I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
7
,
No
.
3
,
J
u
n
e
201
7
,
p
p
.
1620
~
1
6
2
7
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
7
i
3
.
p
p
1
6
2
0
-
1
627
1620
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
M
o
delling
and Ev
a
lua
tion o
f
Seque
ntial Ba
tch
Rea
ct
o
r Using
Artif
i
cia
l Neural
Netw
o
rk
N
o
rj
a
nn
a
h
H
a
za
li
1
,
No
rha
liz
a
Abdu
l Wa
ha
b
2
,
Sy
a
hira
I
b
ra
hi
m
3
1,
2,
3
De
p
a
rtm
e
n
t
o
f
Co
n
tr
o
l
&
M
e
c
h
a
tro
n
ics
E
n
g
in
e
e
rin
g
, Fa
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
lay
sia
,
S
k
u
d
a
i,
Jo
h
o
r
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
30
,
2
0
1
7
R
ev
i
s
ed
A
pr
5
,
2
0
1
7
A
cc
ep
ted
A
p
r
20
,
2
0
1
7
T
h
e
m
a
in
o
b
jec
ti
v
e
o
f
wa
ste
wa
te
r
trea
t
m
e
n
t
p
lan
t
is
to
re
lea
se
sa
fe
e
ff
lu
e
n
t
n
o
t
o
n
ly
to
h
u
m
a
n
h
e
a
lt
h
b
u
t
a
l
so
to
t
h
e
n
a
tu
ra
l
e
n
v
ir
o
n
m
e
n
t.
A
n
a
e
ro
b
ic
g
ra
n
u
lar
slu
d
g
e
tec
h
n
o
lo
g
y
is
u
se
d
f
o
r
n
u
tri
e
n
t
re
m
o
v
a
l
o
f
w
a
ste
w
a
te
r
trea
t
m
e
n
t
p
ro
c
e
ss
u
sin
g
se
q
u
e
n
ti
a
l
b
a
tch
re
a
c
to
r
s
y
ste
m
.
T
h
e
n
a
t
u
re
o
f
th
e
p
ro
c
e
ss
is
h
ig
h
ly
c
o
m
p
le
x
a
n
d
n
o
n
li
n
e
a
r
m
a
k
e
s
th
e
p
re
d
icti
o
n
o
f
b
i
o
lo
g
ica
l
trea
t
m
e
n
t
is
d
iff
icu
lt
to
a
c
h
iev
e
.
T
o
stu
d
y
th
e
n
o
n
li
n
e
a
r
d
y
n
a
m
ic
o
f
a
e
ro
b
ic
g
ra
n
u
lar
slu
d
g
e
,
h
ig
h
tem
p
e
ra
tu
re
re
a
l
d
a
ta
a
t
4
0
˚C
w
e
re
u
se
d
to
m
o
d
e
l
se
q
u
e
n
ti
a
l
b
a
tch
re
a
c
to
r
u
sin
g
a
rti
f
i
c
ial
n
e
u
ra
l
n
e
t
w
o
rk
.
In
th
is
w
o
rk
,
th
e
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
f
o
r
m
o
d
e
ll
in
g
o
f
n
u
tri
e
n
t
re
m
o
v
a
l
p
ro
c
e
ss
wa
s
stu
d
ied
.
T
h
e
n
e
tw
o
r
k
w
a
s
o
p
ti
m
ize
d
w
it
h
se
l
f
-
o
rg
a
n
izin
g
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
w
h
ich
a
d
ju
ste
d
t
h
e
n
e
tw
o
rk
stru
c
tu
re
siz
e
d
u
ri
n
g
lea
rn
in
g
p
h
a
se
.
P
e
rf
o
rm
a
n
c
e
o
f
b
o
th
n
e
tw
o
rk
w
e
re
e
v
a
l
u
a
ted
a
n
d
c
o
m
p
a
re
d
a
n
d
th
e
si
m
u
latio
n
re
su
lt
s
sh
o
w
e
d
th
a
t
th
e
b
e
st
p
re
d
ict
io
n
o
f
th
e
m
o
d
e
l
wa
s g
iv
e
n
b
y
se
l
f
-
o
rg
a
n
izi
n
g
ra
d
ial
b
a
sis f
u
n
c
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
.
K
ey
w
o
r
d
:
A
er
o
b
ic
g
r
an
u
lar
s
l
u
d
g
e
N
u
tr
ie
n
t
r
e
m
o
v
a
l p
r
o
ce
s
s
R
B
FNN
S
elf
-
o
r
g
a
n
izi
n
g
R
B
FNN
S
eq
u
en
t
ial
b
atch
r
ea
cto
r
Co
p
y
rig
h
t
©
2
0
1
7
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
h
aliza
A
b
d
u
l W
ah
ab
,
Dep
ar
t
m
en
t o
f
C
o
n
tr
o
l &
Me
c
h
atr
o
n
ics
E
n
g
in
ee
r
i
n
g
,
Fa
cu
lt
y
o
f
E
lectr
ical
E
n
g
in
ee
r
in
g
,
U
n
i
v
er
s
iti T
ek
n
o
lo
g
i M
al
a
y
s
ia
,
8
1
3
1
0
,
Sk
u
d
ai,
J
o
h
o
r
,
M
alay
s
i
a.
E
m
ail:
aliza
@
f
k
e.
u
t
m
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
An
ae
r
o
b
ic
g
r
an
u
lar
s
lu
d
g
e
(
A
G
S)
tech
n
o
lo
g
y
h
as
b
ee
n
u
s
ed
w
id
el
y
f
o
r
n
u
tr
ien
t
r
e
m
o
v
al
p
r
o
ce
s
s
u
s
i
n
g
s
eq
u
e
n
tial
b
atc
h
r
ea
cto
r
(
SB
R
)
s
y
s
te
m
[
1
]
.
T
h
e
ad
v
an
tag
e
s
o
f
A
G
S
u
s
i
n
g
SB
R
ar
e
b
ec
au
s
e
o
f
th
e
s
tab
ilit
y
a
n
d
f
le
x
ib
ilit
y
,
th
e
l
o
w
r
eq
u
ir
e
m
e
n
t
o
f
en
er
g
y
le
v
el,
th
e
in
cr
ea
s
e
in
b
io
m
as
s
co
n
ce
n
tr
atio
n
,
th
e
p
r
esen
ce
o
f
ae
r
o
b
ic
an
d
an
o
x
ic
p
r
o
ce
s
s
in
th
e
s
a
m
e
s
y
s
t
e
m
an
d
t
h
e
r
ed
u
ctio
n
i
n
o
p
er
atio
n
al
co
s
t
[
2
]
.
SB
R
tr
ea
ts
w
aste
w
ater
i
n
a
b
atch
tr
ea
t
m
e
n
t
p
r
o
ce
s
s
w
h
ic
h
m
ea
n
s
,
ea
ch
o
f
t
h
e
p
r
o
ce
s
s
o
cc
u
r
s
s
eq
u
e
n
tiall
y
i
n
a
s
in
g
le
r
ea
cto
r
b
asi
n
.
T
h
e
f
le
x
i
b
ilit
y
o
f
SB
R
p
r
o
ce
s
s
m
a
k
es
i
t
ap
p
licab
le
f
o
r
all
t
y
p
e
s
o
f
waste
w
ater
an
d
p
la
n
t
ca
p
ac
it
y
f
o
r
b
io
lo
g
ical
tr
ea
t
m
en
t
[
3
]
.
Mo
d
ellin
g
n
u
tr
ie
n
t
r
e
m
o
v
al
p
r
o
ce
s
s
es
u
s
i
n
g
SB
R
in
v
o
l
v
es
p
h
y
s
ical,
b
io
lo
g
ical
an
d
c
h
e
m
ical
p
r
o
ce
s
s
es.
Du
e
to
t
h
is
n
at
u
r
e,
t
h
e
s
y
s
te
m
e
x
h
ib
its
n
o
n
lin
ea
r
it
y
,
co
m
p
le
x
it
y
a
n
d
d
y
n
a
m
ic
b
eh
a
v
io
r
[
4
]
.
T
h
e
u
s
e
o
f
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
(
A
NN)
h
a
s
s
h
o
w
n
a
p
r
o
m
is
in
g
r
esu
lt
i
n
v
ar
io
u
s
en
g
i
n
ee
r
i
n
g
ap
p
licatio
n
,
p
att
er
n
r
ec
o
g
n
itio
n
an
d
f
i
n
a
n
cial
m
ar
k
et
a
n
al
y
s
is
[
4
]
.
So
m
e
o
f
th
e
f
ea
tu
r
es
o
f
n
eu
r
o
n
-
b
ased
ap
p
r
o
ac
h
ar
e
s
im
p
licit
y
,
f
a
u
lt
a
n
d
n
o
is
e
to
ler
an
ce
as
ex
p
lai
n
ed
in
[
5
]
.
A
n
u
m
b
er
o
f
r
esear
c
h
h
a
s
co
n
f
ir
m
ed
th
at
A
NN
o
f
f
er
s
a
b
etter
s
o
lu
tio
n
in
m
o
d
ell
in
g
w
a
s
te
w
ater
tr
ea
t
m
e
n
t
p
lan
t
(
W
W
T
P).
