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.
25
,
No
.
1
,
J
an
u
ar
y
2
0
2
2
,
p
p
.
29
1
~
2
9
7
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijeecs.v
25
.i
1
.
pp
291
-
2
9
7
291
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
E
f
f
i
c
i
e
n
t
e
l
e
c
t
r
o
e
n
c
e
p
h
e
l
o
g
r
a
m
c
l
a
s
s
i
f
i
c
a
t
i
o
n
s
y
s
t
e
m
u
s
i
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
c
l
a
s
s
i
f
i
e
r
a
n
d
a
d
a
p
t
i
v
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
Virupa
x
i
B
a
la
cha
nd
ra
Da
la
l
1
,
Sa
t
is
h
S.
B
ha
ira
nn
a
wa
r
2
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
J
a
i
n
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
R
e
sea
r
c
h
,
B
e
l
a
g
a
v
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
S
D
M
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
D
h
a
r
w
a
d
,
I
n
d
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
13
,
2
0
2
1
R
ev
is
ed
Oct
21
,
2
0
2
1
Acc
ep
ted
No
v
27
,
2
0
2
1
Co
m
p
lex
m
o
d
e
rn
sig
n
a
l
p
ro
c
e
ss
in
g
is
u
se
d
to
a
u
t
o
m
a
te
th
e
a
n
a
ly
sis
o
f
e
lec
tro
e
n
c
e
p
h
e
lo
g
ra
m
(EE
G
)
sig
n
a
ls.
F
o
r
th
e
d
iag
n
o
sis
o
f
se
izu
re
s,
a
p
p
ro
a
c
h
e
s
t
h
a
t
a
re
sim
p
le
a
n
d
p
re
c
ise
m
a
y
b
e
p
re
fe
ra
b
le
r
a
th
e
r
th
a
n
d
iffi
c
u
lt
a
n
d
ti
m
e
-
c
o
n
s
u
m
in
g
.
I
n
th
is
p
a
p
e
r,
e
fficie
n
t
EE
G
c
las
sifica
ti
o
n
sy
ste
m
u
sin
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
a
n
d
A
d
a
p
ti
v
e
lea
rn
in
g
tec
h
n
iq
u
e
is
p
ro
p
o
se
d
.
T
h
e
d
a
tab
a
se
EE
G
sig
n
a
ls
a
re
su
b
jec
ted
to
tem
p
o
ra
l
a
n
d
s
p
a
ti
a
l
fil
teri
n
g
t
o
re
m
o
v
e
u
n
wa
n
ted
n
o
ise
a
n
d
t
o
in
c
re
a
se
th
e
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
o
f
th
e
c
las
sifier
b
y
se
lec
ti
n
g
t
h
e
sp
e
c
ifi
c
b
a
n
d
s
i
n
wh
ic
h
m
o
st
o
f
th
e
EE
G
d
a
ta
a
re
p
re
se
n
t.
Th
e
n
e
u
ra
l
n
e
two
r
k
b
a
se
d
S
VM
is
u
se
d
to
c
las
sify
th
e
tes
t
EE
G
d
a
ta
wit
h
re
sp
e
c
t
t
o
train
in
g
d
a
ta.
Th
e
c
o
st
-
se
n
siti
v
e
S
VM
with
p
ro
p
o
se
d
Ad
a
p
ti
v
e
lea
rn
i
n
g
c
las
sifies
th
e
EE
G
sig
n
a
ls
wh
e
re
th
e
a
d
a
p
ti
v
e
lea
rn
in
g
wit
h
p
ro
b
a
b
il
i
ty
b
a
se
d
fu
n
c
t
i
o
n
h
e
l
p
s
i
n
p
re
d
icti
o
n
o
f
t
h
e
fu
tu
re
sa
m
p
les
a
n
d
th
is
lea
d
s
in
imp
r
o
v
in
g
t
h
e
a
c
c
u
ra
c
y
with
d
e
tec
ti
o
n
t
ime
.
Th
e
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
o
f
th
e
p
r
o
p
o
se
d
a
lg
o
r
it
h
m
is
c
o
m
p
a
re
d
with
e
x
isti
n
g
wh
ich
sh
o
ws
t
h
a
t
t
h
e
p
r
o
p
o
se
d
a
lg
o
rit
h
m
c
a
n
c
las
sify
th
e
EE
G
sig
n
a
l
m
o
re
e
ffe
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
Ad
ap
tiv
e
lear
n
in
g
C
las
s
if
ier
E
lectr
o
en
ce
p
h
elo
g
r
a
m
Sp
atial
f
ilter
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
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
:
Vir
u
p
ax
i
B
alac
h
an
d
r
a
Dala
l
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
J
ain
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
a
n
d
R
esear
ch
B
elag
av
i
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail:
v
ir
u
p
ax
i.
d
alal@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
elec
tr
o
en
ce
p
h
alo
g
r
am
(
E
E
G)
is
o
n
e
o
f
th
e
m
o
s
t
co
m
m
o
n
a
n
d
s
tr
aig
h
t
f
o
r
war
d
m
eth
o
d
s
f
o
r
d
etec
tin
g
an
d
d
ia
g
n
o
s
in
g
s
eiz
u
r
es.
T
h
e
ea
s
e
with
wh
ich
E
E
G
co
u
ld
b
e
u
s
ed
b
y
o
r
d
in
ar
y
p
eo
p
le
o
n
a
b
u
d
g
et
m
ad
e
it
a
p
o
p
u
lar
m
eth
o
d
.
T
h
e
E
E
G
d
ata
ac
q
u
ir
ed
f
r
o
m
th
e
b
r
ain
ar
e
also
co
m
p
lex
d
u
e
t
o
th
e
s
o
p
h
is
ticated
ar
ch
itectu
r
e
o
f
th
e
b
r
ain
s
y
s
tem
.
T
h
e
elec
tr
ical
s
ig
n
al
g
e
n
er
ated
b
y
th
e
h
u
m
a
n
b
r
ai
n
is
ca
p
tu
r
ed
th
r
o
u
g
h
th
e
elec
tr
o
d
e
attac
h
ed
to
a
p
er
s
o
n
’
s
h
ea
d
.
Du
e
to
th
e
ad
v
an
ce
m
en
t
o
f
th
e
co
m
p
u
ter
b
ased
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
,
n
o
w
a
d
ay
s
it
is
p
o
s
s
ib
le
to
d
ev
elo
p
au
to
m
atic
class
if
icatio
n
o
f
E
E
G
s
ig
n
als
.
I
n
t
h
is
p
ap
er
,
we
d
ev
elo
p
ed
ef
f
icien
t
n
e
u
r
al
n
etwo
r
k
b
ase
d
E
E
G
class
if
icatio
n
s
y
s
tem
wh
ich
is
im
p
lem
e
n
ted
a
n
d
te
s
ted
u
s
in
g
s
tan
d
a
r
d
E
E
G
d
ataset
o
n
m
atr
ix
lab
o
r
ato
r
y
(
MA
T
L
AB
)
to
o
l.
Giv
en
r
ec
e
n
t
im
p
r
o
v
em
e
n
ts
in
m
o
b
ile
ap
p
s
,
E
E
G
tech
n
o
lo
g
ies
s
ig
n
if
ied
t
h
e
h
is
to
r
ical
b
eg
in
n
in
g
o
f
h
u
m
an
n
e
u
r
o
s
cien
ce
r
esear
ch
t
o
an
aly
z
e
b
r
ain
ac
tiv
ity
[
1
]
,
an
d
th
e
y
cu
r
r
en
tly
s
tan
d
f
ir
m
l
y
as
o
n
e
o
f
th
e
m
o
s
t
ac
ce
s
s
ib
le
an
d
v
er
s
atile
in
s
tr
u
m
en
ts
to
s
tu
d
y
t
h
e
b
r
ain
in
r
ea
l
-
tim
e.
W
e
h
ig
h
lig
h
ted
im
p
o
r
tan
t
h
u
r
d
les
in
c
o
m
p
letely
in
teg
r
atin
g
b
o
th
r
elev
an
t
h
ar
d
war
e
an
d
s
o
f
twar
e
im
p
r
o
v
em
e
n
ts
in
to
n
eu
r
o
d
ev
elo
p
m
en
tal
r
esear
ch
f
o
r
m
o
b
ile
E
E
G
d
ev
ices.
T
h
er
e
ar
e
s
ev
er
al
o
b
s
tacle
s
to
o
v
er
co
m
e
if
m
o
b
ile
E
E
G
d
ev
elo
p
m
en
ts
ar
e
to
b
e
f
u
lly
u
tili
ze
d
in
n
eu
r
o
d
e
v
elo
p
m
e
n
tal
r
esear
ch
.
Har
d
war
e
an
d
s
o
f
twar
e
ad
v
a
n
ce
m
en
ts
ar
e
ce
r
tain
ly
m
o
v
i
n
g
at
a
b
r
ea
k
n
ec
k
p
ac
e.
I
t
h
as
b
ee
n
s
u
g
g
ested
th
at
we
ca
n
u
s
e
E
E
G
to
co
n
s
tr
u
ct
o
u
r
o
wn
d
at
a
b
ase
f
o
r
em
o
tio
n
an
al
y
s
is
.
