I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
,
p
p
.
1
94
5
~
1
95
3
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
3
.
pp
1
94
5
-
1
95
3
1945
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Sy
nerg
istic ensem
ble clas
sifica
tion
f
ra
mewo
rk:
u
tilizi
ng
a so
ft
v
o
ting a
lg
o
rithm f
o
r enhanced
pre
diction a
nd d
ia
g
no
sis
of
dia
betes melli
tus
B
ha
nu
P
ra
k
a
s
h L
o
ha
ni,
Arv
ind
Da
g
ur
,
Dhiren
dra
K
um
a
r
Sh
uk
la
S
c
h
o
o
l
o
f
C
o
m
p
u
t
i
n
g
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
G
a
l
g
o
t
i
a
s
U
n
i
v
e
r
si
t
y
,
G
r
e
a
t
e
r
N
o
i
d
a
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
4
,
2
0
2
4
R
ev
is
ed
Sep
27
,
2
0
2
4
Acc
ep
ted
Oct
7
,
2
0
2
4
Dia
b
e
tes
,
a
se
rio
u
s
c
o
n
d
it
i
o
n
c
h
a
ra
c
teriz
e
d
b
y
e
lev
a
ted
b
lo
o
d
g
l
u
c
o
se
lev
e
ls,
c
a
n
b
e
e
ffe
c
ti
v
e
ly
id
e
n
ti
fied
,
a
n
d
p
re
d
icte
d
e
a
rly
u
si
n
g
m
a
c
h
i
n
e
lea
rn
in
g
(M
L)
a
lg
o
ri
th
m
s.
Th
e
re
se
a
rc
h
p
ro
v
id
e
s
a
c
o
m
p
re
h
e
n
siv
e
a
ss
e
ss
m
e
n
t
o
f
th
re
e
e
n
se
m
b
le
ML
m
o
d
e
ls
-
sta
c
k
i
n
g
,
s
o
ft
v
o
ti
n
g
,
a
n
d
h
a
rd
v
o
t
in
g
-
f
o
c
u
se
d
o
n
e
n
h
a
n
c
in
g
d
ia
b
e
tes
d
iag
n
o
sis
a
m
o
n
g
P
ima
In
d
ian
wo
m
e
n
d
a
tas
e
t
t
a
k
e
n
fro
m
th
e
Na
ti
o
n
a
l
I
n
sti
tu
te
o
f
Dia
b
e
tes
a
n
d
Dig
e
stiv
e
a
n
d
Kid
n
e
y
Dise
a
se
s,
th
is
stu
d
y
fo
c
u
se
s
o
n
P
ima
In
d
ian
wo
m
e
n
a
g
e
d
2
1
a
n
d
o
ld
e
r,
wi
th
t
h
e
d
a
tas
e
t
c
o
m
p
risin
g
c
rit
ica
l
d
iag
n
o
stic
m
e
a
su
re
m
e
n
ts.
Two
e
n
se
m
b
le
m
o
d
e
l
s
we
re
d
e
v
e
lo
p
e
d
a
n
d
e
v
a
l
u
a
ted
o
n
v
a
r
io
u
s
e
v
a
lu
a
ti
o
n
p
a
ra
m
e
ters
.
Th
e
sta
c
k
in
g
m
o
d
e
l
c
o
m
b
in
e
s
p
re
d
ictio
n
s
fro
m
v
a
rio
u
s
c
las
sifiers
u
sin
g
a
m
e
ta
-
c
las
sifier,
lev
e
ra
g
in
g
t
h
e
ir
stre
n
g
t
h
s
fo
r
fin
a
l
d
e
c
isio
n
-
m
a
k
in
g
.
In
c
o
n
tras
t,
t
h
e
v
o
ti
n
g
m
o
d
e
l
a
g
g
re
g
a
tes
p
ro
b
a
b
il
i
ty
e
stim
a
tes
fro
m
e
a
c
h
c
las
sifier,
p
ro
v
id
i
n
g
n
u
a
n
c
e
d
p
re
d
ictio
n
s.
B
o
th
m
o
d
e
l
s
we
re
rig
o
ro
u
sly
e
v
a
lu
a
ted
o
n
a
v
a
li
d
a
ti
o
n
d
a
tas
e
t,
e
m
p
h
a
siz
in
g
a
c
c
u
ra
c
y
,
sp
e
c
ifi
c
it
y
,
se
n
siti
v
it
y
,
a
n
d
t
h
e
r
e
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic
(ROC)
a
re
a
u
n
d
e
r
t
h
e
c
u
rv
e
(AU
C)
.
N
o
tab
ly
,
th
e
v
o
ti
n
g
-
b
a
se
d
e
n
se
m
b
le
m
e
th
o
d
s
d
e
m
o
n
stra
ted
su
p
e
ri
o
r
p
e
rfo
r
m
a
n
c
e
in
p
re
d
ictin
g
d
iab
e
tes
f
o
r
t
h
is
c
o
h
o
rt.
H
o
we
v
e
r,
t
h
e
ir
e
ffe
c
ti
v
e
n
e
s
s
h
e
a
v
il
y
re
li
e
s
o
n
p
re
p
r
o
c
e
ss
in
g
,
b
a
se
m
o
d
e
l
se
lec
ti
o
n
,
a
n
d
h
y
p
e
rp
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
.
T
h
is
stu
d
y
u
n
d
e
rsc
o
re
s
th
e
p
o
te
n
ti
a
l
o
f
e
n
se
m
b
le
m
o
d
e
ls
in
m
e
d
ica
l
d
iag
n
o
st
ics
,
h
ig
h
li
g
h
ti
n
g
th
e
c
rit
ica
l
ro
le
o
f
d
a
ta
p
re
p
r
o
c
e
ss
in
g
,
a
n
d
c
o
n
fig
u
ra
ti
o
n
i
n
e
n
h
a
n
c
in
g
p
re
d
ic
ti
v
e
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
Diab
etes
E
n
s
em
b
le
m
o
d
el
Hy
p
er
p
ar
a
m
eter
s
Pre
d
ictiv
e
p
er
f
o
r
m
an
ce
R
OC
So
f
t v
o
tin
g
Stack
in
g
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
:
B
h
an
u
Pra
k
ash
L
o
h
an
i
Sch
o
o
l o
f
C
o
m
p
u
tin
g
Scien
ce
an
d
E
n
g
in
ee
r
in
g
,
Galg
o
tias
Un
iv
er
s
ity
Yam
u
n
a
E
x
p
r
ess
way
,
Gr
ea
ter
No
id
a,
U.
P,
I
n
d
ia
E
m
ail: b
h
an
u
p
lo
h
an
i@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Diab
etes
m
ellitu
s
(
DM
)
,
a
g
l
o
b
al
h
ea
lth
c
r
is
is
,
d
iab
etes
is
m
ar
k
ed
b
y
elev
ated
b
lo
o
d
g
l
u
co
s
e
lev
els
an
d
p
o
s
es
a
p
a
r
ticu
lar
ly
s
ev
er
e
r
is
k
t
o
ce
r
tain
eth
n
ic
g
r
o
u
p
s
,
in
clu
d
in
g
t
h
e
Pima
I
n
d
ia
n
wo
m
e
n
.
T
im
el
y
d
etec
tio
n
an
d
m
an
a
g
em
en
t
o
f
d
iab
etes
is
ess
en
tial
f
o
r
r
ed
u
cin
g
its
lo
n
g
-
ter
m
co
m
p
lica
tio
n
s
[
1
]
.
Ma
c
h
in
e
lear
n
in
g
(
ML
)
alg
o
r
ith
m
s
h
a
v
e
b
ec
o
m
e
an
in
v
alu
ab
le
t
o
o
l
f
o
r
im
p
r
o
v
in
g
th
e
ea
r
ly
p
r
ed
ict
io
n
an
d
d
iag
n
o
s
is
o
f
d
iab
etes,
p
r
o
v
id
in
g
a
m
ajo
r
ad
v
an
ce
m
e
n
t
o
v
e
r
tr
ad
itio
n
al
ap
p
r
o
ac
h
es.
T
h
e
p
o
ten
tial
o
f
ML
in
m
ed
ical
d
iag
n
o
s
tics
is
esp
ec
ially
clea
r
with
t
h
e
u
s
e
o
f
en
s
em
b
le
l
ea
r
n
in
g
m
o
d
els,
wh
ich
h
ar
n
e
s
s
th
e
s
tr
en
g
th
s
o
f
m
u
ltip
le
alg
o
r
ith
m
s
to
e
n
h
an
c
e
p
r
ed
ictiv
e
ac
c
u
r
ac
y
[
2
]
.
A
r
an
g
e
o
f
ML
m
o
d
els
h
av
e
b
ee
n
ex
p
lo
r
e
d
f
o
r
DM
class
if
icatio
n
s
,
with
d
ec
is
io
n
tr
ee
s
a
n
d
n
e
u
r
al
n
etwo
r
k
s
s
h
o
win
g
p
r
o
m
is
in
g
p
r
e
d
ictiv
e
ac
cu
r
ac
y
[
3
]
.
D
ee
p
lear
n
i
n
g
(
DL
)
alg
o
r
ith
m
s
,
p
ar
ticu
lar
ly
th
e
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
lo
n
g
s
h
o
r
t
-
te
r
m
m
em
o
r
y
(
C
NN
-
L
STM
)
co
m
b
in
atio
n
,
h
a
v
e
also
d
em
o
n
s
tr
ated
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
94
5
-
1
95
3
1946
h
ig
h
ac
c
u
r
ac
y
in
th
is
c
o
n
tex
t [
4
]
.
