I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
201
9
,
p
p
.
270
~
277
I
SS
N:
2252
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
8
.i
3
.
p
p
270
-
2
7
7
270
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
A
I
K
iller
w
ha
le
-
ba
ckpro
pa
g
a
tion (K
W
-
BP)
alg
o
rith
m
f
o
r accura
cy
i
m
pro
v
e
m
en
t
o
f
n
eura
l net
w
o
rk
f
o
r
ecas
ting
m
o
d
els o
n energy
-
eff
icie
nt
da
ta
Sa
a
di B
in Ah
m
a
d K
a
m
a
r
ud
din
1
,
No
r
Azura
M
d G
ha
ni
2
,
H
a
zr
it
a
Ab R
a
hi
m
3
,
I
s
m
a
il
M
us
irin
4
1,
3
De
p
a
rtm
e
n
t
o
f
Bu
sin
e
ss
S
tu
d
ies
,
F
a
c
u
lt
y
o
f
Bu
sin
e
ss
,
Eco
n
o
m
ics
a
n
d
A
c
c
o
u
n
ti
n
g
,
HEL
P
U
n
iv
e
rsity
,
S
u
b
a
n
g
2
Ca
m
p
u
s.
P
e
rsia
ra
n
Ca
k
e
ra
w
a
la,
S
u
b
a
n
g
Be
sta
ri,
S
e
k
sy
e
n
U4
,
4
0
1
5
0
S
h
a
h
A
la
m
,
S
e
lan
g
o
r,
M
a
lay
sia
2
Ce
n
ter f
o
r
S
tati
stica
l
S
tu
d
ies
a
n
d
De
c
isio
n
S
c
ien
c
e
s,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter an
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
4
0
4
5
0
S
h
a
h
A
lam
,
S
e
lan
g
o
r,
M
a
la
y
sia
4
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
De
p
a
rtm
e
n
t,
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
RA
,
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
u
n
1
9
,
2
0
1
9
R
ev
i
s
ed
A
u
g
1
0
,
2
0
1
9
A
cc
ep
ted
A
u
g
2
6
,
2
0
1
9
G
re
e
n
tec
h
n
o
lo
g
y
b
u
il
d
i
n
g
is
n
o
t
n
e
w
l
y
in
tro
d
u
c
e
d
t
o
th
e
w
o
rld
n
o
r
M
a
la
y
sia
,
b
u
t
it
is
ra
re
l
y
p
ra
c
ti
c
e
d
g
lo
b
a
ll
y
a
n
d
n
o
w
it
h
a
s
p
ro
m
o
ted
n
o
tew
o
rth
y
d
u
e
to
d
e
stru
c
ti
o
n
s
c
a
u
se
d
b
y
h
u
m
a
n
h
a
n
d
s
t
o
w
a
rd
s
th
e
n
a
tu
re
.
No
w
p
e
o
p
le
sta
rted
to
re
a
li
z
e
th
a
t
th
e
w
o
rld
i
s
p
o
ll
u
ted
b
y
m
a
n
y
h
a
z
a
rd
o
u
s
su
b
sta
n
c
e
s.
T
h
e
re
f
o
re
,
He
lp
Un
iv
e
rsit
y
c
a
m
e
u
p
w
it
h
th
e
e
ff
o
rt
o
f
p
re
se
rv
in
g
th
e
n
a
tu
re
th
r
o
u
g
h
a
n
e
w
G
re
e
n
T
e
c
h
n
o
lo
g
y
c
a
m
p
u
s,
w
h
ich
h
a
s
b
e
e
n
f
u
ll
y
o
p
e
ra
ted
sin
c
e
y
e
a
r
2
0
1
7
.
I
n
th
is
re
se
a
rc
h
,
n
e
u
ra
l
n
e
tw
o
rk
f
o
re
c
a
sti
n
g
m
o
d
e
ls
o
n
e
n
e
rg
y
-
e
ff
icie
n
t
d
a
ta
o
f
He
lp
Un
iv
e
rsity
,
S
u
b
a
n
g
2
g
re
e
n
t
e
c
h
n
o
l
o
g
y
c
a
m
p
u
s
a
t
S
u
b
a
n
g
Bistari,
S
e
lan
g
o
r
h
a
s
b
e
e
n
d
o
n
e
w
it
h
re
sp
e
c
t
to
v
a
lu
e
-
f
o
r
-
m
o
n
e
y
(V
F
M
)
a
tt
ri
b
u
te.
P
re
v
io
u
sl
y
th
e
re
w
e
re
n
o
sim
il
a
r
re
se
a
rc
h
d
o
n
e
o
n
e
n
e
rg
y
-
e
ff
ici
e
n
t
d
a
ta
o
f
He
lp
Un
iv
e
rsi
t
y
,
S
u
b
a
n
g
2
c
a
m
p
u
s.
T
h
e
sig
n
if
ica
n
t
f
a
c
to
rs
w
it
h
re
sp
e
c
t
to
e
n
e
rg
y
o
r
e
lec
tri
c
it
y
sa
v
e
d
(M
W
/h
r)
in
th
e
y
e
a
r
2
0
1
7
v
a
riab
le
w
e
re
stu
d
ied
a
s
re
c
o
rd
e
d
b
y
Bu
il
d
in
g
A
u
to
m
a
ti
o
n
a
n
d
Co
n
tro
l
S
y
st
e
m
(B
A
S
)
o
f
H
e
lp
Un
iv
e
rsity
S
u
b
a
n
g
2
c
a
m
p
u
s.
Us
in
g
m
u
lt
ip
le
li
n
e
a
r
re
g
re
ss
io
n
(ste
p
w
ise
m
e
th
o
d
),
t
h
e
sig
n
if
ica
n
t
p
re
d
ict
o
r
t
o
w
a
rd
s
e
n
e
rg
y
sa
v
e
d
(M
W
/h
r)
w
a
s
Bu
il
d
in
g
En
e
r
g
y
In
d
e
x
(BEI)
(k
W
h
/
m
2
/
y
e
a
r)
b
a
se
d
p
-
v
a
lu
e
<
α
=
0
.
0
5
.
A
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
l
wa
s
d
e
v
e
lo
p
e
d
.
M
o
r
e
o
v
e
r,
th
e
p
ro
p
o
se
d
n
e
u
ra
l
n
e
tw
o
rk
f
o
re
c
a
stin
g
m
o
d
e
l
u
sin
g
Kill
e
r
W
h
a
le
-
Ba
c
k
p
ro
p
a
g
a
ti
o
n
A
lg
o
rit
h
m
(K
W
BP
)
w
e
r
e
f
o
u
n
d
to
b
e
tt
e
r
th
a
n
e
x
isti
n
g
c
o
n
v
e
n
ti
o
n
a
l
tec
h
n
iq
u
e
s
to
f
o
re
c
a
st
BEI
d
a
ta.
T
h
is
re
se
a
rc
h
is
e
x
p
e
c
ted
to
sp
e
c
if
ic
a
ll
y
a
ss
ist
m
a
in
ten
a
n
c
e
d
e
p
a
rtm
e
n
t
o
f
He
lp
Un
iv
e
rsity
,
S
u
b
a
n
g
2
c
a
m
p
u
s to
w
a
rd
s lo
a
d
f
o
re
c
a
stin
g
f
o
r
p
o
w
e
r
sa
v
in
g
p
lan
n
in
g
in
y
e
a
r
s to
c
o
m
e
.
K
ey
w
o
r
d
s
:
B
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
E
n
er
g
y
-
e
f
f
icie
n
t
Fo
r
ec
asti
n
g
Gr
ee
n
tech
n
o
lo
g
y
ca
m
p
u
s
Killer
w
h
ale
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Saad
i b
in
A
h
m
ad
Ka
m
ar
u
d
d
in
,
Dep
ar
t
m
en
t o
f
B
u
s
i
n
es
s
St
u
d
i
es,
Facu
lt
y
o
f
B
u
s
i
n
ess
,
E
co
n
o
m
i
cs a
n
d
A
cc
o
u
n
ti
n
g
,
HE
L
P
Un
i
v
er
s
it
y
,
S
u
b
an
g
2
C
a
m
p
u
s
,
P
er
s
ia
r
an
C
ak
er
a
w
ala,
Su
b
an
g
B
estar
i,
Sek
s
y
e
n
U4
,
4
0
1
5
0
Sh
ah
A
la
m
,
Sela
n
g
o
r
,
Ma
la
y
s
ia
.
E
m
ail:
s
aa
d
i.a
k
@
h
elp
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Fo
s
s
il
o
r
e
v
e
n
elec
tr
icit
y
i
s
o
n
e
o
f
t
h
e
m
ai
n
co
n
tr
ib
u
to
r
s
to
w
ar
d
s
g
lo
b
al
cli
m
ate
ch
a
n
g
es
a
s
t
h
e
ex
ce
s
s
iv
e
u
s
e
a
n
d
co
n
s
u
m
p
ti
o
n
o
f
f
o
s
s
il
e
n
er
g
y
w
i
ll
w
i
n
d
u
p
in
r
elea
s
i
n
g
a
h
u
g
e
a
m
o
u
n
t
o
f
g
r
ee
n
h
o
u
s
e
g
as
s
es
i
n
to
t
h
e
at
m
o
s
p
h
er
e
[
1
]
.
Hen
ce
,
f
e
w
m
eth
o
d
s
s
u
c
h
a
s
i
m
p
r
o
v
e
m
en
t
o
f
en
er
g
y
e
f
f
icie
n
c
y
,
f
r
eq
u
en
t
u
s
e
o
f
r
en
e
w
ab
le
-
en
er
g
y
,
p
r
eser
v
atio
n
o
f
a
h
ea
l
th
y
in
d
o
o
r
en
v
ir
o
n
m
e
n
t,
h
a
v
i
n
g
g
r
ee
n
p
lan
t
i
n
t
h
e
b
u
ild
in
g
co
m
p
o
u
n
d
ar
ea
,
in
cr
ea
s
e
u
s
e
o
f
s
u
s
tai
n
ab
ilit
y
o
f
n
atu
r
al
r
eso
u
r
c
es
ar
e
f
e
w
o
f
th
e
h
a
s
ca
u
g
h
t
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
K
iller
w
h
a
le
-
b
a
ck
p
r
o
p
a
g
a
tio
n
(
K
W
-
B
P
)
a
lg
o
r
ith
m
fo
r
…
(
S
a
a
d
i B
in
A
h
ma
d
K
a
ma
r
u
d
d
in
)
271
w
o
r
ld
’
s
atten
tio
n
[
2
]
.
