I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
16
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
1
885
~
1
8
9
8
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
16
i
4
.
pp
1
8
8
5
-
1
8
9
8
1885
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Autom
a
ted
predi
ction o
f
the
mo
de
o
f
birth
delivery
using
g
eo
metric
f
ea
ture
s o
f
ute
rine con
tr
a
ction seg
ments
Ruba
na
H
o
qu
e
Cho
wd
hu
ry
1
,
2
,
Ro
ma
Su
lt
a
na
3
,
Q
ua
zi
Del
wa
r
H
o
s
s
a
in
1
,
M
o
hiu
dd
in A
hm
a
d
4
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
E
n
g
i
n
e
e
r
i
n
g
,
C
h
i
t
t
a
g
o
n
g
U
n
i
v
e
r
si
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
C
h
i
t
t
a
g
o
n
g
,
B
a
n
g
l
a
d
e
s
h
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
E
n
g
i
n
e
e
r
i
n
g
,
N
o
r
t
h
e
r
n
U
n
i
v
e
r
s
i
t
y
B
a
n
g
l
a
d
e
s
h
,
D
h
a
k
a
,
B
a
n
g
l
a
d
e
sh
3
D
e
p
a
r
t
me
n
t
o
f
O
b
s
t
e
t
r
i
c
s
a
n
d
G
y
n
e
c
o
l
o
g
y
,
C
h
i
t
t
a
g
o
n
g
G
e
n
e
r
a
l
H
o
sp
i
t
a
l
,
C
h
i
t
t
a
g
o
n
g
,
B
a
n
g
l
a
d
e
sh
4
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
E
n
g
i
n
e
e
r
i
n
g
,
K
h
u
l
n
a
U
n
i
v
e
r
si
t
y
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
K
h
u
l
n
a
,
B
a
n
g
l
a
d
e
s
h
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
1
,
2
0
2
5
R
ev
is
ed
Ma
y
5
,
2
0
2
6
Acc
ep
ted
J
u
l 2
2
,
2
0
2
6
P
re
g
n
a
n
c
y
is
a
u
n
i
q
u
e
,
c
o
m
p
lex
p
ro
c
e
ss
a
n
d
it
'
s
h
a
rd
t
o
p
re
d
ict
th
e
m
o
d
e
o
f
b
irt
h
d
e
li
v
e
ry
d
u
e
to
th
e
lac
k
re
so
u
rc
e
s.
Th
is
stu
d
y
a
ims
t
o
d
e
v
e
lo
p
a
c
li
n
ica
l
d
e
c
isio
n
s
u
p
p
o
rt
sy
ste
m
to
p
re
d
i
c
t
b
irt
h
d
e
li
v
e
ry
m
o
d
e
a
c
c
o
rd
in
g
t
o
t
h
re
e
c
a
teg
o
ries
:
sp
o
n
ta
n
e
o
u
s
v
a
g
in
a
l
d
e
li
v
e
ry
,
i
n
d
u
c
e
d
v
a
g
i
n
a
l
d
e
li
v
e
ry
,
a
n
d
c
e
sa
re
a
n
se
c
ti
o
n
.
T
h
is
m
e
th
o
d
o
lo
g
y
e
n
tails
th
e
a
u
t
o
m
a
ted
e
x
tr
a
c
ti
o
n
o
f
u
terin
e
c
o
n
trac
ti
o
n
se
g
m
e
n
ts
fr
o
m
th
e
e
lec
tro
h
y
ste
ro
g
ra
m
(
EHG
)
sig
n
a
l
b
a
se
d
o
n
t
h
e
z
e
ro
-
c
ro
ss
in
g
ra
t
e
.
Eac
h
se
g
m
e
n
t
is
p
ro
c
e
ss
e
d
th
ro
u
g
h
a
d
isc
re
te
F
o
u
r
ier
tran
sfo
rm
to
o
b
tain
th
e
F
o
u
r
ier
c
o
e
fficie
n
ts.
G
e
o
m
e
tri
c
fe
a
tu
re
s,
in
c
lu
d
i
n
g
a
re
a
,
p
e
rime
ter,
c
ircu
larit
y
,
v
a
rian
c
e
,
a
n
d
b
e
n
d
i
n
g
e
n
e
rg
y
we
re
e
x
trac
ted
fro
m
t
h
e
b
o
u
n
d
a
r
y
sh
a
p
e
o
f
th
e
se
c
o
m
p
lex
c
o
e
fficie
n
ts
u
si
n
g
th
e
c
o
n
v
e
x
h
u
ll
m
e
th
o
d
.
We
fo
u
n
d
t
h
e
wo
m
e
n
wh
o
e
x
p
e
rien
c
e
sp
o
n
tan
e
o
u
s
d
e
li
v
e
ries
e
x
h
i
b
it
h
ig
h
e
r
fe
a
tu
r
e
v
a
lu
e
s
a
n
d
a
l
o
we
r
c
ircu
larity
v
a
l
u
e
c
o
m
p
a
re
d
t
o
t
h
o
se
w
h
o
u
n
d
e
rg
o
c
e
sa
re
a
n
se
c
ti
o
n
s
o
r
in
d
u
c
e
d
b
irt
h
s.
B
a
se
d
o
n
t
h
e
se
e
x
trac
ted
p
a
ra
m
e
ters
,
th
e
ra
n
d
o
m
fo
re
st
(R
F
)
m
o
d
e
l
y
ield
e
d
p
ro
m
isin
g
re
su
lt
s:
re
a
c
h
in
g
a
n
a
c
c
u
ra
c
y
a
b
o
v
e
9
0
%
i
n
th
e
c
la
ss
ifi
c
a
ti
o
n
b
e
twe
e
n
c
a
e
sa
r
e
a
n
a
n
d
sp
o
n
tan
e
o
u
s
d
e
li
v
e
ries
a
n
d
sp
o
n
ta
n
e
o
u
s
a
n
d
in
d
u
c
e
d
v
a
g
in
a
l
d
e
li
v
e
ries
a
n
d
so
m
e
wh
a
t
lo
we
r,
a
ro
u
n
d
7
0
%
b
e
twe
e
n
i
n
d
u
c
e
d
a
n
d
c
e
sa
re
a
n
.
To
c
o
n
c
lu
d
e
,
t
h
e
u
t
il
iza
ti
o
n
o
f
a
ll
p
ro
p
o
se
d
EHG
p
a
ra
m
e
ters
th
ro
u
g
h
m
a
c
h
in
e
lea
rn
in
g
c
a
n
e
n
h
a
n
c
e
o
b
ste
tri
c
ian
s'
a
b
il
it
y
t
o
p
re
d
ict
th
e
m
o
d
e
o
f
b
irt
h
d
e
li
v
e
ry
.
K
ey
w
o
r
d
s
:
C
esar
ea
n
d
eliv
er
y
E
lectr
o
h
y
s
ter
o
g
r
ap
h
y
Sp
o
n
tan
eo
u
s
d
eliv
er
y
T
o
p
o
lo
g
ical
f
ea
tu
r
es
Uter
in
e
co
n
tr
ac
tio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
u
b
an
a
Ho
q
u
e
C
h
o
wd
h
u
r
y
Dep
ar
tm
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ic
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
E
n
g
in
ee
r
i
n
g
,
C
h
ittag
o
n
g
Un
iv
er
s
ity
o
f
E
n
g
in
ee
r
in
g
an
d
T
ec
h
n
o
lo
g
y
C
h
ittag
o
n
g
-
4
3
4
9
,
B
an
g
lad
es
h
E
m
ail:
r
u
b
an
ac
h
y
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
h
ig
h
g
l
o
b
al
p
r
e
g
n
an
c
y
-
r
e
lated
m
o
r
tality
r
atio
o
f
2
1
6
p
e
r
1
0
0
,
0
0
0
liv
e
b
i
r
th
s
,
as
r
ep
o
r
ted
b
y
th
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
,
is
p
r
im
ar
ily
attr
ib
u
tab
le
to
p
o
s
tp
ar
tu
m
h
em
o
r
r
h
a
g
e,
in
f
ec
tio
n
s
,
an
d
p
r
e
-
ec
lam
p
s
ia.
Po
s
tp
ar
tu
m
h
e
m
o
r
r
h
a
g
e,
a
m
ajo
r
co
n
tr
ib
u
to
r
to
m
ater
n
al
m
o
r
tality
,
is
p
r
ed
o
m
in
an
tly
ca
u
s
ed
b
y
ex
ce
s
s
iv
e
b
lo
o
d
lo
s
s
an
d
u
ter
in
e
ato
n
y
[
1
]
.
Alth
o
u
g
h
ce
s
ar
ea
n
s
ec
tio
n
s
ca
n
b
e
life
-
s
av
i
n
g
in
th
e
tr
ea
tm
e
n
t
o
f
s
ev
er
e
p
r
e
-
ec
lam
p
s
ia,
th
ey
also
elev
ate
th
e
r
is
k
s
o
f
p
o
s
tp
ar
tu
m
b
leed
i
n
g
,
i
n
f
ec
tio
n
s
,
a
n
d
m
ed
ical
ex
p
en
s
es
wh
en
co
n
d
u
cted
with
o
u
t
n
ec
e
s
s
ity
.
C
o
n
s
eq
u
en
tly
,
it
is
e
s
s
e
n
tial
to
f
u
r
n
is
h
in
f
o
r
m
atio
n
th
at
aid
s
in
d
is
ce
r
n
in
g
th
e
s
u
b
jectiv
e
v
iewp
o
in
ts
o
f
m
ed
ical
p
r
ac
titi
o
n
e
r
s
wh
en
u
tili
ze
d
as
a
d
ec
is
io
n
-
s
u
p
p
o
r
t
to
o
l.
Fu
r
th
e
r
m
o
r
e
,
ass
is
tin
g
p
h
y
s
ician
s
in
d
ec
is
i
o
n
-
m
ak
i
n
g
aid
s
h
ea
lth
ca
r
e
p
r
o
v
id
er
s
in
a
v
er
tin
g
m
alp
r
ac
ti
ce
an
d
n
eg
lect,
s
o
im
p
r
o
v
in
g
t
h
e
q
u
ality
o
f
m
ater
n
ity
ca
r
e
an
d
p
r
o
v
id
i
n
g
e
n
h
an
ce
d
s
u
p
p
o
r
t
f
o
r
p
r
eg
n
an
t
in
d
iv
i
d
u
als.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
8
8
5
-
1
898
1886
An
ticip
atin
g
th
e
m
o
d
e
o
f
d
eliv
er
y
en
ab
les
h
ea
lth
ca
r
e
p
r
o
v
id
er
s
to
m
ak
e
in
f
o
r
m
ed
clin
ical
d
ec
is
io
n
s
th
r
o
u
g
h
o
u
t
p
r
eg
n
a
n
cy
an
d
lab
o
r
[
2
]
.
I
n
r
ec
e
n
t
y
ea
r
s
,
r
esear
ch
er
s
h
av
e
d
ir
ec
ted
th
ei
r
atten
tio
n
to
an
aly
zin
g
elec
tr
o
h
y
s
ter
o
g
r
ap
h
y
(
E
HG)
s
ig
n
als,
wh
ich
ar
e
b
io
-
p
o
te
n
tial
r
ec
o
r
d
in
g
s
o
f
u
ter
in
e
s
m
o
o
th
m
u
s
cle
ac
tiv
ity
ch
ar
ac
ter
ized
b
y
lo
w
f
r
eq
u
e
n
cy
[
3
]
.
I
n
tr
a
u
ter
in
e
p
r
ess
u
r
e
ca
th
eter
(
I
UPC
)
,
ca
r
d
io
to
c
o
g
r
am
(
T
OC
O)
,
an
d
E
HG
ar
e
th
e
th
r
ee
d
if
f
er
e
n
t
u
t
er
in
e
m
o
n
ito
r
in
g
tech
n
iq
u
es,
c
o
m
p
ar
is
o
n
am
o
n
g
th
e
m
is
v
er
y
d
if
f
icu
lt
b
ec
au
s
e
o
f
th
eir
d
if
f
er
en
t
ap
p
r
o
ac
h
an
d
n
atu
r
e.
Few
s
tu
d
ies
h
av
e
w
o
r
k
ed
o
n
th
eir
co
m
p
ar
is
o
n
an
d
h
a
v
e
s
h
o
w
n
th
at
E
HG
is
s
u
b
s
tan
tially
m
o
r
e
s
en
s
itiv
e
th
an
T
OC
O
in
d
etec
tin
g
u
ter
in
e
co
n
t
r
ac
tio
n
s
(
UC
)
d
u
r
in
g
ter
m
la
b
o
r
[
4
]
–
[
7
]
.
