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
.
5
,
Octo
b
e
r
2
0
1
7
,
p
p
.
2
8
8
3
~2
894
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v7
i
5
.
pp
2
8
8
3
-
2
894
2883
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
Ins
ig
hts on Resea
rch Techn
iques
tow
a
rds Co
st Esti
ma
tion in
So
ft
w
a
re De
sig
n
P
ra
v
ee
n Na
ik
1
,
Sh
a
nta
ra
m
Na
y
a
k
2
1
V
T
U,
De
p
t
o
f
Co
m
p
u
ter S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
F
a
c
u
l
ty
o
f
En
g
g
,
Ch
rist
Un
iv
e
rsity
,
Ba
n
g
a
lo
re
,
In
d
i
a
2
De
p
t
o
f
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
R
V
Co
l
leg
e
o
f
En
g
in
e
e
rin
g
Ba
n
g
a
lo
re
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
16
,
2
0
1
7
R
ev
i
s
ed
Ma
y
15
,
2
0
1
7
A
cc
ep
ted
A
ug
11
,
2
0
1
7
S
o
f
tw
a
r
e
c
o
st
e
sti
m
a
ti
o
n
is
o
f
th
e
m
o
st
c
h
a
ll
e
n
g
in
g
tas
k
in
p
r
o
jec
t
m
a
n
a
g
e
m
e
n
t
in
o
rd
e
r
t
o
e
n
su
r
in
g
s
m
o
o
th
e
r
d
e
v
e
lo
p
m
e
n
t
o
p
e
ra
ti
o
n
a
n
d
targ
e
t
a
c
h
iev
e
m
e
n
t.
T
h
e
re
h
a
s
b
e
e
n
e
v
o
lu
ti
o
n
o
f
v
a
rio
u
s
sta
n
d
a
rd
s
to
o
ls
a
n
d
tec
h
n
iq
u
e
s
f
o
r
c
o
st
e
stim
a
ti
o
n
p
ra
c
ti
c
e
d
in
t
h
e
i
n
d
u
stry
a
t
p
re
se
n
t
ti
m
e
s.
Ho
w
e
v
e
r,
it
w
a
s
n
e
v
e
r
in
v
e
stig
a
ted
a
b
o
u
t
th
e
o
v
e
ra
ll
p
ictu
ri
z
a
ti
o
n
o
f
e
ffe
c
ti
v
e
n
e
ss
o
f
su
c
h
tec
h
n
iq
u
e
s
t
il
l
d
a
te.
T
h
is
p
a
p
e
r
in
it
iate
s
it
s
c
o
n
tri
b
u
ti
o
n
b
y
p
re
s
e
n
ti
n
g
tax
o
n
o
m
ies
o
f
c
o
n
v
e
n
ti
o
n
a
l
c
o
st
-
e
stim
a
ti
o
n
tec
h
n
iq
u
e
s
a
n
d
th
e
n
in
v
e
stig
a
te
s
th
e
re
se
a
rc
h
tre
n
d
s
to
w
a
rd
s
f
r
e
q
u
e
n
tl
y
a
d
d
re
ss
e
d
p
ro
b
lem
s
in
it
.
T
h
e
p
a
p
e
r
a
lso
re
v
ie
ws
th
e
e
x
isti
n
g
tec
h
n
iq
u
e
s
in
w
e
ll
-
stru
c
tu
re
d
m
a
n
n
e
r
in
o
rd
e
r
to
h
ig
h
li
g
h
t
t
h
e
p
ro
b
lem
s
a
d
d
re
ss
e
d
,
tec
h
n
iq
u
e
s
u
se
d
,
a
d
v
a
n
tag
e
s
a
ss
o
c
iat
e
d
a
n
d
li
m
it
a
ti
o
n
e
x
p
lo
re
d
f
ro
m
li
tera
tu
re
s.
F
in
a
ll
y
,
we
a
lso
b
rief
th
e
e
x
p
l
o
re
d
o
p
e
n
re
se
a
rc
h
issu
e
s
a
s
a
n
a
d
d
e
d
c
o
n
tr
ib
u
t
io
n
to
th
is
m
a
n
u
sc
rip
t.
K
ey
w
o
r
d
s
:
E
f
f
o
r
t e
s
t
i
m
a
tio
n
Fau
lt p
r
ed
ictio
n
So
f
t
w
ar
e
co
s
t e
s
ti
m
at
io
n
So
f
t
w
ar
e
m
o
d
elli
n
g
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
:
P
r
av
ee
n
Naik
,
R
esear
ch
Sch
o
lar
,
Dep
t o
f
C
o
m
p
u
ter
Scien
ce
&
E
n
g
i
n
ee
r
i
n
g
,
Facu
lt
y
o
f
E
n
g
g
,
C
h
r
is
t U
n
i
v
e
r
s
it
y
,
B
an
g
alo
r
e,
I
n
d
ia.
E
m
ail:
p
r
av
ee
n
.
r
esear
ch
.
s
e
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
So
f
t
w
ar
e
d
ev
elo
p
m
e
n
t
c
y
cle
p
la
y
s
a
s
ig
n
i
f
ica
n
t
r
o
le
in
p
r
o
j
e
ct
m
a
n
ag
e
m
e
n
t
t
h
at
d
ir
ec
tl
y
i
m
p
ac
ts
t
h
e
p
r
o
d
u
ctiv
it
y
[
1
]
.
No
r
m
all
y
,
th
e
p
r
o
ce
s
s
o
f
s
o
f
t
w
ar
e
d
ev
elo
p
m
en
t
in
v
o
lv
e
s
lo
n
g
er
d
u
r
atio
n
an
d
it
s
u
f
f
er
s
f
r
o
m
ce
r
tain
p
ar
an
o
ia
o
f
u
n
ce
r
tai
n
t
y
[
2
-
3
]
.
T
h
e
r
o
o
t
ca
u
s
e
o
f
s
u
c
h
u
n
ce
r
tain
t
y
co
u
ld
b
e
r
eq
u
ir
em
en
t
v
o
latili
t
y
[
4
]
,
d
ef
ec
tiv
e
p
r
o
j
ec
t
g
u
id
eli
n
es
[
5
]
,
s
k
ill
g
ap
[
6
]
,
an
d
w
r
o
n
g
p
r
o
j
ec
t
p
lan
n
in
g
[
7
]
.
An
in
ap
p
r
o
p
r
iate
p
r
o
j
ec
t
p
lan
n
i
n
g
ca
n
lead
to
s
ig
n
if
ic
an
t
lo
s
s
o
f
r
eso
u
r
ce
s
w
ith
r
e
s
p
ec
t
to
ti
m
e,
m
o
n
e
y
,
an
d
ef
f
o
r
t
[
8
]
.
T
h
e
p
r
im
e
s
tep
p
in
g
s
to
n
e
o
f
s
u
cc
e
s
s
i
n
p
r
o
j
ec
t
p
lan
n
in
g
is
to
esti
m
ate
t
h
e
co
s
t
in
v
o
l
v
ed
in
t
h
e
s
o
f
t
w
ar
e
p
r
o
j
ec
t
d
ev
elo
p
m
en
t.
T
h
er
ef
o
r
e,
w
e
c
an
d
ef
i
n
e
s
o
f
t
w
ar
e
co
s
t
e
s
ti
m
atio
n
as
t
h
e
m
ec
h
a
n
i
s
m
th
at
p
er
f
o
r
m
s
f
o
r
ec
asti
n
g
th
e
o
r
ig
i
n
al
a
n
d
cu
m
u
lati
v
e
c
o
s
t
r
eq
u
ir
ed
to
co
m
p
lete
th
e
s
o
f
t
w
ar
e
p
r
o
j
ec
t
o
n
a
ten
tati
v
e
ti
m
e
i
n
p
r
ese
n
ce
o
f
all
r
eso
u
r
ce
s
a
n
d
co
n
s
tr
ain
t
s
[
9
-
1
0
]
.
I
t
is
as
s
u
m
ed
to
b
e
h
ig
h
l
y
co
m
p
le
x
itie
s
f
o
r
m
an
y
in
d
u
s
tr
ies
as
co
s
t
in
v
o
l
v
e
m
en
t
d
if
f
er
s
f
o
r
d
if
f
e
r
en
t
p
r
o
j
ec
t
an
d
th
er
e
ar
e
n
u
m
er
o
u
s
f
a
c
to
r
s
th
at
a
f
f
ec
t
it.
I
n
th
is
p
r
o
ce
s
s
,
f
u
n
ctio
n
al
s
ize
m
atter
s
t
h
e
m
o
s
t
as
it
is
r
esp
o
n
s
ib
le
f
o
r
co
m
p
u
ti
n
g
s
ize
o
f
t
h
e
s
o
f
t
w
ar
e
t
h
at
is
co
n
s
id
er
ed
as
th
e
co
r
e
in
p
u
t
f
o
r
m
aj
o
r
it
y
o
f
t
h
e
m
o
d
eli
n
g
.
On
e
o
f
t
h
e
ex
a
m
p
le
s
o
f
s
u
c
h
s
tan
d
ar
d
m
et
h
o
d
is
C
o
m
m
o
n
So
f
t
w
ar
e
Me
as
u
r
e
m
e
n
t
I
n
ter
n
atio
n
al
C
o
n
s
o
r
tiu
m
(
C
OSMI
C
)
th
at
i
s
ce
r
tif
ied
b
y
I
SO
/I
E
X
1
9
7
6
1
:2
0
1
1
[
1
1
]
.
An
o
th
er
e
s
s
e
n
tial
i
n
d
icato
r
o
f
t
h
e
co
s
t
i
n
v
o
l
v
e
m
en
t
is
th
e
d
ev
elo
p
m
e
n
t
e
f
f
o
r
t
[
1
2
]
th
at
ca
n
b
e
d
e
f
i
n
ed
as
ef
f
ec
tiv
e
a
m
o
u
n
t
o
f
ti
m
e
u
s
e
d
f
o
r
d
ev
elo
p
in
g
t
h
e
s
o
f
t
w
ar
e
p
r
o
j
ec
t
in
p
r
o
g
r
ess
iv
e
o
r
d
er
.
Sin
ce
la
s
t
d
ec
ad
e,
th
er
e
h
as
b
ee
n
e
v
o
lu
tio
n
o
f
v
a
r
io
u
s
s
u
c
h
m
ec
h
an
i
s
m
s
;
h
o
w
e
v
er
,
n
o
n
e
o
f
th
e
s
i
n
g
le
m
ec
h
a
n
is
m
ca
n
b
e
s
aid
to
1
0
0
%
f
u
ll
p
r
o
o
f
f
o
r
co
s
t
est
i
m
atio
n
[
1
3
]
.
A
n
o
t
h
er
i
n
d
icato
r
o
f
th
e
co
s
t
f
ac
to
r
i
s
li
n
e
-
of
-
co
d
e
w
h
ic
h
i
s
u
n
i
v
er
s
al
l
y
co
n
s
id
er
ed
as
t
h
e
b
est
m
etr
ic
to
e
s
ti
m
ate
co
s
t
o
f
s
o
f
t
w
ar
e
d
ev
e
lo
p
m
en
t
[
1
4
]
.
Af
ter
t
h
e
s
o
f
t
w
ar
e
is
b
u
ild
,
it
is
also
r
eq
u
ir
ed
to
b
e
p
r
o
p
er
ly
test
ed
t
h
at
co
u
ld
b
e
d
o
n
e
b
o
th
b
y
m
a
n
u
al
an
d
b
y
au
to
m
a
ted
test
i
n
g
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
.
5
,
Octo
b
er
2
0
1
7
:
2
8
8
3
–
2
8
9
4
2884
[
1
5
]
.
T
h
er
e
is
also
a
co
s
t
in
v
o
l
v
e
m
en
t
ev
e
n
i
n
test
in
g
p
h
a
s
e
to
o
an
d
h
en
ce
co
m
p
r
e
h
e
n
s
i
v
e
test
i
n
g
m
ec
h
an
is
m
th
at
co
n
s
u
m
e
s
m
o
r
e
ti
m
e
an
d
m
o
r
e
r
eso
u
r
ce
s
ar
e
n
o
w
f
a
d
in
g
s
lo
w
l
y
f
r
o
m
t
h
e
i
n
d
u
s
tr
y
.
A
cc
o
r
d
in
g
to
t
h
e
ar
ticle
p
r
esen
ted
b
y
S
m
itte
et
al.
[
1
6
]
,
th
er
e
ar
e
m
an
y
r
ep
u
ted
o
r
g
an
izatio
n
w
h
o
h
a
s
alr
ea
d
y
i
n
itiated
s
tep
s
to
w
ar
d
s
s
a
v
i
n
g
co
s
t
o
f
s
o
f
t
w
a
r
e
d
ev
elo
p
m
e
n
t.
I
r
r
esp
ec
tiv
e
o
f
th
e
t
y
p
e
o
f
w
o
r
k
(
co
m
p
lex
s
o
f
t
w
ar
e
p
r
o
j
ec
ts
,
test
a
u
to
m
a
tio
n
,
r
e
m
o
te
s
u
p
p
o
r
t
w
o
r
k
,
a
g
ile
p
r
o
j
ec
ts
,
etc)
,
it
is
f
ea
s
ib
le
f
o
r
s
a
v
i
n
g
t
h
e
co
s
t
p
r
o
v
id
ed
an
ef
f
ec
tiv
e
a
n
d
er
r
o
r
f
r
ee
m
o
d
eli
n
g
o
f
co
s
t e
s
ti
m
atio
n
in
s
o
f
t
war
e
p
r
o
j
ec
ts
d
o
ex
is
ts
.
Ho
w
e
v
er
,
th
er
e
is
a
d
if
f
er
e
n
ce
b
et
w
ee
n
t
h
e
h
y
p
e
a
n
d
r
ea
lit
y
.
A
t
p
r
esen
t,
th
er
e
ar
e
q
u
ite
a
f
e
w
s
tan
d
ar
d
tech
n
iq
u
es
e.
g
.
C
o
n
s
tr
u
cti
v
e
C
o
s
t
Mo
d
elin
g
(
C
OC
OM
O)
th
at
i
s
f
o
u
n
d
ex
er
cised
b
y
v
ar
io
u
s
r
esear
ch
er
s
f
o
r
co
s
t
e
s
ti
m
atio
n
a
n
d
ef
f
o
r
t
e
s
ti
m
atio
n
.
On
e
o
f
t
h
e
b
i
g
g
e
s
t
i
m
p
ed
i
m
en
t
s
to
war
d
s
m
o
d
elin
g
co
s
t
esti
m
atio
n
tec
h
n
iq
u
e
s
is
to
e
n
s
u
r
e
ac
cu
r
ac
y
i
n
p
r
ed
ictio
n
r
ate.
I
n
o
r
d
er
to
p
e
r
f
o
r
m
p
r
ed
ic
tio
n
,
th
e
s
o
f
t
w
ar
e
m
o
d
eli
n
g
w
i
ll
b
e
h
i
g
h
l
y
r
eq
u
i
r
ed
to
p
o
s
s
ess
ce
r
tain
h
eu
r
i
s
ti
c
in
f
o
r
m
at
io
n
[
1
1
]
.
I
n
s
u
ch
ca
s
es,
t
h
e
m
o
d
el
w
i
ll
b
e
r
eq
u
ir
ed
to
h
av
e
ac
ce
s
s
to
h
ig
h
er
n
u
m
b
er
o
f
h
eu
r
i
s
tic
o
r
g
an
izat
io
n
al
d
ata
an
d
th
en
it
s
ac
cu
r
ac
y
w
ill
b
e
h
ig
h
l
y
d
ep
en
d
en
t
o
n
t
h
e
d
i
m
e
n
s
io
n
o
f
h
e
u
r
is
tic
s
.
I
n
o
th
er
wa
y
,
it
ca
n
p
r
o
v
id
e
co
s
t
esti
m
at
io
n
b
u
t
at
th
e
co
s
t
o
f
o
r
g
an
izatio
n
r
e
s
o
u
r
ce
s
.
He
n
ce
,
t
h
er
e
ar
e
v
ar
io
u
s
e
x
p
er
ts
w
h
o
s
ti
ll
b
elie
v
e
t
h
at
co
s
t
-
es
ti
m
atio
n
m
o
d
eli
n
g
is
ac
tu
all
y
i
n
its
n
a
s
ce
n
t
s
ta
g
e
a
n
d
it
w
ill
b
e
q
u
ite
n
ec
ess
ar
y
t
o
p
er
f
o
r
m
r
e
-
i
n
v
e
s
ti
g
atio
n
ta
k
in
g
p
r
o
m
in
e
n
t
ca
s
es
o
f
s
o
f
t
w
ar
e
d
ev
elo
p
m
en
t.
T
h
is
p
ap
er
d
is
cu
s
s
e
s
ab
o
u
t
th
e
ex
is
ti
n
g
s
y
s
te
m
,
th
eir
e
f
f
ec
ti
v
en
e
s
s
,
li
m
itatio
n
,
in
o
r
d
er
to
d
er
iv
e
th
e
o
p
en
is
s
u
es i
n
s
o
f
t
w
ar
e
co
s
t e
s
ti
m
atio
n
.
Sectio
n
1
.
2
d
is
cu
s
s
e
s
ab
o
u
t th
e
s
ta
n
d
ar
d
class
i
f
icat
io
n
o
f
t
h
e
s
o
f
t
w
ar
e
co
s
t
es
ti
m
atio
n
tec
h
n
iq
u
es
i
n
b
r
ief
f
o
llo
w
ed
b
y
d
is
c
u
s
s
io
n
o
f
r
esear
ch
tr
en
d
s
to
w
ar
d
s
a
d
d
r
ess
in
g
r
esear
c
h
p
r
o
b
lem
in
Sec
tio
n
1
.
3
.
Sectio
n
2
elab
o
r
ates
ab
o
u
t
th
e
ex
i
s
tin
g
r
esear
ch
tec
h
n
iq
u
e
s
o
n
m
u
ltip
le
p
r
o
b
lem
s
h
ig
h
li
g
h
ts
t
h
eir
ad
v
a
n
ta
g
es
a
n
d
li
m
itat
io
n
.
