I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
4
,
No
.
1
,
Ma
r
ch
2
0
1
5
,
p
p
.
14
~
19
I
SS
N:
2252
-
8938
14
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
J
AI
Desig
n
a
nd Devel
o
p
m
en
t
o
f
a
n
Ago
rith
m
for Pr
io
ri
ti
z
ing
the
T
est Cas
es Using
Neura
l Ne
tw
o
rk
a
s Cla
ss
ifier
A
m
it
Ver
m
a
,
E
r.
Si
m
ra
nje
et
K
a
ur
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
C
h
a
n
d
ig
a
rh
U
n
iv
e
rsit
y
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
4
,
2
0
1
4
R
ev
i
s
ed
J
an
5
,
2
0
1
5
A
cc
ep
ted
Feb
5
,
2
0
1
5
T
e
st
C
a
se
P
rio
rit
iza
ti
o
n
(T
CP
)
h
a
s
g
a
in
e
d
w
id
e
sp
re
a
d
a
c
c
e
p
tan
c
e
a
s
it
o
f
ten
re
su
lt
s
in
g
o
o
d
q
u
a
li
ty
so
f
t
w
a
r
e
fre
e
f
ro
m
d
e
f
e
c
ts.
Du
e
to
th
e
in
c
re
a
se
in
ra
te
o
f
f
a
u
lt
s
in
so
f
twa
re
trad
it
io
n
a
l
tec
h
n
iq
u
e
s
f
o
r
p
rio
rit
iza
ti
o
n
re
su
lt
s
in
in
c
re
a
se
d
c
o
st
a
n
d
ti
m
e
.
M
a
in
c
h
a
ll
e
n
g
e
in
T
C
P
is
d
if
f
icu
lt
y
in
m
a
n
u
a
ll
y
v
a
li
d
a
te t
h
e
p
rio
rit
ies
o
f
d
iff
e
re
n
t
tes
t
c
a
s
e
s d
u
e
to
larg
e
siz
e
o
f
t
e
st
su
it
e
s an
d
n
o
m
o
re
e
m
p
h
a
sis
a
re
m
a
d
e
to
m
a
k
e
th
e
TCP
p
r
o
c
e
ss
a
u
to
m
a
te.
T
h
e
o
b
jec
ti
v
e
o
f
th
is
p
a
p
e
r
is
t
o
d
e
te
c
t
th
e
p
ri
o
rit
ies
o
f
d
if
f
e
r
e
n
t
tes
t
c
a
se
s
u
sin
g
a
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
w
h
ic
h
h
e
l
p
s
to
p
re
d
ict
th
e
c
o
rre
c
t
p
ri
o
rit
ies
w
it
h
th
e
h
e
lp
o
f
b
a
c
k
p
ro
p
a
g
a
ti
o
n
a
l
g
o
rit
h
m
.
In
o
u
r
p
ro
p
o
se
d
w
o
rk
o
n
e
su
c
h
m
e
th
o
d
is
im
p
le
m
e
n
ted
in
w
h
ich
p
rio
ri
ti
e
s
a
re
a
ss
ig
n
e
d
to
d
iff
e
re
n
t
tes
t
c
a
se
s
b
a
se
d
o
n
th
e
ir
f
re
q
u
e
n
c
y
.
Af
t
e
r
a
ss
i
g
n
in
g
th
e
p
rio
rit
ies
A
N
N
p
re
d
icts
w
h
e
th
e
r
c
o
rre
c
t
p
rio
rit
y
i
s
a
ss
i
g
n
e
d
to
e
v
e
r
y
tes
t
c
a
se
o
r
n
o
t
o
t
h
e
rw
ise
it
g
e
n
e
ra
tes
th
e
in
terru
p
t
w
h
e
n
w
ro
n
g
p
rio
r
it
y
is
a
ss
i
g
n
e
d
.
In
o
rd
e
r
to
c
las
sify
th
e
d
if
f
e
re
n
t
p
rio
rit
y
tes
t
c
a
se
s
c
las
si
f
iers
a
re
u
se
d
.
P
ro
p
o
se
d
a
l
g
o
rit
h
m
is
v
e
r
y
e
ff
e
c
ti
v
e
a
s
it
re
d
u
c
e
s
th
e
c
o
m
p
lex
it
y
w
it
h
ro
b
u
st
e
f
f
i
c
ien
c
y
a
n
d
m
a
k
e
s
th
e
p
r
o
c
e
ss
a
u
to
m
a
ted
to
p
ri
o
rit
iz
e
th
e
tes
t
c
a
se
s.
K
ey
w
o
r
d
:
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
C
las
s
i
f
icatio
n
So
f
t
w
ar
e
test
in
g
T
est ca
s
e
p
r
io
r
itizatio
n
TF
-
I
DF
Co
p
y
rig
h
t
©
2
0
1
5
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
:
Er.
Si
m
r
an
j
ee
t K
au
r
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
&
E
n
g
in
ee
r
i
n
g
,
C
h
a
n
d
ig
ar
h
U
n
iv
er
s
it
y
,
I
n
d
ia.
E
m
ail:
s
i
m
r
a
n
j
ee
tg
ill2
3
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
So
f
t
w
ar
e
e
n
g
in
ee
r
i
n
g
i
s
t
h
e
s
tu
d
y
an
d
ap
p
licatio
n
o
f
en
g
i
n
ee
r
in
g
to
t
h
e
d
esi
g
n
,
d
ev
elo
p
m
en
t
a
n
d
m
ai
n
ten
a
n
ce
o
f
t
h
e
s
o
f
t
w
ar
e.
T
h
e
m
ai
n
ai
m
o
f
s
o
f
t
w
ar
e
test
in
g
i
s
to
h
elp
th
e
d
esi
g
n
er
s
,
d
ev
elo
p
er
s
to
b
u
ild
a
s
y
s
te
m
o
f
h
ig
h
er
q
u
al
it
y
f
r
ee
f
r
o
m
d
ef
ec
ts
.
So
f
t
w
a
r
e
d
ef
ec
ts
ar
e
ca
u
s
ed
d
u
e
to
th
e
i
n
ad
eq
u
ac
y
o
f
s
o
f
t
w
ar
e
test
i
n
g
.
