I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
6
,
No
.
2
,
N
o
v
em
b
e
r
20
24
,
p
p
.
8
6
3
~
8
7
1
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
2
.
pp
863
-
8
7
1
863
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Neuro
ns to
h
ea
rt
bea
ts:
spiki
ng
ne
ura
l net
wo
rks
for
elect
ro
ca
rdio
g
ra
m
pa
tt
er
n recog
ni
tion
No
r
Am
a
lia
Da
y
a
na
B
inti
M
o
ha
m
a
d No
o
r
1
,
Wo
ng
Ya
n C
hiew
1
,
Z
a
rina
M
o
h
d No
h
1
,
Ra
njit
Sin
g
h Sa
rba
n Sin
g
h
2
1
F
a
c
u
l
t
y
o
f
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
Te
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
r
i
n
g
(
F
T
K
E
K
)
,
U
n
i
v
e
r
s
i
t
i
T
e
k
n
i
k
a
l
M
a
l
a
y
s
i
a
M
e
l
a
k
a
(
U
Te
M
)
,
M
e
l
a
k
a
,
M
a
l
a
y
s
i
a
2
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
S
u
n
w
a
y
U
n
i
v
e
r
si
t
y
,
S
e
l
a
n
g
o
r
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
13
,
2
0
2
3
R
ev
is
ed
J
u
l
29
,
2
0
2
4
Acc
ep
ted
A
ug
5
,
2
0
2
4
Th
e
e
lec
tro
c
a
rd
io
g
ra
m
(ECG
)
is
o
n
e
o
f
th
e
m
o
st
sig
n
ifi
c
a
n
t
m
e
th
o
d
s
o
f
d
iag
n
o
stics
fo
r
d
e
term
in
i
n
g
h
e
a
rt
rh
y
t
h
m
d
iso
r
d
e
rs.
F
o
r
t
h
is
stu
d
y
,
ra
w
EC
G
sig
n
a
ls
fro
m
th
e
P
h
y
sio
Ba
n
k
d
a
tab
a
se
a
re
su
b
jec
ted
to
a
n
imp
o
rtan
t
p
re
-
p
ro
c
e
ss
in
g
ste
p
th
a
t
u
se
s
e
m
p
iri
c
a
l
m
o
d
e
d
e
c
o
m
p
o
siti
o
n
(
EM
D)
o
n
si
g
n
a
l
d
e
n
o
isi
n
g
a
n
d
d
isto
rti
o
n
e
l
imin
a
ti
o
n
.
Estab
l
ish
i
n
g
fu
n
c
ti
o
n
in
g
sp
i
k
i
n
g
n
e
u
ra
l
n
e
two
rk
s
(
S
NN
)
in
v
o
l
v
e
s
fig
u
rin
g
o
u
t
t
h
e
n
e
u
r
o
n
’
s
sta
te
t
h
ro
u
g
h
i
ts
a
c
ti
v
it
y
lev
e
l,
c
h
a
ll
e
n
g
i
n
g
d
u
e
t
o
it
s
re
se
m
b
lan
c
e
to
th
e
h
u
m
a
n
b
r
a
in
’
s
d
a
ta
p
ro
c
e
ss
in
g
,
y
e
t
a
p
p
e
a
li
n
g
d
u
e
t
o
f
a
c
to
rs
li
k
e
imp
ro
v
e
d
u
n
su
p
e
rv
ise
d
lea
rn
in
g
m
e
th
o
d
s,
wit
h
ten
p
a
ra
m
e
ters
c
h
o
se
n
fo
r
t
h
e
lea
rn
in
g
a
l
g
o
rit
h
m
o
f
S
NN
.
A
c
o
m
p
re
h
e
n
si
v
e
se
t
o
f
1
5
d
iffere
n
t
ti
m
e
-
d
o
m
a
in
fe
a
tu
re
s
a
n
d
1
0
Ce
p
stra
l
d
o
m
a
in
fe
a
tu
re
s
is
p
re
c
ise
ly
e
x
trac
ted
to
trai
n
th
e
S
NN
c
las
sifier.
An
e
x
ten
si
v
e
stu
d
y
is
c
o
n
d
u
c
te
d
to
a
n
a
ly
se
t
h
e
lea
rn
in
g
p
a
ra
m
e
ters
th
a
t
a
ffe
c
t
S
NN
p
e
rfo
rm
a
n
c
e
,
sig
n
ifi
c
a
n
tl
y
in
f
lu
e
n
c
i
n
g
re
su
lt
a
c
c
u
ra
c
y
.
Th
r
o
u
g
h
a
two
-
c
las
sifica
ti
o
n
p
ro
c
e
ss
,
t
h
e
d
iffere
n
ti
a
ti
o
n
b
e
twe
e
n
n
o
rm
a
l
a
n
d
a
b
n
o
rm
a
l
ECG
p
a
tt
e
rn
s
c
a
n
b
e
a
c
h
iev
e
d
in
th
is
st
u
d
y
.
A
m
a
x
imu
m
tes
ti
n
g
a
c
c
u
ra
c
y
o
f
9
1
.
6
6
6
7
%
a
n
d
a
m
a
x
imu
m
train
i
n
g
a
c
c
u
ra
c
y
o
f
9
9
.
1
6
6
7
%
h
a
v
e
b
e
e
n
a
tt
a
in
e
d
b
y
th
e
p
ro
c
e
ss
.
Th
e
se
re
su
lt
s
d
e
m
o
n
stra
te
th
e
c
o
m
p
e
ten
c
y
o
f
th
e
sy
ste
m
in
d
ist
in
g
u
is
h
in
g
b
e
twe
e
n
d
isti
n
c
t
ECG
c
las
se
s,
p
a
rti
c
u
larly
in
i
d
e
n
ti
f
y
in
g
n
o
rm
a
l
a
n
d
a
b
n
o
rm
a
l
c
a
rd
iac
rh
y
th
m
s
t
h
ro
u
g
h
ECG
c
las
sifica
ti
o
n
.
K
ey
w
o
r
d
s
:
B
io
m
ed
ical
s
ig
n
al
p
r
o
ce
s
s
in
g
C
ar
d
iac
ar
r
h
y
th
m
ia
i
d
en
tific
at
io
n
E
lectr
o
ca
r
d
io
g
r
am
an
al
y
s
is
Ma
ch
in
e
lear
n
in
g
in
h
ea
lth
ca
r
e
Sp
ik
in
g
n
eu
r
al
n
etwo
r
k
s
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
:
W
o
n
g
Yan
C
h
iew
Facu
lty
o
f
E
lectr
o
n
ics an
d
C
o
m
p
u
ter
T
ec
h
n
o
lo
g
y
a
n
d
E
n
g
in
ee
r
in
g
(
FTKE
K)
Un
iv
er
s
iti T
ek
n
ik
al
Ma
lay
s
ia
Me
lak
a
(
UT
eM
)
Han
g
T
u
ah
J
ay
a,
7
6
1
0
0
,
Du
r
ia
n
T
u
n
g
g
al
,
Me
lak
a,
Ma
lay
s
ia
E
m
ail: y
cwo
n
g
@
u
tem
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
o
ca
r
d
io
g
r
am
(
E
C
G
)
p
atter
n
r
ec
o
g
n
itio
n
,
cr
u
cial
f
o
r
d
i
ag
n
o
s
in
g
a
n
d
m
o
n
ito
r
i
n
g
h
ea
r
t
d
is
ea
s
es,
p
r
o
v
id
es
in
s
ig
h
ts
in
to
th
e
h
ea
r
t’
s
elec
tr
ical
ac
tiv
ities
[
1
]
,
[
2
]
.
Desp
ite
ad
v
a
n
ce
m
en
t
s
,
ac
cu
r
ately
an
d
ef
f
icien
tly
in
ter
p
r
etin
g
E
C
G
s
ig
n
als
is
ch
allen
g
in
g
d
u
e
to
th
eir
in
h
e
r
en
t
c
o
m
p
lex
i
ty
an
d
v
ar
ia
b
ilit
y
.
R
af
ie
et
a
l
.
[
3
]
h
a
v
e
ar
g
u
e
d
th
at
tr
ad
itio
n
al
c
o
m
p
u
tatio
n
al
tech
n
iq
u
es
o
f
ten
s
tr
u
g
g
le
to
ad
d
r
ess
th
ese
ch
allen
g
es,
p
r
o
m
p
tin
g
th
e
e
x
p
lo
r
atio
n
o
f
m
o
r
e
ad
v
a
n
ce
d
s
o
lu
tio
n
s
.
R
elev
an
t
liter
atu
r
e
h
as
h
ig
h
lig
h
ted
s
ig
n
if
ican
t c
o
n
tr
ib
u
tio
n
s
to
n
eu
r
al
n
etwo
r
k
ap
p
licatio
n
s
an
d
m
a
ch
in
e
lear
n
in
g
alg
o
r
ith
m
s
in
b
io
m
ed
ical
s
ig
n
al
p
r
o
ce
s
s
in
g
,
as
r
ev
iewe
d
b
y
Z
em
o
u
r
i
et
a
l
.
[
4
]
.
T
h
ese
s
tu
d
ies
h
av
e
laid
th
e
g
r
o
u
n
d
wo
r
k
f
o
r
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
,
n
o
tin
g
ac
h
iev
em
e
n
ts
in
im
p
r
o
v
ed
a
cc
u
r
ac
y
an
d
p
r
o
ce
s
s
in
g
s
p
ee
d
ac
co
r
d
in
g
to
Sio
n
tis
et
a
l
.
[
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
2
,
No
v
em
b
er
20
24
:
8
6
3
-
8
7
1
864
Ho
wev
er
,
ch
allen
g
es
in
g
e
n
er
alizin
g
ac
r
o
s
s
d
iv
er
s
e
p
atien
t
d
atasets
an
d
th
e
n
e
ed
f
o
r
s
u
b
s
tan
tial
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
ar
e
o
f
ten
en
co
u
n
ter
ed
,
ac
co
r
d
in
g
to
s
ev
er
al
r
ec
en
t stu
d
ies [
6
]
,
[
7
]
.
C
u
r
r
en
t
m
eth
o
d
o
lo
g
ies
h
av
e
lim
itatio
n
s
in
p
r
o
ce
s
s
in
g
n
o
is
y
d
ata,
co
n
s
u
m
in
g
h
ig
h
p
o
wer
,
a
n
d
r
ec
o
g
n
izin
g
co
m
p
lex
E
C
G
p
atter
n
s
,
u
n
d
er
s
co
r
i
n
g
th
e
n
ee
d
f
o
r
in
n
o
v
ativ
e
ap
p
r
o
ac
h
es
to
im
p
r
o
v
e
th
e
r
o
b
u
s
tn
ess
an
d
ef
f
icien
c
y
o
f
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
s
y
s
tem
s
,
th
u
s
in
tr
o
d
u
cin
g
a
n
o
v
el
a
p
p
licatio
n
o
f
s
p
ik
in
g
n
eu
r
al
n
etwo
r
k
s
(
SNNs
)
in
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
.
Am
ir
i
et
a
l
.
[
8
]
in
s
p
ir
e
d
b
y
t
h
e
n
eu
r
al
p
r
o
ce
s
s
in
g
o
f
th
e
h
u
m
an
b
r
ain
,
SNNs
p
r
o
m
is
e
t
o
en
h
an
ce
th
e
ac
cu
r
ac
y
an
d
ef
f
icien
cy
o
f
p
atter
n
r
ec
o
g
n
itio
n
task
s
.
L
ev
er
ag
in
g
th
e
tem
p
o
r
al
d
y
n
am
ics
o
f
SNNs
aim
s
to
ad
d
r
ess
th
e
lim
ita
tio
n
s
o
f
tr
ad
itio
n
al
n
eu
r
al
n
et
wo
r
k
s
,
p
r
o
v
id
in
g
a
m
o
r
e
e
f
f
icien
t
a
n
d
s
ca
lab
le
s
o
l
u
tio
n
f
o
r
E
C
G
an
aly
s
is
as
ar
g
u
ed
b
y
Z
h
en
g
et
a
l
.
[
9
]
.
Hea
r
t
d
is
ea
s
e
was
am
o
n
g
th
e
to
p
g
lo
b
al
h
ea
lth
t
h
r
ea
ts
in
2
0
1
9
,
ac
c
o
r
d
in
g
to
th
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO
)
as
d
em
o
n
s
tr
ated
b
y
Yan
et
a
l
.
[
1
0
]
.