Di
s
c
u
s
s
i
o
n
o
f
o
p
en
r
esear
ch
is
s
u
e
s
i
s
ca
r
r
ie
d
o
u
t
i
n
Sectio
n
3
f
o
llo
w
ed
b
y
co
n
clu
s
io
n
i
n
Sec
tio
n
4
.
1
.
1
.
B
a
ck
g
ro
un
d
B
ef
o
r
e,
b
r
ief
in
g
t
h
e
tax
o
n
o
m
i
es
o
f
t
h
e
e
x
is
ti
n
g
s
o
f
t
w
ar
e
co
s
t
es
ti
m
atio
n
tech
n
iq
u
es
f
r
o
m
r
esear
c
h
v
ie
w
p
o
in
t,
it
i
s
ess
e
n
tial
to
u
n
d
er
s
tan
d
ce
r
tain
b
r
ief
d
etaili
n
g
o
f
it.
Ma
j
o
r
ity
o
f
t
h
e
ex
i
s
ti
n
g
m
o
d
els
v
is
u
alize
s
th
e
p
r
o
ce
s
s
o
f
co
s
t
esti
m
atio
n
as t
h
e
f
u
n
ctio
n
t
h
at
i
s
ca
p
ab
le
o
f
p
er
f
o
r
m
i
n
g
co
m
p
u
tatio
n
f
r
o
m
a
e
v
al
u
ated
co
s
t
d
r
iv
er
s
f
o
r
an
e
f
f
ec
ti
v
e
an
al
y
s
i
s
[
1
7
]
.
T
h
e
ex
is
ti
n
g
r
esea
r
ch
w
o
r
k
co
n
s
id
er
s
s
o
f
t
w
ar
e
r
eq
u
ir
e
m
en
t
as
t
h
e
p
r
o
m
i
n
en
t
co
s
t
d
r
iv
er
.
A
t
p
r
es
en
t,
t
h
er
e
ar
e
v
ar
io
u
s
tec
h
n
iq
u
es
o
f
co
s
t
esti
m
atio
n
tec
h
n
iq
u
es
t
h
at
ca
n
b
e
s
ee
n
f
r
o
m
Fi
g
u
r
e
1
.
B
asicall
y
,
t
h
e
r
e
ar
e
t
w
o
d
if
f
er
e
n
t
cla
s
s
i
f
ied
ap
p
r
o
ac
h
es
i.e
.
al
g
o
r
ith
m
ic
ap
p
r
o
ac
h
an
d
n
o
n
-
alg
o
r
ith
m
ic
ap
p
r
o
ac
h
.
A
l
g
o
r
ith
m
ic
tech
n
iq
u
e
s
ar
e
th
o
s
e
th
at
ad
o
p
t
m
at
h
e
m
atica
l a
p
p
r
o
ac
h
w
h
er
e
t
h
e
f
r
eq
u
en
t
l
y
u
s
ed
i
n
p
u
t
s
f
o
r
s
u
c
h
ap
p
r
o
ac
h
es
ar
e
f
u
n
c
tio
n
p
o
in
t,
li
n
e
o
f
co
d
es,
etc.
B
asicall
y
,
t
h
er
e
ar
e
th
r
ee
f
o
r
m
s
o
f
alg
o
r
it
h
m
ic
ap
p
r
o
ac
h
v
iz.
i)
P
u
tn
a
m
’
s
M
o
d
el,
ii)
C
o
n
s
tr
u
c
tiv
e
C
o
s
t
M
o
d
el,
an
d
iii)
Fu
n
ctio
n
P
o
in
t
An
al
y
s
i
s
.
P
u
tn
a
m
’
s
m
o
d
el
p
er
f
o
r
m
s
co
m
p
u
tatio
n
o
f
s
ize
o
f
s
o
f
t
w
ar
e
u
s
i
n
g
e
n
v
i
r
o
n
m
e
n
t
f
ac
to
r
,
lin
e
s
o
f
co
d
e,
d
is
p
atch
i
n
g
ti
m
e
o
f
s
o
f
t
w
ar
e,
a
n
d
b
u
ild
u
p
f
ac
to
r
o
f
m
a
n
p
o
w
er
.
U
n
f
o
r
tu
n
atel
y
t
h
is
m
o
d
el
d
o
esn
’
t
co
n
s
i
d
e
r
v
ar
io
u
s
p
o
ten
tial
f
ac
to
r
s
o
f
d
ev
e
lo
p
m
en
t
li
f
ec
y
c
le
[
1
8
]
.
T
h
e
s
ec
o
n
d
ap
p
r
o
ac
h
i
.
e.
co
n
s
tr
u
c
tiv
e
co
s
t
m
o
d
el
i
s
f
r
eq
u
en
tl
y
u
s
ed
b
y
v
ar
io
u
s
r
esear
ch
er
s
an
d
i
s
a
g
a
in
cla
s
s
i
f
ied
i
n
to
f
u
r
t
h
er
t
h
r
ee
f
o
r
m
s
i.e
.
i)
f
u
n
d
a
m
e
n
tal
m
o
d
el,
ii)
in
ter
m
ed
iate
m
o
d
el,
a
n
d
iii)
d
etailed
m
o
d
e
l.
T
h
e
p
r
im
e
r
ea
s
o
n
f
o
r
its
h
i
g
h
er
ad
o
p
tio
n
is
its
s
i
m
p
le
te
ch
n
iq
u
e
to
est
i
m
a
te
co
s
t
an
d
its
w
id
e
ad
o
p
tio
n
w
it
h
i
n
t
h
e
in
d
u
s
tr
y
[
1
9
]
.
B
u
t
it
also
s
u
f
f
er
s
f
r
o
m
v
ar
io
u
s
p
r
o
b
lem
s
e.
g
.
n
o
n
-
ap
p
licab
ilit
y
o
n
s
m
aller
p
r
o
jects,
est
i
m
a
tio
n
f
ai
lu
r
es
.
T
h
e
th
ir
d
al
g
o
r
it
h
m
ic
ap
p
r
o
ac
h
is
F
u
n
ct
io
n
P
o
in
t
An
al
y
s
i
s
t
h
at
is
u
s
ed
to
m
ea
s
u
r
e
th
e
n
u
m
b
er
o
f
f
u
n
ct
io
n
al
p
o
in
ts
av
a
ilab
le
i
n
t
h
e
s
o
f
t
w
ar
e
p
r
o
j
ec
ts
.
T
h
e
p
r
i
m
e
f
ac
to
r
s
i
n
F
u
n
ct
io
n
P
o
in
t
An
al
y
s
i
s
ar
e
in
ter
f
ac
e
f
ile
(
ex
ter
n
al)
,
lo
g
ical
f
ile
(
i
n
ter
n
al)
,
a
n
d
v
ar
ied
en
q
u
ir
ies.
T
h
e
in
ter
esti
n
g
p
o
in
t
o
f
F
u
n
ctio
n
al
P
o
in
t
An
al
y
s
i
s
is
th
at
it
is
in
d
ep
en
d
en
t
f
r
o
m
to
o
ls
,
lan
g
u
ag
e,
o
r
an
y
s
p
ec
if
ic
i
m
p
le
m
e
n
tatio
n
s
tr
ate
g
y
.
Ho
w
ev
er
,
th
e
p
it
f
all
o
f
F
u
n
ctio
n
al
P
o
in
t
An
al
y
s
is
i
s
its
m
an
u
al
o
p
er
atio
n
al
tech
n
iq
u
e
[
2
0
]
.
On
t
h
e
o
t
h
er
h
an
d
,
n
o
n
-
al
g
o
r
ith
m
ic
ap
p
r
o
ac
h
es
ar
e
b
asica
ll
y
clas
s
i
f
ied
in
t
o
6
t
y
p
es
(
b
ased
o
n
f
r
eq
u
en
t
r
esear
ch
tech
n
iq
u
es)
v
iz.
i)
to
p
-
d
o
w
n
b
ased
,
ii)
E
x
p
er
t
J
u
d
g
m
en
t
b
ased
,
iii)
B
o
tto
m
-
b
ased
,
iv
)
An
alo
g
y
B
ased
,
v
)
A
r
t
if
ic
ial
Neu
r
al
Net
w
o
r
k
(
A
NN)
,
an
d
v
i)
F
u
zz
y
L
o
g
ic.
I
n
to
p
-
d
o
w
n
b
ased
ap
p
r
o
ac
h
,
th
e
g
lo
b
al
ch
ar
ec
ter
is
tics
ar
e
u
s
ed
f
o
r
co
m
p
u
ti
n
g
to
tal
co
s
t
an
d
e
m
p
h
a
s
izes
m
o
r
e
o
n
in
te
g
r
atio
n
.
T
h
e
lim
i
tatio
n
o
f
th
is
ap
p
r
o
ac
h
is
it
s
n
o
n
-
co
n
s
id
er
atio
n
o
f
lo
w
-
le
v
el
p
r
o
b
le
m
s
lead
in
g
to
co
s
t
in
cr
e
m
e
n
t
[
2
1
]
.
I
n
E
x
p
er
t
J
u
d
g
m
e
n
t
b
ased
ap
p
r
o
ac
h
,
an
ex
p
er
t’
s
o
p
i
n
io
n
i
s
co
n
s
id
er
e
d
th
at
is
g
o
o
d
f
o
r
ca
s
es
w
it
h
r
estricte
d
ac
ce
s
s
to
d
ata.
I
t
ca
n
b
e
u
s
ed
f
o
r
p
r
ed
ictin
g
th
e
i
n
f
l
u
en
ce
o
n
co
s
t
d
u
e
t
o
ch
an
g
e
o
f
a
n
y
u
n
d
er
l
y
i
n
g
te
ch
n
o
lo
g
ies
[
2
2
]
.
I
n
b
o
tto
m
-
u
p
b
ased
ap
p
r
o
ac
h
,
th
e
o
v
er
all
co
s
t
is
esti
m
ated
o
n
l
y
a
f
ter
d
er
iv
i
n
g
co
s
t
o
f
ea
ch
c
o
m
p
o
n
en
t
s
in
v
o
l
v
ed
in
s
o
f
t
w
ar
e
d
esi
g
n
.
T
h
e
s
tab
il
it
y
o
f
t
h
e
tec
h
n
iq
u
e
is
q
u
ite
h
ig
h
b
u
t
it
i
g
n
o
r
es
in
te
g
r
atio
n
,
d
o
cu
m
en
tatio
n
,
etc
[
2
1
]
.
T
h
e
an
alo
g
y
-
b
ased
ap
p
r
o
ac
h
is
u
s
ed
f
o
r
d
eter
m
in
i
n
g
t
h
e
p
ar
a
m
eter
s
o
f
ex
is
ti
n
g
s
o
f
t
w
ar
e
p
r
o
j
ec
t
as
w
ell
as
it
also
ex
p
lo
r
es
th
e
eq
u
iv
alen
t
o
ld
p
r
o
j
e
ct
w
h
o
s
e
p
ar
a
m
eter
s
m
atc
h
e
s
w
i
th
t
h
e
cu
r
r
en
t
p
r
o
j
ec
t.
T
h
e
s
ig
n
i
f
ica
n
t
ad
v
a
n
ta
g
e
o
f
u
s
i
n
g
an
alo
g
y
-
b
ased
ap
p
r
o
ac
h
is
s
u
p
p
o
r
tab
ilit
y
o
f
es
ti
m
ato
r
ex
p
e
r
ien
ce
f
o
r
ass
i
s
ti
n
g
in
en
h
a
n
ce
d
co
s
t
esti
m
atio
n
.
Un
f
o
r
tu
n
atel
y
,
t
h
is
ap
p
r
o
ac
h
is
n
o
t
ap
p
licab
le
f
o
r
all
th
e
s
o
f
t
w
ar
e
p
r
o
j
ec
ts
[
2
3
]
.
B
o
th
ar
tif
ic
ial
n
eu
r
al
n
e
t
w
o
r
k
s
as
w
ell
as
f
u
zz
y
lo
g
ic
ar
e
s
o
f
t
co
m
p
u
ti
n
g
tec
h
n
iq
u
es
w
h
er
e
th
e
f
o
r
m
er
u
s
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
I
n
s
ig
h
ts
o
n
R
esea
r
ch
Tech
n
i
q
u
es to
w
a
r
d
s
C
o
s
t E
s
tima
tio
n
in
S
o
ftw
a
r
e
Desig
n
(
P
r
a
ve
en
N
a
ik)
2885
h
is
to
r
ical
d
ata
a
n
d
latter
u
s
es
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
.
A
lt
h
o
u
g
h
A
N
N
o
f
f
er
s
co
n
s
is
ten
c
y
in
co
s
t
e
s
ti
m
atio
n
p
r
o
ce
s
s
b
u
ts
it
h
a
s
m
a
x
i
m
u
m
d
ep
en
d
en
cies
o
f
tr
ain
i
n
g
d
ata
to
en
s
u
r
e
ac
cu
r
ac
y
[
2
4
]
.
Sim
ilar
l
y
,
ad
o
p
tio
n
o
f
f
u
zz
y
lo
g
ic
b
ased
ap
p
r
o
ac
h
h
as
th
e
ad
v
an
tag
e
o
f
ze
r
o
d
ep
en
d
en
cie
s
o
v
er
tr
ain
in
g
as
well
as
it
also
o
f
f
er
co
m
p
r
e
h
en
s
iv
e
tr
u
s
t
w
o
r
t
h
y
co
s
t
esti
m
atio
n
.
Ho
w
ev
er
,
e
v
en
th
e
f
u
zz
y
-
lo
g
ic
b
ased
ap
p
r
o
ac
h
also
s
u
f
f
er
s
f
r
o
m
p
itf
alls
i.e
.
it
o
f
f
er
s
co
m
p
u
t
atio
n
al
co
m
p
lex
i
ties
in
m
an
y
ca
s
es
a
n
d
m
o
r
eo
v
er
t
h
e
a
cc
u
r
ac
y
co
m
p
letel
y
d
ep
en
d
s
o
n
th
e
t
y
p
e
o
f
t
h
e
R
u
l
ese
t b
ein
g
d
esig
n
ed
f
o
r
th
i
s
p
u
r
p
o
s
e
o
f
co
s
t e
s
ti
m
at
io
n
[
2
5
]
.
Hen
ce
,
it
ca
n
b
e
s
aid
th
at
ir
r
esp
ec
tiv
e
o
f
th
e
p
r
esen
ce
o
f
v
ar
io
u
s
co
n
v
e
n
tio
n
al
s
o
f
t
w
ar
e
co
s
t
esti
m
atio
n
tec
h
n
iq
u
e
s
,
t
h
er
e
is
less
e
f
f
ec
ti
v
e
co
s
t
e
s
ti
m
atio
n
tech
n
iq
u
e
f
o
r
a
lar
g
e
s
ca
le
a
n
d
d
y
n
a
m
ic
s
o
f
t
w
ar
e
d
ev
elo
p
m
en
t p
r
o
ce
s
s
.
C
o
s
t
-
E
s
t
i
m
a
t
i
o
n
M
o
d
e
l
s
N
o
n
-
A
l
g
o
r
i
t
h
m
i
c
A
p
p
r
o
a
c
h
A
n
a
l
o
g
y
-
b
a
s
e
d
E
x
p
e
r
t
J
u
d
g
e
m
e
n
t
T
o
p
-
D
o
w
n
B
a
s
e
d
B
o
t
t
o
m
-
U
p
B
a
s
e
d
A
N
N
F
u
z
z
y
L
o
g
i
c
A
l
g
o
r
i
t
h
m
i
c
A
p
p
r
o
a
c
h
C
o
n
s
t
r
u
c
t
i
v
e
C
o
s
t
M
o
d
e
l
P
u
t
n
a
m
’
s
M
o
d
e
l
F
u
n
c
t
i
o
n
P
o
i
n
t
A
n
a
l
y
s
i
s
Fig
u
r
e
1
.
T
ax
o
n
o
m
ie
s
o
f
ex
is
t
in
g
s
o
f
t
w
ar
e
co
s
t
-
e
s
ti
m
atio
n
a
p
p
r
o
ac
h
es
1
.
2
.
T
he
P
ro
ble
m
T
h
is
s
ec
tio
n
h
ig
h
li
g
h
ts
t
h
e
s
ta
tis
tics
o
f
v
ar
ied
n
u
m
b
er
o
f
r
es
ea
r
ch
p
ap
er
s
p
u
b
lis
h
ed
in
I
E
E
E
XP
lo
r
e
d
u
r
in
g
d
u
r
atio
n
f
r
o
m
2
0
1
0
to
till
d
ate
p
er
tain
in
g
to
t
h
e
p
r
o
b
lem
s
as
s
o
ciate
d
w
it
h
s
o
f
t
war
e
co
s
t
esti
m
atio
n
tech
n
iq
u
es.
W
e
r
e
v
ie
w
ed
t
h
e
m
o
s
t
co
m
m
o
n
l
y
ad
d
r
ess
e
s
p
r
o
b
lem
s
in
co
s
t
e
s
ti
m
atio
n
tec
h
n
iq
u
es
an
d
g
r
ap
h
icall
y
h
ig
h
li
g
h
ted
th
e
c
u
r
r
en
t
p
r
o
g
r
ess
i
n
it.
T
h
e
n
u
m
b
er
o
f
r
ec
en
t
j
o
u
r
n
als
to
war
d
s
s
o
f
t
w
ar
e
co
s
t
esti
m
atio
n
is
f
o
u
n
d
to
b
e
les
s
th
a
n
5
0
(
Fi
g
u
r
e
2
)
,
w
h
ich
is
v
er
y
les
s
i
n
n
u
m
b
er
co
m
p
ar
e
d
to
o
th
er
r
esear
c
h
p
r
o
b
lem
s
i
n
s
o
f
t
w
ar
e
m
o
d
eli
n
g
o
r
en
g
in
ee
r
i
n
g
.
T
h
e
av
ailab
ilit
y
o
f
r
elev
a
n
t
p
ap
er
s
is
q
u
ite
less
.
