I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
25
,
No
.
2
,
Feb
r
u
ar
y
20
22
,
p
p
.
8
8
4
~
8
91
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
25
.i
2
.
pp
884
-
8
9
1
884
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Epileptic
seizure
cla
ss
ificatio
n of
el
ectr
o
ence
pha
lo
g
ra
m
sig
na
ls
using
extreme gra
dient
bo
o
sting
c
la
ss
ifier
M
illee
P
a
nig
ra
hi
1
,
Da
y
a
l K
um
a
r
B
eher
a
2
,
K
rish
na
Cha
nd
ra
P
a
t
ra
3
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s
,
S
a
mb
a
l
p
u
r
U
n
i
v
e
r
si
t
y
I
n
st
i
t
u
t
e
o
f
I
n
f
o
r
m
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
B
h
u
b
a
n
e
sw
a
r
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
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
,
S
i
l
i
c
o
n
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
B
h
u
b
a
n
e
sw
a
r
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s
,
S
a
mb
a
l
p
u
r
U
n
i
v
e
r
si
t
y
,
S
a
m
b
a
l
p
u
r
,
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
Au
g
2
8
,
2
0
2
1
R
ev
is
ed
No
v
3
0
,
2
0
2
1
Acc
ep
ted
Dec
9
,
2
0
2
1
Ep
il
e
p
s
y
c
a
u
se
s
re
p
e
a
ted
se
izu
re
s
in
a
n
in
d
iv
id
u
a
l'
s
li
fe
,
wh
ich
c
a
u
se
s
tran
sie
n
t
irreg
u
lariti
e
s
in
th
e
b
ra
i
n
'
s
e
lec
tri
c
a
l
a
c
ti
v
it
y
.
It
re
su
lt
s
i
n
d
iffere
n
t
p
h
y
sic
a
l
sy
m
p
to
m
s
th
a
t
a
re
a
b
n
o
rm
a
l.
Va
rio
u
s
a
n
ti
e
p
i
lep
ti
c
d
r
u
g
s
fa
il
to
m
in
imiz
e
re
p
e
a
ted
p
a
ti
e
n
t
se
izu
re
s.
Th
e
e
lec
tro
e
n
c
e
p
h
a
lo
g
ra
m
(EE
G
)
sig
n
a
l
re
c
o
rd
in
g
s
p
r
o
v
i
d
e
u
s
wit
h
ti
m
e
-
s
e
ries
d
a
ta
se
t
fo
r
e
p
il
e
p
t
ic
se
izu
re
d
e
tec
ti
o
n
a
n
d
a
n
a
ly
sis.
Th
e
se
sig
n
a
ls
a
re
h
ig
h
l
y
n
o
n
li
n
e
a
r
a
n
d
in
c
o
n
siste
n
t
,
a
n
d
t
h
e
y
a
re
re
c
o
rd
e
d
o
v
e
r
t
ime
.
P
re
d
icti
n
g
t
h
e
icta
l
p
e
rio
d
(se
izu
re
p
e
rio
d
a
t
th
e
t
ime
o
f
e
p
i
lep
sy
)
is
t
h
u
s
a
c
h
a
ll
e
n
g
i
n
g
tas
k
i
n
th
e
n
a
k
e
d
e
y
e
f
o
r
th
e
m
e
d
ica
l
p
ra
c
ti
ti
o
n
e
rs.
Va
rio
u
s
m
a
c
h
i
n
e
l
e
a
rn
in
g
tec
h
n
iq
u
e
s
a
re
a
p
p
li
e
d
t
o
i
d
e
n
ti
f
y
th
e
se
izu
re
'
s
o
c
c
u
rre
n
c
e
a
n
d
it
s
c
las
sifica
ti
o
n
in
m
u
lt
ip
le
d
o
m
a
in
s.
A
c
las
sifi
c
a
ti
o
n
m
o
d
e
l
b
a
se
d
o
n
e
x
trem
e
g
ra
d
ien
t
b
o
o
stin
g
(S
C
LXG
B)
is
p
ro
p
o
se
d
h
e
re
fo
r
th
e
c
las
sifica
ti
o
n
o
f
t
h
e
EE
G
sig
n
a
ls.
T
h
e
S
CLX
G
B
m
o
d
e
l
imp
lem
e
n
ts
b
i
n
a
ry
se
izu
re
c
las
sifica
ti
o
n
o
n
th
e
b
e
n
c
h
m
a
r
k
d
a
tas
e
t.
Co
m
p
a
re
d
with
K
-
n
e
a
re
s
t
n
e
ig
h
b
o
r,
li
n
e
a
r
re
g
re
ss
io
n
,
a
n
d
De
c
isio
n
tree
-
b
a
se
d
m
o
d
e
ls,
th
e
p
ro
p
o
se
d
m
o
d
e
l
a
c
h
iev
e
s
t
h
e
b
e
st
a
re
a
u
n
d
e
r
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
u
r
v
e
(AU
C)
o
f
0
.
9
4
6
2
a
n
d
a
n
a
c
c
u
ra
c
y
o
f
9
6
%
wh
ich
sig
n
ifi
e
s
a
c
c
u
ra
te
p
re
d
ictio
n
o
f
se
izu
re
a
n
d
n
o
n
se
izu
re
p
e
ri
o
d
.
T
h
e
p
ro
p
o
se
d
m
o
d
e
l
S
CLXG
B
wa
s
v
a
li
d
a
ted
b
y
tak
in
g
d
iffere
n
t
p
e
rfo
rm
a
n
c
e
m
e
tri
c
s
t
o
i
n
d
ica
te
th
e
o
c
c
u
rre
n
c
e
a
n
d
n
o
n
-
o
c
c
u
rre
n
c
e
o
f
se
izu
re
s
in
p
a
ti
e
n
ts
m
o
re
a
p
p
ro
p
riate
ly
.
K
ey
w
o
r
d
s
:
Dec
is
io
n
tr
ee
E
lectr
o
en
ce
p
h
al
o
g
r
am
E
x
tr
em
e
g
r
a
d
ien
t b
o
o
s
tin
g
Seizu
r
e
class
if
icatio
n
XGBo
o
s
t
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
:
Day
al
Ku
m
ar
B
eh
er
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Sil
ico
n
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
B
h
u
b
an
eswar
,
Od
is
h
a,
I
n
d
ia
E
m
ail:
d
ay
alb
eh
er
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Var
io
u
s
r
ec
o
r
d
in
g
s
y
s
tem
s
ar
e
av
ailab
le
n
o
wa
d
ay
s
to
r
e
co
r
d
th
e
h
u
m
an
b
r
ai
n
s
ig
n
al
in
m
u
ltip
le
f
o
r
m
s
.
T
h
ese
s
ig
n
allin
g
s
y
s
tem
s
h
av
e
m
an
y
ad
v
an
tag
es
an
d
d
is
ad
v
an
tag
es
[
1
]
.
Fo
r
ex
am
p
le,
a
n
elec
tr
o
en
ce
p
h
al
o
g
r
am
(
E
E
G)
is
a
s
ig
n
allin
g
m
eth
o
d
th
a
t
is
m
o
r
e
p
r
o
n
e
t
o
p
r
o
ce
s
s
in
g
s
tep
s
s
u
ch
as
en
h
an
ce
m
e
n
t,
ex
tr
ac
tio
n
o
f
f
e
atu
r
es,
an
d
class
if
icatio
n
f
o
r
ep
ilep
tic
s
eizu
r
e
p
r
ed
ictio
n
.
T
h
er
ef
o
r
e
,
th
e
E
E
G
s
ig
n
als h
av
e
h
ig
h
e
r
tem
p
o
r
al
r
eso
lu
tio
n
an
d
s
af
ety
co
m
p
a
r
ed
to
o
th
er
m
eth
o
d
s
.
E
lectr
o
en
ce
p
h
al
o
g
r
am
(
E
E
G)
r
ec
o
r
d
in
g
is
d
o
n
e
th
r
o
u
g
h
t
h
e
s
tan
d
ar
d
ized
elec
tr
o
d
es
p
l
ac
ed
n
o
n
-
in
v
asiv
ely
o
n
th
e
b
r
ain
'
s
s
ca
lp
.
T
h
e
clin
ical
in
s
p
ec
tio
n
f
o
r
s
eizu
r
e
o
cc
u
r
r
e
n
ce
is
v
is
u
alize
d
b
y
th
e
ce
r
eb
r
u
m
'
s
elec
tr
ical
ac
tio
n
,
wh
ich
co
n
t
ain
s
m
u
ch
d
ata
ab
o
u
t
b
r
ai
n
ac
tiv
ity
[
2
]
.
I
n
th
is
way
,
E
E
G
s
ig
n
als
h
av
e
an
in
cr
ed
ib
le
s
ig
n
if
ica
n
ce
in
b
r
ain
d
iag
n
o
s
is
in
estab
lis
h
in
g
p
r
e
-
esti
m
ated
e
p
ilep
tic
s
eizu
r
e
d
etec
tio
n
[
3
]
.
T
h
e
E
E
G
v
ar
ies
f
r
o
m
a
v
er
ag
e
to
s
p
ik
e,
s
h
ar
p
,
s
p
ik
e
-
a
n
d
-
m
o
d
er
ate
c
o
m
p
lex
wa
v
e,
co
m
p
lex
p
o
in
ted
-
a
n
d
-
m
ed
iu
m
wav
e,
an
d
an
o
th
er
e
p
ilep
tic
f
o
r
m
o
f
s
ig
n
als
[
4
]
.
T
h
u
s
,
E
E
G
r
ec
o
r
d
in
g
s
h
elp
th
e
r
esear
ch
er
s
with
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
p
ilep
tic
s
eizu
r
e
cla
s
s
i
fica
tio
n
o
f
elec
tr
o
en
ce
p
h
a
l
o
g
r
a
m
s
ig
n
a
ls
u
s
in
g
ex
tr
eme
…
(
Mil
lee
P
a
n
ig
r
a
h
i
)
885
g
r
ea
ter
ef
f
icien
cy
a
n
d
less
tim
e
co
n
s
u
m
p
tio
n
f
o
r
a
u
to
m
at
ed
ep
ilep
s
y
d
iag
n
o
s
is
th
an
v
is
u
al
in
s
p
ec
tio
n
o
f
s
eizu
r
es.