T
h
e
I
UPC
is
ac
k
n
o
wled
g
ed
f
o
r
its
p
r
ec
is
io
n
in
p
r
o
v
id
i
n
g
i
n
f
o
r
m
atio
n
.
Ho
we
v
er
,
r
esear
ch
er
s
ar
e
r
ed
ir
ec
tin
g
t
h
eir
atten
tio
n
d
u
e
to
its
in
v
asiv
e
n
atu
r
e.
T
h
e
E
HG
s
ig
n
als
o
f
f
er
v
alu
ab
le
in
s
ig
h
ts
in
to
u
ter
i
n
e
co
n
tr
ac
tio
n
s
,
a
n
d
th
ei
r
d
is
tin
ctiv
e
f
ea
tu
r
es
h
o
ld
p
r
o
m
is
e
a
s
an
ef
f
ec
tiv
e
to
o
l
f
o
r
an
aly
z
in
g
an
d
p
r
ed
ictin
g
p
r
eter
m
b
ir
t
h
[
8
]
.
Var
io
u
s
E
H
G
s
ig
n
al
f
ea
tu
r
es,
in
clu
d
in
g
li
n
ea
r
,
n
o
n
lin
ea
r
f
ea
tu
r
es,
h
a
v
e
b
ee
n
d
e
v
elo
p
ed
to
d
if
f
er
en
tiate
b
etwe
en
ter
m
an
d
p
r
eter
m
lab
o
r
.
T
h
e
r
esear
ch
co
n
d
u
cted
b
y
J
ag
er
et
a
l.
[
9
]
h
as
b
ee
n
n
o
tab
ly
im
p
ac
tf
u
l,
f
o
cu
s
in
g
o
n
th
e
q
u
an
titativ
e
an
aly
s
is
o
f
co
n
tr
ac
tio
n
an
d
d
u
m
m
y
in
ter
v
al
s
o
f
E
HG
s
ig
n
als,
en
co
m
p
ass
in
g
c
o
n
d
u
ctio
n
v
e
lo
city
,
p
r
o
p
a
g
atio
n
d
ir
ec
tio
n
,
an
d
s
o
p
h
is
ticated
f
ea
tu
r
e
-
b
ased
class
if
icatio
n
m
eth
o
d
o
l
o
g
ies.
Gar
f
ield
em
p
l
o
y
ed
v
ec
t
o
r
-
b
ased
a
n
aly
s
is
to
d
elin
ea
te
th
e
s
p
atial
p
r
o
p
a
g
at
io
n
o
f
UC
ac
tiv
ity
.
T
h
eir
f
in
d
in
g
s
u
n
d
er
s
co
r
ed
t
h
e
p
o
te
n
tial
o
f
u
ter
in
e
c
o
n
tr
ac
tili
ty
as
an
in
d
icato
r
o
f
lab
o
r
p
r
o
g
r
ess
io
n
a
n
d
d
eliv
er
y
tim
in
g
[
1
0
]
.
Nev
e
r
th
eless
,
th
ese
m
eth
o
d
o
lo
g
ies
f
r
eq
u
en
tly
n
e
g
lect
th
e
s
h
ap
e
an
d
g
eo
m
etr
y
o
f
th
e
f
o
u
n
d
atio
n
al
d
ata,
attr
i
b
u
tes th
at
m
ay
b
e
ess
en
tial in
d
is
ce
r
n
i
n
g
m
ajo
r
ch
ar
ac
ter
is
tics
o
f
th
e
s
ig
n
als
[
1
1
]
.
Ov
e
r
t
h
e
last
tw
o
d
ec
ad
es,
c
o
n
s
id
e
r
ab
le
r
ese
a
r
c
h
h
as
b
e
en
d
e
d
ic
at
ed
to
em
p
l
o
y
i
n
g
p
att
er
n
r
ec
o
g
n
i
ti
o
n
tec
h
n
i
q
u
es
t
o
e
x
t
r
a
ct
f
ea
tu
r
es
f
r
o
m
E
H
G
s
i
g
n
als
.
M
u
c
h
o
f
t
h
is
r
ese
a
r
c
h
h
as
b
ee
n
ce
n
te
r
ed
o
n
p
r
e
d
i
cti
n
g
te
r
m
an
d
p
r
ete
r
m
b
i
r
t
h
s
,
p
ar
tic
u
l
ar
l
y
f
o
c
u
s
i
n
g
o
n
d
is
t
in
g
u
is
h
i
n
g
b
etwe
e
n
E
HG
r
e
co
r
d
s
ass
o
c
iat
e
d
wit
h
p
r
e
g
n
an
ci
es
cu
l
m
i
n
a
ti
n
g
i
n
p
r
e
te
r
m
s
p
o
n
t
an
eo
u
s
d
eli
v
e
r
y
v
er
s
u
s
te
r
m
s
p
o
n
t
a
n
e
o
u
s
d
e
li
v
e
r
y
.
An
o
t
h
e
r
eq
u
all
y
im
p
o
r
ta
n
t
f
a
ct
o
r
f
o
r
cl
in
ic
al
c
a
r
e
t
h
at
h
a
s
n
o
t
b
e
e
n
c
o
n
s
i
d
e
r
e
d
i
n
th
ese
s
tu
d
i
es
is
d
eli
v
e
r
y
m
o
d
e
,
w
h
i
ch
is
a
n
im
p
o
r
ta
n
t
co
n
s
i
d
e
r
a
ti
o
n
f
o
r
o
b
s
t
et
r
ic
p
l
a
n
n
i
n
g
an
d
d
e
li
v
e
r
y
ca
r
e
.
W
h
il
e
th
e
y
p
r
o
v
id
e
u
s
e
f
u
l
i
n
f
o
r
m
at
io
n
r
e
g
a
r
d
in
g
w
h
en
d
el
iv
e
r
y
s
h
o
u
l
d
ta
k
e
p
l
ac
e,
i
n
o
r
d
er
to
im
p
r
o
v
e
d
eli
v
e
r
y
p
la
n
n
i
n
g
an
d
s
av
e
m
o
n
e
y
o
n
h
ea
l
th
c
a
r
e
a
n
d
a
ch
ie
v
e
g
o
o
d
o
u
t
co
m
es
f
o
r
b
o
t
h
m
o
t
h
er
s
a
n
d
b
a
b
i
es,
it
is
i
m
p
o
r
ta
n
t
to
p
r
e
d
i
ct
i
f
t
h
e
d
e
li
v
e
r
y
w
ill
b
e
v
a
g
i
n
al
,
i
n
d
u
c
e
d
,
o
r
a
ce
s
ar
ea
n
s
ec
t
io
n
.
M
a
k
i
n
g
wr
o
n
g
p
r
ed
ict
io
n
s
m
a
y
e
n
d
u
p
i
n
c
r
ea
s
i
n
g
r
is
k
s
f
o
r
m
o
t
h
e
r
an
d
ch
il
d
.
Pr
ev
io
u
s
wo
r
k
s
d
ea
li
n
g
wi
th
th
is
is
s
u
e
h
a
v
e
u
t
ili
ze
d
t
h
e
co
m
b
i
n
at
io
n
o
f
E
HG
an
d
o
b
s
tet
r
i
c
v
a
r
ia
b
les
.
F
o
r
in
s
ta
n
c
e,
Alb
er
o
l
a
-
R
u
b
i
o
et
a
l.
[
1
2
]
d
em
o
n
s
tr
at
ed
t
h
a
t
to
e
f
f
e
cti
v
e
ly
d
is
ti
n
g
u
is
h
b
e
twe
en
p
a
tie
n
ts
w
h
o
w
ill
h
a
v
e
s
p
o
n
t
a
n
e
o
u
s
la
b
o
r
b
e
f
o
r
e
t
h
e
e
n
d
o
f
t
h
e
e
n
t
ir
e
te
r
m
a
n
d
t
h
o
s
e
w
h
o
will
n
ee
d
la
te
-
te
r
m
la
b
o
r
i
n
d
u
cti
o
n
,
a
s
i
n
g
le
E
HG
in
p
u
t
p
a
r
a
m
et
er
is
i
n
s
u
f
f
icie
n
t
.
T
h
e
y
d
em
o
n
s
t
r
at
ed
t
h
a
t
i
n
c
o
r
p
o
r
ati
n
g
E
HG
p
a
r
a
m
et
e
r
s
a
n
d
o
b
s
tet
r
i
c
d
a
ta
p
o
i
n
ts
(
s
u
c
h
as
m
ate
r
n
a
l
ag
e,
b
o
d
y
m
ass
i
n
d
e
x
(
B
M
I
)
,
g
es
tati
o
n
al
a
g
e,
p
a
r
it
y
,
h
is
to
r
y
o
f
a
b
o
r
ti
o
n
s
,
B
is
h
o
p
s
co
r
e
,
a
n
d
f
e
tal
w
ei
g
h
t
)
s
ig
n
if
i
ca
n
tl
y
e
n
h
a
n
c
es
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
h
e
c
lass
i
f
i
er
s
.
T
h
i
s
i
m
p
r
o
v
e
m
e
n
t
is
r
e
f
le
ct
ed
i
n
t
h
e
c
lass
i
f
i
er
s
'
A
U
C
v
a
lu
es,
w
h
i
ch
r
a
n
g
e
f
r
o
m
0
.
5
8
t
o
0
.
7
6
.
B
e
n
alc
áz
ar
‐
Pa
r
r
a
e
t
a
l.
[
1
3
]
u
n
d
er
to
o
k
a
s
t
u
d
y
ai
m
e
d
at
d
ev
el
o
p
in
g
p
r
e
d
i
cti
v
e
s
y
s
te
m
s
c
ap
a
b
le
o
f
c
lass
i
f
y
in
g
th
r
ee
d
is
ti
n
ct
s
ce
n
ar
io
s
b
as
e
d
o
n
E
HG
d
at
a.
Di
az
-
M
ar
ti
n
ez
et
a
l.
[
1
4
]
c
o
n
d
u
cte
d
a
co
m
p
a
r
is
o
n
o
f
t
h
e
p
o
s
t
p
ar
t
u
m
E
HG
c
h
a
r
ac
t
er
is
tics
b
etw
ee
n
v
a
g
i
n
a
l
a
n
d
ce
s
ar
ea
n
d
e
li
v
e
r
i
es.
T
h
e
y
o
b
s
e
r
v
e
d
t
h
a
t
t
h
e
r
e
we
r
e
n
o
s
tat
is
tic
all
y
s
i
g
n
if
i
ca
n
t
d
i
f
f
e
r
e
n
c
es
i
n
o
b
s
tet
r
i
c
d
ata
an
d
v
it
al
s
i
g
n
v
ar
i
ati
o
n
s
b
etw
ee
n
t
h
e
v
a
g
i
n
a
l
a
n
d
ce
s
a
r
ea
n
d
el
iv
er
y
g
r
o
u
p
s
.
Ac
co
r
d
i
n
g
to
t
h
e
s
tu
d
y
,
E
HG
o
b
tai
n
e
d
a
c
o
n
s
id
er
ab
ly
h
i
g
h
e
r
a
m
p
lit
u
d
e
a
n
d
l
o
wer
k
u
r
to
s
is
o
f
t
h
e
H
il
b
e
r
t
e
n
v
elo
p
e
in
th
e
v
a
g
i
n
al
b
i
r
t
h
g
r
o
u
p
co
m
p
a
r
e
d
t
o
t
h
e
c
esa
r
ea
n
g
r
o
u
p
,
an
d
t
h
e
s
p
ec
t
r
a
l
c
o
n
te
n
t
w
as
p
u
s
h
ed
t
o
w
ar
d
s
h
i
g
h
e
r
f
r
e
q
u
e
n
ci
es
[
1
4
]
.
T
h
e
d
r
aw
b
a
ck
o
f
s
u
c
h
t
e
ch
n
i
q
u
es
is
th
at
th
e
y
r
e
d
u
c
e
t
h
e
o
p
p
o
r
t
u
n
it
y
o
f
a
n
al
y
zi
n
g
t
h
e
p
r
e
d
ic
ti
v
e
p
o
w
er
o
f
ele
ctr
ic
al
a
cti
v
it
y
o
f
u
t
er
u
s
i
n
d
e
p
e
n
d
e
n
t
ly
.