Si
m
i
lar
p
r
o
b
lem
d
o
e
x
is
t
in
g
in
r
esear
c
h
to
w
ar
d
s
e
f
f
o
r
t
es
ti
m
atio
n
wh
er
e
o
n
l
y
less
t
h
an
2
5
j
o
u
r
n
al
s
ar
e
f
o
u
n
d
til
l
d
ate
(
Fig
u
r
e
3
)
.
T
h
e
tr
en
d
is
m
u
ch
r
ed
u
ce
d
f
o
r
f
au
lt
p
r
ed
ictio
n
in
co
s
t
esti
m
atio
n
(
Fi
g
u
r
e
4
)
a
s
th
er
e
ar
e
o
n
l
y
9
j
o
u
r
n
als ass
o
ciate
d
w
it
h
th
is
p
r
o
b
le
m.
Fig
u
r
e
2
R
esear
ch
tr
e
n
d
s
to
w
a
r
d
s
s
o
f
t
w
ar
e
co
s
t e
s
ti
m
atio
n
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
.
5
,
Octo
b
er
2
0
1
7
:
2
8
8
3
–
2
8
9
4
2886
Fig
u
r
e
3
R
esear
ch
tr
e
n
d
s
to
w
a
r
d
s
ef
f
o
r
t e
s
ti
m
atio
n
Fig
u
r
e
4
R
esear
ch
tr
e
n
d
s
to
w
a
r
d
s
f
au
lt p
r
ed
ictio
n
A
p
ar
t
f
r
o
m
th
is
,
w
e
al
s
o
in
v
e
s
tig
a
ted
ab
o
u
t
th
e
tr
e
n
d
s
to
war
d
s
o
th
er
u
s
a
g
e
o
f
o
t
h
er
ap
p
r
o
ac
h
es
o
f
co
s
t
esti
m
a
tio
n
e.
g
.
ex
p
er
t
j
u
d
g
m
e
n
t,
an
a
lo
g
y
-
b
ased
,
P
u
t
n
am
’
s
m
o
d
el,
F
u
n
ct
io
n
al
P
o
in
t
An
al
y
s
i
s
,
C
O
C
OM
O
,
etc.
A
clo
s
er
lo
o
k
i
n
to
t
h
e
r
esear
ch
tr
e
n
d
i
n
Fig
u
r
e
5
s
h
o
w
s
t
h
at
Fu
n
ctio
n
al
P
o
in
t
An
al
y
s
i
s
as
w
ell
as
C
OC
OM
O
m
o
d
el
i
s
t
h
e
m
o
s
t
ad
o
p
ted
tech
n
iq
u
es
b
y
v
ar
i
o
u
s
r
esear
ch
er
s
till
d
ate.
T
h
e
p
r
o
p
o
r
tio
n
o
f
th
e
r
esear
ch
p
ap
er
s
u
s
i
n
g
Fu
n
cti
o
n
al
P
o
in
t
An
al
y
s
i
s
is
f
o
u
n
d
to
b
e
co
m
p
ar
ativ
el
y
h
i
g
h
er
th
an
co
n
v
e
n
tio
n
a
l
C
OC
OM
O
m
o
d
el.
Ho
w
e
v
er
,
t
h
e
m
atter
o
f
i
llu
s
io
n
is
t
h
at
u
s
ag
e
o
f
F
u
n
ctio
n
al
P
o
in
t
An
al
y
s
is
w
as
n
o
t a
d
o
p
ted
s
p
ec
if
icall
y
f
o
r
co
s
t
e
s
ti
m
atio
n
p
r
o
b
le
m
s
in
s
o
f
t
w
ar
e
an
d
h
en
ce
t
h
e
r
ele
v
an
c
y
r
ate
o
f
u
s
i
n
g
F
u
n
ct
io
n
al
p
o
i
n
t
an
al
y
s
is
i
s
q
u
ite
lo
w
.
Si
m
ilar
l
y
,
w
e
f
i
n
d
th
at
alt
h
o
u
g
h
m
a
n
y
r
esear
ch
p
ap
er
s
d
o
esn
’
t
h
i
g
h
l
ig
h
ts
C
OC
O
MO
in
th
e
p
r
eli
m
in
ar
y
s
ec
tio
n
o
f
t
h
e
ir
p
ap
er
s
,
b
u
t
w
e
f
i
n
d
th
at
m
a
j
o
r
ity
(
s
a
y
9
5
%)
o
f
th
e
r
e
s
ea
r
ch
er
s
h
av
e
ad
o
p
ted
C
OC
OM
O
m
o
d
el
in
t
h
e
i
m
p
le
m
en
tatio
n
o
f
t
h
eir
ap
p
r
o
ac
h
es.
Hen
ce
,
th
e
p
r
esen
t
r
esear
ch
tr
en
d
ca
n
b
e
s
aid
to
u
s
e
C
OC
O
MO
m
o
d
el
w
it
h
h
i
g
h
er
r
elev
a
n
c
y
f
ac
to
r
co
m
p
ar
ed
to
u
s
ag
e
an
d
ad
o
p
tio
n
o
f
o
th
er
co
n
v
e
n
tio
n
a
l
tech
n
iq
u
es o
f
co
s
t e
s
ti
m
atio
n
.
Fig
u
r
e
5
R
esear
ch
tr
e
n
d
s
to
w
a
r
d
s
o
th
er
p
r
o
b
lem
s
T
h
e
n
ex
t
s
ec
tio
n
elab
o
r
ates
ab
o
u
t
s
o
m
e
o
f
th
e
f
r
eq
u
e
n
tl
y
ad
d
r
ess
ed
p
r
o
b
lem
s
an
d
t
h
e
in
tr
o
d
u
ce
d
tech
n
iq
u
es
f
r
o
m
r
ec
en
t a
n
d
r
el
ev
an
t l
iter
atu
r
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
I
n
s
ig
h
ts
o
n
R
esea
r
ch
Tech
n
i
q
u
es to
w
a
r
d
s
C
o
s
t E
s
tima
tio
n
in
S
o
ftw
a
r
e
Desig
n
(
P
r
a
ve
en
N
a
ik)
2887
2.
E
XI
ST
I
N
G
RE
SE
AR
CH
T
E
CH
NI
Q
U
E
S
T
h
is
s
ec
tio
n
d
is
cu
s
s
e
s
ab
o
u
t
th
e
ex
i
s
ti
n
g
r
esear
ch
tec
h
n
iq
u
e
s
to
w
ar
d
s
co
s
t
esti
m
atio
n
p
r
o
ce
s
s
in
t
h
e
in
d
u
s
tr
y
.
As
t
h
er
e
is
s
o
m
u
c
h
v
ar
ied
p
r
o
ce
s
s
o
f
i
n
v
esti
g
a
tin
g
t
h
e
co
s
t
f
ac
to
r
b
y
v
ar
io
u
s
r
esear
c
h
er
s
,
t
h
e
d
is
cu
s
s
io
n
is
ca
r
r
ied
o
u
t
f
o
r
th
e
f
r
eq
u
e
n
tl
y
u
s
ed
co
m
p
u
t
atio
n
tec
h
n
iq
u
es
o
f
co
s
t
f
ac
t
o
r
in
th
e
s
o
f
t
w
ar
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
.
W
e
d
is
cu
s
s
o
n
l
y
t
h
e
r
ec
en
t
r
esear
c
h
m
an
u
s
cr
ip
t
p
u
b
l
is
h
ed
in
t
h
e
d
u
r
atio
n
o
f
2
0
1
0
-
til
l
d
ate
in
th
i
s
r
eg
ar
d
s
.
2
.
1
.
G
ener
a
l C
o
s
t
E
s
t
i
m
a
t
io
n T
ec
hn
iqu
e
s
Fro
m
in
d
u
s
tr
y
v
ie
w
p
o
in
t,
ev
er
y
s
ec
to
r
h
as
its
o
w
n
k
i
n
d
o
f
cr
iter
io
n
o
f
m
ea
s
u
r
i
n
g
t
h
e
to
tal
n
u
m
b
er
o
f
r
eso
u
r
ce
s
i
n
v
o
lv
ed
i
n
t
h
e
p
r
o
ce
s
s
o
f
s
o
f
t
w
ar
e
d
e
v
elo
p
m
e
n
t
.
I
n
t
h
is
r
eg
ar
d
s
,
t
h
e
ad
o
p
tio
n
o
f
F
u
n
ctio
n
a
l
P
o
in
t
An
al
y
s
i
s
ca
n
b
e
co
n
s
id
er
ed
as
h
i
g
h
l
y
s
ta
n
d
ar
d
an
d
p
r
ac
tical
o
n
e
as
i
ts
ad
o
p
tio
n
w
a
s
f
o
u
n
d
in
m
an
y
e
x
is
tin
g
co
r
p
o
r
ates
an
d
f
ir
m
s
[
2
6
]
.
B
asicall
y
,
it
i
s
o
n
e
o
f
t
h
e
m
ec
h
an
i
s
m
s
to
p
er
f
o
r
m
q
u
a
n
ti
f
ic
atio
n
o
f
th
e
ac
ti
v
e
f
u
n
ctio
n
s
th
a
t a
r
e
u
s
ed
f
o
r
d
es
ig
n
in
g
th
e
s
o
f
t
w
ar
e
a
n
d
i
t r
eta
in
s
h
ig
h
er
s
ig
n
i
f
ica
n
ce
.
B
u
t
alt
h
o
u
g
h
t
h
e
u
s
a
g
e
o
f
Fu
n
ctio
n
al
P
o
in
t
An
al
y
s
is
s
tar
ted
b
ac
k
i
n
1
9
7
9
in
I
B
M,
it
s
u
f
f
er
s
ce
r
tai
n
p
it
f
alls
to
o
t
h
at
ar
e
in
v
esti
g
ated
b
y
th
e
r
esear
c
h
co
m
m
u
n
it
y
.
So
m
e
o
f
t
h
e
s
i
g
n
i
f
ican
t
p
itf
a
lls
ar
e
i)
in
co
n
s
is
ten
t
o
u
tco
m
e
s
,
ii)
m
i
s
m
a
tch
ed
p
o
in
t
s
d
u
r
in
g
an
al
y
s
is
,
etc.
A
d
is
cu
s
s
io
n
ab
o
u
t te
ch
n
iq
u
e
s
f
o
r
en
h
a
n
cin
g
F
u
n
ctio
n
al
P
o
in
t
An
al
y
s
is
w
as p
r
esen
ted
b
y
J
u
n
io
r
et
al.
[
2
7
]
.
I
t
w
as
s
e
en
th
a
t
th
er
e
ar
e
v
ar
io
u
s
f
o
r
m
s
o
f
en
h
an
ce
m
e
n
t
b
ein
g
c
ar
r
ied
o
u
t
to
w
ar
d
s
i
m
p
r
o
v
i
n
g
t
h
e
ac
c
u
r
ac
y
o
f
F
u
n
ctio
n
al
P
o
in
t
A
n
a
l
y
s
is
e.
g
.
F
u
zz
y
lo
g
ic,
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
,
Stati
s
tical
R
eg
r
es
s
io
n
,
Gen
et
ic
A
l
g
o
r
ith
m
,
i
n
ter
p
o
latio
n
tec
h
n
iq
u
e,
et
c.
Ho
w
e
v
er
,
ac
co
r
d
in
g
to
th
e
an
al
y
s
is
ca
r
r
ied
o
u
t
b
y
a
u
t
h
o
r
m
aj
o
r
ity
o
f
t
h
e
ex
i
s
tin
g
tec
h
n
iq
u
es
d
o
s
till
p
o
s
s
ess
ce
r
tain
p
it
f
all
s
e.
g
.
n
o
cl
ea
r
cu
t
s
o
lu
tio
n
to
co
u
n
ter
m
ea
s
u
r
e
ex
is
t
in
g
p
r
o
b
le
m
s
,
h
i
g
h
er
co
m
p
le
x
it
y
,
d
ep
en
d
en
cies
o
n
cu
r
r
en
t
v
er
s
io
n
,
etc.
A
n
o
t
h
er
s
tan
d
ar
d
in
v
e
s
ti
g
atio
n
to
w
ar
d
s
s
o
f
t
w
ar
e
co
s
t
esti
m
atio
n
was
ca
r
r
ied
o
u
t
b
y
Mitta
s
an
d
A
n
g
eli
s
[
2
8
]
.
A
s
tatis
t
ical
m
o
d
eli
n
g
ap
p
r
o
ac
h
h
as
b
ee
n
u
s
ed
f
o
r
i
n
v
e
s
ti
g
a
tin
g
d
if
f
er
en
t
f
o
r
m
s
o
f
ex
is
ti
n
g
m
o
d
els
o
f
co
s
t
esti
m
atio
n
.
Fu
r
t
h
er
,
a
cl
u
s
ter
i
n
g
m
ec
h
a
n
is
m
w
as
ap
p
lied
f
o
r
u
n
iq
u
e
g
r
o
u
p
s
.
T
h
e
a
u
t
h
o
r
s
h
av
e
p
er
f
o
r
m
ed
t
h
e
ex
p
er
i
m
e
n
ts
u
s
i
n
g
d
ataset
s
f
o
r
m
ea
s
u
r
i
n
g
ac
cu
r
ac
y
f
o
llo
w
e
d
b
y
a
r
a
n
k
in
g
p
r
o
ce
s
s
to
u
n
d
er
s
tan
d
t
h
e
m
o
s
t
elite
o
u
tco
m
e.
T
h
e
a
u
t
h
o
r
s
h
a
v
e
ca
r
r
ied
o
u
t
Sco
tt
-
K
n
o
tt
te
s
t
o
v
er
1
1
s
ta
n
d
ar
d
m
o
d
els
to
f
i
n
d
b
etter
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
T
h
e
co
s
t
f
ac
to
r
o
f
t
h
e
s
o
f
t
w
ar
e
p
r
o
j
ec
ts
also
d
ep
e
n
d
s
o
n
t
h
e
f
u
n
ctio
n
al
s
ize
o
f
t
h
e
co
d
e.
I
t
b
ec
o
m
es
q
u
ite
a
s
ig
n
i
f
ica
n
t
tas
k
w
h
e
n
it
co
m
e
s
to
e
m
b
ed
d
ed
s
y
s
te
m
d
esig
n
as
v
ar
io
u
s
u
n
its
o
f
e
m
b
ed
d
ed
s
y
s
te
m
e.
g
.
m
e
m
o
r
y
i
s
s
i
g
n
i
f
ica
n
tl
y
a
f
f
ec
ted
b
y
t
h
e
co
n
tr
o
l
u
n
i
t.
St
u
d
y
i
n
s
u
ch
d
ir
ec
tio
n
w
as
ca
r
r
i
ed
o
u
t
b
y
L
i
n
d
an
d
Held
al
et
al.
[
2
9
]
b
y
p
r
esen
t
in
g
a
s
ta
n
d
ar
d
m
ec
h
an
i
s
m
f
o
r
es
ti
m
ati
n
g
e
m
b
ed
d
ed
co
d
e
s
ize
ca
lled
as
C
O
SMI
C
ap
p
r
o
ac
h
.
I
n
o
r
d
er
to
ex
tr
ac
t
th
e
p
r
ec
is
e
o
u
tco
m
e
s
o
f
th
e
s
tu
d
y
,
b
o
th
f
u
n
ct
io
n
al
s
ize
s
as
w
ell
as
s
ize
o
f
s
o
f
t
w
ar
e
co
d
e
w
er
e
s
u
b
j
ec
ted
to
co
r
r
elatio
n
al
an
al
y
s
i
s
to
f
i
n
d
t
h
at
t
h
e
y
ar
e
h
ig
h
er
co
r
r
elate
d
.
Statis
tical
an
al
y
s
is
w
as
ap
p
lied
f
o
r
th
i
s
p
u
r
p
o
s
e.
T
h
e
s
tu
d
y
o
u
tco
m
e
s
tates
t
h
at
t
h
er
e
ar
e
ce
r
tai
n
p
r
o
m
i
n
en
t
f
ac
to
r
s
th
a
t
p
o
ten
tiall
y
af
f
ec
t
t
h
e
e
s
ti
m
ati
o
n
p
r
o
ce
s
s
e.
g
.
co
n
s
is
te
n
c
y
o
f
t
h
e
co
n
te
n
ts
,
clea
r
v
i
s
u
al
iza
tio
n
o
f
f
u
n
ct
io
n
al
d
o
m
ai
n
,
s
u
p
er
io
r
r
eq
u
ir
e
m
e
n
t
q
u
alit
y
,
an
d
p
r
ec
is
e
h
i
s
to
r
ical
d
ata.
No
t
o
n
l
y
in
e
m
b
ed
d
ed
s
y
s
te
m
an
d
d
esi
g
n
,
s
i
m
ilar
p
r
o
b
le
m
s
d
o
e
x
is
t
s
in
f
o
u
r
t
h
g
e
n
er
atio
n
la
n
g
u
a
g
e.
T
h
e
d
eg
r
ee
o
f
co
m
p
le
x
it
y
t
o
w
ar
d
s
f
o
u
r
t
h
g
en
er
atio
n
la
n
g
u
a
g
e
i
s
q
u
ite
h
ig
h
er
an
d
t
h
i
s
p
r
o
b
le
m
i
s
i
n
v
e
s
tig
a
ted
b
y
Z
ia
et
al.
[
3
0
]
.
T
h
e
tech
n
iq
u
e
h
a
s
u
s
ed
e
m
p
ir
ical
d
ata
o
n
t
h
e
b
asi
s
o
f
th
e
s
ta
n
d
ar
d
s
p
ec
if
ica
tio
n
o
f
C
OC
OM
O
I
I
m
o
d
el.
T
h
e
s
t
u
d
y
o
u
tco
m
e
h
a
s
b
ee
n
test
ed
u
s
in
g
m
u
ltip
le
to
o
ls
e.
g
.
Vis
u
al
B
asic,
VB
.
Net,
VC
#
in
o
r
d
er
to
co
m
p
u
te
b
o
th
a
ctu
al
a
n
d
f
o
r
ec
asted
e
f
f
o
r
t
to
f
i
n
d
h
ig
h
er
ac
c
u
r
ac
y
.
