I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
2786
~
2
7
9
5
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
3
.
pp
2
7
8
6
-
2
7
9
5
2786
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Electroencep
ha
lo
g
ra
phy
cla
ss
ificatio
n t
echni
que bas
ed on
sta
tistical de
no
ising
a
nd
mo
dified
k
-
nea
rest
neighbo
r
a
lg
o
rithm
with
bi
po
la
r
sig
mo
id rect
i
fied
li
nea
r
unit
’s
fu
nction
T
hej
a
s
win
i Bek
k
a
la
le
M
a
ha
lin
g
eg
o
wda
1,
2
,
G
la
n De
v
a
dh
a
s
G
eo
rg
e
1
,
Sa
t
heesh
a
T
um
a
ku
r
Yo
g
a
3
,
K
a
liy
a
mo
o
rt
hy
E
zhila
ra
s
a
n
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
,
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
C
M
R
U
n
i
v
e
r
s
i
t
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
V
LSI
D
e
si
g
n
a
n
d
Te
c
h
n
o
l
o
g
y
,
B
a
n
g
a
l
o
r
e
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
3
S
c
h
o
o
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
R
EV
A
U
n
i
v
e
r
si
t
y
,
B
e
n
g
a
l
u
r
u
,
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
2
8
,
2
0
2
4
R
ev
is
ed
Dec
2
6
,
2
0
2
4
Acc
ep
ted
J
an
1
6
,
2
0
2
5
Ac
c
u
ra
te
c
las
sific
a
ti
o
n
o
f
e
lec
tro
e
n
c
e
p
h
a
lo
g
ra
p
h
y
(
E
EG
)
d
a
ta
is
m
u
c
h
n
e
e
d
e
d
fo
r
e
a
rly
id
e
n
ti
f
ica
ti
o
n
o
f
d
ise
a
se
s
to
trea
t
v
a
rio
u
s
d
iso
rd
e
rs.
In
t
h
is
p
a
p
e
r,
we
p
ro
p
o
se
EE
G
c
las
sifica
ti
o
n
tec
h
n
iq
u
e
b
a
se
d
o
n
sta
ti
stica
l
d
e
n
o
i
sin
g
a
n
d
m
o
d
ifi
e
d
k
-
n
e
a
re
st n
e
ig
h
b
o
r
(k
-
N
N)
a
lg
o
rit
h
m
with
b
ip
o
lar sig
m
o
i
d
re
c
ti
fie
d
li
n
e
a
r
u
n
it
s
(Re
LU)
fu
n
c
ti
o
n
.
Th
e
EE
G
d
a
ta
is
su
b
jec
ted
to
sta
ti
stica
l
m
e
th
o
d
s
to
re
m
o
v
e
t
h
e
a
rti
fa
c
ts
a
n
d
th
e
n
a
p
p
li
e
d
t
o
m
o
d
ifi
e
d
k
-
NN
a
l
g
o
rit
h
m
t
o
c
a
teg
o
rize
th
e
a
p
p
ro
p
riate
fe
a
tu
re
s
g
iv
in
g
p
re
fe
re
n
c
e
to
n
e
ig
h
b
o
r
s
c
lo
se
r
to
o
n
e
a
n
o
th
e
r
c
o
n
sid
e
ri
n
g
t
h
e
we
ig
h
ted
v
o
tes
o
f
t
h
e
k
-
n
e
a
re
st n
e
ig
h
b
o
rs b
e
fo
re
se
lec
ti
n
g
t
h
e
c
las
s
lab
e
l
b
a
se
d
o
n
t
h
e
h
ig
h
e
st
we
ig
h
ted
v
o
te.
A
c
u
sto
m
ize
d
a
c
ti
v
a
ti
o
n
fu
n
c
ti
o
n
th
a
t
c
o
m
b
i
n
e
s
th
e
se
two
fu
n
c
ti
o
n
s
c
a
ll
e
d
a
s
h
y
b
ri
d
fu
n
c
ti
o
n
t
h
a
t
u
se
s
v
a
rio
u
s
p
o
rti
o
n
s
o
f
e
a
c
h
f
u
n
c
ti
o
n
in
p
a
rti
c
u
lar
ra
n
g
e
s
is
u
se
d
in
o
u
r
wo
r
k
i.
e
.
,
u
se
o
f
b
i
p
o
lar
sig
m
o
id
fo
r
n
e
g
a
ti
v
e
v
a
lu
e
s
a
n
d
t
h
e
Re
LU
fu
n
c
ti
o
n
f
o
r
p
o
sit
iv
e
v
a
lu
e
s
wh
i
c
h
h
e
lp
s
to
li
m
it
t
h
e
si
g
n
a
l
i
n
a
p
a
rti
c
u
la
r
ra
n
g
e
.
Th
e
p
r
o
p
o
se
d
a
lg
o
rit
h
m
'
s
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
is
tes
ted
fo
r
th
e
c
o
n
fu
si
o
n
m
a
tri
x
o
f
tru
e
p
o
siti
v
e
(TP
),
fa
lse
p
o
siti
v
e
(F
P
),
fa
lse
n
e
g
a
ti
v
e
(
F
N)a
n
d
tr
u
e
n
e
g
a
ti
v
e
(TN)
a
n
d
c
o
m
p
a
re
d
t
o
th
e
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
o
f
o
t
h
e
r
e
x
isti
n
g
a
lg
o
rit
h
m
s,
d
e
m
o
n
stra
ti
n
g
t
h
e
a
lg
o
rit
h
m
'
s
e
fficie
n
c
y
with
a
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
a
lmo
st
8
5
p
e
rc
e
n
t
a
n
d
se
n
si
ti
v
i
ty
o
f
9
1
%
f
o
r
sta
n
d
a
rd
Ka
g
g
le
d
a
tas
e
t
.
K
ey
w
o
r
d
s
:
B
ip
o
lar
s
ig
m
o
id
Den
o
is
in
g
E
lectr
o
en
ce
p
h
al
o
g
r
a
p
h
y
K
-
n
ea
r
est n
eig
h
b
o
r
Sen
s
itiv
ity
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
h
ejaswin
i Bek
k
alale
Ma
h
alin
g
eg
o
wd
a
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
,
Sch
o
o
l o
f
E
n
g
in
ee
r
in
g
an
d
T
ec
h
n
o
lo
g
y
,
C
MR Un
iv
er
s
ity
B
en
g
alu
r
u
,
Kar
n
atak
a
-
5
6
0
0
0
4
,
I
n
d
ia
E
m
ail:
th
ejaswin
i.b
m
g
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
l
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
p
h
y
i
s
r
e
f
e
r
r
e
d
t
o
a
s
e
l
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
p
h
y
(
E
E
G
)
.
T
h
i
s
n
o
n
-
i
n
v
a
s
i
v
e
n
e
u
r
o
i
m
a
g
i
n
g
m
e
t
h
o
d
i
s
u
s
e
d
t
o
c
a
p
t
u
r
e
t
h
e
e
l
e
c
t
r
i
c
a
l
a
c
t
i
v
i
ty
t
h
a
t
t
h
e
b
r
ai
n
p
r
o
d
u
c
e
s
.
I
n
o
r
d
e
r
t
o
i
d
e
n
t
i
f
y
t
h
e
e
l
e
c
t
r
ic
a
l
i
m
p
u
l
s
es
g
e
n
e
r
at
e
d
b
y
t
h
e
b
r
a
i
n
'
s
n
e
u
r
o
n
s
,
e
l
e
ct
r
o
d
e
s
a
r
e
a
p
p
l
i
e
d
t
o
t
h
e
s
ca
l
p
.
B
r
a
i
n
w
a
v
es
a
r
e
t
h
e
r
e
p
r
e
s
e
n
t
a
ti
o
n
o
f
t
h
e
e
l
e
c
t
r
i
c
a
l
a
c
t
i
v
i
t
y
p
r
o
d
u
c
e
d
b
y
n
e
u
r
o
n
a
l
c
o
m
m
u
n
i
c
a
t
i
o
n
i
n
t
h
e
b
r
a
i
n
.
T
h
e
s
e
b
r
a
i
n
w
a
v
e
s
a
r
e
c
a
t
e
g
o
r
i
z
e
d
as
b
e
l
o
n
g
i
n
g
t
o
b
e
t
a
,
g
a
m
m
a
,
a
l
p
h
a
,
t
h
e
t
a
,
a
n
d
d
e
l
t
a
f
r
e
q
u
e
n
c
y
r
a
n
g
es
.
C
e
r
t
a
in
m
e
n
t
a
l
p
r
o
c
e
s
s
e
s
,
c
o
g
n
i
t
i
v
e
s
t
a
t
es
,
o
r
a
c
ti
v
i
t
i
es
a
r
e
l
i
n
k
e
d
t
o
e
a
c
h
o
f
t
h
es
e
f
r
e
q
u
e
n
c
y
b
a
n
d
s
.
I
n
c
l
i
n
i
c
al
s
et
t
i
n
g
s
,
E
E
G
i
s
f
r
e
q
u
e
n
tl
y
u
s
e
d
t
o
d
i
a
g
n
o
s
e
a
n
d
t
r
a
c
k
a
v
ar
i
e
t
y
o
f
n
e
u
r
o
l
o
g
i
c
al
p
r
o
b
l
e
m
s
,
i
n
c
l
u
d
i
n
g
e
p
il
e
p
s
y
,
s
l
e
e
p
d
is
o
r
d
e
r
s
,
b
r
a
i
n
t
r
a
u
m
a
s
,
a
n
d
o
t
h
e
r
a
b
n
o
r
m
a
l
i
t
i
e
s
r
e
la
t
ed
t
o
t
h
e
b
r
a
i
n
.
A
d
d
i
t
i
o
n
a
l
l
y
,
i
t
i
s
e
m
p
l
o
y
e
d
i
n
r
e
s
e
a
r
c
h
t
o
e
x
a
m
i
n
e
n
e
u
r
o
l
o
g
i
c
a
l
p
r
o
b
l
e
m
s
,
s
l
e
e
p
p
a
tt
e
r
n
s
,
c
o
g
n
it
i
v
e
f
u
n
c
t
i
o
n
s
,
a
n
d
b
r
a
i
n
f
u
n
c
t
i
o
n
.
N
e
u
r
o
l
o
g
i
s
t
s
o
r
r
e
s
ea
r
c
h
e
r
s
e
x
a
m
i
n
e
t
h
e
w
a
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
cl
a
s
s
ifica
tio
n
tech
n
iq
u
e
…
(
Th
ej
a
s
w
in
i B
ek
ka
la
le
Ma
h
a
lin
g
e
g
o
w
d
a
)
2787
p
a
t
t
e
r
n
s
t
h
a
t
t
h
e
E
E
G
s
i
g
n
a
l
p
r
o
d
u
c
e
s
o
n
a
c
o
m
p
u
t
e
r
s
c
r
e
e
n
in
o
r
d
e
r
t
o
g
e
t
i
n
s
i
g
h
t
i
n
t
o
a
b
n
o
r
m
a
l
b
r
a
i
n
a
ct
i
v
i
t
y
,
c
h
a
n
g
e
s
i
n
r
e
a
ct
i
o
n
t
o
s
t
i
m
u
l
i
,
o
r
b
r
a
i
n
f
u
n
c
t
i
o
n
.
M
o
r
e
p
o
r
t
a
b
l
e
a
n
d
u
s
e
r
-
f
r
i
e
n
d
l
y
E
E
G
d
e
v
ic
e
s
h
a
v
e
b
e
e
n
m
a
d
e
p
o
s
s
i
b
le
b
y
a
d
v
a
n
c
e
m
e
n
t
s
i
n
t
h
e
f
i
e
l
d
.
T
h
i
s
h
a
s
a
l
l
o
w
e
d
r
e
s
ea
r
c
h
e
r
s
t
o
c
o
n
d
u
c
t
s
t
u
d
i
es
i
n
a
v
a
r
i
e
t
y
o
f
s
e
t
t
i
n
g
s
,
s
u
c
h
a
s
d
u
r
i
n
g
r
o
u
t
i
n
e
t
as
k
s
o
r
d
a
i
l
y
a
c
t
i
v
i
t
i
es
,
a
n
d
h
a
s
d
ee
p
e
n
e
d
o
u
r
u
n
d
e
r
s
t
a
n
d
i
n
g
o
f
h
o
w
b
r
a
i
n
a
c
t
i
v
it
y
a
f
f
e
c
ts
b
e
h
a
v
i
o
r
a
n
d
c
o
g
n
i
t
i
o
n
.
B
r
a
i
n
t
r
a
n
s
m
i
s
s
i
o
n
s
a
r
e
ta
m
p
e
r
e
d
w
i
t
h
b
y
u
n
w
a
n
t
e
d
p
o
t
e
n
t
i
a
ls
i
n
t
h
e
E
E
G
s
i
g
n
al
.
A
r
ti
f
a
c
ts
a
r
e
t
h
e
s
e
s
i
g
n
a
l
s
,
a
n
d
t
h
e
y
s
h
o
u
l
d
b
e
e
l
i
m
i
n
at
e
d
b
e
f
o
r
e
m
o
v
i
n
g
o
n
t
o
t
h
e
p
r
o
c
e
s
s
i
n
g
s
t
ag
e
.
T
h
e
a
r
t
i
f
a
ct
s
a
r
e
g
e
n
e
r
a
t
e
d
f
r
o
m
b
o
t
h
p
h
y
s
i
o
l
o
g
i
c
a
l
a
n
d
n
o
n
-
p
h
y
s
i
o
l
o
g
ic
a
l
o
f
th
e
h
u
m
a
n
b
o
d
y
.
