I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
41
,
No
.
1
,
J
an
u
ar
y
20
2
6
,
p
p
.
1
91
~
1
99
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
41
.
i
1
.
pp
1
91
-
1
99
191
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
An
e
nha
nce
d NL
P
a
ppro
a
ch f
o
r
B
I
-
RADS
e
x
tractio
n in br
ea
st
ultras
o
und repor
t
s usin
g
deep
learn
ing
Ahm
ed
Sa
hl
1
,
Sh
a
f
a
a
t
un
nu
r
H
a
s
a
n
2
,
M
a
ie
M
.
Abo
g
ha
za
la
h
3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
C
o
l
l
e
g
e
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
K
i
n
g
K
h
a
l
i
d
U
n
i
v
e
r
s
i
t
y
,
A
b
h
a
,
S
a
u
d
i
A
r
a
b
i
a
2
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
i
n
g
,
U
n
i
v
e
r
si
t
i
Te
k
n
o
l
o
g
i
M
a
l
a
y
s
i
a
, J
o
h
o
r
B
h
a
r
u
,
M
a
l
a
y
si
a
3
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
C
o
l
l
e
g
e
,
N
a
h
d
a
U
n
i
v
e
r
s
i
t
y
,
B
e
n
i
S
u
e
f
,
E
g
y
p
t
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
11
,
2
0
2
4
R
ev
is
ed
Dec
4
,
202
5
Acc
ep
ted
Dec
13
,
2
0
2
5
Bre
a
st
c
a
n
c
e
r
sta
n
d
s
a
s
o
n
e
o
f
th
e
to
p
c
a
u
se
s
o
f
d
e
a
th
a
ro
u
n
d
t
h
e
g
lo
b
e
,
m
a
k
in
g
t
h
e
a
c
c
u
ra
te
in
terp
re
tatio
n
o
f
b
re
a
st
u
lt
ra
so
u
n
d
re
p
o
rts
v
it
a
l
fo
r
e
a
rly
d
iag
n
o
sis
a
n
d
trea
tme
n
t.
Un
fo
r
t
u
n
a
tely
,
k
e
y
fin
d
i
n
g
s
in
t
h
e
se
r
e
p
o
rts
a
re
o
ften
b
u
ried
in
u
n
stru
c
t
u
re
d
tex
t
,
c
o
m
p
l
ica
ti
n
g
a
u
t
o
m
a
ted
e
x
trac
ti
o
n
.
T
h
is
stu
d
y
p
re
se
n
ts
a
d
e
e
p
lea
rn
in
g
-
b
a
se
d
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
i
n
g
(NL
P
)
a
p
p
ro
a
c
h
t
o
e
x
trac
t
b
re
a
st
ima
g
i
n
g
re
p
o
rti
n
g
a
n
d
d
a
ta
sy
ste
m
(
BI
-
RAD
S
)
c
a
teg
o
ries
fro
m
b
re
a
st
u
lt
ra
so
u
n
d
d
a
ta.
We
train
e
d
a
re
c
u
rre
n
t
n
e
u
ra
l
n
e
two
rk
(RNN
)
m
o
d
e
l,
sp
e
c
ifi
c
a
ll
y
u
sin
g
a
BiL
S
T
M
a
rc
h
it
e
c
tu
re
,
o
n
a
d
a
tas
e
t
o
f
re
p
o
rts
t
h
a
t
we
re
m
a
n
u
a
ll
y
a
n
n
o
tate
d
fro
m
a
h
o
sp
it
a
l
in
S
a
u
d
i
Ara
b
ia.
Ou
r
a
p
p
ro
a
c
h
a
ls
o
in
c
o
rp
o
ra
tes
u
n
c
e
rtain
t
y
e
stim
a
ti
o
n
tec
h
n
iq
u
e
s
to
tac
k
le
a
m
b
ig
u
o
u
s
c
a
se
s
a
n
d
u
se
s
d
a
ta
a
u
g
m
e
n
tati
o
n
t
o
b
o
o
st
m
o
d
e
l
p
e
rfo
rm
a
n
c
e
.
T
h
e
e
x
p
e
rime
n
tal
re
su
lt
s
in
d
ica
te
th
a
t
o
u
r
d
e
e
p
lea
rn
in
g
m
e
th
o
d
su
r
p
a
ss
e
s
trad
it
io
n
a
l
ru
l
e
-
b
a
se
d
a
n
d
m
a
c
h
in
e
-
lea
rn
i
n
g
t
e
c
h
n
iq
u
e
s,
a
c
h
iev
in
g
imp
re
ss
iv
e
a
c
c
u
ra
c
y
i
n
c
las
sifica
ti
o
n
tas
k
s.
Th
is
re
se
a
rc
h
p
lay
s
a
sig
n
ifi
c
a
n
t
r
o
le
i
n
a
u
to
m
a
ti
n
g
ra
d
io
l
o
g
y
re
p
o
rti
n
g
,
a
i
d
in
g
c
li
n
ica
l
d
e
c
isio
n
-
m
a
k
in
g
,
a
n
d
p
u
s
h
in
g
f
o
rwa
rd
t
h
e
field
o
f
b
re
a
st ca
n
c
e
r
re
se
a
rc
h
.
K
ey
w
o
r
d
s
:
BI
-
R
ADS
Deep
-
lear
n
in
g
L
STM
Nam
ed
en
tity
r
ec
o
g
n
itio
n
NL
P
R
NN
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
:
Ma
ie
M.
Ab
o
g
h
az
ala
h
C
o
m
p
u
ter
Scien
ce
C
o
llag
e,
N
ah
d
a
Un
iv
er
s
ity
B
en
i Su
ef
,
E
g
y
p
t
E
m
ail:
en
g
_
m
aie@y
ah
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
B
r
ea
s
t
ca
n
ce
r
co
n
tin
u
es
to
b
e
o
n
e
o
f
th
e
m
o
s
t
wid
esp
r
ea
d
ca
n
ce
r
s
g
lo
b
ally
,
p
o
s
in
g
a
s
u
b
s
tan
tial
b
u
r
d
e
n
o
n
b
o
th
i
n
d
iv
id
u
al
p
atien
ts
an
d
p
u
b
lic
h
ea
lth
s
y
s
tem
s
[
1
]
.
E
ar
ly
d
etec
tio
n
is
cr
u
cial
in
r
ed
u
ci
n
g
m
o
r
tality
r
ates
an
d
alle
v
iatin
g
f
in
a
n
cial
s
tr
ain
.
C
o
n
s
eq
u
en
tly
,
m
ed
ical
g
u
id
elin
es
ad
v
o
ca
te
f
o
r
r
o
u
tin
e
m
am
m
o
g
r
a
p
h
y
s
cr
ee
n
i
n
g
to
ass
es
s
b
r
ea
s
t
ca
n
ce
r
r
is
k
[
2
]
.
To
m
in
im
ize
d
is
cr
ep
a
n
cies
an
d
s
tan
d
ar
d
ize
r
ad
io
lo
g
is
ts
’
r
ep
o
r
tin
g
o
f
m
a
m
m
o
g
r
a
p
h
ic
r
esu
lts
,
th
e
Am
e
r
ican
C
o
lleg
e
o
f
R
ad
io
l
o
g
y
(
AC
R
)
in
tr
o
d
u
ce
d
th
e
b
r
ea
s
t
im
ag
in
g
r
e
p
o
r
tin
g
an
d
d
ata
s
y
s
tem
(
B
I
-
R
ADS)
[
3
]
.
T
h
is
s
y
s
tem
p
r
o
v
id
es
a
s
tan
d
ar
d
ized
lex
ico
n
f
o
r
r
ep
o
r
tin
g
m
am
m
o
g
r
ap
h
ic
f
in
d
in
g
s
an
d
a
s
ix
-
ca
teg
o
r
y
class
i
f
icatio
n
f
r
am
ewo
r
k
to
ass
ess
m
alig
n
an
cy
r
is
k
as
s
h
o
wn
in
T
ab
le
1
[
4
]
.
Alth
o
u
g
h
B
I
-
R
ADS
was
in
itia
lly
d
esig
n
ed
f
o
r
m
a
m
m
o
g
r
ap
h
y
,
it
h
as
s
in
ce
b
ee
n
ad
ap
ted
f
o
r
o
th
e
r
im
ag
in
g
m
o
d
alities
,
s
u
ch
as
m
ag
n
etic
r
eso
n
an
ce
im
ag
in
g
(
MRI)
an
d
b
r
ea
s
t
u
ltra
s
o
u
n
d
.
Nev
er
th
eless
,
th
ese
ess
en
tial
r
ad
io
lo
g
y
d
is
co
v
e
r
ies
ar
e
f
r
eq
u
en
tly
r
ec
o
r
d
ed
in
u
n
s
tr
u
ctu
r
ed
n
ar
r
ativ
e
f
o
r
m
ats,
r
en
d
er
in
g
th
em
u
n
av
ailab
le
t
o
co
m
p
u
tatio
n
al
s
y
s
tem
s
d
ep
en
d
en
t
o
n
o
r
g
a
n
ized
d
ata.
Nu
m
e
r
o
u
s
in
v
esti
g
atio
n
s
h
av
e
u
tili
ze
d
n
at
u
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
s
tr
ateg
ies
to
ex
tr
ac
t
B
I
-
R
ADS
f
in
d
in
g
s
a
n
d
f
in
al
ass
ess
m
en
t
ca
teg
o
r
ies
f
r
o
m
d
iv
er
s
e
E
n
g
lis
h
-
lan
g
u
a
g
e
b
r
ea
s
t
r
ad
io
g
r
ap
h
y
r
ep
o
r
ts
,
en
co
m
p
ass
in
g
m
am
m
o
g
r
am
s
an
d
b
r
ea
s
t
u
ltra
s
o
u
n
d
d
ata
.
E
ar
ly
ap
p
r
o
ac
h
es
wer
e
p
r
ed
o
m
in
an
tl
y
r
u
le
-
b
ased
[
5
]
,
s
u
ch
as
Me
d
L
E
E
,
o
n
e
o
f
th
e
p
io
n
ee
r
in
g
clin
ical
NL
P sy
s
tem
s
d
ev
elo
p
ed
f
o
r
ex
tr
ac
tin
g
a
b
n
o
r
m
al
f
in
d
in
g
s
f
r
o
m
m
am
m
o
g
r
ap
h
y
r
e
p
o
r
t
s
[
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
1
,
J
an
u
ar
y
20
2
6
:
1
91
-
1
99
192
T
ab
le
1
.
