I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
11
,
No
.
1
,
J
u
ly
201
8
,
p
p
.
1
21
~
1
28
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
11
.i
1
.
p
p
1
21
-
1
28
121
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
H
y
brid
Arti
ficial
Neura
l Ne
tw
o
rk
w
ith
M
eta
-
H
euris
tics
for
G
rid
-
Co
nnec
ted
Photo
v
o
ltaic Sy
st
e
m
O
u
tpu
t
P
redic
tion
No
rf
a
riza
ni No
rdin
, S
ha
hril
I
rw
a
n Sul
a
i
m
a
n
,
Ah
m
a
d M
a
li
k
i O
m
a
r
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
,
4
0
4
5
0
S
h
a
h
A
la
m
,
S
e
lan
g
o
r,
M
a
lay
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
a
n
4
,
2
0
1
8
R
ev
i
s
ed
Mar
15
,
2
0
1
8
A
cc
ep
ted
A
p
r
5
,
2
0
1
8
T
h
is
p
a
p
e
r
p
re
se
n
ts
th
e
p
e
rf
o
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
h
y
b
rid
A
rti
f
i
c
ial
Ne
u
ra
l
Ne
tw
o
rk
(
A
N
N)
m
o
d
e
l
w
it
h
se
lec
ted
m
e
ta
-
h
e
u
risti
c
s
f
o
r
p
re
d
ictin
g
th
e
A
C
o
u
t
p
u
t
p
o
w
e
r
f
o
f
a
G
rid
-
Co
n
n
e
c
ted
P
h
o
to
v
o
l
taic
(G
CP
V
)
.
T
h
e
A
NN
h
a
s
b
e
e
n
h
y
b
rid
ize
d
w
it
h
th
re
e
m
e
t
a
-
h
e
u
risti
c
s,
i.
e
.
Cu
c
k
o
o
S
e
a
rc
h
A
lg
o
rit
h
m
(CS
A
),
Ev
o
lu
ti
o
n
a
ry
P
ro
g
ra
m
m
in
g
(EP
)
a
n
d
F
iref
l
y
A
lg
o
rit
h
m
(F
A)
se
p
a
ra
tel
y
.
T
h
e
s
e
m
e
ta
-
h
e
u
risti
c
s
w
e
r
e
u
se
d
to
o
p
t
im
ize
th
e
n
u
m
b
e
r
o
f
n
e
u
ro
n
s,
lea
rn
in
g
ra
te
a
n
d
m
o
m
e
n
tu
m
ra
te
su
c
h
th
a
t
th
e
Ro
o
t
M
e
a
n
S
q
u
a
re
Err
o
r
(RM
S
E)
o
f
th
e
p
re
d
icti
o
n
wa
s
m
in
i
m
ize
d
d
u
rin
g
th
e
A
NN
train
in
g
p
ro
c
e
ss
.
T
h
e
re
su
lt
s
sh
o
we
d
th
a
t
CS
A
h
a
d
o
u
tp
e
rf
o
rm
e
d
EP
a
n
d
F
A
in
p
ro
d
u
c
in
g
t
h
e
l
o
w
e
st
RM
S
E.
L
a
ter,
M
u
tate
d
Cu
c
k
o
o
S
e
a
rc
h
A
lg
o
rit
h
m
(M
CS
A
)
w
a
s
in
tro
d
u
c
e
d
b
y
in
c
o
rp
o
ra
ti
n
g
G
a
u
ss
ian
m
u
tatio
n
o
p
e
r
a
to
r
in
th
e
c
o
n
v
e
n
ti
o
n
a
l
CS
A
.
F
u
rth
e
r
in
v
e
stig
a
ti
o
n
sh
o
w
e
d
th
a
t
M
S
CA
p
e
rf
o
r
m
e
d
b
e
tt
e
r
p
re
d
ictio
n
w
h
e
n
c
o
m
p
a
re
d
w
it
h
th
e
c
o
n
v
e
n
ti
o
n
a
l
CS
A
in
term
s
o
f
RM
S
E
a
n
d
c
o
m
p
u
tatio
n
t
im
e
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
n
e
u
r
a
l
n
et
w
o
r
k
(
A
NN)
C
u
c
k
o
o
s
ea
r
ch
a
l
g
o
r
ith
m
(
C
S
A
)
Fire
f
l
y
a
lg
o
r
it
h
m
(
F
A
)
E
v
o
lu
tio
n
ar
y
p
r
o
g
r
a
m
m
i
n
g
(
E
P
)
Gr
id
-
c
o
n
n
ec
etd
p
h
o
to
v
o
ltaic
(
GC
P
V)
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
No
r
f
ar
izan
i N
o
r
d
in
,
Facu
lt
y
o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
4
0
4
5
0
Sh
ah
A
la
m
,
Sela
n
g
o
r
,
Ma
la
y
s
ia
.
E
m
ail:
n
o
r
f
a
n
o
r
d
in
1
9
0
7
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
a
Gr
id
-
C
o
n
n
ec
ted
P
h
o
to
v
o
ltaic
(
GC
P
V)
s
y
s
te
m
,
o
n
e
m
aj
o
r
q
u
esti
o
n
a
m
o
n
g
co
n
s
u
m
er
s
is
h
o
w
m
u
c
h
o
u
tp
u
t
en
er
g
y
ca
n
b
e
o
b
tain
ed
f
r
o
m
t
h
e
s
y
s
te
m
th
r
o
u
g
h
o
u
t
t
h
e
o
p
er
atio
n
.
I
n
m
a
n
y
ca
s
e
s
,
cu
s
to
m
er
s
w
o
u
ld
w
an
t
to
k
n
o
w
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
as
s
o
ciate
d
G
C
P
V
s
y
s
te
m
u
n
d
er
d
if
f
er
en
t
cli
m
atic
co
n
d
itio
n
s
.
T
h
er
ef
o
r
e,
m
a
n
y
s
t
u
d
ies
h
a
v
e
b
ee
n
co
n
d
u
cted
i
n
o
r
d
er
to
p
r
ed
ict
th
e
o
u
tp
u
t
o
f
t
h
e
s
y
s
te
m
.
On
e
o
f
th
e
p
o
p
u
lar
tech
n
iq
u
es
u
s
ed
f
o
r
p
r
ed
ictio
n
is
b
y
u
s
i
n
g
A
r
ti
f
icial
Neu
r
a
l
Net
w
o
r
k
s
(
A
NN)
[
1
]
-
[
4
]
.
W
h
ile
t
h
i
s
s
t
u
d
y
h
ad
d
is
co
v
er
ed
m
a
n
y
f
i
n
d
i
n
g
s
i
n
P
V
o
u
tp
u
t
p
r
ed
ictio
n
u
s
i
n
g
ANN,
th
e
ANN
d
esi
g
n
w
a
s
h
e
av
il
y
d
ep
en
d
en
t
o
n
p
ast
ex
p
er
ien
ce
w
it
h
t
h
e
s
i
m
i
lar
ap
p
licatio
n
an
d
al
s
o
s
u
b
j
ec
ted
to
tr
ial
an
d
er
r
o
r
p
r
o
ce
s
s
[
5
]
.
T
h
e
tr
ial
an
d
er
r
o
r
p
r
o
ce
s
s
d
u
r
in
g
A
NN
tr
ain
i
n
g
ca
n
b
e
v
er
y
co
m
p
le
x
an
d
ti
m
e
co
n
s
u
m
i
n
g
.
T
h
er
ef
o
r
e,
m
eta
-
h
eu
r
i
s
ti
c
alg
o
r
ith
m
s
ar
e
p
r
esen
ted
i
n
t
h
i
s
p
ap
er
to
f
ac
ilit
ate
th
e
ANN
t
r
ain
in
g
s
u
c
h
t
h
at
t
h
e
p
r
ed
ictio
n
o
f
th
e
AC
o
u
tp
u
t
f
r
o
m
t
h
e
GC
P
V
s
y
s
te
m
i
s
o
p
tim
ized
.
I
n
o
r
d
er
to
s
o
lv
e
m
a
n
y
t
y
p
es
o
f
o
p
ti
m
izatio
n
p
r
o
b
le
m
s
,
m
et
a
-
h
e
u
r
is
tics
ar
e
u
s
ed
as
th
e
y
h
av
e
b
etter
p
o
ten
tial
in
s
o
lv
i
n
g
co
m
p
lex
o
p
tim
izatio
n
p
r
o
b
le
m
s
w
h
e
n
co
m
p
ar
ed
to
tr
ad
itio
n
al
alg
o
r
i
th
m
s
[
6
]
.
E
x
a
m
p
le
s
o
f
m
eta
-
h
eu
r
i
s
tics
ar
e
Ge
n
eti
c
A
l
g
o
r
ith
m
s
(
G
A
)
,
S
i
m
u
late
d
A
n
n
ea
li
n
g
(
S
A
)
,
A
n
t
C
o
lo
n
ies
Op
ti
m
izat
io
n
(
AC
O)
,
P
ar
ticle
Sw
ar
m
Op
ti
m
izatio
n
(
P
SO)
,
B
ee
C
o
lo
n
ies
Op
ti
m
izatio
n
(
B
C
O)
,
Har
m
o
n
y
Sear
c
h
A
l
g
o
r
it
h
m
(
HS)
,
Fire
f
l
y
Al
g
o
r
ith
m
(
F
A
)
,
B
at
A
lg
o
r
it
h
m
(
B
A
)
an
d
Kr
ill
Her
d
(
KH)
[
7
]
.
