I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
,
p
p
.
1012
~
1
0
2
0
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
2
.
pp
1
0
1
2
-
1020
1012
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Recog
nition o
f
e
m
o
tiona
l stat
es us
ing
EEG sign
a
ls
ba
sed o
n t
i
m
e
-
fre
quency
ana
ly
sis
and SVM
c
la
ss
ifier
F
a
bia
n P
a
rsia
G
eo
rg
e
,
I
s
t
ia
qu
e
M
a
nn
a
f
ee
Sh
a
ik
a
t
,
P
ro
m
m
y
S
ulta
na
F
er
da
w
o
o
s
,
M
o
ha
m
m
a
d
Z
a
v
id P
a
rv
ez
,
J
ia
Uddi
n
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
BRA
C
Un
iv
e
rsity
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
1
7
,
2
0
1
8
R
ev
i
s
ed
No
v
5
,
2
0
1
8
A
cc
ep
ted
Dec
3
,
2
0
1
8
T
h
e
re
c
o
g
n
it
io
n
o
f
e
m
o
ti
o
n
s
is
a
v
a
st
sig
n
i
f
ica
n
c
e
a
n
d
a
h
ig
h
d
e
v
e
lo
p
in
g
f
ield
o
f
re
se
a
rc
h
in
th
e
re
c
e
n
t
y
e
a
rs.
T
h
e
a
p
p
li
c
a
ti
o
n
s
o
f
e
m
o
ti
o
n
re
c
o
g
n
it
io
n
h
a
v
e
le
f
t
a
n
e
x
c
e
p
ti
o
n
a
l
m
a
rk
in
v
a
rio
u
s
f
ield
s
in
c
lu
d
in
g
e
d
u
c
a
ti
o
n
a
n
d
re
se
a
rc
h
.
T
ra
d
it
io
n
a
l
a
p
p
ro
a
c
h
e
s
u
se
d
f
a
c
ial
e
x
p
re
ss
io
n
s
o
r
v
o
ice
in
to
n
a
ti
o
n
to
d
e
tec
t
e
m
o
ti
o
n
s,
h
o
w
e
v
e
r,
f
a
c
i
a
l
g
e
stu
re
s
a
n
d
sp
o
k
e
n
lan
g
u
a
g
e
c
a
n
lea
d
to
b
ias
e
d
a
n
d
a
m
b
ig
u
o
u
s
re
su
lt
s.
T
h
is
is
w
h
y
,
re
se
a
rc
h
e
rs
h
a
v
e
sta
r
ted
to
u
se
e
lec
tro
e
n
c
e
p
h
a
lo
g
ra
m
(EE
G
)
tec
h
n
i
q
u
e
w
h
ich
is
w
e
ll
d
e
f
in
e
d
m
e
th
o
d
f
o
r
e
m
o
ti
o
n
re
c
o
g
n
it
i
o
n
.
S
o
m
e
a
p
p
ro
a
c
h
e
s
u
se
d
sta
n
d
a
r
d
a
n
d
p
re
-
d
e
f
in
e
d
m
e
th
o
d
s
o
f
th
e
sig
n
a
l
p
ro
c
e
ss
in
g
a
re
a
a
n
d
so
m
e
w
o
rk
e
d
w
it
h
e
i
th
e
r
f
e
we
r
c
h
a
n
n
e
ls
o
r
f
e
we
r
su
b
jec
ts
to
re
c
o
rd
EE
G
sig
n
a
ls
f
o
r
th
e
ir
re
se
a
rc
h
.
T
h
is
p
a
p
e
r
p
ro
p
o
se
d
a
n
e
m
o
ti
o
n
d
e
tec
t
io
n
m
e
th
o
d
b
a
se
d
o
n
t
im
e
-
f
re
q
u
e
n
c
y
d
o
m
a
in
sta
ti
stica
l
f
e
a
tu
re
s.
Bo
x
-
a
n
d
-
w
h
isk
e
r
p
lo
t
is
u
se
d
to
se
lec
t
th
e
o
p
ti
m
a
l
f
e
a
tu
re
s,
w
h
ich
a
re
late
r
f
e
e
d
to
S
V
M
c
las
sif
ier
f
o
r
train
in
g
a
n
d
t
e
stin
g
th
e
DEA
P
d
a
tas
e
t,
w
h
e
re
3
2
p
a
rti
c
i
p
a
n
ts
w
it
h
d
if
f
e
re
n
t
g
e
n
d
e
r
a
n
d
a
g
e
g
ro
u
p
s
a
re
c
o
n
sid
e
re
d
.
T
h
e
e
x
p
e
rim
e
n
tal
re
su
lt
s
sh
o
w
th
a
t
th
e
p
ro
p
o
s
e
d
m
e
th
o
d
e
x
h
ib
it
s
9
2
.
3
6
%
a
c
c
u
ra
c
y
f
o
r
o
u
r
tes
ted
d
a
tas
e
t.
In
a
d
d
it
io
n
,
th
e
p
ro
p
o
se
d
m
e
th
o
d
o
u
t
p
e
rf
o
rm
s
th
a
n
th
e
sta
te
-
of
-
a
rt
m
e
th
o
d
s
b
y
e
x
h
ib
it
in
g
h
ig
h
e
r
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
A
cc
u
r
ac
y
E
E
G
s
ig
n
al
E
m
o
tio
n
s
Featu
r
es
FFT
Fre
q
u
en
c
y
b
an
d
s
SVM
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
J
ia
Ud
d
in
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
,
B
R
AC
U
n
iv
er
s
it
y
,
6
6
Mo
h
a
k
h
ali
,
Dh
ak
a
-
1
2
1
2
,
B
an
g
lad
esh
.
E
m
ail: j
ia.
u
d
d
in
@
b
r
ac
u
.
ac
.
b
d
1.
I
NT
RO
D
UCT
I
O
N
E
m
o
tio
n
,
b
ein
g
a
n
o
n
-
v
er
b
al
v
ital a
p
p
r
o
ac
h
f
o
r
s
o
cial
in
ter
ac
tio
n
,
is
a
p
s
y
ch
o
lo
g
ical
an
d
m
en
tal
s
ta
te
o
f
m
in
d
th
at
p
r
o
v
o
k
es
u
s
to
ef
f
ec
ti
v
el
y
r
ea
ct
to
a
ce
r
tai
n
s
itu
a
tio
n
b
ased
o
n
p
ast
ex
p
er
ien
ce
[
1
]
.
T
h
e
i
m
p
le
m
en
ta
tio
n
o
f
e
m
o
tio
n
r
e
co
g
n
itio
n
ca
n
b
e
ap
p
li
ed
to
v
a
r
io
u
s
f
ield
s
s
u
c
h
a
s
ed
u
ca
tio
n
,
co
g
n
i
tiv
e
s
cie
n
ce
,
en
ter
tai
n
m
e
n
t,
m
ac
h
in
e
lear
n
in
g
,
s
el
f
-
co
n
tr
o
l
a
n
d
s
ec
u
r
it
y
,
b
io
m
ed
ical
en
g
i
n
ee
r
in
g
,
m
ar
k
eti
n
g
a
n
d
p
r
o
d
u
ctio
n
.
A
cc
o
r
d
in
g
to
R
u
s
s
ell,
a
n
y
d
is
cr
ete
e
m
o
tio
n
c
an
b
e
d
ed
u
cted
f
r
o
m
t
h
eir
le
v
el
o
f
ar
o
u
s
al
a
n
d
v
alen
ce
u
s
in
g
h
is
C
ir
cu
m
p
lex
Mo
d
el
o
f
E
m
o
tio
n
[
2
]
.
Ma
n
y
e
x
i
s
ti
n
g
m
et
h
o
d
s
i
m
p
le
m
en
ted
f
ac
ial
e
x
p
r
ess
io
n
,
s
p
e
ec
h
s
i
g
n
als,
a
n
d
s
el
f
-
r
ati
n
g
s
t
o
class
i
f
y
e
m
o
tio
n
s
[
3
]
,
[
4
]
.
Ho
w
e
v
er
,
t
h
e
s
y
s
te
m
s
u
s
ed
i
n
t
h
ese
ex
i
s
tin
g
m
et
h
o
d
s
u
s
u
al
l
y
f
ai
l
to
a
ck
n
o
w
led
g
e
all
th
e
d
etailed
e
m
o
tio
n
al
in
p
u
ts
f
o
r
p
r
o
ce
s
s
in
g
,
s
u
ch
as
t
h
e
h
a
n
d
g
est
u
r
es
o
r
t
h
e
to
n
e
o
f
t
h
e
v
o
ice,
th
u
s
lead
in
g
to
v
ag
u
e
an
d
b
iased
o
u
tco
m
e
[
3
]
.
So
m
e
ap
p
r
o
ac
h
es
u
s
ed
s
u
b
j
ec
tiv
e
m
ea
s
u
r
e
m
e
n
t
t
h
at
ca
n
a
f
f
ec
t
t
h
e
en
d
r
esu
lt
as
th
e
p
r
esen
ce
o
f
an
o
m
a
lo
u
s
tr
ials
ca
n
b
e
s
ig
n
if
ican
t
[
4
]
.
Af
ter
th
e
h
i
g
h
in
f
l
u
en
ce
o
f
E
lec
tr
o
en
ce
p
h
alo
g
r
a
m
(
E
E
G)
s
ig
n
a
ls
o
n
t
h
e
f
ield
o
f
r
esear
ch
,
it
w
a
s
o
b
s
er
v
ed
th
at
h
u
m
a
n
e
m
o
t
io
n
ca
n
b
e
r
ep
r
esen
ted
m
o
r
e
ac
cu
r
atel
y
w
ith
E
E
G
s
i
g
n
a
ls
th
an
w
it
h
f
ac
ia
l
g
e
s
t
u
r
es,
s
p
ee
ch
s
i
g
n
al
s
,
o
r
s
elf
-
r
ep
o
r
tin
g
i
n
f
o
r
m
atio
n
[
5
]
.
E
m
o
tio
n
al
ac
ti
v
itie
s
ca
u
s
e
th
e
b
r
ain
to
g
en
er
ate
s
i
g
n
a
ls
i
n
th
e
f
o
r
m
s
o
f
w
a
v
es
a
n
d
th
e
tech
n
iq
u
e
u
s
ed
to
r
ec
o
r
d
th
ese
s
ig
n
al
s
is
k
n
o
w
n
as
E
E
G
[
5
]
.
P
r
e
d
ictin
g
e
m
o
t
io
n
s
u
s
in
g
E
E
G
s
ig
n
al
s
w
a
s
f
ir
s
t
in
tr
o
d
u
ce
d
b
y
Mu
s
h
a
et
a
l
.
[
6
]
.
Fro
m
t
h
en
o
n
w
ar
d
,
s
tu
d
ies
o
n
t
h
is
ar
ea
i
s
b
r
in
g
in
g
m
o
r
e
in
ter
e
s
t
i
n
t
h
e
cu
r
r
en
t
y
ea
r
s
f
o
r
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
-
8708
R
ec
o
g
n
itio
n
o
f e
mo
tio
n
a
l sta
tes u
s
in
g
E
E
G
s
ig
n
a
ls
b
a
s
ed
o
n
time
-
fr
eq
u
en
cy
…
(
F
a
b
ia
n
P
a
r
s
ia
Geo
r
g
e
)
1013
m
ac
h
in
e
lear
n
i
n
g
p
u
r
p
o
s
e
a
n
d
th
e
p
r
o
v
i
s
io
n
o
f
le
s
s
e
x
p
en
s
i
v
e
E
E
G
m
ea
s
u
r
in
g
d
e
v
ices.
I
n
n
u
m
er
o
u
s
in
v
e
s
ti
g
atio
n
s
,
e
x
p
er
i
m
e
n
t
s
wer
e
r
estricte
d
to
v
er
y
f
e
w
s
u
b
j
ec
ts
,
b
u
t
t
h
e
m
et
h
o
d
s
i
m
p
le
m
en
ted
f
o
r
a
s
i
n
g
le
s
u
b
j
ec
t
w
er
e
i
n
ad
eq
u
atel
y
s
i
m
p
lif
ied
an
d
co
u
ld
n
o
t b
e
u
tili
ze
d
b
r
o
ad
ly
f
o
r
m
u
ltip
le
s
u
b
j
ec
ts
[
7
]
.
Ma
n
y
s
t
u
d
ies
w
er
e
li
m
ited
to
f
e
w
c
h
an
n
els
i
n
o
r
d
er
to
av
o
id
h
ig
h
co
m
p
le
x
it
y
a
n
d
co
m
p
u
tat
io
n
al
co
s
t
s
n
e
v
er
th
ele
s
s
,
t
h
i
s
ca
n
lead
to
f
ee
b
le
r
esu
l
t
d
u
e
to
l
ac
k
o
f
ad
eq
u
ate
in
f
o
r
m
atio
n
[
8
]
.