Di
f
f
er
en
t
to
o
ls
,
alg
o
r
i
th
m
s
an
d
tec
h
n
iq
u
es
ar
e
n
ee
d
ed
f
o
r
ef
f
icie
n
t
an
d
ef
f
ec
ti
v
e
test
i
n
g
i
n
o
r
d
er
t
o
co
m
p
lete
t
h
e
test
i
n
g
p
r
o
ce
s
s
w
it
h
i
n
li
m
ited
ti
m
e
an
d
b
u
d
g
et
co
n
s
tr
ain
t
s
.
I
n
cr
ea
s
e
th
e
li
k
elih
o
o
d
o
f
r
ev
ea
lin
g
f
au
lts
r
elate
d
to
s
p
ec
i
f
ic
co
d
e
ch
a
n
g
e
s
i
n
t
h
e
r
e
g
r
ess
io
n
te
s
tin
g
p
r
o
ce
s
s
.
T
h
e
f
ie
ld
o
f
n
e
u
r
al
n
et
w
o
r
k
s
h
as
a
h
is
to
r
y
o
f
s
o
m
e
f
i
v
e
d
ec
ad
es
b
u
t
h
a
s
f
o
u
n
d
ap
p
licatio
n
o
n
l
y
i
n
t
h
e
p
ast
f
i
f
tee
n
y
ea
r
s
,
a
n
d
th
e
f
ield
i
s
s
t
ill
d
ev
elo
p
in
g
co
n
ti
n
u
o
u
s
l
y
.
Neu
r
al
n
et
w
o
r
k
s
ar
e
co
llectio
n
o
f
ele
m
e
n
ts
.
Ne
u
r
al
n
et
w
o
r
k
is
ab
le
to
u
s
e
s
o
m
e
h
id
d
en
u
n
k
n
o
w
n
i
n
f
o
r
m
atio
n
in
t
h
e
d
ata.
T
h
is
p
r
o
ce
s
s
o
f
c
ap
tu
r
in
g
h
id
d
en
in
f
o
r
m
a
tio
n
i
s
ca
lled
lear
n
i
n
g
o
r
tr
ain
i
n
g
n
et
w
o
r
k
.
W
e
ca
n
tr
ai
n
a
n
e
u
r
al
n
et
w
o
r
k
to
p
er
f
o
r
m
a
p
ar
ticu
lar
f
u
n
c
tio
n
b
y
ad
j
u
s
ti
n
g
t
h
e
v
al
u
es
o
f
th
e
co
n
n
ec
tio
n
s
(
w
ei
g
h
t
s
)
b
etw
ee
n
ele
m
en
ts
.
Ma
n
y
tec
h
n
i
q
u
es
an
d
tec
h
n
o
lo
g
ies
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
an
d
ev
alu
a
ted
b
u
t
s
o
n
o
n
e
o
f
t
h
e
tech
n
o
lo
g
y
f
o
c
u
s
ed
o
n
to
as
s
ig
n
t
h
e
p
r
io
r
ities
b
ased
o
n
t
h
eir
f
r
eq
u
en
c
y
i
n
a
p
ar
ticu
lar
ca
s
e
an
d
to
ch
ec
k
t
h
e
ac
cu
r
ac
y
u
s
i
n
g
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
it
h
m
i
n
ar
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
a
n
d
to
d
if
f
er
e
n
tiate
b
et
w
ee
n
th
e
h
i
g
h
est an
d
lo
w
est p
r
io
r
it
y
u
s
i
n
g
c
lass
i
f
ier
s
.
T
h
e
p
ap
e
r
’
s
o
r
g
an
iza
tio
n
is
a
s
f
o
llo
w
s
:
1.
Sectio
n
2
d
escr
ib
es th
e
o
v
er
v
i
e
w
o
f
t
h
e
liter
at
u
r
e.
2.
Sectio
n
3
d
escr
ib
es th
e
p
r
o
b
lem
s
tate
m
e
n
t.
3.
Sectio
n
4
d
escr
ib
es th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
f
o
r
p
r
io
r
itizatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Desig
n
A
n
d
Dev
elo
p
men
t
o
f A
n
A
g
o
r
ith
m
fo
r
P
r
io
r
itiz
in
g
th
e
Tes
t Ca
s
e
s
Us
in
g
… (
A
mi
t V
erma
)
15
4.
Sectio
n
5
d
escr
ib
es th
e
r
es
u
lt
an
d
an
al
y
s
i
s
.
5.
Sectio
n
6
co
v
er
s
th
e
co
n
clu
s
io
n
an
d
f
u
t
u
r
e
w
o
r
k
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
G.
R
o
th
er
m
el,
R
.
U
n
tch
,
C
.
C
h
u
,
M.
J
.
Har
r
o
ld
(
2
0
0
1
)
d
is
cu
s
s
ed
t
h
e
u
s
e
o
f
test
ca
s
e
p
r
io
r
itizatio
n
i
n
r
eg
r
ess
io
n
test
i
n
g
a
n
d
d
escr
ib
es
v
ar
io
u
s
tech
n
iq
u
e
s
s
u
c
h
as
b
ased
o
n
to
tal
co
v
er
ag
e
o
f
co
d
e
co
m
p
o
n
e
n
ts
a
n
d
b
ased
o
n
f
a
u
lt
d
etec
tio
n
a
b
ilit
y
.
T
h
e
au
t
h
o
r
co
n
cl
u
d
es
th
at
v
er
s
io
n
-
s
p
ec
i
f
ic
p
r
io
r
itizatio
n
p
r
o
d
u
ce
i
m
p
r
o
v
e
m
en
t
s
in
f
au
lt
d
etec
tio
n
r
ate.
I
n
v
esti
g
atio
n
is
d
o
n
e
to
f
in
d
th
e
alter
n
ati
v
e
p
r
io
r
itizatio
n
g
o
als
a
n
d
to
in
cr
ea
s
e
t
h
e
ef
f
ec
ti
v
e
n
ess
.
Me
en
ak
s
h
i
v
a
n
m
ali,
A
b
r
ah
e
m
Kan
d
el
(
2
0
0
2
)
p
r
esen
ted
a
n
e
w
co
n
ce
p
t
o
f
u
s
i
n
g
an
ar
tifi
c
ial
n
eu
r
al
n
et
w
o
r
k
as
a
n
au
to
m
a
ted
o
r
ac
le
f
o
r
test
in
g
s
o
f
t
w
ar
e
s
y
s
te
m
.
