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.
3
9
,
No
.
1
,
Ju
ly
2
0
2
5
,
p
p
.
345
~
3
5
2
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
1
.
pp
345
-
3
5
2
345
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
New
technic
of
tr
a
nsfer learning
for dete
cting e
pilep
sy
by
Efficien
tNe
t
a
nd
Da
rkNet
mo
dels
F
a
t
im
a
E
dd
er
ba
li
1
,
H
a
m
id E
l
M
a
la
li
1
,
E
lm
a
a
t
i Es
s
o
uk
a
k
i
2
,
M
o
ha
m
m
ed
H
a
rmo
uchi
1
1
La
b
o
r
a
t
o
r
y
o
f
R
a
d
i
a
n
c
e
-
M
a
t
e
r
a
n
d
I
n
st
r
u
m
e
n
t
a
t
i
o
n
,
F
S
T,
H
a
ss
a
n
F
i
r
st
U
n
i
v
e
r
si
t
y
,
S
e
t
t
a
t
,
M
o
r
o
c
c
o
2
S
c
i
e
n
c
e
s
a
n
d
En
g
i
n
e
e
r
i
n
g
o
f
B
i
o
m
e
d
i
c
a
l
s,
B
i
o
p
h
y
s
i
c
s
a
n
d
H
e
a
l
t
h
L
a
b
o
r
a
t
o
r
y
,
H
i
g
h
e
r
I
n
st
i
t
u
t
e
o
f
H
e
a
l
t
h
S
c
i
e
n
c
e
s,
H
a
ssan
F
i
r
st
U
n
i
v
e
r
si
t
y
,
S
e
t
t
a
t
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
8
,
2
0
2
4
R
ev
is
ed
Mar
11
,
2
0
2
5
Acc
ep
ted
Mar
25
,
2
0
2
5
Ep
il
e
p
t
ic
se
izu
re
s
a
re
o
n
e
o
f
th
e
m
o
st
p
re
v
a
len
t
b
ra
i
n
d
is
o
rd
e
rs
in
th
e
wo
rld
.
El
e
c
tro
e
n
c
e
p
h
a
lo
g
ra
p
h
y
(EE
G
)
sig
n
a
l
a
n
a
ly
sis
is
u
se
d
to
d
isti
n
g
u
is
h
b
e
twe
e
n
n
o
rm
a
l
a
n
d
e
p
il
e
p
ti
c
b
r
a
in
a
c
ti
v
it
y
.
To
d
a
te,
a
u
to
m
a
ti
c
d
iag
n
o
sis
re
m
a
in
s
a
h
ig
h
l
y
re
lev
a
n
t
a
n
d
si
g
n
i
fica
n
t
re
se
a
rc
h
to
p
ic
w
h
ich
c
a
n
h
e
l
p
i
n
th
is
tas
k
,
e
sp
e
c
ially
c
o
n
sid
e
ri
n
g
th
a
t
su
c
h
d
iag
n
o
sis
re
q
u
ires
a
sig
n
ifi
c
a
n
t
a
m
o
u
n
t
o
f
ti
m
e
to
b
e
c
a
rried
o
u
t
b
y
a
n
e
x
p
e
rt.
As
a
re
su
lt
,
th
e
n
e
e
d
fo
r
a
n
e
ffe
c
ti
v
e
se
izu
re
a
p
p
ro
a
c
h
c
a
p
a
b
l
e
to
c
las
sify
th
e
n
o
rm
a
l
a
n
d
e
p
il
e
p
ti
c
b
ra
i
n
sig
n
a
l
a
u
t
o
m
a
ti
c
a
ll
y
is
c
ru
c
ial.
In
th
is
p
e
rsp
e
c
ti
v
e
,
t
h
is
wo
rk
p
ro
p
o
s
e
s
a
d
e
e
p
n
e
u
ra
l
n
e
two
r
k
a
p
p
r
o
a
c
h
u
sin
g
tran
sfe
r
lea
rn
in
g
to
c
las
sify
s
p
e
c
tro
g
ra
m
ima
g
e
s
th
a
t
h
a
v
e
b
e
e
n
e
x
trac
ted
fro
m
EE
G
sig
n
a
ls.
In
it
iall
y
,
sp
e
c
tro
g
ra
m
ima
g
e
s
h
a
v
e
b
e
e
n
e
x
trac
ted
a
n
d
u
se
d
a
s
in
p
u
t
t
o
p
re
-
trai
n
e
d
m
o
d
e
ls,
a
n
d
a
se
c
o
n
d
re
fin
e
m
e
n
t
is
p
e
rfo
rm
e
d
o
n
c
e
rtain
fe
a
tu
re
e
x
trac
ti
o
n
lay
e
rs
th
a
t
we
re
p
re
v
io
u
sly
fro
z
e
n
.
Th
e
Eff
icie
n
tNe
t
a
n
d
Da
rk
Ne
t
n
e
tw
o
rk
s
a
re
u
se
d
.
To
o
v
e
rc
o
m
e
t
h
e
lac
k
o
f
d
a
ta,
d
a
ta
a
u
g
m
e
n
tatio
n
wa
s
a
ls
o
c
a
rried
o
u
t.
T
h
e
p
ro
p
o
se
d
wo
r
k
p
e
rfo
rm
e
d
e
x
c
e
ll
e
n
tl
y
,
a
s
a
ss
e
ss
e
d
b
y
m
u
lt
ip
le
m
e
tri
c
s,
su
c
h
a
s
th
e
0
.
9
9
a
c
c
u
ra
c
y
a
c
h
iev
e
d
with
Eff
icie
n
tNe
t
c
o
m
b
i
n
e
d
wit
h
a
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM
)
c
las
sifier.
K
ey
w
o
r
d
s
:
Dar
k
Net
EEG
E
f
f
icien
tNet
E
p
ilep
s
y
T
r
an
s
f
er
lear
n
i
n
g
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
:
Fatim
a
E
d
d
er
b
ali
L
ab
o
r
ato
r
y
o
f
R
ad
ian
ce
-
Ma
ter
an
d
I
n
s
tr
u
m
en
tatio
n
,
FS
T
,
Hass
an
First Un
iv
er
s
ity
Settat,
Mo
r
o
cc
o
E
m
ail: f
.
ed
d
er
b
ali@
u
h
p
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
E
p
ilep
s
y
is
a
m
ajo
r
m
e
d
ic
al
p
r
o
b
lem
lin
k
ed
t
o
d
is
o
r
d
er
s
o
f
co
r
tical
ex
citatio
n
.
Acc
u
r
ately
d
iag
n
o
s
in
g
ep
ilep
s
y
in
a
p
ati
en
t
en
ab
les
s
elec
tio
n
o
f
th
e
ap
p
r
o
p
r
iate
d
r
u
g
th
er
ap
y
an
d
ac
cu
r
ate
d
iag
n
o
s
tic
ev
alu
atio
n
in
th
e
v
ast
m
ajo
r
it
y
o
f
s
itu
atio
n
s
.
Hu
m
an
ep
ilep
s
y
is
an
in
tr
in
s
ic
b
r
ain
d
is
ea
s
e
in
th
e
m
ajo
r
ity
o
f
ca
s
es
[
1
]
.
I
t
ca
n
b
e
co
n
s
id
er
e
d
th
e
s
ec
o
n
d
m
o
s
t
co
m
m
o
n
b
r
ain
d
is
ea
s
e
wo
r
ld
wid
e
af
ter
s
tr
o
k
e,
with
ar
o
u
n
d
7
0
0
,
0
0
0
p
e
o
p
le
s
u
f
f
er
i
n
g
f
r
o
m
ep
ilep
s
y
in
Mo
r
o
cc
o
[
2
]
.
Ov
e
r
f
o
r
ty
m
illi
o
n
p
e
o
p
le
wo
r
ld
wi
d
e
(
1
% o
f
th
e
to
tal
h
u
m
an
p
o
p
u
latio
n
)
cu
r
r
en
tly
s
u
f
f
er
f
r
o
m
e
p
ilep
s
y
[
2
]
.
U
n
tr
ea
ted
ep
ilep
s
y
r
ep
r
esen
ts
a
m
ajo
r
is
s
u
e
f
o
r
th
e
m
o
d
er
n
p
o
p
u
latio
n
,
d
u
e
to
th
e
ass
o
ciate
d
h
ea
lth
ca
r
e
co
s
ts
.
E
ar
ly
d
etec
tio
n
a
n
d
tr
ea
tm
en
t
o
f
ep
ilep
s
y
is
f
u
r
th
er
co
m
p
licated
b
y
th
e
d
is
r
u
p
tiv
e
n
atu
r
e
o
f
ep
ilep
s
y
,
in
wh
ich
s
eizu
r
es
ar
e
s
p
o
n
tan
e
o
u
s
a
n
d
u
n
p
r
ed
ictab
le
d
u
e
to
th
e
ch
ao
tic
n
atu
r
e
o
f
th
e
d
is
o
r
d
er
[
3
]
.
Simu
ltan
eo
u
s
h
y
p
e
r
ac
tiv
ity
o
f
g
r
o
u
p
s
o
f
lar
g
e
n
eu
r
o
n
s
is
th
e
tr
ig
g
er
f
o
r
s
eizu
r
es,
wh
ich
ca
n
r
esu
lt
in
a
b
an
d
o
f
tr
an
s
ien
t
ch
an
g
es
in
co
g
n
itio
n
an
d
b
eh
av
io
r
[
4
]
.
T
o
u
n
d
e
r
s
tan
d
th
e
tr
ig
g
er
in
g
s
y
s
tem
o
f
ep
ilep
s
y
an
d
th
e
ev
o
lu
tio
n
o
f
s
eizu
r
e
s
,
we
n
ee
d
to
k
n
o
w
h
o
w
s
ei
zu
r
es
d
ev
elo
p
an
d
ev
o
lv
e
[
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
345
-
3
5
2
346
E
lectr
o
en
ce
p
h
al
o
g
r
a
p
h
y
(
E
E
G)
is
an
ess
en
tial
cl
in
ical
d
iag
n
o
s
tic
to
o
l
f
o
r
th
e
a
s
s
es
s
m
en
t,
m
o
n
ito
r
in
g
,
an
d
m
an
ag
e
m
en
t
o
f
n
eu
r
o
lo
g
ical
d
is
o
r
d
er
s
r
e
lated
to
ep
ilep
s
y
[
5
]
.
I
n
t
h
e
E
E
G,
ep
ilep
tifo
r
m
s
eizu
r
es
ap
p
ea
r
as
a
d
is
tin
cti
v
e
f
ea
tu
r
e,
u
s
u
ally
r
e
f
er
r
ed
t
o
as
r
h
y
th
m
ic
s
ig
n
als,
an
d
o
f
te
n
co
in
cid
e
with
o
r
ev
en
p
r
ec
ed
e
th
e
f
ir
s
t
r
ec
o
g
n
izab
le
co
n
d
u
ct
c
h
an
g
es
.
