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
26
,
p
p
.
1
19
~1
27
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
41.
i
1
.
p
p
1
19
-
1
27
119
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Incipient
ano
ma
lo
us detec
tion in a
bra
in using
t
h
e I
BI
G
P
a
lg
o
rithm
M
o
ha
m
ed
H
ichem
Na
it
C
ha
la
l,
B
ena
bd
ella
h Ya
g
o
ub
i,
Si
da
hm
ed
H
enni
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
S
y
st
e
ms
a
n
d
S
i
g
n
a
l
s
La
b
o
r
a
t
o
r
y
,
M
o
st
a
g
a
n
e
m
U
n
i
v
e
r
si
t
y
,
M
o
s
t
a
g
a
n
e
m
,
A
l
g
e
r
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
10
,
2
0
2
5
R
ev
is
ed
Dec
11
,
2
0
2
5
Acc
ep
ted
Dec
22
,
2
0
2
5
Th
e
d
e
tec
ti
o
n
o
f
a
n
in
c
ip
ien
t
a
n
o
m
a
lo
u
s
g
r
o
wth
o
f
t
issu
e
in
a
b
ra
i
n
is o
ften
a
d
iffi
c
u
lt
tas
k
.
Va
rio
u
s
a
lg
o
rit
h
m
s
fo
r
b
ra
in
a
n
o
m
a
lo
u
s
d
e
tec
ti
o
n
h
a
v
e
b
e
e
n
su
g
g
e
ste
d
a
b
u
n
d
a
n
t
ly
i
n
t
h
e
e
x
i
stin
g
l
it
e
ra
tu
re
.
In
th
e
las
t
d
e
c
a
d
e
,
m
a
n
y
d
e
tec
ti
o
n
m
e
th
o
d
s
h
a
v
e
b
e
e
n
su
g
g
e
ste
d
to
imp
r
o
v
e
a
n
d
fa
c
il
it
a
te
a
b
n
o
rm
a
l
ti
ss
u
e
d
e
tec
ti
o
n
.
H
o
we
v
e
r,
th
e
m
o
st
a
tt
ra
c
ti
v
e
tec
h
n
iq
u
e
s
to
m
a
n
y
re
se
a
rc
h
e
rs
a
re
m
a
y
b
e
th
o
se
th
a
t
a
re
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
ima
g
e
ry
(M
RI)
-
b
a
se
d
a
lg
o
rit
h
m
s.
A
tec
h
n
iq
u
e
k
n
o
w
n
a
s
th
e
in
v
e
rse
o
f
th
e
b
e
lo
n
g
in
g
in
d
i
v
id
u
a
l
G
a
u
ss
ian
p
ro
b
a
b
il
it
y
(
IBIG
P
)
is
a
p
p
li
e
d
t
o
M
RI
i
n
th
i
s
wo
rk
in
o
rd
e
r
t
o
m
it
i
g
a
te
in
c
ip
ien
t
a
n
o
m
a
lo
u
s
t
issu
e
d
e
tec
ti
o
n
i
n
a
b
ra
in
.
T
h
is
stu
d
y
d
e
m
o
n
stra
tes
th
a
t
th
e
IBIG
P
t
e
c
h
n
iq
u
e
,
a
p
p
li
e
d
to
th
e
M
RI
ima
g
e
,
is
e
x
trem
e
ly
e
ffe
c
ti
v
e
in
e
a
rly
d
e
tec
ti
n
g
a
n
a
n
o
m
a
lo
u
s
c
h
a
n
g
e
i
n
t
h
e
b
ra
in
M
RI
ima
g
e
.
Alth
o
u
g
h
t
h
is
tec
h
n
iq
u
e
i
s
stil
l
in
it
s
i
n
fa
n
c
y
,
it
h
a
s
a
g
re
a
t
p
o
ten
ti
a
l
to
e
n
h
a
n
c
e
b
ra
in
a
n
o
m
a
lo
u
s e
a
rly
d
e
tec
ti
o
n
.
K
ey
w
o
r
d
s
:
B
r
ain
an
o
m
alo
u
s
ch
a
n
g
e
Gau
s
s
ian
wh
ite
n
o
is
e
MRI
im
ag
e
Pro
b
ab
ilit
y
in
v
e
r
s
e
alg
o
r
ith
m
I
B
I
GP
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mo
h
am
ed
Hich
em
Nait
C
h
alal
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
Sy
s
tem
s
An
d
Sig
n
als L
ab
o
r
ato
r
y
,
Mo
s
tag
an
e
m
Un
i
v
er
s
ity
Mo
s
tag
an
em
,
Alg
er
ia
E
m
ail:
m
o
h
am
ed
.
n
aitch
alal.
et
u
@
u
n
iv
-
m
o
s
ta.
d
z
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
b
r
ain
b
eh
a
v
io
r
ca
n
b
e
alter
ed
b
y
b
r
ai
n
an
o
m
alo
u
s
ch
a
n
g
e
(
i.e
.
tu
m
o
r
)
.
T
h
e
latter
d
et
ec
tio
n
in
a
b
r
ain
f
r
o
m
m
a
g
n
etic
r
eso
n
an
ce
im
ag
er
y
(
MRI
)
is
a
ch
all
en
g
in
g
an
d
v
er
y
d
if
f
icu
lt
task
.
Sev
er
al
d
if
f
er
en
t
m
eth
o
d
s
h
a
v
e
b
ee
n
s
u
g
g
ested
in
ten
s
iv
ely
i
n
th
e
liter
atu
r
e
f
o
r
d
etec
tio
n
o
f
a
n
o
m
alo
u
s
tis
s
u
e
s
u
ch
as
t
u
m
o
r
s
f
r
o
m
MR im
ag
es.
C
las
s
ical
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
f
o
r
m
ed
th
e
b
aselin
e
f
o
r
th
e
in
iti
al
a
u
to
m
ated
d
etec
ti
o
n
s
y
s
tem
an
d
th
e
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
i
n
es
(
SVM)
d
em
o
n
s
tr
ated
s
tr
o
n
g
ca
p
ab
ilit
y
with
r
ec
en
t
s
u
p
p
o
r
t
f
o
r
co
r
r
ec
tly
class
if
y
in
g
b
r
ain
tu
m
o
r
s
o
f
8
6
.
8
0
%
ac
cu
r
ac
y
[
1
]
.
T
h
e
k
-
Nea
r
es
t
n
eig
h
b
o
r
s
alg
o
r
ith
m
,
p
ar
ti
cu
lar
ly
ca
p
ab
le
in
th
e
f
o
r
m
o
f
a
n
ew
d
en
s
ity
-
b
ased
ad
ap
tiv
e
-
d
is
tan
ce
(
DAk
NN)
d
ev
elo
p
ed
an
d
test
ed
,
h
as
p
r
o
v
id
e
d
g
r
ea
t
o
p
p
o
r
tu
n
ity
with
g
o
o
d
r
esu
lts
ac
h
iev
ed
an
d
an
av
e
r
ag
e
-
d
ice
s
co
r
e
o
f
0
.
9
0
8
2
f
o
r
tu
m
o
r
r
e
g
io
n
-
s
eg
m
en
tatio
n
acc
u
r
ac
y
[
2
]
.
An
im
p
r
o
v
ed
k
er
n
elize
d
r
o
u
g
h
-
f
u
zz
y
c
-
m
ea
n
s
(
KR
F
C
M)
ap
p
r
o
ac
h
h
as
b
ee
n
d
ev
elo
p
ed
f
o
r
s
eg
m
en
tin
g
b
r
ain
tis
s
u
e
u
s
in
g
MRI
d
ata,
wh
ich
aim
s
to
r
ed
u
ce
n
o
is
e
an
d
en
h
a
n
ce
s
eg
m
en
t
atio
n
p
r
ec
is
io
n
[
3
]
.
R
an
d
o
m
f
o
r
est
class
if
ier
s
als
o
p
r
o
v
id
ed
f
o
r
ef
f
ec
tiv
e
class
if
ier
s
with
en
s
em
b
le
tech
n
iq
u
es
[
1
]
,
f
o
llo
wed
b
y
th
e
d
ec
is
io
n
tr
ee
ap
p
r
o
ac
h
with
d
if
f
e
r
en
t
d
ec
is
io
n
tr
ee
r
eg
r
ess
o
r
an
d
d
escr
ib
e
an
in
ter
p
r
e
tab
le
class
if
icatio
n
p
ath
,
an
d
n
aiv
e
b
ay
es
class
if
ie
r
s
also
p
r
o
v
id
ed
f
o
r
s
u
cc
ess
f
u
l
r
esu
lts
u
s
in
g
a
p
r
o
b
ab
ilis
tic
m
eth
o
d
f
o
r
9
9
.
3
2
%
ac
cu
r
ac
y
d
etec
tio
n
o
f
C
A
x
-
r
ay
s
tr
o
k
e
lesi
o
n
[
4
]
.
M
u
lti
-
lay
er
p
er
ce
p
tr
o
n
s
(
ML
P)'
,
h
av
e
h
ad
a
lo
wer
p
er
f
o
r
m
an
ce
o
f
ac
cu
r
ac
y
w
h
e
n
co
m
p
ar
ed
to
o
th
e
r
a
p
p
r
o
a
ch
es
[
1
]
.
Un
s
u
p
er
v
is
ed
id
ea
s
,
w
h
ich
wo
u
ld
i
n
clu
d
e
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es h
av
e
ch
an
g
ed
th
e
n
ew
lan
d
s
ca
p
e
f
o
r
m
ed
ical
im
ag
in
g
m
eth
o
d
s
.
Ho
w?
Fo
r
ex
am
p
le,
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs)
h
av
e
b
ee
n
r
ec
en
tl
y
claim
ed
as
g
o
ld
s
tan
d
ar
d
wi
th
well
-
d
ev
elo
p
e
d
m
u
ltip
le
ar
ch
itectu
r
al
s
o
p
h
is
tica
tio
n
d
e
m
o
n
s
tr
atin
g
ac
cu
r
ac
i
es
ab
o
v
e
9
9
.
8
7
%
f
o
r
b
r
ain
t
u
m
o
r
d
etec
tio
n
[
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
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
26
:
1
19
-
1
27
120
R
esNet
ar
ch
itectu
r
es
h
av
e
b
ee
n
p
ar
ticu
lar
ly
r
a
n
k
ed
as
R
esNet
-
5
0
with
id
en
tific
atio
n
o
f
ca
p
ab
ilit
y
to
ca
p
tu
r
e
elab
o
r
ate
s
p
atial
h
ier
ar
ch
ies
f
r
o
m
b
r
ain
MRI
s
ca
n
im
ag
es
with
9
0
.
0
4
%
ac
cu
r
ac
y
[
6
]
.