I
n
r
esear
ch
o
n
em
o
tio
n
esti
m
ate,
1
6
-
3
2
elec
tr
o
d
es
wer
e
em
p
lo
y
ed
d
u
r
in
g
E
E
G
r
ec
o
r
d
in
g
[
2
]
,
wh
ich
is
a
tim
e
an
d
p
r
o
ce
s
s
in
g
s
p
ee
d
c
o
n
s
tr
ain
t.
Du
r
in
g
E
E
G
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.
25
,
No
.
1
,
J
an
u
ar
y
20
22
:
291
-
2
9
7
292
r
ec
o
r
d
in
g
,
f
ewe
r
elec
tr
o
d
es
ca
n
b
e
u
s
ed
.
Du
e
to
its
im
p
r
ess
i
v
e
f
in
d
in
g
s
,
th
e
ex
t
r
em
e
lear
n
i
n
g
m
ac
h
in
e
(
E
L
M)
h
as
r
is
en
to
th
e
f
o
r
ef
r
o
n
t
o
f
cl
ass
if
icatio
n
.
T
h
e
m
o
s
t
ess
en
tial
ch
ar
ac
ter
is
tic
o
f
t
h
is
m
o
d
el
is
th
at
it
s
p
ee
d
s
u
p
th
e
lear
n
in
g
p
r
o
ce
s
s
.
E
L
M
was
n
o
t
em
p
lo
y
e
d
in
an
y
o
f
th
e
i
n
v
esti
g
atio
n
s
th
at
u
s
ed
E
E
G
t
o
class
if
y
em
o
tio
n
r
ec
o
g
n
itio
n
.
I
t
is
ad
v
is
ed
th
at
f
o
r
th
e
class
if
icatio
n
o
f
em
o
tio
n
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
es
u
s
in
g
E
E
G,
o
n
ly
em
p
lo
y
E
L
M
o
r
co
m
b
in
e
it with
o
t
h
er
ap
p
r
o
ac
h
es.
C
r
aik
et
a
l.
[
3
]
p
er
f
o
r
m
s
a
r
ev
iew
o
n
d
if
f
e
r
en
t
E
E
G
class
if
icatio
n
tech
n
iq
u
es.
Fo
r
th
is
p
u
r
p
o
s
e,
d
ee
p
lear
n
in
g
b
ased
tech
n
iq
u
es
s
u
ch
as
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
(
R
NN)
,
s
p
ar
s
e
au
to
-
en
co
d
er
s
(
SAE)
n
eu
r
al
n
etwo
r
k
s
,
m
u
lti
-
lay
e
r
p
er
ce
p
tr
o
n
(
ML
P)
,
a
n
d
h
y
b
r
i
d
tech
n
i
q
u
es.
T
h
e
h
y
b
r
id
tech
n
iq
u
e
g
en
er
ates
b
ette
r
r
esu
lt
th
an
s
tan
d
alo
n
e
tech
n
i
q
u
e.
I
l
y
as
et
a
l.
[
4
]
p
er
f
o
r
m
s
p
er
f
o
r
m
an
ce
co
m
p
ar
is
o
n
s
o
f
d
if
f
e
r
en
t
ty
p
es
o
f
E
E
G
s
ig
n
als.
Fo
r
th
is
p
u
r
p
o
s
e,
th
e
a
u
th
o
r
s
co
n
s
id
er
e
d
s
u
p
p
o
r
t v
ec
t
o
r
m
ac
h
in
e
(
SVM)
,
k
-
n
ea
r
est
n
eig
h
b
o
u
r
(k
-
NN)
,
m
u
ltil
ay
er
p
e
r
ce
p
tr
o
n
ar
tific
ia
l
n
eu
r
al
n
etwo
r
k
(
ML
P
-
ANN
)
an
d
lo
g
is
tic
r
e
g
r
ess
io
n
(
L
R
)
tech
n
iq
u
es
u
s
in
g
b
r
ain
-
co
m
p
u
ter
in
ter
f
ac
e
(
B
C
I
)
co
m
p
etitio
n
I
V
-
Data
s
et
1
.
A
m
o
n
g
th
o
s
e
tec
h
n
iq
u
es,
L
R
an
d
SVM
tech
n
i
q
u
es
s
h
o
ws
b
etter
ac
cu
r
ac
y
th
a
n
o
th
er
tech
n
iq
u
es.
Nag
ab
u
s
h
an
am
et
a
l.
[
5
]
p
r
o
p
o
s
ed
lo
n
g
-
sh
o
r
t
ter
m
m
em
o
r
y
(
L
STM
)
an
d
im
p
r
o
v
ed
n
eu
r
al
n
etwo
r
k
b
ased
E
E
G
s
ig
n
al
class
if
icat
io
n
.
T
h
e
ex
is
tin
g
n
eu
r
al
n
etwo
r
k
alg
o
r
ith
m
is
m
o
d
if
ied
to
g
et
o
p
tim
ized
ac
cu
r
ac
y
.
T
h
e
g
r
a
d
ie
n
t
b
ased
f
u
n
ctio
n
with
r
ad
ial
b
asis
o
p
er
atio
n
s
ar
e
u
s
ed
f
o
r
im
p
lem
e
n
tatio
n
.
T
h
e
p
er
f
o
r
m
an
ce
is
an
aly
zin
g
u
s
in
g
Py
th
o
n
in
k
e
r
as.
Sh
i
et
a
l.
[
6
]
p
r
esen
ted
s
q
u
ir
r
el
s
ea
r
ch
alg
o
r
ith
m
with
SVM
f
o
r
ef
f
icien
t
E
E
G
class
if
icatio
n
.
T
o
an
aly
ze
th
e
p
er
f
o
r
m
an
ce
,
th
e
b
r
ain
-
co
m
p
u
ter
in
ter
f
ac
e
(
B
C
I
)
co
m
p
etitio
n
2
0
0
3
d
ataset
I
I
I
is
u
s
ed
wh
ich
p
r
o
v
es
th
at
t
h
e
p
r
o
p
o
s
ed
tech
n
i
q
u
e
is
b
etter
th
an
ex
is
tin
g
.
Dai
et
a
l.
[
7
]
p
r
esen
ted
E
E
G
class
if
icatio
n
s
y
s
tem
b
ased
o
n
d
ee
p
lea
r
n
in
g
tech
n
iq
u
es.
I
n
th
is
p
ap
er
,
th
e
v
ar
iatio
n
al
au
t
o
en
co
d
er
(
VAE
)
tech
n
iq
u
e
is
co
m
b
in
e
d
with
th
e
g
en
e
r
al
c
o
n
v
o
lu
ti
o
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN)
alg
o
r
ith
m
to
g
et
g
o
o
d
class
if
icatio
n
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
tem
is
ev
alu
ated
u
s
in
g
B
C
I
co
m
p
etitio
n
I
V
d
ataset
2
b
wh
ich
s
h
o
ws
th
e
in
cr
em
en
t
i
n
d
etec
tio
n
ac
cu
r
ac
y
th
an
e
x
is
tin
g
.
Ku
m
ar
et
a
l.
[
8
]
p
r
esen
ted
E
E
G
class
if
icatio
n
s
y
s
tem
b
ased
o
n
o
p
tical
p
r
e
d
i
cto
r
o
n
d
if
f
er
en
t m
em
o
r
y
b
ased
n
etwo
r
k
.
I
n
th
is
p
a
p
er
th
e
y
p
r
esen
ted
a
n
ew
class
if
icatio
n
m
eth
o
d
t
o
p
r
e
d
ict
th
e
E
E
G
s
ig
n
al
wh
ich
is
th
e
co
m
b
in
atio
n
o
f
co
m
m
o
n
s
p
ati
al
p
atter
n
(
C
SP
)
an
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
n
etw
o
r
k
.
T
h
is
tech
n
iq
u
e
is
test
ed
o
n
d
if
f
er
en
t
s
tan
d
ar
d
d
ataset.
T
ah
ir
et
a
l.
[
9
]
p
r
esen
ted
E
E
G
class
if
icatio
n
u
s
in
g
s
war
m
o
p
tim
izatio
n
with
n
eu
r
al
n
etwo
r
k
f
o
r
e
p
ilep
s
y
d
etec
tio
n
.
T
h
e
al
g
o
r
ith
m
is
im
p
lem
en
ted
o
n
MA
T
L
AB
to
o
l
an
d
s
im
u
late
d
with
s
tan
d
ar
d
E
E
G
d
atab
ases
.
T
h
e
s
im
u
latio
n
r
esu
lt
s
h
o
ws
t
h
at
test
in
g
ac
cu
r
ac
y
is
v
er
y
h
i
g
h
f
o
r
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e.
A
clea
r
u
n
d
e
r
s
tan
d
in
g
o
f
v
ar
io
u
s
s
ig
n
al
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
is
d
escr
ib
ed
in
t
h
is
p
ap
er
[
1
0
]
.
T
h
is
s
u
r
v
ey
will
g
iv
e
th
e
r
esear
c
h
e
r
s
a
way
to
s
elec
t
th
e
ap
p
r
o
p
r
iate
s
ig
n
al
p
r
o
ce
s
s
in
g
m
et
h
o
d
ac
co
r
d
in
g
to
th
eir
n
ee
d
.
