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.
10
,
No
.
1
,
Feb
r
u
ar
y
2020
,
p
p
.
549
~
558
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
0
i
1
.
pp
5
4
9
-
558
549
J
o
ur
na
l
ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
Ra
ndo
m
forest ag
e esti
m
a
tion
m
o
d
el bas
ed on le
ng
th
of left
ha
nd bo
ne f
o
r
a
sia
n
po
pula
tion
M
o
hd
F
a
a
izie
Da
r
m
a
w
a
n
1
,
Ah
m
a
d F
irda
u
s
Z
a
ina
l A
b
id
in
2
,
Sh
a
hree
n K
a
s
i
m
3
,
T
o
le
Su
t
i
kn
o
4
,
Ra
h
m
a
t
B
ud
i
a
rt
o
5
1,
2
S
o
f
t
Co
m
p
u
ti
n
g
a
n
d
I
n
telli
g
e
n
t
S
y
st
e
m
(S
P
INT
),
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
y
ste
m
s &
S
o
f
t
w
a
r
e
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
M
a
lay
sia
P
a
h
a
n
g
,
K
u
a
n
tan
,
P
a
h
a
n
g
,
M
a
lay
sia
3
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
Un
iv
e
rsiti
T
u
n
Hu
ss
e
in
On
n
M
a
lay
sia
,
P
a
rit
Ra
ja,
Jo
h
o
r
,
M
a
lay
sia
4
F
a
c
u
lt
y
o
f
In
d
u
strial
T
e
c
h
n
o
l
o
g
y
,
Un
iv
e
rsitas
A
h
m
a
d
Da
h
lan
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
5
Co
ll
e
g
e
o
f
Co
m
p
u
ter an
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
A
lb
a
h
a
Un
iv
e
rsity
,
A
lb
a
h
a
,
S
a
u
d
i
A
ra
b
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
9
,
2
0
1
9
R
ev
i
s
ed
A
u
g
19
,
2
0
1
9
A
cc
ep
ted
Sep
11
,
2
0
1
9
In
f
o
re
n
sic
a
n
th
r
o
p
o
lo
g
y
,
a
g
e
e
stim
a
ti
o
n
is
u
se
d
to
e
a
se
th
e
p
ro
c
e
ss
o
f
id
e
n
ti
f
y
in
g
th
e
a
g
e
o
f
a
li
v
in
g
b
e
in
g
o
r
t
h
e
b
o
d
y
o
f
a
d
e
c
e
a
se
d
p
e
rso
n
.
No
n
e
th
e
les
s,
th
e
sp
e
c
ialty
o
f
th
e
e
sti
m
a
ti
o
n
m
o
d
e
ls
is
so
lel
y
s
u
it
a
b
le
to
a
sp
e
c
i
f
ic
p
e
o
p
le.
Co
m
m
o
n
ly
,
th
e
m
o
d
e
ls
a
re
in
ter
a
n
d
in
tra
-
o
b
se
rv
e
r
v
a
riab
il
it
y
a
s
th
e
q
u
a
li
tativ
e
se
t
o
f
d
a
ta
is
b
e
in
g
u
se
d
w
h
ich
re
su
lt
s
th
e
e
stim
a
ti
o
n
o
f
a
g
e
to
re
l
y
o
n
f
o
re
n
sic
e
x
p
e
rts.
T
h
is
stu
d
y
p
ro
p
o
se
s
a
n
a
g
e
e
sti
m
a
ti
o
n
m
o
d
e
l
b
y
u
sin
g
len
g
th
o
f
b
o
n
e
in
lef
t
h
a
n
d
o
f
A
sia
n
su
b
jec
ts
ra
n
g
e
f
ro
m
n
e
w
b
o
rn
u
p
to
1
8
-
y
e
a
r
-
o
ld
.
On
e
so
f
t
c
o
m
p
u
ti
n
g
m
o
d
e
l,
w
h
ich
is
Ra
n
d
o
m
F
o
re
st
(RF
)
is
u
se
d
to
d
e
v
e
lo
p
th
e
e
stim
a
ti
o
n
m
o
d
e
l
a
n
d
th
e
re
su
lt
s
a
re
c
o
m
p
a
re
d
w
it
h
A
rti
f
icia
l
N
e
u
ra
l
Ne
tw
o
rk
(
AN
N)
a
n
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
(S
V
M
),
d
e
v
e
lo
p
e
d
i
n
t
h
e
p
re
v
io
u
s
c
a
se
stu
d
ies
.
T
h
e
p
e
rf
o
r
m
a
n
c
e
m
e
a
su
re
m
e
n
t
u
se
d
in
th
is
stu
d
y
a
n
d
th
e
p
re
v
io
u
s
c
a
se
stu
d
y
a
re
R
-
sq
u
a
re
a
n
d
M
e
a
n
S
q
u
a
re
Err
o
r
(
M
S
E)
v
a
lu
e
.
Ba
se
d
o
n
th
e
re
su
lt
s
p
ro
d
u
c
e
d
,
t
h
e
RF
m
o
d
e
l
sh
o
w
s
c
o
m
p
a
ra
b
le
re
su
lt
s
w
it
h
th
e
A
NN
a
n
d
S
V
M
m
o
d
e
l.
F
o
r
m
a
le
su
b
jec
ts,
th
e
p
e
rf
o
rm
a
n
c
e
o
f
th
e
RF
m
o
d
e
l
is
b
e
tt
e
r
th
a
n
A
NN
,
h
o
w
e
v
e
r
le
ss
id
e
a
l
th
a
n
S
V
M
m
o
d
e
l.
A
s
f
o
r
fe
m
a
le
su
b
jec
ts,
th
e
R
F
m
o
d
e
l
o
v
e
rp
e
rf
o
m
s
b
o
t
h
A
NN
a
n
d
S
V
M
m
o
d
e
l.
Ov
e
ra
ll
,
th
e
RF
m
o
d
e
l
is
th
e
m
o
st
su
it
a
b
le
m
o
d
e
l
in
e
stim
a
ti
n
g
a
g
e
f
o
r
fe
m
a
le
su
b
jec
ts
c
o
m
p
a
re
d
to
A
N
N
a
n
d
S
VM
m
o
d
e
l,
h
o
w
e
v
e
r
f
o
r
m
a
le
su
b
jec
ts,
RF
m
o
d
e
l
is
t
h
e
se
c
o
n
d
b
e
st
m
o
d
e
l
c
o
m
p
a
re
d
to
th
e
b
o
th
m
o
d
e
ls.
Ye
t,
th
e
a
p
p
li
c
a
ti
o
n
o
f
th
is
m
o
d
e
l
is
re
stricte
d
o
n
ly
to
e
x
p
e
rim
e
n
tal
p
u
rp
o
se
o
r
f
o
re
n
sic
p
ra
c
ti
c
e
.
K
ey
w
o
r
d
s
:
Ag
e
esti
m
at
io
n
C
o
m
p
u
tatio
n
al
i
n
tell
ig
e
n
ce
Fo
r
en
s
ic
a
n
th
r
o
p
o
lo
g
y
Fu
zz
y
lo
g
ic
Han
d
b
o
n
e
Co
p
y
rig
h
t
©
2
0
2
0
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mo
h
d
Faaizie
Dar
m
a
w
a
n
,
So
f
t Co
m
p
u
ti
n
g
an
d
I
n
te
lli
g
en
t S
y
s
te
m
(
SP
I
NT
)
,
Facu
lt
y
o
f
C
o
m
p
u
ter
S
y
s
te
m
s
an
d
So
f
t
w
ar
e
E
n
g
i
n
ee
r
in
g
,
Un
i
v
er
s
iti Ma
la
y
s
ia
P
ah
an
g
,
L
eb
u
h
r
a
y
a
T
u
n
R
az
ak
,
Ga
m
b
a
n
g
,
2
6
3
0
0
,
Ku
an
tan
,
P
ah
a
n
g
,
Ma
la
y
s
ia
.
E
m
ail:
f
aa
izie
@
u
m
p
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Ag
e
esti
m
atio
n
s
er
v
e
s
a
v
ita
l
r
o
le
in
id
en
ti
f
y
in
g
t
h
e
in
d
i
v
id
u
al’
s
d
etail
s
d
u
e
to
th
e
i
n
cr
ea
s
e
o
f
h
u
m
a
n
tr
af
f
ick
i
n
g
,
as
y
l
u
m
s
ee
k
er
s
,
r
ef
u
g
ee
,
cr
i
m
i
n
al
r
esp
o
n
s
ib
ilit
y
,
ch
ild
p
o
r
n
o
g
r
ap
h
y
,
a
n
d
th
e
f
alsi
f
icatio
n
o
f
ag
e.
T
h
e
tr
ad
itio
n
al
ag
e
esti
m
a
tio
n
m
o
d
el
u
s
i
n
g
le
f
t
h
an
d
b
o
n
e
as
in
p
u
t
s
u
c
h
as
T
an
n
er
W
h
ite
h
o
u
s
e
(
T
W
)
[
1
]
an
d
Gr
eu
lic
h
an
d
P
y
le
(
GP
)
[
2
]
,
a
r
e
b
ased
o
n
q
u
alitativ
e
d
ata
wh
ich
is
t
h
e
o
b
s
er
v
atio
n
o
f
b
o
n
e
m
o
r
p
h
o
lo
g
y
f
r
o
m
a
r
ad
io
g
r
ap
h
o
f
le
f
t
h
an
d
b
y
f
o
r
en
s
ic
an
th
r
o
p
o
lo
g
is
t.
T
h
ese
m
o
d
el
s
h
av
e
d
i
s
ad
v
a
n
tag
e
s
i
n
w
h
ic
h
t
h
e
m
o
d
el
s
ar
e
co
n
s
id
er
ab
le
in
tr
a
an
d
in
t
er
-
o
b
s
er
v
er
v
ar
iab
ilit
y
w
h
er
e
th
e
esti
m
ated
a
g
e
d
ef
i
n
itel
y
r
elies
o
n
t
h
e
f
o
r
en
s
i
c
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.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
549
-
558
550
ex
p
er
t.
T
h
er
ef
o
r
e,
d
if
f
er
en
t
ex
p
er
ts
w
it
h
d
i
f
f
er
e
n
t
e
x
p
er
ien
ce
le
v
els
w
i
l
l
m
o
s
t
l
ik
el
y
p
r
o
d
u
ce
a
g
r
ea
ter
v
ar
iet
y
o
f
in
tr
a
-
o
b
s
er
v
er
,
wh
ich
is
d
if
f
er
e
n
t
p
r
ed
icted
ag
e
w
i
ll
b
e
p
r
o
d
u
ce
d
b
y
t
h
e
d
if
f
er
en
t
ex
p
er
ts
.
T
h
u
s
,
th
e
ac
c
u
r
ac
y
o
f
b
o
n
e
a
g
e
ass
es
s
m
e
n
t i
s
v
er
y
i
m
p
o
r
tan
t
.
T
h
er
e
ar
e
s
ev
er
al
ca
s
e
s
tu
d
ies
th
at
u
s
ed
m
ea
s
u
r
e
m
e
n
t
o
f
h
a
n
d
b
o
n
e
(
q
u
an
titati
v
e
d
ata)
a
s
in
p
u
t
f
o
r
ag
e
est
i
m
a
tio
n
[
3
-
7
]
.
A
ll
th
e
ca
s
e
s
t
u
d
ies
h
a
v
e
p
r
o
v
ed
th
at
th
e
m
ea
s
u
r
e
m
en
t
o
f
t
h
e
h
a
n
d
b
o
n
e
is
ab
le
to
b
e
u
tili
ze
d
as
i
n
d
icato
r
f
o
r
ag
e
esti
m
a
tio
n
.
T
h
is
s
t
u
d
y
c
h
o
o
s
es
th
e
le
n
g
th
o
f
h
a
n
d
b
o
n
e
as
an
alter
n
at
iv
e
p
ar
am
eter
f
o
r
ag
e
esti
m
at
io
n
.
On
t
h
e
o
th
er
h
a
n
d
,
So
f
t
c
o
m
p
u
ti
n
g
m
o
d
els
s
u
ch
a
s
A
N
N,
SVM
an
d
R
F
ar
e
p
r
o
v
ed
r
eliab
le
to
b
e
u
s
ed
o
n
q
u
a
n
tita
tiv
e
d
ata
esp
ec
iall
y
f
o
r
p
r
ed
ictio
n
,
clas
s
i
f
icatio
n
an
d
o
p
ti
m
izatio
n
p
r
o
b
lem
[
6
-
1
3
]
.
T
h
u
s
,
t
h
is
s
t
u
d
y
ad
o
p
ts
an
d
i
m
p
le
m
e
n
ts
t
h
e
R
F
m
o
d
el
o
n
th
e
le
n
g
t
h
o
f
h
a
n
d
b
o
n
e
d
ata
to
pe
r
f
o
r
m
ag
e
e
s
ti
m
atio
n
.
I
n
o
r
d
er
to
ev
alu
ate
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el,
th
is
w
o
r
k
co
m
p
ar
es
th
e
ac
c
u
r
ac
y
r
es
u
lt
s
f
r
o
m
t
h
e
ex
p
er
i
m
e
n
ts
w
it
h
e
x
is
ti
n
g
ANN
m
o
d
el
a
n
d
SVM
m
o
d
el
t
h
at
u
s
ed
t
h
e
s
a
m
e
d
ataset
in
tr
o
d
u
ce
d
in
[
6
]
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Re
s
ea
rc
h m
a
t
er
ia
ls
A
s
u
m
o
f
t
h
r
ee
h
u
n
d
r
ed
an
d
th
ir
t
y
th
r
ee
X
-
r
a
y
s
ca
n
s
o
f
Asi
an
s
’
le
f
t
-
h
an
d
b
o
n
es,
1
6
6
o
f
th
e
m
ar
e
m
ale
an
d
1
6
7
ar
e
f
e
m
ale,
w
e
r
e
tak
en
f
r
o
m
t
h
e
o
n
li
n
e
d
ataset
[
1
4
]
.
T
h
e
ag
es
r
an
g
e
b
et
wee
n
n
e
w
b
o
r
n
to
1
8
y
ea
r
s
o
ld
.
Ag
e
d
is
tr
ib
u
tio
n
f
o
r
th
ese
s
u
b
j
ec
ts
is
ill
u
s
tr
ated
in
T
ab
le
1
.
T
h
is
o
n
li
n
e
d
atas
et
co
n
s
i
s
ts
o
f
f
o
u
r
p
o
p
u
latio
n
s
w
h
ic
h
ar
e
A
s
ian
,
His
p
an
ic,
Af
r
ica
n
Am
er
ican
a
n
d
C
a
u
ca
s
ia
n
a
n
d
h
a
s
b
ee
n
u
s
ed
f
o
r
m
a
n
y
ca
s
e
s
tu
d
ie
s
s
u
c
h
as
i
n
[
1
5
-
18]
.
