I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
2
0
2
1
,
p
p
.
5
2
2
9
~
5
2
3
9
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
1
i
6
.
pp
5
2
2
9
-
5
2
3
9
5229
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Ana
ly
sis
of WEK
A data
m
ining
alg
o
rith
m
s
Ba
y
es
net
,
ra
ndo
m
forest,
M
L
P
a
nd
SM
O
f
o
r
heart
di
sea
se predict
io
n s
y
ste
m
:
A
ca
se study
in
I
ra
q
Ra
na
Ria
d K
.
AL
-
T
a
ie
,
B
a
s
m
a
J
u
m
a
a
Sa
leh,
Ah
m
ed
Yo
us
if
F
a
lih
Sa
edi
,
L
a
m
ee
s
A
b
da
lha
s
a
n Sa
l
m
a
n
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
Al
-
M
u
sta
n
siriy
a
h
Un
iv
e
rsit
y
,
Ba
g
h
d
a
d
,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
17
,
2
0
20
R
ev
i
s
ed
Ma
y
29
,
2
0
2
1
A
cc
ep
ted
Ju
n
11
,
2
0
2
1
Da
ta
m
in
in
g
is d
e
f
in
e
d
a
s
a
se
a
rc
h
th
r
o
u
g
h
larg
e
a
m
o
u
n
ts o
f
d
a
ta fo
r
v
a
lu
a
b
le
in
f
o
rm
a
ti
o
n
.
T
h
e
a
ss
o
c
iatio
n
ru
les
,
g
ro
u
p
in
g
,
c
lu
ste
rin
g
,
p
re
d
ictio
n
,
se
q
u
e
n
c
e
m
o
d
e
li
n
g
is
so
m
e
e
ss
e
n
ti
a
l
a
n
d
m
o
st
g
e
n
e
ra
l
s
trat
e
g
ies
f
o
r
d
a
ta
e
x
trac
ti
o
n
.
T
h
e
p
ro
c
e
ss
in
g
o
f
d
a
ta
p
lay
s
a
m
a
jo
r
ro
le
in
t
h
e
h
e
a
lt
h
c
a
re
in
d
u
str
y
'
s
d
ise
a
s
e
d
e
tec
ti
o
n
.
A
v
a
riet
y
o
f
d
ise
a
se
e
v
a
lu
a
ti
o
n
s
s
h
o
u
ld
b
e
re
q
u
ired
t
o
d
i
a
g
n
o
se
th
e
p
a
ti
e
n
t.
Ho
w
e
v
e
r,
u
sin
g
d
a
ta
m
in
in
g
stra
teg
ies
,
th
e
n
u
m
b
e
r
o
f
e
x
a
m
in
a
ti
o
n
s
sh
o
u
l
d
b
e
d
e
c
re
a
se
d
.
T
h
is d
e
c
re
a
s
e
d
e
x
a
m
in
a
ti
o
n
p
lay
s a
c
ru
c
ial
ro
le i
n
term
s
o
f
ti
m
e
a
n
d
re
su
lt
s.
He
a
rt
d
ise
a
s
e
is a d
e
a
th
-
p
ro
v
o
k
in
g
d
iso
rd
e
r.
In
th
is r
e
c
e
n
t
in
sta
n
c
e
,
h
e
a
lt
h
issu
e
s
a
re
imm
e
n
se
b
e
c
a
u
se
o
f
th
e
a
v
a
il
a
b
il
it
y
o
f
h
e
a
lt
h
issu
e
s
a
n
d
th
e
g
ro
u
p
i
n
g
o
f
v
a
rio
u
s
situ
a
ti
o
n
s.
T
o
d
a
y
,
s
e
c
re
t
in
f
o
rm
a
t
io
n
is
im
p
o
rtan
t
in
th
e
h
e
a
lt
h
c
a
re
in
d
u
s
try
to
m
a
k
e
d
e
c
isio
n
s.
F
o
r
th
e
p
r
e
d
ictio
n
o
f
c
a
rd
io
v
a
sc
u
lar
p
ro
b
lem
s,
(W
e
k
a
3
.
8
.
3
)
t
o
o
ls
f
o
r
t
h
is
a
n
a
ly
sis
a
r
e
u
se
d
f
o
r
th
e
p
re
d
ictio
n
o
f
d
a
ta
e
x
trac
ti
o
n
a
lg
o
rit
h
m
s
li
k
e
se
q
u
e
n
ti
a
l
m
in
ima
l
o
p
ti
m
iza
ti
o
n
(S
M
O),
m
u
lt
il
a
y
e
r
p
e
rc
e
p
tro
n
(
M
L
P
),
ra
n
d
o
m
f
o
re
st
a
n
d
Ba
y
e
s
n
e
t
.
T
h
e
d
a
ta
c
o
ll
e
c
ted
c
o
m
b
in
e
th
e
p
re
d
icti
o
n
a
c
c
u
ra
c
y
re
su
lt
s,
th
e
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic
(
ROC
)
c
u
rv
e
,
a
n
d
th
e
P
RC
v
a
lu
e
.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
Ba
y
e
s
n
e
t
(9
4
.
5
%
)
a
n
d
ra
n
d
o
m
f
o
re
s
t
(9
4
%
)
tec
h
n
o
lo
g
ies
i
n
d
ica
tes
o
p
ti
m
u
m
p
e
rf
o
r
m
a
n
c
e
ra
th
e
r
th
a
n
th
e
se
q
u
e
n
t
ial
m
in
ima
l
o
p
ti
m
iza
ti
o
n
(
S
M
O)
a
n
d
m
u
lt
il
a
y
e
r
p
e
rc
e
p
tro
n
(M
L
P
)
m
e
t
h
o
d
s
.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
Data
m
i
n
i
n
g
Data
s
et
Hea
r
t d
is
ea
s
e
W
E
KA
to
o
l
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
B
as
m
a
J
u
m
aa
Sale
h
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
Al
-
M
u
s
ta
n
s
ir
i
y
a
h
U
n
iv
er
s
it
y
B
ag
h
d
ad
,
I
r
aq
E
m
ail:
e
n
g
.
b
as
m
aj
@
u
o
m
u
s
ta
n
s
ir
i
y
a
h
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
co
m
p
lica
tio
n
s
o
f
h
ea
r
t
a
tt
ac
k
ca
n
b
e
co
n
s
id
er
ed
as
t
h
e
m
ai
n
w
o
r
ld
’
s
lead
i
n
g
ca
u
s
ati
v
e
ag
e
n
t
to
,
to
s
to
p
attac
k
s
in
co
n
j
u
n
c
tio
n
w
it
h
ea
r
l
y
d
iag
n
o
s
i
s
.
Ma
n
y
o
f
i
n
f
o
r
m
atio
n
,
u
s
u
al
l
y
p
r
o
d
u
ce
d
b
y
p
h
y
s
ic
ian
s
w
it
h
r
ich
h
id
d
en
m
ater
ial,
b
u
t
u
s
ed
in
ef
f
icie
n
tl
y
f
o
r
f
o
r
ec
asti
n
g
.
Hen
ce
,
u
t
ilizi
n
g
m
a
n
y
o
f
d
ata
m
i
n
i
n
g
s
tr
ateg
ie
s
h
elp
ed
in
t
u
r
n
i
n
g
u
n
u
s
ed
d
ata
i
n
to
a
u
s
e
f
u
l
d
ata
s
et.
Se
v
er
al
o
f
s
ig
n
s
h
a
v
e
n
o
t
b
ee
n
ta
k
en
in
to
ac
co
u
n
t
,
w
h
ich
let
to
d
y
in
g
p
eo
p
le.
P
r
o
f
ess
io
n
als
o
f
m
ed
ical
s
h
o
u
ld
p
r
ed
ict
h
ea
r
t
d
is
ea
s
e
b
ef
o
r
e
it
h
ap
p
en
s
in
an
y
p
atien
t
[
1
]
.
T
h
e
r
e
ar
e
m
an
y
o
f
c
h
ar
ac
ter
is
t
ics
th
at
m
a
y
i
n
cr
ea
s
e
t
h
e
p
o
s
s
ib
ilit
y
o
f
h
ea
r
t
d
i
s
ea
s
es
[
2
]
:
i)
S
m
o
k
in
g
:
De
s
tr
o
y
s
th
e
li
n
i
n
g
o
f
t
h
e
ar
ter
ies
b
y
r
elea
s
i
n
g
a
f
at
co
n
ten
t,
s
u
ch
a
s
at
h
er
o
m
a,
w
h
ich
d
ec
r
ea
s
es
th
e
ar
t
er
ies
th
at
ac
ti
v
ate
h
ea
r
t
attac
k
,
ii)
Hig
h
ch
o
lest
er
o
l:
C
h
o
le
s
ter
o
l
is
a
w
a
x
y
m
ater
ia
l
f
o
u
n
d
in
th
e
f
att
y
p
laq
u
es
o
f
b
lo
o
d
v
ess
els.
Hi
g
h
ch
o
lest
er
o
l
d
o
esn
'
t
r
ea
ll
y
al
lo
w
s
u
f
f
icie
n
t
b
lo
o
d
to
en
ter
th
e
lu
n
g
s
,
ca
u
s
i
n
g
h
ea
r
t
d
is
ea
s
e
,
iii)
I
n
ap
p
r
o
p
r
i
ate
d
iet:
B
lo
o
d
p
r
ess
u
r
e
an
d
ch
o
lest
er
o
l
ar
e
in
cr
ea
s
ed
b
y
ea
t
in
g
s
o
m
u
ch
u
n
h
ea
lt
h
y
f
o
o
d
,
th
at
ca
n
ca
u
s
e
h
ea
r
t
d
is
ea
s
e
,
iv
)
L
ac
k
o
f
p
h
y
s
ical
ac
ti
v
it
y
:
A
n
i
n
cr
ea
s
e
in
th
e
le
v
els
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
2
0
2
1
:
5
2
2
9
-
5
2
3
9
5230
ch
o
lest
er
o
l
in
th
e
m
u
s
cle
s
,
lead
in
g
to
t
h
e
p
r
o
b
ab
ilit
y
o
f
h
ea
r
t
a
ttack
s
,
v
)
Har
m
f
u
l
alco
h
o
l
in
ta
k
e:
A
p
s
y
ch
o
ac
ti
v
e
s
er
ies
o
f
u
s
e
th
a
t
ca
u
s
e
s
d
a
m
a
g
e
to
h
ea
l
th
.
T
h
e
p
u
r
p
o
s
e
m
a
y
b
e
p
h
y
s
io
lo
g
ica
l
o
r
b
eh
av
io
u
r
al
o
r
e.
g
.
P
r
i
m
ar
y
to
s
er
io
u
s
d
r
in
k
in
g
d
ep
r
ess
ed
ep
i
s
o
d
es.
H
ar
m
f
u
l
lo
ca
tio
n
s
d
o
n
o
t
al
w
a
y
s
h
a
v
e
h
ar
m
f
u
l
p
s
y
ch
o
lo
g
ical
co
n
s
eq
u
en
c
e
s
;
h
o
w
ev
er
,
th
e
s
o
cial
i
m
p
ac
ts
a
r
e
n
o
t
ad
eq
u
ate
to
j
u
s
tify
a
d
iag
n
o
s
is
o
f
h
ar
m
f
u
l
u
s
e
[
3
]
,
v
i)
Hig
h
s
u
g
ar
le
v
els
:
Me
asu
r
e
m
en
ts
o
f
b
lo
o
d
s
u
g
ar
h
ig
h
er
th
a
n
1
8
0
m
g
/D
L
o
r
an
y
m
ea
s
u
r
e
m
e
n
t
s
o
u
ts
id
e
th
e
n
o
r
m
al
r
a
n
g
e
ar
e
a
b
n
o
r
m
a
l.
A
b
lo
o
d
s
u
g
ar
tes
t
o
f
3
0
0
m
g
/
D
L
o
r
h
i
g
h
er
m
a
y
b
e
d
an
g
er
o
u
s
.
W
h
en
y
o
u
h
a
v
e
t
w
o
r
ea
d
i
n
g
s
i
n
a
s
e
q
u
en
ce
o
f
3
0
0
o
r
m
o
r
e,
ca
ll
y
o
u
r
d
o
cto
r
.
I
n
h
i
g
h
in
s
u
li
n
ca
s
es,
t
h
e
p
r
ac
tice
o
f
p
lu
r
al,
g
r
o
w
in
g
h
u
n
g
er
a
n
d
p
o
ly
p
h
o
n
ic
[
4
]
is
g
e
n
er
all
y
o
b
s
er
v
ed
,
v
ii)
Ov
er
s
tr
ess
:
T
h
e
u
n
s
p
ec
if
ic
r
esp
o
n
s
e
o
f
th
e
b
o
d
y
to
an
y
r
eq
u
e
s
t
i
s
a
c
o
n
d
itio
n
g
e
n
er
all
y
o
cc
u
r
r
in
g
d
u
r
in
g
it
s
e
n
tire
l
if
e
s
p
an
.
All
in
d
iv
id
u
als
i
n
t
h
eir
s
o
ciet
y
a
n
d
h
is
to
r
y
h
av
e
f
el
t
i
t.
Stre
s
s
h
a
s
b
ec
o
m
e
o
n
e
o
f
li
f
e
'
s
ex
tr
a
c
h
ar
ac
ter
is
t
ics
a
n
d
it
s
es
s
en
ce
h
a
s
b
ee
n
h
ig
h
li
g
h
ted
i
n
o
r
d
er
to
b
e
ex
p
lo
r
ed
in
all
er
as
o
f
ar
t
h
is
to
r
y
an
d
f
ictio
n
[
5
]
,
an
d
v
iii)
B
lo
o
d
p
r
ess
u
r
e:
A
r
ar
e
d
is
o
r
d
er
in
w
h
ic
h
b
lo
o
d
p
o
w
e
r
f
u
l
e
n
o
u
g
h
f
o
r
th
e
w
all
s
o
f
t
h
e
ar
ter
y
ca
n
u
lti
m
atel
y
tr
i
g
g
er
h
ea
lth
co
n
d
itio
n
s
[
6
]
,
ag
e,
g
en
d
er
an
d
f
a
m
il
y
h
i
s
to
r
y
o
f
d
iab
etes
.
A
Sit
u
atio
n
c
o
m
m
o
n
[7
]
.
Su
ch
r
ea
s
o
n
s
ca
n
b
e
u
s
ed
as li
f
est
y
le
f
ac
to
r
s
f
o
r
t
h
e
p
r
ed
ictio
n
o
f
c
ar
d
iac
d
is
ea
s
e
[
8
]
.
