I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
5
,
Octo
b
er
20
25
,
p
p
.
4
9
3
3
~
4
9
4
1
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
9
3
3
-
4
9
4
1
4933
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Enha
ncing
diabet
es predic
tion t
hro
ug
h proba
bility
-
b
a
sed
co
rrect
io
n:
a met
ho
do
lo
g
ica
l appro
a
ch
Ait
o
uh
a
nn
i Im
a
ne,
B
er
qia
A
m
ine
S
S
LA
B
,
EN
S
I
A
S
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
si
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
1
6
,
2
0
2
5
R
ev
is
ed
J
u
l 5
,
2
0
2
5
Acc
ep
ted
J
u
l 1
2
,
2
0
2
5
P
r
e
d
i
c
t
i
v
e
h
e
a
l
t
h
c
a
r
e
a
n
a
l
y
t
i
c
s
d
e
m
a
n
d
s
a
c
c
u
r
a
te
p
r
e
d
i
c
t
i
o
n
s
f
r
o
m
i
n
t
e
r
p
r
e
t
a
b
l
e
m
o
d
e
l
s
f
o
r
e
a
r
l
y
d
i
a
g
n
o
s
i
s
a
n
d
i
n
t
e
r
v
e
n
t
i
o
n
o
n
d
i
a
b
e
t
e
s
p
r
o
g
n
o
s
i
s
,
w
h
i
c
h
r
e
m
a
i
n
s
a
w
e
l
l
-
e
s
t
a
b
l
i
s
h
e
d
c
h
a
l
le
n
g
e
.
T
h
i
s
s
t
u
d
y
p
r
e
s
e
n
t
s
a
n
e
w
p
r
o
b
a
b
i
l
i
t
y
-
b
a
s
e
d
c
o
r
r
e
c
t
i
o
n
m
e
t
h
o
d
t
o
e
n
h
a
n
c
e
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
a
m
o
d
e
l
i
n
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
.
I
n
i
t
i
a
l
m
o
d
e
l
c
o
m
p
a
r
i
s
o
n
s
a
r
e
p
e
r
f
o
rm
e
d
u
s
i
n
g
t
h
e
P
y
C
a
r
e
t
f
r
a
m
e
w
o
r
k
t
o
i
d
e
n
t
i
f
y
t
h
e
b
a
se
l
i
n
e
m
o
d
e
l
.
L
o
g
i
s
t
i
c
r
e
g
r
e
s
s
i
o
n
w
a
s
s
e
l
e
c
t
e
d
d
u
e
t
o
i
ts
s
im
p
l
i
c
i
t
y
,
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
,
a
n
d
i
t
s
h
i
g
h
e
r
a
c
c
u
r
a
c
y
,
w
h
i
c
h
o
u
t
p
e
r
f
o
r
m
e
d
o
t
h
e
r
m
o
d
e
l
s
.
T
o
f
u
r
t
h
e
r
f
a
c
i
l
i
t
a
te
f
u
t
u
r
e
r
e
s
e
a
r
c
h
i
n
t
h
i
s
f
i
e
l
d
,
t
h
i
s
s
t
u
d
y
w
a
s
c
o
n
d
u
c
t
e
d
u
s
i
n
g
a
n
o
i
s
y
d
a
t
a
s
e
t
w
i
t
h
o
u
t
a
n
y
c
h
a
n
g
e
s
o
r
p
r
e
p
r
o
c
e
s
s
i
n
g
s
t
e
p
s
o
t
h
e
r
t
h
a
n
t
h
o
s
e
a
v
a
i
l
a
b
l
e
i
n
t
h
e
d
a
t
a
s
e
t
f
r
o
m
t
h
e
p
r
o
d
u
c
e
r
.
T
h
i
s
i
n
t
e
n
t
i
o
n
a
l
d
e
c
i
s
i
o
n
m
e
a
n
t
t
h
a
t
t
h
e
n
e
w
p
r
o
b
a
b
i
l
i
t
y
-
b
a
s
e
d
m
e
t
h
o
d
c
o
u
l
d
b
e
e
v
a
l
u
a
t
e
d
i
n
i
s
o
l
a
t
i
o
n
w
i
t
h
o
u
t
a
n
y
a
d
d
i
t
i
o
n
a
l
m
o
d
i
f
i
c
a
t
i
o
n
s
b
e
i
n
g
a
p
p
l
i
e
d
.
T
h
e
p
r
o
p
o
s
e
d
c
o
r
r
e
c
t
i
o
n
m
e
t
h
o
d
a
d
j
u
s
t
s
p
r
e
d
i
c
t
i
o
n
s
i
n
t
o
b
o
r
d
e
r
l
i
n
e
p
r
o
b
a
b
i
l
i
t
y
i
n
t
e
r
v
a
l
s
t
o
o
b
t
a
i
n
m
o
r
e
a
c
c
u
r
a
t
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
s
.
T
h
i
s
a
p
p
r
o
a
c
h
i
n
c
r
e
a
se
d
t
h
e
m
o
d
e
l
a
c
c
u
ra
c
y
b
y
6
%
f
r
o
m
7
5
%
t
o
8
1
%
,
t
h
u
s
p
r
o
v
i
n
g
s
u
c
c
e
s
s
f
u
l
i
n
r
e
s
o
l
v
i
n
g
t
h
e
m
i
s
c
la
s
s
if
i
c
a
t
i
o
n
p
r
o
b
l
e
m
w
it
h
h
i
g
h
e
r
r
i
s
k
.
T
h
i
s
a
p
p
r
o
a
c
h
o
u
t
p
e
r
f
o
r
m
s
s
t
a
t
e
-
of
-
t
h
e
-
a
r
t
m
e
t
h
o
d
s
a
n
d
d
e
m
o
n
s
t
r
a
t
e
s
i
ts
g
e
n
e
ra
l
i
z
a
b
i
l
i
t
y
i
n
e
n
h
a
n
c
i
n
g
t
h
e
c
e
r
ta
i
n
t
y
o
f
d
o
w
n
s
t
r
e
a
m
c
l
i
n
i
c
a
l
d
e
c
i
s
i
o
n
s
.
K
ey
w
o
r
d
s
:
Diab
etes p
r
ed
ictio
n
E
n
h
an
ce
m
e
n
t
Hea
lth
ca
r
e
Ma
ch
in
e
lear
n
in
g
Pro
b
ab
ilit
y
co
r
r
ec
tio
n
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
:
Aito
u
h
an
n
i I
m
an
e
SS
L
AB
,
E
NSI
A
S,
Mo
h
am
m
ed
V
Un
iv
er
s
ity
in
R
ab
at
R
ab
at,
Mo
r
o
cc
o
E
m
ail: im
an
e.
aito
u
h
a
n
n
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Diab
etes
p
r
ed
ictio
n
is
an
i
m
p
o
r
tan
t
p
r
o
b
lem
in
t
h
e
h
e
alth
ca
r
e
f
ield
d
u
e
to
th
e
n
ec
ess
ity
o
f
in
ter
p
r
etab
le
a
n
d
ac
cu
r
ate
m
o
d
els
f
o
r
p
r
o
p
er
d
iab
etes
p
r
ed
ictio
n
an
d
in
te
r
v
en
tio
n
.
W
ith
th
e
in
c
r
ea
s
in
g
in
cid
en
ce
o
f
d
iab
etes
g
lo
b
all
y
,
n
o
w
m
o
r
e
th
an
ev
e
r
,
d
ia
g
n
o
s
tics
m
u
s
t
p
r
o
v
id
e
ac
cu
r
ate
d
etec
tio
n
wh
ile
id
en
tify
in
g
t
h
e
d
is
ea
s
e
b
ef
o
r
e
co
m
p
licatio
n
s
ar
is
e.
Pre
d
ictiv
e
an
aly
tics
n
o
w
s
tan
d
s
at
a
p
o
wer
f
u
l
p
lace
to
h
elp
h
ea
lth
p
r
o
v
id
e
r
s
to
tak
e
th
e
n
ec
ess
ar
y
d
ec
is
io
n
s
at
th
e
r
ig
h
t
tim
e.
W
ell,
it
ca
n
b
e
u
s
ed
to
d
ev
elo
p
p
r
e
d
ictiv
e
alg
o
r
ith
m
s
as
in
th
e
ca
s
e
o
f
th
e
Pima
I
n
d
ia
Diab
etes
d
ataset
[
1
]
wh
ich
p
r
o
v
id
es
a
c
o
m
p
let
e
r
ep
r
esen
tatio
n
o
f
th
e
d
iab
etes
r
is
k
f
ac
to
r
s
.
Usi
n
g
th
is
d
ataset,
s
tu
d
ies
h
av
e
r
ea
ch
ed
h
ig
h
ac
cu
r
ac
ies
with
ad
v
a
n
ce
d
m
ac
h
in
e
lear
n
in
g
m
o
d
els
lik
e
Gr
a
d
ien
t
b
o
o
s
tin
g
a
n
d
r
an
d
o
m
f
o
r
est
[
2
]
wh
ich
a
r
e
g
o
o
d
at
lear
n
i
n
g
c
o
m
p
lex
p
atter
n
s
i
n
d
ata.
Nev
er
th
eless
,
s
u
ch
m
et
h
o
d
s
f
o
c
u
s
m
ain
ly
o
n
m
is
cla
s
s
if
icatio
n
o
n
th
e
av
e
r
ag
e
r
is
k
,
b
o
r
d
er
lin
e
ca
s
es
wh
er
e
th
e
p
r
o
b
ab
ilit
ies
lay
v
e
r
y
n
ea
r
th
e
d
ec
is
io
n
t
h
r
esh
o
ld
s
th
er
ef
o
r
e
co
m
m
o
n
m
is
class
i
f
icatio
n
in
h
ig
h
-
r
is
k
ca
s
es wh
er
e
m
is
tak
es c
o
u
ld
b
e
f
atal
is
m
ain
ly
ig
n
o
r
ed
.
W
ith
in
th
is
co
n
tex
t,
th
is
s
tu
d
y
p
er
f
o
r
m
ed
a
f
ir
s
t
ap
p
r
o
ac
h
to
th
e
co
m
p
ar
is
o
n
o
f
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
els
with
t
h
e
h
elp
o
f
Py
C
ar
et
[
3
]
a
n
d
id
en
tifie
d
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
as
th
e
b
est
-
p
e
r
f
o
r
m
in
g
m
o
d
el
in
ter
m
s
o
f
ac
cu
r
ac
y
with
a
s
i
m
p
le
an
d
in
ter
p
r
eta
b
le
s
o
lu
tio
n
.
it
p
r
esen
t
n
ex
t
a
p
r
o
b
ab
ilit
y
-
b
ased
co
r
r
ec
tio
n
m
eth
o
d
t
o
co
r
r
ec
t
h
ig
h
-
r
is
k
m
is
class
if
icatio
n
.
T
h
e
m
eth
o
d
th
en
r
ef
in
es
m
o
d
el
p
er
f
o
r
m
an
ce
esp
ec
ially
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
3
3
-
4
9
4
1
4934
b
o
r
d
er
li
n
e
ca
s
es
n
o
t
b
y
b
o
o
s
tin
g
ac
cu
r
ac
y
b
u
t
b
y
p
in
p
o
in
tin
g
u
n
ce
r
tain
p
r
e
d
ictio
n
s
an
d
co
r
r
ec
tin
g
th
e
m
,
in
cr
ea
s
in
g
r
eliab
ilit
y
.
T
h
is
a
p
p
r
o
ac
h
d
i
f
f
er
s
f
r
o
m
s
tu
d
ies
th
at
p
r
im
ar
ily
s
tr
iv
e
to
o
b
t
ain
s
tate
-
of
-
th
e
-
ar
t
ac
cu
r
ac
y
,
as we
p
r
esen
t a
n
ew
m
eth
o
d
f
o
r
im
p
r
o
v
em
en
t th
at
ca
n
b
e
ap
p
lied
to
d
if
f
er
en
t
m
o
d
els.
T
h
i
s
w
o
r
k
u
s
e
s
t
h
e
P
i
m
a
d
a
t
a
s
e
t
[
1
]
w
h
o
h
a
s
s
e
e
n
m
a
n
y
a
d
v
a
n
c
e
s
u
t
i
l
i
z
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
.
R
a
n
d
o
m
f
o
r
e
s
t
(
R
F
)
,
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
(
S
V
M
)
a
n
d
G
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
h
a
v
e
b
e
e
n
a
c
h
i
e
v
e
d
b
y
m
o
r
e
t
h
a
n
9
0
%
u
s
u
a
l
l
y
t
h
r
o
u
g
h
f
e
a
t
u
r
e
e
n
g
i
n
e
e
r
i
n
g
,
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
a
n
d
b
a
l
a
n
c
e
d
d
a
t
a
.
A
l
t
h
o
u
g
h
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
h
e
s
e
s
t
u
d
i
e
s
i
s
h
i
g
h
,
t
h
e
y
u
s
u
a
l
l
y
o
v
e
r
l
o
o
k
t
h
e
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
a
n
d
p
o
l
i
s
h
i
n
g
o
f
u
n
c
e
r
t
a
i
n
p
r
e
d
i
c
t
i
o
n
s
.
W
e
ex
ten
d
th
is
p
r
io
r
wo
r
k
b
y
p
r
o
p
o
s
in
g
a
co
r
r
ec
tio
n
m
ec
h
an
is
m
th
at
f
o
cu
s
es
o
n
ca
s
es
wh
er
e
im
p
r
o
v
em
e
n
t
is
m
o
s
t
b
en
ef
icial,
r
ath
er
th
an
co
m
p
etin
g
o
n
ab
s
o
lu
te
ac
cu
r
ac
y
m
etr
ics.
