I
nte
rna
t
io
na
l J
o
urna
l o
f
Appl
ied P
o
wer
E
ng
i
neer
ing
(
I
J
AP
E
)
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
,
p
p
.
692
~
7
0
2
I
SS
N:
2
2
5
2
-
8
7
9
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijap
e.
v
1
5
.
i
2
.
p
p
692
-
702
692
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//
ija
p
e.
ia
esco
r
e.
co
m/
Predic
tive mo
deli
ng
and o
ptimiza
ti
o
n of paper mill
u
sing
hybrid
ma
chine learning
techniqu
es
Abhi
j
it
Sin
g
h
B
ha
k
un
i
,
Sa
n
deep
K
um
a
r
Su
no
ri
,
P
ra
deep
J
un
ej
a
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
mm
u
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
G
r
a
p
h
i
c
Er
a
H
i
l
l
U
n
i
v
e
r
si
t
y
,
N
a
i
n
i
t
a
l
,
I
n
d
i
a
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
mm
u
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
G
r
a
p
h
i
c
Er
a
D
e
e
me
d
To
B
e
U
n
i
v
e
r
si
t
y
,
D
e
h
r
a
d
u
n
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
2
2
,
2
0
2
5
R
ev
is
ed
Feb
1
2
,
2
0
2
6
Acc
ep
ted
Ma
r
1
2
,
2
0
2
6
Th
e
p
a
p
e
r
h
a
s
p
lay
e
d
a
v
it
a
l
ro
l
e
in
th
e
li
fe
o
f
h
u
m
a
n
s
fro
m
a
n
c
ien
t
ti
m
e
s
c
o
v
e
rin
g
a
v
a
st
ra
n
g
e
o
f
a
p
p
li
c
a
ti
o
n
s
s
u
c
h
a
s
wri
ti
n
g
,
p
a
c
k
a
g
i
n
g
,
a
n
d
p
rin
ti
n
g
.
Th
e
p
re
se
n
t
p
a
p
e
r
is
p
re
se
n
ti
n
g
a
c
o
m
p
re
h
e
n
siv
e
re
v
iew
o
f
v
a
ri
o
u
s
o
p
ti
m
iza
ti
o
n
a
n
d
c
o
n
tro
l
m
e
th
o
d
o
lo
g
ies
,
ra
n
g
in
g
fro
m
c
o
n
v
e
n
ti
o
n
a
l
to
a
d
v
a
n
c
e
d
o
n
e
s,
p
e
rtai
n
in
g
to
th
e
p
a
p
e
r
m
il
l.
T
h
e
fi
n
a
l
g
o
a
l
o
f
t
h
e
se
c
o
n
tr
o
l
stra
teg
ies
is
to
u
p
g
ra
d
e
t
h
e
m
il
l’
s
p
ro
d
u
c
ti
o
n
a
n
d
q
u
a
li
t
y
i
n
p
r
e
se
n
c
e
o
f
m
u
lt
ip
le
tec
h
n
ica
l
c
h
a
ll
e
n
g
e
s
s
u
c
h
a
s
n
o
n
li
n
e
a
r
a
n
d
m
u
lt
i
v
a
riab
le
n
a
tu
r
e
o
f
th
e
i
n
v
o
lv
e
d
p
ro
c
e
ss
e
s,
v
a
ri
o
u
s
d
istu
rb
a
n
c
e
p
a
ra
m
e
ters
,
a
n
d
ti
m
e
d
e
lay
s.
I
n
th
is
wo
r
k
,
t
h
e
in
teg
ra
ti
o
n
o
f
m
a
c
h
in
e
lea
rn
i
n
g
wit
h
p
a
p
e
r
m
il
l
p
ro
c
e
ss
is
il
lu
stra
ted
.
F
o
r
a
n
y
m
a
n
u
fa
c
tu
ri
n
g
p
ro
c
e
ss
,
th
e
fin
a
l
p
r
o
d
u
c
t
q
u
a
li
ty
is
th
e
k
e
y
g
o
a
l.
Th
e
re
a
re
v
a
ri
o
u
s
trad
it
i
o
n
a
l
tec
h
n
iq
u
e
s
wh
ich
h
a
v
e
a
lre
a
d
y
b
e
e
n
p
ra
c
ti
c
e
d
fo
r
fi
n
a
l
p
ro
d
u
c
e
d
p
a
p
e
r
q
u
a
li
t
y
i
n
p
a
p
e
r
m
il
ls.
Th
is
p
a
p
e
r
h
ig
h
li
g
h
ts
th
e
c
a
p
a
b
i
li
ty
o
f
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM
)
a
lg
o
rit
h
m
to
a
ss
e
ss
th
e
p
ro
d
u
c
e
d
p
a
p
e
r
q
u
a
li
ty
,
c
a
p
t
u
ri
n
g
th
e
two
c
ru
c
ial
in
p
u
ts
v
iz.
th
e
p
u
lp
c
o
n
siste
n
c
y
a
n
d
t
h
e
h
e
a
d
b
o
x
lev
e
l.
Th
e
b
a
sic
g
o
a
l
o
f
t
h
is r
e
se
a
rc
h
i
s two
fo
l
d
,
firstl
y
it
p
re
se
n
ts
a
n
e
x
h
a
u
sti
v
e
li
tera
tu
re
su
rv
e
y
e
x
p
l
o
rin
g
v
a
rio
u
s
stra
teg
ies
wh
ich
a
re
p
ra
c
ti
c
e
d
c
u
rre
n
tl
y
i
n
th
e
d
o
m
a
in
o
f
c
o
n
tr
o
l
a
n
d
o
p
ti
m
iza
ti
o
n
o
f
v
a
rio
u
s
p
a
p
e
r
m
il
l
p
ro
c
e
ss
e
s.
S
e
c
o
n
d
l
y
,
it
i
n
ten
d
s
to
d
e
v
e
l
o
p
a
n
d
e
v
a
lu
a
te
v
a
rio
u
s
S
V
M
a
n
d
S
V
M
-
RF
h
y
b
r
i
d
m
o
d
e
ls
u
si
n
g
M
AT
LAB
fo
r
a
ss
e
ss
m
e
n
t
o
f
q
u
a
li
t
y
o
f
fi
n
a
l
p
r
o
d
u
c
t
o
n
b
a
sis
o
f
two
p
a
ra
m
e
ters
-
p
u
lp
c
o
n
siste
n
c
y
a
n
d
h
e
a
d
b
o
x
lev
e
l.
F
i
n
a
ll
y
,
g
e
n
e
ti
c
a
lg
o
ri
th
m
h
a
s
b
e
e
n
e
m
p
lo
y
e
d
i
n
M
A
TL
AB
fo
r
m
u
lt
iv
a
riate
o
p
ti
m
iza
ti
o
n
.
K
ey
w
o
r
d
s
:
C
o
n
tr
o
l
Gen
etic
alg
o
r
ith
m
Hea
d
b
o
x
le
v
el
Hy
b
r
id
m
ac
h
in
e
lear
n
i
n
g
Op
tim
izatio
n
Pap
er
m
ill
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
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
:
Ab
h
ijit
Sin
g
h
B
h
ak
u
n
i
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
Gr
ap
h
ic
E
r
a
Hill Un
iv
e
r
s
ity
B
h
im
tal,
Nain
ital,
I
n
d
ia
E
m
ail:
ab
h
ijit
b
h
ak
u
n
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
A
p
iv
o
tal
r
o
le
h
as b
ee
n
p
lay
ed
b
y
p
a
p
er
m
ills
f
r
o
m
an
cien
t
ti
m
es wh
en
its
in
v
en
tio
n
was d
o
n
e
b
y
C
ai
L
u
n
in
1
0
5
A.
D
b
y
p
o
u
n
d
i
n
g
p
u
lp
f
r
o
m
a
m
ix
o
f
r
ag
s
,
m
u
lb
er
r
y
b
ar
k
,
an
d
h
em
p
,
an
d
f
l
atten
in
g
it
in
to
th
in
s
h
ee
ts
.
W
ith
th
e
p
ass
ag
e
o
f
ti
m
e,
th
er
e
ar
e
h
u
g
e
c
h
an
g
es in
p
ap
er
m
ill'
s
o
p
er
atio
n
d
y
n
am
i
cs.
Pap
er
p
r
o
d
u
ctio
n
h
as
b
ee
n
r
em
ar
k
a
b
le
ev
id
en
c
e
o
f
h
u
m
a
n
cr
ea
tiv
ity
an
d
te
ch
n
o
lo
g
y
ev
o
l
u
tio
n
in
th
e
d
o
m
ain
o
f
in
d
u
s
tr
ial
m
an
u
f
ac
tu
r
in
g
.
T
h
e
p
a
p
er
is
a
m
o
s
t
an
cien
t
m
ed
iu
m
o
f
co
m
m
u
n
icatio
n
wh
ich
h
as
p
r
o
v
ed
to
b
e
a
k
ey
s
to
n
e
in
p
r
o
p
a
g
atin
g
th
e
id
ea
s
,
cu
ltu
r
e
,
an
d
k
n
o
wled
g
e
o
v
er
g
en
er
atio
n
s
.
Ho
wev
er
,
th
e
p
ap
er
p
r
o
d
u
c
tio
n
o
f
h
ig
h
q
u
ality
is
a
h
ig
h
ly
m
u
ltiv
ar
iab
le
an
d
i
n
tr
icate
p
r
o
ce
s
s
th
at
r
eq
u
ir
es
a
s
tr
ict
m
o
n
ito
r
in
g
an
d
co
n
tr
o
l o
f
ea
ch
s
tep
o
f
th
is
p
r
o
ce
s
s
.
I
t
is
a
co
m
p
lex
p
r
o
ce
s
s
o
f
in
ter
ac
tio
n
o
f
ch
em
ical,
m
ec
h
an
ical,
an
d
e
n
v
ir
o
n
m
en
ta
l
p
ar
a
m
eter
s
d
u
r
in
g
th
e
p
ap
er
p
r
o
d
u
ctio
n
p
r
o
ce
s
s
th
at
m
ak
es
it
d
if
f
ic
u
lt
to
o
p
tim
ize
g
o
o
d
q
u
ality
p
r
o
d
u
ctio
n
.
I
t
p
lead
s
a
p
r
ess
in
g
co
n
ce
r
n
t
o
m
ain
tain
p
o
s
itiv
e
f
av
o
u
r
a
b
le
co
n
d
itio
n
s
o
f
s
o
m
e
v
ital
p
ar
am
eter
s
s
u
ch
as
h
ea
d
b
o
x
lev
el
a
n
d
p
u
lp
co
n
s
is
ten
cy
wh
ich
d
ir
ec
tly
af
f
ec
t th
e
q
u
ality
o
f
en
d
p
r
o
d
u
ct.
T
h
e
v
ar
iatio
n
s
o
f
th
ese
p
ar
am
eter
s
to
th
e
o
p
tim
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
P
r
ed
ictive
mo
d
elin
g
a
n
d
o
p
timiz
a
tio
n
o
f p
a
p
er mill u
s
in
g
h
yb
r
id
ma
ch
in
e
…
(
A
b
h
ijit
S
in
g
h
B
h
a
k
u
n
i
)
693
v
alu
es
m
ay
r
esu
lt
in
to
d
ef
ec
ts
s
u
ch
as
lo
w
p
r
in
tab
ilit
y
,
n
o
n
-
u
n
if
o
r
m
th
ick
n
ess
,
an
d
lo
w
m
ec
h
an
ical
s
tr
en
g
th
.
E
n
g
in
ee
r
s
an
d
r
esear
ch
er
s
h
a
v
e
ad
d
r
ess
ed
th
ese
ch
allen
g
es
with
th
e
h
elp
o
f
th
e
m
o
s
t
r
e
ce
n
t
co
m
p
u
tatio
n
al
p
r
ac
tices
,
in
clu
d
in
g
ar
tific
ial
in
tellig
en
ce
an
d
m
ac
h
in
e
lear
n
i
n
g
.
T
h
e
s
ig
n
if
ican
ce
o
f
m
ac
h
in
e
le
ar
n
in
g
(
ML
)
in
th
e
ex
p
l
o
itatio
n
o
f
th
e
v
ar
io
u
s
m
an
u
f
ac
tu
r
in
g
p
r
o
ce
s
s
es
was
id
en
tifie
d
with
its
ap
p
licatio
n
s
th
at
d
if
f
er
in
ap
p
licatio
n
if
o
p
er
atio
n
al
s
tr
ateg
ies
o
r
ev
e
n
th
e
m
ain
ten
an
ce
o
f
eq
u
ip
m
en
t.
T
o
tak
e
a
n
ex
a
m
p
le,
p
ass
iv
e
o
p
er
atio
n
al
s
p
ac
e
in
ter
ac
tio
n
co
n
tr
o
l
ex
is
tin
g
in
m
o
r
e
p
r
ec
is
io
n
i
n
p
r
o
d
u
ctio
n
en
v
ir
o
n
m
e
n
t
o
f
p
ap
er
m
ills
th
at
ar
e
f
o
u
n
d
ed
o
n
r
o
b
o
tics
m
illi
n
g
s
tr
ateg
ies
[
1
]
.
I
n
ad
d
itio
n
,
th
e
o
p
tim
izatio
n
o
f
th
e
p
o
wer
s
y
s
tem
s
th
at
u
s
ed
to
b
e
im
p
lem
en
t
ed
in
th
e
tr
ad
itio
n
a
l
s
en
s
e
h
ig
h
lig
h
ts
th
e
lik
elih
o
o
d
o
f
in
co
r
p
o
r
atio
n
o
f
m
o
d
er
n
tec
h
n
o
lo
g
y
to
ac
h
iev
e
ef
f
icien
cy
in
th
e
f
u
n
ctio
n
in
g
o
f
t
h
e
s
y
s
tem
[
2
]
.