T
h
e
m
ain
E
E
G
m
an
if
estatio
n
is
a
n
ep
ilep
tic
s
eizu
r
e
,
wh
ich
ca
n
in
v
o
lv
e
a
d
is
cr
ete
p
ar
t
o
f
th
e
b
r
ai
n
p
ar
tially
o
r
a
wh
o
le
g
e
n
er
alize
d
b
r
ain
m
ass
[
6
]
.
T
h
er
e
ar
e
s
o
m
e
cr
u
cial
p
ar
am
eter
s
a
r
e
o
b
tain
ed
f
r
o
m
th
ese
E
E
G
s
ig
n
als,
wh
ich
ar
e
h
ig
h
ly
u
s
ef
u
l
in
d
etec
tin
g
an
e
p
ilep
tic
s
eizu
r
e.
Desp
ite
th
e
o
v
er
4
0
y
ea
r
s
o
f
in
v
esti
g
atio
n
in
th
e
p
a
th
o
p
h
y
s
io
lo
g
y
o
f
it,
it
r
em
ain
s
elu
s
iv
e
to
ex
p
lain
h
o
w
clin
ical
tr
a
n
s
ien
t
ep
ile
p
ti
c
s
p
o
n
tan
e
o
u
s
s
eizu
r
es
o
cc
u
r
f
r
o
m
t
h
e
co
m
p
ar
ativ
ely
n
o
r
m
ally
b
r
ain
co
n
d
itio
n
th
at
is
n
o
ted
am
o
n
g
s
eizu
r
es
[
7
]
,
[
8
]
.
Du
e
to
th
e
g
r
o
win
g
e
p
ilep
s
y
p
atien
t
p
o
p
u
latio
n
an
d
th
e
lar
g
e
wo
r
k
lo
a
d
o
f
d
etec
tin
g
s
eizu
r
es
b
y
h
u
m
a
n
ex
p
er
ts
,
m
a
n
y
attem
p
ts
at
au
to
m
ated
s
eizu
r
e
d
etec
tio
n
an
d
an
aly
s
is
h
av
e
b
ee
n
u
n
d
er
tak
e
n
[
4
].
Dete
ctin
g
ep
ilep
s
y
,
esp
ec
iall
y
th
r
o
u
g
h
ad
v
a
n
ce
m
en
ts
in
m
ac
h
in
e
lear
n
in
g
a
n
d
d
ee
p
l
ea
r
n
in
g
,
h
as
b
ec
o
m
e
a
s
ig
n
if
ican
t
ar
ea
o
f
r
esear
ch
.
R
ec
en
t
s
tu
d
ies
h
av
e
u
tili
ze
d
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
e
two
r
k
(
C
NNs
)
an
d
r
ec
cu
r
en
t n
eu
r
al
n
etwo
r
k
(
R
NNs
)
to
g
et
a
b
etter
ac
cu
r
ac
y
o
f
ep
ilep
tic
s
eizu
r
e
d
etec
tio
n
f
r
o
m
E
E
G
s
ig
n
als
[
9
]
.
T
h
is
s
tu
d
y
p
r
esen
ts
a
h
y
b
r
id
d
ee
p
lear
n
in
g
m
o
d
el
co
m
b
in
in
g
C
NNs
an
d
R
NN
s
to
d
etec
t
ep
ilep
s
y
au
to
m
atica
lly
f
r
o
m
b
r
ain
s
ig
n
al
r
ec
o
r
d
ed
b
y
th
e
E
E
G
.
T
h
e
a
p
p
r
o
ac
h
e
n
h
an
ce
s
d
etec
tio
n
ac
cu
r
ac
y
an
d
r
ed
u
ce
s
f
alse
p
o
s
itiv
es
co
m
p
ar
ed
t
o
tr
ad
itio
n
al
m
eth
o
d
s
.
Hen
ce
,
it
ca
n
b
e
co
m
p
u
tatio
n
ally
in
ten
s
iv
e
an
d
tim
e
-
co
n
s
u
m
in
g
t
o
tr
ain
,
r
eq
u
ir
i
n
g
s
u
b
s
tan
tial
h
ar
d
war
e
r
eso
u
r
ce
s
an
d
o
p
tim
izatio
n
.
An
d
t
h
e
in
cr
ea
s
ed
co
m
p
lex
ity
o
f
h
y
b
r
i
d
m
o
d
els
m
ay
lead
to
o
v
er
f
itti
n
g
,
esp
ec
ially
if
th
e
tr
ain
in
g
d
ataset
is
n
o
t
s
u
f
f
icien
t
ly
lar
g
e
o
r
d
iv
e
r
s
e.
W
h
ile
atten
tio
n
m
ec
h
an
is
m
s
ca
n
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
th
ey
ca
n
s
o
m
etim
es
lead
to
d
if
f
ic
u
lties
in
in
ter
p
r
etin
g
h
o
w
atten
tio
n
weig
h
ts
ar
e
ass
ig
n
ed
,
co
m
p
licatin
g
th
e
u
n
d
er
s
tan
d
in
g
o
f
m
o
d
el
d
ec
is
io
n
s
.
T
h
e
atten
tio
n
m
ec
h
a
n
is
m
m
ay
in
cr
ea
s
e
th
e
co
m
p
u
tatio
n
al
co
s
t,
m
ak
in
g
r
ea
l
-
tim
e
im
p
lem
e
n
tatio
n
ch
allen
g
in
g
.
B
esid
e
th
at
th
e
d
ee
p
lea
r
n
in
g
m
o
d
els
f
o
r
ep
ilep
tic
s
eizu
r
e
d
etec
tio
n
.
T
h
is
a
p
p
r
o
ac
h
h
as
p
r
o
d
u
ce
d
e
x
ce
llen
t
r
esu
lts
,
b
u
t sti
ll f
ac
es a
n
u
m
b
e
r
o
f
p
r
o
b
lem
s
in
te
r
m
s
o
f
a
p
p
li
ca
tio
n
.
T
h
ese
in
clu
d
e
th
e
n
ee
d
f
o
r
a
la
r
g
e
am
o
u
n
t o
f
d
ata.
T
o
o
v
er
co
m
e
th
o
s
e
lim
itatio
n
s
,
we
p
r
o
p
o
s
ed
to
b
ase
o
u
r
s
tu
d
y
o
n
tr
an
s
f
er
-
lea
r
n
in
g
,
wh
ich
is
in
cr
ea
s
in
g
ly
u
s
ed
to
lev
e
r
ag
e
p
r
e
-
tr
ain
e
d
m
o
d
els
f
o
r
E
E
G
-
b
ased
s
eizu
r
e
d
etec
tio
n
,
a
im
in
g
to
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
with
lim
ited
tr
ai
n
in
g
d
ata.
Ou
r
m
eth
o
d
in
v
o
lv
es
co
m
b
in
in
g
d
ata
au
g
m
e
n
tatio
n
,
in
cl
u
d
in
g
b
o
th
tr
an
s
f
er
-
lear
n
in
g
an
d
th
e
clas
s
if
ier
,
as
p
ar
t
o
f
th
e
s
am
e
d
e
s
i
g
n
.
W
e
p
r
o
p
o
s
ed
th
e
u
s
e
o
f
d
if
f
er
en
t
m
o
d
els:
E
f
f
icien
tNet
an
d
Dar
k
n
et,
c
o
m
b
in
ed
to
v
ar
io
u
s
class
if
ier
,
an
d
e
x
tr
ac
tin
g
th
e
s
p
ec
tr
o
g
r
a
m
im
ag
es
wh
ic
h
will
b
e
an
im
ag
e
d
ataset
f
o
r
th
e
m
o
d
els
,
th
e
ap
p
r
o
ac
h
r
esu
l
tin
g
in
m
o
r
e
s
u
cc
ess
f
u
l
o
u
t
co
m
es.
T
h
e
m
ain
ac
co
m
p
l
is
h
m
en
ts
in
t
h
is
r
esear
ch
ca
n
b
e
s
u
m
m
ar
ized
as
f
o
l
lo
ws:
i)
a
n
ew
d
ee
p
tr
a
n
s
f
er
-
l
ea
r
n
in
g
m
o
d
el
was
p
r
o
p
o
s
ed
with
E
f
f
icien
tNet
to
d
etec
t
s
eizu
r
e
b
r
ain
s
ig
n
al;
ii
)
em
p
lo
y
in
g
s
p
ec
tr
o
g
r
am
im
a
g
es
r
ep
lace
d
E
E
G
E
u
r
o
p
ea
n
d
ata
f
o
r
m
at
(
E
DF)
;
iii)
ass
o
ciatin
g
m
o
d
el
an
d
th
e
p
r
ev
io
u
s
ly
m
en
tio
n
ed
class
if
ier
s
,
an
d
iv
)
ac
h
iev
in
g
s
ig
n
if
ica
n
t
r
esu
lt
.
Sectio
n
2
g
iv
es
f
u
r
th
e
r
in
f
o
r
m
atio
n
o
n
d
atasets
,
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
es,
ex
tr
ac
tin
g
s
p
ec
tr
o
g
r
am
s
,
th
e
p
r
o
p
o
s
ed
C
NN
ar
ch
itectu
r
e
a
n
d
th
e
class
if
ier
s
.
C
h
ap
ter
3
p
r
esen
ts
th
e
r
esu
lts
o
f
tr
an
s
f
er
-
lear
n
in
g
as
esti
m
ated
b
y
m
u
ltip
le
m
etr
ics.
A
co
m
p
a
r
is
o
n
o
f
t
h
e
p
r
o
p
o
s
ed
d
esig
n
with
th
e
liter
atu
r
e
is
g
iv
en
in
t
h
is
ch
ap
ter
.
L
astl
y
,
c
h
ap
ter
4
o
u
tlin
es th
e
p
a
p
er
’
s
c
o
n
clu
s
io
n
s
an
d
p
r
o
s
p
ec
tiv
e
wo
r
k
.
2.
M
E
T
H
O
D
T
h
is
ch
ap
ter
d
is
cu
s
s
es
in
d
etail
th
e
d
atasets
ex
tr
ac
ted
f
r
o
m
E
E
G
E
DF
f
iles
,
au
g
m
en
tatio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
tr
an
s
f
er
-
lear
n
i
n
g
a
n
d
class
if
ier
s
.
I
n
ad
d
itio
n
,
th
e
s
u
g
g
ested
ap
p
r
o
ac
h
is
o
u
tlin
ed
in
d
etail.
im
p
lem
en
t
in
g
p
r
etr
ain
ed
m
o
d
els,
Dar
k
n
et
an
d
E
f
f
icien
tNet,
in
o
r
d
er
to
d
ete
r
m
in
e
th
e
m
o
s
t
ap
p
r
o
p
r
iate
m
o
d
el
f
o
r
th
is
s
tu
d
y
’
s
s
p
ec
if
ic
p
r
o
b
lem
.