L
o
n
g
E
E
G
r
ec
o
r
d
i
n
g
s
ca
n
r
ec
o
g
n
ize
th
e
s
eizu
r
e
p
er
io
d
r
ath
er
th
an
a
s
h
o
r
t
d
u
r
atio
n
o
f
tim
e.
T
h
er
ef
o
r
e,
th
e
lo
n
g
-
ter
m
E
E
G
s
ig
n
als
ca
n
s
ig
n
if
ican
tly
ca
teg
o
r
ize
th
e
in
ter
ictal
an
d
ictal
p
er
io
d
s
.
T
h
e
E
E
G
s
ig
n
al
is
a
lo
n
g
-
ter
m
r
ec
o
r
d
in
g
o
f
th
e
b
r
ain
s
ig
n
al,
s
eg
r
e
g
at
ed
in
to
f
iv
e
d
if
f
er
e
n
t
f
r
eq
u
en
c
y
b
an
d
s
to
p
r
o
p
er
ly
an
aly
ze
s
eizu
r
e
an
d
n
o
n
-
se
izu
r
e
p
atter
n
s
[
5
]
.
T
h
is
n
o
n
-
u
n
if
o
r
m
an
d
n
o
n
-
s
tatio
n
ar
y
s
ig
n
al
is
tim
e
-
d
ep
en
d
en
t
an
d
ch
ar
ac
te
r
ized
b
y
th
e
r
e
p
etitiv
e
h
ig
h
am
p
litu
d
e
an
d
co
m
b
i
n
atio
n
o
f
s
p
ik
e
an
d
s
lo
w
wav
e
s
[
6
]
.
T
h
e
E
E
G
s
ig
n
als
ar
e
h
ig
h
ly
n
o
n
-
s
tatio
n
ar
y
.
T
h
ese
s
ig
n
als
ar
e
an
aly
ze
d
with
f
r
eq
u
en
c
y
,
tim
e,
an
d
tim
e
-
f
r
eq
u
e
n
cy
d
ec
o
m
p
o
s
itio
n
m
eth
o
d
s
in
v
o
lv
in
g
d
is
cr
e
te
wav
elet
tr
an
s
f
o
r
m
,
p
ar
tic
u
lar
ly
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
[
7
]
.
T
h
e
v
is
u
al
f
in
d
in
g
o
f
s
eizu
r
es
is
tim
e
-
co
n
s
u
m
in
g
an
d
ted
io
u
s
to
id
en
tify
t
h
e
ex
ac
t
d
u
r
atio
n
o
f
th
e
p
h
y
s
ician
s
'
ictal
ep
is
o
d
es.
T
h
er
ef
o
r
e,
th
e
r
esear
c
h
er
s
im
p
lem
en
ted
d
if
f
er
en
t
a
u
to
m
ate
d
s
eizu
r
e
p
r
e
d
ictio
n
alg
o
r
ith
m
s
to
en
h
a
n
ce
th
e
p
r
ec
is
e
d
etec
tio
n
o
f
ep
ilep
tic
s
eizu
r
es
f
r
o
m
elec
tr
o
e
n
ce
p
h
al
o
g
r
am
r
ec
o
r
d
in
g
s
.
L
i
et
a
l.
[
8
]
p
r
o
p
o
s
ed
o
th
er
s
o
f
t
co
m
p
u
tin
g
tech
n
iq
u
es
lik
e
g
en
etic
a
lg
o
r
it
h
m
(
GA
)
,
f
u
zz
y
l
o
g
ic
ap
p
r
o
ac
h
es
ar
e
ap
p
lied
to
class
if
y
th
e
ep
i
lep
tic
an
d
n
o
n
-
ep
ilep
tic
E
E
G
s
eg
m
en
ts
.
Du
e
to
th
e
lo
n
g
E
E
G
r
ec
o
r
d
in
g
s
,
th
e
s
ize
r
ed
u
ctio
n
with
o
p
tim
u
m
in
f
o
r
m
atio
n
ab
o
u
t
th
e
ictal
a
ctiv
ity
h
as
b
ee
n
ch
allen
g
i
n
g
f
o
r
th
e
r
esear
ch
er
s
.
T
h
is
p
r
o
b
lem
s
tatem
en
t
r
esu
lt
ed
in
s
elec
tin
g
a
n
d
e
x
tr
ac
tin
g
f
ea
tu
r
es
u
s
in
g
co
m
p
le
x
d
u
al
-
tr
ee
tr
an
s
f
o
r
m
atio
n
with
v
ar
iatio
n
s
in
g
r
an
u
lar
ity
lev
el
[
9
]
.
T
h
e
r
ec
o
r
d
ed
s
ig
n
als
ar
e
f
ea
tu
r
ed
u
s
in
g
t
h
e
wa
v
elet
d
ec
o
m
p
o
s
itio
n
m
eth
o
d
an
d
class
if
ied
u
s
in
g
Naïv
e
B
ay
es
an
d
K
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN
)
cl
ass
if
ier
s
t
o
g
en
er
ate
f
o
u
r
teen
co
m
b
in
atio
n
s
o
f
2
-
class
ep
ilep
s
y
[
1
0
]
.
Du
r
in
g
t
h
e
ictal
an
d
p
r
eicta
l
s
tates,
th
e
am
o
u
n
t
o
f
in
f
o
r
m
atio
n
in
f
lo
w
an
d
o
u
tf
lo
w
b
etwe
en
th
e
b
r
ai
n
'
s
co
r
tical
r
eg
io
n
s
is
co
n
s
id
er
ed
a
p
ar
am
eter
f
o
r
s
eizu
r
e
class
if
icatio
n
[
1
1
]
.
T
h
e
r
e
s
ea
r
ch
im
p
lem
e
n
ted
f
e
atu
r
e
ex
tr
ac
tio
n
a
n
d
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
th
r
o
u
g
h
co
r
r
elatio
n
an
d
r
an
d
o
m
f
o
r
es
t
(
R
F)
f
o
r
s
eizu
r
e
an
d
n
o
n
-
s
eizu
r
e
class
if
icatio
n
[
1
2
]
,
[
1
3
]
.
T
h
e
E
E
G
s
ig
n
als
ar
e
also
h
elp
f
u
l
f
o
r
d
etec
tin
g
o
th
er
b
r
ain
d
is
o
r
d
er
s
lik
e
au
tis
m
,
as illu
s
tr
ated
in
[
1
4
]
,
[
1
5
].
A
m
ac
h
in
e
lear
n
in
g
(
ML
)
ap
p
r
o
ac
h
f
o
r
p
r
ed
ictin
g
th
e
o
n
s
et
o
f
s
eizu
r
es
is
p
r
o
p
o
s
ed
i
n
t
h
is
p
r
esen
t
wo
r
k
.
T
h
e
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
alg
o
r
it
h
m
(
SC
L
XGB)
is
im
p
lem
en
ted
to
esti
m
ate
th
e
d
escr
ip
tiv
e
s
am
p
les
f
r
o
m
a
tr
ain
ed
p
r
e
d
ictiv
e
m
o
d
el.
SC
L
XGB
is
a
s
eizu
r
e
class
if
icatio
n
m
eth
o
d
u
s
in
g
th
e
XGBo
o
s
t
m
o
d
el.
T
h
is
m
eth
o
d
ca
n
co
n
s
id
er
ab
ly
a
p
p
r
o
ac
h
t
h
e
p
a
r
allel
an
d
d
is
tr
ib
u
ted
ca
lc
u
latio
n
to
v
er
if
y
th
e
m
o
d
el'
s
attr
ib
u
tes.
XGBo
o
s
t
lib
r
ar
y
[
1
6
]
is
a
p
r
o
d
u
ctiv
e
an
d
d
is
s
em
in
ated
ap
p
licatio
n
o
f
g
r
ad
ien
t
b
o
o
s
tin
g
[1
7
]
.
I
t
p
r
o
v
i
d
e
s
a
f
a
s
te
r
i
n
t
e
r
p
r
et
a
t
io
n
o
f
t
h
e
m
o
d
e
l
wi
t
h
a
d
e
c
r
e
a
s
e
d
o
v
e
r
f
i
t
t
i
n
g
t
h
a
n
o
t
h
e
r
b
o
o
s
tin
g
a
l
g
o
r
i
t
h
m
s
[
1
8
]
.
T
h
e
s
ig
n
if
ican
t c
o
n
tr
ib
u
tio
n
o
f
th
e
p
ap
er
is
g
iv
en
b
elo
w:
−
Desig
n
o
f
an
e
f
f
icien
t c
lass
if
icatio
n
m
o
d
el
f
o
r
e
p
ilep
tic
s
eizu
r
e
id
en
tific
atio
n
f
r
o
m
E
E
G
s
ig
n
al.
−
E
x
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
is
a
v
ar
ia
n
t
o
f
a
g
r
ad
ien
t
b
o
o
s
tin
g
m
o
d
el
with
ef
f
icien
t
c
o
m
p
u
tatio
n
a
l
f
lex
ib
ilit
y
,
ca
n
elim
in
ate
th
e
p
r
o
b
ab
ilit
y
o
f
m
is
s
in
g
th
e
v
al
u
e
s
.
−
T
h
e
ex
is
tin
g
ex
tr
e
m
e
g
r
a
d
ien
t
b
o
o
s
tin
g
m
o
d
el
is
m
o
d
if
ied
t
o
esti
m
ate
th
e
ea
r
ly
s
to
p
p
in
g
o
f
ep
o
c
h
s
f
o
r
tr
ain
in
g
d
ata
b
y
co
m
p
u
tin
g
th
e
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
v
alu
es
f
o
r
ea
c
h
ep
o
c
h
f
r
o
m
th
e
lo
g
lo
s
s
g
r
ap
h
.