T
h
e
d
ataset
co
m
p
r
is
e
s
o
f
i
n
d
iv
id
u
als
b
elo
w
2
0
y
ea
r
s
o
ld
w
i
th
o
u
t
a
n
y
r
ec
o
r
d
o
f
b
o
n
e
p
r
o
b
lem
o
r
b
o
n
e
d
is
ea
s
e
,
f
o
r
in
s
ta
n
ce
f
r
ac
tu
r
es,
o
s
teo
ar
th
r
itis
,
r
h
e
u
m
a
to
id
ar
th
r
iti
s
,
b
o
n
e
ca
n
ce
r
o
r
o
th
er
p
r
o
b
lem
s
a
s
s
o
ciate
d
w
it
h
g
e
n
etic
.
Du
e
to
th
e
f
ac
t
t
h
at
b
o
n
e
s
w
it
h
s
u
ch
p
r
o
b
le
m
s
h
a
v
e
h
i
g
h
er
t
e
n
d
en
c
y
to
b
e
w
ea
k
,
b
r
is
tled
,
m
i
s
s
h
ap
ed
an
d
b
r
o
k
en
ea
s
il
y
th
at
co
u
ld
lea
d
to
in
ac
c
u
r
ate
m
ea
s
u
r
e
m
e
n
t
s
,
th
o
s
e
b
o
n
e
s
w
er
e
ex
clu
d
ed
i
n
t
h
e
s
tu
d
y
.
T
h
e
s
o
u
r
ce
o
f
t
h
e
s
e
x
-
r
a
y
s
ca
n
s
w
as
f
r
o
m
C
h
ild
r
en
’
s
Ho
s
p
ital
L
o
s
An
g
ele
s
to
g
eth
er
w
it
h
d
e
m
o
g
r
ap
h
ic
d
ata
o
f
p
atien
ts
a
n
d
r
ea
d
in
g
b
y
r
ad
io
lo
g
is
ts
,
ass
ig
n
ed
i
n
to
19
g
r
o
u
p
s
(
n
e
w
-
b
o
r
n
,
1
to
1
8
y
ea
r
s
o
ld
)
f
o
r
b
o
th
m
al
e
an
d
f
e
m
ale.
T
h
e
d
etails o
f
ea
ch
s
u
b
j
ec
t; th
e
i
m
ag
e
n
a
m
e,
th
e
r
ac
e,
th
e
g
e
n
d
er
,
th
e
ch
r
o
n
o
lo
g
ica
l
ag
e
,
th
e
d
ate
o
f
b
ir
th
(
DOB
)
,
th
e
ex
a
m
d
ate,
th
e
h
eig
h
t
(
c
m
)
,
th
e
w
ei
g
h
t
(
k
g
)
,
th
e
tr
u
n
k
(
c
m
)
,
th
e
r
ea
d
in
g
1
,
an
d
th
e
r
ea
d
in
g
2
,
w
er
e
p
er
f
ec
t
l
y
d
o
cu
m
e
n
ted
f
o
r
r
ef
er
e
n
ce
an
d
v
alid
atio
n
p
u
r
p
o
s
e.
Fo
r
th
e
r
ec
o
r
d
,
s
ev
er
al
p
r
ev
io
u
s
ca
s
e
s
t
u
d
ies
also
h
av
e
u
s
ed
th
i
s
d
a
tase
t
to
d
ev
e
lo
p
ag
e
est
i
m
a
tio
n
m
o
d
el
[
6
,
7
,
1
7
,
18]
.
T
ab
le
1
.
Six
ag
e’
g
r
o
u
p
s
w
it
h
its
p
ar
tic
u
lar
s
u
b
j
ec
t’
s
ag
e
d
i
s
t
r
ib
u
tio
n
A
g
e
’
g
r
o
u
p
(
y
e
a
r
)
1
6
-
18
4
-
6
1
3
-
15
7
-
9
4
-
6
N
e
w
b
o
r
n
-
3
T
o
t
a
l
F
e
mal
e
16
19
23
41
38
30
1
6
7
M
a
l
e
17
20
18
44
37
30
1
6
6
A
cc
o
r
d
in
g
to
th
e
s
tr
u
ct
u
r
e
o
f
a
h
an
d
b
o
n
e,
it
is
ca
te
g
o
r
ized
in
to
f
o
u
r
p
ar
ts
,
to
b
e
s
p
ec
if
ic,
p
r
o
x
i
m
al
p
h
alan
x
,
th
e
d
i
s
tal
p
h
ala
n
x
,
m
etac
ar
p
al
an
d
m
id
d
le
p
h
alan
x
.
T
h
r
ee
o
u
t
o
f
f
o
u
r
g
r
o
u
p
s
c
o
n
s
is
t
o
f
f
iv
e
b
o
n
e
s
ea
ch
w
h
i
le
an
o
th
er
g
r
o
u
p
,
m
id
d
le
p
h
alan
x
g
r
o
u
p
h
as
f
o
u
r
b
o
n
es.
T
h
er
ef
o
r
e,
th
e
s
u
m
o
f
b
o
n
es
f
o
u
n
d
in
a
h
a
n
d
is
1
9
.
T
h
r
o
u
g
h
o
u
t
ch
ild
h
o
o
d
an
d
ad
o
lescen
ce
p
h
a
s
es,
t
h
e
l
ef
t
h
a
n
d
’
s
b
o
n
e
d
ev
elo
p
m
e
n
t
c
an
b
e
p
ar
titi
o
n
ed
in
to
s
i
x
i
m
p
o
r
tan
t
s
ta
g
es
.
T
h
e
f
ir
s
t
s
ta
g
e
w
o
u
ld
b
e
t
h
e
i
n
f
an
c
y
(
n
e
w
b
o
r
n
to
1
0
m
o
n
t
h
s
f
o
r
f
e
m
ale,
n
e
w
b
o
r
n
to
1
4
m
o
n
t
h
s
f
o
r
m
ale)
,
f
o
llo
w
e
d
b
y
th
e
s
ec
o
n
d
s
ta
g
e
w
h
ic
h
is
th
e
t
o
d
d
ler
(
1
0
m
o
n
t
h
s
to
2
y
ea
r
s
f
o
r
f
e
m
ale,
1
4
m
o
n
t
h
s
to
3
y
ea
r
s
f
o
r
m
ale
)
,
an
d
th
e
th
ir
d
s
tag
e
w
h
ich
i
s
p
re
-
p
u
b
er
ty
(
2
–
7
y
ea
r
s
f
o
r
f
e
m
ale,
3
–
9
y
ea
r
s
f
o
r
m
ale)
,
an
d
th
e
f
o
u
r
t
h
s
ta
g
e
wh
ich
i
s
t
h
e
e
ar
l
y
an
d
m
id
-
p
u
b
er
t
y
(
7
–
1
3
y
ea
r
s
f
o
r
f
e
m
ale,
9
–
1
4
y
ea
r
s
f
o
r
m
a
le)
,
th
en
t
h
e
f
if
th
s
ta
g
e
w
h
ic
h
i
s
th
e
l
a
te
p
u
b
er
t
y
(
1
3
–
1
5
y
ea
r
s
f
o
r
f
e
m
a
le,
1
4
–
1
6
y
ea
r
s
f
o
r
m
a
le)
an
d
,
la
s
tl
y
th
e
s
i
x
t
h
s
ta
g
e
w
h
ich
i
s
th
e
p
o
s
t
-
p
u
b
er
t
y
(
1
5
–
1
7
y
ea
r
s
f
o
r
f
e
m
ale,
1
6
–
1
9
y
ea
r
s
f
o
r
m
ale)
.
T
o
g
au
g
e
e
v
er
y
le
n
g
t
h
o
f
b
o
n
e
in
ea
ch
s
ta
g
e,
s
o
f
t
w
ar
e
o
f
p
h
o
to
m
a
n
a
g
er
w
as
u
tili
ze
d
to
q
u
an
ti
f
y
al
l
th
e
n
i
n
etee
n
b
o
n
es
b
y
m
a
k
i
n
g
a
lin
e
i
n
ea
ch
b
o
n
e,
b
eg
in
n
in
g
f
r
o
m
t
h
e
b
ase
-
ce
n
ter
p
o
in
t
to
th
e
en
d
-
ce
n
ter
p
o
in
t
o
f
t
h
e
b
o
n
e
o
n
e
v
er
y
X
-
r
a
y
i
m
a
g
e,
an
d
it
co
n
s
eq
u
en
tl
y
cr
ea
ted
th
e
le
n
g
t
h
o
f
t
h
e
li
n
e
i
n
ce
n
ti
m
etr
e
(
c
m
)
.
T
h
e
lin
e
w
as
m
ad
e
b
y
d
i
s
r
eg
ar
d
in
g
th
e
ep
ip
h
y
s
ea
l
(
if
it
h
a
p
p
en
ed
)
in
t
h
e
b
o
n
e
f
o
r
in
f
a
n
c
y
s
tag
e.
T
h
e
li
n
es
w
er
e
m
ad
e
f
o
r
o
th
er
p
h
r
a
s
es
b
y
in
co
r
p
o
r
atin
g
th
e
ep
ip
h
y
s
e
al
r
eg
ar
d
less
o
f
j
u
s
t
a
s
m
al
l
e
p
ip
h
y
s
ea
l
ill
u
s
tr
ated
in
th
e
p
ict
u
r
es.
Fig
u
r
e
1
d
em
o
n
s
tr
ates
a
ca
s
e
o
f
m
ea
s
u
r
in
g
th
e
len
g
th
o
f
th
e
b
o
n
e
w
h
ic
h
b
elo
n
g
s
to
a
m
ale
s
u
b
j
ec
t
f
o
r
ea
ch
s
tag
e
f
r
o
m
h
is
X
-
r
a
y
i
m
ag
e
w
it
h
th
e
h
el
p
o
f
th
e
s
o
f
t
w
ar
e.
Fo
r
ex
p
er
i
m
en
t
an
d
a
n
al
y
s
i
s
p
u
r
p
o
s
e
s
,
ev
er
y
s
i
n
g
le
m
ea
s
u
r
ed
d
ata
f
r
o
m
t
h
e
i
m
ag
e
s
w
as
t
h
en
o
r
g
a
n
ized
in
a
s
p
r
ea
d
s
h
ee
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
R
a
n
d
o
m
f
o
r
est a
g
e
esti
ma
tio
n
mo
d
el
b
a
s
ed
o
n
le
n
g
th
o
f le
ft
h
a
n
d
b
o
n
e
fo
r
…
(
Mo
h
d
F
a
a
iz
ie
Da
r
ma
w
a
n
)
551
I
n
f
a
n
c
y
T
o
d
d
ler
s
P
r
e
-
p
u
b
er
ty
E
ar
ly
a
n
d
Mid
-
p
u
b
er
t
y
L
ate
P
u
b
er
t
y
P
o
s
t
-
p
u
b
er
t
y
Fig
u
r
e
1
.
T
h
e
cr
ea
ted
lin
es
w
it
h
its
p
ar
ticu
lar
m
ea
s
u
r
e
m
en
t i
n
ce
n
ti
m
eter
,
f
o
r
ev
er
y
b
o
n
e
i
n
th
e
le
f
t
h
an
d
f
o
r
ea
ch
p
h
ase
o
f
b
o
n
e
d
ev
e
lo
p
m
e
n
t
B
ef
o
r
e
th
e
p
r
o
p
o
s
ed
m
o
d
el
d
ev
elo
p
ed
,
th
e
n
o
r
m
aliza
tio
n
o
f
d
ata
n
ee
d
to
b
e
d
o
n
e.
T
h
e
d
etails
o
f
th
e
d
ata
n
o
r
m
aliza
tio
n
ar
e
d
es
cr
ib
ed
in
th
e
n
ex
t
s
ec
tio
n
.
Data
n
o
r
m
a
lizatio
n
is
f
r
eq
u
en
tl
y
co
n
d
u
cted
p
r
io
r
t
o
th
e
p
r
o
ce
s
s
o
f
te
s
ti
n
g
a
n
d
tr
ain
in
g
s
tar
ts
.
I
t
is
f
ea
s
ib
le
to
s
ta
n
d
ar
d
ize
th
e
in
p
u
t
an
d
o
u
tp
u
t
to
a
s
tan
d
ar
d
r
an
g
e,
f
o
r
ex
a
m
p
le,
-
1
to
1
o
r
0
to
1
.
Fu
n
d
a
m
e
n
tall
y
,
w
h
i
le
n
o
n
l
in
ea
r
tr
an
s
f
er
f
u
n
ct
io
n
s
,
f
o
r
in
s
ta
n
ce
,
th
e
lo
g
i
s
tic
s
ig
m
o
id
f
u
n
ct
io
n
ar
e
u
tili
ze
d
at
th
e
o
u
tp
u
t
n
o
d
es,
th
e
d
esire
d
o
u
tp
u
t
v
alu
e
s
n
ee
d
to
b
e
ch
a
n
g
ed
in
to
th
e
s
co
p
e
o
f
th
e
in
itial
o
u
tp
u
t
o
f
th
e
s
y
s
te
m
.
R
e
g
ar
d
less
o
f
t
h
e
p
o
s
s
ib
ilit
y
t
h
at
a
lin
ea
r
o
u
tp
u
t
t
r
an
s
f
er
f
u
n
ctio
n
is
u
tili
ze
d
,
it
is
y
et
b
e
n
ef
icial
t
o
n
o
r
m
alize
t
h
e
o
u
tp
u
t
s
a
n
d
ad
d
itio
n
all
y
t
h
e
i
n
p
u
ts
to
p
r
e
v
en
t
co
m
p
u
tatio
n
al
is
s
u
es.
T
o
s
tan
d
ar
d
ize
th
e
g
a
th
er
ed
len
g
th
o
f
t
h
e
b
o
n
e,
th
e
n
o
r
m
aliza
tio
n
eq
u
atio
n
f
r
o
m
p
r
ev
io
u
s
s
t
u
d
ies
[
1
9
,
20]
w
as
u
s
ed
w
h
ic
h
is
illu
s
tr
ated
in
E
q
u
atio
n
1
,
w
h
er
e
r
ef
er
s
to
th
e
it
h
in
p
u
t/o
u
tp
u
t
d
ata,
r
ef
er
s
to
t
h
e
m
i
n
i
m
u
m
v
al
u
e
o
f
th
e
i
n
p
u
t/o
u
tp
u
t
d
ata
a
n
d
r
ef
er
s
to
t
h
e
m
ax
i
m
u
m
v
al
u
e
o
f
t
h
e
i
n
p
u
t/
o
u
tp
u
t d
ata.
