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
C
E)
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
,
p
p
.
3
0
6
0
~
3
0
6
7
I
SS
N:
2
0
8
8
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ec
e.
v
6
i
6
.
1
1
5
1
1
3060
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
So
ft
w
a
re Re
lia
bility Usin
g
SP
RT:
Burr Ty
pe III
Pr
o
cess
Mo
del
CH
.
S
m
it
ha
1
,
R.
Sa
t
y
a
P
ra
s
a
d
2
,
R.
K
ira
n K
u
m
a
r
3
1
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Krish
n
a
Un
iv
e
rsity
,
A
n
d
h
ra
P
r
a
d
e
sh
.
I
n
d
ia
2,
3
CS
E,
A
c
h
a
ry
a
Na
g
a
rju
n
a
Un
iv
e
rsit
y
,
A
n
d
h
ra
P
ra
d
e
sh
,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
1
,
2
0
1
6
R
ev
i
s
ed
A
u
g
1
8
,
2
0
1
6
A
cc
ep
ted
Sep
1
,
2
0
1
6
In
c
re
a
se
d
d
e
p
e
n
d
e
n
c
e
o
n
so
f
tw
a
re
s
y
ste
m
s
e
li
c
it
e
d
th
e
a
ss
e
ss
m
e
n
t
o
f
th
e
ir
re
li
a
b
il
it
y
,
a
c
ru
c
ial
tas
k
in
so
f
t
w
a
r
e
d
e
v
e
lo
p
m
e
n
t.
Eff
e
c
ti
v
e
to
o
ls
a
n
d
m
e
c
h
a
n
is
m
s
a
re
re
q
u
ired
t
o
f
a
c
il
it
a
te
th
e
a
ss
e
ss
m
e
n
t
o
f
so
f
t
w
a
re
re
li
a
b
il
it
y
.
Clas
sic
a
l
a
p
p
ro
a
c
h
e
s
li
k
e
h
y
p
o
th
e
sis
tes
ti
n
g
a
re
sig
n
if
ica
n
tl
y
ti
m
e
c
o
n
su
m
in
g
a
s
th
e
c
o
n
c
lu
sio
n
c
a
n
o
n
ly
b
e
d
ra
w
n
a
f
t
e
r
c
o
ll
e
c
ti
n
g
h
u
g
e
a
m
o
u
n
ts
o
f
d
a
ta.
S
tatisti
c
a
l
m
e
th
o
d
su
c
h
a
s
S
e
q
u
e
n
ti
a
l
A
n
a
l
y
sis
c
a
n
b
e
a
p
p
li
e
d
to
a
rriv
e
a
t
a
d
e
c
isio
n
q
u
ick
ly
.
T
h
is
p
a
p
e
r
im
p
lem
e
n
ted
S
e
q
u
e
n
ti
a
l
P
r
o
b
a
b
il
it
y
Ra
ti
o
T
e
st
(S
P
RT
)
f
o
r
Bu
rr
Ty
p
e
III
m
o
d
e
l
b
a
se
d
o
n
ti
m
e
d
o
m
a
in
d
a
ta.
F
o
r
t
h
is,
p
a
ra
m
e
ters
we
re
e
sti
m
a
t
e
d
u
sin
g
M
a
x
i
m
u
m
L
i
k
e
li
h
o
o
d
Esti
m
a
ti
o
n
to
a
p
p
ly
S
P
RT
o
n
f
iv
e
re
a
l
ti
m
e
so
f
t
w
a
r
e
f
a
il
u
re
d
a
tas
e
ts
b
o
rro
w
e
d
f
ro
m
d
i
ff
e
re
n
t
so
f
t
w
a
re
p
ro
jec
ts.
T
h
e
re
su
lt
s
e
x
e
m
p
li
fy
th
a
t
th
e
a
d
o
p
te
d
m
o
d
e
l
h
a
s
g
iv
e
n
a
n
a
c
c
e
p
tan
c
e
d
e
c
isio
n
f
o
r
th
e
u
se
d
d
a
tas
e
ts.
K
ey
w
o
r
d
:
B
u
r
r
ty
p
e
I
I
I
m
o
d
el
Ml
esti
m
atio
n
So
f
t
w
ar
e
f
a
ilu
r
e
d
ata
So
f
t
w
ar
e
r
eliab
ilit
y
T
im
e
d
o
m
ai
n
d
ata
Co
p
y
rig
h
t
©
2
0
1
6
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
:
C
H.
S
m
it
h
a
C
h
o
w
d
ar
y
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
P
.
B
.
Sid
d
h
ar
th
a
C
o
lle
g
e
o
f
A
r
t
s
&
Scie
n
ce
P
G.
C
e
n
tr
e,
Mo
g
h
alr
aj
p
u
r
a
m
,
Vij
a
y
a
w
ad
a,
An
d
h
r
a
P
r
ad
esh
-
5
2
0
0
1
0
,
I
n
d
i
a.
E
m
ail:
s
m
i
th
ac
s
c@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
So
f
t
w
ar
e
r
eliab
ilit
y
i
s
p
r
o
b
ab
ilit
y
o
f
f
au
l
t
f
r
ee
o
p
er
atio
n
s
p
r
o
v
id
ed
b
y
t
h
e
s
o
f
t
w
ar
e
p
r
o
d
u
ct
u
n
d
er
co
n
s
id
er
atio
n
o
v
er
a
s
p
ec
if
ied
p
er
io
d
o
f
tim
e
i
n
a
s
p
ec
if
ied
o
p
er
atio
n
al
en
v
ir
o
n
m
e
n
t
[
1
]
.
A
g
o
o
d
r
eliab
ilit
y
m
o
d
el
ca
n
p
r
ed
ict
s
o
f
t
w
ar
e
r
eliab
ilit
y
ac
tio
n
ac
cu
r
atel
y
,
an
d
th
is
is
o
f
g
r
ea
t
i
m
p
o
r
ta
n
ce
t
o
s
o
f
t
w
ar
e
r
eso
u
r
ce
allo
ca
tio
n
an
d
s
o
f
t
w
ar
e
m
ar
k
et
d
ec
is
io
n
m
a
k
in
g
[
2
]
.
Sin
c
e
1
9
7
0
s
,
r
esear
ch
o
n
s
o
f
t
w
ar
e
r
eliab
ilit
y
m
o
d
el
d
o
m
ai
n
g
r
ea
tl
y
i
m
p
r
o
v
ed
,
m
a
n
y
m
o
d
el
s
h
av
e
b
ee
n
p
u
t
in
to
p
r
ac
tice,
an
d
s
o
f
t
w
ar
e
r
eliab
ili
t
y
h
as
s
tep
p
ed
i
n
to
en
g
i
n
ee
r
i
n
g
s
tag
e
f
r
o
m
co
n
ce
p
tu
al
s
ta
g
e
[
3
]
.
C
o
n
s
id
er
in
g
t
esti
n
g
e
f
f
o
r
t
in
r
eliab
ilit
y
m
o
d
elin
g
p
r
o
ce
s
s
m
a
y
f
u
r
t
h
er
i
m
p
r
o
v
e
t
h
e
f
it
tin
g
an
d
p
r
ed
ictio
n
r
es
u
lts
o
f
s
o
f
t
w
ar
e
r
eliab
ilit
y
g
r
o
w
t
h
m
o
d
els
(
SR
G
Ms)
[
4
]
.
Ho
w
e
v
er
,
f
ac
i
n
g
i
n
cr
ea
s
i
n
g
c
o
m
p
le
x
it
y
o
f
s
o
f
t
w
ar
e
an
d
t
h
eir
d
ev
elo
p
m
en
t
co
u
r
s
e,
r
elia
b
ilit
y
m
o
d
els
s
till
ap
p
ea
r
to
h
av
e
in
h
er
e
n
t s
h
o
r
tco
m
in
g
s
[
5
]
.
So
f
t
w
ar
e
r
eliab
ilit
y
as
s
ess
m
e
n
t
n
ee
d
s
ef
f
ec
ti
v
e
to
o
ls
/
m
ec
h
an
is
m
s
.
I
n
clas
s
ical
H
y
p
o
t
h
es
is
T
esti
n
g
,
o
n
ce
th
e
e
n
tire
d
ata
h
as
b
ee
n
co
llected
,
th
e
an
al
y
s
i
s
is
d
o
n
e
an
d
co
n
clu
s
io
n
s
ar
e
d
r
a
w
n
.
