I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
14
,
No
.
3
,
Dec
em
b
er
20
25
,
p
p
.
75
1
~
7
5
9
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v14
i
3
.
pp
751
-
7
5
9
751
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
AI
-
ba
sed f
ederate
d learning
f
o
r
hea
rt
disea
se p
redic
ti
o
n:
a
colla
bo
ra
tive a
nd priva
cy
-
preserv
ing
appro
a
ch
Stut
i Bh
a
t
t
1
,
Su
re
nd
er
Re
dd
y
Sa
lk
uti
2
,
Seo
ng
-
Cheo
l K
i
m
2
1
D
e
p
a
r
t
me
n
t
o
f
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
,
G
r
a
p
h
i
c
Er
a
H
i
l
l
U
n
i
v
e
r
si
t
y
,
D
e
h
r
a
d
u
n
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
R
a
i
l
r
o
a
d
a
n
d
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
W
o
o
s
o
n
g
U
n
i
v
e
r
s
i
t
y
,
D
a
e
j
e
o
n
,
R
e
p
u
b
l
i
c
o
f
K
o
r
e
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
2
2
,
2
0
2
4
R
ev
is
ed
J
an
2
6
,
2
0
2
5
Acc
ep
ted
J
u
n
9
,
2
0
2
5
P
e
o
p
le
wit
h
sy
m
p
t
o
m
s
li
k
e
d
iab
e
tes
,
h
ig
h
BP
,
a
n
d
h
ig
h
c
h
o
les
tero
l
a
re
a
t
a
n
in
c
re
a
se
d
risk
fo
r
h
e
a
rt
d
ise
a
se
a
n
d
str
o
k
e
a
s
t
h
e
y
g
e
t
o
ld
e
r.
To
m
it
ig
a
te
t
h
is
th
re
a
t,
p
re
d
ictiv
e
fa
sh
io
n
s
lev
e
ra
g
in
g
m
a
c
h
in
e
lea
rn
in
g
(
ML
)
a
n
d
a
rti
ficia
l
in
telli
g
e
n
c
e
(
AI
)
h
a
v
e
e
m
e
rg
e
d
a
s
a
p
re
c
io
u
s
g
e
a
r;
h
o
we
v
e
r,
h
e
a
rt
d
ise
a
se
p
re
d
ictio
n
is
a
c
o
m
p
li
c
a
ted
tas
k
,
a
n
d
d
iag
n
o
sis
o
u
tco
m
e
s
a
re
h
a
rd
ly
e
v
e
r
a
c
c
u
ra
te.
Cu
rre
n
tl
y
,
t
h
e
e
x
ist
in
g
M
L
tec
h
sa
y
s
it
is
n
e
c
e
ss
a
ry
to
h
a
v
e
d
a
ta
i
n
c
e
rtain
c
e
n
tralize
d
lo
c
a
ti
o
n
s
t
o
d
e
tec
t
h
e
a
rt
d
ise
a
se
,
a
s
d
a
ta
c
a
n
b
e
fo
u
n
d
c
e
n
trally
a
n
d
is
e
a
sily
a
c
c
e
ss
ib
le.
Th
is
re
v
iew
i
n
tro
d
u
c
e
s
fe
d
e
ra
ted
lea
rn
in
g
(F
L)
t
o
a
n
sw
e
r
d
a
ta
p
ri
v
a
c
y
c
h
a
ll
e
n
g
e
s
i
n
h
e
a
rt
d
ise
a
se
p
re
d
ict
io
n
.
FL
,
a
c
o
ll
a
b
o
ra
ti
v
e
tec
h
n
i
q
u
e
p
io
n
e
e
re
d
b
y
G
o
o
g
le,
trai
n
s
a
lg
o
rit
h
m
s
a
c
ro
ss
in
d
e
p
e
n
d
e
n
t
se
ss
io
n
s
u
sin
g
lo
c
a
l
d
a
tas
e
ts.
Th
is
p
a
p
e
r
in
v
e
stig
a
tes
re
c
e
n
t
ML
m
e
th
o
d
s
a
n
d
d
a
tab
a
se
s
fo
r
p
re
d
i
c
ti
n
g
c
a
rd
i
o
v
a
sc
u
lar
d
ise
a
se
(h
e
a
rt
a
tt
a
c
k
).
P
re
v
io
u
s
re
se
a
rc
h
e
x
p
lo
re
s
a
lg
o
rit
h
m
s
li
k
e
re
g
io
n
-
b
a
se
d
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(
RCNN
)
,
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(
C
NN
)
,
a
n
d
fe
d
e
ra
ted
lo
g
ist
ic
re
g
re
ss
io
n
s
(
F
LRs
)
fo
r
h
e
a
rt
a
n
d
o
th
e
r
d
ise
a
se
p
re
d
ictio
n
.
FL
a
ll
o
ws
t
h
e
train
in
g
o
f
a
c
o
ll
a
b
o
ra
ti
v
e
m
o
d
e
l
w
h
il
e
k
e
e
p
in
g
p
a
ti
e
n
t
i
n
fo
sp
re
a
d
o
u
t
a
m
o
n
g
v
a
rio
u
s
sites
,
e
n
su
rin
g
p
ri
v
a
c
y
a
n
d
se
c
u
rit
y
.
T
h
is
p
a
p
e
r
e
x
p
lo
re
s
t
h
e
e
ffica
c
y
o
f
F
L,
a
c
o
ll
a
b
o
ra
ti
v
e
tec
h
n
i
q
u
e
,
in
e
n
h
a
n
c
in
g
th
e
a
c
c
u
ra
c
y
o
f
c
a
rd
io
v
a
sc
u
lar
d
i
se
a
se
(CVD
)
p
re
d
ictio
n
m
o
d
e
ls
wh
il
e
p
re
se
rv
in
g
d
a
ta p
riv
a
c
y
a
c
ro
ss
d
is
tri
b
u
te
d
d
a
tas
e
ts.
K
ey
w
o
r
d
s
:
Dis
ea
s
e
p
r
ed
ictio
n
Dis
tr
ib
u
ted
tr
ain
in
g
Fed
er
ated
lear
n
in
g
Hea
r
t d
is
ea
s
e
Ma
ch
in
e
lear
n
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
:
Su
r
en
d
er
R
ed
d
y
Salk
u
ti
Dep
ar
tm
en
t o
f
R
ailr
o
ad
an
d
E
lectr
ical
E
n
g
in
ee
r
in
g
,
W
o
o
s
o
n
g
Un
iv
er
s
ity
J
ay
an
g
-
Do
n
g
,
Do
n
g
-
Gu
,
Dae
j
eo
n
-
3
4
6
0
6
,
R
ep
u
b
lic
o
f
K
o
r
e
a
E
m
ail: su
r
en
d
er
@
wsu
.
ac
.
k
r
1.
I
NT
RO
D
UCT
I
O
N
A
h
ea
r
t
attac
k
is
a
s
cien
tific
u
r
g
en
cy
w
h
er
ein
th
e
p
atien
t’
s
c
o
r
o
n
ar
y
h
ea
r
t
m
u
s
cle
s
tar
ts
to
d
ie
as
th
e
b
lo
o
d
f
lo
w
to
a
s
ec
tio
n
o
f
th
e
h
ea
r
t
is
o
b
s
tr
u
cted
,
it
r
esu
lt
s
in
d
am
ag
e
o
r
d
ea
th
o
f
th
e
h
ea
r
t
m
u
s
cle
tis
s
u
e.
A
b
lo
ck
ag
e
in
s
id
e
th
e
ar
ter
ies
th
at
s
u
p
p
ly
b
lo
o
d
to
y
o
u
r
h
e
ar
t
co
m
m
o
n
ly
ca
u
s
es
th
is
.
I
f
a
m
ed
ical
p
r
ac
titi
o
n
er
is
n
o
t
a
b
l
e
t
o
r
e
p
a
i
r
b
l
o
o
d
f
l
o
w
a
s
s
o
o
n
a
s
p
o
s
s
i
b
l
e
,
a
c
o
r
o
n
a
r
y
h
e
a
r
t
a
t
t
a
c
k
c
a
n
c
a
u
s
e
p
e
r
m
a
n
e
n
t
h
e
a
r
t
d
a
m
a
g
e
w
h
i
c
h
r
e
s
u
l
ts
i
n
t
h
e
d
e
a
t
h
o
f
t
h
e
p
a
t
i
e
n
t
.
A
m
y
o
c
a
r
d
i
a
l
i
n
f
a
r
c
t
i
o
n
i
s
a
h
a
z
a
r
d
o
u
s
c
i
r
c
u
m
s
t
an
c
e
t
h
a
t
t
a
k
e
s
p
l
a
c
e
d
u
e
t
o
t
h
e
f
a
c
t
y
o
u
d
o
n
’
t
h
a
v
e
s
u
f
f
i
c
i
e
n
t
b
l
o
o
d
f
l
o
w
t
o
a
n
u
m
b
e
r
o
f
y
o
u
r
h
e
a
r
t
m
u
s
c
l
e
s
.
I
t
’
s
e
x
p
e
c
t
e
d
a
r
o
u
n
d
2
h
u
n
d
r
e
d
m
i
l
l
i
o
n
h
u
m
a
n
s
a
r
e
l
iv
i
n
g
w
i
t
h
c
o
r
o
n
a
r
y
h
e
a
r
t
d
i
s
e
as
e
.
G
l
o
b
a
l
l
y
a
r
o
u
n
d
a
h
u
n
d
r
e
d
a
n
d
t
e
n
m
il
l
i
o
n
g
u
y
s
a
n
d
e
i
g
h
t
y
m
i
l
l
i
o
n
l
a
d
i
e
s
h
a
v
e
c
o
r
o
n
a
r
y
h
e
a
r
t
d
i
s
e
a
s
e
.
T
h
e
p
r
e
s
e
n
t
-
d
a
y
o
c
c
u
r
r
e
n
c
e
o
f
d
i
a
b
e
t
e
s
m
el
l
it
u
s
is
4
6
3
m
i
l
l
i
o
n
,
e
q
u
a
l
t
o
9
.
3
%
o
f
t
h
e
w
o
r
l
d
p
o
p
u
l
a
t
i
o
n
.
T
h
e
i
n
t
e
r
n
ati
o
n
a
l
p
a
n
d
e
m
i
c
o
f
d
i
a
b
e
te
s
i
s
p
r
e
d
i
c
t
e
d
t
o
e
l
e
v
at
e
t
h
i
s
f
i
g
u
r
e
t
o
5
7
8
m
i
ll
i
o
n
(
1
0
.
2
%
)
t
h
r
o
u
g
h
t
h
e
y
e
a
r
2
0
3
0
a
n
d
s
e
v
e
n
h
u
n
d
r
e
d
m
i
l
l
i
o
n
(
1
0
.
9
%
)
t
h
r
o
u
g
h
2
0
4
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
14
,
No
.
3
,
Dec
em
b
er
20
25
:
751
-
7
5
9
752
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
(
FL
)
ca
n
p
l
ay
a
s
ig
n
if
ican
t
r
o
le
in
ad
d
r
es
s
in
g
ch
allen
g
es
ass
o
ciate
d
wit
h
co
r
o
n
ar
y
h
ea
r
t
attac
k
s
(
m
y
o
ca
r
d
ial
i
n
f
ar
ctio
n
)
an
d
d
iab
etes
m
ellitu
s
(
DM
)
th
r
o
u
g
h
lev
er
a
g
in
g
co
llab
o
r
ativ
e
r
ec
o
r
d
s
s
h
ar
in
g
at
th
e
s
am
e
tim
e
as p
r
eser
v
in
g
p
r
i
v
ac
y
an
d
s
ec
u
r
ity
.