Ma
n
y
k
i
n
d
s
o
f
h
ea
r
t
i
n
j
u
r
y
co
n
d
itio
n
s
ar
e
in
cl
u
d
ed
in
t
h
e
ter
m
ca
r
d
iac
illn
es
s
.
Hea
r
t d
is
o
r
d
er
s
ar
e
p
r
ev
alen
t in
:
a.
C
o
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e:
T
h
e
m
u
c
h
m
o
r
e
co
m
m
o
n
m
eth
o
d
o
f
h
ea
r
t
d
is
ea
s
e
in
t
h
e
w
o
r
ld
is
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
I
t
is
al
s
o
ca
lled
h
ea
r
t
d
is
ea
s
e.
Stat
u
e
p
ar
ticles
b
lo
ck
th
e
co
r
o
n
ar
y
c
h
an
n
el,
ca
u
s
i
n
g
a
r
ed
u
ce
d
f
lo
w
to
th
e
ca
r
d
io
v
ascu
lar
o
f
o
x
y
g
e
n
ated
b
lo
o
d
.
b.
A
r
r
h
y
t
h
m
ias:
I
t
is
r
elate
d
to
th
e
ir
r
eg
u
lar
ac
ti
v
it
y
o
f
th
e
h
ea
r
tb
ea
t.
I
t
m
a
y
b
e
a
lo
w
,
f
ast
o
r
ir
r
eg
u
lar
h
ea
r
tb
ea
t.
B
esid
es ir
r
eg
u
lar
h
e
ar
tb
ea
ts
,
th
er
e
is
a
d
ef
ec
t i
n
th
e
ca
r
d
io
v
ascu
lar
s
y
s
te
m
.
c.
Hea
r
t
f
ail
u
r
e:
I
t
is
a
co
n
d
itio
n
in
w
h
ic
h
en
o
u
g
h
b
lo
o
d
ca
n
n
o
t
b
e
d
eliv
er
ed
to
th
e
s
p
ec
if
ic
b
o
d
y
b
y
th
e
h
ea
r
t.
No
r
m
all
y
,
i
t is p
o
in
ted
t
o
as h
ea
r
t p
r
o
b
lem
s
.
d.
C
o
n
g
en
i
tal
h
ea
r
t
d
is
ea
s
e:
it
is
o
f
ten
p
o
in
ted
to
as
a
co
n
g
en
it
al
ca
r
d
iac
co
n
d
itio
n
an
d
lead
s
to
an
ab
n
o
r
m
a
l
ca
r
b
o
n
ate
d
ev
elo
p
m
e
n
tal
s
tag
e
an
d
f
u
n
ctio
n
.
Of
te
n
,
i
n
f
a
n
t
s
w
it
h
a
co
n
g
en
ital d
is
o
r
d
er
.
e.
C
ar
d
io
m
y
o
p
ath
y
:
u
n
d
er
m
i
n
i
n
g
t
h
e
h
ea
r
t
m
u
s
cle
o
r
af
f
ec
ti
n
g
t
h
e
m
u
s
c
u
lat
u
r
e
d
u
e
to
t
h
e
i
m
p
r
o
p
er
b
ea
tin
g
o
f
th
e
h
ea
r
t.
Via
ca
r
d
io
m
y
o
p
a
th
y
.
T
h
e
m
o
s
t
co
m
m
o
n
ca
u
s
e
s
o
f
ca
r
d
io
m
y
o
p
ath
y
ar
e
h
ig
h
b
lo
o
d
p
r
ess
u
r
e,
alco
h
o
l in
ta
k
e,
b
ac
ter
ial
in
f
ec
t
io
n
s
,
an
d
g
e
n
etic
ab
n
o
r
m
alitie
s
.
f.
An
g
in
a
p
ec
to
r
alis
:
is
a
m
ed
ica
l
p
r
o
ce
d
u
r
e
f
o
r
an
g
i
n
a
t
h
at
h
a
p
p
en
s
w
h
e
n
t
h
e
h
ea
r
t
is
n
o
t
p
r
o
p
er
ly
s
u
p
p
lied
w
it
h
b
lo
o
d
; it
is
a
s
ig
n
o
f
a
h
e
ar
t a
ttack
.
T
h
er
e
ar
e
s
ev
er
al
s
ec
o
n
d
s
o
r
m
in
u
tes o
f
ch
e
s
t p
ain
.
g.
M
y
o
ca
r
d
itis
:
I
t
is
a
ca
r
d
iac
i
n
f
ec
tio
n
u
s
u
a
ll
y
a
f
f
ec
ti
n
g
th
e
h
e
ar
t
th
at
is
v
ir
al,
f
u
n
g
al,
an
d
b
ac
ter
ial.
I
t
is
a
n
ir
r
itab
le
h
ea
r
tb
ea
t.
I
t
is
a
r
a
r
e
co
n
d
itio
n
t
h
at
h
as
n
o
d
ir
ec
t
co
r
r
elatio
n
w
it
h
p
ain
,
ar
m
s
tiff
n
es
s
o
r
te
m
p
er
atu
r
e
[
9
]
.
A
ll
t
h
e
s
e
co
n
d
itio
n
s
ar
e
th
e
m
ain
ca
u
s
es
o
f
d
ea
t
h
f
o
r
in
d
i
v
i
d
u
als
all
o
v
er
t
h
e
w
o
r
ld
.
T
h
e
W
HO
an
d
C
DC
h
a
s
in
d
icate
d
t
h
at
t
h
e
m
aj
o
r
ca
u
s
e
o
f
m
o
r
talit
y
is
c
ar
d
io
v
ascu
lar
d
is
ea
s
e
[
8
]
an
d
d
is
ea
s
e
p
r
ev
e
n
tio
n
ce
n
tr
es.
I
n
to
d
a
y
's
w
o
r
ld
,
d
ata
m
i
n
i
n
g
i
n
m
ed
ical
tr
ea
t
m
e
n
t
is
b
ec
o
m
in
g
m
o
r
e
p
o
p
u
lar
b
ec
au
s
e
it
o
f
f
er
s
a
g
r
ea
t
v
ar
iet
y
o
f
co
m
p
le
x
k
n
o
w
l
ed
g
e
t
h
at
i
n
clu
d
es
h
ea
lt
h
ca
r
e
f
ac
ilit
ie
s
,
m
ed
ici
n
es,
m
ed
ic
al
d
ev
ices,
p
atie
n
ts
an
d
d
is
ea
s
e
d
iag
n
o
s
i
s
.
Su
c
h
c
o
m
p
le
x
d
ata
m
u
s
t
b
e
p
r
o
ce
s
s
ed
an
d
ev
alu
ated
f
o
r
th
e
r
etr
i
ev
al
o
f
i
n
f
o
r
m
atio
n
,
W
h
ich
,
i
n
d
ec
is
io
n
s
,
is
b
o
th
p
r
ice
-
ef
f
ec
ti
v
e
an
d
b
en
e
f
icial
.
I
n
2
0
1
1
,
th
e
W
o
r
ld
Hea
lth
Or
g
an
i
s
atio
n
lo
s
t
1
7
.
5
m
illi
o
n
p
atie
n
t
s
w
it
h
h
ea
r
t
d
is
ea
s
e,
w
h
ic
h
is
3
1
p
er
ce
n
t
o
f
all
f
o
r
eig
n
d
ea
th
s
.
Of
t
h
e
s
e,
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
af
f
ec
ted
7
.
4
m
illi
o
n
a
n
d
ce
r
eb
r
o
-
s
p
in
al
d
is
ea
s
e
s
af
f
ec
ted
6
.
7
m
illi
o
n
.
Al
m
o
s
t
2
3
.
6
m
illi
o
n
p
eo
p
le
w
ill
d
ie
o
f
h
ea
r
t
attac
k
s
,
ap
p
r
o
x
i
m
atel
y
b
y
th
e
Hea
lt
h
Or
g
a
n
izat
io
n
in
2
0
3
0
[
1
0
]
.
T
h
r
o
u
g
h
s
o
m
e
h
o
s
p
ital
s
y
s
te
m
m
o
n
ito
r
i
n
g
s
y
s
te
m
s
,
m
a
n
y
cli
n
ics
elec
tr
o
n
ica
ll
y
s
to
r
in
g
t
h
ei
r
p
atien
t
r
ec
o
r
d
s
.
E
ac
h
d
ay
,
s
u
ch
d
ev
ices
g
e
n
er
at
e
v
ast
q
u
a
n
titi
e
s
o
f
d
ata.
S
u
ch
d
ata
ca
n
b
e
ar
r
an
g
ed
as
s
er
v
e
r
s
in
in
f
i
n
ite
tex
t
o
r
in
p
ictu
r
e
f
o
r
m
.
Fo
r
ch
o
ice
-
m
ak
in
g
cr
iter
ia,
s
u
c
h
d
ata
ca
n
co
llect
u
s
e
f
u
l
in
f
o
r
m
at
io
n
.
T
h
is
p
r
esu
m
p
tio
n
co
n
tr
ib
u
tes
to
th
e
u
s
e
o
f
k
n
o
w
led
g
e
cr
ea
tio
n
i
n
d
ata
s
e
ts
,
w
h
ich
co
n
v
er
ts
s
m
all
-
le
v
el
d
ata
in
to
in
f
o
r
m
a
tio
n
f
o
r
h
ea
v
y
-
le
v
el
d
ec
i
s
io
n
-
m
ak
in
g
.
T
h
e
r
es
u
lt
s
ca
n
b
e
u
s
ed
an
d
ca
n
b
e
f
u
r
t
h
er
ex
p
lo
r
e
d
in
g
o
o
d
d
ec
is
io
n
s
an
d
a
n
al
y
s
is
.
B
y
co
n
tact
in
g
,
d
ata
m
in
in
g
is
g
r
ad
ed
,
clu
s
te
r
ed
,
an
al
y
ze
d
an
d
id
en
ti
f
ied
[
9
]
.
A
p
p
licatio
n
s
f
o
r
d
ata
m
i
n
in
g
f
o
r
ec
ast
f
u
tu
r
e
d
ev
elo
p
m
en
t
s
b
y
k
n
o
w
led
g
e
-
b
ased
d
ec
is
io
n
-
m
a
k
i
n
g
.
C
ar
d
io
v
ascu
lar
d
is
ea
s
e
id
en
t
if
ic
atio
n
r
eq
u
ir
e
s
a
n
i
m
m
en
s
e
a
m
o
u
n
t
o
f
d
ata,
to
o
d
if
f
ic
u
lt
a
n
d
m
as
s
i
v
e
f
o
r
cu
r
r
en
t
tech
n
iq
u
e
s
to
b
e
p
r
o
ce
s
s
ed
an
d
in
ter
p
r
eted
.
A
n
u
m
b
er
o
f
tech
n
iq
u
e
s
o
f
d
ata
m
in
i
n
g
ar
e
u
s
ed
b
y
e
x
p
er
ts
.
Ou
r
ai
m
is
to
f
i
n
d
alg
o
r
ith
m
i
ca
ll
y
ef
f
icie
n
t
d
ata
m
i
n
in
g
ap
p
licatio
n
s
.
Dif
f
er
en
t
alg
o
r
ith
m
s
f
o
r
th
e
an
al
y
s
i
s
o
f
d
ata
m
i
n
in
g
ar
e
ap
p
lied
in
th
is
p
ap
er
to
h
ea
lth
d
ata
o
n
h
ea
r
t
d
is
ea
s
e
s
.
T
h
is
h
e
lp
ed
d
eter
m
i
n
e
t
h
e
b
es
t
p
r
ed
ictio
n
s
tr
ateg
y
o
n
t
h
e
co
llected
d
ata
s
et
i
n
ter
m
s
o
f
its
p
r
ec
is
io
n
,
Kap
p
a,
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
O
C
)
an
d
ac
cu
r
ac
y
.
T
h
e
r
est
o
f
th
e
ar
ticle
is
ar
r
an
g
ed
ac
co
r
d
in
g
l
y
:
T
h
e
p
r
o
b
lem
s
tate
m
e
n
t
i
s
ill
u
s
tr
ated
in
s
ec
t
io
n
2
.
T
h
e
r
ev
ie
w
o
f
liter
at
u
r
e
a
n
d
r
elate
d
w
o
r
k
s
i
s
i
llu
s
tr
ated
i
n
s
ec
tio
n
3
T
h
e
m
et
h
o
d
o
f
o
u
r
e
x
p
e
r
im
en
t
i
s
e
x
p
lain
ed
in
s
ec
tio
n
4
.
T
h
e
r
esu
l
ts
a
n
d
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
s
o
f
o
u
r
ex
p
er
i
m
e
n
t
ar
e
ex
p
lai
n
ed
i
n
s
ec
tio
n
5
.
Sectio
n
6
ev
en
t
u
all
y
d
r
a
w
s
o
u
r
co
n
cl
u
s
i
o
n
s
.
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:
2
0
8
8
-
8708
A
n
a
lysi
s
o
f W
E
K
A
d
a
ta
min
in
g
a
lg
o
r
ith
ms B
a
ye
s
n
et,
r
a
n
d
o
m
fo
r
est,
ML
P
a
n
d
...
(
B
a
s
ma
Ju
ma
a
S
a
leh
)
5231
2.
P
RO
B
L
E
M
ST
AT
E
M
E
NT
T
h
e
i
m
p
le
m
e
n
tatio
n
o
f
m
ac
h
in
e
lear
n
in
g
m
et
h
o
d
s
f
o
r
t
h
e
class
i
f
icatio
n
a
n
d
p
r
ed
ictio
n
o
f
h
ea
r
t
d
is
ea
s
e
h
as
b
ee
n
i
n
v
esti
g
ated
in
p
r
e
v
io
u
s
r
esear
ch
e
s
.
T
h
es
e,
h
o
w
ev
er
,
o
f
f
er
a
m
o
d
el
f
o
r
p
r
ed
ictio
n
o
f
h
ea
r
t
d
is
ea
s
e
f
o
r
th
e
d
ia
g
n
o
s
is
o
f
h
ea
r
t
d
is
ea
s
e
in
c
id
en
ce
.
I
n
a
d
d
itio
n
,
th
i
s
an
a
l
y
s
is
a
i
m
s
to
d
eter
m
in
e
th
e
b
est
class
i
f
icatio
n
m
et
h
o
d
to
f
in
d
th
e
r
is
k
o
f
h
ea
r
t
d
is
ea
s
e
i
n
a
ca
s
e.
T
h
is
r
esear
ch
is
j
u
s
ti
f
ie
d
b
y
a
co
m
p
ar
ativ
e
s
tu
d
y
an
d
o
b
s
er
v
atio
n
u
s
i
n
g
f
o
u
r
clas
s
i
f
icatio
n
tech
n
iq
u
e
s
,
i.e
.
s
eq
u
e
n
tial
m
i
n
i
m
al
o
p
ti
m
izat
io
n
(
SMO)
,
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
,
r
an
d
o
m
f
o
r
est
a
n
d
B
a
y
e
s
n
et
.
