I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
3180
~
3
1
9
0
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
3
.
p
p
3
1
8
0
-
3
1
9
0
3180
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
M
a
chine learning
-
ba
sed hy
brid
em
o
tions
rec
o
g
nition
mo
del
using
elect
ro
en
ce
pha
lo
g
ra
m sig
na
l
s
T
a
run K
um
a
r,
Ra
j
endra
K
um
a
r,
Ra
m
Cha
nd
ra
Sin
g
h
S
h
a
r
d
a
S
c
h
o
o
l
o
f
B
a
s
i
c
S
c
i
e
n
c
e
s
a
n
d
R
e
se
a
r
c
h
,
S
h
a
r
d
a
U
n
i
v
e
r
si
t
y
,
G
r
e
a
t
e
r
N
o
i
d
a
,
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
Oct
1
5
,
2
0
2
4
R
ev
is
ed
Feb
7
,
2
0
2
5
Acc
ep
ted
Ma
r
3
,
2
0
2
5
Th
is
p
a
p
e
r
u
se
s
Hin
d
i
v
i
d
e
o
c
li
p
s
to
p
r
o
p
o
se
a
n
e
lec
tro
e
n
c
e
p
h
a
lo
g
r
a
m
(EE
G
)
sig
n
a
l
-
b
a
se
d
h
y
b
ri
d
sy
ste
m
f
o
r
e
m
o
ti
o
n
i
d
e
n
ti
fica
ti
o
n
.
EE
G
sig
n
a
l
s
c
a
n
n
o
t
b
e
a
lt
e
re
d
,
u
n
li
k
e
o
th
e
r
fo
rm
s
o
f
e
x
p
re
ss
iv
e
n
e
ss
-
li
k
e
v
o
ice
a
n
d
fa
c
ia
l
e
m
o
ti
o
n
.
Th
e
su
g
g
e
ste
d
a
p
p
r
o
a
c
h
u
se
s
a
se
lf
-
c
re
a
ted
d
a
tas
e
t
u
n
d
e
r
th
e
c
o
n
tro
l
e
n
v
iro
n
m
e
n
ts.
Ac
c
u
ra
c
y
is
t
h
e
m
a
in
o
b
jec
ti
v
e
o
f
th
e
p
r
o
p
o
se
d
m
o
d
e
l.
Th
is
stu
d
y
u
se
d
a
se
lf
-
c
re
a
ted
c
o
n
str
u
c
ted
u
sin
g
a
n
8
-
c
h
a
n
n
e
l
u
n
ico
r
n
b
l
a
c
k
h
y
b
rid
EE
G
m
a
c
h
in
e
o
n
3
0
p
a
rti
c
i
p
a
n
ts
wh
il
e
t
h
e
y
v
iew
e
d
Hi
n
d
i
m
o
v
ie
v
i
d
e
o
c
l
ip
s
m
imic
k
in
g
e
m
o
t
io
n
s:
h
a
p
p
y
,
fe
a
r
fu
l,
sa
d
,
a
n
d
n
e
u
tral.
Th
e
p
ro
p
o
s
e
d
m
o
d
e
l
u
se
d
a
two
-
h
y
b
rid
c
las
sifier
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM
)
a
n
d
k
-
n
e
a
re
st
n
e
ig
h
b
o
r
(
KNN
)
,
imp
lem
e
n
ted
u
sin
g
M
ATLAB
R2
0
1
7
a
.
In
t
h
e
p
ro
p
o
se
d
imp
lem
e
n
tatio
n
,
th
e
fo
u
r
e
m
o
ti
o
n
c
las
sifica
ti
o
n
c
a
teg
o
ries
(
h
a
p
p
y
,
sa
d
,
fe
a
r,
a
n
d
n
e
u
tral)
o
b
se
rv
e
d
a
n
a
v
e
ra
g
e
a
c
c
u
ra
c
y
o
f
6
0
.
8
3
2
%
.
T
h
e
re
su
lt
s
o
f
t
h
e
p
re
se
n
ted
st
u
d
y
we
re
c
o
m
p
a
re
d
w
it
h
two
re
c
e
n
t
s
y
ste
m
s
.
It
wa
s
fo
u
n
d
th
a
t
t
h
e
p
ro
p
o
se
d
s
y
ste
m
o
b
se
rv
e
d
b
e
tt
e
r
a
c
c
u
ra
c
y
fo
r
t
h
e
c
a
teg
o
r
y
o
f
NHP
fiv
e
c
las
se
s
a
n
d
th
e
c
a
teg
o
ry
o
f
HP
F
i
v
e
Clas
se
s.
K
ey
w
o
r
d
s
:
Acc
u
r
ac
y
E
E
G
d
atasets
E
lectr
o
en
ce
p
h
al
o
g
r
am
E
m
o
tio
n
K
-
n
ea
r
est n
eig
h
b
o
r
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
:
T
ar
u
n
Ku
m
ar
Sh
ar
d
a
Sch
o
o
l
o
f
B
asic Scie
n
ce
s
an
d
R
esear
ch
,
Sh
ar
d
a
Un
i
v
er
s
ity
Gr
ea
ter
No
id
a
,
UP,
I
n
d
ia
E
m
ail:
tar
u
n
k
u
m
ar
1
2
4
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
o
en
ce
p
h
al
o
g
r
am
(
E
E
G)
m
ea
s
u
r
es
th
e
ac
tiv
ity
in
th
e
b
r
ain
b
y
elec
tr
ical
s
ig
n
als.
An
a
n
aly
s
is
o
f
s
u
ch
s
ig
n
als
in
v
o
lv
es
th
e
f
r
eq
u
en
cy
b
an
d
s
n
am
ely
Delta,
T
h
eta,
Alp
h
a,
B
eta,
an
d
Gam
m
a.
Mo
s
t
b
asic
em
o
tio
n
s
s
u
ch
as
h
ap
p
in
ess
,
f
ea
r
,
s
ad
n
e
s
s
,
an
d
n
eu
tr
ality
h
av
e
b
ee
n
c
lass
if
ied
th
r
o
u
g
h
th
e
ex
tr
ac
tio
n
o
f
f
ea
tu
r
es
f
r
o
m
th
ese
s
ig
n
als,
f
o
r
in
s
tan
ce
,
u
s
i
n
g
b
an
d
p
o
wer
an
d
e
n
tr
o
p
y
.
T
h
ese
ch
ar
ac
ter
is
tics
allu
d
e
to
a
r
o
u
s
al
an
d
v
alen
ce
;
a
p
atter
n
s
u
ch
as
in
cr
ea
s
ed
B
e
ta
ac
tiv
ity
d
ep
icts
f
ea
r
o
r
an
x
iety
an
d
is
ass
o
ciate
d
with
ca
l
m
n
ess
o
r
n
eu
tr
ali
ty
with
Alp
h
a
wav
es.
Fo
r
r
ec
o
g
n
itio
n
o
f
th
ese
p
atter
n
s
,
m
a
ch
in
e
lear
n
in
g
tech
n
iq
u
es
ca
n
u
s
e
E
E
G
s
ig
n
als
ef
f
ec
tiv
ely
f
o
r
em
o
tio
n
r
ec
o
g
n
itio
n
an
d
a
d
v
an
ce
a
p
p
licatio
n
s
in
n
eu
r
o
f
ee
d
b
ac
k
,
m
en
tal
h
ea
lth
,
Par
k
in
s
o
n
'
s
d
is
ea
s
e,
an
d
h
u
m
a
n
-
co
m
p
u
ter
in
ter
ac
tio
n
[
1
]
,
[
2
]
.
Mo
s
t
o
f
th
e
r
esear
ch
o
n
E
E
G
-
b
ased
em
o
tio
n
id
e
n
tific
atio
n
i
n
h
ea
lth
y
in
d
i
v
id
u
als
h
as
s
h
o
wn
p
o
s
itiv
e
f
in
d
in
g
s
.
Usi
n
g
a
h
ea
r
in
g
lo
s
s
s
im
u
lato
r
an
d
th
e
v
o
ca
l
m
o
r
p
h
in
g
ap
p
r
o
ac
h
,
em
o
tio
n
d
et
ec
tio
n
s
tu
d
ies
wer
e
p
er
f
o
r
m
ed
o
n
b
o
th
el
d
er
ly
an
d
y
o
u
n
g
n
o
r
m
al
h
ea
r
i
n
g
(
YNH)
s
u
b
jects
[
1
]
–
[
3
]
.
Sp
ee
ch
s
o
u
n
d
s
wer
e
alter
ed
to
s
y
m
b
o
lize
f
ee
lin
g
s
b
etwe
en
al
l p
o
s
s
ib
le
co
m
b
in
atio
n
s
o
f
jo
y
,
s
o
r
r
o
w,
an
d
r
ag
e
an
d
h
av
e
lo
o
k
ed
at
p
o
p
u
latio
n
s
lik
e
th
o
s
e
with
h
ea
r
in
g
im
p
air
m
en
ts
[
4
]
,
[
5
]
.
So
m
e
s
p
ec
ialis
ts
claim
th
at
b
ec
au
s
e
o
f
th
eir
h
ea
r
in
g
l
o
s
s
,
p
er
s
o
n
s
with
h
ea
r
in
g
im
p
air
m
e
n
ts
h
av
e
d
if
f
icu
lties
in
u
n
d
er
s
tan
d
in
g
ac
cu
r
ate
in
f
o
r
m
atio
n
f
r
o
m
th
e
o
u
ts
id
e
wo
r
ld
as
co
m
p
ar
ed
to
p
e
r
s
o
n
s
with
n
o
r
m
al
h
ea
r
in
g
[
6
]
,
[
7
]
.
Z
h
u
et
a
l.
[
8
]
p
r
o
p
o
s
ed
a
th
eo
r
y
o
n
im
ag
e
-
s
tim
u
lated
e
m
o
tio
n
i
d
en
tific
atio
n
f
o
r
s
u
b
jects
with
h
ea
r
in
g
i
m
p
air
m
en
ts
u
s
in
g
E
E
G
d
ata
s
ig
n
als
.
T
h
ey
u
s
ed
th
r
ee
d
if
f
er
e
n
t
class
if
icatio
n
s
n
am
ely
n
eu
tr
al,
p
o
s
itiv
e,
an
d
n
e
g
ativ
e;
an
d
also
f
iv
e
d
if
f
er
en
t
class
if
icatio
n
s
n
am
ely
n
eu
tr
al
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
h
yb
r
id
emo
tio
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
…
(
Ta
r
u
n
K
u
ma
r
)
3181
h
ap
p
y
,
s
ad
,
an
g
r
y
,
an
d
f
ea
r
f
u
l
to
test
em
o
tio
n
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
.
T
h
e
r
esu
lts
o
f
th
eir
ex
p
er
im
en
ts
p
r
esen
ted
th
at
th
e
m
u
lti
-
f
ea
tu
r
e
f
u
s
io
n
h
elp
ed
h
ea
r
in
g
-
im
p
air
ed
a
n
d
n
o
n
-
h
ea
r
in
g
-
im
p
air
e
d
p
eo
p
le,
a
n
d
th
e
r
ec
o
m
m
en
d
ed
s
tr
ateg
y
is
b
etter
th
an
th
e
tr
ad
itio
n
al
f
ea
tu
r
e
tech
n
iq
u
e.
T
h
e
av
er
ag
e
class
if
icatio
n
ac
cu
r
ac
y
[
9
]
was
o
b
s
er
v
ed
as
7
2
.
0
5
%
(
th
r
ee
-
class
if
icatio
n
s
)
an
d
5
1
.
5
3
%
(
f
iv
e
-
class
if
icatio
n
s
)
f
o
r
h
ea
r
in
g
-
im
p
air
ed
in
d
iv
id
u
als
an
d
5
0
.
1
5
% (
t
h
r
ee
-
class
if
icatio
n
s
)
f
o
r
n
o
n
-
h
ea
r
in
g
-
im
p
air
ed
s
u
b
j
ec
ts
,
r
esp
ec
tiv
ely
.
J
in
et
a
l
.
p
r
o
p
o
s
ed
a
th
eo
r
y
b
a
s
ed
o
n
f
ac
e
-
af
f
ec
tiv
e
p
h
o
to
s
tim
u
latio
n
.
Fo
r
th
is
p
u
r
p
o
s
e,
th
ey
u
s
ed
a
n
em
o
tio
n
al
s
elf
-
cr
ea
ted
E
E
G
d
ataset
o
f
1
5
h
ea
r
in
g
-
im
p
air
e
d
an
d
1
5
n
o
r
m
al
p
eo
p
le.
T
h
e
d
a
taset
cr
ea
ted
b
y
J
in
et
a
l.
[
1
0
]
in
clu
d
e
d
f
iv
e
d
if
f
er
en
t
em
o
tio
n
ty
p
es
(
h
ap
p
y
,
n
eu
tr
al,
s
o
r
r
o
w,
f
ea
r
,
an
d
r
ag
e)
.
Pre
p
r
o
ce
s
s
in
g
f
ilter
s
an
d
elim
in
ates
ar
tifa
cts
f
r
o
m
th
e
g
ath
er
ed
E
E
G
s
ig
n
als.
Af
te
r
ex
tr
ac
tin
g
tr
aits
in
clu
d
in
g
p
o
wer
s
p
ec
tr
al
d
en
s
ity
(
PS
D)
,
d
if
f
er
en
tial
en
tr
o
p
y
(
DE
)
,
an
d
wa
v
elet
en
tr
o
p
y
(
W
E
)
,
it
was
s
h
o
wn
th
at
th
e
lin
ea
r
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
was
th
e
m
o
s
t
ef
f
ec
tiv
e
class
if
ier
f
o
r
a
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
f
o
r
em
o
tio
n
class
if
i
ca
tio
n
.
As
p
er
th
eir
f
in
d
in
g
s
,
th
e
DE
ch
ar
ac
ter
is
tic
o
b
s
er
v
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
in
id
en
tify
in
g
e
m
o
tio
n
s
am
o
n
g
r
esp
o
n
d
e
n
ts
with
h
ea
r
in
g
im
p
air
m
en
ts
(
4
0
.