T
h
is
ap
p
r
o
ac
h
b
u
ild
s
u
p
o
n
th
e
c
u
r
r
e
n
t
lan
d
s
ca
p
e
o
f
h
ig
h
ac
cu
r
ac
y
m
o
d
els
an
d
p
r
o
v
id
es
a
f
r
am
ewo
r
k
i
n
wh
ich
we
ca
n
in
cr
ea
s
e
th
e
r
eliab
ilit
y
o
f
d
ec
is
io
n
s
m
ad
e
b
y
au
to
m
ated
s
y
s
tem
s
in
th
e
clin
ical
co
n
tex
t.
B
y
r
ef
in
in
g
p
r
ed
ictio
n
s
th
at
lie
n
ea
r
th
e
d
ec
is
io
n
b
o
u
n
d
a
r
y
,
th
is
m
eth
o
d
o
lo
g
y
h
elp
s
r
e
d
u
ce
h
ig
h
-
r
is
k
m
is
class
if
icat
io
n
s
th
at
ar
e
o
f
ten
o
v
er
lo
o
k
ed
in
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
im
p
lem
e
n
tatio
n
s
.
T
h
e
r
est
o
f
th
is
p
a
p
er
is
s
tr
u
c
tu
r
ed
as
f
o
llo
ws.
Sectio
n
2
p
r
esen
ts
th
e
b
ac
k
g
r
o
u
n
d
s
tu
d
y
,
in
clu
d
in
g
n
o
tatio
n
s
an
d
th
e
k
n
o
wn
r
el
ated
wo
r
k
s
.
Sectio
n
3
d
escr
i
b
es
th
e
m
eth
o
d
o
lo
g
y
p
r
o
p
o
s
ed
alo
n
g
with
th
e
d
ataset
p
r
ep
r
o
ce
s
s
in
g
an
d
th
e
p
r
o
b
ab
ilit
ies
-
b
ased
co
r
r
ec
tio
n
m
eth
o
d
.
T
h
e
r
esu
lts
ar
e
p
r
e
s
en
ted
in
s
ec
tio
n
4
,
f
o
llo
wed
b
y
th
e
p
e
r
f
o
r
m
an
ce
im
p
r
o
v
e
m
en
ts
g
ain
ed
with
t
h
e
p
r
o
p
o
s
ed
co
r
r
ec
tio
n
m
eth
o
d
o
lo
g
y
.
Sectio
n
s
5
an
d
6
f
in
alize
th
e
p
ap
e
r
d
is
cu
s
s
in
g
im
p
licatio
n
s
,
co
m
p
ar
in
g
t
h
em
with
p
r
ev
io
u
s
s
tu
d
ies
an
d
lim
itatio
n
s
o
f
t
h
e
s
tu
d
y
,
a
n
d
a
co
n
clu
s
io
n
,
r
esp
ec
tiv
ely
,
s
u
m
m
a
r
izin
g
th
e
c
o
n
tr
ib
u
tio
n
o
f
th
e
p
a
p
er
,
an
d
s
u
g
g
esti
n
g
p
o
ten
tial
f
u
tu
r
e
lin
es o
f
r
esear
ch
.
2.
B
ACK
G
RO
UND
S
T
UD
Y
T
h
is
s
ec
tio
n
d
escr
ib
es
th
e
m
ain
ter
m
in
o
lo
g
ies
an
d
c
o
n
ce
p
ts
u
n
d
er
p
in
n
i
n
g
d
iab
etes
p
r
e
d
ictio
n
an
d
p
r
esen
ts
th
e
p
r
ec
e
d
in
g
b
ac
k
g
r
o
u
n
d
f
o
r
p
r
o
b
a
b
ilit
y
-
b
ased
co
r
r
ec
tio
n
also
in
m
ac
h
in
e
l
ea
r
n
in
g
,
to
lay
th
e
f
o
u
n
d
atio
n
s
f
o
r
th
e
u
n
d
er
s
tan
d
in
g
o
f
t
h
is
s
tu
d
y
.
2
.
1
.
Dia
bet
es a
nd
it
s
predict
io
n c
ha
lleng
es
Diab
etes
is
an
o
n
g
o
in
g
d
is
ea
s
e
s
tate
an
d
is
ch
ar
ac
ter
ized
b
y
elev
ated
b
lo
o
d
g
lu
c
o
s
e
lev
els
wh
ich
,
if
lef
t
u
n
tr
ea
ted
,
will
lead
to
life
-
th
r
ea
ten
in
g
c
o
m
p
licatio
n
s
s
u
ch
as
ca
r
d
io
v
ascu
lar
illn
ess
,
k
id
n
ey
in
ju
r
y
an
d
n
eu
r
o
p
ath
y
[
4
]
.
E
ar
ly
d
etec
t
io
n
an
d
m
an
ag
e
m
en
t
ar
e
c
r
u
cial
to
p
r
ev
e
n
tin
g
th
ese
o
u
tco
m
es.
Pre
d
ictiv
e
m
o
d
elin
g
h
as
b
ec
o
m
e
an
ess
en
tial
to
o
l
in
h
ea
lth
ca
r
e
f
o
r
id
e
n
tify
in
g
in
d
iv
id
u
als
at
r
is
k
o
f
d
iab
etes,
en
ab
lin
g
tim
ely
in
ter
v
en
tio
n
s
[
5
]
.
Pre
d
ictiv
e
m
o
d
els
h
av
e
n
o
w
b
ec
o
m
e
an
in
teg
r
al
p
ar
t
o
f
th
e
h
e
alth
ca
r
e
s
y
s
tem
to
d
eter
m
in
in
g
i
n
d
iv
id
u
als
at
r
is
k
f
o
r
d
iab
etes
ea
r
lier
wh
ic
h
lead
s
th
em
to
tim
ely
in
ter
v
en
tio
n
s
.
Acc
u
r
at
e
p
r
ed
ictio
n
is
d
if
f
icu
lt d
u
e
t
o
p
r
o
b
lem
s
s
u
ch
as im
b
alan
ce
d
d
a
tasets
,
n
o
is
e,
an
d
o
v
er
la
p
p
in
g
f
ea
tu
r
es
[
6
]
.
Pre
d
ictiv
e
m
o
d
elin
g
b
ased
o
n
h
ea
lth
ca
r
e
an
aly
tics
h
as
r
e
ce
n
tly
b
ee
n
em
p
l
o
y
ed
to
d
is
co
v
er
th
o
s
e
ea
r
ly
m
a
r
k
er
s
a
n
d
r
is
k
f
ac
to
r
s
f
o
r
d
ia
b
etes
[
7
]
.
T
h
ese
ap
p
r
o
ac
h
es
u
s
e
d
e
m
o
g
r
ap
h
ic
d
ata,
life
s
ty
le
v
ar
iab
les,
an
d
clin
ical
m
ea
s
u
r
em
en
ts
to
p
r
ed
ict
th
e
p
r
o
b
a
b
ilit
y
o
f
d
ev
elo
p
in
g
d
iab
etes.
Ho
we
v
er
,
d
esp
ite
th
ese
ad
v
an
ce
m
e
n
ts
th
er
e
r
em
ain
s
o
m
e
lim
itatio
n
s
,
esp
ec
ially
in
th
e
co
n
tex
t
o
f
r
e
p
r
o
d
u
cib
ly
class
if
y
in
g
ca
s
es
o
n
th
e
d
ec
is
io
n
th
r
esh
o
l
d
wh
er
e
t
o
m
ak
e
a
n
im
p
o
r
tan
t a
n
d
ac
tio
n
ab
le
in
ter
v
e
n
tio
n
[
8
]
.
2
.
2
.
M
a
chine le
a
rning
in dia
bet
es pre
dict
io
n
Diab
etes
p
r
ed
ictio
n
u
s
in
g
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es
a
r
e
ex
p
ec
ted
t
o
im
p
r
o
v
e
th
e
p
r
ed
ictio
n
ac
cu
r
ac
y
f
o
r
d
iab
etes.
LR
,
RF
,
an
d
Gr
ad
ien
t
b
o
o
s
tin
g
ar
e
am
o
n
g
th
e
p
o
p
u
lar
ch
o
ices,
d
u
e
to
th
eir
ca
p
ab
ilit
y
f
o
r
m
o
d
ellin
g
co
m
p
lex
r
elat
io
n
s
h
ip
s
[
9
]
.
On
t
h
e
o
th
er
h
an
d
,
L
R
,
f
o
r
in
s
tan
ce
,
is
ap
p
r
ec
iated
f
o
r
its
in
ter
p
r
etab
ilit
y
an
d
ef
f
icien
c
y
f
o
r
b
in
ar
y
class
if
icatio
n
task
s
wh
ile
en
s
em
b
le
m
eth
o
d
s
s
u
ch
as
R
F
an
d
Gr
ad
ien
t
b
o
o
s
tin
g
ar
e
b
etter
s
u
ited
to
n
o
n
-
lin
ea
r
in
ter
ac
tio
n
s
an
d
h
ig
h
-
d
im
en
s
io
n
al
d
ata
[
1
0
]
.
T
h
ese
m
o
d
els
ten
d
to
s
h
o
w
well
in
th
e
cr
e
ato
r
d
ata
s
ets,
b
u
t
n
o
t
with
o
u
t
er
r
o
r
;
with
b
o
r
d
er
lin
e
ca
s
es,
th
e
p
r
o
b
ab
ilit
y
o
f
class
if
icatio
n
is
n
ea
r
th
e
d
e
cisi
o
n
th
r
esh
o
ld
,
an
d
t
h
er
e
ar
e
er
r
o
r
s
d
u
e
t
o
m
is
class
if
i
ca
tio
n
[
1
1
]
.
T
h
ese
m
is
class
if
icatio
n
s
lead
to
late
o
r
in
ap
p
r
o
p
r
iate
in
ter
v
e
n
tio
n
s
,
d
em
o
n
s
tr
atin
g
th
e
n
ec
ess
ity
o
f
m
eth
o
d
o
l
o
g
ies
to
allev
iate
th
is
d
r
awb
ac
k
[
1
2
]
.
2
.
3
.
L
o
g
is
t
ic
r
eg
re
s
s
io
n
L
o
g
is
tic
r
eg
r
ess
io
n
is
a
clas
s
if
icatio
n
alg
o
r
ith
m
co
m
m
o
n
’
s
u
s
ed
f
o
r
b
in
ar
y
p
r
o
b
lem
s
,
f
o
r
e
x
am
p
le
if
s
o
m
eo
n
e
h
as
d
iab
etes
o
r
n
o
t
[
5
]
.
I
t
is
a
way
to
m
o
d
el
th
e
p
r
o
b
a
b
ilit
y
th
at
th
e
tar
g
et
v
a
r
iab
le
b
elo
n
g
s
to
a
p
ar
ticu
lar
class
g
iv
en
t
h
e
in
p
u
t
f
ea
tu
r
es
[
1
3
]
.
T
h
is
tech
n
iq
u
e
r
elies
o
n
t
h
e
lo
g
is
tic
f
u
n
ct
io
n
(
also
ca
lled
t
h
e
s
ig
m
o
id
f
u
n
ctio
n
)
,
w
h
ich
is
d
e
f
in
ed
as:
(
=
1
|
)
=
1
/
(
1
+
(
−
(
0
+
1
1
+
2
2
+
.
.
.
+
)
)
)
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
d
ia
b
etes p
r
ed
ictio
n
th
r
o
u
g
h
p
r
o
b
a
b
ilit
y
-
b
a
s
ed
…
(
A
ito
u
h
a
n
n
i I
ma
n
e
)
4935
0
r
ep
r
esen
ts
th
e
in
ter
ce
p
t,
1
,
2
,
.
.
.
,
ar
e
th
e
c
o
ef
f
icien
ts
co
r
r
esp
o
n
d
in
g
to
th
e
f
ea
tu
r
es
1
,
2
,
.
.
.
,
,
an
d
(
=
1
|
)
is
th
e
p
r
o
b
a
b
ilit
y
o
f
th
e
ta
r
g
et
v
ar
iab
le
(
e.
g
.
,
d
iab
etes p
r
esen
ce
)
.
Du
e
to
t
h
e
q
u
alities
o
f
th
e
l
o
g
is
tic
f
u
n
ctio
n
,
t
h
e
o
u
tp
u
t
will
alwa
y
s
lie
in
th
e
r
an
g
e
o
f
0
an
d
1
.
T
r
ain
in
g
th
e
alg
o
r
ith
m
m
ea
n
s
esti
m
atin
g
th
e
c
o
ef
f
icien
ts
b
y
n
o
tin
g
th
at
th
e
lik
elih
o
o
d
o
f
t
h
e
o
b
s
er
v
ed
d
ata
is
m
ax
im
ized
wh
en
th
ese
ar
e
co
r
r
ec
t.
T
h
e
m
o
d
el
m
ak
es
p
r
ed
ictio
n
s
b
y
a
p
p
ly
in
g
a
th
r
esh
o
ld
(
h
er
e,
0
.
5
)
:
≥
ℎ
ℎ
→
1
,
<
ℎ
ℎ
→
0
.
L
R
is
s
im
p
le
an
d
in
ter
p
r
eta
b
le,
an
d
,
th
u
s
,
it
is
u
s
ed
as
a
b
aselin
e
m
o
d
el
f
o
r
m
a
n
y
ap
p
licatio
n
s
in
d
if
f
er
en
t
d
o
m
ai
n
s
,
s
u
ch
as
d
iab
etes
p
r
e
d
ictio
n
i
n
h
ea
lth
ca
r
e
ap
p
licatio
n
s
.