B
esid
es
t
h
at,
s
ev
er
al
atte
m
p
t
s
w
er
e
m
ad
e
to
f
ac
ilit
ate
th
e
A
N
N
d
esig
n
b
y
co
m
b
in
i
n
g
t
h
e
A
NN
m
o
d
els
to
g
et
h
er
w
it
h
an
m
eta
-
h
eu
r
i
s
tic
alg
o
r
ith
m
s
,
s
u
c
h
as
E
v
o
l
u
tio
n
ar
y
P
r
o
g
r
a
m
m
i
n
g
-
A
r
ti
f
icia
l
Neu
r
al
Net
w
o
r
k
(
E
P
-
ANN)
[
8
]
-
[
10
]
,
A
r
tific
ial
B
ee
C
o
lo
n
y
[
11
]
,
Har
m
o
n
y
Sear
ch
-
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
(
H
S
-
A
N
N)
[
12
]
an
d
P
ar
ticle
S
w
ar
m
Op
ti
m
izatio
n
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
11
,
No
.
1
,
J
u
ly
201
8
:
1
2
1
–
1
2
8
122
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
(
P
SO
-
ANN)
[
13
]
.
Mo
s
t
o
f
th
e
m
ar
e
in
s
p
ir
ed
b
y
t
h
e
n
a
tu
r
e
,
b
y
m
i
m
ic
k
in
g
t
h
e
s
u
cc
e
s
s
f
u
l c
h
ar
ac
ter
is
t
ics o
f
t
h
e
p
h
y
s
ica
l,
b
io
lo
g
ical
an
d
s
o
ci
o
lo
g
ical
s
y
s
te
m
s
.
Nev
er
th
e
less
,
s
o
m
e
o
f
t
h
ese
al
g
o
r
ith
m
s
ca
n
g
iv
e
b
etter
s
o
l
u
t
io
n
s
to
s
o
m
e
p
ar
ticu
lar
p
r
o
b
lem
s
.
T
h
er
e
ar
e
n
o
s
p
ec
if
ic
a
l
g
o
r
ith
m
s
i
n
o
r
d
er
to
s
o
lv
e
all
k
i
n
d
o
p
ti
m
i
za
tio
n
p
r
o
b
lem
s
[
6
]
.
I
f
t
w
o
a
lg
o
r
ith
m
s
p
r
o
d
u
ce
s
i
m
ilar
r
esu
lts
b
u
t
o
n
e
is
s
i
g
n
i
f
ican
tl
y
s
i
m
p
ler
t
h
an
th
e
o
th
er
,
th
e
n
t
h
e
s
i
m
p
ler
o
f
t
h
e
t
w
o
is
a
s
u
p
er
io
r
alg
o
r
ith
m
.
A
l
g
o
r
ith
m
s
w
it
h
a
l
o
w
d
eg
r
ee
o
f
co
m
p
lex
it
y
h
av
e
a
n
u
m
b
er
o
f
ad
v
a
n
ta
g
es,
i
n
cl
u
d
in
g
b
ein
g
s
i
m
p
le
to
im
p
le
m
e
n
t
in
a
n
in
d
u
s
tr
ial
s
ettin
g
,
b
ein
g
s
i
m
p
le
to
r
e
-
i
m
p
le
m
e
n
t
b
y
r
esear
ch
er
s
,
an
d
b
ein
g
s
i
m
p
ler
to
ex
p
lain
a
n
d
an
al
y
ze
[
14
]
.
T
h
e
alg
o
r
ith
m
ic
s
tr
u
ct
u
r
e
o
f
a
m
eta
-
h
e
u
r
is
tic
alg
o
r
it
h
m
is
d
esire
d
to
b
e
s
im
p
le
en
o
u
g
h
to
allo
w
f
o
r
its
ea
s
y
ad
ap
tatio
n
to
d
if
f
er
en
t
p
r
o
b
le
m
s
.
A
l
s
o
,
it
is
d
esire
d
th
at
th
e
m
e
ta
-
h
e
u
r
is
tic
alg
o
r
ith
m
h
a
s
n
o
alg
o
r
it
h
m
ic
co
n
tr
o
l
p
ar
am
eter
s
o
r
v
er
y
f
e
w
al
g
o
r
ith
m
ic
co
n
tr
o
l
p
ar
a
m
eter
s
ex
clu
d
i
n
g
th
e
g
en
er
al
o
n
es,
i.e
.
s
ize
o
f
p
o
p
u
latio
n
,
to
tal
n
u
m
b
er
o
f
i
ter
atio
n
s
,
p
r
o
b
lem
d
i
m
e
n
s
io
n
o
f
t
h
e
p
o
p
u
latio
n
b
ase
d
o
p
tim
izatio
n
al
g
o
r
ith
m
s
.
I
f
a
m
e
ta
-
h
e
u
r
is
tic
al
g
o
r
ith
m
h
as
alg
o
r
ith
m
ic
co
n
tr
o
l
p
ar
am
eter
s
,
th
e
r
elate
d
alg
o
r
ith
m
m
u
s
t
n
o
t
b
e
to
o
d
ep
en
d
en
t
o
n
th
e
in
itial
v
alu
e
s
o
f
th
e
m
en
t
io
n
ed
alg
o
r
ith
m
ic
co
n
tr
o
l
p
ar
am
eter
s
[
7
]
.
I
n
th
is
p
ap
er
,
s
elec
ted
m
eta
-
h
eu
r
is
tic
s
,
i.e
.
C
u
ck
o
o
Sear
ch
alg
o
r
ith
m
(
C
S
A
)
,
Fire
f
l
y
al
g
o
r
ith
m
(
F
A
)
an
d
E
v
o
lu
tio
n
ar
y
P
r
o
g
r
a
m
m
in
g
(
E
P
)
w
er
e
u
s
ed
to
o
p
ti
m
ize
t
h
e
ANN
tr
ain
i
n
g
f
o
r
p
r
ed
ictin
g
th
e
p
o
w
er
o
u
tp
u
t
o
f
a
GC
P
V
s
y
s
te
m
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
s
tu
d
y
w
as
i
m
p
le
m
en
ted
in
s
ev
er
al
s
ta
g
e
s
.
Firstl
y
,
a
h
y
b
r
id
A
NN
m
o
d
els
w
er
e
d
ev
elo
p
ed
f
o
r
p
r
ed
ictin
g
t
h
e
AC
p
o
w
er
o
u
tp
u
t
o
f
a
G
C
P
V
s
y
s
te
m
.
A
m
u
lti
-
la
y
er
f
ee
d
f
o
r
w
a
r
d
n
eu
r
al
n
e
t
w
o
r
k
w
as
p
r
o
p
o
s
ed
as
th
e
ar
ch
itec
tu
r
e
o
f
t
h
e
ANN.
I
n
ad
d
itio
n
,
th
e
in
p
u
ts
t
o
th
e
A
N
N
w
er
e
So
lar
I
r
r
ad
i
an
ce
(
SI)
,
Am
b
ie
n
t
T
em
p
er
atu
r
e
(
A
T
)
an
d
Mo
d
u
le
T
em
p
er
atu
r
e
(
MT
)
an
d
th
e
o
u
tp
u
t
o
f
th
e
ANN
w
as
t
h
e
AC
p
o
w
er
o
u
tp
u
t
.
T
h
ese
in
p
u
t
a
n
d
o
u
t
d
ata
w
e
r
e
o
b
tain
ed
f
r
o
m
a
GC
P
V
s
y
s
te
m
lo
ca
ted
at
Gr
ee
n
E
n
er
g
y
R
esear
c
h
C
en
tr
e
(
GE
R
C
)
,
U
n
iv
er
s
iti
T
elk
n
o
lo
g
i
M
AR
A
,
Ma
la
y
s
ia.
T
h
e
s
elec
ted
m
e
ta
-
h
e
u
r
is
tic
s
,
i.
e.
C
u
c
k
o
o
Sear
ch
A
l
g
o
r
ith
m
(
C
S
A
)
,
E
v
o
l
u
tio
n
a
r
y
P
r
o
g
r
a
m
m
i
n
g
(
E
P
)
an
d
Fire
f
l
y
A
l
g
o
r
ith
m
(
F
A
)
w
er
e
t
h
e
n
u
s
ed
s
ep
ar
atel
y
to
d
eter
m
in
e
t
h
e
o
p
ti
m
al
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
h
id
d
en
la
y
e
r
,
lear
n
in
g
r
ate
an
d
m
o
m
e
n
t
u
m
r
ate
d
u
r
in
g
th
e
tr
ain
i
n
g
o
f
t
h
e
A
NN
s
u
c
h
th
a
t
th
e
R
MSE
o
f
t
h
e
p
r
ed
ictio
n
w
a
s
m
i
n
i
m
ized
.
Up
o
n
co
m
p
le
tio
n
o
f
th
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
,
test
in
g
p
r
o
ce
s
s
w
as
s
u
b
s
eq
u
en
t
l
y
p
er
f
o
r
m
ed
to
c
o
n
f
ir
m
th
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
ese
h
y
b
r
id
ANN
m
o
d
els
u
s
in
g
d
if
f
er
en
t
m
eta
-
h
e
u
r
is
t
ics
w
a
s
co
m
p
ar
ed
b
ased
o
n
R
M
SE
an
d
co
m
p
u
tatio
n
ti
m
e.
L
ater
,
Mu
tated
C
u
ck
o
o
Sear
ch
Alg
o
r
it
h
m
(
M
C
S
A
)
w
a
s
in
tr
o
d
u
ce
d
w
it
h
th
e
ai
m
o
f
i
m
p
r
o
v
in
g
t
h
e
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
o
f
h
y
b
r
id
A
NN
u
s
i
n
g
C
S
A
.
Ga
u
s
s
ian
m
u
tatio
n
w
as
i
n
tr
o
d
u
ce
d
as
p
ar
t
o
f
th
e
o
p
tim
izatio
n
p
r
o
ce
s
s
d
u
r
n
g
th
e
A
NN
tr
ai
n
in
g
.
T
h
e
i
m
p
le
m
e
n
tatio
n
o
f
C
u
ck
o
o
Sear
ch
(
C
S
A
)
,
Fire
f
l
y
A
l
g
o
r
ith
m
(
F
A
)
an
d
E
v
o
lu
t
i
o
n
ar
y
P
r
o
g
r
a
m
m
i
n
g
(
E
P
)
f
o
r
th
e
p
r
ed
ictio
n
w
er
e
b
r
ief
l
y
e
x
p
lain
ed
i
n
t
h
e
f
o
llo
w
in
g
s
ec
t
io
n
s
.
