I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
,
p
p
.
1
1
1
3
~1
1
20
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
1
.i
2
.
p
p
1
1
1
3
-
11
20
1113
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Co
m
pa
ra
tive s
tu
dy
of log
istic regr
ess
io
n and
artific
i
a
l neural
netw
o
rk
s o
n pred
icting brea
st
canc
er c
y
tolo
g
y
Yo
us
ra
Abdu
la
ziz
M
o
ha
m
med,
E
m
a
n
G
a
db
a
n Sa
leh
In
stit
u
te
C
o
ll
e
g
e
o
f
m
e
d
icin
e
,
Un
iv
e
rsit
y
o
f
F
a
ll
u
jah
,
Ba
g
h
d
a
d
,
Ira
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
28
,
2
0
2
0
R
ev
i
s
ed
J
u
n
1
5
,
2
0
2
0
A
cc
ep
ted
J
u
l 8
,
2
0
2
0
Cu
rre
n
tl
y
,
b
re
a
st
c
a
n
c
e
r
is
o
n
e
o
f
th
e
m
o
st
c
o
m
m
o
n
c
a
n
c
e
rs
a
n
d
a
m
a
in
re
a
so
n
o
f
w
o
m
e
n
d
e
a
th
w
o
rld
w
i
d
e
p
a
rti
c
u
larly
in
d
e
v
e
lo
p
in
g
c
o
u
n
tri
e
s
su
c
h
a
s
Ira
q
.
Ou
r
w
o
rk
a
i
m
s
to
p
re
d
ict
th
e
ty
p
e
o
f
tu
m
o
r
w
h
e
th
e
r
b
e
n
ig
n
o
r
m
a
li
g
n
a
n
t
th
ro
u
g
h
m
o
d
e
ls
th
a
t
w
e
re
b
u
il
t
u
sin
g
lo
g
isti
c
re
g
re
ss
io
n
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
s
a
n
d
w
e
h
o
p
e
it
w
il
l
h
e
lp
d
o
c
to
rs
i
n
d
e
tec
ti
n
g
th
e
ty
p
e
o
f
b
re
a
st
tu
m
o
r.
F
o
u
r
m
o
d
e
ls
w
e
r
e
se
t
u
sin
g
b
in
a
ry
lo
g
isti
c
re
g
re
ss
io
n
a
n
d
tw
o
d
if
fe
re
n
t
ty
p
e
s
o
f
a
rti
f
i
c
ial
n
e
u
ra
l
n
e
tw
o
rk
s
n
a
m
e
l
y
m
u
lt
il
a
y
e
r
p
e
rc
e
p
tro
n
ML
P
a
n
d
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
RBF
.
Ev
a
lu
a
ti
o
n
o
f
v
a
li
d
a
ted
a
n
d
trai
n
e
d
m
o
d
e
ls
w
a
s
d
o
n
e
u
sin
g
se
v
e
ra
l
p
e
rf
o
r
m
a
n
c
e
m
e
tri
c
s
li
k
e
a
c
c
u
ra
c
y
,
se
n
siti
v
it
y
,
sp
e
c
if
i
c
it
y
,
a
n
d
AU
C
(a
re
a
u
n
d
e
r
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic
ROC).
Da
tas
e
t
w
a
s
d
o
w
n
lo
a
d
e
d
fro
m
UCI
m
l
r
e
p
o
sito
ry
;
it
is
c
o
m
p
o
se
d
o
f
9
a
tt
rib
u
tes
a
n
d
6
9
9
sa
m
p
les
.
T
h
e
f
in
d
in
g
s
a
re
c
lea
rl
y
sh
o
w
in
g
th
a
t
th
e
RBF
NN
c
las
sif
ier
is
th
e
b
e
st i
n
p
re
d
ic
ti
o
n
o
f
th
e
ty
p
e
o
f
b
re
a
st t
u
m
o
rs
s
in
c
e
it
h
a
d
re
c
o
rd
e
d
th
e
h
ig
h
e
st
p
e
rf
o
rm
a
n
c
e
in
term
s
o
f
c
o
rre
c
t
c
las
si
f
ic
a
ti
o
n
r
a
te
(a
c
c
u
ra
c
y
),
se
n
siti
v
it
y
,
sp
e
c
i
f
icit
y
,
a
n
d
A
U
C
(a
re
a
u
n
d
e
r
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic ROC) a
m
o
n
g
a
ll
o
t
h
e
r
m
o
d
e
ls
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
B
r
ea
s
t tu
m
o
r
C
las
s
i
f
icatio
n
L
o
g
i
s
tic
r
eg
r
e
s
s
io
n
UC
I
ML
r
ep
o
s
ito
r
y
Valid
atio
n
T
h
is
is
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
:
Yo
s
r
a
A
b
d
u
laziz
Mo
h
a
m
m
ed
C
o
lleg
e
o
f
Me
d
ici
n
e
Un
i
v
er
s
it
y
o
f
Fal
lu
j
ah
AL
a
n
b
ar
,
I
r
aq
E
m
ail:
y
o
s
r
a_
m
o
h
a
m
m
ed
@
u
o
f
all
u
j
ah
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
C
u
r
r
en
tl
y
,
b
r
ea
s
t
ca
n
ce
r
is
o
n
e
o
f
t
h
e
m
o
s
t
co
m
m
o
n
ca
n
c
er
s
an
d
a
m
a
in
r
ea
s
o
n
o
f
w
o
m
en
d
ea
t
h
w
o
r
ld
w
id
e
p
ar
ticu
lar
l
y
i
n
d
ev
elo
p
in
g
co
u
n
tr
ie
s
li
k
e
I
r
aq
[
1
]
.
I
t
is
ac
co
u
n
ti
n
g
f
o
r
2
5
%
o
f
a
ll
m
al
ig
n
a
n
c
y
,
w
i
th
ab
o
u
t
n
e
w
1
.
5
7
m
i
llio
n
ca
s
es
in
2
0
1
2
[
1
]
.
I
t
is
th
e
f
ir
s
t
–
r
an
k
ed
ca
u
s
e
o
f
w
o
m
a
n
ca
n
ce
r
-
r
elate
d
d
ea
th
s
.
A
lt
h
o
u
g
h
f
u
n
d
a
m
e
n
tal
i
m
p
r
o
v
e
m
en
t
in
th
e
s
u
r
v
iv
al
f
o
r
th
is
d
is
ea
s
e
h
as
b
ee
n
r
ec
o
r
d
ed
in
c
o
u
n
tr
ies
w
i
th
h
ig
h
-
r
eso
u
r
ce
,
th
e
r
is
k
g
o
o
n
to
r
is
e,
r
ec
o
r
d
in
g
h
ig
h
m
o
r
talit
y
r
a
tes
i
n
d
e
v
elo
p
in
g
co
u
n
tr
ies
[
1
]
.
T
h
e
I
r
aq
i
ca
n
ce
r
R
eg
i
s
tr
y
d
i
s
clo
s
ed
t
h
e
b
r
ea
s
t
ca
n
ce
r
is
t
h
e
h
i
g
h
e
s
t
r
ates
o
f
ca
n
ce
r
ca
s
e
s
(
1
9
.
1
%)
an
d
th
e
h
ig
h
e
s
t
an
n
u
al
esti
m
ate
o
f
ca
n
ce
r
in
w
o
m
en
(
2
5
.
8
p
er
h
u
n
d
r
ed
th
o
u
s
a
n
d
o
f
t
h
e
f
e
m
ale
p
o
p
u
latio
n
)
.
T
h
e
s
ec
o
n
d
–
r
an
k
ed
in
cid
en
ce
o
f
ca
n
ce
r
m
o
r
talit
y
w
a
s
b
r
ea
s
t
ca
n
ce
r
(
2
.
7
/1
0
0
,
0
0
0
p
o
p
u
latio
n
s
)
[
2
]
.
A
cc
o
r
d
in
g
to
a
s
tu
d
y
,
t
h
e
r
ate
o
f
co
n
tin
u
i
n
g
to
liv
e
i
s
8
8
%
p
o
s
t
f
iv
e
y
ea
r
s
o
f
d
etec
tio
n
an
d
8
0
%
p
o
s
t
ten
y
ea
r
s
o
f
d
etec
tio
n
in
ea
r
l
y
s
ta
g
e
w
h
ic
h
m
ea
n
s
t
h
at
a
b
o
u
t
8
8
%
o
f
w
o
m
e
n
d
ia
g
n
o
s
ed
w
it
h
b
r
e
ast
ca
n
ce
r
w
ill
s
u
r
v
i
v
e
f
o
r
at
least
5
y
ea
r
s
a
f
ter
th
eir
ea
r
l
y
d
iag
n
o
s
i
s
; t
h
at
’
s
wh
y
it i
s
s
er
io
u
s
to
d
etec
t b
r
ea
s
t c
an
ce
r
as e
ar
lier
as p
o
s
s
ib
le
[
3
]
.
No
w
ad
a
y
s
,
d
iag
n
o
s
i
n
g
ca
n
ce
r
u
s
i
n
g
m
ac
h
i
n
e
lear
n
i
n
g
M
L
i
s
in
f
l
u
en
tial
,
s
i
n
ce
ML
h
a
s
t
h
e
ab
ilit
y
o
f
d
ed
u
ctio
n
s
w
h
ic
h
t
h
e
tr
ad
itio
n
al
s
tatis
t
ical
m
eth
o
d
s
d
o
n
o
t
h
av
e
[
4
]
.
A
cla
s
s
i
f
icatio
n
m
o
d
el
o
r
a
"
class
if
ier
"
can
b
e
p
o
w
er
f
u
l
in
a
s
s
i
s
ti
n
g
o
n
co
lo
g
is
ts
to
co
r
r
ec
tl
y
d
ia
g
n
o
s
e
b
r
ea
s
t
t
u
m
o
r
b
io
p
s
y
.
C
las
s
i
f
icatio
n
m
ea
n
s
g
u
e
s
s
i
n
g
t
h
e
ca
te
g
o
r
y
o
f
n
e
w
in
c
id
en
ce
f
r
o
m
a
s
e
t
o
f
p
r
ed
ictiv
e
f
ea
tu
r
e
s
f
r
o
m
th
e
s
a
m
p
le
d
ataset.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
13
-
11
20
1114
ex
is
te
n
ce
or
n
o
n
-
ex
i
s
ta
n
ce
o
f
th
e
m
al
ig
n
a
n
c
y
ca
n
b
e
ass
u
r
e
d
b
y
th
e
o
u
tco
m
e
o
f
b
io
p
s
y
th
er
ef
o
r
e
it
is
co
u
n
ted
as
a
b
in
ar
y
o
u
t
p
u
t
.
T
h
e
ap
p
licatio
n
o
f
L
o
g
i
s
tic
R
eg
r
ess
i
o
n
(
L
R
)
in
s
ev
er
al
ar
e
as
is
g
r
o
w
i
n
g
esp
ec
iall
y
in
t
h
e
m
ed
ical
d
o
m
ai
n
.
I
t
is
a
s
tatis
tical
alg
o
r
ith
m
t
h
at
ca
n
b
e
u
s
ed
p
er
f
ec
tl
y
f
o
r
b
in
ar
y
cla
s
s
i
f
icatio
n
to
f
i
n
d
th
e
ass
o
ciatio
n
b
et
w
ee
n
o
n
e
o
r
m
o
r
e
co
n
ti
n
u
o
u
s
o
r
ca
te
g
o
r
ical
p
ar
a
m
eter
an
d
a
b
ilater
al
d
ep
en
d
en
t
o
u
tp
u
t
[
5
]
.