E
E
G
class
if
icatio
n
u
s
in
g
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
is
s
till
in
it
s
p
r
im
ar
y
s
tag
es.
T
h
er
e
is
a
n
ee
d
to
f
in
d
ar
ch
itectu
r
e
a
n
d
tr
ai
n
in
g
p
ar
a
d
ig
m
s
f
o
r
d
ee
p
ea
r
n
in
g
m
eth
o
d
s
in
o
r
d
er
to
im
p
r
o
v
e
class
if
icatio
n
.
Ho
wev
e
r
,
as
r
esear
ch
co
n
tin
u
es
in
to
th
e
u
s
e
o
f
d
ee
p
lea
r
n
in
g
f
o
r
class
if
icatio
n
o
f
E
E
G
s
ig
n
als,
b
est
p
r
ac
tices
will
b
ec
o
m
e
well
k
n
o
wn
.
I
n
th
is
wo
r
k
[
1
1
]
,
a
n
o
v
el
s
o
lu
tio
n
to
t
h
e
p
r
o
b
lem
o
f
E
E
G
s
ig
n
al
f
ea
tu
r
e
ex
tr
a
ctio
n
an
d
ca
teg
o
r
izatio
n
is
p
r
esen
ted
.
T
h
e
elec
tr
o
d
es
a
r
e
f
i
r
s
t
s
cr
ee
n
e
d
d
ep
e
n
d
in
g
o
n
th
eir
r
elev
a
n
c
e,
th
en
th
e
wav
elet
tr
an
s
f
o
r
m
is
p
er
f
o
r
m
e
d
to
ex
tr
ac
t
E
E
G
f
ea
tu
r
es,
an
d
f
in
ally
an
Alex
Net
class
if
ier
is
ap
p
lie
d
.
E
E
G
s
ig
n
als
ca
n
b
e
p
r
o
p
er
ly
ex
t
r
ac
ted
an
d
clas
s
if
ied
u
s
in
g
th
e
m
eth
o
d
d
escr
i
b
ed
ab
o
v
e.
Fu
r
th
e
r
m
o
r
e
,
th
e
r
esu
lts
s
h
o
w
th
at
th
e
s
u
g
g
ested
m
eth
o
d
u
s
es
litt
le
r
eso
u
r
ce
s
a
n
d
h
as
a
h
ig
h
d
eg
r
ee
o
f
ac
cu
r
ac
y
.
As
a
r
es
u
lt,
th
is
s
tr
ateg
y
is
ex
tr
em
ely
u
s
ef
u
l
f
o
r
r
eso
lv
in
g
d
if
f
icu
lties
o
f
th
is
n
atu
r
e.
T
h
e
SNR
h
as
to
b
e
im
p
r
o
v
e
d
b
ec
au
s
e
ar
tef
ac
ts
d
is
to
r
t
th
e
E
E
G
s
ig
n
als.
T
h
is
aid
s
in
en
h
an
cin
g
f
ea
tu
r
e
e
x
tr
ac
tio
n
an
d
d
ata
ca
teg
o
r
izatio
n
ac
cu
r
ac
y
p
r
esen
ted
in
p
ap
er
[
1
2
]
.
As
a
r
esu
lt,
r
ec
en
t
s
tr
ateg
ies
ar
e
ex
am
in
e
d
,
t
o
g
eth
er
with
t
h
eir
b
e
n
ef
its
an
d
d
r
awb
ac
k
s
.
I
t
h
as
b
ee
n
d
is
co
v
er
e
d
th
at
th
e
p
r
o
c
ed
u
r
es
o
u
tlin
ed
i
n
th
e
r
ev
iew
p
r
o
d
u
ce
b
etter
r
esu
lts
th
an
tr
ad
itio
n
al
m
eth
o
d
s
.
T
h
e
ce
r
e
b
r
al
c
o
r
tex
g
en
e
r
ates E
E
G
s
ig
n
als,
wh
ich
ar
e
alwa
y
s
tain
ted
b
y
ce
r
tain
d
is
tu
r
b
an
c
es
[
1
3
]
.
Desp
ite
th
e
f
ac
t
th
at
a
v
ar
iety
o
f
s
tr
ateg
ies
f
o
r
r
em
o
v
in
g
u
n
wan
ted
a
r
tef
ac
ts
h
av
e
b
ee
n
cr
ea
ted
,
a
n
ar
tef
ac
t
r
em
o
v
al
m
eth
o
d
t
h
at
co
m
b
i
n
es
h
ig
h
ac
cu
r
ac
y
with
alg
o
r
ith
m
ic
ef
f
ici
en
cy
h
as
y
et
to
b
e
estab
lis
h
ed
.
B
ased
o
n
in
s
ig
h
ts
d
r
awn
f
r
o
m
th
e
liter
atu
r
e,
t
h
is
r
ep
o
r
t
d
escr
ib
e
d
th
e
k
e
y
s
tr
ateg
ies.
E
ac
h
m
eth
o
d
'
s
p
r
o
s
an
d
d
is
ad
v
an
tag
es
ar
e
also
d
is
cu
s
s
ed
.
T
h
er
e
is
n
o
o
n
e
-
s
ize
-
f
its
-
all
s
o
lu
tio
n
f
o
r
r
e
m
o
v
in
g
all
f
o
r
m
s
o
f
a
r
tef
ac
ts
.
As
a
r
esu
lt,
o
n
e
o
f
th
e
lo
n
g
-
ter
m
g
o
als
o
f
ef
f
ec
tiv
e
ar
tef
ac
t
atten
u
atio
n
is
to
cr
e
ate
an
ap
p
licatio
n
-
s
p
ec
if
ic
alg
o
r
ith
m
th
at
is
m
o
r
e
ef
f
icien
t
in
ter
m
s
o
f
tim
e
an
d
ac
cu
r
ac
y
.
Als
o
,
b
ased
o
n
th
e
cu
r
r
en
t
ar
tef
ac
t
r
em
o
v
al
tr
e
n
d
,
f
u
tu
r
e
d
ir
ec
tio
n
s
will
in
teg
r
ate
m
ac
h
in
e
lear
n
i
n
g
an
d
class
ical
m
eth
o
d
o
l
o
g
i
es
f
o
r
s
u
cc
ess
f
u
l
au
to
m
atic
ar
tef
ac
t
r
em
o
v
al.
A
p
r
o
ce
s
s
f
o
r
ex
p
l
o
itin
g
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
class
if
icatio
n
tech
n
iq
u
es
to
E
E
G
s
ig
n
als
is
p
r
esen
ted
in
th
is
p
ap
er
[
1
4
]
,
[
1
5
]
.
Sp
ec
if
ically
,
a
tim
e
-
f
r
eq
u
e
n
cy
a
n
aly
s
is
u
s
in
g
b
o
th
t
h
e
f
o
u
r
ier
an
d
wav
elet
tr
an
s
f
o
r
m
s
is
d
o
n
e
o
n
1
0
9
s
am
p
les
f
r
o
m
th
e
Alzh
eim
er
’
s
d
is
ea
s
e
(
AD)
,
m
il
d
co
g
n
itiv
e
im
p
air
m
e
n
t
(
MC
I
)
an
d
h
ier
ar
c
h
ical
class
if
icatio
n
(
HC
)
class
e
s
.
T
h
e
f
o
llo
win
g
p
h
ases
ar
e
in
clu
d
ed
in
t
h
e
class
if
icatio
n
p
r
o
ce
d
u
r
e:
i)
E
E
G
s
ig
n
al
p
r
e
p
r
o
c
e
s
s
i
n
g
;
(
i
i
)
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
u
s
i
n
g
t
h
e
d
i
s
c
r
et
e
f
o
u
r
ie
r
a
n
d
w
a
v
e
le
t
t
r
a
n
s
f
o
r
m
s
;
a
n
d
(
i
i
i
)
cl
as
s
i
f
i
c
a
ti
o
n
u
s
i
n
g
t
r
e
e
-
b
as
e
d
s
u
p
e
r
v
is
e
d
a
lg
o
r
i
t
h
m
s
.
W
e
d
is
c
o
v
e
r
t
h
a
t
W
a
v
e
l
e
ts
a
n
a
l
y
s
i
s
o
u
t
p
e
r
f
o
r
m
s
f
o
u
r
i
e
r
a
n
a
l
y
s
is
w
h
e
n
c
o
m
p
a
r
i
n
g
c
l
a
s
s
i
f
i
c
a
ti
o
n
p
e
r
f
o
r
m
a
n
c
e
w
i
t
h
b
o
t
h
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
p
p
r
o
a
c
h
e
s
.
I
n
t
h
i
s
p
a
p
e
r
w
e
p
r
o
p
o
s
e
d
a
n
e
f
f
i
c
i
e
n
t
E
E
G
c
l
as
s
i
f
i
c
at
i
o
n
s
y
s
t
e
m
u
s
i
n
g
SV
M
a
n
d
a
d
a
p
t
i
v
e
le
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
c
o
m
b
i
n
e
d
l
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:
2502
-
4
7
5
2
E
fficien
t e
lectro
en
ce
p
h
elo
g
r
a
m
cla
s
s
ifica
tio
n
s
ys
tem
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
… (
V
ir
u
p
a
xi
B
a
la
ch
a
n
d
r
a
D
a
la
l
)
293
2.
