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
.
6
,
Dec
em
b
er
2
0
2
0
,
p
p
.
6
6
5
5
~
6
6
6
3
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
0
i
6
.
pp
6
6
5
5
-
6
6
6
3
6655
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
H
y
brid
ba
t
-
an
t
co
lo
ny
opti
m
i
z
a
tion a
lg
o
rith
m
f
o
r r
ul
e
-
ba
sed
f
ea
ture
s
elect
io
n
i
n
h
ea
lth
c
a
re
Ra
f
id Sa
g
ba
n
1
,
H
a
y
da
r
A.
M
a
rho
o
n
2
,
Ra
a
id Alub
a
dy
3
1,
3
F
a
c
u
lt
y
o
f
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
Un
iv
e
rsit
y
o
f
Ba
b
y
lo
n
,
Ira
q
2
Co
ll
e
g
e
o
f
S
c
ien
c
e
,
Un
iv
e
rsit
y
o
f
Ke
rb
a
la,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
27
,
2
0
1
9
R
ev
i
s
ed
Ma
y
31
,
2020
A
cc
ep
ted
J
u
n
1
7
,
2
0
2
0
Ru
le
-
b
a
se
d
c
las
sif
ic
a
ti
o
n
in
t
h
e
f
ield
o
f
h
e
a
lt
h
c
a
re
u
sin
g
a
rti
f
icia
l
in
telli
g
e
n
c
e
p
r
o
v
id
e
s
so
l
u
ti
o
n
s
in
d
e
c
isio
n
-
m
a
k
in
g
p
ro
b
lem
s
in
v
o
lv
in
g
d
if
fe
re
n
t
d
o
m
a
in
s.
A
n
i
m
p
o
rtan
t
c
h
a
ll
e
n
g
e
is
p
ro
v
id
in
g
a
c
c
e
ss
to
g
o
o
d
a
n
d
f
a
st
h
e
a
lt
h
fa
c
il
it
ies
.
Ce
rv
ic
a
l
c
a
n
c
e
r
i
s
o
n
e
o
f
th
e
m
o
st
f
re
q
u
e
n
t
c
a
u
se
s
o
f
d
e
a
th
i
n
f
e
m
a
les
.
T
h
e
d
iag
n
o
stic
m
e
th
o
d
s
f
o
r
c
e
rv
ica
l
c
a
n
c
e
r
u
se
d
i
n
h
e
a
lt
h
c
e
n
ters
a
re
c
o
stl
y
a
n
d
ti
m
e
-
c
o
n
su
m
in
g
.
In
th
is
p
a
p
e
r,
b
a
t
a
lg
o
rit
h
m
f
o
r
f
e
a
tu
re
se
lec
ti
o
n
a
n
d
a
n
t
c
o
lo
n
y
o
p
ti
m
iza
ti
o
n
-
b
a
se
d
c
las
sif
ica
ti
o
n
a
lg
o
rit
h
m
w
e
r
e
a
p
p
li
e
d
o
n
c
e
rv
ica
l
c
a
n
c
e
r
d
a
ta
se
t
o
b
tain
e
d
f
ro
m
th
e
re
p
o
sito
ry
o
f
th
e
Un
iv
e
rsit
y
o
f
Ca
li
f
o
rn
ia,
Irv
i
n
e
to
a
n
a
ly
z
e
th
e
d
ise
a
se
b
a
se
d
o
n
o
p
ti
m
a
l
f
e
a
tu
re
s.
T
h
e
p
ro
p
o
se
d
a
lg
o
rit
h
m
o
u
tp
e
rf
o
rm
s
o
th
e
r
m
e
th
o
d
s
i
n
term
s
o
f
c
o
m
p
re
h
e
n
sib
il
it
y
a
n
d
o
b
tai
n
s
b
e
tt
e
r
re
su
lt
s
in
term
s
o
f
c
la
ss
if
ic
a
ti
o
n
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
An
t
c
o
lo
n
y
o
p
ti
m
izatio
n
B
at
a
lg
o
r
ith
m
Dete
ctio
n
m
ak
i
n
g
Featu
r
e
s
elec
t
io
n
R
u
le
-
b
ased
c
las
s
i
f
icatio
n
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
:
R
af
id
Sa
g
b
an
,
Facu
lt
y
o
f
I
n
f
o
r
m
a
tio
n
T
ec
h
n
o
lo
g
y
Un
i
v
er
s
it
y
o
f
B
ab
y
lo
n
,
I
r
aq
.
E
m
ail: r
s
a
g
b
an
@
u
o
b
ab
y
lo
n
.
e
d
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
D
if
f
e
r
en
t
t
e
ch
n
o
l
o
g
i
es
an
d
c
o
n
s
i
d
e
r
a
b
l
e
d
a
ta
h
av
e
b
e
en
a
p
p
l
i
ed
i
n
d
if
f
e
r
en
t
f
i
e
l
d
s
.
I
n
th
e
m
e
d
i
c
a
l
f
i
e
l
d
,
d
a
t
a
m
i
n
i
n
g
p
l
ay
s
an
im
p
o
r
ta
n
t
r
o
l
e
i
n
th
e
p
r
e
d
i
c
ti
o
n
o
f
d
i
s
ea
s
es
.
D
a
t
a
m
in
in
g
u
s
es
m
a
ch
in
e
l
e
a
r
n
i
n
g
,
a
r
tif
i
c
ia
l
i
n
te
l
li
g
e
n
c
e
,
an
d
s
t
at
is
t
ic
a
l
p
o
w
e
r
t
o
d
ev
el
o
p
h
ig
h
ly
a
cc
u
r
a
t
e
p
r
e
d
i
ct
iv
e
m
o
d
e
ls
f
o
r
c
r
i
t
i
c
al
d
o
m
a
in
s
[
1
]
.
C
an
c
e
r
is
a
t
o
p
i
c
o
f
in
t
e
r
e
s
t
in
th
e
m
e
d
i
c
a
l
f
i
e
l
d
an
d
th
e
p
r
im
a
r
y
ca
u
s
e
o
f
m
o
r
t
al
i
ty
w
o
r
ld
w
i
d
e
[
2
]
.
C
e
r
v
ic
a
l
c
a
n
c
e
r
is
th
e
f
o
u
r
t
h
m
o
s
t
w
i
d
e
s
p
r
e
a
d
f
o
r
m
o
f
c
a
n
c
e
r
i
n
w
o
m
en
[
3
]
a
n
d
s
ev
en
t
h
am
o
n
g
a
l
l
k
n
o
w
n
c
an
c
e
r
s
.
T
h
e
s
p
r
e
a
d
o
f
c
e
r
v
i
c
a
l
c
an
c
e
r
is
i
n
d
u
c
e
d
b
y
th
e
ch
an
g
es
i
n
g
en
es
t
h
a
t
d
o
m
in
at
e
th
e
g
r
o
w
th
an
d
s
p
l
it
f
u
n
c
ti
o
n
o
f
c
e
l
ls
.
T
h
i
s
c
an
c
e
r
s
p
r
e
a
d
s
t
o
o
th
e
r
p
a
r
t
s
o
f
t
h
e
b
o
d
y
,
s
u
ch
a
s
th
e
lu
n
g
s
a
n
d
th
e
a
b
d
o
m
en
,
w
ith
o
u
t
e
x
h
i
b
i
t
in
g
a
n
y
s
y
m
p
t
o
m
s
.
T
h
u
s
,
n
o
s
ig
n
s
c
an
b
e
o
b
s
e
r
v
e
d
i
n
th
e
e
a
r
ly
s
t
ag
e
s
o
f
th
e
d
is
e
a
s
e
a
n
d
s
y
m
p
t
o
m
s
i
n
c
lu
d
in
g
p
e
l
v
i
c
p
a
i
n
,
b
a
ck
p
a
in
,
f
at
ig
u
e
,
b
r
o
k
en
b
o
n
es
,
le
g
p
ain
,
w
e
ig
h
t
l
o
s
s
,
a
n
d
v
ag
in
a
l
b
le
e
d
in
g
,
a
p
p
e
a
r
in
t
h
e
l
a
t
e
s
t
ag
es
.
Mo
r
eo
v
er
,
n
o
r
o
u
tin
e
s
cr
ee
n
in
g
m
et
h
o
d
f
o
r
ce
r
v
ical
c
an
ce
r
is
b
ei
n
g
p
r
ac
ticed
es
p
ec
iall
y
i
n
lo
w
-
i
n
co
m
e
co
u
n
tr
ies.
C
er
v
ic
al
ca
n
ce
r
in
s
u
ch
co
u
n
tr
ie
s
is
p
r
o
n
e
to
s
p
r
ea
d
r
ap
id
ly
b
ec
au
s
e
o
f
th
e
i
n
cr
ea
s
ed
ex
p
o
s
u
r
e
to
s
ev
er
al
ca
n
ce
r
r
is
k
f
ac
to
r
s
,
in
c
lu
d
i
n
g
h
u
m
a
n
p
ap
illo
m
av
ir
u
s
(
HP
V)
[
4
]
,
an
d
s
o
m
e
o
t
h
er
f
ac
to
r
s
,
s
u
c
h
as
co
n
tr
ac
ep
ti
v
e
u
s
e,
ci
g
ar
ette
s
m
o
k
i
n
g
,
an
d
th
e
n
u
m
b
er
o
f
p
r
eg
n
a
n
cies.
I
n
f
ac
t,
d
o
cto
r
s
m
u
s
t
k
n
o
w
th
e
f
ac
to
r
s
t
h
at
ca
u
s
e
t
h
e
d
is
ea
s
e.
T
h
er
ef
o
r
e,
in
t
h
e
d
ia
g
n
o
s
is
o
f
ce
r
v
ical
ca
n
ce
r
,
t
h
e
e
x
tr
ac
tio
n
o
f
r
ele
v
an
t
f
ea
t
u
r
es
is
i
m
p
o
r
tan
t.
T
h
e
ch
a
n
ce
s
o
f
ce
r
v
ical
ca
n
ce
r
i
n
cr
ea
s
e
t
w
o
o
r
th
r
ee
ti
m
es
w
h
e
n
t
h
e
p
er
s
o
n
is
s
m
o
k
in
g
o
r
in
f
ec
ted
w
it
h
HP
V
[
5
]
.
T
h
e
r
ate
o
f
ce
r
v
ical
ca
n
ce
r
in
w
o
m
en
w
h
o
u
s
e
co
n
tr
ac
ep
ti
v
es
i
s
th
r
ee
ti
m
e
s
h
i
g
h
er
th
an
t
h
o
s
e
w
h
o
d
o
n
o
t
u
s
e
s
u
ch
,
an
d
w
o
m
en
w
h
o
h
a
v
e
u
s
e
d
co
n
tr
ac
ep
tiv
es
f
o
r
m
o
r
e
th
a
n
1
0
y
ea
r
s
i
n
cr
ea
s
e
th
eir
r
is
k
f
o
r
co
n
tr
ac
ti
n
g
ce
r
v
i
ca
l
ca
n
ce
r
f
o
u
r
f
o
ld
.
Mo
r
eo
v
er
,
th
e
i
n
cid
en
ce
o
f
ce
r
v
ical
ca
n
ce
r
in
w
o
m
en
w
h
o
h
av
e
n
o
t
ex
p
er
ien
ce
d
p
r
eg
n
a
n
c
y
a
n
d
ar
e
i
n
f
ec
ted
w
it
h
HP
V
is
lo
w
er
t
h
a
n
i
n
w
o
m
e
n
w
h
o
h
av
e
e
x
p
er
ien
ce
d
at
least
o
n
e
p
r
eg
n
a
n
c
y
.
T
h
er
ef
o
r
e,
ex
tr
ac
tin
g
th
e
r
elev
a
n
t
tr
ai
t
s
is
i
m
p
o
r
tan
t
in
d
iag
n
o
s
i
n
g
th
e
r
is
k
f
ac
to
r
s
th
at
ca
u
s
e
t
h
e
d
is
ea
s
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
.
6
,
Dec
em
b
er
2
0
2
0
:
6
6
5
5
-
6
6
6
3
6656
Dif
f
u
s
io
n
-
w
e
ig
h
ted
i
m
a
g
i
n
g
an
d
m
a
g
n
et
ic
r
eso
n
an
ce
i
m
a
g
i
n
g
ca
n
d
etec
t
ce
r
v
ical
ca
n
ce
r
at
a
ce
r
tain
s
tag
e
[
6
,
7
]
.
T
h
e
P
ap
test
[
8
]
is
a
p
o
p
u
lar
an
d
p
r
ef
er
r
ed
m
et
h
o
d
o
f
s
cr
ee
n
i
n
g
ce
r
v
ical
ca
n
ce
r
.
