l
F
1
sc
o
r
e
(
%)
[
5
]
P
i
ma
I
n
d
i
a
n
8
8
.
3
%:
E
x
t
r
a
t
r
e
e
s
8
7
.
7
3
[
6
]
P
i
ma
I
n
d
i
a
n
8
6
%:
A
N
N
7
8
.
8
[
7
]
P
i
ma
I
n
d
i
a
n
7
9
.
5
7
%
:
R
a
n
d
o
m
f
o
r
e
s
t
8
5
.
1
7
[
9
]
P
i
ma
I
n
d
i
a
n
9
8
.
0
7
%
:
A
N
N
9
4
.
7
2
[
1
0
]
P
i
ma
I
n
d
i
a
n
7
9
.
0
8
%
:
S
o
f
t
v
o
t
i
n
g
c
l
a
ssi
f
i
e
r
7
1
.
5
6
[
1
1
]
P
i
ma
I
n
d
i
a
n
8
7
.
2
6
%
:
LSTM
N
/
A
Th
i
s
w
o
r
k
P
i
ma
I
n
d
i
a
n
+
P
r
i
v
a
t
e
d
a
t
a
set
9
5
%:
S
V
M
91
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100
%
P
er
ce
n
t
ag
e
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100
%
P
e
r
c
e
n
t
age
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
4
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
5
:
408
-
4
1
5
414
4.
CO
NCLU
SI
O
N
Diab
etes
m
ellitu
s
is
a
s
ev
er
e
m
etab
o
lic
d
is
o
r
d
er
with
in
cr
ea
s
ed
ca
s
es
wo
r
ld
wid
e
d
u
e
to
th
e
d
ev
elo
p
m
e
n
t
o
f
m
o
d
e
r
n
life
s
ty
les.
T
h
is
wo
r
k
aim
s
to
b
u
ild
a
m
o
d
el
u
s
in
g
v
ar
io
u
s
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
o
l
o
g
ies
to
ass
is
t
d
o
cto
r
s
in
th
e
ea
r
ly
d
etec
tio
n
o
f
d
ia
b
etes,
en
h
an
cin
g
p
atien
t
q
u
ality
o
f
life
.
T
h
e
I
QR
ap
p
r
o
ac
h
o
f
o
u
tlier
d
etec
tio
n
,
m
in
-
m
ax
n
o
r
m
alize
r
-
b
ased
f
ea
tu
r
e
s
ca
lin
g
,
an
d
m
ea
n
i
m
p
u
tat
io
n
f
o
r
m
is
s
in
g
d
ata
h
av
e
b
ee
n
u
s
ed
.
T
h
e
ex
p
er
im
en
tal
o
u
tco
m
es
illu
s
t
r
ate
th
at
SVM
p
er
f
o
r
m
ed
b
etter
th
an
t
h
e
o
th
e
r
ap
p
r
o
ac
h
es
with
th
e
SMOT
E
tech
n
iq
u
e
an
d
o
p
tim
ized
h
y
p
e
r
p
ar
am
eter
s
.
T
h
e
p
r
ed
ictio
n
p
r
o
v
id
e
d
b
y
t
h
e
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
h
as
b
ee
n
in
ter
p
r
ete
d
b
y
th
e
L
I
ME
ex
p
lain
ab
le
ar
t
if
icial
in
tellig
en
ce
f
r
am
ewo
r
k
.
I
n
th
e
f
u
tu
r
e,
an
ex
ten
s
iv
e
d
ataset
with
d
iv
er
s
e
co
h
o
r
ts
o
f
p
atien
ts
an
d
c
o
m
p
r
eh
en
s
iv
e
f
ea
tu
r
es c
an
b
e
u
s
ed
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
T.
K
h
a
r
r
o
u
b
i
a
n
d
H
.
M
.
D
a
r
w
i
s
h
,
“
D
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
:
T
h
e
e
p
i
d
e
m
i
c
o
f
t
h
e
c
e
n
t
u
r
y
,
”
Wo
r
l
d
J
o
u
rn
a
l
o
f
D
i
a
b
e
t
e
s
,
v
o
l
.