A
u
th
o
r
r
ep
r
esen
ts
ex
p
er
i
m
e
n
tal
r
esu
lts
u
s
i
n
g
a
t
w
o
la
y
er
n
e
u
r
al
n
et
w
o
r
k
to
d
etec
t
th
e
f
a
u
lts
w
it
h
i
n
m
u
tate
d
co
d
e
o
f
s
m
all
cr
ed
it
ca
r
d
ap
p
r
o
v
al
ap
p
licatio
n
.
T
h
is
ap
p
r
o
ac
h
o
r
d
er
s
th
e
tes
t
ca
s
es
i
n
to
s
i
m
ilar
g
r
o
u
p
s
in
s
te
ad
o
f
o
r
d
er
in
g
th
e
m
ac
co
r
d
in
g
to
th
eir
p
r
ef
er
en
ce
d
eg
r
ee
,
s
o
th
ese
test
ca
s
es a
r
e
class
i
f
ied
u
s
in
g
M
L
P
n
e
u
r
al
n
et
w
o
r
k
.
E
r
ick
C
a
n
t
ú
-
P
az
,
C
h
a
n
d
r
ik
a
Ka
m
at
h
(
2
0
0
5
)
p
r
esen
ted
a
co
m
p
ar
is
o
n
o
f
e
ig
h
t
co
m
b
i
n
ati
o
n
s
o
f
E
As
an
d
NNs
to
8
class
if
ica
tio
n
p
r
o
b
lem
s
.
T
h
e
au
th
o
r
ex
p
er
i
m
e
n
ted
w
it
h
r
ea
l
an
d
b
in
ar
y
en
co
d
ed
E
A
s
to
tr
ain
th
e
n
et
w
o
r
k
s
.
E
A
Alg
o
r
it
h
m
s
u
s
e
d
to
tr
ain
t
h
e
n
et
w
o
r
k
,
d
esi
g
n
th
eir
ar
c
h
itect
u
r
e
a
n
d
s
elec
t
t
h
e
f
ea
t
u
r
e
s
u
b
s
ets
.
Usi
n
g
g
e
n
etic
al
g
o
r
ith
m
s
to
s
elec
t
t
h
e
f
ea
t
u
r
e
s
u
b
s
e
t
y
iel
d
ed
th
e
m
o
s
t
ac
cu
r
ate
clas
s
i
f
ier
s
.
E
A
a
n
d
NN
co
m
b
i
n
atio
n
s
w
er
e
n
o
t a
cc
u
r
at
e
th
an
n
et
w
o
r
k
s
tr
ain
ed
w
it
h
s
i
m
p
le
b
ac
k
p
r
o
p
ag
atio
n
.
Dr
.
A
r
v
i
n
d
er
Kau
r
an
d
Sh
i
v
a
n
g
i G
o
y
al
(
2
0
1
1
)
p
r
esen
ted
a
b
ee
co
lo
n
y
o
p
ti
m
izat
io
n
a
lg
o
r
it
h
m
f
o
r
th
e
f
au
lt
co
v
er
ag
e
r
eg
r
e
s
s
io
n
te
s
t
s
u
ite
p
r
io
r
itizatio
n
w
h
ic
h
is
d
o
n
e
b
y
s
tu
d
y
i
n
g
f
o
o
d
f
o
r
ag
in
g
b
eh
av
io
r
o
f
b
ee
s
.
T
h
e
E
f
f
ec
tiv
e
o
f
th
is
a
lg
o
r
it
h
m
h
as
b
ee
n
p
r
esen
ted
u
s
in
g
AP
FD
m
etr
ic
s
a
n
d
ch
ar
t.
T
h
e
ch
allen
g
e
f
ac
ed
i
n
t
h
i
s
alg
o
r
ith
m
is
t
h
e
r
eq
u
ir
e
m
en
t o
f
m
a
n
u
al
i
n
ter
f
ac
e
f
o
r
test
i
n
p
u
t d
ata.
Sh
i
f
a
-
e
-
Z
e
h
r
a
Haid
r
y
,
T
i
m
Miller
(
2
0
1
3
)
p
r
o
p
o
s
ed
a
n
e
w
s
e
t
o
f
tech
n
iq
u
es
f
o
r
f
u
n
ct
io
n
al
te
s
t
ca
s
e
p
r
io
r
itizatio
n
b
ased
o
n
th
e
i
n
h
er
en
t
s
tr
u
ct
u
r
e
o
f
d
ep
en
d
e
n
c
ies
b
et
w
ee
n
t
h
e
te
s
ts
.
T
h
e
au
t
h
o
r
co
n
clu
d
es
t
h
at
test
s
u
i
tes
p
r
io
r
itized
b
y
th
i
s
t
ec
h
n
iq
u
e
o
u
tp
er
f
o
r
m
s
t
h
e
r
an
d
o
m
an
d
u
n
tr
ea
ted
test
s
u
ite
s
b
u
t
n
o
t
ef
f
ic
ien
t
a
s
g
r
ee
d
y
test
s
u
i
tes.
Nid
a
Go
k
ce
,
Mu
b
ar
iz
E
m
i
n
li
(
2
0
1
4
)
s
o
lv
ed
th
e
p
r
o
b
lem
b
y
ap
p
ly
i
n
g
class
if
ica
tio
n
ap
p
r
o
ac
h
to
th
e
f
u
n
ctio
n
al
r
elatio
n
s
h
ip
b
et
w
e
en
t
h
e
test
ca
s
e
p
r
io
r
itizatio
n
g
r
o
u
p
m
e
m
b
er
s
h
ip
an
d
a
u
t
h
o
r
estab
lis
h
ed
t
h
e
i
m
p
o
r
tan
t
in
d
e
x
a
n
d
f
r
eq
u
en
c
y
f
o
r
all
t
h
e
ev
e
n
ts
b
elo
n
g
i
n
g
to
g
iv
e
n
g
r
o
u
p
ar
e
e
s
tab
l
is
h
ed
.