In
th
e
r
ec
e
n
t
s
tu
d
ies,
em
p
h
asi
s
is
laid
m
o
r
e
o
n
in
ter
v
al
ty
p
e
3
f
u
zz
y
lo
g
ic
s
y
s
tem
s
,
wh
ich
d
ep
icts
th
e
n
ew
m
eth
o
d
s
u
s
ed
to
ad
d
r
ess
th
e
u
n
ce
r
tain
ties
in
th
e
m
a
n
u
f
ac
tu
r
in
g
p
r
o
ce
s
s
es
[
3
]
.
L
ik
e
th
is
m
eth
o
d
,
o
n
e
tech
n
iq
u
e
was
ca
lled
as
f
ib
er
esti
m
atio
n
tech
n
iq
u
e
was
ap
p
lied
to
im
p
r
o
v
e
th
e
ef
f
icien
t
n
et
-
b
ased
p
atch
class
if
icatio
n
[
4
]
.
Alo
n
g
with
it,
wh
en
ac
co
m
p
an
ie
d
with
tech
n
iq
u
e
wh
ich
f
o
cu
s
es
o
n
d
e
g
r
ad
atio
n
o
f
ef
f
lu
en
t,
it
n
o
t
o
n
ly
r
esu
lts
in
s
tab
ilit
y
o
f
t
h
e
e
n
v
ir
o
n
m
en
t,
b
u
t
also
o
p
er
atio
n
al
co
n
t
r
o
l
o
f
p
a
p
er
m
ill
s
ec
to
r
[
5
]
.
T
h
e
p
ap
er
m
ills
h
av
e
a
s
er
io
u
s
o
p
er
atio
n
al
p
r
o
b
lem
,
wh
ic
h
is
tr
im
lo
s
s
m
in
im
izatio
n
.
I
t
tak
es
p
lace
wh
en
ju
m
b
o
r
ee
ls
ar
e
cu
t
in
th
e
in
te
r
m
ed
ia
te
r
o
lls
.
T
h
is
h
as
b
ee
n
p
r
o
v
e
n
b
y
r
ec
en
t
s
tu
d
ies
wh
ich
h
av
e
s
h
o
wn
th
at
s
m
ar
t
o
p
tim
izatio
n
tech
n
iq
u
es
s
u
ch
as
r
ein
f
o
r
ce
m
e
n
t
ar
tific
ial
b
ee
co
lo
n
y
alg
o
r
ith
m
ca
n
g
r
ea
tly
m
in
im
is
e
tr
im
lo
s
s
an
d
r
elate
d
c
o
s
ts
[
6
]
.
Oth
er
ar
ea
s
o
f
s
tu
d
y
r
elate
d
to
p
ap
er
m
ills
in
clu
d
e
s
af
ety
co
n
ce
r
n
.
Ad
v
an
ce
d
p
r
o
tectio
n
s
y
s
tem
s
s
u
ch
as
f
ib
er
o
p
tic
s
en
s
o
r
s
an
d
ar
c
-
f
lash
d
etec
tio
n
r
elay
s
h
av
e
b
e
en
s
h
o
wn
to
r
e
d
u
ce
th
e
a
r
c
-
f
la
s
h
en
er
g
y
lev
els
b
y
u
p
to
9
0
p
er
ce
n
t
an
d
m
ak
e
th
e
wo
r
k
in
g
e
n
v
ir
o
n
m
en
t
s
ig
n
if
ican
tly
s
af
er
[
7
]
.
T
h
e
in
co
r
p
o
r
atio
n
o
f
c
o
m
p
u
te
r
-
b
ased
co
n
tr
o
l
s
y
s
tem
s
h
as
b
ee
n
in
s
tr
u
m
en
tal
in
en
s
u
r
in
g
t
h
at
m
ills
th
at
h
av
e
ad
o
p
ted
au
to
m
atio
n
n
o
t
o
n
ly
m
ain
tain
ed
s
tab
ilit
y
with
in
th
eir
p
r
o
ce
s
s
es
b
u
t
also
in
cr
ea
s
e
d
th
eir
p
r
o
d
u
ctio
n
th
r
o
u
g
h
p
u
t
with
a
h
ig
h
d
e
g
r
ee
o
f
r
ea
l
tim
e
d
ata
u
s
e
a
n
d
cl
o
s
e
co
n
tr
o
l
l
o
g
ic
[
8
]
.
Ov
er
th
e
last
f
ew
y
ea
r
s
,
i
n
teg
r
ated
m
ills
h
av
e
tu
r
n
e
d
m
o
r
e
a
n
d
m
o
r
e
to
war
d
s
p
r
ed
ictiv
e
p
lan
n
in
g
p
r
o
ce
d
u
r
es
an
d
d
is
cr
ete
-
ev
en
t
s
im
u
latio
n
in
o
r
d
er
t
o
cr
ea
te
p
r
o
d
u
ctio
n
s
ch
ed
u
les wh
ich
ar
e
m
o
r
e
r
esi
s
tan
t a
n
d
s
tab
le
ev
en
wh
e
n
th
e
r
e
ar
e
o
p
er
atio
n
al
d
is
tu
r
b
an
ce
s
[
9
]
.
On
e
o
f
th
e
r
ec
en
t
d
ev
elo
p
m
en
t
s
th
at
ca
n
b
e
id
en
tifie
d
is
th
e
in
clu
s
io
n
o
f
en
er
g
y
an
d
r
eso
u
r
ce
f
lex
ib
ilit
y
in
th
e
p
r
o
d
u
ctio
n
p
lan
n
in
g
p
r
o
ce
s
s
es.
As
an
illu
s
tr
atio
n
,
o
p
er
atio
n
al
f
ea
tu
r
es
o
f
th
e
s
team
p
o
wer
g
en
e
r
atio
n
a
n
d
its
co
n
tr
ib
u
tio
n
t
o
th
e
g
r
id
s
er
v
ices
ca
n
b
e
em
b
ed
d
e
d
in
t
h
e
s
ch
ed
u
lin
g
f
r
am
ewo
r
k
s
to
en
a
b
le
m
ills
s
ec
u
r
e
an
ad
d
itio
n
al
r
ev
e
n
u
e
an
d
a
s
tab
le
an
d
r
eliab
le
o
p
er
atio
n
[
1
0
]
.
A
n
o
th
er
im
p
o
r
tan
t
f
ield
o
f
r
esear
ch
is
f
au
lt
d
etec
tio
n
an
d
in
c
r
ea
s
in
g
t
h
e
r
esil
ien
ce
o
f
th
e
s
y
s
tem
.
Deta
iled
s
y
s
te
m
s
th
at
co
m
b
in
e
ad
ap
tiv
e
p
r
i
n
cip
al
co
m
p
o
n
e
n
t
an
aly
s
is
,
f
u
zz
y
lo
g
ic
m
eth
o
d
s
,
an
d
ar
tific
ial
n
e
u
r
al
n
etwo
r
k
s
h
av
e
b
ee
n
f
o
u
n
d
to
b
e
q
u
ite
u
s
ef
u
l
in
d
etec
tin
g
f
au
lts
in
lar
g
e
-
s
ca
le
ch
em
ical
an
d
p
u
lp
p
r
o
ce
s
s
es
an
d
th
u
s
en
ab
le
d
ec
en
tr
alize
d
f
a
u
lt
-
to
l
er
an
t
co
n
tr
o
ls
[
1
1
]
.
W
astewa
ter
an
d
s
lu
d
g
e
m
an
a
g
em
en
t
r
em
ain
s
a
k
ey
is
s
u
e
o
f
co
n
ce
r
n
,
p
ar
ticu
lar
ly
to
s
m
all
p
ap
er
m
ills
wh
er
e
ag
r
icu
ltu
r
al
r
esid
u
es
ar
e
u
s
ed
as
f
ee
d
s
to
ck
.
T
h
e
elec
tr
o
ch
em
ical
tr
ea
tm
en
t
m
eth
o
d
s
h
a
v
e
b
ee
n
d
em
o
n
s
tr
ated
to
b
e
ef
f
ec
tiv
e
in
en
h
an
cin
g
th
e
s
lu
d
g
e
s
ettlin
g
an
d
f
iltra
tio
n
as
well
as
f
ac
ilit
atin
g
th
e
b
en
ef
icial
r
eu
s
e
o
f
th
e
r
esu
ltin
g
b
y
-
p
r
o
d
u
cts as a
lter
n
ativ
e
s
o
u
r
ce
s
o
f
f
u
el
o
r
as a
d
d
i
tiv
es in
b
u
ild
in
g
m
ater
ials
[
1
2
]
.
T
h
e
u
s
e
o
f
m
o
d
el
-
b
ased
p
r
ed
i
ctiv
e
co
n
tr
o
l
(
MPC
)
h
as
b
ec
o
m
e
r
elev
an
t
in
th
e
co
n
tr
o
l
o
f
th
e
h
ig
h
l
y
d
y
n
am
ic
n
at
u
r
e
o
f
p
u
lp
a
n
d
p
ap
er
p
r
o
ce
s
s
es
in
wh
ich
o
th
er
m
eth
o
d
s
s
u
ch
as
p
r
o
p
o
r
tio
n
al
-
in
teg
r
al
-
d
e
r
iv
ativ
e
(
PID
)
co
n
tr
o
l
m
ay
f
ail.
T
h
e
MPC
o
p
tim
izes
s
tab
ilit
y
,
co
n
s
er
v
es
en
er
g
y
,
an
d
im
p
r
o
v
es
p
r
o
d
u
ct
q
u
ality
b
y
p
r
ed
ictin
g
r
ea
ctio
n
s
o
n
th
e
p
r
o
ce
s
s
es
an
d
m
ak
in
g
ch
a
n
g
es
to
o
p
er
atio
n
s
i
n
a
d
v
an
ce
[
1
3
]
.
Sp
ec
ialized
alg
o
r
ith
m
s
ar
e
aim
ed
at
m
a
n
ag
in
g
ce
r
tain
ch
an
g
es in
o
p
e
r
at
io
n
with
in
p
a
p
er
m
ills
.
An
ex
am
p
le
o
f
s
u
ch
a
s
y
s
tem
is
m
o
d
el
alg
o
r
ith
m
ic
co
n
tr
o
l
(
MA
C
)
wh
ich
h
as
b
ee
n
s
h
o
wn
to
b
e
e
f
f
ec
tiv
e
in
g
r
ad
e
tr
an
s
itio
n
s
.
M
AC
p
r
o
v
id
es
f
aster
an
d
m
o
r
e
s
tead
y
c
h
an
g
es
th
an
tr
ad
itio
n
al
tech
n
iq
u
es
b
y
m
o
d
elin
g
g
r
a
d
e
ch
an
g
es
u
s
in
g
a
n
eu
r
al
n
etwo
r
k
an
d
co
m
p
u
tin
g
an
im
p
u
ls
e
r
esp
o
n
s
e,
wh
ich
r
esu
lts
in
m
o
r
e
g
r
a
d
u
al
ch
an
g
es a
n
d
h
ig
h
p
r
o
d
u
ct
c
o
n
s
is
ten
cy
[
1
4
]
.
Mo
r
eo
v
er
,
b
r
o
wn
s
to
ck
wash
in
g
,
a
k
ey
s
tep
in
p
u
lp
in
g
,
s
i
g
n
if
ican
tly
af
f
ec
ts
p
r
o
d
u
ctio
n
co
s
ts
an
d
en
v
ir
o
n
m
en
tal
im
p
ac
t.
Usi
n
g
s
y
s
tem
d
y
n
a
m
ics
m
o
d
els,
r
esear
ch
er
s
h
av
e
b
etter
u
n
d
er
s
to
o
d
s
tag
e
-
wis
e
in
ter
ac
tio
n
s
an
d
id
en
tifie
d
w
ay
s
to
o
p
tim
ize
th
is
p
r
o
ce
s
s
f
o
r
m
u
ltip
l
e
p
er
f
o
r
m
a
n
ce
g
o
als
[
1
5
]
.
Fin
ally
,
im
p
r
o
v
in
g
wate
r
u
s
e
ef
f
icien
c
y
r
em
ain
s
cr
u
cial
f
o
r
s
u
s
tain
ab
le
g
r
o
wth
in
th
e
p
u
lp
an
d
p
ap
er
s
ec
to
r
.
Ap
p
r
o
ac
h
es
lik
e
wate
r
-
p
in
ch
a
n
aly
s
is
an
d
t
r
ea
ted
ef
f
lu
e
n
t r
eu
s
e
h
elp
lo
w
er
b
o
th
wate
r
an
d
e
n
er
g
y
d
em
an
d
s
[
1
6
]
.
T
h
er
e
ar
e
s
ev
er
al
g
ap
s
wh
i
ch
p
er
s
is
ts
in
th
e
e
x
is
tin
g
r
esear
ch
p
er
tain
in
g
to
th
e
p
a
p
er
m
ills
.
Un
d
er
s
tan
d
in
g
an
d
a
d
d
r
ess
in
g
th
ese
g
ap
s
is
p
iv
o
tal
to
p
r
o
v
i
d
e
m
o
r
e
e
f
f
icien
t
an
d
co
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
s
to
th
is
in
d
u
s
tr
y
.
