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.
9
,
No
.
1
,
Ma
r
ch
2
0
2
0
,
p
p
.
100
~
108
I
SS
N:
2252
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
9
.i
1
.
p
p
100
-
1
0
8
100
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
M
o
delling
and co
ntrol o
f
fouling
in
sub
m
erged
m
e
mbra
ne
bio
reacto
r using
neura
l net
w
o
rk
in
ternal
m
o
del
co
nt
ro
l
Nura
ziza
h M
a
hm
o
d
1
,
No
rha
liza
Abdu
l Wa
ha
b
2
,
M
uh
a
mm
a
d
Sa
ni G
a
y
a
3
1,
2
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
lay
sia
,
8
1
3
1
0
S
k
u
d
a
i,
Jo
h
o
r
,
M
a
lay
sia
3
Ka
n
o
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
W
u
d
il
&
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Nig
e
ria
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
1
4
,
2
0
1
9
R
ev
i
s
ed
J
an
2
8
,
2
0
20
A
cc
ep
ted
Feb
11
,
2
0
20
M
e
m
b
ra
n
e
b
io
re
a
c
to
r
(M
BR)
is
o
n
e
o
f
th
e
b
e
st
so
lu
ti
o
n
s
f
o
r
w
a
t
e
r
a
n
d
w
a
ste
w
a
ter
trea
t
m
e
n
t
s
y
ste
m
s
in
p
ro
d
u
c
i
n
g
h
ig
h
q
u
a
li
ty
e
ff
lu
e
n
t
th
a
t
m
e
e
t
s
it
s
sta
n
d
a
rd
re
g
u
latio
n
s.
Ho
w
e
v
e
r,
f
o
u
li
n
g
is
o
n
e
o
f
th
e
m
a
in
issu
e
s
in
m
e
m
b
ra
n
e
f
il
tratio
n
f
o
r
m
e
m
b
ra
n
e
b
io
re
a
c
to
r
sy
ste
m
.
T
h
e
p
re
d
ictio
n
o
f
f
o
u
li
n
g
is
c
ru
c
ial
in
th
e
m
e
m
b
r
a
n
e
b
io
re
a
c
to
r
c
o
n
tr
o
l
sy
ste
m
d
e
sig
n
.
T
h
is
p
a
p
e
r
p
re
se
n
ts
a
n
i
n
telli
g
e
n
c
e
m
o
d
e
li
n
g
s
y
ste
m
so
c
a
ll
e
d
a
rti
ficia
l
n
e
u
ra
l
n
e
tw
o
rk
(
A
NN
).
T
h
e
f
e
e
d
f
o
rwa
rd
n
e
u
ra
l
n
e
tw
o
rk
(F
F
NN
),
r
a
d
ial
b
a
sis
f
u
n
c
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
(RBF
NN
)
a
n
d
n
o
n
li
n
e
a
r
a
u
to
re
g
re
ss
iv
e
e
x
o
g
e
n
o
u
s
n
e
u
ra
l
n
e
tw
o
rk
(N
A
RX
NN
)
a
re
a
p
p
li
e
d
to
m
o
d
e
l
th
e
su
b
m
e
r
g
e
d
M
BR
f
il
tratio
n
s
y
ste
m
.
T
h
e
si
m
u
latio
n
re
su
lt
s
sh
o
w
g
o
o
d
p
re
d
icti
o
n
s
f
o
r
a
ll
m
e
th
o
d
s
w
h
ich
th
e
h
ig
h
e
st
p
e
rfo
rm
a
n
c
e
o
f
th
e
m
o
d
e
l
g
iv
e
n
b
y
RBF
NN
.
Ba
se
d
o
n
th
e
d
e
v
e
lo
p
e
d
m
o
d
e
ls,
th
e
n
e
u
ra
l
n
e
tw
o
rk
in
tern
a
l
m
o
d
e
l
c
o
n
tro
l
(NN
IM
C)
is
im
p
lem
e
n
ted
to
c
o
n
tr
o
l
f
o
u
l
in
g
d
e
v
e
lo
p
m
e
n
t
in
m
e
m
b
ra
n
e
f
il
tratio
n
p
r
o
c
e
ss
.
T
h
re
e
d
if
fe
re
n
t
c
o
n
tro
l
stru
c
t
u
re
s
o
f
th
e
N
NIMC
a
re
p
ro
p
o
se
d
.
T
h
e
F
F
NN
IM
C,
RBF
NN
IM
C
a
n
d
N
A
RX
NN
IM
C
c
o
n
tro
ll
e
rs are
c
o
m
p
a
re
d
to
th
e
c
o
n
v
e
n
ti
o
n
a
l
IM
C.
T
h
e
RBF
NN
IM
C
h
a
s
a
su
p
e
rio
r
p
e
rf
o
r
m
a
n
c
e
b
o
th
i
n
trac
k
in
g
a
n
d
d
istu
r
b
a
n
c
e
re
jec
ti
o
n
s.
K
ey
w
o
r
d
s
:
A
N
N
FF
NN
Fo
u
li
n
g
I
n
ter
n
al
m
o
d
el
co
n
tr
o
l
Me
m
b
r
an
e
b
io
r
ea
cto
r
NARXN
N
R
B
FNN
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
No
r
h
aliza
A
b
d
u
l W
ah
ab
,
Sch
o
o
l o
f
E
lectr
ical
E
n
g
i
n
ee
r
i
n
g
,
Fac
u
lt
y
o
f
E
n
g
i
n
ee
r
i
n
g
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i
Ma
la
y
s
ia
,
8
1
3
1
0
Sk
u
d
ai,
J
o
h
o
r
,
Ma
lay
s
i
a.
E
m
ail: a
liza
@
f
k
e.
u
t
m
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Hig
h
co
n
ce
r
n
o
n
t
h
e
q
u
alit
y
o
f
w
ater
an
d
w
aste
w
ater
h
as
led
to
m
o
r
e
r
esear
ch
o
n
tr
ea
t
m
en
t
tech
n
o
lo
g
y
.
Me
m
b
r
a
n
e
b
io
r
ea
cto
r
(
MB
R
)
is
o
n
e
o
f
th
e
tech
n
o
lo
g
ies
to
r
ep
lace
co
n
v
e
n
tio
n
al
ac
ti
v
ated
s
lu
d
g
e
(
C
A
S)
b
ec
au
s
e
MB
R
ca
n
b
e
class
i
f
ied
a
s
t
h
e
b
es
t
alter
n
ativ
e
s
o
lu
t
io
n
.
Sev
er
al
ad
v
a
n
tag
e
s
h
a
v
e
b
ee
n
d
is
co
v
er
ed
b
y
u
s
i
n
g
MB
R
s
y
s
te
m
o
v
er
co
n
v
e
n
tio
n
al
tec
h
n
o
lo
g
ies
[
1
]
.
T
h
e
s
y
s
te
m
h
as
b
ee
n
v
er
i
f
ied
to
b
e
v
er
y
co
m
p
e
ten
t
s
i
n
ce
it
ab
le
to
g
i
v
e
b
etter
tr
ea
t
m
en
t
in
w
a
s
te
w
ater
i
n
ter
m
o
f
p
r
o
d
u
cin
g
g
o
o
d
an
d
h
i
g
h
q
u
alit
y
o
f
ef
f
l
u
e
n
t.
T
h
e
MB
R
tech
n
o
lo
g
y
i
s
a
co
m
b
in
at
io
n
o
f
b
io
lo
g
ical
p
r
o
ce
s
s
a
n
d
f
ilt
r
atio
n
s
y
s
te
m
.
T
h
e
m
e
m
b
r
a
n
e
f
iltra
tio
n
s
y
s
te
m
i
s
a
co
m
p
le
x
p
r
o
ce
s
s
an
d
h
a
r
d
to
b
e
m
o
d
elled
.
T
h
e
f
iltr
atio
n
s
y
s
te
m
s
s
till
s
tr
u
g
g
lin
g
f
r
o
m
m
a
n
y
i
s
s
u
es
s
u
ch
as
f
o
u
li
n
g
an
d
en
er
g
y
ef
f
icie
n
c
y
[
2
-
5
]
.
Fo
u
lin
g
ca
n
b
e
d
eter
m
i
n
ed
as
u
n
d
es
ir
ab
le
o
f
th
e
ac
c
u
m
u
l
atio
n
o
f
s
u
b
s
ta
n
ce
s
s
u
ch
as
co
llo
id
al,
p
ar
ticu
late,
s
o
lu
te
m
ater
ial
a
n
d
m
icr
o
o
r
g
an
i
s
m
o
n
t
h
e
m
e
m
b
r
an
e
d
u
r
in
g
f
iltra
tio
n
p
r
o
ce
s
s
[
6
]
.
Fo
u
lin
g
ca
n
ca
u
s
e
b
lo
c
k
ag
e
o
f
m
e
m
b
r
an
e
s
w
h
er
e
th
e
m
e
m
b
r
an
e
p
o
r
e
w
i
ll
b
e
b
lo
ck
ed
b
y
s
o
lid
m
ater
i
al.
W
h
en
t
h
is
p
h
en
o
m
e
n
o
n
o
cc
u
r
s
,
th
e
p
er
m
ea
te
f
l
u
x
w
ill
d
ec
li
n
e
a
n
d
ca
u
s
e
r
ap
id
in
cr
e
m
e
n
t
i
n
tr
a
n
s
m
e
m
b
r
an
e
p
r
ess
u
r
e
(
T
MP
)
.
Fo
u
lin
g
also
ca
u
s
ed
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
Mo
d
ellin
g
a
n
d
co
n
tr
o
l
o
f fo
u
li
n
g
in
s
u
b
merg
ed
mem
b
r
a
n
e
b
i
o
r
e
a
cto
r
u
s
in
g
…
(
N
o
r
h
a
liz
a
A
b
d
u
l W
a
h
a
b
)
101
in
cr
e
m
e
n
t
o
f
h
y
d
r
au
l
ic
r
esis
t
an
ce
in
t
h
e
f
iltra
tio
n
s
y
s
te
m
an
d
if
n
o
t
co
n
tr
o
lled
w
ill
c
au
s
e
to
m
e
m
b
r
a
n
e
d
am
a
g
e.