T
h
e
p
r
e
c
i
s
e
c
la
s
s
i
f
i
c
at
i
o
n
o
f
E
E
G
d
a
t
a
i
s
t
h
e
a
i
m
o
f
t
h
e
f
i
e
l
d
o
f
E
E
G
c
l
a
s
s
i
f
ic
a
t
i
o
n
r
e
s
ea
r
c
h
.
A
n
u
m
b
e
r
o
f
s
t
r
a
t
e
g
i
e
s
a
n
d
t
a
c
t
i
cs
h
a
v
e
b
e
e
n
p
u
t
f
o
r
t
h
t
o
i
n
c
r
e
as
e
t
h
e
E
E
G
s
i
g
n
a
l
s
'
c
at
e
g
o
r
i
z
a
t
i
o
n
a
c
c
u
r
a
c
y
.
O
n
e
m
e
th
o
d
m
a
p
s
E
E
G
d
a
t
a
t
o
a
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l f
e
a
t
u
r
e
s
p
a
c
e
t
h
a
t
c
a
n
b
e
u
t
il
i
z
e
d
f
o
r
c
l
as
s
i
f
i
c
a
ti
o
n
b
y
c
o
m
b
i
n
i
n
g
d
e
e
p
co
n
v
o
l
u
t
i
o
n
n
e
t
w
o
r
k
s
w
i
t
h
l
o
n
g
s
h
o
r
t
-
t
e
r
m
m
e
m
o
r
y
n
e
t
w
o
r
k
s
a
n
d
a
t
t
e
n
t
i
o
n
p
r
o
c
e
s
s
e
s
[
1
]
.
T
o
i
m
p
r
o
v
e
c
l
a
s
s
i
f
i
ca
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
,
a
n
o
t
h
e
r
t
e
c
h
n
i
q
u
e
u
s
e
s
l
a
b
el
e
d
a
n
d
u
n
l
a
b
e
l
e
d
d
a
t
a
i
n
a
s
e
m
i
-
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
f
r
a
m
ew
o
r
k
[
2
]
.
Fu
r
th
er
m
o
r
e
,
to
ex
tr
ac
t
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
f
r
o
m
E
E
G
d
ata,
f
ea
t
u
r
e
e
x
tr
ac
tio
n
m
eth
o
d
s
s
u
ch
d
im
en
s
io
n
ality
r
e
d
u
ctio
n
,
s
tatis
tical
an
aly
s
is
,
an
d
ad
ap
t
iv
e
s
eg
m
en
tatio
n
h
av
e
b
ee
n
u
s
ed
[
3
]
.
E
E
G
ca
teg
o
r
izatio
n
h
as
b
ee
n
d
o
n
e
u
s
in
g
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
s
u
ch
as
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
k
-
NN)
,
k
-
m
ea
n
s
,
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANNs)
,
an
d
f
u
zz
y
s
ets
[
4
]
.
I
n
th
e
f
ield
s
o
f
m
ac
h
i
n
e
lear
n
in
g
an
d
d
ata
an
aly
s
is
,
in
p
ar
ticu
lar
,
E
E
G
d
ata
ca
n
b
e
u
tili
ze
d
f
o
r
ca
teg
o
r
izatio
n
task
s
.
E
E
G
s
ig
n
als
ar
e
cla
s
s
if
ied
b
y
p
lacin
g
th
em
i
n
s
ev
er
al
g
r
o
u
p
s
o
r
class
es.
T
h
i
s
h
as
a
n
u
m
b
er
o
f
p
o
ten
tial
u
s
es:
b
r
ain
-
co
m
p
u
ter
in
ter
f
ac
es
(
B
C
I
s
)
[
5
]
.
I
n
B
C
I
s
y
s
tem
s
,
wh
er
e
ce
r
tain
co
m
m
an
d
s
o
r
ac
tio
n
s
ar
e
lin
k
ed
to
s
p
ec
if
ic
b
r
ain
ac
tiv
ity
p
atter
n
s
,
E
E
G
ca
teg
o
r
izatio
n
is
cr
u
cial.
C
lass
if
y
in
g
E
E
G
s
ig
n
als
lin
k
ed
to
d
is
tin
ct
m
o
to
r
in
ten
ts
(
e.
g
.
,
u
s
in
g
th
e
lef
t
o
r
r
ig
h
t
h
an
d
to
co
n
tr
o
l
a
g
ad
g
et)
is
o
n
e
ex
am
p
le.
Ne
u
r
o
lo
g
ical
p
r
o
b
lem
s
:
B
r
ain
tr
a
u
m
as,
s
leep
p
r
o
b
lem
s
,
an
d
ep
il
ep
s
y
ar
e
ju
s
t
a
f
ew
o
f
th
e
n
eu
r
o
lo
g
ical
co
n
d
itio
n
s
th
at
ca
n
b
e
d
iag
n
o
s
ed
an
d
tr
ac
k
ed
with
th
e
h
elp
o
f
E
E
G
s
ig
n
al
class
if
icatio
n
.
I
t
is
ess
en
tial
th
at
m
o
d
els
b
e
ab
l
e
to
g
en
e
r
alize
to
n
ew,
u
n
test
ed
d
ata.
R
esear
ch
er
s
u
s
e
a
v
ar
iety
o
f
a
p
p
r
o
ac
h
es,
in
clu
d
in
g
f
ea
tu
r
e
s
elec
tio
n
,
c
r
o
s
s
-
v
alid
atio
n
,
e
n
s
em
b
lin
g
m
eth
o
d
s
,
m
ac
h
in
e
lear
n
in
g
a
lg
o
r
ith
m
s
[
6
]
(
lik
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
an
d
d
ee
p
lear
n
in
g
(
DL
)
)
,
a
n
d
s
ig
n
al
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
s
,
to
o
v
er
co
m
e
th
ese
o
b
s
tacle
s
an
d
im
p
r
o
v
e
th
e
r
o
b
u
s
tn
ess
an
d
ac
cu
r
ac
y
o
f
E
E
G
class
if
icatio
n
m
o
d
els.
Su
g
an
y
ad
e
v
i
et
a
l.
[
7
]
p
r
o
p
o
s
e
a
class
if
icatio
n
tech
n
iq
u
e
f
o
r
au
to
m
ated
ep
ilep
s
y
i
d
en
tific
atio
n
f
r
o
m
E
E
G
d
ata.
Prio
r
to
f
ea
tu
r
e
ex
t
r
ac
tio
n
,
th
e
s
ig
n
als
p
r
o
d
u
c
ed
b
y
th
e
E
E
G
e
q
u
ip
m
e
n
t
wer
e
co
n
v
er
ted
u
s
in
g
th
e
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
(
D
W
T
)
.
A
m
eth
o
d
ca
lled
GB
Ms
f
u
s
io
n
was
cr
ea
ted
to
d
etec
t
E
E
G
d
ata
u
s
in
g
a
v
ar
iety
o
f
s
tatis
tical
f
ac
to
r
s
an
d
cr
o
s
s
in
g
f
r
e
q
u
en
c
y
p
r
o
p
e
r
ties
.
I
n
a
d
d
itio
n
,
a
g
en
etic
alg
o
r
it
h
m
was
u
s
ed
to
p
ic
k
th
e
im
p
o
r
ta
n
t
f
ea
tu
r
es
in
itially
.
W
e
h
av
e
test
ed
th
e
ab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
to
d
is
cr
im
in
ate
b
etwe
en
ictal
an
d
n
o
r
m
al
E
E
G
p
atter
n
s
u
s
in
g
E
E
G
d
ata
f
r
o
m
t
h
e
U
n
iv
er
s
ity
o
f
B
o
n
n
.
Acc
o
r
d
in
g
to
ex
p
e
r
im
en
ts
,
th
e
p
r
o
p
o
s
ed
f
u
s
io
n
o
f
g
r
a
d
ien
t b
o
o
s
tin
g
m
ac
h
in
es
(
GB
Ms)
m
a
y
im
p
r
o
v
e
th
e
E
E
G
class
if
icatio
n
ab
ilit
y
.
W
ith
th
e
p
r
o
p
o
s
ed
GB
Ms
f
u
s
io
n
,
ep
ile
p
s
y
m
ay
also
b
e
1
0
0
%
ac
cu
r
ately
id
en
tifie
d
f
r
o
m
E
E
G
d
a
ta.
Ad
d
itio
n
ally
,
a
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
to
th
e
d
etec
tio
n
o
f
e
p
ilep
tic
E
E
G
s
ig
n
als
is
p
r
o
p
o
s
ed
in
th
is
s
tu
d
y
[
8
]
.
I
n
o
r
d
er
t
o
co
n
d
u
ct
a
co
m
p
a
r
is
o
n
an
aly
s
i
s
,
th
e
b
en
ch
m
a
r
k
d
ataset
was
u
tili
ze
d
f
o
r
th
is
in
v
esti
g
atio
n
.
T
h
r
ee
class
if
icatio
n
m
o
d
els
h
av
e
b
ee
n
u
s
ed
to
d
is
tin
g
u
is
h
b
etwe
en
n
o
r
m
al
E
E
G
an
d
ep
ilep
tic
E
E
G:
r
an
d
o
m
f
o
r
est
(
R
F),
d
ec
is
io
n
tr
ee
(
DT
)
,
an
d
e
x
tr
a
tr
ee
(
E
T
)
.
T
h
r
ee
f
ac
to
r
s
ar
e
u
s
ed
to
ass
es
s
th
e
alg
o
r
ith
m
'
s
p
er
f
o
r
m
an
ce
:
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
an
d
ac
cu
r
ac
y
.
E
T
p
er
f
o
r
m
ed
th
e
b
est
o
u
t
o
f
all
th
e
class
if
ier
s
;
th
e
s
u
g
g
ested
m
eth
o
d
'
s
p
ar
am
eter
s
ar
e
9
9
.
8
5
,
9
9
.
4
2
,
a
n
d
9
9
.
6
3
,
r
esp
ec
tiv
ely
.
I
n
[
9
]
,
t
h
e
Gau
s
s
ian
p
r
o
ce
s
s
class
if
ier
(
GPC
)
is
u
s
ed
to
an
aly
ze
th
e
r
esu
lts
f
o
r
t
h
r
ee
d
is
tin
ct
ty
p
es
o
f
E
E
G
s
ig
n
als:
m
o
to
r
im
ag
e
r
y
,
f
in
g
er
m
o
v
em
en
t
E
E
G
d
at
a,
an
d
s
tead
y
s
tate
v
is
u
ally
ev
o
k
ed
p
o
ten
tial
(
SS
VE
P).
T
h
is
p
ap
er
'
s
p
r
im
ar
y
g
o
al
is
to
in
v
esti
g
ate
wh
eth
er
GPC
i
s
u
s
ef
u
l
f
o
r
class
if
y
in
g
E
E
G
d
ata
f
o
r
v
ar
io
u
s
task
s
.
T
h
e
GP
C
ac
h
iev
es
co
m
p
ar
ab
le
o
r
g
r
ea
ter
p
e
r
f
o
r
m
an
ce
s
wh
en
co
m
p
ar
ed
to
s
o
m
e
well
u
s
ed
alg
o
r
ith
m
s
.
Mo
r
eo
v
er
,
b
o
th
o
n
lin
e
an
d
o
f
f
lin
e
E
E
G
an
aly
s
is
d
ec
is
io
n
-
m
ak
in
g
ca
n
g
r
ea
tly
b
en
ef
it f
r
o
m
th
e
p
r
o
b
ab
ili
s
tic
o
u
tp
u
t th
at
t
h
e
GPC
p
r
o
d
u
ce
s
.
W
u
et
a
l.
[
1
0
]
p
r
o
p
o
s
e
a
n
o
v
el
en
d
-
to
-
e
n
d
s
tr
u
ctu
r
e
d
d
ee
p
lear
n
in
g
m
o
d
el
to
a
u
t
o
m
atica
lly
d
is
cr
im
in
ate
b
etwe
en
n
o
r
m
al
an
d
p
ath
o
l
o
g
ical
E
E
G
s
ig
n
als.
I
n
o
r
d
e
r
to
en
h
a
n
ce
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
we
lo
o
k
in
t
o
th
e
p
r
o
s
p
ec
t
o
f
f
u
s
in
g
th
e
f
u
n
d
am
en
tal
c
o
n
ce
p
ts
o
f
r
esid
u
al
a
n
d
i
n
ce
p
tio
n
ar
ch
itectu
r
es
in
to
a
h
y
b
r
id
m
o
d
el.
W
e
co
n
d
u
cted
co
m
p
r
eh
e
n
s
iv
e
ex
p
e
r
im
en
ts
o
n
a
r
ea
l
-
wo
r
ld
d
ataset
to
e
v
al
u
ate
th
e
s
u
g
g
ested
s
tr
ateg
y
,
an
d
th
e
r
esu
lts
d
em
o
n
s
tr
ate
its
ef
f
ec
tiv
en
ess
an
d
f
e
asib
ilit
y
.
Ou
r
m
eth
o
d
p
er
f
o
r
m
s
b
etter
th
an
o
th
e
r
k
n
o
wn
E
E
G
s
ig
n
al
m
eth
o
d
s
wh
en
co
m
p
ar
ed
to
ea
r
lier
s
tu
d
ies
o
n
th
e
s
am
e
d
ata.
T
h
er
e
f
o
r
e,
th
e
s
u
g
g
ested
ap
p
r
o
ac
h
ca
n
h
elp
m
e
d
ical
p
r
o
f
ess
io
n
als
au
to
m
atica
lly
id
en
tify
b
r
ain
ac
tiv
ity
.