T
h
e
n
o
n
-
in
v
a
s
iv
e
m
eth
o
d
o
f
E
C
G
s
er
v
es
a
s
a
s
ig
n
if
ican
t
t
o
o
l
f
o
r
d
etec
ti
n
g
ca
r
d
io
v
ascu
lar
d
is
ea
s
e,
p
r
im
ar
ily
i
d
en
tify
in
g
ab
n
o
r
m
al
h
ea
r
t
b
ea
ts
with
in
s
e
v
er
al
r
ec
e
n
t
s
tu
d
ies
[
1
1
]
,
[
1
2
]
.
C
o
n
tin
u
o
u
s
E
C
G
m
o
n
ito
r
in
g
o
n
wea
r
a
b
le
d
ev
i
ce
s
h
as
b
ee
n
p
r
o
v
en
life
s
av
i
n
g
b
y
d
etec
tin
g
u
s
er
s
’
h
ea
r
tb
ea
t
ab
n
o
r
m
alities
,
in
cr
ea
s
in
g
ch
an
ce
s
f
o
r
in
itial
i
n
ter
v
en
tio
n
ac
co
r
d
in
g
to
Xiao
x
u
e
et
a
l
.
[
1
3
]
.
T
h
is
wo
r
k
p
r
e
s
en
ts
a
s
et
o
f
E
C
G
class
if
icatio
n
m
eth
o
d
s
u
s
in
g
SNN
to
class
if
y
h
ea
r
tb
ea
ts
i
n
to
n
o
r
m
al
an
d
a
b
n
o
r
m
al
ca
t
eg
o
r
ies,
aim
in
g
to
in
v
esti
g
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
SNN
alg
o
r
ith
m
,
d
ev
elo
p
a
class
if
icatio
n
alg
o
r
ith
m
b
ased
o
n
E
C
G
d
ata,
an
d
v
er
i
f
y
its
p
er
f
o
r
m
an
ce
th
r
o
u
g
h
c
o
n
f
u
s
io
n
tab
les an
d
m
e
an
av
er
ag
e
p
r
ec
is
io
n
.
SNNs
,
as
th
e
th
ir
d
g
e
n
er
atio
n
o
f
n
e
u
r
al
n
etwo
r
k
s
,
o
f
f
er
a
s
ig
n
if
ican
t
ad
v
an
tag
e
i
n
en
e
r
g
y
e
f
f
icien
cy
o
v
er
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
et
wo
r
k
s
(
C
NNs)
b
y
m
im
ick
in
g
th
e
way
b
io
lo
g
ical
n
etwo
r
k
s
p
r
o
ce
s
s
in
f
o
r
m
atio
n
th
r
o
u
g
h
s
p
ik
es.
L
o
wer
en
er
g
y
co
n
s
u
m
p
tio
n
m
ak
es
SNNs
id
ea
l
f
o
r
ap
p
licatio
n
s
in
ed
g
e
c
o
m
p
u
tin
g
,
r
o
b
o
tics
,
an
d
wea
r
ab
le
d
ev
ices
wh
er
e
p
o
wer
ef
f
icien
cy
is
cr
u
cial
as
d
em
o
n
s
tr
ated
in
Yan
et
a
l
.
[
1
0
]
.
Gu
o
et
a
l
.
[
1
4
]
SNNs
,
ca
p
ab
le
o
f
o
p
er
atin
g
with
f
ewe
r
lay
e
r
s
an
d
em
p
lo
y
in
g
a
d
y
n
am
ic
weig
h
t
m
o
d
el,
ef
f
icien
tl
y
ap
p
r
o
x
im
ate
r
ea
l
-
v
al
u
ed
f
u
n
c
tio
n
s
an
d
p
r
o
v
i
d
e
f
aster
c
o
m
p
u
tin
g
o
p
tio
n
s
.
S
o
d
h
r
o
et
a
l
.
[
1
5
]
t
h
e
in
n
o
v
ativ
e
ap
p
r
o
ac
h
en
h
a
n
ce
s
th
e
p
er
f
o
r
m
an
ce
o
f
l
o
w
-
p
o
wer
s
y
s
tem
s
,
p
ar
ticu
lar
ly
in
s
ec
to
r
s
r
eq
u
ir
i
n
g
en
er
g
y
-
e
f
f
icien
t
in
tellig
en
t
s
y
s
tem
s
,
s
u
ch
as
E
C
G
class
if
icatio
n
in
p
o
wer
-
co
n
s
tr
ain
ed
wea
r
ab
le
tech
n
o
l
o
g
y
.
T
h
e
s
tr
u
ctu
r
e
o
f
th
is
wo
r
k
i
n
clu
d
es
a
m
eth
o
d
o
lo
g
y
s
ec
tio
n
d
etailin
g
th
e
d
ev
elo
p
m
en
t
a
n
d
im
p
lem
en
tatio
n
o
f
th
e
SNN
-
b
ased
ap
p
r
o
ac
h
,
a
r
esu
lts
s
ec
tio
n
h
i
g
h
lig
h
tin
g
im
p
r
o
v
ed
p
er
f
o
r
m
an
ce
in
E
C
G
p
atter
n
r
ec
o
g
n
it
io
n
b
y
SNNs
with
r
ed
u
ce
d
co
m
p
u
tatio
n
al
d
em
an
d
s
,
a
d
is
cu
s
s
i
o
n
co
m
p
ar
i
n
g
th
e
a
p
p
r
o
ac
h
with
ex
is
tin
g
m
eth
o
d
s
a
n
d
em
p
h
asizin
g
its
ad
v
a
n
tag
es
an
d
r
ea
l
-
wo
r
ld
h
ea
lth
c
ar
e
a
p
p
licatio
n
s
,
an
d
a
co
n
clu
s
io
n
s
u
m
m
ar
izin
g
th
e
co
n
tr
ib
u
tio
n
s
an
d
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
,
em
p
h
asizin
g
SNNs
’
p
o
ten
tial
to
r
e
v
o
lu
ti
o
n
ize
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
.
2.
RE
L
AT
E
D
WO
RK
T
h
is
s
ec
tio
n
ex
p
lain
s
th
e
s
ig
n
if
ican
ce
o
f
E
C
G
an
d
h
ea
r
t
an
ato
m
y
in
d
iag
n
o
s
in
g
ca
r
d
iac
c
o
n
d
itio
n
s
,
em
p
h
asizin
g
th
e
ac
cu
r
ac
y
o
f
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
.
I
t
also
d
is
cu
s
s
es
th
e
ar
ch
itectu
r
e
o
f
SNNs
,
h
ig
h
lig
h
tin
g
th
eir
en
e
r
g
y
-
e
f
f
ic
ien
t
in
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
in
s
p
ir
ed
b
y
b
i
o
lo
g
ical
n
e
u
r
al
n
et
wo
r
k
s
.
Fin
ally
,
th
e
p
o
ten
tial
ap
p
licatio
n
s
o
f
SNNs
ar
e
ex
p
lo
r
e
d
,
h
ig
h
lig
h
tin
g
th
eir
ad
ap
tab
ilit
y
in
f
ield
s
r
an
g
in
g
f
r
o
m
m
e
d
ical
d
iag
n
o
s
tics
to
th
e
d
e
v
elo
p
m
e
n
t
o
f
en
er
g
y
-
e
f
f
icien
t
wea
r
a
b
le
tech
n
o
l
o
g
ies.
T
h
is
d
is
co
u
r
s
e
s
er
v
es
to
illu
s
tr
ate
th
e
g
r
o
u
n
d
b
r
ea
k
in
g
p
o
s
s
ib
ilit
i
es th
at
SN
Ns p
r
esen
t in
im
p
r
o
v
in
g
h
ea
lth
ca
r
e
o
u
tco
m
es th
r
o
u
g
h
en
h
a
n
ce
d
E
C
G
an
aly
s
is
.
2
.
1
.
E
lect
ro
c
a
rdio
g
ra
m
An
EC
G
ca
n
b
e
u
s
ed
to
d
iag
n
o
s
e
ca
r
d
iac
d
is
ea
s
e
as
d
em
o
n
s
tr
ated
in
Kh
a
n
et
a
l
.
[
1
6
]
.
B
ec
au
s
e
o
f
its
non
-
in
v
asiv
e
n
atu
r
e
,
it’s
co
m
m
o
n
ly
u
s
ed
t
o
id
en
tif
y
ca
r
d
ia
c
p
r
o
b
lem
s
.
B
y
v
is
u
ally
r
ev
ie
win
g
r
ec
o
r
d
in
g
s
o
f
E
C
G
s
ig
n
als,
tr
ain
ed
ca
r
d
io
lo
g
is
ts
ca
n
d
is
co
v
er
ab
n
o
r
m
al
ities
as
d
em
o
n
s
tr
ated
in
C
o
r
r
ad
i
et
a
l
.
[
1
1
]
.
I
t
g
iv
es
in
f
o
r
m
atio
n
o
n
th
e
elec
tr
ical
ac
tiv
ity
o
f
th
e
h
ea
r
t
in
th
e
h
e
ar
tb
ea
ts
o
f
p
atien
ts
in
s
ev
er
al
r
ec
en
t
s
tu
d
ies
[
1
2
]
.
E
C
G
is
g
ath
er
ed
f
r
o
m
ca
r
d
iac
m
u
s
cle
d
ep
o
la
r
izatio
n
to
r
ep
o
lar
izatio
n
b
y
elec
tr
o
d
es
p
u
t
o
n
th
e
p
atien
t’
s
s
k
in
t
h
a
t
r
e
c
o
r
d
e
l
e
c
t
r
i
c
c
h
a
n
g
e
s
d
u
r
i
n
g
t
h
e
c
a
r
d
i
a
c
c
y
c
l
e
a
c
c
o
r
d
i
n
g
t
o
Z
h
e
n
g
e
t
a
l
.
[
1
7
]
.
S
e
v
e
r
a
l
r
e
c
e
n
t
s
t
u
d
i
e
s
[
1
8
]
h
av
e
ar
g
u
ed
t
h
at
h
ea
r
t
m
o
n
ito
r
in
g
o
n
s
m
all
d
ev
ices,
esp
ec
ia
lly
wea
r
ab
le
d
ev
ices,
is
n
o
w
p
o
s
s
ib
le
b
ec
au
s
e
o
f
au
to
m
ated
E
C
G
d
iag
n
o
s
is
.
T
h
e
s
tan
d
ar
d
E
C
G
wav
ef
o
r
m
,
f
e
atu
r
in
g
th
e
P wa
v
e,
QR
S c
o
m
p
lex
,
an
d
T
wa
v
e,
is
d
ep
icted
in
Fig
u
r
e
1
.
T
h
r
o
u
g
h
th
e
wav
ef
o
r
m
’
s
s
ize
an
d
s
h
ap
e,
in
f
o
r
m
atio
n
o
n
ca
r
d
iac
illn
e
s
s
o
r
d
y
s
f
u
n
ctio
n
is
p
r
o
v
id
e
d
.
T
h
e
P
wav
e
ar
is
es
f
r
o
m
th
e
d
e
p
o
lar
izatio
n
o
f
t
h
e
atr
iu
m
.
W
h
en
th
er
e
is
v
e
n
tr
icu
lar
d
ep
o
lar
izatio
n
,
th
e
QR
S
co
m
p
lex
is
g
en
er
ally
th
e
p
r
im
ar
y
an
d
d
is
tin
ct
wav
ef
o
r
m
t
h
at
is
p
r
o
d
u
ce
d
as
d
e
m
o
n
s
tr
ated
in
R
an
a
an
d
Kim
[
1
9
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
N
eu
r
o
n
s
to
h
ea
r
tb
ea
ts
:
s
p
ikin
g
n
eu
r
a
l n
etw
o
r
ks fo
r
…
(
N
o
r
A
ma
lia
Da
ya
n
a
B
in
ti Mo
h
a
m
a
d
N
o
o
r
)
865
Fig
u
r
e
1
.
No
r
m
al
b
ea
t
[
1
9
]
,
[
2
0
]
2
.
2
.
H
ea
rt
a
na
t
o
m
y
Du
r
in
g
a
n
o
r
m
al
ca
r
d
iac
cy
cl
e,
an
elec
tr
ical
im
p
u
ls
e
is
em
itted
b
y
th
e
s
in
u
s
n
o
d
e.
T
h
is
im
p
u
ls
e
is
th
en
p
ass
ed
in
o
r
d
er
th
r
o
u
g
h
th
e
atr
ia,
atr
io
v
en
tr
icu
lar
n
o
d
e,
an
d
v
en
tr
icle.