Fo
r
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
p
r
o
ce
s
s
,
d
if
f
er
en
t
m
et
h
o
d
o
lo
g
ies
w
er
e
u
s
ed
to
r
etr
iev
e
f
ea
t
u
r
es
i
n
p
r
ev
io
u
s
s
tu
d
ie
s
an
d
t
h
ese
i
n
cl
u
d
ed
Sa
m
p
le
E
n
tr
o
p
y
[
9
]
,
Au
to
r
eg
r
es
s
i
v
e
(
AR
)
Mo
d
el
[
1
0
]
,
Dis
cr
ete
W
av
elet
T
r
an
s
f
o
r
m
(
DW
T
)
[
1
1
]
,
an
d
Fas
t
Fo
u
r
ier
T
r
an
s
f
o
r
m
at
io
n
(
FF
T
)
[
1
2
]
.
C
lass
i
f
icatio
n
o
f
th
ese
ex
tr
ac
ted
f
ea
t
u
r
es
w
a
s
d
o
n
e
u
s
in
g
v
ar
io
u
s
clas
s
i
f
ier
s
b
y
t
h
e
r
esear
c
h
er
s
s
u
c
h
as S
u
p
p
o
r
t V
ec
to
r
Ma
ch
in
e
(
SVM)
[
1
3
,
1
4
]
,
Neu
r
al
Net
w
o
r
k
[
1
5
]
,
an
d
k
-
n
ea
r
est
n
ei
g
h
b
o
r
(
KNN)
[
1
6
]
.
R
ef
er
r
i
n
g
to
th
e
p
r
ev
io
u
s
l
y
s
p
ec
if
ied
is
s
u
es
[
3
]
,
[
4
]
,
[
7
]
,
[
8
]
,
a
n
o
v
el
m
et
h
o
d
o
lo
g
y
,
f
o
r
em
o
tio
n
r
ec
o
g
n
itio
n
b
ased
o
n
ti
m
e
-
f
r
eq
u
en
c
y
a
n
al
y
s
i
s
,
is
p
r
o
p
o
s
e
d
a
n
d
ev
alu
ated
w
i
th
E
E
G
s
ig
n
a
ls
f
r
o
m
DE
A
P
d
ataset
[
1
7
]
.
I
n
th
e
p
r
o
p
o
s
ed
m
o
d
el,
i
n
itiall
y
,
th
e
E
E
G
s
i
g
n
als
f
r
o
m
o
n
l
y
t
h
e
p
r
ef
r
o
n
tal
c
o
r
tex
ar
e
r
etr
iev
ed
f
o
r
f
u
r
th
er
w
o
r
k
s
i
n
ce
e
m
o
tio
n
al
ac
ti
v
itie
s
o
cc
u
r
m
ai
n
l
y
in
th
e
f
r
o
n
tal
a
n
d
te
m
p
o
r
al
lo
b
e
o
f
th
e
b
r
ai
n
[
1
8
]
.
A
d
d
itio
n
al
l
y
,
th
i
s
al
s
o
r
ed
u
ce
d
th
e
to
tal
n
u
m
b
er
o
f
ch
a
n
n
e
ls
t
h
at
ar
e
to
b
e
u
s
ed
i
n
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
et
h
o
d
,
as
th
e
ir
r
elev
an
t
ch
a
n
n
els
ar
e
alr
ea
d
y
d
is
ca
r
d
ed
b
ef
o
r
eh
an
d
.
T
h
is
lead
to
less
co
m
p
u
tatio
n
al
co
s
t
an
d
th
u
s
in
cr
ea
s
ed
th
e
ef
f
icie
n
c
y
o
f
t
h
e
al
g
o
r
ith
m
s
u
s
ed
i
n
o
u
r
tech
n
iq
u
e
[
1
9
]
.
E
x
is
ti
n
g
m
et
h
o
d
s
,
w
o
r
k
i
n
g
w
it
h
f
r
eq
u
en
c
y
b
a
n
d
s
,
ex
tr
ac
ted
all
th
e
f
i
v
e
t
y
p
es
o
f
f
r
eq
u
en
c
y
b
an
d
s
,
n
a
m
el
y
d
elta
(
0
.
5
-
4
H
z)
,
th
eta
(
4
-
7
Hz)
,
alp
h
a
(
7
-
1
3
Hz)
,
b
eta
(
1
3
-
3
0
Hz)
,
an
d
g
a
m
m
a
(
3
0
-
6
0
Hz)
[
2
0
]
.
A
cc
o
r
d
in
g
to
th
e
s
tate
-
of
-
th
e
-
ar
t
m
eth
o
d
s
,
th
e
e
m
o
tio
n
al
a
n
d
co
g
n
iti
v
e
ac
tiv
i
ties
o
f
th
e
b
r
ain
ca
n
b
e
w
ell
s
i
g
n
i
f
ied
u
s
i
n
g
t
h
e
alp
h
a,
b
eta,
an
d
th
eta
f
r
eq
u
e
n
c
y
b
an
d
s
[
8
]
,
[
2
1
]
.
T
h
er
ef
o
r
e,
th
ese
s
p
ec
if
ic
b
an
d
s
w
er
e
co
n
s
id
er
ed
in
th
i
s
p
ap
er
.
T
h
e
d
ataset
is
d
is
tr
ib
u
ted
i
n
to
f
o
u
r
e
m
o
tio
n
a
l
q
u
ad
r
a
n
ts
,
wh
ich
ar
e
h
i
g
h
ar
o
u
s
al
-
h
i
g
h
v
ale
n
ce
(
H
AHV)
,
lo
w
ar
o
u
s
al
-
h
i
g
h
v
alen
ce
(
L
A
HV)
,
lo
w
ar
o
u
s
al
-
lo
w
v
alen
ce
(
L
AL
V)
,
an
d
h
i
g
h
ar
o
u
s
al
-
lo
w
v
a
len
ce
(
H
AL
V)
.
T
h
e
d
ataset
in
ea
c
h
s
p
ec
if
ic
q
u
ad
r
an
t
w
as t
h
e
n
a
v
er
ag
ed
f
o
r
all
p
ar
ticip
an
ts
f
o
r
t
h
e
s
p
ec
i
f
ic
e
m
o
tio
n
.
T
h
e
r
ea
s
o
n
f
o
r
av
er
a
g
in
g
th
e
s
a
m
p
les
ac
co
r
d
in
g
to
th
e
q
u
ad
r
an
t
is
d
u
e
to
th
e
in
co
n
s
is
te
n
c
y
i
n
e
m
o
tio
n
s
f
elt
b
y
th
e
p
ar
ticip
an
ts
.
No
t
all
th
e
p
ar
ticip
an
ts
f
ee
l
th
e
s
a
m
e
e
m
o
tio
n
f
o
r
a
p
ar
tic
u
lar
v
id
eo
w
h
ic
h
in
d
icate
s
t
h
at
s
o
m
e
s
a
m
p
l
es
in
th
e
E
E
G
s
ig
n
al
s
ar
e
an
o
m
alo
u
s
an
d
t
h
u
s
ca
n
g
r
ea
tl
y
af
f
ec
t
th
e
e
n
d
r
esu
lt.
T
h
e
p
r
e
m
is
e
o
f
av
er
a
g
i
n
g
is
to
r
ed
u
ce
d
ata
d
ev
iatio
n
an
d
to
s
tatis
tica
ll
y
r
ea
ch
clo
s
e
to
th
e
ac
tu
al
v
al
u
e.
T
h
is
h
y
p
o
t
h
esi
s
m
i
g
h
t
i
m
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
th
e
clas
s
i
f
icatio
n
p
r
o
c
ess
.
Fi
n
all
y
,
th
e
s
tati
s
tical
f
ea
tu
r
e
s
,
ex
tr
ac
ted
in
t
h
e
f
r
eq
u
e
n
c
y
d
o
m
ai
n
,
w
er
e
t
h
e
n
f
ed
in
to
th
e
S
VM
clas
s
i
f
ier
in
o
r
d
er
to
class
if
y
th
e
e
m
o
tio
n
s
.
T
h
e
s
u
b
s
eq
u
en
t
s
ec
tio
n
s
o
f
t
h
e
p
ap
er
h
av
e
b
ee
n
o
r
g
an
ize
d
as
f
o
llo
w
s
.
Sect
io
n
2
in
tr
o
d
u
ce
s
th
e
d
ataset
u
s
ed
i
n
t
h
i
s
p
ap
er
,
as
w
ell
as
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
f
o
r
r
ec
o
g
n
izi
n
g
e
m
o
tio
n
.
Se
ctio
n
3
p
r
o
v
id
es
th
e
ex
p
er
i
m
e
n
tal
r
es
u
lts
alo
n
g
w
i
t
h
th
eir
a
n
al
y
s
i
s
.
Fin
a
ll
y
,
S
ec
ti
o
n
4
co
n
clu
d
es t
h
e
p
ap
er
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
illu
s
tr
a
ted
in
Fi
g
u
r
e
1
r
ep
r
esen
ts
t
h
e
o
v
er
all
f
lo
w
o
f
o
u
r
w
o
r
k
.
Fo
r
th
i
s
r
esear
ch
,
th
e
E
E
G
s
ig
n
al
s
w
e
r
e
f
ir
s
t
ac
cu
m
u
lated
f
o
llo
w
ed
b
y
d
ata
p
r
ep
r
o
ce
s
s
in
g
.
Nex
t,
b
an
d
s
o
f
s
p
ec
if
i
c
f
r
eq
u
en
c
ies
w
er
e
e
x
tr
ac
ted
f
r
o
m
th
e
p
r
ep
r
o
ce
s
s
ed
d
ata.
Su
b
s
eq
u
en
tl
y
,
s
u
itab
le
f
ea
t
u
r
es
w
er
e
e
x
tr
ac
ted
an
d
s
elec
te
d
to
b
e
f
ed
in
to
th
e
clas
s
if
ier
.
Fi
n
all
y
,
SVM
cla
s
s
i
f
ier
w
a
s
u
s
ed
to
class
i
f
y
t
h
ese
s
ele
cted
f
ea
tu
r
es.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
2
.
1
.
Da
t
a
d
escript
io
n
I
n
o
u
r
r
e
s
ea
r
ch
,
w
e
u
s
ed
DE
AP
d
ataset
[
1
7
]
as
t
h
e
s
o
u
r
ce
o
f
b
r
ain
s
ig
n
al
s
.
I
t
i
s
a
m
u
l
ti
m
o
d
al
d
ataset
w
h
ic
h
ca
n
b
e
u
s
ed
to
an
al
y
ze
th
e
h
u
m
a
n
af
f
ec
ti
v
e
s
ta
tes.
T
h
e
d
ata
co
llectio
n
p
r
o
ce
s
s
w
a
s
ca
r
r
ied
o
u
t
in
t
h
e
co
n
tr
o
lled
lig
h
t
en
v
ir
o
n
m
e
n
t.
B
io
s
em
i
A
cti
v
eT
w
o
s
y
s
te
m
w
as
u
s
ed
to
r
ec
o
r
d
th
e
E
E
G
s
ig
n
als
o
f
ea
ch
p
ar
ticip
an
t.
T
w
o
co
m
p
u
ter
s
wer
e
u
s
ed
w
h
ich
w
er
e
s
y
n
c
h
r
o
n
ized
p
er
io
d
ically
w
it
h
th
e
h
e
lp
o
f
m
ar
k
er
s
-
o
n
e
f
o
r
r
ec
o
r
d
in
g
th
e
s
ig
n
als
a
n
d
an
o
th
er
f
o
r
p
r
esen
ta
tio
n
o
f
s
ti
m
u
li.
T
h
e
ex
p
er
i
m
e
n
t
w
a
s
c
ar
r
ied
o
u
t
u
s
i
n
g
a
1
-
m
i
n
u
te
4
0
m
u
s
ic
v
id
eo
s
d
is
p
lay
ed
in
1
7
-
i
n
c
h
s
cr
ee
n
b
u
t
(
8
0
0
x
6
0
0
)
r
eso
lu
tio
n
w
as
m
ai
n
tain
ed
to
m
i
n
i
m
ize
E
E
G
S
i
g
na
l
s
S
i
g
na
l
P
r
e
pr
o
c
e
ss
i
ng
S
i
g
na
l
R
e
f
i
ni
ng
B
an
d
E
xt
r
ac
t
i
o
n
F
e
at
ur
e
E
xt
r
ac
t
i
o
n
E
m
o
t
i
o
n
C
l
as
si
f
i
c
at
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
0
1
2
-
1020
1014
th
e
e
y
e
m
o
v
e
m
en
ts
.
Fo
r
th
e
ex
p
er
i
m
en
t,
3
2
Ag
C
l
elec
tr
o
d
es
w
er
e
u
s
ed
to
r
ec
o
r
d
th
e
E
E
G
s
ig
n
al
s
at
a
s
a
m
p
li
n
g
r
ate
o
f
5
1
2
Hz.
1
6
m
ale
an
d
1
6
f
e
m
a
le
p
ar
ticip
an
ts
w
ith
a
g
es
r
an
g
i
n
g
f
r
o
m
1
9
to
3
7
w
er
e
ch
o
s
en
to
co
n
d
u
ct
t
h
e
e
x
p
er
i
m
e
n
t.
