I
n
d
on
e
s
i
an
Jo
u
r
n
al
o
f
El
e
c
t
r
i
c
al
En
gi
n
e
e
r
i
n
g
an
d
C
o
m
p
u
te
r
S
c
i
e
n
c
e
V
o
l
.
20
,
N
o
.
2
,
N
o
v
e
m
b
e
r
20
20
,
pp.
976
~
984
IS
S
N
:
25
02
-
4752
,
D
O
I
:
10.
1
1591
/
i
j
e
e
c
s
.
v
20
.i
2
.
pp976
-
984
976
Jou
r
n
al
h
o
m
e
pa
ge
:
ht
t
p:
/
/
i
j
e
e
c
s
.
i
a
e
s
c
or
e
.
c
om
A
p
r
o
a
c
t
i
v
e
m
e
t
a
h
e
u
r
i
st
i
c
m
o
d
e
l
f
o
r
o
p
t
i
m
i
z
i
n
g
w
e
i
g
h
t
s
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
A
l
i
H
a
k
e
m
A
l
s
ae
e
d
i
1
,
A
l
i
H
u
s
s
e
i
n
A
l
jan
ab
i
2
,
M
e
h
d
i
Eb
ad
y
M
an
n
a
3
,
A
d
i
l
L
.
A
l
b
u
k
h
n
e
fi
s
4
1,
4
C
o
l
l
e
g
e
o
f
C
o
m
put
e
r
S
c
i
e
nc
e
a
n
d
I
nf
o
r
m
a
t
i
o
n
T
e
c
hno
l
o
gy
,
U
ni
v
e
r
s
i
t
y
o
f
A
l
-
Q
a
di
s
i
y
a
h,
I
r
a
q
2
Al
-
Q
a
di
s
i
y
a
h
E
duc
a
t
i
o
n
D
i
r
e
c
t
o
r
a
t
e
,
I
r
a
q
3
C
o
l
l
e
g
e
o
f
I
nf
o
r
m
a
t
i
o
n
T
e
c
hno
l
o
gy
,
U
ni
v
e
r
s
i
t
y
o
f
B
a
b
y
l
o
n,
I
r
a
q
A
r
ti
c
l
e
I
n
fo
A
B
S
TR
A
C
T
Ar
t
i
c
l
e
h
i
s
t
or
y
:
R
e
c
e
i
v
e
d
J
a
n
14
,
2
020
R
e
v
i
s
e
d
Ma
r
17
,
20
20
A
c
c
e
pt
e
d
M
a
r
3
1
,
202
0
T
hi
s
pa
p
e
r
p
r
o
po
s
e
s
t
h
e
P
a
r
t
i
c
l
e
S
w
a
r
m
O
p
t
i
m
i
z
a
t
i
o
n
m
o
de
l
f
o
r
e
nha
nc
i
ng
t
he
pe
r
f
o
r
m
a
nc
e
o
f
a
n
A
r
t
i
f
i
c
i
a
l
N
e
ur
a
l
N
e
t
w
o
r
k
.
T
h
e
l
e
a
r
ni
ng
pr
o
c
e
s
s
o
f
A
r
t
i
f
i
c
i
a
l
N
e
ur
a
l
N
e
t
w
o
r
k
r
e
q
ui
r
e
s
a
l
o
ng
t
i
m
e
t
o
s
a
t
i
s
f
y
r
e
qui
r
e
m
e
n
t
s
be
c
a
us
e
o
f
pr
o
c
e
s
s
i
ng
c
o
m
pl
e
xi
t
y
o
f
t
he
ba
c
kpr
o
pa
g
a
t
i
o
n
a
l
g
o
r
i
t
h
m
t
ha
t
ha
s
be
e
n
u
s
e
d
i
n
t
r
a
i
ni
ng
A
r
t
i
f
i
c
i
a
l
N
e
ur
a
l
N
e
t
w
o
r
k
.
I
t
i
s
a
no
nl
i
n
e
a
r
c
om
pl
e
x
m
o
de
l
t
ha
t
c
a
n
be
us
e
d
t
o
c
o
nf
i
g
ur
e
a
nd
t
r
a
i
n
a
n
a
r
t
i
f
i
c
i
a
l
ne
u
r
o
n
s
y
s
t
e
m
.
B
o
t
h
A
r
t
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
a
n
d
P
a
r
t
i
c
l
e
S
w
a
r
m
O
pt
i
m
i
z
a
t
i
o
n
m
o
de
l
ha
v
e
be
e
n
m
a
na
g
e
d
t
o
s
o
l
v
e
a
nd
o
p
t
i
m
i
z
e
s
e
v
e
r
a
l
no
nl
i
n
e
a
r
m
o
de
l
s
.
H
e
ur
i
s
t
i
c
O
pt
i
m
i
z
a
t
i
o
n
W
e
i
g
ht
o
f
A
r
t
i
f
i
c
i
a
l
N
e
ur
a
l
N
e
t
w
o
r
k
(
H
N
N
)
i
s
a
pr
o
a
c
t
i
v
e
m
e
t
a
h
e
u
r
i
s
t
i
c
m
o
de
l
pr
o
po
s
e
d
t
o
o
pt
i
m
i
z
e
t
h
e
pe
r
f
o
r
m
a
nc
e
o
f
A
r
t
i
f
i
c
i
a
l
N
e
ur
a
l
N
e
t
w
o
r
k.
T
h
e
pr
o
po
s
e
d
s
y
s
t
e
m
a
ppl
i
e
s
P
a
r
t
i
c
l
e
S
w
a
r
m
O
pt
i
m
i
z
a
t
i
o
n
t
o
f
i
nd
t
h
e
o
pt
i
m
um
w
e
i
g
ht
s
o
f
t
he
A
r
t
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
i
ns
t
e
a
d
o
f
us
i
ng
t
h
e
B
a
c
kpr
o
pa
g
a
t
i
o
n
a
l
g
o
r
i
t
hm
.
E
xp
e
r
i
m
e
n
t
a
l
l
y
,
t
he
p
r
o
po
s
e
d
s
y
s
t
e
m
ha
s
r
e
q
ui
r
e
d
l
e
s
s
pr
o
c
e
s
s
i
ng
t
i
m
e
(
a
v
e
r
a
g
e
o
f
76.
9
1
S
e
c
.
)
t
ha
n
B
a
c
kpr
o
pa
g
a
t
i
o
n
(
a
v
e
r
a
g
e
o
f
93.
32
S
e
c
)
.
F
ur
t
he
r
m
o
r
e
,
I
t
ha
s
pr
o
v
i
de
d
be
t
t
e
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
ur
a
c
y
(
s
t
a
r
t
f
r
o
m
80%
t
o
97.
20
%
)
c
o
m
pa
r
i
ng
w
i
t
h
B
a
c
kpr
o
pa
g
a
t
i
o
n
(
s
t
a
r
t
f
r
o
m
75
.
32
%
t
o
94.
32
%
)
.
Ke
y
w
or
d
s
:
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
B
a
c
kpr
o
pa
ga
t
i
o
n
a
l
go
ri
t
hm
D
a
t
a
m
i
ni
ng
P
a
rt
i
c
l
e
s
w
a
r
m
o
pt
i
m
i
z
a
t
i
o
n
S
upe
r
v
i
s
i
n
g
l
e
a
rni
n
g
C
opy
r
i
gh
t
©
2020
I
n
s
t
i
t
ut
e
o
f
A
dv
anc
e
d
E
ng
i
ne
e
r
i
ng
and
S
c
i
e
nc
e
.
A
l
l
r
i
gh
t
s
r
e
s
e
r
v
e
d
.
Cor
r
e
s
pon
di
n
g
Au
t
h
or
:
A
l
i
H
a
ke
m
A
l
s
a
e
e
di
,
Co
l
l
e
ge
of
Co
m
put
e
r
S
c
i
e
n
c
e
a
nd
I
n
f
o
rm
a
t
i
o
n
t
e
c
hn
o
l
o
g
y
,
U
n
i
v
e
r
s
i
t
y
of
A
l
-
Q
a
di
s
i
y
a
h,
A
l
D
i
w
a
n
i
y
a
h,
Q
a
di
s
i
y
y
a
h
P
r
o
v
i
n
c
e
,
I
ra
q
.
E
m
a
i
l
:
a
l
i
.
a
l
s
a
e
e
di
@
qu
.
e
du.
i
q
1.
I
N
TR
O
D
U
C
TI
O
N
A
r
t
i
f
i
c
i
a
l
N
e
ura
l
N
e
t
w
o
r
k
(A
N
N
)
t
e
c
hn
i
c
a
l
l
y
s
i
m
ul
a
t
e
s
t
h
e
b
r
a
i
n
b
e
h
a
v
i
o
ur
t
o
de
v
e
l
o
p
a
n
a
r
t
i
f
i
c
i
a
l
s
y
s
t
e
m
t
h
a
t
c
a
n
b
e
us
e
d
t
o
m
a
na
ge
c
o
m
pl
e
x
pr
e
di
c
t
i
o
n
pr
o
b
l
e
m
s
[1].
It
i
s
o
ri
gi
na
l
l
y
t
r
a
i
n
e
d
b
a
s
e
d
o
n
B
a
c
kpr
o
pa
ga
t
i
o
n
a
l
go
r
i
t
hm
(B
P
)
c
o
n
c
e
pt
s
[2].
T
h
e
A
N
N
c
o
n
s
i
s
t
s
o
f
s
e
ve
r
a
l
n
e
ur
o
n
s
(
n
o
de
s
)
di
s
t
ri
b
ut
e
d
o
n
l
a
y
e
r
s
(i
n
pu
t
,
h
i
d
de
n,
a
n
d
o
ut
put
)
a
n
d
us
e
s
s
y
n
a
pt
i
c
w
e
i
g
h
t
s
f
o
r
l
a
b
e
l
l
i
n
g
l
i
n
ks
t
ha
t
c
o
nn
e
c
t
n
e
u
r
o
n
s
.
T
h
e
s
e
w
e
i
gh
t
s
h
e
l
p
a
r
t
i
f
i
c
i
a
l
n
e
ura
l
s
y
s
t
e
m
t
o
t
r
a
i
n
o
n
p
r
e
di
c
t
i
n
g
t
h
e
c
l
a
s
s
o
f
c
o
r
r
e
s
po
n
di
ng
i
nput
.
B
P
upd
a
t
e
s
A
N
N
w
e
i
gh
t
s
b
a
s
e
d
o
n
c
a
l
c
u
l
a
t
i
n
g
e
rr
o
r
s
t
h
a
t
r
e
s
ul
t
f
r
o
m
t
h
e
f
e
e
d
b
a
c
k
of
pr
e
v
i
o
us
l
a
y
e
r
s
[3]
.
P
a
rt
i
c
l
e
S
w
a
rm
O
p
t
i
m
i
z
a
t
i
o
n
(P
S
O
)
i
s
a
s
t
o
c
h
a
s
t
i
c
o
pt
i
m
i
z
a
t
i
o
n
a
l
go
r
i
t
h
m
i
n
s
p
i
r
e
d
by
n
e
ut
r
a
l
’
s
b
e
h
a
v
i
o
ur
o
f
s
o
c
i
a
l
a
n
i
m
a
l
s
[4].
I
t
t
e
c
hni
c
a
l
l
y
t
h
e
pr
o
pe
rt
y
of
s
y
s
t
e
m
s
c
o
m
pos
e
d
of
un
i
n
t
e
l
l
i
ge
n
t
a
ge
n
t
s
w
i
t
h
l
i
m
i
t
e
d
i
n
d
i
v
i
dua
l
c
a
p
a
b
i
l
i
t
i
e
s
b
ut
w
i
t
h
a
n
i
n
t
e
l
l
i
ge
n
t
c
o
l
l
e
c
t
i
v
e
b
e
h
a
v
i
o
ur
[5]
.
I
t
i
s
a
n
e
f
f
i
c
i
e
n
t
t
e
c
hni
que
f
o
r
s
t
o
c
h
a
s
t
i
c
s
e
a
r
c
h
i
n
a
m
ul
t
i
d
i
m
e
n
s
i
o
n
a
l
s
pa
c
e
,
h
a
s
s
o
f
a
r
b
e
e
n
a
pp
l
i
e
d
s
uc
c
e
s
s
f
ul
l
y
t
o
s
o
l
ve
t
h
e
di
f
f
e
r
e
n
t
c
o
m
pl
e
x
pr
o
b
l
e
m
s
[6
-
9].
It
i
s
a
gui
de
t
ha
t
us
e
ra
n
do
m
ne
s
s
t
o
f
i
n
d
t
h
e
b
e
s
t
p
o
s
s
i
b
l
e
s
o
l
ut
i
o
n
s
s
w
i
f
t
l
y
.
A
N
N
s
a
r
e
po
w
e
r
f
ul
m
o
de
l
s
t
ha
t
ha
v
e
a
s
i
g
n
i
f
i
c
a
n
t
a
pp
l
i
c
a
t
i
o
n
i
n
a
ra
n
ge
o
f
di
ffe
r
e
nt
f
i
e
l
ds
i
n
m
e
di
c
i
n
e
,
m
ul
t
i
m
e
di
a
p
r
o
c
e
s
s
i
n
g,
s
e
c
ur
i
t
y
,
E
c
o
n
o
m
i
c
,
a
n
d
s
o
o
n
[
10
-
14
].