A
d
escr
ip
tio
n
o
f
B
I
-
R
ADS
s
ix
-
ca
teg
o
r
y
m
am
m
o
g
r
a
p
h
y
f
i
n
d
in
g
s
BI
-
R
A
D
S
c
a
t
e
g
o
r
y
F
i
n
d
i
n
g
s
Li
k
e
l
i
h
o
o
d
o
f
b
r
e
a
s
t
c
a
n
c
e
r
M
a
n
a
g
e
m
e
n
t
0
N
e
e
d
a
d
d
i
t
i
o
n
a
l
i
ma
g
i
n
g
o
r
p
r
i
o
r
e
x
a
mi
n
a
t
i
o
n
N
/
A
R
e
c
a
l
l
f
o
r
a
d
d
i
t
i
o
n
a
l
i
ma
g
i
n
g
a
n
d
/
o
r
a
w
a
i
t
p
r
i
o
r
e
x
a
m
i
n
a
t
i
o
n
s
1
N
e
g
a
t
i
v
e
N
e
g
l
i
g
i
b
l
e
R
o
u
t
i
n
e
s
c
r
e
e
n
i
n
g
2
B
e
n
i
g
n
N
e
g
l
i
g
i
b
l
e
R
o
u
t
i
n
e
s
c
r
e
e
n
i
n
g
3
P
r
o
b
a
b
l
y
b
e
n
i
g
n
<
2
%
S
h
o
r
t
i
n
t
e
r
v
a
l
-
f
o
l
l
o
w
-
up
4
S
u
sp
i
c
i
o
u
s
23
-
3
4
%
Ti
ss
u
e
d
i
a
g
n
o
si
s
5
H
i
g
h
l
y
s
u
g
g
e
st
i
v
e
o
f
ma
l
i
g
n
a
n
c
y
>
9
5
%
Ti
ss
u
e
d
i
a
g
n
o
si
s
6
M
a
l
i
g
n
a
n
c
y
c
o
n
f
i
r
me
d
b
i
o
p
sy
1
0
0
%
S
u
r
g
i
c
a
l
e
x
c
i
s
i
o
n
w
h
e
n
c
l
i
n
i
c
a
l
l
y
a
p
p
r
o
p
r
i
a
t
e
Oth
er
r
u
le
-
b
ased
m
et
h
o
d
s
we
r
e
im
p
lem
en
ted
to
class
if
y
B
I
-
R
ADS
b
r
ea
s
t
ti
s
s
u
e
co
m
p
o
s
itio
n
f
r
o
m
m
am
m
o
g
r
a
p
h
y
r
ec
o
r
d
s
[
7
]
to
ex
am
in
e
am
b
ig
u
ity
in
B
I
-
R
ADS
as
s
es
s
m
en
t
ca
teg
o
r
ies
u
tili
zin
g
th
e
GAT
E
NL
P
f
r
am
ewo
r
k
[
8
]
.
L
ater
a
d
v
an
ce
m
e
n
ts
in
tr
o
d
u
ce
d
m
ac
h
in
e
lear
n
i
n
g
-
b
ased
NL
P
s
y
s
tem
s
,
s
u
ch
as
th
o
s
e
em
p
lo
y
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
(
SVMs)
an
d
Naïv
e
B
ay
es
(
NB
)
to
ex
tr
ac
t
B
I
-
R
ADS
ca
teg
o
r
ies
an
d
l
a
t
e
r
a
l
i
t
y
c
l
a
s
s
i
f
i
ca
t
i
o
n
s
,
ac
h
i
e
v
in
g
a
n
F1
-
s
c
o
r
e
o
f
0
.
9
5
a
n
d
s
u
r
p
a
s
s
i
n
g
r
u
l
e
-
b
a
s
e
d
ap
p
r
o
ac
h
e
s
in
p
e
r
f
o
r
m
a
n
c
e
[
9
]
.
Ad
d
i
t
io
n
al
l
y
,
a
l
te
r
n
a
t
i
v
e
N
L
P
p
i
p
e
l
in
e
s
h
av
e
b
e
en
u
t
i
l
i
z
ed
t
o
e
x
t
r
a
c
t
B
I
-
R
A
D
S
e
v
a
l
u
a
t
i
o
n
ca
t
e
g
o
r
i
e
s
[
1
0
]
,
wh
i
l
e
s
t
a
t
i
s
t
i
c
a
l
t
e
s
t
in
g
h
a
s
b
e
en
em
p
lo
y
ed
t
o
s
u
p
p
o
r
t
c
l
i
n
ica
l
d
e
c
i
s
i
o
n
-
m
ak
i
n
g
u
s
i
n
g
e
x
tr
a
c
t
ed
f
in
d
in
g
s
[
1
1
]
,
[
1
2
]
.
T
h
er
e
ar
e
n
o
w
e
n
o
r
m
o
u
s
d
i
g
ital
ar
ch
iv
es
o
f
clin
ical
d
o
cu
m
en
ts
in
Sau
d
i
Ar
ab
ia
d
u
e
to
th
e
wid
esp
r
ea
d
u
s
e
o
f
elec
tr
o
n
i
c
h
ea
lth
r
ec
o
r
d
s
,
n
ec
ess
itatin
g
NL
P
-
d
r
iv
en
m
eth
o
d
s
to
ex
tr
ac
t
m
ea
n
i
n
g
f
u
l
in
s
ig
h
ts
.
Sev
er
al
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
NL
P
tech
n
iq
u
es
f
o
r
s
y
m
p
to
m
ex
tr
ac
tio
n
an
d
d
is
ea
s
e
p
r
o
g
r
ess
io
n
an
aly
s
is
with
in
Sau
d
i
m
ed
ical
r
ec
o
r
d
s
[
1
3
]
-
[
1
5
]
.
Mo
r
e
r
ec
e
n
tly
,
r
esear
ch
o
n
Sau
d
i
clin
ica
l
tex
t
h
as
ex
p
an
d
ed
to
ad
d
r
ess
b
r
o
ad
er
NL
P
ch
allen
g
es,
in
clu
d
in
g
n
e
g
atio
n
d
et
ec
tio
n
an
d
tu
m
o
r
-
r
elate
d
in
f
o
r
m
atio
n
ex
tr
ac
tio
n
f
r
o
m
s
u
r
g
ical
n
o
tes.
Desp
ite
th
ese
co
n
tr
ib
u
tio
n
s
,
n
o
p
r
io
r
s
tu
d
y
h
as
s
p
ec
if
ically
ad
d
r
es
s
ed
th
e
s
tr
u
ctu
r
ed
ex
tr
ac
tio
n
o
f
B
I
-
R
ADS
f
in
d
in
g
s
f
r
o
m
Sau
d
i b
r
ea
s
t u
ltra
s
o
u
n
d
r
ep
o
r
ts
,
h
ig
h
lig
h
ti
n
g
a
c
r
itical
g
ap
in
th
e
f
ield
.
Stru
ctu
r
ed
B
I
-
R
ADS
ex
tr
ac
ti
o
n
is
cr
u
cial
f
o
r
clin
ical
d
ec
is
io
n
-
m
ak
in
g
.
T
o
ad
d
r
ess
th
is
g
ap
,
w
e
p
r
esen
t
a
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
to
Sau
d
i
Ar
ab
ian
b
r
ea
s
t
u
ltra
s
o
u
n
d
d
ata
th
at
ca
n
ex
tr
ac
t
all
B
I
-
R
AD
S
f
in
d
in
g
c
lass
if
icatio
n
s
.
I
n
lig
h
t
o
f
th
e
g
r
o
win
g
i
n
ter
est
in
d
e
ep
lear
n
i
n
g
m
o
d
els,
we
e
x
p
lic
itly
in
v
esti
g
ate
th
e
ap
p
licatio
n
o
f
a
b
id
ir
ec
tio
n
al
lo
n
g
-
s
h
o
r
t
ter
m
m
em
o
r
y
(
B
iLST
M
)
n
etwo
r
k
f
o
r
th
is
task
.
W
e
s
p
ec
if
ically
ex
p
lo
r
e
th
e
ap
p
licatio
n
o
f
a
B
iLST
M
-
b
ased
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
f
o
r
e
x
tr
ac
tin
g
B
I
-
R
ADS
f
in
d
in
g
s
f
r
o
m
b
r
ea
s
t
u
ltra
s
o
u
n
d
r
ep
o
r
ts
[1
6
]
-
[
1
9
]
.
W
e
u
s
e
an
an
n
o
tated
d
ataset
o
f
4
6
5
r
ep
o
r
ts
to
illu
s
tr
ate
th
at
d
ee
p
lear
n
in
g
m
eth
o
d
o
lo
g
ies
s
u
r
p
ass
co
n
v
en
tio
n
al
c
o
n
d
itio
n
al
r
an
d
o
m
f
ield
s
(
CRF
)
b
ased
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
es
.
T
h
is
u
n
d
er
s
co
r
es
t
h
eir
p
o
ten
tial to
en
h
a
n
ce
b
r
ea
s
t c
an
ce
r
r
esear
ch
a
n
d
clin
ical
d
ec
is
io
n
s
u
p
p
o
r
t.
R
ec
en
t
NL
P
ad
v
an
ce
m
en
ts
s
h
o
w
th
at
R
NN
-
b
ased
m
o
d
els
s
u
r
p
ass
C
R
F
m
o
d
els
in
n
a
m
ed
en
tity
r
ec
o
g
n
itio
n
(
NE
R
)
task
s
,
e
s
p
ec
ially
wh
en
i
n
teg
r
atin
g
h
u
m
an
-
g
en
er
ate
d
f
ea
t
u
r
es
a
n
d
d
o
m
ain
-
s
p
ec
if
ic
d
ictio
n
ar
ies
[
1
9
]
.
I
n
th
e
clin
ic
al
d
o
m
ain
,
R
NN
s
h
av
e
b
ee
n
e
f
f
ec
tiv
ely
ap
p
lied
to
m
e
d
ical
e
v
en
t
d
etec
tio
n
[
2
0
]
,
m
ed
ical
co
n
ce
p
t
ex
tr
ac
tio
n
[
2
1
]
,
ex
tr
ac
tio
n
o
f
tem
p
o
r
al
in
f
o
r
m
atio
n
in
clin
ical
co
n
tex
ts
[
2
2
]
,
an
d
d
is
ea
s
e
n
am
e
r
ec
o
g
n
itio
n
[
2
3
]
.
Ho
we
v
er
,
th
e
r
e
is
s
till
a
lack
o
f
s
tu
d
y
o
n
u
s
in
g
d
ee
p
lear
n
in
g
an
d
m
ac
h
in
e
lear
n
i
n
g
to
ex
tr
ac
t
B
I
-
R
ADS
in
Sau
d
i
h
ea
lth
ca
r
e.
Her
e
is
th
e
o
u
tlin
e
f
o
r
th
e
r
est
o
f
th
e
p
ap
er
:
f
ir
s
t,
we
ex
am
in
e
th
e
m
eth
o
d
o
l
o
g
y
a
n
d
ex
p
er
im
en
t;
s
ec
o
n
d
,
we
p
r
esen
t th
e
r
esu
lts
an
d
d
is
cu
s
s
wh
at
we
f
o
u
n
d
; a
n
d
f
in
ally
,
we
wr
a
p
u
p
th
e
s
tu
d
y
in
s
ec
tio
n
4
.
2.
M
E
T
H
O
D
AND
E
XP
E
R
I
M
E
NT
2
.
1
.
Da
t
a
s
et
a
nd
a
nn
o
t
a
t
io
n
Data
s
o
u
r
ce
:
W
e
u
tili
ze
d
b
r
ea
s
t
u
ltra
s
o
u
n
d
r
ep
o
r
ts
f
r
o
m
Kh
a
m
is
Mu
s
h
ay
t
Ma
ter
n
ity
Ho
s
p
ital
in
Aseer
Pro
v
in
ce
,
Sau
d
i
Ar
ab
ia,
co
v
e
r
in
g
th
e
p
er
io
d
f
r
o
m
2
0
1
5
to
2
0
2
0
.
All
r
ep
o
r
ts
wer
e
an
o
n
y
m
ize
d
to
p
r
o
tect
p
atien
t
co
n
f
id
en
tiality
b
y
r
ep
la
cin
g
s
en
s
itiv
e
in
f
o
r
m
atio
n
(
e.
g
.