T
h
ese
m
o
d
els
wer
e
ea
c
h
tr
ain
ed
o
n
7
0
%
o
f
th
e
d
ataset.
Acc
o
r
d
in
g
ly
,
E
f
f
icien
tNet
p
r
o
v
ed
to
b
e
th
e
b
est o
p
tio
n
,
a
n
d
we
th
e
r
ef
o
r
e
s
elec
ted
it a
s
o
u
r
p
r
e
f
er
r
e
d
m
o
d
el.
2
.
1
.
D
a
t
a
s
et
s
E
E
G
s
ig
n
al
an
aly
s
is
is
u
s
ed
t
o
ad
d
r
ess
a
v
ar
iety
o
f
is
s
u
es
s
tar
tin
g
b
y
p
r
e
p
r
o
ce
s
s
in
g
,
s
u
c
h
as
d
ata
m
in
in
g
,
id
e
n
tifin
g
,
r
ed
u
ci
n
g
n
o
is
e;
s
ig
n
al
s
p
litt
in
g
an
d
ex
tr
ac
t
f
ea
tu
r
es.
T
h
e
s
tu
d
y
o
f
th
ese
s
ig
n
als
is
im
p
o
r
tan
t
f
o
r
n
o
t
o
n
l
y
m
ed
ic
al
r
esear
ch
,
b
u
t
also
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t.
Fig
u
r
e
1
:
il
lu
s
tr
atio
n
o
f
E
E
G
s
ig
n
als
E
E
G
d
ata
,
wh
er
e
th
e
F
ig
u
r
e
1
(
a)
r
e
p
r
esen
ts
th
e
n
o
r
m
al
E
E
G
s
ig
n
al
an
d
th
e
F
ig
u
r
e
1
(
b
)
r
ep
r
esen
ts
th
e
ep
ilep
tic
o
n
e
,
E
E
G
is
a
ty
p
ical
s
ig
n
al
p
r
o
v
id
in
g
in
f
o
r
m
atio
n
o
n
elec
tr
ic
ac
tiv
ity
r
ec
o
r
d
e
d
f
r
o
m
n
er
v
e
ce
lls
in
th
e
ce
r
eb
r
al
co
r
tex
,
h
as
b
ee
n
t
h
e
m
o
s
t
co
m
m
o
n
l
y
u
s
ed
s
ig
n
a
l
f
o
r
clin
ical
ass
ess
m
en
t
o
f
b
r
ain
ac
tiv
ity
an
d
f
o
r
id
en
tify
in
g
s
eizu
r
e
d
is
ch
ar
g
es.
T
h
e
elec
tr
ical
ac
tiv
it
y
m
o
d
el
is
m
ain
ly
b
en
ef
icial
to
clas
s
i
f
y
ep
ilep
tic
s
ig
n
als
an
d
to
s
tu
d
y
o
f
o
th
er
c
o
n
d
itio
n
s
lik
ely
to
im
p
air
ce
r
eb
r
al
f
u
n
ctio
n
ality
,
an
d
th
e
an
aly
ze
b
ased
o
n
ea
ch
b
an
d
ca
n
b
e
m
o
r
e
a
p
p
r
o
p
r
iate
.
T
o
b
e
a
b
l
e
t
o
r
e
d
u
c
e
n
o
i
s
y
c
h
a
r
a
c
t
er
i
s
t
ic
o
f
t
h
i
s
s
i
g
n
a
l
,
i
n
t
h
e
F
i
g
u
r
e
1
w
e
p
r
e
s
e
n
t
t
h
e
E
E
G
s
i
g
n
a
l
a
f
t
e
r
b
e
e
n
e
x
t
r
a
c
t
ed
f
r
o
m
t
h
e
E
D
F
f
i
l
e
w
h
i
c
h
r
e
p
r
e
s
e
n
t
t
h
e
d
a
t
as
e
t
t
h
a
t
h
a
s
b
e
en
p
u
b
l
i
c
l
y
a
v
a
i
l
a
b
l
e
f
r
o
m
t
h
e
A
m
e
r
i
c
a
n
u
n
i
v
e
r
s
i
t
y
o
f
B
e
i
r
u
t
i
n
t
h
e
u
n
i
t
o
f
m
o
n
i
t
o
r
i
n
g
o
f
e
p
i
l
e
p
s
y
,
t
h
e
d
at
as
e
t
i
n
cl
u
d
e
s
6
E
E
G
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:
2502
-
4
7
5
2
N
ew tec
h
n
ic
o
f tra
n
s
fer lea
r
n
i
n
g
fo
r
d
etec
tin
g
e
p
ilep
s
y
b
y
E
f
ficien
tN
et
…
(
F
a
tima
E
d
d
erb
a
li
)
347
e
p
i
l
e
p
s
t
i
c
s
i
g
n
a
ls
a
n
d
2
0
n
o
r
m
a
l
s
i
g
n
a
l
s
w
i
t
h
2
0
g
i
g
a
b
y
t
e
s
ize
,
t
o
o
v
e
r
c
o
m
e
t
h
e
u
n
b
a
l
a
n
c
e
d
d
a
t
a
,
w
e
u
s
e
d
t
h
e
s
a
m
e
a
m
o
u
n
t
f
o
r
e
a
c
h
c
a
t
e
g
o
r
y
,
t
h
e
b
r
a
i
n
s
i
g
n
a
ls
h
a
v
e
b
e
e
n
r
e
c
o
r
d
e
d
b
a
s
e
d
o
n
1
0
-
2
0
e
l
e
c
t
r
o
d
e
s
y
s
t
e
m
[1
0
]
.
At
f
ir
s
t,
we
d
en
o
is
ed
th
e
s
ig
n
als,
ex
tr
ac
tin
g
ea
ch
ch
a
n
n
el
a
n
d
tr
an
s
f
o
r
m
it
t
o
s
p
ec
tr
o
g
r
a
m
im
ag
es
wh
ich
will
b
e
th
e
in
p
u
t f
o
r
o
u
r
m
o
d
el
th
at
will b
e
ass
o
ciate
d
to
class
if
ier
s
as illu
s
tr
ated
in
Fig
u
r
e
2
[1
1
].
(
a)
(
b
)
Fig
u
r
e
1
.
I
ll
u
s
tr
atio
n
o
f
E
E
G
s
ig
n
als E
E
G
d
ata
(
a)
r
ep
r
esen
ta
tio
n
o
f
n
o
r
m
al
E
E
G
s
ig
n
als
an
d
(
b
)
ep
ilep
tic
b
r
ain
s
ig
n
al
Fig
u
r
e
2
.
R
ep
r
esen
tatio
n
o
f
s
t
ep
s
in
clu
d
ed
in
th
e
class
if
icatio
n
ap
p
r
o
ac
h
2
.
2
.
T
he
f
ilte
ring
a
nd
da
t
a
a
da
pta
t
io
n
Kn
o
win
g
th
e
f
ac
t
th
at
to
s
elec
t
th
e
r
ig
h
t
m
o
th
e
r
wav
elet
tr
a
n
s
f
o
r
m
(
W
T
)
ca
n
b
e
v
er
y
cr
u
cial
th
at
d
u
e
to
ea
ch
o
n
e
ca
n
g
iv
e
a
v
er
y
b
ig
ch
an
g
e
in
th
e
o
u
tco
m
es
o
f
th
is
s
tu
d
y
.
T
h
at
is
r
elate
d
to
E
E
G
s
ig
n
als
o
f
ep
ilep
tic
s
eizu
r
e,
f
o
r
th
e
W
T
h
as
ad
v
an
tag
es
o
f
g
iv
in
g
d
ee
p
er
r
ep
r
esen
tatio
n
ca
n
b
e
v
er
y
u
s
ef
u
l
h
en
ce
th
at
d
em
an
d
s
an
im
p
o
r
tan
t
c
o
m
p
u
tatio
n
al
tim
e.
I
n
th
e
F
ig
u
r
e
3
r
ep
r
esen
ts
w
av
elet
d
ec
o
m
p
o
s
itio
n
o
f
th
e
s
u
m
m
o
th
er
wav
elet
o
f
Fp
2
ch
a
n
n
el
an
d
t
h
e
f
r
e
q
u
en
c
y
in
ter
v
al,
an
d
th
ei
r
en
er
g
y
c
o
n
tr
ib
u
tio
n
to
th
e
p
o
we
r
s
p
ec
tr
u
m
af
ter
7
m
o
th
er
wav
el
ets
h
av
e
b
ee
n
u
s
ed
wh
er
e
th
e
r
esem
b
lan
ce
b
y
Su
m
f
r
o
m
lev
e
ls
4
to
6
was
clo
s
e
to
th
e
o
r
ig
i
n
al
s
ig
n
al
[
1
2
].
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
345
-
3
5
2
348
Fig
u
r
e
3.
W
av
elet
d
ec
o
m
p
o
s
it
io
n
o
f
t
h
e
s
u
m
m
o
th
er
wav
elet
o
f
Fp
2
c
h
an
n
el
a
n
d
th
e
f
r
eq
u
e
n
cy
in
ter
v
al,
an
d
th
eir
en
er
g
y
co
n
tr
ib
u
tio
n
to
th
e
p
o
wer
s
p
ec
tr
u
m
2
.
3
.
T
ra
ns
f
er
lea
rning
m
o
de
ls
T
h
is
s
tu
d
y
u
s
ed
s
o
m
e
m
o
d
els
wh
ich
co
n
s
id
er
ed
th
e
m
o
s
t
f
r
eq
u
en
t
m
o
d
els
in
d
ee
p
lear
n
in
g
ap
p
licatio
n
s
[
1
3
]
.
Fo
r
t
h
at
r
ea
s
o
n
,
th
is
s
tu
d
y
u
s
ed
m
o
r
e
t
h
an
o
n
e
m
o
d
el
in
tr
a
n
s
f
er
lear
n
in
g
,
th
e
f
ir
s
t
m
o
d
el
is
Dar
k
Net,
wh
ich
s
tr
u
ctu
r
ed
as
a
C
NN
m
o
d
el
ar
ch
itectu
r
e,
th
is
m
o
d
el
h
as
b
ee
n
p
r
im
ar
ily
m
ad
e
to
b
e
u
s
ed
in
r
ea
l
-
tim
e
ap
p
licatio
n
s
in
o
r
d
e
r
to
d
etec
t
o
b
jects,
th
is
m
o
d
el
h
as
in
tr
o
d
u
ce
d
th
e
m
et
h
o
d
o
f
th
e
y
o
u
o
n
ly
lo
o
k
o
n
ce
(
YOL
O
)
in
to
t
h
e
m
ain
tar
g
et
s
y
s
tem
.
T
h
is
m
o
d
el
is
b
as
ically
s
tr
u
ctu
r
ed
o
f
co
n
v
o
lu
tio
n
al
lay
er
s
,
p
o
o
lin
g
lay
er
s
,
f
u
lly
co
n
n
ec
ted
lay
er
s
[
1
4
].
