I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
ar
y
20
2
5
,
p
p
.
976
~
984
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
2
.
pp
976
-
9
8
4
976
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
M
a
chine learning
-
ba
sed emo
tions
r
ecog
nition mo
del
using
periphera
l sig
na
ls
T
a
run K
um
a
r
1
,
Ra
j
endra
K
um
a
r
2
,
Ra
m
Cha
nd
ra
Sin
g
h
1
1
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
s
e
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
2
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
S
h
a
r
d
a
U
n
i
v
e
r
s
i
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
J
u
n
3
,
2
0
2
4
R
ev
is
ed
Sep
11
,
2
0
2
4
Acc
ep
ted
Sep
29
,
2
0
2
4
Th
is
w
o
rk
p
r
o
p
o
se
s
a
sy
ste
m
fo
r
e
m
o
ti
o
n
re
c
o
g
n
i
ti
o
n
u
sin
g
f
o
u
r
p
e
rip
h
e
ra
l
sig
n
a
ls
e
lec
tro
m
y
o
g
ra
p
h
y
,
g
a
lv
a
n
ic
sk
i
n
re
sp
o
n
se
,
b
l
o
o
d
v
o
lu
m
e
p
u
lse
,
a
n
d
re
sp
iratio
n
.
P
e
rip
h
e
ra
l
sig
n
a
ls
c
a
n
n
o
t
b
e
m
o
d
ifi
e
d
,
u
n
li
k
e
o
t
h
e
r
e
x
p
re
ss
io
n
li
k
e
v
o
ice
a
n
d
fa
c
ial
e
x
p
re
ss
io
n
.
Th
e
p
r
o
p
o
se
d
m
e
th
o
d
is
a
p
p
li
e
d
to
t
h
e
DEAP
d
a
tas
e
ts
to
v
e
rify
t
h
e
a
c
c
u
ra
c
y
o
f
e
m
o
ti
o
n
re
c
o
g
n
i
ti
o
n
.
T
h
e
p
ro
p
o
se
d
m
o
d
e
l
fo
c
u
se
s o
n
a
c
c
u
ra
c
y
a
n
d
F
1
-
sc
o
re
.
DEAP
d
a
tas
e
t
h
a
s m
o
re
s
ig
n
a
ls b
u
t
o
n
l
y
th
i
rty
-
se
v
e
n
fe
a
t
u
re
s
fro
m
fo
u
r
p
e
rip
h
e
ra
l
si
g
n
a
ls
we
re
e
x
trac
t
e
d
fo
r
e
a
c
h
trail
a
n
d
e
a
c
h
v
id
e
o
.
On
t
h
e
DEAP
d
a
tas
e
ts,
th
e
imp
lem
e
n
tatio
n
f
o
u
n
d
th
a
t
t
h
e
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
f
o
r
a
ro
u
sa
l,
v
a
len
c
e
,
li
k
i
n
g
,
a
n
d
d
o
m
in
a
n
c
e
wa
s,
re
sp
e
c
ti
v
e
ly
,
8
0
%
,
7
5
%
,
7
1
%
,
a
n
d
7
8
%
.
F
o
r
two
c
las
se
s
o
f
p
ro
b
lem
s,
th
e
c
o
rre
sp
o
n
d
in
g
F
1
-
sc
o
re
s
f
o
r
a
ro
u
sa
l,
v
a
len
c
e
,
li
k
in
g
,
a
n
d
d
o
m
in
a
n
c
e
a
re
0
.
5
0
,
0
.
4
9
,
0
.
4
7
,
a
n
d
0
.
4
7
.
T
h
e
p
ro
p
o
se
d
m
o
d
e
l
wa
s
imp
le
m
e
n
ted
i
n
M
ATLAB
R2
0
1
7
a
.
K
ey
w
o
r
d
s
:
B
VP
DE
AP d
ataset
E
m
o
tio
n
r
ec
o
g
n
itio
n
GSR
s
ig
n
al
Ma
ch
in
e
lear
n
in
g
Per
ip
h
er
als s
ig
n
als
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
Sch
o
o
l o
f
B
asic Scie
n
ce
s
an
d
R
esear
ch
,
Sh
ar
d
a
Un
iv
er
s
ity
Gr
ea
ter
No
id
a,
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
T
ec
h
n
o
lo
g
y
f
o
r
r
ec
o
g
n
izin
g
an
d
co
m
p
r
eh
e
n
d
in
g
h
u
m
an
em
o
tio
n
s
is
r
ef
er
r
ed
to
as
em
o
tio
n
r
ec
o
g
n
itio
n
tech
n
i
q
u
es.
T
h
es
e
m
eth
o
d
s
ca
n
b
e
g
en
e
r
ally
d
iv
id
ed
in
to
c
ateg
o
r
ies
lik
e
f
ac
ial
ex
p
r
ess
io
n
an
aly
s
is
,
v
o
ice
an
d
s
p
ee
ch
a
n
aly
s
is
,
tex
t
an
d
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
,
p
h
y
s
io
lo
g
ical
s
en
s
o
r
s
,
an
d
g
estu
r
e
an
d
b
o
d
y
lan
g
u
ag
e
a
n
aly
s
is
.
T
h
e
an
aly
s
is
o
f
f
ac
e
ch
a
r
ac
ter
is
tics
an
d
ex
p
r
ess
io
n
s
u
s
in
g
c
o
m
p
u
ter
v
is
io
n
a
n
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
is
r
ef
er
r
ed
to
as
f
ac
ial
ex
p
r
ess
i
o
n
an
aly
s
is
.
B
ased
o
n
v
ar
iatio
n
s
in
f
ac
ial
m
u
s
cle
m
o
v
em
en
ts
,
it
m
ay
id
e
n
tify
em
o
tio
n
s
in
clu
d
in
g
h
ap
p
in
ess
,
s
o
r
r
o
w,
r
ag
e,
f
ea
r
,
d
is
g
u
s
t
,
an
d
s
u
r
p
r
is
e.
An
in
d
iv
id
u
al'
s
em
o
tio
n
al
s
tate
c
an
b
e
in
f
er
r
e
d
b
y
ex
a
m
in
in
g
t
h
eir
s
p
ee
ch
,
to
n
e,
p
itch
,
p
ac
e,
an
d
o
th
er
ac
o
u
s
tic
f
ea
tu
r
es.
Vo
ice
an
d
s
p
ee
ch
e
m
o
tio
n
d
ete
ctio
n
is
th
e
ter
m
u
s
ed
to
d
escr
ib
e
th
is
tech
n
iq
u
e.
Fo
r
th
is
v
o
ice
an
d
s
p
ee
ch
an
aly
s
is
,
m
ac
h
in
e
lear
n
in
g
m
o
d
els an
d
s
p
ee
c
h
p
r
o
ce
s
s
in
g
m
eth
o
d
s
ar
e
co
m
m
o
n
l
y
u
s
ed
[
1
]
.
I
n
s
ev
er
al
f
ield
s
,
s
u
ch
as
p
s
y
c
h
o
lo
g
y
,
n
eu
r
o
lo
g
y
,
h
ea
lth
ca
r
e,
an
d
h
u
m
an
-
c
o
m
p
u
te
r
in
ter
ac
t
io
n
,
th
ese
p
h
y
s
io
lo
g
ical
s
ig
n
als
h
elp
r
e
s
ea
r
ch
an
d
m
o
n
ito
r
em
o
tio
n
a
l
r
ea
ctio
n
s
in
h
u
m
an
s
.
I
n
d
y
n
am
ic,
co
m
p
licated
en
v
ir
o
n
m
en
ts
,
it
ca
n
b
e
d
if
f
i
cu
lt
to
d
is
tin
g
u
is
h
b
etwe
en
d
if
f
er
en
t
em
o
tio
n
s
b
ased
o
n
p
h
y
s
io
lo
g
ical
cu
es.
R
esear
ch
er
s
in
af
f
ec
tiv
e
co
m
p
u
tin
g
an
d
e
m
o
tio
n
r
ec
o
g
n
itio
n
u
s
e
a
m
ix
o
f
p
h
y
s
io
lo
g
ical
s
ig
n
als
an
d
s
o
p
h
is
ticated
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
to
s
o
lv
e
th
ese
p
r
o
b
lem
s
.
C
o
n
tin
u
o
u
s
r
esear
ch
is
also
d
ev
elo
p
i
n
g
m
o
r
e
r
o
b
u
s
t
an
d
ac
cu
r
ate
em
o
tio
n
r
ec
o
g
n
itio
n
m
o
d
els
b
as
ed
o
n
p
h
y
s
io
lo
g
ical
s
ig
n
als,
wh
ile
ta
k
in
g
eth
ical
an
d
p
r
i
v
ac
y
co
n
s
id
er
atio
n
s
in
t
o
ac
co
u
n
t
[2
]
-
[
5]
.
T
h
e
o
b
jectiv
e
o
f
th
is
wo
r
k
is
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
e
m
o
tio
n
s
lik
e
v
alen
ce
,
lik
in
g
,
a
r
o
u
s
al,
an
d
d
o
m
in
an
ce
u
s
in
g
f
o
u
r
p
h
y
s
io
lo
g
ical
s
ig
n
als
f
r
o
m
th
e
p
er
ip
h
er
al
n
e
r
v
o
u
s
s
y
s
tem
(
DE
AP
d
ataset)
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
emo
ti
o
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
p
erip
h
era
l
s
ig
n
a
ls
(
Ta
r
u
n
K
u
ma
r
)
977
e
lectr
o
m
y
o
g
r
ap
h
y
(
EMG
)
,
b
lo
o
d
v
o
l
u
m
e
p
u
ls
e
(
B
VP
)
,
r
esp
i
r
atio
n
(
R
SP
)
,
an
d
g
alv
a
n
ic
s
k
in
r
esp
o
n
s
e
(
GSR
)
.
H
u
m
an
em
o
tio
n
al
s
tates
m
a
y
b
e
id
en
tifie
d
f
r
o
m
e
lectr
o
en
ce
p
h
al
o
g
r
ap
h
y
(
E
E
G
)
-
b
as
ed
b
r
ain
-
c
o
m
p
u
ter
in
ter
f
ac
e
r
esear
ch
b
y
em
p
o
we
r
in
g
r
esear
ch
e
r
s
to
ap
p
ly
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es.
W
e
h
av
e
s
tu
d
ied
r
elate
d
v
ar
io
u
s
p
a
p
er
s
th
at
em
p
lo
y
d
ee
p
lear
n
in
g
a
n
d
Ma
c
h
in
e
le
ar
n
in
g
m
eth
o
d
s
f
o
r
class
if
y
in
g
h
u
m
an
e
m
o
tio
n
s
b
ased
o
n
E
E
G
d
ata
an
d
co
m
p
ar
e
th
em
with
th
e
p
r
o
p
o
s
ed
wo
r
k
.
T
h
e
r
ef
o
r
e
,
th
is
s
tu
d
y
'
s
m
ain
co
n
tr
ib
u
tio
n
f
in
d
s
th
e
an
s
wer
s
to
th
e
f
o
llo
win
g
q
u
esti
o
n
s
.
−
W
h
y
e
s
e
DE
AP d
atasets
?
−
W
h
ich
f
ea
tu
r
e
ex
tr
ac
tio
n
tech
n
iq
u
es a
r
e
th
er
e?
−
W
h
ich
f
ea
tu
r
e
s
elec
tio
n
an
d
r
e
d
u
ctio
n
tech
n
iq
u
es a
r
e
t
h
er
e?
−
W
h
ich
f
ea
tu
r
e
is
u
s
ed
f
o
r
ex
tr
ac
tio
n
f
r
o
m
DE
AP d
ata
s
ets?
−
W
h
ich
d
ee
p
lear
n
i
n
g
an
d
m
a
ch
in
e
lear
n
in
g
m
eth
o
d
s
ar
e
cu
r
r
en
tly
b
ein
g
ap
p
lied
to
E
E
G
-
b
ased
B
C
I
to
ca
teg
o
r
ize
h
u
m
an
em
o
tio
n
al
s
tates?
Dif
f
er
en
t
E
E
G
d
atasets
ar
e
a
v
ailab
le
f
o
r
e
m
o
tio
n
r
ec
o
g
n
itio
n
o
n
l
y
a
f
ew
o
f
th
em
illu
s
tr
ate
lik
e
DE
AP,
DR
E
AM
E
R
[
6
]
,
SE
E
D,
AM
I
GOS
[
7
]
,
SAFE,
G
A
M
EE
MO
,
an
d
MA
HNOB
-
HC
I
tag
g
in
g
.
T
h
ese
d
atasets
ar
e
r
esear
ch
-
wo
r
th
y
a
n
d
h
a
v
e
b
ee
n
ap
p
lied
to
s
ev
er
al
s
tu
d
ies
o
n
em
o
tio
n
id
en
tific
atio
n
.
