I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
5
,
Octo
b
er
20
25
,
p
p
.
4
8
0
3
~
4
8
1
2
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
8
0
3
-
4
8
1
2
4803
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Enha
ncing
so
ft
wa
re f
a
ult
predi
ctio
n using
wrappe
r
-
ba
sed
metah
euristi
c f
ea
ture
sel
ection m
et
ho
ds
H
a
T
hi M
in
h P
hu
o
ng
,
Da
ng
T
hi K
im
Ng
a
n
,
Da
o
K
ha
nh
Duy
,
Ng
uy
en
T
ha
nh
B
in
h
Th
e
U
n
i
v
e
r
si
t
y
of
D
a
n
a
n
g
,
V
i
e
t
n
a
m
-
K
o
r
e
a
U
n
i
v
e
r
s
i
t
y
of
I
n
f
o
r
m
a
t
i
o
n
a
n
d
C
o
mm
u
n
i
c
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
D
a
n
a
n
g
,
V
i
e
t
n
a
m
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
6
,
2
0
2
5
R
ev
is
ed
J
u
l 1
8
,
2
0
2
5
Acc
ep
ted
Au
g
1
,
2
0
2
5
Th
e
a
p
p
li
c
a
ti
o
n
of
so
ftwa
re
f
a
u
lt
p
re
d
icti
o
n
(S
F
P
)
to
p
re
d
i
c
t
fa
u
lt
y
c
o
m
p
o
n
e
n
ts
a
t
th
e
e
a
rly
sta
g
e
h
a
s
b
e
e
n
in
v
e
stig
a
ted
in
v
a
rio
u
s
stu
d
ies
.
Re
d
u
c
in
g
fe
a
tu
re
re
d
u
n
d
a
n
c
y
is
k
e
y
to
e
n
h
a
n
c
i
n
g
t
h
e
p
re
d
ictiv
e
a
c
c
u
ra
c
y
o
f
S
F
P
m
o
d
e
ls.
F
e
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
s
a
re
u
ti
l
ize
d
t
o
se
lec
t
a
n
d
re
tain
t
h
e
fe
a
tu
re
s th
a
t
c
o
n
tri
b
u
te t
h
e
m
o
st
i
n
fo
rm
a
ti
o
n
wh
il
e
e
li
m
in
a
ti
n
g
ir
r
e
lev
a
n
t
or
re
d
u
n
d
a
n
t
fe
a
tu
re
s
f
r
o
m
so
ftwa
re
fa
u
lt
d
a
tas
e
ts.
Ho
we
v
e
r,
fe
a
tu
re
se
lec
ti
o
n
(F
S
)
in
t
h
e
field
of
SFP
re
m
a
in
s
a
b
ro
a
d
a
n
d
c
o
n
t
in
u
o
u
sly
e
v
o
l
v
in
g
field
,
e
n
c
o
m
p
a
ss
in
g
a
d
i
v
e
rse
ra
n
g
e
o
f
tec
h
n
iq
u
e
s
a
n
d
m
e
th
o
d
o
l
o
g
ies
.
In
t
h
is
wo
rk
,
we
stu
d
y
a
n
d
p
e
rfo
rm
e
m
p
iri
c
a
l
e
v
a
lu
a
ti
o
n
o
f
ten
wr
a
p
p
e
r
F
S
m
e
th
o
d
s,
n
a
m
e
ly
a
rti
ficia
l
b
u
tt
e
rfly
o
p
ti
m
iza
ti
o
n
(ABO
)
,
a
to
m
se
a
rc
h
o
p
ti
m
iza
ti
o
n
(ASO)
,
e
q
u
il
ib
ri
u
m
o
p
ti
m
ize
r
(EO)
,
H
e
n
r
y
g
a
s
so
lu
b
il
it
y
o
p
ti
m
iza
ti
o
n
(HG
S
O)
,
p
o
o
r
a
n
d
ri
c
h
o
p
ti
m
iza
ti
o
n
(
P
RO)
,
g
e
n
e
ra
li
z
e
d
n
o
rm
a
l
d
istri
b
u
ti
o
n
o
p
ti
m
iza
ti
o
n
(G
ND
O)
,
slim
e
m
o
l
d
a
l
g
o
ri
th
m
,
H
a
rris
h
a
wk
’s
o
p
ti
m
iza
ti
o
n
,
p
a
th
fi
n
d
e
r
a
lg
o
ri
th
m
(P
F
A)
a
n
d
m
a
n
ta
ra
y
fo
ra
g
in
g
o
p
ti
m
iza
ti
o
n
fo
r
re
so
l
v
i
n
g
t
h
e
d
a
ta
re
d
u
n
d
a
n
c
y
issu
e
i
n
S
F
P
d
a
tas
e
ts.
Ex
p
e
rime
n
tal
re
su
lt
s
o
n
n
i
n
e
fa
u
l
t
d
a
tas
e
ts
fro
m
th
e
P
ROMIS
E
a
n
d
AEEE
M
re
p
o
sito
r
ies
sh
o
w
th
a
t
th
e
EO
a
c
h
iev
e
s
th
e
b
e
st
p
e
rfo
rm
a
n
c
e
,
wit
h
P
RO
a
n
d
HG
S
O
ra
n
k
in
g
n
e
x
t.
T
h
e
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
re
v
e
a
led
t
h
a
t
ten
wra
p
p
e
r
-
b
a
se
d
F
S
m
e
th
o
d
s
d
e
m
o
n
stra
ted
a
su
b
sta
n
ti
a
l
imp
ro
v
e
m
e
n
t
in
h
a
n
d
li
n
g
d
a
ta
re
d
u
n
d
a
n
c
y
issu
e
s fo
r
S
F
P
.
K
ey
w
o
r
d
s
:
Data
s
ets
Featu
r
e
s
elec
tio
n
m
eth
o
d
s
Ma
ch
in
e
lear
n
in
g
So
f
twar
e
f
au
lt p
r
e
d
ictio
n
W
r
ap
p
er
-
b
ased
f
ea
t
u
r
e
s
elec
tio
n
m
eth
o
d
s
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ng
u
y
en
T
h
an
h
B
in
h
T
h
e
Un
iv
er
s
ity
of
Dan
a
n
g
,
Vie
tn
am
-
Ko
r
ea
Un
iv
e
r
s
ity
of
I
n
f
o
r
m
atio
n
a
n
d
C
o
m
m
u
n
icatio
n
T
ec
h
n
o
lo
g
y
4
7
0
T
r
an
Dai
Ng
h
ia,
N
g
u
Han
h
So
n
Dis
tr
ict,
Dan
an
g
5
5
0
0
0
,
Vietn
am
E
m
ail:
n
tb
in
h
@
v
k
u
.
u
d
n
.
v
n
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
f
ea
tu
r
e
s
elec
tio
n
is
to
ex
tr
ac
t
a
s
u
b
s
et
o
f
r
elev
an
t
f
ea
t
u
r
es
f
r
o
m
th
e
o
r
ig
in
a
l
s
et,
aim
in
g
to
r
ed
u
ce
d
im
en
s
io
n
ality
with
o
u
t
co
m
p
r
o
m
is
in
g
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
Featu
r
e
s
elec
tio
n
m
eth
o
d
s
ar
e
ty
p
ically
ca
teg
o
r
ized
in
to
th
r
ee
ty
p
es: f
ilter
-
b
as
ed
,
wr
ap
p
er
-
b
ased
,
an
d
h
y
b
r
id
ap
p
r
o
ac
h
es.
Fil
ter
-
b
ased
tech
n
iq
u
es
r
an
k
f
ea
t
u
r
e
s
ac
co
r
d
in
g
to
s
p
ec
if
ic
cr
iter
ia
an
d
d
is
ca
r
d
t
h
o
s
e
th
at
d
o
n
o
t
m
ee
t
a
p
r
ed
e
f
in
ed
th
r
esh
o
ld
[
1
]
.
W
r
ap
p
er
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
(
FS
)
tech
n
i
q
u
es
u
tili
ze
class
if
icatio
n
m
o
d
els
to
ev
alu
ate
th
e
ef
f
ec
tiv
en
ess
o
f
f
ea
tu
r
e
s
u
b
s
ets,
o
f
ten
r
esu
ltin
g
in
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
co
m
p
ar
e
d
to
f
ilter
-
b
ased
m
eth
o
d
s
[
2
]
.
Hy
b
r
id
ap
p
r
o
ac
h
es
co
m
b
in
e
th
e
ad
v
a
n
tag
es
o
f
b
o
th
f
i
lter
an
d
wr
ap
p
er
m
eth
o
d
s
to
ac
h
iev
e
a
b
alan
c
e
b
etwe
en
co
m
p
u
tatio
n
al
e
f
f
icie
n
cy
an
d
p
r
ed
ictiv
e
ac
c
u
r
ac
y
[
3
]
.
Prio
r
r
esear
ch
h
as
s
h
o
w
n
t
h
at
wr
ap
p
e
r
-
b
ased
ap
p
r
o
ac
h
es
g
en
er
ally
o
u
t
p
er
f
o
r
m
f
ilter
-
b
ased
tech
n
i
q
u
es
[
4
]
.
Nev
er
th
eless
,
a
lar
g
e
n
u
m
b
er
o
f
m
etah
e
u
r
is
tic
v
ar
ian
ts
r
em
ain
u
n
d
e
r
ex
p
lo
r
e
d
in
th
e
co
n
tex
t
o
f
f
ea
tu
r
e
s
el
ec
tio
n
.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
p
r
esen
ts
an
em
p
ir
ical
ev
alu
atio
n
o
f
m
etah
e
u
r
is
tic
alg
o
r
ith
m
s
with
in
wr
ap
p
er
-
b
a
s
ed
FS
m
eth
o
d
s
to
r
ed
u
ce
d
ata
r
ed
u
n
d
a
n
cy
in
co
m
m
o
n
s
o
f
twar
e
f
au
lt
p
r
ed
ictio
n
(
SFP
)
d
atasets
,
with
th
e
g
o
al
o
f
im
p
r
o
v
in
g
m
o
d
e
l
ef
f
icien
cy
wh
ile
p
r
eser
v
in
g
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
.
Sp
ec
if
ically
,
we
in
v
esti
g
ate
a
r
an
g
e
o
f
wr
ap
p
er
-
b
ased
FS
tech
n
iq
u
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
8
0
3
-
4
8
1
2
4804
ap
p
lied
to
s
o
f
twar
e
f
au
lt
d
ata
s
ets,
in
clu
d
in
g
ar
tific
ial
b
u
tter
f
l
y
o
p
tim
izatio
n
(
AB
O)
,
ato
m
s
ea
r
ch
o
p
tim
izatio
n
(
ASO)
,
eq
u
ilib
r
iu
m
o
p
tim
izer
(
E
O)
,
Hen
r
y
g
as
s
o
lu
b
ilit
y
o
p
tim
izatio
n
(
HGSO)
,
p
o
o
r
a
n
d
r
ich
o
p
tim
izatio
n
(
PR
O)
,
g
en
er
alize
d
n
o
r
m
al
d
is
tr
ib
u
tio
n
o
p
tim
izatio
n
(
G
NDO)
,
s
lim
e
m
o
u
l
d
alg
o
r
it
h
m
,
Har
r
is
h
awk
’
s
o
p
tim
izatio
n
,
p
at
h
f
in
d
e
r
alg
o
r
ith
m
(
PF
A)
,
an
d
Ma
n
ta
R
ay
Fo
r
ag
in
g
Op
tim
izatio
n
.
Sp
ec
if
i
ca
lly
,
th
e
p
r
o
p
o
s
ed
wr
ap
p
er
-
b
ased
FS
m
eth
o
d
s
ar
e
ev
alu
ated
ag
ai
n
s
t
a
b
aselin
e
th
at
ap
p
lies
lear
n
in
g
alg
o
r
ith
m
s
d
ir
ec
tly
to
th
e
o
r
ig
in
al
s
o
f
twar
e
f
au
lt
d
atasets
.
E
x
p
er
im
en
ts
wer
e
co
n
d
u
ct
ed
o
n
n
in
e
d
atasets
d
er
iv
ed
f
r
o
m
PR
OM
I
SE
an
d
AE
E
E
M
r
ep
o
s
ito
r
ies.
T
o
ass
ess
clas
s
if
icatio
n
p
er
f
o
r
m
an
c
e,
we
em
p
lo
y
ed
t
h
r
ee
lear
n
in
g
m
o
d
els:
r
an
d
o
m
f
o
r
est,
ex
tr
a
tr
ee
s
,
a
n
d
Ad
aBo
o
s
t.
E
v
alu
atio
n
m
etr
ics
in
clu
d
ed
p
r
ec
is
io
n
,
r
ec
all
,
F1
-
s
co
r
e,
an
d
a
r
e
a
u
n
d
e
r
t
h
e
c
u
r
v
e
(
AUC
)
.
To
d
eter
m
in
e
th
e
s
tati
s
tical
s
ig
n
if
ican
ce
o
f
p
e
r
f
o
r
m
a
n
ce
d
if
f
er
e
n
ce
s
b
etwe
en
th
e
ten
wr
ap
p
er
-
b
ased
FS
tech
n
iq
u
es
an
d
th
e
b
aselin
e,
th
e
W
ilco
x
o
n
s
ig
n
e
d
-
r
an
k
test
was
p
er
f
o
r
m
e
d
at
a
0
.
0
5
s
ig
n
if
ican
ce
lev
el.
E
ac
h
e
x
p
er
im
e
n
t
was
r
e
p
ea
ted
ten
tim
es
to
en
s
u
r
e
r
eliab
ilit
y
,
p
r
o
d
u
cin
g
ten
u
n
iq
u
e
t
est
s
ets.