(
)
(
1
)
T
ab
le
2
illu
s
tr
ates
a
n
i
n
s
ta
n
c
e
o
f
th
e
m
ea
s
u
r
ed
d
ata
g
ath
e
r
ed
f
r
o
m
t
h
e
late
p
u
b
er
t
y
x
-
r
a
y
s
ca
n
s
i
n
Fig
u
r
e
1
af
ter
n
o
r
m
a
lizatio
n
.
I
n
th
i
s
s
t
u
d
y
,
t
h
e
s
u
m
to
tal
o
f
X
-
r
a
y
s
ca
n
s
f
o
r
b
o
th
m
ale
an
d
f
e
m
ale
is
3
3
3
,
it
m
ea
n
s
ea
ch
X
-
r
a
y
s
ca
n
h
as
3
3
3
d
is
tin
cti
v
e
tab
les,
lik
e
t
h
e
o
n
e
ap
p
ea
r
ed
in
T
ab
le
2
.
S
m
all
d
ata
s
et
s
ar
e
in
s
u
f
f
icien
t
f
o
r
in
v
e
s
ti
g
atio
n
s
.
T
o
o
v
er
co
m
e
th
is
cir
cu
m
s
tan
ce
,
it
co
m
es
to
th
e
u
s
e
o
f
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
alg
o
r
ith
m
o
n
R
F
m
o
d
el
.
T
h
e
u
s
e
o
f
th
is
alg
o
r
it
h
m
ai
m
s
to
s
ep
ar
ate
th
e
en
tire
ex
p
er
i
m
e
n
t
s
in
to
t
w
o
s
ec
t
io
n
s
w
h
ic
h
ar
e
t
h
e
tr
ai
n
i
n
g
an
d
tes
tin
g
s
e
ts
.
T
h
e
p
r
ev
io
u
s
o
n
e
i
s
u
tili
ze
d
to
co
n
s
tr
u
ct
t
h
e
m
o
d
e
l
w
h
er
ea
s
t
h
e
latter
is
to
v
alid
ate
th
e
m
o
d
el.
T
h
e
t
w
o
p
ar
ts
n
ee
d
to
tr
av
er
s
e
i
n
p
r
o
g
r
ess
i
v
e
iter
atio
n
s
.
T
en
s
i
m
ilar
l
y
(
r
o
u
g
h
l
y
)
s
ized
s
ets
w
er
e
d
i
v
id
ed
f
r
o
m
th
e
en
tire
s
a
m
p
le
in
f
o
r
m
at
io
n
in
ea
ch
g
r
o
u
p
,
in
w
h
ic
h
e
v
er
y
g
r
o
u
p
co
n
f
ir
m
ed
a
f
e
w
i
m
p
ac
t
p
lace
s
i
n
ev
er
y
d
iv
is
io
n
.
Fo
r
ev
er
y
iter
atio
n
,
o
n
l
y
o
n
e
s
et
w
a
s
s
elec
ted
f
o
r
test
in
g
w
h
e
r
ea
s
th
e
r
es
t
w
er
e
c
h
o
s
e
n
f
o
r
tr
ai
n
i
n
g
.
T
h
e
MSE
v
al
u
es
w
er
e
d
eli
v
er
ed
f
r
o
m
t
h
e
te
s
ti
n
g
d
ata
i
n
ea
ch
iter
atio
n
,
a
n
d
th
e
a
v
er
ag
e
o
f
MSE
w
as
t
h
e
n
f
i
g
u
r
ed
as
th
e
p
er
f
o
r
m
a
n
ce
f
o
r
ea
ch
o
f
t
h
e
s
o
f
t
co
m
p
u
ti
n
g
m
o
d
el.
T
h
e
MSE
s
f
r
o
m
ea
c
h
m
o
d
el
w
er
e
t
h
en
p
r
esen
ted
i
n
a
tab
le
f
o
r
s
u
m
m
ar
izatio
n
.
Af
ter
t
h
at,
co
m
p
ar
is
o
n
w
a
s
m
ad
e
to
d
eter
m
in
e
t
h
e
b
est
m
o
d
el
t
h
at
ca
n
b
e
u
s
ed
f
o
r
ag
e
es
ti
m
a
tio
n
.
T
h
e
MSE
v
alu
e
is
c
h
o
s
en
b
e
ca
u
s
e
t
h
e
p
r
ev
io
u
s
ca
s
e
s
tu
d
y
th
a
t u
s
ed
A
N
N
an
d
SVM
also
ap
p
lied
MSE
as p
er
f
o
r
m
an
ce
f
u
n
ct
io
n
i
n
h
i
s
w
o
r
k
[
6
]
.
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.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
549
-
558
552
T
ab
le
2
.
Me
asu
r
e
m
en
t o
f
x
-
r
a
y
i
m
a
g
e
f
r
o
m
late
p
u
b
er
t
y
p
h
a
s
e
in
Fi
g
u
r
e
2
af
ter
n
o
r
m
al
izat
io
n
o
f
d
ata
F
i
n
g
e
r
1
st
2
nd
3
rd
4
th
5
th
M
e
t
a
c
a
r
p
a
l
0
.
8
5
6
6
0
.
7
8
4
7
0
.
7
5
1
2
0
.
7
7
1
7
0
.
7
5
8
7
P
r
o
x
i
mal
P
h
a
l
a
n
x
0
.
8
3
6
4
0
.
8
2
4
7
0
.
7
6
3
8
0
.
7
8
5
9
0
.
8
1
7
3
D
i
st
a
l
P
h
a
l
a
n
x
0
.
8
0
3
7
0
.
7
8
0
1
0
.
8
3
9
9
0
.
8
1
5
5
0
.
7
7
0
2
M
i
d
d
l
e
P
h
a
l
a
n
x
-
0
.
8
4
4
6
0
.
7
7
3
4
0
.
7
1
3
0
0
.
7
3
1
5
2
.
2
.
Ra
nd
o
m
f
o
re
s
t
R
an
d
o
m
Fo
r
est
(
R
F)
m
o
d
el
is
d
e
v
elo
p
ed
b
y
L
eo
B
r
ei
m
an
[
2
1
]
w
h
er
e
th
e
R
F
h
as
t
u
r
n
ed
i
n
to
a
s
tan
d
ar
d
in
f
o
r
m
atio
n
a
n
al
y
s
is
d
ev
ice
i
n
b
io
in
f
o
r
m
atic
s
.
I
t
h
as
d
e
m
o
n
s
tr
ated
o
u
ts
ta
n
d
i
n
g
p
er
f
o
r
m
an
ce
i
n
s
etti
n
g
s
w
h
er
e
th
e
q
u
a
n
tit
y
of
o
b
s
er
v
atio
n
s
is
m
u
c
h
s
m
aller
th
an
th
e
n
u
m
b
er
o
f
v
ar
iab
les
in
w
h
ic
h
co
m
p
lica
ted
in
ter
ac
tio
n
s
tr
u
ct
u
r
es
ca
n
b
e
co
p
ed
w
ell
w
it
h
as
w
ell
a
s
i
m
m
e
n
s
e
l
y
co
r
r
elate
d
v
ar
iab
les
an
d
r
etu
r
n
s
m
ea
s
u
r
es
o
f
v
ar
iab
le
im
p
o
r
ta
n
ce
[
2
2
]
.
R
F
is
a
r
eg
r
e
s
s
io
n
a
n
d
class
i
f
icatio
n
m
o
d
el
in
ac
co
r
d
an
ce
w
it
h
th
e
co
llectio
n
o
f
a
n
ex
te
n
s
iv
e
q
u
an
tit
y
o
f
d
ec
is
io
n
tr
ee
s
.
I
n
p
ar
ticu
lar
,
it
is
an
ag
g
r
eg
a
tio
n
o
f
tr
ee
s
b
u
ilt
f
r
o
m
a
tr
ain
i
n
g
d
ata
s
et
a
n
d
i
n
ter
n
all
y
v
er
i
f
ied
to
p
r
o
d
u
ce
a
f
o
r
ec
ast
o
f
t
h
e
r
ea
ctio
n
p
r
o
v
id
ed
th
e
p
r
ed
icto
r
s
f
o
r
f
u
tu
r
e
o
b
s
er
v
atio
n
s
.
T
h
e
f
lo
w
o
f
t
h
e
d
ev
elo
p
m
en
t
o
f
R
F
m
o
d
el
f
o
r
a
g
e
e
s
ti
m
atio
n
i
s
s
h
o
w
n
i
n
F
ig
u
r
e
2
.
R
F
m
o
d
el
n
ee
d
s
s
elec
ti
n
g
p
ar
a
m
eter
m
,
th
e
n
u
m
b
er
o
f
v
ar
iab
les
(
a
s
u
b
s
e
t
o
f
av
ailab
le
P
p
r
e
d
icto
r
v
ar
iab
le
s
)
w
h
ich
is
u
tili
ze
d
to
id
en
ti
f
y
th
e
d
ec
is
io
n
at
a
n
o
d
e
o
f
t
h
e
tr
ee
.
Se
v
er
al
s
tu
d
ie
s
[
2
3
,
2
4
]
h
av
e
u
s
ed
t
h
e
s
q
u
ar
e
r
o
o
t
o
f
th
e
n
u
m
b
er
o
f
in
p
u
t
v
ar
iab
les
to
d
eter
m
in
e
th
e
v
al
u
e
o
f
m
,
as
s
u
g
g
ested
b
y
B
r
ei
m
an
.
B
r
ei
m
an
also
s
u
g
g
ested
t
h
e
v
al
u
e
o
f
m
to
b
e
th
e
f
ir
s
t
in
te
g
er
le
s
s
t
h
an
,
w
h
er
e
P
is
t
h
e
n
u
m
b
er
o
f
in
p
u
t
v
ar
iab
les.
T
h
e
o
p
ti
m
a
l
v
alu
e
f
o
r
m
ca
n
also
b
e
id
en
ti
f
ied
b
y
t
h
e
tu
n
eR
F
f
u
n
ct
io
n
o
f
t
h
e
R
-
s
o
f
t
w
ar
e.
R
-
s
o
f
t
w
ar
e
is
a
f
r
ee
s
o
f
t
w
ar
e
th
at
o
f
f
er
s
a
w
id
e
as
s
o
r
t
m
e
n
t
o
f
s
tati
s
tica
l
li
n
ea
r
an
d
n
o
n
lin
ea
r
m
o
d
elli
n
g
,
clas
s
i
f
icatio
n
,
ti
m
e
-
s
er
ies
an
al
y
s
is
,
cl
u
s
ter
i
n
g
,
g
r
ap
h
ical
tec
h
n
iq
u
es
a
n
d
cla
s
s
ical
s
tatis
tical
te
s
ts
,
a
n
d
is
v
er
y
e
x
te
n
d
ab
le.
Tu
n
eR
F
f
u
n
ct
io
n
s
tar
ts
w
it
h
th
e
d
ef
a
u
lt
v
al
u
e
o
f
m
,
an
d
t
h
en
s
ea
r
c
h
es
f
o
r
th
e
o
p
ti
m
al
v
a
lu
e
(
w
it
h
r
esp
ec
t
to
o
u
t
-
of
-
b
a
g
er
r
o
r
esti
m
a
te)
o
f
m
f
o
r
R
F
m
o
d
el.
I
n
t
h
is
s
t
u
d
y
,
th
e
m
v
al
u
e
w
as c
h
o
s
e
n
u
s
in
g
th
e
th
r
ee
m
et
h
o
d
s
ab
o
v
e.
Fig
u
r
e
2
.
T
h
e
d
ev
elo
p
m
en
t o
f
R
F
m
o
d
el
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
R
a
n
d
o
m
f
o
r
est a
g
e
esti
ma
tio
n
mo
d
el
b
a
s
ed
o
n
le
n
g
th
o
f le
ft
h
a
n
d
b
o
n
e
fo
r
…
(
Mo
h
d
F
a
a
iz
ie
Da
r
ma
w
a
n
)
553
T
h
e
s
ec
o
n
d
p
ar
am
eter
r
eq
u
ir
ed
b
y
R
F
is
t
h
e
n
u
m
b
er
o
f
tr
e
es,
t.
T
h
is
s
tu
d
y
u
s
e
s
f
o
u
r
v
a
lu
es
f
o
r
t,
w
h
ic
h
ar
e
1
0
0
,
2
0
0
,
5
0
0
,
an
d
1
0
0
0
.
T
h
e
co
m
b
in
a
tio
n
o
f
t
h
e
s
e
p
ar
a
m
eter
s
w
ill
d
ev
e
lo
p
R
F
’
s
s
tr
u
c
tu
r
e
u
s
ed
to
esti
m
ate
ag
e.
So
,
th
e
co
m
b
i
n
at
io
n
s
o
f
t
h
e
p
ar
a
m
eter
s
u
s
ed
w
i
ll
p
r
o
d
u
ce
t
w
elv
e
R
F
’
s
s
tr
u
ct
u
r
e
w
h
ic
h
is
s
h
o
w
n
in
T
ab
le
3
.
T
h
en
,
ea
ch
R
F
’
s
s
t
r
u
ctu
r
e
w
i
ll
p
r
o
d
u
ce
R
-
s
q
u
ar
e
v
al
u
e
a
n
d
MSE
v
al
u
e
f
o
r
b
o
th
m
ale
a
n
d
f
e
m
a
le.
A
ll
t
h
ese
v
a
lu
e
s
al
s
o
ar
e
s
h
o
w
n
i
n
th
e
s
a
m
e
tab
le.
T
h
e
b
e
s
t
R
F
’
s
s
tr
u
ct
u
r
es
ac
co
r
d
in
g
t
o
th
e
R
-
s
q
u
ar
e
an
d
MSE
v
al
u
es
w
er
e
th
e
n
s
elec
ted
b
y
co
m
p
ar
in
g
ea
c
h
R
F’s
s
tr
u
ct
u
r
e
an
d
t
h
e
n
co
m
p
iled
in
to
T
ab
le
4
f
o
r
co
m
p
ar
is
o
n
p
u
r
p
o
s
e
w
it
h
th
e
A
N
N
an
d
SVM
p
r
o
d
u
ce
d
b
y
t
h
e
p
r
ev
io
u
s
ca
s
e
s
t
u
d
y
i
n
[
6
]
.
T
ab
le
3
.
R
-
s
q
u
ar
e
an
d
MSE
v
alu
es
f
o
r
d
if
f
er
e
n
t n
u
m
b
er
o
f
t
r
ee
s
(
t)
an
d
n
u
m
b
er
o
f
v
ar
iab
les (
m
)
u
s
in
g
R
F f
o
r
n
e
w
b
o
r
n
to
1
8
y
ea
r
s
o
ld
N
u
mb
e
r
o
f
t
r
e
e
s (t
)
N
u
mb
e
r
o
f
V
a
r
i
a
b
l
e
s (m
)
M
a
l
e
F
e
mal
e
R
-
sq
u
a
r
e
M
S
E
R
-
sq
u
a
r
e
M
S
E
1
0
0
4
0
.