I
f
class
ica
l
test
i
n
g
s
tr
ateg
ie
s
ar
e
u
s
ed
(
n
o
u
s
a
g
e
test
i
n
g
)
,
th
e
ap
p
licatio
n
o
f
s
o
f
t
w
ar
e
r
eliab
ilit
y
g
r
o
w
t
h
m
o
d
els
m
a
y
b
e
d
if
f
ic
u
lt
an
d
r
eliab
ilit
y
p
r
ed
ictio
n
s
ca
n
b
e
m
is
lead
i
n
g
.
Ho
w
e
v
er
s
tati
s
tical
m
et
h
o
d
s
ca
n
b
e
s
u
cc
ess
f
u
ll
y
ap
p
lied
to
th
e
f
ail
u
r
e
d
ata
[
6
]
.
Seq
u
en
tial
an
al
y
s
is
i
s
a
m
e
th
o
d
o
f
s
tat
is
tical
in
f
er
e
n
ce
w
h
er
e
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
r
eq
u
ir
ed
b
y
t
h
e
p
r
o
ce
d
u
r
e
is
n
o
t
d
eter
m
i
n
ed
i
n
ad
v
a
n
ce
o
f
th
e
ex
p
er
i
m
en
t.
T
h
e
d
ec
is
io
n
to
ter
m
i
n
ate
th
e
ex
p
er
i
m
e
n
t
d
ep
en
d
s
,
at
ea
ch
s
tag
e,
o
n
th
e
r
es
u
lt
s
o
f
t
h
e
o
b
s
er
v
atio
n
p
r
ev
io
u
s
l
y
m
ad
e.
A
m
er
it
o
f
s
eq
u
e
n
t
ial
m
et
h
o
d
,
as
ap
p
lied
to
test
i
n
g
s
tatis
ticall
y
a
h
y
p
o
t
h
esi
s
,
is
th
at
a
te
s
t
p
r
o
ce
d
u
r
e
ca
n
b
e
co
n
s
tr
u
cted
w
h
ic
h
r
eq
u
ir
es
o
n
av
er
a
g
e
a
s
m
all
n
u
m
b
er
o
f
o
b
s
er
v
a
tio
n
s
t
h
at
eq
u
all
y
te
s
t
t
h
e
r
eliab
ilit
y
o
f
t
h
e
p
r
o
ce
d
u
r
e
b
ased
o
n
a
p
r
ed
eter
m
in
ed
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
[
7
-
8
]
.
Sti
eb
er
‟
s
o
b
s
er
v
atio
n
s
ar
e
d
e
m
o
n
s
tr
ated
b
y
ap
p
ly
i
n
g
t
h
e
w
ell
-
k
n
o
w
n
Seq
u
e
n
tial
P
r
o
b
ab
ilit
y
R
atio
T
est
(
SP
R
T
)
o
f
W
ald
[
9
]
f
o
r
a
s
o
f
t
w
ar
e
f
ai
lu
r
e
d
ata
to
d
etec
t
u
n
r
eliab
le
s
o
f
t
w
ar
e
co
m
p
o
n
e
n
t
s
an
d
co
m
p
ar
e
th
e
r
eliab
ilit
y
o
f
d
i
f
f
er
e
n
t
s
o
f
t
w
ar
e
v
er
s
io
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
3061
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
o
ftw
a
r
e
R
elia
b
ilit
y
Usi
n
g
S
P
R
T:
B
u
r
r
Typ
e
I
I
I
P
r
o
ce
s
s
Mo
d
el
(
C
H.
S
mith
a
)
1
1
1
(
)
!
Nt
t
et
P
Nt
0
0
0
(
)
!
Nt
t
et
P
Nt
So
f
t
w
ar
e
r
eliab
ilit
y
a
n
al
y
s
i
s
n
ee
d
s
s
o
f
t
w
ar
e
f
ail
u
r
e
d
ata.
T
h
er
e
ar
e
tw
o
t
y
p
e
s
o
f
f
a
ilu
r
e
d
ata:
ti
m
e
-
d
o
m
ai
n
d
ata
an
d
in
ter
v
al
-
d
o
m
ai
n
d
ata.
T
h
e
tim
e
-
d
o
m
a
in
d
ata
r
ec
o
r
d
s
th
e
in
d
iv
id
u
al
ti
m
e
s
at
w
h
ic
h
th
e
f
ail
u
r
es
h
a
v
e
o
cc
u
r
r
ed
.
T
h
e
in
ter
v
al
-
d
o
m
ain
d
ata
co
u
n
ts
t
h
e
n
u
m
b
er
o
f
f
ail
u
r
es
o
cc
u
r
r
i
n
g
d
u
r
in
g
a
f
ix
ed
ti
m
e
p
er
io
d
.
W
ith
ex
i
s
ti
n
g
s
o
f
t
w
ar
e
r
eliab
ilit
y
m
o
d
els,
ti
m
e
-
d
o
m
a
in
d
ata
p
r
o
v
id
es b
etter
ac
cu
r
ac
y
i
n
th
e
e
s
ti
m
atio
n
o
f
p
ar
a
m
eter
s
,
b
u
t
in
v
o
lv
e
s
m
o
r
e
d
ata
co
llectio
n
e
f
f
o
r
ts
[
10
]
.
T
h
e
p
r
o
b
ab
ilit
y
eq
u
a
tio
n
o
f
t
h
e
s
to
ch
as
tic
p
r
o
ce
s
s
r
ep
r
esen
tin
g
th
e
f
ail
u
r
e
o
cc
u
r
r
en
ce
s
is
g
iv
e
n
b
y
a
h
o
m
o
g
e
n
eo
u
s
P
o
is
s
o
n
p
r
o
ce
s
s
with
t
h
e
ex
p
r
ess
io
n
.
[
(
)
]
[
]
(
)
(1
)
A
n
u
m
b
er
o
f
m
e
th
o
d
s
ar
e
e
x
ta
n
t
f
o
r
d
escr
ib
in
g
th
e
s
o
f
t
w
ar
e
r
eliab
ilit
y
b
ased
o
n
th
e
SP
R
T
[
1
1
]
-
[
1
3
]
.
T
h
is
p
ap
er
d
escr
ib
es
a
m
et
h
o
d
f
o
r
d
etec
tin
g
r
eliab
le
s
o
f
t
w
ar
e
b
ased
o
n
th
e
SP
R
T
,
u
s
i
n
g
Ma
x
i
m
u
m
L
i
k
eli
h
o
o
d
E
s
ti
m
atio
n
(
M
L
E
)
o
f
p
ar
am
eter
esti
m
a
tio
n
.
T
h
e
W
ald
‟
s
SP
R
T
p
r
o
ce
d
u
r
e
ca
n
b
e
u
s
ed
to
d
is
tin
g
u
is
h
t
h
e
s
o
f
t
w
ar
e
u
n
d
er
test
i
n
to
o
n
e
o
f
th
e
t
w
o
ca
teg
o
r
ies
lik
e
r
eliab
le/
u
n
r
eliab
le,
p
ass
/f
a
il
an
d
ce
r
ti
-
f
ied
/u
n
ce
r
ti
f
ied
[
14
]
.
SP
R
T
is
th
e
o
p
ti
m
al
s
ta
tis
t
ical
te
s
t
t
h
a
t
m
a
k
e
s
t
h
e
co
r
r
ec
t
d
ec
is
io
n
i
n
t
h
e
s
h
o
r
test
ti
m
e
a
m
o
n
g
all
test
s
th
at
ar
e
s
u
b
j
ec
t
to
th
e
s
a
m
e
le
v
el
o
f
d
ec
is
i
o
n
er
r
o
r
s
[
15
]
.
SP
R
T
is
u
s
ed
to
d
etec
t
th
e
f
au
lt
b
ased
o
n
th
e
ca
lcu
lated
lik
el
i
h
o
o
d
o
f
th
e
h
y
p
o
th
e
s
es.
W
e
co
n
s
id
er
o
n
e
o
f
t
h
e
p
o
p
u
lar
s
o
f
t
w
ar
e
r
eliab
ilit
y
g
r
o
w
t
h
m
o
d
el
B
u
r
r
T
y
p
e
I
I
I
an
d
ad
o
p
ted
th
e
p
r
in
cip
le
o
f
Sti
eb
er
[
6
]
in
d
etec
tin
g
w
h
et
h
er
th
e
s
o
f
t
w
ar
e
is
r
eliab
le
o
r
u
n
r
elia
b
le
in
o
r
d
er
t
o
ac
ce
p
t o
r
r
e
j
ec
t th
e
d
ev
elo
p
ed
s
o
f
t
w
ar
e.