,
p
a
tien
t
n
am
es,
ad
d
r
ess
es,
telep
h
o
n
e
n
u
m
b
er
s
,
an
d
m
ed
ical
s
taf
f
n
am
es)
with
s
u
r
r
o
g
ates
o
r
p
s
eu
d
o
n
y
m
s
.
T
h
is
en
s
u
r
ed
th
e
te
x
t
r
em
ai
n
e
d
co
h
er
en
t
with
o
u
t
u
n
u
s
u
al
g
a
p
s
.
No
tab
ly
,
o
u
r
d
at
aset c
o
m
p
r
is
ed
tex
tu
al
r
e
p
o
r
ts
with
o
u
t a
cc
o
m
p
a
n
y
in
g
u
ltra
s
o
u
n
d
im
a
g
es.
An
n
o
tatio
n
p
r
o
ce
s
s
:
An
iter
ativ
e
ap
p
r
o
ac
h
was e
m
p
lo
y
ed
t
o
d
ev
el
o
p
th
e
a
n
n
o
tati
o
n
g
u
i
d
elin
es:
i)
I
n
itial
d
r
af
tin
g
: c
o
llab
o
r
ated
with
d
o
m
ain
e
x
p
er
ts
to
cr
ea
te
th
e
in
itial a
n
n
o
tatio
n
g
u
id
elin
es.
ii)
Pil
o
t
an
n
o
tatio
n
:
two
an
n
o
ta
to
r
s
in
d
ep
e
n
d
en
tly
an
n
o
tated
a
s
u
b
s
et
o
f
6
5
r
ep
o
r
ts
u
s
in
g
th
e
in
itial
g
u
id
elin
es.
T
h
e
in
ter
-
an
n
o
tat
o
r
ag
r
ee
m
en
t
y
ield
e
d
an
F
-
m
ea
s
u
r
e
o
f
0
.
8
2
1
,
h
ig
h
lig
h
ti
n
g
th
e
task
’
s
co
m
p
lex
ity
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
en
h
a
n
ce
d
N
LP
a
p
p
r
o
a
ch
f
o
r
B
I
-
R
A
DS
ex
tr
a
ctio
n
i
n
b
r
ea
s
t u
ltr
a
s
o
u
n
d
r
ep
o
r
ts
…
(
A
h
med
S
a
h
l
)
193
iii)
Gu
id
elin
e
r
ef
in
em
en
t:
b
ased
o
n
d
is
cr
ep
an
cies
o
b
s
er
v
ed
,
th
e
g
u
id
elin
es
w
er
e
r
ef
in
ed
f
o
r
clar
ity
an
d
co
m
p
r
eh
e
n
s
iv
en
ess
.
iv
)
Re
-
an
n
o
tatio
n
:
t
h
e
s
am
e
6
5
r
ep
o
r
ts
wer
e
r
e
-
a
n
n
o
tated
u
s
in
g
th
e
u
p
d
ated
g
u
id
elin
es,
r
esu
ltin
g
in
an
im
p
r
o
v
e
d
F
-
m
ea
s
u
r
e
o
f
0
.
9
4
2
.
v)
Fu
ll
an
n
o
tatio
n
:
th
e
f
in
alize
d
g
u
id
elin
es
wer
e
ap
p
lied
to
an
n
o
tate
th
e
r
em
ain
i
n
g
4
0
0
r
e
p
o
r
ts
,
cu
lm
in
atin
g
in
4
6
5
an
n
o
tate
d
r
ep
o
r
ts
.
Fig
u
r
e
1
.
Fig
u
r
e
1
.
T
h
e
m
eth
o
d
f
lo
wc
h
a
r
t
is
th
e
en
tire
m
eth
o
d
o
lo
g
y
p
i
p
elin
e
A
web
-
b
ased
an
n
o
tatio
n
a
p
p
licatio
n
ca
lled
B
R
AT
,
wh
ich
is
o
p
en
-
s
o
u
r
ce
,
m
ad
e
th
e
a
n
n
o
tatio
n
p
r
o
ce
s
s
ea
s
ier
[
2
4
]
.
Fig
u
r
e
2
i
n
ad
d
itio
n
to
en
tity
an
n
o
tatio
n
,
we
m
ar
k
ed
th
e
n
eg
atio
n
s
tate
o
f
ev
er
y
en
tity
.
Af
ter
war
d
,
th
e
a
n
n
o
tated
co
r
p
u
s
was
d
iv
id
ed
in
t
o
two
h
al
v
es
:
a
tr
ain
in
g
s
et
co
m
p
r
is
in
g
3
1
0
r
ep
o
r
ts
(
ab
o
u
t
two
-
th
ir
d
s
)
an
d
a
test
in
g
s
et
co
m
p
r
is
in
g
1
5
5
r
ep
o
r
ts
(
a
b
o
u
t
o
n
e
-
th
ir
d
)
.
Fig
u
r
e
2
.
B
AR
T
an
n
o
tatio
n
f
o
r
a
b
r
est ca
n
ce
r
r
ad
io
lo
g
y
r
ep
o
r
t
2
.
2
.
NE
R
m
et
ho
ds
NE
R
is
a
cr
u
cial
p
r
o
b
lem
in
NL
P
th
at
en
tails
id
en
tify
i
n
g
an
d
class
if
y
in
g
en
titi
es
in
tex
t
in
t
o
estab
lis
h
ed
ca
teg
o
r
ies
[
2
5
]
,
s
u
ch
as
n
am
es
o
f
p
eo
p
le,
o
r
g
an
izatio
n
s
,
lo
ca
tio
n
s
,
an
d
s
p
e
cif
ic
ter
m
in
o
lo
g
ies
p
er
tin
en
t to
a
d
o
m
ain
Fig
u
r
e
3
.
W
e
ex
p
lo
r
ed
t
h
r
ee
NE
R
ap
p
r
o
ac
h
es:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
1
,
J
an
u
ar
y
20
2
6
:
1
91
-
1
99
194
2
.
2
.
1
.
Rule
-
ba
s
ed
m
et
ho
d:
E
s
tab
lis
h
ed
as
a
b
aselin
e,
th
is
m
eth
o
d
in
teg
r
ates
m
an
u
ally
g
en
er
ated
r
u
les
with
a
n
en
tity
d
ictio
n
ar
y
an
d
is
im
p
lem
en
ted
th
r
o
u
g
h
th
e
UI
MA
R
u
ta
f
r
am
ewo
r
k
.
T
h
e
en
tity
d
ictio
n
a
r
y
was
co
n
s
tr
u
cted
f
r
o
m
th
e
an
n
o
tated
d
ev
elo
p
m
en
t
s
et,
a
n
d
r
eg
u
lar
ex
p
r
ess
io
n
s
wer
e
d
esig
n
ed
to
id
e
n
tify
s
p
ec
if
ic
p
atter
n
s
[
2
6
]
.
R
u
ta
r
u
les h
an
d
led
co
m
p
licated
p
er
m
u
tatio
n
s
,
in
clu
d
in
g
co
m
b
in
in
g
in
teg
er
s
an
d
u
n
its
.
2
.
2
.
2
.
CRF
-
ba
s
ed
m
et
ho
d:
C
R
Fs
ar
e
p
r
o
b
ab
ilis
tic
m
o
d
els
ad
ep
t
in
s
eq
u
en
ce
lab
elin
g
task
s
.
W
e
u
tili
ze
d
th
e
C
R
F++
p
ac
k
ag
e
t
o
in
co
r
p
o
r
ate
ess
en
tial
NE
R
co
m
p
o
n
e
n
ts
,
in
clu
d
in
g
b
ag
-
of
-
wo
r
d
s
an
d
n
-
g
r
am
s
,
to
c
o
n
s
tr
u
ct
th
e
NE
R
m
o
d
el.
C
R
Fs
in
clu
d
e
co
n
tex
tu
al
in
f
o
r
m
atio
n
,
m
ak
i
n
g
th
em
s
u
itab
le
f
o
r
task
s
lik
e
o
u
r
s
.
Fig
u
r
e
3
.
Per
f
o
r
m
an
c
e
c
o
m
p
ar
is
o
n
o
n
NE
R
m
eth
o
d
s
2
.
2
.
3
.
RNN
-
ba
s
ed
deep
lea
rn
ing
m
et
ho
d
:
C
ap
tu
r
in
g
lo
n
g
-
ter
m
d
ep
en
d
e
n
cies
in
s
eq
u
e
n
tial
d
ata
is
a
s
tr
o
n
g
s
u
it
o
f
R
NNs,
esp
ec
ially
L
STM
n
etwo
r
k
s
.
W
e
im
p
lem
en
ted
an
R
NN
ar
ch
itectu
r
e
wi
th
L
ST
M
u
n
its
d
r
awn
f
r
o
m
L
am
p
le
’
s
cr
ea
tio
n
s
et
a
l.
[
1
8
]
en
h
an
ce
m
e
n
ts
ex
p
lo
r
e
d
in
clu
d
ed
:
−
C
h
ar
ac
ter
em
b
ed
d
i
n
g
s
: c
ap
tu
r
i
n
g
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es o
f
wo
r
d
s
.
−
B
i
L
STM
:
r
ad
io
lo
g
y
r
ep
o
r
ts
ar
e
s
tr
u
ctu
r
ed
as
a
s
eq
u
e
n
tial
m
ed
ical
tex
t,
m
ak
in
g
B
iLST
M
ef
f
ec
tiv
e
f
o
r
ca
p
tu
r
in
g
lo
n
g
-
r
an
g
e
d
e
p
en
d
e
n
cies
in
tex
tu
al
p
atter
n
s
.
Pro
ce
s
s
in
g
s
eq
u
en
ce
s
in
f
o
r
war
d
an
d
b
ac
k
war
d
di
r
ec
tio
n
s
to
u
tili
ze
p
ast an
d
f
u
tu
r
e
co
n
tex
t
Fig
u
r
e
4
.
Fin
ally
,
wh
at
was n
ee
d
ed
f
o
r
t
h
e
R
NN
m
o
d
el
wer
e:
−
C
h
ar
ac
ter
em
b
ed
d
i
n
g
d
im
en
s
io
n
: 5
0
−
L
STM
lay
er
s
ize:
1
0
0
u
n
its
at
th
e
wo
r
d
lev
el
−
L
ea
r
n
in
g
r
ate:
0
.
0
0
5
−
Dr
o
p
o
u
t
p
r
o
b
ab
ilit
y
: 0
.
5
Sev
er
al
ep
o
ch
s
p
ass
ed
b
ef
o
r
e
th
e
tr
ain
in
g
a
n
d
v
alid
atio
n
l
o
s
s
es
b
eg
an
to
ch
a
n
g
e.
Fig
u
r
e
5
illu
s
tr
ate
s
th
e
B
iLST
M
m
o
d
el
’
s
lo
s
s
co
n
v
er
g
e
n
ce
cu
r
v
e,
d
e
m
o
n
s
tr
ati
n
g
th
e
s
tab
ilit
y
an
d
ef
f
ec
tiv
e
n
ess
o
f
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
W
h
ile
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els
s
u
ch
as
B
E
R
T
h
av
e
s
h
o
wn
s
tr
o
n
g
p
e
r
f
o
r
m
an
c
e
in
NL
P
task
s
,
we
o
p
ted
f
o
r
a
B
iLST
M
-
b
ased
ap
p
r
o
ac
h
d
u
e
to
its
ef
f
ec
tiv
e
n
ess
in
h
an
d
li
n
g
s
eq
u
en
tial
m
ed
ical
tex
t,
lo
we
r
co
m
p
u
tatio
n
al
r
eq
u
ir
e
m
en
ts
,
a
n
d
b
etter
g
en
er
aliza
b
ilit
y
o
n
a
m
o
d
er
ate
-
s
ized
d
ataset
.
