T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
3
,
J
u
n
e
2
0
2
0
,
p
p
.
1688
~
1
6
9
4
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
KA
.
v
1
8
i3
.
1
3
7
6
4
1688
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
A new
m
o
del f
o
r
l
a
rg
e data
set di
m
e
nsio
na
lity reducti
o
n bas
ed
o
n t
ea
ching
learni
ng
-
ba
sed o
pti
m
i
za
tion a
nd log
istic
regres
sio
n
H
ind
Ra
a
d Ib
ra
hee
m
1
,
Z
a
hr
a
a
F
a
iz
H
us
s
a
in
2
,
Su
ra
M
a
zi
n Ali
3
,
M
o
ha
mm
a
d Alj
a
na
bi
4
,
M
o
s
t
a
f
a
Abdu
lg
ha
f
o
o
r
M
o
h
a
mm
ed
5
,
T
o
le
S
uti
k
no
6
1,
2
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
A
l
S
a
la
m
Un
iv
e
r
sit
y
Co
ll
e
g
e
,
Ira
q
3
Co
ll
e
g
e
o
f
P
o
li
ti
c
a
l
S
c
ien
c
e
,
M
u
sta
n
siriy
a
h
Un
iv
e
rsit
y
,
Ira
q
4
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Co
ll
e
g
e
o
f
Ed
u
c
a
ti
o
n
,
A
li
ra
q
ia
Un
iv
e
rs
i
t
y
,
Ira
q
5
F
a
c
u
lt
y
o
f
A
u
to
m
a
ti
c
Co
n
tro
l
a
n
d
Co
m
p
u
ters
,
Un
iv
e
rsit
y
P
o
ly
tec
h
n
ic o
f
Bu
c
h
a
re
st,
Ro
m
a
n
ia
6
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsitas
A
h
m
a
d
Da
h
lan
,
In
d
o
n
e
sia
6
Em
b
e
d
d
e
d
S
y
ste
m
a
n
d
P
o
w
e
r
El
e
c
tro
n
ics
Re
se
a
rc
h
G
ro
u
p
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 3
0
,
2
0
1
9
R
ev
i
s
ed
Feb
2
8
,
2
0
2
0
A
cc
ep
ted
Ma
r
2
4
,
2
0
2
0
On
e
o
f
th
e
h
u
m
a
n
d
ise
a
se
s
w
it
h
a
h
ig
h
ra
te
o
f
m
o
rtalit
y
e
a
c
h
y
e
a
r
is
b
re
a
st
c
a
n
c
e
r
(BC).
Am
o
n
g
a
ll
th
e
f
o
rm
s
o
f
c
a
n
c
e
r,
BC
is
th
e
c
o
m
m
o
n
e
s
t
c
a
u
se
o
f
d
e
a
th
a
m
o
n
g
w
o
m
e
n
g
lo
b
a
ll
y
.
S
o
m
e
o
f
th
e
e
ffe
c
ti
v
e
w
a
y
s
o
f
d
a
ta
c
l
a
ss
if
i
c
a
ti
o
n
a
re
d
a
ta
m
in
in
g
a
n
d
c
las
sif
ica
ti
o
n
m
e
th
o
d
s.
T
h
e
se
m
e
th
o
d
s
a
re
p
a
rti
c
u
larly
e
ff
ici
e
n
t
in
th
e
m
e
d
ica
l
f
ield
d
u
e
to
th
e
p
re
se
n
c
e
o
f
irrele
v
a
n
t
a
n
d
re
d
u
n
d
a
n
t
a
tt
rib
u
tes
in
m
e
d
ica
l
d
a
tas
e
ts.
S
u
c
h
re
d
u
n
d
a
n
t
a
tt
ri
b
u
te
s
a
re
n
o
t
n
e
e
d
e
d
t
o
o
b
tai
n
a
n
a
c
c
u
ra
te
e
sti
m
a
ti
o
n
o
f
d
ise
a
se
d
iag
n
o
sis.
T
e
a
c
h
in
g
lea
r
n
in
g
-
b
a
se
d
o
p
ti
m
iza
ti
o
n
(T
L
BO)
is
a
n
e
w
m
e
t
a
h
e
u
risti
c
t
h
a
t
h
a
s
b
e
e
n
su
c
c
e
ss
f
u
ll
y
a
p
p
li
e
d
to
se
v
e
ra
l
in
trac
tab
le
o
p
ti
m
iza
ti
o
n
p
ro
b
lem
s
in
re
c
e
n
t
y
e
a
rs.
Th
is
p
a
p
e
r
p
re
se
n
ts
t
h
e
u
se
o
f
a
m
u
lt
i
-
o
b
je
c
ti
v
e
TL
BO
a
lg
o
rit
h
m
f
o
r
th
e
s
e
lec
ti
o
n
o
f
f
e
a
tu
re
su
b
se
ts
in
a
u
t
o
m
a
ti
c
BC
d
iag
n
o
sis.
F
o
r
t
h
e
c
las
sif
ica
ti
o
n
t
a
sk
in
th
is
w
o
rk
,
th
e
l
o
g
isti
c
re
g
re
ss
io
n
(L
R)
m
e
th
o
d
w
a
s
d
e
p
lo
y
e
d
.
F
ro
m
th
e
re
su
lt
s,
th
e
p
ro
jec
ted
m
e
th
o
d
p
r
o
d
u
c
e
d
b
e
tt
e
r
B
C
d
a
tas
e
t
c
l
a
ss
i
f
ica
ti
o
n
a
c
c
u
ra
c
y
(c
las
si
f
ied
in
to
m
a
li
g
n
a
n
t
a
n
d
b
e
n
ig
n
).
T
h
is
re
su
lt
s
h
o
w
e
d
th
a
t
t
h
e
p
ro
jec
ted
TL
BO
is
a
n
e
ff
icie
n
t
f
e
a
tu
re
s
o
p
ti
m
iz
a
ti
o
n
tec
h
n
i
q
u
e
f
o
r
su
sta
in
i
n
g
d
a
ta
-
b
a
se
d
d
e
c
isio
n
-
m
a
k
in
g
s
y
ste
m
s.
K
ey
w
o
r
d
s
:
Featu
r
e
s
elec
t
io
n
FSS
I
DS
NT
L
BO
Su
b
s
et
T
L
B
O
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mo
h
a
m
m
ad
A
lj
an
ab
i,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
A
lira
q
ia
U
n
i
v
er
is
t
y
,
A
ls
a
y
d
y
a,
B
ag
h
d
ad
,
I
r
aq
E
m
ail:
m
o
h
a
m
m
ad
.
cs8
8
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
B
r
e
a
s
t
ca
n
c
e
r
(
B
C
)
i
s
th
e
m
o
s
t
c
o
m
m
o
n
c
an
c
e
r
am
o
n
g
w
o
m
en
a
r
o
u
n
d
th
e
w
o
r
l
d
.
A
b
o
u
t
2
5
%
o
f
al
l
n
e
w
c
a
n
c
e
r
c
as
es
a
r
e
d
i
a
g
n
o
s
e
d
a
s
B
C
i
n
w
o
m
en
as
s
t
at
e
d
b
y
th
e
A
m
e
r
i
c
an
C
an
ce
r
S
o
c
i
e
ty
(
A
C
S
)
.
O
n
e
w
o
m
an
d
i
es
f
r
o
m
B
C
ev
e
r
y
m
in
u
t
e
a
n
d
m
o
r
e
th
an
1
4
0
0
w
o
m
en
d
i
e
ev
e
r
y
d
ay
f
r
o
m
B
C
[
1
]
.
C
a
n
c
e
r
r
esu
l
ts
f
r
o
m
th
e
r
a
p
i
d
a
n
d
u
n
c
o
n
t
r
o
l
l
a
b
l
e
d
iv
is
i
o
n
o
f
c
e
ll
s
w
h
i
ch
r
e
s
u
l
t
s
in
th
e
f
o
r
m
a
ti
o
n
o
f
ex
t
r
a
t
is
s
u
e
m
ass
c
a
ll
e
d
tu
m
o
r
s
in
th
e
b
o
d
y
[
2
]
.
S
u
c
h
tu
m
o
r
s
a
r
e
e
i
th
e
r
c
an
c
e
r
o
u
s
o
r
n
o
n
-
c
an
ce
r
o
u
s
.
T
h
e
s
p
r
ea
d
o
f
t
h
e
m
al
ig
n
an
t
tu
m
o
r
s
is
f
a
s
t
e
r
as
th
ey
s
p
r
e
a
d
r
a
p
i
d
ly
t
o
c
au
s
e
h
a
r
m
t
o
th
e
n
ei
g
h
b
o
r
in
g
t
i
s
s
u
es
.
C
an
c
e
r
is
c
o
m
m
o
n
ly
n
am
e
d
b
as
e
d
o
n
th
e
af
f
e
c
te
d
b
o
d
y
p
a
r
t
o
r
w
h
e
r
e
i
t
s
t
a
r
t
e
d
.
H
en
c
e
,
B
C
i
s
a
f
o
r
m
o
f
m
a
l
ig
n
an
t
tu
m
o
r
w
h
ic
h
r
esu
l
ts
f
r
o
m
th
e
u
n
c
o
n
t
r
o
l
l
ed
d
i
v
is
i
o
n
o
f
b
r
e
a
s
t
c
e
l
ls
.
A
m
o
n
g
t
h
e
m
a
jo
r
s
ig
n
s
o
f
B
C
a
r
e
ch
an
g
e
d
an
d
i
n
c
r
e
a
s
e
i
n
th
e
i
n
c
r
e
a
s
e
n
o
r
m
a
l
s
i
ze
an
d
s
h
a
p
e
o
f
th
e
b
r
e
a
s
t
,
p
a
i
n
in
th
e
b
r
e
as
t
,
in
f
l
am
m
at
i
o
n
o
f
th
e
af
f
e
c
t
e
d
o
r
a
l
l
p
a
r
t
s
o
f
t
h
e
b
r
e
a
s
t
,
v
a
r
y
in
g
b
r
e
a
s
t
s
k
in
c
o
l
o
r
s
,
p
r
e
s
e
n
c
e
o
f
a
l
u
m
p
b
en
e
a
th
t
h
e
a
r
m
a
r
e
a
,
et
c
.