Gr
ee
n
b
u
ild
in
g
,
o
r
k
n
o
w
n
as
e
n
er
g
y
-
e
f
f
icien
t
b
u
ild
i
n
g
i
s
a
co
n
s
tr
u
ct
io
n
o
f
b
u
ild
i
n
g
t
h
at
f
u
lf
i
ls
t
h
e
n
ee
d
s
s
tated
ab
o
v
e
an
d
ca
p
ab
le
o
f
r
ed
u
cin
g
g
r
ee
n
h
o
u
s
e
e
f
f
ec
t
b
y
r
ed
u
ci
n
g
t
h
e
d
ep
en
d
en
c
y
o
f
f
o
s
s
il
o
r
elec
tr
icit
y
u
s
e
[
3
]
.
T
o
s
u
p
p
o
r
t
th
e
co
n
ce
p
t
o
f
e
n
er
g
y
ef
f
icien
c
y
a
n
d
t
h
e
u
s
e
o
f
s
u
s
tain
ab
le
e
n
er
g
y
in
b
u
ild
in
g
s
,
t
h
e
g
o
v
er
n
m
en
t
o
f
Ma
la
y
s
ia
h
a
s
al
s
o
lu
n
c
h
e
d
a
f
e
w
p
r
o
j
ec
ts
as
a
n
ac
t
o
f
d
e
m
o
n
s
tr
atio
n
,
ed
u
ca
tio
n
al
a
n
d
e
n
h
a
n
ce
p
u
b
lic
a
w
ar
en
e
s
s
p
r
o
g
r
a
m
s
[
4
]
.
Gr
ee
n
tec
h
n
o
lo
g
y
o
f
f
ice
b
u
il
d
in
g
is
o
n
e
o
f
th
e
s
h
o
w
ca
s
e
p
r
o
j
ec
ts
th
at
h
a
v
e
h
ig
h
p
er
f
o
r
m
a
n
ce
in
e
n
er
g
y
e
f
f
icien
c
y
[
5
]
.
Ma
la
y
s
ia
E
n
er
g
y
C
en
tr
e
(
P
T
M)
th
at
is
n
o
w
c
u
r
r
en
tl
y
k
n
o
w
n
as
T
ec
h
n
o
lo
g
y
C
o
r
p
o
r
atio
n
o
f
f
icer
b
u
ild
in
g
is
t
h
e
p
r
o
o
f
o
f
t
h
at
t
h
is
co
n
ce
p
t
“g
r
ee
n
tech
n
o
lo
g
y
”
is
co
m
m
er
ciall
y
v
iab
le
f
o
r
m
o
d
er
n
b
u
ild
in
g
s
i
n
Ma
la
y
s
ia
an
d
in
th
e
r
eg
io
n
[
6
]
.
T
h
e
b
u
ild
in
g
is
ac
tu
all
y
b
ased
o
n
Au
to
m
ated
E
n
er
g
y
Sa
v
i
n
g
(
A
E
S)
co
n
ce
p
t.
T
h
e
aim
o
f
t
h
is
p
r
o
j
ec
t
i
s
to
ap
p
ly
m
o
d
er
n
f
o
r
ec
asti
n
g
alg
o
r
it
h
m
o
n
e
n
e
r
g
y
-
e
f
f
ic
ien
t
d
at
a
o
f
HE
L
P
S
u
b
an
g
2
g
r
ee
n
tec
h
n
o
lo
g
y
ca
m
p
u
s
,
w
h
ic
h
w
er
e
ca
p
tu
r
ed
b
y
B
u
ild
i
n
g
A
u
to
m
at
io
n
an
d
C
o
n
tr
o
l S
y
s
te
m
(
B
A
S
)
as sh
o
w
n
i
n
Fi
g
u
r
e
1
.
(
a)
(
b
)
Fig
u
r
e
1
.
(
a)
HE
L
P
Su
b
an
g
2
g
r
ee
n
tec
h
n
o
lo
g
y
ca
m
p
u
s
,
an
d
(
b
)
B
u
ild
in
g
A
u
to
m
atio
n
an
d
C
o
n
tr
o
l
S
y
s
te
m
(
B
A
S)
E
lectr
icit
y
is
o
n
e
o
f
ea
r
th
-
s
h
a
k
in
g
r
eso
u
r
ce
s
in
t
h
i
s
ce
n
t
u
r
y
.
I
t
is
th
e
m
aj
o
r
s
o
u
r
ce
o
f
p
o
w
er
f
o
r
m
o
s
t
o
f
t
h
e
co
u
n
tr
y
's
ec
o
n
o
m
ic
ac
ti
v
itie
s
[
7
]
.
Mo
v
i
n
g
to
w
ar
d
s
en
er
g
y
s
u
s
tai
n
ab
ilit
y
w
i
ll
r
eq
u
ir
e
m
o
d
if
icatio
n
s
n
o
t
o
n
l
y
i
n
th
e
w
a
y
e
n
er
g
y
is
s
u
p
p
lied
,
b
u
t
also
in
th
e
w
a
y
it
is
u
s
ed
as
w
e
ll,
ca
lled
en
er
g
y
p
la
n
n
in
g
[
8
]
.
Gr
ee
n
b
u
ild
i
n
g
r
ef
er
s
to
b
o
th
as
s
e
m
b
l
y
a
n
d
th
e
i
m
p
le
m
en
tatio
n
o
f
p
r
o
ce
s
s
e
s
th
a
t
ar
e
en
v
ir
o
n
m
en
tal
l
y
r
esp
o
n
s
ib
le
an
d
r
eso
u
r
ce
-
e
f
f
i
cien
t
t
h
r
o
u
g
h
o
u
t
t
h
e
b
u
ild
i
n
g
’
s
li
f
e
c
y
cle
f
r
o
m
th
e
p
la
n
n
in
g
,
c
o
n
s
tr
u
ct
io
n
,
o
p
er
atio
n
,
m
ai
n
ten
a
n
ce
,
r
e
n
o
v
atio
n
,
an
d
d
e
m
o
liti
o
n
p
h
a
s
e
[
9
]
.
I
n
o
r
d
er
to
ac
h
ie
v
e
s
u
c
h
ac
h
ie
v
e
m
e
n
t,
th
e
co
n
tr
ac
to
r
,
ar
ch
itects,
en
g
i
n
ee
r
s
,
an
d
th
e
clien
t
at
all
s
tag
es
h
av
e
to
w
o
r
k
clo
s
el
y
to
g
et
h
er
[
1
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
20
1
9
:
2
7
0
–
2
7
7
272
A
Gr
ee
n
b
u
ild
i
n
g
is
a
co
n
ce
p
t
th
at
co
m
p
le
m
e
n
ts
t
h
e
clas
s
ical
b
u
ild
i
n
g
d
esig
n
w
i
th
co
n
ce
r
n
s
o
f
ec
o
n
o
m
y
,
d
u
r
ab
ilit
y
,
co
m
f
o
r
t
an
d
also
u
t
ilit
y
[
1
1
]
.
W
o
r
ld
G
r
ee
n
B
u
ild
in
g
C
o
u
n
cil
c
u
r
r
en
tl
y
is
co
n
d
u
ctin
g
a
r
esear
ch
o
n
th
e
b
en
ef
its
t
h
at
g
r
ee
n
b
u
i
ld
in
g
ca
n
co
n
tr
ib
u
te
to
w
ar
d
s
th
e
h
ea
lt
h
an
d
p
r
o
d
u
ctiv
it
y
o
f
t
h
e
p
eo
p
le
u
s
in
g
it
an
d
is
also
w
o
r
k
in
g
w
i
th
th
e
W
o
r
ld
B
an
k
to
p
r
o
m
o
te
Gr
ee
n
B
u
i
ld
in
g
s
i
n
E
m
er
g
i
n
g
Ma
r
k
e
ts
[
1
2
]
.
T
h
er
e
ar
e
also
o
th
er
m
ea
s
u
r
e
m
en
t to
o
ls
s
u
c
h
as Gr
ee
n
B
u
ild
i
n
g
I
n
d
ex
(
GB
I
)
p
r
ed
o
m
i
n
a
n
tl
y
u
s
ed
in
Ma
la
y
s
ia
[
1
3
]
.
HE
L
P
Un
i
v
er
s
it
y
i
s
o
n
e
o
f
t
h
e
f
ir
s
t
h
i
g
h
er
ed
u
ca
tio
n
i
n
s
t
itu
tio
n
s
th
a
t
i
m
p
le
m
en
ts
g
r
ee
n
b
u
ild
in
g
co
n
ce
p
t
to
its
ca
m
p
u
s
e
s
.
Hen
ce
,
th
er
e
is
n
o
n
e
i
f
n
o
t
a
f
e
w
r
esear
c
h
co
n
d
u
cted
o
n
HE
L
P
Un
iv
er
s
it
y
Su
b
an
g
2
ca
m
p
u
s
.
W
ith
s
u
ch
l
i
m
i
ted
ti
m
e
a
n
d
n
o
p
r
io
r
r
esear
ch
co
n
d
u
cted
in
th
is
u
n
i
v
er
s
it
y,
th
is
r
esear
ch
m
a
y
b
e
ab
l
e
to
ass
i
s
t
HE
L
P
u
n
i
v
er
s
it
y
i
n
ter
m
s
o
f
e
n
er
g
y
e
f
f
icien
c
y
p
r
ac
tices
to
its
f
u
l
l
p
o
ten
tial.
Oth
er
t
h
a
n
th
at,
t
h
er
e
w
a
s
also
n
o
p
r
io
r
m
o
d
el
o
f
v
a
lu
e
-
f
o
r
-
m
o
n
e
y
(
VFM)
i
m
p
le
m
en
ted
o
n
HE
L
P
u
n
iv
er
s
it
y
’
s
en
er
g
y
-
ef
f
icien
c
y
ti
m
e
s
er
ies
d
at
a.
