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
5
5
~
2
862
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
7
i
5
.
pp
2
8
5
5
-
2
862
2855
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
A Nov
el
O
pti
m
i
z
a
tion tow
a
rds H
ig
her Reliabili
ty in
Predic
tive
M
o
delling
t
o
w
a
rds Co
de Re
usa
bilit
y
M
a
no
j
H
.
M
.
1
,
Na
nd
a
k
u
m
a
r
A.
N.
2
1
Ja
in
Un
iv
e
risty
,
Ba
n
g
a
lo
re
,
In
d
ia
2
De
p
t.
o
f
Co
m
p
u
ter S
c
ien
c
e
&
En
g
g
,
Ne
w
Ho
rizo
n
Co
ll
e
g
e
o
f
En
g
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
21
,
2
0
1
7
R
ev
i
s
ed
J
u
n
9
,
2
0
1
7
A
cc
ep
ted
Sep
t
11
,
2
0
1
7
A
lt
h
o
u
g
h
,
th
e
a
re
a
o
f
so
f
t
wa
re
e
n
g
in
e
e
rin
g
h
a
s
m
a
d
e
a
re
m
a
rk
a
b
le
p
ro
g
re
ss
in
las
t
d
e
c
a
d
e
b
u
t
th
e
re
is
les
s
a
tt
e
n
ti
o
n
t
o
w
a
rd
s
th
e
c
o
n
c
e
p
t
o
f
c
o
d
e
re
u
sa
b
il
it
y
in
th
is
re
g
a
rd
s.Co
d
e
re
u
sa
b
il
it
y
is
a
su
b
se
t
o
f
S
o
f
tw
a
r
e
Re
u
sa
b
il
it
y
w
h
ich
is
o
n
e
o
f
th
e
sig
n
a
tu
re
to
p
ics
in
so
f
t
w
a
r
e
e
n
g
in
e
e
rin
g
.
W
e
re
v
ie
w
th
e
e
x
isti
n
g
s
y
st
e
m
to
f
in
d
th
a
t
th
e
r
e
is
n
o
p
ro
g
re
ss
o
r
a
v
a
il
a
b
il
it
y
o
f
sta
n
d
a
rd
re
se
a
rc
h
a
p
p
ro
a
c
h
to
w
a
rd
c
o
d
e
r
e
u
sa
b
il
it
y
b
e
in
g
in
tro
d
u
c
e
d
i
n
las
t
d
e
c
a
d
e
.
He
n
c
e
,
th
is
p
a
p
e
r
i
n
tro
d
u
c
e
d
a
p
re
d
ictiv
e
f
ra
m
e
w
o
rk
th
a
t
is
u
se
d
f
o
r
o
p
ti
m
izin
g
th
e
p
e
rf
o
rm
a
n
c
e
o
f
c
o
d
e
re
u
sa
b
il
it
y
.
F
o
r
t
h
is
p
u
rp
o
se
,
w
e
in
tro
d
u
c
e
a
c
a
se
stu
d
y
o
f
n
e
a
r
re
a
l
-
ti
m
e
c
h
a
ll
e
n
g
e
a
n
d
in
v
o
lv
e
d
it
in
o
u
r
m
o
d
e
ll
in
g
.
W
e
a
p
p
ly
n
e
u
ra
l
n
e
t
wo
rk
a
n
d
Da
m
p
e
d
-
L
e
a
st
sq
u
a
re
a
l
g
o
rit
h
m
to
p
e
rf
o
r
m
o
p
ti
m
iza
ti
o
n
w
it
h
a
s
o
le
targ
e
t
to
c
o
m
p
u
te
a
n
d
e
n
su
r
e
h
ig
h
e
st
p
o
ss
ib
le
re
li
a
b
il
it
y
.
T
h
e
stu
d
y
o
u
tco
m
e
o
f
o
u
r
m
o
d
e
l
e
x
h
ib
it
s
h
ig
h
e
r
re
li
a
b
il
it
y
a
n
d
b
e
tt
e
r
c
o
m
p
u
tati
o
n
a
l
re
sp
o
n
se
ti
m
e
K
ey
w
o
r
d
s
:
C
o
d
e
r
eu
s
ab
ilit
y
Ob
j
ec
t o
r
ien
ted
p
r
o
g
r
am
m
i
n
g
Op
ti
m
izatio
n
So
f
t
w
ar
e
en
g
i
n
ee
r
in
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
:
Ma
n
o
j
H.
M
,
R
esear
ch
Sch
o
lar
,
Natio
n
al
C
h
u
n
g
C
h
e
n
g
Un
i
v
er
s
it
y
,
R
OC
J
ain
U
n
i
v
er
is
t
y
,
B
an
g
alo
r
e
,
I
n
d
ia
E
m
ail:
m
a
n
o
j
.
h
m
h
m
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
W
ith
t
h
e
ch
a
n
g
in
g
d
y
n
a
m
ics
o
f
th
e
c
lien
t
’
s
r
eq
u
ir
e
m
e
n
t,
th
e
m
eth
o
d
o
lo
g
ie
s
ad
o
p
ted
in
s
o
f
t
w
ar
e
p
r
o
j
ec
t
d
ev
elo
p
m
e
n
t
o
r
g
a
n
iza
tio
n
ar
e
co
n
s
i
s
ten
t
ch
a
n
g
in
g
in
o
r
d
er
to
k
ee
p
a
p
ac
e
w
ith
cu
r
r
en
t
d
e
m
a
n
d
s
.
A
lt
h
o
u
g
h
,
t
h
er
e
ar
e
ev
o
lu
ti
o
n
o
f
v
ar
io
u
s
u
p
d
ated
to
o
ls
,
te
ch
n
iq
u
e
s
,
an
d
tec
h
n
o
lo
g
ies
i
n
I
n
f
o
r
m
a
tio
n
T
ec
h
n
o
lo
g
y
,
b
u
t
ad
o
p
tio
n
o
f
all
th
ese
ar
e
ce
r
tain
l
y
n
o
t
co
s
t
ef
f
ec
ti
v
e
in
n
at
u
r
e
[
1
]
.
I
n
t
h
is
d
ir
ec
tio
n
,
co
d
e
r
eu
s
ab
ilit
y
p
la
y
s
a
co
n
tr
ib
u
t
o
r
y
r
o
le
in
in
tr
o
d
u
ci
n
g
ce
r
tain
s
o
f
t
w
ar
e
m
etr
ics
t
h
at
s
i
g
n
if
ica
n
tl
y
a
s
s
i
s
ts
i
n
u
p
g
r
ad
in
g
t
h
e
d
o
m
a
in
o
f
s
o
f
t
w
ar
e
e
n
g
in
ee
r
i
n
g
[
2
-
4
]
.
A
t
p
r
esen
t,
t
h
e
co
n
v
e
n
tio
n
al
a
n
d
f
r
eq
u
en
tl
y
e
x
er
cised
tech
n
iq
u
es
o
f
co
d
e
r
eu
s
ab
ilit
y
ar
e
h
i
g
h
l
y
co
n
n
ec
ted
w
it
h
t
h
e
s
tr
u
ct
u
r
ed
m
eth
o
d
o
f
as
s
ess
in
g
a
n
d
ad
j
u
s
tin
g
th
e
o
b
j
ec
t
-
o
r
ien
ted
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
[
5
]
.
T
h
er
e
is
ce
r
tain
r
esear
ch
w
o
r
k
th
at
h
as
b
ee
n
f
o
cu
s
ed
o
n
v
i
s
u
a
lizi
n
g
th
e
b
en
e
f
it
s
o
f
co
d
e
r
eu
s
ab
ilit
y
w
it
h
r
esp
ec
t
to
o
b
j
ec
t
-
o
r
ien
ted
s
y
s
te
m
[
6
-
7
]
.
W
ith
an
a
id
o
f
p
o
ten
tial
s
o
f
t
w
ar
e
en
g
i
n
ee
r
i
n
g
ap
p
r
o
ac
h
es,
th
e
s
ig
n
if
ican
ce
o
f
co
d
e
r
eu
s
ab
ilit
y
ca
n
b
e
m
e
as
u
r
ed
u
s
in
g
ce
r
t
ain
s
tan
d
ar
d
m
e
tr
ics
[
8
]
.
T
h
e
b
ig
g
e
s
t
q
u
e
s
tio
n
h
e
r
e
is
t
h
at
alt
h
o
u
g
h
t
h
er
e
ar
e
s
o
m
a
n
y
p
ast
tech
n
iq
u
es
f
o
r
en
h
a
n
ci
n
g
co
d
e
r
eu
s
ab
ilit
y
t
h
a
n
w
h
y
th
e
ad
o
p
tio
n
o
f
it
i
n
t
h
e
e
x
is
tin
g
o
r
g
a
n
izatio
n
i
s
s
o
le
s
s
.
T
ak
i
n
g
a
ca
s
e
s
t
u
d
y
o
f
s
m
a
ller
s
ca
le
s
o
f
t
w
ar
e
d
ev
elo
p
m
e
n
t
i
n
d
u
s
tr
y
,
it
is
q
u
ite
w
el
l
k
n
o
w
n
th
at
ad
o
p
tio
n
o
f
s
u
ch
q
u
a
lit
y
p
r
o
g
r
a
m
s
n
e
v
er
w
o
r
k
o
u
t
f
o
r
th
e
m
d
u
e
to
lac
k
o
f
o
r
co
n
s
tr
ai
n
t
o
f
l
iq
u
id
it
y
.
T
h
is
f
ac
t
e
v
e
n
tu
a
ll
y
tells
u
s
t
h
a
t
p
r
o
g
r
ess
to
w
ar
d
s
co
d
e
r
eu
s
ab
ilit
y
is
ex
tr
e
m
el
y
l
ess
.
So
,
th
e
ex
i
s
tin
g
p
ap
er
also
r
ev
ie
w
s
s
o
m
e
o
f
t
h
e
r
ec
en
t
t
ec
h
n
iq
u
es
to
w
ar
d
s
co
d
e
r
eu
s
ab
ilit
y
a
n
d
ch
ec
k
s
th
e
e
x
t
en
t
o
f
p
r
o
g
r
es
s
an
d
tr
ad
eo
f
f
s
.
T
h
er
ef
o
r
e,
it
ca
n
b
e
s
aid
th
at
i
f
a
n
ap
p
r
o
p
r
iate
k
n
o
w
led
g
e
ab
o
u
t
th
e
ad
v
an
tag
eo
u
s
p
o
in
ts
ca
n
b
e
u
n
d
er
s
to
o
d
th
at
it
m
a
y
s
i
g
n
i
f
ican
t
h
elp
u
s
i
n
f
o
r
m
u
lati
n
g
a
n
o
v
el
s
o
f
t
w
ar
e
r
eu
s
ab
le
co
m
p
o
n
en
t
i
n
f
u
t
u
r
e
an
d
t
h
er
eb
y
b
r
in
g
i
n
to
p
r
ac
tic
e.
T
h
e
in
v
esti
g
atio
n
co
n
d
u
cted
o
v
er
th
i
s
s
tr
ea
m
o
f
s
o
f
t
w
ar
e
e
n
g
i
n
ee
r
i
n
g
r
e
co
m
m
e
n
d
s
t
h
at
it
ca
n
p
o
ten
tiall
y
en
h
a
n
ce
th
e
p
r
o
d
u
ctiv
it
y
s
y
s
te
m
a
n
d
o
f
f
er
s
ig
n
i
f
ica
n
t
d
eg
r
ee
o
f
en
r
ic
h
m
e
n
t
to
th
e
s
o
f
t
w
ar
e
d
esig
n
.
I
n
t
h
e
ar
ea
o
f
s
o
f
t
w
ar
e
en
g
i
n
ee
r
i
n
g
,
th
e
ter
m
‘
s
o
f
t
w
a
r
e
r
eu
s
e
’
i
s
n
o
r
m
all
y
li
n
k
ed
w
it
h
th
e
p
r
o
d
u
ctiv
i
t
y
ef
f
ic
ien
t
in
o
r
d
er
to
en
h
an
c
e
th
e
p
r
o
ce
s
s
es
in
v
o
lv
ed
in
s
o
f
t
w
ar
e
d
ev
elo
p
m
e
n
t.