Ho
w
e
v
er
,
p
eo
p
le
h
av
e
lo
w
a
w
ar
e
n
ess
o
f
r
o
u
tin
e
s
cr
ee
n
i
n
g
in
d
ev
e
lo
p
in
g
co
u
n
tr
ies.
I
n
ad
d
itio
n
,
lim
ited
m
ed
ical
ex
p
er
tis
e
a
n
d
th
e
lac
k
o
f
m
e
d
ical
eq
u
ip
m
e
n
t
i
n
cr
ea
s
e
t
h
e
m
o
r
ta
lit
y
r
ate
o
f
ce
r
v
ical
ca
n
ce
r
in
lo
w
-
in
co
m
e
co
u
n
tr
ies.
I
n
t
h
is
p
ap
er
,
B
A
is
ap
p
lied
f
o
r
FS
to
p
r
o
g
r
ess
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
AC
O
-
b
a
s
ed
cla
s
s
i
f
icatio
n
alg
o
r
ith
m
to
an
al
y
s
e
s
th
e
ce
r
v
ical
ca
n
ce
r
d
ata
s
et
f
r
o
m
th
e
r
ep
o
s
ito
r
y
o
f
t
h
e
Un
i
v
er
s
i
t
y
o
f
C
ali
f
o
r
n
ia
at
I
r
v
in
e
(
UC
I
)
.
T
h
is
w
o
r
k
s
h
o
w
s
t
h
at
t
h
e
AC
O
m
et
h
o
d
ca
n
class
i
f
y
ce
r
v
ical
ca
n
ce
r
.
C
o
m
b
i
n
i
n
g
t
h
e
A
C
O
w
ith
t
h
e
b
at
alg
o
r
ith
m
co
u
ld
r
ed
u
ce
t
h
e
co
m
p
u
tat
io
n
b
u
r
d
en
a
n
d
en
ab
le
t
h
e
ex
tr
ac
tio
n
o
f
h
ig
h
l
y
co
r
r
elate
d
r
is
k
f
ac
to
r
s
.
2.
B
AT
AL
G
O
RI
T
H
M
F
O
R
F
E
AT
URE
SE
L
E
C
T
I
O
N
Sev
er
al
s
w
ar
m
in
telli
g
en
ce
alg
o
r
ith
m
s
h
av
e
b
ee
n
u
s
ed
in
th
e
attr
ib
u
te
s
s
ele
cti
o
n
[
9
-
1
7
]
.
Un
f
o
r
tu
n
atel
y
,
n
o
s
i
n
g
le
s
tab
le
s
tr
ateg
y
ex
is
t
s
to
r
ed
u
ce
th
e
b
u
r
d
en
o
f
co
m
p
u
ti
n
g
an
d
ex
tr
ac
tin
g
h
ig
h
l
y
co
r
r
elate
d
r
is
k
f
ac
to
r
s
to
th
e
d
ata
an
d
im
p
r
o
v
e
th
e
clas
s
if
ier
p
er
f
o
r
m
a
n
ce
an
d
ac
h
ie
v
e
h
i
g
h
ac
c
u
r
ac
y
.
S
w
ar
m
i
n
telli
g
e
n
ce
alg
o
r
it
h
m
s
ar
e
i
m
p
o
r
tan
t
i
n
s
o
lv
in
g
p
r
o
b
lem
s
r
eg
ar
d
in
g
attr
ib
u
tes
s
elec
tio
n
.
Ho
w
ev
er
,
th
ese
alg
o
r
it
h
m
s
ar
e
li
m
ited
.
B
at
alg
o
r
it
h
m
w
as
u
s
ed
f
o
r
attr
ib
u
te
s
s
elec
tio
n
.
T
h
e
r
esu
l
ts
s
p
ec
if
ied
th
e
s
u
g
g
e
s
ted
alg
o
r
it
h
m
o
u
tp
e
r
f
o
r
m
s
o
t
h
er
alg
o
r
it
h
m
s
[
1
8
]
.
B
at
alg
o
r
ith
m
ca
n
b
e
a
v
a
l
u
a
b
le
o
p
tio
n
to
s
o
lv
e
th
is
p
r
o
b
le
m
f
o
r
h
i
g
h
d
i
m
e
n
s
io
n
al
d
ata.
T
h
e
b
est
s
u
b
s
et
o
f
attr
ib
u
tes
f
r
o
m
d
if
f
er
en
t
d
at
a
s
izes
is
s
elec
ted
.
T
h
e
B
A
an
d
th
e
o
cc
asio
n
tec
h
n
iq
u
e
f
o
r
FS
ar
e
d
is
cu
s
s
ed
in
t
h
e
n
e
x
t sect
io
n
.
B
ats
ar
e
ex
ce
llen
t
a
n
d
ad
v
an
c
ed
in
ter
m
s
o
f
e
c
h
o
lo
ca
tio
n
.
B
ats
ca
n
m
ak
e
a
d
is
ti
n
ctio
n
b
et
w
ee
n
p
r
e
y
an
d
b
ar
r
ier
s
.
T
h
is
r
em
ar
k
ab
le
ch
ar
ac
ter
is
tic
h
a
s
b
r
o
u
g
h
t
it
to
r
esear
ch
er
s
in
ter
m
s
o
f
its
u
s
e
in
v
ar
io
u
s
f
ield
s
.
B
ats
e
m
it
a
h
i
g
h
an
d
s
h
o
r
t
p
u
ls
e
o
f
s
o
u
n
d
an
d
w
ait
f
o
r
th
e
s
o
u
n
d
to
h
it
a
ce
r
tain
o
b
j
ec
t
.
I
n
a
b
r
ief
s
p
an
o
f
ti
m
e,
t
h
e
ec
h
o
r
etu
r
n
s
to
th
e
ea
r
s
ag
ain
.
T
h
r
o
u
g
h
t
h
is
w
a
y
,
th
e
b
at
ca
n
ca
lc
u
late
h
o
w
f
ar
th
i
s
o
b
j
ec
t
is
.
I
n
ad
d
itio
n
,
b
ats
p
o
s
s
es
s
a
n
a
m
az
i
n
g
tr
ea
d
m
ill
m
ec
h
a
n
i
s
m
t
h
at
m
a
k
es
b
at
s
ca
p
ab
le
o
f
d
is
t
in
g
u
i
s
h
in
g
b
et
w
ee
n
p
r
ey
an
d
o
b
s
tacle
an
d
ch
a
s
in
g
in
co
m
p
lete
d
ar
k
n
es
s
.
B
ased
o
n
th
e
b
at'
s
b
eh
a
v
io
r
an
d
its
ab
ilit
y
to
tr
ac
k
th
e
p
r
ey
i
n
t
h
e
d
ar
k
o
f
d
ar
k
n
e
s
s
.
Yan
g
[
1
9
]
d
ev
elo
p
ed
an
i
n
ter
esti
n
g
an
d
n
e
w
id
ea
ca
lled
th
e
b
at
alg
o
r
ith
m
.
T
h
e
tech
n
iq
u
e
o
f
m
eta
-
o
p
ti
m
i
za
tio
n
is
b
est
k
n
o
w
n
.
T
h
e
te
ch
n
iq
u
e
h
as
b
ee
n
i
m
p
r
o
v
ed
an
d
d
ev
elo
p
ed
u
s
in
g
its
ec
h
o
lo
ca
tio
n
ca
p
ab
ilit
y
to
tr
ac
k
f
o
o
d
,
p
r
ey
,
an
d
b
ar
r
ier
s
.
T
h
e
b
at
alg
o
r
ith
m
d
ea
l
s
w
it
h
th
r
ee
r
u
les,
th
e
y
ar
e:
-
B
ats u
s
e
ec
h
o
lo
ca
tio
n
in
s
en
s
i
n
g
s
p
ac
e.
B
ats ca
n
d
if
f
er
en
tia
t
e
b
et
w
ee
n
d
a
n
g
er
a
n
d
f
o
o
d
.
-
B
ats
(
b
i)
f
l
y
r
a
n
d
o
m
l
y
w
i
th
v
elo
cit
y
(
v
i)
at
p
o
s
itio
n
(
x
i)
w
it
h
a
f
i
x
ed
f
r
eq
u
en
c
y
(
f
m
in
)
,
w
i
th
v
ar
y
i
n
g
w
a
v
ele
n
g
t
h
‘
(
λ
)
’
an
d
lo
u
d
n
es
s
‘
(
A
0
)
’
to
s
ea
r
ch
f
o
r
p
r
ey
s
.
B
ats
(
b
i)
ca
n
au
to
m
atica
ll
y
s
e
t
th
e
w
a
v
ele
n
g
t
h
(
o
r
f
r
eq
u
en
c
y
)
o
f
th
eir
e
m
itt
ed
p
u
ls
es
a
n
d
ad
j
u
s
t
th
e
r
ate
o
f
p
u
ls
e
e
m
i
s
s
io
n
r
∈
[
0
,
1
]
d
ep
en
d
in
g
o
n
th
e
p
r
o
x
i
m
it
y
o
f
th
eir
tar
g
et.
;
an
d
-
L
o
u
d
n
ess
ca
n
v
ar
y
i
n
m
a
n
y
wa
y
s
.
Ya
n
g
(
2
0
1
0
)
ass
u
m
ed
t
h
at
th
e
lo
u
d
n
e
s
s
v
ar
ie
s
f
r
o
m
a
lar
g
e
(
p
o
s
iti
v
e)
,
0
to
a
m
in
i
m
u
m
co
n
s
tan
t
v
al
u
e
.
T
h
e
alg
o
r
ith
m
(
B
A
)
p
r
o
v
ed
to
b
e
m
o
r
e
ef
f
ic
ien
t
t
h
an
th
e
P
SO
an
d
g
en
etic
alg
o
r
ith
m
[
1
9
]
b
ec
au
s
e
th
e
alg
o
r
it
h
m
d
ea
ls
w
i
th
t
h
e
i
m
p
r
ess
i
v
e
ad
v
an
tag
e
s
o
f
P
SO
an
d
g
e
n
etic
alg
o
r
it
h
m
a
n
d
b
ec
au
s
e
B
A
h
as
th
e
ca
p
ac
it
y
o
f
f
r
eq
u
e
n
c
y
t
u
n
i
n
g
a
n
d
au
to
m
atic
zo
o
m
b
ec
au
s
e
o
f
f
le
x
ib
ili
t
y
[
2
0
]
.
Alg
o
rit
h
m
1
s
h
o
w
s
t
h
e
B
A
(
a
d
ap
ted
f
r
o
m
[
1
9
]
):
Objective function (
),
= (
1, ...,
).
Initialize the bat population
and
,
= 1, 2, ...,.
Define pulse frequency
at
,
∀
= 1, 2, . . . ,
.
Initialize pulse rates
and the loudness
,
=
1
,
2,
.
.
.
”
1. While
<
2. For each bat
, do
3. Generate new solutions through Equations (1),
4. (2) and (3).
5. If
>
, then
6. Select a solution among the best solutions.
7.
Generate a local solution around the
8. best solution.
9. If
<
and (
) < (ˆ
), then
10. Accept new solutions.
11. Increase
and reduce
.
12. Rank the bats and find the current best
ˆ
.
”
First,
t
h
e
f
r
eq
u
e
n
c
y
“
”
,
v
elo
cit
y
“
”
,
an
d
p
o
s
it
io
n
“
”
ar
e
in
i
tiated
f
o
r
ev
er
y
b
at
”
.
E
v
er
y
ti
m
e
p
h
ase
”
,
th
e
h
i
g
h
e
s
t
d
ig
i
t
o
f
r
eiter
atio
n
,
“
a
”
v
ir
t
u
al
b
at’
s
ac
t
iv
it
y
is
s
et
b
y
u
p
d
atin
g
th
e
p
o
s
itio
n
a
n
d
v
elo
cit
y
u
s
i
n
g
(
1
)
to
(
3
)
as f
o
llo
w
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
b
a
t
-
a
n
t c
o
lo
n
y
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
fo
r
r
u
le
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
in
h
ea
lth
c
a
r
e
(
R
a
fid
S
a
g
b
a
n
)
6657
=
m
in
+
(
m
in
−
m
a
x
)
,
(
1
)
(
)
=
(
−
1
)
+
[
ˆ
–
(
−
1
)
]
,
(
2
)
(
)
=
(
−
1
)
+
(
)
(
3
)
w
h
er
e
”
is
t
h
e
r
an
d
o
m
l
y
cr
ea
ted
d
ig
it
d
u
r
in
g
th
e
p
er
io
d
[
1
,
0
]
.