Li
[
1
1
]
s
tu
d
ied
th
e
u
s
e
o
f
d
ee
p
lear
n
in
g
m
o
d
els
o
n
a
m
o
to
r
i
m
ag
er
y
E
E
G
s
ig
n
al
d
ataset
with
tem
p
o
r
al
an
d
s
p
atial
in
f
o
r
m
atio
n
ca
teg
o
r
izatio
n
jo
b
.
I
n
o
r
d
er
to
cr
ea
te
tr
ai
n
in
g
s
am
p
les
f
o
r
d
ee
p
lea
r
n
in
g
m
o
d
els
an
d
s
tan
d
ar
d
ize
th
e
t
r
ain
in
g
s
am
p
les
to
en
h
an
ce
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
m
o
d
els,
th
ey
u
tili
ze
s
lid
in
g
win
d
o
ws
with
p
r
ed
eter
m
i
n
e
d
win
d
o
w
s
izes
an
d
s
tr
id
es.
On
th
e
class
if
icatio
n
a
n
d
in
te
r
p
r
etatio
n
p
e
r
f
o
r
m
an
ce
ac
r
o
s
s
th
e
r
elev
a
n
t
d
ataset,
c
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
s
an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs)
ar
e
s
tu
d
ied
an
d
co
n
tr
asted
.
W
h
en
i
t
co
m
es
to
tr
ain
in
g
ef
f
icien
cy
an
d
ac
cu
r
ac
y
,
th
e
c
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
o
u
tp
er
f
o
r
m
s
o
th
er
m
o
d
els.
L
az
ca
n
o
-
Her
r
e
r
a
et
a
l.
[
1
2
]
u
s
ed
a
v
a
r
iety
o
f
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
to
ca
teg
o
r
ize
E
E
G
d
ata.
A
n
u
m
b
er
o
f
al
g
o
r
ith
m
s
h
a
v
e
b
ee
n
test
ed
f
o
r
th
eir
ab
ilit
y
t
o
d
is
tin
g
u
is
h
b
etwe
en
t
h
e
two
ca
teg
o
r
ies
o
f
m
o
v
em
en
t
an
d
in
ac
ti
v
ity
:
SVM,
k
-
NN
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
2
7
8
6
-
2
7
9
5
2788
q
u
ad
r
atic
d
is
cr
im
in
an
t a
n
aly
s
i
s
(
QDA)
,
lin
ea
r
d
is
cr
im
in
an
t a
n
aly
s
is
(
L
DA)
,
n
aiv
e
B
ay
es (
NB
)
,
an
d
en
s
em
b
le
.
T
h
e
m
o
v
em
en
t
class
in
clu
d
e
d
b
aselin
e
m
o
v
em
e
n
t
an
d
i
n
ac
tiv
ity
d
ata
in
ad
d
itio
n
to
MI
d
ata.
T
h
e
s
u
g
g
ested
E
E
G
ca
teg
o
r
izatio
n
tech
n
i
q
u
e
s
,
in
clu
d
in
g
NB
an
d
QDA,
h
av
e
th
e
h
ig
h
est
lev
el
o
f
ac
cu
r
ac
y
.
C
o
n
v
o
lu
tio
n
al
an
d
R
NNs
ar
e
u
s
ed
f
o
r
E
E
G
class
if
icatio
n
ap
p
licatio
n
s
.
T
h
is
s
tu
d
y
[
1
3
]
p
r
o
v
i
d
es
co
m
p
r
eh
e
n
s
iv
e
d
etails
o
n
th
e
d
ee
p
lear
n
in
g
ar
c
h
itectu
r
e,
th
e
E
E
G
p
r
ep
r
o
ce
s
s
in
g
a
p
p
r
o
ac
h
,
a
n
d
th
e
d
ataset
th
at
was
em
p
lo
y
ed
.
Par
ticu
lar
ad
v
ice
f
o
r
h
y
p
er
p
ar
am
eter
a
d
ju
s
tm
e
n
t
is
also
co
v
er
ed
in
th
is
s
tu
d
y
.
B
eh
er
a
an
d
Mo
h
an
ty
[
1
4
]
tr
ie
d
to
u
s
e
n
eu
r
al
n
etwo
r
k
s
f
o
r
d
etec
tio
n
an
d
r
em
o
v
al
o
f
ar
tef
a
cts in
o
r
d
er
to
class
if
y
th
e
s
ig
n
als.
Alth
o
u
g
h
n
eu
r
al
n
etwo
r
k
m
o
d
els
h
a
v
e
o
n
ly
b
ee
n
u
tili
ze
d
in
th
e
p
ast
f
o
r
class
if
icatio
n
p
r
o
b
lem
s
,
th
e
in
n
o
v
atio
n
in
th
is
wo
r
k
is
th
e
d
etec
t
io
n
o
f
ar
tef
ac
ts
.
T
h
e
o
u
tco
m
es o
f
v
ar
io
u
s
m
o
d
els,
in
clu
d
in
g
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
ML
P),
r
ad
ial
b
asis
f
u
n
ctio
n
n
etwo
r
k
(
R
B
FN)
,
an
d
SVM,
ar
e
co
n
tr
asted
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
cu
b
ic
SVM
p
er
f
o
r
m
s
b
etter
th
an
an
y
o
th
er
m
o
d
el.
Featu
r
es
in
th
e
tim
e
an
d
f
r
eq
u
en
c
y
d
o
m
ain
s
h
av
e
b
ee
n
co
llected
to
f
ee
d
th
e
m
o
d
el.
Ad
d
itio
n
ally
,
co
m
b
i
n
in
g
f
ea
tu
r
es
is
an
o
th
er
c
u
ttin
g
-
ed
g
e
m
eth
o
d
th
at
im
p
r
o
v
es
ac
cu
r
ac
y
o
v
er
u
s
in
g
s
im
p
ly
tim
e
-
d
o
m
ain
o
r
f
r
eq
u
e
n
cy
-
d
o
m
ain
in
f
o
r
m
atio
n
in
t
h
e
cu
b
ic
SVM
m
o
d
el.
T
h
e
r
esu
lts
s
ec
tio
n
co
n
tain
s
th
e
ac
cu
r
ac
y
,
wh
ic
h
was
f
o
u
n
d
t
o
b
e
9
5
.
1
%.
T
h
e
im
p
ac
t
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
f
o
r
E
E
G
s
ig
n
al
tr
ain
in
g
was
ex
am
in
ed
[
1
5
]
u
s
in
g
DW
T
,
im
p
u
ls
e
r
esp
o
n
s
e
(
I
I
R
)
,
SVM,
an
d
b
ag
g
e
d
tr
ee
(
B
T
)
ap
p
r
o
ac
h
es.
T
h
e
au
th
o
r
s
also
co
n
d
u
cte
d
a
co
m
p
a
r
is
o
n
b
et
wee
n
all
tech
n
iq
u
es
an
d
th
ei
r
ef
f
ec
ts
o
n
d
ataset
tr
ain
in
g
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
.
T
h
e
p
r
ec
is
io
n
o
f
s
ev
er
al
p
att
er
n
r
ec
o
g
n
itio
n
ap
p
r
o
ac
h
es
an
d
th
e
s
en
s
itiv
ity
o
f
elev
en
m
en
tal
s
tates,
in
clu
d
in
g
s
tates
i
n
v
o
lv
in
g
th
o
u
g
h
t
s
ig
n
als
an
d
ey
e
b
e
h
av
io
r
,
ar
e
th
e
m
ain
ar
ea
s
o
f
f
o
cu
s
f
o
r
th
e
a
u
th
o
r
s
.
T
h
is
p
ap
er
[
1
6
]
d
is
cu
s
s
es m
o
r
e
co
n
tem
p
o
r
ar
y
m
ac
h
in
e
lear
n
in
g
a
p
p
r
o
ac
h
e
s
lik
e
ANN
an
d
DL
in
ad
d
itio
n
t
o
th
e
class
ic
o
n
es lik
e
SVM
an
d
b
ag
g
ed
tr
ee
(
B
T
)
.
I
n
s
u
m
m
ar
y
,
SVM,
n
eu
r
al
n
e
two
r
k
s
,
h
id
d
en
Ma
r
k
o
v
m
o
d
e
ls
,
k
-
NN
,
DT
s
,
an
d
,
m
o
r
e
r
ec
en
tly
,
DL
tech
n
iq
u
es
lik
e
co
n
v
o
lu
tio
n
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs)
an
d
R
NNs
ar
e
ex
am
p
les
o
f
m
ac
h
i
n
e
l
ea
r
n
in
g
alg
o
r
ith
m
s
th
at
ar
e
f
r
e
q
u
en
tly
u
s
ed
in
E
E
G
an
aly
s
is
.
I
t
is
p
o
s
s
ib
le
to
d
iag
n
o
s
e
n
eu
r
o
lo
g
ical
d
is
o
r
d
er
s
,
co
m
p
r
e
h
en
d
b
r
ai
n
f
u
n
ctio
n
,
a
n
d
cr
ea
te
n
o
v
el
a
p
p
licatio
n
s
i
n
n
eu
r
o
lo
g
y
,
b
r
ain
-
c
o
m
p
u
ter
in
te
r
f
ac
e
tech
n
o
lo
g
ie
s
,
an
d
h
ea
lth
ca
r
e
b
y
co
m
b
in
in
g
m
ac
h
in
e
lear
n
in
g
a
lg
o
r
ith
m
s
with
E
E
G
d
ata.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
s
o
f
th
is
p
ap
er
ar
e:
a.
T
h
e
u
s
e
o
f
s
tatis
tical
b
ased
ap
p
r
o
ac
h
f
o
r
d
en
o
is
in
g
an
d
to
r
e
d
u
ce
t
h
e
ef
f
ec
t
o
f
a
r
tifa
cts
in
th
e
E
E
G
s
ig
n
al
by
lik
elih
o
o
d
r
atio
test
(
L
R
T
)
.
b.
T
h
e
u
s
e
o
f
weig
h
ted
v
o
tin
g
in
k
-
NN
:
T
h
is
m
eth
o
d
u
s
es
weig
h
ts
b
ased
o
n
d
is
tan
ce
s
to
ass
ig
n
a
class
lab
el,
f
av
o
r
in
g
n
eig
h
b
o
r
s
wh
o
ar
e
cl
o
s
er
to
g
eth
er
.
c.
T
h
e
u
s
e
o
f
m
o
d
if
ied
p
r
e
d
ictio
n
f
u
n
ctio
n
in
k
-
NN
wh
ich
ch
o
o
s
es
th
e
class
lab
el
b
ased
o
n
t
h
e
h
i
g
h
est
weig
h
ted
v
o
te
a
f
ter
tak
in
g
in
to
ac
co
u
n
t th
e
weig
h
ted
v
o
tes o
f
th
e
k
-
NN
s.
d.
T
o
Op
tim
ize
th
e
tr
ai
n
in
g
u
s
in
g
“
B
ip
o
lar
s
ig
m
o
id
r
ec
tifie
d
lin
ea
r
u
n
its
(
R
eL
U)
f
u
n
ctio
n
”
th
a
t
co
m
b
in
es
tr
aits
f
r
o
m
d
i
f
f
er
en
t a
ctiv
ati
o
n
f
u
n
ct
io
n
s
2.
M
E
T
HOD
Fig
u
r
e
1
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
class
if
y
in
g
E
E
G
s
ig
n
als
u
s
in
g
b
ased
o
n
s
tatis
tica
l
d
en
o
is
in
g
an
d
m
o
d
if
ied
k
-
NN
a
l
g
o
r
i
t
h
m
wi
t
h
b
i
p
o
l
a
r
s
i
g
m
o
i
d
R
eL
U
f
u
n
c
ti
o
n
.
T
h
e
r
a
w
t
r
a
i
n
i
n
g
E
E
G
d
at
a
is
p
r
e
p
r
o
c
e
s
s
e
d
t
o
s
m
o
o
t
h
e
n
t
h
e
ar
t
i
f
a
c
ts
i
n
o
r
d
e
r
t
o
o
b
t
a
i
n
n
o
is
e
-
f
r
e
e
E
E
G
d
a
ta
.
T
h
e
li
k
e
l
i
h
o
o
d
t
e
s
t
r
a
ti
o
is
a
p
p
l
i
e
d
i
n
t
h
e
b
l
o
c
k
t
h
a
t
c
o
m
p
u
t
es
i
n
t
er
f
e
r
e
n
c
e
a
n
d
s
e
p
a
r
a
t
es
t
h
e
E
E
G
d
a
t
a
i
n
t
o
d
is
c
r
e
te
p
o
r
t
i
o
n
s
wi
t
h
n
e
a
r
l
y
c
o
n
s
is
te
n
t
n
o
i
s
e
c
h
a
r
a
ct
e
r
is
t
ic
s
.
F
u
r
t
h
e
r
,
th
e
f
i
l
t
e
r
e
d
E
E
G
d
at
a
is
s
u
b
j
e
cte
d
t
o
m
o
d
i
f
i
e
d
k
-
NN
b
l
o
c
k
t
o
e
x
t
r
a
c
t
t
h
e
f
e
a
t
u
r
es
a
n
d
t
h
e
s
e
f
e
a
t
u
r
e
s
a
r
e
a
p
p
l
i
e
d
t
o
b
i
p
o
l
a
r
s
i
g
m
o
i
d
R
e
L
U
f
u
n
ct
i
o
n
t
h
a
t
c
o
m
b
i
n
e
s
t
r
a
it
s
f
r
o
m
d
i
f
f
e
r
e
n
t
a
c
t
i
v
a
ti
o
n
f
u
n
c
t
i
o
n
s
t
o
l
i
m
i
t
t
h
e
r
a
n
g
e
o
f
s
a
m
p
l
e
v
a
l
u
e
s
a
n
d
c
o
m
p
a
r
e
d
w
it
h
t
e
s
t
d
a
t
a
b
as
e
t
o
o
b
tain
th
e
ac
cu
r
ac
y
.