2
.
1
.
Cuc
k
o
o
Sea
rc
h Alg
o
rit
h
m
(
CSA)
C
u
c
k
o
o
Sear
ch
Alg
o
r
it
h
m
(
C
S
A
)
is
i
n
s
p
ir
ed
b
y
t
h
e
w
a
y
o
f
la
y
i
n
g
e
g
g
s
f
r
o
m
c
u
c
k
o
o
s
p
ec
ies
[
15
]
.
A
cu
ck
o
o
n
o
r
m
all
y
la
y
s
eg
g
s
i
n
th
e
n
e
s
t
o
f
a
b
ir
d
f
r
o
m
o
th
e
r
s
p
ec
ies.
T
h
e
b
asic
p
r
i
n
cip
le
s
o
f
C
S
A
a
n
d
th
e
co
n
ce
p
tu
al
i
m
p
le
m
e
n
tat
io
n
o
f
th
e
A
NN
u
s
i
n
g
C
S
A
ar
e
d
escr
ib
ed
as f
o
llo
w
s
:
(
i)
T
h
e
f
e
m
ale
c
u
c
k
o
o
b
ir
d
la
y
s
eg
g
o
n
e
at
a
ti
m
e,
an
d
p
u
t
i
t
r
an
d
o
m
l
y
in
a
h
o
s
t
n
e
s
t.
T
h
u
s
,
ea
c
h
n
est
in
itial
l
y
co
n
tai
n
s
an
e
g
g
f
r
o
m
th
e
h
o
s
t
b
ir
d
an
d
an
eg
g
f
r
o
m
t
h
e
c
u
ck
o
o
b
ir
d
.
I
n
t
h
is
s
t
u
d
y
,
th
e
cu
c
k
o
o
eg
g
w
as
r
ep
r
esen
ted
b
y
a
s
e
t
o
f
d
ec
is
io
n
v
ar
iab
les
t
h
at
n
ee
d
t
o
b
e
o
p
tim
ized
in
p
r
ed
ictin
g
t
h
e
AC
p
o
w
er
f
r
o
m
th
e
G
C
P
V
s
y
s
te
m
.
T
h
e
d
ec
is
io
n
v
ar
iab
les
u
s
ed
w
er
e
t
h
e
lear
n
in
g
r
ate,
m
o
m
en
tu
m
r
ate
an
d
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
h
id
d
en
la
y
er
o
f
t
h
e
A
NN
m
o
d
el.
(
ii)
T
h
e
n
est
w
i
th
t
h
e
m
o
s
t
q
u
a
l
it
y
eg
g
w
ill
s
u
r
v
iv
e
w
it
h
o
u
t
f
ailu
r
e.
T
h
e
q
u
alit
y
o
f
t
h
e
cu
ck
o
o
eg
g
is
co
m
p
ar
ed
w
it
h
th
e
q
u
al
it
y
o
f
th
e
h
o
s
t
e
g
g
i
n
a
p
ar
ticu
lar
n
e
s
t.
I
n
t
h
is
s
t
u
d
y
,
ea
ch
eg
g
al
s
o
ca
r
r
ied
in
f
o
r
m
atio
n
o
n
q
u
alit
y
,
i.e
.
t
h
e
R
M
SE
o
f
th
e
p
r
ed
ictio
n
u
s
i
n
g
A
NN.
Ho
w
ev
er
,
R
MS
E
ca
n
o
n
l
y
b
e
o
b
tain
ed
af
ter
s
i
m
u
lati
n
g
th
e
A
NN
w
it
h
t
h
e
s
et
o
f
d
ec
is
i
o
n
v
ar
ia
b
le
s
f
o
r
th
at
p
ar
ticu
l
ar
n
est.
I
f
th
e
q
u
alit
y
o
f
t
h
e
cu
c
k
o
o
eg
g
w
a
s
b
etter
th
an
t
h
e
q
u
alit
y
o
f
th
e
h
o
s
t
eg
g
,
t
h
e
cu
c
k
o
o
eg
g
w
as
s
et
to
s
u
r
v
i
v
e
in
th
e
h
o
s
t
n
est,
a
n
d
v
ice
v
er
s
a
.
(
iii)
T
h
e
n
u
m
b
er
o
f
h
o
s
t
n
es
ts
is
f
i
x
ed
w
it
h
t
h
e
p
r
o
b
ab
ilit
y
o
f
cu
ck
o
o
’
s
eg
g
b
ein
g
d
i
s
co
v
er
e
d
b
y
th
e
h
o
s
t
b
ir
d
,
P
a
is
f
r
o
m
0
to
1
[
16
]
.
I
f
t
h
e
c
u
ck
o
o
e
g
g
is
d
is
co
v
er
ed
b
y
t
h
e
h
o
s
t
b
ir
d
,
t
h
e
c
u
ck
o
o
e
g
g
i
s
d
estro
y
ed
o
r
th
r
o
w
n
a
w
a
y
b
y
t
h
e
h
o
s
t
b
i
r
d
.
T
h
is
ev
e
n
t
w
as
e
x
p
ec
ted
to
o
cc
u
r
b
y
ch
a
n
ce
w
it
h
p
r
o
b
ab
ilit
y
P
a
.
I
f
t
h
e
cu
ck
o
o
eg
g
w
as
f
o
u
n
d
to
b
e
d
estro
y
ed
,
n
e
w
n
e
s
t lo
ca
tio
n
s
ar
e
id
en
tif
ied
u
s
i
n
g
+
1
=
(
)
+
⊕
(
)
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Hyb
r
id
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
w
ith
Meta
-
Heu
r
is
tic
s
fo
r
Gri
d
-
C
o
n
n
ec
ted
...
(
N
o
r
fa
r
iz
a
n
i No
r
d
in
)
123
w
h
er
e
x
t
t+
1
is
th
e
n
e
w
e
g
g
at
a
n
e
w
n
est
lo
ca
tio
n
f
o
r
a
cu
ck
o
o
i
an
d
α
d
en
o
ted
as
a
s
tep
s
ize.
T
h
e
p
r
o
d
u
ct
⊕
m
ea
n
s
e
n
tr
y
w
i
s
e
m
u
ltip
licat
i
o
n
s
[
17
]
.
T
h
e
L
´
e
v
y
f
li
g
h
t e
s
s
en
tiall
y
p
r
o
v
id
es
a
r
a
n
d
o
m
w
a
lk
w
h
ile
t
h
e
r
a
n
d
o
m
s
tep
len
g
th
i
s
d
r
a
w
n
f
r
o
m
a
L
´
ev
y
d
i
s
tr
ib
u
tio
n
:
~
=
−
,
(
2
)
w
h
er
e
λ
d
en
o
ted
as th
e
r
an
d
o
m
w
al
k
an
d
th
e
v
al
u
e
w
as se
t b
et
w
ee
n
1
to
2
.
T
h
e
f
lo
w
c
h
ar
t
o
f
C
S
A
w
a
s
il
lu
s
tr
ated
i
n
Fi
g
u
r
e
1
.
First,
cu
ck
o
o
s
ea
r
ch
p
ar
a
m
eter
s
a
n
d
th
e
i
n
itia
l
h
o
s
t
n
est
ar
e
d
ef
i
n
ed
.
Nex
t,
t
h
e
f
it
n
ess
o
f
ea
c
h
c
u
c
k
o
o
is
ev
a
lu
ated
b
ef
o
r
e
it
w
as
r
an
k
ed
.
Af
ter
ev
al
u
atio
n
,
th
e
h
o
s
t
n
es
t
is
m
o
d
i
f
ied
u
s
i
n
g
L
ev
y
f
lig
h
t
eq
u
atio
n
as
s
h
o
w
n
in
E
q
u
a
tio
n
1
a
n
d
t
h
e
f
it
n
es
s
f
o
r
ea
ch
m
o
d
i
f
ied
cu
ck
o
o
is
e
v
al
u
ated
.
Nex
t,
i
f
th
e
co
n
d
itio
n
is
n
o
t
s
ati
s
f
ie
d
,
th
e
cu
c
k
o
o
s
ar
e
m
o
v
ed
to
w
ar
d
s
t
h
e
b
est
n
es
t
en
v
ir
o
n
m
e
n
t
a
n
d
t
h
e
p
r
o
ce
s
s
w
i
ll
b
e
r
ep
ea
ted
f
r
o
m
t
h
e
b
eg
in
n
i
n
g
.
On
th
e
o
t
h
er
h
a
n
d
,
if
t
h
e
co
n
d
itio
n
is
s
atis
f
ied
,
c
h
o
o
s
e
th
e
cu
r
r
e
n
t
b
est
n
est
a
s
t
h
e
b
es
t
c
u
ck
o
o
u
n
til
t
h
e
p
o
p
u
latio
n
ex
c
ee
d
s
th
e
m
a
x
i
m
u
m
g
en
er
atio
n
,
an
d
last
l
y
,
t
h
e
ev
o
l
u
tio
n
p
r
o
ce
s
s
w
il
l b
e
s
to
p
p
ed
.
S
t
a
r
t
D
e
f
i
n
e
C
u
c
k
o
o
S
e
a
r
c
h
A
l
g
o
r
i
t
h
m
p
a
r
a
m
e
t
e
r
s
I
n
i
t
i
a
l
i
z
a
t
i
o
n
o
f
h
o
s
t
n
e
s
t
p
o
p
u
l
a
t
i
o
n
E
v
a
l
u
a
t
e
t
h
e
f
i
t
n
e
s
s
M
o
d
i
f
y
t
h
e
h
o
s
t
n
e
s
t
p
o
p
u
l
a
t
i
o
n
u
s
i
n
g
L
e
v
y
f
l
i
g
h
t
E
v
a
l
u
a
t
e
f
i
t
n
e
s
s
o
f
n
e
w
p
o
p
u
l
a
t
i
o
n
I
s
t
h
e
c
o
n
d
i
t
i
o
n
s
a
t
i
s
f
i
e
d
?