A
d
if
f
er
en
t
f
o
r
m
o
f
th
e
f
r
a
m
e
w
o
r
k
u
s
ed
f
o
r
v
alid
atio
n
o
f
t
h
e
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
201
7
:
2
8
5
5
–
2
8
6
2
28
56
ap
p
r
o
p
r
iaten
ess
o
f
d
esig
n
p
r
o
ce
s
s
h
i
g
h
l
y
d
ep
en
d
s
o
v
er
t
h
e
p
r
ec
is
en
e
s
s
o
f
t
h
e
o
u
tco
m
e
ac
h
iev
ed
b
y
th
e
f
r
a
m
e
w
o
r
k
.
Hen
ce
,
th
er
e
is
a
n
ee
d
o
f
in
v
esti
g
atio
n
in
t
w
o
d
ir
ec
tio
n
s
w
h
er
e
t
h
e
f
ir
s
t
d
ir
ec
tio
n
s
h
o
u
ld
f
o
cu
s
o
n
e
v
o
lv
i
n
g
u
p
w
it
h
s
o
m
e
n
o
v
el
m
o
d
el
o
f
co
d
e
r
eu
s
ab
ilit
y
w
h
i
le
s
ec
o
n
d
d
ir
ec
tio
n
s
h
o
u
ld
f
o
c
u
s
o
n
i
n
co
r
p
o
r
atin
g
o
p
tim
izatio
n
.
T
h
e
s
ig
n
i
f
ica
n
t
ad
v
an
ta
g
e
to
w
ar
d
s
s
u
c
h
m
o
d
elin
g
is
t
h
at
it
w
ill
b
e
ea
s
y
to
b
e
ad
o
p
ted
an
d
w
il
l
b
e
ap
p
licab
le
o
v
er
lar
g
er
r
an
g
e
o
f
ap
p
lic
atio
n
th
at
u
s
es
o
b
j
e
ct
o
r
ien
ted
s
y
s
te
m
.
Fo
r
tu
n
atel
y
,
th
er
e
i
s
a
b
ig
g
er
s
co
p
e
o
f
en
h
a
n
ci
n
g
t
h
e
o
p
ti
m
i
za
tio
n
tech
n
iq
u
e
w
it
h
lar
g
er
r
an
g
e
o
f
o
p
ti
m
izatio
n
alg
o
r
it
h
m
b
ein
g
av
a
ilab
le
in
ex
is
t
in
g
t
i
m
e
s
.
Ho
w
e
v
er
,
th
er
e
is
n
o
m
u
c
h
o
p
ti
m
izatio
n
b
e
in
g
ca
r
r
ied
o
u
t
to
w
ar
d
s
co
d
e
r
eu
s
ab
ilit
y
s
y
s
te
m
.
T
h
er
e
is
also
a
p
o
s
s
ib
ilit
y
t
h
at
ex
is
tin
g
ap
p
r
o
ac
h
es
to
w
ar
d
s
s
o
f
t
w
ar
e
m
etr
ic
s
b
e
f
u
r
th
er
in
v
e
s
ti
g
ated
an
d
clu
b
b
ed
w
i
th
e
x
p
er
i
m
e
n
tal
d
ata
to
f
u
r
th
er
i
n
v
esti
g
ate
th
e
b
et
ter
p
o
s
s
ib
ilit
ies
o
f
co
d
e
r
eu
s
ab
ilit
y
a
n
d
t
h
er
eb
y
a
g
o
o
d
ch
an
ce
f
o
r
ev
o
l
v
i
n
g
u
p
w
it
h
a
p
r
ed
ictiv
e
s
y
s
te
m
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
t
h
er
ef
o
r
e
in
tr
o
d
u
ce
s
a
m
ec
h
a
n
is
m
o
f
o
p
tim
izatio
n
w
h
er
e
t
h
e
co
d
e
r
eu
s
ab
ilit
y
is
e
m
p
h
as
ized
b
y
ad
o
p
tio
n
a
tr
u
e
ca
s
e
s
t
u
d
y
an
d
a
n
al
y
tic
al
ap
p
r
o
ac
h
es.
W
e
also
e
m
p
h
asize
o
n
al
g
o
r
ith
m
ef
f
icien
c
y
.
Sectio
n
2
d
is
c
u
s
s
e
s
ab
o
u
t
t
h
e
r
e
s
ea
r
ch
m
et
h
o
d
o
lo
g
y
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
f
o
ll
o
w
ed
b
y
elab
o
r
ated
d
is
cu
s
s
io
n
o
f
al
g
o
r
ith
m
i
m
p
l
e
m
en
tatio
n
i
n
Sectio
n
3
.
Sectio
n
4
b
r
ief
s
o
u
t
th
e
r
esu
lt
s
b
ein
g
ac
co
m
p
li
s
h
e
d
w
h
ile
s
u
m
m
ar
y
o
f
t
h
e
p
ap
er
ar
e
d
is
cu
s
s
ed
in
Sectio
n
5
.
1
.
1
.
B
a
ck
g
ro
un
d
T
h
is
s
ec
tio
n
d
is
c
u
s
s
es
ab
o
u
t
th
e
e
x
i
s
ti
n
g
ap
p
r
o
ac
h
es
t
h
at
h
a
s
b
ee
n
ca
r
r
ied
o
u
t
to
war
d
s
co
d
e
r
eu
s
ab
ilit
y
.
Ou
r
r
ev
ie
w
w
o
r
k
h
as
alr
ea
d
y
d
is
c
u
s
s
ed
ab
o
u
t
d
if
f
er
e
n
t
tech
n
iq
u
e
s
an
d
tr
a
d
e
-
o
f
f
in
e
x
is
ti
n
g
s
y
s
te
m
[
9
]
,
w
e
ad
d
f
u
r
th
er
u
p
d
ate
to
w
ar
d
s
t
h
e
r
esear
c
h
p
r
o
g
r
ess
in
th
i
s
d
o
m
ai
n
.
Fi
r
s
t
o
f
all,
t
h
er
e
i
s
s
ig
n
i
f
ica
n
tl
y
v
er
y
les
s
n
u
m
b
er
o
f
r
esear
ch
p
r
o
g
r
ess
e
s
in
t
h
e
to
p
ic
o
f
co
d
e
r
eu
s
ab
ilit
y
f
r
o
m
th
e
y
ea
r
2
0
1
0
till
d
ate.
Ho
w
e
v
er
,
w
e
o
n
l
y
d
i
s
c
u
s
s
t
h
e
r
elate
d
w
o
r
k
in
th
i
s
p
er
s
p
ec
tiv
e.
Hu
d
aib
et
al.
[
1
0
]
h
av
e
p
r
ese
n
ted
a
class
i
f
icatio
n
-
b
a
s
ed
ap
p
r
o
ac
h
f
o
r
s
o
f
t
w
ar
e
r
eu
s
ab
ilit
y
u
s
i
n
g
s
el
f
-
o
r
g
an
iz
in
g
m
ap
.
K
h
o
s
h
k
b
ar
f
o
r
o
u
s
h
h
a
et
al.
[
1
1
]
h
av
e
d
is
c
u
s
s
ed
ab
o
u
t
s
o
f
t
w
ar
e
m
etr
ic
i
n
o
r
d
er
to
in
co
r
p
o
r
ate
r
eu
ab
le
co
m
p
o
n
e
n
ts
in
p
r
o
g
r
a
m
m
i
n
g
lan
g
u
a
g
e.
T
ib
er
m
ac
in
e
et
al.
[
1
2
]
h
av
e
ad
d
r
ess
ed
th
e
co
n
s
tr
ai
n
ts
d
u
r
in
g
m
o
d
eli
n
g
o
f
s
o
f
t
w
ar
e
r
eu
s
e
o
n
ar
ch
itect
u
r
al
d
esig
n
.
T
ah
ir
et
al.
[
1
2
]
h
av
e
p
r
esen
ted
a
r
eu
s
ab
ilit
y
-
b
a
s
ed
f
r
a
m
e
w
o
r
k
th
at
o
f
f
er
s
ef
f
icie
n
t
s
elec
tio
n
o
f
co
m
p
o
n
en
t
s
.
T
h
e
r
esear
ch
to
w
ar
d
s
o
f
r
e
u
s
ab
ili
t
y
w
as
also
s
ee
n
i
n
d
i
f
f
er
en
t
p
a
tter
n
i
n
m
o
s
t
r
ec
e
n
t
ti
m
e
s
.
Ve
g
t
et
a
l.
[
1
3
]
h
a
v
e
p
r
esen
ted
s
u
ch
ar
ch
itec
t
u
r
e
t
h
at
e
m
p
h
a
s
izes
o
n
r
eu
s
ab
ilit
y
o
f
g
a
m
i
n
g
co
m
p
o
n
e
n
t
s
.
T
h
e
ar
ch
itect
u
r
e
h
as
b
ee
n
s
h
o
w
n
to
h
av
e
v
er
y
l
o
w
d
ep
en
d
ab
ilit
y
to
w
ar
d
s
co
n
v
en
t
io
n
al
s
o
f
t
w
ar
e
p
atter
n
s
an
d
ex
is
t
i
n
g
p
r
ac
tice
an
d
p
r
o
to
co
ls
o
f
co
d
in
g
.
De
m
r
ao
u
i
et
al.
[
1
4
]
h
av
e
p
r
esen
ted
a
s
y
n
c
h
r
o
n
cit
y
-
b
ased
ap
p
r
o
ac
h
f
o
r
en
h
a
n
cin
g
th
e
r
eu
s
ab
ilit
y
p
er
f
o
r
m
a
n
ce
o
v
er
w
ar
eh
o
u
s
es.
T
h
e
au
t
h
o
r
s
h
av
e
u
s
ed
ca
s
e
-
b
ased
r
ea
s
o
n
in
g
ap
p
r
o
ac
h
in
o
r
d
er
to
en
h
an
ce
th
e
p
r
o
ce
s
s
o
f
s
o
f
t
w
a
r
e
r
eu
s
ab
ili
t
y
.
Ah
m
a
r
o
et
al.
[
1
5
]
h
av
e
p
r
esen
ted
a
d
is
c
u
s
s
io
n
to
w
ar
d
s
ex
is
ti
n
g
p
r
ac
tical
ad
o
p
tio
n
o
f
s
o
f
t
w
ar
e
r
e
u
s
ab
ilit
y
co
n
s
id
e
r
in
g
th
e
ca
s
e
s
t
u
d
y
o
f
s
o
f
t
w
ar
e
d
ev
elo
p
m
en
t
o
r
g
a
n
izatio
n
i
n
Ma
la
y
s
ia.
T
h
e
p
ap
er
g
iv
es
t
h
e
f
air
id
ea
o
f
v
ar
io
u
s
f
o
r
m
s
o
f
r
eu
s
ab
le
ap
p
r
o
ac
h
es
e.
g
.
ap
p
licatio
n
p
r
o
d
u
ct
lin
es,
d
esi
g
n
p
att
er
n
s
,
C
OT
S
in
te
g
r
atio
n
,
p
r
o
g
r
a
m
g
e
n
er
ato
r
s
,
co
m
p
o
n
e
n
t
-
b
ased
d
ev
e
lo
p
m
e
n
t,
co
n
f
i
g
u
r
ab
le
v
er
tical
ap
p
licatio
n
s
,
le
g
ac
y
s
y
s
te
m
w
r
ap
p
in
g
,
asp
ec
t
-
o
r
ien
ted
s
o
f
t
w
ar
e
d
ev
elo
p
m
en
t,
etc.
E
f
at
et
al.
[
1
6
]
h
av
e
a
d
d
r
ess
ed
th
e
p
r
o
b
lem
s
p
er
tain
i
n
g
to
co
m
p
o
n
en
t
r
eu
s
e
a
n
d
an
al
y
ze
d
t
h
e
p
r
o
b
le
m
u
s
i
n
g
d
ata
r
ep
o
s
ito
r
y
.
T
h
e
au
t
h
o
r
co
m
m
en
ted
t
h
at
i
n
o
r
d
er
to
ad
d
r
ess
th
e
p
r
o
b
le
m
o
f
r
eu
s
ab
ilit
y
,
th
e
co
s
t
f
o
r
s
p
ac
e
-
ti
m
e
s
h
o
u
ld
b
e
ad
d
r
ess
ed
f
o
r
t
h
e
s
o
f
t
w
ar
e
co
m
p
o
n
en
ts
.
T
h
e
tech
n
iq
u
e
h
a
s
also
in
tr
o
d
u
ce
d
t
w
o
d
if
f
er
e
n
t
alg
o
r
ith
m
s
w
h
er
e
o
n
e
f
o
cu
s
es
o
n
s
elec
tio
n
o
f
attr
ib
u
tes
w
h
ile
o
th
er
f
o
cu
s
e
s
o
n
r
an
k
i
n
g
as
w
ell
a
s
p
r
io
r
itizin
g
it.