Fo
llo
win
g
a
r
e
f
e
w
n
o
ted
r
esear
ch
g
ap
s
o
f
th
is
d
o
m
ain
:
i)
Ma
n
y
o
f
s
tu
d
ies till
d
ate,
f
o
cu
s
o
n
th
eo
r
etica
l f
r
a
m
ewo
r
k
s
w
h
ich
lag
in
r
ea
l
-
tim
e
co
n
tr
o
l a
n
d
o
p
tim
izatio
n
.
Pap
er
m
ill
is
a
co
n
tin
u
o
u
s
ly
r
u
n
n
in
g
p
r
o
ce
s
s
wh
ich
n
ee
d
s
co
n
s
tan
t
f
ee
d
b
ac
k
an
d
a
d
ju
s
tm
en
t.
B
u
t
th
e
ex
is
tin
g
m
o
d
els
h
av
e
a
lim
ited
r
ea
l
-
tim
e
ap
p
licati
o
n
.
T
h
e
r
ea
l
-
tim
e
ad
ap
tiv
e
m
o
d
els
b
ased
o
n
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM
)
ar
e
h
ar
d
ly
f
o
u
n
d
in
t
h
e
ex
is
tin
g
r
esear
c
h
in
p
ap
er
m
ills
.
ii)
T
h
er
e
ar
e
s
ev
er
al
o
t
h
er
p
ar
a
m
eter
s
also
o
th
er
th
an
h
ea
d
b
o
x
lev
el
a
n
d
p
u
lp
co
n
s
is
ten
cy
wh
ich
af
f
ec
t
th
e
p
ap
er
q
u
ality
s
u
c
h
as
f
l
o
w
r
at
e,
tem
p
er
atu
r
e,
a
n
d
p
r
ess
u
r
e.
B
u
t
s
ev
er
al
s
tu
d
ies
ar
e
f
o
cu
s
in
g
o
n
o
n
ly
f
ew
o
f
th
em
.
A
co
m
p
r
eh
en
s
iv
e
m
o
d
el
co
n
s
id
er
in
g
all
th
ese
p
ar
am
et
er
s
is
h
ar
d
ly
f
o
u
n
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
692
-
702
694
iii)
T
h
er
e
is
lim
ited
r
esear
ch
f
o
u
n
d
o
n
th
e
s
ca
lab
ilit
y
a
n
d
g
en
er
aliza
tio
n
o
f
th
e
d
e
v
elo
p
e
d
m
o
d
els
i.e
.
m
o
d
els
d
ev
elo
p
e
d
f
o
r
o
n
e
p
ap
er
m
ill
m
ay
n
o
t
wo
r
k
s
u
cc
ess
f
u
lly
f
o
r
o
th
er
p
a
p
er
m
ills
.
T
h
e
r
aw
m
ater
ial
q
u
ality
,
m
ac
h
in
e
co
n
f
ig
u
r
atio
n
an
d
en
v
ir
o
n
m
e
n
tal
co
n
d
it
io
n
s
m
ay
v
ar
y
s
ev
er
ely
in
d
if
f
e
r
en
t p
a
p
er
m
ills
.
iv
)
A
lim
ited
f
o
cu
s
h
as
b
ee
n
g
iv
e
n
o
n
en
er
g
y
ef
f
icien
c
y
an
d
s
u
s
tain
ab
ilit
y
in
th
e
r
esear
ch
p
er
t
ain
in
g
to
co
n
tr
o
l
o
f
p
ap
er
m
ill
p
r
o
ce
s
s
es.
I
n
to
d
a
y
’
s
s
ce
n
ar
io
,
m
in
im
izin
g
th
e
e
n
er
g
y
co
n
s
u
m
p
tio
n
an
d
en
v
ir
o
n
m
en
tal
im
p
ac
t
is
a
m
ajo
r
co
n
ce
r
n
.
SVM
o
r
s
o
m
e
s
im
ilar
ML
tech
n
iq
u
e
is
r
elativ
ely
less
ex
p
lo
r
ed
to
a
ttain
an
en
er
g
y
-
ef
f
icien
t p
r
o
ce
s
s
co
n
t
r
o
l.
v)
Av
ailab
ilit
y
o
f
h
ig
h
-
q
u
ality
a
n
d
lar
g
e
-
s
ca
le
d
ata
p
er
tain
i
n
g
to
p
ap
er
m
ills
is
lim
ited
.
A
l
ar
g
e
d
ataset
is
r
eq
u
ir
ed
to
tr
ain
a
ML
b
ased
m
o
d
el
ef
f
ec
tiv
ely
.
I
n
co
n
s
is
ten
t
an
d
n
o
is
y
d
ata
r
esu
lt
in
d
e
g
r
ad
atio
n
in
th
e
p
er
f
o
r
m
an
ce
o
f
m
o
d
els.
Stu
r
d
y
r
esear
ch
is
r
eq
u
ir
ed
to
r
eso
l
v
e
th
is
is
s
u
e.
v
i)
Hy
b
r
id
ML
m
o
d
els ar
e
r
a
r
ely
f
o
u
n
d
in
ad
d
r
ess
in
g
th
e
co
n
tr
o
l o
f
p
ap
e
r
m
ill p
r
o
ce
s
s
es.
2.
RE
L
AT
E
D
WO
RK
T
h
e
r
e
v
iew
p
r
esen
ted
in
th
is
wo
r
k
is
e
x
p
lo
r
i
n
g
v
ar
io
u
s
tech
n
iq
u
es
p
er
tain
in
g
to
o
p
tim
iz
atio
n
an
d
co
n
tr
o
l
o
f
p
a
p
er
m
ills
.
W
ith
r
ap
id
ly
escalatin
g
d
em
an
d
o
f
p
ap
er
p
r
o
d
u
cts
b
y
n
u
m
er
o
u
s
in
d
u
s
tr
ies,
th
er
e
h
as
b
ee
n
a
r
is
e
in
th
e
n
ee
d
f
o
r
m
o
d
er
n
c
o
n
tr
o
l
m
eth
o
d
o
lo
g
ies al
s
o
,
to
m
ee
t th
e
p
r
o
d
u
ctio
n
s
tan
d
ar
d
s
.
T
h
e
class
ical
tech
n
iq
u
es
h
av
e
p
r
o
v
en
to
b
e
a
f
o
u
n
d
atio
n
al
f
r
am
ewo
r
k
b
u
t
th
ey
ar
e
n
o
t
m
atc
h
in
g
to
t
h
e
d
em
an
d
o
f
f
u
tu
r
is
tic
ap
p
r
o
ac
h
es
s
u
ch
as
m
o
d
er
n
s
e
n
s
in
g
tech
n
o
lo
g
ies.
T
h
is
s
u
r
v
e
y
lo
o
k
s
f
o
r
s
u
c
h
ad
v
an
ce
d
a
p
p
r
o
ac
h
es
f
o
r
b
r
i
d
g
in
g
th
is
g
ap
.
T
h
e
o
b
jectiv
e
is
to
s
tu
d
y
th
e
ch
allen
g
es
in
th
eir
im
p
lem
en
tatio
n
an
d
im
p
ac
t
o
n
q
u
ality
an
d
p
r
o
d
u
ctiv
ity
.
T
h
e
f
in
al
im
p
lem
en
tatio
n
o
f
an
y
co
n
tr
o
l
s
y
s
tem
r
eq
u
i
r
es
th
e
in
ter
p
r
etatio
n
o
f
r
elatio
n
s
h
ip
am
o
n
g
p
r
o
ce
s
s
d
y
n
am
ics,
au
to
m
atio
n
,
an
d
m
o
n
ito
r
in
g
in
r
ea
l
tim
e.
T
h
er
ef
o
r
e,
th
e
r
e
is
an
u
r
g
en
t
n
ee
d
to
ad
d
r
ess
all
th
e
ch
allen
g
es
w
h
ich
a
r
e
th
e
r
e
in
r
ea
l
tim
e
im
p
lem
en
tatio
n
o
f
ad
v
a
n
ce
d
co
n
tr
o
l
s
y
s
tem
s
f
o
r
p
ap
e
r
m
ill.
T
h
er
e
is
also
a
n
ee
d
o
f
f
o
r
ec
asti
n
g
f
u
tu
r
e
ad
v
a
n
ce
m
en
ts
in
co
n
tr
o
l
m
ec
h
an
is
m
s
o
f
p
ap
er
p
r
o
d
u
ctio
n
p
r
o
ce
s
s
es
to
u
p
g
r
a
d
e
th
e
q
u
ality
an
d
p
r
o
d
u
ctiv
ity
.
C
ar
lb
er
g
[
1
7
]
p
r
esen
ted
a
r
esear
ch
wo
r
k
o
n
d
ig
ital
twin
s
b
ased
au
to
n
o
m
o
u
s
m
ill
o
f
f
u
tu
r
e
wh
ich
r
u
n
s
its
elf
with
a
lit
tle
o
r
n
o
in
ter
v
en
tio
n
o
f
h
u
m
an
s
.
T
h
is
r
esear
ch
g
av
e
an
o
v
er
v
iew
o
f
eq
u
ip
m
en
t
an
d
o
p
er
atio
n
s
ass
o
ciate
d
with
p
u
lp
an
d
p
ap
e
r
m
ills
,
an
d
c
o
n
clu
d
e
d
with
v
ar
io
u
s
ex
a
m
p
les
wh
er
e
ad
v
an
ce
d
p
r
o
ce
s
s
co
n
tr
o
l
(
APC
)
an
d
MPC
)
b
ased
o
p
ti
m
izatio
n
o
f
c
o
n
tr
o
l
s
y
s
tem
s
ca
n
elev
ate
th
e
p
r
o
d
u
ctio
n
an
d
d
ec
r
ea
s
e
th
e
co
s
t.
R
ajan
et
a
l.
[
1
8
]
d
esig
n
ed
an
d
im
p
lem
en
ted
an
in
tellig
en
t
lo
ad
-
s
h
ed
d
i
n
g
s
y
s
tem
(
I
L
SS
)
in
a
p
ap
er
m
ill
f
o
r
en
s
u
r
in
g
p
o
wer
s
y
s
tem
’
s
s
tab
il
ity
,
af
ter
th
e
s
team
tu
r
b
in
e
g
en
er
ato
r
m
a
k
es
tr
an
s
itio
n
s
f
r
o
m
b
ac
k
-
p
r
ess
u
r
e
m
o
d
e
o
f
o
p
er
atio
n
to
th
e
is
o
ch
r
o
n
o
u
s
m
o
d
e
u
p
o
n
th
e
lo
s
s
o
f
elec
tr
ic
g
r
id
.
T
h
is
ap
p
r
o
ac
h
h
as
b
ee
n
v
alid
ated
b
y
th
e
u
s
e
o
f
d
y
n
am
ic
s
im
u
latio
n
.
Sh
ah
i
an
d
Dia
[
1
9
]
e
v
alu
at
ed
th
e
p
er
f
o
r
m
an
ce
o
f
p
u
l
p
an
d
p
ap
er
m
ills
u
s
in
g
b
o
o
ts
tr
ap
d
ata
en
v
elo
p
m
e
n
t
an
aly
s
is
m
eth
o
d
.
T
h
ey
c
o
m
p
a
r
ed
th
e
p
er
f
o
r
m
a
n
ce
o
f
3
ty
p
es
o
f
On
tar
io
'
s
p
u
lp
an
d
p
ap
er
m
ills
.
T
h
is
s
tu
d
y
p
r
o
v
id
ed
d
etailed
p
er
f
o
r
m
an
ce
an
al
y
s
is
to
th
e
p
o
licy
m
ak
er
s
s
o
th
at
th
e
r
ea
ll
o
ca
tio
n
o
f
t
h
e
in
p
u
t
r
eso
u
r
ce
s
ca
n
b
e
d
o
n
e
f
o
r
im
p
r
o
v
in
g
p
er
f
o
r
m
a
n
ce
o
f
p
u
lp
a
n
d
p
ap
er
m
il
ls
in
On
tar
io
.
T
ao
et
a
l.
[
2
0
]
ca
r
r
ied
o
u
t
a
r
esear
ch
wo
r
k
o
n
o
p
tim
al
r
u
n
n
in
g
m
o
d
el
o
f
p
o
wer
-
h
ea
t
s
y
s
tem
(
co
al
-
f
ir
ed
)
ass
o
ciate
d
with
p
a
p
er
m
ill.
T
h
ey
r
esear
ch
ed
o
n
th
e
p
h
y
s
ical
s
tr
u
ctu
r
e
o
f
p
o
wer
p
lan
t,
estab
lis
h
ed
th
e
s
u
p
er
s
tr
u
ctu
r
e,
an
d
an
aly
ze
d
th
e
b
o
iler
an
d
tu
r
b
in
e
r
u
n
n
in
g
m
o
d
el.
C
asti
llo
n
et
a
l.
[
2
1
]
p
r
esen
ted
r
esear
ch
o
n
s
af
ety
lo
ck
o
u
t
p
e
r
tain
in
g
to
AC
an
d
DC
d
r
iv
es
f
o
r
th
e
p
a
p
er
m
ills
.
T
h
ey
ex
am
i
n
ed
b
o
th
alter
n
atin
g
cu
r
r
en
t
(
AC
)
an
d
d
ir
ec
t
cu
r
r
en
t
(
DC
)
s
o
u
r
ce
s
.
L
i
et
a
l.
[
2
2
]
d
esig
n
ed
a
test
f
o
r
ex
p
lo
r
in
g
th
e
c
o
r
r
elat
io
n
b
etwe
en
m
illi
n
g
s
p
ee
d
an
d
m
illi
n
g
f
o
r
ce
co
ef
f
i
cien
t in
o
r
d
e
r
to
attain
o
p
tim
iz
atio
n
o
f
p
lu
n
g
e
p
r
o
ce
s
s
p
ar
am
eter
s
.