Var
io
u
s
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
p
lay
an
im
p
o
r
tan
t
r
o
le
in
en
h
an
cin
g
th
e
ac
cu
r
ac
y
o
f
well
-
k
n
o
wn
m
et
h
o
d
s
f
o
r
p
r
ed
ictin
g
d
iab
etes
[
1
4
]
.
Mo
d
els
lik
e
L
R
,
R
F,
a
n
d
Gr
ad
ien
t
b
o
o
s
tin
g
ar
e
wid
ely
u
s
ed
f
o
r
th
eir
ab
ilit
y
to
an
aly
ze
co
m
p
lex
r
elatio
n
s
h
ip
s
with
in
d
ata
[
1
5
]
.
L
R
is
ad
o
p
ted
f
o
r
its
s
im
p
l
icity
an
d
i
n
ter
p
r
etab
ilit
y
in
b
in
ar
y
class
if
icatio
n
task
s
,
b
u
t
en
s
em
b
le
m
eth
o
d
s
s
u
ch
as
R
F
an
d
Gr
ad
ien
t
b
o
o
s
tin
g
o
u
tp
u
t
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
s
o
n
n
o
n
-
lin
ea
r
in
ter
ac
tio
n
s
an
d
h
i
g
h
d
im
e
n
s
io
n
al
d
ata
[
1
6
]
.
W
h
ile
p
r
ev
io
u
s
m
o
d
els
h
av
e
t
h
eir
o
wn
s
tr
en
g
th
s
,
th
ey
f
r
e
q
u
en
tly
f
ail
to
p
e
r
f
o
r
m
well
in
b
o
r
d
er
lin
e
ca
s
es,
wh
er
e
th
e
p
r
o
b
ab
i
lity
o
f
class
m
em
b
e
r
s
h
ip
is
a
r
o
u
n
d
th
e
d
ec
is
io
n
b
o
u
n
d
ar
y
,
r
esu
ltin
g
in
p
o
s
s
ib
le
m
is
class
if
icatio
n
s
.
T
h
is
m
is
class
if
icatio
n
ca
n
lead
to
d
ela
y
ed
o
r
in
a
p
p
r
o
p
r
iate
in
ter
v
en
tio
n
s
wh
ich
war
r
an
ts
m
eth
o
d
o
l
o
g
ies th
at
ad
d
r
ess
th
is
lim
itatio
n
.
2
.
4
.
H
i
g
h
-
risk
predict
io
ns
a
nd
pro
ba
bil
it
y
-
ba
s
ed
co
rr
ec
t
io
n
Hig
h
r
is
k
p
r
ed
ictio
n
s
r
e
f
er
to
ca
s
es
wh
er
e
m
o
d
el
p
r
o
b
ab
ili
ties
f
all
with
in
a
s
m
all
r
an
g
e
ab
o
u
t
th
e
d
ec
is
io
n
b
o
u
n
d
ar
y
(
e.
g
.
,
0
.
4
t
o
0
.
6
)
.
T
h
e
p
r
ed
ictio
n
s
m
ad
e
b
y
th
is
k
in
d
o
f
m
o
d
el
ar
e
n
o
t
v
er
y
ac
cu
r
ate,
s
o
th
ese
ca
s
es
will
b
e
af
f
ec
ted
m
o
r
e
ea
s
ily
[
1
7
]
.
W
ith
o
u
t
m
ec
h
an
is
m
s
to
s
p
ec
if
ically
t
ac
k
le
th
ese
ca
s
es,
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els b
ec
o
m
e
less
r
eliab
le
in
th
o
s
e
cr
itical
s
ettin
g
s
[
1
8
]
.
On
e
o
f
th
e
m
eth
o
d
o
l
o
g
ies
th
at
h
av
e
b
ee
n
d
esig
n
ed
to
tack
le
th
is
p
r
o
b
lem
is
ca
lled
p
r
o
b
ab
il
ity
-
b
ased
co
r
r
ec
tio
n
,
wh
ich
f
in
d
s
s
u
ch
r
is
k
y
p
air
s
i
n
ac
c
o
r
d
an
ce
with
th
eir
p
er
ce
n
tag
e
d
if
f
e
r
en
ce
an
d
in
v
e
r
s
ely
s
witch
th
em
,
th
u
s
im
p
r
o
v
in
g
t
h
e
o
v
e
r
all
ac
cu
r
ac
y
o
f
th
e
m
o
d
el
[
1
9
]
.
T
h
is
is
esp
ec
ially
th
e
ca
s
e
f
o
r
h
ea
lth
ca
r
e,
wh
er
e
r
ed
u
cin
g
f
alse
p
o
s
itiv
es
an
d
f
alse
n
eg
ativ
es
ca
n
g
r
ea
tly
af
f
e
ct
p
atien
t
ca
r
e
[
2
0
]
.
T
h
e
in
ten
t
o
f
th
e
p
r
o
b
ab
ilit
y
-
b
ased
co
r
r
ec
tio
n
is
to
im
p
r
o
v
e
d
ec
is
io
n
r
eliab
ilit
y
an
d
m
o
d
el
r
o
b
u
s
tn
ess
b
y
r
e
-
e
v
alu
a
tin
g
an
d
a
d
ju
s
tin
g
p
r
ed
ictio
n
s
in
th
e
id
en
tifie
d
h
i
g
h
-
r
is
k
in
ter
v
al.
2
.
5
.
Clini
ca
l im
pli
ca
t
io
ns
o
f
predict
io
n m
o
dels
Diab
etes
p
r
ed
ictio
n
m
o
d
els
ar
e
an
y
h
ea
lth
ca
r
e
p
r
o
v
id
er
'
s
b
est
f
r
ien
d
,
as
th
ey
liter
ally
g
iv
e
ac
tio
n
ab
le
in
s
ig
h
ts
in
to
wh
at
n
ee
d
s
to
b
e
d
o
n
e
.
C
o
r
r
ec
tly
id
en
tif
y
in
g
p
eo
p
le
at
h
ig
h
r
is
k
m
ak
es
it
p
o
s
s
ib
le
to
in
ter
v
en
e
ea
r
ly
,
wh
ich
h
elp
s
a
v
er
t
th
e
o
n
s
et
o
f
d
iab
etes
a
n
d
a
h
o
s
t
o
f
ass
o
ciate
d
co
m
p
licatio
n
s
[
2
1
]
.
Mo
r
eo
v
er
,
p
r
ed
ictio
n
m
o
d
els
s
h
o
u
ld
b
e
d
is
tin
ct
an
d
cr
ed
ib
le,
as
th
ey
ar
e
s
u
p
p
o
s
ed
t
o
b
e
in
c
o
r
p
o
r
at
ed
in
to
th
e
clin
ical
wo
r
k
f
lo
ws
[
2
2
]
.
Stated
s
u
cc
in
ctly
,
th
e
im
p
licatio
n
s
o
f
m
is
cl
ass
if
icatio
n
s
(
f
alse
p
o
s
itiv
es/n
eg
ativ
es)
r
esu
ltin
g
in
p
o
ten
tially
u
n
n
ec
ess
ar
y
tr
e
atm
en
t
o
r
u
n
d
iag
n
o
s
ed
co
n
d
itio
n
s
em
p
h
asizes
th
e
n
ee
d
f
o
r
im
p
r
o
v
e
d
d
ec
is
io
n
-
m
ak
in
g
in
th
ese
ca
s
es
[
2
3
]
.
2
.
6
.
T
he
ro
le
o
f
f
ea
t
ure
eng
i
neer
ing
I
t
is
th
e
p
r
o
ce
s
s
o
f
u
s
in
g
d
o
m
ain
k
n
o
wled
g
e
o
f
t
h
e
p
r
o
b
l
em
to
cr
ea
te
f
ea
tu
r
es
th
at
m
a
k
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
wo
r
k
[
2
1
]
.
Fo
r
ex
am
p
le,
in
p
r
ed
ictin
g
d
i
ab
etes,
cr
ea
ted
f
ea
tu
r
es
s
u
ch
a
s
in
ter
ac
tio
n
ter
m
s
(
Glu
co
s
e
-
to
-
B
MI
r
atio
)
o
r
n
o
n
-
lin
ea
r
tr
an
s
f
o
r
m
atio
n
s
ca
n
g
r
ea
tly
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
[
1
1
]
.
W
h
ile
b
aselin
e
m
o
d
els
f
r
eq
u
e
n
tly
n
e
g
lect
th
is
s
tep
b
ec
au
s
e
th
ey
ar
e
h
eter
o
g
e
n
eo
u
s
m
eth
o
d
s
,
it
is
a
co
r
n
er
s
to
n
e
o
f
m
ac
h
in
e
lear
n
in
g
im
p
r
o
v
em
e
n
t f
o
r
p
r
ed
ictiv
e
p
e
r
f
o
r
m
an
ce
a
n
d
th
e
in
ter
p
r
etab
ilit
y
o
f
th
e
f
i
n
al
m
o
d
el
[
2
4
]
.
2
.
7
.
Su
mm
a
ry
o
f
re
l
a
t
ed
m
e
t
ho
do
lo
g
ies
Pre
v
io
u
s
ly
,
r
esear
ch
h
as
b
ee
n
lar
g
ely
f
o
cu
s
ed
o
n
m
ax
im
u
m
ac
cu
r
ac
y
v
ia
e
n
s
em
b
le
m
o
d
els,
d
ee
p
-
lear
n
in
g
a
n
d
c
o
m
p
lex
h
y
p
e
r
p
ar
am
eter
co
m
b
i
n
atio
n
s
[
2
5
]
.
Alth
o
u
g
h
th
ese
m
eth
o
d
s
p
r
o
v
id
e
e
x
ce
llen
t
p
er
f
o
r
m
an
ce
,
th
ey
m
o
s
tly
d
o
n
o
t
h
av
e
a
way
to
d
ea
l
with
h
ig
h
-
r
is
k
b
o
r
d
er
lin
e
ca
s
es.
I
t
is
co
m
p
lem
en
tar
y
to
p
r
ev
io
u
s
w
o
r
k
in
th
at
it
s
tar
ts
with
a
s
tatis
tical
m
o
d
el
p
r
e
p
ar
ed
u
s
in
g
e
x
is
tin
g
tech
n
iq
u
es
an
d
p
r
o
v
i
d
es
an
av
en
u
e
f
o
r
p
r
ac
tical
im
p
r
o
v
e
m
en
t o
f
p
r
ed
ictio
n
s
in
s
u
c
h
ca
s
es
[
2
6
]
.
3.
M
E
T
H
O
DO
L
O
G
Y
3
.
1
.
Da
t
a
s
et
a
nd
prepro
ce
s
s
i
ng
T
h
e
Pima
I
n
d
ian
d
iab
etes
d
at
aset,
also
k
n
o
wn
as
Pima
[
1
]
,
is
a
well
-
k
n
o
wn
d
ataset
in
p
r
ed
ictiv
e
m
o
d
elin
g
f
o
r
d
ia
b
etes
r
is
k
.
I
t
co
n
tain
s
7
6
8
s
am
p
les,
h
a
v
in
g
8
clin
ical
f
ea
tu
r
es
in
clu
d
in
g
clin
ical
attr
ib
u
tes
s
u
ch
as
g
lu
c
o
s
e
lev
els,
b
l
o
o
d
p
r
ess
u
r
e,
b
o
d
y
m
ass
in
d
ex
,
an
d
ag
e.
T
h
e
tar
g
et
v
ar
iab
le
(
“Ou
tco
m
e”
)
is
ca
teg
o
r
ical
an
d
tells
wh
eth
er
th
e
p
atien
t
h
as
d
iab
etes
(
0
=
n
o
,
1
=
y
es)
T
o
en
s
u
r
e
th
e
co
n
s
is
ten
cy
an
d
r
eliab
ilit
y
o
f
th
e
d
ata,
Data
p
r
e
p
r
o
ce
s
s
in
g
was
p
er
f
o
r
m
e
d
.
T
h
is
in
clu
d
ed
d
ea
lin
g
with
m
is
s
in
g
v
alu
es,
s
ca
lin
g
f
ea
tu
r
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
3
3
-
4
9
4
1
4936
with
th
e
s
tan
d
ar
d
Scaler
to
n
o
r
m
alize
f
o
r
s
ca
le
d
if
f
er
en
ce
s
an
d
s
p
litt
in
g
th
e
d
ataset
in
to
8
0
%
tr
ain
in
g
an
d
2
0
%
test
in
g
s
u
b
s
ets f
o
r
a
s
o
lid
m
o
d
el
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
.
3
.
2
.
L
o
g
is
t
ic
re
g
re
s
s
io
n ba
s
eline
T
h
is
s
tu
d
y
ad
o
p
ts
LR
as
th
e
b
aselin
e
m
o
d
el
b
ec
a
u
s
e
o
f
its
s
im
p
licity
,
in
ter
p
r
etab
ilit
y
,
an
d
ac
ce
p
tab
le
ac
cu
r
ac
y
co
m
p
ar
ed
to
o
th
e
r
m
o
d
els
test
ed
in
in
itial
co
m
p
ar
is
o
n
s
u
s
in
g
.
T
h
e
m
o
d
el
w
as
tr
ain
ed
u
s
in
g
th
e
tr
ain
in
g
s
u
b
s
et
o
f
th
e
Pima
d
ataset
an
d
test
ed
u
s
in
g
th
e
(
)
m
eth
o
d
with
a
d
ef
au
lt
d
ec
is
io
n
th
r
esh
o
ld
o
f
0
.
