I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
.
10
, N
o.
1
,
Ma
r
ch
2021
, pp.
184
~
190
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
10
.i
1
.pp
184
-
190
184
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
B
r
e
ast
c
an
c
e
r
p
r
e
d
i
c
t
i
on
m
od
e
l
w
i
t
h
d
e
c
i
si
on
t
r
e
e
an
d
ad
ap
t
i
ve
b
oost
i
n
g
T
s
e
h
ay A
d
m
a
s
s
u
A
s
s
e
gi
e
1
,
R
.
L
ak
s
h
m
i
T
u
la
s
i
2
, N
. K
om
al
K
u
m
ar
3
1
De
partment of Computer Science
,
Faculty
of Comp
uting Te
chnolog
y, AIT
, Aksum University,
Aksum,
Ethiopia
2
Department of Compu
ter Science and Engineering,
R.V.R & J.
C College of En
gineering, Guntur,
India.
3
Department of Compu
ter Science and Engineering,
St. Pete
r’s I
nstitute
of Hi
gher
Educa
tion an
d Rese
arch
, Avad
i,
Chennai,
India
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
D
e
c
25
, 20
19
R
e
vi
s
e
d
O
c
t
1
0, 20
20
A
c
c
e
pt
e
d
J
a
n
4
, 20
21
In
this
study,
breast
cancer
prediction
model
is
proposed
with
decision
t
ree
and
adaptive
boosti
ng
(
A
dboost)
.
Further
more,
an
extensiv
e
experi
mental
evaluatio
n of the
predicti
ve performan
ce of the
proposed
model
is
con
ducted
.
The
study
is
conducted
on
breast
cancer
data
set
collected
form
the
kag
gle
data
repository.
The
dataset
consists
of
569
observation
s
of
whi
ch
the
212
or
37.2
5%
are
benign
or
breast
cancer
negative
and
62.74%
are
malig
nant
or
breast
cancer
positive.
Th
e
class
distribution
shows
that,
the
dataset
is
highly
imbalance
d
and
a
learning
algorithm
such
as
decision
tree
is
biased
to
the
benign
observation
and
results
i
n
poor
performance
on
predicti
ng
the
malignant
observation
.
To
improve
the
performa
nce
of
the
decision
tre
e
on
the
malignant
observation
,
boosting
algorithm
namely,
the
adaptive
boo
sting
is
employed
.
Finall
y,
the
predicti
ve
performance
of
the
decision
tr
ee
and
adaptive
boosti
ng
is
analyzed.
The
analysis
on
predictive
performanc
e
of
the
model
on
the
kaggle
breast
cancer
data
repository
shows
that,
a
daptive
boosting
has
92.53%
accuracy
and
the
accuracy
of
decision
tree
is
8
8.80%,
Overall,
the adabo
ost algorithm pe
rformed
better tha
n decision tr
ee.
K
e
y
w
o
r
d
s
:
A
da
boos
t
B
r
e
a
s
t
c
a
n
c
e
r
B
r
e
a
s
t
c
a
n
c
e
r
pr
e
di
c
ti
on
D
e
c
is
io
n t
r
e
e
M
a
c
hi
ne
l
e
a
r
ni
ng
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
T
s
e
ha
y
A
dm
a
s
s
u A
s
s
e
gi
e
D
e
pa
r
tm
e
nt
of
C
om
put
e
r
S
c
ie
nc
e
, A
ks
um
U
ni
ve
r
s
it
y
1010
A
ks
um
,
E
th
io
pi
a
E
m
a
il
:
ts
e
ha
ya
dm
a
s
s
u2006
@
gm
a
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
B
r
e
a
s
t
c
a
n
c
e
r
i
s
c
a
us
e
d
by a
n a
bnor
m
a
l
gr
ow
th
a
nd
c
e
ll
di
vi
s
io
n i
n t
he
br
e
a
s
t
ti
s
s
ue
s
w
it
hout
c
ont
r
ol
.
T
he
a
bnor
m
a
l
gr
ow
th
of
th
e
c
e
ll
s
is
c
a
ll
e
d
a
tu
m
or
a
nd
r
e
s
ul
ts
in
e
it
he
r
be
ni
gn
(
non
-
can
c
e
r
ous
)
or
m
a
li
gna
n
t
(
c
a
nc
e
r
ous
)
.
I
n r
e
c
e
nt
ye
a
r
s
,
br
e
a
s
t
c
a
nc
e
r
ha
s
be
c
om
e
one
of
t
h
e
de
a
dl
ie
s
t
a
nd e
pi
de
m
ic
di
s
e
a
s
e
s
i
n t
h
e
w
or
ld
[1
-
5]
.
A
li
te
r
a
tu
r
e
r
e
vi
e
w
on
th
e
br
e
a
s
t
c
a
nc
e
r
s
how
s
th
a
t,
br
e
a
s
t
c
a
n
c
e
r
ha
s
be
c
om
e
c
om
m
on
in
w
om
e
n
[
1]
a
nd
c
a
nc
e
r
di
s
e
a
s
e
c
a
s
e
s
a
r
e
e
xpe
c
te
d
to
be
27
m
il
li
on
by
2030
[
2]
.
I
n
th
e
li
te
r
a
tu
r
e
,
di
f
f
e
r
e
nt
m
a
c
hi
ne
le
a
r
ni
ng
m
ode
ls
a
r
e
pr
opos
e
d
a
s
a
s
ol
ut
io
n
in
th
e
r
e
duc
ti
on
of
de
a
th
r
a
te
c
a
us
e
d
by
br
e
a
s
t
c
a
n
c
e
r
w
it
h
c
om
put
e
r
a
s
s
is
te
d
br
e
a
s
t
c
a
nc
e
r
di
a
gno
s
is
s
y
s
te
m
.
B
r
e
a
s
t
c
a
n
c
e
r
is
th
e
s
e
c
ond
m
a
jo
r
c
a
nc
e
r
di
s
e
a
s
e
in
w
om
e
n
in
th
e
w
or
ld
[
3]
.
T
he
di
s
e
a
s
e
i
s
c
om
m
on
in
de
ve
lo
pe
d
c
ount
r
ie
s
in
th
e
pa
s
t
but
is
r
a
pi
dl
y
in
c
r
e
a
s
in
g
in
m
id
dl
e
-
in
c
om
e
a
nd
lo
w
-
in
c
om
e
c
ount
r
ie
s
to
o
.
T
hi
s
s
how
s
t
ha
t,
t
he
c
a
nc
e
r
di
s
e
a
s
e
c
a
s
e
s
a
r
e
i
nc
r
e
a
s
in
g r
a
pi
dl
y a
nd ma
c
hi
ne
-
l
e
a
r
ni
ng a
lg
or
it
hm
s
a
r
e
r
e
qui
r
e
d
f
or
de
c
is
io
n
s
uppor
t
to
r
e
duc
e
th
e
e
pi
de
m
ic
c
a
s
e
s
by
pr
e
di
c
ti
ng
br
e
a
s
t
c
a
nc
e
r
a
s
e
a
r
ly
a
s
pos
s
ib
le
.