Acc
o
r
d
in
g
l
y
,
t
h
e
p
ar
am
eter
s
ar
e
o
p
tim
ized
.
−
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
is
co
m
p
ar
ed
with
th
e
ex
is
tin
g
class
if
ier
s
an
d
f
o
u
n
d
to
b
e
m
o
r
e
ac
c
u
r
ate
with
less
co
m
p
u
tatio
n
tim
e
f
o
r
p
r
ed
ictin
g
th
e
s
eizu
r
es
.
2.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
D
T
h
e
ep
ilep
tic
s
eizu
r
e
d
ata
s
et
is
tak
en
f
r
o
m
th
e
Un
iv
er
s
ity
o
f
C
alif
o
r
n
ia
at
I
r
v
in
e
(
UC
I
)
m
ac
h
in
e
lear
n
in
g
r
e
p
o
s
ito
r
y
[
1
9
]
wh
ic
h
co
n
s
is
ts
o
f
f
iv
e
s
tates
o
f
p
a
tien
ts
d
ata
s
ets,
ea
ch
with
1
0
0
f
iles
.
E
ac
h
o
f
th
e
1
0
0
f
iles
r
ep
r
esen
ts
a
s
in
g
le
s
u
b
ject'
s
b
r
ain
a
ctiv
ity
r
ec
o
r
d
f
o
r
2
3
.
6
s
ec
o
n
d
s
.
T
h
e
d
ata
is
a
tim
e
-
s
er
ies
s
ig
n
al
an
d
is
s
am
p
led
in
4
0
9
7
d
ata
p
o
in
ts
.
E
ac
h
s
ig
n
al
is
th
en
p
r
o
c
ess
ed
b
y
d
iv
id
in
g
a
n
d
s
h
u
f
f
lin
g
ea
ch
s
et
o
f
4
0
9
7
d
ata
p
o
in
ts
in
t
o
2
3
p
iece
s
[
1
9
]
.
T
h
is
tim
e
s
er
ies
d
ataset
h
as
1
7
8
(
4
0
9
7
/2
3
)
d
ata
p
o
in
ts
f
o
r
1
s
ec
o
n
d
in
ev
er
y
2
3
p
iece
s
.
T
h
e
d
ata
p
o
in
t
r
ep
r
e
s
en
ts
th
e
E
E
G
r
ec
o
r
d
in
g
v
alu
e
o
n
s
ep
ar
ate
tim
e
in
s
tan
ce
s
.
T
h
u
s
a
to
tal
o
f
2
3
x
5
0
0
=1
1
5
0
0
p
iece
s
o
f
in
f
o
r
m
atio
n
co
n
tain
i
n
g
1
7
8
-
d
im
e
n
s
io
n
al
in
p
u
t
v
ec
to
r
s
r
ep
r
esen
ted
f
o
r
1
s
ec
o
n
d
b
y
X1
,
X2
,
X3
.
.
.
.
.
.
X
1
7
8
.
T
h
er
e
ar
e
f
iv
e
p
atien
t statu
s
es r
ep
r
es
en
ted
b
y
y
{1
,
2
,
3
,
4
,
5
}
as in
d
icate
d
[
1
9
]
:
−
E
E
G
R
ec
o
r
d
in
g
o
f
in
s
tan
ce
s
o
f
s
eizu
r
es (
E
S)
.
−
E
E
G
s
ig
n
al
f
r
o
m
b
r
ain
t
u
m
o
u
r
s
ite
(
E
T
B
)
.
−
E
E
G
R
ec
o
r
d
f
r
o
m
a
h
ea
lth
y
ar
ea
o
f
th
e
b
r
ain
(
E
HB
)
.
−
E
E
G
s
ig
n
al
o
f
th
e
h
ea
lth
y
s
u
b
j
e
ct
with
ey
es c
lo
s
ed
(
E
YE
C
)
.
−
E
E
G
s
ig
n
al
o
f
th
e
h
ea
lth
y
s
u
b
j
ec
t w
ith
ey
es o
p
en
(
E
YE
O)
.
T
h
e
s
u
b
jects
in
ca
teg
o
r
ies
2
,
3
,
4
,
5
h
av
e
n
o
ep
ilep
s
y
,
an
d
th
e
s
u
b
ject
in
ca
teg
o
r
y
1
h
as
ep
ilep
s
y
.
T
h
e
d
a
t
a
p
r
o
c
e
s
s
i
n
g
i
s
d
o
n
e
s
u
c
h
t
h
a
t
i
t
is
e
a
s
i
e
r
f
o
r
b
i
n
a
r
y
c
l
a
s
s
i
f
i
c
at
i
o
n
a
g
a
i
n
s
t
t
h
e
r
e
s
t
o
f
t
h
e
c
l
a
s
s
e
s
.
F
i
g
u
r
e
1
r
ep
r
esen
ts
th
e
f
iv
e
s
tates o
f
th
e
s
u
b
jects.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
2
,
Feb
r
u
a
r
y
20
22
:
8
8
4
-
8
9
1
886
Fig
u
r
e
1
.
An
illu
s
tr
atio
n
o
f
E
E
G
r
ec
o
r
d
in
g
s
3.
M
E
T
H
O
D
Fig
u
r
e
2
r
ep
r
esen
ts
th
e
f
lo
w
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
Firstl
y
th
e
b
en
c
h
m
ar
k
d
ataset
is
co
n
s
id
er
ed
f
o
r
class
if
icatio
n
an
d
th
en
d
ata
p
r
ep
r
o
ce
s
s
in
g
is
d
o
n
e
u
s
in
g
f
ilter
in
g
tech
n
i
q
u
e
.
T
h
en
tr
ain
in
g
an
d
test
in
g
d
ataset
is
co
n
s
id
er
ed
p
er
f
o
r
m
in
g
tr
ain
test
s
p
lit
with
7
0
%
tr
ain
d
ata
an
d
3
0
%
test
d
ata.
Af
ter
th
at
th
e
class
if
icatio
n
is
d
o
n
e
u
s
in
g
S
C
L
X
GB
cla
s
s
if
ier
f
o
r
s
eizu
r
e
p
r
ed
ictio
n
.
T
h
e
d
etailed
e
x
p
la
n
atio
n
is
illu
s
tr
ated
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
T
h
e
f
lo
w
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
SC
L
XGB
3
.
1
.
Da
t
a
p
re
pro
ce
s
s
ing
T
h
e
d
ataset
u
s
ed
in
o
u
r
s
tu
d
y
f
o
r
ep
ilep
tic
s
eizu
r
e
d
ete
ctio
n
is
p
u
b
licly
a
v
ailab
le
a
n
d
ea
s
ily
d
o
wn
lo
ad
a
b
le
[
1
9
]
.
T
h
e
E
E
G
r
ec
o
r
d
in
g
s
ar
e
m
u
ltiv
ar
iate
ti
m
e
s
er
ies
s
ig
n
als
s
am
p
led
at
1
7
3
.
6
1
Hz
h
av
i
n
g
a
s
p
ec
tr
al
b
an
d
wid
th
o
f
0
.
5
Hz
t
o
8
5
Hz.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
is
d
o
n
e
b
y
ap
p
ly
i
n
g
a
lo
w
p
ass
f
ilter
at
a
f
r
eq
u
e
n
cy
o
f
4
0
Hz;
t
h
e
d
ata
is
d
o
wn
s
am
p
lin
g
is
ca
r
r
ie
d
o
u
t
to
t
u
n
e
wit
h
th
e
class
if
ier
s
.
Fig
u
r
e
1
r
e
p
r
esen
ts
th
e
d
if
f
er
e
n
t
d
ataset
lev
els
r
ep
r
esen
ted
in
t
er
m
s
o
f
v
o
ltag
e
lev
els
c
o
n
ce
r
n
in
g
tim
e.
T
h
e
d
ataset
h
av
in
g
th
e
s
eizu
r
e
class
is
m
ar
k
ed
as
1
,
a
n
d
o
t
h
er
d
atas
ets
ar
e
m
ar
k
ed
as
2
,
3
,
4
,
5
,
r
esp
ec
tiv
ely
,
r
ep
r
esen
tin
g
d
if
f
er
en
t
s
tates
o
f
th
e
s
u
b
jects.
W
e
o
n
ly
co
n
ce
n
tr
ate
o
n
th
e
d
ataset
h
av
in
g
a
s
eizu
r
e
an
d
th
e
tim
e
d
u
r
atio
n
o
f
th
e
o
cc
u
r
r
en
ce
o
f
th
e
s
eizu
r
e
.
3.
2
.
E
x
t
re
m
e
g
r
a
dient
bo
o
s
t
ing
(
SCL
XG
B
)
T
h
e
XGBo
o
s
t
alg
o
r
ith
m
[
1
6
]
i
n
co
r
p
o
r
ates
a
m
o
r
e
r
e
g
u
lar
ize
d
m
o
d
el
to
m
an
ag
e
th
e
o
v
er
f
itti
n
g
o
f
th
e
attr
ib
u
tes
b
y
im
p
lem
en
tin
g
a
p
ar
allel
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
with
a
v
ar
y
in
g
n
u
m
b
er
o
f
ter
m
in
al
n
o
d
es.
T
h
ey
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
p
ilep
tic
s
eizu
r
e
cla
s
s
i
fica
tio
n
o
f
elec
tr
o
en
ce
p
h
a
l
o
g
r
a
m
s
ig
n
a
ls
u
s
in
g
ex
tr
eme
…
(
Mil
lee
P
a
n
ig
r
a
h
i
)
887
co
m
p
r
is
e
an
a
r
r
ay
o
f
s
p
lit
p
o
i
n
ts
an
d
th
e
n
o
d
es
r
ep
r
esen
ted
as
i
n
p
u
t
v
ar
ia
b
les.
Her
e
th
e
la
s
t
n
o
d
e
is
th
e
leaf
o
f
th
e
tr
ee
s
th
at
g
iv
es
th
e
s
p
ec
if
i
c
v
alu
es
o
f
o
u
tp
u
t
v
ar
ia
b
les.