E
v
alu
atio
n
m
ea
s
u
r
e
s
:
W
e
u
s
ed
s
tan
d
ar
d
m
etr
ics
m
ea
s
u
r
es to
ass
ess
th
e
NE
R
s
y
s
tem
s
’
ef
f
icac
y
:
−
Pre
cisi
o
n
(
PR
E
)
:
t
h
e
p
r
o
p
o
r
tio
n
o
f
ac
c
u
r
ately
an
ticip
ated
p
o
s
itiv
e
o
b
s
er
v
atio
n
s
to
th
e
p
r
o
jecte
d
p
o
s
itiv
es.
−
R
ec
all
(
R
E
C
)
:
t
h
e
p
r
o
p
o
r
tio
n
o
f
ac
cu
r
ately
p
r
ed
icted
p
o
s
itiv
e
in
s
tan
ce
s
to
th
e
to
tal
in
s
tan
ce
s
in
th
e
ac
tu
al
ca
teg
o
r
y
.
−
F1
-
s
co
r
e
(
F1
)
:
t
h
e
s
u
m
o
f
p
r
ec
is
io
n
an
d
r
ec
all,
ca
lcu
lated
u
s
in
g
weig
h
ts
.
−
Acc
u
r
ac
y
(
AC
C
)
:
t
h
e
p
r
o
p
o
r
ti
o
n
o
f
ac
cu
r
ately
a
n
ticip
ated
o
b
s
er
v
atio
n
s
to
th
e
to
tal
o
b
s
er
v
atio
n
s
.
Ma
th
em
atica
lly
,
th
ese
ar
e
d
e
f
i
n
ed
as:
PR
E
=
+
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
en
h
a
n
ce
d
N
LP
a
p
p
r
o
a
ch
f
o
r
B
I
-
R
A
DS
ex
tr
a
ctio
n
i
n
b
r
ea
s
t u
ltr
a
s
o
u
n
d
r
ep
o
r
ts
…
(
A
h
med
S
a
h
l
)
195
R
E
C
=
+
(
2
)
F1
=
(
2
∗
∗
)
+
(
3
)
ACC
=
+
+
+
(
4
)
T
P =
t
r
u
e
p
o
s
itiv
es
,
FP
=
f
alse
p
o
s
itiv
es
,
FN =
f
alse
n
eg
ativ
e
s
,
T
N
=
t
r
u
e
n
eg
ativ
es
.
T
h
e
tr
ain
in
g
s
et
was
u
tili
ze
d
t
o
d
ev
elo
p
an
d
tr
ain
th
e
NE
R
m
o
d
els,
wh
ile
th
e
test
s
et
s
er
v
ed
to
ev
alu
ate
th
eir
p
er
f
o
r
m
an
ce
b
ased
o
n
t
h
e
m
et
r
ics m
en
tio
n
ed
a
b
o
v
e.
Fig
u
r
e
4
.
B
iLST
M
-
b
ased
m
o
d
el
ar
ch
itectu
r
e
f
o
r
B
I
-
R
ADS
e
x
tr
ac
tio
n
Fig
u
r
e
5
.
L
o
s
s
c
o
n
v
er
g
en
ce
o
f
B
iLST
M
m
o
d
el
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
R
esu
lt
I
n
alig
n
m
en
t
with
B
I
-
R
ADS
s
tan
d
ar
d
s
,
ex
p
er
ts
id
en
tifie
d
20
en
tity
ty
p
es
in
th
e
b
r
ea
s
t
u
ltra
s
o
u
n
d
r
ep
o
r
ts
,
with
an
ad
d
itio
n
al
ca
teg
o
r
y
lab
eled
“
Oth
er
”
to
g
r
o
u
p
in
f
r
e
q
u
en
t
o
cc
u
r
r
en
ce
s
.
Ou
t
o
f
4
6
5
r
ep
o
r
ts
,
9
,
1
3
2
e
n
titi
es
w
er
e
an
n
o
tated
.
Fo
u
r
en
tity
ty
p
es
—
lo
ca
tio
n
,
ec
h
o
,
s
ize,
an
d
v
ascu
lar
ity
—
wer
e
th
e
m
o
s
t
f
r
eq
u
e
n
t,
ea
ch
a
p
p
ea
r
i
n
g
o
v
e
r
1
,
0
0
0
tim
es.
C
o
n
v
er
s
ely
,
t
en
en
tity
ty
p
es,
s
u
ch
as
ar
c
h
itectu
r
al
d
is
to
r
tio
n
,
ca
lcif
icatio
n
s
,
an
d
tis
s
u
e
co
m
p
o
s
itio
n
,
h
ad
f
ewe
r
t
h
an
1
0
0
o
c
cu
r
r
en
ce
s
as sh
o
wn
in
T
ab
le
2
.
T
ab
le
2
.
Dis
tr
ib
u
tio
n
o
f
B
I
-
R
ADS
en
tity
ca
teg
o
r
ies in
th
e
a
n
n
o
tated
c
o
r
p
u
s
En
t
i
t
y
t
y
p
e
N
u
mb
e
r
o
f
e
n
t
i
t
i
e
s
A
l
d
e
r
15
A
r
c
h
i
t
e
c
t
u
r
a
l
-
d
i
s
t
o
r
t
i
o
n
22
C
a
l
c
i
f
i
c
a
t
i
o
n
s
30
D
u
c
t
c
h
a
n
g
e
s
52
Ec
h
o
1
,
3
0
8
El
a
s
t
i
c
i
t
y
-
a
s
sessm
e
n
t
60
H
a
r
d
n
e
ss
-
r
a
t
i
o
19
Lo
c
a
t
i
o
n
2
,
3
0
1
L
y
mp
h
N
o
d
e
3
9
9
M
a
r
g
i
n
8
0
1
M
a
ss
e
s
1
5
8
N
e
g
a
t
i
o
n
6
5
5
O
r
i
e
n
t
a
t
i
o
n
26
P
o
st
e
r
i
o
r
-
f
e
a
t
u
r
e
s
31
R
e
si
st
a
n
c
e
-
i
n
d
e
x
2
3
1
S
h
a
p
e
4
6
1
S
i
z
e
1
,
4
4
0
S
k
i
n
1
3
1
T
i
ss
u
e
-
c
o
m
p
o
si
t
i
o
n
14
V
a
sc
u
l
a
r
i
t
y
9
5
8
O
t
h
e
r
20
T
o
t
a
l
9
,
1
3
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
1
,
J
an
u
ar
y
20
2
6
:
1
91
-
1
99
196
W
e
aim
ed
to
d
eter
m
in
e
wh
ich
o
f
th
r
ee
m
eth
o
d
s
—
th
e
r
u
le
-
b
ased
ap
p
r
o
ac
h
,
th
e
C
R
Fs
-
b
a
s
ed
m
o
d
el,
an
d
th
e
R
NN
-
b
ased
m
o
d
el
(
B
iLST
M)
—
wa
s
m
o
s
t
ef
f
ec
ti
v
e
in
NE
R
ev
alu
atio
n
.
T
h
e
d
ee
p
lear
n
i
n
g
m
o
d
el
u
s
in
g
B
iLST
M
ac
co
m
p
lis
h
ed
th
e
g
r
ea
test
F1
-
s
co
r
e
o
f
0
.
9
0
8
,
f
o
llo
wed
b
y
th
e
m
o
d
el
b
ase
d
o
n
C
R
Fs
with
an
F1
-
s
co
r
e
o
f
0
.
8
8
5
,
a
n
d
th
e
a
p
p
r
o
ac
h
b
ased
o
n
r
u
les
with
an
F1
-
s
co
r
e
o
f
0
.
8
6
4
,
as
illu
s
tr
ated
in
T
ab
le
3
.
C
o
m
p
ar
ed
to
m
o
r
e
c
o
n
v
e
n
tio
n
al
m
eth
o
d
s
,
th
ese
r
esu
lts
d
em
o
n
s
tr
ate
th
at
d
ee
p
lear
n
in
g
-
b
ased
s
y
s
tem
s
ar
e
m
o
r
e
ef
f
ec
tiv
e
in
ex
t
r
ac
tin
g
B
I
-
R
ADS
co
n
clu
s
io
n
s
f
r
o
m
b
r
ea
s
t
u
ltra
s
o
u
n
d
r
ec
o
r
d
s
.
T
h
e
ev
alu
atio
n
m
etr
ics
u
s
ed
to
ass
ess
th
e
p
er
f
o
r
m
a
n
c
e
o
f
th
e
NE
R
m
o
d
els
in
clu
d
e
PR
E
,
R
E
C
,
F1
,
an
d
AC
C
,
w
h
ich
ar
e
ca
lcu
lated
u
s
in
g
th
e
(
5
)
-
(
8
)
:
PR
E
=
+
(
5
)
R
E
C
=
+
(
6
)
F1
=
(
2
∗
∗
)
+
(
7
)
ACC
=
+
+
+
(
8
)
−
Pre
cisi
o
n
(
PR
E
)
is
d
ef
in
ed
as in
(
5
).
−
R
ec
all
(
R
E
C
)
is
d
ef
in
ed
as in
(
6
).
−
F1
-
m
ea
s
u
r
e
(
F1
)
is
d
e
f
in
ed
as
in
(
7
).
−
Acc
u
r
ac
y
(
AC
C
)
is
d
ef
in
ed
as
in
(
8
).
T
ab
le
3
.
Per
f
o
r
m
an
ce
c
o
m
p
a
r
is
o
n
o
f
NE
R
a
p
p
r
o
ac
h
es (
R
u
le
-
b
ased
,
C
R
F,
an
d
B
iLST
M
)
M
e
t
h
o
d
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
R
u
l
e
-
b
a
se
d
0
.
8
7
1
0
.
8
2
0
0
.
8
6
4
C
R
F
s
-
b
a
se
d
0
.
9
0
2
0
.
8
6
2
0
.
8
8
5
B
i
LST
M
0
.
9
1
3
0
.
8
9
5
0
.
9
0
8
T
h
e
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
o
f
th
e
R
NN
-
b
ased
m
o
d
el
s
u
g
g
ests
th
at
d
ee
p
lear
n
in
g
tech
n
iq
u
es
ca
n
ef
f
ec
tiv
ely
ca
p
tu
r
e
co
m
p
le
x
lin
g
u
is
tic
p
atter
n
s
in
r
ad
io
l
o
g
y
r
e
p
o
r
ts
.
H
o
wev
er
,
th
e
m
o
d
el
’
s
p
er
f
o
r
m
a
n
ce
v
ar
ied
ac
r
o
s
s
d
if
f
er
en
t
en
tity
t
y
p
es,
p
ar
ticu
lar
ly
s
tr
u
g
g
lin
g
w
ith
th
o
s
e
with
f
ewe
r
o
cc
u
r
r
en
c
es in
th
e
d
ataset.
3
.
2
.
DIS
CUSSI
O
N
3
.
2
.
1
.