T
h
e
co
ef
f
icien
t
“
(
)
”
is
eq
u
iv
ale
n
t
to
v
ar
iab
le
“
”
f
o
r
b
at
at
ti
m
e
p
h
ase
.
T
h
e
f
ee
d
b
ac
k
o
f
”
in
(
1
)
is
u
s
ed
to
o
b
s
er
v
e
th
e
s
co
p
e
o
f
th
e
m
o
tio
n
o
f
th
e
b
ats
a
n
d
p
ac
e.
A
v
ar
iab
le
”
p
er
f
o
r
m
s
t
h
e
e
x
is
t
in
g
t
h
e
g
lo
b
al
b
est
s
o
lu
tio
n
(
p
o
s
itio
n
)
f
o
r
th
e
r
u
le
v
ar
iab
le
,
”
w
h
ic
h
is
co
m
p
ar
ed
w
it
h
all
th
e
s
o
l
u
tio
n
s
d
o
n
e
b
y
th
e
”
b
ats.
T
h
e
v
ar
iab
ilit
y
o
f
th
e
p
o
ten
tial
s
o
l
u
tio
n
i
s
d
er
iv
ed
.
Yan
g
[
1
9
]
p
r
o
p
o
s
ed
t
o
u
s
e
w
al
k
s
r
an
d
o
m
l
y
.
Mo
s
t
o
f
th
e
ti
m
e,
o
n
e
s
o
lu
tio
n
is
ch
o
s
en
a
m
o
n
g
t
h
e
b
est
s
o
lu
tio
n
s
.
T
h
e
n
,
t
h
e
ca
s
u
al
w
a
lk
i
s
u
s
ed
to
cr
ea
t
e
a
n
e
w
s
o
l
u
tio
n
to
e
v
er
y
b
at
t
h
at
tak
e
s
t
h
e
ca
s
e
i
n
L
in
e
5
o
f
A
l
g
o
r
ith
m
1
:
=
+ (
),
(
4
)
”
in
ev
er
y
(
)
”
p
er
f
o
r
m
s
th
e
r
a
te
tu
n
e
o
f
all
b
ats
at
ti
m
e
,
an
d
∈
[
−1
,
1
]
p
o
w
er
o
f
t
h
e
r
an
d
o
m
w
alk
a
n
d
atte
m
p
ts
t
h
e
d
ir
ec
tio
n
.
E
v
er
y
i
ter
atio
n
o
f
t
h
is
m
et
h
o
d
,
t
h
e
e
m
is
s
io
n
p
u
l
s
e
r
ate
”
ar
e
u
p
d
ated
an
d
t
h
e
lo
u
d
n
es
s
,
as f
o
llo
w
s
:
(
+
1
)
=
(
)
(
5
)
”
a
nd
(
+
1
)
=
(
0
)
[
1
−
(
−
),
(
6
)
”
w
h
er
e
”
an
d
”
ar
e
ad
-
h
o
c
co
n
s
ta
n
t
s
.
T
h
e
f
ir
s
t
s
tep
o
f
t
h
e
m
et
h
o
d
in
v
o
l
v
es
th
e
m
ea
s
u
r
e
m
en
t
o
f
lo
u
d
n
es
s
(
0
)
.
T
h
e
em
i
s
s
io
n
r
ate
(
0
)
”
is
o
f
ten
ti
m
e
s
r
an
d
o
m
l
y
elec
ted
.
I
n
an
y
ev
e
n
t,
(
0
)
∈
[
1
,
2
]
an
d
(
0
)
∈
[
0
,
1
]
.
W
r
ap
p
e
r
FS
h
a
s
b
ee
n
p
o
p
u
lar
ized
b
y
[
2
1
]
.
T
h
e
tech
n
iq
u
e
d
i
f
f
er
s
f
r
o
m
f
ilter
FS
i
n
ter
m
s
o
f
u
s
a
g
e
o
f
th
e
lear
n
in
g
al
g
o
r
ith
m
.
W
r
a
p
p
er
FS
r
elies
s
o
lel
y
o
n
m
ax
i
m
izi
n
g
p
r
ed
ictio
n
ac
cu
r
ac
y
as
p
r
o
d
u
ce
d
b
y
th
e
lear
n
i
n
g
alg
o
r
it
h
m
.
A
l
ea
r
n
in
g
alg
o
r
it
h
m
w
it
h
th
e
o
p
ti
m
izatio
n
t
h
at
u
s
es
t
h
e
W
r
ap
p
e
r
ap
p
r
o
ac
h
in
co
r
p
o
r
ates
an
o
p
ti
m
iza
tio
n
t
o
o
l
an
d
ev
al
u
ates
a
m
o
d
el,
wh
er
ea
s
t
h
e
f
ilter
s
ap
p
r
o
ac
h
i
s
s
i
m
ilar
to
w
r
ap
p
er
s
in
t
h
e
s
ea
r
ch
ap
p
r
o
ac
h
,
b
u
t
in
s
tead
o
f
e
v
al
u
ati
n
g
a
g
ain
s
t
a
m
o
d
el,
a
s
i
m
p
ler
f
ilter
is
ev
al
u
ated
.
T
h
u
s
,
in
d
u
cti
v
e
a
lg
o
r
it
h
m
s
ar
e
u
s
ed
b
y
w
r
ap
p
er
m
et
h
o
d
s
as
th
e
ev
alu
a
tio
n
f
u
n
c
tio
n
,
w
h
er
ea
s
f
ilter
m
et
h
o
d
s
ar
e
in
d
ep
en
d
en
t
o
f
t
h
e
i
n
d
u
cti
v
e
alg
o
r
ith
m
[
2
2
]
.
I
n
th
e
co
n
te
x
t
o
f
FS
,
t
h
e
Fi
lter
ap
p
r
o
ac
h
is
f
a
s
ter
b
u
t
less
ac
cu
r
ate
an
d
co
m
p
u
tatio
n
a
ll
y
in
te
n
s
i
v
e
t
h
an
th
e
W
r
ap
p
er
ap
p
r
o
ac
h
[
2
3
]
.
T
h
e
W
r
ap
p
er
ap
p
r
o
ac
h
is
o
n
e
o
f
th
e
m
o
s
t
w
id
el
y
u
s
ed
ap
p
r
o
ac
h
es b
ec
au
s
e
o
f
it
s
ad
eq
u
ate
r
es
u
lts
a
n
d
ef
f
icie
n
c
y
in
h
a
n
d
lin
g
lar
g
e
an
d
co
m
p
le
x
d
ata
s
et
as
co
m
p
ar
ed
to
th
e
Fil
ter
ap
p
r
o
ac
h
[
2
4
]
.
Ho
w
e
v
er
,
an
ex
p
en
s
i
v
e
tec
h
n
iq
u
e
i
n
v
o
l
v
es
a
co
m
p
le
x
p
r
o
ce
s
s
o
f
b
u
ild
i
n
g
a
clas
s
i
f
i
er
w
it
h
h
u
n
d
r
ed
s
o
f
ite
m
s
to
ev
alu
a
te
o
n
e
f
ea
t
u
r
e
s
u
b
s
et
a
n
d
d
is
p
en
s
i
n
g
h
u
g
e
n
u
m
b
er
s
o
f
f
ea
tu
r
e
s
[
2
5
,
26]
.
Sear
ch
in
g
in
f
ea
tu
r
e
s
p
ac
e
in
f
l
u
e
n
ce
s
t
h
e
p
er
f
o
r
m
an
c
e
o
f
th
e
w
r
ap
p
er
tech
n
iq
u
e,
esp
ec
iall
y
its
q
u
ic
k
n
es
s
to
f
i
n
d
t
h
e
b
est
s
u
b
s
et
f
ea
tu
r
es
to
av
o
id
an
ex
h
a
u
s
ti
v
e
s
ea
r
ch
.
T
h
e
w
r
ap
p
er
FS
ap
p
r
o
ac
h
es
w
h
ich
ar
e
u
s
ed
in
t
h
i
s
p
ap
er
in
cl
u
d
e
t
h
r
ee
p
o
p
u
lar
s
tr
ateg
ies:
a)
f
o
r
w
ar
d
s
elec
tio
n
,
b
)
b
ac
k
w
ar
d
eli
m
i
n
atio
n
an
d
c)
s
to
ch
a
s
tic
s
ea
r
ch
.
Fo
r
w
ar
d
s
elec
tio
n
e
v
al
u
ates
f
r
o
m
n
o
f
ea
t
u
r
es
u
n
t
il
all
f
ea
t
u
r
es
h
av
e
b
ee
n
co
n
s
id
er
ed
.
B
ac
k
w
ar
d
eli
m
i
n
atio
n
s
tar
t
s
w
it
h
all
f
ea
t
u
r
es.
S
to
ch
as
tic
ap
p
r
o
ac
h
es
to
tall
y
d
ep
en
d
o
n
th
e
s
p
ec
if
ic
s
ea
r
ch
i
n
g
s
tr
ate
g
y
o
f
t
h
e
al
g
o
r
ith
m
.
Fo
r
in
s
ta
n
ce
,
i
n
a
g
en
et
ic
s
ea
r
ch
t
h
at
u
tili
ze
s
G
A
ap
p
r
o
ac
h
es,
ea
ch
s
ta
te
is
d
ef
i
n
ed
b
y
a
f
ea
t
u
r
e
m
as
k
s
o
t
h
a
t
a
g
e
n
etic
o
p
er
atio
n
ca
n
b
e
p
er
f
o
r
m
ed
(
s
u
c
h
a
s
cr
o
s
s
o
v
er
,
an
d
m
u
tatio
n
)
[
2
7
]
.
3.
RUL
E
ST
RUCT
URE B
AS
E
D
ANT
-
M
I
NE
R
AL
G
O
R
I
T
H
M
T
h
e
A
C
O
al
g
o
r
ith
m
is
t
h
e
m
ain
p
o
in
t
o
f
t
h
is
s
t
u
d
y
.
I
ts
w
o
r
k
is
b
ased
o
n
th
e
f
o
llo
w
i
n
g
s
u
g
g
e
s
tio
n
s
.
E
ac
h
an
t
tr
ac
k
f
o
llo
w
s
a
n
o
m
i
n
ee
s
o
l
u
tio
n
to
an
is
s
u
e.
T
h
e
an
t
tr
ac
k
s
t
h
e
p
at
h
w
h
e
r
ein
t
h
e
v
o
lu
m
e
o
f
p
h
er
o
m
o
n
e
d
ep
o
s
ited
i
s
p
r
o
p
o
r
tio
n
al
to
th
e
q
u
alit
y
o
f
t
h
e
ca
n
d
id
ate
s
o
l
u
tio
n
co
n
f
o
r
m
ab
le
to
t
h
e
tar
g
e
t
p
r
o
b
lem
.
T
h
e
p
ath
w
h
er
ei
n
th
e
p
h
er
o
m
o
n
e
is
h
ig
h
l
y
co
n
ce
n
tr
ated
is
co
n
s
id
er
ed
th
e
f
ir
s
t
p
ath
,
w
h
ic
h
m
ea
n
s
th
e
p
r
io
r
it
y
p
at
h
o
f
a
n
a
n
t.
T
h
e
A
C
O
u
s
es
d
i
f
f
er
en
t
an
ts
to
s
ea
r
ch
f
o
r
al
l
ca
n
d
id
ate
s
o
lu
tio
n
s
a
n
d
co
n
v
er
g
es
to
th
e
o
p
ti
m
a
l
o
r
n
ea
r
-
o
p
ti
m
al
s
o
lu
tio
n
s
.
L
o
p
es,
P
ar
p
in
elli
e
t.
al
[
2
8
]
w
er
e
th
e
f
ir
s
t
to
s
u
g
g
est
t
h
e
u
s
e
o
f
A
C
O
an
d
a
s
y
s
te
m
ca
lled
a
n
t
-
m
in
er
f
o
r
th
e
d
etec
tio
n
o
f
cla
s
s
i
f
ica
tio
n
r
u
le
s
.
T
h
e
a
nt
-
m
in
er
al
g
o
r
ith
m
[
2
9
]
d
etec
ts
a
s
et
o
f
I
F
-
T
HE
N
r
u
les
o
f
d
ata
in
th
e
f
o
r
m
o
f
I
F
<T
er
m
1
AND
T
er
m
2
AND
.
.
.
>
T
HE
N
<Clas
s
>
i
n
t
h
e
d
ata
m
i
n
in
g
ta
s
k
.
I
n
th
e
b
ase
o
f
th
e
p
r
ec
ed
in
g
p
ar
t,
ea
ch
ter
m
is
a
tr
ip
le
attr
ib
u
te,
o
p
er
ato
r
,
an
d
th
en
v
al
u
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
.