T
h
e
a
u
t
h
o
r
i
m
p
r
o
v
ed
th
e
n
e
w
test
ca
s
e
m
o
d
el
b
ased
ap
p
r
o
ac
h
in
w
h
ic
h
w
h
er
e
i
n
s
tead
o
f
o
r
d
er
in
g
te
s
t
ca
s
es
ac
co
r
d
in
g
to
th
eir
p
r
e
f
er
en
ce
d
eg
r
ee
,
th
e
y
a
r
e
au
to
m
atica
ll
y
d
iv
id
ed
in
to
g
r
o
u
p
s
an
d
h
e
n
ce
d
ataset
is
cl
ass
i
f
ied
u
s
in
g
M
L
P
n
eu
r
al
n
et
w
o
r
k
.
3.
CURR
E
NT
AR
E
AS
T
O
B
E
WO
RK
UP
O
N
T
h
e
p
r
o
b
lem
s
tated
in
t
h
is
p
ap
er
ca
n
b
e
f
o
r
m
all
y
s
tated
as:
T
h
er
e
is
a
d
o
cu
m
e
n
t
h
av
in
g
l
ar
g
e
n
u
m
b
er
o
f
w
o
r
d
s
.
W
e
h
av
e
to
p
r
io
r
itize
th
e
w
o
r
d
s
ac
co
r
d
in
g
to
th
eir
f
r
eq
u
e
n
c
y
in
a
d
o
cu
m
e
n
t
an
d
c
h
ec
k
t
h
e
ac
c
u
r
ac
y
u
s
i
n
g
b
ac
k
p
r
o
p
ag
atio
n
al
g
o
r
ith
m
.
Di
f
f
er
en
t
iate
t
h
e
h
ig
h
e
s
t a
n
d
lo
w
est p
r
io
r
it
y
w
o
r
d
s
w
it
h
t
h
e
h
elp
o
f
clas
s
i
f
ier
s
f
o
r
ea
s
y
p
r
ed
ictio
n
s
.
Nee
d a
nd
Sig
nifica
nce:
Var
io
u
s
T
est ca
s
e
p
r
io
r
itizatio
n
tec
h
n
iq
u
es a
r
e
i
m
p
le
m
en
ted
an
d
d
is
cu
s
s
ed
b
u
t
y
et
n
o
s
u
c
h
alg
o
r
ith
m
in
w
h
ic
h
test
ca
s
e
p
r
io
r
itizatio
n
is
d
o
n
e
u
s
in
g
n
e
u
r
al
n
et
wo
r
k
s
.
A
r
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
h
elp
s
to
co
r
r
ec
tl
y
ass
i
g
n
th
e
p
r
io
r
ities
a
n
d
it
g
e
n
er
ates
t
h
e
i
n
ter
r
u
p
t
w
h
e
n
w
r
o
n
g
p
r
io
r
ities
ar
e
as
s
i
g
n
ed
to
d
if
f
er
e
n
t
te
s
t
ca
s
e
s
.
T
h
er
e
is
also
a
n
ee
d
to
m
a
k
e
t
h
e
p
r
o
ce
s
s
au
to
m
ate
as n
o
e
f
f
o
r
ts
ar
e
y
et
m
ad
e.
4.
AL
G
O
RI
T
H
M
C
alcu
latio
n
o
f
T
F
-
I
DF
i
s
th
e
m
o
s
t
i
m
p
o
r
tan
t
d
e
m
an
d
i
n
g
p
ar
t
o
f
th
e
i
m
p
le
m
en
ted
al
g
o
r
ith
m
.
Fo
r
C
alcu
lati
n
g
th
e
T
F
-
I
DF
v
al
u
e,
it
i
s
es
s
en
tial
to
p
er
f
o
r
m
to
k
e
n
izatio
n
,
s
to
p
w
o
r
d
r
e
m
o
v
a
l
a
n
d
s
te
m
m
i
n
g
w
it
h
th
e
h
elp
o
f
ap
p
r
o
p
r
iate
alg
o
r
ith
m
.
Op
ti
m
izatio
n
T
F
-
I
D
F
w
as
p
er
f
o
r
m
ed
u
s
i
n
g
J
av
a
lan
g
u
a
g
e,
in
o
r
d
er
to
ca
lcu
late
t
h
e
f
r
eq
u
e
n
c
y
o
f
a
p
ar
ticu
lar
w
o
r
d
in
a
d
o
cu
m
e
n
t.
T
F
-
I
DF
ca
lcu
la
tes
t
h
e
r
elat
iv
e
f
r
eq
u
e
n
c
y
o
f
ea
c
h
w
o
r
d
i
n
a
d
o
cu
m
e
n
t
an
d
I
D
F
ca
lcu
late
s
i
n
f
o
r
m
at
iv
e
n
es
s
o
f
ea
ch
w
o
r
d
o
v
er
t
h
e
e
n
tire
d
o
cu
m
e
n
t.
T
h
u
s
,
T
F
-
I
DF
v
al
u
e
o
f
ea
c
h
w
o
r
d
is
a
s
s
ig
n
ed
as
a
w
ei
g
h
t
in
t
h
i
s
i
m
p
le
m
en
ted
al
g
o
r
ith
m
i
n
w
h
ic
h
h
i
g
h
e
s
t
f
r
eq
u
e
n
c
y
w
o
r
d
is
as
s
i
g
n
ed
w
i
th
h
i
g
h
e
s
t
p
r
io
r
ity
.
Di
f
f
er
en
t
r
ep
o
s
ito
r
ie
s
ar
e
cr
ea
ted
to
s
to
r
e
th
e
w
o
r
d
s
h
av
in
g
d
i
f
f
er
e
n
t
p
r
io
r
ity
b
u
t
h
av
in
g
s
a
m
e
co
lo
u
r
as u
s
ed
to
class
i
f
y
th
e
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
4
,
No
.
1
,
Ma
r
ch
2
0
1
5
:
14
–
19
16
T
ab
le
1
.
P
s
u
ed
o
C
o
d
e
o
f
P
r
o
p
o
s
ed
A
l
g
o
r
ith
m
A
l
g
o
r
i
t
h
m
_
P
se
u
d
o
c
o
d
e
S
t
e
p
s
I
n
i
t
i
a
l
i
z
e
T
f
(
T
f
T
e
x
t
f
i
l
e
)
B
e
g
i
n
F
o
r
e
a
c
h
D
f
{
(D
f
= D
t
o
k
,
;
D
f
=D
s
t
e
m
;D
f
++)
}
C
a
l
c
u
l
a
t
e
D
f
(
TF
-
I
D
F
)
A
ssi
g
n
W
i
….