H
E
L
P
Un
i
v
er
s
it
y
h
as
alr
ea
d
y
s
h
o
w
n
it
s
s
u
p
p
o
r
t
b
y
co
n
s
tr
u
ct
in
g
i
ts
n
e
w
ca
m
p
u
s
t
o
b
e
m
o
r
e
en
er
g
y
e
f
f
icie
n
t a
n
d
m
o
r
e
n
a
tu
r
e
f
r
ie
n
d
l
y
w
h
ic
h
is
s
it
u
ated
i
n
S
u
b
an
g
B
estar
i
n
ea
r
S
u
b
an
g
Air
p
o
r
t.
T
h
e
ca
m
p
u
s
is
eq
u
ip
p
ed
w
it
h
Au
to
m
ated
I
n
f
r
ar
ed
Se
n
s
o
r
ce
ilin
g
li
g
h
t
w
h
ic
h
au
to
m
at
icall
y
t
u
r
n
s
o
n
w
h
en
s
en
s
o
r
p
ick
s
u
p
an
d
m
o
tio
n
;
th
is
h
elp
s
t
h
e
b
u
ild
in
g
to
co
n
s
er
v
e
m
o
r
e
en
er
g
y
esp
ec
iall
y
d
u
r
i
n
g
h
o
lid
a
y
s
an
d
also
d
u
r
in
g
t
h
e
n
i
g
h
t
w
h
en
n
o
b
o
d
y
is
i
n
t
h
e
b
u
ild
i
n
g
.
T
h
e
g
r
ee
n
ca
m
p
u
s
i
s
lar
g
el
y
d
ec
o
r
ated
w
it
h
g
r
ee
n
p
lan
ts
a
n
d
also
tr
ee
s
to
e
n
h
a
n
ce
s
tu
d
e
n
t
a
w
ar
en
e
s
s
to
w
ar
d
s
g
r
ee
n
e
n
v
ir
o
n
m
en
t.
T
h
e
b
u
ild
in
g
w
as
co
m
p
le
ted
in
2
0
1
6
;
h
o
w
e
v
er
,
th
e
b
u
ild
in
g
is
y
et
to
r
ea
ch
a
n
o
p
ti
m
u
m
lev
el
o
f
e
n
er
g
y
ef
f
icien
c
y
ev
e
n
h
a
v
i
n
g
ap
p
r
o
x
i
m
atel
y
2
y
ea
r
s
in
o
p
er
atio
n
.
T
h
e
B
u
ild
in
g
E
n
er
g
y
I
n
d
e
x
(
B
E
I
)
o
f
th
e
b
u
ild
in
g
is
y
et
to
ac
h
ie
v
e
an
o
p
ti
m
u
m
lev
el.
A
n
d
t
h
is
r
esear
ch
p
ap
er
w
ill
tr
y
i
t
b
est
to
i
m
p
le
m
e
n
t
tech
n
o
lo
g
y
w
h
ic
h
ca
n
co
n
tr
ib
u
te
i
n
ac
h
iev
i
n
g
th
e
id
ea
l B
u
ild
in
g
E
n
er
g
y
I
n
d
ex
(
B
E
I
)
.
T
h
e
r
esear
ch
o
b
j
ec
tiv
es r
elate
d
to
th
e
r
esear
ch
q
u
esti
o
n
s
ar
e
as f
o
llo
w
s
:
T
o
d
eter
m
i
n
e
th
e
s
i
g
n
i
f
ican
t
f
ac
to
r
s
r
esp
ec
tin
g
to
en
er
g
y
o
r
elec
tr
icity
s
a
v
ed
(
MW
/h
r
)
r
ec
o
r
d
ed
b
y
B
u
ild
in
g
A
u
to
m
atio
n
an
d
C
o
n
tr
o
l S
y
s
te
m
(
B
AS)
o
f
Help
Un
iv
er
s
it
y
S
u
b
an
g
2
ca
m
p
u
s
.
T
o
d
ev
elo
p
m
at
h
e
m
atica
l
m
o
d
el
o
f
en
er
g
y
e
f
f
ic
ien
t
d
at
a
w
h
ic
h
s
at
i
s
f
ies
v
al
u
e
-
f
o
r
-
m
o
n
e
y
(
VFM
)
attr
ib
u
te
o
f
Help
Un
iv
er
s
it
y
S
u
b
an
g
2
ca
m
p
u
s
.
T
o
p
r
o
p
o
s
e
a
r
o
b
u
s
t
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
f
o
r
lo
ad
f
o
r
ec
a
s
tin
g
at
HE
L
P
Un
i
v
er
s
it
y
S
u
b
an
g
2
ca
m
p
u
s
b
ased
o
n
o
u
tp
u
t in
(
a)
w
h
ich
s
atis
f
ies t
h
e
VFM
attr
ib
u
te.
A
t
t
h
e
en
d
o
f
th
i
s
r
esear
ch
,
f
o
r
ec
aster
s
o
r
en
g
in
ee
r
s
o
f
HE
L
P
Un
iv
er
s
it
y
’
s
m
a
in
te
n
a
n
ce
d
ep
ar
tm
e
n
t
to
im
p
r
o
v
e
t
h
eir
lo
ad
f
o
r
e
ca
s
tin
g
ac
ti
v
ities
,
a
n
d
ac
h
i
ev
e
a
s
atis
f
a
cto
r
y
lev
el
o
f
g
r
ee
n
tech
n
o
lo
g
y
b
u
ild
in
g
’
s
GB
I
.
B
y
h
elp
in
g
H
E
L
P
Un
iv
er
s
it
y
to
r
ea
c
h
it
s
f
u
ll
p
o
ten
tial
i
n
e
n
er
g
y
e
f
f
icie
n
c
y
,
it
ca
n
co
n
tr
ib
u
te
ec
o
n
o
m
icall
y
to
R
M
K1
1
as
a
n
a
n
n
u
al
elec
tr
icit
y
g
e
n
er
atio
n
o
f
elec
tr
ici
t
y
co
s
t
ar
o
u
n
d
R
M1
5
.
1
b
illi
o
n
[
1
5
]
.
T
h
e
r
esear
ch
o
u
tli
n
e
o
f
t
h
i
s
p
ap
er
s
tar
ts
r
esear
ch
m
o
ti
v
atio
n
,
f
o
llo
w
ed
b
y
r
esear
c
h
li
m
ita
tio
n
,
p
r
o
b
le
m
s
tate
m
en
t,
r
e
s
ea
r
c
h
q
u
esti
o
n
s
,
r
esear
ch
o
b
j
ec
tiv
es,
an
d
r
esear
ch
s
ig
n
i
f
ica
n
ce
.
Mo
r
eo
v
er
,
th
e
n
ex
t
s
ec
tio
n
s
ar
e
th
e
r
elate
d
liter
atu
r
es,
f
o
llo
w
e
d
b
y
t
h
e
m
et
h
o
d
o
lo
g
y
,
t
h
e
r
es
u
lts
a
n
d
d
is
cu
s
s
io
n
s
,
as
w
el
l a
s
th
e
co
n
cl
u
s
io
n
s
.
2.
RE
L
AT
E
D
L
I
T
E
RA
T
UR
E
S
Neu
r
al
Net
w
o
r
k
i
s
n
ee
d
ed
f
o
r
f
iltra
tio
n
an
d
clas
s
i
f
icatio
n
o
f
t
h
e
m
a
n
y
f
ac
to
r
s
th
at
ca
n
b
e
p
r
o
v
id
ed
b
y
a
ca
u
s
e
an
d
t
h
e
n
to
p
r
ed
ict
th
e
e
f
f
ec
ts
o
f
it
a
n
d
eit
h
er
to
i
m
p
r
o
v
e
o
r
to
m
i
n
i
m
i
s
e
d
a
m
a
g
es
t
h
r
o
u
g
h
ce
r
tai
n
p
atter
n
s
o
r
ch
ar
ac
ter
is
tics
[
1
5
]
.
Ma
ch
in
e
lear
n
in
g
w
il
l
b
e
a
v
er
y
cr
u
ci
al
p
ar
t
f
o
r
th
e
n
e
u
r
al
n
et
w
o
r
k
w
h
er
e
it
is
u
s
e
s
to
lear
n
f
r
o
m
th
e
e
x
is
t
in
g
d
ata
th
at
h
as
b
ee
n
co
llected
o
r
s
o
,
in
a
f
o
r
m
o
f
co
m
p
u
ter
i
ze
d
alg
o
r
ith
m
[
1
6
]
.
A
p
p
ar
en
tl
y
th
a
t
th
e
m
o
r
e
d
ata
th
at
it
u
s
e
s
an
d
th
e
m
o
r
e
r
ela
tiv
e
n
u
m
b
er
s
it
u
s
e
s
th
e
f
o
r
its
lear
n
in
g
p
u
r
p
o
s
es
th
e
m
o
r
e
ac
c
u
r
ate
it
b
ec
o
m
es
[
1
7
]
.
Ma
ch
in
e
lear
n
in
g
al
g
o
r
ith
m
s
ar
e
w
id
el
y
an
d
co
m
m
o
n
l
y
u
s
ed
in
cu
r
r
e
n
t
s
o
ciet
y
to
i
m
p
r
o
v
e
n
o
t
o
n
l
y
i
n
p
r
ed
ictio
n
b
u
t
also
to
im
p
o
s
e
o
n
b
u
ild
in
g
f
o
r
b
etter
en
er
g
y
co
n
s
u
m
p
tio
n
s
an
d
en
er
g
y
e
f
f
icie
n
c
y
,
f
o
r
ex
a
m
p
l
e
co
o
lin
g
th
e
ca
m
p
u
s
w
i
th
co
llected
r
ain
w
ater
co
o
lin
g
s
y
s
te
m
is
a
v
er
y
g
o
o
d
ex
a
m
p
le
[
1
8
]
,
w
h
ic
h
is
cu
r
r
e
n
t
l
y
p
r
ac
tices
b
y
HE
L
P
u
n
i
v
er
s
it
y
.
