I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
.
14
, N
o.
3
,
J
une
20
25
, pp.
1820
~
1828
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
14
.i
3
.pp
1820
-
1828
1820
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
N
ove
l
ar
t
i
f
i
c
i
al
i
n
t
e
l
l
i
ge
n
c
e
-
b
ase
d
e
n
se
m
b
l
e
l
e
ar
n
i
n
g f
or
op
t
i
m
i
z
e
d
sof
t
w
ar
e
q
u
al
i
t
y
S
an
ge
e
t
h
a G
ovi
n
d
a
1
, A
gn
e
s
N
al
in
i
V
in
c
e
n
t
2
, M
e
r
w
a R
am
e
s
h
B
ab
u
3
1
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
, C
hr
i
s
t
U
ni
ve
r
s
i
t
y, B
a
nga
l
or
e
, I
ndi
a
2
F
a
c
ul
t
y of
I
nf
or
m
a
t
i
on T
e
c
hnol
ogy, A
M
I
T
Y
I
ns
t
i
t
ut
e
of
H
i
ghe
r
E
duc
a
t
i
on, Q
u
a
t
r
e
B
or
ne
s
, M
a
ur
i
t
i
us
3
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
,
B
ha
r
a
t
hi
a
r
U
ni
ve
r
s
i
t
y, C
oi
m
ba
t
or
e
, I
ndi
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
M
a
r
19
,
2024
R
e
vi
s
e
d
F
e
b
26
,
2025
A
c
c
e
pt
e
d
M
a
r
15
,
2025
Artificial
intelligence
(AI)
contributes
towards
improving
so
ftware
engineerin
g
quality
;
however,
existin
g
AI
models
are
witness
ed
to
deploy
learning
-
based
approaches
without
addressing
various
compl
exities
associated
with
datasets.
A
literature
review
showcases
an
unequi
lbrium
between
addressing
the
accuracy
and
computational
burden.
Therefore,
the
proposed
manuscript
presents
a
novel
AI
-
based
ensemble
learning
model
that
is
capable
of
performing
an
effective
prediction
of
software
qualit
y.
The
presented
scheme
adopts
correlation
-
based
and
multicollinearity
-
based
attribut
es
to
select
essential
featur
e
selectio
n.
At
the
same
time,
the
s
cheme
also
introduces
a
hybrid
learning
approach
integrated
with
a
bio
-
i
nspired
algorit
hm
f
or
constructing
the
ensemble
learning
scheme.
The
qua
ntified
outcome
of
the
proposed
study
showcases
65%
minimized
d
efect
d
ensity,
94%
minimized
mean
time
to
failure,
62%
minimized
processing
time
of
the
algorit
hm, and
43% enhanced
predicti
ve accuracy
.
K
e
y
w
o
r
d
s
:
A
c
c
ur
a
c
y
A
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
D
e
f
e
c
t
de
ns
it
y
S
of
twa
r
e
e
ngi
ne
e
r
in
g
S
of
twa
r
e
qua
li
ty
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
S
a
nge
e
th
a
G
ovi
nda
D
e
pa
r
tm
e
nt
of
C
om
put
e
r
S
c
ie
nc
e
, C
hr
is
t
U
ni
ve
r
s
it
y
D
ha
r
m
a
r
a
m
C
ol
le
ge
, H
os
ur
M
a
in
R
oa
d, B
ha
v
a
ni
N
a
ga
r
, P
os
t,
B
e
nga
lu
r
u, K
a
r
na
ta
ka
-
560029
, I
ndi
a
E
m
a
il
:
s
a
nge
e
th
a
.g@
c
hr
is
tu
ni
ve
r
s
it
y.i
n
1.
I
N
T
R
O
D
U
C
T
I
O
N
S
of
twa
r
e
qua
li
ty
is
one
of
th
e
e
s
s
e
nt
ia
l
a
ge
nda
s
th
a
t
a
s
s
is
t
i
n
e
ns
ur
in
g
th
e
s
uc
c
e
s
s
of
a
n
ove
r
a
ll
bus
in
e
s
s
,
be
tt
e
r
m
a
in
ta
in
a
bi
li
ty
,
a
nd
pr
a
c
ti
c
a
l
s
ys
te
m
r
e
li
a
bi
li
ty
.
I
t
pos
it
iv
e
ly
in
f
lu
e
nc
e
s
us
e
r
s
a
ti
s
f
a
c
ti
on
in
s
of
twa
r
e
e
ngi
ne
e
r
in
g
[
1]
.
W
h
e
n
s
of
twa
r
e
is
de
s
ig
n
e
d
in
a
dhe
r
e
nc
e
to
hi
ghe
r
qua
li
ty
s
t
a
nda
r
ds
,
it
c
a
n
of
f
e
r
a
pos
it
iv
e
us
e
r
e
xpe
r
ie
nc
e
th
a
t
r
e
s
ul
ts
in
hi
ghe
r
r
e
te
nt
io
n
of
us
e
r
s
a
nd
hi
ghe
r
s
a
ti
s
f
a
c
ti
on
[
2]
.
T
he
be
tt
e
r
de
s
ig
n
qua
li
ty
of
s
of
twa
r
e
a
lw
a
ys
e
ns
ur
e
s
hi
ghe
r
r
e
li
a
bi
li
ty
by
r
e
duc
in
g
une
xpe
c
te
d
f
a
il
ur
e
s
,
r
e
duc
in
g
dow
nt
im
e
a
nd
e
ns
ur
in
g
be
tt
e
r
c
ont
in
ui
ty
in
bus
in
e
s
s
pr
oc
e
s
s
e
s
[
3]
.
A
w
e
ll
-
s
t
r
uc
tu
r
e
d
s
of
twa
r
e
c
ode
c
a
n
of
f
e
r
opt
im
a
l
c
os
t
r
e
duc
ti
on
w
it
h
m
or
e
s
tr
a
ig
ht
f
or
w
a
r
d
m
a
in
ta
in
a
bi
li
ty
[
4
]
.
A
pa
r
t
f
r
om
th
is
,
a
w
e
ll
-
de
s
ig
ne
d
s
of
twa
r
e
pr
oduc
t
is
a
ls
o
le
s
s
s
u
s
c
e
pt
ib
le
to
s
e
c
ur
it
y
vul
ne
r
a
bi
li
ti
e
s
.
T
he
r
e
by
it
c
a
n
pr
ot
e
c
t
s
e
ns
it
iv
e
d
a
ta
a
nd
r
e
s
is
t
le
th
a
l
th
r
e
a
ts
[
5]
.
H
ow
e
ve
r
,
a
c
c
om
pl
is
hi
ng
a
be
tt
e
r
s
of
twa
r
e
qua
li
ty
s
ta
nda
r
d
is
of
te
n
e
nc
ount
e
r
e
d
w
it
h
va
r
io
us
c
ha
ll
e
nge
s
.
W
it
h i
nc
r
e
a
s
in
g c
om
pe
ti
ti
on t
ow
a
r
ds
yi
e
ld
in
g t
he
opt
im
a
l
f
o
r
m
of
pr
oduc
t
de
s
ig
n, t
he
s
of
twa
r
e
de
s
ig
n s
ys
te
m
is
tr
a
ns
f
or
m
in
g
in
to
a
m
or
e
c
om
pl
e
x
pr
obl
e
m
w
he
r
e
it
is
qui
t
e
c
ha
ll
e
ngi
ng
to
e
ns
ur
e
opt
im
a
l
qua
li
ty
a
c
r
os
s
a
ll
it
s
in
te
r
a
c
ti
on
s
a
nd
c
om
pone
nt
s
[
6]
.
C
ha
ngi
ng
r
e
qui
r
e
m
e
nt
s
is
a
not
he
r
c
h
a
ll
e
nge
th
a
t
le
a
d
s
to
a
m
or
e
s
ig
ni
f
ic
a
nt
pr
obl
e
m
if
not
id
e
nt
if
ie
d
on
pr
ope
r
p
r
oduc
t
de
ve
lo
pm
e
nt
ti
m
e
[
7]
.
A
li
m
it
e
d
s
e
t
of
ti
m
e
f
o
r
de
ve
lo
pm
e
nt
is
a
not
he
r
is
s
u
e
th
a
t
le
a
ds
to
ove
r
lo
oke
d
s
of
twa
r
e
de
f
e
c
ts
th
a
t
pot
e
nt
ia
ll
y
a
f
f
e
c
t
de
s
ig
n
qua
li
ty
[
8]
.
A
not
he
r
s
ig
ni
f
ic
a
nt
c
ha
ll
e
nge
is
a
s
s
oc
ia
t
e
d
w
it
h
r
e
s
our
c
e
li
m
it
a
ti
ons
th
a
t
in
vol
ve
s
ki
ll
e
d
pe
r
s
onn
e
l,
budge
t,
a
nd
time
[
9]
.
I
t
w
a
s
a
ls
o
not
e
d
th
a
t
w
he
n
s
of
twa
r
e
de
m
a
nds
in
te
gr
a
ti
on
w
it
h
a
di
f
f
e
r
e
nt
pl
a
tf
or
m
or
s
ys
te
m
,
c
om
pa
ti
bi
li
ty
is
s
ue
s
s
ur
f
a
c
e
th
a
t
pot
e
nt
ia
ll
y
a
f
f
e
c
t
r
e
li
a
bi
li
ty
a
nd
pe
r
f
or
m
a
nc
e
s
im
ul
ta
ne
ous
ly
[
10]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
N
ov
e
l
ar
ti
fi
c
ia
l
in
te
ll
ig
e
nc
e
-
bas
e
d
e
ns
e
m
bl
e
l
e
ar
ni
ng f
or
opt
imi
z
e
d s
of
tw
a
r
e
quali
ty
…
(
Sange
e
th
a G
o
v
in
da
)
1821
F
in
a
ll
y, e
xt
e
ns
iv
e
de
m
a
nd f
or
va
li
da
ti
on a
nd t
e
s
ti
ng t
ool
s
a
nd
m
e
th
odol
ogi
e
s
i
s
s
om
e
ti
m
e
s
r
e
s
our
c
e
-
in
te
ns
iv
e
a
nd t
im
e
-
c
ons
um
in
g
[
11]
.
O
ne
e
f
f
e
c
ti
ve
w
a
y
to
a
ddr
e
s
s
a
ll
th
e
c
ha
ll
e
nge
s
m
e
nt
io
ne
d
a
bo
ve
is
to
a
dopt
a
pr
e
e
m
pt
iv
e
a
ppr
oa
c
h
w
he
r
e
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
(
A
I
)
s
ig
ni
f
ic
a
nt
ly
e
nha
nc
e
s
s
of
twa
r
e
qua
li
ty
.
W
it
h
a
ut
om
a
te
d
te
s
ti
ng,
ge
ne
r
a
ti
ng
te
s
t
c
a
s
e
s
, e
x
e
c
ut
in
g t
he
m
, a
nd pe
r
f
or
m
in
g de
e
pe
r
a
na
ly
s
is
i
s
p
os
s
ib
le
[
12]
.
T
he
t
e
s
t
out
c
om
e
s
c
a
n be
us
e
d f
or
tr
a
in
in
g
us
in
g
a
m
a
c
hi
n
e
le
a
r
ni
ng
a
lg
or
it
hm
,
th
e
r
e
by
a
s
s
i
s
ti
ng
in
pa
tt
e
r
n
id
e
nt
if
ic
a
ti
on
a
nd
pr
e
di
c
ti
on
of
pot
e
nt
ia
l
f
a
il
ur
e
s
a
nd
e
nha
nc
in
g
te
s
ti
ng
c
ove
r
a
ge
[
13]
.
A
not
h
e
r
c
ont
r
ib
ut
io
n
of
A
I
is
to
a
na
ly
z
e
th
e
c
ode
qua
li
ty
th
a
t
c
a
n
id
e
nt
if
y
pot
e
nt
ia
l
e
r
r
or
s
,
f
ol
lo
w
e
d
by
r
e
c
o
m
m
e
ndi
ng
e
nha
nc
e
m
e
nt
s
th
a
t
c
a
n
a
s
s
is
t
th
e
de
ve
lo
pe
r
s
in
de
ve
lo
pi
ng
c
le
a
ne
r
a
nd
m
a
in
ta
in
a
bl
e
c
ode
[
14]
.
A
I
a
lg
or
it
hm
s
c
a
n
a
na
ly
z
e
c
ode
c
ha
nge
s
,
u
s
e
r
f
e
e
dba
c
k, a
nd s
ys
te
m
be
ha
vi
our
t
o i
de
nt
if
y a
nd p
r
io
r
it
iz
e
bugs
.
B
y a
ut
om
a
ti
c
a
ll
y t
r
ia
gi
ng a
nd a
s
s
ig
ni
ng bugs
,
A
I
s
tr
e
a
m
li
ne
s
th
e
bug
r
e
s
ol
ut
io
n
pr
oc
e
s
s
,
r
e
duc
in
g
th
e
ti
m
e
t
o
de
te
c
t
a
nd
f
ix
de
f
e
c
ts
.