T
h
e
u
s
e
o
f
e
n
s
em
b
le
m
o
d
e
ls
,
s
u
ch
as
r
an
d
o
m
f
o
r
est
(
R
F)
,
h
as
b
ee
n
f
o
u
n
d
to
f
u
r
th
er
im
p
r
o
v
e
p
r
e
d
ictio
n
ac
cu
r
ac
y
[
5
]
.
Ho
wev
er
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
ese
m
o
d
els
ca
n
v
ar
y
,
with
s
o
m
e
s
tu
d
ies
h
ig
h
lig
h
tin
g
th
e
e
f
f
ec
tiv
en
ess
o
f
m
o
d
els
lik
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM
)
,
ANN,
an
d
lo
g
is
tic
r
eg
r
ess
io
n
(
LR
)
[
6
]
.
Desp
ite
t
h
ese
v
ar
iatio
n
s
,
t
h
e
c
o
n
s
en
s
u
s
is
th
at
ML
tec
h
n
iq
u
es
h
o
ld
s
ig
n
if
ican
t
p
o
ten
tial
f
o
r
th
e
ac
cu
r
ate
class
if
icatio
n
o
f
DM
.
Ph
o
n
g
y
in
g
a
n
d
Hir
i
o
te
[
7
]
m
o
d
els
u
s
in
g
in
ter
ac
ti
o
n
ter
m
s
ac
h
iev
ed
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
th
an
m
o
d
els
with
o
u
t
in
ter
ac
tio
n
,
with
R
FC
ac
h
iev
in
g
th
e
b
est
r
esu
lts
.
Gan
g
u
ly
an
d
Sin
g
h
[
8
]
e
v
alu
a
ted
s
ix
ML
alg
o
r
ith
m
s
,
in
clu
d
in
g
LR
,
d
ec
is
io
n
tr
ee
(
DT
)
,
r
a
n
d
o
m
f
o
r
est
(
R
F)
,
k
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN)
,
S
VM
,
an
d
Naïv
e
B
ay
es
(
NB
)
,
u
s
in
g
th
e
Pima
I
n
d
ian
d
iab
ete
s
d
atab
ase
.
Dif
f
er
en
t
p
er
f
o
r
m
an
ce
m
etr
ics
-
co
n
f
u
s
io
n
m
atr
ix
,
ac
cu
r
ac
y
,
p
r
ec
is
io
n
an
d
F
-
m
ea
s
u
r
e,
wer
e
u
s
ed
f
o
r
ev
alu
atio
n
.
Yi
[
9
]
u
s
ed
ML
m
o
d
elin
g
a
n
d
class
if
icatio
n
f
o
r
d
iab
etes
d
iag
n
o
s
is
p
r
o
b
lem
s
.
T
h
e
ac
cu
r
ac
y
r
ates
o
f
th
e
KNN
m
o
d
el
an
d
th
e
RF
m
o
d
el
wer
e
f
o
u
n
d
to
b
e
7
6
%
an
d
8
0
%
r
esp
e
ctiv
ely
.
Mu
r
th
y
an
d
Srilath
a
[
1
0
]
co
m
p
ar
ed
th
e
p
er
f
o
r
m
an
ce
o
f
d
ec
is
io
n
t
r
ee
class
if
ier
(
DT
C
)
an
d
LR
al
g
o
r
ith
m
s
an
d
f
o
u
n
d
th
at
L
R
o
f
f
er
ed
h
ig
h
er
ac
cu
r
ac
y
in
p
r
ed
ictin
g
d
iab
etes.
I
s
m
ail
an
d
Ma
ter
wala
[
1
1
]
c
o
n
d
u
cte
d
a
liter
atu
r
e
r
ev
iew
an
d
p
r
o
p
o
s
ed
an
in
tellig
en
t
f
r
am
ewo
r
k
f
o
r
ap
p
ly
in
g
ML
to
p
r
ed
ict
d
iab
etes.
T
h
e
y
ev
al
u
ated
d
ec
is
io
n
tr
ee
em
p
lo
y
in
g
RF
s
an
d
SVMn
e
m
o
d
els f
o
r
d
iab
etes
p
r
ed
ictio
n
[
1
1
]
.
T
h
is
s
tu
d
y
d
elv
es in
to
th
e
ef
f
i
ca
cy
o
f
th
r
ee
ad
v
an
ce
d
e
n
s
em
b
le
ML
m
o
d
els
s
tack
in
g
,
s
o
f
t v
o
tin
g
,
an
d
h
ar
d
v
o
tin
g
.
I
n
d
iag
n
o
s
in
g
d
ia
b
etes
am
o
n
g
Pima
I
n
d
ia
n
wo
m
en
,
th
e
s
tu
d
y
u
tili
ze
s
a
d
atas
et
f
r
o
m
th
e
Natio
n
al
I
n
s
ti
tu
te
o
f
Diab
etes
an
d
Dig
esti
v
e
an
d
Kid
n
ey
Dis
ea
s
es.
T
h
is
u
n
iq
u
e
d
ataset
in
clu
d
es
d
iag
n
o
s
tic
m
ea
s
u
r
em
en
ts
f
r
o
m
Pima
I
n
d
ian
wo
m
e
n
ag
e
d
2
1
an
d
ab
o
v
e,
s
elec
ted
u
n
d
er
s
tr
in
g
en
t
c
r
iter
ia
to
g
u
ar
an
tee
th
e
r
elev
an
ce
a
n
d
ac
c
u
r
ac
y
o
f
th
e
r
esu
lts
.
T
h
e
r
esear
c
h
m
eth
o
d
o
lo
g
y
in
co
r
p
o
r
ates
ex
p
lo
r
ato
r
y
d
ata
a
n
aly
s
is
an
d
p
r
ep
r
o
ce
s
s
in
g
o
f
th
e
d
ataset,
f
o
llo
wed
b
y
th
e
ap
p
licatio
n
an
d
r
ig
o
r
o
u
s
e
v
alu
atio
n
o
f
th
e
e
n
s
em
b
le
m
o
d
els
o
n
th
e
cr
iter
ia
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
an
d
th
e
ar
ea
u
n
d
er
th
e
R
OC
cu
r
v
e.
No
tab
ly
,
o
u
r
r
esu
lts
in
d
icate
th
at
th
e
s
o
f
t
an
d
h
ar
d
v
o
tin
g
m
o
d
els
s
h
o
w
p
r
o
m
is
e
in
d
iab
etes
p
r
ed
ictio
n
.
Ho
wev
er
,
t
h
ese
o
u
tco
m
es
ar
e
in
f
lu
en
ce
d
b
y
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es,
th
e
s
elec
tio
n
o
f
b
ase
m
o
d
els,
an
d
h
y
p
er
p
ar
am
eter
s
ettin
g
s
,
h
ig
h
lig
h
tin
g
th
e
n
u
an
ce
d
n
atu
r
e
o
f
ML
ap
p
licatio
n
s
in
h
e
alth
ca
r
e
[
1
2
]
.
R
ec
en
t
ad
v
an
c
em
en
ts
in
th
e
f
ield
u
n
d
er
s
co
r
e
th
e
d
y
n
am
is
m
o
f
ML
in
d
iab
etes
r
esear
ch
.
Fo
r
in
s
tan
ce
,
[
1
3
]
,
[
1
4
]
h
a
v
e
f
u
r
t
h
er
r
ef
in
ed
e
n
s
em
b
le
lear
n
in
g
tech
n
iq
u
es,
d
e
m
o
n
s
tr
atin
g
im
p
r
o
v
ed
class
if
icatio
n
an
d
p
r
e
d
ictio
n
r
esu
lts
in
v
a
r
io
u
s
m
ed
ical
d
atasets
.
T
h
is
r
esear
ch
ar
ticle
co
n
tr
ib
u
t
es
b
y
d
ev
elo
p
i
n
g
a
n
d
d
em
o
n
s
tr
atin
g
an
en
h
an
ce
d
en
s
em
b
le
m
o
d
el
th
at
im
p
r
o
v
es
th
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
o
f
DM
class
if
icatio
n
.
Fo
r
ass
es
s
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
en
h
a
n
ce
d
m
o
d
el
th
e
f
o
llo
win
g
o
b
jectiv
es a
r
e
o
u
tlin
ed
as f
o
llo
ws:
a)
An
en
s
em
b
le
m
o
d
el
was
d
ev
el
o
p
ed
th
at
in
teg
r
ates
RF
,
L
R
,
NB
,
an
d
o
th
er
alg
o
r
ith
m
s
u
s
in
g
a
v
o
tin
g
a
n
d
s
tack
in
g
en
s
em
b
le
class
if
ier
.
