I
n
t
e
r
n
at
ion
al
Jou
r
n
a
l
of
I
n
f
o
r
m
at
ics
an
d
Com
m
u
n
icat
ion
T
e
c
h
n
ol
ogy
(
I
J
-
I
CT
)
Vo
l
.
13
,
N
o
.
3
,
De
c
e
m
b
e
r
20
24
,
pp.
344
~
353
I
S
S
N:
2252
-
8776
,
DO
I
:
10
.
11591/i
ji
c
t
.
v
13
i
3
.
pp
34
4
-
353
344
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
ict
.
iaes
c
or
e
.
c
om
Op
t
i
m
i
z
e
d
s
u
p
p
or
t
ve
c
t
or
m
a
c
h
in
e
f
or
se
n
t
im
e
n
t
a
n
al
y
si
s o
f
g
a
m
e
r
e
v
ie
w
s
B
r
yan
L
e
on
ar
d
o
S
u
p
r
iyat
n
a
,
F
ar
ica
P
e
r
d
an
a
P
u
t
r
i
D
e
pa
r
tm
e
nt
of
I
n
f
or
ma
ti
c
s
,
F
a
c
ul
t
y
of
E
ngi
n
e
e
r
in
g a
nd I
n
f
or
ma
ti
c
s
,
U
ni
v
e
r
s
it
a
s
M
ul
ti
me
di
a
N
us
a
nt
a
r
a
, T
a
nge
r
a
ng, I
nd
o
n
e
s
ia
Ar
t
ic
l
e
I
n
fo
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
J
a
n
8,
2024
R
e
vi
s
e
d
M
a
y
11,
2024
A
c
c
e
pt
e
d
J
un
18,
2024
T
h
e
rap
i
d
d
ev
e
l
o
p
men
t
o
f
g
a
me
s
h
as
m
a
d
e
g
a
m
e
c
at
eg
o
ri
e
s
d
i
v
e
rs
e
,
s
o
t
h
e
r
e
are
m
a
n
y
o
p
i
n
i
o
n
s
ab
o
u
t
g
a
me
s
t
h
at
h
av
e
b
ee
n
r
el
e
as
ed
.
Sen
t
i
me
n
t
an
a
l
y
s
i
s
o
n
g
a
me
r
ev
i
ew
s
i
s
n
eed
e
d
t
o
at
t
rac
t
p
o
t
e
n
t
i
a
l
p
l
a
y
ers
.
Sen
t
i
m
en
t
an
a
l
y
s
i
s
i
s
c
arri
ed
o
u
t
u
s
i
n
g
t
h
e
s
u
p
p
o
rt
v
ec
t
o
r
m
a
c
h
i
n
e
(S
V
M)
an
d
p
art
i
c
l
e
s
w
ar
m
o
p
t
i
mi
zat
i
o
n
(PSO
)
al
g
o
r
i
t
h
m
s
.
SV
M
t
rai
n
i
n
g
w
as
c
o
n
d
u
c
t
ed
w
i
t
h
a
l
i
n
e
ar
k
e
r
n
e
l
,
t
h
e
‘
C
’
v
a
l
u
e
p
ara
me
t
e
r
w
as
1
0
re
s
u
l
t
i
n
g
i
n
a
n
a
cc
u
ra
cy
v
a
l
u
e
o
f
9
7
.
2
8
%
.
T
h
e
S
V
M
a
l
g
o
ri
t
h
m
o
p
t
i
mi
z
e
d
u
s
i
n
g
t
h
e
PSO
me
t
h
o
d
p
ro
d
u
ce
s
an
acc
u
ra
cy
o
f
9
7
.
6
1
%
u
s
i
n
g
t
h
e
p
arame
t
e
rs
c
1
i
s
0
.
2
,
c
2
i
s
0
.
5
an
d
w
i
s
0
.
6
.
Bas
e
d
o
n
t
h
e
s
e
r
e
s
u
l
t
s
,
s
e
n
t
i
men
t
an
a
l
y
s
i
s
u
s
i
n
g
PSO
-
b
as
e
d
SV
M
o
p
t
i
mi
zat
i
o
n
h
as
b
ee
n
s
u
cce
s
s
fu
l
l
y
c
arr
i
e
d
o
u
t
w
i
t
h
an
i
n
c
r
e
as
e
i
n
a
ccu
ra
cy
o
f
0
.
3
3
%
.
T
h
i
s
g
a
me
r
ev
i
ew
h
as
a
s
e
n
t
i
men
t
v
a
l
u
e
fr
o
m
n
e
u
t
ral
t
o
p
o
s
i
t
i
v
e
s
o
t
h
i
s
g
a
me
c
a
n
b
e
r
ec
o
mmen
d
ed
t
o
o
t
h
e
r
p
l
a
y
e
rs
.
K
e
y
w
o
r
d
s
:
Ga
m
e
r
e
vi
e
w
P
a
r
t
i
c
l
e
s
wa
r
m
o
pt
i
mi
z
a
t
i
o
n
S
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
S
uppor
t
v
e
c
to
r
m
a
c
hi
ne
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
F
a
r
i
c
a
P
e
r
da
n
a
P
ut
r
i
De
pa
r
t
m
e
n
t
o
f
I
nf
o
r
m
a
t
i
c
s
,
F
a
c
u
l
t
y
o
f
E
n
g
i
ne
e
r
i
n
g
a
n
d
I
nf
o
r
m
a
t
i
c
s
,
U
ni
ve
r
s
i
t
a
s
M
u
l
t
im
e
d
i
a
Nus
a
n
t
a
r
a
T
a
n
ge
r
a
n
g,
I
n
do
n
e
s
i
a
E
m
a
i
l
:
f
a
r
i
c
a
@
u
m
n
.
a
c
.
i
d
1.
I
NT
RODU
C
T
I
ON
I
n
t
hi
s
da
y
a
n
d
a
ge
whe
r
e
pe
o
pl
e
a
r
e
l
o
o
ki
n
g
f
o
r
f
o
r
m
s
o
f
e
n
t
e
r
t
a
i
nm
e
n
t
,
m
a
ny
a
r
e
t
ur
ni
n
g
t
o
ga
m
i
ng
t
o
r
e
l
i
e
v
e
t
h
e
da
il
y
gr
i
nd.
T
h
e
pa
n
de
mi
c
p
e
r
i
o
d
i
s
a
l
s
o
a
n
i
m
po
r
t
a
n
t
f
a
c
t
or
i
n
t
h
e
s
ur
ge
i
n
t
h
e
n
u
m
be
r
o
f
ga
m
e
r
s
.
R
e
c
e
n
t
l
y
,
us
e
r
s
o
f
S
t
e
a
m
,
whi
c
h
i
s
t
h
e
l
a
r
ge
s
t
ga
m
e
b
u
yi
ng
a
n
d
s
e
ll
i
ng
po
r
t
a
l
f
o
r
c
o
m
put
e
r
us
e
r
s
to
pl
a
y
ga
m
e
s
o
f
f
i
c
i
a
ll
y
,
b
r
o
ke
a
n
e
w
r
e
c
o
r
d
o
f
r
e
a
c
hi
n
g
30
m
i
ll
i
o
n
pe
o
pl
e
w
h
o
o
pe
n
e
d
t
h
e
a
ppl
ica
t
i
o
n
i
n
202
2
S
t
e
a
m
a
c
c
o
r
di
n
g
to
t
h
e
i
m
a
g
i
ne
ga
m
e
s
ne
t
wor
k
(
I
GN
)
we
b
s
i
t
e
[
1]
.
T
h
e
r
a
p
i
d
de
ve
l
o
p
m
e
n
t
o
f
ga
m
e
s
h
a
s
l
e
d
to
a
v
a
r
i
e
t
y
o
f
ga
m
e
c
a
t
e
g
o
r
i
e
s
,
s
o
t
h
e
r
e
a
r
e
m
a
ny
o
pi
ni
o
ns
o
n
ga
m
e
s
t
h
a
t
h
a
v
e
b
e
e
n
r
e
l
e
a
s
e
d.
P
l
a
y
e
r
s
w
i
ll
l
o
o
k
a
t
r
e
vi
e
ws
f
i
r
s
t
b
e
f
o
r
e
t
r
y
i
ng
t
o
pl
a
y
t
h
e
ga
m
e
,
s
o
t
h
a
t
t
h
e
t
i
m
e
t
h
e
y
h
a
v
e
s
p
e
n
t
i
s
n
o
t
wa
s
t
e
d
.
T
h
e
pr
i
c
e
o
f
g
a
m
e
s
t
h
a
t
c
o
n
t
i
n
ue
s
to
s
o
a
r
un
t
i
l
n
o
w
c
a
n
r
e
a
c
h
6
9.
99
US
do
l
l
a
r
s
a
c
c
o
r
di
n
g
t
o
t
h
e
K
o
t
a
ku
we
b
s
i
t
e
[
2]
i
n
2022.
T
h
e
pr
i
c
e
a
l
s
o
a
f
f
e
c
t
s
t
h
e
pur
c
h
a
s
e
o
f
a
ga
m
e
.
T
h
e
r
e
n
e
e
d
s
to
b
e
s
o
m
e
t
hi
n
g
t
h
a
t
c
a
n
h
e
l
p
de
t
e
r
m
in
e
whe
t
h
e
r
t
h
e
ga
m
e
i
s
f
e
a
s
i
b
l
e
a
n
d
i
n
a
c
c
o
r
da
n
c
e
w
i
t
h
t
h
e
i
n
t
e
r
e
s
t
s
o
f
t
h
e
pl
a
y
e
r
.
T
h
e
r
e
f
o
r
e
,
a
r
a
t
i
n
g
s
y
s
t
e
m
i
s
n
e
e
de
d
t
h
a
t
c
a
n
r
e
vi
e
w
t
h
e
e
x
pe
r
i
e
n
c
e
s
o
f
ot
h
e
r
pl
a
y
e
r
s
wh
o
h
a
v
e
p
l
a
y
e
d
t
h
e
ga
m
e
to
f
i
n
d
o
u
t
wh
e
t
h
e
r
t
h
e
ga
m
e
c
a
n
b
e
r
e
c
o
m
m
e
n
de
d
o
r
n
ot
.
R
e
vi
e
ws
o
n
ga
m
e
s
a
r
e
v
e
r
y
us
e
f
u
l
i
n
h
e
l
p
i
ng
p
l
a
y
e
r
s
c
h
o
o
s
e
whi
c
h
ga
m
e
to
b
u
y
,
t
hi
s
i
s
e
vi
de
n
c
e
d
by
t
h
e
i
n
t
e
r
a
c
t
i
o
n
o
f
po
s
i
t
i
ve
a
nd
n
e
ga
t
i
v
e
r
e
vi
e
ws
a
f
f
e
c
t
i
n
g
81%
o
f
p
l
a
y
e
r
s
[
3]
.
S
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
r
o
pi
ni
o
n
m
i
n
i
ng
i
s
t
h
e
c
o
m
put
a
t
i
o
n
a
l
s
t
ud
y
o
f
pe
o
pl
e
'
s
o
p
i
ni
o
n
s
,
s
e
n
t
i
m
e
n
t
s
,
e
m
o
t
i
o
n
s
,
a
n
d
a
t
t
i
t
ude
s
to
wa
r
ds
a
n
e
n
t
i
t
y
s
uc
h
a
s
a
pr
o
duc
t
,
s
e
r
vi
c
e
,
i
s
s
ue
,
e
ve
n
t
,
to
pi
c
,
a
n
d
i
t
s
a
tt
r
i
b
ut
e
s
[
4]
.
T
h
us
,
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
a
ll
o
w
s
t
r
a
c
ki
n
g
t
h
e
pu
bli
c
m
o
o
d
a
b
o
u
t
a
pa
r
t
i
c
u
l
a
r
e
n
t
i
t
y
t
o
c
r
e
a
t
e
a
c
t
i
o
n
a
bl
e
kn
o
w
l
e
dge
[
5]
,
[
6]
.
B
y
a
ll
o
w
i
ng
us
e
r
s
to
a
c
t
i
v
e
ly
e
n
ga
g
e
i
n
de
f
i
n
i
ng
t
h
e
pr
o
duc
t
r
e
qu
i
r
e
m
e
n
t
s
t
h
r
o
u
gh
t
h
e
i
r
i
nput
,
e
n
d
us
e
r
s
m
a
y
b
e
a
bl
e
to
c
o
n
t
r
i
b
ut
e
v
a
l
u
a
bl
e
i
ns
i
g
h
t
s
i
n
t
o
r
e
qui
r
e
m
e
n
t
s
f
o
r
s
pe
c
i
f
i
c
pr
o
duc
t
s
,
whi
c
h
c
o
ul
d
b
e
a
d
v
a
n
t
a
ge
o
us
to
pr
o
duc
t
o
wn
e
r
s
a
n
d
e
ng
i
n
e
e
r
s
[
7]
.
S
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
c
a
n
be
do
n
e
wi
t
h
s
e
v
e
r
a
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
Optimiz
e
d
s
uppor
t
v
e
c
tor
mac
hine
f
or
s
e
nti
me
nt
analys
is
of
game
r
e
v
ie
w
s
(
B
r
y
an
L
e
onar
do
Supr
iyat
na
)
345
m
e
t
h
o
ds
,
b
ut
t
h
e
m
o
s
t
p
o
pul
a
r
o
n
e
s
a
r
e
Na
i
ve
B
a
y
e
s
(
NB
)
,
r
a
n
do
m
f
o
r
e
s
t
(
R
F
)
,
K
-
n
e
a
r
e
s
t
n
e
i
g
hb
o
r
s
(
K
NN
)
,
de
c
i
s
t
i
o
n
tr
e
e
(
D
T
)
,
l
o
gi
s
t
i
c
r
e
gr
e
s
s
i
o
n
(L
R
)
,
a
n
d
s
uppo
r
t
v
e
c
to
r
m
a
c
hi
ne
(
S
VM
)
.
S
VM
i
s
a
po
pul
a
r
c
l
a
s
s
if
i
e
r
b
e
c
a
us
e
o
f
i
t
s
a
bil
i
t
y
t
o
de
l
i
ve
r
hi
g
h
e
r
ge
n
e
r
a
li
z
a
t
i
o
n
pe
r
f
o
r
m
a
n
c
e
w
h
e
n
t
h
e
i
n
put
f
e
a
t
ur
e
s
s
pa
c
e
h
a
s
a
hi
g
h
-
d
i
m
e
ns
i
o
n
e
m
be
dd
i
ng
[
8]
.
T
h
e
b
a
s
i
c
i
de
a
be
hi
nd
S
VM
i
s
t
o
c
a
t
e
g
o
r
i
z
e
i
n
f
o
r
m
a
t
i
o
n
s
e
pa
r
a
t
e
ly
us
i
ng
hy
pe
r
p
l
a
n
e
s
to
m
a
xi
mi
z
e
t
h
e
m
a
r
g
i
n
b
e
t
we
e
n
t
h
e
m.