.
n
W
d
I
f
(
W
d(f
r
e
q)
=
=
h
i
g
h
e
st
)
{
W
d
=
=
H
p;
W
d
-
-
;
}
El
se
{
W
d
=
=
L
p;
W
d
-
-
;
}
N
e
u
r
a
l
N
e
t
w
o
r
k
i
n
i
t
i
a
l
i
z
e
W
e
i
g
h
t
s (w
o
r
d
,
v
a
l
u
e
)
F
o
r
(
i
=
1
t
o
n
)
{
I
f
(
W
d(F
r
e
q)
=
=
N
N
(W
i
)
)
{
A
ssi
g
n
c
o
r
r
e
c
t
p
r
i
o
r
i
t
y
;
}
El
se
{
B
a
c
k
P
r
o
p
a
g
a
t
i
o
n
Er
r
o
r
(
R
e
–
i
n
i
t
i
a
l
i
z
e
w
e
i
g
h
t
s (w
o
r
d
,
}
v
a
l
u
e
)
}
}
A
ssi
g
n
C
(R
e
d)
Wd
(H
i
g
h
e
s
t
)
A
ssi
g
n
(
G
r
e
e
n
)
W
d(L
ow
e
s
t
)
/
/
I
n
t
i
a
l
i
z
e
t
h
e
P
d
f
F
i
l
e
//
TF
-
I
D
F
c
a
l
c
u
l
a
t
i
o
n
/
/
A
ssi
g
n
W
e
i
g
h
t
s
t
o
e
v
e
r
y
w
o
r
d
/
/
h
i
g
h
e
st
f
r
e
q
u
e
n
c
y
w
o
r
d
h
a
s
h
i
g
h
e
st
p
r
i
o
r
i
t
y
/
/
B
a
c
k
p
r
o
p
a
g
a
t
i
o
n
t
o
g
e
n
e
r
a
t
e
t
h
e
i
n
t
e
r
r
u
p
t
/
/
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
h
i
g
h
e
st
a
n
d
l
o
w
e
st
p
r
i
o
r
i
t
y
w
o
r
d
s b
y
u
si
n
g
c
l
a
ssi
f
i
e
r
5.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
Fig
u
r
e
5
a:
A
f
ter
u
p
lo
ad
in
g
t
h
e
P
d
f
f
ile,
T
o
k
en
izatio
n
,
s
to
p
w
o
r
d
r
em
o
v
al
an
d
s
te
m
m
in
g
is
d
o
n
e
to
ca
lcu
late
ter
m
f
r
eq
u
en
c
y
o
f
ev
er
y
w
o
r
d
in
t
h
e
d
o
cu
m
e
n
t
in
o
r
d
er
to
ass
ig
n
t
h
e
w
ei
g
h
t
to
ea
ch
w
o
r
d
f
o
r
p
r
io
r
itizatio
n
m
ea
n
s
T
F
-
I
DF o
f
f
ile
is
ca
lc
u
lated
.
Fig
u
r
e
5
b
:
A
p
p
l
y
B
ac
k
P
r
o
p
ag
atio
n
al
g
o
r
ith
m
to
c
h
ec
k
w
h
eth
er
co
r
r
ec
t
w
ei
g
h
ts
ar
e
ass
i
g
n
ed
o
r
n
o
t.
I
n
ca
s
e
p
r
io
r
ity
i
s
d
if
f
er
e
n
t
f
r
o
m
t
h
e
a
ctu
al
p
r
io
r
it
y
o
f
t
h
e
w
o
r
d
,
n
eu
r
al
n
et
w
o
r
k
s
b
ac
k
p
r
o
p
ag
ates
t
h
e
er
r
o
r
to
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
.
Fig
u
r
e
5
c:
Af
ter
as
s
i
g
n
in
g
p
r
io
r
iti
es
to
d
if
f
er
e
n
t
w
o
r
d
s
,
r
ep
o
s
ito
r
ies
ar
e
cr
ea
ted
to
s
to
r
e
h
ig
h
er
an
d
lo
w
er
p
r
io
r
ity
tes
t c
ases
f
o
r
ea
s
y
p
r
ed
ictio
n
.
Fig
u
r
e
5
d
: A
f
ter
ass
i
g
n
i
n
g
t
h
e
p
r
io
r
ities
,
h
ig
h
li
g
h
t th
e
m
i
n
th
e
P
DF f
ile
u
p
lo
ad
ed
.
Fig
u
r
e
5
e:
T
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
h
as
h
i
g
h
er
A
P
FD
m
etr
ic
as c
o
m
p
ar
ed
to
ex
is
ti
n
g
tec
h
n
i
q
u
e.
Fig
u
r
e
5
f
:
T
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
h
as
v
er
y
le
s
s
e
x
ec
u
t
io
n
ti
m
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Desig
n
A
n
d
Dev
elo
p
men
t
o
f A
n
A
g
o
r
ith
m
fo
r
P
r
io
r
itiz
in
g
th
e
Tes
t Ca
s
e
s
Us
in
g
… (
A
mi
t V
erma
)
17
Fig
u
r
e
5
a.
T
F
-
I
DF o
f
P
DF Fil
e
Fig
u
r
e
5
b
.
B
ac
k
P
r
o
p
ag
atio
n
A
l
g
o
r
ith
m
Fig
u
r
e
5
c.
C
lass
if
ica
tio
n
o
f
Di
f
f
er
en
t P
r
io
r
ities
Fig
u
r
e
5
d
.
Hig
h
li
g
h
t t
h
e
P
r
io
r
i
ties
Fig
u
r
e
5
e.
A
P
FD M
etr
ic
Fig
u
r
e
5
f
.
E
x
ec
u
tio
n
T
i
m
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
4
,
No
.
1
,
Ma
r
ch
2
0
1
5
:
14
–
19
18
6.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
w
e
r
ep
r
esen
t
a
f
r
a
m
e
w
o
r
k
to
p
r
io
r
itize
th
e
te
s
t
ca
s
es
b
ased
o
n
T
F
-
I
DF,
A
r
ti
f
i
cial
n
e
u
r
al
n
et
w
o
r
k
s
b
ac
k
p
r
o
p
ag
atio
n
alg
o
r
ith
m
a
n
d
n
aï
v
e
b
a
y
es
clas
s
if
ier
al
g
o
r
ith
m
.