C
h
o
o
s
e
c
u
r
r
e
n
t
b
e
s
t
M
a
x
i
m
u
m
g
e
n
e
r
a
t
i
o
n
a
c
h
i
e
v
e
d
?
S
t
o
p
M
o
v
e
a
l
l
c
u
c
k
o
o
s
t
o
w
a
r
d
s
b
e
s
t
n
e
s
t
N
o
Y
e
s
N
o
Y
e
s
Fig
u
r
e
1
.
Flo
w
c
h
ar
t o
f
C
u
c
k
o
o
Sear
ch
A
l
g
o
r
ith
m
2
.
2
.
E
v
o
lutio
na
ry
P
ro
g
r
a
m
m
i
ng
(
E
P
)
E
P
is
o
n
e
o
f
m
eta
-
h
eu
r
i
s
tic
t
ec
h
n
iq
u
e
w
h
ic
h
i
s
u
s
ed
to
p
er
f
o
r
m
r
a
n
d
o
m
s
ea
r
ch
in
o
p
tim
izi
n
g
a
n
o
b
j
ec
tiv
e
f
u
n
ctio
n
.
I
t
h
ad
b
ee
n
u
s
ed
i
n
m
a
n
y
n
u
m
er
ical
a
n
d
co
m
b
i
n
ato
r
ial
o
p
ti
m
izatio
n
p
r
o
b
lem
s
in
r
ec
en
t
y
ea
r
s
.
I
t
is
a
co
m
b
in
at
io
n
o
f
s
ev
er
al
m
ai
n
p
r
o
ce
s
s
es
n
a
m
e
l
y
in
itializat
io
n
o
f
p
ar
en
t
s
,
ev
al
u
atio
n
o
f
th
e
f
it
n
es
s
v
alu
e,
m
u
ta
tio
n
p
r
o
ce
s
s
to
p
r
o
d
u
ce
an
o
f
f
s
p
r
i
n
g
f
r
o
m
t
h
eir
p
ar
en
ts
,
ev
alu
atio
n
o
f
f
it
n
es
s
f
o
r
th
e
o
f
f
s
p
r
in
g
,
a
co
m
b
i
n
atio
n
p
r
o
ce
s
s
,
s
elec
tio
n
an
d
last
l
y
t
h
e
co
n
v
er
g
e
n
ce
test
.
I
n
b
r
ief
,
th
er
e
ar
e
t
w
o
m
aj
o
r
s
tep
s
to
b
e
s
u
m
m
ar
ized
in
o
p
ti
m
iza
tio
n
b
y
E
P
[
18
]
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
11
,
No
.
1
,
J
u
ly
201
8
:
1
2
1
–
1
2
8
124
(
i)
Mu
tate
p
ar
en
ts
i
n
th
e
c
u
r
r
en
t
p
o
p
u
latio
n
.
T
h
e
m
u
tat
io
n
o
f
a
p
ar
en
t
w
a
s
co
n
d
u
cted
u
s
i
n
g
Ga
u
s
s
ian
m
u
tatio
n
a
s
b
elo
w
:
)
1
,
0
(
.
'
1
j
j
j
N
q
q
(
3
)
w
h
er
e
q’
1j
w
er
e
t
h
e
o
f
f
s
p
r
in
g
s
g
e
n
er
ated
f
r
o
m
ea
c
h
p
ar
en
t
b
y
Ga
u
s
s
ia
n
m
u
tatio
n
.
N
j
(
0
,
1
)
r
ep
r
esen
ts
a
n
o
r
m
a
l
Gau
s
s
ia
n
r
an
d
o
m
v
ar
iab
le
w
ith
m
ea
n
0
an
d
s
tan
d
ar
d
d
ev
iatio
n
1
.
I
n
t
h
is
s
t
u
d
y
,
ea
c
h
p
ar
en
t
co
n
tai
n
s
in
f
o
r
m
atio
n
o
f
t
h
e
d
ec
is
io
n
v
a
r
iab
les th
at
n
ee
d
to
b
e
o
p
ti
m
iz
ed
,
i.e
.
lear
n
in
g
r
ate,
m
o
m
e
n
t
u
m
r
ate
a
n
d
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
h
id
d
en
la
y
er
.
(
ii)
Select
t
h
e
n
ex
t
g
e
n
er
atio
n
f
r
o
m
t
h
e
p
ar
en
t
s
a
n
d
m
u
tated
p
ar
en
ts
(
o
f
f
s
p
r
in
g
)
.
A
t
t
h
i
s
s
ta
g
e,
ea
ch
p
ar
en
t
i
s
m
u
tated
to
p
r
o
d
u
ce
an
o
f
f
s
p
r
in
g
.
T
h
en
,
th
e
n
e
x
t
g
en
er
ati
o
n
o
f
ca
n
d
id
ates
f
o
r
p
o
ten
ti
al
s
o
lu
tio
n
i
s
s
elec
ted
b
y
f
ir
s
t
r
an
k
i
n
g
t
h
e
p
o
o
l
o
f
p
ar
en
ts
an
d
o
f
f
s
p
r
in
g
ac
co
r
d
in
g
to
t
h
eir
f
it
n
es
s
v
alu
e
s
.
Su
b
s
eq
u
e
n
tl
y
,
a
p
o
p
u
latio
n
o
f
ca
n
d
id
ates
i
s
tr
a
n
s
cr
ib
ed
to
t
h
e
n
ex
t
g
e
n
er
atio
n
f
o
r
th
e
n
e
x
t
ev
o
l
u
tio
n
.
I
n
th
is
s
t
u
d
y
,
th
e
f
it
n
es
s
v
al
u
e
w
a
s
R
MSE
.
T
h
e
f
lo
w
ch
ar
t
o
f
E
P
w
a
s
il
lu
s
tr
ated
i
n
Fi
g
u
r
e
2
.
First,
in
itial
ize
t
h
e
p
ar
en
t
p
o
p
u
lati
o
n
o
f
th
e
g
en
er
atio
n
.
Seco
n
d
,
th
e
f
it
n
e
s
s
o
f
ea
ch
p
ar
en
t
g
en
er
at
ed
is
ev
alu
a
ted
u
s
i
n
g
t
h
e
s
elec
ted
eq
u
atio
n
o
r
f
u
n
ctio
n
.
Nex
t,
p
er
f
o
r
m
th
e
m
u
tatio
n
p
r
o
ce
s
s
b
y
u
s
in
g
Ga
u
s
s
ia
n
d
is
tr
ib
u
tio
n
o
p
er
ato
r
as
s
h
o
w
n
in
E
q
u
at
io
n
3
to
p
r
o
d
u
ce
th
e
n
e
w
p
o
p
u
latio
n
.
T
h
e
n
e
w
p
o
p
u
latio
n
i
s
k
n
o
w
n
as
t
h
e
o
f
f
s
p
r
in
g
.
Af
ter
t
h
at,
co
m
b
i
n
e
a
ll
p
ar
en
t
s
an
d
o
f
f
s
p
r
i
n
g
s
i
n
o
r
d
er
to
f
in
d
th
e
b
es
t
r
es
u
lt
b
y
u
n
d
er
g
o
in
g
t
h
e
s
e
lectio
n
p
r
o
ce
s
s
.
T
h
e
p
r
o
ce
s
s
is
s
to
p
p
ed
w
h
e
n
t
h
e
co
n
v
er
g
en
ce
is
ac
h
i
ev
ed
.
I
f
n
o
t,
t
h
e
p
r
o
ce
s
s
w
ill
b
e
r
ep
ea
ted
b
y
p
er
f
o
r
m
i
n
g
t
h
e
m
u
tatio
n
p
r
o
ce
s
s
ag
ain
.
S
t
a
r
t
I
n
i
t
i
a
l
i
z
a
t
i
o
n
o
f
p
a
r
e
n
t
s
F
i
t
n
e
s
s
e
v
a
l
u
a
t
i
o
n
o
f
p
a
r
e
n
t
s
M
u
t
a
t
i
o
n
o
f
p
a
r
e
n
t
s
t
o
p
r
o
d
u
c
e
o
f
f
s
p
r
i
n
g
F
i
t
n
e
s
s
e
v
a
l
u
a
t
i
o
n
o
f
o
f
f
s
p
r
i
n
g
C
o
m
b
i
n
a
t
i
o
n
a
n
d
s
e
l
e
c
t
i
o
n
C
o
n
v
e
r
g
e
n
c
e
a
c
h
i
e
v
e
d
?
S
t
o
p
N
o
Y
e
s
Fig
u
r
e
2
.
Flo
w
c
h
ar
t o
f
E
v
o
l
u
ti
o
n
ar
y
P
r
o
g
r
a
m
m
in
g
2
.
3
.
F
iref
ly
Alg
o
rit
h
m
(
F
A)
An
o
th
er
t
y
p
e
o
f
m
eta
-
h
e
u
r
is
ti
c
alg
o
r
ith
m
s
elec
ted
in
t
h
is
s
t
u
d
y
w
as
F
ir
ef
l
y
A
l
g
o
r
ith
m
(
F
A
)
.
F
A
is
a
m
eta
-
h
e
u
r
is
tic
o
p
ti
m
izatio
n
al
g
o
r
ith
m
w
h
ic
h
w
a
s
i
n
tr
o
d
u
ce
d
at
C
a
m
b
r
id
g
e
U
n
i
v
er
s
it
y
i
n
2
0
0
8
b
y
Xi
n
-
S
h
e
Yan
g
[
19
]
.
T
h
e
alg
o
r
ith
m
w
as
in
s
p
ir
ed
b
y
t
h
e
f
la
s
h
in
g
ch
ar
a
cter
is
tics
o
f
f
ir
ef
lie
s
at
n
ig
h
t.