Her
e
’
s
h
o
w
FL
m
ay
b
e
u
s
ef
u
l
in
th
o
s
e
co
n
tex
ts
:
−
Priv
ac
y
-
p
r
eser
v
i
n
g
m
o
d
el
tr
a
in
in
g
:
FL
p
er
m
its
th
e
tr
ain
i
n
g
o
f
th
e
m
ac
h
in
e
lear
n
in
g
(
ML
)
m
o
d
els
th
r
o
u
g
h
o
u
t
d
ec
en
tr
alize
d
r
ec
o
r
d
s
s
o
u
r
ce
s
(
to
g
eth
er
with
m
ed
ical
s
tatis
tic
s
f
r
o
m
d
if
f
e
r
en
t
h
ea
lth
ca
r
e
p
r
o
v
id
e
r
s
)
with
o
u
t
s
h
ar
in
g
r
a
w
r
ec
o
r
d
s
.
T
h
is
is
im
p
o
r
tan
t
f
o
r
p
r
eser
v
in
g
p
atie
n
t
p
r
iv
ac
y
,
as
s
en
s
itiv
e
h
ea
lth
in
f
o
r
m
atio
n
lik
e
ca
r
d
ia
c
h
ea
lth
r
ec
o
r
d
s
an
d
d
iab
etes statu
s
ca
n
r
em
ain
lo
ca
lized
[
1
]
.
−
I
m
p
r
o
v
ed
m
o
d
el
g
e
n
er
aliza
tio
n
:
b
y
le
v
er
ag
in
g
n
u
m
er
o
u
s
r
ec
o
r
d
s
f
r
o
m
v
ar
io
u
s
s
o
u
r
c
es
(
r
ef
lectin
g
s
p
ec
ial
d
em
o
g
r
ap
h
ics,
g
en
etic
b
ac
k
g
r
o
u
n
d
s
,
a
n
d
m
ed
ical
h
is
to
r
ies),
FL
ca
n
ass
is
t
d
ev
elo
p
ex
tr
a
s
tu
r
d
y
an
d
g
e
n
er
aliza
b
le
m
o
d
els
f
o
r
p
r
e
d
ictin
g
an
d
p
r
ev
en
ti
n
g
co
r
o
n
ar
y
h
ea
r
t
attac
k
s
an
d
d
ia
b
etes
co
m
p
licatio
n
s
.
−
Per
s
o
n
alize
d
m
ed
icin
e
:
FL
p
er
m
its
th
e
im
p
r
o
v
em
en
t
o
f
p
er
s
o
n
alize
d
p
r
ed
ictiv
e
m
o
d
els
f
o
r
ass
ess
in
g
in
d
iv
id
u
al
d
a
n
g
er
s
o
f
co
r
o
n
ar
y
h
ea
r
t a
ttack
s
o
r
d
ia
b
etes
-
ass
o
ciate
d
co
m
p
licatio
n
s
p
r
i
m
ar
ily
b
ased
to
tall
y
o
n
d
iv
e
r
s
e
p
atien
t r
ec
o
r
d
s
.
T
h
i
s
ca
n
r
esu
lt in
ex
tr
a
-
ce
n
ter
ed
i
n
ter
v
en
tio
n
s
a
n
d
r
em
e
d
y
s
tr
at
eg
ies [
2
]
.
−
R
ea
l
-
tim
e
m
o
n
ito
r
in
g
an
d
aler
ts
:
FL
m
o
d
els
ca
n
b
e
co
n
s
tan
tly
u
p
d
ated
a
n
d
r
ef
in
e
d
th
r
o
u
g
h
th
e
u
s
ag
e
o
f
r
ea
l
-
tim
e
r
ec
o
r
d
s
f
r
o
m
a
co
u
p
le
o
f
ass
ets,
p
er
m
itti
n
g
f
aster
d
etec
tio
n
o
f
ea
r
ly
war
n
i
n
g
s
ig
n
s
r
elate
d
to
co
r
o
n
a
r
y
h
ea
r
t
attac
k
s
o
r
d
iab
etes
ex
ac
er
b
atio
n
s
.
T
h
is
ca
n
f
ac
ilit
ate
tim
ely
in
ter
v
en
tio
n
s
a
n
d
p
r
ev
en
tiv
e
m
ea
s
u
r
es.
−
Scalin
g
an
d
c
o
llab
o
r
atio
n
:
g
i
v
en
th
e
wo
r
ld
wid
e
i
n
cid
en
ce
o
f
th
o
s
e
c
o
n
d
itio
n
s
,
FL
p
r
o
v
i
d
es
a
s
ca
lab
le
m
eth
o
d
f
o
r
co
llab
o
r
ati
o
n
th
r
o
u
g
h
o
u
t
i
n
s
titu
tio
n
s
,
r
eg
io
n
s
,
an
d
co
u
n
tr
ies.
T
h
is
c
o
llectiv
e
attem
p
t
c
a
n
r
esu
lt in
a
h
ig
h
e
r
u
n
d
er
s
tan
d
in
g
o
f
s
ick
n
ess
p
atter
n
s
,
r
is
k
f
ac
to
r
s
,
an
d
p
o
wer
f
u
l c
o
n
tr
o
l stra
teg
ies.
−
I
n
teg
r
atio
n
with
wea
r
ab
le
d
ev
ices
an
d
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
:
FL
ca
n
co
m
b
in
e
r
ec
o
r
d
s
f
r
o
m
wea
r
ab
le
d
ev
ices
an
d
I
o
T
d
ev
ices
u
s
ed
f
o
r
n
o
n
-
s
to
p
f
itn
ess
m
o
n
ito
r
i
n
g
.
T
h
is
co
m
p
lete
r
ec
o
r
d
s
a
g
g
r
eg
atio
n
ca
n
en
h
an
ce
p
r
ed
ictiv
e
m
o
d
els
f
o
r
f
ig
u
r
i
n
g
o
u
t
p
r
e
-
c
o
r
o
n
ar
y
h
ea
r
t
attac
k
s
ig
n
s
an
d
s
y
m
p
to
m
s
o
r
d
iab
etic
co
m
p
licatio
n
s
.
A
d
iab
etic
p
er
s
o
n
h
as
a
h
ig
h
er
r
is
k
o
f
h
av
i
n
g
a
co
r
o
n
ar
y
h
ea
r
t
attac
k
b
ec
au
s
e
o
f
attr
i
b
u
tes
lik
e
in
s
u
lin
r
esis
tan
ce
an
d
ch
r
o
n
ic
ex
ce
s
s
iv
e
b
lo
o
d
s
u
g
ar
lev
el
s
th
is
is
wh
y
it
's
f
ar
ess
en
tial
th
at
ailm
en
ts
lik
e
d
iab
etes,
b
lo
o
d
p
r
ess
u
r
e,
an
d
ch
o
lest
er
o
l
d
eg
r
ee
ar
e
d
ef
in
e
d
b
ef
o
r
e
an
d
g
iv
e
n
m
o
r
e
atten
ti
o
n
as
th
ey
h
a
v
e
g
o
t
b
etter
p
r
o
b
ab
ilit
ies
o
f
h
az
ar
d
.
Sh
ar
m
a
an
d
Sh
ar
m
a
[
1
]
h
ig
h
lig
h
ts
th
e
u
s
e
o
f
FL
to
d
ea
l
w
ith
d
ata
p
r
i
v
ac
y
in
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
,
ac
c
o
m
p
lis
h
in
g
co
m
p
ar
ab
le
ac
c
u
r
ac
y
to
ce
n
tr
alize
d
m
o
d
els,
a
n
d
in
d
icate
s
f
u
tu
r
e
ex
p
lo
r
atio
n
o
f
tr
a
n
s
f
er
lear
n
in
g
f
o
r
s
tr
o
n
g
er
p
r
e
d
ictiv
e
p
e
r
f
o
r
m
an
ce
.
B
h
ar
ath
i
et
a
l.
[
2
]
e
x
am
in
es
lev
er
a
g
in
g
FL
f
o
r
co
r
o
n
a
r
y
ar
ter
y
d
is
ea
s
e
p
r
ed
ictio
n
u
s
in
g
f
e
d
er
ated
l
o
g
is
tic
r
eg
r
ess
io
n
(
FLR)
an
d
f
ed
er
ated
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
an
d
al
s
o
s
tates
th
at
it
en
s
u
r
es
d
ata
p
r
iv
ac
y
,
r
ea
c
h
in
g
as
m
u
c
h
as
9
5
.
8
%
ac
cu
r
ac
y
,
f
o
r
FLR
ce
n
tr
alize
d
m
o
d
els,
th
r
o
u
g
h
lo
ca
l
s
tatis
t
ics
ag
g
r
eg
atio
n
.
Hay
y
o
lalam
et
a
l.
[
3
]
d
is
cu
s
s
es
th
e
u
s
e
o
f
ed
g
e
co
m
p
u
tin
g
an
d
a
h
y
b
r
i
d
ML
tech
n
iq
u
e
with
b
lac
k
wid
o
w
o
p
tim
izatio
n
f
o
r
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
,
attain
in
g
9
0
.
1
1
%
ac
cu
r
ac
y
,
a
n
d
s
u
g
g
es
ts
f
u
tu
r
e
in
teg
r
atio
n
with
FL
.
Sh
ar
m
a
an
d
Sh
ar
m
a
[
4
]
e
x
a
m
i
n
es
FL
f
o
r
h
e
ar
t
d
is
ea
s
e
d
etec
tio
n
,
r
ea
ch
in
g
9
4
.
9
9
%
ac
cu
r
ac
y
with
a
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etw
o
r
k
(
C
NN
)
m
o
d
el,
em
p
h
asizin
g
p
r
iv
ac
y
p
r
o
tectio
n
,
an
d
s
u
g
g
esti
n
g
f
u
tu
r
e
ex
p
lo
r
atio
n
o
f
d
if
f
er
en
t
ML
an
d
d
ee
p
lear
n
in
g
(
DL
)
tech
n
iq
u
es.
Yu
an
et
a
l.
[
5
]
e
x
p
lo
r
es
a
v
i
r
tu
al
twin
-
ass
is
te
d
FL
p
r
o
to
co
l
f
o
r
d
is
ea
s
e
p
r
e
d
ictio
n
,
wh
ich
will
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
as
well
as
ac
cu
r
ac
y
.
Fu
tu
r
e
s
tu
d
ies
aim
to
o
p
tim
ize
tr
an
s
f
er
lear
n
in
g
f
o
r
im
p
r
o
v
ed
m
ed
ical
im
ag
e
r
ec
o
g
n
itio
n
.
D
o
lo
et
a
l.
[
6
]
e
x
am
in
es
th
e
A
m
o
d
el
f
o
r
p
r
ed
ictin
g
d
iab
ete
s
u
s
in
g
d
if
f
er
e
n
tially
p
r
iv
ate
s
to
ch
asti
c
g
r
ad
ien
t
d
e
s
ce
n
t
f
ed
er
ated
av
er
a
g
in
g
(
D
PS
GDFed
Av
g
)
,
r
ea
ch
in
g
6
0
-
7
0
%
ac
cu
r
ac
y
at
th
e
s
am
e
tim
e
as
m
ak
in
g
s
u
r
e
s
tatis
tics
is
p
r
iv
ate.
Fu
tu
r
e
r
esear
ch
o
b
jectiv
es
a
r
e
to
en
h
an
ce
m
o
d
el
ac
c
u
r
ac
y
an
d
p
r
iv
ac
y
.
Kh
an
et
a
l.
[
7
]
u
s
es
FL
f
o
r
d
is
ea
s
e
p
r
e
d
ictio
n
i
n
u
n
p
r
e
c
e
d
e
n
t
e
d
a
r
e
a
s
u
s
i
n
g
c
h
e
s
t
X
-
r
a
y
s
,
a
c
h
i
e
v
i
n
g
a
2
%
e
f
f
i
c
i
e
n
c
y
i
m
p
r
o
v
e
m
e
n
t
a
n
d
a
n
a
r
e
a
u
n
d
e
r
t
h
e
c
u
r
v
e
(
AUC
)
o
f
7
7
.