Af
ter
2
0
v
id
eo
tr
ials
,
t
h
e
s
u
b
j
ec
ts
co
u
ld
tak
e
a
b
r
ea
k
f
o
r
s
n
ac
k
s
.
E
ac
h
tr
ial
last
ed
f
o
r
6
3
s
ec
o
n
d
s
,
a
to
tal
o
f
6
0
-
s
ec
o
n
d
v
id
eo
an
d
3
-
s
ec
o
n
d
p
r
e
-
tr
ial
b
aselin
e.
A
t
th
e
e
n
d
o
f
ea
ch
v
id
eo
tr
ial,
a
m
an
u
al
r
atin
g
w
as
d
o
n
e
b
y
t
h
e
s
u
b
j
ec
ts
o
n
a
s
ca
le
o
f
1
-
9
to
d
eter
m
i
n
e
f
o
u
r
d
i
f
f
er
en
t
e
m
o
tio
n
s
(
A
r
o
u
s
a
l,
Do
m
i
n
an
ce
,
L
i
k
in
g
,
an
d
Vale
n
ce
)
.
2
.
2
.
Sig
na
l p
re
pro
ce
s
s
ing
T
h
e
d
ataset
w
as
d
o
w
n
s
a
m
p
l
ed
in
to
1
2
8
Hz
an
d
th
en
E
l
ec
tr
o
o
cu
lo
g
r
ap
h
y
(
E
OG)
ar
ti
f
ac
ts
w
er
e
r
e
m
o
v
ed
d
u
e
to
e
y
e
m
o
v
e
m
e
n
ts
.
T
h
e
s
ig
n
al
s
w
er
e
th
e
n
f
ilte
r
ed
w
it
h
a
m
in
i
m
u
m
o
f
4
Hz
an
d
a
m
a
x
i
m
u
m
o
f
4
5
Hz
u
s
i
n
g
a
b
an
d
-
p
ass
f
ilter
.
T
o
cr
ea
te
a
co
m
m
o
n
r
e
f
er
en
ce
,
th
e
d
ata
w
er
e
a
v
er
ag
ed
.
L
a
ter
o
n
,
th
e
d
ata
w
as
s
eg
m
e
n
ted
in
to
6
0
s
ec
o
n
d
s
b
y
r
e
m
o
v
i
n
g
th
e
3
s
ec
o
n
d
s
p
r
e
-
t
r
ial
b
aselin
e
a
n
d
w
as
ar
r
an
g
e
d
in
E
x
p
er
i
m
en
t_
id
o
r
d
er
.
Fo
r
o
u
r
r
esear
ch
,
w
e
h
a
v
e
c
h
o
s
en
p
r
e
-
p
r
o
ce
s
s
ed
d
ata
f
il
es
t
h
at
i
n
cl
u
d
ed
E
E
G
s
i
g
n
a
l
s
o
f
ea
c
h
p
ar
ticip
an
t.
A
l
l p
ar
ticip
an
ts
f
il
e
h
av
e
t
w
o
ar
r
a
y
s
s
u
c
h
as d
ata
an
d
lab
el,
w
h
ich
i
s
clar
if
ied
b
elo
w
i
n
T
ab
le
1
.
T
ab
le
1
.
C
o
n
ten
ts
o
f
ea
c
h
P
ar
ticip
an
t File
s
N
a
me
S
i
z
e
D
e
scri
p
t
i
o
n
D
a
t
a
4
0
×
4
0
×
8
0
6
4
V
i
d
e
o
/
t
r
i
a
l
×
C
h
a
n
n
e
l
×
D
a
t
a
L
a
b
e
l
4
0
×
4
V
i
d
e
o
/
t
r
i
a
l
×
L
a
b
e
l
(
V
a
l
e
n
c
e
,
A
r
o
u
sal
,
D
o
mi
n
a
n
c
e
,
L
i
k
i
n
g
)
T
h
e
d
ata
ar
r
ay
co
n
tain
s
E
E
G
s
ig
n
al
s
f
o
r
all
th
e
p
ar
ticip
an
t
s
an
d
all
th
e
v
id
eo
s
in
cl
u
s
iv
e
wh
er
ea
s
th
e
lab
els
ar
r
ay
co
n
tai
n
s
th
e
v
id
eo
I
D
class
if
icatio
n
s
ac
co
r
d
in
g
to
th
e
lab
el
(
v
alen
ce
,
ar
o
u
s
al,
d
o
m
i
n
an
ce
,
an
d
lik
i
n
g
)
.
2
.
3
.
Sig
na
l r
ef
ini
ng
As th
e
f
ir
s
t step
to
w
ar
d
s
b
an
d
ex
tr
ac
tio
n
,
t
h
e
d
at
a
w
er
e
f
ir
s
t r
ea
r
r
an
g
ed
to
m
a
k
e
it a
p
p
r
o
p
r
ia
te
f
o
r
th
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
.
T
h
e
p
r
ep
r
o
ce
s
s
ed
d
ata
f
r
o
m
DE
A
P
d
at
aset
w
a
s
u
s
ed
f
o
r
o
u
r
w
o
r
k
w
h
ic
h
co
n
tain
ed
3
2
f
iles
r
ep
r
esen
ti
n
g
ea
c
h
p
ar
tici
p
an
t.
E
ac
h
f
ile
co
n
tai
n
ed
t
w
o
ar
r
a
y
s
:
o
n
e
w
as
3
D
ar
r
a
y
,
n
a
m
ed
Da
ta
,
o
f
s
ize
4
0
x
4
0
x
8
0
6
4
an
d
an
o
th
er
w
as
th
e
2
D
ar
r
a
y
,
n
a
m
ed
La
b
el
,
o
f
s
ize
4
0
x
4
.
Fo
r
o
u
r
s
t
u
d
y
,
t
h
e
3
D
d
ata
ar
r
ay
w
a
s
u
s
ed
th
r
o
u
g
h
o
u
t
t
h
e
co
u
r
s
e
o
f
o
u
r
w
o
r
k
.
A
to
tal
o
f
4
0
ch
an
n
els
w
er
e
u
s
ed
to
r
ec
o
r
d
th
e
E
E
G
s
ig
n
als,
o
u
t
o
f
w
h
ic
h
3
2
w
er
e
E
E
G
ch
a
n
n
els
an
d
8
w
er
e
p
er
ip
h
er
al
ch
an
n
el
s
.
P
r
ev
io
u
s
s
t
u
d
ies
i
llu
s
tr
ated
th
at
th
e
in
f
o
r
m
atio
n
r
elate
d
to
e
m
o
ti
o
n
s
ar
e
f
o
cu
s
ed
m
o
s
tl
y
i
n
th
e
f
r
o
n
tal
an
d
te
m
p
o
r
al
ar
ea
s
o
f
th
e
b
r
ain
[
1
8
]
.
Ho
w
e
v
er
,
in
o
r
d
er
to
d
ec
r
ea
s
e
th
e
co
m
p
u
tatio
n
a
l
co
s
ts
o
f
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
,
w
e
o
n
l
y
w
o
r
k
ed
w
it
h
t
h
e
ch
an
n
el
s
t
h
at
ar
e
r
elate
d
to
t
h
e
f
r
o
n
ta
l
lo
b
e
o
f
t
h
e
b
r
ai
n
a
n
d
th
e
s
e
c
h
a
n
n
el
s
ar
e
Fp
1
,
F3
,
F
7
,
FC
5
,
F
C
1
,
Fp
2
,
Fz,
F4
,
F8
,
FC
6
,
an
d
FC
2
.
C
l
ass
i
f
icatio
n
an
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
f
r
o
m
3
D
ar
r
a
y
w
er
e
lab
o
r
io
u
s
as
it
w
a
s
h
ar
d
to
m
an
ip
u
late
t
h
e
d
ata
as
p
e
r
o
u
r
r
eq
u
ir
e
m
e
n
ts
.
Fo
r
t
h
is
r
ea
s
o
n
,
th
e
p
r
ep
r
o
ce
s
s
ed
d
ata
w
a
s
s
o
r
ted
to
4
0
f
iles
ea
ch
r
ep
r
esen
tin
g
th
e
m
u
s
ic
v
id
eo
u
s
ed
in
th
e
DE
A
P
d
ataset.
E
ac
h
v
id
eo
f
ile
co
n
tain
ed
an
ar
r
ay
o
f
s
ize
8
0
6
4
x
3
5
2
w
h
er
e
t
h
e
r
o
w
s
r
ep
r
esen
t
t
h
e
le
n
g
t
h
o
f
d
ata
a
n
d
c
o
lu
m
n
s
r
ep
r
es
en
t
t
h
e
to
tal
n
u
m
b
er
o
f
c
h
an
n
el
s
o
f
th
e
3
2
p
ar
ticip
an
ts
as d
escr
ib
ed
in
T
ab
le
2
.
T
ab
le
2
.
A
r
r
ay
R
ep
r
esen
tat
io
n
o
f
th
e
Vid
eo
Fil
e
A
r
r
a
y
N
a
me
A
r
r
a
y
S
i
z
e
(
R
o
w
×
C
o
l
u
mn
)
A
r
r
a
y
C
o
n
t
e
n
t
s (Ro
w
×
C
o
l
u
mn
)
V
i
d
e
o
_
n
o
8
0
6
4
×
3
5
2
D
a
t
a
×
s
u
b
j
e
c
t
N
o
_
c
h
a
n
n
e
l
N
o
2
.
4
.
B
a
nd
e
x
t
ra
ct
io
n
T
h
e
E
E
G
s
ig
n
als
u
s
ed
f
o
r
o
u
r
r
esear
ch
ar
e
o
n
th
e
ti
m
e
d
o
m
ai
n
.
E
x
i
s
ted
r
esear
ch
e
s
d
em
o
n
s
tr
ated
th
at,
in
o
r
d
er
to
r
ec
o
g
n
ize
e
m
o
tio
n
al
ac
tiv
it
ies
w
it
h
b
etter
ac
cu
r
ac
y
t
h
e
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
in
th
e
f
r
eq
u
e
n
c
y
d
o
m
ai
n
[
2
2
]
.
T
h
is
is
d
o
n
e
b
y
ap
p
ly
i
n
g
F
FT
to
th
e
ti
m
e
d
o
m
ai
n
s
i
g
n
al.
F
FT
is
an
al
g
o
r
i
th
m
t
h
at
i
s
u
s
ed
to
co
n
v
er
t a
s
i
g
n
a
l f
r
o
m
t
h
e
ti
m
e
d
o
m
ai
n
to
th
e
f
r
eq
u
e
n
c
y
d
o
m
a
in
.
Fo
r
X
an
d
Y
o
f
len
g
th
n
,
th
e
s
e
tr
an
s
f
o
r
m
s
ar
e
d
ef
i
n
ed
as f
o
ll
o
w
s
:
∑
(
1)
w
h
er
e
is
o
n
e
o
f
r
o
o
ts
o
f
u
n
it
y
an
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
-
8708
R
ec
o
g
n
itio
n
o
f e
mo
tio
n
a
l sta
tes u
s
in
g
E
E
G
s
ig
n
a
ls
b
a
s
ed
o
n
time
-
fr
eq
u
en
cy
…
(
F
a
b
ia
n
P
a
r
s
ia
Geo
r
g
e
)
1015
As
it
w
as
d
is
c
u
s
s
ed
ea
r
lier
,
e
m
o
tio
n
al
ac
ti
v
itie
s
ca
u
s
e
th
e
b
r
ain
to
g
en
er
ate
s
i
g
n
als
in
t
h
e
f
o
r
m
o
f
w
a
v
es.
T
h
ese
s
ig
n
al
s
,
w
h
ich
c
an
b
e
s
u
b
d
iv
id
ed
in
to
5
f
r
eq
u
e
n
c
y
b
a
n
d
s
,
h
o
ld
a
co
r
r
elatio
n
w
it
h
t
h
e
e
m
o
tio
n
a
l
ac
tiv
itie
s
.
T
h
ese
5
d
if
f
er
e
n
t
t
y
p
es
o
f
f
r
eq
u
e
n
c
y
b
a
n
d
s
ar
e
co
m
p
r
i
s
ed
o
f
d
elta,
th
eta,
alp
h
a,
b
eta,
an
d
g
a
m
m
a
[
2
1
]
.
A
s
s
tated
b
y
[
2
1
]
,
th
e
alp
h
a,
b
eta,
an
d
th
eta
ca
n
w
ell
r
ep
r
esen
t
th
e
e
m
o
tio
n
a
l
an
d
co
g
n
iti
v
e
p
r
o
ce
s
s
o
f
th
e
b
r
ain
th
a
n
t
h
e
o
th
er
2
b
an
d
s
.
T
h
is
is
w
h
y
,
w
e
h
av
e
e
x
tr
ac
ted
th
ese
3
b
an
d
s
u
s
i
n
g
B
u
t
ter
w
o
r
th
b
an
d
-
p
ass
f
ilter
a
f
ter
ap
p
ly
in
g
FF
T
o
n
th
e
E
E
G
s
ig
n
als.