6
,
Dec
em
b
er
2
0
2
0
:
6
6
5
5
-
6
6
6
3
6658
I
n
th
e
f
ield
o
f
ea
c
h
attr
ib
u
te,
t
h
e
v
al
u
e
is
th
e
p
o
ten
t
ial
v
al
u
e
in
th
is
f
i
eld
.
On
l
y
a
‘
=’
o
p
er
ato
r
is
u
s
ed
in
t
h
i
s
task
,
s
u
c
h
a
s
<D
a
y
=
S
u
n
d
a
y
>
.
T
h
e
p
o
r
tio
n
o
f
t
h
e
clas
s
p
r
ed
ictio
n
i
s
d
eter
m
in
ed
o
n
l
y
i
f
t
h
e
ex
p
ec
ted
f
ea
tu
r
es
o
f
all
ter
m
s
ar
e
m
e
t
in
th
e
p
r
ev
io
u
s
s
ec
tio
n
.
Set
r
u
le
s
,
cr
ea
ted
b
y
t
h
i
s
alg
o
r
it
h
m
,
co
v
e
r
all
o
r
alm
o
s
t
a
ll
tr
ain
i
n
g
ca
s
e
s
.
A
s
a
r
es
u
lt,
t
h
ese
r
u
le
s
h
a
v
e
a
f
e
w
ter
m
s
.
Fo
r
d
ata
m
in
in
g
,
a
f
e
w
n
u
m
b
er
s
o
f
r
u
le
s
ar
e
co
n
s
id
er
ed
g
o
o
d
.
4.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
ex
p
er
i
m
en
ta
l
f
r
a
m
e
w
o
r
k
co
n
s
i
s
ts
o
f
f
i
v
e
s
tep
s
.
I
n
t
h
e
f
ir
s
t
s
tep
,
ce
r
v
ical
ca
n
ce
r
d
ata
s
ets
ar
e
s
elec
t
ed
w
h
ic
h
u
s
ed
t
o
test
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
.
T
h
e
n
u
m
b
e
r
o
f
attr
ib
u
tes
an
d
class
ar
e
d
ef
i
n
ed
i
n
T
ab
le
1
.
T
h
e
s
ec
o
n
d
s
tep
in
t
h
i
s
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
,
w
h
er
e
t
h
e
te
s
t
d
ata
is
s
u
b
s
et
s
o
f
th
e
o
r
ig
in
a
l
d
ataset
u
s
ed
to
b
e
tr
ain
ed
u
s
in
g
th
e
An
t
-
Mi
n
er
class
i
f
ier
to
g
et
th
e
ac
cu
r
ac
y
p
r
io
r
t
o
th
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
.
T
h
e
ex
p
er
im
en
t
w
o
r
k
is
estab
li
s
h
ed
in
t
h
e
th
ir
d
s
tep
to
s
elec
t
th
e
b
es
t
s
u
b
s
et
s
o
f
f
ea
t
u
r
es
u
s
i
n
g
B
A
.
T
h
e
f
o
u
r
th
s
tep
s
h
o
w
s
th
e
te
s
t
p
ath
to
ex
ec
u
t
e
th
e
p
r
ed
ictio
n
m
o
d
el.
T
h
e
f
i
f
th
s
tep
is
u
s
ed
to
m
ea
s
u
r
e
th
e
r
es
u
lt
s
.
T
h
e
f
r
a
m
e
w
o
r
k
o
f
th
e
p
r
ed
ictio
n
m
o
d
el
s
h
o
w
n
i
n
F
i
g
u
r
e
1
.
T
ab
le
1
.
Featu
r
es o
f
r
is
k
f
ac
to
r
s
an
d
t
ar
g
ets
f
o
r
c
er
v
ical
c
an
c
er
d
ataset
N
o
.
A
t
t
r
i
b
u
t
e
s Name
D
a
t
a
T
y
p
e
N
o
.
A
t
t
r
i
b
u
t
e
s Name
D
a
t
a
T
y
p
e
1
A
g
e
I
n
t
21
S
T
D
s:
mo
l
l
u
scu
m c
o
n
t
a
g
i
o
su
m
B
o
o
l
2
N
u
mb
e
r
o
f
se
x
u
a
l
p
a
r
t
n
e
r
s
B
o
o
l
×
I
n
t
22
S
T
D
s:
A
I
D
S
B
o
o
l
3
F
i
r
st
se
x
u
a
l
i
n
t
e
r
c
o
u
r
se
(
a
g
e
)
B
o
o
l
×
I
n
t
23
S
T
D
s:
H
I
V
B
o
o
l
4
N
u
mb
e
r
o
f
p
r
e
g
n
a
n
c
i
e
s
B
o
o
l
×
I
n
t
24
S
T
D
s:
H
e
p
a
t
i
t
i
s
B
B
o
o
l
5
S
mo
k
e
s
B
o
o
l
25
S
T
D
s:
H
P
V
B
o
o
l
6
S
mo
k
e
s
(
y
e
a
r
s)
I
n
t
26
S
T
D
s:
N
u
mb
e
r
o
f
d
i
a
g
n
o
s
i
s
C
a
t
e
g
o
r
i
c
a
l
7
S
mo
k
e
s (p
a
c
k
s
/
y
e
a
r
)
I
n
t
27
S
T
D
s:
T
i
me
si
n
c
e
f
i
r
st
d
i
a
g
n
o
si
s
I
n
t
8
H
o
r
mo
n
a
l
C
o
n
t
r
a
c
e
p
t
i
v
e
s
B
o
o
l
28
S
T
D
s:
T
i
me
si
n
c
e
l
a
st
d
i
a
g
n
o
si
s
I
n
t
9
H
o
r
mo
n
a
l
C
o
n
t
r
a
c
e
p
t
i
v
e
s (y
e
a
r
s)
I
n
t
29
D
x
:
C
a
n
c
e
r
B
o
o
l
10
I
U
D
B
o
o
l
30
D
x
:
C
I
N
B
o
o
l
11
I
U
D
(
y
e
a
r
s)
I
n
t
31
D
x
:
H
P
V
B
o
o
l
12
S
T
D
s
B
o
o
l
32
Dx
B
o
o
l
13
S
T
D
s (n
u
mb
e
r
)
I
n
t
20
S
T
D
s:
g
e
n
i
t
a
l
h
e
r
p
e
s
B
o
o
l
14
S
T
D
s:
c
o
n
d
y
l
o
mat
o
si
s
B
o
o
l
21
S
T
D
s:
mo
l
l
u
scu
m c
o
n
t
a
g
i
o
su
m
B
o
o
l
15
S
T
D
s:
c
e
r
v
i
c
a
l
c
o
n
d
y
l
o
mat
o
si
s
B
o
o
l
22
S
T
D
s:
A
I
D
S
B
o
o
l
16
S
T
D
s:
v
a
g
i
n
a
l
c
o
n
d
y
l
o
mat
o
si
s
B
o
o
l
23
S
T
D
s:
H
I
V
B
o
o
l
17
S
T
D
s:
v
u
l
v
o
-
p
e
r
i
n
e
a
l
c
o
n
d
y
l
o
mat
o
si
s
B
o
o
l
24
S
T
D
s:
H
e
p
a
t
i
t
i
s
B
B
o
o
l
18
S
T
D
s:
s
y
p
h
i
l
i
s
B
o
o
l
25
S
T
D
s:
H
P
V
B
o
o
l
19
S
T
D
s:
p
e
l
v
i
c
i
n
f
l
a
mm
a
t
o
r
y
d
i
se
a
se
B
o
o
l
26
S
T
D
s:
N
u
mb
e
r
o
f
d
i
a
g
n
o
s
i
s
C
a
t
e
g
o
r
i
c
a
l
20
S
T
D
s:
g
e
n
i
t
a
l
h
e
r
p
e
s
B
o
o
l
27
S
T
D
s:
T
i
me
si
n
c
e
f
i
r
st
d
i
a
g
n
o
si
s
I
n
t
Fig
u
r
e
1
.
Fra
m
e
w
o
r
k
o
f
t
h
e
p
r
ed
ictio
n
m
o
d
el
a.
Data
s
et
la
y
er
: t
h
i
s
la
y
er
r
ep
r
esen
ts
th
e
u
s
e
o
f
attr
ib
u
te
s
i
n
t
h
e
o
p
er
atio
n
.
Fo
r
in
s
ta
n
ce
,
a
s
et
o
f
f
ea
tu
r
es
w
il
l
co
n
s
is
t
o
f
t
h
e
p
r
o
b
le
m
,
A
i
=
{
A
1
,
A
2
,
.
.
.
,
A
n
}
an
d
ea
c
h
att
r
ib
u
te
co
m
p
r
is
es
a
s
et
o
f
p
o
s
s
i
b
le
v
alu
e
s
a
n
d
Vi
=
{V1
,
V2
,
…,
Vn
}.
E
ac
h
ter
m
(
attr
ib
u
te
o
r
v
alu
e)
is
s
u
p
p
o
s
ed
a
s
an
ap
ex
,
w
h
er
e
th
e
p
r
o
b
lem
i
s
a
g
r
ap
h
.
T
h
e
r
a
w
d
ata
i
s
lo
a
d
ed
f
r
o
m
th
e
U
C
I
r
ep
o
s
ito
r
y
[
3
0
]
.
T
h
e
d
ata
s
et
is
r
ep
r
esen
ted
b
y
3
2
r
is
k
P
r
e
p
r
o
c
e
ssi
n
g
L
a
y
e
r
D
a
t
a
se
t
s
T
r
a
i
n
i
n
g
L
a
y
e
r
Ex
p
e
r
i
me
n
t
a
t
i
o
n
L
a
y
e
r
-
FS
U
si
n
g
BA
-
A
n
t
-
mi
n
e
r
a
l
g
o
r
i
t
h
m
P
e
r
f
o
r
man
c
e
Ev
a
l
u
a
t
i
o
n
-
A
c
c
u
r
a
c
y
-
N
u
mb
e
r
o
f
f
e
a
t
u
r
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
b
a
t
-
a
n
t c
o
lo
n
y
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
fo
r
r
u
le
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
in
h
ea
lth
c
a
r
e
(
R
a
fid
S
a
g
b
a
n
)
6659
f
ac
to
r
s
,
in
c
lu
d
i
n
g
h
i
s
to
r
ical
m
ed
ic
al
r
ec
o
r
d
s
,
p
atien
t
h
ab
it
s
,
an
d
d
e
m
o
g
r
ap
h
ic
i
n
f
o
r
m
ati
o
n
,
as
s
h
o
w
n
in
T
ab
le
1
.
Fo
u
r
tar
g
et
m
ar
k
er
s
,
n
a
m
el
y
,
Hi
n
s
el
m
a
n
n
,
S
ch
iller
,
C
y
to
lo
g
y
,
an
d
B
io
p
s
y
,
al
s
o
e
x
is
t.
T
h
e
Hin
s
el
m
a
n
n
te
s
t
i
n
d
icate
s
to
co
n
d
u
ct
co
lp
o
s
co
p
y
u
s
i
n
g
ac
etic
ac
id
.
C
o
n
c
u
r
r
en
t
l
y
,
c
o
lp
o
s
co
p
y
u
s
i
n
g
L
u
g
o
l
io
d
in
e
is
i
m
p
lied
in
t
h
e
Sch
i
ller
s
test
,
C
y
to
lo
g
y
,
an
d
B
io
p
s
y
.
So
m
e
p
atie
n
ts
d
id
n
o
t
an
s
w
er
th
e
en
tire
q
u
e
s
tio
n
s
f
o
r
p
r
iv
ac
y
r
ea
s
o
n
s
.
T
h
er
ef
o
r
e,
m
is
s
in
g
v
al
u
es
ap
p
ea
r
in
th
e
d
ata,
w
h
ic
h
m
u
s
t
b
e
p
r
e
-
p
r
o
ce
s
s
ed
.
b.
P
r
e
-
p
r
o
ce
s
s
in
g
L
a
y
er
: a
p
r
i
m
a
r
y
p
h
ase
in
d
ata
m
in
i
n
g
a
n
d
m
ac
h
in
e
lear
n
i
n
g
is
th
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
p
h
ase
o
f
th
e
d
ata.
