I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
16
,
No
.
2
,
N
o
v
e
m
b
er
201
9
,
p
p
.
9
6
4
~9
7
1
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
1
6
.i
2
.
p
p
9
6
4
-
9
7
1
964
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Neuro
-
P
hy
sio
lo
g
i
ca
l
po
rn addictio
n det
e
ction using
m
a
chine
learning
a
ppro
a
ch
No
rha
s
lin
da
K
a
m
a
r
ud
d
in
1
,
Abdu
l
Wa
ha
b
2
,
Ya
s
m
ee
n Ro
za
idi
3
1,
3
A
d
v
a
n
c
e
d
A
n
a
l
y
ti
c
s E
n
g
in
e
e
rin
g
Ce
n
ter,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter an
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
,
4
0
4
5
0
S
h
a
h
A
lam
,
S
e
lan
g
o
r
2
Ku
ll
iy
a
h
o
f
In
f
o
r
m
a
ti
o
n
a
n
d
C
o
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
,
In
tern
a
ti
o
n
a
l
Isla
m
ic Un
iv
e
rsit
y
M
a
la
y
si
a
,
Ku
a
la L
u
m
p
u
r,
M
a
l
a
y
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
20
,
2
0
1
8
R
ev
i
s
ed
Mar
17
,
2
0
1
9
A
cc
ep
ted
A
p
r
11
,
2
0
1
9
P
o
rn
o
g
ra
p
h
y
is
a
p
o
rtra
y
a
l
o
f
se
x
u
a
l
su
b
jec
t
c
o
n
ten
ts
f
o
r
th
e
e
x
c
lu
siv
e
p
u
r
p
o
se
o
f
se
x
u
a
l
a
ro
u
sa
l
th
a
t
c
a
n
lea
d
t
o
a
d
d
ictio
n
.
T
h
e
In
tern
e
t
a
c
c
e
s
sib
il
it
y
h
a
s
c
re
a
ted
u
n
p
re
c
e
d
e
n
ted
o
p
p
o
r
tu
n
it
ies
f
o
r
se
x
u
a
l
e
d
u
c
a
ti
o
n
,
lea
rn
in
g
,
a
n
d
g
ro
w
th
.
He
n
c
e
,
th
e
risk
o
f
p
o
rn
a
d
d
icti
o
n
d
e
v
e
lo
p
e
d
b
y
tee
n
a
g
e
rs
h
a
s
a
lso
in
c
re
a
se
d
d
u
e
to
h
ig
h
ly
p
re
v
a
len
t
p
o
rn
c
o
n
su
m
p
ti
o
n
.
T
o
d
a
te,
t
h
e
o
n
ly
a
v
a
il
a
b
le
m
e
a
n
s
o
f
d
e
tec
ti
n
g
p
o
r
n
a
d
d
icti
o
n
i
s
th
ro
u
g
h
q
u
e
stio
n
n
a
ire.
Ho
w
e
v
e
r,
w
h
il
e
a
n
sw
e
rin
g
th
e
q
u
e
stio
n
s
,
p
a
rti
c
i
p
a
n
ts
m
a
y
su
p
p
re
ss
o
r
e
x
a
g
g
e
ra
te
th
e
ir
a
n
s
w
e
r
s
b
e
c
a
u
se
p
o
rn
a
d
d
ictio
n
is
c
o
n
sid
e
re
d
tab
o
o
in
th
e
c
o
m
m
u
n
it
y
.
He
n
c
e
,
th
e
p
u
rp
o
se
o
f
th
is
p
r
o
jec
t
is
t
o
d
e
v
e
lo
p
a
n
e
n
g
in
e
w
it
h
m
u
lt
ip
le
c
las
sif
i
e
rs
to
re
c
o
g
n
ize
p
o
rn
a
d
d
ict
io
n
u
sin
g
e
lec
tro
e
n
c
e
p
h
a
lo
g
ra
p
h
y
sig
n
a
ls
a
n
d
to
c
o
m
p
a
re
c
l
a
s
si
f
iers
p
e
rf
o
r
m
a
n
c
e
.
In
t
h
is
w
o
rk
,
th
re
e
d
if
f
e
re
n
t
c
las
sif
iers
o
f
M
u
lt
il
a
y
e
r
P
e
rc
e
p
tro
n
,
Na
iv
e
B
a
y
e
sia
n
,
a
n
d
Ra
n
d
o
m
F
o
re
st
a
re
e
m
p
lo
y
e
d
.
T
h
e
e
x
p
e
ri
m
e
n
tal
re
su
lt
s
sh
o
w
th
a
t
th
e
M
L
P
c
las
sif
ier
y
ield
e
d
slig
h
tl
y
b
e
tt
e
r
a
c
c
u
ra
c
y
c
o
m
p
a
re
d
to
Na
ïv
e
Ba
y
e
s
a
n
d
Ra
n
d
o
m
F
o
r
e
st
c
las
si
f
iers
m
a
k
in
g
th
e
M
L
P
c
las
si
f
ier
p
re
f
e
ra
b
le
f
o
r
p
o
rn
a
d
d
ictio
n
r
e
c
o
g
n
it
io
n
.
A
lt
h
o
u
g
h
t
h
is
w
o
rk
is
stil
l
a
t
in
f
a
n
c
y
sta
g
e
,
it
is
e
n
v
isa
g
e
d
f
o
r
th
e
w
o
rk
to
b
e
e
x
p
a
n
d
e
d
f
o
r
c
o
m
p
re
h
e
n
siv
e
p
o
r
n
a
d
d
ict
io
n
re
c
o
g
n
it
i
o
n
sy
ste
m
so
th
a
t
e
a
rl
y
in
terv
e
n
ti
o
n
a
n
d
a
p
p
ro
p
riate
su
p
p
o
rt
c
a
n
b
e
g
iv
e
n
f
o
r
th
e
tee
n
a
g
e
rs
w
it
h
p
o
r
n
o
g
ra
p
h
y
a
d
d
icti
o
n
p
ro
b
lem
.
K
ey
w
o
r
d
s
:
E
lectr
o
en
ce
p
h
alo
g
r
a
m
(
E
E
G)
Mu
lti
-
la
y
er
p
er
ce
p
tr
o
n
Naïv
e
b
a
y
e
s
P
o
r
n
ad
d
ictio
n
R
an
d
o
m
f
o
r
est
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
No
r
h
asli
n
d
a
Ka
m
ar
u
d
d
in
,
A
d
v
an
ce
d
An
al
y
t
ics E
n
g
i
n
ee
r
i
n
g
C
en
ter
,
Facu
lt
y
o
f
C
o
m
p
u
ter
an
d
Ma
t
h
e
m
a
tical
Scie
n
ce
s
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
4
0
4
5
0
Sh
ah
A
la
m
,
Sela
n
g
o
r
,
Ma
la
y
s
ia.
E
m
ail:
n
o
r
h
asl
in
d
a
@
t
m
s
k
.
u
it
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Hab
it
an
d
ad
d
ictio
n
ar
e
th
e
r
e
s
u
lt
s
o
f
r
ep
ea
ted
ac
tiv
ities
b
ei
n
g
ca
r
r
ied
o
u
t
f
o
r
a
lo
n
g
t
i
m
e.
A
lt
h
o
u
g
h
th
e
t
w
o
s
ee
m
s
s
i
m
ilar
,
h
ab
it
c
an
b
e
co
n
tr
o
lled
b
y
th
e
i
n
d
iv
i
d
u
als
w
h
ile
ad
d
ictio
n
is
d
if
f
ic
u
lt
to
b
e
co
n
tr
o
lled
.
A
d
d
ictio
n
ca
n
a
f
f
ec
t
an
y
b
o
d
y
an
d
m
o
s
t
p
e
o
p
le
w
ill
ev
e
n
tu
all
y
d
ev
elo
p
at
least
o
n
e
o
f
t
h
e
h
ab
it
i
n
to
a
n
ad
d
ictio
n
,
w
h
ic
h
h
e/
s
h
e
o
f
te
n
d
o
it
in
t
h
eir
d
ail
y
li
f
e
[
1
]
.
P
e
o
p
le
w
it
h
an
ad
d
ictio
n
h
a
v
e
n
o
lo
n
g
er
a
n
y
co
n
tr
o
l
o
n
w
h
at
t
h
e
y
ar
e
d
o
in
g
,
ta
k
i
n
g
o
r
u
s
e
o
f
th
e
s
u
b
s
tan
ce
o
r
b
eh
av
io
r
s
t
h
at
t
h
e
y
ar
e
ad
d
icted
to
[
2
]
.
A
d
d
ictio
n
is
s
i
m
p
l
y
r
e
f
er
r
ed
to
‗
g
i
v
i
n
g
o
v
e
r
‘
o
r
b
ein
g
‗
h
i
g
h
l
y
d
e
v
o
ted
‘
t
o
a
p
er
s
o
n
o
r
ac
tiv
it
y
,
o
r
en
g
ag
in
g
i
n
a
b
e
h
av
io
r
h
ab
itu
al
l
y
w
h
ic
h
co
u
ld
h
a
v
e
p
o
s
itiv
e
o
r
n
eg
ati
v
e
i
m
p
licati
o
n
s
[
3
]
.
A
d
d
ictio
n
ca
n
b
e
d
iv
id
ed
in
to
2
t
y
p
es,
n
a
m
e
l
y
;
b
e
h
av
io
u
r
an
d
s
u
b
s
t
an
ce
ad
d
ictio
n
s
r
esp
ec
ti
v
el
y
[
4
]
.
A
cc
o
r
d
in
g
to
[
5
]
,
s
u
b
s
tan
ce
ad
d
ictio
n
is
a
n
eu
r
o
p
s
y
ch
iatr
ic
d
is
o
r
d
er
an
d
ca
n
b
e
ch
ar
ac
ter
ized
b
y
a
r
ec
u
r
r
in
g
d
esire
to
co
n
t
in
u
e
ta
k
in
g
t
h
e
s
u
b
s
tan
c
e
d
esp
ite
h
ar
m
f
u
l
co
n
s
eq
u
e
n
ce
s
in
w
h
ic
h
it
co
u
ld
b
e
d
r
u
g
s
,
alco
h
o
l,
s
ex
an
d
g
a
m
b
li
n
g
.
T
h
e
m
o
s
t
co
m
m
o
n
s
u
b
s
ta
n
ce
is
d
r
u
g
ad
d
ictio
n
wh
er
e
th
e
ad
d
icts
h
av
e
n
o
t o
n
l
y
ab
u
s
e
o
n
e
t
y
p
e
o
f
d
r
u
g
b
u
t
m
a
y
co
m
b
i
n
e
m
u
ltip
l
e
t
y
p
es
o
f
d
r
u
g
s
o
r
tr
y
i
n
g
d
i
f
f
er
en
t
t
y
p
e
o
f
d
r
u
g
s
[
6
]
.
T
h
e
n
o
n
-
s
u
b
s
ta
n
ce
ad
d
ictio
n
(
b
eh
av
io
u
r
al
ad
d
icti
o
n
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
N
eu
r
o
-
P
h
ysio
lo
g
ica
l P
o
r
n
A
d
d
ictio
n
Dete
ctio
n
u
s
in
g
Ma
c
h
i
n
e
Lea
r
n
in
g
…(
N
o
r
h
a
s
lin
d
a
K
a
ma
r
u
d
d
in
)
965
co
v
er
s
ac
tiv
itie
s
s
u
c
h
as
p
ath
o
lo
g
ical
g
a
m
b
li
n
g
,
f
o
o
d
ad
d
ictio
n
,
in
ter
n
et
ad
d
ictio
n
an
d
m
o
b
ile
p
h
o
n
e
ad
d
ictio
n
.
Hen
ce
,
p
o
r
n
o
g
r
ap
h
y
ad
d
ictio
n
ca
n
b
e
class
if
ied
as o
n
e
o
f
t
h
e
b
eh
av
io
u
r
al
ad
d
ictio
n
s
.