8
%
)
an
d
n
o
r
m
al
s
u
b
jects
(
4
5
.
5
%).
Yan
g
et
a
l.
[
1
1
]
e
x
am
i
n
ed
th
e
em
o
tio
n
al
r
ec
o
g
n
itio
n
p
atter
n
o
f
d
ea
f
p
e
r
s
o
n
s
.
T
h
ey
u
s
ed
a
d
ee
p
b
elie
f
n
etwo
r
k
i
n
co
n
j
u
n
ctio
n
with
th
e
E
E
G
an
d
f
ac
ial
ex
p
r
ess
io
n
s
to
d
is
tin
g
u
is
h
th
r
ee
ty
p
es
o
f
em
o
tio
n
s
.
A
to
tal
o
f
1
5
d
ea
f
p
ar
ticip
an
ts
’
s
ig
n
al
s
wer
e
ca
p
tu
r
ed
as
th
ey
v
iewe
d
th
e
m
o
v
ie
clip
s
.
I
n
th
is
s
tu
d
y
,
a
h
y
b
r
id
s
y
s
tem
is
p
r
o
p
o
s
ed
f
o
r
em
o
tio
n
clas
s
if
icatio
n
an
d
test
ed
u
s
in
g
a
s
elf
-
cr
ea
ted
d
ataset
[
1
2
]
.
T
h
e
m
o
d
el
is
b
ased
o
n
Hin
d
i
m
o
v
ie
v
id
e
o
s
with
v
o
ice,
m
u
te,
an
d
d
ea
f
-
b
ase
d
m
o
v
ie
clip
s
[
1
3
]
.
T
h
e
f
u
r
th
er
s
ec
tio
n
s
i
n
th
e
p
a
p
er
ar
e
o
r
g
an
ized
as
f
o
llo
ws:
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
em
o
tio
n
class
if
icatio
n
is
d
em
o
n
s
tr
ated
in
s
ec
tio
n
2
,
alo
n
g
with
th
e
s
p
ec
if
icatio
n
s
an
d
d
escr
ip
tio
n
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
e
r
esu
lts
an
d
d
is
cu
s
s
io
n
ar
e
p
r
esen
ted
in
s
ec
tio
n
3
,
an
d
th
e
co
n
cl
u
d
in
g
r
em
ar
k
s
with
f
u
tu
r
e
s
co
p
e
a
r
e
d
es
cr
ib
ed
in
s
ec
tio
n
4
.
2.
M
E
T
H
O
D
F
O
R
E
M
O
T
I
O
N
CL
ASS
I
F
I
C
AT
I
O
N
B
y
em
p
lo
y
in
g
t
h
e
r
ig
h
t
m
et
h
o
d
,
em
o
tio
n
r
ec
o
g
n
itio
n
m
ay
b
e
co
m
e
m
o
r
e
s
u
cc
ess
f
u
l.
I
n
o
r
d
e
r
to
en
s
u
r
e
ac
cu
r
ac
y
,
co
n
s
is
ten
cy
,
an
d
ac
c
u
r
ac
y
,
th
e
s
ec
tio
n
o
n
e
x
p
er
im
e
n
ts
/m
eth
o
d
s
p
r
o
v
id
es
a
s
u
m
m
a
r
y
a
n
d
e
x
p
lan
atio
n
o
f
th
e
m
eth
o
d
s
,
to
o
ls
,
p
r
o
ce
s
s
es,
an
d
d
ata
an
aly
s
is
u
s
ed
in
t
h
is
r
esear
ch
.
Usi
n
g
th
e
Un
ico
r
n
B
lack
8
-
ch
an
n
el
E
E
G
p
r
o
g
r
a
m
,
3
0
p
eo
p
le
a
g
ed
b
etwe
en
1
8
an
d
5
6
p
ar
ticip
ate
d
in
th
e
s
elf
-
cr
ea
ted
d
ataset.
T
h
e
p
ar
ticip
an
ts
wer
e
s
h
o
wn
in
s
ep
ar
ate
Hin
d
i
v
id
eo
clip
s
ce
n
es,
in
wh
ich
f
ea
r
s
,
te
ar
s
,
jo
y
s
,
an
d
n
eu
tr
al
em
o
ti
o
n
s
wer
e
r
ef
lecte
d
.
T
o
en
s
u
r
e
u
n
if
o
r
m
ity
o
f
d
ata
c
o
llectio
n
,
th
is
p
r
o
ce
d
u
r
e
w
as
p
er
f
o
r
m
e
d
s
eq
u
en
tially
f
o
r
ea
c
h
p
ar
ticip
an
t.
T
h
e
d
o
m
ain
p
ar
am
eter
s
wer
e
s
elec
ted
b
ased
o
n
wh
at
p
r
ev
io
u
s
r
esear
ch
h
as
s
h
o
wn
to
b
e
u
s
ef
u
l
i
n
d
if
f
e
r
en
tiatin
g
t
h
e
em
o
tio
n
s
p
r
esen
t.
I
n
o
r
d
er
to
ex
p
lo
it
th
e
u
n
iq
u
e
ad
v
a
n
tag
e
s
o
f
ea
ch
class
if
ier
with
im
p
r
o
v
ed
ac
c
u
r
ac
y
a
n
d
r
o
b
u
s
tn
ess
,
a
h
y
b
r
id
class
if
icatio
n
s
tr
ateg
y
was
u
s
ed
in
th
e
s
tu
d
y
,
wh
ich
co
m
b
i
n
ed
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(S
VM
)
an
d
k
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN
)
class
if
ier
s
.
Giv
en
th
e
r
elativ
ely
s
m
all
s
ize
o
f
th
e
d
ataset,
leav
e
-
one
-
o
u
t
cr
o
s
s
-
v
alid
atio
n
(
L
OOCV)
was
u
s
ed
as
a
v
alid
atio
n
m
eth
o
d
t
o
en
s
u
r
e
r
eliab
le
m
o
d
el
esti
m
a
tio
n
an
d
m
a
x
im
ize
th
e
u
s
e
o
f
av
ailab
le
d
ata.
Pre
-
d
ef
in
ed
s
ig
n
al
-
to
-
n
o
is
e
r
atio
a
n
d
v
is
u
al
ass
ess
m
en
t
cr
iter
ia
wer
e
u
s
ed
to
r
ejec
t
tr
ials
with
h
ig
h
n
o
is
e
o
r
p
o
o
r
s
ig
n
al
q
u
ality
.
R
aw
E
E
G
d
ata
wer
e
p
re
-
p
r
o
ce
s
s
ed
u
s
in
g
co
n
v
en
tio
n
al
f
ilter
in
g
m
eth
o
d
s
to
r
em
o
v
e
n
o
is
e
an
d
ar
tifa
cts.
Sectio
n
2
.
1
p
r
o
v
id
e
s
th
e
d
etailed
p
ar
a
m
eter
s
o
f
t
h
e
E
E
G
eq
u
ip
m
en
t,
s
u
ch
as
elec
tr
o
d
e
lo
ca
tio
n
,
ch
an
n
el
s
ettin
g
,
an
d
s
am
p
lin
g
r
ate,
as
well
as
th
e
s
y
n
ch
r
o
n
iz
atio
n
p
r
o
ce
d
u
r
e
f
o
r
em
o
tio
n
lab
elin
g
an
d
s
tim
u
lu
s
p
r
esen
tatio
n
.
Fig
u
r
e
1
p
r
esen
ts
th
e
s
tep
s
f
o
r
th
e
p
r
o
p
o
s
ed
e
m
o
tio
n
r
ec
o
g
n
itio
n
m
o
d
el
a
n
d
t
h
e
co
n
n
ec
tio
n
s
b
et
wee
n
th
e
d
if
f
er
e
n
t
p
r
o
ce
s
s
es.
A
d
etailed
d
is
cu
s
s
io
n
o
f
ea
c
h
s
tep
is
p
r
esen
ted
i
n
th
e
s
u
b
s
eq
u
en
t su
b
-
s
ec
tio
n
s
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
em
o
tio
n
r
e
co
g
n
itio
n
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
8
0
-
3
1
9
0
3182
2
.
1
.
E
E
G
da
t
a
a
cquis
it
io
n
E
E
G
s
ig
n
als
ar
e
ca
p
tu
r
ed
f
r
o
m
a
h
y
b
r
i
d
Un
ico
r
n
B
lack
8
-
ch
a
n
n
el
E
E
G
eq
u
ip
m
en
t
to
r
ec
o
r
d
p
ar
ticip
an
ts
’
b
r
ain
ac
tiv
ity
as
th
ey
watc
h
p
a
r
ticu
lar
v
id
eo
s
tim
u
li
to
g
en
e
r
ate
an
E
E
G
d
ataset
f
o
r
em
o
tio
n
d
etec
tio
n
.
L
o
w
s
p
atial
r
eso
lu
tio
n
n
ec
ess
itates
ap
p
r
o
p
r
iate
v
al
id
atio
n
o
n
a
v
a
r
ied
s
etu
p
with
r
eg
ar
d
t
o
d
iv
e
r
s
ity
in
d
if
f
er
en
t
d
ev
ices
o
r
p
o
p
u
lati
o
n
s
,
b
u
t
th
e
en
h
an
ce
d
8
-
ch
a
n
n
el
Un
ico
r
n
B
lack
h
y
b
r
i
d
E
E
G
m
ac
h
in
e
m
ak
es
th
e
im
p
lem
en
tatio
n
tr
u
ly
p
o
r
tab
le
an
d
s
im
p
le
en
o
u
g
h
f
o
r
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
.
T
h
ir
ty
p
ar
ticip
an
ts
,
r
an
g
in
g
in
ag
e
f
r
o
m
ei
g
h
teen
to
f
i
f
ty
-
s
ix
,
v
iewe
d
Hin
d
i
v
id
eo
s
in
ten
d
ed
to
elicit
f
o
u
r
d
if
f
e
r
en
t
em
o
tio
n
s
:
f
ea
r
,
s
ad
,
h
ap
p
y
,
an
d
n
e
u
tr
al.
T
h
r
ee
d
is
tin
ct
s
tag
es
wer
e
in
clu
d
e
d
in
ea
ch
r
ec
o
r
d
in
g
s
ess
io
n
,
ea
ch
in
cl
u
d
in
g
a
v
ar
iety
o
f
s
tim
u
li
to
allo
w
f
o
r
a
t
h
o
r
o
u
g
h
ex
am
i
n
atio
n
o
f
th
e
em
o
tio
n
al
r
ea
ctio
n
s
.
T
h
e
p
ar
am
eter
s
o
f
th
e
s
elf
-
cr
ea
ted
[
1
2
]
d
ataset
ar
e
p
r
esen
ted
in
T
ab
le
1
.
T
ab
le
1
.
Self
-
cr
ea
te
d
d
ataset
d
escr
ip
tio
n
P
a
r
a
me
t
e
r
D
e
t
a
i
l
s
P
a
r
t
i
c
i
p
a
n
t
s
2
0
M
a
l
e
,
1
0
F
e
m
a
l
e
C
h
a
n
n
e
l
s N
u
m
b
e
r
08
Ty
p
e
o
f
S
i
g
n
a
l
s
EEG
N
u
mb
e
r
o
f
v
i
d
e
o
s (f
o
r
e
a
c
h
p
a
r
t
i
c
i
p
a
n
t
)
12
S
a
mp
l
e
r
a
t
e
f
r
e
q
u
e
n
c
y
(
a
f
t
e
r
p
r
e
-
p
r
o
c
e
ssi
n
g
)
2
5
0
H
z
Th
e
n
u
m
b
e
r
o
f
c
l
a
s
si
f
i
c
a
t
i
o
n
s
f
o
r
t
h
e
d
a
t
a
se
t
4
C
l
a
s
si
f
i
c
a
t
i
o
n
N
a
m
e
H
a
p
p
y
,
F
e
a
r
,
S
a
d
,
a
n
d
N
e
u
t
r
a
l
Q
u
a
n
t
i
t
y
o
f
i
n
f
o
r
m
a
t
i
o
n
(
.
c
s
v
f
i
l
e
)
3
6
0
N
u
meri
c
a
l
d
a
t
a
1
2
v
i
d
e
o
s
×
8
c
h
a
n
n
e
l
s
×
3
0
P
a
r
t
i
c
i
p
a
n
t
s
.
2
.
1
.
1
.
E
E
G
equip
m
ent
a
nd
c
ha
nn
els
T
h
e
Un
ico
r
n
B
lack
E
E
G
8
-
ch
an
n
el
d
ev
ice
is
a
h
ig
h
-
p
er
f
o
r
m
an
ce
wea
r
ab
le
B
C
I
d
ev
ice
d
esig
n
ed
f
o
r
th
e
r
ea
l
-
tim
e
r
ec
o
r
d
in
g
o
f
E
E
G
d
ata
f
r
o
m
t
h
e
s
ca
lp
u
s
in
g
n
o
n
-
in
v
asiv
e
elec
tr
o
d
es.
An
aly
zin
g
m
e
n
tal
s
tates,
in
clu
d
in
g
e
m
o
tio
n
al
r
ea
ctio
n
s
,
r
eq
u
ir
es
s
ig
n
als
in
d
icat
in
g
e
lectr
ical
ac
tiv
ity
p
r
o
d
u
ce
d
b
y
th
e
n
eu
r
o
n
s
o
f
th
e
b
r
ain
.
E
ig
h
t
elec
tr
o
d
es
wer
e
p
l
ac
ed
o
n
s
p
ec
if
ic
s
ca
lp
s
ites
ac
c
o
r
d
in
g
t
o
th
e
s
tan
d
ar
d
1
0
-
2
0
s
y
s
tem
f
o
r
elec
tr
o
d
e
p
lace
m
en
t
in
E
E
G
r
ec
o
r
d
in
g
[
5
]
.