9
1
,
w
h
i
l
e
p
r
e
s
e
r
v
i
n
g
p
a
t
i
e
n
t
p
r
i
v
a
c
y
.
F
u
t
u
r
e
r
e
s
e
a
r
c
h
wi
l
l
b
r
o
a
d
e
n
s
c
a
n
t
y
p
e
s
a
n
d
e
n
h
a
n
c
e
d
a
t
a
s
e
t
d
i
v
e
r
s
i
t
y
.
N
a
n
d
h
i
n
i
et
a
l
.
[
8
]
i
n
v
e
s
t
i
g
at
e
s
FL
f
o
r
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
s
e
a
s
e
p
r
e
d
ic
t
io
n
,
h
i
g
h
l
i
g
h
t
i
n
g
i
m
p
r
o
v
e
d
a
c
c
u
r
a
c
y
a
n
d
e
f
f
i
c
i
e
n
c
y
t
h
r
o
u
g
h
i
m
a
g
e
p
r
o
c
e
s
s
i
n
g
a
n
d
d
e
c
e
n
t
r
a
l
i
z
e
d
d
at
a
t
r
ai
n
i
n
g
.
F
u
t
u
r
e
r
e
s
e
a
r
c
h
ai
m
s
t
o
e
n
h
a
n
c
e
p
r
e
d
i
c
t
i
o
n
b
y
r
e
f
i
n
i
n
g
a
l
g
o
r
i
t
h
m
p
e
r
f
o
r
m
a
n
c
e
a
n
d
a
d
d
r
e
s
s
i
n
g
a
g
e
-
r
el
a
t
e
d
d
is
e
as
e
p
r
o
g
r
e
s
s
i
o
n
.
T
h
is
p
ap
er
p
r
esen
ts
a
co
m
p
r
e
h
en
s
iv
e
an
d
cr
itical
o
v
e
r
v
iew
o
f
th
e
cu
r
r
en
t
s
tate
o
f
r
esear
ch
in
th
is
ar
ea
an
d
also
ca
teg
o
r
izes
r
es
ea
r
ch
b
ased
o
n
d
if
f
er
e
n
t
ap
p
r
o
ac
h
es,
s
u
ch
as
ty
p
es
o
f
FL
alg
o
r
ith
m
s
u
s
ed
,
p
r
iv
ac
y
-
p
r
eser
v
in
g
tech
n
iq
u
es
,
an
d
s
p
ec
if
ic
ap
p
licatio
n
s
in
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
.
T
h
e
p
ap
er
also
i
d
en
tifie
s
th
e
r
esear
ch
g
ap
s
an
d
lim
itatio
n
s
.
T
h
e
o
v
er
v
iew
ass
ess
e
s
th
e
im
p
ac
t
o
f
f
ed
er
ated
lear
n
in
g
o
n
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
an
d
o
v
e
r
all
h
ea
lth
ca
r
e
p
r
ac
tices,
h
i
g
h
lig
h
t
in
g
ca
s
e
r
esear
ch
an
d
p
r
ac
tical
im
p
lem
en
tatio
n
s
.
2.
WO
RK
I
NG
ML
ap
p
r
o
ac
h
es
c
o
m
m
o
n
ly
r
eq
u
ir
e
ce
n
tr
alizin
g
t
h
e
tr
ain
i
n
g
d
ata
in
to
a
c
o
m
m
o
n
s
to
r
e
an
d
it
is
d
ep
icted
in
Fig
u
r
e
1
.
T
h
e
li
m
itatio
n
o
f
th
is
ce
n
tr
alize
d
d
ata
is
th
e
co
m
m
u
n
icatio
n
e
x
ch
an
g
e
b
etwe
en
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
AI
-
b
a
s
ed
fe
d
era
ted
lea
r
n
in
g
f
o
r
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
:
a
co
lla
b
o
r
a
tive
a
n
d
p
r
iva
cy
-
…
(
S
tu
ti B
h
a
tt
)
753
s
er
v
er
an
d
th
e
clien
t
as
it
co
u
l
d
b
e
tim
e
-
co
n
s
u
m
in
g
an
d
h
u
r
t
u
s
er
ex
p
er
ien
ce
d
u
e
to
n
etwo
r
k
laten
cy
,
b
atter
y
life
,
an
d
co
n
n
ec
t
iv
ity
.
FL
(
c
o
llab
o
r
ativ
e
lear
n
i
n
g
)
is
a
s
u
b
-
f
ield
o
f
ML
an
d
is
a
d
ec
en
tr
alize
d
ap
p
r
o
ac
h
t
o
tr
ain
in
g
th
e
ML
m
o
d
els wh
er
e
u
s
er
d
ata
is
n
ev
er
tr
an
s
m
itted
to
a
ce
n
tr
al
s
er
v
er
.
Fig
u
r
e
1
.
C
en
tr
alize
d
s
y
s
tem
Star
t
with
d
is
tr
ib
u
tin
g
th
e
m
o
d
el
f
r
o
m
t
h
e
s
er
v
er
t
o
th
e
clie
n
t
b
u
t
d
e
p
lo
y
m
e
n
t
to
ev
e
r
y
cli
en
t
m
u
s
t
b
e
s
tr
ateg
ic
to
av
o
id
in
ter
r
u
p
tio
n
s
in
u
s
er
ex
p
er
ien
ce
.
He
n
ce
o
u
r
p
r
im
a
r
y
task
is
to
id
en
tify
th
e
clien
ts
th
at
ar
e
av
ailab
le
an
d
p
lu
g
g
ed
in
,
an
d
n
o
t
in
ac
ti
v
e
u
s
e.
Ad
d
itio
n
ally
,
d
is
co
v
er
wh
ich
o
n
es
ar
e
s
u
itab
le
an
d
p
o
s
s
ess
s
u
f
f
icien
t
d
ata,
as
n
o
t
all
clie
n
ts
m
ay
m
ee
t
t
h
is
cr
iter
io
n
.
O
n
ce
s
u
itab
le
d
ev
ices
(
u
s
er
1
,
u
s
er
2
,
an
d
u
s
er
3
)
ar
e
id
en
tifie
d
m
o
d
el
ca
n
b
e
d
ep
l
o
y
ed
.
E
ac
h
clien
t
t
h
en
in
d
ep
en
d
en
tly
tr
ain
s
its
m
o
d
el
l
o
ca
lly
u
s
in
g
th
eir
o
wn
d
ata
at
th
eir
e
n
d
(
lo
ca
lly
)
g
en
er
atin
g
a
n
ew
m
o
d
el
lo
ca
lly
,
wh
ich
is
f
u
r
th
e
r
s
en
t
to
th
e
s
e
r
v
er
.
T
h
e
p
o
in
t
h
e
r
e
is
th
e
d
ata
u
s
ed
to
tr
ain
th
e
m
o
d
el
r
em
ain
s
o
n
r
esp
ec
tiv
e
d
ev
ices
an
d
is
n
o
t
tr
an
s
m
itted
.
On
ly
th
e
m
o
d
el
p
ar
am
eter
s
,
s
u
ch
as
weig
h
ts
(
w1
,
w2
,
an
d
w3
)
,
an
d
b
iases
,
ar
e
s
en
t
to
th
e
s
er
v
er
.
T
h
e
s
er
v
er
p
r
o
ce
s
s
es
all
th
e
lo
ca
lly
tr
ain
ed
m
o
d
els
an
d
th
en
p
er
f
o
r
m
s
ag
g
r
eg
atio
n
,
ef
f
ec
tiv
ely
cr
ea
tin
g
a
n
ew
m
o
d
el.
T
o
k
n
o
w
if
th
is
p
r
o
ce
s
s
is
m
ak
in
g
a
g
o
o
d
m
ea
n
in
g
f
u
l
m
o
d
el
b
y
d
o
in
g
th
e
p
r
o
ce
s
s
r
ep
ea
ted
l
y
an
d
with
ev
er
y
r
o
u
n
d
,
th
e
co
m
b
in
ed
m
o
d
el
g
ets a
litt
le
b
it b
etter
with
th
e
h
elp
o
f
d
ata
g
ain
ed
f
r
o
m
all
th
e
clien
ts
.
Fo
r
ad
d
itio
n
al
s
ec
u
r
ity
in
FL
,
we
ca
n
u
s
e
th
e
co
n
ce
p
t
o
f
s
ec
u
r
e
ag
g
r
eg
atio
n
,
w
h
er
e
th
e
s
er
v
er
p
air
s
u
p
d
ev
ices
with
ea
ch
o
th
er
in
a
b
u
d
d
y
s
y
s
tem
.
T
h
e
f
e
d
er
ated
s
y
s
tem
is
d
ep
icted
in
Fig
u
r
e
2
.
Or
g
an
izatio
n
s
lik
e
h
o
s
p
itals
ca
n
also
b
e
r
e
g
ar
d
e
d
as
r
em
o
te
o
r
lo
ca
l
d
ev
ices
th
at
in
cl
u
d
e
a
lar
g
e
n
u
m
b
er
o
f
p
atien
t
d
ata
f
o
r
p
r
ed
ictiv
e
h
ea
lth
ca
r
e
[
9
]
,
[
1
0
]
.
Ho
wev
er
,
h
o
s
p
itals
p
e
r
f
o
r
m
u
n
d
er
s
tr
ict
p
r
iv
ac
y
p
r
ac
tices
an
d
m
ig
h
t
f
ac
e
leg
al
,
ad
m
in
is
tr
ativ
e,
o
r
m
o
r
al
co
n
s
tr
ain
ts
th
at
r
eq
u
ir
e
d
ata
t
o
r
e
m
ain
lo
ca
l.
FL
is
a
p
r
o
m
is
in
g
an
s
wer
f
o
r
th
ese
ap
p
licatio
n
s
,
as
it
m
ay
r
ed
u
ce
p
r
ess
u
r
e
o
n
th
e
n
etwo
r
k
a
n
d
all
o
w
p
r
iv
ate
lear
n
in
g
am
o
n
g
n
u
m
er
o
u
s
co
r
p
o
r
atio
n
s
.
W
e
f
o
u
n
d
th
at
co
m
p
ar
ed
t
o
o
th
er
m
eth
o
d
o
lo
g
ies
u
s
ed
f
o
r
d
is
ea
s
e
p
r
ed
ictio
n
f
ed
er
ated
lear
n
in
g
g
iv
es
b
ette
r
r
esu
lt
wh
eth
er
it
is
ab
o
u
t
p
r
iv
ac
y
,
s
ec
u
r
ity
m
a
n
ag
em
e
n
t
o
r
b
etter
r
esu
lt
an
d
p
er
f
o
r
m
an
ce
,
FL
tech
n
iq
u
es a
ce
th
em
all.
As
FL
s
im
p
lifie
s
ev
er
y
th
in
g
i
t
also
h
as
ce
r
tain
lim
itatio
n
s
,
o
n
e
o
f
th
e
m
is
th
e
p
r
o
b
lem
f
o
r
m
u
latio
n
.
T
h
e
ty
p
ical
FL
p
r
o
b
le
m
in
v
o
l
v
es
s
tu
d
y
in
g
as
well
as
d
ev
elo
p
in
g
a
s
in
g
le,
g
l
o
b
al
s
tatis
tic
al
m
o
d
el
u
s
in
g
d
ata
s
to
r
ed
o
n
ten
s
t
o
p
r
o
b
a
b
ly
h
u
n
d
r
e
d
s
o
f
th
o
u
s
an
d
s
o
f
r
e
m
o
te
d
ev
ices.