Du
e
to
th
e
s
ig
n
i
f
ica
n
t
c
h
ar
ac
ter
is
tic
o
f
A
NN
i
n
ap
p
r
o
x
i
m
at
in
g
co
m
p
le
x
a
n
d
n
o
n
li
n
ea
r
s
y
s
te
m
,
it
i
s
c
ap
ab
le
o
f
ac
h
ie
v
i
n
g
h
ig
h
ac
c
u
r
ac
y
w
it
h
o
u
t th
e
n
ee
d
s
to
u
n
d
er
s
ta
n
d
th
e
r
u
le
s
g
o
v
er
n
in
g
co
m
p
le
x
b
io
lo
g
ical
r
ea
ctio
n
s
[
5
]
.
T
h
e
w
o
r
k
p
r
ese
n
ted
in
[
4
]
s
h
o
w
ed
a
b
etter
p
r
e
d
ictio
n
o
f
ef
f
l
u
en
t
co
n
ce
n
tr
atio
n
o
f
b
io
lo
g
ical
o
x
y
g
e
n
d
em
a
n
d
(
B
OD)
a
n
d
s
u
s
p
e
n
d
ed
s
o
lid
(
SS
)
i
n
t
h
e
f
i
n
al
cl
ar
if
ier
ta
n
k
u
s
i
n
g
f
ee
d
-
f
o
r
w
a
r
d
n
eu
r
al
n
et
w
o
r
k
(
FF
NN)
.
T
h
e
m
o
d
el
ac
h
iev
ed
a
g
o
o
d
f
it
f
o
r
th
e
m
ea
s
u
r
ed
B
OD
an
d
SS
d
ata.
An
A
N
N
b
lack
-
b
o
x
m
o
d
ellin
g
ap
p
licatio
n
w
as
also
ap
p
lied
at
Do
h
a
W
est
W
W
T
P
in
s
tate
o
f
Qata
r
[
5
]
to
s
tu
d
y
a
n
d
an
al
y
ze
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Mo
d
ellin
g
a
n
d
E
va
lu
a
tio
n
o
f S
eq
u
en
tia
l B
a
tc
h
R
ea
cto
r
Usi
n
g
A
r
tifi
cia
l
N
eu
r
a
l Net
w
o
r
k
(
N
o
r
ja
n
n
a
h
Ha
z
a
li)
1621
in
ter
d
ep
en
d
en
c
y
o
f
i
n
p
u
t
-
o
u
tp
u
t
v
ar
iab
le
s
.
FF
NN
w
i
th
s
i
n
g
l
e
in
p
u
t
a
n
d
m
u
lti
i
n
p
u
t
to
p
o
lo
g
ies
w
er
e
u
tili
ze
d
to
ex
a
m
i
n
e
th
e
r
elatio
n
o
f
in
f
l
u
en
t
a
n
d
ef
f
lu
e
n
t
p
ar
a
m
eter
s
.
Fro
m
th
e
r
esu
l
ts
,
a
b
etter
p
r
e
d
ictio
n
o
f
ch
e
m
ica
l
o
x
y
g
en
d
e
m
a
n
d
(
C
OD)
,
B
OD
an
d
SS
e
f
f
l
u
en
t
co
n
ce
n
tr
atio
n
w
er
e
ac
h
ie
v
ed
w
h
en
C
O
D
o
f
th
e
cr
u
d
e
s
u
p
p
l
y
s
tr
ea
m
w
as
u
s
ed
as
an
i
n
p
u
t
t
o
th
e
n
et
w
o
r
k
.
An
o
th
er
e
x
a
m
p
le
o
f
ANN
ap
p
licatio
n
w
a
s
p
r
esen
ted
i
n
[
3
]
.
T
h
e
m
o
d
ell
in
g
o
f
b
io
lo
g
ical
r
e
m
o
v
al
o
f
o
r
g
an
ic
C
ar
b
o
n
a
n
d
Nitr
o
g
en
w
as
i
m
p
le
m
e
n
ted
o
n
s
la
u
g
h
ter
h
o
u
s
e
w
a
s
te
w
ater
tr
ea
t
m
e
n
t.
T
h
e
ai
m
o
f
t
h
is
w
o
r
k
w
as
to
id
en
t
if
y
t
h
e
b
es
t
o
p
er
atio
n
co
n
d
it
io
n
s
f
o
r
a
c
y
c
le
f
o
r
th
e
tr
ea
t
m
e
n
t
r
eq
u
ir
e
m
en
t.
T
h
e
A
N
N
s
tr
u
ct
u
r
e
u
s
ed
w
as
a
t
h
r
ee
-
la
y
er
ed
F
FNN
w
it
h
b
ac
k
p
r
o
p
ag
atio
n
tr
ain
i
n
g
alg
o
r
ith
m
w
h
ic
h
co
n
s
i
s
ts
o
f
s
ix
i
n
p
u
t
s
,
a
h
id
d
en
la
y
er
w
i
th
th
e
s
a
m
e
n
e
u
r
o
n
s
o
f
th
e
i
n
p
u
t
la
y
er
an
d
t
w
o
o
u
tp
u
ts
.
T
h
e
r
esu
l
ts
i
n
d
icate
d
th
at
t
h
e
A
NN
m
o
d
el
s
ab
le
to
p
r
o
v
id
e
ef
f
ic
ien
t p
r
ed
ictio
n
f
o
r
SB
R
p
er
f
o
r
m
an
ce
.
FF
NN
is
a
p
o
w
er
f
u
l
to
o
l
f
o
r
ap
p
r
o
x
im
a
tin
g
co
n
ti
n
u
o
u
s
f
u
n
ctio
n
a
n
d
it
h
as
b
ee
n
p
r
o
v
ed
in
[
3
]
-
[
5
]
.
Ho
w
e
v
er
,
r
ec
u
r
r
en
t
n
eu
r
al
n
e
t
w
o
r
k
(
R
N
N)
also
p
r
o
v
ed
th
at
it
h
as
m
o
r
e
ca
p
ab
ilit
y
f
o
r
p
r
e
d
ictio
n
o
f
d
y
n
a
m
ic
s
y
s
te
m
as
co
m
p
ar
ed
to
FF
N
N
[
6
]
.
T
h
e
n
et
w
o
r
k
h
as
a
n
i
n
ter
n
al
f
ee
d
b
ac
k
o
n
t
h
e
s
ec
o
n
d
h
id
d
en
la
y
er
.
T
h
e
d
y
n
a
m
ic
p
r
o
p
er
ties
w
a
s
i
n
tr
o
d
u
ce
d
to
f
o
r
m
a
d
y
n
a
m
ic
n
et
w
o
r
k
to
p
r
ed
ict
B
OD
co
n
ce
n
tr
atio
n
.
T
h
e
ex
p
er
i
m
e
n
tal
r
es
u
lts
i
n
d
icate
d
th
at
m
o
d
ellin
g
R
NN
w
as
m
o
r
e
e
f
f
icien
t
as
co
m
p
ar
ed
to
FF
NN.
An
o
t
h
er
ap
p
licatio
n
o
f
R
NN
w
a
s
i
m
p
l
e
m
en
ted
in
[
7
]
.
T
h
e
n
et
w
o
r
k
o
u
tp
u
t
w
as
u
s
ed
as
f
ee
d
b
ac
k
t
o
th
e
in
p
u
t
la
y
er
f
o
r
th
e
s
u
b
s
eq
u
e
n
t
ti
m
e
s
tep
.
T
h
e
o
b
j
ec
tiv
e
o
f
th
is
w
o
r
k
was
to
m
o
d
el
SS
a
n
d
v
o
latile
s
u
s
p
e
n
d
ed
s
o
lid
s
co
n
ce
n
tr
atio
n
.
T
h
e
s
i
m
u
latio
n
r
esu
lt
s
s
h
o
w
ed
t
h
at
t
h
e
p
r
ed
ictio
n
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
w
a
s
b
etter
th
a
n
t
h
e
m
ec
h
a
n
i
s
tic
m
o
d
el
d
ev
elo
p
ed
b
y
Su
n
.
An
o
th
er
ANN
to
p
o
lo
g
y
u
s
ed
in
w
a
s
te
w
ater
tr
ea
t
m
en
t
m
o
d
ellin
g
is
r
ad
ial
b
asi
s
f
u
n
cti
o
n
n
e
u
r
al
n
et
w
o
r
k
(
R
B
FNN)
.
R
B
FN
N
s
tr
u
ctu
r
e
h
as
o
n
l
y
o
n
e
la
y
er
o
f
h
id
d
en
la
y
er
a
n
d
th
e
h
id
d
en
n
o
d
es
i
m
p
le
m
e
n
t
a
s
et
o
f
r
ad
ial
b
asi
s
f
u
n
ctio
n
t
h
at
ar
e
r
ad
iall
y
s
y
m
m
etr
ic.