P
RO
P
O
SE
D
AL
G
O
R
I
T
H
M
T
h
e
p
r
o
p
o
s
ed
E
E
G
class
if
icatio
n
s
y
s
tem
is
s
h
o
wn
in
Fig
u
r
e
1
wh
ich
co
n
s
is
ts
o
f
tem
p
o
r
a
l
f
ilter
in
g
,
s
p
atial
f
ilter
in
g
,
SVM
class
if
i
er
,
co
s
t
-
s
en
s
itiv
e
SVM
(
C
SV
M)
v
alid
atio
n
a
n
d
a
d
ap
tiv
e
le
ar
n
in
g
r
esp
ec
tiv
ely
.
T
h
e
tr
ain
in
g
an
d
test
d
ataset
a
r
e
f
ilter
ed
u
s
in
g
tem
p
o
r
al
f
ilte
r
in
g
wh
ich
ar
e
t
h
en
e
n
h
an
ce
d
u
s
in
g
s
p
atial
f
ilter
an
d
s
en
d
to
SVM
C
las
s
if
ier
.
T
h
e
class
if
ied
s
ig
n
als
ar
e
th
en
v
alid
ate
u
s
in
g
C
SVM
v
alid
atio
n
with
th
e
h
el
p
o
f
ad
ap
tiv
e
lear
n
in
g
b
lo
ck
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
E
E
G
s
y
s
te
m
class
if
icatio
n
2
.
1
.
Da
t
a
s
et
T
h
e
B
C
I
co
m
p
etitio
n
I
V
d
at
aset
[
1
6
]
is
u
s
ed
as
s
tan
d
ar
d
d
atab
ase
f
o
r
tr
ain
in
g
an
d
te
s
t.
Fo
r
o
u
r
im
p
lem
en
tatio
n
,
d
ataset
2
A
is
co
n
s
id
er
ed
wh
ich
co
n
s
is
ts
o
f
9
s
u
b
jects
ca
p
tu
r
ed
u
s
in
g
2
2
E
E
G
ch
an
n
els
an
d
3
m
o
n
o
p
o
lar
elec
tr
o
o
c
u
lo
g
r
a
m
(
E
OG)
ch
an
n
el
as
s
h
o
wn
in
Fi
g
u
r
e
2
[
1
7
]
.
T
h
e
f
o
u
r
m
o
to
r
i
m
ag
er
y
task
s
in
th
e
cu
e
-
b
ased
B
C
I
p
ar
ad
ig
m
wer
e
im
ag
in
atio
n
o
f
m
o
v
em
en
t
o
f
th
e
lef
t
h
an
d
(
class
1
)
,
r
ig
h
t
h
an
d
(
class
2
)
,
b
o
th
f
ee
t
(
class
3
)
,
an
d
to
n
g
u
e
(
class
4
)
.
On
two
s
ep
a
r
ate
d
a
y
s
,
two
s
ess
io
n
s
wer
e
h
eld
.
E
ac
h
s
u
b
ject
w
as
r
ec
o
r
d
ed
.
E
ac
h
s
ess
io
n
co
n
s
is
ts
o
f
s
ix
r
u
n
s
s
ep
ar
ated
b
y
a
m
in
u
te.
B
r
ea
k
s
s
h
o
u
ld
b
e
b
r
ief
.
On
e
r
u
n
co
n
s
is
ts
o
f
4
8
tr
ials
(
1
2
f
o
r
ea
ch
o
f
t
h
e
f
o
u
r
p
o
s
s
ib
le
class
es),
y
ield
in
g
a
to
tal
o
f
2
8
8
tr
ials
p
er
s
ess
io
n
.
Fig
u
r
e
2
.
C
lass
if
icatio
n
elec
tr
o
d
e
p
lac
in
g
f
o
r
E
E
G
s
ig
n
al
ca
p
tu
r
e
2
.
2
.
T
em
po
r
a
l
f
ilte
r
T
h
e
ca
p
tu
r
ed
elec
tr
o
n
ic
s
ig
n
a
ls
th
r
o
u
g
h
elec
tr
o
d
e
ar
e
an
al
o
g
u
es
in
n
atu
r
e
an
d
co
n
s
is
t
o
f
d
if
f
er
en
t
f
r
eq
u
e
n
cy
b
a
n
d
s
.
Am
o
n
g
t
h
o
s
e
f
r
eq
u
e
n
cy
b
an
d
s
,
o
n
ly
th
e
8
-
1
2
Hz
a
n
d
1
4
-
3
0
Hz
f
r
eq
u
e
n
cy
b
an
d
s
d
ata
ar
e
m
ain
ly
u
s
ed
f
o
r
E
E
G
p
r
o
ce
s
s
in
g
p
u
r
p
o
s
e
d
u
e
to
its
s
tab
le
r
esp
o
n
s
e.
T
h
o
s
e
b
an
d
s
ar
e
g
en
er
ally
k
n
o
wn
as
µ
-
b
an
d
an
d
β
-
b
an
d
r
esp
ec
tiv
ely
[
1
8
]
wh
ic
h
ar
e
s
ep
ar
ated
u
s
in
g
tem
p
o
r
al
f
ilter
f
r
o
m
th
e
s
tan
d
ar
d
E
E
G
s
ig
n
al.
T
h
e
s
tan
d
ar
d
b
an
d
-
p
ass
f
ilter
is
u
s
ed
as tem
p
o
r
al
f
ilter
with
s
u
itab
le
co
ef
f
icien
ts
[
1
9
]
.
2
.
3
.
Sp
a
t
i
a
l
f
ilte
r
An
y
r
aw
E
E
G
s
ig
n
al
co
n
s
is
ts
o
f
v
e
r
y
lo
w
s
p
atial
r
eso
lu
tio
n
s
wh
ich
m
a
k
e
it
d
if
f
icu
lt
to
cla
s
s
if
y
E
E
G
s
ig
n
al
ef
f
icien
tly
.
I
n
m
an
y
ca
s
es,
it
cr
ea
te
s
d
if
f
icu
lties
to
a
n
aly
ze
th
e
r
h
y
th
m
p
atter
n
s
g
e
n
er
ated
b
y
th
e
b
r
ain
s
ig
n
als
wh
ich
ar
e
g
en
er
al
ly
k
n
o
wn
as
ev
e
n
t
-
r
elate
d
d
esy
n
ch
r
o
n
izatio
n
(
E
R
D)
o
r
e
v
en
t
-
r
elate
d
s
y
n
ch
r
o
n
izatio
n
(
E
R
S)
[
2
0
]
.
T
h
e
co
m
m
o
n
s
p
atial
p
atter
n
(
C
SP
)
alg
o
r
ith
m
is
n
o
r
m
ally
u
s
ed
to
d
etec
t
s
u
ch
s
ce
n
ar
io
s
.
T
o
g
et
o
p
tim
ize
d
r
esu
lt,
th
e
ex
is
tin
g
alg
o
r
ith
m
i
s
m
o
d
if
ied
.
As
a
r
esu
lt,
th
e
o
v
er
a
ll
tim
e
d
o
m
ain
s
ig
n
al
is
co
n
ca
ten
ate
d
in
t
o
s
m
aller
tim
e
b
ased
s
eg
m
en
ts
a
n
d
d
ec
o
m
p
o
s
es
th
e
o
v
er
all
s
ig
n
al
in
to
a
f
in
ite
s
et
r
ep
r
esen
ted
as
(
1
)
,
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.
25
,
No
.
1
,
J
an
u
ar
y
20
22
:
291
-
2
9
7
294
∈
(
)
×
(
)
(
1
)
w
h
er
e,
c(
t)
is
th
e
s
ig
n
al
f
r
o
m
t
h
e
r
esp
ec
tiv
e
ch
a
n
n
el
at
a
f
i
n
ite
tim
e
s
p
an
.
Fo
r
s
in
g
le
tr
ial
E
E
G
s
ig
n
al,
th
i
s
eq
u
atio
n
ca
n
b
e
r
ewr
itten
as
(
2
)
,
∈
(
)
(
2
)
T
h
e
r
elatio
n
s
b
etwe
en
s
ig
n
al
s
p
ac
es in
d
if
f
er
e
n
t tr
ials
ar
e
,
=
.
(
3
)
w
h
er
e,
E
is
th
e
E
E
G
m
ea
s
u
r
e
m
en
t d
ata
o
f
a
s
in
g
le
tr
ail.
T
o
g
et
ef
f
ec
tiv
e
m
ea
s
u
r
em
e
n
t
o
f
d
if
f
e
r
en
t
m
e
n
tal
s
tate
f
ea
tu
r
es,
it is
es
s
en
tial to
m
ak
e
th
e
v
ar
ian
ce
is
v
er
y
s
m
all.
Fo
r
s
u
ch
ca
s
es,
th
e
f
ea
tu
r
e
v
ec
t
o
r
s
ca
n
b
e
wr
itten
as
(
4
)
,
=
(
(
)
∑
(
)
2
=
1
)
(
4
)
w
h
er
e,
n
is
o
n
e
r
o
w
o
f
th
e
m
at
r
ix
s
ig
n
al.