F
urt
h
e
rm
o
r
e
,
de
e
p
l
e
a
rn
i
ng
m
o
de
l
s
m
a
i
nl
y
b
a
s
e
d
o
n
pr
i
n
c
i
pl
e
s
of
A
N
N
.
G
e
n
e
r
a
l
l
y
,
A
N
N
w
h
e
n
t
r
a
i
ni
n
g
by
P
B
,
s
i
gn
i
f
i
c
a
n
t
l
y
s
u
f
fe
r
i
n
g
f
r
o
m
a
de
l
a
y
i
n
l
e
a
rni
n
g
r
a
t
e
be
c
a
us
e
c
o
m
pl
e
x
a
n
d
l
o
n
g
s
t
e
ps
t
ha
t
Evaluation Warning : The document was created with Spire.PDF for Python.
In
do
n
e
s
i
a
n
J
E
l
e
c
E
ng
&
Co
m
p
S
c
i
IS
S
N
:
2502
-
4752
A
pr
oa
c
t
i
v
e
m
e
t
a
he
ur
i
s
t
i
c
m
od
e
l
f
or
op
t
i
m
i
z
i
ng
w
e
i
ght
s
o
f
ar
t
i
f
i
c
i
al
ne
ur
al
ne
t
w
or
k
(
A
l
i
H
a
k
e
m
A
l
s
ae
e
di
)
977
a
ppl
i
e
d
[1]
.
P
B
t
ra
i
n
s
A
N
N
by
t
un
i
ng
m
o
di
f
i
c
a
t
i
o
n
o
f
w
e
i
g
ht
s
a
f
t
e
r
e
a
c
h
t
ra
i
n
-
c
y
c
l
e
,
t
h
e
r
e
f
o
r
e
l
e
a
rni
n
g
r
a
t
e
w
i
l
l
b
e
i
m
pr
o
v
e
d
s
l
ow
l
y
.
A
s
a
r
e
s
ul
t
,
A
N
N
n
e
e
ds
a
m
a
rka
b
l
e
t
r
e
m
e
n
do
us
t
i
m
e
t
o
t
r
a
i
n
o
n
a
p
a
r
t
i
c
ul
a
r
pr
o
b
l
e
m
.
E
v
i
de
n
t
l
y
,
s
i
gni
f
i
c
a
nt
r
e
m
a
r
k
a
b
l
y
t
i
m
e
r
e
qui
r
e
d
t
o
t
r
a
i
n
A
N
N
by
BP
a
l
go
r
i
t
hm
a
nd
n
e
c
e
s
s
i
t
y
of
i
m
p
r
o
v
i
n
g
t
h
e
pr
e
di
c
t
i
o
n
a
c
c
u
r
a
c
y
of
A
N
N
m
o
t
i
v
e
s
a
s
t
o
pr
o
po
s
e
d
n
e
w
t
r
a
i
n
m
o
de
l
t
o
o
pt
i
m
i
z
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
of
A
N
N
i
n
t
e
r
m
s
o
f
a
c
c
ur
a
c
y
a
n
d
t
i
m
e
.
T
h
e
P
S
O
h
a
s
a
go
o
d
a
c
c
e
pt
a
n
c
e
by
t
h
e
A
rt
i
f
i
c
i
a
l
Int
e
l
l
i
ge
n
c
e
c
o
m
m
uni
t
y
b
e
c
a
us
e
i
t
i
s
a
t
r
e
m
e
n
do
us
o
pt
i
m
i
z
a
t
i
o
n
a
l
go
r
i
t
h
m
a
n
d
c
a
n
s
o
l
v
e
v
a
r
i
a
nt
c
o
m
pl
e
x
o
pt
i
m
i
z
a
t
i
o
n
p
r
o
b
l
e
m
s
.
F
o
r
a
gi
v
e
n
p
r
o
b
l
e
m
,
P
S
O
c
a
n
e
x
pl
o
r
e
b
i
g
m
u
l
t
i
m
o
da
l
a
n
d
n
o
n
c
o
n
t
i
nuo
us
s
e
a
r
c
h
s
pa
c
e
s
a
nd
c
a
n
f
i
nd
t
h
e
b
e
s
t
po
s
s
i
b
l
e
s
o
l
ut
i
o
n
,
n
e
a
r
t
h
e
o
pt
i
m
um
v
a
l
ue
[1
5]
.
T
h
e
r
e
f
o
r
e
,
t
h
e
p
r
o
po
s
e
d
s
y
s
t
e
m
(H
N
N
)
a
ppl
i
e
s
t
h
e
P
S
O
t
o
f
i
n
d
t
h
e
o
pt
i
m
a
l
w
e
i
gh
t
s
o
f
A
N
N
.
In
t
h
i
s
p
a
pe
r,
a
n
e
w
m
o
de
l
of
t
h
e
a
rt
i
f
i
c
i
a
l
n
e
u
r
a
l
s
y
s
t
e
m
i
s
pr
o
po
s
e
d
b
a
s
e
d
o
n
t
h
e
s
t
o
c
h
a
s
t
i
c
s
e
a
r
c
h
o
pt
i
m
i
z
a
t
i
o
n
b
y
P
S
O
a
n
d
p
ri
n
c
i
pl
e
of
A
N
N
.
T
h
e
c
o
n
t
r
i
b
ut
i
o
n
s
o
f
t
hi
s
r
e
s
e
a
r
c
h
m
a
i
n
l
y
f
a
c
e
o
n
i
m
p
r
o
v
i
n
g
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
t
h
e
A
N
N
s
y
s
t
e
m
i
n
t
hr
e
e
a
s
pe
c
t
s
:
T
r
a
i
n
i
n
g
t
i
m
e
r
e
qui
r
e
d,
a
n
d
t
h
e
c
o
m
pl
e
xi
t
y
of
t
r
a
i
n
i
ng
pr
o
c
e
dur
e
,
a
n
d
a
c
c
u
r
a
c
y
.
T
h
e
p
r
o
po
s
e
d
H
N
N
m
o
de
l
c
o
n
s
um
e
s
r
e
m
a
r
k
a
b
l
y
l
e
s
s
t
i
m
e
t
o
f
i
n
d
o
pt
i
m
a
l
w
e
i
gh
t
s
of
a
n
A
N
N
.
T
e
c
hn
i
c
a
l
l
y
,
t
h
i
s
f
a
c
t
i
s
e
xpl
a
i
n
e
d
by
t
h
e
P
S
O
s
e
a
r
c
h
s
t
r
a
t
e
g
y
us
e
d
by
t
h
e
pr
o
po
s
e
d
m
o
de
l
r
a
t
h
e
r
t
u
n
i
ng
m
o
di
f
i
c
a
t
i
o
n
us
e
d
i
n
B
P
.
T
h
e
s
i
m
pl
i
c
i
t
y
of
P
S
O
[8]
a
n
d
us
i
n
g
t
h
e
f
e
w
n
um
b
e
r
s
o
f
pa
ra
m
e
t
e
r
s
i
n
t
h
e
pr
o
po
s
e
d
s
y
s
t
e
m
r
e
duc
e
t
h
e
c
o
m
pl
e
xi
t
y
of
t
h
e
p
r
o
po
s
e
d
s
ys
t
e
m
.
T
h
e
r
e
f
o
r
e
,
t
h
e
p
r
o
po
s
e
d
s
y
s
t
e
m
do
e
s
n
o
t
r
e
qui
r
e
a
n
a
d
di
t
i
o
na
l
p
r
o
c
e
s
s
t
o
a
c
h
i
e
v
e
t
h
e
e
s
t
a
b
l
i
s
h
e
d
s
y
s
t
e
m
o
n
t
h
e
f
i
na
l
s
e
t
of
w
e
i
gh
t
s
.
F
urt
h
e
r
m
o
r
e
,
T
h
e
pr
o
po
s
e
d
t
e
c
hn
i
que
a
i
m
s
t
o
c
r
e
a
t
e
a
n
e
ff
i
c
i
e
n
t
s
upe
r
v
i
s
e
m
o
d
e
l
w
i
t
h
a
v
e
r
y
h
i
g
h
de
gr
e
e
of
pr
e
di
c
t
i
o
n
a
c
c
ur
a
c
y
.
E
xpe
ri
m
e
n
t
a
l
r
e
s
ul
t
s
s
h
o
w
s
i
gn
i
f
i
c
a
n
t
p
r
e
di
c
t
i
o
n
s
f
o
r
i
n
p
ut
d
a
t
a
by
t
h
e
p
r
o
po
s
e
d
m
e
t
h
o
d
i
n
c
o
m
pa
ri
s
o
n
w
i
t
h
P
B
i
n
A
N
N
.
T
h
e
a
c
c
ur
a
t
e
pr
e
di
c
t
i
o
n
s
o
f
t
h
e
p
r
o
po
s
e
d
t
e
c
h
ni
que
a
r
e
c
a
pa
b
l
e
of
a
c
h
i
e
v
i
ng
b
e
t
t
e
r
pr
e
di
c
t
i
o
n
ra
t
i
o
s
o
f
A
N
N
t
h
a
n
A
N
N
w
h
e
n
t
ra
i
ni
n
g
by
B
P
.
H
e
r
e
i
n
,
w
e
pr
o
pos
e
d
P
S
O
a
s
a
t
r
a
i
ni
n
g
m
o
de
l
of
A
N
N
t
o
s
e
a
r
c
h
o
n
o
pt
i
m
a
l
w
e
i
ght
s
t
ha
t
c
o
rr
e
s
po
ndi
n
g
t
h
e
pa
rt
i
c
u
l
a
r
p
r
o
b
l
e
m
.
F
i
gu
r
e
1
i
l
l
us
t
ra
t
e
s
t
h
e
s
c
e
n
a
ri
o
us
e
d
t
o
upd
a
t
e
t
h
e
w
e
i
ght
s
o
f
t
h
e
p
r
o
po
s
e
d
s
y
s
t
e
m
.
I
n
p
u
t
O
p
t
i
m
u
m
We
i
g
h
t
s
F
o
r
w
a
r
d
P
r
p
o
p
a
g
a
t
i
o
n
We
i
g
h
t
s
E
v
a
l
u
a
t
i
o
n
P
S
O
(
u
p
d
a
t
e
w
e
i
g
h
s
)
H
N
N
S
y
s
t
e
m
F
i
gu
r
e
1
.
S
c
e
na
r
i
o
o
f
w
e
i
gh
t
up
da
t
i
n
g
T
o
de
v
e
l
o
p
t
he
A
N
N
a
l
g
o
ri
t
h
m
,
s
e
v
e
ra
l
s
t
u
d
i
e
s
re
l
a
t
e
d
t
o
o
u
r
re
s
e
a
rc
h,
h
a
v
e
b
e
e
n
p
ro
po
s
e
d
f
o
r
s
u
p
e
rv
i
s
e
d
m
a
c
hi
ne
l
e
a
r
ni
ng
t
o
c
l
a
s
s
i
f
y
s
e
v
e
ra
l
o
b
j
e
c
t
s
o
f
d
a
t
a
.
M
o
s
t
o
f
t
he
s
t
u
d
i
e
s
i
n
t
he
a
p
p
ro
a
c
h
o
f
t
he
w
e
i
g
ht
s
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
t
he
ne
u
ra
l
ne
t
w
o
rk
ha
v
e
b
e
e
n
b
a
s
e
d
o
n
s
t
a
nd
a
rd
a
l
g
o
ri
t
h
m
s
(
B
a
c
k
p
ro
p
a
g
a
t
i
o
n)
.
F
a
ng
c
he
ng
e
t
a
l
[16]
,
t
he
a
u
t
ho
rs
p
ro
p
o
s
e
d
t
he
ne
w
m
o
d
e
l
l
i
ng
o
f
a
rt
i
f
i
c
i
a
l
ne
t
c
o
m
b
i
ne
s
b
o
t
h
P
S
O
a
nd
b
a
c
k
p
ro
p
a
g
a
t
i
o
n.
T
he
P
S
O
u
s
e
d
t
o
o
p
t
i
m
i
z
e
t
he
i
n
i
t
i
a
l
w
e
i
g
ht
s
o
f
A
N
N
a
nd
t
he
re
s
t
o
f
t
he
l
e
a
rni
ng
p
ro
c
e
s
s
i
ng
a
re
a
c
h
i
e
v
e
d
b
y
t
he
b
a
c
k
p
ro
p
a
g
a
t
i
o
n
a
l
g
o
ri
t
h
m
.
T
he
p
ro
p
o
s
e
d
s
y
s
t
e
m
go
t
o
n
M
S
E
r
a
t
i
o
re
a
c
he
s
0
.
5
.
G
a
x
i
o
l
a
e
t
a
l
[17]
.
a
u
t
ho
rs
i
n
t
ro
d
u
c
e
b
o
t
h
a
l
g
o
ri
t
hm
a
nd
p
a
r
t
i
c
l
e
s
w
a
rm
o
p
t
i
m
i
z
a
t
i
o
n
t
o
t
y
p
e
-
2
f
u
z
z
y
w
e
i
g
ht
a
d
j
u
s
t
m
e
nt
.