I
n
p
ar
ticu
lar
,
th
e
aim
is
u
s
u
ally
to
m
in
im
ize
th
e
s
u
b
s
eq
u
e
n
t o
b
je
ctiv
e
f
u
n
ctio
n
:
(
)
,
ℎ
(
)
=
∑
(
)
=
1
(
1
)
wh
er
e
m
r
ep
r
esen
ts
t
h
e
to
tal
n
u
m
b
er
o
f
d
ev
ices
,
d
en
o
tes
lo
c
al
o
b
jectiv
e
f
u
n
ctio
n
f
o
r
th
e
k
th
d
ev
ice
,
an
d
i
n
d
icate
s
th
e
r
elativ
e
im
p
ac
t o
f
ea
ch
d
e
v
ice
with
≥
0
.
∑
=
1
=
1
(
2
)
T
h
e
lo
ca
l
o
b
jectiv
e
f
u
n
ctio
n
is
ty
p
ically
d
ef
in
ed
as
th
e
em
p
ir
ical
r
is
k
ca
lcu
lated
f
r
o
m
th
e
lo
ca
l
d
ata.
T
h
e
u
s
er
d
ete
r
m
in
es th
e
r
elativ
e
im
p
ac
t o
f
ea
ch
d
ev
ice
,
co
m
m
o
n
ly
s
et
to
=
1
/m
o
r
=
n
k
/n
,
in
th
is
co
n
tex
t
n
r
ep
r
esen
ts
th
e
to
tal
n
u
m
b
e
r
o
f
s
am
p
les
ac
r
o
s
s
all
d
ev
ices
[
1
1
]
,
[
1
2
]
.
W
h
ile
th
is
is
a
co
m
m
o
n
o
b
jectiv
e
in
FL,
alter
n
ativ
e
a
p
p
r
o
ac
h
es
ex
is
t,
s
u
ch
as
co
n
cu
r
r
en
tly
lear
n
in
g
r
elate
d
l
o
c
al
m
o
d
els
th
r
o
u
g
h
m
u
lti
-
task
lear
n
in
g
wh
er
e
ea
c
h
an
d
ev
er
y
d
ev
ice
co
r
r
esp
o
n
d
s
to
a
d
is
tin
ct
ta
s
k
.
B
o
th
th
e
m
u
lti
-
task
an
d
m
eta
-
lear
n
in
g
p
er
s
p
ec
tiv
es
o
f
f
er
av
en
u
es
f
o
r
p
er
s
o
n
alize
d
o
r
d
ev
ice
-
s
p
ec
if
ic
m
o
d
elin
g
,
ef
f
ec
tiv
ely
ad
d
r
ess
in
g
th
e
s
tatis
t
ical
h
eter
o
g
en
eity
o
f
th
e
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
14
,
No
.
3
,
Dec
em
b
er
20
25
:
751
-
7
5
9
754
Fig
u
r
e
2
.
Fed
er
ate
d
s
y
s
tem
s
3.
F
E
DE
R
AT
E
D
L
E
AR
NING
I
N
H
E
A
L
T
H
CA
RE
Or
g
an
izatio
n
s
s
u
ch
as
h
o
s
p
itals
ca
n
b
e
v
iewe
d
as
r
em
o
te
d
ev
ices
th
at
h
o
u
s
e
ex
ten
s
iv
e
p
atien
t
r
ec
o
r
d
s
f
o
r
p
r
e
d
ictiv
e
h
ea
lth
c
ar
e
p
u
r
p
o
s
es
[
1
3
]
.
H
o
wev
er
,
h
o
s
p
itals
f
u
n
ctio
n
u
n
d
er
s
tr
ict
p
r
iv
ac
y
p
r
o
to
c
o
ls
an
d
m
ay
en
co
u
n
ter
le
g
al,
ad
m
in
is
tr
ativ
e,
o
r
m
o
r
al/eth
ical
co
n
s
tr
ain
ts
th
at
r
eq
u
ir
e
d
ata
lo
ca
lity
.
FL
em
er
g
es
as
a
p
r
o
m
is
in
g
s
o
lu
tio
n
f
o
r
s
u
c
h
s
ce
n
ar
io
s
,
as
it
m
ay
allev
i
ate
s
tr
ess
o
n
th
e
n
etwo
r
k
e
n
ab
lin
g
co
n
f
id
en
tial
lear
n
in
g
am
o
n
g
m
u
ltip
le
d
ev
ices
o
r
o
r
g
an
izatio
n
s
.
Fig
u
r
e
3
illu
s
tr
ates
an
ap
p
licatio
n
s
ce
n
ar
io
wh
er
ein
a
m
o
d
el
is
tr
ain
ed
f
r
o
m
d
is
tr
ib
u
ted
d
ig
ital
h
ea
lth
r
ec
o
r
d
s
.
T
h
e
lo
ca
l
d
ata
co
n
s
is
ts
o
f
th
e
p
atien
t’
s
h
is
to
r
y
o
r
m
ed
ical
r
ec
o
r
d
s
wh
ich
r
em
ain
s
co
n
f
id
en
tial
[
1
4
]
.
Priv
a
cy
an
d
s
ec
u
r
ity
ar
e
a
m
ajo
r
co
n
ce
r
n
o
f
an
y
o
r
g
an
izatio
n
.
Un
lik
e
co
n
v
en
ti
o
n
al
ce
n
tr
alize
d
s
y
s
tem
lear
n
i
n
g
,
wh
er
ei
n
d
ata
is
co
llected
an
d
p
r
o
ce
s
s
ed
in
a
ce
n
tr
al
s
er
v
er
,
FL
allo
ws
m
o
d
els
to
b
e
tr
ain
ed
th
r
o
u
g
h
o
u
t
m
o
r
e
th
an
o
n
e
d
ec
en
tr
a
lized
s
er
v
er
wh
ile
p
r
eser
v
in
g
t
h
e
s
tatis
tics
lo
ca
li
ze
d
.
Min
im
izin
g
t
h
e
tr
an
s
f
er
o
f
s
tatis
tics
d
r
asti
ca
lly
lo
wer
s
th
e
p
r
o
b
ab
ilit
y
o
f
d
ata
in
ter
ce
p
tio
n
o
r
leak
a
g
e
[
1
5
]
.
FL
p
er
m
its
th
e
ag
g
r
eg
atio
n
o
f
k
n
o
wled
g
e
f
r
o
m
n
u
m
er
o
u
s
d
atasets
th
r
o
u
g
h
o
u
t sp
ec
ial
in
s
titu
tio
n
s
,
lead
in
g
to
ex
tr
a
s
tr
o
n
g
an
d
g
en
er
alize
d
m
o
d
els.
Fig
u
r
e
3
.
FL
in
h
ea
lth
ca
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
AI
-
b
a
s
ed
fe
d
era
ted
lea
r
n
in
g
f
o
r
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
:
a
co
lla
b
o
r
a
tive
a
n
d
p
r
iva
cy
-
…
(
S
tu
ti B
h
a
tt
)
755
4.
AL
G
O
RI
T
H
M
S
ML
an
d
in
f
o
r
m
atio
n
m
in
in
g
-
b
ased
tech
n
iq
u
es
f
o
r
th
e
p
r
e
d
ictio
n
an
d
d
etec
tio
n
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
o
r
d
er
co
u
ld
b
e
o
f
s
u
p
er
b
s
cien
tific
u
tili
ty
h
o
wev
er
ar
e
r
elativ
ely
ch
allen
g
in
g
to
d
ev
el
o
p
.
I
n
m
o
s
t
co
u
n
tr
ies,
th
er
e'
s
a
lack
o
f
ca
r
d
io
v
ascu
l
ar
k
n
o
wled
g
e
an
d
an
e
n
o
r
m
o
u
s
p
r
ice
o
f
in
co
r
r
ec
tly
id
e
n
tif
ied
in
s
tan
ce
s
wh
ich
ca
n
b
e
ad
d
r
ess
ed
b
y
d
ev
elo
p
in
g
co
r
r
ec
t
an
d
ef
f
icien
t
ea
r
ly
-
s
tag
e
co
r
o
n
ar
y
h
ea
r
t
d
is
o
r
d
er
p
r
e
d
ictio
n
b
y
an
aly
tical
g
u
id
e
o
f
clin
ical
d
e
cisi
o
n
-
m
ak
in
g
with
v
ir
tu
al
p
at
ien
t
r
ec
o
r
d
s
[
1
6
]
,
[
1
7
].
T
h
is
o
b
s
er
v
atio
n
aim
ed
t
o
d
is
co
v
er
ML
class
if
ier
s
with
th
e
h
ig
h
est
ac
cu
r
ac
y
f
o
r
s
u
ch
d
iag
n
o
s
tic
p
u
r
p
o
s
es.
Sev
e
r
al
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
s
wer
e
ca
r
r
ied
o
u
t
a
n
d
co
m
p
a
r
ed
f
o
r
o
v
er
all
p
er
f
o
r
m
an
ce
an
d
ac
cu
r
ac
y
in
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
.
So
m
e
m
ajo
r
ML
al
g
o
r
ith
m
s
ar
e
d
is
cu
s
s
ed
in
th
e
f
o
llo
win
g
s
ec
tio
n
:
−
S
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
(
S
V
M
)
:
a
t
y
p
e
o
f
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
u
s
e
d
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
r
e
g
r
e
s
s
i
o
n
[
18
]
,
[
19
]
.
T
h
e
m
a
i
n
i
d
e
a
b
e
h
i
n
d
d
e
v
e
l
o
p
i
n
g
i
s
t
o
f
i
n
d
t
h
e
h
y
p
e
r
p
l
a
n
e
i
n
a
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
s
p
a
c
e
t
h
a
t
m
a
x
i
m
a
l
l
y
s
e
p
a
r
a
t
e
s
t
h
e
d
i
f
f
e
r
e
n
t
c
l
a
s
s
e
s
w
h
i
c
h
r
e
s
u
l
t
s
i
n
p
r
é
c
i
s
e
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
.
F
o
r
l
i
n
e
a
r
S
V
M
c
l
a
s
s
i
f
i
e
r
:
=
{
1
:
+
≥
0
0
:
+
<
0
(
3
)
−
L
o
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
:
u
s
e
d
to
p
r
e
d
ict
b
i
-
class
if
icatio
n
p
r
o
b
lem
s
,
s
u
c
h
as
em
ail
s
p
am
o
r
n
o
t,
y
es
o
r
n
o
,
0
o
r
1
,
tr
u
e
o
r
f
alse
.
L
R
u
s
es a
s
ig
m
o
id
f
u
n
ctio
n
,
i.e
.
,
a
lo
g
is
tic
f
u
n
ctio
n
[
1
4
].
(
)
=
1
1
+
−
(
4
)
Sig
m
o
id
f
u
n
ctio
n
is
s
im
p
ly
tr
y
in
g
to
co
n
v
er
t
th
e
in
d
ep
e
n
d
en
t
v
ar
iab
le
(
x
)
in
to
an
e
x
p
r
ess
io
n
o
f
p
r
o
b
a
b
ilit
y
th
at
r
a
n
g
es
b
etwe
en
0
a
n
d
1
with
r
esp
ec
t
to
th
e
d
ep
e
n
d
en
t
v
ar
iab
le
.
L
R
with
m
u
ltip
le
in
d
ep
en
d
en
t v
ar
ia
b
les:
=
(
0
+
1
×
1
+
2
×
2
+
…
…
…
×
)
(
5
)
w
h
er
e
i
s t
h
e
r
eg
r
ess
io
n
co
ef
f
icien
t
.
−
L
in
ea
r
r
eg
r
ess
io
n
:
m
o
d
ellin
g
r
elatio
n
s
h
ip
s
ar
e
lin
ea
r
in
n
at
u
r
e.
I
t
is
a
f
ac
ts
ev
alu
atio
n
a
p
p
r
o
ac
h
th
at
p
r
ed
icts
th
e
v
alu
e
o
f
u
n
k
n
o
wn
f
ac
ts
b
y
u
s
in
g
a
n
o
th
er
ass
o
cia
ted
an
d
k
n
o
wn
d
ata
v
alu
e.
L
ik
e
if
th
e
v
alu
e
o
f
x
in
in
cr
ea
s
in
g
v
alu
e
o
f
y
w
ill also
in
cr
ea
s
e
[
20
].