Address
i
ng
g
a
ps
in pr
ev
io
us
re
s
ea
rc
h
W
h
ile
p
r
ev
io
u
s
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
B
I
-
R
ADS
en
tity
ex
tr
ac
tio
n
u
s
in
g
r
u
le
-
b
ased
an
d
s
tatis
t
ica
l
m
eth
o
d
s
,
th
e
ap
p
licatio
n
o
f
d
e
ep
lear
n
in
g
f
o
r
s
tr
u
ctu
r
ed
in
f
o
r
m
atio
n
ex
tr
ac
tio
n
f
r
o
m
b
r
ea
s
t
u
ltra
s
o
u
n
d
r
e
p
o
r
ts
r
em
a
in
s
u
n
d
er
ex
p
lo
r
ed
.
Ad
d
itio
n
ally
,
m
o
s
t
p
r
io
r
r
esear
c
h
h
as
f
o
cu
s
ed
o
n
m
am
m
o
g
r
ap
h
y
r
ath
er
th
an
u
ltra
s
o
u
n
d
im
ag
in
g
.
T
o
b
r
id
g
e
th
ese
g
a
p
s
,
o
u
r
s
tu
d
y
u
tili
ze
s
a
d
ee
p
-
lear
n
in
g
NE
R
s
y
s
tem
b
ased
o
n
B
iLST
M
to
f
in
d
b
r
ea
s
t u
ltra
s
o
u
n
d
d
ata
with
B
I
-
R
ADS
in
f
o
r
m
atio
n
.
3
.
2
.
2
.
K
ey
f
ind
ing
s
a
nd
no
v
e
l c
o
ntr
ibu
t
io
ns
Ou
r
s
tu
d
y
d
em
o
n
s
tr
ates
th
at
R
NN
-
b
ased
d
ee
p
lear
n
in
g
m
o
d
els
(
B
iLST
M)
o
u
tp
er
f
o
r
m
tr
ad
itio
n
al
C
R
Fs
an
d
r
u
le
-
b
ased
a
p
p
r
o
a
ch
es
in
ex
tr
ac
tin
g
B
I
-
R
ADS
en
titi
es.
T
h
e
b
est
p
o
s
s
ib
le
F1
-
s
co
r
e
of
0
.
9
0
8
,
ac
h
iev
ed
b
y
th
e
R
NN
-
b
ased
m
o
d
el,
u
n
d
er
s
co
r
es
th
e
e
f
f
ec
tiv
en
ess
o
f
d
ee
p
lear
n
in
g
in
th
is
d
o
m
ain
.
Ad
d
itio
n
ally
,
o
u
r
a
n
n
o
tatio
n
p
r
o
ce
s
s
,
in
v
o
lv
in
g
1
8
B
I
-
R
ADS
en
tity
ty
p
es,
s
ets
th
is
s
tu
d
y
ap
ar
t
b
y
p
r
o
v
id
in
g
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
lab
eled
d
ataset
th
an
p
r
ev
io
u
s
ef
f
o
r
ts
.
3
.
2
.
3
.
Co
m
pa
riso
n wit
h
ex
is
t
ing
lite
ra
t
ure
Pre
v
io
u
s
r
esear
ch
h
as
s
h
o
wn
t
h
at
d
ee
p
lear
n
i
n
g
is
u
s
ef
u
l
in
m
ed
ical
tex
t
p
r
o
ce
s
s
in
g
,
a
n
d
o
u
r
r
esu
lts
ar
e
in
lin
e
with
th
at
[
2
7
]
.
Fo
r
in
s
tan
ce
,
An
et
a
l.
[
2
7
]
d
e
m
o
n
s
tr
ated
th
at
B
iLST
M
m
o
d
els
im
p
r
o
v
e
e
n
tity
r
ec
o
g
n
itio
n
in
clin
ical
te
x
t.
Ho
wev
er
,
o
u
r
a
p
p
r
o
ac
h
e
x
ten
d
s
th
is
b
y
a
p
p
ly
in
g
d
ee
p
l
ea
r
n
in
g
t
o
b
r
e
ast
u
ltra
s
o
u
n
d
r
ep
o
r
ts
p
r
ec
is
e
ly
r
ath
er
th
an
b
r
o
a
d
er
clin
ical
n
ar
r
ativ
es.
Un
lik
e
ea
r
lier
m
eth
o
d
s
th
at
r
elied
s
o
lely
o
n
h
a
n
d
-
c
r
af
ted
r
u
les
o
r
s
tatis
tical
m
o
d
els,
o
u
r
d
ee
p
lear
n
in
g
m
o
d
el
ef
f
ec
tiv
ely
c
ap
tu
r
es
co
n
te
x
tu
al
d
ep
en
d
e
n
cies,
en
h
an
ci
n
g
ac
cu
r
ac
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
en
h
a
n
ce
d
N
LP
a
p
p
r
o
a
ch
f
o
r
B
I
-
R
A
DS
ex
tr
a
ctio
n
i
n
b
r
ea
s
t u
ltr
a
s
o
u
n
d
r
ep
o
r
ts
…
(
A
h
med
S
a
h
l
)
197
3
.
2
.
4
.
L
im
it
a
t
io
ns
o
f
t
he
s
t
ud
y
Wh
ile
th
e
r
esu
lt
s
s
h
o
w
p
r
o
m
is
e,
o
u
r
s
tu
d
y
h
as
ce
r
tain
lim
it
atio
n
s
.
First,
wh
ile
th
e
d
ataset
in
clu
d
es
a
d
iv
er
s
e
s
et
o
f
r
ep
o
r
ts
,
th
e
r
el
ativ
ely
lo
w
f
r
eq
u
e
n
cy
o
f
s
o
m
e
en
tity
ty
p
es
m
ay
h
av
e
i
m
p
ac
ted
th
e
m
o
d
el
’
s
ab
ilit
y
to
g
e
n
er
alize
.
Ad
d
itio
n
ally
,
th
e
a
b
s
en
ce
o
f
im
ag
e
-
t
ex
t
alig
n
m
en
t
m
ea
n
s
th
at
e
n
t
ity
ex
tr
ac
tio
n
was
p
er
f
o
r
m
ed
s
o
lely
o
n
tex
tu
al
d
ata,
lim
itin
g
m
u
ltimo
d
al
i
n
s
ig
h
ts
.
Fu
tu
r
e
s
tu
d
ies
s
h
o
u
ld
co
n
s
id
er
in
teg
r
atin
g
im
ag
in
g
f
ea
tu
r
es a
lo
n
g
s
id
e
tex
t
-
b
ased
an
aly
s
is
.
3
.
2
.
5
.
I
m
pli
ca
t
io
ns
f
o
r
f
uture
re
s
ea
rc
h
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
ex
p
l
o
r
e
h
y
b
r
id
m
o
d
els
in
co
r
p
o
r
atin
g
d
ee
p
lea
r
n
in
g
an
d
r
u
le
-
b
ased
tech
n
iq
u
es
to
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
o
n
r
ar
e
en
tity
ty
p
es.
E
x
p
an
d
in
g
t
h
e
d
ataset
with
r
ep
o
r
ts
f
r
o
m
m
u
ltip
le
in
s
titu
tio
n
s
co
u
ld
en
h
a
n
ce
th
e
m
o
d
el
’
s
r
o
b
u
s
tn
ess
an
d
g
en
er
aliza
b
ili
t
y
.
E
x
p
lo
r
i
n
g
tr
an
s
f
o
r
m
er
-
b
ased
ar
ch
itectu
r
es
lik
e
B
E
R
T
o
r
B
io
B
E
R
T
m
ay
im
p
r
o
v
e
en
tity
e
x
tr
ac
tio
n
ac
c
u
r
ac
y
.
3
.
2
.
6
.
Co
nclus
io
n
Ou
r
f
in
d
in
g
s
co
n
f
ir
m
th
at
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es,
p
ar
ticu
lar
ly
R
NN
-
b
ased
m
o
d
els,
ex
tr
ac
t
BI
-
R
ADS
r
esu
lts
f
r
o
m
b
r
ea
s
t
u
ltra
s
o
u
n
d
r
ep
o
r
ts
m
o
r
e
ef
f
ec
tiv
ely
.
T
h
e
s
tu
d
y
co
n
tr
ib
u
t
es
to
th
e
f
ield
b
y
p
r
esen
tin
g
a
co
m
p
r
eh
en
s
iv
e
an
n
o
tated
d
ataset
an
d
d
e
m
o
n
s
tr
atin
g
th
e
f
ea
s
ib
ilit
y
o
f
d
ee
p
lear
n
in
g
f
o
r
s
tr
u
ctu
r
ed
i
n
f
o
r
m
atio
n
e
x
tr
ac
tio
n
in
r
ad
io
l
o
g
y
.
Fu
tu
r
e
ad
v
an
ce
m
en
ts
in
m
u
ltim
o
d
al
le
ar
n
in
g
an
d
d
ataset
ex
p
an
s
io
n
c
o
u
ld
f
u
r
th
e
r
en
h
a
n
ce
au
to
m
ated
B
I
-
R
ADS
class
i
f
icatio
n
an
d
clin
ical
d
ec
is
io
n
s
u
p
p
o
r
t.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
u
cc
ess
f
u
lly
ad
d
r
ess
ed
th
e
ch
allen
g
e
o
f
ex
tr
ac
tin
g
s
tr
u
ctu
r
ed
B
I
-
R
ADS
f
in
d
in
g
s
f
r
o
m
u
n
s
tr
u
ctu
r
ed
r
ep
o
r
t
s
g
en
er
ated
b
y
d
ee
p
lear
n
in
g
f
o
r
b
r
ea
s
t
u
l
tr
aso
u
n
d
s
.
As
an
ticip
ated
in
th
e
I
n
tr
o
d
u
ctio
n
,
o
u
r
B
iLST
M
m
o
d
el
o
u
tp
er
f
o
r
m
e
d
r
u
le
-
b
ased
a
n
d
C
R
F
m
eth
o
d
s
in
B
I
-
R
ADS
ex
tr
ac
tio
n
,
d
em
o
n
s
tr
atin
g
its
ef
f
ec
tiv
en
ess
in
ca
p
tu
r
in
g
li
n
g
u
is
tic
p
atter
n
s
in
r
ad
io
lo
g
y
r
e
p
o
r
ts
.
I
t
ac
h
ie
v
ed
an
F1
-
s
co
r
e
o
f
0
.
9
0
8
,
co
n
f
ir
m
in
g
its
p
o
ten
tial f
o
r
au
t
o
m
ated
clin
ical
d
ec
is
io
n
s
u
p
p
o
r
t.
Ou
r
f
in
d
in
g
s
alig
n
with
p
r
ev
i
o
u
s
r
esear
ch
o
n
d
ee
p
lear
n
in
g
in
m
e
d
ical
tex
t
p
r
o
ce
s
s
in
g
b
u
t
ex
ten
d
its
ap
p
licatio
n
to
b
r
ea
s
t
u
ltra
s
o
u
n
d
,
an
u
n
d
er
ex
p
lo
r
e
d
ar
ea
.