5
,
wh
e
r
e
p
r
o
b
ab
ilit
ies
ab
o
v
e
t
h
is
th
r
esh
o
ld
in
d
icate
a
p
o
s
itiv
e
d
iab
etes
d
iag
n
o
s
is
.
B
aselin
e
p
er
f
o
r
m
an
ce
m
et
r
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
th
e
co
n
f
u
s
io
n
m
atr
ix
we
r
e
c
o
m
p
u
ted
to
p
r
o
v
i
d
e
a
r
ef
er
en
ce
p
o
in
t a
g
ain
s
t w
h
ich
th
e
p
r
o
p
o
s
ed
c
o
r
r
ec
tio
n
m
et
h
o
d
was e
v
alu
ated
.
3
.
3
.
P
r
o
ba
bil
it
y
-
ba
s
ed
co
rr
ec
t
io
n
T
h
is
s
t
u
d
y
p
r
ese
n
ts
a
p
r
o
b
a
b
i
lit
y
-
b
as
e
d
c
o
r
r
ec
ti
o
n
a
p
p
r
o
ac
h
as
its
m
ai
n
in
n
o
v
ati
o
n
.
A
n
y
p
r
e
d
ic
ti
o
n
d
e
em
ed
to
b
e
b
etw
ee
n
0
.
4
a
n
d
0
.
6
is
tr
ea
t
e
d
as
cl
o
u
d
y
.
T
h
es
e
ca
s
es
w
h
ic
h
ar
e
o
n
t
h
e
b
o
r
d
e
r
li
n
e
ar
e
l
ea
s
t
li
k
el
y
to
b
e
c
lass
i
f
i
ed
c
o
r
r
ec
t
ly
as
t
h
e
y
ar
e
v
e
r
y
cl
o
s
e
to
t
h
e
t
h
r
e
s
h
o
ld
o
f
t
h
e
d
ec
is
io
n
b
o
u
n
d
ar
y
.
T
o
a
d
j
u
s
t
t
h
ese
p
r
e
d
ic
ti
o
n
s
,
t
h
ei
r
la
b
e
ls
we
r
e
f
li
p
p
e
d
t
o
t
h
e
o
p
p
o
s
i
te
c
lass
d
u
e
t
o
t
h
e
h
y
p
o
th
esis
t
h
at
h
i
g
h
-
r
is
k
p
r
o
p
o
r
ti
o
n
s
in
d
ic
at
e
a
p
o
s
s
i
b
l
e
m
is
t
a
k
e
.
T
h
is
was
f
o
ll
o
w
ed
b
y
ass
ess
i
n
g
th
e
ch
a
n
g
es
i
n
p
r
e
d
i
cti
o
n
q
u
a
lit
y
wi
th
r
es
p
ec
t
t
o
th
e
t
est
s
et
,
ass
ess
i
n
g
t
h
e
a
cc
u
r
ac
y
,
f
als
e
p
o
s
it
iv
e,
a
n
d
f
a
ls
e
n
e
g
a
ti
v
e
im
p
r
o
v
em
en
ts
m
a
d
e
f
o
r
t
h
e
co
r
r
e
cte
d
p
r
e
d
ic
ti
o
n
s
.
T
o
q
u
a
n
ti
f
y
th
is
c
o
r
r
ec
ti
o
n
wit
h
t
h
e
u
p
d
a
te
d
co
n
f
u
s
io
n
m
at
r
i
x
v
a
lu
es
a
n
d
a
cc
u
r
ac
y
co
m
p
a
r
is
o
n
.
4.
RE
SU
L
T
S
4
.
1
.
M
o
del
co
m
pa
riso
n us
in
g
P
y
Ca
re
t
T
o
co
m
p
ar
e
d
if
f
e
r
en
t
class
if
icatio
n
m
o
d
els
an
d
cr
ea
te
a
b
aselin
e
f
o
r
th
e
s
tu
d
y
,
we
a
p
p
lied
Py
C
ar
et’
s
au
to
m
ated
m
ac
h
in
e
lear
n
in
g
f
r
am
ewo
r
k
f
o
r
p
r
elim
in
a
r
y
a
n
aly
s
is
.
T
ab
le
1
p
r
esen
t
p
er
f
o
r
m
an
ce
o
f
v
ar
io
u
s
m
o
d
els
u
s
ed
in
th
is
an
aly
s
is
,
ac
co
r
d
in
g
to
a
cc
u
r
ac
y
,
ar
e
a
u
n
d
er
t
h
e
cu
r
v
e
(
AUC),
r
ec
all,
p
r
ec
is
io
n
an
d
F1
-
s
co
r
e.
Hen
ce
,
th
e
b
est
m
o
d
el
LR
r
ec
o
r
d
s
th
e
ac
cu
r
ac
y
h
ig
h
est
wh
ich
is
(
7
6
.
0
3
%)
a
n
d
AUC
(
8
2
.
0
1
%)
Als
o
,
b
ec
au
s
e
o
f
its
s
im
p
licity
an
d
ea
s
e
o
f
in
ter
p
r
etab
ilit
y
,
LR
was
ju
s
tifie
d
to
b
e
a
g
o
o
d
ca
n
d
id
ate
to
ap
p
ly
th
e
p
r
o
p
o
s
ed
p
r
o
b
a
b
ilit
y
-
b
ased
co
r
r
ec
tio
n
m
eth
o
d
o
lo
g
y
b
ea
r
in
m
in
d
th
at
th
ese
r
esu
lts
wer
e
o
b
tain
ed
with
o
u
t
m
ak
in
g
an
y
ch
an
g
es
to
th
e
d
ataset
th
at
wa
s
d
o
wn
lo
ad
ed
f
r
o
m
th
e
s
o
u
r
ce
.
W
e
d
id
n
o
t
a
p
p
ly
an
y
a
d
v
an
ce
d
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
en
g
in
e
er
in
g
o
r
h
y
p
er
p
a
r
am
eter
tu
n
in
g
to
im
p
r
o
v
e
p
r
e
d
ictiv
e
p
o
we
r
as
h
ad
b
ee
n
d
o
n
e
in
ea
r
lier
s
tu
d
ies.
T
h
is
m
eth
o
d
was
in
ten
tio
n
ally
s
elec
ted
s
o
as
to
ex
am
in
e
th
e
co
r
r
ec
tio
n
p
r
o
ce
s
s
in
s
tead
o
f
attain
in
g
m
ax
im
u
m
ac
cu
r
ac
y
.
T
ab
le
1
.
Mo
d
el
co
m
p
ar
is
o
n
r
e
s
u
lts
u
s
in
g
Py
C
ar
et
M
o
d
e
l
A
c
c
u
r
a
c
y
(
%)
A
U
C
(
%)
R
e
c
a
l
l
(
%)
P
r
e
c
i
s
i
o
n
(
%)
F1
-
S
c
o
r
e
(
%)
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
7
6
.
0
3
8
2
.
0
1
5
4
.
1
8
7
1
.
6
3
6
1
.
0
1
R
i
d
g
e
c
l
a
ss
i
f
i
e
r
7
5
.
8
7
8
2
.
2
0
5
4
.
1
8
7
1
.
1
5
6
0
.
8
4
Li
n
e
a
r
d
i
scri
m
i
n
a
n
t
a
n
a
l
y
s
i
s
7
5
.
7
0
8
2
.
2
4
5
4
.
6
3
7
0
.
8
0
6
1
.
0
5
Ex
t
r
a
t
r
e
e
s
c
l
a
ssi
f
i
e
r
7
5
.
2
3
8
0
.
0
0
5
5
.
2
4
7
1
.
0
0
6
0
.
0
5
R
a
n
d
o
m f
o
r
e
s
t
c
l
a
ss
i
f
i
e
r
7
4
.
4
3
8
0
.
1
1
5
5
.
6
7
6
7
.
7
1
5
9
.
6
4
N
a
i
v
e
B
a
y
e
s
7
4
.
0
8
8
0
.
3
9
5
7
.
5
1
6
6
.
6
5
6
0
.
7
1
A
d
a
b
o
o
s
t
c
l
a
s
si
f
i
e
r
7
3
.
7
7
7
8
.
3
9
5
8
.
0
1
6
4
.
7
4
5
9
.
8
4
Q
u
a
d
r
a
t
i
c
d
i
scri
mi
n
a
n
t
a
n
a
l
y
s
i
s
7
3
.
5
9
7
9
.
2
6
5
6
.
0
6
6
5
.
0
0
5
9
.
5
0
G
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
c
l
a
ss
i
f
i
e
r
7
3
.
4
3
8
0
.
4
6
5
6
.
5
8
6
5
.
3
4
5
8
.
9
4
Li
g
h
t
G
B
M
7
3
.
1
2
7
7
.
9
2
5
5
.
1
7
6
4
.
5
1
5
8
.
7
3
X
G
B
o
o
st
7
2
.
6
2
7
7
.
2
3
5
6
.
5
6
6
3
.
9
8
5
9
.
1
1
K
n
e
i
g
h
b
o
r
s
c
l
a
ssi
f
i
e
r
7
2
.
3
1
7
3
.
3
8
5
4
.
3
1
6
2
.
2
7
5
6
.
9
5
D
e
c
i
s
i
o
n
t
r
e
e
c
l
a
ss
i
f
i
e
r
6
9
.
2
1
6
6
.
1
3
5
5
.
7
6
5
7
.
0
1
5
5
.
6
6
D
u
mm
y
c
l
a
ss
i
f
i
e
r
6
5
.
1
5
5
0
.
0
0
0
.
0
0
0
.
0
0
0
.
0
0
S
V
M
(
Li
n
e
a
r
k
e
r
n
e
l
)
5
8
.
4
7
5
5
.
2
3
3
6
.
6
5
4
5
.
6
7
3
8
.
0
7
4
.
2
.
I
nitia
l
p
er
f
o
r
m
a
nce
T
h
e
LR
m
o
d
el
was
ev
alu
a
ted
o
n
th
e
test
d
ataset
with
o
u
t
an
y
ad
v
a
n
ce
d
p
r
ep
r
o
c
ess
in
g
o
r
h
y
p
er
p
ar
am
eter
t
u
n
in
g
.
T
h
is
e
v
alu
atio
n
y
ield
ed
a
b
aselin
e
a
cc
u
r
ac
y
o
f
7
6
%,
wh
ich
s
er
v
es a
s
th
e
r
ef
er
en
c
e
f
o
r
f
u
r
th
er
im
p
r
o
v
em
en
t.
T
h
e
r
esu
ltin
g
co
n
f
u
s
io
n
m
atr
ix
s
h
o
wn
in
Fig
u
r
e
1
h
ig
h
lig
h
ted
t
h
e
m
o
d
el'
s
lim
itatio
n
s
,
esp
ec
ially
in
d
is
tin
g
u
is
h
in
g
d
iab
etic
ca
s
es,
r
ev
ea
lin
g
1
8
f
alse
n
eg
ativ
es
an
d
2
1
f
al
s
e
p
o
s
itiv
es,
th
u
s
m
o
tiv
atin
g
th
e
n
ee
d
f
o
r
a
c
o
r
r
ec
tio
n
m
ec
h
an
is
m
.
L
o
o
k
in
g
at
th
e
m
atr
i
x
,
th
e
m
o
d
el
ca
n
p
r
ed
ict
n
o
n
-
d
iab
e
tic
ca
s
es
well,
it
i
s
s
til
l
h
av
in
g
is
s
u
es
id
en
tify
in
g
d
iab
etic
ca
s
es (
i.e
.
,
1
8
f
alse n
eg
ativ
es a
n
d
2
1
f
alse p
o
s
itiv
es).
T
h
e
latter
r
esu
lts
d
r
aw
th
e
lim
itatio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
d
ia
b
etes p
r
ed
ictio
n
th
r
o
u
g
h
p
r
o
b
a
b
ilit
y
-
b
a
s
ed
…
(
A
ito
u
h
a
n
n
i I
ma
n
e
)
4937
o
f
th
e
m
o
d
el
at
h
ig
h
-
r
is
k
b
o
r
d
er
lin
e
ca
s
es.
T
h
is
p
e
r
f
o
r
m
an
c
e
is
also
d
u
e
to
th
e
n
o
is
in
ess
o
f
th
e
d
ataset
its
elf
,
as
n
o
p
r
ep
r
o
ce
s
s
in
g
o
r
f
ea
tu
r
e
en
g
in
ee
r
in
g
s
tep
s
wer
e
ap
p
lied
to
clea
n
th
e
i
n
p
u
t
f
ea
tu
r
es.
Ho
wev
er
,
t
h
is
b
aselin
e
ass
e
s
s
m
en
t
p
r
o
v
id
es
a
r
ef
er
en
ce
p
o
i
n
t
to
ev
alu
ate
th
e
im
p
o
r
tan
ce
o
f
th
e
p
r
o
b
ab
ilit
y
-
b
ased
co
r
r
ec
tio
n
ap
p
r
o
ac
h
.
Fig
u
r
e
1
.
I
n
itial c
o
n
f
u
s
io
n
m
at
r
ix
f
o
r
LR
m
o
d
el
4
.
3
.
P
o
s
t
-
co
rr
ec
t
i
o
n per
f
o
r
m
a
nce
Ap
p
ly
in
g
th
e
p
r
o
b
ab
ilit
y
-
b
ase
d
co
r
r
ec
tio
n
m
eth
o
d
led
to
a
n
im
p
r
o
v
em
e
n
t
in
th
e
m
o
d
el'
s
ac
cu
r
ac
y
f
r
o
m
7
6
%
to
8
1
%.
T
h
e
co
r
r
e
ctio
n
tar
g
eted
p
r
e
d
ictio
n
s
with
in
th
e
0
.