T
he
m
a
jo
r
pr
obl
e
m
i
n br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
w
it
h m
a
c
hi
ne
l
e
a
r
ni
ng
is
th
e
i
m
ba
la
nc
e
be
twe
e
n
t
he
be
ni
gn
a
nd ma
li
gna
nt
obs
e
r
v
a
ti
ons
in
br
e
a
s
t
c
a
nc
e
r
da
ta
s
e
t
[
4]
.
B
r
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
in
vol
ve
s
a
bi
na
r
y
c
la
s
s
if
ic
a
ti
on
pr
obl
e
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
B
r
e
as
t
c
anc
e
r
pr
e
di
c
ti
on m
ode
l
w
it
h de
c
is
io
n t
r
e
e
and adapti
v
e
boos
ti
ng
(
T
s
e
hay
A
dm
as
s
u A
s
s
e
gi
e
)
185
w
he
r
e
a
n
obs
e
r
va
ti
on
be
lo
ngs
to
e
it
he
r
m
a
li
gna
nt
or
be
ni
gn
c
la
s
s
.
H
ow
e
ve
r
,
th
e
num
be
r
of
be
ni
gn
obs
e
r
va
ti
ons
is
a
lwa
ys
gr
e
a
te
r
th
a
n
th
e
num
be
r
of
m
a
li
gna
nt
obs
e
r
va
ti
ons
in
th
e
da
ta
s
e
t
a
s
th
e
num
be
r
s
of
non
-
c
a
nc
e
r
ous
pe
opl
e
a
r
e
gr
e
a
te
r
t
ha
n t
he
numbe
r
of
c
a
nc
e
r
ous
pe
opl
e
i
n t
he
r
e
a
l
w
or
ld
. T
he
i
m
ba
la
nc
e
of
obs
e
r
va
ti
on i
n t
he
d
a
ta
s
e
t
c
r
e
a
te
s
a
pr
obl
e
m
to
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
w
hi
c
h
r
e
s
ul
ts
in
in
c
or
r
e
c
t
pr
e
di
c
ti
ons
on
th
e
c
la
s
s
of
in
te
r
e
s
t
w
hi
c
h
is
th
e
m
a
l
ig
na
nt
(
m
in
or
it
y
c
la
s
s
)
.
A
s
m
a
c
hi
ne
l
e
a
r
ni
ng
a
lg
or
it
hm
m
or
e
f
r
e
que
nt
ly
le
a
r
ns
th
e
m
a
jo
r
it
y
c
la
s
s
,
th
e
m
ode
l
a
ls
o
pr
e
di
c
ts
th
e
be
ni
gn
(
m
a
jo
r
it
y
c
la
s
s
)
w
it
h
be
tt
e
r
a
c
c
ur
a
c
y
th
a
n
th
e
m
in
or
it
y
c
la
s
s
.
H
e
nc
e
,
a
s
ta
nda
r
d m
a
c
hi
ne
-
le
a
r
ni
ng mode
l
m
a
ke
s
bi
a
s
e
d
pr
e
di
c
ti
on
to
w
a
r
ds
t
he
m
a
jo
r
it
y c
la
s
s
.
I
n
th
is
r
e
s
e
a
r
c
h,
w
e
ha
ve
pr
opos
e
d
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
m
o
de
l
w
it
h
a
da
pt
iv
e
boos
ti
ng
a
lg
or
it
h
m
to
opt
im
iz
e
th
e
p
r
e
di
c
ti
on
pe
r
f
o
r
m
a
nc
e
of
de
c
is
io
n
t
r
e
e
a
lg
or
i
th
m
due
t
o
bi
a
s
e
d
pr
e
di
c
ti
on
to
w
a
r
ds
be
ni
gn
obs
e
r
va
ti
on.
F
ur
th
e
r
m
or
e
, t
hi
s
s
tu
dy,
in
ve
s
ti
ga
te
s
t
he
a
n
s
w
e
r
s
to
th
e
f
ol
lo
w
in
g r
e
s
e
a
r
c
h que
s
ti
ons
:
1.
H
ow
t
o opti
m
iz
e
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
de
c
is
io
n t
r
e
e
f
or
c
la
s
s
if
ic
a
ti
on of
im
ba
la
nc
e
d br
e
a
s
t
c
a
nc
e
r
?
2.
W
ha
t
is
t
he
pe
r
f
o
r
m
a
nc
e
of
de
c
is
io
n t
r
e
e
an
d
a
da
pt
iv
e
boos
ti
ng
a
lg
or
it
hm
f
or
pr
e
di
c
ti
ng
b
r
e
a
s
t
c
a
nc
e
r
?
3.
W
hi
c
h f
e
a
tu
r
e
(
s
)
in
t
he
br
e
a
s
t
c
a
nc
e
r
da
ta
s
e
t
h
a
s
s
tr
ong r
e
la
ti
o
ns
hi
p t
o t
he
c
la
s
s
f
e
a
tu
r
e
?
2.
L
I
T
R
E
A
T
U
R
E
R
E
V
I
E
W
M
a
ny
r
e
s
e
a
r
c
h
w
or
ks
ha
v
e
be
e
n
c
onduc
te
d
on
br
e
a
s
t
c
a
n
c
e
r
c
la
s
s
if
ic
a
ti
on
.
T
he
r
e
s
e
a
r
c
h
w
or
ks
a
ppl
ie
d
di
f
f
e
r
e
nt
m
a
c
hi
ne
le
a
r
ni
ng
a
lg
or
it
hm
s
f
o
r
de
ve
lo
pi
ng
pr
e
di
c
ti
ve
m
ode
l
f
or
c
la
s
s
if
ic
a
ti
on
of
br
e
a
s
t
c
a
nc
e
r
.
S
om
e
of
t
he
pr
e
vi
ous
r
e
s
e
a
r
c
h w
or
ks
on br
e
a
s
t
c
a
nc
e
r
c
la
s
s
if
ic
a
ti
on [
5
-
25]
a
r
e
di
s
c
us
s
e
d i
n
th
i
s
s
e
c
ti
on. I
n [
5]
, na
ïv
e
ba
ye
s
,
R
B
F
a
nd
J
48
a
lg
or
it
hm
s
a
r
e
a
ppl
ie
d
to
W
is
c
ons
in
br
e
a
s
t
c
a
nc
e
r
da
ta
s
e
t.
T
he
da
ta
s
e
t
c
ons
is
t
s
of
699
obs
e
r
va
ti
ons
a
nd
two
c
la
s
s
e
s
(
m
a
li
gna
nt
a
nd
be
ni
gn)
a
nd
9
f
e
a
tu
r
e
s
.
T
he
e
xpe
r
im
e
nt
a
l
r
e
s
ul
t
of
th
e
s
tu
dy
s
how
s
th
a
t
na
ïv
e
ba
ye
s
a
lg
or
it
hm
pe
r
f
or
m
e
d be
tt
e
r
t
ha
n R
B
F
a
nd J
48
-
d
e
c
is
io
n t
r
e
e
a
lg
or
it
hm
.