E
n
er
g
y
ef
f
icie
n
c
y
i
s
b
ein
g
p
r
o
m
o
ted
to
in
f
lu
e
n
ce
o
th
er
u
n
iv
er
s
ities
a
n
d
en
co
u
r
ag
i
n
g
th
e
m
to
d
o
th
e
s
a
m
e
n
o
t
j
u
s
t
b
ec
au
s
e
o
f
t
h
e
n
o
r
m
al
f
ac
to
r
s
,
b
u
t
also
th
e
f
ac
to
r
s
o
f
th
e
s
tak
e
h
o
l
d
er
,
g
o
v
er
n
m
e
n
t,
m
an
a
g
er
s
,
a
n
d
ev
en
f
ac
u
lt
y
p
er
ce
p
tio
n
s
[
1
9
]
.
3.
M
E
T
H
O
DO
L
O
G
Y
I
n
t
h
is
r
e
s
ea
r
ch
,
t
h
e
HE
L
P
Su
b
an
g
2
lo
ad
f
o
r
ec
asti
n
g
d
ata
is
o
b
tai
n
ed
f
r
o
m
t
h
e
m
a
in
te
n
an
ce
d
ep
ar
tm
e
n
t,
Help
Un
i
v
er
s
i
t
y
S
u
b
a
n
g
2
ca
m
p
u
s
f
o
r
th
e
y
ea
r
2
0
1
7
r
ec
o
r
d
e
d
in
m
o
n
t
h
l
y
b
asi
s
.
Fo
r
co
n
f
ir
m
atio
n
,
o
n
e
m
a
y
co
n
tact
t
h
e
g
e
n
er
al
li
n
e
+6
0
3
-
2
7
1
6
2
0
0
0
.
Data
co
llected
in
clu
d
e
elec
tr
icit
y
u
s
a
g
e
m
ea
s
u
r
ed
in
k
ilo
w
att
h
o
u
r
(
k
W
h
)
,
ca
r
b
o
n
em
i
s
s
io
n
s
,
en
er
g
y
s
a
v
ed
m
ea
s
u
r
ed
in
m
eg
a
w
a
tt
h
o
u
r
(
M
W
h
)
an
d
m
o
n
e
y
s
av
ed
th
r
o
u
g
h
o
u
t
d
ail
y
d
ata
s
tar
ti
n
g
f
r
o
m
0
6
:4
5
:0
0
p
m
o
n
8
th
Ma
y
2
0
1
7
to
1
2
:0
0
:0
0
p
m
o
n
3
1
st
Dec
e
m
b
er
2
0
1
7
(
ev
er
y
1
5
m
i
n
u
te
s
)
w
ith
t
h
e
u
n
i
v
er
s
it
y
o
p
e
r
atin
g
at
r
eg
u
lar
ca
p
ac
it
y
.
T
h
e
li
m
itatio
n
o
f
th
i
s
r
esear
ch
is
ter
m
s
o
f
a
v
ailab
ili
t
y
d
ata,
s
i
n
ce
t
h
is
ca
m
p
u
s
is
n
e
w
.
T
h
e
s
co
p
e
o
f
t
h
is
r
esear
ch
w
il
l
a
n
al
y
s
e
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
K
iller
w
h
a
le
-
b
a
ck
p
r
o
p
a
g
a
tio
n
(
K
W
-
B
P
)
a
lg
o
r
ith
m
fo
r
…
(
S
a
a
d
i B
in
A
h
ma
d
K
a
ma
r
u
d
d
in
)
273
HE
L
P
U
n
iv
er
s
it
y
elec
tr
ici
t
y
u
s
ag
e,
m
o
n
e
y
s
a
v
ed
,
B
u
ild
i
n
g
E
n
er
g
y
I
n
d
ex
(
B
E
I
)
(
k
W
h
/
m
2
/
y
ea
r
)
an
d
C
ar
b
o
n
Dio
x
id
e
(
C
o
2
)
E
m
is
s
io
n
d
ated
f
o
r
th
e
y
ea
r
2
0
1
7
w
er
e
r
ec
o
r
d
ed
B
u
ild
in
g
Au
to
m
at
io
n
a
n
d
C
o
n
tr
o
l
S
y
s
te
m
(
B
A
S)
o
f
Help
Un
iv
er
s
it
y
Su
b
an
g
2
ca
m
p
u
s
.
T
h
e
f
lo
w
c
h
ar
t
o
f
th
i
s
r
esear
ch
s
h
o
w
n
in
Fig
u
r
e
2
.
On
ce
th
e
d
ata
ass
e
m
b
led
as
s
h
o
w
n
in
Fig
u
r
e
3
,
d
eter
m
in
at
io
n
o
f
n
e
u
r
al
n
e
t
w
o
r
k
ti
m
e
s
er
ies
m
o
d
els
w
er
e
m
ad
e
[
2
0
-
2
1
]
.
T
h
e
cr
itical
p
ar
t
o
f
th
i
s
r
esear
c
h
w
a
s
th
e
i
m
p
le
m
e
n
tatio
n
o
f
p
r
o
p
o
s
ed
k
iller
w
h
a
le
alg
o
r
ith
m
o
n
i
ter
ated
least
m
ed
ia
n
q
u
ar
es
alg
o
r
ith
m
to
r
ep
lace
th
e
o
r
d
in
ar
y
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
w
h
ic
h
w
as b
ased
o
n
m
ea
n
s
q
u
ar
ed
er
r
o
r
[
2
2
]
.
D
a
t
a
C
o
l
l
e
c
t
i
o
n
a
n
d
A
s
s
e
m
b
l
y
M
o
d
e
l
D
e
t
e
r
m
i
n
a
t
i
o
n
:
N
A
R
&
N
A
R
M
A
D
a
t
a
P
r
e
p
r
o
c
e
s
s
i
n
g
T
r
a
i
n
i
n
g
S
e
t
B
P
N
N
T
r
a
i
n
i
n
g
P
r
e
s
e
n
t
i
n
p
u
t
p
a
t
t
e
r
n
a
n
d
c
a
l
c
u
l
a
t
e
o
u
t
p
u
t
v
a
l
u
e
s
C
a
l
c
u
l
a
t
e
M
S
E
M
S
E
≤
M
S
E
m
i
n
No
i
t
e
r
a
t
i
o
n
≥
i
t
e
r
a
t
i
o
n
m
a
x
I
n
i
t
i
a
l
i
z
e
w
e
i
g
h
t
a
n
d
b
i
a
s
e
s
w
i
t
h
r
a
n
d
o
m
v
a
l
u
e
s
I
n
i
t
i
a
l
i
z
e
t
r
a
i
n
i
n
g
e
p
o
c
h
=
1
No
U
p
d
a
t
e
w
e
i
g
h
t
s
a
n
d
b
i
a
s
e
s
i
t
e
r
a
t
i
o
n
=
i
t
e
r
a
t
i
o
n
+
1
V
a
l
i
d
a
t
i
o
n
S
e
t
T
e
s
t
i
n
g
S
e
t
F
o
r
e
c
a
s
t
f
u
t
u
r
e
v
a
l
u
e
s
F
i
n
i
s
h
S
t
o
p
T
r
a
i
n
i
n
g
Y
e
s
Y
e
s
P
r
o
d
u
c
e
B
e
s
t
W
h
a
l
e
P
o
s
i
t
o
n
Y
e
s
D
e
c
r
e
a
s
e
a
f
r
o
m
2
t
o
0
I
n
i
t
i
a
l
i
z
e
v
e
c
t
o
r
s
A
,
C
a
n
d
P
E
v
a
l
u
a
t
e
E
a
c
h
W
h
a
l
e
P
o
s
i
t
i
o
n
u
s
i
n
g
F
n
A
s
s
i
g
n
E
a
c
h
S
u
b
s
e
t
t
o
A
W
h
a
l
e
P
o
s
i
t
i
o
n
R
a
n
d
o
m
I
n
i
t
i
a
l
i
z
a
t
i
o
n
o
f
F
e
a
t
u
r
e
s
S
u
b
s
e
t
s
I
n
i
t
i
a
t
e
L
M
e
d
S
c
o
n
d
i
t
i
o
n
No
Fig
u
r
e
2
.
Flo
w
o
f
K
iller
W
h
al
e
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
Net
w
o
r
k
(
KW
-
B
P
NN)
A
lg
o
r
it
h
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
20
1
9
:
2
7
0
–
2
7
7
274
Fig
u
r
e
3
.
T
im
e
Ser
ies Da
ta
s
et
in
T
h
is
R
e
s
ea
r
ch
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
NS
Usi
n
g
s
ta
tis
tica
l
an
al
y
s
i
s
,
B
u
i
ld
in
g
E
n
er
g
y
I
n
d
ex
(
B
E
I
)
(
k
W
h
/
m
2
/
y
ea
r
)
an
d
C
ar
b
o
n
Dio
x
id
e
(
C
o
2
)
E
m
is
s
io
n
w
er
e
th
e
s
i
g
n
if
ican
t
p
r
ed
icto
r
s
to
w
ar
d
s
e
n
er
g
y
s
av
ed
(
MW
/h
r
)
b
ased
p
-
v
al
u
e<
α
=0
.
0
5
.
T
ab
le
1
s
h
o
w
s
t
h
e
R
MSE
s
o
f
B
P
NN
-
NAR
an
d
B
P
NN
-
N
A
R
M
A
b
y
d
i
f
f
er
en
t
alg
o
r
it
h
m
s
o
n
B
u
i
ld
in
g
E
n
er
g
y
I
n
d
e
x
(
B
E
I
)
d
ata.
B
ased
o
n
o
r
d
in
ar
y
b
ac
k
p
r
o
p
ag
atio
n
a
lg
o
r
it
h
m
,
th
e
b
est
co
n
f
i
g
u
r
atio
n
w
a
s
1
5
-
15
-
1
5
.
T
ab
le
2
s
h
o
w
s
t
h
e
d
escr
ip
ti
v
e
s
tati
s
tic
s
o
f
t
h
e
v
ar
iab
les
in
v
o
lv
ed
in
t
h
is
r
esear
ch
.
T
ab
le
3
s
h
o
w
s
t
h
e
co
ef
f
icie
n
ts
tab
le
f
r
o
m
m
u
ltip
le
li
n
er
r
eg
r
es
s
io
n
(
s
tep
w
i
s
e)
tech
n
iq
u
e.
