I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
,
p
p
.
506
~
514
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
1
.
p
p
5
0
6
-
5
1
4
506
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Autom
a
ted
ergo
no
mic sitting po
st
u
res det
ection
for
o
ff
ice
wo
rksta
tion usin
g
XG
Bo
o
st m
ethod
T
here
s
ia
Am
elia
P
a
wit
ra
1
,
F
a
rida
Dj
um
ia
t
i Sit
a
nia
1
,
Ani
nd
it
a
Septia
rini
2
,
H
a
m
da
ni
H
a
m
da
ni
2
1
D
e
p
a
r
t
me
n
t
o
f
I
n
d
u
s
t
r
i
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
M
u
l
a
w
a
r
m
a
n
U
n
i
v
e
r
si
t
y
,
S
a
mari
n
d
a
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
M
u
l
a
w
a
r
m
a
n
U
n
i
v
e
r
si
t
y
,
S
a
mari
n
d
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
8
,
2
0
2
4
R
ev
is
ed
No
v
1
7
,
2
0
2
5
Acc
ep
ted
Dec
1
5
,
2
0
2
5
S
e
d
e
n
tary
o
ffice
wo
r
k
in
c
re
a
se
s
m
u
sc
u
lo
sk
e
leta
l
ris
k
,
u
n
d
e
rsc
o
rin
g
t
h
e
n
e
e
d
fo
r
n
o
n
-
i
n
tr
u
siv
e
,
re
a
l
-
ti
m
e
p
o
stu
re
m
o
n
it
o
rin
g
.
Th
is
st
u
d
y
p
re
se
n
ts
a
c
o
m
p
u
ter
v
isio
n
a
p
p
r
o
a
c
h
t
h
a
t
c
las
sifies
e
rg
o
n
o
m
ic
v
e
rsu
s
n
o
n
-
e
rg
o
n
o
m
ic
sitt
in
g
p
o
st
u
re
s
u
sin
g
u
p
p
e
r
b
o
d
y
k
e
y
p
o
i
n
ts
e
x
trac
ted
b
y
M
o
v
e
Ne
t
th
u
n
d
e
r
.
Im
a
g
e
s
fro
m
3
0
p
a
rti
c
ip
a
n
ts
we
re
c
a
p
tu
re
d
fro
m
fro
n
tal
a
n
d
si
d
e
v
iew
s
,
a
n
d
lab
e
led
a
c
c
o
rd
i
n
g
t
o
S
NI
9
0
1
1
:
2
0
2
1
c
rit
e
ria.
S
e
v
e
n
tee
n
k
e
y
p
o
in
ts
we
re
d
e
tec
ted
,
with
h
e
a
d
-
to
-
h
ip
la
n
d
m
a
rk
s
re
tain
e
d
,
th
e
n
n
o
rm
a
li
z
e
d
a
n
d
c
e
n
te
re
d
.
Th
re
e
c
las
sifiers
—
a
d
a
p
ti
v
e
b
o
o
sti
n
g
(Ad
a
Bo
o
st),
e
x
t
re
m
e
g
ra
d
ien
t
b
o
o
st
in
g
(XG
Bo
o
st),
a
n
d
a
m
u
lt
i
-
lay
e
r
p
e
rc
e
p
tro
n
(
M
LP
)
—
we
re
tr
a
in
e
d
a
n
d
e
v
a
lu
a
ted
wit
h
10
-
fo
l
d
stra
ti
fied
c
ro
ss
-
v
a
li
d
a
ti
o
n
.
XG
Bo
o
st
a
c
h
i
e
v
e
d
t
h
e
b
e
st
p
e
rfo
rm
a
n
c
e
,
wit
h
a
c
c
u
ra
c
y
9
3
.
0
%
±1
.
9
%
,
p
re
c
isio
n
9
4
.
6
%
,
re
c
a
ll
9
1
.
4
%
,
F
1
-
sc
o
re
9
2
.
9
%
,
a
n
d
a
re
a
u
n
d
e
r
t
h
e
re
c
e
iv
e
r
o
p
e
ra
ti
n
g
c
h
a
ra
c
teristic
c
u
rv
e
(ROC
-
AU
C)
0
.
9
7
4
±0
.
0
1
0
,
o
u
tp
e
rf
o
rm
in
g
M
LP
a
n
d
Ad
a
B
o
o
st.
T
h
e
m
e
th
o
d
s
u
p
p
o
rts
p
ri
v
a
c
y
-
p
re
se
rv
i
n
g
,
o
n
-
d
e
v
ice
i
n
fe
re
n
c
e
a
n
d
is
su
it
a
b
le
fo
r
in
teg
ra
ti
o
n
in
t
o
sm
a
rt
o
ffice
s
y
ste
m
s
to
re
d
u
c
e
e
x
p
o
su
re
to
h
i
g
h
-
ris
k
p
o
stu
re
s.
Li
m
it
a
ti
o
n
s
in
c
lu
d
e
c
o
n
tro
ll
e
d
c
a
p
t
u
re
c
o
n
d
i
ti
o
n
s
a
n
d
a
n
u
p
p
e
r
-
b
o
d
y
f
o
c
u
s;
fu
t
u
re
wo
r
k
will
e
x
p
a
n
d
p
o
stu
re
tax
o
n
o
m
y
a
n
d
re
a
l
-
wo
rld
d
e
p
lo
y
m
e
n
t.