[
2
-
4
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
n
ew mo
d
el
fo
r
la
r
g
e
d
a
t
a
s
et
d
i
men
s
io
n
a
lity red
u
ctio
n
b
a
s
ed
o
n
…
(
Hin
d
R
a
a
d
I
b
r
a
h
ee
m
)
1689
T
h
e
W
o
r
l
d
H
e
a
l
t
h
O
r
g
an
i
z
at
io
n
(
W
H
O
)
[
5
]
r
e
p
o
r
t
e
d
t
h
a
t
t
h
e
r
e
a
r
e
a
r
o
u
n
d
1
.
2
m
i
l
li
o
n
ca
s
es
o
f
B
C
d
i
a
g
n
o
s
e
d
in
w
o
m
en
ev
e
r
y
y
e
ar
.
O
n
e
o
u
t
o
f
8
w
o
m
en
in
th
e
USA
is
liv
in
g
w
it
h
B
C
.
T
h
e
i
d
en
t
if
i
c
at
i
o
n
o
f
B
C
c
an
b
e
d
o
n
e
m
an
u
a
l
ly
b
y
th
e
p
h
y
s
i
ci
a
n
,
b
u
t
i
t
is
a
d
if
f
ic
u
l
t
t
a
s
k
d
u
e
to
t
h
e
n
e
e
d
t
o
r
em
em
b
e
r
a
l
l
t
h
e
r
e
q
u
i
r
e
d
in
f
o
r
m
a
ti
o
n
f
o
r
e
a
ch
c
a
s
e
,
g
iv
in
g
r
is
e
t
o
lo
w
i
d
en
t
if
i
c
a
t
i
o
n
a
c
cu
r
a
cy
.
B
r
e
a
s
t
c
an
c
e
r
-
r
e
l
at
e
d
m
o
r
t
al
i
ty
r
a
t
e
c
an
b
e
r
e
d
u
c
e
d
t
h
r
o
u
g
h
d
i
s
e
a
s
e
d
e
t
ec
t
i
o
n
at
th
e
e
a
r
ly
s
t
ag
e
[
6
-
9
]
.
S
ev
e
r
a
l
c
o
n
v
e
n
ti
o
n
al
B
C
d
e
t
ec
t
i
o
n
m
et
h
o
d
s
e
x
is
t
b
u
t
th
e
h
i
g
h
er
a
c
c
u
r
ac
y
o
f
m
a
ch
in
e
l
e
a
r
n
in
g
(
M
L
)
cl
a
s
s
if
ie
r
s
is
m
ak
in
g
th
em
m
o
r
e
u
s
ef
u
l
r
e
ce
n
t
ly
.
A
s
s
u
c
h
,
th
e
r
e
a
r
e
s
ev
e
r
al
M
L
m
e
th
o
d
s
f
o
r
e
a
r
ly
c
an
ce
r
d
e
t
e
c
t
i
o
n
a
n
d
a
ls
o
ch
e
ck
in
g
f
o
r
it
s
r
el
a
p
s
e
.
A
m
o
n
g
th
es
e
ML
m
e
t
h
o
d
s
a
r
e
a
r
t
if
i
ci
a
l
n
eu
r
a
l
n
e
tw
o
r
k
(
A
NN
)
,
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
ch
in
e
(
SV
M
)
,
N
a
iv
e
B
ay
e
s
,
r
e
l
ev
an
ce
v
e
ct
o
r
m
a
ch
in
e
,
d
e
c
is
i
o
n
t
r
e
es
,
K
-
m
ea
n
s
,
K
-
n
e
a
r
es
t
n
eig
h
b
o
r
,
r
a
n
d
o
m
f
o
r
es
ts
,
e
tc
.
T
h
e
u
s
e
o
f
ML
-
b
a
s
e
d
c
l
ass
if
i
ca
t
i
o
n
s
c
h
em
e
s
is
g
a
in
in
g
a
t
t
en
ti
o
n
in
th
e
m
e
d
i
c
a
l
f
i
el
d
as
th
ey
ca
n
h
e
l
p
b
o
t
h
s
k
i
l
l
e
d
an
d
u
n
s
k
il
l
e
d
ex
p
er
t
s
in
r
e
d
u
c
in
g
p
o
s
s
i
b
l
e
e
r
r
o
r
s
a
n
d
a
c
cu
r
a
te
ly
p
r
o
v
i
d
i
n
g
t
h
e
r
eq
u
i
r
e
d
m
e
d
i
c
al
d
a
t
a
f
o
r
d
i
ag
n
o
s
i
s
w
i
th
in
a
s
h
o
r
t
t
im
e
.
H
o
w
ev
e
r
,
th
e
h
i
g
h
d
im
en
s
i
o
n
a
l
ity
o
f
th
e
d
a
t
as
e
t
r
e
p
r
e
s
en
ts
o
n
e
o
f
th
e
m
a
jo
r
l
im
i
t
at
i
o
n
s
f
o
r
e
f
f
e
c
t
iv
e
u
s
e
o
f
ML
c
l
ass
if
i
e
r
s
.
T
h
e
im
p
o
r
ta
n
t
c
r
i
t
e
r
i
a
w
h
ic
h
m
u
s
t
b
e
c
o
n
s
id
e
r
e
d
f
o
r
ef
f
e
ct
iv
e
ML
-
b
as
e
d
c
l
ass
if
i
c
at
i
o
n
a
r
e
th
e
d
a
t
a
q
u
al
i
ty
an
d
a
c
a
r
e
f
u
l
f
e
at
u
r
e
s
e
l
e
ct
i
o
n
.
F
e
atu
r
e
s
el
e
c
ti
o
n
(
FS
)
i
s
t
h
e
p
r
o
c
e
s
s
o
f
ex
t
r
a
c
t
in
g
a
s
u
b
s
e
t
o
f
r
e
l
ev
an
t
f
e
a
tu
r
es
f
r
o
m
th
e
o
r
ig
in
a
l
d
at
a
s
et
[
10
-
12
]
.
I
t
in
v
o
lv
es
t
h
e
u
s
e
o
f
FS
al
g
o
r
i
th
m
s
t
o
f
i
l
t
e
r
o
u
t
i
r
r
el
ev
an
t
an
d
r
e
d
u
n
d
a
n
t
d
a
ta
f
e
a
tu
r
es
f
r
o
m
th
e
o
r
i
g
in
al
d
a
t
as
e
t
t
o
p
r
ev
en
t
o
v
er
-
f
i
tt
in
g
[
6
,
13
]
an
d
im
p
r
o
v
e
th
e
cl
a
s
s
if
ic
a
t
i
o
n
a
c
cu
r
a
cy
o
f
th
e
m
o
d
e
l
.
F
ea
tu
r
e
s
e
l
e
ct
i
o
n
a
ls
o
r
e
d
u
c
es
th
e
cl
as
s
i
f
i
c
a
ti
o
n
m
o
d
e
ls
’
c
o
m
p
l
ex
ity
in
t
im
e
an
d
s
p
a
c
e
d
o
m
ai
n
s
[
14
-
18
]
.
T
h
e
m
ain
id
e
a
o
f
th
is
p
a
p
e
r
is
t
o
em
p
l
o
y
t
h
e
T
L
B
O
-
b
as
e
d
a
l
g
o
r
ith
m
f
o
r
f
e
a
tu
r
es
s
u
b
s
e
t
s
e
l
e
ct
i
o
n
in
B
C
d
i
ag
n
o
s
is
.
A
r
e
ce
n
t
m
e
t
ah
eu
r
is
ti
c
,
t
e
a
ch
in
g
-
l
e
a
r
n
in
g
-
b
as
e
d
o
p
t
im
i
z
a
ti
o
n
(
T
L
B
O
)
,
h
a
s
b
e
en
r
e
p
o
r
t
e
d
t
o
b
e
a
n
ef
f
i
c
ie
n
t
o
p
t
im
i
z
a
ti
o
n
t
o
o
l
t
h
a
t
i
s
i
n
s
p
i
r
ed
b
y
th
e
k
n
o
w
l
e
d
g
e
p
a
s
s
i
n
g
m
e
ch
an
is
m
s
o
f
t
e
a
ch
e
r
s
a
n
d
l
e
a
r
n
e
r
s
i
n
a
c
l
as
s
r
o
o
m
[
19
-
22
]
.
I
t
h
a
s
b
e
en
a
p
p
l
i
e
d
t
o
s
ev
e
r
a
l
w
el
l
-
k
n
o
w
n
c
o
m
b
in
a
t
o
r
i
a
l
o
p
tim
i
z
at
i
o
n
p
r
o
b
l
em
s
,
p
r
o
d
u
c
in
g
g
o
o
d
r
e
s
u
lt
s
[
23
-
26
]
.
T
h
e
f
o
l
l
o
w
in
g
s
e
c
t
i
o
n
s
d
i
s
cu
s
s
e
d
t
h
e
n
o
v
e
l
m
u
l
ti
-
o
b
je
c
t
i
v
e
T
L
B
O
o
p
t
im
iza
t
i
o
n
a
lg
o
r
i
th
m
f
o
r
a
t
ta
in
in
g
b
et
t
e
r
f
e
a
tu
r
e
s
e
l
ec
t
i
o
n
a
c
cu
r
a
cy
.
2.
RE
L
AT
E
D
WO
RK
S
C
h
u
a
n
g
et
al
.
[
27
]
p
r
o
p
o
s
ed
t
h
e
c
atf
is
h
b
in
ar
y
P
SO
(
C
at
f
i
s
h
B
P
SO)
alg
o
r
ith
m
.
I
n
t
h
is
al
g
o
r
ith
m
,
f
e
w
f
ea
t
u
r
es
ar
e
s
elec
ted
v
ia
t
h
e
in
tr
o
d
u
ctio
n
o
f
n
e
w
ca
t
f
is
h
(
p
ar
ticles)
in
to
th
e
s
o
lu
tio
n
s
p
ac
e
to
ac
h
iev
e
2
m
aj
o
r
ad
v
an
ta
g
es
:
i)
r
ed
u
ce
d
co
m
p
u
tatio
n
ti
m
e,
an
d
ii)
h
ig
h
er
class
i
f
icatio
n
ac
cu
r
ac
y
u
s
in
g
t
h
e
k
-
NN
alg
o
r
ith
m
.