T
h
e
tech
n
iq
u
e
o
f
l
o
g
i
s
tic
r
eg
r
es
s
io
n
is
ab
le
t
o
d
esig
n
ate
d
i
f
f
er
en
t
d
atasets
t
o
p
r
ev
io
u
s
l
y
d
e
f
i
n
ed
clas
s
es
,
t
h
is
is
ca
r
r
ied
o
u
t
b
y
estab
lis
h
in
g
t
h
e
d
is
cr
i
m
i
n
atio
n
r
u
le
s
w
h
ic
h
ar
e
s
et
i
n
t
h
e
t
r
ain
in
g
s
tag
e
a
n
d
th
e
n
u
s
ed
t
o
allo
ca
te
th
e
n
e
w
in
cid
en
ce
s
to
class
e
s
d
eter
m
i
n
ed
in
ad
v
an
ce
[
6
]
.
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
s
(
A
N
N)
ar
e
co
m
m
o
n
l
y
u
s
ed
as
a
r
o
b
u
s
t
d
ec
is
io
n
m
ak
in
g
s
y
s
te
m
s
esp
ec
iall
y
f
o
r
m
ed
ical
d
iag
n
o
s
in
g
af
ter
b
ein
g
tr
ain
ed
u
s
i
n
g
h
is
to
r
ical
d
ata
s
et.
A
N
Ns
ad
v
an
tag
e
s
ca
n
b
e
s
u
m
m
ar
ized
in
th
a
t
t
u
n
in
g
n
eu
r
al
w
ei
g
h
ts
i
s
d
o
n
e
o
n
li
n
e
w
ith
n
o
n
ee
d
to
a
n
y
p
r
e
-
tr
ain
i
n
g
p
h
ase,
a
n
d
p
er
s
is
ten
ce
a
n
d
p
er
f
o
r
m
a
n
ce
s
y
s
te
m
s
is
e
n
s
u
r
ed
.
A
NN
i
s
a
p
o
w
er
f
u
l
clas
s
i
f
ier
th
a
t
r
ep
r
esen
ts
a
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
b
et
w
ee
n
i
n
p
u
t
a
n
d
o
u
tp
u
t.
B
asicall
y
,
a
s
i
m
p
l
e
A
N
N
co
n
s
i
s
ts
o
f
t
h
r
ee
la
y
er
s
,
an
in
p
u
t
la
y
er
,
h
id
d
en
la
y
er
/
s
an
d
an
o
u
tp
u
t
la
y
er
.
A
t
t
h
e
in
p
u
t
la
y
er
th
e
in
p
u
t
s
ar
e
w
ei
g
h
ted
,
i.e
ea
ch
in
p
u
t
v
al
u
e
is
m
u
ltip
lied
b
y
ce
r
tai
n
w
eig
h
t.
A
t
t
h
e
h
id
d
en
la
y
er
,
all
w
eig
h
ted
in
p
u
t
s
alo
n
g
w
it
h
a
b
ias
a
r
e
s
u
m
m
ed
.
Fi
n
all
y
at
th
e
o
u
tp
u
t
la
y
er
th
e
s
u
m
m
e
d
v
al
u
e
o
b
tain
ed
is
co
n
v
er
ted
to
ac
tiv
at
io
n
s
i
g
n
al
u
s
i
n
g
tr
a
n
s
f
o
r
m
f
u
n
ctio
n
.
T
h
e
A
N
N
i
s
tr
ai
n
ed
w
it
h
a
lear
n
i
n
g
al
g
o
r
ith
m
ac
co
r
d
in
g
to
t
h
e
t
y
p
e
o
f
th
e
g
iv
e
n
p
r
o
b
le
m
.
Ge
n
er
all
y
t
h
e
lear
n
in
g
alg
o
r
ith
m
s
ar
e
eit
h
er
s
u
p
er
v
is
ed
lear
n
in
g
,
u
n
s
u
p
er
v
is
ed
lear
n
in
g
o
r
r
ein
f
o
r
ce
m
en
t
lear
n
i
n
g
[
7
].
T
h
e
m
ai
n
g
o
al
o
f
t
h
is
w
o
r
k
is
to
co
m
p
ar
e
th
e
p
er
f
o
r
m
an
ce
o
f
t
w
o
tech
n
iq
u
es,
lo
g
i
s
tic
r
e
g
r
ess
io
n
a
n
d
n
eu
r
al
n
et
w
o
r
k
s
to
d
e
f
i
n
e
t
h
e
m
o
r
e
p
o
w
er
f
u
l
tech
n
iq
u
e
i
n
cl
ass
i
f
y
in
g
t
h
e
t
y
p
e
o
f
b
r
ea
s
t
t
u
m
o
r
in
to
b
en
i
g
n
o
r
m
ali
g
n
a
n
t
clas
s
es.
T
h
e
o
th
er
s
ec
tio
n
s
o
f
t
h
is
p
ap
er
ar
e:
s
ec
tio
n
t
w
o
is
a
liter
atu
r
e
r
ev
ie
w
p
ar
t
an
d
w
o
r
k
d
o
n
e
in
th
e
ar
ea
o
f
B
r
ea
s
t
C
an
ce
r
.
T
h
ir
d
s
ec
tio
n
p
r
esen
ts
d
at
a
co
llectio
n
an
d
p
r
ep
r
o
ce
s
s
in
g
an
d
th
e
u
s
ed
m
et
h
o
d
o
lo
g
y
.
T
h
e
ex
p
er
i
m
e
n
t
al
r
esu
lt
s
ar
e
p
r
esen
ted
i
n
Sect
io
n
f
o
u
r
,
an
d
f
i
n
all
y
Sec
tio
n
s
f
iv
e
an
d
s
ix
d
i
s
cu
s
s
r
esu
lt
s
,
co
n
clu
s
io
n
a
n
d
f
u
t
u
r
e
w
o
r
k
.
2.
L
I
T
E
R
E
T
UR
E
RE
V
I
E
W
A
t
p
r
ese
n
t,
p
h
y
s
ician
s
ar
e
m
a
k
in
g
s
u
r
g
ical
b
io
p
s
y
to
d
ec
id
e
w
h
ea
t
h
er
th
e
b
r
ea
s
t
tu
m
o
r
s
ar
e
b
en
ig
n
o
r
m
ali
g
n
an
t.
Si
n
ce
b
io
p
s
y
m
i
g
h
t
b
e
cr
itical,
th
e
n
it
m
u
s
t
b
e
h
alted
as
p
o
s
s
ib
le
as
w
e
ca
n
.
T
h
u
s
,
to
d
etec
t
th
e
t
y
p
e
o
f
t
u
m
o
r
an
d
k
ee
p
a
w
a
y
f
r
o
m
u
n
n
ec
es
s
ar
y
s
u
r
g
ical
b
io
p
s
y
,
a
s
m
ar
t
s
y
s
te
m
o
r
class
if
ier
i
m
p
le
m
e
n
ti
n
g
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
s
ca
n
b
e
u
s
ef
u
l
f
o
r
b
o
th
p
at
ien
ts
a
n
d
p
h
y
s
icia
n
s
.
R
ec
en
t
l
y
,
m
a
n
y
d
if
f
er
e
n
t
alg
o
r
ith
m
s
h
a
v
e
b
ee
n
d
e
v
elo
p
ed
f
o
r
d
iag
n
o
s
i
n
g
t
h
e
b
r
ea
s
t
tu
m
o
r
s
.
B
r
ea
s
t
C
a
n
ce
r
d
etec
tio
n
o
f
m
ed
ical
i
m
a
g
e
s
is
a
v
er
y
i
m
p
o
r
tan
t
co
m
p
o
n
en
t
o
f
i
m
ag
e
p
r
o
ce
s
s
i
n
g
t
ec
h
n
iq
u
e.
Yo
u
s
i
f
A
.
Ha
m
a
d
et
al.
cla
s
s
i
f
ied
m
a
m
m
o
g
r
a
m
i
m
ag
e
s
i
n
to
t
h
r
ee
class
e
s
:
n
o
r
m
al,
b
en
i
g
n
a
n
d
m
ali
g
n
a
n
t
th
r
o
u
g
h
a
n
ap
p
r
o
ac
h
th
at
i
n
cl
u
d
es
s
o
m
e
f
u
n
ct
io
n
s
f
o
r
n
o
is
e
r
e
m
o
v
al
,
t
h
en
f
ea
t
u
r
es
w
er
e
i
m
p
r
o
v
e
d
to
g
et
b
etter
c
h
ar
ac
ter
is
tics
o
f
m
ed
ical
i
m
ag
e
s
f
o
r
a
co
r
r
ec
t
d
iag
n
o
s
is
u
s
in
g
b
alan
ce
co
n
tr
a
s
t
en
h
a
n
ce
m
en
t
t
ec
h
n
iq
u
es
(
B
C
E
T
)
.
T
h
e
o
u
tco
m
e
o
f
s
ec
o
n
d
s
ta
g
e
w
a
s
s
u
b
j
ec
ted
to
i
m
ag
e
s
e
g
m
en
tatio
n
u
s
in
g
FC
M
clu
s
te
r
in
g
m
et
h
o
d
(
Fu
zz
y
c
-
Me
a
n
s
)
an
d
T
h
r
esh
o
ld
in
g
tech
n
iq
u
e
to
c
u
t
t
h
e
o
u
t
b
o
r
d
er
s
o
f
t
h
e
b
r
ea
s
t
a
n
d
to
lo
ca
te
t
h
e
B
r
ea
s
t
T
u
m
o
r
b
o
u
n
d
ar
ies
(
s
h
ap
e,
ar
ea
,
s
p
atial
s
izes,
etc.
)
in
t
h
e
i
m
a
g
es.
T
h
e
th
ir
d
s
tag
e
w
as
f
ea
tu
r
e
e
x
tr
a
ctio
n
u
s
in
g
Di
s
cr
ete
W
av
elet
T
r
an
s
f
o
r
m
(
DW
T
)
.
A
t
last
,
cla
s
s
i
f
icat
io
n
o
f
th
e
s
tag
e
o
f
B
r
ea
s
t
T
u
m
o
r
in
to
b
en
ig
n
,
m
ali
g
n
an
t
o
r
n
o
r
m
a
l
w
a
s
d
o
n
e
u
s
i
n
g
P
NN
(
P
r
o
b
ab
ilis
tic
Neu
r
al
Net
w
o
r
k
)
,
th
e
f
in
d
i
n
g
s
w
as
a
h
i
g
h
clas
s
if
ica
tio
n
r
ate
o
f
(
9
0
%)
[
8
]
.
M
ah
f
u
za
h
Mu
s
taf
a
et
al
.
h
av
e
co
n
d
u
cted
a
m
et
h
o
d
to
im
p
r
o
v
e
th
e
Gr
ad
ien
t
Vec
to
r
Flo
w
(
GVF)
S
n
ak
e
A
cti
v
e
C
o
n
to
u
r
s
eg
m
e
n
tatio
n
tech
n
iq
u
e
in
m
a
m
m
o
g
r
ap
h
y
s
e
g
m
en
ta
tio
n
.
Di
g
ita
l
Data
b
ase
o
f
Scr
ee
n
in
g
Ma
m
m
o
g
r
a
m
s
(
DDSM)
w
a
s
u
s
ed
f
o
r
th
e
p
u
r
p
o
s
e
o
f
s
cr
ee
n
i
n
g
.
T
h
e
r
esu
lt
s
h
o
w
s
t
h
at
C
h
a
n
-
Vese
tec
h
n
iq
u
e
o
u
tp
er
f
o
r
m
s
L
o
ca
lized
A
c
tiv
e
C
o
n
to
u
r
w
ith
9
0
%
ac
cu
r
ac
y
[
9
]
.
Mu
h
a
m
m
et
Fati
h
A
k
ap
p
lied
Dat
a
v
is
u
aliza
tio
n
an
d
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
in
clu
d
i
n
g
r
an
d
o
m
f
o
r
est,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e,
n
aï
v
e
B
a
y
es,
lo
g
i
s
tic
r
eg
r
ess
io
n
,
d
ec
is
io
n
tr
ee
,
k
-
n
ea
r
est
n
eig
h
b
o
r
s
,
an
d
r
o
tatio
n
f
o
r
est
to
d
ata
o
f
b
r
ea
s
t
ca
n
ce
r
tu
m
o
r
s
f
r
o
m
Dr
.