K
ey
w
o
r
d
s
:
C
o
m
p
u
ter
v
is
io
n
E
r
g
o
n
o
m
ic
s
itti
n
g
p
o
s
tu
r
e
Ma
ch
in
e
lear
n
in
g
Mo
v
eNe
t
Mu
s
cu
lo
s
k
eleta
l d
is
o
r
d
er
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
:
T
h
er
esia A
m
elia
Pawitr
a
Dep
ar
tm
en
t o
f
I
n
d
u
s
tr
ial
E
n
g
i
n
ee
r
in
g
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
Mu
lawa
r
m
an
U
n
iv
er
s
ity
Sam
b
aliu
n
g
No
.
9
,
Sam
ar
in
d
a
7
5
1
1
9
,
I
n
d
o
n
esia
E
m
ail:
tr
iciap
awitr
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
W
o
r
k
in
co
n
tem
p
o
r
ar
y
o
f
f
ice
s
is
lar
g
ely
s
cr
ee
n
/d
esk
-
ce
n
ter
ed
,
leav
in
g
e
m
p
lo
y
ee
s
s
ea
ted
f
o
r
n
ea
r
ly
f
o
u
r
-
f
if
th
s
o
f
th
e
wo
r
k
d
a
y
[
1
]
.
T
h
is
s
ettin
g
co
r
r
elate
s
with
wid
esp
r
ea
d
h
ea
lth
co
m
p
lain
ts
,
n
o
tab
ly
m
u
s
cu
lo
s
k
eleta
l
d
is
o
r
d
er
s
(
M
SDs
)
an
d
co
m
p
u
te
r
v
is
io
n
s
y
n
d
r
o
m
e;
s
u
r
v
ey
s
r
ep
o
r
t
b
ac
k
p
a
in
in
n
ea
r
ly
h
alf
o
f
wo
r
k
er
s
an
d
ey
e
p
ain
in
a
b
o
u
t
o
n
e
-
f
if
th
,
with
a
p
p
ar
e
n
t
k
n
o
ck
-
o
n
ef
f
ec
ts
f
o
r
p
r
o
d
u
ct
iv
ity
th
r
o
u
g
h
b
o
t
h
ab
s
en
teeism
an
d
p
r
esen
teeism
(
wo
r
k
in
g
d
esp
ite
illn
ess
)
.
T
h
ese
p
atter
n
s
h
ig
h
lig
h
t
th
e
im
p
o
r
tan
ce
o
f
p
r
ev
en
tiv
e
an
d
p
r
o
ac
tiv
e
er
g
o
n
o
m
ics in
th
e
wo
r
k
p
lace
[
2
]
.
Alth
o
u
g
h
s
ed
en
tar
y
tim
e
in
clu
d
es a
ll lo
w
-
in
ten
s
ity
ac
tiv
ities
,
s
it
tin
g
d
o
m
in
ates
in
o
f
f
ice
s
ettin
g
s
.
Pro
lo
n
g
e
d
s
itti
n
g
is
ass
o
ciate
d
with
v
ar
io
u
s
h
ea
lth
r
is
k
s
,
s
u
ch
as
ey
e
s
tr
ain
,
o
b
esit
y
,
ty
p
e
2
d
iab
etes,
p
o
o
r
n
u
tr
itio
n
,
h
ig
h
ch
o
lest
er
o
l,
ca
r
d
i
o
v
ascu
l
ar
d
is
ea
s
e,
ce
r
tain
ca
n
ce
r
s
,
an
d
MSDs
[
3
]
–
[
5
]
.
T
ar
g
eted
co
u
n
ter
m
ea
s
u
r
es
in
c
lu
d
e
s
ch
ed
u
lin
g
r
eg
u
lar
,
b
r
ief
b
r
ea
k
s
th
at
f
o
llo
w
er
g
o
n
o
m
ic
g
u
id
elin
es
d
u
r
in
g
p
r
o
lo
n
g
ed
d
esk
wo
r
k
[
4
]
,
[
5
]
.
E
q
u
ally
im
p
o
r
tan
t
is
m
ain
tai
n
in
g
c
o
r
r
ec
t
s
ea
ted
p
o
s
tu
r
e,
as
p
o
o
r
alig
n
m
en
t
is
a
k
n
o
wn
co
n
tr
ib
u
to
r
to
MSDs
[
5
]
–
[
7
]
.
E
m
b
e
d
d
in
g
er
g
o
n
o
m
ics
in
to
d
ay
-
to
-
d
ay
wo
r
k
p
r
ac
tices is
th
er
ef
o
r
e
a
c
en
tr
al
s
tr
ateg
y
f
o
r
r
ed
u
cin
g
s
it
tin
g
-
r
elate
d
r
is
k
s
[
4
]
.
Ass
es
s
in
g
er
g
o
n
o
m
ic
s
itti
n
g
p
o
s
tu
r
e
ty
p
ically
r
eq
u
ir
es
m
ea
s
u
r
in
g
m
u
ltip
le
b
o
d
y
s
eg
m
e
n
ts
,
wh
ich
is
d
is
r
u
p
tiv
e
an
d
im
p
r
ac
tical
at
s
ca
le.