W
h
er
e
ea
ch
in
p
u
t
d
u
r
in
g
th
e
class
if
icatio
n
p
r
o
ce
s
s
h
as
th
e
ac
tiv
atio
n
v
alu
es
o
f
co
m
p
u
tatio
n
al
p
r
o
b
ab
ilit
y
is
g
en
er
ated
b
y
t
h
e
f
u
lly
co
n
n
ec
ted
lay
er
[
1
5
]
.
Sec
o
n
d
ly
th
e
So
f
tMa
x
p
r
o
ce
s
s
ed
th
e
ac
tiv
atio
n
v
alu
e
h
as
b
ee
n
g
iv
en
b
y
th
e
p
r
e
v
io
u
s
lay
er
,
wh
er
e
ev
er
y
in
p
u
t
c
an
b
e
attac
h
ed
to
a
p
r
o
b
a
b
ilit
y
v
alu
e
to
r
elate
it
t
o
n
u
m
b
er
o
f
class
es
,
th
at
m
ea
n
s
to
b
e
ab
le
to
ass
o
ciate
th
e
in
p
u
t
im
a
g
e
to
th
e
class
wh
ich
r
ea
ch
ed
th
e
h
ig
h
e
s
t
v
alu
e
am
o
n
g
th
ese
p
r
o
b
a
b
ilit
y
v
alu
es
b
y
th
e
So
f
tMa
x
lay
er
[
1
6
]
.
Mo
r
eo
v
e
r
,
in
o
r
d
er
t
o
p
r
ev
en
t
th
e
p
r
o
b
lem
o
f
o
v
e
r
f
itti
n
g
an
d
h
av
e
a
q
u
ick
er
c
o
n
v
e
r
g
en
ce
th
e
b
atch
n
o
r
m
aliza
tio
n
h
as
to
be
u
s
ed
in
Dar
k
Net
m
o
d
els [
1
7
]
.
with
th
is
m
o
d
el
th
at
u
s
e
im
ag
e
in
p
u
t
with
s
ize
is
2
2
4
2
2
4
r
eso
lu
tio
n
s
.
T
h
e
E
f
f
icien
tNet
B
0
p
r
o
p
o
s
ed
[
18
]
,
as
s
h
o
wn
in
Fig
u
r
e
4
,
is
a
v
ar
ian
t
o
f
th
e
E
f
f
icien
tNet
ar
ch
itectu
r
e.
Aim
in
g
to
d
eliv
er
to
p
p
er
f
o
r
m
an
ce
with
co
n
s
id
er
ab
ly
less
p
ar
am
eter
s
an
d
FLo
atin
g
-
p
o
i
n
t
o
p
er
atio
n
s
p
er
s
ec
o
n
d
FLOPs,
th
e
E
f
f
icien
tNet
f
am
ily
o
f
m
o
d
els
was
cr
ea
te
d
,
d
i
f
f
er
en
tiatin
g
it
f
r
o
m
ex
is
tin
g
ar
ch
itectu
r
es
s
u
ch
as
R
esNet
o
r
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
VGG,
E
f
f
icien
tNet
B
0
,
was
d
esig
n
ed
t
o
o
f
f
er
a
well
b
alan
c
ed
co
m
p
r
o
m
is
e
o
f
m
o
d
el
s
ize
an
d
p
er
f
o
r
m
an
ce
.
An
ac
tu
al
a
r
ch
itectu
r
e
d
iag
r
am
in
cl
u
d
es
s
ev
er
al
lay
er
s
,
n
o
tab
ly
th
e
in
p
u
t
lay
er
,
wh
ich
h
as
to
b
e
a
n
i
m
ag
e
o
f
a
s
ize:
2
2
4
×
2
2
4
p
ix
el
s
(
R
GB
ch
an
n
els),
a
ty
p
ical
s
ize
f
o
r
m
an
y
co
m
p
u
ter
v
is
io
n
a
p
p
licatio
n
s
.
T
o
f
in
d
th
e
b
est
b
alan
ce
b
etwe
en
m
o
d
el
s
ize
an
d
p
er
f
o
r
m
an
ce
,
th
e
E
f
f
icien
tNet
d
esig
n
ad
d
s
a
b
r
ea
k
th
r
o
u
g
h
tech
n
o
lo
g
y
ca
lled
“c
o
m
p
o
u
n
d
s
ca
lin
g
”,
wh
ich
ev
en
ly
b
alan
ce
s
th
e
d
ep
th
,
wi
d
th
an
d
r
eso
lu
tio
n
o
f
th
e
n
etw
o
r
k
.
Netwo
r
k
d
e
p
th
is
d
ef
in
ed
b
y
th
e
n
u
m
b
er
o
f
lay
er
s
,
wh
ile
wid
th
is
s
et
b
y
th
e
n
u
m
b
e
r
o
f
ch
an
n
els in
ea
ch
l
ay
er
.
Fig
u
r
e
4.
Ar
c
h
itectu
r
e
of
E
f
f
ic
ien
tNetb
0
n
etwo
r
k
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:
2502
-
4
7
5
2
N
ew tec
h
n
ic
o
f tra
n
s
fer lea
r
n
i
n
g
fo
r
d
etec
tin
g
e
p
ilep
s
y
b
y
E
f
ficien
tN
et
…
(
F
a
tima
E
d
d
erb
a
li
)
349
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
E
v
a
lua
t
i
o
n o
f
re
s
ults
I
n
t
h
i
s
s
ec
t
i
o
n
,
w
e
in
t
r
o
d
u
c
e
th
e
r
e
s
u
l
t
s
o
f
th
e
2
c
l
a
s
s
e
s
m
o
d
e
l
th
a
t
c
an
id
e
n
t
if
y
t
h
e
n
o
r
m
a
l
an
d
t
h
e
e
p
i
l
e
p
t
ic
s
p
e
c
t
r
o
g
r
a
m
i
m
ag
e
,
i
n
o
r
d
e
r
t
o
j
u
d
g
e
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
th
e
s
u
g
g
e
s
t
e
d
m
e
th
o
d
,
m
u
l
t
ip
l
e
m
e
t
r
ic
s
h
a
v
e
b
e
en
u
s
e
d
[
19
]
,
[
2
0
]
.
I
n
T
a
b
l
e
s
1
an
d
2
w
e
p
r
e
s
e
n
t
th
e
t
w
o
m
o
d
e
l
a
n
d
t
h
e
r
e
s
u
l
t
s
o
f
th
e
a
s
s
o
c
i
a
t
i
o
n
b
e
t
w
e
en
e
a
ch
m
o
d
e
l
an
d
v
ar
io
u
s
c
l
a
s
s
i
f
ie
r
s
,
a
s
y
o
u
c
a
n
s
ee
t
h
e
E
f
f
i
c
i
en
t
N
e
t
a
s
s
o
c
ia
t
e
d
w
i
t
h
S
V
M
r
e
a
ch
e
d
t
h
e
to
p
o
u
t
co
m
e
s
j
u
d
g
ed
b
y
m
u
l
t
i
p
le
m
e
t
r
i
c
s
,
w
i
th
0
.
9
9
3
1
a
c
cu
r
a
cy
,
e
r
r
o
r
r
a
t
e
0
.
0
06
9,
r
e
c
a
l
l
:
0.
9
8
6
1
,
a
n
d
s
p
e
c
i
f
i
c
i
t
:1
.
A
f
te
r
ev
a
l
u
a
t
i
n
g
t
h
e
m
o
d
e
l
s
w
i
t
h
a
l
l
t
h
e
s
e
m
e
t
r
i
c
s
,
w
e
p
r
e
s
en
t
i
n
F
ig
u
r
e
5
,
t
h
e
m
a
tr
i
x
o
f
c
o
n
f
u
s
i
o
n
,
wh
i
ch
i
s
c
o
n
s
i
d
e
r
e
d
a
s
i
g
n
i
f
i
c
an
t
to
o
l
to
ju
d
g
e
t
h
e
i
n
co
r
r
e
c
tn
e
s
s
o
r
c
o
r
r
e
c
t
n
e
s
s
o
f
th
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
i
n
F
i
g
u
r
e
5
th
at
s
h
o
ws
th
e
o
u
tco
m
e
o
f
t
o
p
m
o
d
el
with
class
if
ier
:
E
f
f
icie
n
t
Net
with
SVM
in
Fig
u
r
e
5
(
a)
an
d
Dar
k
Net
with
K
-
n
ea
r
est n
eig
h
b
o
r
(
K
NN)
in
Fig
u
r
e
5
(
b
)
.
T
ab
le
1
.
Me
tr
ics v
alu
es f
o
r
Da
r
k
Net
m
o
d
el
ass
o
ciate
d
with
s
ev
er
al
class
if
ier
s
D
a
r
k
n
e
t
A
c
c
u
r
a
c
y
Er
r
o
r
R
e
c
a
l
l
S
p
e
c
i
f
i
c
i
t
y
P
r
e
c
i
s
i
o
n
FPR
F
1
_
s
c
o
r
e
M
C
C
D
i
scri
m
i
n
a
n
t
0
.
9
7
0
2
0
.
0
2
0
8
0
.
9
5
8
3
1
.
0
0
0
1
.
0
0
0
0
0
.
9
7
8
7
0
.
9
5
9
2
K
e
r
n
e
l
0
.
5
0
0
0
0
.
5
0
0
0
1
.
0
0
0
0
0
.
5
0
0
0
1
.
0
0
0
0
.
6
6
6
7
N
a
N
K
N
N
0
.
9
7
2
2
0
.
0
2
7
8
0
.
9
5
8
3
0
.
9
8
6
1
0
.
9
8
5
7
0
.
0
1
3
9
0
.
9
7
1
8
0
.
9
4
4
8
Li
n
e
a
r
0
.
9
5
1
4
0
.
0
4
8
6
0
.
9
8
6
1
0
.
9
1
6
7
0
.
9
2
2
1
0
.
0
8
3
3
0
.
9
5
3
0
0
.
9
0
5
0
N
a
ï
v
e
B
a
y
e
s
0
.
8
7
5
0
0
.
1
2
5
0
0
.
7
7
7
8
0
.
9
7
2
2
0
.
9
6
5
5
0
.
0
2
7
8
0
.
8
6
1
5
0
.
7
6
4
6
Tr
e
e
0
.
8
6
1
1
0
.
1
3
8
9
0
.
8
7
5
0
0
.
8
4
7
2
0
.
8
5
1
4
0
.
1
5
2
8
0
.
8
6
3
0
0
.
7
2
2
5
S
V
M
0
.
9
6
5
3
0
.
0
3
4
7
0
.
9
5
8
3
0
.
9
7
2
2
0
.
9
7
1
8
0
.
0
2
7
8
0
.
9
6
5
0
0
.