W
illi
a
m
H.
W
alb
er
g
o
f
th
e
U
n
iv
er
s
it
y
o
f
W
is
co
n
s
i
n
Ho
s
p
it
al.
T
h
e
lo
g
i
s
tic
r
e
g
r
ess
io
n
m
o
d
el
w
i
th
all
f
ea
tu
r
es
o
u
tp
er
f
o
r
m
ed
a
n
d
h
ad
s
co
r
ed
9
8
.
1
%
class
i
f
icat
io
n
ac
c
u
r
ac
y
[1
0
]
.
J
ab
ee
n
s
u
lta
n
a
a
n
d
Ab
d
u
l
Kh
ad
er
J
ila
n
i
p
r
ed
icted
th
e
ex
is
ta
n
ce
of
B
r
ea
s
t
ca
n
ce
r
b
y
ev
al
u
ati
n
g
d
ataset
o
n
v
ar
io
u
s
clas
s
i
f
ie
r
s
lik
e
M
u
lti
-
L
a
y
er
P
er
ce
p
tr
o
n
(
ML
P
)
,
R
an
d
o
m
Fo
r
est,
Si
m
p
le
L
o
g
i
s
tic
-
r
e
g
r
ess
io
n
m
e
th
o
d
,
I
B
K,
K
-
s
t
ar
,
Dec
is
io
n
tab
le,
Dec
is
io
n
T
r
ee
s
(
DT
)
,
P
A
R
T
,
Mu
lti
-
C
las
s
C
las
s
i
f
ier
s
a
n
d
R
E
P
T
r
ee
.
Fin
d
in
g
s
s
h
o
w
ed
th
at
Si
m
p
le
L
o
g
i
s
tic
R
eg
r
es
s
io
n
w
a
s
t
h
e
b
est
m
o
d
el
f
o
llo
w
ed
b
y
o
th
er
m
eth
o
d
s
[
1
1
]
.
Mo
h
am
m
ed
A
b
d
u
lr
az
aq
Kah
y
a
u
s
ed
t
h
e
B
r
ea
KHis
(
T
h
e
B
r
ea
s
t
C
an
ce
r
His
to
p
ath
o
lo
g
ical
I
m
a
g
es)
d
atasets
to
d
ev
elo
p
a
m
et
h
o
d
to
class
if
y
b
r
ea
s
t
tu
m
o
r
s
in
to
t
w
o
cla
s
s
e
s
b
en
i
g
n
an
d
m
ali
g
n
a
n
t.
T
h
e
m
e
th
o
d
u
s
ed
w
as
ad
ap
ti
v
e
p
en
alize
d
lo
g
is
tic
r
e
g
r
ess
io
n
A
P
L
R
b
y
s
m
o
o
th
i
n
g
t
h
e
f
e
atu
r
es
m
a
tr
ix
to
r
aise
th
e
o
v
er
all
class
if
ica
tio
n
ac
cu
r
ac
y
o
f
b
r
ea
s
t
ca
n
ce
r
h
is
to
p
at
h
o
lo
g
ical
i
m
ag
e
s
.
T
h
e
f
in
d
i
n
g
s
s
h
o
w
ed
th
at
A
P
L
R
is
a
p
r
o
m
is
i
n
g
tech
n
iq
u
e
f
o
r
class
if
icatio
n
o
f
m
ed
ical
i
m
ag
e
a
n
d
tu
m
o
r
s
d
iag
n
o
s
is
[
1
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
o
mp
a
r
a
tive
s
tu
d
y
o
f lo
g
is
tic
r
eg
r
ess
io
n
a
n
d
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
ks o
n
…
(
Yo
u
s
r
a
A
b
d
u
la
z
iz
Mo
h
a
mme
d
)
1115
T
h
is
w
o
r
k
r
ep
r
esen
ts
a
co
m
p
ar
is
o
n
b
et
w
ee
n
t
w
o
d
if
f
er
e
n
t
m
ac
h
i
n
e
lear
n
i
n
g
tec
h
n
iq
u
es
in
t
h
e
p
r
o
g
n
o
s
is
o
f
b
r
ea
s
t
t
u
m
o
r
s
wea
th
er
m
ali
g
n
an
t
o
r
b
en
ig
n
.
T
h
e
m
o
d
el
d
ev
elo
p
ed
in
th
is
s
t
u
d
y
ca
n
a
s
s
i
s
t
an
d
h
elp
o
n
co
lo
g
is
ts
i
n
b
r
ea
s
t c
an
c
er
d
etec
tio
n
.
3.
M
AT
E
RIAL
A
ND
M
E
T
H
O
DS
3
.
1
.
Da
t
a
B
r
ea
s
t
-
ca
n
ce
r
-
W
is
co
n
s
i
n
d
ata
d
o
w
n
lo
ad
ed
f
r
o
m
m
ac
h
in
e
l
ea
r
n
in
g
r
ep
o
s
ito
r
y
o
f
U
C
I
is
th
e
d
ataset
u
s
ed
i
n
t
h
is
w
o
r
k
[1
3
].
T
h
e
d
ataset
h
a
s
6
9
9
b
r
ea
s
t
FN
A
s
.
I
t
is
co
m
p
o
s
ed
o
f
1
1
co
lu
m
n
s
,
e
v
er
y
r
o
w
i
s
o
b
s
er
v
atio
n
s
of
a
p
atien
t
's
b
r
ea
s
t
FNA
t
h
at
w
as
o
b
tain
ed
f
r
o
m
m
ed
ical
an
al
y
s
i
s
.
C
o
lu
m
n
n
o
.
1
is
th
e
id
en
ti
f
icatio
n
co
d
e
of
ea
ch
p
atien
t
an
d
w
as
r
e
m
o
v
ed
s
in
ce
it
is
n
o
t
r
eq
u
ir
ed
f
o
r
th
e
an
al
y
s
i
s
;
th
e
n
ex
t
n
i
n
e
co
lu
m
n
s
r
ep
r
esen
t
th
e
p
r
ed
icto
r
s
u
tili
ze
d
to
an
al
y
ze
ev
er
y
FN
A
o
b
tain
ed
f
r
o
m
p
atie
n
t
b
r
ea
s
t
tu
m
o
r
;
cla
m
p
th
ic
k
n
e
s
s
(
r
an
g
e
to
w
h
ic
h
ce
ll
ag
g
r
eg
a
tes
,
m
o
n
o
-
o
r
m
u
ltil
a
y
er
ed
)
,
u
n
i
f
o
r
m
it
y
o
f
ce
ll
s
ize
s
,
u
n
i
f
o
r
m
it
y
o
f
ce
ll
f
o
r
m
s
,
m
ar
g
i
n
al
ad
h
e
s
io
n
(
co
h
er
en
ce
o
f
t
h
e
m
ar
g
in
al
ce
ll
s
o
f
th
e
ce
ll
ag
g
r
eg
ate
s
)
,
s
ize
o
f
th
e
s
in
g
le
ep
ith
e
lial
ce
ll(d
ia
m
eter
o
f
t
h
e
i
n
h
ab
itan
ce
o
f
t
h
e
b
ig
g
e
st
ce
lls
co
m
p
a
r
ativ
e
to
er
y
t
h
r
o
c
y
te
s
)
,
B
ar
e
n
u
cle
i
(
th
e
r
atio
o
f
s
in
g
le
ce
ll
n
u
cle
i
th
at
w
er
e
f
r
ee
d
f
r
o
m
e
n
cir
cle
m
en
t
c
y
to
p
l
as
m
)
,
ch
r
o
m
ati
n
b
lan
d
n
e
s
s
,
n
u
cleo
lu
s
n
o
r
m
a
lit
y
,
an
d
m
ito
s
is
[
1
4
].
C
o
lu
m
n
n
o
.
1
1
r
ep
r
esen
ts
th
e
o
u
tco
m
e
o
r
th
e
tu
m
o
r
clas
s
;
m
ali
g
n
=4
an
d
b
e
n
ig
n
=2
.
"
A
ll
m
ali
g
n
an
t
asp
ir
ates
w
er
e
h
is
to
lo
g
icall
y
co
n
f
ir
m
ed
w
h
e
r
ea
s
FN
A
s
d
ia
g
n
o
s
ed
as
b
en
i
g
n
m
a
s
s
e
s
w
er
e
b
io
p
s
ied
o
n
l
y
at
t
h
e
p
atien
t
'
s
r
eq
u
e
s
t.
T
h
e
r
e
m
ain
d
er
o
f
b
en
ig
n
c
y
to
lo
g
ies
w
er
e
co
n
f
ir
m
ed
b
y
cli
n
ical
r
ee
x
a
m
i
n
atio
n
3
a
n
d
1
2
m
o
n
t
h
s
a
f
ter
th
e
asp
ir
atio
n
.
Ma
s
s
e
s
th
at
p
r
o
d
u
ce
d
u
n
s
ati
s
f
ac
to
r
y
o
r
s
u
s
p
icio
u
s
FN
As
w
er
e
s
u
r
g
ica
ll
y
b
io
p
s
ied
"
[
1
5
].
T
h
e
n
in
e
f
ea
t
u
r
es
ar
e
n
u
m
b
er
s
r
an
g
i
n
g
f
r
o
m
1
to
1
0
,
w
h
ich
w
er
e
r
ec
o
r
d
ed
v
ia
lab
te
s
ts
o
r
m
ed
ical
an
al
y
s
is
.
T
h
e
p
r
o
p
o
r
tio
n
s
o
f
t
h
e
o
u
tco
m
e
o
r
t
h
e
"
C
las
s
"
is
;
Ma
lig
n
an
t:
2
4
1
(
3
4
.
5
%).
an
d
B
en
ig
n
:
4
5
8
(
6
5
.
5
%
(
A
t
f
ir
s
t,
t
h
e
d
ata
w
as
co
n
v
er
te
d
to
E
x
ce
l
s
h
ee
t
f
o
r
ea
s
i
n
es
s
,
t
h
en
d
ata
c
lean
i
n
g
w
a
s
d
o
n
e
b
y
r
ep
lacin
g
m
is
s
i
n
g
v
alu
e
s
b
y
t
h
e
m
ea
n
of
th
e
n
ea
r
b
y
attr
ib
u
te
v
al
u
es
[
16
]
,
af
ter
th
at
t
h
e
d
ata
h
as
b
ee
n
i
m
p
o
r
te
d
to
th
e
s
tatis
t
ical
p
r
o
g
r
am
SP
SS
,
V1
9
.
0
f
o
r
an
aly
s
i
n
g
to
b
u
ild
th
e
s
ta
tis
t
ical
m
o
d
els.
3
.
2
.
L
o
g
is
t
ic
re
g
re
s
s
io
n
(
L
R)
T
h
e
lo
g
is
tic
f
u
n
ctio
n
i
n
(
1
)
r
ep
r
esen
ts
t
h
e
co
n
d
itio
n
al
p
r
o
b
a
b
ilit
y
f
o
r
o
cc
u
r
an
ce
o
f
an
ev
e
n
t
"
d
e
p
en
d
an
t v
ar
iab
le"
[
17
],
(
1
)
W
h
er
e
p
r
o
b
ab
ilit
y
v
al
u
es
ar
e
i
n
t
h
e
r
an
g
e
o
f
0
to
1
,
z
(
o
r
lo
g
it)
is
th
e
li
n
ea
r
m
u
lt
ip
le
r
eg
r
ess
io
n
m
o
d
el
o
f
th
e
p
r
ed
icto
r
s
́
́
(
2
)
T
h
e
co
ef
f
icien
t
s
o
f
th
e
i
n
d
ep
en
d
en
t
v
ar
iab
le
s
ar
e
...
w
h
ic
h
ar
e
co
m
p
u
ted
b
y
es
ti
m
ati
n
g
th
e
m
ax
i
m
u
m
li
k
eli
h
o
o
d
,
…
ar
e
e
x
p
lan
ato
r
y
v
ar
iab
les a
n
d
n
is
t
h
e
ir
n
u
m
b
er
W
h
ile
r
ef
er
en
ce
p
r
o
b
ab
ilit
y
is
d
ef
in
ed
as,
(
3
)
th
e
lo
g
(
o
d
d
s
)
,
o
r
lo
g
-
o
d
d
s
r
atio
,
is
d
ef
in
ed
b
y
,
[
]
=z
(
4
)
I
t
r
ep
r
esen
ts
t
h
e
lo
g
o
f
t
h
e
r
at
io
o
f
t
h
e
c
h
a
n
ce
o
f
a
n
e
v
e
n
t
t
o
h
ap
p
en
,
p
(
Y=
1
)
,
to
th
e
c
h
a
n
ce
it
w
il
l
n
ot
p
(
Y=
0
)
,
it
is
co
m
p
u
ted
f
r
o
m
th
e
p
r
o
b
ab
ilit
y
o
f
e
v
er
y
i
n
ci
d
en
ce
.