T
h
e
d
ev
elo
p
m
en
t
o
f
r
eliab
le
p
r
ed
ictio
n
m
o
d
el
f
o
r
m
e
m
b
r
an
e
f
il
tr
atio
n
s
y
s
te
m
i
s
i
m
p
o
r
ta
n
t
t
o
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
te
m
[7
-
8
]
.
T
o
av
o
id
f
lu
x
d
ec
lin
e
in
t
h
e
M
B
R
f
iltra
tio
n
p
r
o
ce
s
s
,
a
r
eliab
le
f
ee
d
b
ac
k
co
n
tr
o
l
m
et
h
o
d
is
n
e
ed
ed
.
T
h
is
m
eth
o
d
r
eq
u
ir
es
an
ac
ce
p
tab
le
d
eg
r
ee
o
f
m
o
d
el
ac
cu
r
ac
y
an
d
m
o
d
e
l
r
eliab
ilit
y
to
e
n
s
u
r
e
t
h
e
co
n
tr
o
ller
is
at
th
e
d
esire
d
p
er
f
o
r
m
an
ce
.
I
n
tell
ig
e
n
ce
m
o
d
elin
g
tech
n
iq
u
e
w
h
ich
is
ar
tif
ici
al
n
e
u
r
al
n
et
w
o
r
k
(
A
N
N)
is
u
s
ed
to
m
o
d
el
t
h
e
d
ev
el
o
p
ed
s
u
b
m
er
g
ed
MB
R
f
iltra
ti
o
n
s
y
s
te
m
[
9
]
.
A
N
N
is
w
id
el
y
u
s
ed
a
n
d
a
m
o
n
g
t
h
e
m
o
s
t
p
o
p
u
lar
al
g
o
r
ith
m
f
o
r
m
o
d
eli
n
g
m
e
m
b
r
an
e
f
iltra
tio
n
s
y
s
te
m
.
T
h
r
ee
d
if
f
er
e
n
t
s
tr
u
c
tu
r
es
o
f
A
N
N
s
u
ch
as
r
ad
ial
b
asis
f
u
n
ctio
n
n
eu
r
al
n
et
w
o
r
k
(
R
B
FNN)
,
m
u
l
tila
y
er
p
er
ce
p
tr
o
n
n
eu
r
al
n
et
w
o
r
k
a
n
d
g
e
n
er
al
r
eg
r
ess
io
n
n
eu
r
al
n
et
w
o
r
k
h
av
e
b
ee
n
u
s
ed
i
n
m
o
d
elin
g
o
f
f
iltra
tio
n
s
y
s
te
m
f
o
r
s
y
n
t
h
etic
w
as
te
w
ater
tr
ea
t
m
en
t
[
10
]
.
A
ll
th
r
ee
s
tr
u
ct
u
r
es
g
iv
e
b
etter
p
r
ed
ictio
n
o
f
th
e
T
MP
p
r
o
f
ile
d
u
r
in
g
t
h
e
p
r
o
ce
s
s
o
f
f
il
tr
atio
n
.
W
o
r
k
b
y
[
11
]
ap
p
lied
th
e
R
B
FNN
to
m
o
d
el
th
e
e
f
f
l
u
en
t
q
u
al
it
y
p
ar
am
eter
s
o
f
an
SMB
R
tr
ea
tin
g
co
m
b
i
n
ed
m
u
n
icip
al
an
d
in
d
u
s
tr
ial
w
a
s
te
w
ater
.
T
h
e
b
est
r
es
u
lt
s
s
h
o
w
ed
th
at
th
e
test
i
n
g
a
n
d
tr
ain
i
n
g
p
r
o
ce
d
u
r
e
b
y
R
B
FNN
w
er
e
s
u
cc
es
s
f
u
l.
T
h
e
R
B
FNN
h
as
a
l
s
o
b
ee
n
s
u
cc
ess
f
u
ll
y
ap
p
lied
f
o
r
s
o
lv
in
g
d
y
n
a
m
ic
s
y
s
te
m
p
r
o
b
le
m
s
i
n
[
12
-
13
]
a
n
d
it
ca
n
p
r
ed
ict
th
e
d
y
n
a
m
ic
b
eh
av
io
u
r
d
ir
ec
tl
y
f
r
o
m
i
n
p
u
t
an
d
o
u
tp
u
t
d
ata.
I
n
ad
d
itio
n
,
in
[
14
]
d
ev
elo
p
ed
t
w
o
t
y
p
e
s
o
f
f
ee
d
f
o
r
w
ar
d
ar
tif
i
cial
n
et
w
o
r
k
w
h
ic
h
ar
e
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
an
d
r
ad
ial
b
asis
f
u
n
ctio
n
to
ac
h
ie
v
e
o
f
th
is
w
o
r
k
.
T
h
e
s
elec
tio
n
o
f
r
ad
ial
b
asis
f
u
n
ctio
n
a
n
d
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
ar
e
b
ec
au
s
e
o
f
t
h
eir
ab
ilit
y
to
d
etec
t
co
m
p
le
x
n
o
n
li
n
ea
r
r
el
atio
n
s
h
ip
s
i
n
t
h
e
d
a
ta,
r
ep
r
esen
ti
n
g
t
w
o
d
i
f
f
er
en
t
ap
p
r
o
ac
h
es
to
s
o
lv
in
g
p
r
o
b
lem
s
.
T
h
e
r
esu
lt
s
h
o
w
th
at
AN
N
tech
n
iq
u
e
h
a
v
e
a
g
o
o
d
p
er
f
o
r
m
a
n
ce
an
d
h
i
g
h
ac
cu
r
ac
y
.
W
o
r
k
b
y
[
15
-
16
]
d
em
o
n
s
tr
ated
R
B
FNN
to
p
r
ed
ict
th
e
in
ter
f
ac
ial
i
n
ter
ac
tio
n
s
w
i
th
r
an
d
o
m
l
y
r
o
u
g
h
m
e
m
b
r
a
n
e
s
u
r
f
ac
e.
T
h
e
p
r
o
p
o
s
ed
R
B
FNN
m
e
th
o
d
h
as
b
r
o
ad
ap
p
licatio
n
p
r
o
s
p
ec
ts
in
m
e
m
b
r
a
n
e
f
o
u
li
n
g
a
n
d
in
ter
f
ac
e
b
eh
a
v
io
u
r
r
esea
r
ch
.
T
h
e
r
o
b
u
s
t
R
B
FNN
p
r
o
p
o
s
ed
p
av
ed
a
n
e
w
w
a
y
to
s
t
u
d
y
m
e
m
b
r
a
n
e
f
o
u
li
n
g
i
n
MB
R
s
.
I
n
p
r
o
ce
s
s
co
n
tr
o
l,
in
ter
n
al
m
o
d
el
co
n
tr
o
l
(
I
MC)
is
o
f
te
n
u
s
ed
d
u
e
to
its
s
i
m
p
licit
y
an
d
g
o
o
d
d
is
tu
r
b
an
ce
eli
m
i
n
atio
n
.
T
h
e
ap
p
licatio
n
o
f
I
MC
co
n
tr
o
ller
h
as
b
ee
n
e
s
tab
lis
h
ed
in
m
an
y
i
n
d
u
s
tr
ial
ap
p
licatio
n
s
.
I
MC
tec
h
n
iq
u
es
b
elo
n
g
to
a
v
er
y
s
i
m
p
le,
ea
s
y
to
i
m
p
le
m
e
n
t,
r
o
b
u
s
t,
a
n
d
s
u
itab
le
f
o
r
m
a
n
y
in
d
u
s
tr
ial
ap
p
licatio
n
s
[
17
]
.
I
MC
al
s
o
s
u
cc
ess
i
m
p
le
m
e
n
te
d
in
w
a
s
te
w
ater
tr
ea
t
m
e
n
t
s
y
s
te
m
b
u
t
n
o
t
y
e
t
i
m
p
le
m
en
ted
in
s
u
b
m
er
g
ed
m
e
m
b
r
a
n
e
b
io
r
ea
cto
r
f
il
tr
ati
o
n
p
r
o
ce
s
s
.
T
h
e
I
M
C
al
g
o
r
ith
m
i
s
e
f
f
ec
ti
v
e
i
n
r
ej
ec
tin
g
d
is
t
u
r
b
an
ce
s
an
d
ac
h
iev
in
g
g
o
o
d
p
er
f
o
r
m
an
ce
.
I
MC
h
as
s
h
o
w
n
g
r
ea
ter
ca
p
ab
ilit
y
i
n
co
n
tr
o
l
o
f
co
m
p
le
x
s
y
s
te
m
s
co
m
p
ar
ed
to
th
e
clas
s
ical
co
n
tr
o
l
tech
n
iq
u
es
[
18
]
.
P
r
ev
io
u
s
w
o
r
k
s
s
h
o
w
s
th
at
th
e
co
m
b
i
n
atio
n
o
f
A
NN
w
i
th
I
MC
p
r
o
v
id
e
b
etter
p
er
f
o
r
m
a
n
ce
o
f
co
n
tr
o
l
s
y
s
te
m
.
I
n
[
19
]
p
r
o
p
o
s
ed
n
eu
r
al
n
et
w
o
r
k
i
n
ter
n
al
m
o
d
el
co
n
tr
o
l
(
NNI
MC)
to
co
n
tr
o
l
th
e
to
p
an
d
b
o
tto
m
co
m
p
o
s
itio
n
i
n
d
is
till
atio
n
co
lu
m
n
.
T
h
e
r
esu
lt
s
h
o
w
ed
NNI
MC
p
r
o
v
id
e
b
etter
p
er
f
o
r
m
an
ce
w
h
e
n
co
m
p
ar
ed
to
th
e
co
n
v
e
n
tio
n
al
p
r
o
p
o
r
tio
n
al
in
te
g
r
al
p
lu
s
f
ee
d
f
o
r
w
ar
d
co
n
t
r
o
ller
.
W
o
r
k
b
y
[
20
]
ap
p
lied
NNI
MC
u
s
i
n
g
f
ee
d
f
o
r
w
ar
d
ar
ch
itect
u
r
e
to
co
n
tr
o
l
b
io
r
ea
cto
r
co
m
p
o
s
itio
n
b
o
th
f
o
r
s
et
p
o
in
t
a
n
d
d
is
t
u
r
b
an
ce
r
ej
ec
tio
n
.