9
3
0
6
T
ab
le
2
.
Me
tr
ics v
alu
es f
o
r
E
f
f
icien
tNet
m
o
d
el
ass
o
ciate
d
with
s
ev
er
al
class
if
ier
s
Ef
f
i
c
i
e
n
t
N
e
t
A
c
c
u
r
a
c
y
Er
r
o
r
R
e
c
a
l
l
S
p
e
c
i
f
i
c
i
t
y
P
r
e
c
i
s
i
o
n
FPR
F
1
_
s
c
o
r
e
M
C
C
D
i
scri
m
i
n
a
n
t
0
.
9
3
0
6
0
.
0
6
9
4
0
.
9
1
6
7
0
.
9
4
4
4
0
.
9
4
2
9
0
.
0
5
5
6
0
.
9
2
9
6
0
.
8
6
1
4
K
e
r
n
e
l
0
.
5
4
8
6
0
.
4
5
1
4
0
.
5
1
3
9
0
.
5
8
3
3
0
.
5
5
2
2
0
.
4
1
6
7
0
.
5
3
2
4
0
.
0
9
7
5
K
N
N
0
.
9
3
0
6
0
.
0
6
9
4
0
.
9
3
0
6
0
.
9
3
0
6
0
.
9
3
0
6
0
.
0
6
9
4
0
.
9
3
0
6
0
.
8
6
1
1
Li
n
e
a
r
0
.
9
5
8
3
0
.
0
4
1
7
0
.
9
7
2
2
0
.
9
4
4
4
0
.
9
4
5
9
0
.
0
5
5
6
0
.
9
5
8
9
0
.
9
1
7
0
N
a
ï
v
e
B
a
y
e
s
0
.
7
2
9
2
0
.
2
7
0
8
0
.
5
2
7
8
0
.
9
3
0
6
0
.
8
8
3
7
0
.
0
6
9
4
0
.
6
6
0
9
0
.
5
0
0
7
Tr
e
e
0
.
8
4
0
3
0
.
1
5
9
7
0
.
8
4
7
2
0
.
8
3
3
3
0
.
8
3
5
6
0
.
1
6
6
7
0
.
8
4
1
4
0
.
6
8
0
6
S
V
M
0
.
9
9
3
1
0
.
0
0
6
9
0
.
9
8
6
1
1
.
0
0
0
1
.
0
0
0
0
0
.
9
9
3
0
0
.
9
8
6
2
(
a)
(
b
)
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
(
a)
E
f
f
icien
t
Net
+
SVM
an
d
(
b
)
Dar
k
Net
+
Kn
n
3
.
2
.
Dis
cus
s
io
n
Ho
s
s
ain
et
a
l.
[2
1
]
h
av
e
attain
ed
s
ig
n
if
ican
t
f
in
d
i
n
g
s
by
C
NNs
wh
ich
ar
e
u
s
ed
to
d
etec
t
ep
ilep
tic
s
eizu
r
es.
T
h
ey
ev
alu
ate
th
e
C
NN
s
o
lu
tio
n
ca
p
ab
ilit
y
to
p
er
f
o
r
m
v
ig
o
r
o
u
s
f
ea
tu
r
e
lear
n
in
g
f
r
o
m
E
E
G
d
ata
to
id
en
tify
ce
r
e
b
r
al
ep
ilep
tic
s
eizu
r
es.
T
h
is
ap
p
r
o
ac
h
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
8
.
0
5
%.
T
r
an
et
a
l.
[2
2
]
in
tr
o
d
u
ce
a
n
ew
m
ac
h
in
e
-
lear
n
i
n
g
-
b
ased
m
eth
o
d
f
o
r
id
en
tify
in
g
th
e
p
r
esen
ce
o
f
ep
ilep
s
y
ev
e
n
ts
in
r
ec
o
r
d
ed
E
E
G
s
ig
n
als.
Statis
tically
s
ig
n
if
ican
t
f
ea
tu
r
es
wer
e
m
in
ed
f
r
o
m
th
e
r
aw
d
ata
b
y
d
is
cr
ete
WT
p
r
o
ce
s
s
in
g
,
f
o
llo
wed
b
y
s
elec
tio
n
o
f
p
er
tin
e
n
t
f
ea
tu
r
es
b
y
m
ea
n
s
o
f
f
ea
tu
r
e
s
e
lectio
n
o
n
th
e
b
asis
o
f
th
e
b
in
ar
y
p
ar
ticle
s
war
m
o
p
tim
izer
.
T
h
is
m
eth
o
d
r
ed
u
c
ed
d
ata
d
im
en
s
io
n
ality
b
y
7
5
%
an
d
co
m
p
u
tatio
n
tim
e
b
y
4
7
%,
u
ltima
tely
s
p
ee
d
in
g
u
p
th
e
p
r
o
ce
s
s
o
f
ca
te
g
o
r
izatio
n
.
Af
ter
s
elec
tio
n
,
th
e
p
er
tin
en
t
f
ea
tu
r
es
wer
e
em
p
lo
y
ed
t
o
tr
ain
a
n
u
m
b
er
o
f
m
o
d
els,
an
d
h
y
p
er
p
ar
a
m
eter
tu
n
in
g
was
ap
p
lied
t
o
o
p
tim
ize
p
er
f
o
r
m
an
ce
ev
en
f
u
r
th
er
.
T
h
e
m
eth
o
d
attai
n
ed
an
ac
c
u
r
ac
y
o
f
9
8
.
4
%.
R
ag
h
u
et
a
l.
[2
3
]
lu
s
ed
DW
T
b
ased
s
ig
m
o
id
en
tr
o
p
y
in
tim
e
an
d
f
r
eq
u
en
cy
d
o
m
ain
s
f
o
r
au
to
m
ated
d
etec
tio
n
o
f
ep
ilep
tic
s
eizu
r
e
s
u
s
in
g
SVM
class
if
ier
,
f
iv
e
d
if
f
er
e
n
t
m
o
th
e
r
wav
elets
h
av
e
b
ee
n
s
tu
d
ied
.
Cl
as
s
if
icatio
n
was
p
er
f
o
r
m
e
d
u
s
in
g
b
o
th
s
eg
m
e
n
t
an
d
ev
e
n
t
-
b
ased
ap
p
r
o
ac
h
es.
B
io
3
.
1
,
R
b
io
3
.
1
,
a
n
d
Haa
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
345
-
3
5
2
350
wav
elets
wer
e
f
o
u
n
d
to
b
e
b
est
ch
o
ice
f
o
r
s
eizu
r
e
d
etec
tio
n
.
T
h
e
Kap
p
a
co
ef
f
icien
ts
o
b
tain
ed
f
o
r
all
th
e
d
atab
ases
v
er
y
g
o
o
d
r
esu
lt 9
4
.
2
1
%.
L
iu
et
a
l.
[2
4
]
s
u
g
g
est
a
d
u
al
s
elf
-
atten
tiv
e
r
esid
u
al
n
et
wo
r
k
(
R
DANe
t)
ass
o
ciat
in
g
a
s
p
ec
tr
u
m
-
atten
tiv
e
m
o
d
u
le
em
b
ed
d
i
n
g
g
lo
b
al
f
ea
tu
r
es
with
lo
ca
l
o
n
e
s
,
with
a
ch
an
n
el
-
atten
tiv
e
m
o
d
u
le
ex
p
lo
itin
g
th
e
in
ter
d
ep
en
d
en
cy
am
o
n
g
ca
n
a
l
m
ap
p
in
g
s
to
o
b
tain
b
etter
p
r
ed
ictio
n
e
f
f
ic
ien
cies.
T
h
e
a
p
p
r
o
ac
h
s
u
g
g
este
d
r
ea
ch
ed
an
ac
cu
r
ac
y
o
f
9
2
.
0
7
%.
Au
n
g
an
d
W
o
n
g
s
awa
t
[2
5
]
ex
p
lo
r
ed
th
e
b
en
ef
its
o
f
r
eli
ab
le
en
tr
o
p
ies,
f
u
zz
y
an
d
d
i
s
tr
ib
u
tio
n
en
tr
o
p
y
,
u
s
in
g
a
m
o
d
if
ie
d
d
is
tr
ib
u
tio
n
en
tr
o
p
y
(
m
Dis
tEn
)
to
d
etec
t
s
eizu
r
es.
T
h
eir
f
in
d
in
g
s
in
d
icate
th
at
th
e
ap
p
r
o
ac
h
ac
h
iev
es th
e
s
am
e
c
o
n
s
is
ten
cy
an
d
b
etter
ac
cu
r
ac
y
(
9
2
%).
Z
h
en
g
et
a
l.
[
9
]
u
s
ed
f
ea
tu
r
e
f
u
s
io
n
an
d
h
y
b
r
id
d
ee
p
lear
n
in
g
m
o
d
els
f
o
r
ep
ilep
tic
s
eizu
r
e
d
etec
tio
n
b
ased
o
n
m
u
lti
-
class
f
ea
tu
r
e
f
u
s
io
n
an
d
t
h
e
C
NN
-
g
ated
r
ec
u
r
r
en
t
u
n
it
-
at
ten
tio
n
m
ec
h
an
is
m
(
C
NN
-
GR
U
-
AM
)
m
o
d
el.
I
n
itially
,
th
e
E
E
G
s
ig
n
al
u
n
d
er
g
o
es
wav
elet
d
e
co
m
p
o
s
itio
n
th
r
o
u
g
h
th
e
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
(
DW
T
)
,
r
esu
ltin
g
in
s
ix
s
u
b
b
a
n
d
.
Su
b
s
eq
u
en
tly
,
tim
e
-
f
r
eq
u
e
n
cy
d
o
m
ain
a
n
d
n
o
n
lin
ea
r
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
ea
ch
s
u
b
b
a
n
d
.
Fin
ally
,
t
h
e
C
NN
-
GR
U
-
AM
f
u
r
th
er
ex
tr
ac
ts
f
ea
tu
r
es
an
d
p
er
f
o
r
m
s
class
if
icatio
n
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
is
m
eth
o
d
ac
h
iev
ed
a
9
4
.
9
3
% a
cc
u
r
ac
y
.
Ou
r
m
eth
o
d
b
ased
o
n
u
s
in
g
WT
an
d
ex
tr
ac
t
s
p
ec
tr
o
g
r
a
m
i
m
ag
es
f
r
o
m
ea
c
h
E
E
G
s
ig
n
al
to
u
s
e
it
a
s
in
p
u
t
to
m
o
d
el
p
r
etr
ain
e
d
,
t
o
o
v
e
r
co
m
e
th
e
lim
ited
am
o
u
n
t
o
f
d
ataset
af
te
r
th
at
we
p
r
o
p
o
s
ed
to
u
s
e
th
e
E
f
f
icien
tNet
an
d
Dar
k
Net
to
ex
tr
ac
t
f
ea
tu
r
es
a
n
d
u
s
e
m
u
lt
ip
le
class
if
ier
s
as
a
r
esu
lt
we
ac
h
iev
ed
9
9
.