2
.
5
.
F
e
a
t
ure
e
x
t
ra
ct
io
n
T
h
e
ex
p
er
im
e
n
ter
s
i
n
[
1
7
]
als
o
p
r
o
v
id
ed
in
f
o
r
m
atio
n
r
eg
ar
d
in
g
e
m
o
tio
n
s
th
at
ar
e
s
u
p
p
o
s
e
d
to
b
e
f
elt
af
ter
w
atch
in
g
ea
ch
v
id
eo
.
I
t
w
a
s
esti
m
ated
t
h
at
ea
ch
v
id
eo
ca
n
b
e
p
lace
d
in
an
y
o
f
th
e
4
e
m
o
tio
n
al
q
u
ad
r
a
n
ts
w
h
ic
h
ar
e
H
A
HV,
L
A
HV,
L
AL
V,
an
d
H
AL
V
a
s
r
ep
r
esen
te
d
in
Fig
u
r
e
2
.
I
n
d
iv
id
u
als
ca
n
r
esp
o
n
d
d
if
f
er
en
tl
y
f
o
r
a
s
p
ec
if
ic
v
id
eo
,
w
h
ic
h
ca
n
r
esu
lt
in
t
h
e
p
r
ese
n
ce
o
f
ir
r
eg
u
lar
s
a
m
p
les
i
n
th
e
E
E
G
s
ig
n
als.
T
h
es
e
er
r
o
n
eo
u
s
s
a
m
p
le
s
ar
e
r
eq
u
ir
ed
to
b
e
r
u
led
o
u
t
o
f
ea
ch
q
u
ad
r
an
t
in
o
r
d
er
to
m
in
i
m
ize
th
e
i
n
co
n
s
is
te
n
c
y
i
n
t
h
e
s
a
m
p
les.
Fo
r
o
u
r
r
esear
ch
,
i
n
o
r
d
er
to
r
e
d
u
ce
th
e
d
ata
d
ev
iat
io
n
,
th
e
e
x
tr
ac
ted
b
an
d
v
a
lu
e
s
o
f
th
e
v
id
eo
s
w
er
e
av
er
ag
ed
ac
co
r
d
in
g
to
th
e
ir
co
r
r
esp
o
n
d
in
g
q
u
ad
r
an
t a
lo
n
g
w
i
th
s
p
ec
i
f
ic
e
m
o
tio
n
as ill
u
s
tr
ated
in
T
ab
le
3
.
Fig
u
r
e
2
.
Fo
u
r
q
u
ad
r
an
ts
o
f
e
m
o
tio
n
T
ab
le
3
.
L
is
t o
f
4
0
Vid
eo
s
(
Den
o
ted
b
y
t
h
e
E
x
p
er
i
m
en
t_
I
d
)
a
n
d
t
h
eir
C
o
r
r
esp
o
n
d
in
g
Q
u
ad
r
an
t
H
A
H
V
L
A
H
V
L
A
L
V
H
A
L
V
1
8
16
10
2
9
22
21
3
12
23
31
4
13
24
32
5
14
25
33
6
15
26
34
7
17
27
35
11
18
28
36
-
19
29
37
-
20
30
38
Af
ter
s
o
r
ti
n
g
th
e
v
id
eo
i
n
ac
c
o
r
d
an
ce
w
it
h
t
h
eir
q
u
ad
r
an
t
a
n
d
av
er
a
g
in
g
t
h
e
b
an
d
s
o
f
al
l
th
e
v
id
eo
s
f
r
o
m
ea
c
h
q
u
ad
r
an
t,
4
v
id
eo
f
iles
w
er
e
cr
ea
ted
w
h
ic
h
co
n
t
ain
ed
o
n
l
y
th
e
a
v
er
ag
es
v
a
lu
es
o
f
t
h
e
e
x
tr
ac
ted
b
an
d
s
.
T
h
ese
b
an
d
v
alu
e
s
w
e
r
e
f
u
r
t
h
er
s
ca
led
s
o
t
h
a
t
t
h
e
SVM
clas
s
i
f
ier
d
o
es
n
o
t
g
et
i
n
f
lu
e
n
ce
d
b
y
lar
g
e
b
an
d
v
alu
es.
O
n
ce
th
e
b
an
d
v
alu
es
w
er
e
s
ca
led
,
th
e
f
ea
t
u
r
es
o
f
th
e
in
p
u
t
s
i
g
n
als
w
er
e
th
e
n
ex
tr
ac
ted
.
Fo
r
o
u
r
w
o
r
k
,
w
e
h
a
v
e
e
x
tr
ac
ted
th
e
s
tatis
tical
f
ea
t
u
r
es
m
i
n
i
m
u
m
,
m
ax
i
m
u
m
,
v
ar
ian
ce
,
s
tan
d
a
r
d
d
ev
iat
io
n
,
w
a
v
e
en
tr
o
p
y
,
p
o
w
er
b
an
d
w
id
th
,
s
k
e
w
n
es
s
,
an
d
k
u
r
to
s
i
s
b
ase
d
th
e
lo
ca
tio
n
o
r
ce
n
tr
al
ten
d
en
c
y
(
s
tati
s
tical
Featu
r
es
I
)
,
th
e
d
is
p
er
s
io
n
o
r
s
p
r
ea
d
(
Statis
tical
Feat
u
r
es
I
I
)
,
an
d
th
e
s
h
ap
e
o
f
d
is
tr
i
b
u
tio
n
(
S
tatis
t
ical
Featu
r
es I
I
I
)
as illu
s
tr
ated
in
T
ab
le
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
0
1
2
-
1020
1016
T
ab
le
4
.
T
y
p
es o
f
Feat
u
r
es E
x
tr
ac
ted
Fo
r
C
lass
i
f
icatio
n
S
t
a
t
i
st
i
c
a
l
F
e
a
t
u
r
e
s
I
S
t
a
t
i
st
i
c
a
l
F
e
a
t
u
r
e
s
I
I
S
t
a
t
i
st
i
c
a
l
F
e
a
t
u
r
e
s
I
I
I
M
i
n
i
m
u
m
V
a
r
i
a
n
c
e
S
k
e
w
n
e
ss
M
a
x
i
m
u
m
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
K
u
r
t
o
si
s
M
e
a
n
W
a
v
e
e
n
t
r
o
p
y
-
-
P
o
w
e
r
b
a
n
d
w
i
d
t
h
-
2
.
6
.
E
m
o
t
io
n c
la
s
s
if
ica
t
io
n
Nu
m
er
o
u
s
m
ac
h
i
n
e
lear
n
in
g
a
lg
o
r
ith
m
s
h
a
v
e
b
ee
n
in
th
e
ex
i
s
ted
s
t
u
d
ies,
o
u
t
o
f
S
VM
i
s
m
ea
s
u
r
ed
a
s
o
n
e
o
f
t
h
e
m
o
s
t
ef
f
ic
ien
t
clas
s
if
ier
s
f
o
r
class
if
y
i
n
g
e
m
o
t
io
n
s
[
8
]
,
[
9
]
.
T
h
e
b
asic
p
er
ce
p
tio
n
o
f
th
e
SVM
is
to
d
eter
m
in
e
a
d
ec
is
io
n
h
y
p
er
p
lan
e
in
o
r
d
er
to
class
if
y
d
ata
s
am
p
les
in
to
t
w
o
class
e
s
.
T
h
e
o
p
ti
m
u
m
h
y
p
er
p
lan
e
f
o
r
d
if
f
er
en
tiat
in
g
t
w
o
g
r
o
u
p
s
is
d
eter
m
i
n
ed
b
y
m
ax
i
m
izin
g
th
e
d
is
ta
n
ce
s
b
et
w
ee
n
n
ea
r
est
d
ata
p
o
in
t
o
f
b
o
th
th
e
class
e
s
an
d
th
e
h
y
p
er
p
lan
e
[
2
3
]
.
T
h
e
class
i
f
icatio
n
p
r
o
ce
d
u
r
e
in
clu
d
es
p
r
ed
ictin
g
a
co
n
f
u
s
io
n
m
atr
i
x
m
o
d
el
b
y
p
ar
titi
o
n
i
n
g
t
h
e
s
a
m
p
le
d
ata
in
to
a
tr
ai
n
in
g
s
et
a
n
d
a
te
s
t
s
et,
f
o
r
tr
ai
n
in
g
a
n
d
v
a
lid
atio
n
r
esp
ec
tiv
el
y
,
u
s
i
n
g
a
tech
n
iq
u
e
ca
lled
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
[
2
4
]
.
T
h
is
tech
n
iq
u
e
r
an
d
o
m
l
y
d
i
v
id
es
th
e
d
ata
in
to
k
eq
u
al
s
u
b
s
et
o
f
th
e
d
ata
an
d
is
r
ep
ea
ted
1
0
tim
e
s
.
E
ac
h
ti
m
e,
o
n
e
o
f
t
h
e
k
s
u
b
s
et
s
is
u
s
ed
as
t
h
e
tes
t
s
et
an
d
th
e
o
th
er
k
-
1
s
u
b
s
et
s
ar
e
p
u
t to
g
et
h
er
to
f
o
r
m
a
tr
ai
n
in
g
s
et
[
2
4
]
.
I
n
o
u
r
p
ap
er
,
d
if
f
er
en
t
co
m
b
in
atio
n
s
o
f
f
ea
t
u
r
es
w
er
e
u
s
ed
f
o
r
tr
ain
in
g
an
d
test
i
n
g
th
e
SVM
class
i
f
ier
i
n
o
r
d
er
to
g
en
er
ate
th
e
co
n
f
u
s
io
n
m
atr
ix
m
o
d
el.
T
h
is
m
o
d
el
w
as
t
h
en
u
s
ed
t
o
f
i
n
d
t
h
e
ac
c
u
r
ac
y
d
ep
en
d
in
g
o
n
t
h
e
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
Her
e,
w
e
i
n
teg
r
at
ed
SVM
w
i
th
1
0
-
f
o
ld
cr
o
s
s
f
o
ld
v
alid
atio
n
w
it
h
th
e
p
ar
a
m
eter
s
,
k
er
n
el
a
n
d
r
eg
u
lar
iza
tio
n
,
w
h
ich
w
er
e
s
e
lecte
d
b
y
t
h
e
g
r
id
-
s
ea
r
c
h
m
eth
o
d
.
I
n
o
r
d
er
to
i
m
p
le
m
en
t
SVM,
L
I
B
SVM
l
ib
r
ar
y
i
s
u
s
ed
,
w
h
ic
h
is
a
w
id
el
y
u
s
ed
lib
r
ar
y
f
o
r
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
i
n
es [
2
5
]
.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
C
las
s
i
f
y
i
n
g
t
h
e
s
tat
is
tical
f
ea
t
u
r
es
f
o
r
o
b
tain
in
g
a
d
ec
en
t
o
u
tco
m
e
w
as
n
o
t
a
n
ea
s
y
p
r
o
ce
s
s
.
Var
io
u
s
asp
ec
ts
w
er
e
r
eq
u
ir
ed
to
b
e
co
n
s
id
er
ed
p
r
io
r
to
r
ea
ch
in
g
to
a
co
n
clu
s
io
n
as
th
e
i
n
itia
l
tr
ials
d
id
n
o
t
g
en
er
ate
a
s
atis
f
y
in
g
o
u
tp
u
t.
I
n
t
h
i
s
p
ap
er
,
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
w
a
s
i
n
co
r
p
o
r
ated
w
i
th
th
e
SVM
clas
s
i
f
ier
u
s
i
n
g
t
h
e
r
eg
u
lar
izatio
n
an
d
k
er
n
el
p
ar
am
eter
,
w
h
ic
h
w
er
e
s
elec
ted
v
i
a
a
g
r
id
-
s
ea
r
ch
ap
p
r
o
ac
h
.
I
n
o
r
d
er
to
d
eter
m
i
n
e
th
e
ac
cu
r
ac
y
o
f
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
f
o
r
th
e
cla
s
s
i
f
icatio
n
tech
n
iq
u
e,
(
2
)
w
as
u
s
ed
.
T
h
e
eq
u
atio
n
f
o
r
ac
cu
r
ac
y
i
s
d
ef
i
n
ed
as:
(
2
)
w
h
er
e
T
P
: th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
e,
T
N:
th
e
n
u
m
b
er
o
f
tr
u
e
n
e
g
ati
v
e,
FP
: th
e
n
u
m
b
er
o
f
f
al
s
e
p
o
s
iti
v
e,
an
d
FN: th
e
n
u
m
b
er
o
f
f
alse
n
eg
at
i
v
e.
A
t
t
h
e
v
er
y
b
eg
i
n
n
in
g
,
p
r
io
r
t
o
av
er
ag
i
n
g
t
h
e
e
x
tr
ac
ted
b
a
n
d
v
al
u
es
ac
co
r
d
in
g
to
t
h
eir
co
r
r
esp
o
n
d
in
g
q
u
ad
r
an
ts
,
all
th
e
s
tat
is
tical
f
ea
tu
r
es
f
r
o
m
T
ab
le
4
w
er
e
f
ed
in
to
t
h
e
S
VM
clas
s
i
f
ier
at
o
n
c
e.