T
h
e
s
t
u
d
y
o
u
tco
m
es
w
er
e
ass
es
s
ed
u
s
i
n
g
s
u
cc
es
s
a
n
d
f
a
ilu
r
es
ca
s
es
o
f
test
o
u
tco
m
es.
Mo
j
ica
et
al.
[
1
7
]
h
av
e
p
r
esen
ted
a
n
e
m
p
ir
ical
-
b
ased
in
v
esti
g
atio
n
to
w
ar
d
s
s
o
f
t
w
ar
e
r
eu
s
ab
ilit
y
.
Mo
b
ile
ap
p
licatio
n
s
ar
e
co
n
s
i
d
er
ed
as
a
ca
s
e
s
t
u
d
y
w
h
er
e
t
h
e
a
u
th
o
r
s
i
n
v
e
s
ti
g
ated
s
o
f
t
war
e
r
eu
s
ab
ilit
y
.
T
h
e
au
th
o
r
also
co
m
m
en
ted
th
at
d
esig
n
o
f
th
e
m
o
b
ile
ap
p
licato
n
s
,
at
p
r
ese
n
t;
m
a
k
e
u
s
e
o
f
v
ar
io
u
s
f
o
r
m
s
o
f
class
es,
i
n
h
er
itan
ce
,
a
n
d
lib
r
ar
y
r
e
u
s
e.
I
t
w
ill
s
ig
n
i
f
ica
n
t
ass
is
t
s
t
h
e
d
ev
elo
p
er
to
f
u
r
th
er
u
p
g
r
ad
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
s
o
f
t
w
ar
e
r
eu
s
ab
ilit
y
.
Naz
ir
et
al.
[
1
8
]
h
av
e
p
r
esen
ted
a
d
is
cu
s
s
io
n
to
w
ar
d
s
s
elec
t
io
n
o
f
s
o
f
t
w
ar
e
co
m
p
o
n
e
n
ts
b
y
i
n
tr
o
d
u
cin
g
a
u
n
iq
u
e
an
al
y
tical
f
r
a
m
e
w
o
r
k
co
n
s
id
er
in
g
ca
s
e
s
tu
d
y
.
T
h
e
au
t
h
o
r
b
asicall
y
u
s
e
s
an
ex
is
ti
n
g
m
e
ch
an
i
s
m
an
d
th
e
n
m
o
d
i
f
ie
s
i
n
to
an
al
y
tical
n
et
w
o
r
k
p
r
o
ce
s
s
th
at
s
ig
n
i
f
ica
n
tl
y
d
ep
en
d
s
o
n
f
ee
d
b
ac
k
(
i.e
.
ex
p
er
t
o
p
in
io
n
)
as
w
ell
as
d
y
n
a
m
ic
s
t
r
u
c
tu
r
e
o
f
th
e
n
et
w
o
r
k
.
T
h
e
s
ig
n
i
f
ica
n
t
ad
v
an
ta
g
e
o
f
th
is
s
tu
d
y
i
s
it
s
s
u
p
p
o
r
tab
ilit
y
o
f
v
ar
io
u
s
t
y
p
es
o
f
r
e
u
s
ab
le
f
ac
to
r
s
.
I
t
al
s
o
ass
i
s
ts
in
d
ec
i
s
io
n
m
ak
in
g
f
o
r
co
m
p
lex
n
et
w
o
r
k
s
.
T
h
e
s
tu
d
y
o
u
tco
m
e
i
s
as
s
ess
ed
u
s
i
n
g
g
r
ap
h
ical
w
eig
h
t
s
.
S
p
o
elst
r
a
et
al.
[
1
9
]
h
av
e
d
is
c
u
s
s
ed
th
e
u
s
ag
e
o
f
t
h
e
s
o
f
t
w
ar
e
r
e
u
s
e
to
w
ar
d
s
th
e
o
r
g
an
izat
io
n
t
h
at
p
r
ac
tices
a
g
ile
m
et
h
o
d
o
lo
g
ies.
T
h
e
au
th
o
r
s
h
a
v
e
al
s
o
d
is
cu
s
s
ed
ab
o
u
t
v
ar
io
u
s
r
e
u
s
e
f
ac
to
r
s
o
n
e
x
is
t
in
g
m
o
d
els
a
s
w
ell
as
d
is
c
u
s
s
ed
ab
o
u
t
v
alid
ated
o
u
tco
m
e
o
f
t
h
e
s
t
u
d
y
.
B
asicall
y
,
t
h
e
s
t
u
d
y
r
ep
r
esen
ts
a
t
y
p
e
o
f
s
o
f
t
w
ar
e
m
an
a
g
e
m
en
t to
o
l to
s
u
p
p
o
r
t
r
eu
s
b
ab
ilit
y
co
n
ce
p
t.
Z
h
u
et
al.
[
2
0
]
h
av
e
d
is
cu
s
s
ed
ab
o
u
t
th
e
s
o
f
t
w
ar
e
r
e
u
s
ab
ilit
y
in
t
er
m
s
o
f
f
r
a
m
e
w
o
r
k
r
eu
s
ab
ilit
y
w
it
h
r
esp
ec
t
to
d
is
tr
ib
u
ted
p
r
o
ce
s
s
o
f
s
i
m
u
lat
io
n
.
T
h
e
s
o
lu
tio
n
p
r
o
v
id
ed
b
y
t
h
e
au
th
o
r
is
a
f
r
a
m
e
w
o
r
k
w
ith
r
eu
s
ab
le
co
m
p
o
n
en
t
th
at
is
co
n
s
tr
u
c
ted
b
y
t
h
e
d
o
m
ai
n
ex
p
er
ts
.
T
h
e
au
th
o
r
also
in
tr
o
d
u
ce
s
m
u
ltip
le
s
er
v
ice
-
o
r
ien
ted
i
n
t
er
f
ac
es
f
o
r
p
er
f
o
r
m
a
n
ce
en
h
an
ce
m
e
n
t.
T
h
e
co
m
b
i
n
ed
wo
r
k
o
f
Ma
n
o
j
an
d
Nan
d
ak
u
m
ar
[
2
1
]
h
av
e
d
escr
ib
ed
co
d
e
r
eu
s
ab
ilit
y
co
n
ce
p
t
f
o
r
co
s
t
o
p
ti
m
izatio
n
in
I
T
s
y
s
te
m
.
T
h
e
s
t
u
d
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
A
N
o
ve
l O
p
timiz
a
tio
n
to
w
a
r
d
s
Hig
h
er R
elia
b
ilit
y
in
P
r
ed
ictive
Mo
d
ellin
g
to
w
a
r
d
s
C
o
d
e
… (
Ma
n
o
j H
.
M.
)
2857
p
r
o
v
id
es
an
a
n
al
y
tical
m
o
d
e
l
to
b
r
in
g
r
elatio
n
s
h
ip
a
m
o
n
g
th
e
s
ta
n
d
ar
d
m
etr
ic
co
m
p
o
n
en
ts
a
n
d
co
d
e
r
eu
s
ab
ilit
y
.
T
h
e
Ma
r
k
o
v
m
o
d
e
is
u
tili
ze
d
f
o
r
s
i
g
n
if
ican
t
in
f
o
r
m
at
io
n
e
x
tr
ac
tio
n
w
h
ich
p
r
o
v
id
es
h
ig
h
es
t
co
d
e
r
eu
s
ab
ilit
y
v
al
u
e.
1
.
2
.
T
he
P
ro
ble
m
T
h
e
p
r
io
r
s
ec
tio
n
h
a
s
p
r
esen
ted
a
b
r
ief
d
is
c
u
s
s
io
n
o
f
s
o
m
e
o
f
t
h
e
r
elate
d
w
o
r
k
co
n
n
ec
ted
w
it
h
co
d
e
r
eu
s
ab
ilit
y
.
C
o
d
e
r
eu
s
ab
ilit
y
i
s
o
n
e
s
u
b
s
et
o
f
s
o
f
t
w
ar
e
r
eu
s
a
b
ilit
y
w
h
ich
h
as
h
ig
h
er
r
ate
o
f
tech
n
ic
al
ad
o
p
tio
n
b
y
m
an
y
s
o
f
t
w
ar
e
en
g
i
n
ee
r
s
i
r
r
esp
ec
tiv
e
o
f
th
e
s
ca
le
o
f
th
e
o
r
g
an
izatio
n
.
Ho
w
e
v
er
,
in
s
p
i
te
o
f
s
u
ch
m
as
s
iv
e
u
s
a
g
e
o
f
co
d
e
r
eu
s
ab
ilit
y
,
t
h
er
e
is
a
v
er
y
les
s
n
u
m
b
er
o
f
atte
n
tio
n
s
b
ei
n
g
attr
ac
ted
f
r
o
m
t
h
e
r
esear
c
h
co
m
m
u
n
it
y
to
w
ar
d
s
t
h
i
s
to
p
ic.
Hen
c
e,
th
er
e
ar
e
v
ar
io
u
s
s
et
o
f
o
p
en
-
e
n
d
p
r
o
b
lem
s
t
h
at
ar
e
y
et
to
b
e
ad
d
r
ess
ed
in
f
u
t
u
r
e.
Fo
llo
w
i
n
g
ar
e
th
e
o
p
en
r
esear
ch
p
r
o
b
lem
s
af
ter
r
ev
ie
w
i
n
g
t
h
e
ex
is
ti
n
g
liter
at
u
r
es:
-
T
h
er
e
is
n
o
s
o
lid
r
esear
ch
co
n
d
u
cted
f
o
r
co
d
e
r
eu
s
ab
ilit
y
i
n
s
o
f
t
w
ar
e
en
g
i
n
ee
r
in
g
til
l
d
ate.
Ma
j
o
r
ity
o
f
th
e
e
x
is
tin
g
r
esear
ch
lack
s
m
o
d
el
v
alid
atio
n
f
o
r
w
h
ic
h
r
ea
s
o
n
t
h
e
s
t
u
d
y
o
u
tco
m
es
o
f
e
x
is
tin
g
s
y
s
te
m
ca
n
n
o
t b
e
d
ir
ec
tly
s
aid
to
b
e
ap
p
licab
le.
T
h
er
e
is
n
o
a
v
ailab
il
it
y
o
f
an
y
b
en
ch
m
ar
k
m
o
d
els
o
r
tec
h
n
iq
u
es
to
w
ar
d
s
co
d
e
r
eu
s
ab
ili
t
y
o
r
o
p
ti
m
izatio
n
tech
n
q
i
u
es
w
h
ic
h
m
ak
e
s
its
s
ti
ll a
n
o
p
en
r
esear
ch
is
s
u
es.
No
n
e
o
f
th
e
e
x
i
s
tin
g
tec
h
n
q
i
u
e
s
ar
e
f
o
u
n
d
to
ad
o
p
t a
n
y
tec
h
n
iq
u
e
th
at
o
f
f
er
s
al
g
o
r
it
h
m
co
s
t
ef
f
ec
t
iv
e
n
es
s
.
T
h
er
ef
o
r
e,
af
ter
r
ev
ie
w
i
n
g
th
e
ex
is
ti
n
g
p
r
o
b
lem
s
,
it
ca
n
b
e
co
n
clu
d
ed
th
at
t
h
er
e
is
a
n
ee
d
to
w
o
r
k
o
n
s
u
c
h
ab
o
v
e
m
en
tio
n
ed
r
esear
ch
p
r
o
b
lem
s
.
He
n
ce
,
th
e
p
r
o
b
le
m
s
tate
m
en
t
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
is
–
“
I
t
is
s
ig
n
i
f
ica
n
tl
y
a
c
h
alle
n
g
in
g
tas
k
to
f
o
r
m
u
late
a
s
y
s
te
m
m
o
d
el
th
at
ap
p
lies
o
p
ti
m
izatio
n
in
o
r
d
er
to
en
h
a
n
ce
t
h
e
p
r
ed
ictiv
en
es
s
o
f
t
h
e
co
d
e
r
eu
s
ab
ilit
y
.
”
T
h
e
n
e
x
t
s
ec
tio
n
d
is
cu
s
s
es
ab
o
u
t
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
to
ad
d
r
ess
s
u
c
h
is
s
u
es.
1
.
3
.
T
he
P
ro
po
s
ed
So
lutio
n
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
d
is
c
u
s
s
ed
in
t
h
is
p
ap
er
is
a
co
n
ti
n
u
a
tio
n
o
f
o
u
r
p
r
io
r
w
o
r
k
[
2
2
]
.