T
h
is
m
o
d
el
is
d
esig
n
ed
to
ca
t
eg
o
r
ize
th
e
u
s
ed
d
ataset
in
to
t
wo
ca
teg
o
r
ies
p
o
s
itiv
e
o
r
n
e
g
ativ
e.
b)
Pre
cisi
o
n
,
r
ec
all,
F1
-
s
co
r
e,
a
cc
u
r
ac
y
,
an
d
th
e
ar
ea
AUC
as
o
u
r
p
r
im
ar
y
m
etr
ics
to
ev
alu
ate
th
e
ef
f
ec
tiv
en
ess
o
f
o
u
r
p
r
o
p
o
s
ed
m
o
d
el.
c)
T
h
e
p
r
o
p
o
s
ed
en
s
em
b
le
m
o
d
el
’
s
o
u
tco
m
es
e
x
h
ib
it
en
h
a
n
c
ed
p
e
r
f
o
r
m
an
ce
w
h
en
b
en
c
h
m
ar
k
ed
ag
ain
s
t
ex
is
tin
g
m
eth
o
d
s
wh
ile
m
ain
ta
in
in
g
th
e
d
ef
in
ed
p
ar
am
eter
s
.
d)
T
h
e
ass
ess
m
en
t
o
f
o
u
r
ap
p
r
o
ac
h
in
clu
d
es
a
r
ig
o
r
o
u
s
c
o
m
p
ar
is
o
n
with
s
tan
d
a
r
d
b
ase
class
if
ier
s
,
in
clu
d
in
g
LR
,
RF
,
NB
,
Gr
ad
ien
tB
o
o
s
t,
XGBo
o
s
t,
Ad
aBo
o
s
t,
an
d
C
atB
o
o
s
t,
d
em
o
n
s
tr
atin
g
th
e
r
o
b
u
s
tn
ess
o
f
o
u
r
p
r
o
p
o
s
ed
m
e
th
o
d
o
lo
g
y
.
2.
RE
L
AT
E
D
WO
RK
T
h
e
p
r
o
g
r
ess
io
n
o
f
m
ac
h
in
e
-
lear
n
in
g
tech
n
iq
u
es
h
as
s
ig
n
if
ican
tly
in
f
lu
en
ce
d
th
e
m
e
d
ica
l
f
ield
o
f
d
iag
n
o
s
tics
,
I
n
t
h
e
d
etec
tio
n
a
n
d
class
if
icatio
n
o
f
DM
.
I
n
s
tu
d
ies,
v
ar
io
u
s
ML
m
o
d
els
h
a
v
e
b
ee
n
r
ig
o
r
o
u
s
ly
test
ed
an
d
ev
alu
ated
f
o
r
t
h
eir
ef
f
icac
y
in
d
iag
n
o
s
in
g
d
iab
ete
s
with
p
r
o
m
is
in
g
r
esu
lts
.
Hir
io
te
co
n
d
u
cted
an
i
n
-
d
ep
th
an
aly
s
is
o
f
RF
,
SVM
,
DT
,
an
d
KNN
,
lev
er
ag
in
g
h
y
p
er
p
ar
am
eter
tu
n
in
g
an
d
in
ter
ac
tio
n
ter
m
s
t
o
en
h
an
ce
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
T
h
e
s
tu
d
y
f
o
u
n
d
th
at
RF
s
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
,
o
u
tp
e
r
f
o
r
m
in
g
th
e
o
th
er
m
o
d
els
with
a
r
em
ar
k
a
b
le
9
7
.
5
%
ac
cu
r
ac
y
r
ate
[
7
]
.
V
id
y
a
et
a
l.
[
1
5
]
p
r
esen
ted
alg
o
r
ith
m
s
f
o
r
d
is
ea
s
e
d
iag
n
o
s
is
,
h
ig
h
lig
h
tin
g
t
h
at
RF
an
d
d
ee
p
n
eu
r
al
n
etwo
r
k
s
co
u
ld
f
u
r
th
e
r
i
n
cr
ea
s
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
Hass
an
et
a
l.
[
1
6
]
in
v
esti
g
ated
ea
r
ly
p
r
e
d
ictiv
e
an
aly
tics
u
s
in
g
LR
,
SVM
ac
h
iev
in
g
u
p
to
9
7
.
5
%
ac
cu
r
ac
y
with
th
e
latter
.
B
h
u
iy
a
n
et
a
l.
[
1
7
]
p
r
esen
ted
a
p
r
e
-
p
r
o
ce
s
s
in
g
m
eth
o
d
f
o
r
m
e
d
ical
d
ata,
r
esu
ltin
g
in
a
9
2
.
2
7
%
class
if
icatio
n
ac
cu
r
ac
y
wh
en
ap
p
lied
wi
th
th
e
NB
alg
o
r
ith
m
.
I
s
m
ail
an
d
Ma
ter
wala
[
1
1
]
in
tr
o
d
u
ce
d
t
h
e
I
DM
PF
,
an
in
tellig
en
t
f
r
am
ewo
r
k
,
u
tili
zin
g
tr
ee
-
b
ased
SVM
m
o
d
els,
em
p
h
asizin
g
th
e
in
teg
r
atio
n
o
f
in
tellig
en
t
s
y
s
tem
s
f
o
r
d
iab
et
es
p
r
ed
ictio
n
.
Yi
[
9
]
d
e
m
o
n
s
tr
ated
th
e
s
u
p
er
io
r
p
r
e
d
ictiv
e
ab
ilit
y
o
f
LR
in
class
if
y
in
g
d
iab
etes
r
is
k
.
Dee
p
ak
et
a
l.
[
1
8
]
d
e
v
elo
p
e
d
a
s
y
s
t
em
u
s
in
g
a
n
im
p
r
o
v
e
d
class
if
icatio
n
tech
n
iq
u
e
to
p
r
ed
ict
d
iab
etic
r
is
k
lev
els with
h
i
g
h
er
ac
c
u
r
ac
y
.
So
n
i
[
1
9
]
e
m
p
lo
y
ed
e
n
s
em
b
le
ML
with
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A
)
an
d
K
-
m
ea
n
s
clu
s
ter
in
g
,
r
esu
ltin
g
in
an
en
s
em
b
le
m
o
d
el
th
at
o
u
tp
er
f
o
r
m
ed
b
ase
class
if
ier
m
o
d
els
.
Satu
et
a
l.
[
2
0
]
s
u
g
g
e
s
t
a
n
o
v
el
h
y
b
r
id
ML
m
o
d
el
i
n
co
r
p
o
r
atin
g
s
y
n
th
etic
m
in
o
r
ity
o
v
er
s
am
p
lin
g
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
yn
erg
is
tic
en
s
emb
le
cla
s
s
ific
a
tio
n
fr
a
mewo
r
k:
u
tili
z
in
g
a
s
o
ft v
o
tin
g
a
l
g
o
r
ith
m
…
(
B
h
a
n
u
P
r
a
ka
s
h
Lo
h
a
n
i
)
1947
s
im
p
le
K
-
m
ea
n
s
clu
s
ter
in
g
,
with
RF
s
h
o
win
g
t
h
e
b
est
ac
cu
r
ac
y
at
9
9
.
0
6
7
%
.
Ma
lv
iy
a
et
a
l.
[
2
1
]
ev
alu
ated
s
ev
er
al
ML
an
d
DL
m
o
d
els
f
o
r
th
ei
r
ca
p
a
b
ilit
y
to
p
r
ed
ict
d
iab
etic
r
is
k
le
v
els,
ad
v
o
ca
t
in
g
f
o
r
th
e
u
s
e
o
f
d
iv
er
s
e
alg
o
r
ith
m
s
f
o
r
en
h
a
n
c
ed
class
if
icatio
n
ac
cu
r
ac
y
.
R
ed
d
y
et
a
l.
[
2
2
]
ap
p
lied
RF
an
d
KNN
alg
o
r
ith
m
s
to
d
etec
t
d
iab
etes,
u
tili
zin
g
th
e
P
I
MA
d
ata
s
et
f
o
r
th
eir
an
aly
s
is
wo
r
k
.
Similar
ly
,
Das
et
a
l.
[
2
3
]
ex
p
lo
r
ed
v
a
r
io
u
s
class
if
ier
s
,
wh
ich
in
clu
d
e
DT
C
,
KNN
alg
o
r
ith
m
,
LR
,
an
d
NB
,
id
en
tify
in
g
p
r
o
g
n
o
s
tic
b
io
m
ar
k
er
s
f
o
r
d
iab
etes
p
r
ed
ictio
n
a
n
d
ac
h
iev
ed
a
n
ac
cu
r
ac
y
o
f
9
8
.
0
8
%
wh
ic
h
is
v
e
r
y
im
p
r
ess
iv
e
.
Ud
d
in
et
a
l.
[
2
4
]
ev
alu
ate
d
m
o
d
el
p
er
f
o
r
m
an
ce
ac
r
o
s
s
two
d
atasets
,
d
eter
m
in
in
g
th
at
th
e
b
est
r
esu
lt
was
p
r
o
v
id
ed
b
y
t
h
e
RF
class
if
ier
,
with
an
ac
cu
r
ac
y
o
f
9
7
%
o
n
th
e
2
0
1
9
d
ataset
.
Ab
d
o
llah
i
an
d
Ar
ef
[
2
5
]
im
p
lem
e
n
ted
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
f
o
r
f
ea
tu
r
e
s
elec
tio
n
,
f
o
llo
wed
b
y
a
co
m
p
ar
is
o
n
o
f
p
er
f
o
r
m
an
ce
m
etr
ics
.
T
h
e
ab
o
v
e
r
esear
ch
p
ap
e
r
s
wer
e
s
tu
d
ied
b
ef
o
r
e
g
o
in
g
t
o
war
d
s
th
e
s
u
cc
ess
f
u
l im
p
lem
en
t
atio
n
o
f
th
is
r
esear
ch
wo
r
k
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
I
n
th
is
p
ap
e
r
,
th
e
o
b
jectiv
e
is
to
m
eticu
lo
u
s
ly
co
n
s
tr
u
ct
a
n
d
ass
ess
th
r
ee
d
is
tin
ct
en
s
em
b
le
m
o
d
els
n
am
ely
th
e
s
tack
in
g
m
o
d
el,
t
h
e
s
o
f
t
v
o
tin
g
m
o
d
el,
a
n
d
t
h
e
h
ar
d
v
o
tin
g
m
o
d
el
.