P
o
r
n
o
g
r
ap
h
y
is
th
e
p
o
r
tr
ay
al
o
f
s
ex
u
al
s
u
b
j
ec
t
m
at
ter
f
o
r
th
e
ex
clu
s
i
v
e
p
u
r
p
o
s
e
o
f
s
ex
u
a
l
ar
o
u
s
al
[
7
]
.
P
o
r
n
ad
d
ictio
n
is
an
ad
d
ictio
n
m
o
d
el
o
f
co
m
p
u
ls
i
v
e
s
e
x
u
a
l
ac
tiv
it
y
w
it
h
co
n
c
u
r
r
en
t
u
s
e
o
f
p
o
r
n
o
g
r
ap
h
ic
m
ater
ials
,
d
esp
ite
n
e
g
ati
v
e
co
n
s
eq
u
e
n
ce
s
to
an
in
d
iv
id
u
al
p
h
y
s
ical,
m
e
n
tal,
s
o
cial,
o
r
f
in
a
n
cial
w
ell
-
b
ein
g
[
8
]
.
T
h
er
e
ar
e
m
an
y
s
o
u
r
ce
s
t
h
at
allo
w
p
o
r
n
ad
d
icts
to
ac
c
ess
p
o
r
n
o
g
r
ap
h
y
an
d
s
e
x
u
a
l
a
m
u
s
e
m
en
t
w
it
h
s
ev
er
a
l
m
ed
ia
ac
ce
s
s
ib
ilit
y
s
u
c
h
as
s
e
x
u
al
p
ictu
r
es,
a
u
d
io
s
,
v
id
eo
s
a
n
d
w
r
itte
n
m
ater
ials
.
T
h
e
p
o
r
n
o
g
r
ap
h
y
m
ater
ials
ca
n
b
e
s
o
u
r
ce
d
t
h
r
o
u
g
h
ele
ctr
o
n
ic
m
ed
ia
(
tele
v
i
s
io
n
,
r
a
d
io
an
d
DVDs)
,
p
r
in
t
m
ed
i
a
(
n
e
w
s
p
ap
er
an
d
m
ag
az
in
e)
a
n
d
t
h
e
in
ter
n
et
[
9
]
.
At
p
r
esen
t,
2
5
%
o
f
t
h
e
to
tal
d
ail
y
s
ea
r
c
h
e
n
g
in
e
d
e
m
a
n
d
s
ar
e
f
o
r
p
o
r
n
o
g
r
ap
h
y
co
n
ten
t
s
w
i
th
6
8
m
i
llio
n
p
o
r
n
o
g
r
ap
h
ic
d
e
m
an
d
s
i
n
t
h
e
s
ea
r
ch
i
n
g
[
1
0
]
r
eq
u
ested
f
r
o
m
4
.
2
m
i
llio
n
p
o
r
n
o
g
r
ap
h
ic
w
eb
s
ites
w
i
th
t
h
e
av
er
ag
e
ag
e
o
f
f
ir
s
t
in
ter
n
et
p
o
r
n
o
g
r
ap
h
y
ex
p
o
s
u
r
e
is
1
1
y
ea
r
s
o
ld
.
T
h
e
in
ten
s
e
u
s
e
o
f
p
o
r
n
o
g
r
ap
h
y
i
s
s
tr
o
n
g
l
y
r
elate
d
to
s
ex
u
al
ag
g
r
e
s
s
io
n
w
h
ic
h
t
h
e
co
n
t
en
t
o
f
t
h
e
p
o
r
n
o
g
r
ap
h
y
ca
n
lead
to
a
v
io
len
t
cr
i
m
e
[
1
1
]
.
T
h
e
ca
u
s
e
o
f
s
u
c
h
ad
d
ictio
n
m
i
g
h
t
b
e
h
ar
m
f
u
l
n
o
t
o
n
l
y
f
o
r
th
e
in
d
i
v
id
u
al
b
u
t
al
s
o
a
f
f
ec
t
in
g
th
e
s
o
ciet
y
s
u
ch
as
th
e
r
ap
e
ca
s
es
a
n
d
i
n
ap
p
r
o
p
r
iate
b
eh
av
io
u
r
.
A
cc
o
r
d
in
g
to
[
1
2
]
,
th
e
f
ac
to
r
o
f
g
e
n
es
an
d
ag
e
its
el
f
m
i
g
h
t
lead
t
h
e
ad
d
icts
f
o
r
h
a
v
i
n
g
a
s
tr
o
n
g
e
r
ad
d
ictio
n
to
w
ar
d
s
s
o
m
et
h
i
n
g
.
E
n
v
ir
o
n
m
e
n
tal
f
ac
to
r
m
a
y
also
ad
d
ed
to
th
e
f
ac
t
o
r
th
at
in
f
lu
e
n
ce
a
n
in
d
i
v
id
u
al
ad
d
ictio
n
.
T
h
is
p
r
o
j
ec
t
f
o
cu
s
es
o
n
t
h
e
alter
n
ativ
e
m
ea
s
u
r
e
m
en
t
o
f
p
o
r
n
ad
d
ictio
n
f
o
r
teen
ag
er
s
to
d
etec
t
w
h
et
h
er
th
e
y
m
a
y
h
av
e
p
o
r
n
ad
d
ictio
n
o
r
n
o
t
b
ased
o
n
th
eir
b
r
ain
r
esp
o
n
s
es
d
u
r
in
g
t
h
e
in
itial
s
ta
g
e
at
e
y
e
s
o
p
en
an
d
e
y
es
clo
s
e.
T
h
ese
E
E
G
s
ig
n
als
d
u
r
i
n
g
th
e
i
n
iti
al
s
tag
e
w
il
l
p
r
o
v
id
e
en
o
u
g
h
in
f
o
r
m
atio
n
to
th
e
b
iasn
es
s
o
f
th
e
f
r
o
n
tal
p
ar
t
o
f
th
e
b
r
ai
n
r
esp
o
n
s
e
s
.
T
h
is
i
s
t
o
o
f
f
er
a
p
s
y
c
h
o
lo
g
ical
ap
p
r
o
ac
h
t
h
at
m
a
y
g
iv
e
b
etter
m
ea
s
u
r
e
m
e
n
t to
d
etec
t p
o
r
n
ad
d
ictio
n
a
m
o
n
g
teen
a
g
er
s
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
E
lectr
o
en
ce
p
h
alo
g
r
ap
h
y
(
E
E
G)
is
m
ad
e
o
f
e
lectr
o
d
es
an
d
it
m
ea
s
u
r
es
th
e
b
r
ain
ac
tiv
iti
es
f
r
o
m
th
e
s
ca
lp
.
B
r
ain
h
as
1
0
0
b
illi
o
n
n
eu
r
o
n
s
a
n
d
th
e
in
f
o
r
m
at
io
n
ar
e
p
ass
ed
f
r
o
m
o
n
e
n
e
u
r
o
n
to
t
h
e
o
th
er
t
h
r
o
u
g
h
t
h
e
f
ir
in
g
o
f
t
h
e
n
e
u
r
o
n
s
.
T
h
e
el
ec
tr
o
d
es
in
E
E
G
m
ea
s
u
r
e
ch
an
g
e
s
i
n
t
h
e
elec
tr
ical
p
o
ten
t
ial
o
f
t
h
e
n
e
u
r
o
n
s
.
Fig
u
r
e
1
s
h
o
w
s
t
h
e
in
ter
n
ati
o
n
al
1
0
-
2
0
s
y
s
te
m
o
f
elec
tr
o
d
e
p
lace
m
en
t
t
h
at
ar
e
co
m
m
o
n
l
y
u
s
ed
w
h
e
n
an
al
y
s
i
n
g
b
r
ain
w
a
v
es.
I
t
b
r
o
ad
ly
d
escr
ib
ed
th
e
lo
ca
tio
n
o
f
elec
tr
o
d
es
at
th
e
u
n
iq
u
e
in
te
r
v
als
alo
n
g
s
id
e
th
e
h
ea
d
.
E
v
er
y
elec
tr
o
d
e
n
o
d
e
h
as
a
letter
to
d
is
co
v
er
th
e
lo
b
e
,
alo
n
g
w
i
th
v
a
lu
ab
le
n
u
m
b
er
o
r
an
o
th
er
letter
to
p
er
ce
iv
e
th
e
h
e
m
i
s
p
h
er
ic
r
e
g
i
o
n
o
f
e
ith
er
th
e
r
ig
h
t
an
d
le
f
t
s
id
e
o
f
t
h
e
s
ca
lp
[
1
3
]
.
T
h
e
elec
tr
o
d
es
ar
e
p
lace
d
at
s
p
ec
if
ic
d
is
ta
n
ce
f
r
o
m
ea
c
h
o
th
er
.
T
h
e
o
d
d
n
u
m
b
er
s
ar
e
r
ec
o
r
d
in
g
ac
tiv
i
t
y
f
r
o
m
th
e
le
f
t
s
id
e
an
d
th
e
ev
e
n
n
u
m
b
er
s
ar
e
r
ec
o
r
d
in
g
ac
tiv
it
y
f
r
o
m
t
h
e
r
ig
h
t
s
id
e.
Fo
r
th
e
ce
n
tr
e
o
r
m
id
d
le
lin
e,
it
is
d
en
o
ted
as
Z
.
Fp
m
ea
n
s
f
r
o
n
tal
p
o
lar
an
d
F3
al
s
o
is
a
f
r
o
n
tal
p
o
lar
elec
tr
o
d
e.
C
3
it
is
i
n
t
h
e
ce
n
tr
al
lo
ca
tio
n
w
h
i
ch
is
lo
ca
ted
at
th
e
ce
n
tr
e
li
n
e.
Me
a
n
w
h
ile,
P
3
i
s
r
ec
o
r
d
in
g
f
r
o
m
t
h
e
p
ar
ietal
r
eg
io
n
an
d
la
s
tl
y
,
O
is
r
ec
o
r
d
in
g
t
h
e
o
cc
ip
ital
r
eg
io
n
.
Fig
u
r
e
1
.
T
h
e
in
ter
n
atio
n
al
1
0
-
2
0
elec
tr
o
d
e
p
lace
m
e
n
t s
y
s
te
m
A
lt
h
o
u
g
h
t
h
e
b
r
ain
w
a
v
e
s
i
g
n
als
ar
e
lo
w
f
r
eq
u
en
c
ies
(
b
et
wee
n
0
.
1
h
z
to
5
0
h
z)
,
t
h
e
y
ar
e
n
o
r
m
all
y
ca
ter
g
o
r
ized
in
to
f
iv
e
b
an
d
s
o
f
d
elta,
th
eta,
ap
la,
b
eta
an
d
g
a
m
m
a
as
d
escr
ib
ed
in
T
ab
le
1
.
I
n
ter
esti
n
g
l
y
ea
c
h
b
an
d
in
d
icate
ce
r
tain
f
u
n
ctio
n
alit
y
o
f
t
h
e
b
r
ain
s
an
d
n
o
r
m
a
l
l
y
in
d
icate
a
n
ac
ti
v
atio
n
o
f
th
e
p
ar
t
o
f
th
e
b
r
ain
clo
s
e
to
th
e
s
ca
lp
r
eg
io
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
16
,
No
.
2
,
No
v
e
m
b
er
2
0
1
9
:
9
6
4
-
9
7
1
966
T
ab
le
1
.
T
h
e
B
r
ain
W
av
e
Fre
q
u
en
cie
s
C
ate
g
o
r
ie
s
C
a
t
e
g
o
r
i
e
s
(
W
a
v
e
t
y
p
e
)
W
a
v
e
s
F
r
e
q
u
e
n
c
y
(
H
z
)
F
u
n
c
t
i
o
n
s
D
e
l
t
a
0
.