T
h
e
p
r
im
e
p
u
r
p
o
s
e
o
f
t
h
is
w
o
r
k
is
to
in
t
r
o
d
u
ce
a
f
r
a
m
e
w
o
r
k
w
h
er
e
c
o
d
e
r
eu
s
ab
ilit
y
ca
n
b
e
tes
ted
an
d
an
a
l
y
ze
d
w
i
th
v
ar
ied
r
an
g
es
o
f
n
ea
r
r
ea
l
-
ti
m
e
p
r
o
b
lem
s
as
s
o
ciate
d
w
it
h
s
o
f
t
w
ar
e
d
ev
e
lo
p
m
en
t.
T
h
e
s
c
h
e
m
atic
ar
c
h
itect
u
r
e
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
as
s
h
o
w
n
i
n
Fi
g
u
r
e
1.
C
o
d
e
H
a
n
d
l
i
n
g
C
a
p
a
c
i
t
y
(
α
)
E
f
f
e
c
t
i
v
e
E
f
f
o
r
t
(
β
)
R
e
s
o
u
r
c
e
f
o
r
N
e
w
D
e
s
i
g
n
(
γ
)
E
r
r
o
r
P
r
o
b
a
b
i
l
i
t
y
(
φ
)
D
a
m
p
e
d
-
L
e
a
s
t
S
q
u
a
r
e
A
l
g
o
r
i
t
h
m
R
e
l
i
a
b
i
l
i
t
y
σ
r
e
l
S
t
a
b
i
l
i
t
y
A
t
t
r
i
b
u
t
e
σ
s
t
a
b
T
r
a
i
n
i
n
g
v
a
l
i
d
a
t
i
o
n
Fig
u
r
e
1
.
Sch
e
m
atic
ar
ch
itec
tu
r
e
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
T
h
er
e
ar
e
m
ai
n
l
y
f
o
u
r
es
s
e
n
ti
al
s
ta
g
es
in
v
o
l
v
ed
i
n
d
esi
g
n
in
g
p
r
o
p
o
s
ed
f
r
a
m
e
w
o
r
k
e.
g
.
i)
in
t
h
e
f
ir
s
t
s
tag
e,
w
e
tak
e
s
a
m
p
le
o
b
j
ec
t
-
o
r
ien
ted
s
o
u
r
ce
co
d
e
f
r
o
m
t
w
o
s
o
f
t
w
ar
e
p
r
o
j
ec
ts
an
d
ex
tr
ac
ts
its
s
o
f
t
w
ar
e
m
etr
ic
v
alu
e
s
w
ith
r
esp
ec
t
to
C
o
u
p
li
n
g
b
et
w
ee
n
o
b
j
ec
ts
,
R
esp
o
n
s
e
f
o
r
class
es,
w
ei
g
h
ted
m
et
h
o
d
s
p
er
class
,
Dep
t
h
o
f
in
h
er
i
tan
ce
tr
ee
,
Nu
m
b
er
o
f
C
h
ild
r
en
,
ii)
in
th
e
s
ec
o
n
d
s
ta
g
e,
w
e
in
tr
o
d
u
ce
4
d
if
f
er
en
t
p
r
o
b
lem
s
in
s
o
f
t
w
ar
e
d
ev
elo
p
m
en
t
as
ca
s
e
s
t
u
d
y
,
i
i
i
)
in
th
e
t
h
ir
d
s
ta
g
e,
w
e
co
m
p
u
te
co
d
e
r
eu
s
ab
ilit
y
u
s
i
n
g
co
n
ce
p
t
m
en
tio
n
ed
i
n
[
2
2
]
,
an
d
iv
)
w
e
ap
p
l
y
o
p
tim
izatio
n
tech
n
iq
u
e
to
en
s
u
r
e
r
eliab
ilit
y
o
f
th
e
o
u
tco
m
e
o
b
tain
ed
f
o
r
co
d
e
r
eu
s
ab
ilit
y
.
T
h
is
p
ar
t
o
f
th
e
s
tu
d
y
f
o
r
m
u
lates
an
e
m
p
ir
i
ca
l
ap
p
r
o
ac
h
f
o
r
f
u
r
th
er
co
m
p
u
ti
n
g
th
e
co
d
in
g
attr
ib
u
te,
)
(
1
Q
P
R
C
A
(
1
)
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
201
7
:
2
8
5
5
–
2
8
6
2
2858
W
h
er
e,
th
e
v
ar
iab
le
P
r
ep
r
esen
ts
p
r
o
d
u
ct
o
f
s
o
f
t
w
ar
e
m
etr
i
cs,
to
tal
ef
f
o
r
t,
an
d
h
o
u
r
s
o
f
w
o
r
k
.
T
h
e
v
ar
iab
le
Q
r
ep
r
ese
n
ts
p
r
o
d
u
ct
o
f
s
o
f
t
w
ar
e
m
etr
ics,
e
f
f
o
r
t
f
o
r
in
co
r
p
o
r
atin
g
co
d
e
r
eu
s
a
b
ilit
y
,
a
n
d
h
o
u
r
s
o
f
w
o
r
k
,
w
h
i
le
R
w
ill
r
ep
r
ese
n
t
d
if
f
er
en
ce
o
f
c
u
m
u
lati
v
e
e
f
f
o
r
t
d
ay
s
w
it
h
d
a
y
s
r
eq
u
ir
ed
t
o
in
co
r
p
o
r
ate
co
d
e
r
eu
s
ab
ilit
y
.
W
e
also
f
o
r
m
u
lat
e
co
n
d
itio
n
w
h
er
e
s
o
f
t
w
ar
e
en
g
i
n
ee
r
s
h
av
e
to
d
eliv
er
th
e
s
o
f
t
w
ar
e
co
d
e
w
it
h
in
cl
u
s
io
n
o
f
ce
r
tain
r
an
g
e
o
f
co
d
e
r
eu
s
ab
ilit
y
to
en
s
u
r
e
co
s
t
s
av
i
n
g
o
f
p
r
o
d
u
ctio
n
in
f
u
t
u
r
e.
T
h
is
p
r
ed
icted
o
u
tco
m
e
o
f
co
d
e
r
eu
s
ab
ilit
y
i
s
th
e
n
a
s
s
es
s
ed
u
s
i
n
g
a
m
ac
h
i
n
e
lear
n
i
n
g
ap
p
r
o
ac
h
to
en
s
u
r
e
h
i
g
h
er
d
eg
r
ee
o
f
r
eliab
ilit
y
as
w
ell
as
s
tab
ilit
y
in
th
e
o
u
tco
m
e
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
.
T
h
e
n
ex
t
s
ec
tio
n
d
is
cu
s
s
es
ab
o
u
t
r
esear
ch
m
et
h
o
d
o
lo
g
y
ad
o
p
ted
in
p
r
o
p
o
s
ed
s
tu
d
y
.
2.
RE
S
E
ACH
M
E
T
H
O
DO
L
O
G
Y
T
h
e
d
esig
n
o
f
t
h
e
p
r
o
p
o
s
e
d
r
esear
ch
w
o
r
k
is
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
an
al
y
tica
l
r
esear
ch
m
et
h
o
d
o
lo
g
y
f
o
r
en
h
a
n
ci
n
g
c
o
d
e
r
esu
ab
ilt
y
i
n
s
o
f
t
w
ar
e
en
g
in
ee
r
i
n
g
.
A
s
o
p
ti
m
izatio
n
is
th
e
p
r
i
m
e
m
o
ti
v
e
o
f
p
r
o
p
o
s
ed
s
tu
d
y
th
er
e
f
o
r
e
a
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
is
a
p
p
lied
f
o
r
th
is
p
u
r
p
o
s
e.
T
h
is
jo
b
is
d
o
n
e
b
y
u
s
in
g
n
eu
r
al
n
e
t
w
o
r
k
f
o
r
th
e
p
u
r
p
o
s
e
o
f
r
an
k
i
n
g
o
p
ti
m
iza
tio
n
in
s
o
f
t
w
ar
e
en
g
i
n
ee
r
i
n
g
.
T
h
e
p
r
im
e
r
ea
s
o
n
f
o
r
ad
o
p
tin
g
n
e
u
r
al
n
et
w
o
r
k
f
o
r
o
p
ti
m
izatio
n
is
b
ec
a
u
s
e
o
f
its
m
u
lti
-
tas
k
i
n
g
ca
p
ab
ilit
ie
s
.
W
e
co
n
s
tr
u
ct
a
s
ch
e
m
atic
ar
c
h
itect
u
r
e
t
h
at
ta
k
es
t
h
e
i
n
p
u
t
o
f
4
d
i
f
f
er
e
n
t
t
y
p
e
s
o
f
p
r
o
b
le
m
s
as
s
o
ciate
d
w
it
h
r
ea
l
-
ti
m
e
s
o
f
t
w
ar
e
d
ev
elo
p
m
en
t
th
a
t
f
in
al
l
y
r
e
s
u
l
t
s
in
co
m
p
u
tatio
n
o
f
R
eliab
ilit
y
as
w
ell
a
s
s
tab
ilit
y
attr
ib
u
te.
F
o
llo
w
i
n
g
ar
e
b
r
ie
f
d
escr
ip
tio
n
o
f
th
e
i
n
p
u
t
s
to
w
ar
d
s
th
e
m
o
d
el
f
o
r
co
d
e
r
eu
s
ab
il
it
y
:
Co
de
H
a
nd
lin
g
Ca
p
a
cit
y
(
α
)
:
T
h
is
att
r
i
b
u
t
e
is
co
n
s
i
d
e
r
e
d
as
th
e
m
ax
i
m
u
m
n
u
m
b
er
o
f
s
o
f
tw
ar
e
co
d
es
th
a
t
ca
n
b
e
n
ew
l
y
d
esig
n
e
d
an
d
d
e
v
elir
e
d
b
y
a
t
ea
m
f
o
r
o
n
e
m
o
n
th
ag
ain
s
t
th
e
cl
ien
t’
s
r
e
q
u
i
r
em
en
t.
o
R
a
ti
o
n
a
l
e
:
T
h
is
at
tr
ib
u
t
e
α
w
i
ll
d
ir
ec
t
ly
r
ep
r
es
en
t
th
e
q
u
an
t
if
icat
io
n
o
f
o
p
t
im
izati
o
n
te
ch
n
iq
u
e
to
w
ar
d
p
r
o
p
o
s
e
d
c
o
d
e
r
eu
s
a
b
i
lity
co
n
ce
p
t
.
I
n
cr
ea
s
e
in
th
e
v
alu
e
o
f
th
is
att
r
i
b
u
te
b
y
k
ee
p
i
n
g
th
e
o
th
e
r
att
r
i
b
u
tes
s
im
ila
r
is
th
e
d
ir
e
ct
in
d
ica
t
o
r
o
f
o
p
tim
izati
o
n
.
E
f
f
ec
t
i
v
e
E
f
f
o
rt
(
β
)
:
T
h
is
a
tt
r
ib
u
te
is
c
o
n
s
id
er
e
d
as
th
e
p
r
e
c
is
e
t
im
e
co
n
s
u
m
ed
b
y
d
esig
in
er
w
h
en
a
c
o
d
e
is
d
ev
el
o
p
e
d
b
y
in
c
o
r
p
o
r
at
in
g
co
d
e
r
eu
s
a
b
il
ity
w
ith
in
it.
o
R
a
ti
o
n
a
l
e
:
T
h
i
s
att
r
i
b
u
t
e
β
w
ill
r
e
p
r
esen
t
s
av
in
g
o
f
p
r
o
d
u
cti
o
n
tim
e
w
h
en
o
p
t
im
izat
io
n
is
p
e
r
f
o
r
m
ed
to
s
ee
h
o
w
m
u
ch
tim
e
is
r
eq
u
i
r
e
d
in
i)
e
ith
e
r
b
u
ild
in
g
th
e
c
o
d
e
f
r
o
m
s
cr
atch
o
r
ii
)
ap
p
ly
in
g
th
e
co
d
e
r
eu
s
a
b
i
lity
c
o
n
ce
p
t
.
Reso
u
rc
e
f
o
r
N
e
w
D
esi
g
n
(
γ
)
:
T
h
is
at
tr
ib
u
t
e
d
ef
in
es
n
u
m
b
er
o
f
r
es
o
u
r
c
es
b
e
in
g
u
tili
z
e
d
f
o
r
d
ev
el
o
p
in
g
th
e
n
ew
co
d
e
w
ith
co
d
e
r
eu
s
a
b
ilit
y
w
ith
in
it.
o
R
a
ti
o
n
a
l
e
:
T
h
is
a
tt
r
i
b
u
te
γ
w
ill
d
i
r
e
ctly
r
ep
r
es
en
t
th
e
c
o
s
t
in
v
o
lv
e
d
in
p
r
o
d
u
c
ti
o
n
.