T
he
c
l
a
s
s
i
f
i
c
a
t
i
o
n
i
n
a
p
ro
p
o
s
e
d
s
y
s
t
e
m
t
e
c
hni
c
a
l
l
y
de
p
e
nd
s
o
n
t
he
t
y
p
e
-
2
f
u
z
z
y
a
n
d
b
a
c
k
p
ro
p
a
g
a
t
i
o
n
t
o
e
na
b
l
e
t
he
ne
u
ra
l
ne
t
w
o
rk
t
o
l
e
a
r
n.
V
a
ru
n
e
t
a
l
[18]
.
t
hi
s
s
t
u
d
y
a
i
m
s
t
o
o
p
t
i
m
i
z
e
w
e
i
g
ht
a
nd
p
a
r
a
m
e
t
e
rs
o
f
t
he
o
b
j
e
c
t
i
v
e
f
u
nc
t
i
o
n.
V
a
ri
o
u
s
t
y
pe
s
o
f
t
ra
ns
f
e
r
f
u
nc
t
i
o
ns
w
e
re
c
ho
s
e
n
f
o
r
t
he
p
u
rp
o
s
e
o
f
t
he
R
i
go
ro
u
s
a
na
l
y
s
i
s
o
f
t
he
i
nf
l
u
e
nc
e
o
f
t
he
t
ra
ns
f
e
r
f
u
nc
t
i
o
ns
o
p
t
i
m
i
z
a
t
i
o
n
t
o
g
e
t
he
r
w
i
t
h
t
he
N
N
w
e
i
g
ht
s
.
A
p
a
rt
f
ro
m
t
h
e
m
e
t
a
he
u
ri
s
t
i
c
a
l
g
o
ri
t
hm
s
,
t
he
b
a
c
k
p
ro
p
a
g
a
t
i
o
n
a
l
g
o
ri
t
h
m
w
a
s
u
s
e
d
f
o
r
t
he
c
o
m
p
re
he
ns
i
v
e
c
o
m
p
a
ri
s
o
n
a
nd
v
a
l
i
d
a
t
i
o
n
o
f
t
he
s
i
g
ni
f
i
c
a
nc
e
o
f
t
he
N
N
-
T
F
s
m
o
de
l
.
Y
u
e
t
a
l
[7]
.
ha
v
e
a
p
p
l
i
e
d
t
he
o
p
t
i
m
i
z
a
t
i
o
n
t
e
c
h
ni
q
u
e
t
o
s
e
t
o
p
t
i
m
a
l
ne
u
ro
ns
i
n
t
he
h
i
d
d
e
n
l
a
y
e
r
o
f
A
rt
i
f
i
c
i
a
l
N
e
u
ra
l
N
e
t
w
o
rk
.
P
a
rt
i
c
l
e
S
w
a
rm
O
p
t
i
m
i
z
a
t
i
o
n
u
s
e
d
w
i
t
h
p
ro
p
o
s
e
d
s
y
s
t
e
m
t
o
d
e
t
e
rm
i
ne
o
p
t
i
m
a
l
nu
m
b
e
rs
o
f
ne
u
ro
ns
i
n
t
he
hi
d
d
e
n
l
a
y
e
r.
T
he
p
ro
p
o
s
e
d
s
y
s
t
e
m
a
c
hi
e
v
e
t
he
b
e
s
t
re
s
u
l
t
w
he
n
t
he
f
i
v
e
ne
u
ro
ns
i
n
t
he
hi
d
d
e
n
l
a
y
e
r.
2.
R
ES
EA
R
C
H
M
ET
H
O
D
In
t
hi
s
s
e
c
t
i
o
n
e
xpl
a
i
n
t
h
e
m
a
i
n
m
e
c
h
a
ni
s
m
o
f
B
P
t
o
t
ra
i
n
A
N
N
,
P
S
O
,
a
n
d
t
h
e
l
a
s
t
p
a
r
t
i
l
l
us
t
ra
t
e
s
t
h
e
pr
o
po
s
e
d
H
N
N
s
y
s
t
e
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2502
-
4752
In
do
n
e
s
i
a
n
J
E
l
e
c
E
ng
&
Co
m
p
S
c
i
,
V
o
l
.
20
,
N
o
.
2
,
N
o
v
e
m
be
r
20
20
:
97
6
-
984
978
2.
1
.
A
r
t
i
fi
c
i
a
l
n
e
u
r
al
n
e
tw
o
r
k
(A
N
N
)
A
N
N
s
y
s
t
e
m
b
a
s
i
c
a
l
l
y
c
o
n
s
i
s
t
s
o
f
n
e
u
r
o
n
s
a
n
d
w
e
i
gh
t
s
.
T
h
e
n
e
ur
o
n
s
r
e
p
r
e
s
e
n
t
e
d
a
s
l
e
a
rn
i
ng
u
ni
t
i
s
di
s
t
r
i
b
ut
e
d
o
n
A
N
N
'
l
a
y
e
r
s
(i
n
p
ut
,
h
i
dde
n,
a
n
d
o
ut
pu
t
)
[1]
.
W
e
i
gh
t
s
de
f
i
n
e
t
h
e
v
a
l
ue
o
f
t
h
e
i
nt
e
r
c
o
nn
e
c
t
i
o
n
l
i
n
e
t
h
a
t
c
o
nn
e
c
t
n
e
u
r
o
n
s
t
o
ge
t
h
e
r.
G
e
n
e
ra
l
l
y
,
t
h
e
a
r
c
hi
t
e
c
t
u
re
of
t
h
e
A
N
N
s
e
t
by
d
e
pt
h,
w
i
dt
h
,
a
n
d
a
c
t
i
v
a
t
i
o
n
f
un
c
t
i
o
n
s
us
e
d
o
n
e
a
c
h
l
a
y
e
r
[19].
D
e
pt
h
de
t
e
rm
i
n
e
s
t
h
e
de
e
p
l
e
a
rni
n
g
l
e
v
e
l
i
n
h
o
w
m
a
n
y
l
a
y
e
r
s
i
n
s
i
de
h
i
dde
n
l
a
y
e
r
s
.
T
h
e
w
i
dt
h
de
f
i
n
e
s
t
h
e
n
u
m
b
e
r
o
f
n
e
u
r
o
n
s
i
n
e
a
c
h
hi
dde
n
l
a
y
e
r
(s
).
T
h
e
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
i
s
a
ppl
i
e
d
t
o
de
f
i
n
e
t
h
e
n
o
n
-
l
i
n
e
a
r
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
e
i
nput
s
a
n
d
t
h
e
i
n
pu
t
i
n
f
o
r
m
a
t
i
o
n
i
n
t
o
a
m
o
r
e
us
e
f
ul
o
ut
put
[2
0].
F
i
gu
r
e
2
s
h
o
w
s
t
h
e
a
r
c
h
i
t
e
c
t
ur
e
o
f
A
N
N
.
X
2
X
1
X
n
O
u
t
p
u
t
1
O
u
t
p
u
t
2
b
h
1
b
h
2
b
o
1
In
p
u
t
L
a
y
er
Hi
d
d
e
n
L
a
y
e
r
s
O
u
t
p
u
t
L
a
y
er
F
i
gu
r
e
2
.
T
h
e
a
r
c
hi
t
e
c
t
u
r
e
o
f
A
N
N
T
e
c
hn
i
c
a
l
l
y
,
t
h
e
pr
o
c
e
s
s
i
n
g
p
r
o
b
l
e
m
of
A
N
N
i
s
b
a
s
e
d
o
n
t
w
o
o
p
e
r
a
t
i
o
n
s
p
r
e
di
c
t
i
o
n
a
nd
t
ra
i
ni
n
g
[21,
22]
.
F
i
r
s
t
,
a
p
r
e
d
i
c
t
i
o
n
i
s
a
c
hi
e
v
e
d
by
F
o
r
w
a
r
d
P
ro
pa
ga
t
i
o
n
a
l
go
ri
t
hm
,
i
t
f
o
r
w
a
r
d
s
um
m
a
t
i
o
n
o
f
m
ul
t
i
p
l
i
c
a
t
i
o
n
i
n
pu
t
s
o
f
n
e
ur
o
n
s
w
i
t
h
c
o
nn
e
c
t
i
ng
w
e
i
gh
t
s
t
o
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
f
o
r
p
r
e
di
c
t
i
n
g
t
h
e
c
l
a
s
s
of
i
n
put
.
I
n
(1
)
a
n
d
(
2)
c
a
l
c
ul
a
t
e
s
t
h
e
o
ut
p
ut
o
f
F
o
r
w
a
r
d
P
r
o
pa
g
a
t
i
o
n
.
T
h
e
n
e
t
s
u
m
m
a
t
i
o
n
a
n
d
i
t
s
o
ut
put
f
o
r
t
h
e
a
c
t
i
v
a
t
i
o
n
f
un
c
t
i
o
n
[23]
.
∑
,
j
=
1,
2
,
3,
…
………
n
(1)
(2)
w
h
e
r
e
i
s
t
h
e
r
e
s
ul
t
o
f
n
e
t
i
nput
s
xi
m
ul
t
i
p
l
i
e
d
by
i
nt
e
r
c
o
nn
e
c
t
i
o
n
w
e
i
g
h
t
,
i
s
t
h
e
a
c
t
i
v
a
t
i
o
n
f
un
c
t
i
o
n,
a
n
d
t
h
e
a
c
t
u
a
l
o
ut
put
o
f
t
h
e
n
e
t
.
S
e
c
o
n
d,
T
h
e
A
N
N
t
r
a
i
n
s
i
t
s
w
e
i
ght
o
r
i
g
i
n
a
l
l
y
by
a
B
a
c
k
P
r
o
pa
ga
t
i
o
n
(B
P
)
a
l
go
ri
t
hm
[1]
.
T
h
e
B
a
c
k
P
r
o
pa
ga
t
i
o
n
(B
P
)
upd
a
t
e
s
w
e
i
gh
t
s
o
f
A
N
N
a
f
t
e
r
e
a
c
h
t
ra
i
n
-
c
y
c
l
e
(e
poc
h
)
a
c
c
o
r
di
n
g
t
o
p
r
o
duc
t
e
rr
o
r
.
G
e
n
e
ra
l
l
y
,
t
h
e
e
rr
o
r
i
s
c
a
l
c
ul
a
t
e
d
i
n
(3)
:
∑
(3)
W
h
e
r
e
:
n
n
u
m
b
e
r
o
f
o
ut
put
s
A
l
go
r
i
t
h
m
I
i
l
l
us
t
ra
t
e
s
t
r
a
i
n
i
ng
A
N
N
by
c
o
n
c
e
pt
s
o
f
BP
:
A
l
go
r
i
th
m
(I
):
Bac
k
p
r
o
p
agati
o
n
a
l
go
r
i
th
m
(P
B
)
.
I
n
p
u
t:
D
a
t
a
s
e
t
Evaluation Warning : The document was created with Spire.PDF for Python.
In
do
n
e
s
i
a
n
J
E
l
e
c
E
ng
&
Co
m
p
S
c
i
IS
S
N
:
2502
-
4752
A
pr
oa
c
t
i
v
e
m
e
t
a
he
ur
i
s
t
i
c
m
od
e
l
f
or
op
t
i
m
i
z
i
ng
w
e
i
ght
s
o
f
ar
t
i
f
i
c
i
al
ne
ur
al
ne
t
w
or
k
(
A
l
i
H
a
k
e
m
A
l
s
ae
e
di
)
979
O
u
tp
u
t:
o
pt
i
m
u
m
W
e
i
g
ht
1.
S
e
t
n
e
t
w
o
r
k
l
a
y
e
r
s
a
n
d
n
e
u
r
o
n
(
n
o
de
s
,
h
i
d
de
n
n
o
de
s
,
a
nd
o
ut
put
n
o
de
s
)
2.
Ini
t
i
a
l
i
z
e
a
l
l
n
e
t
w
o
r
k
w
e
i
gh
t
s
w
i
t
h
ra
n
do
m
v
a
l
ue
s
.
3.
R
e
p
e
at
u
n
t
i
l
t
h
e
t
e
r
m
i
n
a
t
i
o
n
c
o
n
d
i
t
i
o
n
i
s
m
e
t
:
4.
F
o
r
e
a
c
h
t
r
a
i
n
i
ng
e
xa
m
pl
e
(x,
t
)
ϵ
D
do
5.
In
p
ut
x
t
o
t
h
e
n
e
t
w
o
r
k
a
n
d
c
o
m
put
e
t
h
e
o
ut
put
a
k
o
f
uni
t
s
i
n
t
h
e
o
ut
put
l
a
y
e
r
.
6.
F
o
r
e
a
c
h
n
e
t
w
o
r
k
o
ut
pu
t
u
ni
t
k
,
c
a
l
c
ul
a
t
e
i
t
s
e
rr
o
r
t
e
rm
δ
k:
δ
k
←
a
k
(
1
-
a
k)
(t
k
-
a
k)
(
4
)
7.
F
o
r
e
a
c
h
hi
dde
n
u
ni
t
h,
c
a
l
c
ul
a
t
e
i
t
s
e
rr
o
r
t
e
rm
δ
h
δ
h
←
a
h
(1
-
a
h)
∑
(
5
)
8.
U
p
d
ate
e
a
c
h
n
e
t
w
o
r
k
w
e
i
g
h
t
w
j
i
←
+
9.
R
e
tu
r
n
o
pt
i
m
u
m
W
e
i
g
ht
2.
2
.