No
r
m
a
ll
y
,
Ga
u
s
s
ian
ac
ti
v
atio
n
f
u
n
ctio
n
w
i
th
t
h
e
r
ad
iu
s
an
d
ce
n
ter
p
ar
a
m
eter
s
ar
e
d
ef
in
ed
s
ep
ar
atel
y
at
ea
ch
R
B
F
u
n
it
[
8
]
.
T
h
e
o
u
tp
u
t
n
o
d
es
i
m
p
le
m
en
t
lin
ea
r
s
u
m
m
atio
n
f
u
n
ctio
n
.
T
h
e
ad
v
an
tag
e
s
o
f
R
B
FNN
o
v
er
FF
N
N
an
d
R
N
N
ar
e
m
e
n
tio
n
ed
in
[
8
]
s
u
ch
a
s
f
aster
co
n
v
er
g
e
n
ce
,
s
m
aller
tr
ain
i
n
g
er
r
o
r
s
an
d
h
ig
h
er
r
el
iab
ilit
y
.
T
h
e
ai
m
o
f
w
o
r
k
p
r
esen
ted
in
[
8
]
w
a
s
to
ev
alu
at
e
p
er
f
o
r
m
a
n
ce
o
f
a
s
u
b
m
er
g
ed
m
e
m
b
r
a
n
e
b
io
r
ea
cto
r
tr
ea
tin
g
co
m
b
in
ed
m
u
n
icip
al
a
n
d
i
n
d
u
s
tr
ial
w
aste
w
a
ter
.
T
h
e
ev
alu
atio
n
o
f
ef
f
l
u
e
n
t
q
u
alit
y
p
ar
a
m
eter
s
w
as
m
o
d
elled
u
s
i
n
g
R
B
FNN.
T
h
e
tr
ain
i
n
g
a
n
d
test
i
n
g
p
r
ed
ictio
n
w
er
e
v
er
y
clo
s
e
to
th
e
ex
p
er
i
m
en
tal
d
ata.
W
ith
c
o
ef
f
icie
n
t
o
f
d
eter
m
i
n
atio
n
h
i
g
h
er
t
h
an
0
.
9
8
an
d
r
o
o
t
m
ea
n
s
q
u
ar
e
les
s
th
a
n
7
%,
th
i
s
i
n
d
icate
d
th
at
R
B
FN
N
m
o
d
elli
n
g
w
as
q
u
ite
e
f
f
ic
ie
n
t.
A
co
m
p
ar
i
s
o
n
o
f
R
B
FNN
an
d
FF
NN
p
er
f
o
r
m
a
n
ce
w
as
also
co
n
d
u
c
ted
in
[
9
]
.
B
o
th
n
et
w
o
r
k
s
w
er
e
d
ev
e
lo
p
ed
to
s
tu
d
y
t
h
e
ef
f
ec
ts
o
f
i
n
f
lu
e
n
t
co
n
ce
n
tr
at
io
n
,
f
ill
in
g
ti
m
e,
r
ea
ctio
n
ti
m
e,
ae
r
atio
n
in
ten
s
it
y
,
s
o
lid
s
r
eten
tio
n
ti
m
e
an
d
m
i
x
ed
liq
u
o
r
v
o
latile
s
u
s
p
e
n
d
ed
s
o
lid
s
co
n
ce
n
tr
atio
n
o
n
t
h
e
ef
f
l
u
en
t
co
n
ce
n
tr
atio
n
o
f
to
ta
l
s
u
s
p
e
n
d
ed
s
o
lid
s
,
to
tal
p
h
o
s
p
h
o
r
u
s
(
T
P
)
,
C
OD
an
d
NH4
+
-
N
u
s
i
n
g
SB
R
.
R
B
FNN
d
e
m
o
n
s
tr
ated
a
g
o
o
d
p
er
f
o
r
m
a
n
ce
w
it
h
co
n
s
id
er
atio
n
o
f
m
o
r
e
in
p
u
t
s
t
o
th
e
n
et
w
o
r
k
.
An
en
h
a
n
ce
m
e
n
t
o
f
R
B
FNN
w
a
s
i
m
p
le
m
e
n
ted
in
[
1
0
]
to
ca
p
tu
r
e
th
e
B
OD
co
n
ce
n
tr
atio
n
o
f
W
W
T
P.
A
g
r
o
w
in
g
a
n
d
p
r
u
n
in
g
al
g
o
r
ith
m
w
a
s
p
r
esen
ted
w
h
ic
h
w
a
s
n
a
m
ed
as
s
el
f
-
o
r
g
an
iz
in
g
r
a
d
ial
b
asis
f
u
n
ctio
n
n
et
w
o
r
k
(
SO
R
B
FNN)
.
T
h
e
n
et
w
o
r
k
w
as
ab
le
to
ad
j
u
s
t
th
e
n
u
m
b
er
o
f
h
id
d
en
n
e
u
r
o
n
s
au
to
m
at
icall
y
d
u
r
in
g
tr
ain
i
n
g
p
h
ase.
T
h
e
f
i
n
al
s
tr
u
ctu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
w
a
s
a
n
al
y
ze
d
o
n
li
n
e
a
n
d
it
was
o
b
s
er
v
ed
th
at
t
h
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
w
as
b
etter
in
ter
m
s
o
f
C
P
U
ti
m
e,
test
i
n
g
er
r
o
r
an
d
th
e
f
in
al
n
u
m
b
er
o
f
h
id
d
en
n
o
d
es.
T
h
e
s
a
m
e
n
et
w
o
r
k
w
a
s
also
ap
p
lie
d
in
[
1
1
]
to
m
o
d
el
d
is
s
o
lv
ed
o
x
y
g
e
n
co
n
ce
n
tr
atio
n
i
n
ac
ti
v
at
ed
s
lu
d
g
e
W
W
T
P.
T
h
e
ca
p
ab
ilit
y
o
f
t
h
e
SO
R
B
FNN
m
o
d
el
i
n
m
o
d
el
p
r
ed
ictiv
e
co
n
tr
o
l
f
o
r
th
e
s
y
s
te
m
w
a
s
s
t
u
d
ied
.
T
h
e
d
ev
elo
p
ed
m
o
d
el
s
h
o
w
ed
t
h
at
an
ac
c
u
r
ate
p
r
ed
ictio
n
h
ad
b
ee
n
ac
h
iev
ed
.
T
h
e
ab
ilit
y
to
u
p
d
ate
h
id
d
en
n
o
d
es
o
f
t
h
e
R
B
F
i
n
cr
ea
s
ed
t
h
e
n
et
w
o
r
k
ac
cu
r
ac
y
to
ad
ap
t
to
n
o
n
li
n
ea
r
d
y
n
a
m
ic
s
y
s
te
m
.
An
o
th
er
ap
p
licatio
n
o
f
SOR
B
FNN
w
a
s
f
o
u
n
d
i
n
[
1
2
]
f
o
r
p
r
ed
ictio
n
o
f
ac
tiv
ated
s
l
u
d
g
e
b
u
lk
i
n
g
.
T
h
e
ai
m
o
f
t
h
is
s
tu
d
y
to
p
r
ed
ict
th
e
s
lu
d
g
e
v
o
l
u
m
e
in
d
e
x
ev
o
l
u
ti
o
n
.
T
h
e
ad
v
an
tag
e
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
w
a
s
t
h
e
ab
ilit
y
to
s
i
m
p
lify
a
n
d
acc
eler
ate
th
e
s
tr
u
c
tu
r
e
t
h
u
s
,
g
iv
i
n
g
a
b
etter
p
r
ed
ictio
n
o
f
s
l
u
d
g
e
v
o
lu
m
e
i
n
d
ex
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
t
h
is
w
o
r
k
,
th
e
m
a
in
o
b
j
ec
t
iv
e
i
s
to
m
o
d
el
SB
R
u
s
in
g
R
B
FNN
an
d
to
i
n
tr
o
d
u
ce
s
e
lf
-
o
r
g
an
izi
n
g
alg
o
r
ith
m
in
t
h
e
R
B
FNN
s
tr
u
ctu
r
e
to
en
h
a
n
ce
th
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
Sel
f
-
o
r
g
an
izin
g
al
g
o
r
ith
m
a
llo
w
s
th
e
n
et
w
o
r
k
s
tr
u
ct
u
r
e
to
g
r
o
w
o
r
p
r
u
n
e
w
it
h
r
esp
ec
t to
th
e
d
ata.
2
.
1
.
Ra
dia
l B
a
s
is
F
un
ct
io
n Ne
ur
a
l N
et
wo
rk
T
h
e
b
asic
o
f
R
B
FNN
ar
c
h
ite
ctu
r
e
co
m
p
r
is
e
s
o
f
t
h
r
ee
la
y
er
s
:
a
n
i
n
p
u
t
la
y
er
,
a
h
id
d
en
la
y
er
an
d
a
n
o
u
tp
u
t
la
y
er
.
T
h
e
n
et
w
o
r
k
s
tr
u
ctu
r
e
o
f
p
r
o
p
o
s
ed
R
B
FNN
co
n
s
i
s
t
o
f
s
i
x
i
n
p
u
t
n
o
d
es,
s
ix
h
i
d
d
en
n
o
d
es
an
d
o
n
e
o
u
tp
u
t
n
o
d
e.