A
d
etai
led
m
eth
o
d
o
lo
g
y
is
s
h
o
wn
in
Fig
u
r
e
1
.
W
e
h
av
e
p
r
esen
ted
th
e
s
tep
s
o
f
p
r
ep
r
o
ce
s
s
in
g
in
s
ec
tio
n
s
3
.
1
an
d
3
.
2
.
af
ter
th
e
p
r
ep
r
o
ce
s
s
in
g
an
d
E
DA
s
tep
s
,
Fig
u
r
e
s
2
a
n
d
3
r
ep
r
esen
t
th
e
d
ata
d
is
tr
ib
u
tio
n
a
n
d
co
r
r
elati
o
n
.
T
h
e
alg
o
r
ith
m
ic
s
tep
s
ar
e
d
ef
in
e
d
in
Alg
o
r
ith
m
1
wh
ich
is
f
o
r
p
r
o
ce
d
u
r
e
f
o
r
ea
r
ly
d
iab
etes
p
r
e
d
ictio
n
u
s
in
g
an
en
s
em
b
le
ap
p
r
o
ac
h
.
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
:
f
l
o
w
ch
ar
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
94
5
-
1
95
3
1948
3
.
1
.
Descript
io
n o
f
t
he
da
t
a
s
et
T
h
e
d
a
t
a
s
e
t
f
o
r
t
h
e
d
i
a
g
n
o
s
i
s
o
f
d
i
a
b
e
t
es
is
ta
k
e
n
f
r
o
m
t
h
e
N
at
i
o
n
a
l
I
n
s
t
i
t
u
t
e
o
f
Di
a
b
e
t
es
a
n
d
D
i
g
es
t
i
v
e
a
n
d
K
i
d
n
e
y
D
is
e
as
es
.
I
t
e
n
c
o
m
p
a
s
s
es
a
s
el
e
c
ti
o
n
o
f
d
i
a
g
n
o
s
t
i
c
m
e
as
u
r
e
m
e
n
t
s
o
f
f
e
m
a
l
e
p
a
t
i
e
n
ts
o
f
t
h
e
P
i
m
a
I
n
d
i
a
n
d
a
t
a
s
e
t
a
g
e
d
2
1
y
e
a
r
s
o
r
o
l
d
e
r
.
T
h
i
s
d
a
t
a
s
e
t
i
n
cl
u
d
e
s
8
f
e
a
t
u
r
e
s
a
n
d
o
n
e
o
u
t
c
o
m
e
.
O
u
t
o
f
7
6
8
i
n
d
i
v
i
d
u
a
l
s
i
n
t
h
e
d
a
t
a
s
e
t
,
2
6
8
a
r
e
m
a
r
k
e
d
w
i
t
h
t
h
e
o
u
t
c
o
m
e
‘
1
’
,
d
e
n
o
t
i
n
g
a
d
i
a
b
e
t
e
s
d
i
a
g
n
o
s
is
,
w
h
i
l
e
t
h
e
r
e
s
t
a
r
e
l
a
b
e
l
e
d
as
‘
0
’
,
i
n
d
i
c
a
t
i
n
g
n
o
d
ia
b
e
t
es
.
T
h
is
is
a
v
a
l
u
a
b
l
e
d
a
t
a
s
e
t
t
h
a
t
is
a
r
e
s
o
u
r
c
e
f
o
r
c
o
n
s
t
r
u
c
ti
n
g
p
r
ed
i
c
t
i
v
e
m
o
d
e
ls
a
n
d
a
p
p
l
y
i
n
g
M
L
t
e
c
h
n
i
q
u
e
s
t
o
i
d
en
t
i
f
y
p
a
t
t
e
r
n
s
a
n
d
f
a
c
t
o
r
s
s
i
g
n
i
f
i
c
a
n
t
i
n
t
h
e
d
ia
g
n
o
s
is
o
f
d
i
a
b
e
te
s
.
3
.
2
.
Da
t
a
prepro
ce
s
s
ing
s
t
ep
T
h
e
d
ataset
u
n
d
er
we
n
t
a
th
o
r
o
u
g
h
p
r
e
-
p
r
o
ce
s
s
in
g
r
eg
i
m
en
to
en
s
u
r
e
d
ata
q
u
ality
f
o
r
th
e
s
u
b
s
eq
u
en
t
an
aly
s
is
.
I
n
itially
,
th
e
ab
s
en
ce
o
f
m
is
s
in
g
v
alu
es
was
ch
ec
k
e
d
an
d
c
o
n
f
ir
m
ed
th
at
all
f
ea
t
u
r
es
wer
e
n
u
m
er
ical,
n
eg
atin
g
th
e
n
ee
d
f
o
r
im
p
u
tat
io
n
o
r
ty
p
e
co
n
v
er
s
io
n
.
T
h
e
b
alan
ce
o
f
o
u
r
tar
g
et
v
ar
iab
le
an
d
f
o
u
n
d
it
to
b
e
ev
en
ly
d
is
tr
ib
u
ted
,
elim
in
atin
g
co
n
ce
r
n
s
o
v
er
tar
g
et
im
b
al
an
ce
.
Ob
s
er
v
i
n
g
s
ig
n
if
ican
t
p
r
o
p
o
r
ti
o
n
s
o
f
ze
r
o
v
alu
es
in
th
e
s
o
m
e
f
ea
tu
r
es,
th
ese
ze
r
o
es
wer
e
s
u
b
s
titu
t
ed
with
th
e
r
esp
ec
tiv
e
f
ea
tu
r
e
m
ea
n
s
to
av
o
id
d
is
to
r
tio
n
in
th
e
d
ata
d
is
tr
ib
u
ti
o
n
.
T
h
is
s
u
b
s
titu
tio
n
,
alo
n
g
w
ith
lin
ea
r
an
d
s
tan
d
ar
d
s
ca
lin
g
,
h
elp
ed
n
o
r
m
alize
th
e
d
is
tr
ib
u
tio
n
.
Ho
wev
er
,
d
u
e
to
th
e
p
er
s
is
ten
ce
o
f
s
k
ewe
d
d
is
tr
ib
u
tio
n
s
in
s
o
m
e
f
ea
tu
r
e
s
,
n
o
n
lin
ea
r
s
ca
lin
g
u
s
in
g
th
e
q
u
an
tiletra
n
s
f
o
r
m
er
to
ap
p
r
o
x
im
ate
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
was
em
p
lo
y
e
d
.
Fu
r
t
h
er
,
we
id
e
n
tifie
d
a
n
o
tab
le
co
r
r
elatio
n
b
etwe
en
‘
Ou
tco
m
e
’
an
d
‘
Glu
c
o
s
e
’
,
in
d
icatin
g
‘
Glu
co
s
e
’
as
a
p
o
ten
tial
k
ey
p
r
ed
icto
r
.
‘
B
MI
’
,
‘
Pre
g
n
an
cies
’
,
an
d
‘
Ag
e
’
also
em
er
g
ed
as
im
p
o
r
tan
t
f
ea
tu
r
es.
A
h
ig
h
co
r
r
ela
tio
n
was
o
b
s
er
v
ed
b
etwe
en
‘
Sk
in
T
h
ick
n
ess
’
an
d
‘
B
MI
’
,
h
in
tin
g
at
p
o
s
s
ib
le
m
u
ltico
llin
ea
r
ity
,
wh
ich
we
p
lan
to
in
v
esti
g
ate
f
u
r
th
er
if
m
o
d
el
p
er
f
o
r
m
an
ce
is
im
p
ac
ted
.
Fig
u
r
es
2
an
d
3
s
h
o
ws
th
e
d
is
tr
ib
u
tio
n
an
d
co
r
r
elatio
n
o
f
d
if
f
er
e
n
t
p
ar
am
eter
s
.
Fig
u
r
e
2
.
Dis
tr
ib
u
tio
n
o
f
d
if
f
er
en
t p
ar
am
eter
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
yn
erg
is
tic
en
s
emb
le
cla
s
s
ific
a
tio
n
fr
a
mewo
r
k:
u
tili
z
in
g
a
s
o
ft v
o
tin
g
a
l
g
o
r
ith
m
…
(
B
h
a
n
u
P
r
a
ka
s
h
Lo
h
a
n
i
)
1949
Fig
u
r
e
3
.
C
o
r
r
elatio
n
o
f
d
if
f
e
r
en
t p
ar
am
eter
s
Alg
o
r
ith
m
1
.
Diab
etes
p
r
ed
icti
o
n
u
s
in
g
e
n
s
em
b
le
ap
p
r
o
ac
h
Input: A PIMA data set containing X features (x
1
to x
8
) and one target variable, y.
Output: Prediction of whether the patient is diabetic or nondiabetic.
Steps:
1.
Data Preprocessing
•
Collect the data set and load the CSV file.
•
Data Cleaning
2.
Feature Extraction and Correlation analysis
•
Correlation analysis using Pearson
correlation analysis (Heatmap)
•
Select the higher correlated feature
3.
Data Splitting
•
Split the data set (Criteria 80:20 train test ratio)
4.