Acc
o
r
d
in
g
to
th
e
r
esear
ch
in
th
is
s
tu
d
y
,
Fig
u
r
e
1
illu
s
tr
ates
th
e
p
r
o
p
o
r
tio
n
o
f
E
E
G
d
atasets
u
s
ed
f
o
r
e
m
o
tio
n
r
ec
o
g
n
itio
n
.
T
h
e
two
m
o
s
t
o
f
ten
u
s
ed
p
r
o
g
r
am
s
ar
e
DE
E
P
an
d
SEE
D,
with
1
9
%
a
n
d
5
1
%
o
f
p
ar
tici
p
an
ts
,
r
esp
ec
tiv
ely
.
A
s
m
aller
p
er
ce
n
tag
e
o
f
r
esear
ch
(
1
7
%)
u
s
ed
th
eir
d
atasets
,
wh
ich
ar
e
f
r
e
q
u
en
tly
n
o
t
p
u
b
licly
av
ailab
le
[
8
]
.
A
p
u
b
licly
ac
ce
s
s
ib
le
d
ataset
ca
lled
DR
E
AM
E
R
s
h
o
wed
u
p
in
th
is
ev
alu
atio
n
with
a
p
ar
ticip
atio
n
r
ate
o
f
7
%.
I
n
o
u
r
r
esear
ch
s
am
p
le,
th
e
MA
HNOB
-
H
C
I
,
GAM
EE
MO
,
an
d
AM
I
GOS
wer
e
p
r
ese
n
t,
with
a
r
esp
ec
tiv
e
p
ar
ticip
atio
n
r
ate
o
f
2
%.
Fig
u
r
e
1
.
Usag
e
o
f
d
atasets
A
r
ev
iew
o
f
th
e
wo
r
k
s
o
f
li
ter
atu
r
e
p
r
o
v
id
es
a
s
u
m
m
a
r
y
o
f
th
e
m
ajo
r
d
is
co
v
er
ies,
a
p
p
r
o
ac
h
es,
d
if
f
icu
lties
,
an
d
n
ew
d
ev
el
o
p
m
en
ts
in
th
e
s
u
b
ject
o
f
p
h
y
s
io
lo
g
ically
b
ased
h
u
m
an
em
o
tio
n
id
en
tific
atio
n
.
Hu
m
an
b
e
h
av
io
r
r
eq
u
i
r
es
a
k
n
o
wled
g
e
o
f
em
o
tio
n
s
,
wh
ich
h
as
b
en
ef
its
in
ar
ea
s
lik
e
h
ea
lth
ca
r
e
an
d
h
u
m
a
n
-
co
m
p
u
ter
in
te
r
ac
tio
n
[
9
]
.
T
h
e
s
tu
d
y
o
n
h
u
m
an
e
m
o
tio
n
id
en
tific
atio
n
u
s
in
g
v
a
r
io
u
s
p
h
y
s
io
lo
g
ical
s
ig
n
als,
s
u
ch
as
elec
tr
o
ca
r
d
io
g
r
ap
h
y
,
elec
tr
o
en
ce
p
h
alo
g
r
a
p
h
y
,
g
alv
an
ic
s
k
in
r
esp
o
n
s
e,
r
esp
ir
atio
n
,
an
d
s
k
in
tem
p
er
atu
r
e,
is
th
o
r
o
u
g
h
ly
e
x
a
m
i
n
ed
in
th
is
liter
atu
r
e
o
v
er
v
iew.
Ma
r
tin
ez
et
a
l.
[
1
0
]
p
r
esen
te
d
th
e
em
o
tio
n
s
d
e
p
th
p
h
y
s
io
lo
g
ical
m
o
d
els
u
s
in
g
two
p
h
y
s
io
lo
g
ical
s
ig
n
als
with
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN
)
.
Oh
et
a
l.
[
1
1
]
in
tr
o
d
u
ce
d
th
e
cr
ea
tio
n
o
f
C
NN
ar
ch
itectu
r
es
th
at
u
s
e
m
an
y
p
h
y
s
i
o
lo
g
ical
s
ig
n
als
to
c
lass
if
y
em
o
tio
n
s
in
to
s
ix
o
p
tim
al
ca
teg
o
r
ies.
C
h
ac
o
n
et
a
l.
[
1
2
]
ca
teg
o
r
ize
h
u
m
an
em
o
tio
n
s
u
s
in
g
th
e
DE
AP
d
ataset
with
o
u
t
th
e
n
ee
d
f
o
r
an
y
s
en
s
o
r
s
t
h
at
m
ea
s
u
r
e
b
io
s
ig
n
als.
Her
ea
f
te
r
co
llect
th
e
m
o
v
em
en
t
s
ig
n
als,
f
ilter
th
em
,
ex
tr
ac
t
t
h
e
m
ain
co
m
p
o
n
en
ts
,
r
ec
o
n
s
titu
te
th
e
h
ea
r
t
r
ate
(
HR
)
s
ig
n
al,
an
d
th
e
n
em
p
lo
y
th
e
HR
s
ig
n
al
in
th
e
em
o
tio
n
class
if
icatio
n
p
r
o
ce
s
s
u
s
in
g
th
e
L
u
ca
s
-
Kan
ad
e
m
eth
o
d
f
o
r
o
p
tical
f
lo
w.
Salar
i
et
a
l.
[
1
3
]
f
o
cu
s
ed
en
tire
class
if
icatio
n
o
f
em
o
tio
n
s
u
s
in
g
n
eu
r
al
n
etwo
r
k
m
o
d
els
an
d
two
n
e
u
r
al
n
etwo
r
k
-
b
as
ed
m
o
d
els
i.e
.
,
th
e
d
ee
p
n
eu
r
al
n
etwo
r
k
an
d
th
e
C
NN
b
o
th
u
s
ed
to
class
if
y
d
o
m
in
an
ce
a
n
d
lik
in
g
in
to
two
y
es/n
o
(
h
ig
h
a
n
d
lo
w
)
ca
teg
o
r
i
es
an
d
v
alen
ce
an
d
ar
o
u
s
al
in
to
th
r
ee
(
h
ig
h
,
n
o
r
m
al,
an
d
l
o
w
)
ca
teg
o
r
ies
r
esp
ec
tiv
ely
.
L
ee
et
a
l.
[
1
4
]
d
e
f
in
ed
C
NN
-
b
ased
em
o
tio
n
r
ec
o
g
n
itio
n
with
s
p
e
cif
ic
s
tatis
tical
p
h
o
to
p
leth
y
s
m
o
g
r
am
(
PP
G)
f
ea
tu
r
es.
PP
G
s
ig
n
al
is
ea
s
y
with
a
v
ar
iety
o
f
in
s
tr
u
m
en
ts
an
d
r
ec
o
r
d
in
g
.
T
h
is
s
ig
n
al
is
n
o
t
as
c
o
m
p
licated
as
r
ec
o
r
d
in
g
o
th
er
p
h
y
s
io
lo
g
ical
d
ata.
T
h
e
e
x
p
er
im
e
n
tal
r
esu
lts
wer
e
d
is
cu
s
s
ed
clea
r
ly
.
Xu
an
d
Platan
io
tis
[
1
5
]
p
r
esen
ted
th
e
u
s
e
o
f
s
em
i
-
s
u
p
er
v
is
ed
d
ee
p
lear
n
i
n
g
al
g
o
r
ith
m
s
wit
h
E
E
G
in
th
e
ca
teg
o
r
izatio
n
o
f
e
m
o
tio
n
al
s
tates.
Fu
et
a
l.
[
1
6
]
p
r
o
p
o
s
ed
m
u
ltimo
d
al
p
h
y
s
io
lo
g
ical
s
ig
n
als
an
d
tr
a
n
s
f
er
lea
r
n
in
g
f
o
r
e
m
o
tio
n
r
ec
o
g
n
iti
o
n
.
T
h
e
alg
o
r
ith
m
s
-
b
ased
r
esu
lts
r
eg
ar
d
in
g
ac
cu
r
ac
y
a
n
d
F
1
-
s
co
r
e
wer
e
d
is
cu
s
s
ed
.
Han
et
a
l.
[
1
7
]
p
r
o
p
o
s
ed
p
h
y
s
io
lo
g
ical
s
ig
n
als
f
r
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
7
6
-
9
8
4
978
p
h
o
to
p
let
h
y
s
m
o
g
r
ap
h
y
(
PP
G)
an
d
elec
tr
o
m
y
o
g
r
ap
h
y
(
E
M
G)
to
cr
ea
te
a
r
ea
l
-
tim
e
em
o
tio
n
id
en
tific
atio
n
s
y
s
tem
.
Ham
et
a
l.
[
1
8
]
p
r
o
p
o
s
ed
a
m
u
ltimo
d
al
b
i
o
s
ig
n
al
d
ata
-
b
ased
in
ter
n
et
o
f
t
h
in
g
s
-
b
ased
n
eg
ativ
e
em
o
tio
n
r
ec
o
g
n
itio
n
s
y
s
tem
u
s
in
g
f
iv
e
E
E
G
s
ig
n
als
an
d
th
r
e
e
p
h
y
s
io
lo
g
ical
s
ig
n
als
r
ec
o
r
d
ed
b
y
a
s
m
ar
t
b
an
d
.
W
an
g
et
a
l.
[
1
9
]
d
is
cu
s
s
ed
a
s
y
s
tem
atic
d
etailed
s
u
r
v
ey
with
d
if
f
e
r
en
t
p
u
b
lic
d
ata
s
ets
lik
e
DE
AP,
SEE
D,
an
d
MPE
D.
Des
s
ai
an
d
Vir
an
i
[
2
0
]
p
r
o
p
o
s
ed
an
em
o
tio
n
ch
ar
ac
ter
izatio
n
m
o
d
el
b
ased
o
n
GSR
,
co
n
tin
u
o
u
s
wav
elet
tr
an
s
f
o
r
m
(
CWT
)
,
an
d
E
C
G
s
ig
n
als
u
s
in
g
v
ar
i
o
u
s
C
NN
m
o
d
elin
g
.
Als
u
b
ai
[
2
1
]
p
r
o
p
o
s
ed
a
s
tu
d
y
u
s
in
g
th
e
d
is
cr
im
in
ati
v
e
r
ep
r
esen
tatio
n
o
f
f
ea
tu
r
es,
d
ee
p
n
o
r
m
alize
d
atten
tio
n
-
b
ased
r
es
id
u
al
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
(
DNA
-
R
C
NN
)
ex
tr
ac
ts
th
e
r
elev
an
t
ch
ar
ac
ter
is
tics
.
W
ith
th
e
s
u
g
g
ested
atten
tio
n
m
o
d
u
les
r
esu
ltin
g
in
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
,
th
e
p
r
o
p
o
s
ed
n
eu
r
al
n
etwo
r
k
ad
d
itio
n
ally
in
v
esti
g
at
es
attr
ac
tiv
e
asp
ec
t
s
.
Pid
g
eo
n
et
a
l.
[
2
2
]
p
r
o
p
o
s
ed
a
s
tu
d
y
b
ased
o
n
GSR
,
R
SP
,
an
d
B
VP
p
ar
am
eter
s
u
s
ed
f
r
o
m
DE
AP
d
ata
s
ets
to
ca
teg
o
r
ize
th
e
em
o
tio
n
s
,
an
d
t
h
e
alg
o
r
ith
m
s
-
b
ased
r
esu
lts
r
e
g
ar
d
in
g
ac
cu
r
ac
y
an
d
F
1
-
s
co
r
e
wer
e
d
is
cu
s
s
ed
.
2.
ME
T
H
O
D
OR
F
RAM
E
WO
RK
F
O
R
E
M
O
T
I
O
N
CL
A
S
SI
F
I
CA
T
I
O
N
T
h
e
ef
f
ec
tiv
e
n
ess
o
f
em
o
tio
n
r
ec
o
g
n
itio
n
ca
n
b
e
in
cr
ea
s
ed
b
y
u
s
in
g
th
e
ap
p
r
o
p
r
iate
tech
n
iq
u
e.
Fig
u
r
e
2
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
em
o
tio
n
r
ec
o
g
n
itio
n
m
o
d
el
an
d
h
o
w
v
ar
io
u
s
s
tep
s
ar
e
in
ter
co
n
n
ec
ted
.
Fig
u
r
e
2
.
Pro
p
o
s
ed
em
o
tio
n
r
e
co
g
n
itio
n
m
o
d
el
2
.
1
.
I
np
ut
s
ig
na
l
o
r
s
ig
na
l pro
ce
s
s
ing
DE
AP
d
ata
s
ets
ar
e
u
s
ed
as
a
n
in
p
u
t
s
ig
n
al.
I
n
th
e
DE
AP
p
r
e
-
p
r
o
ce
s
s
ed
d
ataset
f
iles
wer
e
u
tili
ze
d
in
th
is
wo
r
k
.