T
h
e
r
esu
lts
in
d
icate
th
at
th
e
wr
ap
p
e
r
-
b
ase
d
m
eth
o
d
s
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
th
e
b
aselin
e.
Am
o
n
g
th
e
m
,
th
e
EO
ac
h
iev
e
d
th
e
b
est
o
v
e
r
all
p
er
f
o
r
m
a
n
ce
,
f
o
llo
wed
b
y
PR
O
an
d
HGSO
.
T
h
is
s
tu
d
y
s
p
ec
if
ically
ad
d
r
ess
es
th
e
f
o
llo
win
g
r
esear
ch
q
u
e
s
tio
n
s
:
a.
Ho
w
ef
f
ec
tiv
e
ar
e
th
e
a
p
p
lie
d
FS
tech
n
iq
u
es
in
en
h
an
cin
g
SFP
b
y
f
ilter
in
g
o
u
t
ir
r
elev
a
n
t
o
r
r
e
d
u
n
d
an
t
s
o
f
twar
e
m
etr
ics?
b.
W
h
ich
wr
ap
p
er
-
b
ased
FS
m
eth
o
d
p
e
r
f
o
r
m
s
b
est f
o
r
s
elec
tin
g
th
e
o
p
tim
al
f
ea
tu
r
es f
o
r
SF
P?
T
h
e
s
tr
u
ctu
r
e
o
f
th
e
p
ap
er
is
o
r
g
an
ized
as.
Sectio
n
2
r
ev
ie
ws
th
e
r
elate
d
liter
atu
r
e,
wh
ile
s
ec
tio
n
3
o
u
tlin
es
th
e
r
esear
c
h
m
eth
o
d
o
lo
g
y
.
Sectio
n
4
p
r
esen
ts
an
d
d
is
cu
s
s
e
s
th
e
ex
p
er
im
en
tal
f
in
d
in
g
s
,
an
d
s
ec
tio
n
5
h
ig
h
lig
h
ts
th
e
m
ain
co
n
clu
s
io
n
s
an
d
r
ec
o
m
m
en
d
atio
n
s
.
2.
RE
L
AT
E
D
WO
RK
A
h
y
b
r
i
d
FS
m
et
h
o
d
was
i
n
t
r
o
d
u
ce
d
b
y
An
ju
et
a
l
.
[
5
]
.
T
h
is
s
tu
d
y
p
r
o
p
o
s
e
d
a
m
et
h
o
d
t
h
a
t
co
m
b
i
n
es
q
u
a
n
t
u
m
p
ar
tic
le
s
w
a
r
m
o
p
tim
i
za
t
i
o
n
(
QP
SO)
a
n
d
p
r
in
cip
al
c
o
m
p
o
n
e
n
t
an
al
y
s
is
(
PC
A)
.
T
h
e
r
esu
lts
d
e
m
o
n
s
tr
ate
t
h
at
t
h
e
p
r
o
p
o
s
ed
m
o
d
el,
e
m
p
l
o
y
in
g
a
n
a
r
t
if
ici
al
n
e
u
r
al
n
etw
o
r
k
(
ANN
)
class
if
i
er
,
ac
h
ie
v
ed
h
ig
h
er
ac
c
u
r
a
cy
a
n
d
p
r
ec
is
i
o
n
c
o
m
p
a
r
e
d
to
e
x
is
ti
n
g
a
p
p
r
o
ac
h
es
.
T
h
e
a
u
t
h
o
r
s
f
u
r
t
h
e
r
s
u
g
g
es
t
t
h
a
t
th
es
e
f
i
n
d
i
n
g
s
h
o
ld
s
ig
n
i
f
ic
a
n
t
i
m
p
li
ca
t
io
n
s
f
o
r
b
o
t
h
ac
a
d
em
i
a
an
d
th
e
s
o
f
tw
ar
e
i
n
d
u
s
t
r
y
.
Ac
c
o
r
d
i
n
g
t
o
Ali
et
a
l
.
[
6
]
,
m
et
ah
e
u
r
is
tic
ap
p
r
o
ac
h
es
wit
h
i
n
wr
a
p
p
er
-
b
a
s
ed
FS
m
et
h
o
d
s
o
u
t
p
er
f
o
r
m
e
d
tr
ad
iti
o
n
al
te
c
h
n
iq
u
es
s
u
c
h
a
s
B
est
Fi
r
s
t
Se
ar
ch
an
d
G
r
e
ed
y
St
ep
wis
e
S
ea
r
c
h
.
S
o
m
e
e
x
a
m
p
les
o
f
th
ese
a
l
g
o
r
i
th
m
s
i
n
c
lu
d
e
:
w
h
al
e
o
p
t
i
m
iz
ati
o
n
al
g
o
r
it
h
m
(
W
OA
)
[
7
]
,
g
e
n
e
tic
al
g
o
r
i
th
m
(
GA
)
[
8
]
a
n
d
p
ar
ticl
e
s
wa
r
m
o
p
ti
m
iz
ati
o
n
(
PS
O)
[
8
]
ar
e
p
o
p
u
la
r
m
eta
h
eu
r
is
tic
alg
o
r
it
h
m
s
u
s
e
d
f
o
r
FS
i
n
SF
P.
Ali
et
a
l
.
[
6
]
e
m
p
h
asiz
ed
t
h
at
r
em
o
v
i
n
g
ir
r
e
le
v
a
n
t
o
r
r
ed
u
n
d
an
t
f
ea
t
u
r
es
m
a
y
b
r
in
g
b
ett
er
p
r
ed
icti
v
e
p
e
r
f
o
r
m
an
ce
.
H
o
w
ev
er
,
in
c
o
r
r
e
ct
F
S
o
r
o
m
itti
n
g
im
p
o
r
ta
n
t
f
e
at
u
r
es
c
an
le
ad
t
o
a
d
e
cli
n
e
in
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
T
h
er
ef
o
r
e,
a
n
a
ly
zi
n
g
a
n
d
ev
al
u
a
ti
n
g
d
i
f
f
e
r
e
n
t
FS
m
et
h
o
d
s
is
ess
e
n
ti
al
to
i
d
e
n
ti
f
y
th
e
m
o
s
t
e
f
f
e
cti
v
e
a
p
p
r
o
a
c
h
f
o
r
s
o
f
twa
r
e
d
e
f
e
ct
p
r
e
d
ic
ti
o
n
.
B
al
o
g
u
n
et
a
l.
[
9
]
p
r
o
p
o
s
e
d
a
h
y
b
r
id
FS
m
e
th
o
d
th
at
co
m
b
i
n
es
m
u
lt
ip
le
f
i
lte
r
te
ch
n
iq
u
es
wit
h
a
w
r
a
p
p
e
r
ap
p
r
o
ac
h
u
s
i
n
g
r
a
n
k
a
g
g
r
e
g
ati
o
n
.
B
y
co
m
b
i
n
i
n
g
f
ilt
er
a
n
d
wr
a
p
p
e
r
tec
h
n
i
q
u
es
,
t
h
is
a
p
p
r
o
a
ch
ai
m
s
t
o
b
o
o
s
t
t
h
e
e
f
f
ic
a
cy
o
f
SF
P
m
o
d
els
.
I
t
was
s
h
o
w
n
t
h
r
o
u
g
h
th
ei
r
ex
p
e
r
i
m
e
n
ts
t
h
a
t
t
h
e
p
r
o
p
o
s
e
d
m
et
h
o
d
o
lo
g
y
c
o
n
s
id
e
r
a
b
l
y
e
n
h
an
ce
d
t
h
e
p
r
ed
ict
iv
e
p
er
f
o
r
m
a
n
c
e
o
f
SF
P
m
o
d
els
.
Sh
a
h
an
d
Das
[
1
0
]
i
n
v
esti
g
a
t
ed
th
e
ef
f
e
cti
v
en
ess
o
f
PS
O
f
o
r
F
S
i
n
co
n
j
u
n
ct
io
n
wit
h
k
-
n
ea
r
es
t
n
ei
g
h
b
o
r
s
(k
-
N
N)
,
n
a
i
v
e
B
a
y
es
a
n
d
d
ec
is
io
n
t
r
e
e
c
lass
i
f
i
er
s
.
T
h
ei
r
e
x
p
e
r
i
m
e
n
ta
l
r
es
u
lts
d
em
o
n
s
t
r
at
e
t
h
at
i
n
te
g
r
at
in
g
PS
O
wit
h
t
h
ese
cl
ass
i
f
ie
r
s
e
n
h
a
n
ce
s
p
r
e
d
i
cti
v
e
p
e
r
f
o
r
m
a
n
c
e
ac
r
o
s
s
m
u
lt
ip
le
d
at
asets
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
3
.
1
.
E
x
perim
ent
a
l
d
esig
n
Fig
u
r
e
1
i
n
d
ic
ates
t
h
e
m
ai
n
s
t
e
p
s
o
f
o
u
r
m
et
h
o
d
o
l
o
g
y
.
A
f
t
er
s
p
li
tti
n
g
t
h
e
d
a
ta
i
n
t
o
tr
ai
n
i
n
g
a
n
d
tes
ti
n
g
p
a
r
ts
,
we
f
i
lle
d
i
n
m
is
s
i
n
g
v
al
u
es
an
d
n
o
r
m
a
liz
ed
th
e
d
at
a.
Su
b
s
e
q
u
e
n
tl
y
,
te
n
FS
t
ec
h
n
i
q
u
es
b
ase
d
o
n
wr
ap
p
er
s
tr
a
te
g
ies
we
r
e
e
m
p
lo
y
ed
to
i
d
en
t
if
y
th
e
m
o
s
t
r
ele
v
an
t
s
et
o
f
f
e
at
u
r
es.
S
p
ec
i
f
i
ca
l
ly
,
w
e
u
til
i
ze
d
a
n
o
p
e
n
-
s
o
u
r
ce
to
o
l
k
it
,
wr
a
p
p
er
-
f
e
at
u
r
e
-
s
ele
ct
io
n
-
to
o
l
b
o
x
,
w
h
i
ch
i
m
p
le
m
e
n
t
s
o
v
er
4
0
d
i
f
f
er
e
n
t
wr
a
p
p
er
m
eth
o
d
s
.
Fi
n
all
y
,
w
e
u
ti
liz
ed
t
h
r
e
e
ML
cl
ass
i
f
ie
r
s
,
n
am
e
ly
r
a
n
d
o
m
f
o
r
est
,
e
x
t
r
a
t
r
e
e
s
,
a
n
d
A
d
aBo
o
s
t
.
p
r
e
cisi
o
n
,
r
ec
a
ll,
F
1
-
s
c
o
r
e,
a
n
d
AUC a
r
e
t
h
e
m
et
r
i
cs
u
s
e
d
t
o
d
ete
r
m
in
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
s
e
le
cte
d
wr
a
p
p
er
-
d
r
i
v
e
n
ap
p
r
o
a
ch
es.
3
.
2
.
Wra
pp
er
-
ba
s
ed
f
ea
t
ure
s
elec
t
io
n t
ec
hn
iq
ues
T
h
er
e
ar
e
v
ar
io
u
s
wr
ap
p
e
r
-
b
a
s
ed
FS
m
eth
o
d
s
th
at
h
av
e
b
e
en
ap
p
lied
in
s
o
f
twar
e
f
au
lt
p
r
ed
ictio
n
,
in
clu
d
in
g
b
in
ar
y
g
en
etic
alg
o
r
ith
m
(
B
GA)
,
b
in
ar
y
p
ar
ticl
e
s
war
m
o
p
tim
izatio
n
(
B
PS
O)
,
an
d
b
i
n
ar
y
a
n
t
co
lo
n
y
o
p
tim
izatio
n
(
B
AC
O)
[
1
1
]
.
W
e
co
n
s
id
er
th
e
f
o
llo
win
g
wr
ap
p
e
r
-
b
ased
FS
ap
p
r
o
ac
h
es
in
th
is
s
tu
d
y
.
AB
O,
in
s
p
ir
ed
b
y
b
u
tter
f
ly
b
eh
av
io
r
,
was
p
r
o
p
o
s
ed
b
y
Qi
et
a
l.
[
1
2
]
.
T
h
is
alg
o
r
ith
m
is
b
ased
o
n
th
e
p
r
ef
er
en
ce
o
f
s
p
ec
k
led
wo
o
d
s
,
wh
ich
s
ee
k
o
u
t
war
m
s
u
n
s
p
o
ts
in
wo
o
d
s
an
d
ar
ea
s
.
ASO
was
in
tr
o
d
u
ce
d
b
y
Z
h
ao
et
a
l.
[
1
3
]
f
o
r
s
o
lv
in
g
o
p
tim
izatio
n
ch
allen
g
es.
Z
h
a
o
et
a
l.
[
1
3
]
d
em
o
n
s
tr
ated
th
at
ASO
o
u
tp
er
f
o
r
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
s
o
ftw
a
r
e
fa
u
lt p
r
ed
ictio
n
u
s
in
g
w
r
a
p
p
er
-
b
a
s
ed
m
eta
h
eu
r
is
tic
…
(
Ha
Th
i Min
h
P
h
u
o
n
g
)
4805
m
an
y
class
ic
an
d
em
e
r
g
in
g
a
lg
o
r
ith
m
s
in
b
e
n
ch
m
ar
k
test
s
an
d
th
ey
h
a
v
e
s
h
o
w
n
th
at
A
SO
is
a
p
r
o
m
is
in
g
s
o
lu
tio
n
f
o
r
r
ea
l
-
wo
r
ld
en
g
in
ee
r
in
g
p
r
o
b
lem
s
.
T
h
e
E
O,
p
r
o
p
o
s
ed
b
y
Far
am
ar
zi
et
a
l.