4
to
0
.
6
p
r
o
b
ab
ilit
y
r
an
g
e
as
s
h
o
wn
in
Fig
u
r
e
2
an
d
s
u
cc
ess
f
u
lly
r
e
d
u
ce
d
f
alse
p
o
s
itiv
es
f
r
o
m
2
1
to
2
0
an
d
f
alse
n
eg
ativ
es
f
r
o
m
1
8
to
1
5
.
T
h
is
ad
ju
s
tm
en
t
h
ig
h
lig
h
ts
th
e
ef
f
ec
tiv
en
ess
o
f
r
ef
in
in
g
b
o
r
d
e
r
lin
e
p
r
ed
ictio
n
s
an
d
illu
s
tr
ate
s
th
e
p
o
ten
tial
f
o
r
im
p
r
o
v
in
g
th
e
m
o
d
el’
s
clin
ica
l r
eliab
ilit
y
with
o
u
t a
d
d
itio
n
al
p
r
ep
r
o
ce
s
s
in
g
o
r
f
ea
t
u
r
e
en
g
in
ee
r
in
g
.
Fig
u
r
e
2
.
C
o
r
r
ec
te
d
co
n
f
u
s
io
n
m
atr
ix
f
o
r
LR
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
3
3
-
4
9
4
1
4938
T
h
e
m
eth
o
d
co
n
ce
n
tr
ated
o
n
lo
w
-
r
is
k
s
p
ac
e
(
p
r
o
b
a
b
ilit
ies
b
etwe
en
0
.
4
an
d
0
.
6
)
an
d
s
u
cc
ess
f
u
lly
d
ec
r
ea
s
ed
f
alse
p
o
s
itiv
e
f
r
o
m
2
1
to
2
0
a
n
d
f
alse
n
eg
ativ
es
f
r
o
m
1
8
to
1
5
.
T
h
is
ad
j
u
s
tm
en
t
s
h
o
wca
s
es
h
o
w
well
th
e
ap
p
r
o
ac
h
ca
n
ad
ju
s
t
m
o
d
el
p
r
ed
ictio
n
s
wh
en
class
if
icatio
n
th
r
esh
o
l
d
s
ar
e
n
o
t
en
o
u
g
h
.
T
h
e
s
im
p
licity
an
d
s
tr
aig
h
tf
o
r
war
d
n
atu
r
e
o
f
th
is
co
r
r
ec
tio
n
m
et
h
o
d
is
o
n
e
o
f
its
k
ey
ad
v
an
tag
es.
T
h
is
ap
p
r
o
ac
h
d
o
es
n
o
t
r
eq
u
ir
e
s
ig
n
if
ican
t
f
ea
tu
r
e
en
g
in
ee
r
in
g
,
ex
te
n
s
iv
e
p
r
e
p
r
o
ce
s
s
in
g
,
o
r
h
y
p
e
r
p
ar
a
m
eter
o
p
ti
m
izatio
n
as
is
th
e
ca
s
e
with
m
an
y
m
o
r
e
c
o
m
p
u
tatio
n
ally
in
ten
s
iv
e
tech
n
iq
u
es.
I
t
u
s
es
th
e
m
o
d
el
p
r
o
b
ab
ilit
y
s
co
r
es
to
f
in
d
an
d
tack
le
th
e
u
n
ce
r
tai
n
class
if
icat
io
n
s
in
s
tead
.
W
ith
th
is
co
r
r
ec
tio
n
,
b
o
r
d
er
l
in
e
ca
s
es
b
ec
o
m
e
th
e
f
o
c
u
s
.
T
h
is
m
ak
es
s
en
s
e
in
th
e
r
ea
l
wo
r
ld
,
esp
ec
ially
in
h
ea
lth
ca
r
e
s
ettin
g
s
th
at
co
u
ld
lead
to
d
is
astro
u
s
f
alse
p
o
s
itiv
e
an
d
n
eg
ativ
e
d
iag
n
o
s
es.
Alth
o
u
g
h
th
e
im
p
r
o
v
em
e
n
t
in
ac
cu
r
ac
y
is
n
o
t
d
r
am
atic,
th
e
d
ec
r
ea
s
ed
n
u
m
b
er
o
f
m
is
class
if
icatio
n
s
s
u
g
g
ests
th
e
p
o
ten
tial
f
o
r
th
e
m
et
h
o
d
to
i
m
p
r
o
v
e
co
n
f
id
en
ce
i
n
d
ec
is
io
n
s
.
W
h
ile
th
is
is
tr
u
e
f
o
r
alm
o
s
t
ev
er
y
d
ataset,
it
h
o
ld
s
p
a
r
ticu
lar
ly
if
th
e
d
atas
et
is
n
o
is
y
lik
e
th
e
Pima
I
n
d
i
an
Diab
etes
d
ataset
wh
e
r
e
i
n
tr
in
s
ic
u
n
ce
r
tain
ties
ca
n
h
id
e
m
ea
n
in
g
f
u
l p
atter
n
s
.
4
.
4
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
T
o
ass
ess
h
o
w
a
co
r
r
ec
tio
n
b
ased
o
n
p
r
o
b
ab
ilit
ies
af
f
e
cts
class
if
icatio
n
p
er
f
o
r
m
a
n
c
e,
T
ab
le
2
co
m
p
ar
es
r
elev
a
n
t
class
if
icati
o
n
m
etr
ics
with
an
d
with
o
u
t
co
r
r
ec
tio
n
.
T
h
is
ap
p
r
o
ac
h
p
r
o
v
ed
e
f
f
ec
tiv
e
in
lo
wer
in
g
f
alse
class
if
icatio
n
s
an
d
r
esu
lted
in
b
etter
o
v
er
all
ac
cu
r
ac
y
.
T
h
e
c
o
m
p
ar
ativ
e
s
tu
d
y
clea
r
ly
d
em
o
n
s
tr
ates
th
e
s
tr
en
g
th
o
f
th
e
co
r
r
ec
tio
n
p
r
o
ce
s
s
b
a
s
ed
o
n
th
e
p
r
o
b
ab
ilit
y
.
I
n
co
n
tr
ast
to
o
t
h
er
m
eth
o
d
o
l
o
g
ies
th
at
d
ep
en
d
o
n
d
ataset
p
er
tu
r
b
atio
n
s
o
r
tu
n
in
g
,
th
is
m
eth
o
d
o
lo
g
y
o
n
ly
u
s
es
o
u
tp
u
ts
f
r
o
m
p
r
e
-
ex
is
tin
g
m
o
d
els
to
f
o
cu
s
o
n
p
ar
ticu
lar
h
ig
h
-
r
is
k
ca
s
es.
T
h
e
b
etter
m
etr
ics
h
ig
h
lig
h
t
h
o
w
th
is
m
eth
o
d
ca
n
au
g
m
en
t
th
e
estab
lis
h
ed
q
u
a
n
titi
es
o
f
m
ac
h
in
e
lear
n
in
g
,
esp
ec
ially
wh
en
d
ataset
lim
itatio
n
o
r
co
m
p
lex
ity
m
ak
e
it
im
p
r
ac
tical
to
o
p
tim
ize
th
ese
d
ir
ec
tly
.
T
ab
le
2
s
u
m
m
ar
izes
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
b
ef
o
r
e
an
d
af
te
r
th
e
co
r
r
ec
tio
n
m
eth
o
d
o
lo
g
y
.
T
h
e
p
r
o
b
ab
ilit
y
-
b
ased
c
o
r
r
e
ctio
n
im
p
r
o
v
ed
th
e
r
eliab
ilit
y
o
f
th
e
m
o
d
el
b
y
r
ed
u
cin
g
f
alse
p
o
s
itiv
es
an
d
f
alse
n
eg
ativ
es.
On
ce
m
o
r
e,
it
m
u
s
t
b
e
em
p
h
asized
-
n
eith
er
t
h
e
o
r
ig
in
al
d
ataset
was
alter
ed
,
n
o
r
t
h
e
h
y
p
er
p
ar
am
eter
s
o
f
th
e
L
R
m
o
d
el.
T
h
is
is
co
n
s
is
ten
t
with
o
u
r
f
o
cu
s
in
th
is
s
tu
d
y
o
n
s
h
o
win
g
th
e
v
al
u
e
o
f
t
h
e
co
r
r
e
ctio
n
m
eth
o
d
as o
p
p
o
s
ed
to
o
b
tain
in
g
a
n
ea
r
o
p
tim
al
m
o
d
el.
T
ab
le
2
.
C
o
m
p
a
r
ativ
e
p
er
f
o
r
m
an
ce
m
etr
ics
M
e
t
r
i
c
I
n
i
t
i
a
l
p
e
r
f
o
r
m
a
n
c
e
P
o
st
-
c
o
r
r
e
c
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
A
c
c
u
r
a
c
y
7
5
%
8
1
%
Tr
u
e
p
o
si
t
i
v
e
s
37
86
Tr
u
e
n
e
g
a
t
i
v
e
s
78
79
F
a
l
se
p
o
si
t
i
v
e
s
21
20
F
a
l
se
n
e
g
a
t
i
v
e
s
18
15
5.
DIS
CU
SS
I
O
N
5
.
1
.
I
m
pli
ca
t
i
o
ns
o
f
r
esu
lt
s
T
h
e
co
n
ce
p
t
o
f
co
r
r
ec
tin
g
m
o
d
els
b
ased
o
n
p
r
o
b
a
b
ilit
ies
p
r
o
p
o
s
ed
in
th
is
s
tu
d
y
s
h
o
ws
th
at
it
ca
n
s
er
v
e
as a
v
alu
ab
le
en
h
an
ce
m
e
n
t m
eth
o
d
f
o
r
p
r
ed
ictiv
e
m
o
d
e
lin
g
.
T
h
e
g
ain
f
r
o
m
7
5
% to
8
1
% o
v
er
all
m
ay
n
o
t
s
ee
m
im
p
r
ess
iv
e,
h
o
wev
er
g
i
v
en
th
e
s
ig
n
if
ican
t
s
av
in
g
s
as
s
o
ciate
d
with
m
is
class
if
icatio
n
s
,
tar
g
etin
g
h
ig
h
-
r
is
k
,
b
o
r
d
e
r
lin
e
p
r
e
d
ictio
n
s
d
e
s
p
ite
th
e
m
o
d
est
ac
cu
r
ac
y
g
ai
n
,
is
a
r
ea
s
o
n
ab
le
s
o
lu
tio
n
.
R
e
d
u
cin
g
th
e
n
u
m
b
er
o
f
f
alse
p
o
s
itiv
es
an
d
f
alse
n
eg
ativ
es
in
p
r
ac
tical
clin
ical
s
e
ttin
g
s
ca
n
h
av
e
s
ig
n
if
ican
t
im
p
licatio
n
s
,
as
in
th
e
ca
s
e
o
f
d
iab
etes w
h
er
e
tim
ely
an
d
co
r
r
ec
t d
etec
tio
n
is
ess
en
tial.
T
h
e
p
r
o
p
o
s
ed
co
r
r
ec
tio
n
tech
n
iq
u
e
d
em
o
n
s
tr
ates
th
at
tar
g
eted
ad
ju
s
tm
en
ts
b
ased
o
n
p
r
ed
ictio
n
p
r
o
b
a
b
ilit
ies
ca
n
s
ig
n
if
ican
tly
en
h
a
n
ce
d
ec
is
io
n
-
m
a
k
in
g
r
eliab
ilit
y
in
clin
ical
s
ettin
g
s
.
W
h
ile
th
e
o
v
er
all
ac
cu
r
ac
y
im
p
r
o
v
em
en
t
o
f
6
%
m
ig
h
t
s
ee
m
m
o
d
est,
th
e
r
ed
u
ctio
n
in
m
is
class
if
icat
io
n
s
c
an
h
av
e
a
p
r
o
f
o
u
n
d
im
p
ac
t,
esp
ec
ially
in
h
ig
h
-
r
is
k
m
ed
ical
co
n
d
itio
n
s
lik
e
d
iab
e
tes.
T
h
is
s
im
p
le
y
et
ef
f
ec
tiv
e
m
eth
o
d
p
r
o
v
i
d
es
a
v
iab
le
en
h
a
n
ce
m
en
t
to
o
l
th
at
in
teg
r
ates
s
ea
m
less
ly
in
to
ex
is
tin
g
m
ac
h
in
e
lear
n
in
g
p
ip
eli
n
es,
o
f
f
er
i
n
g
g
r
ea
ter
co
n
f
id
en
ce
in
th
e
p
r
ed
ictiv
e
o
u
tp
u
t.
T
h
is
ap
p
r
o
ac
h
r
eso
lv
es
a
co
m
m
o
n
b
o
ttlen
ec
k
in
m
o
s
t
m
ac
h
in
e
lear
n
in
g
(
ML
)
m
o
d
els
d
u
e
to
u
n
d
er
-
p
er
f
o
r
m
in
g
f
o
r
s
am
p
le
s
th
at
ar
e
at
th
e
d
ec
is
io
n
b
o
u
n
d
a
r
ies.
T
h
e
p
r
o
p
o
s
ed
co
r
r
ec
tio
n
f
r
a
m
ewo
r
k
im
p
r
o
v
es
d
ec
is
io
n
r
eliab
ilit
y
b
y
u
s
in
g
p
r
o
b
ab
ilit
y
s
co
r
es
to
co
r
r
ec
t
s
u
ch
p
r
e
d
ictio
n
s
with
o
u
t
an
y
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
e
n
g
in
e
er
in
g
,
o
r
m
o
d
el
tu
n
i
n
g
o
v
er
th
e
o
r
ig
in
al
m
o
d
els.