I
t
in
clu
d
es
8
a
d
d
iti
o
n
al
p
er
ip
h
e
r
al
p
h
y
s
io
lo
g
ical
s
ig
n
als
in
ad
d
itio
n
to
t
h
e
3
2
-
c
h
an
n
el
[
2
3
]
.
I
n
p
r
e
-
p
r
o
ce
s
s
in
g
o
u
t
o
f
8
s
ig
n
als,
w
e
ex
tr
ac
ted
o
n
ly
f
o
u
r
p
e
r
ip
h
er
al
p
h
y
s
io
lo
g
ical
s
ig
n
als
(
E
MG
,
GSR
,
B
VP,
an
d
R
SP
)
.
T
h
e
DE
AP
d
ataset
co
m
p
r
is
es
3
2
p
eo
p
le
with
g
o
o
d
h
ea
lth
(
n
a
m
ely
f
r
o
m
s
0
1
t
o
s
3
2
)
,
h
alf
o
f
th
em
a
r
e
f
em
ale,
b
etwe
en
th
e
a
g
es
o
f
1
9
an
d
3
7
,
a
n
d
e
i
g
h
t
s
ig
n
als
f
r
o
m
th
e
p
er
i
p
h
er
al
n
er
v
o
u
s
s
y
s
tem
(
e
lectr
o
o
cu
lo
g
r
ap
h
y
(
E
OG
)
,
GSR
,
B
VP,
R
SP
,
E
MG
,
an
d
s
k
in
tem
p
er
atu
r
e
(
SKT
)
)
.
E
ac
h
p
ar
ticip
an
t
s
aw
f
o
r
ty
-
one
-
m
i
n
u
te
m
o
v
ies
th
at
wer
e
s
en
s
ib
ly
ch
o
s
en
to
i
n
d
u
ce
v
ar
i
o
u
s
em
o
tio
n
al
s
tates
wh
ile
th
e
E
E
G
an
d
p
h
y
s
io
lo
g
ical
d
ata
wer
e
b
ein
g
ca
p
tu
r
ed
.
I
n
th
e
DE
AP d
ataset
o
f
4
0
tr
ials
o
f
m
o
v
ies,
ea
ch
p
ar
ticip
an
t in
DE
AP
ass
es
s
ed
ea
ch
v
id
eo
clip
o
n
a
s
ca
le
o
f
1
to
9
f
o
r
ar
o
u
s
al
an
d
v
alen
ce
.
T
a
b
le
1
s
h
o
ws
th
e
c
ompl
ete
d
etails
o
f
DE
AP
d
atasets
.
W
h
en
id
en
tif
y
in
g
e
m
o
tio
n
s
,
o
n
e
lab
el
f
o
r
class
if
icatio
n
th
at
m
ay
b
e
ap
p
lied
is
th
e
d
is
cr
ete
r
atin
g
v
alu
e.
Data
was
g
ath
er
ed
with
a
5
1
2
Hz
s
am
p
le
r
ate
,
an
d
p
r
e
-
p
r
o
ce
s
s
in
g
was
ca
r
r
i
ed
o
u
t.
T
h
e
s
ig
n
als
wer
e
ca
p
tu
r
ed
at
1
2
8
Hz
d
o
w
n
-
tem
p
o
.
T
h
e
DE
AP
d
ataset
h
as
1
2
8
0
tr
ials
(
3
2
ch
a
n
n
els
4
0
v
id
eo
)
)
in
t
o
tal
(
4
0
tr
ials
f
o
r
ea
ch
p
e
r
s
o
n
)
[
2
3
].
T
ab
le
1
.
Par
am
eter
o
f
DE
AP d
ataset
P
a
r
a
me
t
e
r
D
e
t
a
i
l
s
N
o
.
o
f
p
a
r
t
i
c
i
p
a
n
t
s
1
6
ma
l
e
,
1
6
f
e
ma
l
e
N
u
mb
e
r
o
f
c
h
a
n
n
e
l
s
3
2
EEG
,
8
p
e
r
i
p
h
e
r
a
l
p
h
y
si
o
l
o
g
i
c
a
l
si
g
n
a
l
s
Ty
p
e
o
f
s
i
g
n
a
l
s
EEG
,
EO
G
,
E
M
G
,
G
S
R
,
R
ESP
,
B
V
P
,
H
S
T
C
h
a
n
n
e
l
n
a
m
e
s f
o
r
p
e
r
i
p
h
e
r
a
l
p
h
y
si
o
l
o
g
i
c
a
l
s
i
g
n
a
l
s
h
EO
G
,
v
EO
G
,
z
E
M
G
,
t
E
M
G
,
G
S
R
,
R
ESP
,
B
V
P
,
H
S
T
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
)
40
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
)
1
2
8
Hz
Th
e
n
u
m
b
e
r
o
f
l
a
b
e
l
s fo
r
t
h
e
d
a
t
a
s
e
t
4
La
b
e
l
n
a
me
V
a
l
e
n
c
e
,
l
i
k
i
n
g
,
a
r
o
u
sa
l
,
d
o
mi
n
a
n
c
e
Ea
c
h
l
a
b
e
l
’
s rat
i
n
g
v
a
l
u
e
s
1
t
o
9
Q
u
a
n
t
i
t
y
o
f
i
n
f
o
r
m
a
t
i
o
n
f
o
r
e
v
e
r
y
l
a
b
e
l
1
,
2
8
0
N
u
meri
c
a
l
v
a
l
u
e
s fo
r
e
a
c
h
su
b
j
e
c
t
4
0
v
i
d
e
o
s ×
3
2
c
h
a
n
n
e
l
s
×
8
0
6
4
d
a
t
a
(
n
u
m
e
r
i
c
d
a
t
a
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
emo
ti
o
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
p
erip
h
era
l
s
ig
n
a
ls
(
Ta
r
u
n
K
u
ma
r
)
979
T
h
is
s
tu
d
y
em
p
lo
y
e
d
f
o
u
r
d
is
tin
ct
f
o
r
m
s
f
r
o
m
th
e
DE
AP
d
ataset
o
f
p
er
ip
h
er
al
p
h
y
s
io
lo
g
i
ca
l
s
ig
n
als
(
E
MG
,
B
VP,
R
SP
,
an
d
GSR
)
to
d
eter
m
in
e
em
o
tio
n
s
.
T
h
e
s
ize
o
f
ex
tr
ac
ted
f
ea
tu
r
es
is
3
2
×4
0
a
n
d
ev
er
y
ce
ll
h
as
m
u
ch
m
o
r
e
in
f
o
r
m
atio
n
li
k
e
f
ea
tu
r
es
n
u
m
e
r
ical
v
alu
e
a
n
d
n
a
m
e
o
f
E
MG
,
GSR
,
B
V
P,
an
d
R
SP
s
ig
n
als
alo
n
g
with
f
ee
d
b
a
ck
r
atin
g
.
Vale
n
ce
,
lik
in
g
,
ar
o
u
s
al,
an
d
d
o
m
in
an
ce
ar
e
u
s
ed
to
ca
lcu
l
ate
th
e
ac
cu
r
ac
y
o
f
em
o
tio
n
r
ec
o
g
n
itio
n
.
All
f
ea
tu
r
es
ar
e
s
to
r
ed
in
.
m
at
f
il
e
ex
ten
s
i
o
n
with
a
d
im
en
s
io
n
o
f
3
2
×4
0
.
T
h
e
p
leasan
tn
ess
o
r
u
n
p
leasan
tn
es
s
o
f
an
em
o
ti
o
n
al
ev
e
n
t
o
r
m
o
o
d
is
r
ep
r
esen
ted
b
y
th
e
v
al
en
ce
.
L
ik
in
g
,
also
k
n
o
wn
as
“h
e
d
o
n
ic
t
o
n
e,
”
is
c
lo
s
ely
co
n
n
ec
ted
t
o
v
alen
ce
b
u
t
h
ig
h
lig
h
ts
h
o
w
m
u
c
h
a
p
er
s
o
n
lo
v
es
o
r
lik
es
a
s
p
ec
if
ic
e
m
o
tio
n
al
s
tate.
A
p
e
r
s
o
n
’
s
s
u
b
jectiv
e
ass
ess
m
en
t
o
f
h
o
w
m
u
c
h
th
e
y
lik
e
o
r
h
ate
an
em
o
tio
n
al
e
v
en
t
is
ca
lled
lik
in
g
.
T
h
e
d
eg
r
ee
o
f
ar
o
u
s
al
is
a
m
ea
s
u
r
e
o
f
h
o
w
a
ctiv
e
o
r
in
te
n
s
e
an
em
o
tio
n
al
ex
p
er
ien
ce
is
.
On
a
s
ca
le
f
r
o
m
lo
w
ar
o
u
s
al
(
ca
lm
o
r
r
elax
e
d
)
t
o
h
i
g
h
a
r
o
u
s
al
(
e
x
cited
o
r
d
is
tu
r
b
e
d
)
,
it
is
o
f
te
n
ch
ar
ac
ter
ize
d
.
T
h
e
d
eg
r
ee
o
f
co
n
t
r
o
l
o
r
in
f
lu
e
n
c
e
th
at
a
p
e
r
s
o
n
f
ee
ls
th
ey
h
av
e
o
v
er
th
eir
e
m
o
tio
n
al
s
tate
is
r
ef
er
r
ed
to
as
d
o
m
in
an
ce
.
I
t d
e
f
in
es h
o
w
a
p
er
s
o
n
r
ea
cts to
a
s
p
ec
if
ic
f
ee
li
n
g
an
d
h
o
w
d
o
m
in
atin
g
o
r
s
u
b
m
is
s
iv
e
th
ey
f
ee
l.
2
.
2
.
F
e
a
t
ure
e
x
t
r
a
ct
io
n
I
t
is
p
o
s
s
ib
le
to
d
is
ca
r
d
d
ata
t
h
at
is
u
n
im
p
o
r
tan
t
to
th
e
o
b
je
ctiv
e,
p
er
f
o
r
m
ca
lcu
latio
n
s
m
o
r
e
q
u
ick
ly
,
escap
e
th
e
d
im
en
s
io
n
ality
cu
r
s
e,
an
d
en
h
an
ce
th
e
m
o
d
el’
s
g
en
er
aliza
b
ilit
y
.
Featu
r
e
ex
tr
a
ctio
n
is
f
r
eq
u
e
n
tly
n
ec
ess
ar
y
b
ef
o
r
e
th
e
e
n
tr
y
o
f
s
ig
n
als
in
to
s
ev
er
al
co
n
v
en
tio
n
al
class
if
icatio
n
m
o
d
els.
I
n
th
is
s
tu
d
y
,
th
e
f
is
h
er
d
is
cr
im
in
an
t
ap
p
r
o
ac
h
is
u
s
ed
wh
ich
is
a
d
im
en
s
io
n
ality
r
ed
u
ctio
n
alg
o
r
ith
m
.
T
h
e
d
im
e
n
s
io
n
o
f
th
e
d
ata
is
r
ed
u
ce
d
u
s
in
g
th
is
ap
p
r
o
ac
h
.
T
h
e
p
r
o
ce
d
u
r
e
o
f
s
elec
tin
g
a
co
llectio
n
o
f
f
ea
tu
r
es
f
r
o
m
th
e
w
h
o
le
s
et
o
f
f
ea
tu
r
es
is
r
ef
er
r
e
d
to
as
f
ea
t
u
r
e
s
elec
tio
n
.
I
n
ad
d
itio
n
to
s
elec
tin
g
th
e
ch
a
r
ac
ter
is
tics
,
th
ey
also
r
ed
u
ce
th
e
d
im
en
s
io
n
o
f
th
e
d
ata.
Fis
h
er
'
s
alg
o
r
ith
m
also
h
elp
s
to
ac
h
iev
e
th
e
m
ain
g
o
al
o
f
lo
wer
in
g
th
e
n
u
m
b
er
o
f
v
ar
iab
les.
W
h
en
an
aly
zin
g
p
h
y
s
io
lo
g
ical
o
r
m
u
ltimo
d
al
d
at
a,
th
e
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
k
n
o
wn
as
r
id
g
e
r
eg
r
ess
io
n
is
f
r
eq
u
e
n
tly
u
tili
z
ed
f
o
r
em
o
tio
n
id
en
tific
atio
n
.
R
id
g
e
r
e
g
r
ess
io
n
m
a
y
b
e
u
s
e
d
f
o
r
class
if
icatio
n
task
s
,
wh
ich
is
f
r
eq
u
en
tly
th
e
ca
s
e
in
em
o
tio
n
r
ec
o
g
n
itio
n
,
ev
en
th
o
u
g
h
it
is
m
o
r
e
f
r
eq
u
en
tly
r
elate
d
to
r
eg
r
ess
io
n
is
s
u
es.