Model Evaluation and Training
•
Model Evaluation done for ML classifier
LR, XGBOOST, RF, Schocastic Gradient
Descend, Adaboost, Gboost, KNN, and SVM
•
Calculate prediction and find the performance matrices
•
Calculate the metrics as follows:
•
-
Accuracy = (correct predictions / total predictions) * 100
•
-
Precision = (true positives/(true positives + false positives))
•
-
Recall = (true positives / (true positives + false negatives))
•
-
F1
-
score = 2 * ((Precision * Recall) / (Precision + Recall))
5.
Voting Classifier
Assign a weight to each classifier. These weights often represent confidence in the model
’
s
predictions, which can be determined by (P
v
)
•
Accuracy on a validation dataset.
•
Cross
-
validation scores.
•
Domain
-
specific knowledge or heuristics.
6.
Stacking
•
New training and Stacking done S= [Prediction of [
LR, XGBOOST, RF,
Schocastic Gradient
Descend, Adaboost, Gboost, KNN, and SVM]
•
Training of Meta learner M on S ( Where M =meta learner and S represents
stacking of classifiers)
7.
Final Prediction & Evaluation
•
Select the best model in the criteria of performance (Voting or Stacking)
•
Final Prediction & Evaluation done.
4.
M
O
DE
L
ARCH
I
T
E
CT
URE
W
e
h
av
e
s
p
lit
th
e
d
ataset
in
a
r
atio
o
f
8
0
:2
0
f
o
r
tr
ain
in
g
an
d
test
in
g
.
I
n
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
o
lo
g
y
s
ev
en
s
tan
d
alo
n
e
m
o
d
els
n
am
ely
LR
,
XGBOOST,
RF
,
s
ch
o
ca
s
tic
g
r
ad
ien
t d
esce
n
d
,
Ad
ab
o
o
s
t,
Gb
o
o
s
t,
KNN,
an
d
SVM
wer
e
tr
ai
n
ed
o
n
t
h
e
d
ataset.
A
v
o
tin
g
class
if
ier
s
er
v
es
as
an
e
n
s
em
b
le
m
eth
o
d
th
at
ag
g
r
e
g
ates
th
e
p
r
ed
ictio
n
s
f
r
o
m
v
ar
io
u
s
m
o
d
els
to
m
ak
e
a
f
i
n
al
p
r
e
d
ictio
n
f
o
r
n
ew
d
ata.
I
n
th
is
ap
p
r
o
ac
h
,
a
weig
h
ted
v
o
tin
g
class
if
ier
wh
er
e
ea
ch
co
n
s
titu
en
t
m
o
d
el
is
ass
ig
n
ed
a
weig
h
t
p
r
o
p
o
r
tio
n
al
to
its
ac
cu
r
ac
y
was
u
s
ed
to
m
ak
e
f
in
al
p
r
ed
ictio
n
s
.
C
o
n
s
eq
u
en
tl
y
,
th
e
m
o
d
el
ex
h
ib
itin
g
th
e
h
i
g
h
est
in
d
iv
id
u
al
ac
cu
r
ac
y
will
r
ec
eiv
e
th
e
m
o
s
t
s
ig
n
if
ican
t
weig
h
t,
th
e
r
eb
y
h
a
v
in
g
th
e
m
o
s
t
in
f
l
u
en
ce
o
n
th
e
f
in
al
p
r
ed
ictio
n
.
Fig
u
r
e
4
s
h
o
ws
th
e
p
er
f
o
r
m
an
c
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
94
5
-
1
95
3
1950
m
etr
ics
f
o
r
th
e
d
if
f
er
en
t
ML
m
o
d
els
an
d
th
e
en
s
em
b
le
v
o
ti
n
g
class
if
ier
in
ter
m
s
o
f
a
cc
u
r
ac
y
,
AUC,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
.
T
h
e
v
o
tin
g
class
if
ier
ac
h
ie
v
ed
an
ac
cu
r
ac
y
o
f
7
6
.
1
7
%.
Stack
in
g
is
a
n
en
s
em
b
le
tech
n
iq
u
e
th
at
lev
er
a
g
es
a
m
eta
-
lear
n
er
to
co
m
b
i
n
e
m
u
ltip
l
e
p
r
im
ar
y
m
o
d
els,
o
f
ten
o
f
v
a
r
io
u
s
ty
p
es,
u
n
lik
e
m
o
r
e
h
o
m
o
g
en
eo
u
s
m
eth
o
d
s
lik
e
b
ag
g
i
n
g
a
n
d
b
o
o
s
tin
g
.
T
h
is
ap
p
r
o
ac
h
in
v
o
lv
es
tr
ain
i
n
g
f
ir
s
t
-
lev
el
m
o
d
els,
also
k
n
o
wn
as
L
e
v
el
0
class
if
ier
s
,
o
n
th
e
d
ata
an
d
th
e
n
u
s
in
g
th
eir
d
etec
tio
n
as
in
p
u
t
f
ea
tu
r
es
f
o
r
a
s
ec
o
n
d
-
lev
el
m
o
d
el,
th
e
L
e
v
el
1
cla
s
s
if
ier
.
I
n
th
is
ap
p
r
o
ac
h
,
KNN
was
ch
o
s
en
as
th
e
m
eta
-
class
if
ier
b
ased
o
n
ac
cu
r
ac
y
.
T
h
e
L
e
v
el
1
class
if
ier
’
s
r
o
le
is
to
d
is
ce
r
n
th
e
o
p
tim
al
way
to
s
y
n
th
esize
th
e
L
ev
el
0
class
if
ier
s
’
o
u
tp
u
ts
to
m
ak
e
f
in
al
p
r
ed
ic
tio
n
s
.
A
cr
o
s
s
-
v
alid
atio
n
(
1
0
-
f
o
ld
)
was
u
s
ed
to
ac
h
iev
e
t
h
e
f
in
al
ac
cu
r
ac
y
.
T
h
e
s
tack
in
g
en
s
em
b
le
a
p
p
r
o
a
ch
g
av
e
a
n
ac
cu
r
ac
y
o
f
7
4
.
8
6
%.
5.
RE
SU
L
T
ANAL
YSI
S AN
D
I
NT
E
RP
R
E
T
A
T
I
O
N
Fig
u
r
e
4
s
h
o
wca
s
es
a
r
esp
ec
tiv
e
p
er
f
o
r
m
a
n
ce
an
al
y
s
is
o
f
ML
m
o
d
els
ev
al
u
ated
o
n
s
ev
er
al
m
etr
ics
p
er
tin
en
t
to
class
if
icatio
n
task
s
.
Fro
m
th
e
F
ig
u
r
e
4
,
it
was
o
b
s
er
v
ed
th
at
b
o
th
th
e
v
o
tin
g
c
lass
if
ier
an
d
lin
ea
r
d
is
cr
im
in
an
t
an
aly
s
is
(
L
DA)
ex
h
ib
it
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
7
6
.
1
7
%,
with
th
e
v
o
tin
g
cl
ass
if
ier
ac
h
iev
in
g
a
m
ar
g
in
ally
s
u
p
er
i
o
r
AUC
o
f
8
4
.
5
7
%
co
m
p
ar
ed
to
L
DA
’
s
8
4
.
2
1
%.
T
h
is
s
u
g
g
ests
th
at
w
h
ile
b
o
th
m
o
d
els
ar
e
clo
s
ely
m
atch
ed
in
ter
m
s
o
f
o
v
er
all
ac
cu
r
ac
y
,
th
e
v
o
tin
g
class
if
ier
m
ay
p
o
s
s
es
s
an
im
p
r
o
v
e
d
tr
ad
e
-
o
f
f
b
etwe
en
tr
u
e
+v
e
r
ate
an
d
f
alse +
v
e
r
ate
(
+
v
e
p
o
s
itiv
e)
.
Fig
u
r
e
4
.
ML
a
l
g
o
r
ith
m
s
:
p
e
r
f
o
r
m
an
ce
a
n
aly
s
is
I
n
ter
m
s
o
f
s
p
ee
d
,
L
DA
is
th
e
f
astes
t
m
o
d
el
with
a
tr
ain
in
g
tim
e
o
f
o
n
ly
0
.
0
3
s
ec
o
n
d
s
,
an
o
r
d
er
o
f
m
ag
n
itu
d
e
q
u
ic
k
er
t
h
an
th
e
LR
m
o
d
el,
w
h
ich
,
d
esp
ite
its
c
o
m
p
ar
ab
le
ac
cu
r
a
cy
a
n
d
AUC,
is
th
e
s
lo
west
at
1
.
1
3
1
s
ec
o
n
d
s
.
T
h
e
ad
a
b
o
o
s
t,
g
r
ad
ien
t
b
o
o
st
(
GB
c
lass
if
ier
)
,
an
d
RF
class
if
ier
s
h
o
w
a
b
alan
ce
d
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
all
m
etr
ics,
with
r
elativ
ely
h
i
g
h
ac
cu
r
ac
y
,
AUC,
a
n
d
F1
-
s
co
r
e
s
,
s
h
o
win
g
a
g
o
o
d
b
alan
ce
b
etwe
en
r
ec
all
an
d
p
r
ec
is
io
n
.
I
t
is
n
o
t
ab
le
th
at
th
e
C
atB
o
o
s
t
c
lass
if
ier
,
wh
ile
n
o
t
t
h
e
to
p
p
er
f
o
r
m
er
in
ac
c
u
r
ac
y
o
r
AUC,
r
eq
u
ir
es
th
e
lo
n
g
est
tr
ain
in
g
tim
e
at
o
v
e
r
2
s
ec
o
n
d
s
.