T
h
e
leaf
weig
h
ts
h
av
in
g
less
in
f
o
r
m
atio
n
ab
o
u
t
th
e
o
cc
u
r
r
e
n
ce
o
f
s
eizu
r
es
ar
e
s
h
r
iek
ed
to
r
ed
u
ce
m
o
d
el
co
m
p
lex
ity
.
XGBo
o
s
t
alg
o
r
ith
m
h
as
two
s
ig
n
if
ican
t
u
p
g
r
a
d
atio
n
s
th
an
o
th
er
b
o
o
s
ti
n
g
alg
o
r
ith
m
s
as
:
−
I
t is r
o
b
u
s
t a
n
d
s
p
ee
d
s
u
p
th
e
co
n
s
tr
u
ctio
n
o
f
th
e
tr
ee
.
−
Pro
p
o
s
in
g
a
n
ew
d
is
tr
ib
u
te
d
a
lg
o
r
ith
m
f
o
r
tr
ee
s
ea
r
ch
in
g
a
n
d
ex
tr
a
r
a
n
d
o
m
izatio
n
p
ar
am
e
ter
is
ap
p
lied
to
d
ec
r
ea
s
e
th
e
co
r
r
elatio
n
b
etwe
en
tr
ee
s.
−
XGB
p
r
o
v
id
es
a
m
o
r
e
r
eg
u
lar
ized
s
tr
u
ctu
r
e
to
m
an
ag
e
o
v
er
f
it
an
d
allo
ws
p
ar
allel
p
r
o
ce
s
s
in
g
b
etter
th
an
th
e
g
r
ad
ien
t
b
o
o
s
tin
g
m
o
d
el
.
−
T
h
e
n
o
v
el
co
n
tr
ib
u
tio
n
o
f
th
is
p
ap
er
is
th
at
th
e
p
ar
am
eter
s
ar
e
o
p
tim
ized
to
o
b
tain
h
ig
h
e
r
ac
cu
r
ac
y
with
r
ed
u
ce
d
c
o
m
p
lex
i
ty
o
f
t
h
e
m
o
d
el.
T
h
e
ex
tr
e
m
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t)
alg
o
r
ith
m
[
1
6
]
,
[
2
0
]
was
im
p
lem
en
te
d
u
s
in
g
t
h
e
Scik
it
-
lear
n
[
2
1
]
P
y
th
o
n
m
o
d
u
les.
3.
3
.
M
o
del
d
escript
io
n
T
h
e
E
E
G
s
ig
n
al
class
if
icat
io
n
h
as
b
ec
o
m
e
an
ar
d
u
o
u
s
task
f
o
r
m
ed
ical
p
r
ac
titi
o
n
e
r
s
to
d
etec
t
an
ep
ilep
tic
p
atien
t'
s
s
eizu
r
e
an
d
n
o
n
-
s
eizu
r
e
ac
tiv
ity
[
2
2
]
.
T
h
e
m
ain
id
ea
b
eh
i
n
d
th
is
m
o
d
el
is
to
ca
r
r
y
o
u
t
a
m
o
r
e
a
u
to
m
ated
b
in
ar
y
class
if
icatio
n
o
f
th
e
E
E
G
s
ig
n
al
u
s
in
g
a
s
tate
-
of
-
th
e
-
ar
t
XGBo
o
s
t
lear
n
in
g
m
o
d
el
(
SC
L
XG
B
)
th
at
o
u
t
p
er
f
o
r
m
s
o
th
er
s
eizu
r
e
class
-
d
eter
m
in
atio
n
m
o
d
els.
E
x
tr
em
e
g
r
ad
ien
t b
o
o
s
tin
g
(
XGBo
o
s
t)
[
23
]
is
a
b
r
ea
k
th
r
o
u
g
h
am
o
n
g
en
s
em
b
le
lear
n
in
g
m
o
d
e
ls
th
at
in
co
r
p
o
r
ate
s
ep
a
r
ate
v
ar
iab
les
with
o
u
t
o
v
er
f
itti
n
g
d
ir
ec
tly
an
d
ca
n
h
a
n
d
le
n
o
n
-
lin
ea
r
s
ig
n
als
s
u
c
h
a
s
E
E
G.
Af
t
er
d
ata
p
r
e
p
r
o
ce
s
s
in
g
,
t
h
e
o
v
er
all
s
tep
s
ca
r
r
ied
o
u
t a
r
e
as f
o
llo
ws.
−
T
h
e
tr
ain
in
g
d
ataset
is
7
0
%,
a
n
d
th
e
test
in
g
d
ataset
is
3
0
%.
Ou
t
o
f
1
1
5
0
0
d
ata
p
o
in
ts
,
8
0
5
0
d
ata
p
o
in
ts
ar
e
co
n
s
id
er
ed
f
o
r
th
e
tr
ain
in
g
d
at
a
s
et,
an
d
3
4
5
0
d
ata
ar
e
tak
e
n
f
o
r
test
in
g
.
−
T
est
d
ataset
is
u
s
ed
to
v
alid
ate
th
e
SC
L
XGB m
o
d
el.
−
Valid
ated
m
o
d
el
is
u
s
ed
f
o
r
p
r
ed
ictio
n
Alg
o
r
ith
m
1
:
p
r
o
p
o
s
ed
m
o
d
el
SC
L
XG
B
Input: UCI machine
learning repository
Output:
p
erformance
metrics
and
area under the curve (
AUC
)
1.
Data
prep
rocessing
and generating the feature set.
2.
Normalizing the data using StandardScaler
.
3.
Modeling as a classification problem
.
4.
Train
-
test split
.
5.
Train and tuning the XGBoost Model using all the features
.
6.
Calculating the classification metrics
.
7.
Plot the train and test c
onfusion matrix and ROC
.
Alg
o
r
ith
m
1
r
ep
r
esen
ts
th
e
s
tep
s
f
o
llo
wed
i
n
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
e
tr
ai
n
an
d
test
er
r
o
r
o
f
th
e
S
C
L
X
GB
m
o
d
e
l
i
s
t
r
a
i
n
e
d
w
i
th
d
i
f
f
e
r
e
n
t
e
p
o
c
h
s
a
n
d
t
h
e
c
o
r
r
e
s
p
o
n
d
i
n
g
R
MS
E
v
a
l
u
e
is
r
e
p
r
e
s
e
n
t
e
d
i
n
F
i
g
u
r
e
3
.
T
h
e
s
to
ch
asti
c
n
atu
r
e
o
f
th
e
al
g
o
r
ith
m
is
esti
m
ated
b
y
p
lo
ttin
g
th
e
R
MSE
v
alu
es with
7
0
%
tr
ain
d
ata
an
d
3
0
%
test
d
ata
s
ets
f
o
r
ea
ch
ep
o
c
h
.
I
t
is
o
b
s
er
v
e
d
th
at
af
ter
r
o
u
n
d
4
0
ep
o
c
h
s
th
e
iter
atio
n
s
s
h
o
u
ld
b
e
s
to
p
p
e
d
to
av
o
id
o
v
er
f
itti
n
g
o
f
th
e
t
r
ain
in
g
m
o
d
el.
Fig
u
r
e
3
.
T
h
e
lear
n
in
g
cu
r
v
e
(
l
o
g
lo
s
s
)
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
SC
L
XG
B
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
2
,
Feb
r
u
a
r
y
20
22
:
8
8
4
-
8
9
1
888
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
UC
I
m
ac
h
in
e
lear
n
in
g
r
e
p
o
s
ito
r
y
d
ataset
[
19
]
f
o
r
ep
ile
p
tic
s
eizu
r
e
d
etec
tio
n
is
co
n
s
id
er
ed
f
o
r
test
in
g
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
e
r
esu
lts
o
b
tain
ed
ar
e
c
o
m
p
ar
ed
wit
h
th
e
s
tate
o
f
th
e
ar
t
m
o
d
els
lik
e
KNN,
lo
g
is
tic
r
eg
r
ess
io
n
an
d
d
ec
is
io
n
tr
ee
a
n
d
Gau
s
s
ian
Naïv
e
B
ay
es
class
if
ier
s
[2
4]
-
[
2
6
]
.
Gr
ad
ien
t
b
o
o
s
ted
d
ec
is
io
n
tr
ee
s
(
GB
DT
)
is
an
en
s
em
b
le
lear
n
in
g
m
eth
o
d
o
l
o
g
y
th
at
c
o
m
b
in
es
m
an
y
d
ec
is
io
n
tr
ee
s
in
s
er
ies.
XGBo
o
s
t
wa
s
in
itially
in
tr
o
d
u
ce
d
b
y
C
h
en
a
n
d
Gu
estrin
[
1
6
]
an
d
was
th
en
f
u
r
th
er
em
p
lo
y
ed
b
y
r
esear
ch
er
s
d
u
e
to
its
ef
f
icac
y
in
d
ec
r
ea
s
i
n
g
p
r
o
ce
s
s
in
g
tim
e
an
d
ef
f
icien
tly
u
tili
s
in
g
m
em
o
r
y
r
eso
u
r
ce
s
.
T
ab
le
1
s
h
o
ws
th
e
p
ar
am
eter
s
th
at
ar
e
co
n
s
id
er
ed
f
o
r
th
e
class
if
icat
io
n
o
f
th
e
m
o
d
els
.
T
ab
le
1
.
Mo
d
el
p
ar
am
ete
r
s
C
l
a
s
si
f
i
e
r
s
P
a
r
a
me
t
e
r
s
K
N
N
N
e
i
g
h
b
o
r
s(
k
)
=
5
,
w
e
i
g
h
t
s=
u
n
i
f
o
r
m
,
l
e
a
f
_
si
z
e
=
3
0
,
p
=
2
,
m
e
t
r
i
c
=
m
i
n
k
o
w
sk
i
D
e
c
i
s
i
o
n
t
r
e
e
c
r
i
t
e
r
i
o
n
=
'g
i
n
i
',
sp
l
i
t
t
e
r
=
'b
e
st
'
,
m
i
n
_
sa
mp
l
e
s_
s
p
l
i
t
=
2
,
m
i
n
_
s
a
mp
l
e
s
_
l
e
a
f
=
1
S
C
LX
G
B
b
a
s
e
_
s
c
o
r
e
=
0
.