Su
ch
ap
p
licatio
n
s
ar
e
v
er
y
ap
p
licab
le
to
n
o
is
y
d
atasets
l
ik
e
th
e
Pima
I
n
d
ian
Diab
etes
d
ataset,
f
o
r
wh
ich
th
e
t
r
ad
it
io
n
al
o
p
tim
izatio
n
tech
n
iq
u
es m
ig
h
t
n
o
t p
e
r
f
o
r
m
well.
I
n
ad
d
itio
n
,
t
h
is
m
eth
o
d
o
f
f
er
s
a
s
tr
u
ctu
r
e
wh
ich
ca
n
f
it
s
ea
m
less
ly
in
to
cu
r
r
e
n
t
p
r
ed
ictiv
e
p
ip
elin
es.
I
t
is
a
g
r
ea
t
ass
et
f
o
r
h
ea
lth
ca
r
e
p
r
o
f
ess
io
n
als
an
d
d
ata
s
cien
t
is
ts
to
im
p
r
o
v
e
th
eir
m
o
d
els,
s
tay
in
g
as
s
im
p
le
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
d
ia
b
etes p
r
ed
ictio
n
th
r
o
u
g
h
p
r
o
b
a
b
ilit
y
-
b
a
s
ed
…
(
A
ito
u
h
a
n
n
i I
ma
n
e
)
4939
p
o
s
s
ib
le
an
d
av
o
id
in
g
co
m
p
u
t
atio
n
al
co
m
p
lex
ity
.
T
h
is
co
r
r
ec
tio
n
m
eth
o
d
o
lo
g
y
b
ased
o
n
p
r
o
b
a
b
ilit
ies
lo
o
k
s
p
r
o
m
is
in
g
as
an
ad
d
itio
n
al
co
m
p
lem
en
tar
y
en
h
an
ce
m
e
n
t
tech
n
iq
u
e.
Desp
ite
a
m
o
d
est
im
p
r
o
v
em
en
t
in
o
v
er
all
ac
cu
r
ac
y
(
6
%),
th
e
i
n
cr
ea
s
e
in
s
p
ec
if
icity
f
o
r
m
is
class
if
icati
o
n
em
p
h
asizes
th
e
clin
ical
r
el
ev
an
ce
o
f
th
e
m
o
d
el
as,
in
clin
ical
p
r
ac
tice,
a
h
ig
h
f
alse d
iag
n
o
s
is
m
ay
cr
itically
d
eter
m
in
e
p
atien
t o
u
tco
m
e.
5
.
2
.
Co
m
pa
riso
n
wit
h pre
v
io
us
s
t
ud
ie
s
T
h
is
r
esear
ch
tak
es
a
co
m
p
let
ely
d
if
f
er
e
n
t
ap
p
r
o
ac
h
co
m
p
a
r
ed
to
m
an
y
p
r
e
v
io
u
s
s
tu
d
ies
th
at
f
o
cu
s
o
n
o
b
tain
in
g
s
tate
-
of
-
t
h
e
-
ar
t
a
cc
u
r
ac
y
[
2
7
]
,
u
s
u
ally
t
h
r
o
u
g
h
en
s
em
b
le
m
eth
o
d
s
o
r
d
ee
p
lea
r
n
in
g
.
R
ath
er
t
h
an
ad
ju
s
tin
g
th
e
d
ataset,
p
er
f
o
r
m
i
n
g
h
ea
v
y
f
ea
tu
r
e
en
g
in
ee
r
in
g
,
o
r
f
i
n
e
-
tu
n
in
g
m
o
d
el
h
y
p
e
r
p
ar
am
eter
s
,
we
aim
e
d
to
im
p
r
o
v
e
m
o
d
el
in
ter
p
r
eta
b
ilit
y
an
d
r
eliab
ilit
y
b
y
m
itig
atin
g
th
e
h
ig
h
-
r
is
k
p
r
ed
ict
io
n
s
.
Sp
ec
if
ically
,
en
s
em
b
le
tech
n
iq
u
es
ar
e
p
o
we
r
f
u
l
b
u
t
f
all
s
h
o
r
t
in
ter
m
s
o
f
t
r
an
s
p
ar
en
cy
an
d
a
d
ap
tab
ilit
y
—
im
p
o
r
tan
t
asp
ec
ts
wh
en
it c
o
m
es to
h
i
g
h
-
s
tak
es
ap
p
licatio
n
s
s
u
ch
as h
ea
lth
ca
r
e.
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
[
2
8
]
co
n
tr
ib
u
te
to
th
e
ex
is
tin
g
liter
atu
r
e
o
n
d
ia
b
etes
p
r
e
d
ictio
n
b
y
d
em
o
n
s
tr
atin
g
im
p
r
o
v
em
en
ts
in
p
e
r
f
o
r
m
an
ce
with
o
u
t
n
ee
d
in
g
to
o
v
er
h
a
u
l
th
e
d
at
aset
o
r
r
eso
r
t
to
co
m
p
u
tatio
n
ally
ex
p
e
n
s
iv
e
a
lg
o
r
ith
m
s
.
T
h
is
u
n
ce
r
tain
ty
-
a
war
e
ad
ju
s
tm
en
t
s
tr
ateg
y
co
r
r
ec
tio
n
b
ased
o
n
p
r
o
b
a
b
ilit
ies
th
at
atten
tiv
e
f
in
e
-
tu
n
in
g
o
f
p
r
e
d
ictio
n
s
in
u
n
c
er
tain
ar
ea
s
r
ath
er
th
a
n
b
o
u
n
d
in
g
was
ce
n
tu
r
ies
in
th
e
s
ce
n
e
la
n
g
u
a
g
e
d
ed
icate
d
to
ex
tr
em
ity
r
ec
o
n
s
tr
u
ctio
n
.
T
h
is
co
n
n
ec
ts
a
v
o
id
in
t
h
e
liter
atu
r
e
b
y
d
escr
ib
in
g
a
p
r
ac
tical
lig
h
t
-
weig
h
t
ap
p
r
o
ac
h
th
at
m
atch
es
s
o
m
e
o
f
th
e
p
r
ac
titi
o
n
er
s
ap
p
lied
n
ee
d
.
W
h
ile
s
tu
d
ies
lik
e
[
2
9
]
–
[
3
3
]
th
at
g
iv
e
h
i
g
h
er
ac
c
u
r
ac
y
th
r
o
u
g
h
en
s
em
b
le
m
eth
o
d
s
o
r
d
ee
p
lea
r
n
in
g
,
th
is
s
tu
d
y
im
p
r
o
v
es
e
x
is
tin
g
m
o
d
els
th
at
g
en
er
ate
u
n
ce
r
tai
n
p
r
ed
ictio
n
s
.
I
t
is
n
o
t
in
ten
d
e
d
b
e
a
s
tate
-
of
-
th
e
-
ar
t
r
ep
lace
m
en
t,
r
ath
er
it
is
an
in
ten
d
ed
a
u
g
m
en
tatio
n
an
d
tar
g
eted
s
o
lu
tio
n
f
o
r
s
h
o
r
tco
m
in
g
s
.
5
.
3
.
L
im
it
a
t
io
ns
a
nd
f
uture
wo
rk
Alth
o
u
g
h
th
is
ap
p
r
o
ac
h
is
p
r
o
m
is
in
g
,
th
is
s
tu
d
y
h
as
l
im
itatio
n
s
,
an
d
we
en
co
u
r
a
g
e
f
u
r
th
er
ex
p
lo
r
atio
n
.
First,
it
was
r
u
n
o
n
o
n
e
m
o
d
el
LR
,
a
n
d
it
is
u
n
k
n
o
wn
i
f
it
wo
u
ld
wo
r
k
o
n
a
m
o
r
e
c
o
m
p
lex
alg
o
r
ith
m
s
u
c
h
as
RF
o
r
G
r
a
d
ien
t
b
o
o
s
tin
g
m
ac
h
in
es
.
Sec
o
n
d
,
we
d
id
n
o
t
g
en
e
r
alize
th
e
p
r
o
b
ab
ilit
y
r
a
n
g
e
[
0
.
4
to
0
.
6
]
f
o
r
p
r
ed
ictin
g
h
ig
h
-
r
is
k
em
p
ir
ically
an
d
th
e
r
ef
o
r
e
m
ay
n
o
t
ap
p
ly
o
th
e
r
d
atasets
o
r
co
n
tex
ts
.
An
in
ter
esti
n
g
av
en
u
e
f
o
r
f
u
tu
r
e
wo
r
k
is
to
ex
p
an
d
th
is
to
d
y
n
am
ic
t
h
r
esh
o
ld
s
elec
tio
n
m
eth
o
d
s
,
to
b
etter
d
eter
m
in
e
th
is
r
an
g
e.
T
h
is
s
tu
d
y
also
d
id
n
o
t
u
s
e
m
o
r
e
ad
v
a
n
ce
d
p
r
e
p
r
o
ce
s
s
in
g
o
r
f
ea
tu
r
e
-
en
g
in
ee
r
in
g
tech
n
iq
u
e
s
th
at
m
a
y
g
en
er
ally
u
p
lift
th
e
p
er
f
o
r
m
an
ce
b
aselin
e
o
f
t
h
e
m
o
d
el.
Fu
r
t
h
er
e
x
p
lo
r
atio
n
o
f
th
e
c
o
m
p
le
m
en
tar
y
n
atu
r
e
o
f
th
ese
tech
n
iq
u
es
with
t
h
e
p
r
o
p
o
s
ed
c
o
r
r
ec
tio
n
f
r
a
m
ewo
r
k
m
ay
r
ev
ea
l
m
o
r
e
o
f
its
v
al
u
e.
C
o
m
b
in
i
n
g
th
is
ap
p
r
o
ac
h
with
en
s
em
b
le
m
eth
o
d
s
o
r
d
ee
p
lear
n
in
g
m
o
d
els
co
u
ld
p
r
o
v
id
e
a
h
y
b
r
id
s
o
lu
t
io
n
th
at
m
ax
im
izes
in
ter
p
r
etab
ilit
y
,
p
e
r
f
o
r
m
an
ce
a
n
d
ef
f
icien
c
y
.
6.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
o
p
o
s
es
a
n
ew
m
eth
o
d
o
lo
g
y
f
o
r
co
r
r
ec
tin
g
t
h
e
d
is
tr
ib
u
tio
n
s
o
f
p
r
o
b
ab
ilit
ies
in
o
r
d
er
t
o
im
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
d
iab
etes
p
r
ed
ictio
n
m
o
d
els
b
y
em
p
h
asizin
g
p
ar
ticu
lar
p
r
ed
ictio
n
s
th
at
ar
e
b
o
r
d
er
li
n
e,
a
n
d
at
h
ig
h
r
is
k
,
wh
ich
n
o
r
m
ally
d
o
n
o
t
g
et
th
r
o
u
g
h
a
c
o
m
m
o
n
m
ac
h
in
e
-
lear
n
in
g
m
eth
o
d
.
B
ased
o
n
p
r
o
b
a
b
ilit
y
s
co
r
es
o
f
t
h
e
m
o
d
el
p
r
ed
ictio
n
s
,
th
is
ap
p
r
o
ac
h
p
r
o
v
id
es
a
n
e
f
f
ec
tiv
e
wa
y
to
in
c
r
ea
s
e
d
ec
is
io
n
r
eliab
ilit
y
wh
ile
n
o
t m
o
d
if
y
in
g
th
e
d
ataset
o
r
u
s
in
g
ex
p
en
s
iv
e
m
eth
o
d
s
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
co
r
r
ec
tio
n
b
ased
o
n
p
r
o
b
ab
ilit
ies
b
r
o
u
g
h
t
an
elev
atio
n
f
r
o
m
7
5
%
to
8
1
%
ac
cu
r
ac
y
to
t
h
e
lo
g
is
tic
r
eg
r
es
s
io
n
m
o
d
el,
a
s
m
all
b
u
t
s
ig
n
i
f
ican
t
in
cr
ea
s
e
co
n
s
id
er
in
g
th
e
r
an
d
o
m
n
ess
o
f
th
e
d
ata
an
d
th
e
a
b
s
en
ce
o
f
f
u
r
th
er
p
r
ep
r
o
ce
s
s
in
g
o
r
f
ea
tu
r
e
en
g
in
ee
r
in
g
.
T
h
e
b
etter
p
er
f
o
r
m
an
ce
s
h
o
ws
th
e
p
r
o
m
is
e
o
f
th
is
ap
p
r
o
ac
h
to
s
o
lv
e
m
is
class
if
icatio
n
s
in
im
p
o
r
tan
t
h
ea
lth
ca
r
e
p
r
o
b
lem
s
,
w
h
er
e
f
alse
d
iag
n
o
s
is
s
h
o
u
ld
b
e
a
v
o
id
e
d
as m
u
ch
as p
o
s
s
ib
le.
T
h
is
wo
r
k
co
n
tr
asts
with
ea
r
li
er
s
tu
d
ies
wh
o
s
e
f
o
cu
s
o
n
h
ig
h
ac
cu
r
ac
y
h
as
ten
d
e
d
to
b
e
attain
ed
with
co
m
p
lex
m
o
d
els
an
d
b
y
ex
ten
s
iv
e
o
p
tim
izatio
n
;
th
e
cu
r
r
en
t
r
esear
ch
s
tr
ess
es
s
im
p
licity
,
ad
ap
tab
ilit
y
,
an
d
th
e
p
o
ten
tial
f
o
r
ex
te
n
d
in
g
ex
is
tin
g
p
r
ed
ictiv
e
f
r
am
ewo
r
k
s
.