2
.
4
.
SVM
cla
s
s
if
ier
a
nd
v
a
lid
a
t
io
n
T
h
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
u
s
es
lear
n
in
g
m
et
h
o
d
b
ased
o
n
s
tatis
tical
p
r
o
p
e
r
ties
o
f
th
e
in
p
u
t
s
ig
n
al.
T
h
e
s
ep
ar
ate
h
y
p
er
-
p
l
an
es
ar
e
m
ath
em
atica
lly
d
er
iv
es
f
r
o
m
th
o
s
e
p
r
o
p
er
ties
with
m
ax
im
u
m
m
ar
g
i
n
.
T
h
e
eq
u
atio
n
s
u
s
ed
to
g
e
n
er
at
e
o
p
tim
u
m
h
y
p
e
r
-
p
lan
e
ar
e
,
.
+
=
{
≥
+
1
;
=
+
1
<
+
1
;
=
−
1
(
5
)
w
h
er
e,
x
i is th
e
ith
in
p
u
t v
ec
t
o
r
.
y
i is th
e
ass
ig
n
ed
lev
el
o
f
t
h
e
i
th
in
p
u
t.
ɷ
is
th
e
weig
h
t v
ec
to
r
.
T
h
e
o
p
tim
al
m
a
r
g
in
s
ep
ar
atin
g
d
if
f
er
e
n
t h
y
p
er
-
p
lan
es c
an
b
e
wr
itten
as [
2
1
]
.
+
≤
±
1
(
6
)
T
h
e
s
u
p
p
o
r
t v
ec
to
r
s
ar
e
th
en
c
alcu
lated
th
r
o
u
g
h
th
e
tr
an
s
f
o
r
m
s
p
ac
e
,
(
,
)
=
(
)
(
)
(
7
)
Fo
r
th
e
ab
o
v
e
eq
u
atio
n
,
th
e
f
e
atu
r
e
class
ca
lcu
latio
n
eq
u
atio
n
ca
n
b
e
wr
itten
as
(
8
)
,
(
)
=
(
∑
(
)
(
)
+
)
(
8
)
w
h
er
e,
α
is
d
y
n
am
ic
weig
h
t
f
a
cto
r
.
2
.
5
.
Ada
ptiv
e
le
a
rning
T
h
e
f
ea
tu
r
es
g
en
er
ated
b
y
t
h
e
class
if
ier
ar
e
th
en
u
s
ed
t
o
p
r
ed
ict
th
e
class
es
o
f
f
u
tu
r
e
s
am
p
les
d
ep
en
d
i
n
g
u
p
o
n
th
e
tr
ain
in
g
d
ataset
an
d
test
d
ataset.
T
h
e
e
f
f
icien
t
class
if
icatio
n
is
g
en
er
at
ed
b
y
th
is
m
et
h
o
d
.
I
n
o
u
r
ca
s
e
we
co
n
s
id
er
th
e
p
r
o
b
a
b
ilit
y
d
is
tr
ib
u
tio
n
f
u
n
cti
o
n
to
p
r
e
d
ict
th
e
f
u
tu
r
e
s
am
p
les.
T
o
m
ak
e
t
h
e
class
if
icatio
n
ef
f
ec
tiv
e
th
e
f
o
ll
o
win
g
eq
u
ati
o
n
s
ar
e
u
s
ed
.
T
h
e
eq
u
atio
n
o
f
tr
ain
in
g
d
ataset
in
ad
ap
tiv
e
le
ar
n
in
g
c
o
n
d
iti
o
n
ca
n
b
e
d
ef
i
n
ed
as
(
9
)
,
=
∏
{
,
}
=
1
(
9
)
w
h
er
e,
N
is
th
e
to
tal
o
b
s
er
v
atio
n
n
u
m
b
er
;
y
i
is
th
e
lev
el
ass
ig
n
ed
f
o
r
r
esp
ec
tiv
e
x
i in
p
u
t.
Sin
ce
f
o
r
th
e
class
if
icatio
n
o
n
l
y
two
class
es a
r
e
co
n
s
id
er
ed
,
s
o
we
ca
n
wr
ite
,
y
∈
{
c
1
;
if
x
i
b
e
l
on
gs
to
c
l
a
s
s
ω
1
c
2
;
if
x
i
b
e
l
on
gs
to
c
l
a
s
s
ω
2
(
1
0
)
Fo
r
SVM,
we
h
av
e
co
n
s
id
er
e
d
th
e
class
v
alu
e
is
±
1
in
s
ec
tio
n
3
.
So
,
th
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
o
f
th
e
in
p
u
t sig
n
al
ca
n
b
e
wr
itten
as
(
1
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:
2502
-
4
7
5
2
E
fficien
t e
lectro
en
ce
p
h
elo
g
r
a
m
cla
s
s
ifica
tio
n
s
ys
tem
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
… (
V
ir
u
p
a
xi
B
a
la
ch
a
n
d
r
a
D
a
la
l
)
295
p
(
x
i
)
=
p
(
ω
1
)
.
p
(
x
i
|
ω
1
)
+
p
(
ω
2
)
.
p
(
x
i
|
ω
2
)
(
1
1
)
W
h
er
e,
p
(
ɷ
1
)
a
n
d
p
(
ɷ
2
)
a
r
e
th
e
p
r
o
b
a
b
ilit
y
o
f
t
h
e
r
esp
ec
tiv
e
class
;
p
(x
i
|
ɷ
1
)
an
d
p
(
x
i
|
ɷ
2
)
ar
e
th
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
.
T
h
e
p
r
e
d
icted
f
u
tu
r
e
s
am
p
le
is
th
en
(
1
2
)
,
X
T
r
ai
n
f
u
t
u
r
e
=
∏
{
y
i
|
x
i
}
M
i
=
1
(
1
2
)
w
he
r
e,
M
is
o
b
s
er
v
atio
n
in
test
in
g
;
y
i
is
th
e
p
r
ed
icted
s
am
p
le
.
3.
SI
M
UL
A
T
I
O
N
R
E
S
UL
T
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
s
im
u
lated
o
n
MA
T
L
AB
2
0
1
7
a
s
o
f
twar
e
u
s
in
g
s
tan
d
ar
d
p
r
o
g
r
am
m
in
g
m
eth
o
d
.
Fo
r
th
is
s
im
u
latio
n
,
s
tan
d
ar
d
B
C
I
co
m
p
etitio
n
I
V
d
ataset
ar
e
u
s
ed
.
T
h
e
f
ea
tu
r
e
s
g
en
er
ated
b
y
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
s
h
o
w
n
in
th
e
Fig
u
r
e
3
an
d
Fig
u
r
e
4
f
o
r
d
if
f
er
e
n
t
f
r
e
q
u
en
c
y
b
an
d
s
wh
ich
is
class
if
ied
in
to
two
d
if
f
e
r
en
t d
ata
f
ea
t
u
r
e
s
ets
n
am
ely
f
ir
s
t
a
n
d
s
ec
o
n
d
b
est
f
ea
tu
r
es.
I
n
th
is
ca
s
e
th
e
f
ir
s
t
b
est
f
ea
tu
r
es
a
r
e
g
en
er
ated
b
y
co
n
s
id
er
i
n
g
th
e
ac
cu
r
ate
f
ea
tu
r
e
s
ets
o
f
th
e
c
o
r
r
esp
o
n
d
i
n
g
f
r
eq
u
en
cies
an
d
f
o
r
th
e
s
ec
o
n
d
b
est
f
ea
tu
r
e
s
ets
wh
ich
ar
e
v
er
y
n
ea
r
er
to
th
e
ac
cu
r
ate
f
ea
tu
r
es
ar
e
co
n
s
id
er
ed
.
T
h
e
in
ter
s
ec
tio
n
s
o
f
th
e
f
ir
s
t
an
d
s
ec
o
n
d
f
ea
tu
r
es
ar
e
m
ain
l
y
u
s
ed
f
o
r
a
class
if
icatio
n
wh
i
ch
h
elp
s
to
in
cr
ea
s
e
t
h
e
d
et
ec
tio
n
r
ate.
Fo
r
th
e
s
tan
d
ar
d
d
ataset
[
1
6
]
we
o
b
tain
ed
8
5
.
7
1
4
% a
cc
u
r
ac
y
in
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
.
Fig
u
r
e
3
.
Featu
r
e
s
et
at
8
-
1
2
Hz
b
an
d
Fig
u
r
e
4
.
Featu
r
e
s
et
at
1
5
-
3
0
Hz
b
an
d
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.
25
,
No
.
1
,
J
an
u
ar
y
20
22
:
291
-
2
9
7
296
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
B
C
I
co
m
p
etitio
n
I
V
d
ataset
i
s
u
s
ed
as
s
tan
d
ar
d
d
atab
ase
f
o
r
tr
ain
in
g
an
d
test
.