T
h
ey
w
er
e
u
s
ed
to
tr
ain
an
d
te
s
t
th
e
SVM
w
it
h
a
s
p
ec
i
f
ic
e
n
d
g
o
al
to
co
n
s
tr
u
ct
t
h
e
co
n
f
u
s
io
n
m
atr
ix
m
o
d
el.
T
h
is
m
o
d
el
w
a
s
th
en
u
s
ed
to
d
eter
m
i
n
e
th
e
ac
cu
r
ac
y
b
ased
o
n
th
e
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
Ho
w
e
v
er
,
th
e
v
er
y
f
ir
s
t
tr
ial
d
id
n
o
t
p
r
o
v
id
e
a
n
ex
p
ec
ted
o
u
tp
u
t
s
i
n
ce
th
e
ac
cu
r
a
c
y
w
as
o
n
l
y
f
o
u
n
d
to
b
e
2
.
0
3
%.
T
h
is
o
c
cu
r
r
ed
b
ec
au
s
e
th
e
f
ea
t
u
r
es,
b
ef
o
r
e
av
er
ag
i
n
g
th
e
d
ata,
d
o
n
o
t
co
n
tain
d
is
tin
g
u
i
s
h
ab
le
ch
ar
ac
ter
is
tic
s
as
it
ca
n
b
e
s
ee
n
f
r
o
m
Fig
u
r
e
3
.
A
b
o
x
-
a
n
d
-
w
h
i
s
k
er
p
lo
t
w
a
s
u
s
ed
to
g
r
ap
h
icall
y
r
ep
r
esen
t
ea
c
h
f
ea
t
u
r
e
t
h
r
o
u
g
h
th
eir
q
u
ar
tile
s
,
as
s
h
o
w
n
in
F
ig
u
r
e
3
(
a)
.
(
a)
(
b
)
Fig
u
r
e
3
.
B
o
x
p
lo
t o
f
th
e
s
tatis
t
ical
f
ea
t
u
r
es: (
a)
b
ef
o
r
e
av
er
ag
in
g
,
(
b
)
af
ter
av
er
a
g
i
n
g
t
h
e
v
id
eo
d
ata
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
-
8708
R
ec
o
g
n
itio
n
o
f e
mo
tio
n
a
l sta
tes u
s
in
g
E
E
G
s
ig
n
a
ls
b
a
s
ed
o
n
time
-
fr
eq
u
en
cy
…
(
F
a
b
ia
n
P
a
r
s
ia
Geo
r
g
e
)
1017
Af
ter
w
ar
d
,
w
e
a
v
er
ag
ed
t
h
e
b
an
d
v
alu
e
s
,
in
ac
co
r
d
an
ce
w
it
h
t
h
eir
q
u
ad
r
an
t
to
r
ed
u
c
e
th
e
d
ata
d
ev
iatio
n
an
d
i
m
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
t
h
e
clas
s
if
icatio
n
p
r
o
ce
s
s
.
O
n
ce
t
h
e
d
ata
w
er
e
av
er
ag
ed
,
th
e
s
e
w
er
e
s
ca
led
an
d
th
e
s
tati
s
tical
f
ea
t
u
r
es
w
er
e
e
x
tr
ac
ted
ag
ai
n
as
d
is
cu
s
s
ed
in
S
ec
tio
n
2
.
5
.
T
h
e
f
ea
t
u
r
es
w
er
e
o
n
ce
m
o
r
e
f
ed
in
to
th
e
cla
s
s
i
f
ier
a
ll
at
o
n
ce
.
T
h
is
ti
m
e,
th
er
e
w
a
s
a
s
ig
n
i
f
ica
n
t
i
m
p
r
o
v
e
m
e
n
t
in
t
h
e
p
er
ce
n
ta
g
e
ac
cu
r
ac
y
f
o
r
class
i
f
icatio
n
as i
t in
cr
ea
s
ed
d
r
asti
ca
ll
y
f
r
o
m
2
.
0
3
% to
3
2
.
1
4
%.
T
h
e
p
er
ce
n
tag
e
o
f
ac
cu
r
ac
y
b
ef
o
r
e
an
d
a
f
ter
a
v
er
ag
i
n
g
t
h
e
d
ata
o
f
all
th
e
f
ea
t
u
r
es
is
s
u
m
m
ar
ized
i
n
T
ab
le
5
.
I
t
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
th
e
tab
le
t
h
at
th
e
f
e
at
u
r
e
s
d
o
n
o
t
o
f
f
er
s
ati
s
f
ac
to
r
y
o
u
tco
m
e
p
r
io
r
to
av
er
ag
i
n
g
th
e
d
ata
b
ec
au
s
e
n
o
t
all
th
e
p
ar
ticip
an
ts
f
ee
l
t
h
e
s
a
m
e
e
m
o
tio
n
f
o
r
a
s
p
ec
if
ic
ca
teg
o
r
y
o
f
v
id
eo
.
Hen
ce
,
t
h
e
SVM
cla
s
s
i
f
ier
c
o
u
ld
n
o
t
cr
ea
te
o
u
r
ex
p
ec
ted
m
o
d
el
d
u
e
to
th
e
ir
r
eg
u
lar
it
y
in
d
ata
f
o
r
ea
ch
q
u
ad
r
an
t.
T
ab
le
5
.
A
cc
u
r
ac
y
f
o
r
C
las
s
if
i
ca
tio
n
b
ef
o
r
e
an
d
af
ter
Av
er
ag
in
g
t
h
e
Vid
eo
Data
S
t
a
t
e
o
f
t
h
e
D
a
t
a
A
c
c
u
r
a
c
y
(
%)
B
e
f
o
r
e
a
v
e
r
a
g
i
n
g
t
h
e
d
a
t
a
2
.
0
3
A
f
t
e
r
a
v
e
r
a
g
i
n
g
t
h
e
d
a
t
a
3
2
.
1
4
E
v
en
t
h
o
u
g
h
th
e
ac
c
u
r
ac
y
f
o
r
class
i
f
icatio
n
i
m
p
r
o
v
ed
b
y
a
ce
r
tain
a
m
o
u
n
t
af
ter
a
v
er
ag
i
n
g
th
e
b
a
n
d
v
alu
e
s
,
it
s
till
d
id
n
o
t
p
r
o
v
id
e
th
e
e
x
p
ec
ted
o
u
tp
u
t.
S
u
b
s
e
q
u
en
tl
y
,
w
e
r
ec
o
n
s
tr
u
cted
t
h
e
b
o
x
p
lo
t
to
an
al
y
ze
ea
ch
f
ea
t
u
r
e
t
h
at
ca
n
b
e
s
ee
n
f
r
o
m
Fi
g
u
r
e
3
(
b
)
,
b
u
t
th
is
ti
m
e
a
f
ter
av
er
a
g
in
g
t
h
e
d
ata
ac
co
r
d
in
g
to
th
eir
co
r
r
esp
o
n
d
in
g
q
u
ad
r
an
t
s
.
A
b
o
x
-
an
d
-
w
h
is
k
er
p
lo
t
w
a
s
u
s
ed
to
d
is
tin
g
u
is
h
ea
ch
f
ea
tu
r
e
o
n
ce
th
e
d
ata
w
er
e
av
er
ag
ed
w
i
th
r
esp
ec
t
to
th
eir
eq
u
iv
ale
n
t
q
u
a
d
r
an
ts
,
as
s
h
o
w
n
i
n
Fig
u
r
e
3
(
b
)
.
I
t
ca
n
b
e
o
b
s
er
v
e
d
f
r
o
m
t
h
e
f
i
g
u
r
e
t
h
at
th
e
d
ata
o
f
th
e
f
ea
t
u
r
es
s
k
e
w
n
e
s
s
,
k
u
r
t
o
s
is
,
an
d
w
a
v
e
e
n
tr
o
p
y
ca
n
b
e
ea
s
il
y
d
is
ti
n
g
u
i
s
h
ed
f
r
o
m
ea
c
h
o
th
er
a
s
th
e
d
ata
d
o
n
o
t
o
v
er
lap
an
d
ar
e
s
ig
n
i
f
ican
tl
y
d
ev
iated
.
T
h
e
s
it
u
atio
n
is
al
s
o
s
i
m
ilar
f
o
r
th
e
f
ea
t
u
r
es
s
k
e
w
n
es
s
an
d
p
o
w
er
b
a
n
d
w
id
th
as
th
e
s
e
t
w
o
f
ea
tu
r
e
s
co
n
tai
n
ed
s
i
g
n
if
i
ca
n
t
d
is
ti
n
g
u
is
h
ab
le
ch
ar
ac
ter
is
tics
.
O
n
t
h
e
o
th
er
h
an
d
,
th
e
f
ea
tu
r
es
m
ea
n
,
v
ar
ian
ce
an
d
s
tan
d
ar
d
d
ev
iatio
n
wer
e
r
elativ
el
y
d
ev
iated
f
r
o
m
e
ac
h
o
th
er
,
b
u
t
m
o
s
t
o
f
th
e
d
ata
w
er
e
s
t
ill
s
ee
n
to
b
e
o
v
er
lap
p
in
g
.
Fu
r
t
h
er
m
o
r
e
,
it
w
as
s
ee
n
t
h
at
t
h
e
d
i
f
f
er
e
n
ce
i
n
t
h
e
f
ea
t
u
r
es
m
i
n
i
m
u
m
,
m
a
x
i
m
u
m
,
a
n
d
v
ar
ian
ce
w
a
s
n
o
t
as
p
r
o
m
in
e
n
t
as
th
e
d
ev
iatio
n
i
n
t
h
e
d
ata
w
as
v
er
y
i
n
s
i
g
n
if
ican
t.
B
ased
o
n
th
e
ab
o
v
e
p
ar
am
e
ter
s
,
w
e
s
eg
r
e
g
ated
all
th
e
f
ea
t
u
r
es in
to
t
h
e
f
o
llo
w
i
n
g
co
m
b
in
at
io
n
s
:
1
)
Featu
r
e
co
m
b
i
n
atio
n
A
:
m
e
an
,
s
ta
n
d
ar
d
d
ev
iatio
n
,
v
ar
ia
n
c
e.
2
)
Featu
r
e
co
m
b
i
n
atio
n
B
: sk
e
w
n
es
s
,
k
u
r
to
s
is
,
w
a
v
e
en
tr
o
p
y
.
3
)
Featu
r
e
co
m
b
i
n
atio
n
C
:
m
i
n
i
m
u
m
,
m
ax
i
m
u
m
,
v
ar
ia
n
ce
.
4
)
Featu
r
e
co
m
b
i
n
atio
n
D:
s
k
e
w
n
es
s
,
p
o
w
er
b
an
d
w
id
th
.
I
t
w
as
o
b
s
er
v
ed
th
at
t
h
e
ac
cu
r
ac
y
f
o
r
clas
s
i
f
icatio
n
i
m
p
r
o
v
e
d
b
y
a
s
i
g
n
i
f
ican
t
a
m
o
u
n
t
a
s
i
llu
s
tr
ated
in
T
ab
le
6
.
I
t
ca
n
b
e
n
o
ticed
th
at
t
h
e
co
m
b
i
n
atio
n
B
p
r
o
v
id
ed
a
b
etter
r
esu
lt
w
it
h
a
n
ac
cu
r
ac
y
o
f
9
2
.
3
6
%
f
o
r
th
e
q
u
ad
r
an
t
H
A
HV_
L
AL
V
an
d
8
9
.
1
1
%
f
o
r
th
e
q
u
ad
r
a
n
t
H
AL
V_
L
A
HV,
w
h
er
ea
s
t
h
e
co
m
b
in
at
io
n
C
p
r
o
v
id
ed
th
e
least
r
esu
lt
w
ith
an
ac
cu
r
ac
y
o
f
1
1
.
2
3
%
f
o
r
t
h
e
q
u
ad
r
an
t
H
A
HV_
L
AL
V
a
n
d
1
5
.
6
9
%
f
o
r
th
e
q
u
ad
r
an
t H
AL
V_
L
AHV.
T
ab
le
6
.
A
cc
u
r
ac
y
o
f
t
h
e
Feat
u
r
e
C
o
m
b
i
n
atio
n
s
af
ter
Av
er
a
g
in
g
t
h
e
Vid
eo
Data
A
c
c
u
r
a
c
y
o
f
F
e
a
t
u
r
e
C
o
mb
i
n
a
t
i
o
n
s (
%)
H
A
H
V
_
L
A
L
V
H
A
L
V
_
L
A
H
V
A
2
5
.
3
4
±
5
.
2
0
2
1
.
2
1
±
3
.
2
0
B
9
2
.
3
6
±
6
.
3
0
8
9
.
1
1
±
8
.
3
0
C
1
1
.
2
3
±
5
.
2
0
1
5
.
6
9
±
3
.
5
0
D
4
4
.
3
1
±
7
.