Simp
le
l
i
n
ea
r
r
eg
r
ess
io
n
:
=
0
+
1
+
1
(
6
)
W
h
e
r
e
1
is
th
e
in
d
ep
en
d
en
t v
a
r
iab
le
,
y
is
th
e
d
e
p
en
d
e
n
t v
ar
iab
le
,
0
,
1
ar
e
co
e
f
f
icien
t
s
o
f
r
eg
r
ess
io
n
.
T
h
e
M
u
ltip
le
L
in
e
ar
r
eg
r
ess
io
n
s
ar
e
r
e
p
r
esen
ted
b
y
,
=
0
×
0
+
1
×
1
+
2
×
2
+
…
…
.
×
+
(
7
)
−
R
an
d
o
m
f
o
r
est
:
t
y
p
e
o
f
en
s
e
m
b
le
ML
m
o
d
el,
wh
e
r
e
m
u
lti
p
le
m
o
d
els
ar
e
wo
r
k
i
n
g
to
g
et
h
er
to
m
ak
e
a
p
r
ed
ictio
n
.
I
n
th
e
ca
s
e
o
f
r
an
d
o
m
f
o
r
est,
th
e
s
m
aller
m
o
d
els
ar
e
d
ec
is
io
n
tr
ee
s
[
2
1
]
,
[
2
2
]
.
E
ac
h
in
d
iv
id
u
al
d
ec
is
io
n
t
r
ee
will
m
ak
e
a
p
r
ed
ictio
n
an
d
t
h
en
th
e
f
in
al
p
r
ed
ictio
n
is
m
ad
e
a
f
ter
a
g
g
r
eg
atio
n
o
f
all
th
e
p
r
ev
io
u
s
o
u
tp
u
ts
/ p
r
ed
i
ctio
n
s
[
18
]
,
[
19
].
=
1
∑
(
−
)
2
=
1
(
8
)
W
h
er
e
MSE
i
s
a
m
ea
n
s
q
u
a
r
e
er
r
o
r
,
f
o
r
n
n
u
m
b
er
o
f
d
a
ta
p
o
in
ts
,
fi
is
th
e
v
alu
e
r
etu
r
n
ed
b
y
ea
c
h
d
ec
is
io
n
tr
ee
m
o
d
el
en
s
em
b
le
,
i is a
d
ata
p
o
in
t a
n
d
y
i is th
e
a
ctu
al
v
alu
e
f
o
r
i.
−
Naïv
e
B
ay
es
(
NB
)
clas
s
if
ier
:
s
u
p
er
v
is
ed
lear
n
in
g
b
ased
o
n
p
r
o
b
ab
ilis
tic
lo
g
ic
u
s
es
B
a
y
es’
th
eo
r
em
.
Her
e
n
aïv
e
p
ar
t
ca
m
e
f
r
o
m
a
n
ass
u
m
p
tio
n
s
tatin
g
f
ea
t
u
r
es
in
d
ata
ar
e
i
n
d
ep
e
n
d
en
t,
(
n
o
t
in
th
e
c
ase
o
f
r
ea
l
-
wo
r
ld
d
ata
)
[
2
3
]
.
T
h
e
p
r
o
b
ab
ilit
y
(
P
)
is
r
ep
r
esen
ted
b
y
,
(
|
)
=
(
|
)
∙
(
)
(
)
(
9
)
5.
CO
M
P
ARA
T
I
V
E
ANA
L
YS
I
S
T
ab
le
1
in
clu
d
es
a
co
m
p
ar
ati
v
e
an
aly
s
is
b
etwe
en
d
if
f
er
en
t
wo
r
k
s
f
o
r
th
e
p
u
r
p
o
s
e
o
f
d
e
tectio
n
o
f
ca
r
d
io
v
ascu
lar
d
is
ea
s
e
(
C
VD)
.
T
h
is
an
aly
s
is
in
clu
d
es
a
s
u
m
m
ar
y
o
f
th
e
m
eth
o
d
o
lo
g
y
a
p
p
lied
b
y
d
if
f
er
e
n
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
14
,
No
.
3
,
Dec
em
b
er
20
25
:
751
-
7
5
9
756
au
th
o
r
s
an
d
th
e
co
r
r
esp
o
n
d
in
g
r
esu
lts
o
b
tain
ed
af
ter
th
e
a
p
p
l
ica
tio
n
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
ies
[
2
4
]
,
[
2
5
]
.
T
h
e
k
ey
f
in
d
in
g
s
ar
e
also
s
ep
ar
ately
m
en
tio
n
e
d
wh
ic
h
s
u
g
g
ests
th
e
ef
f
ec
tiv
en
es
s
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
.
Priv
ac
y
an
d
s
e
cu
r
ity
f
ea
tu
r
e
is
also
m
en
tio
n
ed
in
th
e
ab
o
v
e
wo
r
k
s
[
2
6
]
.
T
h
e
co
m
p
a
r
ativ
e
ev
alu
atio
n
o
f
ar
tific
ial
in
tellig
en
ce
(
AI
)
-
p
r
im
ar
ily
b
ased
FL
f
o
r
C
VD
p
r
ed
ictio
n
s
u
g
g
ests
th
at
FL
ca
n
ac
h
iev
e
ac
cu
r
ac
y
n
ea
r
a
ce
n
tr
alize
d
m
o
d
el
wh
ile
m
ain
tain
in
g
in
f
o
r
m
atio
n
p
r
iv
ac
y
.
Fo
r
ex
a
m
p
le
,
f
ed
e
r
ated
L
R
a
n
d
f
ed
er
ated
SVM
ac
co
m
p
lis
h
ed
as
m
u
c
h
as
9
5
.
8
ac
c
u
r
ac
y
an
d
f
e
d
er
ated
C
NN
m
o
d
el
r
ea
ch
ed
9
4
.
9
9
ac
cu
r
ac
y
,
n
ea
r
in
g
th
e
ce
n
tr
alize
d
f
ash
io
n
o
f
9
7
%
[
2
7
].
Ov
er
all,
FL
a
f
f
o
r
d
s
a
s
tr
o
n
g
,
p
r
iv
ac
y
-
m
ain
t
ain
in
g
o
p
p
o
r
tu
n
ity
co
m
p
ar
ed
to
ce
n
tr
alize
d
ap
p
r
o
ac
h
es,
with
f
u
tu
r
e
s
tu
d
ies h
av
i
n
g
to
o
p
tim
ize
its
ef
f
ec
tiv
en
es
s
in
h
ea
lth
ca
r
e.
T
ab
le
1
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
b
etwe
en
d
if
f
e
r
en
t w
o
r
k
s
f
o
r
t
h
e
p
u
r
p
o
s
e
o
f
d
etec
tio
n
o
f
C
VD
M
e
t
h
o
d
o
l
o
g
y
K
e
y
f
i
n
d
i
n
g
s
A
l
g
o
r
i
t
h
ms
D
a
t
a
s
o
u
r
c
e
P
&S
F
L
u
s
i
n
g
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
a
n
d
S
V
M
[
2
]
P
r
e
d
i
c
t
i
n
g
h
e
a
r
t
d
i
sea
s
e
a
c
c
u
r
a
c
y
:
F
L
=
8
9
%,
c
e
n
t
r
a
l
i
z
e
d
=
9
5
.
8
;
F
S
V
M
p
e
r
f
o
r
m
e
d
w
e
l
l
c
o
m
p
a
r
e
d
t
o
F
L
R
.
F
LR
,
f
e
d
e
r
a
t
e
d
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
(
F
S
V
M
)
U
C
I
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
r
e
p
o
si
t
o
r
y
.
✓
R
a
n
d
o
m
o
v
e
r
sa
mp
l
i
n
g
o
n
t
h
e
d
a
t
a
s
e
t
i
n
c
l
u
d
i
n
g
sam
p
l
e
s
o
f
a
b
o
u
t
1
l
a
k
h
.
FL
w
i
t
h
C
N
N
o
n
U
C
I
C
l
e
v
e
l
a
n
d
d
a
t
a
set
[
4
]
F
o
r
h
e
a
r
t
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
:
f
e
d
e
r
a
t
e
d
C
N
N
=
9
4
.
9
9
%
,
c
l
o
se
d
t
o
c
e
n
t
r
a
l
i
z
e
d
C
N
N
=
9
7
%
FL
-
C
N
N
U
C
I
C
l
e
v
e
l
a
n
d
d
a
t
a
se
t
✓
C
l
a
s
si
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s (
d
e
c
i
si
o
n
t
r
e
e
(
DT
)
,
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
,
p
o
l
y
n
o
mi
a
l
r
e
g
r
e
ss
i
o
n
,
NB
,
S
V
M
,
C
N
N
)
a
r
e
c
o
m
p
a
r
e
d
,
a
n
d
m
i
ssi
n
g
v
a
l
u
e
s
a
r
e
p
r
e
d
i
c
t
e
d
u
si
n
g
s
i
n
g
l
e
a
n
d
m
u
l
t
i
-
v
a
l
u
e
i
mp
u
t
a
t
i
o
n
s
[
8
]
F
o
r
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
s
e
a
se
.
A
c
c
u
r
a
c
y
:
LR
=
9
8
.
4
P
o
l
y
n
o
m
i
a
l
R
.
:
9
5
.
3
NB
=
9
1
.
3
DT
=
9
3
.
6
F
L=
9
8
.
7
D
T,
l
i
n
e
a
r
r
e
g
r
e
s
si
o
n
,
P
o
l
y
n
o
m
i
a
l
r
e
g
r
e
ss
i
o
n
,
NB
a
n
d
p
r
o
p
o
s
e
d
F
L
K
a
g
g
l
e
d
a
t
a
se
t
✓
mRM
R
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
w
i
t
h
LR
a
n
d
S
V
M
[
9
]
P
r
e
d
i
c
t
i
n
g
H
e
a
r
t
d
i
se
a
se.
A
c
c
u
r
a
c
y
:
F
L=
8
5
%
C
e
n
t
r
a
l
i
z
e
d
=
3
6
%
a
n
d
s
i
mi
l
a
r
F1
-
s
c
o
r
e
s,
F
L=
9
1
%,
c
e
n
t
r
a
l
i
z
e
d
=
9
2
%
LR
S
V
M
P
TB
d
i
a
g
n
o
st
i
c
EC
G
d
a
t
a
b
a
se
✓
C
o
r
r
e
l
a
t
i
o
n
-
b
a
s
e
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
n
d
o
v
e
r
sa
m
p
l
i
n
g
,
S
M
O
TE
w
i
t
h
a
v
a
r
i
e
t
y
o
f
M
L
a
l
g
o
r
i
t
h
ms
o
n
a
d
a
t
a
se
t
w
i
t
h
1
4
f
e
a
t
u
r
e
s
a
n
d
1
0
0
0
r
e
c
o
r
d
s
[
1
0
]
P
r
e
d
i
c
t
i
o
n
o
f
h
e
a
r
t
d
i
s
e
a
s
e
A
c
c
u
r
a
c
y
%
a
f
t
e
r
sam
p
l
i
n
g
(
o
v
e
r
sam
p
l
i
n
g
,
smo
t
e
):
LR
=
9
6
.
1
%,
1
0
0
%
NB
=
9
4
.
7
%
,
1
0
0
%
K
N
N
=
9
7
%
,
9
8
.
3
6
%
R
a
n
d
o
m f
o
r
e
s
t
=
9
9
.
2
0
%,
1
0
0
%,
S
V
M
=
9
7
.
6
0
%,
1
0
0
%,
Tr
e
e
=
9
8
.
7
5
%
,
1
0
0
%
R
a
n
d
o
m
o
v
e
r
sam
p
l
i
n
g
,
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
(
K
N
N
)
,
a
n
d
S
M
O
TE
t
e
c
h
n
i
q
u
e
P
u
b
l
i
c
d
a
t
a
se
t
✓
X
G
B
o
o
st
,
A
d
a
B
o
o
st
,
r
a
n
d
o
m f
o
r
e
s
t
,
DT
,
NB
,
a
n
d
LR
.