R
id
g
e
r
eg
r
ess
io
n
is
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
u
s
ed
in
th
is
wo
r
k
to
b
e
u
tili
ze
d
in
th
e
co
n
tex
t
o
f
em
o
tio
n
id
en
tific
atio
n
.
I
t
m
ay
b
e
u
s
ed
f
o
r
m
u
lticlas
s
task
s
l
ik
e
id
en
tify
in
g
d
i
f
f
er
en
t
em
o
tio
n
s
lik
e
h
ap
p
in
ess
,
s
ad
n
ess
,
an
d
r
ag
e
as
well
as
f
o
r
b
in
ar
y
em
o
tio
n
class
if
icatio
n
task
s
lik
e
ca
teg
o
r
izin
g
em
o
tio
n
s
as
p
o
s
itiv
e
o
r
n
eg
ativ
e.
3
2
p
a
r
ticip
an
ts
p
ar
ticip
ated
in
4
0
v
id
eo
tr
ials
(
1
,
2
8
0
×5
×
8
,
0
6
4
)
with
5
ch
an
n
els,
6
3
s
ec
o
n
d
s
o
f
s
ig
n
al
s
am
p
lin
g
at
1
2
8
Hz
(
8
,
0
6
4
v
alu
es),
a
n
d
d
ata
ar
r
a
y
s
with
th
ese
d
im
en
s
io
n
s
(
s
am
p
les×ch
an
n
els×tim
estep
s
)
wer
e
ac
q
u
ir
ed
.
T
h
e
d
ata
ar
r
a
y
'
s
E
E
G,
E
O
G,
an
d
t
em
p
ch
an
n
els we
r
e
r
em
o
v
ed
.
Fo
r
th
e
f
o
u
r
r
em
ain
in
g
ch
an
n
els
(
GSR
,
B
VP,
R
SP
,
an
d
E
MG
)
,
th
e
r
an
g
e
[
0
,
1
]
was
u
s
ed
.
T
ab
le
2
p
r
esen
ted
t
he
p
ar
am
ete
r
s
th
at
a
r
e
ex
tr
a
cted
o
r
u
s
ed
in
th
is
s
tu
d
y
a
n
d
th
ese
ch
ar
ac
ter
is
tics
wer
e
t
ak
en
o
u
t
o
f
e
v
er
y
ch
an
n
el
f
o
r
ev
e
r
y
p
ar
ticip
an
t.
So
m
e
f
ea
tu
r
e
d
e
f
in
itio
n
s
ar
e
e
x
p
lain
ed
b
elo
w
with
m
ath
e
m
a
tical
f
o
r
m
u
latio
n
s
.
T
h
is
s
tu
d
y
u
s
ed
tim
e
-
d
o
m
ain
s
tatis
tical
ch
ar
ac
ter
is
tic
s
[
1
]
,
[
24
].
T
ab
le
2
.
Featu
r
e
o
f
p
e
r
ip
h
er
al
p
h
y
s
io
lo
g
ical
s
ig
n
als
P
e
r
i
p
h
e
r
a
l
p
h
y
s
i
o
l
o
g
i
c
a
l
s
i
g
n
a
l
s
N
u
mb
e
r
o
f
c
h
a
n
n
e
l
s
N
o
.
o
f
f
e
a
t
u
r
e
s
N
a
me
o
f
f
e
a
t
u
r
e
s
EM
G
02
05
M
e
a
n
,
st
d
,
k
u
r
t
o
s
i
s,
s
k
e
w
n
e
ss
,
E
M
G
_
p
o
w
e
r
G
S
R
01
07
n
b
P
e
a
k
s,
a
m
p
P
e
a
k
s,
r
i
s
e
Ti
m
e
,
mea
n
G
S
R
,
s
t
d
G
S
R
,
f
i
r
st
Q
u
a
r
t
i
l
e
G
S
R
,
t
h
i
r
d
Q
u
a
r
t
i
l
e
G
S
R
B
V
P
01
13
mea
n
,
H
R
V
,
m
e
a
n
I
B
I
,
M
S
E,
s
p
0
0
0
1
,
sp
0
1
0
2
,
sp
0
2
0
3
,
s
p
0
3
0
4
,
s
p
_
e
n
e
r
g
y
R
a
t
i
o
,
t
a
c
h
o
g
r
a
m_
LF,
t
a
c
h
o
g
r
a
m_
M
F
,
t
a
c
h
o
g
r
a
m
_
H
F
,
t
a
c
h
o
g
r
a
m_
e
n
e
r
g
y
_
r
a
t
i
o
R
S
P
01
12
mea
n
,
s
t
d
,
k
u
r
t
o
s
i
s,
sk
e
w
n
e
ss,
sp
0
0
0
1
,
sp
0
1
0
2
,
sp
0
2
0
3
,
s
p
0
3
0
,
s
p
0
4
0
7
,
sp
0
7
1
0
,
sp
1
0
2
5
,
m
a
i
n
_
f
r
e
q
Mean
ca
n
b
e
ca
lc
u
lated
b
y
d
iv
id
in
g
t
h
e
to
tal
n
u
m
b
er
i
n
th
e
d
ataset
b
y
its
s
ize
as
p
r
esen
ted
in
(
1
)
,
wh
ich
is
a
m
ath
em
atica
l r
ep
r
e
s
en
tatio
n
o
f
th
e
u
s
u
al
v
alu
e
o
f
a
s
et
o
f
d
ata.
μ
=
1
∑
=
1
(
1
)
wh
er
e
M
r
ep
r
esen
ts
d
ata
s
am
p
le
n
u
m
b
e
r
s
an
d
Pi
f
o
r
th
e
s
ig
n
al.
Stan
d
ar
d
d
ev
iatio
n
is
a
s
tatis
tical
m
etr
ic
u
s
ed
to
ass
es
s
th
e
d
eg
r
ee
o
f
v
a
r
iatio
n
o
r
d
is
p
er
s
io
n
in
a
co
llecti
o
n
o
f
d
ata
is
th
e
s
tan
d
ar
d
d
ev
iatio
n
,
wr
itten
as
σ
(
s
ig
m
a)
as
p
r
esen
ted
in
(
2
)
.
C
alcu
latin
g
th
e
s
tan
d
ar
d
d
ev
iatio
n
in
th
e
co
n
tex
t
o
f
E
E
G
s
ig
n
als
g
iv
es
in
f
o
r
m
atio
n
ab
o
u
t
th
e
v
ar
ia
b
ilit
y
o
f
t
h
e
s
ig
n
al’
s
am
p
litu
d
e
a
t
ce
r
tain
elec
tr
o
d
e
s
ites
o
r
d
u
r
in
g
s
p
ec
if
ied
tim
e
f
r
am
es.
I
t c
an
b
e
r
ep
r
esen
ted
b
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
7
6
-
9
8
4
980
=
√
1
∑
(
−
µ
)
2
=
1
(
2
)
I
n
T
ab
le
3
k
u
r
to
s
is
ass
ess
e
s
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
s
o
r
a
d
ataset’
s
s
h
ap
e
an
d
p
ea
k
in
ess
.
I
t
r
ev
ea
ls
th
e
d
is
tr
ib
u
tio
n
’
s
tails
an
d
wh
eth
er
o
r
n
o
t
it
h
as
a
h
ig
h
er
o
r
lo
wer
p
ea
k
th
a
n
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
.
Ku
r
to
s
is
ca
n
b
e
c
o
m
p
u
te
d
in
t
h
e
co
n
t
ex
t
o
f
E
E
G
s
ig
n
als
to
ex
am
i
n
e
th
e
p
r
o
p
e
r
ties
o
f
th
e
E
E
G
s
ig
n
al’
s
am
p
litu
d
e
d
is
tr
ib
u
tio
n
.
Sk
ew
n
ess
is
u
s
ed
u
n
d
er
tim
e
d
o
m
ain
f
ea
tu
r
es
.
Sk
ewn
ess
ca
lcu
lates
th
e
v
ar
i
an
ce
in
d
is
tr
ib
u
tio
n
b
etwe
en
ea
ch
v
a
r
iab
le'
s
m
ea
n
an
d
m
ed
ia
n
ac
r
o
s
s
ep
o
c
h
s
.
T
h
e
s
tr
en
g
th
o
f
t
h
e
E
MG
s
ig
n
a
l
is
ex
p
r
ess
ed
as
a
u
s
ef
u
l
ch
ar
ac
ter
is
tic
b
y
th
e
v
ar
ian
ce
o
f
E
MG
.
T
h
e
p
o
wer
o
f
th
e
E
MG
s
ig
n
al
is
m
ea
s
u
r
ed
b
y
t
h
is
ch
ar
ac
ter
is
tic.
Fro
m
th
e
GSR
p
er
ip
h
er
al
p
h
y
s
io
lo
g
ic
s
ig
n
als
th
e
q
u
an
tity
o
f
GSR
p
ea
k
s
p
er
s
ec
o
n
d
,
av
er
a
g
e
p
ea
k
am
p
litu
d
e,
a
v
er
ag
e
p
ea
k
r
is
es
a
p
er
io
d
av
e
r
ag
e
G
S
R
v
alu
e,
an
d
av
er
a
g
e
v
a
r
iatio
n
o
f
GSR
wer
e
ca
lcu
lated
.
Fro
m
B
VP,
HR
v
ar
iab
ilit
y
an
d
o
t
h
er
f
ea
t
u
r
es we
r
e
ex
tr
ac
ted
.
E
ac
h
lab
el’
s
r
atin
g
v
alu
es
ar
e
1
t
o
9
,
lab
el
n
am
es
a
r
e
v
alen
ce
,
lik
in
g
,
ar
o
u
s
al,
an
d
d
o
m
in
an
ce
,
an
d
v
ales f
o
r
(
1
,
1
)
ar
e
s
h
o
wn
in
T
ab
le
4
.
In
DE
AP d
ata
s
et
s
,
a
3
2
×
4
0
m
atr
ix
is
d
escr
ib
ed
,
an
d
atten
tio
n
is
d
ir
ec
ted
to
elu
cid
atin
g
th
e
v
alu
e
at
co
o
r
d
in
ate
(
1
,
1
)
with
in
th
e
m
atr
ix
.
T
h
is
elu
cid
atio
n
im
p
lies
a
s
y
s
tem
atic
ap
p
r
o
ac
h
o
r
m
et
h
o
d
b
y
wh
ic
h
o
th
er
co
o
r
d
in
ates'
v
alu
es
ca
n
s
im
ilar
ly
b
e
ex
p
licated
.
T
a
b
le
s
3
an
d
4
s
h
o
w
t
h
e
p
r
o
ce
s
s
d
etailed
f
o
r
d
is
ce
r
n
i
n
g
t
h
e
v
alu
e
at
(
1
,
1
)
to
s
er
v
e
as
th
e
s
am
e
p
r
o
ce
s
s
f
o
r
ex
tr
ap
o
latin
g
v
al
u
es
at
o
th
e
r
co
o
r
d
in
ates
(
3
2
×4
0
)
with
in
th
e
m
atr
ix
,
s
u
g
g
esti
n
g
a
s
tr
u
ctu
r
ed
an
d
r
e
p
licab
le
m
eth
o
d
f
o
r
co
m
p
r
eh
e
n
d
in
g
th
e
m
atr
ix
'
s
e
n
tire
ty
i.e
.
,
1
,
2
8
0
tim
es d
ata
r
ec
o
r
d
e
d
f
o
r
r
o
tal
m
atr
ix
.
T
ab
le
3
.
Featu
r
e
v
alu
e
o
f
E
M
G,
GSR
,
B
V
P a
n
d
R
SP
s
ig
n
al
s
EM
G
G
S
R
B
V
P
R
S
P
N
u
mb
e
r
o
f
c
h
a
n
n
e
l
/
f
e
a
t
u
r
e
s
C
H
1
C
H
2
N
u
mb
e
r
o
f
c
h
a
n
n
e
l
/
f
e
a
t
u
r
e
s
C
H
1
N
u
mb
e
r
o
f
c
h
a
n
n
e
l
/
f
e
a
t
u
r
e
s
C
H
1
N
u
mb
e
r
o
f
c
h
a
n
n
e
l
/
f
e
a
t
u
r
e
s
C
H
1
M
e
a
n
1
9
.
5
2
5
-
1
5
.
4
3
n
b
P
e
a
k
s
1
2
8
0
M
e
a
n
-
2
0
9
.
8
6
1
M
e
a
n
4
4
1
.
8
7
2
9
st
d
3
1
.
5
8
4
4
2
.
2
9
2
a
mp
P
e
a
k
s
2
7
6
7
.
2
1
H
R
V
0
.
0
4
8
7
6
9
S
t
d
9
6
5
.
2
5
4
K
u
r
t
o
si
s
2
.
6
4
0
3
.
0
1
5
7
R
i
se
t
i
me
1
.