I
n
[
6]
,
de
e
p
ne
ur
a
l
ne
twor
k
a
nd
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
is
a
p
pl
ie
d
to
a
n
onl
in
e
br
e
a
s
t
c
a
nc
e
r
da
ta
r
e
pos
it
or
y
c
ol
le
c
te
d
f
r
om
b
r
oa
d
G
D
A
C
f
ir
e
hous
e
a
va
il
a
bl
e
onl
in
e
a
t
ht
tp
s
:/
/g
da
c
.b
r
oa
di
ns
ti
tu
te
.or
g/
.
T
he
a
lg
or
it
hm
s
a
r
e
e
va
lu
a
te
d a
ga
in
s
t
th
e
ir
pr
e
di
c
ti
ve
a
c
c
ur
a
c
y a
nd r
e
s
ul
t
s
how
s
t
ha
t
th
e
hi
gh
e
s
t
a
c
c
ur
a
c
y a
c
hi
e
v
e
d
by
th
e
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
is
69.8%
.
T
he
de
e
p
n
e
ur
a
l
ne
twor
k
pe
r
f
or
m
e
d
lo
w
e
r
th
a
n
th
e
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
.
I
n [
7]
,
th
e
a
ut
hor
s
a
ppl
ie
d s
uppor
t
ve
c
to
r
m
a
c
hi
ne
(
S
V
M
)
, na
ïv
e
ba
ye
s
(
N
B
)
, de
c
i
s
io
n t
r
e
e
(
D
T
)
a
nd
k
-
ne
a
r
e
s
t
ne
ig
hbor
(
K
N
N
)
on
W
is
c
on
s
in
br
e
a
s
t
c
a
nc
e
r
da
ta
s
e
t
a
nd
pr
o
pos
e
d
a
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
m
ode
l
w
it
h
S
V
M
,
N
B
,
D
T
a
nd
K
N
N
.
T
he
da
t
a
r
e
pos
it
or
y
c
ont
a
in
s
699
obs
e
r
va
ti
ons
of
w
hi
c
h
459
a
r
e
be
ni
gn
a
nd
241
a
r
e
m
a
li
gna
nt
.
T
he
c
om
pa
r
a
ti
ve
pe
r
f
or
m
a
nc
e
a
n
a
ly
s
is
on
th
e
e
f
f
ic
ie
nc
y
of
th
e
pr
e
di
c
ti
on
m
ode
ls
s
how
s
th
a
t
S
V
M
ha
s
be
tt
e
r
a
c
c
ur
a
c
y t
ha
n t
he
ot
he
r
a
lg
or
it
hm
s
.
I
n
a
not
he
r
s
tu
dy
[
8]
,
on
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
m
ode
l
is
p
r
o
pos
e
d
by
e
m
pl
oyi
ng
th
r
e
e
m
a
c
hi
ne
-
le
a
r
ni
ng
a
lg
or
it
hm
s
na
m
e
ly
,
li
ne
a
r
r
e
gr
e
s
s
io
n,
de
c
is
io
n
tr
e
e
a
nd
r
a
ndom
f
or
e
s
t.
I
n
th
e
s
tu
dy,
th
e
a
ut
hor
s
a
ppl
ie
d
th
e
s
e
m
a
c
hi
ne
-
le
a
r
ni
ng
a
lg
or
it
hm
s
on
th
e
W
is
c
ons
in
br
e
a
s
t
c
a
nc
e
r
da
ta
r
e
pos
it
or
y.
T
he
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
m
ode
l
is
a
na
ly
z
e
d
a
nd
th
e
r
e
s
ul
t
o
f
a
na
ly
s
is
s
how
s
a
n
a
c
c
ur
a
c
y
of
84.14%
.
T
he
r
e
gr
e
s
s
io
n
a
lg
or
it
hm
is
us
e
d
to
a
na
ly
z
e
th
e
r
e
la
ti
ons
hi
p
be
tw
e
e
n
th
e
a
tt
r
ib
u
te
s
in
th
e
da
ta
r
e
po
s
it
or
y.
I
n
[
9]
,
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
a
lg
or
it
hm
is
a
ppl
ie
d
to
573
ob
s
e
r
va
ti
ons
c
ol
le
c
te
d
f
r
om
m
e
di
c
a
l
r
e
pos
it
or
y.
T
he
a
ut
hor
s
c
om
pa
r
e
d
th
e
pe
r
f
or
m
a
nc
e
of
li
ne
a
r
a
nd
non
-
li
ne
a
r
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
.
T
he
r
e
s
ul
t
of
pe
r
f
or
m
a
nc
e
a
na
ly
s
i
s
s
how
s
th
a
t
li
ne
a
r
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
out
pe
r
f
or
m
e
d t
ha
n t
he
non
-
li
ne
a
r
s
upp
or
t
ve
c
to
r
m
a
c
hi
ne
.
I
n
a
not
he
r
s
tu
dy
[
10]
,
N
B
a
nd
lo
gi
s
ti
c
r
e
gr
e
s
s
io
n
is
a
ppl
ie
d
to
th
e
W
is
c
ons
in
br
e
a
s
t
c
a
nc
e
r
da
ta
r
e
pos
it
or
y.
T
he
da
ta
r
e
pos
it
or
y
c
ont
a
in
s
697
obs
e
r
va
ti
ons
a
nd
11
f
e
a
tu
r
e
s
.
T
he
a
ut
hor
s
c
om
pa
r
e
d
th
e
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
m
ode
l
a
nd
t
he
r
e
s
ul
t
of
pe
r
f
o
r
m
a
nc
e
a
na
ly
s
i
s
s
ho
w
s
th
a
t
th
e
na
ïv
e
ba
ye
s
a
lg
or
it
hm
s
out
pe
r
f
or
m
e
d
th
a
n
th
e
lo
gi
s
ti
c
r
e
gr
e
s
s
io
n
a
lg
or
it
hm
.
I
n
[
11]
,
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
m
od
e
l
is
pr
opos
e
d
by
e
m
pl
oyi
ng
th
e
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
a
lg
or
it
hm
W
is
c
on
s
in
da
ta
r
e
pos
it
or
y.
T
h
e
num
b
e
r
of
obs
e
r
va
ti
ons
us
e
d
in
th
e
da
ta
s
e
t
is
569
a
nd
th
e
num
be
r
of
f
e
a
t
ur
e
s
is
10.
T
h
e
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
m
ode
l
is
e
va
lu
a
te
d
a
nd
th
e
a
c
c
ur
a
c
y
of
th
e
a
lg
or
it
hm
is
90.86
%
.
T
he
a
c
c
ur
a
c
y r
e
s
ul
t
s
ho
w
s
t
ha
t
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
pe
r
f
or
m
e
d w
e
ll
on t
he
pr
e
di
c
ti
on of
br
e
a
s
t
c
a
nc
e
r
.
I
n
[
12]
,
a
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
a
nd
c
onvolut
io
na
l
ne
ur
a
l
ne
twor
k
(
C
N
N
)
ba
s
e
d
br
e
a
s
t
c
a
nc
e
r
c
la
s
s
if
ic
a
ti
on
m
ode
l
is
pr
opos
e
d.