P
ar
ti
c
l
e
s
w
a
r
m
o
p
ti
m
i
z
ati
o
n
(P
S
O
)
P
S
O
i
s
a
pub
l
i
c
m
e
t
a
h
e
u
ri
s
t
i
c
o
pt
i
m
i
z
a
t
i
o
n
a
l
go
ri
t
hm
i
n
s
pi
re
d
by
t
h
e
s
oc
i
a
l
b
e
h
a
v
i
o
ur
o
f
a
n
i
m
a
l
s
,
w
h
i
c
h
l
i
v
e
i
n
g
r
o
ups
.
I
t
’s
i
nt
r
o
duc
e
d
by
(
R
.
E
b
e
rh
a
rt
a
nd
J
.
K
e
nn
e
dy
)
[4]
.
T
h
e
m
a
i
n
c
ha
r
a
c
t
e
r
i
s
t
i
c
s
o
f
P
S
O
a
r
e
t
h
e
s
i
m
p
l
i
c
i
t
y
of
i
m
pl
e
m
e
n
t
a
t
i
o
n
,
f
e
w
n
um
b
e
r
s
o
f
pa
r
a
m
e
t
e
r
s
,
a
n
d
s
uc
c
e
s
s
e
s
i
n
o
pt
i
m
i
z
i
n
g
di
f
f
e
r
e
n
t
f
i
e
l
ds
s
uc
h
a
s
da
t
a
m
i
ni
n
g
,
m
e
di
c
a
l
a
pp
l
i
c
a
t
i
o
n,
s
pe
e
c
h
r
e
c
o
gn
i
t
i
o
n,
a
n
d
i
m
a
ge
pr
o
c
e
s
s
i
n
g,
t
h
e
r
e
f
o
r
e
t
h
e
P
S
O
i
s
a
n
i
n
t
e
r
e
s
t
i
n
g
t
o
pi
c
f
o
r
r
e
s
e
a
r
c
h
e
r
s
[8]
.
T
h
e
s
t
a
nda
rd
s
e
a
r
c
h
m
e
c
ha
n
i
s
m
o
f
t
h
e
P
S
O
s
t
a
rt
s
w
i
t
h
s
e
l
e
c
t
i
n
g
t
h
e
f
i
r
s
t
l
o
c
a
l
o
pt
i
m
u
m
(
)
by
e
a
c
h
pa
rt
i
c
l
e
t
h
e
n
i
t
s
e
l
e
c
t
s
t
h
e
b
e
s
t
a
s
gl
o
b
a
l
o
pt
i
m
u
m
(
).
T
h
e
v
e
l
o
c
i
t
i
e
s
of
pa
rt
i
c
l
e
s
a
r
e
up
da
t
e
d
dy
n
a
m
i
c
a
l
l
y
duri
n
g
t
h
e
s
e
a
r
c
h
p
r
o
c
e
s
s
a
n
d
a
dde
d
t
o
t
h
e
c
urr
e
n
t
pa
rt
i
c
l
e
’s
v
a
l
ue
f
o
r
upda
t
i
n
g
.
T
h
e
i
ni
t
i
a
l
v
e
l
o
c
i
t
y
of
pa
rt
i
c
l
e
s
s
e
t
by
z
e
r
o
s
.
T
h
e
v
a
l
ue
o
f
,
a
n
d
a
r
e
upd
a
t
e
d
i
t
e
r
a
t
i
v
l
l
y
(
6
)
c
a
l
c
ul
a
t
e
s
t
h
e
p
a
r
t
i
c
l
e
v
e
l
o
c
i
t
y
[5]
.
(
)
(
)
(
6
)
W
h
e
r
e
:
a
nd
a
r
e
ra
n
do
m
v
a
ri
a
b
l
e
s
i
n
t
h
e
r
a
n
ge
[
0,
1],
,
a
n
d
a
r
e
po
s
i
t
i
v
e
c
o
n
s
t
a
n
t
s
(a
c
c
e
l
e
r
a
t
i
o
n
c
o
e
ff
i
c
i
e
n
t
s
),
a
n
d
i
s
t
h
e
i
n
e
r
t
i
a
w
e
i
ght
.
T
h
e
,
i
s
i
n
d
i
c
a
t
i
n
g
t
h
e
v
e
l
o
c
i
t
y
a
n
d
po
s
i
t
i
o
n
of
pa
r
t
i
c
l
e
a
t
i
t
e
ra
t
i
o
n
t
i
n
di
m
e
n
s
i
o
n,
r
e
s
pe
c
t
i
v
e
l
y
.
T
h
e
P
S
O
us
e
s
t
h
e
(
7
)
t
o
upd
a
t
e
t
h
e
v
a
l
ue
o
f
t
h
e
pa
r
t
i
c
l
e
s
(c
a
n
di
da
t
e
s
o
l
ut
i
o
n
)
[5]
.
(
7
)
w
h
e
r
e
:
i
s
o
l
d
p
a
r
t
i
c
l
e
v
a
l
ue
,
i
s
a
n
e
w
pa
r
t
i
c
l
e
v
a
l
ue
.
2.
3
.
P
r
o
p
o
s
e
d
h
e
u
r
i
s
ti
c
o
p
ti
m
i
z
at
i
o
n
w
e
i
gh
t
o
f
ar
ti
fi
c
i
al
n
e
u
r
al
n
e
tw
o
r
k
(H
N
N
)
T
h
e
l
i
m
i
t
a
t
i
o
n
o
f
A
N
N
n
e
e
ds
a
l
o
t
of
t
i
m
e
fo
r
t
r
a
i
n
i
ng
n
e
t
w
o
r
k
o
n
ob
j
e
c
t
i
ve
f
un
c
t
i
o
n
[24]
.
T
h
e
w
e
i
gh
t
s
t
h
a
t
c
o
nn
e
c
t
t
h
e
n
e
ur
o
n
s
c
o
n
t
ri
b
ut
e
p
r
i
m
a
ri
l
y
t
o
t
h
e
o
bj
e
c
t
fo
r
w
h
i
c
h
t
h
e
A
N
N
i
s
us
e
d.
T
h
e
p
r
o
po
s
e
d
m
e
t
h
o
d
f
oc
us
e
s
o
n
f
i
n
d
i
n
g
o
pt
i
m
um
w
e
i
g
h
t
s
d
uri
n
g
t
h
e
m
i
n
i
m
u
m
po
s
s
i
b
l
e
t
i
m
e
.
T
h
e
s
t
o
c
h
a
s
t
i
c
o
pt
i
m
i
z
a
t
i
o
n
t
e
c
hni
que
s
upe
r
s
e
de
s
t
h
e
b
a
c
kpr
o
pa
g
a
t
i
o
n
i
n
o
r
i
gi
na
l
A
N
N
.
A
c
c
o
r
di
n
g
t
o
[24,
25]
,
t
h
e
P
S
O
s
uc
c
e
e
ds
i
n
o
pt
i
m
i
z
i
n
g
s
e
v
e
r
a
l
pr
o
b
l
e
m
s
,
t
h
e
r
e
f
o
r
e
,
i
t
i
s
us
e
d
a
s
a
n
o
pt
i
m
i
z
e
r
t
o
e
nh
a
n
c
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
A
N
N
.
It
i
s
c
l
e
a
r
l
y
s
h
o
w
n
f
r
o
m
t
h
e
F
i
gu
r
e
3
t
h
a
t
t
h
e
p
r
o
po
s
e
d
s
y
s
t
e
m
r
e
c
e
i
ve
s
t
h
e
da
t
a
a
f
t
e
r
i
ni
t
i
a
l
i
z
i
n
g
t
h
e
pa
r
a
m
e
t
e
r
s
t
h
e
n
i
t
o
pt
i
m
i
z
e
s
t
h
e
A
N
N
’s
w
e
i
gh
t
s
.
T
e
s
t
i
n
g
da
t
a
e
v
a
l
ua
t
e
t
h
e
o
pt
i
m
u
m
w
e
i
gh
t
o
b
t
a
i
n
e
d
f
r
o
m
t
h
e
t
r
a
i
ni
n
g
p
r
o
g
r
e
s
s
.
2.
3
.
1.
I
n
i
ti
al
i
z
at
i
o
n
F
i
r
s
t
l
y
,
t
h
e
a
l
go
r
i
t
hm
ha
s
t
o
s
e
t
t
h
e
po
pul
a
t
i
o
n
s
i
z
e
w
h
i
c
h
c
o
r
r
e
s
po
n
di
ng
t
h
e
c
a
n
d
i
d
a
t
e
w
e
i
gh
t
s
t
o
a
da
p
t
P
S
O
w
i
t
h
A
N
N
.
T
o
i
n
c
r
e
a
s
e
t
h
e
e
xpl
o
r
a
t
i
o
n
o
f
P
S
O
,
t
h
e
w
e
i
gh
t
i
n
e
rt
i
a
(ω
)
i
s
c
a
l
c
ul
a
t
e
d
a
c
c
o
r
di
n
g
to
[8]
.
It
i
s
c
a
l
c
ul
a
t
e
d
i
t
e
r
a
t
i
v
e
l
y
by
us
i
n
g
(8).
(8)
w
h
e
r
e
[
]
.
2.
3
.
2.
F
i
tn
e
s
s
o
r
c
o
s
t
fu
n
c
ti
o
n
T
h
e
v
a
l
ue
o
f
t
h
e
M
e
a
n
S
qua
r
e
E
rr
o
r
(M
S
E
)
i
s
us
e
d
a
s
a
n
i
n
d
i
c
a
t
o
r
t
o
e
v
a
l
ua
t
e
t
h
e
pe
r
f
o
r
m
a
n
c
e
of
t
h
e
p
r
o
po
s
e
d
s
y
s
t
e
m
.
A
s
s
h
o
w
n
i
n
9
c
a
l
c
u
l
a
t
e
s
t
h
e
M
S
E
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2502
-
4752
In
do
n
e
s
i
a
n
J
E
l
e
c
E
ng
&
Co
m
p
S
c
i
,
V
o
l
.
20
,
N
o
.
2
,
N
o
v
e
m
be
r
20
20
:
97
6
-
984
980
∑
(9)
w
h
e
r
e
:
i
s
di
f
f
e
r
e
n
t
b
e
t
w
e
e
n
a
c
t
ua
l
o
ut
put
a
nd
de
s
i
r
e
d
o
ut
put
of
.
2.
3
.
3.
W
e
i
gh
ts
u
p
d
ate
A
f
t
e
r
c
a
l
c
ul
a
t
i
n
g
t
h
e
f
i
t
n
e
s
s
of
c
a
n
di
d
a
t
e
w
e
i
gh
t
,
p
r
o
po
s
e
d
a
l
go
r
i
t
hm
u
pda
t
e
s
t
h
e
v
e
l
oc
i
t
y
t
o
be
a
dde
d
t
o
w
e
i
ght
s
a
nd
p
r
o
duc
e
a
n
e
w
c
a
n
di
da
t
e
w
e
i
ght
.
T
h
e
w
e
i
gh
t
s
m
a
t
r
i
x
(
)
i
s
up
da
t
e
d
a
s
s
h
o
w
n
i
n
A
l
go
r
i
t
h
m
II
f
r
e
que
nt
l
y
un
t
i
l
t
h
e
H
N
N
a
c
hi
e
v
e
s
t
h
e
t
e
r
m
i
na
t
i
o
n
c
r
i
t
e
ri
a
.
T
h
e
po
pul
a
t
i
o
n
s
i
z
e
o
f
P
S
O
i
s
a
da
p
t
i
v
e
t
o
c
o
r
r
e
s
po
n
d
t
o
t
h
e
w
e
i
gh
t
’s
m
a
t
ri
x
o
f
A
N
N
.
T
he
pr
o
po
s
e
d
s
y
s
t
e
m
c
o
m
b
i
n
e
s
w
e
i
gh
t
s
o
f
w
h
o
l
e
A
N
N
i
n
o
n
e
m
a
t
ri
x
a
s
s
h
o
w
n
i
n
F
o
r
m
ul
a
7
:
⋃
⋃
(10)
F
o
r
e
xa
m
pl
e
,
a
s
s
u
m
e
t
h
e
i
s
di
m
e
n
s
i
o
na
l
o
f
w
e
i
gh
t
m
a
t
ri
x
(w
)
o
f
A
N
N
[
]
T
h
e
do
m
i
na
t
i
o
n
o
f
po
pul
a
t
i
o
n
(
)
a
n
d
v
e
l
o
c
i
t
y
(
)
t
ha
t
ge
n
e
ra
t
e
d
i
s
s
t
h
e
v
a
l
ue
o
f
s
i
s
c
a
l
c
ul
a
t
e
s
b
y
s
qua
r
e
o
f
t
h
e
w
e
i
ght
m
a
t
r
i
x
.
[
]
,
[
]
T
o
c
o
n
t
r
o
l
o
n
l
e
a
rni
n
g
o
ri
e
nt
a
t
i
o
n
,
t
h
e
p
r
o
po
s
e
d
s
y
s
t
e
m
m
o
di
f
i
e
s
b
i
a
s
e
s
(
)
v
a
l
ue
b
a
s
e
d
o
n
t
h
e
e
rr
o
r
of
t
h
e
s
y
s
t
e
m
.
I
n
(
11
)
m
o
di
f
i
e
s
b
i
a
s
e
s
.