T
h
e
s
ig
n
i
f
ica
n
t
s
tu
d
ie
s
to
w
ar
d
s
g
e
n
er
al
co
s
t
e
s
ti
m
atio
n
is
q
u
ite
le
s
s
in
ter
m
s
o
f
n
u
m
b
er
o
f
j
o
u
r
n
al
s
.
A
lt
h
o
u
g
h
,
f
e
w
s
i
g
n
if
ican
t
co
n
f
er
en
ce
m
a
n
u
s
cr
ip
ts
h
av
e
eq
u
all
y
c
o
n
tr
ib
u
ted
to
s
h
ar
e
ce
r
tain
n
o
v
el
id
ea
s
to
w
ar
d
s
en
h
a
n
ci
n
g
co
s
t
esti
m
at
io
n
tech
n
iq
u
e
s
in
s
o
f
t
w
ar
e
d
esig
n
.
M
o
s
t
r
ec
en
tl
y
,
Hih
n
et
al.
[
3
1
]
h
av
e
p
r
esen
ted
a
tech
n
iq
u
e
t
h
at
ca
n
es
ti
m
ate
co
s
t
f
o
r
Natio
n
al
A
er
o
n
a
u
tic
s
an
d
Sp
ac
e
A
d
m
in
i
s
tr
ati
on
(
NA
S
A
)
b
ased
r
ep
o
s
ito
r
y
d
ata
.
T
h
e
tech
n
iq
u
e
a
ls
o
e
m
p
h
a
s
iz
es
o
n
p
o
te
n
tial
s
o
f
t
w
ar
e
m
etr
i
c
e.
g
.
lo
g
ical
li
n
e
s
o
f
co
d
e
w
it
h
v
ar
ied
s
y
s
te
m
p
ar
a
m
eter
s
.
U
s
i
n
g
m
u
lt
ip
le
m
i
s
s
io
n
t
y
p
es
o
f
s
p
ac
e
o
b
jects
(
ea
r
th
o
r
b
iter
,
o
b
s
er
v
ato
r
y
,
d
ee
p
s
p
ac
e,
etc
)
,
s
tatis
tical
m
ea
s
u
r
e
s
w
er
e
ap
p
lied
o
n
th
e
b
asis
o
f
s
tan
d
ar
d
C
OC
OM
O
-
I
I
s
p
ec
if
icatio
n
.
T
h
e
tech
n
iq
u
e
u
s
es
a
n
alo
g
y
-
b
a
s
ed
ap
p
r
o
ac
h
w
ith
v
ar
io
u
s
i
n
p
u
t
s
o
f
lev
el
s
o
f
in
h
er
i
tan
ce
,
s
ize
o
f
s
o
f
t
w
ar
e,
t
y
p
es
o
f
ele
m
e
n
ts
,
t
y
p
e
s
o
f
m
is
s
io
n
,
etc
an
d
th
e
n
s
p
ec
tr
al
clu
s
ter
in
g
is
ap
p
li
ed
f
o
r
co
m
p
u
ti
n
g
ef
f
o
r
t.
Si
m
i
lar
f
o
r
m
o
f
ce
le
s
tial
ca
s
e
s
t
u
d
y
w
as
a
ls
o
s
ee
n
in
t
h
e
wo
r
k
ca
r
r
ied
o
u
t
b
y
C
a
n
n
o
n
an
d
B
u
r
let
[
3
2
]
.
T
h
e
s
tu
d
y
m
ai
n
l
y
d
e
v
elo
p
s
a
p
r
o
t
o
ty
p
e
o
f
f
li
g
h
t
s
o
f
t
w
ar
e
u
s
i
n
g
C
lan
g
u
a
g
e
an
d
o
b
s
er
v
atio
n
w
a
s
m
ad
e
f
o
r
ti
m
e
v
ar
iab
ilit
y
,
co
m
p
o
s
it
io
n
,
a
n
d
d
en
s
it
y
o
v
er
t
h
e
m
o
o
n
s
u
r
f
ac
e.
T
h
e
au
th
o
r
co
m
p
u
ted
co
s
t o
f
t
h
is
s
o
f
t
w
ar
e
m
o
d
el
u
s
i
n
g
ex
tr
ap
o
latio
n
ap
p
r
o
ac
h
,
C
OC
OM
O
u
s
i
n
g
a
g
ile
m
e
th
o
d
o
lo
g
ies
u
s
in
g
s
o
u
r
ce
li
n
e
o
f
co
d
e.
T
h
ese
ap
p
r
o
ac
h
es
h
av
e
u
s
ed
t
h
e
s
t
an
d
ar
d
d
ata
f
r
o
m
t
h
e
s
p
ac
e
ce
n
ter
s
a
n
d
ca
n
b
e
co
n
s
id
er
ed
as
b
est
in
itiati
v
e
to
w
ar
d
s
co
s
t
co
m
p
u
ti
n
g
m
o
d
els
u
s
in
g
s
p
ac
e
r
elate
d
d
ata.
An
o
th
er
u
n
iq
u
e
o
p
ti
m
izat
io
n
-
b
ased
tech
n
iq
u
e
o
f
u
s
i
n
g
b
io
-
i
n
s
p
ir
ed
ap
p
r
o
ac
h
w
as seen
i
n
t
h
e
w
o
r
k
o
f
Gar
g
an
d
Gu
p
ta
[
3
3
]
.
T
h
e
au
th
o
r
s
ad
d
r
ess
ed
th
e
p
r
o
b
le
m
o
f
ac
cu
r
ac
y
p
er
tain
in
g
to
u
s
a
g
e
o
f
ag
i
le
m
et
h
o
d
o
lo
g
ies.
T
h
e
p
r
o
b
le
m
s
o
f
attr
ib
u
te
d
i
m
en
s
io
n
s
h
a
v
e
b
ee
n
m
i
n
i
m
ized
u
s
i
n
g
P
r
in
cip
le
C
o
m
p
o
n
en
t
An
al
y
s
i
s
f
o
llo
w
ed
b
y
id
e
n
ti
f
icatio
n
o
f
p
r
o
m
in
e
n
t
f
ac
to
r
w
it
h
h
i
g
h
e
r
co
r
r
el
atio
n
o
n
s
o
f
t
w
ar
e
d
esi
g
n
co
s
t.
T
h
e
s
t
u
d
y
o
u
tco
m
e
is
co
m
p
le
te
l
y
i
n
d
ep
en
d
en
t
o
f
h
i
s
to
r
ical
d
ata
o
r
an
y
f
o
r
m
o
f
o
t
h
er
in
f
o
r
m
at
io
n
.
T
h
e
s
tu
d
y
h
a
s
ev
al
u
ated
co
ef
f
ici
en
t
v
a
lu
e
o
f
v
ar
io
u
s
tes
t
co
m
p
o
n
en
ts
e.
g
.
s
ize
o
f
tea
m
,
co
m
p
lex
i
t
y
i
n
v
o
l
v
ed
in
p
r
o
j
ec
ts
,
ty
p
e
o
f
ap
p
licatio
n
,
to
tal
f
u
n
ctio
n
al
p
o
in
t
s
,
p
latf
o
r
m
u
s
ed
in
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
.
5
,
Octo
b
er
2
0
1
7
:
2
8
8
3
–
2
8
9
4
2888
de
v
elo
p
m
en
t,
etc.
T
h
e
p
r
ac
tice
o
f
ap
p
l
y
in
g
o
p
ti
m
izati
o
n
tech
n
iq
u
e
w
as
also
s
ee
n
i
n
t
h
e
w
o
r
k
o
f
Gh
ar
eh
c
h
o
p
o
g
h
et
al.
[
3
4
]
.
T
h
e
au
th
o
r
h
as
ap
p
lies
T
ab
u
s
ea
r
ch
alg
o
r
ith
m
as
w
ell
as
g
en
eti
c
alg
o
r
ith
m
f
o
r
th
i
s
p
u
r
p
o
s
e.
T
h
e
tech
n
iq
u
e
u
s
e
s
NAS
A
-
r
elate
d
d
ataset
alo
n
g
w
it
h
C
OC
OM
O
m
o
d
el
to
f
in
d
r
ed
u
ce
d
e
r
r
o
r
in
o
u
tco
m
es.
S
i
m
ilar
au
t
h
o
r
h
as
also
ap
p
lied
A
r
tif
ic
ial
B
ee
C
o
lo
n
y
alo
n
g
w
i
th
g
en
et
ic
alg
o
r
i
th
m
[
3
5
]
.
A
d
o
p
tio
n
o
f
Fu
zz
y
L
o
g
ic
w
as
s
ee
n
i
n
t
h
e
w
o
r
k
o
f
I
d
r
i
an
d
Z
a
h
i
[
3
6
]
co
n
s
id
er
in
g
t
h
e
d
ataset
o
f
w
eb
s
o
f
t
w
ar
e.
L
iu
e
t
al.
[
3
7
]
h
av
e
also
u
s
ed
P
ar
ticle
S
w
ar
m
Op
ti
m
izatio
n
in
o
r
d
er
to
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
o
f
co
s
t
esti
m
atio
n
f
o
r
an
alo
g
y
b
ased
ap
p
r
o
ac
h
.
Un
iq
u
el
y
,
th
e
a
u
th
o
r
co
n
s
id
er
s
a
f
ac
to
r
ca
lled
as
N
o
n
-
Ort
h
o
g
o
n
a
l
S
p
a
ce
Dis
ta
n
ce
f
o
r
esti
m
at
in
g
th
e
s
i
m
i
lar
it
y
m
ea
s
u
r
es
o
f
th
e
p
r
o
j
ec
t.
Sar
n
o
et
al.
[
3
8
]
h
av
e
u
s
ed
n
e
u
r
al
n
et
w
o
r
k
f
o
r
s
i
m
i
lar
ca
u
s
e.
E
n
h
an
ce
m
e
n
t
o
f
a
n
alo
g
y
-
b
ased
ap
p
r
o
ac
h
w
a
s
s
ee
n
in
th
e
s
t
u
d
y
o
f
P
h
an
n
ac
h
itt
a
et
al.
[
3
9
]
u
s
in
g
p
r
o
b
a
b
ilit
y
-
b
a
s
ed
co
m
p
u
tatio
n
o
f
d
is
tan
ce
f
u
n
ctio
n
f
o
r
co
s
t c
o
m
p
u
tatio
n
.
T
ab
le
1
.
S
u
m
m
ar
y
o
f
t
h
e
E
x
i
s
t
in
g
T
ec
h
n
iq
u
es o
f
C
o
s
t E
s
ti
m
atio
n
A
u
t
h
o
r
s
P
r
o
b
l
e
ms
T
e
c
h
n
i
q
u
e
s
A
d
v
a
n
t
a
g
e
s
L
i
mi
t
a
t
i
o
n
Ju
n
i
o
r
[
2
7
]
A
c
c
u
r
a
c
y
p
r
o
b
l
e
m
o
f
F
u
n
c
t
i
o
n
a
l
P
o
i
n
t
A
n
a
l
y
si
s
Q
u
a
l
i
t
a
t
i
v
e
S
t
u
d
y
H
i
g
h
l
i
g
h
t
e
d
t
e
c
h
n
i
q
u
e
s
t
o
i
mp
r
o
v
e
-
n
o
c
l
e
a
r
c
u
t
so
l
u
t
i
o
n
-
h
i
g
h
e
r
c
o
m
p
l
e
x
i
t
y
-
d
e
p
e
n
d
e
n
c
i
e
s o
n
c
u
r
r
e
n
t
v
e
r
si
o
n
M
i
t
t
a
s
[
2
8
]
P
r
e
d
i
c
t
i
v
e
A
c
c
u
r
a
c
y
S
t
a
t
i
st
i
c
a
l
M
e
a
s
u
r
e
s
(
A
N
O
V
A
)
-
Ex
t
e
n
si
v
e
A
sse
ssm
e
n
t
-
-
d
o
e
sn
’
t
c
o
n
si
d
e
r
d
y
n
a
mi
c
o
r
u
n
c
e
r
t
a
i
n
t
y
f
a
c
t
o
r
i
n
mo
d
e
l
i
n
g
L
i
n
d
[
2
9
]
Est
i
m
a
t
i
n
g
c
o
d
e
si
z
e
i
n
e
mb
e
d
d
e
d
sy
st
e
m
-
C
O
S
M
I
C
-
S
t
a
t
i
st
i
c
a
l
M
e
a
su
r
e
s
-
S
i
mp
l
e
&
P
r
a
c
t
i
c
a
l
F
r
a
mew
o
r
k
d
e
si
g
n
-
D
o
e
sn
’
t
d
i
s
c
u
ss
t
h
e
a
p
p
l
i
c
a
b
i
l
i
t
y
-
N
o
b
e
n
c
h
mark
i
n
g
Z
i
a
[
3
0
]
F
o
u
r
t
h
G
e
n
e
r
a
t
i
o
n
l
a
n
g
u
a
g
e
-
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
-
Emp
i
r
i
c
a
l
A
p
p
r
o
a
c
h
-
S
i
mp
l
e
mo
d
e
l
i
n
g
a
p
p
r
o
a
c
h
-
d
o
e
sn
’
t
c
o
n
si
d
e
r
d
y
n
a
mi
c
o
r
u
n
c
e
r
t
a
i
n
t
y
f
a
c
t
o
r
i
n
mo
d
e
l
i
n
g
H
i
h
n
[
3
1
]
N
A
S
A
D
a
t
a
-
S
t
a
t
i
st
i
c
a
l
(
f
-
t
e
st
,
t
-
t
e
st
)
-
sp
e
c
t
r
a
l
c
l
u
st
e
r
i
n
g
-
C
a
p
a
b
l
e
o
f
c
o
n
s
i
d
e
r
i
n
g
c
o
mp
l
e
x
d
a
t
a
-
N
o
b
e
n
c
h
mark
i
n
g
C
a
n
n
o
n
[
3
2
]
C
o
st
e
st
i
mat
i
o
n
f
o
r
l
u
n
a
r
d
a
t
a
C
O
C
O
M
O
,
Ex
t
r
a
p
o
l
a
t
i
o
n
,
S
o
u
r
c
e
L
i
n
e
s o
f
C
o
d
e
,
A
g
i
l
e
-
Ef
f
e
c
t
i
v
e
A
n
a
l
y
si
s
t
e
c
h
n
i
q
u
e
-
O
f
f
e
r
g
o
o
d
e
st
i
mat
e
s
-
N
o
b
e
n
c
h
mark
i
n
g
o
r
v
a
l
i
d
a
t
i
o
n
G
a
r
g
[
3
3
]
A
c
c
u
r
a
c
y
o
f
A
g
i
l
e
P
r
i
n
c
i
p
l
e
C
o
m
p
o
n
e
n
t
A
n
a
l
y
si
s
-
N
o
d
e
p
e
n
d
e
n
c
y
o
v
e
r
h
i
s
t
o
r
i
c
a
l
d
a
t
a
-
N
o
b
e
n
c
h
mark
i
n
g
o
r
v
a
l
i
d
a
t
i
o
n
G
h
a
r
e
h
c
h
o
p
o
g
h
[
3
4
]
C
o
st
e
st
i
mat
i
o
n
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
,
T
a
b
u
S
e
a
r
c
h
,
C
O
C
O
M
O
-
R
e
d
u
c
e
d
e
r
r
o
r
i
n
o
u
t
c
o
me
s
-
D
o
e
sn
’
t
d
i
s
c
u
ss
c
o
mp
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
S
o
l
e
i
man
i
a
n
[
3
5
]
C
o
st
e
st
i
mat
i
o
n
G
e
n
e
t
i
c
A
l
g
o
r
i
t
h
m
,
A
r
t
i
f
i
c
i
a
l
B
e
e
C
o
l
o
n
y
,
C
O
C
O
M
O
-
R
e
d
u
c
e
d
e
r
r
o
r
i
n
o
u
t
c
o
me
s
-
D
o
e
sn
’
t
d
i
s
c
u
ss
c
o
mp
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
I
d
r
i
[
3
6
]
C
o
mp
a
r
i
n
g
a
n
a
l
o
g
y
-
b
a
se
d
a
p
p
r
o
a
c
h
F
u
z
z
y
L
o
g
i
c
-
A
p
p
l
i
c
a
b
l
e
f
o
r
w
e
b
a
p
p
l
i
c
a
t
i
o
n
s
-
N
o
b
e
n
c
h
mark
i
n
g
-
D
o
e
sn
’
t
d
i
s
c
u
ss
c
o
mp
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
L
i
u
[
3
7
]
A
c
c
u
r
a
c
y
i
n
c
o
st
e
st
i
mat
i
o
n
P
a
r
t
i
c
l
e
S
w
a
r
m
O
p
t
i
mi
z
a
t
i
o
n
-
F
i
t
s t
o
r
e
a
l
-
w
o
r
l
d
p
r
o
j
e
c
t
s
-
R
e
d
u
c
e
d
Er
r
o
r
-
D
o
e
sn
’
t
d
i
s
c
u
ss
c
o
mp
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
S
a
r
n
o
[
3
8
]
A
c
c
u
r
a
c
y
i
n
c
o
st
e
st
i
mat
i
o
n
-
F
e
e
d
-
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
-
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
-
C
O
C
O
M
O
-
R
e
d
u
c
e
d
e
r
r
o
r
-
S
i
mp
l
e
i
mp
l
e
me
n
t
a
t
i
o
n
-
N
o
b
e
n
c
h
mark
i
n
g
-
C
o
n
v
e
r
g
e
n
c
e
p
e
r
f
o
r
man
c
e
n
o
t
d
i
s
c
u
s
se
d
P
h
a
n
n
a
c
h
i
t
t
a
[
3
9
]
Er
r
o
r
r
e
d
u
c
t
i
o
n
i
n
a
n
a
l
o
g
y
-
b
a
se
d
a
p
p
r
o
a
c
h
P
r
o
b
a
b
i
l
i
st
i
c
A
p
p
r
o
a
c
h
-
F
a
st
e
r
i
mp
l
e
me
n
t
a
t
i
o
n
-
t
e
st
e
d
o
v
e
r
mu
l
t
i
p
l
e
d
a
t
a
se
t
-
N
o
b
e
n
c
h
mark
i
n
g
-
C
o
n
v
e
r
g
e
n
c
e
p
e
r
f
o
r
man
c
e
n
o
t
d
i
s
c
u
s
se
d
2
.