I
n
[
21
-
22
]
th
e
r
ec
u
r
r
en
t
n
eu
r
al
n
e
t
w
o
r
k
ar
ch
itect
u
r
e
is
u
s
ed
to
tr
ain
t
h
e
in
v
er
s
e
m
o
d
el
co
n
tr
o
ller
i
n
I
MC
co
n
f
i
g
u
r
atio
n
.
T
h
e
r
es
u
lts
s
h
o
w
ed
t
h
at
t
h
e
NNI
MC
h
as
b
etter
p
er
f
o
r
m
a
n
ce
th
a
n
th
e
o
p
ti
m
all
y
tu
n
ed
lin
ea
r
co
n
tr
o
ller
s
f
o
r
s
etp
o
i
n
t
an
d
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
in
a
v
ar
iet
y
o
f
co
n
d
itio
n
s
.
F
u
r
t
h
er
m
o
r
e,
th
e
ap
p
li
ca
tio
n
o
f
I
MC
ca
n
al
s
o
d
e
m
o
n
s
tr
ated
i
n
[
23
]
f
o
r
s
i
m
u
lat
io
n
o
f
in
v
er
ted
p
en
d
u
l
u
m
.
I
MC
w
a
s
d
esig
n
ed
u
s
in
g
th
e
in
v
er
s
e
o
f
th
e
p
lan
t
m
o
d
el
in
s
er
ies
w
it
h
a
lo
w
-
p
ass
f
ilter
.
T
h
e
r
esu
lts
s
h
o
w
s
r
o
b
u
s
tn
e
s
s
o
f
th
e
I
M
C
an
d
g
o
t g
r
ad
ed
r
esp
o
n
s
es
w
h
en
c
o
m
p
ar
ed
w
it
h
P
I
D.
I
n
[
24
]
im
p
le
m
en
ted
I
MC
a
n
d
n
eu
r
o
-
f
u
zz
y
I
MC
(
N
FIM
C
)
f
o
r
co
n
tr
o
l
o
f
n
o
n
l
in
ea
r
p
r
o
ce
s
s
w
as
d
esi
g
n
ed
to
co
n
tr
o
l
o
f
a
th
er
m
o
-
o
p
tical
p
lan
t.
T
h
e
m
ai
n
ai
m
is
to
s
h
o
w
th
e
ef
f
ec
ti
v
e
n
ess
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
h
e
NFI
MC
w
a
s
d
esi
g
n
m
o
d
i
f
ie
d
I
MC
s
c
h
e
m
e
to
i
n
c
r
ea
s
e
th
e
d
i
s
tu
r
b
an
ce
r
ej
ec
tio
n
an
d
th
e
r
o
b
u
s
t
n
es
s
p
er
f
o
r
m
a
n
ce
.
T
h
e
r
esu
lt
s
s
h
o
w
ed
t
h
at
th
e
N
FIM
C
h
as b
ette
r
p
er
f
o
r
m
a
n
ce
an
d
v
er
y
ef
f
ec
ti
v
e
m
et
h
o
d
.
As
f
o
r
th
is
p
ap
er
,
it
is
co
n
s
is
t
o
f
f
o
u
r
m
ai
n
s
ec
tio
n
s
an
d
ar
e
o
r
g
an
ized
as
f
o
llo
w
s
.
T
h
e
f
ir
s
t
s
ec
tio
n
s
tar
t
ed
w
it
h
th
e
b
ac
k
g
r
o
u
n
d
o
f
th
is
s
tu
d
y
a
n
d
s
ev
er
al
liter
atu
r
e
o
n
th
e
r
elate
d
w
o
r
k
s
.
T
h
en
,
s
ec
o
n
d
s
ec
tio
n
p
r
esen
ts
t
h
e
m
eth
o
d
o
lo
g
y
o
f
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
d
ev
elo
p
m
e
n
t
a
n
d
I
MC
co
n
tr
o
ller
d
esig
n
f
o
r
s
u
b
m
er
g
ed
MB
R
f
il
tr
atio
n
p
r
o
ce
s
s
w
h
ile
in
t
h
e
t
h
ir
d
s
ec
tio
n
is
th
e
r
e
s
u
l
ts
an
d
d
is
c
u
s
s
io
n
.
Fi
n
all
y
,
th
e
f
o
r
th
s
ec
tio
n
g
i
v
es
co
n
clu
s
io
n
a
n
d
f
u
tu
r
e
w
o
r
k
s
b
ased
o
n
th
i
s
s
t
u
d
y
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
Su
cc
es
s
f
u
l
o
p
er
atio
n
o
f
w
ast
e
w
ater
tr
ea
t
m
en
t
p
lan
t
d
ep
en
d
s
o
n
th
e
ac
cu
r
ac
y
o
f
t
h
e
m
o
d
els
f
o
r
co
n
tr
o
l
s
y
s
te
m
d
ev
e
lo
p
m
en
t.
Sev
er
al
n
o
n
lin
ea
r
in
te
lli
g
en
ce
m
o
d
elli
n
g
tech
n
iq
u
e
s
w
h
i
ch
ar
e
f
ee
d
f
o
r
w
ar
d
n
eu
r
al
n
et
w
o
r
k
(
F
FNN)
,
R
B
F
NN
an
d
n
o
n
li
n
ea
r
au
to
r
eg
r
es
s
iv
e
ex
o
g
en
o
u
s
n
eu
r
al
n
et
w
o
r
k
(
NARXNN)
w
er
e
p
er
f
o
r
m
ed
f
o
r
m
o
d
eli
n
g
o
f
MB
R
s
y
s
te
m
.
T
h
e
in
p
u
t
is
p
er
m
ea
te
p
u
m
p
v
o
lta
g
e
an
d
an
d
th
e
o
u
tp
u
t
s
ar
e
p
er
m
ea
te
f
lu
x
an
d
tr
an
s
m
e
m
b
r
a
n
e
p
r
es
s
u
r
e
o
f
f
i
ltra
tio
n
p
r
o
ce
s
s
e
s
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
els
i
s
m
ea
s
u
r
ed
u
s
i
n
g
th
r
ee
cr
iter
ia
w
h
ich
ar
e
co
r
r
elatio
n
co
ef
f
icien
t
(
R
2
)
,
m
ea
n
s
q
u
ar
e
er
r
o
r
an
d
a
b
s
o
lu
te
d
ev
iatio
n
.
Fo
r
co
n
tr
o
l
p
ar
t,
t
h
e
NNI
M
C
w
as
i
m
p
le
m
e
n
te
d
to
co
n
tr
o
l
f
o
u
li
n
g
d
ev
elo
p
m
en
t
i
n
m
e
m
b
r
an
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
20
20
:
100
–
1
0
8
102
f
iltra
tio
n
p
r
o
ce
s
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
co
n
tr
o
ller
w
as
m
ea
s
u
r
ed
u
s
i
n
g
r
is
e
ti
m
e,
s
ett
lin
g
ti
m
e,
o
v
er
s
h
o
o
t,
I
A
E
,
I
SE
an
d
I
T
A
E
.
T
h
e
d
etai
ls
o
f
t
h
e
f
lo
w
o
f
m
et
h
o
d
o
lo
g
y
is
d
ep
icted
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Flo
w
o
f
r
esear
c
h
m
e
th
o
d
o
lo
g
y
I
n
t
h
is
w
o
r
k
,
t
h
e
f
i
ltra
tio
n
d
a
ta
s
et
s
w
er
e
co
llected
f
r
o
m
t
h
e
d
ev
e
lo
p
ed
SMB
R
p
ilo
t
p
l
an
t.
S
tep
s
in
p
u
t
w
it
h
r
an
d
o
m
m
ag
n
it
u
d
e
w
er
e
ex
cited
in
to
th
e
s
u
ctio
n
p
u
m
p
to
o
b
tain
th
e
d
y
n
a
m
i
c
b
eh
av
io
u
r
o
f
th
e
f
iltra
tio
n
p
r
o
ce
s
s
.
Du
r
in
g
th
e
o
p
er
atio
n
,
p
er
m
ea
te
to
r
elax
atio
n
p
er
io
d
is
m
a
in
ta
in
ed
at
1
2
0
s
ec
o
n
d
s
p
er
m
ea
t
e
an
d
3
0
s
ec
o
n
d
s
r
elax
at
io
n
w
a
s
ch
o
s
en
w
it
h
co
n
ti
n
u
o
u
s
ae
r
ati
o
n
air
f
lo
w
.
T
h
e
ae
r
atio
n
air
f
lo
w
d
u
r
in
g
f
iltra
tio
n
is
s
et
ar
o
u
n
d
6
to
8
S
L
P
M
to
m
ai
n
tai
n
h
ig
h
i
n
te
n
s
i
t
y
o
f
b
u
b
b
l
e
f
lo
w
i
n
clea
n
i
n
g
th
e
m
e
m
b
r
an
e.
T
h
e
in
p
u
t
o
f
th
is
f
iltra
t
io
n
p
r
o
ce
s
s
is
t
h
e
p
er
m
ea
te
p
u
m
p
v
o
ltag
e
w
h
il
e
th
e
o
u
tp
u
ts
ar
e
th
e
f
l
u
x
a
n
d
tr
an
s
m
e
m
b
r
an
e
p
r
ess
u
r
e
(
T
MP
)
.
T
h
e
SMB
R
f
i
ltra
tio
n
d
ata
s
et
is
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
Fro
m
t
h
e
d
ata,
it c
a
n
b
e
o
b
s
er
v
ed
th
at
th
e
p
er
m
ea
te
f
l
u
x
a
n
d
T
MP
h
as
an
i
m
p
ac
t
w
i
th
t
h
e
ch
a
n
g
es
o
f
p
er
m
ea
te
p
u
m
p
v
o
ltag
e
s
e
ttin
g
.
A
t
th
e
h
i
g
h
v
o
ltag
e
s
etti
n
g
,
p
er
m
ea
te
f
l
u
x
an
d
T
MP
is
h
ig
h
er
th
a
n
at
t
h
e
lo
w
v
o
ltag
e
s
e
tti
n
g
.