2
.
1
.
Da
t
a
ba
s
e
T
h
e
d
ataset
[
1
7
]
co
m
p
r
is
es
o
f
5
d
if
f
er
e
n
t
f
o
l
d
er
s
,
ea
ch
f
o
ld
er
is
h
av
in
g
1
0
0
f
iles
,
ea
ch
f
ile
r
ep
r
esen
ts
a
s
in
g
le
s
u
b
ject/p
er
s
o
n
.
E
ac
h
f
ile
h
as 2
3
.
6
s
d
u
r
atio
n
,
ca
p
tu
r
e
d
b
y
th
e
i
n
ter
n
atio
n
al
1
0
–
2
0
el
ec
tr
o
d
e
p
lace
m
en
t
s
ch
em
e.
T
h
er
e
a
r
e
4
,
0
9
7
d
ata
p
o
in
ts
in
th
e
co
r
r
esp
o
n
d
in
g
ti
m
e
s
er
ies.
E
ac
h
d
ata
p
o
i
n
t
is
th
e
v
alu
e
o
f
th
e
E
E
G
r
ec
o
r
d
in
g
at
a
d
if
f
er
en
t tim
e
p
o
in
t.
2
.
2
.
Deno
is
ing
Dy
n
am
ic
in
ter
f
er
en
ce
[
1
8
]
ca
n
r
esu
lt
f
r
o
m
n
o
is
e,
d
is
to
r
tio
n
s
,
elec
tr
o
m
ag
n
etic
in
ter
f
er
en
c
e,
an
d
o
th
er
u
n
d
esire
d
s
ig
n
als
in
ter
f
er
i
n
g
with
a
s
ig
n
al'
s
tr
an
s
m
is
s
io
n
o
r
r
ec
ep
tio
n
.
Utilizin
g
s
ig
n
al
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
an
d
co
m
p
r
eh
e
n
d
in
g
th
e
in
ter
f
er
en
ce
'
s
p
r
o
p
er
ties
ar
e
u
s
u
ally
n
ec
ess
ar
y
f
o
r
ca
lcu
latin
g
o
r
m
in
im
izin
g
d
y
n
am
ic
in
ter
f
er
en
ce
.
Sev
er
al
m
eth
o
d
s
f
o
r
c
o
n
tr
o
llin
g
o
r
esti
m
atin
g
d
y
n
am
ic
in
te
r
f
er
en
ce
in
clu
d
e:
S
ig
n
al
f
ilter
in
g
is
th
e
p
r
o
ce
s
s
o
f
r
em
o
v
i
n
g
n
o
is
e
o
r
u
n
d
esira
b
le
f
r
eq
u
e
n
cies
f
r
o
m
a
s
ig
n
al
b
y
u
s
in
g
f
ilter
s
.
Dep
e
n
d
in
g
o
n
t
h
e
ty
p
e
o
f
in
ter
f
er
en
ce
,
th
is
m
ay
in
clu
d
e
th
e
u
s
e
o
f
lo
w
-
p
ass
,
h
ig
h
-
p
ass
,
b
an
d
-
p
ass
,
o
r
n
o
tch
f
ilter
s
.
Usi
n
g
m
eth
o
d
s
th
at
ca
n
ad
ju
s
t
to
ch
a
n
g
in
g
in
ter
f
er
en
ce
s
itu
atio
n
s
is
k
n
o
wn
as
ad
ap
tiv
e
s
ig
n
al
p
r
o
ce
s
s
in
g
.
Ad
ap
tiv
e
f
ilter
s
,
f
o
r
ex
am
p
le,
h
av
e
th
e
a
b
ilit
y
t
o
co
n
tin
u
o
u
s
ly
m
o
d
if
y
th
eir
p
a
r
am
eter
s
in
o
r
d
er
to
m
in
im
iz
e
in
ter
f
er
en
ce
in
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
cl
a
s
s
ifica
tio
n
tech
n
iq
u
e
…
(
Th
ej
a
s
w
in
i B
ek
ka
la
le
Ma
h
a
lin
g
e
g
o
w
d
a
)
2789
ch
an
g
in
g
en
v
ir
o
n
m
en
t.
E
s
tim
atin
g
in
ter
f
er
e
n
ce
o
r
n
o
is
e
ch
ar
ac
ter
is
tics
an
d
co
m
in
g
u
p
with
m
itig
atio
n
o
r
r
em
o
v
al
s
tr
ateg
ies ar
e
k
n
o
wn
as n
o
is
e
esti
m
atio
n
an
d
r
em
o
v
al.
T
h
is
co
u
l
d
en
tail sp
ec
tr
al
o
r
s
tatis
tical
an
aly
s
is
to
lo
ca
te
an
d
r
em
o
v
e
u
n
d
esire
d
elem
en
ts
.
T
h
e
ar
tifa
cts
in
E
E
G
s
ig
n
als
ar
e
id
en
tifie
d
b
y
m
ea
n
s
o
f
a
d
y
n
am
ic
in
ter
f
er
en
ce
ca
lc
u
latio
n
tech
n
i
q
u
e.
T
h
is
tech
n
iq
u
e
u
s
es
a
u
n
i
q
u
e
s
tr
ateg
y
d
ev
elo
p
ed
f
r
o
m
th
e
m
o
d
i
f
ied
r
o
b
u
s
t
s
u
b
s
p
ac
e
d
etec
tio
n
m
eth
o
d
to
ex
am
i
n
e
in
te
r
f
er
en
ce
s
in
t
h
e
lear
n
e
d
s
u
b
s
p
ac
e.
T
h
e
p
r
ev
io
u
s
ly
c
o
m
p
u
te
d
u
n
k
n
o
wn
in
te
r
f
er
en
ce
s
ca
n
s
u
b
s
eq
u
en
tly
b
e
u
s
ed
to
id
en
tify
th
e
r
ea
l
in
ter
f
er
en
ce
s
.
E
x
a
m
i
n
e
th
e
E
E
G
s
ig
n
al,
wh
ich
m
ay
b
e
m
ath
em
atica
lly
r
ep
r
esen
ted
as f
o
llo
ws an
d
is
m
ad
e
u
p
o
f
E
E
G
d
ata
an
d
s
o
m
e
u
n
k
n
o
wn
n
o
is
e:
=
+
+
(
1
)
h
er
e
is
th
e
E
E
G
d
ata
b
e
f
o
r
e
n
o
is
e,
x
u
is
i
n
ter
f
er
en
ce
in
ter
m
s
o
f
ar
tifa
cts,
an
d
is
th
e
n
o
is
e
in
ter
f
er
en
ce
lev
el.
As
s
h
o
wn
in
(
1
)
s
p
ec
if
ies
th
e
r
eg
io
n
t
h
at
h
o
ld
s
th
e
c
o
m
p
lete
E
E
G
s
ig
n
al.
T
o
o
f
f
er
ex
ac
t
in
t
er
f
er
en
ce
,
a
s
u
b
s
p
ac
e
c
o
m
p
u
tatio
n
tec
h
n
i
q
u
e
is
u
s
ed
.
L
et
b
e
t
h
e
s
u
b
s
p
a
ce
f
o
r
d
ata
esti
m
atio
n
.
I
n
o
r
d
e
r
to
d
eter
m
in
e
th
e
en
tire
s
u
b
s
p
ac
e,
as
s
h
o
wn
in
(
1
)
is
t
h
er
ef
o
r
e
c
h
an
g
e
d
as
f
o
llo
ws:
a
K
v
ec
t
o
r
a
n
d
an
M
-
s
u
b
s
p
ac
e,
o
r
wid
e
d
im
en
s
io
n
al
s
ig
n
al,
ar
e
u
s
ed
.
=
+
+
(
2
)
w
h
er
e
is
th
e
u
n
ex
p
ec
ted
n
o
is
e
g
ain
,
is
am
p
litu
d
e
o
f
n
o
is
e,
a
n
d
is
n
o
is
e
p
h
ase.
As s
h
o
wn
in
(
2
)
'
s
lik
elih
o
o
d
r
atio
test
[
1
9
]
p
r
o
d
u
ce
s
th
e
f
o
ll
o
win
g
as th
e
eq
u
atio
n
f
o
r
lo
g
y
ield
s
:
(
)
=
(
1
1
‖
−
‖
2
)
2
+
(
1
0
‖
−
‖
2
)
2
(
3
)
Ap
p
ly
in
g
th
e
lik
elih
o
o
d
r
atio
test
to
(
2
)
u
s
in
g
(
3
)
r
esu
lts
in
th
e
d
iv
is
io
n
o
f
th
e
en
tire
d
ata
s
ig
n
al
o
f
E
E
G
in
to
in
cr
ed
ib
ly
s
m
all
s
eg
m
e
n
ts
with
n
ea
r
ly
co
n
s
tan
t
n
o
is
e
ch
ar
ac
ter
is
tics
.
E
f
f
ec
tiv
e
s
ig
n
al
d
en
o
is
in
g
will
b
e
m
ad
e
p
o
s
s
ib
le
b
y
th
is
,
as it w
ill b
e
s
im
p
ler
to
tr
ac
k
th
e
r
ele
v
an
t n
o
is
es th
at
ar
e
p
r
esen
t f
o
r
lim
ited
p
er
io
d
s
o
f
tim
e.
Fig
u
r
e
1
.
Pro
p
o
s
ed
m
et
h
o
d
o
lo
g
y
2
.
3
.
M
o
dified
k
-
NN
a
l
g
o
rit
h
m
2
.
3
.
1
.
E
x
is
t
ing
k
-
NN
I
n
m
ac
h
in
e
lear
n
in
g
,
t
h
e
k
-
NN
alg
o
r
ith
m
[
2
0
]
is
a
s
tr
aig
h
tf
o
r
war
d
an
d
ef
f
icien
t
m
eth
o
d
f
o
r
b
o
th
class
if
icatio
n
an
d
r
eg
r
ess
io
n
p
r
o
b
lem
s
.
I
t
i
s
a
k
in
d
o
f
n
o
n
-
p
ar
am
etr
ic,
in
s
tan
ce
-
b
ased
lea
r
n
in
g
in
wh
ich
th
e
m
o
d
el
f
o
r
ec
asts
a
g
iv
en
d
ata
p
o
in
t
b
y
co
n
s
id
er
in
g
its
clo
s
est
n
eig
h
b
o
r
s
.
T
h
e
ex
is
tin
g
k
-
NN
s
elec
ts
th
e
s
tan
d
ar
d
s
et
o
f
f
ea
tu
r
es u
s
in
g
d
ef
in
ed
r
ad
iu
s
wh
er
e
th
er
e
is
a
p
r
o
b
a
b
ilit
y
o
f
s
elec
tin
g
n
o
n
p
r
o
m
in
e
n
t f
ea
tu
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
2
7
8
6
-
2
7
9
5
2790
2
.
3
.
2
.
M
o
dified
k
-
NN
W
h
ile
k
-
NN
is
v
er
y
ea
s
y
to
im
p
lem
en
t,
it
ca
n
b
e
co
m
p
u
tatio
n
ally
ex
p
en
s
iv
e
f
o
r
lar
g
e
d
atas
ets.
T
o
g
et
o
p
tim
al
p
er
f
o
r
m
an
ce
,
it
is
cr
u
c
ial
to
s
elec
t
th
e
ap
p
r
o
p
r
iate
'
K'
an
d
p
r
o
p
er
ly
p
r
ep
r
o
ce
s
s
th
e
in
p
u
t.
A
d
ata
p
o
in
t'
s
class
lab
el
is
as
s
ig
n
ed
b
y
th
e
s
tan
d
ar
d
k
-
NN
tech
n
iq
u
e
b
a
s
ed
o
n
th
e
f
ea
tu
r
e
s
p
ac
e'
s
k
n
ea
r
est
n
eig
h
b
o
r
s
’
m
ajo
r
ity
class
.
T
h
e
f
o
llo
win
g
p
r
o
p
er
ties
ar
e
in
clu
d
ed
i
n
th
i
s
im
p
r
o
v
e
d
k
-
NN
al
g
o
r
ith
m
:
i)
weig
h
ted
v
o
tin
g
:
T
h
is
m
eth
o
d
u
s
es
weig
h
ts
b
ase
d
o
n
d
is
tan
ce
s
to
ass
ig
n
a
class
lab
el,
f
a
v
o
r
in
g
n
ei
g
h
b
o
r
s
wh
o
ar
e
clo
s
er
t
o
g
eth
er
an
d
ii)
ef
f
ec
tiv
e
p
r
e
d
ictio
n
:
th
e
p
r
ed
ictio
n
f
u
n
ctio
n
ch
o
o
s
es th
e
class
lab
el
b
ased
o
n
th
e
h
i
g
h
est
weig
h
ted
v
o
te
af
ter
tak
in
g
in
t
o
ac
c
o
u
n
t
th
e
weig
h
ted
v
o
tes
o
f
th
e
k
-
NN
s.
T
o
ex
p
e
r
im
en
t
with
th
e
alg
o
r
ith
m
,
ad
ju
s
t
t
h
e
d
is
tan
ce
ca
lcu
latio
n
ap
p
r
o
ac
h
b
ased
o
n
th
e
p
ar
ticu
lar
p
r
o
b
lem
d
o
m
ain
o
r
d
ev
elo
p
u
n
iq
u
e
d
is
tan
ce
m
e
asu
r
es.