T
h
e
ev
alu
a
tio
n
s
ar
e
u
s
ed
at
v
a
r
io
u
s
le
v
el
s
.
W
h
ile
th
ese
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
ar
e
w
id
el
y
u
s
ed
,
th
e
p
r
ed
ictio
n
o
f
h
ea
r
t
d
is
ea
s
e
i
s
a
cr
itical
task
r
eq
u
ir
i
n
g
t
h
e
h
ig
h
e
s
t
p
o
s
s
ib
le
p
r
ec
is
io
n
,
co
m
p
ar
i
n
g
w
it
h
[
11
]
-
[
17
]
.
T
h
er
e
f
o
r
e,
th
e
f
o
u
r
alg
o
r
it
h
m
s
ar
e
te
s
ted
in
a
n
u
m
b
er
o
f
ass
es
s
m
en
t
lev
el
s
an
d
t
y
p
es.
I
t
p
r
o
v
id
es
m
ed
ical
r
esear
c
h
er
s
an
d
p
h
y
s
icia
n
s
w
i
th
a
g
r
ea
ter
u
n
d
er
s
ta
n
d
i
n
g
a
n
d
h
elp
s
t
h
e
m
f
i
n
d
t
h
e
b
es
t
w
a
y
to
p
r
ev
e
n
t
ca
r
d
iac
d
is
ea
s
e.
W
E
KA
s
o
f
t
w
ar
e
s
h
o
u
ld
be
u
s
ed
in
t
h
e
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
.
T
h
e
W
ek
a
s
o
f
t
w
ar
e
to
o
l
h
as
b
ee
n
u
s
ed
to
ev
alu
a
te
h
ea
r
t
d
is
ea
s
e
d
ata.
T
h
is
p
ap
er
'
s
k
e
y
co
n
tr
ib
u
tio
n
s
ar
e:
a.
C
las
s
i
f
ied
p
r
ec
is
io
n
ex
tr
ac
tio
n
is
i
m
p
o
r
tan
t
f
o
r
p
r
ed
ictio
n
o
f
h
ea
r
t d
is
ea
s
e.
b.
Use
th
e
I
b
n
al
-
B
itar
Ho
s
p
ital
C
ar
d
iac
Su
r
g
er
y
a
n
d
th
e
B
a
g
h
d
ad
Me
d
ical
C
it
y
elec
tr
o
n
ic
d
iag
n
o
s
tic
ca
r
d
iac
co
n
d
itio
n
d
atab
ase
an
d
th
e
co
llected
ac
tu
al
in
f
o
r
m
atio
n
d
atab
ase
f
o
r
th
e
tr
ain
in
g
an
d
test
in
g
o
f
th
e
p
r
o
g
r
am
.
c.
T
o
ac
h
iev
e
t
h
e
h
i
g
h
e
s
t
le
v
el
o
f
cla
s
s
i
f
icat
i
o
n
ac
c
u
r
ac
y
b
a
y
es
n
et
(
9
4
.
5
%)
an
d
r
an
d
o
m
f
o
r
est
(
9
4
%
)
m
et
h
o
d
s
,
in
v
esti
g
ate
k
n
o
w
led
g
ea
b
le
class
i
f
icat
io
n
s
tr
ate
g
ie
s
.
d.
E
v
alu
a
tio
n
o
f
s
u
g
g
e
s
ted
clas
s
if
ier
cla
s
s
i
f
icatio
n
r
esu
lt
s
.
An
d
ch
ec
k
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
class
i
f
ier
s
s
u
g
g
e
s
ted
b
y
co
m
p
ar
in
g
t
h
e
m
w
it
h
e
x
i
s
t
in
g
clas
s
i
f
ier
s
o
f
o
t
h
er
w
o
r
k
s
.
e.
E
v
alu
a
te
th
e
b
est r
es
u
lt
s
o
f
t
h
e
s
u
g
g
e
s
ted
W
E
KA
s
o
f
t
w
ar
e
cl
ass
i
f
ier
s
.
f.
C
o
m
p
ar
is
o
n
o
f
v
ar
io
u
s
al
g
o
r
ith
m
s
f
o
r
d
ata
m
i
n
i
n
g
o
n
th
e
d
at
aset f
o
r
ca
r
d
io
v
ascu
lar
d
is
ea
s
e
.
g.
C
las
s
i
f
icatio
n
o
f
th
e
b
est al
g
o
r
ith
m
s
f
o
r
p
r
ed
ictio
n
o
f
h
ea
r
t d
is
ea
s
e
b
ased
o
n
th
e
r
es
u
lt
s
.
3.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
A
ND
RE
L
AT
E
D
WO
RK
S
D
w
iv
ed
i
[
1
8
]
u
s
ed
s
ix
m
ac
h
in
e
lear
n
i
n
g
clas
s
i
f
icatio
n
tec
h
n
iq
u
es
t
h
at
w
er
e
ap
p
lied
to
th
e
h
ea
r
t
d
is
ea
s
e
d
ataset.
I
n
t
h
is
s
t
u
d
y
,
t
h
is
a
u
t
h
o
r
u
s
ed
ten
f
o
ld
cr
o
s
s
v
alid
atio
n
f
o
r
e
v
alu
at
io
n
a
n
d
elev
en
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es
f
o
r
co
m
p
ar
i
s
o
n
.
T
h
er
ea
f
ter
,
a
s
tu
d
y
o
f
G
h
ar
eh
c
h
o
p
o
g
h
et
a
l.
[
1
1
]
.
R
esear
ch
er
s
u
s
ed
4
0
p
eo
p
le
in
th
eir
m
ed
ical
r
ec
o
r
d
s
.
B
lo
o
d
p
r
ess
u
r
e,
g
e
n
d
er
,
ag
e
a
n
d
to
b
ac
co
u
s
e
ar
e
th
e
c
o
n
d
itio
n
s
u
s
ed
f
o
r
d
etec
tio
n
.
T
h
e
m
o
d
el
co
r
r
ec
tl
y
an
t
icip
ated
8
5
%
o
f
ca
s
es.
M
u
ltil
a
y
er
p
e
r
ce
p
tr
o
n
(
ML
P
)
u
tili
za
tio
n
o
n
t
h
e
h
ea
r
t
d
is
ea
s
e
d
atasets
ex
ce
ed
ed
ac
cu
r
ac
y
b
y
8
0
.
8
9
%
in
t
h
e
W
E
KA
s
o
f
t
w
ar
e.
R
a
m
o
tr
a
et
a
l.
[
1
2
]
Su
g
g
esti
o
n
o
f
a
m
ac
h
i
n
e
lear
n
in
g
m
o
d
el
f
o
r
u
s
i
n
g
t
h
e
W
E
KA
m
et
h
o
d
f
o
r
p
r
ed
icti
n
g
ca
r
d
io
v
asc
u
lar
d
is
ea
s
e.
T
h
e
d
ata
co
n
tai
n
ed
3
0
3
d
ata
an
d
7
6
s
p
ec
if
icatio
n
s
.
2
9
7
d
ata
w
it
h
1
3
i
n
p
u
t
f
u
n
ctio
n
s
ar
e
r
eq
u
ir
ed
f
o
r
an
al
y
s
i
s
af
ter
p
r
etr
ea
t
m
en
t
o
f
d
ata
a
n
d
r
e
m
o
v
al
o
f
m
i
s
s
i
n
g
v
a
lu
e
s
.
T
h
e
a
u
th
o
r
s
clai
m
to
b
e
8
0
.
8
9
p
er
ce
n
t
ac
cu
r
ate
.
An
ef
f
icie
n
t
h
ea
r
t
d
is
ea
s
e
d
etec
tio
n
s
y
s
te
m
w
as
in
tr
o
d
u
ce
d
b
y
P
u
r
u
s
h
o
tta
m
et
a
l.
[
17
]
d
ata
m
i
n
i
n
g
u
tili
z
atio
n
.
I
t
ca
n
h
elp
d
o
cto
r
s
m
ak
e
p
ar
a
m
eter
-
b
ase
d
d
ec
is
io
n
s
ef
f
ec
t
iv
el
y
.
T
h
e
d
ev
ice
i
s
f
o
r
m
ed
a
n
d
te
s
ted
b
y
a
m
o
d
el
1
0
ti
m
es,
an
d
th
e
p
r
ec
is
io
n
o
f
8
6
.
3
% d
u
r
in
g
th
e
test
an
d
8
7
.
3
% d
u
r
i
n
g
th
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
i
s
p
r
o
v
en
.
T
h
e
au
th
o
r
s
n
o
ted
th
at
t
h
e
o
v
er
all
ac
cu
r
ac
y
o
f
t
h
e
m
u
l
tico
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
class
if
icatio
n
w
a
s
7
4
.
8
5
%.
J
o
th
ik
u
m
ar
et
a
l.
[
1
8
]
Su
g
g
e
s
tio
n
o
f
a
m
o
d
el
u
s
i
n
g
a
lear
n
in
g
m
et
h
o
d
to
esti
m
ate
m
ed
ic
al
h
is
to
r
y
w
it
h
2
9
5
s
a
m
p
le
s
a
n
d
1
3
ch
ar
ac
ter
is
tics
ap
p
l
y
to
th
e
n
aiv
e
B
ay
e
s
al
g
o
r
ith
m
i
n
q
u
ic
k
p
r
o
d
u
ce
r
.
Oth
er
s
i
m
ilar
m
etr
ics
ar
e
Kap
p
a
0
.
4
9
9
,
ab
s
o
lu
te
er
r
o
r
0
.
2
4
7
%,
R
MSE
is
0
.
3
7
8
,
an
d
r
elativ
e
er
r
o
r
2
4
.
1
9
%.
Sar
an
g
a
m
Ko
d
ati
et
a
l.
[
19
]
I
t
is
s
u
g
g
e
s
ted
th
at
t
h
e
p
r
ec
ed
in
g
an
a
l
y
s
is
i
s
7
7
.
9
%
in
Or
an
g
e
a
n
d
7
3
.
4
%
in
R
ec
all
o
f
ca
r
d
io
p
ath
y
r
es
u
lt
s
.
I
n
t
h
e
W
E
KA
p
r
e
ce
s
s
io
n
,
8
1
.
8
p
er
ce
n
t
an
d
r
ec
all,
8
1
.
9
p
er
ce
n
t.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
t
h
e
s
o
f
t
w
ar
e
Or
an
g
e
a
n
d
W
E
KA
,
W
ek
a
is
th
e
b
est
r
e
m
i
n
d
er
an
d
p
r
ec
ess
io
n
.
T
h
e
s
eq
u
en
t
ial
m
i
n
i
m
a
l
o
p
ti
m
izatio
n
(
SMO)
m
et
h
o
d
w
as
in
tr
o
d
u
ce
d
b
y
P
latt
[
20
]
in
1
9
9
8
an
d
w
a
s
th
e
f
a
s
test
m
et
h
o
d
f
o
r
o
p
tim
iz
in
g
al
g
o
r
ith
m
ic
p
r
o
g
r
a
m
m
i
n
g
.
Seq
u
en
tia
l
m
i
n
i
m
al
o
p
ti
m
iza
t
io
n
(
SMO)
is
u
s
ed
to
p
r
ep
a
r
e
th
e
alg
eb
r
aic
k
er
n
e
l
o
r
R
B
F
k
er
n
el
v
ec
to
r
class
i
f
icatio
n
s
u
p
p
o
r
ter
s
.
T
h
is
r
ep
lace
s
all
co
n
d
itio
n
al
attr
ib
u
tes
w
it
h
t
h
e
n
u
ll
v
al
u
es
an
d
tr
an
s
f
o
r
m
s
th
e
m
in
to
b
i
n
a
r
y
o
n
e
s
.
Au
n
g
et
a
l.
S
u
g
g
e
s
ts
a
m
ac
h
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
f
o
r
p
r
e
d
ictin
g
h
ea
r
t
co
n
d
itio
n
s
u
s
i
n
g
th
e
W
E
KA
to
o
l
[
15
]
,
d
esig
n
th
a
t
u
tili
ze
s
a
m
in
i
m
u
m
s
eq
u
en
tial
o
p
ti
m
iza
tio
n
s
tr
ateg
y
a
n
d
a
m
i
tig
a
tio
n
s
tr
ateg
y
f
o
r
laz
y
clas
s
i
f
icatio
n
.
T
h
e
W
ek
a
d
ata
m
i
n
in
g
ap
p
r
o
ac
h
h
as
b
ee
n
u
s
ed
to
p
r
e
d
ict
h
ea
r
t
d
i
s
ea
s
e.
6
6
p
er
ce
n
t
o
f
t
h
e
d
ata
s
et
(
tr
ai
n
in
g
)
a
n
d
3
4
p
er
ce
n
t
(
test
i
n
g
)
f
o
r
an
al
y
s
i
s
w
as i
n
s
tr
u
cti
v
e.
I
n
o
r
d
er
to
ev
al
u
ate
h
ea
r
t
d
i
s
e
ase,
Mir
m
o
za
f
f
ar
i
et
a
l.
[1
6
]
p
r
o
p
o
s
ed
a
m
et
h
o
d
f
o
r
th
e
cla
s
s
i
f
icatio
n
o
f
v
ar
io
u
s
d
ata
m
in
in
g
m
et
h
o
d
s
.
I
t
h
as
d
ev
elo
p
ed
a
p
ar
ticu
lar
m
o
d
el
o
f
d
i
f
f
er
en
t
f
i
lte
r
s
an
d
m
e
th
o
d
s
o
f
an
al
y
s
is
.
Fo
r
m
u
lti
-
la
y
er
p
r
e
-
p
r
o
ce
s
s
f
ilter
i
n
g
,
t
h
e
s
u
p
er
io
r
ap
p
r
o
ac
h
an
d
th
e
m
o
r
e
p
r
ec
is
e
clin
ical
r
eso
l
u
tio
n
ass
is
tan
ce
s
y
s
te
m
s
f
o
r
th
e
d
iag
n
o
s
is
o
f
d
is
ea
s
e
s
ar
e
u
s
ed
,
as a
r
e
v
ar
y
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
2
0
2
1
:
5
2
2
9
-
5
2
3
9
5232
T
h
e
UC
I
s
y
s
te
m
i
n
f
o
r
m
atio
n
is
r
o
u
tin
e
l
y
v
ie
w
ed
in
a
d
atab
ase
o
r
in
a
r
ep
o
r
t.
T
h
is
w
o
r
k
u
s
e
s
th
e
W
aik
ato
f
r
a
m
e
w
o
r
k
f
o
r
k
n
o
w
led
g
e
ev
al
u
atio
n
.