M
a
ny
s
tu
d
i
e
s
h
a
v
e
us
e
d
m
a
c
hi
n
e
l
e
a
r
ni
n
g
a
pp
r
oa
c
h
e
s
to
d
e
tec
t
th
e
s
e
n
t
i
m
e
n
t
o
f
a
g
a
m
e
.
A
s
tu
dy
by
[
9
]
us
e
d
S
VM
to
c
l
a
s
s
if
y
s
e
n
t
i
m
e
n
t
o
n
ga
m
e
r
e
vi
e
w
s
o
r
i
g
i
na
t
i
n
g
f
r
o
m
t
h
e
S
t
e
a
m
o
nl
i
ne
p
l
a
t
f
o
r
m
.
T
h
e
r
e
s
u
l
t
s
o
b
t
a
i
n
e
d
t
h
e
hi
g
h
e
s
t
a
c
c
ur
a
c
y
r
e
a
c
he
d
97%
.
S
e
nt
i
m
e
n
t
a
n
a
ly
s
i
s
o
n
ga
m
e
r
e
vi
e
w
s
to
e
v
a
l
ua
t
e
vi
d
e
o
ga
m
e
a
c
c
e
pt
a
n
c
e
wa
s
c
o
n
duc
t
e
d
by
[
10]
us
i
ng
P
o
r
t
ug
ue
s
e
B
r
a
li
z
il
i
a
n
l
a
n
gua
ge
.
S
e
v
e
r
a
l
c
l
a
s
s
i
f
i
e
r
s
a
r
e
us
e
d
in
de
t
e
c
t
i
n
g
s
e
n
t
i
m
e
n
t
,
n
a
m
e
ly
LR
,
S
VM
,
a
n
d
RF
.
B
a
s
e
d
o
n
t
h
e
e
x
pe
r
i
m
e
n
t
r
e
s
u
l
t
s
,
i
t
wa
s
f
o
un
d
t
h
a
t
S
VM
m
a
n
a
ge
d
t
o
ge
t
t
h
e
b
e
s
t
pe
r
f
o
r
m
a
n
c
e
s
f
o
r
a
l
l
f
o
ur
m
e
t
r
i
c
s
:
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
o
n
,
r
e
c
a
l
l
,
a
n
d
F
1
-
s
c
o
r
e
,
wi
t
h
a
n
a
c
c
ur
a
c
y
o
f
82.
54%
.
M
e
a
n
w
hil
e
,
L
R
a
n
d
R
F
ge
t
th
e
s
e
c
o
n
d
a
n
d
t
hi
r
d
po
s
i
t
i
o
ns
,
r
e
s
pe
c
t
i
v
e
ly
.
L
R
pr
oduc
e
s
a
n
a
v
e
r
a
ge
a
c
c
ur
a
c
y
o
f
82.
40%
a
n
d
R
F
o
f
79.
89%
.
A
c
o
m
pa
r
a
t
i
ve
s
t
udy
o
n
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
o
n
ga
m
e
r
e
vi
e
ws
wa
s
c
o
n
duc
t
e
d
by
T
a
n
e
t
al.
[
11]
. S
e
v
e
r
a
l
m
a
c
hi
n
e
l
e
a
r
ni
ng
a
l
go
r
i
t
hm
s
a
r
e
us
e
d,
i
nc
l
ud
i
ng
S
VM
,
m
u
l
t
i
-
l
a
y
e
r
pe
r
c
e
pt
r
o
n
(
M
L
P
)
,
e
x
tr
e
m
e
gr
a
d
i
e
n
t
b
o
o
s
t
i
n
g
(
XG
B
)
,
L
R
,
a
n
d
m
u
l
t
i
n
o
mi
a
l
Na
ï
ve
B
a
y
e
s
(
M
NB
)
.
I
n
c
o
m
pa
r
i
s
o
n
to
t
h
e
f
i
ve
a
l
go
r
i
t
hm
s
,
S
VM
h
a
s
91%
a
c
c
ur
a
c
y
b
e
c
a
u
s
e
S
VM
pe
r
f
o
r
m
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
b
a
s
e
d
o
n
hy
pe
r
p
l
a
n
e
s
r
a
t
h
e
r
t
h
a
n
pr
o
b
a
bil
i
t
i
e
s
whi
c
h
i
s
m
o
r
e
s
ui
t
a
bl
e
f
o
r
t
e
x
t
c
l
a
s
s
if
i
c
a
t
i
o
n
w
i
t
h
a
l
a
r
ge
nu
m
b
e
r
o
f
f
e
a
t
ur
e
s
.
S
VM
a
l
s
o
pr
o
duc
e
d
c
o
m
pe
t
i
t
i
ve
a
c
c
ur
a
c
y
w
i
t
h
M
NB
a
n
d
de
e
p
n
e
ur
a
l
n
e
t
wo
r
k
(
DN
N)
i
n
[
12]
in
c
l
a
s
s
if
yi
ng
s
e
n
t
i
m
e
n
t
i
n
ga
m
e
r
e
vi
e
ws
.
T
e
r
m
f
r
e
q
ue
n
c
y
a
n
d
i
nve
r
s
e
do
c
u
m
e
n
t
f
r
e
que
n
c
y
(
TF
-
I
DF
)
a
n
d
b
a
g
o
f
wo
r
ds
(
B
o
W
)
a
r
e
us
e
d
a
s
d
o
c
um
e
n
t
r
e
pr
e
s
e
n
t
a
t
i
o
n
f
o
r
S
VM
a
n
d
M
NB
,
whi
l
e
de
e
p
a
v
e
r
a
g
i
ng
n
e
t
wo
r
k
(
DA
N)
a
n
d
t
r
a
n
s
f
o
r
m
e
r
a
r
e
us
e
d
f
o
r
DN
N.
E
v
o
l
ut
i
o
n
a
r
y
a
l
go
r
i
t
hm
s
(
E
As
)
a
r
e
a
t
y
pe
o
f
o
pt
i
mi
z
a
t
i
o
n
a
l
go
r
i
t
hm
i
ns
p
i
r
e
d
by
n
a
t
ur
a
l
s
e
l
e
c
t
i
o
n
a
n
d
Da
r
w
i
ni
a
n
s
ur
vi
va
l
o
f
t
h
e
f
i
t
t
e
s
t
.
T
h
e
y
a
r
e
i
n
t
e
n
de
d
to
s
o
l
v
e
o
p
t
i
mi
z
a
t
i
o
n
a
n
d
s
e
a
r
c
h
i
s
s
ue
s
by
s
im
u
l
a
t
i
n
g
na
t
ur
a
l
s
e
l
e
c
t
i
o
n
,
ge
n
e
t
i
c
r
e
c
o
m
bi
na
t
i
o
n
,
a
n
d
m
ut
a
t
i
o
n
.
E
A
s
h
a
v
e
b
e
e
n
w
i
de
ly
a
pp
l
i
e
d
to
v
a
r
i
o
us
o
p
t
i
mi
z
a
t
i
o
n
pr
o
bl
e
m
s
,
s
u
c
h
a
s
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
,
f
u
n
c
t
i
o
n
o
pt
i
mi
z
a
t
i
o
n
,
a
n
d
pa
r
a
m
e
t
e
r
t
uni
n
g
i
n
m
a
c
hi
ne
l
e
a
r
ni
ng.
S
e
v
e
r
a
l
E
A
s
ut
i
li
z
e
d
t
o
o
p
t
i
mi
z
e
d
t
h
e
S
VM
a
r
e
ge
n
e
t
i
c
a
lgo
r
i
t
hm
(
GA
)
[
13]
,
pa
r
t
i
c
l
e
s
wa
r
m
o
pt
i
m
i
z
a
t
i
o
n
(
P
S
O)
[
14]
,
a
n
d
a
n
t
c
o
l
o
ny
o
pt
i
m
i
z
a
t
i
o
n
(
A
C
O)
[
15]
.
T
h
e
P
S
O
m
e
t
h
o
do
l
o
g
y
a
ll
o
ws
f
o
r
n
u
m
e
r
o
us
o
p
t
i
m
i
z
a
t
i
o
n
m
e
t
h
o
ds
,
i
n
c
l
ud
i
ng
r
a
i
s
i
ng
t
h
e
a
tt
r
i
b
ut
e
we
i
g
ht
o
f
a
ll
a
tt
r
i
b
ut
e
s
o
r
v
a
r
i
a
bl
e
s
us
e
d,
s
e
l
e
c
t
i
n
g
a
tt
r
i
b
ut
e
s
,
a
n
d
s
e
l
e
c
t
i
n
g
f
e
a
t
ur
e
s
.
T
hi
s
s
t
ud
y
i
nv
e
s
t
i
ga
t
e
d
t
h
e
e
f
f
e
c
t
s
o
f
P
S
O
f
o
r
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
to
o
p
t
i
mi
z
e
S
VM
i
n
ga
m
e
r
e
vi
e
w
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
,
w
hil
e
a
ll
t
h
e
a
f
o
r
e
m
e
n
t
i
o
n
e
d
s
t
udi
e
s
f
o
c
us
o
n
wor
d
r
e
p
r
e
s
e
n
t
a
t
i
o
n
a
n
d
S
VM
to
c
l
a
s
s
if
y
t
h
e
s
e
n
t
i
m
e
n
t
.
2.
RE
S
E
AR
CH
M
E
T
HO
D
T
h
e
m
e
t
h
o
do
l
o
g
y
o
f
t
hi
s
s
t
ud
y
c
o
n
s
i
s
t
s
o
f
s
e
v
e
r
a
l
s
t
e
ps
a
n
d
i
s
pr
e
s
e
n
t
e
d
i
n
t
hi
s
s
e
c
t
i
o
n
.
T
h
e
s
t
e
ps
i
nc
l
ude
da
t
a
de
s
c
r
i
pt
i
o
n
a
n
d
c
o
l
l
e
c
t
i
o
n
,
da
t
a
pr
e
pa
r
a
t
i
o
n
,
a
n
d
t
h
e
pr
o
po
s
e
d
m
e
t
h
o
d.
E
a
c
h
o
f
t
h
e
s
e
s
t
e
ps
i
s
de
s
c
r
i
be
d
i
n
de
t
a
i
l
.
2.
1.
Dat
a
d
e
s
c
r
ip
t
ion
an
d
c
ol
l
e
c
t
ion
T
h
e
da
t
a
u
t
i
li
z
e
d
i
n
t
hi
s
st
u
d
y
i
s
a
r
e
vi
e
w
o
f
B
a
l
dur
’
s
Ga
t
e
3
a
f
t
e
r
pa
t
c
h
5,
da
t
e
d
N
o
v
e
m
b
e
r
30,
2020
.
Da
t
a
c
o
l
l
e
c
t
i
o
n
wa
s
do
n
e
us
i
ng
a
da
t
a
s
e
t
o
f
r
e
vi
e
ws
f
r
o
m
t
h
e
S
t
e
a
m
d
i
g
i
t
a
l
s
t
o
r
e
,
a
s
i
t
r
e
pr
e
s
e
n
t
s
t
h
e
m
a
j
o
r
i
t
y
o
f
c
o
m
put
e
r
pl
a
y
e
r
s
.
T
h
e
da
t
a
wa
s
c
o
l
l
e
c
t
e
d
o
n
K
a
gg
l
e
[
16]
.
T
ot
a
l
da
t
a
di
vi
de
d
i
n
t
o
253,
976
po
s
i
t
i
v
e
r
e
vi
e
w
s
a
n
d
7,
079
n
e
ga
t
i
v
e
r
e
vi
e
ws
.
An
e
x
a
m
p
l
e
o
f
t
h
e
r
e
vi
e
w
da
t
a
us
e
d
i
s
de
s
c
r
i
b
e
d
i
n
T
a
bl
e
1.
T
h
e
c
o
l
u
m
ns
ut
i
li
z
e
d
i
n
t
r
a
i
ni
ng
a
r
e
r
e
vi
e
w
a
n
d
v
o
t
e
d_up
,
whi
l
e
t
i
m
e
s
t
a
m
ps
_
c
r
e
a
t
e
d,
wr
i
tt
e
n
_dur
i
n
g_e
a
r
l
y
_a
c
c
e
s
s
,
a
n
d
r
e
c
e
i
ve
d_
f
o
r
_
f
r
e
e
a
r
e
us
e
d
a
s
pa
r
a
m
e
t
e
r
s
to
f
i
l
t
e
r
t
h
e
da
t
a
.
v
ot
e
d_u
p
w
i
l
l
b
e
T
r
ue
i
f
t
h
e
s
e
n
t
i
m
e
n
t
i
s
po
s
i
t
i
v
e
a
n
d
f
a
l
s
e
i
f
i
t
i
s
n
e
ga
t
i
v
e
.
t
i
m
e
s
t
a
m
p
s
_c
r
e
a
t
e
d
i
s
us
e
d
to
f
il
t
e
r
r
e
vi
e
w
da
t
a
a
f
t
e
r
pa
t
c
h
5.
wr
i
tt
e
n
_dur
i
n
g_e
a
r
l
y
_
a
c
c
e
s
s
i
n
d
i
c
a
t
e
s
t
h
a
t
t
h
e
r
e
vi
e
w
wa
s
wr
i
t
t
e
n
wh
e
n
t
h
e
v
e
r
s
i
o
n
o
f
th
e
ga
m
e
wa
s
s
t
i
ll
a
b
e
t
a
v
e
r
s
i
o
n
a
n
d
n
ot
t
h
e
o
f
f
i
c
i
a
l
v
e
r
s
i
o
n
o
f
t
h
e
ga
m
e
,
t
h
e
r
e
f
o
r
e
t
h
e
r
e
vi
e
w
i
s
o
nly
us
e
d
wh
e
n
wr
i
tt
e
n
_dur
i
n
g_e
a
r
l
y
_a
c
c
e
s
s
i
s
F
a
l
s
e
.
r
e
c
e
i
ve
d_
f
o
r
_f
r
e
e
i
nd
i
c
a
t
e
s
t
h
a
t
t
h
e
g
a
m
e
i
s
a
ga
m
e
t
h
a
t
wa
s
o
b
t
a
i
n
e
d
f
o
r
f
r
e
e
whi
c
h
i
s
l
i
ke
ly
a
ga
m
e
f
r
o
m
a
s
po
n
s
o
r
o
r
gi
f
t
f
r
o
m
t
h
e
publ
i
s
he
r
.
T
h
e
r
e
f
o
r
e
,
to
e
l
i
mi
na
t
e
bi
a
s
f
r
o
m
r
e
vi
e
ws
,
we
o
nl
y
us
e
da
t
a
wh
e
n
r
e
c
e
i
ve
d_
f
o
r
_
f
r
e
e
e
qua
l
s
F
a
l
s
e
.