9
1
1
2
.
0
2
2
0
.
8
4
0
3
.
5
5
1
5
0
.
9
1
1
2
.
0
2
7
0
.
8
4
2
3
.
5
2
4
12
0
.
9
1
3
1
.
9
7
7
0
.
8
4
4
3
.
4
8
1
2
0
0
4
0
.
9
1
4
1
.
9
5
8
0
.
8
4
3
3
.
4
9
7
5
0
.
9
1
2
2
.
0
0
0
0
.
8
4
4
3
.
4
7
0
12
0
.
9
0
9
2
.
0
6
4
0
.
8
4
1
3
.
5
3
9
5
0
0
4
0
.
9
1
1
2
.
0
1
3
0
.
8
4
4
3
.
4
7
5
5
0
.
9
1
2
1
.
9
9
5
0
.
8
4
2
3
.
5
0
7
12
0
.
9
1
1
2
.
0
2
7
0
.
8
4
3
3
.
4
9
8
1
0
0
0
4
0
.
9
1
3
1
.
9
8
8
0
.
8
4
6
3
.
4
3
8
5
0
.
9
1
2
2
.
0
0
2
0
.
8
4
4
3
.
4
7
7
12
0
.
9
1
2
1
.
9
9
4
0
.
8
4
5
3
.
4
5
5
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
ab
le
3
illu
s
tr
ates
t
h
e
r
es
u
lt
s
o
f
ag
e
es
ti
m
atio
n
i
n
t
h
e
f
o
r
m
o
f
R
-
s
q
u
ar
e
v
al
u
es
a
n
d
MSE
v
alu
e
s
f
o
r
b
o
th
m
ale
a
n
d
f
e
m
ale,
f
o
r
ea
ch
R
F’s
s
tr
u
ct
u
r
e.
T
h
e
tab
le
r
e
v
ea
ls
t
h
at
R
F
’
s
s
tr
u
ct
u
r
e
w
it
h
n
u
m
b
er
o
f
tr
ee
2
0
0
an
d
n
u
m
b
er
o
f
v
ar
iab
le
4
is
t
h
e
b
est
R
F
’
s
s
tr
u
ct
u
r
e
w
h
ic
h
p
r
o
d
u
ce
d
th
e
g
r
ea
test
R
-
s
q
u
ar
e
v
alu
e
o
f
0
.
9
1
4
an
d
lo
w
es
t
MSE
v
al
u
e
o
f
1
.
9
5
8
f
o
r
m
ale,
w
h
ile
f
o
r
f
e
m
ale,
R
F
’
s
s
tr
u
ct
u
r
e
w
it
h
n
u
m
b
er
o
f
tr
ee
1
0
0
0
an
d
n
u
m
b
er
o
f
v
ar
iab
le
4
is
t
h
e
b
est
s
tr
u
c
t
u
r
e
w
h
ic
h
p
r
o
d
u
ce
d
R
-
s
q
u
ar
e
v
alu
e
o
f
0
.
8
4
6
an
d
MSE
v
al
u
e
o
f
3
.
4
3
8
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
g
r
ap
h
o
f
p
r
ed
icted
ag
e
p
r
o
d
u
ce
d
b
y
R
F
m
o
d
el
an
d
th
e
r
ea
l
ag
e
f
o
r
b
o
th
g
en
d
er
s
.
T
h
e
g
r
ap
h
s
s
h
o
w
g
o
o
d
r
elatio
n
s
h
ip
b
et
w
ee
n
th
e
p
r
ed
icted
ag
e
an
d
th
e
r
ea
l
ag
e.
T
ab
le
4
s
h
o
w
s
th
e
r
es
u
l
ts
o
f
th
e
b
est
R
F
’
s
s
tr
u
ct
u
r
e
s
elec
ted
b
ef
o
r
e,
to
g
eth
er
w
it
h
t
h
e
A
N
N
a
n
d
SV
M
’
s
r
es
u
lt
s
ta
k
e
n
f
r
o
m
t
h
e
p
r
ev
io
u
s
ca
s
e
s
t
u
d
y
.
T
h
e
tab
le
s
h
o
w
s
th
a
t
th
e
SV
M
p
r
o
d
u
ce
d
th
e
g
r
ea
test
R
-
s
q
u
ar
e
v
al
u
e
o
f
0
.
9
1
6
an
d
th
e
l
o
w
est
M
SE
v
al
u
e
o
f
1
.
9
1
7
,
f
o
r
m
ale,
w
h
ile
f
o
r
f
e
m
ale,
t
h
e
R
F
m
o
d
el
s
h
o
w
s
t
h
e
g
r
ea
test
R
-
s
q
u
ar
e
v
a
lu
e
o
f
0
.
8
4
6
an
d
th
e
lo
w
est
MSE
v
al
u
e
o
f
3
.
4
3
8
.
T
ab
le
4
.
T
h
e
b
est R
-
s
q
u
ar
e
a
n
d
MSE
v
alu
e
s
ch
o
s
e
n
f
r
o
m
th
e
R
F
m
o
d
el
an
d
th
e
A
NN
a
n
d
SVM
m
o
d
el
f
r
o
m
p
r
ev
io
u
s
ca
s
e
s
t
u
d
y
M
o
d
e
l
s
M
a
l
e
F
e
mal
e
R
-
sq
u
a
r
e
M
S
E
R
-
sq
u
a
r
e
M
S
E
A
N
N
[
6
]
0
.
9
0
4
2
.
1
9
3
0
.
8
2
4
3
.
9
1
9
S
V
M
[
6
]
0
.
9
1
6
1
.
9
1
7
0
.
8
3
2
3
.
7
7
5
RF
0
.
9
1
4
1
.
9
5
8
0
.
8
4
6
3
.
4
3
8
Fo
r
en
s
ic
an
t
h
r
o
p
o
lo
g
is
t
s
ar
e
ce
aseless
l
y
e
n
d
ea
v
o
u
r
i
n
g
to
en
h
a
n
ce
th
e
ap
p
r
o
ac
h
es
o
f
ass
ess
i
n
g
a
g
e
th
r
o
u
g
h
s
k
eleta
l
id
en
ti
f
icatio
n
[
2
5
]
.
I
n
a
s
tu
d
y
o
n
s
e
x
u
al
d
i
m
o
r
p
h
is
m
in
ca
r
p
al
b
o
n
es
co
n
d
u
cted
b
y
Su
lz
m
a
n
n
et
a
l
.
[
2
6
]
,
th
e
au
t
h
o
r
s
clai
m
ed
th
at
r
i
g
h
t
-
h
a
n
d
d
o
m
i
n
a
n
ce
is
a
v
er
y
co
m
m
o
n
o
cc
u
r
r
en
ce
a
m
o
n
g
h
u
m
a
n
p
o
p
u
latio
n
s
.
A
d
d
itio
n
all
y
,
m
o
r
e
p
r
o
m
i
n
en
t
p
r
ac
tica
l
lo
ad
in
g
o
n
t
h
e
d
o
m
i
n
a
n
t
h
a
n
d
lead
s
to
b
ig
g
er
b
o
n
e.
T
h
er
ef
o
r
e,
th
e
lef
t
h
a
n
d
’
s
b
o
n
e
w
as
u
tili
ze
d
in
t
h
is
s
t
u
d
y
s
i
n
ce
it
is
r
ela
ti
v
el
y
le
s
s
u
s
ed
,
w
h
ic
h
r
esu
lts
th
e
g
r
o
w
th
o
f
t
h
ese
b
o
n
es
to
b
e
alm
o
s
t
s
i
m
ilar
a
m
o
n
g
ev
er
y
p
ar
ticip
an
ts
.
P
ar
ticip
a
n
ts
w
h
o
ar
e
u
n
d
er
1
9
y
ea
r
s
o
ld
w
er
e
also
in
v
e
s
ti
g
ated
in
t
h
is
s
t
u
d
y
.
T
h
is
is
b
ec
a
u
s
e
a
f
e
w
r
esear
c
h
h
a
v
e
d
e
m
o
n
s
tr
ated
th
at
t
h
e
m
eth
o
d
s
o
f
ag
e
esti
m
atio
n
ar
e
u
n
d
ep
en
d
a
b
le
w
it
h
an
er
r
o
r
o
f
m
o
r
e
o
r
less
t
w
el
v
e
y
ea
r
s
af
ter
t
h
e
3
0
y
e
ar
s
o
ld
[
2
7
]
.
Fo
r
r
o
u
tin
e
f
o
r
en
s
ic
ap
p
licat
io
n
,
R
ö
s
in
g
a
n
d
K
v
aa
l
[
2
8
]
ex
p
r
ess
ed
th
at
a
m
o
d
el
t
h
a
t
p
r
o
d
u
ce
s
tan
d
ar
d
er
r
o
r
o
f
r
eg
r
es
s
io
n
o
f
m
o
r
e
t
h
an
5
o
r
7
y
ea
r
s
ca
n
n
o
t
b
e
ac
ce
p
ted
f
o
r
ag
e
e
s
ti
m
atio
n
.
9
5
%
co
n
f
id
en
ce
in
ter
v
a
ls
o
f
ar
o
u
n
d
1
4
y
ea
r
s
an
d
ab
o
v
e
n
ee
d
to
b
e
tak
en
i
n
to
ac
co
u
n
t
i
n
esti
m
ati
n
g
ag
e
,
g
iv
e
n
th
at
t
h
er
e
is
a
s
ta
n
d
ar
d
er
r
o
r
o
f
s
ev
en
y
ea
r
s
.
Selecti
n
g
th
e
les
s
r
eliab
le
m
e
th
o
d
s
ca
n
b
e
tr
o
u
b
leso
m
e
as
t
h
e
es
ti
m
a
tio
n
o
f
a
n
―
ap
p
ar
en
t
a
g
e‖
u
s
u
all
y
co
n
d
u
cted
b
y
th
e
in
v
es
tig
a
tin
g
tea
m
s
m
a
y
n
o
t
b
e
en
h
a
n
ce
d
b
y
t
h
e
r
esu
lt
s
,
f
o
r
i
n
s
ta
n
ce
in
li
v
in
g
h
u
m
a
n
an
d
f
r
esh
co
r
p
s
e.
T
h
er
ef
o
r
e,
it w
i
ll b
e
a
w
a
s
te
o
f
m
o
n
e
y
a
n
d
ti
m
e.
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.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
549
-
558
554
T
h
er
e
ar
e
m
a
n
y
r
ep
o
r
ted
m
et
h
o
d
s
th
at
u
s
ed
b
o
n
es
f
o
r
ag
e
esti
m
atio
n
an
d
th
e
y
ar
e
s
u
b
d
iv
id
ed
in
to
th
r
ee
m
ai
n
ca
te
g
o
r
ies:
i
m
ag
e
p
r
o
ce
s
s
in
g
[
2
9
-
31]
,
b
y
co
m
p
a
r
in
g
w
it
h
b
o
n
e
a
g
e
atla
s
[
3
2
-
34]
,
an
d
s
tati
s
tical
r
eg
r
ess
io
n
an
al
y
s
is
[
3
5
-
38]
.
As
b
ein
g
co
m
p
ar
ed
w
i
th
t
h
e
atlas,
as
t
h
e
n
a
m
e
p
r
o
p
o
s
es,
X
-
r
a
y
i
m
a
g
e
o
f
th
e
s
u
b
j
ec
ts
ar
e
b
ein
g
m
ad
e
co
m
p
ar
is
o
n
w
it
h
an
atlas
w
h
ich
co
n
tain
s
a
s
et
o
f
r
ad
io
g
r
ap
h
s
o
f
id
en
ti
f
ied
g
en
d
er
an
d
ag
e.
Dif
f
er
en
t
b
o
n
e
f
ea
tu
r
es
ar
e
r
eliab
ly
ex
tr
icate
d
i
n
th
e
i
m
ag
e
p
r
o
ce
s
s
i
n
g
m
et
h
o
d
.
I
t
is
b
ein
g
ac
co
u
n
ted
th
at
t
h
is
m
o
d
el
i
s
f
it
f
o
r
ac
co
m
p
li
s
h
in
g
m
o
r
e
s
o
lid
in
f
o
r
m
atio
n
f
o
r
ag
e
esti
m
atio
n
.
I
n
co
m
p
ar
is
o
n
w
i
th
th
e
o
th
er
t
w
o
m
e
th
o
d
s
,
r
eg
r
es
s
io
n
an
al
y
s
i
s
is
a
w
el
l
-
k
n
o
w
n
d
ec
is
io
n
b
ec
au
s
e
o
f
it
s
co
m
p
ar
ativ
e
an
d
s
i
m
p
li
s
tic
ac
cu
r
ac
y
.
T
h
e
p
r
im
ar
y
p
u
r
p
o
s
e
is
to
f
in
d
o
u
t
t
h
e
r
elatio
n
s
h
i
p
b
etw
ee
n
o
n
e
o
r
m
o
r
e
in
d
ep
en
d
en
t
v
ar
iab
les
an
d
a
d
ep
en
d
en
t
v
ar
iab
le
th
r
o
u
g
h
th
e
R
-
s
q
u
ar
e
v
al
u
e
p
r
o
d
u
ce
d
b
y
t
h
e
m
o
d
els
u
s
ed
.
T
h
e
in
d
ep
e
n
d
en
t
v
ar
iab
les
ar
e
also
k
n
o
w
n
as e
x
p
lan
ato
r
y
o
r
p
r
ed
icto
r
v
ar
iab
les.
So
f
t
co
m
p
u
ti
n
g
m
o
d
els
s
u
ch
as
R
F
m
o
d
el
ca
n
b
e
u
ti
lize
d
as
o
p
tio
n
m
o
d
el
b
ec
au
s
e
i
t
p
r
o
v
id
es
ad
v
an
ta
g
es
s
u
ch
as
k
n
o
w
led
g
e
o
f
i
n
ter
n
a
l
s
y
s
te
m
v
ar
iab
le
s
is
n
o
t
r
eq
u
ir
ed
,
f
ac
tu
a
l
ca
lc
u
latio
n
a
n
d
s
i
m
p
ler
s
o
lu
tio
n
s
f
o
r
m
u
lt
ip
le
v
ar
i
ab
le
p
r
o
b
lem
s
.
So
f
t
co
m
p
u
ti
n
g
is
a
cr
ea
tiv
e
ap
p
r
o
ac
h
i
n
d
ev
elo
p
i
n
g
co
m
p
u
tatio
n
all
y
s
a
v
v
y
f
r
a
m
e
w
o
r
k
s
.