T
h
e
o
d
d
s
r
atio
is
d
ef
in
e
d
as
́
́
(
5
)
T
w
o
m
o
d
el
s
w
er
e
d
ev
elo
p
ed
u
s
i
n
g
L
R
,
a
f
u
ll
m
o
d
el
w
it
h
al
l
9
p
r
ed
icto
r
s
an
d
a
r
ed
u
ce
d
m
o
d
el
w
it
h
o
n
l
y
5
attr
ib
u
te
s
w
h
ic
h
s
h
o
w
e
d
s
tatis
tical
s
ig
n
i
f
ica
n
ce
i.e
p
-
v
alu
e
w
a
s
les
s
th
a
n
0
.
0
5
.
Valid
atio
n
o
f
a
m
o
d
el
i
s
a
n
e
s
s
en
tia
l
s
tag
e
in
m
o
d
el
b
u
ild
i
n
g
[
18
].
T
h
e
v
alid
atio
n
is
u
s
i
n
g
d
i
f
f
er
e
n
t
d
ata
s
et
p
er
tain
in
g
t
h
e
v
al
u
es
o
f
th
e
co
ef
f
icien
t
as
f
o
r
th
e
tr
ain
i
n
g
d
ata
to
ca
lcu
late
th
e
p
er
ce
n
tag
e
o
f
co
r
r
ec
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
13
-
11
20
1116
class
i
f
icatio
n
s
.
T
h
e
p
er
ce
n
tag
e
o
f
co
r
r
ec
tly
p
r
ed
icted
s
am
p
les
f
r
o
m
t
h
e
tr
ain
i
n
g
s
a
m
p
le
s
m
u
s
t
b
e
≥
to
th
e
v
alid
a
ted
s
a
m
p
le
s
[
19
].
T
h
er
e
ar
e
a
lo
t
o
f
s
tatis
tical
m
et
h
o
d
s
o
f
v
alid
atio
n
o
f
a
m
o
d
el
in
b
in
ar
y
lo
g
is
tic
r
eg
r
e
s
s
io
n
s
u
c
h
as
b
o
o
ts
tr
ap
p
in
g
,
j
ac
k
k
n
if
e
tech
n
iq
u
e
,
r
ep
ea
ted
d
ata
-
s
p
litt
i
n
g
,
an
d
d
ata
s
p
litt
in
g
[
20
].
W
e
i
m
p
le
m
en
ted
d
ata
-
s
p
litt
i
n
g
m
e
h
to
d
in
t
h
i
s
s
t
u
d
y
.
R
an
d
o
m
d
i
v
is
io
n
o
f
th
e
d
at
a
in
to
t
w
o
s
et
s
;
t
h
e
f
ir
s
t
s
et
w
it
h
o
f
8
0
%
(
5
5
0
)
s
a
m
p
le
u
s
ed
f
o
r
b
u
ild
in
g
t
h
e
L
R
m
o
d
el
h
av
in
g
1
7
7
m
ali
g
n
an
t
an
d
3
7
3
b
en
ig
n
,
w
h
ile
t
h
e
s
ec
o
n
d
s
et
w
a
s
co
m
p
o
s
ed
o
f
2
0%
(
1
4
9
)
s
a
m
p
le
w
i
th
6
4
m
a
lig
n
a
n
t
an
d
8
5
b
en
ig
n
w
a
s
u
s
ed
f
o
r
th
e
p
u
r
p
o
s
e
o
f
v
alid
ati
io
n
o
f
th
e
t
w
o
m
o
d
els.
B
o
th
f
u
l
l
an
d
r
ed
u
ce
d
m
o
d
e
ls
w
er
e
tr
ain
ed
i
n
th
e
s
tar
t
w
it
h
t
h
e
tr
ai
n
in
g
d
ata
s
et,
a
f
ter
th
at
t
h
e
v
alid
atio
n
d
ata
s
et
w
as
ap
p
lied
to
th
e
f
itted
m
o
d
els
to
ass
e
s
s
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
t
w
o
m
o
d
els
.
T
h
e
v
alu
e
o
f
th
e
o
b
tain
ed
p
o
s
ter
io
r
p
r
o
b
a
b
ilit
y
f
o
r
m
a
lig
n
a
n
c
y
w
a
s
th
en
class
if
ied
i
n
to
t
w
o
d
iv
i
s
i
o
n
s
;
w
h
er
e
v
alu
e
s
r
an
g
i
n
g
f
r
o
m
0
to
0
.
5
w
er
e
ass
i
g
n
ed
to
b
en
ig
n
class
,
an
d
v
alu
e
s
r
an
g
in
g
f
r
o
m
>
0
.
5
to
1
w
er
e
ass
ig
n
ed
to
m
ali
g
n
a
n
t
cla
s
s
.
E
v
a
lu
atio
n
o
f
th
e
t
w
o
m
o
d
els
w
a
s
d
o
n
e
th
e
n
in
ter
m
s
o
f
m
etr
ic
s
m
e
n
tio
n
e
d
in
s
ec
tio
n
3
.
4
.
3.3.
Neura
l
net
w
o
rk
s
I
n
o
u
r
s
tu
d
y
,
t
w
o
t
y
p
es
o
f
A
N
N
w
er
e
u
s
ed
.
T
h
e
f
ir
s
t
o
n
e
i
s
Mu
ltil
a
y
er
P
er
ce
p
tr
o
n
(
ML
P
)
n
et
w
o
r
k
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
w
h
ic
h
is
a
w
e
ll
k
n
o
w
n
n
et
w
o
r
k
ar
ch
itectu
r
e
h
a
s
b
ee
n
u
s
ed
in
m
ed
i
ca
l,
en
g
i
n
ee
r
in
g
,
m
at
h
e
m
a
tical
m
o
d
elin
g
r
esea
r
ch
.
I
n
M
L
P
,
a
f
ix
ed
v
al
u
e
(
b
ias)
alo
n
g
w
it
h
w
eig
h
ted
s
u
m
o
f
i
n
p
u
t
s
ar
e
p
r
o
p
ag
ated
to
th
e
h
id
d
en
la
y
er
v
ia
a
tr
an
s
f
er
f
u
n
ctio
n
to
g
e
n
e
r
ate
th
e
o
u
tp
u
t,
a
n
d
th
e
to
p
o
lo
g
y
o
f
f
ee
d
-
f
o
r
w
ar
d
la
y
er
s
ar
r
an
g
e
m
en
t
o
f
u
n
it
s
is
ca
lled
Feed
Fo
r
w
ar
d
Neu
r
al
Net
w
o
r
k
(
FF
NN)
[
2
1
]
.
T
h
e
le
ar
n
in
g
ab
ilit
y
o
f
t
h
e
ML
P
is
h
i
g
h
l
y
i
n
cr
ea
s
ed
b
y
t
h
e
h
id
d
en
la
y
er
.
T
h
e
in
p
u
t
i
s
m
o
d
if
ied
b
y
th
e
ac
t
iv
at
io
n
f
u
n
ct
io
n
o
f
t
h
e
n
et
w
o
r
k
s
o
as
to
g
i
v
e
a
r
eq
u
ir
ed
o
u
tp
u
t.
Mo
d
el
b
u
ild
in
g
i
s
s
tr
o
n
g
l
y
af
f
ec
te
d
b
y
t
h
e
h
id
d
en
n
o
d
es
n
u
m
b
er
,
h
id
d
en
la
y
er
s
n
u
m
b
er
,
an
d
th
e
t
y
p
e
o
f
ac
tiv
atio
n
f
u
n
c
tio
n
s
elec
tio
n
[2
2
]
.
T
h
e
o
u
tp
u
t o
f
a
ML
P
NN
is
;
∑
(
6
)
W
h
er
e
y
(
j
)
is
th
e
o
u
tp
u
t
v
alu
e,
x
k
is
t
h
e
in
p
u
t v
ec
to
r
,
T
is
th
e
tr
an
s
f
o
r
m
f
u
n
ctio
n
,
c
is
a
co
n
s
tan
t,
w
k
is
t
h
e
v
ec
to
r
o
f
w
e
ig
h
t
s
,
n
is
t
h
e
s
ize
o
f
in
p
u
t
v
ec
to
r
.
T
h
e
eq
u
atio
n
is
in
d
is
cr
e
s
te
ti
m
e
j
[
7
]
.
T
h
e
s
ec
o
n
d
t
y
p
e
o
f
NN
u
s
e
d
is
r
ad
ial
b
asis
f
u
n
ct
io
n
n
e
u
r
al
n
et
w
o
r
k
R
B
F
w
h
ich
is
b
ased
o
n
s
u
p
er
v
i
s
ed
lear
n
i
n
g
.
R
B
F
NN
ar
e
ef
f
ic
ien
t
in
m
o
d
elin
g
n
o
n
li
n
ea
r
d
ata
an
d
tr
ain
in
g
t
h
is
t
y
p
e
o
f
NN
ca
n
b
e
d
o
n
e
in
o
n
e
s
ta
g
e
co
u
n
ter
to
ML
P
.
I
n
t
h
e
h
id
d
en
la
y
er
R
B
FNN
u
s
es
n
o
n
li
n
ea
r
Ga
u
s
s
i
an
tr
an
s
f
er
f
u
n
ctio
n
w
h
er
ea
s
i
n
th
e
o
u
tp
u
t
la
y
er
it
u
s
e
s
a
lin
ea
r
s
u
m
m
at
io
n
tr
an
s
f
er
f
u
n
ctio
n
.
T
h
e
r
ea
l
v
alu
e
s
o
f
th
e
n
-
d
i
m
e
n
s
io
n
al
in
p
u
t
v
ec
to
r
X
is
f
ed
to
all
u
n
i
ts
in
th
e
h
id
d
en
la
y
er
at
t
h
e
s
a
m
e
ti
m
e
as
s
h
o
w
n
i
n
F
ig
u
r
e
2.
T
h
e
Gau
s
s
ian
R
B
F
is
g
i
v
e
n
b
y
;
(
‖
‖
)
(
‖
‖
)
(
7
)
W
h
er
e
th
e
f
u
n
ctio
n
s
‖
‖
,
i=1
,
2
,
…,
N
ar
e
ca
lled
t
h
e
R
B
Fs
,
w
h
er
e
a
p
-
n
o
r
m
(
o
f
te
n
t
h
e
E
u
clid
ea
n
2
-
n
o
r
m
)
d
en
o
tes
‖
‖
,
x
(i)
is
th
e
b
asis
f
u
n
ctio
n
ce
n
tr
e
an
d
i
is
its
r
ad
iu
s
.
A
li
n
ea
r
co
m
b
i
n
atio
n
o
f
b
asi
s
f
u
n
ctio
n
s
ca
n
b
e
u
s
ed
f
o
r
ap
p
r
o
x
i
m
at
io
n
o
f
a
n
o
n
li
n
ea
r
f
u
n
ct
io
n
.
T
h
e
o
u
tp
u
t:
R
n
→
R
,
o
f
th
e
n
et
w
o
r
k
is
t
h
u
s
∑
‖
‖
(
8
)
W
h
er
e
N
r
ep
r
esen
ts
th
e
n
e
u
r
o
n
s
n
u
m
b
er
in
th
e
h
id
d
en
la
y
er
an
d
th
e
r
ea
l
p
ar
am
e
ter
s
w
i
,
i
=
1
,
2
.