VGG
n
etwo
r
k
s
,
m
o
s
t
n
o
tab
ly
VGG
-
1
6
,
ar
e
s
tate
-
of
-
th
e
-
ar
t
f
o
r
d
etailed
f
ea
tu
r
e
e
x
t
r
ac
tio
n
an
d
ar
e
o
f
ten
u
tili
ze
d
i
n
co
m
b
i
n
atio
n
with
o
th
er
ar
ch
itectu
r
es,
as
p
ar
t
o
f
a
h
y
b
r
id
a
p
p
r
o
ac
h
[
7
]
.
T
h
e
U
-
Net
ar
ch
itectu
r
es
h
av
e
ch
a
n
g
ed
th
e
f
ield
with
th
eir
ab
ilit
y
to
p
r
esen
t
ex
a
ct
tu
m
o
r
b
o
u
n
d
a
r
ies
f
r
o
m
m
ed
ical
im
ag
e
s
eg
m
en
tatio
n
[
8
]
.
Mo
r
eo
v
e
r
,
au
to
en
co
d
er
s
an
d
v
a
r
iatio
n
s
o
f
au
to
e
n
co
d
e
r
s
,
s
u
ch
as
Var
iatio
n
al
Au
to
e
n
co
d
er
s
(
VAE
)
,
h
a
v
e
o
f
f
er
ed
ex
citin
g
n
ew
av
en
u
es
f
o
r
u
n
s
u
p
e
r
v
is
ed
an
o
m
aly
d
etec
tio
n
b
y
co
n
s
tr
u
ctin
g
n
o
r
m
al
b
r
ain
p
atter
n
s
,
an
d
d
etec
tin
g
an
o
m
alies
f
r
o
m
th
at
n
o
r
m
al
r
ec
o
n
s
tr
u
cted
r
ep
r
esen
tatio
n
[
9
]
.
E
f
f
icien
tNet
ar
ch
itectu
r
e
s
h
av
e
also
s
h
o
wn
in
tellig
en
t
o
r
ig
in
al
co
m
b
in
i
n
g
ex
ten
s
iv
e
f
ea
tu
r
e
s
elec
tio
n
s
,
with
n
u
m
b
er
s
r
ea
ch
in
g
9
9
.
5
1
%
o
v
er
all
ac
cu
r
ac
y
[
1
0
]
.
Den
s
eNe
t
an
d
o
th
er
n
o
v
el
an
d
m
o
d
er
n
ar
ch
it
ec
tu
r
es
h
av
e
p
r
o
v
e
n
th
at
it
is
p
o
s
s
ib
le
to
r
aise
th
e
ce
ilin
g
o
n
class
if
icatio
n
ca
p
ab
ilit
ies
[
8
]
.
Fu
r
th
er
m
o
r
e,
th
e
r
e
h
av
e
ev
en
b
ee
n
m
o
r
e
m
o
d
er
n
ad
v
an
ce
s
,
s
u
ch
as
T
r
an
s
f
o
r
m
e
r
(
i.e
.
T
r
an
s
f
o
r
m
e
r
s
with
atten
tio
n
)
b
ased
lear
n
in
g
m
o
d
els,
alth
o
u
g
h
th
eir
u
s
e
in
th
e
co
n
tex
t
o
f
m
ed
ical
im
ag
in
g
an
d
b
r
ain
M
R
I
s
h
as
o
n
ly
ju
s
t
s
tar
ted
to
b
e
f
u
lly
r
ea
lized
[
1
1
]
.
Her
e
g
en
e
r
atio
n
m
o
d
els
s
u
ch
as
g
en
er
ativ
e
ad
v
er
s
ar
ial
n
et
wo
r
k
s
(
GANs)
,
h
av
e
b
eg
u
n
t
o
b
e
im
p
lem
en
te
d
in
d
ata
au
g
m
en
tatio
n
f
o
r
tu
m
o
r
r
ec
o
n
s
tr
u
ctio
n
an
d
/o
r
g
e
n
er
at
io
n
o
f
s
y
n
th
etic
tr
ain
in
g
d
at
a
[
1
1
]
.
A
h
y
b
r
id
s
t
r
ateg
y
h
as
b
ee
n
u
s
ed
th
at
co
m
b
in
es
a
m
o
d
if
ie
d
C
NN
ar
ch
itectu
r
e
f
o
r
ac
c
u
r
ate
tu
m
o
r
class
if
icatio
n
an
d
a
U
-
Net
b
as
ed
m
o
d
el
f
o
r
r
o
b
u
s
t
tu
m
o
r
s
eg
m
en
tatio
n
[
1
2
]
.
An
o
th
er
p
o
ten
tial a
r
ea
is
in
m
o
d
eli
n
g
tem
p
o
r
al
MRI
s
ca
n
s
eq
u
en
ce
s
,
v
ia
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
n
etw
o
r
k
s
,
wh
ich
ca
n
p
r
o
v
e
to
b
e
im
p
o
r
tan
t
in
th
e
c
o
n
tex
t
o
f
tr
ac
k
in
g
d
is
ea
s
e
p
r
o
g
r
ess
io
n
[
1
1
]
.
Desp
ite
th
e
m
an
y
ef
f
o
r
ts
to
y
ield
d
if
f
e
r
en
t
alg
o
r
ith
m
s
to
en
h
a
n
ce
th
e
d
at
a
s
y
n
th
esis
,
th
er
e
is
s
till
a
lim
itatio
n
th
at
is
u
n
d
er
ly
in
g
th
e
tr
a
d
itio
n
al
ap
p
r
o
ac
h
[
1
3
]
,
[
1
4
]
.
Mo
s
t
m
eth
o
d
s
ten
d
to
b
e
eith
er
a
s
co
r
in
g
m
eth
o
d
,
o
r
th
ey
r
e
ly
o
n
lar
g
e
am
o
u
n
ts
o
f
lab
eled
d
atasets
to
tr
ain
o
n
,
wh
ich
m
ea
n
s
th
e
y
ar
e
esp
ec
ially
v
u
ln
er
a
b
le
wh
en
d
etec
tin
g
e
ar
ly
p
r
esen
c
e
o
f
d
if
f
icu
lt
to
s
ee
an
o
m
alies
wh
ich
h
a
v
e
n
o
t
co
n
d
itio
n
ed
an
y
o
f
t
h
e
ty
p
ical
s
ig
n
atu
r
es
th
at
th
e
u
s
ef
u
l
alg
o
r
ith
m
s
h
av
e
b
ee
n
tr
ain
e
d
[
1
3
]
,
[
1
4
]
.
T
h
e
c
o
m
p
lex
ity
an
d
v
ar
iab
ilit
y
o
f
b
r
ai
n
tu
m
o
r
s
m
ak
es
ea
r
l
y
-
s
tag
e
d
etec
tio
n
in
h
e
r
en
tly
d
if
f
icu
lt
as
ab
n
o
r
m
al
a
n
d
n
o
r
m
al
tis
s
u
es
m
ay
r
esem
b
le
ea
c
h
o
th
er
in
th
e
e
ar
ly
s
tag
es
[
5
]
,
[
1
5
]
.
T
h
e
m
ed
ical
co
n
s
eq
u
en
ce
s
o
f
d
elay
ed
d
ia
g
n
o
s
is
ar
e
e
x
ten
s
iv
e
an
d
q
u
an
tifia
b
le.
Fo
r
ex
am
p
le,
wh
e
n
b
r
ai
n
tu
m
o
r
s
ar
e
d
etec
ted
an
d
ar
e
less
th
an
3
cm
in
d
iam
eter
,
r
ate
o
f
c
o
m
p
lete
s
u
r
g
ical
r
em
o
v
al
(
g
r
o
s
s
r
esectio
n
)
n
ea
r
l
y
d
o
u
b
les
f
r
o
m
3
5
%
to
6
5
-
8
0
%
[
1
6
]
.
M
o
r
e
im
p
o
r
tan
tly
,
f
i
v
e
-
y
ea
r
s
u
r
v
iv
al
r
ates
f
o
r
m
alig
n
an
c
y
ca
n
in
cr
ea
s
e
4
0
-
6
0
%
with
ea
r
lier
d
etec
tio
n
[
1
6
]
.
T
h
er
e
was
in
d
ee
d
,
a
s
ig
n
if
ic
an
t
r
ec
en
t
s
cr
ee
n
in
g
s
tu
d
y
t
h
at
f
o
u
n
d
4
.
1
%
o
f
asy
m
p
to
m
atic
p
atien
ts
w
h
o
u
n
d
er
wen
t
an
MRI
an
d
h
a
d
a
n
ab
n
o
r
m
ality
th
at
war
r
a
n
ted
im
m
ed
ia
te
m
e
d
ical
atten
tio
n
.
T
h
is
h
ig
h
lig
h
ts
th
e
p
o
in
t th
at
s
ilen
t p
ath
o
lo
g
y
o
f
ten
p
r
ec
ed
es c
lin
ical
s
y
m
p
to
m
s
[
1
6
]
.
T
h
e
ch
allen
g
e
is
n
o
t
o
n
l
y
th
e
ac
cu
r
ac
y
o
f
d
etec
tio
n
.
T
h
e
p
o
o
l
o
f
d
ata
in
MRI
im
ag
in
g
is
b
ec
o
m
in
g
lar
g
er
,
an
d
th
e
lo
ad
o
n
r
ad
io
lo
g
is
ts
i
s
b
ec
o
m
in
g
g
r
ea
ter
,
it
w
ill
n
o
t
b
e
p
r
ac
tical
to
co
n
d
u
ct
m
an
u
al
in
s
p
ec
tio
n
s
o
f
MRI
d
ata
m
o
v
in
g
f
o
r
war
d
[
1
]
,
[
1
4
]
.
I
n
d
iv
i
d
u
al
h
u
m
an
in
ter
p
r
etatio
n
an
d
s
tan
d
ar
d
izatio
n
cr
ea
tes
v
ar
iatio
n
th
at
au
to
m
ated
s
y
s
tem
s
m
ay
b
e
ab
le
to
ad
d
r
ess
[
1
5
]
.
An
d
o
f
co
u
r
s
e,
f
o
r
t
h
e
p
ed
iatr
ic
a
n
d
y
o
u
n
g
ad
u
lt
ag
e
g
r
o
u
p
,
wh
er
e
o
v
er
1
7
,
6
0
0
p
eo
p
le
u
n
d
er
th
e
ag
e
o
f
3
9
ar
e
d
i
ag
n
o
s
ed
with
a
b
r
ain
tu
m
o
r
e
v
er
y
y
ea
r
in
th
e
US,
th
e
v
ar
io
u
s
n
o
n
s
p
ec
if
ic
s
y
m
p
to
m
s
will
lead
to
d
elay
s
in
m
a
k
in
g
th
e
co
r
r
ec
t
d
ia
g
n
o
s
is
[
1
7
]
,
[
1
8
]
.