T
h
e
d
ata
s
ets
m
u
s
t
b
e
in
th
e
attr
ib
u
te
-
r
elatio
n
f
i
le
f
o
r
m
a
t
(
AR
FF
)
,
to
u
s
e
t
h
is
d
ata
f
o
r
t
h
e
W
E
K
A
m
e
th
o
d
.
I
n
p
r
e
-
p
r
o
ce
s
s
in
g
t
h
e
d
ataset,
t
h
e
W
E
KA
m
et
h
o
d
is
u
s
ed
.
J
u
s
t
m
aj
o
r
attr
ib
u
tes,
i.e
.
1
3
in
th
i
s
ca
s
e,
ar
e
tak
e
n
i
n
to
ac
co
u
n
t
w
h
en
ev
al
u
ati
n
g
all
th
e
s
e
1
3
attr
ib
u
tes,
w
h
ic
h
p
r
o
v
id
e
b
etter
an
d
clea
r
er
r
esu
lts
.
Af
ter
al
l,
u
n
i
m
p
o
r
tan
t
at
tr
ib
u
tes
ar
e
d
is
ca
r
d
ed
.
T
h
e
1
3
th
is
ess
e
n
tia
ll
y
an
ex
p
ec
ted
class
f
ea
t
u
r
e.
T
h
r
o
u
g
h
an
al
y
zi
n
g
th
e
v
ar
io
u
s
d
ec
is
io
n
tr
ee
alg
o
r
it
h
m
s
i
n
s
id
e
W
E
K
A
to
o
ls
ex
ten
s
i
v
el
y
a
n
d
m
a
k
i
n
g
t
h
e
ch
o
ices
it
m
a
k
e
s
,
th
e
d
ev
ice
will
h
elp
p
r
ed
ict
th
e
p
r
o
b
a
b
le
e
x
is
te
n
ce
o
f
ca
r
d
iac
d
is
ea
s
es
in
a
p
atien
t
a
n
d
d
ef
in
i
tel
y
h
e
lp
d
iag
n
o
s
e
ca
r
d
iac
d
i
s
ea
s
es
w
ell
i
n
p
r
ep
ar
atio
n
an
d
cu
r
e
th
e
m
i
n
g
o
o
d
ti
m
e.
So
m
e
o
f
t
h
e
s
ta
n
d
ar
d
m
a
ch
in
e
lear
n
i
n
g
o
f
d
ata
m
i
n
i
n
g
ch
alle
n
g
e
s
is
i
n
th
e
f
o
llo
w
i
n
g
ar
ea
s
:
a.
E
x
tr
ac
tio
n
o
f
v
a
lu
ab
le
in
f
o
r
m
atio
n
an
d
d
ev
elo
p
m
e
n
t
o
f
s
ci
en
ti
f
ic
d
ec
is
io
n
-
m
ak
in
g
ca
p
ab
ilit
y
f
o
r
d
is
ea
s
e
tr
ea
t
m
e
n
t a
n
d
d
iag
n
o
s
i
s
.
b.
C
las
s
i
f
icatio
n
o
f
th
e
d
ev
e
lo
p
m
en
ts
o
f
ef
f
ec
ti
v
e
m
ed
ical
tr
ea
t
m
en
ts
f
o
r
v
ar
io
u
s
ail
m
e
n
ts
.
c.
T
o
o
m
a
n
y
a
ttrib
u
tes
a
v
ailab
le
f
o
r
d
ec
is
io
n
-
m
a
k
i
n
g
s
o
m
u
s
t
d
eter
m
in
e
w
h
ic
h
t
h
e
b
est
p
r
ed
ictio
n
o
f
h
ea
r
t
d
is
ea
s
e.
d.
W
ith
t
h
e
a
s
s
i
s
ta
n
ce
o
f
co
m
p
u
ter
is
atio
n
,
v
o
l
u
m
in
o
u
s
r
ea
l
d
ata
(
tex
t,
g
r
ap
h
s
,
a
n
d
i
m
ag
e
s
)
ar
e
n
o
w
b
ei
n
g
p
r
o
ce
s
s
ed
,
b
u
t it
is
s
till
m
o
r
e
d
if
f
icu
lt to
co
llect.
e.
Han
d
lin
g
n
o
is
y
(
co
n
ta
in
i
n
g
e
r
r
o
r
s
o
r
o
u
tlier
s
)
,
co
n
f
u
s
i
n
g
(
co
n
tain
i
n
g
co
d
e
o
r
n
a
m
e
d
is
cr
ep
an
cies)
an
d
lack
o
f
attr
ib
u
tes to
b
e
p
r
e
-
p
r
o
ce
s
s
ed
f
o
r
m
ed
ical
d
ata
p
r
o
b
lem
s
.
f.
Dete
r
m
i
n
e
th
e
b
est
to
o
ls
an
d
alg
o
r
ith
m
s
f
o
r
an
al
y
s
is
t
h
e
d
atasets
b
y
u
s
in
g
W
E
K
A
to
o
ls
,
an
d
f
o
r
f
u
tu
r
e
w
o
r
k
tr
y
i
n
g
to
u
s
e
M
A
T
L
A
B
p
r
o
g
r
am
f
o
r
d
ev
elo
p
in
g
t
h
e
wo
r
k
.
4.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
p
u
r
p
o
s
e
o
f
th
i
s
s
t
u
d
y
is
t
o
s
u
cc
es
s
f
u
ll
y
p
r
ed
ict
p
o
s
s
ib
l
e
h
ea
r
t
attac
k
s
f
r
o
m
t
h
e
co
m
p
ilatio
n
o
f
m
ed
ic
al
d
ata.
U
s
i
n
g
p
r
ed
ictio
n
al
g
o
r
ith
m
s
to
ev
al
u
ate
th
e
ch
ar
ac
ter
is
t
ics
o
f
ca
r
d
iac
d
is
ea
s
e
b
y
ce
r
tai
n
attr
ib
u
tes,
a
m
o
d
el
h
a
v
e
b
ee
n
d
ev
elo
p
ed
.
Data
m
in
i
n
g
i
s
u
s
ed
in
th
i
s
w
o
r
k
to
cr
ea
te
clas
s
p
r
ed
ictiv
e
m
o
d
els
b
ased
o
n
f
ea
tu
r
es
s
elec
ted
.
T
h
e
W
aik
a
to
en
v
ir
o
n
m
e
n
t
f
o
r
k
n
o
w
led
g
e
r
esear
c
h
(
W
E
K
A
)
h
as
b
ee
n
u
s
ed
f
o
r
p
r
ed
ictio
n
b
ec
au
s
e
o
f
it
s
ab
ili
t
y
to
d
is
co
v
er
,
s
t
u
d
y
,
a
n
d
f
o
r
ec
ast
tr
en
d
s
.
I
t
is
t
y
p
icall
y
p
o
s
s
ib
le
to
d
iv
id
e
t
h
e
e
n
tire
p
r
o
ce
s
s
in
to
6
s
ta
g
es:
4
.
1
.
Descript
io
n o
f
t
he
a
lg
o
r
it
h
m
s
Hea
r
t
d
is
ea
s
e
is
a
w
o
r
d
u
s
ed
to
d
escr
ib
e
a
lar
g
e
v
ar
iet
y
o
f
h
ea
lth
cir
cu
m
s
tan
ce
s
ass
o
ciate
d
w
ith
t
h
e
h
ea
r
t.
T
h
ese
m
ed
ical
co
n
d
itio
n
s
s
p
ec
i
f
icall
y
d
escr
ib
e
th
e
p
a
th
o
lo
g
ical
d
is
ea
s
es
o
f
th
e
h
ea
r
t
as
w
ell
as
all
p
ar
ts
o
f
it.
A
s
u
b
s
ta
n
tial
h
ea
lt
h
co
n
ce
r
n
i
s
h
ea
r
t
d
i
s
ea
s
e.
O
v
er
t
h
e
y
ea
r
s
,
th
e
n
u
m
b
er
o
f
p
eo
p
le
w
h
o
h
a
v
e
h
ea
r
t
d
is
ea
s
e
h
a
s
i
n
cr
ea
s
ed
[
2
0
]
.
Se
v
er
al
s
t
u
d
ies
f
o
cu
s
ed
o
n
th
e
m
an
ag
e
m
e
n
t
o
f
h
ea
r
t
d
is
ea
s
e
h
a
v
e
b
ee
n
co
n
d
u
cted
.
Var
io
u
s
tec
h
n
iq
u
es
f
o
r
d
iag
n
o
s
tic
d
ata
m
in
i
n
g
h
a
v
e
b
ee
n
ap
p
lied
an
d
v
ar
io
u
s
p
r
o
b
ab
ilit
ies
h
a
v
e
b
ee
n
o
b
tain
ed
.
Ma
n
y
s
t
u
d
ies
ar
e
b
e
in
g
co
n
d
u
c
ted
to
ass
e
s
s
t
h
e
i
n
ef
f
icien
c
y
o
f
M
L
P
,
B
a
y
es
n
et
,
S
MO
a
n
d
r
an
d
o
m
f
o
r
est
alg
o
r
it
h
m
s
.
T
h
er
e
ar
e
s
ev
er
al
p
o
s
s
ib
le
s
tr
ate
g
ies to
tr
e
at
h
ea
r
t
d
is
ea
s
e
[
21]
:
a.
ML
P
:
T
h
e
p
er
ce
p
tr
o
n
m
u
lti
-
la
y
er
alg
o
r
ith
m
s
h
elp
t
h
e
p
r
o
b
le
m
s
o
f
r
e
g
r
ess
io
n
an
d
clas
s
i
f
ic
atio
n
.
I
t
is
also
ca
lled
,
f
o
r
s
h
o
r
t,
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
s
o
r
j
u
s
t
n
eu
r
al
n
et
w
o
r
k
s
.
Neu
r
al
n
et
w
o
r
k
s
ar
e
a
ch
allen
g
i
n
g
alg
o
r
ith
m
to
b
e
u
s
ed
f
o
r
p
r
ed
ictiv
e
m
o
d
elin
g
s
in
ce
th
er
e
ar
e
s
o
m
a
n
y
p
ar
a
m
eter
s
o
f
co
n
f
i
g
u
r
atio
n
t
h
at
ca
n
b
e
ef
f
ec
ti
v
el
y
tu
n
ed
o
n
l
y
b
y
o
b
s
er
v
at
io
n
a
n
d
a
n
u
m
b
er
o
f
tr
i
al
an
d
er
r
o
r
[
2
0
]
.
b.
R
an
d
o
m
f
o
r
est
:
An
en
s
e
m
b
le
o
f
r
an
d
o
m
d
ec
is
io
n
tr
ee
clas
s
i
f
ier
s
is
a
r
an
d
o
m
f
o
r
est
t
h
at
m
ak
es
p
r
ed
ictio
n
s
b
y
co
m
b
i
n
in
g
th
e
in
d
i
v
id
u
a
l
t
r
ee
s
'
p
r
ed
ictio
n
s
.
I
n
t
h
e
d
ec
is
i
o
n
tr
ee
co
n
s
tr
u
ct
io
n
p
r
o
ce
s
s
,
v
ar
io
u
s
m
e
th
o
d
s
ar
e
p
o
s
s
ib
le
to
in
co
r
p
o
r
ate
r
an
d
o
m
n
e
s
s
.
T
o
m
a
k
e
f
o
r
ec
asts
ab
o
u
t
clas
s
i
f
icatio
n
o
r
ch
ar
ac
ter
is
tic
s
,
a
r
an
d
o
m
f
o
r
est ca
n
b
e
u
s
ed
.
On
e
o
f
th
e
b
est p
r
ed
ictiv
e
a
n
al
y
t
i
cs is
r
an
d
o
m
f
o
r
ests
[
2
2
]
.
c.
Seq
u
en
t
ial
m
in
i
m
al
o
p
ti
m
izat
io
n
(
SMO)
:
is
an
al
g
o
r
ith
m
f
o
r
s
o
lv
in
g
th
e
q
u
ad
r
atic
p
r
o
g
r
a
m
m
in
g
(
QP
)
p
r
o
b
lem
t
h
at
ar
is
e
s
d
u
r
in
g
t
h
e
tr
ain
in
g
o
f
s
u
p
p
o
r
t
-
v
ec
to
r
m
ac
h
in
e
s
(
SVM)
.
I
t
is
co
m
m
o
n
l
y
u
s
ed
f
o
r
m
ac
h
in
e
le
ar
n
i
n
g
tr
ain
i
n
g
,
s
u
p
p
o
r
t
an
d
is
i
n
tr
o
d
u
ce
d
b
y
th
e
co
m
m
o
n
L
I
B
SVM
to
o
l
.
I
n
th
e
SVM
co
m
m
u
n
it
y
,
th
e
p
u
b
lis
h
i
n
g
o
f
t
h
e
SMO
alg
o
r
it
h
m
in
1
9
9
8
cr
ea
ted
a
lo
t
o
f
an
ticip
atio
n
,
as
p
r
ev
io
u
s
l
y
av
ailab
le
tec
h
n
iq
u
es
f
o
r
SV
M
tr
ain
i
n
g
w
er
e
m
u
c
h
m
o
r
e
co
m
p
lica
ted
an
d
co
s
tl
y
t
h
ir
d
-
p
ar
ty
QP
s
o
lv
er
s
w
er
e
r
eq
u
ir
ed
[
2
3
]
.
d.
B
ay
e
s
n
et
:
T
h
e
B
a
y
es
ian
n
e
t
w
o
r
k
i
s
a
co
m
b
in
a
tio
n
o
f
p
r
o
b
ab
ilit
y
a
n
d
g
r
ap
h
ic
m
o
d
el
s
.
I
t
is
w
id
el
y
ap
p
licab
le
in
m
ac
h
i
n
e
lear
n
in
g
,
d
ata
m
i
n
i
n
g
,
an
d
d
iag
n
o
s
ti
cs
.
b
ec
au
s
e
it
h
as
a
s
o
lid
ev
id
en
tiar
y
-
b
ase
d
co
n
clu
s
io
n
t
h
at
is
f
a
m
iliar
to
h
u
m
a
n
i
n
t
u
itio
n
[
2
4
]
.
4.
2.
T
o
o
l
s
a
nd
da
t
a
s
o
urce
T
h
e
W
aik
ato
E
n
v
ir
o
n
m
en
t
f
o
r
Kn
o
w
led
g
e
A
n
al
y
s
is
2018
(
W
E
KA
2
0
1
8
,
v
er
s
io
n
3
.
8
.