E
lectr
o
d
es
wer
e
p
lace
d
n
o
r
m
ally
ac
r
o
s
s
th
e
f
r
o
n
tal,
te
m
p
o
r
al,
an
d
p
a
r
ietal
r
eg
io
n
s
o
f
t
h
e
b
r
ain
ar
ea
s
s
en
s
itiv
e
to
em
o
tio
n
al
in
p
u
ts
.
E
ac
h
elec
tr
o
d
e
r
ec
o
r
d
ed
v
a
r
io
u
s
b
r
ain
wav
e
f
r
e
q
u
en
c
y
b
an
d
s
with
d
if
f
er
en
t
v
ar
ia
n
ts
ap
p
lied
to
m
ea
s
u
r
e
s
h
if
ts
in
d
if
f
er
en
t
s
tates
o
f
em
o
tio
n
s
.
Fi
g
u
r
e
2
p
r
o
v
id
es
th
e
p
o
s
itio
n
o
f
t
h
e
eig
h
t c
h
an
n
els
ap
p
lied
f
o
r
s
ig
n
al
r
ec
o
r
d
in
g
th
at
in
clu
d
e
Fp
1
,
Fp
2
,
C
3
,
C
4
,
P
3
,
P4
,
O1
,
a
n
d
O2
.
Fig
u
r
e
2
.
First Au
th
o
r
with
Un
ico
r
n
b
lack
E
E
G
d
ev
ice
with
1
0
/2
0
s
y
s
tem
2
.
1
.
2
.
P
ro
ce
du
re
f
o
r
g
a
t
heri
ng
da
t
a
T
h
e
s
tu
d
y
is
d
iv
id
e
d
in
to
th
r
e
e
p
h
ases
:
P
h
ase
1
is
th
e
lis
ten
in
g
s
u
p
p
o
r
t
wh
ile
watc
h
in
g
Hin
d
i
v
id
eo
clip
s
,
Ph
ase
2
is
h
ea
r
in
g
-
im
p
air
ed
o
r
d
ea
f
-
m
u
te
p
er
s
o
n
s
w
atch
in
g
Hin
d
i
v
id
e
o
clip
s
,
a
n
d
Ph
ase
3
is
a
s
ilen
t
watc
h
in
g
b
y
p
ar
ticip
an
ts
o
f
o
r
i
g
in
al
Hin
d
i c
lip
s
with
o
u
t so
u
n
d
s
u
p
p
o
r
t.
Ph
ase
1
: So
u
n
d
-
ass
is
ted
Hin
d
i v
id
eo
clip
s
Ph
ase
1
o
f
th
e
d
ata
co
llectio
n
p
r
o
ce
s
s
in
v
o
l
v
es
watc
h
in
g
s
o
u
n
d
-
ass
is
ted
Hin
d
i
m
o
v
ie
v
i
d
eo
clip
s
(
as
s
h
o
wn
in
Fig
u
r
e
3
)
.
Par
ticip
an
ts
in
th
e
f
ir
s
t
p
h
ase
s
aw
f
o
u
r
Hin
d
i
m
o
v
ie
v
id
eo
clip
s
,
ea
ch
o
f
wh
ich
r
ep
r
esen
ted
o
n
e
o
f
th
e
f
o
u
r
ta
r
g
et
em
o
tio
n
s
:
Hap
p
y
,
Fear
,
Sad
,
a
n
d
Neu
t
r
al.
B
ec
au
s
e
th
e
a
u
d
io
i
n
th
ese
f
ilm
s
was
n
o
r
m
al,
v
iewe
r
s
co
u
ld
s
ee
th
e
v
is
u
al
m
ater
ial
in
ad
d
itio
n
to
h
ea
r
in
g
it
.
T
h
e
E
E
G
g
ad
g
et
m
o
n
ito
r
ed
t
h
e
b
r
ain
ac
tiv
ity
in
r
esp
o
n
s
e
to
th
ese
m
u
ltimo
d
al
in
p
u
ts
(
au
d
ito
r
y
an
d
v
is
u
al)
d
u
r
in
g
th
is
p
h
ase.
T
h
e
f
ile
o
f
th
is
p
h
ase
was
s
to
r
ed
as
1
.
csv
,
2
.
csv
,
3
.
csv
,
an
d
4
.
csv
,
wh
ich
s
tan
d
f
o
r
th
e
f
ee
l
in
g
s
o
f
h
ap
p
in
ess
,
f
ea
r
,
s
ad
n
ess
,
an
d
n
eu
tr
ality
,
r
esp
ec
tiv
ely
.
T
h
is
s
tag
e
atte
m
p
ted
to
r
ec
o
r
d
th
e
p
ar
ticip
an
ts
’
au
th
en
tic
em
o
tio
n
al
r
e
ac
tio
n
s
d
u
r
i
n
g
th
eir
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
h
yb
r
id
emo
tio
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
…
(
Ta
r
u
n
K
u
ma
r
)
3183
co
m
p
lete
im
m
er
s
io
n
in
th
e
v
i
s
u
al
an
d
au
r
al
elem
en
ts
o
f
th
e
v
id
eo
clip
s
,
as
b
o
th
v
is
u
al
a
n
d
au
d
ito
r
y
s
tim
u
li
m
ig
h
t a
f
f
ec
t
b
r
ain
wav
e
p
atter
n
s
.
Fig
u
r
e
3
.
No
r
m
al
Hin
d
i
m
o
v
ie
clip
s
Ph
ase
2
: H
ea
r
in
g
-
im
p
air
e
d
o
r
d
ea
f
-
m
u
te
i
n
d
iv
id
u
als v
iewin
g
Hin
d
i v
id
eo
clip
s
Du
r
in
g
th
is
s
tag
e,
ea
ch
p
ar
ti
cip
an
t
was
s
h
o
wn
f
o
u
r
d
is
tin
ct
Hin
d
i
v
id
e
o
s
eg
m
en
ts
(
as
s
h
o
wn
in
Fig
u
r
e
4
)
.
Sin
ce
th
ese
wer
e
m
ad
e
f
o
r
d
ea
f
o
r
d
ea
f
-
m
u
te
p
e
o
p
le,
it
is
lik
ely
t
h
at
th
e
v
id
eo
m
a
ter
ial
r
elied
less
o
n
au
r
al
in
p
u
t
a
n
d
was
m
o
s
tly
v
is
u
al,
p
o
ten
tially
with
s
u
b
titl
es
o
r
m
o
r
e
e
x
p
r
ess
iv
e
v
is
u
al
clu
es.
Du
r
in
g
th
is
p
h
ase,
th
e
in
d
iv
id
u
als’
E
E
G
wav
es
wer
e
g
ath
er
e
d
in
o
r
d
er
to
ex
am
i
n
e
th
e
d
if
f
e
r
en
ce
s
in
em
o
tio
n
a
l
r
ea
ctio
n
s
wh
en
th
e
au
d
io
c
o
m
p
o
n
en
t
was
eith
er
m
in
im
al
o
r
m
is
s
in
g
.
E
E
G
r
ec
o
r
d
in
g
s
o
f
th
is
p
h
ase
wer
e
s
t
o
r
ed
as
5
.
csv
,
6
.
csv
,
7
.
csv
,
an
d
8
.
csv
,
wh
ich
ar
e
m
o
r
e
co
r
r
elate
d
to
th
e
f
o
u
r
em
o
tio
n
s
:
Hap
p
y
,
Fear
,
Sad
,
an
d
Neu
tr
al.
T
h
e
ex
ten
t
t
o
wh
ich
au
d
ito
r
y
in
p
u
t p
la
y
s
a
r
o
le
in
th
e
e
m
o
tio
n
al
p
r
o
ce
s
s
in
g
o
f
t
h
ese
v
id
eo
clip
s
b
y
c
o
n
tr
asti
n
g
th
e
o
u
tc
o
m
es
o
f
th
is
p
h
ase
with
Ph
ase
1
was
estab
lis
h
ed
.
Fig
u
r
e
4
.
Hin
d
i
m
o
v
ie
clip
b
as
ed
o
n
d
ea
f
p
e
r
s
o
n
Ph
ase
3
: M
u
ted
/
s
ilen
tly
watc
h
in
g
th
e
o
r
ig
in
al
Hin
d
i c
lip
s
P
a
r
t
i
c
i
p
an
t
s
r
e
w
a
t
c
h
e
d
t
h
e
f
ir
s
t
b
a
t
ch
o
f
H
i
n
d
i
m
o
v
ie
v
i
d
eo
c
l
ip
s
f
r
o
m
P
h
a
s
e
1
in
th
e
f
in
a
l
p
h
a
s
e,
b
u
t
t
h
i
s
t
i
m
e
w
i
t
h
t
h
e
s
o
u
n
d
m
u
t
ed
(
a
s
s
h
o
wn
i
n
F
i
g
u
r
e
5
)
.
W
i
t
h
j
u
s
t
v
i
s
u
a
l
s
t
i
m
u
l
i
a
v
a
i
la
b
l
e
i
n
th
i
s
s
e
s
s
i
o
n
,
p
a
r
t
i
c
ip
a
n
t
s
m
a
y
d
e
c
ip
h
e
r
th
e
e
m
o
t
io
n
s
s
h
o
wn
i
n
th
e
m
o
v
i
e
s
b
y
c
o
n
c
en
t
r
a
t
in
g
o
n
b
o
d
y
l
an
g
u
ag
e
,
f
a
c
i
a
l
e
x
p
r
e
s
s
i
o
n
s
,
a
n
d
o
th
e
r
n
o
n
-
au
d
i
to
r
y
c
l
u
e
s
.
T
h
i
s
s
t
a
g
e
o
f
f
e
r
e
d
im
p
o
r
t
an
t
in
f
o
r
m
a
t
io
n
o
n
h
o
w
t
h
e
b
r
a
i
n
’
s
e
m
o
t
io
n
a
l r
e
s
p
o
n
s
e
w
a
s
i
m
p
ac
t
e
d
b
y
th
e
la
c
k
o
f
a
u
d
i
t
o
r
y
i
n
p
u
t
.
T
h
i
s
s
t
a
g
e
h
e
l
p
s
i
n
v
e
s
t
i
g
a
t
e
h
o
w
e
f
f
e
c
t
i
v
e
l
y
t
h
e
b
r
a
i
n
c
a
n
r
e
t
a
in
a
n
d
u
n
d
er
s
t
a
n
d
e
m
o
t
io
n
a
l
s
i
g
n
a
l
s
o
n
ly
t
h
r
o
u
g
h
v
i
s
u
a
l
m
a
te
r
i
a
l
b
e
c
au
s
e
t
h
e
p
a
r
t
i
c
ip
an
t
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
8
0
-
3
1
9
0
3184
h
a
d
a
lr
e
ad
y
s
e
en
t
h
e
s
e
f
i
lm
s
w
i
t
h
s
o
u
n
d
.
T
h
i
s
p
h
a
s
e
’
s
E
E
G
d
a
t
a
w
a
s
s
t
o
r
ed
a
s
9
.
c
s
v
,
1
0
.
c
s
v
,
1
1
.
c
s
v
,
an
d
1
2
.
c
s
v
f
i
le
s
.
Fig
u
r
e
5
.
Hin
d
i
m
o
v
ie
clip
b
as
ed
o
n
m
u
ted
2
.
1
.
3
.
Dig
it
a
l
o
r
g
a
niza
t
io
n
T
h
e
E
E
G
s
ig
n
als
in
d
ig
itized
f
o
r
m
wer
e
k
e
p
t
f
o
r
ea
c
h
p
ar
ticip
an
t
in
a
f
o
ld
er
s
tr
u
ctu
r
e
ar
r
a
n
g
ed
as
S0
1
th
r
o
u
g
h
S3
0
,
with
o
n
e
f
o
ld
er
f
o
r
ea
ch
p
ar
ticip
an
t.
T
welv
e
.
c
s
v
f
iles
,
o
n
e
f
o
r
ea
c
h
o
f
th
e
t
h
r
ee
p
h
ases
’
v
a
r
io
u
s
em
o
tio
n
al
s
tates,
ar
e
co
n
tain
e
d
with
in
ea
c
h
f
o
ld
er
.
Fil
es
1
.
c
s
v
to
4
.
csv
co
r
r
esp
o
n
d
to
th
e
i
n
itial
p
h
ase
(
a
u
d
io
-
v
is
u
al
s
tan
d
ar
d
with
s
o
u
n
d
)
,
f
iles
5
.
csv
to
8
.
csv
r
ep
r
esen
t
th
e
s
ec
o
n
d
p
h
ase
(
v
i
d
eo
s
f
o
r
d
ea
f
o
r
d
ea
f
-
m
u
te
in
d
iv
id
u
als),
a
n
d
f
iles
9
.
csv
to
1
2
.
csv
co
r
r
esp
o
n
d
to
th
e
th
ir
d
p
h
ase
(
o
r
i
g
in
al
v
id
e
o
s
with
m
u
ted
au
d
i
o
)
.
2
.
1
.
4
.
I
nte
rpre
t
a
t
io
n a
nd
un
dersta
nd
ing
B
r
ain
ac
tiv
ities
v
ar
y
as
p
ar
tic
ip
an
ts
ex
p
er
ien
ce
em
o
tio
n
s
th
r
o
u
g
h
d
is
tin
ct
s
en
s
o
r
y
c
h
an
n
e
ls
(
au
d
io
-
v
is
u
al,
v
is
u
al
-
o
n
l
y
f
o
r
d
ea
f
o
r
m
u
te,
an
d
v
is
u
al
-
o
n
ly
f
o
llo
wi
n
g
ex
p
o
s
u
r
e
to
th
e
au
d
io
-
v
is
u
al)
an
d
ex
am
in
e
th
e
E
E
G
d
ata
f
r
o
m
th
ese
th
r
ee
s
ta
g
es.
E
E
G
d
ata
f
r
o
m
ea
ch
c
o
n
d
itio
n
m
ay
b
e
co
m
p
ar
ed
t
o
ex
tr
ac
t p
r
o
p
er
ties
,
s
u
ch
as
b
r
ain
wav
e
p
atter
n
s
o
r
f
r
eq
u
en
cy
b
an
d
s
,
wh
ich
ar
e
u
n
iq
u
e
to
a
ce
r
tain
em
o
tio
n
al
s
tate.