6
0
5
4
mea
n
I
B
I
'
0
.
9
2
7
5
3
7
K
u
r
t
o
si
s
2
.
3
1
9
3
6
4
S
k
e
w
n
e
ss
0
.
4
8
1
0
0
.
0
4
7
2
mea
n
G
S
R
1
7
1
6
.
5
0
M
S
E
0
.
3
3
6
7
7
3
S
k
e
w
n
e
ss
-
0
.
2
7
6
8
8
EM
G
_
p
o
w
e
r
4
.
2
9
0
5
.
4
4
6
st
d
G
S
R
2
7
7
3
.
2
4
sp
0
0
0
1
0
.
6
2
7
9
6
4
sp
0
0
0
1
1
4
.
8
0
0
0
7
f
i
r
st
Q
u
a
r
t
i
l
e
G
S
R
-
6
3
9
.
2
6
sp
0
1
0
2
0
.
9
3
1
8
3
2
sp
0
1
0
2
1
3
.
7
5
8
9
5
t
h
i
r
d
Q
u
a
r
t
i
l
e
G
S
R
4
4
5
9
.
4
sp
0
2
0
3
1
.
2
0
6
4
6
1
sp
0
2
0
3
1
3
.
6
3
2
4
4
sp
0
3
0
4
1
.
3
0
5
3
6
2
sp
0
3
0
4
1
5
.
4
7
1
0
5
sp
_
e
n
e
r
g
y
R
a
t
i
o
-
0
.
3
6
3
3
8
sp
0
4
0
7
1
4
.
8
5
1
8
9
t
a
c
h
o
g
r
a
m_
LF
-
3
.
0
4
1
5
sp
0
7
1
0
1
3
.
7
5
8
4
8
t
a
c
h
o
g
r
a
m_
M
F
-
5
.
5
0
8
9
5
sp
1
0
2
5
1
3
.
2
5
0
3
7
t
a
c
h
o
g
r
a
m_
H
F
-
7
.
3
6
3
3
7
mai
n
_
f
r
e
q
0
.
5
t
a
c
h
o
g
r
a
m_
e
n
e
r
g
y
_
r
a
t
i
o
3
.
2
7
2
8
8
3
T
ab
le
4
.
Feed
b
ac
k
v
alu
es/ra
tin
g
o
f
e
m
o
tio
n
s
La
b
e
l
V
a
l
e
n
c
e
A
r
o
u
sa
l
D
o
mi
n
a
n
c
e
Li
k
i
n
g
R
a
t
i
n
g
7
.
7
1
7
.
6
6
.
9
7
.
8
3
2
.
3
.
Cla
s
s
if
ica
t
io
n
Dif
f
er
en
t
in
p
u
t
s
ig
n
als
a
r
e
cl
ass
if
ied
b
y
th
e
class
if
ier
,
wh
i
ch
th
en
o
u
tp
u
ts
th
e
ap
p
r
o
p
r
ia
te
em
o
tio
n
ca
teg
o
r
y
.
T
h
e
q
u
ality
o
f
th
e
class
if
ier
d
eter
m
in
es
h
o
w
well
em
o
tio
n
s
ar
e
r
ec
o
g
n
i
ze
d
.
Dee
p
lear
n
in
g
ap
p
r
o
ac
h
es
an
d
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
ar
e
two
g
r
o
u
p
s
in
t
o
wh
ich
th
e
c
u
r
r
en
t
class
if
icatio
n
tech
n
iq
u
es
ar
e
s
u
b
d
i
v
id
ed
.
T
h
e
f
ea
tu
r
es
ar
e
p
r
o
v
id
e
d
to
t
h
e
class
if
ier
f
o
r
class
if
icatio
n
o
n
ce
th
e
o
p
tim
u
m
f
ea
tu
r
e
f
o
r
class
if
icatio
n
ac
cu
r
ac
y
h
as
b
ee
n
ch
o
s
en
.
A
class
if
ier
m
ay
d
em
ar
ca
te
b
et
wee
n
two
o
r
m
o
r
e
ca
teg
o
r
ies
b
ef
o
r
e
ass
ig
n
in
g
a
l
ab
el
b
ased
o
n
t
h
e
f
ea
tu
r
es
it
h
as
s
elec
ted
.
I
t
is
p
o
s
s
ib
le
to
th
i
n
k
o
f
t
h
e
b
o
r
d
er
as
a
u
n
iq
u
e
h
y
p
er
p
lan
e
th
at
is
p
a
r
t
o
f
a
m
u
ltid
im
e
n
s
io
n
al
f
ea
t
u
r
e
s
p
ac
e.
I
n
o
th
er
w
o
r
d
s
,
th
e
g
r
ea
ter
th
e
d
is
tan
ce
f
r
o
m
all
ca
teg
o
r
ies,
th
e
b
ett
er
th
e
h
y
p
e
r
p
lan
e,
a
n
d
th
e
b
etter
th
e
class
if
ier
.
T
h
ese
ch
ar
ac
ter
is
tics
ar
e
f
u
r
th
er
ca
teg
o
r
ized
b
y
co
m
b
in
in
g
r
el
ated
f
ea
tu
r
es
in
to
a
s
in
g
le
ca
teg
o
r
y
u
s
in
g
d
is
cr
im
in
a
n
t
an
al
y
s
is
an
d
cr
ea
tin
g
a
co
n
f
u
s
io
n
ch
a
r
t
u
s
in
g
th
e
r
ea
l
lab
els
in
ea
ch
g
r
o
u
p
an
d
th
e
ex
p
e
cted
lab
els
in
ea
ch
class
af
ter
clas
s
if
y
in
g
s
am
p
le
Data
with
d
ialin
ea
r
/l
in
ea
r
/q
u
ad
r
atic
/d
iag
q
u
ad
r
ati
c
d
is
cr
im
in
an
t
an
aly
s
is
.
A
d
i
s
cr
im
in
an
t
an
aly
s
is
class
if
ier
,
wh
ich
is
a
g
au
s
s
ian
m
ix
tu
r
e
m
o
d
el
f
o
r
d
ata
p
r
o
d
u
ctio
n
,
is
in
cl
u
d
ed
with
in
a
class
if
icatio
n
d
is
cr
im
in
an
t
o
b
ject.
Usi
n
g
th
e
p
r
ed
icted
ap
p
r
o
ac
h
,
a
class
if
icatio
n
d
is
cr
im
in
an
t
o
b
ject
m
ay
an
ticip
ate
o
u
tco
m
es
f
o
r
f
r
esh
d
ata.
T
h
e
o
b
ject
h
as
ac
ce
s
s
to
th
e
tr
ain
in
g
d
ata
an
d
ca
n
ca
lc
u
late
r
esu
b
s
titu
tin
g
p
r
ed
ictio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
emo
ti
o
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
p
erip
h
era
l
s
ig
n
a
ls
(
Ta
r
u
n
K
u
ma
r
)
981
2
.
4
.
O
utput
o
r
v
a
lid
a
t
io
n
In
m
ac
h
i
n
e
le
ar
n
i
n
g
a
n
d
s
tatis
tical
m
o
d
el
ev
alu
atio
n
,
L
O
OC
V
m
eth
o
d
o
lo
g
y
is
a
s
p
ec
i
alize
d
an
d
th
o
r
o
u
g
h
cr
o
s
s
-
v
alid
atio
n
m
e
th
o
d
.
I
t
is
a
tech
n
i
q
u
e
f
o
r
d
e
ter
m
in
in
g
a
p
r
ed
ictiv
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
b
y
u
s
in
g
all
b
u
t
o
n
e
d
ata
p
o
i
n
t
f
o
r
tr
ain
in
g
an
d
th
e
o
n
ly
r
em
ai
n
in
g
d
ata
p
o
in
t
f
o
r
test
in
g
.
E
ac
h
d
ata
p
o
in
t
in
th
e
d
ataset
is
th
en
g
iv
en
th
e
s
am
e
tr
ea
tm
en
t
o
n
ce
a
g
ain
.
A
s
p
ec
if
ic
in
s
tan
ce
o
f
K
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
,
wh
er
e
K
is
th
e
to
tal
n
u
m
b
er
o
f
d
ata
p
o
i
n
ts
in
th
e
d
ataset,
is
u
s
ed
.
L
O
OC
V
is
o
p
er
ated
in
th
e
f
o
llo
w
in
g
s
tep
s
.
−
I
t
is
tem
p
o
r
ar
ily
h
eld
o
u
t a
s
th
e
“test”
d
ata
p
o
in
t f
o
r
ea
ch
d
at
a
p
o
in
t in
t
h
e
d
ataset.
−
T
h
e
r
em
ain
in
g
d
ata
p
o
in
ts
o
f
te
n
r
ef
er
r
ed
to
as th
e
“t
r
ain
in
g
”
d
ata
ar
e
u
s
ed
to
tr
ain
th
e
m
o
d
e
l.
−
T
esti
n
g
th
e
m
o
d
el
o
n
th
e
lo
n
e
h
eld
-
o
u
t
d
ata
p
o
i
n
t a
llo
ws f
o
r
an
ev
alu
atio
n
o
f
its
p
er
f
o
r
m
a
n
ce
.
−
T
h
e
m
o
d
el
is
tr
ain
ed
a
n
d
test
ed
N
tim
es,
leav
in
g
o
u
t
o
n
e
d
at
a
p
o
in
t
ea
ch
tim
e,
if
t
h
er
e
ar
e
N
d
ata
p
o
in
ts
in
th
e
d
ataset.
T
h
is
p
r
o
ce
s
s
is
p
er
f
o
r
m
ed
f
o
r
ea
ch
d
ata
p
o
in
t in
th
e
d
ataset.
2
.
5
.
P
er
f
o
r
m
a
nce
m
e
t
ric
T
h
e
m
o
s
t
o
f
ten
u
s
ed
p
er
f
o
r
m
a
n
ce
in
d
icato
r
s
in
m
ac
h
in
e
lear
n
in
g
a
r
e
r
ec
all,
p
r
ec
is
io
n
,
ac
c
u
r
ac
y
,
an
d
s
tan
d
ar
d
d
ev
iatio
n
.
F1
-
s
co
r
e
is
d
ep
en
d
en
t
o
n
r
ec
all
an
d
ac
cu
r
ac
y
in
(
6
)
.
I
n
p
h
y
s
io
lo
g
ic
al
s
ig
n
als,
em
o
tio
n
id
en
tific
atio
n
,
an
d
o
th
e
r
class
i
f
icatio
n
task
s
,
ac
cu
r
ac
y
in
(
3)
is
a
f
r
eq
u
en
t
p
er
f
o
r
m
an
ce
p
a
r
am
eter
[
2
4
]
,
[
25]
.
T
o
q
u
an
tif
y
ac
cu
r
ac
y
,
a
s
y
s
tem
o
f
ten
n
ee
d
s
b
o
th
th
e
p
r
o
jecte
d
lab
els
f
o
r
a
d
ataset
an
d
th
e
tr
u
e
lab
els
(
g
r
o
u
n
d
tr
u
th
)
.
T
h
e
p
er
f
o
r
m
a
n
ce
f
o
r
m
u
lae
ar
e
g
iv
en
b
elo
w.
c
c
ura
c
y
=
TP
+
TN
TP
+
TN
+
FP
+
FN
(
3
)
Pr
e
c
ision
=
TP
TP
+
FP
(
4
)
R
e
c
a
l
l
=
TP
TP
+
FN
(
5
)
1
=
2
∗
Pr
ec
i
s
i
o
n
∗
Recal
l
Pr
ecis
i
o
n
+
Recal
l
(
6
)
W
h
er
e
tr
u
e
p
o
s
itiv
e
(
T
P)
is
th
e
m
o
d
el
th
at
ac
cu
r
ately
class
if
ies
d
ata
as
p
o
s
itiv
e.
T
r
u
e
n
eg
a
tiv
e
(
T
N)
d
ata
is
in
f
o
r
m
atio
n
th
at
th
e
m
o
d
el
co
r
r
ec
tl
y
class
if
ies as n
eg
ativ
e.
FP
is
th
e
m
o
d
el
th
at
m
is
class
if
ies d
ata
f
r
o
m
th
e
n
eg
ativ
e
ca
teg
o
r
y
as
p
o
s
itiv
e.
FN
i
s
in
clu
d
ed
wh
en
th
e
m
o
d
el
m
is
class
if
ies
d
ata
f
r
o
m
th
e
p
o
s
itiv
e
ca
teg
o
r
y
as
n
e
g
ativ
e
[
24
]
,
[
25
]
.