Fo
r
o
u
r
im
p
lem
en
tatio
n
,
d
ataset
2
A
is
co
n
s
id
er
ed
wh
ich
co
n
s
is
ts
o
f
9
s
u
b
jects
ca
p
tu
r
ed
u
s
in
g
2
2
E
E
G
ch
an
n
els
an
d
3
m
o
n
o
p
o
l
a
r
E
O
G
c
h
a
n
n
e
l
.
T
h
e
t
r
u
e
d
e
t
e
c
ti
o
n
r
a
t
e
o
f
t
h
e
p
r
o
p
o
s
e
d
a
l
g
o
r
it
h
m
i
s
c
o
m
p
a
r
e
d
wi
th
t
h
e
d
e
t
e
ct
i
o
n
r
a
t
e
o
f
v
a
r
i
o
u
s
e
x
i
s
t
i
n
g
a
l
g
o
r
it
h
m
s
[
2
2
]
-
[
2
6
]
i
n
T
a
b
l
e
1
.
I
t
c
a
n
b
e
s
e
e
n
t
h
e
e
x
is
t
i
n
g
r
e
f
r
e
n
c
es
m
e
n
t
i
o
n
e
d
[
2
2
]
-
[
26]
u
s
es
s
im
p
le
SVM
to
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
an
d
Fu
zz
y
L
o
g
i
cs
with
o
u
t
m
u
ch
f
o
c
u
s
in
g
o
n
Ad
ap
tiv
e
L
ea
r
n
in
g
.
B
u
t,
in
o
u
r
m
eth
o
d
th
at
d
u
e
to
th
e
u
s
e
o
f
SVM
class
if
icatio
n
an
d
Ad
a
p
tiv
e
L
ea
r
n
i
n
g
tech
n
iq
u
es,
th
e
d
etec
tio
n
ac
cu
r
ac
y
is
h
ig
h
e
r
in
th
e
ca
s
e
o
f
p
r
o
p
o
s
ed
alg
o
r
ith
m
th
a
n
e
x
is
tin
g
tech
n
iq
u
es
d
u
e
t
o
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
b
ased
lear
n
in
g
tech
n
iq
u
e
wh
er
e
it p
r
ed
icts
f
u
tu
r
e
s
am
p
les.
T
ab
le
1
.
T
r
u
e
d
etec
tio
n
r
ate
co
m
p
ar
is
o
n
A
u
t
h
o
r
s
Te
c
h
n
i
q
u
e
s
D
e
t
e
c
t
i
o
n
R
a
t
e
G
a
r
r
e
t
t
e
t
a
l
.
[
2
2
]
B
a
si
c
S
V
M
7
2
%
K
e
r
k
e
n
i
e
t
a
l
.
[
2
3
]
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
7
6
%
A
l
j
a
z
a
e
r
y
e
t
a
l
.
[
2
4
]
Q
u
a
n
t
u
m N
e
u
r
a
l
N
e
t
w
o
r
k
8
1
.
3
3
%
N
a
n
d
i
s
h
e
t
a
l
.
[
2
5
]
F
u
z
z
y
C
l
a
ssi
f
i
e
r
8
0
%
B
h
a
t
t
a
n
d
G
o
p
a
l
[
2
6
]
F
u
z
z
y
C
l
a
ssi
f
i
c
a
t
i
o
n
7
6
.
2
%
P
r
o
p
o
se
d
S
V
M
w
i
t
h
A
d
a
p
t
i
v
e
Le
a
r
n
i
n
g
8
5
.
7
1
4
%
5.
CO
NCLU
SI
O
N
I
n
th
is
p
a
p
er
a
n
ef
f
icien
t
E
E
G
class
if
icatio
n
alg
o
r
ith
m
is
p
r
o
p
o
s
ed
wh
ich
u
s
es
SVM
class
if
ier
with
ad
ap
tiv
e
lear
n
i
n
g
tech
n
iq
u
es.
T
h
e
SVM
tech
n
iq
u
e
is
u
s
ed
to
g
en
er
ate
th
e
f
ea
tu
r
e
v
ec
to
r
s
f
r
o
m
th
e
E
E
G
d
ata
.
T
h
e
ad
ap
tiv
e
lear
n
i
n
g
tech
n
iq
u
e
will
o
p
tim
ize
th
e
f
ea
tu
r
es
ac
co
r
d
in
g
to
class
es
b
y
u
s
in
g
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
.
T
h
e
test
an
d
d
atab
ase
d
ata
ar
e
th
en
co
m
p
ar
ed
to
g
et
th
e
d
etec
t
ed
v
ec
to
r
s
.
T
o
g
et
ac
cu
r
ate
d
etec
tio
n
s
,
th
e
f
ir
s
t
b
est
f
ea
tu
r
es
an
d
s
ec
o
n
d
b
est
f
ea
tu
r
es
ar
e
co
n
s
id
er
ed
.
T
o
ac
h
i
ev
e
m
o
r
e
ac
c
u
r
ac
y
th
e
ad
ap
tiv
e
lear
n
in
g
tech
n
iq
u
es
ar
e
u
s
ed
wh
ich
c
h
an
g
es
t
h
e
weig
h
ts
u
s
ed
i
n
f
ea
t
u
r
e
e
x
tr
ac
tio
n
s
.
W
e
o
b
tain
ed
8
5
.
7
1
4
%
ac
cu
r
ac
y
with
o
u
r
p
r
o
p
o
s
ed
tech
n
iq
u
e
d
u
e
to
o
p
tim
ized
class
if
icatio
n
o
f
f
ea
tu
r
es
in
to
class
es.
I
n
f
u
tu
r
e
th
e
al
g
o
r
ith
m
ca
n
b
e
f
u
r
th
er
im
p
r
o
v
ed
i
n
ter
m
s
o
f
clas
s
if
icatio
n
ac
cu
r
ac
y
with
tim
e
t
o
class
if
y
all
ty
p
es
o
f
s
u
b
d
ata
s
ets av
ailab
le
in
t
h
e
d
ataset.
ACK
NO
WL
E
DG
E
M
E
NT
S
Au
th
o
r
s
th
an
k
s
to
Dep
a
r
tm
en
t
o
f
E
lectr
o
n
ics
an
d
C
o
m
m
u
n
icatio
n
E
n
g
g
in
ee
r
in
g
,
SDMCET
,
Dh
ar
wad
an
d
De
p
ar
tm
en
t
o
f
E
l
ec
tr
o
n
ics
an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
in
g
,
J
ain
C
o
lleg
e
o
f
E
n
g
i
n
ee
r
in
g
an
d
R
esear
ch
,
B
elag
av
i,
Kar
n
atak
a,
I
n
d
ia,
f
o
r
p
r
o
v
i
d
in
g
an
in
f
r
astru
ctu
r
e
to
ca
r
r
y
r
esear
ch
o
n
ab
o
v
e
m
en
tio
n
ed
to
p
ic.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
La
u
-
Z
h
u
,
M
.
P
.
H
.
La
u
,
a
n
d
G
.
M
c
L
o
u
g
h
l
i
n
,
“
M
o
b
i
l
e
E
EG
i
n
r
e
se
a
r
c
h
o
n
n
e
u
r
o
d
e
v
e
l
o
p
me
n
t
a
l
d
i
s
o
r
d
e
r
s:
O
p
p
o
r
t
u
n
i
t
i
e
s
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
D
e
v
e
l
o
p
m
e
n
t
a
l
C
o
g
n
i
t
i
v
e
N
e
u
r
o
s
c
i
e
n
c
e
,
v
o
l
.
3
6
,
p
p
.
1
-
1
4
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
c
n
.
2
0
1
9
.
1
0
0
6
3
5
.
[
2
]
N
.
Y
o
l
d
o
r
o
m
a
n
d
A
.
V
a
r
o
l
,
“
A
R
e
s
e
a
r
c
h
o
n
Est
i
ma
t
i
o
n
o
f
E
mo
t
i
o
n
U
si
n
g
EEG
S
i
g
n
a
l
s
a
n
d
B
r
a
i
n
C
o
m
p
u
t
e
r
I
n
t
e
r
f
a
c
e
s
,
”
i
n
Pro
c
.
2
nd
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
p
u
t
e
r sc
i
e
n
c
e
a
n
d
e
n
g
g
I
EE
E,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
U
B
M
K
.
2
0
1
7
.
8
0
9
3
5
2
3
.
[
3
]
A
.
C
r
a
i
k
,
Y
.
He
,
a
n
d
J
.
L
.
C
o
n
t
r
e
r
a
s
-
V
i
d
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
e
l
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
m(
E
EG
)
c
l
a
s
si
f
i
c
a
t
i
o
n
t
a
s
k
s
:
a
r
e
v
i
e
w
,
”
I
O
P
J
o
u
rn
a
l
o
f
N
e
u
r
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
6
,
n
o
.
3
,
p
p
.
1
-
2
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
1
-
2
5
5
2
/
a
b
0
a
b
5
.
[
4
]
M
.
Z.
I
l
y
a
s
,
P
.
S
a
a
d
,
M
.
I
.
A
h
m
a
d
,
a
n
d
A
.
R
.
I
.