T
h
e
th
eo
r
y
p
r
o
p
o
s
ed
b
y
Sti
eb
er
is
d
escr
ib
ed
in
Sectio
n
2
.
I
m
p
le
m
e
n
tat
io
n
o
f
SP
R
T
f
o
r
th
e
p
r
o
p
o
s
ed
B
u
r
r
ty
p
e
I
I
I
So
f
t
w
ar
e
R
eliab
i
lit
y
Gr
o
w
th
Mo
d
el
is
ill
u
s
tr
at
ed
in
Sectio
n
3
.
Ma
x
i
m
u
m
L
i
k
eli
h
o
o
d
esti
m
atio
n
m
et
h
o
d
is
u
s
ed
to
esti
m
ate
th
e
p
ar
am
eter
s
is
p
r
esen
ted
in
Se
ctio
n
4
.
A
p
p
licatio
n
o
f
th
e
d
ec
is
io
n
r
u
le
to
d
etec
t
th
e
u
n
r
eliab
le
s
o
f
t
w
ar
e
w
ith
r
ef
er
en
ce
to
th
e
So
f
t
w
ar
e
R
el
ia
b
ilit
y
Gr
o
w
th
Mo
d
el
B
u
r
r
T
y
p
e
I
I
I
is
d
ep
icted
i
n
Sectio
n
5
.
2.
WAL
D’
S
SE
Q
U
E
N
T
I
A
L
T
E
S
T
F
O
R
A
P
O
I
SS
O
N
P
RO
CE
SS
T
h
e
Seq
u
en
t
ial
P
r
o
b
ab
ilit
y
R
atio
T
est
(
SP
R
T
)
w
as
d
ev
elo
p
ed
b
y
A
b
r
ah
a
m
W
ald
a
t
C
o
lu
m
b
ia
Un
i
v
er
s
it
y
i
n
1
9
4
3
[
9
]
.
T
h
e
SP
R
T
p
r
o
ce
d
u
r
e
is
u
s
ed
f
o
r
q
u
alit
y
co
n
tr
o
l
s
t
u
d
ies
d
u
r
in
g
t
h
e
m
a
n
u
f
ac
t
u
r
in
g
o
f
s
o
f
t
w
ar
e
p
r
o
d
u
cts.
T
h
e
test
s
ca
n
b
e
p
er
f
o
r
m
ed
o
n
f
i
x
ed
s
a
m
p
le
s
ize
s
ets
w
ith
f
e
w
er
o
b
s
er
v
atio
n
s
.
T
h
e
SP
R
T
m
et
h
o
d
o
lo
g
y
f
o
r
Ho
m
o
g
en
eo
u
s
P
o
is
s
o
n
P
r
o
ce
s
s
is
d
escr
ib
e
d
b
elo
w
.
L
et
{
N(
t)
,
t
≥
0
}
b
e
a
h
o
m
o
g
en
eo
u
s
P
o
is
s
o
n
p
r
o
ce
s
s
w
it
h
r
ate
„
λ
‟
.
I
n
t
h
i
s
ca
s
e,
N(
t)
=
n
u
m
b
er
o
f
f
ail
u
r
es
u
p
to
ti
m
e
„
t
‟
an
d
„
λ
‟
is
th
e
f
ail
u
r
e
r
ate
(
f
ailu
r
es
p
er
u
n
it
ti
m
e)
.
I
f
th
e
s
y
s
te
m
i
s
p
u
t
o
n
test
an
d
th
at
if
w
e
w
a
n
t
to
esti
m
ate
it
s
f
ail
u
r
e
r
ate
„
λ
‟
.
W
e
ca
n
n
o
t
ex
p
ec
t
to
esti
m
ate
„
λ
‟
p
r
ec
is
el
y
.
B
u
t
we
w
a
n
t
to
r
ej
ec
t
th
e
s
y
s
te
m
w
it
h
a
h
ig
h
p
r
o
b
ab
ilit
y
i
f
th
e
d
ata
s
u
g
g
est
t
h
at
t
h
e
f
ail
u
r
e
r
ate
is
lar
g
er
th
a
n
λ
1
a
n
d
ac
ce
p
t
it
w
it
h
a
h
ig
h
p
r
o
b
ab
ilit
y
,
i
f
it
i
s
s
m
al
l
er
th
a
n
λ
0
.
Her
e
w
e
h
av
e
to
s
p
ec
if
y
t
w
o
(
s
m
all)
n
u
m
b
er
s
„
α
‟
an
d
„
β
‟
,
w
h
er
e
„
α
‟
is
th
e
p
r
o
b
ab
ilit
y
o
f
f
al
s
el
y
r
ej
ec
tin
g
t
h
e
s
y
s
te
m
.
T
h
at
is
r
ej
ec
tin
g
th
e
s
y
s
te
m
ev
e
n
i
f
λ
≤
λ
0
.
T
h
is
is
t
h
e
“
p
r
o
d
u
ce
r
‟
s
”
r
is
k
.
„
β
‟
i
s
t
h
e
p
r
o
b
ab
ilit
y
o
f
f
alse
l
y
ac
ce
p
tin
g
th
e
s
y
s
te
m
.
T
h
at
i
s
ac
ce
p
ti
n
g
th
e
s
y
s
te
m
e
v
e
n
i
f
λ
≤
λ
1
.
T
h
is
is
t
h
e
“
co
n
s
u
m
er
‟
s
”
r
is
k
.
W
ald
„
s
clas
s
ical
SP
R
T
is
v
er
y
s
en
s
iti
v
e
to
th
e
c
h
o
ice
o
f
r
elativ
e
r
is
k
r
eq
u
ir
ed
in
t
h
e
s
p
ec
if
icatio
n
o
f
t
h
e
alter
n
ati
v
e
h
y
p
o
t
h
esi
s
.
W
ith
th
e
clas
s
ical
SP
R
T
,
test
s
ar
e
p
er
f
o
r
m
ed
co
n
tin
u
o
u
s
l
y
a
t
ev
er
y
t
i
m
e
p
o
in
t
as
t
>
0
ad
d
itio
n
al
d
ata
ar
e
co
llected
.
W
ith
s
p
ec
if
ied
ch
o
ices
o
f
λ
0
an
d
λ
1
s
u
c
h
t
h
at
0
<
λ
0
<
λ
1
,
th
e
p
r
o
b
ab
ilit
y
o
f
f
i
n
d
in
g
N(
t)
f
a
ilu
r
es
in
t
h
e
ti
m
e
s
p
an
(
0
,
t)
w
ith
λ
1
,
λ
0
as
t
h
e
f
ail
u
r
e
r
ates a
r
e
r
esp
ec
tiv
el
y
g
i
v
en
b
y
(2
)
(3
)
T
h
e
r
atio
at
a
n
y
ti
m
e
‟
t
‟
i
s
co
n
s
id
er
ed
as a
m
ea
s
u
r
e
o
f
d
ec
i
d
in
g
t
h
e
tr
u
t
h
to
w
ar
d
s
or
,
g
i
v
e
n
a
s
eq
u
e
n
ce
o
f
ti
m
e
i
n
s
tan
ts
s
a
y
an
d
t
h
e
co
r
r
esp
o
n
d
in
g
r
ea
liza
tio
n
s
o
f
N(
t)
.
Si
m
p
li
f
icatio
n
o
f
g
i
v
es
1
0
P
P
0
1
1
2
3
........
K
t
t
t
t
12
(
)
,
(
)
,
.
.
.
.
.
.
.
.
(
)
K
N
t
N
t
N
t
1
0
P
P
11
01
00
e
x
p
(
)
Nt
P
t
P
Evaluation Warning : The document was created with Spire.PDF for Python.
3062
I
SS
N:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
3
0
6
0
–
3
067
1
0
P
A
P
1
0
P
B
P
1
0
P
BA
P
T
h
e
d
ec
is
io
n
r
u
le
o
f
SP
R
T
is
to
d
ec
id
e
in
f
a
v
o
r
o
f
,
in
f
av
o
r
o
f
o
r
to
co
n
tin
u
e
b
y
o
b
s
er
v
in
g
th
e
n
u
m
b
er
o
f
f
ail
u
r
es
at
a
lat
er
ti
m
e
th
a
n
'
t
'
ac
co
r
d
in
g
a
s
is
g
r
ea
ter
th
an
o
r
eq
u
al
to
a
co
n
s
tan
t
s
a
y
A
,
le
s
s
th
an
o
r
eq
u
al
to
a
co
n
s
ta
n
t
s
a
y
B
o
r
in
b
et
w
ee
n
t
h
e
co
n
s
tan
t
s
A
a
n
d
B
.