1
–
3
I
n
st
i
n
c
t
:
S
u
r
v
i
v
a
l
,
D
e
e
p
S
l
e
e
p
,
C
o
ma,
D
r
e
a
mi
n
g
T
h
e
t
a
4
–
7
Emo
t
i
o
n
:
F
e
e
l
i
n
g
s,
D
r
e
a
ms,
D
r
o
w
s
y
,
I
d
e
a
-
l
i
n
g
A
l
p
h
a
8
–
12
C
o
n
sc
i
o
u
s
n
e
ss:
A
w
a
r
e
n
e
ss o
f
b
o
d
y
,
I
n
t
e
g
r
a
t
i
o
n
o
f
F
e
e
l
i
n
g
s,
R
e
l
a
x
B
e
t
a
1
3
–
40
C
o
n
c
e
n
t
r
a
t
i
o
n
:
T
h
i
n
k
i
n
g
,
P
e
r
c
e
p
t
i
o
n
,
M
e
n
t
a
l
A
c
t
i
v
i
t
y
,
A
l
e
r
t
u
G
a
mm
a
4
0
–
44
S
p
i
r
i
t
u
a
l
:
C
o
g
n
i
t
i
v
e
D
e
c
l
i
n
e
,
S
h
o
r
t
-
T
e
r
m M
e
mo
r
y
,
Q
u
i
e
t
,
C
o
n
sci
o
u
s
n
e
ss
P
s
y
c
h
o
lo
g
ica
l
f
in
d
i
n
g
s
o
n
d
etec
tin
g
p
o
r
n
ad
d
ictio
n
i
n
v
o
lv
e
s
q
u
es
tio
n
air
e
[
1
4
]
f
o
r
ad
u
lt
s
w
h
ile
f
o
r
k
id
s
,
t
h
e
p
ar
en
ts
an
d
teac
h
er
s
w
ill
b
e
i
n
v
o
l
v
ed
w
it
h
th
e
q
u
esti
o
n
air
e.
Su
c
h
s
ce
n
ar
io
ca
n
p
o
s
e
a
s
a
ch
al
len
g
e
esp
ec
iall
y
i
f
p
ar
en
ts
h
a
v
e
th
e
ten
d
en
c
y
to
s
u
p
p
r
ess
t
h
eir
c
h
ild
r
en
s
itu
at
io
n
[
1
5
]
.
T
h
er
e
h
as
b
ee
n
s
tu
d
ie
s
to
an
al
y
s
e
p
o
r
n
ad
d
ictio
n
u
s
i
n
g
t
h
e
b
r
ain
w
a
v
e
p
atter
n
s
[
1
6
,
1
7
]
.
Ho
w
e
v
er
,
s
u
c
h
s
tu
d
y
o
n
l
y
c
o
n
s
id
er
s
t
h
e
p
o
w
er
d
is
tr
ib
u
tio
n
o
f
t
h
e
f
r
o
n
t
al
ar
ea
s
d
u
r
in
g
t
h
e
e
y
es
o
p
en
a
n
d
e
y
es
clo
s
e
an
d
co
m
p
ar
i
s
o
n
w
it
h
lear
n
in
g
d
is
ab
ili
ties
[
1
8
]
.
I
n
th
is
p
r
o
j
ec
t
w
e
lo
o
k
i
n
to
o
th
er
ar
tifif
ia
l
i
n
telli
g
e
n
ce
(
A
I
)
to
o
ls
u
s
i
n
g
m
ac
h
i
n
e
lear
n
in
g
to
an
a
l
y
s
e
t
h
e
b
r
ain
w
a
v
e
p
atter
n
at
e
y
es o
p
en
an
d
e
y
e
s
clo
s
e
an
d
t
h
is
i
s
th
e
in
itial c
o
n
d
it
io
n
o
f
t
h
e
b
r
ain
.
3.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
Fig
u
r
e
2
s
h
o
w
s
t
h
e
f
lo
w
o
f
th
e
p
r
o
j
ec
t
th
at
co
n
s
i
s
ts
o
f
d
ata
co
llectio
n
s
,
f
ea
t
u
r
e
ex
tr
ac
tio
n
s
a
n
d
class
i
f
icatio
n
s
.
I
n
t
h
i
s
p
r
o
j
ec
t
,
w
e
o
n
l
y
f
o
c
u
s
o
n
t
h
e
c
lass
i
f
icatio
n
s
u
s
in
g
A
I
tec
h
n
iq
u
es
to
u
n
d
er
s
ta
n
d
t
h
e
r
o
b
u
s
tn
es
s
o
f
t
h
e
cla
s
s
i
f
icati
o
n
s
b
ased
o
n
t
h
r
ee
class
i
f
ie
r
s
n
a
m
el
y
th
e
M
u
lti
L
a
y
er
P
er
ce
p
tr
o
n
(
ML
P
)
,
Naiv
e
B
a
y
es
ian
(
NB
)
an
d
R
a
n
d
o
m
Fo
r
est (
R
F).
Fig
u
r
e
2
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
f
lo
w
c
h
ar
t
3
.
1
.
D
a
t
a
C
o
llect
io
n
T
h
e
d
ata
co
llectio
n
w
as
p
r
ep
ar
ed
b
y
t
h
e
I
n
ter
n
atio
n
a
l
I
s
la
m
ic
U
n
iv
er
s
it
y
Ma
la
y
s
ia
(
I
I
U
M)
r
esear
ch
er
s
u
s
in
g
t
h
e
elec
tr
o
en
ce
p
h
alo
g
r
a
m
(
E
E
G)
d
ev
ice
f
o
r
1
4
I
n
d
o
n
esian
teen
a
g
er
s
[
1
7
]
.
T
h
er
e
ar
e
a
to
tal
o
f
1
4
p
ar
ticip
an
ts
w
i
th
ag
e
r
an
g
i
n
g
b
et
w
ee
n
9
to
1
3
y
ea
r
s
o
ld
E
E
G
d
ata
w
as
co
lle
cted
b
u
t
o
n
ly
1
1
p
ar
ticip
an
ts
d
ata
w
er
e
u
s
ed
in
th
is
s
tu
d
y
.
T
h
e
E
E
G
d
ata
r
ec
eiv
ed
in
a
f
o
r
m
o
f
s
p
r
ea
d
s
h
ee
t
ex
ce
l
f
i
le
an
d
th
e
p
ar
ticip
an
ts
ad
d
ictio
n
s
tat
u
s
ar
e
alr
ea
d
y
lab
elled
b
ased
o
n
t
h
e
p
s
y
c
h
o
lo
g
ical
q
u
es
tio
n
n
air
e
an
s
w
er
s
.
T
h
e
E
E
G
r
aw
d
ata
ar
e
p
r
e
-
p
r
o
ce
s
s
ed
to
r
e
m
o
v
e
u
n
w
a
n
ted
ar
tef
ac
ts
s
u
c
h
as b
ac
k
g
r
o
u
n
d
n
o
i
s
e
an
d
m
o
v
e
m
e
n
t
d
ata.
T
h
en
,
th
e
Me
l
Fre
q
u
en
c
y
C
ep
s
tr
al
C
o
e
f
f
ic
ien
t
(
MF
C
C
)
f
ea
tu
r
e
ex
tr
ac
tio
n
m
e
th
o
d
is
ap
p
lied
to
g
et
th
e
r
elev
an
t
f
ea
t
u
r
es.
T
h
e
MFC
C
f
ea
t
u
r
es
ar
e
w
id
el
y
u
s
ed
in
ex
tr
ac
ti
n
g
r
elev
a
n
t
f
ea
tu
r
es
in
s
p
ee
ch
t
h
a
t
ap
p
r
o
x
im
a
tes
t
h
e
h
u
m
an
au
d
it
o
r
y
s
y
s
te
m
.
I
t
h
ad
b
ee
n
u
s
ed
i
n
p
r
ev
io
u
s
s
t
u
d
ies
[
1
7
,
1
8
]
an
d
th
e
e
x
p
er
i
m
e
n
tal
r
esu
lt
s
s
h
o
w
p
o
ten
tial o
f
u
s
i
n
g
s
u
c
h
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
e
th
o
d
to
ex
tr
ac
t r
elev
an
t
f
ea
tu
r
e
s
f
r
o
m
b
r
ain
s
ig
n
al
s
.
T
h
e
d
ata
co
n
s
is
ts
o
f
7
ad
d
icts
an
d
4
n
o
n
-
ad
d
icts
an
d
f
o
r
ea
ch
p
ar
ticip
an
t
h
a
s
e
y
e
s
clo
s
e
an
d
e
y
es
o
p
en
d
ata.
T
h
er
e
ar
e
5
b
an
d
wav
es
f
o
r
t
h
e
e
y
es
o
p
en
an
d
e
y
es
clo
s
e
d
ata,
n
a
m
el
y
;
alp
h
a,
t
h
eta,
g
a
m
m
a,
d
elta
an
d
b
eta.
E
ac
h
b
an
d
w
a
v
e
h
a
v
e
b
ee
n
d
iv
id
ed
in
to
2
b
asis
f
u
n
ct
io
n
o
f
Vale
n
ce
an
d
A
r
o
u
s
al
d
ata.
T
h
er
e
ar
e
8
8
0
in
s
tan
ce
s
i
n
v
o
lv
e
f
o
r
a
p
a
r
ticip
an
t a
n
d
all
o
f
t
h
e
d
ata
r
ec
eiv
ed
is
i
n
n
u
m
er
ical
v
al
u
es.
3
.
2
.
M
ul
t
i
-
la
y
er
P
er
ce
ptr
o
n
Fo
r
s
i
m
p
licit
y
,
o
n
l
y
t
w
o
a
n
d
th
r
ee
la
y
er
m
u
lti
-
la
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
w
er
e
u
s
ed
w
it
h
th
e
s
a
m
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
.
Star
ti
n
g
f
r
o
m
5
0
n
e
u
r
o
n
s
,
t
h
e
n
u
m
b
er
o
f
te
s
ted
n
e
u
r
o
n
s
w
as
i
n
cr
ea
s
ed
to
7
2
,
1
0
0
,
2
5
0
S
T
A
R
T
D
A
T
A
C
O
L
L
E
C
T
IO
N
F
E
A
T
U
R
E
E
X
T
R
A
C
T
I
O
N
M
F
C
C
C
L
A
S
SI
FI
C
A
T
I
O
N
M
L
P
N
A
Ï
V
E
B
A
Y
E
S
R
A
N
DO
M
FO
R
E
ST
R
E
S
U
L
T
S
E
N
D
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
N
eu
r
o
-
P
h
ysio
lo
g
ica
l P
o
r
n
A
d
d
ictio
n
Dete
ctio
n
u
s
in
g
Ma
c
h
i
n
e
Lea
r
n
in
g
…(
N
o
r
h
a
s
lin
d
a
K
a
ma
r
u
d
d
in
)
967
n
eu
r
o
n
s
,
as
t
h
er
e
ar
e
f
ea
tu
r
e
s
in
o
u
r
d
ata
s
et
alo
n
g
w
it
h
1
0
0
0
m
ax
iter
at
io
n
s
.
O
n
ce
th
e
m
o
d
el
is
cr
ea
ted
,
th
e
tr
ain
in
g
d
ata
is
f
itted
to
th
e
m
o
d
el
[
1
9
,
2
0
]
.
E
ac
h
in
s
tan
ce
s
o
f
th
e
d
ata
w
il
l b
e
u
s
ed
to
tr
ain
t
h
e
n
e
t
w
o
r
k
f
o
r
p
o
r
n
ad
d
icts
o
r
o
th
er
w
i
s
e.
3
.
3
.
N
a
ïv
e
B
a
y
es
T
h
e
d
ataset
co
n
tain
s
3
clas
s
es
o
f
8
8
0
in
s
ta
n
ce
s
ea
ch
,
wh
er
e
ea
ch
cla
s
s
r
e
f
er
s
to
a
t
y
p
e
lab
el.
T
h
e
Gau
s
s
ian
NB
a
n
d
B
er
n
o
u
lliNB
m
o
d
els
ar
e
a
v
ailab
le
in
t
h
e
Sc
k
it
-
lear
n
L
ib
r
ar
y
[
2
1
]
.