T
o
cr
ea
te
r
eliab
le
em
o
tio
n
d
etec
tio
n
m
o
d
els b
ased
o
n
E
E
G
d
ata,
th
ese
ch
a
r
ac
ter
is
tics
m
ay
f
u
r
th
er
b
e
an
aly
s
e
d
an
d
class
if
ied
.
2
.
1
.
5
.
Cha
lleng
es
Fig
u
r
e
6
d
em
o
n
s
tr
ates
th
e
ex
p
er
im
en
tal
s
etu
p
f
o
r
th
e
s
elf
-
cr
e
ated
E
E
G
d
ataset.
Ma
in
tain
in
g
co
n
s
is
ten
t
d
ata
q
u
ality
a
m
o
n
g
p
a
r
ticip
an
ts
,
r
ed
u
cin
g
ar
tifa
cts
(
in
cl
u
d
in
g
e
y
e
b
lin
k
s
an
d
m
u
s
cle
m
o
v
em
e
n
ts
)
,
an
d
m
an
ag
in
g
in
te
r
-
s
u
b
ject
v
ar
ia
b
ilit
y
wer
e
th
e
ch
allen
g
es
with
th
e
s
elf
-
cr
ea
ted
E
E
G
d
atasets
.
T
o
g
u
ar
an
tee
r
eliab
ilit
y
,
s
tr
in
g
en
t
p
r
o
ce
d
u
r
es
wer
e
f
o
llo
wed
d
u
r
in
g
th
e
E
E
G
s
ig
n
al
r
ec
o
r
d
in
g
p
r
o
ce
s
s
s
u
ch
as
u
n
if
o
r
m
s
tim
u
lu
s
p
r
esen
tatio
n
a
n
d
r
eg
u
lated
am
b
ie
n
t
co
n
d
itio
n
s
.
Pr
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
f
o
r
im
p
r
o
v
in
g
s
ig
n
al
q
u
ality
wer
e
q
u
ite
r
eliab
le.
C
r
o
s
s
-
v
alid
atin
g
em
o
tio
n
la
b
els
with
p
ar
ticip
an
t
f
ee
d
b
ac
k
p
r
eser
v
ed
in
ter
-
r
ater
r
eliab
ilit
y
.
I
n
o
r
d
e
r
to
en
s
u
r
e
th
at
th
e
m
o
d
el
is
g
en
er
aliza
b
le
ac
r
o
s
s
p
ar
ticip
an
ts
an
d
s
ess
io
n
s
,
r
o
b
u
s
tn
ess
i
s
ac
h
iev
ed
b
y
f
ea
tu
r
e
ex
tr
ac
tio
n
th
at
c
ap
t
u
r
e
s
a
r
an
g
e
o
f
s
ig
n
al
ch
ar
ac
te
r
is
tics
an
d
L
OOCV c
r
o
s
s
-
v
alid
atio
n
.
Fig
u
r
e
6
.
A
p
ar
ticip
an
t in
E
E
G
s
ig
n
al
r
ec
o
r
d
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
h
yb
r
id
emo
tio
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
…
(
Ta
r
u
n
K
u
ma
r
)
3185
2
.
2
.
Da
t
a
pre
-
pro
ce
s
s
ing
S
i
n
c
e
e
a
c
h
i
n
d
i
v
i
d
u
a
l
h
as
a
u
n
i
q
u
e
i
m
p
e
d
a
n
c
e
o
n
t
h
e
e
le
c
t
r
o
d
e
s
a
n
d
a
d
is
ti
n
c
t
s
i
g
n
al
s
t
r
e
n
g
t
h
,
n
o
r
m
a
l
i
z
a
t
i
o
n
f
a
l
ls
w
it
h
i
n
t
h
e
p
r
e
-
p
r
o
c
e
s
s
i
n
g
s
t
e
p
a
n
d
m
u
s
t
b
e
d
o
n
e
f
i
r
s
t
.
A
d
d
i
t
i
o
n
a
ll
y
,
t
h
e
r
e
a
r
e
v
a
r
i
a
t
i
o
n
s
i
n
t
h
e
s
i
g
n
a
l
b
e
t
we
e
n
a
c
q
u
i
s
it
i
o
n
d
a
y
s
f
o
r
t
h
e
s
a
m
e
p
e
r
s
o
n
.
B
e
f
o
r
e
c
a
t
e
g
o
r
i
z
a
ti
o
n
,
a
l
l
d
a
t
a
s
h
o
u
l
d
b
e
s
t
a
n
d
a
r
d
i
z
e
d
o
r
n
o
r
m
a
l
i
z
e
d
.
T
h
r
e
e
m
a
j
o
r
n
o
r
m
a
l
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
a
r
e
Z
-
s
c
o
r
e
n
o
r
m
a
l
i
z
at
i
o
n
,
M
i
n
i
m
u
m
-
M
a
x
i
m
u
m
n
o
r
m
a
l
i
z
a
t
i
o
n
,
a
n
d
d
e
c
i
m
a
l
s
ca
l
i
n
g
n
o
r
m
a
l
i
z
a
ti
o
n
.
T
h
e
s
e
t
h
r
e
e
a
p
p
r
o
a
c
h
e
s
a
r
e
i
d
e
n
t
i
c
al
t
o
o
n
e
a
n
o
t
h
e
r
.
T
h
e
Z
-
s
c
o
r
e
N
o
r
m
a
li
z
a
ti
o
n
t
e
c
h
n
i
q
u
e
w
as
a
p
p
l
i
e
d
i
n
t
h
is
s
t
u
d
y
.
T
h
e
s
t
a
n
d
a
r
d
d
e
v
ia
t
i
o
n
a
n
d
m
e
a
n
w
e
r
e
u
s
e
d
t
o
s
t
a
n
d
a
r
d
i
z
e
t
h
e
d
at
a
.
F
o
r
a
l
l
d
at
a
,
t
h
e
s
ta
n
d
a
r
d
d
e
v
i
a
t
i
o
n
i
s
o
n
e
a
n
d
t
h
e
m
e
a
n
i
s
0
.
T
o
d
e
t
e
r
m
i
n
e
t
h
e
Z
-
s
c
o
r
e
o
f
e
a
c
h
v
a
r
i
a
b
l
e
,
s
u
b
t
r
a
ct
i
o
n
o
f
t
h
e
m
e
a
n
w
as
m
a
d
e
f
r
o
m
e
a
c
h
d
at
a
p
o
i
n
t
a
n
d
t
h
e
n
d
i
v
i
d
e
d
b
y
t
h
e
s
t
a
n
d
a
r
d
d
e
v
i
at
i
o
n
.
2
.
3
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
Af
ter
E
E
G
s
ig
n
als
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
is
th
e
n
ex
t
s
tep
.
Fre
q
u
en
c
y
-
d
o
m
ain
p
r
o
p
e
r
ties
ar
e
v
er
y
im
p
o
r
tan
t
f
o
r
u
n
d
er
s
tan
d
in
g
th
e
p
atter
n
s
o
f
b
r
ain
a
ctiv
ity
r
elate
d
to
d
if
f
e
r
en
t
em
o
tio
n
s
d
u
r
in
g
E
E
G
em
o
tio
n
d
etec
tio
n
.
T
h
e
b
a
n
d
p
o
wer
r
atio
s
p
la
y
an
im
p
o
r
tan
t r
o
le
in
th
e
b
r
ain
-
co
m
p
u
ter
in
te
r
f
ac
e
o
r
it d
ep
en
d
s
o
n
m
en
tal
s
tates.
B
y
co
m
p
u
tin
g
r
atio
s
b
etwe
en
d
if
f
er
en
t
f
r
eq
u
en
cy
b
a
n
d
s
b
y
an
aly
s
in
g
p
o
wer
d
is
tr
ib
u
tio
n
ac
r
o
s
s
th
ese
b
an
d
s
,
s
ev
e
r
al
e
m
o
tio
n
al
s
tates
ca
n
b
e
d
etec
te
d
[
1
4
]
,
[
1
5
]
.
T
h
ese
r
atio
s
h
elp
to
d
is
tin
g
u
is
h
s
tates
lik
e
h
ap
p
in
ess
,
f
ea
r
,
s
ad
n
ess
,
an
d
n
eu
tr
ality
as
th
ey
in
d
icate
h
o
w
v
ar
y
in
g
th
e
am
p
litu
d
e
o
f
b
r
ain
wav
es
f
o
r
d
if
f
er
en
t
em
o
tio
n
s
.
T
h
is
m
eth
o
d
o
lo
g
y
in
cr
ea
s
es
th
e
r
eliab
ili
ty
o
f
id
en
tif
y
in
g
em
o
tio
n
as
m
o
r
e
im
p
o
r
tan
ce
is
g
iv
en
to
s
u
b
tle
v
ar
iatio
n
s
b
etwe
en
f
r
eq
u
e
n
cy
d
o
m
ain
s
in
b
r
ain
wav
e
ac
tiv
ity
.
Delta
ac
tiv
ity
p
r
ed
o
m
i
n
ates
in
d
ee
p
s
leep
,
th
eta
b
a
n
d
a
p
p
ea
r
s
in
a
v
er
y
r
elax
e
d
,
co
n
tem
p
lativ
e,
d
r
o
wsy
,
o
r
m
ed
itativ
e
s
tate.
Peo
p
le
wh
o
ar
e
awa
k
e
an
d
p
a
y
in
g
v
e
r
y
ca
lm
,
p
ass
iv
e
atten
tio
n
ar
e
k
n
o
wn
t
o
ex
h
i
b
it
th
e
a
lp
h
a
b
an
d
th
at
is
m
o
r
e
p
r
o
n
o
u
n
ce
d
w
h
e
n
th
eir
ey
es
ar
e
o
p
e
n
ed
.
W
h
e
n
f
o
cu
s
ed
o
r
th
i
n
k
in
g
ac
tiv
el
y
,
th
e
b
eta
b
an
d
is
v
is
ib
le.
T
h
e
b
eta
b
an
d
is
v
is
ib
l
e
wh
en
an
x
iety
is
p
r
ed
o
m
in
an
t
,
ac
tiv
e,
an
d
r
elax
ed
.
C
o
n
ce
n
tr
atio
n
m
ay
b
e
f
o
u
n
d
in
th
e
g
a
m
m
a
b
a
n
d
[
1
6
]
,
[
1
7
]
.
Hig
h
d
elta
p
o
wer
in
d
icate
s
th
at
th
e
b
r
ain
is
in
a
v
er
y
r
elax
ed
s
tate
o
r
th
e
r
ec
o
v
e
r
y
p
h
ase
in
d
ee
p
s
leep
.
Hig
h
er
th
eta
p
o
wer
in
d
icate
s
r
ed
u
ce
d
al
er
tn
ess
,
p
er
h
ap
s
in
a
s
tate
o
f
d
ay
d
r
ea
m
in
g
o
r
lig
h
t
s
leep
.
I
n
cr
ea
s
ed
alp
h
a
p
o
wer
i
s
ac
co
m
p
an
ied
b
y
a
ca
lm
,
r
ela
x
ed
,
b
u
t a
wak
e
s
tate,
s
u
ch
as c
lo
s
in
g
th
e
e
y
es in
a
q
u
iet
r
o
o
m
.
B
eta
p
o
wer
in
cr
e
ases
with
in
cr
ea
s
ed
m
en
tal
ac
tiv
ity
,
atten
tio
n
,
o
r
f
o
cu
s
.
I
t
m
ig
h
t
b
e
ass
o
ciate
d
with
an
x
iety
o
r
s
tr
ess
in
ex
tr
em
e
ca
s
es.
Hig
h
g
am
m
a
p
o
w
er
was
o
f
ten
s
ee
n
to
ac
c
o
m
p
an
y
h
ig
h
lev
e
ls
o
f
co
n
ce
n
tr
atio
n
,
lear
n
in
g
,
o
r
p
r
o
ce
s
s
in
g
.
E
E
G
d
ata
was
an
aly
s
ed
f
o
r
th
e
f
ir
s
t
Hin
d
i
m
o
v
ie
clip
s
f
o
r
p
ar
ticip
an
t
S0
1
.
Af
ter
p
r
o
ce
s
s
in
g
th
e
E
E
G
d
ata
f
r
o
m
0
1
.
csv
in
MA
T
L
AB
R
2
0
1
7
b
,
th
e
v
alu
es
o
f
v
a
r
io
u
s
b
an
d
p
o
wer
s
f
o
r
ea
ch
ch
an
n
el
ar
e
d
is
p
lay
ed
in
Fig
u
r
e.
7
.
T
h
e
X
-
ax
is
r
ep
r
esen
ts
th
e
ch
an
n
el
in
Gr
ap
h
ical
r
ep
r
esen
tatio
n
a
n
d
th
e
Y
-
ax
is
r
ep
r
esen
ts
th
e
p
o
wer
.
Fig
u
r
e
7
.
E
E
G
b
an
d
p
o
wer
f
o
r
ea
ch
ch
an
n
el
f
o
r
S0
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
8
0
-
3
1
9
0
3186
2
.
4
.
Sig
na
l
cla
s
s
if
ica
t
io
n
A
f
t
e
r
t
h
e
c
o
m
p
l
et
i
o
n
o
f
f
e
at
u
r
e
e
x
t
r
a
ct
i
o
n
f
o
r
e
ac
h
p
a
r
t
ic
i
p
an
t
,
t
h
e
p
r
o
c
e
d
u
r
e
o
f
c
l
ass
i
f
i
c
ati
o
n
c
o
m
e
s
u
n
d
e
r
c
o
n
s
i
d
e
r
a
t
i
o
n
.