(11)
A
f
t
e
r
H
N
N
m
o
di
f
i
e
s
w
e
i
gh
t
s
,
t
h
e
pr
o
po
s
e
d
s
y
s
t
e
m
r
e
c
o
n
s
t
r
u
c
t
s
t
h
e
w
e
i
gh
t
s
m
a
t
ri
x
t
o
b
e
s
ui
t
a
b
l
e
fo
r
fo
r
w
a
r
d
i
n
g
p
r
o
pa
ga
t
i
o
n
.
A
s
s
h
o
w
n
i
n
(12
)
r
e
di
s
t
r
i
b
ut
e
d
w
e
i
ght
ge
n
e
r
a
t
e
d
by
P
O
S
.
⋃
⋃
(12)
2.
3
.
4.
T
e
r
m
i
n
ati
o
n
c
r
i
te
r
i
a
T
h
e
pr
o
po
s
e
d
m
o
de
l
s
t
o
ps
w
h
e
n
o
n
e
of
t
h
e
s
t
o
ppi
n
g
c
r
i
t
e
ri
a
us
e
d
i
n
t
h
e
s
t
o
c
h
a
s
t
i
c
a
l
go
ri
t
hm
i
s
s
a
t
i
s
f
i
e
d.
T
h
e
s
e
c
ri
t
e
r
i
a
a
r
e
:
e
xc
e
e
d
o
f
o
pt
i
m
i
z
a
t
i
o
n
t
i
m
e
,
no
c
h
a
n
ge
o
f
o
pt
i
m
i
z
a
t
i
o
n
i
n
n
i
t
e
ra
t
i
o
n,
o
r
us
e
r
'
s
pr
e
-
de
f
i
n
e
d
c
o
n
di
t
i
o
n
[26
,
27]
.
F
i
gu
r
e
3
s
h
o
w
s
t
h
e
m
a
i
n
s
t
e
p
s
o
f
t
h
e
p
r
o
po
s
e
d
s
y
s
t
e
m
.
T
h
e
A
l
go
r
i
t
h
m
(II)
i
l
l
us
t
r
a
t
e
s
t
h
e
ps
e
udo
c
o
de
of
t
h
e
H
N
N
.
A
l
go
r
i
th
m
(I
I
):
H
e
u
r
i
s
ti
c
o
p
ti
m
i
z
at
i
o
n
w
e
i
gh
t
o
f
a
r
ti
f
i
c
i
al
n
e
u
r
al
n
e
tw
o
r
k
(
H
N
N
)
I
n
p
u
t:
D
a
t
a
s
e
t
O
u
tp
u
t:
O
pt
i
m
um
W
e
i
g
h
t
1.
S
e
t
n
e
t
w
o
r
k
l
a
y
e
r
s
a
n
d
n
e
u
r
o
n
(
n
o
de
s
,
h
i
d
de
n
n
o
de
s
,
a
nd
o
ut
put
n
o
de
s
)
2.
Ini
t
i
a
l
i
z
e
PSO
3.
R
e
p
e
at
u
n
t
i
l
t
h
e
t
e
r
m
i
n
a
t
i
o
n
c
o
n
d
i
t
i
o
n
i
s
m
e
t
:
4.
F
o
r
e
a
c
h
(c
a
n
di
da
t
e
w
e
i
gh
t
s
)
ϵ
po
pul
a
t
i
o
n
do
5.
Co
n
v
e
r
t
t
o
c
o
rr
e
s
po
n
d
A
N
N
w
e
i
ght
s
i
n
e
a
c
h
l
a
y
e
r
(
12
)
6.
E
v
a
l
ua
t
e
7.
U
pda
t
e
v
e
l
oc
i
t
y
of
,
,
of
(
6
)
,
(
7
)
8.
R
e
tu
r
n
o
pt
i
m
u
m
W
e
i
g
ht
Evaluation Warning : The document was created with Spire.PDF for Python.
In
do
n
e
s
i
a
n
J
E
l
e
c
E
ng
&
Co
m
p
S
c
i
IS
S
N
:
2502
-
4752
A
pr
oa
c
t
i
v
e
m
e
t
a
he
ur
i
s
t
i
c
m
od
e
l
f
or
op
t
i
m
i
z
i
ng
w
e
i
ght
s
o
f
ar
t
i
f
i
c
i
al
ne
ur
al
ne
t
w
or
k
(
A
l
i
H
a
k
e
m
A
l
s
ae
e
di
)
981
P
re
p
ro
c
e
s
s
i
n
g
D
a
t
a
s
e
t
F
o
rw
a
rd
P
r
o
p
a
g
a
t
i
o
n
E
v
a
l
u
a
t
i
o
n
S
e
t
i
s
f
y
S
t
o
p
Cri
t
e
ri
a
O
p
t
i
m
i
z
e
A
N
N
w
e
i
g
h
t
b
a
s
e
d
o
n
P
S
O
T
ra
i
n
F
o
rw
a
rd
P
r
o
p
a
g
a
t
i
o
n
P
re
d
e
c
t
i
o
n
T
e
s
t
P
re
d
i
c
t
D
a
t
a
c
l
a
s
s
O
p
t
i
m
u
m
W
e
i
g
h
t
s
F
i
gu
r
e
3
.
T
h
e
m
a
i
n
s
t
e
ps
o
f
t
h
e
p
r
o
po
s
e
d
H
N
N
m
o
de
l
3.
R
ES
U
LTS
A
N
D
D
I
S
C
U
S
S
I
O
N
T
h
e
e
v
a
l
ua
t
i
o
n
s
t
ra
t
e
gy
i
s
b
a
s
e
d
o
n
t
e
s
t
i
n
g
t
h
e
p
r
o
po
s
e
d
m
o
de
l
us
i
n
g
t
h
e
t
e
n
da
t
a
s
e
t
s
o
f
U
CI
w
i
t
h
di
f
fe
r
e
nt
a
t
t
ri
b
ut
e
s
[28]
.
T
h
e
p
r
o
po
s
e
d
H
N
N
i
s
c
o
m
pa
r
e
d
w
i
t
h
B
P
i
n
t
r
a
i
n
i
ng
A
N
N
.
T
a
b
l
e
1
i
l
l
us
t
ra
t
e
s
t
h
e
da
t
a
s
e
t
de
s
c
r
i
pt
i
o
n
:
T
a
b
l
e
1
.
U
CI
d
a
t
a
s
e
t
de
s
c
r
i
pt
i
o
n
s
[1
9]
N
o
.
D
a
t
a
s
e
t
N
a
m
e
S
i
z
e
(
A
t
t
r
i
b
u
t
e
x
F
e
a
t
u
re
x
Cl
a
s
s
)
1
Bre
a
s
t
c
a
n
c
e
r1
6
9
9
x
8
x
2
2
W
i
n
e
1
7
8
x
1
3
x
3
3
S
p
e
c
t
f
2
6
7
x
4
4
x
2
4
O
z
o
n
e
l
e
v
e
l
d
e
t
e
c
t
i
o
n
2
5
3
6
x
7
2
x
2
5
Bre
a
s
t
T
i
s
s
u
e
1
0
6
x
9
x
4
6
Ca
r
e
v
a
l
u
a
t
i
o
n
1
7
2
8
x
6
x
4
7
D
ru
g
c
o
n
s
u
m
p
t
i
o
n
1
8
8
5
x
3
2
x
7
8
H
T
Ru
-
2
1
6
3
8
4
x
8
x
2
9
Bu
rs
t
H
e
a
d
e
r
P
a
c
k
e
t
1
0
7
5
x
2
2
x
4
10
A
v
i
l
a
2
0
8
6
7
x
1
0
x
1
2
T
h
e
pr
o
po
s
e
d
H
N
N
m
o
d
e
l
i
s
t
e
s
t
e
d
ove
r
t
e
n
da
t
a
s
e
t
s
t
o
c
l
a
s
s
i
fy
t
h
e
pr
o
b
l
e
m
i
n
t
h
e
U
CI
m
a
c
hi
n
e
l
e
a
rn
i
ng.
T
h
e
da
t
a
s
e
t
s
h
a
v
e
be
e
n
e
xpl
a
i
n
e
d
i
n
t
h
e
T
a
b
l
e
2
w
hi
c
h
i
s
us
e
d
a
s
a
b
e
n
c
hm
a
rk
i
n
o
r
de
r
t
o
e
v
a
l
ua
t
e
t
h
e
pr
o
po
s
e
d
a
l
go
r
i
t
hm
a
n
d
c
o
m
pa
r
e
t
h
e
r
e
s
ul
t
s
w
i
t
h
t
h
e
s
t
a
n
da
r
d
A
N
N
.
T
h
e
pa
ra
m
e
t
e
r
s
o
f
a
l
go
r
i
t
h
m
s
w
e
a
r
e
c
o
m
pa
r
e
d
s
e
t
a
s
s
h
o
w
n
i
n
T
a
b
l
e
2:
T
a
b
l
e
2
.
A
N
N
a
n
d
P
S
O
a
l
go
ri
t
hm
s
pa
ra
m
e
t
e
r
s
A
l
g
o
ri
t
h
m
P
a
ra
m
e
t
e
r
s
A
N
N
w
i
t
h
B
P
HNN
T
he
e
x
p
e
ri
m
e
nt
s
u
s
e
t
he
l
o
g
i
s
t
i
c
a
nd
t
he
t
a
ng
e
nt
hy
p
e
rb
o
l
i
c
f
unc
t
i
o
ns
a
s
a
n
a
c
t
i
v
a
t
i
o
n
f
u
nc
t
i
o
n
f
o
r
b
o
t
h
t
he
H
N
N
a
nd
B
P
a
l
g
o
ri
t
h
m
s
.
T
a
b
l
e
3
s
ho
w
s
t
he
re
s
u
l
t
s
o
f
t
he
e
x
pe
ri
m
e
nt
s
o
f
b
o
t
h
t
he
m
e
nt
i
o
ne
d
a
l
g
o
ri
t
h
m
s
.
T
he
re
s
u
l
t
s
o
f
H
N
N
s
ho
w
a
b
e
t
t
e
r
p
e
rf
o
rm
a
nc
e
i
n
t
he
s
a
m
p
l
e
d
a
t
a
s
e
t
s
B
re
a
s
t
c
a
nc
e
r1
,
W
i
ne
,
O
z
o
ne
l
e
v
e
l
d
e
t
e
c
t
i
o
n,
C
a
r
e
v
a
l
u
a
t
i
o
n,
H
T
R
u
-
2
,
B
u
rs
t
H
e
a
d
e
r
P
a
c
ke
t
,
a
nd
A
v
i
l
a
.
W
h
i
l
e
t
he
A
N
N
w
i
t
h
B
P
re
c
o
rd
e
d
t
he
b
e
s
t
re
s
u
l
t
s
i
n
d
a
t
a
s
e
t
S
p
e
c
t
f
a
nd
B
re
a
s
t
T
i
s
s
u
e
.
B
o
t
h
a
l
g
o
ri
t
hm
s
o
b
t
a
i
ne
d
e
q
u
a
l
a
c
c
u
ra
c
y
i
n
d
a
t
a
s
e
t
D
C
.
T
he
t
ra
i
ni
ng
t
i
m
e
o
f
HN
N
re
q
u
i
re
d
l
e
s
s
t
i
m
e
t
h
a
n
A
N
N
.
I
t
i
s
c
l
e
a
r
l
y
s
ho
w
n
i
n
t
h
e
T
a
b
l
e
3
t
h
a
t
t
he
m
e
t
a
he
u
ri
s
t
i
c
f
u
nc
t
i
o
n
he
l
p
s
i
n
u
p
d
a
t
i
ng
t
he
w
e
i
g
ht
a
s
f
a
s
t
a
s
p
o
s
s
i
b
l
e
c
o
m
p
a
re
d
w
i
t
h
t
he
o
ri
g
i
na
l
A
N
N
-
w
i
t
h
B
P
-
.
F
i
g
u
re
3
s
ho
w
n
c
o
m
p
a
re
p
e
rf
o
rm
a
nc
e
o
f
A
N
N
b
y
u
s
i
ng
B
P
a
nd
H
N
N
(
d
a
t
a
s
e
t
b
re
a
s
t
c
a
nc
e
r)
.
F
i
g
u
re
4
s
ho
w
n
c
o
m
p
a
re
p
e
rf
o
rm
a
nc
e
o
f
A
N
N
b
y
u
s
i
ng
B
P
a
nd
H
N
N
(
d
a
t
a
s
e
t
w
i
ne
).
F
i
g
u
re
5
s
ho
w
n
t
h
e
p
e
rf
o
rm
a
nc
e
o
f
a
l
g
o
ri
t
h
m
s
b
y
u
s
i
ng
t
he
M
S
E
a
s
c
o
m
p
a
re
d
c
ri
t
e
ri
a
.
T
he
re
s
u
l
t
s
i
nd
i
c
a
t
e
t
ha
t
B
P
ha
s
b
e
t
t
e
r
a
c
c
u
ra
c
y
:
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2502
-
4752
In
do
n
e
s
i
a
n
J
E
l
e
c
E
ng
&
Co
m
p
S
c
i
,
V
o
l
.
20
,
N
o
.
2
,
N
o
v
e
m
be
r
20
20
:
97
6
-
984
982
T
a
b
l
e
3
.