Fro
m
T
ab
le
4
,
th
e
b
est
co
n
f
i
g
u
r
at
i
o
n
f
o
r
k
iller
w
h
ale
b
ac
k
p
r
o
p
ag
atio
n
al
g
o
r
ith
m
w
a
s
3
0
-
30
-
3
0
.
Fire
f
l
y
al
g
o
r
ith
m
o
n
b
ac
k
p
r
o
p
ag
atio
n
a
n
d
p
ar
ticle
s
w
ar
m
o
p
tim
izatio
n
o
n
b
ac
k
p
r
o
p
ag
at
io
n
p
er
f
o
r
m
ed
eq
u
all
y
g
o
o
d
w
h
er
e
th
e
b
est
co
n
f
i
g
u
r
atio
n
s
f
o
r
b
o
th
alg
o
r
ith
m
s
w
er
e
2
0
-
20
-
2
0
.
C
o
m
p
ar
in
g
t
h
e
p
er
f
o
r
m
a
n
ce
f
o
r
all
alg
o
r
ith
m
,
it
ca
n
b
e
co
n
clu
d
ed
th
at
t
h
e
p
r
o
p
o
s
ed
k
iller
w
h
ale
b
ac
k
p
r
o
p
ag
atio
n
(
KW
B
P
)
n
eu
r
al
n
et
w
o
r
k
w
a
s
f
o
u
n
d
to
b
etter
th
an
ex
is
ti
n
g
co
n
v
en
tio
n
al
tech
n
iq
u
e
s
,
w
h
er
e
th
e
R
M
SE
f
o
r
B
P
NN
-
NAR
w
as
0
.
0
0
0
7
8
an
d
B
P
NN
-
N
AR
M
A
w
as
0
.
0
0
0
8
5
as
s
h
o
w
n
in
Fi
g
u
r
e
4
.
T
h
is
m
ea
n
s
t
h
at
t
h
e
b
est
m
o
d
e
l
f
o
r
b
u
ild
in
g
E
n
er
g
y
I
n
d
ex
(
B
E
I
)
d
ata
is
B
P
NN
-
NAR
w
it
h
KW
-
B
P
NN
o
p
tim
izatio
n
w
it
h
co
n
f
i
g
u
r
atio
n
s
i
g
m
o
id
-
li
n
ea
r
3
0
-
30
-
3
0
f
o
r
i
m
p
u
t
lag
s
,
er
r
o
r
lag
s
an
d
h
id
d
en
n
o
d
es
r
esp
ec
tiv
el
y
.
T
h
is
r
esear
c
h
i
s
ex
p
ec
ted
to
s
p
ec
i
f
icall
y
a
s
s
i
s
t
elec
tr
icia
n
i
n
Help
U
n
iv
er
s
it
y
to
w
ar
d
s
lo
ad
f
o
r
ec
asti
n
g
f
o
r
p
o
w
er
s
y
s
te
m
p
lan
n
i
n
g
an
d
o
p
er
atio
n
in
y
ea
r
s
to
co
m
e.
A
ll t
h
e
o
b
j
ec
tiv
es o
f
th
is
r
esear
ch
h
a
v
e
b
ee
n
s
u
cc
e
s
s
f
u
ll
y
ac
h
ie
v
ed
.
T
h
e
f
i
n
al
n
u
m
er
ical
m
o
d
el
to
d
eter
m
i
n
e
en
er
g
y
s
a
v
ed
w
as
T
ab
le
1
.
Var
iab
les I
n
v
o
lv
ed
in
T
h
is
R
esear
ch
V
a
r
i
a
b
l
e
s
D
e
scri
p
t
i
o
n
B
EI
k
W
h
/
m2
/
y
e
a
r
*
b
u
i
l
d
i
n
g
e
n
e
r
g
y
i
n
d
e
x
k
W
h
/
m
2
/
y
e
a
r
C
O
2
S
A
V
E
e
mi
ssi
o
n
e
s o
f
C
O
2
p
e
r
k
W
h
o
f
e
n
e
r
g
y
p
r
o
d
u
c
e
d
EN
ER
G
Y
S
A
V
ED
(
M
W
-
h
r
)
e
l
e
c
t
r
i
c
i
t
y
sav
e
d
M
e
g
a
w
a
t
t
h
o
u
r
s (
M
W
h
)
/
H
o
u
r
s (h
)
M
O
N
EY
S
A
V
E
mo
n
e
y
sav
e
d
i
n
r
i
n
g
g
i
t
mal
a
y
si
a
(
R
M
)
T
h
is
r
esear
ch
i
s
ex
p
ec
ted
to
g
i
v
e
a
s
i
g
n
i
f
ican
t
co
n
tr
ib
u
ti
o
n
an
d
d
e
m
o
n
s
tr
atio
n
i
n
t
h
e
ef
f
o
r
t
o
f
co
u
n
ter
i
n
g
t
h
e
c
u
r
r
en
t
g
lo
b
al
w
ar
m
i
n
g
is
s
u
e
p
ar
allel
to
1
1
th
Ma
la
y
s
ia
P
lan
-
R
MK
1
1
o
b
j
ec
tiv
it
y
.
R
MK
1
1
o
r
also
k
n
o
w
n
a
s
1
1
th
Ma
la
y
s
ia
n
P
lan
is
t
h
e
f
i
n
al
f
i
v
e
y
ea
r
s
p
lan
in
e
x
c
u
r
s
io
n
to
w
ar
d
s
ac
h
ie
v
i
n
g
Vis
io
n
2
0
5
0
.
I
n
th
e
n
ea
r
f
u
t
u
r
e,
th
is
r
esear
ch
c
an
b
e
f
u
r
t
h
er
i
m
p
r
o
v
ed
b
y
ad
a
p
tin
g
t
h
e
tec
h
n
iq
u
es
[
2
7
-
3
0
]
,
an
d
th
e
s
a
m
p
le
s
ize
s
h
o
u
ld
b
e
in
cr
ea
s
ed
.
T
h
e
r
elat
ed
p
r
ev
io
u
s
w
o
r
k
s
ca
n
b
e
r
ef
er
r
ed
in
[
3
1
-
3
5
]
.
-300
000
00
-250
000
00
-200
000
00
-150
000
00
-100
000
00
-500
000
0
0
5000000
1
13
25
37
49
61
73
85
97
109
121
133
145
157
169
181
193
205
217
229
BE
I kW
h
/m2/ye
ar
CO
2 S
A
V
E
E
N
E
R
G
Y
S
A
V
E
D (MW
-h
r)
MO
N
E
Y
S
A
V
E
.
*
8
535
.
8
*
154
.
15
785
.
3030
D
E
N
E
R
G
Y
S
A
V
E
M
O
N
E
Y
S
A
V
E
E
B
E
I
k
W
h
m
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
K
iller
w
h
a
le
-
b
a
ck
p
r
o
p
a
g
a
tio
n
(
K
W
-
B
P
)
a
lg
o
r
ith
m
fo
r
…
(
S
a
a
d
i B
in
A
h
ma
d
K
a
ma
r
u
d
d
in
)
275
T
ab
le
2
.
Desc
r
ip
tiv
e
Statis
tic
s
M
e
a
n
S
t
d
.
D
e
v
i
a
t
i
o
n
N
EN
ER
G
Y
S
A
V
ED
2
0
1
7
M
W
h
r
-
3
8
5
5
.
9
6
7
7
2
0
1
4
6
.
8
6
2
1
7
2
3
8
B
EI
k
W
h
m2
y
e
a
r
4
5
4
.
4
5
5
9
1
3
2
9
.
4
7
0
7
4
2
3
8
C
O
2
S
A
V
E
-
3
0
8
4
7
.
7
4
6
4
1
6
1
1
7
4
.
8
9
9
9
1
2
3
8
M
O
N
EY
S
A
V
E
-
1
4
1
5
7
9
4
.
8
5
8
7
7
3
5
1
2
9
6
.
6
3
3
8
1
2
3
8
T
ab
le
3
.
C
o
ef
f
icie
n
ts
(
Step
w
i
s
e
Me
th
o
d
)
M
o
d
e
l
U
n
st
a
n
d
a
r
d
i
z
e
d
C
o
e
f
f
i
c
i
e
n
t
s
S
t
a
n
d
a
r
d
i
z
e
d
C
o
e
f
f
i
c
i
e
n
t
s
t
S
i
g
.
B
S
t
d
.
Er
r
o
r
B
e
t
a
1
(
C
o
n
st
a
n
t
)
3
0
3
0
.
7
8
5
.
2
9
4
1
0
3
1
4
.
5
5
5
.
0
0
0
B
EI
k
W
h
m2
y
e
a
r
-
1
5
.
1
5
4
.
0
0
1
-
1
.
0
0
0
-
1
0
2
6
9
.
7
2
5
.
0
0
0
M
O
N
EY
S
A
V
E
8
.
5
3
5
E
-
8
.
0
0
0
.
0
0
0
.
3
2
0
.
7
4
9
T
ab
le
4
.
R
MSE
s
o
f
B
P
NN
-
NAR
an
d
B
P
NN
-
N
AR
M
A
b
y
d
if
f
er
en
t a
l
g
o
r
ith
m
s
o
n
B
u
ild
in
g
E
n
er
g
y
I
n
d
e
x
(
B
E
I
)
d
ata
I
n
p
u
t
L
a
g
s
Er
r
o
r
L
a
g
s
H
i
d
d
e
n
N
o
d
e
s
B
P
N
N
KW
-
B
P
N
N
FFA
-
B
P
N
N
PSO
-
B
P
N
N
B
P
N
N
-
N
A
R
B
P
N
N
-
N
A
R
M
A
B
P
N
N
-
N
A
R
B
P
N
N
-
N
A
R
M
A
B
P
N
N
-
N
A
R
B
P
N
N
-
N
A
R
M
A
B
P
N
N
-
N
A
R
B
P
N
N
-
N
A
R
M
A
R
e
f
e
r
e
n
c
e
s
[
2
3
]
[
2
4
]
[
2
5
]
[
2
6
]
5
5
5
0
.
0
0
0
9
7
5
0
.
0
0
1
0
4
0
.
0
0
1
0
4
0
.