T
h
e
m
eth
o
d
o
lo
g
y
aim
s
n
o
t
to
r
ep
lace
a
n
y
o
f
th
e
s
o
p
h
is
ticated
alg
o
r
ith
m
s
b
u
t
to
s
u
p
p
lem
en
t
th
o
s
e
b
y
a
d
d
r
ess
in
g
h
ig
h
-
r
is
k
ca
s
es
th
at
ar
e
o
f
ten
b
ey
o
n
d
th
e
s
co
p
e
o
f
tr
a
d
itio
n
al
tech
n
i
q
u
es.
Fu
tu
r
e
wo
r
k
p
r
o
jects
in
clu
d
e
,
b
u
t
is
n
o
t
lim
ited
to
,
ex
ten
d
i
n
g
th
is
m
eth
o
d
o
lo
g
y
to
co
m
p
le
x
m
o
d
els,
ex
p
lo
r
in
g
f
u
tu
r
e
d
y
n
am
ic
th
r
esh
o
ld
s
elec
tio
n
b
ased
o
n
h
ig
h
-
r
is
k
p
r
e
d
ictio
n
,
an
d
ex
p
lo
r
i
n
g
its
co
m
b
in
atio
n
with
en
s
em
b
le
f
r
am
ewo
r
k
s
.
T
h
e
ap
p
licab
ilit
y
o
f
th
is
ap
p
r
o
ac
h
to
o
th
er
d
atasets
an
d
d
o
m
ain
s
co
u
l
d
b
e
ex
p
lo
r
ed
to
estab
lis
h
its
u
s
ef
u
ln
ess
an
d
g
en
er
aliza
b
ilit
y
ev
en
f
u
r
th
e
r
.
T
h
is
s
tu
d
y
p
r
o
v
id
es
an
in
itial
s
tep
to
war
d
s
a
s
ca
lab
le
a
n
d
p
r
a
g
m
atic
en
h
an
ce
m
en
t
f
r
am
ewo
r
k
en
a
b
lin
g
c
o
n
tin
u
ed
p
r
o
g
r
ess
to
war
d
s
m
ac
h
i
n
e
lear
n
in
g
u
s
ag
e
ac
r
o
s
s
h
ea
lth
ca
r
e
p
r
o
v
id
er
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
3
3
-
4
9
4
1
4940
RE
F
E
R
E
NC
E
S
[
1
]
K
a
g
g
l
e
,
“
P
i
ma
I
n
d
i
a
n
s
D
i
a
b
e
t
e
s
d
a
t
a
b
a
s
e
,
”
K
a
g
g
l
e
.
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
u
c
i
ml
/
P
i
ma
-
i
n
d
i
a
n
s
-
d
i
a
b
e
t
e
s
-
d
a
t
a
b
a
se
(
a
c
c
e
s
se
d
D
e
c
.
2
8
,
2
0
2
4
)
.
[
2
]
O
.
I
p
a
r
r
a
g
u
i
r
r
e
-
V
i
l
l
a
n
u
e
v
a
,
K
.
Es
p
i
n
o
l
a
-
Li
n
a
r
e
s
,
R
.
O
.
F
l
o
r
e
s
C
a
s
t
a
ñ
e
d
a
,
a
n
d
M
.
C
a
b
a
n
i
l
l
a
s
-
C
a
r
b
o
n
e
l
l
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
e
a
r
l
y
d
e
t
e
c
t
i
o
n
a
n
d
a
c
c
u
r
a
t
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
t
y
p
e
2
d
i
a
b
e
t
e
s,
”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
1
4
,
p
.
2
3
8
3
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
3
1
4
2
3
8
3
.
[
3
]
G
i
t
H
u
b
,
“
p
y
c
a
r
e
t
/
p
y
c
a
r
e
t
:
a
n
o
p
e
n
-
s
o
u
r
c
e
,
l
o
w
-
c
o
d
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
l
i
b
r
a
r
y
i
n
P
y
t
h
o
n
,
”
G
i
t
H
u
b
.
h
t
t
p
s
:
/
/
g
i
t
h
u
b
.
c
o
m/
p
y
c
a
r
e
t
/
p
y
c
a
r
e
t
(
a
c
c
e
sse
d
D
e
c
.
2
9
,
2
0
2
4
)
.
[
4
]
H
.
L.
T
o
n
g
,
H
.
N
g
,
a
n
d
H
.
A
r
u
l
A
n
a
n
t
h
a
n
,
“
P
r
e
d
i
c
t
i
n
g
d
i
a
b
e
t
e
s
me
l
l
i
t
u
s
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
Ap
p
l
i
e
d
Ph
y
s
i
c
s
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
9
1
–
9
9
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
0
9
3
/
j
e
t
a
p
.
2
0
2
4
.
6
.
1
.
1
2
.
[
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
.
[
6
]
R
.
J
o
se,
F
.
S
y
e
d
,
A
.
Th
o
m
a
s,
a
n
d
M
.
T
o
ma
,
“
C
a
r
d
i
o
v
a
sc
u
l
a
r
h
e
a
l
t
h
m
a
n
a
g
e
me
n
t
i
n
d
i
a
b
e
t
i
c
p
a
t
i
e
n
t
s
w
i
t
h
mac
h
i
n
e
-
l
e
a
r
n
i
n
g
-
d
r
i
v
e
n
p
r
e
d
i
c
t
i
o
n
s a
n
d
i
n
t
e
r
v
e
n
t
i
o
n
s,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
4
,
n
o
.
5
,
p
.
2
1
3
2
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
4
0
5
2
1
3
2
.
[
7
]
D
.
T
h
a
k
u
r
,
T.
G
e
r
a
,
V
.
B
h
a
r
d
w
a
j
,
A
.
A
.
A
l
Z
u
b
i
,
F
.
A
l
i
,
a
n
d
J
.
S
i
n
g
h
,
“
A
n
e
n
h
a
n
c
e
d
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
a
m
i
d
s
t
C
O
V
I
D
-
1
9
u
s
i
n
g
e
n
s
e
mb
l
e
mo
d
e
l
s,
”
Fr
o
n
t
i
e
rs
i
n
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
1
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
u
b
h
.
2
0
2
3
.
1
3
3
1
5
1
7
.
[
8
]
W
H
O
,
“
D
i
a
b
e
t
e
s,”
WHO
.
h
t
t
p
s:
/
/
w
w
w
.
w
h
o
.
i
n
t
/
n
e
w
s
-
r
o
o
m/
f
a
c
t
-
s
h
e
e
t
s
/
d
e
t
a
i
l
/
d
i
a
b
e
t
e
s (
a
c
c
e
sse
d
D
e
c
.
2
9
,
2
0
2
4
)
.
[
9
]
A
meric
a
n
D
i
a
b
e
t
e
s
A
ss
o
c
i
a
t
i
o
n
,
“
D
i
a
g
n
o
s
i
s
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
d
i
a
b
e
t
e
s
mel
l
i
t
u
s
,
”
D
i
a
b
e
t
e
s
C
a
r
e
,
v
o
l
.
3
2
,
n
o
.
S
u
p
p
l
e
m
e
n
t
_
1
,
p
p
.
S
6
2
--
S
6
7
,
Ja
n
.
2
0
0
9
,
d
o
i
:
1
0
.
2
3
3
7
/
d
c
0
9
-
S
0
6
2
.
[
1
0
]
R
.
G
o
y
a
l
,
M
.
S
i
n
g
h
a
l
,
a
n
d
I
.
Ji
a
l
a
l
,
“
Ty
p
e
2
d
i
a
b
e
t
e
s,”
N
a
t
i
o
n
a
l
L
i
b
r
a
ry
o
f
M
e
d
i
c
i
n
e
,
2
0
2
3
.
h
t
t
p
s
:
/
/
w
w
w
.
n
c
b
i
.
n
l
m
.
n
i
h
.
g
o
v
/
b
o
o
k
s
/
N
B
K
5
1
3
2
5
3
/
(
a
c
c
e
sse
d
D
e
c
.
2
9
,
2
0
2
4
)
.
[
1
1
]
T.
A
.
O
j
u
r
o
n
g
b
e
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
f
o
r
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
t
y
p
e
2
d
i
a
b
e
t
e
s
u
s
i
n
g
p
a
t
i
e
n
t
s’
c
l
i
n
i
c
a
l
s
y
mp
t
o
ms,
d
e
m
o
g
r
a
p
h
i
c
f
e
a
t
u
r
e
s,
a
n
d
k
n
o
w
l
e
d
g
e
o
f
d
i
a
b
e
t
e
s,
”
H
e
a
l
t
h
S
c
i
e
n
c
e
Re
p
o
rt
s
,
v
o
l
.
7
,
n
o
.
1
,
Jan
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
2
/
h
sr
2
.
1
8
3
4
.
[
1
2
]
J.
N
w
o
k
e
,
“
H
e
a
l
t
h
c
a
r
e
d
a
t
a
a
n
a
l
y
t
i
c
s
a
n
d
p
r
e
d
i
c
t
i
v
e
m
o
d
e
l
l
i
n
g
:
e
n
h
a
n
c
i
n
g
o
u
t
c
o
mes
i
n
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
,
d
i
se
a
se
p
r
e
v
a
l
e
n
c
e
a
n
d
h
i
g
h
-
r
i
sk
p
o
p
u
l
a
t
i
o
n
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
H
e
a
l
t
h
S
c
i
e
n
c
e
s
,
v
o
l
.
7
,
n
o
.
7
,
p
p
.
1
–
3
5
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
4
7
9
4
1
/
i
j
h
s.
2
2
4
5
.
[
1
3
]
A
.
K
u
r
b
a
n
o
v
,
R
.
I
sae
v
,
a
n
d
G
.
G
i
mal
e
t
d
i
n
o
v
a
,
“
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
t
e
c
h
n
i
q
u
e
s:
a
c
o
m
p
r
e
h
e
n
si
v
e
a
n
a
l
y
si
s
,
”
Pr
e
p
ri
n
t
s
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
2
0
9
4
4
/
p
r
e
p
r
i
n
t
s
2
0
2
4
1
2
.
0
9
0
1
.
v
1
.
[
1
4
]
H
.
A
.
A
b
d
e
l
h
a
f
e
z
,
“
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
f
o
r
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
:
a
c
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
,
”
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
D
a
t
a
S
c
i
e
n
c
e
s
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
7
9
2
–
8
0
7
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
4
7
7
3
8
/
j
a
d
s.
v
5
i
2
.
2
1
9
.
[
1
5
]
V
.
Ji
t
h
e
n
d
r
a
,
R
.
M
.
S
a
i
M
o
h
i
t
,
M
.
M
a
d
h
u
s
u
d
h
a
n
,
B
.
J
a
g
a
d
e
e
s
h
,
a
n
d
S
.
K
u
su
m
a
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
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,
”
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
a
n
d
C
a
p
s
u
l
e
N
e
t
w
o
r
k
s
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
1
9
0
–
2
0
6
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
6
5
4
8
/
j
a
i
c
n
.
2
0
2
3
.
2
.
0
0
8
.
[
1
6
]
C
o
u
r
sera
,
“
L
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
:
a
n
o
v
e
r
v
i
e
w
,
”
C
o
u
rse
ra
,
2
0
2
4
.
h
t
t
p
s:
/
/
w
w
w
.
c
o
u
r
sera
.
o
r
g
/
a
r
t
i
c
l
e
s/
l
o
g
i
s
t
i
c
-
r
e
g
r
e
ssi
o
n
(
a
c
c
e
sse
d
D
e
c
.
2
9
,
2
0
2
4
)
.
[
1
7
]
S
p
i
c
e
w
o
r
k
s,
“
E
v
e
r
y
t
h
i
n
g
y
o
u
n
e
e
d
t
o
k
n
o
w
a
b
o
u
t
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
,
”
S
p
i
c
e
w
o
r
k
s
.
h
t
t
p
s:
/
/
w
w
w
.
s
p
i
c
e
w
o
r
k
s.
c
o
m/
t
e
c
h
/
a
r
t
i
f
i
c
i
a
l
-
i
n
t
e
l
l
i
g
e
n
c
e
/
a
r
t
i
c
l
e
s/
w
h
a
t
-
is
-
l
o
g
i
s
t
i
c
-
r
e
g
r
e
ss
i
o
n
/
(
a
c
c
e
s
se
d
D
e
c
.
2
9
,
2
0
2
4
)
.
[
1
8
]
H
.
A
l
-
R
i
mm
a
w
i
,
“
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
u
s
i
n
g
l
o
g
i
st
i
c
r
e
g
r
e
s
si
o
n
t
e
c
h
n
i
q
u
e
s,
”
T
u
rk
i
sh
J
o
u
rn
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
R
C
O
MA
T
)
,
v
o
l
.
1
5
,
n
o
.
1
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
6
1
8
4
1
/
t
u
r
c
o
m
a
t
.
v
1
5
i
1
.
1
3
8
7
5
.
[
1
9
]
D
a
t
a
C
a
m
p
,
“
P
y
t
h
o
n
l
o
g
i
s
t
i
c
r
e
g
r
e
ss
i
o
n
t
u
t
o
r
i
a
l
w
i
t
h
S
k
l
e
a
r
n
&
S
c
i
k
i
t
,
”
D
a
t
a
C
a
m
p
.
h
t
t
p
s
:
/
/
w
w
w
.
d
a
t
a
c
a
mp
.
c
o
m/
t
u
t
o
r
i
a
l
/
u
n
d
e
r
st
a
n
d
i
n
g
-
l
o
g
i
st
i
c
-
r
e
g
r
e
ss
i
o
n
-
p
y
t
h
o
n
(
a
c
c
e
ss
e
d
D
e
c
.