I
r
r
eg
u
lar
s
o
u
r
ce
s
o
f
elec
tr
ical
im
p
u
ls
es
ca
n
lead
t
o
ab
n
o
r
m
a
l
ca
r
d
iac
r
h
y
th
m
s
ac
c
o
r
d
in
g
t
o
[
2
1
]
.
E
lectr
o
d
e
in
s
er
tio
n
o
n
th
e
s
k
in
o
f
a
p
er
s
o
n
d
etec
ts
th
at
elec
tr
icity
an
d
p
r
o
d
u
ce
s
a
v
o
ltag
e
-
tim
e
r
ea
d
o
u
t
th
at
p
r
o
d
u
ce
s
an
E
C
G.
T
h
e
E
C
G
s
ig
n
al
g
iv
es
h
u
m
an
h
ea
r
t
in
f
o
r
m
atio
n
wh
i
ch
in
clu
d
es
h
ea
r
t
p
o
s
itio
n
an
d
r
elativ
e
ch
am
b
er
s
ize,
o
r
i
g
in
an
d
p
r
o
p
ag
atio
n
o
f
im
p
u
ls
e,
r
h
y
th
m
ic
h
ea
r
t
an
d
co
n
d
u
ctio
n
,
m
y
o
ca
r
d
ial
is
ch
e
m
ia
s
ize,
an
d
lo
ca
tio
n
,
elec
tr
o
ly
te
co
n
ce
n
t
r
atio
n
ch
an
g
es,
an
d
h
ea
r
t e
f
f
ec
ts
ac
co
r
d
in
g
to
Aziz
et
a
l
.
[
1
2
]
.
2
.
3
.
SNN
a
rc
hite
ct
ure
I
n
Fig
u
r
e
2
,
th
e
ar
ch
itectu
r
e
o
f
th
e
SNN,
th
e
th
ir
d
g
e
n
e
r
atio
n
o
f
n
eu
r
al
n
etwo
r
k
s
,
is
d
ep
icted
,
s
h
o
win
g
h
o
w
in
f
o
r
m
atio
n
is
p
r
o
ce
s
s
ed
th
r
o
u
g
h
s
p
ik
e
s
ig
n
a
l
p
r
o
p
ag
atio
n
an
d
tim
in
g
,
with
s
y
n
ap
s
es
f
o
r
m
in
g
weig
h
ted
co
n
n
ec
tio
n
s
b
etwe
e
n
n
eu
r
o
n
s
to
f
a
cilitate
lear
n
in
g
v
ia
s
p
ik
e
-
tim
e
-
d
ep
e
n
d
en
t
p
last
icity
(
STDP)
.
T
h
e
STDP
r
u
le
is
u
s
ed
to
d
eter
m
in
e
h
o
w
m
u
c
h
ea
ch
p
r
e
-
s
y
n
ap
tic
s
p
ik
e
co
n
tr
ib
u
tes
to
th
e
t
o
tal
weig
h
t
ch
an
g
e
as
d
em
o
n
s
tr
ated
in
s
ev
er
al
r
e
ce
n
t
s
tu
d
ies
[
2
2
]
.
B
in
ar
y
s
p
ik
es
ar
e
th
e
d
ata
tr
an
s
f
er
r
ed
b
et
wee
n
lay
er
s
f
o
r
th
e
SNN
ac
co
r
d
in
g
to
L
iu
et
a
l
.
[
2
3
]
.
Utilizin
g
a
lear
n
in
g
alg
o
r
ith
m
d
esig
n
ed
f
o
r
m
u
lti
-
class
task
s
an
d
ex
ten
d
i
n
g
th
e
lear
n
in
g
r
u
le
to
h
an
d
le
m
u
lticlas
s
clas
s
if
icatio
n
ef
f
icien
tly
.
T
h
is
co
m
p
ac
t
ar
ch
itectu
r
e
e
n
s
u
r
es
co
m
p
ar
ab
le
p
er
f
o
r
m
an
ce
o
n
m
u
lti
-
class
class
if
icatio
n
p
r
o
b
lem
s
.
Fig
u
r
e
2
.
Ar
c
h
itectu
r
e
o
f
SNN
[
1
9
]
I
n
Fig
u
r
e
3
,
it
is
illu
s
tr
ated
t
h
at
in
p
u
t
s
p
ik
e
tim
in
g
s
ar
e
d
er
iv
ed
f
r
o
m
r
ea
l
-
v
alu
ed
d
ata,
wh
er
e
th
e
s
tr
en
g
th
o
f
r
ec
ep
tiv
e
f
ield
(
R
F)
n
eu
r
o
n
s
in
p
o
p
u
latio
n
en
co
d
in
g
is
tr
an
s
lated
in
to
s
p
ik
e
tim
e
s
.
Sy
n
ap
s
es
d
ef
in
e
th
e
s
tr
en
g
th
o
f
n
eu
r
al
co
n
n
ec
tio
n
s
,
u
tili
zin
g
a
tim
e
-
v
a
r
y
in
g
weig
h
t m
o
d
el
to
e
n
h
an
ce
th
e
d
y
n
am
ics o
f
lear
n
in
g
alg
o
r
ith
m
s
,
in
cl
u
d
in
g
th
e
STDP
r
u
le
f
o
r
weig
h
t
ad
j
u
s
tm
en
t.
Su
m
i
a
n
d
Har
ad
a
[
2
4
]
a
p
o
s
itiv
e
ch
an
g
e
in
weig
h
t
is
ca
lled
lo
n
g
-
ter
m
p
o
t
en
tiati
on
(
L
T
P)
an
d
a
n
eg
ativ
e
ch
an
g
e
in
weig
h
t
is
f
o
r
L
T
D.
Fo
r
class
if
icatio
n
task
s
,
SNN
s
ar
e
em
p
lo
y
ed
,
wh
er
e
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
,
th
r
o
u
g
h
m
ac
h
in
e
lear
n
i
n
g
,
le
ar
n
f
r
o
m
ev
en
ts
an
d
m
ak
e
d
ec
is
io
n
s
b
y
co
m
p
a
r
in
g
th
em
t
o
s
im
ilar
p
ast
o
cc
u
r
r
e
n
ce
s
.
I
n
ad
d
itio
n
,
a
r
tific
ial
n
e
u
r
al
n
etwo
r
k
s
h
a
v
e
th
e
p
o
ten
tial to
e
x
ec
u
te
s
ev
er
a
l ta
s
k
s
at
th
e
s
am
e
tim
e
as d
em
o
n
s
tr
ated
in
[
2
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
2
,
No
v
em
b
er
20
24
:
8
6
3
-
8
7
1
866
Fig
u
r
e
3
.
Me
ch
a
n
is
m
o
f
SNN
[
2
5
]
2
.
4
.
P
o
t
ent
ia
l
a
pp
lica
t
io
ns
R
ec
en
t
ad
v
an
ce
m
e
n
ts
in
m
e
d
ical
tech
n
o
l
o
g
y
h
av
e
s
h
if
te
d
to
war
d
s
e
n
ab
lin
g
co
n
tin
u
o
u
s
h
ea
lth
m
o
n
ito
r
in
g
o
u
ts
id
e
th
e
h
o
s
p
ital,
n
o
tab
ly
th
r
o
u
g
h
wea
r
ab
le
d
e
v
ices
f
o
r
d
aily
u
s
e,
allo
win
g
f
o
r
ea
s
y
tr
ac
k
in
g
o
f
v
ital
s
ig
n
s
lik
e
E
C
G
s
at
h
o
m
e
o
r
o
n
th
e
g
o
.
W
ea
r
ab
le
E
C
G
d
ev
ices
s
u
ch
as
th
e
Ap
p
le
W
a
tch
an
d
th
e
Xiao
m
i
Mi
B
u
n
n
y
Sm
ar
t
W
atch
n
o
w
ca
n
i
d
en
tify
h
ea
r
t
is
s
u
es
in
r
ea
l
-
tim
e
as
d
e
m
o
n
s
tr
ated
in
Yan
et
a
l
[
1
0
]
.
W
ea
r
ab
le
d
ev
ices,
f
o
cu
s
in
g
o
n
h
ea
lth
f
u
n
ctio
n
s
,
h
a
v
e
n
o
t
r
ec
eiv
ed
f
u
ll
f
o
o
d
a
n
d
d
r
u
g
s
a
d
m
in
is
tr
atio
n
(
FDA
)
ap
p
r
o
v
al
as m
ed
ical
eq
u
i
p
m
en
t,
an
d
co
n
s
u
ltatio
n
with
a
d
o
cto
r
is
d
ee
m
ed
ess
en
tial f
o
r
m
ed
ical
tr
ea
tm
en
t.
3.
M
E
T
H
O
D
E
C
G
d
ata,
s
o
u
r
ce
d
f
r
o
m
th
e
Ph
y
s
io
Net
d
atab
ases
an
d
in
clu
s
iv
e
o
f
v
ar
i
o
u
s
ca
r
d
iac
co
n
d
itio
n
s
an
d
h
ea
lth
y
co
n
tr
o
ls
,
was
p
r
e
-
p
r
o
ce
s
s
ed
to
en
h
an
ce
s
ig
n
al
q
u
al
ity
an
d
co
n
s
is
ten
cy
.
T
h
is
p
r
e
p
r
o
ce
s
s
in
g
in
v
o
lv
ed
b
an
d
-
p
ass
f
ilter
in
g
,
n
o
r
m
aliza
tio
n
,
an
d
s
eg
m
en
tatio
n
i
n
to
in
d
iv
id
u
al
h
ea
r
tb
ea
ts
.
Fo
r
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
,
an
SNN
ar
ch
itectu
r
e
was
s
p
ec
ially
d
esig
n
ed
,
t
h
is
ar
ch
itectu
r
e
f
ea
tu
r
ed
in
p
u
t,
h
id
d
en
,
an
d
o
u
tp
u
t
la
y
er
s
with
leak
y
in
teg
r
ate
-
a
n
d
-
f
ir
e
n
eu
r
o
n
s
,
ef
f
ec
tiv
ely
em
u
latin
g
b
i
o
lo
g
ical
in
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
an
d
e
f
f
icien
tly
ca
p
tu
r
in
g
t
h
e
tem
p
o
r
al
d
y
n
am
ics o
f
E
C
G
s
ig
n
als.
T
h
e
SNN
was
tr
ain
e
d
u
s
in
g
a
s
p
ec
if
ic
lear
n
in
g
alg
o
r
ith
m
an
d
m
o
d
if
ied
to
s
u
it
t
h
e
s
p
ec
if
icities
o
f
E
C
G
s
ig
n
al
p
r
o
ce
s
s
in
g
.
Par
a
m
eter
s
wer
e
m
eticu
lo
u
s
ly
s
el
ec
ted
b
ased
o
n
p
a
r
am
eter
s
ele
ctio
n
o
f
th
e
n
u
m
b
e
r
o
f
RF
n
eu
r
o
n
s
in
th
e
p
o
p
u
lati
o
n
en
c
o
d
in
g
s
ch
em
e
R
F,
th
e
i
n
ter
v
al
b
etwe
en
p
r
esy
n
ap
tic
s
p
ik
es
(
p
r
e
(
m
s
)
)
,
th
e
in
ter
v
al
b
etwe
en
p
o
s
ts
y
n
ap
tic
s
p
ik
es
(
p
o
s
t
(
m
s
)
)
,
th
e
d
esire
d
p
o
s
ts
y
n
ap
tic
f
ir
in
g
tim
e
(
d
esire
d
p
o
s
t
(
m
s
)
)
,
tim
e
-
s
tep
p
r
ec
is
io
n
(
p
r
ec
is
io
n
)
,
th
e
weig
h
t
u
p
d
ate
r
ate
o
f
l
ea
r
n
in
g
(
∆w
)
,
th
e
s
ig
m
a
o
f
a
weig
h
t
k
er
n
al
th
at
ch
an
g
es
with
tim
e
(
σ
(
m
s
)
)
,
th
e
tim
e
co
n
s
tan
t
o
f
th
e
s
p
i
k
e
r
esp
o
n
s
e
f
u
n
ctio
n
(
(
m
s
)
)
,
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
ep
o
c
h
s
(
ep
o
ch
)
,
an
d
STD
P
lear
n
in
g
win
d
o
w
o
f
tim
e
c
o
n
s
tan
t
(
STDP
(
m
s
)
)
,
en
s
u
r
in
g
o
p
tim
al
n
etwo
r
k
p
er
f
o
r
m
an
ce
.