T
a
bl
e
1.
S
a
m
p
l
e
o
f
ga
m
e
r
e
vi
e
ws
R
e
c
o
mm
e
nda
ti
o
ni
d
R
e
vi
e
w
T
im
e
s
ta
mp_
c
r
e
a
te
d
V
o
t
e
d_up
W
r
it
te
n_dur
in
g_e
a
r
l
y
_a
c
c
e
s
s
R
e
c
e
i
ve
d_
f
o
r
_
f
r
e
e
153560814
G
a
m
e
hi
t
r
ig
ht
ma
r
k
1702542971
T
r
u
e
F
a
ls
e
F
a
ls
e
153560623
T
oo
k
li
ke
h
o
u
r
unde
r
s
ta
nd ba
s
ic
1702542657
T
r
u
e
F
a
ls
e
F
a
ls
e
153560414
G
a
m
e
pl
a
y
s
t
o
r
i
f
ir
s
t
tu
r
n ba
s
e
r
pg
ga
me
lo
ve
f
a
r
1702542275
T
r
u
e
F
a
ls
e
F
a
ls
e
153560343
G
a
l
e
ba
bi
gi
r
l
1702542158
T
r
u
e
F
a
ls
e
F
a
ls
e
153559963
Y
e
s
w
it
ho
ut
f
n d
o
ubt
1702541518
T
r
u
e
F
a
ls
e
F
a
ls
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
13
,
N
o.
3
,
De
c
e
m
be
r
2
0
24
:
344
-
353
346
2.
2.
Dat
a
p
r
e
p
ar
at
ion
Da
t
a
pr
e
pa
r
a
t
i
o
n
c
o
n
s
i
s
t
s
o
f
t
h
r
e
e
ph
a
s
e
s
.
T
h
e
s
e
ph
a
s
e
s
i
n
c
l
ude
da
t
a
p
r
e
-
pr
o
c
e
s
s
i
n
g,
v
e
c
t
o
r
i
z
a
t
i
o
n
us
i
n
g
T
F
-
I
DF
,
a
n
d
da
t
a
s
pl
i
t
t
i
n
g.
F
i
gur
e
1
i
ll
us
t
r
a
tes
t
hi
s
pr
o
c
e
s
s
.
F
i
gur
e
1.
T
h
e
f
l
o
w
o
f
da
t
a
pr
e
pa
r
a
t
i
o
n
2
.
2.
1.
P
r
e
-
p
r
oc
e
s
s
in
g
Af
t
e
r
t
h
e
r
e
vi
e
w
da
t
a
i
s
f
il
t
e
r
e
d
by
r
e
m
o
vi
ng
e
a
r
l
y
a
c
c
e
s
s
r
e
vi
e
w
s
,
t
e
x
t
pr
e
-
p
r
o
c
e
s
s
i
ng
i
s
pe
r
f
o
r
m
e
d
to
c
l
e
a
n
t
h
e
da
t
a
.
F
i
r
s
t
,
t
h
e
t
e
x
t
r
e
vi
e
w
i
s
c
o
nv
e
r
t
e
d
i
n
t
o
l
o
we
r
c
a
s
e
,
t
h
e
n
n
o
t
i
nf
o
r
m
a
t
i
v
e
t
hi
n
gs
s
uc
h
a
s
hy
pe
r
li
nk,
n
u
m
be
r
s
,
e
m
o
t
i
c
o
ns
,
e
x
t
r
a
s
pa
c
e
s
,
punc
t
ua
t
i
o
n
s
a
r
e
r
e
m
o
v
e
d.
S
to
pw
or
ds
or
c
o
m
m
o
n
wo
r
d
s
t
h
a
t
d
o
n
o
t
pr
o
vi
de
i
nf
o
r
m
a
t
i
o
n
,
f
o
r
e
x
a
m
p
l
e
,
c
o
nj
u
n
c
t
i
o
n
s
(
and
,
or
)
a
n
d
n
o
un
s
(
is
,
w
e
r
e
,
w
a
s
)
,
a
r
e
a
l
s
o
r
e
m
o
v
e
d.
T
h
e
n
,
t
h
e
r
e
vi
e
w
s
e
n
t
e
nc
e
s
a
r
e
a
l
s
o
s
e
pa
r
a
t
e
d
wor
d
-
by
-
wo
r
d
i
n
to
to
ke
n
s
or
i
t
i
s
c
a
ll
e
d
to
k
e
ni
z
a
t
i
o
n
.
I
n
a
dd
i
t
i
o
n
to
f
a
c
il
i
t
a
t
i
n
g
pr
e
d
i
c
t
i
o
n
,
t
hi
s
pha
s
e
is
a
l
s
o
us
e
d
f
o
r
t
h
e
s
t
e
m
mi
ng
pr
o
c
e
s
s
,
wh
e
r
e
t
h
e
a
f
f
i
xe
d
wo
r
ds
wi
ll
b
e
c
o
nv
e
r
t
e
d
i
n
t
o
t
h
e
i
r
r
oot
w
o
r
ds
.
1.
T
h
e
r
e
s
u
l
t
o
f
s
t
e
m
mi
ng
i
s
uni
qu
e
wor
d
s
e
t
whi
c
h
i
s
e
x
pe
c
t
e
d
to
i
m
pr
o
v
e
t
h
e
a
c
c
ur
a
c
y
o
f
t
h
e
m
o
de
l
[
17]
.
T
h
e
e
m
pt
y
d
a
t
a
a
f
t
e
r
pr
e
-
pr
o
c
e
s
s
i
n
g
i
s
c
o
nv
e
r
t
e
d
to
t
h
e
e
m
pt
y
s
t
r
i
n
g
(
“
”
)
a
n
d
t
h
e
e
m
pt
y
s
t
r
i
n
g
i
s
r
e
m
o
v
e
d.
T
a
bl
e
2
s
h
o
ws
t
h
e
r
e
s
u
l
t
o
f
t
e
x
t
r
e
vi
e
w
s
b
e
f
o
r
e
a
n
d
a
f
t
e
r
t
h
e
pr
e
-
pr
o
c
e
s
s
i
n
g
s
t
e
p.
T
a
bl
e
2.
T
h
e
r
e
s
u
l
t
s
o
f
pr
e
-
pr
o
c
e
s
s
i
n
g
s
t
e
p
T
e
x
t
r
e
v
i
e
w
b
e
f
or
e
p
r
e
-
pr
oc
e
s
s
in
g
T
e
x
t
r
e
v
i
e
w
a
f
t
e
r
p
r
e
-
pr
oc
e
s
s
in
g
T
h
is
ga
me
hi
ts
a
ll
t
he
r
ig
ht
ma
r
ks
. 10/
10
G
a
m
e
hi
t
r
ig
ht
ma
r
k
T
oo
k
me
l
ik
e
11 h
o
u
r
s
t
o
und
e
r
s
ta
nd t
h
e
ba
s
ic
s
T
oo
k
li
ke
h
o
u
r
unde
r
s
ta
nd ba
s
ic
10/
10 ga
me
pl
a
y
a
nd s
to
r
y
!
I
t
’
s
m
y
f
ir
s
t
tu
r
n ba
s
e
d r
pg ga
m
e
, a
nd I
ha
ve
be
e
n
L
ovi
ng i
t
s
o
f
a
r
:
D
G
a
m
e
pl
a
y
s
t
o
r
i
f
ir
s
t
tu
r
n ba
s
e
r
pg ga
me
L
ove
f
a
r
G
a
l
e
i
s
s
o
ba
b
y
gi
r
l
G
a
l
e
ba
bi
gi
r
l
Y
E
S
,
\
n
\
nW
I
T
H
O
U
T
A
F
****
N
D
O
U
B
T
.
Y
e
s
w
it
ho
ut
f
n d
o
ubt
T
h
e
r
e
vi
e
w
da
t
a
i
s
a
l
s
o
de
p
i
c
t
e
d
us
i
n
g
a
wo
r
d
c
l
o
ud,
whi
c
h
a
im
s
t
o
p
r
o
vi
d
e
a
bi
g
p
i
c
t
ur
e
o
f
po
s
i
t
i
v
e
a
n
d
n
e
ga
t
i
v
e
r
e
vi
e
ws
.
F
i
gur
e
2
s
h
o
ws
t
h
e
wo
r
d
c
l
o
ud
o
f
t
h
e
r
e
vi
e
w
da
t
a
.
F
i
gur
e
2(
a
)
i
s
a
wo
r
d
c
l
o
ud
o
f
po
s
i
t
i
v
e
r
e
vi
e
w
wo
r
ds
a
n
d
i
t
c
a
n
b
e
s
e
e
n
t
h
a
t
t
h
e
e
x
a
m
p
l
e
s
o
f
wor
ds
t
h
a
t
a
ppe
a
r
m
o
s
t
o
f
t
e
n
a
r
e
“
b
e
s
t
ga
m
e
”
,
“
b
a
l
dur
ga
t
e
”
,
“
gr
e
a
t
ga
m
e
”
a
n
d
“
o
n
e
b
e
s
t
”
.
F
i
gur
e
2(
b
)
i
s
t
h
e
wo
r
d
c
l
o
ud
o
f
n
e
g
a
t
i
ve
r
e
vi
e
w
s
a
n
d
s
o
m
e
o
f
t
h
e
wor
ds
t
h
a
t
a
ppe
a
r
f
r
e
que
n
t
l
y
a
r
e
“
c
o
m
b
a
t
”
,
“
ga
m
e
”
,
“
b
ug
”
a
n
d
“
c
h
a
r
a
c
t
”
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
Optimiz
e
d
s
uppor
t
v
e
c
tor
mac
hine
f
or
s
e
nti
me
nt
analys
is
of
game
r
e
v
ie
w
s
(
B
r
y
an
L
e
onar
do
Supr
iyat
na
)
347
(
a
)
(
b
)
F
i
gur
e
2.
W
o
r
d
c
l
o
ud
o
f
t
h
e
r
e
vi
e
w
da
t
a
(
a
)
w
o
r
d
c
l
o
ud
o
f
po
s
i
t
i
v
e
r
e
vi
e
w
s
a
n
d
(
b
)
wo
r
d
c
l
o
ud
o
f
n
e
ga
t
i
v
e
r
e
vi
e
ws
2
.
2.
2
.
TF
-
I
DF
F
e
a
t
ur
e
e
x
t
r
a
c
t
i
o
n
i
s
do
n
e
t
o
r
e
t
r
i
e
v
e
i
m
po
r
t
a
n
t
r
e
vi
e
w
da
t
a
.
F
e
a
t
ur
e
e
x
tr
a
c
t
i
o
n
i
s
do
n
e
w
i
t
h
t
h
e
TF
-
I
DF
m
e
t
h
o
d
wh
e
r
e
e
a
c
h
wo
r
d
t
h
a
t
a
ppe
a
r
s
i
s
we
i
g
h
t
e
d,
t
h
e
r
e
vi
e
w
s
w
i
ll
a
l
s
o
b
e
c
o
n
v
e
r
t
e
d
i
n
t
o
v
e
c
t
or
s
us
i
n
g
t
h
e
‘
n
gr
a
m
_
r
a
n
ge
’
pa
r
a
m
e
t
e
r
.
A
n
n
-
gr
a
m
i
s
a
c
o
n
t
i
guo
us
s
e
que
n
c
e
o
f
n
i
t
e
m
s
dr
a
wn
f
r
o
m
a
p
a
r
t
i
c
u
l
a
r
s
a
m
p
l
e
o
f
t
e
x
t
o
r
a
udi
o
.
I
n
t
hi
s
c
o
n
t
e
x
t
o
f
T
F
-
I
D
F
v
e
c
t
o
r
i
z
e
r
,
a
n
n
-
gr
a
m
is
a
s
e
que
n
c
e
o
f
wo
r
ds
.
He
r
e
,
we
us
e
d
n
gr
a
m
_r
a
n
ge
b
e
t
we
e
n
1
t
o
3,
i
t
s
pe
c
i
f
i
e
s
t
h
a
t
uni
gr
a
m
s
,
bi
gr
a
m
s
,
a
n
d
t
r
i
gr
a
m
s
w
i
ll
b
e
c
o
n
s
i
d
e
r
e
d
wh
e
n
ge
n
e
r
a
t
i
n
g
T
F
-
I
DF
f
e
a
t
ur
e
s
.
TF
-
I
DF
i
s
o
n
e
o
f
t
h
e
m
e
t
h
o
ds
f
o
r
t
e
r
m
o
r
w
or
d
we
i
g
h
t
i
n
g.
S
pe
c
i
f
i
c
a
ll
y
,
i
t
i
s
us
e
d
to
e
x
t
r
a
c
t
c
or
e
w
or
ds
(
i
.
e
.
,
ke
y
wo
r
ds
)
f
r
o
m
do
c
um
e
n
t
s
,
c
a
l
c
u
l
a
t
e
t
h
e
de
gr
e
e
o
f
s
i
mi
l
a
r
i
t
y
b
e
t
we
e
n
do
c
u
m
e
n
t
s
,
de
t
e
r
m
i
ne
s
e
a
r
c
h
r
a
n
k
i
ngs
,
e
t
c
.
T
F
(
t
e
r
m
f
r
e
que
nc
y
)
m
e
a
ns
t
h
e
o
c
c
ur
r
e
n
c
e
o
f
c
e
r
t
a
i
n
wo
r
ds
i
n
doc
u
m
e
n
t
s
.
W
o
r
ds
w
i
t
h
a
hi
g
h
T
F
v
a
l
ue
h
a
v
e
a
n
im
po
r
t
a
n
t
m
e
a
ni
ng
i
n
t
h
e
do
c
u
m
e
n
t
.
T
h
e
T
F
v
a
l
ue
c
a
n
be
c
a
l
c
u
l
a
t
e
d
by
(
1)
a
n
d
i
s
t
h
e
n
u
m
be
r
o
f
o
c
c
ur
r
e
n
c
e
s
o
f
t
h
e
t
e
r
m
t
.
=
1
+
log
(
1)
DF
(
do
c
um
e
n
t
f
r
e
que
n
c
y
)
im
p
li
e
s
t
h
e
n
u
m
be
r
o
f
t
i
m
e
s
a
pa
r
t
i
c
u
l
a
r
wo
r
d
a
ppe
a
r
s
i
n
a
s
e
t
o
f
do
c
um
e
n
t
s
.
I
t
c
o
un
t
s
t
h
e
o
c
c
ur
r
e
n
c
e
o
f
a
wo
r
d
i
n
m
u
l
t
i
p
l
e
do
c
u
m
e
n
t
s
,
n
o
t
j
us
t
i
n
a
s
i
n
g
l
e
do
c
u
m
e
n
t
.