T
h
er
ef
o
r
e,
au
to
m
ated
s
y
s
tem
s
ar
e
n
ec
ess
ar
y
to
class
i
f
y
p
o
s
tu
r
e
as
eith
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
erg
o
n
o
mic
s
itti
n
g
p
o
s
tu
r
es d
etec
tio
n
fo
r
o
ffice
w
o
r
ksta
tio
n
u
s
in
g
…
(
Th
eres
ia
A
melia
P
a
w
itr
a
)
507
er
g
o
n
o
m
ic
o
r
n
o
n
-
er
g
o
n
o
m
i
c
with
o
u
t
r
eq
u
ir
in
g
m
an
u
al
m
ea
s
u
r
em
en
t.
Pre
v
i
o
u
s
s
tu
d
i
es
h
av
e
em
p
lo
y
ed
s
en
s
o
r
-
b
ased
an
d
m
ac
h
in
e
lea
r
n
in
g
m
et
h
o
d
s
f
o
r
p
o
s
tu
r
e
d
et
ec
tio
n
,
p
r
o
v
id
in
g
ac
cu
r
ate
r
ea
l
-
tim
e
f
ee
d
b
ac
k
,
b
u
t
o
f
ten
r
ely
in
g
o
n
wea
r
ab
le
o
r
ex
ter
n
al
d
e
v
ices
[
3
]
,
[
8
]
–
[
1
1
]
.
R
ap
id
p
r
o
g
r
ess
in
co
m
p
u
ter
v
is
io
n
,
p
r
o
p
elled
b
y
d
ee
p
lear
n
in
g
,
h
as
tr
an
s
f
o
r
m
ed
au
to
m
atio
n
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
[
1
2
]
.
Dep
lo
y
e
d
ap
p
licatio
n
s
s
p
an
3
D
r
ec
o
n
s
tr
u
ctio
n
f
r
o
m
2
D
im
ag
er
y
,
r
o
b
o
t
g
u
i
d
an
ce
,
p
ar
t
ca
teg
o
r
izatio
n
,
an
d
au
to
m
ated
in
s
p
ec
tio
n
[
1
2
]
,
[
1
3
]
,
alo
n
g
with
f
ac
ial
-
r
ec
o
g
n
itio
n
-
b
ased
atten
d
an
ce
s
y
s
tem
s
[
1
4
]
–
[
1
7
]
,
tr
af
f
ic
in
cid
en
t
d
etec
tio
n
[
1
8
]
,
a
n
d
p
o
s
tu
r
e
r
ec
o
g
n
itio
n
f
o
r
s
ea
ted
wo
r
k
e
r
s
[
1
9
]
,
[
2
0
]
.
B
y
lev
e
r
ag
in
g
th
ese
ca
p
ab
ilit
ies,
co
m
p
u
ter
v
is
io
n
ca
n
r
ep
lace
m
an
u
al
m
ea
s
u
r
em
en
ts
a
n
d
r
e
d
u
ce
t
h
e
n
ee
d
f
o
r
co
n
tin
u
o
u
s
h
u
m
a
n
s
u
p
er
v
is
io
n
,
au
t
o
m
atica
lly
d
etec
tin
g
an
d
f
lag
g
in
g
r
is
k
y
s
ea
ted
p
o
s
tu
r
es so
u
s
er
s
ca
n
ad
ju
s
t in
r
ea
l
-
tim
e
[
1
9
]
.
A
r
ec
en
t
s
tu
d
y
p
r
o
p
o
s
ed
an
a
n
o
m
aly
-
s
itti
n
g
p
o
s
tu
r
e
d
etec
tio
n
m
o
d
el
th
at
r
u
n
s
o
n
in
ter
n
e
t
o
f
t
h
in
g
s
(
I
o
T
)
d
ev
ices.
I
t
lev
e
r
ag
es
th
e
lig
h
tweig
h
t
p
o
s
e
esti
m
atio
n
m
o
d
el,
Mo
v
eNe
t
th
u
n
d
er
,
to
ex
tr
ac
t
1
7
k
ey
b
o
d
y
lan
d
m
ar
k
s
as
well
as
a
s
h
o
e
p
o
s
itio
n
d
etec
to
r
as
an
ad
d
i
tio
n
al
f
ea
tu
r
e
to
en
h
an
ce
d
et
ec
tio
n
.
T
h
e
s
tu
d
y
em
p
lo
y
ed
a
5
,
0
4
2
lab
eled
im
ag
e
d
ataset
with
th
r
ee
d
is
tin
ct
p
o
s
tu
r
e
ca
teg
o
r
ies:
n
o
r
m
al,
cr
o
s
s
ed
leg
,
an
d
f
o
r
war
d
h
ea
d
.
T
h
e
f
ea
t
u
r
es
wer
e
class
if
ied
with
a
n
eu
r
al
n
etwo
r
k
m
o
d
el
th
at
co
n
s
is
ts
o
f
an
em
b
ed
d
i
n
g
lay
e
r
an
d
s
ev
er
al
d
e
n
s
e
lay
er
s
.
T
h
e
m
o
d
el
ac
h
iev
es a
n
o
v
e
r
all
F1
-
s
co
r
e
o
f
9
7
%
[
7
]
.
E
s
tr
ad
a
et
a
l.