W
h
ile
o
u
r
m
o
d
el
d
em
o
n
s
tr
ates
h
ig
h
ac
cu
r
ac
y
,
lim
itatio
n
s
s
u
ch
as
d
ataset
d
i
v
er
s
ity
an
d
th
e
lac
k
o
f
im
a
g
e
-
tex
t
alig
n
m
e
n
t
h
ig
h
lig
h
t
a
r
ea
s
f
o
r
f
u
r
th
e
r
s
tu
d
y
.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
ex
p
l
o
r
e
h
y
b
r
id
d
ee
p
lear
n
in
g
-
r
u
le
-
b
ase
d
m
o
d
els,
ex
p
an
d
d
atasets
ac
r
o
s
s
in
s
titu
tio
n
s
,
an
d
in
teg
r
ate
tr
an
s
f
o
r
m
er
m
o
d
els
lik
e
B
E
R
T
f
o
r
im
p
r
o
v
ed
ac
cu
r
ac
y
.
I
n
c
o
r
p
o
r
atin
g
m
u
lt
im
o
d
al
lear
n
i
n
g
—
alig
n
in
g
te
x
t
with
u
ltra
s
o
u
n
d
im
ag
es
—
co
u
ld
f
u
r
th
e
r
e
n
h
a
n
ce
ar
tific
ial
in
tellig
en
ce
(
AI
)
-
d
r
iv
e
n
r
a
d
io
lo
g
y
d
ec
is
io
n
s
u
p
p
o
r
t.
ACK
NO
WL
E
DG
M
E
N
T
S
A
h
e
a
r
t
f
el
t
“
t
h
a
n
k
y
o
u
”
f
r
o
m
a
l
l
o
f
u
s
g
o
e
s
o
u
t
t
o
D
r
.
A
b
d
A
l
m
o
t
e
a
M
a
h
o
m
u
d
a
n
d
D
r
.
B
el
g
a
s
im
M
o
h
a
m
m
e
d
f
o
r
t
h
e
i
r
i
n
v
al
u
a
b
le
a
s
s
is
t
a
n
c
e
d
u
r
i
n
g
t
h
is
r
es
e
a
r
c
h
.
T
h
e
i
r
e
x
p
e
r
t
g
u
i
d
a
n
ce
a
n
d
i
n
s
i
g
h
t
f
u
l
f
e
e
d
b
a
c
k
h
a
v
e
s
i
g
n
i
f
i
c
a
n
t
l
y
e
n
h
a
n
c
e
d
t
h
e
q
u
a
l
i
t
y
o
f
t
h
is
w
o
r
k
.
W
e
a
r
e
d
e
e
p
l
y
a
p
p
r
e
c
i
a
t
i
v
e
o
f
t
h
ei
r
t
i
m
e
a
n
d
s
u
p
p
o
r
t
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
N
o
f
u
n
d
in
g
is
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ah
m
ed
Sah
l
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sh
af
aa
tu
n
n
u
r
Hasan
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ma
ie
M.
Ab
o
g
h
az
ala
h
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
1
,
J
an
u
ar
y
20
2
6
:
1
91
-
1
99
198
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
As
th
e
wr
iter
s
o
f
t
h
is
p
ap
e
r
,
we
af
f
ir
m
th
at
n
o
ties
o
r
f
i
n
a
n
cial
in
ter
ests
h
av
e
an
y
b
ea
r
i
n
g
o
n
th
e
co
n
ten
t o
r
co
n
clu
s
io
n
s
d
r
awn
f
r
o
m
it.
DATA AV
AI
L
AB
I
L
I
T
Y
-
Yo
u
ca
n
r
e
q
u
est
a
co
p
y
o
f
t
h
e
d
ata
u
s
ed
to
s
u
p
p
o
r
t
th
e
s
tu
d
y
’
s
co
n
clu
s
io
n
s
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
,
[
Ma
ie
M.
Ab
o
g
h
az
al
ah
]
.
R
estrictio
n
m
ea
s
u
r
es
p
r
ev
en
t
th
e
d
ata,
wh
ich
m
a
y
r
ev
ea
l
r
esear
ch
p
ar
ticip
an
ts
’
p
er
s
o
n
al
i
n
f
o
r
m
a
tio
n
,
f
r
o
m
b
ein
g
p
u
b
licly
av
ail
ab
le.
-
I
f
y
o
u
wo
u
ld
lik
e
d
er
iv
e
d
d
ata
to
b
ac
k
u
p
th
e
s
tu
d
y
’
s
co
n
clu
s
io
n
s
,
y
o
u
ca
n
g
et
in
to
u
ch
with
th
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
,
[
Ma
ie
M.
Ab
o
g
h
az
ala
h
]
.
RE
F
E
R
E
NC
E
S
[
1
]
F
.
B
r
a
y
,
J.
F
e
r
l
a
y
,
I
.
S
o
e
r
j
o
m
a
t
a
r
a
m
,
R
.
L
.
S
i
e
g
e
l
,
L.
A
.
T
o
r
r
e
,
a
n
d
A
.
Jema
l
,
“
G
l
o
b
a
l
c
a
n
c
e
r
st
a
t
i
st
i
c
s
2
0
1
8
:
G
LO
B
O
C
A
N
e
st
i
mat
e
s
o
f
i
n
c
i
d
e
n
c
e
a
n
d
m
o
r
t
a
l
i
t
y
w
o
r
l
d
w
i
d
e
f
o
r
3
6
c
a
n
c
e
r
s
i
n
1
8
5
c
o
u
n
t
r
i
e
s,
”
C
A:
A
C
a
n
c
e
r
J
o
u
r
n
a
l
f
o
r
C
l
i
n
i
c
i
a
n
s
,
v
o
l
.
6
8
,
n
o
.
6
,
p
p
.
3
9
4
–
4
2
4
,
N
o
v
.
2
0
1
8
,
d
o
i
:
1
0
.
3
3
2
2
/
c
a
a
c
.
2
1
4
9
2
.
[
2
]
A
.
O
.
B
e
r
g
e
t
a
l
.
,
“
S
c
r
e
e
n
i
n
g
f
o
r
b
r
e
a
st
c
a
n
c
e
r
:
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
a
n
d
r
a
t
i
o
n
a
l
e
,
”
A
n
n
a
l
s
o
f
I
n
t
e
rn
a
l
Me
d
i
c
i
n
e
,
v
o
l
.
1
3
7
,
n
o
.
5
I
,
p
p
.
3
4
4
–
3
4
6
,
S
e
p
.
2
0
0
2
,
d
o
i
:
1
0
.
7
3
2
6
/
0
0
0
3
-
4
8
1
9
-
1
3
7
-
5
_
p
a
r
t
_
1
-
2
0
0
2
0
9
0
3
0
-
0
0
0
1
1
.
[
3
]
S
.
J.
M
a
g
n
y
,
R
.
S
h
i
k
h
ma
n
,
a
n
d
A
.
L.
K
e
p
p
k
e
,
“
B
r
e
a
st
i
m
a
g
i
n
g
r
e
p
o
r
t
i
n
g
a
n
d
d
a
t
a
sy
s
t
e
m
,
”
S
t
a
t
Pe
a
r
ls
,
2
0
2
3
.
h
t
t
p
s
:
/
/
w
w
w
.
n
c
b
i
.
n
l
m
.
n
i
h
.
g
o
v
/
b
o
o
k
s
/
N
B
K
4
5
9
1
6
9
/
(
a
c
c
e
sse
d
A
u
g
.
2
8
,
2
0
2
3
)
.
[
4
]
M
.
M
.
E
b
e
r
l
,
C
.
H
.
F
o
x
,
S
.
B
.
E
d
g
e
,
C
.
A
.
C
a
r
t
e
r
,
a
n
d
M
.
C
.
M
a
h
o
n
e
y
,
“
B
I
-
R
A
D
S
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
ma
n
a
g
e
m
e
n
t
o
f
a
b
n
o
r
m
a
l
mammo
g
r
a
ms,”
J
o
u
r
n
a
l
o
f
t
h
e
A
m
e
ri
c
a
n
Bo
a
r
d
o
f
Fa
m
i
l
y
Me
d
i
c
i
n
e
,
v
o
l
.
1
9
,
n
o
.
2
,
p
p
.
1
6
1
–
1
6
4
,
M
a
r
.
2
0
0
6
,
d
o
i
:
1
0
.
3
1
2
2
/
j
a
b
f
m
.
1
9
.
2
.
1
6
1
.
[
5
]
N
.
L.
Jai
n
a
n
d
C
.
F
r
i
e
d
ma
n
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
f
i
n
d
i
n
g
s
s
u
sp
i
c
i
o
u
s
f
o
r
b
r
e
a
st
c
a
n
c
e
r
b
a
se
d
o
n
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
o
f
mammo
g
r
a
m re
p
o
r
t
s,”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
ri
c
a
n
M
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s A
ss
o
c
i
a
t
i
o
n
,
v
o
l
.
4
,
n
o
.
S
U
P
P
L
.
,
p
p
.
8
2
9
–
8
3
3
,
1
9
9
7
.
[
6
]
B
.
P
e
r
c
h
a
,
H
.
N
a
ssi
f
,
J.
L
i
p
s
o
n
,
E.
B
u
r
n
si
d
e
,
a
n
d
D
.
R
u
b
i
n
,
“
A
u
t
o
m
a
t
i
c
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
m
a
mm
o
g
r
a
p
h
y
r
e
p
o
r
t
s
b
y
B
I
-
R
A
D
S
b
r
e
a
s
t
t
i
ssu
e
c
o
m
p
o
s
i
t
i
o
n
c
l
a
ss
,
”
J
o
u
rn
a
l
o
f
t
h
e
Am
e
r
i
c
a
n
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
Ass
o
c
i
a
t
i
o
n
,
v
o
l
.
1
9
,
n
o
.
5
,
p
p
.
9
1
3
–
9
1
6
,
S
e
p
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
3
6
/
a
mi
a
j
n
l
-
2
0
1
1
-
0
0
0
6
0
7
.
[
7
]
B
.
S
e
l
e
n
a
n
d
R
.
D
a
n
i
e
l
,
“
A
u
t
o
m
a
t
e
d
d
e
t
e
c
t
i
o
n
o
f
a
m
b
i
g
u
i
t
y
i
n
B
I
-
R
A
D
S
a
ssess
me
n
t
c
a
t
e
g
o
r
i
e
s
i
n
m
a
mm
o
g
r
a
p
h
y
r
e
p
o
r
t
s,
”
i
n
S
t
u
d
i
e
s
i
n
H
e
a
l
t
h
T
e
c
h
n
o
l
o
g
y
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
9
7
,
2
0
1
4
,
p
p
.
3
5
–
3
9
.
[
8
]
H
.
G
a
o
,
E.
J
.
A
.
B
o
w
l
e
s,
D
.
C
a
r
r
e
l
l
,
a
n
d
D
.
S
.
M
.
B
u
i
st
,
“
U
si
n
g
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
t
o
e
x
t
r
a
c
t
mamm
o
g
r
a
p
h
i
c
f
i
n
d
i
n
g
s,
”
J
o
u
rn
a
l
o
f
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
5
4
,
p
p
.
7
7
–
8
4
,
A
p
r
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
.
2
0
1
5
.
0
1
.
0
1
0
.
[
9
]
S
.
M
.
C
a
s
t
r
o
e
t
a
l
.
,
“
A
u
t
o
ma
t
e
d
a
n
n
o
t
a
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
B
I
-
R
A
D
S
a
ssessmen
t
f
r
o
m
r
a
d
i
o
l
o
g
y
r
e
p
o
r
t
s
,
”
J
o
u
rn
a
l
o
f
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
6
9
,
p
p
.
1
7
7
–
1
8
7
,
M
a
y
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
.
2
0
1
7
.
0
4
.
0
1
1
.
[
1
0
]
S
.