5
,
g
a
m
ma=
0
,
l
e
a
r
n
i
n
g
_
r
a
t
e
=
0
.
1
,
m
a
x
_
d
e
l
t
a
_
s
t
e
p
=
0
,
m
a
x
_
d
e
p
t
h
=
3
,
n
_
e
s
t
i
m
a
t
o
r
s=
1
0
0
,
o
b
j
e
c
t
i
v
e
=
'
b
i
n
a
r
y
:
l
o
g
i
st
i
c
'
,
r
e
g
_
a
l
p
h
a
=
0
,
r
e
g
_
l
a
m
b
d
a
=
1
T
ab
le
1
elab
o
r
ates
th
e
p
ar
am
e
ter
s
s
et
f
o
r
o
p
tim
izin
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
class
if
ier
.
Ou
r
r
esear
ch
f
o
cu
s
ed
o
n
th
e
m
o
d
el
co
m
p
lex
ity
an
d
a
d
ju
s
ted
th
e
f
o
llo
w
in
g
th
r
ee
p
r
o
p
o
s
ed
m
o
d
el
p
ar
am
eter
s
SC
L
XG
B
.
T
h
e
m
o
d
el
wo
r
k
s
ef
f
icien
tly
with
les
s
co
m
p
u
tatio
n
tim
e
a
n
d
in
cr
ea
s
ed
ac
cu
r
ac
y
.
T
h
e
“
m
ax
_
d
ep
th
”
is
a
p
ar
am
eter
th
at
e
m
p
h
asizes
th
e
m
o
d
el
co
m
p
le
x
ity
.
T
h
e
h
ig
h
er
t
h
e
v
alu
e
,
th
e
m
o
r
e
co
m
p
lex
th
e
m
o
d
el
b
ec
o
m
es
[
2
7
]
.
T
h
e
“
m
in
_
c
h
ild
_
weig
h
t
”
alwa
y
s
tak
es
p
o
s
itiv
e
in
teg
er
v
alu
es.
I
t
f
u
r
th
er
ev
alu
ates
th
e
s
p
litt
in
g
o
f
n
o
d
es
if
th
e
s
u
m
o
f
weig
h
ts
is
g
r
ea
ter
th
an
th
e
p
ea
k
v
alu
e.
T
h
is
p
ar
am
eter
m
a
k
es
th
e
alg
o
r
ith
m
m
o
r
e
cu
s
to
m
ar
y
as
th
e
v
alu
e
in
c
r
ea
s
es.
T
h
e
th
ir
d
p
ar
am
eter
is
th
e
“
lear
n
in
g
_
r
ate
”
,
w
h
ich
is
tu
n
ed
to
p
r
e
v
en
t
th
e
s
y
s
tem
f
r
o
m
b
ei
n
g
less
o
v
er
f
itti
n
g
an
d
m
o
r
e
r
o
b
u
s
t.
I
t
s
h
r
in
k
s
th
e
s
tep
s
ize
s
o
th
at
it
p
r
o
v
id
es
m
o
r
e
ar
ea
f
o
r
f
u
r
th
er
en
h
an
ce
m
e
n
t.
T
h
e
cla
s
s
if
ier
'
s
p
er
f
o
r
m
an
ce
is
ev
alu
ated
b
y
th
e
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
f
1
-
m
ea
s
u
r
e
an
d
AUC
ar
e
ca
lcu
lated
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
o
f
v
ar
io
u
s
m
o
d
el
s
ar
e
illu
s
tr
ated
in
T
ab
le
2
.
A
h
i
g
h
er
v
alu
e
in
d
icate
s
a
b
etter
r
esu
lt
.
Fro
m
th
e
ab
o
v
e
tab
le
it
s
h
o
ws
th
at
KNN
ex
h
ib
its
b
etter
p
r
ec
is
io
n
o
f
9
8
.
3
%
th
an
an
y
o
th
er
m
o
d
el
f
o
r
th
is
b
en
ch
m
ar
k
d
ataset.
I
t
ca
n
b
e
s
ee
n
th
at
L
o
g
is
tic
r
eg
r
ess
io
n
an
d
d
ec
is
io
n
tr
ee
m
o
d
el
d
o
es
n
o
t
h
av
e
a
r
em
ar
k
ab
le
p
er
f
o
r
m
a
n
ce
in
th
is
co
n
tex
t.
L
R
h
as
an
ac
cu
r
a
cy
o
f
7
3
.
6
%
wh
ic
h
is
v
e
r
y
lo
w
an
d
DT
h
as
a
n
ac
cu
r
ac
y
o
f
ab
o
u
t
8
9
.
9
wh
ic
h
is
lo
wer
as
co
m
p
ar
ed
to
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
SC
L
XGB
o
u
tp
er
f
o
r
m
s
o
t
h
er
class
if
ier
s
in
r
ec
all,
F1
m
ea
s
u
r
e,
a
cc
u
r
ac
y
an
d
AUC.
I
t
h
as
ac
h
iev
ed
a
n
ac
cu
r
ac
y
o
f
9
6
%
with
less
co
m
p
u
tatio
n
tim
e.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
y
s
tem
ca
n
b
e
ev
alu
ated
in
ter
m
s
o
f
co
m
p
u
tatio
n
tim
e
co
m
p
ar
in
g
with
KNN
an
d
DT
[
2
8
]
.
F
r
o
m
th
e
g
r
a
p
h
s
h
o
wn
in
Fi
g
u
r
e
4
t
h
e
c
o
m
p
u
tatio
n
al
ti
m
e
o
r
th
e
elap
s
ed
t
r
ain
in
g
ti
m
e
f
o
r
th
e
p
r
o
p
o
s
ed
m
o
d
el
SC
L
XGB
is
2
.
6
6
m
s
an
d
th
at
o
f
KNN
i
s
7
.
8
7
m
s
an
d
DT
is
3
.
1
5
m
s
.
T
h
e
co
n
f
u
s
io
n
,
p
r
ec
is
io
n
an
d
r
ec
all
m
atr
ix
o
f
K
n
ea
r
est
n
eig
h
b
or
s
h
o
w
n
in
Fig
u
r
e
5
(
a
)
,
lin
ea
r
r
eg
r
ess
io
n
in
Fig
u
r
e
5
(
b
)
,
d
ec
is
io
n
tr
ee
in
Fig
u
r
e
5
(
c)
,
N
aïv
e
B
ay
es a
n
d
p
r
o
p
o
s
ed
m
o
d
el
SC
L
XG
B
clas
s
if
ier
in
Fig
u
r
e
5
(
d
)
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
test
d
ata
M
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
1
S
c
o
r
e
AUC
K
N
N
0
.
9
3
1
0
.
9
8
3
0
.
6
7
8
0
.
8
0
3
0
.
8
3
7
8
LR
0
.
7
3
6
0
.
3
7
7
0
.
4
3
8
0
.
4
0
6
0
.
6
2
5
9
DT
0
.
8
9
8
0
.
7
0
8
0
.
8
6
0
0
.
7
7
7
0
.
8
8
4
4
GNB
0
.
9
5
8
0
.
9
0
7
0
.
8
9
4
0
.
8
9
9
0
.
9
3
4
9
S
C
LX
G
B
(
P
r
o
p
o
se
d
)
0
.
9
6
0
0
.
8
9
2
0
.
9
1
6
0
.
9
0
4
0
.
9
4
6
2
Fig
u
r
e
4
.
C
o
m
p
u
tatio
n
al
tim
e
o
f
th
e
class
if
ier
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
p
ilep
tic
s
eizu
r
e
cla
s
s
i
fica
tio
n
o
f
elec
tr
o
en
ce
p
h
a
l
o
g
r
a
m
s
ig
n
a
ls
u
s
in
g
ex
tr
eme
…
(
Mil
lee
P
a
n
ig
r
a
h
i
)
889
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
: (
a
)
KNN,
(
b
)
L
R
,
(
c
)
DT
,
an
d
(
d
)
SC
L
XGB
T
h
e
AUC
o
f
th
e
v
ar
io
u
s
class
if
icatio
n
m
o
d
els
is
d
ep
icted
in
Fig
u
r
e
6
.
Hig
h
er
AUC
v
alu
e
r
ef
lects
a
b
etter
m
o
d
el.
I
t is seen
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
ex
h
i
b
its
b
etter
p
er
f
o
r
m
an
ce
as c
o
m
p
ar
e
d
t
o
o
th
er
m
o
d
els.
Fig
u
r
e
6
.
AUC o
f
class
if
icatio
n
m
o
d
els o
n
test
d
ata
5.
CO
NCLU
SI
O
N
I
n
th
is
p
r
esen
t
s
tu
d
y
,
d
if
f
e
r
en
t
ML
class
if
ier
s
ar
e
co
m
p
a
r
ed
to
o
b
tain
th
e
ictal
p
er
io
d
o
f
s
eizu
r
es
in
ep
ilep
tic
p
atien
ts
.
I
n
th
e
f
o
r
m
o
f
th
e
ab
o
v
e
i
n
v
esti
g
atio
n
,
it
is
f
o
u
n
d
th
at
th
e
b
in
a
r
y
class
if
icatio
n
o
f
s
eizu
r
es
o
u
tp
er
f
o
r
m
s
o
th
er
m
o
d
els
in
ter
m
s
o
f
r
eg
u
lar
izatio
n
an
d
m
in
im
izatio
n
o
f
co
m
p
u
tatio
n
al
tim
e.
Seizu
r
e
class
if
icatio
n
u
s
in
g
th
e
SC
L
XGB
m
o
d
el
is
a
n
o
v
el
a
p
p
r
o
ac
h
an
d
p
r
o
v
i
d
es
th
e
b
est
AUC
o
f
0
.