M
o
r
e
o
v
e
r
,
t
h
e
y
ex
t
r
ac
t
ed
co
n
t
r
ac
t
io
n
b
u
r
s
ts
m
an
u
a
ll
y
.
T
h
is
s
t
u
d
y
f
o
c
u
s
es
o
n
th
e
a
u
t
o
m
at
ic
c
o
n
t
r
a
cti
o
n
-
l
e
v
el
an
al
y
s
is
o
f
th
e
E
HG
s
ig
n
a
l,
em
p
h
asi
zi
n
g
its
g
eo
m
e
tr
ic
a
n
d
to
p
o
l
o
g
ica
l
ch
a
r
ac
te
r
is
t
ics
.
U
n
lik
e
p
r
i
o
r
s
t
u
d
i
es
t
h
at
f
o
c
u
s
ed
o
n
ei
th
e
r
g
l
o
b
al
s
i
g
n
a
l
ch
ar
a
cte
r
is
t
ics
o
r
cl
in
ic
al
cr
i
te
r
ia
,
t
h
e
p
r
o
p
o
s
e
d
m
et
h
o
d
o
lo
g
y
ef
f
ec
t
iv
el
y
ca
p
t
u
r
es
d
is
t
i
n
ct
co
n
t
r
ac
t
io
n
d
y
n
am
i
cs,
p
o
t
en
t
ial
ly
p
r
o
v
i
d
i
n
g
a
s
u
p
e
r
i
o
r
r
e
p
r
ese
n
t
ati
o
n
o
f
t
h
e
p
h
y
s
i
o
l
o
g
ic
al
d
if
f
e
r
e
n
ce
s
a
m
o
n
g
n
at
u
r
al
,
s
ti
m
u
lat
ed
,
a
n
d
ce
s
a
r
e
a
n
d
e
li
v
e
r
ies
.
T
h
is
r
esea
r
c
h
s
i
g
n
i
f
i
es
p
r
o
g
r
ess
io
n
i
n
t
h
e
e
x
a
m
i
n
at
io
n
o
f
t
h
e
E
HG
s
ig
n
a
l
b
y
f
o
c
u
s
i
n
g
o
n
f
o
r
ec
asti
n
g
t
h
e
m
a
n
n
e
r
o
f
d
e
li
v
e
r
y
r
at
h
er
t
h
a
n
atte
m
p
ti
n
g
to
f
o
r
e
ca
s
t t
h
e
co
m
m
e
n
c
em
en
t
o
f
d
e
li
v
e
r
y
.
2.
M
E
T
H
O
D
T
h
is
p
ap
er
in
v
esti
g
ates
th
e
v
i
ab
ilit
y
o
f
u
s
in
g
th
e
g
eo
m
etr
ic
p
r
o
p
er
ties
o
f
co
n
tr
ac
tio
n
b
u
r
s
ts
to
cr
ea
te
a
co
m
p
u
ter
ized
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
.
A
d
d
itio
n
ally
,
it
in
teg
r
ates
co
n
tr
ac
tio
n
attr
ib
u
tes
to
im
p
r
o
v
e
th
e
s
y
s
tem
'
s
p
r
ed
ictiv
e
p
o
wer
.
T
h
e
s
u
g
g
ested
m
eth
o
d
s
ee
k
s
to
f
o
r
ec
ast
th
e
m
o
d
e
o
f
d
eliv
e
r
y
in
th
r
ee
d
if
f
er
en
t
ca
teg
o
r
ies:
in
d
u
ce
d
v
ag
in
al
d
e
liv
er
y
,
s
p
o
n
ta
n
eo
u
s
v
a
g
in
al
d
e
liv
er
y
,
an
d
ce
s
ar
ea
n
s
ec
tio
n
.
2
.
1
.
Da
t
a
des
cr
iptio
n
T
h
is
s
tu
d
y
u
tili
ze
d
an
E
HG
d
ataset
th
at
in
clu
d
ed
in
d
u
ce
d
,
ce
s
ar
ea
n
,
an
d
in
d
u
ce
d
ce
s
a
r
ea
n
E
HG
r
ec
o
r
d
s
(
I
C
E
HG
DS)
af
ter
3
7
wee
k
s
o
f
g
estatio
n
,
o
r
wh
e
n
th
e
p
r
eg
n
a
n
cy
en
d
ed
with
d
eliv
e
r
y
[
1
5
]
.
Mo
r
e
o
v
er
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
u
to
ma
ted
p
r
ed
ictio
n
o
f th
e
mo
d
e
o
f b
ir
th
d
elive
r
y
u
s
in
g
…
(
R
u
b
a
n
a
Ho
q
u
e
C
h
o
w
d
h
u
r
y
)
1887
o
u
r
s
tu
d
y
also
u
s
ed
a
ter
m
-
p
r
eter
m
s
p
o
n
tan
eo
u
s
E
HG
d
ata
s
et
(
T
PEHG
T
DS
an
d
T
PE
HG
DB
)
[
1
6
]
.
T
h
e
T
PEHG
DB
d
ataset
(
with
o
u
t
T
OC
O)
h
as
3
0
0
r
ec
o
r
d
s
,
with
2
6
2
ter
m
r
ec
o
r
d
s
an
d
3
8
p
r
e
-
ter
m
r
ec
o
r
d
s
.
T
h
e
T
PEHG
T
DS
d
ataset
(
with
T
OC
O)
h
as
2
6
th
r
ee
-
s
ig
n
al
3
0
-
m
in
u
ter
in
e
E
HG
r
ec
o
r
d
s
,
with
1
3
p
r
eter
m
r
ec
o
r
d
s
f
r
o
m
eig
h
t
a
n
d
1
3
ter
m
r
ec
o
r
d
s
f
r
o
m
ten
p
r
eg
n
a
n
t
wo
m
en
.
T
h
e
s
p
o
n
ta
n
eo
u
s
te
r
m
g
r
o
u
p
E
HG
r
ec
o
r
d
e
d
ea
r
l
y
(
af
ter
3
1
wee
k
s
d
u
r
in
g
p
r
eg
n
a
n
cy
)
h
as
b
ee
n
u
tili
ze
d
i
n
th
is
s
tu
d
y
.
T
ab
le
1
p
r
o
v
id
es
a
co
n
cise
o
v
er
v
iew
o
f
t
h
e
clin
ical
d
ata
ass
o
ciate
d
w
ith
a
ll
E
HG
d
atab
ase
r
ec
o
r
d
s
.
T
h
e
in
teg
r
atio
n
o
f
th
ese
d
atasets
i
s
ju
s
tifie
d
b
y
th
eir
co
m
p
ar
ab
le
ac
q
u
is
itio
n
p
r
o
t
o
c
o
ls
.
Sp
ec
if
ically
,
all
d
atasets
e
m
p
lo
y
ed
a
4
-
elec
tr
o
d
e
(
e1
–
e
4
)
p
lace
m
en
t
o
n
t
h
e
ab
d
o
m
in
al
s
u
r
f
ac
e
to
r
ec
o
r
d
E
HG
s
ig
n
al
f
o
r
a
p
p
r
o
x
im
atel
y
3
0
m
in
u
tes
as
s
h
o
wn
in
Fig
u
r
e
1
.
T
h
e
s
ig
n
als
wer
e
s
am
p
led
at
2
0
Hz
an
d
s
u
b
jecte
d
to
b
a
n
d
p
ass
f
ilter
in
g
with
in
th
e
r
a
n
g
e
o
f
0
.
0
8
t
o
5
.
0
Hz
with
a
4
-
p
o
le
d
ig
ital
B
u
tter
wo
r
th
f
ilter
.
A
b
id
ir
ec
tio
n
al
f
ilter
in
g
a
p
p
r
o
ac
h
was
ap
p
lied
to
elim
in
ate
p
h
ase
d
is
to
r
tio
n
,
en
s
u
r
in
g
s
ig
n
al
in
te
g
r
ity
.
D
esp
ite
th
ese
s
im
ilar
itie
s
,
p
o
ten
tial
v
ar
iab
ilit
y
d
u
e
t
o
d
if
f
er
en
ce
s
in
p
atien
t
p
o
p
u
latio
n
s
,
r
ec
o
r
d
i
n
g
en
v
ir
o
n
m
en
ts
,
an
d
eq
u
ip
m
en
t
ca
li
b
r
atio
n
ca
n
n
o
t
b
e
e
n
tire
ly
e
x
clu
d
ed
.
T
h
is
m
ay
in
tr
o
d
u
ce
h
i
d
d
en
b
iases
in
th
e
co
m
b
in
ed
d
ataset,
wh
ich
is
ac
k
n
o
wled
g
e
d
as a
lim
itatio
n
o
f
th
e
s
tu
d
y
.
A
r
ec
en
t
s
tu
d
y
f
o
u
n
d
th
at
th
e
E
HG
f
r
o
m
ch
an
n
el
3
was
th
e
m
o
s
t
d
is
tin
ct
s
ig
n
al
f
o
r
d
is
tin
g
u
is
h
in
g
p
r
eter
m
an
d
ter
m
d
eliv
er
ies
[
1
7
]
.
I
n
lig
h
t
o
f
t
h
eir
f
in
d
in
g
s
,
ch
an
n
el
3
was
s
p
ec
if
ically
s
elec
ted
in
o
u
r
s
tu
d
y
to
ass
ess
th
e
ef
f
ec
tiv
en
ess
o
f
o
u
r
tech
n
iq
u
e
in
id
en
tify
in
g
u
ter
in
e
co
n
tr
ac
ti
o
n
s
eg
m
en
ts
.
T
ab
le
1
.
T
h
e
p
atien
t'
s
d
em
o
g
r
ap
h
ic
in
f
o
r
m
atio
n
is
av
ailab
le
in
th
e
T
PEHG
an
d
I
C
E
HG
Da
tab
ases
[
1
5
]
,
[
1
6
]
EH
G
si
g
n
a
l
D
e
scri
p
t
i
o
n
M
a
t
e
r
n
a
l
a
g
e
(
y
e
a
r
s)
(
a
v
g
±
st
d
)
G
e
st
a
t
i
o
n
a
l
a
g
e
(
w
e
e
k
s)
(
a
v
g
±
st
d
)
S
p
o
n
t
a
n
e
o
u
s
v
a
g
i
n
a
l
d
e
l
i
v
e
r
y
(
1
1
3
r
e
c
o
r
d
s)
La
b
o
r
c
o
mm
e
n
c
e
s
sp
o
n
t
a
n
e
o
u
s
l
y
,
a
n
d
t
h
e
b
a
b
y
i
s
d
e
l
i
v
e
r
e
d
t
h
r
o
u
g
h
t
h
e
m
o
t
h
e
r
's
p
u
sh
i
n
g
e
f
f
o
r
t
s a
n
d
t
h
e
n
a
t
u
r
a
l
c
o
n
t
r
a
c
t
i
o
n
s
o
f
t
h
e
b
a
b
y
w
i
t
h
o
u
t
r
e
q
u
i
r
i
n
g
me
d
i
c
a
l
i
n
t
e
r
v
e
n
t
i
o
n
.
2
8
.
3
9
±
4
.
2
5
3
6
.
2
8
±
1
.
3
0
C
e
sar
e
a
n
sec
t
i
o
n
d
e
l
i
v
e
r
y
(
8
r
e
c
o
r
d
s)
I
t
i
s a
s
u
r
g
i
c
a
l
t
e
c
h
n
i
q
u
e
w
h
e
r
e
i
n
t
h
e
mo
t
h
e
r
's
u
t
e
r
u
s a
n
d
a
b
d
o
mi
n
a
l
w
a
l
l
a
r
e
c
u
t
t
o
d
e
l
i
v
e
r
t
h
e
b
a
b
y
.
3
1
.
8
9
±
2
.
5
5
3
7
.
5
0
3
±
2
.
0
3
6
I
n
d
u
c
e
d
v
a
g
i
n
a
l
d
e
l
i
v
e
r
y
(
3
7
)
:
T
h
i
s
m
e
t
h
o
d
e
m
p
l
o
y
s
e
x
t
e
r
n
a
l
f
o
r
c
e
t
o
i
n
d
u
c
e
u
t
e
r
i
n
e
c
o
n
t
r
a
c
t
i
o
n
s
i
n
c
a
s
e
s
w
h
e
r
e
s
p
o
n
t
a
n
e
o
u
s
l
a
b
o
r
d
o
e
s
n
o
t
c
o
m
m
e
n
c
e
.
3
0
.