Aziz
et
a
l.
[
2
3
]
p
r
esen
ted
a
n
e
w
d
ec
is
io
n
m
o
d
el,
p
e
r
tain
in
g
to
th
e
p
ap
er
m
ill,
f
o
r
m
ee
tin
g
th
e
ac
tu
al
cu
s
to
m
er
d
em
a
n
d
.
I
t
ca
n
b
e
u
s
ed
to
s
im
u
ltan
e
o
u
s
ly
cu
t
th
e
m
aster
r
ee
ls
an
d
s
to
c
k
ed
r
o
lls
.
Her
e,
th
e
g
o
al
is
to
s
atis
f
y
cu
s
to
m
er
n
ee
d
with
lea
s
t
p
o
s
s
ib
le
n
u
m
b
er
o
f
m
aster
r
ee
ls
an
d
s
to
ck
ed
r
o
lls
.
Du
an
et
a
l.
[
2
4
]
ca
r
r
ie
d
o
u
t
r
esear
ch
with
an
aim
to
en
h
an
ce
tr
ea
tm
en
t
p
er
f
o
r
m
an
ce
o
f
t
h
e
p
u
lp
a
n
d
p
a
p
er
m
ill
ef
f
lu
e
n
ts
.
T
h
ey
p
r
o
p
o
s
ed
a
co
m
b
in
atio
n
o
f
ad
s
o
r
p
tio
n
an
d
co
ag
u
latio
n
tr
ea
tm
e
n
t.
Mc
Au
liff
e
et
a
l.
[
2
5
]
an
al
y
ze
d
th
e
i
m
p
ac
t
o
f
u
p
g
r
ad
in
g
th
e
p
o
wer
d
is
tr
ib
u
tio
n
e
q
u
ip
m
en
t
in
p
ap
er
m
ill
(
b
y
r
ep
lacin
g
th
e
v
in
tag
e
ai
r
-
b
r
ea
k
cir
c
u
it
b
r
ea
k
er
s
b
y
th
e
n
ew
v
ac
u
u
m
ci
r
cu
it
b
r
ea
k
er
s
in
th
e
ex
is
tin
g
s
witch
g
ea
r
)
v
er
s
u
s
r
e
p
lacin
g
it
with
n
ew
e
q
u
ip
m
e
n
t
,
o
n
t
o
tal
in
s
talled
co
s
t
an
d
p
r
o
f
itab
ilit
y
.
T
h
e
p
r
esen
ted
liter
atu
r
e
s
u
r
v
ey
o
f
f
e
r
s
a
co
m
p
lete
u
n
d
e
r
s
tan
d
in
g
o
f
d
if
f
er
en
t
f
ac
to
r
s
im
p
ac
tin
g
th
e
p
a
p
er
q
u
ality
,
o
p
p
o
r
tu
n
ities
an
d
ch
allen
g
es
i
n
h
er
en
t
in
p
a
p
er
m
ill,
an
d
th
e
te
ch
n
iq
u
es
a
d
o
p
ted
to
d
ea
l
with
th
em
.
Mo
r
e
s
tr
ess
i
s
o
n
d
ata
an
aly
tics
,
s
en
s
o
r
tech
n
o
lo
g
ies,
an
d
m
ac
h
in
e
lear
n
in
g
in
h
an
d
lin
g
f
in
al
p
r
o
d
u
ct
q
u
ality
,
e
n
h
an
ci
n
g
o
v
er
all
ef
f
icien
cy
.
Hav
in
g
g
ai
n
ed
th
e
p
r
im
ar
y
k
n
o
wled
g
e
f
r
o
m
th
is
liter
atu
r
e
r
ev
iew,
v
ar
io
u
s
SVM
b
ased
m
o
d
els
h
av
e
b
ee
n
ex
p
lo
r
ed
f
o
r
ass
ess
in
g
th
e
p
r
o
d
u
ce
d
p
a
p
er
q
u
ality
o
n
th
e
b
asis
o
f
two
s
ig
n
if
ican
t
p
ar
am
eter
s
v
iz.
p
u
lp
co
n
s
is
ten
cy
an
d
h
ea
d
b
o
x
lev
el.
T
h
e
p
u
l
p
co
n
s
is
ten
cy
is
a
m
ea
s
u
r
e
o
f
ce
llu
lo
s
e
f
i
b
er
co
n
ce
n
tr
atio
n
in
p
u
lp
s
u
s
p
en
s
io
n
.
T
h
e
m
ec
h
an
ical
p
r
o
p
er
ties
an
d
p
r
in
ta
b
ilit
y
o
f
th
e
f
in
al
p
r
o
d
u
ct
is
s
ev
er
el
y
af
f
ec
ted
b
y
th
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
P
r
ed
ictive
mo
d
elin
g
a
n
d
o
p
timiz
a
tio
n
o
f p
a
p
er mill u
s
in
g
h
yb
r
id
ma
ch
in
e
…
(
A
b
h
ijit
S
in
g
h
B
h
a
k
u
n
i
)
695
p
ar
am
eter
.
An
o
t
h
er
cr
itical
p
a
r
am
eter
d
ec
id
in
g
th
e
u
n
if
o
r
m
i
ty
an
d
s
tab
ilit
y
o
f
p
r
o
d
u
ce
d
p
a
p
er
is
th
e
h
ea
d
b
o
x
lev
el.
I
ts
r
eg
u
latio
n
co
n
t
r
o
ls
th
e
r
ate
o
f
f
lo
w
o
f
p
u
lp
o
n
to
th
e
p
ap
er
m
ac
h
i
n
e
wir
e.
SVM
m
o
d
els
ar
e
well
k
n
o
wn
f
o
r
th
eir
ca
p
ab
ilit
y
o
f
d
ea
lin
g
with
h
ig
h
-
d
im
en
s
io
n
al
an
d
n
o
n
lin
ea
r
d
ata
o
f
f
er
in
g
a
p
r
o
m
is
in
g
av
en
u
e
o
f
d
ev
elo
p
m
e
n
t
o
f
p
r
ed
ictiv
e
m
o
d
els
b
ased
o
n
in
tr
icate
d
y
n
a
m
ics
o
f
p
ap
er
m
ak
in
g
p
r
o
ce
s
s
.
I
n
t
h
is
wo
r
k
,
f
o
u
r
d
is
tin
ct
v
ar
ian
ts
o
f
SVM
ar
e
e
x
p
lo
r
ed
v
iz.
l
in
ea
r
SVM,
q
u
ad
r
atic
SVM,
cu
b
ic
SVM,
a
nd
f
i
n
e
Gau
s
s
ian
SVM.
3.
M
E
T
H
O
D
T
h
e
b
asic
aim
o
f
th
is
r
esear
c
h
is
th
e
co
n
tr
o
l
an
d
o
p
tim
izat
io
n
o
f
th
e
cr
itical
p
r
o
ce
s
s
es
o
f
th
e
p
a
p
er
m
ill
,
p
ar
ticu
lar
ly
ac
cu
r
ate
ass
ess
m
en
t
o
f
f
in
al
p
r
o
d
u
ct
q
u
ality
b
ased
o
n
h
ea
d
b
o
x
lev
el
an
d
p
u
lp
co
n
s
is
ten
cy
.
T
o
m
ee
t
th
is
g
o
al,
SVM
b
ased
p
r
ed
ictiv
e
m
o
d
el
h
as
b
ee
n
d
e
v
elo
p
ed
f
o
r
im
p
r
o
v
in
g
t
h
e
p
a
p
er
q
u
ality
.
Fo
llo
win
g
ar
e
th
e
k
e
y
o
b
jectiv
es
o
f
th
is
r
esear
ch
:
i)
t
o
d
ev
elo
p
p
r
e
d
i
ctiv
e
m
o
d
els
f
o
r
ac
cu
r
ately
d
eter
m
in
in
g
h
ea
d
b
o
x
lev
el
an
d
p
u
lp
c
o
n
s
is
ten
cy
s
o
th
at
th
eir
co
n
tr
o
l
ca
n
b
e
d
o
n
e
f
o
r
attain
in
g
g
o
o
d
f
in
al
p
r
o
d
u
ct
q
u
ality
;
ii
)
a
s
s
es
s
m
en
t
o
f
f
in
al
p
r
o
d
u
ct
q
u
ality
u
s
in
g
v
ar
i
o
u
s
SVM
m
o
d
els
alo
n
g
with
th
eir
co
n
f
u
s
io
n
m
atr
ices
an
d
co
m
p
ar
is
o
n
tab
le
;
an
d
iii)
t
o
d
e
v
e
l
o
p
m
u
l
t
i
v
a
r
i
a
t
e
o
p
ti
m
i
z
a
t
i
o
n
m
o
d
e
l
b
as
e
d
o
n
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
(
GA
)
c
o
n
s
i
d
e
r
i
n
g
s
e
v
e
r
a
l
p
a
r
a
m
e
te
r
s
.
T
h
e
aim
is
to
p
ar
allelly
co
n
tr
o
l
v
ar
io
u
s
cr
itical
asp
ec
ts
to
o
p
tim
ize
th
e
o
v
er
all
f
in
al
p
ap
er
q
u
ality
.
3
.
1
.
Dev
el
o
pm
ent
o
f
predict
iv
e
m
o
dels
f
o
r
pu
lp co
ns
is
t
en
cy
a
nd
hea
db
o
x
lev
el
In
th
is
s
ec
tio
n
,
th
e
f
ir
s
t
o
b
ject
iv
e
o
f
th
is
r
esear
ch
is
ad
d
r
ess
ed
i.e
.
to
d
ev
elo
p
p
r
e
d
ictiv
e
m
o
d
els
f
o
r
two
o
u
tp
u
t
v
ar
iab
les,
h
ea
d
b
o
x
lev
el
an
d
p
u
l
p
co
n
s
is
ten
cy
,
b
ased
o
n
th
r
ee
in
p
u
t
f
ea
tu
r
es:
f
lo
w
r
ate,
p
r
ess
u
r
e,
an
d
v
al
v
e
p
o
s
itio
n
as
d
e
p
icted
in
Fig
u
r
e
1
.
T
h
e
c
h
allen
g
e
is
to
ac
cu
r
ately
m
o
d
el
th
e
r
elatio
n
s
h
ip
b
etwe
en
th
ese
in
p
u
ts
an
d
o
u
tp
u
ts
to
p
r
o
v
id
e
a
r
eliab
le
p
r
ed
ictio
n
to
o
l
f
o
r
p
r
o
ce
s
s
o
p
tim
izatio
n
.
T
h
is
r
esear
c
h
p
r
o
p
o
s
es
th
e
u
s
e
o
f
SVM
an
d
r
an
d
o
m
f
o
r
ests
(
R
F)
in
a
h
y
b
r
id
m
o
d
el
to
p
r
e
d
i
ct
th
e
o
u
t
p
u
t
v
a
r
iab
les
u
s
in
g
MA
T
L
AB
,
f
o
llo
wed
b
y
a
co
m
p
ar
ativ
e
ev
al
u
atio
n
b
ased
o
n
p
er
f
o
r
m
a
n
ce
m
etr
ics
s
u
ch
as
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
an
d
R
-
s
q
u
ar
ed
(
R
²)
.
T
h
e
o
v
er
all
o
b
jectiv
e
is
to
ass
es
s
th
e
ac
cu
r
ac
y
o
f
th
ese
m
o
d
els
an
d
t
o
d
eter
m
in
e
wh
eth
e
r
co
m
b
in
in
g
SVM
an
d
R
F c
an
i
m
p
r
o
v
e
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
c
e
co
m
p
ar
e
d
to
in
d
iv
id
u
al
m
o
d
els.
3
.
2
.
Dev
el
o
pm
ent
o
f
pa
per
qu
a
lity
a
s
s
ess
m
ent
m
o
dels
T
h
e
SVM
alg
o
r
ith
m
m
ay
b
e
b
ased
o
n
d
if
f
er
en
t
k
er
n
el
f
u
n
cti
o
n
s
s
u
ch
as
lin
ea
r
,
q
u
ad
r
atic,
cu
b
ic,
an
d
Gau
s
s
ian
.
T
h
e
s
ec
o
n
d
ar
y
d
ata
co
n
tain
in
g
1
0
0
s
am
p
les
with
two
attr
ib
u
tes
v
iz.
p
u
lp
co
n
s
is
ten
cy
(
%)
an
d
th
e
h
ea
d
b
o
x
lev
el
(
m
m
)
,
a
n
d
th
r
ee
class
es
o
f
q
u
ality
,
i.e
.
,
h
ig
h
,
m
ed
iu
m
,
a
n
d
lo
w
is
d
ep
icted
in
Fig
u
r
e
2
.
No
w
u
s
in
g
th
is
d
ata,
a
class
if
icatio
n
m
o
d
el
s
u
ch
as
s
h
o
wn
in
Fig
u
r
e
3
is
to
b
e
d
e
v
elo
p
e
d
,
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
tech
n
iq
u
e
i
n
MA
T
L
AB
,
wh
ich
ca
n
esti
m
ate
th
e
q
u
ality
o
f
p
r
o
d
u
ce
d
p
ap
e
r
b
ased
o
n
th
e
p
u
lp
co
n
s
is
ten
cy
an
d
h
ea
d
b
o
x
lev
e
l v
alu
es.
Fig
u
r
e
1
.
C
o
n
ce
p
tu
al
r
ep
r
esen
tatio
n
o
f
th
e
d
esire
d
m
o
d
el
Fig
u
r
e
2
.