6
,
n
o
.
6
,
2
0
1
5
,
d
o
i
:
1
0
.
4
2
3
9
/
w
j
d
.
v
6
.
i
6
.
8
5
0
.
[
2
]
S
.
S
c
h
l
e
si
n
g
e
r
e
t
a
l
.
,
“
P
r
e
d
i
a
b
e
t
e
s
a
n
d
r
i
sk
o
f
m
o
r
t
a
l
i
t
y
,
d
i
a
b
e
t
e
s
-
r
e
l
a
t
e
d
c
o
m
p
l
i
c
a
t
i
o
n
s
a
n
d
c
o
mo
r
b
i
d
i
t
i
e
s:
u
m
b
r
e
l
l
a
r
e
v
i
e
w
o
f
m
e
t
a
-
a
n
a
l
y
ses
o
f
p
r
o
s
p
e
c
t
i
v
e
s
t
u
d
i
e
s,
”
D
i
a
b
e
t
o
l
o
g
i
a
,
v
o
l
.
6
5
,
n
o
.
2
,
p
p
.
2
7
5
–
2
8
5
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
1
2
5
-
021
-
0
5
5
9
2
-
3.
[
3
]
“
C
o
mm
u
n
i
t
y
-
b
a
se
d
d
e
t
e
c
t
i
o
n
a
n
d
s
u
r
v
e
i
l
l
a
n
c
e
o
f
g
e
st
a
t
i
o
n
a
l
d
i
a
b
e
t
es
,
”
W
o
rl
d
D
i
a
b
e
t
e
s
F
o
u
n
d
a
t
i
o
n
,
2
0
2
0
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
w
o
r
l
d
d
i
a
b
e
t
e
sf
o
u
n
d
a
t
i
o
n
.
o
r
g
/
p
r
o
j
e
c
t
s/
b
a
n
g
l
a
d
e
sh
-
w
d
f
1
5
-
962
[
4
]
N
.
A
b
d
u
l
h
a
d
i
a
n
d
A
.
A
l
-
M
o
u
s
a
,
“
D
i
a
b
e
t
e
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
m
e
t
h
o
d
s,
”
i
n
2
0
2
1
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
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
I
T
)
,
Ju
l
.
2
0
2
1
,
p
p
.
3
5
0
–
354
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
T5
2
6
8
2
.
2
0
2
1
.
9
4
9
1
7
8
8
.
[
5
]
S
.
M
.
M
.
H
a
s
a
n
,
M
.
F
.
R
a
b
b
i
,
A
.
I
.
C
h
a
m
p
a
,
a
n
d
M
.
A
.
Z
a
ma
n
,
“
A
n
e
f
f
e
c
t
i
v
e
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
sy
s
t
e
m
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
i
n
2
0
2
0
2
n
d
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
Ad
v
a
n
c
e
d
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
C
AI
C
T
)
,
N
o
v
.
2
0
2
0
,
p
p
.
2
3
–
28
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
C
T5
1
7
8
0
.
2
0
2
0
.
9
3
3
3
4
9
7
.
[
6
]
J.
J.
K
h
a
n
a
m
a
n
d
S
.
Y
.
F
o
o
,
“
A
c
o
m
p
a
r
i
so
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
,
”
I
C
T
Ex
p
res
s
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
4
3
2
–
4
3
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
c
t
e
.
2
0
2
1
.
0
2
.
0
0
4
.
[
7
]
V
.
C
h
a
n
g
,
J
.
B
a
i
l
e
y
,
Q
.
A
.
X
u
,
a
n
d
Z
.
S
u
n
,
“
P
i
m
a
I
n
d
i
a
n
s
d
i
a
b
e
t
e
s
me
l
l
i
t
u
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
(
M
L)
a
l
g
o
r
i
t
h
ms
,
”
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
5
,
n
o
.
2
2
,
p
p
.
1
6
1
5
7
–
1
6
1
7
3
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
022
-
07049
-
z.
[
8
]
B
.