I
t
w
as
ap
p
lied
an
d
co
m
p
ar
ed
t
o
1
0
class
if
icatio
n
p
r
o
b
le
m
s
ta
k
en
f
r
o
m
t
h
e
liter
atu
r
e.
E
x
p
er
i
m
en
tal
r
esu
lts
s
h
o
w
th
at
C
a
tf
is
h
B
P
SO
s
i
m
p
li
f
ie
s
t
h
e
f
ea
t
u
r
e
s
elec
tio
n
p
r
o
ce
s
s
e
f
f
ec
ti
v
el
y
,
a
n
d
eit
h
er
o
b
tain
s
h
ig
h
er
cla
s
s
i
f
icat
io
n
ac
cu
r
ac
y
o
r
u
s
e
s
f
e
w
er
f
ea
t
u
r
es th
a
n
o
th
er
f
ea
tu
r
e
s
elec
tio
n
m
et
h
o
d
s
.
B
ah
ass
i
n
e
et
al
.
[
28
]
p
r
o
p
o
s
ed
a
n
o
v
el
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
f
o
r
A
r
ab
ic
tex
t
cla
s
s
i
f
icatio
n
.
T
h
e
m
et
h
o
d
us
es
an
en
h
an
ce
d
C
h
i
-
s
q
u
ar
e
m
et
h
o
d
to
im
p
r
o
v
e
th
e
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
e
co
m
b
in
atio
n
o
f
th
e
p
r
o
p
o
s
ed
A
r
ab
ic
te
x
t
clas
s
if
icatio
n
m
o
d
el
w
it
h
SVM
cla
s
s
i
f
ier
s
i
g
n
i
f
ica
n
tl
y
en
h
a
n
ce
d
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
el
as it a
c
h
ie
v
ed
th
e
b
est F
-
m
ea
s
u
r
e
v
alu
e
o
f
9
0
.
5
0
% u
s
in
g
9
0
0
f
ea
tu
r
es.
Srid
ev
an
d
Mu
r
u
g
an
[
29
]
d
ev
elo
p
ed
a
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
f
o
r
m
ed
ical
an
al
y
s
i
s
o
f
B
C
an
d
co
m
p
ar
ed
w
it
h
s
e
v
er
al
cl
ass
i
f
icatio
n
al
g
o
r
ith
m
s
.
T
h
e
o
b
j
ec
tiv
e
o
f
th
e
p
r
esen
ted
al
g
o
r
ith
m
i
s
to
s
elec
t
a
m
i
n
i
m
u
m
n
u
m
b
er
o
f
f
ea
tu
r
es
to
p
r
o
v
id
e
h
ig
h
cla
s
s
i
f
icat
io
n
ac
cu
r
ac
y
.
T
h
e
y
r
ed
u
ce
d
t
h
e
f
e
atu
r
e
v
ec
to
r
s
to
2
2
2
f
o
r
b
o
th
d
iag
n
o
s
i
s
an
d
p
r
o
g
n
o
s
is
B
C
d
ata
s
et
s
u
s
in
g
r
o
u
g
h
s
ets an
d
co
r
r
elatio
n
tech
n
iq
u
e
s
.
Ag
r
a
w
al
et
al
.
[
30
]
p
r
o
p
o
s
ed
a
f
ea
t
u
r
e
s
elec
tio
n
s
y
s
te
m
f
o
r
cl
ass
i
f
icatio
n
o
f
ce
r
v
ical
ca
n
ce
r
C
T
im
a
g
es
u
s
i
n
g
ar
ti
f
icial
b
ee
co
lo
n
y
al
g
o
r
ith
m
(
A
B
C
)
a
n
d
k
-
NN
clas
s
if
ier
;
an
d
ar
ti
f
icial
b
ee
co
lo
n
y
a
l
g
o
r
ith
m
w
i
th
SVM
class
i
f
ier
.
T
h
e
r
esu
lt
s
h
o
w
s
t
h
at
th
e
co
m
b
i
n
atio
n
o
f
A
B
C
w
it
h
SVM
g
av
e
b
etter
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
th
e
co
m
b
i
n
atio
n
o
f
A
B
C
w
it
h
K
-
NN
cla
s
s
i
f
ier
.
A
lla
m
et
al
.
[
31
]
m
e
n
tio
n
ed
th
e
i
m
p
o
r
ta
n
ce
o
f
a
u
to
m
a
ti
c
m
ed
ical
d
is
ea
s
e
d
ia
g
n
o
s
is
to
h
an
d
le
th
e
p
r
o
b
lem
s
ef
f
icie
n
tl
y
i
n
th
e
ea
r
ly
s
ta
g
es.
T
h
e
s
tu
d
y
al
s
o
d
is
cu
s
s
ed
v
ar
io
u
s
i
m
a
g
i
n
g
m
o
d
alities
f
o
r
ca
p
tu
r
in
g
th
e
i
m
a
g
es,
f
ea
t
u
r
e
e
x
tr
ac
tio
n
m
et
h
o
d
s
f
o
r
co
llecti
n
g
t
h
e
r
eq
u
ir
ed
attr
ib
u
te
s
,
an
d
f
ea
t
u
r
e
s
e
lectio
n
tec
h
n
iq
u
e
s
f
o
r
n
ec
es
s
ar
y
f
ea
tu
r
es l
ik
e
te
x
t
u
r
e,
an
d
co
lo
r
.
C
h
e
n
et
al
.
[
32
]
p
r
o
p
o
s
ed
a
co
ar
s
e
-
g
r
ain
ed
p
ar
allel
g
en
e
tic
alg
o
r
ith
m
(
C
GP
G
A
)
f
o
r
o
p
tim
izin
g
th
e
f
ea
tu
r
es
in
t
h
e
d
ataset
a
n
d
co
n
s
tr
ain
t
s
f
o
r
SVM.
T
h
e
y
also
p
r
o
p
o
s
ed
a
n
ew
f
it
n
es
s
f
u
n
ctio
n
w
h
ich
i
s
co
m
p
o
s
ed
o
f
clas
s
if
icatio
n
a
cc
u
r
ac
y
,
n
u
m
b
er
o
f
s
elec
ted
f
ea
t
u
r
es,
an
d
t
h
e
n
u
m
b
er
o
f
s
u
p
p
o
r
t
v
ec
to
r
s
to
o
p
tim
ize
g
e
n
er
aliza
tio
n
er
r
o
r
s
.
T
h
e
r
esu
lts
s
h
o
w
ed
th
at
th
e
p
er
f
o
r
m
an
ce
w
as
te
n
t
i
m
e
s
f
o
r
th
e
ac
cu
r
ac
y
,
s
ize
o
f
s
u
b
s
et
f
ea
t
u
r
es,
n
u
m
b
er
o
f
s
u
p
p
o
r
t v
ec
to
r
s
,
an
d
th
e
p
r
ac
tice
ti
m
e.
Sh
a
h
b
eig
e
t
a
l
.
[
33
]
p
r
o
p
o
s
ed
a
m
u
tated
f
u
zz
y
ad
ap
tiv
e
P
SO
co
m
b
i
n
ed
w
it
h
T
L
B
O
alg
o
r
ith
m
f
o
r
f
i
n
d
in
g
th
e
m
o
s
t
r
elev
a
n
t
an
d
l
ea
s
t
s
et
o
f
g
e
n
es
i
n
B
C
m
icr
o
a
r
r
ay
d
ata.
T
h
e
n
ee
d
to
r
e
d
u
ce
th
e
n
u
m
b
er
o
f
g
e
n
es
an
d
in
cr
ea
s
e
t
h
e
p
er
f
o
r
m
an
ce
l
ed
to
th
e
u
s
e
o
f
a
m
u
lti
-
o
b
j
ec
tiv
e
f
o
r
o
p
ti
m
izatio
n
p
r
o
b
lem
s
.
T
h
e
r
esu
lt sh
o
w
ed
th
e
m
o
d
el
to
ac
h
ie
v
e
an
ac
c
u
r
ac
y
o
f
9
1
.
8
8
%
w
it
h
SVM
cla
s
s
if
ier
.
J
u
n
g
et
al
.
[
34
]
p
r
esen
ted
a
m
eth
o
d
to
o
b
tain
ad
d
itio
n
al
n
u
m
er
ical
p
ar
a
m
ete
r
s
f
r
o
m
B
C
i
m
ag
e
d
ata
an
al
y
s
is
u
s
in
g
m
an
y
n
e
u
r
al
n
et
w
o
r
k
al
g
o
r
ith
m
s
to
e
x
p
lai
n
s
h
o
w
to
g
et
th
e
h
i
g
h
e
s
t
n
u
m
b
er
o
f
n
u
m
er
ical
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
3
,
J
u
n
e
2
0
2
0
:
1
6
8
8
-
1
6
9
4
1690
p
ar
am
eter
s
f
r
o
m
d
ata
o
f
B
C
i
m
a
g
e
a
n
d
m
ad
e
a
co
m
p
ar
i
s
o
n
b
et
w
ee
n
t
h
ese
a
lg
o
r
it
h
m
s
to
f
in
d
t
h
e
b
es
t
class
i
f
icatio
n
b
et
w
ee
n
b
en
i
g
n
an
d
m
a
li
g
n
an
t.
T
h
ein
et
al
.
[
35
]
p
r
o
p
o
s
ed
th
e
tr
ain
i
n
g
o
f
A
NN
u
s
in
g
t
h
e
i
s
la
n
d
-
b
ased
m
o
d
el
f
o
r
d
is
ti
n
g
u
i
s
h
i
n
g
d
if
f
er
e
n
t
t
y
p
e
s
o
f
B
C
w
it
h
b
et
ter
ac
cu
r
ac
y
an
d
r
ed
u
ce
d
tr
ain
in
g
ti
m
e
o
n
W
is
co
n
s
in
d
ia
g
n
o
s
tic
an
d
p
r
o
g
n
o
s
tic
b
r
ea
s
t
ca
n
ce
r
.