T
h
e
t
r
ain
in
g
i
n
v
o
lv
e
d
a
s
u
p
er
v
is
ed
lear
n
i
n
g
ap
p
r
o
ac
h
with
cr
o
s
s
-
v
alid
atio
n
to
p
r
e
v
en
t
o
v
er
f
itti
n
g
,
wi
th
p
er
f
o
r
m
an
ce
m
etr
ics in
clu
d
in
g
ac
c
u
r
ac
y
,
s
en
s
itiv
ity
,
an
d
s
p
ec
if
icity
.
E
x
p
er
im
en
ts
wer
e
co
n
d
u
cted
u
s
in
g
MA
T
L
AB
to
en
s
u
r
e
r
ep
r
o
d
u
cib
ilit
y
,
with
th
e
d
ataset
d
iv
id
e
d
in
to
tr
ain
in
g
an
d
test
in
g
s
p
lits
o
f
6
0
%
-
4
0
%,
7
0
%
-
3
0
%,
an
d
8
0
%
-
2
0
%
r
esp
ec
tiv
ely
.
T
h
ese
ex
p
er
im
en
ts
allo
wed
f
o
r
th
e
co
m
p
ar
is
o
n
o
f
r
esu
lts
ag
ain
s
t
estab
lis
h
ed
b
en
ch
m
ar
k
s
f
o
r
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
.
C
h
o
s
en
f
o
r
th
eir
u
n
iq
u
e
ab
ilit
y
to
p
r
o
ce
s
s
tem
p
o
r
al
s
eq
u
en
ce
s
in
E
C
G
s
ig
n
als,
SN
Ns
d
em
o
n
s
tr
ated
co
m
p
u
tatio
n
al
ef
f
icien
cy
a
n
d
p
er
f
o
r
m
an
ce
a
cc
u
r
ac
y
a
d
v
an
ta
g
es
o
v
e
r
tr
ad
i
tio
n
al
n
eu
r
al
n
etwo
r
k
s
,
a
ca
p
ab
ilit
y
u
n
d
er
p
in
n
ed
b
y
r
ec
en
t
a
d
v
an
ce
m
en
ts
in
n
eu
r
o
m
o
r
p
h
ic
co
m
p
u
tin
g
.
T
h
e
m
eth
o
d
o
lo
g
y
,
d
esig
n
ed
to
b
e
tr
an
s
p
ar
e
n
t
an
d
r
ep
licab
le,
was
ef
f
ec
tiv
ely
ap
p
lied
to
u
tili
ze
in
n
o
v
ativ
e
SNN
tech
n
o
lo
g
y
f
o
r
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
.
T
h
is
ap
p
r
o
ac
h
ad
d
r
ess
ed
id
en
tifie
d
g
ap
s
,
b
eg
in
n
in
g
with
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
,
a
n
d
in
clu
d
in
g
m
eticu
lo
u
s
p
r
ep
r
o
ce
s
s
in
g
,
s
im
u
latio
n
,
an
d
f
in
e
-
tu
n
in
g
o
f
th
e
SNN
alg
o
r
i
th
m
to
o
p
tim
ize
weig
h
t a
d
ju
s
t
m
en
ts
,
cu
lm
in
atin
g
in
a
co
m
p
r
eh
en
s
iv
e
a
n
aly
s
is
o
f
s
i
m
u
latio
n
o
u
tc
o
m
es wh
en
tr
ain
in
g
an
d
test
in
g
r
esu
lts
wer
e
u
n
s
atis
f
ac
to
r
y
.
3
.
1
.
H
ea
rt
bea
t
da
t
a
s
et
Utilizin
g
th
e
Ph
y
s
io
n
et
d
atab
ase,
th
is
s
tu
d
y
an
aly
s
ed
2
0
0
E
C
G
s
ig
n
als,
in
clu
d
in
g
8
0
‘
n
o
r
m
al
’
an
d
1
2
0
‘
ab
n
o
r
m
al
’
,
th
r
o
u
g
h
em
p
ir
ical
m
o
d
e
d
ec
o
m
p
o
s
itio
n
(
E
MD
)
f
o
r
s
ig
n
al
q
u
ality
en
h
a
n
ce
m
en
t,
e
x
tr
ac
tin
g
3
0
0
f
ea
tu
r
es
p
er
s
ig
n
al
to
tr
ai
n
th
e
SNN
f
o
r
p
r
ec
is
e
class
if
icatio
n
.
Desp
ite
ef
f
o
r
ts
to
en
h
a
n
ce
SNN
ac
cu
r
ac
y
with
an
ad
d
itio
n
al
lay
er
,
t
h
e
m
o
s
t
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
ca
m
e
f
r
o
m
E
MD
-
b
ased
f
ea
tu
r
e
r
ef
in
em
e
n
t
,
u
n
d
er
s
co
r
i
n
g
its
e
f
f
ec
tiv
en
ess
in
p
r
e
p
r
o
ce
s
s
in
g
f
o
r
ac
cu
r
ate
E
C
G
p
atter
n
an
al
y
s
is
.
T
h
is
s
tr
ea
m
lin
ed
ap
p
r
o
ac
h
n
o
t
o
n
l
y
o
p
tim
ized
th
e
class
if
icatio
n
p
r
o
ce
s
s
b
u
t
also
d
em
o
n
s
tr
ated
th
e
p
o
ten
tial
o
f
E
MD
in
ad
v
a
n
cin
g
E
C
G
s
ig
n
al
in
ter
p
r
etatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
N
eu
r
o
n
s
to
h
ea
r
tb
ea
ts
:
s
p
ikin
g
n
eu
r
a
l n
etw
o
r
ks fo
r
…
(
N
o
r
A
ma
lia
Da
ya
n
a
B
in
ti Mo
h
a
m
a
d
N
o
o
r
)
867
3
.
2
.
P
re
-
pro
ce
s
s
ing
Fig
u
r
e
4
s
h
o
ws
th
e
b
lo
c
k
d
iag
r
am
f
o
r
p
r
e
-
p
r
o
ce
s
s
in
g
i
n
Fig
u
r
e
4
(
a)
an
d
f
o
r
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
in
Fig
u
r
e
4
(
b
)
.
I
n
th
ese
m
eth
o
d
s
,
n
o
is
e
an
d
d
is
to
r
tio
n
s
wer
e
i
n
itially
r
em
o
v
e
d
f
r
o
m
b
o
th
n
o
r
m
al
an
d
ab
n
o
r
m
al
d
atasets
u
s
in
g
E
MD
,
an
d
weig
h
t
m
o
d
els
f
r
o
m
I
MF1
to
I
MF1
0
wer
e
s
elec
ted
f
o
r
th
e
SNN
’
s
lear
n
in
g
alg
o
r
ith
m
.
T
h
e
E
C
G
tr
ain
in
g
a
n
d
test
in
g
d
atasets
wer
e
d
iv
id
ed
in
to
th
r
ee
g
r
o
u
p
s
o
f
60%
-
4
0
%,
7
0
%
-
3
0
%,
an
d
80%
-
20%
to
ac
co
m
m
o
d
ate
th
e
ef
f
ec
ts
o
f
lo
w
o
r
h
i
g
h
-
f
r
eq
u
en
cy
n
o
is
e
th
at
ca
n
in
f
lu
en
ce
QR
S
d
etec
tio
n
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
d
u
r
in
g
r
ec
o
r
d
in
g
.
T
h
is
d
iv
is
io
n
allo
ws
f
o
r
a
th
o
r
o
u
g
h
a
n
aly
s
is
o
f
v
ar
io
u
s
E
C
G
d
ataset
s
,
h
elp
in
g
to
id
en
tif
y
th
e
m
o
s
t
s
u
itab
le
f
ea
tu
r
es
f
o
r
ea
ch
d
iag
n
o
s
tic
s
y
s
tem
b
y
elim
in
at
in
g
n
o
is
e
p
r
im
ar
ily
ca
u
s
ed
b
y
ar
tifa
cts
an
d
ad
d
r
ess
in
g
in
d
iv
id
u
al
d
if
f
er
en
ce
s
in
p
ea
k
an
d
wav
ef
o
r
m
s
h
ap
es
th
r
o
u
g
h
f
u
r
th
er
ex
am
in
atio
n
a
n
d
p
r
ep
r
o
ce
s
s
in
g
o
f
th
e
1
2
-
lea
d
E
C
G
s
ig
n
als.
(
a)
(
b
)
Fig
u
r
e
4
.
B
lo
ck
d
iag
r
am
f
o
r
(
a
)
p
re
-
p
r
o
ce
s
s
in
g
an
d
(
b
)
p
r
o
p
o
s
ed
m
eth
o
d
3
.
3
.
E
x
t
r
a
ct
io
n a
nd
s
elec
t
io
n o
f
f
ea
t
ures
Fo
r
th
is
wo
r
k
,
2
5
f
ea
tu
r
es
wer
e
ex
tr
ac
ted
,
in
cl
u
d
in
g
15
-
tim
e
d
o
m
ain
f
ea
tu
r
es
s
u
ch
as
m
ea
n
,
s
tan
d
ar
d
d
ev
iatio
n
,
an
d
s
k
ewn
ess
,
alo
n
g
with
10
ce
p
s
tr
al
d
o
m
ai
n
f
ea
tu
r
es
th
at
in
clu
d
e
c
o
ef
f
icien
ts
o
f
th
e
m
el
f
r
eq
u
e
n
cy
ce
p
s
tr
al
an
d
g
am
m
ato
n
e
ce
p
s
tr
al
f
ea
tu
r
es
(
MFC
C
+G
T
C
C
)
.
T
h
ese
f
ea
tu
r
es
ar
e
p
r
o
ce
s
s
ed
th
r
o
u
g
h
m
u
ltip
le
o
p
er
a
tio
n
s
s
u
ch
as
f
o
u
r
ier
tr
a
n
s
f
o
r
m
,
f
ilter
b
a
n
k
ap
p
licatio
n
,
an
d
d
is
cr
ete
co
s
i
n
e
tr
an
s
f
o
r
m
,
wh
ich
ar
e
ex
ec
u
ted
in
s
eq
u
en
ce
.
T
h
is
co
m
b
in
atio
n
o
f
tim
e
-
d
o
m
a
in
an
d
ce
p
s
tr
al
f
ea
tu
r
es
ca
p
tu
r
es
b
o
th
s
tatis
tical
p
r
o
p
er
ties
an
d
s
p
ec
tr
al
ch
a
r
a
cter
is
tics
,
o
f
f
er
in
g
b
en
ef
its
f
o
r
v
ar
io
u
s
m
ac
h
in
e
lea
r
n
in
g
a
p
p
licatio
n
s
s
u
ch
as
class
if
icatio
n
,
clu
s
ter
in
g
,
o
r
r
e
g
r
ess
io
n
.
3
.
4
.
L
ea
rning
a
lg
o
rit
hm
pa
r
a
m
et
er
s
o
f
SNN
I
n
a
SNN
,
th
e
n
eu
r
o
n
’
s
s
tate
i
s
d
eter
m
in
ed
b
y
its
ac
tiv
ity
lev
el,
m
o
d
elled
as
a
d
if
f
er
e
n
tial
eq
u
atio
n
,
wh
er
e
an
in
p
u
t
p
u
ls
e
tem
p
o
r
a
r
ily
in
cr
ea
s
es
th
e
cu
r
r
en
t
s
tate
v
alu
e
an
d
th
e
n
g
r
ad
u
ally
d
ec
r
ea
s
es
.
E
s
tab
li
s
h
in
g
a
f
u
n
ctio
n
in
g
SNN
is
ch
allen
g
in
g
,
as
th
e
tr
ai
n
in
g
p
r
o
ce
s
s
r
esem
b
les
th
e
h
u
m
an
b
r
ain
’
s
d
ata
p
r
o
ce
s
s
in
g
,
b
u
t
f
ac
to
r
s
s
u
ch
as
im
p
r
o
v
ed
u
n
s
u
p
er
v
is
ed
lear
n
in
g
m
eth
o
d
s
m
ak
e
SNNs
ap
p
ea
lin
g
.