Dep
en
d
in
g
o
n
th
e
s
p
ec
if
icatio
n
s
o
f
y
o
u
r
a
s
s
ig
n
m
en
t,
ch
an
g
e
th
e
v
al
u
e
o
f
k
a
n
d
th
e
s
elec
ted
d
is
tan
ce
m
ea
s
u
r
e.
Fo
r
b
o
th
th
e
tr
ain
in
g
a
n
d
test
d
ata
s
ets,
th
e
d
ata'
s
f
ea
tu
r
es m
u
s
t b
e
r
etr
ie
v
ed
an
d
class
if
ied
.
Nex
t,
t
h
e
ca
t
eg
o
r
ies wh
er
e
m
o
s
t
o
f
th
e
K
d
ata
m
atch
ed
wer
e
r
e
m
o
v
ed
,
as we
r
e
th
e
k
-
NN
d
ata
f
r
o
m
th
e
test
s
et.
L
astl
y
,
th
e
d
ata
th
at
n
ee
d
s
t
o
b
e
class
if
ied
is
ar
r
an
g
ed
u
s
in
g
th
i
s
ca
teg
o
r
y
.
Usi
n
g
th
e
k
-
NN
class
if
icatio
n
tech
n
iq
u
e,
s
ev
er
al
s
am
p
les
in
S1
,
S2
,
S3
,
an
d
s
o
o
n
a
r
e
ca
teg
o
r
ize
d
.
Her
e,
th
e
tr
ain
in
g
s
am
p
les
ar
e
s
elec
ted
as
p
ar
ts
o
f
N,
a
n
d
th
eir
s
elec
tio
n
is
co
n
tin
g
en
t
u
p
o
n
o
u
r
n
ee
d
s
.
W
e
n
o
w
n
ee
d
to
u
s
e
K
d
is
tan
ce
to
lo
ca
te
s
am
p
les
th
at
ar
e
clo
s
e
b
y
.
T
h
is
h
elp
s
to
in
cr
ea
s
e
tr
ain
in
g
s
p
ee
d
a
n
d
f
u
r
th
er
r
estricts
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
u
s
ed
.
T
h
e
d
is
cr
i
m
in
an
t
f
u
n
ctio
n
is
(
)
=
,
=
1,
2,
...,
,
an
d
(
)
=
(
)
d
eter
m
in
es th
e
class
if
icatio
n
ca
teg
o
r
y
f
o
r
s
am
p
le
X.
T
h
e
m
o
d
if
ied
k
-
NN
class
if
icatio
n
alg
o
r
ith
m
'
s
(
)
im
p
lem
en
tatio
n
p
r
o
ce
d
u
r
es
ar
e
as f
o
llo
ws:
First,
th
e
tr
ain
in
g
an
d
test
s
am
p
les
ar
e
cr
ea
ted
u
s
in
g
th
e
d
ataset.
W
e
ca
n
p
r
esu
m
e
t
h
at
A
is
th
e
test
s
am
p
le
an
d
X
is
th
e
tr
ain
in
g
s
am
p
le.
W
ith
in
s
am
p
le
S,
th
e
tr
ain
in
g
s
am
p
le
d
ata
s
et
ca
n
b
e
ca
teg
o
r
ized
in
t
o
=
1
,
2,
.
.
.
,
.
Ass
ig
n
th
e
in
itial
k
v
alu
e
t
o
X's
clo
s
est
n
eig
h
b
o
r
in
t
h
e
s
e
co
n
d
s
tep
.
Me
asu
r
e
t
h
e
s
ep
ar
atio
n
b
etwe
en
ea
ch
tr
ain
in
g
s
am
p
le
p
o
in
t a
n
d
th
e
t
est s
am
p
le
p
o
in
t in
th
e
th
ir
d
p
h
ase.
(
)
=
∑
(
x
i
−
w
p
)
2
=
1
(
4
)
T
h
e
d
is
tan
ce
was so
r
ted
in
asc
en
d
in
g
o
r
d
e
r
,
an
d
th
e
ap
p
r
o
p
r
i
ate
k
v
alu
e
was selec
ted
in
th
e
f
o
u
r
th
s
tag
e.
Select
th
e
k
s
am
p
les
th
at
ar
e
m
o
s
t
s
im
ilar
to
th
e
s
elec
ted
s
am
p
le
u
s
in
g
th
r
esh
o
ld
i
n
g
i
n
f
if
t
h
s
tag
e.
T
h
e
co
u
n
tin
g
o
f
K
k
n
o
wn
s
am
p
les
with
th
e
h
ig
h
est
p
r
o
b
ab
ilit
y
with
in
th
e
ca
teg
o
r
y
is
t
h
e
s
ix
t
h
s
tep
.
So
r
t
th
e
test
s
am
p
le
p
o
in
ts
i
n
to
th
e
r
elev
a
n
t
g
r
o
u
p
b
y
ap
p
ly
in
g
th
e
s
tatis
tics
f
r
o
m
s
tep
s
ix
.
Fin
ally
,
S
o
r
t
th
e
test
s
am
p
le
p
o
in
ts
in
to
th
e
r
elev
an
t g
r
o
u
p
b
y
ap
p
l
y
in
g
t
h
e
s
tatis
tics
f
r
o
m
s
tep
s
ix
.
2
.
4
.
B
ipo
la
r
s
ig
mo
id
R
e
L
U
f
un
ct
io
n
I
t
s
ee
m
s
th
at
th
e
p
h
r
ase
“
b
ip
o
lar
s
ig
m
o
id
R
eL
U
f
u
n
ctio
n
”
[
2
1
]
c
o
m
b
in
es
tr
aits
f
r
o
m
d
if
f
er
en
t
ac
tiv
atio
n
f
u
n
ctio
n
s
.
A
s
ig
m
o
i
d
f
u
n
ctio
n
,
w
h
ich
is
b
ip
o
lar
,
c
o
n
v
er
ts
an
y
in
p
u
t
v
alu
e
in
to
a
v
alu
e
b
etwe
en
0
an
d
1
.
I
n
co
n
tr
ast,
a
b
ip
o
lar
s
ig
m
o
id
m
ap
s
v
alu
es
b
etwe
en
-
1
an
d
1
.
T
h
e
ex
p
r
ess
io
n
f
o
r
th
e
r
eg
u
lar
s
ig
m
o
i
d
f
u
n
ctio
n
is
(
5
)
.
(
)
=
1
1
+
−
(
5
)
W
h
ile
a
b
ip
o
lar
s
ig
m
o
id
f
u
n
cti
o
n
m
ay
b
e
d
e
f
in
ed
as
(
6
)
.
(
)
=
2
1
+
−
−
1
(
6
)
T
h
is
f
u
n
ctio
n
t
r
an
s
f
o
r
m
s
th
e
in
p
u
t in
to
th
e
r
an
g
e
[
-
1
,
1
]
.
W
h
en
a
p
o
s
itiv
e
in
p
u
t
is
r
ec
ei
v
ed
,
th
e
R
eL
U
ac
tiv
atio
n
f
u
n
c
tio
n
r
etu
r
n
s
th
e
in
p
u
t
v
alu
e;
o
t
h
er
wis
e,
it
r
etu
r
n
s
0
.
I
t is ab
le
to
b
e
s
tated
as
(
7
)
(
)
=
(
0
,
)
(
7
)
A
c
u
s
t
o
m
i
z
e
d
a
c
t
i
v
at
i
o
n
f
u
n
c
tio
n
t
h
a
t
c
o
m
b
i
n
es
t
h
e
s
e
tw
o
f
u
n
c
t
i
o
n
s
c
a
l
l
e
d
as
h
y
b
r
i
d
f
u
n
c
t
io
n
t
h
a
t
u
s
e
s
v
a
r
i
o
u
s
p
o
r
t
i
o
n
s
o
f
e
ac
h
f
u
n
c
t
i
o
n
i
n
p
ar
t
i
c
u
l
a
r
r
a
n
g
es
i
s
u
s
e
d
i
n
o
u
r
wo
r
k
.
F
o
r
e
x
a
m
p
l
e
,
y
o
u
c
o
u
l
d
u
s
e
a
b
i
p
o
l
a
r
s
i
g
m
o
i
d
f
o
r
n
e
g
a
t
i
v
e
v
a
l
u
e
s
a
n
d
t
h
e
R
eL
U
f
u
n
c
t
i
o
n
f
o
r
p
o
s
i
t
i
v
e
v
a
l
u
es.
T
h
i
s
h
e
l
p
s
t
o
l
i
m
it
t
h
e
s
i
g
n
a
l
in
a
p
a
r
t
i
c
u
l
a
r
r
a
n
g
e
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
en
tire
f
lo
w
was sim
u
lated
u
s
in
g
t
h
e
MA
T
L
AB
s
o
f
twar
e
[
2
2
]
a
n
d
t
h
e
Kag
g
le
E
E
G
d
at
ab
ase
f
r
o
m
th
e
s
tu
d
y
[
1
7
]
wer
e
u
s
ed
to
v
al
id
ate
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
in
ter
m
s
o
f
ac
c
u
r
ac
y
an
d
s
en
s
itiv
ity
.
T
h
e
r
esu
lts
o
b
tain
ed
wer
e
u
s
ed
to
m
ea
s
u
r
e
th
e
p
er
f
o
r
m
an
ce
v
ar
io
u
s
p
er
f
o
r
m
an
ce
p
ar
am
eter
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
cl
a
s
s
ifica
tio
n
tech
n
iq
u
e
…
(
Th
ej
a
s
w
in
i B
ek
ka
la
le
Ma
h
a
lin
g
e
g
o
w
d
a
)
2791
3
.
1
.
RO
C
g
ra
ph
T
h
e
Fig
u
r
e
2
d
is
p
lay
s
th
e
r
ec
ei
v
er
o
p
er
atin
g
ch
ar
a
cter
is
tic
(
R
OC
)
cu
r
v
e
t
h
at
was
o
b
tain
ed
.
T
h
e
g
r
ap
h
s
o
f
th
e
n
o
is
eless
d
ata
cu
r
r
en
tly
av
ailab
le
in
th
e
E
E
G
d
atab
ase
f
o
r
a
r
an
d
o
m
p
er
s
o
n
a
n
d
th
e
n
o
is
y
E
E
G
d
at
a
s
m
o
o
th
ed
b
y
o
u
r
s
u
g
g
ested
m
eth
o
d
ar
e
alm
o
s
t
id
en
tical
an
d
o
v
er
lap
,
p
r
o
v
in
g
th
e
ac
c
u
r
ac
y
o
f
th
e
d
en
o
is
in
g
.
T
h
e
s
im
ilar
ity
o
f
th
e
R
OC
cu
r
v
e
s
u
g
g
ests
th
at
th
e
E
E
G
d
ata
ap
p
ea
r
s
n
ea
r
ly
id
en
tical
to
th
e
o
r
ig
in
al
d
ata
p
r
io
r
to
n
o
is
e
in
ter
f
er
en
ce
.
Fu
r
th
er
,
th
e
f
alse
p
o
s
itiv
e
r
ate
g
r
ap
h
is
p
lo
tted
as
s
h
o
wn
in
Fig
u
r
e
3
to
s
h
o
w
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
is
p
r
o
n
e
to
l
ess
m
is
m
atch
co
m
p
ar
ed
to
e
x
i
s
tin
g
m
eth
o
d
.
Fig
u
r
e
2
.
C
o
m
p
a
r
is
o
n
in
ter
m
s
o
f
R
OC
Gr
ap
h
Fig
u
r
e
3
.
Fals
e
p
o
s
itiv
e
r
ates g
r
ap
h
3
.
2
.
P
e
a
k si
g
na
l
-
to
-
no
is
e
ra
t
io
ca
lcula
t
io
n
T
h
e
av
er
a
g
e
p
ea
k
s
ig
n
al
-
to
-
n
o
is
e
r
atio
(
PS
NR
)
ca
lcu
latio
n
s
ar
e
d
o
n
e
f
o
r
r
an
d
o
m
s
am
p
les
t
ak
en
f
r
o
m
Kag
g
le
ep
ilep
tic
d
ataset
with
1
0
%
o
f
Gau
s
s
ian
n
o
is
e
a
n
d
im
p
u
ls
e
n
o
is
e,
as
s
h
o
wn
in
T
a
b
le
1
.
I
t
is
o
b
s
er
v
ed
th
at
th
e
r
esu
lts
o
f
PS
NR
ar
e
h
i
g
h
in
d
icatin
g
t
h
e
q
u
ality
o
f
f
ilt
er
in
g
.
T
h
e
Ga
u
s
s
ian
an
d
im
p
u
ls
e
f
ilter
b
o
th
h
av
e
alm
o
s
t sam
e
av
er
ag
e
PS
NR
v
alu
es.
T
ab
le
1
.
PS
NR
Valu
es
S
a
mp
l
e
s
P
S
N
R
V
a
l
u
e
(
d
B
)
(
G
a
u
ssi
a
n
n
o
i
s
e
)
P
S
N
R
V
a
l
u
e
(
d
B
)
(
I
mp
u
l
s
e
n
o
i
se)
S
a
mp
l
e
1
7
2
.
1
5
7
2
.
8
5
S
a
mp
l
e
2
7
1
.
2
5
7
1
.
6
5
S
a
mp
l
e
3
7
1
.
1
4
7
1
.
7
5
S
a
mp
l
e
4
7
1
.
2
1
7
1
.
3
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
2
7
8
6
-
2
7
9
5
2792
3
.
3
.