T
h
ey
p
r
o
p
o
s
ed
2
d
if
f
er
en
t m
i
g
r
atio
n
to
p
o
lo
g
i
es w
ith
r
a
n
d
o
m
-
r
an
d
o
m
p
o
lic
y
an
d
later
co
m
p
ar
ed
th
eir
r
es
u
lt
s
.
Fro
m
th
e
r
es
u
lts
,
th
e
to
r
u
s
to
p
o
lo
g
y
n
ee
d
ed
m
o
r
e
tr
ain
i
n
g
ti
m
e
co
m
p
ar
ed
to
t
h
e
r
an
d
o
m
to
p
o
lo
g
y
alth
o
u
g
h
it p
r
esen
ted
s
i
m
i
lar
s
o
lu
tio
n
p
er
f
o
r
m
a
n
ce
to
th
e
r
a
n
d
o
m
to
p
o
lo
g
y
.
T
h
a
w
k
ar
e
t
al
.
[
36
]
ex
p
lo
r
e
d
th
e
u
s
e
o
f
Fire
f
l
y
a
lg
o
r
it
h
m
to
s
e
lect
a
s
u
b
s
et
o
f
f
ea
t
u
r
es.
A
r
ti
f
i
cial
n
e
u
r
al
n
et
w
o
r
k
a
n
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
clas
s
if
ier
s
ar
e
e
m
p
l
o
y
ed
to
e
v
al
u
a
te
f
it
n
es
s
o
f
t
h
e
s
e
lecte
d
f
ea
tu
r
es.
Featu
r
es
s
elec
ted
b
y
Fire
f
l
y
a
l
g
o
r
ith
m
ar
e
u
s
ed
to
class
i
f
y
m
as
s
es
i
n
to
b
en
i
g
n
a
n
d
m
al
ig
n
an
t,
u
s
i
n
g
ar
tific
ial
n
eu
r
al
n
et
w
o
r
k
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
clas
s
i
f
ier
s
.
R
es
u
l
ts
s
h
o
w
th
at
Fire
f
l
y
al
g
o
r
ith
m
w
it
h
ar
tific
ial
n
e
u
r
al
n
et
w
o
r
k
i
s
s
u
p
er
io
r
to
Fire
f
l
y
alg
o
r
ith
m
w
it
h
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
in
e.
S
a
s
i
k
a
l
a
e
t
a
l
.
[
37
]
p
r
o
p
o
s
e
d
a
n
o
v
e
l
s
h
a
p
e
l
y
v
a
l
u
e
e
m
b
e
d
d
e
d
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
(
S
V
E
G
A
)
.
T
h
e
m
e
t
h
o
d
s
e
l
e
c
t
s
t
h
e
g
e
n
e
s
t
h
a
t
c
a
n
m
a
x
i
m
i
z
e
t
h
e
c
a
p
a
b
i
l
i
t
y
t
o
d
i
s
c
r
i
m
i
n
a
t
e
b
e
t
w
e
e
n
d
i
f
f
e
r
e
n
t
c
l
a
s
s
e
s
.
T
h
u
s
,
t
h
e
d
i
m
e
n
s
i
o
n
a
l
i
t
y
o
f
d
a
t
a
f
e
a
t
u
r
e
s
i
s
r
e
d
u
c
e
d
a
n
d
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
r
a
t
e
i
s
i
m
p
r
o
v
e
d
.
T
h
e
n
u
m
b
e
r
o
f
f
e
a
t
u
r
e
s
r
e
d
u
c
e
d
f
r
o
m
2
4
,
4
8
1
t
o
m
i
n
i
m
u
m
o
f
6
f
e
a
t
u
r
e
s
.
Srid
ev
an
d
M
u
r
u
g
a
n
[
29
]
p
r
e
s
en
ted
a
m
o
d
i
f
ied
co
r
r
elatio
n
r
o
u
g
h
s
et
f
ea
t
u
r
e
s
elec
t
io
n
(
MCR
SF
S)
.
I
t
is
co
m
p
o
s
ed
o
f
t
w
o
f
ea
tu
r
e
r
ed
u
ctio
n
alg
o
r
it
h
m
s
.
R
o
u
g
h
s
e
t
q
u
ick
r
ed
u
ct
alg
o
r
it
h
m
i
s
ap
p
lied
at
f
ir
s
t
to
o
b
tain
th
e
m
in
i
m
al
f
ea
t
u
r
e
s
u
b
s
et.
T
h
en
th
e
s
ec
o
n
d
alg
o
r
it
h
m
co
r
r
el
atio
n
f
ea
t
u
r
e
s
elec
t
io
n
(
C
F
S)
i
s
u
s
ed
to
d
o
f
u
r
t
h
er
r
ed
u
ctio
n
in
m
i
n
i
m
al
f
ea
tu
r
e
s
u
b
s
et.
T
h
e
MCR
SF
S
ac
h
ie
v
ed
h
ig
h
est
clas
s
i
f
icatio
n
ac
cu
r
ac
y
co
m
p
ar
ed
to
o
th
er
f
ea
t
u
r
e
s
elec
tio
n
m
et
h
o
d
s
.
Du
r
g
ala
k
s
h
m
i
a
n
d
Vij
ay
a
k
u
m
ar
[
3
8
]
p
r
o
p
o
s
ed
an
ef
f
icie
n
t
m
et
h
o
d
f
o
r
b
r
ea
s
t
ca
n
ce
r
d
etec
tio
n
b
ased
o
n
W
is
co
n
s
i
n
p
r
o
g
n
o
s
tic
b
r
ea
s
t
ca
n
ce
r
(
W
P
B
C
)
d
ata
s
et.
T
h
e
co
r
r
elatio
n
m
a
tr
ix
m
et
h
o
d
is
u
s
ed
f
o
r
f
ea
t
u
r
e
s
elec
tio
n
w
h
ic
h
r
e
m
o
v
e
t
h
e
in
s
i
g
n
if
ican
t
f
ea
t
u
r
es
f
r
o
m
th
e
m
a
s
s
i
v
e
a
m
o
u
n
t
o
f
d
ataset,
f
o
llo
w
ed
w
i
t
h
th
e
cla
s
s
i
f
icatio
n
al
g
o
r
ith
m
s
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
clas
s
i
f
i
ca
tio
n
,
lo
g
i
s
tic
r
e
g
r
ess
io
n
a
n
d
r
an
d
o
m
f
o
r
est
w
a
s
d
ep
lo
y
ed
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
im
p
r
o
v
es t
h
e
ac
cu
r
ac
y
[
3
,
4
,
7
-
12
,
15
-
18
,
20
-
22
,
24
-
26
,
3
9
,
40
]
.
3.
T
HE
P
RO
P
O
SE
D
AL
G
O
RI
T
H
M
AND
M
ACH
I
NE
L
E
ARNIN
G
T
E
Q
NI
Q
U
E
S
Featu
r
e
s
elec
tio
n
is
a
p
r
o
ce
s
s
o
f
o
p
tim
izi
n
g
in
d
iv
id
u
als
(
r
ec
o
r
d
s
)
b
y
ex
tr
ac
t
in
g
th
e
b
est
s
u
b
s
et
o
f
attr
ib
u
tes
f
r
o
m
s
u
c
h
r
ec
o
r
d
s
.
Du
r
in
g
f
ea
t
u
r
e
s
elec
tio
n
,
f
it
n
e
s
s
is
ass
e
s
s
ed
f
o
r
ea
ch
r
ec
o
r
d
in
ev
er
y
g
e
n
er
atio
n
w
h
ile
n
e
w
r
ec
o
r
d
s
ar
e
g
en
er
ated
to
estab
lis
h
t
h
e
p
o
p
u
lat
io
n
o
f
t
h
e
s
u
b
s
eq
u
e
n
t
g
e
n
er
atio
n
s
.
Af
ter
m
a
n
y
g
en
er
atio
n
s
,
th
e
co
m
p
o
n
e
n
ts
o
f
th
e
s
u
cc
e
s
s
i
v
e
g
e
n
er
atio
n
s
ar
e
b
etter
c
o
m
p
ar
ed
to
th
e
in
itial
p
o
p
u
latio
n
.
T
h
e
co
n
s
tr
u
ctio
n
o
f
a
d
ataset
o
f
o
p
ti
m
al
f
ea
tu
r
e
s
r
eq
u
ir
es
a
n
o
v
el
al
g
o
r
ith
m
.
T
h
e
tech
n
iq
u
e
p
r
o
p
o
s
ed
in
th
is
s
tu
d
y
h
as
t
w
o
p
h
ase
s
.
T
h
e
f
ir
s
t
p
h
ase
in
v
o
l
v
es
th
e
u
s
e
o
f
an
o
p
ti
m
izatio
n
s
ch
e
m
e
to
s
elec
t
th
e
b
est
s
et
o
f
f
ea
t
u
r
es
f
o
r
th
e
class
i
f
ica
tio
n
p
r
o
ce
s
s
.
T
h
en
,
in
th
e
s
ec
o
n
d
p
h
ase,
th
e
class
if
icatio
n
m
o
d
e
ls
ar
e
g
en
er
ated
f
o
r
th
e
ev
a
lu
atio
n
o
f
t
h
e
p
r
o
p
o
s
ed
in
ten
d
ed
s
c
h
e
m
e
o
n
B
C
d
atase
t
in
ter
m
s
o
f
its
p
er
f
o
r
m
a
n
ce
.
I
n
t
h
is
s
tu
d
y
,
a
m
u
lti
-
o
b
j
ec
tiv
e
T
L
B
O
o
p
tim
izatio
n
alg
o
r
ith
m
w
as
m
o
d
eled
w
ith
t
w
o
m
aj
o
r
o
b
j
ec
tiv
es
w
h
ich
ar
e
r
esu
lt
s
ac
cu
r
ac
y
m
a
x
i
m
izatio
n
an
d
m
in
i
m
izatio
n
o
f
th
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
s
u
c
h
th
at
th
er
e
w
ill
b
e
a
s
et
o
f
s
o
lu
tio
n
s
in
s
tead
o
f
j
u
s
t
o
n
e
s
o
lu
tio
n
.