.
.
N
ar
e
th
e
lin
ea
r
o
u
tp
u
t n
e
u
r
o
n
s
w
ei
g
h
ts
[2
3
].
T
o
tr
ain
R
B
F
n
et
w
o
r
k
s
,
o
n
c
e
th
e
t
y
p
e
o
f
r
ad
ial
b
asis
f
u
n
ctio
n
i
s
s
elec
ted
,
all
n
ee
d
e
d
to
d
o
is
ch
o
o
s
in
g
t
h
e
f
u
n
ctio
n
s
'
d
i
m
en
s
io
n
s
a
n
d
ce
n
ter
s
an
d
es
ti
m
ati
n
g
th
e
o
u
tp
u
t
n
e
u
r
o
n
w
ei
g
h
t
s
.
Fo
r
th
e
A
NN,
t
w
o
m
o
d
el
s
w
er
e
d
e
v
elo
p
ed
u
s
i
n
g
t
w
o
d
i
f
f
er
e
n
t t
y
p
e
s
o
f
N
N,
n
a
m
el
y
M
L
P
an
d
R
B
F.
T
h
e
ar
ch
itectu
r
e
o
f
t
h
e
M
L
P
n
eu
r
al
n
et
w
o
r
k
h
ad
f
o
u
r
la
y
er
s
;
t
h
e
i
n
p
u
t
la
y
er
co
n
s
is
ted
o
f
9
in
p
u
t
ele
m
en
ts
,
co
r
r
esp
o
n
d
e
d
to
th
e
d
ata
ta
k
en
f
r
o
m
c
y
to
lo
g
y
,
th
e
n
t
w
o
h
id
d
en
la
y
er
s
w
it
h
s
ig
m
o
id
ac
ti
v
a
t
io
n
f
u
n
ctio
n
,
t
h
e
f
ir
s
t
o
n
e
h
ad
7
n
o
d
es
w
h
i
le
t
h
e
s
ec
o
n
d
h
id
d
en
la
y
er
co
n
s
is
ted
o
f
5
n
o
d
es
an
d
t
h
e
o
u
tp
u
t
la
y
e
r
w
i
th
2
n
e
u
r
o
n
s
,
r
ep
r
esen
ti
n
g
0
f
o
r
b
en
i
g
n
an
d
1
f
o
r
m
ali
g
n
a
n
t
lesi
o
n
s
.
A
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
it
h
m
b
ased
o
n
s
ca
led
co
n
j
u
g
ate
o
p
ti
m
izat
io
n
tech
n
iq
u
e
w
a
s
u
s
ed
to
m
o
d
el
M
L
P
f
o
r
o
u
r
d
ataset.
T
o
g
et
t
h
e
o
p
ti
m
u
m
n
e
u
r
al
n
et
w
o
r
k
s
tr
u
c
tu
r
e,
a
co
n
s
id
er
ab
le
n
u
m
b
er
o
f
n
eu
r
al
n
et
w
o
r
k
s
h
av
e
b
ee
n
s
i
m
u
lated
b
y
c
h
an
g
i
n
g
th
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
,
h
id
d
en
n
o
d
es,
iter
atio
n
s
an
d
lear
n
in
g
r
ates.
W
h
er
ea
s
th
e
f
e
ed
f
o
r
w
ar
d
to
p
o
lo
g
y
o
f
R
B
F
n
et
w
o
r
k
d
ev
elo
p
ed
f
o
r
th
is
w
o
r
k
w
a
s
co
m
p
o
s
ed
o
f
3
lay
er
s
,
i
n
p
u
t
la
y
er
w
it
h
th
e
9
in
p
u
t
ele
m
en
ts
,
a
s
in
g
le
h
id
d
en
la
y
er
h
av
i
n
g
a
n
o
n
li
n
e
ar
R
B
F
ac
tiv
atio
n
f
u
n
ctio
n
w
it
h
9
n
eu
r
o
n
s
f
u
ll
y
in
ter
co
n
n
ec
ted
to
th
e
o
u
tp
u
t
la
y
er
u
n
it
s
an
d
a
lin
e
ar
o
u
tp
u
t
la
y
er
w
ith
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
o
mp
a
r
a
tive
s
tu
d
y
o
f lo
g
is
tic
r
eg
r
ess
io
n
a
n
d
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
ks o
n
…
(
Yo
u
s
r
a
A
b
d
u
la
z
iz
Mo
h
a
mme
d
)
1117
ele
m
e
n
ts
.
T
h
e
er
r
o
r
f
u
n
ctio
n
E
u
s
ed
to
in
d
ex
t
h
e
lear
n
i
n
g
e
f
f
icien
c
y
o
f
b
o
th
n
e
u
r
al
n
et
w
o
r
k
s
w
as
t
h
e
S
u
m
o
f
Sq
u
ar
ed
E
r
r
o
r
(
SS
E
)
cr
iter
io
n
f
u
n
ctio
n
w
h
ic
h
h
ad
to
b
e
m
i
n
i
m
ized
o
v
er
t
h
e
g
i
v
en
tr
ain
i
n
g
s
et.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
NN
m
o
d
el
s
w
a
s
d
eter
m
in
ed
b
y
d
iv
id
i
n
g
th
e
d
ataset
in
to
t
w
o
s
ep
ar
ate
s
ets
7
0
%
o
f
s
a
m
p
les
f
o
r
th
e
tr
ain
in
g
an
d
3
0
% f
o
r
th
e
v
alid
atio
n
.
Af
ter
t
h
e
n
et
w
o
r
k
s
h
ad
b
ee
n
tr
ain
ed
p
er
f
ec
tl
y
u
s
i
n
g
t
h
e
tr
a
in
i
n
g
d
ata,
ea
ch
n
et
w
o
r
k
w
as
test
ed
b
y
p
r
esen
tin
g
t
h
e
test
in
g
s
et
to
t
h
e
tr
ain
ed
n
et
w
o
r
k
a
n
d
a
d
iag
n
o
s
tic
o
u
tp
u
t
v
ec
to
r
o
f
0
'
s
a
n
d
1
'
s
w
a
s
g
e
n
er
ated
.
Fig
u
r
e
1
.
Mu
ltil
a
y
er
f
ee
d
f
o
r
w
ar
d
ML
P
Fig
u
r
e
2
.
R
ad
ial
b
asis
f
u
n
ctio
n
NN
3
.
4
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n
T
h
e
w
id
el
y
u
s
ed
m
etr
ic
in
c
l
ass
i
f
icatio
n
p
r
o
ce
s
s
is
ac
c
u
r
ac
y
[
2
1
,
2
4
,
2
5
]
.
I
t
is
th
e
r
ate
o
f
co
r
r
ec
tly
class
i
f
ied
te
s
t
s
a
m
p
les
[
2
1
,
2
5
]
.
Sen
s
iti
v
it
y
i
s
t
h
e
ab
ilit
y
o
f
a
m
o
d
el
to
co
r
r
ec
tl
y
id
e
n
ti
f
y
tr
u
e
p
o
s
i
tiv
e
in
s
ta
n
ce
s
a
n
d
is
ca
lled
tr
u
e
p
o
s
itiv
e
r
ate
w
h
er
ea
s
s
p
ec
if
ic
it
y
i
s
t
h
e
ab
ili
t
y
o
f
th
e
m
o
d
el
o
r
test
to
co
r
r
ec
tl
y
id
e
n
ti
f
y
t
h
e
tr
u
e
n
eg
a
tiv
e
i
n
s
ta
n
ce
s
an
d
is
ca
lled
tr
u
e
n
eg
at
iv
e
r
ate.
T
h
e
A
UC
(
ar
ea
u
n
d
er
R
ec
eiv
er
Op
er
atin
g
C
u
r
v
e
)
w
a
s
also
u
s
ed
in
t
h
e
ev
alu
a
tio
n
o
f
m
o
d
els
p
er
f
o
r
m
an
ce
[2
6
].
T
w
o
m
o
d
els
w
er
e
b
u
ilt
an
d
ev
a
lu
ated
u
s
i
n
g
m
etr
ic
s
in
d
icate
d
b
y
(
9
)
-
(
13
)
an
d
co
n
f
u
s
io
n
m
atr
i
x
s
h
o
w
n
b
elo
w
,
(
9
)
T
P
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
p
o
s
itiv
e
s
a
m
p
le
s
cla
s
s
i
f
ied
co
r
r
ec
tl
y
a
n
d
T
N
is
t
h
e
n
u
m
b
er
o
f
n
e
g
ativ
e
s
a
m
p
les
co
r
r
ec
tl
y
clas
s
if
ied
.
F
N
is
th
e
n
u
m
b
er
o
f
p
o
s
iti
v
e
s
a
m
p
les
in
co
r
r
ec
tl
y
clas
s
i
f
ied
a
s
n
e
g
ati
v
e.
FP
i
s
t
h
e
n
u
m
b
er
o
f
n
e
g
ati
v
e
s
a
m
p
les
i
n
co
r
r
ec
tly
cla
s
s
i
f
ied
as p
o
s
iti
v
e
[2
7
].
(
1
0
)
(
1
1
)
(
1
2
)
W
h
er
e,
T
P
r
ate
is
s
en
s
iti
v
it
y
a
n
d
(
1
3
)
C
o
n
f
u
s
io
n
m
atr
i
x
p
r
e
d
i
c
t
e
d
c
l
a
ss
A
c
t
u
a
l
c
l
a
ss
B
e
n
i
g
n
(
0
)
M
a
l
i
g
n
a
n
t
(
1
)
B
e
n
i
g
n
(
0
)
TN
FP
M
a
l
i
g
n
a
n
t
(
1
)
FN
TP
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
13
-
11
20
1118
4.
RE
SU
L
T
S
I
n
th
is
s
t
u
d
y
,
d
if
f
e
r
en
t
m
o
d
e
ls
w
e
r
e
s
et
u
s
in
g
I
B
M
S
PS
S
s
ta
t
is
t
i
cs
1
9
s
o
f
tw
ar
e
an
d
t
h
e
p
e
r
f
o
r
m
an
c
e
o
f
t
h
e
c
l
as
s
i
f
i
e
r
s
w
as
c
o
m
p
a
r
e
d
.
T
h
e
b
r
e
a
s
t
c
an
c
e
r
d
a
t
as
e
t
u
s
e
d
w
as
o
b
t
a
in
e
d
f
r
o
m
UC
I
-
M
a
c
h
in
e
L
e
a
r
n
in
g
r
e
p
o
s
i
t
o
r
y
,
a
n
d
w
as
f
e
d
t
o
o
u
r
L
o
g
is
t
i
c
-
r
eg
r
ess
i
o
n
m
o
d
e
ls
,
ML
P,
a
n
d
R
B
F
n
eu
r
a
l
n
e
t
w
o
r
k
s
.
E
a
c
h
c
l
ass
if
i
e
r
w
as
w
el
l
t
r
a
in
e
d
w
ith
th
e
d
a
t
as
e
t
a
n
d
a
M
o
d
e
l
i
s
s
e
t
a
n
d
v
al
i
d
a
t
e
d
w
ith
t
es
t
s
am
p
l
es
,
th
en
r
esu
l
ts
w
e
r
e
o
b
t
a
in
e
d
.
Fro
m
T
ab
le
1
,
w
e
ca
n
s
ee
t
h
at
clu
m
p
t
h
ic
k
n
e
s
s
,
m
ar
g
i
n
al
ad
h
esio
n
,
b
ar
e
n
u
clei,
an
d
b
la
n
d
c
h
r
o
m
ati
n
h
av
e
p
-
v
al
u
es
<0
.
0
5
w
h
ich
m
ea
n
s
th
at
t
h
ese
ar
e
s
i
g
n
i
f
ica
n
t
p
r
ed
icto
r
s
o
f
m
ali
g
n
an
c
y
in
th
e
s
et
m
o
d
el
.