G
h
a
n
i
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
E
EG
S
i
g
n
a
l
s
f
o
r
B
r
a
i
n
-
C
o
m
p
u
t
e
r
I
n
t
e
r
f
a
c
e
A
p
p
l
i
c
a
t
i
o
n
s
:
P
e
r
f
o
r
ma
n
c
e
C
o
m
p
a
r
i
so
n
,
”
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ro
b
o
t
i
c
s,
Au
t
o
m
a
t
i
o
n
a
n
d
S
c
i
e
n
c
e
s
(
I
C
O
RA
S
)
,
2
0
1
6
,
p
p
.
1
-
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
R
A
S
.
2
0
1
6
.
7
8
7
2
6
1
0
.
[
5
]
P
.
N
a
g
a
b
u
sh
a
n
a
m,
S
.
T
.
G
e
o
r
g
e
,
a
n
d
S
.
R
a
d
h
a
,
“
EEG
si
g
n
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
LST
M
a
n
d
i
m
p
r
o
v
e
d
n
e
u
r
a
l
n
e
t
w
o
r
k
a
l
g
o
r
i
t
h
ms
,
”
M
e
t
h
o
d
o
l
o
g
i
e
s
a
n
f
A
p
p
l
i
c
a
t
i
o
n
,
v
o
l
.
2
4
,
p
p
.
9
9
8
1
-
1
0
0
0
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
0
1
9
-
0
4
5
1
5
-
0
.
[
6
]
M
.
S
h
i
,
C
.
W
a
n
g
,
X
.
-
Z
.
Li
,
M
.
-
Q
.
Li
,
L
.
W
a
n
g
,
a
n
d
N
.
-
G
.
X
i
e
,
“
EEG
si
g
n
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
se
d
o
n
S
V
M
w
i
t
h
i
mp
r
o
v
e
d
s
q
u
i
r
r
e
l
sea
r
c
h
a
l
g
o
r
i
t
h
m
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Bi
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
/
Bi
o
m
e
d
i
z
i
n
i
sc
h
e
T
e
c
h
n
i
k
,
v
o
l
.
6
6
,
no
.
2
,
p
p
.
1
3
7
-
1
5
2
,
S
e
p
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
5
1
5
/
b
mt
-
2
0
2
0
-
0
0
3
8
.
[
7
]
M
.
D
a
i
,
D
.
Zh
e
n
g
,
R
.
N
a
,
S
.
W
a
n
g
,
a
n
d
S
.
Zh
a
n
g
,
“
EEG
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
M
o
t
o
r
I
mag
e
r
y
U
s
i
n
g
a
N
o
v
e
l
D
e
e
p
Le
a
r
n
i
n
g
F
r
a
mew
o
r
k
,
”
S
e
n
so
rs
,
v
o
l
.
1
9
,
p
p
.
1
-
1
6
,
J
a
n
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
0
3
0
5
5
1
.
[
8
]
S
.
K
u
mar,
A
.
S
h
a
r
ma
,
a
n
d
T
.
T
su
n
o
d
a
,
“
B
r
a
i
n
w
a
v
e
c
l
a
ss
i
f
c
a
t
i
o
n
u
si
n
g
l
o
n
g
sh
o
r
t
-
t
e
r
m
mem
o
r
y
n
e
t
w
o
r
k
b
a
se
d
O
p
t
i
c
a
l
p
r
e
d
i
c
t
o
r
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
N
a
t
u
r
e
,
v
o
l
.
9
,
p
p
.
1
-
1
3
,
Ju
n
e
2
0
1
9
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
1
9
-
4
5
6
0
5
-
1.
[
9
]
I
.
Ta
h
i
r
,
U
.
Q
a
mar,
H
.
A
b
b
a
s
,
B
.
Z
e
b
,
a
n
d
S
.
A
b
i
d
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
EEG
S
i
g
n
a
l
b
y
Tr
a
i
n
i
n
g
N
e
u
r
a
l
N
e
t
w
o
r
k
w
i
t
h
S
w
a
r
m
O
p
t
i
mi
z
a
t
i
o
n
f
o
r
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
E
p
i
l
e
p
sy
,
”
i
n
Pr
o
c
.
11
th
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
C
o
m
p
u
t
i
n
g
,
F
e
b
.
2
0
1
9
,
p
p
.
1
9
7
-
2
0
3
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
1
8
2
9
9
.
3
3
1
8
3
7
4
.
[
1
0
]
M
.
I
f
t
i
k
h
a
r
,
S
.
A
.
K
h
a
n
,
a
n
d
A
.
H
a
ssa
n
,
"
A
S
u
r
v
e
y
o
f
D
e
e
p
Le
a
r
n
i
n
g
a
n
d
T
r
a
d
i
t
i
o
n
a
l
A
p
p
r
o
a
c
h
e
s
f
o
r
EEG
S
i
g
n
a
l
P
r
o
c
e
ss
i
n
g
a
n
d
C
l
a
s
si
f
i
c
a
t
i
o
n
,
”
i
n
Pr
o
c
.
I
E
EE
9
th
An
n
u
a
l
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
El
e
c
t
r
o
n
i
c
s
a
n
d
Mo
b
i
l
e
C
o
m
m
u
n
i
c
a
t
i
o
n
C
o
n
f
e
r
e
n
c
e
(
I
EM
C
O
N
)
,
2
0
1
8
,
p
p
.
3
9
5
-
4
0
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
EM
C
O
N
.
2
0
1
8
.
8
6
1
4
8
9
3
.
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
E
fficien
t e
lectro
en
ce
p
h
elo
g
r
a
m
cla
s
s
ifica
tio
n
s
ys
tem
u
s
in
g
s
u
p
p
o
r
t v
ec
to
r
… (
V
ir
u
p
a
xi
B
a
la
ch
a
n
d
r
a
D
a
la
l
)
297
[
1
1
]
S
.
Li
a
n
d
H
.
F
e
n
g
,
"
E
EG
S
i
g
n
a
l
C
l
a
ssi
f
i
c
a
t
i
o
n
M
e
t
h
o
d
B
a
se
d
o
n
F
e
a
t
u
r
e
P
r
i
o
r
i
t
y
A
n
a
l
y
s
i
s
a
n
d
C
N
N
,
”
i
n
Pr
o
c
.
I
n
t
e
r
n
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
s,
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
(
C
I
S
C
E)
,
2
0
1
9
,
p
p
.
4
0
3
-
4
0
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
S
C
E.
2
0
1
9
.
0
0
0
9
5
.
[
1
2
]
R
.
S
.
M
a
h
a
mu
n
e
a
n
d
S
.
H
.
L
a
sk
a
r
,
“
A
r
e
v
i
e
w
o
n
a
r
t
i
f
a
c
t
s
r
e
m
o
v
a
l
t
e
c
h
n
i
q
u
e
s
f
o
r
El
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
m
s
i
g
n
a
l
s
,
”
i
n
Pr
o
c
.
2
nd
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
n
o
v
a
t
i
o
n
s
i
n
E
l
e
c
t
r
o
n
i
c
s
,
S
i
g
n
a
l
Pro
c
e
ssi
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
(
I
ES
C
)
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
ESP
C
.
2
0
1
9
.
8
9
0
2
3
6
3
.
[
1
3
]
X
.
J
i
a
n
g
,
G.
-
B
.
B
i
a
n
,
a
n
d
Z.
T
i
a
n
,
“
R
e
m
o
v
a
l
o
f
A
r
t
i
f
a
c
t
s
f
r
o
m
E
EG
S
i
g
n
a
l
s:
A
R
e
v
i
e
w
,
”
S
e
n
so
rs
,
v
o
l
.
1
9
,
n
o
.
5
,
p
.
9
8
7
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
0
5
0
9
8
7
.
[
1
4
]
G
.
F
i
sc
o
n
e
t
a
l
.
,
“
C
o
m
b
i
n
i
n
g
EEG
s
i
g
n
a
l
p
r
o
c
e
ssi
n
g
w
i
t
h
su
p
e
r
v
i
se
d
m
e
t
h
o
d
s
f
o
r
A
l
z
h
e
i
mer'
s
p
a
t
i
e
n
t
s
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
BM
C
Me
d
I
n
f
o
rm
D
e
c
i
s
Ma
k
,
v
o
l
.
1
8
,
n
o
.
1
,
p
.
3
5
,
M
a
y
2
0
1
8
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
1
1
-
0
1
8
-
0
6
1
3
-
y
.
[
1
5
]
S
.
Li
a
n
d
H
.
F
e
n
g
,
"
EEG
S
i
g
n
a
l
C
l
a
ssi
f
i
c
a
t
i
o
n
M
e
t
h
o
d
B
a
s
e
d
o
n
F
e
a
t
u
r
e
P
r
i
o
r
i
t
y
A
n
a
l
y
s
i
s
a
n
d
C
N
N
,
"
i
n
Pr
o
c
.
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
s,
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
C
I
S
C
E)
,
2
0
1
9
,
p
p
.
4
0
3
-
4
0
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
S
C
E.
2
0
1
9
.
0
0
0
9
5
.
[
1
6
]
B
C
I
C
o
mp
e
t
i
t
i
o
n
I
V
,
h
t
t
p
:
/
/
w
w
w
.
b
b
c
i
.
d
e
/
c
o
m
p
e
t
i
t
i
o
n
/
i
v
/
[
1
7
]
R
.