3
)
h
ad
b
ee
n
ad
o
p
ted
as
th
e
s
ta
n
d
ar
d
in
te
r
f
ac
e
to
co
m
p
ar
e
d
i
f
f
er
en
t
d
ata
m
in
i
n
g
tec
h
n
iq
u
es
a
n
d
d
eter
m
i
n
e
t
h
e
b
es
t
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:
2
0
8
8
-
8708
A
n
a
lysi
s
o
f W
E
K
A
d
a
ta
min
in
g
a
lg
o
r
ith
ms B
a
ye
s
n
et,
r
a
n
d
o
m
fo
r
est,
ML
P
a
n
d
...
(
B
a
s
ma
Ju
ma
a
S
a
leh
)
5233
m
et
h
o
d
s
[
2
5
]
.
T
h
e
s
ta
n
d
ar
d
d
ata
k
it
h
ad
b
ee
n
g
etti
n
g
f
r
o
m
t
h
e
I
r
aq
i
h
o
s
p
ital
s
u
n
d
er
t
h
e
o
v
er
s
ig
h
t
o
f
t
h
e
Natio
n
al
M
in
i
s
ter
o
f
Hea
lt
h
i
n
clu
d
e
s
2
0
0
s
a
m
p
le
s
.
T
o
d
etec
t
h
ea
r
t
d
i
s
ea
s
e
w
it
h
a
h
i
g
h
d
eg
r
ee
of
ac
cu
r
ac
y
,
a
lar
g
e
r
an
g
e
o
f
r
elev
a
n
t
in
p
u
t
s
m
u
s
t
b
e
co
n
s
id
er
ed
.
T
h
e
p
h
y
s
ician
r
elies
o
n
all
t
h
e
r
ec
o
r
d
ed
s
y
m
p
to
m
s
,
p
atien
tl
y
an
s
w
er
in
g
q
u
e
s
tio
n
s
,
m
ed
ical
te
s
ti
n
g
a
n
d
lab
o
r
ato
r
y
p
er
f
o
r
m
an
ce
s
.
Ov
er
all,
th
e
d
ata
h
ad
b
ee
n
co
llected
f
r
o
m
th
e
I
b
n
al
-
B
it
ar
Ho
s
p
ital
an
d
th
e
B
ag
h
d
ad
Me
d
ical
cit
y
b
ased
o
n
t
h
ese
m
ed
ical
f
ac
to
r
s
to
p
r
o
v
id
e
ap
p
r
o
p
r
iate
m
ed
ical
c
r
iter
ia
f
o
r
th
e
d
etec
tio
n
o
f
h
ea
r
t
d
is
ea
s
e.
T
h
er
e
h
as
b
ee
n
co
n
s
id
er
ab
le
d
if
f
ic
u
lt
y
in
co
llecti
n
g
t
h
ese
f
ac
to
r
s
b
y
s
o
m
e
m
ed
ical
v
ar
iab
les,
s
u
c
h
as
(
Ma
x
i
m
u
m
ca
r
d
iac
r
ate,
ST
d
ep
r
ess
io
n
,
f
air
l
y
r
estfu
l e
x
er
cise,
t
h
e
s
lo
p
e
o
f
t
h
e
ST
h
ig
h
e
s
t e
x
er
ci
s
e
s
ec
t
io
n
,
an
d
Nu
m
b
er
o
f
k
e
y
f
l
u
o
r
o
s
co
p
y
-
co
lo
r
ed
v
ess
el
s
)
Su
c
h
v
ar
iab
l
e
s
ar
e
th
er
e
f
o
r
e
s
u
b
s
t
itu
ted
f
o
r
m
ed
ical
ca
u
s
es
b
y
ca
r
d
io
lo
g
i
s
ts
(
h
ea
r
t
r
ate,
f
a
m
il
y
h
i
s
to
r
y
,
s
m
o
k
in
g
,
h
y
p
er
k
i
n
es
ia
E
ch
o
,
an
d
an
ea
r
lier
an
g
in
a
a
s
s
a
u
lt)
[
2
6
]
.
T
h
e
ad
a
p
ted
m
ed
ical
v
ar
iab
le
s
,
co
n
s
id
er
th
e
ca
u
s
al
f
ac
to
r
,
th
e
f
a
m
il
y
m
ed
ical
h
is
to
r
y
,
b
esid
es
th
e
o
b
s
er
v
ed
ec
h
o
th
e
p
r
o
b
ab
ilit
y
o
f
p
r
io
r
an
g
in
a
to
g
et
ad
eq
u
a
te
m
ed
ical
ca
u
s
es;
t
h
ese
d
ata
w
o
u
ld
in
cl
u
d
e
f
o
u
r
class
es
o
f
h
ea
r
t
d
is
ea
s
e
b
esid
es
n
o
r
m
a
l
clas
s
es.
T
ab
le
1
s
h
o
w
s
th
e
a
v
ailab
ili
t
y
o
f
t
h
e
f
i
v
e
class
e
s
o
f
ca
r
d
iac
d
is
ea
s
es
a
n
d
in
cl
u
d
es
1
3
m
e
d
ical
f
e
atu
r
e
s
r
eq
u
ir
ed
f
o
r
ca
r
d
io
v
ascu
lar
tr
ea
t
m
en
t.
T
o
cr
e
ate
a
d
iag
n
o
s
t
ics
s
y
s
te
m
,
t
h
ese
f
ac
to
r
s
ar
e
tu
r
n
e
d
in
to
a
n
u
m
er
ical
s
i
m
p
li
f
icati
o
n
[
2
7
]
.
T
ab
le
1
.
C
o
llected
d
ataset
(
C
D)
A
g
e
R
e
a
l
(
0
-
7
6
)
S
e
x
M
a
l
e
"
0
"
F
e
mal
e
"
1
"
CP
t
y
p
_
a
n
g
i
n
a
"
1
"
A
s
y
mp
t
"
2
"
n
o
n
_
a
n
g
i
n
a
l
"
3
"
a
t
y
p
_
a
n
g
i
n
a
"
4
"
BP
R
e
a
l
C
o
l
N
o
r
mal
"
0
"
A
b
n
o
r
mal
"
1
"
F
o
b
s v
a
l
u
e
>
1
2
0
mg
/
d
e
l
"
1
"
t
r
u
e
<
1
2
0
mg
/
d
e
l
"
0
"
f
a
l
se
R
e
st
E
C
G
N
o
r
mal
"
0
"
A
b
n
o
r
mal
i
t
y
"
1
"
l
e
f
t
_
v
e
n
t
_
h
y
p
e
r
"
2
"
T
h
a
l
a
c
h
V
a
l
u
e
R
e
a
l
Ex
a
m
No
"
0
"
Y
e
s
"
1
"
FH
No
"
0
"
Y
e
s
"
1
"
SM
No
"
0
"
Y
e
s
"
1
"
HYP
No
"
0
"
Y
e
s
"
1
"
P
ER
A
N
G
I
N
A
N
o
(
N
e
g
a
t
i
v
e
)
"
0
"
Y
e
s (P
o
si
t
i
v
e
)
"
1
"
4
.
3
.
At
t
ribute
des
cr
iptio
n
a.
Ag
e
: r
ep
r
esen
t
s
in
y
ea
r
s
t
h
e
n
u
m
er
ic
v
al
u
e
o
f
ag
e.
b.
Sex
:
w
h
ic
h
w
ill b
e
r
ep
r
esen
te
d
in
b
in
ar
y
(
0
=
m
ale,
1
=f
e
m
ale
).
c.
C
u
p
T
y
p
e:
t
h
e
ab
b
r
ev
iatio
n
o
f
C
h
e
s
t p
ain
t
y
p
e
s
,
w
h
ic
h
w
il
l b
e
in
tr
o
d
u
ce
d
as f
o
llo
w
s
:
Valu
e
1
:
T
y
p
ical
B
u
r
n
in
g
Se
n
s
atio
n
i
n
h
ea
r
t
.
Valu
e
2
:
A
cu
te
s
tab
b
in
g
(
s
u
c
h
as
p
ain
).
Valu
e
3
:
B
u
r
n
i
n
g
Se
n
s
atio
n
.
Valu
e
4
:
A
cu
te
C
r
u
s
h
in
g
P
ain
in
h
ea
r
t
.
d.
C
o
l
:
C
h
o
lest
er
o
l le
v
el
i
n
p
atie
n
t
w
h
er
e
1
=
A
b
n
o
r
m
al,
0
=
N
o
r
m
al
e.
Fo
b
s
:
f
ast
in
g
b
lo
o
d
s
u
g
ar
le
v
e
l
w
h
er
e
1
=
tr
u
e
(
>1
2
0
m
g
/d
el
)
,
0
=
f
alse (
<1
2
0
m
g
/d
el)
.
f.
R
est E
C
G
: th
e
ab
b
r
ev
iat
io
n
o
f
R
ested
E
lectr
o
ca
r
d
io
G
r
ap
h
ic
,
th
e
in
d
icate
d
v
al
u
e
s
o
f
th
e
r
e
p
o
r
t
ar
e:
Valu
e
0
: n
o
r
m
a
l
Valu
e
1
: ST
-
T
w
a
v
e
A
b
n
o
r
m
a
lit
y
Valu
e
2
: V
en
tr
ic
u
lar
A
b
n
o
r
m
a
lit
y
.
g.
T
h
alac
h
Valu
e
:
s
h
o
w
s
th
e
ac
h
i
ev
ed
m
a
x
i
m
u
m
h
ea
r
t r
ate
.
h.
E
x
a
m
:
w
h
ic
h
i
m
p
lies
t
h
e
e
n
g
i
n
e
th
at
ca
u
s
ed
b
y
e
x
er
cisi
n
g
(
1
=
y
es,
0
=
n
o
)
.
i.
FH
:
f
a
m
il
y
h
is
to
r
y
ca
n
b
e
as st
r
o
n
g
o
f
a
m
ar
k
er
f
o
r
h
ea
r
t d
is
e
ase
(
1
=
y
es,
0
=
n
o
)
.
j.
SM
:
S
m
o
k
i
n
g
i
n
cr
ea
s
e
s
th
e
r
i
s
k
o
f
d
ev
elo
p
in
g
ca
r
d
io
v
asc
u
la
r
d
is
ea
s
es (
1
=
y
e
s
,
0
=
n
o
)
.
k.
HYP
-
E
ch
o
f
i
n
d
i
n
g
f
o
r
h
y
p
o
K
in
esi
s
(
1
=
y
e
s
,
0
=
n
o
)
.
l.
P
E
R
A
NGI
N
A
:
p
r
ev
io
u
s
attac
k
o
f
an
g
i
n
a
(
1
=
y
es,
0
=
n
o
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
2
0
2
1
:
5
2
2
9
-
5
2
3
9
5234
m.
C
las
s
:
C
la
s
s
o
f
P
atien
t
s
w
it
h
h
ea
r
t
d
is
ea
s
e.
Valu
e
0
:
C
o
r
o
n
ar
y
Hea
r
t
d
is
ea
s
e,
Valu
e
1
:
An
g
i
n
a
p
ec
to
r
is
,
Valu
e
2
: Co
n
g
e
s
tiv
e
h
ea
r
t f
a
il
u
r
e,
Valu
e
3
:
A
r
r
h
y
th
m
ia
s
,
Va
lu
e
4
: N
o
r
m
al
.
4
.
4
.
P
er
f
o
rm
a
nce
m
et
rics
T
h
e
m
etr
ic
s
u
s
ed
in
t
h
e
an
al
y
s
is
w
ill b
e
d
ef
i
n
ed
in
d
etail
t
h
r
o
u
g
h
o
u
t th
i
s
s
ec
tio
n
[
2
5
]
:
4
.
4
.
1
.
P
re
cisi
o
n
P
r
ec
is
io
n
1
: th
e
p
ar
t b
et
w
ee
n
t
h
e
ac
cu
m
u
lated
in
s
tan
ce
s
o
f
m
aj
o
r
ca
s
es.
T
h
e
p
r
ec
is
io
n
eq
u
atio
n
is
:
P
r
ec
is
io
n
1
=
T
P
1
/ (
T
P
1
+FP
1
)
(
1
)
4
.
4
.
2
.
Rec
a
ll
T
h
e
s
m
al
l
s
u
b
s
et
o
f
th
e
r
eq
u
i
r
ed
in
s
ta
n
ce
s
i
n
t
h
e
o
v
er
all
n
u
m
b
er
o
f
p
ar
tic
u
lar
i
n
s
ta
n
ce
s
.
T
h
e
r
ec
all
eq
u
atio
n
is
:
R
ec
all
1
=
T
P
1
/ (
T
P
1
+
FN
1
)
(
2
)
4
.
4
.
3
.
F
-
M
e
a
s
ure
T
h
e
f
-
m
ea
s
u
r
e
is
e
x
a
m
in
ed
b
ased
o
n
th
e
2
-
f
o
ld
p
r
ec
is
io
n
r
e
m
i
n
d
er
p
er
io
d
s
ep
ar
ate
d
b
y
t
h
e
s
u
m
o
f
ac
cu
r
ac
y
a
n
d
r
e
m
in
d
er
[
2
8
]
.
T
h
e
F
-
Me
as
u
r
e
eq
u
atio
n
i
s
p
r
o
v
id
ed
in
(
3
)
.
=
1
∗
1
−
1
∗
1
√
(
1
+
1
)
(
1
+
1
)
(
1
+
1
)
(
1
+
1
)
(
3
)
4
.
4
.
4
.
Are
a
o
f
RO
C
R
OC
eq
u
atio
n
s
ar
e
co
m
m
o
n
l
y
u
s
ed
as
v
is
u
als
ab
o
u
t
a
n
y
cu
to
f
f
,
i
n
clu
d
i
n
g
cli
n
ical
s
e
n
s
itiv
it
y
a
n
d
ac
cu
r
ac
y
,
f
o
r
an
a
s
s
es
s
m
en
t o
r
a
v
ar
iet
y
o
f
te
s
ts
,
r
elatio
n
s
h
ip
s
,
an
d
tr
ad
e
-
o
f
f
.
4
.
4
.
5
.
Are
a
o
f
P
RC
T
h
e
n
u
m
b
er
o
f
lo
w
er
g
r
ad
es
o
f
p
atien
t
s
w
it
h
o
u
t
a
d
ia
g
n
o
s
i
s
ar
e
n
o
t
a
f
f
ec
ted
b
y
cu
r
v
es
f
o
r
co
r
r
ec
t
r
ec
all.
I
t
is
p
ar
ticu
lar
l
y
i
m
p
o
r
tan
t
to
u
s
e
p
r
ec
is
io
n
r
ec
o
r
d
in
g
f
o
r
m
u
la
s
to
s
u
p
p
le
m
e
n
t
t
h
e
R
OC
f
o
r
m
u
las
to
o
b
tain
th
e
co
m
p
lete
s
p
ec
tr
u
m
d
u
r
in
g
an
a
l
y
s
is
a
n
d
s
e
lectio
n
.