T
h
is
p
h
ase
ex
ec
u
te
s
s
o
m
e
ca
lc
u
latio
n
s
,
s
u
c
h
as
d
ata
clea
n
in
g
(
eli
m
i
n
ati
n
g
an
n
o
y
in
g
d
ata,
f
illi
n
g
m
is
s
in
g
v
al
u
es),
d
ata
r
ed
u
ctio
n
a
n
d
d
ata
co
n
v
er
s
io
n
(
ag
g
r
eg
a
tio
n
,
n
o
r
m
aliza
t
io
n
)
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
s
tep
i
n
th
is
s
tu
d
y
is
to
co
n
d
u
ct
d
ata
i
n
itia
lizatio
n
to
r
ea
ch
t
h
e
q
u
alit
y
r
eq
u
ir
ed
b
y
t
h
e
class
i
f
icatio
n
.
T
h
e
h
ig
h
q
u
a
lit
y
o
f
in
f
o
r
m
ati
o
n
m
ak
e
s
th
e
d
ec
is
io
n
p
r
o
ce
s
s
g
o
o
d
.
T
h
e
d
ata
ar
e
in
itializ
ed
b
y
r
ep
lacin
g
th
e
m
is
s
i
n
g
v
al
u
es
a
n
d
co
n
v
er
tin
g
th
e
d
ata
f
r
o
m
n
u
m
er
ical
v
alu
es
i
n
to
n
o
m
i
n
al
v
al
u
es
b
y
u
s
i
n
g
th
e
W
e
k
a
to
o
l.
T
w
o
r
is
k
f
ac
to
r
s
ar
e
d
i
s
co
v
er
ed
,
n
a
m
el
y
,
2
7
s
ex
u
all
y
tr
a
n
s
m
it
ted
d
is
ea
s
es
(
ST
Ds):
T
im
e
s
i
n
ce
th
e
f
ir
s
t
d
iag
n
o
s
is
a
n
d
2
8
STDs:
T
h
e
d
ata
in
v
o
lv
in
g
th
e
ti
m
e
s
i
n
ce
th
e
l
a
s
t
d
iag
n
o
s
is
a
r
e
d
elete
d
af
ter
th
e
p
r
e
-
tr
ea
t
m
e
n
t
th
at
b
ec
au
s
e
o
f
t
h
e
lac
k
o
f
a
v
ailab
le
v
al
u
e
s
.
Fi
n
all
y
,
t
h
e
a
n
al
y
s
i
s
o
f
ce
r
v
ical
ca
n
ce
r
d
at
a
w
o
u
ld
b
e
f
r
o
m
3
0
f
ea
tu
r
es i
n
8
5
8
p
atien
ts
.
c.
T
r
ain
in
g
L
a
y
er
:
in
th
i
s
la
y
er
,
th
e
d
ata
s
et
s
ar
e
class
if
ied
i
n
to
tr
ain
i
n
g
a
n
d
test
g
r
o
u
p
s
a
f
ter
p
r
e
-
p
r
o
ce
s
s
in
g
,
d
ep
en
d
in
g
o
n
t
h
e
n
u
m
b
er
o
f
f
o
ld
s
in
t
h
e
cr
o
s
s
-
v
a
lid
atio
n
.
I
n
th
i
s
s
t
u
d
y
,
af
ter
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
la
y
er
,
th
e
ex
p
er
i
m
e
n
tal
a
n
al
y
s
is
i
s
co
n
d
u
cted
o
n
a
d
ata
s
et
f
o
r
f
o
u
r
tar
g
et
s
,
n
a
m
e
l
y
,
Hi
n
s
el
m
an
n
,
Sc
h
iller
,
c
y
to
lo
g
y
,
an
d
b
io
p
s
y
.
T
h
e
d
ata
ar
e
lo
ad
ed
to
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
,
w
h
ic
h
is
p
r
o
g
r
a
m
m
e
d
alr
ea
d
y
i
n
J
av
a
,
E
clip
s
e
an
d
r
u
n
o
n
a
co
m
p
u
ter
I
n
tel
(
R
)
C
o
r
eT
M
i5
Du
o
C
P
U
@
2
.
4
0
p
r
o
ce
s
s
o
r
an
d
W
in
d
o
w
s
1
0
.
T
h
e
p
ar
am
eter
s
u
s
ed
in
th
e
p
r
o
p
o
s
ed
m
eth
o
d
ar
e
C
r
o
s
s
_
v
a
lid
atio
n
=5
,
N
u
m
b
er
_
o
f
_
an
ts
=3
0
,
Min
_
ca
s
es_
p
er
_
r
u
le=
5
,
Ma
x
_
u
n
co
v
er
ed
_
ca
s
es,
an
d
No
_
o
f
_
r
u
les_
co
n
v
er
g
e
=
1
0
.
d.
E
x
p
er
i
m
e
n
tal
L
a
y
er
:
I
n
t
h
i
s
la
y
er
,
a
B
in
ar
y
B
A
is
u
s
ed
a
s
t
h
e
h
e
u
r
is
tic
m
e
th
o
d
to
i
m
p
r
o
v
e
th
e
ef
f
ec
ti
v
e
n
es
s
o
f
A
n
t
-
M
in
e
r
.
E
ac
h
b
at’
s
s
it
u
atio
n
in
t
h
e
s
ea
r
ch
d
is
tan
ce
e
n
co
d
es
an
d
p
er
f
o
r
m
s
a
s
u
b
s
e
t
o
f
attr
ib
u
tes.
T
h
u
s
,
f
o
r
ea
c
h
s
u
b
s
et,
an
An
t
-
Min
er
clas
s
i
f
i
er
is
tr
ai
n
ed
i
n
o
n
e
p
ar
t
a
n
d
ev
al
u
ated
o
v
er
an
o
th
er
p
ar
t
u
n
s
ee
n
d
u
r
i
n
g
t
h
e
tr
ain
in
g
to
o
b
s
er
v
e
t
h
e
f
itn
e
s
s
v
a
lu
e
o
f
ea
ch
b
at.
T
r
ain
in
g
an
d
ev
al
u
ati
n
g
s
u
b
s
et
s
m
a
y
b
e
p
er
f
o
r
m
ed
s
ev
er
al
ti
m
e
s
b
et
w
ee
n
b
ats
b
ec
au
s
e
ea
ch
b
at
m
a
y
e
n
co
d
e
s
ev
er
al
s
u
b
s
ets
o
f
attr
ib
u
tes
T
h
is
la
y
er
co
n
s
is
t
s
o
f
th
e
AC
O
-
b
ased
class
i
f
ic
atio
n
alg
o
r
it
h
m
t
h
at
g
e
n
er
at
es
o
u
tp
u
t
f
r
o
m
th
e
tr
ain
i
n
g
g
r
o
u
p
a
n
d
d
eter
m
in
es
t
h
e
test
s
tat
u
s
.
T
h
e
alg
o
r
ith
m
i
m
p
l
e
m
e
n
ts
ca
lc
u
lat
io
n
s
o
n
th
e
d
ata
s
e
t
an
d
g
en
er
ate
th
e
r
es
u
lt
s
.
T
h
e
test
ca
s
es
an
d
th
e
tr
ain
i
n
g
p
ac
k
ag
e
ar
e
class
if
ied
b
y
u
s
in
g
a
f
i
v
e
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
m
et
h
o
d
.
Nin
e
t
y
p
er
ce
n
t
o
f
t
h
e
tr
ai
n
in
g
d
ata
an
d
2
0
%
o
f
th
e
tes
t
d
ata
ar
e
u
s
ed
in
ea
ch
f
o
ld
test
.
A
f
t
er
th
e
p
h
er
o
m
o
n
e
i
n
it
ializatio
n
,
n
u
m
er
o
u
s
b
ase
s
ar
e
cr
ea
ted
in
th
e
r
ep
ea
t
lo
o
p
.
T
h
e
p
r
o
ce
d
u
r
e
is
co
n
tin
u
ed
w
it
h
t
h
e
p
r
u
n
in
g
,
b
ase,
an
d
t
h
e
p
h
er
o
m
o
n
e
u
p
d
at
e
m
et
h
o
d
.
W
h
en
t
h
e
a
n
ts
b
u
il
d
th
e
s
a
m
e
r
u
le
co
n
s
is
ten
tl
y
m
o
r
e
th
a
n
o
n
ce
(
No
_
R
u
le_
C
o
n
v
er
g
)
o
r
th
e_
n
u
m
b
e
r
_
o
f
_
an
t
s
eq
u
al
s
th
e_
n
u
m
b
er
_
o
f
_
r
u
les,
th
e
lo
o
p
w
ill
s
to
p
.
I
n
t
h
e
li
s
t
o
f
r
u
le
s
,
th
e
b
est
r
u
le
w
il
l
b
e
ad
d
ed
w
h
e
n
t
h
e
i
n
n
er
lo
o
p
“Rep
ea
t
-
U
n
til”
is
co
m
p
leted
As
a
r
esu
lt,
all
tr
ain
i
n
g
ca
s
es
p
r
o
v
id
ed
f
o
r
in
th
is
r
u
le
w
il
l
b
e
r
e
m
o
v
ed
f
r
o
m
t
h
e
tr
ain
i
n
g
p
ac
k
ag
e
.
P
h
er
o
m
o
n
e
i
s
in
i
t
ialized
ag
ain
.
T
h
e
ex
ter
n
al
lo
o
p
co
n
tr
o
ls
th
e
s
ess
io
n
r
esp
o
n
s
ib
le
f
o
r
co
n
f
i
g
u
r
in
g
t
h
i
s
p
h
er
o
m
o
n
e.
Fo
r
th
e
“Rep
ea
t
-
Un
t
il”
lo
o
p
,
a
li
m
it
m
o
r
e
th
a
n
th
e
n
u
m
b
er
o
f
i
n
d
eter
m
i
n
at
e
tr
ain
i
n
g
s
e
s
s
io
n
s
i
s
ca
lled
Ma
x
_
u
n
co
v
er
ed
_
ca
s
es.
e.
P
er
f
o
r
m
a
n
ce
An
a
l
y
s
i
s
L
a
y
er
:
p
er
f
o
r
m
a
n
ce
a
n
al
y
s
i
s
i
s
u
s
ed
to
m
ea
s
u
r
e
t
h
e
r
es
u
lt
s
ex
tr
ac
ted
f
r
o
m
th
e
e
x
p
er
i
m
e
n
t.
T
h
is
la
y
er
v
a
l
id
ates
t
h
e
r
es
u
lt
s
b
ased
o
n
d
if
f
er
en
t
p
er
f
o
r
m
a
n
ce
a
n
al
y
s
i
s
o
p
er
ato
r
s
,
s
u
c
h
as
r
u
le
g
e
n
er
atio
n
n
u
m
b
er
,
n
u
m
b
er
o
f
ter
m
s
p
er
r
u
les a
n
d
ac
cu
r
ac
y
.
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
i
s
p
ap
er
,
th
e
ex
p
er
i
m
e
n
t
s
tar
ted
w
i
th
te
s
t
t
h
e
ef
f
ec
ti
v
e
n
ess
o
f
B
A
f
o
r
FS
o
n
t
h
e
s
ize
o
f
f
ea
t
u
r
es
in
th
e
ce
r
v
ical
ca
n
ce
r
d
ataset.
T
h
is
p
ar
t
d
is
cu
s
s
e
s
th
e
ex
p
er
i
m
e
n
tal
r
esu
l
ts
o
f
ce
r
v
ical
ca
n
ce
r
d
atasets
f
r
o
m
UC
I
r
ep
o
s
ito
r
y
w
it
h
s
e
lecte
d
f
ea
tu
r
e
s
u
s
i
n
g
B
A
a
n
d
m
ea
s
u
r
ed
b
y
AC
O
cla
s
s
i
f
ie
r
.
T
a
b
le
2
s
h
o
w
s
th
e
ch
ar
ac
ter
is
t
ics
o
f
th
e
ce
r
v
ical
ca
n
ce
r
d
ataset
an
d
th
e
n
u
m
b
er
o
f
s
elec
ted
f
ea
tu
r
es
f
o
r
ea
ch
tar
g
et
in
th
e
d
ataset
b
y
u
s
in
g
B
A
.
Ob
s
er
v
atio
n
f
r
o
m
t
h
e
r
esu
lt
in
T
ab
le
2
s
h
o
w
s
th
e
h
i
g
h
e
s
t
r
ed
u
ctio
n
is
co
m
i
n
g
f
r
o
m
ce
r
v
ical
-
ca
n
ce
r
(
Hi
n
s
e
l
m
a
n
n
)
,
f
i
v
e
f
ea
t
u
r
es
s
elec
ted
f
o
llo
wed
b
y
ce
r
v
ical
-
ca
n
ce
r
(
C
y
to
lo
g
y
)
,
s
ev
e
n
f
ea
t
u
r
es
s
elec
ted
an
d
ce
r
v
ical
-
ca
n
ce
r
(
Sch
iller
)
,
eig
h
t
f
ea
t
u
r
es
s
ele
cted
.
ce
r
v
ical
-
ca
n
ce
r
(
B
io
p
s
y
)
s
h
o
w
s
th
e
lo
w
es
t
r
ed
u
ctio
n
o
f
attr
ib
u
tes
d
i
s
m
i
s
s
ed
w
it
h
o
n
l
y
n
in
e
attr
ib
u
te
s
s
elec
ted
.