A
I
-
dr
iv
e
n
pr
e
di
c
ti
ve
a
na
ly
ti
c
s
c
a
n
a
nt
ic
ip
a
te
s
of
twa
r
e
f
a
il
ur
e
s
by
a
na
ly
z
in
g
hi
s
to
r
ic
a
l
da
ta
,
s
ys
te
m
lo
gs
,
a
nd
pe
r
f
or
m
a
nc
e
m
e
tr
ic
s
.
T
hi
s
pr
oa
c
ti
ve
a
ppr
oa
c
h
e
na
bl
e
s
or
ga
ni
z
a
ti
ons
to
a
ddr
e
s
s
is
s
ue
s
be
f
or
e
th
e
y
im
pa
c
t
us
e
r
s
,
im
pr
ovi
ng
s
ys
te
m
r
e
li
a
bi
li
ty
a
nd
upt
im
e
.
A
I
c
a
n
a
ut
om
a
te
pa
r
ts
of
th
e
s
of
twa
r
e
de
ve
lo
pm
e
nt
pr
oc
e
s
s
by
ge
ne
r
a
ti
ng
c
ode
s
ni
ppe
ts
,
te
m
pl
a
te
s
,
or
e
ve
n
e
nt
ir
e
m
odul
e
s
ba
s
e
d
on
hi
gh
-
le
ve
l
s
pe
c
if
ic
a
ti
ons
or
de
s
ig
n
pa
tt
e
r
ns
.
T
hi
s
a
c
c
e
le
r
a
te
s
de
ve
lo
pm
e
nt
a
nd r
e
duc
e
s
t
he
l
ik
e
li
hood of
e
r
r
or
s
i
nt
r
oduc
e
d dur
in
g m
a
nua
l
c
odi
ng. AI
a
lg
or
it
h
m
s
c
a
n
opt
im
iz
e
s
of
twa
r
e
pe
r
f
or
m
a
nc
e
by
a
na
ly
z
in
g
us
a
ge
pa
tt
e
r
ns
,
r
e
s
our
c
e
c
ons
um
pt
io
n,
a
nd
s
ys
te
m
c
onf
ig
ur
a
ti
ons
.
B
y
dyna
m
ic
a
ll
y
a
dj
us
ti
ng
pa
r
a
m
e
te
r
s
a
nd
c
onf
ig
ur
a
ti
ons
,
A
I
s
ys
te
m
s
c
a
n
m
a
xi
m
iz
e
e
f
f
ic
ie
nc
y,
s
c
a
la
bi
li
ty
,
a
nd
r
e
s
pon
s
iv
e
ne
s
s
.
H
ow
e
v
e
r
,
th
e
r
e
a
r
e
c
ha
ll
e
nge
s
in
e
f
f
e
c
ti
ve
A
I
im
pl
e
m
e
nt
a
ti
on
to
w
a
r
ds
s
of
twa
r
e
qu
a
li
ty
im
pr
ove
m
e
nt
[
15]
,
[
16]
.
i)
A
I
m
ode
ls
tr
a
in
e
d
on
bi
a
s
e
d
or
in
c
om
pl
e
te
d
a
ta
s
e
t
s
m
a
y
pr
oduc
e
bi
a
s
e
d
pr
e
di
c
ti
ons
,
l
e
a
di
ng
to
unf
a
ir
out
c
om
e
s
.
E
ns
u
r
in
g
f
a
ir
ne
s
s
a
nd
m
it
ig
a
ti
ng
bi
a
s
in
s
of
twa
r
e
qua
li
ty
pr
e
di
c
ti
on
m
ode
ls
r
e
qui
r
e
s
c
a
r
e
f
ul
da
ta
c
ol
le
c
ti
on,
pr
e
pr
oc
e
s
s
in
g,
a
nd
m
ode
l
tr
a
in
in
g
te
c
hni
que
s
,
ii
)
e
xt
r
a
c
ti
ng
r
e
le
va
nt
f
e
a
tu
r
e
s
f
r
om
s
of
twa
r
e
a
r
te
f
a
c
ts
f
or
i
nput
i
nt
o A
I
m
ode
ls
r
e
qui
r
e
s
doma
in
e
xpe
r
ti
s
e
a
nd
c
a
r
e
f
ul
c
ons
id
e
r
a
ti
on
of
f
e
a
tu
r
e
s
e
le
c
ti
on
te
c
hni
que
s
.
I
na
de
qua
te
f
e
a
tu
r
e
r
e
pr
e
s
e
nt
a
ti
on
c
a
n
l
e
a
d
to
s
ubopti
m
a
l
pe
r
f
or
m
a
nc
e
a
nd
pr
e
di
c
ti
v
e
a
c
c
ur
a
c
y
,
a
nd
ii
i)
A
I
m
ode
ls
tr
a
in
e
d
on
s
pe
c
if
ic
d
a
ta
s
e
t
s
or
c
ont
e
xt
s
m
a
y
s
tr
uggl
e
to
ge
n
e
r
a
li
z
e
to
n
e
w
or
uns
e
e
n
s
c
e
na
r
io
s
.
E
ns
ur
in
g
th
e
r
obus
tn
e
s
s
a
nd
g
e
ne
r
a
li
z
a
bi
li
ty
of
s
of
twa
r
e
qua
li
ty
pr
e
di
c
ti
on mode
ls
a
c
r
os
s
di
f
f
e
r
e
nt
pr
oj
e
c
ts
, doma
in
s
, a
nd e
nvi
r
onm
e
nt
s
r
e
m
a
in
s
a
s
ig
ni
f
ic
a
nt
c
ha
ll
e
nge
.
T
he
r
e
la
te
d
w
or
k
in
th
i
s
pe
r
s
pe
c
ti
ve
of
A
I
-
ba
s
e
d
m
e
th
od
s
h
a
s
be
e
n
r
e
vi
e
w
e
d
to
in
c
lu
de
va
r
ie
d
a
ppr
oa
c
he
s
a
nd
te
c
hni
que
s
a
ddr
e
s
s
in
g
e
nh
a
nc
in
g
s
of
twa
r
e
qu
a
l
it
y.
T
he
w
or
k
c
ondu
c
te
d
by
C
h
e
ng
e
t
al
.
[
17]
us
e
d
m
a
c
hi
ne
le
a
r
ni
ng
to
in
ve
s
ti
ga
te
th
e
s
uppor
ta
bi
li
ty
of
to
ol
s
ta
r
ge
ti
ng
in
c
r
e
a
s
in
g
r
e
li
a
bi
li
ty
in
va
li
da
ti
on
te
c
hni
que
s
.
S
a
kl
a
m
a
e
va
a
nd
P
a
vl
ič
[
18]
ha
ve
a
ls
o
in
ve
s
ti
ga
te
d
A
I
-
ba
s
e
d
a
ppr
oa
c
he
s
,
f
oc
us
in
g
on
s
of
twa
r
e
de
ve
lo
pm
e
nt
in
a
gi
le
m
e
th
odol
ogi
e
s
.
T
he
s
tu
dy
s
how
c
a
s
e
s
th
e
be
tt
e
r
s
c
ope
of
A
I
-
ba
s
e
d
m
e
th
ods
,
pr
ovi
di
ng
it
s
in
he
r
e
nt
is
s
ue
s
c
a
n
b
e
a
ddr
e
s
s
e
d.
K
okol
[
19]
ha
ve
pr
e
s
e
nt
e
d
a
w
or
k
w
he
r
e
th
e
s
ig
ni
f
ic
a
nc
e
of
r
e
s
e
a
r
c
h
on
s
of
twa
r
e
qua
li
ty
is
in
c
r
e
a
s
in
g
w
it
h
m
or
e
a
dva
nc
e
m
e
nt
of
da
ta
m
in
in
g
a
nd
f
a
ul
t
pr
e
di
c
ti
on
us
in
g
m
a
c
hi
ne
le
a
r
ni
ng.
A
I
m
e
th
odol
ogy
ha
s
a
ls
o
b
e
e
n
in
ve
s
ti
ga
te
d
c
on
c
e
r
ni
ng
pha
r
m
a
c
e
ut
ic
a
l
r
e
s
e
a
r
c
h
d
e
s
ig
n,
a
s
r
e
por
te
d
in
th
e
w
or
k
of
G
onz
á
le
z
e
t
al
.
[
20]
.
T
h
e
s
tu
dy
by
S
ie
be
r
t
e
t
al
.
[
21]
di
s
c
u
s
s
e
d
a
f
r
a
m
e
w
or
k
f
or
s
of
twa
r
e
qua
li
ty
m
ode
ls
us
in
g
m
a
c
hi
ne
le
a
r
ni
ng.
T
he
w
or
k
pr
e
s
e
nt
e
d
by
S
to
c
c
o
e
t
al
.
[
22]
di
s
c
us
s
e
d
th
e
im
pa
c
t
of
m
a
c
hi
ne
le
a
r
ni
ng
a
nd
de
e
p
le
a
r
ni
ng
th
a
t
c
a
n
f
a
c
il
it
a
te
a
ut
o
m
a
te
d
te
s
ti
ng
pr
ogr
a
m
s
to
a
ddr
e
s
s
s
of
twa
r
e
s
e
c
ur
it
y
th
r
e
a
ts
.
C
ho
e
t
al
.
[
23]
ha
ve
de
ve
lo
p
e
d
a
uni
que
m
a
tu
r
it
y
f
r
a
m
e
w
or
k
us
in
g
A
I
to
in
c
r
e
a
s
e
th
e
de
gr
e
e
of
r
e
li
a
bi
li
ty
of
s
of
twa
r
e
pr
oc
e
s
s
e
s
w
he
r
e
s
ta
ti
s
ti
c
a
l
a
na
ly
s
is
is
c
a
r
r
ie
d
out
c
ons
id
e
r
in
g
m
ul
ti
pl
e
r
e
a
l
-
ti
m
e
s
of
twa
r
e
pr
oj
e
c
ts
.
T
h
e
di
s
c
u
s
s
io
n
pr
e
s
e
nt
e
d
by
B
oukhli
f
e
t
al
.
[
24]
ha
s
di
s
c
lo
s
e
d
th
a
t
na
tu
r
a
l
la
ngua
ge
pr
oc
e
s
s
in
g
a
nd
ne
ur
a
l
ne
twor
ks
a
r
e
f
r
e
que
nt
ly
a
dopt
e
d
a
ppr
oa
c
he
s
f
or
pr
e
di
c
ti
ve
a
s
s
e
s
s
m
e
nt
in
s
of
twa
r
e
te
s
ti
ng.
O
ve
r
a
ll
,
th
e
a
ut
hor
s
c
onc
lu
d
e
d
th
e
be
n
e
f
ic
ia
l
s
c
op
e
of
us
in
g
A
I
in
s
of
twa
r
e
te
s
ti
ng.
T
he
di
s
c
us
s
io
n
r
e
por
te
d by B
a
r
e
nka
m
p
e
t
al
.
[
25
]
ha
s
r
e
por
te
d a
s
im
il
a
r
a
s
pe
c
t
of
t
he
e
nha
nc
e
d s
c
ope
of
A
I
t
ow
a
r
ds
m
ul
t
ip
le
ope
r
a
ti
ons
in
s
of
twa
r
e
de
ve
lo
pm
e
nt
,
f
r
om
di
s
c
ove
r
in
g
th
e
pa
tt
e
r
n
to
in
c
r
e
a
s
in
g
th
e
c
om
put
a
ti
ona
l
s
pe
e
d.
T
he
pr
im
e
l
im
it
a
ti
on of
r
e
vi
e
w
i
s
a
dopt
io
n of
s
ophi
s
ti
c
a
te
d A
I
-
a
ppr
oa
c
he
s
f
oc
u
s
in
g
m
a
in
ly
on l
oc
a
l
pe
r
s
pe
c
ti
ve
of
s
of
twa
r
e
is
s
ue
s
w
it
hout
m
uc
h
c
ons
id
e
r
a
ti
on
of
gl
oba
l
is
s
u
e
s
.
A
not
he
r
s
ig
ni
f
ic
a
nt
is
s
ue
is
r
e
la
te
d
to
lo
w
c
om
put
a
ti
ona
l
e
f
f
ic
ie
nc
y be
in
g r
e
c
or
de
d.
T
he
pr
opos
e
d s
ys
t
e
m
, t
he
r
e
f
or
e
, c
ont
r
ib
ut
e
s
t
o a
nove
l
f
or
m
o
f
s
im
pl
if
ie
d pr
e
di
c
ti
ve
A
I
-
ba
s
e
d m
ode
l
to
w
a
r
ds
opt
im
iz
a
ti
on
of
th
e
de
gr
e
e
of
s
of
twa
r
e
qua
li
ty
.