0
0
1
4
5
0
.
0
0
1
1
2
0
.
0
0
1
5
4
0
.
0
0
1
1
2
0
.
0
0
1
5
4
10
10
10
0
.
0
0
0
8
7
7
0
.
0
0
1
0
8
0
.
0
0
1
0
5
0
.
0
0
1
4
6
0
.
0
0
1
0
2
0
.
0
0
1
3
3
0
.
0
0
1
0
2
0
.
0
0
1
3
3
15
15
15
0
.
0
0
0
8
5
7
0
.
0
0
1
0
4
0
.
0
0
1
0
5
0
.
0
0
1
4
7
0
.
0
0
0
9
6
0
.
0
0
1
2
0
.
0
0
0
9
6
0
.
0
0
1
2
20
20
20
0
.
0
0
1
0
0
8
0
.
0
0
1
3
8
0
.
0
0
1
1
0
.
0
0
1
5
4
0
.
0
0
0
8
1
0
.
0
0
0
8
9
0
.
0
0
0
8
1
0
.
0
0
0
8
9
25
25
25
0
.
0
0
1
0
1
1
0
.
0
0
1
3
8
0
.
0
0
1
0
6
0
.
0
0
1
4
5
0
.
0
0
0
9
8
0
.
0
0
1
2
4
0
.
0
0
0
9
8
0
.
0
0
1
2
4
30
30
30
0
.
0
0
1
0
1
4
0
.
0
0
1
3
9
0
.
0
0
0
7
8
0
.
0
0
0
8
5
0
.
0
0
1
1
0
.
0
0
1
5
2
0
.
0
0
1
1
0
.
0
0
1
5
2
35
35
35
0
.
0
0
1
0
1
7
0
.
0
0
1
4
0
.
0
0
0
9
8
0
.
0
0
1
2
7
0
.
0
0
1
1
3
0
.
0
0
1
5
9
0
.
0
0
1
1
3
0
.
0
0
1
5
9
40
40
40
0
.
0
0
1
0
2
0
.
0
0
1
4
1
0
.
0
0
1
0
6
0
.
0
0
1
4
6
0
.
0
0
1
1
3
0
.
0
0
1
5
9
0
.
0
0
1
1
3
0
.
0
0
1
5
9
(
a)
(
b
)
Fig
u
r
e
4
.
(
a)
P
er
f
o
r
m
a
n
ce
C
o
m
p
ar
i
s
o
n
s
o
f
N
AR
Mo
d
el
in
T
h
is
R
esear
ch
,
a
n
d
(
b
)
P
e
r
f
o
r
m
an
ce
C
o
m
p
ar
is
o
n
s
o
f
N
A
R
M
A
Mo
d
el
i
n
T
h
is
R
e
s
ea
r
ch
5.
CO
NCLU
SI
O
NS
T
h
is
p
ap
er
h
as
p
r
esen
ted
th
e
p
er
f
o
r
m
a
n
ce
s
o
f
m
u
ltip
le
ev
o
lu
tio
n
ar
y
p
r
o
g
r
a
m
m
i
n
g
tech
n
iq
u
e
s
on
en
er
g
y
-
e
f
f
icie
n
t
d
ata
o
f
Help
Un
i
v
er
s
it
y
,
S
u
b
an
g
2
ca
m
p
u
s
.
T
h
r
o
u
g
h
t
h
e
i
m
p
le
m
e
n
tatio
n
o
n
th
e
B
E
I
d
ataset;
it
ca
n
b
e
h
ig
h
li
g
h
ted
th
at
t
h
e
p
r
o
p
o
s
ed
KW
-
B
P
NN
is
a
f
lex
ib
le
an
d
r
o
b
u
s
t
al
g
o
r
ith
m
t
o
s
o
lv
e
th
e
o
p
ti
m
al
p
o
w
er
s
c
h
ed
u
li
n
g
p
r
o
ce
s
s
in
t
h
e
atte
m
p
t
to
co
n
tr
o
l t
h
e
lo
s
s
i
n
p
o
w
er
s
y
s
te
m
.
W
it
h
o
n
l
y
m
i
n
o
r
m
o
d
i
f
icatio
n
i
n
th
e
B
P
alg
o
r
it
h
m
,
b
etter
r
esu
lts
h
av
e
b
ee
n
ac
h
ie
v
ed
w
h
ich
in
tu
r
n
ca
n
b
e
tr
an
s
lated
i
n
t
o
v
alu
e
-
f
o
r
-
m
o
n
e
y
attr
ib
u
tes.
T
h
e
d
ev
elo
p
ed
o
p
ti
m
ized
N
AR
an
d
N
AR
M
A
m
o
d
els
s
h
o
u
ld
b
e
test
ed
o
n
s
i
m
u
latio
n
d
atase
ts
i
n
0
0.0005
0.001
0.0015
(
5,
5,5)
(
10,
10,10)
(
15,
15,15)
(
20,
20,20)
(
25,
25,25)
(
30,
30,30)
(
35,
35,35)
(
40,
40,40)
N
A
R
BP
N
N
KW
-B
PN
N
F
F
A
-B
PN
N
PSO-B
P
N
N
0
0.0005
0.001
0.0015
0.002
(
5,
5,5)
(
10,
10,10)
(
15,
15,15)
(
20,
20,20)
(
25,
25,25)
(
30,
30,30)
(
35,
35,35)
(
40,
40,40)
N
A
R
M
A
BP
N
N
KW
-B
PN
N
F
F
A
-B
PN
N
PSO-B
P
N
N
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
20
1
9
:
2
7
0
–
2
7
7
276
o
r
d
er
to
o
b
s
er
v
e
th
eir
d
i
v
er
s
i
f
ied
ca
p
ab
ilit
ies.
I
t
i
s
a
g
o
o
d
n
o
te
to
m
e
n
tio
n
th
a
t
t
h
e
d
e
v
e
lo
p
ed
o
p
tim
izatio
n
alg
o
r
ith
m
is
e
f
f
icien
t
o
n
n
eu
r
al
n
et
w
o
r
k
ti
m
e
s
er
ie
s
m
o
d
els.
On
to
p
o
f
th
at,
ap
p
licatio
n
o
f
th
e
p
r
o
p
o
s
ed
r
o
b
u
s
tif
ied
al
g
o
r
ith
m
o
n
b
ig
d
atasets
s
h
o
u
ld
b
e
n
ex
t e
n
d
ea
v
o
u
r
s
.
ACK
NO
WL
E
D
G
M
E
NT
W
e
w
o
u
ld
lik
e
to
d
ed
icate
o
u
r
g
r
ate
f
u
ln
e
s
s
to
Help
U
n
iv
er
s
it
y
f
o
r
s
u
p
p
o
r
tin
g
th
i
s
r
ese
ar
ch
u
n
d
er
I
R
GS
S
tater
Gr
an
t
No
.
1
9
-
04
-
0
0
5
.
No
t
to
b
e
f
o
r
g
o
tten
e
n
d
less
g
r
atit
u
d
e
to
th
e
Ma
in
te
n
a
n
ce
Dep
ar
t
m
e
n
t
o
f
Help
Un
i
v
er
s
it
y
,
Su
b
a
n
g
2
ca
m
p
u
s
f
o
r
th
e
d
ata
s
h
ar
in
g
.
RE
F
E
R
E
NC
E
S
[1
]
W
.
W
.
Ke
ll
o
g
g
,
Cli
ma
te
c
h
a
n
g
e
a
n
d
so
c
iety
:
c
o
n
se
q
u
e
n
c
e
s
o
f
i
n
c
re
a
sin
g
a
tmo
sp
h
e
ric
c
a
rb
o
n
d
io
x
id
e
,
Ro
u
tl
e
d
g
e
,
2
0
1
9
.
[2
]
P
.
Bre
e
z
e
,
Po
we
r g
e
n
e
ra
t
io
n
tec
h
n
o
l
o
g
ies
,
Ne
w
n
e
s,
2
0
1
9
.
[3
]
G
.
T
re
n
c
h
e
r
&
J.
V
a
n
d
e
r
He
ij
d
e
n
,
“
In
str
u
m
e
n
t
in
tera
c
ti
o
n
s
a
n
d
re
latio
n
s
h
ip
s
i
n
p
o
li
c
y
m
i
x
e
s:
A
c
h
iev
in
g
c
o
m
p
le
m
e
n
tarit
y
in
b
u
il
d
i
n
g
e
n
e
rg
y
e
ff
icie
n
c
y
p
o
li
c
ies
in
Ne
w
Yo
rk
,
S
y
d
n
e
y
a
n
d
T
o
k
y
o
,
”
En
e
r
g
y
Res
e
a
rc
h
&
S
o
c
ia
l
S
c
ien
c
e
,
5
4
,
2
0
1
9
,
p
p
.
3
4
-
4
5
.
[4
]
U.
H.
Ob
a
id
e
ll
a
h
,
M
.
Da
n
a
e
e
,
M
.
A
.
A
.
M
a
m
u
n
,
M
.
Ha
sa
n
u
z
z
a
m
a
n
&
N.
A
.
R
a
h
im
,
“
A
n
a
p
p
li
c
a
ti
o
n
o
f
T
P
B
c
o
n
stru
c
ts
o
n
e
n
e
rg
y
-
sa
v
in
g
b
e
h
a
v
io
u
ra
l
in
ten
ti
o
n
a
m
o
n
g
u
n
iv
e
rsity
o
ff
ic
e
b
u
il
d
in
g
o
c
c
u
p
a
n
ts:
a
p
il
o
t
stu
d
y
in
M
a
la
y
sia
n
tro
p
ica
l
c
li
m
a
te,”
J
o
u
rn
a
l
o
f
H
o
u
si
n
g
a
n
d
t
h
e
Bu
il
t
E
n
v
i
ro
n
me
n
t
,
3
4
(2
),
2
0
1
9
,
p
p
.
5
3
3
-
5
6
9
.
[5
]
T
.
S
u
sc
a
,
“
G
r
e
e
n
ro
o
f
s
to
r
e
d
u
c
e
b
u
il
d
in
g
e
n
e
rg
y
u
se
?