F
a
r
h
a
n
a
,
K
.
M
u
n
i
d
h
a
n
a
l
a
k
sh
m
i
,
a
n
d
D
.
R
.
M
.
M
o
h
a
n
a
,
“
P
r
e
d
i
c
t
d
i
a
b
e
t
e
s
mel
l
i
t
u
s
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,”
J
o
u
r
n
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
2
0
8
9
,
n
o
.
1
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
2
0
8
9
/
1
/
0
1
2
0
0
2
.
[
9
]
H
.
N
a
z
a
n
d
S
.
A
h
u
j
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
si
n
g
P
I
M
A
I
n
d
i
a
n
d
a
t
a
se
t
,
”
J
o
u
r
n
a
l
o
f
D
i
a
b
e
t
e
s
a
n
d
Me
t
a
b
o
l
i
c
D
i
s
o
r
d
e
rs
,
v
o
l
.
1
9
,
n
o
.
1
,
p
p
.
3
9
1
–
4
0
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
2
0
0
-
0
2
0
-
0
0
5
2
0
-
5.
[
1
0
]
S
.
K
u
mar
i
,
D
.
K
u
mar,
a
n
d
M
.
M
i
t
t
a
l
,
“
A
n
e
n
se
mb
l
e
a
p
p
r
o
a
c
h
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
o
f
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
u
si
n
g
so
f
t
v
o
t
i
n
g
c
l
a
ss
i
f
i
e
r
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
i
n
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
,
p
p
.
4
0
–
4
6
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
c
c
e
.
2
0
2
1
.
0
1
.
0
0
1
.
[
1
1
]
U
.
M
.
B
u
t
t
,
S
.
L
e
t
c
h
mu
n
a
n
,
M
.
A
l
i
,
F
.
H
.
H
a
ssa
n
,
A
.
B
a
q
i
r
,
a
n
d
H
.
H
.
R
.
S
h
e
r
a
z
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
d
i
a
b
e
t
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
f
o
r
h
e
a
l
t
h
c
a
r
e
a
p
p
l
i
c
a
t
i
o
n
s
,
”
J
o
u
r
n
a
l
o
f
H
e
a
l
t
h
c
a
re
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
0
2
1
,
p
p
.
1
–
1
7
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
9
9
3
0
9
8
5
.
[
1
2
]
M
.
S
.
I
sl
a
m,
M
.
K
.
Q
a
r
a
q
e
,
S
.
B
.
B
e
l
h
a
o
u
a
r
i
,
a
n
d
M
.
A
.
A
b
d
u
l
-
G
h
a
n
i
,
“
A
d
v
a
n
c
e
d
t
e
c
h
n
i
q
u
e
s f
o
r
p
r
e
d
i
c
t
i
n
g
t
h
e
f
u
t
u
r
e
p
r
o
g
r
e
ss
i
o
n
o
f
t
y
p
e
2
d
i
a
b
e
t
e
s
,
”
I
EE
E
A
c
c
e
s
s
,
v
o
l
.
8
,
p
p
.
1
2
0
5
3
7
–
1
2
0
5
4
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
5
5
4
0
.
[
1
3
]
E.
A
.
P
u
s
t
o
z
e
r
o
v
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
p
o
st
p
r
a
n
d
i
a
l
b
l
o
o
d
g
l
u
c
o
s
e
p
r
e
d
i
c
t
i
o
n
i
n
g
e
s
t
a
t
i
o
n
a
l
d
i
a
b
e
t
e
s
mel
l
i
t
u
s,”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
2
1
9
3
0
8
–
2
1
9
3
2
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
4
2
4
8
3
.
[
1
4
]
K
.
A
z
b
e
g
,
M
.
B
o
u
d
h
a
n
e
,
O
.
O
u
c
h
e
t
t
o
,
a
n
d
S
.
J
.