As
p
ar
t
o
f
th
is
b
ac
k
d
r
o
p
o
f
co
m
p
u
tatio
n
al
in
n
o
v
atio
n
an
d
clin
ical
n
ee
d
is
t
h
e
in
v
er
s
e
o
f
th
e
b
elo
n
g
in
g
in
d
i
v
id
u
al
G
au
s
s
ian
p
r
o
b
ab
ilit
y
(
I
B
I
GP
)
alg
o
r
i
th
m
o
p
tio
n
th
at
is
p
o
ten
tially
n
o
t
th
e
s
am
e
as
th
e
m
ac
h
in
e
lear
n
in
g
o
r
d
ee
p
lear
n
in
g
o
p
tio
n
s
th
at
r
el
y
o
n
s
co
r
in
g
s
y
s
tem
o
r
class
if
icatio
n
b
o
u
n
d
ar
ies,
b
u
t
in
s
tead
is
b
ased
o
n
p
u
r
e
p
r
o
b
a
b
ilis
tic
r
ea
s
o
n
in
g
in
s
tead
.
I
n
s
u
m
m
ar
y
,
it
tak
es
an
MRI
im
ag
e(
s
)
an
d
c
o
n
v
er
ts
i
t
in
to
a
p
r
o
b
ab
ilit
y
s
p
ac
e,
ca
lled
I
B
I
GP
im
ag
es,
with
th
e
p
o
ten
tial
o
f
h
ig
h
lig
h
tin
g
s
u
b
tle
an
o
m
alie
s
th
at
T
r
ad
itio
n
al
s
co
r
in
g
/p
er
f
o
r
m
an
ce
alg
o
r
ith
m
s
m
ay
m
is
s
alto
g
eth
er
.
As
we
s
tan
d
o
n
th
e
c
u
s
p
o
f
co
n
ti
n
u
in
g
co
m
p
u
tatio
n
al
ad
v
an
ce
m
e
n
t
an
d
i
n
cr
ea
s
in
g
c
lin
ical
n
ee
d
,
m
o
v
in
g
to
war
d
m
o
r
e
s
en
s
itiv
e
d
etec
tio
n
to
o
ls
is
n
o
lo
n
g
er
s
im
p
ly
a
tech
n
ical
g
o
al,
b
u
t
a
h
u
m
a
n
itar
ian
o
b
ject
o
f
n
ec
ess
ity
[
1
1
]
,
[
1
3
]
,
[
1
4
]
.
Alg
o
r
ith
m
s
lik
e
I
B
I
GP
h
av
e
th
e
p
o
s
s
ib
ilit
y
to
wo
r
k
with
ex
is
tin
g
alg
o
r
ith
m
s
to
im
p
r
o
v
e
t
h
e
d
iag
n
o
s
is
p
o
p
u
latio
n
a
n
d
h
o
p
e
f
o
r
an
ea
r
lier
in
ter
v
en
tio
n
,
b
etter
p
atien
t r
esu
l
ts
,
an
d
h
av
e
liv
es sav
ed
b
y
e
ar
lier
d
etec
tio
n
.
T
h
e
o
b
jectiv
e
o
f
th
e
d
etec
tio
n
,
in
th
is
p
ap
er
,
is
to
p
u
r
s
u
e
an
y
c
h
an
g
es
th
at
m
ay
b
e
o
cc
u
r
r
in
g
b
ec
au
s
e
o
f
th
e
p
r
o
b
ab
le
i
n
cip
ie
n
t
ab
n
o
r
m
al
tis
s
u
e
in
a
h
u
m
a
n
b
r
ai
n
an
d
s
in
ce
t
h
e
r
e
is
litt
le
r
ea
l
-
wo
r
ld
m
ed
ical
i
m
a
g
e
d
ata
with
s
m
all
tu
m
o
r
s
i
n
it,
we
in
tr
o
d
u
ce
d
tu
m
o
r
-
lik
e
f
ea
tu
r
es
ar
tific
ially
in
to
b
r
ain
im
a
g
es.
T
h
e
d
etec
t
io
n
m
eth
o
d
p
r
o
ce
d
u
r
es,
p
r
o
p
o
s
ed
in
th
is
ar
ticle,
ar
e
alm
o
s
t
th
e
s
am
e
as
th
e
p
r
o
p
o
s
ed
tec
h
n
iq
u
es
i
n
th
e
liter
atu
r
e.
Ho
wev
e
r
,
th
e
d
if
f
er
en
c
e
o
f
th
e
I
B
I
GP/MR
I
m
eth
o
d
is
th
at
th
e
I
B
I
GP
is
ab
le
to
m
a
k
e
th
e
s
lig
h
test
ch
an
g
e
in
a
b
r
ai
n
tis
s
u
e
clea
r
ly
v
is
ib
le,
t
h
er
eb
y
ass
is
tin
g
in
th
e
d
etec
tio
n
o
f
th
e
in
cip
ien
t a
b
n
o
r
m
al
tis
s
u
e
as y
o
u
will see
b
elo
w.
2.
M
E
T
H
O
D
First,
we
s
tar
t
b
y
s
eg
m
en
tin
g
ea
ch
n
o
r
m
al
MRI
im
ag
e
m
atr
ix
lin
e
in
to
s
m
all
an
d
r
eg
u
lar
s
tatio
n
ar
y
in
ter
v
als
an
d
m
o
d
el
ea
ch
o
f
th
em
b
y
an
ad
e
q
u
ate
G
au
s
s
ian
wh
ite
n
o
is
e
(
GW
N)
[
1
9
]
,
f
o
r
ea
ch
in
ter
v
al,
we
will
ca
lcu
late
th
e
m
ea
n
an
d
v
ar
ian
ce
p
ar
a
m
eter
s
;
th
ese
p
ar
am
eter
s
will
r
ep
r
esen
t
ea
ch
s
e
g
m
en
t,
allo
win
g
u
s
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
I
n
cip
ien
t a
n
o
ma
lo
u
s
d
etec
tio
n
in
a
b
r
a
in
u
s
in
g
th
e
I
B
I
GP
a
l
g
o
r
ith
m
…
(
Mo
h
a
med
Hich
em
N
a
it
C
h
a
la
l)
121
to
ac
h
iev
e
co
m
p
r
ess
io
n
a
n
d
s
av
e
o
n
ly
t
h
e
p
ar
am
eter
s
in
s
te
ad
o
f
th
e
wh
o
le
im
ag
e,
On
ce
th
e
o
p
tim
al
GW
Ns
f
o
r
th
e
wh
o
le
m
atr
ix
ar
e
est
im
ated
,
we
r
ep
lace
th
eir
p
a
r
am
eter
s
wh
ich
ar
e
t
h
e
m
ea
n
s
an
d
v
ar
ian
ce
s
to
co
m
p
u
te
th
e
in
d
iv
id
u
al
p
r
o
b
a
b
ilit
y
o
f
ea
ch
in
ter
v
al
v
alu
e
o
f
th
e
ab
n
o
r
m
al
MRI
im
ag
e.
B
y
in
v
er
s
in
g
th
ese
p
r
o
b
a
b
ilit
ies,
we
o
b
tain
th
e
I
B
I
P
im
ag
e
o
f
th
e
ab
n
o
r
m
al
M
R
I
im
ag
e
.
T
h
e
I
B
I
GP
tech
n
iq
u
e
o
p
er
ates
th
r
o
u
g
h
two
p
r
in
cip
al
p
h
ases
:
m
o
d
elin
g
an
d
d
etec
tio
n
.
2
.
1
.
M
o
delin
g
ph
a
s
e
−
Step
1
:
Seg
m
en
t
ea
ch
MRI
im
ag
e
m
atr
ix
X
lin
e
in
to
s
m
all
en
o
u
g
h
s
tatio
n
ar
y
s
eg
m
en
ts
as
s
h
o
wn
in
Fig
u
r
e
1
an
d
th
e
(
1
)
:
Fig
u
r
e
1
.
Seg
m
e
n
tatio
n
o
f
in
p
u
t n
o
r
m
al
b
r
ain
im
a
g
e
in
to
L
s
eg
m
en
ts
=
[
1
(
0
)
1
(
1
)
1
(
−
1
)
⏟
…
…
…
1
(
·
−
1
)
2
(
0
)
2
(
1
)
…
…
…
2
(
·
−
1
)
⋮
⋮
⋮
⋮
⋮
(
0
)
(
1
)
…
…
…
(
·
−
1
)
]
(
1
)
−
Step
2
:
Use
(
2
)
an
d
(
3
)
to
e
s
tim
ate
th
e
p
ar
am
eter
s
o
f
ea
ch
n
o
r
m
al
lin
e
in
te
r
v
al
in
o
r
d
er
to
o
b
tain
a
n
ad
eq
u
ate
m
ath
e
m
atica
l m
o
d
el.
̂
,
=
1
∑
(
)
−
1
=
(
−
1
)
(
2
)
σ
̂
i
,
j
2
=
1
∑
(
x
i
(
n
)
−
m
̂
i
,
j
)
2
−
1
=
(
−
1
)
(
3
)
w
h
er
e
m
̂
i
,
j
an
d
σ
̂
i
,
j
2
ar
e
th
e
esti
m
ated
a
v
er
ag
e
an
d
v
a
r
ian
ce
o
f
ea
ch
in
ter
v
al
o
f
ea
c
h
lin
e
,
,
(
−
1
)
,
…
,
,
(
)
ar
e
th
e
v
alu
es o
f
th
e
ℎ
(
=
1
,
2
,
…
.
,
)
in
ter
v
al
,
is
th
e
in
ter
v
al
len
g
th
an
d
N
i
s
th
e
n
u
m
b
er
o
f
s
eg
m
e
n
ts
in
ea
ch
li
n
e
.
−
Step
3
:
T
h
e
r
ec
o
n
s
tr
u
ctio
n
o
f
ea
ch
n
o
r
m
al
GW
N
in
ter
v
al
ca
n
b
e
ac
h
iev
ed
u
s
in
g
th
e
b
u
ilt
-
in
f
u
n
ctio
n
“r
an
d
”
(
Scilab
,
Py
t
h
o
n
,
o
r
MA
T
L
AB
)
to
g
en
er
ate
th
e
GW
N
in
ter
v
al
o
f
L
s
am
p
les.
−
Step
4
:
Gath
er
th
ese
in
ter
v
als
in
o
r
d
er
to
r
ec
o
n
s
tr
u
ct
th
e
wh
o
le
im
ag
e
m
o
d
el
an
d
ch
ec
k
its
q
u
ality
b
y
co
m
p
ar
in
g
th
e
r
ec
o
n
s
tr
u
cted
i
m
ag
e
with
its
o
r
ig
in
al.
So
,
if
t
h
e
two
im
ag
es
ar
e
r
ea
s
o
n
a
b
ly
th
e
s
am
e,
s
av
e
th
ese
m
o
d
el
p
ar
am
eter
s
,
else,
r
ed
u
ce
s
lo
wly
th
e
in
ter
v
al
len
g
th
an
d
g
o
b
ac
k
to
s
tep
2
.
R
e
p
ea
t
th
e
s
tep
s
2
,
3
,
an
d
4
u
n
til
ac
h
iev
in
g
a
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MSE
)
le
s
s
th
an
0
.