K
a
g
g
l
e
d
a
t
a
s
e
t
[
28
]
P
r
e
d
i
c
t
i
o
n
o
f
h
e
a
r
t
d
i
s
e
a
s
e
LR
m
o
d
e
l
a
c
c
u
r
a
c
y
=
9
1
.
5
7
%
X
GB
o
o
st
,
A
d
a
B
o
o
st
,
r
a
n
d
o
m
f
o
r
e
s
t
,
DT
,
LR
,
NB
K
a
g
g
l
e
d
a
t
a
se
t
(
3
1
9
,
7
9
5
)
✓
To
h
a
n
d
l
e
c
l
a
ss
e
s
t
h
a
t
a
r
e
i
m
b
a
l
a
n
c
e
d
r
e
sea
r
c
h
e
r
s
u
s
e
S
M
O
TE,
a
n
d
M
I
N
-
M
A
X
n
o
r
ma
l
i
z
a
t
i
o
n
i
s
a
p
p
l
i
e
d
a
f
t
e
r
w
a
r
d
.
A
t
t
h
e
e
n
d
3
M
L
c
l
a
ssi
f
i
e
r
s
a
r
e
u
se
d
i
.
e
.
G
a
u
ssi
a
n
N
B
,
K
N
N
f
o
r
K
=
5
,
S
V
M
(
‘
r
b
f
’
)
[
29
]
P
r
e
d
i
c
t
i
o
n
o
f
h
e
a
r
t
d
i
s
e
a
s
e
P
r
e
c
i
s
i
o
n
=
9
2
.
5
0
%
R
e
c
a
l
l
,
9
2
.
2
2
%
a
n
d
F
1
-
sc
o
r
e
=
9
2
.
3
6
%
G
a
u
ss
i
a
n
,
NB
,
S
V
M
,
K
N
N
,
s
o
f
t
v
o
t
i
n
g
C
l
e
v
e
l
a
n
d
h
e
a
r
t
d
i
s
e
a
se
d
a
t
a
se
t
t
a
k
e
n
f
r
o
m
U
C
I
mac
h
i
n
e
l
e
a
r
n
i
n
g
r
e
p
o
si
t
o
r
y
✓
P
r
o
p
o
se
d
h
y
b
r
i
d
r
a
n
d
o
m f
o
r
e
st
w
i
t
h
a
l
i
n
e
a
r
mo
d
e
l
(
H
R
F
LM
)
[1
1
]
A
c
c
u
r
a
c
y
=
8
8
.
4
,
p
r
e
c
i
s
i
o
n
=
9
0
.
1
,
F
-
mea
su
r
e
=
9
0
,
se
n
s
i
t
i
v
i
t
y
=
9
2
.
8
,
s
p
e
c
i
f
i
c
i
t
y
=
8
2
.
6
M
L
t
e
c
h
n
i
q
u
e
s
,
H
R
F
LM
.
C
l
e
v
e
l
a
n
d
d
a
t
a
se
t
c
o
l
l
e
c
t
e
d
f
r
o
m a
U
C
I
M
L
r
e
p
o
si
t
o
r
y
.
X
D
e
si
g
n
e
d
A
C
V
D
-
H
B
O
M
D
L
t
e
c
h
n
i
q
u
e
w
i
t
h
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
h
y
p
e
r
p
a
r
a
me
t
e
r
t
u
n
i
n
g
[1
2
]
A
C
V
D
-
H
B
O
M
D
L
a
c
h
i
e
v
e
d
9
9
.
3
9
%
a
c
c
u
r
a
c
y
i
n
C
V
D
d
i
a
g
n
o
si
s.
M
i
n
-
ma
x
s
c
a
l
e
r
f
o
r
d
a
t
a
p
r
e
p
r
o
c
e
ss
i
n
g
H
o
n
e
y
b
a
d
g
e
r
o
p
t
i
m
i
z
a
t
i
o
n
(
H
B
O
)
a
l
g
o
r
i
t
h
m f
o
r
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
,
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
i
f
i
e
d
n
e
u
r
a
l
n
e
t
w
o
r
k
c
l
a
ss
i
f
i
e
r
,
B
a
y
e
s
i
a
n
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
h
y
p
e
r
p
a
r
a
me
t
e
r
t
u
n
i
n
g
K
a
g
g
l
e
r
e
p
o
si
t
o
r
y
:
a
g
g
r
e
g
a
t
e
d
f
r
o
m
v
a
r
i
o
u
s re
g
i
o
n
s
a
n
d
S
t
a
t
l
o
g
d
a
t
a
se
t
s.
✓
C
V
w
i
t
h
K
-
f
o
l
d
,
D
a
t
a
s
p
l
i
t
i
n
t
o
t
r
a
i
n
i
n
g
,
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
,
a
n
d
t
e
s
t
i
n
g
;
e
v
a
l
u
a
t
e
d
w
i
t
h
K
-
f
o
l
d
C
V
[1
3
]
A
c
c
u
r
a
c
y
=
9
7
.
3
2
%,
r
e
c
a
l
l
=
9
7
.
5
8
%
,
P
r
e
c
i
s
i
o
n
=
9
7
.
1
6
%,
F
1
-
m
e
a
s
u
r
e
=
9
7
.
3
7
%,
s
p
e
c
i
f
i
c
i
t
y
=
9
6
.
8
7
%
G
-
mea
n
=
9
7
.
2
2
%
N
B
,
K
-
N
N
,
S
V
M
,
r
a
n
d
o
m
f
o
r
e
s
t
,
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
ANN)
S
p
e
c
i
f
i
c
me
d
i
c
a
l
d
a
t
a
se
t
(
r
e
p
o
si
t
o
r
y
n
o
t
m
e
n
t
i
o
n
e
d
)
✓
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
AI
-
b
a
s
ed
fe
d
era
ted
lea
r
n
in
g
f
o
r
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
:
a
co
lla
b
o
r
a
tive
a
n
d
p
r
iva
cy
-
…
(
S
tu
ti B
h
a
tt
)
757
6.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
e
x
p
lo
r
es
th
e
u
tili
ty
o
f
AI
-
b
ased
FL
f
o
r
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
,
em
p
h
asizin
g
its
im
p
o
r
tan
ce
in
m
ai
n
tain
in
g
an
af
f
ec
ted
p
e
r
s
o
n
'
s
p
r
iv
ac
y
ev
en
as
lev
er
ag
in
g
d
is
tr
ib
u
ted
r
ec
o
r
d
s
f
r
o
m
h
o
s
p
itals
an
d
o
th
er
o
r
g
an
izatio
n
s
.
FL
em
er
g
es
as
a
p
o
wer
f
u
l
s
o
l
u
ti
o
n
,
ad
d
r
ess
in
g
th
e
r
estrict
io
n
s
o
f
tr
ad
itio
n
al
ce
n
tr
alize
d
ML
m
o
d
els,
in
p
a
r
ticu
lar
with
in
th
e
c
o
n
tex
t
o
f
d
ata
wh
ich
is
v
er
y
s
en
s
itiv
e
f
o
r
th
e
p
atien
t.
T
h
e
co
m
p
ar
ativ
e
ev
alu
atio
n
am
o
n
g
ce
n
tr
alize
d
an
d
FL
s
tr
ateg
ie
s
ex
h
ib
its
th
at
FL
ca
n
g
ath
er
c
o
m
p
etitiv
e
a
cc
u
r
ac
y
r
ates.
Fo
r
in
s
tan
ce
,
th
e
FL
-
C
NN
m
o
d
el
v
alid
ated
a
v
alid
atio
n
ac
cu
r
ac
y
o
f
9
4
.
9
9
%
o
n
th
e
UC
I
C
lev
elan
d
d
ataset,
wh
ich
is
r
em
ar
k
ab
ly
clo
s
e
to
th
e
9
7
%
ac
cu
r
ac
y
p
er
f
o
r
m
ed
b
y
ce
n
tr
alize
d
C
NN
m
o
d
els.
T
h
is
h
ig
h
lig
h
ts
FL`
s
ca
p
ab
ilit
y
to
o
f
f
er
ef
f
ec
tiv
e
p
r
ed
ictiv
e
o
v
e
r
all
p
er
f
o
r
m
a
n
ce
ev
en
as
en
s
u
r
in
g
th
at
af
f
ec
ted
p
er
s
o
n
in
f
o
r
m
atio
n
s
tay
s
s
tab
le
an
d
d
ec
e
n
tr
alize
d
.
ACK
NO
WL
E
DG
E
M
E
NT
T
h
is
r
esear
ch
wo
r
k
was
s
u
p
p
o
r
ted
by
“
W
o
o
s
o
n
g
Un
iv
e
r
s
ity
’
s
Aca
d
em
ic
R
esear
ch
Fu
n
d
in
g
-
2
0
2
5
”
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
wo
r
k
was
s
u
p
p
o
r
ted
by
“
W
o
o
s
o
n
g
Un
iv
e
r
s
ity
’
s
Aca
d
em
ic
R
esear
ch
Fu
n
d
in
g
-
2
0
2
5
”
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Stu
ti B
h
att
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Su
r
en
d
er
R
ed
d
y
Salk
u
ti
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Seo
n
g
-
C
h
eo
l K
im
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
No
t a
p
p
licab
le
—
th
is
s
tu
d
y
d
i
d
n
o
t in
v
o
lv
e
h
u
m
a
n
p
ar
ticip
a
n
ts
r
eq
u
ir
in
g
in
f
o
r
m
ed
c
o
n
s
en
t.
E
T
H
I
CAL AP
P
RO
V
AL
No
t a
p
p
licab
le
—
th
is
s
tu
d
y
d
i
d
n
o
t in
v
o
lv
e
h
u
m
a
n
p
ar
ticip
a
n
ts
o
r
an
im
als.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
d
o
es
n
o
t a
p
p
l
y
to
th
is
ar
ticle
as n
o
n
ew
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
P
.
S
h
a
r
m
a
a
n
d
S
.
S
h
a
r
m
a
,
“
A
c
o
mp
r
e
h
e
n
si
v
e
st
u
d
y
o
f
t
h
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
w
i
t
h
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
p
r
e
d
i
c
t
i
n
g
h
e
a
r
t
d
i
s
e
a
se
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
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
n
t
e
m
p
o
ra
ry
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s,
I
C
3
I
2
0
2
3
,
S
e
p
.
2
0
2
3
,
p
p
.
1
8
6
7
–
1
8
7
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
I
5
9
1
1
7
.
2
0
2
3
.
1
0
3
9
7
7
1
6
.
[
2
]
S
.
K
.
B
h
a
r
a
t
h
i
,
M
.
D
h
a
v
a
ma
n
i
,
a
n
d
K
.
N
i
r
a
n
j
a
n
,
“
A
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
b
a
s
e
d
a
p
p
r
o
a
c
h
f
o
r
h
e
a
r
t
d
i
se
a
s
e
p
r
e
d
i
c
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
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
p
u
t
i
n
g
Me
t
h
o
d
o
l
o
g
i
e
s
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
C
M
C
2
0
2
2
,
M
a
r
.
2
0
2
2
,
p
p
.
1
1
1
7
–
1
1
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
M
C
5
3
4
7
0
.
2
0
2
2
.
9
7
5
4
1
1
9
.
[
3
]
V
.
H
a
y
y
o
l
a
l
a
m,
S
.
O
t
o
u
m
,
a
n
d
O
.
O
z
k
a
sap
,
“
A
h
y
b
r
i
d
e
d
g
e
-
a
s
si
st
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
h
e
a
r
t
d
i
s
e
a
se
,
”
i
n
I
E
EE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
M
a
y
2
0
2
2
,
v
o
l
.
2
0
2
2
-
M
a
y
,
p
p
.