[
1
4
]
,
is
a
p
h
y
s
ics
-
in
s
p
ir
ed
alg
o
r
ith
m
t
h
at
r
eg
u
l
ates
th
e
v
o
lu
m
e
m
ass
b
alan
ce
m
o
d
el
to
d
eter
m
i
n
e
d
y
n
am
ic
an
d
eq
u
ilib
r
iu
m
s
tates.
T
h
is
m
ec
h
an
is
m
en
ab
l
es
E
O
to
ef
f
ec
tiv
ely
b
alan
ce
ex
p
lo
r
atio
n
a
n
d
ex
p
lo
itatio
n
d
u
r
i
n
g
t
h
e
s
ea
r
ch
p
r
o
ce
s
s
.
Similar
ly
,
th
e
HGSO
alg
o
r
ith
m
[
1
5
]
,
g
r
o
u
n
d
ed
i
n
Hen
r
y
’
s
law
[
1
6
]
,
s
o
lv
es
c
o
m
p
lex
o
p
tim
izatio
n
task
s
b
y
s
im
u
latin
g
g
as
m
o
lec
u
le
clu
s
ter
in
g
,
wh
ich
h
elp
s
m
a
in
tain
ex
p
l
o
r
atio
n
-
e
x
p
lo
itatio
n
b
alan
ce
an
d
av
o
id
p
r
em
atu
r
e
co
n
v
er
g
en
ce
.
T
h
e
PR
O
a
lg
o
r
ith
m
,
p
r
o
p
o
s
ed
b
y
Mo
o
s
av
i
an
d
B
ar
d
s
ir
i
[
1
7
]
,
is
in
s
p
ir
ed
b
y
th
e
f
in
an
cial
b
eh
av
i
o
r
o
f
in
d
iv
id
u
als
with
in
s
o
ciety
,
m
o
d
eled
th
r
o
u
g
h
th
e
in
ter
ac
tio
n
b
et
wee
n
wea
lth
ier
an
d
p
o
o
r
er
g
r
o
u
p
s
s
tr
iv
in
g
to
im
p
r
o
v
e
t
h
eir
s
tatu
s
.
T
h
e
g
e
n
er
alize
d
n
o
r
m
al
d
is
tr
ib
u
tio
n
o
p
tim
izatio
n
(
GNDO
)
alg
o
r
ith
m
,
in
t
r
o
d
u
ce
d
b
y
Z
h
a
n
g
et
a
l.
[
1
8
]
,
o
p
er
ates
in
th
r
e
e
s
tag
es:
in
itial
s
o
lu
tio
n
d
is
p
er
s
io
n
,
co
n
v
er
g
e
n
ce
to
war
d
th
e
o
p
tim
al
r
e
g
io
n
,
an
d
r
ef
i
n
em
en
t,
u
s
in
g
m
u
ltip
le
n
o
r
m
al
d
is
tr
ib
u
tio
n
s
wit
h
g
r
a
d
u
ally
r
e
d
u
ce
d
v
ar
ian
ce
.
th
e
s
lim
e
m
o
ld
al
g
o
r
ith
m
(
SMA)
,
d
e
v
elo
p
e
d
b
y
L
i
et
a
l.
[
1
9
]
,
is
b
ased
o
n
th
e
f
o
r
ag
in
g
b
eh
a
v
io
r
o
f
Ph
y
s
ar
u
m
p
o
l
y
ce
p
h
alu
m
,
wh
i
ch
id
en
tifie
s
o
p
tim
al
p
ath
s
to
f
o
o
d
s
o
u
r
ce
s
with
o
u
t
a
ce
n
tr
al
n
er
v
o
u
s
s
y
s
tem
.
Har
r
is
h
awk
s
o
p
tim
izatio
n
(
HHO)
,
in
tr
o
d
u
ce
d
b
y
Heid
ar
i
et
a
l.
[
2
0
]
,
s
im
u
lates
th
e
c
o
o
p
er
ativ
e
h
u
n
tin
g
s
tr
ateg
y
o
f
Har
r
is
h
awk
s
.
T
h
e
alg
o
r
ith
m
b
eg
in
s
b
y
r
a
n
d
o
m
l
y
in
itializin
g
h
awk
a
g
en
ts
ac
r
o
s
s
th
e
s
ea
r
ch
s
p
ac
e
an
d
g
u
id
es
th
em
th
r
o
u
g
h
e
x
p
l
o
r
atio
n
a
n
d
ex
p
l
o
itatio
n
p
h
ases
.
T
h
e
PF
A,
p
r
o
p
o
s
ed
b
y
Ya
p
ici
an
d
C
etin
k
ay
a
[
2
1
]
,
is
a
m
etah
eu
r
is
tic
m
eth
o
d
th
at
s
im
u
lates
th
e
c
o
llectiv
e
f
o
r
ag
in
g
b
eh
av
io
r
o
f
a
n
i
m
al
g
r
o
u
p
s
,
w
h
er
e
in
d
iv
id
u
als
f
o
llo
w
a
lea
d
er
w
h
ile
r
ely
in
g
o
n
th
eir
o
wn
p
e
r
c
ep
tio
n
to
ex
p
lo
r
e
th
e
s
ea
r
ch
s
p
ac
e.
T
h
e
m
a
n
ta
r
ay
f
o
r
ag
in
g
o
p
tim
izatio
n
(
MRF
O)
alg
o
r
ith
m
,
in
tr
o
d
u
ce
d
b
y
Z
h
ao
et
a
l.
[
2
2
]
,
is
in
s
p
ir
ed
b
y
t
h
e
u
n
iq
u
e
f
o
r
ag
in
g
s
tr
ateg
ies
o
f
m
a
n
ta
r
a
y
s
,
wh
ic
h
s
ea
r
ch
lar
g
e
ar
ea
s
a
n
d
d
y
n
a
m
ically
ad
ju
s
t
th
ei
r
p
o
s
itio
n
s
t
o
war
d
r
eg
io
n
s
with
g
r
ea
ter
r
eso
u
r
ce
av
ailab
ilit
y
.
Fig
u
r
e
1
.
T
h
e
m
ain
s
tep
s
of
th
e
e
v
a
l
u
a
t
i
o
n
3
.
3
.
Da
t
a
s
et
I
n
th
is
s
tu
d
y
,
we
o
b
tain
ed
n
in
e
d
atasets
f
r
o
m
th
e
PR
OM
I
SE
an
d
AE
E
E
M
r
ep
o
s
ito
r
ies,
b
o
t
h
o
f
wh
ic
h
ar
e
wid
ely
r
ec
o
g
n
ize
d
an
d
f
r
eq
u
e
n
tly
u
tili
ze
d
in
SF
P
r
esear
ch
.
T
h
ese
d
atasets
co
m
p
r
is
e
in
d
ep
en
d
e
n
t
v
ar
iab
les,
s
u
ch
as
lin
es
o
f
co
d
e
(
L
OC
o
d
e)
an
d
lin
es
o
f
co
m
m
en
ts
(
L
OC
o
m
m
en
t)
,
alo
n
g
with
a
d
ep
e
n
d
en
t
v
ar
iab
le
in
d
i
ca
tin
g
th
e
s
tatu
s
o
f
a
s
o
f
twar
e
c
o
m
p
o
n
en
t,
clas
s
if
y
in
g
it
as
eith
er
f
a
u
lty
o
r
n
o
n
-
f
au
lt
y
.
A
n
o
tab
le
ch
ar
ac
ter
is
tic
o
f
th
e
d
ataset
is
th
e
p
r
ed
o
m
in
an
ce
o
f
n
o
n
-
f
a
u
lty
s
am
p
les
o
v
er
f
au
lty
o
n
es,
w
h
ich
in
tr
o
d
u
ce
s
an
im
b
alan
ce
d
d
ata
p
r
o
b
lem
.
T
h
e
d
etails ar
e
p
r
esen
ted
in
T
ab
le
1
.
T
ab
le
1.
T
h
e
d
atasets
u
s
ed
in
t
h
e
s
t
u
d
y
D
a
t
a
s
e
t
P
r
o
j
e
c
t
s
I
n
st
a
n
c
e
s
F
a
u
l
t
y
i
n
s
t
a
n
c
e
s
N
o
n
-
f
a
u
l
t
y
i
n
st
a
n
c
e
s
F
a
u
l
t
y
r
a
t
i
o
(
%)
C
M
1
P
R
O
M
I
S
E
5
0
5
48
4
5
7
9
.
5
0
K
C
1
P
R
O
M
I
S
E
2
1
0
7
3
2
5
1
7
8
2
1
5
.
4
2
K
C
2
P
R
O
M
I
S
E
5
2
2
1
0
7
4
1
5
2
0
.
5
0
P
C
1
P
R
O
M
I
S
E
1
1
0
7
76
1
0
3
1
6
.
8
7
EQ
A
EEEM
3
2
4
1
2
9
1
9
5
3
9
.
8
1
JD
T
A
EEEM
9
9
7
1
0
5
8
9
2
1
0
.
5
3
Lu
c
e
n
e
A
EEEM
6
9
1
64
6
2
7
9
.
2
6
M
y
l
y
n
A
EEEM
1
8
6
2
2
4
5
1
6
1
7
1
3
.
1
6
P
D
E
A
EEEM
1
4
9
7
2
0
9
1
2
8
8
1
3
.
9
6
3
.
4
.
E
v
a
lua
t
i
o
n
m
ea
s
ures
Du
r
in
g
th
e
f
a
u
lt
p
r
e
d
ictio
n
m
o
d
el
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
,
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
m
etr
ics
ar
e
ap
p
lied
to
s
y
s
tem
atica
lly
as
s
es
s
th
e
ef
f
ec
tiv
en
ess
of
th
e
m
o
d
els
an
d
id
en
tify
th
e
m
o
s
t
ap
p
r
o
p
r
iate
one
f
o
r
a
g
iv
en
d
ataset.
I
n
th
is
s
tu
d
y
,
we
a
d
o
p
t p
r
ec
is
io
n
(
P),
r
ec
all
(
R
)
,
F1
-
s
co
r
e
(
F1
)
a
n
d
AUC as e
v
alu
atio
n
m
ea
s
u
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
8
0
3
-
4
8
1
2
4806
3
.
5
.
M
a
chine
lea
rning
t
ec
hn
iqu
es
R
an
d
o
m
f
o
r
est
[
2
3
]
r
ep
r
esen
ts
a
s
u
p
er
v
is
ed
lear
n
in
g
ap
p
r
o
ac
h
p
r
im
a
r
ily
u
s
ed
f
o
r
r
eg
r
ess
io
n
an
d
class
if
icatio
n
task
s
.
I
t
o
p
er
ates
by
co
m
b
in
in
g
m
u
ltip
le
d
ec
i
s
io
n
tr
ee
s
,
with
th
e
f
in
al
p
r
ed
ictio
n
b
ased
on
th
e
ag
g
r
eg
ated
r
esu
lts
o
f
th
ese
tr
ee
s
.
R
an
d
o
m
f
o
r
est
is
k
n
o
wn
f
o
r
its
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
a
n
d
its
r
esis
tan
ce
to
o
v
er
f
itti
n
g
.
A
d
aBo
o
s
t
[
2
4
]
is
a
well
-
k
n
o
wn
B
o
o
s
tin
g
alg
o
r
ith
m
d
esig
n
e
d
to
en
h
an
ce
weak
class
if
ier
s
by
iter
ativ
ely
cr
ea
ti
n
g
n
ew
m
o
d
els
an
d
a
d
ju
s
tin
g
th
eir
weig
h
ts
.
It
o
p
er
ates
by
s
eq
u
en
tially
tr
ain
in
g
m
u
ltip
le
weak
class
if
ier
s
,
w
ith
ea
ch
n
ew
m
o
d
el
p
r
io
r
itizin
g
t
h
e
co
r
r
ec
tio
n
of
er
r
o
r
s
m
ad
e
by
its
p
r
ed
ec
ess
o
r
s
.
ET
[
2
5
]
is
a
v
a
r
ian
t
of
r
an
d
o
m
f
o
r
est
th
at
s
elec
ts
attr
ib
u
tes
r
a
n
d
o
m
ly
f
o
r
class
if
icatio
n
r
at
h
e
r
th
an
ch
o
o
s
in
g
th
e
o
p
tim
al
o
n
e,
as
r
an
d
o
m
f
o
r
est
d
o
es.
T
h
is
ap
p
r
o
ac
h
en
h
a
n
ce
s
tr
ain
in
g
s
p
ee
d
an
d
r
ed
u
ce
s
o
v
er
f
itti
n
g
;
h
o
wev
e
r
,
in
s
o
m
e
ca
s
es,
it m
ay
r
esu
lt in
lo
wer
ac
cu
r
ac
y
.
4.
R
E
S
UL
T
S
A
ND
D
I
S
CU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
ex
p
e
r
i
m
en
tal
f
i
n
d
in
g
s
to
s
y
s
tem
ati
ca
lly
ad
d
r
ess
th
e
two
a
f
o
r
e
m
en
tio
n
ed
r
esear
ch
q
u
esti
o
n
s
.
4
.
1
.
Resea
rc
h
q
ues
t
io
n
1
:
How
ef
f
ec
t
iv
e
a
re
t
he
presente
d
f
ea
t
ure
s
elec
t
io
n
m
et
ho
ds
f
o
r
re
du
ci
ng
t
he
irre
lev
a
nt/r
edun
da
nt
m
et
rics f
o
r
SFP
?
To
an
s
wer
r
esear
ch
q
u
esti
o
n
1,
we
p
er
f
o
r
m
v
a
r
io
u
s
ex
p
er
im
en
ts
to
co
m
p
ar
e
ten
FS
ap
p
r
o
a
ch
es
u
s
in
g
th
r
ee
ML
class
if
ier
s
d
escr
ib
ed
in
s
ec
tio
n
3
.