A
cc
o
r
d
in
g
to
Z
ad
eh
[
3
9
]
,
s
o
f
t
co
m
p
u
t
in
g
is
a
d
ev
elo
p
in
g
s
tr
ate
g
y
to
w
ar
d
s
co
m
p
u
ti
n
g
w
h
ich
co
r
r
esp
o
n
d
s
to
th
e
i
m
p
o
r
tan
t
ca
p
ac
it
y
o
f
t
h
e
h
u
m
a
n
i
n
te
lli
g
e
n
c
e
to
co
m
p
r
eh
en
d
i
n
a
d
o
m
ai
n
o
f
i
m
p
r
ec
i
s
io
n
a
n
d
v
u
l
n
er
ab
ilit
y
.
I
n
th
is
s
t
u
d
y
,
m
ea
s
u
r
e
m
e
n
t
w
a
s
m
ad
e
o
n
a
to
tal
n
u
m
b
er
o
f
1
9
b
o
n
es
i
n
t
h
e
le
f
t
h
a
n
d
a
n
d
R
F
s
o
f
t
co
m
p
u
ti
n
g
m
o
d
els
w
e
r
e
co
n
d
u
cted
o
n
all
th
e
b
o
n
e
s
to
es
ti
m
ate
a
g
e.
Fo
r
co
m
p
ar
is
o
n
p
u
r
p
o
s
e,
f
o
r
m
ale,
t
h
e
b
est
s
o
f
t
co
m
p
u
ti
n
g
a
g
e
e
s
ti
m
atio
n
m
o
d
el
ac
co
r
d
in
g
to
th
e
p
er
f
o
r
m
an
ce
m
ea
s
u
r
e
m
e
n
t
p
r
o
d
u
ce
d
is
S
VM
m
o
d
el
wh
er
e
t
h
e
R
-
s
q
u
ar
e
a
n
d
M
SE
v
alu
e
p
r
o
d
u
ce
d
is
0
.
9
1
6
an
d
1
.
9
1
7
,
r
esp
ec
tiv
ely
.
Fo
r
f
e
m
ale,
R
F
i
s
t
h
e
b
est
s
o
f
t
co
m
p
u
t
in
g
m
o
d
el
w
h
er
e
th
e
R
-
s
q
u
ar
e
a
n
d
MS
E
v
alu
e
p
r
o
d
u
ce
d
is
8
.
4
6
an
d
3
.
4
3
8
,
r
esp
ec
tiv
el
y
as c
o
m
p
ar
ed
w
it
h
t
h
e
o
th
er
m
o
d
els.
Fig
u
r
e
3
.
Gr
ap
h
o
f
th
e
p
r
ed
icted
ag
e
p
r
o
d
u
ce
d
b
y
R
F
m
o
d
el,
an
d
th
e
ac
tu
a
l a
g
e,
f
o
r
b
o
th
m
ale
(
th
e
f
ir
s
t r
o
w
)
an
d
f
e
m
a
le
(
th
e
s
ec
o
n
d
r
o
w
)
0
2
4
6
8
10
12
14
16
18
20
1
11
21
31
41
51
61
71
81
91
101
111
121
131
141
151
161
Ag
e
(y
e
a
r
s)
N
um
be
r
o
f
D
a
ta
se
t
P
r
e
di
c
ted
A
g
e
pr
odu
c
e
d
by
R
F
wi
th
n
u
m
be
r
of
tr
e
e
s
200
a
n
d
n
u
m
be
r
of
v
a
r
i
a
bl
e
4
a
n
d
th
e
A
c
tu
a
l
A
g
e
Ac
tual
Age
P
r
e
dicte
d
Age
0
2
4
6
8
10
12
14
16
18
20
1
11
21
31
41
51
61
71
81
91
101
111
121
131
141
151
161
Ag
e
(y
e
a
r
s)
N
um
be
r
o
f
D
a
ta
se
t
P
r
e
di
c
ted
A
g
e
pr
odu
c
e
d
by
R
F
wi
th
n
u
m
be
r
of
tr
e
e
s
1000
a
n
d
n
u
m
be
r
of
v
a
r
i
a
bl
e
4,
a
n
d
th
e
A
c
tu
a
l
A
g
e
Ac
tual
Age
P
r
e
dicte
d
Age
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
R
a
n
d
o
m
f
o
r
est a
g
e
esti
ma
tio
n
mo
d
el
b
a
s
ed
o
n
le
n
g
th
o
f le
ft
h
a
n
d
b
o
n
e
fo
r
…
(
Mo
h
d
F
a
a
iz
ie
Da
r
ma
w
a
n
)
555
Fig
u
r
e
3
s
h
o
w
s
t
h
e
g
r
ap
h
s
o
f
th
e
p
r
ed
icted
o
u
tp
u
t
p
r
o
d
u
ce
d
b
y
t
h
e
R
F
m
o
d
el
a
n
d
th
e
a
ctu
al
a
g
e,
o
f
b
o
th
m
ale
a
n
d
f
e
m
ale.
T
h
e
g
r
ap
h
s
s
h
o
w
t
h
at
f
o
r
m
ale
ag
e
d
f
r
o
m
n
e
w
-
b
o
r
n
u
p
to
1
6
y
ea
r
s
o
ld
,
th
e
p
r
ed
icted
ag
es
o
f
al
l
b
o
th
m
o
d
els
w
e
r
e
co
n
s
is
ten
t
w
it
h
th
e
ac
tu
a
l
ag
e.
Ho
w
e
v
e
r
,
f
o
r
m
ale
ab
o
v
e
1
6
y
ea
r
s
o
ld
,
th
e
p
r
ed
icted
ag
e
s
ee
m
ed
to
d
ev
iate
f
r
o
m
t
h
e
ac
tu
al
a
g
e,
s
h
o
w
i
n
g
i
n
co
n
s
is
te
n
c
y
i
n
o
u
t
p
u
t
f
r
o
m
t
h
e
b
o
th
m
o
d
el
s
(
s
ee
t
h
e
b
lack
lin
e
b
et
w
ee
n
a
g
e
1
5
y
ea
r
s
o
ld
an
d
1
7
y
ea
r
s
o
ld
)
.
Fo
r
f
e
m
ale,
t
h
e
p
r
ed
icted
ag
e
f
r
o
m
th
e
b
o
th
m
o
d
el
s
s
h
o
w
ed
co
n
s
i
s
ten
c
y
w
i
th
t
h
e
ac
t
u
al
a
g
e,
b
u
t
af
ter
1
5
y
ea
r
s
o
ld
,
t
h
e
p
r
ed
ict
ed
ag
e
al
s
o
s
ee
m
ed
to
h
av
e
d
ev
iated
f
r
o
m
t
h
e
ac
t
u
al
a
g
e,
s
a
m
e
a
s
t
h
e
m
a
le
(
s
e
e
th
e
b
lac
k
li
n
e
b
et
w
ee
n
ag
e
1
4
y
ea
r
s
o
ld
an
d
1
6
y
ea
r
s
o
ld
)
.
T
h
ese
f
in
d
i
n
g
s
w
e
r
e
s
i
m
ilar
w
it
h
t
h
e
p
r
ev
io
u
s
c
ase
s
t
u
d
y
ch
o
s
e
n
w
h
er
e
t
h
e
g
r
ap
h
p
r
o
d
u
ce
d
b
y
A
N
N
an
d
SVM
also
th
e
s
h
o
w
t
h
e
s
i
m
ilar
ca
s
e.
R
itz
-
T
i
m
m
e
et
a
l
.
[
4
0
]
s
tated
th
at
th
e
v
alid
atio
n
o
f
ag
e
esti
m
atio
n
o
f
m
o
s
t
m
o
r
p
h
o
lo
g
ical
m
et
h
o
d
s
is
th
e
lea
s
t
ac
cu
r
ate
in
ad
u
lt
h
o
o
d
.
San
to
s
et
a
l
.
[
4
1
]
in
th
eir
s
tu
d
y
o
n
ag
e
esti
m
at
io
n
u
s
i
n
g
t
h
e
Se
m
p
é
m
eth
o
d
b
u
ilt
f
o
r
co
m
p
u
ter
–
Ma
tu
r
o
s
4
.
0
(
M
T
)
p
r
o
g
r
a
m
s
h
o
w
ed
th
at
th
e
MT
p
r
o
g
r
a
m
o
n
l
y
p
r
o
d
u
ce
d
r
eliab
le
r
esu
lt
s
f
o
r
ag
e
u
n
d
er
1
6
y
ea
r
s
o
ld
.
Mo
lin
ar
i
e
t
a
l
.
[
4
2
]
in
h
i
s
s
tu
d
y
also
s
tated
th
at
t
h
e
g
r
o
w
t
h
o
f
t
h
e
s
k
eleto
n
h
as p
r
ac
ticall
y
s
to
p
p
ed
f
o
r
th
e
s
k
eleta
l d
ev
e
lo
p
m
en
t a
t
th
e
b
o
n
e
a
g
e
o
f
1
6
.
5
y
ea
r
s
a
n
d
1
5
y
ea
r
s
f
o
r
b
o
y
s
a
n
d
g
ir
l
s
r
esp
ec
ti
v
el
y
.
A
f
ter
th
at
ag
e,
th
e
ev
a
lu
at
io
n
o
f
ag
e
te
n
d
to
b
e
in
ac
cu
r
ate,
r
es
u
lti
n
g
to
a
v
a
s
t
d
ev
iatio
n
b
et
w
ee
n
t
h
e
r
ea
l
an
d
th
e
est
i
m
a
ted
ag
e.
Fro
m
t
h
ese
s
u
p
p
o
r
ted
liter
atu
r
es,
w
e
ca
n
s
a
y
th
at
t
h
e
b
est
r
an
g
e
o
f
ag
e
f
o
r
ag
e
es
ti
m
atio
n
is
b
et
w
ee
n
n
e
w
-
b
o
r
n
to
1
6
y
ea
r
s
o
ld
f
o
r
m
ale,
an
d
n
e
w
-
b
o
r
n
to
1
5
-
1
6
y
ea
r
s
o
ld
f
o
r
f
e
m
ale.
I
n
ad
d
itio
n
,
b
ased
o
n
o
u
r
g
r
ap
h
s
,
o
u
r
R
F
m
o
d
el
ca
n
p
r
ed
ict
w
e
ll f
o
r
b
o
th
m
a
le
an
d
f
e
m
a
le
in
t
h
at
r
an
g
e
o
f
a
g
e.
Gen
er
all
y
,
d
i
f
f
er
e
n
t
co
n
tr
ib
u
ti
n
g
v
ar
iab
les
s
u
ch
as
d
i
f
f
er
en
t
m
et
h
o
d
o
lo
g
y
ap
p
r
o
ac
h
es,
d
iv
er
s
e
r
ac
ial
b
ac
k
g
r
o
u
n
d
s
,
o
r
d
is
s
i
m
ilar
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
,
c
o
u
ld
clar
if
y
t
h
e
co
n
tr
a
s
ts
b
et
w
ee
n
m
u
l
tira
cial
in
v
e
s
ti
g
atio
n
s
o
f
s
k
eleta
l
d
ev
elo
p
m
e
n
t
[
4
3
]
.
Fu
r
t
h
er
m
o
r
e,
a
lo
t
o
f
f
ac
to
r
s
s
u
c
h
as
n
u
tr
itio
n
,
o
cc
u
p
at
io
n
,
en
d
o
cr
in
e
f
ac
to
r
s
,
g
en
e
tic,
o
v
er
all
li
f
est
y
le
a
n
d
h
ea
lt
h
,
g
r
o
w
th
,
a
n
d
ac
ti
v
it
y
s
i
g
n
if
ica
n
tl
y
i
n
f
lu
e
n
ce
t
h
es
e
in
d
icato
r
s
i
n
a
n
u
n
f
o
r
eseea
b
le
w
a
y
[
4
4
,
4
5
]
.
Du
e
to
th
e
s
e
r
e
aso
n
s
,
t
h
e
l
i
m
itatio
n
o
f
tec
h
n
i
ca
l
ap
p
licatio
n
n
ee
d
to
b
e
d
o
n
e
to
th
e
tar
g
eted
p
o
p
u
latio
n
f
r
o
m
w
h
ic
h
th
e
b
o
n
e
s
w
er
e
g
a
th
er
ed
.
E
s
ti
m
ati
n
g
a
g
e
f
r
o
m
a
p
ar
ticu
lar
p
o
p
u
latio
n
s
h
o
u
ld
b
e
e
x
ce
p
tio
n
all
y
an
al
y
ze
d
i
n
w
h
ic
h
t
h
e
ap
p
lied
r
eg
r
ess
io
n
m
o
d
el
s
o
r
m
at
h
e
m
atica
l
f
u
n
ctio
n
s
m
a
y
d
i
f
f
er
b
ec
au
s
e
o
f
th
e
s
e
d
if
f
er
en
ce
s
.
4.
CO
NCLU
SI
O
N
A
cc
o
r
d
in
g
to
th
is
s
tu
d
y
,
th
e
n
u
m
b
er
o
f
X
-
r
a
y
o
f
t
h
e
lef
t
h
a
n
d
f
r
o
m
a
s
et
o
f
d
ata
o
f
A
s
ia
n
ch
ild
r
e
n
w
er
e
u
s
ed
f
o
r
ag
e
esti
m
at
io
n
i
s
3
3
3
.
On
e
s
o
f
t
co
m
p
u
ti
n
g
m
o
d
el
w
as
u
s
ed
w
h
ich
i
s
R
F
m
o
d
el
to
b
e
c
o
m
p
ar
ed
w
it
h
t
h
e
ANN
an
d
SVM
m
o
d
el
d
ev
elo
p
ed
in
th
e
p
r
ev
io
u
s
ca
s
e
s
tu
d
y
.
B
ased
o
n
th
e
f
i
n
d
in
g
s
,
R
F
m
o
d
el
is
co
m
p
ar
ab
le
w
it
h
th
e
A
NN
a
n
d
SVM
m
o
d
el
esp
ec
iall
y
f
o
r
f
e
m
ale
w
h
er
e
R
F
m
o
d
el
p
r
o
d
u
ce
d
b
etter
r
esu
lts
th
an
ANN
an
d
SVM
i
n
ter
m
o
f
th
e
p
er
f
o
r
m
an
ce
m
ea
s
u
r
e
m
e
n
t
u
s
ed
.
Ho
w
e
v
er
,
f
o
r
m
ale,
th
e
R
F
m
o
d
el
is
le
s
s
ef
f
icien
t th
a
n
SVM
m
o
d
el
b
u
t
b
etter
th
an
A
NN
m
o
d
el.
A
cc
o
r
d
in
g
to
th
e
g
r
ap
h
p
r
o
d
u
ce
d
b
y
th
e
R
F
m
o
d
el
an
d
t
h
e
s
u
p
p
o
r
ted
liter
atu
r
e,
R
F
m
o
d
el
ca
n
esti
m
ate
w
e
ll
th
e
ag
e
f
o
r
r
an
g
e
o
f
ag
e
b
et
w
ee
n
n
e
w
b
o
r
n
t
o
1
6
y
ea
r
s
o
ld
an
d
b
etw
ee
n
n
e
w
b
o
r
n
to
1
5
y
ea
r
s
o
ld
,
f
o
r
m
ale
an
d
f
e
m
a
le,
r
esp
ec
tiv
el
y
.