Fig
u
r
e
2
.
I
n
p
u
t a
n
d
o
u
tp
u
ts
S
MB
R
f
iltra
tio
n
p
r
o
ce
s
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
Mo
d
ellin
g
a
n
d
co
n
tr
o
l
o
f fo
u
li
n
g
in
s
u
b
merg
ed
mem
b
r
a
n
e
b
i
o
r
e
a
cto
r
u
s
in
g
…
(
N
o
r
h
a
liz
a
A
b
d
u
l W
a
h
a
b
)
103
2
.
1
.
Neura
l ne
t
w
o
rk
m
o
del
T
h
e
n
et
w
o
r
k
ar
ch
itect
u
r
e
w
i
t
h
th
e
b
est
h
id
d
en
n
e
u
r
o
n
,
lea
r
n
in
g
r
ate
v
al
u
e
an
d
s
p
r
ea
d
v
alu
e
w
er
e
u
s
ed
to
tr
ain
t
h
e
ac
q
u
ir
ed
s
et
o
f
2
4
0
0
d
ata.
T
h
e
MB
R
f
il
tr
atio
n
d
ata
ar
e
d
iv
id
ed
in
to
6
0
%
an
d
4
0
%
f
o
r
tr
ain
i
n
g
an
d
test
in
g
d
ata
s
et,
r
esp
ec
tiv
el
y
.
T
h
e
in
v
er
s
e
o
f
th
e
d
ev
elo
p
ed
FF
NN,
R
B
FNN
an
d
NARXN
N
m
o
d
el
s
ar
e
t
h
en
tr
ai
n
ed
,
w
h
er
e
v
o
ltag
e
as
a
n
o
u
tp
u
t
d
ata
a
n
d
f
lu
x
a
n
d
T
MP
as
in
p
u
ts
d
at
a
u
s
i
n
g
L
ev
e
n
b
er
g
-
Ma
r
q
u
ar
d
lear
n
in
g
al
g
o
r
ith
m
w
it
h
b
ac
k
p
r
o
p
ag
atio
n
.
T
o
im
p
r
o
v
e
r
o
b
u
s
tn
es
s
,
th
e
e
f
f
ec
t
s
o
f
m
is
m
atc
h
b
et
w
ee
n
th
e
ac
tu
a
l
an
d
th
e
p
r
ed
icted
m
o
d
el
w
a
s
m
in
i
m
ized
.
T
h
e
d
if
f
er
en
ce
s
b
et
w
ee
n
t
h
e
ac
tu
a
l
d
ata
an
d
th
e
p
r
ed
icted
m
o
d
el
o
cc
u
r
r
ed
at
h
i
g
h
f
r
eq
u
en
c
y
r
esp
o
n
s
e
o
f
t
h
e
s
y
s
te
m
,
a
lo
w
-
p
as
s
f
ilter
i
s
t
h
u
s
ad
d
ed
to
atten
u
ate
t
h
i
s
ef
f
ec
t
[
25
]
.
I
n
th
is
ca
s
e,
I
MC
is
d
esi
g
n
ed
f
o
r
th
e
a
f
o
r
e
m
e
n
tio
n
ed
A
NN
s
tr
u
ct
u
r
es
u
s
i
n
g
th
e
i
n
v
er
s
e
o
f
t
h
e
p
r
ed
icted
m
o
d
el
in
s
er
ies
w
i
t
h
a
lo
w
-
p
a
s
s
f
ilter
.
T
h
e
lo
w
p
as
f
ilter
h
ad
b
ee
n
u
s
ed
to
f
i
lter
h
i
g
h
f
r
eq
u
e
n
c
y
s
ig
n
al
an
d
ad
j
u
s
ti
n
g
t
h
e
co
n
tr
o
ller
s
en
s
iti
v
it
y
.
Fo
r
m
e
m
b
r
an
e
f
o
u
l
in
g
co
n
tr
o
l,
th
e
s
ec
o
n
d
o
r
d
er
f
ilter
is
id
en
ti
f
ied
w
ith
t
h
e
f
ilter
tu
n
i
n
g
p
ar
a
m
eter
o
f
0
.
0
0
1
.
T
h
e
f
ilte
r
tr
an
s
f
er
f
u
n
ctio
n
,
G
f
(
s
)
f
o
r
th
e
s
y
s
te
m
i
s
[
25
]
:
(
1
)
2
.
2
.
Neura
l net
w
o
rk
inte
rna
l
m
o
del c
o
ntr
o
l
T
h
e
d
ev
elo
p
ed
A
N
N
m
o
d
els
ar
e
ap
p
lied
f
o
r
I
MC
co
n
tr
o
ll
er
d
esig
n
.
I
n
t
h
is
w
o
r
k
,
th
e
NNI
MC
i
s
d
esig
n
ed
s
u
c
h
th
at
to
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
th
r
o
u
g
h
d
is
t
u
r
b
an
ce
f
ee
d
b
ac
k
s
ig
n
a
l
an
d
f
ilter
i
n
g
ac
tio
n
a
s
s
h
o
w
n
in
Fi
g
u
r
e
3
.
I
n
t
h
is
p
ap
er
,
th
e
in
v
er
s
e
m
o
d
el
w
er
e
o
b
tain
e
d
b
y
i
n
v
er
ti
n
g
th
e
n
eu
r
al
n
e
t
w
o
r
k
m
o
d
el
u
s
i
n
g
Ne
w
to
n
s
m
eth
o
d
a
n
d
s
o
lv
i
n
g
n
u
m
er
icall
y
th
e
co
n
tr
o
l
ac
tio
n
b
y
d
ir
ec
tl
y
tr
ain
ed
in
v
er
s
e
m
o
d
el
n
e
u
r
al
n
et
w
o
r
k
co
n
tr
o
ller
[
26
]
.
T
h
e
d
ir
ec
t tr
ain
ed
n
e
u
r
al
n
et
w
o
r
k
h
a
s
b
ee
n
u
tili
ze
d
in
t
h
is
w
o
r
k
to
d
esig
n
t
h
e
n
e
u
r
al
n
e
t
w
o
r
k
co
n
tr
o
ller
an
d
s
h
o
w
g
o
o
d
p
er
f
o
r
m
an
ce
b
o
th
f
o
r
s
et
p
o
in
t
an
d
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
.
T
h
e
d
esig
n
ed
f
il
ter
s
ab
le
to
i
m
p
r
o
v
e
d
is
t
u
r
b
an
ce
r
ej
ec
tio
n
an
d
s
et
p
o
in
t
tr
ac
k
in
g
an
d
t
h
i
s
r
eq
u
ir
es
g
o
o
d
u
n
d
er
s
ta
n
d
in
g
o
f
th
e
b
eh
av
io
u
r
o
f
t
h
e
s
y
s
te
m
f
o
r
t
h
e
s
elec
t
io
n
o
f
f
i
lter
in
g
t
u
n
i
n
g
p
ar
a
m
eter
.
T
h
e
co
m
p
ar
is
o
n
b
et
w
ee
n
t
h
e
th
r
e
e
A
NN
b
ased
I
MC
co
n
tr
o
l
s
t
r
u
ctu
r
es
n
a
m
el
y
F
FNN
-
I
MC,
R
B
FNN
-
I
M
C
an
d
NARXN
N
-
I
M
C
ar
e
p
r
esen
ted
.
T
h
e
r
o
b
u
s
tn
ess
i
s
s
u
e
is
co
n
f
ir
m
ed
b
y
s
tab
il
it
y
o
f
t
h
e
s
y
s
t
e
m
w
it
h
r
esp
ec
t
to
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
p
er
f
o
r
m
an
ce
.
W
h
ile,
th
e
b
est
p
er
f
o
r
m
an
ce
o
f
m
o
d
ellin
g
w
h
ich
is
R
B
FNN
w
as
u
s
ed
to
d
esig
n
th
e
co
n
v
e
n
tio
n
a
l
-
I
M
C
t
o
co
n
tr
o
l f
o
u
lin
g
d
ev
elo
p
m
en
t
in
m
e
m
b
r
an
e
f
iltra
tio
n
p
r
o
ce
ss.
Fig
u
r
e
3
.
T
h
e
NNI
MC b
lo
ck
d
iag
r
a
m
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
T
h
e
s
u
b
m
er
g
ed
MB
R
f
iltra
tio
n
d
ata
ar
e
d
iv
id
ed
in
to
tr
ain
in
g
an
d
test
i
n
g
d
ata
s
et
w
h
ic
h
i
s
6
0
%
f
o
r
tr
ain
i
n
g
an
d
4
0
%
f
o
r
test
in
g
.
T
h
e
in
p
u
t
p
ar
am
eter
is
p
er
m
e
ate
p
u
m
p
v
o
ltag
e
an
d
t
h
e
o
u
t
p
u
ts
ar
e
th
e
p
er
m
ea
te
f
l
u
x
a
n
d
T
M
P
o
f
th
e
f
iltra
tio
n
p
r
o
ce
s
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
els
w
a
s
ev
al
u
ated
u
s
i
n
g
th
r
ee
cr
iter
ia
w
h
ic
h
ar
e
co
r
r
elatio
n
co
ef
f
icie
n
t
R
2
,
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MSE
)
an
d
ab
s
o
lu
te
d
ev
iatio
n
(
M
A
D)
.
3
.
1
.
Su
b
m
er
g
ed
M
B
R
f
iltr
a
t
io
n
t
ra
ini
ng
a
nd
t
esting
T
h
e
tr
ain
in
g
an
d
te
s
ti
n
g
r
es
u
lt
s
o
f
t
h
e
f
l
u
x
an
d
T
MP
m
o
d
els
ar
e
p
lo
tted
as
s
h
o
w
n
i
n
Fi
g
u
r
e
4
(
a)
-
(
b
)
an
d
Fi
g
u
r
e
5
(
a)
-
(
b
)
,
r
esp
ec
tiv
el
y
.
T
h
e
co
m
p
ar
is
o
n
b
et
w
ee
n
FF
NN,
R
B
FNN
an
d
N
AR
X
N
N
m
o
d
el
s
tr
u
ct
u
r
es
w
it
h
t
h
e
ac
t
u
al
d
ata
w
er
e
d
is
c
u
s
s
ed
.