T
en
p
ar
am
eter
s
will
b
e
ch
o
s
en
f
o
r
th
e
lear
n
i
n
g
alg
o
r
ith
m
p
ar
am
eter
s
o
f
SNN,
in
clu
d
in
g
th
e
n
u
m
b
e
r
o
f
RF
n
eu
r
o
n
s
in
th
e
p
o
p
u
latio
n
en
co
d
in
g
s
ch
em
e
(
R
F),
in
ter
v
als
b
etwe
en
p
r
esy
n
ap
tic
s
p
ik
es
(
p
r
e)
,
in
ter
v
als
b
etwe
en
p
o
s
ts
y
n
ap
tic
s
p
ik
es
(
p
o
s
t)
,
d
esire
d
p
o
s
ts
y
n
ap
tic
f
i
r
in
g
tim
e
(
d
esire
d
p
o
s
t)
,
tim
e
-
s
tep
p
r
ec
is
io
n
(
p
r
ec
is
io
n
)
,
th
e
weig
h
t
u
p
d
ate
r
ate
o
f
lear
n
in
g
(
∆w
)
,
s
ig
m
a
o
f
a
weig
h
t
ed
k
er
n
el
th
at
ch
a
n
g
e
s
with
tim
e
(
σ
)
,
th
e
tim
e
co
n
s
tan
t
o
f
th
e
s
p
ik
e
r
esp
o
n
s
e
f
u
n
ctio
n
(
)
,
t
h
e
m
ax
im
u
m
n
u
m
b
er
o
f
e
p
o
ch
s
(
ep
o
ch
)
,
an
d
STDP
lear
n
i
n
g
win
d
o
w
o
f
tim
e
co
n
s
tan
t (
STDP)
.
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
is
s
tu
d
y
em
b
ar
k
ed
o
n
a
jo
u
r
n
ey
to
u
n
v
eil
th
e
in
tr
icac
ies
o
f
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
u
s
in
g
SNNs
.
Prio
r
in
v
esti
g
atio
n
s
h
av
e
d
el
v
ed
in
to
th
e
r
ea
lm
s
o
f
n
e
u
r
al
n
etwo
r
k
ap
p
licatio
n
s
an
d
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
f
o
r
b
io
m
e
d
ical
s
ig
n
al
p
r
o
ce
s
s
in
g
,
y
et
a
g
a
p
p
er
s
is
ts
in
f
u
lly
h
ar
n
ess
in
g
th
e
te
m
p
o
r
al
d
y
n
am
ics
o
f
E
C
G
s
ig
n
als.
Ou
r
r
esear
ch
a
im
s
to
b
r
id
g
e
th
is
d
iv
id
e,
o
f
f
er
in
g
in
s
ig
h
ts
in
to
th
e
ap
p
licatio
n
o
f
SNNs
f
o
r
ac
cu
r
ate
an
d
e
f
f
icien
t c
ar
d
iac
ar
r
h
y
th
m
ia
id
en
tific
atio
n
.
Ou
r
r
esu
lts
s
h
o
w
s
ig
n
if
ican
t
p
r
o
g
r
ess
in
E
C
G
p
atter
n
r
ec
o
g
n
itio
n
,
with
a
test
in
g
ac
cu
r
a
cy
r
ea
ch
in
g
9
1
.
6
6
6
7
%
an
d
tr
ain
in
g
ac
c
u
r
ac
y
u
p
to
9
9
.
2
8
5
7
%.
T
h
ese
f
ig
u
r
es
h
ig
h
lig
h
t
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
SNN
class
if
ier
in
ac
cu
r
ately
d
is
tin
g
u
is
h
in
g
b
etwe
en
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
E
C
G
p
atter
n
s
.
Su
ch
p
er
f
o
r
m
an
ce
co
n
f
ir
m
s
th
e
class
if
ier
’
s
r
eliab
ilit
y
an
d
p
r
ec
is
io
n
i
n
an
aly
s
in
g
ca
r
d
iac
r
h
y
th
m
s
.
C
o
m
p
ar
ativ
ely
,
o
u
r
s
tu
d
y
u
n
d
er
s
co
r
es
th
e
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
o
f
SNNs
ag
ain
s
t
tr
ad
itio
n
al
n
eu
r
al
n
etwo
r
k
s
an
d
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
.
T
h
e
em
p
l
o
y
m
en
t
o
f
SNNs
ca
p
ital
izes
o
n
th
eir
ab
ilit
y
to
m
im
ic
b
io
lo
g
ical
n
eu
r
al
p
r
o
ce
s
s
in
g
m
o
r
e
clo
s
ely
,
r
esu
ltin
g
in
en
h
an
ce
d
ef
f
icien
c
y
an
d
lo
wer
p
o
wer
co
n
s
u
m
p
tio
n
.
T
h
is
ap
p
r
o
ac
h
n
o
t
o
n
ly
alig
n
s
with
b
u
t
also
s
u
r
p
ass
es
cu
r
r
e
n
t
m
eth
o
d
o
lo
g
ies,
p
ar
ticu
lar
ly
in
r
ec
o
g
n
izin
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
2
,
No
v
em
b
er
20
24
:
8
6
3
-
8
7
1
868
co
m
p
lex
,
tem
p
o
r
al
p
atter
n
s
i
n
h
er
en
t
in
E
C
G
d
ata.
Ou
r
r
e
s
ea
r
ch
th
o
r
o
u
g
h
l
y
ass
ess
es
S
NNs
in
r
ec
o
g
n
izin
g
E
C
G
p
atter
n
s
b
u
t
r
elies
h
ea
v
ily
o
n
p
r
e
-
p
r
o
ce
s
s
ed
d
ata
f
r
o
m
th
e
Ph
y
s
io
Net
d
atab
ase.
I
t
’
s
n
ec
ess
ar
y
to
test
th
e
m
o
d
el
o
n
a
wid
er
v
a
r
iety
o
f
d
atasets
,
esp
ec
ially
th
o
s
e
f
r
o
m
r
ea
l
-
wo
r
ld
clin
ical
e
n
v
ir
o
n
m
en
ts
wh
er
e
d
ata
v
ar
ies m
o
r
e.
T
h
is
s
tep
will h
elp
co
n
f
i
r
m
th
e
m
o
d
el
’
s
ef
f
ec
tiv
en
ess
in
d
if
f
er
en
t settin
g
s
.
Ou
r
r
esear
ch
o
p
en
s
u
p
ex
citin
g
p
o
s
s
ib
ilit
ies
f
o
r
im
p
r
o
v
in
g
ca
r
d
iac
m
o
n
ito
r
in
g
tec
h
n
o
lo
g
i
es.
Fu
tu
r
e
s
tu
d
ies
m
ig
h
t
lo
o
k
in
to
co
m
b
in
in
g
SNNs
with
n
e
u
r
o
m
o
r
p
h
ic
h
ar
d
war
e
to
cr
ea
te
h
y
b
r
id
m
o
d
els
th
at
b
r
in
g
to
g
eth
er
d
if
f
er
en
t
c
o
m
p
u
tin
g
t
ec
h
n
iq
u
es.
Su
ch
d
ev
elo
p
m
en
t
s
c
o
u
ld
ex
ten
d
th
e
u
s
e
o
f
SNNs
to
a
wid
er
r
an
g
e
o
f
task
s
in
b
io
m
e
d
ical
s
ig
n
al
p
r
o
ce
s
s
in
g
,
en
h
a
n
cin
g
th
ei
r
o
v
e
r
all
ef
f
ec
tiv
en
ess
.
Ou
r
r
esear
ch
d
em
o
n
s
tr
ates
m
ajo
r
im
p
r
o
v
em
e
n
ts
in
u
s
in
g
SNNs
to
r
ec
o
g
n
ize
E
C
G
p
atter
n
s
,
wh
ich
h
elp
s
b
etter
id
e
n
tify
ca
r
d
iac
a
r
r
h
y
th
m
ias
an
d
r
aises
th
e
ac
cu
r
ac
y
s
tan
d
a
r
d
s
f
o
r
h
ea
r
t
m
o
n
ito
r
in
g
.
T
h
is
wo
r
k
ad
d
r
ess
es
s
ig
n
if
ican
t
g
a
p
s
in
o
u
r
s
cien
tific
u
n
d
er
s
tan
d
i
n
g
an
d
s
h
o
ws
th
at
ad
v
a
n
ce
d
n
eu
r
al
n
etwo
r
k
s
ca
n
s
u
b
s
tan
tially
im
p
r
o
v
e
p
atien
t
ca
r
e.
W
e
r
ec
o
m
m
en
d
ad
o
p
tin
g
th
ese
ad
v
an
ce
d
tech
n
o
lo
g
i
es
to
d
ev
elo
p
s
m
ar
ter
an
d
m
o
r
e
ad
ap
tiv
e
h
ea
lth
ca
r
e
s
o
lu
tio
n
s
.
4
.
1
.
E
v
a
lua
t
i
o
n o
f
t
he
perf
o
rm
a
nce
o
f
E
CG
s
Fig
u
r
e
5
s
h
o
ws
th
e
p
r
e
-
p
r
o
c
ess
in
g
s
ig
n
al
u
s
in
g
E
MD
f
o
r
n
o
r
m
al
d
ata
in
Fig
u
r
e
5
(
a
)
an
d
f
o
r
ab
n
o
r
m
al
d
ata
in
Fig
u
r
e
5
(
b
)
.
B
ased
o
n
Fig
u
r
e
5
,
it
is
o
b
s
e
r
v
ed
th
at
t
h
e
b
l
u
e
c
u
r
v
e
ex
h
ib
its
a
h
ig
h
er
f
r
eq
u
e
n
cy
f
o
r
th
e
o
r
ig
i
n
al
s
ig
n
al,
wh
er
ea
s
th
e
o
r
an
g
e
c
u
r
v
e
ap
p
ea
r
s
s
m
o
o
th
e
r
f
o
r
th
e
p
r
e
-
p
r
o
ce
s
s
ed
(
f
ilter
ed
)
s
ig
n
al.
Fig
u
r
e
6
s
h
o
ws
t
h
e
e
f
f
ec
t
o
f
th
e
o
p
tim
ized
p
a
r
am
ete
r
o
f
SNN
f
o
r
th
r
ee
g
r
o
u
p
s
o
f
t
r
ain
in
g
an
d
te
s
tin
g
r
esp
ec
tiv
ely
at
60%
-
4
0
%,
7
0
%
-
3
0
%,
an
d
8
0
%
-
20%
,
an
d
th
eir
ac
cu
r
ac
ies
to
war
d
s
t
h
e
p
er
f
o
r
m
an
ce
o
f
co
n
v
er
g
en
ce
b
ased
o
n
th
e
p
a
r
am
eter
tu
n
in
g
o
f
l
ea
r
n
i
n
g
r
a
te
o
f
weig
h
t
u
p
d
ate
(
∆w
)
,
th
e
s
ig
m
a
o
f
a
weig
h
t
k
er
n
al
th
at
ch
an
g
es
with
tim
e
(
σ
(
m
s
)
)
,
t
h
e
tim
e
c
o
n
s
tan
t
o
f
th
e
s
p
ik
e
r
esp
o
n
s
e
f
u
n
ctio
n
(
(
m
s
)
)
,
an
d
a
m
ax
im
u
m
n
u
m
b
er
o
f
ep
o
ch
s
.
Fig
u
r
es
6
d
ep
ict
lear
n
in
g
o
u
tco
m
es
u
s
in
g
d
if
f
e
r
en
t
tr
ain
in
g
-
test
in
g
d
ata
s
p
lits
f
o
r
6
0
%
-
4
0
%,
7
0
%
-
3
0
%,
an
d
8
0
%
-
20%
in
Fig
u
r
es 6
(
a)
t
o
6
(
i)
.
(
a)
(
b
)
Fig
u
r
e
5
.
E
C
G
p
r
e
-
p
r
o
ce
s
s
in
g
f
o
r
(
a)
n
o
r
m
al
s
ig
n
al
an
d
(
b
)
a
b
n
o
r
m
al
s
ig
n
al
B
ased
o
n
Fig
u
r
e
6
,
t
h
e
o
p
tim
ized
p
ar
am
eter
s
f
o
r
SNNs
u
n
d
er
d
if
f
e
r
en
t
tr
ain
in
g
-
test
in
g
s
p
lits
an
d
th
eir
r
esp
ec
tiv
e
ac
cu
r
ac
ies.
Fo
r
tr
ain
in
g
a
n
d
test
in
g
ac
cu
r
a
cies,
th
e
ac
cu
r
ac
ies
v
ar
y
ac
r
o
s
s
d
if
f
er
en
t
s
p
lits
.
Gen
er
ally
,
tr
ain
in
g
ac
cu
r
ac
y
is
h
ig
h
er
,
wh
ich
is
ex
p
ec
ted
.
Ho
wev
er
,
th
e
test
in
g
ac
c
u
r
ac
y
s
h
o
ws
s
o
m
e
v
ar
ian
ce
,
n
o
tab
ly
b
ei
n
g
lo
wer
in
th
e
tr
ain
in
g
test
in
g
r
atio
o
f
8
0
:2
0
s
p
lit.