T
he
n
ove
l
va
lu
e
a
dde
d
to
th
e
pr
opos
e
d
s
tu
dy
is
a
s
f
ol
lo
w
s
:
i)
in
tr
oduc
e
s
a
s
im
pl
if
ie
d
s
c
he
m
e
to
id
e
nt
i
f
y
th
e
is
s
ue
s
f
ol
lo
w
e
d
by
im
pr
ov
in
g
th
e
la
r
ge
da
ta
s
e
t
a
s
s
oc
ia
t
e
d w
it
h s
of
twa
r
e
qua
li
ty
a
s
s
e
s
s
m
e
nt
, i
i)
a
nove
l
a
nd s
im
pl
if
ie
d e
m
pi
r
ic
a
l
s
c
he
m
e
i
s
pr
e
s
e
nt
e
d t
ow
a
r
ds
le
ve
r
a
gi
ng
th
e
pr
e
li
m
in
a
r
y
s
ui
ta
bi
li
ty
a
nd
us
a
ge
of
c
om
pl
e
x
da
ta
s
e
t
to
w
a
r
ds
ne
xt
-
le
ve
l
of
a
na
ly
ti
c
a
l
ope
r
a
ti
on,
ii
i)
a
s
im
pl
e
c
or
r
e
la
te
d
-
ba
s
e
d
s
e
le
c
ti
on
m
e
th
od
of
a
n
e
s
s
e
nt
ia
l
f
e
a
tu
r
e
ha
s
be
e
n
pr
e
s
e
nt
e
d
to
w
a
r
ds
s
im
pl
if
yi
ng
th
e
c
om
pl
e
x
r
e
la
ti
ons
hi
p
a
m
ong
th
e
va
r
ia
bl
e
s
in
th
e
da
ta
s
e
t,
a
nd
iv
)
a
nove
l
e
ns
e
m
bl
e
d
ba
s
e
d
A
I
a
ppr
oa
c
h
ha
s
be
e
n
us
e
d
th
a
t
u
s
e
s
bot
h
s
upe
r
vi
s
e
d
a
nd
un
s
u
pe
r
vi
s
e
d
le
a
r
ni
ng
m
e
th
odol
ogi
e
s
to
c
a
r
r
y
out
pr
e
di
c
ti
ve
a
na
ly
s
i
s
of
s
of
twa
r
e
qua
li
ty
.
T
he
f
ol
lo
w
in
g
s
e
c
ti
on
di
s
c
u
s
s
e
s
th
e
r
e
s
e
a
r
c
h
m
e
th
odol
ogy
im
pl
e
m
e
nt
e
d t
ow
a
r
ds
a
c
c
om
pl
is
hi
ng t
he
a
bove
-
s
ta
te
d
s
tu
dy c
o
nt
r
ib
ut
io
n.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
14
, N
o.
3
,
J
une
20
25
:
1820
-
1828
1822
2.
M
E
T
H
O
D
T
he
pr
opos
e
d
s
ys
te
m
'
s
c
or
e
pur
pos
e
is
to
ha
r
ne
s
s
A
I
'
s
pot
e
n
ti
a
l
to
in
c
r
e
a
s
e
th
e
qu
a
li
ty
s
c
or
e
of
s
of
twa
r
e
de
ve
lo
pm
e
nt
.
F
or
th
is
pur
pos
e
,
th
e
pr
opo
s
e
d
s
ys
te
m
de
ve
lo
ps
a
uni
que
da
ta
s
e
t
m
ot
iv
a
te
d
by
th
e
e
xi
s
ti
ng
s
ta
nda
r
d
da
ta
s
e
t
[
26]
th
a
t
is
f
r
e
que
nt
ly
us
e
d
f
or
in
ve
s
t
ig
a
ti
ng
s
of
twa
r
e
qua
li
ty
c
onc
e
r
ni
ng
th
e
s
c
or
e
of
de
f
e
c
ts
.
T
he
pr
im
e
a
ge
nda
of
th
e
pr
opos
e
d
a
na
ly
ti
c
a
l
s
tu
dy
m
ode
l
is
to
r
e
duc
e
th
e
c
os
t
of
te
s
ti
ng
th
e
s
of
twa
r
e
qua
li
ty
a
lo
ng
w
it
h
th
e
r
e
te
nt
io
n
of
a
n
opt
im
a
l
s
c
or
e
of
a
c
c
ur
a
c
y
w
hi
le
de
pl
oyi
ng
A
I
.
F
r
om
th
e
pe
r
s
pe
c
ti
ve
of
A
I
,
th
e
e
xi
s
ti
ng
li
te
r
a
tu
r
e
f
in
ds
th
a
t
e
xi
s
ti
ng
A
I
ha
s
m
a
in
ly
us
e
d
le
a
r
ni
ng
-
ba
s
e
d
a
ppr
oa
c
he
s
f
or
pr
e
di
c
ti
ng
th
e
s
c
or
e
of
s
of
twa
r
e
qua
li
ty
;
how
e
ve
r
,
va
r
io
us
de
gr
e
e
s
of
f
lu
c
tu
a
ti
ons
a
nd
in
c
ons
is
te
nc
ie
s
a
r
e
a
s
s
oc
ia
t
e
d
w
it
h
it
.
H
e
nc
e
,
th
e
pr
opos
e
d
s
c
he
m
e
im
pl
e
m
e
nt
s
di
f
f
e
r
e
nt
va
r
ia
nt
s
of
le
a
r
ni
ng
a
ppr
oa
c
he
s
w
he
r
e
onl
y
s
e
le
c
ti
ve
a
tt
r
ib
ut
e
s
a
nd
c
a
te
gor
iz
a
ti
on
ope
r
a
ti
ons
a
r
e
c
a
r
r
i
e
d
out
to
a
c
c
om
pl
is
h
opt
im
a
l
a
c
c
ur
a
c
y
s
c
or
e
s
.
T
he
pr
oc
e
s
s
f
lo
w
of
t
he
pr
opos
e
d s
tu
dy mode
l
is
s
how
n i
n F
ig
ur
e
1.
F
ig
ur
e
1
.
P
r
o
c
e
s
s
f
lo
w
of
pr
op
o
s
e
d
s
t
udy
A
c
c
or
di
ng
to
F
ig
ur
e
1,
th
e
pr
opos
e
d
s
c
he
m
e
in
ve
s
ti
ga
te
s
di
f
f
e
r
e
nt
f
or
m
s
of
le
a
r
ni
ng
-
ba
s
e
d
a
ppr
oa
c
he
s
in
A
I
on
publ
ic
ly
a
va
il
a
bl
e
d
a
ta
s
e
t
s
w
it
h
th
e
s
ol
e
in
te
nt
io
n
of
opt
im
iz
in
g
th
e
a
c
c
ur
a
c
y
of
th
e
da
ta
s
e
t
in
c
ont
r
a
s
t
to
e
xi
s
ti
ng
s
tu
di
e
s
.
T
he
pr
opos
e
d
s
ys
te
m
us
e
s
a
c
lu
s
te
r
in
g
a
ppr
oa
c
h
to
gr
oup
th
e
c
la
s
s
la
be
ls
a
nd
th
e
n
s
ubj
e
c
t
th
e
e
xt
r
a
c
te
d
a
tt
r
ib
ut
e
s
to
c
la
s
s
if
ic
a
ti
on
a
ppr
oa
c
he
s
.
T
he
s
c
he
m
e
a
ls
o
us
e
s
a
na
tu
r
e
-
in
s
pi
r
e
d
a
lg
or
it
hm
to
opt
im
iz
e
th
e
in
te
r
na
l
ope
r
a
ti
on
of
le
a
r
ni
ng
-
ba
s
e
d
m
e
th
odol
ogi
e
s
.
S
ta
nda
r
d
pe
r
f
or
m
a
nc
e
pa
r
a
m
e
te
r
s
a
s
s
o
c
ia
te
d
w
it
h
a
c
c
ur
a
c
ie
s
a
r
e
a
dopt
e
d
to
te
s
ti
f
y
to
th
e
s
tu
dy
m
ode
l'
s
e
f
f
e
c
ti
ve
ne
s
s
.
F
ol
lo
w
in
g
is
th
e
s
e
que
nc
e
of
ope
r
a
ti
ons
be
in
g
c
a
r
r
ie
d
out
in
th
e
pr
opos
e
d
m
ode
l
to
w
a
r
ds
a
c
c
om
pl
is
hi
ng
th
e
s
tu
dy obje
c
ti
ve
s
:
‒
P
r
e
pr
oc
e
s
s
in
g
d
a
ta
:
th
e
pr
im
a
r
y
ta
s
k
in
th
e
p
r
opos
e
d
s
tu
dy
is
t
o
tr
a
ns
f
or
m
th
e
da
ta
s
e
t
be
f
or
e
s
ubj
e
c
ti
ng
it
to
th
e
le
a
r
ni
ng
ope
r
a
ti
on
to
a
c
c
om
pl
is
h
a
s
ta
nda
r
d
f
or
m
a
t.
I
t
w
a
s
not
e
d
th
a
t
th
e
r
e
is
a
s
ig
ni
f
ic
a
nt
ga
p
be
twe
e
n
th
e
c
ol
um
na
r
va
lu
e
s
w
it
hi
n
th
e
d
a
ta
s
e
t
c
onc
e
r
ni
ng
va
r
ie
d
s
t
a
nda
r
d
m
e
tr
ic
s
.
T
hi
s
s
ig
ni
f
ic
a
nt
di
f
f
e
r
e
nc
e
le
a
ds
to
a
bnor
m
a
ll
y
hi
ghe
r
s
ta
ti
s
ti
c
a
l
s
c
or
e
s
r
e
g
a
r
di
ng
s
ta
nda
r
d
de
vi
a
ti
on.
T
hi
s
is
s
or
te
d
out
by
us
in
g
a
s
ta
nd
a
r
d
s
c
a
li
ng
m
e
c
ha
ni
s
m
,
w
hi
c
h
c
a
n
m
a
ke
th
e
da
ta
s
e
t
m
uc
h
m
or
e
s
ta
nd
a
r
di
z
e
d
in
c
ont
r
a
s
t
to
w
ha
t
it
w
a
s
i
n i
ts
or
ig
in
a
l
f
or
m
. T
he
e
m
pi
r
ic
a
l
e
xpr
e
s
s
io
n of
s
u
c
h s
c
a
le
α i
s
r
e
pr
e
s
e
nt
e
d
as
(
1)
.
=
1
2
(
1)
I
n
(
1)
,
th
e
c
om
put
a
ti
on
of
s
c
a
le
α
f
or
s
ta
nda
r
di
z
a
ti
on
is
r
e
p
r
e
s
e
nt
e
d
a
s
th
e
A
1
a
nd
A
2
va
r
ia
bl
e
s
.
T
he
va
r
ia
bl
e
A
1
is
a
r
e
pr
e
s
e
nt
a
ti
on
of
th
e
di
f
f
e
r
e
nc
e
be
twe
e
n
obs
e
r
va
ti
on
σ
a
nd
th
e
m
e
a
n
va
lu
e
of
s
a
m
pl
e
s
of
tr
a
in
in
g
da
ta
μ,
i.
e
.,
A
1
=
(
σ
-
μ
)
,
w
hi
le
th
e
s
e
c
ond
va
r
ia
bl
e
A
2
r
e
pr
e
s
e
nt
s
s
t
a
nda
r
d
de
vi
a
ti
on
a
s
s
oc
ia
t
e
d
w
it
h
s
a
m
pl
e
s
of
t
r
a
in
in
g γ
, i
.e
.,
A
2
=
γ
.
‒
S
e
le
c
ti
on of
f
e
a
tu
r
e
:
th
e
pr
i
m
e
pur
pos
e
of
t
hi
s
m
odul
e
i
s
t
o
m
in
im
iz
e
t
he
c
a
r
di
na
li
ty
of
f
e
a
tu
r
e
s
a
s
s
oc
ia
te
d
w
it
h
pe
r
f
or
m
in
g
tr
a
in
in
g
a
nd
va
li
da
ti
on
ope
r
a
ti
ons
in
a
pr
e
di
c
ti
ve
m
ode
l.
T
h
e
pr
opos
e
d
s
c
he
m
e
us
e
s
a
m
ul
ti
c
ol
li
ne
a
r
it
y
a
nd
c
or
r
e
la
ti
on
a
ppr
oa
c
h
f
or
de
te
r
m
in
in
g
th
e
s
ig
ni
f
ic
a
nc
e
of
und
e
r
ta
ke
n
f
e
a
tu
r
e
s
onc
e
th
e
da
ta
s
e
t
is
r
e
a
dy
to
be
pr
oc
e
s
s
e
d.
T
h
e
pr
opos
e
d
s
c
he
m
e
c
ons
id
e
r
s
th
a
t
if
one
f
e
a
tu
r
e
is
di
r
e
c
tl
y
pr
opor
ti
ona
l
to
a
not
he
r
,
th
e
n
it
s
ta
te
s
two
f
e
a
tu
r
e
s
to
pos
s
e
s
s
a
pos
it
iv
e
c
or
r
e
la
ti
on
s
c
or
e
.