T
h
e
e
v
a
l
ua
t
i
o
n
r
e
s
ul
t
o
f
t
h
e
H
N
N
a
n
d
A
N
N
N
o
.
D
a
t
a
s
e
t
N
a
m
e
P
e
r
fo
r
m
a
n
c
e
o
f
t
h
e
A
N
N
P
e
r
fo
r
m
a
n
c
e
o
f
t
h
e
H
N
N
A
c
c
u
ra
c
y
T
i
m
e
i
n
s
e
c
A
c
c
u
ra
c
y
T
i
m
e
i
n
s
e
c
1
Bre
a
s
t
c
a
n
c
e
r1
9
4
.
3
2
1
5
.
2
5
9
6
.
7
2
1
0
.
2
8
2
W
i
n
e
7
5
.
3
2
5
.
9
8
92
3
.
2
2
3
S
p
e
c
t
f
7
9
.
4
1
8
.
9
5
7
6
.
6
1
4
.
3
7
4
O
z
o
n
e
l
e
v
e
l
d
e
t
e
c
t
i
o
n
9
0
.
3
7
1
2
8
.
5
9
7
.
1
2
9
8
.
2
2
5
Bre
a
s
t
T
i
s
s
u
e
8
5
.
9
1
8
.
9
9
80
13
6
Ca
r
e
v
a
l
u
a
t
i
o
n
8
2
.
3
1
6
8
.
3
2
8
4
.
2
2
4
8
.
4
7
7
D
ru
g
c
o
n
s
u
m
p
t
i
o
n
8
4
.
2
9
5
.
4
5
8
4
.
2
8
0
.
3
6
8
H
T
Ru
-
2
8
8
.
6
1
3
7
.
9
9
7
.
2
0
1
2
2
.
9
5
9
Bu
rs
t
H
e
a
d
e
r
P
a
c
k
e
t
8
9
.
4
4
1
8
5
.
7
3
9
3
.
5
1
1
6
8
.
0
2
10
A
v
i
l
a
7
9
.
3
2
2
5
8
.
1
5
8
6
.
3
1
2
1
0
.
1
7
F
i
gu
r
e
3
.
Co
m
p
a
r
e
pe
r
f
o
r
m
a
n
c
e
o
f
A
N
N
by
us
i
n
g
B
P
a
n
d
H
N
N
(
da
t
a
s
e
t
b
r
e
a
s
t
c
a
n
c
e
r
)
F
i
gu
r
e
4
.
Co
m
p
a
r
e
pe
r
f
o
r
m
a
n
c
e
o
f
A
N
N
by
us
i
n
g
B
P
a
n
d
H
N
N
(
da
t
a
s
e
t
w
i
n
e
)
F
i
gu
r
e
5
.
Co
m
p
a
r
e
pe
r
f
o
r
m
a
n
c
e
o
f
A
N
N
by
us
i
n
g
B
P
a
n
d
H
N
N
(
da
t
a
s
e
t
s
pe
c
t
f
)
Evaluation Warning : The document was created with Spire.PDF for Python.
In
do
n
e
s
i
a
n
J
E
l
e
c
E
ng
&
Co
m
p
S
c
i
IS
S
N
:
2502
-
4752
A
pr
oa
c
t
i
v
e
m
e
t
a
he
ur
i
s
t
i
c
m
od
e
l
f
or
op
t
i
m
i
z
i
ng
w
e
i
ght
s
o
f
ar
t
i
f
i
c
i
al
ne
ur
al
ne
t
w
or
k
(
A
l
i
H
a
k
e
m
A
l
s
ae
e
di
)
983
T
h
e
pr
o
po
s
e
d
s
y
s
t
e
m
s
h
ow
s
t
h
a
t
t
h
e
s
t
o
c
h
a
s
t
i
c
t
e
c
hn
i
q
ue
s
(P
S
O
)
ove
r
c
o
m
e
o
n
t
h
e
s
t
a
g
na
t
i
o
n
i
n
A
N
N
w
h
e
n
us
i
n
g
t
h
e
B
P
a
l
go
r
i
t
hm
;
a
l
s
o
,
i
t
o
pt
i
m
i
z
e
s
t
h
e
a
c
c
ura
c
y
of
A
N
N
pr
e
di
c
t
i
o
n
.
T
h
e
a
c
c
ura
c
y
of
H
N
N
i
s
l
e
s
s
t
ha
n
B
P
a
s
s
h
o
w
n
i
n
F
i
gu
r
e
5
,
a
l
t
h
o
ug
h
t
h
e
pe
r
f
o
r
m
a
nc
e
of
H
N
N
i
s
b
e
t
t
e
r
b
e
c
a
us
e
i
t
c
o
ul
d
be
j
um
pi
n
g
f
r
o
m
t
h
e
s
t
a
g
na
t
i
o
n
s
t
a
ge
a
t
l
a
s
t
qu
a
r
t
e
r
f
r
o
m
s
e
a
r
c
h
p
r
o
g
r
e
s
s
.
4.
C
O
N
C
LU
S
I
O
N
A
r
t
i
f
i
c
i
a
l
N
e
u
ra
l
N
e
t
w
o
r
k
i
s
a
n
o
nl
i
n
e
a
r
c
o
m
put
i
ng
s
y
s
t
e
m
i
n
s
pi
r
e
d
b
y
t
h
e
b
i
o
l
o
gi
c
a
l
n
e
u
r
a
l
n
e
t
w
o
r
ks
of
t
h
e
b
r
a
i
n.
It
c
o
n
s
i
s
t
s
o
f
s
e
v
e
r
a
l
l
a
y
e
r
s
a
n
d
e
a
c
h
l
a
y
e
r
ha
s
s
e
ve
r
a
l
n
e
u
r
o
n
s
(n
o
de
s
).
T
h
e
l
e
a
rni
n
g
b
e
h
a
v
i
o
ur
o
f
A
N
N
i
s
b
a
s
e
d
o
n
e
rr
o
r
s
t
ha
t
r
e
s
ul
t
f
r
o
m
t
h
e
f
e
e
db
a
c
k
of
t
h
e
p
r
e
v
i
o
us
l
a
y
e
r
t
o
upda
t
e
t
h
e
w
e
i
ght
s
of
t
h
e
n
e
u
r
o
n
l
a
y
e
r
s
.
T
h
e
w
e
i
g
h
t
s
a
r
e
t
h
e
o
ut
c
o
m
e
of
t
h
e
t
ra
i
n
e
d
n
e
t
w
o
r
k
o
n
a
s
pe
c
i
f
i
c
pr
o
b
l
e
m
t
ha
t
i
s
us
e
d
t
o
pr
e
di
c
t
t
h
e
c
l
a
s
s
o
f
i
n
put
s
.
T
h
e
y
s
t
a
r
t
ra
n
do
m
l
y
a
n
d
upd
a
t
e
d
y
n
a
m
i
c
a
l
l
y
by
t
h
e
b
a
c
kpr
o
pa
g
a
t
i
o
n
a
l
go
ri
t
hm
duri
n
g
A
N
N
t
r
a
i
n
i
ng.
T
h
e
t
ra
i
ni
n
g
p
r
o
c
e
s
s
o
f
A
N
N
r
e
qui
re
s
t
r
e
m
e
n
do
us
t
i
m
e
,
i
n
a
dd
i
t
i
o
n
t
o
t
h
e
c
o
m
pl
e
x
pr
o
c
e
dur
e
t
h
a
t
h
a
s
b
e
e
n
fo
l
l
ow
e
d
w
h
e
n
us
i
n
g
b
a
c
kp
r
o
pa
g
a
t
i
o
n
t
o
t
r
a
i
n
A
N
N
.
P
S
O
i
s
o
n
e
of
t
h
e
po
pul
a
r
s
t
o
c
h
a
s
t
i
c
m
e
t
h
o
ds
fo
r
fe
a
t
u
r
e
s
s
e
l
e
c
t
i
o
n
.
It
ha
s
b
e
e
n
r
e
c
ogni
z
e
d
a
s
f
a
s
t
,
f
l
e
xi
b
l
e
,
e
a
s
y
t
o
i
m
pl
e
m
e
n
t
,
a
n
d
s
uc
c
e
e
d
i
n
o
pt
i
m
i
z
i
n
g
di
f
f
e
r
e
n
t
f
i
e
l
ds
.
T
h
e
r
e
f
o
r
e
,
t
h
e
P
S
O
i
s
us
e
d
t
o
f
i
n
d
t
h
e
o
pt
i
m
a
l
w
e
i
gh
t
o
f
A
N
N
.
By
us
i
n
g
t
h
e
m
e
t
a
h
e
u
ri
s
t
i
c
(P
S
O
),
t
h
e
p
r
o
po
s
e
d
s
y
s
t
e
m
e
nha
n
c
e
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
A
N
N
i
n
b
o
t
h
a
c
c
ura
c
y
a
n
d
p
r
o
c
e
s
s
i
n
g
t
i
m
e
.
T
h
e
t
ra
i
ni
n
g
t
i
m
e
i
s
r
e
duc
e
d
be
c
a
us
e
of
t
h
e
s
i
m
p
l
i
c
i
t
y
of
pr
o
c
e
s
s
e
s
i
n
t
h
e
t
r
a
i
ni
n
g
s
t
a
ge
of
m
e
t
a
h
e
u
r
i
s
t
i
c
.
I
n
f
ut
u
r
e
w
o
r
k,
w
e
s
ugge
s
t
e
nh
a
n
c
i
ng
t
h
e
e
xpl
o
r
a
t
i
o
n
o
f
m
e
t
a
h
e
u
ri
s
t
i
c
m
o
de
l
b
e
fo
r
e
us
i
n
g
t
o
o
pt
i
m
i
z
e
A
N
N
w
e
i
g
h
t
t
o
r
e
duc
e
s
t
a
g
na
t
i
o
n
i
n
t
h
e
a
dv
a
n
c
e
s
e
a
r
c
h
p
r
o
c
e
s
s
.
R
EF
ER
EN
C
ES
[
1]
J
.
T
o
o
,
A
.
R
.
A
bdul
l
a
h
,
N
.
M
.
S
a
a
d
,
N
.
M
.
A
l
i
,
a
nd
T
.
N
.
S
.
T
e
ng
ku
Z
a
w
a
w
i
,
“
F
e
a
t
u
r
e
l
e
s
s
E
M
G
pa
t
t
e
r
n
r
e
c
o
g
ni
t
i
o
n
ba
s
e
d
o
n
c
o
nv
o
l
ut
i
o
na
l
ne
ur
a
l
ne
t
w
o
r
k
,
”
I
n
done
s
.
J
.
E
l
e
c
t
r
.
E
ng
.
C
om
put
.
Sc
i
.
,
v
o
l
.
14
,
no
.
3,
pp
.
129
1
–
12
97
,
2
019
.
[
2]
S
.
D
i
ng
,
H
.
L
i
,
C
.
S
u
,
J
.
Y
u,
a
nd
F
.
J
i
n,
“
E
v
o
l
ut
i
o
na
r
y
a
r
t
i
f
i
c
i
a
l
n
e
ur
a
l
ne
t
w
o
r
ks
:
A
r
e
v
i
e
w
,
”
A
r
t
i
f
.
I
nt
e
l
l
.
R
e
v
.
,
v
o
l
.
39,
no
.
3
,
pp.
2
51
–
2
60
,
2
013
.
[
3]
S
.
A
.
M
o
ha
m
e
d,
M
.
O
t
hm
a
n
,
a
n
d
M
.
H
.
A
.
A
bdul
l
a
h,
“
A
r
e
v
i
e
w
o
n
da
t
a
c
l
us
t
e
r
i
ng
us
i
ng
s
pi
k
i
ng
ne
u
r
a
l
ne
t
w
o
r
k
(
S
N
N
)
m
o
de
l
s
,
”
I
ndone
s
.
J
.
E
l
e
c
t
r
.
E
ng
.
C
om
pu
t
.
S
c
i
.
,
v
o
l
.
15
,
no
.
3,
pp
.
1392
–
140
0,
20
19.
[
4]
R
.
E
b
e
r
ha
r
t
a
nd
J
.
K
e
nne
dy
,
“
N
e
w
o
pt
i
m
i
z
e
r
u
s
i
ng
p
a
r
t
i
c
l
e
s
w
a
r
m
t
he
o
r
y
,
”
P
r
oc
.
I
n
t
.
Sy
m
p
.
M
i
c
r
o
M
a
c
h
.
H
um
.
Sc
i
.
,
p
p.
39
–
43
,
1995
.
[
5]
S
.
M
i
r
j
a
l
i
l
i
a
nd
A
.
L
e
w
i
s
,
“
S
-
s
ha
p
e
d
v
e
r
s
us
V
-
s
ha
p
e
d
t
r
a
ns
f
e
r
f
un
c
t
i
o
ns
f
o
r
bi
n
a
r
y
P
a
r
t
i
c
l
e
S
w
a
r
m
O
p
t
i
m
i
z
a
t
i
o
n,
”
Sw
ar
m
E
v
o
l
.
C
om
p
ut
.
,
v
o
l
.
9,
pp
.
1
–
14,
2
013
.
[
6]
R
.
I
s
l
a
m
,
M
.
N
.
A
kht
a
r
,
B
.
R
.
A
hm
a
d,
U
.
K
.
D
a
s
,
M
.
R
a
hm
a
n,
a
nd
Z
.
I
.
A
.