Mo
s
t
p
ar
a
m
eter
s
o
f
SNN
lik
e
R
F
with
th
e
v
alu
e
o
f
1
5
,
p
r
esy
n
ap
tic
(
p
r
e)
,
p
o
s
ts
y
n
ap
tic
(
p
o
s
t)
,
d
esire
d
p
o
s
ts
y
n
ap
tic
(
d
esire
d
p
o
s
t)
with
t
h
e
v
al
u
e
o
f
0
.
2
,
tim
e
-
s
tep
p
r
ec
is
io
n
(
p
r
ec
is
io
n
)
with
th
e
v
alu
e
o
f
0
.
0
1
,
a
n
d
STDP
r
em
ain
co
n
s
is
t
en
t
ac
r
o
s
s
d
if
f
er
en
t
s
p
lits
,
wh
ile
o
th
er
s
lik
e
lear
n
in
g
r
ate
(
∆
w
)
,
e
f
f
icac
y
u
p
d
ate
r
an
g
e
(
σ)
,
T
au
(
)
,
an
d
ep
o
c
h
s
h
o
w
v
ar
iatio
n
s
.
E
f
f
ec
ts
o
n
c
o
n
v
er
g
en
ce
,
s
u
ch
as
th
e
p
ar
am
eter
o
f
lear
n
in
g
r
a
te
(
∆w
)
,
p
ar
ticu
la
r
ly
with
a
h
i
g
h
er
v
alu
e
(
∆w
=
0
.
5
)
in
th
e
8
0
:2
0
tr
ain
i
n
g
-
test
in
g
r
atio
s
p
lit,
m
a
y
ca
u
s
e
th
e
m
o
d
el
to
o
v
er
s
h
o
o
t
th
e
o
p
tim
al
s
o
lu
tio
n
.
R
esu
ltin
g
in
lo
wer
test
in
g
a
cc
u
r
ac
y
,
with
th
e
lear
n
in
g
r
ate
af
f
ec
tin
g
b
o
th
th
e
s
p
ee
d
a
n
d
s
tab
ilit
y
o
f
co
n
v
er
g
en
ce
.
W
h
ile
a
h
ig
h
le
ar
n
in
g
r
ate
(
∆w
)
ca
n
lea
d
to
f
aster
co
n
v
er
g
e
n
ce
,
it
m
ay
o
v
e
r
s
h
o
o
t
th
e
o
p
tim
al
s
o
lu
tio
n
,
as
o
b
s
er
v
ed
in
Fig
u
r
e
s
6
(
g
)
,
6
(
h
)
,
an
d
6
(
i)
,
in
d
icatin
g
th
at
b
o
th
ex
ce
s
s
iv
ely
lo
w
an
d
h
ig
h
lear
n
in
g
r
ates
ca
n
ad
v
er
s
ely
af
f
ec
t
p
er
f
o
r
m
a
n
ce
,
s
u
g
g
esti
n
g
th
at
a
m
o
d
er
ate
lear
n
in
g
r
ate
is
o
p
tim
al
f
o
r
b
alan
cin
g
tr
ain
in
g
s
p
ee
d
a
n
d
c
o
n
v
er
g
en
c
e
s
tab
ilit
y
.
T
h
en
,
f
o
r
t
h
e
ef
f
icac
y
u
p
d
ate
r
an
g
e
(
σ
)
,
th
is
p
ar
am
eter
also
in
cr
ea
s
es
in
th
e
tr
ain
in
g
test
in
g
r
atio
o
f
8
0
:2
0
s
p
lit
with
th
e
v
alu
e
o
f
(
σ
=
0
.
5
5
)
,
wh
ich
af
f
ec
ts
th
e
m
o
d
el’
s
g
en
er
aliza
tio
n
ca
p
a
b
ilit
y
.
Fo
r
T
a
u
(
)
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
N
eu
r
o
n
s
to
h
ea
r
tb
ea
ts
:
s
p
ikin
g
n
eu
r
a
l n
etw
o
r
ks fo
r
…
(
N
o
r
A
ma
lia
Da
ya
n
a
B
in
ti Mo
h
a
m
a
d
N
o
o
r
)
869
th
e
v
alu
e
in
th
e
tr
ain
in
g
test
in
g
r
atio
o
f
8
0
:2
0
s
p
lit,
wh
ich
af
f
ec
ts
th
e
m
o
d
el’
s
ab
ilit
y
t
o
ca
p
tu
r
e
tem
p
o
r
al
d
y
n
am
ics
in
th
e
d
ata
with
th
e
v
alu
e
o
f
(
=
1,
2,
a
n
d
3
)
r
esp
ec
ti
v
ely
.
T
h
is
s
h
o
ws
t
h
a
t
th
e
v
alu
e
o
f
T
au
in
f
lu
en
ce
s
th
e
m
o
d
el’
s
ab
ilit
y
to
ca
p
tu
r
e
tem
p
o
r
al
d
y
n
a
m
ics
in
E
C
G
d
ata,
wh
ich
is
cr
u
cial
f
o
r
ac
cu
r
ately
class
if
y
in
g
h
ea
r
tb
ea
ts
T
h
en
,
f
o
r
ep
o
c
h
s
m
ax
im
u
m
,
th
e
m
a
x
im
u
m
n
u
m
b
e
r
o
f
ep
o
c
h
s
is
co
n
s
is
ten
t
in
m
o
s
t
ca
s
es,
b
u
t
r
ed
u
ce
d
ep
o
ch
s
in
o
n
e
o
f
th
e
tr
ain
in
g
test
in
g
r
atio
s
o
f
7
0
:3
0
s
p
lit
s
ce
n
ar
io
s
ex
p
lain
th
e
s
lig
h
tly
lo
wer
tr
ain
in
g
ac
c
u
r
ac
y
with
t
h
e
v
alu
e
o
f
(
e
p
o
ch
=
2
0
).
I
n
ad
d
itio
n
,
f
o
r
STDP
(
Sp
ik
e
-
T
im
in
g
-
Dep
e
n
d
en
t
Plas
ticit
y
)
with
th
e
v
alu
e
o
f
1
.
6
,
th
i
s
r
em
ain
s
co
n
s
tan
t
ac
r
o
s
s
all
s
ce
n
ar
io
s
,
s
u
g
g
esti
n
g
th
at
th
e
m
o
d
el’
s
ab
ilit
y
to
ad
ap
t
its
s
y
n
ap
tic
wei
g
h
ts
b
ased
o
n
s
p
ik
e
tim
in
g
s
is
u
n
c
h
an
g
e
d
.
T
h
en
,
f
o
r
p
r
esy
n
ap
tic
(
p
r
e)
an
d
p
o
s
ts
y
n
ap
tic
(
p
o
s
t)
p
ar
a
m
eter
s
with
th
e
v
alu
es
o
f
(
p
r
e=
0
.
3
)
an
d
(
p
o
s
t=0
.
4
4
)
r
esp
ec
tiv
ely
,
th
ese
p
ar
am
eter
s
ar
e
m
o
s
tly
co
n
s
is
ten
t b
u
t d
o
s
h
o
w
a
m
in
o
r
ch
an
g
e
in
o
n
e
o
f
th
e
tr
ai
n
in
g
test
in
g
r
ati
o
s
o
f
8
0
:2
0
s
p
lit
s
ce
n
ar
io
s
,
wh
ich
co
u
ld
a
f
f
ec
t
th
e
m
o
d
el’
s
s
en
s
itiv
ity
to
in
p
u
t
an
d
o
u
t
p
u
t
s
p
ik
es.
T
h
e
r
o
le
o
f
s
p
ik
e
-
tim
in
g
-
d
e
p
en
d
e
n
t
p
last
icity
(
STDP
)
in
ad
ap
tin
g
s
y
n
a
p
tic
weig
h
ts
b
ased
o
n
th
e
tim
in
g
o
f
in
co
m
in
g
s
p
ik
es
is
h
ig
h
lig
h
ted
as
a
k
e
y
f
e
atu
r
e
o
f
SNNs
th
at
co
n
tr
ib
u
te
s
to
th
eir
b
io
lo
g
ical
r
ea
lis
m
an
d
ef
f
ec
tiv
e
n
ess
in
cla
s
s
if
icatio
n
task
s
.
T
h
e
o
p
tim
ized
p
a
r
am
eter
s
s
ig
n
if
ican
tl
y
af
f
ec
t
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
i
n
b
o
th
tr
ain
in
g
an
d
test
in
g
ac
cu
r
ac
ies,
with
p
ar
am
eter
s
s
u
c
h
as
lear
n
in
g
r
ate
(
∆w
)
,
ef
f
icac
y
u
p
d
ate
r
an
g
e
(
σ
)
,
T
au
(
)
,
an
d
ep
o
ch
p
lay
in
g
cr
u
cial
r
o
les
in
th
e
m
o
d
el
’
s
co
n
v
er
g
en
ce
ca
p
ab
ilit
ies,
h
ig
h
lig
h
tin
g
th
e
im
p
o
r
ta
n
ce
o
f
p
a
r
am
eter
o
p
tim
izatio
n
f
o
r
en
h
an
ci
n
g
m
o
d
el
p
er
f
o
r
m
an
ce
an
d
ac
h
iev
in
g
a
b
alan
ce
b
etwe
en
tr
ai
n
in
g
a
n
d
t
esti
n
g
ac
cu
r
ac
ies ac
r
o
s
s
v
ar
io
u
s
d
ata
s
p
lits
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(f)
(
g
)
(
h
)
(
i)
Fig
u
r
e
6
.
C
o
n
v
er
g
e
n
ce
p
er
f
o
r
m
an
ce
f
o
r
d
ata
o
f
:
(
a)
6
0
%
tr
a
in
in
g
-
4
0
% testi
n
g
,
(
b
)
6
0
% tr
a
in
in
g
-
4
0
% testi
n
g
,
(
c)
6
0
% tr
ain
i
n
g
-
4
0
% testi
n
g
,
(
d
)
7
0
% tr
ain
in
g
-
2
0
% testi
n
g
,
(
e)
7
0
% tr
ain
i
n
g
-
2
0
% testi
n
g
,
(
f
)
7
0
% tr
ain
in
g
-
2
0
% testi
n
g
,
(
g
)
8
0
% tr
ain
in
g
-
2
0
% testi
n
g
,
(
h
)
8
0
% tr
ain
in
g
-
2
0
% testi
n
g
,
an
d
(
i)
8
0
% tr
ain
in
g
-
2
0
% testi
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
2
,
No
v
em
b
er
20
24
:
8
6
3
-
8
7
1
870
5.
CO
NCLU
SI
O
N
C
ar
d
io
v
ascu
lar
ar
r
h
y
th
m
ia
d
i
ag
n
o
s
is
r
elies
o
n
ch
a
r
ac
ter
is
tics
o
f
h
ea
r
tb
ea
ts
an
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
.
W
h
en
u
s
ed
in
co
m
b
in
atio
n
with
a
n
E
MD
E
C
G
s
y
s
t
em
,
th
e
cr
ea
ted
SNN
m
o
d
els
ar
e
ca
p
a
b
le
o
f
class
if
y
in
g
m
u
ltip
le
h
ea
r
tb
ea
t
ty
p
es.
SNN’
s
lear
n
in
g
p
ar
am
e
ter
s
h
av
e
b
ee
n
ev
alu
ate
d
wh
er
e
th
e
v
alu
e
o
f
T
a
u
(
)
,
ef
f
icac
y
u
p
d
ate
r
an
g
e
(
σ
)
,
lear
n
in
g
r
ate
(
∆w
)
,
a
n
d
m
ax
i
m
u
m
n
u
m
b
er
o
f
e
p
o
ch
s
(
e
p
o
c
h
)
,
s
h
o
w
s
ig
n
if
ica
n
t
ef
f
ec
ts
f
o
r
th
e
ac
cu
r
ac
y
o
f
th
e
tr
ain
in
g
an
d
test
in
g
d
ata
r
esp
ec
tiv
ely
.
T
h
is
wo
r
k
ac
h
iev
es m
ax
im
u
m
o
f
tr
ai
n
in
g
ac
cu
r
ac
y
an
d
test
in
g
ac
cu
r
ac
y
o
f
9
9
.
1
6
6
7
%
an
d
9
1
.
2
5
%
f
o
r
tr
ain
in
g
test
in
g
r
atio
o
f
6
0
:4
0
,
9
9
.
2
8
5
7
%
an
d
9
1
.
6
6
6
7
%
o
f
tr
ain
in
g
ac
cu
r
ac
y
an
d
test
in
g
ac
cu
r
ac
y
f
o
r
tr
ai
n
in
g
test
in
g
r
atio
o
f
7
0
:3
0
s
p
l
it,
an
d
8
3
.