Fo
r
th
e
tr
ain
i
n
g
o
f
t
h
e
f
l
u
x
,
al
m
o
s
t
s
i
m
ilar
p
er
f
o
r
m
a
n
ce
o
b
s
er
v
ed
f
r
o
m
all
s
tr
u
ct
u
r
es
w
i
th
R
2
o
f
9
0
.
1
5
%,
9
0
.
5
5
%
an
d
9
0
.
3
9
%,
r
esp
ec
tiv
el
y
.
T
h
e
MSE
g
i
v
e,
o
f
r
esp
ec
tiv
el
y
0
.
0
0
5
7
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
20
20
:
100
–
1
0
8
104
0
.
0
0
5
5
an
d
0
.
0
0
5
6
f
o
r
FF
NN,
R
B
FNN
a
n
d
N
A
R
X
NN.
T
h
e
MA
D
v
al
u
es
f
o
r
FF
NN
an
d
R
B
FN
N
ar
e
0
.
0
4
4
6
an
d
0
.
0
4
4
0
an
d
0
.
0
4
4
4
f
o
r
N
AR
XNN
.
I
n
ter
m
s
o
f
n
u
m
b
er
o
f
n
eu
r
o
n
,
th
e
R
B
F
NN
r
eq
u
ir
es
o
n
l
y
th
r
ee
h
id
d
en
n
eu
r
o
n
s
co
m
p
ar
ed
w
it
h
F
FN
N
an
d
N
A
R
XNN
w
h
ic
h
is
f
iv
e
an
d
s
i
x
h
id
d
en
n
e
u
r
o
n
s
,
r
e
s
p
ec
tiv
el
y
.
Fo
r
T
MP
,
th
e
R
B
FNN
d
e
m
o
n
s
tr
ated
t
h
e
b
est
m
o
d
el
as
co
m
p
ar
ed
to
F
FNN
a
n
d
N
AR
XN
N
w
i
th
v
al
u
e
o
f
R
2
is
9
1
.
2
9
%
an
d
MSE
v
al
u
e
o
f
0
.
0
0
5
0
.
Fo
r
th
e
tr
ain
i
n
g
r
e
s
u
l
t,
th
e
R
B
F
NN
is
m
o
r
e
ac
cu
r
ate
a
n
d
r
eliab
le
co
m
p
ar
ed
w
i
t
h
th
e
o
th
er
tec
h
n
iq
u
es.
Fig
u
r
e
4
.
(
a)
Flu
x
m
o
d
el
tr
ai
n
i
n
g
Fig
u
r
e
4
.
(
b
)
T
M
P
m
o
d
el
tr
ain
in
g
Fig
u
r
e
5
.
(
a)
Flu
x
m
o
d
el
tes
tin
g
Fig
u
r
e
5
.
(
b
)
T
M
P
m
o
d
el
test
i
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
Mo
d
ellin
g
a
n
d
co
n
tr
o
l
o
f fo
u
li
n
g
in
s
u
b
merg
ed
mem
b
r
a
n
e
b
i
o
r
e
a
cto
r
u
s
in
g
…
(
N
o
r
h
a
liz
a
A
b
d
u
l W
a
h
a
b
)
105
Fro
m
t
h
e
tes
tin
g
r
e
s
u
l
ts
i
n
Fig
u
r
e
5
(
a)
-
(
b
)
,
s
li
g
h
tl
y
s
i
m
ilar
t
r
en
d
o
f
p
er
f
o
r
m
a
n
ce
w
a
s
d
ep
i
cted
as g
iv
e
n
b
y
t
h
e
tr
ain
i
n
g
r
es
u
lts
.
T
h
e
R
B
FNN
s
h
o
w
ed
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
f
o
r
b
o
th
f
lu
x
an
d
T
MP
co
m
p
ar
ed
to
th
e
o
th
er
t
w
o
m
et
h
o
d
s
in
ter
m
o
f
R
2
,
MSE
an
d
MA
D.
T
ab
les
1
an
d
2
p
r
o
v
id
e
m
o
r
e
d
etails
r
esu
lt
s
f
o
r
th
e
f
lu
x
an
d
T
MP,
f
o
r
th
e
tr
ain
in
g
an
d
tes
tin
g
,
r
esp
ec
tiv
el
y
.
T
ab
le
1
.
Flu
x
an
d
T
MP
tr
ain
in
g
r
esu
lts
T
ab
le
2
.
Flu
x
an
d
T
MP
Mo
d
ellin
g
test
i
n
g
r
esu
lts
F
l
u
x
M
o
d
e
l
s
R
2
M
S
E
M
A
D
F
F
N
N
9
0
.
1
5
0
.
0
0
5
7
0
.
0
4
4
6
R
B
F
N
N
9
0
.
5
5
0
.
0
0
5
5
0
.
0
4
4
0
N
A
R
X
N
N
9
0
.
3
9
0
.
0
0
5
6
0
.
0
4
4
4
T
M
P
M
o
d
e
l
s
R
2
M
S
E
M
A
D
F
F
N
N
8
8
.
4
3
0
.
0
0
6
1
0
.
0
5
4
3
R
B
F
N
N
9
1
.
2
9
0
.
0
0
5
0
0
.
0
3
4
0
N
A
R
X
N
N
9
0
.
3
4
0
.
0
0
5
9
0
.
0
4
7
6
F
l
u
x
M
o
d
e
l
s
R
2
M
S
E
M
A
D
F
F
N
N
9
0
.
2
2
0
.
0
0
6
3
0
.
0
4
4
6
R
B
F
N
N
9
2
.
4
5
0
.
0
0
5
0
0
.
0
3
4
3
N
A
R
X
N
N
9
2
.
3
3
0
.
0
0
5
2
0
.
0
3
6
5
T
M
P
M
o
d
e
l
s
R
2
M
S
E
M
A
D
F
F
N
N
8
8
.
6
7
0
.
0
0
6
1
0
.
0
5
6
4
R
B
F
N
N
9
1
.
1
1
0
.
0
0
5
1
0
.
0
2
3
0
N
A
R
X
N
N
9
1
.
3
2
0
.
0
0
5
3
0
.
0
2
3
3
3
.
2
.
Neura
l net
w
o
rk
inte
rna
l
m
o
del c
o
ntr
o
l
I
n
th
i
s
s
ec
tio
n
,
th
e
N
NI
MC
w
it
h
d
i
f
f
er
e
n
t
s
tr
u
ct
u
r
es
n
a
m
el
y
FF
N
N
I
MC,
R
B
F
NN
I
MC
an
d
NARXN
N
is
co
m
p
ar
ed
w
it
h
th
e
co
n
v
en
t
io
n
al
I
M
C
(
C
-
I
MC)
b
o
th
f
o
r
tr
ac
k
in
g
a
n
d
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
p
er
f
o
r
m
a
n
ce
s
.
Fi
g
u
r
e
6
(
a)
-
(
c)
s
h
o
w
th
e
in
p
u
t
a
n
d
o
u
tp
u
t
r
esp
o
n
s
es
f
o
r
al
l
co
n
tr
o
ller
f
o
r
tr
ac
k
in
g
p
er
p
er
f
o
m
a
n
ce
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
co
n
tr
o
ller
w
as
m
ea
s
u
r
ed
u
s
in
g
s
e
v
er
al
cr
iter
ia
as
s
h
o
w
n
in
T
ab
le
3
.
T
h
e
s
tep
r
esp
o
n
s
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
co
n
tr
o
ller
is
at
2
0
L
/
m
2
h
o
f
p
er
m
ea
te
f
l
u
x
.
T
h
e
p
er
ce
n
tag
e
o
f
I
A
E
s
h
o
w
ed
th
e
lo
w
est
f
o
r
R
B
FN
N
I
MC
w
it
h
0
.
0
4
2
2
,
f
o
llo
w
ed
b
y
0
.
0
6
3
1
f
o
r
NA
R
XNN
I
M
C
,
0
.
0
7
8
5
f
o
r
FF
NN
I
MC
an
d
0
.
1
1
7
8
f
o
r
C
-
I
MC.
T
h
e
f
astes
t
s
e
ttli
n
g
ti
m
e
is
g
i
v
en
b
y
R
B
FNN
I
M
C
w
ith
o
n
l
y
3
.
7
5
s
ec
o
n
d
s
w
h
ic
h
is
m
o
r
e
th
a
n
8
0
%
f
a
s
ter
t
h
an
t
h
e
C
-
I
MC.
O
v
er
all,
t
h
e
R
B
FN
N
I
MC
s
h
o
w
ed
t
h
e
b
est
tr
ac
k
i
n
g
p
er
f
o
r
m
an
ce
i
n
a
l
m
o
s
t a
ll c
r
iter
ia
as
s
h
o
w
n
i
n
T
ab
le
3
an
d
h
en
ce
is
p
r
ef
er
ab
l
e
to
o
th
er
m
e
th
o
d
s
.
(
a)
(
b
)
(
c)
Fig
u
r
e
6
.
(
a)
Vo
ltag
e
in
p
u
t r
es
p
o
n
s
e;
(
b
)
Flu
x
o
u
tp
u
t r
esp
o
n
s
e;
(
c)
T
MP
o
u
tp
u
t r
esp
o
n
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
20
20
:
100
–
1
0
8
106
T
ab
le
3
.
T
r
ac
k
in
g
p
er
f
o
r
m
a
n
c
e
in
d
ex
f
o
r
all
co
n
tr
o
ller
s
C
r
i
t
e
r
i
a
C
-
I
M
C
F
F
N
N
I
M
C
R
B
F
N
N
I
M
C
N
A
R
X
N
N
I
M
C
R
i
se
t
i
me
(
s)
5
.
8
6
4
.
5
3
1
.
5
1
2
.
0
4
S
e
t
t
l
i
n
g
t
i
me
2
7
.
5
1
2
5
.
7
7
3
.
7
5
4
.
5
2
O
v
e
r
sh
o
o
t
(
%)
1
0
.
4
5
6
.
7
3
2
.
4
4
3
.
9
8
I
A
E
0
.
1
1
7
8
0
.
0
7
8
5
0
.
0
4
2
2
0
.
0
6
3
1
I
S
E
0
.
2
9
1
3
0
.