I
DF
(
i
nv
e
r
s
e
do
c
um
e
n
t
f
r
e
que
n
c
y
)
,
t
h
e
i
nve
r
s
e
o
f
DF
,
i
s
us
e
d
t
o
a
s
s
e
s
s
t
h
e
i
m
po
r
t
a
n
c
e
o
f
t
e
r
m
s
i
n
a
ll
do
c
u
m
e
n
t
s
.
A
hi
g
h
I
D
F
v
a
l
ue
m
e
a
n
s
t
h
a
t
r
a
r
e
w
or
ds
a
r
e
f
o
un
d
a
c
r
o
s
s
d
o
c
um
e
n
t
s
,
t
h
us
i
n
c
r
e
a
s
i
ng
t
h
e
i
r
i
m
po
r
t
a
n
c
e
[
18]
.
T
h
e
DF
v
a
l
ue
c
a
n
be
c
a
l
c
u
l
a
t
e
d
by
(
2)
.
D
i
s
t
h
e
n
u
m
b
e
r
o
f
d
o
c
u
m
e
n
t
s
a
n
d
i
s
t
h
e
n
u
m
b
e
r
o
f
d
o
c
um
e
n
t
s
a
v
a
il
a
bl
e
i
s
t
h
e
t
e
r
m
t
.
=
log
(
)
(
2
)
Af
t
e
r
t
h
e
c
a
l
c
u
l
a
t
i
o
n
o
f
T
F
a
n
d
I
DF
i
s
do
n
e
,
we
c
a
n
c
a
l
c
u
l
a
t
e
t
h
e
T
F
-
I
DF
v
a
l
u
e
us
i
n
g
(
3
)
,
wh
e
r
e
t
h
e
v
a
l
ue
o
f
,
i
s
t
h
e
we
i
g
h
t
o
f
t
e
r
m
t
i
n
do
c
um
e
n
t
d
.
,
=
×
(
3
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
13
,
N
o.
3
,
De
c
e
m
be
r
2
0
24
:
344
-
353
348
T
h
e
pr
o
c
e
s
s
o
f
f
e
a
t
ur
e
e
x
t
r
a
c
t
i
o
n
i
s
us
e
d
t
o
ge
t
c
r
u
c
i
a
l
r
e
vi
e
w
da
t
a
.
T
h
e
T
F
-
I
DF
a
ppr
o
a
c
h
i
s
us
e
d
f
o
r
f
e
a
t
ur
e
e
x
t
r
a
c
t
i
o
n;
e
a
c
h
wo
r
d
t
h
a
t
a
ppe
a
r
s
i
s
g
i
ve
n
a
we
i
g
h
t
,
a
n
d
t
h
e
o
u
t
pu
t
i
s
t
r
a
n
s
f
o
r
m
e
d
i
n
t
o
a
v
e
c
t
o
r
.
R
e
vi
e
ws
c
a
n
b
e
r
e
pr
e
s
e
n
t
e
d
us
i
n
g
T
F
-
I
DF
by
mak
i
n
g
a
gr
a
p
h
o
f
t
h
e
m
o
s
t
f
r
e
que
n
t
l
y
o
c
c
ur
r
i
n
g
wo
r
ds
a
s
s
h
o
w
n
i
n
F
i
gur
e
3
.
T
h
e
bi
gr
a
m
s
o
f
t
h
e
m
o
s
t
f
r
e
que
n
t
l
y
o
c
c
ur
r
i
n
g
t
e
r
m
s
i
s
d
i
s
p
l
a
y
e
d
i
n
F
i
gur
e
3
(
a
)
.
“
B
e
s
t
ga
m
e
”
h
a
s
m
o
r
e
t
h
a
n
700
o
c
c
ur
r
e
n
c
e
s
,
a
n
d
“
b
a
l
du
r
g
a
t
e
”
h
a
s
800
o
c
c
ur
r
e
n
c
e
s
.
T
h
e
to
p
t
e
n
t
r
i
gr
a
m
t
e
r
m
s
t
h
a
t
o
c
c
ur
f
r
e
que
n
t
l
y
a
r
e
d
i
s
p
l
a
y
e
d
i
n
F
i
gur
e
3(
b
)
.
“
O
n
e
b
e
s
t
ga
m
e
”
a
n
d
“
be
s
t
ga
m
e
e
v
e
r
”
a
r
e
t
w
o
o
f
th
e
m
o
s
t
o
f
t
e
n
us
e
d
ph
r
a
s
e
s
,
w
i
t
h
o
v
e
r
200
a
n
d
300
i
n
s
t
a
n
c
e
s
,
r
e
s
pe
c
t
i
v
e
ly
.
(
a
)
(
b
)
F
i
gur
e
3.
T
o
p
10
o
f
t
h
e
m
o
s
t
f
r
e
que
n
t
l
y
n
-
gr
a
m
s
(
a
)
m
o
s
t
f
r
e
que
n
t
l
y
o
c
c
ur
r
i
n
g
bi
gr
a
m
s
a
n
d
(
b
)
m
o
s
t
f
r
e
que
n
t
l
y
o
c
c
ur
r
i
n
g
t
r
i
gr
a
m
s
2
.
2.
3
.
Dat
a
s
p
l
it
t
in
g
T
h
e
wh
o
l
e
da
t
a
i
n
t
h
e
da
t
a
s
e
t
s
pl
i
t
t
e
d
i
n
t
o
da
t
a
tr
a
i
ni
ng
a
n
d
da
t
a
t
e
s
t
i
n
g
w
i
t
h
pe
r
c
e
n
t
a
ge
o
f
80%
a
n
d
20%
,
r
e
s
pe
c
t
i
ve
l
y
.
T
h
e
t
ot
a
l
s
a
m
p
l
e
f
o
r
t
r
a
i
ni
ng
da
t
a
i
s
208,
844,
a
n
d
t
h
e
tot
a
l
s
a
m
p
l
e
f
o
r
t
e
s
t
i
ng
da
t
a
i
s
52,
211
.
T
a
bl
e
3
de
s
c
r
i
be
s
t
h
e
e
x
a
m
p
l
e
s
o
f
po
s
i
t
i
ve
a
n
d
n
e
ga
t
i
v
e
r
e
vi
e
w
s
f
r
o
m
t
h
e
da
t
a
s
e
t
.
T
h
e
r
e
view
da
t
a
wa
s
f
il
t
e
r
e
d
by
r
e
m
o
vi
ng
e
a
r
ly
a
c
c
e
s
s
r
e
vi
e
w
s
,
whic
h
a
r
e
r
e
vi
e
w
s
whe
n
t
h
e
ga
m
e
i
s
o
n
tr
i
a
l
.
T
a
bl
e
3
.
E
x
a
m
p
l
e
o
f
po
s
i
t
i
v
e
a
n
d
n
e
g
a
t
i
ve
r
e
vi
e
w
s
P
o
s
it
i
ve
r
e
v
i
e
w
s
N
e
ga
ti
v
e
r
e
vi
e
w
s
G
o
t
y
i
m
o
B
a
d
w
r
it
in
g a
nd
ov
e
r
s
im
pl
i
f
i
e
d
c
o
mba
t
B
e
s
t
R
P
G
t
ha
t
c
a
me
o
ut
in
y
e
a
r
s
ki
nda
mi
d t
bh w
it
c
h
e
r
3 ha
d b
e
tt
e
r
v
ib
e
s
B
e
s
t
dnd
ba
s
e
ga
m
e
e
v
e
r
, j
us
t
be
p
r
e
pa
r
e
d t
o
di
e
a
l
o
t
G
a
m
e
c
r
a
s
he
d a
nd ma
de
m
e
ve
r
i
f
y
f
il
e
s
t
w
ic
e
J
us
t
a
n
in
c
r
e
di
bl
y
g
oo
d
ga
m
e
.
T
h
e
de
v
s
p
e
r
f
e
c
t
e
d
a
nd
di
s
ti
ll
e
d
th
e
ir
p
r
e
v
i
o
us
w
or
k
o
n
th
e
D
i
v
in
it
y
ga
me
s
a
nd
th
is
ma
na
ge
s
to
c
a
pt
ur
e
th
e
s
pi
r
it
of
th
e
o
r
ig
in
a
l
B
a
ld
ur
’s
G
a
t
e
ga
me
s
a
s
w
e
ll
.
S
o
p
o
li
s
he
d,
lo
ve
t
h
e
s
c
o
p
e
,
e
tc
. J
us
t
a
n a
ma
z
in
g ga
m
e
.
T
h
e
ga
me
is
a
n
unb
e
a
r
a
bl
y
bugg
y
m
e
s
s
.
I
ha
ve
e
n
c
o
unt
e
r
e
d
s
o
ma
n
y
bugs
it
is
unr
e
a
l.
I
ha
ve
a
ha
d
e
ne
mi
e
s
hi
t
me
w
it
h
me
le
e
a
tt
a
c
ks
f
r
o
m
f
a
r
b
e
y
ond
w
he
r
e
th
e
y
s
h
o
ul
d
be
a
bl
e
t
o
a
nd
th
e
n
t
o
c
a
s
t
he
a
li
ng
w
o
r
d,
a
t
o
u
c
h
s
pe
ll
,
o
n
m
y
a
ll
y
I
ha
dt
o
m
ove
a
ll
th
e
w
a
y
t
o
w
he
r
e
th
e
y
w
e
r
e
.
I
ha
ve
a
ls
o
e
n
c
o
unt
e
r
e
d
bugs
th
a
t
ha
ve
s
to
pp
e
d
m
e
f
r
o
m
s
a
v
in
g
in
b
o
th
s
in
gl
e
pl
a
y
e
r
a
nd
mul
ti
pl
a
y
e
r
r
e
s
ul
ti
ng
in
pr
o
g
r
e
s
s
l
o
s
t
o
n
mu
lt
ip
l
e
oc
c
a
s
io
ns
.
T
he
ga
me
c
oul
d
be
g
oo
d but wa
it
unt
il
i
ts
n
o
t
a
bugg
y
s
hi
t
s
ho
w
a
n
y
m
o
r
e
.
2.
3.
P
r
op
os
e
d
al
go
r
it
h
m
T
hi
s
s
u
b
-
s
e
c
t
i
o
n
de
s
c
r
i
be
s
t
h
e
m
e
t
h
o
d
pr
o
p
o
s
e
d
i
n
t
hi
s
s
t
udy
a
n
d
t
h
e
s
t
e
ps
t
a
ke
n
to
o
b
t
a
i
n
s
e
n
t
i
m
e
n
t
c
l
a
s
s
if
i
c
a
t
i
o
n
r
e
s
u
l
t
s
.
Af
t
e
r
t
h
e
da
t
a
i
s
ve
c
t
or
i
z
e
d
us
i
n
g
T
F
-
I
DF
a
n
d
s
p
li
t
i
n
t
o
tr
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
da
t
a
,
t
h
e
t
r
a
i
ni
ng
da
t
a
wi
ll
b
e
f
o
r
wa
r
de
d
to
P
S
O
f
o
r
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
.
T
h
e
f
e
a
t
ur
e
s
r
e
f
e
r
r
e
d
to
h
e
r
e
a
r
e
to
ke
n
s
b
e
c
a
us
e
t
h
e
da
t
a
us
e
d
i
s
t
e
x
t
da
t
a
.
L
a
t
e
r
,
t
h
e
s
e
l
e
c
t
e
d
f
e
a
t
ur
e
s
by
P
S
O
a
r
e
us
e
d
f
o
r
tr
a
i
ni
n
g
S
VM
i
n
c
las
s
if
yi
ng
s
e
n
t
i
m
e
n
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
Optimiz
e
d
s
uppor
t
v
e
c
tor
mac
hine
f
or
s
e
nti
me
nt
analys
is
of
game
r
e
v
ie
w
s
(
B
r
y
an
L
e
onar
do
Supr
iyat
na
)
349
2
.
3
.
1
.
P
S
O
P
S
O
i
s
a
s
i
m
p
l
e
o
p
t
i
mi
z
a
t
i
o
n
m
e
t
h
o
d
to
m
o
d
i
f
y
s
e
v
e
r
a
l
pa
r
a
m
e
t
e
r
s
.
P
S
O
c
o
n
v
e
r
ge
s
f
a
s
t
a
n
d
h
a
s
f
e
w
pa
r
a
m
e
t
e
r
s
to
a
l
t
e
r
,
t
h
e
r
e
f
o
r
e
t
h
e
c
o
m
put
i
n
g
t
i
m
e
o
f
t
hi
s
t
e
c
hni
que
i
s
a
l
s
o
r
e
duc
e
d.
S
i
nc
e
s
e
v
e
r
a
l
pa
r
t
i
c
l
e
s
a
tt
e
m
pt
to
f
i
nd
a
s
o
l
ut
i
o
n
,
t
h
e
pr
o
b
a
bil
i
t
y
o
f
be
c
o
m
i
ng
t
r
a
ppe
d
i
n
a
n
i
de
a
l
l
o
c
a
l
s
o
l
ut
i
o
n
i
s
r
e
duc
e
d
[
19]
.
I
ni
t
i
a
l
ly
,
pa
r
t
i
c
l
e
s
a
r
e
p
l
a
c
e
d
i
n
po
s
i
t
i
o
ns
us
i
ng
(
4)
a
n
d
(
5)
a
n
d
t
h
e
n
pe
r
f
o
r
m
a
s
e
a
r
c
h
f
o
r
t
h
e
o
p
t
i
m
a
l
v
a
l
ue
o
f
a
pa
r
t
i
c
u
l
a
r
o
bj
e
c
t
i
v
e
f
u
nc
t
i
o
n
t
h
r
o
ugh
e
x
p
l
o
r
a
t
i
o
n
a
n
d
e
x
p
l
o
i
t
a
t
i
o
n
.
T
h
e
f
i
t
ne
s
s
va
l
ue
o
f
t
h
e
o
bj
e
c
t
i
v
e
f
u
n
c
t
i
o
n
a
t
t
h
a
t
p
o
s
i
t
i
o
n
i
s
a
l
s
o
s
to
r
e
d
,
whi
c
h
i
s
c
a
lcu
l
a
t
e
d
b
y
(
6)
[
20]
.
0
=
+
(
0
,
1
)
(
−
)
(
4
)
0
=
+
(
0
,
1
)
(
−
)
(
5
)
+
1
=
(
+
1
)
(
6
)
wh
e
r
e
,
x
=
pa
r
t
i
c
l
e
’
s
po
s
i
t
i
o
n
v
=
pa
r
t
i
c
l
e
’
s
v
e
l
o
c
i
t
y
.
i
=
pa
r
t
i
c
l
e
i
n
d
e
x
.
f
(
x
)
i
s
t
h
e
o
bj
e
c
t
i
v
e
f
u
n
c
t
i
o
n
E
a
c
h
pa
r
t
i
c
l
e
w
il
l
h
a
v
e
a
pbe
s
t
(
pe
r
s
o
n
a
l
b
e
s
t
)
a
n
d
a
gbe
s
t
(
g
l
o
b
a
l
b
e
s
t
)
v
a
l
ue
.