T
h
e
p
r
o
j
ec
ted
m
o
d
el
is
co
m
p
r
is
e
d
o
f
th
e
T
L
B
O
an
d
L
R
f
o
r
s
u
b
s
et
f
ea
t
u
r
e
s
elec
tio
n
.
LR
-
b
ased
cla
s
s
i
f
icat
io
n
i
n
v
o
lv
es
th
e
esti
m
at
io
n
o
f
an
ev
e
n
t
s
’
o
cc
u
r
r
en
ce
p
r
o
b
ab
ilit
y
b
ased
o
n
th
e
s
i
m
ilar
it
y
o
f
g
iv
e
n
d
ata
p
o
in
ts
.
T
h
e
L
R
u
s
es
s
ig
m
o
id
f
u
n
ctio
n
to
d
eter
m
in
e
th
e
ev
e
n
t
s
’
o
cc
u
r
r
en
ce
p
r
o
b
ab
ilit
y
.
A
n
e
v
en
t
w
it
h
a
n
o
cc
u
r
r
en
ce
p
r
o
b
ab
ilit
y
o
f
>0
.
5
is
p
r
ed
icted
as
’
o
cc
u
r
r
ed
’
,
else,
as
‘
n
o
t
o
cc
u
r
r
ed
’
.
Fig
u
r
e
1
d
ep
icts
th
e
p
r
o
p
o
s
ed
m
o
d
el
w
h
ile
Fig
u
r
e
2
d
e
p
icts
th
e
T
L
B
O
alg
o
r
ith
m
.
T
h
r
ee
p
a
r
a
m
eter
s
i
n
h
er
it
f
r
o
m
g
e
n
etic
alg
o
r
ith
m
to
r
ep
r
esen
t a
n
d
u
p
d
ate
th
e
s
et
o
f
f
ea
t
u
r
es,
ea
ch
s
e
t o
f
f
ea
tu
r
es r
ep
r
esen
ted
in
a
ch
r
o
m
o
s
o
m
e.
Fig
u
r
e
1
.
T
h
e
p
r
o
j
ec
ted
f
ea
tu
r
e
s
elec
tio
n
m
o
d
el
b
ased
o
n
T
L
B
O
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
n
ew mo
d
el
fo
r
la
r
g
e
d
a
t
a
s
et
d
i
men
s
io
n
a
lity red
u
ctio
n
b
a
s
ed
o
n
…
(
Hin
d
R
a
a
d
I
b
r
a
h
ee
m
)
1691
Fig
u
r
e
2
.
T
h
e
T
L
B
O
A
l
g
o
r
ith
m
E
ac
h
g
e
n
i
n
th
e
c
h
r
o
m
o
s
r
ep
r
esen
t
o
n
e
f
ea
t
u
r
e,
if
t
h
e
v
alu
e
o
f
th
e
g
en
1
t
h
e
f
ea
t
u
r
e
is
s
ele
cted
an
d
0
r
ep
r
esen
t
u
n
s
elec
ted
f
ea
t
u
r
e,
as
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
T
o
u
p
d
ates
th
e
v
al
u
e
o
f
ea
ch
g
e
n
(
f
ea
t
u
r
es)
f
r
o
m
s
elec
ted
to
u
n
s
elec
ted
o
r
Vis
v
er
s
a,
cr
o
s
s
o
v
er
b
et
w
ee
n
t
w
o
ch
r
o
m
o
s
o
m
e
an
d
t
h
e
n
m
u
tatio
n
is
u
s
ed
t
o
g
et
n
e
w
s
u
b
s
e
t
o
f
f
ea
t
u
r
es
(
ch
r
o
m
o
s
o
m
e)
as s
h
o
w
n
i
n
Fi
g
u
r
e
4.
T
h
e
p
ar
am
eter
s
u
s
ed
i
n
th
is
al
g
o
r
ith
m
s
h
o
w
n
in
T
ab
le
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
3
,
J
u
n
e
2
0
2
0
:
1
6
8
8
-
1
6
9
4
1692
Fig
u
r
e
3
.
S
tr
u
ct
u
r
e
o
f
th
e
c
h
r
o
m
o
s
o
m
e
C
h
r
o
m
o
s
o
m
e
1
1
1
0
0
0
1
0
1
C
h
r
o
m
o
s
o
m
e
2
1
1
1
0
0
0
0
1
C
r
o
s
s
o
v
er
Ne
w
C
h
r
o
m
o
s
o
m
e
1
1
1
0
0
1
0
1
Mu
tatio
n
Ne
w
C
h
r
o
m
o
s
o
m
e
1
1
1
0
1
0
0
1
Fig
u
r
e
4
.
C
r
o
s
s
o
v
er
an
d
m
u
ta
t
io
n
o
p
er
atio
n
s
T
ab
le
1
.
T
he
P
a
r
am
eter
s
o
f
al
g
o
r
ith
m
P
a
r
a
me
t
e
r
V
a
l
u
e
P
o
p
u
l
a
t
i
o
n
s
i
z
e
20
N
u
mb
e
r
o
f
g
e
n
e
r
a
t
i
o
n
40
C
r
o
d
d
o
v
e
r
t
y
p
e
H
a
l
f
-
u
n
i
f
o
r
m
M
u
t
a
t
i
o
n
t
y
p
e
Bit
-
f
l
i
p
4.
R
E
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
e
r
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
al
g
o
r
ith
m
ar
e
s
h
o
w
n
in
T
ab
le
2
.
T
h
e
r
esu
lts
s
h
o
w
ed
ea
ch
s
et
o
f
f
ea
tu
r
e
s
an
d
th
e
ac
cu
r
ac
y
.
Stati
s
tical
test
s
w
er
e
p
er
f
o
r
m
ed
o
n
t
h
e
r
esu
lt
to
v
er
i
f
y
th
e
r
es
u
lt
s
.
T
ab
l
e
3
s
h
o
w
ed
th
e
co
n
f
u
s
io
n
m
atr
i
x
.
B
ased
o
n
th
e
co
n
f
u
s
io
n
m
atr
i
x
,
w
e
ca
n
ca
l
cu
late
t
h
e
d
etec
tio
n
r
ate
u
s
in
g
(
1
)
.
Dete
ctio
n
r
ate
=
+
(
1
)
=
444
444
+
0
=
1
.
0
0
T
h
e
co
m
p
ar
is
o
n
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
n
th
is
s
tu
d
y
w
it
h
P
C
A
a
n
d
Fi
n
e
tr
ee
b
u
ilt
i
n
M
A
T
L
A
B
as
s
h
o
w
n
i
n
T
ab
le
4
r
ev
ea
led
th
e
s
u
p
er
io
r
it
y
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
o
v
er
t
h
e
b
en
c
h
m
ar
k
ed
s
ch
e
m
e
s
.
T
ab
le
2
.
R
esu
lts
f
o
r
ea
ch
s
et
o
f
f
ea
t
u
r
es
N
o
.
F
e
a
t
u
r
e
s
A
c
c
u
r
a
c
y
1
0
.
9
7
2
0
.
9
9
3
1
.
0
0
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
P
r
e
d
i
c
a
t
e
d
m
a
l
i
g
n
a
n
t
P
r
e
d
i
c
a
t
e
d
B
e
n
i
g
n
A
c
t
u
a
l
mal
i
g
n
a
n
t
4
4
4
0
A
c
t
u
a
l
B
e
n
i
g
n
0
2
3
9
T
ab
le
4
.
Co
m
p
ar
is
io
n
tab
le
N
o
.
f
e
a
t
u
r
e
s
O
u
r
M
o
d
e
l
P
C
A
+
F
i
n
e
T
r
e
e
1
0
.
9
7
6
2
.
1
2
0
.
9
9
9
5
.
6
3
1
.
0
0
9
6
.
5
1
0
1
0
0
0
0
0
1
0
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
n
ew mo
d
el
fo
r
la
r
g
e
d
a
t
a
s
et
d
i
men
s
io
n
a
lity red
u
ctio
n
b
a
s
ed
o
n
…
(
Hin
d
R
a
a
d
I
b
r
a
h
ee
m
)
1693
5.
CO
NCLU
SI
O
N
T
h
i
s
s
tu
d
y
p
r
es
en
t
e
d
a
m
u
l
ti
-
o
b
je
c
t
i
v
e
T
L
B
O
al
g
o
r
i
th
m
f
o
r
s
o
l
v
in
g
o
p
tim
a
l
f
e
a
tu
r
e
s
e
le
c
t
i
o
n
p
r
o
b
l
em
s
.
A
c
c
u
r
a
cy
is
m
o
s
t
im
p
o
r
t
an
t
i
n
t
h
e
f
i
e
l
d
o
f
m
e
d
i
c
al
d
i
ag
n
o
s
i
s
to
d
i
a
g
n
o
s
e
th
e
p
a
t
ie
n
t’
s
d
i
s
e
a
s
e
.
T
h
e
o
b
je
c
t
iv
e
o
f
t
h
is
a
lg
o
r
i
th
m
is
t
o
s
e
l
e
c
t
m
in
im
u
m
n
u
m
b
e
r
o
f
f
e
a
tu
r
es
p
r
o
v
id
i
n
g
h
ig
h
c
l
ass
if
i
c
at
i
o
n
a
c
c
u
r
ac
y
.
T
h
e
r
e
s
u
l
ts
f
r
o
m
t
h
e
in
v
e
s
t
ig
a
ti
o
n
s
s
h
o
w
e
d
th
a
t
t
h
e
p
r
o
p
o
s
e
d
T
L
B
O
-
b
as
e
d
f
e
atu
r
e
o
p
tim
i
z
at
i
o
n
s
y
s
t
em
c
an
im
p
r
o
v
e
th
e
a
c
cu
r
a
cy
o
f
cl
a
s
s
if
ie
r
s
c
o
m
p
a
r
e
d
t
o
p
r
ev
i
o
u
s
m
e
th
o
d
s
o
n
B
C
d
a
t
as
e
t
.