9
4
6
2
a
n
d
test
ac
cu
r
ac
y
o
f
9
6
%
co
m
p
ar
ed
to
o
th
er
m
ac
h
i
n
e
lear
n
in
g
m
o
d
e
ls
s
u
ch
as
KNN,
lin
ea
r
r
eg
r
ess
io
n
,
d
ec
is
io
n
tr
ee
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
25
,
No
.
2
,
Feb
r
u
a
r
y
20
22
:
8
8
4
-
8
9
1
890
an
d
Naïv
e
B
ay
es
m
o
d
els.
Af
ter
p
r
e
-
p
r
o
ce
s
s
in
g
,
th
e
d
ata
tr
ain
test
s
p
lit
tin
g
is
ca
r
r
ied
o
u
t,
an
d
7
0
%
o
f
th
e
tr
ain
an
d
3
0
%
o
f
th
e
test
d
ata
ar
e
co
n
s
id
er
ed
f
o
r
v
alid
atio
n
o
f
th
e
m
o
d
el.
T
h
e
ar
ea
u
n
d
er
t
h
e
R
OC
cu
r
v
e
was
0
.
9
4
6
2
f
o
r
t
h
e
p
r
o
p
o
s
ed
m
o
d
e
l.
C
o
m
p
ar
ed
t
o
th
e
KNN,
L
R
d
ec
is
io
n
tr
ee
a
n
d
Naïv
e
B
ay
es
m
o
d
els,
SC
L
XGB
is
th
e
m
o
s
t
ac
ce
p
tab
le
c
lass
if
icatio
n
m
o
d
el.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
p
r
o
v
id
es
f
o
r
a
s
u
itab
le
r
eg
u
lar
izatio
n
th
at
p
r
ev
en
ts
it
f
r
o
m
b
ein
g
o
v
er
-
f
it
ted
.
SC
L
XGB
in
teg
r
ates
d
ata
s
p
ar
s
ity
with
a
s
p
lit
-
f
in
d
in
g
al
g
o
r
ith
m
t
o
m
an
a
g
e
d
if
f
er
en
t
ty
p
es
o
f
d
ata
s
p
a
r
s
ity
p
atter
n
s
.
T
h
e
d
ata
is
o
r
g
an
i
ze
d
in
m
em
o
r
y
ce
lls
ca
lled
b
lo
ck
s
to
b
e
r
eu
s
ed
in
r
ep
ea
ted
iter
atio
n
s
in
s
tead
o
f
r
e
-
ca
lcu
lated
.
T
h
is
h
elp
s
to
r
ed
u
ce
th
e
co
m
p
u
tatio
n
tim
e
o
f
2
.
6
6
m
s
an
d
m
a
k
es
th
e
m
o
d
el
m
o
r
e
r
o
b
u
s
t
f
o
r
class
if
icatio
n
.
I
n
SC
L
XG
B
,
d
is
co
n
tin
u
o
u
s
m
em
o
r
y
ac
ce
s
s
is
r
eq
u
ir
ed
to
o
b
tain
g
r
ad
ien
t
in
f
o
r
m
ati
o
n
b
y
r
o
w
i
n
d
icato
r
f
o
r
o
p
tim
u
m
h
ar
d
wa
r
e
u
tili
za
tio
n
.
T
h
is
is
d
o
n
e
b
y
ass
ig
n
in
g
in
ter
n
al
b
u
f
f
er
s
to
ea
c
h
t
h
r
ea
d
wh
er
e
g
r
ad
ien
t
s
tatis
tics
ca
n
b
e
s
to
r
e
d
.
T
h
is
f
ea
tu
r
e
en
a
b
les
o
p
tim
i
ze
d
u
s
e
o
f
av
ailab
le
d
is
c
s
p
ac
e
with
a
lar
g
e
d
ataset
h
an
d
lin
g
ca
p
ab
ilit
y
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
B
r
i
h
a
d
i
sw
a
r
a
n
,
D
.
H
a
p
u
t
h
a
n
t
h
r
i
,
S
.
G
u
n
a
t
h
i
l
a
k
a
,
D
.
M
e
e
d
e
n
i
y
a
,
a
n
d
S
.
J
a
y
a
r
a
t
h
n
a
,
“
A
R
e
v
i
e
w
o
f
EEG
-
b
a
se
d
C
l
a
s
si
f
i
c
a
t
i
o
n
f
o
r
A
u
t
i
sm
S
p
e
c
t
r
u
m
D
i
s
o
r
d
e
r
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
J
C
S
)
,
v
o
l
.
1
5
,
n
o
.
8
,
p
p
.
1
1
6
1
-
1
1
8
3
,
2
0
1
9
,
d
o
i
:
1
0
.
3
8
4
4
/
j
c
ssp
.
2
0
1
9
.
1
1
6
1
.
1
1
8
3
.
[
2
]
M
.
Ta
n
v
e
e
r
a
n
d
A
.
A
.
S
a
l
ma
n
,
“
E
p
i
l
e
p
t
i
c
s
e
i
z
u
r
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
g
r
a
d
i
e
n
t
t
r
e
e
b
o
o
st
i
n
g
c
l
a
ssi
f
i
e
r
,
”
I
n
Pro
c
e
e
d
i
n
g
s o
f
t
h
e
2
0
1
9
9
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
Bi
o
m
e
d
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
1
9
,
p
p
.
7
1
-
7
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
2
6
1
7
2
.
3
3
2
6
1
8
2
.
[
3
]
A
.
S
u
b
a
si
,
“
E
p
i
l
e
p
t
i
c
se
i
z
u
r
e
d
e
t
e
c
t
i
o
n
u
si
n
g
d
y
n
a
mi
c
w
a
v
e
l
e
t
n
e
t
w
o
r
k
,
”
E
x
p
e
rt
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
9
,
n
o
.
2
,
p
p
.
3
4
3
-
3
5
5
,
2
0
0
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
0
5
.
0
4
.
0
0
7
.
[
4
]
F
.
L.
D
a
S
i
l
v
a
,
W
.
B
l
a
n
e
s,
S
.
N
.
K
a
l
i
t
z
i
n
,
J
.
P
a
r
r
a
,
P
.
S
u
f
f
c
z
y
n
sk
i
,
a
n
d
D
.
N
.
V
e
l
i
s
,
“
E
p
i
l
e
p
si
e
s
a
s
d
y
n
a
mi
c
a
l
d
i
s
e
a
se
s
o
f
b
r
a
i
n
sy
st
e
ms:
b
a
si
c
m
o
d
e
l
s
o
f
t
h
e
t
r
a
n
si
t
i
o
n
b
e
t
w
e
e
n
n
o
r
mal
a
n
d
e
p
i
l
e
p
t
i
c
a
c
t
i
v
i
t
y
,
”
E
p
i
l
e
p
si
a
,
v
o
l
.
4
4
,
p
p
.
72
-
8
3
,
2
0
0
3
.
[
5
]
M
.
D
.
A
l
e
s
sa
n
d
r
o
,
R
.
Est
e
l
l
e
r
,
G
.
V
a
c
h
t
se
v
a
n
o
s,
A
.
H
i
n
s
o
n
,
J.
Ec
h
a
u
z
,
a
n
d
B
.
Li
t
t
,
“
Ep
i
l
e
p
t
i
c
se
i
z
u
r
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
h
y
b
r
i
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
o
v
e
r
m
u
l
t
i
p
l
e
i
n
t
r
a
c
r
a
n
i
a
l
EEG
e
l
e
c
t
r
o
d
e
c
o
n
t
a
c
t
s
:
a
r
e
p
o
r
t
o
f
f
o
u
r
p
a
t
i
e
n
t
s
,
”
I
E
EE
t
r
a
n
s
a
c
t
i
o
n
s
o
n
b
i
o
m
e
d
i
c
a
l
e
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
0
,
n
o
.
5
,
p
p
.
6
0
3
-
6
1
5
,
2
0
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TB
M
E
.
2
0
0
3
.
8
1
0
7
0
6
.
[
6
]
C
.
M
a
sw
a
n
g
a
n
y
i
,
C
.
Tu
,
P
.
O
w
o
l
a
w
i
,
a
n
d
S
.
D
u
,
“
F
a
c
t
o
r
s
i
n
f
l
u
e
n
c
i
n
g
l
o
w
i
n
t
e
n
si
o
n
d
e
t
e
c
t
i
o
n
r
a
t
e
i
n
a
n
o
n
-
i
n
v
a
si
v
e
E
EG
-
b
a
s
e
d
b
r
a
i
n
c
o
mp
u
t
e
r
i
n
t
e
r
f
a
c
e
sy
s
t
e
m
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EEC
S
)
,
v
o
l
.
2
0
,
p
p
.
1
6
7
-
1
7
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
2
0
.
i
1
.
p
p
1
6
7
-
175
.
[
7
]
T
.
Y
.
W
e
n
a
n
d
S
.
A
.
M
.
A
r
i
s
,
“
E
l
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
a
m
(
E
EG
)
st
r
e
ss
a
n
a
l
y
s
i
s
o
n
a
l
p
h
a
/
b
e
t
a
r
a
t
i
o
a
n
d
t
h
e
t
a
/
b
e
t
a
r
a
t
i
o
,”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EE
C
S
)
,
v
o
l
.
1
7
,
n
o
.
1
7
5
,
p
p
.
10
-
1
1
5
9
1
,
2
0
2
0
,
d
o
i
:
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
1
7
.
i
1
.
p
p
1
7
5
-
1
8
2
.
[
8
]
F
.
Li
e
t
a
l
.
,
“
B
r
a
i
n
v
a
r
i
a
b
i
l
i
t
y
i
n
d
y
n
a
m
i
c
r
e
s
t
i
n
g
-
st
a
t
e
n
e
t
w
o
r
k
s
i
d
e
n
t
i
f
i
e
d
b
y
f
u
z
z
y
e
n
t
r
o
p
y
:
a
sc
a
l
p
EEG
s
t
u
d
y
,”
J
o
u
r
n
a
l
o
f
N
e
u
ra
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
8
,
n
o
.