T
h
e
alg
o
r
ith
m
w
a
s
f
o
r
m
u
lated
b
ased
o
n
th
r
ee
id
ea
lized
r
u
les
[
15
]
:
(
i)
A
ll
f
ir
e
f
lies
ar
e
u
n
is
e
x
.
T
h
u
s
,
o
n
e
f
ir
ef
l
y
w
i
ll
b
e
attr
ac
ted
to
th
e
o
th
er
f
ir
e
f
lies
r
e
g
ar
d
less
o
f
th
eir
s
e
x
.
I
n
th
is
s
t
u
d
y
,
b
esid
es
b
ei
n
g
u
n
i
s
e
x
,
e
v
er
y
f
ir
e
f
l
y
g
en
er
ated
co
n
t
ain
s
a
s
e
t
o
f
d
ec
is
io
n
v
ar
iab
les
t
h
at
n
ee
d
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Hyb
r
id
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
w
ith
Meta
-
Heu
r
is
tic
s
fo
r
Gri
d
-
C
o
n
n
ec
ted
...
(
N
o
r
fa
r
iz
a
n
i No
r
d
in
)
125
b
e
o
p
tim
ized
in
p
r
ed
ictin
g
t
h
e
AC
p
o
w
er
f
r
o
m
t
h
e
G
C
P
V
s
y
s
te
m
.
T
h
e
d
ec
is
io
n
v
ar
iab
les
u
s
ed
w
er
e
th
e
lear
n
in
g
r
ate,
m
o
m
en
tu
m
r
ate
an
d
n
u
m
b
er
o
f
n
eu
r
o
n
s
in
h
id
d
en
la
y
er
o
f
t
h
e
A
NN
m
o
d
el.
(
ii)
A
ttra
ct
iv
e
n
es
s
i
s
p
r
o
p
o
r
tio
n
al
to
th
e
b
r
ig
h
tn
e
s
s
o
f
f
ir
e
f
lies
.
Ho
w
e
v
er
,
t
h
e
b
r
ig
h
t
n
es
s
d
ec
r
ea
s
es
as
t
h
e
d
is
tan
ce
i
n
cr
ea
s
e
s
.
Fo
r
a
n
y
t
w
o
f
las
h
i
n
g
f
ir
ef
l
ies,
f
ir
e
f
l
y
w
it
h
less
b
r
ig
h
tn
e
s
s
w
ill
f
l
y
to
w
ar
d
s
th
e
b
r
ig
h
ter
o
n
e
an
d
if
th
er
e
is
n
o
b
r
ig
h
ter
o
n
e
th
a
n
a
p
ar
ti
cu
lar
f
ir
ef
l
y
,
t
h
e
f
ir
ef
l
y
w
ill
f
l
y
r
a
n
d
o
m
l
y
.
T
h
er
ef
o
r
e,
th
e
lo
w
er
t
h
e
d
is
ta
n
ce
b
et
w
ee
n
t
w
o
f
ir
e
f
lie
s
,
b
etter
ag
r
ee
m
e
n
t
o
n
t
h
e
s
o
l
u
tio
n
i
s
o
b
tain
ed
.
On
th
e
o
t
h
er
h
an
d
,
r
a
n
d
o
m
f
li
g
h
t
b
y
a
f
ir
ef
l
y
w
as
i
m
p
le
m
e
n
te
d
b
y
r
an
d
o
m
l
y
ad
j
u
s
ti
n
g
t
h
e
v
alu
e
o
f
ea
ch
d
ec
is
io
n
v
ar
iab
les.
(
iii)
T
h
e
b
r
ig
h
tn
es
s
o
f
f
ir
e
f
l
y
r
e
p
r
esen
t
s
th
e
q
u
alit
y
o
f
s
o
l
u
tio
n
a
n
d
it
is
ass
o
ciate
d
to
th
e
f
it
n
es
s
v
al
u
e
o
f
th
e
o
b
j
ec
tiv
e
f
u
n
c
tio
n
.
I
n
t
h
is
s
t
u
d
y
,
t
h
e
b
r
ig
h
tn
e
s
s
o
f
th
e
f
ir
e
f
l
y
w
as
r
ep
r
esen
ted
b
y
t
h
e
f
it
n
ess
v
a
lu
e,
i.e
.
th
e
R
MSE
.
T
h
er
ef
o
r
e,
t
h
e
f
ir
ef
l
y
w
it
h
less
b
r
ig
h
tn
e
s
s
h
ad
h
i
g
h
er
R
M
SE
w
h
ile
t
h
e
f
ir
e
f
l
y
w
it
h
m
o
r
e
b
r
ig
h
t
n
es
s
h
ad
lo
w
er
R
MSE
.
T
h
e
f
lo
w
c
h
ar
t
o
f
F
A
w
a
s
illu
s
tr
ated
in
Fig
u
r
e
3
.
First,
g
en
er
ate
th
e
in
itial
p
o
p
u
latio
n
o
f
th
e
f
ir
e
f
l
y
an
d
ev
al
u
ate
t
h
e
f
it
n
ess
o
f
e
ac
h
f
ir
ef
lie
s
g
en
er
ated
b
y
u
s
i
n
g
th
e
s
elec
ted
eq
u
atio
n
o
r
f
u
n
ct
i
o
n
.
Af
ter
t
h
at,
u
p
d
ate
th
e
li
g
h
t
in
ten
s
it
y
o
f
t
h
e
f
ir
ef
l
y
b
y
u
s
in
g
li
g
h
t
in
ten
s
it
y
eq
u
atio
n
.
Nex
t,
t
h
e
f
it
n
ess
o
f
all
t
h
e
f
ir
ef
lie
s
is
ev
alu
a
ted
an
d
r
an
k
ed
ac
o
o
r
d
in
g
to
th
e
co
r
r
esp
o
n
d
i
n
g
f
it
n
es
s
v
alu
e.
I
f
t
h
e
m
ax
i
m
u
m
iter
atio
n
w
as r
ea
c
h
ed
,
th
e
p
r
o
ce
s
s
w
ill
p
r
o
ce
ed
b
y
f
i
n
d
in
g
t
h
e
g
lo
b
al
b
est
th
r
o
u
g
h
o
u
t
al
l
t
h
e
g
en
er
at
io
n
s
o
f
th
e
f
ir
e
f
l
y
.
T
h
e
n
e
w
p
o
p
u
latio
n
o
f
f
ir
e
f
l
y
f
r
o
m
th
e
b
est g
en
er
atio
n
w
ill b
e
u
s
ed
to
r
ep
r
esen
t th
e
b
est p
o
p
u
latio
n
.
S
t
a
r
t
G
e
n
e
r
a
t
e
i
n
i
t
i
a
l
p
o
p
u
l
a
t
i
o
n
o
f
f
i
r
e
f
l
y
E
v
a
l
u
a
t
e
f
i
t
n
e
s
s
o
f
a
l
l
f
i
r
e
f
l
i
e
s
U
p
d
a
t
e
l
i
g
h
t
i
n
t
e
n
s
i
t
y
(
f
i
t
n
e
s
s
v
a
l
u
e
)
o
f
f
i
r
e
f
l
y
R
a
n
k
f
i
r
e
f
l
i
e
s
a
c
c
o
r
d
i
n
g
t
o
i
t
s
f
i
t
n
e
s
s
a
n
d
u
p
d
a
t
e
p
o
s
i
t
i
o
n
M
a
x
i
m
u
m
i
t
e
r
a
t
i
o
n
a
c
h
i
e
v
e
d
?
F
i
n
d
g
l
o
b
a
l
b
e
s
t
t
h
r
o
u
g
h
o
u
t
a
l
l
g
e
n
e
r
a
t
i
o
n
s
S
t
o
p
N
o
Y
e
s
Fig
u
r
e
3
.
Flo
w
c
h
ar
t o
f
Fire
f
l
y
A
l
g
o
r
ith
m
2
.
4
.
M
ut
a
t
ed
Cuck
o
o
Sea
rc
h Alg
o
rit
h
m
(
M
CSA)
I
n
th
i
s
s
tu
d
y
,
th
e
p
er
f
o
r
m
an
ce
o
f
C
S
A
w
as i
m
p
r
o
v
ed
b
y
m
o
d
if
y
in
g
t
h
e
o
p
ti
m
izatio
n
p
r
o
ce
s
s
in
C
S
A.
T
h
e
co
n
v
en
t
io
n
al
C
S
A
co
m
m
o
n
l
y
e
m
p
lo
y
s
L
ev
y
f
li
g
h
t
to
u
p
d
ate
th
e
lo
ca
tio
n
o
f
t
h
e
n
est
d
u
r
in
g
th
e
e
v
o
l
u
tio
n
of
cu
c
k
o
o
.
Ho
w
e
v
er
,
th
e
r
an
d
o
m
w
al
k
o
f
c
u
c
k
o
o
u
s
i
n
g
L
e
v
y
f
li
g
h
t
is
v
er
y
r
an
d
o
m
i
n
n
at
u
r
e
an
d
th
u
s
ca
u
s
in
g
th
e
c
u
ck
o
o
to
d
iv
er
t
f
ar
a
w
a
y
f
r
o
m
t
h
e
p
o
s
s
ib
le
o
p
ti
m
al
s
o
lu
tio
n
s
d
u
r
in
g
t
h
e
s
ea
r
ch
f
o
r
o
p
ti
m
al
s
o
lu
t
io
n
.
T
h
i
s
r
an
d
o
m
w
al
k
ca
n
b
e
i
m
p
r
o
v
ed
b
y
i
n
tr
o
d
u
ci
n
g
a
c
h
ar
ac
ter
is
tic
o
f
in
h
er
ita
n
ce
s
u
c
h
t
h
a
t
th
e
m
o
v
e
m
e
n
t
o
f
cu
ck
o
o
is
s
till
d
ep
en
d
en
t o
n
t
h
e
g
r
o
u
p
p
er
f
o
r
m
an
ce
o
f
c
u
c
k
o
o
s
in
th
e
p
o
p
u
latio
n
.