0
1
c
o
r
r
esp
o
n
d
in
g
t
o
an
ac
ce
p
tab
le
r
ec
o
n
s
tr
u
ctio
n
(
Fig
u
r
e
2
)
.
On
c
e
th
e
m
ath
em
atica
l
m
o
d
el
is
r
ea
d
y
,
co
m
p
u
te
th
e
I
B
I
GP
o
f
e
ac
h
s
eg
m
en
t
o
f
each
n
o
r
m
al
im
ag
e
m
at
r
ix
lin
e
u
s
in
g
th
e
m
o
d
el
p
ar
a
m
eter
s
(
m
̂
i
,
j
,
σ
̂
i
,
j
2
)
g
iv
en
b
y
(
2
)
an
d
(
3
)
ab
o
v
e
t
o
o
b
tain
an
I
B
I
GP
m
atr
ix
(
in
4
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
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
26
:
1
19
-
1
27
122
Fig
u
r
e
2
.
M
o
d
elin
g
p
r
o
ce
s
s
o
f
n
o
r
m
al
im
a
g
e
with
d
if
f
e
r
en
t s
eg
m
en
ts
len
g
th
2
.
2
.
Det
ec
t
io
n pha
s
e
On
ce
an
ac
ce
p
tab
le
r
ec
o
n
s
tr
u
ctio
n
is
ac
h
iev
ed
,
co
m
p
u
te
th
e
in
v
er
s
e
o
f
th
e
p
r
o
b
a
b
ilit
y
o
f
ea
ch
in
ter
v
al
in
th
e
a
b
n
o
r
m
al
im
a
g
e
u
s
in
g
th
e
n
o
r
m
al
in
ter
v
al
GW
N
p
ar
am
eter
s
(
m
̂
i
,
j
an
d
σ
̂
i
,
j
2
)
in
(
2
)
an
d
(
3
)
to
o
b
tain
th
e
f
o
llo
win
g
I
B
I
GP m
atr
ix
r
ep
r
esen
tatio
n
o
f
th
e
ab
n
o
r
m
a
l im
ag
e.
IB
IP
=
[
1
p
̂
11
…
1
p
̂
1N
⋮
⋱
⋮
1
p
̂
I1
…
1
p
̂
IN
]
(
4
)
I
t
s
h
o
u
ld
b
e
n
o
ted
th
at
th
e
m
ai
n
id
ea
o
f
th
e
I
B
I
P
alg
o
r
ith
m
is
to
co
n
s
id
er
an
y
an
o
m
alo
u
s
(
c
h
an
g
e)
in
th
e
b
r
ain
MRI
im
ag
e
as
a
r
ar
e
ev
en
t
co
m
p
ar
ed
to
th
e
n
o
r
m
al
MRI
im
ag
e.
Fig
u
r
e
3
illu
s
tr
ate
s
th
is
p
r
in
cip
le
b
y
co
m
p
ar
in
g
a
s
tan
d
a
r
d
Ga
u
s
s
ian
d
is
tr
ib
u
tio
n
with
its
in
v
er
s
e
tr
an
s
f
o
r
m
atio
n
.
T
h
e
Gau
s
s
ian
p
r
o
b
ab
ilit
y
g
iv
en
b
y
(
5
)
b
elo
w,
to
b
el
o
n
g
to
t
h
e
n
o
r
m
al
MRI,
s
h
o
u
ld
b
e
v
er
y
s
m
all
as
in
d
icate
d
in
Fig
u
r
e
3
(
a
)
.
So
,
b
y
in
v
er
s
in
g
th
e
p
r
o
b
ab
ilit
ies
o
f
th
e
a
b
n
o
r
m
al
d
ata,
we
o
b
tain
v
er
y
b
ig
p
r
o
b
a
b
ilit
y
in
v
er
s
e
v
al
u
es
co
r
r
esp
o
n
d
i
n
g
to
r
ar
e
ev
en
ts
(
an
o
m
al
o
u
s
)
as
illu
s
tr
a
ted
in
Fig
u
r
e
3
(
b
)
.
T
h
e
b
asic
id
ea
o
f
t
h
e
I
B
I
P
alg
o
r
ith
m
is
alr
ea
d
y
d
escr
ib
ed
elsewh
er
e
[
2
0
]
,
[
2
1
]
a
n
d
is
r
ep
o
r
te
d
in
t
h
e
f
o
llo
win
g
f
o
r
m
o
r
e
co
n
v
en
ien
ce
.
T
h
e
i
n
d
iv
id
u
al
g
au
s
s
ian
p
r
o
b
a
b
ilit
y
o
f
ea
c
h
s
am
p
le
n
f
o
r
ea
ch
in
te
r
v
al
j in
th
e
ℎ
lin
e
is
ex
p
r
ess
ed
as f
o
llo
ws:
̂
,
(
)
=
1
̂
,
√
2
e
xp
[
−
(
,
(
)
−
̂
,
)
2
2
̂
,
2
]
(
5
)
an
d
its
in
v
er
s
e
is
:
1
̂
,
(
)
=
̂
,
√
2
e
xp
[
(
,
(
)
−
̂
,
)
2
2
̂
,
2
]
(
6
)
wh
er
e
m
̂
i
,
j
an
d
σ
̂
i
,
j
2
ar
e
th
e
esti
m
ated
v
ar
ian
ce
an
d
a
v
er
ag
e
o
f
ea
c
h
m
atr
ix
lin
e
in
ter
v
al
r
esp
ec
tiv
e
ly
.
Sin
ce
th
e
Gau
s
s
ian
law
i
s
s
y
m
m
etr
ical
with
r
esp
ec
t
to
th
e
av
er
ag
e,
t
h
e
r
ar
e
ev
en
ts
(
p
i
x
els)
co
r
r
es
p
o
n
d
in
g
to
in
cip
ien
t
ab
n
o
r
m
al
tis
s
u
es
lie
o
n
b
o
th
t
ails
o
f
th
e
Gau
s
s
ian
law
Fig
u
r
e
3
(
a)
.
So
,
b
y
in
v
e
r
s
in
g
th
e
p
r
o
b
a
b
ilit
y
o
f
ea
ch
p
ix
el
v
alu
e
o
f
th
e
im
a
g
e
wit
h
ea
r
ly
an
o
m
al
o
u
s
,
th
e
p
r
o
b
ab
ilit
y
in
v
er
s
e
(
6
)
o
f
t
h
ese
r
ar
e
ev
en
ts
will
r
is
e
ex
p
o
n
e
n
tially
,
wh
er
ea
s
th
o
s
e
b
elo
n
g
in
g
to
th
e
o
r
ig
in
al
im
a
g
e
(
n
o
r
m
al)
will
r
em
ai
n
eq
u
al
t
o
ze
r
o
,
as
s
h
o
wn
in
Fig
u
r
e
3
(
b
)
.
Fig
u
r
e
4
illu
s
tr
ates
th
e
co
m
p
lete
f
lo
wch
ar
t
o
f
th
e
I
B
I
GP
alg
o
r
ith
m
.
T
h
e
m
o
d
elin
g
p
h
ase
(
lef
t
p
an
el)
in
v
o
lv
es
s
eg
m
en
tin
g
n
o
r
m
al
MRI
im
ag
es,
esti
m
atin
g
s
t
atis
tical
p
ar
am
eter
s
,
an
d
iter
ativ
ely
r
ef
in
in
g
t
h
e
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
I
n
cip
ien
t a
n
o
ma
lo
u
s
d
etec
tio
n
in
a
b
r
a
in
u
s
in
g
th
e
I
B
I
GP
a
l
g
o
r
ith
m
…
(
Mo
h
a
med
Hich
em
N
a
it
C
h
a
la
l)
123
m
o
d
el.
T
h
e
d
etec
tio
n
p
h
ase
(
r
ig
h
t
p
an
el)
ap
p
lies
th
ese
p
ar
am
eter
s
to
a
b
n
o
r
m
al
im
ag
es,
co
m
p
u
tin
g
in
v
er
s
e
p
r
o
b
a
b
ilit
ies to
h
ig
h
lig
h
t a
n
o
m
alies a
s
b
r
ig
h
t sp
o
ts
in
th
e
o
u
tp
u
t.
(
a)
(
b
)
Fig
u
r
e
3
.
I
ll
u
s
tr
atio
n
o
f
t
h
e
co
r
e
I
B
I
GP p
r
in
cip
le
f
o
r
en
h
an
ci
n
g
r
ar
e
ev
en
t
v
is
ib
ilit
y
(
a)
Gau
s
s
ian
law
an
d
(
b
)
its
co
r
r
esp
o
n
d
in
g
m
o
d
if
ied
in
v
er
s
e
(
I
B
I
GP)
Fig
u
r
e
4
.
Flo
wch
ar
t
o
f
th
e
I
B
I
GP a
lg
o
r
ith
m
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
Fig
u
r
e
5
p
r
esen
ts
a
b
aselin
e
c
o
m
p
ar
is
o
n
b
etwe
en
a
n
o
r
ig
in
a
l
MRI
s
ca
n
an
d
its
I
B
I
GP
tr
an
s
f
o
r
m
atio
n
f
o
r
a
h
ea
lth
y
b
r
ain
.
Fig
u
r
e
5
(
a)
in
d
icate
s
th
e
r
ef
er
en
ce
b
r
ain
MRI
im
ag
e
at
b
aselin
e
p
r
io
r
to
th
e
v
is
ib
le
d
ev
elo
p
m
e
n
t o
f
tis
s
u
e
g
r
o
wth
,
wh
er
ea
s
Fig
u
r
e
5
(
b
)
s
h
o
ws its
co
r
r
esp
o
n
d
in
g
I
B
I
GP r
ef
er
en
ce
im
ag
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
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
26
:
1
19
-
1
27
124
(
a)
(
b
)
Fig
u
r
e
5
.
B
aselin
e
r
ef
er
e
n
ce
i
m
ag
es f
o
r
n
o
r
m
al
b
r
ain
tis
s
u
e
(
a)
t
h
e
MRI
b
ef
o
r
e
an
y
tis
s
u
e
g
r
o
wth
an
d
(
b
)
its
co
r
r
esp
o
n
d
in
g
I
B
I
GP im
ag
e
Fig
u
r
e
6
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
I
B
I
GP
alg
o
r
ith
m
'
s
ef
f
ec
tiv
en
ess
in
in
cr
ea
s
in
g
th
e
v
is
u
al
d
etec
tio
n
o
f
ea
r
ly
ch
a
n
g
es
in
b
r
ai
n
ti
s
s
u
e.
T
h
e
o
r
ig
in
al
MRI
is
s
h
o
wn
in
Fig
u
r
e
6
(
a
)
,
an
d
its
co
r
r
esp
o
n
d
i
n
g
I
B
I
GP
im
ag
e
is
p
r
esen
ted
i
n
Fig
u
r
e
6
(
b
)
.