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
1
-
2
5
5
2
/
a
c
0
d
4
1
.
[
9
]
M
.
C
h
a
k
r
a
b
o
r
t
y
a
n
d
D
.
M
i
t
r
a
,
“
A
u
t
o
ma
t
e
d
d
e
t
e
c
t
i
o
n
o
f
e
p
i
l
e
p
t
i
c
s
e
i
z
u
r
e
s
u
si
n
g
m
u
l
t
i
s
c
a
l
e
a
n
d
r
e
f
i
n
e
d
c
o
m
p
o
s
i
t
e
m
u
l
t
i
sca
l
e
d
i
s
p
e
r
s
i
o
n
e
n
t
r
o
p
y
,”
C
h
a
o
s
,
S
o
l
i
t
o
n
s
& Fra
c
t
a
l
s
,
v
o
l
.
1
4
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
a
o
s.
2
0
2
1
.
1
1
0
9
3
9
.
[
1
0
]
D
.
K
.
B
e
h
e
r
a
,
M
.
D
a
s,
S
.
S
w
e
t
a
n
i
s
h
a
,
a
n
d
P
.
K
.
S
e
t
h
y
,
“
H
y
b
r
i
d
m
o
d
e
l
f
o
r
mo
v
i
e
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
s
t
e
m
u
s
i
n
g
c
o
n
t
e
n
t
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
a
n
d
r
e
st
r
i
c
t
e
d
b
o
l
t
z
ma
n
n
mac
h
i
n
e
,”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
E
EC
S
)
,
v
o
l
.
2
3
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
3
.
i
1
.
p
p
4
4
5
-
4
5
2
.
[
1
1
]
G
.
W
a
n
g
,
Z.
S
u
n
,
R
.
Ta
o
,
K
.
Li
,
G
.
B
a
o
,
a
n
d
X
.
Y
a
n
,
“
E
p
i
l
e
p
t
i
c
se
i
z
u
r
e
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
p
a
r
t
i
a
l
d
i
r
e
c
t
e
d
c
o
h
e
r
e
n
c
e
a
n
a
l
y
s
i
s
,”
I
EEE
j
o
u
rn
a
l
o
f
b
i
o
m
e
d
i
c
a
l
a
n
d
h
e
a
l
t
h
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
873
-
8
7
9
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
J
B
H
I
.
2
0
1
5
.
2
4
2
4
0
7
4
.
[
1
2
]
M
.
M
u
r
sal
i
n
,
Y
.
Z
h
a
n
g
,
Y
.
C
h
e
n
,
a
n
d
N
.
V
.
C
h
a
w
l
a
,
“
A
u
t
o
ma
t
e
d
e
p
i
l
e
p
t
i
c
s
e
i
z
u
r
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
i
m
p
r
o
v
e
d
c
o
r
r
e
l
a
t
i
o
n
-
b
a
s
e
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
w
i
t
h
r
a
n
d
o
m f
o
r
e
st
c
l
a
ssi
f
i
e
r
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
2
4
1
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
1
7
.
0
2
.
0
5
3
.
[
1
3
]
S
.
R
a
g
h
a
v
e
n
d
r
a
a
n
d
J
.
S
.
K
u
mar,
“
P
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
r
a
n
d
o
m
f
o
r
e
st
w
i
t
h
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
me
t
h
o
d
s
i
n
p
r
e
d
i
c
t
i
o
n
o
f
d
i
a
b
e
t
e
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
3
5
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
0
i
1
.
p
p
3
5
3
-
359
.
[
1
4
]
D
.
H
a
p
u
t
h
a
n
t
h
r
i
e
t
a
l
.
,
“
A
n
EEG
b
a
sed
C
h
a
n
n
e
l
O
p
t
i
m
i
z
e
d
C
l
a
ssi
f
i
c
a
t
i
o
n
A
p
p
r
o
a
c
h
f
o
r
A
u
t
i
sm
S
p
e
c
t
r
u
m
D
i
so
r
d
e
r
,
”
In
2
0
1
9
Mo
r
a
t
u
w
a
En
g
i
n
e
e
r
i
n
g
Re
se
a
r
c
h
C
o
n
f
e
re
n
c
e
(
M
ERC
o
n
)
,
2
0
1
9
,
p
p
.
1
2
3
-
128
,
d
o
i
:
1
0
.
1
1
0
9
/
M
ER
C
o
n
.
2
0
1
9
.
8
8
1
8
8
1
4
.
[
1
5
]
D
.
H
a
p
u
t
h
a
n
t
h
r
i
e
t
a
l
.
,
“
I
n
t
e
g
r
a
t
i
o
n
o
f
F
a
c
i
a
l
Th
e
r
mo
g
r
a
p
h
y
i
n
E
EG
-
b
a
s
e
d
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
A
S
D
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Au
t
o
m
a
t
i
o
n
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
7
,
n
o
.
6
,
p
p
.
8
3
7
-
8
5
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
6
3
3
-
0
2
0
-
1
2
3
1
-
6
.
[
1
6
]
T
.
C
h
e
n
a
n
d
C
.
G
u
e
s
t
r
i
n
,
“
X
g
b
o
o
s
t
:
A
sc
a
l
a
b
l
e
t
r
e
e
b
o
o
s
t
i
n
g
s
y
st
e
m,
”
I
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
2
n
d
a
c
m
s
i
g
k
d
d
i
n
t
e
r
n
a
t
i
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
k
n
o
w
l
e
d
g
e
d
i
sc
o
v
e
ry
a
n
d
d
a
t
a
m
i
n
i
n
g
,
2
0
1
6
,
p
p
.
7
8
5
-
7
9
4
,
d
o
i
:
1
0
.
1
1
4
5
/
2
9
3
9
6
7
2
.
2
9
3
9
7
8
5
.
[
1
7
]
J
.
H
.
F
r
i
e
d
ma
n
,
“
S
t
o
c
h
a
s
t
i
c
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
S
t
a
t
i
st
i
c
s
&
D
a
t
a
A
n
a
l
y
s
i
s
,
v
o
l
.
38
,
n
o
.
4
,
p
p
.
3
6
7
-
3
7
8
,
2
0
0
2
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
1
6
7
-
9
4
7
3
(
0
1
)
0
0
0
6
5
-
2
.
[
1
8
]
G
.
C.
C
a
w
l
e
y
a
n
d
N
.
L
.
C
.
Ta
l
b
o
t
,
“
O
n
o
v
e
r
-
f
i
t
t
i
n
g
i
n
mo
d
e
l
se
l
e
c
t
i
o
n
a
n
d
su
b
se
q
u
e
n
t
se
l
e
c
t
i
o
n
b
i
a
s
i
n
p
e
r
f
o
r
man
c
e
e
v
a
l
u
a
t
i
o
n
,
”
T
h
e
J
o
u
r
n
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
Re
s
e
a
r
c
h
,
v
o
l
.
1
1
,
p
p
.
2
0
7
9
-
2
1
0
7
,
2
0
1
0
,
d
o
i
:
1
0
.
5
5
5
5
/
1
7
5
6
0
0
6
.
1
8
5
9
9
2
1
.
[
1
9
]
Q
.
W
u
a
n
d
E
.
F
o
k
o
u
e
,
E
p
i
l
e
p
t
i
c
S
e
i
z
u
r
e
R
e
c
o
g
n
i
t
i
o
n
,
U
C
I
M
a
c
h
i
n
e
Le
a
r
n
i
n
g
R
e
p
o
si
t
o
r
.
A
c
c
e
sse
d
:
J
u
n
1
5
,
2
0
2
1
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
a
r
c
h
i
v
e
.
i
c
s.u
c
i
.
e
d
u
/
ml
/
d
a
t
a
s
e
t
s
/
Ep
i
l
e
p
t
i
c
+
S
e
i
z
u
r
e
+
R
e
c
o
g
n
i
t
i
o
n
[
2
0
]
X
.
W
a
n
g
,
L
.
W
a
n
g
,
S
.
W
a
n
g
,
J
.
C
h
e
n
,
a
n
d
C
.
W
u
,
“
A
n
X
G
B
o
o
s
t
-
e
n
h
a
n
c
e
d
f
a
s
t
c
o
n
st
r
u
c
t
i
v
e
a
l
g
o
r
i
t
h
m
f
o
r
f
o
o
d
d
e
l
i
v
e
r
y
r
o
u
t
e
p
l
a
n
n
i
n
g
p
r
o
b
l
e
m
,”
C
o
m
p
u
t
e
rs
& I
n
d
u
st
r
i
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
5
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
e
.
2
0
2
0
.
1
0
7
0
2
9
.
[
2
1
]
S
.
R
a
s
c
h
k
a
,
P
y
t
h
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
.
P
a
c
k
t
p
u
b
l
i
s
h
i
n
g
l
t
d
,
2
0
1
5
.
[
O
n
l
i
n
e
]
.
A
v
a
l
i
a
b
l
e
:
h
t
t
p
s
:
/
/
r
a
w
.
g
i
t
h
u
b
u
serc
o
n
t
e
n
t
.
c
o
m/
r
a
sb
t
/
p
y
t
h
o
n
-
ma
c
h
i
n
e
-
l
e
a
r
n
i
n
g
-
b
o
o
k
/
m
a
st
e
r
/
d
o
c
s
/
e
q
u
a
t
i
o
n
s/
p
y
ml
e
-
e
q
u
a
t
i
o
n
s.
p
d
f
[
2
2
]
M
.
P
a
n
i
g
r
a
h
i
,
D
.
K
.
B
e
h
e
r
a
,
a
n
d
K
.
C
.
P
a
t
r
a
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
E
EG
R
e
c
o
r
d
i
n
g
i
n
a
n
Ep
i
l
e
p
t
i
c
P
a
t
i
e
n
t
U
s
i
n
g
D
W
T
a
n
d
E
x
t
r
e
m
e
G
r
a
d
i
e
n
t
B
o
o
st
i
n
g
C
l
a
ss
i
f
i
e
r
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
9
,
n
o
.