H
ow
e
ve
r
,
if
one
f
e
a
tu
r
e
is
in
ve
r
s
e
ly
pr
opor
ti
ona
l
to
a
not
h
e
r
,
it
s
ta
t
e
s
two
f
e
a
tu
r
e
s
to
po
s
s
e
s
s
a
ne
ga
ti
ve
c
or
r
e
la
ti
on
s
c
or
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
N
ov
e
l
ar
ti
fi
c
ia
l
in
te
ll
ig
e
nc
e
-
bas
e
d
e
ns
e
m
bl
e
l
e
ar
ni
ng f
or
opt
imi
z
e
d s
of
tw
a
r
e
quali
ty
…
(
Sange
e
th
a G
o
v
in
da
)
1823
O
n
th
e
ot
he
r
ha
nd,
if
one
f
e
a
tu
r
e
va
lu
e
doe
s
n'
t
a
f
f
e
c
t
th
e
f
e
a
t
ur
e
va
lu
e
of
a
not
he
r
,
th
e
pr
opos
e
d
s
c
he
m
e
c
ons
id
e
r
s
i
t
to
ha
ve
a
z
e
r
o
-
c
or
r
e
la
ti
on s
c
or
e
. T
o s
im
pl
if
y t
he
a
n
a
ly
s
is
, t
he
pr
opos
e
d
s
c
he
m
e
c
ons
id
e
r
s
onl
y
th
e
in
it
ia
l
m
num
be
r
of
n
a
tt
r
ib
ut
e
s
(
n
<<
m
)
w
he
r
e
s
uc
h
s
e
le
c
te
d
m
a
tt
r
ib
ut
e
s
a
r
e
e
it
he
r
ne
ga
ti
v
e
ly
or
z
e
r
o
c
or
r
e
la
te
d
w
it
hout
th
e
pr
e
s
e
nc
e
of
a
ny
c
la
s
s
la
be
ls
.
T
hi
s
s
e
le
c
ti
on
pr
oc
e
s
s
of
f
e
a
tu
r
e
s
a
s
s
is
ts
in
s
ig
ni
f
ic
a
nt
ly
c
ont
r
ol
li
ng
th
e
ove
r
f
it
ti
ng
is
s
ue
s
a
nd
m
in
im
iz
in
g
th
e
ope
r
a
ti
on
c
os
t
in
vol
ve
d
in
opt
im
iz
in
g
th
e
pe
r
f
or
m
a
nc
e
of
th
e
pr
opos
e
d
s
tu
dy
m
ode
l.
T
he
pr
opos
e
d
s
c
he
m
e
a
dopt
s
th
e
hybr
id
le
a
r
ni
ng
a
ppr
oa
c
h
in
A
I
w
he
r
e
uns
upe
r
vi
s
e
d a
nd s
upe
r
vi
s
e
d l
e
a
r
ni
ng a
ppr
oa
c
he
s
a
r
e
us
e
d f
or
c
a
te
gor
iz
in
g a
nd c
la
s
s
if
ic
a
ti
on,
r
e
s
pe
c
ti
ve
ly
t
ow
a
r
ds
opt
im
iz
in
g t
he
s
of
twa
r
e
qua
li
ty
pr
e
di
c
ti
on. F
ol
lo
w
in
g i
s
f
ur
th
e
r
i
nf
or
m
a
ti
on a
bout
i
ts
im
pl
e
m
e
nt
a
ti
on
.
‒
C
a
te
gor
iz
a
ti
on:
th
e
pr
opo
s
e
d
s
t
udy
m
ode
l
us
e
s
th
e
k
-
m
e
a
n
s
c
lu
s
t
e
r
in
g
(
K
M
C
)
a
ppr
oa
c
h
to
s
t
udy
c
la
s
s
la
be
l
s
t
o
c
ho
os
e
t
h
e
c
a
r
di
n
a
li
ty
of
c
lu
s
te
r
s
o
pt
im
a
ll
y.
T
he
e
m
pi
r
i
c
a
l
f
or
m
of
t
he
k
s
c
or
e
of
c
lu
s
te
r
s
i
s
a
s
(
2)
:
=
∑
2
=
1
(
2)
T
he
a
bov
e
e
m
pi
r
ic
a
l
e
xpr
e
s
s
io
n
(
2)
r
e
pr
e
s
e
nt
s
δ
,
i.
e
.,
th
e
s
um
of
s
qua
r
e
s
pr
e
s
e
nt
s
in
one
c
lu
s
te
r
out
of
k
c
lu
s
te
r
s
r
e
pr
e
s
e
nt
e
d
by
τ,
i.
e
.,
th
e
di
s
ta
nc
e
be
twe
e
n
th
e
da
ta
poi
nt
a
nd
r
e
s
pe
c
ti
ve
c
e
nt
r
oi
d
in
th
e
k
num
be
r
of
c
lu
s
te
r
s
.
‒
C
la
s
s
if
ic
a
ti
on:
th
e
pr
opos
e
d
s
c
he
m
e
us
e
s
a
s
upe
r
vi
s
e
d
le
a
r
ni
n
g
m
e
th
od
f
or
th
e
da
ta
c
ha
r
a
c
te
r
iz
e
d
by
th
e
c
la
s
s
la
be
l
a
s
th
e
out
put
.
F
ur
th
e
r
,
th
e
s
c
he
m
e
c
la
s
s
if
ie
s
th
e
d
a
ta
in
to
70%
a
nd
30%
of
th
e
tr
a
in
in
g
a
nd
te
s
ti
ng
da
ta
,
r
e
s
pe
c
ti
ve
ly
.
T
he
da
ta
w
it
h
c
la
s
s
la
be
ls
a
r
e
c
on
s
id
e
r
e
d
f
or
t
r
a
in
in
g
w
hi
le
da
ta
w
it
hout
a
ny
c
la
s
s
la
be
ls
a
r
e
us
e
d
f
or
te
s
ti
ng.
F
ur
th
e
r
,
th
e
s
c
he
m
e
us
e
s
m
ul
ti
pl
e
c
la
s
s
if
ie
r
s
to
c
onduc
t
c
la
s
s
if
ic
a
ti
on
a
na
ly
s
is
in
th
e
f
or
m
of
e
ns
e
m
bl
e
c
l
a
s
s
if
ie
r
s
. T
he
s
c
he
m
e
u
s
e
s
r
a
ndom
f
or
e
s
t
(
R
F
)
,
n
a
ïv
e
B
a
ye
s
(
N
B
)
,
a
nd
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
(
S
V
M
)
, w
he
r
e
t
he
R
F
a
nd
S
V
M
a
r
e
c
ons
id
e
r
e
d a
s
c
a
ndi
da
te
pr
e
di
c
ti
ve
m
ode
ls
. I
n
c
ont
r
a
s
t,
N
B
i
s
c
on
s
id
e
r
e
d a
ba
s
e
li
ne
pr
e
di
c
ti
ve
m
ode
l
f
or
pe
r
f
or
m
in
g c
la
s
s
if
ic
a
ti
on.
T
he
pr
im
e
ju
s
ti
f
ic
a
ti
on
be
hi
nd
a
dopt
in
g
th
e
R
F
a
ppr
oa
c
h
is
t
ha
t
it
a
c
ts
a
s
a
n
in
te
gr
a
te
d
l
e
a
r
ni
ng
m
e
th
od
th
a
t
in
te
gr
a
te
s
va
r
ie
d
f
or
m
s
of
c
la
s
s
if
ie
r
s
f
or
opt
im
iz
i
ng
th
e
pr
e
di
c
ti
ve
out
c
om
e
.
M
ul
ti
pl
e
de
c
is
io
n
tr
e
e
s
c
a
n
be
de
pl
oye
d
to
th
e
da
ta
s
ubs
e
t
f
ol
lo
w
e
d
by
e
xt
r
a
c
ti
n
g
it
s
m
e
a
n
va
lu
e
to
a
r
r
iv
e
a
t
th
e
f
in
a
l
va
lu
e
of
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
.
T
he
s
c
he
m
e
us
e
s
a
950
tr
e
e
s
tr
uc
tu
r
e
a
lo
ng
w
it
h
50
a
r
bi
tr
a
r
y
s
ta
te
s
f
or
im
pl
e
m
e
nt
in
g
th
is
c
la
s
s
if
ie
r
.
T
h
e
s
c
h
e
m
e
us
e
s
th
e
N
B
a
lg
or
it
hm
known
f
or
it
s
c
a
te
gor
iz
a
ti
on
c
a
p
a
bi
li
ti
e
s
a
nd
c
la
s
s
if
ic
a
ti
on.
T
hi
s
a
ppr
oa
c
h
c
om
put
e
s
a
ll
th
e
li
ke
li
hoods
a
nd
th
e
n
e
s
ti
m
a
te
s
pr
oba
bi
li
ti
e
s
th
a
t
don'
t
f
a
vour
th
e
li
ke
li
hoods
.
T
he
a
ppr
oa
c
h
w
or
ks
s
ui
ta
bl
y
in
th
e
pr
e
s
e
nc
e
of
no
c
onne
c
ti
o
n
a
m
ong
th
e
e
s
s
e
nt
ia
l
f
e
a
tu
r
e
s
of
th
e
da
ta
s
e
t.
T
he
s
c
he
m
e
c
ons
id
e
r
s
40
a
s
a
s
ta
t
e
of
a
r
bi
tr
a
r
in
e
s
s
.
F
in
a
ll
y,
th
e
pr
opos
e
d
s
c
he
m
e
us
e
s
S
V
M
,
a
not
he
r
dom
in
a
nt
f
or
m
of
s
upe
r
vi
s
e
d
le
a
r
ni
ng
a
ppr
oa
c
h
in
A
I
.
C
ons
id
e
r
in
g
a
r
e
s
tr
ic
te
d
da
ta
s
e
t
s
i
z
e
,
S
V
M
of
f
e
r
s
be
tt
e
r
pe
r
f
or
m
a
nc
e
a
nd
r
e
duc
e
d
pr
oc
e
s
s
in
g
ti
m
e
.
T
he
c
ons
i
de
r
e
d
da
ta
is
c
la
s
s
if
ie
d
us
in
g
a
bounda
r
y
of
de
c
is
io
n
by
S
V
M
w
he
r
e
e
a
c
h
in
vol
ve
d
c
la
s
s
a
r
e
c
la
s
s
if
ie
d.
T
h
e
s
ys
te
m
a
c
c
om
pl
is
h
e
s
a
n
opt
im
a
l
hype
r
pl
a
ne
in
th
e
pr
e
s
e
nc
e
of
th
e
hi
ghe
s
t
de
gr
e
e
of
m
a
r
gi
ns
ge
ne
r
a
te
d
f
r
om
a
ll
th
e
c
la
s
s
e
s
.
A
s
im
il
a
r
va
lu
e
of
40
is
c
ons
id
e
r
e
d a
s
t
a
te
of
a
r
bi
tr
a
r
in
e
s
s
i
n S
V
M
i
m
pl
e
m
e
nt
a
ti
on.
I
t
is
to
be
not
e
d
th
a
t
th
e
pr
opos
e
d
A
I
m
e
th
od
us
e
s
a
n
e
ns
e
m
bl
e
f
or
m
o
f
pr
e
di
c
ti
ve
a
ppr
oa
c
h
a
nd
not
a
n
in
te
gr
a
te
d
f
or
m
of
pr
e
di
c
ti
ve
a
ppr
oa
c
h.
I
t
w
il
l
m
e
a
n
th
a
t
th
e
pr
opos
e
d
s
c
he
m
e
h
a
s
c
ons
id
e
r
e
d
one
le
a
r
ni
ng
m
ode
l
N
B
a
s
th
e
b
a
s
e
li
ne
pr
e
di
c
ti
ve
m
ode
l
w
hi
l
e
ot
he
r
m
ode
ls
R
F
a
nd
S
V
M
a
c
t
a
s
c
a
ndi
da
te
pr
e
di
c
ti
ve
m
ode
ls
.
T
he
pr
opos
e
d
s
c
he
m
e
im
pl
e
m
e
nt
s
th
is
A
I
a
ppr
oa
c
h
us
in
g
a
s
ta
c
ki
ng
c
la
s
s
if
ic
a
ti
on
-
ba
s
e
d
m
e
th
odol
ogy.
A
t
th
e
s
a
m
e
ti
m
e
,
a
va
lu
e
of
40
is
a
ls
o
m
a
in
ta
in
e
d
to
im
pl
e
m
e
nt
th
is
e
ns
e
m
bl
e
pr
e
di
c
ti
ve
m
ode
l
w
it
h
r
e
s
pe
c
t
to
it
s
va
lu
e
of
s
ta
t
e
of
it
s
a
r
bi
tr
a
r
in
e
s
s
.
T
h
e
s
ta
nda
r
d
pe
r
f
or
m
a
nc
e
pa
r
a
m
e
t
e
r
s
a
s
s
oc
ia
te
d
w
it
h
th
e
a
c
c
ur
a
c
y
-
ba
s
e
d a
tt
r
ib
ut
e
s
a
r
e
c
ons
id
e
r
e
d
f
or
th
e
a
s
s
e
s
s
m
e
nt
.
T
he
f
ol
lo
w
in
g
s
e
c
ti
on
e
la
bor
a
te
s
on
th
e
out
c
om
e
a
f
te
r
i
m
pl
e
m
e
nt
in
g t
hi
s
s
c
he
m
e
of
pr
e
di
c
ti
ng s
of
twa
r
e
qua
li
ty
.
3.
R
E
S
U
L
T
S
T
hi
s
s
e
c
ti
on
di
s
c
us
s
e
s
th
e
out
c
om
e
of
th
e
pr
opo
s
e
d
s
tu
dy
i
ll
us
tr
a
te
d
in
th
e
pr
io
r
s
e
c
ti
on.