T
h
is
f
i
n
d
in
g
also
p
r
o
v
es
t
h
at
th
e
le
n
g
th
o
f
b
o
n
e
is
r
eliab
le
to
b
e
u
s
ed
as
a
g
e
i
n
d
icato
r
f
o
r
a
g
e
e
s
ti
m
atio
n
.
T
o
co
n
clu
d
e
,
t
h
e
R
F
m
o
d
el
is
s
till
co
m
p
ar
ab
le
w
it
h
t
h
e
o
t
h
er
m
o
d
el
s
a
n
d
s
u
itab
le
to
b
e
u
s
ed
f
o
r
ag
e
est
i
m
atio
n
.
Ho
w
e
v
er
,
f
u
r
t
h
er
s
t
u
d
y
w
ill
li
m
it
t
h
e
s
u
b
j
ec
t
ag
e
f
r
o
m
n
e
w
-
b
o
r
n
to
1
6
y
ea
r
s
o
ld
f
o
r
m
ale
an
d
n
e
w
-
b
o
r
n
to
1
5
y
ea
r
s
o
ld
f
o
r
f
e
m
al
e,
f
o
r
ag
e
esti
m
atio
n
,
ac
co
r
d
in
g
to
t
h
e
s
u
p
p
o
r
ted
lite
r
atu
r
es
an
d
t
h
e
f
i
n
d
in
g
s
.
T
h
e
f
u
tu
r
e
s
t
u
d
y
w
il
l
i
m
p
r
o
v
e
t
h
e
r
esu
lt
s
o
f
th
e
ag
e
es
ti
m
atio
n
b
y
s
tu
d
y
i
n
g
o
th
er
alg
o
r
ith
m
s
u
s
ed
b
y
v
ar
io
u
s
o
th
er
ca
s
e
s
t
u
d
ies
a
v
ailab
le
s
u
c
h
as
b
y
L
e
n
i
n
,
R
ed
d
y
,
a
n
d
Kala
v
at
h
i
[
4
6
]
,
I
s
m
ail
et
a
l
.
[
4
5
]
,
I
s
m
ail
et
a
l
.
[
4
6
]
,
Kh
alee
l
et
a
l
.
[
4
7
]
an
d
al
l o
th
er
class
i
f
icatio
n
m
e
th
o
d
s
[
4
8
-
57]
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
s
tu
d
y
th
a
n
k
ed
to
Min
i
s
tr
y
o
f
Hi
g
h
er
E
d
u
ca
tio
n
(
M
OHE
)
f
o
r
Fu
n
d
a
m
e
n
tal
R
ese
ar
ch
Gr
an
t
Sch
e
m
e
(
FR
G
S)
w
it
h
g
r
a
n
t
n
u
m
b
er
R
DU1
9
0
1
9
0
an
d
UM
P
in
ter
n
al
g
r
a
n
t
w
it
h
g
r
an
t
n
u
m
b
er
R
DU1
7
0
3
1
2
7
,
f
or
th
ie
r
s
u
p
p
o
r
t.
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.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
549
-
558
556
RE
F
E
R
E
NC
E
S
[1
]
J.
M
.
T
a
n
n
e
r,
M
.
J.
R.
He
a
l
y
,
H.
G
o
ld
ste
in
,
a
n
d
N.
Ca
m
e
ro
n
,
―
S
k
e
leta
l
M
a
tu
rity
a
n
d
Pre
d
ictio
n
o
f
Ad
u
lt
He
ig
h
t
(
T
W
3
M
e
th
o
d
)
,
‖
3
e
d
it
i
o
n
.
S
a
u
n
d
e
rs L
td
,
2
0
0
1
.
[2
]
W
.
G
re
u
li
c
h
a
n
d
S
.
P
y
le,
―
Ra
d
io
g
ra
p
h
ic
At
la
s
o
f
S
k
e
leta
l
De
v
e
lo
p
me
n
t
o
f
th
e
Ha
n
d
a
n
d
W
rist
,‖
P
a
l
o
A
lt
o
,
CA
:
S
tan
f
o
rd
Un
iv
.
P
re
ss
,
1
9
7
1
.
[3
]
R.
Ca
m
e
riere
,
S
.
De
L
u
c
a
,
R.
Bia
g
i,
M
.
Cin
g
o
lan
i
,
G
.
F
a
rro
n
a
to
,
a
n
d
L
.
F
e
rra
n
te,
―
A
c
c
u
ra
c
y
o
f
th
re
e
a
g
e
e
sti
m
a
ti
o
n
m
e
th
o
d
s
i
n
c
h
il
d
re
n
b
y
m
e
a
su
re
m
e
n
ts
o
f
d
e
v
e
lo
p
in
g
tee
th
a
n
d
c
a
rp
a
ls
a
n
d
e
p
i
p
h
y
se
s
o
f
th
e
u
ln
a
a
n
d
ra
d
i
u
s.,
‖
J
.
Fo
re
n
sic
S
c
i.
,
v
o
l.
5
7
,
n
o
.
5
,
p
p
.
1
2
6
3
–
7
0
,
S
e
p
.
2
0
1
2
.
[4
]
A
.
a
.
El
-
Ba
k
a
r
y
e
t
a
l
.
,
―
A
g
e
e
stim
a
ti
o
n
i
n
Eg
y
p
ti
a
n
c
h
il
d
re
n
b
y
m
e
a
su
re
m
e
n
ts
o
f
c
a
rp
a
ls
a
n
d
e
p
i
p
h
y
se
s
o
f
th
e
u
ln
a
a
n
d
ra
d
i
u
s,‖
J
.
F
o
re
n
sic
Ra
d
i
o
l.
I
ma
g
in
g
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
1
2
1
–
1
2
5
,
2
0
1
4
.
[5
]
M
.
F
.
Da
rm
a
w
a
n
,
S
.
M
.
Y
u
su
f
,
M
.
R.
A
b
d
u
l
Ka
d
ir,
a
n
d
H.
Ha
r
o
n
,
―
A
g
e
e
sti
m
a
ti
o
n
b
a
se
d
o
n
b
o
n
e
len
g
th
u
si
n
g
1
2
re
g
re
ss
io
n
m
o
d
e
ls
o
f
lef
t
h
a
n
d
X
-
ra
y
i
m
a
g
e
s
f
o
r
A
sia
n
c
h
il
d
re
n
b
e
lo
w
1
9
y
e
a
rs
o
ld
,
‖
L
e
g
.
M
e
d
.
,
v
o
l.
1
7
,
n
o
.
2
,
p
p
.
7
1
–
7
8
,
2
0
1
5
.
[6
]
M
.
F
.
Da
rm
a
w
a
n
,
M
.
Z.
Os
m
a
n
,
a
n
d
K.
M
o
o
r
th
y
,
―
Ag
e
Esti
m
a
ti
o
n
o
f
A
sia
n
Us
in
g
S
o
f
t
Co
m
p
u
ti
n
g
M
o
d
e
l
Ba
se
d
o
n
B
o
n
e
L
e
n
g
th
o
f
L
e
f
t
Ha
n
d
,
‖
Ad
v
.
S
c
i.
L
e
tt
.
,
v
o
l.
2
4
,
n
o
.
1
0
,
p
p
.
7
5
5
9
–
7
5
6
5
,
2
0
1
8
.
[7
]
M
.
Da
rm
a
w
a
n
,
H.
Ha
sa
n
,
S
.
S
a
d
im
o
n
,
S
.
Yu
su
f
,
a
n
d
H.
Ha
ro
n
,
―
A
H
y
b
rid
A
rti
f
icia
l
In
telli
g
e
n
t
S
y
ste
m
f
o
r
A
g
e
Esti
m
a
ti
o
n
Ba
se
d
o
n
L
e
n
g
th
o
f
Lef
t
Ha
n
d
Bo
n
e
,
‖
Ad
v
.
S
c
i.
L
e
tt
.
,
v
o
l.
2
4
,
n
o
.
2
,
p
p
.
1
0
4
7
–
1
0
5
1
,
2
0
1
8
.
[8
]
K.
M
o
o
r
th
y
,
M
.
S
.
M
o
h
a
m
a
d
,
a
n
d
S
.
De
ris,
―
M
u
lt
i
p
le
G
e
n
e
S
e
ts
f
o
r
Ca
n
c
e
r
Clas
si
f
ic
a
ti
o
n
Us
in
g
G
e
n
e
Ra
n
g
e
S
e
lec
ti
o
n
Ba
se
d
o
n
Ra
n
d
o
m
F
o
re
st,‖
Asia
n
Co
n
f.
I
n
tell.
I
n
f.
Da
t
a
b
a
se
S
y
st.
,
p
p
.
3
8
5
–
3
9
3
,
2
0
1
3
.
[9
]
D.
Na
v
e
g
a
,
C.
Co
e
lh
o
,
R.
V
ice
n
t
e
,
M
.
T
.
F
e
rre
ira,
S
.
Was
terla
in
,
a
n
d
E.
Cu
n
h
a
,
―
A
n
c
e
sT
r
e
e
s:
a
n
c
e
str
y
e
sti
m
a
ti
o
n
w
it
h
ra
n
d
o
m
ize
d
d
e
c
isio
n
tree
s,‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l
.
1
2
9
,
n
o
.
5
,
p
p
.
1
1
4
5
–
1
1
5
3
,
2
0
1
5
.
[1
0
]
D.
Na
v
e
g
a
,
R.
V
ice
n
te,
D.
N.
V
ieira
,
A
.
H.
Ro
ss
,
a
n
d
E.
Cu
n
h
a
,
―
S
e
x
e
sti
m
a
ti
o
n
f
ro
m
th
e
tars
a
l
b
o
n
e
s
i
n
a
P
o
rtu
g
u
e
se
sa
m
p
le:
a
m
a
c
h
in
e
lea
rn
in
g
a
p
p
r
o
a
c
h
,
‖
In
t
.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
2
9
,
n
o
.
3
,
p
p
.
6
5
1
–
6
5
9
,
2
0
1
5
.
[1
1
]
Š
.
Be
jd
o
v
á
,
J.
Du
p
e
j,
V
.
Kra
jí
č
e
k
,
J.
V
e
lem
ín
sk
á
,
a
n
d
P
.
V
e
lem
ín
s
k
ý
,
―
S
tab
il
it
y
o
f
u
p
p
e
r
f
a
c
e
s
e
x
u
a
l
d
im
o
rp
h
ism
in
c
e
n
tral
Eu
r
o
p
e
a
n
p
o
p
u
lati
o
n
s
(C
z
e
c
h
Re
p
u
b
li
c
)
d
u
rin
g
t
h
e
m
o
d
e
rn
a
g
e
,
‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
3
2
,
n
o
.
1
,
p
p
.
3
2
1
–
3
3
0
,
2
0
1
8
.
[1
2
]
K.
Zh
a
n
g
e
t
a
l
.
,
―
T
h
e
ro
le
o
f
m
u
lt
isli
c
e
c
o
m
p
u
ted
t
o
m
o
g
ra
p
h
y
o
f
th
e
c
o
sta
l
c
a
rti
lag
e
in
a
d
u
lt
a
g
e
e
sti
m
a
ti
o
n
,
‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
p
p
.
7
9
1
–
7
9
8
,
2
0
1
7
.
[1
3
]
F
.
Ca
v
a
ll
i,
L
.
L
u
sn
ig
,
a
n
d
E.
T
re
n
ti
n
,
―
Us
e
o
f
p
a
tt
e
rn
re
c
o
g
n
it
io
n
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
n
o
n
-
m
e
tr
ic
se
x
d
iag
n
o
sis
f
ro
m
late
r
a
l
sh
a
p
e
o
f
c
a
l
v
a
riu
m
:
a
n
in
n
o
v
a
ti
v
e
m
o
d
e
l
f
o
r
c
o
m
p
u
ter
-
a
id
e
d
d
iag
n
o
sis
in
f
o
re
n
sic
a
n
d
p
h
y
sic
a
l
a
n
th
ro
p
o
lo
g
y
,
‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
3
1
,
n
o
.
3
,
p
p
.
1
–
1
1
,
2
0
1
7
.
[1
4
]
―
h
tt
p
s://
i
p
il
a
b
.
u
sc
.
e
d
u
/co
m
p
u
ter
-
a
id
e
d
-
b
o
n
e
-
a
g
e
-
a
ss
e
ss
m
e
n
t
-
of
-
c
h
il
d
re
n
-
u
si
n
g
-
a
-
d
ig
it
a
l
-
h
a
n
d
-
a
tl
a
s
-
2
/
.
‖
[1
5
]
E.
P
ietk
a
,
A
.
G
e
rt
y
c
h
,
S
.
P
o
sp
iec
h
,
F
.
Ca
o
,
H.
K.
Hu
a
n
g
,
a
n
d
V.
Gilsa
n
z
,
―
Co
m
p
u
ter
-
a
ss
isted
b
o
n
e
a
g
e
a
ss
e
ss
m
e
n
t:
Im
a
g
e
p
re
p
ro
c
e
ss
in
g
a
n
d
e
p
ip
h
y
se
a
l/
m
e
tap
h
y
se
a
l
ROI
e
x
trac
ti
o
n
,
‖
IEE
E
T
r
a
n
s.
M
e
d
.
Ima
g
in
g
,
v
o
l.
2
0
,
n
o
.
8
,
p
p
.
7
1
5
–
7
2
9
,
2
0
0
1
.
[1
6
]
H.
K.
Hu
a
n
g
e
t
a
l
.
,
―
Da
ta g
rid
f
o
r
larg
e
-
sc
a
le
m
e
d
ica
l
i
m
a
g
e
a
rc
h
iv
e
a
n
d
a
n
a
ly
sis,‖
in
Pro
c
e
e
d
in
g
s
o
f
th
e
1
3
t
h
ACM
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
u
l
t
ime
d
ia
,
p
p
.
1
0
0
5
–
1
0
1
3
,
2
0
0
5
.
[1
7
]
A
.
Zh
a
n
g
,
A
.
G
e
rt
y
c
h
,
B.
J.
L
iu
,
a
n
d
H.
K.
H
u
a
n
g
,
―
Bo
n
e
A
g
e
A
s
se
ss
m
e
n
t
f
o
r
Yo
u
n
g
Ch
il
d
re
n
f
ro
m
Ne
w
b
o
rn
t
o
7
-
Ye
a
r
-
Old
Us
in
g
Ca
rp
a
l
B
o
n
e
s,
‖
Co
mp
u
t
.
M
e
d
.
Ima
g
i
n
g
Gr
a
p
h
.
,
v
o
l.
6
5
1
6
,
n
o
.
1
8
,
p
p
.
1
–
1
1
,
M
a
r.