T
h
e
r
esu
lt
also
s
h
o
w
s
t
h
at
B
A
h
a
s
r
ed
u
ce
d
m
o
r
e
th
a
n
5
0
%
o
f
t
h
e
n
u
m
b
er
o
f
o
r
i
g
in
al
f
ea
t
u
r
es
i
n
t
h
e
ce
r
v
ical
ca
n
ce
r
d
ataset.
Sin
ce
t
h
e
e
f
f
icie
n
c
y
o
f
FS
in
clas
s
if
icatio
n
is
u
n
d
eter
m
in
ed
.
T
h
e
clas
s
i
f
icatio
n
p
er
f
o
r
m
a
n
ce
i
s
m
ea
s
u
r
ed
ac
co
r
d
in
g
to
t
h
r
ee
cr
iter
ia:
r
u
le
g
e
n
er
atio
n
n
u
m
b
er
,
n
u
m
b
er
o
f
ter
m
s
p
er
r
u
les
an
d
ac
cu
r
ac
y
as
s
h
o
w
n
i
n
T
ab
le
3
.
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
.
6
,
Dec
em
b
er
2
0
2
0
:
6
6
5
5
-
6
6
6
3
6660
T
ab
le
2
.
Selecte
d
f
ea
tu
r
es
T
a
r
g
e
t
A
c
c
u
r
a
c
y
N
u
mb
e
r
o
f
R
u
l
e
s
N
u
mb
e
r
o
f
t
e
r
ms
p
e
r
R
u
l
e
s
H
i
n
se
l
man
n
9
5
.
9
3
%
+
/
-
0
.
5
5
%
7
.
4
+
/
-
0
.
2
7
9
.
6
+
/
-
0
.
4
3
S
c
h
i
l
l
e
r
9
0
.
9
1
%
+
/
-
0
.
8
9
%
7
.
1
+
/
-
0
.
1
9
.
9
+
/
-
0
.
3
1
C
i
t
o
l
o
g
y
9
4
.
8
8
%
+
/
-
0
.
5
8
%
8
.
4
+
/
-
0
.
4
9
.
5
+
/
-
0
.
4
B
i
o
p
sy
9
5
.
8
%
+
/
-
0
.
7
8
%
8
.
5
+
/
-
0
.
4
3
9
.
7
+
/
-
0
.
2
6
T
ab
le
3
.
A
v
er
ag
e
a
n
d
s
tan
d
ar
d
d
ev
iatio
n
o
f
c
la
s
s
i
f
icatio
n
ac
c
u
r
ac
y
,
r
u
le
n
u
m
b
er
an
d
n
u
m
b
e
r
o
f
ter
m
s
p
er
r
u
le
u
s
i
n
g
f
i
v
e
f
o
ld
cr
o
s
s
-
va
lid
atio
n
f
o
r
h
in
s
el
m
an
n
,
s
c
h
iller
,
c
y
to
lo
g
y
,
an
d
b
io
p
s
y
T
a
r
g
e
t
N
u
mb
e
r
o
f
A
t
t
r
i
b
u
t
e
s
N
u
mb
e
r
o
f
S
e
l
e
c
t
e
d
A
t
t
r
i
b
u
t
e
s
C
e
r
v
i
c
a
l
-
c
a
n
c
e
r
(
B
i
o
p
sy
)
30
9
C
e
r
v
i
c
a
l
-
c
a
n
c
e
r
(
C
i
t
o
l
o
g
y
)
30
7
C
e
r
v
i
c
a
l
-
c
a
n
c
e
r
(
H
i
n
se
l
man
n
)
30
5
C
e
r
v
i
c
a
l
-
c
a
n
c
e
r
(
S
c
h
i
l
l
e
r
)
30
8
T
h
e
ex
p
er
i
m
en
t
r
es
u
lts
s
h
o
w
f
i
v
e
f
ea
tu
r
e
s
o
u
t
o
f
3
0
.
I
n
th
e
Hi
n
s
el
m
an
n
te
s
t,
t
h
e
ac
cu
r
ac
y
o
f
th
e
An
t
-
Mi
n
er
cla
s
s
i
f
icatio
n
alg
o
r
ith
m
y
ield
ed
a
r
ate
o
f
9
5
.
9
3
%,
w
it
h
7
.
4
as
t
h
e
r
u
le
n
u
m
b
er
a
n
d
9
.
6
as
th
e
n
u
m
b
er
o
f
ter
m
s
p
er
r
u
le.
Sch
iller
’
s
test
s
h
o
w
s
ei
g
h
t
f
ea
tu
r
es
o
u
t
o
f
3
0
.
T
h
e
A
C
O
class
i
f
ier
ac
h
ie
v
ed
9
0
.
9
1
%
ac
cu
r
ac
y
an
d
th
e
r
u
l
e
n
u
m
b
er
is
7
.
1
w
i
th
9
.
9
th
e
n
u
m
b
er
o
f
ter
m
s
p
er
r
u
le.
I
n
ad
d
itio
n
to
p
er
f
ec
t
d
iag
n
o
s
i
s
i
n
d
ex
e
s
,
t
h
e
c
y
to
lo
g
y
te
s
t
s
h
o
w
s
s
ev
e
n
f
ea
t
u
r
es
o
u
t
o
f
3
0
w
it
h
9
4
.
8
8
%
ac
cu
r
ac
y
f
r
o
m
th
e
clas
s
i
f
ier
o
f
AC
O,
8
.
4
f
o
r
r
u
le
n
u
m
b
er
an
d
9
.
5
f
o
r
th
e
n
u
m
b
er
o
f
ter
m
s
p
er
r
u
le.
T
h
e
b
io
p
s
y
tes
t
l
ea
d
s
to
d
if
f
er
en
t
d
etec
tio
n
r
esu
lt
s
,
h
i
g
h
er
th
an
th
e
th
r
ee
p
r
ev
io
u
s
test
s
in
t
h
e
f
ea
t
u
r
es,
w
h
er
e
9
f
ea
tu
r
es
o
f
o
u
t
o
f
3
0
w
er
e
s
h
o
w
n
w
i
th
9
5
.
8
% a
cc
u
r
ac
y
f
r
o
m
t
h
e
cla
s
s
i
f
ier
.
T
h
e
r
u
le
n
u
m
b
er
s
h
o
w
s
8
.
5
,
an
d
th
e
n
u
m
b
er
o
f
ter
m
s
p
er
r
u
le
is
9
.
7
.
T
h
e
class
i
f
icat
io
n
p
er
f
o
r
m
an
ce
r
es
u
lt
s
ar
e
co
m
p
ar
ed
w
it
h
t
h
e
o
th
er
ap
p
r
o
ac
h
es
[
3
1
,
3
2
]
th
at
ap
p
lied
o
n
th
e
s
a
m
e
ce
r
v
ical
ca
n
ce
r
d
ata
s
et
w
i
th
o
u
t
th
e
u
s
e
o
f
FS
t
ec
h
n
iq
u
es,
s
u
c
h
as
SVM,
as
s
h
o
w
n
in
T
ab
le
4
.
Fu
r
t
h
er
m
o
r
e,
th
e
co
m
p
ar
is
o
n
w
it
h
t
h
e
An
t
-
Mi
n
er
a
f
ter
u
s
in
g
B
A
f
o
r
F
S
s
h
o
w
s
a
n
i
n
cr
ea
s
e
in
th
e
ac
c
u
r
ac
y
an
d
d
ec
r
ea
s
e
in
th
e
n
u
m
b
er
o
f
ter
m
s
r
u
les
w
it
h
a
s
m
all
i
n
cr
ea
s
e
in
th
e
n
u
m
b
er
o
f
r
u
le
s
as
s
h
o
w
n
in
Fi
g
u
r
e
2
an
d
Fig
u
r
e
3
.
T
ab
le
4
.
C
o
m
p
ar
is
o
n
o
f
a
nt
-
m
in
er
c
lass
if
ica
tio
n
T
a
r
g
e
t
A
c
c
u
r
a
c
y
(
%)
A
n
t
-
M
i
n
e
r
S
V
M
S
V
M
-
P
C
A
S
V
M
-
R
F
E
H
i
n
se
l
man
n
9
5
.
9
3
9
3
.
9
7
9
3
.
7
9
9
3
.
6
9
S
c
h
i
l
l
e
r
9
0
.
9
1
9
0
.
1
8
9
0
.
1
8
9
0
.
1
8
C
i
t
o
l
o
g
y
9
4
.
8
8
9
2
.
7
5
9
2
.
4
6
9
2
.
3
7
B
i
o
p
sy
9
5
.
8
9
4
.
1
3
9
4
.
0
3
9
4
.
0
3
Fig
u
r
e
2
.
Nu
m
b
er
o
f
ter
m
s
p
er
r
u
le
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
Hyb
r
id
b
a
t
-
a
n
t c
o
lo
n
y
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
fo
r
r
u
le
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
in
h
ea
lth
c
a
r
e
(
R
a
fid
S
a
g
b
a
n
)
6661
Fig
u
r
e
3
.
P
er
ce
n
tag
e
o
f
t
h
e
c
la
s
s
i
f
icatio
n
a
cc
u
r
ac
y
a
n
d
n
u
m
b
er
o
f
r
u
les
u
s
i
n
g
A
C
O
w
i
th
a
n
d
w
it
h
o
u
t s
elec
tin
g
f
ea
t
u
r
es
6.
CO
NCLU
SI
O
N
P
atien
ts
w
h
o
h
a
v
e
u
n
d
er
g
o
n
e
ce
r
v
ical
ca
n
ce
r
s
cr
ee
n
i
n
g
test
s
p
r
o
v
id
e
ac
cu
r
ate
in
f
o
r
m
atio
n
to
p
h
y
s
ician
s
w
h
o
u
s
e
t
h
i
s
i
n
f
o
r
m
atio
n
to
d
etec
t,
u
n
d
er
s
ta
n
d
,
an
d
ass
e
s
s
t
h
e
s
y
m
p
to
m
s
o
f
t
h
e
d
is
ea
s
e.
I
n
th
i
s
p
ap
er
,
a
h
y
b
r
id
b
at
an
d
an
t
co
lo
n
y
o
p
ti
m
iza
tio
n
-
b
ased
cl
a
s
s
i
f
icatio
n
alg
o
r
it
h
m
w
as
p
r
o
p
o
s
ed
to
an
aly
ze
th
e
ce
r
v
ical
ca
n
ce
r
d
ata
s
et.
T
h
is
s
tu
d
y
i
s
t
h
e
f
ir
s
t
to
u
s
e
m
etah
e
u
r
is
tic
al
g
o
r
ith
m
s
f
o
r
ce
r
v
ical
ca
n
ce
r
d
iag
n
o
s
i
s
.
P
atien
t
ex
a
m
i
n
atio
n
d
ata
ar
e
co
m
p
o
s
ed
ac
co
r
d
in
g
to
ce
r
tain
cr
iter
ia
b
y
u
s
i
n
g
h
y
b
r
id
alg
o
r
it
h
m
s
an
d
d
ata
in
v
o
l
v
i
n
g
8
5
8
p
atien
ts
.
T
h
e
v
ar
iab
le
tar
g
et
s
ar
e
Hin
s
el
m
a
n
n
,
Sch
i
ller
,
C
y
t
o
lo
g
y
,
an
d
B
io
p
s
y
.
B
y
co
m
p
ar
i
n
g
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
w
it
h
o
th
er
w
o
r
k
s
,
t
h
e
h
y
b
r
id
alg
o
r
ith
m
s
d
et
ec
t
u
n
d
e
r
s
tan
d
ab
le
r
u
les
w
it
h
a
h
i
g
h
d
eg
r
ee
o
f
clas
s
i
f
icatio
n
ac
cu
r
ac
y
d
ep
e
n
d
in
g
o
n
t
h
e
le
ast
f
ea
tu
r
e
s
s
e
lecte
d
.
T
h
u
s
,
t
h
ese
al
g
o
r
ith
m
s
ar
e
s
u
itab
le
f
o
r
d
ec
is
io
n
-
m
ak
in
g
in
t
h
e
m
ed
ical
f
ield
,
esp
ec
iall
y
in
th
e
id
e
n
ti
f
icatio
n
an
d
d
e
tectio
n
o
f
t
h
e
r
is
k
f
ac
to
r
s
th
a
t c
au
s
e
t
h
e
d
is
ea
s
e.