T
h
e
im
pl
e
m
e
nt
a
ti
on
of
th
e
pr
opos
e
d
s
tu
dy
ha
s
be
e
n
c
a
r
r
ie
d
out
c
ons
id
e
r
in
g
th
e
s
ta
nda
r
d
C
M
1
d
a
ta
s
e
t
th
a
t
c
ons
is
ts
of
22
pr
ope
r
ti
e
s
w
it
h
499
m
odul
e
s
w
it
h
449
de
f
e
c
t
f
r
e
e
in
s
ta
nc
e
s
,
49
de
f
e
c
ti
ve
in
s
ta
nc
e
s
, a
nd
w
r
it
te
n
in
C
la
ngua
ge
.
A
c
lo
s
e
r
lo
ok
in
to
th
is
da
ta
s
e
t
s
how
s
a
ppr
oxi
m
a
te
ly
a
10%
de
f
e
c
t
r
a
te
.
F
r
om
th
e
pe
r
s
pe
c
ti
ve
of
m
e
tr
ic
s
,
th
is
d
a
ta
s
e
t
c
ons
i
s
ts
of
H
a
ls
te
a
d
a
nd
M
c
c
a
be
m
e
tr
ic
s
,
w
hi
c
h
a
r
e
num
e
r
ic
a
l
da
ta
a
nd
m
e
th
od
-
le
ve
l
a
tt
r
ib
ut
e
s
.
T
hi
s
da
ta
s
e
t
is
s
ubj
e
c
te
d
to
pr
e
pr
oc
e
s
s
in
g,
s
e
le
c
ti
ng
e
s
s
e
nt
ia
l
f
e
a
tu
r
e
s
,
a
nd
p
e
r
f
or
m
in
g
a
n
e
ns
e
m
bl
e
d A
I
-
ba
s
e
d l
e
a
r
ni
ng a
ppr
oa
c
h w
it
h r
e
s
p
e
c
t
to
c
a
te
gor
i
z
a
ti
on a
nd c
la
s
s
if
ic
a
ti
on.
T
he
pr
opos
e
d s
y
s
te
m
m
ode
l
is
s
c
r
ip
te
d
us
in
g
P
yt
hon,
c
ons
id
e
r
in
g
a
nor
m
a
l
w
in
dow
s
m
a
c
hi
ne
.
T
he
pr
opos
e
d
s
ys
te
m
i
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
14
, N
o.
3
,
J
une
20
25
:
1820
-
1828
1824
be
nc
hm
a
r
ki
ng
by
c
om
pa
r
in
g
it
w
it
h
a
n
e
xi
s
ti
ng
s
ta
nda
lo
ne
a
p
pr
oa
c
h
of
le
a
r
ni
ng
a
lg
or
it
hm
s
,
vi
z
.
N
B
,
S
V
M
,
R
F
,
K
M
C
.
I
t
is
a
l
s
o
c
om
pa
r
e
d
w
it
h
s
t
a
nda
lo
ne
bi
o
-
in
s
pi
r
e
d
a
ppr
oa
c
he
s
vi
z
:
pa
r
ti
c
le
s
w
a
r
m
opt
im
iz
a
ti
on
(
P
S
O
)
a
nd
a
nt
c
ol
ony
opt
im
iz
a
ti
on
(
A
C
O
)
.
T
he
a
s
s
e
s
s
m
e
nt
c
onc
e
r
ns
de
f
e
c
t
de
n
s
it
y,
m
e
a
n
ti
m
e
-
to
-
f
a
il
ur
e
(
M
T
T
F
)
, a
c
c
ur
a
c
y, a
nd a
lg
or
it
hm
pr
oc
e
s
s
in
g t
im
e
.
3.1
.
A
c
c
om
p
li
s
h
e
d
ou
t
c
om
e
T
he
pr
im
a
r
y
pe
r
f
or
m
a
nc
e
m
e
tr
ic
e
va
lu
a
te
d
in
th
e
out
c
om
e
a
s
s
e
s
s
m
e
nt
pr
oc
e
s
s
i
s
de
f
e
c
t
d
e
ns
it
y,
w
hi
c
h
is
c
om
pu
a
te
d
a
s
to
ta
l
num
be
r
of
de
f
e
c
ts
in
e
a
c
h
c
ode
li
ne
.
I
t
c
a
n
a
ls
o
be
a
na
ly
z
e
d
f
r
om
th
e
f
unc
ti
ona
l
poi
nt
s
.
A
pr
a
c
ti
c
a
l
de
s
ig
n
of
s
of
twa
r
e
w
il
l
a
lwa
ys
a
nt
ic
ip
a
te
f
or
lo
w
e
r
nu
m
be
r
of
de
f
e
c
t
de
ns
it
ie
s
.
T
o
of
f
e
r
c
le
a
r
a
nd
unde
r
s
ta
nd
a
bl
e
in
f
e
r
e
nc
e
,
th
e
d
e
f
e
c
t
de
n
s
it
y
s
c
or
e
i
s
tr
a
ns
f
or
m
e
d
to
pr
oba
bi
li
ty
va
lu
e
s
f
or
be
tt
e
r
qua
nt
if
ic
a
ti
on
of
out
c
om
e
s
.
T
h
e
s
im
ul
a
te
d
out
c
om
e
of
th
e
pr
o
pos
e
d
s
y
s
te
m
w
it
h
a
n
e
xi
s
ti
ng
A
I
-
ba
s
e
d
ot
he
r
s
ta
nda
lo
ne
l
e
a
r
ni
ng a
ppr
oa
c
h
e
s
a
nd bio
-
in
s
pi
r
e
d a
ppr
oa
c
h
e
s
a
r
e
s
how
n i
n F
ig
ur
e
2
.
F
ig
ur
e
2
.
C
om
p
a
r
a
ti
ve
a
na
ly
s
i
s
of
de
f
e
c
t
d
e
n
s
it
y
T
he
out
c
om
e
s
ho
w
n
in
F
ig
ur
e
2
s
ho
w
c
a
s
e
s
th
a
t
th
e
pr
opos
e
d
s
ys
te
m
p
r
op
of
f
e
r
s
a
ppr
oxi
m
a
te
ly
65%
of
th
e
r
e
duc
e
d
s
c
or
e
of
de
f
e
c
t
de
ns
it
y
in
c
ont
r
a
s
t
to
th
e
e
xi
s
ti
n
g
s
ys
te
m
.
S
om
e
of
th
e
in
te
r
e
s
ti
ng
f
in
di
ngs
c
a
n
be
w
it
hdr
a
w
n
f
r
o
m
th
is
out
c
om
e
.
A
c
lo
s
e
r
lo
ok
in
to
th
e
out
c
o
m
e
s
how
s
th
a
t
th
e
N
B
a
ppr
oa
c
h,
w
hi
c
h
a
c
ts
a
s
a
ba
s
e
li
ne
m
ode
l
in
th
e
pr
opos
e
d
s
ys
te
m
,
pe
r
f
or
m
s
m
uc
h
be
tt
e
r
th
a
n
th
e
s
ta
nda
lo
ne
N
B
a
ppr
oa
c
h.
A
s
im
il
a
r
tr
e
nd
is
a
ls
o
s
e
e
n
f
or
c
onve
nt
io
na
l
s
ta
nda
lo
ne
S
V
M
a
nd
R
F
a
ppr
oa
c
he
s
,
a
ls
o
us
e
d
in
e
ns
e
m
bl
e
f
or
m
in
th
e
pr
opos
e
d
s
ys
te
m
.
I
t
c
a
n
a
ls
o
be
s
e
e
n
th
a
t
K
M
C
us
a
ge
a
s
a
s
ta
nda
lo
ne
a
ppr
oa
c
h
of
f
e
r
s
m
or
e
de
f
e
c
t
s
in
c
ont
r
a
s
t
to
it
s
in
te
gr
a
te
d
us
a
ge
in
th
e
pr
opos
e
d
s
c
he
m
e
.
T
hi
s
out
c
om
e
s
how
c
a
s
e
s
th
a
t
th
e
e
ns
e
m
bl
e
a
ppr
oa
c
h
of
A
I
us
e
d
in
th
e
pr
opos
e
d
s
y
s
te
m
of
f
e
r
s
be
tt
e
r
r
e
du
c
ti
on
of
de
f
e
c
t
de
ns
it
y
pe
r
f
or
m
a
nc
e
in
c
ont
r
a
s
t
to
c
onve
nt
io
na
l
A
I
-
ba
s
e
d
s
ta
nda
lo
ne
a
ppr
oa
c
he
s
.
A
pa
r
t
f
r
om
th
is
,
it
is
not
e
d
th
a
t
us
in
g
bi
o
-
in
s
pi
r
e
d
a
ppr
oa
c
he
s
in
te
gr
a
te
d
in
to
th
e
pr
opos
e
d
s
ys
t
e
m
ha
s
r
e
duc
e
d
de
f
e
c
t
de
n
s
it
y s
c
or
e
s
c
om
pa
r
e
d
to
s
ta
nda
lo
ne
P
S
O
a
nd
A
C
O
a
lg
or
it
hm
s
.
T
he
s
e
c
ond
li
ne
of
a
na
ly
s
i
s
s
how
n
in
F
ig
ur
e
3
is
a
s
s
oc
ia
te
d
w
it
h
e
va
lu
a
ti
ng
M
T
T
F
,
c
om
put
e
d
a
s
m
e
a
n
dur
a
ti
on
be
twe
e
n
th
e
s
of
twa
r
e
f
a
il
ur
e
s
r
e
pr
e
s
e
nt
e
d
in
t
he
pr
oba
bi
li
ty
s
c
or
e
.
F
ur
th
e
r
,
F
ig
ur
e
s
3
to
5
s
how
s
t
ha
t
th
e
pr
opos
e
d s
y
s
te
m
of
f
e
r
s
a
ppr
oxi
m
a
te
ly
94%
r
e
du
c
e
d M
T
T
F
, 43%
i
nc
r
e
a
s
e
d a
c
c
ur
a
c
y, a
nd 62%
r
e
duc
e
d a
lg
or
it
hm
pr
oc
e
s
s
in
g t
im
e
i
n c
ont
r
a
s
t
to
e
xi
s
ti
ng A
I
-
ba
s
e
d a
ppr
oa
c
he
s
f
or
e
nha
nc
in
g s
of
twa
r
e
qua
li
ty
pr
e
di
c
ti
on.
3.2
.
D
is
c
u
s
s
io
n
o
f
r
e
s
u
lt
s
T
he
ove
r
a
ll
r
e
s
ul
t
s
c
or
e
s
how
c
a
s
e
s
th
a
t
th
e
pr
opos
e
d
s
y
s
te
m
of
f
e
r
s
a
c
on
s
is
te
nt
p
a
tt
e
r
n
of
out
c
om
e
s
c
om
pa
r
e
d
to
e
xi
s
ti
ng
A
I
-
ba
s
e
d
a
ppr
oa
c
he
s
.
T
h
e
pr
im
e
r
e
a
s
o
n
be
hi
nd
th
e
s
e
out
c
om
e
pa
tt
e
r
ns
a
nd
tr
e
nds
s
how
n
in
gr
a
phi
c
a
l
out
c
om
e
s
c
a
n
be
ju
s
ti
f
ie
d
a
s
f
ol
lo
w
s
:
u
n
li
ke
a
ny
c
onve
nt
io
na
l
s
tu
di
e
s
w
it
h
A
I
-
ba
s
e
d
s
of
twa
r
e
e
ngi
ne
e
r
in
g
s
ol
ut
io
ns
,
th
e
pr
opos
e
d
s
y
s
te
m
doe
s
n'
t
c
ons
id
e
r
it
s
in
put
da
ta
s
e
t
a
s
it
is
s
ubj
e
c
te
d
to
le
a
r
ni
ng
a
ppr
oa
c
he
s
.
I
ns
te
a
d,
th
e
r
a
w
da
t
a
s
e
t
unde
r
goe
s
a
s
e
r
i
e
s
of
ope
r
a
ti
ons
,
e
li
m
in
a
ti
ng
it
s
in
c
ons
is
te
nc
y
a
nd
e
nha
nc
in
g
th
e
qua
li
ty
,
th
e
r
e
by
of
f
e
r
in
g
hi
ghe
r
da
ta
pur
it
y.
H
e
nc
e
,
it
of
f
e
r
s
a
s
ig
ni
f
ic
a
nt
ly
lo
w
c
om
put
a
ti
ona
l
bur
de
n
w
he
n
A
I
-
ba
s
e
d
m
e
th
odol
ogi
e
s
a
r
e
a
pp
li
e
d.
T
he
pr
opos
e
d
s
c
h
e
m
e
pr
e
s
e
nt
s
a
nove
l
e
ns
e
m
bl
e
a
ppr
oa
c
h
of
dua
l
f
or
m
s
a
f
te
r
pe
r
f
or
m
in
g
th
e
c
a
t
e
gor
iz
a
ti
on
ope
r
a
ti
on
us
in
g
K
M
C
.