T
h
e
s
a
m
e
p
r
o
c
e
s
s
as
m
e
n
t
i
o
n
e
d
i
n
F
i
g
u
r
e
7
n
e
e
d
s
t
o
b
e
a
p
p
l
ie
d
f
o
r
s
0
2
t
o
s
3
0
p
a
r
t
ic
i
p
a
n
ts
a
n
d
f
r
e
q
u
e
n
c
i
e
s
o
f
E
E
G
l
i
k
e
alp
h
a
,
b
e
t
a
,
t
h
et
a
,
d
e
lt
a
,
a
n
d
p
o
we
r
;
t
h
e
p
r
o
c
e
d
u
r
e
o
f
c
l
as
s
i
f
i
c
a
tio
n
b
e
g
i
n
s
.
V
a
r
i
o
u
s
c
l
a
s
s
i
f
ie
r
s
a
r
e
e
m
p
l
o
y
e
d
i
n
t
h
e
r
e
s
e
a
r
c
h
b
as
e
d
o
n
h
o
w
w
el
l
t
h
e
y
f
u
n
c
t
i
o
n
i
n
E
E
G
a
p
p
l
i
c
at
i
o
n
s
,
a
n
d
t
h
e
i
r
e
f
f
i
c
a
c
y
i
s
as
s
e
s
s
e
d
t
o
d
i
r
e
c
t
t
h
e
o
p
t
i
m
i
z
a
t
i
o
n
p
r
o
c
e
d
u
r
e
s
u
g
g
e
s
t
e
d
,
l
ik
e
a
r
t
i
f
i
ci
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
KNN
,
l
i
n
e
a
r
S
V
M
,
S
V
M
wi
t
h
r
a
d
i
al
b
a
s
i
s
f
u
n
c
ti
o
n
s
,
d
e
c
is
i
o
n
t
r
e
es
,
l
i
n
ea
r
d
i
s
c
r
i
m
i
n
a
n
t
a
n
a
l
y
s
i
s
,
a
n
d
n
a
i
v
e
B
a
y
es
[
1
8
]
.
T
h
is
s
tu
d
y
o
f
f
er
s
a
f
u
s
io
n
o
f
SVM
an
d
KNN,
two
d
is
tin
ct
ca
teg
o
r
izatio
n
tech
n
iq
u
es.
SVM
an
d
KNN,
two
h
y
b
r
id
class
if
ier
s
,
wer
e
ch
o
s
en
d
u
e
to
th
eir
co
m
p
lem
en
tar
y
a
d
v
an
ta
g
es
in
E
E
G
-
b
ased
em
o
tio
n
class
if
icatio
n
.
W
h
ile
KNN
s
u
cc
ess
f
u
lly
ca
p
tu
r
es
lo
ca
l
p
atte
r
n
s
,
SVM
is
ad
ep
t
at
h
an
d
lin
g
h
ig
h
-
d
im
en
s
io
n
al
d
ata
with
s
tr
o
n
g
g
l
o
b
al
d
ec
is
io
n
lim
its
.
G
r
id
s
ea
r
ch
with
L
OOCV
wa
s
u
s
ed
to
o
p
tim
ize
t
h
e
h
y
p
e
r
p
ar
am
ete
r
s
f
o
r
KNN
an
d
SVM
in
o
r
d
er
t
o
g
u
ar
a
n
tee
g
e
n
er
aliza
tio
n
.
T
h
e
h
y
b
r
i
d
m
o
d
el,
wh
ich
was
ad
ju
s
ted
f
o
r
b
alan
ce
d
co
n
tr
i
b
u
tio
n
s
,
in
teg
r
ated
t
h
eir
o
u
tp
u
ts
b
y
weig
h
ted
v
o
tin
g
.
T
h
e
SVM
-
KNN
h
y
b
r
id
m
o
d
el
o
u
tp
er
f
o
r
m
e
d
p
r
ev
io
u
s
c
o
m
b
in
atio
n
s
,
ac
co
r
d
in
g
to
em
p
ir
ical
e
v
alu
atio
n
s
,
p
r
o
v
id
in
g
s
tr
o
n
g
ac
cu
r
ac
y
an
d
F1
-
s
co
r
es
ac
r
o
s
s
em
o
tio
n
s
(
h
a
p
p
y
,
f
ea
r
,
s
ad
,
an
d
n
eu
tr
al
)
an
d
s
u
cc
ess
f
u
lly
h
a
n
d
lin
g
p
ar
ticip
an
t a
n
d
s
ess
io
n
v
ar
iab
ilit
y
.
E
v
er
y
in
d
iv
id
u
al
was
ex
p
o
s
ed
to
f
o
u
r
d
if
f
er
en
t
k
in
d
s
o
f
em
o
tio
n
al
s
tim
u
li.
On
ce
th
e
r
aw
E
E
G
d
ata
was
p
r
e
-
p
r
o
ce
s
s
ed
,
f
ea
tu
r
e
ex
t
r
ac
tio
n
was
u
s
ed
t
o
r
etr
ie
v
e
in
f
o
r
m
atio
n
f
r
o
m
ev
e
r
y
c
h
an
n
el
a
t
ev
er
y
ep
o
c
h
.
Du
e
to
th
eir
co
m
p
lem
en
tar
y
ch
a
r
ac
ter
is
tics
,
S
VM
an
d
KNN
class
if
ier
s
ar
e
o
f
ten
h
y
b
r
i
d
ized
f
o
r
em
o
ti
o
n
id
en
tific
atio
n
u
s
in
g
E
E
G
d
ata.
SVM
ca
n
id
en
tify
th
e
id
ea
l
h
y
p
er
p
lan
e
th
at
d
i
v
id
es
d
if
f
er
e
n
t
class
b
o
u
n
d
ar
ies.
On
th
e
o
t
h
er
h
an
d
,
KNN
is
an
i
n
s
tan
ce
-
b
ased
l
ea
r
n
i
n
g
al
g
o
r
it
h
m
th
at
d
o
es
n
o
t
d
e
p
en
d
o
n
an
y
s
p
ec
if
i
c
s
tatis
tical
d
is
tr
ib
u
tio
n
o
f
th
e
in
p
u
t
s
p
ac
e.
Mo
r
eo
v
er
,
b
ei
n
g
n
o
n
-
p
a
r
am
et
r
ic,
it
ad
ap
ts
to
lo
ca
l
p
atter
n
s
a
n
d
ten
d
s
to
d
o
well
with
n
o
is
y
d
ata.
As
b
o
th
th
e
SVM
an
d
KNN
clas
s
if
ier
s
co
m
p
lem
en
t
ea
ch
o
th
er
well,
th
ey
ar
e
id
ea
l
f
o
r
th
e
class
if
icatio
n
o
f
em
o
tio
n
s
f
r
o
m
E
E
G
d
ata.
SVM
p
er
f
o
r
m
s
r
ath
er
well
in
h
ig
h
-
d
im
e
n
s
io
n
al
en
v
ir
o
n
m
e
n
ts
b
ec
au
s
e
th
e
id
en
tific
atio
n
o
f
b
est
d
ec
is
io
n
b
o
u
n
d
ar
ies
y
ield
s
s
tab
le
s
ep
ar
atio
n
b
etwe
en
em
o
tio
n
al
s
tates.
I
t
als
o
m
ak
es
g
o
o
d
u
s
e
o
f
k
er
n
el
f
u
n
ctio
n
s
to
m
an
ag
e
n
o
n
-
lin
ea
r
i
n
ter
ac
tio
n
s
.
Alth
o
u
g
h
KNN
is
in
tu
itiv
e
an
d
ad
a
p
ts
well
to
lo
ca
l
p
atter
n
s
,
ev
en
n
o
is
y
o
r
o
v
er
lap
p
in
g
d
ata
,
s
in
ce
it
m
ak
es
d
ec
is
io
n
s
b
ased
o
n
n
ei
g
h
b
o
u
r
in
g
ex
am
p
les,
its
h
y
b
r
id
s
tr
ateg
y
,
wh
en
co
m
b
in
e
d
,
im
p
r
o
v
es
class
if
icatio
n
ac
cu
r
ac
y
f
o
r
th
e
m
a
n
y
in
tr
icate
p
atter
n
s
p
r
esen
t in
E
E
G
d
ata
t
o
f
in
d
th
e
b
alan
ce
b
etwe
en
g
lo
b
al
d
ec
is
io
n
-
m
ak
in
g
an
d
l
o
ca
l a
d
ap
tat
io
n
.
2
.
4
.
1
.
Appro
a
ch
t
o
hy
brid cla
s
s
if
iers
T
h
e
ex
tr
ac
ted
f
ea
tu
r
e
s
et
o
f
E
E
G
d
ata
ca
n
b
e
r
ep
r
esen
ted
as
(
1
)
,
=
{
1
,
2
,
…
}
(
1
)
r
ep
r
esen
ts
th
e
f
ea
tu
r
e
v
ec
to
r
o
f
th
e
i
th
s
am
p
le
an
d
=
{
1
,
2
,
…
}
is
th
e
c
o
llectio
n
o
f
lab
els
f
o
r
all
th
e
r
elate
d
em
o
tio
n
s
.
T
h
e
SVM
s
ee
k
s
to
id
en
tify
t
h
e
h
y
p
er
p
lan
e
o
r
d
ec
is
io
n
b
o
r
d
er
th
at
m
ax
im
ally
d
iv
id
es
t
wo
class
es
,
wh
er
e
.
+
=
0
.
T
h
e
f
o
llo
win
g
is
th
e
SVM
o
b
jectiv
e
f
u
n
ctio
n
:
1
2
‖
‖
2
s
u
b
ject
to
(
⋅
+
)
≥
1
∀
I
(
2
)
w
h
en
th
e
lab
el
is
th
e
weig
h
t
v
ec
to
r
is
w
,
th
e
in
p
u
t
f
ea
tu
r
e
v
ec
to
r
is
an
d
th
e
b
ias
ter
m
is
b
.
T
h
e
d
ec
is
io
n
b
o
u
n
d
ar
y
n
ee
d
ed
f
o
r
class
if
icatio
n
is
p
r
o
v
i
d
ed
b
y
th
e
o
p
tim
i
za
tio
n
p
r
o
b
lem
’
s
s
o
lu
tio
n
.
KNN
u
s
es
th
e
KNN
ap
p
r
o
ac
h
t
o
class
if
y
an
in
p
u
t
i
n
s
tan
ce
x
i
.
T
h
e
m
etr
ic
o
f
d
is
tan
ce
(
,
)
is
u
tili
ze
d
to
d
eter
m
in
e
th
ese
n
eig
h
b
o
r
s
,
an
d
it
is
o
f
ten
E
u
clid
ea
n
d
is
tan
ce
.
T
h
e
f
o
llo
win
g
f
ac
to
r
s
ar
e
u
s
ed
to
ass
ig
n
th
e
lab
el
y
i
.
=
∑
(
=
)
∈
(
)
(
3
)
wh
er
e
th
e
in
d
icato
r
f
u
n
ctio
n
is
d
en
o
ted
b
y
I
(
⋅
)
an
d
th
e
co
llect
io
n
o
f
KNN
is
r
ep
r
esen
te
d
b
y
N
(
x
i
).
2
.
4
.
2
.
T
he
s
t
ra
t
eg
y
o
f
hy
bridi
za
t
io
n
I
n
th
e
h
y
b
r
i
d
m
o
d
el,
KNN
class
if
ies
in
s
tan
ce
s
clo
s
e
to
th
e
d
ec
is
io
n
b
o
r
d
e
r
,
wh
er
e
SVM
co
u
ld
h
a
v
e
tr
o
u
b
le,
t
o
r
ef
i
n
e
th
e
i
n
itial
class
if
icatio
n
m
ad
e
b
y
th
e
SV
M.
T
h
is
co
m
b
i
n
atio
n
im
p
r
o
v
e
s
ac
cu
r
ac
y
f
o
r
E
E
G
-
b
ased
em
o
tio
n
id
e
n
tific
atio
n
t
ask
s
b
y
c
o
m
b
in
in
g
th
e
g
l
o
b
al
d
ec
is
io
n
-
m
a
k
in
g
p
o
wer
o
f
S
VM
with
th
e
l
o
ca
l
f
lex
ib
ilit
y
o
f
KNN
.
T
o
im
p
r
o
v
e
class
if
icatio
n
ac
cu
r
ac
y
,
th
i
s
h
y
b
r
id
class
if
icatio
n
m
eth
o
d
ap
p
lied
SVM
an
d
KNN
u
s
in
g
th
e
m
ajo
r
ity
v
o
tin
g
m
eth
o
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
h
yb
r
id
emo
tio
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
…
(
Ta
r
u
n
K
u
ma
r
)
3187
2
.
5
.
Cla
s
s
if
ica
t
io
n
o
utput
I
n
g
en
er
al,
E
E
G
d
atasets
ar
e
u
s
u
ally
m
o
d
est
in
s
ize
b
u
t
h
ig
h
ly
d
im
en
s
io
n
al.
T
ec
h
n
iq
u
es
lik
e
leav
e
-
one
-
o
u
t
cr
o
s
s
-
v
alid
atio
n
ar
e
q
u
ite
ef
f
ec
tiv
e
in
t
h
e
ev
al
u
atio
n
o
f
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
els
f
o
r
em
o
tio
n
id
en
tific
atio
n
b
ased
o
n
E
E
G
s
ig
n
als.
L
OOCV
en
s
u
r
es
th
at
ea
ch
s
am
p
le
o
f
th
e
E
E
G
s
ig
n
al
h
as
b
ee
n
u
s
ed
o
n
ce
as
a
te
s
t
p
o
in
t
an
d
also
as
a
tr
a
in
in
g
s
et,
wh
ich
c
o
m
p
letes
an
ex
h
au
s
tiv
e
ass
ess
m
en
t
o
f
g
en
er
aliza
b
ilit
y
f
o
r
th
e
m
o
d
el.
W
h
y
Use L
OOCV to
r
ec
o
g
n
ize
em
o
tio
n
s
?
E
E
G
d
atasets
u
s
u
ally
h
av
e
f
ewe
r
tr
ials
an
d
s
u
b
ject
s
am
p
les,
esp
ec
ially
in
th
e
ca
s
e
o
f
em
o
tio
n
d
etec
tio
n
.