T
hi
s
p
b
e
s
t
v
a
l
ue
i
s
t
h
e
b
e
s
t
pa
r
t
i
c
l
e
po
s
i
t
i
o
n
dur
i
n
g
t
h
e
i
t
e
r
a
t
i
o
n
pe
r
f
o
r
m
e
d
(
+
1
<
)
,
whi
l
e
gb
e
s
t
i
s
t
h
e
pa
r
t
i
c
l
e
po
s
i
t
i
o
n
va
l
ue
t
h
a
t
i
s
c
l
o
s
e
s
t
to
t
h
e
t
a
r
ge
t
(
+
1
1
<
)
.
T
h
e
m
o
ve
m
e
n
t
o
f
pa
r
t
i
c
l
e
s
i
n
a
f
l
o
c
k
de
pe
n
ds
o
n
t
h
r
e
e
f
a
c
t
or
s
,
n
a
m
e
ly
p
b
e
s
t
,
gb
e
s
t
,
a
n
d
v
e
l
o
c
i
t
y
[
21]
.
T
h
e
pa
r
t
i
c
le
v
e
l
o
c
i
t
y
f
o
r
m
u
l
a
c
a
n
b
e
c
a
l
c
u
l
a
t
e
d
us
i
n
g
(
7)
.
+
1
=
+
1
(
−
)
+
2
(
−
)
(
7
)
W
h
e
r
e
,
pbe
s
t
i
=
pe
r
s
o
n
a
l
b
e
s
t
pa
r
t
i
c
l
e
i
w
=
i
ne
r
t
i
a
we
i
g
h
t
(
us
ua
l
l
y
b
e
t
we
e
n
0.
9
-
0.
4
)
gbe
s
t
i
=
g
l
o
b
a
l
b
e
s
t
pa
r
t
i
c
l
e
i
c
1
=
pe
r
s
o
n
a
l
l
e
a
r
ni
ng
f
a
c
t
or
(
us
ua
l
ly
b
e
t
we
e
n
0
-
1)
c
2
=
gl
o
b
a
l
l
e
a
r
ni
ng
f
a
c
t
o
r
(
us
ua
l
ly
b
e
t
we
e
n
0
-
1)
F
i
r
s
t
,
t
h
e
pa
r
a
m
e
t
e
r
v
a
l
ue
s
c
1
a
n
d
c
2
m
us
t
b
e
i
n
i
t
i
a
li
z
e
d.
Ne
x
t
,
us
e
(
5)
to
de
t
e
r
m
i
ne
t
h
e
v
e
l
o
c
i
t
y
,
a
n
d
(
6)
to
a
s
s
e
s
s
t
h
e
f
i
t
n
e
s
s
v
a
l
ue
.
K
e
e
p
r
e
c
o
r
d
o
f
t
h
e
pb
e
s
t
a
n
d
gb
e
s
t
v
a
l
ue
s
.
I
f
t
h
e
r
e
qu
i
r
e
m
e
n
t
s
a
r
e
n
’
t
s
a
t
i
s
f
i
e
d,
us
e
(
7)
to
a
s
s
e
s
s
t
h
e
pa
r
t
i
c
l
e
v
e
l
o
c
i
t
y
a
n
d
(
8)
to
upda
t
e
t
h
e
pa
r
t
i
c
l
e
po
s
i
t
i
o
n
.
T
h
e
f
i
t
ne
s
s
v
a
l
ue
i
s
upda
t
e
d
c
o
n
t
i
n
ua
ll
y
dur
i
ng
i
t
e
r
a
t
i
o
n
to
e
n
s
ur
e
t
h
a
t
t
h
e
gb
e
s
t
a
n
d
pb
e
s
t
v
a
l
u
e
s
s
a
t
i
s
f
y
t
h
e
r
e
qu
i
r
e
m
e
n
t
s
.
+
1
=
+
+
1
(
8
)
2
.
3
.
2
.
S
V
M
S
VM
i
s
a
s
tr
a
i
g
h
t
f
o
r
wa
r
d
a
n
d
a
da
p
t
a
bl
e
m
a
c
hi
ne
l
e
a
r
ni
ng
t
e
c
h
ni
que
t
h
a
t
m
a
y
b
e
us
e
d
to
a
ddr
e
s
s
a
v
a
r
i
e
t
y
o
f
c
a
t
e
go
r
i
z
a
t
i
o
n
i
s
s
ue
s
.
P
a
r
t
i
c
u
l
a
r
ly
,
S
VM
pr
o
duc
e
s
b
a
l
a
n
c
e
d
pr
e
d
i
c
t
e
d
pe
r
f
o
r
m
a
n
c
e
,
e
v
e
n
i
n
r
e
s
e
a
r
c
h
w
i
t
h
s
m
a
ll
s
a
m
p
l
e
s
i
z
e
s
[
22]
.
Us
i
n
g
c
l
u
s
ter
da
t
a
a
s
a
s
t
a
r
t
i
n
g
po
i
n
t
,
t
h
e
S
VM
a
ppr
o
a
c
h
c
r
e
a
tes
a
l
i
n
e
o
f
s
e
pa
r
a
t
i
o
n
(
de
c
i
s
i
o
n
b
o
un
d
a
r
y
)
o
r
hy
pe
r
p
l
a
n
e
l
in
e
f
r
o
m
t
h
e
c
l
u
s
t
e
r
da
t
a
.
M
a
xi
m
u
m
l
i
k
e
l
i
h
o
o
d
l
i
ne
s
t
h
a
t
l
i
e
i
n
a
s
pa
c
e
a
n
d
c
l
a
s
s
if
y
d
a
t
a
s
e
pa
r
a
t
e
d
by
n
o
n
-
l
i
ne
a
r
o
r
l
i
ne
a
r
b
o
un
da
r
i
e
s
c
a
n
be
c
o
n
s
t
r
uc
t
e
d
by
f
i
nd
i
ng
a
s
e
t
o
f
hy
pe
r
p
l
a
n
e
s
t
h
a
t
s
e
pa
r
a
t
e
t
w
o
or
m
o
r
e
c
l
a
s
s
e
s
o
f
da
t
a
po
i
n
t
s
.
Af
t
e
r
t
h
e
c
o
n
s
t
r
uc
t
i
o
n
o
f
hy
pe
r
p
l
a
ne
s
,
S
VM
f
i
nds
t
h
e
d
i
s
t
a
n
c
e
b
e
t
we
e
n
t
h
e
i
n
put
c
l
a
s
s
e
s
,
a
n
d
t
h
e
i
n
put
e
l
e
m
e
n
t
s
o
n
t
h
e
hy
pe
r
p
l
a
n
e
a
r
e
c
a
l
l
e
d
s
uppo
r
t
v
e
c
t
o
r
s
.
F
r
o
m
a
gi
v
e
n
s
e
t
o
f
t
r
a
i
ni
ng
s
a
m
p
l
e
s
l
a
b
e
led
p
o
s
i
t
i
v
e
o
r
n
e
ga
t
i
v
e
,
t
h
e
hy
pe
r
p
l
a
n
e
d
i
vi
de
s
t
h
e
po
s
i
t
i
ve
o
r
n
e
ga
t
i
v
e
t
r
a
i
ni
ng
s
a
m
p
l
e
s
s
o
t
h
a
t
t
h
e
di
s
t
a
n
c
e
b
e
t
we
e
n
t
h
e
m
a
r
g
i
n
a
n
d
t
h
e
hy
pe
r
p
l
a
n
e
i
s
m
a
xim
i
z
e
d.
I
f
t
h
e
r
e
i
s
n
o
hy
pe
r
p
l
a
n
e
t
h
a
t
c
a
n
d
i
vi
de
po
s
i
t
i
v
e
or
n
e
ga
t
i
ve
s
a
m
p
l
e
s
,
S
VM
w
il
l
c
h
o
o
s
e
a
hy
pe
r
p
l
a
n
e
t
h
a
t
d
i
vi
de
s
t
h
e
s
a
m
p
l
e
s
a
s
c
l
o
s
e
ly
a
s
po
s
s
i
bl
e
w
hil
e
s
t
i
ll
m
a
xim
i
z
i
ng
t
h
e
di
s
t
a
n
c
e
t
o
t
h
e
c
l
o
s
e
s
t
e
x
a
m
p
le
t
h
a
t
i
s
s
t
r
i
c
t
l
y
s
p
li
t
[
23]
.
Di
f
f
e
r
e
n
t
c
l
a
s
s
e
s
a
r
e
pr
e
di
c
t
e
d
b
a
s
e
d
o
n
t
h
e
da
t
a
p
o
i
n
t
s
a
n
d
t
h
e
s
i
de
o
n
whi
c
h
t
h
e
y
l
i
e
o
n
t
h
e
hy
p
e
r
p
l
a
n
e
,
whi
c
h
s
e
r
v
e
s
a
s
t
h
e
de
c
i
s
i
o
n
b
o
unda
r
y
i
n
S
VM
[
24]
.
T
h
e
ke
r
n
e
l
f
u
n
c
t
i
o
n
p
l
a
y
s
a
c
r
uc
i
a
l
r
o
l
e
i
n
t
r
a
n
s
f
o
r
mi
ng
t
h
e
i
n
put
da
t
a
i
n
t
o
a
hi
g
h
e
r
-
d
i
m
e
n
s
i
o
na
l
s
pa
c
e
whe
r
e
t
h
e
da
t
a
b
e
c
o
m
e
s
l
i
ne
a
r
ly
s
e
pa
r
a
bl
e
,
i
nc
l
ud
i
ng
l
i
ne
a
r
,
r
a
di
a
l
b
a
s
i
c
f
u
nc
t
i
o
n
(
R
B
F
)
,
a
n
d
P
o
l
y
n
o
m
i
a
l
ke
r
n
e
l
.
L
i
ne
a
r
ke
r
n
e
a
l
i
s
t
h
e
s
im
p
l
e
s
t
ke
r
n
e
l
,
w
i
t
h
o
ut
us
i
ng
t
h
e
ga
m
m
a
va
l
u
e
(
γ)
,
us
i
n
g
(
9)
.
x
i
i
s
t
h
e
v
a
l
ue
o
f
t
h
e
t
r
a
i
ni
ng
da
t
a
,
x
j
i
s
t
h
e
v
a
l
ue
o
f
t
h
e
t
e
s
t
da
t
a
,
a
n
d
k
(
x
i
.
x
j
)
i
s
t
h
e
ke
r
n
e
l
v
a
l
u
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
13
,
N
o.
3
,
De
c
e
m
be
r
2
0
24
:
344
-
353
350
(
.
)
=
(
9
)
R
B
F
i
s
a
n
o
n
-
l
i
ne
a
r
ke
r
n
e
l
,
us
i
ng
t
h
e
ga
m
m
a
v
a
l
u
e
pa
r
a
m
e
t
e
r
(
γ>
0)
a
s
a
de
t
e
r
m
i
na
n
t
o
f
t
h
e
f
l
e
xi
b
i
li
t
y
o
f
t
hi
s
ke
r
n
e
l
,
c
a
n
b
e
de
s
c
r
i
be
d
by
(
10)
.
T
hi
s
ke
r
n
e
l
i
s
s
u
i
t
a
bl
e
f
o
r
da
t
a
t
h
a
t
c
a
nn
o
t
b
e
s
o
l
ve
d
l
i
ne
a
r
l
y
w
i
t
h
a
hi
g
h
l
e
v
e
l
o
f
a
c
c
ur
a
c
y
a
n
d
pr
e
c
i
s
i
o
n
[
20]
.
(
.
)
=
(
−
.
‖
.
‖
2
)
(
10
)
P
o
l
y
n
o
m
i
a
l
ke
r
n
e
l
i
s
a
n
o
n
-
l
i
ne
a
r
ke
r
n
e
l
,
us
i
n
g
t
h
e
pa
r
a
m
e
t
e
r
v
a
l
u
e
o
f
t
h
e
ga
m
m
a
v
a
l
ue
(
γ>
0)
a
n
d
th
e
va
l
u
e
o
f
d
a
s
t
h
e
c
o
e
f
f
i
c
i
e
n
t
o
f
t
h
e
pe
n
a
l
t
y
de
gr
e
e
f
o
r
f
l
e
xi
b
il
i
t
y
as
de
s
c
r
i
be
d
i
n
(
11)
.
(
.
)
=
(
.
+
)
(
11
)
A
l
a
r
ge
ga
m
m
a
v
a
l
ue
w
il
l
a
l
s
o
c
a
l
c
u
l
a
t
e
t
r
a
i
ni
n
g
da
t
a
t
h
a
t
i
s
f
a
r
f
r
o
m
t
h
e
de
c
i
s
i
o
n
b
o
un
da
r
y
b
ut
w
i
l
l
c
a
us
e
a
s
m
a
l
l
a
c
c
ur
a
c
y
v
a
l
ue
,
a
n
d
t
h
e
v
a
l
ue
o
f
C
i
s
a
f
r
e
e
pa
r
a
m
e
t
e
r
,
t
h
e
v
a
l
ue
o
f
r
i
s
a
bi
a
s
,
a
n
d
t
h
e
ga
m
m
a
a
n
d
r
pa
r
a
m
e
t
e
r
s
h
a
v
e
a
s
t
r
o
n
g
r
e
l
a
t
i
o
n
s
hi
p
[
25]
.
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
I
n
t
hi
s
s
e
c
t
i
o
n
,
t
h
e
e
x
pe
r
i
m
e
n
t
r
e
s
u
l
t
s
a
r
e
de
s
c
r
i
be
d
a
n
d
a
n
a
ly
z
e
d.
W
e
a
l
s
o
e
x
p
l
a
i
n
t
h
e
m
o
de
l
pa
r
a
m
e
t
e
r
s
us
e
d
i
n
S
VM
t
r
a
i
ni
ng,
whi
c
h
t
h
e
n
b
e
c
o
m
e
t
h
e
b
a
s
i
s
f
o
r
t
uni
n
g
hy
pe
r
pa
r
a
m
e
t
e
r
s
i
n
t
h
e
opt
i
mi
z
e
d
-
S
VM
m
o
de
l
us
i
ng
P
S
O,
whi
c
h
i
n
t
hi
s
a
r
t
i
c
l
e
w
il
l
b
e
r
e
f
e
r
r
e
d
to
a
s
S
VM
-
P
S
O.