5
.
I
n
T
ab
les
2
an
d
3,
th
e
b
est
ex
p
er
im
en
tal
r
esu
lts
ar
e
h
ig
h
lig
h
ted
in
b
o
ld
.
a.
R
an
d
o
m
f
o
r
est
r
esu
lts
:
T
ab
le
2
s
h
o
ws
th
at,
am
o
n
g
all
ev
al
u
ated
FS
m
eth
o
d
s
,
th
e
co
m
b
i
n
a
tio
n
o
f
E
O
an
d
r
an
d
o
m
f
o
r
est
ac
h
iev
ed
t
h
e
h
ig
h
est
av
er
ag
e
p
er
f
o
r
m
an
ce
a
cr
o
s
s
all
m
etr
ics,
with
PR
O
r
an
k
in
g
s
ec
o
n
d
.
No
tab
ly
,
E
O
ac
h
iev
ed
th
e
h
i
g
h
est
av
er
ag
e
v
alu
es
ac
r
o
s
s
all
ev
alu
atio
n
m
etr
ics,
with
p
r
ec
is
io
n
o
f
0
.
6
9
,
r
ec
all
o
f
0
.
8
3
,
AUC
o
f
0
.
7
6
a
n
d
F1
-
s
co
r
e
o
f
0
.
8
7
.
PR
O
ac
h
iev
ed
th
e
s
ec
o
n
d
-
h
ig
h
est
p
er
f
o
r
m
an
ce
m
etr
ics,
with
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e
an
d
AUC
v
alu
es
of
0
.
6
8
,
0
.
8
4
,
0
.
7
6
an
d
0
.
8
4
,
r
esp
ec
tiv
ely
.
T
h
e
an
aly
s
is
r
esu
lts
d
em
o
n
s
tr
ate
th
at
EO
an
d
PR
O
ac
h
iev
ed
c
o
m
p
a
r
ativ
ely
s
u
p
er
i
o
r
p
e
r
f
o
r
m
an
ce
w
h
en
u
s
ed
as
FS
m
eth
o
d
s
f
o
r
th
e
R
an
d
o
m
Fo
r
e
s
t c
lass
if
ier
,
o
u
tp
er
f
o
r
m
in
g
th
e
o
th
er
FS
ev
alu
ated
i
n
th
is
s
tu
d
y
.
T
ab
le
2
.
T
h
e
p
er
f
o
r
m
a
n
ce
of
th
e
wr
ap
p
er
-
b
ased
FS
m
eth
o
d
s
wh
en
ap
p
lie
d
with
th
e
RF
m
o
d
el
an
d
th
e
Ad
aBo
o
s
t m
o
d
e
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
s
o
ftw
a
r
e
fa
u
lt p
r
ed
ictio
n
u
s
in
g
w
r
a
p
p
er
-
b
a
s
ed
m
eta
h
eu
r
is
tic
…
(
Ha
Th
i Min
h
P
h
u
o
n
g
)
4807
b.
A
d
a
B
o
o
s
t
r
es
u
l
ts
:
T
h
e
r
es
u
l
ts
s
u
m
m
a
r
i
z
e
d
i
n
T
a
b
l
e
2
r
e
v
e
al
t
h
a
t
t
h
e
H
GS
O
c
o
n
s
is
t
e
n
t
l
y
y
ie
l
d
e
d
t
h
e
h
i
g
h
e
s
t
p
r
e
c
i
s
i
o
n
a
n
d
A
UC
v
a
l
u
es
i
n
th
e
m
a
j
o
r
i
t
y
o
f
t
h
e
e
x
p
e
r
i
m
e
n
t
al
d
a
t
as
e
ts
.
S
p
ec
i
f
i
c
al
l
y
,
o
n
t
h
e
K
C
1
,
KC
2
,
PC
1
,
E
Q
,
a
n
d
L
u
c
e
n
e
d
a
t
a
s
et
s
,
t
h
e
h
i
g
h
e
s
t
AU
C
v
al
u
e
s
we
r
e
r
e
c
o
r
d
e
d
i
n
H
G
S
O
w
i
t
h
0
.
8
0
,
0
.
8
2
,
0
.
8
9
,
0
.
9
2
a
n
d
0
.
8
8
,
r
e
s
p
e
c
t
i
v
e
l
y
.
I
n
a
d
d
i
t
i
o
n
,
E
O
o
b
t
a
i
n
e
d
t
h
e
g
r
e
a
t
es
t
v
a
lu
e
s
o
n
r
e
c
a
l
l
v
a
l
u
es
o
n
m
o
s
t
o
f
t
h
e
d
a
t
a
s
e
ts
.
F
i
n
a
l
l
y
,
E
O
a
c
h
i
e
v
e
d
t
h
e
g
r
ea
t
e
s
t
a
v
e
r
a
g
e
r
e
c
a
ll
a
n
d
F
1
-
s
co
r
e
v
a
l
u
e
s
o
f
0
.
8
2
a
n
d
0
.
7
3
,
w
h
e
r
e
a
s
H
GSO
d
e
m
o
n
s
t
r
a
t
e
d
s
u
p
e
r
i
o
r
a
v
e
r
a
g
e
p
r
e
c
i
s
i
o
n
a
n
d
AU
C
w
i
t
h
v
a
l
u
es
o
f
0
.
6
4
a
n
d
0
.
8
1
,
r
e
s
p
e
c
t
i
v
e
l
y
.
c.
ET
r
esu
lts
:
I
t
ca
n
b
e
o
b
s
er
v
e
d
in
T
ab
le
3,
E
O
ac
h
iev
e
d
s
u
p
er
io
r
r
ec
all,
F1
-
s
co
r
e,
a
n
d
A
UC
co
m
p
ar
ed
to
th
e
o
th
er
wr
ap
p
e
r
-
b
ased
FS
m
eth
o
d
s
f
o
r
th
e
C
M1
,
KC
1
,
KC
2
an
d
PC
1
d
ataset
s
.
AS
O
o
b
tain
ed
th
e
h
ig
h
est
p
r
ec
is
io
n
o
n
th
e
E
Q,
J
DT
an
d
L
u
ce
n
e
d
atasets
,
with
v
alu
es
o
f
0
.
8
2
,
0
.
7
3
an
d
0
.
7
4
,
r
esp
ec
tiv
ely
.
Fo
r
th
e
EQ
d
ataset,
EO
h
ig
h
lig
h
ted
b
etter
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
th
an
all
o
th
er
FS
m
o
d
els
with
th
e
g
r
ea
test
r
ec
all
an
d
AUC
v
alu
e
s
o
f
0
.
9
6
an
d
0
.
8
6
.
Fo
r
t
h
e
E
Q
d
ataset,
E
O
d
em
o
n
s
tr
ated
b
etter
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
all
o
th
er
FS
m
o
d
els,
ac
h
iev
in
g
th
e
h
ig
h
est
r
ec
all
an
d
AUC
v
alu
es
o
f
0
.
9
6
an
d
0
.
8
6
,
r
esp
ec
tiv
ely
.
Ag
ain
,
f
o
r
th
e
av
er
ag
e
v
alu
es
o
f
r
ec
all,
F1
-
s
co
r
e
an
d
AUC,
E
O
o
u
tp
er
f
o
r
m
ed
all
o
th
er
FS
m
o
d
els
in
ter
m
s
o
f
r
ec
all,
F1
-
s
co
r
e
a
n
d
AUC
v
alu
es,
with
0
.
7
7
,
0
.
7
0
an
d
0
.
8
4
,
w
h
ile
th
e
h
ig
h
est
av
er
ag
e
p
r
ec
is
io
n
v
alu
e
was r
e
co
r
d
ed
i
n
ASO
m
eth
o
d
,
with
a
v
alu
e
o
f
0
.
6
7
.
T
ab
le
3.
T
h
e
p
er
f
o
r
m
a
n
ce
of
t
h
e
wr
ap
p
er
-
b
ased
FS
m
eth
o
d
s
wh
en
ap
p
lied
with
th
e
ET
m
o
d
e
l
D
a
t
a
s
e
t
M
e
t
r
i
c
s
B
a
s
e
l
i
n
e
A
B
O
A
S
O
EO
H
G
S
O
P
R
O
G
N
D
O
S
M
A
HHO
PFA
M
R
F
O
C
M
1
P
0
.
5
5
0
.
5
5
0
.
5
9
0
.
6
1
0
.
5
4
0
.
4
7
0
.
6
0
.
5
5
0
.
4
9
0
.
6
1
0
.
4
8
R
0
.
7
1
0
.
7
1
0
.
6
6
0
.
9
6
0
.
7
0
0
.
4
5
0
.
7
1
0
.
7
1
0
.
4
6
0
.
9
6
0
.
4
5
F1
0
.
6
2
0
.
6
2
0
.
6
3
0
.
7
5
0
.
6
1
0
.
4
6
0
.
6
5
0
.
6
2
0
.
4
7
0
.
7
5
0
.
4
7
AUC
0
.
8
5
0
.
8
5
0
.
8
0
0
.
8
6
0
.
8
1
0
.
7
0
0
.
7
5
0
.
4
7
0
.
5
4
0
.
7
7
0
.
6
6
K
C
1
P
0
.
6
5
0
.
6
5
0
.
6
2
0
.
6
6
0
.
6
4
0
.
6
2
0
.
6
4
0
.
5
6
0
.
6
4
0
.
6
3
0
.
6
2
R
0
.
7
0
0
.
7
0
0
.
6
8
0
.
7
5
0
.
6
9
0
.
7
0
0
.
6
9
0
.
6
9
0
.
7
0
0
.
6
7
0
.
7
0
F1
0
.
6
7
0
.
6
7
0
.
6
5
0
.
7
0
0
.
6
6
0
.
6
6
0
.
6
7
0
.
6
2
0
.
6
7
0
.
6
5
0
.
6
6
AUC
0
.
8
1
0
.
8
1
0
.
7
9
0
.
8
1
0
.
7
8
0
.
8
0
0
.
8
2
0
.
8
1
0
.
8
1
0
.
8
1
0
.
7
9
K
C
2
P
0
.
7
0
0
.
7
0
0
.
7
0
0
.
7
2
0
.
6
4
0
.
7
1
0
.
5
6
0
.
6
5
0
.
6
5
0
.
7
2
0
.
7
8
R
0
.
7
5
0
.
7
5
0
.
7
3
0
.
7
5
0
.
6
9
0
.
8
0
0
.
5
9
0
.
6
7
0
.
6
5
0
.
7
5
0
.
8
1
F1
0
.
7
3
0
.
7
3
0
.
7
1
0
.
7
3
0
.
6
6
0
.
7
5
0
.
5
8
0
.
6
6
0
.
6
5
0
.
7
3
0
.
8
0
AUC
0
.
8
6
0
.
8
6
0
.
8
1
0
.
8
3
0
.
7
8
0
.
8
3
0
.
5
8
0
.
6
2
0
.
7
8
0
.
8
2
0
.
8
9
P
C
1
P
0
.
5
2
0
.
5
6
0
.
6
3
0
.
6
9
0
.
6
6
0
.
6
2
0
.
5
9
0
.
6
3
0
.
5
1
0
.
6
2
0
.
6
6
R
0
.
5
5
0
.
8
0
0
.
7
6
0
.
7
8
0
.
7
5
0
.
7
2
0
.
6
6
0
.
7
6
0
.
5
2
0
.
7
2
0
.
7
9
F1
0
.
5
3
0
.
6
6
0
.
6
9
0
.
7
3
0
.
7
0
0
.
6
7
0
.
6
2
0
.
6
9
0
.
5
2
0
.
6
7
0
.
7
2
AUC
0
.
6
0
0
.
7
8
0
.
8
2
0
.
9
4
0
.
8
7
0
.
8
5
0
.
8
3
0
.
7
4
0
.
6
4
0
.
8
2
0
.
8
8
EQ
P
0
.
7
7
0
.
7
7
0
.
8
2
0
.
6
1
0
.
6
8
0
.
7
2
0
.
7
7
0
.
6
7
0
.
8
1
0
.
8
1
0
.
6
8
R
0
.
7
6
0
.
7
6
0
.
8
1
0
.
9
6
0
.
6
7
0
.
7
2
0
.
7
7
0
.
6
9
0
.
8
0
.
8
0
.
6
9
F1
0
.
7
7
0
.
7
7
0
.
8
2
0
.
7
5
0
.
6
8
0
.
7
2
0
.
7
7
0
.
6
8
0
.
8
1
0
.
8
0
.
6
8
AUC
0
.
8
3
0
.
8
3
0
.
8
4
0
.
8
6
0
.
8
3
0
.
8
0
0
.
8
4
0
.
7
3
0
.
8
9
0
.
8
4
0
.
8
3
J
D
T
P
0
.
7
8
0
.
7
3
0
.
7
3
0
.
7
2
0
.
7
3
0
.
7
5
0
.
7
2
0
.
7
5
0
.
6
9
0
.
7
3
0
.
6
9
R
0
.
8
2
0
.
8
6
0
.
8
0
0
.
8
1
0
.
8
2
0
.
7
8
0
.
7
7
0
.
7
8
0
.
7
7
0
.
8
4
0
.
7
7
F1
0
.
8
0
0
.
7
9
0
.
7
7
0
.
7
6
0
.
7
7
0
.
7
6
0
.
7
4
0
.
7
6
0
.
7
3
0
.
7
8
0
.
7
3
AUC
0
.
8
7
0
.
8
6
0
.
8
8
0
.
8
7
0
.
8
9
0
.
9
0
0
.
8
3
0
.
8
3
0
.
8
7
0
.
8
8
0
.