[
2
0
]
d
ev
elo
p
ed
a
r
u
le
-
b
ased
m
o
d
el
f
o
r
s
itti
n
g
p
o
s
tu
r
e
class
if
icatio
n
u
s
in
g
k
ey
b
o
d
y
p
o
in
ts
(
n
o
s
e,
s
h
o
u
l
d
er
s
,
an
d
s
p
in
e)
o
b
tain
ed
v
ia
h
u
m
a
n
p
o
s
e
esti
m
atio
n
,
ac
h
iev
in
g
9
1
.
5
%
a
n
d
9
7
.
0
5
%
ac
cu
r
ac
y
o
n
lef
t
an
d
r
ig
h
t
ca
m
er
a
d
ata,
r
esp
ec
tiv
ely
.
Op
e
n
Po
s
e
was
al
s
o
ap
p
lied
to
an
aly
ze
jo
in
t
an
g
les
an
d
m
o
v
em
en
ts
f
r
o
m
v
id
eo
d
ata.
L
in
et
a
l.
[
2
1
]
em
p
lo
y
e
d
a
d
ec
is
io
n
tr
ee
f
o
r
er
g
o
n
o
m
ic
as
s
ess
m
en
t
b
ased
o
n
r
ap
id
en
tire
b
o
d
y
ass
ess
m
en
t
(
R
E
B
A)
,
r
ap
id
u
p
p
er
lim
b
a
s
s
es
s
m
en
t
(
R
UL
A)
,
an
d
o
v
ak
o
wo
r
k
in
g
p
o
s
tu
r
e
an
aly
zin
g
s
y
s
tem
(
OW
AS)
,
id
en
tify
in
g
h
ig
h
-
r
is
k
p
o
s
tu
r
es
in
1
0
.
4
% o
f
wo
r
k
in
g
tim
e,
wh
ic
h
is
co
n
s
is
ten
t
with
ex
p
er
t
ev
alu
atio
n
s
.
A
r
an
d
o
m
f
o
r
est
m
o
d
el
test
ed
o
n
th
e
KT
H
d
ataset
ac
h
iev
ed
th
e
h
ig
h
est
p
er
f
o
r
m
an
ce
,
with
9
0
.
4
8
% a
cc
u
r
ac
y
at
1
5
s
am
p
le
r
ates a
n
d
1
5
-
f
r
am
e
s
eq
u
en
ce
s
[
2
2
]
.
Ak
h
ter
et
a
l
.
[
2
3
]
h
av
e
d
e
v
el
o
p
ed
an
e
v
en
t
r
ec
o
g
n
itio
n
s
y
s
tem
u
s
in
g
ad
ap
tiv
e
b
o
o
s
tin
g
(
Ad
aBo
o
s
t)
f
o
r
h
u
m
an
ac
tiv
ity
.
T
h
e
s
tu
d
y
em
p
lo
y
e
d
f
ea
tu
r
e
r
ep
r
esen
tat
io
n
s
,
in
clu
d
in
g
m
o
v
ab
le
b
o
d
y
,
o
p
tical
f
lo
w,
a
n
d
m
o
tio
n
d
ata.
T
h
e
UC
F1
0
1
an
d
Yo
u
T
u
b
e
d
atasets
wer
e
u
s
ed
to
d
ev
el
o
p
th
e
m
o
d
el.
T
h
es
e
in
clu
d
e
a
d
iv
er
s
e
r
an
g
e
o
f
ac
tiv
ities
s
u
ch
as c
y
cl
in
g
,
s
win
g
in
g
,
an
d
walk
in
g
.
T
h
e
m
o
d
el
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
7
5
.
3
3
% o
n
th
e
UC
F1
0
1
d
ataset
an
d
7
6
.
6
6
%
o
n
th
e
Yo
u
T
u
b
e
d
ataset.
Gao
et
a
l.
[
2
4
]
d
e
v
elo
p
e
d
a
B
ay
esian
-
o
p
tim
ized
ex
tr
em
e
g
r
a
d
ien
t
b
o
o
s
tin
g
(
X
GB
o
o
s
t)
alg
o
r
ith
m
to
r
ec
o
g
n
ize
lo
wer
-
lim
b
m
o
tio
n
in
te
n
tio
n
s
u
s
in
g
co
m
b
in
ed
elec
tr
o
m
y
o
g
r
ap
h
y
(
E
MG
)
an
d
in
er
tial
m
ea
s
u
r
em
en
t
u
n
it
(
I
MU
)
d
ata
f
r
o
m
ten
p
ar
ticip
an
ts
p
er
f
o
r
m
in
g
walk
in
g
,
s
q
u
attin
g
,
an
d
leg
ex
ten
s
io
n
task
s
,
ac
h
iev
i
n
g
an
av
er
a
g
e
F1
-
s
co
r
e
o
f
9
5
.
3
3
%.
Me
an
w
h
ile,
Fan
g
et
a
l.
[
2
5
]
in
tr
o
d
u
ce
d
s
itti
n
g
p
o
s
tu
r
e
r
ec
o
g
n
itio
n
n
et
wo
r
k
(
SP
R
Net
)
,
a
v
is
io
n
tr
a
n
s
f
o
r
m
er
m
o
d
el
th
at
u
s
es
Op
en
Po
s
e
-
ex
tr
ac
ted
b
o
d
y
k
ey
p
o
i
n
ts
to
class
if
y
th
r
ee
s
tu
d
en
t
s
itti
n
g
p
o
s
tu
r
es,
ac
h
iev
i
n
g
9
9
.