3
1
%
ac
cu
r
ac
y
T
a
b
le
3
r
e
p
r
esen
t th
e
co
m
p
ar
is
o
n
b
etwe
en
all
s
tu
d
i
es h
av
e
b
ee
n
cited
b
ef
o
r
e
an
d
o
u
r
s
.
T
ab
le
3
.
C
o
m
p
a
r
in
g
o
u
tco
m
es
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
with
r
e
ce
n
t r
esear
ch
r
elate
d
t
o
ep
ilep
s
y
class
f
icatio
n
A
u
t
h
o
r
M
e
t
h
o
d
A
C
C
A
c
c
i
mp
r
o
v
e
me
n
t
H
o
ssa
i
n
e
t
a
l
.
[2
1
]
C
N
N
9
8
.
0
5
%
1
.
2
6
%
Tr
a
n
e
t
a
l
.
[2
2
]
D
W
T
9
8
.
4
%
0
.
9
1
%
R
a
g
h
u
e
t
a
l
.
[2
3
]
D
W
T
b
a
se
d
s
i
g
m
o
i
d
e
n
t
r
o
p
y
w
i
t
h
S
V
M
9
4
.
2
1
%
5
.
1
%
Li
u
e
t
a
l
.
[2
4
]
R
D
A
N
e
t
9
2
.
0
7
%
7
.
2
4
%
A
u
n
g
a
n
d
W
o
n
g
s
a
w
a
t
[2
5
]
F
u
z
z
y
e
n
t
r
o
p
y
mD
i
st
E
n
9
2
%
7
.
3
1
%
Zh
e
n
g
e
t
a
l
.
[
9
]
C
N
N
-
G
R
U
-
AM
9
4
.
9
3
%
4
.
3
8
%
Th
i
s
st
u
d
y
D
a
r
k
N
e
t
+
K
n
n
9
7
.
2
2
%
2
.
0
9
%
Ef
f
i
c
i
e
n
t
N
e
t
+
S
V
M
9
9
.
3
1
%
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
is
b
ased
o
n
th
e
tr
an
s
f
er
lear
n
i
n
g
m
o
d
el
ap
p
r
o
a
ch
wh
er
e
,
f
i
r
s
tly
,
we
e
x
tr
ac
te
d
th
e
E
E
G
s
ig
n
als
f
r
o
m
th
e
E
DF
f
iles
;
th
en
,
we
tr
ied
to
r
ed
u
ce
th
e
n
o
is
e
in
th
ese
s
ig
n
als
b
y
a
f
ilter
a
n
d
we
u
s
ed
th
e
WT
to
o
b
tain
th
e
s
p
ec
tr
o
g
r
a
m
im
a
g
es o
f
ea
ch
ch
an
n
el
,
wh
ic
h
wer
e
u
s
ed
as in
p
u
t f
o
r
th
e
Dar
k
N
et
an
d
E
f
f
icien
tNet
p
r
e
-
tr
ain
ed
m
o
d
els,
wh
ich
wer
e
ass
o
ciate
d
ea
ch
tim
e
w
ith
a
d
if
f
er
en
t
class
if
ier
,
th
e
m
o
d
els
ch
o
s
en
ar
e
th
e
latest
m
o
d
el
with
th
e
C
NN
s
tr
u
ctu
r
e,
well
k
n
o
wn
f
o
r
its
g
r
e
at
in
v
o
lv
em
en
t
i
n
th
e
au
to
m
ate
d
d
etec
tin
g
in
th
e
d
o
m
ain
o
f
m
ed
icin
e,
it
is
co
n
s
id
er
ed
as
a
v
er
y
p
r
o
m
is
in
g
a
p
p
r
o
ac
h
th
at
is
ab
le
to
ac
h
iev
e
g
r
ea
t
r
esu
lts
wh
en
u
s
ed
as
a
f
ea
tu
r
e
ex
tr
ac
to
r
w
h
er
e
th
e
in
p
u
t
is
im
ag
es.
T
h
u
s
,
we
u
s
ed
as
f
ea
tu
r
e
ex
tr
ac
to
r
s
,
th
e
two
m
o
d
els
m
en
tio
n
ed
a
b
o
v
e,
a
n
d
as
class
if
ier
s
.
As
a
r
esu
lt,
f
o
r
ep
ilep
s
y
class
if
icatio
n
,
th
e
m
eth
o
d
p
r
o
p
o
s
ed
in
th
is
s
tu
d
y
ac
h
iev
ed
a
r
em
a
r
k
ab
le
r
esu
lt,
wh
ich
m
ay
b
e
a
g
r
ea
t
m
o
tiv
at
io
n
to
g
o
f
u
r
th
er
with
th
e
aim
o
f
n
o
t
k
ee
p
in
g
th
e
s
ea
r
ch
lim
ited
to
th
e
id
en
tific
atio
n
o
f
two
class
es
o
n
ly
b
u
t
r
ec
o
g
n
izin
g
th
e
af
f
ec
ted
ar
ea
an
d
th
e
s
p
ec
if
ic
ty
p
e
o
f
ep
ilep
s
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
d
id
n
o
t
b
en
e
f
it
f
r
o
m
an
y
s
p
ec
if
ic
f
in
a
n
cial
s
u
p
p
o
r
t
f
r
o
m
a
n
y
f
u
n
d
in
g
o
r
g
an
izatio
n
in
th
e
p
u
b
lic,
c
o
m
m
er
cial
o
r
n
o
t
-
f
o
r
-
p
r
o
f
it secto
r
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Fatim
a
E
d
d
er
b
ali
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ham
id
E
l
M
alali
✓
✓
✓
E
lm
aa
ti E
s
s
o
u
k
ak
i
✓
✓
✓
Mo
h
am
m
ed
Har
m
o
u
c
h
i
✓
✓
✓
✓
✓
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:
2502
-
4
7
5
2
N
ew tec
h
n
ic
o
f tra
n
s
fer lea
r
n
i
n
g
fo
r
d
etec
tin
g
e
p
ilep
s
y
b
y
E
f
ficien
tN
et
…
(
F
a
tima
E
d
d
erb
a
li
)
351
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
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
in
d
in
g
s
o
f
t
h
is
s
tu
d
y
ar
e
o
p
en
ly
av
ailab
le
i
n
Me
n
d
ele
y
Data
at
h
ttp
://d
o
i.o
r
g
/
1
0
.
1
7
6
3
2
/5
p
c
2
j4
6
cb
c.
1
RE
F
E
R
E
NC
E
S
[
1
]
C
.
O
.
O
l
u
i
g
b
o
,
A
.
S
a
l
m
a
,
a
n
d
A
.
R
.
R
e
z
a
i
,
“
D
e
e
p
b
r
a
i
n
st
i
m
u
l
a
t
i
o
n
f
o
r
n
e
u
r
o
l
o
g
i
c
a
l
d
i
so
r
d
e
r
s,
”
I
E
EE
Re
v
i
e
w
s
i
n
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
,
p
p
.
8
8
–
9
9
,
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
R
B
M
E
.
2
0
1
2
.
2
1
9
7
7
4
5
.
[
2
]
N
a
j
i
Y
,
H
r
o
u
c
h
W
,
La
a
d
a
mi
S
,
A
d
a
l
i
N
.
A
n
t
i
-
se
i
z
u
r
e
m
e
d
i
c
a
t
i
o
n
p
r
e
s
c
r
i
p
t
i
o
n
p
r
e
f
e
r
e
n
c
e
s
:
a
M
o
r
o
c
c
a
n
m
u
l
t
i
c
e
n
t
e
r
st
u
d
y
.
F
r
o
n
t
N
e
u
r
o
l
.
2
0
2
4
A
u
g
2
3
;
1
5
:
1
4
3
5
0
7
5
.
d
o
i
:
1
0
.
3
3
8
9
/
f
n
e
u
r
.
2
0
2
4
.
1
4
3
5
0
7
5
.
P
M
I
D
:
3
9
2
4
6
6
0
5
;
P
M
C
I
D
:
P
M
C
1
1
3
7
8
5
2
4
.
[
3
]
E.
K
a
b
i
r
,
S
i
u
l
y
,
J.
C
a
o
,
a
n
d
H
.
W
a
n
g
,
“
A
c
o
m
p
u
t
e
r
a
i
d
e
d
a
n
a
l
y
s
i
s
sc
h
e
me
f
o
r
d
e
t
e
c
t
i
n
g
e
p
i
l
e
p
t
i
c
s
e
i
z
u
r
e
f
r
o
m
EEG
d
a
t
a
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
S
y
s
t
e
m
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
p
.
6
6
3
–
6
7
1
,
2
0
1
8
,
d
o
i
:
1
0
.
2
9
9
1
/
i
j
c
i
s
.
1
1
.
1
.
5
1
.
[
4
]
S
.
S
i
u
l
y
a
n
d
Y
.
Z
h
a
n
g
,
“
M
e
d
i
c
a
l
b
i
g
d
a
t
a
:
n
e
u
r
o
l
o
g
i
c
a
l
d
i
se
a
ses
d
i
a
g
n
o
si
s
t
h
r
o
u
g
h
me
d
i
c
a
l
d
a
t
a
a
n
a
l
y
s
i
s,
”
D
a
t
a
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
5
4
–
6
4
,
Ju
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
1
0
1
9
-
0
1
6
-
0
0
1
1
-
3.
[
5
]
U
.
R
.
A
c
h
a
r
y
a
,
S
.
V
.
S
r
e
e
,
G
.
S
w
a
p
n
a
,
R
.
J
.
M
a
r
t
i
s,
a
n
d
J.
S
.
S
u
r
i
,
“
A
u
t
o
mat
e
d
EEG
a
n
a
l
y
si
s
o
f
e
p
i
l
e
p
s
y
:
a
r
e
v
i
e
w
,
”
K
n
o
w
l
e
d
g
e
-
Ba
se
d
S
y
st
e
m
s
,
v
o
l
.
4
5
,
p
p
.
1
4
7
–
1
6
5
,
Ju
n
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s
.
2
0
1
3
.
0
2
.
0
1
4
.
[
6
]
F
.
H
.
Lo
p
e
s d
a
S
i
l
v
a
,
“
T
h
e
i
m
p
a
c
t
o
f
EEG
/
M
EG
si
g
n
a
l
p
r
o
c
e
ss
i
n
g
a
n
d
m
o
d
e
l
i
n
g
i
n
t
h
e
d
i
a
g
n
o
st
i
c
a
n
d
ma
n
a
g
e
m
e
n
t
o
f
e
p
i
l
e
p
s
y
.
,
”
I
EEE
re
v
i
e
w
s
i
n
b
i
o
m
e
d
i
c
a
l
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
,
p
p
.
1
4
3
–
1
5
6
,
2
0
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
R
B
M
E
.