2
.
E
f
f
o
r
t
E
s
t
i
m
a
t
io
n
T
ec
hn
iqu
e
E
f
f
o
r
t
e
s
ti
m
atio
n
i
s
t
h
e
d
ir
e
ct
f
u
n
ctio
n
al
tas
k
to
b
e
ca
r
r
ied
o
u
t
to
w
ar
d
s
m
aj
o
r
it
y
o
f
th
e
co
s
t
-
esti
m
atio
n
m
o
d
el
till
d
ate.
A
lt
h
o
u
g
h
,
th
er
e
ar
e
v
ar
io
u
s
to
o
ls
an
d
tec
h
n
iq
u
e
to
co
m
p
u
te
e
f
f
o
r
t
f
ac
to
r
w
it
h
i
n
a
n
in
d
u
s
tr
y
,
b
u
t
s
ti
ll
th
er
e
ar
e
ce
r
tain
o
p
en
ch
allen
g
es
to
w
ar
d
s
i
m
p
le
m
e
n
ti
n
g
it
e.
g
.
in
f
er
io
r
k
n
o
w
led
g
e
m
an
a
g
e
m
e
n
t,
n
o
n
-
ad
ap
tab
ilit
y
o
n
s
ta
n
d
ar
d
esti
m
a
tio
n
te
ch
n
iq
u
es,
to
o
l
-
r
elate
d
p
r
o
b
le
m
s
,
n
e
g
li
g
en
ce
o
f
p
r
o
j
ec
t
p
e
r
f
o
r
m
a
n
ce
p
ar
a
m
ete
r
s
[
4
0
]
.
Var
io
u
s
ch
allen
g
es
p
e
r
tain
i
n
g
to
th
e
tec
h
n
iq
u
es
o
f
e
f
f
o
r
t
esti
m
at
i
o
n
at
p
r
esen
t a
r
e
f
o
u
n
d
to
b
e
h
u
m
a
n
r
eso
u
r
ce
s
,
g
o
v
er
n
a
n
ce
,
to
o
ls
,
an
d
p
r
o
ce
s
s
es.
A
t p
r
ese
n
t,
t
h
er
e
is
n
o
s
u
c
h
m
o
d
el
o
r
f
r
a
m
e
w
o
r
k
t
h
at
o
v
er
all
ad
d
r
ess
es
s
u
c
h
p
r
o
b
le
m
s
j
o
in
tl
y
.
Mo
s
t
r
ec
en
tl
y
,
t
h
er
e
i
s
i
n
v
esti
g
atio
n
to
w
ar
d
s
ef
f
o
r
t
es
ti
m
atio
n
i
n
s
o
f
t
w
ar
e
d
esig
n
in
ea
r
l
y
s
ta
g
e
s
f
o
r
b
ett
er
co
n
s
id
er
atio
n
o
f
p
r
o
b
ab
le
co
s
t
in
v
o
lv
ed
w
it
h
i
n
th
is
.
O
n
e
s
u
ch
tec
h
n
iq
u
e
h
a
s
b
ee
n
p
r
esen
ted
b
y
Satap
at
h
y
et
al.
[
4
1
]
,
w
h
er
e
th
e
au
th
o
r
s
h
a
v
e
ap
p
lied
f
r
eq
u
en
tl
y
u
s
ed
m
ac
h
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
k
n
o
w
n
a
s
r
a
n
d
o
m
fo
r
est
.
T
h
e
tech
n
iq
u
e
u
s
e
s
r
an
d
o
m
f
o
r
est
f
o
r
o
p
tim
izin
g
th
e
ac
cu
r
ac
y
i
n
t
h
e
p
r
ed
ictiv
e
o
u
tco
m
e.
T
h
e
s
tu
d
y
al
s
o
co
n
s
id
er
s
v
ar
io
u
s
f
o
r
m
s
o
f
th
e
co
m
p
le
x
it
y
f
ac
to
r
s
e.
g
.
p
o
r
tab
ilit
y
,
c
h
a
n
g
ea
b
ilit
y
,
co
n
c
u
r
r
en
c
y
,
e
f
f
icie
n
c
y
o
f
en
d
u
s
er
,
co
d
e
r
eu
s
ab
ilit
y
,
s
ec
u
r
it
y
f
ea
t
u
r
es
etc.
T
h
e
a
u
th
o
r
s
h
a
v
e
also
p
er
f
o
r
m
s
a
n
al
y
s
i
s
o
v
er
th
e
er
r
o
r
,
p
r
o
x
i
m
itie
s
,
co
m
p
lex
i
ties
,
an
d
o
u
tlier
s
.
T
h
e
s
tu
d
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
I
n
s
ig
h
ts
o
n
R
esea
r
ch
Tech
n
i
q
u
es to
w
a
r
d
s
C
o
s
t E
s
tima
tio
n
in
S
o
ftw
a
r
e
Desig
n
(
P
r
a
ve
en
N
a
ik)
2889
o
u
tco
m
e
w
as
as
s
es
s
ed
u
s
i
n
g
s
tan
d
ar
d
p
er
f
o
r
m
a
n
ce
p
ar
am
e
t
er
s
e.
g
.
m
ea
n
s
q
u
ar
ed
er
r
o
r
s
,
p
r
ed
ictio
n
ac
cu
r
ac
y
,
m
ea
n
m
a
g
n
i
tu
d
e
o
f
r
elati
v
e
er
r
o
r
.
Stu
d
y
to
w
ar
d
s
d
ev
elo
p
m
e
n
t
ef
f
o
r
ts
an
d
it
s
esti
m
atio
n
te
ch
n
iq
u
es
h
av
e
b
ee
n
also
p
r
esen
ted
b
y
B
ar
d
s
ir
i
et
al.
[
4
2
]
to
w
ar
d
s
t
h
e
ai
m
o
f
en
h
a
n
ci
n
g
th
e
ac
c
u
r
ac
y
lev
el.
T
h
e
au
th
o
r
s
h
av
e
ap
p
lied
j
o
in
tl
y
m
u
ltip
le
tech
n
i
q
u
es
e.
g
.
an
alo
g
y
-
b
ased
tech
n
i
q
u
es,
f
u
zz
y
lo
g
ic,
an
d
n
eu
r
al
n
et
w
o
r
k
.
T
h
e
s
tu
d
y
o
u
tco
m
e
s
h
o
w
s
i
m
p
r
e
s
s
i
v
e
p
e
r
ce
n
tag
e
o
f
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
I
t
w
as
o
b
s
er
v
ed
th
a
t
m
u
c
h
o
f
t
h
e
e
m
p
h
a
s
is
w
a
s
laid
o
n
k
n
o
w
led
g
e
d
is
co
v
er
y
p
r
o
ce
s
s
u
s
in
g
m
i
n
i
n
g
tech
n
i
q
u
es
in
e
f
f
o
r
t
esti
m
atio
n
tec
h
n
iq
u
es.
A
p
p
l
y
i
n
g
m
i
n
in
g
ap
p
r
o
ac
h
ca
n
i
n
co
r
p
o
r
a
te
f
u
r
t
h
er
p
r
ed
ictiv
e
f
ea
t
u
r
e
in
s
o
f
t
w
ar
e
m
o
d
elin
g
.
Dej
ae
g
er
et
al.
[
4
3
]
h
av
e
ca
r
r
ied
o
u
t
a
d
is
cu
s
s
io
n
w
h
er
e
th
e
i
m
p
o
r
tan
ce
o
f
m
i
n
i
n
g
a
p
p
r
o
ac
h
es
h
av
e
b
ee
n
m
ad
e.
A
s
tatis
tical
ap
p
r
o
ac
h
is
ap
p
lied
f
o
r
p
er
f
o
r
m
i
n
g
co
m
p
ar
at
iv
e
an
al
y
s
is
o
n
v
ar
io
u
s
tech
n
iq
u
e
s
.
Gr
b
ac
et
al.
[
4
4
]
h
a
v
e
ca
r
r
ied
o
u
t
a
s
tu
d
y
to
w
ar
d
s
ef
f
o
r
t
esti
m
ati
o
n
d
u
r
in
g
i
n
s
p
ec
tio
n
.
T
h
e
s
p
e
cial
co
n
s
id
er
atio
n
is
ab
o
u
t
th
e
ea
r
ly
s
ta
g
e
o
f
th
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
.
T
h
e
o
u
t
co
m
e
o
f
th
e
s
t
u
d
y
s
u
g
g
e
s
ts
th
at
an
ef
f
ec
ti
v
e
d
ec
i
s
io
n
f
ac
to
r
s
ig
n
i
f
ica
n
tl
y
as
s
is
t
s
i
n
e
n
h
a
n
ci
n
g
t
h
e
p
r
o
d
u
ct
r
el
iab
ilit
y
.
An
o
t
h
er
b
ig
g
er
ch
al
len
g
e
i
n
t
h
e
ar
ea
o
f
s
o
f
t
w
ar
e
en
g
in
ee
r
i
n
g
t
h
e
d
is
p
er
s
io
n
o
f
t
h
e
f
a
ls
i
f
ied
i
n
f
o
r
m
at
io
n
t
h
at
lead
s
to
d
ec
lin
a
tio
n
o
f
t
h
e
p
r
o
d
u
ct
q
u
alit
y
as
w
ell
a
s
er
r
o
r
-
p
r
o
n
e
ef
f
o
r
t
es
ti
m
ates.
St
u
d
y
to
w
ar
d
s
s
u
c
h
p
r
o
b
l
em
w
a
s
d
is
c
u
s
s
ed
b
y
J
o
r
g
en
s
e
n
a
n
d
Gr
i
m
s
t
ad
[
4
5
]
w
h
er
e
t
h
e
au
th
o
r
s
h
a
v
e
p
er
f
o
r
m
ed
an
e
x
p
er
i
m
e
n
t
co
n
s
id
er
in
g
v
ar
io
u
s
o
r
g
an
izat
io
n
al
d
ata.
T
h
e
p
r
im
e
p
u
r
p
o
s
e
o
f
t
h
e
p
r
esen
ted
s
t
u
d
y
is
to
p
er
f
o
r
m
co
s
t
co
m
p
u
tatio
n
o
f
t
h
e
e
f
f
o
r
t
b
ein
g
u
s
ed
f
o
r
esti
m
ati
n
g
u
n
n
ec
es
s
ar
y
ta
s
k
.
T
h
i
s
tech
n
iq
u
e
p
la
y
s
m
u
ch
i
m
p
o
r
ta
n
t
r
o
le
f
o
r
an
y
o
r
g
an
izatio
n
to
f
i
n
d
o
r
ig
i
n
al
e
f
f
o
r
t
to
w
ar
d
s
p
r
o
d
u
ctiv
it
y
a
n
d
n
o
t
to
w
ar
d
s
u
n
n
ec
ess
ar
y
tr
ials
o
f
w
o
r
k
.
T
h
e
au
th
o
r
s
h
av
e
u
s
ed
q
u
an
tita
tiv
e
-
b
ased
m
e
th
o
d
o
lo
g
y
u
s
i
n
g
s
tati
s
tics
i
n
o
r
d
er
t
o
ca
r
r
y
o
u
t
th
e
o
b
j
ec
ti
v
es.
A
s
i
g
n
if
ica
n
t
p
r
o
b
le
m
with
ef
f
o
r
t
esti
m
atio
n
is
les
s
in
v
o
lv
e
m
e
n
t
o
f
m
o
r
e
n
u
m
b
er
o
f
ef
f
ec
ti
v
e
q
u
alit
y
p
ar
am
eter
s
.
St
u
d
y
to
w
ar
d
s
th
is
p
r
o
b
le
m
w
a
s
ad
d
r
ess
ed
b
y
A
za
th
a
n
d
W
ah
id
ab
an
u
[
4
6
]
u
s
in
g
s
ta
n
d
ar
d
C
OC
OM
O
m
o
d
el
alo
n
g
w
it
h
u
s
a
g
e
o
f
I
SO
9
1
2
6
s
ta
n
d
ar
d
s
an
d
its
co
m
p
lian
t
q
u
alit
y
f
ac
to
r
s
.
T
h
e
au
t
h
o
r
s
h
a
v
e
also
u
s
ed
f
u
n
c
tio
n
al
p
o
i
n
ts
an
d
its
o
u
tco
m
e
is
ass
e
s
s
ed
u
s
in
g
to
tal
d
eg
r
ee
o
f
in
f
lu
e
n
ce
,
u
s
ab
il
it
y
,
r
eliab
ilit
y
,
m
ai
n
tai
n
ab
ilit
y
,
an
d
e
f
f
ici
en
c
y
.
Si
m
ilar
l
y
,
t
h
e
f
ac
to
r
s
in
v
o
l
v
ed
i
n
e
f
f
o
r
t
esti
m
atio
n
w
i
ll
n
ee
d
a
p
r
ec
is
e
co
m
b
in
a
tio
n
o
f
d
if
f
er
en
t
ap
p
r
o
ac
h
to
m
a
k
e
a
s
u
itab
le
b
alan
ce
b
et
w
ee
n
s
i
m
p
lic
it
y
a
n
d
s
o
p
h
is
ticatio
n
.
T
h
er
ef
o
r
e,
s
tu
d
y
e
m
p
h
asizi
n
g
o
n
co
n
ten
t
s
an
d
p
ar
am
e
ter
s
r
eq
u
ir
ed
f
o
r
ef
f
o
r
t
esti
m
atio
n
w
as
ca
r
r
ied
o
u
t
b
y
Ko
ca
g
u
n
eli
et
al.
[
4
7
]
.
T
h
e
au
th
o
r
u
s
e
s
s
p
atial
-
b
ased
ap
p
r
o
ac
h
b
etw
ee
n
th
e
in
s
ta
n
ce
s
a
n
d
f
ea
tu
r
es
t
h
at
f
u
r
th
er
as
s
is
ts
in
ef
f
o
r
t
e
s
ti
m
atio
n
.
A
C
AR
T
-
b
ased
ap
p
r
o
ac
h
a
s
w
ell
as
C
O
C
OM
O
is
also
u
tili
ze
d
f
o
r
ac
tiv
e
lear
n
in
g
i
n
o
r
d
er
to
p
er
f
o
r
m
p
r
ed
ictiv
e
m
o
d
eli
n
g
.
T
h
e
s
a
m
e
au
t
h
o
r
s
[
4
8
]
h
av
e
also
p
er
f
o
r
m
ed
in
v
e
s
ti
g
atio
n
to
w
a
r
d
s
1
0
d
if
f
er
en
t
d
atasets
u
s
i
n
g
an
alo
g
y
-
b
a
s
ed
ap
p
r
o
ac
h
f
o
r
ef
f
o
r
t
esti
m
a
tio
n
.
Ko
ca
g
u
n
eli
et
al.
[
4
9
]
h
av
e
also
d
is
cu
s
s
ed
th
a
t
it
is
n
o
t
n
ec
ess
ar
y
to
s
elec
t
th
e
b
est
esti
m
atio
n
m
et
h
o
d
o
u
t
o
f
m
an
y
m
eth
o
d
b
u
t
to
u
s
e
th
e
m
e
th
o
d
s
in
ter
m
it
ten
t
l
y
.
T
h
e
au
th
o
r
co
n
clu
d
es
t
h
at
s
elec
t
io
n
o
f
o
n
e
m
et
h
o
d
s
h
o
u
ld
b
e
d
is
co
u
r
a
g
ed
an
d
i
n
s
p
ite
a
co
m
b
i
n
atio
n
o
f
d
i
f
f
e
r
en
t
m
et
h
o
d
ca
n
b
est
s
u
it
th
e
p
u
r
p
o
s
e
o
f
e
f
f
o
r
t
esti
m
atio
n
.
T
ab
le
2
Su
m
m
ar
y
o
f
t
h
e
e
x
is
ti
n
g
T
ec
h
n
iq
u
es o
f
E
f
f
o
r
t E
s
ti
m
atio
n
A
u
t
h
o
r
s
P
r
o
b
l
e
ms
T
e
c
h
n
i
q
u
e
s
A
d
v
a
n
t
a
g
e
s
L
i
mi
t
a
t
i
o
n
S
a
t
a
p
a
t
h
y
e
t
a
l
.
[
4
1
]
P
r
e
d
i
c
t
i
o
n
A
c
c
u
r
a
c
y
-
R
a
n
d
o
m F
o
r
e
st
-
U
se
C
a
se
P
o
i
n
t
s
-
H
i
g
h
e
r
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
-
c
o
mp
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
n
o
t
a
n
a
l
y
z
e
d
.
B
a
r
d
s
i
r
i
e
t
a
l
.
[
4
2
]
I
n
c
r
e
a
si
n
g
a
c
c
u
r
a
c
y
-
A
n
a
l
o
g
y
-
b
a
se
d
T
e
c
h
n
i
q
u
e
s
-
F
u
z
z
y
L
o
g
i
c
-
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
-
H
i
g
h
e
r
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
-
A
p
p
l
i
c
a
b
l
e
o
n
l
a
r
g
e
d
a
t
a
se
t
-
L
a
c
k
o
f
u
n
c
e
r
t
a
i
n
t
y
f
a
c
t
o
r
-
S
t
a
b
i
l
i
t
y
f
a
c
t
o
r
n
o
t
f
o
u
n
d
D
e
j
a
e
g
e
r
e
t
a
l
.
[
4
3
]
-
C
o
mp
a
r
a
t
i
v
e
S
t
u
d
y
-
d
i
f
f
e
r
e
n
t
mi
n
i
n
g
a
p
p
r
o
a
c
h
-
r
e
g
r
e
ssi
o
n
a
n
d
C
O
C
O
M
O
a
r
e
b
e
st
su
i
t
e
d
-
H
i
g
h
l
y
d
e
p
e
n
d
e
n
t
o
n
e
x
p
e
r
t
’
s
j
u
d
g
me
n
t
G
r
b
a
c
e
t
a
l
.