T
h
e
y
all
d
ep
e
n
d
o
n
h
o
w
a
m
o
d
el
th
at
h
as
b
ee
n
tr
ain
ed
to
d
is
tin
g
u
is
h
b
etwe
en
a
ce
r
tain
ca
teg
o
r
y
o
f
in
ter
est (
p
o
s
itiv
e
ca
teg
o
r
y
)
an
d
th
e
r
est
o
f
th
e
d
ata
(
n
e
g
ativ
e
ca
teg
o
r
y
)
wo
r
k
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
th
e
an
aly
s
is
an
d
id
en
tific
atio
n
o
f
em
o
tio
n
s
h
av
e
two
o
b
jectiv
es.
T
h
e
two
-
d
im
en
s
io
n
al
em
o
tio
n
m
o
d
el
is
cr
o
s
s
-
v
alid
ated
u
s
in
g
L
OOCV,
an
d
th
en
th
r
o
u
g
h
th
e
u
s
e
o
f
m
ac
h
in
e
lear
n
in
g
,
d
if
f
er
en
t
em
o
tio
n
s
ar
e
ass
ess
ed
an
d
p
r
ed
icted
f
r
o
m
p
er
ip
h
e
r
al
s
ig
n
als.
A
m
u
lti
-
task
ca
teg
o
r
izatio
n
ch
allen
g
e
is
th
e
r
ec
o
g
n
itio
n
o
f
em
o
tio
n
s
.
T
h
e
t
ests
u
s
e
th
e
b
en
ch
m
ar
k
DE
AP
d
ataset
,
wh
ich
co
n
tain
s
m
u
lti
-
ch
an
n
el
E
E
G
d
ata
alo
n
g
with
p
e
r
ip
h
er
al
s
ig
n
als
as
well
as
v
alen
ce
an
d
ar
o
u
s
al
d
ata.
3
2
E
E
G
s
ig
n
als
an
d
8
p
er
ip
h
er
al
s
ig
n
als
ar
e
u
s
ed
in
th
e
DE
AP
d
ataset.
All
test
s
ar
e
co
n
d
u
cted
o
n
MA
T
L
AB
2
0
1
7
a,
u
s
in
g
8
GB
R
A
M
an
d
a
6
4
-
b
it
I
n
tel
I
5
C
PU.
B
ef
o
r
e
th
e
an
aly
s
is
o
f
th
e
cu
r
r
en
t
r
esu
lts
,
p
r
e
v
io
u
s
s
tu
d
ies
lik
e
[
1
2]
,
[
14
]
,
[
16
]
,
[
1
7
]
,
[
22
]
,
[
23
]
h
a
v
e
b
ee
n
r
ev
iewe
d
b
ased
o
n
d
if
f
er
en
t p
h
y
s
io
lo
g
ical
s
ig
n
als,
ac
cu
r
ac
y
an
d
F
1
-
s
co
r
e.
T
h
e
class
if
icatio
n
r
ate
o
r
ac
cu
r
ac
y
f
o
r
th
e
v
alen
ce
t
y
p
e
o
f
e
m
o
tio
n
ca
teg
o
r
y
f
o
r
3
2
s
u
b
jec
ts
is
0
.
6
7
5
,
0
.
7
2
5
,
1
,
0
.
5
2
5
,
0
.
7
2
5
,
1
,
0
.
8
5
,
0
.
9
2
5
,
1
,
0
.
7
7
5
,
0
.
7
7
5
,
0
.
5
2
5
,
0
.
5
7
5
,
0
.
3
7
5
,
0
.
7
,
0
.
7
2
5
,
1
,
1
,
0
.
7
5
,
1
,
0
.
7
7
5
,
0
.
5
,
0
.
8
7
5
,
0
.
5
,
0
.
5
7
5
,
0
.
5
2
5
,
0
.
9
7
5
,
0
.
5
2
5
,
0
.
5
5
,
1
,
0
.
6
5
,
an
d
0
.
7
7
5
r
esp
ec
tiv
ely
f
r
o
m
s
0
1
to
s
3
2
.
T
h
e
av
er
a
g
e
ac
cu
r
ac
y
is
0
.
7
5
f
o
r
v
alen
ce
.
I
n
th
e
s
am
e
way
,
th
e
class
if
icatio
n
r
ate
o
r
ac
cu
r
ac
y
f
o
r
th
e
ar
o
u
s
al,
lik
in
g
,
an
d
d
o
m
in
an
ce
ty
p
e
o
f
em
o
tio
n
c
ateg
o
r
y
f
o
r
3
2
s
u
b
jects
was
a
ls
o
r
ec
o
r
d
ed
,
wh
ich
is
s
h
o
wn
in
T
ab
le
s
5
an
d
6
.
I
n
th
e
last
th
e
v
alu
e
o
f
t
h
e
ac
cu
r
ac
y
is
s
av
e
d
in
a
v
ar
iab
le
i
n
MA
T
L
AB
p
r
o
g
r
am
m
i
n
g
f
o
r
ea
ch
s
u
b
ject.
T
h
e
v
ar
iab
le
o
f
th
e
MA
T
L
AB
f
ile
an
d
th
e
last
av
er
ag
e
was
d
o
n
e.
T
h
e
F
1
s
co
r
e
f
o
r
th
e
v
alen
ce
ty
p
e
o
f
em
o
tio
n
ca
teg
o
r
y
f
o
r
3
2
s
u
b
jects
is
0
.
5
5
1
,
0
.
6
8
,
0
.
5
,
0
.
5
2
2
,
0
.
5
8
9
1
,
0
.
5
,
0
.
7
0
5
8
,
0
.
4
8
0
5
,
0
.
5
,
0
.
5
2
5
6
,
0
.
5
8
6
,
0
.
3
8
6
,
0
.
3
6
5
,
0
.
2
7
2
7
,
0
.
4
8
0
5
,
0
.
4
9
4
,
0
.
5
,
0
.
5
,
0
.
4
2
8
,
0
.
5
,
0
.
4
3
6
6
,
0
.
4
3
0
1
,
0
.
4
6
6
6
,
0
.
3
3
3
3
3
,
0
.
4
8
1
3
,
0
.
3
4
4
,
0
.
8
9
3
3
,
0
.
4
6
8
,
0
.
4
,
0
.
5
,
0
.
5
3
3
3
,
an
d
0
.
4
3
6
.
T
h
e
av
er
a
g
e
F
1
s
co
r
e
is
0
.
5
0
f
o
r
v
alen
c
e.
I
n
th
e
s
am
e
way
,
T
h
e
F1
-
s
co
r
e
f
o
r
t
h
e
ar
o
u
s
al,
lik
in
g
,
an
d
d
o
m
in
an
ce
ty
p
e
o
f
em
o
tio
n
ca
te
g
o
r
y
f
o
r
3
2
s
u
b
jects
was
also
r
ec
o
r
d
e
d
,
as
s
h
o
wn
in
T
ab
le
6
.
I
n
th
e
last
th
e
v
alu
e
o
f
F
1
-
s
co
r
e
is
s
av
ed
i
n
a
v
a
r
iab
le
in
MA
T
L
AB
p
r
o
g
r
a
m
m
i
n
g
f
o
r
ea
ch
s
u
b
ject.
T
h
e
f
in
d
i
n
g
s
o
f
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
ar
e
co
m
p
ar
e
d
with
th
e
p
r
ev
io
u
s
wo
r
k
[
1
2
]
,
[
1
4
]
,
[
1
6
]
,
[
1
7
]
,
[
2
2
]
,
[
2
3
]
.
C
o
m
p
ar
ed
to
o
th
er
in
v
esti
g
atio
n
s
,
th
is
ef
f
o
r
t
p
r
o
d
u
ce
d
th
e
b
est
ca
teg
o
r
izatio
n
o
f
v
ale
n
ce
class
f
in
d
in
g
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
7
6
-
9
8
4
982
Acc
o
r
d
in
g
to
th
e
ex
p
er
im
en
ta
l
f
in
d
in
g
s
,
th
e
s
u
g
g
ested
s
tu
d
y
class
if
ied
d
ata
f
o
r
ar
o
u
s
al,
v
alen
ce
,
lik
in
g
,
an
d
d
o
m
in
an
ce
o
n
t
h
e
DE
AP
d
ata
s
ets
with
an
ac
cu
r
ac
y
o
f
8
0
%,
7
5
%,
7
1
%,
a
n
d
7
8
%,
r
esp
ec
ti
v
ely
.
Ad
d
itio
n
ally
,
f
o
r
th
e
two
clas
s
es
p
r
o
b
lem
,
t
h
e
F1
-
s
co
r
e
v
alu
es
f
o
r
ar
o
u
s
al,
v
alen
ce
,
lik
in
g
,
an
d
d
o
m
in
a
n
ce
ar
e
0
.
5
0
,
0
.
4
9
,
0
.
4
7
,
a
n
d
0
.
4
7
,
r
esp
ec
tiv
ely
.
I
t
ap
p
ea
r
s
th
at
th
e
r
esu
lts
d
em
o
n
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
.
T
ab
le
5
an
d
T
a
b
le
6
s
h
o
w
t
h
e
ex
p
e
r
im
en
t
o
u
tco
m
es
th
at,
i
n
th
e
c
o
n
tex
t
o
f
p
h
y
s
io
lo
g
ical
p
er
ip
h
er
al
d
ata,
th
e
p
r
o
jecte
d
alg
o
r
ith
m
o
b
tain
s
a
m
ed
io
c
r
e
r
ec
o
g
n
itio
n
ac
c
u
r
a
cy
lev
el
.
F
o
u
r
p
e
r
ip
h
er
ical
s
ig
n
als,
s
u
ch
as
GSR
,
B
VP,
R
SP
,
an
d
E
MG
wer
e
u
s
ed
f
o
r
t
h
is
s
tu
d
y
,
f
o
r
a
s
in
g
le
ch
an
n
el
4
2
f
e
atu
r
es
h
av
e
b
ee
n
ex
tr
a
cte
d
an
d
ca
lcu
lated
f
o
r
f
o
u
r
s
aid
p
er
ip
h
er
ical
s
ig
n
als.
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
o
f
p
r
o
p
o
s
ed
wo
r
k
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
a
l
r
e
sp
o
n
se
A
r
o
u
sa
l
acc
V
a
l
e
n
c
e
acc
A
f
f
e
c
t
i
v
e
r
a
t
i
n
g
H
a
n
e
t
a
l
.
[
1
7
]
D
EA
P
P
P
G
,
EM
G
7
5
.
7
6
7
4
.
3
2
A
r
o
u
sa
l
,
v
a
l
e
n
c
e
Fu
e
t
a
l
.
[
1
6
]
D
EA
P
EEG
,
P
P
G
,
G
S
R
,
R
ES
6
3
.
6
6
4
.
4
A
r
o
u
sa
l
,
v
a
l
e
n
c
e
P
i
d
g
e
o
n
e
t
a
l
.
[
2
2
]
D
EA
P
R
S
P
6
1
.
2
5
6
4
.
2
4
A
r
o
u
sa
l
,
v
a
l
e
n
c
e
D
EA
P
G
S
R
6
2
.
5
0
6
0
.
1
8
A
r
o
u
sa
l
,
v
a
l
e
n
c
e
D
EA
P
B
V
P
6
3
.
4
9
6
1
.
1
3
A
r
o
u
sa
l
,
v
a
l
e
n
c
e
Le
e
e
t
a
l
.
[
1
4
]
D
EA
P
PPG
8
0
.
9
8
2
.
1
----
C
h
a
c
o
n
e
t
a
l
.
[
1
2
]
D
EA
P
H
R
V
,
B
P
M
,
p
u
l
se
5
7
.
0
6
0
.
6
-----
P
r
o
p
o
se
d
w
o
r
k
D
EA
P
G
S
R
,
B
V
P
,
R
S
P
,
a
n
d
E
M
G
8
0
.
0
0
7
5
.
0
0
A
r
o
u
sa
l
,
v
a
l
e
n
c
e
,
l
i
k
i
n
g
,
d
o
mi
n
a
n
c
e
T
ab
le
6
.
C
o
m
p
a
r
is
o
n
o
f
F1
-
s
co
r
e/ac
cu
r
ac
y
[
2
3
]
an
d
[
1
6
]
M
o
d
a
l
i
t
y
A
r
o
u
sa
l
V
a
l
e
n
c
e
Li
k
i
n
g
D
o
mi
n
a
n
c
e
A
c
c
F
1
S
A
c
c
F
1
S
A
c
c
F
1
S
A
c
c
F
1
S
K
o
e
l
s
t
r
a
l
e
t
a
l
.
[
2
3
]
5
7
.
0
0
.
5
3
3
6
2
.
7
0
.
6
0
8
5
9
.
1
0
.
5
0
2
--
--
Fu
e
t
a
l
.
[
1
6
]
6
4
.
4
0
.
6
7
9
6
3
.
6
0
.
6
5
3
--
--
--
--
P
r
o
p
o
se
d
m
e
t
h
o
d
8
0
.
0
0
.
5
0
7
5
.
0
0
.
4
9
7
1
.
0
0
.
4
9
7
8
.
0
0
.