T
he
f
ir
s
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
N
ov
e
l
ar
ti
fi
c
ia
l
in
te
ll
ig
e
nc
e
-
bas
e
d
e
ns
e
m
bl
e
l
e
ar
ni
ng f
or
opt
imi
z
e
d s
of
tw
a
r
e
quali
ty
…
(
Sange
e
th
a G
o
v
in
da
)
1825
e
ns
e
m
bl
e
a
ppr
oa
c
h
w
a
s
to
c
ons
id
e
r
R
F
,
N
B
,
a
nd
S
V
M
,
w
hi
le
th
e
s
e
c
ond
w
a
s
to
in
te
gr
a
te
a
ll
th
r
e
e
le
a
r
ni
ng
a
ppr
oa
c
he
s
w
it
h
th
e
bi
o
-
in
s
pi
r
e
d
a
ppr
oa
c
h
of
P
S
O
.
T
hi
s
r
e
du
c
e
s
th
e
c
om
put
a
ti
ona
l
lo
a
d
a
nd
in
c
r
e
a
s
e
s
th
e
a
c
c
ur
a
c
y, w
hi
c
h c
a
n be
di
r
e
c
tl
y s
ta
te
d
a
s
t
he
c
or
e
r
e
a
s
on f
or
s
of
twa
r
e
qua
li
ty
i
m
pr
ove
m
e
nt
.
H
ow
e
ve
r
,
th
e
c
onve
nt
io
na
l
A
I
-
ba
s
e
d
a
ppr
oa
c
he
s
in
th
e
ir
s
ta
nda
lo
ne
f
or
m
w
e
r
e
w
it
ne
s
s
e
d
w
it
h
s
ub
-
opt
im
a
l
pe
r
f
or
m
a
nc
e
s
c
or
e
s
.
W
he
n
th
e
N
B
a
ppr
oa
c
h
is
us
e
d
in
th
e
pr
opos
e
d
d
e
s
ig
n
im
pl
e
m
e
nt
a
ti
on,
it
e
f
f
e
c
ti
ve
ly
of
f
e
r
s
e
f
f
e
c
ti
ve
ne
s
s
to
w
a
r
ds
be
tt
e
r
pr
oc
e
s
s
in
g
of
c
a
te
gor
ic
a
l
da
ta
a
nd
hi
ghe
r
di
m
e
ns
io
n
a
l
da
ta
.
H
ow
e
ve
r
,
w
he
n
us
e
d
a
s
a
s
ta
nda
lo
n
e
f
or
m
,
it
s
how
e
d
unde
r
-
pe
r
f
or
m
a
nc
e
is
s
ue
s
in
a
ll
th
e
e
va
lu
a
ti
on
m
e
tr
ic
s
,
e
s
pe
c
ia
ll
y
in
th
e
pr
e
s
e
n
c
e
of
a
hi
ghe
r
num
be
r
of
c
or
r
e
la
te
d
f
e
a
tu
r
e
s
.
F
ur
th
e
r
,
s
ta
nda
lo
ne
N
B
w
a
s
pr
ove
n
not
to
of
f
e
r
m
uc
h
a
s
s
is
ta
n
c
e
to
w
a
r
d
s
c
om
pl
e
x
r
e
la
ti
ons
hi
ps
w
it
hi
n t
he
da
ta
. T
he
s
e
c
ond
a
lg
or
it
hm
of
S
V
M
,
w
he
n
us
e
d
w
it
h
th
e
pr
opos
e
d
s
ys
te
m
,
s
how
c
a
s
e
d
it
s
c
a
pa
bi
li
ty
to
pr
oc
e
s
s
hi
gh
-
di
m
e
ns
io
na
l
da
ta
,
a
nd
th
e
r
e
a
r
e
not
m
a
ny
is
s
ue
s
to
w
a
r
ds
ov
e
r
f
it
ti
ng.
H
ow
e
ve
r
,
th
e
s
ta
nda
lo
ne
us
a
g
e
of
S
V
M
on
th
e
C
M
1
da
ta
s
e
t
w
a
s
w
it
ne
s
s
e
d
w
it
h
hi
ghe
r
pr
oc
e
s
s
in
g
ti
m
e
.
A
s
im
il
a
r
tr
e
nd
w
a
s
a
l
s
o
w
it
ne
s
s
e
d
f
or
th
e
R
F
a
lg
or
it
hm
,
w
hi
c
h
la
c
ke
d
in
te
r
pr
e
ta
bi
li
ty
a
nd w
a
s
e
nc
ount
e
r
e
d w
it
h a
n i
nt
e
r
m
it
te
nt
s
lo
w
t
r
a
in
in
g pr
oc
e
s
s
.
F
ur
th
e
r
,
th
e
R
F
a
lg
or
it
hm
doe
s
n'
t
p
e
r
f
or
m
w
e
ll
in
a
n
im
ba
la
n
c
e
d
da
ta
s
e
t.
I
t
i
s
to
be
not
e
d
th
a
t
th
e
K
M
C
a
lg
or
it
hm
w
a
s
s
ig
ni
f
ic
a
nt
ly
a
s
s
is
ti
ve
in
th
e
pr
opos
e
d
s
c
he
m
e
to
w
a
r
ds
c
a
te
gor
iz
a
ti
on
w
it
h
m
or
e
s
tr
a
ig
ht
f
or
w
a
r
d i
m
pl
e
m
e
nt
a
ti
on
e
f
f
ic
ie
nc
y f
o
r
l
a
r
ge
r
da
ta
s
e
ts
, t
oo. T
he
s
ta
nda
lo
ne
ve
r
s
io
n of
K
M
C
w
a
s
not
e
d
w
it
h
hi
ghe
r
s
e
ns
it
iv
it
y
to
w
a
r
ds
in
it
ia
l
c
lu
s
te
r
s
a
nd
de
m
a
nds
th
e
a
c
qui
s
it
io
n
of
pr
e
de
f
in
e
d
c
lu
s
te
r
s
,
w
hi
c
h
m
a
y
not
be
s
ui
ta
bl
e
f
or
th
e
r
e
a
l
-
ti
m
e
e
nvi
r
onm
e
nt
of
s
of
twa
r
e
d
e
s
i
gn
a
s
s
e
s
s
m
e
nt
.
W
h
e
n
us
e
d
w
it
h
th
e
pr
opos
e
d
e
ns
e
m
bl
e
a
ppr
oa
c
h
w
it
h
A
I
m
e
th
ods
,
a
bi
o
-
in
s
pi
r
e
d
a
ppr
oa
c
h
li
ke
P
S
O
w
a
s
w
it
ne
s
s
e
d
w
it
h
m
or
e
s
tr
a
ig
ht
f
or
w
a
r
d i
m
pl
e
m
e
nt
a
ti
on w
it
h be
tt
e
r
c
ons
is
te
nc
y. H
ow
e
v
e
r
, t
he
s
ta
nda
lo
ne
ve
r
s
io
n of
P
S
O
a
nd A
C
O
i
s
w
it
ne
s
s
e
d
to
of
f
e
r
li
m
it
e
d
pe
r
f
or
m
a
nc
e
in
hi
gh
-
di
m
e
ns
io
na
l
s
pa
c
e
s
a
nd
s
lo
w
e
r
c
onve
r
ge
nc
e
s
pe
e
d
s
,
r
e
s
pe
c
ti
ve
ly
.
T
hi
s
r
e
s
ul
ts
in
hi
ghe
r
de
f
e
c
t
de
ns
it
y,
hi
ghe
r
M
T
T
F
,
lo
w
e
r
a
c
c
ur
a
c
y,
a
nd
in
c
r
e
a
s
e
d
a
lg
or
it
hm
pr
oc
e
s
s
in
g
ti
m
e
.
H
e
nc
e
,
th
e
ove
r
a
ll
out
c
om
e
s
ugge
s
ts
th
e
pr
opos
e
d
e
ns
e
m
bl
e
A
I
-
ba
s
e
d
a
ppr
oa
c
h
to
of
f
e
r
opt
im
a
l
s
of
twa
r
e
de
s
ig
n qua
li
ty
.
F
ig
ur
e
3
.
C
om
pa
r
a
ti
ve
a
na
ly
s
is
of
m
e
a
n t
im
e
t
o
f
a
il
ur
e
F
ig
ur
e
4
.
C
om
p
a
r
a
ti
ve
a
na
ly
s
i
s
of
a
c
c
ur
a
c
y
F
ig
ur
e
5
.
C
om
pa
r
a
ti
ve
a
na
ly
s
is
of
a
lg
or
it
hm
pr
oc
e
s
s
in
g t
im
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
14
, N
o.
3
,
J
une
20
25
:
1820
-
1828
1826
4.
C
O
N
C
L
U
S
I
O
N
T
he
pr
opos
e
d
s
y
s
te
m
ha
s
pr
e
s
e
nt
e
d
a
nove
l
e
ns
e
m
bl
e
-
ba
s
e
d
A
I
m
e
th
od
to
w
a
r
ds
le
ve
r
a
gi
ng
th
e
pr
e
di
c
ti
ve
pe
r
f
or
m
a
nc
e
a
s
s
oc
ia
te
d
w
it
h
s
of
twa
r
e
qua
li
ty
.
T
he
pr
opos
e
d
s
tu
dy
ha
s
de
pl
oye
d
le
a
r
ni
ng
-
ba
s
e
d
a
ppr
oa
c
he
s
th
a
t
a
s
s
is
t
to
w
a
r
ds
f
e
a
tu
r
e
s
e
le
c
ti
on
w
hi
le
th
e
s
of
twa
r
e
qua
li
ty
pr
e
di
c
ti
on
is
c
a
r
r
ie
d
out
by
c
lu
s
te
r
in
g.
T
he
pr
opos
e
d
s
tu
dy
m
ode
l
c
ont
r
ib
ut
e
s
to
w
a
r
ds
th
e
f
ol
lo
w
in
g
nove
l
f
e
a
tu
r
e
s
:
i)
th
e
pr
opos
e
d
s
c
he
m
e
us
e
s
a
s
ta
nd
a
r
d
publ
ic
ly
a
va
il
a
bl
e
da
ta
s
e
t
f
or
s
of
twa
r
e
qua
li
ty
th
a
t
is
s
ubj
e
c
te
d
to
e
m
pi
r
ic
a
ll
y
de
s
ig
ne
d
s
c
a
la
r
a
tt
r
ib
ut
e
s
to
w
a
r
ds
pe
r
f
or
m
in
g
th
e
pr
e
pr
oc
e
s
s
in
g
ope
r
a
ti
on,
unl
ik
e
th
e
e
xi
s
ti
ng
a
ppr
oa
c
h
th
a
t
doe
s
n'
t
e
m
pha
s
iz
e
m
uc
h on thi
s
s
te
p, i
i)
t
he
pr
opos
e
d s
c
h
e
m
e
a
l
s
o i
nt
r
oduc
e
d a
s
im
pl
if
ie
d s
e
le
c
ti
on of
f
e
a
tu
r
e
c
ons
id
e
r
in
g
c
or
r
e
la
ti
on
a
nd
m
ul
ti
c
ol
li
ne
a
r
it
y
a
tt
r
ib
ut
e
th
a
t
is
s
uc
c
e
s
s
f
ul
ly
us
e
d
f
or
e
s
ta
bl
is
hi
ng
r
e
la
ti
ons
hi
p
a
m
ong
c
om
pl
e
x
a
tt
r
ib
ut
e
s
of
da
ta
s
e
t,
ii
i)
th
e
pr
opos
e
d
s
c
he
m
e
us
e
s
uns
up
e
r
vi
s
e
d
le
a
r
ni
ng
a
ppr
oa
c
h
in
A
I
f
or
pe
r
f
or
m
in
g
c
a
te
gor
iz
a
ti
on
w
hi
le
s
upe
r
vi
s
e
d
a
ppr
oa
c
h
is
u
s
e
d
to
w
a
r
ds
c
a
r
r
yi
ng
out
pr
e
di
c
ti
ve
p
e
r
f
or
m
a
nc
e
,
a
nd
iv
)
pr
opos
e
d
s
tu
dy
m
ode
l
of
f
e
r
s
a
ppr
oxi
m
a
te
ly
65%
of
m
in
im
iz
e
d
de
f
e
c
t
de
n
s
it
y,
94%
of
m
in
im
iz
e
d
M
T
T
F
,
62%
of
m
in
im
iz
e
d
pr
oc
e
s
s
in
g
ti
m
e
of
a
lg
or
it
hm
,
a
nd
43%
of
e
nha
nc
e
d
pr
e
di
c
ti
ve
a
c
c
ur
a
c
y.
H
ow
e
ve
r
,
th
e
pr
im
e
li
m
it
a
ti
on
of
th
e
c
ur
r
e
nt
w
or
k
is
th
a
t
i
t
doe
s
n’
t
a
ddr
e
s
s
th
e
pr
obl
e
m
of
im
pr
ovi
ng
s
of
twa
r
e
qua
li
ty
w
he
r
e
th
e
r
e
is
a
c
ons
id
e
r
a
bl
e
le
s
s
e
r
a
m
ount
of
in
put
s
or
ne
c
e
s
s
a
r
y
gr
ound
tr
ut
h
in
f
o
r
m
a
ti
on.