T
h
at
is
,
w
e
d
ec
id
e
th
e
g
i
v
e
n
s
o
f
t
w
ar
e
p
r
o
d
u
ct
as
u
n
r
eliab
le,
r
eliab
le
o
r
co
n
tin
u
e
[
1
6
]
th
e
test
p
r
o
ce
s
s
w
i
th
o
n
e
m
o
r
e
o
b
s
er
v
ati
o
n
in
f
a
ilu
r
e
d
ata,
ac
co
r
d
in
g
to
(4
)
(5
)
(6
)
T
h
e
ap
p
r
o
x
i
m
ate
v
a
lu
e
s
o
f
t
h
e
co
n
s
tan
ts
A
a
n
d
B
ar
e
tak
en
as
, B
w
h
er
e
„
‟
a
n
d
„
‟
ar
e
t
h
e
r
is
k
p
r
o
b
ab
ilit
ies
as
d
ef
i
n
ed
ea
r
lier
.
A
s
i
m
p
l
if
ied
v
er
s
io
n
o
f
t
h
e
a
b
o
v
e
d
ec
is
io
n
p
r
o
ce
s
s
es is
t
o
r
ej
ec
t th
e
s
y
s
te
m
as
u
n
r
eliab
le
i
f
N(
t)
f
all
s
f
o
r
th
e
f
ir
s
t ti
m
e
ab
o
v
e
th
e
li
n
e
(
7
)
T
o
ac
ce
p
t th
e
s
y
s
te
m
to
b
e
r
eliab
le
if
N(
t)
f
all
s
f
o
r
th
e
f
ir
s
t ti
m
e
b
elo
w
t
h
e
li
n
e
(
8
)
T
o
co
n
tin
u
e
t
h
e
tes
t
w
i
th
o
n
e
m
o
r
e
o
b
s
er
v
atio
n
o
n
(
t,
N(
t)
)
as
th
e
r
an
d
o
m
g
r
ap
h
o
f
[
t,
N(
t)
]
is
b
et
w
ee
n
t
h
e
t
w
o
li
n
ea
r
b
o
u
n
d
ar
ies
g
iv
e
n
b
y
eq
u
atio
n
s
(
7
)
an
d
(
8
)
w
h
er
e
(
9
)
(
10
)
(
11
)
T
h
e
p
ar
am
eter
s
,
an
d
ca
n
b
e
ch
o
s
en
in
s
ev
er
al
w
a
y
s
.
O
n
e
w
a
y
s
u
g
g
es
ted
b
y
Sti
eb
er
is
1
0
1
0
P
P
2
.
U
N
t
a
t
b
1
.
L
N
t
a
t
b
10
1
0
l
o
g
a
1
1
0
1
l
o
g
l
o
g
b
2
1
0
1
l
o
g
l
o
g
b
,
0
1
Evaluation Warning : The document was created with Spire.PDF for Python.
3063
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
o
ftw
a
r
e
R
elia
b
ilit
y
Usi
n
g
S
P
R
T:
B
u
r
r
Typ
e
I
I
I
P
r
o
ce
s
s
Mo
d
el
(
C
H.
S
mith
a
)
,
I
f
λ
0
a
n
d
λ
1
ar
e
ch
o
s
e
n
i
n
t
h
is
w
a
y
,
t
h
e
s
lo
p
e
o
f
NU
(
t)
a
n
d
NL
(
t)
eq
u
al
s
λ
.
T
h
e
o
th
er
t
wo
w
a
y
s
o
f
ch
o
o
s
in
g
λ
0
an
d
λ
1
ar
e
f
r
o
m
p
ast
p
r
o
j
ec
ts
(
f
o
r
a
co
m
p
ar
is
o
n
o
f
t
h
e
p
r
o
j
ec
ts
)
an
d
f
r
o
m
p
ar
t
o
f
th
e
d
ata
to
co
m
p
ar
e
t
h
e
r
eliab
ilit
y
o
f
d
if
f
e
r
en
t f
u
n
c
tio
n
al
ar
ea
s
(
co
m
p
o
n
en
ts
)
.
3.
SE
Q
U
E
NT
I
A
L
T
E
ST
F
O
R
SO
F
T
WAR
E
R
E
L
I
AB
I
L
I
T
Y
G
RO
W
T
H
M
O
DE
L
S
W
e
k
n
o
w
th
at
f
o
r
an
y
P
o
is
s
o
n
p
r
o
ce
s
s
,
th
e
e
x
p
ec
ted
v
al
u
e
o
f
N(
t)
=
λ
(
t)
ca
lled
th
e
av
er
ag
e
n
u
m
b
er
o
f
f
ail
u
r
es e
x
p
er
ien
ce
d
in
ti
m
e
'
t
'
.
W
h
ic
h
is
al
s
o
ca
lled
th
e
m
ea
n
v
al
u
e
f
u
n
ctio
n
o
f
t
h
e
P
o
is
s
o
n
p
r
o
ce
s
s
.
On
t
h
e
o
th
er
h
a
n
d
if
w
e
co
n
s
id
er
a
P
o
is
s
o
n
p
r
o
ce
s
s
w
it
h
a
g
en
er
al
f
u
n
ctio
n
(
n
o
t
n
ec
ess
ar
il
y
li
n
ea
r
)
m
(
t)
as
i
ts
m
ea
n
v
alu
e
f
u
n
c
tio
n
t
h
e
p
r
o
b
ab
ilit
y
eq
u
atio
n
o
f
a
s
u
c
h
a
p
r
o
ce
s
s
is
Dep
en
d
in
g
o
n
t
h
e
f
o
r
m
s
o
f
m
(
t)
w
e
g
e
t
v
ar
io
u
s
P
o
is
s
o
n
p
r
o
ce
s
s
es
ca
lled
NHP
P
,
f
o
r
th
e
B
u
r
r
T
y
p
e
I
I
I
m
o
d
el.
T
h
e
m
ea
n
v
a
lu
e
f
u
n
ctio
n
is
g
iv
e
n
as
(
)
[
]
I
t
ca
n
also
b
e
w
r
itte
n
as
w
h
er
e
m
1
(
t)
,
m
0
(
t)
r
ep
r
esen
t
s
t
h
e
m
ea
n
v
al
u
e
f
u
n
ctio
n
o
f
s
ta
ted
p
ar
a
m
eter
s
i
n
d
icati
n
g
r
eliab
le
s
o
f
t
w
ar
e
a
n
d
u
n
r
eli
ab
le
s
o
f
t
war
e
r
esp
ec
tiv
el
y
.
T
h
e
m
ea
n
v
alu
e
f
u
n
ctio
n
m
(
t)
co
m
p
r
is
e
s
th
e
p
ar
a
m
eter
s
„
a‟
,
„
b
‟
a
n
d
„
c
‟
.
T
h
e
t
w
o
s
p
ec
i
f
i
ca
tio
n
s
o
f
N
HP
P
f
o
r
b
a
r
e
co
n
s
id
er
ed
as
b
0
,
b
1
w
h
er
e
(
b
0
<
b
1
)
an
d
tw
o
s
p
ec
if
icatio
n
s
o
f
c
s
a
y
c
0
,
c
1
w
h
er
e
(
c
0
<
c
1
)
.
Fo
r
o
u
r
p
r
o
p
o
s
ed
m
o
d
el,
m
(
t)
at
b
1
is
s
aid
to
b
e
g
r
ea
ter
th
an
b
0
an
d
m
(
t)
at
c
1
is
s
aid
to
b
e
g
r
ea
ter
th
an
c
0
.
T
h
e
s
am
e
ca
n
b
e
d
e
n
o
ted
s
y
m
b
o
licall
y
a
s
m
0
(
t)
<
m
1
(
t)
.
T
h
e
i
m
p
le
m
en
ta
tio
n
o
f
SP
R
T
p
r
o
c
ed
u
r
e
is
illu
s
tr
ated
b
elo
w
.
S
y
s
te
m
i
s
s
aid
to
b
e
r
eliab
le
an
d
ca
n
b
e
ac
ce
p
ted
if
i.e
.
,
i.e
.
,
(1
2
)
S
y
s
te
m
i
s
s
aid
to
b
e
u
n
r
eliab
le
an
d
r
ej
ec
ted
if
0
.
l
o
g
1
q
q
1
.
l
o
g
1
q
q
q
1
0
w
h
e
r
e
q
()
()
(
)
.