T
h
e
d
ev
elo
p
er
is
ass
u
m
ed
to
d
esig
n
th
e
n
e
w
co
d
e
in
s
u
ch
a
w
a
y
th
at
it
s
h
o
u
l
d
h
av
e
ce
r
t
ain
th
r
esh
o
l
d
e
d
p
e
r
c
en
tag
e
o
f
c
o
d
e
r
eu
s
a
b
il
ity
.
Hen
c
e,
th
is
v
alu
e
s
h
o
u
ld
b
e
k
ep
t
as
l
o
w
as
p
o
s
s
ib
le
.
E
rr
o
r
P
r
o
b
a
bil
it
y
(
φ
)
:
I
n
o
r
d
e
r
t
o
ch
e
ck
th
e
in
te
r
n
al
v
ali
d
aity
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
,
w
e
in
ten
tio
n
ally
in
co
r
p
o
r
a
te
c
er
t
ain
r
an
g
e
o
f
er
r
o
r
as
an
u
n
ce
r
ta
in
ty
.
o
R
a
ti
o
n
a
l
e
:
T
h
e
en
ti
te
c
o
n
ce
p
t
o
f
co
d
e
r
eu
s
ab
ilit
y
an
d
its
o
p
tim
izat
io
n
is
f
r
am
ed
w
ith
o
u
t
ev
en
k
n
o
w
in
g
th
e
f
o
r
m
o
f
r
eq
u
i
r
e
m
en
t
o
f
clien
t.
W
e
ca
ll
th
is
f
ac
t
o
r
as
u
n
c
ert
a
i
n
ty
.
T
h
e
r
ef
o
r
e,
th
is
att
r
i
b
u
te
φ
w
ill
p
e
r
f
o
r
m
co
m
p
u
tat
io
n
o
f
c
o
d
e
r
eu
s
a
b
il
ity
b
y
in
clu
s
io
n
o
f
u
n
ce
r
t
ain
ty
f
ac
to
r
o
r
er
r
o
r
p
r
o
b
a
b
il
ity
.
W
e
u
s
e
all
th
e
ab
o
v
e
m
e
n
tio
n
ed
attr
ib
u
tes
as
i
n
p
u
t
to
w
ar
d
s
th
e
p
r
o
ce
s
s
o
r
,
w
h
ich
u
p
o
n
p
r
o
ce
s
s
in
g
w
il
l
g
iv
e
th
e
o
u
tp
u
t
o
f
r
eliab
il
it
y
a
n
d
s
tab
ilit
y
.
W
e
ap
p
l
y
Da
m
p
ed
-
L
ea
s
t
Sq
u
ar
e
al
g
o
r
ith
m
as
th
e
o
p
ti
m
izatio
n
alg
o
r
ith
m
i
n
o
r
d
er
to
p
e
r
f
o
r
m
o
p
tim
izatio
n
u
s
i
n
g
n
e
u
r
al
n
et
w
o
r
k
.
3.
AL
G
O
RI
T
H
M
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
e
i
m
p
le
m
e
n
tat
io
n
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
ca
r
r
ied
o
u
t
u
s
i
n
g
M
atlab
.
T
h
e
al
g
o
r
ith
m
d
esi
g
n
m
ai
n
l
y
f
o
c
u
s
e
s
o
n
i
m
p
r
o
v
i
n
g
t
h
e
s
t
u
d
y
o
u
tco
m
es
o
f
o
p
ti
m
izat
io
n
i.e
.
r
eliab
ilit
y
a
n
d
th
e
s
tab
ilit
y
.
T
h
e
alg
o
r
ith
m
i
m
p
licat
io
n
s
i
n
itiat
e
w
ith
t
h
e
4
d
i
f
f
er
e
n
t
f
o
r
m
s
o
f
t
h
e
i
n
p
u
t
i.e
.
C
o
d
e
Han
d
lin
g
C
ap
ac
it
y
(
α
)
,
E
f
f
ec
tiv
e
E
f
f
o
r
t
(
β)
,
R
eso
u
r
ce
f
o
r
Ne
w
Desi
g
n
(
γ
)
,
an
d
E
r
r
o
r
P
r
o
b
ab
ilit
y
(
φ)
.
T
h
e
n
u
m
e
r
ical
v
al
u
es
o
f
t
h
i
s
in
p
u
t
ar
e
o
b
tain
ed
b
y
co
n
s
id
er
in
g
2
s
o
f
t
w
ar
e
e
n
g
i
n
ee
r
s
ca
p
ab
le
o
f
d
eliv
er
y
i
n
g
2
an
d
3
s
o
f
t
w
ar
e
co
d
es
f
o
r
n
e
w
p
r
o
j
ec
ts
in
2
6
w
o
r
k
i
n
g
d
a
y
s
.
T
o
tal
o
f
8
h
o
u
r
s
o
f
w
o
r
k
i
n
g
t
i
m
e
is
co
n
s
id
er
ed
f
o
r
th
is
p
u
r
p
o
s
e.
W
e
ad
h
er
e
to
th
e
s
ta
n
d
ar
d
o
f
th
e
n
e
u
r
al
n
et
w
o
r
k
b
ased
o
p
ti
m
izatio
n
p
o
licy
b
y
a
s
s
o
ciati
n
g
w
eig
h
t
s
w
it
h
th
e
in
p
u
t
attr
ib
u
te
s
.
T
h
e
ca
r
d
in
alit
y
o
f
t
h
e
in
p
u
t
lay
er
is
4
w
h
ile
th
at
o
f
t
h
e
in
ter
m
ed
iate
la
y
er
is
2
4
an
d
2
.
Si
m
ilar
l
y
,
t
h
e
ca
r
d
in
alit
y
o
f
th
e
o
u
tco
m
e
is
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
A
N
o
ve
l O
p
timiz
a
tio
n
to
w
a
r
d
s
Hig
h
er R
elia
b
ilit
y
in
P
r
ed
ictive
Mo
d
ellin
g
to
w
a
r
d
s
C
o
d
e
… (
Ma
n
o
j H
.
M.
)
2859
Fig
u
r
e
2
Sch
e
m
a
o
f
n
eu
r
al
n
et
w
o
r
k
u
s
ed
i
n
p
r
o
p
o
s
ed
s
y
s
te
m
T
h
e
n
eu
r
al
n
e
t
w
o
r
k
m
ap
p
in
g
co
n
f
i
g
o
f
n
o
d
es
ar
e
4
(
in
p
u
t)
-
2
4
(
in
ter
m
ed
iate)
-
2
(
o
u
p
u
t)
as
s
h
o
w
n
i
n
Fig
u
r
e
2
,
w
h
er
e
ca
r
d
in
alit
y
o
f
in
p
u
t
n
o
d
es
is
4
,
ca
r
d
in
al
it
y
o
f
h
id
d
en
n
o
d
es
is
2
4
,
an
d
ca
r
d
in
alit
y
o
f
o
u
tp
u
t
n
o
d
e
is
2
.
T
h
e
ess
en
tial s
tep
s
i
n
v
o
l
v
ed
in
p
r
o
p
o
s
ed
alg
o
r
ith
m
ar
e
as f
o
llo
w
s
:
O
pt
im
iza
t
i
o
n
Al
g
o
ri
t
hm
f
o
r
Co
de
R
eus
a
bil
i
t
y
I
np
ut
:
C
o
d
e
H
an
d
lin
g
C
a
p
ac
i
ty
(
α
)
,
E
f
f
ec
tiv
e
E
f
f
o
r
t
(
β
)
,
R
e
s
o
u
r
ce
f
o
r
New
Desig
n
(
γ
)
,
an
d
E
r
r
o
r
Pr
o
b
a
b
il
ity
(
φ
)
.
O
utpu
t
:
σ
re
l
(
r
eli
a
b
ili
ty
)
,
σ
s
ta
b
.
(
s
tab
ilit
y
at
tr
ib
u
t
e
)
Sta
r
t
:
1
.
in
it
Δ
=
[
α
,
β,
γ
,
ϕ
]
2
.
C
o
m
p
u
te
w
eig
h
t (
δ
)
3
.
a
=m
in
-
m
ax
(
v
alu
e(
Δ
)
)
4
.
n
o
r
m
(
Δ
,
o
)
[(
-
4
,
+
4
)
(
0
.
1
,
0
.
9
)
]
5
.
A
p
p
ly
tr
ain
g
_
A
lg
6
.
E
r
r
o
r
M
in
Ma
x
(
N
o
-
T
o
)
7
.
C
o
m
p
u
te
.
)
.(
2
1
c
c
re
l
&
σ
st
ab
.
E
nd
T
h
e
ab
o
v
e
m
en
tio
n
ed
al
g
o
r
ith
m
ad
o
p
ts
t
h
e
d
esi
g
n
p
r
in
cip
le
o
f
Fi
g
u
r
e
1
an
d
p
er
f
o
r
m
s
i
n
i
tializatio
n
o
f
m
u
ltip
le
attr
ib
u
te
s
ass
o
ciat
ed
w
it
h
th
e
ca
s
e
s
tu
d
ies
i.e
.
(
α
,
β,
γ
,
φ)
.
A
f
ter
in
itializi
n
g
t
h
e
in
p
u
t
attr
ib
u
te
s
(
L
in
e
-
1
)
,
t
h
e
n
ex
t
i
m
p
o
r
ta
n
t
s
tep
o
f
al
g
o
r
ith
m
i
s
to
c
o
m
p
u
te
w
e
ig
h
t
a
s
{(
4
(
in
p
u
t
la
y
er
)
x
2
4
(
h
id
d
en
la
y
er
)
)+
(
2
4
(
h
id
d
en
la
y
er
)
x
2
(
o
u
tp
u
t
la
y
er
)
)
=1
4
4
}.
T
h
is
w
ei
g
h
t
is
u
s
ed
f
o
r
co
m
p
u
ti
n
g
o
u
tp
u
t
(
L
in
e
-
7
)
.
T
h
e
p
r
im
e
tar
g
et
o
f
t
h
is
a
lg
o
r
it
h
m
i
s
to
e
v
o
l
v
e
u
p
w
i
t
h
a
n
u
m
b
er
o
f
p
er
ce
p
tr
o
n
s
la
y
er
s
f
o
r
t
h
e
p
u
r
p
o
s
e
o
f
p
r
ed
ictin
g
r
eliab
ili
t
y
attr
ib
u
te
an
d
s
tab
ili
t
y
attr
ib
u
te.
Var
io
u
s
f
o
r
m
s
o
f
iter
atio
n
s
h
av
e
b
ee
n
o
b
s
er
v
ed
i
n
o
r
d
er
to
lo
o
k
f
o
r
a
n
ell
ite
o
u
tco
m
e
o
f
o
p
ti
m
izatio
n
.
T
h
e
al
g
o
r
ith
m
p
er
f
o
r
m
s
p
r
o
ce
s
s
i
n
g
co
n
s
id
er
in
g
v
ar
io
u
s
n
u
m
b
er
s
o
f
p
er
m
u
tatio
n
s
w
it
h
in
p
u
t
attr
ib
u
tes.
A
p
ar
t
f
r
o
m
th
is
d
ata,
w
e
also
co
n
s
tr
u
cte
d
a
tr
ain
in
g
d
atase
t
w
h
er
e
elo
n
g
ated
s
er
ies
o
f
tr
a
in
i
n
g
d
ata
as
s
o
ciate
d
w
it
h
o
u
r
ca
s
e
s
t
u
d
y
is
d
ev
elo
p
ed
.
T
h
is
d
ata
w
as
ca
lled
d
u
r
in
g
i
m
p
licatio
n
o
f
t
h
e
tr
ai
n
in
g
al
g
o
r
ith
m
.
W
e
s
p
lit
th
e
d
a
ta
in
to
t
w
o
p
ar
ts
w
h
er
e
t
h
e
b
i
g
g
er
p
r
o
p
o
r
tio
n
o
f
th
e
d
ata
is
co
n
s
id
er
ed
f
o
r
ap
p
ly
in
g
i
ts
el
f
to
tr
ai
n
in
g
o
p
er
atio
n
i
n
n
e
u
r
al
n
et
w
o
r
k
a
n
d
s
m
all
er
p
r
o
p
o
r
tio
n
o
f
th
e
d
ata
is
co
n
s
id
er
ed
f
o
r
ca
r
r
y
i
n
g
o
u
t
i
n
ter
n
al
m
o
d
el
v
al
id
atio
n
.