0
9
±
4
.
3
6
4
0
.
0
9
±
1
.
3
9
Fig
u
r
e
1
.
Fo
u
r
elec
tr
o
d
e
p
lace
m
en
ts
o
n
th
e
lo
we
r
ab
d
o
m
en
s
p
ac
ed
s
ev
en
cm
ap
ar
t
2
.
2
.
P
re
-
pro
ce
s
s
ing
T
h
e
d
atab
ases
o
b
tain
ed
f
r
o
m
th
e
Ph
y
s
io
Net
web
s
ite
ar
e
f
o
r
m
atted
as
W
FDB
(
wav
ef
o
r
m
d
atab
ase
)
s
ig
n
al
f
iles
.
T
h
e
E
HG
co
m
p
r
is
es
t
wo
s
ig
n
als:
a
s
lo
w
wav
e
an
d
a
q
u
ick
wav
e.
T
h
e
s
lo
w
wav
e
o
s
cillates
b
etwe
en
0
.
0
0
5
an
d
0
.
0
3
Hz,
ex
h
ib
itin
g
an
am
p
litu
d
e
o
f
0
.
5
to
1
5
m
V.
T
h
e
r
ap
id
wav
e
o
s
cillates
b
etwe
en
0
.
1
an
d
3
Hz,
with
an
am
p
litu
d
e
r
an
g
in
g
f
r
o
m
0
.
0
2
to
0
.
5
m
V,
r
esp
ec
tiv
ely
[
1
8
]
.
T
h
e
f
ast
wav
e
s
u
p
er
im
p
o
s
es
th
e
s
lo
w
wav
e
to
f
o
r
m
an
E
HG
s
ig
n
al.
Mo
s
t
o
f
t
h
e
r
esea
r
ch
er
s
f
o
c
u
s
ed
o
n
th
e
h
ig
h
w
av
e
b
an
d
d
u
r
in
g
th
e
f
ilter
in
g
p
r
o
ce
s
s
d
u
e
to
p
r
o
p
er
co
n
tr
ac
tio
n
ch
ar
ac
ter
iz
atio
n
,
b
ec
au
s
e
m
o
s
t
o
f
th
e
u
ter
in
e
ac
tiv
ity
is
co
n
ce
n
tr
ated
in
th
is
b
an
d
wid
th
(
B
W
)
[
5
]
,
[
1
6
]
.
Prio
r
to
e
x
am
in
in
g
th
e
f
ea
t
u
r
e
e
x
tr
ac
tio
n
tech
n
iq
u
e,
two
p
r
elim
in
ar
y
s
tag
es
ar
e
co
n
d
u
c
ted
in
th
is
s
tu
d
y
:
i
)
T
h
e
r
aw
E
HG
r
ec
o
r
d
in
g
s
u
n
d
e
r
wen
t
b
an
d
p
ass
f
ilter
in
g
with
a
f
o
u
r
th
-
o
r
d
er
B
u
tter
wo
r
th
d
i
g
ital
f
ilter
,
with
a
f
r
eq
u
e
n
cy
r
an
g
e
o
f
0
.
0
3
4
–
3
Hz,
to
r
e
d
u
ce
h
ig
h
-
f
r
eq
u
e
n
cy
n
o
is
e,
m
o
tio
n
ar
tifa
cts,
m
ater
n
al
r
esp
ir
atio
n
,
an
d
b
aselin
e
i
n
ter
f
er
en
ce
.
ii
)
T
h
e
b
u
r
s
ts
o
f
all
E
HG
r
ec
o
r
d
in
g
s
ass
o
ciate
d
with
co
n
tr
ac
tio
n
s
wer
e
au
to
m
atica
lly
s
eg
m
en
ted
u
tili
zin
g
th
e
Z
er
o
-
cr
o
s
s
in
g
r
at
e,
s
u
cc
ee
d
ed
b
y
t
h
e
am
p
litu
d
e
m
o
d
u
latio
n
ap
p
r
o
a
ch
.
Sin
ce
th
e
I
C
E
HG
d
ataset
d
o
es
n
o
t
i
n
clu
d
e
T
OC
O
r
ec
o
r
d
in
g
s
o
r
m
a
n
u
al
an
n
o
tatio
n
s
f
o
r
c
o
n
tr
ac
tio
n
ev
en
ts
,
d
ir
ec
t
v
alid
atio
n
o
f
d
etec
ted
co
n
tr
ac
ti
o
n
s
with
in
th
is
d
ataset
is
n
o
t
f
ea
s
ib
le.
T
o
ad
d
r
ess
th
is
lim
i
tatio
n
,
th
e
p
r
o
p
o
s
ed
d
etec
tio
n
alg
o
r
ith
m
was
f
ir
s
t
ev
alu
ated
o
n
th
e
T
PEHG
T
d
ataset,
wh
er
e
r
ef
er
en
ce
a
n
n
o
t
atio
n
s
o
f
u
ter
in
e
co
n
tr
ac
tio
n
s
ar
e
av
ailab
le.
T
h
e
d
etec
ted
c
o
n
tr
ac
tio
n
s
eg
m
en
ts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
8
8
5
-
1
898
1888
wer
e
co
m
p
ar
ed
ag
ai
n
s
t
an
n
o
t
ated
in
ter
v
als
to
v
er
if
y
th
e
r
el
iab
ilit
y
o
f
th
e
m
eth
o
d
.
Af
ter
t
h
is
v
alid
atio
n
s
tep
,
th
e
s
am
e
Z
C
R
-
b
ased
d
etec
tio
n
f
r
am
ewo
r
k
was
ap
p
lied
t
o
t
h
e
I
C
E
HG
d
ataset
to
ex
tr
ac
t
co
n
tr
ac
tio
n
s
eg
m
e
n
ts
in
a
f
u
lly
au
to
m
ated
m
a
n
n
er
.
T
h
is
cr
o
s
s
-
d
ataset
v
alid
atio
n
en
s
u
r
es
th
at
th
e
co
n
tr
ac
tio
n
id
en
tific
atio
n
p
r
o
ce
s
s
is
r
o
b
u
s
t
an
d
b
ased
o
n
a
m
e
th
o
d
th
at
h
as
b
ee
n
in
d
ep
en
d
en
tly
ev
alu
ated
o
n
a
n
n
o
tated
d
ata.
T
h
e
o
v
er
all
au
to
m
atic
ex
tr
ac
tio
n
p
r
o
ce
d
u
r
e
o
f
co
n
tr
ac
tio
n
s
eg
m
e
n
ts
h
a
s
b
ee
n
d
escr
ib
ed
i
n
d
etail
in
o
u
r
p
r
ev
io
u
s
s
tu
d
y
[
1
9
]
,
a
n
d
a
s
ch
e
m
atic
o
v
er
v
ie
w
o
f
th
e
p
i
p
elin
e
is
p
r
esen
ted
i
n
Fig
u
r
e
2
.
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
am
o
f
th
e
m
eth
o
d
o
lo
g
y
2
.
3
.
Co
m
plex
pla
ne
o
f
ea
ch
c
o
ntr
a
ct
io
n seg
m
ent
T
h
e
d
is
cr
ete
Fo
u
r
ier
tr
a
n
s
f
o
r
m
(
DFT)
is
a
wid
ely
u
tili
ze
d
an
aly
tical
m
eth
o
d
i
n
s
ig
n
al
p
r
o
ce
s
s
in
g
s
y
s
tem
s
.
T
h
e
DFT
is
a
m
ath
e
m
atica
l
p
r
o
ce
d
u
r
e
th
at
co
n
v
er
ts
a
s
eq
u
en
ce
o
f
c
o
m
p
le
x
n
u
m
b
er
s
in
to
an
o
th
e
r
s
eq
u
en
ce
o
f
co
m
p
le
x
n
u
m
b
er
s
,
r
ep
r
esen
tin
g
th
e
s
ig
n
al
in
th
e
f
r
eq
u
en
c
y
d
o
m
ain
.
T
h
is
s
tu
d
y
in
v
o
lv
ed
d
ec
o
m
p
o
s
in
g
th
e
E
HG
s
ig
n
al
in
to
its
r
ea
l
an
d
im
ag
in
ar
y
co
m
p
o
n
en
ts
v
ia
th
e
DFT
m
eth
o
d
in
Py
th
o
n
.
T
h
e
m
ath
em
atica
l f
o
r
m
u
latio
n
o
f
DFT
is
p
r
o
v
id
ed
in
(
1
)
.
=
∑
[
]
−
2
−
1
=
0
(
1
)
Her
e,
th
e
E
HG
tim
e
s
er
ies,
[
]
is
co
n
v
e
r
ted
i
n
to
th
e
E
HG
f
r
eq
u
en
cy
s
er
ies
.
T
h
e
r
ea
l
co
m
p
o
n
en
t
p
er
tain
s
to
th
e
ag
g
r
eg
ate
o
f
th
e
ac
tu
al
co
m
p
o
n
en
ts
o
f
th
e
p
r
o
d
u
cts,
wh
ile
th
e
im
ag
in
ar
y
co
m
p
o
n
en
t
p
er
tain
s
to
th
e
ag
g
r
eg
ate
o
f
t
h
e
im
ag
i
n
ar
y
co
m
p
o
n
e
n
ts
o
f
th
ese
p
r
o
d
u
cts
f
r
o
m
(
1
)
.
T
h
e
co
m
p
lex
p
lan
e
is
f
o
r
m
ed
b
y
g
r
a
p
h
in
g
th
e
r
ea
l
an
d
im
ag
in
ar
y
c
o
m
p
o
n
en
ts
o
f
th
e
Fo
u
r
ier
co
e
f
f
ic
ien
ts
,
with
th
e
r
ea
l
p
ar
t
o
n
th
e
x
-
ax
is
an
d
th
e
im
ag
in
ar
y
p
ar
t
o
n
th
e
y
-
ax
is
.
T
h
is
s
tu
d
y
ex
am
in
es
b
o
u
n
d
ar
y
s
h
ap
es,
s
u
ch
as
th
e
co
n
v
ex
h
u
ll,
with
in
a
s
et
o
f
p
o
in
ts
in
th
e
p
lan
e
[
2
0
]
.
C
o
n
v
ex
h
u
ll
was
s
elec
ted
in
th
is
s
t
u
d
y
b
ec
a
u
s
e
o
f
its
ea
s
e
o
f
co
m
p
u
tatio
n
,
r
esil
ien
ce
to
n
o
is
e,
an
d
ca
p
ac
ity
to
r
ep
r
esen
t
th
e
g
l
o
b
al
g
eo
m
etr
ic
s
tr
u
ctu
r
e
o
f
th
e
E
HG
co
n
tr
ac
tio
n
p
atter
n
s
[
2
1
]
.
O
n
th
e
o
th
er
h
a
n
d
,
m
eth
o
d
s
lik
e
a
lp
h
a
s
h
ap
es n
ee
d
t
o
h
a
v
e
th
eir
p
ar
am
eter
s
s
et
a
n
d
a
r
e
m
o
r
e
s
en
s
itiv
e
to
ch
a
n
g
es
in
n
o
is
e
an
d
p
o
in
t
d
en
s
ity
.
T
h
e
alg
o
r
ith
m
o
f
th
e
c
o
n
v
e
x
h
u
ll f
o
r
m
atio
n
is
g
iv
en
b
elo
w
.
Alg
o
r
ith
m
1
.
Gr
ah
am
s
ca
n
Select
₀
with minimum y
-
coordinate and sort remaining points by polar angle w.r.t.
₀
.
Initialize
=
[
₀
,
1
,
2
]
. For each point
[
]
(
=
3
|
|
)
, remove the last point
from
while orientation
(
[
−
2
]
,
[
−
1
]
,
[
]
)
≥
0
, then append
[
]
.
Return
.
orientation
(
,
,
)
=
(
−
)
(
−
)
−
(
−
)
(
−
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
u
to
ma
ted
p
r
ed
ictio
n
o
f th
e
mo
d
e
o
f b
ir
th
d
elive
r
y
u
s
in
g
…
(
R
u
b
a
n
a
Ho
q
u
e
C
h
o
w
d
h
u
r
y
)
1889
2
.
4
.
F
ea
t
ure
ex
t
ra
c
t
io
n
T
h
e
b
asic
g
eo
m
etr
ic
c
h
ar
ac
ter
is
tics
ar
e
th
e
s
o
le
f
ac
to
r
d
is
ti
n
g
u
is
h
in
g
s
h
a
p
es
th
at
v
ar
y
s
u
b
s
tan
tially
[
2
0
]
.