I
n
th
e
s
tu
dy,
C
N
N
i
s
us
e
d
f
or
f
e
a
tu
r
e
e
xt
r
a
c
ti
on
a
nd
th
e
s
uppo
r
t
ve
c
to
r
m
a
c
hi
ne
is
e
m
pl
oye
d
f
or
p
r
e
di
c
ti
on
of
th
e
br
e
a
s
t
c
a
nc
e
r
.
I
n [
13]
,
KNN
ba
s
e
d
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
m
ode
l
is
pr
opos
e
d.
T
he
da
ta
s
e
t
c
on
s
is
ts
of
209
obs
e
r
va
ti
ons
c
ol
le
c
t
e
d
m
a
nua
ll
y
by
th
e
a
ut
hor
s
.
T
he
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
m
ode
l
i
s
a
c
c
e
p
T
a
bl
e
w
it
h
pr
e
di
c
ti
on
a
c
c
ur
a
c
y
of
93%
.
I
n
a
not
he
r
s
tu
dy
[
14]
,
a
de
c
is
io
n
tr
e
e
a
lg
or
it
hm
is
a
ppl
ie
d
to
W
is
c
on
s
in
br
e
a
s
t
c
a
nc
e
r
pr
ognos
is
da
ta
s
e
t
a
nd
a
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
m
ode
l
is
pr
opos
e
d.
I
n
[
15]
,
th
e
a
ut
hor
s
c
om
pa
r
e
d
th
e
a
c
c
ur
a
c
y
of
na
ïv
e
ba
y
e
s
a
lg
or
it
hm
w
it
h
de
c
is
io
n
tr
e
e
a
nd
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
a
lg
or
it
hm
on
b
r
e
a
s
t
c
a
nc
e
r
da
ta
c
ol
le
c
te
d
f
r
om
W
is
c
ons
in
da
ta
r
e
pos
it
or
y.
T
he
da
ta
s
e
t
c
ons
is
t
s
of
699
obs
e
r
va
ti
ons
a
nd
a
m
ong
th
e
obs
e
r
va
ti
ons
,
458
a
r
e
m
a
li
gna
nt
a
nd
248
a
r
e
be
ni
gn.
T
he
r
e
s
ul
t
o
f
pe
r
f
or
m
a
nc
e
a
na
ly
s
is
s
how
s
th
a
t
th
e
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
out
pe
r
f
or
m
e
d
th
e
K
N
N
a
nd
na
ïv
e
ba
ye
s
a
lg
or
it
hm
ha
vi
ng a
be
tt
e
r
a
c
c
ur
a
c
y
s
c
or
e
on br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1
,
M
a
r
c
h
20
2
1
:
184
–
190
186
I
n
[
16]
,
S
V
M
a
nd
K
N
N
i
s
a
ppl
ie
d
to
W
is
c
on
s
in
br
e
a
s
t
c
a
n
c
e
r
a
nd
a
pr
e
di
c
ti
ve
m
ode
l
is
pr
opos
e
d
us
in
g
th
e
s
e
a
lg
or
it
hm
s
.
T
he
da
ta
s
e
t
c
ont
a
in
s
699
ob
s
e
r
va
ti
on
s
a
nd
11
f
e
a
tu
r
e
s
.
T
h
e
a
ut
hor
s
c
om
pa
r
e
d
th
e
pe
r
f
or
m
a
nc
e
of
th
e
a
lg
or
i
th
m
s
a
nd
r
e
s
ul
t
s
how
s
th
e
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
a
s
a
be
tt
e
r
a
lg
or
it
hm
w
it
h
hi
ghe
r
a
c
c
ur
a
c
y
th
a
n
th
e
K
N
N
a
lg
or
it
hm
.
A
not
he
r
s
tu
dy
[
17]
,
e
m
pl
oy
e
d
th
e
W
is
c
on
s
in
br
e
a
s
t
c
a
n
c
e
r
da
t
a
r
e
pos
it
or
y
to
a
na
ly
z
e
th
e
pr
e
di
c
ti
ve
p
e
r
f
or
m
a
nc
e
of
K
N
N
a
lg
or
it
hm
on
pr
e
di
c
ti
on
of
br
e
a
s
t
c
a
nc
e
r
.
T
he
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
t
he
pr
opos
e
d K
N
N
ba
s
e
d br
e
a
s
t
c
a
n
c
e
r
pr
e
di
c
ti
on mode
l
ha
s
a
n a
ve
r
a
g
e
a
c
c
ur
a
c
y of
76%
.
3.
R
E
S
E
A
R
C
H
M
E
T
H
O
D
I
n
th
is
r
e
s
e
a
r
c
h,
br
e
a
s
t
c
a
nc
e
r
da
t
a
s
e
t
c
ol
le
c
te
d
f
r
om
th
e
k
a
ggl
e
r
e
pos
it
or
y
is
e
m
pl
oye
d
in
tr
a
in
in
g
a
nd
te
s
ti
ng t
he
pr
opos
e
d
m
ode
l
.
I
n t
he
i
m
pl
e
m
e
nt
a
ti
on
a
nd e
xpe
r
im
e
nt
a
l
te
s
ti
ng, P
yt
hon pr
ogr
a
m
m
in
g l
a
ngua
ge
i
s
e
m
pl
oye
d.
A
s
ta
ti
s
ti
c
a
l
m
e
th
od
th
a
t
is
P
e
a
r
s
on’
s
c
or
r
e
la
ti
on
a
n
a
ly
s
is
a
nd
da
ta
vi
s
ua
li
z
a
ti
on
a
s
w
e
ll
a
s
f
e
a
tu
r
e
r
e
la
ti
ons
hi
p
m
e
a
s
ur
e
s
a
r
e
e
m
pl
oye
d
f
or
id
e
nt
if
ic
a
ti
on
a
nd
in
te
r
pr
e
ta
ti
on
of
br
e
a
s
t
c
a
nc
e
r
da
ta
r
e
pos
it
or
y
to
di
s
c
ove
r
th
e
r
e
la
ti
on
s
hi
p
be
twe
e
n
th
e
c
la
s
s
a
nd
th
e
f
e
a
tu
r
e
s
in
ob
s
e
r
va
ti
ons
.
D
e
c
is
io
n
tr
e
e
a
nd
a
da
pt
iv
e
boo
s
ti
ng
a
lg
or
it
hm
s
a
r
e
e
m
pl
oye
d
f
or
de
v
e
lo
pi
ng
th
e
pr
e
di
c
ti
on
m
od
e
l.
T
he
da
ta
r
e
po
s
it
or
y
c
ons
is
t
s
of
a
li
s
t
ob
s
e
r
va
ti
ons
th
a
t
be
lo
ng
to
m
a
li
gna
nt
(
c
a
nc
e
r
ous
)
a
nd
be
ni
gn
(
non
-
c
a
nc
e
r
o
us
)
c
la
s
s
.
T
he
pe
r
c
e
nt
a
ge
of
th
e
m
a
li
gna
nt
a
nd
be
ni
gn obs
e
r
va
ti
ons
i
n t
he
da
ta
r
e
po
s
it
or
y i
s
de
m
ons
tr
a
te
d i
n
F
i
gur
e
1.