4
7
4.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
SCO
P
E
Du
e
to
t
h
e
r
o
b
u
s
t
f
ea
t
u
r
e
e
x
tr
ac
tio
n
m
eth
o
d
a
n
d
ef
f
ec
tiv
e
cl
ass
if
ier
,
s
ev
er
al
r
ec
en
t
m
ac
h
in
e
lear
n
in
g
ex
p
er
im
en
ts
o
n
p
h
y
s
io
lo
g
ical
s
ig
n
als
an
d
em
o
tio
n
id
en
tifi
ca
tio
n
h
av
e
s
h
o
wn
p
r
o
m
is
in
g
r
esu
lts
.
T
h
is
wo
r
k
elab
o
r
ates
th
e
em
o
tio
n
r
ec
o
g
n
itio
n
u
s
in
g
p
e
r
ip
h
er
al
s
ig
n
al
s
with
th
e
c
o
m
b
in
atio
n
o
f
r
id
g
e
r
eg
r
ess
io
n
with
Fis
h
er
’
s
d
is
ce
r
n
m
en
t
an
aly
s
is
u
s
in
g
4
2
d
if
f
er
e
n
t
f
ea
tu
r
es
f
o
r
ea
ch
ce
ll
o
f
3
2
×4
0
s
ize
o
f
m
atr
ix
.
R
esu
lts
wer
e
ca
lcu
lated
b
ased
o
n
f
e
atu
r
es
r
ec
o
r
d
ed
1
,
2
8
0
tim
es.
L
OOCV
tech
n
iq
u
e
u
s
ed
f
o
r
d
eter
m
i
n
in
g
a
p
er
f
o
r
m
an
ce
p
r
ed
ictiv
e
m
o
d
el.
Fro
m
th
e
e
x
p
er
im
en
tal
r
esu
lts
,
ev
alu
ate
th
e
m
o
d
el
co
n
ce
r
n
in
g
ac
cu
r
ac
y
an
d
F1
-
s
co
r
e.
On
th
e
DE
AP
d
atasets
,
th
e
p
r
o
p
o
s
ed
s
tu
d
y
u
s
ed
f
o
u
r
p
er
ip
h
er
ica
l
s
ig
n
als,
s
u
ch
as
GSR
,
B
VP,
R
SP
,
an
d
E
MG
f
o
r
ar
o
u
s
al,
v
alen
ce
,
lik
in
g
,
an
d
d
o
m
in
an
ce
,
r
esp
ec
tiv
ely
,
an
d
o
b
tain
ed
h
ig
h
e
r
class
if
icatio
n
ac
cu
r
ac
y
o
f
8
0
%,
7
5
%,
7
1
%,
an
d
7
8
%.
I
n
th
e
f
u
tu
r
e
SKT,
E
C
G,
PP
G,
an
d
o
x
i
m
etr
y
o
f
p
u
ls
e
b
io
s
ig
n
als
ca
n
b
e
u
s
ed
f
o
r
em
o
tio
n
r
e
co
g
n
itio
n
with
d
if
f
er
e
n
t
d
ata
s
ets
f
o
r
b
et
ter
ac
cu
r
ac
y
with
d
if
f
er
e
n
t
co
m
b
in
atio
n
s
o
f
class
if
ier
s
alo
n
g
with
d
i
f
f
er
en
t
an
d
ap
p
r
o
p
r
iate
f
ea
tu
r
e
s
ets.
Hu
m
an
-
r
o
b
o
t
i
n
ter
ac
tio
n
s
,
elec
tr
o
n
ic
lear
n
i
n
g
,
an
aly
s
is
o
f
m
ar
k
ets,
an
d
s
ev
er
al
h
ea
lth
ca
r
e
a
p
p
licatio
n
s
s
u
ch
as
th
e
d
ia
g
n
o
s
is
o
f
d
e
p
r
ess
io
n
,
s
ch
izo
p
h
r
en
ia
,
alzh
eim
e
r
'
s
d
is
ea
s
e,
p
ar
k
in
s
o
n
'
s
d
is
ea
s
e,
an
d
o
th
er
co
n
d
itio
n
s
all
b
en
ef
it
f
r
o
m
t
h
e
u
s
ag
e
o
f
em
o
tio
n
s
.
Ho
wev
er
,
b
ec
au
s
e
t
h
er
e
ar
e
n
o
t
m
an
y
p
u
b
licly
a
v
ailab
le
d
atasets
,
th
er
e
h
as
n
o
t
b
ee
n
m
u
c
h
s
tu
d
y
in
th
ese
d
is
cip
lin
es
o
n
h
u
m
a
n
em
o
tio
n
d
etec
tio
n
s
y
s
tem
s
.
T
h
er
ef
o
r
e
,
to
in
c
r
ea
s
e
th
e
ap
p
licab
ilit
y
o
f
r
esear
ch
s
tu
d
ies
o
n
h
u
m
a
n
e
m
o
tio
n
s
,
o
u
r
e
v
alu
atio
n
ad
v
is
es
cr
ea
tin
g
an
d
m
ak
in
g
p
u
b
licly
av
ailab
le
d
atasets
.
T
h
e
f
in
d
in
g
s
p
r
esen
ted
i
n
th
is
s
tu
d
y
s
h
o
w
th
at
it
is
f
ea
s
ib
le
to
id
en
tify
em
o
tio
n
s
f
r
o
m
p
er
ip
h
er
al
p
h
y
s
io
lo
g
ical
d
ata.
Su
b
s
eq
u
en
t r
esear
ch
e
n
d
ea
v
o
r
s
will e
x
am
in
e
en
h
an
cin
g
th
e
tech
n
i
q
u
es f
o
r
e
x
tr
ac
tin
g
f
ea
tu
r
es to
au
g
m
e
n
t r
ec
o
g
n
itio
n
e
f
f
icac
y
an
d
in
v
est
ig
ate
s
o
p
h
is
ticated
n
eu
r
al
p
r
ed
ictio
n
m
o
d
els
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
S
o
l
e
y
ma
n
i
,
F
.
V
i
l
l
a
r
o
-
D
i
x
o
n
,
T
.
P
u
n
,
a
n
d
G
.
C
h
a
n
e
l
,
“
To
o
l
b
o
x
f
o
r
e
mo
t
i
o
n
a
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
f
r
o
m
p
h
y
si
o
l
o
g
i
c
a
l
si
g
n
a
l
s
(
TEA
P
)
,
”
Fr
o
n
t
i
e
rs
i
n
I
C
T
,
v
o
l
.
4
,
n
o
.
F
eb
,
F
e
b
.
2
0
1
7
,
d
o
i
:
1
0
.
3
3
8
9
/
f
i
c
t
.
2
0
1
7
.
0
0
0
0
1
.
[
2
]
J.
W
a
n
g
a
n
d
M
.
W
a
n
g
,
“
R
e
v
i
e
w
o
f
t
h
e
e
m
o
t
i
o
n
a
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
EEG
s
i
g
n
a
l
s,
”
C
o
g
n
i
t
i
v
e
R
o
b
o
t
i
c
s
,
v
o
l
.
1
,
p
p
.
2
9
–
4
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
g
r
.
2
0
2
1
.
0
4
.
0
0
1
.
[
3
]
R
.
A
l
h
a
l
a
s
e
h
a
n
d
S
.
A
l
a
s
a
sf
e
h
,
“
M
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
-
b
a
se
d
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
s
y
st
e
m
u
si
n
g
EEG
s
i
g
n
a
l
s,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
1
–
1
5
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
mp
u
t
e
r
s
9
0
4
0
0
9
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
-
b
a
s
ed
emo
ti
o
n
s
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
p
erip
h
era
l
s
ig
n
a
ls
(
Ta
r
u
n
K
u
ma
r
)
983
[
4
]
Y
.
Li
u
a
n
d
G
.
F
u
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
b
y
d
e
e
p
l
y
l
e
a
r
n
e
d
m
u
l
t
i
-
c
h
a
n
n
e
l
t
e
x
t
u
a
l
a
n
d
EEG
f
e
a
t
u
r
e
s,
”
F
u
t
u
re
G
e
n
e
ra
t
i
o
n
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
,
v
o
l
.
1
1
9
,
p
p
.
1
–
6
,
J
u
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
1
.
0
1
.
0
1
0
.
[
5
]
R
.
N
a
w
a
z
,
K
.
H
.
C
h
e
a
h
,
H
.
N
i
s
a
r
,
a
n
d
V
.
V
.
Y
a
p
,
“
C
o
m
p
a
r
i
so
n
o
f
d
i
f
f
e
r
e
n
t
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
m
e
t
h
o
d
s
f
o
r
EE
G
-
b
a
se
d
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
Bi
o
c
y
b
e
rn
e
t
i
c
s
a
n
d
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
.
3
,
p
p
.
9
1
0
–
9
2
6
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
b
e
.
2
0
2
0
.
0
4
.
0
0
5
.
[
6
]
S
.
K
a
t
s
i
g
i
a
n
n
i
s
a
n
d
N
.
R
a
m
z
a
n
,
“
D
R
EA
M
E
R
:
a
d
a
t
a
b
a
s
e
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
si
g
n
a
l
s
f
r
o
m
w
i
r
e
l
e
s
s
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
rn
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
,
J
a
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
.
[
7
]
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
.
[
8
]
E.
H
.
H
o
u
ss
e
i
n
,
A
.
H
a
mm
a
d
,
a
n
d
A
.
A
.
A
l
i
,
“
H
u
ma
n
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
EEG
-
b
a
s
e
d
b
r
a
i
n
–
c
o
m
p
u
t
e
r
i
n
t
e
r
f
a
c
e
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
:
a
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
4
,
n
o
.
1
5
,
p
p
.
1
2
5
2
7
–
1
2
5
5
7
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
022
-
0
7
2
9
2
-
4.
[
9
]
S
.
K
.
K
h
a
r
e
,
V
.
B
l
a
n
e
s
-
V
i
d
a
l
,
E.
S
.
N
a
d
i
mi
,
a
n
d
U
.
R
.
A
c
h
a
r
y
a
,
“
E
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
a
n
d
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
:
a
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
(
2
0
1
4
–
2
0
2
3
)
a
n
d
r
e
s
e
a
r
c
h
r
e
c
o
mm
e
n
d
a
t
i
o
n
s,
”
I
n
f
o
rm
a
t
i
o
n
Fu
si
o
n
,
v
o
l
.
1
0
2
,
p
.
1
0
2
0
1
9
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s.
2
0
2
3
.
1
0
2
0
1
9
.
[
1
0
]
H
.
P
.
M
a
r
t
i
n
e
z
,
Y
.
B
e
n
g
i
o
,
a
n
d
G
.
Y
a
n
n
a
k
a
k
i
s,
“
L
e
a
r
n
i
n
g
d
e
e
p
p
h
y
si
o
l
o
g
i
c
a
l
m
o
d
e
l
s o
f
a
f
f
e
c
t
,
”
I
EEE
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Ma
g
a
zi
n
e
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
2
0
–
3
3
,
M
a
y
2
0
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
M
C
I
.
2
0
1
3
.
2
2
4
7
8
2
3
.
[
1
1
]
S
.
O
h
,
J
.
Y
.
L
e
e
,
a
n
d
D
.
K
.
K
i
m,
“
T
h
e
d
e
si
g
n
o
f
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
o
p
t
i
ma
l
s
i
x
b
a
s
i
c
e
m
o
t
i
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
mu
l
t
i
p
l
e
p
h
y
s
i
o
l
o
g
i
c
a
l
s
i
g
n
a
l
s,
”
S
e
n
so
r
s (S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
2
0
,
n
o
.
3
,
p
.
8
6
6
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
0
3
0
8
6
6
.
[
1
2
]
L.
A
.
B
.
C
h
a
c
o
n
,
A
.
F
e
d
o
s
k
i
n
,
E.
S
h
c
h
e
g
l
a
k
o
v
a
,
S
.
N
e
a
msu
p
,
a
n
d
A
.
R
a
sh
e
d
,
“
Em
o
t
i
o
n
a
n
a
l
y
s
i
s
u
s
i
n
g
h
e
a
r
t
r
a
t
e
d
a
t
a
,
”
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s i
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
,
v
o
l
.
1
0
6
2
,
2
0
1
9
,
p
p
.
1
4
7
–
1
5
4
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
2
7
6
8
4
-
3
_
1
9
.
[
1
3
]
S
.
S
a
l
a
r
i
,
A
.
A
n
sar
i
a
n
,
a
n
d
H
.
A
t
r
i
a
n
f
a
r
,
“
R
o
b
u
st
e
m
o
t
i
o
n
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
s,
”
i
n
2
0
1
8
6
t
h
I
r
a
n
i
a
n
J
o
i
n
t
C
o
n
g
ress
o
n
F
u
zz
y
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s,
C
FI
S
2
0
1
8
,
I
EEE,
F
e
b
.