T
h
is
m
ig
h
t
b
e
a
co
n
s
id
er
atio
n
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
wh
er
e
m
o
d
el
in
f
er
en
ce
s
p
ee
d
is
cr
itical.
T
h
e
g
r
ad
ien
t
b
o
o
s
tin
g
class
if
ier
(
GB
C
)
an
d
lig
h
t
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
in
e
(
L
GB
M)
p
r
esen
t
h
ig
h
F1
-
s
co
r
e
s
an
d
AUC,
wh
ich
s
ig
n
if
ies
a
s
tr
o
n
g
ab
ilit
y
t
o
h
an
d
le
b
o
th
class
es
ef
f
ec
tiv
ely
,
d
esp
ite
a
s
lig
h
t
tr
ad
e
-
o
f
f
in
ter
m
s
o
f
tr
ain
in
g
tim
e
f
o
r
L
GB
M.
NB
,
d
esp
ite
it
s
s
im
p
licity
,
s
h
o
ws
co
m
m
e
n
d
ab
le
p
er
f
o
r
m
an
ce
,
esp
ec
ially
c
o
n
s
id
er
in
g
its
v
er
y
s
h
o
r
t
tr
ain
i
n
g
tim
e,
wh
ich
co
u
ld
m
ak
e
it
an
attr
ac
tiv
e
o
p
tio
n
f
o
r
v
e
r
y
lar
g
e
d
atasets
o
r
in
i
tial
b
aselin
e
m
o
d
elin
g
.
Fig
u
r
es
5
an
d
6
p
r
esen
t
co
n
f
u
s
io
n
m
atr
ices
f
o
r
th
e
s
tack
in
g
class
if
ier
an
d
th
e
v
o
tin
g
class
if
ier
.
Fig
u
r
e
7
r
ep
r
esen
ts
th
e
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
e
c
o
m
p
ar
is
o
n
f
o
r
v
a
r
i
o
u
s
ML
m
o
d
els.
T
h
e
R
OC
cu
r
v
e
is
a
g
r
ap
h
ical
r
ep
r
esen
tatio
n
th
at
s
h
o
ws h
o
w
well
a
b
in
ar
y
class
if
ier
p
er
f
o
r
m
s
as its
d
ec
is
io
n
th
r
esh
o
ld
ch
an
g
es.
Per
f
ec
t
p
r
ed
ictio
n
is
r
ep
r
esen
ted
b
y
a
n
AUC
o
f
1
.
0
,
wh
ile
a
0
.
5
v
al
u
e
o
f
AUC
s
u
g
g
ests
n
o
d
is
cr
im
in
ativ
e
p
o
wer
,
eq
u
i
v
alen
t
to
r
an
d
o
m
g
u
ess
in
g
.
T
h
e
RF
an
d
ex
tr
a
tr
ee
s
m
o
d
els
ex
h
ib
it
ex
ce
p
tio
n
al
p
er
f
o
r
m
an
ce
with
AUCs
o
f
0
.
9
8
,
in
d
icatin
g
th
ey
ar
e
ex
c
ellen
t
at
d
is
tin
g
u
is
h
in
g
b
etwe
en
th
e
two
class
e
s
.
XGBo
o
s
t
also
o
u
tp
er
f
o
r
m
s
with
an
AUC
o
f
0
.
9
7
.
T
h
e
v
o
t
in
g
class
if
ier
,
en
s
em
b
le
,
an
d
GB
C
s
h
o
w
s
tr
o
n
g
p
er
f
o
r
m
an
ce
with
AUCs
o
f
0
.
9
5
.
T
h
e
s
tack
in
g
class
if
ier
an
d
th
e
d
ec
is
io
n
tr
ee
d
is
p
lay
r
o
b
u
s
t
d
is
cr
im
in
atio
n
ab
ilit
ies
with
AUC
s
o
f
0
.
9
3
a
n
d
0
.
9
4
,
r
esp
ec
tiv
ely
.
Ov
er
all
,
th
e
g
r
ap
h
in
d
icate
s
th
at
en
s
e
m
b
le
m
eth
o
d
s
an
d
tr
ee
-
b
ased
m
o
d
els
ten
d
to
o
u
t
p
er
f
o
r
m
s
im
p
ler
m
o
d
els
in
te
r
m
s
o
f
R
OC
AUC,
s
u
g
g
esti
n
g
th
at
th
ey
m
ay
b
e
m
o
r
e
s
u
itab
le
f
o
r
th
is
p
ar
ticu
lar
class
if
icatio
n
ta
s
k
.
Fig
u
r
es
8
an
d
9
s
h
o
w
th
e
th
r
esh
o
ld
p
lo
t
f
o
r
v
o
tin
g
an
d
s
tack
in
g
class
if
ier
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
yn
erg
is
tic
en
s
emb
le
cla
s
s
ific
a
tio
n
fr
a
mewo
r
k:
u
tili
z
in
g
a
s
o
ft v
o
tin
g
a
l
g
o
r
ith
m
…
(
B
h
a
n
u
P
r
a
ka
s
h
Lo
h
a
n
i
)
1951
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
s
tack
in
g
Fig
u
r
e
6
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
v
o
tin
g
class
if
ier
Fig
u
r
e
7
.
R
OC
cu
r
v
e
f
o
r
v
a
r
io
u
s
ML
m
o
d
els
Fig
u
r
e
8
.
T
h
r
esh
o
ld
p
lo
t f
o
r
s
tack
in
g
class
if
ier
Fig
u
r
e
9
.
T
h
r
esh
o
ld
p
lo
t f
o
r
v
o
tin
g
class
if
ier
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
94
5
-
1
95
3
1952
6.
CO
NCLU
SI
O
N
T
h
is
r
esear
ch
wo
r
k
s
h
o
wca
s
ed
th
e
p
o
wer
f
u
l
ef
f
ec
tiv
e
n
ess
o
f
en
s
em
b
le
ML
m
eth
o
d
s
in
th
e
ea
r
ly
d
etec
tio
n
an
d
d
iag
n
o
s
is
f
o
r
DM
,
s
p
ec
if
ically
with
in
t
h
e
Pima
I
n
d
ian
f
em
ale
p
o
p
u
lati
o
n
.
O
u
r
m
eticu
lo
u
s
ev
alu
atio
n
o
f
s
ev
er
al
en
s
em
b
l
e
m
o
d
els,
in
clu
d
in
g
s
tack
in
g
an
d
v
o
tin
g
,
o
n
a
r
ich
d
ataset
f
r
o
m
th
e
Natio
n
al
I
n
s
titu
te
o
f
Diab
etes
a
n
d
Dig
e
s
tiv
e
an
d
Kid
n
ey
Dis
ea
s
es,
h
a
s
y
ield
ed
s
ig
n
if
ica
n
t
in
s
ig
h
ts
.
Am
o
n
g
t
h
e
m
o
d
els
ass
es
s
ed
,
th
e
v
o
tin
g
class
if
ier
,
wh
ich
co
m
b
in
es
p
r
o
b
a
b
ilit
y
e
s
tim
ates
f
r
o
m
v
ar
io
u
s
alg
o
r
ith
m
s
,
em
er
g
ed
as
th
e
s
u
p
er
io
r
m
o
d
el
i
n
ter
m
s
o
f
R
OC
AUC,
h
ig
h
lig
h
tin
g
its
r
o
b
u
s
tn
ess
in
p
r
ed
ictin
g
d
ia
b
etes.
Ad
d
itio
n
ally
,
t
h
e
r
esu
lts
ad
v
o
ca
te
f
o
r
th
e
im
p
o
r
tan
ce
o
f
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
as
it
f
o
r
m
s
th
e
f
o
u
n
d
atio
n
f
o
r
t
h
e
s
u
cc
ess
f
u
l
ap
p
licatio
n
o
f
co
m
p
lex
m
o
d
els.
Alth
o
u
g
h
th
is
r
esear
ch
wo
r
k
h
as m
ad
e
s
ig
n
if
ican
t c
o
n
tr
ib
u
tio
n
s
to
th
e
f
ield
o
f
m
ed
ical
d
iag
n
o
s
tics
,
f
u
r
th
er
r
esear
ch
is
war
r
an
ted
.
I
n
v
esti
g
atin
g
th
e
s
ca
lab
ilit
y
o
f
th
e
m
o
d
els
in
lar
g
er
a
n
d
m
o
r
e
d
iv
e
r
s
e
p
o
p
u
latio
n
s
,
as
well
as
ex
p
lo
r
in
g
th
e
in
teg
r
atio
n
o
f
a
d
d
itio
n
al
p
r
e
d
ictiv
e
v
ar
iab
les,
co
u
ld
en
h
an
ce
th
e
m
o
d
els
’
d
ia
g
n
o
s
t
ic
ac
cu
r
ac
y
.
Mo
r
eo
v
e
r
,
an
al
y
zin
g
th
e
im
p
lem
e
n
tatio
n
o
f
th
ese
m
o
d
els
in
r
ea
l
-
wo
r
ld
clin
ical
e
n
v
ir
o
n
m
en
ts
c
o
u
ld
o
f
f
er
p
r
ac
tical
i
n
s
ig
h
ts
in
to
th
eir
u
tili
ty
an
d
im
p
ac
t o
n
h
ea
lth
ca
r
e
o
u
tc
o
m
es
f
o
r
d
ia
b
etic
p
atien
ts
.