7
9
L
u
c
e
n
e
P
0
.
5
6
0
.
5
8
0
.
7
4
0
.
6
5
0
.
5
7
0
.
6
1
0
.
6
5
0
.
6
1
0
.
6
8
0
.
6
4
0
.
7
2
R
0
.
6
3
0
.
9
6
0
.
8
1
0
.
6
9
0
.
7
1
0
.
7
6
0
.
7
2
0
.
6
8
0
.
7
0
.
6
7
0
.
6
9
F1
0
.
5
9
0
.
7
3
0
.
7
7
0
.
6
7
0
.
6
3
0
.
6
8
0
.
6
8
0
.
6
4
0
.
6
9
0
.
6
6
0
.
7
0
AUC
0
.
5
5
0
.
8
4
0
.
7
9
0
.
8
4
0
.
7
1
0
.
6
3
0
.
8
3
0
.
7
1
0
.
6
4
0
.
8
1
0
.
8
3
M
y
l
y
n
P
0
.
5
5
0
.
6
0
0
.
6
1
0
.
5
3
0
.
5
2
0
.
5
6
0
.
6
1
0
.
5
6
0
.
6
1
0
.
6
1
0
.
6
0
R
0
.
6
3
0
.
7
1
0
.
7
1
0
.
5
9
0
.
5
5
0
.
6
3
0
.
7
0
.
7
7
0
.
7
2
0
.
7
1
0
.
7
1
F1
0
.
5
9
0
.
6
5
0
.
6
6
0
.
5
6
0
.
5
3
0
.
5
9
0
.
6
5
0
.
6
5
0
.
6
6
0
.
6
6
0
.
6
5
AUC
0
.
5
4
0
.
7
9
0
.
8
5
0
.
8
0
0
.
7
6
0
.
7
4
0
.
8
2
0
.
6
8
0
.
8
3
0
.
8
5
0
.
8
1
P
D
E
P
0
.
5
7
0
.
6
0
0
.
5
8
0
.
5
7
0
.
5
6
0
.
6
0
0
.
6
1
0
.
5
8
0
.
5
9
0
.
5
9
0
.
6
2
R
0
.
6
1
0
.
7
7
0
.
7
1
0
.
6
2
0
.
8
0
0
.
6
8
0
.
7
8
0
.
6
9
0
.
7
8
0
.
7
5
0
.
7
4
F1
0
.
5
9
0
.
6
7
0
.
6
4
0
.
6
0
0
.
6
6
0
.
6
4
0
.
6
9
0
.
6
3
0
.
6
7
0
.
6
6
0
.
6
7
AUC
0
.
6
0
0
.
7
6
0
.
7
7
0
.
7
3
0
.
7
9
0
.
7
5
0
.
7
7
0
.
6
7
0
.
7
6
0
.
7
4
0
.
7
6
A
v
e
r
a
g
e
v
a
l
u
e
s
P
0
.
6
3
0
.
6
4
0
.
6
7
0
.
6
4
0
.
6
2
0
.
6
3
0
.
6
4
0
.
6
2
0
.
6
3
0
.
6
6
0
.
6
5
R
0
.
6
8
0
.
7
8
0
.
7
4
0
.
7
7
0
.
7
1
0
.
6
9
0
.
7
1
0
.
7
2
0
.
6
8
0
.
7
6
0
.
7
1
F1
0
.
6
5
0
.
7
0
0
.
7
0
0
.
7
0
0
.
6
6
0
.
6
6
0
.
6
7
0
.
6
6
0
.
6
5
0
.
7
1
0
.
6
8
AUC
0
.
7
2
0
.
8
2
0
.
8
2
0
.
8
4
0
.
8
0
0
.
7
8
0
.
7
9
0
.
7
0
0
.
7
5
0
.
8
2
0
.
8
0
4
.
2
.
Resea
rc
h
qu
estio
n
2
:
w
hich
wra
pp
er
-
ba
s
ed
f
ea
t
ure
s
elec
t
io
n
m
et
ho
d
perf
o
r
m
s
bes
t
f
o
r
s
elec
t
ing
t
he
o
ptim
a
l f
e
a
t
ures f
o
r
SFP
?
Fig
u
r
e
2
(
a
)
-
(
i)
in
A
p
p
en
d
ix
,
p
r
esen
ts
th
e
AUC
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
wr
ap
p
e
r
-
b
ased
FS
m
eth
o
d
s
.
T
h
e
x
-
a
x
is
in
d
icate
s
th
e
n
am
es
o
f
th
e
FS
alg
o
r
ith
m
s
,
wh
ile
th
e
y
-
ax
is
s
h
o
ws
th
eir
co
r
r
esp
o
n
d
in
g
AUC
s
co
r
es.
Acc
o
r
d
in
g
to
t
h
e
ch
ar
t,
E
O
an
d
PR
O
co
n
s
is
ten
tly
d
eliv
er
ed
s
u
p
e
r
io
r
r
esu
lts
ac
r
o
s
s
s
ev
er
al
d
atasets
.
Sp
ec
if
ically
,
E
O
atta
in
ed
to
p
AUC
s
co
r
es
o
f
0
.
7
8
,
0
.
9
0
,
0
.
8
4
,
a
n
d
0
.
7
5
o
n
KC
1
,
E
Q,
L
u
ce
n
e,
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
8
0
3
-
4
8
1
2
4808
PDE,
r
esp
ec
tiv
ely
.
Similar
ly
,
PR
O
ac
h
iev
ed
n
o
tab
le
AUC
v
alu
es
o
f
0
.
8
8
,
0
.
9
3
,
an
d
0
.
8
6
o
n
PC
1
,
E
Q,
an
d
J
DT
.
T
o
f
u
r
th
e
r
a
n
aly
ze
o
v
er
all
p
er
f
o
r
m
an
ce
,
th
e
av
er
a
g
e
AUC
ac
r
o
s
s
d
if
f
er
en
t
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
was
co
m
p
u
ted
.
All
ev
alu
ate
d
FS
m
eth
o
d
s
ac
h
iev
ed
m
ea
n
AUC
v
alu
es
ab
o
v
e
0
.
6
5
.
A
m
o
n
g
t
h
em
,
E
O
in
co
m
b
in
atio
n
with
r
an
d
o
m
f
o
r
est
y
ield
ed
th
e
h
ig
h
est
av
er
ag
e
s
co
r
e
o
f
0
.
8
7
,
f
o
llo
wed
cl
o
s
ely
b
y
PR
O
with
r
an
d
o
m
f
o
r
est
at
0
.
8
4
.
On
th
e
o
th
er
h
an
d
,
SMA
co
u
p
led
wi
th
E
T
o
b
tain
ed
th
e
lo
west
av
er
ag
e
AUC,
with
a
s
co
r
e
o
f
0
.
6
5
.
T
h
ese
o
u
tco
m
es
s
u
g
g
est
th
at
E
O
o
f
f
e
r
s
th
e
m
o
s
t
r
eliab
le
FS
s
tr
ateg
y
f
o
r
SF
P,
ef
f
ec
tiv
ely
en
h
an
cin
g
class
if
ier
p
er
f
o
r
m
a
n
ce
.
PR
O
an
d
HGSO
also
d
em
o
n
s
tr
ated
s
tr
o
n
g
a
n
d
co
n
s
i
s
ten
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
m
u
ltip
le
s
ce
n
ar
io
s
.
4.
3
.
Sta
t
is
t
ica
l
a
na
ly
s
is
T
o
c
o
m
p
a
r
e
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
e
n
w
r
a
p
p
e
r
-
b
a
s
e
d
F
S
m
e
t
h
o
d
s
(
AB
O
,
AS
O
,
E
O
,
HGS
O
,
PR
O
,
G
N
D
O
,
S
MA
,
HH
O
,
P
F
A
,
a
n
d
M
R
F
O
)
wi
t
h
t
h
at
o
f
t
h
e
b
ase
l
i
n
e
m
e
t
h
o
d
,
t
h
e
W
i
l
c
o
x
o
n
s
ig
n
e
d
-
r
a
n
k
t
e
s
t
wa
s
a
p
p
l
i
e
d
w
it
h
α
=
0
.
0
5
.
T
a
b
l
e
4
p
r
e
s
e
n
t
s
t
h
e
d
e
ta
i
l
e
d
s
ta
t
is
t
ica
l
t
es
t
r
es
u
l
ts
f
o
r
al
l
e
v
al
u
a
t
e
d
M
L
a
l
g
o
r
i
t
h
m
s
a
n
d
w
r
a
p
p
e
r
-
b
a
s
e
d
FS
m
e
t
h
o
d
s
w
i
th
r
e
s
p
e
c
t
t
o
p
r
e
c
is
i
o
n
,
r
e
c
al
l
,
F1
-
s
c
o
r
e
,
a
n
d
A
UC
.
T
a
b
l
e
4
p
r
es
e
n
ts
t
h
e
s
t
a
t
is
ti
c
a
l
a
n
a
l
y
s
is
r
e
s
u
l
ts
,
i
n
c
l
u
d
i
n
g
P
-
v
a
l
u
e
s
,
e
f
f
e
c
t
s
i
z
e
(
r
)
,
a
n
d
m
e
a
n
d
i
f
f
e
r
e
n
c
e
s
.
A
n
a
s
t
e
r
is
k
(
*
)
d
e
n
o
t
e
s
a
s
t
a
ti
s
t
i
c
a
ll
y
s
i
g
n
i
f
i
c
a
n
t
d
i
f
f
e
r
e
n
c
e
,
c
o
r
r
e
s
p
o
n
d
i
n
g
t
o
a
P
-
v
a
l
u
e
l
e
s
s
t
h
a
n
0
.
0
5
.
T
h
e
e
f
f
e
c
t
s
i
z
e
r
q
u
a
n
t
i
f
ie
s
t
h
e
m
a
g
n
i
t
u
d
e
o
f
t
h
e
p
e
r
f
o
r
m
a
n
c
e
d
i
f
f
e
r
e
n
c
e
b
e
tw
e
e
n
t
h
e
c
o
m
p
a
r
e
d
m
e
t
h
o
d
s
,
w
h
i
l
e
t
h
e
m
ea
n
d
i
f
f
e
r
e
n
c
e
i
n
d
ic
a
t
e
s
w
h
i
c
h
m
e
t
h
o
d
a
c
h
i
e
v
e
s
a
h
i
g
h
e
r
a
v
e
r
a
g
e
s
c
o
r
e
.
A
c
c
o
r
d
i
n
g
t
o
T
a
b
l
e
4
,
s
e
v
e
r
al
F
S
m
e
t
h
o
d
s
d
e
m
o
n
s
t
r
a
t
e
d
s
t
at
i
s
t
i
c
al
l
y
s
i
g
n
i
f
i
c
a
n
t
i
m
p
r
o
v
e
m
e
n
t
s
i
n
F
1
-
s
c
o
r
e
c
o
m
p
a
r
e
d
t
o
t
h
e
b
a
s
e
l
i
n
e
.
F
o
r
ex
a
m
p
l
e
,
A
S
O
a
c
h
i
e
v
e
d
a
s
t
ati
s
ti
c
a
ll
y
s
i
g
n
i
f
i
ca
n
t
i
m
p
r
o
v
e
m
e
n
t
w
i
t
h
a
P
-
v
a
l
u
e
o
f
0
.
0
2
6
a
n
d
a
l
a
r
g
e
e
f
f
e
c
t
s
i
z
e
(
r
=
0
.
9
1
3
)
,
a
l
o
n
g
w
i
t
h
a
m
e
a
n
d
i
f
f
e
r
e
n
c
e
o
f
0
.
0
7
1
.
S
i
m
i
la
r
l
y
,
H
G
SO
a
n
d
P
R
O
d
em
o
n
s
t
r
a
t
e
d
m
e
a
n
i
n
g
f
u
l
g
a
i
n
s
,
w
i
t
h
P
-
v
a
l
u
e
s
o
f
0
.
0
2
2
a
n
d
0
.
0
3
3
,
a
n
d
m
o
d
e
r
a
t
e
e
f
f
e
c
t
s
i
z
es
o
f
0
.
5
2
0
a
n
d
0
.
5
6
1
,
r
e
s
p
e
c
t
i
v
e
l
y
.
I
n
c
o
n
t
r
a
s
t
,
E
O
s
h
o
w
e
d
a
m
o
d
e
r
a
t
e
e
f
f
e
c
t
s
i
z
e
(
r
=
0
.
4
8
9
)
b
u
t
a
non
-
s
i
g
n
i
f
i
c
a
n
t
P
-
v
al
u
e
o
f
0
.
2
9
3
,
i
n
d
i
c
a
t
i
n
g
t
h
at
i
ts
p
e
r
f
o
r
m
a
n
c
e
d
i
f
f
e
r
e
n
c
e
f
r
o
m
t
h
e
b
a
s
e
li
n
e
m
a
y
n
o
t
b
e
s
t
a
ti
s
t
i
c
al
l
y
r
e
l
ia
b
l
e
.
I
n
c
o
n
t
r
a
s
t
,
S
M
A
a
n
d
H
H
O
s
h
o
w
e
d
P
-
v
a
l
u
e
s
o
f
1
.
0
0
0
,
i
n
d
i
c
a
t
i
n
g
n
o
s
t
a
t
is
t
ic
a
l
d
i
f
f
e
r
e
n
ce
f
r
o
m
t
h
e
b
a
s
e
l
i
n
e
,
e
v
e
n
t
h
o
u
g
h
t
h
e
i
r
e
f
f
e
c
t
s
i
z
es
w
e
r
e
m
o
d
er
a
t
e
(
0
.
5
3
4
a
n
d
0
.
6
3
3
)
.