2
0
0
7
.
[1
8
]
A
.
G
e
rt
y
c
h
,
A
.
Zh
a
n
g
,
J.
S
a
y
re
,
S
.
P
o
s
p
iec
h
-
Ku
rk
o
w
sk
a
,
a
n
d
H.
.
Hu
a
n
g
,
―
Bo
n
e
A
g
e
A
s
se
ss
m
e
n
t
o
f
Ch
il
d
re
n
u
sin
g
a
Dig
it
a
l
Ha
n
d
A
tl
a
s,‖
Co
mp
u
t
M
e
d
Ima
g
i
n
g
Gr
a
p
h
,
v
o
l
.
3
1
,
p
p
.
3
2
2
–
3
3
1
,
2
0
0
7
.
[1
9
]
A
.
M
.
Zain
,
H.
Ha
ro
n
,
a
n
d
S
.
S
h
a
rif
,
―
P
re
d
ictio
n
o
f
su
rfa
c
e
ro
u
g
h
n
e
ss
in
th
e
e
n
d
m
il
li
n
g
m
a
c
h
in
in
g
u
sin
g
A
rti
f
icia
l
Ne
u
ra
l
Ne
tw
o
rk
,
‖
Exp
e
rt S
y
st.
Ap
p
l.
,
v
o
l.
3
7
,
n
o
.
2
,
p
p
.
1
7
5
5
–
6
8
,
M
a
r.
2
0
1
0
.
[2
0
]
M
.
F
.
Da
rm
a
w
a
n
,
S
.
M
.
Yu
su
f
,
M
.
R.
A
b
d
u
l
Ka
d
ir,
a
n
d
H.
Ha
ro
n
,
―
Co
m
p
a
riso
n
o
n
t
h
re
e
c
las
sif
ic
a
ti
o
n
tec
h
n
i
q
u
e
s
f
o
r
se
x
e
sti
m
a
ti
o
n
f
ro
m
th
e
b
o
n
e
len
g
th
o
f
A
sia
n
c
h
il
d
re
n
b
e
lo
w
1
9
y
e
a
rs
o
ld
:
A
n
a
n
a
l
y
sis
u
sin
g
d
iff
e
r
e
n
t
g
ro
u
p
o
f
a
g
e
s,‖
Fo
re
n
sic
S
c
i.
In
t.
,
v
o
l.
2
4
7
,
p
.
1
3
0
.
e
1
-
1
3
0
.
e
1
1
,
2
0
1
5
.
[2
1
]
L
.
Bre
i
m
a
n
,
―
Ra
n
d
o
m
f
o
re
sts,‖
M
a
c
h
.
L
e
a
rn
.
,
p
p
.
5
–
3
2
,
2
0
0
1
.
[2
2
]
A
.
L
.
Bo
u
les
teix
,
S
.
J
a
n
it
z
a
,
J.
Kru
p
p
a
,
a
n
d
I.
R.
Kö
n
ig
,
―
Ov
e
rv
iew
o
f
r
a
n
d
o
m
f
o
re
st
m
e
th
o
d
o
lo
g
y
a
n
d
p
ra
c
ti
c
a
l
g
u
id
a
n
c
e
w
it
h
e
m
p
h
a
sis
o
n
c
o
m
p
u
tatio
n
a
l
b
io
l
o
g
y
a
n
d
b
io
i
n
f
o
rm
a
ti
c
s,‖
W
il
e
y
In
ter
d
isc
ip
.
Rev
.
Da
t
a
M
in
.
Kn
o
wl.
Disc
o
v
.
,
v
o
l.
2
,
n
o
.
1
2
9
,
p
p
.
4
9
3
–
5
0
7
,
2
0
1
2
.
[2
3
]
P
.
F
.
S
m
it
h
,
S
.
G
a
n
e
sh
,
a
n
d
P
.
Li
u
,
―
A
c
o
m
p
a
riso
n
o
f
ra
n
d
o
m
f
o
r
e
st
re
g
r
e
ss
io
n
a
n
d
m
u
lt
ip
le
li
n
e
a
r
re
g
re
ss
io
n
f
o
r
p
re
d
ictio
n
i
n
n
e
u
ro
sc
ien
c
e
,
‖
J
.
Ne
u
ro
sc
i.
M
e
th
o
d
s
,
v
o
l
.
2
2
0
,
n
o
.
1
,
p
p
.
8
5
–
9
1
,
2
0
1
3
.
[2
4
]
P
.
V
e
z
z
a
,
R.
M
u
ñ
o
z
-
M
a
s,
F
.
M
a
rti
n
e
z
-
Ca
p
e
l,
a
n
d
a
.
M
o
u
t
o
n
,
―
R
a
n
d
o
m
f
o
re
sts
to
e
v
a
lu
a
te
b
io
ti
c
in
tera
c
ti
o
n
s
in
f
ish
d
istri
b
u
ti
o
n
m
o
d
e
ls,
‖
En
v
ir
o
n
.
M
o
d
e
l.
S
o
ft
w.
,
v
o
l.
6
7
,
p
p
.
1
7
3
–
1
8
3
,
2
0
1
5
.
[2
5
]
M
.
S
tey
n
a
n
d
M
.
Y.
Işc
a
n
,
―
M
e
tri
c
se
x
d
e
ter
m
in
a
ti
o
n
f
ro
m
th
e
p
e
lv
is
in
m
o
d
e
rn
G
re
e
k
s.,
‖
Fo
re
n
sic
S
c
i.
In
t.
,
v
o
l.
1
7
9
,
n
o
.
1
,
p
.
8
6
.
e
1
-
6
,
Ju
l.
2
0
0
8
.
[2
6
]
C.
E.
S
u
lzm
a
n
n
,
J.
L
.
Bu
c
k
b
e
rry
,
a
n
d
R.
F
.
P
a
sto
r,
―
T
h
e
Util
it
y
o
f
Ca
rp
a
ls
f
o
r
S
e
x
A
ss
e
ss
m
e
n
t :
A
P
re
li
m
in
a
r
y
S
tu
d
y
,
‖
Am.
J
.
P
h
y
s.
An
t
h
ro
p
o
l
.
,
v
o
l.
1
3
5
,
p
p
.
2
5
2
–
2
6
2
,
2
0
0
8
.
[2
7
]
J.
M
.
S
u
c
h
e
y
,
―
P
ro
b
lem
s
in
th
e
a
g
in
g
o
f
f
e
m
a
l
e
s
u
sin
g
th
e
Os
p
u
b
is,
‖
Am.
J
.
Ph
y
s.
An
th
r
o
p
o
l.
,
v
o
l.
5
1
,
p
p
.
4
6
7
–
4
7
0
,
1
9
7
9
.
[2
8
]
F
.
W
.
Rö
sin
g
a
n
d
S
.
I.
Kv
a
a
l,
―
De
n
tal
Ag
e
in
A
d
u
lt
s
—
A
Re
v
iew
o
f
Esti
m
a
ti
o
n
M
e
th
o
d
s,‖
De
n
t.
An
t
h
ro
p
o
l
.
,
p
p
.
4
4
3
–
4
6
8
,
1
9
9
8
.
[2
9
]
S
.
Ku
c
h
e
ry
a
v
sk
i,
I.
Be
l
y
a
e
v
,
a
n
d
S
.
F
o
m
in
y
k
h
,
―
Esti
m
a
ti
o
n
o
f
a
g
e
in
f
o
re
n
sic
m
e
d
icin
e
u
sin
g
m
u
lt
iv
a
riate
a
p
p
ro
a
c
h
to
im
a
g
e
a
n
a
l
y
sis,‖
Ch
e
mo
m.
In
te
ll
.
L
a
b
.
S
y
st.
,
v
o
l.
9
7
,
n
o
.
1
,
p
p
.
3
9
–
4
5
,
M
a
y
2
0
0
9
.
[3
0
]
O.
Ek
izo
g
lu
e
t
a
l
.
,
―
Co
m
p
u
ted
to
m
o
g
ra
p
h
y
e
v
a
lu
a
ti
o
n
o
f
th
e
il
iac
c
re
st
a
p
o
p
h
y
sis:
a
g
e
e
sti
m
a
ti
o
n
in
li
v
i
n
g
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
R
a
n
d
o
m
f
o
r
est a
g
e
esti
ma
tio
n
mo
d
el
b
a
s
ed
o
n
le
n
g
th
o
f le
ft
h
a
n
d
b
o
n
e
fo
r
…
(
Mo
h
d
F
a
a
iz
ie
Da
r
ma
w
a
n
)
557
in
d
iv
id
u
a
ls,
‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
3
0
,
n
o
.
4
,
p
p
.
1
1
0
1
–
1
1
0
7
,
2
0
1
6
.
[3
1
]
T
.
L
u
c
a
s
a
n
d
M
.
He
n
n
e
b
e
rg
,
―
Esti
m
a
ti
n
g
a
c
h
il
d
’s
a
g
e
f
ro
m
a
n
ima
g
e
u
sin
g
w
h
o
le
b
o
d
y
p
ro
p
o
r
ti
o
n
s,‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
3
1
,
n
o
.
5
,
p
p
.
1
3
8
5
–
1
3
9
0
,
2
0
1
7
.
[3
2
]
A
.
De
Do
n
n
o
,
V
.
S
a
n
to
r
o
,
S
.
L
u
b
e
ll
i,
M
.
M
a
rro
n
e
,
P
.
L
o
z
it
o
,
a
n
d
F
.
In
tr
o
n
a
,
―
A
g
e
a
ss
e
ss
m
e
n
t
u
sin
g
th
e
G
re
u
li
c
h
a
n
d
P
y
le
m
e
th
o
d
o
n
a
h
e
tero
g
e
n
e
o
u
s
sa
m
p
le
o
f
3
0
0
Italian
h
e
a
lt
h
y
a
n
d
p
a
th
o
l
o
g
ic
su
b
jec
ts.
,
‖
F
o
re
n
sic
S
c
i.
I
n
t.
,
v
o
l.
2
2
9
,
n
o
.
1
–
3
,
p
.
1
5
7
.
e
1
-
6
,
Ju
n
.
2
0
1
3
.
[3
3
]
M
.
S
c
h
a
e
f
e
r,
L
.
Ha
c
k
m
a
n
,
a
n
d
J.
Ga
ll
a
g
h
e
r,
―
V
a
riab
il
it
y
in
d
e
v
e
lo
p
m
e
n
tal
ti
m
in
g
s
o
f
th
e
k
n
e
e
in
y
o
u
n
g
Am
e
rica
n
c
h
il
d
re
n
a
s
a
ss
e
ss
e
d
th
ro
u
g
h
P
y
le
a
n
d
Ho
e
rr’s
ra
d
io
g
ra
p
h
ic
a
tl
a
s,‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
3
0
,
n
o
.
2
,
p
p
.
5
0
1
–
5
0
9
,
2
0
1
6
.
[3
4
]
M
.
A
lcin
a
,
A
.
L
u
c
e
a
,
M
.
S
a
li
c
rú
,
a
n
d
D.
T
u
rb
ó
n
,
―
Re
li
a
b
il
i
ty
o
f
th
e
G
re
u
li
c
h
a
n
d
P
y
le
m
e
th
o
d
f
o
r
c
h
ro
n
o
l
o
g
ica
l
a
g
e
e
sti
m
a
ti
o
n
a
n
d
a
g
e
m
a
jo
rit
y
p
re
d
ictio
n
in
a
S
p
a
n
ish
sa
m
p
le,‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
3
2
,
n
o
.
4
,
p
p
.
1
1
3
9
–
1
1
4
9
,
2
0
1
8
.
[3
5
]
J.
E.
O’Co
n
n
o
r,
J
.
Co
y
le,
C.
B
o
g
u
e
,
L
.
D.
S
p
e
n
c
e
,
a
n
d
J.
L
a
s
t,
―
Ag
e
p
re
d
ictio
n
f
o
rm
u
lae
f
ro
m
ra
d
io
g
ra
p
h
ic
a
ss
e
ss
m
e
n
t
o
f
sk
e
let
a
l
m
a
tu
ra
ti
o
n
a
t
t
h
e
k
n
e
e
in
a
n
Irish
p
o
p
u
la
ti
o
n
.
,
‖
Fo
re
n
sic
S
c
i.
I
n
t.
,
v
o
l.
2
3
4
,
p
.
1
8
8
.
e
1
-
8
,
Ja
n
.
2
0
1
4
.
[3
6
]
J.
Iru
rit
a
Ol
iv
a
re
s
a
n
d
I.
A
le
m
á
n
A
g
u
il
e
ra
,
―
P
r
o
p
o
sa
l
o
f
n
e
w
re
g
re
ss
io
n
f
o
rm
u
lae
f
o
r
th
e
e
stim
a
ti
o
n
o
f
a
g
e
in
in
f
a
n
t
sk
e
leta
l
re
m
a
in
s f
ro
m
th
e
m
e
tri
c
stu
d
y
o
f
th
e
p
a
rs b
a
silaris,‖
In
t
.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
3
1
,
n
o
.
3
,
p
p
.
1
–
8
,
2
0
1
7
.
[3
7
]
K.
Zh
a
n
g
,
X
.
Do
n
g
,
F
.
F
a
n
,
a
n
d
Z.
De
n
g
,
―
Ag
e
e
sti
m
a
ti
o
n
b
a
se
d
o
n
p
e
lv
ic
o
ss
if
ica
ti
o
n
u
sin
g
re
g
re
ss
io
n
m
o
d
e
ls
f
ro
m
c
o
n
v
e
n
ti
o
n
a
l
ra
d
io
g
ra
p
h
y
,
‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l
.
1
3
0
,
n
o
.
4
,
p
p
.
1
1
4
3
–
1
1
4
8
,
2
0
1
6
.
[3
8
]
A
.
B.
M
á
rq
u
e
z
-
Ru
iz,
L
.
G
o
n
z
á
lez
-
He
rre
ra
,
a
n
d
A
.
V
a
len
z
u
e
la,
―
Us
e
f
u
ln
e
ss
o
f
telo
m
e
re
len
g
th
in
DN
A
f
ro
m
h
u
m
a
n
tee
th
f
o
r
a
g
e
e
sti
m
a
ti
o
n
,
‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l.
1
3
2
,
n
o
.
2
,
p
p
.
3
5
3
–
3
5
9
,
2
0
1
8
.
[3
9
]
L
.
a
Zad
e
h
,
―
F
u
z
z
y
lo
g
ic,
n
e
u
ra
l
n
e
tw
o
rk
s,
a
n
d
so
f
t
c
o
m
p
u
ti
n
g
,
‖
F
u
zz
y
S
y
st.
,
v
o
l.
3
7
,
p
p
.
7
7
–
8
4
,
1
9
9
4
.
[4
0
]
S
.
Rit
z
-
T
i
m
m
e
e
t
a
l
.