Pap
er
q
u
ality
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
692
-
702
696
Fig
u
r
e
3
.
SVM
b
ased
class
if
icatio
n
m
o
d
el
t
o
b
e
estab
lis
h
ed
3
.
3
.
Dev
el
o
pm
ent
o
f
m
ultiv
a
ria
t
e
o
ptim
iza
t
io
n mo
del
T
h
e
g
o
al
is
to
en
s
u
r
e
h
i
g
h
-
q
u
ality
p
ap
er
p
r
o
d
u
ctio
n
b
y
m
in
i
m
izin
g
d
e
v
iatio
n
s
f
r
o
m
th
e
tar
g
et
v
alu
es
o
f
k
e
y
p
a
r
am
eter
s
:
h
ea
d
b
o
x
l
ev
el,
p
u
l
p
co
n
s
is
ten
cy
,
an
d
t
em
p
er
atu
r
e.
T
h
e
f
o
llo
win
g
p
a
r
am
eter
s
af
f
ec
t
th
e
p
r
o
p
er
ties
,
q
u
ality
o
f
p
a
p
er
,
a
n
d
r
eq
u
ir
es
p
r
ec
is
e
co
n
tr
o
l
an
d
o
p
tim
izatio
n
.
T
h
e
lim
itatio
n
s
an
d
b
o
u
n
d
ar
ies
f
o
r
th
ese
p
ar
am
eter
s
ca
n
b
e
d
eter
m
in
ed
b
y
th
e
m
ac
h
in
er
y
a
n
d
p
r
o
ce
s
s
lim
itatio
n
s
in
tr
in
s
ic
to
th
e
in
d
u
s
tr
y
.
Ma
th
em
atica
lly
,
th
is
ca
n
b
e
f
r
am
ed
as
a
r
estricte
d
o
p
tim
izat
io
n
p
r
o
b
le
m
.
B
y
u
s
in
g
weig
h
ted
s
u
m
o
f
s
q
u
ar
ed
d
i
f
f
er
en
ce
s
,
t
h
e
o
b
ject
iv
e
f
u
n
ctio
n
d
e
v
iates f
r
o
m
t
h
e
tar
g
et
v
alu
es,
wh
ich
is
m
in
im
i
s
ed
b
y
m
a
k
in
g
u
s
e
o
f
o
p
tim
izatio
n
p
r
o
ce
s
s
to
en
s
u
r
e
o
p
e
r
atio
n
al
f
ea
s
ib
ilit
y
.
T
h
e
p
ar
am
eter
s
an
d
co
n
s
tr
ain
ts
a
r
e
as f
o
llo
ws:
-
Flo
w
r
ate
(
m
³/s
)
: [
3
0
,
1
0
0
]
-
Pre
s
s
u
r
e
(
Pa)
: [
4
0
,
200]
-
T
em
p
er
atu
r
e
(
°
C
)
: [
2
8
,
80]
-
Hea
d
b
o
x
le
v
el
(
m
)
: [
3
,
1
5
]
-
Pu
lp
co
n
s
is
ten
cy
(
%):
[
4
,
1
4
]
T
h
e
f
o
llo
win
g
ar
e
th
e
ta
r
g
et
v
alu
es f
o
r
o
p
tim
al
q
u
ality
:
-
Hea
d
b
o
x
le
v
el
=
8
m
-
Pu
lp
co
n
s
is
ten
cy
=
12%
-
T
em
p
er
atu
r
e
=
65
°
C
No
w,
g
en
etic
alg
o
r
ith
m
is
ap
p
lied
u
s
in
g
MA
T
L
AB
to
s
o
lv
e
t
h
is
o
p
tim
izatio
n
p
r
o
b
lem
.
I
t
en
v
elo
p
s
a
p
o
p
u
latio
n
o
f
ca
n
d
i
d
ate
s
o
lu
tio
n
s
o
v
e
r
m
u
ltip
le
iter
atio
n
s
co
n
v
e
r
g
e
to
w
ar
d
s
th
e
o
p
tim
al
s
o
lu
tio
n
.
-
Po
p
u
latio
n
s
ize:
3
0
-
Nu
m
b
er
o
f
g
en
e
r
atio
n
s
: 1
5
0
-
Mu
tatio
n
r
ate:
0
.
1
-
E
liti
s
m
co
u
n
t: 1
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
All
th
e
m
eth
o
d
s
h
av
e
b
ee
n
co
n
s
id
er
ed
an
d
ev
alu
ate
d
in
th
is
s
ec
tio
n
an
d
a
clea
r
an
al
y
s
is
h
as
b
ee
n
m
ad
e
b
ased
o
n
th
e
v
ar
io
u
s
p
ar
am
ete
r
s
.
4
.
1
.
P
re
dict
iv
e
m
o
delin
g
a
n
d a
na
ly
s
is
f
o
r
pu
lp co
ns
i
s
t
en
cy
a
nd
hea
db
o
x
lev
el
Usi
n
g
th
e
in
p
u
ts
f
lo
w
r
ate,
p
r
ess
u
r
e
,
an
d
v
al
v
e
p
o
s
itio
n
,
th
e
o
u
tp
u
ts
—
h
ea
d
b
o
x
lev
el
an
d
p
u
lp
co
n
s
is
ten
cy
as sh
o
wn
in
Fig
u
r
e
1
—
wer
e
ca
lcu
lated
u
s
in
g
th
e
r
esp
ec
tiv
e
lin
ea
r
m
o
d
els.
T
h
e
d
ata
was sp
lit in
to
two
s
ec
tio
n
s
,
tr
ain
in
g
(
8
0
%
o
f
d
ata)
an
d
test
in
g
(
2
0
%
o
f
d
at
a)
s
ets
to
co
n
f
ig
u
r
e
t
h
e
g
u
a
r
a
n
teed
ev
alu
atio
n
o
f
m
o
d
els o
n
u
n
s
ee
n
d
ata.
T
h
e
u
s
ed
s
ec
o
n
d
ar
y
d
ata
is
s
h
o
wn
in
Fig
u
r
e
4.
SVM,
a
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
,
is
wid
ely
u
tili
ze
d
f
o
r
r
eg
r
ess
io
n
task
s
.
I
n
th
is
s
tu
d
y
,
th
e
SVM
m
o
d
el
in
co
r
p
o
r
ates
a
Gau
s
s
ian
(
r
ad
ial
b
asi
s
f
u
n
ctio
n
)
k
er
n
el,
wh
ich
is
well
s
u
ited
f
o
r
ca
p
tu
r
i
n
g
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
b
etwe
en
in
p
u
t
an
d
o
u
tp
u
t
v
a
r
iab
les.
T
o
en
s
u
r
e
th
e
m
o
d
els
p
er
f
o
r
m
an
ce
,
th
e
d
ata
was
s
tan
d
ar
d
ized
to
en
s
u
r
e
all
f
e
atu
r
es
ar
e
o
n
a
co
m
p
a
r
ab
le
s
ca
le.
SVM
r
eg
r
ess
io
n
o
p
e
r
ates
b
y
id
en
tify
in
g
a
h
y
p
er
p
lan
e
t
h
at
o
p
tim
ally
f
its
th
e
t
r
ain
in
g
d
ata
wh
ile
m
i
n
im
izin
g
er
r
o
r
s
with
in
a
d
ef
i
n
e
d
m
ar
g
in
.
T
h
e
SVM
m
o
d
e
l
s
w
e
r
e
i
n
d
i
v
i
d
u
a
l
l
y
t
r
ai
n
e
d
f
o
r
h
e
a
d
b
o
x
l
e
v
e
l
a
n
d
p
u
l
p
c
o
n
s
i
s
t
e
n
c
y
u
s
i
n
g
t
h
e
t
r
a
i
n
i
n
g
d
a
t
a
s
e
t
.
F
o
r
e
a
c
h
m
o
d
e
l
,
h
y
p
e
r
p
a
r
a
m
e
t
e
r
s
s
u
c
h
as
k
e
r
n
e
l
f
u
n
c
t
i
o
n
s
a
n
d
s
t
a
n
d
a
r
d
i
z
a
t
i
o
n
o
p
t
i
o
n
s
a
r
e
o
p
t
i
m
i
z
e
d
f
o
r
b
e
s
t
p
e
r
f
o
r
m
a
n
c
e
.
R
an
d
o
m
f
o
r
est,
an
en
s
em
b
le
lear
n
in
g
m
eth
o
d
,
co
n
s
tr
u
cts
m
u
l
tip
le
d
ec
is
io
n
tr
ee
s
d
u
r
in
g
tr
ai
n
in
g
.
E
ac
h
tr
ee
is
b
u
ilt u
s
in
g
a
r
an
d
o
m
ly
s
elec
ted
s
u
b
s
et
o
f
th
e
d
ata,
an
d
p
r
e
d
ictio
n
s
ar
e
m
ad
e
b
y
ag
g
r
eg
atin
g
t
h
e
o
u
tp
u
ts
o
f
all
th
e
in
d
i
v
id
u
al
tr
ee
s
.
I
n
th
is
s
tu
d
y
,
th
e
r
an
d
o
m
m
eth
o
d
em
p
lo
y
ed
b
ag
g
in
g
as
th
e
e
n
s
em
b
le
tech
n
i
q
u
e
a
n
d
u
tili
ze
d
1
0
0
lear
n
in
g
cy
cles
to
co
n
s
tr
u
ct
th
e
f
o
r
est.
T
h
e
r
an
d
o
m
f
o
r
est
p
r
o
v
e
d
to
b
e
a
m
o
r
e
r
eliab
le
ch
o
ice
f
o
r
th
is
r
eg
r
ess
io
n
d
u
e
to
its
n
atu
r
ally
m
an
ag
in
g
th
e
s
p
ac
e
o
v
er
f
i
ttin
g
.
T
h
e
s
am
e
tr
ain
in
g
d
ataset
wer
e
u
s
ed
f
o
r
R
F
m
o
d
els
tr
ain
in
g
as
SVM
m
o
d
e
ls
f
o
r
b
o
th
o
u
tp
u
ts
.
An
in
teg
r
a
ted
h
y
b
r
i
d
m
o
d
el
is
d
esig
n
ed
f
o
r
th
e
o
u
t
p
u
ts
f
r
o
m
SVM
an
d
r
an
d
o
m
f
o
r
est
m
o
d
els,
in
o
r
d
e
r
to
en
h
an
ce
th
e
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
T
h
is
h
y
b
r
id
m
o
d
el
m
a
k
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
P
r
ed
ictive
mo
d
elin
g
a
n
d
o
p
timiz
a
tio
n
o
f p
a
p
er mill u
s
in
g
h
yb
r
id
ma
ch
in
e
…
(
A
b
h
ijit
S
in
g
h
B
h
a
k
u
n
i
)
697
p
r
ed
ictio
n
s
b
y
co
m
b
i
n
in
g
th
e
o
u
tp
u
ts
o
b
tain
e
d
f
r
o
m
th
ese
m
o
d
els
b
y
ass
ig
n
in
g
weig
h
ts
to
p
r
ed
ictio
n
s
o
b
tai
n
ed
f
r
o
m
SVM
an
d
r
an
d
o
m
f
o
r
est,
r
esp
ec
tiv
ely
.
Fig
u
r
e
5
s
h
o
ws
th
e
co
m
p
a
r
ativ
e
d
if
f
er
en
ce
b
etwe
en
th
e
tr
u
e
an
d
p
r
ed
ictiv
e
v
alu
es
f
o
r
p
ap
e
r
co
n
s
is
ten
cy
.
T
h
is
co
m
p
ar
is
o
n
h
ig
h
lig
h
ts
th
e
d
if
f
er
e
n
ce
in
th
e
p
er
f
o
r
m
an
ce
b
etwe
en
SVM
-
R
F
m
o
d
el.
Fo
llo
win
g
ar
e
th
e
k
ey
o
b
s
er
v
atio
n
s
:
-
T
h
ese
two
m
o
d
els
eq
u
ally
ap
p
r
eh
en
d
th
e
co
m
p
r
eh
e
n
s
iv
e
tr
en
d
o
f
th
e
tr
u
e
v
alu
es,
s
ig
n
if
y
in
g
th
eir
ca
p
ab
ilit
y
to
m
o
d
el
th
e
s
y
s
tem
d
y
n
am
ics
.
-
Gr
ea
ter
p
r
ec
is
io
n
is
o
b
s
er
v
ed
u
s
in
g
h
y
b
r
id
m
o
d
el
in
r
eg
io
n
with
s
h
ar
p
v
ar
iab
ilit
y
,
h
ig
h
lig
h
ti
n
g
its
ca
p
ab
ilit
y
in
r
ed
u
cin
g
o
u
tf
itti
n
g
an
d
b
ett
er
h
an
d
lin
g
o
f
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
.
-
L
ar
g
er
p
r
ed
ictio
n
er
r
o
r
is
o
b
s
e
r
v
ed
in
ca
s
e
o
f
SVM
m
o
d
el
wi
th
ex
tr
em
e
p
ap
er
co
n
s
is
ten
cy
v
alu
es,
wh
ich
is
s
u
cc
ess
f
u
lly
ad
d
r
ess
ed
b
y
th
e
h
y
b
r
id
m
o
d
el.
T
h
is
r
ein
f
o
r
ce
s
th
e
r
o
b
u
s
tn
ess
o
f
u
s
in
g
h
y
b
r
id
ap
p
r
o
ac
h
.