T
hi
s
l
im
it
a
ti
on c
a
n be
a
ddr
e
s
s
e
d i
n f
ut
ur
e
di
r
e
c
ti
on of
w
or
k w
h
e
r
e
ge
ne
r
a
ti
ve
A
I
m
ode
ll
in
g c
a
n be
c
a
r
r
ie
d out
to
w
a
r
ds
ge
ne
r
a
ti
ng pos
s
ib
le
c
a
s
e
s
of
s
ynt
he
s
iz
e
da
ta
.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
A
ut
hor
s
s
ta
te
no f
undi
ng i
nvol
ve
d.
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
d
iT
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
S
a
nge
e
th
a
G
ovi
nda
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
A
gne
s
N
a
li
ni
V
in
c
e
nt
✓
✓
✓
✓
✓
✓
✓
✓
M
e
r
w
a
R
a
m
e
s
h B
a
bu
✓
✓
✓
✓
✓
✓
✓
C
:
C
onc
e
pt
ua
l
i
z
a
t
i
on
M
:
M
e
t
hodol
ogy
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
da
t
i
on
Fo
:
Fo
r
m
a
l
a
na
l
ys
i
s
I
:
I
nve
s
t
i
ga
t
i
on
R
:
R
e
s
our
c
e
s
D
:
D
a
t
a
C
ur
a
t
i
on
O
:
W
r
i
t
i
ng
-
O
r
i
gi
na
l
D
r
a
f
t
E
:
W
r
i
t
i
ng
-
R
e
vi
e
w
&
E
di
t
i
ng
Vi
:
Vi
s
ua
l
i
z
a
t
i
on
Su
:
Su
pe
r
vi
s
i
on
P
:
P
r
oj
e
c
t
a
dm
i
ni
s
t
r
a
t
i
on
Fu
:
Fu
ndi
ng a
c
qui
s
i
t
i
on
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
A
ut
hor
s
s
ta
te
no c
onf
li
c
t
of
i
nt
e
r
e
s
t.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
da
ta
th
a
t
s
uppor
t
th
e
f
in
di
ngs
of
th
is
s
tu
dy
a
r
e
a
va
il
a
bl
e
f
r
om
th
e
c
or
r
e
s
ponding
a
ut
hor
,
[
S
G
]
,
upon r
e
a
s
ona
bl
e
r
e
que
s
t.
R
E
F
E
R
E
N
C
E
S
[
1]
A
.
A
l
a
m
i
a
nd
O
.
K
r
a
nc
he
r
,
“
H
ow
s
c
r
um
a
dds
va
l
ue
t
o
a
c
hi
e
vi
ng
s
of
t
w
a
r
e
qua
l
i
t
y?
,”
E
m
pi
r
i
c
al
Sof
t
w
ar
e
E
ngi
ne
e
r
i
ng
,
vol
.
27,
no. 7, D
e
c
. 2022, doi
:
10.1007/
s
10664
-
022
-
10208
-
4.
[
2]
P
.
K
a
r
ha
pä
ä
e
t
al
.
,
“
S
t
r
a
t
e
gi
e
s
t
o
m
a
na
ge
qua
l
i
t
y
r
e
qui
r
e
m
e
nt
s
i
n
a
gi
l
e
s
of
t
w
a
r
e
de
ve
l
opm
e
nt
:
a
m
ul
t
i
pl
e
c
a
s
e
s
t
udy,”
E
m
pi
r
i
c
al
Sof
t
w
ar
e
E
ngi
ne
e
r
i
ng
, vol
. 26, no. 2, M
a
r
. 2021, doi
:
10.1007/
s
10664
-
020
-
09903
-
x.
[
3]
L
.
C
ha
z
e
t
t
e
,
W
.
B
r
unot
t
e
,
a
nd
T
.
S
pe
i
t
h,
“
E
xpl
a
i
na
bl
e
s
of
t
w
a
r
e
s
ys
t
e
m
s
:
f
r
om
r
e
qui
r
e
m
e
nt
s
a
na
l
ys
i
s
t
o
s
ys
t
e
m
e
va
l
ua
t
i
on,”
R
e
qui
r
e
m
e
nt
s
E
ngi
ne
e
r
i
ng
, vol
. 27, no. 4, pp. 457
–
487, D
e
c
. 2022, doi
:
10.1007/
s
00766
-
022
-
00393
-
5.
[
4]
L
.
L
a
v
a
z
z
a
,
S
.
M
or
a
s
c
a
,
a
nd
M
.
G
a
t
t
o,
“
A
n
e
m
pi
r
i
c
a
l
s
t
udy
on
s
of
t
w
a
r
e
unde
r
s
t
a
nda
bi
l
i
t
y
a
nd
i
t
s
de
p
e
nde
nc
e
on
c
ode
c
ha
r
a
c
t
e
r
i
s
t
i
c
s
,”
E
m
pi
r
i
c
al
Sof
t
w
a
r
e
E
ngi
ne
e
r
i
ng
, vol
. 28, no. 6, N
ov. 2023, doi
:
10.1007/
s
10664
-
023
-
10396
-
7.
[
5]
M
.
A
ydos
,
Ç
.
A
l
d
a
n,
E
.
C
oş
kun,
a
nd
A
.
S
oyda
n,
“
S
e
c
ur
i
t
y
t
e
s
t
i
ng
of
w
e
b
a
ppl
i
c
a
t
i
ons
:
a
s
ys
t
e
m
a
t
i
c
m
a
ppi
ng
of
t
he
l
i
t
e
r
a
t
ur
e
,”
J
our
nal
of
K
i
ng
Saud
U
ni
v
e
r
s
i
t
y
-
C
om
put
e
r
and
I
nf
or
m
at
i
on
Sc
i
e
nc
e
s
,
vol
.
34,
no.
9,
pp.
6775
–
6792,
O
c
t
.
2022
,
doi
:
10.1016/
j
.j
ks
uc
i
.2021.09.018.
[
6]
P
. O
r
vi
z
F
e
r
ná
nde
z
,
M
. D
a
vi
d,
D
. C
.
D
um
a
, E
.
R
onc
hi
e
r
i
, J
. G
om
e
s
,
a
nd D
.
S
a
l
om
oni
, “
S
of
t
w
a
r
e
qua
l
i
t
y a
s
s
ur
a
nc
e
i
n I
N
D
I
G
O
-
da
t
a
c
l
oud
pr
oj
e
c
t
:
a
c
onve
r
gi
ng
e
vol
ut
i
on
o
f
s
of
t
w
a
r
e
e
ngi
ne
e
r
i
n
g
pr
a
c
t
i
c
e
s
t
o
s
uppor
t
e
u
r
ope
a
n
r
e
s
e
a
r
c
h
e
-
i
nf
r
a
s
t
r
uc
t
ur
e
s
,”
J
our
nal
of
G
r
i
d C
om
put
i
ng
, vol
. 18, no. 1, pp. 81
–
98, M
a
r
. 2020, doi
:
10.1007/
s
10723
-
020
-
09509
-
z.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
N
ov
e
l
ar
ti
fi
c
ia
l
in
te
ll
ig
e
nc
e
-
bas
e
d
e
ns
e
m
bl
e
l
e
ar
ni
ng f
or
opt
imi
z
e
d s
of
tw
a
r
e
quali
ty
…
(
Sange
e
th
a G
o
v
in
da
)
1827
[
7]
M
.
A
.
A
kba
r
,
A
.
A
.
K
ha
n,
S
.
M
a
hm
ood,
a
nd
A
.
M
i
s
hr
a
,
“
S
R
C
M
I
M
M
:
t
he
s
of
t
w
a
r
e
r
e
qui
r
e
m
e
nt
s
c
ha
nge
m
a
na
ge
m
e
nt
a
nd
i
m
pl
e
m
e
nt
a
t
i
on
m
a
t
ur
i
t
y
m
ode
l
i
n
t
he
dom
a
i
n
of
gl
oba
l
s
of
t
w
a
r
e
de
ve
l
o
pm
e
nt
i
ndus
t
r
y,”
I
nf
or
m
at
i
on
T
e
c
hnol
ogy
and
M
anage
m
e
nt
, vol
. 24, no. 3, pp. 195
–
219, S
e
p. 2023, doi
:
10.1007/
s
10799
-
022
-
00364
-
w.
[
8]
L
.
N
e
e
l
u
a
nd
D
.
K
a
vi
t
ha
,
“
E
s
t
i
m
a
t
i
on
of
s
of
t
w
a
r
e
qua
l
i
t
y
pa
r
a
m
e
t
e
r
s
f
or
hybr
i
d
a
gi
l
e
pr
oc
e
s
s
m
ode
l
,”
SN
A
ppl
i
e
d
Sc
i
e
nc
e
s
,
vol
. 3, no. 3, M
a
r
. 2021, doi
:
10.1007/
s
42452
-
021
-
04305
-
0.
[
9]
E
.
R
onc
hi
e
r
i
a
nd
M
.
C
a
na
pa
r
o,
“
A
s
s
e
s
s
i
ng
t
he
i
m
pa
c
t
of
s
of
t
w
a
r
e
qua
l
i
t
y
m
ode
l
s
i
n
he
a
l
t
hc
a
r
e
s
of
t
w
a
r
e
s
ys
t
e
m
s
,”
H
e
al
t
h
Sy
s
t
e
m
s
, vol
. 12, no. 1, pp. 85
–
97, J
a
n. 2023, doi
:
10.1080/
20476965.2022.216
2445.
[
10]
S
.
W
a
i
,
“
S
of
t
w
a
r
e
qua
l
i
t
y
a
nd
b
a
c
kw
a
r
d
c
om
pa
t
i
bi
l
i
t
y
i
n
t
he
vi
d
e
o
ga
m
e
i
ndus
t
r
y,”
J
our
nal
of
I
ndus
t
r
i
al
and
B
us
i
n
e
s
s
E
c
onom
i
c
s
, vol
. 49, no. 3, pp. 545
–
570, S
e
p. 2022, doi
:
10.1007/
s
40812
-
022
-
00224
-
2.
[
11]
M
. S
a
a
da
t
m
a
nd
e
t
al
.
,
“
S
m
a
r
t
D
e
l
t
a
pr
oj
e
c
t
:
a
ut
om
a
t
e
d
qua
l
i
t
y a
s
s
ur
a
nc
e
a
nd
o
pt
i
m
i
z
a
t
i
on a
c
r
os
s
pr
oduc
t
ve
r
s
i
ons
a
nd
va
r
i
a
nt
s
,”
M
i
c
r
opr
oc
e
s
s
or
s
and M
i
c
r
o
s
y
s
t
e
m
s
, vol
. 103, N
ov. 2023, doi
:
10.1016/
j
.m
i
c
pr
o.2023.104967.
[
12]
V
. L
e
na
r
duz
z
i
,
F
. L
om
i
o, S
.
M
or
e
s
c
hi
ni
, D
.
T
a
i
bi
, a
nd D
.
A
. T
a
m
bur
r
i
, “
S
of
t
w
a
r
e
qua
l
i
t
y f
or
A
I
:
w
he
r
e
w
e
a
r
e
no
w
?
,”
Sof
t
w
ar
e
Q
ual
i
t
y
:
F
ut
ur
e
P
e
r
s
pe
c
t
i
v
e
s
on
Sof
t
w
ar
e
E
ngi
ne
e
r
i
ng
Q
ual
i
t
y
,
S
pr
i
nge
r
,
C
ha
m
,
vol
.
404,
pp.
43
–
53,
J
a
n.
2021,
doi
:
10.1007/
978
-
3
-
030
-
65854
-
0_4.
[
13]
F
.
A
l
a
s
w
a
d
a
nd
E
.
P
oova
m
m
a
l
,
“
S
of
t
w
a
r
e
qua
l
i
t
y
pr
e
di
c
t
i
on
us
i
ng
m
a
c
hi
ne
l
e
a
r
ni
ng,”
M
at
e
r
i
al
s
T
oday
:
P
r
oc
e
e
di
ngs
,
vol
.
62,
pp. 4714
–
4720, 2022, doi
:
10.1016/
j
.m
a
t
pr
.2022.03.165.
[
14]
A
.
K
ha
n,
R
.
R
.
M
e
kur
i
a
,
a
nd
R
.
I
s
a
e
v,
“
A
ppl
yi
ng
m
a
c
hi
ne
l
e
a
r
ni
ng
a
na
l
y
s
i
s
f
or
s
of
t
w
a
r
e
qua
l
i
t
y
t
e
s
t
,”
i
n
2023
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on C
ode
Q
ual
i
t
y
(
I
C
C
Q
)
, pp. 1
–
15
,
A
pr
. 2023,
doi
:
10.1109/
I
C
C
Q
57276.2023.10114664.
[
15]
F
.
A
.
B
a
t
a
r
s
e
h,
L
.
F
r
e
e
m
a
n,
a
nd
C
.
-
H
.
H
ua
ng,
“
A
s
ur
ve
y
on
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
nc
e
a
s
s
ur
a
nc
e
,”
J
our
nal
of
B
i
g
D
at
a
,
vol
.
8,
no. 1, D
e
c
. 2021, doi
:
10.1186/
s
40537
-
021
-
00445
-
7.
[
16]
B
.
G
e
z
i
c
i
a
nd
A
.
K
.