Gau
s
s
ia
n
Na
ïv
e
B
ay
e
s
is
u
s
ed
i
n
ca
s
es
w
h
e
n
all
o
f
th
e
f
ea
t
u
r
es
ar
e
co
n
ti
n
u
o
u
s
.
Me
an
w
h
ile,
B
er
n
o
u
lli
N
aïv
e
B
a
y
es
a
s
s
u
m
es
th
at
all
f
ea
tu
r
e
s
ar
e
b
in
ar
y
s
u
ch
th
at
i
t
tak
e
s
o
n
l
y
t
w
o
v
al
u
es
s
u
c
h
as
0
to
r
ep
r
esen
ts
as
n
o
n
-
ad
d
icts
an
d
1
to
r
ep
r
esen
ts
a
s
ad
d
icts
.
T
h
e
f
ea
tu
r
e
clas
s
n
ee
d
s
a
lab
el,
w
h
ic
h
i
s
d
en
o
ted
as
t
h
e
―
lab
el‖
cl
ass
.
I
f
t
h
e
f
ea
t
u
r
e
v
alu
e
s
ar
e
n
u
m
er
ical,
"
b
in
"
is
n
ee
d
ed
to
r
e
d
u
ce
th
e
n
u
m
b
er
o
f
p
o
s
s
ib
le
f
ea
tu
r
e
v
al
u
es
.
T
h
e
f
ir
s
t
r
o
w
d
o
es
n
o
t
n
ee
d
to
―
b
in
‖
b
ec
au
s
e
it
is
a
c
lass
r
o
w
,
s
o
b
in
_
w
id
th
w
i
ll
b
e
s
et
to
No
n
e.
T
w
o
f
ea
tu
r
es
w
i
ll
b
e
cr
ea
ted
w
h
er
e
o
n
e
f
ea
t
u
r
e
class
co
n
tai
n
s
th
e
lab
el
f
o
r
th
e
Naiv
e
B
a
y
es
class
‗
Vale
n
ce
‘
a
n
d
o
n
e
th
e
lab
el
f
o
r
th
e
class
‗
A
r
o
u
s
al
‘
.
3.
4
.
R
a
nd
o
m
F
o
re
s
t
Dee
p
tr
ee
s
w
er
e
co
n
s
tr
u
cted
w
it
h
a
m
in
i
m
u
m
n
u
m
b
er
o
f
tr
ain
i
n
g
r
o
w
s
at
ea
ch
n
o
d
e
o
f
1
.
Sa
m
p
les
o
f
th
e
tr
ain
i
n
g
d
ataset
w
er
e
cr
ea
t
ed
w
ith
t
h
e
s
a
m
e
s
ize
as
th
e
o
r
ig
in
a
l
d
ataset,
w
h
ic
h
is
a
d
ef
au
lt
ex
p
ec
tatio
n
f
o
r
th
e
R
a
n
d
o
m
Fo
r
est
alg
o
r
it
h
m
[
2
2
]
.
T
h
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
co
n
s
id
er
ed
at
ea
ch
s
p
lit
p
o
i
n
t
w
a
s
s
et
i
n
to
‗
au
to
‘
,
‗
s
q
r
t
‘
an
d
‗
lo
g
2
‘
.
A
s
u
ite
o
f
3
d
if
f
er
en
t
n
u
m
b
er
s
o
f
tr
ee
s
w
er
e
ev
a
lu
ated
f
o
r
co
m
p
ar
is
o
n
,
s
h
o
w
in
g
th
e
in
cr
ea
s
i
n
g
s
k
il
l
as
m
o
r
e
tr
ee
s
ar
e
ad
d
ed
.
T
h
is
p
ar
am
eter
d
ef
i
n
es
th
e
n
u
m
b
er
o
f
tr
ee
s
in
th
e
r
an
d
o
m
f
o
r
est.
I
t
w
ill
s
tar
t
w
it
h
n
_
est
i
m
a
to
r
=
1
0
0
0
to
s
ee
h
o
w
th
e
al
g
o
r
ith
m
p
er
f
o
r
m
s
.
3.
5
.
K
-
f
o
ld
Va
lid
a
t
io
n
A
ll
clas
s
i
f
icatio
n
m
o
d
els
i
n
s
i
d
e
th
e
p
r
esen
t
w
o
r
k
h
ad
b
ee
n
tr
ain
ed
an
d
te
s
ted
w
it
h
E
E
G
d
ata
af
ter
w
h
ic
h
it
i
s
co
n
f
ir
m
ed
u
s
i
n
g
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
K
-
f
o
ld
cr
o
s
s
v
alid
atio
n
i
s
a
tech
n
i
q
u
e
th
at
co
m
m
o
n
l
y
u
s
ed
to
co
m
p
ar
e
th
e
p
er
f
o
r
m
a
n
ce
b
et
w
ee
n
t
w
o
c
lass
if
ier
s
a
n
d
to
ev
al
u
ates
a
cla
s
s
i
f
ier
‘
s
p
e
r
f
o
r
m
an
ce
f
r
o
m
t
h
e
ex
tr
ac
ted
d
ata
[
2
3
]
.
I
t
h
as
th
e
b
en
ef
it
o
f
t
h
e
u
s
e
o
f
all
i
n
s
t
a
n
ce
s
i
n
an
e
x
tr
ac
ted
d
ata
f
o
r
eith
er
tr
ain
i
n
g
o
r
test
i
n
g
,
w
h
er
ei
n
e
v
er
y
in
s
ta
n
c
e
is
e
m
p
lo
y
ed
f
o
r
v
a
lid
atio
n
ex
ac
tl
y
o
n
ce
.
Fo
r
th
is
p
r
o
j
ec
t,
o
n
l
y
tes
tin
g
p
h
ase
w
il
l b
e
d
o
n
e.
T
h
e
tw
o
p
h
a
s
es r
ep
r
esen
t th
e
K
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
Fo
r
th
i
s
p
r
o
j
ec
t,
th
er
e
w
ill
b
e
5
-
f
o
ld
cr
o
s
s
v
alid
atio
n
th
a
t
ea
ch
d
ata
s
et
co
n
s
is
ts
o
f
8
0
:
2
0
test
in
g
.
T
h
e
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
will
b
e
d
iv
id
ed
in
to
k
s
u
b
s
ets
w
h
ic
h
(
k
-
1
)
s
u
b
s
e
t
is
u
s
ed
f
o
r
tr
ain
i
n
g
p
h
ases
a
n
d
o
n
e
r
em
a
in
i
n
g
s
u
b
s
et
f
o
r
test
i
n
g
p
h
a
s
es.
T
o
test
all
th
e
class
if
ier
s
,
k
t
i
m
es
o
f
ea
c
h
s
u
b
s
e
t
p
r
o
ce
s
s
is
r
ep
ea
ted
.
C
las
s
i
f
ier
p
er
f
o
r
m
an
ce
w
a
s
m
ea
s
u
r
e
f
o
r
th
e
ir
ac
cu
r
ac
y
a
s
f
o
llo
w
s
:
A
cc
u
r
ac
y
=
x
1
0
0
4.
P
RE
L
I
M
ANAR
Y
E
XP
E
RI
M
E
NT
T
h
is
s
ec
tio
n
f
o
cu
s
ed
o
n
t
h
e
d
ata
m
i
n
in
g
e
x
p
er
ien
ce
u
s
i
n
g
P
y
th
o
n
an
d
W
ek
a
as
to
o
ls
t
h
at
ar
e
w
id
el
y
u
s
ed
in
f
ield
o
f
d
ata
an
a
l
y
tic
s
[
2
4
]
.
T
ab
le
2
.
ML
P
A
cc
u
r
ac
y
C
o
m
p
ar
is
o
n
b
et
w
ee
n
W
E
K
A
an
d
P
y
th
o
n
f
o
r
S
u
b
j
ec
t1
W
a
v
e
F
r
e
q
u
e
n
c
i
e
s
Ey
e
s Op
e
n
Ey
e
s C
l
o
se
W
E
K
A
(
%)
P
y
t
h
o
n
(
%)
D
i
f
f
e
r
e
n
c
e
W
E
K
A
(
%)
P
y
t
h
o
n
(
%)
D
i
f
f
e
r
e
n
c
e
A
l
p
h
a
71
76
+5
82
82
-
B
e
t
a
61
65
+4
69
69
-
D
e
l
t
a
74
74
-
70
73
+3
G
a
mm
a
70
70
-
65
66
+1
T
h
e
t
a
68
70
+2
74
74
-
T
h
e
ex
p
er
im
e
n
t
s
w
er
e
p
er
f
o
r
m
ed
u
s
i
n
g
a
to
o
l
n
a
m
ed
W
ek
a
3
.
8
.
3
.
W
ek
a
3
.
8
.
3
is
a
to
o
l
w
h
er
e
p
r
e
-
p
r
o
ce
s
s
in
g
d
ata
ca
n
b
e
m
ad
e.
W
ek
a
is
a
b
u
ilt
-
i
n
f
ea
t
u
r
e
t
h
at
r
eq
u
ir
e
n
o
p
r
o
g
r
a
m
m
i
n
g
a
n
d
co
d
in
g
k
n
o
w
led
g
e.
C
las
s
i
f
icatio
n
al
s
o
ca
n
b
e
co
n
d
u
cted
u
s
i
n
g
th
is
to
o
l.
T
h
e
r
esu
lt
s
o
f
W
e
k
a
w
ill
b
e
co
m
p
ar
ed
w
it
h
An
ac
o
n
d
a
2
.
7
(
f
o
r
P
y
th
o
n
)
.
Fo
r
s
tar
t
-
u
p
ex
p
er
i
m
e
n
ts
,
s
ets
o
f
C
SV
d
ata
is
lo
ad
ed
in
W
E
K
A
an
d
p
er
ce
n
tag
e
s
p
lit
w
a
s
s
e
t
to
8
0
%.
T
h
e
Mu
lti
-
L
a
y
er
P
e
r
ce
p
tr
o
n
class
i
f
ier
is
s
elec
ted
f
o
r
ac
cu
r
ac
y
co
m
p
ar
is
o
n
b
e
t
w
ee
n
W
E
K
A
a
n
d
P
y
t
h
o
n
.
T
h
e
co
m
p
ar
is
o
n
r
es
u
l
ts
o
f
W
E
K
A
an
d
P
y
t
h
o
n
is
p
r
esen
ted
i
n
T
ab
le
2
.
I
n
b
o
th
ca
s
es,
th
e
r
es
u
lt
s
ar
e
v
er
y
clo
s
e
w
i
th
m
ax
i
m
u
m
d
i
f
f
er
en
ce
o
f
5
%
f
o
r
e
x
p
er
i
m
e
n
t
u
s
i
n
g
P
y
t
h
o
n
i
n
A
lp
h
a
w
a
v
e
f
r
eq
u
en
cies
f
o
r
e
y
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
16
,
No
.
2
,
No
v
e
m
b
er
2
0
1
9
:
9
6
4
-
9
7
1
968
o
p
en
.
I
t
is
also
o
b
s
er
v
ed
th
at
P
y
t
h
o
n
s
co
r
e
s
li
g
h
tl
y
b
etter
ac
cu
r
ac
y
i
n
e
y
e
s
clo
s
e
ex
p
er
i
m
en
t
w
it
h
3
%
b
etter
p
er
f
o
r
m
a
n
ce
u
s
i
n
g
d
elta
w
a
v
es.
Hen
ce
,
P
y
t
h
o
n
i
m
p
le
m
e
n
t
atio
n
w
ill
b
e
u
s
ed
f
o
r
th
e
f
u
r
th
er
an
al
y
s
is
s
i
n
ce
P
y
t
h
o
n
m
a
n
ag
ed
to
y
ield
b
ette
r
p
er
f
o
r
m
a
n
ce
.