Co
m
pa
riso
n
o
f
P
SNR
v
a
lues
T
h
e
ac
cu
r
ac
y
o
f
th
e
two
tec
h
n
iq
u
es
is
co
m
p
ar
ed
in
T
ab
le
2
,
an
d
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
is
s
h
o
wn
to
b
e
s
u
p
e
r
io
r
i
n
PS
NR
v
ale
as
we
u
s
e
lik
elih
o
o
d
d
etec
to
r
tes
t
to
lim
it
th
e
ef
f
ec
t
o
f
ar
tifa
cts
p
r
esen
t
in
th
e
E
E
G
s
ig
n
al.
T
ab
le
3
s
h
o
ws
c
o
n
f
u
s
io
n
m
atr
i
x
o
b
tain
ed
f
o
r
test
in
g
ep
ilep
tic
s
u
b
jects.
T
h
e
c
o
n
f
u
s
io
n
m
atr
ix
ex
ac
tly
p
r
o
v
id
es
th
e
d
etailed
in
f
o
r
m
ati
o
n
r
eg
ar
d
in
g
tr
u
e
p
o
s
itiv
e
(
T
P),
f
alse
p
o
s
itiv
e
(
FP
)
,
f
alse
n
eg
ativ
e
(
FN)
an
d
tr
u
e
n
eg
ativ
e
(
T
N)
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
p
r
o
p
o
s
ed
an
d
ex
is
tin
g
m
et
h
o
d
i
n
ter
m
s
o
f
PS
NR
A
u
t
h
o
r
Te
c
h
n
i
q
u
e
P
S
N
R
(
d
b
)
[
2
3
]
A
d
a
p
t
i
v
e
f
i
l
t
e
r
s
4
6
.
6
P
r
o
p
o
se
d
M
a
t
h
e
ma
t
i
c
a
l
M
o
d
e
l
71
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
ix
A
c
t
u
a
l
V
a
l
u
e
s
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
P
r
e
d
i
c
t
e
d
V
a
l
u
e
s
P
o
si
t
i
v
e
(
P
)
(
TP)
30
(FP)
4
N
e
g
a
t
i
v
e
(
N
)
(FN)
3
(
TN
)
9
T
h
e
ac
cu
r
ac
y
o
f
p
r
o
p
o
s
ed
tech
n
iq
u
e
with
ex
is
tin
g
tech
n
iq
u
es
is
s
h
o
wn
in
T
ab
le
4
,
an
d
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
is
s
h
o
wn
to
b
e
b
etter
.
I
t
is
o
b
s
er
v
ed
th
at
we
ar
e
g
ettin
g
b
etter
r
esu
lts
co
m
p
ar
ed
to
ex
is
tin
g
wo
r
k
s
an
d
also
with
o
u
r
o
wn
w
o
r
k
[
2
4
]
wh
er
e
we
im
p
r
o
v
ed
th
e
k
-
NN
m
o
d
if
icatio
n
b
y
co
n
s
id
er
in
g
:
a.
T
h
e
u
s
e
o
f
s
tatis
tical
b
ased
ap
p
r
o
ac
h
f
o
r
d
en
o
is
in
g
an
d
to
r
e
d
u
ce
t
h
e
ef
f
ec
t
o
f
a
r
tifa
cts
in
th
e
E
E
G
s
ig
n
al
by
lik
elih
o
o
d
r
atio
test
.
b.
T
h
e
u
s
e
o
f
weig
h
ted
v
o
tin
g
in
k
-
NN
:
T
h
is
m
eth
o
d
u
s
es
weig
h
ts
b
ased
o
n
d
is
tan
ce
s
to
ass
ig
n
a
class
lab
el,
f
av
o
r
in
g
n
eig
h
b
o
r
s
wh
o
ar
e
cl
o
s
er
to
g
eth
er
.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
in
ter
m
s
o
f
ac
cu
r
ac
y
S
e
r
i
a
l
N
o
.
D
i
sea
s
e
t
y
p
e
A
c
c
u
r
a
c
y
(
%)
[
2
5
]
M
a
x
i
m
u
m
mar
g
i
n
a
l
a
p
p
r
o
a
c
h
(
K
a
g
g
l
e
d
a
t
a
se
t
)
86
[
2
6
]
M
o
d
i
f
i
e
d
K
o
h
o
n
e
n
n
e
u
r
a
l
n
e
t
w
o
r
k
I
I
(
S
e
l
f
b
u
i
l
t
d
a
t
a
se
t
)
86
[
2
4
]
M
o
d
i
f
i
e
d
k
-
NN
K
M
e
a
n
s
+
S
V
M
(
B
C
I
d
a
t
a
s
e
t
)
8
0
.
8
1
P
r
o
p
o
se
d
S
t
a
t
i
st
i
c
a
l
d
e
n
o
i
s
i
n
g
+
M
o
d
i
f
i
e
d
k
-
NN
+
b
i
p
o
l
a
r
s
i
g
mo
i
d
R
e
LU
(
K
a
g
g
l
e
d
a
t
a
set
)
8
4
.
7
8
T
h
e
s
en
s
itiv
ity
f
ac
to
r
o
f
p
r
o
p
o
s
ed
tech
n
i
q
u
e
with
e
x
is
tin
g
tech
n
iq
u
es
is
s
h
o
wn
in
T
a
b
le
5
.
I
t
is
o
b
s
er
v
ed
th
at
we
ar
e
g
ettin
g
b
etter
r
esu
lts
co
m
p
ar
ed
to
ex
is
tin
g
wo
r
k
s
[
2
7
]
–
[
2
9
]
wh
e
r
e
we
im
p
r
o
v
e
d
th
e
k
-
NN
m
o
d
if
icatio
n
b
y
co
n
s
id
er
in
g
:
a.
T
h
e
u
s
e
o
f
m
o
d
if
ied
p
r
e
d
ictio
n
f
u
n
ctio
n
in
k
-
NN
wh
ich
ch
o
o
s
es
th
e
class
lab
el
b
ased
o
n
t
h
e
h
i
g
h
est
weig
h
ted
v
o
te
a
f
ter
tak
in
g
in
to
ac
co
u
n
t th
e
weig
h
ted
v
o
tes o
f
th
e
k
-
NN
s
; a
n
d
b.
T
o
Op
tim
ize
th
e
tr
ain
in
g
u
s
i
n
g
“
b
ip
o
lar
s
ig
m
o
id
R
eL
U
f
u
n
ctio
n
”
th
at
c
o
m
b
in
es
tr
aits
f
r
o
m
d
if
f
er
e
n
t
ac
tiv
atio
n
f
u
n
cti
o
n
s
B
y
co
m
p
ar
in
g
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
with
ex
is
tin
g
r
ef
er
en
c
e
wo
r
k
s
it
is
clea
r
er
th
at
th
e
r
em
o
v
al
o
f
ar
tifa
cts
b
y
lik
elih
o
o
d
r
atio
t
est
an
d
m
o
d
if
ied
k
-
NN
to
ex
tr
ac
t
th
e
s
elec
tiv
e
u
n
iq
u
e
f
ea
tu
r
es
im
p
r
o
v
e
d
th
e
ac
cu
r
ac
y
o
f
p
r
o
p
er
d
iag
n
o
s
is
.
Fu
r
th
er
th
e
s
ig
m
o
id
R
eL
U
f
u
n
ctio
n
lim
ited
th
e
n
u
m
b
er
o
f
tr
ain
in
g
f
ea
tu
r
es
to
im
p
r
o
v
e
t
h
e
s
p
ee
d
o
f
tr
ain
in
g
.
T
ab
le
5
.
C
o
m
p
a
r
is
o
n
in
ter
m
s
o
f
s
en
s
itiv
ity
S
l
.
N
o
.
D
i
sea
s
e
T
y
p
e
S
e
n
s
i
t
i
v
i
t
y
(
%)
[
2
7
]
W
a
v
e
l
e
t
+
C
N
N
(
M
I
T,
M
S
S
N
)
8
7
.
8
[
2
8
]
[
2
8
]
[
2
9
]
[
2
9
]
P
r
o
p
o
se
d
S
h
o
r
t
t
i
me
F
o
u
r
i
e
r
t
r
a
n
sf
o
r
m
C
N
N
(
M
I
T,
1
3
p
a
t
i
e
n
t
s)
S
h
o
r
t
t
i
me
F
o
u
r
i
e
r
t
r
a
n
sf
o
r
m
C
N
N
(
K
a
g
g
l
e
,
7
p
a
t
i
e
n
t
s)
M
O
D
W
T
w
i
t
h
1
D
-
C
N
N
(
C
H
B
-
M
I
T,
2
3
P
a
t
i
e
n
t
s)
M
O
D
W
T
w
i
t
h
1
D
-
C
N
N
(
K
a
g
g
l
e
)
S
t
a
t
i
st
i
c
a
l
d
e
n
o
i
s
i
n
g
+
M
o
d
i
f
i
e
d
k
-
NN
+
b
i
p
o
l
a
r
s
i
g
mo
i
d
Re
LU
(
K
a
g
g
l
e
d
a
t
a
set
)
8
1
.
2
75
82
85
9
0
.
9
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
cl
a
s
s
ifica
tio
n
tech
n
iq
u
e
…
(
Th
ej
a
s
w
in
i B
ek
ka
la
le
Ma
h
a
lin
g
e
g
o
w
d
a
)
2793
4.
CO
NCLU
SI
O
N
T
h
e
Statis
tical
d
en
o
is
in
g
,
m
o
d
if
ied
k
-
NN
alg
o
r
ith
m
a
n
d
b
ip
o
lar
s
ig
m
o
id
R
e
LU
f
u
n
ctio
n
ar
e
co
m
b
in
e
d
in
th
is
p
ap
er
to
cr
ea
te
an
ef
f
ec
t
iv
e
ap
p
r
o
ac
h
f
o
r
class
if
y
in
g
E
E
G
s
ig
n
als
f
o
r
co
r
r
ec
t
d
is
ea
s
e
id
en
tific
atio
n
.
Af
ter
ap
p
ly
in
g
s
tatis
tical
tech
n
iq
u
es
to
d
en
o
is
e
th
e
E
E
G
d
ata,
a
m
o
d
if
ied
k
-
NN
alg
o
r
ith
m
is
u
s
ed
to
class
if
y
th
e
r
elev
an
t
f
ea
tu
r
es
wh
er
e
n
eig
h
b
o
r
s
wh
o
ar
e
clo
s
er
to
o
n
e
an
o
th
er
ar
e
g
iv
en
p
r
ef
er
e
n
ce
,
an
d
th
e
weig
h
ted
v
o
tes
o
f
th
e
k
-
n
ea
r
est
n
eig
h
b
o
r
s
ar
e
tak
en
in
to
co
n
s
id
er
ati
o
n
.
Fin
al
ly
,
th
e
class
lab
el
with
th
e
h
ig
h
est
weig
h
ted
v
o
te
is
ch
o
s
en
an
d
to
o
p
tim
ize
th
e
tr
ain
in
g
“
b
i
p
o
lar
s
ig
m
o
id
R
eL
U
f
u
n
ctio
n
”
th
at
co
m
b
in
es
tr
aits
f
r
o
m
d
if
f
er
en
t
ac
tiv
atio
n
f
u
n
ctio
n
s
is
u
s
ed
.
T
h
e
ef
f
icien
cy
o
f
th
e
s
u
g
g
ested
alg
o
r
ith
m
is
d
em
o
n
s
tr
ated
with
a
class
if
icat
io
n
ac
cu
r
ac
y
a
n
d
s
en
s
itiv
ity
test
,
wh
er
e
th
e
d
etec
tio
n
ac
cu
r
ac
y
o
f
tr
u
e
p
o
s
itiv
e
(
T
P),
f
alse
p
o
s
itiv
e
(
FP
)
,
f
alse
n
eg
ativ
e
(
FN)
,
an
d
tr
u
e
n
eg
a
tiv
e
(
T
N)
is
test
ed
an
d
co
m
p
ar
ed
to
th
e
d
etec
tio
n
ac
cu
r
ac
y
o
f
o
t
h
er
ex
is
tin
g
alg
o
r
ith
m
s
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
s
p
ec
ially
th
an
k
R
esear
ch
C
en
ter
,
C
MR Un
iv
er
s
ity
f
o
r
th
e
s
u
p
p
o
r
t to
o
u
r
r
esea
r
ch
wo
r
k
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
d
id
n
o
t r
ec
eiv
e
s
u
p
p
o
r
t f
r
o
m
a
n
y
o
r
g
an
izatio
n
f
o
r
th
e
s
u
b
m
itted
wo
r
k
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
ejaswin
i
B
ek
k
alale
Ma
h
alin
g
eg
o
wd
a
d
ev
elo
p
ed
th
e
i
d
ea
an
d
p
er
f
o
r
m
e
d
th
e
m
e
th
o
d
o
lo
g
y
co
m
p
u
tatio
n
s
.
Glan
Dev
a
d
h
as
Geo
r
g
e
p
er
f
o
r
m
e
d
th
e
f
o
r
m
al
an
aly
s
is
,
in
v
esti
g
ated
an
d
v
er
if
ied
th
e
an
aly
tical
m
eth
o
d
s
.
Sath
ee
s
h
a
T
u
m
ak
u
r
Yo
g
a
an
d
Kaliy
am
o
o
r
th
y
E
z
h
i
lar
asan
en
co
u
r
ag
ed
t
o
in
v
esti
g
ate
an
d
s
u
p
e
r
v
is
ed
th
e
f
in
d
in
g
s
o
f
th
is
wo
r
k
.