T
h
e
co
n
ce
n
tr
ati
o
n
o
f
i
n
f
l
u
e
n
ts
s
u
c
h
a
s
c
h
e
m
i
ca
l
o
x
y
g
e
n
d
e
m
a
n
d
(
C
OD)
,
t
o
tal
o
r
g
an
ic
ca
r
b
o
n
(
T
OC
)
,
to
tal
n
itro
g
en
(
T
N)
,
t
o
tal
p
h
o
s
p
h
o
r
u
s
(
T
P
)
,
am
m
o
n
ia
n
i
tr
o
g
en
(
A
N)
,
an
d
m
i
x
e
d
liq
u
o
r
s
u
s
p
en
d
ed
s
o
lid
s
(
ML
S
S)
ar
e
th
e
i
n
p
u
t
t
o
th
e
n
et
w
o
r
k
f
o
r
p
r
ed
ictio
n
o
f
T
N,
T
P
o
r
A
N
ef
f
lu
e
n
t.
T
h
ese
in
p
u
t
an
d
o
u
tp
u
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
3
,
J
u
n
e
2
0
1
7
:
1
6
2
0
–
1
6
2
7
1622
p
ar
am
eter
s
ar
e
u
s
ed
to
tr
ai
n
R
B
FNN
n
et
w
o
r
k
.
T
h
e
ex
p
er
i
m
en
tal
d
ata
co
n
tai
n
s
2
1
r
ea
l
d
ata
p
o
in
ts
at
te
m
p
er
atu
r
e
o
f
4
0
˚
C
.
T
h
e
o
u
tp
u
t
o
f
t
h
e
p
r
o
p
o
s
ed
n
et
w
o
r
k
,
w
it
h
n
u
m
b
er
o
f
h
id
d
en
n
o
d
es
ar
e
ca
lcu
lated
a
s
E
q
u
atio
n
(
1
)
w
h
er
e
r
ep
r
esen
ts
th
e
in
p
u
t
o
f
th
e
n
et
w
o
r
k
,
=
(
,
,
,
,
,
)
,
w
ith
w
ei
g
h
t
s
,
at
o
u
tp
u
t la
y
er
an
d
(
)
is
th
e
o
u
tp
u
t o
f
Ga
u
s
s
ian
f
u
n
c
tio
n
as d
es
cr
ib
ed
in
E
q
u
atio
n
(
2
)
.
=
∑
=
1
(
)
(
1
)
(
)
=
|
|
−
|
|
2
⁄
(
2
)
T
h
e
v
alu
e
o
f
an
d
d
en
o
te
th
e
v
al
u
e
o
f
ce
n
ter
an
d
r
ad
iu
s
o
f
ea
ch
R
B
F
u
n
i
t
r
esp
ec
tiv
el
y
.
|
|
−
|
|
is
th
e
E
u
c
lid
ea
n
d
is
ta
n
ce
b
et
w
ee
n
an
d
.
R
ad
iall
y
s
y
m
m
etr
ic
b
asis
f
u
n
ctio
n
is
u
s
ed
as
an
ac
ti
v
atio
n
f
u
n
ctio
n
w
h
ic
h
m
ap
p
in
g
t
h
e
in
p
u
t
n
o
d
es
to
th
e
h
id
d
en
n
o
d
es
n
o
n
li
n
ea
r
l
y
.
T
h
u
s
,
th
e
tr
ai
n
i
n
g
o
f
ce
n
ter
an
d
r
ad
iu
s
o
f
ea
ch
R
B
F
u
n
it
a
r
e
co
n
d
u
cted
b
y
a
n
u
n
s
u
p
er
v
is
ed
lear
n
i
n
g
[
8
]
.
Fo
r
th
e
u
n
it
ce
n
ter
,
K
-
m
ea
n
s
cl
u
s
ter
i
n
g
al
g
o
r
ith
m
is
s
elec
ted
to
d
eter
m
i
n
e
t
h
e
p
ar
am
eter
o
f
h
id
d
en
n
eu
r
o
n
s
.
T
h
e
s
tan
d
ar
d
s
tep
s
f
o
r
o
b
tain
i
n
g
ce
n
ter
an
d
r
ad
iu
s
ar
e
d
escr
i
b
ed
as f
o
llo
w
:
1.
T
h
e
ce
n
ter
o
f
ea
c
h
R
B
F
u
n
it
is
i
n
itialized
r
a
n
d
o
m
l
y
w
i
th
r
esp
ec
t
to
th
e
tr
ain
in
g
d
ata.
T
h
e
v
al
u
e
o
f
ea
c
h
ce
n
ter
m
u
s
t b
e
d
if
f
er
e
n
t f
r
o
m
ea
ch
o
th
er
.
2.
C
alcu
late
E
u
clid
ea
n
d
is
ta
n
ce
s
b
et
w
ee
n
tr
ain
in
g
d
ata
an
d
th
e
ce
n
ter
s
o
f
ea
ch
R
B
F
an
d
ass
ig
n
ea
ch
o
f
t
h
e
tr
ain
i
n
g
d
ata
is
a
s
s
i
g
n
ed
to
th
e
n
ea
r
est v
al
u
e
o
f
t
h
e
ce
n
ter
s
.
3.
Ne
w
R
B
F c
en
ter
s
ar
e
ca
lcu
lat
ed
b
ased
o
n
th
e
av
er
ag
e
ce
n
ter
f
o
r
ea
ch
clu
s
ter
in
s
tep
(
2
)
.
4.
Go
to
s
tep
s
(
2
)
an
d
(
3
)
,
u
n
til t
h
e
R
B
F c
e
n
ter
s
r
e
m
ai
n
u
n
c
h
a
n
g
ed
f
o
r
th
e
s
u
b
s
eq
u
e
n
t iter
ati
o
n
s
.
5.
W
h
en
R
B
F c
en
ter
s
h
a
v
e
b
ee
n
d
eter
m
in
ed
,
t
h
e
r
ad
iu
s
i
s
ca
lc
u
lated
u
s
i
n
g
K
-
n
ea
r
est
n
ei
g
h
b
o
r
s
alg
o
r
ith
m
a
s
E
q
u
atio
n
(
3
)
:
=
√
∑
(
−
)
2
=
1
(
3
)
T
h
e
tr
ain
in
g
m
et
h
o
d
o
f
th
e
w
e
ig
h
ts
at
th
e
o
u
tp
u
t
la
y
er
ar
e
co
n
d
u
cted
in
s
u
p
er
v
i
s
ed
lear
n
in
g
[
8
]
.
T
h
is
is
ac
h
ie
v
ed
b
y
s
i
m
p
l
y
m
a
n
ip
u
l
atin
g
E
q
u
atio
n
(
1
)
in
a
m
atr
ix
f
o
r
m
as
s
h
o
w
n
in
E
q
u
a
tio
n
s
(
4
)
an
d
(
5
)
.
=
(
4
)
=
(
′
)
−
1
′
(
5
)
Fig
u
r
e
1
s
u
m
m
ar
ize
s
th
e
f
lo
w
o
f
R
B
FNN
alg
o
r
it
h
m
.
I
n
th
e
b
eg
in
n
i
n
g
,
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
is
ap
p
lied
to
th
e
d
atab
ase.
T
h
e
n
et
w
o
r
k
i
n
itializa
tio
n
s
tar
t
s
w
it
h
d
eter
m
in
atio
n
o
f
th
e
h
id
d
en
la
y
er
p
ar
a
m
eter
s
w
h
ic
h
ar
e
th
e
r
ad
iu
s
an
d
t
h
e
ce
n
ter
o
f
Gau
s
s
ia
n
f
u
n
ct
io
n
.
T
h
en
,
it
is
p
r
o
ce
e
d
w
it
h
d
eter
m
i
n
atio
n
o
f
w
ei
g
h
ts
at
o
u
tp
u
t
la
y
er
.
Af
ter
t
h
at,
w
e
ig
h
t
ad
j
u
s
t
m
e
n
t
i
s
e
x
ec
u
ted
.
On
ce
,
t
r
ain
in
g
p
h
ase
co
m
p
leted
it
w
il
l
b
e
f
o
llo
w
ed
b
y
n
et
w
o
r
k
e
v
alu
a
tio
n.
Fig
u
r
e
1
.
Flo
w
c
h
ar
t o
f
R
B
FN
N
alg
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Mo
d
ellin
g
a
n
d
E
va
lu
a
tio
n
o
f S
eq
u
en
tia
l B
a
tc
h
R
ea
cto
r
Usi
n
g
A
r
tifi
cia
l
N
eu
r
a
l Net
w
o
r
k
(
N
o
r
ja
n
n
a
h
Ha
z
a
li)
1623
2
.
2
.