5.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
I
n
t
h
is
s
ec
tio
n
w
il
l
s
h
o
w
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
t
h
r
ee
d
i
f
f
er
en
t
clas
s
i
f
ier
s
b
a
s
ed
o
n
P
y
t
h
o
n
a
s
t
h
e
to
o
ls
.
T
h
e
r
esu
lts
ar
e
an
al
y
s
e
d
an
d
co
m
p
ar
ed
to
s
ee
th
e
p
er
f
o
r
m
an
ce
o
f
ea
ch
m
ac
h
i
n
e
lear
n
in
g
cla
s
s
i
f
ier
s
.
Fro
m
th
e
p
r
ev
io
u
s
s
t
u
d
ies
o
n
an
al
y
s
i
n
g
th
e
E
E
G
d
ata,
o
n
l
y
th
e
r
esti
n
g
s
tate
o
f
e
y
e
o
p
en
an
d
e
y
e
clo
s
e
d
ata
ar
e
u
s
ed
b
ec
au
s
e
it is
s
u
f
f
icie
n
t to
p
r
o
v
id
e
th
e
in
itial scr
ee
n
i
n
g
o
f
t
h
e
s
u
b
j
ec
ts
[
2
5
,
2
6
]
.
5
.
1
.
M
ul
t
i
-
la
y
er
P
er
ce
ptr
o
n Ac
cura
cy
Resul
t
Fo
r
Mu
lti
-
L
a
y
er
P
er
ce
p
tr
o
n
(
ML
P
)
,
th
e
ex
p
er
i
m
en
ts
w
er
e
f
o
cu
s
ed
o
n
d
eter
m
in
in
g
th
e
o
p
tim
al
p
ar
am
eter
s
w
h
ic
h
h
a
v
e
th
e
s
a
m
e
n
u
m
b
er
o
f
lear
n
i
n
g
ep
o
ch
s
b
u
t
d
i
f
f
er
en
t
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
a
n
d
th
e
ti
m
e
co
m
p
u
tatio
n
al
ta
k
en
.
T
ab
les
3
s
h
o
w
s
t
h
e
r
es
u
lt
s
o
f
u
s
i
n
g
alp
h
a
an
d
g
a
m
m
a
w
av
e
s
r
esp
ec
tiv
el
y
f
o
r
e
y
es
o
p
en
an
d
e
y
es c
lo
s
e
e
x
p
er
i
m
e
n
ts
.
Ta
b
le
3
.
ML
P
E
x
p
er
im
e
n
tal
R
esu
lt
s
*
A
C
C
=
A
c
c
u
r
a
c
y
,
C
T
=
C
o
m
p
u
t
a
t
i
o
n
T
i
me
Fro
m
th
e
o
b
s
er
v
atio
n
s
,
it
clea
r
l
y
s
h
o
w
th
a
t
A
lp
h
a
w
av
e
s
y
i
eld
ed
h
ig
h
est
ac
c
u
r
ac
y
co
m
p
ar
ed
to
all
th
e
b
an
d
w
a
v
e
s
an
d
Ga
m
m
a
h
as
t
h
e
lo
w
e
s
t.
A
l
m
o
s
t
all
r
es
u
lts
s
ee
m
s
to
b
e
co
n
s
i
s
te
n
t
w
i
th
ac
c
u
r
ac
y
r
a
n
g
in
g
f
r
o
m
8
8
%
to
8
9
%
f
o
r
b
o
th
e
y
es
o
p
en
o
r
e
y
e
s
clo
s
e
co
n
d
itio
n
s
.
I
t
is
i
n
ter
es
tin
g
to
n
o
te
t
h
a
t
as
t
h
e
n
u
m
b
er
o
f
n
eu
r
o
n
s
i
n
cr
ea
s
es,
t
h
e
co
m
p
u
t
io
n
w
ill
al
s
o
in
cr
ea
s
e
r
e
s
u
lt
in
g
in
h
i
g
h
er
co
m
p
u
ta
tio
n
ti
m
e.
T
h
u
s
,
a
t
w
o
-
la
y
er
ML
P
is
s
u
f
f
icie
n
t
to
p
r
o
d
u
ce
a
r
ea
s
o
n
ab
l
y
co
n
s
i
s
ta
n
t
g
o
o
d
r
esu
lt
s
an
d
r
eq
u
ir
es
les
s
th
a
n
8
0
s
o
f
co
m
p
u
tatio
n
ti
m
e.
5
.
2
.
N
a
ïv
e
B
a
y
es Ac
cura
cy
Resul
t
Fo
r
Naïv
e
B
a
y
es,
t
h
e
ex
p
er
i
m
en
ts
w
er
e
f
o
cu
s
ed
o
n
d
eter
m
i
n
in
g
t
h
e
o
p
ti
m
al
p
ar
a
m
e
ter
s
w
h
ic
h
h
a
v
e
th
e
s
a
m
e
n
u
m
b
er
o
f
lear
n
i
n
g
ep
o
ch
s
b
u
t
d
i
f
f
er
e
n
t
m
o
d
el
o
f
Naï
v
e
B
a
y
es.
Ga
u
s
s
ia
n
an
d
B
er
n
o
u
lli
Naï
v
e
B
ay
e
s
ar
e
u
s
ed
f
o
r
th
i
s
ex
p
e
r
i
m
en
tal
s
t
u
d
y
.
T
ab
le
4
s
h
o
w
s
th
e
r
es
u
lt
s
o
f
th
e
Ga
u
s
s
ia
n
Naïv
e
B
a
y
e
s
an
d
B
er
n
o
u
lli Na
ï
v
e
B
a
y
es
f
o
r
e
y
e
s
o
p
en
an
d
e
y
es c
lo
s
e
co
n
d
itio
n
s
r
esp
ec
ti
v
el
y
.
T
ab
le
4
.
Naïv
e
B
ay
es E
x
p
er
im
en
tal
R
e
s
u
l
t
*
A
C
C
=
A
c
c
u
r
a
c
y
,
C
T
=
C
o
m
p
u
t
a
t
i
o
n
T
i
me
I
n
b
o
th
ca
s
es
th
e
r
es
u
lt
o
f
t
h
e
e
y
es
o
p
en
o
r
e
y
es
c
lo
s
e
f
o
r
alp
h
a
w
a
v
es
s
ee
m
s
to
p
r
o
d
u
ce
s
t
h
e
b
est
p
er
f
o
r
m
a
n
ce
.
T
h
is
is
co
n
s
is
te
n
t
w
it
h
t
h
e
p
r
ev
io
u
s
r
es
u
lt
s
u
s
i
n
g
M
L
P
.
C
o
m
p
u
tatio
n
ti
m
e
f
o
r
all
ca
s
es
s
ee
m
s
to
b
e
b
elo
w
1
0
s
ex
ce
p
t
f
o
r
t
h
et
a
w
a
v
es
f
o
r
e
y
es
clo
s
e
co
n
d
i
tio
n
.
Mo
r
eo
v
er
,
th
e
r
es
u
lt
s
f
o
r
B
er
n
o
u
lli
Naï
v
e
B
ay
e
s
is
also
co
n
s
i
s
ten
t
w
i
th
t
h
e
b
est
ac
cu
r
ac
y
is
r
ec
o
r
d
ed
u
s
in
g
alp
h
a
w
av
e
s
w
it
h
ac
cu
r
ac
y
g
r
ea
ter
th
a
n
8
0
%
M
L
P
N
u
mb
e
r
o
f
N
e
u
r
o
n
s
A
l
p
h
a
W
a
v
e
G
a
mm
a
W
a
v
e
Ey
e
s Op
e
n
Ey
e
s c
l
o
se
Ey
e
s Op
e
n
Ey
e
s c
l
o
se
A
c
c
(
%)
C
T
(
S
)
A
c
c
(
%)
C
T
(
S
)
A
c
c
(
%)
C
T
(
S
)
A
c
c
(
%)
C
T
(
S
)
5
0
,
5
0
88
7
8
.
1
1
89
5
8
.
2
5
67
3
0
.
6
3
55
3
6
.
7
3
7
2
,
7
2
88
8
6
.
3
5
88
5
3
.
1
9
67
4
1
.
5
5
56
3
7
.
0
3
1
0
0
,
1
0
0
88
8
6
.
1
0
89
6
2
.
2
5
66
4
7
.
9
2
56
4
0
.
2
6
2
5
0
,
2
5
0
88
1
8
8
.
7
9
88
1
4
0
.
6
8
70
1
1
3
.
9
4
57
1
0
4
.
4
7
5
0
,
5
0
,
5
0
88
6
4
.
3
8
88
8
9
.
5
7
68
3
4
.
5
1
56
3
2
.
7
6
7
2
,
7
2
,
7
2
88
6
9
.
0
8
89
5
3
.
5
8
69
4
3
.
3
9
57
3
4
.
1
2
1
0
0
,
1
0
0
,
1
0
0
88
8
1
.
9
1
89
6
4
.
0
6
71
4
9
.
9
3
57
4
8
.
5
3
2
5
0
,
2
5
0
,
2
5
0
88
2
3
6
.
3
6
88
1
9
1
.
6
4
70
1
6
2
.
1
2
58
1
3
7
.
9
3
B
a
n
d
G
a
u
ssi
a
n
N
a
ï
v
e
B
a
y
e
s
B
e
r
n
o
u
l
l
i
N
a
ï
v
e
B
a
y
e
s
Ey
e
s Op
e
n
Ey
e
s c
l
o
se
Ey
e
s Op
e
n
Ey
e
s c
l
o
se
A
c
c
(
%)
C
T
(
S
)
A
c
c
(
%)
C
T
(
S
)
A
c
c
(
%)
C
T
(
S
)
A
c
c
(
%)
C
T
(
S
)
A
l
p
h
a
84
5
.
1
6
86
6
.
3
7
82
4
.
4
0
84
4
.
6
3
B
e
t
a
77
5
.
7
3
74
6
.
3
7
75
4
.
3
9
72
6
.
5
3
D
e
l
t
a
68
5
.
9
2
58
6
.
6
1
62
6
.
2
5
55
3
.
6
8
G
a
mm
a
64
7
.
5
0
57
6
.
9
3
64
4
.
2
4
55
3
.
6
6
T
h
e
t
a
62
8
.
7
2
66
1
6
.
4
0
62
4
.
4
8
64
3
.
7
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
N
eu
r
o
-
P
h
ysio
lo
g
ica
l P
o
r
n
A
d
d
ictio
n
Dete
ctio
n
u
s
in
g
Ma
c
h
i
n
e
Lea
r
n
in
g
…(
N
o
r
h
a
s
lin
d
a
K
a
ma
r
u
d
d
in
)
969
an
d
co
m
p
u
tatio
n
ti
m
e
i
s
le
s
s
th
an
7
s
ec
o
n
d
s
.
W
h
e
n
co
m
p
a
r
in
g
b
o
th
t
y
p
es
o
f
B
er
n
o
u
lli
a
n
d
Ga
u
s
s
ian
Naï
v
e
B
ay
e
s
class
if
ier
,
it
is
o
b
s
er
v
e
d
th
at
Gau
s
s
ia
n
Naï
v
e
B
a
y
es
g
iv
e
h
i
g
h
er
ac
c
u
r
ac
y
t
h
an
B
er
n
o
u
lli
Na
ïv
e
B
a
y
e
s
in
e
y
e
s
clo
s
e
co
n
d
itio
n
.
Hen
c
e,
f
r
o
m
th
is
o
b
s
er
v
atio
n
,
Gau
s
s
ian
Naï
v
e
B
a
y
e
s
m
o
d
el
is
m
o
r
e
f
av
o
u
r
ab
le
th
a
n
B
er
n
o
u
lli Na
ï
v
e
B
a
y
es c
la
s
s
i
f
i
er
.
5
.
3
.
R
a
nd
o
m
F
o
re
s
t
Acc
ura
cy
Resul
t
T
h
e
ex
p
er
i
m
e
n
ts
u
s
i
n
g
R
a
n
d
o
m
Fo
r
est
as
t
h
e
cla
s
s
i
f
ier
s
w
e
r
e
also
co
n
d
u
cted
.