5
0
4
9
.
2
3
±
8
.
3
0
T
h
e
r
ea
s
o
n
f
o
r
f
ea
t
u
r
e
co
m
b
in
atio
n
B
p
r
o
v
id
in
g
b
etter
r
e
s
u
lt
is
th
a
t
t
h
e
s
a
m
p
les
o
f
th
e
f
ea
t
u
r
es
s
k
e
w
n
es
s
,
k
u
r
to
s
is
,
a
n
d
w
a
v
e
en
tr
o
p
y
ca
n
b
e
ea
s
il
y
d
is
tin
g
u
i
s
h
ed
f
r
o
m
ea
ch
o
th
er
a
s
th
e
d
ata
ar
e
s
i
g
n
i
f
ican
tl
y
d
ev
iated
(
s
ee
Fi
g
u
r
e
3
(
b
)
.
Si
m
ilar
l
y
,
t
h
e
ac
cu
r
ac
y
f
o
r
f
ea
tu
r
e
co
m
b
i
n
atio
n
D
w
as
also
s
ee
m
ed
to
b
e
s
atis
f
ac
to
r
y
f
o
r
th
e
s
a
m
e
r
ea
s
o
n
.
On
th
e
o
t
h
er
h
a
n
d
,
t
h
e
f
e
atu
r
e
co
m
b
i
n
atio
n
s
A
,
a
n
d
C
co
u
ld
n
o
t
p
r
o
v
id
e
a
s
atis
f
ac
to
r
y
r
es
u
lt
d
u
e
to
th
e
o
v
er
lap
p
in
g
an
d
s
i
m
ilar
it
y
o
f
th
e
d
ata.
T
h
is
af
f
ec
t
s
th
e
SVM
class
i
f
ier
in
g
en
er
ati
n
g
a
co
n
f
u
s
io
n
m
atr
ix
m
o
d
el
th
at
f
ails
to
d
ep
ict
th
e
b
etter
ac
cu
r
ac
y
.
B
y
o
b
s
er
v
i
n
g
th
e
ab
o
v
e
r
esu
lt
s
,
w
e
co
u
ld
co
n
cl
u
d
e
t
h
at
t
h
e
s
h
ap
e
o
f
th
e
d
i
s
tr
ib
u
tio
n
co
u
ld
w
ell
r
ep
r
esen
t
t
h
e
e
m
o
tio
n
a
l
a
ctiv
itie
s
o
f
th
e
b
r
ain
an
d
th
u
s
h
as p
r
o
v
id
ed
a
b
etter
p
er
ce
n
tag
e
ac
cu
r
ac
y
f
o
r
clas
s
i
f
icatio
n
.
As
DE
A
P
is
a
p
u
b
lic
d
ataset,
w
e
to
o
k
a
s
tep
f
o
r
w
ar
d
to
co
m
p
ar
e
a
n
d
an
a
l
y
ze
t
h
e
e
x
is
tin
g
m
eth
o
d
s
th
at
h
av
e
alr
ea
d
y
u
s
ed
t
h
e
D
E
A
P
d
ataset
f
o
r
r
ec
o
g
n
iz
in
g
e
m
o
tio
n
s
w
it
h
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
T
ab
le
7
illu
s
tr
ates
s
o
m
e
o
f
th
e
ex
i
s
ti
n
g
m
et
h
o
d
s
f
o
r
e
m
o
tio
n
r
ec
o
g
n
itio
n
u
s
i
n
g
t
h
e
DE
A
P
d
atas
et.
I
t
also
p
r
o
v
id
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
0
1
2
-
1020
1018
in
f
o
r
m
atio
n
r
eg
ar
d
i
n
g
t
h
e
em
o
tio
n
s
id
en
ti
f
ied
,
th
e
f
ea
t
u
r
es
ex
tr
ac
ted
an
d
th
e
ac
cu
r
ac
y
f
o
r
e
m
o
tio
n
class
i
f
icatio
n
b
y
ea
c
h
m
e
th
o
d
.
I
t
ca
n
b
e
o
b
s
er
v
ed
th
at
m
o
s
t
o
f
th
e
e
x
is
tin
g
m
et
h
o
d
s
ex
tr
ac
ted
m
o
r
e
th
an
o
n
e
t
y
p
e
o
f
f
ea
t
u
r
es
a
n
d
f
e
w
id
e
n
ti
f
ied
m
o
r
e
t
h
a
n
t
w
o
e
m
o
ti
o
n
s
.
Ho
w
e
v
er
,
f
o
r
o
u
r
w
o
r
k
,
o
n
l
y
th
e
s
tati
s
tical
f
ea
t
u
r
es
w
er
e
co
n
s
id
er
ed
f
o
r
th
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
an
d
o
n
l
y
t
w
o
s
tate
s
o
f
e
m
o
ti
o
n
w
er
e
id
en
t
if
ied
,
n
a
m
e
l
y
v
ale
n
ce
a
n
d
ar
o
u
s
al.
Fu
r
t
h
er
m
o
r
e,
it
ca
n
b
e
al
s
o
s
e
en
f
r
o
m
t
h
e
tab
le
th
at
th
e
ac
c
u
r
ac
y
o
f
t
h
e
e
x
is
t
in
g
m
et
h
o
d
o
lo
g
ies i
s
li
m
ited
w
i
th
i
n
8
0
%,
w
h
er
ea
s
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
p
r
o
v
id
ed
an
ac
cu
r
ac
y
o
f
ap
p
r
o
x
i
m
atel
y
9
2
.
3
6
%.
T
h
u
s
,
it
ca
n
b
e
s
aid
th
at
o
u
r
ap
p
r
o
ac
h
is
m
o
r
e
ef
f
i
cien
t
in
ter
m
s
o
f
clas
s
i
f
y
in
g
e
m
o
tio
n
s
th
a
n
m
a
n
y
o
f
th
e
e
x
is
ti
n
g
ap
p
r
o
ac
h
es.
T
ab
le
7
.
A
cc
u
r
ac
y
o
f
E
x
is
tin
g
A
p
p
r
o
ac
h
es b
ased
o
n
DE
A
P
Data
s
et
R
e
f
e
r
e
n
c
e
Emo
t
i
o
n
s
F
e
a
t
u
r
e
s
A
c
c
u
r
a
c
y
(
%)
[
2
6
]
V
a
l
e
n
c
e
a
n
d
a
r
o
u
sal
D
W
T
,
W
E,
a
n
d
S
t
a
t
i
st
i
c
a
l
7
1
.
4
0
[
2
7
]
M
a
l
e
/
f
e
mal
e
v
a
l
e
n
c
e
a
n
d
m
a
l
e
/
f
e
mal
e
a
r
o
u
sal
S
t
a
t
i
st
i
c
a
l
,
L
i
n
e
a
r
,
a
n
d
N
o
n
-
st
a
t
i
s
t
i
c
a
l
7
8
.
6
0
[
2
8
]
S
t
r
e
ss a
n
d
c
a
l
m
S
t
a
t
i
st
i
c
a
l
,
P
S
D
,
a
n
d
H
O
C
7
1
.
4
0
[
2
9
]
V
a
l
e
n
c
e
,
a
r
o
u
sal
,
a
n
d
d
o
mi
n
a
n
c
e
S
t
a
t
i
st
i
c
a
l
a
n
d
H
F
D
7
1
.
4
0
[
3
0
]
Ex
c
i
t
a
t
i
o
n
,
h
a
p
p
i
n
e
ss,
s
a
d
n
e
ss,
a
n
d
h
a
t
r
e
d
W
T
(
d
b
5
)
,
S
E,
C
C
,
a
n
d
A
R
7
8
.
6
0
[
3
1
]
A
n
g
e
r
,
su
r
p
r
i
se
,
a
n
d
o
t
h
e
r
H
H
S
,
H
O
C
,
a
n
d
S
T
F
T
7
8
.
6
0
P
r
o
p
o
se
d
A
p
p
r
o
a
c
h
V
a
l
e
n
c
e
a
n
d
a
r
o
u
sal
S
t
a
t
i
st
i
c
a
l
9
2
.
3
6
4.
CO
NCLU
SI
O
N
I
n
t
h
is
p
ap
er
,
th
e
p
r
ep
r
o
ce
s
s
ed
E
E
G
s
ig
n
al
s
f
r
o
m
DE
A
P
d
ataset
w
er
e
u
s
ed
to
cla
s
s
i
f
y
t
w
o
t
y
p
es
o
f
e
m
o
tio
n
s
,
n
a
m
e
l
y
v
a
len
ce
an
d
ar
o
u
s
al.
T
h
e
s
a
m
p
les
in
t
h
e
d
ataset
w
er
e
f
ir
s
t
tr
an
s
f
er
r
ed
f
r
o
m
ti
m
e
d
o
m
ai
n
to
f
r
eq
u
en
c
y
d
o
m
ain
b
y
ap
p
l
y
i
n
g
F
FT
f
o
llo
w
ed
b
y
t
h
e
ex
tr
ac
tio
n
o
f
t
h
e
a
lp
h
a,
b
eta,
an
d
t
h
e
ta
f
r
eq
u
e
n
c
y
b
an
d
s
th
at
ar
e
p
ar
tic
u
lar
l
y
s
i
g
n
i
f
ica
n
t
f
o
r
e
m
o
tio
n
r
ec
o
g
n
i
tio
n
.
Su
b
s
eq
u
en
tl
y
,
t
h
e
e
x
tr
ac
ted
b
an
d
s
w
er
e
av
er
a
g
ed
i
n
co
r
r
esp
o
n
d
en
ce
to
th
eir
q
u
ad
r
an
t
f
o
r
ea
ch
e
m
o
tio
n
a
n
d
t
h
e
a
v
er
ag
ed
b
an
d
v
alu
e
s
w
e
r
e
u
s
ed
to
e
x
tr
ac
t
s
tat
is
t
ical
f
ea
t
u
r
es.
A
f
ter
th
at,
th
e
ex
tr
ac
ted
f
ea
tu
r
e
s
w
er
e
s
ca
led
an
d
v
ar
io
u
s
f
ea
t
u
r
e
co
m
b
in
at
io
n
s
w
er
e
f
ed
in
to
t
h
e
SVM
c
lass
if
ier
f
o
r
e
m
o
tio
n
r
ec
o
g
n
i
tio
n
.
I
t
w
as
o
b
s
er
v
ed
th
a
t
o
u
r
ap
p
r
o
ac
h
p
r
ed
ict
s
e
m
o
tio
n
s
w
i
th
an
ac
cu
r
ac
y
o
f
9
2
.
3
6
%
u
s
i
n
g
s
k
e
w
n
es
s
,
k
u
r
to
s
is
,
a
n
d
w
a
v
e
en
t
r
o
p
y
f
ea
t
u
r
es.
O
u
r
p
r
o
p
o
s
ed
m
o
d
el
s
h
o
w
s
b
etter
r
esu
lt
s
co
m
p
ar
ed
to
th
e
ex
is
tin
g
m
et
h
o
d
s
f
o
r
DE
A
P
d
ataset.
RE
F
E
R
E
NC
E
S
[
1
]
I.
B.
M
a
u
ss
a
n
d
M
.
D.
R
o
b
in
s
o
n
,
“
M
e
a
su
re
s
o
f
e
m
o
ti
o
n
:
A
re
v
ie
w
,
”
Co
g
n
it
i
o
n
a
n
d
Em
o
ti
o
n
,
v
o
l.
2
3
,
n
o
.
2
,
p
p
.
2
0
9
–
2
3
7
,
2
0
0
9
.
[
2
]
J.
P
o
sn
e
r,
J.
A
.
Ru
ss
e
ll
,
a
n
d
B.
S
.
P
e
ters
o
n
,
“
T
h
e
c
ircu
m
p
lex
m
o
d
e
l
o
f
a
ff
e
c
t:
A
n
in
teg
ra
ti
v
e
a
p
p
ro
a
c
h
to
a
f
fe
c
ti
v
e
n
e
u
ro
sc
ien
c
e
,
c
o
g
n
it
iv
e
d
e
v
e
lo
p
m
e
n
t,
a
n
d
p
sy
c
h
o
p
a
th
o
l
o
g
y
,
”
De
v
e
lo
p
me
n
t
a
n
d
Psy
c
h
o
p
a
t
h
o
l
o
g
y
,
v
o
l.
1
7
,
n
o
.
3
,
2
0
0
5
.
[
3
]
T
.
M
u
sh
a
,
Y.
T
e
ra
sa
k
i,
H.
A
.
Ha
q
u
e
,
a
n
d
G
.
A
.
Iv
a
m
it
s
k
y
,
“
F
e
a
tu
re
e
x
trac
ti
o
n
f
ro
m
EE
G
s
a
ss
o
c
iate
d
w
it
h
e
m
o
ti
o
n
s,”
Art
if
icia
l
L
if
e
a
n
d
R
o
b
o
ti
c
s
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
1
5
-
1
9
,
1
9
9
7
.
[
4
]
N.
T
h
a
m
m
a
sa
n
,
K.
M
o
riy
a
m
a
,
K.