2
%
ac
cu
r
ac
y
an
d
s
u
r
p
ass
in
g
o
t
h
er
p
r
e
-
tr
ain
ed
m
o
d
els.
T
h
is
s
tu
d
y
p
r
esen
ts
a
m
eth
o
d
f
o
r
ass
ess
in
g
er
g
o
n
o
m
ic
s
itti
n
g
p
o
s
tu
r
e
b
y
an
al
y
zin
g
k
ey
p
o
in
ts
o
f
th
e
h
u
m
an
b
o
d
y
ex
tr
ac
ted
f
r
o
m
im
ag
es.
T
h
e
Mo
v
eNe
t
p
o
s
e
esti
m
atio
n
m
o
d
el
was
s
elec
t
ed
as
th
e
k
ey
p
o
in
t
ex
tr
ac
to
r
(
e.
g
.
,
n
o
s
e,
s
h
o
u
ld
er
s
,
elb
o
ws,
an
d
s
p
in
e)
f
o
r
g
en
er
atin
g
f
ea
tu
r
es
u
s
ed
b
y
m
ac
h
in
e
lear
n
i
n
g
class
if
ier
s
s
u
ch
as
m
u
lti
-
lay
er
p
er
ce
p
tr
o
n
(
ML
P)
,
Ad
aBo
o
s
t
,
an
d
XGBo
o
s
t
,
d
u
e
to
its
co
m
p
ac
tn
ess
an
d
lo
w
co
m
p
u
tatio
n
al
d
em
an
d
[
2
0
]
,
[
2
6
]
,
[
2
7
]
.
Un
lik
e
p
r
e
v
io
u
s
s
y
s
tem
s
u
s
in
g
Op
en
Po
s
e
[
2
1
]
,
[
2
5
]
o
r
Me
d
iaPip
e
[
2
0
]
f
o
r
m
u
lti
-
ac
tiv
ity
r
ec
o
g
n
itio
n
o
r
lim
ited
-
a
n
g
le
clin
ic
al
an
aly
s
is
,
th
is
s
tu
d
y
f
o
cu
s
es
o
n
o
f
f
ice
s
itti
n
g
er
g
o
n
o
m
ics
with
b
o
th
f
r
o
n
tal
an
d
s
id
e
ca
m
er
a
v
iews.
Us
in
g
Mo
v
eNe
t
th
u
n
d
er
to
ex
tr
ac
t
1
7
k
ey
p
o
in
ts
,
th
e
s
y
s
tem
en
ab
les
r
ea
l
-
tim
e
s
in
g
le
-
p
er
s
o
n
in
f
er
e
n
ce
o
n
m
o
b
il
e
o
r
ed
g
e
d
e
v
ices,
ac
h
ie
v
in
g
lo
wer
late
n
cy
an
d
m
o
d
el
s
ize
th
an
Op
en
Po
s
e
w
h
ile
m
ain
tain
in
g
h
ig
h
p
o
s
e
-
esti
m
atio
n
ac
cu
r
ac
y
[
2
8
]
.
T
h
e
ap
p
r
o
ac
h
en
h
an
ce
s
cr
o
s
s
-
v
iew
g
en
er
aliza
tio
n
an
d
class
if
icatio
n
ef
f
icien
cy
in
er
g
o
n
o
m
ic
p
o
s
tu
r
e
d
etec
tio
n
,
th
er
eb
y
r
ed
u
cin
g
MSD
r
is
k
an
d
p
r
o
m
o
tin
g
w
o
r
k
p
lace
h
ea
lth
.
2.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
d
iv
id
ed
i
n
to
f
i
v
e
s
tag
es:
d
ata
co
llectio
n
,
k
ey
p
o
in
t
ex
tr
ac
tio
n
,
d
ata
p
r
ep
ar
atio
n
,
class
if
icatio
n
,
an
d
ev
alu
atio
n
.
Fig
u
r
e
1
d
i
s
p
lay
s
th
e
en
tire
p
r
o
ce
s
s
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
T
h
e
s
u
b
s
eq
u
en
t su
b
s
ec
tio
n
ex
p
lain
s
th
e
s
p
ec
if
ics o
f
ea
ch
p
h
ase.
2
.
1
.
Da
t
a
c
o
llect
io
n
T
h
e
s
tu
d
y
u
s
ed
d
ata
f
r
o
m
3
0
p
ar
ticip
an
ts
,
ea
c
h
p
r
o
v
id
in
g
3
0
s
am
p
les
o
f
er
g
o
n
o
m
ic
an
d
non
-
er
g
o
n
o
m
ic
p
o
s
tu
r
es.
Data
wer
e
co
llected
in
a
well
-
lit
o
f
f
ice
with
a
p
lain
b
ac
k
g
r
o
u
n
d
,
ca
p
tu
r
in
g
s
ea
ted
p
ar
ticip
an
ts
f
r
o
m
s
id
e
an
d
f
r
o
n
t
v
iews
(
with
s
id
e
v
iews
m
ir
r
o
r
ed
f
o
r
b
alan
ce
)
.