A
b
etter
p
er
f
o
r
m
a
n
ce
o
f
h
y
b
r
i
d
m
o
d
el
is
n
o
ticea
b
le
th
r
o
u
g
h
r
ed
u
ce
d
p
r
ed
ictio
n
d
e
v
iatio
n
s
as
h
ig
h
lig
h
ted
in
ca
s
e
o
f
lo
wer
R
MSE
an
d
h
ig
h
er
R
2
v
alu
es.
Fig
u
r
e
6
s
h
o
wca
s
es th
e
b
en
e
f
i
ts
o
f
h
y
b
r
id
m
o
d
el
in
p
r
ed
ictin
g
h
ea
d
b
o
x
le
v
el:
-
A
b
etter
p
er
f
o
r
m
an
ce
th
a
n
s
tan
d
alo
n
e
SVM
m
o
d
el
is
o
b
s
er
v
ed
in
ca
s
e
o
f
u
s
in
g
h
y
b
r
id
m
o
d
el,
wh
er
ein
th
e
h
y
b
r
id
m
o
d
el
h
as a
co
n
s
is
ten
t
alig
n
m
en
t w
h
ich
is
clo
s
e
to
th
e
tr
u
e
v
alu
es a
cr
o
s
s
all
test
ed
s
am
p
les.
-
Flu
ctu
atio
n
in
p
r
ed
ictio
n
ac
cu
r
ac
y
in
co
m
p
a
r
ativ
ely
r
ed
u
ce
d
in
ca
s
e
o
f
h
y
b
r
id
m
o
d
el
in
th
e
p
r
esen
ce
o
f
o
u
tlier
s
o
r
ed
g
e
ca
s
es.
T
h
is
s
im
p
ly
s
ig
n
if
ies
th
e
h
a
r
m
o
n
i
o
u
s
s
tr
en
g
th
s
o
f
u
s
in
g
r
an
d
o
m
f
o
r
est’s
en
s
em
b
le
-
b
ased
g
en
er
aliza
tio
n
an
d
SV
M’
s
k
er
n
el
-
b
ased
a
p
p
r
o
x
im
ati
o
n
.
-
B
y
u
s
in
g
r
an
d
o
m
f
o
r
est’s
wo
r
k
ab
ilit
y
in
m
o
d
if
y
i
n
g
t
o
lo
ca
l
v
ar
iatio
n
s
an
d
SVM’
s
ab
ilit
y
to
ca
p
tu
r
e
s
m
o
o
th
tr
en
d
s
,
th
e
h
y
b
r
i
d
m
o
d
el
b
ec
o
m
es
ca
p
ab
le
to
p
r
o
v
id
e
a
c
o
m
p
r
eh
en
s
iv
e
an
aly
s
is
o
f
in
p
u
t
o
u
t
p
u
t
r
elatio
n
s
h
ip
.
T
h
ese
f
in
d
in
g
s
v
alid
ate
th
e
h
y
b
r
id
m
o
d
el
as
a
r
eliab
le
an
d
p
r
ec
is
e
s
o
lu
tio
n
f
o
r
ap
p
licatio
n
s
r
eq
u
ir
in
g
h
i
g
h
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
.
Fig
u
r
e
4
.
Av
ailab
le
s
ec
o
n
d
ar
y
d
ata
Fig
u
r
e
5
.
C
o
m
p
a
r
is
o
n
o
f
test
r
esu
lts
f
o
r
p
u
lp
co
n
s
is
ten
cy
Fig
u
r
e
6
.
C
o
m
p
a
r
is
o
n
o
f
test
r
esu
lts
f
o
r
p
u
lp
c
o
n
s
is
ten
cy
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
692
-
702
698
T
h
e
q
u
an
titativ
e
d
em
o
n
s
tr
atio
n
o
f
s
u
p
er
io
r
ity
o
f
th
e
h
y
b
r
id
m
o
d
el
is
p
r
esen
ted
b
y
th
e
co
m
p
ar
is
o
n
o
f
th
e
R
MSE
an
d
R
2
m
etr
ics,
s
h
o
wn
in
Fig
u
r
e
7
an
d
T
ab
le
1
:
i)
R
o
o
t
m
ea
n
s
q
u
ar
e
d
er
r
o
r
(
R
M
SE)
:
-
I
n
ca
s
e
o
f
th
e
h
ea
d
b
o
x
lev
el
,
t
h
e
h
y
b
r
id
m
o
d
el
h
as
a
s
ig
n
if
i
ca
n
t
d
r
o
p
i
n
R
MSE
m
o
d
el
(
3
.
4
5
)
th
an
t
h
e
SVM
m
o
d
el
(
4
.
7
0
)
,
w
h
ich
is
an
im
p
r
o
v
em
en
t in
2
6
.
6
% o
f
th
e
m
o
d
el.
-
I
n
th
e
ca
s
e
o
f
p
u
lp
co
n
s
is
ten
cy
,
th
e
h
y
b
r
id
m
o
d
el
d
ec
r
ea
s
es th
e
R
MSE
b
y
5
% i.
e.
to
4
.
7
1
f
r
o
m
4
.
9
6
.
ii)
R
²
m
etr
ics:
-
T
h
e
h
y
b
r
id
m
o
d
el
h
as
g
r
ea
ter
v
alu
es
o
f
R
2
o
f
b
o
th
o
u
tp
u
ts
with
a
v
alu
e
o
f
0
.
9
7
o
f
h
ea
d
b
o
x
lev
el
a
n
d
0
.
9
5
o
f
p
u
l
p
c
o
n
s
is
ten
cy
as
co
m
p
a
r
ed
to
0
.
9
4
an
d
0
.
9
3
o
f
p
u
l
p
co
n
s
is
ten
cy
an
d
h
e
ad
b
o
x
lev
el
,
r
esp
ec
tiv
ely
in
th
e
SVM
m
o
d
e
l.
T
h
is
m
ea
n
s
th
at
th
er
e
is
a
cl
o
s
er
co
r
r
elatio
n
b
etwe
en
t
h
e
p
r
ed
icted
an
d
tr
u
e
v
alu
es
,
an
d
th
e
m
o
d
el
th
at
in
clu
d
es a
h
y
b
r
id
m
o
d
el
is
b
et
ter
ab
le
to
ac
co
u
n
t
f
o
r
a
lar
g
er
p
er
ce
n
tag
e
o
f
th
e
v
a
r
ian
ce
in
t
h
e
o
u
t
p
u
t.
-
T
h
e
s
u
cc
ess
o
f
th
e
h
y
b
r
id
m
o
d
el
is
ex
p
lain
ed
b
y
th
e
f
ac
t
th
at
it
ca
n
tr
ad
e
-
o
f
f
lo
ca
l
a
n
d
g
l
o
b
al
er
r
o
r
s
.
SVM
co
m
p
o
n
e
n
t
o
f
f
er
s
lo
ca
l
tr
en
d
f
itti
n
g
ac
cu
r
ac
y
a
n
d
th
e
r
an
d
o
m
f
o
r
est
co
m
p
o
n
en
t
o
f
f
er
s
r
o
b
u
s
t
o
u
tlier
s
an
d
v
a
r
iab
ilit
y
r
esis
tan
ce
.
T
h
e
f
in
d
in
g
s
c
o
n
clu
s
iv
ely
esta
b
lis
h
th
e
h
y
b
r
id
SVM
-
R
F
m
o
d
el
as
a
s
u
p
er
io
r
alter
n
ati
v
e
to
s
tan
d
alo
n
e
SVM
f
o
r
p
r
ed
ictin
g
c
r
itical
p
ar
am
eter
s
in
in
d
u
s
tr
ial
p
r
o
ce
s
s
es.
B
y
ac
h
iev
in
g
lo
wer
R
MSE
an
d
h
i
g
h
er
R
2
v
alu
es,
th
e
h
y
b
r
id
m
o
d
el
d
eliv
er
s
im
p
r
o
v
e
p
r
ec
is
io
n
an
d
r
o
b
u
s
tn
ess
.
Ad
d
itio
n
ally
,
its
ad
ap
tab
ilit
y
an
d
s
ca
lab
ilit
y
m
ak
e
it
well
-
s
u
ited
f
o
r
d
e
p
lo
y
m
e
n
t in
cr
itical,
d
ata
-
d
r
iv
e
n
d
ec
is
io
n
-
m
ak
in
g
s
ce
n
ar
i
o
s
.
4
.
2
.
Ass
ess
m
ent
o
f
f
ina
l pro
du
ct
qu
a
lity
us
ing
S
VM
T
h
e
co
n
f
u
s
io
n
m
atr
ices
o
f
f
o
u
r
d
if
f
er
en
t
SVM
m
o
d
els
d
e
v
elo
p
ed
in
MA
T
L
AB
ar
e
p
r
esen
ted
in
Fig
u
r
es
8
-
1
1
.
E
ac
h
f
ig
u
r
e
illu
s
tr
ates
th
e
p
er
f
o
r
m
an
ce
o
f
a
s
p
e
cif
ic
SVM
m
o
d
el
in
ter
m
s
o
f
class
if
icatio
n
r
esu
lts
,
p
r
o
v
id
i
n
g
a
clea
r
r
ep
r
esen
tatio
n
o
f
p
r
ed
ictio
n
ac
cu
r
ac
y
a
n
d
e
r
r
o
r
d
is
tr
ib
u
tio
n
.
Fu
r
th
e
r
m
o
r
e
,
th
e
c
o
m
p
ar
is
o
n
o
f
th
e
r
esp
ec
tiv
e
ac
cu
r
ac
ies o
f
th
ese
m
o
d
els
is
s
u
m
m
ar
ized
in
T
ab
le
2
.
Fig
u
r
e
7
.
C
o
m
p
a
r
is
o
n
o
f
p
er
f
o
r
m
an
ce
m
atr
ices
T
ab
le
1
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
Te
c
h
n
i
q
u
e
R
.
M
.
S
.
E
.
R
2
H
e
a
d
b
o
x
l
e
v
e
l
(
m)
P
u
l
p
c
o
n
si
s
t
e
n
c
y
(
%)
H
e
a
d
b
o
x
l
e
v
e
l
(
m)
P
u
l
p
c
o
n
si
s
t
e
n
c
y
(
%)
S
V
M
4
.
7
0
4
.
9
6
0
.
9
4
0
.
9
3
S
V
M
-
R
F
h
y
b
r
i
d
3
.
4
5
4
.
7
1
0
.
9
7
0
.
9
5
T
ab
le
2
.
Per
f
o
r
m
an
ce
co
m
p
a
r
is
o
n
o
f
v
a
r
io
u
s
SVM
m
o
d
els
S
.
L.
Te
c
h
n
i
q
u
e
A
c
c
u
r
a
c
y
(
%)
1
Li
n
e
a
r
S
V
M
7
3
.
3
%
2
Q
u
a
d
r
a
t
i
c
S
V
M
8
0
%
3
C
u
b
i
c
S
V
M
9
0
%
4
F
i
n
e
g
a
u
ssi
a
n
A
V
M
8
3
.
3
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
P
r
ed
ictive
mo
d
elin
g
a
n
d
o
p
timiz
a
tio
n
o
f p
a
p
er mill u
s
in
g
h
yb
r
id
ma
ch
in
e
…
(
A
b
h
ijit
S
in
g
h
B
h
a
k
u
n
i
)
699
Fig
u
r
e
8
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
lin
ea
r
SVM
m
o
d
el
Fig
u
r
e
9
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
q
u
ad
r
atic
SVM
m
o
d
el
Fig
u
r
e
10
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
cu
b
ic
SVM
m
o
d
el
F
i
g
u
r
e
1
1
.
C
o
n
f
u
s
i
o
n
m
a
t
r
i
x
o
f
f
i
n
e
G
a
u
s
s
i
a
n
S
V
M
m
o
d
e
l
4
.
3
.
M
ultiv
a
ria
t
e
o
ptim
iza
t
io
n us
ing
G
A
f
o
r
qu
a
lity
enha
ncem
ent
Fig
u
r
e
1
2
illu
s
tr
ates
th
e
co
n
v
er
g
en
ce
b
e
h
av
io
u
r
o
f
th
e
f
itn
ess
f
u
n
ctio
n
o
v
er
1
5
0
g
en
e
r
atio
n
s
.
T
h
e
r
ap
id
d
ec
lin
e
in
th
e
f
itn
ess
v
alu
e
d
u
r
in
g
th
e
in
itial
g
en
er
atio
n
s
in
d
icate
s
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
g
en
etic
alg
o
r
ith
m
in
n
ar
r
o
win
g
th
e
s
o
lu
tio
n
s
p
ac
e.
T
h
e
v
alu
es
o
f
f
itn
ess
s
tab
il
ize
af
ter
th
e
5
0
th
g
en
er
atio
n
in
d
icatin
g
th
at
th
e
alg
o
r
ith
m
h
as
r
ea
c
h
ed
a
n
ea
r
o
p
tim
al
s
o
lu
tio
n
at
th
e
b
eg
in
n
in
g
.
T
h
e
last
o
b
jectiv
e
v
alu
e
o
f
0
.
0
2
in
d
icate
s
th
at
th
e
d
ev
iatio
n
is
m
in
im
al
to
th
e
id
ea
l
tar
g
et,
wh
ich
is
a
s
tr
en
g
th
o
f
th
e
ch
o
s
en
weig
h
ts
in
th
e
o
b
jectiv
e
f
u
n
ctio
n
.
Fig
u
r
e
1
3
s
h
o
ws
th
e
b
ar
ch
a
r
t
th
at
g
iv
es
th
e
clea
r
p
ictu
r
e
o
f
th
e
o
b
tain
ed
p
ar
am
eter
v
alu
e
s
.