T
h
e
class
i
f
icatio
n
m
o
d
el
p
r
o
d
u
ct
[
2
6
]
,
as
s
h
o
w
n
in
T
ab
le
2
.
T
ab
le
2
.
Var
io
u
s
ef
f
ec
t
s
o
f
a
t
w
o
-
clas
s
m
o
d
el
S
p
e
c
i
f
i
c
C
l
a
ss
C
l
a
ss Pr
e
d
i
c
t
e
d
Y
ES
No
Y
ES
P
o
si
t
i
v
e
T
r
u
e
(
T
P
1
)
N
e
g
a
t
i
v
e
F
a
l
se
(
F
N
1
)
No
P
o
si
t
i
v
e
F
a
l
se
(
F
P
1
)
N
e
g
a
t
i
v
e
T
r
u
e
(
T
N
1
)
a.
P
o
s
itiv
e
tr
u
e
(TP
1
)
:
I
t
w
a
s
f
ai
r
l
y
ex
p
ec
ted
th
at
p
atien
t
s
w
er
e
p
o
s
itiv
e
(
P
atien
ts
ar
e
lik
el
y
to
r
eq
u
ir
e
h
ea
r
t
f
ail
u
r
e
an
d
h
ea
r
t c
a
u
ter
is
atio
n
.
)
.
b.
P
o
s
itiv
e
f
alse
(
FP
1
)
:
I
f
T
P
1
a
n
d
T
N
1
ar
e
ap
p
r
o
x
i
m
atel
y
1
0
0
p
er
ce
n
t,
th
e
m
o
d
el
is
id
ea
ll
y
p
r
ed
icted
to
b
e
n
eg
at
iv
e,
b
ec
au
s
e
th
e
y
ar
e
n
o
t
s
u
p
p
o
s
ed
to
h
av
e
a
ca
r
d
iac
ca
th
eter
iza
tio
n
.
c.
TN
1
is
a
n
eg
ativ
e
tr
u
e:
Hea
lt
h
y
p
eo
p
le
ar
e
p
r
o
p
er
ly
class
i
f
ie
d
as h
ea
lth
y
.
d.
FN
1
is
n
e
g
ati
v
e
f
al
s
e
: C
lass
if
i
ed
in
co
r
r
ec
tly
a
s
h
ea
lt
h
y
[
2
8
]
h
ea
r
t d
is
ea
s
e
p
atie
n
ts
.
e.
C
o
r
r
ec
t
class
i
f
ied
ca
s
e
s
(
C
C
C
)
:
T
h
is
r
ep
r
esen
ts
th
e
p
r
o
p
o
r
tio
n
o
f
p
atie
n
t
s
w
h
o
n
ee
d
a
n
d
n
o
t
n
ee
d
h
ea
r
t
s
u
r
g
er
y
an
d
ar
e
d
iag
n
o
s
ed
co
r
r
ec
tl
y
.
A
cc
u
r
ac
y
[
2
9
]
is
also
k
n
o
w
n
as
el
k
(
4
)
.
A
cc
u
r
ac
y
=
1
+
1
1
+
1
+
1
+
1
(
4
)
f.
Me
an
ab
s
o
l
u
te
er
r
o
r
(
MA
E
)
:
A
test
o
f
p
r
ed
icto
r
s
.
T
h
e
ca
lcu
latio
n
o
f
1
-
AC
C
is
p
r
o
b
ab
le.
A
s
tr
o
n
g
s
y
s
te
m
h
as a
v
er
y
h
i
g
h
ab
s
o
lu
te
m
ea
n
er
r
o
r
[
3
0
]
.
g.
Kap
p
a:
P
r
e
d
ictio
n
id
en
tific
ati
o
n
w
i
th
a
co
r
r
ec
t
class
is
c
h
ec
k
ed
b
y
Kap
p
a.
T
h
e
s
tatis
tica
l
ef
f
ec
t
o
f
a
k
ap
p
a
is
a
s
co
r
e
in
th
e
0
-
1
r
an
g
e.
A
v
alu
e
g
r
ea
ter
t
h
an
0
m
ea
n
s
it is
b
etter
th
an
a
v
er
ag
e
f
o
r
th
e
cla
s
s
i
f
ier
[
3
1
]
.
h.
R
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
1
)
:
T
he
d
if
f
er
en
ce
b
et
w
e
en
th
e
v
al
u
e
p
r
ed
icted
an
d
th
e
v
alu
e
o
b
s
er
v
ed
[
3
2
]
is
th
e
r
o
o
t m
ea
n
s
q
u
ar
ed
er
r
o
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
A
n
a
lysi
s
o
f W
E
K
A
d
a
ta
min
in
g
a
lg
o
r
ith
ms B
a
ye
s
n
et,
r
a
n
d
o
m
fo
r
est,
ML
P
a
n
d
...
(
B
a
s
ma
Ju
ma
a
S
a
leh
)
5235
R
M
SE1
=
√
1
∑
(
1
,
1
−
)
2
=
1
(
5
)
1
,
1
=
Valu
e
p
r
ed
icted
.
=
Ma
x
v
al
u
e
o
f
f
it
n
es
s
ap
p
licab
ilit
y
o
f
j
.
4
.
5
.
P
ro
po
s
ed
ٍ
s
t
ra
t
eg
ies
T
h
is
r
esear
ch
ai
m
s
to
p
r
ed
ict
th
e
p
o
s
s
ib
ilit
y
o
f
h
ea
r
t
d
is
ea
s
e
o
cc
u
r
r
en
ce
b
y
ea
r
l
y
a
u
to
m
atic
d
iag
n
o
s
is
w
it
h
i
n
s
h
o
r
t
ti
m
e.
I
n
ad
d
itio
n
,
th
at
w
il
l
h
elp
h
ea
lt
h
ca
r
e
p
r
o
f
ess
io
n
als
to
tr
ea
t
th
eir
p
atien
ts
ea
r
l
y
b
ased
o
n
ac
cu
r
ate
d
ec
is
i
on
-
m
ak
in
g
.
I
n
ad
d
itio
n
,
th
e
p
r
o
p
o
s
al
h
as
a
c
r
u
cial
r
o
le
in
h
ea
lt
h
ca
r
e
Or
g
a
n
izatio
n
e
s
p
ec
iall
y
f
o
r
ex
p
er
ts
w
it
h
h
a
v
in
g
le
s
s
k
n
o
w
led
g
e
an
d
s
k
ill
s
.
T
h
e
ac
cu
r
ate
r
esu
lts
co
n
s
id
er
ed
as
th
e
m
aj
o
r
lim
i
tatio
n
o
f
ex
is
t
in
g
m
et
h
o
d
o
lo
g
y
.
T
h
e
p
r
o
p
o
s
al
u
s
ed
b
o
th
d
ata
m
i
n
i
n
g
tech
n
iq
u
e
s
an
d
m
ac
h
in
e
l
ea
r
n
in
g
al
g
o
r
ith
m
s
SMO,
ML
P
,
r
an
d
o
m
f
o
r
est
a
n
d
B
ay
e
s
n
et
,
w
it
h
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
to
p
r
ed
ict
th
e
o
cc
u
r
r
en
ce
o
f
h
ea
r
t
d
is
ea
s
e.
Ma
n
y
o
f
m
ed
ical
attr
ib
u
tes
h
ad
b
ee
n
u
s
ed
to
id
en
t
if
y
i
f
t
h
e
p
atien
t
eith
er
h
as
h
ea
r
t
d
is
ea
s
e
o
r
n
o
t,
s
u
c
h
as
b
lo
o
d
p
r
ess
u
r
e,
ch
o
les
ter
o
l,
ag
e,
b
lo
o
d
s
u
g
ar
,
s
e
x
,
a
n
d
h
ea
r
t
r
ate.
T
h
e
d
ata
s
e
t
h
ad
b
ee
n
an
a
l
y
ze
d
a
n
d
co
m
p
u
ted
u
s
i
n
g
t
h
e
W
E
K
A
s
o
f
t
w
ar
e.
W
E
K
A
i
s
o
p
en
-
s
o
u
r
ce
s
o
f
t
w
ar
e
t
h
at
i
n
cl
u
d
es
a
s
et
o
f
m
ac
h
i
n
e
lear
n
i
n
g
alg
o
r
ith
m
s
f
o
r
th
e
d
ata
m
in
in
g
task
s
.
W
E
KA
h
ad
b
ee
n
i
m
p
le
m
en
ted
w
ith
J
av
a
co
d
e.
W
E
KA
co
n
tain
s
s
e
v
er
al
to
o
ls
,
w
h
ic
h
ar
e
i
m
p
o
r
tan
t
i
n
d
ata
m
i
n
i
n
g
ta
s
k
s
:
p
r
ep
r
o
ce
s
s
i
n
g
d
ata,
r
eg
r
es
s
io
n
,
c
lu
s
ter
in
g
,
clas
s
i
f
icatio
n
,
ass
o
ciatio
n
a
n
d
v
i
s
u
al
izatio
n
.
T
h
e
an
al
y
s
i
s
o
f
W
E
K
A
m
eth
o
d
o
lo
g
y
as s
h
o
w
n
i
n
Fi
g
u
r
e
1.
Fig
u
r
e
1
.
T
h
e
s
tep
s
f
o
llo
w
ed
i
n
th
e
m
et
h
o
d
o
lo
g
y
5.
RE
SU
L
T
S
A
ND
P
E
RF
O
RM
ANCE CO
M
P
ARIS
O
NS
T
h
e
W
ek
a
d
ata
m
i
n
i
n
g
to
o
l
h
as
b
ee
n
u
s
ed
f
o
r
cli
n
ical
f
o
r
ec
asts
,
P
ar
t
of
t
h
e
d
ataset
is
u
s
ed
f
o
r
lear
n
in
g
a
n
d
th
e
r
e
m
ai
n
d
er
o
f
test
i
n
g
t
h
e
cla
s
s
i
f
icatio
n
r
esu
lts
ar
e
s
h
o
w
n
i
n
t
h
e
T
ab
le
3
.
T
h
e
r
esu
lts
of
th
e
class
i
f
icatio
n
d
iag
r
a
m
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
2
.
T
o
co
n
clu
d
e,
th
e
esti
m
a
te
r
esu
l
ts
s
ep
ar
ated
b
y
a
d
if
f
er
en
t
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
e
s
.
T
h
e
p
latf
o
r
m
w
as
b
u
ilt
w
it
h
2
0
0
u
n
its
.
Se
v
er
al
ev
alu
a
tio
n
m
etr
ic
s
w
er
e
co
m
p
ar
ed
an
d
s
h
o
w
n
i
n
Fi
g
u
r
e
2
:
C
las
s
if
icatio
n
p
r
ec
is
io
n
,
R
E
M,
Kap
p
a,
M
A
E
,
R
MSE
,
R
A
E
,
R
R
S
E
,
F
-
m
ea
s
u
r
e,
P
R
C
an
d
R
OC
v
alu
es.
B
ased
o
n
th
e
ac
c
u
r
ac
y
o
f
clas
s
i
f
icat
io
n
s
w
h
ich
i
s
ca
lcu
lated
b
y
(
4
)
,
Fig
u
r
e
2
(
a
)
,
T
h
e
h
ig
h
est
ac
c
u
r
ac
y
i
s
g
i
v
e
n
b
y
B
a
y
es
Net
,
a
b
o
u
t
9
4
.
5
0
%
an
d
T
h
e
w
o
r
s
t
(
8
3
%
)
ac
h
iev
ed
b
y
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
in
e
s
ti
m
ati
n
g
h
ea
r
t
d
i
s
ea
s
e
ca
s
es.
Fro
m
Fi
g
u
r
e
2
(
b
)
,
it
ca
n
b
e
co
n
clu
d
ed
t
h
at
R
an
d
o
m
Fo
r
est
h
as
th
e
h
i
g
h
es
t
p
r
ec
is
io
n
m
ea
s
u
r
e
(
0
.
8
9
7
)
,
a
n
d
r
ec
all
(
0
.
8
9
5
)
.
Mo
s
tly
o
n
b
ase
o
f
Fig
u
r
e
2
(
b
).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
2
0
2
1
:
5
2
2
9
-
5
2
3
9
5236
I
t
ca
n
al
s
o
b
e
s
h
o
w
n
th
at
i
n
t
h
e
r
ec
all
m
etr
ic
s
,
m
u
lt
ila
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
an
d
SMO
ar
e
al
m
o
s
t
id
en
t
ical,
b
u
t
d
is
tin
c
t
in
p
r
ec
is
io
n
.
F
ig
u
r
e
2
(
c
)
d
em
o
n
s
tr
ates
th
a
t
B
a
y
es
Net
p
er
f
o
r
m
s
th
e
b
est,
p
r
o
v
id
in
g
m
ax
i
m
u
m
F
-
m
ea
s
u
r
e
v
alu
e
s
(
0
.
8
8
5
)
,
R
OC
(
0
.
9
7
1
)
an
d
P
R
C
(
0
.
8
6
4
)
.
Fig
u
r
e
2
(
d
)
d
em
o
n
s
tr
ates
t
h
at,
w
h
ile
r
an
d
o
m
f
o
r
est,
M
A
E
(
0
.
0
8
8
)
h
ig
h
l
y
s
m
aller
th
a
n
s
eq
u
e
n
tia
l
m
i
n
i
m
al
o
p
tim
iza
tio
n
(
SMO)
(
0
.
2
4
9
2
)
b
u
t
R
MSE
o
f
r
an
d
o
m
f
o
r
est
(
0
.
1
9
9
2
)
is
th
e
least
an
d
Kap
p
a
o
f
r
an
d
o
m
f
o
r
est
(
0
.
8
4
3
1
)
is
th
e
g
r
ea
test
.
Fig
u
r
e
2
(
e
)
s
h
o
w
s
R
R
SE
o
f
B
a
y
es Ne
t (
5
4
.
8
4
%),
w
h
ic
h
co
n
tr
ib
u
te
s
to
b
etter
p
r
ed
ictio
n
r
esu
lt
s
.
T
ab
le
3
.
T
h
e
c
o
m
p
ar
is
o
n
r
es
u
l
t o
f
th
e
f
o
u
r
clas
s
if
ier
s
A
l
g
o
r
i
t
h
m
P
a
r
a
me
t
e
r
R
a
n
d
o
m F
o
r
e
st
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
(
M
L
P
)
S
e
q
u
e
n
t
i
a
l
M
i
n
i
m
a
l
O
p
t
i
mi
z
a
t
i
o
n
(
S
M
O
)
B
a
y
e
s Ne
t
C
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
s
t
a
n
c
e
s
8
9
.