T
h
e
s
e
f
i
n
d
i
n
g
s
s
u
g
g
e
s
t
t
h
a
t
n
o
t
a
l
l
n
u
m
e
r
i
c
a
l
d
i
f
f
e
r
e
n
c
es
t
r
a
n
s
l
at
e
i
n
t
o
m
e
a
n
i
n
g
f
u
l
s
ta
t
is
t
i
ca
l
s
i
g
n
i
f
i
c
a
n
c
e
.
O
v
e
r
al
l
,
AS
O
,
H
GS
O
,
PR
O,
P
F
A
,
a
n
d
MR
FO
s
t
o
o
d
o
u
t
a
s
s
t
a
ti
s
t
i
c
al
l
y
a
n
d
p
r
a
c
t
i
c
al
l
y
e
f
f
ec
t
i
v
e
FS
m
e
t
h
o
d
s
f
o
r
r
a
n
d
o
m
f
o
r
e
s
t
a
n
d
s
h
o
u
l
d
b
e
p
r
i
o
r
i
t
i
z
e
d
f
o
r
r
e
a
l
-
w
o
r
l
d
d
e
p
l
o
y
m
e
n
t
i
n
S
FP
m
o
d
e
ls
.
T
ab
le
4
.
Statis
tical
test
r
e
s
u
lts
f
o
r
th
e
co
m
p
ar
is
o
n
b
etwe
en
ten
wr
ap
p
er
-
b
ased
FS
m
eth
o
d
s
a
n
d
th
e
b
aselin
e
m
eth
o
d
f
o
r
r
an
d
o
m
f
o
r
est,
ET
an
d
Ad
aBo
o
s
t
C
o
m
p
a
r
i
so
n
g
r
o
u
p
M
e
a
su
r
e
R
a
n
d
o
m
fo
r
es
t
ET
A
d
a
B
o
o
s
t
AUC
F1
P
R
AUC
F1
P
R
AUC
F1
P
R
A
B
O
&
B
a
se
l
i
n
e
P
-
v
a
l
u
e
0
.
0
8
0
.
0
8
0
.
4
1
6
0
.
0
4
3
*
0
.
0
8
0
.
0
8
0
.
4
1
6
0
.
0
4
3
*
0
.
0
1
8
*
0
.
0
5
2
*
0
.
2
3
6
0
.
8
5
8
Ef
f
e
c
t
r
0
.
6
9
5
0
.
7
8
2
0
.
9
7
4
-
0
.
0
6
2
0
.
6
9
5
0
.
7
8
2
0
.
9
7
4
-
0
.
0
6
2
0
.
5
8
9
0
.
8
1
4
0
.
5
4
9
0
.
4
8
1
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
0
9
7
0
.
0
4
4
0
.
0
1
0
.
0
9
6
0
.
0
9
7
0
.
0
4
4
0
.
0
1
0
.
0
9
6
0
.
0
5
9
0
.
0
0
2
0
.
0
2
8
0
.
0
1
6
A
S
O
& B
a
s
e
l
i
n
e
P
-
v
a
l
u
e
0
.
0
1
3
*
0
.
1
0
9
0
.
1
0
7
0
.
0
5
3
*
0
.
0
1
3
*
0
.
1
0
9
0
.
1
0
7
0
.
0
5
3
*
0
.
0
1
8
*
0
.
3
6
2
0
.
0
3
5
*
0
.
5
9
Ef
f
e
c
t
r
0
.
2
5
6
0
.
5
8
5
0
.
7
1
4
0
.
1
8
4
0
.
2
5
6
0
.
5
8
5
0
.
7
1
4
0
.
1
8
4
-
0
.
1
0
4
0
.
7
6
8
0
.
7
0
3
0
.
5
3
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
0
9
3
0
.
0
5
0
.
0
4
1
0
.
0
5
7
0
.
0
9
3
0
.
0
5
0
.
0
4
1
0
.
0
5
7
0
.
0
8
7
0
.
0
2
7
0
.
0
7
8
0
.
0
2
7
EO
& B
a
se
l
i
n
e
P
-
v
a
l
u
e
0
.
0
5
1
*
0
.
2
9
3
0
.
5
7
4
0
.
0
5
0
*
0
.
0
5
1
*
0
.
2
9
3
0
.
5
7
4
0
.
0
5
0
*
0
.
4
0
7
0
.
0
1
8
*
0
.
0
6
8
0
.
1
2
3
Ef
f
e
c
t
r
0
.
2
0
5
0
.
5
4
0
.
4
3
5
0
.
5
2
5
0
.
2
0
5
0
.
5
4
0
.
4
3
5
0
.
5
2
5
-
0
.
2
8
4
0
.
5
0
9
0
.
5
3
2
-
0
.
0
1
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
1
1
4
0
.
0
4
0
.
0
1
2
0
.
0
8
3
0
.
1
1
4
0
.
0
4
0
.
0
1
2
0
.
0
8
3
0
.
0
2
8
0
.
0
9
6
0
.
0
6
6
0
.
1
0
2
H
G
S
O
& B
a
s
e
l
i
n
e
P
-
v
a
l
u
e
0
.
2
0
8
0
.
0
2
2
*
0
.
1
8
9
0
.
0
3
3
*
0
.
2
0
8
0
.
0
2
2
*
0
.
1
8
9
0
.
0
3
3
*
0
.
0
1
1
*
0
.
0
9
2
0
.
0
1
1
*
0
.
5
2
8
Ef
f
e
c
t
r
0
.
4
4
6
0
.
5
2
0
.
7
6
5
0
.
1
2
3
0
.
4
4
6
0
.
5
2
0
.
7
6
5
0
.
1
2
3
0
.
2
2
6
0
.
4
0
1
0
.
7
7
6
-
0
.
0
1
3
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
0
7
9
0
.
0
0
1
-
0
.
0
1
2
0
.
0
2
4
0
.
0
7
9
0
.
0
0
1
-
0
.
0
1
2
0
.
0
2
4
0
.
1
0
.
0
5
6
0
.
0
8
1
0
.
0
2
7
P
R
O
&
B
a
s
e
l
i
n
e
P
-
v
a
l
u
e
0
.
2
8
4
0
.
0
3
3
*
1
0
.
4
9
8
0
.
2
8
4
0
.
0
3
3
*
1
0
.
4
9
8
0
.
1
5
5
0
.
2
0
5
0
.
2
0
7
0
.
9
0
5
Ef
f
e
c
t
r
0
.
4
8
7
0
.
5
6
1
0
.
8
3
7
0
.
1
6
5
0
.
4
8
7
0
.
5
6
1
0
.
8
3
7
0
.
1
6
5
0
.
0
4
2
0
.
5
9
7
0
.
6
7
7
0
.
4
8
8
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
0
5
4
0
.
0
0
4
0
.
0
0
1
0
.
0
0
9
0
.
0
5
4
0
.
0
0
4
0
.
0
0
1
0
.
0
0
9
0
.
0
5
0
.
0
2
1
0
.
0
3
7
0
.
0
1
1
G
N
D
O
& B
a
s
e
l
i
n
e
P
-
v
a
l
u
e
0
.
3
7
2
0
.
0
4
5
*
0
.
0
2
8
*
0
.
0
6
2
0
.
3
7
2
0
.
0
4
5
*
0
.
0
2
8
*
0
.
0
6
2
0
.
0
5
0
*
0
.
7
5
2
0
.
0
2
4
*
0
.
4
0
1
Ef
f
e
c
t
r
-
0
.
3
6
1
0
.
4
9
1
0
.
6
8
5
0
.
1
4
4
-
0
.
3
6
1
0
.
4
9
1
0
.
6
8
5
0
.
1
4
4
-
0
.
3
7
2
0
.
1
1
3
0
.
7
6
9
-
0
.
2
1
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
0
6
2
0
.
0
1
8
0
.
0
1
1
0
.
0
2
6
0
.
0
6
2
0
.
0
1
8
0
.
0
1
1
0
.
0
2
6
0
.
0
6
7
0
.
0
0
3
0
.
0
5
1
0
.
0
5
1
S
M
A
&
B
a
s
e
l
i
n
e
P
-
v
a
l
u
e
0
.
0
8
9
1
0
.
0
2
6
*
0
.
0
4
1
*
0
.
0
8
9
1
0
.
0
2
6
*
0
.
0
4
1
*
1
0
.
3
1
0
.
0
2
8
*
0
.
5
7
5
Ef
f
e
c
t
r
-
0
.
0
6
1
0
.
5
3
4
0
.
7
5
7
-
0
.
0
6
3
-
0
.
0
6
1
0
.
5
3
4
0
.
7
5
7
-
0
.
0
6
3
0
.
1
9
9
0
.
3
1
4
0
.
7
4
5
0
.
3
2
6
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
-
0
.
0
2
8
0
.
0
0
7
-
0
.
0
1
0
.
0
3
1
-
0
.
0
2
8
0
.
0
0
7
-
0
.
0
1
0
.
0
3
1
0
.
0
0
1
0
.
0
2
4
0
.
0
4
8
0
H
H
O
& B
a
s
e
l
i
n
e
P
-
v
a
l
u
e
0
.
4
9
9
1
1
1
0
.
4
9
9
1
1
1
0
.
1
7
3
0
.
0
3
7
*
0
.
0
1
7
*
0
.
3
7
3
Ef
f
e
c
t
r
0
.
2
3
1
0
.
6
3
3
0
.
7
8
0
.
3
0
9
0
.
2
3
1
0
.
6
3
3
0
.
7
8
0
.
3
0
9
-
0
.
1
9
8
0
.
7
0
.
9
0
.
5
5
2
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
0
2
8
-
0
.
0
0
2
0
.
0
0
2
-
0
.
0
0
7
0
.
0
2
8
-
0
.
0
0
2
0
.
0
0
2
-
0
.
0
0
7
0
.
0
4
8
0
.
0
1
9
0
.
0
5
4
0
.
0
3
P
F
A
& B
a
s
e
l
i
n
e
P
-
v
a
l
u
e
0
.
0
2
3
*
0
.
0
3
5
*
0
.
0
6
5
0
.
0
2
5
*
0
.
0
2
3
*
0
.
0
3
5
*
0
.
0
6
5
0
.
0
2
5
*
0
.
0
2
4
*
0
.
4
0
5
0
.
0
1
7
*
0
.
5
5
3
Ef
f
e
c
t
r
0
.
2
0
3
0
.
7
8
6
0
.
8
9
4
0
.
4
8
3
0
.
2
0
3
0
.
7
8
6
0
.
8
9
4
0
.
4
8
3
-
0
.
1
3
3
0
.
6
8
6
0
.
8
8
6
0
.
4
1
3
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
0
9
2
0
.
0
5
2
0
.
0
3
4
0
.
0
7
9
0
.
0
9
2
0
.
0
5
2
0
.
0
3
4
0
.
0
7
9
0
.
0
7
8
0
.
0
1
4
0
.
0
5
9
0
.
0
3
3
M
R
F
O
&
B
a
se
l
i
n
e
P
-
v
a
l
u
e
0
.
2
0
7
0
.
0
3
5
*
0
.
5
9
3
0
.
4
8
3
0
.
2
0
7
0
.
0
3
5
*
0
.
5
9
3
0
.
4
8
3
0
.
0
1
3
*
0
.
3
7
3
0
.
0
2
8
*
0
.
5
1
4
Ef
f
e
c
t
r
-
0
.
2
0
7
0
.
2
9
3
0
.
4
7
1
-
0
.
0
7
6
-
0
.
2
0
7
0
.
2
9
3
0
.
4
7
1
-
0
.
0
7
6
0
.
4
2
6
0
.
6
7
1
0
.
7
8
4
0
.
3
9
8
M
e
a
n
-
d
i
f
f
e
r
e
n
c
e
0
.
0
8
1
0
.
0
2
1
0
.
0
2
2
0
.
0
2
1
0
.
0
8
1
0
.
0
2
1
0
.
0
2
2
0
.
0
2
1
0
.
0
8
0
.
0
1
8
0
.
0
5
9
0
.
0
2
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
s
o
ftw
a
r
e
fa
u
lt p
r
ed
ictio
n
u
s
in
g
w
r
a
p
p
er
-
b
a
s
ed
m
eta
h
eu
r
is
tic
…
(
Ha
Th
i Min
h
P
h
u
o
n
g
)
4809
5.
CO
NCLU
SI
O
N
T
h
e
o
b
jectiv
e
o
f
SF
P
m
o
d
el
s
is
to
b
u
ild
h
ig
h
-
q
u
ality
s
o
f
twar
e
with
m
in
im
al
test
in
g
ef
f
o
r
ts
b
y
id
en
tify
in
g
f
au
lty
m
o
d
u
les
e
ar
ly
in
th
e
s
o
f
twar
e
d
ev
el
o
p
m
en
t
p
r
o
ce
s
s
.
T
h
e
p
er
f
o
r
m
a
n
ce
of
SFP
m
o
d
els,
h
o
wev
er
,
is
i
n
f
lu
en
ce
d
by
t
h
e
q
u
ality
of
th
e
s
o
f
twar
e
d
ef
ec
t
d
atasets
,
wh
ich
co
m
m
o
n
l
y
s
u
f
f
er
f
r
o
m
h
ig
h
d
im
en
s
io
n
ality
.
T
h
er
e
f
o
r
e,
th
e
elim
in
atio
n
o
f
ir
r
elev
an
t
an
d
r
ed
u
n
d
an
t
f
ea
tu
r
es
f
r
o
m
s
o
f
twar
e
f
au
lt
d
atasets
is
an
im
p
o
r
ta
n
t
s
tep
in
b
u
ild
i
n
g
a
r
o
b
u
s
t
SF
P
m
o
d
el.