Par
ticip
an
t
s
f
o
llo
wed
p
o
s
tu
r
e
g
u
id
elin
es
f
r
o
m
an
e
r
g
o
n
o
m
ic
ex
p
er
t,
b
ased
o
n
SNI
9
0
1
1
:2
0
2
1
.
E
r
g
o
n
o
m
ic
p
o
s
tu
r
es
f
ea
t
u
r
ed
s
tr
aig
h
t
b
ac
k
s
,
f
lat
f
ee
t,
9
0
°
k
n
ee
b
e
n
d
s
,
an
d
ar
m
s
o
n
th
e
d
esk
,
wh
ile
n
o
n
-
er
g
o
n
o
m
ic
o
n
es
s
h
o
wed
c
u
r
v
ed
b
ac
k
s
,
b
o
d
y
twis
t
s
,
o
r
d
o
wn
war
d
g
az
in
g
.
Data
wer
e
co
llected
u
s
in
g
a
d
ig
ital
ca
m
er
a
with
a
5
4
7
2
×
3
6
4
8
-
p
ix
el
r
eso
lu
tio
n
,
an
I
SO o
f
2
5
0
,
an
ap
er
tu
r
e
o
f
f
/2
.
8
,
an
d
a
1
/3
0
s
s
h
u
tter
s
p
ee
d
.
T
h
e
ca
m
er
a
was p
o
s
itio
n
ed
1
.
6
7
m
eter
s
f
o
r
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
506
-
5
1
4
508
f
r
o
n
t
v
iew
an
d
1
.
1
5
m
eter
s
f
o
r
th
e
s
id
e
v
iew,
m
ea
s
u
r
ed
f
r
o
m
th
e
p
er
s
o
n
’
s
b
o
d
y
.
T
h
e
h
eig
h
t
is
co
n
s
tan
t
at
1
.
2
7
m
eter
s
f
o
r
all
v
iews.
T
h
is
r
esu
lted
in
9
0
0
in
s
tan
ce
s
f
o
r
e
ac
h
p
o
s
tu
r
e.
E
x
am
p
les ar
e
s
h
o
wn
in
Fig
u
r
e
2
.
Fig
u
r
e
1
.
T
h
e
p
r
o
ce
s
s
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
s
itti
n
g
p
o
s
tu
r
e
class
if
icatio
n
m
o
d
el
Fig
u
r
e
2
.
E
x
am
p
les o
f
co
llected
d
ata
f
o
r
er
g
o
n
o
m
ic
an
d
n
o
n
-
er
g
o
n
o
m
ic
p
o
s
tu
r
es
2
.
2
.
K
ey
po
ints e
x
t
ra
c
t
io
n
T
h
e
k
e
y
p
o
in
t
e
x
tr
ac
tio
n
p
h
ase
u
tili
ze
s
th
e
Mo
v
eNe
t
p
o
s
e
esti
m
atio
n
m
o
d
el,
d
ev
elo
p
ed
b
y
I
n
clu
d
eHe
alth
an
d
Go
o
g
le
in
2
0
2
1
,
to
d
etec
t
h
u
m
an
b
o
d
y
k
ey
p
o
in
ts
in
r
ea
l
-
tim
e
[
2
6
]
.
Mo
v
eNe
t
h
as
two
v
er
s
io
n
s
—
lig
h
tn
in
g
a
n
d
th
u
n
d
er
—
with
th
e
latter
u
s
ed
in
th
is
s
tu
d
y
f
o
r
h
ig
h
er
ac
c
u
r
ac
y
.
B
u
ilt
o
n
th
e
T
en
s
o
r
Flo
w
o
b
ject
d
etec
tio
n
API
an
d
Mo
b
ileNetV2
,
Mo
v
eNe
t
em
p
lo
y
s
th
e
C
en
ter
Net
ap
p
r
o
ac
h
,
wh
ich
d
etec
ts
ce
n
ter
p
o
in
ts
in
s
tead
o
f
b
o
u
n
d
i
n
g
b
o
x
es
f
o
r
ef
f
icien
t
m
u
lti
-
p
er
s
o
n
d
etec
tio
n
with
o
u
t
n
o
n
-
m
ax
im
u
m
s
u
p
p
r
ess
io
n
,
th
er
eb
y
en
s
u
r
in
g
f
ast
an
d
p
r
ec
is
e
k
ey
p
o
in
t
lo
c
aliza
tio
n
[
2
8
]
.
T
o
e
x
tr
ac
t
th
e
k
ey
p
o
in
ts
f
r
o
m
an
im
ag
e
u
s
in
g
Mo
v
eNe
t,
it
is
n
ec
ess
ar
y
to
en
s
u
r
e
th
at
th
e
im
ag
e
m
ee
ts
th
e
s
p
ec
if
ied
s
ize
r
eq
u
ir
em
en
ts
.
Fo
r
Mo
v
eNe
t
to
p
r
o
ce
s
s
th
e
i
m
ag
e,
it
m
u
s
t
b
e
r
esized
to
a
2
5
6
×
2
5
6
-
p
ix
el
s
ize.