T
h
e
p
ar
a
m
eter
s
t
h
at
h
ad
b
ee
n
v
ar
ied
f
o
r
t
h
e
e
x
p
er
i
m
e
n
ts
w
as
t
h
e
n
u
m
b
er
o
f
tr
e
es
in
t
h
e
f
o
r
est.
A
ll
o
t
h
er
p
ar
a
m
eter
s
w
er
e
s
et
to
th
e
s
tan
d
ar
d
v
al
u
es
o
f
f
er
ed
b
y
t
h
e
m
o
d
el.
T
h
e
n
u
m
b
er
s
o
f
tr
ee
s
w
er
e
v
ar
ied
to
1
0
an
d
th
e
p
ar
a
m
eter
f
o
r
m
ax
i
m
u
m
f
ea
t
u
r
es
w
a
s
te
s
te
d
w
it
h
d
i
f
f
er
en
t
f
ea
tu
r
es.
T
ab
le
5
,
6
an
d
7
s
h
o
w
t
h
e
r
es
u
lts
o
f
u
s
in
g
a
u
to
,
s
q
r
t
r
o
o
t
an
d
lo
g
2
s
ettin
g
s
r
esp
ec
tiv
el
y
f
o
r
ey
e
s
o
p
en
an
d
ey
es
clo
s
e
co
n
d
itio
n
s
f
o
r
d
if
f
er
en
t
w
av
e
s
.
I
t
ca
n
b
e
s
ee
n
t
h
at
alp
h
a
w
a
v
es
s
till
p
r
o
d
u
ce
th
e
b
est
p
er
f
o
r
m
a
n
c
e
o
f
ab
o
v
e
8
0
%
f
o
r
b
o
th
e
y
es
o
p
en
an
d
clo
s
e
co
n
d
itio
n
s
i
n
all
s
etti
n
g
s
.
I
t
is
also
n
o
ted
th
at
R
an
d
o
m
Fo
r
est
class
i
f
ier
r
eq
u
ir
es
lo
n
g
er
co
m
p
u
tat
io
n
ti
m
e
th
a
t
is
g
r
ea
ter
th
a
n
2
0
0
s
as c
o
m
p
ar
ed
t
o
Naïv
e
B
ay
e
s
an
d
M
L
P
class
i
f
ier
s
.
T
ab
le
5
.
R
an
d
o
m
Fo
r
est
‗
Au
to
‘
Setti
n
g
R
e
s
u
l
t
f
o
r
E
y
es Op
e
n
an
d
E
y
es C
lo
s
e
T
ab
le
6
.
R
an
d
o
m
Fo
r
est
‗
Sq
r
t
‘
Settin
g
R
e
s
u
lt
f
o
r
E
y
e
s
Op
en
an
d
E
y
es
C
lo
s
e
T
ab
le
7
.
R
an
d
o
m
Fo
r
est
‗
lo
g
2
‘
Setti
n
g
R
e
s
u
l
t
f
o
r
E
y
es Op
e
n
an
d
E
y
es C
lo
s
e
5
.
4
.
Dis
cus
s
io
n
Af
ter
t
h
e
r
esu
lts
o
f
a
ll
th
e
ex
p
er
i
m
e
n
ts
f
o
r
ea
ch
clas
s
if
ier
w
er
e
o
b
tain
ed
,
f
i
n
al
a
n
al
y
s
i
s
an
d
ev
alu
a
tio
n
w
er
e
co
n
d
u
cted
.
T
h
e
an
al
y
s
i
s
w
as
r
ec
o
r
d
ed
an
d
co
m
p
ar
is
o
n
g
r
ap
h
s
f
o
r
ea
ch
class
i
f
ier
a
n
d
r
ep
r
esen
tatio
n
o
f
d
ata
w
er
e
p
r
esen
ted
.
Fi
n
all
y
,
th
e
r
es
u
lt
s
we
r
e
s
u
m
m
ar
ized
i
n
Fi
g
u
r
e
3
.
I
t
w
as c
lear
th
at
M
u
lti
-
L
a
y
er
P
er
ce
p
tr
o
n
g
av
e
h
i
g
h
er
ac
c
u
r
a
c
y
r
esu
lts
t
h
a
n
Naï
v
e
B
a
y
es a
n
d
R
a
n
d
o
m
Fo
r
est
f
o
r
e
y
e
s
o
p
en
a
n
d
e
y
e
s
clo
s
e
co
n
d
itio
n
s
.
T
h
e
Mu
lti
-
L
a
y
er
P
er
ce
p
tr
o
n
class
i
f
ier
c
o
n
tr
ib
u
ted
a
lo
t
o
f
tr
ain
i
n
g
p
r
o
ce
s
s
u
s
i
n
g
t
h
e
m
o
d
el
d
u
e
to
th
e
h
i
g
h
n
u
m
b
er
o
f
la
y
er
s
an
d
n
eu
r
o
n
s
.
T
h
e
d
is
co
v
er
y
i
s
b
ased
o
n
th
e
o
b
s
er
v
atio
n
t
h
at
th
e
h
i
g
h
er
th
e
p
ar
am
eter
s
o
f
la
y
er
s
an
d
n
eu
r
o
n
s
,
th
e
b
etter
t
h
e
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
.
I
n
al
l
ca
s
es
alp
h
a
w
a
v
es
y
ield
ed
t
h
e
b
est
p
r
ed
icted
ac
cu
r
ac
y
a
s
c
o
m
p
ar
ed
to
all
s
u
b
j
ec
ts
i
n
b
o
th
co
n
d
itio
n
s
.
Naiv
es
B
a
y
e
s
g
i
v
es
th
e
s
h
o
r
te
s
t
co
m
p
u
tatio
n
ti
m
e
w
it
h
Gau
s
s
ia
n
Naiv
e
s
B
ay
e
s
class
if
ier
p
er
f
o
r
m
s
b
etter
th
an
B
er
n
o
u
lli
Nai
v
e
s
B
a
y
e
s
clas
s
i
f
ier
.
Fi
g
u
r
e
3
also
s
h
o
w
s
a
cl
ea
r
r
esu
lt
th
at
M
u
lti
-
L
a
y
er
P
e
r
ce
p
tr
o
n
class
i
f
ier
g
av
e
m
o
r
e
ac
cu
r
ate
p
r
ed
ictio
n
r
es
u
lts
.
T
h
e
p
ea
k
ac
c
u
r
ac
y
r
esu
lt
w
a
s
p
r
o
d
u
ce
d
f
r
o
m
Al
p
h
a
an
d
t
h
e
lo
w
est
ac
cu
r
ac
y
r
es
u
lts
w
a
s
p
r
o
d
u
ce
d
f
r
o
m
Ga
m
m
a.
I
t
is
also
n
o
ted
th
at
a
b
ig
d
if
f
er
en
ce
o
f
ac
c
u
r
ac
y
o
cc
u
r
s
b
et
w
ee
n
Mu
lti
-
L
a
y
er
P
er
ce
p
tr
o
n
an
d
Naïv
e
B
a
y
es
i
n
Delta
b
r
ain
w
a
v
es.
B
a
n
d
Ey
e
s Op
e
n
Ey
e
s c
l
o
se
A
c
c
u
r
a
c
y
(
%)
C
o
mp
u
t
a
t
i
o
n
T
i
me
(
S
)
A
c
c
u
r
a
c
y
(
%)
C
o
mp
u
t
a
t
i
o
n
T
i
me
(
S
)
A
l
p
h
a
82
2
3
1
.
4
7
82
2
6
3
.
7
8
B
e
t
a
67
2
7
4
.
0
5
69
2
7
4
.
8
4
D
e
l
t
a
73
2
9
1
.
1
1
69
2
6
2
.
1
0
G
a
mm
a
64
2
5
9
.
6
1
52
2
6
2
.
4
3
T
h
e
t
a
65
2
7
0
.
5
9
68
2
2
8
.
2
8
B
a
n
d
Ey
e
s Op
e
n
Ey
e
s c
l
o
se
A
c
c
u
r
a
c
y
(
%)
C
o
mp
u
t
a
t
i
o
n
T
i
me
(
S
)
A
c
c
u
r
a
c
y
(
%)
C
o
mp
u
t
a
t
i
o
n
T
i
me
(S)
A
l
p
h
a
82
2
1
5
.
3
6
82
2
1
5
.
3
0
B
e
t
a
69
2
4
2
.
9
3
69
2
4
8
.
4
3
D
e
l
t
a
73
2
1
7
.
9
9
69
2
3
4
.
4
1
G
a
mm
a
64
2
3
1
.
9
5
52
2
4
5
.
1
0
T
h
e
t
a
65
2
2
9
.
6
9
68
2
4
0
.
1
7
B
a
n
d
Ey
e
s Op
e
n
Ey
e
s c
l
o
se
A
c
c
u
r
a
c
y
(
%)
C
o
mp
u
t
a
t
i
o
n
T
i
me
(
S
)
A
c
c
u
r
a
c
y
(
%)
C
o
mp
u
t
a
t
i
o
n
T
i
me
(
S
)
A
l
p
h
a
82
2
2
6
.
7
5
82
2
1
4
.
3
2
B
e
t
a
69
2
4
4
.
3
2
69
2
4
4
.
2
1
D
e
l
t
a
73
2
1
8
.
0
6
69
2
2
7
.
3
6
G
a
mm
a
64
2
3
2
.
3
3
52
2
4
3
.
0
3
T
h
e
t
a
65
2
4
2
.
2
8
68
2
2
6
.
1
9
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
16
,
No
.
2
,
No
v
e
m
b
er
2
0
1
9
:
9
6
4
-
9
7
1
970
(
a)
(
b
)
Fig
u
r
e
3
.
P
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
o
f
(
a)
e
y
es o
p
en
a
n
d
(
b
)
e
y
es c
lo
s
e
co
n
d
itio
n
s
6.
CO
NCLU
SI
O
N
Fro
m
th
e
r
esu
l
ts
an
d
o
b
s
er
v
at
io
n
it
is
clea
r
th
at
alp
h
a
w
a
v
es
ca
n
b
e
u
s
ed
to
d
etec
t
p
o
r
n
ad
d
ictio
n
ef
f
ec
tiv
e
l
y
esp
ec
ial
l
y
w
it
h
i
n
t
h
e
f
r
o
n
ta
l
r
eg
io
n
o
f
t
h
e
b
r
ain
.
T
h
e
v
alen
ce
an
d
ar
o
u
s
al
w
er
e
u
s
ed
in
t
h
is
ca
s
e
an
d
s
ee
m
s
to
p
r
o
v
id
e
r
o
b
u
s
t
p
r
ed
ictio
n
o
f
p
o
r
n
ad
d
ictio
n
p
r
eli
m
i
n
ar
y
s
cr
ee
n
i
n
g
.
T
h
e
r
esu
lts
is
a
ls
o
b
ased
o
n
th
e
f
ac
t
th
at
t
h
e
q
u
e
s
tio
n
air
e
p
r
o
d
u
ce
b
y
th
e
p
s
y
c
h
o
lo
g
i
s
t
i
s
ac
cu
r
ate
en
o
u
g
h
a
n
d
f
r
o
m
[
1
4
]
it
is
f
o
u
n
d
t
h
e
o
th
er
2
0
%
o
f
th
e
ac
cu
r
ac
y
co
u
ld
b
e
d
u
e
to
in
co
n
s
is
te
n
c
y
o
f
th
e
p
s
y
c
h
o
lo
g
ical
in
s
tr
u
m
e
n
t
s
u
s
ed
.
Fo
r
ef
f
icie
n
t
co
m
p
u
tatio
n
ti
m
e,
th
e
Naï
v
e
B
ay
e
s
clas
s
if
ier
ca
n
p
r
o
d
u
ce
th
e
f
a
s
test
w
ith
r
ea
s
o
n
ab
l
y
g
o
o
d
en
o
u
g
h
ac
cu
r
ac
y
.