I
n
th
is
s
tu
d
y
,
we
p
r
esen
t
an
ev
al
u
atio
n
o
f
th
ese
wr
ap
p
er
s
tr
ateg
ies to
s
elec
t o
p
tim
al
f
ea
tu
r
es.
Su
b
s
eq
u
en
tly
,
we
ap
p
lied
v
ar
io
u
s
ML
tech
n
iq
u
es to
th
e
d
atasets
with
th
e
p
r
ev
io
u
s
ly
e
x
tr
ac
ted
o
p
tim
al
f
ea
tu
r
es.
Mo
r
eo
v
er
,
th
is
s
tu
d
y
co
n
d
u
cted
a
co
m
p
ar
ativ
e
p
er
f
o
r
m
a
n
ce
an
aly
s
is
b
etwe
en
th
e
p
r
o
p
o
s
ed
wr
a
p
p
er
-
b
ased
FS
m
eth
o
d
s
an
d
th
e
b
aselin
e
ap
p
r
o
ac
h
.
T
h
e
e
x
p
er
im
en
tal
r
esu
lts
s
h
o
wed
th
at
ten
p
r
esen
ted
wr
ap
p
er
-
b
ased
FS
m
eth
o
d
s
ac
h
i
ev
ed
b
etter
p
er
f
o
r
m
an
ce
c
o
m
p
ar
ed
to
t
h
e
b
aselin
e
m
eth
o
d
w
h
ich
ap
p
lied
ML
tec
h
n
iq
u
es
to
th
e
o
r
ig
in
al
d
ataset
.
Mo
r
eo
v
er
,
th
e
r
esu
lts
in
d
icate
d
th
at
E
O
was
th
e
m
o
s
t
ef
f
ec
tiv
e,
with
PR
O
an
d
HGSO
f
o
llo
win
g
.
Ho
wev
er
,
th
is
s
tu
d
y
s
till
h
as
ce
r
tain
lim
itatio
n
s
.
First,
th
e
d
atasets
u
s
ed
ar
e
s
tatic
an
d
r
elativ
ely
well
-
b
alan
ce
d
,
wh
ic
h
m
ay
n
o
t
f
u
lly
ca
p
t
u
r
e
t
h
e
c
h
allen
g
es
p
o
s
ed
b
y
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
in
v
o
lv
in
g
im
b
alan
ce
d
d
is
tr
ib
u
tio
n
s
o
r
d
ata
th
at
ch
an
g
e
o
v
er
tim
e.
Seco
n
d
,
e
v
alu
atin
g
th
e
m
eth
o
d
s
u
s
in
g
o
n
ly
th
r
ee
class
if
ier
s
m
ay
lim
it
th
e
g
en
er
aliza
b
ilit
y
o
f
th
e
f
in
d
in
g
s
ac
r
o
s
s
o
th
er
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
I
n
th
e
f
u
tu
r
e,
we
aim
to
ex
p
lo
r
e
th
e
in
teg
r
atio
n
of
t
h
e
p
r
o
p
o
s
ed
wr
ap
p
e
r
-
b
ased
FS
m
eth
o
d
s
with
s
am
p
lin
g
tech
n
iq
u
es
s
u
c
h
as
SMOT
E
or
ADASYN
to
ad
d
r
ess
th
e
ch
allen
g
es
of
h
ig
h
-
d
im
en
s
io
n
al
a
n
d
im
b
alan
ce
d
d
atasets
,
th
er
e
b
y
e
n
h
an
cin
g
th
e
p
e
r
f
o
r
m
an
ce
o
f
SF
P m
o
d
els.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Fu
n
d
in
g
f
o
r
th
is
r
esear
ch
was
p
r
o
v
id
ed
b
y
th
e
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
Dev
elo
p
m
en
t
F
u
n
d
o
f
th
e
Un
iv
er
s
ity
o
f
Dan
a
n
g
,
p
r
o
ject
n
u
m
b
er
B
2
0
2
2
-
DN0
7
-
02
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ha
T
h
i M
in
h
Ph
u
o
n
g
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Dan
g
T
h
i K
im
Ng
a
n
✓
✓
✓
✓
✓
✓
✓
✓
Dao
Kh
an
h
Du
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ng
u
y
en
T
h
an
h
B
in
h
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
er
e
ar
e
n
o
co
n
f
licts
o
f
in
ter
est r
eg
ar
d
in
g
t
h
e
p
u
b
licatio
n
o
f
th
is
p
ap
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
an
d
s
o
u
r
ce
co
d
e
u
s
ed
can
be
ac
ce
s
s
ed
at
h
ttp
s
:
//g
ith
u
b
.
co
m/Du
yc
a
n
1
7
/Wr
a
p
p
er
-
B
a
s
e
d
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
C
h
a
n
d
r
a
s
h
e
k
a
r
a
n
d
F
.
S
a
h
i
n
,
“
A
s
u
r
v
e
y
o
n
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
m
e
t
h
o
d
s
,
”
C
o
m
p
u
t
e
rs
&
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
0
,
n
o
.
1
,
p
p
.
16
–
2
8
,
Ja
n
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
e
l
e
c
e
n
g
.
2
0
1
3
.
1
1
.
0
2
4
.
[
2
]
E.
Ll
o
b
e
t
e
t
a
l
.
,
“
Ef
f
i
c
i
e
n
t
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
f
o
r
mass
s
p
e
c
t
r
o
m
e
t
r
y
b
a
s
e
d
e
l
e
c
t
r
o
n
i
c
n
o
se
a
p
p
l
i
c
a
t
i
o
n
s,
”
C
h
e
m
o
m
e
t
r
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
L
a
b
o
r
a
t
o
r
y
S
y
st
e
m
s
,
v
o
l
.
8
5
,
n
o
.
2
,
p
p
.
2
5
3
–
2
6
1
,
F
e
b
.
2
0
0
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
e
m
o
l
a
b
.
2
0
0
6
.
0
7
.
0
0
2
.
[
3
]
H.
-
H
.
H
su
,
C
.
-
W
.
H
si
e
h
,
a
n
d
M
.
-
D
.
Lu
,
“
H
y
b
r
i
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
b
y
c
o
mb
i
n
i
n
g
f
i
l
t
e
r
s
a
n
d
w
r
a
p
p
e
r
s,”
E
x
p
e
rt
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
8
,
n
o
.
7
,
p
p
.
8
1
4
4
–
8
1
5
0
,
J
u
l
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
0
.
1
2
.
1
5
6
.
[
4
]
M
.
M
a
b
a
y
o
j
e
,
A
.
B
a
l
o
g
u
n
,
S
.
B
e
l
l
o
,
a
n
d
J.
A
t
o
y
e
b
i
,
“
W
r
a
p
p
e
r
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
b
a
se
d
H
e
t
e
r
o
g
e
n
e
o
u
s
c
l
a
s
si
f
i
e
r
s
f
o
r
s
o
f
t
w
a
r
e
d
e
f
e
c
t
p
r
e
d
i
c
t
i
o
n
,”
Ad
e
l
e
k
e
U
n
i
v
e
rsi
t
y
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
(
AU
J
ET)
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
1
–
1
1
,
2
0
1
9
.
[
5
]
A
.
J.
A
n
j
u
a
n
d
J.
E.
J
u
d
i
t
h
,
“
H
y
b
r
i
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
me
t
h
o
d
f
o
r
p
r
e
d
i
c
t
i
n
g
so
f
t
w
a
r
e
d
e
f
e
c
t
,
”
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
ri
n
g
a
n
d
A
p
p
l
i
e
d
S
c
i
e
n
c
e
,
v
o
l
.
7
1
,
n
o
.
1
,
p
.
1
2
4
,
2
0
2
4
.
[
6
]
M
.
A
l
i
e
t
a
l
.
,
“
A
n
a
l
y
s
i
s
o
f
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
d
s
i
n
so
f
t
w
a
r
e
d
e
f
e
c
t
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
1
4
5
9
5
4
–
1
4
5
9
7
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
4
3
2
4
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
8
0
3
-
4
8
1
2
4810
[
7
]
M
.
M
a
f
a
r
j
a
,
I
.
Jab
e
r
,
S
.
A
h
me
d
,
a
n
d
T.
Th
a
h
e
r
,
“
W
h
a
l
e
o
p
t
i
m
i
sa
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
h
i
g
h
-
d
i
m
e
n
si
o
n
a
l
s
mal
l
-
i
n
st
a
n
c
e
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Pa
r
a
l
l
e
l
,
Em
e
r
g
e
n
t
a
n
d
D
i
s
t
ri
b
u
t
e
d
S
y
s
t
e
m
s
,
v
o
l
.
3
6
,
n
o
.
2
,
p
p
.
8
0
–
9
6
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
0
/
1
7
4
4
5
7
6
0
.
2
0
1
9
.
1
6
1
7
8
6
6
.
[
8
]
A
.
A
mi
r
u
l
l
a
h
,
U
.
L
.
Y
u
h
a
n
a
,
a
n
d
M
.
A
l
f
i
a
n
,
“
I
mp
r
o
v
e
s
o
f
t
w
a
r
e
d
e
f
e
c
t
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
sy
n
t
h
e
t
i
c
mi
n
o
r
i
t
y
o
v
e
r
-
sa
mp
l
i
n
g
t
e
c
h
n
i
q
u
e
,
”
S
c
i
e
n
t
i
f
i
c
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
1
1
2
7
–
1
1
3
6
,
2
0
2
4
.
[
9
]
A
.
O
.
B
a
l
o
g
u
n
e
t
a
l
.
,
“
A
n
o
v
e
l
r
a
n
k
a
g
g
r
e
g
a
t
i
o
n
‐
b
a
se
d
h
y
b
r
i
d
m
u
l
t
i
f
i
l
t
e
r
w
r
a
p
p
e
r
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
me
t
h
o
d
i
n
so
f
t
w
a
r
e
d
e
f
e
c
t
p
r
e
d
i
c
t
i
o
n
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
2
0
2
1
,
n
o
.
1
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
5
0
6
9
0
1
6
.
[
1
0
]
H
.
S
h
a
h
a
n
d
H
.
D
a
s,
“
A
w
r
a
p
p
e
r
-
b
a
s
e
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
p
p
r
o
a
c
h
u
s
i
n
g
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
f
o
r
so
f
t
w
a
r
e
f
a
u
l
t
p
r
e
d
i
c
t
i
o
n
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
c
o
m
p
u
t
a
t
i
o
n
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
,
2
0
2
2
,
p
p
.
3
7
5
–
3
8
6
.
[
1
1
]
H
.
T
u
r
a
b
i
e
h
,
M
.
M
a
f
a
r
j
a
,
a
n
d
X
.
Li
,
“
I
t
e
r
a
t
e
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
l
g
o
r
i
t
h
ms
w
i
t
h
l
a
y
e
r
e
d
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
so
f
t
w
a
r
e
f
a
u
l
t
p
r
e
d
i
c
t
i
o
n
,
”
Ex
p
e
rt
S
y
st
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
2
,
p
p
.
2
7
–
4
2
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
8
.
1
2
.
0
3
3
.
[
1
2
]
X
.
Q
i
,
Y
.
Zh
u
,
a
n
d
H
.
Z
h
a
n
g
,
“
A
n
e
w
met
a
-
h
e
u
r
i
s
t
i
c
b
u
t
t
e
r
f
l
y
-
i
n
sp
i
r
e
d
a
l
g
o
r
i
t
h
m,”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
,
v
o
l
.
2
3
,
p
p
.
2
2
6
–
2
3
9
,
N
o
v
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
c
s.
2
0
1
7
.
0
6
.
0
0
3
.
[
1
3
]
W
.
Z
h
a
o
,
L.
W
a
n
g
,
a
n
d
Z.
Z
h
a
n
g
,
“
A
t
o
m
se
a
r
c
h
o
p
t
i
mi
z
a
t
i
o
n
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
t
o
s
o
l
v
e
a
h
y
d
r
o
g
e
o
l
o
g
i
c
p
a
r
a
met
e
r
e
st
i
ma
t
i
o
n
p
r
o
b
l
e
m,
”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
s
t
e
m
s
,
v
o
l
.
1
6
3
,
p
p
.
2
8
3
–
3
0
4
,
Ja
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s
.
2
0
1
8
.
0
8
.
0
3
0
.
[
1
4
]
A
.
F
a
r
a
m
a
r
z
i
,
M
.
H
e
i
d
a
r
i
n
e
j
a
d
,
B
.
S
t
e
p
h
e
n
s,
a
n
d
S
.
M
i
r
j
a
l
i
l
i
,
“
Eq
u
i
l
i
b
r
i
u
m
o
p
t
i
mi
z
e
r
:
a
n
o
v
e
l
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
,
”
K
n
o
w
l
e
d
g
e
-
B
a
s
e
d
S
y
s
t
e
ms
,
v
o
l
.
1
9
1
,
p
.
1
0
5
1
9
0
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
1
9
.
1
0
5
1
9
0
.
[
1
5
]
F
.
A
.
H
a
s
h
i
m
,
E
.
H
.
H
o
u
s
s
e
i
n
,
M
.
S
.
M
a
b
r
o
u
k
,
W
.
A
l
-
A
t
a
b
a
n
y
,
a
n
d
S
.
M
i
r
j
a
l
i
l
i
,
“
H
e
n
r
y
g
a
s
s
o
l
u
b
i
l
i
t
y
o
p
t
i
m
i
z
a
t
i
o
n
:
A
n
o
v
e
l
p
h
y
s
i
c
s
-
b
a
s
e
d
a
l
g
o
r
i
t
h
m
,
”
F
u
t
u
r
e
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
,
v
o
l
.
1
0
1
,
p
p
.
6
4
6
–
6
6
7
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
1
9
.
0
7
.
0
1
5
.
[
1
6
]
Y
.