B
o
th
th
e
i
n
p
u
t
s
attr
ib
u
te
Δ
an
d
o
u
tp
u
t
attr
ib
u
te
σ
h
as
b
ee
n
s
u
b
j
ec
ted
to
n
o
r
m
a
lizatio
n
ar
r
a
y
o
f
(
0
,
+1
)
.
T
h
e
n
u
m
er
ical
v
al
u
es
o
f
i
n
p
u
t
attr
i
b
u
tes
Δ
is
o
b
tai
n
ed
an
d
m
i
n
-
m
a
x
alg
o
r
it
h
m
i
s
ap
p
lied
(
L
in
e
-
3
)
.
T
h
e
alg
o
r
ith
m
a
ls
o
p
er
f
o
r
m
s
n
o
r
m
al
izatio
n
o
f
th
e
b
o
th
in
p
u
t
a
n
d
o
u
tp
u
t
n
u
m
er
ical
o
u
tco
m
e
s
to
en
s
u
r
e
t
h
at
th
e
n
u
m
er
ical
o
u
tco
m
es
ar
e
s
tatis
t
icall
y
w
i
th
i
n
p
r
o
b
ab
ilit
y
li
m
it
s
(
L
in
e
-
4
)
.
Fo
r
ea
s
in
e
s
s
i
n
co
m
p
u
tatio
n
,
w
e
c
h
o
o
s
e
th
e
n
o
r
m
aliza
tio
n
v
alu
e
o
f
i
n
p
u
t
a
s
-
4
to
+4
w
h
ile
th
a
t
o
f
o
u
tp
u
t
is
co
n
s
id
er
ed
to
b
e
0
.
1
to
0
.
9
.
T
h
ese
v
alu
e
s
ca
n
b
e
ch
an
g
ed
ac
co
r
d
in
g
to
th
e
test
en
v
ir
o
n
m
e
n
t;
h
o
w
ev
er
,
w
e
ch
o
o
s
e
th
is
v
a
l
u
e
o
f
s
h
ar
p
r
ese
m
b
le
m
s
w
it
h
o
u
t
co
n
s
id
er
atio
n
o
f
ca
s
e
s
t
u
d
y
.
A
f
ee
d
f
o
r
w
ar
d
n
eu
r
al
n
et
w
o
r
k
is
u
s
ed
as
a
m
ed
ia
o
f
tr
ain
i
n
g
alg
o
r
it
h
m
(
L
i
n
e
-
5
)
f
o
llo
w
ed
b
y
co
m
p
u
ta
tio
n
o
f
o
u
tp
u
t
f
r
o
m
n
eu
r
al
n
et
w
o
r
k
N
o
a
n
d
tr
ain
in
g
T
o
.
W
e
f
in
d
d
if
f
er
en
ce
o
f
t
h
ese
t
w
o
r
i
n
ter
m
ed
iate
o
u
tco
m
es
an
d
ag
ai
n
ap
p
l
y
m
i
n
-
m
a
x
al
g
o
r
ith
m
i
n
o
r
d
er
to
ex
tr
ac
t
th
e
p
o
s
s
ib
le
er
r
o
r
(
L
in
e
-
6
)
.
T
h
is
er
r
o
r
is
u
s
ed
f
o
r
in
ter
n
al
m
o
d
el
v
alid
atio
n
i
n
later
s
t
a
g
e
o
f
m
o
d
el
ch
ec
k
i
n
g
.
Fin
a
ll
y
,
w
e
co
m
p
u
te
th
e
r
eliab
ilit
y
attr
ib
u
te
σ
re
l
w
h
o
s
e
d
ep
en
d
ab
le
v
ar
iab
les
ar
e
c
1
,
c
2
,
Δ
,
a
n
d
δ
(
L
i
n
e
-
7
)
.
T
h
e
f
ir
s
t
v
ar
iab
le
c
1
r
ep
r
esen
ts
a
h
i
g
h
er
-
l
i
m
i
t
co
n
s
t
an
t
1
/0
.
8
w
h
ile
th
e
s
ec
o
n
d
v
ar
iab
le
c
2
r
ep
r
esen
t
lo
w
er
-
li
m
it
co
n
s
tan
t
o
f
v
a
lu
e
0
.
1
.
T
h
ese
v
alu
es
ca
n
b
e
s
u
itab
l
y
c
h
a
n
g
ed
b
ased
o
n
th
e
n
ec
e
s
s
it
y
o
f
t
h
e
an
ticip
ate
d
co
n
v
er
g
en
ce
o
u
tco
m
es.
T
h
e
co
n
s
id
er
atio
n
s
o
f
t
h
ese
v
a
lu
e
s
ar
e
p
u
r
ely
b
ased
o
n
p
r
o
b
ab
ilit
y
th
eo
r
y
.
A
d
o
p
ti
o
n
o
f
h
i
g
h
er
l
i
m
it
0
.
8
is
d
o
n
e
as
s
tat
is
tical
l
y
,
t
h
e
p
er
m
is
s
ib
le
h
i
g
h
er
l
i
m
it
i
s
til
l
0
.
8
,
w
h
ile
n
u
m
b
er
s
m
o
r
e
t
h
an
it is
co
n
s
id
er
ed
as i
m
p
r
ac
t
ical.
T
h
e
last
v
ar
iab
le
δ
is
w
e
ig
h
t
w
h
ic
h
is
eq
u
i
v
alen
t
to
1
4
4
in
o
u
r
ca
s
e.
Hen
ce
,
o
n
c
e
th
e
r
eliab
ilit
y
at
tr
ib
u
te
is
co
m
p
u
ted
,
w
e
ch
ec
k
f
o
r
s
t
ab
ilit
y
f
ac
to
r
i.e
.
σ
stab
j
u
s
t
to
en
s
u
r
e
th
e
to
tal
n
u
m
b
er
o
f
o
cc
u
r
a
n
ce
o
f
r
eliab
le
o
u
tco
m
es.
I
f
t
h
e
to
tal
f
r
eq
u
en
cie
s
o
f
m
aj
o
r
it
y
o
f
th
e
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
201
7
:
2
8
5
5
–
2
8
6
2
2860
g
en
er
ated
v
alu
e
s
o
f
σ
rel
is
n
ea
r
l
y
s
i
m
i
lar
th
a
n
w
e
co
n
s
id
er
th
at
th
e
p
r
o
p
o
s
ed
test
s
ce
n
ar
io
i
s
h
i
g
h
l
y
s
tab
le.
T
h
e
tr
ain
i
n
g
p
er
f
o
r
m
a
n
ce
w
as
ch
e
ck
ed
f
o
r
1
0
0
0
-
5
0
0
0
iter
atio
n
s
in
o
r
d
er
to
s
ee
th
e
co
n
v
er
g
en
ce
p
er
f
o
r
m
an
ce
o
f
b
o
th
ex
p
er
i
m
e
n
tal
an
d
h
y
p
o
t
h
etica
l
o
u
tco
m
es.
An
i
n
ter
esti
n
g
f
ac
t
ab
o
u
t
t
h
i
s
al
g
o
r
ith
m
i
s
t
h
at
it
is
m
o
r
e
p
r
o
n
e
to
co
n
v
er
g
e
to
w
ar
d
s
lo
w
er
r
o
r
r
ate
as
an
el
li
te
o
u
tco
m
e,
w
h
ic
h
e
n
s
u
r
es
t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
a
n
d
o
u
tco
m
e
w
h
o
s
e
v
al
id
atio
n
lea
d
s
to
h
i
g
h
l
y
a
u
th
e
n
tica
ted
o
u
t
co
m
e.
T
h
is
al
s
o
m
ea
n
s
t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
ca
n
tr
u
ell
y
o
p
ti
m
ize
t
h
e
co
n
ce
p
t o
f
co
d
e
r
eu
s
ab
ilit
y
u
n
d
er
co
n
s
id
er
atio
n
o
f
v
ar
io
u
s
r
ea
l
-
li
f
e
ch
a
llen
g
es i
n
s
o
f
t
w
ar
e
p
r
o
j
ec
t
d
ev
elo
p
m
en
t.
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
t
h
e
p
r
o
p
o
s
ed
al
g
o
r
ith
m
is
n
ea
r
l
y
f
o
u
n
d
s
i
m
i
lar
u
n
d
er
d
if
f
er
en
t
f
o
r
m
s
o
f
c
h
an
g
es
b
ein
g
ca
r
r
ied
o
u
t
to
w
ar
d
s
test
i
n
g
t
h
e
alg
o
r
ith
m
p
er
f
o
r
m
an
ce
.
A
t
t
h
e
s
a
m
e
ti
m
e
t
h
e
co
m
p
le
x
it
y
o
f
th
e
al
g
o
r
ith
m
is
als
o
f
o
u
n
d
q
u
ite
lo
w
.
T
h
e
n
e
x
t
s
ec
tio
n
d
is
c
u
s
s
es
a
b
o
u
t
th
e
o
u
tco
m
e
s
ac
co
m
p
li
s
h
ed
f
r
o
m
p
r
o
p
o
s
ed
s
tu
d
y
.
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
As
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
f
o
cu
s
e
s
m
ain
l
y
o
n
t
w
o
f
ac
to
r
s
i.e
.
o
p
ti
m
izatio
n
a
n
d
r
eliab
ilit
y
,
we
co
n
s
id
er
test
i
f
y
i
n
g
th
e
s
t
u
d
y
o
u
tco
m
e
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
n
t
h
e
b
asis
o
f
er
r
o
r
p
er
f
o
r
m
an
ce
o
f
p
r
o
p
o
s
ed
m
o
d
el,
v
alid
atio
n
p
er
f
o
r
m
an
ce
,
a
n
d
r
esp
o
n
s
e
ti
m
e
m
ain
l
y
.
T
h
e
m
o
d
el
is
allo
w
ed
to
iter
ate
f
o
r
2
0
,
0
0
0
r
o
u
n
d
s
in
o
r
d
er
to
ch
ec
k
th
e
co
n
v
er
g
e
n
ce
p
er
f
o
r
m
a
n
ce
.
Fi
g
u
r
e
3
(
a)
s
h
o
w
s
th
e
tr
ain
ed
r
esu
l
t
s
ig
n
i
f
ica
n
tl
y
co
n
v
er
g
e
s
w
it
h
th
e
b
est
f
it
r
es
u
lt
t
h
er
eb
y
s
h
o
w
i
n
g
th
e
h
i
g
h
er
r
eliab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
e
m
o
d
el
r
eliab
ilit
y
i
s
f
u
r
t
h
er
p
r
o
v
en
b
y
li
n
ea
r
it
y
tr
en
d
o
f
th
e
v
alid
atio
n
cu
r
v
e
in
Fi
g
u
r
e
3
(
b
)
.
A
lth
o
u
g
h
,
2
0
,
0
0
0
e
p
o
ch
s
h
as
b
ee
n
g
iv
e
n
,
b
u
t
t
h
e
co
n
v
er
g
e
n
ce
to
w
ar
d
s
elite
o
u
tco
m
e
w
as
s
ee
n
o
n
l
y
w
i
th
i
n
2
1
7
8
ep
o
ch
.
E
p
o
c
h
E
r
r
o
r
P
e
r
f
o
r
m
a
m
n
c
e
(
a)
E
r
r
o
r
p
e
r
f
o
r
m
a
n
ce
(
b
)
V
a
l
i
d
a
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
(
c)
C
o
m
p
ar
ati
v
e
r
esp
o
n
s
e
ti
m
e
(d
)
C
o
m
p
ar
ativ
e
er
r
o
r
p
er
f
o
r
m
an
ce
Fig
u
r
e
3
.
Ou
tco
m
e
o
f
p
r
o
p
o
s
e
d
s
tu
d
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
A
N
o
ve
l O
p
timiz
a
tio
n
to
w
a
r
d
s
Hig
h
er R
elia
b
ilit
y
in
P
r
ed
ictive
Mo
d
ellin
g
to
w
a
r
d
s
C
o
d
e
… (
Ma
n
o
j H
.
M.