Ho
w
e
v
er
,
ML
P
o
u
tp
er
f
o
r
m
e
d
b
o
th
Naiv
es
B
ay
e
s
an
d
R
an
d
o
m
Fo
r
est
clas
s
i
f
ier
s
i
n
ter
m
o
f
ac
cu
r
ac
y
.
T
h
e
ex
p
er
i
m
en
ta
l
r
esu
lts
s
h
o
w
p
o
ten
tial
f
o
r
ex
p
en
s
io
n
f
o
r
p
o
r
n
ad
d
ictio
n
d
etec
tio
n
th
at
it
ca
n
b
e
u
s
ed
f
o
r
ea
r
l
y
in
ter
v
en
tio
n
a
n
d
alter
n
at
iv
e
m
ea
s
u
r
e
m
e
n
t to
s
u
p
p
o
r
t p
s
y
ch
o
lo
g
ical
q
u
es
tio
n
n
air
e
m
et
h
o
d
s
[
2
7
]
.
RE
F
E
R
E
NC
E
S
[1
]
K.
Ch
e
rry
,
―
A
n
Ov
e
rv
ie
w
o
f
Be
h
a
v
io
ra
l
P
sy
c
h
o
lo
g
y
‖
[
On
li
n
e
]
,
2
0
1
6
,
A
v
a
il
a
b
le
f
ro
m
:
h
ttp
s
:/
/
www
.
v
er
y
w
el
l
m
i
n
d
.
co
m
/b
eh
a
v
io
r
al
-
p
s
y
c
h
o
lo
g
y
-
4157183
.
2
0
1
6
.
[2
]
A
.
F
e
l
m
a
n
,
―
A
d
d
ictio
n
:
De
f
in
it
io
n
,
S
y
m
p
to
m
s,
W
it
h
d
ra
w
a
l,
a
n
d
T
re
a
t
m
e
n
t
‖
[
On
li
n
e
]
,
A
v
a
il
a
b
le
f
ro
m
:
h
ttp
s
:/
/
www
.
m
ed
icaln
e
w
s
to
d
ay
.
co
m
/ar
ticle
s
/3
2
3
4
6
5
.
p
h
p
.
2
0
1
8
.
[3
]
S
.
S
u
ss
m
a
n
a
n
d
A
.
N.
S
u
ss
m
a
n
,
―
Co
n
sid
e
ri
n
g
th
e
De
f
in
it
io
n
o
f
A
d
d
ictio
n
‖
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
v
iro
n
me
n
t
a
l
Res
e
a
rc
h
a
n
d
P
u
b
li
c
He
a
lt
h
,
v
o
l.
8
(1
0
),
p
p
.
4
0
2
5
–
4
0
3
8
,
2
0
1
1
.
[4
]
S
.
S
.
A
la
v
i,
M
.
F
e
rd
o
si,
F
.
Ja
n
n
a
t
if
a
rd
,
M
.
Esla
m
i,
H.
A
lag
h
e
m
a
n
d
a
n
a
n
d
M
.
S
e
tare
,
―
Be
h
a
v
io
ra
l
Ad
d
icti
o
n
v
e
rsu
s
S
u
b
sta
n
c
e
A
d
d
icti
o
n
:
Co
rre
sp
o
n
d
e
n
c
e
o
f
P
sy
c
h
iatric
a
n
d
P
s
y
c
h
o
lo
g
ica
l
V
iew
s‖
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Pre
v
e
n
ti
v
e
M
e
d
icin
e
,
v
o
l.
3
(
4
),
p
p
.
2
9
0
–
2
9
4
,
2
0
1
2
.
[5
]
Z.
Z
o
u
,
H.
W
a
n
g
,
F
.
D.
U
q
u
i
ll
a
s,
X.
W
a
n
g
,
J.
Di
n
g
a
n
d
H.
C
h
e
n
,
―
De
f
in
it
io
n
o
f
S
u
b
sta
n
c
e
a
n
d
No
n
-
su
b
sta
n
c
e
A
d
d
ictio
n
‖
,
A
d
v
a
n
c
e
s
in
Ex
p
e
ri
m
e
n
tal
M
e
d
icin
e
a
n
d
Bio
lo
g
y
S
u
b
sta
n
c
e
a
n
d
No
n
-
su
b
sta
n
c
e
A
d
d
ictio
n
,
p
p
.
2
1
-
4
1
,
2
0
1
7
.
[6
]
T
.
D
y
e
r,
―
Cro
ss
A
d
d
ictio
n
s
‖
[
In
tern
e
t]
,
A
v
a
il
a
b
le
f
ro
m
:
h
tt
p
s://
ww
w
.
d
ru
g
re
h
a
b
.
c
o
m
/ad
d
ictio
n
/cr
o
ss
-
a
d
d
icti
o
n
s/
.
2
0
1
8
.
[7
]
E.
W
.
Ow
e
n
s,
R.
J.
Be
h
u
n
,
J.
C.
M
a
n
n
i
n
g
a
n
d
R,
C.
R
e
i
d
,
―
T
h
e
Im
p
a
c
t
o
f
In
tern
e
t
P
o
rn
o
g
ra
p
h
y
o
n
A
d
o
les
c
e
n
ts:
A
Re
v
ie
w
o
f
th
e
Re
se
a
r
c
h
‖
,
S
e
x
u
a
l
A
d
d
ictio
n
&
C
o
m
p
u
lsiv
it
y
,
v
o
l.
1
9
(1
-
2
),
p
p
.
9
9
-
1
2
2
,
2
0
1
2
.
[8
]
B.
K.
Hin
m
a
n
,
―
M
ix
e
d
M
e
th
o
d
s
A
n
a
l
y
si
s
o
f
Co
u
n
se
lo
r
V
iew
s,
A
tt
it
u
d
e
s
a
n
d
P
e
rc
e
iv
e
d
Co
m
p
e
ten
c
ies
Re
g
a
rd
in
g
t
h
e
T
re
a
t
m
e
n
t
o
f
In
tern
e
t
P
o
r
n
o
g
ra
p
h
y
A
d
d
ictio
n
‖
.
Diss
e
rtatio
n
s,
G
ra
d
u
a
te
Co
ll
e
g
e
,
Wes
tern
M
ich
i
g
a
n
Un
iv
e
rsit
y
,
2
0
1
3
[9
]
S
.
M
a
h
b
u
b
a
,
―
Dru
g
A
d
d
ictio
n
a
m
o
n
g
Un
d
e
rg
ra
d
u
a
te
S
tu
d
e
n
ts
o
f
P
riv
a
te
Un
iv
e
rsiti
e
s
in
Ba
n
g
lad
e
sh
‖
,
P
r
o
c
e
d
ia
-
S
o
c
ial
a
n
d
Be
h
a
v
io
ra
l
S
c
ien
c
e
s,
5
,
p
p
.
4
9
8
–
5
0
1
,
2
0
1
0
.
[1
0
]
M
.
S
.
Da
rsh
a
n
,
T
.
S
.
R.
S
a
t
h
y
a
n
a
ra
y
a
n
a
,
S
.
M
a
n
ick
a
m
,
A
.
T
a
n
d
o
n
a
n
d
D.
Ra
m
,
―
A
Ca
se
Re
p
o
rt
o
f
P
o
r
n
o
g
ra
p
h
y
A
d
d
ictio
n
w
it
h
Dh
a
t
S
y
n
d
ro
m
e
‖
,
In
d
i
a
n
J
o
u
rn
a
l
o
f
Psy
c
h
i
a
try
,
v
o
l.
5
6
(
4
),
p
p
.
3
8
5
–
3
8
7
,
2
0
1
4
.
[1
1
]
P
.
F
.
F
a
g
a
n
,
―
Eff
e
c
ts
o
f
P
o
rn
o
g
ra
p
h
y
‖
,
[
In
tern
e
t
]
,
A
v
a
il
a
b
le
f
ro
m
h
tt
p
:/
/m
a
rrip
e
d
ia.o
rg
/eff
e
c
ts_
o
f
_
p
o
rn
o
g
ra
p
h
y
.
2
0
1
7
.
[1
2
]
H.
W
e
in
,
―
Bio
lo
g
y
o
f
A
d
d
ictio
n
.
T
o
wa
rd
s
a
Be
tt
e
r
T
o
m
o
rro
w
:
C
h
il
d
Rig
h
ts
a
n
d
He
a
lt
h
‖
,
G
e
n
e
v
a
,
S
w
it
z
e
rlan
d
:
W
o
rld
He
a
lt
h
Org
a
n
iza
ti
o
n
,
2
0
1
5
.
[1
3
]
K.
B.
Bo
c
k
e
r,
J.
A
.
v
a
n
A
v
e
r
m
a
e
te,
M
.
M
.
v
a
n
d
e
n
Be
rg
-
L
e
n
ss
e
n
,
―
T
h
e
In
tern
a
ti
o
n
a
l
1
0
-
2
0
S
y
ste
m
Re
v
isit
e
d
:
Ca
rtes
ian
a
n
d
S
p
h
e
rica
l
Co
-
o
rd
in
a
tes
‖
,
Bra
in
T
o
p
o
g
ra
p
h
y
,
6
(3
),
p
p
2
3
1
—
2
3
5
,
1
9
9
4
.
[1
4
]
S
.
W
.
Kra
u
s,
H.
Ro
se
n
b
e
rg
a
n
d
C
.
J.
T
o
m
p
se
tt
,
―
A
ss
e
ss
m
e
n
t
o
f
S
e
lf
-
e
ff
ic
a
c
y
to
E
m
p
lo
y
S
e
l
f
-
In
it
iate
d
P
o
r
n
o
g
ra
p
h
y
Use
-
re
d
u
c
ti
o
n
S
trate
g
ies
‖
,
J
o
u
rn
a
l
o
f
A
d
d
ictive
Beh
a
v
i
o
rs
,
v
o
l
4
0
,
p
p
.
1
1
5
-
1
1
8
,
2
0
1
5
.
[1
5
]
L
.
T
sa
li
k
i,
―
P
la
y
in
g
w
it
h
P
o
r
n
:
G
re
e
k
Ch
il
d
re
n
'
s
Ex
p
lo
ra
ti
o
n
s
in
p
o
rn
o
g
ra
p
h
y
‖
,
S
e
x
Ed
u
c
a
ti
o
n
,
1
1
(
3
),
pp
.
2
9
3
-
3
0
2
,
2
0
1
1
.
[1
6
]
W
.
H.
Kh
a
li
f
a
,
M
.
I.
Ro
u
sh
d
y
,
A
.
M
.
S
a
le
m
a
n
d
K.
Re
v
e
tt
,
K,
―
A
IS
In
sp
ired
A
p
p
ro
a
c
h
f
o
r
Us
e
r
Id
e
n
ti
f
ica
ti
o
n
Ba
se
d
o
n
E
EG
S
ig
n
a
ls‖
Re
c
e
n
t
Ad
v
a
n
c
e
s in
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
,
v
o
l.
1
0
,
p
p
.
8
4
–
8
9
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
N
eu
r
o
-
P
h
ysio
lo
g
ica
l P
o
r
n
A
d
d
ictio
n
Dete
ctio
n
u
s
in
g
Ma
c
h
i
n
e
Lea
r
n
in
g
…(
N
o
r
h
a
s
lin
d
a
K
a
ma
r
u
d
d
in
)
971
[1
7
]
N.
Ka
m
a
ru
d
d
in
,
A
.
W
a
h
a
b
a
n
d
D.
Ha
n
d
iy
a
n
i,
―
P
o
r
n
o
g
ra
p
h
y
De
tec
ti
o
n
b
a
se
d
o
n
Ne
u
ro
p
h
y
sio
lo
g
ica
l
Co
m
p
u
tatio
n
a
l
A
p
p
r
o
a
c
h
‖
,
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
1
0
(
1
),
p
p
1
3
8
-
1
4
5
,
2
0
1
8
.
[1
8
]
N.
I.
M
.
Ra
z
i,
A
.