T
h
e
e
x
tr
ac
ted
G
au
s
s
ian
s
tatis
tical
f
ea
tu
r
es
(
th
e
m
ea
n
s
an
d
v
ar
ia
n
ce
s
o
f
s
tatio
n
ar
y
in
ter
v
als
alo
n
g
ea
c
h
o
f
th
e
r
o
ws
in
th
e
m
atr
ix
)
wer
e
estab
lis
h
ed
o
r
d
e
v
elo
p
e
d
u
s
in
g
th
e
I
B
I
GP
alg
o
r
ith
m
.
T
h
ese
s
tatis
tical
p
ar
am
eter
s
r
ep
r
esen
t
th
e
d
is
tr
ib
u
tio
n
f
o
r
n
o
r
m
al
b
r
ain
tis
s
u
e
an
d
p
r
o
v
id
e
a
r
eliab
le
m
o
d
el
o
f
h
ea
lth
y
b
e
h
av
io
r
.
W
h
en
t
h
e
m
o
d
el
o
f
n
o
r
m
al
b
r
ain
tis
s
u
e
is
ap
p
lied
to
n
ew
im
ag
es,
it
o
r
ig
in
ates
a
m
ea
n
s
th
at
allo
w
s
u
s
to
co
n
s
id
er
h
o
w
lik
el
y
it
is
th
at
ea
ch
p
ix
el
v
alu
e
b
elo
n
g
s
to
th
e
"n
o
r
m
al"
d
is
tr
ib
u
tio
n
.
T
h
e
in
v
e
r
s
e
p
r
o
b
ab
ilit
ies
co
m
p
u
ted
u
s
in
g
th
is
m
o
d
el
p
r
o
v
id
e
em
p
h
asis
o
n
r
eg
io
n
s
o
f
ab
n
o
r
m
ality
(
h
ig
h
lig
h
tin
g
)
s
o
th
at
ch
an
g
es
th
at
a
r
e
r
elativ
ely
s
m
a
ll
ar
e
m
ad
e
s
ig
n
if
ica
n
tly
m
o
r
e
v
is
ib
le
as
s
h
o
wn
in
Fig
u
r
e
6
(
b
)
.
T
h
e
o
r
i
g
in
al
MRI
im
ag
e
Fig
u
r
e
6
(
a)
co
n
tain
s
ea
r
ly
s
tag
e
tis
s
u
e
ch
an
g
es
th
at
h
av
e
n
o
t
g
o
n
e
u
n
n
o
ticed
b
ec
au
s
e
th
er
e
ar
e
ch
an
g
es
th
at
ar
e
v
is
u
ally
i
n
d
is
tin
ct
an
d
n
ea
r
ly
im
p
o
s
s
ib
le
to
p
er
ce
iv
e
ev
en
b
y
th
e
n
ak
e
d
ey
e
with
s
im
p
le
im
ag
e
p
r
o
ce
s
s
in
g
f
u
n
ctio
n
ali
ties
.
Ag
ain
,
th
ese
s
u
b
tle
s
p
o
ts
ca
n
b
e
o
v
er
lo
o
k
ed
en
tire
ly
l
ea
d
in
g
to
th
e
m
is
s
ed
o
r
d
elay
ed
d
ia
g
n
o
s
is
.
Ho
wev
er
,
as
s
h
o
wn
in
Fig
u
r
e
6
(
b
)
,
t
h
e
m
o
d
el
b
u
ilt
with
th
e
I
B
I
GP
alg
o
r
ith
m
s
tar
ted
t
o
s
h
o
w
a
d
r
am
atic
im
p
r
o
v
e
m
en
t
in
th
e
h
ig
h
lig
h
ts
o
f
t
h
e
ch
an
g
es.
T
h
e
r
eg
io
n
s
I
h
av
e
d
r
awn
ar
r
o
ws
o
n
,
in
d
ic
ated
th
e
in
cip
ien
t
p
ath
s
p
h
y
s
io
lo
g
ical
alter
atio
n
s
r
elate
d
t
o
b
r
ain
p
ath
o
l
o
g
y
,
wh
er
e
n
o
w
s
ig
n
if
ican
tly
m
o
r
e
v
is
ib
le.
T
h
e
im
p
r
o
v
em
e
n
t
co
m
es
as
a
s
tat
is
tica
l
s
u
p
p
r
ess
io
n
o
f
"n
o
r
m
al"
r
eg
io
n
s
,
wh
ile
en
h
a
n
cin
g
th
e
p
r
esen
ce
o
f
d
e
v
iatio
n
s
f
r
o
m
th
e
lear
n
e
d
G
au
s
s
ian
m
o
d
el.
T
h
e
o
v
er
all
r
es
u
lts
s
tr
o
n
g
ly
s
u
p
p
o
r
t
th
at
t
h
e
I
B
I
GP/MR
I
p
latf
o
r
m
will
p
r
o
v
id
e
v
alu
e
b
y
r
o
u
tin
ely
ap
p
ly
in
g
th
is
co
m
p
r
eh
e
n
s
iv
e
ap
p
r
o
ac
h
to
r
ea
l
-
wo
r
ld
d
iag
n
o
s
tics
,
wh
ich
will
r
ev
ea
l
ch
an
g
es
in
cir
cu
latio
n
an
d
s
tr
u
ctu
r
e
im
m
ed
iately
,
an
d
with
co
n
f
id
e
n
ce
s
o
th
at
a
n
y
h
id
d
en
ab
n
o
r
m
alities
d
o
n
o
t
f
ester
u
n
til
m
o
r
e
clin
ically
p
r
o
b
lem
atic
s
tates
estab
lis
h
.
W
ith
a
r
elativ
ely
lo
w
MSE
(
MSE
<
0
.
0
1
)
ass
o
ciate
d
with
th
e
m
o
d
el
in
r
ec
o
n
s
tr
u
ctin
g
n
o
r
m
al
b
eh
av
io
r
ea
ch
tim
e
it
is
u
s
ed
f
o
r
ea
c
h
im
a
g
e,
a
n
d
h
ig
h
d
ete
ctio
n
r
ates,
it
is
e
v
id
en
t
th
a
t
I
B
I
GP
is
n
o
t
s
im
p
ly
an
en
h
an
ce
m
e
n
t
to
o
l
f
o
r
v
is
u
ally
d
ep
ictiv
e
im
ag
in
g
,
it
is
a
s
tati
s
tical
an
d
ev
id
en
ce
-
b
ased
g
u
id
e
to
d
ec
is
io
n
m
ak
in
g
.
C
o
m
p
ar
ed
t
o
co
n
v
en
tio
n
al
s
u
p
er
v
is
ed
d
e
ep
lear
n
in
g
ap
p
r
o
a
ch
es,
s
u
ch
as
t
h
e
f
in
e
-
tu
n
e
d
E
f
f
icien
tNet
ar
ch
itectu
r
es
wh
ich
h
av
e
ac
h
iev
ed
h
ig
h
ac
cu
r
ac
y
in
b
r
ai
n
tu
m
o
r
class
if
icatio
n
[
2
2
]
,
th
e
I
B
I
GP
alg
o
r
ith
m
d
em
o
n
s
tr
ates
d
is
tin
ct
ad
v
an
ta
g
es
in
th
e
co
n
tex
t
o
f
in
cip
ien
t
an
o
m
aly
d
etec
tio
n
.
W
h
ile
s
u
p
er
v
is
ed
C
NNs
ar
e
r
o
b
u
s
t
wh
en
ab
u
n
d
an
t
lab
eled
d
ata
is
av
ailab
le,
th
ey
o
f
ten
s
tr
u
g
g
le
to
g
en
e
r
alize
to
s
u
b
tle
o
r
r
ar
e
an
o
m
alies
th
at
d
ev
iate
f
r
o
m
th
e
t
r
ain
in
g
d
is
tr
ib
u
tio
n
.
T
o
a
d
d
r
ess
th
e
li
m
itatio
n
s
o
f
s
u
p
er
v
is
io
n
,
u
n
s
u
p
er
v
is
ed
g
e
n
er
ativ
e
m
o
d
els,
s
p
ec
if
ically
GANs
a
n
d
VAE
s
h
av
e
b
ee
n
wid
ely
ad
o
p
ted
f
o
r
m
ed
ical
a
n
o
m
aly
d
etec
tio
n
i
n
b
r
ai
n
MRI
[
2
3
]
.
T
h
ese
m
eth
o
d
s
,
alo
n
g
with
b
r
o
ad
er
d
ee
p
an
o
m
aly
d
etec
tio
n
f
r
am
ew
o
r
k
s
[
2
4
]
,
ty
p
ically
id
en
tif
y
ab
n
o
r
m
alities
b
y
lear
n
i
n
g
t
h
e
m
an
if
o
ld
o
f
n
o
r
m
al
tis
s
u
e
an
d
f
lag
g
in
g
d
ev
iatio
n
s
.
Ho
we
v
er
,
th
ey
o
f
ten
r
eq
u
ir
e
s
ig
n
if
ican
t
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
f
o
r
tr
a
i
n
in
g
an
d
in
f
er
e
n
ce
.
I
n
p
a
r
allel,
class
ical
s
tati
s
tical
d
etec
to
r
s
lik
e
L
o
ca
l
Ou
tlier
Facto
r
(
L
OF)
a
n
d
I
s
o
latio
n
Fo
r
ests
r
em
ain
p
o
p
u
lar
f
o
r
th
eir
co
m
p
u
tatio
n
al
ef
f
icien
cy
,
b
u
t
t
h
eir
p
er
f
o
r
m
an
ce
c
an
d
eg
r
a
d
e
o
n
c
o
m
p
lex
,
h
ig
h
-
d
im
en
s
io
n
al
im
ag
in
g
d
ata,
wh
e
r
e
s
u
b
tle
an
o
m
alies
ar
e
em
b
ed
d
ed
in
r
ich
tex
tu
r
e
p
atter
n
s
[
2
5
]
,
W
h
ile
ad
v
an
ce
d
d
ee
p
lear
n
in
g
s
eg
m
en
tatio
n
m
o
d
els
(
e.
g
.
,
U
-
Net
v
ar
ian
ts
)
o
f
f
e
r
h
ig
h
p
r
ec
is
io
n
,
th
er
e
is
a
g
r
o
win
g
n
ee
d
f
o
r
ef
f
icien
t,
lo
w
-
r
eso
u
r
ce
alter
n
ativ
es
f
o
r
p
r
ac
tical
clin
ical
d
ep
lo
y
m
e
n
t
[
1
2
]
.
I
n
th
is
lan
d
s
ca
p
e,
I
B
I
GP
o
cc
u
p
ies
a
u
n
iq
u
e
n
ich
e:
it
o
p
er
ates
o
n
a
p
r
o
b
ab
ilis
tic
in
v
er
s
io
n
p
r
in
cip
le
th
at
is
co
m
p
u
tatio
n
ally
lig
h
ter
th
an
GAN
-
b
ased
m
eth
o
d
s
wh
ile
o
f
f
e
r
in
g
s
u
p
er
io
r
s
en
s
itiv
ity
to
s
u
b
tle,
ea
r
ly
-
s
tag
e
tis
s
u
e
ch
an
g
es c
o
m
p
ar
e
d
to
tr
ad
itio
n
al
s
tatis
tical
o
r
s
u
p
er
v
is
ed
b
aselin
es.