W
e
h
a
v
e
ex
tr
ac
ted
s
ev
er
al
g
eo
m
etr
ic
attr
ib
u
tes
f
r
o
m
th
e
wh
o
le
E
HG
s
ig
n
al
an
d
ea
c
h
u
ter
in
e
co
n
t
r
ac
tio
n
s
eg
m
en
t
in
th
e
E
HG
s
ig
n
al,
o
u
tlin
ed
in
T
ab
le
2
.
Alo
n
g
with
th
e
f
ea
tu
r
e
ex
t
r
ac
tio
n
,
a
s
tatis
tical
an
aly
s
i
s
was
ca
r
r
ied
o
u
t
to
ex
a
m
in
e
th
e
d
i
s
cr
im
in
ato
r
y
p
o
wer
o
f
th
e
o
b
t
ain
ed
g
e
o
m
etr
ical
f
ea
tu
r
es.
F
o
r
th
is
p
u
r
p
o
s
e,
we
co
n
d
u
cte
d
th
e
n
o
n
-
p
ar
a
m
etr
ic
Ma
n
n
-
W
h
itn
ey
U
test
to
ass
ess
th
e
s
ta
tis
tica
lly
s
ig
n
if
ican
t
d
if
f
er
en
ce
s
am
o
n
g
all
th
e
f
ea
tu
r
es
b
etwe
en
th
e
f
o
llo
win
g
g
r
o
u
p
s
:
s
p
o
n
tan
eo
u
s
v
s
.
ce
s
ar
ea
n
E
HG
(
E
S
v
s
.
E
C
)
,
ce
s
ar
ea
n
v
s
.
in
d
u
ce
d
v
ag
in
al
E
HG
(
E
S
v
s
.
E
I
)
,
a
n
d
s
p
o
n
tan
e
o
u
s
v
a
g
in
al
v
s
.
in
d
u
ce
d
v
ag
in
al
(
E
S
v
s
.
E
I
)
.
T
h
e
B
o
n
f
er
r
o
n
i
co
r
r
ec
tio
n
was
u
s
ed
to
lo
wer
th
e
ch
an
ce
o
f
m
ak
i
n
g
a
ty
p
e
I
er
r
o
r
b
ec
au
s
e
th
er
e
wer
e
s
o
m
an
y
co
m
p
ar
is
o
n
s
.
T
h
e
s
ig
n
if
ican
ce
th
r
esh
o
l
d
w
as
co
n
s
eq
u
en
tly
m
o
d
if
ied
to
p
<
0
.
0
0
1
2
b
y
d
iv
id
in
g
th
e
n
o
m
in
al
s
ig
n
if
ican
ce
lev
el
(
α
=
0
.
0
5
)
b
y
th
e
to
tal
n
u
m
b
er
o
f
s
tatis
tical
te
s
ts
co
n
d
u
cted
(
N
=
4
2
)
.
T
ab
le
2
.
Ma
th
em
atica
l r
e
p
r
ese
n
tatio
n
o
f
e
x
tr
ac
ted
f
ea
tu
r
es
G
e
o
me
t
r
i
c
a
l
F
e
a
t
u
r
e
s
M
a
t
h
e
ma
t
i
c
a
l
e
q
u
a
t
i
o
n
A
r
e
a
=
1
2
∑
|
(
(
[
]
×
[
+
1
]
)
−
(
[
+
1
]
×
[
]
)
|
−
1
=
1
H
e
r
e
,
i
t
i
s
c
a
l
c
u
l
a
t
e
d
b
y
p
o
l
y
g
o
n
v
e
r
t
i
c
e
s (
a
n
d
)
.
r
e
p
r
e
se
n
t
s t
h
e
n
u
m
b
e
r
o
f
p
o
i
n
t
s
i
n
t
h
e
s
h
a
p
e
.
P
e
r
i
me
t
e
r
=
(
[
+
1
]
−
[
]
)
×
(
[
+
1
]
−
[
]
)
=
(
[
+
1
]
−
[
]
)
×
(
[
+
1
]
−
[
]
)
=
∑
√
+
−
1
=
1
C
i
r
c
u
l
a
r
i
t
y
r
a
t
i
o
=
4
×
(
)
2
V
a
r
i
a
n
c
e
=
(
(
,
)
,
(
[
]
,
[
]
=
1
∑
−
1
=
0
=
1
∑
(
−
−
1
=
0
)
2
B
e
n
d
i
n
g
e
n
e
r
g
y
=
∑
[
(
[
−
1
]
−
2
[
]
+
[
+
1
]
)
2
+
(
[
−
1
]
−
2
[
]
+
[
+
1
]
)
2
−
2
=
1
]
U
t
e
r
i
n
e
C
o
n
t
r
a
c
t
i
o
n
’
s Fe
a
t
u
r
e
s
En
e
r
g
y
=
∑
2
C
o
n
t
r
a
c
t
i
o
n
P
o
w
e
r
=
∑
(
)
=
×
/
H
a
n
d
L
a
r
e
t
h
e
P
S
D
c
o
mp
o
n
e
n
t
n
u
m
b
e
r
s
c
o
r
r
e
s
p
o
n
d
i
n
g
t
o
t
h
e
u
p
p
e
r
a
n
d
l
o
w
e
r
l
i
m
i
t
o
f
t
h
e
EH
G
f
r
e
q
u
e
n
c
y
b
a
n
d
,
r
e
s
p
e
c
t
i
v
e
l
y
,
i
s t
h
e
sam
p
l
i
n
g
f
r
e
q
u
e
n
c
y
,
a
n
d
N
i
s
t
h
e
n
u
mb
e
r
o
f
sam
p
l
e
s w
i
t
h
i
n
t
h
e
c
o
n
t
r
a
c
t
i
l
e
a
c
t
i
v
i
t
y
seg
m
e
n
t
.
P
e
a
k
a
m
p
l
i
t
u
d
e
=
(
)
−
(
)
2
.
5
.
Cla
s
s
if
iers
T
h
is
s
tu
d
y
ass
ess
e
s
th
e
ef
f
icac
y
o
f
a
r
a
n
d
o
m
f
o
r
est
(
R
F)
class
if
ier
,
r
en
o
wn
ed
f
o
r
its
ex
ce
llen
t
class
if
icatio
n
ac
cu
r
ac
y
an
d
ad
ap
tab
ilit
y
ac
r
o
s
s
v
ar
io
u
s
d
ata
ty
p
es
[
2
2
]
.
T
o
en
s
u
r
e
a
m
o
r
e
s
y
s
tem
atic
an
d
r
ep
r
o
d
u
cib
le
m
o
d
el
d
esig
n
,
h
y
p
er
p
ar
am
eter
tu
n
in
g
was
p
er
f
o
r
m
ed
u
s
in
g
a
s
tr
u
ctu
r
e
d
s
ea
r
ch
s
tr
ateg
y
.
Sp
ec
if
ically
,
a
g
r
id
-
b
ased
s
ea
r
ch
co
m
b
in
ed
with
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
(
=
5
)
was
em
p
lo
y
ed
o
n
th
e
tr
ain
in
g
d
ataset
to
id
en
tify
t
h
e
o
p
tim
al
s
et
o
f
h
y
p
er
p
a
r
am
eter
s
.
T
h
e
o
p
tim
al
h
y
p
e
r
p
ar
am
eter
s
o
b
tain
ed
f
r
o
m
th
is
p
r
o
ce
s
s
wer
e:
′
_
′
s
et
to
2
0
0
,
wh
ich
m
ea
n
s
th
e
r
an
d
o
m
f
o
r
es
t
co
n
s
is
ts
o
f
2
0
0
d
ec
is
io
n
tr
e
es;
′
_
ℎ′
s
et
to
5
;
an
d
′
_
_
′
s
et
to
5
.
T
h
e
s
elec
tio
n
o
f
a
r
elativ
ely
s
h
all
o
w
tr
ee
d
ep
th
(
_
ℎ
=
5
)
h
el
p
s
co
n
tr
o
l
m
o
d
el
co
m
p
lex
ity
an
d
m
itig
ates
o
v
er
f
i
ttin
g
,
wh
ich
is
p
ar
ticu
lar
ly
im
p
o
r
tan
t
g
iv
en
th
e
lim
ited
s
ize
an
d
in
h
er
en
t
v
ar
ia
b
ilit
y
o
f
E
HG
s
ig
n
als.
Mo
r
eo
v
er
,
we
u
tili
ze
d
a
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
class
if
ier
a
s
a
co
m
p
ar
is
o
n
m
o
d
el
in
ad
d
iti
o
n
to
R
F.
W
e
u
s
ed
g
r
id
s
ea
r
c
h
with
5
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
to
ch
o
o
s
e
th
e
m
o
d
e
l
h
y
p
er
p
a
r
am
eter
s
.
T
h
e
m
o
s
t
e
f
f
ec
tiv
e
s
etu
p
h
ad
a
r
e
g
u
lar
iza
tio
n
p
ar
am
eter
(
C
)
o
f
1
0
an
d
a
k
er
n
el
co
ef
f
icie
n
t
(
γ
)
o
f
0
.
1
.
T
h
e
d
ataset
co
m
p
r
is
es
1
4
6
E
HG
s
ig
n
als,
with
a
p
r
ed
o
m
i
n
an
t
p
r
o
p
o
r
tio
n
o
r
ig
i
n
atin
g
f
r
o
m
s
p
o
n
tan
eo
u
s
d
eliv
er
ies.
Giv
e
n
th
is
im
b
ala
n
ce
,
a
d
ilig
en
t
ef
f
o
r
t
was
m
ad
e
to
m
itig
ate
b
ias
b
y
en
s
u
r
in
g
eq
u
itab
le
r
ep
r
esen
tatio
n
ac
r
o
s
s
s
ig
n
als
d
er
iv
ed
f
r
o
m
s
p
o
n
tan
eo
u
s
,
ce
s
ar
ea
n
,
an
d
in
d
u
ce
d
d
eli
v
er
ies.
T
o
ad
d
r
ess
th
is
im
b
alan
ce
,
th
e
s
y
n
th
etic
m
in
o
r
ity
o
v
er
-
s
am
p
lin
g
tech
n
i
q
u
e
(
SMOT
E
)
was
ap
p
lied
to
th
e
tr
ain
in
g
s
et.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
8
8
5
-
1
898
1890
3.
RE
SU
L
T
S
T
h
e
m
o
d
els
wer
e
d
ev
elo
p
ed
,
tr
ain
ed
,
an
d
ev
al
u
ated
u
s
in
g
Py
C
h
ar
m
,
a
s
cien
tific
p
r
o
g
r
am
m
in
g
en
v
ir
o
n
m
en
t
wr
itten
in
Py
t
h
o
n
3
.
8
,
a
n
d
Scik
it
-
lear
n
0
.
2
2
,
a
m
ac
h
in
e
lear
n
in
g
lib
r
a
r
y
.
Fig
u
r
e
2
illu
s
tr
ates
th
e
au
to
m
atic
ex
tr
ac
tio
n
o
f
c
o
n
tr
ac
tio
n
s
eg
m
en
ts
,
wh
ich
alig
n
clo
s
ely
with
th
e
s
im
u
ltan
eo
u
s
ly
r
ec
o
r
d
ed
T
OC
O
co
n
tr
ac
tio
n
s
.
T
h
e
co
n
t
r
ac
tio
n
b
u
r
s
ts
wer
e
ex
tr
ac
ted
f
r
o
m
th
e
E
HG
s
ig
n
al
u
s
in
g
th
e
ze
r
o
cr
o
s
s
in
g
an
d
R
MS
-
b
ased
m
eth
o
d
[
1
9
]
.
Fig
u
r
e
3
d
is
p
lay
s
th
e
s
am
p
le
o
f
ex
tr
ac
te
d
co
n
tr
ac
tio
n
f
r
o
m
th
e
E
HG
s
ig
n
al
alo
n
g
with
its
attr
ib
u
tes.
I
n
th
e
r
ec
o
r
d
in
g
s
f
r
o
m
th
e
Sp
o
n
tan
eo
u
s
g
r
o
u
p
,
we
d
etec
ted
ab
o
u
t
3
9
6
c
o
n
tr
ac
tile
ep
is
o
d
es,
wh
er
ea
s
in
th
e
in
d
u
ce
d
g
r
o
u
p
an
d
ce
s
ar
ea
n
g
r
o
u
p
,
we
e
x
tr
ac
ted
ab
o
u
t
2
9
a
n
d
3
4
r
esp
ec
tiv
ely
.