T
h
is
is
v
ital
in
s
m
all
d
atasets
as
L
OOC
V
[
1
4
]
allo
ws
th
e
m
o
d
el
to
b
e
tr
ai
n
ed
o
n
n
-
1
s
am
p
les,
u
s
in
g
all
th
e
d
atasets
b
o
th
f
o
r
tr
ain
i
n
g
an
d
v
alid
atio
n
.
T
h
e
em
o
tio
n
al
s
tates
in
E
E
G
s
ig
n
als
ar
e
f
ai
n
t
an
d
o
v
e
r
lap
p
in
g
;
th
u
s
,
f
in
d
in
g
th
em
is
n
o
t a
n
ea
s
y
task
.
C
o
m
p
ar
ed
t
o
p
r
ev
io
u
s
k
-
f
o
l
d
ap
p
r
o
ac
h
es,
L
OOCV g
u
ar
an
tees th
at
ea
ch
s
am
p
le
is
ev
alu
ated
,
g
iv
in
g
a
m
o
r
e
th
o
r
o
u
g
h
an
d
p
r
ec
is
e
esti
m
atio
n
o
f
th
e
class
if
ier
’
s
p
er
f
o
r
m
an
ce
.
L
OOCV
m
in
im
izes
th
e
d
an
g
er
o
f
o
v
e
r
f
itti
n
g
,
p
ar
ticu
lar
ly
i
n
s
itu
atio
n
s
wh
er
e
em
o
tio
n
-
s
p
ec
i
f
ic
E
E
G
s
ig
n
als
d
if
f
er
b
etwe
en
p
eo
p
le
o
r
s
ess
io
n
s
,
b
y
tr
ain
in
g
o
n
alm
o
s
t th
e
wh
o
le
d
ataset
f
o
r
ea
ch
iter
atio
n
.
Hy
b
r
id
class
if
ier
s
,
s
u
ch
as
SVM
-
KNN
in
co
n
ju
n
ctio
n
with
L
OOCV,
p
r
o
v
id
e
ac
cu
r
ate
i
n
s
ig
h
ts
ab
o
u
t
th
e
p
o
ten
tial
o
f
th
e
m
o
d
el
to
g
en
er
alize
to
n
ew,
u
n
s
ee
n
d
ata
f
o
r
em
o
tio
n
r
ec
o
g
n
itio
n
.
Su
ch
m
o
d
els
ca
n
g
en
er
alize
em
o
tio
n
r
ec
o
g
n
iti
o
n
to
f
r
esh
an
d
u
n
test
ed
d
at
a.
Af
ter
ev
er
y
iter
atio
n
o
f
th
e
f
in
al
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es,
wh
ich
in
clu
d
e
th
e
F1
-
s
co
r
e,
ac
cu
r
ac
y
,
an
d
p
r
ec
is
io
n
,
ar
e
av
er
a
g
ed
,
a
n
d
an
o
b
je
ctiv
e
ass
es
s
m
en
t
o
f
th
e
class
if
ier
’
s
ca
p
ac
ity
to
id
e
n
tify
em
o
tio
n
s
f
r
o
m
E
E
G
d
ata
is
p
r
o
v
id
ed
[
1
9
]
–
[
2
2
]
.
2
.
6
.
P
er
f
o
r
m
a
nce
m
e
t
ric
T
h
e
ac
cu
r
ac
y
o
f
th
e
class
if
ie
r
in
th
e
p
r
esen
ted
s
tu
d
y
was
d
eter
m
in
ed
b
y
ass
ess
in
g
it
s
c
ap
ac
ity
to
ac
cu
r
ately
d
etec
t
em
o
tio
n
s
f
r
o
m
E
E
G
d
ata
(
4
)
.
T
h
e
p
e
r
ce
n
ta
g
e
o
f
p
r
o
p
er
ly
ca
teg
o
r
ized
ca
s
es
ac
r
o
s
s
all
s
am
p
le
s
will
b
e
ca
lcu
lated
.
T
h
is
ac
cu
r
a
cy
m
etr
ic
aid
s
in
m
ea
s
u
r
in
g
h
o
w
well
th
e
p
r
o
p
o
s
ed
s
y
s
tem
r
e
co
g
n
izes
em
o
tio
n
s
[
2
3
]
.
=
+
+
+
+
(
4
)
T
h
e
m
o
d
el
th
at
co
r
r
ec
tly
class
if
ies
as
p
o
s
itiv
e
is
ca
lled
tr
u
e
p
o
s
itiv
e
(
T
P).
I
n
f
o
r
m
atio
n
th
at
th
e
m
o
d
el
ac
c
u
r
ately
id
en
tifie
s
as
n
eg
ativ
e
is
ca
lle
d
tr
u
e
n
e
g
ativ
e
(
T
N)
.
T
h
e
m
o
d
el
th
at
in
co
r
r
ec
tly
class
if
ies
f
r
o
m
th
e
n
eg
ativ
e
ca
teg
o
r
y
as
p
o
s
itiv
e
is
k
n
o
wn
as
f
alse
p
o
s
it
iv
e
(
FP
)
.
Fal
s
e
n
eg
ativ
e
(
FN)
d
ata
is
p
r
o
d
u
ce
d
b
y
th
e
m
o
d
el
wh
en
it e
r
r
o
n
eo
u
s
ly
class
if
ies p
o
s
iti
v
e
ca
teg
o
r
y
d
ata
as n
e
g
ativ
e
[
1
5
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
r
e
s
e
ar
c
h
er
s
d
e
v
e
l
o
p
e
d
a
h
y
b
r
i
d
em
o
t
io
n
-
id
en
t
i
f
i
c
a
t
io
n
s
y
s
t
e
m
b
a
s
ed
o
n
K
-
Ne
a
r
e
s
t N
e
i
g
h
b
o
u
r
s
a
n
d
S
V
M
c
l
a
s
s
i
f
i
e
r
s
u
s
i
n
g
E
E
G
d
a
ta
.
F
o
r
th
e
s
a
k
e
o
f
ex
p
er
im
e
n
t
a
t
io
n
,
th
e
d
e
v
e
lo
p
ed
s
y
s
te
m
w
a
s
ap
p
l
i
ed
t
o
E
E
G
d
a
ta
a
cq
u
i
r
e
d
f
r
o
m
th
i
r
ty
s
u
b
je
c
t
s
a
t
t
w
e
lv
e
tr
i
a
l
s
i
n
t
en
d
ed
t
o
e
v
o
k
e
f
o
u
r
d
i
s
t
i
n
c
t
em
o
t
i
o
n
a
l
co
n
d
i
t
i
o
n
s
:
f
e
a
r
,
s
a
d
n
e
s
s
,
h
a
p
p
i
n
e
s
s
,
a
n
d
n
eu
t
r
a
l
i
ty
.
T
h
e
P
r
o
p
o
s
ed
m
o
d
e
l
wo
r
k
e
d
w
i
t
h
th
e
e
i
g
h
t
ch
a
n
n
e
l
s
o
f
t
h
e
E
E
G
r
e
c
o
r
d
in
g
s
an
d
ap
p
l
i
ed
L
O
OC
V
f
o
r
t
h
e
a
s
s
e
s
s
m
e
n
t
o
f
t
h
e
h
y
b
r
i
d
c
l
a
s
s
i
f
i
e
r
.
F
r
o
m
n
o
r
m
al
i
z
e
d
E
E
G
d
a
t
a
,
we
o
b
t
a
in
e
d
f
r
e
q
u
en
c
y
-
d
o
m
a
in
ch
a
r
a
c
te
r
i
s
t
i
c
s
.
T
h
e
f
o
u
r
p
r
ed
o
m
i
n
an
t
f
r
eq
u
en
c
y
b
a
n
d
s
f
o
r
w
h
i
c
h
w
e
co
m
p
u
t
ed
t
h
e
b
an
d
p
o
w
e
r
ar
e
d
e
l
t
a
(
1
-
4
H
z
)
,
t
h
e
t
a
(
4
-
8
H
z
)
,
a
l
p
h
a
(
8
-
1
2
H
z)
,
an
d
b
e
t
a
(
1
2
-
3
0
Hz
)
[
2
4
]
,
[
2
5
]
.
T
h
e
s
e
f
r
e
q
u
en
c
y
b
a
n
d
s
a
r
e
r
e
l
a
t
ed
to
v
ar
i
o
u
s
s
t
a
t
e
s
o
f
co
g
n
i
t
i
v
e
a
n
d
em
o
t
io
n
a
l
ch
an
g
e
s
,
th
e
y
a
r
e
w
e
l
l
-
k
n
o
w
n
in
E
E
G
r
e
s
e
a
r
c
h
.
B
an
d
p
o
w
er
i
n
t
h
e
s
e
f
r
eq
u
e
n
cy
b
an
d
s
w
a
s
c
al
c
u
l
a
t
ed
f
o
r
e
a
ch
t
r
i
a
l
an
d
ch
an
n
e
l
th
a
t
m
ad
e
t
h
e
f
e
a
t
u
r
e
s
e
t
to
b
e
u
s
ed
f
o
r
c
l
as
s
i
f
i
c
a
t
i
o
n
.
B
y
u
s
i
n
g
t
h
e
d
a
t
as
e
t
o
f
E
E
G
,
th
e
h
y
b
r
id
c
l
a
s
s
if
i
e
r
i
s
t
e
s
t
ed
in
t
h
e
M
A
T
L
A
B
c
o
d
e.
E
E
G
d
a
t
a
o
f
a
l
l
p
a
r
t
i
c
ip
a
n
t
s
i
s
r
e
ad
f
r
o
m
co
r
r
e
s
p
o
n
d
in
g
.
c
s
v
f
i
l
e
s
,
p
r
e
-
p
r
o
c
e
s
s
i
n
g
,
a
n
d
e
x
t
r
a
c
t
io
n
o
f
ch
a
r
a
c
t
e
r
i
s
t
i
c
s
.
T
h
e
ac
c
u
r
a
cy
o
f
th
e
s
y
s
t
e
m
wa
s
a
s
s
e
s
s
e
d
u
s
i
n
g
l
ea
v
e
-
o
n
e
-
o
u
t
c
r
o
s
s
-
v
a
l
i
d
a
t
io
n
(
L
O
O
C
V
)
.
E
a
ch
d
a
t
a
s
e
t
s
a
m
p
l
e
w
a
s
u
t
i
l
i
z
ed
o
n
ce
a
s
a
te
s
t
s
a
m
p
l
e
i
n
L
O
O
C
V
,
w
i
t
h
t
h
e
r
em
a
i
n
in
g
d
a
t
a
b
e
i
n
g
u
s
e
d
f
o
r
t
r
a
in
i
n
g
.
B
e
c
a
u
s
e
i
t
m
a
k
e
s
t
h
e
m
o
s
t
u
s
e
o
f
t
h
e
av
ai
l
a
b
l
e
d
a
t
a,
th
i
s
v
a
l
i
d
a
t
i
o
n
ap
p
r
o
a
c
h
i
s
e
s
p
e
c
i
a
l
ly
h
e
l
p
f
u
l
f
o
r
t
i
n
y
d
a
t
a
s
e
t
s
.
T
h
e
m
o
d
e
l
w
a
s
tr
a
in
e
d
u
s
in
g
t
h
e
h
y
b
r
i
d
S
V
M
-
K
N
N
m
e
th
o
d
f
o
r
e
v
er
y
L
O
O
C
V
i
t
e
r
a
t
i
o
n
.
B
o
t
h
c
l
a
s
s
i
f
ie
r
s
w
er
e
u
s
ed
to
p
r
e
d
i
c
t
em
o
t
io
n
a
c
cu
r
a
cy
,
a
n
d
a
m
a
j
o
r
i
t
y
v
o
t
e
w
as
u
s
e
d
t
o
m
a
k
e
th
e
f
i
n
a
l
c
h
o
i
c
e.
A
f
t
e
r
t
h
e
c
r
o
s
s
-
v
a
l
i
d
a
t
io
n
p
r
o
c
e
d
u
r
e,
ac
c
u
r
a
cy
w
a
s
d
e
t
er
m
in
e
d
.
T
h
e
D
E
AP
[
5
]
,
D
R
E
A
M
E
R
[
1
9
]
,
M
A
H
N
O
B
-
H
C
I
[
2
6
]
,
SE
E
D
[
2
7
]
,
a
n
d
A
M
I
G
O
S
[
2
8
]
d
a
t
a
s
e
t
s
s
e
r
v
ed
a
s
i
n
s
p
ir
a
t
i
o
n
f
o
r
t
h
e
r
e
co
r
d
i
n
g
a
n
d
p
r
o
c
e
s
s
i
n
g
o
f
a
n
E
E
G
d
a
ta
s
e
t
f
o
r
em
o
t
io
n
i
d
en
t
i
f
i
ca
t
i
o
n
.
E
m
o
t
io
n
s
s
u
c
h
a
s
h
a
p
p
i
n
e
s
s
,
s
a
d
n
e
s
s
,
f
e
ar
,
a
n
d
n
e
u
tr
a
l
i
t
y
we
r
e
ev
o
k
ed
b
y
H
in
d
i
v
i
d
eo
c
l
ip
s
.
T
h
e
U
n
i
co
r
n
B
l
a
c
k
8
-
c
h
an
n
e
l
d
ev
i
c
e
w
a
s
u
s
e
d
t
o
r
e
c
o
r
d
E
E
G
d
a
t
a
.
I
n
M
A
T
L
A
B
R
2
0
1
7
a,
al
l
t
h
e
s
t
e
p
s
ar
e
p
er
f
o
r
m
ed
to
p
r
e
-
p
r
o
c
e
s
s
th
e
E
E
G
d
a
t
a
,
ex
t
r
a
c
t
f
e
a
tu
r
e
s
,
a
n
d
c
l
a
s
s
i
f
y
th
e
e
m
o
t
i
o
n
a
l
s
t
a
t
e
s
w
i
t
h
a
lg
o
r
i
t
h
m
s
s
u
ch
a
s
S
V
M
a
n
d
K
N
N
i
n
v
o
lv
ed
.