R
ec
o
g
n
izin
g
th
e
co
n
ti
n
u
ed
i
m
p
o
r
tan
ce
o
f
co
m
p
lem
en
tar
y
s
tatis
tical
ap
p
r
o
ac
h
es,
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
f
o
r
th
is
wo
r
k
in
cl
u
d
e
ex
te
n
d
in
g
I
B
I
GP
to
p
r
o
ce
s
s
th
r
ee
-
d
im
e
n
s
io
n
al
MRI
v
o
l
u
m
es,
in
teg
r
atin
g
it
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
I
n
cip
ien
t a
n
o
ma
lo
u
s
d
etec
tio
n
in
a
b
r
a
in
u
s
in
g
th
e
I
B
I
GP
a
l
g
o
r
ith
m
…
(
Mo
h
a
med
Hich
em
N
a
it
C
h
a
la
l)
125
with
d
ee
p
lear
n
i
n
g
class
if
ier
s
as
an
in
itial
p
r
ep
r
o
ce
s
s
in
g
s
tep
to
en
h
a
n
ce
o
v
er
all
s
en
s
itiv
ity
to
in
cip
ien
t
ch
an
g
es,
an
d
v
alid
atin
g
t
h
e
m
eth
o
d
u
s
in
g
s
tan
d
ar
d
ize
d
b
en
ch
m
a
r
k
d
atasets
s
u
ch
a
s
B
r
aT
S
to
en
ab
le
co
m
p
r
eh
e
n
s
iv
e
co
m
p
ar
is
o
n
wi
th
s
tate
-
of
-
th
e
-
ar
t a
n
o
m
aly
d
et
ec
tio
n
m
eth
o
ds
(
a
)
(
b
)
Fig
u
r
e
6
.
Dete
ctio
n
o
f
in
ci
p
ien
t b
r
ain
a
n
o
m
alies u
s
in
g
th
e
I
B
I
GP a
lg
o
r
ith
m
ac
r
o
s
s
m
u
ltip
le
p
atien
t c
ases
(
a)
th
e
MRI
with
in
cip
ien
t a
b
n
o
r
m
al
tis
s
u
e
g
r
o
wth
a
n
d
(
b
)
its
co
r
r
esp
o
n
d
in
g
I
B
I
GP im
ag
e
4.
CO
NCLU
SI
O
N
W
e
h
av
e
ap
p
lied
th
e
I
B
I
GP
tech
n
iq
u
e
to
th
e
b
r
ai
n
MRI
to
en
h
an
ce
th
e
d
etec
tio
n
o
f
an
y
in
cip
ien
t
an
o
m
alo
u
s
g
r
o
wth
o
f
a
b
r
ai
n
tis
s
u
e.
W
e
h
av
e
s
h
o
wn
th
at
th
e
m
ain
s
tr
en
g
th
o
f
th
is
tech
n
iq
u
e
is
th
at
it
ca
n
ex
p
o
n
e
n
tially
m
a
g
n
if
y
th
e
M
R
I
im
ag
e
s
p
o
t
in
ten
s
ity
co
r
r
esp
o
n
d
in
g
t
o
th
e
in
ci
p
ien
t
c
h
an
g
e
an
d
r
e
d
u
ce
to
ze
r
o
th
o
s
e
b
elo
n
g
in
g
to
th
e
o
r
i
g
in
al
im
ag
e
b
ef
o
r
e
a
n
y
ch
an
g
e.
I
t,
th
u
s
,
r
en
d
e
r
s
th
e
in
cip
ien
t
an
o
m
alo
u
s
ch
an
g
e
m
u
ch
ea
s
ier
to
d
etec
t.
W
e
h
av
e
s
h
o
wn
,
in
ad
d
itio
n
,
o
n
e
o
f
th
e
m
ajo
r
ad
v
an
tag
es
o
f
th
e
I
B
I
GP/MR
I
t
ec
h
n
iq
u
e
is
it
s
ab
ilit
y
to
s
to
ck
m
o
r
e
d
a
ta
th
an
th
e
d
ir
ec
t
co
m
p
ar
is
o
n
b
etwe
en
im
ag
es.
W
e
b
eliev
e
,
th
er
ef
o
r
e,
th
at
th
e
I
B
I
GP/MR
I
tech
n
iq
u
e
h
as
a
g
r
ea
t
p
o
ten
tial
in
en
h
a
n
cin
g
t
h
e
in
cip
ien
t
ab
n
o
r
m
al
tis
s
u
e
g
r
o
wth
d
etec
tio
n
in
h
u
m
an
b
r
ain
.
is
,
th
er
ef
o
r
e,
a
v
er
y
p
r
o
m
is
in
g
tech
n
iq
u
e
f
o
r
in
cip
ien
t
an
o
m
al
o
u
s
ch
an
g
e
in
a
b
r
ain
an
d
ca
n
b
e
co
n
s
id
er
ed
as
a
cr
u
cial
s
tep
to
war
d
s
a
v
er
y
im
p
o
r
tan
t
en
h
an
ce
m
en
t
o
f
in
cip
ien
t
ab
n
o
r
m
al
tis
s
u
e
g
r
o
wth
d
etec
tio
n
in
h
u
m
an
b
r
ain
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
was in
v
o
lv
ed
in
th
e
r
esear
ch
d
escr
ib
ed
in
th
is
ar
t
icle.
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
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
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
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
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
26
:
1
19
-
1
27
126
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Mo
h
am
ed
Hich
em
Nait
C
h
alal
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
B
en
ab
d
ellah
Yag
o
u
b
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sid
ah
m
ed
Hen
n
i
✓
✓
✓
✓
✓
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
si
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
m
i
n
i
s
t
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
s
i
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
aila
b
le
o
n
r
eq
u
est
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
,
[
M
.
N]
.
T
h
e
d
ata,
wh
ich
co
n
tain
in
f
o
r
m
atio
n
th
at
co
u
ld
co
m
p
r
o
m
is
e
th
e
p
r
iv
ac
y
o
f
r
esear
c
h
p
ar
ticip
an
ts
,
ar
e
n
o
t p
u
b
licly
a
v
ailab
le
d
u
e
to
ce
r
tain
r
estrictio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
H
.
N
e
g
i
,
A
.
B
h
a
t
t
,
S
.
D
i
mr
i
,
a
n
d
B
.
K
u
m
a
r
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
i
n
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
re
n
d
s
i
n
E
l
e
c
t
r
o
n
i
c
s
a
n
d
I
n
f
o
rm
a
t
i
c
s,
I
C
O
EI
2
0
2
3
-
Pr
o
c
e
e
d
i
n
g
s
,
I
EEE,
A
p
r
.
2
0
2
3
,
p
p
.
1
1
8
1
–
1
1
8
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
EI
5
6
7
6
5
.
2
0
2
3
.
1
0
1
2
5
6
6
7
.
[
2
]
R
.
K
i
r
t
a
n
i
a
,
S
.
M
i
t
r
a
,
a
n
d
B
.
U
.
S
h
a
n
k
a
r
,
“
A
n
o
v
e
l
a
d
a
p
t
i
v
e
k
-
N
N
c
l
a
ssi
f
i
e
r
f
o
r
h
a
n
d
l
i
n
g
i
m
b
a
l
a
n
c
e
:
a
p
p
l
i
c
a
t
i
o
n
t
o
b
r
a
i
n
M
R
I
,
”
I
n
t
e
l
l
i
g
e
n
t
D
a
t
a
An
a
l
y
si
s
,
v
o
l
.
2
4
,
n
o
.
4
,
p
p
.
9
0
9
–
9
2
4
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
2
3
3
/
I
D
A
-
1
9
4
6
4
7
.
[
3
]
H
.
H
.
Jab
b
a
r
,
R
.
M
.
M
u
t
t
a
s
h
e
r
,
a
n
d
A
.
F
.
D
a
k
h
i
l
,
“
S
e
g
me
n
t
a
t
i
o
n
o
f
b
r
a
i
n
t
i
ss
u
e
u
si
n
g
i
m
p
r
o
v
e
d
k
e
r
n
e
l
i
z
e
d
r
o
u
g
h
-
f
u
z
z
y
c
-
m
e
a
n
s
t
e
c
h
n
i
q
u
e
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
2
,
n
o
.
1
,
p
p
.
2
1
6
–
2
2
6
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
2
.
i
1
.
p
p
2
1
6
-
2
2
6
.
[
4
]
S.
Ja
y
a
c
h
i
t
r
a
a
n
d
A
.
P
r
a
sa
n
t
h
,
“
M
u
l
t
i
-
f
e
a
t
u
r
e
a
n
a
l
y
s
i
s
f
o
r
a
u
t
o
m
a
t
e
d
b
r
a
i
n
s
t
r
o
k
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
w
e
i
g
h
t
e
d
g
a
u
ssi
a
n
n
a
ï
v
e
b
a
y
e
s
c
l
a
s
si
f
i
e
r
,
”
J
o
u
r
n
a
l
o
f
C
i
r
c
u
i
t
s,
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
e
rs
,
v
o
l
.
3
0
,
n
o
.
1
0
,
p
.
2
1
5
0
1
7
8
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
8
1
2
6
6
2
1
5
0
1
7
8
4
.
[
5
]
K
.
N
a
r
a
y
a
n
a
sam
y
,
El
a
n
g
o
v
a
n
,
L.
S
.
K
u
mar,
M
.
M
a
r
a
g
a
t
h
a
r
a
j
a
n
,
a
n
d
D
.
D
e
e
p
a
,
“
C
N
N
-
b
a
se
d
D
e
e
p
Le
a
r
n
i
n
g
A
p
p
r
o
a
c
h
f
o
r
M
R
I
-
b
a
s
e
d
B
r
a
i
n
T
u
mo
r
D
e
t
e
c
t
i
o
n
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
4
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
m
a
rt
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
O
S
E
C
2
0
2
3
,
I
EEE,
S
e
p
.
2
0
2
3
,
p
p
.
8
7
5
–
879
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
S
EC
5
8
1
4
7
.
2
0
2
3
.
1
0
2
7
6
0
8
6
.
[
6
]
A
.
R
a
m
a
n
a
g
i
r
i
,
M
.
M
u
k
u
n
t
h
a
n
,
a
n
d
G
.
B
a
l
a
m
u
r
u
g
a
n
,
“
E
n
h
a
n
c
e
d
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
r
e
sn
et
-
5
0
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
4
1
0
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
I
C
C
S
P
2
0
2
4
,
I
EEE,
A
p
r
.
2
0
2
4
,
p
p
.
1
7
0
8
–
1
7
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
S
P
6
0
8
7
0
.