Fig
u
r
e
4
d
ep
icts
th
e
c
o
n
v
e
x
h
u
ll
r
e
p
r
esen
tin
g
th
e
b
o
u
n
d
ar
y
s
h
ap
e
o
f
t
h
e
en
tire
s
ig
n
al,
A
d
d
itio
n
ally
,
Fig
u
r
e
5
s
h
o
ws
th
e
b
o
u
n
d
ar
y
s
h
ap
e
o
f
th
e
co
n
v
ex
h
u
ll f
o
r
m
e
d
f
r
o
m
th
e
d
ata
p
o
i
n
ts
o
f
th
e
co
n
tr
ac
tile seg
m
en
ts
.
T
h
e
em
p
ty
s
p
ac
es
th
at
ap
p
ea
r
with
in
th
e
en
clo
s
e
d
ar
ea
s
in
Fig
u
r
e
5
ca
n
b
e
attr
ib
u
ted
to
th
e
co
n
v
ex
h
u
ll
o
f
Fo
u
r
ier
d
escr
ip
to
r
s
.
T
h
is
is
d
u
e
to
th
e
u
n
e
v
en
clu
s
ter
in
g
o
f
p
o
in
ts
in
th
e
co
m
p
lex
p
lan
e.
Alth
o
u
g
h
th
ey
m
ay
n
o
t
h
av
e
p
h
y
s
io
lo
g
ical
s
ig
n
if
ican
ce
,
th
ey
af
f
ec
t
g
e
o
m
etr
ical
ch
a
r
ac
ter
is
tics
.
T
ab
le
3
d
is
p
lay
s
th
e
av
er
ag
e
v
alu
es
o
f
g
eo
m
etr
ical
attr
ib
u
tes
d
er
i
v
ed
f
r
o
m
t
h
e
co
m
p
lete
wh
o
le
E
H
G
s
ig
n
al
an
d
co
n
tr
ac
tio
n
s
eg
m
en
ts
o
f
th
e
s
ig
n
al
th
r
o
u
g
h
a
c
o
n
v
e
x
h
u
ll,
in
cl
u
d
in
g
a
r
ea
,
p
e
r
im
eter
,
cir
c
u
l
ar
ity
,
v
ar
ian
c
e,
b
e
n
d
in
g
en
e
r
g
y
,
e
n
er
g
y
,
p
ea
k
am
p
litu
d
e
o
f
co
n
tr
ac
tio
n
c
u
r
v
e,
an
d
c
o
n
tr
ac
tio
n
p
o
we
r
.
Alth
o
u
g
h
f
ea
tu
r
es
wer
e
in
itially
ex
tr
ac
ted
f
r
o
m
ea
c
h
d
etec
ted
co
n
tr
ac
tio
n
s
eg
m
en
t,
m
u
ltip
le
s
eg
m
e
n
ts
with
in
a
s
in
g
le
r
ec
o
r
d
wer
e
ag
g
r
eg
ated
to
f
o
r
m
a
r
ep
r
esen
tativ
e
f
ea
tu
r
e
v
ec
to
r
.
Sp
ec
if
ically
,
s
tatis
tical
m
ea
s
u
r
es,
p
r
im
ar
ily
th
e
m
ea
n
,
wer
e
c
o
m
p
u
ted
ac
r
o
s
s
all
co
n
tr
ac
tio
n
s
eg
m
e
n
ts
o
f
ea
ch
r
ec
o
r
d
.
T
h
ese
ag
g
r
e
g
ated
f
ea
t
u
r
es
wer
e
th
en
u
s
ed
f
o
r
s
tatis
tical
an
aly
s
is
.
I
n
th
is
s
tu
d
y
,
th
e
u
n
it
o
f
a
n
aly
s
is
is
th
e
i
n
d
iv
id
u
al
r
ec
o
r
d
.
T
h
e
s
tatis
tical
m
ea
s
u
r
es
d
er
iv
ed
f
r
o
m
th
e
g
e
o
m
etr
ical
f
ea
tu
r
es
ar
e
also
p
r
esen
ted
in
T
ab
le
3
.
Fig
u
r
e
s
6
(
a)
-
(
h
)
p
r
esen
ts
th
e
b
o
x
p
lo
t
d
is
tr
ib
u
tio
n
s
o
f
in
d
iv
id
u
al
g
eo
m
etr
ical
a
n
d
co
n
tr
ac
tio
n
-
b
ased
f
ea
tu
r
es
ac
r
o
s
s
s
p
o
n
tan
e
o
u
s
,
ce
s
ar
ea
n
,
an
d
in
d
u
ce
d
g
r
o
u
p
s
,
h
ig
h
lig
h
ti
n
g
th
e
v
ar
iatio
n
an
d
d
is
cr
im
in
ati
v
e
p
atter
n
s
am
o
n
g
th
ese
class
es.
W
e
al
s
o
u
s
ed
R
F
an
d
SV
M
class
if
ier
s
to
ch
ec
k
h
o
w
ef
f
ec
tiv
ely
th
e
class
if
icatio
n
wo
r
k
e
d
.
Fig
u
r
e
7
s
h
o
ws
th
e
r
ec
eiv
er
o
p
er
atin
g
ch
a
r
ac
te
r
is
tic
(
R
O
C
)
cu
r
v
es
an
d
a
r
ea
u
n
d
er
th
e
cu
r
v
e
(
AUC)
v
alu
es
f
o
r
t
h
e
R
F
an
d
SV
M
m
o
d
els.
T
h
e
R
F
an
d
SVM
class
if
ier
u
s
ed
a
o
n
e
-
vs
-
r
est
s
tr
ateg
y
to
d
o
m
u
lti
-
cl
ass
clas
s
if
icatio
n
.
T
o
ass
ess
t
h
e
d
is
cr
im
in
ativ
e
ab
ilit
y
o
f
g
eo
m
etr
ical
f
ea
tu
r
es
an
d
co
n
tr
ac
tio
n
attr
ib
u
tes
am
o
n
g
th
r
ee
g
r
o
u
p
s
—
Sp
o
n
tan
eo
u
s
E
HG,
E
ar
ly
C
esar
ea
n
E
HG,
an
d
E
ar
ly
I
n
d
u
ce
d
E
HG
—
we
m
ea
s
u
r
ed
th
e
f
i
v
e
ev
alu
atio
n
p
ar
am
eter
s
b
y
a
p
p
ly
in
g
a
n
R
F
class
if
ier
,
wh
ich
is
r
ep
r
esen
ted
b
y
Fig
u
r
e
8
.
T
o
in
te
r
p
r
et
th
e
R
F
m
o
d
el
a
n
d
p
r
o
v
id
e
b
io
lo
g
ical
in
s
ig
h
t,
we
p
er
f
o
r
m
ed
f
ea
tu
r
e
im
p
o
r
tan
ce
an
aly
s
is
u
s
in
g
m
ea
n
d
ec
r
ea
s
e
in
im
p
u
r
i
ty
(
MD
I
)
,
as p
r
esen
te
d
in
Fig
u
r
e
9
.
Fig
u
r
e
3
.
Featu
r
es o
f
u
ter
in
e
c
o
n
tr
ac
tio
n
Fig
u
r
e
4
.
T
h
e
co
n
v
ex
h
u
ll with
b
o
u
n
d
ar
y
r
ec
tan
g
le.
B
o
u
n
d
a
r
y
s
h
ap
e
f
o
r
m
ed
u
s
in
g
d
ata
p
o
in
ts
f
r
o
m
th
e
e
n
tire
s
ig
n
al
(
r
ec
o
r
d
iceh
g
7
5
9
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
u
to
ma
ted
p
r
ed
ictio
n
o
f th
e
mo
d
e
o
f b
ir
th
d
elive
r
y
u
s
in
g
…
(
R
u
b
a
n
a
Ho
q
u
e
C
h
o
w
d
h
u
r
y
)
1891
Fig
u
r
e
5
.
C
o
n
v
ex
h
u
ll f
o
r
m
ed
f
r
o
m
d
ata
p
o
in
ts
o
f
th
e
co
n
tr
a
ctio
n
s
eg
m
en
ts
(
Fiv
e
co
n
tr
ac
tio
n
s
ex
t
r
ac
ted
f
r
o
m
r
ec
o
r
d
iceh
g
7
5
9
)
T
ab
le
3
.
T
h
e
m
ea
n
v
alu
es o
f
g
eo
m
etr
ical
an
d
c
o
n
tr
ac
tile e
p
is
o
d
e
f
ea
tu
r
es o
b
tain
ed
ac
r
o
s
s
all
r
ec
o
r
d
in
g
s
.
Statis
t
ical
s
ig
n
if
ican
ce
an
aly
s
is
o
f
th
e
f
ea
tu
r
es b
etwe
en
g
r
o
u
p
s
E
S a
n
d
E
C
,
E
C
an
d
E
I
,
E
S
an
d
E
I
F
e
a
t
u
r
e
s
F
e
a
t
u
r
e
s
e
x
t
r
a
c
t
e
d
f
r
o
m
t
h
e
w
h
o
l
e
si
g
n
a
l
F
e
a
t
u
r
e
s
e
x
t
r
a
c
t
e
d
f
r
o
m
t
h
e
c
o
n
t
r
a
c
t
i
o
n
se
g
m
e
n
t
s
M
e
a
n
v
a
l
u
e
P
-
v
a
l
u
e
b
e
t
w
e
e
n
g
r
o
u
p
s
M
e
a
n
v
a
l
u
e
P
-
v
a
l
u
e
b
e
t
w
e
e
n
g
r
o
u
p
s
ES
EC
EI
ES & E
C
EC
&
EI
ES & E
I
ES
EC
EI
ES & E
C
EC
&
EI
ES & E
I
A
r
e
a
5
0
2
4
1
5
4
4
3
0
6
1
2
0
.
1
1
2
0
.
0
2
4
0
.
9
1
2
0
.
1
1
4
0
.
0
0
3
6
0
.
0
0
3
2
.
0
1
e
-
06
0
.
3
5
6
0
.
0
0
0
6
P
e
r
i
me
t
e
r
2
2
3
1
4
4
2
1
5
0
.
1
0
4
0
.
0
4
3
0
.
4
6
7
1
.
0
7
0
.
1
4
0
2
0
.
1
3
1
0
.
2
9
3
e
-
03
1
.
1
4
e
-
06
0
.
0
0
0
4
C
i
r
c
u
l
a
r
i
t
y
0
.
9
0
.
8
9
0
.
9
0
.
7
0
6
0
.
3
4
1
0
.
6
0
6
0
.
5
5
0
.
6
2
2
3
0
.
6
3
8
1
.
3
8
e
-
11
0
.
0
1
9
1
.
5
1
e
-
07
V
a
r
i
a
n
c
e
1
8
2
2
5
5
5
1
3
4
5
0
.
1
2
1
0
.
0
1
1
2
0
.
9
1
2
0
.
1
3
6
0
.
0
0
2
6
0
.
0
0
1
8
7
.
4
1
e
-
07
0
.
0
5
6
0
.
0
0
0
3
B
e
n
d
i
n
g
e
n
e
r
g
y
3
.
4
7
e
0
6
1
.
4
5
e
0
6
9
.
6
e
0
6
0
.
1
1
6
0
.
0
2
4
0
.
9
2
4
2
8
.
5
5
0
.
0
0
3
6
0
.
0
0
1
6
9
.
5
9
e
-
07
0
.
0
5
2
0
.
0
0
0
1
En
e
r
g
y
(
mV
2
/
s)
×
×
×
×
×
×
0
.
0
1
9
0
.
0
0
0
3
0
.
0
0
0
5
0
.
0
0
1
1
0
.
0
0
4
0
.
0
0
3
P
e
a
k
a
m
p
l
i
t
u
d
e
(
mV
)
×
×
×
×
×
×
1
.
1
8
9
1
.
1
3
3
9
1
.
1
1
2
6
.
0
6
e
-
10
0
.
0
0
5
2
.
2
3
e
-
05
C
o
n
t
r
a
c
t
i
o
n
p
o
w
e
r
(
mV
2
.
s)
×
×
×
×
×
×
0
.
0
1
9
0
.
0
1
9
7
0
.
0
2
0
9
.
9
5
e
-
10
0
.
0
0
4
1
.
3
4
e
-
07
C
o
n
t
r
a
c
t
i
o
n
d
u
r
a
t
i
o
n
(
s
)
×
×
×
×
×
×
5
4
.