2
9
6
6
–
2
9
7
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
4
5
8
5
5
.
2
0
2
2
.
9
8
3
8
9
3
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
14
,
No
.
3
,
Dec
em
b
er
20
25
:
751
-
7
5
9
758
[
4
]
P
.
S
h
a
r
ma
a
n
d
S
.
S
h
a
r
ma,
“
A
n
e
f
f
e
c
t
i
v
e
F
L
-
C
N
N
b
a
se
d
d
a
t
a
se
c
u
r
i
n
g
mo
d
e
l
f
o
r
h
e
a
r
t
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
,
”
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
C
o
n
f
e
r
e
n
c
e
o
n
C
o
n
t
e
m
p
o
ra
r
y
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
I
C
3
I
2
0
2
3
,
S
e
p
.
2
0
2
3
,
p
p
.
1
8
6
2
–
1
8
6
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
I
5
9
1
1
7
.
2
0
2
3
.
1
0
3
9
7
6
4
9
.
[
5
]
X
.
Y
u
a
n
,
J.
Zh
a
n
g
,
J.
L
u
o
,
J
.
C
h
e
n
,
Z
.
S
h
i
,
a
n
d
M
.
Q
i
n
,
“
A
n
e
f
f
i
c
i
e
n
t
d
i
g
i
t
a
l
t
w
i
n
a
ss
i
st
e
d
c
l
u
s
t
e
r
e
d
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
,
”
i
n
I
EE
E
Ve
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
C
o
n
f
e
r
e
n
c
e
,
J
u
n
.
2
0
2
2
,
v
o
l
.
2
0
2
2
-
J
u
n
e
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
V
TC
2
0
2
2
-
S
p
r
i
n
g
5
4
3
1
8
.
2
0
2
2
.
9
8
6
0
7
0
4
.
[
6
]
B
.
D
o
l
o
,
F
.
L
o
u
k
i
l
,
a
n
d
K
.
B
o
u
k
a
d
i
,
“
Ea
r
l
y
d
e
t
e
c
t
i
o
n
o
f
d
i
a
b
e
t
e
s
mel
l
i
t
u
s
u
si
n
g
d
i
f
f
e
r
e
n
t
i
a
l
l
y
p
r
i
v
a
t
e
S
G
D
i
n
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
I
EE
E/
A
C
S
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
AI
C
C
S
A
,
D
e
c
.
2
0
2
2
,
v
o
l
.
2
0
2
2
-
D
e
c
e
m
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
A
I
C
C
S
A
5
6
8
9
5
.
2
0
2
2
.
1
0
0
1
7
9
0
8
.
[
7
]
S
.
K
h
a
n
,
L.
S
.
P
a
l
a
n
i
sa
my
,
a
n
d
M
.
R
a
g
h
u
r
a
m
a
n
,
“
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
-
a
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
p
r
e
d
i
c
t
i
n
g
d
i
s
e
a
s
e
s
i
n
u
n
p
r
e
c
e
n
t
e
d
a
r
e
a
s,
”
i
n
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
I
n
f
o
r
m
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
AI
I
C
2
0
2
4
,
F
e
b
.
2
0
2
4
,
p
p
.
5
8
–
6
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
I
C
6
0
2
0
9
.
2
0
2
4
.
1
0
4
6
3
3
6
0
.
[
8
]
J.
M
.
N
a
n
d
h
i
n
i
,
S
.
J
o
s
h
i
,
a
n
d
K
.
A
n
u
r
a
t
h
a
,
“
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
b
a
se
d
p
r
e
d
i
c
t
i
o
n
o
f
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
s
e
a
s
e
s,”
i
n
2
0
2
2
1
st
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
a
t
i
o
n
a
l
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
I
C
C
S
T
2
0
2
2
-
Pr
o
c
e
e
d
i
n
g
s
,
N
o
v
.
2
0
2
2
,
p
p
.
8
5
1
–
8
5
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
S
T
5
5
9
4
8
.
2
0
2
2
.
1
0
0
4
0
3
1
7
.
[
9
]
B
.
Ü
l
v
e
r
,
R
.
A
.
Y
u
r
t
o
ǧ
l
u
,
H
.
D
e
r
v
i
şo
ǧ
l
u
,
R
.
H
a
l
e
p
m
o
l
l
a
s
i
,
a
n
d
M
.
H
a
k
l
i
d
i
r
,
“
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
i
n
p
r
e
d
i
c
t
i
n
g
h
e
a
r
t
d
i
s
e
a
s
e
,
”
i
n
3
1
s
t
I
EEE
C
o
n
f
e
r
e
n
c
e
o
n
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
Ap
p
l
i
c
a
t
i
o
n
s,
S
I
U
2
0
2
3
,
Ju
l
.
2
0
2
3
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
S
I
U
5
9
7
5
6
.
2
0
2
3
.
1
0
2
2
3
9
3
5
.
[
1
0
]
F
.
S
a
b
a
h
,
Y
.
C
h
e
n
,
Z
.
Y
a
n
g
,
A
.
R
a
h
e
e
m,
M
.
A
z
a
m,
a
n
d
R
.
S
a
r
w
a
r
,
“
H
e
a
r
t
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
w
i
t
h
1
0
0
%
a
c
c
u
r
a
c
y
,
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
p
e
r
f
o
r
m
a
n
c
e
i
mp
r
o
v
e
me
n
t
w
i
t
h
f
e
a
t
u
r
e
s
s
e
l
e
c
t
i
o
n
a
n
d
sam
p
l
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
2
0
2
3
8
t
h
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
N
e
t
w
o
rk
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
i
g
i
t
a
l
C
o
n
t
e
n
t
,
I
C
-
N
I
D
C
2
0
2
3
,
N
o
v
.
2
0
2
3
,
p
p
.
4
1
–
4
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
-
N
I
D
C
5
9
9
1
8
.
2
0
2
3
.
1
0
3
9
0
6
9
3
.
[1
1
]
S
.
M
o
h
a
n
,
C
.
T
h
i
r
u
ma
l
a
i
,
a
n
d
G
.
S
r
i
v
a
st
a
v
a
,
“
Ef
f
e
c
t
i
v
e
h
e
a
r
t
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
h
y
b
r
i
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
8
1
5
4
2
–
8
1
5
5
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
2
3
7
0
7
.
[1
2
]
M
.
O
b
a
y
y
a
,
J.
M
.
A
l
samr
i
,
M
.
A
.
A
l
-
H
a
g
e
r
y
,
A
.
M
o
h
a
mm
e
d
,
a
n
d
M
.
A
.
H
a
mza
,
“
A
u
t
o
ma
t
e
d
c
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
sea
s
e
d
i
a
g
n
o
si
s
u
si
n
g
h
o
n
e
y
b
a
d
g
e
r
o
p
t
i
m
i
z
a
t
i
o
n
w
i
t
h
mo
d
i
f
i
e
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
6
4
2
7
2
–
6
4
2
8
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
6
6
6
1
.
[1
3
]
C
.
C
h
a
k
r
a
b
o
r
t
y
a
n
d
A
.
K
i
s
h
o
r
,
“
R
e
a
l
-
t
i
m
e
c
l
o
u
d
-
b
a
se
d
p
a
t
i
e
n
t
-
c
e
n
t
r
i
c
m
o
n
i
t
o
r
i
n
g
u
si
n
g
c
o
m
p
u
t
a
t
i
o
n
a
l
h
e
a
l
t
h
sy
s
t
e
ms
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
o
c
i
a
l
S
y
st
e
m
s
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
1
6
1
3
–
1
6
2
3
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
S
S
.
2
0
2
2
.
3
1
7
0
3
7
5
.
[1
4
]
A
.
Y
a
sh
u
d
a
s,
D
.
G
u
p
t
a
,
G
.
C
.
P
r
a
sh
a
n
t
,
A
.
D
u
a
,
D
.
A
l
q
a
h
t
a
n
i
,
a
n
d
A
.
S
.
K
.
R
e
d
d
y
,
“
D
EEP
-
C
A
R
D
I
O
:
r
e
c
o
m
men
d
a
t
i
o
n
sy
s
t
e
m
f
o
r
c
a
r
d
i
o
v
a
s
c
u
l
a
r
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
u
si
n
g
I
o
T
n
e
t
w
o
r
k
,
”
I
E
EE
S
e
n
s
o
rs
J
o
u
rn
a
l
,
v
o
l
.
2
4
,
n
o
.
9
,
p
p
.
1
4
5
3
9
–
1
4
5
4
7
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
EN
.
2
0
2
4
.
3
3
7
3
4
2
9
.
[1
5
]
G
.
K
o
u
t
i
t
a
s
,
K
.
N
o
l
e
n
,
S
.
A
t
t
a
l
,
A
.
V
e
n
t
o
u
r
i
s
,
Y
.
D
o
l
e
v
,
a
n
d
H
.
T.
V
a
n
D
e
n
B
r
o
e
k
,
“
T
e
c
h
n
i
c
a
l
f
e
a
si
b
i
l
i
t
y
o
f
i
mp
l
e
me
n
t
i
n
g
a
n
d
c
o
mm
e
r
c
i
a
l
i
z
i
n
g
a
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
r
a
r
e
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
8
4
4
3
0
–
8
4
4
3
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
9
8
6
6
.
[1
6
]
B
.
T.
H
.
D
a
n
g
,
P
.
H
.
L
u
a
n
,
V
.
D
.
T.
N
g
a
n
,
N
.
T
.
Tr
o
n
g
,
P
.
T
.
D
u
y
,
a
n
d
V
.
H
.
P
h
a
m
,
“
Tr
u
st
F
e
d
H
e
a
l
t
h
:
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
w
i
t
h
h
o
m
o
m
o
r
p
h
i
c
e
n
c
r
y
p
t
i
o
n
a
n
d
b
l
o
c
k
c
h
a
i
n
f
o
r
h
e
a
r
t
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
i
n
t
h
e
smar
t
h
e
a
l
t
h
c
a
r
e
,
”
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
Ad
v
a
n
c
e
d
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
O
c
t
.
2
0
2
3
,
p
p
.
1
7
8
–
1
8
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
TC
5
8
7
1
0
.
2
0
2
3
.
1
0
3
1
8
9
4
4
.
[
1
7
]
R
.
K
a
p
i
l
a
,
T.
R
a
g
u
n
a
t
h
a
n
,
S
.
S
a
l
e
t
i
,
T.
J.
La
k
s
h
mi
,
a
n
d
M
.
W
.
A
h
m
a
d
,
“
H
e
a
r
t
d
i
sea
s
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
n
o
v
e
l
q
u
i
n
e
M
c
C
l
u
s
k
e
y
b
i
n
a
r
y
c
l
a
ss
i
f
i
e
r
(
Q
M
B
C
)
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
6
4
3
2
4
–
6
4
3
4
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
9
5
8
4
.
[
18
]
N
.
M
o
h
a
n
,
V
.
J
a
i
n
,
a
n
d
G
.
A
g
r
a
w
a
l
,
“
H
e
a
r
t
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
s
u
p
e
r
v
i
se
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,”
i
n
2
0
2
1
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
e
r
N
e
t
w
o
rk
s,
I
S
C
O
N
2
0
2
1
,
O
c
t
.
2
0
2
1
,
p
p
.
1
–
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
O
N
5
2
0
3
7
.
2
0
2
1
.
9
7
0
2
3
1
4
.
[
19
]
S
.
J
.
P
a
s
h
a
a
n
d
E
.
S
.
M
o
h
a
m
e
d
,
“
N
o
v
e
l
f
e
a
t
u
r
e
r
e
d
u
c
t
i
o
n
(
N
F
R
)
m
o
d
e
l
w
i
t
h
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
a
t
a
m
i
n
i
n
g
a
l
g
o
r
i
t
h
m
s
f
o
r
e
f
f
e
c
t
i
v
e
d
i
s
e
a
s
e
r
i
s
k
p
r
e
d
i
c
t
i
o
n
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
8
,
p
p
.