Self
-
o
rg
a
nizin
g
Ra
dia
l B
a
s
is
F
un
ct
io
n Ne
ura
l N
et
w
o
rk
I
n
SOR
B
FNN,
t
h
e
h
id
d
en
n
o
d
es
ar
e
u
p
d
atin
g
its
s
tr
u
c
tu
r
e
b
ased
o
n
r
ate
n
o
d
e
ac
tiv
it
y
(
N
A
)
an
d
th
e
m
u
tu
al
i
n
f
o
r
m
atio
n
(
MI
)
.
T
h
e
f
o
llo
w
ex
p
la
n
atio
n
o
f
n
o
d
e
a
d
j
u
s
tin
g
a
n
d
s
p
lit
tin
g
m
ec
h
a
n
i
s
m
is
b
ased
o
n
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
i
n
[
1
1
]
an
d
[
1
2
]
,
an
d
it is
i
m
p
le
m
en
ted
i
n
t
h
is
w
o
r
k
.
C
a
lcu
lat
io
n
o
f
MI
is
b
ased
o
n
E
q
u
atio
n
(
6
)
w
h
ic
h
h
av
in
g
i
n
f
o
r
m
atio
n
o
f
s
tati
s
tical
d
ep
en
d
e
n
ce
b
et
w
ee
n
r
an
d
o
m
v
ar
iab
le
w
h
er
e
(
,
)
is
t
h
e
j
o
in
t
d
is
tr
ib
u
tio
n
,
(
)
an
d
(
)
ar
e
th
e
p
r
o
b
ab
ilit
y
d
en
s
it
y
f
u
n
ctio
n
,
is
t
h
e
o
u
tp
u
t
o
f
th
h
id
d
en
n
o
d
e
an
d
is
th
e
n
et
w
o
r
k
’
s
o
u
tp
u
t.
(
:
)
=
∑
(
,
,
)
2
(
,
)
(
)
(
)
(6
)
T
h
e
E
q
u
atio
n
(
7
)
also
ca
n
b
e
i
n
ter
p
r
et
in
ter
m
s
o
f
th
eir
Sh
a
n
n
o
n
en
tr
o
p
y
(
)
an
d
(
)
.
T
h
e
MI
is
p
o
s
itiv
e
an
d
eq
u
al
ze
r
o
if
an
d
ar
e
s
tati
s
tica
ll
y
in
d
ep
en
d
e
n
t.
(
:
)
≤
min
(
(
)
,
(
)
)
(7
)
T
h
is
b
o
u
n
d
(
E
q
u
atio
n
(
7
)
)
,
tak
in
g
to
g
et
h
er
w
it
h
(
:
)
≥
0
,
tells
th
at
th
e
n
o
r
m
alize
d
MI
,
(
:
)
is
as
in
E
q
u
atio
n
(
8
)
w
h
er
e
0
≤
(
:
)
≤
1
.
(
:
)
=
(
:
)
m
i
n
(
(
)
,
(
)
)
(
8
)
I
n
th
e
n
et
w
o
r
k
s
tr
u
ct
u
r
e
o
f
R
B
FNN,
th
e
co
n
n
ec
tio
n
is
d
ele
ted
if
n
o
r
m
alize
d
MI
v
al
u
e
i
s
ze
r
o
as
it
in
d
icate
s
th
at
th
e
n
o
d
e
an
d
ar
e
in
d
ep
en
d
en
t.
Fo
r
s
p
litt
i
n
g
n
o
d
e
ca
s
e,
t
h
e
N
A
is
ca
lc
u
lat
ed
as
in
E
q
u
atio
n
(9
)
w
h
er
e
is
th
e
ac
ti
v
e
f
ir
i
n
g
o
f
th
e
th
h
id
d
en
n
o
d
e,
is
th
e
MI
v
alu
e
o
f
th
e
th
h
id
d
en
n
o
d
e,
an
d
is
th
e
o
u
tp
u
t v
al
u
e
o
f
t
h
e
th
h
id
d
en
n
o
d
e.
=
|
√
(
)
(9
)
I
f
NA
i
s
g
r
ea
ter
th
a
n
th
r
es
h
o
l
d
NA
,
th
e
h
id
d
en
n
o
d
es
w
ill
b
e
s
p
lit
in
to
f
e
w
n
o
d
es.
T
h
e
c
en
ter
s
an
d
th
e
r
ad
iu
s
e
s
o
f
t
h
e
n
e
w
d
iv
id
e
d
h
id
d
en
n
o
d
es a
r
e
ex
p
lai
n
ed
i
n
E
q
u
atio
n
s
(
1
0
)
an
d
(
1
1
)
w
h
e
r
e
0
.
9
5
<
<
1
.
0
5
an
d
0
<
<
0
.
1
,
an
d
ar
e
th
e
ce
n
ter
an
d
r
ad
iu
s
o
f
th
e
th
h
i
d
d
en
n
o
d
e,
an
d
is
th
e
n
u
m
b
e
r
o
f
th
e
n
e
w
d
iv
id
ed
n
o
d
es to
b
e
d
ec
id
ed
b
y
th
e
r
ate
o
f
a
v
er
ag
e
f
ir
i
n
g
as E
q
u
atio
n
(
1
2
)
.
,
=
+
,
(
1
0
)
,
=
,
=
1
,
2
,
…
,
(
1
1
)
=
1
‖
−
‖
+
(
)
∑
(
)
=
1
,
(
=
1
,
2
,
…
,
)
(
1
2
)
T
h
e
w
eig
h
t
s
f
o
r
th
e
n
e
w
n
o
d
es
an
d
th
e
o
u
tp
u
t
la
y
er
ar
e
u
p
d
ated
b
ased
o
n
E
q
u
atio
n
s
(
1
3
)
an
d
(
1
4
)
w
h
er
e
is
th
e
allo
ca
ti
n
g
p
ar
a
m
eter
s
f
o
r
th
e
n
e
w
n
o
d
es,
(
)
is
th
e
o
u
tp
u
t
v
al
u
e
o
f
th
e
th
h
id
d
en
n
o
d
e,
,
(
)
is
t
h
e
o
u
tp
u
t
v
al
u
e
o
f
t
h
e
n
e
w
d
i
v
id
ed
th
h
id
d
en
n
o
d
e,
is
th
e
w
e
ig
h
t
o
f
t
h
e
th
h
id
d
en
n
o
d
e,
(
)
)
is
t
h
e
cu
r
r
e
n
t a
p
p
r
o
x
i
m
at
io
n
e
r
r
o
r
o
f
th
e
R
B
FN
N
(
E
q
u
atio
n
(
1
5
)
)
,
an
d
(
)
is
t
h
e
o
u
tp
u
t o
f
th
e
n
eu
r
al
n
et
w
o
r
k
an
d
̂
(
)
is
th
e
s
y
s
te
m
o
u
tp
u
t
f
o
r
th
e
cu
r
r
en
t
s
a
m
p
le
at
ti
m
e
.
,
=
.
(
)
−
(
)
.
,
(
)
,
(
1
3
)
∑
=
1
=
1
,
=
1
,
2
,
…
,
(
1
4
)
(
)
=
̂
(
)
−
(
)
,
(
1
5
)
T
h
e
s
u
m
m
ar
y
o
f
SOR
B
F
NN
i
s
ill
u
s
tr
ated
i
n
Fi
g
u
r
e
2
.
A
w
o
r
k
in
g
R
B
FNN
n
et
w
o
r
k
w
i
th
f
i
v
e
h
id
d
en
n
o
d
es
is
e
s
tab
lis
h
ed
f
ir
s
t
b
e
f
o
r
e
ca
lcu
lati
n
g
MI
.
I
f
MI
le
s
s
t
h
en
th
r
es
h
o
ld
MI
,
th
e
co
n
n
ec
t
io
n
w
ill
b
e
d
elete
d
.
E
ls
e,
N
A
w
ill b
e
ex
a
m
i
n
e
d
.
I
f
NA
h
i
g
h
er
t
h
an
t
h
r
es
h
o
ld
N
A
,
th
e
co
n
n
ec
tio
n
w
il
l b
e
d
iv
id
ed
in
to
t
w
o
n
o
d
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
3
,
J
u
n
e
2
0
1
7
:
1
6
2
0
–
1
6
2
7
1624
Fig
u
r
e
2
.
Flo
w
c
h
ar
t o
f
SO
FR
B
NN
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
Fo
r
R
B
FNN,
t
h
e
n
et
w
o
r
k
co
n
s
is
t
o
f
t
h
r
ee
la
y
er
s
w
h
ic
h
w
er
e
in
p
u
t,
h
id
d
en
an
d
o
u
tp
u
t
la
y
er
.
I
t
w
a
s
d
esig
n
ed
b
ased
o
n
th
e
n
u
m
b
er
o
f
h
id
d
en
n
eu
r
o
n
s
g
i
v
en
b
y
u
s
er
.
T
h
e
n
et
w
o
r
k
p
ar
am
e
ter
o
f
h
id
d
en
an
d
o
u
tp
u
t
la
y
er
w
er
e
d
eter
m
in
ed
s
ep
ar
atel
y
u
s
i
n
g
d
i
f
f
er
en
t
m
et
h
o
d
.