,
0
,
1
,
2
,
!
y
mt
mt
P
N
t
Y
e
y
y
1
()
()
1
1
.
(
)
(
)
!
Nt
mt
e
m
t
P
Nt
0
()
()
0
0
.
(
)
(
)
!
Nt
mt
e
m
t
P
Nt
1
0
P
B
P
1
0
()
()
1
()
()
0
.
(
)
.
(
)
Nt
mt
Nt
mt
e
m
t
B
e
m
t
10
10
l
o
g
(
)
(
)
1
()
l
o
g
(
)
l
o
g
(
)
m
t
m
t
Nt
m
t
m
t
Evaluation Warning : The document was created with Spire.PDF for Python.
3064
I
SS
N:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
3
0
6
0
–
3
067
i.e
.
,
(
1
3)
C
o
n
ti
n
u
e
th
e
te
s
t p
r
o
ce
d
u
r
e
as lo
n
g
as
(
1
4
)
Su
b
s
ti
tu
t
in
g
th
e
ap
p
r
o
p
r
iate
e
x
p
r
ess
io
n
s
o
f
th
e
r
esp
ec
tiv
e
m
ea
n
v
al
u
e
f
u
n
c
tio
n
,
w
e
g
et
t
h
e
r
esp
ec
tiv
e
d
ec
is
io
n
r
u
le
s
an
d
ar
e
g
i
v
en
i
n
f
o
llo
w
in
g
s
li
n
e
s
.
A
cc
ep
ta
n
ce
R
e
g
io
n
(
)
(
)
(
(
)
(
)
)
[
(
)
(
)
]
(1
5
)
R
ej
ec
tio
n
R
eg
io
n
:
(
)
(
)
(
(
)
(
)
)
[
(
)
(
)
]
(
16
)
C
o
n
ti
n
u
atio
n
R
eg
io
n
:
(
)
(
(
)
(
)
)
[
(
)
(
)
]
(
)
(
)
(
(
)
(
)
)
[
(
)
(
)
]
(
17
)
Fo
r
th
e
s
p
ec
if
ied
m
o
d
el,
it
m
a
y
b
e
o
b
s
er
v
ed
th
at
th
e
d
ec
is
io
n
r
u
les
ar
e
ex
cl
u
s
i
v
el
y
b
as
ed
o
n
th
e
s
tr
en
g
th
o
f
th
e
s
eq
u
e
n
tia
l
p
r
o
ce
d
u
r
e
(
α
,
β)
an
d
th
e
v
alu
e
o
f
th
e
m
ea
n
v
al
u
e
f
u
n
c
tio
n
s
n
a
m
el
y
m
0
(
t)
m
1
(
t)
.
A
s
d
escr
ib
ed
b
y
S
tieb
er
,
th
ese
d
ec
is
io
n
r
u
les
b
ec
o
m
e
d
ec
is
io
n
li
n
es
if
th
e
m
ea
n
v
al
u
e
f
u
n
ctio
n
is
l
in
ea
r
i
n
p
ass
in
g
t
h
r
o
u
g
h
o
r
ig
i
n
,
t
h
at
is
m
(
t)
=
λ
t.
T
h
e
eq
u
atio
n
s
(
1
2
)
an
d
(
1
3
)
ar
e
c
o
n
s
id
er
ed
as
g
en
er
aliza
tio
n
s
f
o
r
th
e
d
ec
is
io
n
p
r
o
ce
d
u
r
e
o
f
Sti
eb
er
.
SP
R
T
p
r
o
ce
d
u
r
e
is
ap
p
lied
o
n
liv
e
s
o
f
t
w
ar
e
f
ail
u
r
e
d
ata
s
ets
an
d
t
h
e
r
esu
lt
s
th
at
w
er
e
an
al
y
ze
d
ar
e
illu
s
tr
at
ed
in
Sectio
n
5
.
4.
P
ARAM
E
T
E
R
E
ST
I
M
AT
I
O
N
W
e
p
r
esen
t
ex
p
r
ess
io
n
s
f
o
r
t
h
e
p
ar
am
eter
e
s
ti
m
ates
o
f
t
h
e
B
u
r
r
t
y
p
e
I
I
I
m
o
d
el.
P
ar
am
eter
esti
m
atio
n
is
v
er
y
s
i
g
n
i
f
ica
n
t
in
s
o
f
t
w
ar
e
r
eliab
ilit
y
p
r
ed
ictio
n
.
O
n
ce
t
h
e
a
n
al
y
tical
s
o
lu
t
io
n
f
o
r
m
is
k
n
o
w
n
f
o
r
a
g
i
v
e
n
m
o
d
el,
p
ar
a
m
eter
est
i
m
a
tio
n
is
ac
h
ie
v
ed
b
y
ap
p
l
y
in
g
a
w
e
ll
-
k
n
o
w
n
esti
m
at
io
n
,
Ma
x
i
m
u
m
L
ik
eli
h
o
o
d
E
s
ti
m
a
tio
n
(
M
L
E
)
.
T
h
e
m
ai
n
id
ea
b
eh
in
d
Ma
x
i
m
u
m
L
ik
elih
o
o
d
p
ar
am
eter
ass
e
s
s
m
e
n
t
is
to
d
ec
id
e
t
h
e
p
ar
am
eter
s
t
h
at
m
a
x
i
m
ize
t
h
e
p
r
o
b
ab
ilit
y
(
li
k
eli
h
o
o
d
)
o
f
th
e
s
p
ec
i
m
en
d
ata.
I
n
th
e
o
th
er
w
o
r
d
s
,
ML
E
m
et
h
o
d
s
ar
e
v
er
s
atile
a
n
d
ap
p
licab
le
to
m
o
s
t
m
o
d
els
a
n
d
f
o
r
d
if
f
er
e
n
t
t
y
p
e
s
o
f
d
ata.
H
er
e
p
ar
am
eter
s
ar
e
esti
m
ated
f
r
o
m
t
h
e
ti
m
e
d
o
m
ai
n
d
ata
[
1
7
]
.
T
h
e
m
ea
n
v
a
lu
e
f
u
n
ctio
n
o
f
B
u
r
r
t
y
p
e
I
I
I
m
o
d
el
is
g
iv
e
n
b
y
(
)
[
]
t>0
a,
b
,
c
>
0
(
18
)
1
0
P
A
P
10
10
1
l
o
g
(
)
(
)
()
l
o
g
(
)
l
o
g
(
)
m
t
m
t
Nt
m
t
m
t
1
0
1
0
1
0
1
0
1
l
o
g
(
)
(
)
l
o
g
(
)
(
)
1
()
l
o
g
(
)
l
o
g
(
)
l
o
g
(
)
l
o
g
(
)
m
t
m
t
m
t
m
t
Nt
m
t
m
t
m
t
m
t
Evaluation Warning : The document was created with Spire.PDF for Python.
3065
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
o
ftw
a
r
e
R
elia
b
ilit
y
Usi
n
g
S
P
R
T:
B
u
r
r
Typ
e
I
I
I
P
r
o
ce
s
s
Mo
d
el
(
C
H.
S
mith
a
)
T
h
e
p
ar
am
eter
s
a,
b
,
c
ar
e
es
ti
m
ated
w
it
h
Ma
x
i
m
u
m
L
i
k
el
ih
o
o
d
(
ML
)
esti
m
atio
n
.
T
h
e
lik
eli
h
o
o
d
f
u
n
ctio
n
f
o
r
ti
m
e
d
o
m
ai
n
d
ata
is
g
i
v
e
n
b
y
∑
[
(
)
]
(
)
(
19
)
Su
b
s
ti
tu
t
in
g
E
q
u
atio
n
(
18
)
in
eq
u
atio
n
(
19
)
w
e
g
et
[
]
∑
(
)
∑
[
(
)
(
)
(
)
]
(
20
)
T
ak
in
g
t
h
e
P
ar
tial d
er
iv
ativ
e
w
it
h
r
esp
ec
t to
„
a
‟
an
d
eq
u
at
in
g
to
„
0
‟
.
(
)
(
21
)
T
ak
in
g
t
h
e
P
ar
tial d
er
iv
ativ
e
w
it
h
r
esp
ec
t to
„
b
‟
an
d
eq
u
ati
n
g
to
„
0
‟
.