As
a
r
e
s
u
l
t,
m
u
tatio
n
w
as
in
tr
o
d
u
ce
d
s
u
c
h
t
h
at
t
h
e
c
u
ck
o
o
w
a
s
m
u
tated
a
f
ter
a
r
a
n
d
o
m
w
al
k
u
s
in
g
L
e
v
y
f
l
ig
h
t.
I
n
M
C
S
A
,
L
e
v
y
f
li
g
h
t
w
il
l
b
e
co
m
b
i
n
ed
w
it
h
t
h
e
Ga
u
s
s
ia
n
d
is
tr
ib
u
tio
n
o
p
er
ato
r
to
p
er
f
o
r
m
t
h
e
m
u
tatio
n
p
r
o
ce
s
s
.
Me
an
w
h
i
le,
th
e
r
est
o
f
t
h
e
p
r
o
ce
s
s
es
ar
e
s
i
m
ilar
w
it
h
t
h
e
p
r
o
ce
s
s
o
f
C
S
A.
Hen
ce
,
th
e
g
r
o
u
p
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
11
,
No
.
1
,
J
u
ly
201
8
:
1
2
1
–
1
2
8
126
p
er
f
o
r
m
a
n
ce
o
f
cu
c
k
o
o
w
as
p
r
eser
v
ed
d
u
r
in
g
t
h
e
e
v
o
lu
t
io
n
o
f
cu
c
k
o
o
.
E
v
e
n
tu
a
ll
y
,
a
b
ett
er
o
p
tim
a
l
s
o
l
u
tio
n
ca
n
b
e
f
o
u
n
d
.
I
n
s
h
o
r
t,
t
h
e
o
v
e
r
all
p
r
o
ce
s
s
f
o
r
MCS
A
is
il
lu
s
t
r
ated
as in
th
e
f
o
llo
w
in
g
f
lo
w
c
h
ar
t.
S
t
a
r
t
D
e
f
i
n
e
C
S
-
A
N
N
p
a
r
a
m
e
t
e
r
s
G
e
n
e
r
a
t
e
i
n
i
t
i
a
l
h
o
s
t
n
e
s
t
p
o
p
u
l
a
t
i
o
n
E
v
a
l
u
a
t
e
t
h
e
f
i
t
n
e
s
s
M
o
d
i
f
y
t
h
e
h
o
s
t
n
e
s
t
p
o
p
u
l
a
t
i
o
n
u
s
i
n
g
L
e
v
y
f
l
i
g
h
t
M
u
t
a
t
i
o
n
p
r
o
c
e
s
s
u
s
i
n
g
C
a
u
c
h
y
-
G
a
u
s
s
i
a
n
d
i
s
t
r
i
b
u
t
i
o
n
o
p
e
r
a
t
o
r
E
v
a
l
u
a
t
e
f
i
t
n
e
s
s
o
f
n
e
w
p
o
p
u
l
a
t
i
o
n
I
s
t
h
e
c
o
n
d
i
t
i
o
n
s
a
t
i
s
f
i
e
d
?
C
h
o
o
s
e
c
u
r
r
e
n
t
b
e
s
t
t
<
m
a
x
_
g
e
n
E
n
d
M
o
v
e
a
l
l
c
u
c
k
o
o
s
t
o
w
a
r
d
s
b
e
s
t
e
n
v
i
r
o
n
m
e
n
t
N
o
N
o
Y
e
s
Y
e
s
Fig
u
r
e
4
.
Flo
w
c
h
ar
t o
f
M
u
tate
d
C
u
ck
o
o
Sear
ch
al
g
o
r
ith
m
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
S
T
h
is
s
ec
tio
n
p
r
ese
n
ts
th
e
r
e
s
u
l
ts
an
d
d
is
c
u
s
s
io
n
o
f
t
h
e
s
t
u
d
y
.
T
h
e
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
o
f
h
y
b
r
id
A
N
N
m
o
d
el
s
,
i.e
.
C
S
A
-
ANN,
E
P
-
A
NN
a
n
d
F
A
-
A
NN
is
s
h
o
w
n
i
n
Sectio
n
3
.
1
.
Af
ter
th
at,
th
e
p
er
f
o
r
m
a
n
ce
o
f
MCS
A
-
A
N
N
is
s
h
o
w
n
i
n
Sect
io
n
3
.
2
.
T
h
e
r
esu
lts
ac
h
iev
ed
b
y
M
C
S
A
-
A
NN
w
a
s
ev
alu
a
te
d
an
d
b
en
ch
m
ar
k
ed
w
it
h
C
S
A
-
A
NN.
3
.
1
.
P
er
f
o
r
m
a
nce
Co
m
pa
riso
n o
f
H
y
brid Ar
t
if
icia
l N
eura
l N
et
w
o
rk
M
o
dels
Af
ter
all
t
h
e
A
NN
tr
ai
n
i
n
g
p
a
r
a
m
eter
s
h
ad
b
ee
n
d
eter
m
in
ed
f
o
r
th
e
m
o
d
els,
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
h
y
b
r
id
A
NN
m
o
d
els
w
a
s
co
m
p
ar
ed
in
ter
m
s
o
f
p
r
ed
ictio
n
ac
cu
r
ac
y
b
ased
o
n
R
M
SE
an
d
R
2
as
s
h
o
w
n
i
n
T
ab
le
1
.
C
S
A
-
ANN
w
a
s
d
is
co
v
er
ed
to
b
e
th
e
b
est
m
o
d
el
as
it
p
r
o
d
u
ce
s
th
e
lo
w
e
s
t
R
MSE
d
u
r
i
n
g
b
o
t
h
tr
ain
i
n
g
an
d
test
i
n
g
.
T
h
e
R
MSE
d
u
r
in
g
tr
ain
i
n
g
p
r
o
d
u
ce
d
b
y
C
S
A
-
ANN
is
ap
p
r
o
x
i
m
atel
y
4
3
.
6
0
%
lo
w
er
t
h
a
n
FA
-
ANN
a
n
d
3
8
.
2
6
%
lo
w
er
t
h
an
E
P
-
A
NN.
Me
a
n
w
h
il
e,
th
e
R
MSE
d
u
r
in
g
test
i
n
g
p
r
o
d
u
ce
d
b
y
C
S
A
-
A
NN
i
s
ap
p
r
o
x
im
a
tel
y
4
7
.
5
5
%
lo
w
er
th
a
n
F
A
-
A
NN
a
n
d
4
2
.
8
6
%
lo
w
er
th
a
n
E
P
-
ANN.
Mo
r
eo
v
er
,
C
S
A
-
ANN
al
s
o
y
ield
s
t
h
e
h
i
g
h
e
s
t
R
2
d
u
r
i
n
g
b
o
th
tr
ain
in
g
a
n
d
test
i
n
g
w
h
en
co
m
p
ar
ed
w
it
h
F
A
-
ANN
a
n
d
E
P
-
A
N
N.
B
esid
e
s
th
at,
C
S
A
-
A
NN
w
a
s
also
ap
p
r
o
x
i
m
ate
l
y
5
.
3
an
d
5
.
6
tim
e
s
f
a
s
ter
th
a
n
E
P
-
A
NN
a
n
d
F
A
-
A
NN
r
esp
ec
tiv
el
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Hyb
r
id
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
w
ith
Meta
-
Heu
r
is
tic
s
fo
r
Gri
d
-
C
o
n
n
ec
ted
...
(
N
o
r
fa
r
iz
a
n
i No
r
d
in
)
127
T
ab
le
1
.
P
er
f
o
r
m
a
n
ce
co
m
p
ar
i
s
o
n
o
f
H
y
b
r
id
A
NN
m
o
d
els
P
a
r
a
me
t
e
r
s
C
S
A
-
A
N
N
EP
-
A
N
N
FA
-
ANN
O
p
t
i
mal
n
o
.
o
f
n
e
u
r
o
n
s i
n
h
i
d
d
e
n
l
a
y
e
r
5
20
9
O
p
t
i
mal
p
o
p
u
l
a
t
i
o
n
s
i
z
e
20
60
60
O
p
t
i
mal
l
e
a
r
n
i
n
g
r
a
t
e
0
.
2
3
9
3
0
.
6
9
7
3
0
.
5
6
5
5
O
p
t
i
mal
mo
me
n
t
u
m r
a
t
e
0
.
7
2
4
4
0
.
7
1
6
6
0
.
6
9
0
4
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
i
n
h
i
d
d
e
n
l
a
y
e
r
L
O
G
S
I
G
L
O
G
S
I
G
L
O
G
S
I
G
L
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
T
R
A
I
N
L
M
T
R
A
I
N
L
M
T
R
A
I
N
L
M
R
M
S
E
t
r
a
i
n
i
n
g
,
i
n
W
a
t
t
1
2
.
3
4
6
3
1
9
.
9
9
8
8
2
1
.
8
9
0
7
R
2
t
r
a
i
n
i
n
g
0
.
9
9
8
8
0
.
9
7
7
0
0
.
9
7
5
5
R
M
S
E
t
e
st
i
n
g
,
i
n
W
a
t
t
1
4
.
2
7
1
8
2
4
.
9
7
7
6
2
7
.
2
1
1
3
R
2
t
e
st
i
n
g
0
.
9
8
9
9
0
.
9
7
3
4
0
.
9
7
5
3
C
o
mp
u
t
a
t
i
o
n
t
i
me
,
i
n
mi
n
u
t
e
s
2
1
.
2
5
6
8
1
1
2
.
7
0
9
4
1
1
9
.
4
7
3
6
3
.
2
.