T
h
e
f
ac
t
th
at
th
ese
v
alu
es
ar
e
clo
s
e
to
th
eir
tar
g
et
ju
s
tifie
s
th
e
ac
cu
r
ac
y
o
f
th
e
g
en
etic
alg
o
r
ith
m
i
n
o
p
tim
izatio
n
o
f
a
n
u
m
b
er
o
f
o
b
jectiv
es a
t th
e
s
a
m
e
tim
e.
T
h
e
im
p
li
ca
tio
n
s
ar
e
f
o
llo
wed
b
y
:
-
Flo
w
r
ate
:
At
9
0
.
3
9
m
³/s
,
th
e
s
y
s
tem
ac
h
iev
es
an
ef
f
icien
t
t
h
r
o
u
g
h
p
u
t
with
o
u
t
c
o
m
p
r
o
m
is
in
g
o
th
er
q
u
ality
p
ar
am
eter
s
.
-
Pre
s
s
u
r
e:
T
h
e
lo
w
p
r
ess
u
r
e
o
f
4
0
.
0
8
Pa
en
s
u
r
es
m
in
im
al
en
er
g
y
u
s
ag
e
wh
ile
m
ain
tain
in
g
s
tr
u
ctu
r
al
in
teg
r
ity
d
u
r
in
g
p
r
o
c
ess
in
g
.
-
T
em
p
er
atu
r
e:
T
h
e
v
alu
e
o
f
6
5
.
0
3
°C
alig
n
s
with
th
e
tar
g
et,
cr
u
cial
f
o
r
en
s
u
r
in
g
u
n
if
o
r
m
p
u
lp
d
is
tr
ib
u
tio
n
an
d
b
o
n
d
in
g
q
u
ality
.
-
Hea
d
b
o
x
lev
el
:
T
h
e
o
p
tim
ized
lev
el
o
f
8
.
0
4
m
f
ac
ili
tates
s
m
o
o
th
s
h
ee
t
f
o
r
m
ati
o
n
,
p
r
ev
en
tin
g
in
co
n
s
is
ten
cies in
th
ick
n
ess
.
-
Pu
lp
co
n
s
is
ten
cy
:
Ach
iev
in
g
1
2
.
0
8
%
en
s
u
r
es
o
p
tim
al
f
ib
er
d
is
tr
ib
u
tio
n
,
co
n
tr
i
b
u
tin
g
to
i
m
p
r
o
v
e
d
p
ap
e
r
s
tr
en
g
th
an
d
s
u
r
f
ac
e
p
r
o
p
e
r
ties
.
T
h
e
o
p
tim
izatio
n
p
r
o
ce
s
s
s
u
cc
ess
f
u
lly
d
eter
m
in
ed
th
e
b
est
s
et
o
f
p
ar
am
eter
s
th
at
m
in
im
ize
th
e
d
e
v
iatio
n
f
r
o
m
th
e
tar
g
et
q
u
ality
m
etr
ics f
o
r
p
ap
er
p
r
o
d
u
ctio
n
.
T
h
e
f
in
al
o
p
tim
ized
p
ar
am
eter
s
ar
e
s
u
m
m
ar
ized
in
T
ab
le
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
9
2
I
n
t J Ap
p
l Po
wer
E
n
g
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
692
-
702
700
Fig
u
r
e
12
.
Fit
n
ess
v
alu
es
Fig
u
r
e
13
.
Attain
ed
o
p
tim
ized
v
alu
es
T
ab
le
3
.
Attain
ed
o
p
tim
ized
v
alu
es
S
.
L.
P
a
r
a
me
t
e
r
O
p
t
i
mi
z
e
d
v
a
l
u
e
1.
F
l
o
w
r
a
t
e
(
m
3
/
s)
9
0
.
3
9
2.
P
r
e
ssu
r
e
(
P
a
)
4
0
.
0
8
3.
Te
mp
e
r
a
t
u
r
e
(
º
C
)
6
5
.
0
3
4.
H
e
a
d
b
o
x
l
e
v
e
l
(
m)
8
.
0
4
5.
P
u
l
p
c
o
n
si
s
t
e
n
c
y
(
%)
1
2
.
0
8
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
ex
am
in
es
h
o
w
to
in
co
r
p
o
r
ate
an
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
an
d
o
p
tim
izatio
n
in
en
h
an
cin
g
th
e
wo
r
k
in
g
o
f
in
d
u
s
tr
ies,
s
p
ec
if
ically
in
th
e
m
eth
o
d
o
f
m
o
n
ito
r
in
g
an
d
o
p
tim
izatio
n
o
f
i
m
p
o
r
tan
t
m
ea
s
u
r
es
lik
e
th
e
h
ea
d
b
o
x
lev
el
an
d
p
u
l
p
co
n
s
is
ten
cy
.
T
h
is
s
tu
d
y
o
f
f
e
r
s
an
ac
co
u
n
t
o
f
an
e
x
ten
s
iv
e
liter
atu
r
e
r
ev
iew
an
d
em
p
lo
y
s
th
e
p
r
ed
ictiv
e
ca
p
ac
it
y
o
f
d
if
f
er
en
t
SVM
m
o
d
els
u
s
in
g
MA
T
L
AB
an
d
h
elp
s
in
ill
u
m
in
atin
g
s
o
m
e
o
f
th
e
is
s
u
es
th
at
ar
e
in
tr
in
s
ic
t
o
p
ap
e
r
m
a
n
u
f
ac
tu
r
in
g
,
an
d
n
ew
d
ir
ec
tio
n
s
th
at
ca
n
b
e
ta
k
en
i
n
th
e
q
u
est
o
f
en
h
an
cin
g
s
u
s
tain
ab
ilit
y
in
p
ap
er
p
r
in
tin
g
.
A
v
e
r
y
c
o
m
p
r
eh
en
s
iv
e
a
n
aly
s
is
o
f
th
e
c
u
r
r
en
t
liter
atu
r
e
o
n
o
p
tim
izatio
n
an
d
co
n
t
r
o
l
o
f
d
if
f
er
en
t
s
y
s
tem
s
wh
ich
m
ak
e
u
p
a
p
ap
er
m
ill
h
as
b
ee
n
d
is
cu
s
s
ed
.
Var
io
u
s
m
eth
o
d
s
o
f
SVM
h
av
e
also
b
ee
n
c
r
ea
ted
to
id
en
tif
y
p
a
p
er
q
u
ality
in
class
if
icatio
n
m
o
d
els
in
M
AT
L
AB
.
T
h
e
f
in
e
G
au
s
s
ian
SVM
m
o
d
el
h
as
b
e
en
o
b
s
er
v
e
d
to
s
h
o
w
th
e
b
est
ac
cu
r
ac
y
o
f
all
th
e
SVM
m
o
d
els
d
ev
elo
p
ed
.
T
h
is
p
ap
er
em
p
lo
y
s
a
h
y
b
r
id
ap
p
r
o
a
ch
with
SVM
an
d
r
an
d
o
m
f
o
r
e
s
t
to
d
em
o
n
s
tr
ate
th
at
h
y
b
r
id
m
o
d
els
ar
e
ef
f
ec
tiv
e
in
p
r
ed
ictin
g
r
esu
lts
co
m
p
ar
e
d
to
wh
en
th
e
in
d
iv
i
d
u
al
s
tan
d
alo
n
e
m
eth
o
d
is
ap
p
lied
.
T
h
e
h
y
b
r
id
m
et
h
o
d
h
a
s
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
in
ter
m
s
o
f
less
er
r
o
r
s
(
s
m
all
R
MSE
)
an
d
h
ig
h
e
r
r
eliab
ilit
y
(
in
cr
ea
s
ed
R
2
v
alu
es).
T
h
e
last
o
n
e
is
to
s
tr
ea
m
lin
e
in
d
u
s
tr
ial
en
v
ir
o
n
m
e
n
t
s
u
ch
as
h
ea
d
b
o
x
lev
el,
p
u
lp
c
o
n
s
is
ten
cy
,
an
d
tem
p
er
atu
r
e
b
y
u
tili
zin
g
g
en
etic
alg
o
r
ith
m
(
G
A)
in
MA
T
L
AB
.
T
h
e
b
est
s
ets
o
f
th
ese
p
ar
am
eter
s
ar
e
in
d
icat
ed
u
s
in
g
th
is
m
eth
o
d
as
th
e
g
o
als
ar
e
b
alan
ce
d
to
ac
h
iev
e
q
u
ality
s
tan
d
ar
d
s
a
n
d
a
d
h
er
in
g
t
o
ce
r
tain
lim
its
to
m
ak
e
th
e
r
esu
lts
v
iab
le
an
d
r
ea
lis
tic.
T
h
is
s
tu
d
y
d
escr
ib
es
th
e
ad
v
a
n
tag
es
o
f
h
y
b
r
id
m
o
d
ellin
g
a
n
d
o
p
tim
izatio
n
in
s
o
lv
i
n
g
n
o
n
-
lin
ea
r
an
d
co
m
p
licated
in
d
u
s
tr
ial
s
y
s
tem
s
.
An
o
th
er
is
s
u
e
th
at
i
s
b
r
o
u
g
h
t
to
th
e
f
o
r
e
in
th
is
s
tu
d
y
is
t
h
e
n
ee
d
to
in
teg
r
ate
p
r
ed
ictio
n
a
n
d
o
p
tim
izatio
n
t
o
en
h
an
ce
th
e
e
f
f
icien
cy
a
n
d
q
u
ality
o
f
p
r
o
d
u
cts
o
f
co
m
p
le
x
in
d
u
s
tr
ial
s
y
s
tem
s
.
Als
o
,
it
em
p
lo
y
s
v
is
u
al
co
m
p
a
r
is
o
n
s
to
ass
is
t
in
m
ak
in
g
s
u
p
e
r
io
r
ju
d
g
m
en
ts
as
well.
T
h
e
s
t
u
d
y
f
o
r
m
s
a
s
tr
o
n
g
f
o
u
n
d
atio
n
o
n
ad
d
itio
n
al
in
n
o
v
atio
n
s
in
th
e
ar
ea
o
f
m
o
n
ito
r
i
n
g
,
co
n
t
r
o
l
,
an
d
o
p
tim
izatio
n
s
tr
ateg
y
in
th
e
p
a
p
er
in
d
u
s
tr
y
with
p
r
o
s
p
ec
ts
o
f
en
h
an
ce
d
q
u
ality
an
d
e
f
f
icien
cy
g
u
ar
an
tees.
Fu
tu
r
e
wo
r
k
co
u
ld
i
n
clu
d
e
r
ea
l
-
tim
e
d
ata
f
r
o
m
f
u
t
u
r
is
tic
s
en
s
o
r
s
,
an
d
o
th
e
r
o
p
tim
izatio
n
m
e
th
o
d
s
lik
e
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
o
r
d
if
f
e
r
en
tial
ev
o
lu
tio
n
(
DE
)
.
Fu
r
th
er
m
o
r
e,
c
o
m
b
in
i
n
g
co
s
t
a
n
d
e
n
er
g
y
s
av
in
g
p
r
o
ce
s
s
es
f
o
r
o
p
tim
iza
tio
n
.
Ov
er
all,
th
is
s
tu
d
y
s
h
o
w
s
h
o
w
ar
tific
ial
in
tellig
en
ce
(
AI
)
tech
n
iq
u
es
ca
n
im
p
r
o
v
e
i
n
d
u
s
tr
ial
p
r
o
ce
s
s
es a
n
d
m
ak
e
it
a
s
m
ar
ter
an
d
m
o
r
e
ef
f
icien
t m
an
u
f
ac
tu
r
in
g
s
y
s
tem
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
n
o
f
u
n
d
in
g
was
r
ec
eiv
e
d
f
o
r
th
is
r
esear
ch
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ap
p
l Po
wer
E
n
g
I
SS
N:
2252
-
8
7
9
2
P
r
ed
ictive
mo
d
elin
g
a
n
d
o
p
timiz
a
tio
n
o
f p
a
p
er mill u
s
in
g
h
yb
r
id
ma
ch
in
e
…
(
A
b
h
ijit
S
in
g
h
B
h
a
k
u
n
i
)
701
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ab
h
ijit
Sin
g
h
B
h
ak
u
n
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
San
d
ee
p
Ku
m
ar
Su
n
o
r
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
Pra
d
ee
p
J
u
n
eja
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
t
h
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
el
atio
n
s
h
ip
s
th
at
co
u
ld
h
av
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
e
p
o
r
te
d
in
t
h
is
p
ap
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
is
wo
r
k
is
b
ased
o
n
a
v
ailab
le
d
ata
wh
ich
b
elo
n
g
s
to
th
e
p
ap
er
m
ill
-
C
en
tu
r
y
Pu
l
p
an
d
P
ap
er
Mill,
L
alk
u
an
,
Uttar
ak
h
an
d
.
RE
F
E
R
E
NC
E
S
[
1
]
J.
H
a
t
h
a
w
a
y
,
A
.
R
a
s
t
e
g
a
r
p
a
n
a
h
,
a
n
d
R
.
S
t
o
l
k
i
n
,
“
Le
a
r
n
i
n
g
r
o
b
o
t
i
c
m
i
l
l
i
n
g
st
r
a
t
e
g
i
e
s
b
a
se
d
o
n
p
a
ssi
v
e
v
a
r
i
a
b
l
e
o
p
e
r
a
t
i
o
n
a
l
s
p
a
c
e
i
n
t
e
r
a
c
t
i
o
n
c
o
n
t
r
o
l
,
”
i
n
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Au
t
o
m
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
2
0
2
4
,
p
p
.
3
4
3
5
–
3
4
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
TA
S
E.