W
a
h
a
b
a
n
d
N.
Ka
m
a
ru
d
d
i
n
,
"
Ne
u
ro
p
h
y
sio
lo
g
ica
l
A
n
a
l
y
sis
o
f
P
o
r
n
A
d
d
icti
o
n
t
o
L
e
a
rn
in
g
Disa
b
il
it
ies
,
"
In
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
f
o
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
lo
g
y
f
o
r
th
e
M
u
slim
W
o
rld
(ICT
4
M
),
Ku
a
la L
u
m
p
u
r,
p
p
.
2
7
2
-
2
7
7
,
2
0
1
8
[1
9
]
S
.
K.
P
a
l
a
n
d
S
.
M
i
tra,
"
M
u
lt
il
a
y
e
r
P
e
rc
e
p
tro
n
,
F
u
z
z
y
S
e
ts,
a
n
d
Clas
sif
ica
ti
o
n
,
"
IEE
E
T
ra
n
s
a
c
t
io
n
s
o
n
Ne
u
ra
l
Ne
two
rk
s
,
v
o
l.
3
(
5
),
p
p
.
6
8
3
-
6
9
7
,
1
9
9
2
.
[2
0
]
K.
S
.
Ra
h
n
u
m
a
,
A
.
W
a
h
a
b
,
N.
Ka
m
a
ru
d
d
in
a
n
d
H.
M
a
ji
d
,
"
EE
G
A
n
a
l
y
sis
f
o
r
Un
d
e
rsta
n
d
in
g
S
tres
s
b
a
se
d
o
n
Aff
e
c
ti
v
e
M
o
d
e
l
Ba
sis
F
u
n
c
ti
o
n
,
"
In
1
5
t
h
I
n
ter
n
a
t
io
n
a
l
S
y
mp
o
si
u
m
o
n
C
o
n
su
me
r
El
e
c
tro
n
ics
(
IS
CE),
S
i
n
g
a
p
o
re
,
p
p
.
5
9
2
-
597
.
2
0
1
1
.
[2
1
]
R.
G
a
rre
t
a
,
G
.
M
o
n
c
e
c
c
h
i,
―
L
e
a
rn
in
g
S
c
ik
it
-
lea
rn
:
M
a
c
h
in
e
L
e
a
rn
in
g
in
P
y
th
o
n
‖
,
P
A
CKT
P
u
b
li
sh
i
n
g
,
Bu
rm
in
g
h
a
m
-
M
u
m
b
a
i,
2
0
1
3
.
[2
2
]
L
.
G
u
o
,
Y.
M
a
,
B.
Cu
k
ic
a
n
d
Ha
rsh
in
d
e
r
S
in
g
h
,
"
Ro
b
u
st
P
re
d
ictio
n
o
f
F
a
u
lt
-
p
ro
n
e
n
e
ss
b
y
Ra
n
d
o
m
F
o
re
sts,"
In
1
5
th
I
n
tern
a
ti
o
n
a
l
S
y
m
p
o
siu
m
o
n
S
o
f
tw
a
re
R
e
li
a
b
il
it
y
En
g
in
e
e
rin
g
,
S
a
in
t
-
M
a
lo
,
Bre
tag
n
e
,
2
0
0
4
,
p
p
.
4
1
7
-
4
2
8
.
2
0
0
4
.
[2
3
]
T
.
T
.
W
o
n
g
,
―
P
e
rf
o
rm
a
n
c
e
E
v
a
lu
a
ti
o
n
o
f
Clas
si
f
ica
ti
o
n
A
l
g
o
rit
h
m
s
b
y
K
-
f
o
ld
a
n
d
L
e
a
v
e
-
one
-
o
u
t
Cro
s
s
V
a
li
d
a
ti
o
n
‖
,
P
a
tt
e
rn
Re
c
o
g
n
i
ti
o
n
,
v
o
l.
4
8
(9
),
p
p
.
2
8
3
9
–
2
8
4
6
,
2
0
1
5
.
[2
4
]
J.
L
.
M
it
rp
a
n
o
n
t,
W
.
S
a
w
a
n
g
p
h
o
l,
T
.
Vith
a
n
ti
ra
w
a
t,
S
.
P
a
e
n
g
k
a
e
w
,
P
.
S
u
w
a
n
n
a
sin
g
,
A
.
Da
ra
m
a
s
a
n
d
Y.
Ch
e
n
,
―
A
S
tu
d
y
o
n
u
sin
g
P
y
th
o
n
v
s
W
e
k
a
o
n
Dia
l
y
sis
Da
t
a
A
n
a
l
y
sis‖
,
I
n
2
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(IN
CI
T
),
p
p
.
1
-
6
,
2
0
1
7
[2
5
]
D.
M
a
n
ti
n
i,
M
.
G
.
P
e
rru
c
c
i,
C.
D
e
l
G
ra
tt
a
,
G
.
L
.
Ro
m
a
n
i
a
n
d
M
.
Co
rb
e
t
ta,
―
El
e
c
tro
p
h
y
sio
lo
g
ica
l
S
ig
n
a
tu
re
s
o
f
Re
stin
g
S
tate
Ne
tw
o
rk
s
in
th
e
Hu
m
a
n
Bra
in
‖
,
In
P
r
o
c
e
e
d
i
n
g
s
o
f
th
e
Na
ti
o
n
a
l
A
c
a
d
e
m
y
o
f
S
c
ien
c
e
s,
104
(3
2
)
1
3
1
7
0
-
1
3
1
7
5
,
2
0
0
7
[2
6
]
I.
K
a
rim
,
A
.
W
a
h
a
b
a
n
d
N.
K
a
m
a
ru
d
d
in
,
"
Clas
sif
i
c
a
ti
o
n
o
f
Dy
sle
x
ic
a
n
d
No
rm
a
l
Ch
il
d
re
n
d
u
rin
g
Re
stin
g
Co
n
d
it
io
n
u
si
n
g
KD
E
a
n
d
M
L
P
,
"
In
5
t
h
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
In
f
o
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
y
f
o
r
th
e
M
u
slim
W
o
rld
(ICT
4
M
),
Ra
b
a
t,
p
p
.
1
-
5
,
2
0
1
3
.
[2
7
]
A
.
W
a
h
a
b
a
n
d
N.
Ka
m
a
ru
d
d
in
,
―
Bra
in
De
v
e
lo
p
m
e
n
tal
Diso
rd
e
rs‘
M
o
d
e
ll
in
g
b
a
se
d
o
n
P
re
sc
h
o
o
lers
Ne
u
ro
-
p
h
y
sio
lo
g
ica
l
P
ro
f
il
in
g
‖
,
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ie
n
c
e
,
v
o
l.
1
2
(
2
)
,
p
p
.
5
4
2
-
5
4
7
.
2
0
1
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
A
s
so
c
.
P
r
o
f
.
T
s.
Dr.
No
rh
a
slin
d
a
c
u
rre
n
tl
y
h
o
ld
s
a
p
o
st
o
f
a
ss
o
c
iate
p
ro
f
e
ss
o
r
in
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
Tek
n
o
lo
g
i
M
A
R
A
(
UiT
M
),
M
a
la
y
sia
.
S
h
e
se
rv
e
d
Ui
T
M
sin
c
e
2
0
1
1
.
S
h
e
re
c
e
i
v
e
d
h
e
r
b
a
c
h
e
lo
r‘s
d
e
g
r
e
e
in
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(Co
m
p
u
ter
S
c
ien
c
e
)
f
ro
m
Un
iv
e
r
siti
Ke
b
a
n
g
sa
a
n
M
a
la
y
sia
in
2
0
0
1
f
o
ll
o
w
e
d
b
y
h
e
r
M
a
ste
r
o
f
S
o
f
tw
a
r
e
En
g
in
e
e
rin
g
f
ro
m
M
a
la
y
a
Un
iv
e
rsit
y
in
2
0
0
6
.
In
2
0
1
3
,
s
h
e
is
a
w
a
rd
e
d
w
it
h
Do
c
to
r
o
f
P
h
il
o
so
p
h
y
(Co
m
p
u
ter
En
g
in
e
e
rin
g
)
f
ro
m
N
a
n
y
a
n
g
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
r
si
t
y
(S
in
g
a
p
o
re
)
f
o
c
u
sin
g
o
n
c
o
m
p
u
tatio
n
a
l
i
n
telli
g
e
n
c
e
e
sp
e
c
iall
y
o
n
Aff
e
c
ti
v
e
Co
m
p
u
ti
n
g
.
S
h
e
is
v
e
ry
a
c
ti
v
e
in
re
se
a
rc
h
f
ield
s
o
f
a
ff
e
c
ti
v
e
c
o
m
p
u
ti
n
g
,
sp
e
e
c
h
e
m
o
ti
o
n
re
c
o
g
n
it
io
n
,
n
e
u
ro
-
c
o
g
n
i
ti
v
e
in
f
o
rm
a
ti
c
s
a
n
d
d
r
iv
e
r
b
e
h
a
v
io
ra
l
stu
d
y
.
A
b
d
u
l
W
a
h
a
b
re
c
e
iv
e
d
th
e
De
g
re
e
f
ro
m
th
e
Un
iv
e
rsity
o
f
Esse
x
,
Esse
x
,
U.K.,
in
1
9
7
9
,
t
h
e
M
.
S
c
.
d
e
g
re
e
f
ro
m
th
e
Na
ti
o
n
a
l
Un
iv
e
rsity
o
f
S
in
g
a
p
o
re
,
S
in
g
a
p
o
re
,
i
n
1
9
8
7
,
a
n
d
t
h
e
P
h
.
D.
d
e
g
re
e
f
ro
m
Na
n
y
a
n
g
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsity
,
S
in
g
a
p
o
re
.
His
re
se
a
r
c
h
h
a
s
b
e
e
n
in
t
h
e
a
re
a
s
o
f
tele
c
o
m
m
u
n
ica
ti
o
n
,
sig
n
a
l
p
ro
c
e
ss
in
g
,
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
c
e
.
He
w
a
s
w
it
h
He
w
lett
P
a
c
k
a
rd
S
in
g
a
p
o
re
,
S
i
n
g
a
p
o
re
,
a
s
a
R
e
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
P
ro
jec
t
M
a
n
a
g
e
r
b
o
th
in
CO,
USA
.
H
e
jo
in
e
d
Na
n
y
a
n
g
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsity
in
1
9
9
0
,
w
h
e
re
h
e
wa
s
a
n
A
s
so
c
iate
P
ro
f
e
ss
o
r,
b
e
f
o
re
jo
in
i
n
g
th
e
I
n
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
o
f
M
a
la
y
sia
,
M
a
la
y
si
a
,
a
s
a
P
r
o
f
e
ss
o
r,
in
2
0
0
9
.
He
h
a
s
a
u
th
o
re
d
o
v
e
r
1
0
0
c
o
n
f
e
re
n
c
e
p
a
p
e
rs,
jo
u
rn
a
l
p
a
p
e
rs,
p
a
ten
ts,
a
n
d
b
o
o
k
c
h
a
p
ters
in
th
e
a
re
a
s
o
f
d
ig
it
a
l
a
n
d
o
p
t
ica
l
c
o
m
p
u
ti
n
g
,
sig
n
a
l
p
ro
c
e
ss
in
g
,
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
c
e
.
Ya
s
m
e
e
n
Ro
z
a
id
i
g
ra
d
u
a
ted
f
ro
m
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
(U
iT
M
)
P
a
h
a
n
g
w
it
h
a
Dip
lo
m
a
in
Co
m
p
u
ter
S
c
ien
c
e
in
2
0
1
6
.
S
h
e
is
n
o
w
a
f
in
a
l
-
y
e
a
r
stu
d
e
n
t
in
Ba
c
h
e
lo
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
(Ho
n
s.)
a
t
U
n
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
(Ui
T
M
)
S
h
a
h
A
lam
,
S
e
la
n
g
o
r,
M
a
lay
sia
.
Evaluation Warning : The document was created with Spire.PDF for Python.