A
n
d
a
l
o
u
s
si
,
“
D
i
a
b
e
t
e
s
e
merg
e
n
c
y
c
a
s
e
s
i
d
e
n
t
i
f
i
c
a
t
i
o
n
b
a
se
d
o
n
a
st
a
t
i
st
i
c
a
l
p
r
e
d
i
c
t
i
v
e
m
o
d
e
l
,
”
J
o
u
r
n
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
9
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
2
-
0
0
5
8
2
-
7.
[
1
5
]
I
.
Ta
si
n
,
T.
U
.
N
a
b
i
l
,
S
.
I
sl
a
m,
a
n
d
R
.
K
h
a
n
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
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
t
e
c
h
n
i
q
u
e
s,”
H
e
a
l
t
h
c
a
re
T
e
c
h
n
o
l
o
g
y
L
e
t
t
e
rs
,
v
o
l
.
1
0
,
n
o
.
1
–
2
,
p
p
.
1
–
1
0
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
4
9
/
h
t
l
2
.
1
2
0
3
9
.
[
1
6
]
M
.
N
.
I
.
S
u
v
o
n
,
S
.
C
.
S
i
a
m,
M
.
F
e
r
d
o
u
s,
M
.
A
l
a
m,
a
n
d
R
.
K
h
a
n
,
“
M
a
s
t
e
r
s
a
n
d
d
o
c
t
o
r
o
f
p
h
i
l
o
so
p
h
y
a
d
mi
ss
i
o
n
p
r
e
d
i
c
t
i
o
n
o
f
b
a
n
g
l
a
d
e
s
h
i
st
u
d
e
n
t
s
i
n
t
o
d
i
f
f
e
r
e
n
t
c
l
a
sses
o
f
u
n
i
v
e
r
si
t
i
e
s
,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
-
AI
)
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
1
5
4
5
–
1
5
5
3
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
1
.
i
4
.
p
p
1
5
4
5
-
1
5
5
3
.
[
1
7
]
P
.
R
a
j
e
n
d
r
a
a
n
d
S
.
La
t
i
f
i
,
“
P
r
e
d
i
c
t
i
o
n
o
f
d
i
a
b
e
t
e
s
u
s
i
n
g
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
a
n
d
e
n
sem
b
l
e
t
e
c
h
n
i
q
u
e
s
,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pro
g
ra
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
U
p
d
a
t
e
,
v
o
l
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
u
p
.
2
0
2
1
.
1
0
0
0
3
2
.
[
1
8
]
A
.
D
e
si
a
n
i
,
S
.
Y
a
h
d
i
n
,
A
.
K
a
r
t
i
k
a
s
a
r
i
,
a
n
d
I
.
I
r
mei
l
y
a
n
a
,
“
H
a
n
d
l
i
n
g
t
h
e
i
m
b
a
l
a
n
c
e
d
d
a
t
a
w
i
t
h
mi
ss
i
n
g
v
a
l
u
e
e
l
i
m
i
n
a
t
i
o
n
S
M
O
T
E
i
n
t
h
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
t
h
e
r
e
l
e
v
a
n
c
e
e
d
u
c
a
t
i
o
n
b
a
c
k
g
r
o
u
n
d
w
i
t
h
g
r
a
d
u
a
t
e
s
e
mp
l
o
y
me
n
t
,
”
I
AE
S
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
I
J
-
AI
)
,
v
o
l
.
1
0
,
n
o
.
2
,
p
p
.
3
4
6
–
3
5
4
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
0
.
i
2
.
p
p
3
4
6
-
3
5
4
.
[
1
9
]
R
.
H
a
q
u
e
,
S
.
H
o
,
I
.
C
h
a
i
,
a
n
d
A
.
A
b
d
u
l
l
a
h
,
“
P
a
r
a
me
t
e
r
a
n
d
h
y
p
e
r
p
a
r
a
m
e
t
e
r
o
p
t
i
mi
s
a
t
i
o
n
o
f
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
f
o
r
p
e
r
s
o
n
a
l
i
se
d
p
r
e
d
i
c
t
i
o
n
s
o
f
a
st
h
ma
,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
512
–
5
1
7
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
2
7
2
0
/
j
a
i
t
.
1
3
.
5
.
5
1
2
-
5
1
7
.