2
0
2
3
.
3
2
7
9
7
1
8
.
[
2
]
C
.
B
u
r
n
e
t
t
e
a
n
d
G
.
O
g
l
e
s,
“
P
o
w
e
r
s
y
s
t
e
m
i
mp
r
o
v
e
me
n
t
s
a
t
a
c
e
n
t
u
r
y
-
o
l
d
p
a
p
e
r
mi
l
l
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
ry
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
6
0
,
n
o
.
3
,
p
p
.
5
2
2
9
–
5
2
4
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
A
.
2
0
2
4
.
3
3
6
5
6
6
8
.
[
3
]
G
.
M
.
M
e
n
d
e
z
,
I
.
L
o
p
e
z
-
J
u
a
r
e
z
,
P
.
N
.
M
o
n
t
e
s
-
D
o
r
a
n
t
e
s,
a
n
d
M
.
A
.
G
a
r
c
i
a
,
“
A
n
e
w
m
e
t
h
o
d
f
o
r
t
h
e
d
e
s
i
g
n
o
f
i
n
t
e
r
v
a
l
t
y
p
e
-
3
f
u
z
z
y
l
o
g
i
c
sy
s
t
e
ms
w
i
t
h
u
n
c
e
r
t
a
i
n
t
y
p
e
-
2
n
o
n
-
s
i
n
g
l
e
t
o
n
i
n
p
u
t
s
(
IT
3
N
S
F
LS
-
2
)
:
a
c
a
se
s
t
u
d
y
i
n
a
h
o
t
s
t
r
i
p
m
i
l
l
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
4
4
0
6
5
–
4
4
0
8
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
7
2
5
3
1
.
[
4
]
N
.
K
a
m
i
y
a
,
Y
.
Y
o
s
h
i
z
a
t
o
,
Y
.
Z
h
o
u
,
Y
.
O
h
y
a
n
a
g
i
,
a
n
d
K
.
S
h
i
b
a
z
a
k
i
,
“
F
i
b
e
r
e
s
t
i
m
a
t
i
o
n
f
r
o
m
p
a
p
e
r
mac
r
o
i
m
a
g
e
s
v
i
a
e
f
f
i
c
i
e
n
t
n
e
t
-
b
a
s
e
d
p
a
t
c
h
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
2
2
7
1
–
1
2
2
7
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
5
5
1
1
5
.
[
5
]
S
.
R
.
V
a
r
s
h
a
a
,
N
.
T
h
i
r
u
m
u
r
u
g
a
n
,
a
n
d
K
.
S
u
r
e
s
h
,
“
Ef
f
i
c
i
e
n
t
d
e
g
r
a
d
a
t
i
o
n
o
f
p
a
p
e
r
mi
l
l
e
f
f
l
u
e
n
t
b
y
sy
n
e
r
g
y
o
f
m
i
c
r
o
d
i
s
c
h
a
r
g
e
p
l
a
sma
a
n
d
f
e
n
t
o
n
-
l
i
k
e
p
r
o
c
e
ss,”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Pl
a
sm
a
S
c
i
e
n
c
e
,
v
o
l
.
5
2
,
n
o
.
7
,
p
p
.
2
5
9
5
–
2
6
0
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
TPS
.
2
0
2
4
.
3
3
7
1
6
4
7
.
[
6
]
S
.
F
a
i
r
e
e
,
C
.
K
h
o
m
p
a
t
r
a
p
o
r
n
,
B
.
S
i
r
i
n
a
o
v
a
k
u
l
,
a
n
d
S
.
P
r
o
m
-
O
n
,
“
Tr
i
m
l
o
ss
o
p
t
i
m
i
z
a
t
i
o
n
i
n
p
a
p
e
r
p
r
o
d
u
c
t
i
o
n
u
s
i
n
g
r
e
i
n
f
o
r
c
e
m
e
n
t
a
r
t
i
f
i
c
i
a
l
b
e
e
c
o
l
o
n
y
,
”
I
EE
E
A
c
c
e
s
s
,
v
o
l
.
8
,
p
p
.
1
3
0
6
4
7
–
1
3
0
6
6
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
8
9
2
2
.
[
7
]
H
.
N
e
w
t
o
n
a
n
d
J
.
M
c
C
r
o
r
y
,
“
M
a
k
i
n
g
my
p
a
p
e
r
m
i
l
l
s
a
f
e
r
:
a
n
a
r
c
-
f
l
a
sh
e
n
e
r
g
y
r
e
d
u
c
t
i
o
n
s
t
o
r
y
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
s
t
ry
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
5
6
,
n
o
.
4
,
p
p
.
3
3
3
1
–
3
3
3
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
A
.
2
0
2
0
.
2
9
8
6
3
3
4
.
[
8
]
E.
J.
S
m
i
t
h
,
“
A
c
o
mp
u
t
e
r
i
z
e
d
p
u
l
p
a
n
d
p
a
p
e
r
m
i
l
l
i
n
st
r
u
me
n
t
a
t
i
o
n
a
n
d
c
o
n
t
r
o
l
sy
s
t
e
m
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
ri
a
l
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
ro
l
I
n
st
r
u
m
e
n
t
a
t
i
o
n
,
v
o
l
.
I
EC
I
-
1
3
,
n
o
.
1
,
p
p
.
1
0
–
1
6
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
t
i
e
c
i
.
1
9
6
6
.
6
5
9
2
6
4
4
.
[
9
]
G
.
F
i
g
u
e
i
r
a
,
M
.
F
u
r
l
a
n
,
a
n
d
B
.
A
l
m
a
d
a
-
Lo
b
o
,
“
P
r
e
d
i
c
t
i
v
e
p
r
o
d
u
c
t
i
o
n
p
l
a
n
n
i
n
g
i
n
a
n
i
n
t
e
g
r
a
t
e
d
p
u
l
p
a
n
d
p
a
p
e
r
mi
l
l
,
”
I
FAC
Pro
c
e
e
d
i
n
g
s V
o
l
u
m
e
s
(
I
FAC
-
Pa
p
e
rs
O
n
l
i
n
e
)
,
v
o
l
.
4
6
,
n
o
.
9
,
p
p
.
3
7
1
–
3
7
6
,
2
0
1
3
,
d
o
i
:
1
0
.
3
1
8
2
/
2
0
1
3
0
6
1
9
-
3
-
RU
-
3
0
1
8
.
0
0
4
0
9
.
[
1
0
]
C
.
W
u
,
Y
.
Z
h
o
u
,
W
.
G
a
n
,
a
n
d
J
.
W
u
,
“
R
o
b
u
st
s
c
h
e
d
u
l
i
n
g
o
f
a
p
u
l
p
a
n
d
p
a
p
e
r
mi
l
l
c
o
n
s
i
d
e
r
i
n
g
f
l
e
x
i
b
i
l
i
t
y
p
r
o
v
i
si
o
n
f
r
o
m
s
t
e
a
m
p
o
w
e
r
g
e
n
e
r
a
t
i
o
n
,
”
Ap
p
l
i
e
d
En
e
rg
y
,
v
o
l
.
3
7
7
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
e
n
e
r
g
y
.
2
0
2
4
.
1
2
4
5
9
5
.
[
1
1
]
D
.
Zu
m
o
f
f
e
n
a
n
d
M
.
B
a
s
u
a
l
d
o
,
“
F
r
o
m
l
a
r
g
e
c
h
e
mi
c
a
l
p
l
a
n
t
d
a
t
a
t
o
f
a
u
l
t
d
i
a
g
n
o
s
i
s
i
n
t
e
g
r
a
t
e
d
t
o
d
e
c
e
n
t
r
a
l
i
z
e
d
f
a
u
l
t
-
t
o
l
e
r
a
n
t
c
o
n
t
r
o
l
:
p
u
l
p
mi
l
l
p
r
o
c
e
ss
a
p
p
l
i
c
a
t
i
o
n
,
”
I
n
d
u
st
ri
a
l
a
n
d
E
n
g
i
n
e
e
ri
n
g
C
h
e
m
i
st
ry
R
e
se
a
rc
h
,
v
o
l
.
4
7
,
n
o
.
4
,
p
p
.
1
2
0
1
–
1
2
2
0
,
2
0
0
8
,
d
o
i
:
1
0
.
1
0
2
1
/
i
e
0
7
1
0
6
4
m.
[
1
2
]
S
.
M
a
h
e
s
h
,
B
.
P
r
a
s
a
d
,
I
.
D
.
M
a
l
l
,
a
n
d
I
.
M
.
M
i
sh
r
a
,
“
E
l
e
c
t
r
o
c
h
e
m
i
c
a
l
d
e
g
r
a
d
a
t
i
o
n
o
f
p
u
l
p
a
n
d
p
a
p
e
r
mi
l
l
w
a
st
e
w
a
t
e
r
.
P
a
r
t
2
.
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
a
n
d
a
n
a
l
y
s
i
s
o
f
s
l
u
d
g
e
,
”
I
n
d
u
st
r
i
a
l
a
n
d
E
n
g
i
n
e
e
r
i
n
g
C
h
e
m
i
st
ry
Re
se
a
r
c
h
,
v
o
l
.
4
5
,
n
o
.
1
6
,
p
p
.
5
7
6
6
–
5
7
7
4
,
2
0
0
6
,
d
o
i
:
1
0
.
1
0
2
1
/
i
e
0
6
0
3
9
6
9
.
[
1
3
]
J.
M
i
z
u
k
i
,
“
M
o
d
e
l
-
b
a
s
e
d
p
r
e
d
i
c
t
i
v
e
a
d
a
p
t
i
v
e
c
o
n
t
r
o
l
o
f
p
u
l
p
a
n
d
p
a
p
e
r
mi
l
l
p
r
o
c
e
ss
e
s,
”
J
a
p
a
n
T
a
p
p
i
J
o
u
r
n
a
l
,
v
o
l
.
6
3
,
n
o
.
8
,
p
p
.
9
3
0
–
9
3
5
,
2
0
0
9
,
d
o
i
:
1
0
.
2
5
2
4
/
j
t
a
p
p
i
j
.
6
3
.
9
3
0
.
[
1
4
]
Y
.
K
.
Y
e
o
,
J.
H
.
P
a
r
k
,
S
.
H
.
P
a
r
k
,
a
n
d
C
.
S
o
h
n
,
“
M
o
d
e
l
a
l
g
o
r
i
t
h
mi
c
c
o
n
t
r
o
l
o
f
g
r
a
d
e
c
h
a
n
g
e
o
p
e
r
a
t
i
o
n
s
i
n
p
a
p
e
r
mi
l
l
s,
”
K
o
re
a
n
J
o
u
rn
a
l
o
f
C
h
e
m
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
2
,
n
o
.
3
,
p
p
.
3
3
9
–
3
4
4
,
2
0
0
5
,
d
o
i
:
1
0
.
1
0
0
7
/
B
F
0
2
7
1
9
4
0
8
.
[
1
5
]
B
.
K
a
y
a
l
,
Y
.
N
a
sr
,
H
.
El
Za
k
h
e
m
,
a
n
d
M
.
El
B
a
c
h
a
w
a
t
i
,
“
O
p
t
i
mi
z
i
n
g
b
r
o
w
n
st
o
c
k
w
a
s
h
i
n
g
i
n
t
h
e
p
u
l
p
a
n
d
p
a
p
e
r
i
n
d
u
s
t
r
y
:
a
sy
s
t
e
m
d
y
n
a
mi
c
s
a
p
p
r
o
a
c
h
,
”
Pr
o
c
e
ss
e
s
,
v
o
l
.
1
3
,
n
o
.
2
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
p
r
1
3
0
2
0
3
6
8
.
[
1
6
]
F
.
O
c
k
l
i
n
d
,
K
.
Li
b
a
c
k
,
L
.
Lu
n
d
q
v
i
s
t
,
W
.
H
a
r
g
e
,
a
n
d
G
.
V
e
n
k
a
t
e
sh
,
“
O
p
t
i
m
i
sat
i
o
n
o
f
w
a
t
e
r
-
u
se
i
n
p
u
l
p
a
n
d
p
a
p
e
r
mi
l
l
s:
a
st
r
e
a
ml
i
n
e
d
r
e
v
i
e
w
o
f
s
c
i
e
n
t
i
f
i
c
j
o
u
r
n
a
l
p
u
b
l
i
c
a
t
i
o
n
s,”
S
t
u
d
i
a
E
c
o
l
o
g
i
a
e
e
t
Bi
o
e
t
h
i
c
a
e
,
v
o
l
.
2
2
,
n
o
.
3
,
p
p
.
9
5
–
1
0
5
,
2
0
2
4
,
d
o
i
:
1
0
.
2
1
6
9
7
/
se
b
.
5
8
1
3
.
[
1
7
]
B
.
S
.
C
a
r
l
b
e
r
g
,
“
Th
e
a
u
t
o
n
o
m
o
u
s mi
l
l
:
u
t
i
l
i
z
i
n
g
d
i
g
i
t
a
l
t
w
i
n
s
t
o
o
p
t
i
mi
z
e
t
h
e
p
u
l
p
& p
a
p
e
r
mi
l
l
o
f
t
h
e
f
u
t
u
r
e
,
”
i
n
I
EEE
C
o
n
f
e
r
e
n
c
e
Re
c
o
rd
o
f
An
n
u
a
l
P
u
l
p
a
n
d
P
a
p
e
r I
n
d
u
st
r
y
T
e
c
h
n
i
c
a
l
C
o
n
f
e
r
e
n
c
e
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
P
P
I
C
4
7
8
4
6
.
2
0
2
1
.
9
6
2
0
3
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.