T
h
e
tr
ain
in
g
o
f
h
id
d
en
la
y
e
r
w
as
i
m
p
le
m
en
ted
u
s
i
n
g
u
n
s
u
p
er
v
is
ed
lear
n
i
n
g
m
et
h
o
d
.
I
n
u
n
s
u
p
er
v
is
ed
lear
n
in
g
m
e
th
o
d
,
o
u
tp
u
t
w
a
s
n
o
t
n
ec
e
s
s
ar
il
y
n
ee
d
ed
an
d
th
e
lear
n
i
n
g
w
as
d
ep
en
d
e
n
t
m
ai
n
l
y
o
n
in
p
u
t
d
ata.
T
h
e
c
en
ter
an
d
r
ad
iu
s
o
f
ea
ch
r
ad
ial
b
asis
f
u
n
ctio
n
u
n
it
w
er
e
d
eter
m
i
n
e
u
s
i
n
g
K
-
me
a
n
s
clu
s
ter
in
g
al
g
o
r
ith
m
to
f
in
d
t
h
e
b
est
ce
n
ter
s
w
it
h
r
esp
ec
t
to
th
e
i
n
p
u
t
d
ata.
A
ll
r
ad
iu
s
v
al
u
e
s
w
er
e
d
ef
i
n
ed
as
0
.
5
f
o
r
s
i
m
p
licit
y
s
i
n
ce
r
ad
i
u
s
d
id
n
o
t
a
f
f
ec
t
m
u
c
h
o
n
t
h
e
p
er
f
o
r
m
a
n
ce
.
T
h
e
w
ei
g
h
ts
at
o
u
tp
u
t
la
y
er
,
w
er
e
d
eter
m
i
n
ed
u
s
i
n
g
s
u
p
er
v
i
s
e
d
lear
n
i
n
g
m
e
th
o
d
.
I
n
co
n
tr
a
s
t
to
u
n
s
u
p
er
v
is
ed
lear
n
in
g
m
et
h
o
d
,
s
u
p
er
v
is
ed
l
ea
r
n
in
g
m
eth
o
d
r
eq
u
ir
ed
o
u
tp
u
t
d
ata.
T
h
e
lear
n
in
g
m
et
h
o
d
w
a
s
r
ea
lized
u
s
i
n
g
P
s
eu
d
o
in
v
er
s
e
tec
h
n
iq
u
e.
Af
t
er
all
R
B
FNN
p
ar
a
m
eter
s
w
e
r
e
in
it
ialized
,
t
h
e
w
ei
g
h
ts
w
e
r
e
f
u
r
th
er
ad
j
u
s
ted
u
s
i
n
g
Gr
ad
ien
t D
esce
n
t a
l
g
o
r
it
h
m
w
h
ic
h
h
elp
ed
to
im
p
r
o
v
e
n
et
w
o
r
k
p
er
f
o
r
m
an
ce
b
y
r
ed
u
c
i
n
g
o
u
tp
u
t e
r
r
o
r
.
SOR
B
FNN
a
lg
o
r
it
h
m
w
as
a
n
en
h
a
n
ce
m
e
n
t
o
f
R
B
FNN
al
g
o
r
ith
m
.
T
h
e
w
a
y
SO
R
B
FNN
ad
ap
ted
to
th
e
ch
a
n
g
es
w
a
s
b
y
ad
j
u
s
ti
n
g
th
e
n
e
t
w
o
r
k
s
ize
o
n
its
o
w
n
.
I
n
itiall
y
,
a
w
o
r
k
i
n
g
R
B
FN
N
w
i
th
f
i
v
e
h
id
d
en
n
eu
r
o
n
s
w
as
n
ee
d
ed
to
b
e
estab
lis
h
ed
.
As
th
e
d
ata
s
a
m
p
le
in
tr
o
d
u
ce
d
to
th
e
n
et
w
o
r
k
,
SOR
B
FNN
s
tar
ted
to
ca
lcu
late
MI
at
ea
ch
R
B
F
u
n
it
.
T
h
e
s
m
alle
s
t
MI
w
i
ll
b
e
co
m
p
ar
ed
w
ith
th
r
e
s
h
o
ld
MI
.
T
h
e
co
n
n
ec
tio
n
w
ill
b
e
d
elete
d
if
t
h
e
v
al
u
e
w
a
s
le
s
s
t
h
an
th
r
e
s
h
o
ld
v
al
u
e.
Fo
r
t
h
e
r
e
m
ai
n
in
g
R
B
F
u
n
it,
N
A
w
ill
b
e
f
u
r
t
h
er
e
v
alu
a
ted
.
T
h
e
h
ig
h
er
N
A
r
ate
w
i
ll
b
e
s
e
lecte
d
an
d
co
m
p
ar
ed
w
it
h
th
r
e
s
h
o
ld
N
A
.
I
f
t
h
e
ca
lcu
la
ted
NA
w
a
s
g
r
ea
ter
th
a
n
th
r
es
h
o
ld
NA
,
t
h
e
co
n
n
ec
tio
n
w
il
l b
e
d
iv
id
ed
in
to
t
w
o
n
o
d
es
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
T
P
p
r
ed
ic
tio
n
d
u
r
in
g
tr
ai
n
in
g
a
n
d
test
i
n
g
p
h
ase.
I
n
tr
ai
n
i
n
g
p
h
ase,
S
OR
B
FNN
o
n
l
y
s
co
r
es
0
.
0
2
8
4
o
f
MSE
v
alu
e
as
co
m
p
ar
ed
to
R
B
FNN
w
h
ic
h
is
0
.
0
1
4
8
.
T
h
e
v
al
u
e
o
f
2
f
o
r
SO
R
B
FNN
is
0
.
8
7
8
8
w
h
ile
f
o
r
R
B
F
NN
is
0
.
9
3
6
7
.
Ho
w
e
v
er
in
test
i
n
g
p
h
a
s
e,
SO
R
B
FNN
ac
h
ie
v
e
s
b
etter
MSE
w
i
th
0
.
0
3
1
3
an
d
2
w
i
th
0
.
8
4
4
2
.
T
h
e
d
etail
o
f
T
P
p
er
f
o
r
m
an
ce
i
s
s
h
o
w
n
in
T
ab
le
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Mo
d
ellin
g
a
n
d
E
va
lu
a
tio
n
o
f S
eq
u
en
tia
l B
a
tc
h
R
ea
cto
r
Usi
n
g
A
r
tifi
cia
l
N
eu
r
a
l Net
w
o
r
k
(
N
o
r
ja
n
n
a
h
Ha
z
a
li)
1625
Fig
u
r
e
3
.
C
o
m
p
ar
is
o
n
o
f
FF
N
N,
R
B
FNN
an
d
SO
R
B
FNN
m
o
d
ellin
g
f
o
r
T
P
T
ab
le
1
.
P
er
f
o
r
m
a
n
ce
r
esu
l
t f
o
r
T
P
T
r
a
i
n
i
n
g
M
S
E
M
A
D
2
F
F
N
N
0
.
0
5
0
8
0
.
2
7
5
0
0
.
7
8
2
9
R
B
F
N
N
0
.
0
1
4
8
0
.
3
0
4
0
0
.
9
3
6
7
S
O
R
B
F
N
N
0
.
0
2
8
4
0
.
2
9
3
7
0
.
8
7
8
8
T
e
st
i
n
g
M
S
E
M
A
D
2
F
F
N
N
0
.
0
3
7
2
0
.
2
9
1
1
0
.
8
1
4
6
R
B
F
N
N
0
.
3
2
7
3
0
.
4
9
4
2
-
0
.
6
3
0
0
S
O
R
B
F
N
N
0
.
0
3
1
3
0
.
2
8
1
2
0
.
8
4
4
2
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
T
N
esti
m
atio
n
as d
ep
icted
in
Fi
g
u
r
e
4
.
T
h
e
tr
ain
in
g
r
esu
lt i
n
d
icate
s
t
h
at
R
B
FNN
h
as
b
etter
ac
c
u
r
ac
y
t
h
a
n
SO
R
B
FNN
w
it
h
M
SE
0
.
0
1
0
4
an
d
0
.
0
2
4
5
r
esp
ec
tiv
el
y
.
T
h
e
v
al
u
e
o
f
2
f
o
r
SOR
B
FNN
is
0
.
8
9
0
1
w
h
ile
f
o
r
R
B
FNN
is
0
.
9
5
3
4
.
Me
a
n
w
h
ile,
SO
R
B
FN
N
g
i
v
es
g
o
o
d
esti
m
atio
n
o
v
er
R
B
FNN
w
it
h
MSE
a
n
d
2
v
alu
e
ar
e
0
.
0
5
6
9
an
d
0
.
7
2
8
2
(
r
ef
er
T
ab
le
2
)
.
Fig
u
r
e
4
.
C
o
m
p
ar
is
o
n
o
f
FF
N
N,
R
B
FNN
an
d
SO
R
B
FNN
m
o
d
ellin
g
f
o
r
T
N
T
ab
le
2
.
P
er
f
o
r
m
a
n
ce
r
esu
l
t f
o
r
T
N
T
r
a
i
n
i
n
g
M
S
E
M
A
D
2
F
F
N
N
0
.