2
0
0
8
.
2
0
0
8
2
4
6
.
[
7
]
H
.
W
i
t
t
e
,
L.
D
.
I
a
semi
d
i
s
,
a
n
d
B
.
Li
t
t
,
“
S
p
e
c
i
a
l
i
ss
u
e
o
n
e
p
i
l
e
p
t
i
c
s
e
i
z
u
r
e
p
r
e
d
i
c
t
i
o
n
,
”
I
EE
E
T
r
a
n
sa
c
t
i
o
n
s
o
n
Bi
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
0
,
n
o
.
5
,
p
p
.
5
3
7
–
5
3
9
,
M
a
y
2
0
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
B
M
E.
2
0
0
3
.
8
1
0
7
0
8
.
[
8
]
S
.
S
i
u
l
y
a
n
d
Y
.
L
i
,
“
D
e
s
i
g
n
i
n
g
a
r
o
b
u
st
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
m
e
t
h
o
d
b
a
se
d
o
n
o
p
t
i
mu
m
a
l
l
o
c
a
t
i
o
n
a
n
d
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
si
s
f
o
r
e
p
i
l
e
p
t
i
c
EEG
s
i
g
n
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
C
o
m
p
u
t
e
r
M
e
t
h
o
d
s
a
n
d
Pr
o
g
r
a
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
1
9
,
n
o
.
1
,
p
p
.
2
9
–
4
2
,
A
p
r
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
mp
b
.
2
0
1
5
.
0
1
.
0
0
2
.
[
9
]
J.
Z
h
a
n
g
,
S
.
Z
h
e
n
g
,
W
.
C
h
e
n
,
G
.
D
u
,
Q
.
F
u
,
a
n
d
H
.
J
i
a
n
g
,
“
A
sc
h
e
m
e
c
o
m
b
i
n
i
n
g
f
e
a
t
u
r
e
f
u
si
o
n
a
n
d
h
y
b
r
i
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
e
p
i
l
e
p
t
i
c
s
e
i
z
u
r
e
d
e
t
e
c
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
4
,
n
o
.
1
,
p
.
1
6
9
1
6
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
024
-
6
7
8
5
5
-
4.
[1
0
]
F
.
Ed
d
e
r
b
a
l
i
,
M
.
H
a
r
mo
u
c
h
i
,
a
n
d
E.
Esso
u
k
a
k
i
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
EEG
s
i
g
n
a
l
b
a
s
e
d
o
n
p
r
e
-
t
r
a
i
n
e
d
2
D
C
N
N
mo
d
e
l
f
o
r
e
p
i
l
e
p
sy
d
e
t
e
c
t
i
o
n
,
”
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
N
e
t
w
o
rks
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
6
6
8
LN
N
S
,
2
0
2
3
,
p
p
.
1
0
0
8
–
1
0
1
6
.
[1
1
]
F
.
E
d
d
e
r
b
a
l
i
,
M
.
H
a
r
m
o
u
c
h
i
,
a
n
d
E
.
Ess
o
u
k
a
k
i
,
“
Tr
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
e
p
i
l
e
p
s
y
d
e
t
e
c
t
i
o
n
u
si
n
g
s
p
e
c
t
r
o
g
r
a
m
i
ma
g
e
s,
”
I
AE
S
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
0
2
2
–
1
0
2
9
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
1
.
p
p
1
0
2
2
-
1
0
2
9
.
[1
2
]
F
.
Ed
d
e
r
b
a
l
i
,
M
.
H
a
r
mo
u
c
h
i
,
a
n
d
E
.
Ess
o
u
k
a
k
i
,
“
M
o
b
i
l
e
n
e
t
,
i
n
c
e
p
t
i
o
n
R
e
sN
e
t
a
n
d
G
o
o
g
l
e
N
e
t
f
o
r
e
p
i
l
e
p
s
y
d
e
t
e
c
t
i
o
n
u
si
n
g
sp
e
c
t
r
o
g
r
a
m
i
ma
g
e
s
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
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
(
I
J
EE
C
S
)
,
v
o
l
.
3
4
,
n
o
.
2
,
p
p
.
8
7
0
–
8
7
7
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
4
.
i
2
.
p
p
8
7
0
-
8
7
7
.
[1
3
]
M
.
To
ğ
a
ç
a
r
,
“
U
s
i
n
g
D
a
r
k
N
e
t
m
o
d
e
l
s
a
n
d
me
t
a
h
e
u
r
i
s
t
i
c
o
p
t
i
m
i
z
a
t
i
o
n
m
e
t
h
o
d
s
t
o
g
e
t
h
e
r
t
o
d
e
t
e
c
t
w
e
e
d
s
g
r
o
w
i
n
g
a
l
o
n
g
w
i
t
h
see
d
l
i
n
g
s,
”
E
c
o
l
o
g
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
6
8
,
p
.
1
0
1
5
1
9
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
o
i
n
f
.
2
0
2
1
.
1
0
1
5
1
9
.
[1
4
]
P
.
S
o
w
a
a
n
d
J.
I
z
y
d
o
r
c
z
y
k
,
“
D
a
r
k
n
e
t
o
n
O
p
e
n
C
L:
A
m
u
l
t
i
p
l
a
t
f
o
r
m
t
o
o
l
f
o
r
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
C
o
n
c
u
rre
n
c
y
a
n
d
C
o
m
p
u
t
a
t
i
o
n
:
Pr
a
c
t
i
c
e
a
n
d
Ex
p
e
ri
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
1
5
.
Ju
l
.
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
c
p
e
.
6
9
3
6
.
[1
5
]
Y
.
D
.
Z
h
a
n
g
,
S
.
C
.
S
a
t
a
p
a
t
h
y
,
S
.
L
i
u
,
a
n
d
G
.
R
.
L
i
,
“
A
f
i
v
e
-
l
a
y
e
r
d
e
e
p
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
w
i
t
h
s
t
o
c
h
a
st
i
c
p
o
o
l
i
n
g
f
o
r
c
h
e
st
C
T
-
b
a
se
d
C
O
V
I
D
-
1
9
d
i
a
g
n
o
si
s
,
”
M
a
c
h
i
n
e
V
i
si
o
n
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
2
,
n
o
.
1
,
p
.
1
4
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
1
3
8
-
0
2
0
-
0
1
1
2
8
-
8.
[1
6
]
S
.
M
a
h
a
r
j
a
n
,
A
.
A
l
s
a
d
o
o
n
,
P
.
W
.
C
.
P
r
a
sad
,
T.
A
l
-
D
a
l
a
i
n
,
a
n
d
O
.
H
.
A
l
s
a
d
o
o
n
,
“
A
n
o
v
e
l
e
n
h
a
n
c
e
d
s
o
f
t
m
a
x
l
o
ss
f
u
n
c
t
i
o
n
f
o
r
b
r
a
i
n
t
u
m
o
u
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
J
o
u
rn
a
l
o
f
N
e
u
ro
s
c
i
e
n
c
e
Me
t
h
o
d
s
,
v
o
l
.
3
3
0
,
p
.
1
0
8
5
2
0
,
Jan
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
n
e
u
me
t
h
.
2
0
1
9
.
1
0
8
5
2
0
.
[1
7
]
H
.
C
h
e
n
,
Y
.
H
.
W
a
n
g
,
a
n
d
C
.
H
.
F
a
n
,
“
A
c
o
n
v
o
l
u
t
i
o
n
a
l
a
u
t
o
e
n
c
o
d
e
r
-
b
a
s
e
d
a
p
p
r
o
a
c
h
w
i
t
h
b
a
t
c
h
n
o
r
ma
l
i
z
a
t
i
o
n
f
o
r
e
n
e
r
g
y
d
i
s
a
g
g
r
e
g
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
7
,
n
o
.
3
,
p
p
.
2
9
6
1
–
2
9
7
8
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
0
2
0
-
0
3
3
7
5
-
y.
[
18
]
M
.
Ta
n
a
n
d
Q
.
V
.
Le
,
“
Ef
f
i
c
i
e
n
t
N
e
t
V
2
:
S
ma
l
l
e
r
M
o
d
e
l
s
a
n
d
F
a
st
e
r
Tr
a
i
n
i
n
g
,
”
Pro
c
e
e
d
i
n
g
s
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
3
9
,
p
p
.
1
0
0
9
6
–
1
0
1
0
6
,
2
0
2
1
.
[
19
]
M
.
S
o
k
o
l
o
v
a
a
n
d
G
.
L
a
p
a
l
me,
“
A
sy
st
e
ma
t
i
c
a
n
a
l
y
s
i
s
o
f
p
e
r
f
o
r
m
a
n
c
e
me
a
su
r
e
s
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
t
a
s
k
s,”
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
& M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
4
5
,
n
o
.
4
,
p
p
.
4
2
7
–
4
3
7
,
J
u
l
.
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
p
m.
2
0
0
9
.
0
3
.
0
0
2
.
[2
0
]
G
.
C
a
n
b
e
k
,
T
.
T
.
Te
m
i
z
e
l
,
a
n
d
S
.
S
a
g
i
r
o
g
l
u
,
“
B
e
n
c
h
M
e
t
r
i
c
s:
a
sy
s
t
e
m
a
t
i
c
b
e
n
c
h
mar
k
i
n
g
me
t
h
o
d
f
o
r
b
i
n
a
r
y
c
l
a
ssi
f
i
c
a
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
m
e
t
r
i
c
s,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
3
,
n
o
.
2
1
,
p
p
.
1
4
6
2
3
–
1
4
6
5
0
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
1
-
0
6
1
0
3
-
6.
[2
1
]
M
.
S
.
H
o
ssa
i
n
,
S
.
U
.
A
mi
n
,
M
.
A
l
s
u
l
a
i
ma
n
,
a
n
d
G
.
M
u
h
a
mm
a
d
,
“
A
p
p
l
y
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
e
p
i
l
e
p
s
y
se
i
z
u
r
e
d
e
t
e
c
t
i
o
n
a
n
d
b
r
a
i
n
map
p
i
n
g
v
i
su
a
l
i
z
a
t
i
o
n
,
”
AC
M
T
r
a
n
sa
c
t
i
o
n
s
o
n
M
u
l
t
i
m
e
d
i
a
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
5
,
n
o
.
1
s,
p
p
.
1
–
1
7
,
Ja
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
4
5
/
3
2
4
1
0
5
6
.
[2
2
]
L.
V
.
Tr
a
n
,
H
.
M
.
Tr
a
n
,
T
.
M
.
Le
,
T.
T.
M
.
H
u
y
n
h
,
H
.
T.
Tr
a
n
,
a
n
d
S
.
V
.
T.
D
a
o
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
i
n
e
p
i
l
e
p
t
i
c
sei
z
u
r
e
d
e
t
e
c
t
i
o
n
,
”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
2
,
n
o
.
1
1
,
p
.