[
4
4
]
-
v
a
l
u
e
q
u
a
n
t
i
f
i
c
a
t
i
o
n
d
u
r
i
n
g
i
n
s
p
e
c
t
i
o
n
-
e
x
p
e
r
t
j
u
d
g
me
n
t
-
S
t
a
t
i
st
i
c
a
l
M
e
a
su
r
e
s
-
i
n
c
r
e
a
se
d
i
n
q
u
a
l
i
t
y
o
f
p
r
o
d
u
c
t
-
N
o
e
f
f
e
c
t
i
v
e
b
e
n
c
h
mar
k
i
n
g
Jo
r
g
e
n
se
n
a
n
d
G
r
i
msta
d
[
4
5
]
-
f
a
l
si
f
i
e
d
e
f
f
o
r
t
e
st
i
mat
i
o
n
-
S
t
a
t
i
st
i
c
a
l
M
e
a
su
r
e
s
-
S
i
mp
l
i
f
i
e
d
mo
d
e
l
i
n
g
-
o
v
e
r
a
l
l
o
u
t
c
o
me
c
a
n
n
o
t
b
e
g
e
n
e
r
a
l
i
z
e
d
t
o
o
t
h
e
r
sce
n
a
r
i
o
A
z
a
t
h
a
n
d
W
a
h
i
d
a
b
a
n
u
[
4
6
]
-
e
f
f
o
r
t
e
st
i
ma
t
i
o
n
-
F
u
n
c
t
i
o
n
a
l
p
o
i
n
t
-
C
O
C
O
M
O
-
I
S
O
9
1
2
6
-
v
e
r
y
si
mp
l
e
i
mp
l
e
me
n
t
a
t
i
o
n
a
p
p
r
o
a
c
h
-
D
o
e
sn
’
t
a
d
d
r
e
ss
t
h
e
u
n
c
e
r
t
a
i
n
t
y
/
d
y
n
a
m
i
c
p
r
o
b
l
e
ms
K
o
c
a
g
u
n
e
l
i
e
t
a
l
.
[
4
7
]
-
e
f
f
o
r
t
e
st
i
ma
t
i
o
n
-
C
O
C
O
M
O
-
C
A
R
T
-
Eu
c
l
i
d
e
a
n
d
i
st
a
n
c
e
-
o
f
f
e
r
b
e
t
t
e
r
su
g
g
e
st
i
o
n
f
o
r
c
h
o
i
c
e
o
f
e
st
i
m
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
-
N
o
b
e
n
c
h
mark
i
n
g
-
D
o
e
sn
’
t
d
i
s
c
u
ss
a
b
o
u
t
c
o
mp
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
.
K
o
c
a
g
u
n
e
l
i
e
t
a
l
.
[
4
8
]
-
Ef
f
o
r
t
e
st
i
mat
i
o
n
-
A
n
a
l
o
g
y
-
b
a
se
d
e
st
i
mat
i
o
n
-
se
l
e
c
t
i
o
n
o
f
n
e
a
r
e
st
n
e
i
g
h
b
o
r
-
I
mp
r
o
v
e
d
sy
st
e
m
p
e
r
f
o
r
man
c
e
-
R
e
d
u
c
e
d
e
r
r
o
r
r
a
t
e
-
N
o
b
e
n
c
h
mark
i
n
g
-
D
o
e
sn
’
t
d
i
s
c
u
ss
c
o
m
p
u
t
a
t
i
o
n
a
l
p
r
o
b
l
e
ms
K
o
c
a
g
u
n
e
l
i
e
t
a
l
.
[
4
9
]
-
Ef
f
o
r
t
e
st
i
mat
i
o
n
C
o
mb
i
n
a
t
i
o
n
o
f
m
u
l
t
i
p
l
e
me
t
h
o
d
s
-
R
e
d
u
c
e
d
e
r
r
o
r
r
a
t
e
-
N
o
b
e
n
c
h
mark
i
n
g
-
D
o
e
sn
’
t
d
i
s
c
u
ss
c
o
m
p
u
t
a
t
i
o
n
a
l
p
r
o
b
l
e
ms
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
.
5
,
Octo
b
er
2
0
1
7
:
2
8
8
3
–
2
8
9
4
2890
2
.
3
.
F
a
ult
E
s
t
i
m
a
t
io
n T
ec
h
ni
qu
es
W
h
en
t
h
e
s
o
f
t
w
ar
e
is
d
es
ig
n
e
d
w
it
h
ce
r
tai
n
er
r
o
r
p
r
o
n
e
p
lan
n
i
n
g
,
it
is
o
u
g
h
t
to
p
o
s
s
es
s
c
er
tain
le
v
el
o
f
f
au
lt
o
r
d
ef
ec
t.
Fo
r
th
is
r
ea
s
o
n
,
th
e
test
i
n
g
an
d
q
u
alit
y
a
s
s
u
r
an
ce
m
e
m
b
er
s
ar
e
r
esp
o
n
s
ib
le
f
o
r
id
en
tify
i
n
g
a
b
u
g
a
n
d
r
e
m
o
v
e
it.
Ho
w
e
v
e
r
,
th
e
co
n
ce
p
t
o
f
co
s
t
co
m
p
u
tatio
n
e
v
o
lv
e
s
i
n
e
s
ti
m
ati
n
g
f
a
u
lt
s
r
esid
i
n
g
i
n
s
o
f
t
w
ar
e
d
esig
n
.
A
lt
h
o
u
g
h
,
m
aj
o
r
ity
o
f
th
e
ex
i
s
ti
n
g
m
ec
h
an
is
m
o
f
f
au
lt
d
etec
tio
n
o
n
l
y
w
o
r
k
s
af
ter
t
h
e
f
a
u
lt
is
r
ea
ll
y
in
co
r
p
o
r
ated
w
it
h
i
n
th
e
s
o
f
t
w
ar
e,
b
y
t
h
at
ti
m
e,
it
b
ec
o
m
es
to
o
late
to
d
eb
u
g
it.
So
m
e
ti
m
e
i
s
ev
e
n
a
v
er
y
h
ig
h
e
x
p
en
s
i
v
e
m
a
tter
to
r
e
m
o
v
e
th
e
f
a
u
lt
s
.
Hen
ce
,
t
h
e
co
n
ce
p
t
o
f
p
r
ed
ictiv
e
p
r
i
n
cip
le
i
n
co
s
t
e
s
ti
m
atio
n
is
eq
u
all
y
h
elp
f
u
l
f
o
r
f
a
u
lt
d
ete
ctio
n
w
h
ic
h
is
d
ef
in
ite
l
y
i
n
t
h
e
ea
r
l
y
s
ta
g
e.
T
h
e
ad
v
an
tag
e
is
to
id
en
tify
t
h
e
p
o
s
s
ib
le
f
a
u
lt
s
e
v
e
n
b
ef
o
r
e
i
t
co
u
ld
p
o
s
s
ib
l
y
i
n
f
lict
s
o
m
e
s
er
io
u
s
p
r
o
b
lem
s
i
n
th
e
s
o
f
t
w
ar
e
d
es
ig
n
.
Stu
d
y
ad
d
r
ess
in
g
s
u
c
h
p
r
o
b
lem
ca
n
b
e
f
o
u
n
d
in
t
h
e
w
o
r
k
ca
r
r
ied
o
u
t
b
y
Fa
g
u
n
d
es
et
al.
[
5
0
]
w
h
er
e
a
p
r
ed
ictiv
e
p
r
in
cip
le
is
in
tr
o
d
u
ce
d
b
y
t
h
e
au
t
h
o
r
.
T
h
e
tech
n
iq
u
e
j
o
in
tl
y
u
s
e
s
b
o
th
p
ar
a
m
etr
ic
a
s
w
ell
as
n
o
n
-
p
ar
a
m
etr
ic
f
r
a
m
e
w
o
r
k
s
f
o
r
en
h
a
n
cin
g
t
h
e
ac
cu
r
ac
y
o
f
f
au
lt
p
r
ed
ictio
n
.
C
o
n
s
id
er
in
g
th
e
N
A
S
A
d
atase
t,
th
e
a
u
t
h
o
r
s
h
a
v
e
ca
r
r
ied
o
u
t
ex
p
er
im
e
n
ts
u
s
i
n
g
m
ac
h
i
n
e
lear
n
i
n
g
la
n
g
u
a
g
e
.
T
h
e
s
tu
d
y
o
u
tco
m
e
w
a
s
f
o
u
n
d
to
h
av
e
b
etter
ca
p
ab
ilit
y
o
f
id
en
tify
i
n
g
th
e
n
o
n
-
f
a
u
lt
y
to
f
a
u
lt
y
m
e
th
o
d
s
.
U
ca
n
et
al.
[
5
1
]
in
tr
o
d
u
ce
d
an
esti
m
atio
n
p
r
o
ce
s
s
e
s
to
f
i
n
d
t
h
e
co
s
t
o
f
“
d
etec
ti
n
g
d
ef
ec
t”
i
n
t
h
e
in
s
tr
u
m
e
n
ted
p
r
o
g
r
a
m
s
w
h
ich
m
a
y
w
o
r
k
tr
ad
itio
n
all
y
o
r
co
u
ld
b
e
s
u
p
p
o
r
ted
w
i
th
a
co
llab
o
r
ativ
e
p
latf
o
r
m
.
I
t
i
s
f
o
u
n
d
t
h
at
th
e
co
llab
o
r
ativ
e
as
s
o
ciate
p
lat
f
o
r
m
g
iv
e
n
d
e
f
ec
t
o
f
3
.
7
6
p
er
h
o
u
r
as
co
m
p
ar
e
to
t
h
e
tr
ad
itio
n
al
p
r
o
ce
s
s
,
w
h
er
e
it
is
4
.
0
7
.
T
h
is
w
o
r
k
m
a
y
i
n
f
l
u
en
ce
th
e
t
h
o
u
g
h
t
o
f
w
eb
b
ased
en
ter
p
r
is
e
ap
p
licatio
n
to
co
n
s
id
er
th
e
p
ar
a
m
eter
s
th
at
s
y
s
te
m
h
a
v
i
n
g
co
llab
o
r
ativ
e
ap
p
r
o
ac
h
o
f
d
ev
elo
p
m
en
t
o
r
n
o
t b
y
i
n
tr
o
d
u
cin
g
s
o
m
e
f
ac
to
r
s
a
y
α
(
w
h
er
e,
th
e
v
al
u
e
o
f
α
w
ill b
e
h
i
g
h
er
if
n
o
co
llab
o
r
ati
v
e
to
o
l
u
s
ed
f
o
r
d
ev
elo
p
m
e
n
t)
.
T
h
e
p
ar
a
m
eter
α
r
ed
u
ce
d
t
h
e
co
s
t
o
f
d
ev
elo
p
m
e
n
t.
T
h
e
ad
o
p
ti
o
n
o
f
co
llab
o
r
ativ
e
p
latf
o
r
m
i
s
co
m
in
g
m
a
n
d
ato
r
y
as
t
h
e
s
o
f
t
w
ar
e
p
r
o
d
u
ctio
n
p
r
o
ce
s
s
u
s
e
s
v
ar
io
u
s
m
o
d
els
o
f
o
u
t
-
s
o
u
r
cin
g
,
i
n
-
s
o
u
r
cin
g
,
o
f
f
-
s
h
o
r
e
d
ev
elo
p
m
e
n
t
etc,
w
h
er
e
p
eo
p
le
ar
e
lo
ca
ted
at
d
if
f
er
en
t
g
eo
g
r
ap
h
ic
al
r
eg
io
n
an
d
n
o
t
p
o
s
s
ib
le
to
h
av
e
f
r
o
n
t
to
f
r
o
n
t
ad
-
h
o
c
d
is
c
u
s
s
io
n
s
.
So
m
eti
m
e
s
h
ar
d
w
ar
e
as
w
ell
a
s
s
o
f
t
w
ar
e
-
b
ased
d
esig
n
a
n
d
th
eir
as
s
o
ciate
d
co
m
p
o
n
e
n
t
s
c
o
u
ld
b
e
r
esp
o
n
s
ib
le
f
o
r
s
o
f
t
war
e
f
ail
u
r
es.
S
t
u
d
y
i
n
s
u
c
h
d
ir
ec
tio
n
w
a
s
ca
r
r
ied
o
u
t
b
y
Ozc
e
lik
an
d
Yi
l
m
az
[
5
2
]
w
h
er
e
a
p
r
ed
ictiv
e
s
y
s
te
m
i
s
d
esi
g
n
th
at
ca
n
e
s
ti
m
ate
t
h
e
a
m
o
u
n
t
o
f
f
au
lt
s
i
n
th
e
s
o
f
t
w
ar
e.
T
h
e
ev
al
u
atio
n
o
f
th
e
s
t
u
d
y
w
a
s
ca
r
r
ied
o
u
t
u
s
in
g
a
s
tan
d
ar
d
tr
an
s
f
o
r
m
atio
n
to
o
l
in
p
r
esen
ce
o
f
m
u
l
tip
le
d
ef
ec
ts
w
h
ile
s
t
u
d
y
o
u
tco
m
es
ar
e
ev
al
u
ated
u
s
i
n
g
p
er
f
o
r
m
an
ce
p
ar
a
m
eter
s
o
f
p
r
ed
ictio
n
ac
cu
r
ac
y
.
P
r
ed
ictiv
e
s
tu
d
y
to
w
ar
d
s
f
au
l
t
co
m
p
u
tatio
n
w
as
al
s
o
ca
r
r
ied
o
u
t
b
y
L
i
u
et
al.
[
5
3
]
w
h
er
e
th
e
e
m
p
h
a
s
is
i
s
m
ai
n
l
y
laid
o
v
er
th
e
clas
s
i
f
ica
tio
n
p
r
o
ce
s
s
.
T
h
e
tech
n
iq
u
e
m
ak
e
s
u
s
e
o
f
b
o
th
f
ea
t
u
r
e
as
w
ell
a
s
r
ed
u
ctio
n
o
f
n
u
m
b
er
o
f
in
s
ta
n
ce
s
a
s
a
p
a
r
t
o
f
d
ata
p
r
ep
r
o
ce
s
s
in
g
.
An
an
al
y
s
i
s
o
f
r
elev
a
n
ce
i
s
ca
r
r
ied
o
u
t
d
u
r
in
g
t
h
e
s
elec
tio
n
p
r
o
ce
s
s
o
f
f
ea
t
u
r
e.
I
t
th
a
n
p
er
f
o
r
m
s
co
n
tr
o
llin
g
o
f
r
ed
u
n
d
a
n
cies
u
s
i
n
g
th
r
es
h
o
ld
-
b
ased
clu
s
ter
in
g
ap
p
r
o
ac
h
.
Sim
ilar
lin
e
o
f
w
o
r
k
w
as a
ls
o
ca
r
r
ied
o
u
t b
y
Dej
ae
g
er
et
al.
[
5
4
]
b
y
in
tr
o
d
u
ci
n
g
a
B
ay
e
s
ian
n
et
w
o
r
k
class
i
f
ier
.
T
h
e
au
t
h
o
r
s
h
a
v
e
al
s
o
in
v
esti
g
ated
t
h
e
f
ea
s
ib
ilit
y
o
f
i
m
p
le
m
e
n
ti
n
g
Ma
r
k
o
v
b
lan
k
et
p
r
in
cip
le
w
it
h
r
esp
ec
t
to
B
ay
e
s
ia
n
n
e
t
w
o
r
k
th
eo
r
y
.
S
i
m
ilar
N
A
S
A
d
ataset
h
a
s
b
ee
n
u
s
ed
f
o
r
d
eter
m
i
n
in
g
l
in
e
o
f
co
d
e
m
etr
ics,
Hal
s
tead
m
etr
ic
s
,
an
d
Mc
C
ab
e
m
etr
ic.
Mo
n
d
en
et
a
l.
[
5
5
]
h
av
e
p
r
esen
ted
a
tech
n
iq
u
e
f
o
r
p
r
ed
ictin
g
f
au
lt
as
w
e
ll
as
ass
es
s
i
n
g
t
h
e
co
s
t
esti
m
ate
s
o
u
t
o
f
it.
W
ith
an
aid
o
f
s
o
f
t
w
ar
e
test
i
n
g
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
ev
alu
a
tes
t
h
e
p
o
s
s
ib
le
allo
ca
t
io
n
tec
h
n
iq
u
es
f
o
r
e
f
f
o
r
t
e
s
ti
m
atio
n
d
ep
en
d
in
g
o
n
t
h
e
o
u
t
co
m
e
o
f
th
e
f
a
u
lt
s
.
A
r
c
u
r
i
et
al.
[
5
6
]
h
av
e
p
r
ese
n
ted
a
tech
n
iq
u
e
t
h
at
u
s
es
r
an
d
o
m
test
i
n
g
in
o
r
d
er
to
d
et
ec
t
th
e
f
au
lt
in
th
e
so
f
t
w
ar
e
d
esi
g
n
.
T
h
e
r
ea
s
o
n
b
eh
in
d
ad
ap
tio
n
o
f
r
an
d
o
m
test
i
n
g
is
i
ts
s
u
p
p
o
r
tab
ilit
y
o
f
lar
g
e
n
u
m
b
er
o
f
f
ea
t
u
r
es.
B
is
h
n
u
an
d
B
h
attac
h
er
j
ee
[
5
7
]
h
av
e
i
n
tr
o
d
u
ce
d
a
class
if
ica
tio
n
tech
n
iq
u
e
f
o
r
p
er
f
o
r
m
i
n
g
f
a
u
lt
p
r
ed
ictio
n
.
T
h
e
au
th
o
r
s
h
a
v
e
u
s
ed
K
-
m
ea
n
s
cl
u
s
ter
i
n
g
a
lg
o
r
ith
m
in
o
r
d
er
to
ev
al
u
ate
t
h
e
clu
s
ter
q
u
alit
y
an
d
p
r
ed
ictin
g
t
h
e
p
o
s
s
ib
le
f
a
u
lt
s
in
th
e
co
d
e.
J
in
e
t
al.
[
5
8
]
h
av
e
p
r
esen
ted
a
tech
n
iq
u
e
u
s
in
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
a
s
w
el
l
as
n
e
u
r
al
n
et
w
o
r
k
f
o
r
as
s
is
t
in
g
i
n
s
elec
tio
n
o
f
p
ar
a
m
eter
s
th
a
t
w
o
u
ld
p
o
s
i
t
iv
e
a
f
f
ec
t
t
h
e
f
au
lt
p
r
ed
ictio
n
.