5
%
81
%
8
3
%
8
8
.
5
%
I
n
c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
st
a
n
c
e
s
1
0
.
5
%
1
9
%
17
%
1
1
.
5
%
K
a
p
p
a
s
t
a
t
i
s
t
i
c
0
.
8
4
3
1
0
.
7
1
5
6
0
.
7
3
7
4
0
.
8
3
0
1
M
e
a
n
a
b
so
l
u
t
e
e
r
r
o
r
0
.
0
8
8
0
.
0
8
3
5
0
.
2
4
9
2
0
.
0
7
0
7
R
o
o
t
me
a
n
sq
u
a
r
e
d
e
r
r
o
r
0
.
1
9
9
2
0
.
2
5
5
0
.
3
3
0
3
0
.
2
0
2
R
e
l
a
t
i
v
e
a
b
so
l
u
t
e
e
r
r
o
r
3
2
.
2
9
9
4
%
3
0
.
6
7
1
8
%
9
1
.
4
8
6
7
%
2
5
.
9
6
6
4
%
R
o
o
t
r
e
l
a
t
i
v
e
sq
u
a
r
e
d
e
r
r
o
r
5
4
.
0
9
9
9
%
6
9
.
2
3
6
3
%
8
9
.
7
0
7
2
%
5
4
.
8
4
3
8
%
A
c
c
u
r
a
c
y
9
4
%
8
3
%
8
9
%
9
4
.
5
%
C
o
n
st
r
u
c
t
i
o
n
T
i
me
0
.
1
4
S
e
c
0
.
5
6
S
e
c
0
.
1
3
S
e
c
0
.
0
1
S
e
c
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
2
.
E
v
alu
atio
n
o
f
p
er
f
o
r
m
an
ce
m
etr
ic
s
u
s
in
g
p
er
ce
n
ta
g
e
s
p
lit o
f
,
(
a)
A
cc
u
r
ac
y
,
(
b
)
P
r
ec
is
io
n
an
d
r
ec
all
m
etr
i
cs,
(
c)
R
O
C
,
P
R
C
,
an
d
F
-
m
ea
s
u
r
e
m
etr
ic
s
,
(
d
)
Kap
p
a,
MA
E
a
n
d
R
MSE
m
etr
ics
,
(
e)
R
A
E
an
d
R
R
SE
m
etr
ics
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:
2
0
8
8
-
8708
A
n
a
lysi
s
o
f W
E
K
A
d
a
ta
min
in
g
a
lg
o
r
ith
ms B
a
ye
s
n
et,
r
a
n
d
o
m
fo
r
est,
ML
P
a
n
d
...
(
B
a
s
ma
Ju
ma
a
S
a
leh
)
5237
T
o
ev
alu
ate
th
e
e
f
f
icien
c
y
o
f
class
i
f
icatio
n
s
tr
ate
g
ies
f
o
r
class
p
r
ed
ictio
n
an
d
d
et
er
m
in
a
tio
n
ac
cu
r
ac
y
,
t
h
e
alg
o
r
it
h
m
is
e
m
p
lo
y
ed
in
th
e
d
ata
s
e
t
t
h
r
o
u
g
h
s
tr
atif
ied
1
0
-
f
o
ld
tes
tin
g
.
T
h
e
r
esu
lti
n
g
u
n
ce
r
tai
n
t
y
m
atr
i
x
ca
lcu
lates
t
h
e
m
ea
s
u
r
e
m
e
n
t
s
f
o
r
ac
c
u
r
ac
y
,
s
e
n
s
it
iv
i
t
y
,
a
n
d
s
p
ec
i
f
icit
y
.
T
h
e
m
atr
ix
ap
p
lie
s
to
s
a
m
p
les
lab
eled
as
tr
u
e,
o
th
er
s
as
f
a
ls
e
an
d
o
th
er
s
as
w
r
o
n
g
.
C
o
n
f
u
s
io
n
m
atr
i
x
esti
m
atio
n
r
ev
ea
ls
th
a
t
s
eq
u
en
tial
m
i
n
i
m
al
o
p
ti
m
izati
o
n
(
SMO)
,
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
,
r
an
d
o
m
f
o
r
est
a
n
d
B
ay
e
s
n
et
s
h
o
w
2
0
0
in
s
tan
ce
s
w
it
h
t
h
e
p
o
s
i
ti
v
e
ca
u
s
al
f
ac
to
r
f
o
r
a
h
ea
r
t
a
ttack
.
P
r
ed
ictio
n
s
s
h
o
w
a
p
r
e
d
ictiv
e
m
o
d
el.
T
h
e
m
et
h
o
d
s
s
tr
o
n
g
l
y
ad
v
is
e
t
h
at
tech
n
iq
u
es
f
o
r
d
ata
m
i
n
i
n
g
ca
n
p
r
ed
ict
a
d
iag
n
o
s
tic
cl
ass
.
T
h
e
m
atr
i
x
o
f
u
n
ce
r
tai
n
t
y
s
p
ec
i
f
icall
y
clas
s
i
f
ies th
e
f
u
n
ctio
n
al
ac
cu
r
ac
y
.
T
h
e
m
atr
i
x
co
n
f
ir
m
s
t
h
e
m
o
d
el
's p
er
f
o
r
m
an
ce
.
W
e
ch
ec
k
ed
t
h
e
f
o
r
m
u
las
f
o
r
th
e
cla
s
s
i
f
icatio
n
o
f
h
ear
t
d
i
s
e
ases
m
e
n
tio
n
ed
i
n
t
h
e
w
o
r
k
e
x
p
er
ien
ce
s
ec
tio
n
o
f
t
h
e
s
u
g
g
e
s
ted
clas
s
if
ier
s
.
I
t
co
n
tr
ast
s
t
h
e
s
u
g
g
e
s
ted
W
E
KA
m
et
h
o
d
clas
s
if
ic
atio
n
m
eth
o
d
w
it
h
o
th
er
r
esear
ch
f
i
n
d
in
g
s
in
T
ab
le
4
an
d
Fig
u
r
e
3
,
i
n
co
m
p
a
r
is
o
n
w
it
h
t
h
e
c
u
r
r
en
t
m
et
h
o
d
s
an
d
e
x
p
er
i
m
e
n
tal
test
s
,
w
e
co
n
s
id
er
th
a
t
o
u
r
p
r
o
p
o
s
ed
s
y
s
te
m
i
s
b
etter
th
a
n
t
h
e
o
th
er
m
o
d
el
in
p
r
ed
ictio
n
a
n
d
d
iag
n
o
s
i
s
o
f
h
ea
r
t
d
is
ea
s
e.
T
h
er
ef
o
r
e,
th
e
p
r
ec
is
io
n
o
f
th
e
cla
s
s
i
f
icatio
n
o
f
c
u
r
r
en
t
m
o
d
els i
s
i
m
p
r
o
v
ed
.
T
ab
le
4
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
s
y
s
te
m
u
s
i
n
g
d
i
f
f
er
e
n
t
tec
h
n
iq
u
es a
n
d
o
th
er
w
o
r
k
s
M
o
d
e
l
o
f
o
t
h
e
r
w
o
r
k
s
T
e
c
h
n
i
q
u
e
s
u
se
d
A
c
c
u
r
a
c
y
P
r
o
p
o
se
d
M
o
d
e
l
G
h
a
r
e
h
c
h
o
p
o
g
h
e
t
a
l
.
[
1
1
]
(
2
0
1
1
)
M
L
P
8
0
.
8
9
%
8
3
%
A
.
K
.
R
a
mo
t
r
a
e
t
a
l
.
[
1
2
]
(
2
0
2
0
)
M
L
P
8
0
.
8
9
%
8
3
%
P
u
r
u
s
h
o
t
t
a
m
e
t
a
l
.
[
1
3
]
(
2
0
1
6
)
M
L
P
7
4
.
8
5
8
3
%
A
u
n
g
N
w
a
y
O
o
e
t
a
l
.
[
1
4
]
(
2
0
1
9
)
S
M
O
8
2
.
6
%
8
9
%
M
i
r
p
o
u
y
a
M
i
r
mo
z
a
f
f
a
r
i
e
t
a
l
.
[
1
5
]
(
2
0
1
7
)
B
a
y
e
s Ne
t
8
0
.
8
3
%
9
4
.
5
%
R
.
Jo
t
h
i
k
u
mar
e
t
a
l
.
[
1
6
]
(
2
0
1
6
)
R
a
n
d
o
m F
o
r
e
st
7
8
.
2
4
%
9
4
%
S
a
r
a
n
g
a
m
K
o
d
a
t
i
e
t
a
l
.
[
1
7
]
(
2
0
1
8
)
R
a
n
d
o
m F
o
r
e
st
8
1
.
9
%
9
4
%
Fig
u
r
e
3
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
s
y
s
t
e
m
u
s
i
n
g
d
i
f
f
er
e
n
t
t
ec
h
n
iq
u
es
an
d
o
th
er
w
o
r
k
s
6.
CO
NCLU
SI
O
N
I
n
th
is
a
n
al
y
s
i
s
,
w
e
h
av
e
s
u
b
m
itted
an
ef
f
ec
ti
v
e
p
r
ed
ictio
n
m
et
h
o
d
f
o
r
h
ea
r
t
d
is
ea
s
e
w
it
h
d
ata
ex
tr
ac
tio
n
a
n
d
test
t
h
e
ac
c
u
r
a
c
y
o
f
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
w
i
th
a
g
r
o
u
p
o
f
cla
s
s
i
f
ier
s
.
T
h
e
co
llected
h
ea
r
t
d
atab
ase
f
o
r
tr
ai
n
in
g
a
n
d
te
s
ti
n
g
p
u
r
p
o
s
es
w
as
u
s
ed
f
r
o
m
t
h
e
h
o
s
p
ital
o
f
I
b
n
al
-
B
itar
an
d
B
ag
h
d
ad
m
ed
ical
cit
y
.
T
h
is
p
r
o
g
r
a
m
w
i
ll
ass
i
s
t
p
h
y
s
ic
ian
s
in
ac
c
u
r
ac
y
,
p
ar
am
eter
-
s
p
ec
if
ic
d
ec
is
io
n
s
.
T
h
e
r
esear
ch
h
as
b
ee
n
s
u
cc
e
s
s
f
u
ll
y
p
er
f
o
r
m
ed
i
n
s
e
v
er
al
tech
n
iq
u
es
f
o
r
t
h
e
clas
s
i
f
icatio
n
o
f
d
ata
m
i
n
i
n
g
(
SMO,
ML
P
,
B
a
y
es
Ne
t
an
d
R
a
n
d
o
m
Fo
r
est)
w
it
h
a
d
iag
o
n
al
o
u
tp
u
t
o
f
ten
f
o
ld
,
an
d
it
i
s
f
o
u
n
d
t
h
at
t
h
e
B
a
y
e
s
Net
alg
o
r
it
h
m
g
iv
e
s
g
r
ea
ter
ac
cu
r
ac
y
t
h
a
n
t
h
e
o
th
er
d
ata
s
et
s
u
p
p
lied
(
9
4
.
5
%
)
.
I
t
ca
n
also
b
e
u
s
ed
w
it
h
m
an
y
cla
s
s
i
f
icatio
n
tech
n
iq
u
es.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
lik
e
to
th
a
n
k
M
u
s
ta
n
s
ir
i
y
a
h
Un
i
v
er
s
it
y
(
www
.
u
o
m
u
s
tan
s
ir
i
y
ah
.
ed
u
.
iq
)
B
ag
h
d
ad
-
I
r
aq
f
o
r
its
s
u
p
p
o
r
t in
th
e
p
r
es
en
t
w
o
r
k
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
6
,
Dec
em
b
er
2
0
2
1
:
5
2
2
9
-
5
2
3
9
5238
RE
F
E
R
E
NC
E
S
[1
]
A
.
K.
S
e
n
,
S.
B.
P
a
tel,
a
n
d
D
.
S
h
u
k
la,
“
A
Da
t
a
M
in
in
g
T
e
c
h
n
iq
u
e
f
o
r
P
re
d
icti
o
n
o
f
Co
ro
n
a
ry
He
a
rt
Dise
a
se
Us
in
g
Ne
u
ro
-
F
u
z
z
y
In
teg
ra
ted
A
p
p
ro
a
c
h
Tw
o
L
e
v
e
l,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
in
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
(
IJ
ECS
)
,
v
o
l.
2
,
n
o
.
9
,
p
p
.
1
6
6
3
–
1
6
7
1
,
2
0
1
3
.
[2
]
K.
Div
y
a
a
n
d
K.
Na
v
p
re
e
t,
“
Re
v
iew
On
P
re
d
ictio
n
S
y
ste
m
F
o
r
H
e
a
rt
Dia
g
n
o
sis
Us
in
g
Da
ta
M
in
in
g
Tec
h
n
iq
u
e
s,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
L
a
tes
t
R
e
se
a
rc
h
in
E
n
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
IJ
L
RE
T
),
v
o
l
.
1
,
n
o
.
5
,
p
p
.
9
–
1
4
,
2
0
1
5
.
[3
]
J.
A
d
a
m
so
n
,
N.
He
a
th
e
r,
V
.
M
o
rto
n
,
a
n
d
D.
Ra
istri
c
k
,
“
In
it
ial
p
re
fe
re
n
c
e
f
o
r
d
rin
k
in
g
g
o
a
l
i
n
th
e
trea
tme
n
t
o
f
a
lco
h
o
l
p
ro
b
lem
s:
II.
T
re
a
t
m
e
n
t
o
u
tco
m
e
s,”
Al
c
o
h
o
l
a
n
d
A
lco
h
o
li
sm
,
v
o
l.
4
5
,
n
o
.
2
,
p
p
.
1
3
6
–
1
4
2
,
2
0
1
0
,
d
o
i:
1
0
.
1
0
9
3
/alc
a
lc/a
g
q
0
0
5
.
[4
]
S
.
L
a
l,
“
Dia
b
e
tes
:
Ca
u
se
s,
S
y
m
p
to
m
s
A
n
d
T
re
a
t
m
e
n
ts,”
Pu
b
li
c
He
a
lt
h
En
v
iro
n
me
n
t
a
n
d
S
o
c
ia
l
Iss
u
e
s
in
In
d
ia
.
Ed
it
i
o
n
:
1
.
C
h
a
p
ter
:
5
.
In
d
i
a
:
S
e
r
ia
ls P
u
b
li
c
a
ti
o
n
s
,
p
p
.
5
5
–
6
7
,
2
0
1
6
.
[5
]
A
.
M.
S
h
a
h
sa
v
a
ra
n
i
,
E.
A
.
M
.
A
b
a
d
i,
a
n
d
M
.
H.