All
au
th
o
r
s
d
is
cu
s
s
ed
th
e
r
esu
lts
an
d
co
n
t
r
ib
u
ted
t
o
th
e
f
i
n
al
m
a
n
u
s
cr
ip
t.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
T
h
ejaswin
i Bek
k
alale
Ma
h
alin
g
eg
o
wd
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
Glan
Dev
ad
h
as Ge
o
r
g
e
✓
✓
✓
✓
✓
✓
Sath
ee
s
h
a
T
u
m
ak
u
r
Yo
g
a
✓
✓
✓
✓
✓
Kaliy
am
o
o
r
th
y
E
zh
ilar
asan
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
h
av
e
n
o
c
o
n
f
lict
s
o
f
in
ter
est
to
d
ec
lar
e.
All
co
-
au
th
o
r
s
h
av
e
s
ee
n
a
n
d
a
g
r
e
e
with
th
e
co
n
ten
ts
o
f
th
e
m
an
u
s
cr
ip
t.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
au
th
o
r
s
co
n
f
ir
m
th
at
th
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
with
in
th
e
ar
ticle
[
an
d
/o
r
]
its
s
u
p
p
lem
en
tar
y
m
a
ter
ials
.
RE
F
E
R
E
NC
E
S
[
1
]
C
.
X
u
a
n
d
R
.
-
Z
.
X
i
a
,
“
E
EG
s
i
g
n
a
l
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
:
A
r
e
v
i
e
w
,
”
i
n
2
0
2
3
2
nd
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Bi
g
D
a
t
a
,
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r
N
e
t
w
o
rk
(
BD
I
C
N
)
,
Ja
n
.
2
0
2
3
,
p
p
.
1
8
6
–
1
8
9
,
d
o
i
:
1
0
.
1
1
0
9
/
B
D
I
C
N
5
8
4
9
3
.
2
0
2
3
.
0
0
0
4
6
.
[
2
]
S
.
K
.
Y
a
d
a
v
a
n
d
V
.
S
.
,
“
EEG
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
sem
i
su
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
T
re
n
d
i
n
S
c
i
e
n
t
i
f
i
c
R
e
se
a
rc
h
a
n
d
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
3
,
p
p
.
1
4
4
1
–
1
4
4
5
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
3
1
1
4
2
/
i
j
t
sr
d
2
3
3
5
5
.
[
3
]
J.
R
a
b
c
a
n
,
V
.
L
e
v
a
s
h
e
n
k
o
,
E.
Z
a
i
t
se
v
a
,
a
n
d
M
.
K
v
a
ssa
y
,
“
R
e
v
i
e
w
o
f
m
e
t
h
o
d
s
f
o
r
EEG
s
i
g
n
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
d
e
v
e
l
o
p
m
e
n
t
o
f
n
e
w
f
u
z
z
y
c
l
a
ssi
f
i
c
a
t
i
o
n
-
b
a
se
d
a
p
p
r
o
a
c
h
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
8
9
7
2
0
–
1
8
9
7
3
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
3
1
4
4
7
.
[
4
]
S
.
R
o
y
,
U
.
A
s
i
f
,
J
.
T
a
n
g
,
a
n
d
S
.
H
a
r
r
e
r
,
“
S
e
i
z
u
r
e
t
y
p
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
E
E
G
si
g
n
a
l
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
:
S
e
t
t
i
n
g
a
b
e
n
c
h
mark
,
”
i
n
2
0
2
0
I
EEE
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
i
n
M
e
d
i
c
i
n
e
a
n
d
Bi
o
l
o
g
y
S
y
m
p
o
si
u
m
(
S
PM
B)
,
D
e
c
.
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
2
7
8
6
-
2
7
9
5
2794
1
0
.
1
1
0
9
/
S
P
M
B
5
0
0
8
5
.
2
0
2
0
.
9
3
5
3
6
4
2
.
[
5
]
R
.
V
i
s
h
w
a
k
a
r
ma
,
H
.
K
h
w
a
j
a
,
V
.
S
a
m
a
n
t
,
P
.
G
a
u
d
e
,
M
.
G
a
mb
h
i
r
,
a
n
d
S
.
A
sw
a
l
e
,
“
EEG
si
g
n
a
l
s
a
n
a
l
y
si
s
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
B
C
I
sy
st
e
ms:
A
r
e
v
i
e
w
,
”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Em
e
r
g
i
n
g
T
r
e
n
d
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
En
g
i
n
e
e
ri
n
g
(
i
c
-
ETI
T
E)
,
F
e
b
.
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
-
E
TI
TE4
7
9
0
3
.
2
0
2
0
.
0
6
6
.
[
6
]
E.
M
.
K
a
me
l
,
Y
.
M
.
M
a
ss
o
u
d
,
M
.
A
.
El
G
h
a
n
y
,
a
n
d
M
.
A
.
-
M
.
S
a
l
e
m,
“
E
EG
c
l
a
ssi
f
i
c
a
t
i
o
n
f
o
r
s
e
i
z
u
r
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
S
V
M
v
s
d
e
e
p
ANN,
”
i
n
2
0
2
1
T
e
n
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
(
I
C
I
C
I
S
)
,
D
e
c
.
2
0
2
1
,
p
p
.
3
8
9
–
395
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
I
S
5
2
5
9
2
.
2
0
2
1
.
9
6
9
4
1
4
9
.
[
7
]
S
.
S
u
g
a
n
y
a
d
e
v
i
,
S
.
S
h
a
n
m
u
g
a
P
r
i
y
a
,
B
.
K
i
r
u
b
a
,
M
.
G
o
m
a
t
h
i
,
a
n
d
J.
N
.
K
a
l
sh
e
t
t
y
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
EEG
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
a
l
g
o
r
i
t
h
ms
,
”
i
n
2
0
2
2
I
EE
E
2
nd
M
y
s
o
re
S
u
b
S
e
c
t
i
o
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
(
M
y
s
u
ru
C
o
n
)
,
O
c
t
.
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
M
y
s
u
r
u
C
o
n
5
5
7
1
4
.
2
0
2
2
.
9
9
7
2
3
6
4
.
[
8
]
G
.
C
h
a
n
d
e
l
,
S
.
K
.
S
a
i
n
i
,
a
n
d
A
.
S
h
a
r
ma,
“
Ep
i
l
e
p
t
i
c
EEG
s
i
g
n
a
l
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
mo
d
e
l
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
D
i
sru
p
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s (I
C
D
T
)
,
M
a
y
2
0
2
3
,
p
p
.
7
3
3
–
7
3
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
T5
7
9
2
9
.
2
0
2
3
.
1
0
1
5
0
7
9
3
.
[
9
]
B
.
W
a
n
g
,
F
.
W
a
n
,
P
.
U
.
M
a
k
,
P
.
I
.
M
a
k
,
a
n
d
M
.
I
.
V
a
i
,
“
EEG
si
g
n
a
l
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
b
r
a
i
n
c
o
m
p
u
t
e
r
i
n
t
e
r
f
a
c
e
s
b
a
se
d
o
n
G
a
u
ss
i
a
n
p
r
o
c
e
ss
c
l
a
ssi
f
i
e
r
,
”
i
n
2
0
0
9
7
th
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
,
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
(
I
C
I
C
S
)
,
D
e
c
.
2
0
0
9
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
S
.
2
0
0
9
.
5
3
9
7
5
7
0
.
[
1
0
]
T.
W
u
,
X
.
K
o
n
g
,
Y
.
W
a
n
g
,
X
.
Y
a
n
g
,
J.
Li
u
,
a
n
d
J.
Q
i
,
“
A
u
t
o
m
a
t
i
c
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
EEG
s
i
g
n
a
l
s v
i
a
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
1
I
EEE
19
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
d
u
st
ri
a
l
I
n
f
o
rm
a
t
i
c
s (I
N
D
I
N
)
,
J
u
l
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
D
I
N
4
5
5
2
3
.
2
0
2
1
.
9
5
5
7
4
7
3
.
[
1
1
]
Z.
Li
,
“
E
l
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
p
h
y
s
i
g
n
a
l
a
n
a
l
y
si
s
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
0
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
,
C
o
m
p
u
t
e
r
T
e
c
h
n
o
l
o
g
y
a
n
d
T
ra
n
s
p
o
r
t
a
t
i
o
n
(
I
S
C
T
T
)
,
N
o
v
.
2
0
2
0
,
p
p
.
1
1
9
–
1
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
TT5
1
5
9
5
.
2
0
2
0
.
0
0
0
2
9
.
[
1
2
]
A
.
G
.
La
z
c
a
n
o
-
H
e
r
r
e
r
a
,
R
.
Q
.
F
u
e
n
t
e
s
-
A
g
u
i
l
a
r
,
a
n
d
M
.
A
l
f
a
r
o
-
P
o
n
c
e
,
“
EEG
mo
t
o
r
/
i
ma
g
e
r
y
s
i
g
n
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
c
o
mp
a
r
a
t
i
v
e
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
i
n
2
0
2
1
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
C
o
m
p
u
t
i
n
g
S
c
i
e
n
c
e
a
n
d
A
u
t
o
m
a
t
i
c
C
o
n
t
r
o
l
(
C
C
E)
,
N
o
v
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
C
E
5
3
5
2
7
.
2
0
2
1
.
9
6
3
3
0
5
5
.
[
1
3
]
D
.
A
c
h
a
r
y
a
,
R
.
A
h
me
d
S
a
y
y
a
d
,
P
.
D
w
i
v
e
d
i
,
A
.
S
h
a
j
i
,
P
.
S
r
i
r
a
m
,
a
n
d
A
.
B
h
a
r
d
w
a
j
,
“
EEG
si
g
n
a
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
S
o
f
t
C
o
m
p
u
t
i
n
g
f
o
r
Pr
o
b
l
e
m
S
o
l
v
i
n
g
,
2
0
2
1
,
p
p
.
3
9
3
–
4
0
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
2
7
0
9
-
5
_
3
0
.
[
1
4
]
S
.
B
e
h
e
r
a
a
n
d
M
.
N
.
M
o
h
a
n
t
y
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
E
EG
si
g
n
a
l
u
si
n
g
S
V
M
,
”
i
n
A
d
v
a
n
c
e
s
i
n
El
e
c
t
ri
c
a
l
C
o
n
t
r
o
l
a
n
d
S
i
g
n
a
l
S
y
st
e
m
s
,
2
0
2
0
,
p
p
.
8
5
9
–
8
6
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
15
-
5
2
6
2
-
5
_
6
5
.
[
1
5
]
G
.
C
h
e
k
h
m
a
n
e
a
n
d
R
.
B
e
n
a
l
i
,
“
EE
G
si
g
n
a
l
s
a
n
a
l
y
si
s
u
s
i
n
g
S
V
M
a
n
d
M
L
P
N
N
c
l
a
s
s
i
f
i
e
r
s
f
o
r
e
p
i
l
e
p
sy
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
2
2
5
th
I
n
t
e
rn
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
I
n
f
o
r
m
a
t
i
c
s
a
n
d
i
t
s
Ap
p
l
i
c
a
t
i
o
n
s
(
I
S
I
A
)
,
N
o
v
.
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
I
A
5
5
8
2
6
.
2
0
2
2
.
9
9
9
3
5
7
7
.
[
1
6
]
H.
-
T.
-
T.
V
o
,
L
.
-
N.
-
T.
D
a
n
g
,
V
.
-
T.
-
N
.
N
g
u
y
e
n
,
a
n
d
V
.
-
T
.
H
u
y
n
h
,
“
A
s
u
r
v
e
y
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms i
n
E
EG
,
”
i
n
2
0
1
9
6
t
h
N
AFO
S
T
ED
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
N
I
C
S
)
,
D
e
c
.
2
0
1
9
,
p
p
.
5
0
0
–
505
,
d
o
i
:
1
0
.
1
1
0
9
/
N
I
C
S
4
8
8
6
8
.
2
0
1
9
.
9
0
2
3
8
8
4
.
[
1
7
]
V
.
A
d
i
t
y
a
,
“
E
p
i
l
e
p
t
i
c
s
e
i
z
u
r
e
s
d
a
t
a
se
t
,
”
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
set
s
/
c
h
a
d
i
t
y
a
9
5
/
e
p
i
l
e
p
t
i
c
-
s
e
i
z
u
r
e
s
-
d
a
t
a
s
e
t
,
2
0
1
8
(
a
c
c
e
sse
d
J
u
n
2
8
,
2
0
2
4
)
.
[
1
8
]
O
.
S
a
ss
i
,
P
.
H
e
r
v
e
,
a
n
d
B
.
W
i
l
l
m
a
n
n
,
“
C
a
l
c
u
l
a
t
i
o
n
a
p
p
r
o
a
c
h
o
f
si
g
n
a
l
t
o
i
n
t
e
r
f
e
r
e
n
c
e
a
n
d
p
a
c
k
e
t
e
r
r
o
r
r
a
t
e
e
s
t
i
m
a
t
i
o
n
:
A
p
p
l
i
c
a
t
i
o
n
t
o
a
u
t
o
m
o
t
i
v
e
sc
e
n
a
r
i
o
s,
”
i
n
2
0
1
9
I
EEE
1
9
th
M
e
d
i
t
e
rra
n
e
a
n
M
i
c
r
o
w
a
v
e
S
y
m
p
o
si
u
m
(
MM
S
)
,
O
c
t
.
2
0
1
9
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
M
M
S
4
8
0
4
0
.
2
0
1
9
.
9
1
5
7
3
1
0
.
[
1
9
]
L.
H
u
a
n
g
,
J.
Za
l
k
i
k
a
r
,
a
n
d
R
.
C
.