4
9
4
7
.
1
2
5
4
8
.
7
7
0
0
.
0
5
3
0
.
2
5
6
0
.
7
4
N
o
t
e
:
‘
×
’
i
n
d
i
c
a
t
e
s t
h
a
t
t
h
e
f
e
a
t
u
r
e
i
s
n
o
t
a
p
p
l
i
c
a
b
l
e
f
o
r
t
h
e
w
h
o
l
e
s
i
g
n
a
l
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
8
8
5
-
1
898
1892
(
a)
(
b
)
(
c)
(
d
)
(
e)
(f)
(
g
)
(
h
)
Fig
u
r
e
6
.
B
o
x
p
lo
t sh
o
win
g
in
d
iv
id
u
al
f
ea
tu
r
es
:
(
a)
ar
ea
,
(
b
)
b
en
d
in
g
en
er
g
y
,
(
c)
p
e
r
im
eter
,
(
d
)
v
a
r
ian
ce
,
(
e)
cir
cu
lar
ity
,
(
f
)
C
o
n
tr
ac
tio
n
p
o
wer
,
(
g
)
en
e
r
g
y
,
an
d
(
h
)
p
ea
k
am
p
litu
d
e
f
o
r
s
p
o
n
tan
eo
u
s
v
ag
in
al,
ce
s
ar
ea
n
,
an
d
in
d
u
ce
d
g
r
o
u
p
Fig
u
r
e
7
.
R
OC
p
lo
t o
f
SVM
a
n
d
R
F
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
u
to
ma
ted
p
r
ed
ictio
n
o
f th
e
mo
d
e
o
f b
ir
th
d
elive
r
y
u
s
in
g
…
(
R
u
b
a
n
a
Ho
q
u
e
C
h
o
w
d
h
u
r
y
)
1893
Fig
u
r
e
8
.
Per
f
o
r
m
an
c
e
r
esu
lts
o
f
R
F f
o
r
p
r
ed
ictin
g
E
C
v
s
.
E
I
,
E
S v
s
.
E
I
,
an
d
E
S v
s
.
E
C
(
a)
(
b
)
(
c)
Fig
u
r
e
9
.
Me
an
d
ec
r
ea
s
e
in
im
p
u
r
ity
(
MD
I
)
f
o
r
f
ea
tu
r
e
im
p
o
r
tan
ce
in
r
a
n
d
o
m
f
o
r
est m
o
d
el
s
: (
a)
C
esar
ea
n
v
s
s
p
o
n
tan
eo
u
s
,
(
b
)
in
d
u
ce
d
v
s
s
p
o
n
tan
e
o
u
s
an
d
(
c)
in
d
u
ce
d
v
s
ce
s
ar
ea
n
4.
DIS
CU
SS
I
O
N
Mu
ltip
le
s
tu
d
ies
h
av
e
in
v
esti
g
ated
th
e
u
tili
ty
o
f
E
HG
s
ig
n
al
s
,
em
p
lo
y
in
g
lin
ea
r
(
s
p
ec
tr
al,
tem
p
o
r
al,
s
tatis
t
ical
p
ar
am
eter
s
)
as
well
as
n
o
n
lin
ea
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
m
eth
o
d
s
[
2
3
]
,
[
2
4
]
.
T
h
is
s
tu
d
y
f
o
cu
s
ed
o
n
th
e
ex
tr
ac
tio
n
o
f
g
eo
m
etr
ic
f
ea
t
u
r
es
f
r
o
m
u
ter
i
n
e
co
n
tr
ac
tio
n
b
u
r
s
ts
.
T
h
is
allo
ws
f
o
r
a
m
o
r
e
lo
ca
lized
an
d
p
h
y
s
io
lo
g
ically
r
elev
a
n
t d
ep
ic
tio
n
o
f
u
ter
in
e
ac
tiv
ity
.
Fo
r
ea
ch
co
n
tr
ac
tio
n
s
eg
m
en
t,
th
e
ex
tr
ac
ted
g
eo
m
etr
ical
f
ea
tu
r
es
s
h
o
w
th
e
f
o
r
m
,
s
tr
en
g
th
,
an
d
m
o
r
p
h
o
lo
g
ical
co
m
p
lex
ity
o
f
th
e
E
HG
s
ig
n
al
d
u
r
in
g
ac
tiv
e
u
ter
in
e
co
n
tr
ac
tio
n
s
.
T
h
ese
f
ea
tu
r
es
a
r
e
ch
ar
ac
ter
ize
d
b
y
s
im
p
licity
an
d
c
o
m
p
u
tatio
n
al
ef
f
icien
cy
co
m
p
ar
ed
to
lin
ea
r
an
d
n
o
n
lin
ea
r
f
ea
t
u
r
es
[
2
5
]
.
I
n
th
e
p
ast
ten
y
ea
r
s
,
s
tu
d
ies
o
n
E
HG
s
ig
n
als
h
av
e
ten
d
ed
to
ad
o
p
t
th
e
wh
o
le
s
ig
n
al
an
d
class
if
y
p
r
eter
m
b
ir
th
b
ased
o
n
m
ac
h
in
e
lear
n
in
g
[
2
6
]
–
[
2
8
]
.
T
h
is
s
tu
d
y
in
v
o
lv
e
d
th
e
ex
tr
ac
tio
n
o
f
g
eo
m
etr
ical
f
ea
tu
r
es
f
r
o
m
th
e
co
m
p
lete
E
HG
s
ig
n
al
o
f
s
p
o
n
t
an
eo
u
s
,
ce
s
ar
ea
n
,
a
n
d
in
d
u
ce
d
d
eliv
er
ies,
as
well
as
f
r
o
m
th
e
e
x
tr
ac
ted
co
n
tr
a
ctio
n
b
u
r
s
ts
.
T
h
is
a
r
ti
cl
e
ex
a
m
i
n
es
t
h
e
a
p
p
li
ca
b
ili
ty
o
f
u
t
ilizi
n
g
c
o
n
tr
ac
ti
o
n
v
a
r
i
ab
les
a
n
d
t
h
eir
g
eo
m
e
tr
ic
c
h
a
r
a
cte
r
is
tics
to
p
r
e
d
i
ct
t
h
e
m
e
th
o
d
o
f
d
e
li
v
e
r
y
ac
r
o
s
s
t
h
r
ee
c
ate
g
o
r
ies:
ce
s
ar
ea
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
8
8
5
-
1
898
1894
s
ec
ti
o
n
,
in
d
u
c
e
d
v
ag
in
al
d
e
li
v
e
r
y
,
an
d
s
p
o
n
ta
n
e
o
u
s
v
a
g
i
n
a
l
d
e
li
v
e
r
y
.
U
n
d
e
r
s
t
an
d
i
n
g
u
te
r
i
n
e
co
n
t
r
a
cti
o
n
s
is
v
it
al
in
ass
ess
in
g
th
e
p
r
o
g
r
ess
o
f
la
b
o
r
a
n
d
e
n
s
u
r
i
n
g
a
s
u
c
ce
s
s
f
u
l
d
el
iv
er
y
[
2
9
]
.
F
u
r
t
h
e
r
m
o
r
e,
o
u
r
i
n
v
esti
g
ati
o
n
ex
t
e
n
d
s
t
o
e
x
a
m
i
n
i
n
g
l
ab
o
r
o
u
t
co
m
es
d
u
r
i
n
g
th
e
p
r
e
g
n
a
n
c
y
,
t
y
p
ic
all
y
a
f
te
r
3
1
we
ek
s
o
f
g
est
ati
o
n
.
Ho
wev
er
,
u
p
o
n
ex
am
i
n
atio
n
o
f
T
ab
le
3
,
it
b
ec
am
e
ev
id
e
n
t
th
at
n
o
s
ig
n
if
ican
t
d
if
f
e
r
e
n
ce
s
wer
e
o
b
s
er
v
ab
le
a
m
o
n
g
th
ese
g
r
o
u
p
s
.
C
o
n
s
eq
u
en
tl
y
,
o
u
r
f
o
cu
s
s
h
if
ted
to
war
d
s
id
e
n
tify
in
g
a
s
h
ap
e
o
f
ea
ch
co
n
tr
ac
tio
n
s
eg
m
en
t
th
at
c
o
u
l
d
p
r
o
v
id
e
p
r
ec
is
e
b
o
u
n
d
a
r
ies
an
d
v
al
u
ab
le
in
f
o
r
m
atio
n
ac
r
o
s
s
all
ca
s
es.
L
im
ited
r
esear
ch
h
as
f
o
cu
s
ed
e
x
clu
s
iv
ely
o
n
an
al
y
zin
g
th
e
u
ter
in
e
c
o
n
tr
ac
tio
n
s
eg
m
e
n
ts
o
f
E
HG
t
o
id
en
tify
p
r
em
atu
r
e
b
ir
th
[
3
0
]
–
[
3
2
]
.
T
y
p
ically
,
th
e
co
n
tr
ac
tio
n
b
u
r
s
ts
ar
e
m
an
u
ally
d
iv
id
ed
f
r
o
m
a
3
0
-
m
in
u
te
-
lo
n
g
r
ec
o
r
d
in
g
o
f
E
HG
u
s
in
g
T
OC
O.
W
ith
in
t
h
e
E
HG
s
tr
u
ctu
r
e,
co
n
tr
ac
tio
n
d
etec
tio
n
is
a
cr
u
cial
s
u
b
j
ec
t
th
at
m
ay
y
ield
s
ig
n
if
ican
t
in
s
ig
h
ts
f
o
r
lo
n
g
-
te
r
m
p
r
eg
n
a
n
cy
m
o
n
ito
r
in
g
.
T
h
e
m
ajo
r
ity
o
f
n
o
n
-
lin
ea
r
f
ea
tu
r
es
s
u
ch
as
en
tr
o
p
y
,
an
d
ze
r
o
cr
o
s
s
in
g
r
ate
i
n
f
o
r
m
atio
n
p
er
tin
e
n
t
to
th
e
c
h
ar
ac
te
r
izatio
n
o
f
p
r
eg
n
a
n
cy
p
er
tain
s
to
th
e
co
n
t
r
ac
tio
n
p
h
ase,
wh
er
ea
s
th
e
r
esid
u
al
s
ig
n
al
co
n
tr
i
b
u
tes
n
o
is
e
to
th
e
ass
ess
m
en
t
[
9
]
.
T
h
is
s
tu
d
y
e
n
d
ea
v
o
r
s
to
au
to
m
atica
lly
ex
tr
ac
t
u
ter
in
e
co
n
tr
ac
tio
n
s
f
r
o
m
E
HG
s
ig
n
als
u
n
d
er
ter
m
co
n
d
itio
n
s
,
aim
in
g
to
an
aly
ze
th
eir
g
eo
m
etr
ic
ch
a
r
ac
ter
is
tics
.
W
e
ex
tr
ac
ted
g
eo
m
etr
ical
f
ea
tu
r
es
f
r
o
m
th
e
b
o
u
n
d
a
r
ies
o
f
d
ata
p
o
in
ts
o
f
ea
ch
co
n
tr
ac
tile
s
eg
m
en
t
to
p
r
ed
ict
th
e
m
o
d
e
o
f
b
ir
th
d
eliv
er
y
.
Fr
o
m
T
a
b
le
3
we
o
b
s
er
v
ed
th
at
all
th
e
g
e
o
m
etr
ical
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
th
ese
s
h
ap
es
ex
h
ib
ited
s
ig
n
if
ica
n
t
d
i
f
f
er
en
ce
s
b
etwe
en
E
HGs
o
f
s
p
o
n
tan
e
o
u
s
v
ag
in
al
an
d
ce
s
ar
ea
n
d
eliv
er
y
,
ce
s
ar
e
an
an
d
in
d
u
ce
d
v
ag
i
n
al
d
eliv
er
y
,
as
well
as
s
p
o
n
tan
e
o
u
s
v
ag
in
al
an
d
in
d
u
ce
d
v
ag
in
al
d
eliv
e
r
y
.
T
h
e
ex
a
m
in
atio
n
o
f
t
h
e
tab
les
u
n
e
q
u
iv
o
c
ally
in
d
icate
s
th
at
th
e
g
e
o
m
et
r
ic
f
ea
tu
r
es
d
er
i
v
ed
f
r
o
m
th
e
u
ter
in
e
co
n
tr
ac
tio
n
s
eg
m
en
ts
u
s
in
g
a
co
n
v
ex
h
u
ll
y
ield
s
u
b
s
tan
tial
d
is
tin
ctio
n
s
(
p
≤
0
.