K
h
a
l
i
b
,
“
A
n
a
ppr
o
a
c
h
t
o
bui
l
d
i
ng
e
ne
r
g
y
c
l
us
t
e
r
s
us
i
ng
pa
r
t
i
c
l
e
s
w
a
r
m
o
pt
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
hm
f
o
r
a
l
l
o
c
a
t
i
ng
t
h
e
t
a
s
ks
i
n
c
o
m
put
a
t
i
o
na
l
g
r
i
d,
”
I
ndo
ne
s
.
J
.
E
l
e
c
t
r
.
E
ng
.
C
om
pu
t
.
S
c
i
.
,
v
o
l
.
14
,
no
.
2
,
pp
.
826
–
833
,
2
019.
[
7]
L
.
B
.
K
huz
y
a
t
o
v
a
a
nd
L
.
A
.
G
a
l
i
ul
l
i
n,
“
O
pt
i
m
i
z
a
t
i
o
n
o
f
pa
r
a
m
e
t
e
r
s
o
f
ne
ur
o
-
f
uz
z
y
m
o
de
l
,
”
I
n
done
s
.
J
.
E
l
e
c
t
r
.
E
ng.
C
om
put
.
Sc
i
.
,
v
o
l
.
17
,
no
.
3,
pp
.
120
6
–
12
09
,
2
019
.
[
8]
A
.
H
.
J
a
bo
r
a
nd
A
.
H
.
A
l
i
,
“
D
u
a
l
H
e
u
r
i
s
t
i
c
F
e
a
t
ur
e
S
e
l
e
c
t
i
o
n
B
a
s
e
d
o
n
G
e
n
e
t
i
c
A
l
g
o
r
i
t
hm
a
nd
B
i
n
a
r
y
P
a
r
t
i
c
l
e
S
w
a
r
m
O
pt
i
m
i
z
a
t
i
o
n,
”
J
.
U
n
i
v
.
B
A
B
Y
L
O
N
pur
e
A
ppl
.
Sc
i
.
,
v
o
l
.
2
7,
no
.
1
,
pp.
1
71
–
1
83,
2
019
.
[
9]
M
.
B
a
n
d
G
.
H
o
l
i
,
“
A
n
o
pt
i
m
a
l
a
nd
s
e
c
u
r
e
w
a
t
e
r
m
a
r
k
i
ng
s
y
s
t
e
m
us
i
ng
S
W
T
-
S
V
D
a
n
d
P
S
O
,
”
I
nd
one
s
.
J
.
E
l
e
c
t
r
.
E
ng.
C
om
p
ut
.
Sc
i
.
,
v
o
l
.
18
,
no
.
2,
p
.
917
,
2020
.
[
10]
S
.
S
h
i
n
d
o
,
T
.
G
o
t
o
,
T
.
K
i
r
i
s
h
i
m
a
,
a
n
d
K
.
T
s
u
c
h
i
d
a
,
“
A
n
o
p
t
i
m
i
z
a
t
i
o
n
o
f
f
a
c
i
a
l
f
e
a
t
u
r
e
p
o
i
n
t
d
e
t
e
c
t
i
o
n
p
r
o
g
r
a
m
by
u
s
i
n
g
s
e
v
e
r
a
l
t
y
p
e
s
o
f
c
o
nv
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
d
o
n
e
s
.
J
.
E
l
e
c
t
r
.
E
n
g
.
C
o
m
p
u
t
.
S
c
i
.
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
8
2
7
–
8
3
4
,
2
0
1
9
.
[
11]
M
.
Y
us
o
f
f
,
F
.
M
.
D
na
j
i
b
,
a
nd
R
.
I
s
m
a
i
l
,
“
H
y
br
i
d
ba
c
kp
r
o
pa
g
a
t
i
o
n
ne
ur
a
l
ne
t
w
o
r
k
-
pa
r
t
i
c
l
e
s
w
a
r
m
o
pt
i
m
i
z
a
t
i
o
n
f
o
r
s
e
i
s
m
i
c
d
a
m
a
g
e
b
ui
l
d
i
ng
p
r
e
d
i
c
t
i
o
n,
”
I
nd
one
s
.
J
.
E
l
e
c
t
r
.
E
ng.
C
om
p
ut
.
S
c
i
.
,
v
o
l
.
14
,
no
.
1
,
pp
.
360
–
367
,
2019
.
[
12]
R
.
T
.
C
a
nd
R
.
S
i
v
r
a
m
a
kr
i
s
h
na
n
,
“
F
uz
z
y
N
e
ur
o
-
G
e
ne
t
i
c
A
ppr
o
a
c
h
f
o
r
F
e
a
t
ur
e
S
e
l
e
c
t
i
o
n
a
n
d
I
m
a
g
e
C
l
a
s
s
i
f
i
c
a
t
i
o
n
i
n
A
ug
m
e
nt
e
d
R
e
a
l
i
t
y
S
y
s
t
e
m
s
,
”
v
o
l
.
8,
no
.
x
,
p
p.
19
4
–
20
4,
2
019
.
[
13]
A
.
S
a
r
ka
r
,
J
.
D
e
y
,
a
nd
A
.
B
how
m
i
k,
“
M
ul
t
i
l
a
y
e
r
ne
ur
a
l
ne
t
w
o
r
k
s
y
nc
hr
o
ni
z
e
d
s
e
c
ur
e
d
s
e
s
s
i
o
n
ke
y
ba
s
e
d
e
nc
r
y
pt
i
o
n
i
n
w
i
r
e
l
e
s
s
c
o
m
m
uni
c
a
t
i
o
n,
”
I
ndone
s
.
J
.
E
l
e
c
t
r
.
E
ng
.
C
o
m
put
.
Sc
i
.
,
v
o
l
.
14
,
no
.
1
,
p
.
1
69
,
2
019
.
[
14]
S
.
V
e
r
m
a
,
G
.
T
.
T
h
a
m
pi
,
a
nd
M
.
R
a
o
,
“
A
N
N
ba
s
e
d
m
e
t
ho
d
f
o
r
i
m
pr
o
v
i
ng
go
l
d
pr
i
c
e
f
o
r
e
c
a
s
t
i
ng
a
c
c
ur
a
c
y
t
hr
o
ug
h
m
o
di
f
i
e
d
g
r
a
di
e
nt
d
e
s
c
e
n
t
m
e
t
ho
ds
,
”
I
A
E
S
I
n
t
.
J
.
A
r
t
i
f
.
I
nt
e
l
l
.
,
v
o
l
.
9,
no
.
1,
pp
.
46
–
57,
2
020
.
[
15]
M
.
L
o
ne
s
,
Se
an
L
uk
e
:
e
s
s
e
nt
i
al
s
of
m
e
t
ahe
ur
i
s
t
i
c
s
,
v
o
l
.
12
,
no
.
3.
2
011.
[
16
]
R
.
Y
u
,
X
.
A
n,
B
.
J
i
n,
J
.
S
hi
,
O
.
A
.
M
o
v
e
,
a
n
d
Y
.
L
i
u,
“
P
a
r
t
i
c
l
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
pt
i
m
i
z
a
t
i
o
n
-
ba
s
e
d
B
P
ne
t
w
o
r
k
f
o
r
t
e
l
e
c
o
m
m
uni
c
a
t
i
o
n
c
us
t
o
m
e
r
c
hu
r
n
pr
e
d
i
c
t
i
o
n,
”
N
e
ur
al
C
om
pu
t
.
A
p
pl
.
,
v
o
l
.
2
9,
no
.
3,
p
p.
70
7
–
72
0,
20
18
.
[
17]
F
.
G
a
x
i
o
l
a
,
P
.
M
e
l
i
n
,
F
.
V
a
l
de
z
,
a
n
d
O
.
C
a
s
t
i
l
l
o
,
“
O
p
t
i
m
i
z
a
t
i
o
n
of
t
y
pe
-
2
f
uz
z
y
w
e
i
g
ht
f
o
r
ne
ur
a
l
n
e
t
w
o
r
k
u
s
i
ng
g
e
ne
t
i
c
a
l
g
o
r
i
t
hm
a
n
d
pa
r
t
i
c
l
e
s
w
a
r
m
o
pt
i
m
i
z
a
t
i
o
n,
”
201
3
W
or
l
d
C
ongr
.
N
a
t
.
B
i
o
l
.
I
ns
pi
r
e
d
C
om
put
.
N
aB
I
C
20
13
,
v
o
l
.
1,
no
.
1,
p
p.
22
–
28
,
201
3.
[
18]
V
.
K
.
O
j
a
h,
A
.
A
br
a
ha
m
,
a
n
d
V
.
S
na
s
e
,
“
S
i
m
u
l
t
a
ne
o
us
O
pt
i
m
i
z
a
t
i
o
n
o
f
N
e
ur
a
l
N
e
t
w
o
r
k
W
e
i
g
ht
s
a
nd
A
c
t
i
v
e
N
o
de
s
us
i
ng
M
e
t
a
he
u
r
i
s
t
i
c
s
,
”
i
n
14
t
h
I
n
t
e
r
na
t
i
ona
l
C
on
f
e
r
e
nc
e
on
H
y
br
i
d
I
nt
e
l
l
i
ge
nt
Sy
s
t
e
m
s
,
2
014
,
pp.
2
48
–
2
53.
[
19]
N
.
Z
.
M
o
h
d
A
l
i
,
I
.
M
u
s
i
r
i
n
,
a
n
d
H
.
M
o
h
a
m
a
d
,
“
C
l
o
n
a
l
e
v
o
l
u
t
i
o
n
a
r
y
p
a
r
t
i
c
l
e
s
w
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
c
o
n
g
e
s
t
i
o
n
m
a
n
a
g
e
m
e
n
t
a
n
d
c
o
m
p
e
n
s
a
t
i
o
n
s
c
h
e
m
e
i
n
p
o
w
e
r
s
y
s
t
e
m
,
”
I
n
d
o
n
e
s
.
J
.
E
l
e
c
t
r
.
E
n
g
.
C
o
m
p
u
t
.
S
c
i
.
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
5
9
1
–
5
9
8
,
2
0
1
9
.
[
20]
C
.
G
u
l
c
e
hr
e
,
M
.
M
o
c
z
ul
s
ki
,
M
.
D
e
n
i
l
,
a
nd
Y
.
B
e
ng
i
o
,
“
N
o
i
s
y
a
c
t
i
v
a
t
i
o
n
f
unc
t
i
o
ns
,
”
3
3r
d
I
n
t
.
C
on
f
.
M
a
c
h
.
L
e
ar
n
.
I
C
M
L
2
016
,
v
o
l
.
6
,
p
p.
44
57
–
4
466
,
2016
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2502
-
4752
In
do
n
e
s
i
a
n
J
E
l
e
c
E
ng
&
Co
m
p
S
c
i
,
V
o
l
.
20
,
N
o
.
2
,
N
o
v
e
m
be
r
20
20
:
97
6
-
984
984
[
21]
R
.
K
a
u
br
u
e
g
g
e
r
,
L
.
P
a
s
t
o
r
i
,
a
nd
J
.
C
.
B
u
di
c
h,
“
C
h
i
r
a
l
t
o
po
l
o
g
i
c
a
l
pha
s
e
s
f
r
o
m
a
r
t
i
f
i
c
i
a
l
ne
ur
a
l
n
e
t
w
o
r
k
s
,
”
P
hy
s
.
R
e
v
.
B
,
v
o
l
.
97
,
no
.
19,
p
p.
1
–
8,
20
18.
.
[
22]
N
.
F
.
F
a
dz
a
i
l
,
S
.
M
.
Z
a
l
i
,
M
.
A
.
K
h
a
i
r
ud
i
n
,
a
nd
N
.
H
.
H
a
na
f
i
,
“
S
t
a
t
o
r
w
i
nd
i
ng
f
a
ul
t
d
e
t
e
c
t
i
o
n
o
f
i
nduc
t
i
o
n
g
e
ne
r
a
t
o
r
ba
s
e
d
w
i
nd
t
ur
b
i
n
e
us
i
ng
A
N
N
,
”
I
ndo
ne
s
.
J
.
E
l
e
c
t
r
.
E
ng
.
C
om
pu
t
.
S
c
i
.
,
v
o
l
.
1
9,
no
.
1
,
p
p.
12
6
–
13
3,
20
20
.
[
23]
S
.
L
a
w
r
e
nc
e
,
A
.
C
.
T
s
o
i
,
a
nd
A
.
D
.
B
a
c
k,
“
F
unc
t
i
o
n
A
ppr
o
xi
m
a
t
i
o
n
w
i
t
h
N
e
ur
a
l
N
e
t
w
o
r
ks
a
nd
L
oc
a
l
M
e
t
ho
ds
:
B
i
a
s
,
V
a
r
i
a
nc
e
a
nd
S
m
o
o
t
hne
s
s
,
”
A
u
s
t
.
C
onf
.
N
e
ur
a
l
N
e
t
w
or
k
s
,
pp
.
16
–
21
,
199
6.
[
24]
A
.
R
a
ki
t
i
a
n
s
ka
i
a
a
nd
A
.
E
ng
e
l
b
r
e
c
ht
,
“
W
e
i
g
ht
r
e
g
u
l
a
r
i
s
a
t
i
o
n
i
n
pa
r
t
i
c
l
e
s
w
a
r
m
o
p
t
i
m
i
s
a
t
i
o
n
ne
ur
a
l
n
e
t
w
o
r
k
t
r
a
i
n
i
ng
,
”
I
E
E
E
SSC
I
201
4
-
201
4
I
E
E
E
S
y
m
p.