O
n
t
h
e
o
th
er
h
a
n
d
,
T
ab
le
2
s
h
o
w
s
th
e
r
ed
u
ce
d
m
o
d
el
co
ef
f
icie
n
ts
w
h
ic
h
w
er
e
ca
lc
u
lated
f
r
o
m
m
o
d
el
tr
ain
i
n
g
u
s
i
n
g
th
e
tr
ai
n
in
g
s
a
m
p
les b
y
t
h
e
s
te
p
w
is
e
m
et
h
o
d
.
Fo
r
th
e
n
e
u
r
al
n
e
t
w
o
r
k
,
b
o
th
ML
P
an
d
R
B
F
m
o
d
els
h
as
s
h
o
w
n
a
co
n
s
id
er
ab
le
i
m
p
r
o
v
e
m
en
t
i
n
al
l
p
er
f
o
r
m
a
n
ce
m
etr
ic
s
t
h
a
n
t
h
o
s
e
s
co
r
ed
b
y
lo
g
is
t
ic
r
e
g
r
ess
io
n
m
o
d
els,
an
d
R
B
F
N
N
h
as
p
r
ec
ed
ed
all
th
e
o
th
er
m
o
d
el
s
d
ev
elo
p
ed
in
th
i
s
w
o
r
k
w
it
h
h
i
g
h
e
s
t c
o
r
r
ec
t c
lass
if
ic
atio
n
r
ate
o
f
9
5
.
4
%,
s
e
n
s
it
iv
i
t
y
o
f
9
8
.
5
%,
A
U
C
o
f
9
6
.
1
2
5
%,
ex
ce
p
t
f
o
r
s
p
ec
i
f
ici
t
y
w
h
ic
h
w
as
9
3
%
t
h
e
s
a
m
e
f
o
r
b
o
th
M
L
P
an
d
R
B
F.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
d
ev
elo
p
ed
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
s
an
d
n
e
u
r
al
n
et
w
o
r
k
s
i
s
co
m
p
ar
ed
in
T
a
b
le
3
a
n
d
F
ig
u
r
e
3
o
n
test
i
n
g
s
a
m
p
les
i
n
ter
m
s
o
f
p
er
ce
n
ta
g
e
o
f
co
r
r
ec
t
class
i
f
icatio
n
r
ate
(
ac
cu
r
ac
y
)
,
s
en
s
iti
v
it
y
,
s
p
e
cif
icit
y
,
an
d
ar
ea
s
u
n
d
er
R
O
C
cu
r
v
e
A
U
C
.
T
ab
le
1
.
P
ar
am
eter
esti
m
atio
n
o
f
th
e
f
u
l
l
L
R
m
o
d
el
u
s
i
n
g
tr
ain
in
g
s
a
m
p
le
V
a
r
i
a
b
l
e
C
o
e
f
f
i
c
i
e
n
t
e
st
i
ma
t
e
S
t
a
n
d
a
r
d
e
r
r
o
r
W
a
l
d
S
i
g
.
c
l
u
mp
_
t
h
i
c
k
n
e
ss
.
5
8
6
.
1
8
0
1
0
.
6
4
8
.
0
0
1
*
u
n
i
f
o
r
mi
t
y
_
o
f
_
c
e
l
l
_
si
z
e
.
2
1
8
.
2
3
8
.
8
3
8
.
3
6
0
u
n
i
f
o
r
mi
t
y
_
o
f
_
c
e
l
l
_
sh
a
p
e
.
1
5
9
.
2
6
0
.
3
7
4
.
5
4
1
marg
i
n
a
l
_
a
d
h
e
si
o
n
.
3
0
4
.
1
3
0
5
.
4
7
6
.
0
1
9
*
si
n
g
l
e
_
e
p
i
t
h
i
l
i
a
l
_
c
e
l
l
_
si
z
e
-
.
1
1
0
.
2
4
3
.
2
0
5
.
6
5
0
b
a
r
e
_
n
u
c
l
e
i
.
3
9
4
.
1
0
5
1
3
.
9
6
3
.
0
0
0
*
b
l
a
n
d
_
c
h
r
o
mat
i
n
.
4
8
3
.
2
0
4
5
.
5
8
9
.
0
1
8
*
n
o
r
mal
_
n
u
c
l
e
o
l
i
.
1
1
5
.
1
3
7
.
7
0
8
.
4
0
0
me
t
o
si
s
.
4
8
7
.
4
7
7
1
.
0
4
2
.
3
0
7
C
o
n
st
a
n
t
-
1
0
.
1
1
2
1
.
4
6
0
4
7
.
9
7
3
.
0
0
0
*
si
g
n
i
f
i
c
a
n
t
a
t
l
e
v
e
l
o
f
0
.
0
5
T
ab
le
2
.
P
ar
am
eter
esti
m
atio
n
o
f
th
e
r
ed
u
ce
d
L
R
m
o
d
el
u
s
i
n
g
th
e
tr
ai
n
i
n
g
s
a
m
p
le
s
.
V
a
r
i
a
b
l
e
C
o
e
f
f
i
c
i
e
n
t
e
st
i
ma
t
e
S
t
a
n
d
a
r
d
e
r
r
o
r
W
a
l
d
S
i
g
.
c
l
u
mp
_
t
h
i
c
k
n
e
ss
.
6
2
7
.
1
7
2
1
3
.
3
2
3
.
0
0
0
u
n
i
f
o
r
mi
t
y
_
o
f
_
c
e
l
l
_
si
z
e
.
3
7
6
.
1
4
9
6
.
4
0
9
.
0
1
1
marg
i
n
a
l
_
a
d
h
e
si
o
n
.
2
8
2
.
1
2
2
5
.
3
2
0
.
0
2
1
b
a
r
e
_
n
u
c
l
e
i
.
3
9
6
.
0
9
9
1
6
.
0
2
1
.
0
0
0
b
l
a
n
d
_
c
h
r
o
mat
i
n
.
5
6
6
.
1
9
3
8
.
6
4
3
.
0
0
3
C
o
n
st
a
n
t
-
9
.
9
1
1
1
.
3
1
2
5
7
.
0
6
4
.
0
0
0
*
si
g
n
i
f
i
c
a
n
t
a
t
l
e
v
e
l
o
f
0
.
0
5
T
ab
le
3
.
C
o
m
p
ar
ativ
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
f
o
u
r
m
o
d
els o
n
v
a
l
id
atio
n
s
a
m
p
le
s
M
o
d
e
l
F
u
l
l
L
R
mo
d
e
l
R
e
d
u
c
e
d
L
R
mo
d
e
l
M
L
P
N
N
R
B
F
N
N
S
e
n
si
t
i
v
i
t
y
%
6
8
.
7
5
6
4
.
1
9
5
.
1
9
8
.
5
S
p
e
c
i
f
i
c
i
t
y
%
8
3
.
5
3
8
5
.
8
8
9
3
.
8
9
3
.
8
A
c
c
u
r
a
c
y
%
7
4
.
7
7
4
.
0
3
9
4
.
2
9
5
.
4
A
U
C
%
7
6
.
1
7
4
.
9
7
9
4
.
4
5
9
6
.
1
2
5
Fig
u
r
e
3
.
C
o
m
p
ar
is
o
n
o
f
m
o
d
els p
er
f
o
r
m
an
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
C
o
mp
a
r
a
tive
s
tu
d
y
o
f lo
g
is
tic
r
eg
r
ess
io
n
a
n
d
a
r
tifi
cia
l n
eu
r
a
l n
etw
o
r
ks o
n
…
(
Yo
u
s
r
a
A
b
d
u
la
z
iz
Mo
h
a
mme
d
)
1119
5.
DIS
CU
SS
I
O
N
A
N
N
an
d
L
R
ar
e
w
id
el
y
u
s
e
d
f
o
r
task
s
o
f
p
r
ed
ictio
n
o
r
class
i
f
icatio
n
.
I
n
t
h
is
w
o
r
k
,
co
m
p
ar
i
s
o
n
o
f
th
e
f
o
u
r
m
o
d
el
s
d
ev
elo
p
ed
w
a
s
b
ased
o
n
t
h
e
v
al
id
atio
n
d
ata
s
et
af
ter
th
e
m
o
d
els
h
ad
b
ee
n
s
u
f
f
icie
n
tl
y
tr
ain
ed
w
it
h
th
e
tr
ain
in
g
d
ata
to
a
s
s
u
r
e
w
h
et
h
er
t
h
e
o
u
tp
u
t
o
f
t
h
e
s
e
m
o
d
el
s
w
i
ll
p
r
ed
ict
f
u
t
u
r
e
s
a
m
p
les
p
r
ec
is
e
l
y
.
T
h
e
f
ir
s
t
m
o
d
el
b
u
i
lt
w
as
lo
g
i
s
tic
r
eg
r
ess
io
n
f
u
ll
m
o
d
el
i
n
cl
u
d
in
g
all
th
e
9
f
ea
t
u
r
es
an
d
th
e
s
e
co
n
d
m
o
d
el
w
as
t
h
e
r
ed
u
ce
d
m
o
d
el
u
s
in
g
t
h
e
s
tep
w
i
s
e
m
et
h
o
d
w
h
er
e
t
h
e
v
ar
ia
b
les
w
it
h
t
h
e
lar
g
e
s
t
p
-
v
al
u
e
h
as
b
ee
n
r
e
m
o
v
ed
k
ee
p
in
g
t
h
e
s
i
g
n
if
ica
n
t
v
ar
iab
les
o
n
l
y
,
h
o
w
ev
er
n
o
n
e
o
f
t
h
e
m
etr
ics
u
s
ed
w
as
i
m
p
r
o
v
ed
b
y
th
e
r
ed
u
ce
d
m
o
d
el
ex
ce
p
t th
e
s
p
ec
i
f
icit
y
as
s
h
o
wn
in
T
ab
le
3
an
d
Fig
u
r
e
3.
T
h
e
r
esu
lt
an
al
y
s
is
o
f
o
u
r
s
t
u
d
y
s
h
o
w
ed
t
h
at
t
h
e
ab
ilit
y
o
f
R
B
F
NN
to
d
iag
n
o
s
e
b
r
ea
s
t
ca
n
ce
r
is
s
u
p
er
io
r
to
B
in
ar
y
L
o
g
is
tic
R
eg
r
ess
io
n
m
o
d
el
s
(
b
o
th
f
u
ll
a
n
d
r
ed
u
ce
d
)
an
d
to
M
L
P
ac
h
iev
i
n
g
h
i
g
h
est
a
n
d
m
o
s
t
ac
c
u
r
ate
r
es
u
lt
s
w
h
er
e
th
e
ac
c
u
r
ac
y
o
f
t
h
e
R
B
F
N
N
m
o
d
el
w
a
s
9
5
.
4
%
an
d
a
s
en
s
it
iv
i
t
y
o
f
9
8
.
5
%
f
o
llo
w
ed
b
y
M
L
P
.
W
h
ile
lo
g
i
s
t
ic
r
eg
r
es
s
io
n
m
et
h
o
d
s
h
o
w
e
d
m
u
c
h
les
s
ac
cu
r
ac
y
(
7
4
.
7
%
f
o
r
f
u
ll
m
o
d
el
an
d
7
4
.
0
3
%
f
o
r
r
ed
u
ce
d
)
,
s
en
s
iti
v
i
t
y
(
6
8
.
7
5
%
f
o
r
f
u
ll
m
o
d
el
an
d
6
4
.
1
%
f
o
r
r
e
d
u
ce
d
)
,
s
p
ec
if
icit
y
(
8
3
.
5
3
%
f
o
r
f
u
ll
m
o
d
el
a
n
d
8
5
.
3
3
%
f
o
r
r
ed
u
ce
d
)
,
an
d
A
U
C
(
7
6
.
1
%
f
o
r
f
u
ll
m
o
d
el
a
n
d
7
4
.