T
h
e
f
r
a
m
e
wo
r
k
w
it
h
e
m
b
ed
d
ed
m
et
h
o
d
s
g
a
v
e
g
o
o
d
r
esu
lts
,
c
o
n
f
ir
m
ed
o
u
r
co
n
ce
p
ts
an
d
i
n
itial
ex
p
ec
tat
io
n
s
.
E
v
al
u
atio
n
o
f
th
e
alg
o
r
it
h
m
i
s
d
o
n
e
o
n
v
ar
io
u
s
d
o
cu
m
e
n
t
s
.
T
h
e
f
r
a
m
e
w
o
r
k
w
as
v
er
y
s
ta
b
le
an
d
r
eliab
le.
P
er
f
o
r
m
ed
test
s
h
a
v
e
d
etec
t
ed
a
s
en
s
iti
v
it
y
o
f
t
h
e
i
m
p
le
m
en
te
d
alg
o
r
ith
m
.
T
h
e
an
al
y
s
is
o
f
t
h
e
d
o
cu
m
en
t
s
co
n
te
n
t
s
h
o
w
ed
th
at
t
h
e
a
m
o
u
n
t
o
f
u
n
u
s
ab
le
w
o
r
d
s
in
d
o
cu
m
e
n
ts
h
as
s
i
g
n
i
f
ican
t
i
m
p
ac
t
o
n
t
h
e
class
i
f
icatio
n
s
o
it
is
n
ec
ess
ar
y
to
i
m
p
r
o
v
e
th
e
p
r
ep
r
o
ce
s
s
in
g
o
f
d
o
cu
m
e
n
ts
t
o
ac
h
iev
e
t
h
e
b
etter
r
esu
lt
s
.
C
lass
i
f
icatio
n
is
v
er
y
i
m
p
o
r
tan
t
to
ea
s
il
y
d
etec
t
t
h
e
h
ig
h
e
s
t p
r
io
r
it
y
an
d
lo
w
est p
r
i
o
r
ity
w
o
r
d
in
a
d
o
cu
m
en
t.
T
h
e
i
m
p
le
m
e
n
ted
al
g
o
r
ith
m
i
n
cr
ea
s
es t
h
e
r
o
b
u
s
tn
e
s
s
,
ef
f
icien
c
y
a
n
d
r
ed
u
ce
s
th
e
co
m
p
lex
i
t
y
.
RE
F
E
R
E
NC
E
S
[1
]
Bin
g
Ch
e
n
g
,
DM
T
it
terin
g
to
n
.
N
e
u
ra
l
Ne
t
w
o
rk
s:
A
Re
v
ie
w
f
ro
m
S
tatisti
c
a
l
P
e
rsp
e
c
ti
v
e
.
S
tatisti
c
a
l
sc
ien
c
e
.
1
9
9
4
;
9
(
1
):
2
-
5
4
.
[2
]
Ke
n
-
ich
i
F
u
n
a
h
a
sh
i
.
M
u
lt
il
a
y
e
r
n
e
u
ra
l
n
e
tw
o
rk
s an
d
Ba
y
e
s d
e
c
isio
n
th
e
o
ry
.
El
se
v
ier
S
c
ien
c
e
.
1
9
9
7
:
209
-
2
1
3
.
[3
]
G
u
o
q
ian
g
P
e
ter
Zh
a
n
g
.
Ne
u
ra
l
Ne
t
w
o
r
k
s
f
o
r
Clas
si
f
ic
a
ti
o
n
:
A
S
u
rv
e
y
.
IEE
E
T
ra
n
s.On
M
a
n
,
S
y
ste
ms
,
a
n
d
Cy
b
e
rn
e
ti
c
s
.
2
0
0
0
;
30
(
4
).
[4
]
G
Ro
th
e
r
m
e
l,
R
Un
tch
,
C
Ch
u
,
M
J
Ha
rro
ld
.
P
r
io
rit
izin
g
T
e
st
Ca
s
e
s
f
o
r
Re
g
re
ss
io
n
T
e
stin
g
.
IEE
E
T
ra
n
s.
S
o
ft
w
a
re
En
g
.
2
0
0
1
;
27
(
10
):
9
2
9
-
9
4
8
.
[5
]
M
e
e
n
a
k
sh
i
V
a
n
m
a
li
,
M
a
rk
Las
t,
A
b
ra
h
a
m
Ka
n
d
e
l
.
Us
in
g
a
Ne
u
ra
l
Ne
tw
o
rk
in
th
e
S
o
f
t
w
a
re
Tes
ti
n
g
P
ro
c
e
ss
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
telli
g
e
n
t
S
y
ste
ms
.
2
0
0
2
;
17
:
45
-
6
2
.
[6
]
S
e
b
a
stian
El
b
a
u
m
,
A
le
x
e
y
G
M
a
li
sh
e
v
sk
y
,
G
Ro
th
e
rm
e
l
.
Tes
t
Ca
se
P
rio
ri
ti
z
a
ti
o
n
:
A
F
a
m
il
y
o
f
E
m
p
iri
c
a
l
S
tu
d
ies
.
IEE
E
T
ra
n
s.
S
o
f
twa
re
En
g
.
2
0
0
2
;
28
(
2
)
.
[7
]
Isa
b
e
ll
e
G
u
y
o
n
,
Ja
so
n
W
e
sto
n
,
S
tep
h
e
n
Ba
r
n
h
il
l.
G
e
n
e
S
e
lec
ti
o
n
f
o
r
c
a
n
c
e
r
c
las
si
f
ic
a
ti
o
n
u
si
n
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
.
M
a
c
h
in
e
L
e
a
rn
in
g
.
Kl
u
w
e
r
Ac
a
d
e
m
ic P
u
b
l
ish
e
rs.
M
a
n
u
f
a
c
tu
re
d
in
T
h
e
Ne
th
e
rlan
d
s.
2
0
0
2
;
4
6
:
3
8
9
–
4
2
2
.
[8
]
Ja
m
e
s
A
Jo
n
e
s,
M
a
ry
Je
a
n
Ha
r
ro
ld
.
T
e
st
-
S
u
it
e
Re
d
u
c
ti
o
n
a
n
d
P
ri
o
rit
iza
ti
o
n
f
o
r
M
o
d
if
ied
Co
n
d
it
io
n
/De
c
isio
n
Co
v
e
ra
g
e
.