-
I.
F
u
k
u
i
,
a
n
d
M
.
N
u
m
a
o
,
“
F
a
m
il
iarity
e
ffe
c
ts
in
EE
G
-
b
a
se
d
e
m
o
ti
o
n
re
c
o
g
n
it
io
n
,
”
Bra
in
I
n
f
o
rm
a
ti
c
s
,
v
o
l.
4
,
n
o
.
1
,
p
p
.
3
9
-
5
0
,
2
0
1
6
.
[
5
]
P
.
C.
P
e
tran
to
n
a
k
is
a
n
d
L
.
J.
Ha
d
ji
leo
n
t
iad
is,
“
A
No
v
e
l
E
m
o
ti
o
n
E
li
c
it
a
ti
o
n
I
n
d
e
x
Us
in
g
F
ro
n
tal
Bra
in
A
s
y
m
m
e
tr
y
f
o
r
En
h
a
n
c
e
d
EE
G
-
Ba
se
d
E
m
o
ti
o
n
Re
c
o
g
n
it
i
o
n
,
”
IEE
E
T
r
a
n
s
a
c
ti
o
n
s
o
n
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
in
Bi
o
me
d
ici
n
e
,
v
o
l.
1
5
,
n
o
.
5
,
p
p
.
7
3
7
-
7
4
6
,
2
0
1
1
.
[
6
]
T
.
M
u
sh
a
,
Y.
T
e
ra
sa
k
i,
H.
A
.
Ha
q
u
e
,
a
n
d
G
.
A
.
Iv
a
m
it
s
k
y
,
“
F
e
a
tu
re
e
x
trac
ti
o
n
f
ro
m
EE
G
s
a
ss
o
c
iate
d
w
it
h
e
m
o
ti
o
n
s,”
Art
if
icia
l
L
if
e
a
n
d
R
o
b
o
ti
c
s
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
1
5
-
1
9
,
1
9
9
7
.
[
7
]
X
ian
g
L
i,
Da
w
e
i
S
o
n
g
,
P
e
n
g
Z
h
a
n
g
,
G
u
a
n
g
li
a
n
g
Yu
,
Yu
e
x
ian
Ho
u
a
n
d
Bi
n
Hu
,
“
Em
o
ti
o
n
r
e
c
o
g
n
it
io
n
f
ro
m
m
u
lt
ich
a
n
n
e
l
EE
G
d
a
ta
t
h
ro
u
g
h
Co
n
v
o
l
u
t
io
n
a
l
Re
c
u
rre
n
t
Ne
u
ra
l
Ne
tw
o
rk
,
”
2
0
1
6
I
EE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
in
fo
rm
a
t
ics
a
n
d
Bi
o
me
d
ici
n
e
(
BIB
M
)
,
S
h
e
n
z
h
e
n
,
2
0
1
6
,
p
p
.
3
5
2
-
3
5
9
.
[
8
]
D.
Hu
a
n
g
,
S
.
Z
h
a
n
g
,
a
n
d
Y.
Zh
a
n
g
,
“
EE
G
-
b
a
se
d
e
m
o
ti
o
n
re
c
o
g
n
i
ti
o
n
u
sin
g
e
m
p
iri
c
a
l
w
a
v
e
let
tran
sf
o
r
m
,
”
2
0
1
7
4
th
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
y
ste
ms
a
n
d
I
n
f
o
rm
a
ti
c
s (
ICS
AI)
,
2
0
1
7
.
[
9
]
X
.
Jie
,
R.
Ca
o
,
a
n
d
L
.
L
i,
“
E
m
o
t
io
n
re
c
o
g
n
it
i
o
n
b
a
se
d
o
n
th
e
sa
m
p
le
e
n
tro
p
y
o
f
EE
G
,
”
Bio
-
me
d
ic
a
l
ma
ter
ia
ls
a
n
d
e
n
g
in
e
e
rin
g
,
v
o
l
.
2
4
,
n
o
.
1
,
p
p
.
1
1
8
5
-
9
2
,
2
0
1
4
.
[
1
0
]
T
.
D.
P
h
a
m
,
D.
T
ra
n
,
W
.
M
a
,
a
n
d
N.
T
.
T
r
a
n
,
“
En
h
a
n
c
i
n
g
P
e
rf
o
rm
a
n
c
e
o
f
EE
G
-
b
a
se
d
E
m
o
ti
o
n
Re
c
o
g
n
it
io
n
S
y
ste
m
s
Us
in
g
F
e
a
tu
re
S
m
o
o
th
i
n
g
,
”
Ne
u
ra
l
In
fo
rm
a
t
io
n
Pro
c
e
ss
in
g
L
e
c
tu
r
e
No
tes
in
C
o
mp
u
ter
S
c
ien
c
e
,
p
p
.
9
5
-
1
0
2
,
2
0
1
5
.
[
1
1
]
Z.
M
o
h
a
m
m
a
d
i,
J.
F
ro
u
n
c
h
i,
a
n
d
M
.
Am
iri
,
“
W
a
v
e
let
-
b
a
se
d
e
m
o
ti
o
n
re
c
o
g
n
it
i
o
n
sy
ste
m
u
sin
g
EE
G
sig
n
a
l,
”
Ne
u
ra
l
Co
mp
u
t
in
g
a
n
d
Ap
p
li
c
a
t
io
n
s
,
v
o
l.
2
8
,
n
o
.
8
,
p
p
.
1
9
8
5
-
1
9
9
0
,
2
0
1
6
.
[
1
2
]
M
.
M
u
ru
g
a
p
p
a
n
a
n
d
S
.
M
u
r
u
g
a
p
p
a
n
,
“
Hu
m
a
n
e
m
o
ti
o
n
re
c
o
g
n
it
io
n
t
h
ro
u
g
h
sh
o
rt
ti
m
e
El
e
c
tro
e
n
c
e
p
h
a
lo
g
ra
m
(EE
G
)
sig
n
a
ls
u
sin
g
F
a
st
F
o
u
rier
T
ra
n
sfo
rm
(F
F
T
),
”
2
0
1
3
IE
EE
9
th
In
ter
n
a
ti
o
n
a
l
C
o
ll
o
q
u
iu
m
o
n
S
ig
n
a
l
P
ro
c
e
ss
in
g
a
n
d
it
s
Ap
p
li
c
a
ti
o
n
s
,
2
0
1
3
.
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
-
8708
R
ec
o
g
n
itio
n
o
f e
mo
tio
n
a
l sta
tes u
s
in
g
E
E
G
s
ig
n
a
ls
b
a
s
ed
o
n
time
-
fr
eq
u
en
cy
…
(
F
a
b
ia
n
P
a
r
s
ia
Geo
r
g
e
)
1019
[
1
3
]
R.
Biswa
s,
J.
Ud
d
in
,
a
n
d
J.
Ha
sa
n
,
“
A
Ne
w
A
p
p
ro
a
c
h
o
f
Iris
De
t
e
c
ti
o
n
a
n
d
Re
c
o
g
n
it
i
o
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
7
,
n
o
.
5
,
p
p
.
2
5
3
0
-
2
5
3
6
,
2
0
1
7
.
[
1
4
]
N.A
.
Ra
k
ib
,
S
.
Z.
F
a
rh
a
n
,
M
.
B.
S
o
b
h
a
n
,
J.
Ud
d
in
,
A
.
Ha
b
ib
,
“
A
No
v
e
l
2
D
F
e
a
tu
re
Ex
trac
t
io
n
M
e
th
o
d
f
o
r
F
in
g
e
rp
rin
ts
Us
in
g
M
in
u
ti
a
e
P
o
i
n
ts
a
n
d
T
h
e
ir
In
ters
e
c
ti
o
n
s,”
I
n
t
e
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
7
,
n
o
.
5
,
p
p
.
2
5
4
7
-
2
5
5
4
,
2
0
1
7
.
[
1
5
]
X
ian
g
L
i,
Da
w
e
i
S
o
n
g
,
P
e
n
g
Z
h
a
n
g
,
G
u
a
n
g
li
a
n
g
Yu
,
Yu
e
x
ian
Ho
u
a
n
d
Bi
n
Hu
,
“
Em
o
ti
o
n
r
e
c
o
g
n
it
io
n
f
ro
m
m
u
lt
ich
a
n
n
e
l
EE
G
d
a
ta
t
h
ro
u
g
h
Co
n
v
o
l
u
ti
o
n
a
l
Re
c
u
rre
n
t
Ne
u
ra
l
Ne
tw
o
rk
,
”
2
0
1
6
I
EE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
in
fo
rm
a
t
ics
a
n
d
Bi
o
me
d
ici
n
e
(
BIB
M
)
,
S
h
e
n
zh
e
n
,
2
0
1
6
,
p
p
.
3
5
2
-
3
5
9
.
[
1
6
]
M
.
M
u
r
u
g
a
p
p
a
n
,
“
Hu
m
a
n
e
m
o
ti
o
n
c
las
sif
ic
a
ti
o
n
u
sin
g
w
a
v
e
l
e
t
tran
sf
o
r
m
a
n
d
KN
N,”
2
0
1
1
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
P
a
tt
e
rn
An
a
lys
is
a
n
d
I
n
telli
g
e
n
c
e
Ro
b
o
ti
c
s
,
2
0
1
1
.
[
1
7
]
S
.
Ko
e
lstra,
C.
M
u
h
l,
M
.
S
o
ley
m
a
n
i,
J.
-
S
.
L
e
e
,
A
.
Ya
z
d
a
n
i,
T
.
E
b
r
a
h
im
i,
T
.
P
u
n
,
A
.
Nijh
o
lt
,
a
n
d
I
.
P
a
tras
,
“
DE
A
P
:
A
Da
tab
a
se
f
o
r
Em
o
ti
o
n
A
n
a
ly
sis
;
Us
in
g
P
h
y
sio
lo
g
ica
l
S
ig
n
a
ls,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
A
ff
e
c
ti
v
e
Co
mp
u
ti
n
g
,
v
o
l.
3
,
n
o
.
1
,
p
p
.
1
8
-
3
1
,
2
0
1
2
.
[
1
8
]
R.
Je
n
k
e
,
A
.
P
e
e
r,
a
n
d
M
.
Bu
ss
,
“
F
e
a
tu
re
Ex
trac
ti
o
n
a
n
d
S
e
lec
ti
o
n
f
o
r
Em
o
ti
o
n
Re
c
o
g
n
i
ti
o
n
f
ro
m
EE
G
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Af
fec
ti
v
e
Co
mp
u
t
in
g
,
v
o
l.
5
,
n
o
.
3
,
p
p
.
3
2
7
-
3
3
9
,
Ja
n
.
2
0
1
4
.
[
1
9
]
J.
Ed
m
o
n
d
s
a
n
d
R.
M
.
Ka
rp
,
“
T
h
e
o
re
ti
c
a
l
im
p
ro
v
e
m
e
n
ts
in
a
lg
o
rit
h
m
ic
e
ff
ici
e
n
c
y
f
o
r
n
e
tw
o
rk
f
lo
w
p
ro
b
lem
s,
”
J
o
u
rn
a
l
o
f
th
e
ACM
(
J
ACM
)
,
v
o
l.
1
9
,
n
o
.
2
,
p
p
.
2
4
8
-
2
6
4
,
1
9
7
2
.
[
2
0
]
Z.
L
a
n
,
O.
S
o
u
rin
a
,
L
.
W
a
n
g
,
a
n
d
Y.
L
iu
,
“
S
tab
il
it
y
o
f
F
e
a
tu
re
s
in
Re
a
l
-
T
im
e
EE
G
-
b
a
se
d
Em
o
ti
o
n
Re
c
o
g
n
i
ti
o
n
A
l
g
o
rit
h
m
,
”
2
0
1
4
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Cy
b
e
rwo
rld
s
,
2
0
1
4
.
[
2
1
]
K.
Ka
li
m
e
ri
a
n
d
C.
S
a
it
is,
“
Ex
p
lo
rin
g
m
u
lt
im
o
d
a
l
b
io
sig
n
a
l
f
e
a
tu
re
s
f
o
r
stre
ss
d
e
tec
ti
o
n
d
u
ri
n
g
in
d
o
o
r
m
o
b
il
it
y
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
8
t
h
ACM
In
t
e
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
u
lt
im
o
d
a
l
In
ter
a
c
ti
o
n
-
ICM
I
2
0
1
6
,
2
0
1
6
.
[
2
2
]
V
.
N.
V
a
p
n
ik
,
“
Dire
c
t
M
e
th
o
d
s
in
S
tatisti
c
a
l
L
e
a
rn
in
g
T
h
e
o
ry
,
”
T
h
e
Na
tu
re
o
f
S
ta
ti
stica
l
L
e
a
rn
in
g
T
h
e
o
ry
,
p
p
.
2
2
5
-
2
6
5
,
2
0
0
0
.
[
2
3
]
A
.
Ch
a
tch
in
a
ra
t,
K.
W
.
W
o
n
g
,
a
n
d
C.
C.