Data
b
ase
f
r
o
m
N
A
S
A
is
u
s
ed
w
it
h
m
u
ltip
le
m
e
tr
ics
i
n
o
r
d
er
to
p
er
f
o
r
m
cr
o
s
s
-
v
alid
atio
n
f
o
llo
w
ed
b
y
ac
cu
r
ac
y
test
i
n
g
.
T
h
e
s
tu
d
y
o
u
tco
m
e
w
a
s
f
o
u
n
d
to
p
o
s
s
es
s
a
p
o
ten
tial
li
n
k
b
et
w
ee
n
f
a
u
lt
f
ac
to
r
s
an
d
s
o
f
t
w
ar
e
m
etr
ic
s
.
So
f
t
w
ar
e
t
esti
n
g
h
a
s
al
s
o
s
i
g
n
if
ican
t
l
y
g
ai
n
ed
h
ig
h
er
d
e
g
r
ee
o
f
a
t
ten
tio
n
a
m
o
n
g
t
h
e
r
esear
ch
er
s
.
I
n
ac
cu
r
ate
te
s
ti
n
g
s
tr
ate
g
ies
w
i
ll
ess
e
n
tia
ll
y
lea
d
to
g
en
er
atio
n
o
f
f
au
lts
a
n
d
th
er
eb
y
it
n
e
g
ati
v
el
y
af
f
ec
ts
th
e
ec
o
n
o
m
y
o
f
an
o
r
g
an
izatio
n
.
St
u
d
y
to
w
ar
d
s
s
tr
en
g
th
e
n
i
n
g
th
e
s
o
f
t
w
ar
e
test
in
g
w
a
s
al
s
o
ca
r
r
ied
o
u
t
R
a
m
o
s
et
a
l.
[
5
9
]
.
T
h
e
au
th
o
r
s
h
a
v
e
i
n
tr
o
d
u
ce
d
a
m
o
d
el
t
h
at
s
ig
n
i
f
ica
n
tl
y
as
s
is
ts
in
en
s
u
r
i
n
g
le
s
s
er
a
m
o
u
n
t
o
f
d
ef
ec
ts
a
s
w
ell
a
s
f
au
l
ts
i
n
t
h
e
s
o
f
t
w
ar
e
d
esi
g
n
.
I
t
also
a
s
s
i
s
t
s
in
o
v
er
co
m
i
n
g
t
h
e
s
k
ill
g
ap
a
m
o
n
g
t
h
e
tes
ter
s
.
T
h
is
co
m
p
ete
n
ce
m
o
d
el
ca
n
b
e
u
s
ed
b
y
an
y
o
r
g
a
n
izatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
I
n
s
ig
h
ts
o
n
R
esea
r
ch
Tech
n
i
q
u
es to
w
a
r
d
s
C
o
s
t E
s
tima
tio
n
in
S
o
ftw
a
r
e
Desig
n
(
P
r
a
ve
en
N
a
ik)
2891
T
ab
le
3
Su
m
m
ar
y
o
f
E
x
is
tin
g
T
ec
h
n
iq
u
es o
f
Fau
l
t E
s
ti
m
atio
n
A
u
t
h
o
r
s
P
r
o
b
l
e
ms
T
e
c
h
n
i
q
u
e
s
A
d
v
a
n
t
a
g
e
s
L
i
mi
t
a
t
i
o
n
F
a
g
u
n
d
e
s e
t
a
l
.
[
5
1
]
F
a
u
l
t
p
r
e
d
i
c
t
i
o
n
-
Jo
i
n
t
u
s
a
g
e
o
f
p
a
r
a
me
t
r
i
c
&
n
o
n
-
p
a
r
a
me
t
r
i
c
t
e
c
h
n
i
q
u
e
s
-
f
i
t
t
i
n
g
mo
d
e
l
t
o
se
t
o
f
d
a
t
a
p
o
i
n
t
s
-
C
o
mp
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
n
o
t
a
sse
sse
d
.
U
c
a
n
e
t
a
l
.
[
5
9
]
Ef
f
i
c
i
e
n
c
y
i
n
D
e
f
e
c
t
d
e
t
e
c
t
i
o
n
-
c
o
l
l
a
b
o
r
a
t
i
v
e
v
i
r
t
u
a
l
e
n
v
i
r
o
n
me
n
t
-
f
a
st
e
r
r
e
sp
o
n
se
-
N
o
b
e
n
c
h
mark
i
n
g
-
S
p
a
c
e
c
o
m
p
l
e
x
i
t
y
i
s n
o
t
a
d
d
r
e
sse
d
.
O
z
c
e
l
i
k
a
n
d
Y
i
l
maz
[
5
3
]
R
u
n
t
i
me
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
C
I
L
t
o
o
l
,
W
e
k
a
,
P
A
P
I
t
o
o
l
,
R
e
d
u
c
e
d
r
u
n
t
i
me
o
v
e
r
h
e
a
d
-
N
o
b
e
n
c
h
mark
i
n
g
L
i
u
e
t
a
l
.
[
5
4
]
C
l
a
ssi
f
i
c
a
t
i
o
n
p
r
o
b
l
e
ms
D
a
t
a
p
r
e
p
r
o
c
e
ssi
n
g
,
r
a
n
d
o
m u
n
d
e
r
-
samp
l
i
n
g
-
mai
n
t
a
i
n
b
e
t
t
e
r
b
a
l
a
n
c
e
b
e
t
w
e
e
n
i
n
s
t
a
n
c
e
s
-
N
o
b
e
n
c
h
mark
i
n
g
-
D
o
e
sn
’
t
a
d
d
r
e
ss t
h
e
d
y
n
a
mi
c
p
r
o
b
l
e
ms
D
e
j
a
e
g
e
r
e
t
a
l
.
[
5
5
]
F
a
u
l
t
p
r
e
d
i
c
t
i
o
n
B
a
y
e
si
a
n
n
e
t
w
o
r
k
c
l
a
ssi
f
i
e
r
-
b
a
l
a
n
c
e
d
p
r
e
d
i
c
t
i
v
e
a
n
d
c
o
mp
r
e
h
e
n
si
b
i
l
i
t
y
p
e
r
f
o
r
man
c
e
-
C
o
mp
l
e
x
r
e
l
a
t
i
o
n
s
h
i
p
i
n
b
o
t
h
d
y
n
a
mi
c
a
n
d
st
a
t
i
c
f
e
a
t
u
r
e
s o
f
c
o
d
e
n
o
t
c
o
n
s
i
d
e
r
e
d
.
M
o
n
d
e
n
e
t
a
l
.
[
5
6
]
-
F
o
r
e
c
a
st
i
n
g
f
a
u
l
t
-
A
l
l
o
c
a
t
i
o
n
o
f
e
f
f
o
r
t
-
Emp
i
r
i
c
a
l
a
p
p
r
o
a
c
h
-
S
i
mu
l
a
t
i
o
n
-
c
o
st
e
f
f
e
c
t
i
v
e
p
r
e
d
i
c
t
i
o
n
o
f
f
a
u
l
t
-
h
i
g
h
e
r
d
e
p
e
n
d
e
n
c
i
e
s o
n
i
n
t
e
r
n
a
l
r
e
so
u
r
c
e
s.
A
r
c
u
r
i
e
t
a
l
.
[
5
7
]
F
a
u
l
t
d
e
t
e
c
t
i
o
n
R
a
n
d
o
m
t
e
st
i
n
g
-
su
p
p
o
r
t
a
b
i
l
i
t
y
o
f
h
i
g
h
e
r
f
e
a
t
u
r
e
s
-
N
/
A
-
B
i
s
h
n
u
a
n
d
B
h
a
t
t
a
c
h
e
r
j
e
e
[
5
8
]
F
a
u
l
t
p
r
e
d
i
c
t
i
o
n
k
-
me
a
n
s
c
l
u
s
t
e
r
i
n
g
-
b
e
t
t
e
r
p
e
r
f
o
r
man
c
e
o
f
e
r
r
o
r
r
a
t
e
s
-
n
o
a
p
p
l
i
c
a
b
l
e
o
n
d
y
n
a
m
i
c
p
r
o
g
r
a
ms
Ji
n
e
t
a
l
.
[
5
9
]
F
a
u
l
t
p
r
e
d
i
c
t
i
o
n
-
N
e
u
r
a
l
n
e
t
w
o
r
k
-
S
u
p
p
o
r
t
v
e
c
t
o
r
M
a
c
h
i
n
e
-
N
o
e
x
t
r
a
c
o
st
t
o
w
a
r
d
s
i
mp
l
e
me
n
t
a
t
i
o
n
-
n
o
d
e
p
e
n
d
e
n
c
y
t
o
w
a
r
d
s
e
x
p
e
r
t
s k
n
o
w
l
e
d
g
e
-
t
r
a
i
n
i
n
g
c
o
m
p
l
e
x
i
t
i
e
s
a
sso
c
i
a
t
e
d
i
s
n
o
t
d
i
sc
u
sse
d
R
a
mo
s e
t
a
l
.
[
D
1
0
]
M
i
n
i
m
i
z
i
n
g
f
a
u
l
t
s
-
C
o
mp
e
t
e
n
c
e
mo
d
e
l
-
p
r
a
c
t
i
c
a
l
l
y
a
f
f
e
c
t
u
se
r
s t
o
mi
n
i
mi
z
e
f
a
u
l
t
s
-
O
u
t
c
o
me
a
p
p
l
i
c
a
b
i
l
i
t
y
i
s
n
a
r
r
o
w
f
o
r
l
a
r
g
e
sca
l
e
a
p
p
l
i
c
a
t
i
o
n
s
3
O
P
E
N
RE
S
E
AR
CH
I
SS
UE
S
Fro
m
t
h
e
p
r
io
r
s
ec
tio
n
,
it
w
a
s
s
ee
n
th
at
t
h
er
e
ar
e
v
ar
io
u
s
tech
n
iq
u
e
s
to
w
ar
d
s
en
s
u
r
i
n
g
th
at
co
s
t
esti
m
atio
n
i
n
t
h
e
s
o
f
t
w
ar
e
d
esig
n
.
I
t
h
a
s
b
ee
n
e
x
p
lo
r
ed
th
at
t
h
e
ex
i
s
ti
n
g
tech
n
iq
u
e
s
o
f
s
o
f
t
w
ar
e
co
s
t
esti
m
atio
n
h
a
v
e
h
i
g
h
l
y
d
i
v
er
s
i
f
ied
s
tr
ate
g
ies
to
i
m
p
le
m
en
t
b
u
t
u
n
f
o
r
tu
n
atel
y
,
it
is
f
o
u
n
d
with
h
ig
h
er
n
u
m
b
er
o
f
c
h
allen
g
e
s
.
A
ll
t
h
e
tec
h
n
iq
u
es
h
a
v
e
t
h
eir
o
w
n
ad
v
an
ta
g
e
s
as
w
ell
as
li
m
itatio
n
s
to
o
.
Ho
w
e
v
er
,
t
h
er
e
ar
e
ce
r
tain
s
et
o
f
p
r
o
b
le
m
s
t
h
at
h
a
s
b
ee
n
f
o
u
n
d
n
o
t to
b
e
ad
d
r
e
s
s
ed
b
y
th
e
e
x
i
s
ti
n
g
r
esear
c
h
w
o
r
k
.
L
ess
f
o
cus
o
n
I
n
pu
t
:
B
asicall
y
9
9
%
o
f
all
th
e
ex
i
s
ti
n
g
r
esea
r
ch
p
ap
er
s
h
a
v
e
ad
o
p
ted
d
atas
et
e.
g
.
N
AS
A
,
w
h
er
e
th
e
e
x
is
t
in
g
f
r
a
m
e
w
o
r
k
s
co
n
s
id
er
s
in
p
u
t
to
b
e
i)
f
u
n
ct
io
n
al
p
o
in
t,
ii)
li
n
e
o
f
s
o
u
r
ce
co
d
e,
iii)
in
s
tr
u
ctio
n
s
e
t,
etc.
S
u
c
h
tec
h
n
iq
u
e
d
o
esn
’
t
o
f
f
er
an
ac
cu
r
at
e
o
u
tco
m
e
w
h
en
it
is
ap
p
lied
f
o
r
esti
m
ati
n
g
co
s
t
f
o
r
t
h
e
s
o
f
t
w
ar
e
d
ev
e
lo
p
m
en
t.
S
u
ch
s
ce
n
ar
io
s
ar
e
h
ig
h
l
y
s
tatic
a
n
d
u
n
i
f
o
r
m
a
n
d
t
h
er
eb
y
its
o
u
tco
m
e
ca
n
n
o
t
b
e
s
aid
to
b
e
ap
p
licab
le
f
o
r
d
y
n
a
m
ic
e
n
v
ir
o
n
m
en
t.
Hen
c
e,
th
er
e
w
a
s
a
les
s
er
e
m
p
h
asis
to
w
ar
d
s
en
s
u
r
in
g
m
o
r
e
p
r
ec
is
e
i
n
p
u
ts
w
h
ile
es
ti
m
ati
n
g
co
s
t.
No
Studies
t
o
w
a
rds
Co
m
p
uta
t
io
na
l
E
f
f
iciency
:
E
x
is
ti
n
g
tec
h
n
iq
u
e
s
h
a
v
e
m
a
in
l
y
i
n
tr
o
d
u
ce
d
co
s
t
co
m
p
u
tatio
n
m
eth
o
d
o
n
d
i
f
f
er
en
t d
ataset.
T
h
er
e
ar
e
also
s
t
u
d
ies
w
h
er
e
la
r
g
e
n
u
m
b
er
s
o
f
d
atasets
ar
e
u
s
ed
w
it
h
m
o
r
e
i
n
cl
u
s
io
n
o
f
r
ec
u
r
s
iv
e
f
u
n
ctio
n
.
S
u
ch
t
y
p
e
s
o
f
ap
p
r
o
ac
h
es
s
i
g
n
i
f
ica
n
tl
y
i
n
cr
e
ases
b
o
th
ti
m
e
an
d
s
p
ac
e
co
m
p
lex
i
t
y
.
So
m
e
o
f
th
e
s
tu
d
ie
s
h
a
v
e
b
ee
n
clai
m
ed
to
o
f
f
er
r
ed
u
ce
d
p
r
o
ce
s
s
i
n
g
b
u
r
d
en
,
b
u
t
ex
ac
t
v
a
lid
atio
n
o
f
i
t
is
m
is
s
in
g
i
n
th
e
l
iter
atu
r
e.
W
ith
o
u
t
en
s
u
r
in
g
co
s
t
e
f
f
ec
t
iv
e
co
m
p
u
tat
io
n
,
t
h
e
ap
p
licab
ilit
y
o
f
s
u
ch
co
s
t c
o
m
p
u
tatio
n
tec
h
n
iq
u
es o
v
er
lo
w
-
p
o
w
er
ed
d
ev
ices a
r
e
q
u
esti
o
n
a
b
le.
M
o
re
G
ener
a
lized
a
nd
L
e
s
s
S
pecif
ic
:
T
h
e
ex
is
tin
g
t
ec
h
n
iq
u
es
h
a
v
e
n
o
t
tak
e
n
c
ase
s
t
u
d
ies
o
f
ap
p
licab
ilit
y
o
f
co
s
t
est
i
m
a
tio
n
m
o
d
el
o
n
p
ar
ticu
lar
s
o
f
t
w
ar
e.
A
l
l
t
h
e
cu
r
r
e
n
t
i
n
v
e
s
ti
g
atio
n
s
u
s
e
th
e
ter
m
s
o
ftw
a
r
e
a
s
a
v
er
y
g
en
er
ic
m
o
d
el
w
i
th
n
o
d
i
s
cr
ete
elab
o
r
atio
n
o
f
t
h
e
s
y
s
te
m
.
B
ec
au
s
e
o
f
t
h
is
r
ea
s
o
n
,
it
i
s
n
o
t
s
u
r
e
w
h
eth
er
t
h
e
e
x
is
tin
g
co
s
t
-
co
m
p
u
ti
n
g
m
o
d
els
ar
e
r
ea
ll
y
ap
p
licab
le
i
n
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
.
At
p
r
esen
t,
th
er
e
ar
e
m
o
r
e
t
h
an
l
ak
h
s
o
f
s
o
f
t
w
ar
e
w
it
h
t
h
o
u
s
an
d
n
u
m
b
er
s
o
f
tec
h
n
o
lo
g
ies
r
u
n
n
i
n
g
o
v
er
it.
I
t
is
w
ell
k
n
o
w
n
t
h
at
i
n
p
r
es
en
t
ti
m
e
’
s
u
s
a
g
e
o
f
w
ir
eles
s
-
b
ased
p
r
o
d
u
cts
ar
e
i
n
i
n
c
r
ea
s
in
g
tr
e
n
d
s
.
Un
f
o
r
tu
n
atel
y
,
t
h
er
e
is
n
o
s
u
c
h
s
t
u
d
y
o
n
co
s
t c
o
m
p
u
tatio
n
m
o
d
el
t
h
at
d
ea
ls
w
i
th
w
ir
ele
s
s
-
b
ased
p
r
o
d
u
cts.
No
Net
w
o
rk
Co
ns
idera
t
io
n
:
Ma
j
o
r
ity
o
f
t
h
e
ex
i
s
ti
n
g
s
y
s
te
m
u
s
e
s
th
e
ter
m
s
o
f
t
w
ar
e
an
d
d
o
esn
’
t
co
n
s
id
er
an
y
th
i
n
g
else.
I
n
r
ea
l
it
y
,
it
is
k
n
o
w
n
t
h
at
m
a
x
i
m
u
m
s
o
f
t
w
ar
e
is
n
o
w
co
n
n
ec
ted
w
it
h
t
h
e
ad
v
e
n
t
o
f
p
er
v
as
iv
e
an
d
u
b
iq
u
i
to
u
s
c
o
m
p
u
ti
n
g
.