0
9
6
8
0
.
3
6
9
7
0
.
5
6
6
6
R
B
F
N
N
0
.
0
1
0
4
0
.
2
6
4
5
0
.
9
5
3
4
S
O
R
B
F
N
N
0
.
0
2
4
5
0
.
2
3
3
7
0
.
8
9
0
1
T
e
st
i
n
g
M
S
E
M
A
D
2
F
F
N
N
0
.
1
1
2
8
0
.
4
1
0
4
0
.
4
6
1
2
R
B
F
N
N
2
.
8
4
6
6
1
.
1
0
9
2
-
1
2
.
6
0
0
7
S
O
R
B
F
N
N
0
.
0
5
6
9
0
.
3
0
8
3
0
.
7
2
8
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
3
,
J
u
n
e
2
0
1
7
:
1
6
2
0
–
1
6
2
7
1626
I
n
A
N
ap
p
r
o
x
i
m
atio
n
as
in
Fi
g
u
r
e
5
,
SOR
B
FN
N
d
e
m
o
n
s
tr
a
tes
g
o
o
d
ap
p
r
o
x
im
at
io
n
f
o
r
b
o
th
tr
ai
n
i
n
g
an
d
test
i
n
g
p
h
ases
co
m
p
ar
ed
to
R
B
FNN
an
d
FNN.
MSE
a
n
d
2
v
alu
e
d
u
r
in
g
tr
ain
in
g
f
o
r
SOR
B
FNN
ar
e
0
.
0
1
6
8
an
d
0
.
9
1
9
5
w
h
ile
f
o
r
R
B
FNN
ar
e
0
.
0
1
9
1
an
d
0
.
9
0
8
4
.
A
p
p
r
o
x
i
m
a
tio
n
f
o
r
A
N
d
u
r
i
n
g
test
in
g
p
h
a
s
e
w
as
d
if
f
ic
u
lt
to
ac
h
iev
ed
.
T
h
er
ef
o
r
e
th
e
r
esu
l
t
in
T
ab
le
3
s
h
o
w
t
h
at
er
r
o
r
f
o
r
FF
NN,
R
B
FNN
an
d
SOR
B
FN
N
ar
e
q
u
ite
h
u
g
e.
R
B
FNN
a
n
d
SOR
B
FNN
g
i
v
e
s
i
m
ilar
r
es
u
lt
w
it
h
MSE
0
.
1
3
0
8
an
d
2
0
.
2
8
3
3
.
Fig
u
r
e
5
.
C
o
m
p
ar
is
o
n
o
f
FF
N
N
,
R
B
FNN
an
d
SO
R
B
FNN
m
o
d
ellin
g
f
o
r
A
N
T
ab
le
3
.
P
er
f
o
r
m
a
n
ce
r
esu
l
t f
o
r
A
N
T
r
a
i
n
i
n
g
M
S
E
M
A
D
2
F
F
N
N
0
.
5
8
5
5
0
.
4
6
4
2
-
1
.
8
1
2
0
R
B
F
N
N
0
.
0
1
9
1
0
.
2
5
4
2
0
.
9
0
8
4
S
O
R
B
F
N
N
0
.
0
1
6
8
0
.
2
5
5
2
0
.
9
1
9
5
T
e
st
i
n
g
M
S
E
M
A
D
2
F
F
N
N
0
.
6
9
9
9
0
.
3
8
3
5
-
2
.
8
3
3
6
R
B
F
N
N
0
.
1
3
0
8
0
.
3
5
2
8
0
.
2
8
3
7
S
O
R
B
F
N
N
0
.
1
3
0
8
0
.
3
6
4
2
0
.
2
8
3
3
I
n
th
i
s
s
ec
tio
n
,
it
is
e
x
p
lai
n
ed
th
e
r
esu
lts
o
f
r
esear
ch
an
d
at
th
e
s
a
m
e
ti
m
e
is
g
iv
e
n
t
h
e
co
m
p
r
e
h
en
s
iv
e
d
is
c
u
s
s
io
n
.
R
e
s
u
lt
s
ca
n
b
e
p
r
ese
n
ted
i
n
f
i
g
u
r
es,
g
r
ap
h
s
,
tab
le
s
a
n
d
o
th
er
s
t
h
at
m
a
k
e
t
h
e
r
ea
d
er
u
n
d
er
s
ta
n
d
ea
s
il
y
[
2
]
,
[
5
]
.
T
h
e
d
is
cu
s
s
io
n
ca
n
b
e
m
ad
e
in
s
e
v
er
al
s
u
b
-
c
h
ap
ter
s
.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
esen
ts
t
h
e
m
o
d
ellin
g
o
f
SB
R
u
s
i
n
g
R
B
F
NN
an
d
S
OR
B
FN
N.
SO
R
B
FNN
h
as
a
ca
p
ab
ilit
y
o
f
g
r
o
w
in
g
a
n
d
p
r
u
n
i
n
g
t
h
e
n
et
w
o
r
k
s
tr
u
ct
u
r
e
i
n
lear
n
in
g
p
h
a
s
e
to
ad
ap
t
w
it
h
t
h
e
d
ata
b
eh
a
v
io
r
.
T
h
e
r
esu
lts
in
d
icate
t
h
at
SO
R
B
FNN
h
a
s
h
i
g
h
p
o
ten
tia
l
in
esti
m
ati
n
g
n
u
tr
ien
t
r
e
m
o
v
a
l
p
r
o
ce
s
s
.
T
h
e
er
r
o
r
esti
m
atio
n
i
n
te
s
ti
n
g
p
h
ase
f
o
r
SOR
B
FNN
is
m
u
ch
lo
w
er
as
co
m
p
ar
ed
to
R
B
FNN.
Ho
w
e
v
er
,
an
i
m
p
r
o
v
e
m
en
t
is
n
ee
d
ed
to
b
e
co
n
s
id
er
ed
in
f
u
tu
r
e
w
o
r
k
to
g
et
a
b
etter
co
ef
f
icie
n
t d
eter
m
i
n
atio
n
o
f
th
e
p
r
ed
ictio
n
.
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
t
h
an
k
t
h
e
R
esear
c
h
U
n
i
v
er
s
it
y
Gr
a
n
t
(
GUP
)
v
o
te
1
3
H7
0
,
Un
i
v
er
s
it
i
T
ek
n
o
lo
g
i M
ala
y
s
ia
f
o
r
t
h
e
f
i
n
an
cial
s
u
p
p
o
r
t.
RE
F
E
R
E
NC
E
S
[1
]
Y.
Hu
n
g
,
e
t
a
l
.
,
“
Ha
n
d
b
o
o
k
o
f
e
n
v
iro
n
m
e
n
t
a
n
d
w
a
ste
m
a
n
a
g
e
m
e
n
t,
”
S
in
g
a
p
o
re
,
W
o
rld
S
c
ien
ti
f
ic,
2
0
1
2
.
[2
]
M
.
K.
Ju
n
g
les
,
e
t
a
l
.,
“
S
e
q
u
e
n
ti
n
g
b
a
tch
re
a
c
to
r
o
p
e
ra
ti
o
n
f
o
r
trea
ti
n
g
w
a
st
e
w
a
te
r
w
it
h
a
e
ro
b
ic
g
ra
n
u
lar
slu
d
g
e
,
”
Bra
zill
ia
n
J
o
u
rn
a
l
o
f
Ch
e
mic
a
l
E
n
g
i
n
e
e
rin
g
,
v
o
l
/i
ss
u
e
:
31
(
1
)
,
p
p
.
2
7
–
33
,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Mo
d
ellin
g
a
n
d
E
va
lu
a
tio
n
o
f S
eq
u
en
tia
l B
a
tc
h
R
ea
cto
r
Usi
n
g
A
r
tifi
cia
l
N
eu
r
a
l Net
w
o
r
k
(
N
o
r
ja
n
n
a
h
Ha
z
a
li)
1627
[3
]
P.
Ku
n
d
u
,
e
t
a
l
.,
“
A
rti
f
i
c
ial
n
e
u
ra
l
n
e
tw
o
rk
m
o
d
e
li
n
g
f
o
r
b
io
lo
g
ic
a
l
re
m
o
v
a
l
o
f
o
rg
a
n
ic
c
a
rb
o
n
a
n
d
n
it
ro
g
e
n
f
ro
m
sla
u
g
h
terh
o
u
se
w
a
ste
wa
ter i
n
a
se
q
u
e
n
c
i
n
g
b
a
tch
re
a
c
to
r,
”
A
d
v
a
n
c
e
s in
Arti
f
icia
l
Ne
u
ra
l
S
y
ste
ms
,
v
o
l.
2
0
1
3
,
2
0
1
3
.
[4
]
M
.
M
.
Ha
m
e
d
,
e
t
a
l
.,
“
P
re
d
icti
o
n
o
f
w
a
ste
wa
ter
trea
t
m
e
n
t
p
lan
t
p
e
rf
o
rm
a
n
c
e
u
sin
g
a
rti
f
i
c
ial
n
e
u
ra
l
n
e
tw
o
rk
,
”
En
v
iro
n
me
n
ta
l
M
o
d
e
li
n
g
a
n
d
S
o
ft
wa
re
,
v
o
l
/i
ss
u
e
:
19
(
10
)
,
p
p
.