P
er
f
o
r
m
a
nce
Co
m
pa
riso
n o
f
M
uta
t
ed
Cuck
o
o
Sea
rc
h Al
g
o
rit
h
m
A
lt
h
o
u
g
h
C
S
A
w
a
s
f
o
u
n
d
to
b
e
th
e
b
est
m
e
ta
-
h
e
u
r
is
tic
s
f
o
r
th
e
h
y
b
r
id
A
NN
m
o
d
el,
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
co
n
v
e
n
tio
n
al
C
S
A
d
ep
e
n
d
s
o
n
r
an
d
o
m
w
al
k
u
s
in
g
L
e
v
y
f
lig
h
t
w
h
ich
is
v
er
y
r
a
n
d
o
m
i
n
n
at
u
r
e.
T
h
u
s
,
it
m
a
y
ca
u
s
e
t
h
e
cu
c
k
o
o
to
d
iv
er
t
f
ar
a
w
a
y
f
r
o
m
t
h
e
p
o
s
s
ib
le
o
p
tim
al
s
o
l
u
tio
n
s
d
u
r
in
g
t
h
e
s
ea
r
c
h
f
o
r
o
p
ti
m
al
s
o
lu
tio
n
.
T
h
er
ef
o
r
e,
a
M
u
tat
ed
C
u
c
k
o
o
Sear
ch
A
l
g
o
r
ith
m
-
Ar
ti
f
icial
Neu
r
al
Net
w
o
r
k
(
MCS
A
-
ANN)
w
a
s
d
ev
elo
p
ed
to
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
co
n
v
en
t
io
n
al
C
S
A
.
T
h
e
MC
S
A
-
ANN
w
as
l
ater
u
s
ed
to
i
m
p
r
o
v
e
th
e
h
y
b
r
id
A
NN
f
o
r
th
e
p
r
ed
ictio
n
tas
k
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
M
C
S
A
-
A
NN
an
d
C
S
A
-
A
N
N
w
a
s
co
m
p
ar
ed
i
n
T
ab
le
2
.
MCS
A
-
A
NN
h
ad
o
u
tp
er
f
o
r
m
ed
C
S
A
-
A
NN
b
y
p
r
o
d
u
cin
g
lo
w
er
R
MSE
an
d
h
i
g
h
er
R
2
d
u
r
in
g
b
o
th
tr
ain
i
n
g
an
d
te
s
ti
n
g
.
T
h
e
MC
S
A
-
ANN
w
a
s
al
s
o
s
l
ig
h
tl
y
f
a
s
ter
t
h
an
C
S
A
-
ANN.
I
n
s
h
o
r
t,
th
e
in
tr
o
d
u
ctio
n
o
f
MCS
A
-
A
N
N
f
o
r
t
h
e
p
r
ed
ictio
n
w
as
j
u
s
ti
f
ied
s
h
o
w
n
b
y
t
h
e
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
o
b
tai
n
e
d
d
u
r
in
g
th
e
test
i
n
g
an
d
tr
ain
in
g
p
r
o
ce
s
s
.
T
h
e
M
C
S
A
-
A
NN
h
ad
ex
h
ib
ited
th
e
o
p
tim
a
l
n
u
m
b
er
o
f
n
e
u
r
o
n
s
i
n
h
id
d
en
la
y
er
o
f
4
,
w
h
ile
t
h
e
o
p
ti
m
al
v
al
u
e
s
f
o
r
lear
n
in
g
r
ate
an
d
m
o
m
e
n
t
u
m
r
at
e
ar
e
0
.
6
7
4
0
an
d
0
.
7
9
6
5
r
esp
ec
tiv
el
y
.
T
h
is
alg
o
r
ith
m
h
ad
also
y
ield
ed
lo
w
e
s
t
R
MSE
o
f
1
1
.
0
5
3
4
W
d
u
r
in
g
tr
ai
n
in
g
an
d
1
3
.
1
3
4
8
W
d
u
r
in
g
test
i
n
g
.
Oth
er
th
an
t
h
at,
it
h
ad
p
r
o
d
u
ce
d
m
a
x
i
m
u
m
R
2
w
it
h
0
.
9
9
9
4
an
d
0
.
9
9
1
3
f
o
r
b
o
th
tr
ain
in
g
an
d
tes
tin
g
,
w
i
th
t
h
e
least
co
m
p
u
tatio
n
al
ti
m
e
o
f
1
7
.
9
6
1
6
m
i
n
u
tes
w
h
e
n
co
m
p
ar
ed
to
o
th
er
h
y
b
r
id
A
NNs.
T
ab
le
2
.
P
er
f
o
r
m
a
n
ce
co
m
p
ar
i
s
o
n
o
f
M
u
tated
C
u
ck
o
o
Sear
c
h
A
l
g
o
r
ith
m
P
a
r
a
me
t
e
r
s
CS
-
A
N
N
M
C
S
-
A
N
N
O
p
t
i
mal
n
o
.
o
f
n
e
u
r
o
n
s i
n
h
i
d
d
e
n
l
a
y
e
r
5
4
O
p
t
i
mal
l
e
a
r
n
i
n
g
r
a
t
e
0
.
2
3
9
3
0
.
6
7
4
0
O
p
t
i
mal
mo
me
n
t
u
m r
a
t
e
0
.
7
2
4
4
0
.
7
9
6
5
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
i
n
h
i
d
d
e
n
l
a
y
e
r
L
O
G
S
I
G
L
O
G
S
I
G
L
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
T
R
A
I
N
L
M
T
R
A
I
N
L
M
R
M
S
E
t
r
a
i
n
i
n
g
,
i
n
W
a
t
t
1
2
.
3
4
6
3
1
1
.
0
5
3
4
R
2
t
r
a
i
n
i
n
g
0
.
9
9
8
8
0
.
9
9
9
4
R
M
S
E
t
e
st
i
n
g
,
i
n
W
a
t
t
1
4
.
2
7
1
8
1
3
.
1
3
4
8
R
2
t
e
st
i
n
g
0
.
9
8
9
9
0
.
9
9
1
3
C
o
mp
u
t
a
t
i
o
n
t
i
me
,
i
n
mi
n
u
t
e
s
2
1
.
2
5
6
8
1
7
.
9
6
1
6
4.
CO
NCLU
SI
O
N
T
h
e
p
er
f
o
r
m
an
ce
o
f
s
elec
ted
h
y
b
r
id
ANN
m
o
d
els
w
a
s
co
m
p
ar
ed
.
T
h
e
r
esu
lts
s
h
o
w
ed
th
at
C
S
A
-
A
N
N
h
ad
o
u
tp
er
f
o
r
m
ed
E
P
-
ANN
an
d
F
A
-
ANN
b
y
p
r
o
d
u
cin
g
th
e
lo
w
est
R
MSE
an
d
co
m
p
u
tatio
n
ti
m
e.
A
p
ar
t
f
r
o
m
t
h
at,
th
e
in
tr
o
d
u
ctio
n
o
f
MC
S
A
-
A
NN
s
h
o
w
ed
t
h
at
MCS
A
-
A
N
N
h
ad
o
u
tp
er
f
o
r
m
ed
C
S
A
-
ANN
b
y
ex
h
ib
it
in
g
t
h
e
lo
w
e
s
t
R
M
SE
d
u
r
in
g
tr
ai
n
i
n
g
a
n
d
tes
tin
g
a
s
w
ell
as
t
h
e
h
i
g
h
e
s
t
R
2
d
u
r
i
n
g
tr
ain
i
n
g
a
n
d
tes
tin
g
.
I
n
ter
m
s
o
f
co
m
p
u
tatio
n
ti
m
e,
MCS
A
-
A
N
N
n
ee
d
ed
less
co
m
p
u
tat
io
n
ti
m
e
t
h
a
n
C
S
A
-
AN
N.
As
a
co
n
cl
u
s
io
n
,
th
e
ca
b
ilit
y
o
f
MC
S
A
-
A
NN
f
o
r
th
e
o
u
tp
u
t p
r
ed
ictio
n
w
as j
u
s
tif
ied
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
w
o
r
k
w
a
s
s
u
p
p
o
r
ted
in
p
ar
t
b
y
t
h
e
Fu
n
d
a
m
e
n
tal
R
e
s
ea
r
ch
Gr
an
t
Sc
h
e
m
e
(
F
R
GS)
,
Min
i
s
tr
y
o
f
E
d
u
ca
tio
n
(
R
e
f
: 6
0
0
-
R
MI
/F
R
GS 5
/3
(
1
2
0
/2
0
1
5
)
an
d
Un
iv
er
s
iti T
ek
n
o
lo
g
i M
AR
A
(
UiT
M)
Ma
la
y
s
ia.
RE
F
E
R
E
NC
E
S
[1
]
F
.
Ha
sh
im
,
e
t
a
l.
,
“
P
re
d
ictio
n
o
f
ra
in
f
a
ll
b
a
se
d
o
n
w
e
a
th
e
r
p
a
ra
m
e
ter
u
sin
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
,
”
J
o
u
rn
a
l
o
f
Fu
n
d
a
me
n
t
a
l
a
n
d
A
p
p
l
ied
S
c
ie
n
c
e
s
,
v
o
l.
9
,
p
p
.
4
9
3
-
5
0
2
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
11
,
No
.
1
,
J
u
ly
201
8
:
1
2
1
–
1
2
8
128
[2
]
S
.
S
u
laim
a
n
,
e
t
a
l.
,
“
P
e
rf
o
r
m
a
n
c
e
A
n
a
l
y
sis
o
f
E
v
o
lu
ti
o
n
a
ry
AN
N
f
o
r
Ou
tp
u
t
P
re
d
ictio
n
o
f
a
G
rid
-
Co
n
n
e
c
ted
P
h
o
t
o
v
o
lt
a
ic S
y
ste
m
,
”
Pro
c
e
e
d
in
g
s o
f
W
o
rl
d
Ac
a
d
e
my
o
f
S
c
ien
c
e
:
En
g
i
n
e
e
rin
g
&
T
e
c
h
n
o
lo
g
y
,
v
o
l.