B
o
z
k
u
r
t
,
F
.
G
i
me
n
e
z
,
E.
S
.
B
u
r
n
si
d
e
,
K
.
H
.
G
u
l
k
e
se
n
,
a
n
d
D
.
L.
R
u
b
i
n
,
“
U
si
n
g
a
u
t
o
ma
t
i
c
a
l
l
y
e
x
t
r
a
c
t
e
d
i
n
f
o
r
mat
i
o
n
f
r
o
m
mammo
g
r
a
p
h
y
r
e
p
o
r
t
s
f
o
r
d
e
c
i
si
o
n
-
su
p
p
o
r
t
,
”
J
o
u
rn
a
l
o
f
B
i
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
6
2
,
p
p
.
2
2
4
–
2
3
1
,
A
u
g
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
.
2
0
1
6
.
0
7
.
0
0
1
.
[
1
1
]
D
.
A
.
S
i
p
p
o
e
t
a
l
.
,
“
A
u
t
o
m
a
t
e
d
e
x
t
r
a
c
t
i
o
n
o
f
B
I
-
R
A
D
S
f
i
n
a
l
a
ssess
me
n
t
c
a
t
e
g
o
r
i
e
s
f
r
o
m
r
a
d
i
o
l
o
g
y
r
e
p
o
r
t
s
w
i
t
h
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ss
i
n
g
,
”
J
o
u
rn
a
l
o
f
D
i
g
i
t
a
l
I
m
a
g
i
n
g
,
v
o
l
.
2
6
,
n
o
.
5
,
p
p
.
9
8
9
–
9
9
4
,
O
c
t
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
2
7
8
-
0
1
3
-
9
6
1
6
-
5.
[
1
2
]
T.
A
.
P
a
t
e
l
e
t
a
l
.
,
“
C
o
r
r
e
l
a
t
i
n
g
ma
mm
o
g
r
a
p
h
i
c
a
n
d
p
a
t
h
o
l
o
g
i
c
f
i
n
d
i
n
g
s
i
n
c
l
i
n
i
c
a
l
d
e
c
i
si
o
n
s
u
p
p
o
r
t
u
si
n
g
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ss
i
n
g
a
n
d
d
a
t
a
mi
n
i
n
g
m
e
t
h
o
d
s,
”
C
a
n
c
e
r
,
v
o
l
.
1
2
3
,
n
o
.
1
,
p
p
.
1
1
4
–
1
2
1
,
Jan
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
2
/
c
n
c
r
.
3
0
2
4
5
.
[
1
3
]
D
.
A
l
-
S
a
l
e
h
,
M
.
B
i
n
A
l
-
A
m
i
r
,
a
n
d
S
.
La
r
a
b
i
-
M
a
r
i
e
-
S
a
i
n
t
e
,
“
S
N
A
D
A
r
a
b
i
c
d
a
t
a
se
t
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
A
d
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
2
5
0
A
I
S
C
,
2
0
2
1
,
p
p
.
6
3
0
–
6
4
0
.
[
1
4
]
S
.
A
l
o
t
a
i
b
i
,
R
.
M
e
h
m
o
o
d
,
I
.
K
a
t
i
b
,
O
.
R
a
n
a
,
a
n
d
A
.
A
l
b
e
s
h
r
i
,
“
S
e
h
a
a
:
a
b
i
g
d
a
t
a
a
n
a
l
y
t
i
c
s
t
o
o
l
f
o
r
h
e
a
l
t
h
c
a
r
e
sy
m
p
t
o
ms
a
n
d
d
i
s
e
a
se
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
t
w
i
t
t
e
r
,
a
p
a
c
h
e
s
p
a
r
k
,
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zerl
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
4
,
p
.
1
3
9
8
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
0
4
1
3
9
8
.
[
1
5
]
A
.
S
a
h
l
a
n
d
S
.
H
a
s
a
n
,
“
R
a
d
i
o
l
o
g
y
r
e
p
o
r
t
s a
u
t
o
m
a
t
e
d
a
n
n
o
t
a
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
:
r
u
l
e
-
b
a
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
V
s d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
ET
C
o
n
f
e
re
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
v
o
l
.
2
0
2
0
,
n
o
.
6
,
p
p
.
4
3
3
–
4
3
6
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
4
9
/
i
c
p
.
2
0
2
1
.
0
8
9
3
.
[
1
6
]
C
o
l
e
r
t
e
t
a
l
.
,
“
N
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
(
a
l
m
o
st
)
f
r
o
m
scra
t
c
h
,
”
J
o
u
rn
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
se
a
rc
h
,
v
o
l
.
1
2
,
n
o
.
A
u
g
,
p
p
.
2
4
9
3
–
2
5
3
7
,
2
0
1
1
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
w
w
w
.
j
ml
r
.
o
r
g
/
p
a
p
e
r
s
/
v
1
2
/
c
o
l
l
o
b
e
r
t
1
1
a
.
h
t
m
l
.
[
1
7
]
N
.
K
a
l
c
h
b
r
e
n
n
e
r
,
E.
G
r
e
f
e
n
st
e
t
t
e
,
a
n
d
P
.
B
l
u
n
s
o
m,
“
A
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
m
o
d
e
l
l
i
n
g
s
e
n
t
e
n
c
e
s,
”
i
n
5
2
n
d
A
n
n
u
a
l
Me
e
t
i
n
g
o
f
t
h
e
As
so
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
st
i
c
s
,
A
C
L
2
0
1
4
-
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
C
o
n
f
e
r
e
n
c
e
,
2
0
1
4
,
v
o
l
.
1
,
p
p
.
6
5
5
–
6
6
5
,
d
o
i
:
1
0
.
3
1
1
5
/
v
1
/
p
1
4
-
1
0
6
2
.
[
1
8
]
G
.
La
m
p
l
e
,
M
.
B
a
l
l
e
st
e
r
o
s
,
S
.
S
u
b
r
a
man
i
a
n
,
K
.
K
a
w
a
k
a
mi
,
a
n
d
C
.
D
y
e
r
,
“
N
e
u
r
a
l
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
n
a
m
e
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
,
”
2
0
1
6
C
o
n
f
e
r
e
n
c
e
o
f
t
h
e
N
o
r
t
h
A
m
e
ri
c
a
n
C
h
a
p
t
e
r
o
f
t
h
e
Ass
o
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
s
t
i
c
s:
H
u
m
a
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
l
o
g
i
e
s
,
N
AA
C
L
H
L
T
2
0
1
6
-
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
C
o
n
f
e
re
n
c
e
,
p
p
.
2
6
0
–
2
7
0
,
2
0
1
6
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
n
1
6
-
1
0
3
0
.
[
1
9
]
A
.
N
.
Ja
g
a
n
n
a
t
h
a
a
n
d
H
.
Y
u
,
“
B
i
d
i
r
e
c
t
i
o
n
a
l
R
N
N
f
o
r
m
e
d
i
c
a
l
e
v
e
n
t
d
e
t
e
c
t
i
o
n
i
n
e
l
e
c
t
r
o
n
i
c
h
e
a
l
t
h
r
e
c
o
r
d
s
,
”
i
n
2
0
1
6
C
o
n
f
e
r
e
n
c
e
o
f
t
h
e
N
o
rt
h
Am
e
ri
c
a
n
C
h
a
p
t
e
r
o
f
t
h
e
Asso
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
st
i
c
s:
H
u
m
a
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
l
o
g
i
e
s,
N
A
AC
L
H
L
T
2
0
1
6
-
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
C
o
n
f
e
r
e
n
c
e
,
2
0
1
6
,
p
p
.
4
7
3
–
4
8
2
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
n
1
6
-
1
0
5
6
.
[
2
0
]
Z.
Li
u
e
t
a
l
.
,
“
En
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
c
l
i
n
i
c
a
l
t
e
x
t
s
v
i
a
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
BM
C
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
a
n
d
D
e
c
i
s
i
o
n
Ma
k
i
n
g
,
v
o
l
.
1
7
,
n
o
.
S
2
,
p
.
6
7
,
J
u
l
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
1
1
-
017
-
0
4
6
8
-
7.
[
2
1
]
J.
A
.
F
r
i
e
s
,
“
B
r
u
n
d
l
e
f
l
y
a
t
S
e
mE
v
a
l
-
2
0
1
6
t
a
s
k
1
2
:
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
v
s
.
j
o
i
n
t
i
n
f
e
r
e
n
c
e
f
o
r
c
l
i
n
i
c
a
l
t
e
m
p
o
r
a
l
i
n
f
o
r
m
a
t
i
o
n
e
x
t
r
a
c
t
i
o
n
,
”
S
e
m
E
v
a
l
2
0
1
6
-
1
0
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
W
o
r
k
sh
o
p
o
n
S
e
m
a
n
t
i
c
Ev
a
l
u
a
t
i
o
n
,
Pro
c
e
e
d
i
n
g
s
,
p
p
.
1
2
7
4
–
1
2
7
9
,
2
0
1
6
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
s
1
6
-
1
1
9
8
.
[
2
2
]
S
.
K
.
S
a
h
u
a
n
d
A
.
A
n
a
n
d
,
“
R
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
s
f
o
r
d
i
sea
s
e
n
a
m
e
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
d
o
mai
n
i
n
v
a
r
i
a
n
t
f
e
a
t
u
r
e
s
,
”
5
4
t
h
A
n
n
u
a
l
Me
e
t
i
n
g
o
f
t
h
e
Ass
o
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
st
i
c
s,
A
C
L
2
0
1
6
-
L
o
n
g
P
a
p
e
rs
,
v
o
l
.
4
,
p
p
.
2
2
1
6
–
2
2
2
5
,
2
0
1
6
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
p
1
6
-
1
2
0
9
.
[
2
3
]
J.
Li
,
A
.
S
u
n
,
J.
H
a
n
,
a
n
d
C
.
L
i
,
“
A
s
u
r
v
e
y
o
n
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
n
a
m
e
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
4
,
n
o
.
1
,
p
p
.
5
0
–
7
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E.
2
0
2
0
.
2
9
8
1
3
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
en
h
a
n
ce
d
N
LP
a
p
p
r
o
a
ch
f
o
r
B
I
-
R
A
DS
ex
tr
a
ctio
n
i
n
b
r
ea
s
t u
ltr
a
s
o
u
n
d
r
ep
o
r
ts
…
(
A
h
med
S
a
h
l
)
199
[
2
4
]
“
B
r
a
t
r
a
p
i
d
a
n
n
o
t
a
t
i
o
n
t
o
o
l
,
”
2
0
1
2
.
h
t
t
p
:
/
/
b
r
a
t
.
n
l
p
l
a
b
.
o
r
g
/
(
a
c
c
e
sse
d
N
o
v
.
0
8
,
2
0
1
2
)
.
[
2
5
]
A
.
M
a
n
so
u
r
i
,
L.
S
.
A
f
f
e
n
d
e
y
,
a
n
d
A
.
M
a
m
a
t
,
“
N
a
me
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
a
p
p
r
o
a
c
h
e
s,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
3
3
9
–
3
4
4
,
2
0
0
8
.
[
2
6
]
P
.
K
l
u
e
g
l
,
M
.
T
o
e
p
f
e
r
,
P
.
-
D
.
B
e
c
k
,
G
.
F
e
t
t
e
,
a
n
d
F
.