7
5
%
an
d
8
0
%
o
f
tr
ain
i
n
g
ac
cu
r
ac
y
a
n
d
test
in
g
ac
cu
r
ac
y
f
o
r
tr
ain
in
g
te
s
tin
g
r
atio
o
f
8
0
:2
0
s
p
lit
d
ata
r
esp
ec
tiv
ely
f
o
r
th
e
class
if
icatio
n
o
f
E
C
G
r
h
y
th
m
s
,
d
em
o
n
s
tr
ates th
e
ca
p
ab
ilit
y
t
o
class
if
y
h
ea
r
tb
ea
ts
u
s
in
g
SNN.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
ac
k
n
o
wled
g
e
t
h
e
tech
n
ical
an
d
f
in
a
n
cial
s
u
p
p
o
r
t
b
y
th
e
Min
is
tr
y
o
f
Hig
h
er
E
d
u
ca
tio
n
,
Ma
lay
s
ia,
u
n
d
er
r
esear
ch
g
r
an
t
n
o
.
FR
GS/1
/2
0
2
0
/I
C
T
0
2
/UT
E
M/0
2
/1
an
d
Un
iv
er
s
iti
T
ek
n
ik
al
Ma
lay
s
ia
Me
lak
a
(
UT
eM
)
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
A
z
i
z
,
S
.
A
h
me
d
,
a
n
d
M
.
S
.
A
l
o
u
i
n
i
,
“
EC
G
-
b
a
s
e
d
ma
c
h
i
n
e
-
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
h
e
a
r
t
b
e
a
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
.
1
8
7
3
8
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
1
-
9
7
1
1
8
-
5.
[
2
]
H
.
W
u
e
t
a
l
.
,
“
A
f
u
l
l
y
-
a
u
t
o
ma
t
e
d
p
a
p
e
r
EC
G
d
i
g
i
t
i
s
a
t
i
o
n
a
l
g
o
r
i
t
h
m
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
2
0
9
6
3
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
022
-
2
5
2
8
4
-
1.
[
3
]
N
.
R
a
f
i
e
,
A
.
H
.
K
a
s
h
o
u
,
a
n
d
P
.
A
.
N
o
sewo
r
t
h
y
,
“
EC
G
i
n
t
e
r
p
r
e
t
a
t
i
o
n
:
c
l
i
n
i
c
a
l
r
e
l
e
v
a
n
c
e
,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
a
d
v
a
n
c
e
s,”
H
e
a
rt
s
,
v
o
l
.
2
,
n
o
.
4
,
p
p
.
5
0
5
–
5
1
3
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
h
e
a
r
t
s
2
0
4
0
0
3
9
.
[
4
]
R
.
Ze
m
o
u
r
i
,
N
.
Ze
r
h
o
u
n
i
,
a
n
d
D
.
R
a
c
o
c
e
a
n
u
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
t
h
e
b
i
o
m
e
d
i
c
a
l
a
p
p
l
i
c
a
t
i
o
n
s
:
r
e
c
e
n
t
a
n
d
f
u
t
u
r
e
st
a
t
u
s,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
9
,
n
o
.
8
,
p
.
1
5
2
6
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
9
0
8
1
5
2
6
.
[
5
]
K
.
C
.
S
i
o
n
t
i
s,
P
.
A
.
N
o
s
e
w
o
r
t
h
y
,
Z.
I
.
A
t
t
i
a
,
a
n
d
P
.
A
.
F
r
i
e
d
ma
n
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
-
e
n
h
a
n
c
e
d
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
p
h
y
i
n
c
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
sea
s
e
ma
n
a
g
e
me
n
t
,
”
N
a
t
u
r
e
R
e
v
i
e
w
s
C
a
rd
i
o
l
o
g
y
,
v
o
l
.
1
8
,
n
o
.
7
,
p
p
.
4
6
5
–
4
7
8
,
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
6
9
-
020
-
0
0
5
0
3
-
2.
[
6
]
F
.
K
h
a
n
,
X
.
Y
u
,
Z
.
Y
u
a
n
,
a
n
d
A
.
u
r
R
e
h
ma
n
,
“
E
C
G
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
1
-
D
c
o
n
v
o
l
u
t
i
o
n
a
l
d
e
e
p
r
e
s
i
d
u
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
PLO
S
O
N
E
,
v
o
l
.
1
8
,
n
o
.
4
,
p
.
e
0
2
8
4
7
9
1
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
4
7
9
1
.
[
7
]
P
.
S
i
l
v
a
e
t
a
l
.
,
“
T
o
w
a
r
d
s
b
e
t
t
e
r
h
e
a
r
t
b
e
a
t
s
e
g
m
e
n
t
a
t
i
o
n
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
.
2
0
7
0
1
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
0
-
7
7
7
4
5
-
0.
[
8
]
M
.
A
mi
r
i
,
A
.
H
.
J
a
f
a
r
i
,
B
.
M
a
k
k
i
a
b
a
d
i
,
a
n
d
S
.
N
a
z
a
r
i
,
“
R
e
c
o
g
n
i
z
i
n
g
i
n
t
e
r
t
w
i
n
e
d
p
a
t
t
e
r
n
s
u
s
i
n
g
a
n
e
t
w
o
r
k
o
f
sp
i
k
i
n
g
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
p
l
a
t
f
o
r
ms
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
1
9
4
3
6
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
022
-
2
3
3
2
0
-
8.
[
9
]
H
.
Z
h
e
n
g
e
t
a
l
.
,
“
Te
m
p
o
r
a
l
d
e
n
d
r
i
t
i
c
h
e
t
e
r
o
g
e
n
e
i
t
y
i
n
c
o
r
p
o
r
a
t
e
d
w
i
t
h
s
p
i
k
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
l
e
a
r
n
i
n
g
mu
l
t
i
-
t
i
mes
c
a
l
e
d
y
n
a
mi
c
s
,
”
N
a
t
u
re
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
2
7
7
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
4
6
7
-
0
2
3
-
4
4
6
1
4
-
z.
[
1
0
]
Z.
Y
a
n
,
J.
Z
h
o
u
,
a
n
d
W
.
-
F
.
W
o
n
g
,
“
E
n
e
r
g
y
e
f
f
i
c
i
e
n
t
EC
G
c
l
a
ss
i
f
i
c
a
t
i
o
n
w
i
t
h
s
p
i
k
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
B
i
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pro
c
e
ssi
n
g
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
6
3
,
p
.
1
0
2
1
7
0
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
0
.
1
0
2
1
7
0
.
[
1
1
]
F
.
C
o
r
r
a
d
i
e
t
a
l
.
,
“
E
C
G
-
b
a
se
d
h
e
a
r
t
b
e
a
t
c
l
a
ssi
f
i
c
a
t
i
o
n
i
n
n
e
u
r
o
m
o
r
p
h
i
c
h
a
r
d
w
a
r
e
,
”
i
n
2
0
1
9
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
N
e
u
ra
l
N
e
t
w
o
rks
(
I
J
C
N
N
)
,
Ju
l
.
2
0
1
9
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
JC
N
N
.
2
0
1
9
.
8
8
5
2
2
7
9
.
[
1
2
]
S
.
A
z
i
z
,
M
.
U
.
K
h
a
n
,
M
.
A
l
h
a
i
so
n
i
,
T.
A
k
r
a
m,
a
n
d
M
.
A
l
t
a
f
,
“
P
h
o
n
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
p
r
o
c
e
ss
i
n
g
f
o
r
a
u
t
o
m
a
t
i
c
d
i
a
g
n
o
s
i
s
o
f
c
o
n
g
e
n
i
t
a
l
h
e
a
r
t
d
i
so
r
d
e
r
s
t
h
r
o
u
g
h
f
u
si
o
n
o
f
t
e
m
p
o
r
a
l
a
n
d
c
e
p
s
t
r
a
l
f
e
a
t
u
r
e
s,
”
S
e
n
s
o
rs
,
v
o
l
.
2
0
,
n
o
.
1
3
,
p
.
3
7
9
0
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
1
3
3
7
9
0
.
[
1
3
]
L.
X
i
a
o
x
u
e
e
t
a
l
.
,
“
R
e
v
i
e
w
o
f
me
d
i
c
a
l
d
a
t
a
a
n
a
l
y
si
s
b
a
s
e
d
o
n
s
p
i
k
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
2
1
,
p
p
.
1
5
2
7
–
1
5
3
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
3
.
0
8
.
1
3
8
.
[
1
4
]
Y
.
G
u
o
e
t
a
l
.
,
“
R
e
a
l
s
p
i
k
e
:
l
e
a
r
n
i
n
g
r
e
a
l
-
v
a
l
u
e
d
s
p
i
k
e
s
f
o
r
s
p
i
k
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
s
e
ri
e
s
L
e
c
t
u
re
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
B
i
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
1
3
6
7
2
LN
C
S
,
2
0
2
2
,
p
p
.
5
2
–
6
8
.
[
1
5
]
A
.
S
o
d
h
r
o
,
A
.
S
a
n
g
a
i
a
h
,
G
.
S
o
d
h
r
o
,
S
.
L
o
h
a
n
o
,
a
n
d
S
.
P
i
r
b
h
u
l
a
l
,
“
A
n
e
n
e
r
g
y
-
e
f
f
i
c
i
e
n
t
a
l
g
o
r
i
t
h
m
f
o
r
w
e
a
r
a
b
l
e
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
p
r
o
c
e
ss
i
n
g
i
n
u
b
i
q
u
i
t
o
u
s
h
e
a
l
t
h
c
a
r
e
a
p
p
l
i
c
a
t
i
o
n
s
,
”
S
e
n
s
o
rs
,
v
o
l
.
1
8
,
n
o
.
3
,
p
.
9
2
3
,
M
a
r
.
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
s1
8
0
3
0
9
2
3
.
[
1
6
]
M
.
U
.
K
h
a
n
,
S
.
A
z
i
z
,
S
.
Z
.
H
a
ss
a
n
N
a
q
v
i
,
a
n
d
A
.
R
e
h
ma
n
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
c
o
r
o
n
a
r
y
a
r
t
e
r
y
d
i
s
e
a
s
e
s
u
s
i
n
g
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m
si
g
n
a
l
s,
”
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
S
m
a
rt
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
ET
S
T
)
,
M
a
r
.
2
0
2
0
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
ETST
4
9
9
6
5
.
2
0
2
0
.
9
0
8
0
6
9
4
.
[
1
7
]
J.
Zh
e
n
g
,
J.
Zh
a
n
g
,
S
.
D
a
n
i
o
k
o
,
H
.
Y
a
o
,
H
.
G
u
o
,
a
n
d
C
.
R
a
k
o
v
s
k
i
,
“
A
1
2
-
l
e
a
d
e
l
e
c
t
r
o
c
a
r
d
i
o
g
r
a
m d
a
t
a
b
a
se
f
o
r
a
r
r
h
y
t
h
mi
a
r
e
sea
r
c
h
c
o
v
e
r
i
n
g
m
o
r
e
t
h
a
n
1
0
,
0
0
0
p
a
t
i
e
n
t
s,”
S
c
i
e
n
t
i
f
i
c
D
a
t
a
,
v
o
l
.
7
,
n
o
.
1
,
p
.
4
8
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
7
-
0
2
0
-
0
3
8
6
-
x.
[
1
8
]
Q
.
Li
u
a
n
d
Z.
Z
h
a
n
g
,
“
U
l
t
r
a
l
o
w
p
o
w
e
r
a
l
w
a
y
s
-
o
n
i
n
t
e
l
l
i
g
e
n
t
a
n
d
c
o
n
n
e
c
t
e
d
S
N
N
-
b
a
se
d
sy
s
t
e
m
f
o
r
mu
l
t
i
me
d
i
a
I
o
T
-
e
n
a
b
l
e
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
I
EE
E
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s J
o
u
r
n
a
l
,
v
o
l
.
9
,
n
o
.
1
7
,
p
p
.
1
5
5
7
0
–
1
5
5
7
7
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
2
.
3
1
5
0
3
0
7
.
[
1
9
]
A
.
R
a
n
a
a
n
d
K
.
K
.
K
i
m,
“
A
n
o
v
e
l
s
p
i
k
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
EC
G
s
i
g
n
a
l
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
O
U
RN
AL O
F
S
EN
S
O
R
S
C
I
EN
C
E
A
N
D
T
EC
H
N
O
L
O
G
Y
,
v
o
l
.
3
0
,
n
o
.
1
,
p
p
.
2
0
–
2
4
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
4
6
6
7
0
/
JS
S
T.
2
0
2
1
.
3
0
.
1
.
2
0
.
[
2
0
]
L.
G
u
o
,
G
.