A
di
s
c
us
s
i
o
n
a
b
o
ut
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
e
v
a
l
ua
t
i
o
n
o
n
B
a
l
dur
’
s
Ga
t
e
3
b
a
s
e
d
o
n
t
h
e
r
e
vi
e
ws
i
s
a
l
s
o
pr
e
s
e
n
t
e
d.
3.
1.
E
x
p
e
r
im
e
n
t
a
l
s
e
t
u
p
T
hi
s
s
t
ud
y
us
e
s
a
3.
1
GH
z
I
n
t
e
l
C
o
r
e
i
5
-
12500
H
pr
o
c
e
s
s
o
r
wi
t
h
m
e
m
o
r
y
:
16
GB
R
A
M
.
Go
o
gl
e
C
o
l
a
b
a
n
d
l
i
br
a
r
i
e
s
s
uc
h
a
s
s
c
i
k
i
t
-
l
e
a
r
n
,
s
e
a
b
o
r
n
,
a
n
d
pa
n
da
s
a
r
e
us
e
d
to
e
x
e
c
ut
e
P
y
t
h
o
n
c
o
de
a
n
d
da
t
a
vi
s
u
a
l
i
z
a
t
i
o
n
.
T
he
pr
o
p
o
s
e
d
a
ppr
o
a
c
h
wa
s
e
x
e
c
ut
e
d
us
i
n
g
P
S
O
i
t
e
r
a
t
i
o
ns
o
f
5
a
n
d
t
h
e
n
u
m
be
r
o
f
pa
r
t
i
c
l
e
s
o
f
30.
T
h
e
hy
pe
r
pa
r
a
m
e
t
e
r
s
t
uni
n
g
f
o
r
S
VM
i
n
c
l
ude
d
ke
r
n
e
l
,
ga
m
m
a
,
a
n
d
C
.
3.
2.
E
val
u
at
ion
m
e
as
u
r
e
s
E
v
a
l
ua
t
i
o
n
i
n
t
hi
s
s
t
ud
y
us
e
s
a
c
o
nf
u
s
i
o
n
m
a
t
r
i
x
wh
e
r
e
pr
e
c
i
s
i
o
n
,
a
c
c
ur
a
c
y
,
r
e
c
a
ll
,
a
n
d
F
1
-
s
c
o
r
e
v
a
l
ue
s
w
i
ll
b
e
s
o
ugh
t
to
de
t
e
r
m
i
ne
t
h
e
s
u
i
t
a
bil
i
t
y
o
f
t
he
a
l
go
r
i
t
hm
t
h
a
t
h
a
s
b
e
e
n
u
s
e
d.
A
c
c
ur
a
c
y
m
e
a
s
ur
e
s
t
h
e
o
v
e
r
a
l
l
c
o
r
r
e
c
t
n
e
s
s
o
f
t
h
e
m
o
de
l
’
s
pr
e
d
i
c
t
i
o
ns
,
a
nd
i
s
c
a
l
c
u
l
a
t
e
d
a
s
t
h
e
r
a
t
i
o
o
f
c
o
r
r
e
c
t
l
y
pr
e
d
i
c
t
e
d
i
n
s
t
a
n
c
e
s
,
to
t
h
e
tot
a
l
n
u
m
be
r
o
f
i
ns
t
a
n
c
e
s
i
n
t
h
e
da
t
a
s
e
t
b
a
s
e
d
o
n
(
12
)
.
=
+
+
+
+
(
12)
T
h
e
F
1
-
s
c
o
r
e
i
s
t
h
e
h
a
r
m
o
ni
c
m
e
a
n
o
f
pr
e
c
i
s
i
o
n
a
n
d
r
e
c
a
ll
,
r
e
s
u
l
t
i
n
g
i
n
a
s
i
ng
l
e
m
e
t
r
i
c
t
h
a
t
b
a
l
a
n
c
e
s
b
o
t
h
m
e
a
s
ur
e
m
e
n
t
s
,
a
s
s
h
o
wn
i
n
(
13)
.
P
r
e
c
i
s
i
o
n
i
s
t
h
e
pr
o
p
o
r
t
i
o
n
o
f
t
r
ue
p
o
s
i
t
i
v
e
(
T
P
)
p
r
e
di
c
t
i
o
ns
a
m
o
n
g
a
l
l
po
s
i
t
i
v
e
pr
e
d
i
c
t
i
o
n
s
m
a
d
e
by
t
h
e
m
o
de
l
,
a
s
s
h
o
wn
i
n
(
14)
.
R
e
c
a
l
l
i
s
d
e
f
i
ne
d
a
s
t
h
e
pr
o
p
o
r
t
i
o
n
o
f
t
r
ue
po
s
i
t
i
v
e
(
T
P
)
pr
e
di
c
t
i
o
n
s
a
m
o
n
g
a
l
l
r
e
a
l
po
s
i
t
i
ve
c
a
s
e
s
i
n
t
h
e
da
t
a
s
e
t,
a
s
s
h
o
wn
i
n
(
15)
.
1
−
=
2
×
×
+
(
13)
=
+
(
14)
=
+
(
15)
3.
3.
B
as
e
l
in
e
m
od
e
l
A
gr
i
d
s
e
a
r
c
h
i
s
pe
r
f
o
r
m
e
d
i
n
o
r
de
r
to
f
i
nd
t
h
e
b
e
s
t
ke
r
n
e
l
a
n
d
pa
r
a
m
e
t
e
r
s
o
f
S
VM
.
T
h
e
t
e
s
t
e
d
hy
pe
r
pa
r
a
m
e
t
e
r
s
a
r
e
de
s
c
r
i
be
d
in
T
a
bl
e
4
.
Af
t
e
r
doi
ng
a
gr
i
d
s
e
a
r
c
h
,
t
h
e
be
s
t
pa
r
a
m
e
t
e
r
is
fo
u
n
d
to
b
e
a
l
i
ne
a
r
ke
r
n
e
l
w
i
t
h
a
‘
C
’
v
a
l
ue
o
f
10.
T
h
e
e
va
l
u
a
t
i
o
n
r
e
s
u
lt
s
f
o
r
t
h
e
n
e
ga
t
i
v
e
c
l
a
s
s
s
h
o
w
a
19%
F
1
-
s
c
o
r
e
,
11
%
r
e
c
a
l
l
,
a
n
d
89%
pr
e
c
i
s
i
o
n
.
T
h
e
pr
e
c
i
s
i
o
n
,
r
e
c
a
ll
,
a
n
d
F
1
-
s
c
o
r
e
v
a
l
ue
s
f
o
r
t
h
e
po
s
i
t
i
v
e
c
l
a
s
s
a
r
e
97%
,
100%
,
a
n
d
99%
,
r
e
s
pe
c
t
i
ve
ly
.
T
h
e
a
c
c
ur
a
c
y
v
a
l
ue
i
s
97.
28%
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
Optimiz
e
d
s
uppor
t
v
e
c
tor
mac
hine
f
or
s
e
nti
me
nt
analys
is
of
game
r
e
v
ie
w
s
(
B
r
y
an
L
e
onar
do
Supr
iyat
na
)
351
T
a
bl
e
4
.
S
VM
pa
r
a
m
e
t
e
r
s
K
e
r
n
e
l
C
G
a
mm
a
L
in
e
a
r
1
,
10
-
R
BF
1
,
10
1,
0.1
S
ig
moi
d
1
,
10
1,
0.1
3.
4.
S
V
M
-
P
S
O
r
e
s
u
l
t
s
W
hil
e
o
t
h
e
r
r
e
s
e
a
r
c
h
m
e
r
e
ly
hi
g
hli
g
h
t
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
S
VM
w
i
t
h
o
ut
a
ny
o
pt
i
m
i
z
a
t
i
o
n
,
t
hi
s
s
t
udy
f
o
c
us
e
s
o
n
t
h
e
i
m
pa
c
t
o
f
t
h
e
e
v
o
l
ut
i
o
n
a
r
y
P
S
O
m
e
t
h
o
d
o
n
t
h
e
o
u
t
c
o
m
e
s
o
f
s
e
n
t
i
m
e
n
t
c
a
t
e
g
o
r
i
z
a
t
i
o
n
us
i
n
g
S
VM
.
T
h
e
t
e
s
t
s
c
e
n
a
r
i
o
wa
s
c
a
r
r
i
e
d
o
u
t
by
c
h
a
n
g
i
ng
t
h
e
P
S
O
pa
r
a
m
e
t
e
r
s
c
1
a
n
d
c
2
wi
t
h
v
a
l
u
e
s
o
f
0.
2
a
n
d
0.
5
a
n
d
pa
r
a
m
e
t
e
r
w
w
i
t
h
v
a
l
ue
s
o
f
0.
4,
0.
6
,
a
n
d
0.
9.
B
a
s
e
d
o
n
o
ur
e
x
pe
r
i
m
e
n
t
s
,
we
f
o
un
d
t
h
a
t
us
i
n
g
P
S
O
a
s
f
e
a
t
ur
e
s
e
l
e
c
t
i
o
n
a
f
f
e
c
t
s
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
S
VM
.
T
hi
s
i
s
e
vi
de
nc
e
d
by
t
h
e
i
nc
r
e
a
s
e
d
a
c
c
ur
a
c
y
a
nd
F1
-
s
c
o
r
e
o
f
S
VM
-
P
S
O
c
o
m
pa
r
e
d
to
S
VM
,
whi
c
h
c
a
n
b
e
s
e
e
n
i
n
T
a
bl
e
5.
T
h
e
b
e
s
t
P
S
O
pa
r
a
m
e
t
e
r
s
a
r
e
c
1
=
0.
2,
c
2
=
0
.
5,
a
n
d
w=
0.
6,
wi
t
h
t
h
e
hi
g
h
e
s
t
a
c
c
ur
a
c
y
v
a
l
ue
.
T
hi
s
c
o
u
l
d
b
e
b
e
c
a
us
e
t
h
e
pa
r
t
i
c
l
e
m
o
ve
m
e
n
t
i
s
m
o
r
e
c
o
n
s
t
a
n
t
wh
e
n
t
h
e
c
1
a
n
d
c
2
pa
r
a
m
e
t
e
r
v
a
l
ue
s
a
r
e
t
h
e
s
a
m
e
;
t
h
e
w
v
a
l
ue
h
a
s
t
h
e
m
o
s
t
i
m
pa
c
t
o
n
t
h
e
pa
r
t
i
c
l
e
m
o
v
e
m
e
n
t
.
T
h
e
pa
r
t
i
c
l
e
s
m
o
ve
c
o
n
t
i
n
uo
us
l
y
w
h
e
n
t
h
e
c
1
a
n
d
c
2
pa
r
a
m
e
t
e
r
s
ha
v
e
d
i
f
f
e
r
e
n
t
v
a
l
ue
s
.
I
n
t
h
e
m
e
a
n
t
i
m
e
,
t
h
e
pa
r
t
i
c
l
e
m
o
v
e
m
e
n
t
w
i
l
l
be
do
m
i
na
t
e
d
by
t
h
e
pb
e
s
t
v
a
l
u
e
i
f
t
h
e
v
a
l
ue
o
f
pa
r
a
m
e
t
e
r
c
1
i
s
gr
e
a
t
e
r
a
n
d
t
h
e
gbe
s
t
v
a
l
ue
i
f
t
h
e
v
a
l
ue
o
f
pa
r
a
m
e
t
e
r
c
2
i
s
gr
e
a
t
e
r
.
I
n
c
a
s
e
t
h
e
w
v
a
l
u
e
i
s
too
hi
g
h
,
th
e
pa
r
t
i
c
l
e
w
i
ll
u
n
de
r
go
e
x
c
e
s
s
i
ve
ly
e
a
r
ly
mi
gr
a
t
i
o
n
.
I
n
a
dd
i
t
i
o
n
,
i
t
c
a
n
b
e
s
e
e
n
t
h
a
t
t
h
e
R
e
c
a
ll
a
n
d
F
1
-
s
c
o
r
e
v
a
l
ue
s
f
o
r
t
h
e
n
e
g
a
t
i
ve
c
l
a
s
s
a
r
e
v
e
r
y
l
o
w
c
o
m
pa
r
e
d
to
t
h
e
p
o
s
i
t
i
ve
c
l
a
s
s
.
T
hi
s
i
s
due
to
t
h
e
d
i
f
f
e
r
e
n
c
e
i
n
t
h
e
a
m
o
un
t
o
f
da
t
a
f
o
r
e
a
c
h
c
l
a
s
s
,
t
h
e
p
o
s
i
t
i
ve
c
l
a
s
s
h
a
s
m
uc
h
m
o
r
e
da
t
a
t
h
a
n
t
h
e
n
e
ga
t
i
v
e
c
l
a
s
s
.
T
h
e
r
e
f
o
r
e
,
f
ur
t
h
e
r
s
t
udi
e
s
a
r
e
n
e
e
d
e
d
o
n
h
o
w
to
mi
t
i
ga
t
e
im
ba
l
a
n
c
e
d
c
l
a
s
s
e
s
a
n
d
t
h
e
i
r
e
f
f
e
c
t
o
n
t
h
e
pe
r
f
o
r
m
a
n
c
e
o
f
S
VM
-
P
S
O.
T
a
bl
e
5.
R
e
s
u
l
t
s
o
f
S
VM
-
P
S
O
a
n
d
S
VM
c
1
c
2
w
A
c
c
u
r
a
c
y
P
r
e
c
is
i
o
n
R
e
c
a
ll
F1
-
s
c
o
r
e
-
1
1
-
1
1
-
1
1
0.2
0.2
0.4
97.36
100
97
12
100
22
99
0.2
0.2
0.6
97.45
87
98
18
100
29
99
0.2
0.2
0.9
97.40
100
97
14
100
24
99
0.2
0.5
0.6
97.61
94
98
22
100
35
99
0.5
0.2
0.6
97.53
100
98
18
100
30
99
S
V
M
97.28
89
97
11
100
19
99
3
.
5.
S
e
n
t
im
e
n
t
a
n
al
ys
is
E
v
a
l
ua
t
i
o
n
o
f
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
c
a
r
r
i
e
d
o
ut
us
i
n
g
t
e
x
t
bl
o
b
pr
o
duc
e
s
s
e
n
t
i
m
e
n
t
v
a
l
ue
s
,
w
hi
c
h
c
a
n
be
s
e
e
n
i
n
F
i
gur
e
4
.
B
a
s
e
d
o
n
t
hi
s
f
i
gur
e
,
i
t
c
a
n
be
s
e
e
n
t
h
a
t
t
h
e
r
e
vi
e
ws
h
a
v
e
m
a
ny
s
e
n
t
i
m
e
n
t
v
a
l
ue
s
t
h
a
t
l
e
a
n
to
wa
r
ds
n
e
utr
a
l
a
n
d
po
s
i
t
i
v
e
,
n
a
m
e
ly
-
0.