5
3
,
2
0
0
9
.
[3
]
N.
No
rd
in
,
e
t
a
l
.
,
“
P
re
d
ictio
n
o
f
A
C
p
o
w
e
r
o
u
tp
u
t
in
g
rid
-
c
o
n
n
e
c
ted
p
h
o
to
v
o
lt
a
ic
sy
ste
m
u
sin
g
Artif
icia
l
N
e
u
ra
l
Ne
tw
o
rk
w
it
h
m
u
lt
i
-
v
a
riab
le
in
p
u
ts,
”
in
S
y
ste
ms
,
Pro
c
e
ss
a
n
d
C
o
n
tro
l
(
ICS
PC),
2
0
1
6
IEE
E
Co
n
fer
e
n
c
e
o
n
,
p
p
.
192
-
1
9
5
,
2
0
1
6
.
[4
]
S
.
S
u
p
ian
,
e
t
a
l.
,
“
M
a
th
e
m
a
ti
c
a
l
M
o
d
e
l
f
o
r
Diss
o
lv
e
d
Ox
y
g
e
n
P
re
d
ictio
n
i
n
Cirata
Re
se
rv
o
ir,
W
e
st
Ja
v
a
b
y
Us
in
g
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
,
”
J
o
u
rn
a
l
o
f
F
u
n
d
a
me
n
ta
l
a
n
d
Ap
p
li
e
d
S
c
ien
c
e
s
,
v
o
l.
1
0
,
p
p
.
6
6
-
7
8
,
2
0
1
8
.
[5
]
X
.
Ya
o
,
“
Ev
o
lv
in
g
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s,
”
Pro
c
e
e
d
in
g
s o
f
t
h
e
I
EE
E
,
v
o
l.
8
7
,
p
p
.
1
4
2
3
-
1
4
4
7
,
1
9
9
9
.
[6
]
A
.
Ou
a
a
ra
b
,
e
t
a
l.
,
“
Disc
re
te
c
u
c
k
o
o
se
a
rc
h
a
lg
o
ri
th
m
f
o
r
t
h
e
trav
e
ll
in
g
sa
les
m
a
n
p
ro
b
lem
,
”
Ne
u
ra
l
Co
mp
u
t
in
g
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
p
p
.
1
-
1
1
,
2
0
1
3
.
[7
]
P
.
Civ
icio
g
lu
a
n
d
E.
Be
sd
o
k
,
“
A
c
o
n
c
e
p
tu
a
l
c
o
m
p
a
riso
n
o
f
th
e
Cu
c
k
o
o
-
se
a
rc
h
,
p
a
rti
c
le
s
w
a
r
m
o
p
ti
m
iza
ti
o
n
,
d
if
fe
re
n
ti
a
l
e
v
o
lu
ti
o
n
a
n
d
a
rti
f
ici
a
l
b
e
e
c
o
lo
n
y
a
lg
o
rit
h
m
s,
”
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
Rev
iew
,
v
o
l.
3
9
,
p
p
.
3
1
5
-
3
4
6
,
2
0
1
3
.
[8
]
S
.
I.
S
u
laim
a
n
,
e
t
a
l.
,
“
Ev
o
lu
t
io
n
a
r
y
p
ro
g
ra
m
m
in
g
v
e
rsu
s
a
rti
f
i
c
ia
l
imm
u
n
e
s
y
ste
m
in
e
v
o
lv
in
g
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
g
rid
-
c
o
n
n
e
c
ted
p
h
o
to
v
o
lt
a
ic
sy
st
e
m
o
u
tp
u
t
p
re
d
icti
o
n
,
”
W
S
EA
S
T
ra
n
sa
c
ti
o
n
s
o
n
S
y
ste
ms
a
n
d
Co
n
tro
l
,
v
o
l.
6
,
p
p
.
197
-
2
0
6
,
2
0
1
1
.
[9
]
S
.
I.
S
u
laim
a
n
,
e
t
a
l.
,
“
H
y
b
rid
i
z
a
ti
o
n
o
f
M
e
ta
-
Ev
o
lu
ti
o
n
a
ry
P
r
o
g
ra
m
m
in
g
a
n
d
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
f
o
r
p
re
d
ictin
g
g
rid
-
c
o
n
n
e
c
ted
p
h
o
t
o
v
o
lt
a
ic
sy
ste
m
o
u
tp
u
t,
”
in
T
ENCO
N
S
p
ri
n
g
Co
n
fer
e
n
c
e
,
2
0
1
3
IEE
E
,
p
p
.
4
4
5
-
4
4
9
,
2
0
1
3
.
[1
0
]
S
.
A
.
S
h
a
a
y
a
,
e
t
a
l.
,
“
I
m
m
u
n
ize
d
-
e
v
o
lu
ti
o
n
a
ry
a
l
g
o
rit
h
m
b
a
se
d
t
e
c
h
n
iq
u
e
f
o
r
lo
ss
c
o
n
tro
l
i
n
tran
s
m
issio
n
s
y
ste
m
w
it
h
m
u
lt
i
-
lo
a
d
in
c
re
m
e
n
t,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
(I
J
EE
CS
)
,
v
o
l.
6
,
p
p
.
7
3
7
-
7
4
8
,
2
0
1
7
.
[1
1
]
J.
S
h
a
h
ra
b
i
a
n
d
S
.
M
.
Kh
a
m
e
n
e
h
,
“
De
v
e
lo
p
m
e
n
t
o
f
a
H
y
b
rid
S
y
st
e
m
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
a
n
d
A
rti
f
icia
l
Be
e
Co
lo
n
y
A
lg
o
rit
h
m
f
o
r
P
re
d
i
c
ti
o
n
a
n
d
M
o
d
e
li
n
g
o
f
Cu
sto
m
e
r
Ch
o
ice
i
n
t
h
e
M
a
rk
e
t,
”
J
o
u
rn
a
l
o
f
Fu
n
d
a
me
n
ta
l
a
n
d
Ap
p
li
e
d
S
c
ien
c
e
s
,
v
o
l.
9
,
p
p
.
1
5
4
-
1
8
3
,
2
0
1
7
.
[1
2
]
N.
Ka
ss
i
m
,
e
t
a
l.
,
“
Ha
r
m
o
n
y
s
e
a
r
c
h
-
b
a
se
d
o
p
t
im
iza
ti
o
n
o
f
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
p
re
d
ictin
g
AC
p
o
w
e
r
f
ro
m
a
p
h
o
to
v
o
l
taic
sy
ste
m
,
”
in
Po
we
r E
n
g
i
n
e
e
rin
g
a
n
d
Op
ti
miz
a
ti
o
n
Co
n
fer
e
n
c
e
(
PE
OCO
),
2
0
1
4
IEE
E
8
t
h
In
ter
n
a
t
io
n
a
l
,
p
p
.
5
0
4
-
507
,
2
0
1
4
.
[1
3
]
T
.
N.
Hu
ss
a
in
,
e
t
a
l.
,
“
A
h
y
b
rid
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
g
rid
-
c
o
n
n
e
c
ted
p
h
o
t
o
v
o
lt
a
ic
sy
ste
m
o
u
t
p
u
t
p
re
d
icti
o
n
,
”
in
Co
m
p
u
ter
s &
In
fo
rm
a
ti
c
s (
IS
CI),
2
0
1
3
IEE
E
S
y
mp
o
siu
m
o
n
,
p
p
.
1
0
8
-
1
1
1
,
2
0
1
3
.
[1
4
]
J.
S
il
b
e
rh
o
lz
a
n
d
B.
G
o
ld
e
n
,
“
Co
m
p
a
riso
n
o
f
m
e
tah
e
u
risti
c
s,
”
in
Ha
n
d
b
o
o
k
o
f
M
e
tah
e
u
risti
c
s,
e
d
:
S
p
rin
g
e
r,
p
p
.
625
-
6
4
0
,
2
0
1
0
.
[1
5
]
X.
S
.
Ya
n
g
,
“
Na
tu
re
-
in
s
p
ired
m
e
tah
e
u
risti
c
a
lg
o
rit
h
m
s
,”
L
u
n
iv
e
r
p
re
ss
,
2
0
1
0
.
[1
6
]
X.
S
.
Ya
n
g
a
n
d
S
.
De
b
,
“
Cu
c
k
o
o
se
a
rc
h
v
ia
L
é
v
y
f
li
g
h
ts,
”
in
Na
tu
re
&
Bi
o
lo
g
ica
ll
y
I
n
sp
ire
d
Co
mp
u
ti
n
g
,
N
a
BI
C
2
0
0
9
.
W
o
rld
C
o
n
g
re
ss
o
n
,
p
p
.
2
1
0
-
2
1
4
,
2
0
0
9
.
[1
7
]
X.
S
.
Ya
n
g
a
n
d
S
.
De
b
,
“
En
g
in
e
e
rin
g
o
p
ti
m
isa
ti
o
n
b
y
c
u
c
k
o
o
se
a
rc
h
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
M
a
th
e
ma
ti
c
a
l
M
o
d
e
ll
in
g
a
n
d
Nu
me
ric
a
l
O
p
ti
mi
sa
ti
o
n
,
v
o
l
.
1
,
p
p
.
3
3
0
-
3
4
3
,
2
0
1
0
.
[1
8
]
X
.
Ya
o
,
e
t
a
l.
,
“
Ev
o
lu
ti
o
n
a
ry
p
ro
g
ra
m
m
in
g
m
a
d
e
f
a
ste
r,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Evo
l
u
ti
o
n
a
ry
c
o
mp
u
ta
ti
o
n
,
v
o
l.
3
,
p
p
.
8
2
-
1
0
2
,
1
9
9
9
.
[1
9
]
X.
S
.
Ya
n
g
,
“
Na
tu
re
-
in
s
p
ired
o
p
ti
m
iz
a
ti
o
n
a
lg
o
rit
h
m
s
,”
El
se
v
i
e
r,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.