∑
(
)
(
)
(
2
2
)
T
h
e
p
ar
am
eter
„
c
‟
is
e
s
ti
m
ated
b
y
iter
ati
v
e
Ne
w
to
n
-
R
ap
h
s
o
n
Me
th
o
d
u
s
i
n
g
(
)
(
)
w
h
er
e
g
(
c)
an
d
g
‟
(
c)
ar
e
ex
p
r
ess
ed
as f
o
llo
w
s
.
(
)
(
)
∑
[
]
(
23
)
(
)
(
)
(
)
∑
(
)
(
)
(
24
)
5.
SPRT AN
A
L
Y
SI
S O
F
L
I
V
E
DATAS
E
T
S
SP
R
T
m
eth
o
d
o
lo
g
y
i
s
ap
p
lied
o
n
f
i
v
e
d
i
f
f
er
en
t
d
ata
s
e
ts
th
at
ar
e
b
o
r
r
o
w
ed
f
r
o
m
p
h
a
m
[
1
8
]
,
l
y
u
[
1
9
]
an
d
SON
A
T
A
[
2
0
]
s
o
f
t
w
ar
e
s
er
v
ices.
T
h
e
d
ec
is
io
n
s
ar
e
ev
alu
a
ted
b
ased
o
n
th
e
co
n
s
i
d
er
ed
m
ea
n
v
al
u
e
f
u
n
ctio
n
(
1
8
)
.
B
ased
o
n
t
h
e
e
s
ti
m
ates
o
f
t
h
e
p
ar
a
m
eter
s
„
b
‟
a
n
d
„
c‟
i
n
ea
c
h
m
ea
n
v
a
lu
e
f
u
n
c
tio
n
,
w
e
h
av
e
ch
o
s
en
th
e
s
p
ec
if
icatio
n
s
o
f
b
0
=
b
–
δ,
b
1
=
b
–
δ a
n
d
c
0
= c
–
δ,
c
1
= c
–
δ,
an
d
ap
p
l
y
SP
R
T
s
u
ch
t
h
at
b
0
<
b
<
b
1
an
d
c
0
< c < c
1
.
A
s
s
u
m
in
g
t
h
e
δ v
al
u
e
o
f
0
.
6
th
e
ch
o
ice
s
a
r
e
g
iv
e
n
in
T
ab
le
1
.
Usi
n
g
t
h
e
s
p
ec
i
f
icatio
n
b
0
,
b
1
,
an
d
c
0
,
c
1
th
e
m
ea
n
v
al
u
e
f
u
n
ctio
n
s
m
0
(
t)
an
d
m
1
(
t)
ar
e
co
m
p
u
ted
f
o
r
ea
ch
„
t
‟
.
L
ater
t
h
e
d
ec
is
io
n
s
a
r
e
m
ad
e
b
ased
o
n
th
e
d
ec
is
io
n
r
u
les
s
p
ec
i
f
ied
b
y
th
e
eq
u
ati
o
n
s
(
1
5
)
,
(
1
6
)
,
(
1
7
)
f
o
r
th
e
d
ata
s
e
ts
.
At
ea
c
h
„
t
‟
o
f
th
e
d
ata
s
et,
th
e
s
tr
e
n
g
th
s
(
α
,
β)
ar
e
co
n
s
id
er
ed
as (
0
.
3
,
0
.
3
)
.
SP
R
T
p
r
o
ce
d
u
r
e
is
ap
p
lied
o
n
f
iv
e
d
if
f
er
en
t d
ata
s
ets an
d
th
e
n
ec
es
s
ar
y
ca
lc
u
lati
o
n
s
ar
e
g
i
v
en
i
n
T
ab
le
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
3066
I
SS
N:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
3
0
6
0
–
3
067
T
ab
le
1
.
E
s
tim
a
tes o
f
a,
b
,
c
&
Sp
ec
if
icatio
n
s
o
f
b
0
, b
1
, c
0
, c
1
D
a
t
a
se
t
s
Est
i
m
a
t
e
o
f
'a'
Est
i
m
a
t
e
o
f
'b
'
b
0
b
1
Est
i
m
a
t
e
o
f
'c'
c
0
c
1
N
T
D
S
3
4
.
4
6
5
7
0
6
1
.
7
6
3
6
4
7
1
.
1
6
3
6
4
7
2
.
3
6
3
6
4
7
1
.
8
1
0
2
2
2
1
.
2
1
0
2
2
2
2
.
4
1
0
2
2
2
A
T&
T
2
6
.
8
3
9
8
2
9
1
.
6
5
8
6
9
2
1
.
0
5
8
6
9
2
2
.
2
5
8
6
9
2
1
0
.
4
1
.
6
S
O
N
A
TA
7
9
.
8
3
1
3
5
9
6
.
7
4
2
8
1
6
.
1
4
2
8
1
7
.
3
4
2
8
1
0
.
6
0
2
4
4
0
.
0
0
2
4
4
1
.
2
0
2
4
4
X
I
E
3
3
.
3
1
0
4
2
6
2
.
2
7
0
0
9
5
1
.
6
7
0
0
9
5
2
.
8
7
0
0
9
5
1
.
3
7
1
9
7
4
0
.
7
7
1
9
7
4
1
.
9
7
1
9
7
4
I
B
M
2
0
.
6
2
4
7
8
5
1
.
7
1
1
6
3
1
.
1
1
1
6
3
2
.
3
1
1
6
3
1
.
4
4
7
8
1
5
0
.
8
4
7
8
1
5
2
.
0
4
7
8
1
5
T
ab
le
2
.
SP
R
T
A
n
al
y
s
i
s
f
o
r
5
Data
Sets
D
a
t
a
S
e
t
T
N
(
t
)
R
.
H
.
S
.
o
f
e
q
u
a
t
i
o
n
(
1
5
)
A
c
c
e
p
t
a
n
c
e
r
e
g
i
o
n
(
≤
)
R
.
H
.
S
.
o
f
e
q
u
a
t
i
o
n
(
1
6
)
R
e
j
e
c
t
i
o
n
r
e
g
i
o
n
(
≥
)
D
e
c
i
si
o
n
N
T
D
S
9
1
2
2
.
1
6
9
8
3
8
3
2
2
.
7
9
0
9
0
2
4
4
7
A
C
C
EPT
A
T
&
T
5
.
5
1
3
.
7
9
8
8
4
5
2
4
6
2
.
8
4
3
0
0
6
4
6
A
C
C
EPT
SON
A
T
A
5
2
.
5
1
1
6
.
8
0
9
9
1
8
1
2
.
2
3
8
7
2
0
6
6
6
A
C
C
EPT
XI
E
3
0
.
0
2
1
3
.
4
8
8
3
4
5
9
5
8
2
.
2
7
4
0
6
1
3
9
5
A
C
C
EPT
I
B
M
10
1
4
.
0
6
1
2
6
5
7
2
8
1
.
6
7
0
4
0
8
7
2
2
A
C
C
EPT
I
t
m
a
y
b
e
n
o
ted
t
h
at
t
h
e
d
ec
is
io
n
is
o
b
tai
n
ed
in
s
i
g
n
i
f
ican
t
l
y
les
s
er
n
u
m
b
er
o
f
i
ter
atio
n
s
N(
t)
in
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
w
h
e
n
d
r
a
w
n
i
n
co
m
p
ar
is
io
n
w
ith
o
t
h
er
m
o
d
els [
1
1
]
b
ased
o
n
SP
R
T
.
6.
CO
NCLU
SI
O
N
T
h
e
SP
R
T
m
et
h
o
d
o
lo
g
y
f
o
r
t
h
e
p
r
o
p
o
s
ed
s
o
f
t
w
ar
e
r
eliab
ili
t
y
g
r
o
w
t
h
m
o
d
el
B
u
r
r
t
y
p
e
I
I
I
is
ap
p
lied
f
o
r
th
e
s
o
f
t
w
ar
e
f
ail
u
r
e
d
ata
s
ets.
Fro
m
t
h
e
o
b
s
er
v
at
io
n
w
e
ar
e
ab
le
to
co
m
e
to
a
co
n
c
lu
s
io
n
i
n
a
v
er
y
le
s
s
ti
m
e
r
eg
ar
d
i
n
g
t
h
e
r
eliab
ilit
y
o
r
u
n
r
e
liab
ilit
y
o
f
a
s
o
f
t
w
ar
e
p
r
o
d
u
ct.