T
h
en
,
a
cc
u
r
a
cy
i
s
c
o
m
p
u
t
ed
b
y
e
q
u
a
t
i
o
n
4
.
E
E
G
s
i
g
n
a
l
s
w
e
r
e
a
c
q
u
i
r
ed
w
i
th
a
d
e
v
ic
e
w
i
t
h
6
4
c
h
a
n
n
e
l
s
f
r
o
m
4
0
i
n
d
i
v
id
u
a
l
s
i
n
[
8
]
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
1
8
0
-
3
1
9
0
3188
E
E
G
d
a
t
a
w
a
s
r
e
co
r
d
e
d
f
r
o
m
3
0
p
ar
t
i
c
ip
a
n
t
s
in
[
1
0
]
d
u
r
i
n
g
t
h
e
d
a
t
a
-
g
a
t
h
e
r
i
n
g
p
r
o
c
e
s
s
.
T
h
e
co
m
p
a
r
i
s
o
n
o
f
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
w
i
th
o
t
h
e
r
a
l
g
o
r
i
th
m
s
i
s
s
h
o
w
n
i
n
T
a
b
l
e
2
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
p
r
o
p
o
s
ed
m
o
d
el
C
o
n
t
r
i
b
u
t
i
o
n
D
a
t
a
s
e
t
P
h
y
s
i
o
l
o
g
i
c
al
s
i
g
n
a
l
s
A
v
e
r
a
g
e
a
c
c
u
r
a
c
y
M
o
d
e
l
Emo
t
i
o
n
c
l
a
ss
i
f
y
Zh
u
e
t
a
l
.
[
8
]
O
w
n
d
a
t
a
se
t
s
EEG
7
0
.
2
%
H
P
Th
r
e
e
C
l
a
s
ses
p
o
s
i
t
i
v
e
,
n
e
u
t
r
a
l
,
n
e
g
a
t
i
v
e
5
0
.
1
5
%
H
P
F
i
v
e
C
l
a
ss
e
s
h
a
p
p
y
,
n
e
u
t
r
a
l
,
s
a
d
,
a
n
g
r
y
,
f
e
a
r
f
u
l
7
2
.
0
5
%
N
H
P
Th
r
e
e
C
l
a
ss
e
s
p
o
s
i
t
i
v
e
,
n
e
u
t
r
a
l
,
n
e
g
a
t
i
v
e
5
1
.
5
3
%
N
H
P
F
i
v
e
C
l
a
ss
e
s
h
a
p
p
y
,
n
e
u
t
r
a
l
,
s
a
d
,
a
n
g
r
y
,
f
e
a
r
f
u
l
Ji
n
e
t
a
l
.
[
1
0
]
O
w
n
d
a
t
a
se
t
s
EEG
4
0
.
8
%
H
P
F
i
v
e
C
l
a
ss
e
s
h
a
p
p
i
n
e
ss,
n
e
u
t
r
a
l
,
s
a
d
n
e
ss,
f
e
a
r
a
n
d
a
n
g
e
r
P
r
o
p
o
se
d
w
o
r
k
S
e
l
f
-
c
r
e
a
t
e
d
d
a
t
a
se
t
EEG
6
0
.
8
3
2
%
N
H
P
F
o
u
r
C
l
a
sses
h
a
p
p
y
,
f
e
a
r
,
sa
d
,
a
n
d
n
e
u
t
r
a
l
*
H
P
st
a
n
d
s f
o
r
h
e
a
r
i
n
g
-
i
mp
a
i
r
e
d
p
a
r
t
i
c
i
p
a
n
t
s.
*
N
H
P
st
a
n
d
s f
o
r
N
o
n
-
h
e
a
r
i
n
g
-
i
m
p
a
i
r
e
d
p
a
r
t
i
c
i
p
a
n
t
s
.
4.
CO
NCLU
SI
O
N
T
h
e
em
o
tio
n
al
-
v
i
d
eo
clip
-
in
d
u
ce
d
E
E
G
em
o
tio
n
r
ec
o
g
n
itio
n
tech
n
iq
u
e
was
p
r
esen
ted
in
th
is
s
tu
d
y
.
T
h
ir
ty
v
o
lu
n
teer
s
'
E
E
G
s
ig
n
als
wer
e
r
ec
o
r
d
e
d
as
th
ey
watc
h
ed
th
e
v
a
r
io
u
s
Hin
d
i v
id
eo
clip
s
.
W
ith
f
r
eq
u
en
c
y
-
d
o
m
ain
f
ea
tu
r
e
ex
tr
ac
tio
n
,
a
h
y
b
r
id
SVM
-
KNN
class
if
ier
,
an
d
Z
-
s
co
r
e
n
o
r
m
aliza
tio
n
f
o
r
p
r
ep
r
o
ce
s
s
in
g
,
t
h
e
s
u
g
g
ested
m
eth
o
d
p
r
o
v
e
d
s
u
cc
ess
f
u
l
in
id
en
tify
i
n
g
e
m
o
tio
n
s
,
with
L
OOCV
g
u
ar
an
teein
g
a
n
ac
cu
r
ate
ac
c
u
r
ac
y
esti
m
ate.
T
ab
le
2
d
is
p
lay
s
th
e
p
r
o
p
o
s
ed
m
o
d
el
f
in
d
i
n
g
s
,
wh
i
ch
in
d
icate
an
ac
cu
r
ac
y
o
f
6
0
.
8
3
2
%
o
n
av
er
a
g
e
f
o
r
th
e
f
o
u
r
e
m
o
tio
n
al
class
es
-
h
ap
p
in
ess
,
s
ad
n
ess
,
f
ea
r
,
an
d
n
e
u
tr
al.
B
ased
o
n
E
E
G
d
ata
a
n
d
b
an
d
p
o
wer
r
atio
s
,
th
is
ac
cu
r
ac
y
s
u
g
g
ests
a
m
o
d
e
s
t p
er
f
o
r
m
an
ce
l
e
v
e
l
i
n
d
i
f
f
e
r
e
n
t
i
a
t
i
n
g
b
e
tw
e
e
n
e
m
o
t
i
o
n
s
.
A
l
th
o
u
g
h
t
h
e
o
u
t
c
o
m
es
s
h
o
w
t
h
a
t
t
h
e
m
et
h
o
d
c
a
n
d
i
s
t
in
g
u
i
s
h
b
e
t
w
e
e
n
d
i
s
t
i
n
c
t
e
m
o
t
i
o
n
a
l
s
ta
t
es
w
el
l
,
t
h
e
r
e
is
s
t
i
ll
s
p
ac
e
f
o
r
d
e
v
e
l
o
p
m
e
n
t
.
F
u
r
t
h
e
r
r
e
s
ea
r
c
h
e
n
d
e
a
v
o
r
s
m
ay
o
p
t
i
m
i
z
e
f
e
a
t
u
r
e
e
x
t
r
a
c
ti
o
n
t
ec
h
n
i
q
u
e
s
,
i
n
v
e
s
t
i
g
a
t
e
m
o
r
e
i
n
t
r
i
c
a
t
e
c
at
e
g
o
r
i
z
a
ti
o
n
s
c
h
e
m
e
s
,
o
r
i
n
t
e
g
r
a
t
e
s
u
p
p
l
em
e
n
t
a
r
y
i
n
f
o
r
m
a
t
i
o
n
t
o
a
u
g
m
e
n
t
e
m
o
t
i
o
n
i
d
e
n
t
i
f
i
c
a
ti
o
n
’
s
g
e
n
e
r
a
l
p
r
e
c
i
s
i
o
n
a
n
d
r
e
s
i
li
e
n
ce
.
T
h
e
p
l
a
n
i
n
t
h
e
f
u
t
u
r
e
s
h
o
u
l
d
b
e
t
o
i
n
c
r
e
a
s
e
t
h
e
s
i
z
e
o
f
o
u
r
d
a
t
a
s
e
t
w
it
h
o
t
h
e
r
l
a
n
g
u
a
g
e
v
i
d
e
o
c
l
i
p
s
a
n
d
f
o
c
u
s
o
n
h
y
b
r
i
d
f
e
at
u
r
e
e
x
t
r
ac
t
io
n
a
p
p
r
o
a
c
h
e
s
an
d
class
if
icati
o
n
tech
n
iq
u
es
f
o
r
p
eo
p
le
with
an
d
with
o
u
t
h
ea
r
in
g
p
r
o
b
lem
s
in
s
u
b
s
eq
u
en
t
s
tu
d
ie
s
o
r
b
ased
o
n
v
id
eo
clip
s
,
wh
ich
ar
e
b
ased
o
n
o
th
er
lo
ca
l
la
n
g
u
ag
es
.
Pro
p
o
s
ed
d
atasets
,
lik
e
s
ev
er
al
s
tan
d
ar
d
d
atasets
DR
E
AM
E
R
,
AM
I
G
OS,
SEE
D
,
an
d
MA
HNOB
-
HC
I
,
m
ay
b
e
m
a
d
e
p
u
b
licly
av
ailab
le
f
o
r
r
esear
ch
r
ea
s
o
n
s
,
esp
ec
ially
if
cu
ttin
g
-
ed
g
e
m
eth
o
d
s
ar
e
u
s
ed
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
is
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
T
ar
u
n
Ku
m
ar
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
ajen
d
r
a
Ku
m
ar
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
am
C
h
an
d
r
a
Sin
g
h
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
h
yb
r
id
emo
tio
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
…
(
Ta
r
u
n
K
u
ma
r
)
3189
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
th
is
s
tu
d
y
ar
e
o
p
en
ly
a
v
ailab
le
in
Me
n
d
el
ey
at
d
o
i:
1
0
.
1
7
6
3
2
/
5
8
r
y
d
c6
v
wc.
1
.
RE
F
E
R
E
NC
E
S
[
1
]
Z.
M
a
o
,
X
.
Zh
a
o
,
a
n
d
Y
.
S
o
n
g
,
“
R
e
se
a
r
c
h
o
f
E
EG
-
b
a
s
e
d
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
o
r
t
h
e
d
e
a
f
w
i
t
h
f
e
a
t
u
r
e
f
u
s
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Bi
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
5
,
n
o
.
3
,
p
p
.
2
1
6
–
2
3
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
5
0
4
/
I
JB
ET
.
2
0
2
4
.
1
3
8
9
7
3
.
[
2
]
A
.
M
a
h
m
o
u
d
I
b
r
a
h
i
m
a
n
d
M
.
A
b
e
d
M
o
h
a
mm
e
d
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
n
a
d
v
a
n
c
e
m
e
n
t
s
i
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
p
p
r
o
a
c
h
e
s
a
n
d
f
u
t
u
r
e
p
e
r
sp
e
c
t
i
v
e
s
f
o
r
e
a
r
l
y
d
i
a
g
n
o
si
s
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
M
a
t
h
e
m
a
t
i
c
s,
S
t
a
t
i
s
t
i
c
s,
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
,
p
p
.
1
7
3
–
1
8
2
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
5
9
5
4
3
/
i
j
m
scs.
v
2
i
.
8
9
1
5
.
[
3
]
F
.
H
o
u
e
t
a
l
.
,
“
D
e
e
p
f
e
a
t
u
r
e
p
y
r
a
mi
d
n
e
t
w
o
r
k
f
o
r
EEG
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
M
e
a
s
u
rem
e
n
t
,
v
o
l
.
2
0
1
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
su
r
e
me
n
t
.
2
0
2
2
.
1
1
1
7
2
4
.
[
4
]
J.
A
.
C
h
r
i
st
e
n
s
e
n
,
J.
S
i
s,
A
.
M
.
K
u
l
k
a
r
n
i
,
a
n
d
M
.
C
h
a
t
t
e
r
j
e
e
,
“
Ef
f
e
c
t
s
o
f
a
g
e
a
n
d
h
e
a
r
i
n
g
l
o
ss
o
n
t
h
e
r
e
c
o
g
n
i
t
i
o
n
o
f
e
m
o
t
i
o
n
s
i
n
sp
e
e
c
h
,
”
E
a
r &
H
e
a
r
i
n
g
,
v
o
l
.
4
0
,
n
o
.
5
,
p
p
.
1
0
6
9
–
1
0
8
3
,
S
e
p
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
9
7
/
A
U
D
.
0
0
0
0
0
0
0
0
0
0
0
0
0
6
9
4
.
[
5
]
S
.
K
o
e
l
s
t
r
a
e
t
a
l
.
,
“
D
EA
P
:
A
d
a
t
a
b
a
s
e
f
o
r
e
mo
t
i
o
n
a
n
a
l
y
si
s
;
u
s
i
n
g
p
h
y
si
o
l
o
g
i
c
a
l
s
i
g
n
a
l
s,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
Af
f
e
c
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
1
8
–
3
1
,
J
a
n
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
-
A
F
F
C
.
2
0
1
1
.
1
5
.
[
6
]
M
.
F
.
D
o
r
m
a
n
e
t
a
l
.
,
“
A
p
p
r
o
x
i
ma
t
i
o
n
s
t
o
t
h
e
v
o
i
c
e
o
f
a
c
o
c
h
l
e
a
r
i
m
p
l
a
n
t
:
E
x
p
l
o
r
a
t
i
o
n
s
w
i
t
h
s
i
n
g
l
e
-
si
d
e
d
d
e
a
f
l
i
st
e
n
e
r
s
,
”
T
re
n
d
s i
n
H
e
a
ri
n
g
,
v
o
l
.
2
4
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
7
7
/
2
3
3
1
2
1
6
5
2
0
9
2
0
0
7
9
.
[
7
]
Z.
B
a
i
e
t
a
l
.