T
i
w
a
r
i
,
“
L
i
k
e
l
i
h
o
o
d
r
a
t
i
o
t
e
s
t
-
b
a
se
d
m
e
t
h
o
d
f
o
r
s
i
g
n
a
l
d
e
t
e
c
t
i
o
n
i
n
d
r
u
g
c
l
a
sses
u
si
n
g
F
D
A
’
s
A
ER
S
d
a
t
a
b
a
s
e
,
”
J
o
u
r
n
a
l
o
f
Bi
o
p
h
a
rm
a
c
e
u
t
i
c
a
l
S
t
a
t
i
s
t
i
c
s
,
v
o
l
.
2
3
,
n
o
.
1
,
p
p
.
1
7
8
–
2
0
0
,
J
a
n
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
5
4
3
4
0
6
.
2
0
1
3
.
7
3
6
8
1
0
.
[
2
0
]
U
.
I
.
A
w
a
n
,
U
.
H
.
R
a
j
p
u
t
,
G
.
S
y
e
d
,
R
.
I
q
b
a
l
,
I
.
S
a
b
a
t
,
a
n
d
M
.
M
a
n
so
o
r
,
“
Ef
f
e
c
t
i
v
e
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
E
EG
si
g
n
a
l
s
u
si
n
g
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
a
l
g
o
r
i
t
h
m,
”
i
n
2
0
1
6
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Fr
o
n
t
i
e
rs
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
FI
T
)
,
D
e
c
.
2
0
1
6
,
p
p
.
1
2
0
–
1
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
F
I
T.
2
0
1
6
.
0
3
0
.
[
2
1
]
M
.
A
.
M
e
r
c
i
o
n
i
,
A
.
M
.
T
a
t
,
a
n
d
S
.
H
o
l
b
a
n
,
“
I
mp
r
o
v
i
n
g
t
h
e
a
c
c
u
r
a
c
y
o
f
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
t
h
r
o
u
g
h
d
e
v
e
l
o
p
i
n
g
n
e
w
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s,
”
i
n
2
0
2
0
I
EEE
1
6
th
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
e
r
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
Pro
c
e
ss
i
n
g
(
I
C
C
P)
,
S
e
p
.
2
0
2
0
,
p
p
.
3
8
5
–
391
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
P
5
1
0
2
9
.
2
0
2
0
.
9
2
6
6
1
6
2
.
[
2
2
]
“
M
a
t
h
W
o
r
k
s.
”
h
t
t
p
s
:
/
/
w
w
w
.
ma
t
h
w
o
r
k
s
.
c
o
m/
c
o
n
t
e
n
t
/
d
a
m/
m
a
t
h
w
o
r
k
s/
m
a
t
h
w
o
r
k
s
-
d
o
t
-
c
o
m/
c
a
m
p
a
i
g
n
s
/
p
o
r
t
a
l
s
/
f
i
l
e
s/
i
n
t
e
l
/
ma
y
-
12
-
2
0
1
5
-
a
d
v
a
n
c
e
d
-
ma
t
l
a
b
.
p
d
f
(
a
c
c
e
ss
e
d
M
a
y
1
2
,
2
0
1
5
)
.
[
2
3
]
R
.
A
n
a
n
y
a
,
S
.
I
sh
a
a
sam
y
u
k
t
h
a
,
V
.
H
a
r
i
ma
n
i
,
M
.
V
e
e
z
h
i
n
a
t
h
a
n
,
B
.
G
e
e
t
h
a
n
j
a
l
i
,
a
n
d
B
.
R
a
j
e
n
d
r
a
n
,
“
P
r
o
c
e
ss
i
n
g
o
f
EEG
si
g
n
a
l
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
e
p
i
l
e
p
sy
,
”
i
n
2
0
2
0
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
(
I
C
C
S
P)
,
J
u
l
.
2
0
2
0
,
p
p
.
1
5
3
2
–
1
5
3
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
S
P
4
8
5
6
8
.
2
0
2
0
.
9
1
8
2
2
7
1
.
[
2
4
]
B
.
M
.
Th
e
j
a
sw
i
n
i
,
T.
Y
.
S
a
t
h
e
e
s
h
a
,
a
n
d
S
.
B
h
a
i
r
a
n
n
a
w
a
r
,
“
EEG
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
m
o
d
i
f
i
e
d
K
N
N
a
l
g
o
r
i
t
h
m,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
p
p
l
i
e
d
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
u
s
t
a
i
n
a
b
l
e
C
o
m
p
u
t
i
n
g
(
I
C
AI
S
C
)
,
J
u
n
.
2
0
2
3
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
S
C
5
8
4
4
5
.
2
0
2
3
.
1
0
2
0
0
1
0
4
.
[
2
5
]
G
.
Li
a
n
d
J.
J.
Ju
n
g
,
“
M
a
x
i
m
u
m
m
a
r
g
i
n
a
l
a
p
p
r
o
a
c
h
o
n
EEG
si
g
n
a
l
p
r
e
p
r
o
c
e
s
si
n
g
f
o
r
e
m
o
t
i
o
n
d
e
t
e
c
t
i
o
n
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
2
1
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
2
1
7
6
7
7
.
[
2
6
]
D
.
J.
H
e
ma
n
t
h
,
“
EEG
s
i
g
n
a
l
b
a
s
e
d
m
o
d
i
f
i
e
d
k
o
h
o
n
e
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
h
u
ma
n
me
n
t
a
l
e
m
o
t
i
o
n
s
,
”
J
o
u
r
n
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
y
st
e
m
s
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
1
–
1
3
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
6
9
/
A
I
S
.
2
0
2
0
.
2
1
0
0
1
.
[
2
7
]
H
.
K
h
a
n
,
L.
M
a
r
c
u
s
e
,
M
.
F
i
e
l
d
s
,
K
.
S
w
a
n
n
,
a
n
d
B
.
Y
e
n
e
r
,
“
F
o
c
a
l
o
n
s
e
t
s
e
i
z
u
r
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
s,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
6
5
,
n
o
.
9
,
p
p
.
2
1
0
9
–
2
1
1
8
,
S
e
p
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
T
B
M
E.
2
0
1
7
.
2
7
8
5
4
0
1
.
[
2
8
]
N
.
D
.
Tr
u
o
n
g
e
t
a
l
.
,
“
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
s
f
o
r
s
e
i
z
u
r
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
i
n
t
r
a
c
r
a
n
i
a
l
a
n
d
sc
a
l
p
e
l
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
m,
”
N
e
u
ra
l
N
e
t
w
o
rks
,
v
o
l
.
1
0
5
,
p
p
.
1
0
4
–
1
1
1
,
S
e
p
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
n
e
t
.
2
0
1
8
.
0
4
.
0
1
8
.
[
2
9
]
A
.
I
b
r
a
h
i
m,
H
.
Zh
u
a
n
g
,
E.
T
o
g
n
o
l
i
,
A
.
M
.
A
l
i
,
a
n
d
N
.
Er
d
o
l
,
“
E
p
i
l
e
p
t
i
c
se
i
z
u
r
e
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
mu
l
t
i
r
e
s
o
l
u
t
i
o
n
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
s
.
”
Fro
n
t
i
e
r
s i
n
S
i
g
n
a
l
Pro
c
e
ssi
n
g
,
O
c
t
.
1
1
,
2
0
2
2
,
d
o
i
:
1
0
.
2
1
2
0
3
/
r
s
.
3
.
r
s
-
2
1
2
1
4
9
2
/
v
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
lectro
en
ce
p
h
a
lo
g
r
a
p
h
y
cl
a
s
s
ifica
tio
n
tech
n
iq
u
e
…
(
Th
ej
a
s
w
in
i B
ek
ka
la
le
Ma
h
a
lin
g
e
g
o
w
d
a
)
2795
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Th
e
ja
sw
in
i
Be
k
k
a
la
le
Ma
h
a
li
n
g
e
g
o
wd
a
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
P
h
.
D.
a
t
C
M
R
Un
iv
e
rsity
i
n
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
S
OET
Re
se
a
rc
h
Ce
n
ter.
He
r
re
se
a
rc
h
in
tere
sts
a
r
e
in
th
e
a
re
a
o
f
a
rti
ficia
l
i
n
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
p
a
rti
c
u
larly
in
EE
G
fo
r
e
p
il
e
p
ti
c
se
izu
re
d
e
tec
ti
o
n
.
S
h
e
h
a
s
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
fr
o
m
VTU,
Be
lg
a
u
m
,
a
n
d
m
a
ste
r’s
d
e
g
re
e
fro
m
VTU,
Be
lg
a
u
m
,
a
s
we
ll
.
He
r
two
p
ro
jec
t
p
ro
p
o
sa
ls
h
a
v
e
b
e
e
n
re
c
o
g
n
ize
d
b
y
t
h
e
sta
te
o
f
Ka
rn
a
tak
a
a
s
g
o
o
d
p
r
o
jec
t
i
d
e
a
s.
S
h
e
h
a
s
a
lrea
d
y
p
u
b
li
sh
e
d
o
n
e
p
a
p
e
r
in
a
c
o
n
fe
re
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
t
h
e
jas
win
i.
b
m
g
@g
m
a
il
.
c
o
m
.
G
la
n
De
v
a
d
h
a
s
G
e
o
r
g
e
is
wo
rk
in
g
a
s
d
irec
to
r,
d
irec
to
ra
t
e
o
f
re
se
a
rc
h
a
n
d
in
n
o
v
a
ti
o
n
o
f
C
M
R
Un
iv
e
rsit
y
,
Ba
n
g
a
lo
re
.
He
h
a
s
h
e
ld
v
a
ri
o
u
s
p
o
siti
o
n
s
a
s
Vic
e
P
rin
c
ip
a
l,
P
ro
fe
ss
o
r,
He
a
d
o
f
th
e
De
p
a
rtme
n
t,
B
o
a
rd
o
f
S
tu
d
ies
C
h
a
irma
n
,
Ac
a
d
e
m
ic
Co
u
n
c
il
M
e
m
b
e
r,
a
n
d
Do
c
to
ra
l
Co
m
m
it
tee
M
e
m
b
e
r
in
v
a
rio
u
s
e
n
g
i
n
e
e
rin
g
c
o
l
leg
e
s
a
n
d
u
n
iv
e
rsiti
e
s
a
n
d
h
a
s
2
2
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
.
He
h
a
s
a
u
t
h
o
re
d
a
n
d
c
o
-
a
u
th
o
re
d
7
1
j
o
u
r
n
a
l
p
a
p
e
rs
in
S
CI
,
S
c
o
p
u
s
-
i
n
d
e
x
e
d
j
o
u
r
n
a
ls,
a
n
d
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
p
r
o
c
e
e
d
in
g
s.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
d
rg
lan
.
d
@c
m
r.
e
d
u
.
in
.
S
a
th
e
e
sha
T
u
m
a
k
u
r
Y
o
g
a
is
c
u
rre
n
tl
y
wo
r
k
in
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
th
e
S
c
h
o
o
l
o
f
CS
E
,
REVA
Un
iv
e
rsit
y
.
He
h
a
s
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r’s
a
n
d
m
a
ste
r’s
d
e
g
re
e
s
fr
o
m
VTU,
Be
lg
a
u
m
,
Ka
rn
a
tak
a
,
I
n
d
ia
.
He
h
a
s
re
c
e
iv
e
d
a
d
o
c
t
o
ra
l
d
e
g
re
e
fro
m
JN
TU
An
a
n
tap
u
r
,
An
d
h
ra
P
ra
d
e
sh
.
In
a
d
d
it
io
n
,
h
e
h
a
s
se
c
u
re
d
a
n
h
o
n
o
ra
ry
d
e
g
re
e
o
f
D.
Tec
h
.
,
s
p
e
c
ializin
g
i
n
sig
n
a
l
p
ro
c
e
ss
in
g
,
fr
o
m
Ca
li
fo
r
n
ia
P
u
b
li
c
Un
i
v
e
rsity
.
P
re
se
n
tl
y
,
h
e
is
p
u
rsu
i
n
g
a
P
DF
a
t
UN
IF
ACV
ES
T
Un
iv
e
rsit
y
Ce
n
tr
a
l,
Lag
e
s,
Bra
z
il
,
S
o
u
th
Am
e
rica
,
v
irt
u
a
ll
y
in
th
e
field
o
f
b
io
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ty
.
sa
ti
s
h
@g
m
a
il
.
c
o
m
.
K
a
li
y
a
m
o
o
r
th
y
Ez
h
il
a
r
a
sa
n
h
a
s
re
c
e
iv
e
d
h
is
B.
E
.
i
n
ECE
fr
o
m
M
a
n
o
n
m
a
n
ia
m
S
u
n
d
a
ra
n
a
r
Un
iv
e
rsit
y
,
Tam
il
Na
d
u
,
M
.
Tec
h
.
i
n
VLS
I
fr
o
m
S
a
th
y
a
b
a
m
a
Un
iv
e
rsity
,
Ch
e
n
n
a
i,
a
n
d
P
h
.
D.
fr
o
m
Ja
in
Un
i
v
e
rsity
,
Be
n
g
a
l
u
ru
.
He
h
a
s
1
9
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
i
n
g
a
n
d
re
se
a
rc
h
wo
rk
,
a
n
d
h
is
a
re
a
o
f
i
n
t
e
re
st
is
in
ima
g
e
p
ro
c
e
ss
in
g
,
sig
n
a
l
p
ro
c
e
ss
in
g
,
a
n
d
VLS
I
.
He
is
th
e
e
x
-
He
a
d
o
f
th
e
De
p
a
rtme
n
t
in
th
e
De
p
a
rtme
n
t
o
f
ECE
a
t
CM
R
Un
iv
e
rsity
,
Ba
n
g
a
l
o
re
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
u
ra
li
9
8
1
9
8
3
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.