W
h
en
th
e
o
r
ig
in
al
im
ag
e
is
r
esized
to
a
1
:1
r
atio
,
it
ca
n
c
au
s
e
th
e
im
ag
e
o
r
th
e
s
u
b
ject
with
in
it
to
ap
p
ea
r
s
q
u
ee
ze
d
.
T
o
o
v
er
c
o
m
e
th
is
is
s
u
e,
p
ad
d
in
g
is
ad
d
e
d
to
th
e
lo
n
g
er
s
id
e
—
s
p
ec
if
ically
,
th
e
to
p
an
d
b
o
tto
m
—
to
co
m
p
en
s
a
te
f
o
r
th
e
r
e
d
u
ctio
n
in
p
ix
els
th
at
o
cc
u
r
s
wh
en
r
e
s
izin
g
th
e
im
ag
e.
T
h
is
p
r
o
ce
s
s
en
s
u
r
es
th
at
th
e
s
h
o
r
ter
s
i
d
e
o
f
th
e
im
ag
e
is
p
r
eser
v
ed
,
p
r
e
v
en
tin
g
a
s
q
u
e
ez
ed
ap
p
ea
r
an
ce
.
Af
ter
r
esizin
g
an
d
p
ad
d
in
g
th
e
im
ag
e,
i
t
is
in
p
u
t
in
t
o
th
e
Mo
v
eNe
t
m
o
d
el,
wh
ich
d
ete
cts
1
7
k
ey
p
o
i
n
ts
o
n
th
e
h
u
m
an
b
o
d
y
as
s
h
o
wn
in
Fig
u
r
e
3
[
7
]
,
[
2
1
]
,
[
2
7
]
.
E
ac
h
k
e
y
p
o
in
t
is
r
ep
r
esen
ted
b
y
x
a
n
d
y
co
o
r
d
in
ates
alo
n
g
with
a
s
co
r
e,
with
a
t
h
r
esh
o
ld
o
f
0
.
1
s
et
f
o
r
v
alid
ity
.
I
f
all
k
ey
p
o
in
ts
e
x
ce
ed
th
is
th
r
esh
o
ld
,
t
h
e
im
ag
e
is
co
n
s
id
er
e
d
v
alid
,
an
d
th
e
k
e
y
p
o
in
ts
a
r
e
s
to
r
ed
.
Ho
wev
er
,
th
is
s
tu
d
y
o
n
ly
co
n
s
id
er
ed
th
e
k
e
y
p
o
in
ts
f
r
o
m
h
ea
d
to
h
ip
s
,
wh
ic
h
r
e
p
r
ese
n
t
th
e
m
o
s
t
cr
itical
p
o
in
ts
f
o
r
d
ete
r
m
in
in
g
p
o
s
tu
r
e
[
2
9
]
–
[
3
1
]
.
T
h
is
is
b
ec
au
s
e
th
ese
b
o
d
y
p
ar
ts
g
en
er
ally
p
r
o
v
id
e
s
u
f
f
icien
t
in
f
o
r
m
atio
n
f
o
r
p
eo
p
le
wh
o
s
it
b
eh
in
d
a
d
esk
,
as o
n
ly
th
e
t
o
p
p
ar
t o
f
th
e
b
o
d
y
is
v
is
ib
le.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
erg
o
n
o
mic
s
itti
n
g
p
o
s
tu
r
es d
etec
tio
n
fo
r
o
ffice
w
o
r
ksta
tio
n
u
s
in
g
…
(
Th
eres
ia
A
melia
P
a
w
itr
a
)
509
Fig
u
r
e
3
.
T
h
e
1
7
k
ey
p
o
in
ts
d
e
tecte
d
b
y
th
e
M
o
v
eNe
t m
o
d
el
2
.
3
.
Da
t
a
prepa
ra
t
i
o
n
T
h
e
d
a
t
a
p
r
e
p
a
r
a
t
i
o
n
p
h
a
s
e
i
n
v
o
l
v
e
d
p
r
e
p
r
o
c
e
s
s
i
n
g
a
n
d
s
p
l
i
tt
in
g
t
h
e
d
a
t
a
s
e
t
.
E
x
t
r
a
ct
e
d
k
e
y
p
o
i
n
t
s
w
e
r
e
n
o
r
m
a
l
i
z
e
d
s
o
t
h
a
t t
h
e
m
a
x
i
m
u
m
d
i
s
ta
n
c
e
b
e
tw
e
e
n
t
h
e
m
e
q
u
al
e
d
o
n
e
,
e
n
s
u
r
i
n
g
p
o
s
e
c
o
m
p
a
r
a
b
i
l
i
t
y
r
e
g
a
r
d
l
e
s
s
o
f
b
o
d
y
s
i
z
e
o
r
c
a
m
e
r
a
d
i
s
t
a
n
ce
.
T
h
e
k
e
y
p
o
i
n
t
s
w
e
r
e
t
h
e
n
c
e
n
te
r
e
d
t
o
s
t
a
n
d
a
r
d
i
z
e
p
o
s
es
a
n
d
e
m
p
h
a
s
i
z
e
r
e
la
t
i
v
e
l
a
n
d
m
a
r
k
p
o
s
i
t
i
o
n
s
.
F
i
n
al
l
y
,
t
h
e
d
a
t
a
s
et
w
as
d
i
v
i
d
e
d
i
n
t
o
1
0
s
tr
a
t
i
f
i
e
d
f
o
l
d
s
f
o
r
c
r
o
s
s
-
v
a
li
d
a
t
io
n
.