0
5
)
am
o
n
g
all
g
r
o
u
p
s
.
Ad
d
itio
n
ally
,
we
d
er
iv
ed
co
n
tr
ac
tio
n
-
r
elate
d
f
ea
tu
r
es
s
u
ch
as e
n
er
g
y
,
p
ea
k
am
p
litu
d
e,
an
d
co
n
tr
ac
tio
n
p
o
wer
f
r
o
m
th
e
au
to
m
atica
ll
y
s
eg
m
en
ted
co
n
t
r
ac
tile
s
eg
m
en
t.
T
h
e
a
n
al
y
s
is
o
f
th
e
ta
b
les
u
n
am
b
i
g
u
o
u
s
ly
r
e
v
e
als th
at
t
h
es
e
f
e
at
u
r
es,
d
e
r
i
v
e
d
f
r
o
m
t
h
e
s
e
g
m
e
n
ts
o
f
u
t
er
i
n
e
c
o
n
t
r
ac
ti
o
n
,
m
an
if
est
s
ig
n
i
f
ica
n
t
d
is
c
r
e
p
a
n
cies
am
o
n
g
a
ll
g
r
o
u
p
s
.
T
h
ese
v
ar
ia
b
l
es
w
er
e
s
u
b
s
e
q
u
e
n
tl
y
e
m
p
lo
y
ed
i
n
a
r
a
n
d
o
m
f
o
r
est cla
s
s
if
i
e
r
t
o
ass
ess
t
h
e
d
is
c
r
im
i
n
a
ti
v
e
ab
i
lit
y
a
m
o
n
g
th
r
e
e
u
n
i
q
u
e
ca
t
eg
o
r
ies
:
S
p
o
n
ta
n
e
o
u
s
v
a
g
i
n
al
E
HG
,
C
es
ar
ea
n
E
H
G,
a
n
d
I
n
d
u
c
ed
v
a
g
i
n
a
l
E
HG
.
Fro
m
th
e
T
ab
le
3
th
er
e
ar
e
n
o
s
ig
n
if
ican
t
d
if
f
er
e
n
ce
f
o
u
n
d
a
m
o
n
g
th
ese
g
r
o
u
p
s
th
er
ef
o
r
e
t
h
is
s
tu
d
y
n
eg
lecte
d
co
n
tr
ac
tio
n
d
u
r
atio
n
f
ac
t
o
r
.
B
ased
o
n
th
e
f
in
d
in
g
s
p
r
esen
ted
in
Fig
u
r
e
s
6
(
a)
-
(
h
)
,
it
is
ev
id
en
t
th
at
th
e
a
v
er
ag
e
an
d
m
ea
n
v
al
u
es
o
f
th
e
f
ea
tu
r
es
d
er
iv
ed
f
r
o
m
th
e
s
h
ap
e
ch
a
r
ac
ter
is
tics
(
Fig
u
r
e
6
(
a)
ar
ea
,
Fig
u
r
e
6
(
b
)
b
en
d
i
n
g
en
er
g
y
,
Fig
u
r
e
6
(
c)
p
er
im
ete
r
an
d
Fig
u
r
e
6
(
d
)
v
ar
ian
ce
o
f
th
e
u
n
d
er
ly
in
g
d
ata
e
x
h
ib
it
a
n
o
tab
ly
h
ig
h
e
r
m
ag
n
itu
d
e
in
th
e
s
p
o
n
ta
n
eo
u
s
v
ag
in
al
d
eliv
er
y
co
n
d
itio
n
co
m
p
ar
ed
to
b
o
th
ce
s
ar
ea
n
a
n
d
in
d
u
ce
d
v
a
g
in
al
d
eliv
er
y
m
o
d
es.
T
h
e
ar
ea
a
n
d
p
er
im
eter
m
etr
ics
r
ef
lect
t
h
e
d
is
p
er
s
io
n
o
f
s
ig
n
al
d
ata
p
o
in
ts
with
in
th
e
en
clo
s
ed
b
o
u
n
d
a
r
y
.
T
h
er
ef
o
r
e,
th
e
o
b
s
er
v
ed
in
cr
ea
s
e
in
t
h
ese
f
ea
tu
r
es
d
u
r
in
g
s
p
o
n
tan
eo
u
s
d
eliv
er
y
m
ay
in
d
icate
m
o
r
e
v
a
r
ied
u
ter
i
n
e
co
n
tr
ac
tio
n
s
.
Su
ch
c
o
n
tr
ac
tili
ty
is
r
ec
o
g
n
ized
as
a
k
e
y
f
ac
t
o
r
in
th
e
co
m
p
lex
p
r
o
ce
s
s
o
f
ch
ild
b
ir
th
[
1
9
]
.
Fro
m
Fig
u
r
e
7
we
o
b
s
er
v
e
d
th
at
t
h
e
p
r
o
p
o
s
ed
g
eo
m
etr
ic
f
ea
tu
r
e
s
et
wo
r
k
s
well
f
o
r
class
if
icatio
n
in
b
o
th
R
F
an
d
SVM
m
o
d
els,
wh
ich
s
h
o
ws
th
at
it
is
s
tr
o
n
g
.
Alth
o
u
g
h
SVM
g
iv
es
g
o
o
d
r
esu
lts
,
R
F
clas
s
if
ier
co
n
s
is
ten
tly
p
r
o
d
u
ce
s
h
ig
h
er
AUC
v
alu
es
th
an
SVM.
T
h
e
R
F
m
o
d
el
g
o
t
h
ig
h
AUC
v
alu
es:
0
.
9
9
f
o
r
ce
s
ar
ea
n
v
s
.
r
est,
0
.
9
8
f
o
r
s
p
o
n
tan
eo
u
s
v
s
.
r
est,
an
d
0
.
9
3
f
o
r
in
d
u
ce
d
v
s
.
r
est.
T
h
ese
r
e
s
u
lts
s
h
o
w
th
at
th
e
p
r
o
p
o
s
ed
f
ea
tu
r
e
s
et
ca
n
d
is
tin
g
u
is
h
am
o
n
g
all
th
r
ee
class
es
v
er
y
well,
b
u
t
it
p
er
f
o
r
m
s
a
litt
le
less
well
f
o
r
th
e
in
d
u
ce
d
class
.
Fig
u
r
e
8
illu
s
tr
ates
th
e
ef
f
ica
cy
o
f
an
R
F
in
ca
teg
o
r
izin
g
s
ev
er
al
class
es,
in
clu
d
in
g
ce
s
ar
ea
n
E
HG,
s
p
o
n
tan
eo
u
s
v
ag
in
al
E
HG,
a
n
d
f
o
r
ce
d
v
ag
in
al
d
eliv
er
y
,
wh
ich
n
ec
ess
itates
an
ex
ter
n
al
f
o
r
ce
to
g
en
e
r
ate
u
ter
in
e
co
n
tr
ac
tio
n
s
.
T
h
e
o
p
tim
al
r
esu
lts
wer
e
ac
h
iev
ed
i
n
class
if
y
in
g
s
p
o
n
ta
n
eo
u
s
v
a
g
in
al
an
d
ce
s
ar
ea
n
s
ec
tio
n
d
eliv
er
ies,
with
9
8
%
ac
cu
r
ac
y
,
9
2
%
p
r
ec
is
io
n
,
9
9
%
s
en
s
itiv
ity
,
an
d
9
5
%
F1
-
s
co
r
e.
I
n
a
s
im
ilar
m
an
n
er
,
wh
en
d
if
f
er
e
n
tiatin
g
b
etwe
en
s
p
o
n
tan
eo
u
s
v
ag
in
a
l
an
d
in
d
u
ce
d
v
ag
i
n
al
d
eliv
er
ies,
we
o
b
tain
ed
a
m
ar
g
in
ally
lo
wer
o
u
tco
m
e,
al
b
eit
s
till
an
ex
ce
llen
t r
esu
lt,
w
ith
9
6
% a
cc
u
r
ac
y
,
9
8
% p
r
ec
is
io
n
,
8
3
% sen
s
itiv
ity
,
8
9
% F1
-
s
co
r
e,
an
d
an
AUC o
f
9
8
%.
Ho
wev
er
,
th
e
g
r
ap
h
in
d
icate
s
th
at
wh
en
d
if
f
er
en
tiatin
g
b
etwe
en
ce
s
ar
ea
n
s
ec
tio
n
s
an
d
in
d
u
ce
d
v
a
g
in
al
d
eliv
er
ies,
we
ac
h
iev
ed
a
s
lig
h
tly
lo
wer
o
u
tco
m
e
with
7
0
%
ac
cu
r
ac
y
,
7
6
%
p
r
ec
is
io
n
,
7
5
%
s
en
s
itiv
ity
,
7
5
%
F1
-
s
co
r
e,
an
d
a
n
AUC
o
f
9
3
%.
Fro
m
th
e
r
esu
lts
,
we
o
b
s
er
v
ed
th
at
m
u
lti
-
class
cla
s
s
if
icatio
n
d
o
esn
'
t
wo
r
k
as
well
as
b
in
ar
y
tas
k
s
.
I
n
d
u
ce
d
an
d
ce
s
ar
ea
n
d
eliv
er
ies
m
ay
h
av
e
co
n
s
id
er
ab
le
p
h
y
s
io
lo
g
ical
o
v
er
lap
,
s
in
ce
b
o
th
m
ay
p
r
esen
t
ir
r
eg
u
lar
o
r
m
ed
ically
d
r
i
v
en
co
n
tr
ac
tio
n
p
atter
n
s
th
at
r
ed
u
ce
class
s
ep
ar
ab
ilit
y
.
T
h
e
m
o
d
el
m
ig
h
t
also
b
e
b
iased
b
ec
au
s
e
t
h
er
e
a
r
en
'
t
as
m
an
y
e
x
am
p
les
o
f
in
d
u
ce
d
a
n
d
ce
s
ar
ea
n
b
ir
th
s
,
wh
ich
m
ak
es
th
e
class
es
u
n
ev
en
.
I
t
g
ets
co
n
s
id
er
a
b
ly
h
ar
d
er
t
o
r
em
em
b
er
d
ec
is
io
n
b
o
u
n
d
ar
ies
f
o
r
th
r
ee
class
es
th
at
o
n
ly
p
ar
tially
o
v
er
lap
,
wh
ich
m
ak
es
p
er
f
o
r
m
a
n
c
e
ev
en
wo
r
s
e.
Als
o
,
m
ed
icin
al
th
er
ap
ies
lik
e
o
x
y
to
cin
d
u
r
i
n
g
f
o
r
ce
d
lab
o
r
m
ig
h
t
m
o
d
if
y
h
o
w
co
n
tr
ac
ti
o
n
s
o
cc
u
r
,
wh
ich
m
ak
es
it
to
u
g
h
er
to
p
u
t
th
em
in
to
g
r
o
u
p
s
.
T
h
e
f
in
d
i
n
g
s
h
ig
h
lig
h
t
th
e
ef
f
icac
y
o
f
th
e
b
in
ar
y
R
F
m
eth
o
d
o
lo
g
y
i
n
ac
cu
r
ately
ca
teg
o
r
izin
g
th
e
d
ataset
in
to
its
r
esp
ec
tiv
e
g
r
o
u
p
s
,
u
tili
zin
g
th
e
ch
o
s
en
f
ea
tu
r
es,
wh
ich
in
cl
u
d
e
b
o
th
g
e
o
m
etr
ical
ch
ar
ac
ter
is
t
ics
an
d
co
n
tr
ac
tio
n
-
r
elate
d
f
ac
to
r
s
.
T
h
is
m
eth
o
d
allo
we
d
u
s
to
ev
alu
ate
th
e
ef
f
icac
y
o
f
th
e
am
alg
am
atio
n
o
f
g
eo
m
etr
ical
ch
ar
ac
ter
is
tics
an
d
co
n
t
r
ac
tio
n
p
r
o
p
e
r
ties
o
f
th
e
E
HG
s
ig
n
al
in
d
is
tin
g
u
is
h
in
g
b
etwe
en
th
e
d
e
s
ig
n
ated
g
r
o
u
p
s
.
I
n
th
e
s
p
o
n
ta
n
eo
u
s
v
ag
in
al
d
eliv
er
y
g
r
o
u
p
,
co
n
tr
ac
tio
n
b
u
r
s
ts
Evaluation Warning : The document was created with Spire.PDF for Python.