2
0
2
4
.
1
0
5
4
3
7
4
2
.
[
7
]
Y
.
M
.
R
o
p
a
,
K
.
R
.
M
o
o
n
,
a
n
d
T.
S
i
n
g
h
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
h
y
b
r
i
d
f
r
a
m
e
w
o
r
k
u
t
i
l
i
z
i
n
g
o
p
e
n
C
V
a
n
d
C
N
N
f
o
r
a
u
t
o
ma
t
e
d
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
a
n
d
M
R
I
i
ma
g
e
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
i
n
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
u
s
t
a
i
n
a
b
l
e
Ex
p
e
rt
S
y
st
e
m
s,
I
C
S
E
S
2
0
2
4
-
Pro
c
e
e
d
i
n
g
s
,
I
EEE,
O
c
t
.
2
0
2
4
,
p
p
.
1
6
7
4
–
1
6
8
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
ES6
3
4
4
5
.
2
0
2
4
.
1
0
7
6
2
9
9
1
.
[
8
]
S
.
S
a
e
e
d
i
,
S
.
R
e
z
a
y
i
,
H
.
K
e
sh
a
v
a
r
z
,
a
n
d
S
.
R
.
N
.
K
a
l
h
o
r
i
,
“
M
R
I
-
b
a
se
d
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
d
e
e
p
l
e
a
r
n
i
n
g
met
h
o
d
s
a
n
d
c
h
o
se
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
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
si
o
n
Ma
k
i
n
g
,
v
o
l
.
2
3
,
n
o
.
1
,
p
.
1
6
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
9
1
1
-
0
2
3
-
0
2
1
1
4
-
6.
[
9
]
R
.
G
i
a
n
c
o
t
t
i
,
U
.
Lo
m
o
i
o
,
P
.
V
e
l
t
r
i
,
P
.
H
.
G
u
z
z
i
,
a
n
d
P
.
V
i
z
z
a
,
“
A
ma
c
h
i
n
e
-
l
e
a
r
n
i
n
g
b
a
se
d
t
o
o
l
f
o
r
b
i
o
i
ma
g
e
s
ma
n
a
g
i
n
g
a
n
d
a
n
n
o
t
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
2
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Bi
o
i
n
f
o
rm
a
t
i
c
s
a
n
d
Bi
o
m
e
d
i
c
i
n
e
,
BI
BM
2
0
2
2
,
I
EEE,
D
e
c
.
2
0
2
2
,
p
p
.
2
5
8
9
–
2
5
9
4
,
d
o
i
:
1
0
.
1
1
0
9
/
B
I
B
M
5
5
6
2
0
.
2
0
2
2
.
9
9
9
5
6
0
8
.
[
1
0
]
M
.
M
u
j
a
h
i
d
,
A
.
R
e
h
m
a
n
,
F
.
S
.
A
l
a
m
r
i
,
S
.
A
l
o
t
a
i
b
i
,
a
n
d
T
.
S
a
b
a
,
“
B
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
t
h
r
o
u
g
h
n
o
v
e
l
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
u
si
n
g
d
e
e
p
e
f
f
i
c
i
e
n
t
N
e
t
-
C
N
N
-
b
a
se
d
f
e
a
t
u
r
e
s
w
i
t
h
s
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
a
n
d
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
,
”
Ph
y
si
c
a
S
c
r
i
p
t
a
,
v
o
l
.
9
9
,
n
o
.
7
,
p
.
0
7
5
0
0
2
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
8
8
/
1
4
0
2
-
4
8
9
6
/
a
d
4
f
2
d
.
[
1
1
]
K
.
S
a
k
p
a
l
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
i
n
h
e
a
l
t
h
c
a
r
e
:
b
r
a
i
n
t
u
m
o
r
,
”
I
n
t
e
r
a
n
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
i
e
n
t
i
f
i
c
Re
se
a
r
c
h
i
n
En
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
0
9
,
n
o
.
0
1
,
p
p
.
1
–
9
,
Jan
.
2
0
2
5
,
d
o
i
:
1
0
.
5
5
0
4
1
/
i
j
sr
e
m
4
1
2
2
8
.
[
1
2
]
M
.
B
a
a
l
i
,
N
.
B
o
u
r
b
i
a
,
K
.
M
e
ssa
o
u
d
i
,
a
n
d
E.
B
.
B
o
u
r
e
n
n
a
n
e
,
“
Ef
f
i
c
i
e
n
t
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
a
n
d
seg
m
e
n
t
a
t
i
o
n
b
a
se
d
o
n
a
d
v
a
n
c
e
d
C
N
N
a
n
d
U
-
N
e
t
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
7
,
n
o
.
2
,
p
p
.
1
3
6
5
–
1
3
7
5
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
7
.
i
2
.
p
p
1
3
6
5
-
1
3
7
5
.
[
1
3
]
J.
B
a
o
,
H
.
S
u
n
,
H
.
D
e
n
g
,
Y
.
H
e
,
Z.
Z
h
a
n
g
,
a
n
d
X
.
L
i
,
“
B
M
A
D
:
b
e
n
c
h
mar
k
s
f
o
r
me
d
i
c
a
l
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
,
”
i
n
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
si
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
Wo
r
k
sh
o
p
s
,
I
EEE,
J
u
n
.
2
0
2
4
,
p
p
.
4
0
4
2
–
4
0
5
3
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
W
6
3
3
8
2
.
2
0
2
4
.
0
0
4
0
8
.
[
1
4
]
A
.
B
h
a
r
a
l
i
,
L.
D
i
h
i
n
g
i
a
,
S
.
S
h
o
m
e
,
a
n
d
A
.
G
a
n
g
u
l
y
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
s
e
d
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
s
y
s
t
e
m,
”
i
n
I
C
EPE
2
0
2
4
-
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
En
e
r
g
y
,
P
o
w
e
r
a
n
d
En
v
i
r
o
n
m
e
n
t
:
T
o
w
a
r
d
s
I
n
d
i
g
e
n
o
u
s
En
e
rg
y
U
t
i
l
i
za
t
i
o
n
,
I
EEE,
Ju
n
.
2
0
2
4
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
E
P
E6
3
2
3
6
.
2
0
2
4
.
1
0
6
6
8
9
1
6
.
[
1
5
]
A
.
A
.
A
si
r
i
,
T.
A
.
S
o
o
mr
o
,
A
.
A
.
S
h
a
h
,
G
.
P
o
g
r
e
b
n
a
,
M
.
I
r
f
a
n
,
a
n
d
S
.
A
l
q
a
h
t
a
n
i
,
“
O
p
t
i
m
i
z
e
d
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
:
a
d
u
a
l
-
mo
d
u
l
e
a
p
p
r
o
a
c
h
f
o
r
M
R
I
i
ma
g
e
e
n
h
a
n
c
e
men
t
a
n
d
t
u
m
o
r
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
4
2
8
6
8
–
4
2
8
8
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
7
9
1
3
6
.
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
I
n
cip
ien
t a
n
o
ma
lo
u
s
d
etec
tio
n
in
a
b
r
a
in
u
s
in
g
th
e
I
B
I
GP
a
l
g
o
r
ith
m
…
(
Mo
h
a
med
Hich
em
N
a
it
C
h
a
la
l)
127
[
1
6
]
V
.
A
.
R
e
d
d
y
,
“
H
o
w
i
m
p
o
r
t
a
n
t
i
s
e
a
r
l
y
d
e
t
e
c
t
i
o
n
i
n
t
r
e
a
t
i
n
g
b
r
a
i
n
t
u
m
o
r
s?,
”
D
r
V
i
j
a
y
A
n
a
n
d
R
e
d
d
y
.
c
o
m
.
A
c
c
e
sse
d
:
D
e
c
.
1
0
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
d
r
v
i
j
a
y
a
n
a
n
d
r
e
d
d
y
.
c
o
m
/
h
o
w
-
i
m
p
o
r
t
a
n
t
-
is
-
e
a
r
l
y
-
d
e
t
e
c
t
i
o
n
-
in
-
t
r
e
a
t
i
n
g
-
b
r
a
i
n
-
t
u
mo
r
s
/
[
1
7
]
N
a
t
i
o
n
a
l
B
r
a
i
n
T
u
m
o
r
S
o
c
i
e
t
y
,
“
B
r
a
i
n
t
u
m
o
r
f
a
c
t
s
.
”
A
c
c
e
ss
e
d
:
D
e
c
.
0
1
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
b
r
a
i
n
t
u
m
o
r
.
o
r
g
/
b
r
a
i
n
-
t
u
m
o
r
s/
a
b
o
u
t
-
b
r
a
i
n
-
t
u
m
o
r
s/
b
r
a
i
n
-
t
u
m
o
r
-
f
a
c
t
s
/
[
1
8
]
Q
.
T.
O
st
r
o
m
e
t
a
l
.
,
“
C
B
TR
U
S
s
t
a
t
i
s
t
i
c
a
l
r
e
p
o
r
t
:
p
r
i
mar
y
b
r
a
i
n
a
n
d
o
t
h
e
r
c
e
n
t
r
a
l
n
e
r
v
o
u
s
s
y
st
e
m
t
u
m
o
r
s
d
i
a
g
n
o
s
e
d
i
n
t
h
e
U
n
i
t
e
d
S
t
a
t
e
s
i
n
2
0
1
5
–
2
0
1
9
,
”
N
e
u
r
o
-
O
n
c
o
l
o
g
y
,
v
o
l
.
2
4
,
n
o
.
5
S
,
p
p
.
V
1
–
V
9
5
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
9
3
/
n
e
u
o
n
c
/
n
o
a
c
2
0
2
.
[
1
9
]
B
.
Y
a
g
o
u
b
i
,
“
A
g
e
o
m
e
t
r
i
c
a
p
p
r
o
a
c
h
t
o
a
n
o
n
st
a
t
i
o
n
a
r
y
p
r
o
c
e
ss,
”
In
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
n
d
i
n
t
e
rn
a
t
i
o
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
Ma
t
h
e
m
a
t
i
c
a
l
M
o
d
e
l
s
f
o
r
En
g
i
n
e
e
r
i
n
g
S
c
i
e
n
c
e
,
a
n
d
p
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
n
d
i
n
t
e
rn
a
t
i
o
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
D
e
v
e
l
o
p
m
e
n
t
,
E
n
e
r
g
y
,
En
v
i
r
o
n
m
e
n
t
,
Ec
o
n
o
m
i
c
s
,
a
n
d
p
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
n
d
i
n
t
e
rn
a
t
i
o
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
Ma
n
a
g
e
m
e
n
t
i
n
T
e
c
h
n
o
l
o
g
i
c
a
l
I
n
n
o
v
a
t
i
o
n
a
n
d
Ac
a
d
e
m
i
c
G
l
o
b
a
l
i
z
a
t
i
o
n
,
2
0
1
1
,
p
p
.
1
7
9
–
1
8
3
.
[
2
0
]
S
.