T
h
e
cl
as
s
if
i
c
a
ti
o
n
m
o
d
el
w
as
t
r
ai
n
e
d
w
i
th
a
r
e
d
u
c
e
d
n
u
m
b
e
r
o
f
f
ea
tu
r
e
s
.
Ou
r
f
u
t
u
r
e
s
tu
d
i
es
w
il
l
f
o
cu
s
o
n
w
o
r
k
in
g
w
ith
a
n
ew
h
y
b
r
i
d
a
lg
o
r
it
h
m
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
W
a
n
g
,
R.
V
.
Ra
o
,
P
.
C
h
e
n
,
Y.
Zh
a
n
g
,
A
.
L
iu
,
a
n
d
L
.
W
e
i,
"
A
b
n
o
rm
a
l
b
re
a
st
d
e
tec
ti
o
n
in
m
a
m
m
o
g
ra
m
im
a
g
e
s
b
y
f
e
e
d
-
f
o
r
w
a
rd
n
e
u
ra
l
n
e
tw
o
rk
train
e
d
b
y
Ja
y
a
a
lg
o
rit
h
m
,
"
Fu
n
d
a
me
n
t
a
In
f
o
rm
a
ti
c
a
e
,
v
o
l.
1
5
1
,
No
.
1
-
4
,
p
p
.
1
9
1
-
2
1
1
,
2
0
1
7
.
[2
]
F
.
G
a
o
,
T
.
W
u
,
J.
L
i,
B.
Zh
e
n
g
,
L
.
Ru
a
n
,
D.
S
h
a
n
g
,
e
t
a
l.
,
"
S
D
-
CNN
:
A
sh
a
ll
o
w
-
d
e
e
p
CNN
f
o
r
im
p
ro
v
e
d
b
re
a
st
c
a
n
c
e
r
d
iag
n
o
sis,"
C
o
mp
u
ter
ize
d
M
e
d
ica
l
Ima
g
in
g
a
n
d
Gr
a
p
h
ics
,
v
o
l.
7
0
,
p
p
.
5
3
-
6
2
,
De
c
e
m
b
e
r
2
0
1
8
.
[3
]
M
.
A
.
A
h
m
e
d
,
R.
A
.
Ha
sa
n
,
A
.
H.
A
li
,
a
n
d
M
.
A
.
M
o
h
a
m
m
e
d
,
"
T
h
e
c
l
a
ss
i
f
ica
ti
o
n
o
f
th
e
m
o
d
e
rn
a
ra
b
ic
p
o
e
try
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
,
"
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
i
c
s
a
n
d
Co
n
tr
o
l
,
v
o
l.
1
7
,
No
.
5
,
p
p
.
2
6
6
7
-
2
6
7
4
,
2
0
1
9
.
[4
]
A
.
H.
A
li
a
n
d
M
a
h
m
o
o
d
Zak
i
A
b
d
u
ll
a
h
,
"
A
S
u
rv
e
y
o
n
V
e
rti
c
a
l
a
n
d
Ho
rizo
n
tal
S
c
a
li
n
g
P
latf
o
r
m
s
f
o
r
Big
Da
ta
A
n
a
l
y
ti
c
s,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
teg
ra
ted
En
g
i
n
e
e
rin
g
,
v
o
l.
1
1
,
No
.
6
,
p
p
.
1
3
8
-
1
5
0
,
2
0
1
9
.
[5
]
M.
A
.
M
o
h
a
m
m
e
d
,
B.
A
l
-
Kh
a
tee
b
,
A
.
N.
Ra
sh
id
,
D.
A
.
Ib
ra
h
im
,
M
.
K.
A
.
G
h
a
n
i,
a
n
d
S
.
A
.
M
o
sta
f
a
,
"
Ne
u
ra
l
n
e
tw
o
rk
a
n
d
m
u
lt
i
-
f
ra
c
tal
d
im
e
n
sio
n
f
e
a
tu
r
e
s
f
o
r
b
re
a
st
c
a
n
c
e
r
c
las
sif
ica
ti
o
n
f
ro
m
u
lt
ra
so
u
n
d
im
a
g
e
s,"
Co
mp
u
te
rs
&
El
e
c
trica
l
En
g
i
n
e
e
rin
g
,
v
o
l.
7
0
,
p
p
.
8
7
1
-
8
8
2
,
A
u
g
u
st
2
0
1
8
.
[6
]
J.
H.
W
a
n
g
,
J.
H.
Jia
n
g
,
a
n
d
R
.
Q.
Yu
,
"
Ro
b
u
st
b
a
c
k
p
ro
p
a
g
a
ti
o
n
a
lg
o
rit
h
m
a
s
a
c
h
e
m
o
m
e
tri
c
to
o
l
to
p
re
v
e
n
t
th
e
o
v
e
rf
it
ti
n
g
to
o
u
tl
iers
,
"
Ch
e
mo
me
trics
a
n
d
i
n
telli
g
e
n
t
la
b
o
r
a
to
ry
sy
ste
ms
,
v
o
l.
3
4
,
No
.
1
,
p
p
.
1
0
9
-
1
1
5
,
A
u
g
.
1
9
9
6
.
[7
]
A
.
H.
A
li
a
n
d
M
.
Z.
A
b
d
u
ll
a
h
,
"
Re
c
e
n
t
tren
d
s
in
d
istri
b
u
te
d
o
n
li
n
e
stre
a
m
p
ro
c
e
ss
in
g
p
lat
f
o
rm
f
o
r
b
ig
d
a
ta:
S
u
rv
e
y
,
"
2
0
1
8
1
st A
n
n
u
a
l
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
fo
rm
a
ti
o
n
a
n
d
S
c
ie
n
c
e
s (
Ai
CIS
)
,
p
p
.
1
4
0
-
1
4
5
,
20
18
.
[8
]
A
.
H.
A
li
a
n
d
M
.
Z.
A
b
d
u
ll
a
h
,
"
A
n
o
v
e
l
a
p
p
ro
a
c
h
f
o
r
b
ig
d
a
ta cla
ss
if
ica
ti
o
n
b
a
se
d
o
n
h
y
b
rid
p
a
ra
ll
e
l
d
im
e
n
sio
n
a
li
ty
re
d
u
c
ti
o
n
u
si
n
g
sp
a
rk
c
lu
ste
r,
"
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
2
0
,
n
o
.
4
,
p
p
.
4
1
3
-
4
3
1
,
2
0
1
9
.
[9
]
M
.
A
.
H.
A
li
,
"
A
n
Ef
f
ici
e
n
t
M
o
d
e
l
f
o
r
Da
ta
Clas
sif
ica
ti
o
n
Ba
se
d
o
n
S
V
M
G
rid
P
a
ra
m
e
ter
Op
ti
m
iz
a
ti
o
n
a
n
d
P
S
O
F
e
a
tu
re
W
e
ig
h
t
S
e
lec
ti
o
n
,
"
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
2
,
n
o
.
1
,
p
p
.
1
-
1
2
,
2
0
1
8
.
[1
0
]
N.
Q.
M
o
h
a
m
m
e
d
,
M
.
S
.
A
h
m
e
d
,
M
.
A
.
M
o
h
a
m
m
e
d
,
O.
A
.
H
a
m
m
o
o
d
,
H.
A
.
N.
A
lsh
a
ra
,
a
n
d
A
.
A
.
Ka
m
il
,
"
Co
m
p
a
r
a
ti
v
e
A
n
a
l
y
sis
b
e
t
w
e
e
n
S
o
lar
a
n
d
W
in
d
T
u
r
b
in
e
E
n
e
rg
y
S
o
u
rc
e
s
in
I
o
T
Ba
se
d
o
n
Ec
o
n
o
m
ica
l
a
n
d
Ef
f
icie
n
c
y
Co
n
sid
e
ra
ti
o
n
s,"
2
0
1
9
2
2
n
d
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
n
tro
l
S
y
ste
ms
a
n
d
Co
mp
u
ter
S
c
ien
c
e
(
CS
CS
)
,
p
p
.
4
4
8
-
4
5
2
,
2
0
1
9
.
[1
1
]
Z.
H.
S
a
li
h
,
G
.
T
.
Ha
sa
n
,
a
n
d
M
.
A
.
M
o
h
a
m
m
e
d
,
"
In
v
e
stig
a
te
a
n
d
a
n
a
ly
z
e
th
e
lev
e
ls
o
f
e
lec
tro
m
a
g
n
e
ti
c
ra
d
iati
o
n
s
e
m
it
ted
f
ro
m
u
n
d
e
rg
ro
u
n
d
p
o
w
e
r
c
a
b
les
e
x
ten
d
e
d
i
n
m
o
d
e
rn
c
it
ies
,
"
2
0
1
7
9
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
tro
n
ics
,
Co
m
p
u
ter
s a
n
d
Arti
fi
c
ia
l
In
tell
ig
e
n
c
e
(
ECA
I)
,
p
p
.
1
-
4
,
2
0
1
7
.
[1
2
]
Z.
H.
S
a
li
h
,
G
.
T
.
Ha
sa
n
,
M
.
A
.
M
o
h
a
m
m
e
d
,
M
.
A
.
S
.
Kli
b
,
A
.
H.
A
li
,
a
n
d
R.
A
.
Ib
ra
h
im
,
"
S
tu
d
y
th
e
Eff
e
c
t
o
f
In
teg
ra
ti
n
g
th
e
S
o
lar
E
n
e
rg
y
S
o
u
rc
e
o
n
S
tab
il
it
y
o
f
El
e
c
tri
c
a
l
Distrib
u
ti
o
n
S
y
ste
m
,
"
2
0
1
9
2
2
n
d
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
n
tro
l
S
y
ste
ms
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
(
CS
CS
)
,
p
p
.
4
4
3
-
4
4
7
,
2
0
1
9
.
[1
3
]
K.
Hu
b
e
r
-
Ke
e
n
e
r,
"
Be
y
o
n
d
BRCA
:
C
a
n
c
e
r
Risk
As
se
ss
m
e
n
t
i
n
th
e
Era
o
f
P
a
n
e
l
G
e
n
e
ti
c
Tes
ti
n
g
,
"
M
ich
ig
a
n
M
e
d
icin
e
-
Un
ive
rs
it
y
o
f
M
ich
ig
a
n
,
p
p
.