Le
e
b
,
F
.
Le
e
,
C
.
K
e
i
n
r
a
t
h
,
a
n
d
R
.
S
c
h
e
r
e
r
,
“
B
r
a
i
n
-
C
o
m
p
u
t
e
r
C
o
mm
u
n
i
c
a
t
i
o
n
:
M
o
t
i
v
a
t
i
o
n
,
A
i
m
,
a
n
d
I
mp
a
c
t
o
f
E
x
p
l
o
r
i
n
g
a
V
i
r
t
u
a
l
A
p
a
r
t
me
n
t
,
”
I
EEE
t
ra
n
s
a
c
t
i
o
n
o
n
n
e
u
r
a
l
sys
t
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
:
a
p
u
b
l
i
c
a
t
i
o
n
o
f
t
h
e
I
EE
E
e
n
g
i
n
e
e
ri
n
g
i
n
Me
d
i
c
i
n
e
a
n
d
Bi
o
l
o
g
y
S
o
c
i
e
t
y
,
vol
.
15
,
n
o
.
4
,
2
0
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
R
E.
2
0
0
7
.
9
0
6
9
5
6
.
[
1
8
]
S
.
S
i
u
l
y
,
Y
.
Li
,
a
n
d
Y
.
Z
h
a
n
g
,
“
EEG
S
i
g
n
a
l
A
n
a
l
y
s
i
s a
n
d
C
l
a
s
si
f
i
c
a
t
i
o
n
,
”
S
p
ri
n
g
e
r
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
319
-
4
7
6
5
3
-
7.
[
1
9
]
J
.
B
a
r
a
n
o
w
s
k
a
n
d
P
.
P
i
ą
t
e
k
,
“
F
r
a
c
t
i
o
n
a
l
B
a
n
d
-
P
a
ss
F
i
l
t
e
r
s:
D
e
si
g
n
,
I
mp
l
e
men
t
a
t
i
o
n
a
n
d
A
p
p
l
i
c
a
t
i
o
n
t
o
E
EG
S
i
g
n
a
l
P
r
o
c
e
ssi
n
g
,
”
J
o
u
rn
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
.
2
6
,
n
o
.
1
1
,
p
p
.
1
-
2
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
8
1
2
6
6
1
7
5
0
1
7
0
5
.
[
2
0
]
K
.
K
.
A
n
g
,
Z
.
Y
.
C
h
i
n
,
C
.
W
a
n
g
,
C
.
G
u
a
n
,
a
n
d
H
.
Z
h
a
n
g
,
“
F
i
l
t
e
r
b
a
n
k
c
o
mm
o
n
s
p
a
t
i
a
l
p
a
t
t
e
r
n
a
l
g
o
r
i
t
h
m
o
n
B
C
I
c
o
m
p
e
t
i
t
i
o
n
I
V
D
a
t
a
s
e
t
s
2
a
a
n
d
2
b
,
”
J
o
u
r
n
a
l
o
f
f
r
o
n
t
i
e
r i
n
n
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
6
,
no
.
3
9
,
p
p
.
1
-
9
,
2
0
1
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s
.
2
0
1
2
.
0
0
0
3
9
.
[
2
1
]
C
.
M
.
B
i
sh
o
p
,
N
e
u
r
a
l
N
e
t
w
o
rk
s f
o
r
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
,
O
x
f
o
r
d
U
n
i
v
e
r
s
i
t
y
P
r
e
ss,
C
a
m
b
r
i
d
g
e
,
1
9
9
5
.
[
2
2
]
D
.
G
a
r
r
e
t
t
,
D
.
A
.
P
e
t
e
r
s
o
n
,
C
.
W
.
A
n
d
e
r
so
n
,
a
n
d
M
.
H
.
T
h
a
u
t
,
“
C
o
mp
a
r
i
so
n
o
f
l
i
n
e
a
r
a
n
d
n
o
n
l
i
n
e
a
r
m
e
t
h
o
d
s
f
o
r
EEG
s
i
g
n
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
N
e
u
ra
l
S
y
s
t
e
m
s
a
n
d
Re
h
a
b
i
l
i
t
a
t
i
o
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
,
p
p
.
1
4
1
-
1
4
4
,
2
0
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
R
E
.
2
0
0
3
.
8
1
4
4
4
1
.
[
2
3
]
N
.
K
e
r
k
e
n
i
,
F
.
A
l
e
x
a
n
d
r
e
,
H
.
M
.
B
e
d
o
u
i
,
L
.
B
o
u
g
r
a
i
n
,
a
n
d
M
.
D
o
g
u
i
,
“
A
u
t
o
m
a
t
i
c
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
s
l
e
e
p
st
a
g
e
s
o
n
a
EEG
si
g
n
a
l
b
y
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
i
n
Pr
o
c
.
5
th
W
S
E
AS
I
n
t
.
C
o
n
f
.
o
n
S
i
g
S
p
e
e
c
h
A
n
d
İ
m
a
g
e
Pro
c
e
ss
i
n
g
,
2
0
0
5
,
p
p
.
1
2
8
-
1
3
1
.
[
2
4
]
I
.
A
.
A
l
j
a
z
a
e
r
y
,
A
.
A
.
A
l
i
,
a
n
d
H
.
M
.
A
b
d
u
l
r
i
d
h
a
,
“
C
l
a
s
si
f
i
c
a
t
i
o
n
o
f
e
l
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
p
h
(
EEG
)
si
g
n
a
l
s
u
s
i
n
g
q
u
a
n
t
u
m
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
:
An
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
(
S
PI
J
)
,
v
o
l
.
4
,
n
o
.
6
,
2
0
1
1
.
[
2
5
]
M
.
N
a
n
d
i
s
h
,
M
.
S
t
a
f
f
o
r
d
,
P
.
H
.
K
u
mar,
a
n
d
F
.
A
h
me
d
,
“
F
e
a
t
u
r
e
Ex
t
r
a
c
t
i
o
n
a
n
d
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
EEG
S
i
g
n
a
l
U
si
n
g
N
e
u
r
a
l
N
e
t
w
o
r
k
B
a
se
d
T
e
c
h
n
i
q
u
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
ri
n
g
a
n
d
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
y
(
I
J
EI
T
)
,
v
o
l
.
2
,
n
o
.
4
,
O
c
t
.
2
0
1
2
.
[
2
6
]
R
.
B
.
B
h
a
t
t
a
n
d
M
.
G
h
o
p
a
l
,
“
F
R
I
D
:
f
u
z
z
y
-
r
o
u
g
h
i
n
t
e
r
a
c
t
i
v
e
d
i
c
h
o
t
o
mi
z
e
r
s
,
”
i
n
Pr
o
c
.
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
Fu
z
zy
S
y
s
t
e
m
s
,
2
0
0
4
,
p
p
.
1
3
3
7
-
1
3
4
2
,
d
o
i
:
1
0
.
1
1
0
9
/
F
U
ZZY
.
2
0
0
4
.
1
3
7
5
3
6
3
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Vir
u
p
a
x
i
Ba
l
a
c
h
a
n
d
r
a
D
a
la
l
is
a
re
se
a
rc
h
sc
h
o
lar
a
t
De
p
a
rtme
n
t
o
f
E
lec
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
g
in
e
e
ri
n
g
,
S
DMCE
T,
Dh
a
rwa
d
,
Ka
rn
a
tak
a
,
In
d
ia.
Au
t
h
o
r
is
a
lso
wo
rk
i
n
g
a
s
As
sista
n
t
P
ro
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
E
lec
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
a
t
Ja
in
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
n
d
Re
se
a
rc
h
,
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
i
a
.
Au
th
o
r’s
a
re
a
o
f
in
tres
t
i
s
S
ig
n
a
ls
P
ro
c
e
ss
in
g
a
n
d
Im
a
g
e
P
ro
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
iru
p
a
x
i.
d
a
lal@g
m
a
il
.
c
o
m
.
Dr
.
S
a
tish
S
.
Bh
a
ira
n
n
a
w
a
r
h
o
l
d
s
t
h
e
p
o
si
ti
o
n
o
f
De
a
n
of
In
d
u
stry
I
n
stit
u
te
In
terfa
c
e
(III),
C
h
a
irp
e
rso
n
,
C
EIR
S
tart
u
p
in
c
u
b
a
ti
o
n
a
n
d
P
ro
fe
ss
o
r
of
El
e
c
tr
o
n
ics
&
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
ri
n
g
,
S
DMCE
T,
Dh
a
rwa
d
.
He
h
a
s
b
e
e
n
in
v
o
l
v
e
d
i
n
re
se
a
rc
h
a
c
ti
v
it
ies
fu
n
d
e
d
b
y
re
p
u
te
d
sta
te
a
n
d
c
e
n
tral
g
o
v
t.
o
r
g
a
n
iza
ti
o
n
s
a
n
d
h
a
s
p
u
b
li
sh
e
d
o
v
e
r
3
0
re
se
a
rc
h
p
u
b
li
c
a
ti
o
n
s
in
S
CI,
S
CI
E
a
n
d
S
c
o
p
u
s
In
d
e
x
e
d
J
o
u
r
n
a
l.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
ti
sh
b
h
a
iran
n
a
wa
r@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.