7
9
%
f
o
r
r
ed
u
ce
d
)
,
in
co
m
p
ar
is
o
n
w
it
h
n
eu
r
al
n
et
w
o
r
k
s
.
6.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
r
ep
r
esen
ts
a
co
m
p
ar
i
s
o
n
o
f
t
h
e
d
ia
g
n
o
s
in
g
p
er
f
o
r
m
an
ce
o
f
t
w
o
d
if
f
er
e
n
t
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
w
h
ic
h
ar
e
lo
g
is
tic
r
eg
r
es
s
io
n
a
n
d
n
e
u
r
al
n
et
w
o
r
k
s
i
n
th
e
p
r
o
g
n
o
s
i
s
o
f
b
r
ea
s
t
tu
m
o
r
s
w
ea
t
h
er
m
ali
g
n
a
n
t
o
r
b
en
i
g
n
u
s
i
n
g
t
h
e
b
r
ea
s
t
-
ca
n
ce
r
-
W
is
c
o
n
s
i
n
.
d
ata
f
i
le
.
T
h
e
d
iag
n
o
s
i
n
g
p
er
f
o
r
m
a
n
ce
o
f
t
w
o
t
y
p
e
s
o
f
ar
tif
icial
n
eu
r
al
n
et
w
o
r
k
s
an
d
b
in
ar
y
lo
g
i
s
tic
r
eg
r
ess
io
n
th
r
o
u
g
h
th
e
d
if
f
er
en
t
m
o
d
els
th
at
w
er
e
b
u
ilt,
w
as
co
m
p
ar
ed
b
ased
o
n
s
en
s
iti
v
it
y
,
s
p
ec
i
f
icit
y
,
A
U
C
,
an
d
ac
cu
r
ac
y
o
r
C
C
R
cr
iter
ia.
T
h
e
r
esu
lts
s
h
o
w
ed
th
at
u
s
i
n
g
ANN
i
n
p
r
ed
ictiv
e
an
al
y
s
is
in
o
n
co
lo
g
y
i
s
m
o
r
e
p
o
w
er
f
u
l
t
h
an
lo
g
is
tic
r
e
g
r
ess
i
o
n
alg
o
r
ith
m
,
R
B
F
o
u
tp
er
f
o
r
m
s
ML
P
a
n
d
lo
g
is
ti
c
r
eg
r
ess
io
n
f
o
r
all
m
etr
ic
s
.
T
h
e
s
en
s
i
tiv
i
t
y
C
C
R
,
AUC
v
alu
es
f
o
r
R
B
F
o
n
test
i
n
g
d
ata
w
er
e
th
e
h
ig
h
e
s
t.
T
h
e
f
in
d
in
g
s
i
n
d
icate
th
at
t
h
is
s
tu
d
y
m
ig
h
t
b
e
h
elp
f
u
l
in
t
h
e
d
iag
n
o
s
i
s
o
f
b
r
ea
s
t
tu
m
o
r
s
.
Fo
r
F
u
t
u
r
e
w
o
r
k
o
th
er
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
it
h
m
c
an
b
e
e
x
p
er
i
m
e
n
ted
or
h
y
b
r
id
alg
o
r
ith
m
w
h
ic
h
is
a
co
m
b
in
a
tio
n
o
f
e
x
i
s
ti
n
g
t
wo
o
r
m
o
r
e
al
g
o
r
ith
m
s
ca
n
b
e
ap
p
lied
to
cr
ea
te
a
p
r
ed
ictiv
e
m
o
d
el
w
h
ic
h
ca
n
p
r
ed
ict
w
it
h
h
i
g
h
er
ac
cu
r
ac
y
.
Oth
er
t
y
p
e
s
o
f
n
e
u
r
al
n
et
w
o
r
k
s
s
u
ch
a
s
co
n
v
o
lu
t
io
n
al
n
eu
r
al
n
et
w
o
r
k
n
et
w
o
r
k
s
C
NN
ca
n
b
e
i
m
p
le
m
e
n
ted
,
o
th
er
class
if
ier
s
s
u
ch
a
s
m
u
ltip
le
lo
g
is
t
ic
r
e
g
r
ess
io
n
ca
n
b
e
test
e
d
.
RE
F
E
R
E
NC
E
S
[1
]
NA
.
A
l
wa
n
,
"
b
re
a
st
c
a
n
c
e
r
a
m
o
n
g
iraq
i
w
o
m
e
n
:
P
re
li
m
in
a
r
y
f
in
d
in
g
s
f
ro
m
a
re
g
io
n
a
l
c
o
m
p
a
ra
ti
v
e
b
re
a
st
c
a
n
c
e
r
re
se
a
rc
h
p
ro
jec
t
,
"
J
o
u
rn
a
l
o
f
g
lo
b
a
l
o
n
c
o
l
o
g
y
,
v
o
l.
2
,
no.
5
,
p
p
.
2
5
5
,
2
0
1
6
.
[2
]
Ira
q
i
Ca
n
c
e
r
Bo
a
rd
.
Re
su
l
ts
o
f
th
e
Ira
q
i
Ca
n
c
e
r
Re
g
istr
y
Ba
g
h
d
a
d
,
Ira
q
,
Ira
q
i
Ca
n
c
e
r
Re
g
istr
y
Ce
n
t
e
r,
M
in
istry
o
f
He
a
lt
h
,
2
0
1
5
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
m
o
h
.
g
o
v
.
iq
/
u
p
lo
a
d
/
u
p
f
il
e
/ar/8
3
3
.
[
A
c
c
e
ss
e
d
o
n
Ja
n
27
.
2
0
2
0
.
[3
]
M
.
Ra
th
i,
A
.
K.
S
in
g
h
,
"
Bre
a
st
c
a
n
c
e
r
p
re
d
ictio
n
u
sin
g
Na
ïv
e
b
a
y
e
s
c
las
si
f
ier
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
&
S
y
ste
ms
,
v
o
l.
1
,
n
o
.
2
,
p
p
.
77
-
8
0
,
2
0
1
2
.
[4
]
JA
Cru
z
,
DS
W
ish
a
rt,
"
A
p
p
li
c
a
ti
o
n
s
o
f
m
a
c
h
in
e
lea
rn
in
g
i
n
c
a
n
c
e
r
p
re
d
icti
o
n
a
n
d
p
r
o
g
n
o
sis
,
"
Ca
n
c
e
r
In
fo
rm
a
ti
c
s
.
v
o
l.
2
,
p
p
.
2
-
21
,
2
0
0
6
.
[5
]
Ro
n
n
y
G
u
n
n
a
rss
o
n
,
“
L
o
g
isti
c
re
g
re
ss
io
n
,”
S
c
ien
c
e
Ne
two
rk
T
V
,
F
i
rst
p
u
b
l
ish
e
d
Ju
n
e
2
2
,
2
0
1
4
,
L
a
st
re
v
ise
d
A
u
g
u
st
3
0
,
2
0
1
9
.
h
tt
p
s:/
/sc
ien
c
e
-
n
e
tw
o
rk
.
tv
/l
o
g
isti
c
-
re
g
re
ss
io
n
/
,
[
A
c
c
e
ss
e
d
on
S
e
p
2
4
.
2
0
1
9
.
[6
]
DW
Ho
s
m
e
r,
S
.
L
e
m
e
sh
o
w
,
Ap
p
l
ied
lo
g
isti
c
re
g
re
ss
io
n
,
Ne
w
Yo
rk
:
W
il
e
y
;
1
9
8
9
.
[7
]
M
.
G
Ka
n
o
ji
a
,
S
.
A
b
ra
h
a
m
,
"
Bre
a
st
c
a
n
c
e
r
d
e
tec
ti
o
n
u
sin
g
RBF
n
e
u
ra
l
n
e
tw
o
rk
,
"
in
2
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
n
tem
p
o
ra
ry
Co
m
p
u
t
in
g
a
n
d
In
fo
rm
a
ti
c
s (
IC3
I)
2
0
1
6
,
p
p
.
3
6
3
-
3
6
8
,
2
0
1
6
.
[8
]
Y
Ha
m
a
d
,
K
S
i
m
o
n
o
v
,
&
M
.
B.
Na
e
e
m
,
"
Br
e
a
st
c
a
n
c
e
r
d
e
te
c
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
,
"
In
1
st A
n
n
u
a
l
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
fo
rm
a
ti
o
n
a
n
d
S
c
ien
c
e
s (
Ai
CIS
)
,
p
p
.
5
1
-
5
7
,
2
0
1
8
.
[9
]
M
M
u
sta
f
a
,
e
t
a
l.
,
"
M
a
m
m
o
g
ra
p
h
y
i
m
a
g
e
s
e
g
m
e
n
tatio
n
:
Ch
a
n
-
Ve
se
a
c
t
iv
e
c
o
n
to
u
r
a
n
d
lo
c
a
li
se
d
a
c
ti
v
e
c
o
n
to
u
r
a
p
p
ro
a
c
h
"
,
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
5
,
n
o
.
3
,
pp
.
5
7
7
-
5
8
8
,
2
0
1
7
.
[1
0
]
M
.
F
.
A
k
,
"
A
Co
m
p
a
r
a
ti
v
e
a
n
a
l
y
sis
o
f
b
re
a
st
c
a
n
c
e
r
d
e
tec
ti
o
n
a
n
d
d
iag
n
o
sis
u
sin
g
d
a
ta
v
isu
a
li
z
a
ti
o
n
a
n
d
m
a
c
h
in
e
lea
rn
in
g
a
p
p
l
ica
ti
o
n
s"
,
He
a
lt
h
c
a
r
e
,
v
o
l.
8
,
n
o
.
2
,
p
.
1
1
1
,
2
0
2
0
.
[1
1
]
J
S
u
lt
a
n
a
,
a
n
d
A
.
K.
Jila
n
i,
"
P
re
d
icti
n
g
b
re
a
st
c
a
n
c
e
r
u
sin
g
lo
g
isti
c
re
g
re
ss
io
n
a
n
d
m
u
lt
i
-
c
las
s
c
las
si
f
ier
s
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
&
T
e
c
h
n
o
lo
g
y
,
v
o
l.
7
,
n
o
.
(4
.
2
0
)
,
pp
.
2
2
-
2
6
,
2
0
1
8
.
[1
2
]
M
.
A
K
a
h
y
a
,
"
Clas
si
f
ic
a
ti
o
n
e
n
h
a
n
c
e
m
e
n
t
o
f
b
re
a
st
c
a
n
c
e
r
h
isto
p
a
th
o
lo
g
ica
l
im
a
g
e
u
sin
g
p
e
n
a
li
z
e
d
lo
g
isti
c
re
g
re
ss
io
n
,
"
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
13
,
n
o
.
1
,
pp
.
4
0
5
-
4
1
0
,
2
0
1
9
.
[1
3
]
D
Du
a
,
C
G
ra
ff
,
“
UCI
M
a
c
h
in
e
L
e
a
rn
in
g
Re
p
o
sito
ry
”
.
Irv
in
e
,
CA:
Un
iv
e
rsity
o
f
Ca
li
f
o
rn
ia,
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
o
n
a
n
d
Co
m
p
u
ter S
c
ie
n
c
e
,
2
0
1
9
.
[
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
.
[1
4
]
F
L
e
is
c
h
,
E.
Dim
it
riad
o
u
,
“
M
a
c
h
in
e
lea
rn
in
g
b
e
n
c
h
m
a
rk
p
ro
b
lem
s
,
”
Cra
n
.
r
-
p
ro
jec
t
,
2
0
1
5
.
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/cra
n
.
r
-
p
r
o
jec
t.
o
rg
/w
e
b
/p
a
c
k
a
g
e
s/
m
lb
e
n
c
h
/m
lb
e
n
c
h
.
p
d
f
.
[
A
c
c
e
ss
e
d
on
S
e
p
24
.