,
―
Ag
e
e
sti
m
a
ti
o
n
:
th
e
sta
te
o
f
th
e
a
rt
in
re
lati
o
n
to
th
e
sp
e
c
if
ic
d
e
m
a
n
d
s
o
f
f
o
r
e
n
sic
p
ra
c
ti
se
.
,
‖
In
t.
J
.
L
e
g
a
l
M
e
d
.
,
v
o
l
.
1
1
3
,
n
o
.
3
,
p
p
.
1
2
9
–
3
6
,
Ja
n
.
2
0
0
0
.
[4
1
]
C.
S
a
n
to
s,
M
.
F
e
rre
ira
,
F
.
C.
A
lv
e
s,
a
n
d
E.
Cu
n
h
a
,
―
Co
m
p
a
ra
ti
v
e
s
tu
d
y
o
f
G
r
e
u
li
c
h
a
n
d
P
y
le
A
tl
a
s
a
n
d
M
a
tu
r
o
s
4
.
0
p
ro
g
ra
m
f
o
r
a
g
e
e
sti
m
a
ti
o
n
i
n
a
P
o
rtu
g
u
e
se
sa
m
p
le.,
‖
Fo
re
n
sic
S
c
i.
In
t.
,
v
o
l.
2
1
2
,
n
o
.
1
–
3
,
p
.
2
7
6
.
e
1
-
7
,
Oc
t.
2
0
1
1
.
[4
2
]
L
.
M
o
li
n
a
ri,
T
.
G
a
ss
e
r,
a
n
d
R.
L
a
rg
o
,
―
A
c
o
m
p
a
riso
n
o
f
sk
e
leta
l
m
a
tu
rit
y
a
n
d
g
ro
w
th
.
,
‖
An
n
.
Hu
m.
Bi
o
l
.
,
v
o
l
.
4
0
,
n
o
.
4
,
p
p
.
3
3
3
–
4
0
,
J
u
l.
2
0
1
3
.
[4
3
]
A
.
A
l
-
Ha
d
laq
,
M
.
A
l
-
Qa
rn
i,
A
.
Al
-
Ka
h
tan
i,
a
n
d
A
.
A
l
-
Ob
a
id
,
―
Co
m
p
a
ra
ti
v
e
stu
d
y
b
e
twe
e
n
h
a
n
d
-
w
rist
m
e
th
o
d
a
n
d
c
e
rv
ica
l
v
e
rteb
ra
l
m
a
tu
ra
ti
o
n
m
e
t
h
o
d
f
o
r
e
v
a
lu
a
ti
o
n
o
f
sk
e
leta
l
m
a
t
u
rit
y
in
S
a
u
d
i
b
o
y
s,‖
Pa
k
ista
n
Or
a
l
De
n
t.
J
.
,
v
o
l
.
2
7
,
n
o
.
2
,
p
p
.
1
8
7
–
1
9
2
,
2
0
0
7
.
[4
4
]
R.
M
a
li
n
a
,
―
P
h
y
sic
a
l
a
c
ti
v
it
y
a
n
d
train
in
g
:
e
f
f
e
c
ts
o
n
sta
tu
re
a
n
d
a
d
o
les
c
e
n
t
g
ro
w
th
sp
u
rt,
‖
M
e
d
S
c
i
S
p
o
rt.
Exe
rc
,
v
o
l.
2
6
,
p
p
.
7
5
9
–
6
6
,
1
9
9
4
.
[4
5
]
E.
Bé
n
é
f
ice
,
D.
G
a
rn
ier,
a
n
d
G
.
Nd
iay
e
,
―
Hig
h
lev
e
ls
o
f
h
a
b
it
u
a
l
p
h
y
sic
a
l
a
c
ti
v
it
y
in
we
st
Af
rica
n
a
d
o
les
c
e
n
t
g
irl
s
a
n
d
re
lati
o
n
sh
ip
to
m
a
tu
ra
ti
o
n
,
g
ro
w
th
,
a
n
d
n
u
tri
t
io
n
a
l
sta
tu
s
:
re
su
lt
s
f
ro
m
a
3
-
y
e
a
r
p
ro
sp
e
c
ti
v
e
stu
d
y
.
,
‖
Am.
J
.
Hu
m.
Bi
o
l
.
,
v
o
l
.
1
3
,
n
o
.
6
,
p
p
.
8
0
8
–
2
0
,
2
0
0
1
.
[4
6
]
K.
L
e
n
in
,
B.
R.
Re
d
d
y
,
a
n
d
M
.
S
.
Ka
lav
a
th
i,
―
P
ro
g
re
ss
iv
e
P
a
rti
c
le
S
w
a
r
m
Op
ti
m
iza
ti
o
n
A
lg
o
rit
h
m
f
o
r
S
o
lv
in
g
Re
a
c
ti
v
e
P
o
w
e
r
P
ro
b
lem
,
‖
In
t.
J
.
Ad
v
.
In
tell.
I
n
fo
rm
a
ti
c
s
,
v
o
l.
1
,
n
o
.
3
,
p
p
.
1
2
5
–
1
3
1
,
2
0
1
5
.
[4
7
]
M
.
A
.
Is
m
a
il
,
V
.
M
e
z
h
u
y
e
v
,
K.
M
o
o
rt
h
y
,
S
.
Ka
si
m
,
a
n
d
A
.
O.
Ib
ra
h
im
,
―
Op
ti
m
is
a
ti
o
n
o
f
b
io
c
h
e
m
ica
l
s
y
ste
m
s
p
ro
d
u
c
ti
o
n
u
si
n
g
h
y
b
rid
o
f
n
e
w
to
n
m
e
th
o
d
,
d
if
f
e
re
n
ti
a
l
e
v
o
lu
ti
o
n
a
lg
o
rit
h
m
a
n
d
c
o
o
p
e
ra
ti
v
e
c
o
e
v
o
lu
ti
o
n
a
lg
o
rit
h
m
,
‖
In
d
o
n
e
s.
J
.
El
e
c
tr.
E
n
g
.
Co
m
p
u
t
.
S
c
i
.
,
v
o
l.
8
,
n
o
.
1
,
p
p
.
2
7
–
3
5
,
2
0
1
7
.
[4
8
]
M
.
A
.
Is
m
a
il
,
V
.
M
e
z
h
u
y
e
v
,
S
.
D
e
ris,
M
.
S
.
M
o
h
a
m
a
d
,
S
.
Ka
si
m
,
a
n
d
R.
S
a
e
d
u
d
in
,
―
M
u
lt
i
-
o
b
jec
ti
v
e
Op
ti
m
iz
a
ti
o
n
o
f
Bio
c
h
e
m
ica
l
S
y
st
e
m
P
ro
d
u
c
ti
o
n
Us
in
g
a
n
Im
p
ro
v
e
Ne
w
to
n
Co
m
p
e
ti
ti
v
e
Di
ff
e
r
e
n
ti
a
l
Ev
o
lu
t
io
n
M
e
th
o
d
,
‖
In
t.
J
.
Ad
v
.
S
c
i
.
En
g
.
I
n
f.
T
e
c
h
n
o
l.
,
v
o
l.
7
,
n
o
.
4
–
2
,
p
p
.
1
5
3
5
–
1
5
4
2
,
2
0
1
7
.
[4
9
]
M
.
K.
K
h
a
lee
l,
M
.
A
.
Ism
a
il
,
U.
Yu
n
a
n
,
a
n
d
S
.
Ka
sim
,
―
Re
v
ie
w
o
n
In
t
ru
sio
n
De
tec
ti
o
n
S
y
ste
m
Ba
s
e
d
o
n
T
h
e
G
o
a
l
o
f
T
h
e
De
tec
ti
o
n
S
y
ste
m
,
‖
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
In
teg
r
a
ted
En
g
in
e
e
rin
g
,
v
o
l.
1
0
,
n
o
.
6
,
2
0
1
8
.
[5
0
]
Zu
n
a
i
d
i,
W
.
H.
A
.
W
.
,
S
a
e
d
u
d
in
,
R.
R.
,
S
h
a
h
,
Z
.
A
.
,
Ka
si
m
,
S
.
,
S
e
a
h
,
C.
S
.
,
&
A
b
d
u
ro
h
m
a
n
,
M
.
―
P
e
rf
o
rm
a
n
c
e
s
A
n
a
l
y
si
s
o
f
H
e
a
rt
Dise
a
se
D
a
t
a
se
t
u
sin
g
Diffe
re
n
t
Da
ta
M
in
in
g
Clas
sif
ic
a
ti
o
n
s
,‖
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
n
Ad
v
a
n
c
e
d
S
c
ien
c
e
,
E
n
g
i
n
e
e
rin
g
a
n
d
I
n
fo
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
8
(
6
),
2
6
7
7
-
2
6
8
2
,
2
0
1
8
.
[5
1
]
Ku
sa
iri
,
R.
M
.
,
M
o
o
rt
h
y
,
K.,
H
a
ro
n
,
H.
,
M
o
h
a
m
a
d
,
M
.
S
.
,
Na
p
is,
S
.
,
&
Ka
sim
,
S
.
―
A
n
Im
p
ro
v
e
d
P
a
ra
ll
e
li
z
e
d
m
RM
R
f
o
r
G
e
n
e
S
u
b
se
t
S
e
le
c
ti
o
n
in
Ca
n
c
e
r
Clas
sif
i
c
a
ti
o
n
,‖
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
n
Ad
v
a
n
c
e
d
S
c
ien
c
e
,
En
g
i
n
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
7
(
4
-
2
)
,
1
5
9
5
-
1
6
0
0
,
2
0
1
7
.
[5
2
]
Na
sru
d
in
,
N.
A
.
,
Ch
a
n
,
W
.
H.,
M
o
h
a
m
a
d
,
M
.
S
.
,
De
ris,
S
.
,
Na
p
i
s,
S
.
,
&
Ka
sim
,
S
.
―
P
a
th
w
a
y
-
b
a
s
e
d
A
n
a
l
y
sis
w
it
h
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
(S
VM
-
LA
S
S
O)
f
o
r
G
e
n
e
S
e
l
e
c
ti
o
n
a
n
d
Clas
sif
ic
a
ti
o
n
,‖
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
n
Ad
v
a
n
c
e
d
S
c
ien
c
e
,
E
n
g
i
n
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
7
(
4
-
2
),
1
6
0
9
-
1
6
1
4
,
2
0
1
7
.
[5
3
]
Na
w
i,
N.
M
.
,
Zaid
i,
N.
M
.
,
Ha
m
i
d
,
N.
A
.
,
Re
h
m
a
n
,
M
.
Z.
,
Ra
m
li
,
A
.
A
.
,
&
Ka
si
m
,
S
.
―
Op
ti
m
a
l
P
a
ra
m
e
ter S
e
le
c
ti
o
n
Us
in
g
T
h
re
e
-
ter
m
Ba
c
k
P
ro
p
a
g
a
ti
o
n
A
lg
o
rit
h
m
f
o
r
Da
ta
Clas
sif
ica
ti
o
n
,‖
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
n
Ad
v
a
n
c
e
d
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
l
o
g
y
,
7
(
4
-
2
),
1
5
2
8
-
1
5
3
4
,
2
0
1
7
.
[5
4
]
Ha
sri,
N.
M
.
,
W
e
n
,
N.
H.,
Ho
w
e
,
C.
W
.
,
M
o
h
a
m
a
d
,
M
.
S
.
,
De
r
is,
S
.
,
&
Ka
sim
,
S
,
―
I
m
p
ro
v
e
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
u
sin
g
m
u
lt
ip
le
S
V
M
-
RF
E
f
o
r
c
a
n
c
e
r
c
las
sif
ica
ti
o
n
,‖
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
n
Ad
v
a
n
c
e
d
S
c
ien
c
e
,
En
g
i
n
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
7
(
4
-
2
)
,
1
5
8
9
-
1
5
9
4
,
2
0
1
7
.
[5
5
]
Nie
s,
H.
W
.
,
Da
u
d
,
K.
M
.
,
Re
m
li
,
M
.
A
.
,
M
o
h
a
m
a
d
,
M
.
S
.
,
De
ris,
S
.
,
Om
a
tu
,
S
.
,
.
.
.
&
S
u
l
o
n
g
,
G
.
―
Cla
ss
if
ica
ti
o
n
o
f
Co
lo
re
c
ta
l
Ca
n
c
e
r
Us
in
g
Clu
ste
r
in
g
a
n
d
Fe
a
tu
re
S
e
lec
ti
o
n
Ap
p
r
o
a
c
h
e
s
,”
In
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
P
ra
c
ti
c
a
l
A
p
p
li
c
a
ti
o
n
s o
f
Co
m
p
u
tati
o
n
a
l
Bi
o
lo
g
y
&
Bio
in
f
o
rm
a
ti
c
s
(p
p
.
5
8
-
6
5
).
S
p
rin
g
e
r,
C
h
a
m
,
Ju
n
e
,
2
0
1
7
.
[5
6
]
Re
m
li
,
M
.
A
.
,
Da
u
d
,
K
.
M
.
,
Ni
e
s,
H.
W
.
,
M
o
h
a
m
a
d
,
M
.
S
.
,
D
e
ris,
S
.
,
Om
a
tu
,
S
.
,
.
.
.
&
S
u
l
o
n
g
,
G
.
“
K
-
me
a
n
s
c
lu
ste
rin
g
w
it
h
in
f
in
it
e
fea
t
u
re
se
lec
ti
o
n
f
o
r
c
la
ss
if
ica
ti
o
n
ta
sk
s
in
g
e
n
e
e
x
p
re
ss
io
n
d
a
t
a
,”
In
I
n
tern
a
ti
o
n
a
l
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.
10
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
0
:
549
-
558
558
Co
n
f
e
re
n
c
e
o
n
P
ra
c
ti
c
a
l
A
p
p
li
c
a
ti
o
n
s
o
f
Co
m
p
u
tatio
n
a
l
Bi
o
lo
g
y
&
Bio
in
f
o
rm
a
ti
c
s
(p
p
.
5
0
-
5
7
).
S
p
rin
g
e
r,
Ch
a
m
,
Ju
n
e
,
2
0
1
7
.
[5
7
]
S
ian
g
,
T
.
C.
,
S
o
o
n
,
T
.
W
.
,
Ka
sim
,
S
.
,
M
o
h
a
m
a
d
,
M
.
S
.
,
Ho
w
e
,
C.
W
.
,
De
ris,
S
.
,
.
.
.
&
Ib
ra
h
im
,
Z.
―
A
re
v
ie
w
o
f
c
a
n
c
e
r
c
las
si
f
ica
ti
o
n
so
f
t
w
a
re
f
o
r
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta,‖
In
t
e
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Bio
-
S
c
ie
n
c
e
a
n
d
Bi
o
-
T
e
c
h
n
o
l
o
g
y
,
7
(
4
),
8
9
-
1
0
8
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.