)
2861
As
t
h
er
e
ar
e
v
ar
io
u
s
f
o
r
m
s
o
f
o
p
ti
m
iza
tio
n
tech
n
iq
u
e
s
t
h
er
ef
o
r
e
w
e
co
m
p
ar
e
o
u
r
o
p
ti
m
izat
io
n
tech
n
iq
u
e
u
s
in
g
n
e
u
r
al
n
et
w
o
r
k
a
n
d
v
ar
io
u
s
o
t
h
er
s
f
r
eq
u
e
n
tl
y
u
s
ed
o
p
ti
m
izat
io
n
tech
n
q
i
u
es
e.
g
.
k
-
Nea
r
est
Neig
h
b
o
u
r
(
KNN)
a
n
d
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
SV
M)
u
n
d
er
s
i
m
ilar
en
v
ir
o
n
m
e
n
t
p
ar
am
eter
s
.
T
h
e
a
n
al
y
s
i
s
s
h
o
w
s
th
at
p
r
o
p
o
s
ed
s
tu
d
y
o
f
f
er
s
i
g
n
if
ica
n
tl
y
lo
w
er
r
esp
o
n
s
e
ti
m
e
(
Fig
u
r
e
3
.
(
c)
)
an
d
h
i
g
h
er
r
eliab
ilit
y
as
s
ee
n
f
r
o
m
er
r
o
r
p
er
f
o
r
m
an
ce
(
Fig
u
r
e
3
.
(
d
)
)
.
KNN
-
alg
o
r
i
th
m
d
o
esn
’
t
g
iv
e
b
etter
o
u
tc
o
m
e
as
it
is
m
u
c
h
d
is
tan
ce
-
b
ased
ap
p
r
o
ac
h
f
o
r
a
ll
th
e
tr
ain
i
n
g
d
ata
w
h
ile
p
er
f
o
r
m
i
n
g
o
p
ti
m
izatio
n
.
T
h
er
ef
o
r
e
r
esp
o
n
s
e
ti
m
e
is
q
u
ite
h
i
g
h
er
as
w
ell
a
s
er
r
o
r
is
also
to
o
h
i
g
h
.
O
n
t
h
e
o
th
er
h
an
d
,
SVM
h
as
b
ett
er
p
er
f
o
r
m
an
ce
in
co
n
tr
ast
to
KNN
d
u
e
to
its
ab
ilit
y
to
p
er
f
o
r
m
b
o
th
li
n
ea
r
an
d
n
o
n
-
lin
ea
r
clas
s
if
icatio
n
.
A
d
o
p
tio
n
o
f
k
er
n
el
-
b
ased
ap
p
r
o
ac
h
also
ass
is
ts
it
to
o
f
f
e
r
b
etter
er
r
o
r
p
er
f
o
r
m
an
ce
.
Ho
w
e
v
er
,
th
e
r
esp
o
n
s
e
ti
m
e
co
u
l
d
b
e
o
n
l
y
lo
w
er
ed
to
ce
r
tain
ex
te
n
t
in
SVM,
w
h
i
ch
is
n
o
t
co
s
t
ef
f
ec
ti
v
e
in
n
at
u
r
e
alth
o
u
g
h
,
it
o
f
f
er
lo
w
er
ed
er
r
o
r
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
u
s
e
s
n
e
u
r
al
n
et
w
o
r
k
wh
o
s
e
ac
cu
r
ac
y
le
v
el
ca
n
b
e
in
cr
ea
s
in
g
l
y
co
n
tr
o
lled
in
ev
er
y
cy
cle
o
f
ep
o
ch
.
On
th
e
o
th
er
h
an
d
,
ad
o
p
tio
n
o
f
d
am
p
ed
least
s
q
u
ar
e
alg
o
r
ith
m
s
ig
n
i
f
ica
n
tl
y
a
s
s
i
s
ts
i
n
s
o
lv
i
n
g
n
o
n
-
li
n
ea
r
o
p
tim
izatio
n
p
r
o
b
le
m
a
n
d
h
e
n
ce
t
h
e
co
n
tr
ib
u
t
io
n
o
f
n
e
u
r
al
n
et
w
o
r
k
i
s
p
r
o
p
o
s
ed
s
y
s
te
m
is
m
o
r
e
i
n
cli
n
ed
to
er
r
o
r
p
e
r
f
o
r
m
a
n
ce
t
h
a
n
o
n
p
er
f
o
r
m
an
ce
ti
m
e.
Hen
ce
,
it
c
an
b
e
s
aid
t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
a
co
s
t
e
f
f
ec
tiv
e
a
s
w
ell
as
h
i
g
h
l
y
r
eli
ab
le
o
p
tim
izat
io
n
o
f
t
h
e
f
r
a
m
e
w
o
r
k
t
h
at
s
u
p
p
o
r
ts
co
d
e
r
eu
s
ab
ilit
y
.
5.
CO
NCLU
SI
O
N
T
h
e
co
n
ce
p
t
o
f
s
o
f
t
w
ar
e
r
eu
s
ab
ilit
y
h
a
s
r
ec
eiv
ed
lo
ts
o
f
atten
tio
n
w
ith
in
r
esear
ch
co
m
m
u
n
it
y
1
0
y
ea
r
s
b
ac
k
th
a
t
r
esu
lt
s
i
n
e
v
o
lu
tio
n
o
f
v
ar
io
u
s
s
ta
n
d
ar
d
s
o
f
t
w
ar
e
m
etr
ics.
Ho
w
ev
er
,
th
er
e
is
less
n
u
m
b
er
o
f
in
ter
est
s
to
w
ar
d
s
t
h
is
d
o
m
ain
f
o
u
n
d
as
t
h
er
e
ar
e
v
er
y
le
s
s
r
esear
ch
p
ap
er
s
in
th
is
.
C
o
d
e
r
eu
s
ab
ilit
y
i
s
o
n
e
o
f
th
e
p
ar
t
o
f
s
o
f
t
w
ar
e
r
eu
s
ab
il
it
y
th
a
t
h
as
n
ev
er
b
ein
g
i
n
v
esti
g
a
ted
in
p
ast
alth
o
u
g
h
t
h
e
co
n
ce
p
t
o
f
co
d
e
r
eu
s
ab
ilit
y
i
s
p
r
ac
ticed
i
n
m
an
y
o
r
g
a
n
izatio
n
w
it
h
o
u
t
e
v
en
f
o
llo
w
i
n
g
an
y
p
r
o
to
co
ls
.
T
h
e
p
r
i
m
e
r
ea
s
o
n
b
eh
i
n
d
it
is
t
h
at
t
h
er
e
ar
e
n
o
s
u
c
h
b
e
n
ch
m
ar
k
ed
m
o
d
el
s
i
n
th
i
s
r
e
g
ar
d
s
.
T
h
er
ef
o
r
e,
w
e
ad
d
r
ess
t
h
is
p
r
o
b
lem
b
y
ta
k
i
n
g
a
ca
s
e
s
t
u
d
y
t
h
at
m
i
m
ick
s
r
ea
l
-
ti
m
e
p
r
o
b
le
m
in
s
o
f
t
w
ar
e
d
ev
elo
p
m
e
n
t.
W
e
also
u
s
e
s
a
m
p
l
e
s
o
f
t
w
ar
e
p
r
o
j
ec
ts
an
d
co
m
p
u
te
s
its
co
n
v
e
n
tio
n
a
l
s
o
f
t
w
ar
e
m
etr
ics
v
alu
e
s
t
h
at
w
e
u
s
e
f
o
r
o
u
r
an
al
y
tical
m
o
d
ellin
g
.
W
e
in
tr
o
d
u
ce
a
f
o
r
m
u
la
tio
n
to
co
m
p
u
te
th
e
co
d
e
attr
ib
u
te
w
it
h
an
in
c
lu
s
io
n
o
f
co
d
e
r
eu
s
ab
ilit
y
lo
g
ic.
Neu
r
al
n
et
w
o
r
k
is
ap
p
lied
f
o
r
o
p
tim
izatio
n
to
f
i
n
d
th
at
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
ex
tr
e
m
el
y
lo
w
er
er
r
o
r
s
co
r
e
an
d
r
ed
u
ce
d
co
m
p
u
tatio
n
al
ti
m
e
in
co
m
p
ar
is
o
n
to
ex
i
s
ti
n
g
o
p
ti
m
izatio
n
t
ec
h
n
iq
u
es.
RE
F
E
R
E
NC
E
S
[1
]
J.
P
o
rtm
a
n
,
“
Bu
il
d
in
g
S
e
rv
ice
s E
n
g
in
e
e
rin
g
:
A
f
t
e
r
De
sig
n
,
Du
rin
g
Co
n
stru
c
ti
o
n
,”
J
o
h
n
W
il
e
y
&
S
o
n
s,
2
0
1
6
[2
]
R.
L
u
to
w
sk
i,
“
S
o
f
t
w
a
re
R
e
q
u
irem
e
n
ts:
En
c
a
p
su
lati
o
n
,
Qu
a
li
ty
,
a
n
d
Re
u
se
,
”
CRC
Pre
ss
,
2
0
1
6
[3
]
D.
W
ieb
u
sc
h
,
“
Re
u
sa
b
il
it
y
f
o
r
In
t
e
ll
ig
e
n
t
Re
a
lt
im
e
In
tera
c
ti
v
e
S
y
st
e
m
s,”
Bo
D
–
B
o
o
k
s
o
n
De
ma
n
d
-
Co
mp
u
ter
,
2
0
1
6
[4
]
J.
S
a
m
e
ti
n
g
e
r,
“
S
o
f
t
wa
re
En
g
in
e
e
rin
g
w
it
h
Re
u
sa
b
le Co
m
p
o
n
e
n
ts,
”
S
p
ri
n
g
e
r S
c
ie
n
c
e
&
Bu
sin
e
ss
M
e
d
ia
,
2
0
1
3
[5
]
M
.
Kra
e
li
n
g
,
A
n
d
re
w
M
c
Ka
y
,
“
S
o
f
twa
re
En
g
in
e
e
rin
g
f
o
r
Em
b
e
d
d
e
d
S
y
ste
m
s
,”
El
se
v
ier
In
c
,
2
0
1
3
[6
]
L
.
A
n
to
v
sk
i1
a
n
d
F
lo
ri
n
d
a
Im
e
r
i2
,
“
Re
v
ie
w
o
f
S
o
f
t
w
a
re
R
e
u
se
P
r
o
c
e
ss
e
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
Iss
u
e
s,
v
o
l.
1
0
,
issu
e
6
,
n
o
.
2
,
2
0
1
3
[7
]
P
.
S
.
S
a
n
d
h
u
,
A
a
sh
i
m
a
,
P
.
Ka
k
k
a
r
a
n
d
S
.
S
h
a
rm
a
,
“
A
su
rv
e
y
o
n
S
o
f
tw
a
re
Re
u
sa
b
il
it
y
,”
IEE
E
-
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
e
c
h
a
n
ic
a
l
a
n
d
E
lec
tr
ica
l
T
e
c
h
n
o
lo
g
y
,
S
in
g
a
p
o
re
,
p
p
.
7
6
9
-
7
7
3
,
2
0
1
0
[8
]
N.
P
a
d
h
y
,
R.
P
a
n
ig
ra
h
i
a
n
d
S
.
Ba
b
o
o
,
“
A
S
y
ste
m
a
ti
c
L
it
e
ra
tu
re
Re
v
ie
w
o
f
a
n
Ob
jec
t
Orie
n
ted
M
e
tri
c
:
Re
u
sa
b
il
it
y
,
”
IEE
E
-
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
m
p
u
t
a
ti
o
n
a
l
In
telli
g
e
n
c
e
a
n
d
Ne
two
rk
s,
Bh
u
b
a
n
e
sh
w
a
r
,
p
p
.
1
9
0
-
1
9
1
,
2
0
1
5
[9
]
H.M
.
M
a
n
o
j
a
n
d
A
.
N.
Na
n
d
a
k
u
m
a
r,
“
A
S
u
rv
e
y
o
n
M
o
d
e
ll
i
n
g
o
f
S
o
f
tw
a
r
e
M
e
tri
c
s
f
o
r
Ra
n
k
in
g
Co
d
e
Re
u
sa
b
il
it
y
in
Ob
jec
t
Orie
n
ted
De
sig
n
S
tag
e
,"
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
in
e
e
ri
n
g
Res
e
a
rc
h
&
T
e
c
h
n
o
lo
g
y
(
IJ
ER
T
),
v
o
l.
3
,
issu
e
.
1
2
,
2
0
1
4
[1
0
]
A
.
Hu
d
a
ib
,
A
.
Hu
n
e
it
i,
I.