F
ig
ur
e
1.
P
e
r
c
e
nt
a
ge
of
m
a
li
gna
nt
a
nd be
ni
gn obs
e
r
va
ti
ons
i
n t
he
ka
ggl
e
br
e
a
s
t
c
a
nc
e
r
da
ta
r
e
po
s
it
or
y
3.1.
D
at
as
e
t
d
e
s
c
r
ip
t
io
n
T
he
ka
ggl
e
br
e
a
s
t
c
a
nc
e
r
da
ta
r
e
pos
it
or
y
us
e
d
in
th
is
s
tu
dy
c
ons
is
ts
of
569
obs
e
r
va
ti
ons
a
nd
31
f
e
a
tu
r
e
s
. A
m
ong a
t
ot
a
l
of
t
he
569 obs
e
r
va
ti
ons
a
nd
212 ob
s
e
r
va
ti
ons
a
r
e
b
e
ni
gn or
br
e
a
s
t
c
a
n
c
e
r
ne
ga
ti
ve
a
nd
357
a
r
e
m
a
li
gna
nt
or
br
e
a
s
t
c
a
nc
e
r
pos
it
iv
e
.
T
hi
s
s
how
s
37.25
%
of
th
e
obs
e
r
va
ti
on
c
ons
is
ts
of
br
e
a
s
t
c
a
nc
e
r
ne
ga
ti
ve
a
nd
62.74%
of
th
e
obs
e
r
va
ti
on
is
br
e
a
s
t
c
a
nc
e
r
pos
it
i
ve
.
T
he
da
ta
s
e
t
ha
s
no
m
is
s
in
g
f
e
a
tu
r
e
va
lu
e
s
.
T
he
f
e
a
tu
r
e
s
of
th
e
br
e
a
s
t
c
a
nc
e
r
da
ta
r
e
pos
it
or
y
a
r
e
s
um
m
a
r
iz
e
d
in
T
a
bl
e
1. T
he
da
t
a
s
e
t
ob
s
e
r
va
ti
ons
us
e
d
in
tr
a
in
in
g i
s
75%
a
nd i
n t
e
s
ti
ng 25%
of
t
he
obs
e
r
va
ti
ons
i
s
us
e
d.
T
a
bl
e
1.
T
he
ka
ggl
e
c
e
r
vi
c
a
l
c
a
nc
e
r
da
ta
r
e
pos
it
o
r
y f
e
a
tu
r
e
s
de
s
c
r
ip
ti
on
O
bs
e
r
va
t
i
ons
F
e
a
t
ur
e
D
e
s
c
r
i
pt
i
on
1
M
e
a
n r
a
di
us
T
he
m
e
a
n of
di
s
t
a
nc
e
s
f
r
om
c
e
nt
e
r
t
o poi
nt
s
on t
he
pe
r
i
m
e
t
e
r
, i
nt
e
ge
r
2
M
e
a
n
-
t
e
xt
ur
e
S
t
a
nda
r
d de
vi
a
t
i
on of
gr
a
y
-
s
c
a
l
e
va
l
ue
s
, i
nt
e
ge
r
3
M
e
a
n
-
pe
r
i
m
e
t
e
r
m
e
a
n s
i
z
e
of
t
he
c
or
e
t
um
or
, i
nt
e
ge
r
4
M
e
a
n
-
a
r
e
a
M
e
a
n of
a
r
e
a
, i
nt
e
ge
r
5
M
e
a
n
-
s
m
oot
hne
s
s
t
he
l
oc
a
l
va
r
i
a
t
i
on i
n r
a
di
us
l
e
ngt
hs
, i
nt
e
ge
r
6
D
i
a
gnos
i
s
C
l
a
s
s
l
a
b
e
l
(
1=M
a
l
i
gna
nt
, 0=B
e
ni
gn)
T
he
br
e
a
s
t
c
a
nc
e
r
da
ta
s
e
t
f
e
a
tu
r
e
s
a
r
e
de
m
ons
tr
a
te
d
in
F
ig
ur
e
2
.
A
s
de
m
ons
tr
a
te
d
in
F
ig
ur
e
2
,
th
e
num
be
r
of
m
a
li
gna
nt
obs
e
r
va
ti
ons
i
s
m
or
e
t
ha
n t
he
be
ni
gn obs
e
r
va
ti
ons
.
62.7%
37.3%
Mal
i
gn
a
n
t
B
enign
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
B
r
e
as
t
c
anc
e
r
pr
e
di
c
ti
on m
ode
l
w
it
h de
c
is
io
n t
r
e
e
and adapti
v
e
boos
ti
ng
(
T
s
e
hay
A
dm
as
s
u A
s
s
e
gi
e
)
187
F
ig
ur
e
2
. T
he
br
e
a
s
t
c
a
n
c
e
r
da
ta
r
e
pos
it
or
y
f
e
a
tu
r
e
s
3.2.
C
or
r
e
la
t
io
n
an
al
ys
is
W
e
ha
ve
e
m
pl
oye
d
P
e
a
r
s
on’
s
c
or
r
e
la
ti
on
a
na
ly
s
is
f
or
vi
s
u
a
li
z
a
ti
on
of
th
e
r
e
la
ti
ons
hi
p
be
twe
e
n
e
a
c
h
f
e
a
tu
r
e
. T
hi
s
he
lp
s
t
o i
de
nt
if
y t
he
f
e
a
tu
r
e
th
a
t
is
s
tr
ongl
y r
e
la
te
d
t
o t
he
c
la
s
s
f
e
a
tu
r
e
i
n t
he
da
ta
r
e
pos
it
or
y. T
h
e
P
e
a
r
s
on’
s
c
or
r
e
la
ti
on
m
a
tr
ix
f
or
e
a
c
h
f
e
a
tu
r
e
s
of
th
e
br
e
a
s
t
c
a
n
c
e
r
da
ta
s
e
t
is
s
how
n
in
F
ig
ur
e
3
.
A
s
s
how
n
in
F
ig
ur
e
3
th
e
c
la
s
s
is
pe
r
f
e
c
tl
y
r
e
la
te
d
to
m
e
a
n
r
a
di
us
a
nd
m
e
a
n
pe
r
im
e
te
r
f
e
a
tu
r
e
s
.
T
hi
s
s
how
s
th
a
t
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on i
s
hi
ghl
y i
nf
lu
e
nc
e
d by thos
e
f
e
a
tu
r
e
s
.
F
ig
ur
e
3
. T
he
r
e
la
ti
ons
hi
p be
twe
e
n br
e
a
s
t
c
a
nc
e
r
f
e
a
tu
r
e
s
4.
R
E
S
U
L
T
S
A
ND
D
I
S
C
U
S
S
I
O
N
I
n
th
is
s
e
c
ti
on,
th
e
e
xpe
r
im
e
nt
a
l
te
s
t
r
e
s
ul
t
s
on
th
e
pr
opos
e
d
m
ode
l
is
e
xpl
a
in
e
d
.