RE
F
E
R
E
NC
E
S
[
1
]
Q
.
Zo
u
,
K
.
Q
u
,
Y
.
L
u
o
,
D
.
Y
i
n
,
Y
.
Ju
,
a
n
d
H
.
Ta
n
g
,
“
P
r
e
d
i
c
t
i
n
g
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
w
i
t
h
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,
”
Fr
o
n
t
i
e
rs
i
n
G
e
n
e
t
i
c
s
,
v
o
l
.
9
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
3
3
8
9
/
f
g
e
n
e
.
2
0
1
8
.
0
0
5
1
5
.
[
2
]
A
.
H
u
s
a
i
n
a
n
d
M
.
H
.
K
h
a
n
,
“
E
a
r
l
y
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
v
o
t
i
n
g
b
a
s
e
d
e
n
sem
b
l
e
l
e
a
r
n
i
n
g
,
”
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s
i
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
,
v
o
l
.
9
0
5
,
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
1
8
,
p
p
.
9
5
–
1
0
3
.
[
3
]
M
.
O
.
O
l
u
s
a
n
y
a
,
R
.
E.
O
g
u
n
sa
k
i
n
,
M
.
G
h
a
i
,
a
n
d
M
.
A
.
A
d
e
l
e
k
e
,
“
A
c
c
u
r
a
c
y
o
f
ma
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
o
d
e
l
s
f
o
r
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
t
y
p
e
2
d
i
a
b
e
t
e
s
me
l
l
i
t
u
s
:
a
sy
s
t
e
m
a
t
i
c
su
r
v
e
y
a
n
d
met
a
-
a
n
a
l
y
si
s
a
p
p
r
o
a
c
h
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
En
v
i
r
o
n
m
e
n
t
a
l
Re
se
a
rc
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
9
,
n
o
.
2
1
,
p
.
1
4
2
8
0
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
1
9
2
1
1
4
2
8
0
.
[
4
]
K
.
V
.
B
a
l
a
j
i
a
n
d
R
.
S
u
g
u
mar,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
d
i
a
b
e
t
e
s
mel
l
i
t
u
s
e
x
p
o
s
u
r
e
a
n
d
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
i
n
2
0
2
2
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
D
a
t
a
S
c
i
e
n
c
e
,
A
g
e
n
t
s
a
n
d
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
I
C
D
S
AAI
2
0
2
2
,
D
e
c
.
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
S
A
A
I
5
5
4
3
3
.
2
0
2
2
.
1
0
0
2
8
8
3
2
.
[
5
]
O
.
A
b
e
,
O
.
O
b
e
,
O
.
B
o
y
i
n
b
o
d
e
,
a
n
d
O
.
B
i
o
d
u
n
,
“
C
l
a
ss
i
f
i
e
r
a
l
g
o
r
i
t
h
ms
a
n
d
e
n
sem
b
l
e
m
o
d
e
l
s
f
o
r
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
p
r
e
d
i
c
t
i
o
n
:
a
r
e
v
i
e
w
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
T
re
n
d
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
4
3
0
–
4
3
9
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
0
5
3
4
/
i
j
a
t
c
s
e
/
2
0
2
1
/
6
4
1
0
1
2
0
2
1
.
[
6
]
A
.
H
u
ssa
i
n
a
n
d
S
.
N
a
a
z
,
“
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
:
C
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
v
a
r
i
o
u
s ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
i
n
A
d
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
1
6
6
,
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
2
1
,
p
p
.
1
0
3
–
1
1
5
.
[
7
]
M
.
P
h
o
n
g
y
i
n
g
a
n
d
S
.
H
i
r
i
o
t
e
,
“
D
i
a
b
e
t
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
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,
”
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
1
1
,
n
o
.
5
,
p
.
9
6
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
a
t
i
o
n
1
1
0
5
0
0
9
6
.
[
8
]
R
.
G
a
n
g
u
l
y
a
n
d
D
.
S
i
n
g
h
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
t
o
p
r
e
d
i
c
t
d
i
a
b
e
t
e
s
u
si
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
ms,
”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
0
3
7
LN
EE,
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
i
n
g
a
p
o
r
e
,
2
0
2
3
,
p
p
.
2
7
1
–
2
8
2
.
[
9
]
M
.
Y
i
,
“
R
e
s
e
a
r
c
h
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
s
f
o
r
d
i
a
b
e
t
e
s
d
a
t
a
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
l
g
o
ri
t
h
m
s,
Mi
c
r
o
c
h
i
p
s
a
n
d
N
e
t
w
o
rk
Ap
p
l
i
c
a
t
i
o
n
s
,
M
a
y
2
0
2
2
,
p
.
7
9
,
d
o
i
:
1
0
.
1
1
1
7
/
1
2
.
2
6
3
6
5
2
6
.
[
1
0
]
B
.
S
.
M
u
r
t
h
y
a
n
d
J
.
S
r
i
l
a
t
h
a
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
n
d
i
a
b
e
t
e
s
d
a
t
a
se
t
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
E
l
e
c
t
r
o
n
i
c
s
S
y
st
e
m
s
,
I
C
C
ES
2
0
2
1
,
Ju
l
.
2
0
2
1
,
p
p
.
1
4
1
6
–
1
4
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
ES5
1
3
5
0
.
2
0
2
1
.
9
4
8
8
9
5
4
.
[
1
1
]
L.
I
smai
l
a
n
d
H
.
M
a
t
e
r
w
a
l
a
,
“
I
D
M
P
F
:
i
n
t
e
l
l
i
g
e
n
t
d
i
a
b
e
t
e
s
mel
l
i
t
u
s
p
r
e
d
i
c
t
i
o
n
f
r
a
m
e
w
o
r
k
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Ap
p
l
i
e
d
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
8
/
a
c
i
-
10
-
2
0
2
0
-
0
0
9
4
.
[
1
2
]
S
.
A
r
u
k
o
n
d
a
a
n
d
R
.
C
h
e
r
u
k
u
,
“
A
n
o
v
e
l
s
t
a
c
k
i
n
g
f
r
a
mew
o
r
k
w
i
t
h
P
S
O
o
p
t
i
m
i
z
e
d
S
V
M
f
o
r
e
f
f
e
c
t
i
v
e
d
i
sea
s
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
a
n
d
F
u
zzy
S
y
st
e
m
s
,
v
o
l
.
4
5
,
n
o
.
3
,
p
p
.
4
1
0
5
–
4
1
2
3
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
3
2
3
3
/
JI
F
S
-
2
3
2
2
6
8
.
[
1
3
]
M
.
K
.
H
a
sa
n
,
M
.
A
.
A
l
a
m,
D
.
D
a
s,
E.
H
o
s
sai
n
,
a
n
d
M
.
H
a
sa
n
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
e
n
s
e
mb
l
i
n
g
o
f
d
i
f
f
e
r
e
n
t
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
7
6
5
1
6
–
7
6
5
3
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
8
9
8
5
7
.
[
1
4
]
G
.
T.
R
e
d
d
y
e
t
a
l
.
,
“
A
n
e
n
sem
b
l
e
b
a
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Em
e
r
g
i
n
g
T
re
n
d
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
i
c
-
ETI
T
E
2
0
2
0
,
F
e
b
.
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
-
E
TI
TE4
7
9
0
3
.
2
0
2
0
.
2
3
5
.
[
1
5
]
J
.
V
i
d
y
a
,
S
.
T
.
J
a
i
n
,
S
.
B
o
o
si
,
H
.
C
.
B
h
a
n
u
j
y
o
t
h
i
,
C
.
Tu
k
k
o
j
i
,
“
P
r
o
g
n
o
si
s o
f
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s u
s
i
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,”
T
u
rk
i
sh
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
Ma
t
h
e
m
a
t
i
c
s
E
d
u
c
a
t
i
o
n
(
T
U
RC
O
M
AT)
,
v
o
l
.
1
2
,
n
o
.
5
,
p
p
.
8
3
6
–
8
4
1
,
2
0
2
1
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
t
u
r
c
o
ma
t
.
o
r
g
/
i
n
d
e
x
.
p
h
p
/
t
u
r
k
b
i
l
mat
/
a
r
t
i
c
l
e
/
v
i
e
w
/
1
4
9
1
.
[
1
6
]
M
.
M
.
H
a
ssa
n
,
M
.
A
.
M
.
B
i
l
l
a
h
,
M
.
M
.
R
a
h
m
a
n
,
S
.
Za
m
a
n
,
M
.
M
.
H
.
S
h
a
k
i
l
,
a
n
d
J.
H
.
A
n
g
o
n
,
“
Ea
r
l
y
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s
i
n
h
e
a
l
t
h
c
a
r
e
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
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
N
T
5
1
5
2
5
.
2
0
2
1
.
9
5
7
9
7
9
9
.
[
1
7
]
M
.
F
.
U
.
B
h
u
i
y
a
n
,
M
.
T.
R
a
h
m
a
n
,
M
.
A
.
A
n
i
k
,
a
n
d
M
.
K
h
a
n
,
“
A
f
r
a
m
e
w
o
r
k
f
o
r
T
y
p
e
-
I
I
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
p
p
r
o
a
c
h
e
s,”
i
n
2
0
2
1
1
2
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
i
n
g
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
N
e
t
w
o
r
k
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
,
I
C
C
C
N
T
2
0
2
1
,
Ju
l
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
N
T
5
1
5
2
5
.
2
0
2
1
.
9
5
8
0
1
5
8
.
[
1
8
]
V
.