1
8
4
0
8
7
–
1
8
4
1
0
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
0
.
3
0
2
8
7
1
4
.
[
20
]
S
.
B
h
a
t
t
,
S
.
S
h
a
r
ma
,
a
n
d
S
.
B
h
a
d
u
l
a
,
“
A
d
v
a
n
c
e
d
b
l
o
c
k
c
h
a
i
n
a
p
p
l
i
c
a
t
i
o
n
s
i
n
c
r
y
p
t
o
c
u
r
r
e
n
c
y
a
n
d
v
a
r
i
o
u
s
se
c
t
o
r
s,”
i
n
2
0
2
3
1
st
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
i
rc
u
i
t
s,
P
o
w
e
r,
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s,
C
C
PI
S
2
0
2
3
,
S
e
p
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
P
I
S
5
9
1
4
5
.
2
0
2
3
.
1
0
2
9
1
4
6
5
.
[2
1
]
G
.
M
u
h
a
mm
a
d
e
t
a
l
.
,
“
E
n
h
a
n
c
i
n
g
p
r
o
g
n
o
si
s
a
c
c
u
r
a
c
y
f
o
r
i
sc
h
e
mi
c
c
a
r
d
i
o
v
a
s
c
u
l
a
r
d
i
s
e
a
s
e
u
si
n
g
K
n
e
a
r
e
st
n
e
i
g
h
b
o
r
a
l
g
o
r
i
t
h
m:
a
r
o
b
u
st
a
p
p
r
o
a
c
h
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
9
7
8
7
9
–
9
7
8
9
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
1
2
0
4
6
.
[2
2]
G
.
Jo
o
,
Y
.
S
o
n
g
,
H
.
I
m,
a
n
d
J.
P
a
r
k
,
“
C
l
i
n
i
c
a
l
i
m
p
l
i
c
a
t
i
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
p
r
e
d
i
c
t
i
n
g
t
h
e
o
c
c
u
r
r
e
n
c
e
o
f
c
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
s
e
a
se
u
si
n
g
b
i
g
d
a
t
a
(
N
a
t
i
o
n
w
i
d
e
C
o
h
o
r
t
D
a
t
a
i
n
K
o
r
e
a
)
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
5
7
6
4
3
–
1
5
7
6
5
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
1
5
7
5
7
.
[2
3
]
D
.
Y
.
O
m
k
a
r
i
a
n
d
K
.
S
h
a
i
k
,
“
A
n
i
n
t
e
g
r
a
t
e
d
t
w
o
-
l
a
y
e
r
e
d
v
o
t
i
n
g
(
TLV
)
f
r
a
mew
o
r
k
f
o
r
c
o
r
o
n
a
r
y
a
r
t
e
r
y
d
i
s
e
a
s
e
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
c
l
a
ssi
f
i
e
r
s,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
5
6
2
7
5
–
5
6
2
9
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
8
9
7
0
7
.
[2
4
]
V
.
V
e
e
r
a
mse
t
t
y
,
D
.
R
a
k
e
s
h
C
h
a
n
d
r
a
,
a
n
d
S
.
R
.
S
a
l
k
u
t
i
,
“
S
h
o
r
t
t
e
r
m
a
c
t
i
v
e
p
o
w
e
r
l
o
a
d
f
o
r
e
c
a
st
i
n
g
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
w
i
t
h
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s i
n
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
8
2
4
,
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
2
,
p
p
.
1
0
3
–
1
2
4
.
[2
5
]
S
.
R
.
S
a
l
k
u
t
i
,
“
A
s
u
r
v
e
y
o
f
b
i
g
d
a
t
a
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
5
7
5
–
5
8
0
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
0
i
1
.
p
p
5
7
5
-
5
8
0
.
[2
6
]
K
.
B
a
d
a
p
a
n
d
a
,
D
.
P
.
M
i
s
h
r
a
,
a
n
d
S
.
R
.
S
a
l
k
u
t
i
,
“
A
g
r
i
c
u
l
t
u
r
e
d
a
t
a
v
i
s
u
a
l
i
z
a
t
i
o
n
a
n
d
a
n
a
l
y
si
s
u
si
n
g
d
a
t
a
mi
n
i
n
g
t
e
c
h
n
i
q
u
e
s:
a
p
p
l
i
c
a
t
i
o
n
o
f
u
n
su
p
e
r
v
i
s
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
T
e
l
k
o
m
n
i
k
a
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
ro
n
i
c
s
a
n
d
C
o
n
t
r
o
l
)
,
v
o
l
.
2
0
,
n
o
.
1
,
p
p
.
9
8
–
1
0
8
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
2
9
2
8
/
TE
LK
O
M
N
I
K
A
.
v
2
0
i
1
.
1
8
9
3
8
.
[2
7
]
D
.
P
.
M
i
sh
r
a
,
S
.
M
i
sh
r
a
,
S
.
J
e
n
a
,
a
n
d
S
.
R
.
S
a
l
k
u
t
i
,
“
I
mag
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
1
,
n
o
.
3
,
p
p
.
1
5
5
1
–
1
5
5
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
1
.
i
3
.
p
p
1
5
5
1
-
15
5
8
.
[
28
]
M
.
M
a
m
u
n
,
M
.
M
.
U
d
d
i
n
,
V
.
K
u
mar
T
i
w
a
r
i
,
A
.
M
.
I
sl
a
m,
a
n
d
A
.
U
.
F
e
r
d
o
u
s
,
“
M
LH
e
a
r
t
D
i
s
:
C
a
n
M
a
c
h
i
n
e
Le
a
r
n
i
n
g
T
e
c
h
n
i
q
u
e
s
En
a
b
l
e
t
o
P
r
e
d
i
c
t
H
e
a
r
t
D
i
se
a
ses?
,
”
i
n
2
0
2
2
I
EE
E
1
3
t
h
A
n
n
u
a
l
U
b
i
q
u
i
t
o
u
s
C
o
m
p
u
t
i
n
g
,
El
e
c
t
ro
n
i
c
s
a
n
d
M
o
b
i
l
e
C
o
m
m
u
n
i
c
a
t
i
o
n
C
o
n
f
e
re
n
c
e
,
U
E
MC
O
N
2
0
2
2
,
O
c
t
.
2
0
2
2
,
p
p
.
5
6
1
–
5
6
5
,
d
o
i
:
1
0
.
1
1
0
9
/
U
E
M
C
O
N
5
4
6
6
5
.
2
0
2
2
.
9
9
6
5
7
1
4
.
[
29
]
R
.
A
.
N
a
z
r
i
,
S
.
D
a
s
,
a
n
d
R
.
T
.
H
a
q
u
e
P
r
o
mi
,
“
H
e
a
r
t
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
sy
n
t
h
e
t
i
c
mi
n
o
r
i
t
y
o
v
e
r
sa
mp
l
i
n
g
t
e
c
h
n
i
q
u
e
a
n
d
s
o
f
t
v
o
t
i
n
g
,
”
i
n
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
u
t
o
m
a
t
i
o
n
,
C
o
n
t
r
o
l
a
n
d
Me
c
h
a
t
r
o
n
i
c
s
f
o
r
I
n
d
u
st
r
y
4
.
0
,
A
C
MI
2
0
2
1
,
Ju
l
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
M
I
5
3
8
7
8
.
2
0
2
1
.
9
5
2
8
1
8
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
AI
-
b
a
s
ed
fe
d
era
ted
lea
r
n
in
g
f
o
r
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
:
a
co
lla
b
o
r
a
tive
a
n
d
p
r
iva
cy
-
…
(
S
tu
ti B
h
a
tt
)
759
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
tu
ti
Bh
a
tt
c
o
m
p
lete
d
h
e
r
d
i
p
lo
m
a
in
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
f
ro
m
G
.
P
S
rin
a
g
a
r
G
a
rh
wa
l.
S
h
e
p
u
rsu
e
d
h
e
r
Ba
c
h
e
l
o
r'
s
d
e
g
re
e
in
IT
fro
m
HN
B
G
a
rh
wa
l
Un
iv
e
rsity
fo
ll
o
we
d
b
y
h
e
r
p
o
st
-
g
ra
d
u
a
ti
o
n
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
fro
m
G
ra
p
h
ic
Era
De
e
m
e
d
to
b
e
Un
iv
e
rsity
.
C
u
rre
n
tl
y
s
h
e
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
t
t
h
e
D
e
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
G
ra
p
h
ic
Era
Hill
Un
iv
e
rsity
,
De
h
ra
d
u
n
,
Uttara
k
h
a
n
d
,
I
n
d
ia
.
He
r
re
se
a
rc
h
in
tere
sts
sp
a
n
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
6
G
wire
les
s
c
o
m
m
u
n
ica
ti
o
n
n
e
two
r
k
s,
q
u
a
n
t
u
m
c
o
m
p
u
ti
n
g
,
h
e
a
lt
h
c
a
re
,
b
lo
c
k
c
h
a
in
,
a
n
d
c
y
b
e
rse
c
u
rit
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
stu
ti
b
h
a
tt
1
0
2
8
@g
m
a
il
.
c
o
m
.
S
u
r
e
n
d
e
r
Re
d
d
y
S
a
lk
u
ti
re
c
e
i
v
e
d
P
h
.
D
.
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
fr
o
m
th
e
In
d
ian
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
(IIT
)
,
Ne
w
De
l
h
i,
In
d
ia,
in
2
0
1
3
.
He
wa
s
a
P
o
std
o
c
to
ra
l
Re
se
a
rc
h
e
r
a
t
Ho
wa
rd
Un
i
v
e
rsity
,
Was
h
i
n
g
t
o
n
,
DC,
USA,
fro
m
2
0
1
3
t
o
2
0
1
4
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
t
h
e
De
p
a
rtme
n
t
o
f
Ra
il
r
o
a
d
a
n
d
E
lec
tri
c
a
l
En
g
i
n
e
e
rin
g
,
Wo
o
so
n
g
Un
iv
e
rsity
,
Da
e
jeo
n
,
Re
p
u
b
l
ic
o
f
Ko
re
a
.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
rk
e
t
c
lea
rin
g
,
in
c
lu
d
in
g
re
n
e
wa
b
le
e
n
e
r
g
y
s
o
u
r
c
e
s,
d
e
m
a
n
d
re
sp
o
n
se
,
a
n
d
sm
a
rt
g
ri
d
d
e
v
e
lo
p
m
e
n
t
with
th
e
in
teg
ra
ti
o
n
o
f
win
d
a
n
d
so
lar
p
h
o
t
o
v
o
lt
a
ic
e
n
e
rg
y
so
u
rc
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
re
n
d
e
r@
ws
u
.
a
c
.
k
r
.
S
e
o
n
g
-
Che
o
l
K
im
re
c
e
iv
e
d
B.
S
.
,
M
.
S
.
a
n
d
P
h
.
D
.
d
e
g
r
e
e
s,
in
e
lec
tro
n
ic
e
n
g
in
e
e
rin
g
fro
m
Ko
re
a
Un
i
v
e
rsity
in
1
9
8
7
,
1
9
8
9
,
a
n
d
1
9
9
7
,
re
sp
e
c
ti
v
e
ly
.
He
is
c
u
rre
n
tl
y
se
rv
in
g
a
s
He
a
d
o
f
t
h
e
Ra
il
ro
a
d
a
n
d
El
e
c
tri
c
a
l
En
g
in
e
e
ri
n
g
De
p
a
rt
m
e
n
t,
Wo
o
so
n
g
Un
i
v
e
rsity
,
Ko
re
a
.
His
re
se
a
rc
h
in
tere
sts
a
re
m
o
b
i
le
c
o
m
m
u
n
ica
ti
o
n
sy
ste
m
s
a
n
d
p
u
lse
d
p
o
we
r
sy
ste
m
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
m
i
n
@w
su
.
a
c
.
k
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.