9
1
9
–
9
2
8
,
2
0
0
4
.
[5
]
F
.
S
.
M
jalli
,
e
t
a
l
.,
“
Us
e
o
f
a
rti
f
ic
ial
n
e
u
ra
l
n
e
tw
o
rk
b
lac
k
-
b
o
x
m
o
d
e
li
n
g
f
o
r
th
e
p
re
d
icti
o
n
o
f
w
a
st
e
w
a
t
e
r
trea
t
m
e
n
t
p
lan
ts
p
e
rf
o
rm
a
n
c
e
,
”
J
o
u
rn
a
l
o
f
E
n
v
iro
n
me
n
t
a
l
M
a
n
a
g
e
me
n
t,
v
o
l
/i
ss
u
e
:
83
(
3
)
,
p
p
.
3
2
9
–
3
3
8
,
2
0
0
7
.
[6
]
Ch
e
n
Q.,
e
t
a
l
.,
“
M
o
d
e
ll
i
n
g
o
f
w
a
ste
wa
ter
trea
t
m
e
n
t
p
ro
c
e
ss
u
sin
g
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
,
”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
8
th
W
o
rl
d
C
o
n
g
re
ss
o
n
I
n
telli
g
e
n
t
Co
n
tro
l
a
n
d
A
u
to
m
a
ti
o
n
,
Ji
n
a
n
,
Ch
in
a
,
2
0
1
0
.
[7
]
M
.
N.
Ka
sh
a
n
i
a
n
d
S
.
S
h
a
h
h
o
ss
e
in
i,
“
A
m
e
th
o
d
o
l
o
g
y
f
o
r
m
o
d
e
ll
in
g
b
a
tch
re
a
c
to
rs
u
sin
g
g
e
n
e
r
a
li
z
e
d
d
y
n
a
m
ic
n
e
u
ra
l
n
e
tw
o
rk
s,
”
Ch
e
mic
a
l
E
n
g
i
n
e
e
rin
g
J
o
u
rn
a
l,
v
o
l
/i
ss
u
e
:
1
5
9
(
1
-
3
)
,
p
p
.
1
9
5
–
2
0
2
,
2
0
1
0
.
[8
]
S
.
A
.
M
irb
a
g
h
e
ri,
e
t
a
l.
,
“
P
e
rf
o
rm
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
ra
n
e
b
io
r
e
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
str
i
a
l
w
a
ste
wa
ter
u
sin
g
r
a
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
s,
”
J
o
u
rn
a
l
o
f
En
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
,
vol
/i
ss
u
e
:
13
(
1
)
,
p
p
.
1
7
,
2
0
1
5
.
[9
]
M.
Ba
g
h
e
ri,
e
t
a
l
.,
“
M
o
d
e
li
n
g
o
f
a
s
e
q
u
e
n
c
in
g
b
a
tch
re
a
c
to
r
t
re
a
ti
n
g
m
u
n
icip
a
l
w
a
ste
wa
ter
u
s
in
g
m
u
lt
i
-
la
y
e
r
p
e
rc
e
p
tro
n
a
n
d
ra
d
ial
b
a
sis
f
u
n
c
t
io
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s,
”
Pr
o
c
e
ss
S
a
fety
a
n
d
En
v
ir
o
n
me
n
t
a
l
Pro
tec
ti
o
n
,
v
o
l.
9
3
,
p
p
.
1
1
1
–
1
2
3
,
2
0
1
5
.
[1
0
]
H.
Ha
n
,
e
t
a
l
.
,
“
Re
se
a
rc
h
o
n
a
n
o
n
li
n
e
se
lf
-
o
rg
a
n
izin
g
ra
d
ial
b
a
sis
f
u
n
c
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
,
”
Ne
u
ra
l
Co
mp
u
t
in
g
a
n
d
Ap
p
li
c
a
ti
o
n
s,
vo
l
/i
ss
u
e
:
19
(
5
)
,
p
p
.
6
6
7
-
6
7
6
,
2
0
1
0
.
[1
1
]
H.
G
.
H
a
n
,
e
t
a
l
.
,
“
M
o
d
e
l
p
re
d
ic
ti
v
e
c
o
n
tro
l
o
f
d
isso
lv
e
d
o
x
y
g
e
n
c
o
n
c
e
n
trati
o
n
b
a
se
d
o
n
a
se
lf
-
o
rg
a
n
izin
g
RBF
n
e
u
ra
l
n
e
tw
o
rk
,
”
Co
n
tr
o
l
E
n
g
i
n
e
e
rin
g
Pr
a
c
ti
c
e
,
v
o
l
/i
ss
u
e
:
20
(
4
)
,
p
p
.
4
6
5
–
4
7
6
,
2
0
1
2
.
[1
2
]
H.
G
.
H
a
n
a
n
d
J.
F
.
Qia
o
,
“
P
re
d
ic
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
lf
-
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
/i
s
su
e
:
22
(
6
)
,
p
p
.
1
1
0
3
–
1
1
1
2
,
2
0
1
2
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
No
rjan
n
a
h
Ha
z
a
li
re
c
e
iv
e
d
h
e
r
B.
En
g
.
Ho
n
s
(El
e
c
tri
c
-
M
e
c
h
a
tr
o
n
ics
)
f
ro
m
Un
iv
e
rsiti
Isla
m
A
n
tara
b
a
n
g
sa
in
2
0
1
1
.
S
h
e
is
c
u
rre
n
tl
y
w
o
rk
in
g
to
w
a
rd
h
e
r
M
a
ste
r
d
e
g
re
e
in
M
e
c
h
a
tro
n
ic
s
En
g
in
e
e
rin
g
a
t
F
a
c
u
l
ty
o
f
El
e
c
ri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
l
o
g
i
M
a
lay
sia
.
He
r
cu
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
o
d
e
li
n
g
a
n
d
o
p
ti
m
isa
ti
o
n
o
f
m
e
m
b
ra
n
e
wa
ste
w
a
ter
trea
t
m
e
n
t
p
ro
c
e
ss
a
n
d
o
th
e
r
m
a
n
u
f
a
c
tu
rin
g
s
y
ste
m
.
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
ss
o
c
iate
P
ro
f
e
ss
o
r
a
t
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
la
y
sia
(UT
M
).
S
h
e
is
c
u
rr
e
n
tl
y
th
e
He
a
d
De
p
a
rtm
e
n
t
o
f
Co
n
tro
l
a
n
d
M
e
c
h
a
tro
n
ic
s
En
g
in
e
e
rin
g
De
p
a
rtme
n
t
a
t
th
e
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
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
E
n
g
in
e
e
rin
g
m
a
jo
rin
g
in
Co
n
tro
l
i
n
Ju
ly
2
0
0
9
.
S
h
e
is
a
c
ti
v
e
ly
in
v
o
lv
e
d
i
n
re
se
a
rc
h
in
g
a
n
d
tea
c
h
in
g
in
th
e
f
ield
o
f
in
d
u
str
ial
p
r
o
c
e
ss
c
o
n
tr
o
l.
He
r
e
x
p
e
rti
se
is
in
m
o
d
e
ll
i
n
g
a
n
d
c
o
n
tr
o
l
o
f
in
d
u
strial
p
r
o
c
e
s
s
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
f
e
r
e
n
t
t
y
p
e
s
o
f
d
o
m
e
stic
a
n
d
in
d
u
strial
w
a
ste
wa
ter
trea
t
m
e
n
t
tec
h
n
o
lo
g
y
to
wa
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
.
S
y
a
h
ira
Ib
ra
h
im
re
c
e
i
v
e
d
h
e
r
B.
En
g
.
Ho
n
s
(El
e
c
tri
c
-
Co
n
tr
o
l
a
n
d
In
stru
m
e
n
tatio
n
)
a
n
d
M
S
c
.
o
f
En
g
in
e
e
rin
g
(El
e
c
tri
c
a
l)
f
ro
m
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
lay
sia
in
2
0
1
1
a
n
d
2
0
1
5
re
sp
e
c
ti
v
e
ly
.
S
h
e
is
c
u
rre
n
tl
y
w
o
rk
in
g
to
wa
rd
h
e
r
P
h
D
i
n
p
ro
c
e
ss
c
o
n
tr
o
l
a
t
F
a
c
u
lt
y
o
f
El
e
c
rica
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
la
y
sia
.
He
r
cu
rre
n
t
re
se
a
rc
h
in
tere
s
ts
in
c
lu
d
e
m
o
d
e
li
n
g
o
f
n
e
a
r
-
in
f
ra
re
d
sp
e
c
tro
sc
o
p
y
a
n
d
m
e
m
b
ra
n
e
f
il
tratio
n
u
si
n
g
a
rti
f
icia
l
in
telli
g
e
n
t
sy
s
tem
.
Evaluation Warning : The document was created with Spire.PDF for Python.