D
e
e
p
a
k
,
P
.
S
r
i
v
i
d
d
h
y
a
,
M
.
M
u
t
h
u
mari,
R
.
S
h
a
mel
i
,
a
n
d
S
.
N
.
D
e
v
i
,
“
I
d
e
n
t
i
f
y
i
n
g
l
e
t
h
a
l
e
f
f
e
c
t
s
a
n
d
r
i
s
k
l
e
v
e
l
u
si
n
g
a
n
i
mp
r
o
v
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
r
d
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
v
e
n
t
i
v
e
R
e
se
a
rc
h
i
n
C
o
m
p
u
t
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s,
I
C
I
RC
A
2
0
2
1
,
S
e
p
.
2
0
2
1
,
p
p
.
7
6
1
–
7
6
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
R
C
A
5
1
5
3
2
.
2
0
2
1
.
9
5
4
4
7
0
8
.
[
1
9
]
A
.
N
.
S
o
n
i
,
“
D
i
a
b
e
t
e
s
me
l
l
i
t
u
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
e
n
s
e
mb
l
e
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
,
”
S
S
RN
E
l
e
c
t
r
o
n
i
c
J
o
u
r
n
a
l
,
2
0
2
0
,
d
o
i
:
1
0
.
2
1
3
9
/
s
sr
n
.
3
6
4
2
8
7
7
.
[
2
0
]
M
.
S
.
S
a
t
u
,
S
.
T.
A
t
i
k
,
a
n
d
M
.
A
.
M
o
n
i
,
“
A
n
o
v
e
l
h
y
b
r
i
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
t
o
p
r
e
d
i
c
t
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
2
0
,
p
p
.
4
5
3
–
4
6
5
.
[
2
1
]
L.
M
a
l
v
i
y
a
,
S
.
M
a
l
,
P
.
L
a
l
w
a
n
i
,
a
n
d
J.
S
.
C
h
a
d
h
a
,
“
D
i
a
b
e
t
e
s
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s,
”
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
7
9
6
,
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
2
1
,
p
p
.
4
8
7
–
5
0
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
S
yn
erg
is
tic
en
s
emb
le
cla
s
s
ific
a
tio
n
fr
a
mewo
r
k:
u
tili
z
in
g
a
s
o
ft v
o
tin
g
a
l
g
o
r
ith
m
…
(
B
h
a
n
u
P
r
a
ka
s
h
Lo
h
a
n
i
)
1953
[
2
2
]
S
.
K
.
R
e
d
d
y
,
T
.
K
r
i
s
h
n
a
v
e
n
i
,
G
.
N
i
k
i
t
h
a
,
a
n
d
E.
V
i
j
a
y
k
a
n
t
h
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
d
i
f
f
e
r
e
n
t
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
rd
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
v
e
n
t
i
v
e
Re
s
e
a
r
c
h
i
n
C
o
m
p
u
t
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s,
I
C
I
R
C
A
2
0
2
1
,
S
e
p
.
2
0
2
1
,
p
p
.
1
2
6
1
–
1
2
6
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
R
C
A
5
1
5
3
2
.
2
0
2
1
.
9
5
4
4
5
9
3
.
[
2
3
]
U
.
D
a
s,
A
.
Y
.
S
r
i
z
o
n
,
M
.
A
.
I
sl
a
m
,
D
.
S
.
T
o
n
m
o
y
,
a
n
d
M
.
A
.
-
M
.
H
a
s
a
n
,
“
P
r
o
g
n
o
s
t
i
c
b
i
o
mar
k
e
r
s
i
d
e
n
t
i
f
i
c
a
t
i
o
n
f
o
r
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
b
y
u
t
i
l
i
z
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
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
re
n
c
e
o
n
S
u
st
a
i
n
a
b
l
e
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
I
n
d
u
st
r
y
4
.
0
,
S
T
I
2
0
2
0
,
D
e
c
.
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
S
TI
5
0
7
6
4
.
2
0
2
0
.
9
3
5
0
4
9
8
.
[
2
4
]
M
.
A
.
U
d
d
i
n
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
s
e
d
d
i
a
b
e
t
e
s
d
e
t
e
c
t
i
o
n
m
o
d
e
l
f
o
r
f
a
l
se
n
e
g
a
t
i
v
e
r
e
d
u
c
t
i
o
n
,
”
B
i
o
m
e
d
i
c
a
l
Ma
t
e
r
i
a
l
s
a
n
d
D
e
v
i
c
e
s
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
4
2
7
–
4
4
3
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
4
1
7
4
-
0
2
3
-
0
0
1
0
4
-
w.
[
2
5
]
J.
A
b
d
o
l
l
a
h
i
a
n
d
S
.
A
r
e
f
,
“
E
a
r
l
y
p
r
e
d
i
c
t
i
o
n
o
f
d
i
a
b
e
t
e
s
u
si
n
g
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
,
n
o
.
2
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
9
7
9
-
0
2
3
-
0
2
5
4
5
-
y.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Bh
a
n
u
Pra
k
a
sh
Lo
h
a
n
i
is
a
re
se
a
rc
h
s
c
h
o
lar
in
t
h
e
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t
a
t
G
a
lg
o
ti
a
s
Un
i
v
e
rsity
,
G
re
a
ter
No
id
a
.
He
h
o
l
d
s
b
o
th
M
.
Tec
h
.
a
n
d
B.
Tec
h
.
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
.
Wi
t
h
1
6
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
a
c
a
d
e
m
ia
a
n
d
re
se
a
rc
h
,
h
is
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta
a
n
a
ly
ti
c
s,
m
a
c
h
i
n
e
lea
rn
in
g
,
a
n
d
h
e
a
lt
h
c
a
re
in
fo
rm
a
ti
o
n
s
y
ste
m
s.
He
is
a
m
e
m
b
e
r
o
f
IE
EE
a
n
d
h
a
s
a
u
t
h
o
re
d
m
o
re
th
a
n
2
6
p
u
b
li
c
a
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
h
a
n
u
p
lo
h
a
n
i@g
m
a
il
.
c
o
m
.
Dr
.
Ar
v
in
d
Da
g
u
r
i
s
c
u
r
r
e
n
t
l
y
a
p
r
o
f
e
s
s
o
r
i
n
t
h
e
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
D
e
p
a
r
t
m
e
n
t
a
t
G
a
l
g
o
t
i
a
s
U
n
i
v
e
rs
i
t
y
,
G
r
e
a
t
e
r
N
o
i
d
a
.
Hi
s
r
e
s
e
a
r
c
h
i
n
t
e
re
s
t
s
i
n
c
l
u
d
e
m
a
c
h
i
n
e
le
a
r
n
i
n
g
,
A
I
a
p
p
l
i
c
a
t
i
o
n
s
,
d
a
t
a
m
i
n
i
n
g
,
a
n
d
d
a
t
a
a
n
a
l
y
t
ic
s
.
He
h
a
s
a
u
t
h
o
r
e
d
o
r
c
o
-
a
u
t
h
o
r
e
d
o
v
e
r
7
5
p
u
b
l
i
c
a
t
i
o
n
s
,
w
i
t
h
a
n
H
-
i
n
d
e
x
o
f
1
5
a
n
d
m
o
r
e
t
h
a
n
5
0
0
c
i
t
a
t
i
o
n
s
.
D
r
.
D
a
g
u
r
h
a
s
o
r
g
a
n
i
z
e
d
v
a
r
i
o
u
s
c
o
n
f
e
r
e
n
c
e
s
,
se
m
i
n
a
r
s
,
a
n
d
w
o
r
k
s
h
o
p
s
a
t
t
h
e
u
n
i
v
e
r
s
i
t
y
l
e
v
e
l
.
He
i
s
a
m
e
m
b
e
r
o
f
I
E
E
E
a
n
d
A
C
M
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
a
r
v
i
n
d
.
d
a
g
u
r
@
g
a
l
g
o
t
i
a
s
u
n
i
v
e
r
s
i
t
y
.
e
d
u
.
i
n
.
Dr
.
Dhi
r
e
n
d
r
a
K
u
m
a
r
S
h
u
k
la
is
a
d
isti
n
g
u
ish
e
d
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
e
r
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
ri
n
g
with
o
v
e
r
a
d
e
c
a
d
e
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
a
c
ro
ss
v
a
rio
u
s
p
re
stig
i
o
u
s
i
n
stit
u
ti
o
n
s.
Cu
rre
n
t
ly
,
h
e
se
rv
e
s
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
t
h
e
S
c
h
o
o
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
G
a
lg
o
ti
a
s
Un
iv
e
r
sity
.
Dr.
S
h
u
k
la
’
s
re
se
a
rc
h
in
tere
sts
a
re
d
e
e
p
ly
ro
o
ted
in
c
l
o
u
d
c
o
m
p
u
ti
n
g
,
m
a
c
h
i
n
e
lea
rn
in
g
m
o
d
e
ls
a
n
d
AI.
Dr.
S
h
u
k
la
h
a
s
o
rg
a
n
ize
d
v
a
rio
u
s
c
o
n
fe
re
n
c
e
s
a
n
d
se
m
in
a
rs
a
t
t
h
e
u
n
i
v
e
rsit
y
lev
e
l.
He
is
a
m
e
m
b
e
r
o
f
IEE
E
a
n
d
CS
I.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
h
iren
d
ra
.
s
h
u
k
la@
g
a
lg
o
ti
a
su
n
i
v
e
rs
it
y
.
e
d
u
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.