T
h
e
r
esu
lts
o
b
tain
e
d
f
r
o
m
t
h
e
d
atasets
ex
e
m
p
li
f
y
t
h
at
t
h
e
m
o
d
el
h
a
s
g
iv
e
n
a
d
ec
is
io
n
o
f
ac
ce
p
tan
c
e
f
o
r
all
t
h
e
d
ata
s
e
ts
at
v
er
y
f
ir
s
t
ti
m
e
i
n
s
ta
n
ce
o
f
th
e
d
ata.
He
n
ce
,
w
e
m
a
y
co
n
c
lu
d
e
t
h
at,
b
y
ap
p
l
y
i
n
g
SP
R
T
o
n
d
ata
s
et
s
w
e
ca
n
co
m
e
to
a
n
ea
r
l
y
d
ec
is
io
n
o
f
r
eliab
le/u
n
r
eliab
le
o
f
s
o
f
t
w
ar
e
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
S
.
M
a
rin
o
s,
e
t
a
l.
,
“
I
m
p
o
rtan
t
M
il
e
sto
n
e
s
in
S
o
f
twa
re
R
e
li
a
b
il
it
y
M
o
d
e
li
n
g
,”
i
n
Pro
c
e
e
d
in
g
s
o
f
S
o
ft
w
a
re
En
g
i
n
e
e
rin
g
a
n
d
K
n
o
wle
d
g
e
E
n
g
i
n
e
e
rin
g
(
S
EKE
'
9
6
),
L
a
k
e
T
a
h
o
e
,
NV
,
p
p
.
3
4
5
-
3
5
2
,
1
9
9
6
.
[2
]
Re
b
e
ll
o
,
e
t
a
l
.
,
“
S
o
f
tw
a
re
s
y
st
e
m
re
li
a
b
il
it
y
a
n
d
sa
fe
t
y
a
ss
e
ss
m
e
n
t
:
A
n
e
x
ten
d
e
d
F
M
EA
a
p
p
ro
a
c
h
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Reli
a
b
il
it
y
a
n
d
S
a
fety
,
v
o
l/
issu
e
:
2
0
(4
)
,
p
p
.
3
6
6
-
3
8
0
,
2
0
1
0
.
[3
]
Y
.
Z
h
a
n
g
a
n
d
H
.
Ch
e
n
g
,
“
I
m
p
ro
v
e
d
Ge
n
e
ti
c
P
ro
g
ra
m
m
in
g
A
l
g
o
rit
h
m
A
p
p
li
e
d
to
S
y
m
b
o
li
c
Re
g
re
ss
io
n
a
n
d
S
o
f
tw
a
r
e
Re
li
a
b
il
it
y
M
o
d
e
li
n
g
,
”
S
o
ft
w
a
re
En
g
in
e
e
rin
g
&
Ap
p
li
c
a
t
io
n
s
,
v
o
l.
2
,
p
p
.
3
5
4
-
3
6
0
,
2
0
0
9
.
[4
]
Z
.
Qia
n
,
e
t
a
l.
,
“
S
o
f
tw
a
r
e
Re
li
a
b
il
it
y
M
o
d
e
li
n
g
w
it
h
T
e
stin
g
-
Eff
o
rt
F
u
n
c
ti
o
n
a
n
d
Im
p
e
rf
e
c
t
De
b
u
g
g
in
g
,
”
In
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
ol
/i
ss
u
e
:
10
(
8
)
,
p
p
.
1
9
9
2
-
1
9
9
8
,
2
0
1
2
.
[5
]
S.
J.
S
u
n
a
n
d
J.
X
iao
,
“
A
S
o
f
t
wa
re
Re
li
a
b
il
it
y
G
EP
M
o
d
e
l
Ba
se
d
o
n
Us
a
g
e
P
ro
f
il
e
,
”
T
EL
KOM
NIKA
,
v
ol
/i
ss
u
e
:
10
(
7
)
,
p
p
.
1
7
5
6
~
1
7
6
4
,
2
0
1
2
.
e
-
IS
S
N:
2
0
8
7
-
2
7
8
X
.
[6
]
H.
A
.
S
ti
e
b
e
r,
“
S
tatisti
c
a
l
Qu
a
li
t
y
Co
n
tro
l:
Ho
w
T
o
D
e
tec
t
Un
re
li
a
b
le
S
o
f
tw
a
r
e
Co
m
p
o
n
e
n
ts
,
”
Pro
c
e
e
d
in
g
s
th
e
8
t
h
In
ter
n
a
t
io
n
a
l
S
y
mp
o
si
u
m o
n
S
o
f
t
wa
re
Relia
b
il
it
y
E
n
g
i
n
e
e
rin
g
,
p
p
.
8
-
12
,
1
9
9
7
.
[7
]
Ca
rd
D.,
“
S
tatisti
c
a
l
P
r
o
c
e
ss
Co
n
t
ro
l
f
o
r
S
o
f
twa
re
,
”
IEE
E
S
o
ft
w
a
re
,
pp.
95
-
97
,
1
9
9
4
.
[8
]
J
.
D.
M
u
s
a
,
“
S
o
f
twa
re
Qu
a
l
it
y
a
n
d
Re
li
a
b
il
it
y
Ba
sic
s
,
”
AT
&
T
Bell
L
a
b
o
ra
t
o
rie
s
,
1
9
9
4
.
CH
2
4
6
8
-
7
/8
7
/0
0
0
0
/0
1
4
,
1
9
8
7
IEE
E.
[9
]
W
a
ld
A
.
,
“
S
e
q
u
e
n
ti
a
l
A
n
a
l
y
sis
,
”
Ne
w
I
m
p
re
ss
io
n
e
d
it
i
o
n
,
Ne
w
Yo
rk
,
Jo
h
n
W
il
e
y
a
n
d
S
o
n
,
I
n
c
,
1
9
4
7
.
[1
0
]
K.
B.
M
isra
,
“
Ha
n
d
b
o
o
k
o
f
P
e
rf
o
rm
a
b
il
it
y
En
g
in
e
e
ri
ng
,
”
S
p
rin
g
e
r
,
2
0
0
8
.
[1
1
]
R.
S
.
P
ra
sa
d
,
e
t
a
l.
,
“
S
o
f
tw
a
re
Re
li
a
b
il
it
y
u
sin
g
S
P
RT
:
L
o
g
P
o
w
e
r
M
o
d
e
l
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Cu
rr
e
n
t
Res
e
a
rc
h
a
n
d
Aca
d
e
mic
Rev
iew
,
v
ol
/i
ss
u
e
:
2
(
9
)
,
p
p
.
2
5
-
32
,
2
0
1
4
.
I
S
S
N:
2
3
4
7
-
3
2
1
5
.
[1
2
]
K.
V
.
M
.
M
o
h
a
n
,
e
t
a
l
.
,
“
De
tec
ti
o
n
o
f
Bu
rr
Ty
p
e
X
II
Re
li
a
b
le
S
o
f
tw
a
r
e
u
sin
g
S
e
q
u
e
n
ti
a
l
P
r
o
c
e
ss
Ra
ti
o
Tes
t
,
”
In
d
i
a
n
J
o
u
rn
a
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
ol
/i
ss
u
e
:
8
(
16
)
,
2
0
1
5
.
IS
S
N:
0
9
7
4
-
5
6
4
5
.
[1
3
]
S
.
D.
Ha
rit
h
a
a
n
d
R.
S
.
P
ra
sa
d
,
“
A
S
e
q
u
e
n
ti
a
l
P
ro
b
a
b
il
i
ty
Ra
t
io
T
e
st
in
A
ss
e
ss
in
g
S
o
f
t
w
a
re
Qu
a
li
ty
Us
in
g
LP
ET
M
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Ex
p
lo
ri
n
g
En
g
in
e
e
rin
g
,
v
ol
/i
ss
u
e
:
2
(
5
)
,
p
p
.
3
4
5
-
3
4
8
,
2
0
1
3
.
IS
S
N:
2
2
7
8
-
3
0
7
5
.
[1
4
]
Re
c
k
a
se
M
.
D.
,
“
A
P
ro
c
e
d
u
re
f
o
r
d
e
c
isio
n
m
a
k
in
g
u
sin
g
tai
lo
re
d
tes
ti
n
g
,”
i
n
W
e
iss
DJ
,
e
d
it
o
r
,
“
N
e
w
h
o
rizo
n
s
i
n
tes
ti
n
g
:
L
a
ten
t
trait
th
e
o
ry
a
n
d
c
o
m
p
u
teriz
e
d
a
d
a
p
ti
v
e
tes
ti
n
g
,”
Ne
w
Yo
rk
,
A
c
a
d
e
m
i
c
P
re
ss
,
p
p
.