[
2
0
]
R
.
S
i
d
d
i
q
u
a
,
N
.
I
sl
a
m,
J
.
F
.
B
o
l
a
k
a
,
R
.
K
h
a
n
,
a
n
d
S
.
M
o
m
e
n
,
“
A
I
D
A
:
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
b
a
se
d
d
e
p
r
e
ssi
o
n
a
ssessme
n
t
a
p
p
l
i
e
d
t
o
B
a
n
g
l
a
d
e
sh
i
s
t
u
d
e
n
t
s,”
Arr
a
y
,
v
o
l
.
1
8
,
p
.
1
0
0
2
9
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
r
a
y
.
2
0
2
3
.
1
0
0
2
9
1
.
[2
1
]
A
.
Y
.
A
.
A
mer
,
“
G
l
o
b
a
l
-
l
o
c
a
l
l
e
a
s
t
-
sq
u
a
r
e
s
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
(
G
L
o
c
a
l
-
LS
-
S
V
M
)
,”
PL
o
S
O
N
E
,
v
o
l
.
1
8
,
n
o
.
4
,
p
p
.
1
–
1
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
5
1
3
1
.
[2
2
]
E.
A
sam
o
a
h
a
,
G
.
B
.
M
.
H
e
u
v
e
l
i
n
k
a
,
I
.
C
h
a
i
r
i
e
,
P
.
S
.
B
i
n
d
r
a
b
a
n
f
,
a
n
d
V
.
L
o
g
a
h
, “
R
a
n
d
o
m
f
o
r
e
st
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
m
a
i
z
e
y
i
e
l
d
a
n
d
a
g
r
o
n
o
m
i
c
e
f
f
i
c
i
e
n
c
y
p
r
e
d
i
c
t
i
o
n
i
n
G
h
a
n
a
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
1
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
3
7
0
6
5
.
[2
3
]
I
.
D
.
M
i
e
n
y
e
a
n
d
N
.
J
e
r
e
,
“
A
su
r
v
e
y
o
f
d
e
c
i
si
o
n
t
r
e
e
s:
c
o
n
c
e
p
t
s,
a
l
g
o
r
i
t
h
m
s,
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
8
6
7
1
6
-
8
6
7
2
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
1
6
8
3
8
.
[2
4
]
T
.
A.
A
sse
g
i
e
,
“
An
o
p
t
i
mi
z
e
d
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
b
a
s
e
d
b
r
e
a
st
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
R
o
b
o
t
i
c
s
a
n
d
C
o
n
t
ro
l
(
J
RC
)
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
1
1
5
–
1
1
8
,
M
a
y
202
0
,
d
o
i
:
1
0
.
1
8
1
9
6
/
j
r
c
.
2
3
6
3
.
[2
5
]
N
.
J.
R
i
y
a
,
M
.
C
h
a
k
r
a
b
o
r
t
y
,
a
n
d
R
.
K
h
a
n
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
b
a
se
d
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
d
e
n
g
u
e
u
si
n
g
C
B
C
d
a
t
a
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
1
2
3
5
5
-
1
1
2
3
6
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
4
3
2
9
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
tic
d
ia
b
etes p
r
ed
ictio
n
w
ith
ex
p
la
in
a
b
le
m
a
ch
in
e
le
a
r
n
in
g
tech
n
i
q
u
es
(
A
d
i
b
a
Ha
q
u
e
)
415
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Adi
b
a
H
a
q
u
e
o
b
tai
n
e
d
h
e
r
Ba
c
h
e
lo
r’s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fro
m
No
rth
S
o
u
th
U
n
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
S
h
e
is cu
rre
n
tl
y
wo
rk
i
n
g
a
t
S
ta
n
d
a
rd
C
h
a
rtere
d
Ba
n
k
,
Ba
n
g
lad
e
sh
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
a
n
d
n
e
two
rk
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
d
i
b
a
.
h
a
q
u
e
@n
o
rt
h
so
u
th
.
e
d
u
.