5
to
1
or
n
e
ut
r
a
l
to
p
o
s
i
t
i
v
e
w
i
t
h
a
c
o
un
t
o
f
3500
r
e
vi
e
w
s
.
F
i
gur
e
5
i
s
a
c
o
m
pa
r
i
s
o
n
c
ha
r
t
o
f
r
e
vi
e
ws
i
nc
l
ude
d
i
n
t
h
e
“
r
e
c
o
m
m
e
n
da
t
i
o
n
”
w
i
t
h
a
po
l
a
r
i
t
y
va
l
u
e
o
f
-
0.
5
to
1.
0
,
w
i
t
h
t
h
e
m
o
s
t
r
e
vi
e
w
s
o
n
n
e
ut
r
a
l
a
r
o
un
d
3
,
500,
whi
l
e
r
e
vi
e
ws
t
h
a
t
i
n
c
l
ude
“
n
o
r
e
c
o
m
m
e
n
da
t
i
o
n
”
h
a
ve
a
po
l
a
r
i
t
y
v
a
l
ue
o
f
-
0.
75
to
0
o
r
n
e
ga
t
i
ve
to
n
e
ut
r
a
l
a
s
m
uc
h
a
s
a
r
o
un
d
200.
W
i
t
h
r
e
vi
e
ws
t
h
a
t
h
a
v
e
ne
ut
r
a
l
a
n
d
p
o
s
i
t
i
ve
s
e
n
t
i
m
e
n
t
v
a
l
ue
s
,
t
h
i
s
ga
m
e
c
a
n
b
e
r
e
c
o
m
m
e
n
de
d
to
ot
h
e
r
pl
a
y
e
r
s
.
F
i
gur
e
4.
P
o
l
a
r
i
t
y
d
i
s
t
r
i
b
ut
i
o
n
o
f
da
t
a
r
e
vi
e
ws
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
13
,
N
o.
3
,
De
c
e
m
be
r
2
0
24
:
344
-
353
352
F
i
gur
e
5.
S
e
n
t
i
m
e
n
t
p
o
l
a
r
i
t
y
d
i
s
t
r
i
b
ut
i
o
n
o
f
r
e
vi
e
w
s
b
a
s
e
d
o
n
r
e
c
o
m
m
e
n
da
t
i
o
n
3.
CONC
L
USI
ON
T
h
e
S
VM
m
e
t
h
o
d
h
a
s
b
e
e
n
i
m
p
l
e
m
e
n
t
e
d
i
n
ga
m
e
s
e
n
t
i
m
e
n
t
a
n
a
ly
s
i
s
,
w
i
t
h
t
h
e
b
e
s
t
pa
r
a
m
e
t
e
r
b
e
i
ng
a
l
i
ne
a
r
ke
r
n
e
l
w
i
t
h
c
be
i
n
g
10.
T
h
e
e
x
p
e
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
s
h
o
w
t
h
a
t
t
h
e
n
e
ga
t
i
v
e
c
l
a
s
s
h
a
s
a
pr
e
c
i
s
i
o
n
o
f
89%
,
a
r
e
c
a
l
l
o
f
11%
,
a
n
d
a
F
1
-
s
c
o
r
e
o
f
19%
.
T
h
e
p
o
s
i
t
i
ve
c
l
a
s
s
ha
s
a
pr
e
c
i
s
i
o
n
v
a
l
ue
o
f
97%
,
a
r
e
c
a
l
l
v
a
l
ue
o
f
100%
,
a
n
d
a
n
F
1
-
s
c
o
r
e
v
a
l
ue
o
f
99%
.
T
h
e
a
c
c
u
r
a
c
y
v
a
l
ue
i
s
97.
28%
.
S
VM
o
p
t
i
mi
z
a
t
i
o
n
w
i
t
h
th
e
P
S
O
a
l
go
r
i
t
hm
i
s
c
a
r
r
i
e
d
o
u
t
us
i
n
g
d
i
f
f
e
r
e
n
t
pa
r
a
m
e
t
e
r
v
a
r
i
a
t
i
o
ns
.
T
h
e
hi
g
h
e
s
t
r
e
s
ul
t
s
a
r
e
w
i
t
h
v
a
l
ue
s
o
f
c
1
=
0.
2
,
c
2
=
0.
5,
a
n
d
w
=
0.
6,
a
n
d
t
h
e
a
c
c
ur
a
c
y
i
s
97.
61%
.
T
h
e
e
v
a
l
ua
t
i
o
n
v
a
l
ue
f
o
r
t
h
e
n
e
ga
t
i
v
e
c
l
a
s
s
i
s
a
pr
e
c
i
s
i
o
n
o
f
94%
,
a
r
e
c
a
l
l
o
f
22%
,
a
n
d
a
f
1
-
s
c
o
r
e
o
f
45%
.
M
e
a
n
w
hil
e
,
t
h
e
po
s
i
t
i
v
e
c
l
a
s
s
h
a
s
a
pr
e
c
i
s
i
o
n
o
f
98%
,
a
r
e
c
a
l
l
o
f
100%
,
a
n
d
a
f
1
-
s
c
o
r
e
o
f
99%
.
S
VM
-
P
S
O
h
a
s
a
high
e
r
a
c
c
ur
a
c
y
o
f
0.
33%
c
o
m
pa
r
e
d
t
o
t
h
e
S
VM
b
a
s
e
m
o
de
l
.
W
i
t
h
a
s
e
n
t
i
m
e
n
t
r
a
t
i
n
g
r
a
n
g
i
ng
f
r
o
m
n
e
ut
r
a
l
t
o
po
s
i
t
i
v
e
,
t
hi
s
ga
m
e
c
a
n
be
r
e
c
o
m
m
e
n
d
e
d
to
ot
h
e
r
p
l
a
y
e
r
s
.
T
h
e
a
pp
l
i
c
a
t
i
o
n
o
f
wo
r
d
e
m
b
e
dd
i
ng,
s
uc
h
a
s
wo
r
d
2v
e
c
o
r
B
E
R
T
,
a
n
d
s
tr
a
t
e
gi
e
s
f
o
r
m
a
n
a
g
i
ng
t
h
e
i
mb
a
l
a
n
c
e
d
da
t
a
s
e
t
b
e
t
we
e
n
po
s
i
t
i
v
e
a
n
d
n
e
ga
t
i
v
e
c
l
a
s
s
e
s
wo
ul
d
b
e
t
a
ke
n
i
n
t
o
c
o
n
s
i
de
r
a
t
i
o
n
f
o
r
f
ur
t
h
e
r
r
e
s
e
a
r
c
h
.
RE
F
E
R
E
NC
E
S
[
1]
A
.
B
a
nkhur
s
t,
“
S
t
e
a
m
br
e
a
ks
it
s
o
w
n
c
o
n
c
ur
r
e
nt
r
e
c
o
r
d
a
s
30
mi
ll
i
o
n
us
e
r
s
w
e
r
e
o
nl
in
e
a
t
o
n
e
ti
m
e
th
is
w
e
e
ke
nd
-
ig
n
s
o
ut
h
e
a
s
t
a
s
ia
,”
IG
N
Sout
he
as
t
A
s
ia
,
2022.
ht
tp
s
:/
/s
e
a
.i
gn.c
o
m/
s
t
e
a
m
-
de
c
k/
191728/ne
w
s
/s
te
a
m
-
br
e
a
ks
-
its
-
o
w
n
-
c
o
n
c
u
r
r
e
nt
-
r
e
c
o
r
d
-
as
-
30
-
mi
ll
i
o
n
-
us
e
r
s
-
w
e
r
e
-
o
n
li
ne
-
at
-
o
n
e
-
ti
m
e
-
th
is
-
w
e
e
k
e
nd.
[
2]
Z
.
Z
w
i
e
z
e
n,
“
T
h
e
e
r
a
of
$70
ga
m
e
s
tr
ul
y
be
g
in
s
th
is
f
a
ll
,”
k
ot
ak
u
,
2022.
ht
tp
s
:/
/k
o
ta
ku.
c
o
m
/7
0
-
d
o
ll
a
r
-
ga
m
e
s
-
60
-
ubi
s
of
t
-
ea
-
go
th
a
m
-
kni
gh
ts
-
ps
5
-
x
b
ox
-
1849593604 (
a
c
c
e
s
s
e
d S
e
p. 28, 2022
)
.
[
3]
G
.
A
ndr
e
e
v
,
D
.
S
a
xe
na
,
a
nd
J
.
K
.
V
e
r
ma
,
“
I
mpa
c
t
of
r
e
v
i
e
w
s
e
nt
im
e
nt
a
nd
ma
gni
tu
de
o
n
c
us
t
o
m
e
r
s
’
r
e
c
o
mm
e
nda
ti
o
ns
f
o
r
vi
de
o
ga
m
e
s
,”
in
2021
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on
C
om
put
at
io
nal
P
e
r
f
or
m
anc
e
E
v
al
uat
io
n,
C
om
P
E
2021
,
D
e
c
.
2
021,
pp. 992
–
995, do
i:
10.1109/C
o
mP
E
53109.2021.9752380.
[
4]
B
.
L
iu
,
Se
nt
ime
nt
analy
s
is
:
M
in
in
g opini
ons
, s
e
nt
ime
nt
s
, and e
m
ot
io
ns
. C
a
mbr
id
ge
U
ni
ve
r
s
it
y
P
r
e
s
s
, 2015.
[
5]
A
.
L
ig
th
a
r
t,
C
.
C
a
ta
l
,
a
nd
B
.
T
e
ki
n
e
r
d
o
ga
n,
“
S
y
s
te
ma
ti
c
r
e
v
i
e
w
s
in
s
e
nt
im
e
n
t
a
na
l
y
s
is
:
a
te
r
ti
a
r
y
s
tu
d
y
,”
A
r
ti
f
ic
ia
l
I
nt
e
ll
ig
e
nc
e
R
e
v
ie
w
, vol
. 54, n
o
. 7, pp. 4997
–
5053, Oc
t.
2021, d
o
i
:
10.1007/
s
10462
-
021
-
09973
-
3.
[
6]
L
.
M
o
s
ta
f
a
,
“
S
tu
d
e
nt
s
e
nt
im
e
n
t
a
na
l
y
s
is
us
in
g
ga
mi
f
i
c
a
ti
o
n
f
or
e
duc
a
ti
o
n
c
o
nt
e
x
t,
”
in
A
dv
anc
e
s
in
I
nt
e
ll
ig
e
nt
Sy
s
te
m
s
and
C
om
put
in
g
, vo
l.
1058, 2020, pp. 329
–
339.
[
7]
R
.
S
e
ti
a
budi
,
N
.
M
.
S
.
I
s
w
a
r
i,
a
nd
A
.
R
u
s
li
,
“
E
nha
nc
in
g
te
x
t
c
la
s
s
if
i
c
a
ti
o
n
pe
r
f
o
r
ma
n
c
e
b
y
pr
e
p
r
o
c
e
s
s
in
g
mi
s
s
pe
ll
e
d
w
o
r
d
s
in
I
ndo
n
e
s
ia
n
la
ngua
ge
,”
Te
lk
om
ni
k
a
(
T
e
le
c
om
m
uni
c
at
io
n
C
om
put
in
g
E
le
c
tr
oni
c
s
and
C
ont
r
ol
)
,
vo
l.
19,
no
.
4,
pp.
1234
–
1241,
A
ug. 2021, do
i:
10.12928/
T
E
L
K
O
M
N
I
K
A
.
v
19i
4.20369.
[
8]
B
.
A
lB
a
da
ni
,
R
.
S
hi
,
a
nd
J
.
D
o
ng,
“
A
n
ove
l
ma
c
hi
ne
le
a
r
n
i
ng
a
ppr
o
a
c
h
f
o
r
s
e
nt
im
e
nt
a
na
l
y
s
is
o
n
T
w
it
t
e
r
in
c
o
r
p
o
r
a
ti
ng
th
e
uni
ve
r
s
a
l
la
ngua
ge
m
o
d
e
l
f
in
e
-
tu
ni
ng
a
nd
S
V
M
,”
A
ppl
ie
d
Sy
s
te
m
I
nnov
at
io
n
,
v
o
l.
5,
n
o
.
1,
p.
13,
J
a
n.
2022,
do
i:
10.3390/as
i5
010013.
[
9]
I
.
M
.
U
r
r
iz
a
a
nd
M
.
A
.
A
.
C
la
r
in
o
,
“
A
s
pe
c
t
-
ba
s
e
d
s
e
nt
im
e
nt
a
na
l
y
s
is
of
us
e
r
c
r
e
a
te
d
ga
m
e
r
e
v
i
e
w
s
,”
in
202
1
24t
h
C
onf
e
r
e
nc
e
o
f
th
e
O
r
ie
nt
al
C
O
C
O
SD
A
I
nt
e
r
nat
io
nal
C
om
m
it
te
e
f
o
r
th
e
C
o
-
O
r
di
nat
io
n
and
St
andar
di
s
at
io
n
of
Spe
e
c
h
D
at
aba
s
e
s
and
A
s
s
e
s
s
m
e
nt
T
e
c
hni
que
s
, O
-
C
O
C
O
SD
A
2021
, N
o
v
. 2021, pp. 76
–
81, do
i:
10.1109/O
-
C
O
C
O
S
D
A
202152914.2021.9660559.
[
10]
Y
.
H
a
C
o
h
e
n
-
K
e
r
n
e
r
,
D
.
M
il
le
r
,
a
nd
Y
.
Y
ig
a
l,
“
T
h
e
in
f
lu
e
n
c
e
of
pr
e
p
r
o
c
e
s
s
in
g
o
n
t
e
x
t
c
la
s
s
if
i
c
a
ti
o
n
us
in
g
a
ba
g
-
of
-
w
o
r
ds
r
e
pr
e
s
e
n
ta
ti
o
n,”
P
L
oS O
N
E
,
vo
l.
15, n
o
. 5, p.
e
0232525, M
a
y
2
020, do
i:
10.1371/j
o
u
r
na
l.
p
o
ne
.0232525.
[
11]
J
.
Y
.
T
a
n,
A
.
S
.
K
.
C
ho
w
,
a
nd
C
.
W
.
T
a
n,
“
A
c
o
mpa
r
a
ti
ve
s
tu
d
y
of
ma
c
hi
ne
l
e
a
r
ni
ng
a
lg
o
r
i
th
ms
f
o
r
s
e
nt
im
e
nt
a
na
l
y
s
is
of
g
a
me
r
e
v
i
e
w
s
,”
T
he
J
our
nal
of
T
he
I
ns
ti
tu
ti
on o
f
E
ngi
ne
e
r
s
, M
al
ay
s
i
a
, vo
l.
82, n
o
. 3, N
ov
. 2022, d
o
i:
10.54552/
v
82i
3.101.
[
12]
S
. R
us
e
ti
, M
. D
.