1
-
5
3
,
2
0
1
8
.
[1
4
]
S
.
V
a
n
a
ja
a
n
d
K.
Ra
m
e
sh
Ku
m
a
r,
"
A
n
a
l
y
sis
o
f
f
e
a
tu
re
se
le
c
ti
o
n
a
lg
o
rit
h
m
s
o
n
c
las
sif
ica
ti
o
n
:
a
su
rv
e
y
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
A
p
p
l
ica
ti
o
n
s,
v
o
l.
9
6
,
N
o
.
1
7
,
p
p
.
2
8
-
3
5
,
Ju
n
e
2
0
1
4
.
[1
5
]
R.
A
.
Ha
sa
n
,
I.
A
lh
a
y
a
li
,
A
.
Ro
y
i
d
a
,
N.
D.
Zak
i,
a
n
d
A
.
H.
A
li
,
"
A
n
a
d
a
p
ti
v
e
c
lu
ste
rin
g
a
n
d
c
las
sif
ic
a
ti
o
n
a
lg
o
rit
h
m
f
o
r
Tw
it
ter
d
a
ta
stre
a
m
in
g
in
Ap
a
c
h
e
S
p
a
rk
,
"
T
EL
KOM
N
IKA
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
m
p
u
t
in
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l.
1
7
,
N
o
.
6
,
p
p
.
3
0
8
6
-
3
0
9
9
,
De
c
e
m
b
e
r
2
0
1
9
.
[1
6
]
R.
A
.
Ha
sa
n
,
M
.
A
.
M
o
h
a
m
m
e
d
,
Z.
H.
S
a
li
h
,
M
.
A
.
B.
A
m
e
e
d
e
e
n
,
N.
Ţ
ă
p
u
ş,
a
n
d
M
.
N.
M
o
h
a
m
m
e
d
,
"
HSO:
A
H
y
b
rid
S
w
a
r
m
Op
ti
m
iza
ti
o
n
A
lg
o
rit
h
m
f
o
r
Re
d
u
c
in
g
En
e
rg
y
Co
n
su
m
p
ti
o
n
in
th
e
Clo
u
d
lets,"
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
E
lec
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
o
l
.
1
6
,
N
o
.
5
,
p
p
.
2
1
4
4
-
2
1
5
4
,
Oc
to
b
e
r
2
0
1
8
.
[1
7
]
R.
A
.
Ha
sa
n
,
M
.
A
.
M
o
h
a
m
m
e
d
,
N.
Ţ
ă
p
u
ş,
a
n
d
O.
A
.
Ha
m
m
o
o
d
,
"
A
c
o
m
p
re
h
e
n
siv
e
stu
d
y
:
A
n
t
Co
lo
n
y
Op
ti
m
iz
a
ti
o
n
(A
CO)
f
o
r
f
a
c
il
it
y
la
y
o
u
t
p
ro
b
le
m
,
"
2
0
1
7
1
6
th
R
o
E
d
u
Ne
t
Co
n
fe
re
n
c
e
:
Ne
two
rk
in
g
in
Ed
u
c
a
ti
o
n
a
n
d
Res
e
a
rc
h
(
Ro
Ed
u
Ne
t)
,
p
p
.
1
-
8
,
2
0
1
7
.
[1
8
]
Z.
F
.
H
u
ss
a
in
,
H.
R.
Ib
ra
h
e
e
m
,
M
.
A
lsa
jri
,
A
.
Hu
ss
e
in
A
li
,
M
.
A
.
Is
m
a
il
,
S
.
Ka
sim
,
e
t
a
l.
,
"
A
n
e
w
m
o
d
e
l
f
o
r
iri
s
d
a
ta
se
t
c
las
si
f
ica
ti
o
n
b
a
se
d
o
n
li
n
e
a
r
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
p
a
ra
m
e
ter'
s
o
p
ti
m
iz
a
ti
o
n
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
&
Co
mp
u
ter
En
g
in
e
e
ri
n
g
(
2
0
8
8
-
8
7
0
8
)
,
v
o
l.
1
0
,
No
.
1
,
p
p
.
1
0
7
9
-
1
0
8
4
,
F
e
b
r
u
a
ry
2020.
[1
9
]
R.
V.
Ra
o
,
V
.
J
.
S
a
v
sa
n
i
,
a
n
d
D
.
V
a
k
h
a
ria,
"
T
e
a
c
h
in
g
–
lea
rn
in
g
-
b
a
se
d
o
p
ti
m
iza
ti
o
n
:
a
n
o
v
e
l
m
e
th
o
d
f
o
r
c
o
n
stra
in
e
d
m
e
c
h
a
n
ica
l
d
e
sig
n
o
p
t
im
iza
ti
o
n
p
ro
b
lem
s,"
Co
mp
u
ter
-
Ai
d
e
d
De
sig
n
,
v
o
l.
4
3
,
No
.
3
,
p
p
.
3
0
3
-
3
1
5
,
M
a
rc
h
2
0
1
1
.
[2
0
]
M
.
A
.
M
o
h
a
m
m
e
d
a
n
d
R.
A
.
Ha
s
a
n
,
"
P
a
rti
c
le
sw
a
r
m
o
p
ti
m
iza
ti
o
n
f
o
r
f
a
c
il
it
y
la
y
o
u
t
p
ro
b
lem
s
F
L
P
-
A
c
o
m
p
re
h
e
n
siv
e
stu
d
y
,
"
in
2
0
1
7
1
3
t
h
IEE
E
In
te
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
telli
g
e
n
t
Co
mp
u
ter
Co
mm
u
n
ica
ti
o
n
a
n
d
Pr
o
c
e
ss
in
g
(
ICCP)
,
p
p
.
9
3
-
99
,
2
0
1
7
.
[2
1
]
M
.
A
.
M
o
h
a
m
m
e
d
,
R.
A
.
Ha
s
a
n
,
M
.
A
.
A
h
m
e
d
,
N.
T
a
p
u
s,
M
.
A
.
S
h
a
n
a
n
,
M
.
K.
Kh
a
lee
l
,
e
t
a
l.
,
"
A
F
o
c
a
l
lo
a
d
b
a
lan
c
e
r
b
a
se
d
a
lg
o
rit
h
m
f
o
r
tas
k
a
ss
i
g
n
m
e
n
t
in
c
lo
u
d
e
n
v
ir
o
n
m
e
n
t,
"
in
2
0
1
8
1
0
t
h
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
tro
n
ics
,
Co
mp
u
ter
s
a
n
d
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
(
ECA
I)
,
p
p
.
1
-
4
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
3
,
J
u
n
e
2
0
2
0
:
1
6
8
8
-
1
6
9
4
1694
[2
2
]
M
.
A
.
M
o
h
a
m
m
e
d
,
A
.
A
.
Ka
m
il
,
R.
A
.
Ha
sa
n
,
a
n
d
N.
T
a
p
u
s,
"
A
n
Eff
e
c
ti
v
e
Co
n
tex
t
S
e
n
siti
v
e
Of
f
lo
a
d
in
g
S
y
ste
m
f
o
r
M
o
b
i
le
Cl
o
u
d
E
n
v
iro
n
m
e
n
ts
u
sin
g
S
u
p
p
o
rt
V
a
lu
e
-
b
a
se
d
Clas
sif
ica
ti
o
n
,
"
S
c
a
l
a
b
le
Co
m
p
u
ti
n
g
:
Pra
c
ti
c
e
a
n
d
Exp
e
rie
n
c
e
,
v
o
l.
2
0
,
N
o
.
4
,
p
p
.
6
8
7
-
6
9
8
,
De
c
e
m
b
e
r
2
0
1
9
.
[2
3
]
T
.
Do
k
e
ro
g
lu
,
"
H
y
b
rid
tea
c
h
in
g
–
lea
rn
in
g
-
b
a
se
d
o
p
ti
m
iza
ti
o
n
a
lg
o
rit
h
m
s
f
o
r
th
e
q
u
a
d
ra
ti
c
a
ss
ig
n
m
e
n
t
p
ro
b
lem
,
"
Co
mp
u
ter
s &
In
d
u
stria
l
E
n
g
in
e
e
rin
g
,
v
o
l.
8
5
,
p
p
.
8
6
-
1
0
1
,
J
u
ly
2
0
1
5
.
[2
4
]
M
.
A
.
M
o
h
a
m
m
e
d
,
I.
A
.
M
o
h
a
m
m
e
d
,
R.
A
.
Ha
sa
n
,
N
.
Ţ
ă
p
u
ş,
A
.
H.
A
li
,
a
n
d
O.
A
.
Ha
m
m
o
o
d
,
"
G
r
e
e
n
En
e
rg
y
S
o
u
rc
e
s:
Iss
u
e
s
a
n
d
Ch
a
ll
e
n
g
e
s,"
in
2
0
1
9
1
8
t
h
R
o
E
d
u
Ne
t
Co
n
fer
e
n
c
e
:
Ne
two
rk
in
g
in
E
d
u
c
a
ti
o
n
a
n
d
Res
e
a
rc
h
(
Ro
Ed
u
Ne
t
)
,
p
p
.
1
-
8
,
2
0
1
9
.
[2
5
]
M
.
A
.
M
o
h
a
m
m
e
d
,
Z.
H.
S
a
li
h
,
N
.
Ţ
ă
p
u
ş,
a
n
d
R
.
A
.
K.
Ha
sa
n
,
"
S
e
c
u
rit
y
a
n
d
a
c
c
o
u
n
ta
b
il
it
y
f
o
r
sh
a
rin
g
th
e
d
a
ta
sto
re
d
in
t
h
e
c
lo
u
d
,
"
in
2
0
1
6
1
5
t
h
Ro
Ed
u
Ne
t
Co
n
fer
e
n
c
e
:
Ne
two
rk
in
g
in
Ed
u
c
a
ti
o
n
a
n
d
Res
e
a
rc
h
,
p
p
.
1
-
5
,
2
0
1
6
.