RE
F
E
R
E
NC
E
S
[1
]
G
.
S
u
m
a
lath
a
a
n
d
N.
J.
R.
M
u
n
iraj,
“
S
u
rv
e
y
o
n
m
e
d
ica
l
d
iag
n
o
sis
u
sin
g
d
a
ta
m
in
in
g
tec
h
n
iq
u
e
s,”
2
0
1
3
In
t
e
rn
a
t
io
n
a
l
C
o
n
f
e
re
n
c
e
o
n
O
p
t
i
c
a
l
Ima
g
in
g
S
e
n
s
o
r a
n
d
S
e
c
u
r
ity
,
p
p
.
1
-
8
,
2
0
1
3
.
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
.
6
,
Dec
em
b
er
2
0
2
0
:
6
6
5
5
-
6
6
6
3
6662
[2
]
B.
W
.
S
tew
a
rt
a
n
d
C.
P
.
W
il
d
,
“
W
o
rld
c
a
n
c
e
r
re
p
o
rt
2
0
1
4
,
”
W
o
rld
He
a
l
th
Org
a
n
iza
ti
o
n
,
p
p
.
1
-
2
,
2
0
1
4
.
[3
]
O
.
N.
Ha
y
a
ti
,
“
Ca
n
c
e
r
o
f
th
e
c
e
rv
ix
-
F
ro
m
b
lea
k
p
a
st
to
b
rig
h
t
f
u
tu
re
:
A
re
v
ie
w
,
w
it
h
a
n
e
m
p
h
a
sis
o
n
c
a
n
c
e
r
o
f
th
e
c
e
rv
ix
in
M
a
la
y
sia
,
”
M
a
la
y
sia
n
J
o
u
rn
a
l
o
f
M
e
d
ica
l
S
c
i
e
n
c
e
s
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
1
3
-
2
6
,
2
0
0
3
.
[4
]
A
.
G
a
d
d
u
c
c
i,
e
t
a
l.
,
“
S
m
o
k
in
g
h
a
b
it
,
im
m
u
n
e
su
p
p
re
ss
i
o
n
,
o
ra
l
c
o
n
trac
e
p
ti
v
e
u
se
,
a
n
d
h
o
rm
o
n
e
re
p
la
c
e
m
e
n
t
th
e
ra
p
y
u
se
a
n
d
c
e
rv
ica
l
c
a
r
c
in
o
g
e
n
e
sis:
a
re
v
ie
w
o
f
th
e
li
tera
tu
re
,
”
Gy
n
e
c
o
l
o
g
ica
l
En
d
o
c
rin
o
l
ogy
,
v
o
l.
2
7
,
n
o
.
8
,
p
p
.
5
9
7
-
6
0
4
,
2
0
1
1
.
[5
]
P
.
L
u
h
n
,
e
t
a
l.
,
“
T
h
e
ro
le
o
f
c
o
-
fa
c
to
rs
in
th
e
p
ro
g
re
ss
io
n
f
ro
m
h
u
m
a
n
p
a
p
il
lo
m
a
v
iru
s
in
f
e
c
ti
o
n
to
c
e
rv
ica
l
c
a
n
c
e
r,
”
Gy
n
e
c
o
l
o
g
ic
O
n
c
o
l
o
g
y
,
v
o
l
.
1
2
8
,
n
o
.
2
,
p
p
.
2
6
5
-
2
7
0
,
2
0
1
3
.
[6
]
M
.
Ex
n
e
r
,
e
t
a
l.
,
“
V
a
l
u
e
o
f
d
if
f
u
sio
n
-
w
e
ig
h
ted
M
RI
in
d
iag
n
o
sis
o
f
u
terin
e
c
e
rv
ica
l
c
a
n
c
e
r:
a
p
ro
sp
e
c
ti
v
e
stu
d
y
e
v
a
lu
a
ti
n
g
th
e
b
e
n
e
f
it
s
o
f
DW
I
c
o
m
p
a
re
d
to
c
o
n
v
e
n
ti
o
n
a
l
M
R
se
q
u
e
n
c
e
s
in
a
3
T
e
n
v
iro
n
m
e
n
t
,
”
Acta
ra
d
io
l
o
g
ica
,
v
o
l
.
5
7
,
n
o
.
7
,
p
p
.
8
6
9
-
8
7
7
,
2
0
1
6
.
[7
]
P
.
Z.
M
c
V
e
ig
h
,
e
t
a
l.
,
“
Dif
f
u
s
io
n
-
w
e
ig
h
ted
M
RI
i
n
c
e
rv
ica
l
c
a
n
c
e
r,
”
Eu
r
o
p
e
a
n
R
a
d
io
l
ogy
,
v
o
l.
1
8
,
n
o
.
5
,
p
p
.
1
0
5
8
-
1
0
6
4
,
2
0
0
8
.
[8
]
H.
S
.
Cro
n
jé,
“
S
c
re
e
n
in
g
f
o
r
c
e
r
v
ica
l
c
a
n
c
e
r
in
d
e
v
e
lo
p
in
g
c
o
u
n
t
ries
,
”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Gy
n
e
c
o
l
o
g
y
a
n
d
Ob
ste
t
ric
s
,
v
o
l.
8
4
,
n
o
.
2
,
p
p
.
1
0
1
-
1
0
8
,
2
0
0
4
.
[9
]
M
.
Da
sh
a
n
d
H.
L
iu
,
“
F
e
a
tu
re
se
lec
ti
o
n
f
o
r
c
las
sif
ica
ti
o
n
,
”
In
tell
i
g
e
n
t
D
a
ta
A
n
a
l
y
sis
,
v
o
l.
1
,
n
o
.
1
-
4
,
p
p
.
1
3
1
-
1
5
6
,
1
9
9
7
.
[1
0
]
H.
L
iu
a
n
d
L
.
Yu
,
“
T
o
wa
rd
in
teg
ra
ti
n
g
f
e
a
tu
re
s
e
lec
ti
o
n
a
lg
o
rit
h
m
s
f
o
r
c
las
si
f
ic
a
ti
o
n
a
n
d
c
lu
ste
rin
g
,
”
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
Kn
o
wl
e
d
g
e
a
n
d
Da
ta
E
n
g
in
e
e
rin
g
,
v
o
l.
1
7
,
n
o
.
4
,
p
p
.
4
9
1
-
5
0
2
,
2
0
0
5
.
[1
1
]
Y.
G
ó
m
e
z
,
e
t
a
l.
,
“
M
u
lt
i
-
c
o
lo
n
y
A
CO
a
n
d
Ro
u
g
h
S
e
t
T
h
e
o
ry
to
Distrib
u
ted
F
e
a
tu
re
S
e
lec
ti
o
n
P
ro
b
lem
,
”
in
In
ter
n
a
t
io
n
a
l
W
o
rk
-
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
i
a
l
Ne
u
r
a
l
Ne
two
rk
s
,
p
p
.
4
5
8
-
4
6
1
,
2
0
0
9
.
[1
2
]
C.
L
.
Hu
a
n
g
,
“
A
CO
-
b
a
se
d
h
y
b
rid
c
las
sif
ic
a
ti
o
n
s
y
ste
m
w
it
h
fe
a
tu
re
su
b
se
t
se
lec
ti
o
n
a
n
d
m
o
d
e
l
p
a
ra
m
e
ters
o
p
ti
m
iza
ti
o
n
,
”
Ne
u
r
o
c
o
mp
u
ti
n
g
,
v
o
l.
7
3
,
n
o
.
1
-
3
,
p
p
.
4
3
8
-
4
4
8
,
2
0
0
9
.
[1
3
]
M
.
M
.
Ka
b
ir,
e
t
a
l.
,
“
A
n
e
w
h
y
b
rid
a
n
t
c
o
lo
n
y
o
p
ti
m
iza
ti
o
n
a
lg
o
rit
h
m
f
o
r
f
e
a
tu
re
se
le
c
ti
o
n
,
”
Exp
e
rt
S
y
st
e
ms
wit
h
Ap
p
l
ic
a
ti
o
n
s
,
v
o
l
.
3
9
,
n
o
.
3
,
p
p
.
3
7
4
7
-
3
7
6
3
,
2
0
1
2
.
[1
4
]
H.
Ba
n
a
ti
a
n
d
M
.
Ba
jaj,
“
F
iref
ly
b
a
s
e
d
f
e
a
tu
re
se
lec
ti
o
n
a
p
p
ro
a
c
h
,
”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
t
er
S
c
i
e
n
c
e
Iss
u
e
s
,
v
o
l.
8
,
n
o
.
4
,
p
p
.
4
7
3
-
4
8
0
,
2
0
1
1
.
[1
5
]
S
.
M
.
V
ieira
,
e
t
a
l.
,
“
M
o
d
if
ied
b
i
n
a
ry
P
S
O
f
o
r
f
e
a
tu
re
s
e
lec
ti
o
n
u
si
n
g
S
V
M
a
p
p
li
e
d
t
o
m
o
rtalit
y
p
re
d
ictio
n
o
f
se
p
ti
c
p
a
ti
e
n
ts,”
A
p
p
l
ie
d
S
o
ft
C
o
mp
u
t
i
n
g
,
v
o
l.
1
3
,
n
o
.
8
,
p
p
.
3
4
9
4
-
3
5
0
4
,
2
0
1
3
.
[1
6
]
M
.
S
.
R.
Na
ll
u
r
i
,
e
t
a
l.
,
“
A
n
Eff
icie
n
t
F
e
a
tu
re
S
e
lec
ti
o
n
u
sin
g
A
rti
f
icia
l
F
ish
S
w
a
r
m
Op
ti
m
iza
t
io
n
a
n
d
S
VM
Clas
sif
ier,
”
2
0
1
7
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ne
two
rk
s
a
n
d
Ad
v
a
n
c
e
s
in
C
o
mp
u
ta
t
io
n
a
l
T
e
c
h
n
o
lo
g
ies
,
p
p
.
4
07
-
41
1
,
2
0
1
7
.
[1
7
]
V
.
A
g
ra
w
a
l
a
n
d
S
.
C
h
a
n
d
ra
,
“
F
e
a
tu
re
se
lec
ti
o
n
u
si
n
g
A
rti
f
i
c
ial
Be
e
Co
lo
n
y
a
lg
o
rit
h
m
f
o
r
m
e
d
ica
l
ima
g
e
c
las
si
f
ica
ti
o
n
,
”
2
0
1
5
Ei
g
h
t
h
In
t
e
rn
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Co
n
tem
p
o
ra
ry
Co
mp
u
t
i
n
g
,
p
p
.
1
7
1
-
1
7
6
,
2
0
1
5
.
[1
8
]
B.
Ya
n
g
,
e
t
a
l.
,
“
F
e
a
tu
re
S
e
lec
ti
o
n
Ba
se
d
o
n
M
o
d
if
ied
Ba
t
A
lg
o
rit
h
m
,
”
IEI
CE
T
ra
n
s
a
c
ti
o
n
s
o
n
I
n
fo
rm
a
t
io
n
a
n
d
S
y
ste
ms
,
v
o
l.
E1
0
0
.
D,
n
o
.
8
,
p
p
.
1
8
6
0
-
1
8
6
9
,
2
0
1
7
.
[1
9
]
X
.
S
.
Ya
n
g
,
“
A
n
e
w
m
e
tah
e
u
risti
c
Ba
t
-
in
s
p
ired
A
lg
o
rit
h
m
,
”
Na
tu
re
I
n
sp
ire
d
Co
o
p
e
ra
ti
v
e
S
tra
teg
ie
f
o
r
Op
ti
miza
ti
o
n
,
p
p
.
6
5
-
7
4
,
2
0
1
0
.
[2
0
]
B.
Ba
n
sa
l
a
n
d
A
.
S
a
h
o
o
,
“
F
u
l
l
m
o
d
e
l
se
lec
ti
o
n
u
si
n
g
Ba
t
a
lg
o
rit
h
m
,
”
2
0
1
5
I
n
t
e
rn
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Co
g
n
it
ive
Co
mp
u
t
in
g
a
n
d
In
f
o
rm
a
ti
o
n
Pro
c
e
ss
in
g
,
p
p
.
1
-
4
,
2
0
1
5
.
[2
1
]
H.
Zh
a
n
g
a
n
d
G
.