2
0
1
9
]
[1
5
]
W
H
W
o
lb
e
rg
,
OL
M
a
n
g
a
s
a
rian
,
"
M
u
lt
isu
rf
a
c
e
m
e
th
o
d
o
f
p
a
tt
e
r
n
s
e
p
a
ra
ti
o
n
f
o
r
m
e
d
ica
l
d
iag
n
o
sis
a
p
p
li
e
d
t
o
b
re
a
st
c
y
to
lo
g
y
,
"
in
Pro
c
e
e
d
in
g
s o
f
th
e
n
a
ti
o
n
a
l
a
c
a
d
e
my
o
f
sc
ien
c
e
s,
v
o
l
.
8
7
,
n
o
.
2
3
,
p
p
.
9
1
9
3
-
9
1
9
6
,
1
9
9
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
2
0
2
1
:
1
1
13
-
11
20
1120
[1
6
]
H.
Ka
n
g
,
"
T
h
e
p
re
v
e
n
ti
o
n
a
n
d
h
a
n
d
li
n
g
o
f
th
e
m
i
ss
in
g
d
a
ta,"
Ko
re
a
n
jo
u
rn
a
l
o
f
a
n
e
sth
e
si
o
lo
g
y
,
"
v
o
l.
6
4
,
no.
5
,
p
p
.
402
-
4
0
6
,
2
0
1
3
.
d
o
i:
1
0
.
4
0
9
7
/k
jae
.
2
0
1
3
.
6
4
.
5
.
4
0
2
.
[1
7
]
J
S
c
h
w
a
rz
,
p
.
He
id
i
Bru
d
e
re
r
E
n
z
ler,
“
Re
se
a
rc
h
m
e
th
o
d
o
lo
g
y
:
T
o
o
ls;
A
p
p
li
e
d
d
a
ta
a
n
a
ly
s
is
(
w
it
h
S
P
S
S
)
,”
L
u
rc
e
rn
Un
iv
e
rsit
y
,
2
0
1
4
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
:/
/w
ww
.
sc
h
w
a
r
z
p
a
rtn
e
rs.ch
[
e
x
trac
ted
o
n
S
e
p
3
0
,
2
0
1
9
]
.
[1
8
]
J.
S
h
a
o
,
"
L
in
e
a
r
M
o
d
e
l
S
e
lec
ti
o
n
b
y
Cro
ss
-
V
a
li
d
a
ti
o
n
,
"
J
o
u
rn
a
l
o
f
t
h
e
Ame
ric
a
n
S
ta
ti
stic
a
l
Asso
c
i
a
ti
o
n
,
v
o
l
.
8
8
,
n
o.
4
2
2
,
p
p
.
4
8
6
-
4
9
4
,
1
9
9
3
.
[1
9
]
H.
Yu
su
f
f
,
N.
M
o
h
a
m
a
d
,
U.K.
N
g
a
h
,
A
.
Ya
h
a
y
a
,
"
Br
e
a
st
c
a
n
c
e
r
a
n
a
ly
sis
u
sin
g
lo
g
isti
c
re
g
re
ss
io
n
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Res
e
a
rc
h
a
n
d
Rev
iews
in
A
p
p
li
e
d
S
c
ien
c
e
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
14
-
2
2
,
2
0
1
2
.
[2
0
]
S
.
Ra
n
a
,
H
M
id
i,
S
K
S
a
rk
a
r
,
"
V
a
li
d
a
ti
o
n
a
n
d
p
e
rf
o
rm
a
n
c
e
a
n
a
l
y
sis
o
f
b
in
a
ry
lo
g
isti
c
re
g
r
e
ss
io
n
m
o
d
e
l
,
"
in
Pro
c
e
e
d
in
g
s
o
f
t
h
e
W
S
EA
S
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
En
v
ir
o
n
me
n
t,
me
d
ici
n
e
a
n
d
h
e
a
lt
h
sc
i
e
n
c
e
s
,
P
e
n
a
n
g
,
M
a
la
y
sia
,
p
p
.
51
-
55
,
2
0
1
0
.
[2
1
]
Y.
M
o
h
a
m
m
e
d
,
"
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
b
e
t
w
e
e
n
a
rti
f
ici
a
l
in
telli
g
e
n
c
e
tec
h
n
iq
u
e
s
in
a
n
a
u
to
m
a
ti
c
i
n
f
a
n
t'
s
p
a
in
c
r
y
id
e
n
ti
f
ica
ti
o
n
sy
ste
m
,
"
in
2
0
1
8
1
st
An
n
u
a
l
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
fo
rm
a
ti
o
n
a
n
d
S
c
ien
c
e
s
(
Ai
CIS
)
,
F
a
l
lu
jah
,
Ira
q
,
p
p
.
3
3
-
39
,
2
0
1
8
.
d
o
i
:
1
0
.
1
1
0
9
/A
iCIS
.
2
0
1
8
.
0
0
0
1
9
[2
2
]
J.
P
a
d
m
a
v
a
ti
,
"
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
n
b
re
a
st
c
a
n
c
e
r
p
re
d
ictio
n
u
sin
g
RBF
a
n
d
M
L
P
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ien
ti
fi
c
&
En
g
in
e
e
rin
g
Res
e
a
rc
h
,
v
o
l.
2
,
n
o
.
1
,
p
p
.
1
-
5
,
2
0
1
1
.
[2
3
]
H.
Ja
f
a
rn
e
jad
sa
n
i,
J.
P
ie
p
e
r,
J.
Eh
lers
,
"
A
d
a
p
ti
v
e
c
o
n
tro
l
o
f
a
v
a
riab
le
-
sp
e
e
d
v
a
riab
le
-
p
it
c
h
w
in
d
tu
r
b
in
e
u
si
n
g
ra
d
ial
-
b
a
sis
f
u
n
c
ti
o
n
n
e
u
ra
l
n
e
two
rk
,
"
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
c
o
n
tro
l
sy
ste
ms
tec
h
n
o
l
o
g
y
,
v
o
l.
2
1
,
n
o
.
6
,
p
p
.
2
2
6
4
-
2
2
7
2
,
2
0
1
3
.
d
o
i
:
1
0
.
1
1
0
9
/T
CS
T
.
2
0
1
2
.
2
2
3
7
5
1
8
.
[2
4
]
H S
o
f
ian
,
J
.
T
.
C
M
in
g
,
S
M
u
h
a
m
m
a
d
,
a
n
d
N.
M
No
o
r,
"
Ca
lcif
ica
ti
o
n
d
e
tec
ti
o
n
u
si
n
g
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
a
rc
h
it
e
c
tu
re
s
in
i
n
trav
a
sc
u
lar
u
lt
ra
so
u
n
d
im
a
g
e
,
"
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
17
,
n
o
.
3
,
pp
.
1
3
1
3
-
1
3
2
1
,
2
0
2
0
.
do
i
:
1
0
.
1
1
5
9
1
/
ij
e
e
c
s.v
1
7
.
i3
.
p
p
1
3
1
3
-
1
3
2
1
.
[2
5
]
Y.
A
b
d
u
laz
iz
a
n
d
S
.
M
.
S
.
A
h
m
a
d
,
"
In
f
a
n
t
c
r
y
re
c
o
g
n
it
io
n
sy
ste
m
:
A
c
o
m
p
a
riso
n
o
f
s
y
ste
m
p
e
r
f
o
rm
a
n
c
e
b
a
se
d
o
n
m
e
l
f
re
q
u
e
n
c
y
a
n
d
li
n
e
a
r
p
re
d
icti
o
n
c
e
p
stra
l
c
o
e
ff
icie
n
ts,
"
2
0
1
0
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
fo
rm
a
ti
o
n
Ret
rie
v
a
l
&
Kn
o
wled
g
e
M
a
n
a
g
e
me
n
t
(
CA
M
P)
,
p
p
.
2
6
0
-
2
6
3
,
2
0
1
0
,
d
o
i:
1
0
.
1
1
0
9
/INF
RKM
.
2
0
1
0
.
5
4
6
6
9
0
7
.
[2
6
]
S
M
iri
Ro
sta
m
i,
M
A
h
m
a
d
z
a
d
e
h
,
"
Ex
trac
ti
n
g
p
re
d
icto
r
v
a
riab
les
to
c
o
n
stru
c
t
b
re
a
st ca
n
c
e
r
su
rv
iv
a
b
il
it
y
m
o
d
e
l
w
it
h
c
las
s
i
m
b
a
lan
c
e
p
ro
b
lem
,
"
J
o
u
rn
a
l
o
f
AI
a
n
d
Da
ta
M
in
i
n
g
,
v
o
l.
6
,
n
o
.
2
,
p
p
.
2
6
3
-
2
7
6
,
2
0
1
8
.
doi
:
1
0
.
2
2
0
4
4
/JA
DM.
2
0
1
7
.
5
0
6
1
.
1
6
0
9
.
[2
7
]
R
Ro
sly
,
M
M
a
k
h
tar,
M
.
K
Aw
a
n
g
,
M
.
I
A
w
a
n
g
,
M
.
N.
A
Ra
h
m
a
n
,
a
n
d
H
M
a
h
d
in
,
"
Co
m
p
re
h
e
n
siv
e
stu
d
y
o
n
e
n
se
m
b
le
c
las
si
f
ica
ti
o
n
f
o
r
m
e
d
i
c
a
l
a
p
p
li
c
a
ti
o
n
s
,
"
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
in
e
e
rin
g
&
T
e
c
h
n
o
lo
g
y
,
v
o
l.
7
,
n
o
.
(2
.
1
4
),
p
p
.
1
8
6
-
1
9
0
,
2
0
1
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Yo
u
sr
a
A.A
M
o
h
a
m
m
e
d
,
sh
e
is
c
u
rre
n
tl
y
a
tt
a
c
h
e
d
a
s
Lec
tu
re
r
in
Un
iv
e
rsit
y
o
f
F
a
ll
u
jah
A
n
b
a
r,
Ira
q
.
S
h
e
re
c
e
iv
e
d
h
e
r
B.
En
g
.
in
Co
m
p
u
ters
a
n
d
C
o
n
t
ro
l
E
n
g
in
e
e
rin
g
f
ro
m
Un
iv
e
sit
y
o
f
T
e
c
h
n
o
lo
g
y
Ba
g
h
d
a
d
,
Ira
q
a
n
d
h
e
r
M
a
ste
r
o
f
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
in
Co
m
p
u
ter
s
c
ien
c
e
s
f
ro
m
Un
iv
e
r
sit
y
T
e
n
a
g
a
N
a
sio
n
a
l,
M
a
la
y
sia
(
UN
I
T
EN).
He
r
re
se
a
rc
h
in
tere
st
is
in
th
e
m
a
c
h
in
e
lea
rn
in
g
,
E
-
L
e
a
rn
in
g
,
c
las
si
f
ica
ti
o
n
,
Ne
u
ra
l
Ne
tw
o
rk
s,
si
g
n
a
l
p
r
o
c
e
ss
in
g
a
n
d
i
m
a
g
e
p
ro
c
e
ss
in
g
.
He
r
c
u
rre
n
t
w
o
rk
c
o
n
c
e
n
trate
s o
n
m
e
d
ica
l
d
a
ta an
a
ly
sis
a
n
d
c
las
sif
i
c
a
ti
o
n
i
n
d
e
e
p
lea
rn
in
g
.
E
m
a
n
G
a
d
b
a
n
S
a
le
h
,
Re
c
e
iv
e
d
h
e
r
P
h
.
D.
d
e
g
re
e
in
g
y
n
e
c
o
lo
g
y
a
n
d
o
b
ste
tri
c
s
f
ro
m
Co
u
n
c
il
o
f
A
ra
b
H
e
a
lt
h
M
in
isters
,
c
u
rre
n
tl
y
w
o
rk
s
a
s
a
l
e
c
tu
re
r
in
c
o
ll
e
g
e
o
f
m
e
d
icin
e
,
u
n
iv
e
rsity
o
f
F
a
ll
u
jah
,
Ira
q
.
He
r
re
se
a
rc
h
in
tere
sts in
c
lu
d
e
o
n
c
o
lo
g
y
,
o
b
ste
tri
c
s an
d
g
y
n
e
c
o
lo
g
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.