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
so
ft
wa
re
e
n
g
in
e
e
rin
g
.
2
0
0
3
;
29
(
3
):
1
9
5
-
2
0
9
.
[9
]
L
i
Ba
o
li
,
Yu
S
h
iw
e
n
,
L
u
Qin
.
A
n
Im
p
ro
v
e
d
k
-
Ne
a
re
st Ne
ig
h
b
o
r
A
l
g
o
rit
h
m
f
o
r
Tex
t
Ca
te
g
o
riza
ti
o
n
.
Ch
in
a
2
0
0
3
.
[1
0
]
D
Rich
a
rd
Ku
h
n
,
S
e
n
i
o
r
M
e
m
b
e
r,
Do
lo
re
s
R
W
a
ll
a
c
e
.
S
o
f
t
wa
re
F
a
u
lt
In
tera
c
ti
o
n
s
a
n
d
Im
p
li
c
a
ti
o
n
s
f
o
r
S
o
f
t
w
a
re
T
e
stin
g
.
IEE
E
T
ra
n
s.
o
n
so
f
twa
re
e
n
g
i
n
e
e
rin
g
.
2
0
0
4
;
30
(
6
)
.
[1
1
]
Eri
c
k
Ca
n
tu
-
P
a
z
,
Ch
a
n
d
rik
a
Ka
m
a
th
.
A
n
E
m
p
iri
c
a
l
Co
m
p
a
ri
so
n
o
f
Co
m
b
in
a
ti
o
n
s
o
f
Ev
o
lu
ti
o
n
a
ry
Alg
o
rit
h
m
s
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
s
f
o
r
Clas
si
f
ica
ti
o
n
P
r
o
b
lem
s
.
IEE
E
T
ra
n
s.
On
S
y
st
e
ms
,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s
.
2
0
0
5
.
[1
2
]
Zh
e
n
g
L
i,
M
a
rk
Ha
r
m
a
n
,
Ro
b
e
r
t
M
.
Hie
ro
n
s
.
S
e
a
rc
h
A
lg
o
rit
h
m
s
f
o
r
Re
g
re
ss
io
n
T
e
st
C
a
se
P
rio
rit
iza
ti
o
n
.
I
EE
E
T
ra
n
s.
S
o
ft
wa
re
E
n
g
.
2
0
0
7
;
33
(
4
)
.
[1
3
]
Ra
n
d
a
ll
S
S
e
x
to
n
,
Ro
b
e
rt
E
Do
r
se
y
.
Re
li
a
b
le
Clas
si
f
ica
ti
o
n
Us
in
g
Ne
u
ra
l
Ne
t
w
o
rk
s:
A
Ge
n
e
ti
c
A
l
g
o
rit
h
m
a
n
d
Ba
c
k
p
ro
p
a
g
a
ti
o
n
C
o
m
p
a
riso
n
.
[1
4
]
Us
h
a
Ba
d
h
e
ra
,
G
N
P
u
ro
h
it
,
De
b
a
ru
p
a
Bisw
a
s
.
T
e
st
c
a
se
p
rio
rit
iza
ti
o
n
a
lg
o
rit
h
m
b
a
se
d
u
p
o
n
m
o
d
if
ied
c
o
d
e
c
o
v
e
ra
g
e
in
re
g
re
ss
io
n
tes
ti
n
g
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
f
twa
re
En
g
i
n
e
e
rin
g
&
Ap
p
li
c
a
ti
o
n
s
(
IJ
S
EA
)
.
2
0
1
2
;
3
(
6
)
:
29
-
37.
[1
5
]
S
tef
a
n
Walli
n
,
L
e
if
L
a
n
d
´
e
n
.
T
e
lec
o
m
Al
a
rm
Prio
riti
z
a
ti
o
n
u
sin
g
Ne
u
ra
l
Ne
two
rk
s
.
2
2
n
d
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
In
f
o
rm
a
ti
o
n
Ne
tw
o
r
k
in
g
a
n
d
A
p
p
li
c
a
ti
o
n
s
–
W
o
rk
sh
o
p
s.
2
0
0
8
:
1
4
6
8
-
1
4
7
3
.
[1
6
]
A
d
a
m
S
lo
w
ik
,
M
ich
a
l
Bialk
o
.
T
ra
in
in
g
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
Us
in
g
Di
ff
e
re
n
ti
a
l
Ev
o
lu
t
io
n
A
lg
o
rit
h
m
.
IEE
E
Kra
k
o
w
,
Po
la
n
d
.
2
0
0
8
:
60
-
65,
M
a
y
2
5
-
27
.
[1
7
]
S
h
i
Yu
,
S
tev
e
n
V
a
n
V
o
o
re
n
,
L
e
o
n
-
Ch
a
rl
e
s T
ra
n
c
h
e
v
e
n
t,
Ba
rt
De
M
o
o
r
,
Yv
e
s M
o
re
a
u
.
Co
m
p
a
riso
n
o
f
v
o
c
a
b
u
larie
s,
re
p
re
se
n
tatio
n
s an
d
ra
n
k
i
n
g
a
lg
o
rit
h
m
s
f
o
r
g
e
n
e
p
rio
rit
iza
ti
o
n
b
y
tex
t
m
in
in
g
.
2
0
0
8
;
24
,
ECCB
:
1
1
9
-
125
.
[1
8
]
Us
m
a
n
F
a
ro
o
q
,
C
P
L
a
m
.
Evo
lvin
g
th
e
Q
u
a
l
it
y
o
f
M
o
d
e
l
B
a
se
d
T
e
st
S
u
it
e
.
IEE
E
In
ter
n
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
o
n
S
o
f
tw
a
r
e
Tes
ti
n
g
v
e
ri
f
ica
ti
o
n
a
n
d
v
a
li
d
a
ti
o
n
w
o
rk
sh
o
p
s
.
2
0
0
9
.
[1
9
]
S
ira
V
e
g
a
s,
Na
talia
Ju
risto
,
V
ict
o
r
R
Ba
sili
.
M
a
tu
rin
g
S
o
f
tw
a
re
En
g
in
e
e
rin
g
Kn
o
w
led
g
e
th
ro
u
g
h
Clas
sif
i
c
a
ti
o
n
s:
A
Ca
se
S
tu
d
y
o
n
Un
i
t
T
e
stin
g
T
e
c
h
n
iq
u
e
s
.