F
u
n
g
,
“
A
c
o
m
p
a
riso
n
stu
d
y
o
n
t
h
e
re
latio
n
s
h
ip
b
e
tw
e
e
n
th
e
se
lec
ti
o
n
o
f
EE
G
e
lec
tro
d
e
c
h
a
n
n
e
ls
a
n
d
f
re
q
u
e
n
c
y
b
a
n
d
s
u
se
d
i
n
c
las
sif
ica
ti
o
n
f
o
r
e
m
o
ti
o
n
re
c
o
g
n
i
ti
o
n
,
”
2
0
1
6
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
a
n
d
Cy
b
e
rn
e
ti
c
s (
ICM
L
C)
,
2
0
1
6
.
[
2
4
]
G
.
H.
G
o
lu
b
,
M
.
He
a
th
,
a
n
d
G
.
W
a
h
b
a
,
“
Ge
n
e
ra
li
z
e
d
c
ro
ss
-
v
a
li
d
a
ti
o
n
a
s
a
m
e
th
o
d
f
o
r
c
h
o
o
si
n
g
a
g
o
o
d
rid
g
e
p
a
ra
m
e
ter,”
T
e
c
h
n
o
me
trics
,
v
o
l.
2
1
,
n
o
.
2
,
p
p
.
2
1
5
-
2
2
3
,
1
9
7
9
.
[
2
5
]
C.
-
C.
Ch
a
n
g
a
n
d
C
.
-
J.
L
in
,
“
L
ib
sv
m
,
”
ACM
T
ra
n
sa
c
ti
o
n
s
o
n
I
n
telli
g
e
n
t
S
y
ste
ms
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
1
-
2
7
,
Ja
n
.
2
0
1
1
.
[
2
6
]
M
.
A
li
,
A
.
H.
M
o
sa
,
F
.
A
l
M
a
c
h
o
t,
a
n
d
K.
Ky
a
m
a
k
y
a
,
“
EE
G
-
b
a
s
e
d
e
m
o
ti
o
n
re
c
o
g
n
it
io
n
a
p
p
ro
a
c
h
f
o
r
e
-
h
e
a
lt
h
c
a
re
a
p
p
li
c
a
ti
o
n
s,”
in
Ub
iq
u
it
o
u
s
a
n
d
Fu
tu
re
Ne
two
rk
s
(
ICUFN)
,
2
0
1
6
Ei
g
h
th
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
,
2
0
1
6
,
p
p
.
9
4
6
-
9
5
0
:
IEE
E
.
[
2
7
]
J.
Ch
e
n
,
B.
Hu
,
P
.
M
o
o
re
,
X
.
Z
h
a
n
g
,
a
n
d
X.
M
a
,
“
El
e
c
tro
e
n
c
e
p
h
a
lo
g
ra
m
-
b
a
s
e
d
e
m
o
ti
o
n
a
ss
e
ss
m
e
n
t
s
y
ste
m
u
sin
g
o
n
t
o
lo
g
y
a
n
d
d
a
ta m
in
in
g
tec
h
n
i
q
u
e
s,”
Ap
p
li
e
d
S
o
ft
Co
m
p
u
ti
n
g
,
v
o
l.
3
0
,
p
p
.
6
6
3
-
6
7
4
,
M
a
y
2
0
1
5
.
[
2
8
]
T
.
F
.
Ba
sto
s
-
F
il
h
o
,
A
.
F
e
rre
ira,
A
.
C.
A
ten
c
io
,
S
.
A
rju
n
a
n
,
a
n
d
D.
Ku
m
a
r,
“
Ev
a
lu
a
ti
o
n
o
f
f
e
a
tu
re
e
x
trac
ti
o
n
tec
h
n
iq
u
e
s in
e
m
o
ti
o
n
a
l
sta
te rec
o
g
n
it
io
n
,
”
in
In
telli
g
e
n
t
h
u
ma
n
c
o
mp
u
ter
in
ter
a
c
ti
o
n
(
IHCI)
,
2
0
1
2
,
p
p
.
1
-
6.
[
2
9
]
Y.
L
iu
a
n
d
O.
S
o
u
r
in
a
,
“
Re
a
l
-
ti
m
e
su
b
jec
t
-
d
e
p
e
n
d
e
n
t
EE
G
-
b
a
se
d
e
m
o
ti
o
n
re
c
o
g
n
it
io
n
a
lg
o
rit
h
m
,
”
T
ra
n
sa
c
ti
o
n
s
o
n
Co
mp
u
t
a
ti
o
n
a
l
S
c
ien
c
e
XX
III:
S
p
rin
g
e
r
,
p
p
.
1
9
9
-
2
2
3
,
2
0
1
4
.
[
3
0
]
A
.
V
ij
a
y
a
n
,
D.
S
e
n
,
a
n
d
A
.
S
u
d
h
e
e
r,
“
EE
G
-
Ba
se
d
E
m
o
ti
o
n
Re
c
o
g
n
it
io
n
Us
in
g
S
tatisti
c
a
l
M
e
a
su
re
s
a
n
d
A
u
to
-
Re
g
re
ss
i
v
e
M
o
d
e
li
n
g
,
”
in
Co
mp
u
ta
ti
o
n
a
l
In
telli
g
e
n
c
e
a
n
d
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
(
CICT
)
,
p
p
.
5
8
7
-
5
9
1
,
2
0
1
5
.
[
3
1
]
P
.
A
c
k
e
r
m
a
n
n
,
C.
Ko
h
lsc
h
e
in
,
J.
A
.
Bit
sc
h
,
K.
W
e
h
rle,
a
n
d
S
.
Je
sc
h
k
e
,
“
EE
G
-
b
a
se
d
a
u
to
m
a
ti
c
e
m
o
ti
o
n
re
c
o
g
n
i
ti
o
n
:
F
e
a
t
u
re
e
x
trac
ti
o
n
,
se
lec
ti
o
n
a
n
d
c
las
sif
i
c
a
ti
o
n
m
e
th
o
d
s,”
2
0
1
6
I
EE
E
1
8
th
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
e
-
He
a
lt
h
Ne
two
rk
in
g
,
Ap
p
li
c
a
t
io
n
s a
n
d
S
e
rv
ice
s
(
He
a
lt
h
c
o
m)
,
p
p
.
1
-
6
,
2
0
1
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Fa
b
ia
n
Pa
r
sia
G
e
o
r
g
e
p
u
rsu
e
d
h
e
r
g
ra
d
u
a
ti
o
n
o
n
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
(B.
S
c
.
)
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
BR
A
C
Un
iv
e
r
sit
y
in
th
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
rin
g
in
S
e
p
tem
b
e
r
2
0
1
8
.
S
h
e
h
a
s
se
rv
e
d
a
s
a
S
tu
d
e
n
t
T
u
t
o
r
(S
T
)
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
BR
A
C
Un
iv
e
r
sit
y
.
Cu
rre
n
tl
y
,
sh
e
is
w
o
r
k
in
g
a
s
a
T
e
a
c
h
e
r
in
G
re
e
n
Da
le
In
tern
a
ti
o
n
a
l
S
c
h
o
o
l.
S
h
e
a
sp
i
re
s
to
p
u
rsu
e
a
c
a
re
e
r
in
th
e
f
ield
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
,
Bra
in
-
Co
m
p
u
ter In
terf
a
c
e
,
Im
a
g
e
P
ro
c
e
ss
in
g
,
a
n
d
Da
ta
M
in
i
n
g
.
I
s
t
ia
qu
e
M
a
nn
a
f
ee
Sh
a
ik
a
t
p
u
rsu
e
d
h
is
g
ra
d
u
a
ti
o
n
o
n
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
(B.
S
c
.
)
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
BR
A
C
Un
iv
e
rsit
y
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
in
M
a
y
2
0
1
8
.
C
u
rre
n
tl
y
,
h
e
is
w
o
rk
in
g
in
th
e
d
e
p
a
rtm
e
n
t
o
f
Dig
it
a
l
In
telli
g
e
n
c
e
a
t
G
ra
m
e
e
n
p
h
o
n
e
L
td
.
,
Ba
n
g
la
d
e
sh
.
He
a
sp
ires
to
p
u
rsu
e
a
c
a
re
e
r
in
th
e
f
ield
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
,
Bra
in
-
Co
m
p
u
ter In
terf
a
c
e
,
I
m
a
g
e
P
r
o
c
e
ss
in
g
,
a
n
d
Da
ta M
in
i
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
2
,
A
p
r
il
201
9
:
1
0
1
2
-
1020
1020
Pro
m
m
y
S
u
lt
a
n
a
Fer
d
a
w
o
o
s
is
a
n
u
n
d
e
rg
ra
d
u
a
te
stu
d
e
n
t
f
ro
m
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
B
RA
C
Un
iv
e
rsit
y
.
S
h
e
w
il
l
b
e
c
o
m
p
letin
g
h
e
r
g
ra
d
u
a
ti
o
n
o
n
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
(B.
S
c
.
)
in
C
o
m
p
u
ter
S
c
ien
c
e
b
y
th
e
e
n
d
o
f
De
c
e
m
b
e
r
2
0
1
8
.
S
h
e
a
sp
ires
to
p
u
rsu
e
a
c
a
re
e
r
in
t
h
e
f
ield
o
f
Br
a
in
-
Co
m
p
u
ter
In
terf
a
c
e
,
Bio
In
f
o
r
m
a
ti
c
s,
A
rti
f
icia
l
In
telli
g
e
n
c
e
,
Ne
tw
o
rk
in
g
a
n
d
Im
a
g
e
P
ro
c
e
ss
in
g
.
Dr
.
M
o
h
a
m
m
a
d
Za
v
i
d
P
a
r
v
e
z
i
s cu
rre
n
tl
y
w
o
r
k
in
g
a
s
a
n
A
ss
ista
n
t
P
ro
f
e
ss
o
r
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
a
t
BRA
C
Un
iv
e
rsit
y
,
Ba
n
g
l
a
d
e
sh
.
He
re
c
e
iv
e
d
h
is
P
h
D
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
Ch
a
rles
S
tu
rt
Un
iv
e
rsity
-
A
u
stra
li
a
,
M
S
c
.
De
g
re
e
in
S
ig
n
a
l
P
r
o
c
e
ss
in
g
f
ro
m
Ble
k
in
g
e
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
-
S
we
d
e
n
,
a
n
d
BS
c
.
En
g
.
(Ho
n
s.)
De
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
f
ro
m
A
sia
n
Un
iv
e
rsit
y
o
f
Ba
n
g
lad
e
sh
.
M
o
re
o
v
e
r,
h
e
w
o
rk
e
d
a
s
a
p
o
std
o
c
to
ra
l
re
se
a
rc
h
e
r
u
n
d
e
r
t
h
e
Eu
ro
p
e
a
n
Un
i
o
n
’s
H
o
rizo
n
2
0
2
0
re
se
a
rc
h
a
n
d
i
n
n
o
v
a
ti
o
n
p
ro
g
ra
m
m
e
.
P
a
rv
e
z
’s
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
b
i
o
m
e
d
ica
l
sig
n
a
l
p
r
o
c
e
ss
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
Dr.
P
a
rv
e
z
h
a
s
p
u
b
li
sh
e
d
se
v
e
ra
l
jo
u
rn
a
l
a
n
d
c
o
n
f
e
re
n
c
e
p
a
p
e
rs
in
t
h
e
a
re
a
o
f
sig
n
a
l
p
ro
c
e
ss
in
g
a
n
d
c
o
g
n
it
iv
e
ra
d
io
.
Dr
.
J
ia
U
d
d
i
n
r
e
c
e
i
v
e
d
a
B.
S
c
.
d
e
g
re
e
in
Co
m
p
u
ter
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
f
ro
m
th
e
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
,
Ch
it
tag
o
n
g
(IIUC),
Ba
n
g
lad
e
sh
,
in
2
0
0
5
,
a
n
M
S
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
w
it
h
a
n
e
m
p
h
a
sis
o
n
T
e
le
c
o
m
m
u
n
ica
ti
o
n
s
f
ro
m
th
e
Blek
in
g
e
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
(B
T
H),
S
w
e
d
e
n
,
in
2
0
1
0
.
He
c
o
m
p
lete
d
h
is
P
h
.
D.
(
Co
m
p
u
ter
En
g
in
e
e
rin
g
)
a
t
th
e
Un
iv
e
rsit
y
o
f
Ulsa
n
(Uo
U),
S
o
u
th
Ko
re
a
in
2
0
1
5
.
He
is
a
n
A
ss
o
c
iate
P
r
o
f
e
ss
o
r
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
BRAC
Un
iv
e
rsit
y
,
Ba
n
g
lad
e
sh
.
Hi
s
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
F
a
u
lt
Dia
g
n
o
sis,
P
a
ra
ll
e
l
Co
m
p
u
ti
n
g
,
a
n
d
W
irele
ss
N
e
t
w
o
rk
s.
He
is
a
m
e
m
b
e
r
o
f
th
e
IEB
a
n
d
t
h
e
IA
CS
IT
.
Evaluation Warning : The document was created with Spire.PDF for Python.