A
re
v
ie
w
o
n
k
e
y
stru
c
tu
ra
l
f
a
c
to
rs
o
f
g
r
e
e
n
ro
o
f
s
a
n
d
th
e
i
r
e
ffe
c
ts o
n
u
r
b
a
n
c
li
m
a
te,”
Bu
il
d
i
n
g
a
n
d
En
v
iro
n
me
n
t
,
1
0
6
2
7
3
,
2
0
1
9
.
[6
]
S
a
ra
v
a
n
a
n
(Ed
.
),
“
M
a
lay
sia
-
P
T
M
ZE
O Bu
il
d
i
n
g
,
”
Ro
o
f
a
n
d
Fa
ç
a
d
e
Asia
,
5
,
4
6
,
2
0
0
8
.
[7
]
T
.
K.
Ru
d
e
l,
S
h
o
c
k
s,
S
t
a
tes
,
a
n
d
S
u
sta
in
a
b
il
it
y
:
T
h
e
Or
ig
i
n
s
o
f
Ra
d
ica
l
E
n
v
iro
n
me
n
t
a
l
Refo
rm
s
.
Ox
f
o
rd
Un
iv
e
rsit
y
P
re
ss
,
2
0
1
9
.
[8
]
Á
.
Ha
ll
d
ó
rss
o
n
,
C.
S
u
n
d
g
re
n
&
J.
W
e
h
n
e
r,
2
5
S
u
st
a
in
a
b
le
su
p
p
ly
c
h
a
i
n
s
a
n
d
e
n
e
rg
y
:
wh
e
re
‘p
la
n
e
t’me
e
ts
‘p
ro
fi
t’
,
Ha
n
d
b
o
o
k
o
n
t
h
e
S
u
sta
i
n
a
b
le S
u
p
p
ly
Ch
a
in
,
4
4
4
,
2
0
1
9
.
[9
]
V
.
Y.
T
a
m
&
K.
N.
L
e
,
S
u
sta
in
a
b
le
C
o
n
stru
c
ti
o
n
T
e
c
h
n
o
lo
g
ies
:
L
if
e
-
c
y
c
le
Asse
ss
m
e
n
t
,
Bu
tt
e
rw
o
rth
-
He
in
e
m
a
n
n
2
0
1
9
.
[1
0
]
P
.
Jia
n
g
,
A
n
a
l
y
sis
o
f
n
a
ti
o
n
a
l
a
n
d
lo
c
a
l
e
n
e
rg
y
-
e
ff
icie
n
c
y
d
e
sig
n
sta
n
d
a
rd
s
i
n
th
e
p
u
b
li
c
b
u
il
d
in
g
se
c
to
r
i
n
Ch
in
a
,
”
E
n
e
rg
y
f
o
r
S
u
s
tain
a
b
le D
e
v
e
lo
p
m
e
n
t,
1
5
(4
),
2
0
1
1
,
p
p
.
4
4
3
-
4
5
0
.
[1
1
]
C.
J.
Kib
e
rt,
S
u
sta
i
n
a
b
le co
n
stru
c
ti
o
n
:
g
re
e
n
b
u
il
d
i
n
g
d
e
sig
n
a
n
d
d
e
li
v
e
ry
,
Jo
h
n
W
il
e
y
&
S
o
n
s,
2
0
1
6
.
[1
2
]
J.
S
.
Kh
a
n
,
R.
Zak
a
ria,
S
.
M
.
S
h
a
m
su
d
in
,
N.
I
.
A
.
A
b
id
in
,
S
.
R.
S
a
h
a
m
ir,
D.
N.
A
b
b
a
s
&
E.
Am
in
u
d
in
,
“
Ev
o
l
u
ti
o
n
to
Em
e
rg
e
n
c
e
o
f
G
re
e
n
Bu
il
d
i
n
g
s: A
Re
v
ie
w
,
”
Ad
min
istra
t
ive
S
c
ien
c
e
s
,
9
(1
)
,
6
,
2
0
1
9
.
[1
3
]
S
.
C.
Ch
u
a
&
T
.
H.
Oh
,
“
G
r
e
e
n
p
ro
g
re
ss
a
n
d
p
ro
sp
e
c
t
in
M
a
la
y
sia
,
”
Ren
e
wa
b
le
a
n
d
S
u
st
a
in
a
b
le
En
e
rg
y
Rev
iews
,
1
5
(6
)
,
2
0
1
1
,
p
p
.
2
8
5
0
-
2
8
6
1
.
[1
4
]
H.
L
e
o
n
g
,
“
Risin
g
c
o
st
o
f
e
lec
t
ricit
y
g
e
n
e
ra
ti
o
n
-
Bu
si
n
e
ss
Ne
w
s
|
T
h
e
S
tar
On
li
n
e
,
”
re
tri
e
v
e
d
f
ro
m
h
tt
p
s:/
/www
.
th
e
sta
r.
c
o
m
.
m
y
/b
u
sin
e
ss
/b
u
sin
e
ss
-
n
e
w
s/2
0
1
7
/0
4
/
0
1
/ri
sin
g
-
c
o
st
-
of
-
e
lec
tri
c
it
y
-
g
e
n
e
ra
ti
o
n
/
,
2
0
1
9
.
[1
5
]
I.
W
.
W
o
o
d
s,
K.
H.
Ro
b
e
rts
&
R.
K.
Ra
c
in
e
,
“
Ne
u
ra
l
Ne
u
ra
l
Ne
tw
o
rk
,
”
M
a
jo
r
Qu
a
li
f
y
in
g
P
ro
jec
ts,
2
0
1
9
.
[1
6
]
R.
M
ii
k
k
u
lain
e
n
,
J.
L
ian
g
,
E.
M
e
y
e
rso
n
,
A
.
Ra
w
a
l,
D.
F
in
k
,
O.
F
ra
n
c
o
n
,
.
.
.
&
B.
Ho
d
jat,
“
Ev
o
lv
in
g
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
s,”
Arti
fi
c
ia
l
In
tell
ig
e
n
c
e
in
t
h
e
Ag
e
o
f
Ne
u
r
a
l
Ne
two
rk
s a
n
d
Bra
i
n
C
o
mp
u
ti
n
g
,
2
0
1
9
,
p
p
.
2
9
3
-
3
1
2
.
[1
7
]
D.
S
p
ieg
e
lh
a
lt
e
r.
T
h
e
Art
o
f
S
ta
t
isti
c
s: L
e
a
rn
i
n
g
fr
o
m Da
t
a
,
P
e
n
g
u
i
n
UK
,
2
0
1
9
.
[1
8
]
T
.
L
u
n
a
,
J.
Ri
b
a
u
,
D.
F
ig
u
e
ired
o
&
R.
A
lv
e
s,
“
I
m
p
ro
v
in
g
e
n
e
rg
y
e
ff
icie
n
c
y
in
w
a
ter
su
p
p
ly
s
y
ste
m
s
w
it
h
p
u
m
p
sc
h
e
d
u
li
n
g
o
p
t
im
iza
ti
o
n
,
”
J
o
u
rn
a
l
o
f
c
lea
n
e
r p
ro
d
u
c
ti
o
n
,
2
1
3
,
2
0
1
9
,
p
p
.
3
4
2
-
3
5
6
.
[1
9
]
Y.
L
i,
N.
Z
h
u
&
B.
Qin
,
“
W
h
a
t
Aff
e
c
ts
th
e
P
r
o
g
re
ss
a
n
d
T
ra
n
sf
o
rm
a
ti
o
n
o
f
Ne
w
Re
sid
e
n
ti
a
l
Bu
il
d
in
g
En
e
rg
y
Eff
icie
n
c
y
P
ro
m
o
ti
o
n
in
C
h
in
a
:
S
tak
e
h
o
ld
e
rs’
P
e
rc
e
p
ti
o
n
s.”
En
e
r
g
i
e
s
,
1
2
(
6
),
2
0
1
9
,
p
p
.
1
0
2
7
.
[2
0
]
S
.
N.
Ka
d
ir,
N.
M
.
Tah
ir,
I.
M
.
Ya
ss
in
&
A
.
Zab
id
i,
“
M
a
la
y
sia
n
to
u
rism
in
tere
st
f
o
re
c
a
stin
g
u
sin
g
n
o
n
li
n
e
a
r
a
u
to
-
re
g
re
ss
i
v
e
m
o
v
in
g
a
v
e
ra
g
e
(N
ARMA
)
m
o
d
e
l,
”
2
0
1
4
IEE
E
S
y
mp
o
siu
m
o
n
W
ire
les
s
T
e
c
h
n
o
l
o
g
y
a
n
d
A
p
p
l
ica
ti
o
n
s
(
IS
W
T
A)
,
2
0
1
4
,
p
p
.
1
9
3
-
1
9
8
).
[2
1
]
I.
M
.
Ya
ss
in
,
A
.
Zab
id
i,
M
.
K.
M
.
S
a
ll
e
h
&
N.
A
.
Kh
a
li
d
,
“
M
a
la
y
s
ian
to
u
rism
in
tere
st
f
o
re
c
a
stin
g
u
sin
g
No
n
li
n
e
a
r
A
u
to
-
Re
g
re
ss
i
v
e
(N
AR)
m
o
d
e
l,
”
2
0
1
3
IEE
E
3
rd
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
y
ste
m E
n
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
2
0
1
3
,
p
p
.
3
2
-
3
6
).
[2
2
]
A
.
Ru
sie
c
k
i,
“
Ro
b
u
st
lea
rn
i
n
g
a
lg
o
rit
h
m
b
a
se
d
o
n
it
e
ra
ti
v
e
lea
st
m
e
d
ian
o
f
sq
u
a
re
s,”
Ne
u
ra
l
p
ro
c
e
ss
in
g
letter
s
,
3
6
(
2
),
2
0
1
2
,
p
p
.
1
4
5
-
1
6
0
.
[2
3
]
N.
A
.
M
.
G
h
a
n
i,
S
.
B.
A
.
Ka
m
a
ru
d
d
i
n
,
N.
M
.
Ra
m
li
&
A
.