0
0
8
3
0
.
0
0
2
4
0
.
0
0
5
4
I
TA
E
0
.
4
2
4
5
0
.
0
9
0
6
0
.
0
5
9
9
0
.
0
6
7
5
Fig
u
r
es
7
(
a)
-
(
d
)
s
h
o
w
t
h
e
am
p
lit
u
d
e
o
f
s
tep
d
is
tu
r
b
an
ce
s
an
d
f
lu
x
p
er
f
o
r
m
a
n
ce
s
f
o
r
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
C
-
I
MC,
F
FNN
I
MC,
R
B
FN
N
I
MC
an
d
NARXN
N
I
MC
co
n
tr
o
ller
s
ar
e
p
lo
tted
as
s
h
o
w
n
in
Fig
u
r
e
7
.
T
h
e
s
tep
d
is
t
u
r
b
an
ce
s
o
f
m
a
g
n
itu
d
e
1
0
%
o
f
t
h
e
f
l
u
x
f
o
r
2
0
s
ec
o
n
d
s
w
a
s
e
x
cited
f
ir
s
t
in
to
th
e
s
y
s
te
m
a
n
d
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
s
y
s
te
m
i
s
o
b
s
er
v
ed
.
As
s
ee
n
i
n
Fig
u
r
e
7
(
b
)
,
th
e
R
B
FNN
I
M
C
p
r
o
v
id
es
s
m
al
l
o
v
er
s
h
o
o
t
f
o
r
1
0
%
am
p
lit
u
d
e
o
f
d
is
tu
r
b
a
n
ce
r
ej
e
ctio
n
co
m
p
ar
ed
to
o
th
er
m
e
th
o
d
s
.
T
o
s
ee
th
e
r
o
b
u
s
tn
es
s
o
f
th
e
p
r
o
p
o
s
ed
co
n
tr
o
ller
,
5
0
%
d
is
tu
r
b
an
ce
w
as
also
ex
cited
in
to
th
e
s
y
s
te
m
.
T
h
e
R
B
FNN
I
MC
r
e
m
ain
s
t
h
e
h
i
g
h
est
p
er
f
o
r
m
an
ce
in
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
,
f
o
llo
w
ed
b
y
t
h
e
N
AR
XN
N
an
d
FF
NN
I
M
C
co
n
tr
o
ller
s
as
p
r
esen
ted
in
Fig
u
r
e
7
(
d
)
.
T
h
e
C
-
I
MC
d
ep
icted
th
e
h
ig
h
es
t
o
v
er
s
h
o
o
t
in
r
esp
o
n
d
to
th
e
d
is
tu
r
b
an
ce
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
7
.
(
a)
1
0
% d
is
tu
r
b
an
ce
r
ej
ec
tio
n
; (
b
)
Flu
x
p
er
f
o
r
m
an
c
e
f
o
r
1
0
%; (
c)
5
0
% d
is
tu
r
b
an
c
e
r
ej
ec
tio
n
;
(
d
)
Flu
x
p
er
f
o
r
m
a
n
ce
f
o
r
5
0
%;
4.
CO
NCLU
SI
O
N
Mo
d
ellin
g
a
n
d
co
n
tr
o
l
is
a
n
i
m
p
o
r
tan
t
asp
ec
t
o
f
t
h
e
m
e
m
b
r
a
n
e
b
io
r
ea
cto
r
f
iltra
ti
o
n
s
y
s
te
m
.
Ob
tain
i
n
g
a
r
eliab
le
m
o
d
el
i
s
a
v
er
y
c
h
alle
n
g
in
g
tas
k
b
e
ca
u
s
e
o
f
t
h
e
n
at
u
r
e
o
f
th
e
p
r
o
ce
s
s
an
d
f
o
u
lin
g
p
h
en
o
m
e
n
o
n
.
Ho
w
ev
er
,
g
o
o
d
f
iltra
tio
n
p
r
o
ce
s
s
is
cr
u
cial
an
d
h
e
n
ce
g
o
o
d
m
o
d
el
f
o
r
co
n
tr
o
l
s
y
s
te
m
d
esi
g
n
i
s
n
ee
d
ed
.
T
h
r
ee
p
r
e
d
ictio
n
m
o
d
els
f
o
r
s
u
b
m
er
g
ed
MB
R
s
y
s
te
m
w
a
s
d
ev
elo
p
ed
w
h
ic
h
i
s
th
e
F
FNN,
R
B
FNN
an
d
N
A
R
X
NN
m
o
d
el
s
.
Fro
m
th
e
s
i
m
u
latio
n
r
es
u
lts
,
it
ca
n
b
e
o
b
s
er
v
ed
th
at
t
h
e
R
B
FN
N
a
n
d
N
A
R
XNN
g
iv
e
g
o
o
d
r
esu
lts
f
o
r
f
l
u
x
an
d
T
MP
p
r
e
d
ictio
n
m
o
d
els
co
m
p
ar
e
d
to
FF
NN.
Ho
w
e
v
er
,
t
h
e
R
B
FNN
is
p
r
ef
er
ab
le
d
u
e
to
h
ig
h
ac
c
u
r
ac
y
an
d
m
o
r
e
r
eliab
le
p
r
ed
ictio
n
co
m
p
ar
ed
w
ith
o
th
er
t
w
o
m
et
h
o
d
s
.
Fo
r
th
e
co
n
tr
o
l
p
a
r
t,
th
r
ee
s
tr
u
ct
u
r
es
o
f
N
NI
MC
h
a
v
e
b
ee
n
d
ev
elo
p
ed
an
d
co
m
p
a
r
ed
to
th
e
co
n
v
en
tio
n
al
I
MC.
T
h
e
r
esu
lts
s
h
o
w
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
Mo
d
ellin
g
a
n
d
co
n
tr
o
l
o
f fo
u
li
n
g
in
s
u
b
merg
ed
mem
b
r
a
n
e
b
i
o
r
e
a
cto
r
u
s
in
g
…
(
N
o
r
h
a
liz
a
A
b
d
u
l W
a
h
a
b
)
107
th
e
R
B
FNN
I
M
C
p
r
o
v
id
es
b
et
ter
tr
ac
k
i
n
g
p
er
f
o
r
m
a
n
ce
t
h
an
FF
NN
I
M
C
,
N
AR
XNN
I
MC
an
d
C
-
I
MC
f
o
r
al
l
p
er
f
o
r
m
a
n
ce
cr
iter
ia.
I
n
ad
d
iti
o
n
,
th
e
R
B
FN
N
I
MC
p
er
f
o
r
m
ed
w
ell
i
n
1
0
%
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
co
m
p
ar
ed
to
o
th
er
m
eth
o
d
s
.
I
t
is
al
s
o
s
ee
n
to
b
e
m
o
r
e
r
o
b
u
s
t
w
h
e
n
a
b
le
to
r
e
m
ai
n
s
w
it
h
lo
w
o
v
e
r
s
h
o
o
t
f
o
r
th
e
5
0
%
d
is
tu
r
b
an
ce
r
ej
ec
tio
n
.
Sev
er
al
r
ec
o
m
m
e
n
d
atio
n
s
o
f
w
o
r
k
ca
n
b
e
co
n
s
id
er
ed
f
o
r
f
u
r
th
er
i
m
p
r
o
v
e
m
en
t.
I
n
m
o
d
ellin
g
o
f
SMB
R
,
an
ex
ter
n
al
o
p
ti
m
is
at
i
o
n
s
u
ch
as
p
ar
ticle
s
w
ar
m
o
p
ti
m
i
s
a
tio
n
a
n
d
g
r
av
ita
tio
n
al
s
e
ar
ch
alg
o
r
it
h
m
ca
n
b
e
i
m
p
le
m
en
ted
to
en
h
a
n
ce
t
h
e
p
r
ed
ictio
n
o
f
th
e
f
i
ltra
tio
n
m
o
d
els.
Oth
er
n
o
n
l
in
ea
r
m
o
d
ell
in
g
tec
h
n
iq
u
e
s
u
c
h
as
w
a
v
elet
n
e
u
r
al
n
e
t
w
o
r
k
c
an
b
e
ap
p
lied
to
p
r
ed
ict
th
e
b
eh
av
io
u
r
o
f
lo
n
g
ter
m
f
iltr
atio
n
c
y
cle.
I
n
th
e
co
n
tr
o
ller
d
esig
n
p
ar
t,
o
th
er
t
y
p
e
o
f
d
is
tu
r
b
an
ce
test
ca
n
b
e
ap
p
lied
to
estab
lis
h
th
e
r
eliab
ili
t
y
o
f
th
e
co
n
tr
o
ller
in
h
an
d
li
n
g
d
is
t
u
r
b
an
ce
s
w
h
ich
ca
n
r
ev
ea
l
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
co
n
tr
o
ller
u
n
d
er
m
i
s
m
a
tch
m
o
d
el
co
n
d
itio
n
s
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
li
k
e
to
th
an
k
t
h
e
Mi
n
is
tr
y
o
f
E
d
u
ca
tio
n
(
MO
E
)
P
R
GS
v
o
te
R
.
J
1
3
0
0
0
0
.
7
8
5
1
.
4
L
7
0
2
an
d
th
e
Un
i
v
er
s
iti
T
ek
n
o
lo
g
i
Ma
la
y
s
ia
UT
MH
I
R
v
o
te
0
8
G7
4
f
o
r
th
eir
f
in
a
n
cial
a
n
d
f
ac
ilit
y
s
u
p
p
o
r
t o
f
th
is
w
o
r
k
.
RE
F
E
R
E
NC
E
S
[1
]
T
.
S
tep
h
e
n
so
n
,
K.
Bri
n
d
le,
S
.
J
u
d
d
,
a
n
d
B.
Je
ff
e
rso
n
,
M
e
mb
ra
n
e
b
io
re
a
c
t
o
rs
fo
r
w
a
ste
wa
ter
t
re
a
tme
n
t
:
IW
A
p
u
b
li
sh
i
n
g
,
2
0
0
0
.
[2
]
A
.