S
u
n
,
“
F
e
a
tu
r
e
se
lec
ti
o
n
u
sin
g
tab
u
se
a
rc
h
m
e
th
o
d
,
”
P
a
tt
e
rn
Rec
o
g
n
i
t
io
n
,
v
o
l.
3
5
,
n
o
.
3
,
p
p
.
7
0
1
-
7
1
1
,
2
0
0
2
.
[2
2
]
M
.
R.
Ho
ss
a
in
,
e
t
a
l.
,
“
T
h
e
Ef
fe
c
ti
v
e
n
e
ss
o
f
F
e
a
tu
re
S
e
lec
ti
o
n
M
e
th
o
d
in
S
o
lar
P
o
w
e
r
P
re
d
icti
o
n
,
”
J
o
u
rn
a
l
o
f
Ren
e
w
a
b
le
E
n
e
rg
y
,
v
o
l.
2
0
1
3
,
n
o
.
2
,
p
p
.
1
-
9
,
2
0
1
3
.
[2
3
]
D.
T
.
P
h
a
m
,
e
t
a
l.
,
“
A
p
p
li
c
a
ti
o
n
o
f
th
e
Be
e
s
A
l
g
o
rit
h
m
to
th
e
S
e
lec
ti
o
n
F
e
a
tu
re
s
f
o
r
M
a
n
u
f
a
c
tu
r
in
g
Da
ta,”
3
rd
In
ter
n
a
t
io
n
a
l
Vi
rtu
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
telli
g
e
n
t
Pr
o
d
u
c
ti
o
n
M
a
c
h
i
n
e
a
n
d
S
y
ste
ms
,
2
0
0
7
.
[2
4
]
Y.
S
u
n
,
e
t
a
l.
,
“
L
o
c
a
l
-
L
e
a
rn
in
g
b
a
se
d
F
e
a
tu
re
S
e
lec
ti
o
n
f
o
r
Hig
h
Dim
e
n
sio
n
a
l
Da
ta
A
n
a
l
y
sis,”
IE
EE
T
ra
n
s
a
c
ti
o
n
s
o
n
P
a
tt
e
rn
An
a
lyi
a
n
d
M
a
c
h
i
n
e
I
n
telli
g
e
n
c
e
,
v
o
l.
3
2
,
n
o
.
9
,
p
p
.
16
1
0
-
1
6
2
6
,
2
0
1
0
.
[2
5
]
Q
.
S
o
n
g
,
e
t
a
l.
,
“
A
F
a
st
Clu
ste
rin
g
-
Ba
se
d
F
e
a
tu
re
S
u
b
se
t
S
e
lec
ti
o
n
A
lg
o
rit
h
m
f
o
r
Hig
h
Di
m
e
n
sio
n
a
l
Da
ta,”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Kn
o
wled
g
e
a
n
d
Da
ta
E
n
g
in
e
e
rin
g
,
v
o
l.
25
,
n
o
.
1
,
p
p
.
1
-
1
4
,
2
0
1
3
.
[2
6
]
S
.
Dre
y
e
r,
“
E
v
o
lu
ti
o
n
a
ry
F
e
a
tu
re
S
e
lec
ti
o
n
,
”
E
n
c
y
c
lo
p
e
d
i
a
o
f
M
a
c
h
in
e
L
e
a
rn
i
n
g
,
p.
7
8
,
2
0
1
0
.
[2
7
]
El
B
.
A
sm
a
e
,
e
t
a
l.
,
“
A
g
e
n
e
ti
c
a
lg
o
rit
h
m
f
o
r
th
e
o
p
ti
m
a
l
d
e
sig
n
o
f
a
m
u
lt
istag
e
a
m
p
li
f
ier,”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tr
ica
l
a
n
d
C
o
mp
u
t
er
En
g
in
e
e
rin
g
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
1
2
9
-
1
3
8
,
2
0
2
0
.
[2
8
]
R.
S
.
P
a
rp
in
e
ll
i,
e
t
a
l.
,
“
Da
ta
M
in
i
n
g
w
it
h
a
n
A
n
t
Co
lo
n
y
O
p
ti
m
iza
ti
o
n
A
l
g
o
rit
h
m
,
”
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
Evo
l
u
ti
o
n
a
ry
Co
mp
u
t
a
ti
o
n
,
v
o
l.
6
,
n
o
.
4
,
p
p
.
3
2
1
-
3
3
2
,
2
0
0
2
.
[2
9
]
B.
L
iu
,
e
t
a
l
.
,
“
Clas
sif
ica
ti
o
n
ru
le
d
isc
o
v
e
ry
w
it
h
a
n
t
c
o
lo
n
y
o
p
ti
m
iza
ti
o
n
,
”
2
0
0
3
IEE
E/
W
IC
In
t
e
rn
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
on
In
tell
ig
e
n
t
Ag
e
n
t
T
e
c
h
n
o
l
ogy
,
p
p
.
8
3
-
8
8
,
2
0
0
3
.
[3
0
]
K.
Ba
c
h
e
a
n
d
M
.
L
ich
m
a
n
,
“
UCI
M
a
c
h
in
e
L
e
a
rn
in
g
Re
p
o
si
to
ry
,
”
Un
iv
e
rs
it
y
o
f
C
a
li
f
o
rn
i
a
,
S
c
h
o
o
l
o
f
I
n
f
o
rm
a
ti
o
n
a
n
d
Co
m
p
u
ter
S
c
ie
n
c
e
,
2
0
1
3
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:
//
a
rc
h
iv
e
.
ics
.
u
c
i.
e
d
u
/m
l.
[3
1
]
J.
W
a
h
id
a
n
d
H.
F
.
A
.
A
l
-
m
a
z
i
n
i,
“
Clas
sif
ica
ti
o
n
o
f
Ce
rv
ica
l
Ca
n
c
e
r
Us
in
g
A
n
t
-
M
in
e
r
f
o
r
M
e
d
ica
l
Ex
p
e
rti
se
Clas
sif
ic
a
ti
o
n
o
f
Ce
rv
ic
a
l
Ca
n
c
e
r
Us
in
g
A
n
t
-
M
in
e
r
f
o
r
M
e
d
ica
l
Ex
p
e
rti
se
Kn
o
w
led
g
e
M
a
n
a
g
e
m
e
n
t,
”
Kn
o
wled
g
e
M
a
n
a
g
e
me
n
t
In
ter
n
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
,
p
p
.
3
9
3
-
3
9
7
,
2
0
1
8
.
[3
2
]
W
.
W
u
a
n
d
H.
Zh
o
u
,
“
Da
ta
-
d
riv
e
n
Dia
g
n
o
sis
o
f
Ce
rv
ica
l
Ca
n
c
e
r
w
it
h
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
-
Ba
se
d
A
p
p
ro
a
c
h
e
s,”
IEE
E
Acc
e
ss
,
v
o
l.
5
,
p
p
.
2
5
1
8
9
-
2
5
1
9
5
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
b
a
t
-
a
n
t c
o
lo
n
y
o
p
timiz
a
tio
n
a
lg
o
r
ith
m
fo
r
r
u
le
-
b
a
s
ed
fea
tu
r
e
s
elec
tio
n
in
h
ea
lth
c
a
r
e
(
R
a
fid
S
a
g
b
a
n
)
6663
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Dr
.
Ra
fid
S
a
g
b
a
n
,
h
o
ld
s
a
Ba
c
h
e
lo
r
in
Co
m
p
u
ter
S
c
ie
n
c
e
s
f
ro
m
Un
iv
e
rsit
y
o
f
Ba
b
y
lo
n
,
Ira
q
i
n
1
9
9
9
a
n
d
Hig
h
e
r
Dip
l
o
m
a
in
Da
ta
S
e
c
u
rit
y
f
ro
m
Ir
a
q
i
Co
m
m
is
sio
n
f
o
r
Co
m
p
u
ters
a
n
d
In
f
o
rm
a
ti
c
s
in
2
0
0
1
.
His
M
a
ste
r
’s
d
e
g
re
e
a
n
d
P
h
.
D
in
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
re
b
o
th
f
ro
m
Un
iv
e
rsiti
Uta
ra
M
a
la
y
sia
in
2
0
1
5
.
Ra
f
id
'
s
re
se
a
rc
h
a
n
d
d
e
v
e
lo
p
m
e
n
t
e
x
p
e
r
ien
c
e
in
c
lu
d
e
s
o
v
e
r
1
3
y
e
a
rs
in
th
e
Ac
a
d
e
m
ia
a
n
d
In
d
u
stry
.
He
w
o
rk
s
in
a
m
u
lt
i
-
d
isc
ip
li
n
a
ry
e
n
v
iro
n
m
e
n
t
in
v
o
lv
in
g
c
o
m
p
u
tatio
n
a
l
in
telli
g
e
n
c
e
,
sw
a
r
m
in
telli
g
e
n
c
e
a
l
g
o
rit
h
m
s,
b
u
sin
e
ss
in
telli
g
e
n
c
e
a
n
d
w
e
b
d
e
si
g
n
a
n
d
d
e
v
e
lo
p
m
e
n
t
.
Dr
.
H
a
y
d
a
r
A.
M
a
r
h
o
o
n
h
o
ld
s
a
Ba
c
h
e
lo
r
in
C
o
n
tr
o
l
a
n
d
S
y
ste
m
En
g
in
e
e
rin
g
f
ro
m
Un
iv
e
r
sit
y
o
f
T
e
c
h
n
o
lo
g
y
,
Ba
g
h
d
a
d
in
2
0
0
3
.
His
M
a
ste
r’s
d
e
g
re
e
a
n
d
P
h
.
D
i
n
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
re
b
o
t
h
f
ro
m
Un
iv
e
rsiti
Uta
ra
M
a
la
y
sia
in
2
0
1
2
a
n
d
2
0
1
7
re
sp
e
c
ti
v
e
l
y
.
Ha
y
d
a
r
A
b
d
u
lam
e
e
r
M
a
rh
o
o
n
c
u
rre
n
tl
y
w
o
rk
s
a
t
th
e
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsit
y
o
f
Ke
rb
a
la.
Ha
y
d
a
r
d
o
e
s
re
se
a
rc
h
in
Co
m
p
u
ter
Co
m
m
u
n
ica
ti
o
n
s
(
Ne
tw
o
rk
s)
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
.
T
h
e
ir
m
o
st
re
c
e
n
t
p
u
b
li
c
a
ti
o
n
is
'
P
e
rf
o
r
m
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
CCM
a
n
d
T
S
CP
ro
u
ti
n
g
p
ro
t
o
c
o
ls
w
it
h
in
/w
it
h
o
u
t
d
a
ta
f
u
sin
g
in
W
S
Ns
'
.
Ra
a
i
d
Alu
b
a
d
y
re
c
e
iv
e
d
h
is P
h
.
D.
d
e
g
re
e
s
in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
f
ro
m
th
e
Un
iv
e
rsiti
Uta
ra
M
a
la
y
sia
,
in
2
0
1
7
.
He
g
o
t
a
Ba
c
h
e
lo
r'
s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
s
f
ro
m
Un
iv
e
rsit
y
o
f
Ba
b
y
lo
n
-
Ira
q
,
a
Hig
h
e
r
Dip
lo
m
a
in
Da
ta
S
e
c
u
rit
y
f
ro
m
Ira
q
i
Co
m
m
issio
n
f
o
r
Co
m
p
u
ters
a
n
d
In
f
o
rm
a
ti
c
s
-
Ira
q
,
a
n
d
a
M
a
ste
r'
s
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
f
ro
m
UU
M
-
M
a
la
y
sia
.
Cu
rre
n
tl
y
a
tt
a
c
h
e
d
to
th
e
I
n
terN
e
tW
o
rk
s
Re
s
e
a
rc
h
L
a
b
o
r
a
to
ry
(I
RL
).
A
lu
b
a
d
y
'
s
r
e
se
a
r
c
h
a
n
d
d
e
v
e
lo
p
m
e
n
t
e
x
p
e
rien
c
e
in
c
lu
d
e
s
o
v
e
r
1
5
y
e
a
rs
in
th
e
Ac
a
d
e
m
ia.
His
c
u
rre
n
t
a
re
a
o
f
r
e
se
a
r
c
h
f
o
c
u
se
s
o
n
th
e
F
u
tu
re
In
ter
n
e
t
(ICN
a
n
d
ND
N),
W
irele
ss
Ne
t
wo
rk
in
g
/
M
A
NE
T
,
In
tern
e
t
o
f
T
h
in
g
s,
Ro
u
ti
n
g
P
ro
to
c
o
l,
P
e
rf
o
r
m
a
n
c
e
A
n
a
l
y
sis a
n
d
Co
m
p
u
tatio
n
a
l
In
telli
g
e
n
c
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.