B
e
n
k
r
a
o
u
d
a
,
B
.
Y
a
g
o
u
b
i
,
M
.
R
e
b
h
i
,
a
n
d
A
.
B
o
u
z
i
a
n
e
,
“
B
e
l
o
n
g
i
n
g
p
r
o
b
a
b
i
l
i
t
y
i
n
v
e
r
s
e
i
m
a
g
e
a
p
p
r
o
a
c
h
f
o
r
f
o
r
e
st
f
i
r
e
d
e
t
e
c
t
i
o
n
,
”
Af
ri
c
a
n
J
o
u
r
n
a
l
o
f
Ec
o
l
o
g
y
,
v
o
l
.
5
2
,
n
o
.
3
,
p
p
.
3
6
3
–
3
6
9
,
N
o
v
.
2
0
1
4
,
d
o
i
:
1
0
.
1
1
1
1
/
a
j
e
.
1
2
1
2
8
.
[
2
1
]
B
.
Y
a
g
o
u
b
i
,
“
M
u
l
t
i
-
f
a
u
l
t
s
d
e
t
e
c
t
i
o
n
i
n
r
a
n
d
o
m
p
r
o
c
e
ss
e
s u
s
i
n
g
t
h
e
P
S
D
a
n
d
t
h
e
I
B
I
P
h
y
b
r
i
d
t
e
c
h
n
i
q
u
e
,
”
M
e
c
h
a
t
r
o
n
i
c
S
y
st
e
m
s
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
4
6
,
n
o
.
4
,
p
p
.
1
5
0
–
1
5
6
,
2
0
1
8
,
d
o
i
:
1
0
.
2
3
1
6
/
Jo
u
r
n
a
l
.
2
0
1
.
2
0
1
8
.
4
.
2
0
1
-
2
8
0
6
.
[
2
2
]
H
.
A
.
S
h
a
h
,
F
.
S
a
e
e
d
,
S
.
Y
u
n
,
J.
H
.
P
a
r
k
,
A
.
P
a
u
l
,
a
n
d
J.
M
.
K
a
n
g
,
“
A
r
o
b
u
s
t
a
p
p
r
o
a
c
h
f
o
r
b
r
a
i
n
t
u
mo
r
d
e
t
e
c
t
i
o
n
i
n
ma
g
n
e
t
i
c
r
e
so
n
a
n
c
e
i
ma
g
e
s
u
s
i
n
g
f
i
n
e
t
u
n
e
d
Ef
f
i
c
i
e
n
t
N
e
t
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
6
5
4
2
6
–
6
5
4
3
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
8
4
1
1
3
.
[
2
3
]
C
.
H
a
n
e
t
a
l
.
,
“
M
A
D
G
A
N
:
u
n
s
u
p
e
r
v
i
se
d
m
e
d
i
c
a
l
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
G
A
N
u
si
n
g
mu
l
t
i
p
l
e
a
d
j
a
c
e
n
t
b
r
a
i
n
M
R
I
sl
i
c
e
r
e
c
o
n
st
r
u
c
t
i
o
n
,
”
BM
C
Bi
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
2
,
n
o
.
S
2
,
p
.
3
1
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
8
5
9
-
0
2
0
-
0
3
9
3
6
-
1.
[
2
4
]
G
.
P
a
n
g
,
C
.
S
h
e
n
,
L.
C
a
o
,
a
n
d
A
.
V
a
n
D
e
n
H
e
n
g
e
l
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
:
a
r
e
v
i
e
w
,
”
A
C
M
C
o
m
p
u
t
i
n
g
S
u
r
v
e
y
s
,
v
o
l
.
5
4
,
n
o
.
2
,
p
p
.
1
–
3
8
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
3
9
9
5
0
.
[
2
5
]
N
.
Za
n
g
r
a
n
d
o
,
P
.
F
r
a
t
e
r
n
a
l
i
,
M
.
P
e
t
r
i
,
N
.
O
.
P
i
n
c
i
r
o
l
i
V
a
g
o
,
a
n
d
S
.
L
.
H
e
r
r
e
r
a
G
o
n
z
á
l
e
z
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
i
n
q
u
a
s
i
-
p
e
r
i
o
d
i
c
e
n
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
d
a
t
a
s
e
r
i
e
s
:
a
c
o
m
p
a
r
i
so
n
o
f
a
l
g
o
r
i
t
h
ms,”
E
n
e
r
g
y
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
5
,
n
o
.
S
4
,
p
.
6
2
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
2
1
6
2
-
0
2
2
-
0
0
2
3
0
-
7.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mr.
Mo
h
a
m
e
d
H
ichem
N
a
it
Cha
l
a
l
re
c
e
iv
e
d
a
d
i
p
l
o
m
a
o
f
M
a
ste
r’
s
d
e
g
re
e
in
e
lec
tro
n
ic
e
m
b
e
d
d
e
d
sy
ste
m
s
fro
m
Un
iv
e
rsity
o
f
sc
ien
c
e
a
n
d
tec
h
n
o
l
o
g
y
,
o
ra
n
,
Alg
e
ria,
in
2
0
2
0
.
Cu
rre
n
tl
y
is
a
P
h
.
D
.
stu
d
e
n
t
a
t
Ab
d
e
l
h
a
m
id
Ib
n
Ba
d
is
Un
i
v
e
rsity
o
f
M
o
sta
g
a
n
e
m
,
Alg
e
ria,
wh
e
re
h
e
jo
in
e
d
t
h
e
S
ig
n
a
ls
a
n
d
S
y
ste
m
s
Lab
o
ra
to
ry
(S
S
L).
E
ar
ly
d
etec
tio
n
o
f
a
n
o
m
alies
in
a
s
to
ch
asti
c
p
r
o
ce
s
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
h
a
m
e
d
.
n
a
i
t
c
h
a
l
a
l
.
e
t
u
@u
n
iv
-
m
o
s
t
a
.
d
z
.
Pro
f.
Be
n
a
b
d
e
ll
a
h
Ya
g
o
u
b
i
re
c
e
iv
e
d
th
e
M
.
S
c
d
e
g
re
e
in
El
e
c
t
rica
l
En
g
in
e
e
rin
g
in
1
9
8
5
fro
m
Be
l
-
A
b
b
e
s
Un
iv
e
rsi
ty
,
Al
g
e
ria
a
n
d
t
h
e
P
h
.
D
.
d
e
g
re
e
(th
in
fil
m
s)
(
1
9
8
6
-
1
9
8
9
)
in
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s
fro
m
Br
u
n
e
l
Un
iv
e
rsity
(UK
).
He
wa
s
th
e
h
e
a
d
o
f
th
e
S
ig
n
a
ls
a
n
d
S
y
ste
m
s
Lab
o
ra
to
r
y
(
1
9
9
9
-
2
0
0
3
)
a
n
d
t
h
e
h
e
a
d
o
f
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
(2
0
0
5
-
2
0
0
6
).
He
is
lec
tu
ri
n
g
th
e
t
h
e
o
ry
o
f
d
i
g
it
a
l
si
g
n
a
l,
sy
ste
m
s
m
o
d
e
li
n
g
a
n
d
i
d
e
n
ti
f
ica
ti
o
n
,
ra
n
d
o
m
p
ro
c
e
ss
e
s
a
n
d
d
e
tec
ti
o
n
(1
9
9
6
-
2
0
2
4
)
a
t
M
o
sta
g
a
n
e
m
Un
i
v
e
rsity
,
Al
g
e
ria.
Cu
rre
n
tl
y
,
h
e
is
i
n
v
o
lv
e
d
in
so
m
e
n
a
ti
o
n
a
l
p
ro
jec
ts;
fo
re
st
fire
d
e
tec
ti
o
n
,
h
e
a
rt
ra
te
v
a
riab
il
it
y
i
n
th
e
LF
a
n
d
H
F
b
a
n
d
s
t
o
c
h
a
ra
c
teriz
e
th
e
a
u
to
n
o
m
o
u
s
n
e
rv
o
u
s
sy
ste
m
,
a
n
d
stu
d
y
a
n
d
a
p
p
li
c
a
ti
o
n
o
f
ra
n
d
o
m
p
ro
c
e
ss
e
s.
F
u
r
th
e
r
re
se
a
rc
h
in
tere
sts
a
re
in
re
a
l
sig
n
a
ls
a
n
d
m
o
d
e
ls
g
e
o
m
e
tri
c
re
p
re
se
n
tatio
n
b
a
se
d
o
n
G
ra
m
-
S
c
h
m
id
t
o
rt
h
o
g
o
n
a
li
z
a
ti
o
n
c
o
n
c
e
p
t,
a
s
we
ll
a
s
u
sin
g
a
re
lati
v
e
g
e
o
m
e
tri
c
sp
a
c
e
o
f
o
b
se
rv
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
e
n
a
b
d
e
ll
a
h
.
y
a
g
o
u
b
i@u
n
iv
-
m
o
sta
.
d
z
.
Mr.
S
id
a
h
m
e
d
H
e
n
n
i
is
a
re
se
a
rc
h
p
ro
fe
ss
o
r
a
t
I
b
n
Ba
d
i
ss
e
Un
iv
e
rsity
o
f
M
o
sta
g
a
n
e
m
,
Al
g
e
ria,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
De
p
a
rtme
n
t
o
f
E
lec
tri
c
a
l
En
g
i
n
e
e
rin
g
.
S
tate
e
n
g
in
e
e
r
in
e
lec
tro
n
ics
,
i
n
d
u
str
ial
c
o
n
tr
o
l
o
p
ti
o
n
1
9
9
7
,
M
a
ste
rs
i
n
e
lec
tro
n
ics
a
t
th
e
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
o
f
Ora
n
in
2
0
0
1
He
o
b
tain
e
d
h
is
d
o
c
to
ra
te
in
sc
ien
c
e
fro
m
th
e
U
n
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
Ora
n
in
2
0
1
8
,
a
n
d
h
e
o
b
tai
n
e
d
h
is
HD
R
u
n
iv
e
rsity
a
c
c
re
d
it
a
ti
o
n
fro
m
th
e
Un
i
v
e
rsity
o
f
M
o
sta
g
a
n
e
m
in
2
0
2
0
.
Hi
s
re
se
a
rc
h
a
re
a
is
sig
n
a
l,
ima
g
e
a
n
d
sp
e
e
c
h
p
ro
c
e
ss
in
g
,
a
rti
ficia
l
i
n
t
e
ll
ig
e
n
c
e
,
h
o
m
e
a
u
t
o
m
a
ti
o
n
.
He
h
a
s
p
r
o
d
u
c
e
d
se
v
e
ra
l
in
ter
n
a
t
io
n
a
l
p
u
b
li
c
a
ti
o
n
s
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sid
h
e
n
n
i@y
a
h
o
o
.
fr
,
sid
a
h
m
e
d
h
e
n
n
i@u
n
iv
-
m
o
st
a
.
d
z
.
Evaluation Warning : The document was created with Spire.PDF for Python.