T
he
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
de
c
is
io
n
tr
e
e
a
nd
a
da
pt
iv
e
boos
ti
ng
a
lg
or
it
h
m
is
a
na
ly
z
e
d
by
e
m
pl
oyi
ng
th
e
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
s
uc
h a
s
a
c
c
ur
a
c
y a
nd c
onf
us
io
n m
a
tr
ix
a
lo
ng w
it
h l
e
a
r
n
in
g c
ur
ve
of
t
he
a
lg
or
it
hm
s
.
4
.1.
P
r
e
d
ic
t
iv
e
ac
c
u
r
ac
y an
al
ys
is
T
he
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
m
ode
l
is
e
xp
e
r
im
e
nt
e
d
on
th
e
tr
a
in
in
g
s
e
t.
T
he
pr
e
di
c
ti
ve
a
c
c
ur
a
c
y
of
th
e
pr
opos
e
d
m
od
e
l
is
s
how
n
in
F
ig
ur
e
4
.
M
or
e
ov
e
r
,
th
e
a
c
c
ur
a
c
y
f
or
de
c
is
io
n
tr
e
e
a
nd
a
da
pt
iv
e
boos
ti
ng f
or
br
e
a
s
t
c
a
nc
e
r
c
la
s
s
if
ic
a
ti
on on r
a
ndom t
e
s
t
is
gi
ve
n
i
n T
a
bl
e
2.
T
a
bl
e
2
.
A
c
c
ur
a
c
y of
a
da
pt
iv
e
boos
ti
ng a
nd
d
e
c
is
io
n t
r
e
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1
,
M
a
r
c
h
20
2
1
:
184
–
190
188
L
e
a
r
ni
ng a
l
gor
i
t
hm
A
c
c
ur
a
c
y i
n %
on e
xpe
r
i
m
e
nt
a
l
t
e
s
t
A
da
pt
i
ve
boos
t
i
ng
90.20
90.90
96.50
D
e
c
i
s
i
on t
r
e
e
88.81
87.41
90.20
F
ig
ur
e
4
.
A
c
c
ur
a
c
y of
de
c
is
io
n t
r
e
e
a
nd a
d
a
pt
iv
e
boos
ti
ng a
lg
or
it
hm
4
.2.
C
on
f
u
s
io
n
m
at
r
ix
an
al
ys
is
A
c
onf
us
io
n
m
a
tr
ix
is
a
m
e
a
s
ur
e
th
e
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
m
ode
l
s
in
te
r
m
s
of
th
e
num
be
r
of
c
or
r
e
c
t
a
nd
in
c
or
r
e
c
t
pr
e
di
c
ti
ons
on
th
e
te
s
t
s
e
t
by
th
e
de
c
is
io
n
tr
e
e
a
nd
a
da
pt
iv
e
boos
ti
ng
a
lg
or
it
hm
.
T
he
c
onf
us
io
n m
a
tr
ix
of
t
he
de
c
is
io
n t
r
e
e
a
n
d a
da
pt
iv
e
boos
ti
n
g a
lg
or
it
hm
is
s
how
n i
n
F
ig
u
r
e
5
(
a
)
a
nd
F
ig
u
r
e
5
(
b)
r
e
s
pe
c
ti
ve
ly
.
(
a)
(
b)
F
ig
ur
e
5
. C
onf
us
io
n m
a
tr
ix
f
or
t
he
de
c
is
io
n t
r
e
e
a
nd a
da
pt
iv
e
boos
ti
ng
, (
a
)
D
e
c
is
io
n t
r
e
e
c
onf
us
io
n m
a
tr
ix
,
(
b)
A
da
pt
iv
e
boos
ti
ng c
onf
us
io
n m
a
tr
ix
A
s
s
how
n
in
F
ig
ur
e
5
(a
)
a
nd
F
ig
ur
e
(
b)
th
e
a
c
c
ur
a
c
y
of
th
e
a
d
a
p
ti
ve
boos
ti
ng
a
lg
or
it
hm
s
is
be
tt
e
r
th
a
n
th
e
a
c
c
ur
a
c
y
of
th
e
de
c
is
io
n
tr
e
e
a
lg
or
it
hm
.
T
he
a
c
c
ur
a
c
y
of
th
e
m
ode
ls
c
a
n
be
c
a
lc
ul
a
te
d
f
or
m
th
e
c
onf
us
io
n
m
a
tr
ix
us
in
g
(
1)
.
A
c
c
ur
a
c
y=
(
T
P
+
T
N
)
/
(
T
P
+
T
N
+
F
P
+
F
N
)
*100
(
1)
T
he
a
c
c
ur
a
c
y
of
th
e
d
e
c
is
io
n
tr
e
e
m
od
e
l
is
c
a
lc
ul
a
te
d
a
s
us
in
g
th
e
(
1)
.
A
c
c
ur
a
c
y=
(
55+
45)
/(
55+
45)
/(
55+
45+
11
+
3)
*100=
87.71%
,
li
ke
w
is
e
,
th
e
a
c
c
ur
a
c
y
of
th
e
a
da
pt
iv
e
boos
ti
ng
a
lg
or
it
hm
i
s
c
a
lc
ul
a
te
d a
s
,
A
c
c
ur
a
c
y
=
(
59+
43)
/(
59+
43+
3
+
9)
*100=
89.47%
. T
hi
s
r
e
s
ul
t
s
how
s
t
h
a
t
th
e
a
da
pt
iv
e
boos
ti
ng a
lg
or
it
hm
out
pe
r
f
or
m
e
d t
ha
n t
he
de
c
is
io
n t
r
e
e
a
lg
or
it
hm
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
B
r
e
as
t
c
anc
e
r
pr
e
di
c
ti
on m
ode
l
w
it
h de
c
is
io
n t
r
e
e
and adapti
v
e
boos
ti
ng
(
T
s
e
hay
A
dm
as
s
u A
s
s
e
gi
e
)
189
4
.
3
.
L
e
ar
n
in
g
c
u
r
ve
s
L
e
a
r
ni
ng
c
ur
ve
s
of
th
e
p
r
opos
e
d
m
ode
l
s
how
s
th
e
pe
r
f
or
m
a
nc
e
of
th
e
m
ode
l
on
t
r
a
in
in
g
s
e
t
a
s
de
m
ons
tr
a
te
d
in
F
ig
ur
e
6
.
A
s
de
m
ons
tr
a
te
d
in
F
ig
ur
e
6
,
th
e
le
a
r
ni
ng
c
ur
ve
f
or
th
e
pr
opos
e
d
m
ode
l’
s
te
s
ti
ng
e
r
r
or
i
s
hi
ghe
r
f
or
t
he
de
c
is
io
n t
r
e
e
m
ode
l
th
a
n t
h
e
a
da
pt
iv
e
boo
s
ti
ng mode
l.