S
i
m
,
a
n
d
B
.
M
a
t
u
s
z
e
w
s
k
i
,
“
I
n
t
e
r
-
p
a
t
i
e
n
t
EC
G
c
l
a
ssi
f
i
c
a
t
i
o
n
w
i
t
h
c
o
n
v
o
l
u
t
i
o
n
a
l
a
n
d
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
Bi
o
c
y
b
e
r
n
e
t
i
c
s
a
n
d
Bi
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
9
,
n
o
.
3
,
p
p
.
8
6
8
–
8
7
9
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
b
e
.
2
0
1
9
.
0
6
.
0
0
1
.
[
2
1
]
S
.
J.
R
.
J
.
Lo
g
a
n
t
h
a
e
t
a
l
.
,
“
S
i
n
u
s
n
o
d
e
-
l
i
k
e
p
a
c
e
ma
k
e
r
mec
h
a
n
i
sms
r
e
g
u
l
a
t
e
e
c
t
o
p
i
c
p
a
c
e
m
a
k
e
r
a
c
t
i
v
i
t
y
i
n
t
h
e
a
d
u
l
t
r
a
t
a
t
r
i
o
v
e
n
t
r
i
c
u
l
a
r
r
i
n
g
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
9
,
n
o
.
1
,
p
.
1
1
7
8
1
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
1
9
-
4
8
2
7
6
-
0.
[
2
2
]
A
.
Je
y
a
s
o
t
h
y
,
S
.
S
u
n
d
a
r
a
m,
a
n
d
N
.
S
u
n
d
a
r
a
r
a
j
a
n
,
“
S
EFRO
N
:
a
n
e
w
s
p
i
k
i
n
g
n
e
u
r
o
n
mo
d
e
l
w
i
t
h
t
i
m
e
-
v
a
r
y
i
n
g
sy
n
a
p
t
i
c
e
f
f
i
c
a
c
y
f
u
n
c
t
i
o
n
f
o
r
p
a
t
t
e
r
n
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
s
a
n
d
L
e
a
r
n
i
n
g
S
y
s
t
e
m
s
,
v
o
l
.
3
0
,
n
o
.
4
,
p
p
.
1
2
3
1
–
1
2
4
0
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
N
LS.
2
0
1
8
.
2
8
6
8
8
7
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
N
eu
r
o
n
s
to
h
ea
r
tb
ea
ts
:
s
p
ikin
g
n
eu
r
a
l n
etw
o
r
ks fo
r
…
(
N
o
r
A
ma
lia
Da
ya
n
a
B
in
ti Mo
h
a
m
a
d
N
o
o
r
)
871
[
2
3
]
F
.
L
i
u
,
W
.
Zh
a
o
,
Y
.
C
h
e
n
,
Z.
W
a
n
g
,
T.
Y
a
n
g
,
a
n
d
L.
Ji
a
n
g
,
“
S
S
TD
P
:
S
u
p
e
r
v
i
s
e
d
s
p
i
k
e
t
i
m
i
n
g
d
e
p
e
n
d
e
n
t
p
l
a
s
t
i
c
i
t
y
f
o
r
e
f
f
i
c
i
e
n
t
sp
i
k
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
t
r
a
i
n
i
n
g
,
”
Fro
n
t
i
e
rs
i
n
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
1
5
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
8
9
/
f
n
i
n
s
.
2
0
2
1
.
7
5
6
8
7
6
.
[
2
4
]
T.
S
u
mi
a
n
d
K
.
H
a
r
a
d
a
,
“
M
e
c
h
a
n
i
s
m
u
n
d
e
r
l
y
i
n
g
h
i
p
p
o
c
a
m
p
a
l
l
o
n
g
-
t
e
r
m
p
o
t
e
n
t
i
a
t
i
o
n
a
n
d
d
e
p
r
e
ssi
o
n
b
a
se
d
o
n
c
o
m
p
e
t
i
t
i
o
n
b
e
t
w
e
e
n
e
n
d
o
c
y
t
o
s
i
s
a
n
d
e
x
o
c
y
t
o
s
i
s
o
f
A
M
P
A
r
e
c
e
p
t
o
r
s
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
.
1
4
7
1
1
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
020
-
7
1
5
2
8
-
3.
[
2
5
]
A
.
Jey
a
s
o
t
h
y
,
S
.
R
a
m
a
sam
y
,
a
n
d
S
.
S
u
n
d
a
r
a
m,
“
M
L
m
e
t
h
o
d
s
i
n
sp
i
k
i
n
g
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
p
r
o
b
l
e
ms,
”
I
J
C
N
N
,
n
o
.
Ju
l
y
,
2
0
1
9
,
d
o
i
:
1
0
.
1
3
1
4
0
/
R
G
.
2
.
2
.
2
2
4
8
6
.
4
0
0
0
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
No
r
Am
a
li
a
Da
y
a
n
a
B
in
ti
Mo
h
a
m
a
d
N
o
o
r
is
c
u
rr
e
n
tl
y
u
n
d
e
rtak
i
n
g
p
o
stg
ra
d
u
a
te
st
u
d
ies
a
t
Un
i
v
e
rsiti
Tek
n
ik
a
l
M
a
lay
sia
M
e
lak
a
(
UTe
M
),
M
a
lay
sia
.
S
h
e
h
a
s
c
o
m
p
lete
d
h
e
r
M
a
ste
r
o
f
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
,
s
p
e
c
ializin
g
i
n
El
e
c
tro
n
ic
S
y
ste
m
s,
a
t
UTe
M
in
2
0
2
1
.
T
h
is
a
c
h
iev
e
m
e
n
t
f
o
ll
o
ws
h
e
r
g
ra
d
u
a
ti
o
n
wit
h
a
Ba
c
h
e
l
o
r
o
f
El
e
c
tro
n
ics
En
g
i
n
e
e
rin
g
Tec
h
n
o
l
o
g
y
,
f
o
c
u
si
n
g
o
n
I
n
d
u
str
ial
El
e
c
tro
n
ics
,
with
Ho
n
o
u
rs
i
n
2
0
2
0
,
a
lso
fro
m
UTe
M
i
n
M
a
lac
c
a
,
M
a
lay
sia
.
He
r
a
c
a
d
e
m
ic
jo
u
r
n
e
y
is
m
a
rk
e
d
b
y
a
n
in
te
n
se
e
a
g
e
rn
e
ss
to
e
x
p
l
o
re
a
n
d
a
ss
imilate
k
n
o
wle
d
g
e
p
e
rt
in
e
n
t
t
o
h
e
r
field
o
f
stu
d
y
,
sh
o
wc
a
sin
g
h
e
r
d
e
d
ica
ti
o
n
a
n
d
p
a
ss
io
n
fo
r
h
e
r
s
p
e
c
ializa
ti
o
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
0
2
2
2
1
0
0
0
4
@s
tu
d
e
n
t
.
u
tem
.
e
d
u
.
m
y
.
Wo
n
g
Y
a
n
Chi
e
w
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
o
f
th
e
F
a
c
u
lt
y
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
p
u
ter
Tec
h
n
o
lo
g
y
a
n
d
En
g
i
n
e
e
rin
g
a
t
Un
i
v
e
rsiti
Tek
n
i
k
a
l
M
a
lay
sia
M
e
lak
a
(UTe
M
).
S
h
e
c
o
m
p
lete
d
h
e
r
d
o
c
to
ra
te
fro
m
Th
e
Un
iv
e
rsity
o
f
Ed
i
n
b
u
rg
h
,
Un
it
e
d
Kin
g
d
o
m
in
2
0
1
4
.
S
h
e
h
a
s
m
o
re
th
a
n
n
i
n
e
y
e
a
rs
o
f
in
d
u
str
y
e
x
p
e
rien
c
e
in
se
m
ico
n
d
u
c
to
r
d
e
sig
n
.
S
h
e
h
a
s
p
re
v
io
u
sly
w
o
rk
e
d
a
t
In
f
in
e
o
n
T
e
c
h
n
o
l
o
g
ies
,
In
tel,
a
n
d
S
o
fa
n
t
T
e
c
h
n
o
l
o
g
ies
.
S
h
e
h
a
s
b
e
e
n
in
v
o
lv
e
d
in
ten
si
v
e
ly
i
n
t
h
e
re
se
a
rc
h
o
f
IC
d
e
sig
n
,
a
p
p
li
e
d
i
n
telli
g
e
n
t
c
o
m
p
u
ti
n
g
,
a
n
d
p
o
we
r
m
a
n
a
g
e
m
e
n
t/
h
a
rv
e
st
in
g
d
e
sig
n
.
S
h
e
is
a
re
c
ip
ie
n
t
o
f
d
iffere
n
t
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
a
wa
rd
s
su
c
h
a
s
ITE
X,
INN
OV
ATE,
IEM
,
a
n
d
EDS
so
c
ieties
.
S
h
e
is
e
q
u
i
p
p
e
d
wit
h
b
o
th
d
e
sig
n
a
n
d
imp
lem
e
n
tatio
n
sk
il
ls.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
y
c
wo
n
g
@
u
tem
.
e
d
u
.
m
y
.
Za
r
in
a
Mo
h
d
No
h
is
a
se
n
i
o
r
lec
tu
re
r
a
t
t
h
e
F
a
c
u
lt
y
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
p
u
ter
Tec
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
rin
g
a
t
Un
iv
e
rsiti
Tek
n
ik
a
l
M
a
lay
sia
M
e
lak
a
(UTe
M
).
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
.
D.
d
e
g
re
e
fr
o
m
Un
i
v
e
rsiti
P
u
tra
M
a
lay
sia
in
2
0
1
9
m
a
jo
rin
g
in
Co
m
p
u
ter
a
n
d
e
m
b
e
d
d
e
d
sy
ste
m
e
n
g
i
n
e
e
rin
g
.
Cu
rre
n
tl
y
a
tt
a
c
h
e
d
to
t
h
e
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t
i
n
th
e
fa
c
u
lt
y
,
s
h
e
h
a
s
ta
u
g
h
t
c
o
u
rse
s
m
o
stly
re
late
d
to
c
o
m
p
u
ter
e
n
g
i
n
e
e
rin
g
c
o
u
rse
s.
He
r
m
a
in
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
,
e
m
b
e
d
d
e
d
sy
ste
m
s,
a
n
d
ima
g
e
p
ro
c
e
ss
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
z
a
r
in
a
.
n
o
h
@
u
tem
.
e
d
u
.
m
y
.
Ra
n
jit
S
i
n
g
h
S
a
r
b
a
n
S
in
g
h
is
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
a
t
th
e
S
c
h
o
o
l
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
,
S
u
n
wa
y
Un
i
v
e
rsity
,
M
a
lay
sia
.
He
c
o
m
p
lete
d
h
is
d
o
c
to
ra
te
fr
o
m
Bru
n
e
l
U
n
iv
e
rsit
y
,
L
o
n
d
o
n
Un
it
e
d
Kin
g
d
o
m
in
2
0
1
6
.
He
h
a
s
3
y
e
a
rs
o
f
i
n
d
u
strial
wo
r
k
in
g
e
x
p
e
rien
c
e
a
s
a
n
e
n
g
in
e
e
r
with
Wes
tern
Dig
it
a
l
S
d
n
.
Bh
d
.
As
a
n
a
c
a
d
e
m
icia
n
,
h
is
re
se
a
r
c
h
a
re
a
m
o
stly
fo
c
u
se
d
o
n
e
m
b
e
d
d
e
d
sy
ste
m
d
e
sig
n
–
b
a
tt
e
ry
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s,
re
n
e
wa
b
le
e
n
e
rg
y
s
y
ste
m
d
e
v
e
lo
p
m
e
n
t,
a
n
d
ima
g
e
p
r
o
c
e
ss
in
g
.
He
h
a
s
a
lso
wo
n
n
u
m
e
ro
u
s
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
a
wa
rd
s
a
t
ITE
X,
M
TE
,
INN
OV
A
Bru
ss
e
ls,
a
n
d
m
a
n
y
m
o
re
.
He
is
a
lso
a
c
ti
v
e
ly
e
n
g
a
g
i
n
g
wit
h
in
d
u
str
ies
to
e
q
u
i
p
h
ims
e
lf
with
i
n
d
u
strial
k
n
o
wl
e
d
g
e
,
wh
ich
c
a
n
b
e
sh
a
re
d
d
u
ri
n
g
h
is
tea
c
h
in
g
a
n
d
lea
rn
i
n
g
a
c
ti
v
i
ti
e
s
with
stu
d
e
n
ts.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
n
ji
ts@s
u
n
wa
y
.
e
d
u
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.