5
,
p
p
.
4
1
6
3
-
4
1
8
0
,
2
0
2
0
.
[
2
3
]
D
.
K
.
B
e
h
e
r
a
,
M
.
D
a
s,
S
.
S
w
e
t
a
n
i
sh
a
,
J
.
N
a
y
a
k
,
S
.
V
i
ma
l
,
a
n
d
B
.
N
a
i
k
,
“
F
o
l
l
o
w
e
r
L
i
n
k
P
r
e
d
i
c
t
i
o
n
U
s
i
n
g
t
h
e
X
G
B
o
o
st
C
l
a
s
si
f
i
c
a
t
i
o
n
M
o
d
e
l
w
i
t
h
M
u
l
t
i
p
l
e
G
r
a
p
h
F
e
a
t
u
r
e
s,
”
W
i
re
l
e
ss
Pe
rs
o
n
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
p
p
.
1
-
2
0
,
A
p
r
.
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
7
7
-
0
2
1
-
0
8
3
9
9
-
y
.
[
2
4
]
M
.
P
a
n
i
g
r
a
h
i
,
D
.
K
.
B
e
h
e
r
a
,
a
n
d
K
.
C
.
P
a
t
r
a
,
“
A
H
y
b
r
i
d
M
o
d
e
l
f
o
r
E
p
i
l
e
p
t
i
c
S
e
i
z
u
r
e
C
l
a
ssi
f
i
c
a
t
i
o
n
U
s
i
n
g
W
a
v
e
l
e
t
P
a
c
k
e
t
D
e
c
o
m
p
o
si
t
i
o
n
a
n
d
S
V
M
,
”
Ad
v
a
n
c
e
s
i
n
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
p
p
.
2
1
1
-
2
1
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
0
6
9
5
-
3
_
2
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
E
p
ilep
tic
s
eizu
r
e
cla
s
s
i
fica
tio
n
o
f
elec
tr
o
en
ce
p
h
a
l
o
g
r
a
m
s
ig
n
a
ls
u
s
in
g
ex
tr
eme
…
(
Mil
lee
P
a
n
ig
r
a
h
i
)
891
[
2
5
]
R
.
G
.
A
n
d
r
z
e
j
a
k
,
K
.
Le
h
n
e
r
t
z
,
C
.
R
i
e
k
e
,
F
.
M
o
r
ma
n
n
,
P
.
D
a
v
i
d
,
a
n
d
C
.
E
.
El
g
e
r
,
“
I
n
d
i
c
a
t
i
o
n
s o
f
n
o
n
l
i
n
e
a
r
d
e
t
e
r
mi
n
i
st
i
c
a
n
d
f
i
n
i
t
e
d
i
m
e
n
s
i
o
n
a
l
st
r
u
c
t
u
r
e
s
i
n
t
i
m
e
s
e
r
i
e
s
o
f
b
r
a
i
n
e
l
e
c
t
r
i
c
a
l
a
c
t
i
v
i
t
y
:
D
e
p
e
n
d
e
n
c
e
o
n
r
e
c
o
r
d
i
n
g
r
e
g
i
o
n
a
n
d
b
r
a
i
n
s
t
a
t
e
,
”
P
h
y
s
i
c
a
l
Re
v
i
e
w
E
,
v
o
l
.
6
4
,
n
o
.
6
,
2
0
0
1
,
d
o
i
:
1
0
.
1
1
0
3
/
P
h
y
sR
e
v
E.
6
4
.
0
6
1
9
0
7
.
[
2
6
]
S
.
K
u
i
l
a
,
N
.
D
h
a
n
d
a
,
a
n
d
S
.
J
o
a
r
d
a
r
,
“
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
o
f
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
(
I
J
E
C
E)
,
v
o
l
.
1
0
,
n
o
.
6
,
p
p
.
6
5
9
8
-
6
6
0
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
0
i
6
.
p
p
6
5
9
8
-
6
6
0
5
.
[
2
7
]
A
.
H
a
i
d
e
r
a
n
d
M
.
Z.
A
l
-
F
a
i
z
,
“
O
n
l
i
n
e
mu
l
t
i
c
l
a
ss
EEG
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
m
o
d
i
f
i
e
d
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
met
h
o
d
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
(
I
J
EC
E)
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
4
016
-
4
0
2
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
1
i
5
.
p
p
4
0
1
6
-
4
0
2
6
.
[
2
8
]
H
.
R
.
Esma
e
e
l
,
“
A
n
a
l
y
s
i
s
o
f
c
l
a
ss
i
f
i
c
a
t
i
o
n
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
I
J
EE
C
S
)
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
1
0
2
9
-
1
0
3
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
1
7
.
i
2
.
p
p
1
0
2
9
-
1
0
3
9
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Mi
ll
e
e
Pa
n
ig
r
a
h
i
h
a
s
c
o
m
p
l
e
t
e
d
h
e
r
ba
c
h
e
l
o
r
i
n
e
l
e
c
t
r
o
n
i
c
s
a
n
d
t
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
e
n
g
g
i
n
e
e
r
i
n
g
a
n
d
m
a
s
t
e
r
i
n
s
i
g
n
a
l
p
r
o
c
e
s
s
i
n
g
a
n
d
t
e
l
e
m
a
t
ic
s
fr
o
m
B
P
U
T
,
O
d
i
s
h
a
,
I
n
d
i
a
.
P
r
e
s
e
n
t
l
y
s
h
e
i
s
w
o
r
k
i
n
g
a
s
a
s
s
i
s
t
a
n
t
p
r
o
f
e
s
s
o
r
i
n
d
e
p
t
.
o
f
e
l
e
c
t
r
o
n
i
c
s
a
n
d
t
e
l
e
c
o
m
m
e
n
g
g
.
a
t
T
r
i
d
e
n
t
A
c
a
d
e
m
y
o
f
T
e
c
h
n
o
l
o
g
y
,
B
h
u
b
a
n
e
s
w
a
r
,
O
d
i
s
h
a
,
I
n
d
i
a
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
te
d
a
t
e
m
a
i
l
:
m
i
l
l
e
e
.
p
a
n
i
g
r
a
h
i
8
2
@
g
m
a
i
l
.
c
o
m
.
Dr
.
Da
y
a
l
K
u
m
a
r
Be
h
e
r
a
h
a
s
c
o
m
p
lete
d
P
h
.
D.
fro
m
KII
T
U
n
iv
e
rsit
y
,
Od
ish
a
.
He
h
a
s
b
e
e
n
wo
rk
in
g
a
s
a
n
a
ss
t.
p
ro
fe
ss
o
r
in
t
h
e
d
e
p
a
rtme
n
t
o
f
CS
E
a
t
S
il
ico
n
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Bh
u
b
a
n
e
sw
a
r.
He
is
h
a
v
in
g
fo
u
rtee
n
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
a
n
d
c
a
rry
in
g
o
u
t
re
se
a
rc
h
in
v
a
rio
u
s
a
sp
e
c
ts
o
f
re
c
o
m
m
e
n
d
e
r
sy
ste
m
,
m
a
c
h
in
e
lea
rn
in
g
,
d
a
ta
sc
ien
c
e
,
I
o
T
a
n
d
n
a
t
u
ra
l
lan
g
u
a
g
e
p
ro
c
e
s
sin
g
.
He
is
h
a
v
in
g
2
0
p
u
b
li
c
a
ti
o
n
s
in
v
a
rio
u
s
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
a
n
d
g
u
i
d
e
d
n
u
m
e
ro
u
s
B.
Tec
h
.
a
n
d
M
.
Tec
h
.
p
ro
jec
ts
i
n
h
is
a
re
a
o
f
i
n
tere
sts.
He
is
a
li
fe
ti
m
e
m
e
m
b
e
r
o
f
p
ro
fe
ss
io
n
a
l
so
c
ieties
li
k
e
IS
TE
a
n
d
IAE
NG
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
a
y
a
lb
e
h
e
ra
@g
m
a
il
.
c
o
m
.
Dr
.
K
r
ish
n
a
C
h
a
n
d
r
a
Pa
tr
a
h
a
s
c
o
m
p
l
e
t
e
d
h
i
s
P
h
.
D
.
i
n
e
l
e
c
t
r
o
n
i
c
s
f
r
o
m
D
e
l
h
i
U
n
i
v
e
r
s
i
t
y
.
P
r
e
s
e
n
t
l
y
h
e
i
s
w
o
r
k
i
n
g
i
n
d
e
p
a
r
t
m
e
n
t
o
f
e
l
e
c
t
r
o
n
i
c
s
i
n
S
U
I
I
T
,
S
a
m
b
a
l
p
u
r
U
n
i
v
e
r
s
i
t
y
,
O
d
i
s
h
a
,
I
n
d
i
a
.
H
e
h
a
s
p
u
b
l
i
s
h
e
d
m
o
r
e
t
h
a
n
1
6
p
a
p
e
r
s
i
n
j
o
u
r
n
a
l
a
n
d
c
o
n
f
e
r
e
n
c
e
.
M
o
r
e
t
h
a
n
5
c
a
n
d
i
d
a
t
e
s
h
a
v
e
c
o
m
p
l
e
t
e
d
t
h
e
i
r
M
.
P
h
i
l
.
u
n
d
e
r
h
i
s
s
u
p
e
r
v
i
s
i
o
n
i
n
t
h
e
a
r
e
a
o
f
e
l
e
c
t
r
o
n
i
c
s
c
o
m
m
u
n
i
c
a
t
i
o
n
s
y
s
t
e
m
a
n
d
r
e
la
t
e
d
d
i
s
c
i
p
l
i
n
e
s
.
H
i
s
a
re
a
o
f
r
e
s
e
a
r
c
h
i
s
a
d
v
a
n
c
e
d
c
o
m
m
u
n
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
a
n
d
o
n
p
h
o
t
o
n
i
c
s
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
k
r
i
s
h
n
a
c
h
.
p
a
t
r
a
@
g
m
a
i
l
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.