Li
,
W
.
Z
h
a
n
g
,
L.
W
a
n
g
,
F
.
Z
h
a
o
,
W
.
H
a
n
,
a
n
d
G
.
C
h
e
n
,
“
H
e
n
r
y
’
s
l
a
w
a
n
d
a
c
c
u
mu
l
a
t
i
o
n
o
f
w
e
a
k
so
u
r
c
e
f
o
r
c
r
u
st
-
d
e
r
i
v
e
d
h
e
l
i
u
m:
A
c
a
s
e
s
t
u
d
y
o
f
W
e
i
h
e
B
a
si
n
,
C
h
i
n
a
,
”
J
o
u
rn
a
l
o
f
N
a
t
u
r
a
l
G
a
s
G
e
o
sc
i
e
n
c
e
,
v
o
l
.
2
,
n
o
.
5
–
6
,
p
p
.
3
3
3
–
3
3
9
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
n
g
g
s.
2
0
1
8
.
0
2
.
0
0
1
.
[
1
7
]
S
.
H
.
S
a
m
a
r
e
h
M
o
o
s
a
v
i
a
n
d
V
.
K
.
B
a
r
d
s
i
r
i
,
“
P
o
o
r
a
n
d
r
i
c
h
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
:
A
n
e
w
h
u
m
a
n
-
b
a
s
e
d
a
n
d
m
u
l
t
i
p
o
p
u
l
a
t
i
o
n
s
a
l
g
o
r
i
t
h
m
,
”
E
n
g
i
n
e
e
r
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
8
6
,
p
p
.
1
6
5
–
1
8
1
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
1
9
.
0
8
.
0
2
5
.
[
1
8
]
Y
.
Z
h
a
n
g
,
Z
.
J
i
n
,
a
n
d
S
.
M
i
r
j
a
l
i
l
i
,
“
G
e
n
e
r
a
l
i
z
e
d
n
o
r
m
a
l
d
i
s
t
r
i
b
u
t
i
o
n
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
s
i
n
p
a
r
a
m
e
t
e
r
e
x
t
r
a
c
t
i
o
n
o
f
p
h
o
t
o
v
o
l
t
a
i
c
m
o
d
e
l
s
,
”
E
n
e
r
g
y
C
o
n
v
e
r
s
i
o
n
a
n
d
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
2
2
4
,
p
.
1
1
3
3
0
1
,
N
o
v
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
c
o
n
m
a
n
.
2
0
2
0
.
1
1
3
3
0
1
.
[
1
9
]
S
.
L
i
,
H
.
C
h
e
n
,
M
.
W
a
n
g
,
A
.
A
.
H
e
i
d
a
r
i
,
a
n
d
S
.
M
i
r
j
a
l
i
l
i
,
“
S
l
i
me
mo
u
l
d
a
l
g
o
r
i
t
h
m:
a
n
e
w
met
h
o
d
f
o
r
st
o
c
h
a
st
i
c
o
p
t
i
mi
z
a
t
i
o
n
,
”
Fu
t
u
r
e
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
e
r
S
y
s
t
e
m
s
,
v
o
l
.
1
1
1
,
p
p
.
3
0
0
–
3
2
3
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
0
.
0
3
.
0
5
5
.
[
2
0
]
A
.
A
.
H
e
i
d
a
r
i
,
S
.
M
i
r
j
a
l
i
l
i
,
H
.
F
a
r
i
s,
I
.
A
l
j
a
r
a
h
,
M
.
M
a
f
a
r
j
a
,
a
n
d
H
.
C
h
e
n
,
“
H
a
r
r
i
s
h
a
w
k
s
o
p
t
i
m
i
z
a
t
i
o
n
:
a
l
g
o
r
i
t
h
m
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
F
u
t
u
re
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
e
r
S
y
st
e
m
s
,
v
o
l
.
9
7
,
p
p
.
8
4
9
–
8
7
2
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
1
9
.
0
2
.
0
2
8
.
[
2
1
]
H
.
Y
a
p
i
c
i
a
n
d
N
.
C
e
t
i
n
k
a
y
a
,
“
A
n
e
w
me
t
a
-
h
e
u
r
i
st
i
c
o
p
t
i
m
i
z
e
r
:
p
a
t
h
f
i
n
d
e
r
a
l
g
o
r
i
t
h
m
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
7
8
,
p
p
.
5
4
5
–
5
6
8
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
1
9
.
0
3
.
0
1
2
.
[
2
2
]
W
.
Z
h
a
o
,
Z
.
Z
h
a
n
g
,
a
n
d
L
.
W
a
n
g
,
“
M
a
n
t
a
r
a
y
f
o
r
a
g
i
n
g
o
p
t
i
m
i
z
a
t
i
o
n
:
A
n
e
f
f
e
c
t
i
v
e
b
i
o
-
i
n
s
p
i
r
e
d
o
p
t
i
m
i
z
e
r
f
o
r
e
n
g
i
n
e
e
r
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
,
”
E
n
g
i
n
e
e
r
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
8
7
,
p
.
1
0
3
3
0
0
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
1
9
.
1
0
3
3
0
0
.
[
2
3
]
L.
B
r
e
i
m
a
n
,
“
R
a
n
d
o
m Fo
r
e
st
s
,
”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
5
–
3
2
,
O
c
t
.
2
0
0
1
,
d
o
i
:
1
0
.
1
0
2
3
/
A
:
1
0
1
0
9
3
3
4
0
4
3
2
4
.
[
2
4
]
Y
.
F
r
e
u
n
d
a
n
d
R
.
E
.
S
c
h
a
p
i
r
e
,
“
A
d
e
c
i
si
o
n
-
t
h
e
o
r
e
t
i
c
g
e
n
e
r
a
l
i
z
a
t
i
o
n
o
f
o
n
-
l
i
n
e
l
e
a
r
n
i
n
g
a
n
d
a
n
a
p
p
l
i
c
a
t
i
o
n
t
o
b
o
o
st
i
n
g
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
a
n
d
S
y
s
t
e
m
S
c
i
e
n
c
e
s
,
v
o
l
.
5
5
,
n
o
.
1
,
p
p
.
1
1
9
–
1
3
9
,
A
u
g
.
1
9
9
7
,
d
o
i
:
1
0
.
1
0
0
6
/
j
c
ss.
1
9
9
7
.
1
5
0
4
.
AP
P
E
NDI
X
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
C
o
m
p
a
r
is
o
n
o
f
AUC v
alu
es f
o
r
t
h
e
wr
ap
p
er
-
b
ased
FS
m
eth
o
d
s
ac
r
o
s
s
th
e
d
if
f
er
e
n
t d
atasets
,
(
a)
th
e
co
m
p
ar
ativ
e
AUC v
alu
es o
n
C
M1
,
(
b
)
th
e
co
m
p
ar
ativ
e
AUC v
alu
es o
n
KC
1
,
(
c)
th
e
co
m
p
ar
ativ
e
AUC v
alu
es o
n
KC
2
,
(
d
)
th
e
c
o
m
p
ar
ativ
e
AUC v
alu
es o
n
PC
1
(
C
o
n
tin
u
e
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
s
o
ftw
a
r
e
fa
u
lt p
r
ed
ictio
n
u
s
in
g
w
r
a
p
p
er
-
b
a
s
ed
m
eta
h
eu
r
is
tic
…
(
Ha
Th
i Min
h
P
h
u
o
n
g
)
4811
(
e)
(f)
(
g
)
(
h
)
(
i)
Fig
u
r
e
2.
C
o
m
p
ar
is
o
n
of
AUC
v
alu
es
f
o
r
th
e
wr
a
p
p
er
-
b
ased
FS
m
eth
o
d
s
ac
r
o
s
s
th
e
d
if
f
er
en
t
d
a
t
a
s
e
ts
,
(
e)
t
he
co
m
p
ar
ativ
e
AUC
v
alu
es
on
E
Q
,
(
f
)
t
he
c
o
m
p
ar
ativ
e
AUC
v
alu
es
on
J
D
T
,
(
g
)
t
h
e
co
m
p
ar
ativ
e
AUC
v
alu
es o
n
L
u
ce
n
e
,
(
h
)
t
h
e
co
m
p
ar
ativ
e
AUC v
alu
es o
n
My
ly
n
,
(
i)
t
he
co
m
p
ar
ativ
e
AUC
v
al
u
es
on
P
D
E
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
a
Th
i
Mi
n
h
Ph
u
o
n
g
re
c
e
iv
e
d
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
i
n
fo
r
m
a
ti
o
n
tec
h
n
o
lo
g
y
fro
m
Th
e
U
n
iv
e
rsit
y
o
f
Da
n
a
n
g
-
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
in
2
0
1
0
.
S
h
e
e
a
rn
e
d
M
.
S
c
.
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
t
Yu
a
n
Ze
U
n
iv
e
rsit
y
,
Taiwa
n
in
2
0
1
3
.
S
h
e
is
a
lec
tu
re
r
a
t
Th
e
Un
i
v
e
rsity
o
f
Da
n
a
n
g
-
Vie
t
n
a
m
-
Ko
re
a
Un
iv
e
rsity
o
f
In
f
o
r
m
a
ti
o
n
a
n
d
C
o
m
m
u
n
ica
ti
o
n
Tec
h
n
o
l
o
g
y
.
S
h
e
is
c
u
rre
n
tl
y
p
u
rs
u
in
g
a
P
h
.
D
.
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
t
th
e
Un
iv
e
rsity
o
f
Da
n
a
n
g
.
He
r
c
u
rre
n
t
re
se
a
rc
h
fo
c
u
se
s
o
n
so
ftwa
re
tes
ti
n
g
,
d
e
e
p
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
tmp
h
u
o
n
g
@
v
k
u
.
u
d
n
.
v
n
.
Da
n
g
Th
i
K
i
m
Ng
a
n
g
ra
d
u
a
ted
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
in
f
o
rm
a
ti
o
n
m
a
n
a
g
e
m
e
n
t
a
t
th
e
Un
i
v
e
rsity
o
f
Da
n
a
n
g
-
U
n
iv
e
r
sity
o
f
Eco
n
o
m
ics
i
n
2
0
1
1
.
S
h
e
g
o
t
M
S
c
d
e
g
re
e
o
f
a
t
Ch
i
n
e
se
Cu
lt
u
re
U
n
iv
e
rsit
y
,
Taiwa
n
i
n
2
0
1
4
.
S
h
e
is
c
u
rre
n
tl
y
se
rv
in
g
a
s
a
l
e
c
tu
re
r
a
t
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
,
Th
e
Un
i
v
e
rsi
ty
o
f
Da
n
a
n
g
-
Vie
t
n
a
m
-
Ko
re
a
Un
iv
e
rsity
o
f
In
f
o
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
Tec
h
n
o
l
o
g
y
.
H
e
r
re
se
a
rc
h
fo
c
u
se
s
o
n
so
f
twa
re
e
n
g
i
n
e
e
rin
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
t
k
n
g
a
n
@
v
k
u
.
u
d
n
.
v
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
8
0
3
-
4
8
1
2
4812
Da
o
K
h
a
n
h
Duy
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
Ba
c
h
e
lo
r
of
E
n
g
in
e
e
rin
g
at
Th
e
Un
iv
e
rsity
of
D
a
n
a
n
g
Vie
tn
a
m
-
Ko
re
a
Un
iv
e
rsity
o
f
I
n
fo
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
Tec
h
n
o
l
o
g
y
.
He
h
a
s
b
e
e
n
g
a
in
i
n
g
v
a
l
u
a
b
le
h
a
n
d
s
-
o
n
e
x
p
e
rien
c
e
i
n
re
se
a
rc
h
a
n
d
d
e
v
e
l
o
p
m
e
n
t
th
ro
u
g
h
in
ter
n
sh
i
p
s
a
t
Kin
g
M
o
n
g
k
u
t’s
Un
iv
e
rsit
y
o
f
Tec
h
n
o
l
o
g
y
No
rth
Ba
n
g
k
o
k
a
n
d
M
G
M
tec
h
n
o
l
o
g
y
p
a
rt
n
e
rs.
His
c
u
rre
n
t
re
se
a
rc
h
fo
c
u
se
s
o
n
so
ftwa
re
tes
ti
n
g
a
n
d
so
ftwa
re
e
ffo
r
t
e
stim
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
u
y
d
k
.
2
2
g
it
@v
k
u
.
u
d
n
.
v
n
.
N
g
u
y
e
n
T
h
a
n
h
B
i
n
h
g
ra
d
u
a
ted
in
i
n
fo
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
fr
o
m
th
e
Un
iv
e
rsit
y
o
f
Da
n
a
n
g
-
Un
i
v
e
rsity
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
i
n
1
9
9
7
.
He
re
c
e
iv
e
d
P
h
D.
d
e
g
re
e
in
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
t
G
re
n
o
b
le
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
,
F
r
a
n
c
e
in
2
0
0
4
.
He
h
a
s
b
e
e
n
q
u
a
li
fied
a
s
As
so
c
iate
P
ro
fe
ss
o
r
sin
c
e
2
0
1
3
.
He
is
c
u
rre
n
tl
y
wo
rk
i
n
g
a
t
t
h
e
Un
i
v
e
rsity
o
f
Da
n
a
n
g
-
Vie
tn
a
m
-
Ko
re
a
Un
iv
e
rs
it
y
o
f
I
n
fo
rm
a
ti
o
n
a
n
d
C
o
m
m
u
n
ica
ti
o
n
Tec
h
n
o
l
o
g
y
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
s
o
ftwa
re
e
n
g
in
e
e
rin
g
a
n
d
s
o
ftwa
re
q
u
a
l
it
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
tb
i
n
h
@
v
k
u
.
u
d
n
.
v
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.