2
0
1
8
,
p
p
.
1
9
0
–
1
9
4
.
d
o
i
:
1
0
.
1
1
0
9
/
C
F
I
S
.
2
0
1
8
.
8
3
3
6
6
2
6
.
[
1
4
]
M
.
S
.
Le
e
,
Y
.
K
.
Le
e
,
M
.
T
.
Li
m
,
a
n
d
T.
K
.
K
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
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
se
l
e
c
t
e
d
st
a
t
i
st
i
c
a
l
p
h
o
t
o
p
l
e
t
h
y
sm
o
g
r
a
m
f
e
a
t
u
r
e
s,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
1
0
,
p
.
3
5
0
1
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
1
0
3
5
0
1
.
[
1
5
]
H
.
X
u
a
n
d
K
.
N
.
P
l
a
t
a
n
i
o
t
i
s
,
“
A
f
f
e
c
t
i
v
e
s
t
a
t
e
s
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
EEG
a
n
d
sem
i
-
su
p
e
r
v
i
se
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,”
i
n
2
0
1
6
I
EEE
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
Wo
r
k
sh
o
p
o
n
Mu
l
t
i
m
e
d
i
a
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
,
MM
S
P
2
0
1
6
,
I
EEE,
S
e
p
.
2
0
1
7
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
M
M
S
P
.
2
0
1
6
.
7
8
1
3
3
5
1
.
[
1
6
]
Z.
F
u
,
B
.
Zh
a
n
g
,
X
.
H
e
,
Y
.
L
i
,
H
.
W
a
n
g
,
a
n
d
J
.
H
u
a
n
g
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
mu
l
t
i
-
m
o
d
a
l
p
h
y
si
o
l
o
g
i
c
a
l
s
i
g
n
a
l
s
a
n
d
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
Fro
n
t
i
e
rs
i
n
N
e
u
r
o
sci
e
n
c
e
,
v
o
l
.
1
6
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s
.
2
0
2
2
.
1
0
0
0
7
1
6
.
[
1
7
]
E.
G
.
H
a
n
,
T
.
K
.
K
a
n
g
,
a
n
d
M
.
T.
L
i
m,
“
P
h
y
si
o
l
o
g
i
c
a
l
si
g
n
a
l
-
ba
s
e
d
r
e
a
l
-
t
i
m
e
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
e
x
p
l
o
i
t
i
n
g
m
u
t
u
a
l
i
n
f
o
r
mat
i
o
n
w
i
t
h
p
h
y
si
o
l
o
g
i
c
a
l
l
y
c
o
mm
o
n
f
e
a
t
u
r
e
s
,
”
E
l
e
c
t
r
o
n
i
c
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
1
3
,
p
.
2
9
3
3
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
2
1
3
2
9
3
3
.
[
1
8
]
S
.
M
.
H
a
m
,
H
.
M
.
Le
e
,
J.
H
.
Li
m,
a
n
d
J
.
S
e
o
,
“
A
n
e
g
a
t
i
v
e
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
s
y
st
e
m
w
i
t
h
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
b
a
s
e
d
mu
l
t
i
m
o
d
a
l
b
i
o
s
i
g
n
a
l
d
a
t
a
,
”
E
l
e
c
t
r
o
n
i
c
s (
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
2
0
,
p
.
4
3
2
1
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
2
2
0
4
3
2
1
.
[
1
9
]
X
.
W
a
n
g
,
Y
.
R
e
n
,
Z.
L
u
o
,
W
.
H
e
,
J.
H
o
n
g
,
a
n
d
Y
.
H
u
a
n
g
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
EEG
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
:
c
u
r
r
e
n
t
t
r
e
n
d
s
a
n
d
f
u
t
u
r
e
p
e
r
s
p
e
c
t
i
v
e
s,”
Fr
o
n
t
i
e
rs
i
n
Psy
c
h
o
l
o
g
y
,
v
o
l
.
1
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
s
y
g
.
2
0
2
3
.
1
1
2
6
9
9
4
.
[
2
0
]
A
.
D
e
ssai
a
n
d
H
.
V
i
r
a
n
i
,
“
Emo
t
i
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
C
W
T
o
f
E
C
G
a
n
d
G
S
R
s
i
g
n
a
l
s
u
si
n
g
v
a
r
i
o
u
s
C
N
N
mo
d
e
l
s
,
”
El
e
c
t
r
o
n
i
c
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
2
,
n
o
.
1
3
,
p
.
2
7
9
5
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
1
3
2
7
9
5
.
[
2
1
]
S
.
A
l
s
u
b
a
i
,
“
Em
o
t
i
o
n
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
n
o
r
m
a
l
i
z
e
d
a
t
t
e
n
t
i
o
n
-
b
a
se
d
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
m
o
d
i
f
i
e
d
-
r
a
n
d
o
m
f
o
r
e
s
t
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
1
,
p
.
2
2
5
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
1
0
2
2
5
.
[
2
2
]
M
.
P
i
d
g
e
o
n
,
N
.
K
a
n
w
a
l
,
N
.
M
u
r
r
a
y
,
a
n
d
M
.
A
sg
h
a
r
,
“
E
n
d
-
to
-
e
n
d
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
p
e
r
i
p
h
e
r
a
l
p
h
y
s
i
o
l
o
g
i
c
a
l
si
g
n
a
l
s,”
i
n
3
5
t
h
Bri
t
i
s
h
H
C
I
C
o
n
f
e
r
e
n
c
e
T
o
w
a
rd
s
a
H
u
m
a
n
-
C
e
n
t
re
d
D
i
g
i
t
a
l
S
o
c
i
e
t
y
,
H
C
I
2
0
2
2
,
2
0
2
2
.
d
o
i
:
1
0
.
1
4
2
3
6
/
e
w
i
c
/
H
C
I
2
0
2
2
.
1
9
.
[
2
3
]
S
.
K
o
e
l
s
t
r
a
e
t
a
l
.
,
“
D
EA
P
:
a
d
a
t
a
b
a
se
f
o
r
e
m
o
t
i
o
n
a
n
a
l
y
s
i
s;
u
si
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
ra
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
.
3
,
n
o
.
1
,
p
p
.
1
8
–
31
,
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
.
[
2
4
]
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
s
e
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
m
e
-
f
r
e
q
u
e
n
c
y
f
e
a
t
u
r
e
s,
”
S
e
n
so
r
s
,
v
o
l
.
2
1
,
n
o
.
1
8
,
p
.
6
3
0
0
,
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
.
[
2
5
]
T.
K
u
mar,
R
.
C
.
S
i
n
g
h
,
a
n
d
R
.
K
u
m
a
r
,
“
E
mo
t
i
o
n
s
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
p
h
y
si
o
l
o
g
i
c
a
l
s
i
g
n
a
l
s u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
T
e
c
h
n
o
l
o
g
i
c
a
l
A
d
v
a
n
c
e
m
e
n
t
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
s
,
I
C
T
AC
S
2
0
2
3
,
I
EEE
,
N
o
v
.
2
0
2
3
,
p
p
.
8
2
3
–
8
2
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
TA
C
S
5
9
8
4
7
.
2
0
2
3
.
1
0
3
9
0
2
6
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ta
r
u
n
K
u
m
a
r
re
c
e
iv
e
d
h
is
M
.
E.
fro
m
Th
a
p
a
r
Un
i
v
e
rsity
in
2
0
1
0
,
a
n
d
d
o
i
n
g
Ph
.
D.
fr
o
m
S
h
a
rd
a
Un
i
v
e
rsity
G
re
a
ter No
id
a
.
He
is t
e
a
c
h
in
g
sin
c
e
2
0
1
0
.
He
is a q
u
a
li
fie
d
NET
JRF
a
n
d
h
e
h
a
s
p
u
b
li
s
h
e
d
m
a
n
y
p
a
p
e
rs
i
n
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
h
a
s
c
o
m
p
lete
d
3
-
NPT
E
L
c
o
u
rse
s,
m
o
re
th
a
n
2
0
F
DP
fro
m
NITT
TR
Ch
a
n
d
i
g
a
rh
a
n
d
c
o
m
p
lete
d
8
-
NITT
T
m
o
d
u
le
a
s
p
e
r
AICTE
re
q
u
irem
e
n
ts.
He
h
a
s
a
lso
p
u
b
li
s
h
e
d
0
2
p
a
ten
ts
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
taru
n
k
u
m
a
r1
2
4
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
2
,
Feb
r
u
a
r
y
20
2
5
:
9
7
6
-
9
8
4
984
Dr
.
Ra
je
n
d
r
a
K
u
m
a
r
is
wo
rk
in
g
a
s
a
n
As
so
c
iate
P
ro
fe
ss
o
r
a
t
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
ri
n
g
,
S
h
a
r
d
a
S
c
h
o
o
l
o
f
En
g
in
e
e
ri
n
g
a
n
d
Tec
h
n
o
l
o
g
y
,
S
h
a
rd
a
Un
iv
e
rsity
,
G
re
a
ter
No
id
a
,
In
d
ia.
He
h
a
s
2
6
y
e
a
rs
o
f
Tea
c
h
in
g
a
n
d
Re
se
a
rc
h
Ex
p
e
rien
c
e
.
He
is
a
lso
a
g
u
st
p
ro
fe
ss
o
r
a
t
UCSI
Gra
d
u
a
te
Bu
sin
e
ss
S
c
h
o
o
l,
Ku
a
la
Lu
m
p
u
r
,
M
a
lay
sia
.
He
h
a
s
p
u
b
li
sh
e
d
0
5
tex
t
b
o
o
k
s,
0
2
m
o
n
o
g
ra
p
h
s,
0
4
p
a
ten
ts
a
n
d
0
7
e
d
it
e
d
b
o
o
k
s
.
He
h
a
s
p
u
b
li
sh
e
d
3
0
p
a
p
e
rs
in
n
a
ti
o
n
a
l/
in
ter
n
a
ti
o
n
a
l
j
o
u
r
n
a
ls
,
a
n
d
1
0
b
o
o
k
c
h
a
p
ters
.
He
h
a
s
v
isit
e
d
S
i
n
g
a
p
o
re
,
UA
E,
M
a
lay
sia
,
P
h
il
i
p
p
i
n
e
s,
Uz
b
e
k
istan
,
Vie
tn
a
m
,
In
d
o
n
e
sia
,
a
n
d
Th
a
il
a
n
d
to
p
a
rti
c
i
p
a
te
i
n
c
o
n
fe
re
n
c
e
a
s k
e
y
n
o
te sp
e
a
k
e
r/se
ss
io
n
c
h
a
ir/
p
a
p
e
r
p
re
se
n
ter.
He
is
se
n
io
r
m
e
m
b
e
r
o
f
IEE
E
a
n
d
m
e
m
b
e
r
o
f
m
a
n
y
o
th
e
r
p
r
o
fe
ss
io
n
a
l
b
o
d
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
taru
n
m
a
li
k
1
2
4
@g
m
a
il
.
c
o
m
.
Dr
.
Ra
m
Cha
n
d
r
a
S
in
g
h
h
a
s
a
rich
e
x
p
e
rien
c
e
o
f
o
v
e
r
3
0
y
e
a
rs
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
,
in
c
lu
d
i
n
g
o
v
e
r
1
3
y
e
a
r
s
a
s
a
P
ro
fe
ss
o
r
o
f
P
h
y
sic
s.
P
re
se
n
tl
y
,
he
is
a
P
r
o
fe
ss
o
r
o
f
P
h
y
sic
s,
a
n
d
i
n
a
d
d
it
io
n
t
o
th
a
t
h
e
is
a
lso
a
C
o
n
tr
o
ll
e
r
o
f
Ex
a
m
in
a
ti
o
n
s
a
t
S
h
a
rd
a
Un
i
v
e
rsity
,
G
re
a
ter
No
id
a
(UP).
He
o
b
tain
e
d
h
is
P
h
.
D.
d
e
g
re
e
fro
m
Ba
n
a
ra
s
Hin
d
u
Un
i
v
e
rsity
(BHU
),
Va
ra
n
a
si
in
t
h
e
o
re
ti
c
a
l
Co
n
d
e
n
se
d
M
a
tt
e
r
P
h
y
sic
s.
He
o
b
tain
e
d
h
i
s
B.
S
c
.
(Ho
n
s.)
a
n
d
M
.
S
c
.
d
e
g
re
e
s
in
P
h
y
sic
s
a
lso
fro
m
B
a
n
a
ra
s
Hin
d
u
Un
iv
e
rsity
.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
t
h
a
n
4
5
re
se
a
rc
h
p
a
p
e
rs
a
n
d
b
o
o
k
c
h
a
p
ter
s
in
p
e
e
r
-
re
v
iew
e
d
i
n
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
rc
sin
g
h
_
p
h
y
sic
s@
y
a
h
o
o
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.