Ka
l
k
h
o
ra
n
,
“
S
tres
s:
F
a
c
ts
a
n
d
T
h
e
o
ries
th
r
o
u
g
h
L
it
e
ra
tu
re
Re
v
ie
w
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
M
e
d
ica
l
Rev
iews
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
2
3
0
–
2
4
1
,
2
0
1
5
.
[6
]
Blo
o
d
P
re
ss
u
re
,
“
W
h
a
t
Is
Hig
h
Blo
o
d
P
re
ss
u
re
,
”
T
h
e
S
o
u
t
h
Ca
r
o
li
n
a
S
t
a
te
L
i
b
ra
ry
Dig
it
a
l
Co
ll
e
c
ti
o
n
s
,
2
0
1
7
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
d
c
.
sta
telib
ra
ry
.
sc
.
g
o
v
/h
a
n
d
le/1
0
8
2
7
/
2
5
1
3
1
.
[7
]
F
.
Ch
a
rles
,
M
.
Ca
th
e
rin
e
,
F
.
Ju
l
ian
,
W
.
De
W
a
y
n
e
,
a
n
d
B.
A
n
d
re
w
,
“
S
e
x
a
n
d
f
a
m
il
y
h
isto
ry
o
f
c
a
rd
io
v
a
sc
u
lar
d
ise
a
se
in
f
lu
e
n
c
e
h
e
a
rt
ra
te
v
a
ri
a
b
il
it
y
d
u
rin
g
stre
ss
a
m
o
n
g
h
e
a
lt
h
y
a
d
u
lt
s
,
”
J
.
Psy
c
h
o
so
m
Res
.
,
v
o
l.
1
1
0
,
p
p
.
5
4
–
6
0
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/
j.
j
p
sy
c
h
o
re
s.2
0
1
8
.
0
4
.
0
1
1
.
[8
]
M
.
S
u
lt
a
n
a
,
A
.
Ha
id
e
r,
a
n
d
M
.
S
.
Ud
d
i
n
,
“
A
n
a
ly
sis
o
f
d
a
ta
m
in
in
g
tec
h
n
iq
u
e
s
f
o
r
h
e
a
rt
d
ise
a
se
p
re
d
ictio
n
,
”
2
0
1
6
3
rd
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
I
n
fo
r
ma
ti
o
n
C
o
mm
u
n
ic
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(
ICEE
ICT
).
Dh
a
k
a
,
Ba
n
g
lad
e
sh
,
2
0
1
6
,
p
p
.
1
–
5
,
d
o
i:
1
0
.
1
1
0
9
/CE
EICT
.
2
0
1
6
.
7
8
7
3
1
4
2
.
[9
]
B.
J.
S
a
le
h
,
A
.
Y.
F
.
S
a
e
d
i,
A
.
T
.
Q.
A
l
-
A
q
b
i,
a
n
d
L
.
A
.
S
a
lm
a
n
,
“
A
Re
v
ie
w
P
a
p
e
r:
A
n
a
ly
sis
o
f
We
k
a
Da
ta
M
in
in
g
T
e
c
h
n
iq
u
e
s
F
o
r
He
a
rt
Dise
a
se
P
re
d
ictio
n
S
y
ste
m
,
”
L
ib
ra
ry
Ph
il
o
so
p
h
y
a
n
d
Pra
c
ti
c
e
,
p
p
.
1
–
1
7
,
2
0
2
0
,
d
o
i:
1
0
.
3
0
4
9
1
/
ij
m
r.
2
0
2
0
.
2
2
1
4
7
4
.
1
0
7
8
.
[1
0
]
S
.
Ch
a
it
ra
li
a
n
d
S
.
A
p
te,
“
A
Da
ta
M
in
in
g
A
p
p
ro
a
c
h
f
o
r
P
re
d
icti
o
n
o
f
He
a
rt
D
ise
a
s
e
Us
in
g
N
e
u
ra
l
Ne
t
w
o
rk
s,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
(
IJ
CET
)
,
v
o
l.
3
,
n
o
.
3
,
p
p
.
3
0
–
4
0
,
2
0
1
2
.
[1
1
]
S.
C
h
a
re
h
c
h
o
p
o
g
h
a
n
d
Z.
Kh
a
li
f
e
lu
,
“
N
e
u
ra
l
n
e
tw
o
rk
a
p
p
li
c
a
ti
o
n
in
d
iag
n
o
sis
o
f
p
a
ti
e
n
t:
a
c
a
s
e
stu
d
y
,
”
2
0
1
1
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
Ne
two
rk
s a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
A
b
b
o
tt
a
b
a
d
,
2
0
1
1
.
[1
2
]
K.
Ra
m
o
tra,
A
.
M
a
h
a
jan
,
R.
K
u
m
a
r,
a
n
d
V
.
M
a
n
s
o
tra,
“
Co
m
p
a
ra
ti
v
e
A
n
a
l
y
sis
o
f
D
a
ta
M
in
in
g
Clas
si
f
ic
a
ti
o
n
T
e
c
h
n
iq
u
e
s f
o
r
P
re
d
ict
io
n
o
f
He
a
rt
Dise
a
se
Us
in
g
th
e
W
e
k
a
a
n
d
S
P
S
S
M
o
d
e
ler T
o
o
ls,”
S
m
a
rt T
re
n
d
s in
Co
m
p
u
t
in
g
a
n
d
Co
mm
u
n
ica
ti
o
n
s.
S
ma
rt
I
n
n
o
v
a
ti
o
n
,
S
y
ste
ms
a
n
d
T
e
c
h
n
o
lo
g
i
e
s
,
v
o
l.
1
6
5
,
p
p
.
8
9
–
9
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
15
-
0
0
7
7
-
0
_
1
0
.
[1
3
]
R.
Jo
th
ik
u
m
a
r
a
n
d
V
.
S
iv
a
b
a
lan
,
“
A
n
a
l
y
sis
o
f
Clas
si
f
ic
a
ti
o
n
Alg
o
rit
h
m
s
f
o
r
He
a
rt
Dise
a
se
P
re
d
ictio
n
a
n
d
it
s
A
c
c
u
ra
c
ies
,
”
M
id
d
le
-
Ea
st Jo
u
r
n
a
l
o
f
S
c
ien
ti
f
ic R
e
se
a
rc
h
,
p
p
.
2
0
0
–
2
0
6
,
2
0
1
6
.
[1
4
]
He
a
rt
Dise
a
s
e
,
“
G
e
n
e
ra
l
In
f
o
a
n
d
P
e
e
r
re
v
i
e
w
e
d
stu
d
ies
,
”
[
O
n
li
n
e
]
.
Av
a
il
a
b
le:
h
tt
p
:/
/www
.
a
risto
lo
f
t.
c
o
m
.
[1
5
]
N.
A
u
n
g
a
n
d
T
.
H.
Na
in
g
,
“
S
M
O
a
n
d
L
a
z
y
C
las
si
f
iers
f
o
r
H
e
a
r
t
D
ise
a
se
P
re
d
icti
o
n
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
Res
e
a
rc
h
a
n
d
In
n
o
v
a
ti
v
e
Id
e
a
s i
n
E
d
u
c
a
t
io
n
(
IJ
AR
IIE
)
,
v
o
l.
5
,
n
o
.
2
,
p
p
.
2
3
9
5
–
4
3
9
6
,
2
0
1
9
.
[1
6
]
M
.
M
ir
p
o
u
y
a
,
A
.
A
li
n
e
z
h
a
d
,
a
n
d
A.
G
il
a
n
p
o
u
,
“
Da
ta
M
in
i
n
g
Ap
rio
ri
A
lg
o
rit
h
m
f
o
r
He
a
rt
Dise
a
se
P
re
d
icti
o
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
t
in
g
,
C
o
mm
u
n
ica
ti
o
n
a
n
d
In
str
u
me
n
ta
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
o
l.
4
,
n
o
.
1
,
p
p
.
2
0
–
2
3
,
2
0
1
7
,
d
o
i:
1
0
.
1
5
2
4
2
/IJCCIE.
DIR
1
1
1
6
0
1
0
.
[1
7
]
P
u
ru
s
h
o
tt
a
m
a
,
K.
S
a
x
e
n
a
b
,
a
n
d
R.
S
h
a
rm
a
,
“
E
ff
icie
n
t
He
a
rt
D
ise
a
se
P
re
d
ictio
n
S
y
ste
m
,
”
Pro
c
e
d
ia
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
8
5
,
p
p
.
9
6
2
–
9
6
9
,
2
0
1
6
,
d
o
i:
1
0
.
1
0
1
6
/
j.
p
r
o
c
s.2
0
1
6
.
0
5
.
2
8
8
.
[1
8
]
A.
D
w
i
v
e
d
i,
“
P
e
rf
o
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
d
if
f
e
r
e
n
t
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
f
o
r
p
re
d
ictio
n
o
f
h
e
a
rt
d
ise
a
se
,
”
Ne
u
ra
l
Co
m
p
u
t
a
n
d
Ap
p
li
c
,
v
o
l.
2
9
,
n
o
.
1
0
,
p
p
.
6
8
5
–
6
9
3
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
0
7
/s0
0
5
2
1
-
0
1
6
-
2
6
0
4
-
1
.
[1
9
]
K.
S
a
ra
n
g
a
m
a
n
d
R.
Viv
e
k
a
n
a
n
d
a
m
,
“
A
n
a
l
y
sis
o
f
He
a
rt
Dise
a
se
u
sin
g
i
n
Da
ta
M
i
n
in
g
T
o
o
ls
Ora
n
g
e
a
n
d
W
e
k
a
,
”
Do
u
b
le
Bl
in
d
Pee
r R
e
v
iewe
d
In
te
rn
a
ti
o
n
a
l
Res
e
a
rc
h
J
o
u
rn
a
l
,
v
o
l.
1
8
,
n
o
.
1
,
p
p
.
1
6
–
2
2
,
2
0
1
8
.
[2
0
]
J.
P
latt,
“
S
e
q
u
e
n
ti
a
l
M
in
im
a
l
Op
ti
m
iza
ti
o
n
:
A
F
a
st
A
l
g
o
rit
h
m
f
o
r
T
ra
in
in
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
s,”
T
e
c
h
n
ica
l
Rep
o
rt M
S
R
-
TR
,
p
p
.
9
8
–
1
4
,
1
9
9
8
.
[2
1
]
J.
Bro
w
n
lee
,
“
Ho
w
T
o
Us
e
Cla
ss
if
ic
a
ti
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
A
l
g
o
rit
h
m
s
in
W
e
k
a
,
”
M
a
c
h
in
e
lea
rn
in
g
ma
ste
ry
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
m
a
c
h
in
e
lea
rn
in
g
m
a
ste
r
y
.
c
o
m
.
[2
2
]
C.
V
e
n
s,
“
Ra
n
d
o
m
F
o
re
st,”
En
c
y
c
lo
p
e
d
i
a
o
f
S
y
ste
ms
Bi
o
lo
g
y
,
S
p
ri
n
g
e
r
,
2
0
1
3
.
[2
3
]
H.
Na
v
e
e
d
,
G
.
Kh
a
n
,
A
.
U.
Kh
a
n
,
A
.
S
id
d
iq
i
,
a
n
d
M
.
U.
G
.
Kh
a
n
,
“
Hu
m
a
n
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
u
sin
g
m
i
x
tu
re
o
f
h
e
tero
g
e
n
e
o
u
s
f
e
a
tu
re
s
a
n
d
se
q
u
e
n
t
ial
m
in
im
a
l
o
p
ti
m
iza
ti
o
n
,
”
In
t.
J
.
M
a
c
h
.
L
e
a
rn
.
a
n
d
C
y
b
e
r
,
v
o
l.
1
0
,
p
p
.
2
3
2
9
–
2
3
4
0
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s1
3
0
4
2
-
0
1
8
-
0
8
7
0
-
1
.
[2
4
]
L
.
Ng
u
y
e
n
,
“
Ov
e
r
v
ie
w
o
f
B
a
y
e
si
a
n
Ne
tw
o
rk
,
”
S
c
ien
c
e
J
o
u
rn
a
l
o
f
M
a
th
e
ma
ti
c
s
a
n
d
S
ta
ti
st
ics
,
v
o
l.
2
0
1
3
,
p
p
.
1
–
9
9
,
2
0
1
3
.
[2
5
]
M
.
Ku
m
a
r,
K.
Nik
h
il
,
S
.
Ko
u
sh
ik
,
a
n
d
K.
De
e
p
a
k
,
“
P
re
d
ictio
n
o
f
He
a
rt
Dise
a
se
s
Us
in
g
Da
ta
M
in
in
g
a
n
d
M
a
c
h
in
e
L
e
a
rn
in
g
A
l
g
o
rit
h
m
s
a
n
d
T
o
o
ls,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ien
ti
f
ic
Res
e
a
rc
h
in
Co
m
p
u
ter
S
c
ien
c
e
,
En
g
in
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
v
o
l
.
3
,
n
o
.
3
,
p
p
.
8
8
7
–
8
9
8
,
2
0
1
8
.
[2
6
]
T
.
T
.
Ha
sa
n
,
“
De
sig
n
a
n
d
Im
p
l
e
m
e
n
tatio
n
o
f
In
telli
g
e
n
t
A
lg
o
rit
h
m
f
o
r
th
e
Dia
g
n
o
sis
o
f
He
a
rt
Dise
a
se
Us
in
g
F
P
GA
,
”
M
S
c
.
T
h
e
sis,
Un
iv
e
rsit
y
o
f
T
e
c
h
n
o
l
o
g
y
,
Ira
q
,
2
0
1
7
.
[2
7
]
H.
Be
n
jam
in
,
F
.
Da
v
id
,
a
n
d
S
.
Be
lc
y
,
“
He
a
rt
Dise
a
s
e
P
re
d
ictio
n
Us
in
g
Da
ta
M
in
in
g
T
e
c
h
n
iq
u
e
s,”
IC
T
ACT
J
o
u
rn
a
l
On
S
o
ft
C
o
mp
u
ti
n
g
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
1
8
2
4
–
1
8
3
0
,
2
0
1
8
.
[2
8
]
I.
Cv
it
ić
,
D.
P
e
ra
k
o
v
ic,
M
.
P
e
risa
,
a
n
d
B.
G
u
p
ta
,
“
En
se
m
b
le
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
f
o
r
c
las
si
f
ica
ti
o
n
o
f
Io
T
d
e
v
ice
s in
sm
a
rt
h
o
m
e
,
”
In
t.
J
.
M
a
c
h
.
L
e
a
rn
.
a
n
d
Cy
b
e
r
,
2
0
2
1
,
d
o
i:
1
0
.
1
0
0
7
/s1
3
0
4
2
-
0
2
0
-
0
1
2
4
1
-
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.