T
h
e
t
e
s
ti
ng
e
r
r
or
f
or
de
c
is
io
n t
r
e
e
m
ode
l
f
a
ll
s
in
th
e
r
a
nge
12.5
%
to
25
%
,
w
hi
c
h
s
how
s
th
a
t
th
e
a
c
c
ur
a
c
y
of
th
e
m
ode
l
f
a
ll
s
in
th
e
in
te
r
va
l
75
%
t
o
87.5%
. T
he
t
e
s
ti
ng e
r
r
or
f
or
t
he
a
da
pt
iv
e
boos
ti
ng a
lg
or
it
hm
f
a
l
ls
i
n t
he
r
a
nge
0.03%
t
o 0.11%
a
nd t
hi
s
s
how
s
th
a
t
th
e
a
c
c
ur
a
c
y of
t
he
a
da
pt
iv
e
boo
s
ti
ng a
lg
or
it
hm
f
a
ll
s
i
n t
he
r
a
nge
89%
t
o 97%
.
(
a
)
(
b)
F
ig
ur
e
6
. T
he
l
e
a
r
ni
ng c
ur
ve
f
or
A
da
boos
t
a
nd
de
c
i
s
io
n t
r
e
e
,
(
a
)
D
e
c
is
io
n t
r
e
e
le
a
r
ni
ng c
ur
ve
,
(
b)
A
dboos
t
le
a
r
ni
ng c
ur
ve
5.
C
O
N
C
L
U
S
I
O
N
I
n
th
is
r
e
s
e
a
r
c
h,
w
e
ha
ve
pr
opos
e
d
a
br
e
a
s
t
c
a
nc
e
r
pr
e
di
c
ti
on
m
ode
l
w
it
h
a
da
pt
iv
e
boos
ti
ng
a
nd
de
c
is
io
n
tr
e
e
a
lg
or
it
hm
on
br
e
a
s
t
c
a
n
c
e
r
da
ta
s
e
t
c
ol
le
c
te
d
f
or
m
ka
ggl
e
da
ta
r
e
pos
it
or
y.
T
he
pr
opo
s
e
d
m
ode
l
s
ol
ve
s
th
e
pr
obl
e
m
of
bi
a
s
e
d
c
la
s
s
if
ic
a
ti
on
on
im
ba
la
n
c
e
d
ob
s
e
r
va
ti
on
by
non
-
e
ns
e
m
bl
e
a
lg
or
it
hm
th
r
ough
e
ns
e
m
bl
e
c
la
s
s
if
ie
r
na
m
e
ly
th
e
a
da
pt
iv
e
boos
ti
ng
.
T
he
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
m
ode
l
is
e
va
lu
a
te
d
by
e
m
pl
oyi
ng
di
f
f
e
r
e
nt
pe
r
f
o
r
m
a
nc
e
m
e
tr
ic
s
s
uc
h
a
s
a
c
c
ur
a
c
y
a
nd
c
onf
us
io
n
m
a
tr
ix
on
th
e
te
s
t
s
e
t.
T
he
r
e
s
ul
t
of
pe
r
f
or
m
a
nc
e
a
n
a
ly
s
is
r
e
ve
a
l
s
th
a
t
th
e
a
da
pt
iv
e
b
oos
ti
ng
a
lg
or
it
hm
ha
s
be
tt
e
r
pe
r
f
or
m
a
nc
e
th
a
n
th
e
de
c
is
io
n
tr
e
e
.
H
e
nc
e
,
th
e
a
da
pt
iv
e
boo
s
ti
ng
a
lg
or
it
hm
is
a
be
tt
e
r
c
la
s
s
if
ie
r
f
or
im
ba
la
nc
e
d
da
ta
s
e
t
w
he
r
e
th
e
us
e
of
non
-
e
ns
e
m
bl
e
a
lg
or
it
hm
s
uc
h
a
s
de
c
i
s
io
n
tr
e
e
,
r
e
s
ul
ts
i
n
bi
a
s
e
d
pr
e
di
c
ti
on
to
w
a
r
d
s
th
e
m
a
jo
r
it
y
c
la
s
s
yi
e
ld
in
g be
tt
e
r
pe
r
f
or
m
a
nc
e
on pr
e
di
c
ti
on of
t
he
m
a
jo
r
it
y c
la
s
s
a
nd poor
pe
r
f
or
m
a
nc
e
on t
he
m
in
or
it
y c
la
s
s
.
R
E
F
E
R
E
N
C
E
S
[1]
R.
Chand,
D.
K.
Rao,
T.
B.
Tekabu
and
M.G.M
Khan,
“
Modeling
Bre
ast
Cancer
Cases
in
Fiji,
”
Asia
-
Pacific
World
Congress o
n Compute
r Scienc
e and En
gineerin
g
, 2018
.
[2]
Mohammed
Abdulrazaq
Kahya,
“
Classific
ation
enhanc
ement
of
breast
cance
r
histopathol
ogical
image
using
penalized logistic regress
ion,
”
Indonesian
Journal
of Electr
ical Engi
n
eering and
Computer S
cience
, Vol.
13, No. 1
,
2019.
[3]
Vikas
Chaurasia,
Saurabh
Pal,
BB
Tiwari,
“
Predic
tion
of
benign
an
d
maligna
nt
brea
st
canc
er
using
data
mining
techniques,
”
Journal
of Al
gorith
ms & C
omputat
ional
T
echnology
, 2018
.
[4]
May
Phu
Paing,
C.
Pintavirooj,
Kazuhiko
Hamamoto,
“
Comparison
of
Sampling
Methods
for
Imbalan
ced
Dat
a
Classific
ation in Ra
ndom Fore
st,
”
Biomedical Engineering International
Conference, IEEE
, 2018.
[5]
Dongdong
Sun,
Minghui
Wang,
Huanqing
Feng,
Ao
Li,
“
Progno
sis
Prediction
of
Human
Breast
Cancer
by
integrating
Deep
Neural
Network
and
Support
Vector
Machine,
Superv
ised
Feature
Extraction
and
Classification
fo
r
Breast
Cancer
Prognosis
Prediction,
”
Internati
onal
Congress
on
Image
and
Signal
Process
ing,
BioMedical
Engineering and Informatics
, 2017.
[6]
Ebru
Aydındag
Bayrak,
Pınar
Kırcı,
Tolga
Ensari,
“
Comparison
of
Machine
Learn
ing
Methods
for
Breast
Cancer
Diagnosis,
”
IEEE
, 2019.
[7]
S.
Murugan,
Muthu
Kumar,
S.
Amudha,
“
Classific
ation
and
Predic
tion
of
Breas
t
Cance
r
using
Linea
r
Regre
ssion,
”
Decision
Tree
and
Random
Forest,
International
Conference
on
Curre
nt
Trends
in
Computer,
Electrical,
Electronics
and Communication
, 2017.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1
,
M
a
r
c
h
20
2
1
:
184
–
190
190
[8]
Shahrb
anoo
Goli,
Hossein
Mahjub,
Javad
Farad
mal,
Hoda
Mashay
ekhi
,
Ali
-
Reza
Soltanian,
“
Surviva
l
Predic
tion
an
d
Featur
e
Select
ion
in
Patients
with
Breas
t
Cance
r
Using
Support
Vecto
r
Regre
ssion,
”
Hindawi
Publishin
g
Corporation Co
mputational
and Mathe
matical M
ethods in
Medicin
e
, 2016.
https://doi.org/10.1155/2016/2157984
.