P
u
p
p
e
,
“
U
I
M
A
r
u
t
a
:
r
a
p
i
d
d
e
v
e
l
o
p
me
n
t
o
f
r
u
l
e
-
b
a
se
d
i
n
f
o
r
mat
i
o
n
e
x
t
r
a
c
t
i
o
n
a
p
p
l
i
c
a
t
i
o
n
s,
”
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
2
,
n
o
.
1
,
p
p
.
1
–
4
0
,
J
a
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
7
/
S
1
3
5
1
3
2
4
9
1
4
0
0
0
1
1
4
.
[
2
7
]
Y
.
A
n
,
X
.
X
i
a
,
X
.
C
h
e
n
,
F
.
X
.
W
u
,
a
n
d
J.
W
a
n
g
,
“
C
h
i
n
e
se
c
l
i
n
i
c
a
l
n
a
me
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
v
i
a
mu
l
t
i
-
h
e
a
d
s
e
l
f
-
a
t
t
e
n
t
i
o
n
b
a
se
d
B
i
LST
M
-
C
R
F
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
Me
d
i
c
i
n
e
,
v
o
l
.
1
2
7
,
p
.
1
0
2
2
8
2
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
t
me
d
.
2
0
2
2
.
1
0
2
2
8
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ahm
e
d
S
a
h
l
h
e
e
a
rn
e
d
h
is
B
.
S
c
.
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
S
u
d
a
n
Un
i
v
e
rsity
f
o
r
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
,
S
u
d
a
n
,
in
2
0
0
6
,
f
o
ll
o
we
d
b
y
a
n
M
.
S
c
.
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Un
iv
e
rsity
o
f
Kh
a
rto
u
m
i
n
2
0
1
2
.
No
w
h
e
is
a
P
h
.
D.
c
a
n
d
id
a
te
in
c
o
m
p
u
ter
sc
ien
c
e
a
t
F
a
c
u
l
t
y
o
f
Co
m
p
u
ti
n
g
,
Un
i
v
e
rsiti
Tek
n
o
l
o
g
i
M
a
lay
sia
.
He
c
u
rre
n
tl
y
se
rv
e
s
a
s
l
e
c
tu
re
r
a
t
Kin
g
K
h
a
li
d
Un
iv
e
rsity
.
His
p
r
o
fe
ss
io
n
a
l
f
o
c
u
s
is
firmly
a
n
c
h
o
re
d
i
n
m
a
c
h
in
e
lea
rn
in
g
,
d
a
ta
a
n
a
l
y
sis,
a
n
d
NLP
.
Th
is
d
e
d
ica
ti
o
n
is
e
v
id
e
n
t
i
n
h
is
c
o
n
ti
n
u
o
u
s
re
se
a
rc
h
,
wh
e
re
h
e
e
x
p
l
o
re
s
e
m
e
rg
in
g
a
re
a
s
o
f
tec
h
n
o
lo
g
y
.
He
re
m
a
in
s
a
t
th
e
fo
re
fro
n
t
o
f
i
n
n
o
v
a
ti
o
n
,
with
a
p
a
rti
c
u
lar
in
tere
st
in
a
d
v
a
n
c
e
d
field
s
li
k
e
d
e
e
p
lea
rn
i
n
g
a
n
d
NLP
.
His
c
o
m
m
it
m
e
n
t
t
o
sta
y
in
g
u
p
-
to
-
d
a
te
wit
h
t
h
e
late
s
t
d
e
v
e
lo
p
m
e
n
ts
h
i
g
h
li
g
h
ts
h
is
d
ri
v
e
to
p
u
sh
tec
h
n
o
lo
g
ica
l
b
o
u
n
d
a
ries
a
n
d
m
a
k
e
m
e
a
n
in
g
fu
l
c
o
n
tri
b
u
ti
o
n
s
t
o
t
h
e
ra
p
i
d
ly
e
v
o
l
v
in
g
tec
h
la
n
d
sc
a
p
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
k
a
ld
in
@
k
k
u
.
e
d
u
.
sa
.
Dr
.
S
h
a
fa
a
tu
n
n
u
r
H
a
sa
n
re
c
e
iv
e
d
a
b
a
c
h
e
lo
r
’
s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
(a
rti
ficia
l
in
telli
g
e
n
c
e
)
fro
m
U
n
i
v
e
rsiti
M
a
lay
a
,
a
m
a
ste
r
’
s
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
,
a
n
d
a
P
h
.
D.
in
G
P
U
-
b
a
se
d
m
a
c
h
in
e
le
a
rn
in
g
fro
m
Un
i
v
e
rsiti
Te
k
n
o
lo
g
i
M
a
lay
sia
.
S
h
e
wo
rk
e
d
a
t
S
h
ima
n
o
Co
m
p
o
n
e
n
ts
M
a
la
y
sia
f
o
r
fi
v
e
y
e
a
rs
a
s
a
p
lan
n
i
n
g
a
n
d
a
n
a
ly
ti
c
s
o
ffice
r
d
e
a
li
n
g
with
fish
in
g
tac
k
le
c
o
m
p
o
n
e
n
ts.
S
h
e
is
re
se
a
rc
h
in
g
G
P
U
-
b
a
se
d
Ha
d
o
o
p
tec
h
n
o
lo
g
y
fo
r
b
i
g
d
a
t
a
a
n
d
P
e
lan
g
i
d
e
e
p
lea
rn
i
n
g
a
n
a
ly
ti
c
s
fo
r
b
ig
d
a
ta
re
se
a
rc
h
a
n
d
d
e
v
e
lo
p
m
e
n
t
.
S
h
e
h
a
s
d
e
v
e
lo
p
e
d
G
P
UML
iB:
m
a
c
h
in
e
lea
rn
in
g
li
b
ra
ry
fo
r
b
ig
d
a
ta
p
ro
c
e
ss
in
g
,
a
n
o
p
e
n
-
s
o
u
rc
e
li
b
ra
ry
u
sin
g
C
u
d
a
lan
g
u
a
g
e
to
d
e
a
l
with
Nth
d
ime
n
sio
n
a
l
sp
a
c
e
u
n
d
e
r
G
P
U
p
latfo
rm
(h
tt
p
:
//
g
p
u
m
li
b
.
so
u
rc
e
fo
rg
e
.
n
e
t/
),
with
p
ro
fe
ss
o
r
No
e
l
Lo
p
e
s
fro
m
P
o
rt
u
g
a
l.
He
r
e
x
p
e
rien
c
e
s
in
so
lv
i
n
g
in
d
u
str
y
p
ro
b
lem
s
ra
n
g
in
g
fr
o
m
fu
n
d
a
m
e
n
tal
iss
u
e
s
to
p
ra
c
ti
c
a
l
a
p
p
li
c
a
ti
o
n
s,
su
c
h
a
s
p
o
ly
m
e
r
d
e
g
ra
d
a
ti
o
n
a
n
a
ly
t
ics
,
re
tail
sp
o
rt
a
n
a
l
y
ti
c
s,
d
e
sk
h
e
lp
se
rv
ice
a
n
a
ly
ti
c
s,
m
a
lwa
re
a
n
a
ly
ti
c
s
,
a
n
d
o
t
h
e
rs.
S
h
e
h
a
s
p
u
b
li
sh
e
d
in
m
a
n
y
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
p
a
p
e
rs.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
b
i
g
d
a
ta
c
o
m
p
u
t
in
g
,
m
a
c
h
in
e
lea
rn
i
n
g
,
so
f
t
c
o
m
p
u
ti
n
g
,
C
u
d
a
p
ro
g
ra
m
m
in
g
,
Ha
d
o
o
p
e
n
g
in
e
e
rin
g
,
a
n
d
b
ig
d
a
t
a
p
latfo
rm
s.
S
h
e
is
a
lso
t
h
e
m
a
n
a
g
in
g
e
d
it
o
r
o
f
S
c
o
p
u
s
-
I
n
d
e
x
Jo
u
rn
a
l,
I
n
tern
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
s
in
S
o
ft
C
o
m
p
u
t
in
g
a
n
d
Its
Ap
p
li
c
a
ti
o
n
s
(h
tt
p
:
//
ww
w.h
o
m
e
.
ij
a
sc
a
.
c
o
m
),
a
n
d
re
v
iew
e
r
o
f
m
a
n
y
i
n
tern
a
ti
o
n
a
l
re
p
u
tab
le
jo
u
rn
a
ls
re
late
d
to
h
e
r
f
ield
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
S
h
a
fa
a
tu
n
n
u
r@u
tm.m
y
.
Dr
.
Ma
ie
M.
A
b
o
g
h
a
z
a
l
a
h
s
h
e
e
a
rn
e
d
h
e
r
B
.
S
c
.
i
n
C
o
m
p
u
ter
S
c
ien
c
e
fr
o
m
El
,
M
e
n
o
u
fia
Un
i
v
e
rsity
,
E
g
y
p
t,
i
n
2
0
0
6
,
fo
ll
o
we
d
b
y
a
n
M
.
S
c
.
fr
o
m
Ain
S
h
a
m
s
Un
iv
e
rsit
y
i
n
2
0
1
7
.
Afte
r
th
a
t
sh
e
re
c
e
iv
e
d
h
e
r
P
h
.
D.
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
,
M
e
n
u
fia
U
n
iv
e
rsit
y
,
Eg
y
p
t
i
n
2
0
2
2
.
S
h
e
c
u
rre
n
t
ly
se
rv
e
s
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
a
n
d
d
a
ta
a
n
a
ly
st
a
t
El
n
a
h
d
a
U
n
iv
e
rsit
y
.
He
r
p
ro
fe
ss
io
n
a
l
p
u
rsu
i
ts are
d
e
e
p
ly
ro
o
ted
in
m
a
c
h
in
e
lea
rn
in
g
,
d
a
ta
a
n
a
ly
sis,
a
n
d
c
o
m
p
u
ter
v
isi
o
n
.
His
d
e
d
ica
ti
o
n
t
o
th
e
se
field
s
is
re
flec
ted
i
n
h
is
o
n
g
o
in
g
re
se
a
rc
h
e
n
d
e
a
v
o
rs,
w
h
e
re
h
e
c
o
n
ti
n
u
a
ll
y
e
x
p
lo
re
s
n
e
w
d
ime
n
si
o
n
s
o
f
tec
h
n
o
lo
g
y
.
M
o
re
o
v
e
r,
h
e
re
m
a
in
s
a
t
th
e
fo
re
fro
n
t
o
f
i
n
n
o
v
a
ti
o
n
a
n
d
is
d
e
e
p
l
y
in
tere
ste
d
i
n
c
u
tt
in
g
-
e
d
g
e
d
o
m
a
in
s
s
u
c
h
a
s
d
e
e
p
lea
rn
in
g
a
n
d
c
o
m
p
u
ter
v
i
sio
n
(CV).
Th
is
c
o
m
m
it
m
e
n
t
to
s
tay
in
g
a
b
re
a
st
o
f
th
e
late
st
a
d
v
a
n
c
e
m
e
n
ts
u
n
d
e
rsc
o
re
s
h
is
d
e
d
ica
ti
o
n
t
o
p
u
sh
in
g
t
h
e
b
o
u
n
d
a
ries
o
f
tec
h
n
o
l
o
g
y
a
n
d
c
o
n
tri
b
u
ti
n
g
si
g
n
ifi
c
a
n
tl
y
t
o
it
s
e
v
e
r
-
e
v
o
lv
i
n
g
lan
d
sc
a
p
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
n
g
_
m
a
ie@
y
a
h
o
o
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.