2
3
7
–
54
,
1
9
8
3
.
[1
5
]
V.
G
o
u
th
a
m
a
n
d
R.
S
.
P
ra
sa
d
,
“
A
n
S
P
RT
P
ro
c
e
d
u
re
f
o
r
a
n
Un
g
ro
u
p
e
d
Da
ta
u
sin
g
M
M
L
E
Ap
p
r
o
a
c
h
,
”
IOS
R
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
(
IOS
R
-
J
CE)
,
v
ol
/i
ss
u
e
:
14
(
6
),
p
p
.
37
-
42
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
3067
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
o
ftw
a
r
e
R
elia
b
ilit
y
Usi
n
g
S
P
R
T:
B
u
r
r
Typ
e
I
I
I
P
r
o
ce
s
s
Mo
d
el
(
C
H.
S
mith
a
)
[1
6
]
R.
S
.
P
ra
sa
d
,
“
Ha
lf
L
o
g
isti
c
S
o
f
t
w
a
r
e
Re
li
a
b
il
it
y
G
ro
w
th
M
o
d
e
l
,”
[P
h
D T
h
e
sis]
,
In
d
ia
,
A
NU
,
2
0
0
7
.
[1
7
]
C.
S
.
C
h
o
w
d
a
ry
,
e
t
a
l.
,
“
Bu
rr
T
y
p
e
III
S
o
f
tw
a
re
R
e
li
a
b
il
it
y
G
ro
w
th
M
o
d
e
l,
”
IO
S
R
-
J
CE
,
v
ol
/i
ss
u
e
:
17
(
1
)
,
2
0
1
5
.
[1
8
]
P
h
a
m
H.
,
“
S
y
ste
m
S
o
f
t
w
a
r
e
Re
li
a
b
ility
,”
S
p
rin
g
e
r
,
2
0
0
6
.
[1
9
]
Ly
u
M
.
R.
,
“
T
h
e
Ha
n
d
b
o
o
k
o
f
so
f
twa
re
Re
li
a
b
il
it
y
e
n
g
in
e
e
r
in
g
,”
M
c
G
ra
wH
il
l
a
n
d
IEE
E
C
o
m
p
u
ter
S
o
c
iety
P
re
ss
,
1
9
9
5
.
IS
BN:
9
-
07
-
0
3
9
4
0
0
-
8.
[2
0
]
A
sh
o
k
a
M
.
,
“
Da
ta se
t
,”
Ba
n
g
a
lo
r
e
,
S
o
n
a
ta
S
o
f
tw
a
re
L
i
m
it
e
d
,
2
0
1
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
M
r
s.
Ch
.
S
m
it
h
a
C
h
o
w
d
a
r
y
re
c
e
iv
e
d
M
C
A
f
ro
m
Ka
k
a
ti
y
a
Un
iv
e
rsit
y
in
2
0
0
3
a
n
d
M
.
T
e
c
h
.
,
(Co
m
p
u
ter
S
c
ien
c
e
&
En
g
in
e
e
rin
g
)
f
ro
m
A
c
h
a
r
y
a
Na
g
a
rju
n
a
Un
iv
e
rsity
in
2
0
1
0
.
N
o
w
sh
e
is
p
u
rsu
i
n
g
P
h
.
D.,
i
n
Co
m
p
u
ter
S
c
ien
c
e
&
En
g
in
e
e
rin
g
f
ro
m
Kri
sh
n
a
Un
iv
e
rsity
a
s
P
a
rt
-
Ti
m
e
Re
se
a
rc
h
S
c
h
o
lar
u
n
d
e
r
th
e
g
u
id
a
n
c
e
o
f
Dr.
R.
S
a
t
y
a
P
ra
sa
d
a
n
d
c
o
g
u
id
e
Dr.R.
Kira
n
Ku
m
a
r.
H
e
r
re
se
a
rc
h
in
tere
st l
ies
in
S
o
f
twa
re
Re
li
a
b
il
it
y
En
g
in
e
e
rin
g
,
Da
ta W
a
re
h
o
u
si
n
g
a
n
d
Da
ta M
in
i
n
g
Dr
.
R
S
a
ty
a
Pr
a
sa
d
r
e
c
e
i
v
e
d
P
h
.
D.d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
in
th
e
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
in
2
0
0
7
f
ro
m
A
c
h
a
r
y
a
Na
g
a
rju
n
a
Un
iv
e
rsity
,
A
n
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
He
re
c
e
i
v
e
d
g
o
ld
m
e
d
a
l
f
ro
m
A
c
h
a
r
y
a
N
a
g
a
rju
n
a
Un
iv
e
rsit
y
f
o
r
h
is
o
u
tstan
d
in
g
p
e
rf
o
rm
a
n
c
e
in
m
a
ste
r‟s
d
e
g
re
e
.
H
e
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
A
ss
o
c
iat
e
P
r
o
f
e
ss
o
r
in
t
h
e
d
e
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
&
En
g
in
e
e
ri
n
g
,
A
c
h
a
r
y
a
Na
g
a
rju
n
a
Un
iv
e
rsit
y
.
He
p
e
rf
o
r
m
e
d
v
a
rio
u
s
a
c
a
d
e
m
ic
ro
les
li
k
e
p
ra
c
ti
c
a
l
e
x
a
m
in
e
r,
p
ro
jec
t
a
d
ju
d
ica
to
r,
e
x
tern
a
l
m
e
m
b
e
r
o
f
b
o
a
rd
o
f
e
x
a
m
in
e
rs
f
o
r
v
a
r
io
u
s
u
n
iv
e
rsiti
e
s
a
n
d
c
o
ll
e
g
e
s
in
a
n
d
a
ro
u
n
d
A
n
d
h
ra
P
ra
d
e
sh
.
H
e
re
c
e
i
v
e
d
Dr.
A
b
d
u
l
Ka
lam
L
i
f
e
T
i
m
e
Ac
h
iev
e
m
e
n
t
Aw
a
rd
f
o
r
h
is
re
m
a
rk
a
b
le
a
c
h
iev
e
m
e
n
ts
in
th
e
f
ield
o
f
T
e
a
c
h
in
g
,
Re
se
a
rc
h
a
n
d
P
u
b
li
c
a
ti
o
n
s.
His
c
u
rre
n
t
re
se
a
rc
h
is
f
o
c
u
se
d
o
n
S
o
f
tw
a
r
e
e
n
g
in
e
e
rin
g
,
Im
a
g
e
p
ro
c
e
ss
in
g
&
Da
tab
a
se
M
a
n
a
g
e
m
e
n
t
s
y
ste
m
.
He
h
a
s
p
u
b
li
sh
e
d
7
0
re
se
a
rc
h
p
a
p
e
rs i
n
Na
ti
o
n
a
l
&
In
tern
a
t
io
n
a
l
Jo
u
rn
a
ls
Dr
.
K
K
ira
n
k
u
m
a
r
is
a
A
ss
i
sta
n
t
p
ro
f
e
ss
o
r
in
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Krish
n
a
Un
iv
e
rsit
y
.
He
is
h
a
v
in
g
1
2
+
e
x
p
e
rien
c
e
in
T
e
a
c
h
in
g
a
n
d
c
o
ll
e
g
e
A
d
m
in
istratio
n
.
He
g
u
id
e
d
a
n
d
d
e
v
e
lo
p
e
d
m
a
n
y
to
o
ls
f
o
r
s
m
o
o
th
a
d
m
in
istratio
n
o
f
th
e
c
o
ll
e
g
e
.
He
is
h
a
v
in
g
m
o
re
th
a
n
2
5
p
u
b
li
c
a
ti
o
n
s
in
d
if
f
e
r
e
n
t
In
tern
a
ti
o
n
a
l
jo
u
rn
a
ls.
His
a
re
a
s
o
f
in
te
re
st
a
re
b
io
in
f
o
rm
a
ti
c
s,
d
a
ta
m
in
in
g
,
so
f
t
wa
r
e
e
n
g
in
e
e
rin
g
,
e
m
b
e
d
d
e
d
s
y
ste
m
s,
a
n
d
n
e
tw
o
rk
s
e
c
u
rit
y
.
H
e
is
g
u
id
in
g
th
e
P
h
D
sc
h
o
lars
,
w
h
o
a
re
d
o
in
g
re
se
a
rc
h
f
ro
m
re
p
u
ted
u
n
iv
e
rsiti
e
s.
Evaluation Warning : The document was created with Spire.PDF for Python.