Dr
e
w
s,
"
M
e
m
b
r
a
n
e
f
o
u
li
n
g
in
m
e
m
b
ra
n
e
b
io
re
a
c
to
rs
—
c
h
a
ra
c
terisa
ti
o
n
,
c
o
n
trad
ictio
n
s,
c
a
u
se
a
n
d
c
u
re
s,"
J
o
u
rn
a
l
o
f
me
mb
ra
n
e
sc
ien
c
e
,
v
o
l.
3
6
3
,
p
p
.
1
-
2
8
,
2
0
1
0
.
[3
]
P
.
L
e
-
Clec
h
,
V
.
C
h
e
n
,
a
n
d
T
.
A
.
F
a
n
e
,
"
F
o
u
l
in
g
i
n
m
e
m
b
ra
n
e
b
io
r
e
a
c
to
rs
u
se
d
in
w
a
ste
w
a
ter
trea
t
m
e
n
t,
"
J
o
u
rn
a
l
o
f
me
mb
ra
n
e
sc
ien
c
e
,
v
o
l.
2
8
4
,
p
p
.
1
7
-
5
3
,
2
0
0
6
.
[4
]
S
.
Ju
d
d
,
T
h
e
M
BR
b
o
o
k
:
p
rin
c
i
p
l
e
s
a
n
d
a
p
p
li
c
a
ti
o
n
s
o
f
me
mb
ra
n
e
b
io
re
a
c
t
o
rs
fo
r
wa
ter
a
n
d
wa
ste
w
a
te
r
tre
a
tme
n
t
:
El
se
v
ier,
2
0
1
0
.
[5
]
Z.
W
a
n
g
,
J.
M
a
,
C.
Y.
T
a
n
g
,
K.
Kim
u
ra
,
Q.
Wan
g
,
a
n
d
X
.
Ha
n
,
"
M
e
m
b
ra
n
e
c
lea
n
in
g
in
m
e
m
b
ra
n
e
b
io
re
a
c
to
rs:
a
re
v
ie
w
,
"
J
o
u
rn
a
l
o
f
me
mb
ra
n
e
sc
i
e
n
c
e
,
v
o
l.
4
6
8
,
p
p
.
2
7
6
-
3
0
7
,
2
0
1
4
.
[6
]
E.
H.
Bo
u
h
a
b
il
a
,
R
.
B.
A
ı
̈
m
,
a
n
d
H.
B
u
isso
n
,
"
F
o
u
li
n
g
c
h
a
ra
c
teris
a
ti
o
n
in
m
e
m
b
ra
n
e
b
io
re
a
c
to
rs,"
S
e
p
a
r
a
ti
o
n
a
n
d
Pu
rifi
c
a
t
io
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
2
,
p
p
.
1
2
3
-
1
3
2
,
2
0
0
1
.
[7
]
K.
Hu
n
t
a
n
d
D.
S
b
a
rb
a
r
o
,
"
Ne
u
ra
l
n
e
tw
o
rk
s
f
o
r
n
o
n
li
n
e
a
r
in
tern
a
l
m
o
d
e
l
c
o
n
tro
l,
"
in
IEE
Pro
c
e
e
d
i
n
g
s
D
(
Co
n
tro
l
T
h
e
o
ry
a
n
d
Ap
p
li
c
a
t
io
n
s)
,
1
9
9
1
,
p
p
.
4
3
1
-
4
3
8
.
[8
]
R.
W
.
Ok
e
y
,
"
P
h
o
sp
h
o
r
o
u
s rem
o
v
a
l
in
m
e
m
b
ra
n
e
w
a
st
e
wa
ter t
re
a
tm
e
n
t,
"
e
d
:
G
o
o
g
le P
a
ten
ts,
1
9
6
8
.
[9
]
A
.
R.
P
e
n
d
a
sh
teh
,
A
.
F
a
k
h
ru
’l
-
Ra
z
i,
N.
Ch
a
ib
a
k
h
sh
,
L
.
C.
A
b
d
u
ll
a
h
,
S
.
S
.
M
a
d
a
e
n
i
,
a
n
d
Z.
Z.
A
b
id
i
n
,
"
M
o
d
e
li
n
g
o
f
m
e
m
b
ra
n
e
b
io
re
a
c
to
r
trea
ti
n
g
h
y
p
e
rs
a
li
n
e
o
il
y
w
a
st
e
w
a
ter
b
y
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
,
"
J
o
u
rn
a
l
o
f
h
a
za
r
d
o
u
s
ma
ter
ia
ls,
v
o
l
.
1
9
2
,
p
p
.
5
6
8
-
5
7
5
,
2
0
1
1
.
[1
0
]
L
.
Erd
e
i,
S
.
V
ig
n
e
sw
a
ra
n
,
a
n
d
J.
Ka
n
d
a
sa
m
y
,
"
M
o
d
e
ll
in
g
o
f
su
b
m
e
rg
e
d
m
e
m
b
ra
n
e
f
lo
c
c
u
latio
n
h
y
b
rid
s
y
ste
m
s
u
sin
g
sta
ti
stica
l
a
n
d
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
m
e
th
o
d
s,"
J
o
u
rn
a
l
o
f
W
a
ter
S
u
p
p
ly:
Res
e
a
rc
h
a
n
d
T
e
c
h
n
o
lo
g
y
-
Aq
u
a
,
v
o
l.
5
9
,
p
p
.
1
9
8
-
2
0
8
,
2
0
1
0
.
[1
1
]
S.
A
.
M
irb
a
g
h
e
ri,
M
.
Ba
g
h
e
ri,
S
.
Bo
u
d
a
g
h
p
o
u
r,
M
.
E
h
tes
h
a
m
i,
a
n
d
Z.
Ba
g
h
e
ri,
"
P
e
rf
o
r
m
a
n
c
e
e
v
a
lu
a
ti
o
n
a
n
d
m
o
d
e
li
n
g
o
f
a
su
b
m
e
rg
e
d
m
e
m
b
r
a
n
e
b
io
re
a
c
to
r
trea
ti
n
g
c
o
m
b
in
e
d
m
u
n
icip
a
l
a
n
d
in
d
u
strial
w
a
ste
w
a
ter
u
sin
g
ra
d
ia
l
b
a
sis f
u
n
c
ti
o
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s,
"
J
o
u
rn
a
l
o
f
E
n
v
iro
n
me
n
ta
l
He
a
lt
h
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
1
3
,
p
.
1
7
,
2
0
1
5
.
[1
2
]
S
.
F
e
rra
ri,
F
.
Be
ll
o
c
c
h
io
,
V
.
P
iu
ri
,
a
n
d
N.
A
.
Bo
rg
h
e
se
,
"
A
Hie
ra
r
c
h
ica
l
RBF
On
li
n
e
L
e
a
rn
in
g
A
lg
o
rit
h
m
f
o
r
Re
a
l
-
T
i
m
e
3
-
D S
c
a
n
n
e
r,
"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ne
u
ra
l
Ne
tw
o
rk
s,
v
o
l.
2
1
,
p
p
.
2
7
5
-
2
8
5
,
2
0
1
0
.
[1
3
]
H.
-
G
.
H
a
n
a
n
d
J.
-
F
.
Qia
o
,
"
P
re
d
i
c
ti
o
n
o
f
a
c
ti
v
a
t
e
d
slu
d
g
e
b
u
lk
in
g
b
a
se
d
o
n
a
se
l
f
-
o
rg
a
n
izin
g
RBF
n
e
u
ra
l
n
e
tw
o
rk
,
"
J
o
u
rn
a
l
o
f
Pro
c
e
ss
Co
n
tro
l,
v
o
l.
2
2
,
p
p
.
1
1
0
3
-
1
1
1
2
,
2
0
1
2
.
[1
4
]
M
.
Ba
g
h
e
ri,
S
.
A
.
M
irb
a
g
h
e
ri,
A.
M
.
Ka
m
a
rk
h
a
n
i,
a
n
d
Z.
Ba
g
h
e
ri,
"
M
o
d
e
li
n
g
o
f
e
ff
lu
e
n
t
q
u
a
li
ty
p
a
ra
m
e
ters
in
a
su
b
m
e
rg
e
d
m
e
m
b
ra
n
e
b
io
re
a
c
to
r
w
it
h
sim
u
lt
a
n
e
o
u
s
u
p
w
a
rd
a
n
d
d
o
w
n
wa
rd
a
e
ra
ti
o
n
trea
ti
n
g
m
u
n
icip
a
l
w
a
ste
w
a
ter
u
sin
g
h
y
b
rid
m
o
d
e
ls,"
De
sa
li
n
a
ti
o
n
a
n
d
W
a
ter
T
re
a
tme
n
t,
v
o
l.
5
7
,
p
p
.
8
0
6
8
-
8
0
8
9
,
2
0
1
6
/
0
4
/
1
4
2
0
1
6
.
[1
5
]
Z.
Zh
a
o
,
Y.
L
o
u
,
Y.
C
h
e
n
,
H.
L
i
n
,
R.
L
i,
a
n
d
G
.
Yu
,
"
P
re
d
icti
o
n
o
f
in
terf
a
c
ial
in
tera
c
ti
o
n
s
re
late
d
w
it
h
m
e
m
b
ra
n
e
f
o
u
li
n
g
in
a
m
e
m
b
ra
n
e
b
io
re
a
c
to
r
b
a
se
d
o
n
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
(
A
N
N),"
Bi
o
re
so
u
rc
e
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
2
8
2
,
p
p
.
2
6
2
-
2
6
8
,
2
0
1
9
/
0
6
/
0
1
/
2
0
1
9
.
[1
6
]
Y.
Ch
e
n
,
G
.
Yu
,
Y.
L
o
n
g
,
J.
T
e
n
g
,
X
.
Yo
u
,
B.
-
Q.
L
iao
,
e
t
a
l.
,
"
A
p
p
li
c
a
ti
o
n
o
f
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
to
q
u
a
n
ti
fy
in
terf
a
c
ial
e
n
e
rg
ies
re
late
d
to
m
e
m
b
ra
n
e
fo
u
li
n
g
in
a
m
e
m
b
ra
n
e
b
io
re
a
c
to
r,
"
Bi
o
re
so
u
rc
e
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
9
3
,
p
.
1
2
2
1
0
3
,
2
0
1
9
/
1
2
/
0
1
/
2
0
1
9
.
[1
7
]
T
.
L
iu
,
F
.