S
e
l
a
m
a
t
,
“
A
u
th
e
n
ti
c
a
ti
n
g
A
NN
-
N
A
R
a
n
d
AN
N
-
NA
RM
A
m
o
d
e
ls
u
ti
li
z
in
g
b
o
o
tstrap
tec
h
n
i
q
u
e
s,”
Asia
n
Co
n
fer
e
n
c
e
o
n
In
telli
g
e
n
t
In
f
o
rm
a
ti
o
n
a
n
d
D
a
ta
b
a
s
e
S
y
ste
ms
,
2
0
1
7
,
p
p
.
7
6
1
-
7
7
1
.
[2
4
]
T
.
R.
Biy
a
n
to
,
S
.
Ira
w
a
n
,
H.
Y.
F
e
b
rian
to
,
N.
A
f
d
a
n
n
y
,
A
.
H.
Ra
h
m
a
n
,
K.
S
.
G
u
n
a
w
a
n
,
.
.
.
&
T
.
N.
Be
th
ian
a
,
“
Kill
e
r
w
h
a
le
a
lg
o
rit
h
m
:
a
n
a
lg
o
rit
h
m
in
sp
ired
b
y
th
e
li
f
e
o
f
k
il
ler
w
h
a
le,”
Pro
c
e
d
ia
c
o
mp
u
ter
sc
ien
c
e
,
1
2
4
,
2
0
1
7
,
p
p
.
1
5
1
-
1
5
7
.
[2
5
]
N.
A
.
M
.
G
h
a
n
i,
S
.
B.
A
.
K
a
m
a
r
u
d
d
in
,
N.
M
.
Ra
m
li
,
I.
M
u
sirin
&
H.
Ha
sh
i
m
,
"
M
o
d
if
ied
BP
NN
v
ia
Itera
ted
L
e
a
st
M
e
d
ia
n
S
q
u
a
re
s,
P
a
rti
c
le
S
w
a
rm
Op
ti
m
iza
ti
o
n
a
n
d
F
iref
ly
A
l
g
o
rit
h
m
,
”
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
C
o
mp
u
ter
S
c
ien
c
e
,
8
(3
),
2
0
1
7
,
p
p
.
7
7
9
-
7
8
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
K
iller
w
h
a
le
-
b
a
ck
p
r
o
p
a
g
a
tio
n
(
K
W
-
B
P
)
a
lg
o
r
ith
m
fo
r
…
(
S
a
a
d
i B
in
A
h
ma
d
K
a
ma
r
u
d
d
in
)
277
[2
6
]
S
.
B.
A
.
Ka
m
a
ru
d
d
in
,
S
.
M
.
T
o
lo
s,
P
.
C
.
He
e
,
N.
A
.
M
.
G
h
a
n
i,
N.
M
.
Ra
m
li
,
N.
B.
M
.
Na
sir,
.
.
.
&
M
.
S
.
Hu
q
,
“
T
h
e
q
u
a
d
rice
p
s
m
u
sc
le
o
f
k
n
e
e
jo
in
t
m
o
d
e
ll
in
g
Us
in
g
H
y
b
rid
P
a
rti
c
l
e
S
w
a
r
m
Op
ti
m
iz
a
ti
o
n
-
Ne
u
ra
l
Ne
tw
o
rk
(P
S
O
-
NN
),
”
J
o
u
rn
a
l
o
f
Ph
y
sic
s: Co
n
fer
e
n
c
e
S
e
rie
s
,
V
o
l.
8
1
9
,
No
.
1
,
2
0
1
7
,
p
.
0
1
2
0
2
9
.
[2
7
]
E.
A
.
L
i
m
e
t
a
l.
,
“
A
n
I
m
p
ro
v
e
d
Ra
d
ial
Ba
sis
F
u
n
c
ti
o
n
Ne
tw
o
rk
s
Ba
se
d
o
n
Qu
a
n
tu
m
Ev
o
lu
ti
o
n
a
ry
A
l
g
o
rit
h
m
f
o
r
T
ra
in
in
g
No
n
li
n
e
a
r
Da
tas
e
ts”
,
I
AES
In
ter
n
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
A
rti
f
i
c
ial
In
telli
g
e
n
c
e
(IJ
-
A
I),
V
o
l
8
,
N
o
2
,
2
0
1
9
.
[2
8
]
S
.
K.
Da
s
e
t
a
l.
,
“
De
v
e
lo
p
m
e
n
t
o
f
P
a
th
P
lan
n
in
g
A
lg
o
rit
h
m
o
f
Ce
n
ti
p
e
d
e
In
s
p
ired
W
h
e
e
led
R
o
b
o
t
in
P
re
se
n
c
e
o
f
S
tatic
a
n
d
M
o
v
i
n
g
Ob
sta
c
les
Us
in
g
M
o
d
if
ied
Crit
ica
l
-
S
n
a
k
e
B
u
g
A
lg
o
rit
h
m
”
,
I
A
ES
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
A
rti
f
icia
l
In
telli
g
e
n
c
e
(IJ
-
A
I),
V
o
l
8
,
N
o
2
,
2
0
1
9
.
[2
9
]
X
.
Hu
a
n
g
,
X.
Zen
g
,
R.
Ha
n
a
n
d
X
.
W
a
n
g
,
“
A
n
e
n
h
a
n
c
e
d
h
y
b
rid
ize
d
a
rti
f
icia
l
b
e
e
c
o
lo
n
y
a
lg
o
rit
h
m
f
o
r
o
p
ti
m
iza
ti
o
n
p
ro
b
lem
s,”
IAE
S
In
t
e
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Arti
fi
c
i
a
l
In
telli
g
e
n
c
e
(
IJ
-
AI)
,
Vo
l.
8
,
N
o
.
1
,
2
0
1
9
,
p
p
.
8
7
-
94.
[3
0
]
K.
L
e
n
in
,
“
S
h
ri
n
k
a
g
e
o
f
re
a
l
p
o
w
e
r
lo
ss
b
y
e
n
rich
e
d
b
ra
in
st
o
r
m
o
p
ti
m
iz
a
ti
o
n
a
lg
o
rit
h
m
”
,
IA
E
S
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
A
rti
f
icia
l
In
telli
g
e
n
c
e
(IJ
-
A
I),
V
o
l.
8
,
N
o
.
1
,
2
0
1
9
,
p
p
.
1
-
6.
[3
1
]
S
.
B.
A
.
Ka
m
a
ru
d
d
in
,
N.
A
.
M
.
G
h
a
n
i
&
N.
M
.
Ra
m
li
,
“
T
h
e
Im
p
ro
v
e
d
B
P
NN
-
NA
R
a
n
d
B
P
NN
-
N
A
RM
A
M
o
d
e
ls
o
n
M
a
lay
sia
n
Ag
g
re
g
a
te Co
st I
n
d
ice
s
w
it
h
Ou
tl
y
in
g
Da
ta,”
J
u
rn
a
l
T
e
k
n
o
lo
g
i
,
7
8
,
2
0
1
6
,
p
p
.
1
2
-
3.
[3
2
]
S
.
B.
A
.
Ka
m
a
ru
d
d
in
,
N.
A
.
M
.
G
h
a
n
i
&
N.
M
.
Ra
m
li
,
“
T
h
e
e
n
h
a
n
c
e
d
BP
NN
-
NA
R
a
n
d
BP
NN
-
N
A
RM
A
m
o
d
e
ls
f
o
r
M
a
l
a
y
sia
n
a
g
g
re
g
a
te
c
o
st
in
d
ice
s
w
it
h
o
u
tl
y
in
g
d
a
ta,”
2
0
1
5
I
EE
E
Co
n
fer
e
n
c
e
o
n
e
-
L
e
a
rn
in
g
,
e
-
M
a
n
a
g
e
me
n
t
a
n
d
e
-
S
e
rv
ice
s (
IC3
e
)
,
2
0
1
5
,
p
p
.
4
3
-
48.
[3
3
]
S
.
B.
A
.
K
a
m
a
ru
d
d
in
,
N.
A
.
M
.
G
h
a
n
i
&
N.
M
.
Ra
m
li
,
“
Co
n
s
o
li
d
a
ted
Ba
c
k
p
ro
p
a
g
a
ti
o
n
Ne
u
ra
l
Ne
t
w
o
rk
f
o
r
M
a
la
y
sia
n
Co
n
str
u
c
ti
o
n
Co
sts
In
d
ice
s
Da
ta
w
it
h
Ou
tl
iers
P
ro
b
lem
,
”
Per
ta
n
ika
J
o
u
r
n
a
l
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
l
o
g
y
,
2
6
(1
),
2
0
1
8
.
[3
4
]
N.
A
.
M
.
G
h
a
n
i,
S
.
B.
A
.
Ka
m
a
ru
d
d
i
n
,
N.
M
.
Ra
m
li
,
N.
B.
M
.
Na
sir,
B.
S
.
B.
K.
Ka
d
e
r
&
M
.
S
.
Hu
q
,
“
T
h
e
q
u
a
d
rice
p
s
m
u
sc
le
o
f
k
n
e
e
jo
in
t
m
o
d
e
ll
in
g
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
a
p
p
ro
a
c
h
:
P
a
rt
1
,
”
2
0
1
6
IEE
E
C
o
n
fer
e
n
c
e
o
n
e
-
L
e
a
rn
in
g
,
e
-
M
a
n
a
g
e
me
n
t
a
n
d
e
-
S
e
rv
ice
s
(
IC3
e
)
,
2
0
1
6
,
p
p
.
5
2
-
5
7
.
[
3
5
]
N.
A
.
M
.
G
h
a
n
i,
S
.
B.
A
.
Ka
m
a
ru
d
d
i
n
,
N.
M
.
Ra
m
li
,
N.
B.
M
.
Na
sir,
B.
S
.
B.
K.
Ka
d
e
r
&
M
.
S
.
Hu
q
,
“
T
h
e
q
u
a
d
rice
p
s
m
u
sc
le
o
f
k
n
e
e
jo
in
t
m
o
d
e
ll
in
g
u
sin
g
n
e
u
ra
l
n
e
tw
o
r
k
a
p
p
ro
a
c
h
:
P
a
rt
2
,
”
2
0
1
6
IEE
E
Co
n
fer
e
n
c
e
o
n
Op
e
n
S
y
ste
ms
(
ICOS
)
,
2
0
1
6
,
p
p
.
5
3
-
58.
Evaluation Warning : The document was created with Spire.PDF for Python.