2
8
7
9
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
2
1
1
2
8
7
9
.
[2
3
]
S
.
R
a
g
h
u
,
N
.
S
r
i
r
a
a
m,
Y
.
Te
me
l
,
S
.
V
.
R
a
o
,
A
.
S
.
H
e
g
d
e
,
a
n
d
P
.
L.
K
u
b
b
e
n
,
“
P
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
D
W
T
b
a
s
e
d
s
i
g
m
o
i
d
e
n
t
r
o
p
y
i
n
t
i
me
a
n
d
f
r
e
q
u
e
n
c
y
d
o
ma
i
n
s
f
o
r
a
u
t
o
ma
t
e
d
d
e
t
e
c
t
i
o
n
o
f
e
p
i
l
e
p
t
i
c
sei
z
u
r
e
s
u
si
n
g
S
V
M
c
l
a
ssi
f
i
e
r
,
”
C
o
m
p
u
t
e
rs i
n
B
i
o
l
o
g
y
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
1
0
,
p
p
.
1
2
7
–
1
4
3
,
Ju
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
m
e
d
.
2
0
1
9
.
0
5
.
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
345
-
3
5
2
352
[2
4
]
Y
.
Li
u
,
W
.
Z
h
o
u
,
Q
.
Y
u
a
n
,
a
n
d
S
.
C
h
e
n
,
“
A
u
t
o
m
a
t
i
c
s
e
i
z
u
r
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m a
n
d
S
V
M
i
n
l
o
n
g
-
t
e
r
m i
n
t
r
a
c
r
a
n
i
a
l
EEG
,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
N
e
u
ra
l
S
y
st
e
m
s
a
n
d
R
e
h
a
b
i
l
i
t
a
t
i
o
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
,
n
o
.
6
,
p
p
.
7
4
9
–
7
5
5
,
N
o
v
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
R
E.
2
0
1
2
.
2
2
0
6
0
5
4
.
[2
5
]
S
.
T.
A
u
n
g
a
n
d
Y
.
W
o
n
g
sawa
t
,
“
M
o
d
i
f
i
e
d
-
d
i
st
r
i
b
u
t
i
o
n
e
n
t
r
o
p
y
a
s
t
h
e
f
e
a
t
u
r
e
s
f
o
r
t
h
e
d
e
t
e
c
t
i
o
n
o
f
e
p
i
l
e
p
t
i
c
s
e
i
z
u
r
e
s,”
Fro
n
t
i
e
r
s
i
n
Ph
y
s
i
o
l
o
g
y
,
v
o
l
.
1
1
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
h
y
s.
2
0
2
0
.
0
0
6
0
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Fa
tim
a
Ed
d
e
r
b
a
li
h
o
ld
s
a
M
a
ste
r
o
f
a
u
to
m
a
ti
c
d
e
g
re
e
fr
o
m
Ha
ss
a
n
F
irst
Un
iv
e
rsity
o
f
S
e
tt
a
t
in
M
o
r
o
c
c
o
i
n
2
0
1
5
.
S
h
e
a
lso
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r
’
s
d
e
g
re
e
o
n
e
lec
tro
n
ic
a
n
d
su
p
e
rio
r
tec
h
n
icia
n
in
e
lec
tr
o
n
ic
m
a
in
te
n
a
n
c
e
,
re
sp
e
c
ti
v
e
ly
.
S
h
e
is
c
u
rre
n
tl
y
a
tea
c
h
e
r
o
f
e
lec
tri
c
e
n
g
in
e
e
rin
g
a
t
h
i
g
h
sc
h
o
o
l
si
n
c
e
2
0
1
2
.
He
r
re
se
a
rc
h
i
n
c
lu
d
e
s
b
i
o
m
e
d
ica
l
sc
ien
c
e
a
n
d
d
e
e
p
lea
rn
i
n
g
a
p
p
l
ica
ti
o
n
in
t
h
e
h
e
a
lt
h
fiel
d
.
S
h
e
h
a
s
p
u
b
l
ish
e
d
p
u
b
li
c
a
ti
o
n
s
a
n
d
a
rt
icle
s
su
c
h
a
s
a
c
h
a
p
ter
p
a
p
e
r
in
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
ICDTA:
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
o
n
d
i
g
it
a
l
tec
h
n
o
l
o
g
ies
a
n
d
a
p
p
l
ica
ti
o
n
s
.
F
r
o
m
Oc
to
b
e
r
2
0
1
9
u
n
ti
l
n
o
w,
s
h
e
h
a
s
b
e
e
n
P
h
.
D.
st
u
d
e
n
t
a
t
Lab
o
ra
to
r
y
o
f
Ra
d
ian
c
e
-
M
a
ter
a
n
d
In
str
u
m
e
n
tatio
n
a
t
Ha
ss
a
n
F
irst
Un
iv
e
rsit
y
o
f
S
e
t
tat,
M
o
ro
c
c
o
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
f.
e
d
d
e
rb
a
li
@
u
h
p
.
a
c
.
m
a
.
H
a
m
id
E
l
M
a
la
li
Ha
m
id
El
m
a
lali
wa
s
b
o
rn
i
n
Err
ich
-
M
i
d
e
l
t
M
o
r
o
c
c
o
.
He
is
d
o
c
to
ra
te
i
n
Bi
o
m
e
d
ica
l
En
g
in
e
e
rin
g
a
n
d
I
n
stru
m
e
n
tati
o
n
Lab
o
ra
to
ry
“
RM
I”
in
sc
ien
c
e
a
n
d
tec
h
n
o
l
o
g
y
fa
c
u
lt
y
Ha
ss
a
n
1
st,
U
n
iv
e
rsit
y
S
e
tt
a
t
M
o
r
o
c
c
o
.
He
h
o
l
d
s
a
b
a
c
h
e
lo
r
’
s
in
p
h
y
sic
s
a
t
Si
d
i
M
o
h
a
m
m
e
d
b
e
n
A
b
d
e
ll
a
h
Un
iv
e
rsit
y
F
e
s
i
n
1
9
9
7
,
a
n
d
a
M
a
ste
r
o
f
S
c
ie
n
c
e
a
n
d
Tec
h
n
o
l
o
g
y
in
Bi
o
m
e
d
ica
l
En
g
i
n
e
e
rin
g
a
n
d
In
str
u
m
e
n
tatio
n
a
t
Ha
ss
a
n
1
st
Un
iv
e
rsity
S
e
tt
a
t
i
n
2
0
1
6
.
His
re
se
a
rc
h
in
tere
sts
a
re
c
o
m
p
u
ter
v
isio
n
,
ima
g
e
p
r
o
c
e
ss
in
g
,
m
a
c
h
i
n
e
lea
rn
in
g
,
a
nd
a
rti
ficia
l
in
telli
g
e
n
c
e
.
In
2
0
0
3
,
h
e
h
o
l
d
s
a
d
i
p
lo
m
a
i
n
c
o
m
p
u
ter
sc
ien
c
e
fro
m
th
e
Re
g
i
o
n
a
l
P
e
d
a
g
o
g
ica
l
Ce
n
ter
o
f
F
e
z
.
Cu
r
re
n
tl
y
,
h
e
is
p
r
o
fe
ss
o
r
o
f
p
h
y
si
c
s
a
n
d
m
e
d
ica
l
ima
g
in
g
a
t
Ha
ss
a
n
F
irst
Un
iv
e
rsit
y
S
e
tt
a
t
M
o
ro
c
c
o
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
.
e
l
m
a
lali@u
h
p
.
a
c
.
m
a
.
Elm
a
a
ti
Ess
o
u
k
a
k
i
b
o
rn
o
n
1
Ja
n
u
a
ry
1
9
9
0
.
He
is
c
u
rre
n
tl
y
a
P
r
o
fe
ss
o
r
o
f
In
stru
m
e
n
tati
o
n
a
n
d
Bio
m
e
d
ica
l
En
g
i
n
e
e
rin
g
a
t
Hig
h
e
r
In
stit
u
te
o
f
He
a
lt
h
S
c
ien
c
e
s
(IS
S
S
)
,
Ha
ss
a
n
F
irst
Un
iv
e
rsity
.
His
r
e
se
a
rc
h
in
tere
sts
in
c
lu
d
e
in
str
u
m
e
n
tatio
n
a
n
d
b
i
o
m
e
d
ica
l
e
n
g
in
e
e
rin
g
,
b
i
o
m
e
d
ica
l
ima
g
i
n
g
,
a
n
d
si
g
n
a
l
p
ro
c
e
ss
in
g
.
He
h
o
l
d
s
se
v
e
ra
l
p
u
b
li
c
a
ti
o
n
s
a
n
d
in
n
o
v
a
ti
o
n
p
a
ten
ts
i
n
t
h
e
fiel
d
s o
f
b
i
o
p
h
y
sic
s
a
n
d
b
i
o
m
e
d
ica
l
e
n
g
in
e
e
rin
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
.
e
ss
o
u
k
a
k
i@u
h
p
.
a
c
.
m
a
.
Mo
h
a
m
m
e
d
H
a
r
m
o
u
c
h
i
b
o
r
n
i
n
S
e
fro
u
,
M
o
r
o
c
c
o
,
i
n
1
9
5
9
.
He
is
i
n
c
h
a
rg
e
o
f
th
e
m
a
ste
r
’
s
d
e
g
re
e
in
b
io
m
e
d
ica
l
e
n
g
in
e
e
rin
g
:
in
str
u
m
e
n
tatio
n
a
n
d
m
a
in
ten
a
n
c
e
.
He
is
th
e
Ex
-
Dire
c
to
r
o
f
t
h
e
Lab
o
ra
t
o
ry
o
f
Ra
d
iatio
n
-
M
a
tt
e
r
a
n
d
I
n
st
ru
m
e
n
tatio
n
,
Ha
ss
a
n
F
irst
Un
iv
e
rsity
,
S
e
tt
a
t,
M
o
r
o
c
c
o
,
w
h
e
re
h
e
is
c
u
rr
e
n
tl
y
a
P
r
o
fe
ss
o
r
o
f
Hig
h
e
r
E
d
u
c
a
ti
o
n
a
n
d
t
h
e
Ex
-
He
a
d
o
f
t
h
e
De
p
a
rtme
n
t
o
f
A
p
p
li
e
d
P
h
y
sic
s,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
.
He
h
o
l
d
s
se
v
e
ra
l
p
u
b
li
c
a
ti
o
n
s
a
n
d
in
n
o
v
a
ti
o
n
p
a
ten
ts
i
n
t
h
e
f
ield
s
o
f
b
io
p
h
y
sic
s
a
n
d
b
io
m
e
d
ica
l
e
n
g
in
e
e
rin
g
(
b
a
se
d
o
n
d
o
c
u
m
e
n
t
p
u
b
li
sh
e
d
o
n
9
Oc
to
b
e
r
2
0
2
0
).
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
h
a
rm
o
u
c
h
i1
4
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.