S
a
n
ji
d
a
Is
la
m
c
o
m
p
lete
d
h
e
r
Ba
c
h
e
lo
r’s i
n
Co
m
p
u
ter S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
fro
m
No
rth
S
o
u
th
Un
iv
e
rsity
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
He
r
re
se
a
rc
h
in
tere
st
in
c
lu
d
e
s
d
a
tab
a
se
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
n
ji
d
a
.
islam
1
6
@
n
o
rt
h
so
u
th
.
e
d
u
.
Nusr
a
t
Ra
h
i
m
M
im
fin
ish
e
d
h
e
r
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
i
n
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
fr
o
m
No
rt
h
S
o
u
th
Un
iv
e
rsity
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
He
r
re
se
a
rc
h
fo
c
u
s
a
re
a
s
a
re
n
e
two
rk
i
n
g
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
u
sra
t.
m
im@
n
o
rt
h
so
u
t
h
.
e
d
u
.
S
a
b
r
in
a
M
a
n
n
a
n
Mee
m
h
a
s
c
o
m
p
lete
d
h
e
r
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
fro
m
No
rt
h
S
o
u
th
Un
i
v
e
rsity
,
Dh
a
k
a
,
Ba
n
g
lad
e
s
h
.
S
h
e
is
wo
r
k
in
g
a
s
a
train
e
e
e
n
g
in
e
e
r
sp
e
c
ializin
g
i
n
d
a
ta
sc
ien
c
e
in
a
g
o
v
e
r
n
m
e
n
t
g
ra
n
t
trai
n
in
g
p
ro
g
ra
m
.
He
r
re
se
a
rc
h
i
n
c
lu
d
e
s
d
a
ta
a
n
a
ly
ti
c
s,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
He
r
th
e
sis
a
rti
c
le
o
n
se
n
ti
m
e
n
tal
a
n
a
ly
sis
is
p
u
b
li
s
h
e
d
i
n
th
e
Vie
t
n
a
m
Jo
u
rn
a
l
o
f
C
o
m
p
u
ter
S
c
ien
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
sa
b
rin
a
.
m
e
e
m
@n
o
rth
so
u
th
.
e
d
u
.
Ana
n
y
a
S
a
h
a
o
b
tai
n
e
d
h
is
B.
S
c
.
d
e
g
re
e
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
fr
o
m
No
rth
S
o
u
t
h
Un
i
v
e
rsity
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
His
re
se
a
rc
h
in
tere
st
s
in
v
o
lv
e
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
d
e
e
p
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
a
n
a
n
y
a
.
sa
h
a
@n
o
r
t
h
so
u
t
h
.
e
d
u
.
Ria
sa
t
K
h
a
n
e
a
rn
e
d
h
is
B.
S
c
.
d
e
g
re
e
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
fr
o
m
th
e
Isla
m
ic
Un
i
v
e
rsity
o
f
Tec
h
n
o
lo
g
y
,
Ba
n
g
lad
e
sh
,
in
2
0
1
0
.
He
fu
rt
h
e
r
p
u
rsu
e
d
h
is
a
c
a
d
e
m
ic
jo
u
r
n
e
y
,
c
o
m
p
leti
n
g
b
o
th
th
e
M
.
S
c
.
a
n
d
P
h
.
D.
d
e
g
re
e
s
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
t
Ne
w
M
e
x
ico
St
a
te
Un
iv
e
rsity
,
Las
Cru
c
e
s,
US
A,
in
2
0
1
8
.
P
re
se
n
tl
y
,
h
e
h
o
ld
s
t
h
e
p
o
siti
o
n
o
f
As
so
c
iate
P
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
a
t
N
o
rth
S
o
u
th
U
n
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
c
o
m
p
u
t
a
ti
o
n
a
l
b
i
o
e
lec
tro
m
a
g
n
e
ti
c
s,
m
o
d
e
l
o
rd
e
r
re
d
u
c
ti
o
n
,
a
n
d
p
o
we
r
e
lec
tro
n
ics
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
r
ias
a
t.
k
h
a
n
@n
o
rt
h
so
u
th
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.