2
9
,
2
0
2
4
)
.
[
2
0
]
G
e
e
k
sf
o
r
G
e
e
k
s,
“
L
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
i
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
G
e
e
k
s
f
o
r
G
e
e
k
s
.
h
t
t
p
s
:
/
/
w
w
w
.
g
e
e
k
sf
o
r
g
e
e
k
s.
o
r
g
/
u
n
d
e
r
s
t
a
n
d
i
n
g
-
l
o
g
i
s
t
i
c
-
r
e
g
r
e
ssi
o
n
/
(
a
c
c
e
sse
d
D
e
c
.
2
9
,
2
0
2
4
)
.
[
2
1
]
C.
-
W
.
S
u
n
g
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
o
n
o
f
h
i
g
h
-
r
i
sk
e
m
e
r
g
e
n
c
y
d
e
p
a
r
t
me
n
t
r
e
v
i
s
i
t
s
f
r
o
m
a
m
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m:
a
p
r
o
o
f
-
of
-
c
o
n
c
e
p
t
st
u
d
y
,
”
BM
J
H
e
a
l
t
h
&
C
a
re
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
3
1
,
n
o
.
1
,
p
.
e
1
0
0
8
5
9
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
3
6
/
b
m
j
h
c
i
-
2
0
2
3
-
1
0
0
8
5
9
.
[
2
2
]
B
.
N
j
e
i
,
E
.
O
st
a
,
N
.
N
j
e
i
,
Y
.
A
.
A
l
-
A
j
l
o
u
n
i
,
a
n
d
J.
K
.
L
i
m,
“
A
n
e
x
p
l
a
i
n
a
b
l
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
h
i
g
h
-
r
i
s
k
n
o
n
a
l
c
o
h
o
l
i
c
st
e
a
t
o
h
e
p
a
t
i
t
i
s,”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
4
,
n
o
.
1
,
p
.
8
5
8
9
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
4
-
5
9
1
8
3
-
4.
[
2
3
]
R
.
K
e
n
n
e
d
y
,
“
M
a
k
i
n
g
u
s
e
f
u
l
c
o
n
f
l
i
c
t
p
r
e
d
i
c
t
i
o
n
s,
”
J
o
u
r
n
a
l
o
f
P
e
a
c
e
R
e
s
e
a
r
c
h
,
v
o
l
.
5
2
,
n
o
.
5
,
p
p
.
6
4
9
–
6
6
4
,
S
e
p
.
2
0
1
5
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
2
2
3
4
3
3
1
5
5
8
5
6
1
1
.
[
2
4
]
S
.
C
.
Y
.
W
a
n
g
,
G
.
N
i
c
k
e
l
,
K
.
P
.
V
e
n
k
a
t
e
s
h
,
M
.
M
.
R
a
z
a
,
a
n
d
J.
C
.
K
v
e
d
a
r
,
“
A
I
-
b
a
sed
d
i
a
b
e
t
e
s
c
a
r
e
:
r
i
s
k
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
a
n
d
i
mp
l
e
m
e
n
t
a
t
i
o
n
c
o
n
c
e
r
n
s,
”
n
p
j
D
i
g
i
t
a
l
M
e
d
i
c
i
n
e
,
v
o
l
.
7
,
n
o
.
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
7
4
6
-
024
-
0
1
0
3
4
-
7.
[
2
5
]
F
.
Za
f
a
r
,
S
.
R
a
z
a
,
M
.
U
.
K
h
a
l
i
d
,
a
n
d
M
.
A
.
Ta
h
i
r
,
“
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
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
9
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
Bi
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
M
a
r
.
2
0
1
9
,
p
p
.
2
5
3
–
2
5
9
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
2
6
1
7
2
.
3
3
2
6
2
1
3
.
[
2
6
]
Z.
G
u
a
n
e
t
a
l
.
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
d
i
a
b
e
t
e
s
ma
n
a
g
e
m
e
n
t
:
a
d
v
a
n
c
e
me
n
t
s,
o
p
p
o
r
t
u
n
i
t
i
e
s,
a
n
d
c
h
a
l
l
e
n
g
e
s,”
C
e
l
l
Re
p
o
r
t
s
Me
d
i
c
i
n
e
,
v
o
l
.
4
,
n
o
.
1
0
,
p
.
1
0
1
2
1
3
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
x
c
r
m.
2
0
2
3
.
1
0
1
2
1
3
.
[
2
7
]
F
.
H
o
r
n
,
R
.
P
a
c
k
,
a
n
d
M
.
R
i
e
g
e
r
,
“
T
h
e
a
u
t
o
f
e
a
t
p
y
t
h
o
n
l
i
b
r
a
r
y
f
o
r
a
u
t
o
mat
e
d
f
e
a
t
u
r
e
e
n
g
i
n
e
e
r
i
n
g
a
n
d
se
l
e
c
t
i
o
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
.
1
1
6
7
C
C
I
S
,
p
p
.
1
1
1
–
1
2
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
4
3
8
2
3
-
4
_
1
0
.
[
2
8
]
L.
L
i
a
o
,
H
.
Li
,
W
.
S
h
a
n
g
,
a
n
d
L
.
M
a
,
“
A
n
e
m
p
i
r
i
c
a
l
st
u
d
y
o
f
t
h
e
i
m
p
a
c
t
o
f
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
a
n
d
m
o
d
e
l
o
p
t
i
m
i
z
a
t
i
o
n
o
n
t
h
e
p
e
r
f
o
r
m
a
n
c
e
p
r
o
p
e
r
t
i
e
s
o
f
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
A
C
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
S
o
f
t
w
a
re
En
g
i
n
e
e
r
i
n
g
a
n
d
Me
t
h
o
d
o
l
o
g
y
,
v
o
l
.
3
1
,
n
o
.
3
,
p
p
.
1
–
4
0
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
0
6
6
9
5
.
[
2
9
]
Y
.
R
i
ma
l
,
N
.
S
h
a
r
ma,
a
n
d
A
.
A
l
sa
d
o
o
n
,
“
T
h
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
mo
d
e
l
s
r
e
l
i
e
s
o
n
h
y
p
e
r
p
a
r
a
me
t
e
r
t
u
n
i
n
g
:
s
t
u
d
e
n
t
r
e
s
u
l
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
r
a
n
d
o
m
f
o
r
e
s
t
,
r
a
n
d
o
m
i
z
e
d
se
a
r
c
h
,
g
r
i
d
s
e
a
r
c
h
,
b
a
y
e
s
i
a
n
,
g
e
n
e
t
i
c
,
a
n
d
o
p
t
u
n
a
a
l
g
o
r
i
t
h
ms,”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
3
0
,
p
p
.
7
4
3
4
9
–
7
4
3
6
4
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
4
-
1
8
4
2
6
-
2.
[
3
0
]
M
.
E
l
A
r
n
i
,
I
.
L
a
h
s
e
n
-
C
h
e
r
i
f
,
a
n
d
M
.
B
e
l
l
a
f
k
i
h
,
“
P
r
e
d
i
c
t
i
n
g
d
i
a
b
e
t
e
s u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
:
X
G
B
o
o
st
a
n
d
t
h
e
P
I
M
A
d
a
t
a
se
t
,
”
i
n
2
0
2
4
S
i
x
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
i
n
D
a
t
a
S
c
i
e
n
c
e
s
(
I
C
D
S
)
,
O
c
t
.
2
0
2
4
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
S
6
2
0
8
9
.
2
0
2
4
.
1
0
7
5
6
3
7
9
.
[
3
1
]
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
s
e
t
,
”
J
o
u
r
n
a
l
o
f
D
i
a
b
e
t
e
s
&
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
,
Ju
n
.
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.
[
3
2
]
P
.
H
o
u
n
g
u
è
a
n
d
A
.
G
.
B
i
g
i
r
i
m
a
n
a
,
“
Le
v
e
r
a
g
i
n
g
P
i
ma
d
a
t
a
s
e
t
t
o
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
:
c
a
se
st
u
d
y
o
f
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
0
,
n
o
.
1
1
,
p
p
.
1
5
–
2
8
,
2
0
2
2
,
d
o
i
:
1
0
.
4
2
3
6
/
j
c
c
.
2
0
2
2
.
1
0
1
1
0
0
2
.
[
3
3
]
A
.
A
h
m
e
d
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
-
b
a
s
e
d
p
r
e
d
i
c
t
i
o
n
o
f
d
i
a
b
e
t
e
s
a
m
o
n
g
f
e
ma
l
e
p
o
p
u
l
a
t
i
o
n
u
s
i
n
g
P
I
M
A
d
a
t
a
se
t
,
”
H
e
a
l
t
h
c
a
re
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
3
7
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
h
e
a
l
t
h
c
a
r
e
1
3
0
1
0
0
3
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
cin
g
d
ia
b
etes p
r
ed
ictio
n
th
r
o
u
g
h
p
r
o
b
a
b
ilit
y
-
b
a
s
ed
…
(
A
ito
u
h
a
n
n
i I
ma
n
e
)
4941
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Im
a
n
e
Ait
o
u
h
a
n
n
i
re
c
e
i
v
e
d
t
h
e
e
n
g
in
e
e
rin
g
d
e
g
re
e
in
in
f
o
rm
a
ti
o
n
a
n
d
c
o
m
m
u
n
ica
ti
o
n
s
y
ste
m
s
fro
m
th
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
Ap
p
li
e
d
S
c
ie
n
c
e
s
(ENS
A)
o
f
El
Ja
d
id
a
,
M
o
ro
c
c
o
.
S
h
e
is
c
u
rre
n
t
ly
p
u
rsu
in
g
a
d
v
a
n
c
e
d
re
se
a
rc
h
a
t
t
h
e
S
m
a
rt
S
y
ste
m
s
Lab
o
ra
to
r
y
(S
S
LAB),
S
c
h
o
o
l
o
f
I
n
fo
rm
a
ti
o
n
S
c
ien
c
e
s
(ENS
IAS),
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
in
Ra
b
a
t
.
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
rti
ficia
l
in
telli
g
e
n
c
e
,
m
e
d
ica
l
d
a
ta
a
n
a
ly
sis,
h
e
a
lt
h
c
a
re
in
f
o
rm
a
ti
c
s,
a
n
d
p
re
d
ictiv
e
m
o
d
e
li
n
g
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
se
v
e
ra
l
p
a
p
e
rs
i
n
p
e
e
r
-
re
v
iew
e
d
jo
u
rn
a
ls
a
n
d
h
a
s
p
a
rti
c
ip
a
ted
i
n
v
a
rio
u
s
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
o
n
in
telli
g
e
n
t
sy
ste
m
s a
n
d
b
i
o
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
ima
n
e
.
a
it
o
u
h
a
n
n
i@
g
m
a
il
.
c
o
m
.
Am
in
e
Be
r
q
ia
re
c
e
iv
e
d
th
e
P
h
.
D.
d
e
g
re
e
in
c
o
m
p
u
ter sc
ien
c
e
fro
m
th
e
Un
iv
e
rsit
y
o
f
Dij
o
n
,
F
ra
n
c
e
.
He
is
c
u
rre
n
tl
y
a
fu
l
l
p
ro
fe
ss
o
r
a
n
d
h
e
a
d
o
f
t
h
e
Co
m
m
u
n
ica
ti
o
n
Ne
two
rk
s
De
p
a
rtme
n
t
a
t
ENS
IAS,
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
i
n
Ra
b
a
t,
M
o
r
o
c
c
o
,
a
n
d
a
m
e
m
b
e
r
o
f
it
s
S
m
a
rt
S
y
ste
m
s
Lab
o
ra
to
r
y
(
S
S
LAB)
a
n
d
Ra
b
a
t
I
T
Ce
n
ter.
H
e
p
re
v
i
o
u
sl
y
se
rv
e
d
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
a
t
th
e
Un
iv
e
rsity
o
f
G
e
n
e
v
a
,
wh
e
re
h
e
c
o
o
r
d
in
a
ted
t
h
e
S
wiss
Virtu
a
l
Ca
m
p
u
s
P
ro
jec
t
VITE
LS
fro
m
2
0
0
0
t
o
2
0
0
3
.
He
h
a
s
a
u
th
o
re
d
o
v
e
r
5
0
p
e
e
r
-
re
v
iew
e
d
a
rti
c
les
in
c
o
m
p
u
ter
n
e
two
r
k
s,
n
e
two
r
k
se
c
u
rit
y
,
wire
les
s
a
n
d
m
o
b
il
e
n
e
two
r
k
s,
a
n
d
i
n
telli
g
e
n
t
sy
ste
m
s.
He
h
a
s
re
c
e
iv
e
d
se
v
e
ra
l
a
wa
rd
s,
in
c
l
u
d
in
g
re
c
o
g
n
it
i
o
n
fro
m
t
h
e
IE
EE
Ed
u
c
a
ti
o
n
S
o
c
iety
in
2
0
1
2
a
n
d
th
e
IEE
E
s
tan
d
a
rd
s
a
ss
o
c
iatio
n
i
n
2
0
1
9
fo
r
h
is
c
o
n
tri
b
u
ti
o
n
s
t
o
IEE
E
S
tan
d
a
rd
1
8
7
6
.
His
tea
c
h
i
n
g
a
n
d
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
t
e
r
sc
ien
c
e
,
c
o
m
m
u
n
ica
ti
o
n
n
e
two
rk
s,
o
p
e
ra
ti
n
g
sy
ste
m
s,
n
e
two
rk
se
c
u
rit
y
,
a
n
d
wire
les
s/m
o
b
il
e
n
e
two
rk
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
e
r
q
ia@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.