He
n
ce
,
i
g
n
o
r
i
n
g
t
h
e
n
et
w
o
r
k
s
tatis
t
ics
a
n
d
p
r
o
ce
ed
in
g
to
w
ar
d
s
co
s
t
co
m
p
u
ta
tio
n
al
m
o
d
el
f
o
r
s
o
f
t
w
ar
e
w
ill
b
e
i
m
p
ar
tial
w
o
r
k
.
I
t
is
n
ec
es
s
ar
y
th
a
t
all
th
e
co
n
n
ec
te
d
co
m
p
o
n
e
n
t
s
o
f
t
h
e
s
o
f
t
w
ar
e
e
.
g
.
u
s
er
,
n
et
w
o
r
k
,
etc.
s
h
o
u
ld
b
e
co
n
s
id
er
ed
w
h
ile
w
o
r
k
i
n
g
o
v
er
th
e
co
s
t
co
m
p
u
tatio
n
m
o
d
el.
F
ew
Studies
t
o
w
a
rds
M
ini
m
iza
t
io
n
:
C
o
s
t
is
a
v
ar
iab
le
in
t
h
e
ar
ea
o
f
s
o
f
t
w
ar
e
p
r
o
j
ec
t
m
an
ag
e
m
e
n
t.
An
ef
f
ec
tiv
e
p
r
o
j
ec
t p
lan
n
in
g
al
wa
y
s
ca
l
ls
f
o
r
r
ed
u
ctio
n
o
f
t
h
e
c
o
s
t in
v
o
lv
ed
i
n
it.
U
n
f
o
r
t
u
n
ate
l
y
,
t
h
e
e
x
is
ti
n
g
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
.
5
,
Octo
b
er
2
0
1
7
:
2
8
8
3
–
2
8
9
4
2892
tech
n
iq
u
es
ar
e
m
o
r
e
f
o
cu
s
o
n
co
s
t
esti
m
at
io
n
u
s
in
g
d
if
f
er
en
t
d
ataset
an
d
less
to
w
ar
d
s
co
s
t
m
i
n
i
m
izatio
n
.
Stu
d
y
to
w
ar
d
s
a
n
ef
f
ec
ti
v
e
o
p
ti
m
izat
io
n
tec
h
n
iq
u
e
w
ill
al
w
a
y
s
r
es
u
lt
s
in
m
i
n
i
m
al
co
s
t
i
n
v
o
lv
e
m
e
n
t.
T
h
i
s
th
eo
r
etica
l
v
ie
w
p
o
i
n
t
w
a
s
n
o
t
s
ee
n
i
n
m
a
n
y
s
tu
d
ie
s
to
w
a
r
d
s
s
o
f
t
w
ar
e
m
o
d
eli
n
g
an
d
c
o
s
t
es
ti
m
atio
n
tech
n
iq
u
es i
n
p
r
esen
t ti
m
es.
F
ew
Sta
nd
a
rd
M
o
delin
g
t
o
w
a
rds
Co
s
t
E
s
t
i
m
a
t
io
n
:
A
clo
s
er
lo
o
k
in
to
th
e
o
u
tco
m
e
s
o
f
an
y
o
f
t
h
e
r
ec
en
t
s
t
u
d
ies
to
w
ar
d
s
co
s
t
est
i
m
atio
n
w
ill
s
h
o
w
v
er
y
f
e
w
b
e
n
ch
m
ar
k
ed
tech
n
iq
u
es.
U
s
ag
e
o
f
C
O
C
OM
O
m
o
d
el
is
d
ef
i
n
itel
y
n
o
t
w
i
t
h
o
u
t
f
la
w
s
e.
g
.
m
o
r
e
p
r
o
n
e
t
o
ad
o
p
t
b
ac
k
d
ated
w
ater
f
all
m
o
d
el,
m
o
r
e
ex
p
er
i
m
e
n
tal
a
n
d
le
s
s
ca
lib
r
ated
,
n
o
n
-
s
u
p
p
o
r
tab
ilit
y
o
f
d
u
r
atio
n
ca
lcu
la
tio
n
in
s
m
all
s
ca
le
s
o
f
t
w
ar
e
p
r
o
j
ec
ts
.
Hen
ce
,
ev
e
n
a
f
ter
k
n
o
w
i
n
g
s
u
c
h
p
itf
a
lls
,
m
aj
o
r
it
y
o
f
th
e
w
o
r
k
h
as
b
ee
n
u
s
in
g
C
O
C
OM
O
ir
r
esp
ec
tiv
e
o
f
ta
k
in
g
a
ch
a
n
ce
to
in
tr
o
d
u
ce
a
n
e
w
m
a
th
e
m
ati
ca
l
m
o
d
elin
g
o
r
alg
o
r
ith
m
ic
a
p
p
r
o
ac
h
.
3.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
h
as
d
i
s
cu
s
s
ed
t
h
e
r
esear
ch
tr
ait
s
o
f
t
h
e
s
o
f
t
war
e
co
s
t
esti
m
atio
n
.
T
h
er
e
ar
e
v
ar
io
u
s
co
n
v
e
n
tio
n
al
m
o
d
el
s
f
o
r
p
er
f
o
r
m
i
n
g
co
s
t
e
s
ti
m
atio
n
e
x
p
l
o
r
ed
in
r
ec
en
t
ti
m
e
e.
g
.
al
g
o
r
ith
m
ic
an
d
n
o
n
-
alg
o
r
ith
m
ic
ap
p
r
o
ac
h
.
A
lt
h
o
u
g
h
b
o
th
th
e
ap
p
r
o
ac
h
es
h
as
as
s
o
ciate
d
ad
v
an
tag
e
s
as
w
e
ll
as
li
m
itatio
n
,
b
u
t
s
till
th
e
y
ar
e
in
p
r
ac
tice
at
lar
g
e.
W
e
also
d
is
cu
s
s
th
e
ex
is
ti
n
g
r
esear
ch
tr
en
d
s
to
f
in
d
th
a
t
th
er
e
ar
e
v
er
y
le
s
s
n
u
m
b
er
o
f
g
o
o
d
r
esear
ch
w
o
r
k
b
ein
g
ca
r
r
ied
o
u
t
to
w
ar
d
s
s
o
f
t
w
ar
e
co
s
t
e
s
ti
m
atio
n
,
ef
f
o
r
t
esti
m
atio
n
,
f
au
l
t
p
r
ed
ictio
n
,
etc.
W
e
f
in
d
th
at
C
OC
OM
O
is
t
h
e
b
ac
k
b
o
n
e
o
f
m
aj
o
r
ity
o
f
t
h
e
ex
is
ti
n
g
r
esea
r
ch
tech
n
iq
u
e
s
.
Ou
r
f
i
n
d
in
g
s
ar
e
i)
th
er
e
ar
e
v
er
y
less
b
en
c
h
m
ar
k
ed
r
esear
ch
m
eth
o
d
o
lo
g
y
t
h
at
ca
n
b
e
r
ec
o
m
m
en
d
ed
in
p
r
ese
n
t
d
ay
,
ii)
n
o
t
a
s
i
n
g
le
co
s
t
-
esti
m
atio
n
tech
n
iq
u
e
ca
n
b
e
r
ef
e
r
r
ed
as
a
r
o
b
u
s
t
o
n
e,
h
o
w
e
v
e
r
,
a
co
m
b
in
a
tio
n
o
f
m
u
ltip
le
tec
h
n
iq
u
es
(
h
y
b
r
id
izi
n
g
)
ca
n
s
h
o
w
b
etter
r
esu
lt,
iii)
n
o
n
e
o
f
t
h
e
e
x
i
s
ti
n
g
tech
n
iq
u
es
ar
e
r
ea
ll
y
f
o
u
n
d
to
ad
d
r
ess
co
m
p
u
tat
io
n
al
co
m
p
lex
i
t
y
p
r
o
b
le
m
s
,
i
v
)
th
er
e
ar
e
v
ar
io
u
s
o
p
en
r
esear
ch
i
s
s
u
es
p
er
tain
i
n
g
to
ex
is
t
in
g
li
ter
atu
r
es
o
f
co
s
t
-
es
ti
m
atio
n
ap
p
r
o
ac
h
,
w
h
ic
h
w
i
l
l
r
eq
u
ir
e
s
er
io
u
s
co
n
s
id
er
atio
n
,
etc.
He
n
ce
,
o
u
r
f
u
tu
r
e
d
ir
ec
tio
n
o
f
t
h
e
r
esear
c
h
w
o
r
k
w
ill b
e
to
w
ar
d
s
b
r
id
g
in
g
t
h
e
g
ap
o
f
e
x
is
tin
g
s
y
s
te
m
.
W
e
h
av
e
n
o
ticed
t
h
at
al
m
o
s
t
all
th
e
ex
i
s
ti
n
g
r
esear
c
h
w
o
r
k
h
a
s
u
s
e
t
h
e
ter
m
s
o
f
t
w
ar
e
in
g
e
n
er
ic
s
en
s
e
w
h
er
ea
s
in
r
ea
ll
y
t
h
er
e
ar
e
d
iv
er
s
e
f
o
r
m
s
o
f
it
w
it
h
m
an
i
f
o
ld
c
o
m
p
lex
ities
.
Hen
ce
,
w
e
w
ill
li
k
e
to
ad
o
p
t
a
s
p
ec
if
ic
ca
s
e
s
t
u
d
y
o
f
s
o
f
t
war
e
an
d
m
a
k
e
it
m
o
r
e
d
is
cr
ete.
I
t
is
b
ec
au
s
e
it
is
n
o
t
s
u
r
e
if
an
y
o
f
t
h
e
ex
i
s
ti
n
g
tech
n
iq
u
e
ca
n
b
e
ap
p
licab
le
in
an
y
s
p
ec
i
f
ic
s
o
f
t
w
ar
e
ap
p
licatio
n
.
Hen
ce
,
o
u
r
f
ir
s
t
f
u
t
u
r
e
w
o
r
k
w
ill
b
e
to
co
n
s
id
er
a
s
o
f
t
w
ar
e
t
h
at
as
s
is
t
s
in
w
ir
eles
s
co
m
m
u
n
icatio
n
a
n
d
th
e
co
m
p
u
te
a
co
s
t
p
er
tai
n
i
n
g
to
d
ev
elo
p
m
e
n
t
o
f
it.
Ou
r
s
ec
o
n
d
lev
el
o
f
f
u
t
u
r
e
w
o
r
k
w
ill
b
e
to
r
e
-
th
in
k
o
n
th
e
ter
m
s
o
f
t
w
ar
e
an
d
m
a
k
e
it
m
o
r
e
ap
p
licab
le
to
th
e
p
r
esen
t
ti
m
e
ap
p
licatio
n
a
n
d
p
r
esen
t
a
co
s
t
-
e
s
ti
m
atio
n
m
o
d
el
f
o
r
it.
W
e
w
ill
li
k
e
to
in
v
e
s
ti
g
ate
ab
o
u
t
th
e
u
s
a
g
e
o
f
h
i
g
h
f
r
eq
u
e
n
c
y
s
i
g
n
a
l a
n
d
t
h
eir
u
tili
za
t
io
n
o
v
er
th
e
s
o
f
t
w
ar
e
f
o
r
civ
ic
b
en
e
f
it
s
i
n
o
r
d
er
to
s
ee
th
e
co
s
t
in
v
o
l
v
e
m
en
t
in
it.
Ou
r
f
i
n
al
le
v
el
o
f
f
u
t
u
r
e
w
o
r
k
w
il
l
b
e
to
e
n
s
u
r
e
th
at
o
u
r
co
s
t
in
v
o
lv
e
m
e
n
t
co
u
ld
b
e
p
o
s
s
ib
ly
m
i
n
i
m
ized
w
h
ile
r
etai
n
i
n
g
h
ig
h
er
p
r
o
d
u
ct
ef
f
ic
ien
c
y
.
I
n
s
h
o
r
t,
o
u
r
f
u
t
u
r
e
d
ir
ec
tio
n
o
f
th
e
wo
r
k
w
ill
b
e
to
g
iv
e
a
p
r
ac
tical
s
h
ap
e
to
s
o
f
t
w
ar
e
u
s
i
n
g
a
ca
s
e
s
tu
d
y
o
f
it
s
o
th
a
t
it
b
ec
o
m
es
ea
s
y
f
o
r
th
e
r
esear
c
h
co
m
m
u
n
it
y
to
u
n
d
er
s
ta
n
d
th
e
ap
p
licab
ilit
y
o
f
m
y
f
r
a
m
e
w
o
r
k
.
RE
F
E
R
E
NC
E
S
[
1
]
S
u
d
h
a
k
a
r,
“
S
o
f
twa
re
De
v
e
lo
p
m
e
n
t
T
e
a
m
s: P
e
rf
o
rm
a
n
c
e
,”
p
ro
d
u
c
t
ivity a
n
d
i
n
n
o
v
a
ti
o
n
,
p
h
i
lea
r
n
in
g
p
v
t.
lt
d
,
2
0
1
5
[
2
]
H.
M
o
h
a
n
ty
,
J.
R.
M
o
h
a
n
ty
,
A
.
K.
Ba
lak
rish
n
a
n
,
“
T
re
n
d
s in
S
o
f
tw
a
re
T
e
stin
g
,”
S
p
rin
g
e
r
-
Co
m
p
u
ter
s,
2
0
1
6
[
3
]
J.
M
c
M
a
n
u
s,
“
Risk
M
a
n
a
g
e
m
e
n
t
in
S
o
f
twa
re
De
v
e
lo
p
m
e
n
t
P
ro
jec
ts
,”
Ro
u
t
led
g
e
,
2
0
1
2
[
4
]
A
.
P
.
S
a
g
e
,
W
.
B.
Ro
u
se
,
“
Ha
n
d
b
o
o
k
o
f
S
y
ste
m
s E
n
g
in
e
e
rin
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,”
J
o
h
n
W
il
e
y
&
S
o
n
s
,
2
0
0
9
[
5
]
S
.
Jh
a
,
“
T
h
e
P
ro
jec
t
M
a
n
a
g
e
r'
s C
o
m
m
u
n
ica
ti
o
n
T
o
o
lk
it
”
,
CRC
Pre
ss
,
2
0
1
0
[
6
]
B.
T
u
lg
a
n
,
“
Brid
g
in
g
th
e
S
o
f
t
S
k
i
ll
s G
a
p
:
Ho
w
to
Tea
c
h
th
e
M
issin
g
Ba
sic
s to
T
o
d
a
y
s Yo
u
n
g
Tale
n
t
,”
J
o
h
n
W
il
e
y
&
Sons
,
2
0
1
5
[
7
]
P
.
S
e
rra
d
o
r,
“
P
r
o
jec
t
P
lan
n
in
g
a
n
d
P
r
o
jec
t
S
u
c
c
e
ss
:
T
h
e
2
5
%
S
o
lu
t
io
n
,”
C
RC
Pre
ss
,
2
0
1
4
[
8
]
T
.
M
e
lt
o
n
,
“
Re
a
l
P
r
o
jec
t
P
lan
n
i
n
g
:
De
v
e
lo
p
in
g
a
P
r
o
jec
t
De
li
v
e
ry
S
trate
g
y
,”
Bu
tt
e
rwo
rth
-
He
in
e
ma
n
n
,
2
0
1
1
[
9
]
C.
A
rti
g
u
e
s,
S
.
De
m
a
s
se
y
,
E.
Ne
ro
n
,
“
Re
so
u
rc
e
-
Co
n
stra
i
n
e
d
P
ro
j
e
c
t
S
c
h
e
d
u
li
n
g
:
M
o
d
e
ls,
A
lg
o
rit
h
m
s,
Ex
ten
sio
n
s
a
n
d
A
p
p
li
c
a
ti
o
n
s
,”
J
o
h
n
W
il
e
y
&
S
o
n
s
,
2
0
1
3
[
1
0
]
R.
Kle
in
,
“
S
c
h
e
d
u
l
in
g
o
f
Re
so
u
rc
e
-
Co
n
stra
in
e
d
P
ro
jec
ts
,”
S
p
ri
n
g
e
r
S
c
ien
c
e
&
Bu
sin
e
ss
M
e
d
ia
,
2
0
1
2
[
1
1
]
C.
Eb
e
rt
a
n
d
H.
S
o
u
b
ra
,
"
F
u
n
c
ti
o
n
a
l
S
ize
Esti
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
S
o
f
twa
re
M
a
in
ten
a
n
c
e
,
"
in
IEE
E
S
o
ft
wa
re
,
v
o
l.
3
1
,
n
o
.
6
,
p
p
.
2
4
-
2
9
,
No
v
.
-
De
c
.
2
0
1
4
.
[
1
2
]
M
.
Jø
rg
e
n
se
n
,
"
R
e
lativ
e
Esti
m
a
ti
o
n
o
f
S
o
f
tw
a
re
De
v
e
lo
p
m
e
n
t
E
ff
o
rt:
It
M
a
tt
e
rs w
it
h
W
h
a
t
a
n
d
Ho
w Yo
u
Co
m
p
a
re
,
"
in
IEE
E
S
o
ft
w
a
re
,
v
o
l.
3
0
,
n
o
.
2
,
p
p
.
7
4
-
7
9
,
M
a
rc
h
-
A
p
ril
2
0
1
3
.
[
1
3
]
M
.
Jø
rg
e
n
se
n
,
"
W
h
a
t
W
e
Do
a
n
d
Do
n
'
t
Kn
o
w
a
b
o
u
t
S
o
f
twa
re
D
e
v
e
lo
p
m
e
n
t
E
ff
o
rt
Esti
m
a
ti
o
n
,
"
in
IEE
E
S
o
f
twa
re
,
v
o
l.
3
1
,
n
o
.
2
,
p
p
.
3
7
-
4
0
,
M
a
r.
-
A
p
r.
2
0
1
4
.
[
1
4
]
E.
M
o
r
o
z
o
f
f
,
"
Us
in
g
a
L
in
e
o
f
C
o
d
e
M
e
tri
c
to
Un
d
e
rsta
n
d
S
o
f
tw
a
re
Re
w
o
rk
,
"
in
IEE
E
S
o
ft
w
a
re
,
v
o
l.
2
7
,
n
o
.
1
,
p
p
.
72
-
7
7
,
Ja
n
.
-
F
e
b
.
2
0
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.