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
r
e
si
d
u
a
l
n
e
t
w
o
r
k
d
r
i
v
e
n
b
y
s
p
a
t
i
a
l
-
f
r
e
q
u
e
n
c
y
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
o
f
EEG
r
e
c
o
r
d
e
d
f
r
o
m
h
e
a
r
i
n
g
-
i
mp
a
i
r
e
d
a
d
u
l
t
s
i
n
r
e
sp
o
n
se
t
o
v
i
d
e
o
c
l
i
p
s,
”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
1
5
2
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
m
e
d
.
2
0
2
2
.
1
0
6
3
4
4
.
[
8
]
M
.
Z
h
u
,
H
.
Ji
n
,
Z.
B
a
i
,
Z.
L
i
,
a
n
d
Y
.
S
o
n
g
,
“
I
mag
e
-
e
v
o
k
e
d
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
o
r
h
e
a
r
i
n
g
-
i
m
p
a
i
r
e
d
s
u
b
j
e
c
t
s
w
i
t
h
EEG
s
i
g
n
a
l
s,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
1
2
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
1
2
5
4
6
1
.
[
9
]
S.
-
K
.
K
i
m
a
n
d
H
.
-
B
.
K
a
n
g
,
“
A
n
a
n
a
l
y
s
i
s
o
f
smar
t
p
h
o
n
e
o
v
e
r
u
se
r
e
c
o
g
n
i
t
i
o
n
i
n
t
e
r
ms
o
f
e
mo
t
i
o
n
s
u
si
n
g
b
r
a
i
n
w
a
v
e
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
2
7
5
,
p
p
.
1
3
9
3
–
1
4
0
6
,
Ja
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
7
.
0
9
.
0
8
1
.
[
1
0
]
H
.
Ji
n
,
Y
.
S
o
n
g
,
Z
.
M
a
o
,
Z.
B
a
i
,
Z.
Li
,
a
n
d
Y
.
C
h
e
n
,
“
R
e
c
o
g
n
i
t
i
o
n
a
n
d
r
e
sea
r
c
h
o
f
p
i
c
t
u
r
e
-
i
n
d
u
c
e
d
e
m
o
t
i
o
n
b
a
se
d
o
n
EEG
s
i
g
n
a
l
s,
”
i
n
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
Me
c
h
a
t
ro
n
i
c
s
a
n
d
Au
t
o
m
a
t
i
o
n
(
I
C
MA
)
,
2
0
2
2
,
p
p
.
4
4
4
–
4
4
9
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
M
A
5
4
5
1
9
.
2
0
2
2
.
9
8
5
6
3
5
7
.
[
1
1
]
Y
.
Y
a
n
g
,
Q
.
G
a
o
,
Y
.
S
o
n
g
,
X
.
S
o
n
g
,
Z.
M
a
o
,
a
n
d
J.
Li
u
,
“
I
n
v
e
st
i
g
a
t
i
n
g
o
f
d
e
a
f
e
m
o
t
i
o
n
c
o
g
n
i
t
i
o
n
p
a
t
t
e
r
n
b
y
EEG
a
n
d
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
c
o
mb
i
n
a
t
i
o
n
,
”
I
E
EE
J
o
u
r
n
a
l
o
f
B
i
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
r
m
a
t
i
c
s
,
v
o
l
.
2
6
,
n
o
.
2
,
p
p
.
5
8
9
–
5
9
9
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JB
H
I
.
2
0
2
1
.
3
0
9
2
4
1
2
.
[
1
2
]
T.
K
u
m
a
r
,
R
.
K
u
m
a
r
,
a
n
d
R
.
C
.
S
i
n
g
h
,
“
A
n
EEG
d
a
t
a
s
e
t
f
o
r
b
r
a
i
n
w
a
v
e
r
e
c
o
r
d
i
n
g
d
u
r
i
n
g
e
m
o
t
i
o
n
e
l
i
c
i
t
a
t
i
o
n
v
i
a
v
i
d
e
o
c
l
i
p
s,”
Me
n
d
e
l
e
y
D
a
t
a
,
V1
,
2
0
2
4
.
[
1
3
]
Z
.
T
i
a
n
,
D
.
L
i
,
Y
.
S
o
n
g
,
Q
.
G
a
o
,
Q
.
K
a
n
g
,
a
n
d
Y
.
Y
a
n
g
,
“
E
E
G
-
b
a
s
e
d
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
o
f
d
e
a
f
s
u
b
j
e
c
t
s
b
y
i
n
t
e
g
r
a
t
e
d
g
e
n
e
t
i
c
f
i
r
e
f
l
y
a
l
g
o
r
i
t
h
m
,
”
I
E
E
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
s
t
r
u
m
e
n
t
a
t
i
o
n
a
n
d
M
e
a
s
u
r
e
m
e
n
t
,
v
o
l
.
7
0
,
p
p
.
1
–
1
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
T
I
M
.
2
0
2
1
.
3
1
2
1
4
7
3
.
[
1
4
]
H
.
Zh
e
n
g
a
n
d
X
.
L
i
,
“
A
n
EEG
-
b
a
s
e
d
f
r
a
mew
o
r
k
o
f
E
M
D
a
n
d
C
N
N
f
o
r
a
r
o
u
sa
l
a
n
d
v
a
l
e
n
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
Re
se
a
r
c
h
o
n
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
0
,
n
o
.
2
,
p
p
.
3
8
7
–
3
9
5
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
2
6
0
0
-
0
2
4
-
0
0
3
5
1
-
w.
[
1
5
]
A
.
H
a
g
,
D
.
H
a
n
d
a
y
a
n
i
,
T.
P
i
l
l
a
i
,
T
.
M
a
n
t
o
r
o
,
M
.
H
.
K
i
t
,
a
n
d
F
.
A
l
-
S
h
a
r
g
i
e
,
“
EEG
me
n
t
a
l
s
t
r
e
ss
a
sses
sme
n
t
u
s
i
n
g
h
y
b
r
i
d
m
u
l
t
i
-
d
o
m
a
i
n
f
e
a
t
u
r
e
se
t
s
o
f
f
u
n
c
t
i
o
n
a
l
c
o
n
n
e
c
t
i
v
i
t
y
n
e
t
w
o
r
k
a
n
d
t
i
me
-
f
r
e
q
u
e
n
c
y
f
e
a
t
u
r
e
s
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
1
8
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
1
8
6
3
0
0
.
[
1
6
]
A
.
A
.
-
S
i
s
o
d
e
,
“
E
mo
t
i
o
n
s a
n
d
b
r
a
i
n
w
a
v
e
s,”
T
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
d
i
a
n
Ps
y
c
h
o
l
o
g
y
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
1
4
–
1
8
,
2
0
1
6
.
[
1
7
]
P
.
A
.
A
b
h
a
n
g
,
B
.
W
.
G
a
w
a
l
i
,
a
n
d
S
.
C
.
M
e
h
r
o
t
r
a
,
“
Te
c
h
n
o
l
o
g
i
c
a
l
b
a
si
c
s
o
f
E
EG
r
e
c
o
r
d
i
n
g
a
n
d
o
p
e
r
a
t
i
o
n
o
f
a
p
p
a
r
a
t
u
s,”
i
n
I
n
t
r
o
d
u
c
t
i
o
n
t
o
EEG
-
a
n
d
S
p
e
e
c
h
-
B
a
se
d
Em
o
t
i
o
n
Re
c
o
g
n
i
t
i
o
n
,
E
l
se
v
i
e
r
,
2
0
1
6
,
p
p
.
1
9
–
5
0
.
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
12
-
8
0
4
4
9
0
-
2
.
0
0
0
0
2
-
6.
[
1
8
]
Z.
A
.
A
.
A
l
y
a
ss
e
r
i
e
t
a
l
.
,
“
EEG
c
h
a
n
n
e
l
s
e
l
e
c
t
i
o
n
b
a
se
d
u
s
e
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
v
i
a
i
mp
r
o
v
e
d
f
l
o
w
e
r
p
o
l
l
i
n
a
t
i
o
n
a
l
g
o
r
i
t
h
m,”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
6
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
2
0
6
2
0
9
2
.
[
1
9
]
S
.
K
a
t
s
i
g
i
a
n
n
i
s
a
n
d
N
.
R
a
mza
n
,
“
D
R
EA
M
E
R
:
A
d
a
t
a
b
a
se
f
o
r
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
t
h
r
o
u
g
h
E
EG
a
n
d
E
C
G
s
i
g
n
a
l
s
f
r
o
m
w
i
r
e
l
e
ss
l
o
w
-
c
o
st
o
f
f
-
t
h
e
-
sh
e
l
f
d
e
v
i
c
e
s,”
I
EE
E
J
o
u
r
n
a
l
o
f
Bi
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
2
,
n
o
.
1
,
p
p
.
9
8
–
1
0
7
,
Ja
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
JB
H
I
.
2
0
1
7
.
2
6
8
8
2
3
9
.
[
2
0
]
Z.
W
a
n
g
,
R
.
Ji
a
o
,
a
n
d
H
.
J
i
a
n
g
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
W
T
-
S
V
M
i
n
h
u
man
-
c
o
m
p
u
t
e
r
i
n
t
e
r
a
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
N
e
w
Me
d
i
a
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
1
2
1
–
1
3
0
,
2
0
2
0
,
d
o
i
:
1
0
.
3
2
6
0
4
/
j
n
m
.
2
0
2
0
.
0
1
0
6
7
4
.
[
2
1
]
A
.
M
e
r
t
a
n
d
A
.
A
k
a
n
,
“
Emo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
EEG
si
g
n
a
l
s
b
y
u
si
n
g
m
u
l
t
i
v
a
r
i
a
t
e
e
m
p
i
r
i
c
a
l
m
o
d
e
d
e
c
o
m
p
o
s
i
t
i
o
n
,
”
P
a
t
t
e
r
n
An
a
l
y
si
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
8
1
–
8
9
,
F
e
b
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
0
4
4
-
0
1
6
-
0
5
6
7
-
6.
[
2
2
]
T.
K
u
m
a
r
,
R
.
K
u
m
a
r
,
a
n
d
R
.
C
h
a
n
d
r
a
S
i
n
g
h
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
e
mo
t
i
o
n
s
r
e
c
o
g
n
i
t
i
o
n
mo
d
e
l
u
s
i
n
g
p
e
r
i
p
h
e
r
a
l
si
g
n
a
l
s,”
I
n
d
o
n
e
si
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
7
,
n
o
.
2
,
p
p
.
9
7
6
–
9
8
4
,
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
9
7
6
-
9
8
4
.
[
2
3
]
R
.
C
.
J
o
y
e
t
a
l
.
,
“
D
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
A
D
H
D
f
r
o
m
E
EG
s
i
g
n
a
l
s
u
si
n
g
t
u
n
a
b
l
e
Q
-
f
a
c
t
o
r
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m,”
J
o
u
rn
a
l
o
f
S
e
n
so
rs
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
7
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
3
5
9
0
9
7
3
.
[
2
4
]
D
.
L
i
e
t
a
l
.
,
“
Emo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
o
f
su
b
j
e
c
t
s
w
i
t
h
h
e
a
r
i
n
g
i
m
p
a
i
r
me
n
t
b
a
s
e
d
o
n
f
u
s
i
o
n
o
f
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
a
n
d
EEG
t
o
p
o
g
r
a
p
h
i
c
map
,
”
I
EE
E
T
r
a
n
s
a
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
.
3
1
,
p
p
.
4
3
7
–
4
4
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
R
E.
2
0
2
2
.
3
2
2
5
9
4
8
.
[
2
5
]
Y
.
S
u
,
Y
.
L
i
u
,
Y
.
X
i
a
o
,
J
.
M
a
,
a
n
d
D
.
Li
,
“
A
r
e
v
i
e
w
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
m
e
t
h
o
d
s
e
n
a
b
l
e
d
mu
s
i
c
-
e
v
o
k
e
d
EEG
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
a
n
d
t
h
e
i
r
a
p
p
l
i
c
a
t
i
o
n
s,”
F
ro
n
t
i
e
rs
i
n
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
1
8
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s.
2
0
2
4
.
1
4
0
0
4
4
4
.
[
2
6
]
M
.
S
o
l
e
y
ma
n
i
,
J.
Li
c
h
t
e
n
a
u
e
r
,
T
.
P
u
n
,
a
n
d
M
.
P
a
n
t
i
c
,
“
A
m
u
l
t
i
m
o
d
a
l
d
a
t
a
b
a
se
f
o
r
a
f
f
e
c
t
r
e
c
o
g
n
i
t
i
o
n
a
n
d
i
m
p
l
i
c
i
t
t
a
g
g
i
n
g
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
A
f
f
e
c
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
4
2
–
5
5
,
J
a
n
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
-
A
F
F
C
.
2
0
1
1
.
2
5
.
[
2
7
]
W
e
i
-
L
o
n
g
Z
h
e
n
g
a
n
d
B
a
o
-
Li
a
n
g
Lu
,
“
I
n
v
e
st
i
g
a
t
i
n
g
c
r
i
t
i
c
a
l
f
r
e
q
u
e
n
c
y
b
a
n
d
s
a
n
d
c
h
a
n
n
e
l
s
f
o
r
EEG
-
b
a
se
d
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Au
t
o
n
o
m
o
u
s
M
e
n
t
a
l
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
1
6
2
–
1
7
5
,
S
e
p
.
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TA
M
D
.
2
0
1
5
.
2
4
3
1
4
9
7
.
[
2
8
]
J.
A
.
M
i
r
a
n
d
a
-
C
o
r
r
e
a
,
M
.
K
.
A
b
a
d
i
,
N
.
S
e
b
e
,
a
n
d
I
.
P
a
t
r
a
s,
“
A
M
I
G
O
S
:
A
d
a
t
a
se
t
f
o
r
a
f
f
e
c
t
,
p
e
r
so
n
a
l
i
t
y
a
n
d
m
o
o
d
r
e
s
e
a
r
c
h
o
n
i
n
d
i
v
i
d
u
a
l
s
a
n
d
g
r
o
u
p
s
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Af
f
e
c
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
2
,
n
o
.
2
,
p
p
.
4
7
9
–
4
9
3
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TA
F
F
C
.
2
0
1
8
.
2
8
8
4
4
6
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.