T
a
r
ha
n,
“
S
ys
t
e
m
a
t
i
c
l
i
t
e
r
a
t
ur
e
r
e
vi
e
w
on
s
of
t
w
a
r
e
qua
l
i
t
y
f
or
A
I
-
ba
s
e
d
s
of
t
w
a
r
e
,”
E
m
pi
r
i
c
al
Sof
t
w
a
r
e
E
ngi
ne
e
r
i
ng
, vol
. 27, no. 3, M
a
y 2022, doi
:
10.1007/
s
10664
-
021
-
10105
-
2.
[
17]
K
.
S
.
C
he
ng,
P
.
-
C
.
H
u
a
ng,
T
.
-
H
.
A
hn,
a
nd
M
.
S
ong,
“
T
ool
s
uppor
t
f
or
i
m
pr
ovi
ng
s
of
t
w
a
r
e
qua
l
i
t
y
i
n
m
a
c
hi
ne
l
e
a
r
ni
ng
pr
ogr
a
m
s
,”
I
nf
or
m
at
i
on
, vol
. 14, no. 1, J
a
n. 2023, doi
:
10.3390/
i
nf
o14010053.
[
18]
V
.
S
a
kl
a
m
a
e
va
a
nd
L
.
P
a
vl
i
č
,
“
T
he
pot
e
nt
i
a
l
o
f
A
I
-
d
r
i
ve
n
a
s
s
i
s
t
a
nt
s
i
n
s
c
a
l
e
d
a
gi
l
e
s
of
t
w
a
r
e
de
ve
l
opm
e
nt
,”
A
ppl
i
e
d
Sc
i
e
nc
e
s
,
vol
. 14, no. 1, D
e
c
. 2023, doi
:
10.3390/
a
pp14010319.
[
19]
P
.
K
okol
,
“
S
of
t
w
a
r
e
qua
l
i
t
y:
how
m
uc
h
doe
s
i
t
m
a
t
t
e
r
?
,”
E
l
e
c
t
r
oni
c
s
,
vol
.
11,
no.
16,
A
ug.
2022,
doi
:
10.3390/
e
l
e
c
t
r
oni
c
s
11162485.
[
20]
A
.
B
.
-
G
onz
á
l
e
z
e
t
al
.
,
“
T
he
r
ol
e
of
A
I
i
n
dr
ug
di
s
c
ove
r
y:
c
ha
l
l
e
nge
s
,
oppor
t
uni
t
i
e
s
,
a
nd
s
t
r
a
t
e
gi
e
s
,”
P
har
m
ac
e
ut
i
c
al
s
,
vol
. 16, no. 6, J
un. 2023, doi
:
10.3390/
ph16060891.
[
21]
J
.
S
i
e
be
r
t
e
t
al
.
,
“
C
ons
t
r
uc
t
i
on
of
a
qua
l
i
t
y
m
ode
l
f
or
m
a
c
hi
ne
l
e
a
r
ni
ng
s
ys
t
e
m
s
,”
Sof
t
w
ar
e
Q
ual
i
t
y
J
our
nal
,
vol
.
30,
no.
2,
pp. 307
–
335, J
un. 2022, doi
:
10.1007/
s
11219
-
021
-
09557
-
y.
[
22]
A
.
S
t
oc
c
o
e
t
al
.
,
“
S
of
t
w
a
r
e
t
e
s
t
i
ng
i
n
t
he
m
a
c
hi
ne
l
e
a
r
ni
ng
e
r
a
:
s
pe
c
i
a
l
i
s
s
ue
of
t
he
e
m
pi
r
i
c
a
l
s
of
t
w
a
r
e
e
ngi
ne
e
r
i
ng
(
E
M
S
E
)
j
our
na
l
,”
E
m
pi
r
i
c
al
Sof
t
w
ar
e
E
ngi
ne
e
r
i
ng
, vol
. 28, no. 3, M
a
y 2023, doi
:
10.10
07/
s
10664
-
023
-
10326
-
7.
[
23]
S
.
C
ho,
I
.
K
i
m
,
J
.
K
i
m
,
H
.
W
oo,
a
nd
W
.
S
hi
n,
“
A
m
a
t
ur
i
t
y
m
ode
l
f
or
t
r
us
t
w
or
t
hy
A
I
s
of
t
w
a
r
e
de
ve
l
opm
e
nt
,”
A
ppl
i
e
d
Sc
i
e
nc
e
s
,
vol
. 13, no. 8, A
pr
. 2023, doi
:
10.3390/
a
pp13084771.
[
24]
M
.
B
oukhl
i
f
,
M
.
H
a
ni
ne
,
a
nd
N
.
K
ha
r
m
oum
,
“
A
de
c
a
de
of
i
nt
e
l
l
i
ge
nt
s
of
t
w
a
r
e
t
e
s
t
i
ng
r
e
s
e
a
r
c
h:
a
bi
bl
i
om
e
t
r
i
c
a
na
l
ys
i
s
,”
E
l
e
c
t
r
oni
c
s
, vol
. 12, no. 9, M
a
y 2023, doi
:
10.3390/
e
l
e
c
t
r
oni
c
s
12092109.
[
25]
M
.
B
a
r
e
nka
m
p,
J
.
R
e
bs
t
a
dt
,
a
nd
O
.
T
hom
a
s
,
“
A
ppl
i
c
a
t
i
ons
of
A
I
i
n
c
l
a
s
s
i
c
a
l
s
of
t
w
a
r
e
e
ngi
ne
e
r
i
ng,”
A
I
P
e
r
s
pe
c
t
i
v
e
s
,
vol
.
2,
no. 1, D
e
c
. 2020, doi
:
10.1186/
s
42467
-
020
-
00005
-
4.
[
26]
A
. A
l
i
, N
. K
ha
n, M
. A
bu
-
T
a
i
r
,
J
. N
oppe
n, S
. M
c
C
l
e
a
n, a
n
d I
. M
c
C
he
s
ne
y, “
D
i
s
c
r
i
m
i
na
t
i
n
g f
e
a
t
ur
e
s
-
ba
s
e
d c
os
t
-
s
e
ns
i
t
i
ve
a
pp
r
oa
c
h
f
or
s
o
f
t
w
a
r
e
de
f
e
c
t
p
r
e
di
c
t
i
on
,”
A
ut
om
a
t
e
d
So
f
t
w
ar
e
E
ngi
ne
e
r
i
ng
,
v
ol
.
2
8,
no.
11
,
pp.
1
-
1
8,
J
ul
.
2021,
doi
:
10.1
007/
s
1
0515
-
021
-
00289
-
8.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Dr.
Sangeetha
Govinda
a
n
esteemed
faculty
member
in
the
Department
of
Computer
Scienc
e
at
Christ
(Dee
med
to
be
Univer
sity),
Centra
l
Ca
mpus,
Bangal
ore,
India,
holds
a
Ph
.
D
.
degree
from
Bharathiar
University,
Coimbatore.
W
ith
an
extensive
car
eer
spanning
over
19
years,
she
has
made
significant
contributions
to
teaching,
researc
h,
and
adminis
tration,
shaping
education
al
methodo
logies
across
undergra
duate
and
postgrad
uate
levels.
Her
scholarly
endeavors
are
underscored
by
the
publicatio
n
of
6
national
and
12
internationa
l
resear
ch
papers
in
prestigious
journals
indexed
in
IE
EE,
WoS,
and
S
copus.
Beyond
academia,
she
actively
serves
as
a
board
of
examination
(BO
E)
member
for
esteemed
institutions
such
as
Bengaluru
City
University,
Bangalore
Univers
ity,
and
Mount
Carmel
College.
Additional
ly,
she
contribut
es
her
experti
se
as
a
member
of
t
he
review
committee
for
ASTES
journal.
Her
diverse
research
interests
encompass
data
mining
,
IoT,
softwar
e
engineerin
g,
cryptograp
hy,
computer
networks
,
R
basics
,
and
IT
for
Business.
Her
dedication
to
academic
excellence
extends
beyond
research,
as
evid
enced
by
her
numerous
invited
talks,
guest
lectures,
international
and
national
conference
participatio
n,
and
organization
of
workshops,
seminars,
and
faculty
development
programs
(FDPs
).
Recogniz
ed
for
he
r
outstanding
contributions,
she
was
honored
as
a
Microsoft
res
earch
fellow
in
2014.
Further
more,
she
has
rece
ived a
cclai
m
for
her
innovat
ive
work,
includ
ing
an
Austra
lian
Patent
(No.
2021103341)
granted
for
eight
years
from
June
15,
2021,
on
August
4,
2021,
for
he
r
groundbreaking
project
titled
"
A
rtificial
intellig
ence
based
automati
c
detection
of
infection
rate
of
COVID
-
19."
Her
remarkable
journey
exemplifies
her
unwavering
dedication
to
advancing
education
and
research
in
the
field
of
computer
science,
le
aving
an
indelib
le
mar
k
on both academia and society.
She ca
n be c
ontact
ed
at email
: sangeet
ha.g@
christun
iversit
y.in
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
14
, N
o.
3
,
J
une
20
25
:
1820
-
1828
1828
Agnes
Nalini
Vincent
is
the
Dean
of
Faculty
of
Information
Te
chnology
and
Head
of
Teaching
and
L
earning
at
AMITY
Institute
of
Higher
Educa
tion
(AIHE),
Mauritius.
She
holds
a
master'
s
in
engineering
degree
from
Anna
University,
Chennai,
India
and
is
currently
pursuin
g
her
Ph
.
D
.
in
the
field
of
artificial
intell
igence
.
With
over
17+
years
of
experience
in
teaching,
research
and
adminis
tration,
she
has
been
inst
rumental
in
framing
the
pedagogies
from
undergraduate
to
post
graduate
studies.
She
has
bee
n
the
pioneer
to
develop
curriculum
in
big
data
analytics,
internet
of
things
and
d
ata
science
s
and
launched
them
as
courses
in
Mauriti
us.
She
has
publis
hed
national
and
internati
onal
res
earch
papers
in
journals
indexed
in
IEEE,
and
Scopus.
As
a
faculty,
she
has
been
offering
a
wealth
of
talent
in
the
development
and
implementation
of
educational
technology
tools
and
applications
in
the
classroom
.
Her
area
of
inter
ests
includes
artificial
intell
igence,
data
mi
ning,
big
data
analytics
,
internet
of
things,
compute
r
networks,
and
business
data
analytics
.
Sh
e
has
deeply
inv
ested
in
achieving
her
tenure
through
administrative
service
contributions
a
nd
an
accomplishment
-
oriented
approach
to
teaching.
She
has
given
more
than
10+
invited
talks,
12+
guest
lectures,
has
conducted
1
International
conference,
has
organized
5+
nat
ional
and
internationa
l
workshops.
Her
contribution
to
quality
standards
formulation
and
t
o
development
of
credit
system
in
the
capacity
of
head
of
teaching
and
learning
at
AIHE
is
r
emarkable.
Her
sterling
track
record
of
academic
excellence
and
visionary
leadership
brings
a
we
alth
of
knowledge,
experience,
and
insigh
t
to
the
forefront
of
the
ICT
field.
Through
her
unique
and
people
-
centric
approach
towards
adminis
tration
and
management
,
she
has
always
fostered
a
supportive
and
collaborative
environment
that
enables
each
member
o
f
the
team
to
reach
their
full pot
ential.
She ca
n be c
ontact
ed at
email:
vanalini@
mauritius.amity.edu
.
Merwa
Ramesh
Babu
is
the
research
scholar
in
Bharathiar
University,
Coimbatore
,
Tamil
Nadu,
India.
He
holds
a
master'
s
in
computer
a
pplications
degree
from
Bangalor
e
Universi
ty,
Bangalor
e,
India
and
is
curre
ntly
pursuing
h
is
Ph
.
D
.
in
the
field
of
internet
of
things
(IoT).
With
over
13+
years
of
experience
in
teaching,
research
and
adminis
tration,
he has been instrumental in framing the peda
gogies from undergraduate to post
graduate
studies.
He
has
been
the
pioneer
to
develop
curricu
lum
in
object
-
oriented
programming
using
java,
internet
of
things
and
data
sciences
and
laun
c
hed
them
as
courses
i
n
various
institutions.
He
has
published
national
and
international
research
papers
in
journals
indexed
in
IEEE,
and
Scopus.
As
a
r
esear
ch
schol
ar,
he
has
been
off
er
ing
a
wea
lth
of
talen
t
i
n
the
dev
elopm
ent
and
i
mplem
entat
ion
o
f
edu
catio
nal
t
echn
ology
tools
and
ap
plica
tions
in
t
he
resear
ch
f
ield.
Hi
s
a
rea
of
inte
rests
in
clude
s
a
rtifi
cial
int
ellig
ence
,
data
mi
ning,
bi
g
da
ta
analyti
cs,
i
ntern
et
of
things
,
mob
ile
ap
plica
tion
devel
opmen
t,
an
d
o
op'
s
using
java
.
He
ha
s
attende
d more t
han 10+
in
vited t
alks,
12+
guest
lectu
res, 1
i
ntern
ation
al
confere
nce, 2+
na
tiona
l
and
int
ernat
ional
wor
kshops
. He
can
be co
ntact
ed at
ema
il: m
erwar
ame
sh@
gmail
.com
.
Evaluation Warning : The document was created with Spire.PDF for Python.