Ga
o
,
a
n
d
Y.
W
a
n
g
,
"
I
M
C
-
b
a
se
d
it
e
ra
ti
v
e
lea
rn
in
g
c
o
n
tro
l
f
o
r
b
a
tch
p
ro
c
e
ss
e
s
w
it
h
u
n
c
e
rtain
ti
m
e
d
e
la
y
,
"
J
o
u
rn
a
l
o
f
Pro
c
e
ss
Co
n
tro
l,
v
o
l.
2
0
,
p
p
.
1
7
3
-
1
8
0
,
2
0
1
0
.
[1
8
]
G
.
C.
G
o
o
d
w
in
,
S
.
F
.
G
ra
e
b
e
,
a
n
d
M
.
E.
S
a
lg
a
d
o
,
"
Co
n
tr
o
l
sy
ste
m
d
e
sig
n
,
"
Up
p
e
r S
a
d
d
le R
ive
r,
p
.
1
3
,
2
0
0
1
.
[1
9
]
D.
M
u
h
a
m
m
a
d
,
Z.
A
h
m
a
d
,
a
n
d
N.
A
z
i
z
,
"
I
m
p
le
m
e
n
tatio
n
o
f
in
ter
n
a
l
m
o
d
e
l
c
o
n
tro
l
(im
c
)
in
c
o
n
ti
n
u
o
u
s
d
isti
ll
a
ti
o
n
c
o
lu
m
n
,
"
in
Pro
c
e
e
d
in
g
s
o
f
t
h
e
5
th
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
De
sig
n
,
Op
e
ra
ti
o
n
a
n
d
C
o
n
t
r
o
l
o
f
Ch
e
mic
a
l
Pro
c
e
ss
e
s
,
2
0
1
0
,
p
p
.
8
1
2
-
8
2
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell
,
Vo
l.
9
,
No
.
1
,
Ma
r
ch
20
20
:
100
–
1
0
8
108
[2
0
]
I.
Ha
ji
z
a
d
e
h
a
n
d
S
.
Ho
ss
e
in
i,
"
A
r
ti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
Ba
s
e
d
Co
n
tr
o
l
o
f
CS
T
Rs
w
it
h
V
a
n
d
e
Vu
ss
e
Re
a
c
ti
o
n
,
"
In
telli
g
e
n
t
A
u
to
m
a
ti
o
n
a
n
d
S
o
ft
Co
mp
u
t
in
g
,
1
0
/
3
1
2
0
1
4
.
[2
1
]
M
.
A
.
Hu
ss
a
in
,
"
Re
v
ie
w
o
f
th
e
a
p
p
li
c
a
ti
o
n
s
o
f
n
e
u
ra
l
n
e
tw
o
rk
s
in
c
h
e
m
i
c
a
l
p
ro
c
e
ss
c
o
n
tro
l
—
sim
u
l
a
ti
o
n
a
n
d
o
n
l
in
e
im
p
le
m
e
n
tatio
n
,
"
Arti
fi
c
ia
l
in
tell
i
g
e
n
c
e
in
e
n
g
i
n
e
e
rin
g
,
v
o
l.
1
3
,
p
p
.
5
5
-
6
8
,
1
9
9
9
.
[2
2
]
M
.
Nik
o
lao
u
a
n
d
V
.
Ha
n
a
g
a
n
d
i,
"
Co
n
tro
l
o
f
n
o
n
li
n
e
a
r
d
y
n
a
m
ica
l
s
y
ste
m
s
m
o
d
e
led
b
y
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
s
,
"
AICh
E
j
o
u
r
n
a
l,
v
o
l.
3
9
,
p
p
.
1
8
9
0
-
1
8
9
4
,
1
9
9
3
.
[2
3
]
D.
J.
Vo
ra
a
n
d
M
.
N.
Ba
su
,
"
M
o
d
e
ll
i
n
g
a
n
d
S
im
u
latio
n
o
f
In
v
e
rted
P
e
n
d
u
l
u
m
u
sin
g
In
tern
a
l
M
o
d
e
l
C
o
n
tr
o
l,
"
J
o
u
rn
a
l
f
o
r R
e
se
a
rc
h
|
V
o
l
u
me
,
v
o
l.
1
,
2
0
1
6
.
[2
4
]
J.
P
a
u
lu
s
o
v
á
a
n
d
M
.
P
a
u
lu
s,
"
In
t
e
rn
a
l
m
o
d
e
l
c
o
n
tr
o
l
o
f
th
e
r
mo
-
o
p
ti
c
a
l
p
lan
t,
"
i
n
Pr
o
c
e
ss
Co
n
tro
l
(
PC),
2
0
1
7
2
1
st
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
,
2
0
1
7
,
p
p
.
1
7
9
-
1
8
4
.
[2
5
]
W
.
R.
M
.
Iss
a
,
"
A
Ne
w
A
p
p
ro
a
c
h
o
f
Ro
b
u
st
I
n
tern
a
l
M
o
d
e
l
Co
n
tro
l
f
o
r
No
n
li
n
e
a
r
P
e
n
d
u
lu
m
S
y
ste
m
,
"
A
Ne
w
Ap
p
ro
a
c
h
o
f
Ro
b
u
st I
n
ter
n
a
l
M
o
d
e
l
Co
n
tr
o
l
f
o
r No
n
li
n
e
a
r P
e
n
d
u
l
u
m S
y
ste
m,
2
0
1
1
.
[2
6
]
M
.
A
.
He
n
so
n
a
n
d
D
.
E.
S
e
b
o
rg
,
"
A
n
in
tern
a
l
m
o
d
e
l
c
o
n
tr
o
l
stra
t
e
g
y
f
o
r
n
o
n
li
n
e
a
r
sy
ste
m
s,"
AICh
E
J
o
u
r
n
a
l,
v
o
l
.
3
7
,
p
p
.
1
0
6
5
-
1
0
8
1
,
1
9
9
1
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Nu
ra
z
iza
h
Bin
ti
M
a
h
m
o
d
is
M
a
ste
r
stu
d
e
n
t
in
S
c
h
o
o
l
o
f
El
e
c
tr
ica
l
En
g
in
e
e
rin
g
,
F
a
c
u
l
ty
o
f
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
la
y
sia
,
S
k
u
d
a
i,
Jo
h
o
r.
Re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r
d
e
g
re
e
in
El
e
c
tri
c
a
l
Co
n
tro
l
&
In
stru
m
e
n
t
in
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
lay
sia
,
S
k
u
d
a
i,
a
n
d
Jo
h
o
r.
He
r
a
re
a
o
f
in
tere
st i
s a
p
p
ly
in
g
d
a
ta m
in
in
g
tec
h
n
iq
u
e
in
W
a
ste
wa
ter T
re
a
t
m
e
n
t
f
ield
s a
n
d
a
p
p
li
c
a
ti
o
n
.
Ir.
Dr
No
rh
a
li
z
a
A
b
d
u
l
W
a
h
a
b
is
c
u
rre
n
tl
y
a
n
A
s
so
c
iate
P
ro
f
e
ss
o
r
a
t
Un
iv
e
r
siti
Tek
n
o
lo
g
i
M
a
la
y
sia
(UT
M
).
S
h
e
is
c
u
rre
n
t
l
y
th
e
Dire
c
to
r
f
o
r
Co
n
tr
o
l
a
n
d
M
e
c
h
a
tro
n
ic
E
n
g
in
e
e
rin
g
a
t
t
h
e
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
,
UT
M
.
S
h
e
c
o
m
p
lete
d
h
e
r
P
h
D
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
m
a
jo
rin
g
in
C
o
n
tr
o
l
i
n
Ju
ly
2
0
0
9
.
S
h
e
is
a
c
ti
v
e
l
y
in
v
o
lv
e
d
in
re
se
a
rc
h
in
g
a
n
d
tea
c
h
in
g
i
n
th
e
f
ield
o
f
in
d
u
strial
p
r
o
c
e
ss
c
o
n
tro
l
.
He
r
e
x
p
e
rti
se
is
in
m
o
d
e
ll
in
g
a
n
d
c
o
n
tr
o
l
o
f
in
d
u
strial
p
r
o
c
e
ss
p
lan
t.
Re
c
e
n
tl
y
sh
e
h
a
s
w
o
rk
e
d
p
rim
a
ril
y
o
n
d
if
fe
re
n
t
ty
p
e
s
o
f
d
o
m
e
stic
a
n
d
in
d
u
strial
w
a
ter
a
n
d
w
a
ste
w
a
ter t
re
a
t
m
e
n
t
tec
h
n
o
l
o
g
y
to
w
a
rd
s o
p
ti
m
iza
ti
o
n
a
n
d
e
n
e
rg
y
sa
v
in
g
s
y
st
e
m
.
M
u
h
a
m
m
a
d
S
a
n
i
Ga
y
a
re
c
e
iv
e
d
B.
En
g
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
in
2
0
0
2
,
M
.
E
n
g
(El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
.
)
in
2
0
0
8
b
o
t
h
f
ro
m
Ba
y
e
ro
Un
iv
e
rsit
y
Ka
n
o
,
Nig
e
r
ia
a
n
d
P
h
D
d
e
g
re
e
f
ro
m
th
e
De
p
a
rtme
n
t
o
f
Co
n
tro
l
a
n
d
M
e
c
h
a
tro
n
ics
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
la
y
sia
in
2
0
1
4
.
His
c
u
rre
n
t
re
se
a
r
c
h
in
tere
st
c
e
n
tres
a
ro
u
n
d
sy
ste
m
id
e
n
t
if
ica
ti
o
n
,
f
e
e
d
b
a
c
k
c
o
n
tro
l,
IM
C
a
n
d
in
v
e
rse
c
o
n
tro
l
o
f
u
n
c
e
rtain
/
n
o
n
li
n
e
a
r
sy
ste
m
s
b
a
se
d
o
n
n
e
u
ra
l
n
e
tw
o
rk
,
f
u
z
z
y
a
n
d
A
NFIS
.
Cu
rre
n
tl
y
,
w
o
rk
in
g
w
it
h
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
in
e
e
rin
g
,
Ka
n
o
U
n
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
W
u
d
il
.
Evaluation Warning : The document was created with Spire.PDF for Python.