[2
6
]
M
.
A
.
M
o
h
a
m
m
e
d
a
n
d
N.
Ţ
ă
p
u
ş
,
"
A
No
v
e
l
A
p
p
ro
a
c
h
o
f
Re
d
u
c
i
n
g
En
e
rg
y
Co
n
su
m
p
ti
o
n
b
y
Util
izin
g
En
t
h
a
lp
y
in
M
o
b
i
le Cl
o
u
d
C
o
m
p
u
ti
n
g
,
"
S
t
u
d
i
e
s in
In
f
o
rm
a
ti
c
s
a
n
d
Co
n
tro
l
,
v
o
l
.
2
6
,
n
o
.
4
,
p
p
.
4
2
5
-
4
3
4
,
De
c
e
m
b
e
r
2
0
1
7
.
[2
7
]
L.
-
Y.
Ch
u
a
n
g
,
S
.
-
W
.
T
sa
i,
a
n
d
C
.
-
H.
Ya
n
g
,
"
Im
p
ro
v
e
d
b
i
n
a
ry
p
a
rti
c
le
sw
a
r
m
o
p
ti
m
iz
a
ti
o
n
u
sin
g
c
a
tf
ish
e
ff
e
c
t
f
o
r
f
e
a
tu
re
se
lec
ti
o
n
,
"
Exp
e
rt S
y
ste
ms
wit
h
A
p
p
li
c
a
ti
o
n
s,
v
o
l.
3
8
,
No
.
1
0
,
p
p
.
1
2
6
9
9
-
1
2
7
0
7
,
S
e
p
tem
b
e
r
2
0
1
1
.
[2
8
]
S
.
Ba
h
a
ss
in
e
,
A
.
M
a
d
a
n
i,
M
.
A
l
-
S
a
re
m
,
a
n
d
M
.
Kiss
i,
"
F
e
a
tu
re
se
lec
ti
o
n
u
sin
g
a
n
im
p
ro
v
e
d
Ch
i
-
sq
u
a
re
f
o
r
A
ra
b
ic
te
x
t
c
las
si
f
ic
a
ti
o
n
,
"
J
o
u
rn
a
l
o
f
K
in
g
S
a
u
d
Un
ive
rs
it
y
-
Co
mp
u
ter
a
n
d
I
n
fo
rm
a
ti
o
n
S
c
ien
c
e
s,
v
o
l.
3
2
,
n
o
.
2
,
p
p
.
2
2
5
-
2
3
1
,
F
e
b
ru
a
ry
2
0
1
8
.
[2
9
]
T
.
S
rid
e
v
i
a
n
d
A
.
M
u
r
u
g
a
n
,
"
A
n
o
v
e
l
f
e
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
f
o
r
e
ffe
c
ti
v
e
b
re
a
st
c
a
n
c
e
r
d
iag
n
o
sis
a
n
d
p
r
o
g
n
o
sis,"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
Ap
p
l
ica
ti
o
n
s,
v
o
l.
8
8
,
No
.
1
1
,
p
p
.
2
8
-
3
3
,
Ja
n
u
a
ry
2
0
1
4
.
[3
0
]
V
.
A
g
ra
w
a
l
a
n
d
S
.
Ch
a
n
d
ra
,
"
F
e
a
tu
re
se
lec
ti
o
n
u
si
n
g
A
rti
f
ici
a
l
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
,
"
in
2
0
1
5
E
ig
h
th
In
t
e
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
n
tem
p
o
ra
ry
C
o
mp
u
ti
n
g
(
IC3
)
,
p
p
.
1
7
1
-
1
7
6
,
2
0
1
5
.
[3
1
]
M
.
A
ll
a
m
a
n
d
M
.
Na
n
d
h
i
n
i,
"
A
S
tu
d
y
o
n
O
p
ti
m
iza
ti
o
n
T
e
c
h
n
iq
u
e
s
i
n
F
e
a
tu
re
S
e
lec
ti
o
n
f
o
r
M
e
d
ica
l
I
m
a
g
e
A
n
a
l
y
sis,
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
n
Co
mp
u
t
e
r S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
(
IJ
CS
E)
,
V
o
.
9
,
No
.
3
,
p
p
.
7
5
-
8
2
,
M
a
rc
h
2
0
1
7
.
[3
2
]
Z.
Ch
e
n
,
T
.
L
in
,
N.
T
a
n
g
,
a
n
d
X
.
X
ia,
"
A
p
a
ra
ll
e
l
g
e
n
e
ti
c
a
l
g
o
rit
h
m
b
a
se
d
fe
a
tu
re
se
lec
ti
o
n
a
n
d
p
a
ra
m
e
ter
o
p
ti
m
iza
ti
o
n
f
o
r
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
,
"
S
c
ien
ti
fi
c
Pro
g
r
a
mm
in
g
,
v
o
l.
2
0
1
6
,
No
.
2
,
p
p
.
1
-
1
0
,
Ja
n
u
a
r
y
2016.
[3
3
]
S
.
S
h
a
h
b
e
ig
,
M
.
S
.
He
lf
ro
u
sh
,
a
n
d
A
.
Ra
h
id
e
h
,
"
A
f
u
z
z
y
m
u
l
ti
-
o
b
jec
ti
v
e
h
y
b
rid
T
lb
o
-
P
s
o
a
p
p
r
o
a
c
h
to
se
lec
t
th
e
a
ss
o
c
iate
d
g
e
n
e
s
w
it
h
b
re
a
st ca
n
c
e
r,
"
S
ig
n
a
l
Pr
o
c
e
ss
in
g
,
v
o
l.
1
3
1
,
p
p
.
5
8
-
6
5
,
F
e
b
ru
a
ry
20
1
7
.
[3
4
]
I.
-
S
.
Ju
n
g
,
D.
T
h
a
p
a
,
a
n
d
G
.
-
N.
W
a
n
g
,
"
Ne
u
ra
l
n
e
tw
o
rk
b
a
se
d
a
l
g
o
rit
h
m
s
f
o
r
d
iag
n
o
sis
a
n
d
c
las
sif
ica
ti
o
n
o
f
b
re
a
st
c
a
n
c
e
r
tu
m
o
r,
"
in
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
m
p
u
t
a
ti
o
n
a
l
a
n
d
In
fo
rm
a
t
io
n
S
c
ien
c
e
,
p
p
.
1
0
7
-
1
1
4
,
2
0
0
5
.
[3
5
]
H.
T
.
T
.
T
h
e
in
a
n
d
K.
M
.
M
.
T
u
n
,
"
A
n
a
p
p
ro
a
c
h
f
o
r
b
re
a
st
c
a
n
c
e
r
d
iag
n
o
sis
c
las
sif
ica
ti
o
n
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
,
"
Ad
v
a
n
c
e
d
Co
mp
u
ti
n
g
:
An
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
(
ACIJ),
Vo
l.
6
,
n
o.
1,
p
p
.
1
-
11,
Ja
n
u
a
ry
2
0
1
5
.
[3
6
]
S
.
T
h
a
w
k
a
r
a
n
d
R.
In
g
o
li
k
a
r,
"
Cl
a
ss
if
i
c
a
ti
o
n
o
f
M
a
ss
e
s in
Dig
it
a
l
M
a
m
m
o
g
ra
m
s Us
in
g
F
iref
l
y
b
a
se
d
Op
ti
m
iza
ti
o
n
,
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Im
a
g
e
,
G
ra
p
h
ics
&
S
ig
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
2
5
-
3
3
,
F
e
b
ru
a
ry
2
0
1
8
.
[3
7
]
S
.
S
a
sik
a
la,
S
.
A
.
a
li
a
s
Ba
la
m
u
ru
g
a
n
,
a
n
d
S
.
G
e
e
th
a
,
"
A
n
o
v
e
l
f
e
a
tu
re
se
lec
ti
o
n
tec
h
n
i
q
u
e
f
o
r
im
p
ro
v
e
d
su
rv
iv
a
b
il
it
y
d
iag
n
o
sis o
f
b
re
a
st ca
n
c
e
r,
"
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
5
0
,
p
p
.
1
6
-
2
3
,
2
0
1
5
.
[3
8
]
Du
rg
a
lak
sh
m
i
B,
V
ij
a
y
a
k
u
m
a
r
V
,
"
Im
p
a
c
t
o
f
Di
m
e
n
sio
n
a
li
ty
Re
d
u
c
ti
o
n
a
n
d
C
las
sif
ica
ti
o
n
in
Bre
a
st
Ca
n
c
e
r,
"
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
In
n
o
v
a
ti
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Ex
p
lo
ri
n
g
En
g
in
e
e
rin
g
.
v
o
l.
8
,
n
o
.
8
,
p
p
.
2
5
9
9
-
2
6
0
3
,
Ju
n
e
2
0
1
9
.
[3
9
]
S
.
B.
M
e
sk
in
a
,
"
On
t
h
e
e
ff
e
c
t
o
f
d
a
ta
re
d
u
c
ti
o
n
o
n
c
las
sif
ica
ti
o
n
a
c
c
u
ra
c
y
,
"
2
0
1
3
3
r
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
a
n
d
e
-
S
e
rv
ice
s
(
ICIT
e
S
)
,
p
p
.
1
-
7
,
2
0
1
3
.
[4
0
]
S
.
A
.
-
B
.
S
a
lm
a
n
,
A
.
-
H.
A
.
S
a
li
h
,
A
.
H.
A
li
,
M
.
K.
K
h
a
lee
l,
a
n
d
M
.
A
.
M
o
h
a
m
m
e
d
,
"
A
Ne
w
M
o
d
e
l
f
o
r
Ir
is
Clas
sif
ic
a
ti
o
n
Ba
se
d
o
n
Na
ïv
e
Ba
y
e
s
G
rid
P
a
ra
m
e
ter
s
Op
ti
m
iz
a
ti
o
n
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ie
n
c
e
s:
Ba
sic
a
n
d
Ap
p
li
e
d
Res
e
a
rc
h
(
IJ
S
BA
R),
v
o
l.
4
0
,
N
o
.
2
,
p
p
.
1
5
0
-
1
5
5
,
A
u
g
u
st
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.