Ot
h
m
a
n
,
“
S
o
f
tw
a
r
e
Re
u
sa
b
il
it
y
Clas
si
f
ic
a
ti
o
n
a
n
d
P
re
d
ica
ti
o
n
Us
in
g
S
e
lf
-
Org
a
n
izin
g
M
a
p
(S
OM)
,”
Co
mm
u
n
ica
ti
o
n
s
a
n
d
N
e
two
rk
,
p
p
.
1
7
9
-
1
9
2
,
2
0
1
6
[1
1
]
A
.
Kh
o
sh
k
b
a
rf
o
ro
u
sh
h
a
,
P
.
Ja
m
sh
id
i,
M
.
F
.
G
h
o
lam
i,
L
.
Wan
g
a
n
d
R.
Ra
n
jan
,
"
M
e
tri
c
s
f
o
r
BP
EL
P
r
o
c
e
ss
Re
u
sa
b
il
it
y
A
n
a
l
y
sis in
a
W
o
rk
f
lo
w
S
y
ste
m
,
"
in
IEE
E
S
y
ste
ms
J
o
u
rn
a
l,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
3
6
-
4
5
,
M
a
rc
h
2
0
1
6
.
[1
2
]
C.
T
ib
e
rm
a
c
in
e
,
S
.
S
a
d
o
u
,
M
.
T
.
T
.
T
h
a
t,
a
n
d
C.
Do
n
y
,
"
S
o
f
t
w
a
re
A
rc
h
it
e
c
tu
re
Co
n
stra
in
t
Re
u
se
-
by
-
c
o
m
p
o
siti
o
n
,"
Fu
tu
re
Ge
n
e
ra
ti
o
n
Co
m
p
u
ter
S
y
st
e
ms
,
v
o
l.
6
1
,
p
p
.
3
7
-
5
3
,
2
0
1
6
.
[1
3
]
M
.
T
a
h
ir,
F
.
Kh
a
n
,
M
.
Ba
b
a
r,
F
.
A
ri
f
,
a
n
d
F
.
Kh
a
n
,
"
F
ra
m
e
wo
rk
f
o
r
B
e
tt
e
r
Re
u
sa
b
il
it
y
in
C
o
m
p
o
n
e
n
t
Ba
se
d
S
o
f
tw
a
r
e
En
g
in
e
e
rin
g
,"
T
h
e
J
o
u
r
n
a
l
o
f
A
p
p
l
ied
E
n
v
iro
n
me
n
t
a
l
a
n
d
Bi
o
lo
g
ica
l
S
c
ien
c
e
s
(
J
AE
BS
),
v
o
l.
6
,
p
p
.
7
7
-
8
1
,
2
0
1
6
[1
4
]
W
.
V
.
D.
V
e
g
t,
W
.
W
im
,
E.
Ny
a
m
su
re
n
,
A
.
G
e
o
rg
ie
v
,
a
n
d
I.
M
.
Ortiz,
“
RAG
E
A
rc
h
it
e
c
tu
re
f
o
r
Re
u
sa
b
le
S
e
rio
u
s
G
a
m
in
g
Tec
h
n
o
lo
g
y
Co
m
p
o
n
e
n
ts
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
mp
u
ter
Ga
me
s T
e
c
h
n
o
lo
g
y
,
v
o
l.
3
,
2
0
1
6
[1
5
]
L
.
De
m
r
a
o
u
i,
H.
Be
h
ja,
a
n
d
R.
B.
A
b
b
o
u
,
“
A
Ca
s
e
-
b
a
se
d
Re
a
so
n
in
g
A
p
p
ro
a
c
h
to
t
h
e
Re
u
sa
b
il
it
y
o
f
C
W
M
M
e
tad
a
ta
,”
In
S
y
ste
ms
o
f
Co
ll
a
b
o
ra
ti
o
n
(
S
y
sCo
),
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
,
p
p
.
1
-
6
,
2
0
1
6
[1
6
]
I.
Y.Y.
A
h
m
a
ro
,
M
.
Z.
b.
M
.
Yu
so
f
f
,
a
n
d
A
.
M
.
A
b
u
a
lk
ish
ik
,
"
T
h
e
Cu
rre
n
t
P
ra
c
ti
c
e
s
o
f
S
o
f
t
w
a
r
e
Re
u
sa
b
il
it
y
A
p
p
ro
a
c
h
e
s
in
M
a
lay
sia
,”
In
S
o
ft
wa
re
En
g
in
e
e
rin
g
Co
n
fer
e
n
c
e
(
M
y
S
EC),
8
th
M
a
l
a
y
sia
n
,
p
p
.
1
7
2
-
1
7
6
,
2
0
1
4
.
[1
7
]
M.
I.
A.
Ef
a
t,
M
.
S.
S
id
d
ik
,
M
.
S
h
o
y
a
ib
,
a
n
d
S
.
M.
Kh
a
led
,
“
F
e
a
tu
re
P
rio
ri
ti
z
a
ti
o
n
f
o
r
A
n
a
l
y
z
in
g
a
n
d
En
h
a
n
c
in
g
S
o
f
tw
a
r
e
Re
u
sa
b
il
it
y
,
”
In
In
fo
rm
a
ti
c
s,
El
e
c
tro
n
ics
&
Vi
sio
n
(
ICIEV
),
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
,
p
p
.
1
-
5
,
2
0
1
4
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
201
7
:
2
8
5
5
–
2
8
6
2
2862
[1
8
]
I.
J.
M
o
ji
c
a
,
B.
A
d
a
m
s,
M
.
Na
g
a
p
p
a
n
,
S
.
Die
n
st,
T
.
Be
rg
e
r,
a
n
d
A.
E.
Ha
ss
a
n
,
“
A
L
a
r
g
e
-
sc
a
le
E
m
p
iri
c
a
l
S
tu
d
y
on
S
o
f
tw
a
r
e
Re
u
se
In
M
o
b
il
e
A
p
p
s
”
,
IEE
E
so
ft
wa
re
,
v
o
l
.
3
1
,
n
o
.
2
,
p
p
.
7
8
-
8
6
,
2
0
1
4
.
[1
9
]
S
.
Na
z
ir,
S
.
A
n
wa
r,
S
.
A
.
Kh
a
n
,
S
.
S
h
a
h
z
a
d
,
M
.
A
li
,
R.
Am
in
,
M
.
Na
w
a
z
,
P
.
L
a
z
a
rid
is,
a
n
d
J.
Co
s
m
a
s,
“
S
o
f
t
w
a
re
Co
m
p
o
n
e
n
t
S
e
lec
ti
o
n
Ba
se
d
on
Qu
a
li
ty
Crit
e
ria
U
sin
g
th
e
A
n
a
l
y
ti
c
Ne
t
w
o
rk
P
ro
c
e
ss
,”
In
Ab
str
a
c
t
a
n
d
Ap
p
li
e
d
An
a
lys
is,
v
o
l
.
2
0
1
4
[2
0
]
W
.
S
p
o
e
lstra,
M
.
Ia
c
o
b
,
a
n
d
M
.
V.
S
in
d
e
re
n
,
“
S
o
f
tw
a
r
e
Re
u
se
in
A
g
il
e
De
v
e
lo
p
m
e
n
t
Org
a
n
iza
ti
o
n
s
:
a
Co
n
c
e
p
t
u
a
l
M
a
n
a
g
e
m
e
n
t
T
o
o
l
,
”
In
Pr
o
c
e
e
d
in
g
s o
f
th
e
ACM
S
y
m
p
o
si
u
m o
n
A
p
p
li
e
d
C
o
mp
u
ti
n
g
,
p
p
.
3
1
5
-
3
2
2
,
2
0
1
1
[2
1
]
M
a
n
o
j
H.
M
,
Dr.
Na
n
d
a
k
u
m
a
r
A
.
N,
“
Co
n
str
u
c
ti
n
g
Re
latio
n
sh
i
p
B
e
twe
e
n
S
o
f
twa
re
M
e
tri
c
s
a
n
d
Co
d
e
Re
u
sa
b
il
it
y
in
Ob
jec
t
Orie
n
ted
De
sig
n
,”
(IJ
ACSA
)
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
A
p
p
li
c
a
ti
o
n
s,
Vo
l.
7
,
No
.
2
,
2
0
1
6
[2
2
]
F
.
Z
h
u
,
Y.
Ya
o
,
H.
C
h
e
n
,
a
n
d
F
.
Ya
o
,
“
Re
u
sa
b
le
Co
m
p
o
n
e
n
t
M
o
d
e
l
De
v
e
lo
p
m
e
n
t
A
p
p
ro
a
c
h
f
o
r
P
a
ra
ll
e
l
a
n
d
Distrib
u
te
d
S
im
u
latio
n
,”
T
h
e
S
c
ie
n
ti
fi
c
W
o
rl
d
J
o
u
rn
a
l
,
p
p
.
1
2
,
2
0
1
4
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
R
M
a
n
o
j
H
M
,
C
u
rre
n
tl
y
w
o
rk
in
g
a
s A
ss
i
sta
n
t
P
ro
f
e
ss
o
r,
De
p
t
o
f
CS
E,
a
n
d
Do
n
Bo
sc
o
I
n
stit
u
te o
f
T
e
c
h
n
o
lo
g
y
,
Ba
n
g
a
lo
re
,
In
d
ia.
He
h
a
s to
tal
e
x
p
e
rien
c
e
o
f
6
y
e
a
rs &
4
m
o
n
th
s
in
tea
c
h
i
n
g
.
His
re
se
a
rc
h
d
o
m
a
in
is
S
o
f
twa
re
En
g
in
e
e
rin
g
.
He
h
a
s co
m
p
lete
d
B.
E
i
n
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
f
ro
m
Ka
lp
a
taru
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
T
ip
tu
r,
In
d
ia.
A
n
d
M
.
T
e
c
h
in
S
o
f
twa
re
En
g
in
e
e
rin
g
f
ro
m
Eas
t
P
o
i
n
t
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
Ba
n
g
a
lo
re
,
In
d
ia.
He
h
a
s
p
u
b
li
sh
e
d
3
re
se
a
rc
h
p
a
p
e
rs i
n
i
n
t
e
rn
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
5
tec
h
n
ica
l
p
a
p
e
rs i
n
In
tern
a
ti
o
n
a
l/
Na
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s.
He
is
p
u
rsu
i
n
g
P
h
.
D
in
C
o
m
p
u
ter S
c
ien
c
e
&
En
g
in
e
e
rin
g
f
ro
m
Ja
in
Un
iv
e
rsit
y
,
Ba
n
g
a
lo
re
,
In
d
ia.
Dr.
Na
n
d
a
Ku
m
a
r
A
N,
P
r
o
f
e
ss
o
r
in
th
e
De
p
t
o
f
CS
E,
NH
CE,
Ba
n
g
a
lo
re
.
He
h
a
s m
o
re
th
a
n
3
5
y
e
a
rs o
f
te
a
c
h
in
g
e
x
p
e
rien
c
e
.
He
h
a
s co
m
p
lete
d
P
.
h
D f
ro
m
Be
rh
a
n
p
u
r
U
n
iv
e
rsity
.
He
h
a
s d
o
n
e
BE
in
E
lec
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
f
ro
m
M
y
so
re
U
n
iv
e
rsity
,
M
y
so
re
,
In
d
ia.
He
h
a
s co
m
p
lete
d
M
.
T
e
c
h
in
Co
m
p
u
t
e
r
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
f
ro
m
Ro
o
rk
e
e
Un
iv
e
rsity
Ro
o
rk
e
e
.
He
h
a
s p
u
b
li
sh
e
d
m
o
re
th
a
n
5
0
re
se
a
rc
h
p
a
p
e
rs i
n
v
a
rio
u
s
In
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
in
ter
n
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s.
His a
re
a
o
f
in
tere
sts in
c
lu
d
e
so
f
tw
a
r
e
En
g
in
e
e
rin
g
,
Im
a
g
e
p
ro
c
e
ss
in
g
,
w
irel
e
ss
se
n
so
r
n
e
tw
o
rk
s,
p
a
ra
ll
e
l
c
o
m
p
u
ti
n
g
a
n
d
o
th
e
rs.
He
h
a
s als
o
se
rv
e
d
a
s P
ri
n
c
ip
a
l
i
n
m
a
n
y
re
p
u
ted
e
n
g
in
e
e
rin
g
c
o
ll
e
g
e
s in
Ka
rn
a
tak
a
a
n
d
A
n
d
h
ra
in
c
l
u
d
i
n
g
De
a
n
(re
se
a
rc
h
)
in
a
re
p
u
ted
u
n
iv
e
rsit
y
in
T
a
m
il
Na
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.