IEE
E
tra
n
s
a
c
ti
o
n
s o
n
so
ft
wa
re
e
n
g
i
n
e
e
rin
g
.
2
0
0
9
;
35
(
4
)
:
5
5
1
–
5
6
5
.
[2
0
]
N
S
u
g
u
n
a
1
,
K
T
h
a
n
u
sh
k
o
d
i
.
A
n
Im
p
ro
v
e
d
k
-
N
e
a
re
st
Ne
ig
h
b
o
r
Clas
si
f
ica
ti
o
n
Us
in
g
G
e
n
e
ti
c
Alg
o
rit
h
m
.
IJ
CS
I
In
ter
n
a
t
io
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
.
2
0
1
0
;
7
(
4
)
.
[2
1
]
A
ji
th
a
,
T
V
S
u
re
s
h
Ku
m
a
r,
D
Ev
a
n
g
e
li
n
G
e
e
th
a
,
K
Ra
jn
ik
a
n
th
.
Per
fo
rm
a
n
c
e
Pre
d
icti
o
n
i
n
Ea
rly
S
t
a
g
e
s
o
f
S
o
ft
wa
re
S
y
ste
ms
:
Arti
fi
c
ia
l
Ne
u
r
a
l
Ne
two
r
k
M
o
d
e
l.
ICCCCT
.
2
0
1
0
:
7
4
3
-
7
4
7
.
[2
2
]
Im
p
ro
v
in
g
T
e
stin
g
Eff
i
c
ien
c
y
:
Ag
il
e
T
e
st
Ca
se
P
rio
rit
iza
ti
o
n
.
S
o
f
tw
a
r
e
Be
n
c
h
m
a
r
k
in
g
Org
a
n
iza
ti
o
n
,
2
0
0
9
-
2
0
1
0
:
1
-
7.
[2
3
]
Am
it
G
a
n
a
tra,
Y
P
Ko
sta
G
a
u
ra
n
g
P
a
n
c
h
a
l,
Ch
i
n
tan
G
a
jj
a
r.
In
it
ial
Clas
si
f
ica
ti
o
n
T
h
ro
u
g
h
Ba
c
k
P
ro
p
a
g
a
ti
o
n
I
n
a
Ne
u
ra
l
Ne
t
w
o
rk
F
o
ll
o
w
in
g
Op
ti
m
iz
a
ti
o
n
T
h
ro
u
g
h
G
A
to
Ev
a
lu
a
te
th
e
F
it
n
e
ss
o
f
a
n
A
l
g
o
rit
h
m
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
&
I
n
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
(
IJ
CS
IT
)
.
2
0
1
1
;
3
(
1
):
98
-
1
1
6
.
[2
4
]
A
sh
w
in
G
Ra
i
y
a
n
i,
S
h
e
e
tal
S
P
a
n
d
y
a
.
P
r
o
rit
iza
ti
o
n
tec
h
n
iq
u
e
f
o
r
m
in
i
m
izin
g
n
u
m
b
e
r
o
f
tes
t
c
a
se
s.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
ft
w
a
re
En
g
in
e
e
rin
g
Res
e
a
rc
h
&
Pra
c
ti
c
e
s
.
2
0
1
1
;
1
(
1
)
:
3
-
9.
[2
5
]
A
r
v
in
d
e
r
Ka
u
r,
S
h
u
b
h
r
a
G
o
y
a
l
.
A
g
e
n
e
ti
c
a
lg
o
rit
h
m
f
o
r
re
g
re
ss
i
o
n
tes
t
c
a
se
p
ri
o
rit
iza
ti
o
n
u
sin
g
c
o
d
e
c
o
v
e
ra
g
e
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
n
C
o
mp
u
t
e
r S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
.
2
0
1
1
;
3
(
5
)
:
1
8
3
9
-
1
8
4
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Desig
n
A
n
d
Dev
elo
p
men
t
o
f A
n
A
g
o
r
ith
m
fo
r
P
r
io
r
itiz
in
g
th
e
Tes
t Ca
s
e
s
Us
in
g
… (
A
mi
t V
erma
)
19
[2
6
]
S
o
n
a
li
K
h
a
n
d
a
i,
A
ru
p
A
b
h
i
n
n
a
A
c
h
a
r
y
a
,
Du
rg
a
P
ra
sa
d
M
o
h
a
p
a
tra.
P
ri
o
rit
izi
n
g
T
e
st
Ca
se
s
Us
in
g
B
u
sin
e
ss
Crit
ica
li
ty
T
e
st V
a
lu
e
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Co
m
p
u
t
e
r S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s
.
2
0
1
1
;
3
(
5
):
1
0
3
-
1
1
0
.
[2
7
]
Zh
e
n
-
G
u
o
Ch
e
,
T
z
u
-
A
n
Ch
ian
g
,
Zh
e
n
-
Hu
a
Ch
e
3
.
F
e
e
d
-
f
o
rw
a
rd
n
e
u
ra
l
n
e
tw
o
rk
s
train
in
g
:
a
c
o
m
p
a
riso
n
b
e
tw
e
e
n
g
e
n
e
ti
c
a
lg
o
rit
h
m
a
n
d
Ba
c
k
-
p
ro
p
a
g
a
ti
o
n
lea
rn
i
n
g
a
lg
o
rit
h
m
.
In
t
e
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
ti
v
e
Co
mp
u
t
in
g
,
In
fo
rm
a
t
io
n
a
n
d
Co
n
tro
l
.
2
0
1
1
;
7
(
10
):
5
8
3
9
-
5
8
5
0
.
[2
8
]
A
r
v
in
d
e
r
Ka
u
r
,
S
h
iv
a
n
g
i
G
o
y
a
l.
A
Be
e
Co
lo
n
y
Op
ti
m
iza
ti
o
n
A
lg
o
rit
h
m
f
o
r
F
a
u
lt
Co
v
e
ra
g
e
Ba
se
d
Re
g
re
ss
io
n
T
e
st
S
u
it
e
P
r
io
ri
t
iza
ti
o
n
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
.
2
0
1
1
;
29
.
Evaluation Warning : The document was created with Spire.PDF for Python.