Se
r
.
C
om
pu
t
.
I
n
t
e
l
l
.
-
S
I
S
201
4
2014
I
E
E
E
Sy
m
p.
Sw
ar
m
I
n
t
e
l
l
.
P
r
oc
.
,
p
p.
34
–
41
,
2015
.
[
25]
M
.
D
.
S
ul
i
s
t
i
y
o
,
R
.
N
.
D
a
y
a
w
a
t
i
,
a
n
d
N
ur
l
a
s
m
a
y
a
,
“
E
v
o
l
ut
i
o
n
s
t
r
a
t
e
g
i
e
s
f
o
r
w
e
i
g
ht
o
pt
i
m
i
z
a
t
i
o
n
o
f
A
r
t
i
f
i
c
i
a
l
N
e
ur
a
l
N
e
t
w
o
r
k
i
n
t
i
m
e
s
e
r
i
e
s
p
r
e
d
i
c
t
i
o
n,
”
P
r
oc
.
20
13
I
nt
.
C
onf
.
R
ob
ot
.
B
i
om
i
m
e
t
i
c
s
,
I
n
t
e
l
l
.
C
om
p
ut
.
Sy
s
t
.
R
O
B
I
O
N
E
T
I
C
S
2
013
,
no
.
N
o
v
e
m
be
r
,
p
p.
14
3
–
14
7,
20
13
.
[
26]
A
.
H
.
A
l
-
s
a
e
e
d
i
,
“
B
i
n
a
r
y
M
e
a
n
-
V
a
r
i
a
nc
e
M
a
pp
i
ng
O
pt
i
m
i
z
a
t
i
o
n
A
l
g
o
r
i
t
hm
(
B
M
V
M
O
)
,
”
J
.
A
pp
l
.
P
hy
s
.
S
c
i
.
,
v
o
l
.
2,
no
.
2
,
pp.
4
2
–
47
,
201
6.
[
27]
A
.
O
.
T
o
pa
l
a
nd
O
.
A
l
t
un,
“
A
no
v
e
l
m
e
t
a
-
he
ur
i
s
t
i
c
a
l
g
o
r
i
t
hm
:
D
yna
m
i
c
V
i
r
t
ua
l
B
a
t
s
A
l
go
r
i
t
hm
,
”
I
n
f
.
Sc
i
.
(
N
y
)
.
,
v
o
l
.
354
,
pp.
2
22
–
2
35
,
2
016
.
[
28]
D
.
A
ha
,
E
.
K
e
o
g
h,
P
a
t
r
i
c
k
M
u
r
phy
C
hr
i
s
t
o
phe
r
M
e
r
z
,
C
.
B
l
a
ke
,
S
.
H
e
t
t
i
c
h,
a
nd
D
.
N
e
w
m
a
n
,
“
T
he
U
C
I
M
a
c
hi
ne
L
e
a
r
ni
ng
R
e
po
s
i
t
o
r
y
,
”
N
at
i
on
al
Sc
i
e
nt
i
f
i
c
F
ounda
t
i
on
,
2
007
.
B
I
O
G
R
A
P
H
I
ES
O
F
A
U
T
H
O
R
S
A
l
i
H
ak
e
m
A
l
s
a
e
e
d
i
i
s
c
o
m
pl
e
t
e
d
B
.
S
c
.
i
n
C
o
m
put
e
r
S
c
i
e
nc
e
s
i
n
200
6
f
r
o
m
t
he
c
o
l
l
e
g
e
o
f
s
c
i
e
nc
e
s
a
t
U
n
i
v
e
r
s
i
t
y
o
f
Al
-
Q
a
di
s
i
y
a
h,
D
i
w
a
n
i
y
a
,
I
r
a
q.
R
e
c
e
i
v
e
d
h
i
s
M
.
S
c
.
(
m
a
s
t
e
r
)
i
n
c
o
m
put
e
r
s
c
i
e
nc
e
s
i
n
t
h
e
y
e
a
r
2016
f
r
o
m
t
he
c
o
l
l
e
g
e
o
f
c
o
m
put
e
r
s
c
i
e
n
c
e
s
a
t
t
he
Y
i
l
d
i
z
T
e
c
hni
c
a
l
U
ni
v
e
r
s
i
t
y
(
Y
T
U
)
,
I
s
t
a
nbu
l
,
T
ur
k
e
y
.
H
e
ha
s
w
o
r
ke
d
a
s
a
l
e
c
t
u
r
e
r
a
t
a
num
be
r
o
f
t
he
I
r
a
qi
U
ni
v
e
r
s
i
t
i
e
s
i
n
t
he
a
r
e
a
s
o
f
A
r
t
i
f
i
c
i
a
l
I
nt
e
l
l
i
g
e
n
t
,
D
a
t
a
m
i
n
i
ng
,
a
nd
s
i
g
na
l
pr
o
c
e
s
s
i
ng
.
H
e
c
ur
r
e
n
t
l
y
w
o
r
ks
a
s
a
l
e
c
t
u
r
e
r
i
n
t
he
U
n
i
v
e
r
s
i
t
y
of
A
l
-
Q
a
di
s
i
y
a
h.
H
i
s
r
e
s
e
a
r
c
h
i
nt
e
r
e
s
t
s
m
a
c
hi
ne
l
e
a
r
ni
ng
,
s
m
a
r
t
o
pt
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
hm
s
,
a
nd
o
pt
i
m
i
z
a
t
i
o
n
o
f
B
i
g
D
a
t
a
.
A
l
i
ha
s
s
e
v
e
r
a
l
publ
i
c
a
t
i
o
ns
i
n
t
he
a
r
e
a
s
o
f
t
h
e
bi
na
r
y
o
f
m
e
t
a
he
ur
i
s
t
i
c
o
pt
i
m
i
z
a
t
i
o
n
a
nd
d
a
t
a
m
i
n
i
ng
A
l
i
H
u
s
s
e
i
n
A
l
j
an
a
b
i
i
s
c
o
m
pl
e
t
e
d
B
.
S
c
.
i
n
C
o
m
put
e
r
S
c
i
e
nc
e
s
i
n
200
6
f
r
o
m
t
he
c
o
l
l
e
g
e
o
f
s
c
i
e
nc
e
s
a
t
U
n
i
v
e
r
s
i
t
y
o
f
A
l
-
Q
a
di
s
i
y
a
h,
D
i
w
a
n
i
y
a
,
I
r
a
q.
R
e
c
e
i
v
e
d
h
i
s
M
.
S
c
.
(
m
a
s
t
e
r
)
i
n
c
o
m
put
e
r
s
c
i
e
nc
e
s
i
n
t
he
y
e
a
r
2014
f
r
o
m
t
he
c
o
l
l
e
g
e
of
c
o
m
put
e
r
s
c
i
e
nc
e
s
a
t
t
h
e
B
a
by
l
o
n
U
ni
v
e
r
s
i
t
y
,
B
a
bi
l
,
I
r
a
q.
H
e
i
s
c
ur
r
e
nt
l
y
w
o
r
ki
ng
a
s
a
l
e
c
t
u
r
e
r
i
n
t
h
e
A
l
-
Q
a
di
s
i
y
a
h
E
duc
a
t
i
o
n
D
i
r
e
c
t
o
r
a
t
e
.
H
i
s
r
e
s
e
a
r
c
h
i
nt
e
r
e
s
t
s
m
a
c
hi
n
e
l
e
a
r
ni
ng
,
S
e
c
ur
i
t
y
i
nf
o
r
m
a
t
i
o
n,
a
nd
s
o
f
t
c
om
put
i
ng
.
A
l
i
h
a
s
s
e
v
e
r
a
l
pub
l
i
c
a
t
i
o
ns
i
n
t
he
a
r
e
a
s
o
f
da
t
a
m
i
n
i
ng
a
n
d
n
e
t
w
o
r
k
i
de
n
t
i
f
i
c
a
t
i
o
n.
M
e
h
d
i
E
b
ad
y
M
an
a
a
i
s
c
u
r
r
e
n
t
l
y
a
n
a
s
s
i
s
t
a
n
t
p
r
o
f
e
s
s
o
r
i
n
t
he
d
e
pa
r
t
m
e
n
t
o
f
i
nf
o
r
m
a
t
i
o
n
n
e
t
w
o
r
k
,
C
o
l
l
e
g
e
o
f
I
nf
o
r
m
a
t
i
o
n
T
e
c
hno
l
o
g
y
,
U
n
i
v
e
r
s
i
t
y
o
f
B
a
by
l
o
n
.
H
e
r
e
c
e
i
v
e
d
h
i
s
b
a
c
h
e
l
o
r
'
s
de
g
r
e
e
f
r
o
m
t
he
U
n
i
v
e
r
s
i
t
y
o
f
B
a
by
l
o
n
,
c
o
l
l
e
g
e
o
f
s
c
i
e
nc
e
i
n
1
9
99
-
20
0
0
.
H
i
s
m
a
s
t
e
r
o
f
s
c
i
e
nc
e
f
r
o
m
U
n
i
v
e
r
s
i
t
y
U
t
a
r
a
M
a
l
a
y
s
i
a
(
U
U
M
)
,
M
a
l
a
y
s
i
a
i
n
2
0
12
.
H
e
r
e
c
e
i
v
e
d
h
i
s
P
hD
i
n
C
o
m
p
u
t
e
r
S
c
i
e
nc
e
a
nd
i
n
t
h
e
f
i
e
l
d
N
e
t
w
o
r
k
S
e
c
u
r
i
t
y
a
n
d
D
a
t
a
M
i
n
i
ng
u
s
i
ng
C
l
o
u
d
C
o
m
p
u
t
i
ng
f
r
o
m
t
he
U
n
i
v
e
r
s
i
t
y
o
f
B
a
by
l
o
n
-
C
o
l
l
e
g
e
o
f
I
nf
o
r
m
a
t
i
o
n
T
e
c
hno
l
o
g
y
i
n
20
1
6
.
H
e
i
s
c
u
r
r
e
n
t
l
y
f
o
c
us
i
ng
o
n
t
he
de
t
e
c
t
i
o
n
o
f
t
he
a
t
t
a
c
k
s
us
i
ng
d
a
t
a
m
i
n
i
ng
t
e
c
hn
i
q
u
e
s
.
T
h
e
m
a
i
n
i
n
t
e
r
e
s
t
i
ng
f
i
e
l
d
s
a
r
e
n
e
t
w
o
r
k
a
d
m
i
n
i
s
t
r
a
t
i
o
n
a
n
d
d
i
s
t
r
i
b
u
t
e
d
o
b
j
e
c
t
-
o
r
i
e
n
t
e
d
t
o
p
i
c
s
,
n
e
t
w
o
r
k
p
r
o
t
o
c
o
l
s
T
C
P
/
I
P
s
u
i
t
e
,
M
o
b
i
l
e
A
d
-
ho
c
n
e
t
w
o
r
k
(
M
A
N
e
t
)
,
D
a
t
a
M
i
n
i
ng
T
e
c
h
n
i
qu
e
s
(
c
l
u
s
t
e
r
i
ng
a
n
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
)
,
c
o
m
m
u
n
i
c
a
t
i
o
n
s
o
f
t
w
a
r
e
,
ne
t
w
o
r
k
s
e
c
u
r
i
t
y
,
c
l
o
u
d
c
o
m
p
u
t
i
ng
,
I
n
t
e
r
n
e
t
o
f
T
h
i
ng
s
,
a
n
d
u
ns
t
r
uc
t
u
r
e
d
d
a
t
a
A
d
i
l
r
e
c
e
i
v
e
d
hi
s
B
.
S
c
.
i
n
C
o
m
put
e
r
S
c
i
e
nc
e
i
n
200
9
f
r
o
m
t
he
C
o
l
l
e
g
e
o
f
S
c
i
e
nc
e
a
t
U
ni
v
e
r
s
i
t
y
o
f
A
l
-
Q
a
di
s
i
y
a
h,
D
i
w
a
ni
y
a
,
I
r
a
q.
H
e
r
e
c
e
i
v
e
d
hi
s
M
.
S
c
.
i
n
C
o
m
put
e
r
S
c
i
e
nc
e
i
n
2016
f
r
o
m
K
e
nt
S
t
a
t
e
U
ni
v
e
r
s
i
t
y
,
O
hi
o
,
U
n
i
t
e
d
S
t
a
t
e
s
.
H
e
i
s
w
o
r
ki
ng
a
s
a
l
e
c
t
u
r
e
r
a
t
t
he
U
ni
v
e
r
s
i
t
y
of
A
l
-
Q
a
di
s
i
y
a
h.
H
i
s
t
e
a
c
hi
ng
a
nd
r
e
s
e
a
r
c
h
i
n
t
e
r
e
s
t
s
i
nc
l
ude
C
o
m
put
e
r
V
i
s
i
o
n
,
B
i
o
m
e
di
c
a
l
I
m
a
g
i
ng
,
I
m
a
g
e
P
r
o
c
e
s
s
i
ng
,
m
a
c
hi
n
e
a
nd
de
e
p
l
e
a
r
ni
ng
.
Evaluation Warning : The document was created with Spire.PDF for Python.