[9]
P.
Sathiyanarayanan,
Pavithra,
Sai
Saranya.M,
Makeswari.M,
“
Identif
ication
of
Breast
Cancer
Using
The
Decision
Tree
Algorithm,
”
Proceedings
of
international
conference
on
syste
ms
computation
automation
and
networking,
IEEE
, 2019.
DOI: 10.1109/ICS
CAN.2019.
8878757
.
[10]
Ahmet
Mert,
Niyazi
KJlJç,
Erdem
Bilgili,
Aydin
Akan,
“
Breast
C
ancer
Detection
with
Reduc
ed
Feature
Set,
”
Hindawi Publ
ishing Cor
poration C
omputational
and Mathematical
Methods in Medicin
e
, Volume 2015.
[11]
Abdullah
-
Al
Nahid,
Yinan
Kong,
“
Involvement
of
Machine
Learnin
g
for
Breast
Cancer
Image
Classification:
A
Survey
,
”
Hindawi Co
mputational
and Mathematical
Methods in Medicin
e
, Volume 2017.
[12]
Mohd Rasoul Al
-
hadidi, Abdulsalam
Alarabeyyat, Mohann
ad Alhanah
na,
“
Breast Ca
ncer
Detec
tion using
K
-
nearest
Neighb
or
Machine
Learning
Algorithm,
”
Internati
onal
Conference
on
Developments
in
eSystems
Engineering
,
IEEE
,
2017.
DOI: 10.1109/DeSE
.2016.8
.
[13]
Shabina
Sayed,
Shoeb
Ahmed,
Rakesh
Poonia,
“
Holo
Entropy
Enable
d
Decision
Tree
Classifier
For
Breast
Cancer
Diagnosis
Us
ing
Wisconsin
(Prognostic)
Data
Set,
”
Internati
onal
Conference
on
Communicat
ion
Systems
and
Network Te
chnologie
s, IEEE
, 2017.
[14]
Wan
Nor
Liyana
Wan
Hassan
Ibeni,
et
al
.
,
“
Comparat
ive
analysis
on
Bayesian
classific
ation
for
breast
cance
r
problem,
”
Bulletin
of
Electrical
Engineering
and
Informatics
(BEEI)
,
Vol.
8,
No.
4,
2019.
DOI:
https://doi.org/10.11591/eei.v8i4.1628
.
[15]
Md.
Milon
Islam,
Hasib
Iqbal,
Md.
Rezwanul
Haque,
Md.
Kamrul
Hasan,
“
Predic
tion
of
Breas
t
Cance
r
Using
Support
Vecto
r
Machine and K
-
Nearest Neighbors,
”
Humanitarian
Technology Conf
erence, IEEE
, 2017.
[16]
Alberto
Palacios
Pawlovsky,
Mai
Nagahashi,
“
A
Method
to
Select
a
Good
Setting
for
the
kNN
Algorithm
when
Using it for B
reast Cancer Prognosis
,
”
IEEE
, 2014.
DOI: 10.1109/B
HI.2
014.6864336
.
[17]
Assegie,
Tsehay
Admassu,
Sushma
S
J.,
Prasanna
Kumar
S
C,
“
Weig
hted
Decision
Tree
Model
for
Breast
Cancer
Detection,
”
Technology Reports of Kansai University, Volum
e 62, Issue 03, 2020.
[18]
Assegie
Tsehay
Admassu,
Sushma
S.
J.,
“A
Support
Vector
M
achi
ne
and
Decision
Tree
Based
Breast
Cance
r
Predic
tion,”
Internati
onal
Journal
of
Engineering
and
Advanced
Tech
nology
(IJEAT)
,
vol.
9,
no.
3,
pp.
2972
-
2976,
2020, DOI: 10.35940/ijeat.A1752.029320.
[19]
Assegie
Tsehay
Admassu,
“An
optimized
K
-
Nearest
Neighbor
b
ased
breast
cancer
detection,”
Journal
of
Roboti
cs
and Control (JRC),
vol. 2, no. 3, pp. 115
-
118, 2020, DOI: 10.18196/jrc.2363
.
[20]
Sushma
S.
J,
S.
C.
Prasanna
Kumar,
A
novel
approach
to
jointly
ad
dress
localization
and
classification
of
breas
t
cancer
using
bi
o
-
inspired
approac
h,
Internati
onal
Journal
of
Electrica
l
and
Computer
Engineering
(IJECE),
vol.
9,
no. 2, pp. 992
-
1001, 2019
,
DOI: 10.11591/i
jece.v9i2.pp992
-
1001.
[21]
Amandeep
Kaur,
Prabhjeet
Kaur,
“Breast
Cancer
Detection
and
C
lassification
using
Analysis
and
Gene
-
Back
Proport
ional
Neura
l
Networ
k
Algorit
hm,”
Internati
onal
Journal
of
Innovative
Technology
and
Exploring
Engineering
(IJITEE),
vol.
8,
no.
8,
pp.
2789
-
2803,
2019,
available:
https:
//www.ijitee.
org/wp
-
content/
uploads/
papers/v8
i8/H699
2068819
.pdf.
[22]
P.
Suryachandra
and
P.
V.
S.
Reddy,
“Comparison
of
machine
le
arning
algorithms
for
breast
cancer,”
2016
Internati
onal
Conference
on
Inventive
Computat
ion
Technologi
es
(ICICT)
,
Coimbatore,
pp.
1
-
6,
2016,
doi:
10.1109/INVENTIVE.2016.7830090.
[23]
Achmad
Ridok,
Nashi
Widodo,
Wayan
Firdaus
Mahmudy,
Muhaimi
n
Rifa,
“A
hybrid
feature
selection
on
AIR
S
method
for
identifying
breast
cancer
diseases,”
Internati
onal
Journ
al
of
Electrical
and
Computer
Engineer
ing
(IJECE)
,
vol. 11, no. 1, pp. 728, 735, 2021
, DOI: 10.11591/ijece.v11i1.pp728
-
735.
[24]
Mohammed
Y.
Kamil,
“Computer
-
aided
diagnosis
system
for
breast
cancer
based
on
the
Gabor
filter
technique,”
Internati
onal
Journal
of
Electrical
and
Computer
Engineering
(
IJEC
E),
vol.
10,
no.
5,
pp.
5235
-
5242,
2020,
DOI:
10.11591/ijece.v10i5.pp5235
-
5242
.
[25]
Susama
Bagchi,
Kim
Gaik
Tay,
Audrey
Huong,
Sanjoy
Kumar
Debn
ath,
“Image
processing
and
machine
learning
techniques
used in compu
ter
-
aided
detection system for
mammogram s
cr
eening
-
A review,”
Internati
onal Journ
al
of
Electrical
and
Computer
Engineering
(IJECE),
vol.
10,
no.
3,
pp.
2336
-
2348,
2020,
DOI:
10.11591/ijece.v10i5.pp5235
-
5242
.
Evaluation Warning : The document was created with Spire.PDF for Python.