S
ir
bu,
M
. A
. C
a
li
n
, M
. D
a
s
c
a
lu
, S
.
T
r
a
us
a
n
-
M
a
tu
, a
nd G
.
M
il
it
a
r
u, “
C
o
mpr
e
h
e
ns
iv
e
e
x
pl
or
a
ti
o
n
of
ga
me
r
e
v
i
e
w
s
e
x
tr
a
c
ti
o
n
a
nd
o
pi
ni
o
n
mi
ni
ng
us
in
g
nl
p
te
c
hni
qu
e
s
,”
in
A
d
v
anc
e
s
in
I
nt
e
ll
ig
e
nt
Sy
s
te
m
s
and
C
om
put
in
g
,
v
o
l.
1041,
20
20,
pp. 323
–
331.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
Optimiz
e
d
s
uppor
t
v
e
c
tor
mac
hine
f
or
s
e
nti
me
nt
analys
is
of
game
r
e
v
ie
w
s
(
B
r
y
an
L
e
onar
do
Supr
iyat
na
)
353
[
13]
P
.
D
.
W
in
dha
M
e
ga
a
nd
H
a
r
y
ok
o
,
“
O
pt
im
i
z
a
ti
o
n
of
pa
r
a
m
e
t
e
r
s
uppo
r
t
ve
c
t
o
r
ma
c
hi
n
e
(
S
V
M
)
us
in
g
g
e
ne
ti
c
a
lg
or
it
hm
t
o
r
e
vi
e
w
go
-
j
e
k
’
s
s
e
r
vi
c
e
s
,”
in
2019
4t
h
I
nt
e
r
nat
io
nal
C
on
f
e
r
e
nc
e
o
n
I
nf
or
m
at
io
n
T
e
c
hnol
ogy
,
I
n
f
or
m
at
io
n
S
y
s
te
m
s
and
E
le
c
t
r
ic
al
E
ngi
ne
e
r
in
g, I
C
I
T
I
SE
E
2019
, N
ov
. 2019, pp
. 301
–
304, d
o
i
:
10.
1109/I
C
I
T
I
S
E
E
48480.2019.9003894.
[
14]
R
.
O
bi
e
da
t
e
t
al
.
,
“
S
e
nt
im
e
nt
a
na
l
y
s
is
of
c
us
t
o
me
r
s
’
r
e
v
i
e
w
s
us
in
g
a
hy
b
r
id
e
vol
ut
i
o
na
r
y
S
V
M
-
ba
s
e
d
a
ppr
o
a
c
h
in
a
n
im
ba
la
nc
e
d
da
ta
di
s
tr
ib
ut
io
n,”
I
E
E
E
A
c
c
e
s
s
, v
o
l.
10, pp. 22260
–
22273, 202
2, do
i:
10.1
109/
A
C
C
E
S
S
.2022.3149482.
[
15]
V
.
M
a
li
k,
R
.
M
it
ta
l,
J
.
S
in
gh,
V
.
R
a
tt
a
n,
a
nd
A
.
M
it
ta
l,
“
F
e
a
tu
r
e
s
e
l
e
c
ti
o
n
o
pt
i
mi
z
a
ti
o
n
us
in
g
A
C
O
t
o
im
pr
ove
th
e
c
la
s
s
if
i
c
a
t
io
n
pe
r
f
or
ma
nc
e
of
w
e
b
l
o
g da
ta
,”
i
n
P
r
oc
e
e
di
ngs
of
t
he
8t
h
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on Signal
P
r
oc
e
s
s
in
g and I
nt
e
gr
at
e
d N
e
tw
o
r
k
s
,
SP
I
N
2021
, A
ug. 2021, pp. 671
–
675, do
i
:
10.1109/S
P
I
N
52536.
2021.9566126.
[
16]
H
.
Y
a
f
i
e
,
“
B
a
ld
ur
’
s
ga
te
3
s
t
e
a
m
r
e
v
i
e
w
s
,”
k
aggl
e
,
2024.
ht
tp
s
:/
/ww
w
.ka
ggl
e
.c
o
m/
da
ta
s
e
ts
/h
a
r
is
y
a
f
i
e
/b
a
ld
ur
s
-
ga
te
-
3
-
s
t
e
a
m
-
r
e
v
i
e
w
s
.
[
17]
D
.
G
una
w
a
n,
F
.
P
.
P
ut
r
i,
a
nd
H
.
M
e
id
ia
,
“
B
e
r
s
h
c
a
:
b
r
i
ngi
ng
c
ha
tb
o
t
in
t
o
h
o
t
e
l
in
dus
tr
y
in
I
nd
o
n
e
s
ia
,”
T
e
lk
om
ni
k
a
(
T
e
le
c
om
m
uni
c
at
io
n
C
om
put
in
g
E
le
c
tr
oni
c
s
and
C
ont
r
ol
)
,
vol
.
18,
n
o
.
2,
pp.
839
–
845,
A
pr
.
2
020,
do
i:
10.12928/
T
E
L
K
O
M
N
I
K
A
.V
18I
2.14841.
[
18]
S
.
W
.
K
im
a
nd
J
.
M
.
G
il
,
“
R
e
s
e
a
r
c
h
pa
pe
r
c
la
s
s
i
f
i
c
a
ti
o
n
s
y
s
te
ms
ba
s
e
d
o
n
T
F
-
I
D
F
a
nd
L
D
A
s
c
he
me
s
,”
H
um
an
-
c
e
nt
r
ic
C
om
put
in
g and I
nf
or
m
at
io
n Sc
ie
n
c
e
s
, v
o
l.
9, n
o
. 1, p. 30, De
c
.
2019, do
i:
10.1186/s
13673
-
019
-
0192
-
7.
[
19]
S
.
M
a
la
ka
r
,
S
.
S
e
n,
S
.
R
oma
nov
,
D
.
K
a
pl
un,
a
nd
R
.
S
a
r
ka
r
,
“
R
o
l
e
of
t
r
a
ns
f
e
r
f
un
c
ti
o
ns
in
P
S
O
t
o
s
e
l
e
c
t
di
a
gn
o
s
ti
c
a
tt
r
ib
ut
e
s
f
o
r
c
hr
o
ni
c
di
s
e
a
s
e
pr
e
di
c
ti
o
n:
A
n
e
x
p
e
r
im
e
nt
a
l
s
tu
d
y
,”
J
our
nal
of
K
in
g
Saud
U
ni
v
e
r
s
it
y
-
C
om
put
e
r
and
I
nf
o
r
m
at
io
n
Sc
ie
n
c
e
s
,
vo
l.
35, n
o
. 9, p. 101757, O
c
t.
2023, d
o
i:
10.1016/j
.j
ks
u
c
i.
2
023.
101757.
[
20]
D
.
K
.
C
h
o
ub
e
y
,
S
.
T
r
ip
a
th
i,
P
.
K
uma
r
,
V
.
S
hukl
a
,
a
nd
V
.
K
.
D
ha
ndha
ni
a
,
“
C
la
s
s
if
ic
a
ti
o
n
of
D
ia
b
e
t
e
s
b
y
K
e
r
n
e
l
b
a
s
e
d
S
V
M
w
it
h
P
S
O
,”
R
e
c
e
nt
A
dv
anc
e
s
in
C
om
put
e
r
Sc
ie
nc
e
and
C
o
m
m
uni
c
at
io
ns
,
v
ol
.
14,
n
o
.
4,
pp.
1242
–
1255,
J
ul
.
2019,
do
i:
10.21
74/
2213275912666190716094836.
[
21]
D
.
S
a
put
r
a
,
W
.
S
.
D
ha
r
ma
w
a
n,
a
nd
W
.
I
r
ma
y
a
ni
,
“
P
e
r
f
or
ma
nc
e
c
o
mpa
r
is
o
n
of
th
e
S
V
M
a
nd
S
V
M
-
P
S
O
a
lg
o
r
it
hms
f
o
r
h
e
a
r
t
di
s
e
a
s
e
pr
e
di
c
ti
o
n,”
I
nt
e
r
nat
io
nal
J
our
nal
of
A
dv
anc
e
s
in
D
at
a
and
I
nf
or
m
at
io
n
Sy
s
te
m
s
,
v
o
l.
3,
n
o
.
2,
pp.
74
–
86,
N
ov
.
2022,
do
i:
10.25008/i
ja
di
s
.v
3i
2.1243.
[
22]
D
.
A
.
P
is
ne
r
a
nd
D
.
M
.
S
c
hn
y
e
r
,
“
S
upp
or
t
v
e
c
t
or
ma
c
hi
n
e
,”
in
M
ac
hi
ne
L
e
ar
ni
ng:
M
e
th
ods
and
A
ppl
ic
at
io
ns
to
B
r
ai
n
D
is
or
d
e
r
s
,
E
ls
e
v
i
e
r
, 2019, pp. 101
–
121.
[
23]
J
.
C
e
r
v
a
nt
e
s
,
F
.
G
a
r
c
ia
-
L
a
m
o
nt
,
L
.
R
o
d
r
íg
u
ez
-
M
a
z
a
hua
,
a
nd
A
.
L
o
p
e
z
,
“
A
c
o
mp
r
e
h
e
ns
i
ve
s
ur
ve
y
o
n
s
upp
o
r
t
ve
c
t
o
r
ma
c
h
in
e
c
la
s
s
if
i
c
a
ti
o
n:
A
ppl
ic
a
ti
o
ns
,
c
ha
ll
e
ng
e
s
a
nd
tr
e
nds
,”
N
e
ur
oc
om
put
in
g
,
vo
l.
408,
pp.
189
–
215,
S
e
p.
2020,
do
i:
10.1016/j
.n
e
u
c
o
m.2019.10.118.
[
24]
D
.
K
.
D
a
ke
a
nd
E
.
G
y
im
a
h,
“
U
s
in
g
s
e
nt
im
e
nt
a
na
l
y
s
is
t
o
e
v
a
lu
a
te
qua
li
ta
ti
ve
s
tu
de
nt
s
’
r
e
s
po
ns
e
s
,”
E
duc
at
io
n
and
I
nf
or
m
at
io
n
T
e
c
hnol
ogi
e
s
, v
o
l.
28, n
o
. 4, pp. 4629
–
4647, Ap
r
. 2023, d
o
i:
10
.1007/s
10639
-
022
-
11349
-
1.
[
25]
K
.
V
.
K
a
m
r
a
n,
B
.
F
e
i
z
i
z
a
de
h,
B
.
K
h
o
r
r
a
mi
,
a
nd
Y
.
E
ba
di
,
“
A
c
o
mpa
r
a
ti
ve
a
p
pr
o
a
c
h
of
s
uppor
t
ve
c
t
o
r
ma
c
hi
n
e
k
e
r
ne
l
f
un
c
ti
o
ns
f
or
G
I
S
-
ba
s
e
d
la
nds
li
d
e
s
us
c
e
pt
ib
il
it
y
ma
ppi
ng,”
A
ppl
ie
d
G
e
om
at
ic
s
,
v
o
l.
13,
n
o
.
4,
pp.
837
–
851,
D
e
c
.
20
21,
do
i:
10.1007/s
12518
-
021
-
00393
-
0.
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
Bry
a
n
Leo
n
a
rdo
Su
pri
y
a
tn
a
w
as
b
o
rn
i
n
T
an
g
e
ran
g
,
A
u
g
u
s
t
2
0
,
1
9
9
9
,
g
rad
u
at
e
d
fro
m
h
i
s
s
t
u
d
i
e
s
at
Mu
l
t
i
med
i
a
N
u
s
an
t
ara
U
n
i
v
e
rs
i
t
y
i
n
2
0
2
3
w
i
t
h
a
m
a
j
o
r
i
n
Bac
h
el
o
r
o
f
In
fo
r
m
at
i
c
s
.
H
e
i
s
i
n
t
e
r
e
s
t
ed
i
n
d
at
ab
as
e
a
d
m
i
n
i
s
t
rat
i
o
n
,
fr
o
n
t
-
e
n
d
w
e
b
s
i
t
e
d
ev
e
l
o
p
men
t
,
an
d
ro
i
d
d
e
v
el
o
p
me
n
t
an
d
m
a
c
h
i
n
e
l
e
ar
n
i
n
g
.
H
e
h
as
i
n
t
e
r
n
e
d
as
a
w
e
b
s
i
t
e
d
ev
e
l
o
p
e
r
fo
r
W
3
O
In
d
o
S
c
i
en
t
i
a.
H
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
ai
l
:
l
e
o
n
ard
o
s
.
b
r
y
an
@
g
m
a
i
l
.
co
m
.
F
a
ri
ca
P
erda
n
a
P
u
tr
i
w
as
b
o
rn
o
n
J
an
u
ar
y
3
1
,
1
9
9
3
i
n
I
n
d
o
n
e
s
i
a.
S
h
e
r
ecei
v
ed
a
b
ac
h
e
l
o
r's
d
e
g
r
ee
i
n
co
m
p
u
t
e
r
s
c
i
e
n
ce
fr
o
m
U
n
i
v
e
rs
i
t
as
Mu
l
t
i
me
d
i
a
N
u
s
an
t
ara
i
n
2
0
1
4
an
d
an
M.
Sc.
i
n
c
o
m
p
u
t
e
r
s
ci
en
ce
fro
m
N
at
i
o
n
a
l
T
ai
w
an
U
n
i
v
ers
i
t
y
i
n
2
0
1
7
.
Sh
e
cu
rr
e
n
t
l
y
w
o
rk
s
as
a
l
ec
t
u
r
e
r
at
U
n
i
v
e
rs
i
t
as
Mu
l
t
i
med
i
a
N
u
s
an
t
ara
an
d
i
s
p
u
rs
u
i
n
g
h
e
r
P
h
.
D
.
at
U
CS
I
U
n
i
v
e
rs
i
t
y
.
H
e
r
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
m
ai
n
l
y
fo
cu
s
i
n
s
em
a
n
t
i
c
an
a
l
y
s
i
s
o
n
n
at
u
ral
l
an
g
u
a
g
e
p
ro
ce
s
s
i
n
g
(N
L
P),
art
i
fi
ci
al
i
n
t
el
l
i
g
en
ce
,
c
o
m
p
u
t
e
r
v
i
s
i
o
n
,
m
a
ch
i
n
e
l
e
ar
n
i
n
g
,
a
n
d
r
e
l
at
e
d
fi
el
d
s
,
w
h
e
r
e
s
h
e
h
as
s
u
cce
s
s
fu
l
l
y
b
ee
n
g
ran
t
e
d
s
o
me
r
e
s
e
ar
c
h
g
ra
n
t
s
fro
m
t
h
e
g
o
v
e
r
n
me
n
t
.
S
h
e
c
an
b
e
c
o
n
t
ac
t
e
d
at
em
a
i
l
:
far
i
c
a
@
u
mn
.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.