2
.
4
.
Cla
s
s
if
ica
t
io
n
T
h
e
class
if
icatio
n
p
h
ase
in
v
o
lv
es
tr
ain
in
g
m
o
d
els
o
n
ea
ch
cr
o
s
s
-
v
alid
atio
n
f
o
ld
u
s
in
g
Ad
aBo
o
s
t,
XGBo
o
s
t,
an
d
ML
P.
Ad
aBo
o
s
t
is
an
en
s
em
b
le
m
eth
o
d
th
a
t
co
m
b
in
es
m
u
ltip
le
wea
k
lea
r
n
er
s
in
to
a
s
tr
o
n
g
class
if
ier
[
2
3
]
,
[
3
2
]
.
XGBo
o
s
t
o
p
tim
izes
d
ec
is
io
n
-
tr
ee
m
o
d
els
u
s
in
g
a
s
ec
o
n
d
-
o
r
d
er
T
ay
lo
r
e
x
p
an
s
io
n
o
f
th
e
o
b
jectiv
e
f
u
n
ctio
n
a
n
d
in
c
o
r
p
o
r
ates
tr
ee
c
o
m
p
lex
ity
as
a
r
eg
u
lar
izatio
n
te
r
m
[
2
4
]
.
M
ea
n
wh
ile,
ML
P
is
a
f
ee
d
-
f
o
r
war
d
n
e
u
r
al
n
etwo
r
k
with
in
p
u
t,
h
id
d
en
,
an
d
o
u
t
p
u
t
lay
er
s
th
at
lear
n
s
p
atter
n
s
th
r
o
u
g
h
weig
h
t u
p
d
ates
v
ia
b
ac
k
p
r
o
p
a
g
atio
n
[
1
2
]
.
2
.
5
.
E
v
a
lua
t
i
o
n
T
h
e
ev
alu
atio
n
p
h
ase
ass
ess
ed
th
e
m
o
d
el’
s
ab
ilit
y
t
o
d
etec
t
e
r
g
o
n
o
m
ic
p
o
s
tu
r
e
u
s
in
g
a
10
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
s
ch
em
e,
w
h
er
e
e
ac
h
f
o
ld
u
s
ed
9
0
%
o
f
th
e
d
ata
f
o
r
t
r
ain
in
g
a
n
d
1
0
%
f
o
r
test
in
g
.
Mo
d
el
p
er
f
o
r
m
an
ce
f
o
r
ea
ch
f
o
ld
wa
s
ev
alu
ated
u
s
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
an
d
th
e
r
esu
lts
wer
e
s
u
m
m
ar
ized
as
th
e
m
ea
n
±
s
tan
d
ar
d
d
e
v
iatio
n
(
SD)
to
ass
ess
s
tab
ilit
y
an
d
g
en
er
aliza
tio
n
.
T
h
e
co
m
p
u
tatio
n
o
f
th
ese
m
etr
ics
as in
(
1
)
to
(
4
)
[
9
]
.
=
+
+
+
+
(
1
)
=
+
(
2
)
=
+
(
3
)
1
−
=
2
×
+
×
(
4
)
T
P,
T
N,
FP
,
an
d
F
N
d
en
o
te
tr
u
e
p
o
s
itiv
es,
tr
u
e
n
eg
ativ
es,
f
alse
p
o
s
itiv
es,
an
d
f
alse
n
eg
ativ
es,
r
esp
ec
tiv
ely
.
T
P
a
n
d
T
N
r
e
p
r
esen
t
co
r
r
ec
tly
class
if
ied
p
o
s
itiv
e
an
d
n
eg
ativ
e
in
s
tan
ce
s
,
wh
ile
FP
an
d
FN
d
en
o
te
m
is
class
if
ied
n
eg
ativ
e
an
d
p
o
s
itiv
e
in
s
tan
ce
s
[
9
]
.
Mo
d
el
p
er
f
o
r
m
an
ce
was
also
ass
e
s
s
ed
u
s
in
g
th
e
ar
ea
u
n
d
er
th
e
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
cu
r
v
e
(
R
OC
-
AUC)
,
wh
er
e
th
e
R
OC
illu
s
tr
ates
d
is
cr
im
in
atio
n
ac
r
o
s
s
th
r
esh
o
ld
s
an
d
th
e
AUC
m
ea
s
u
r
es
th
e
ar
ea
u
n
d
er
th
e
cu
r
v
e;
an
AUC
o
f
1
in
d
icate
s
p
er
f
ec
t
class
if
icatio
n
,
wh
er
ea
s
0
.
5
r
e
f
lects
r
an
d
o
m
p
er
f
o
r
m
an
ce
[
9
]
,
[
3
2
]
.
Fo
r
v
is
u
aliza
tio
n
,
o
u
t
-
of
-
f
o
l
d
p
r
e
d
ictio
n
s
f
r
o
m
all
1
0
f
o
ld
s
wer
e
a
g
g
r
e
g
ated
to
p
r
o
d
u
ce
a
s
in
g
le
co
n
f
u
s
io
n
m
atr
ix
an
d
R
OC
cu
r
v
e,
en
s
u
r
in
g
u
n
b
iased
p
r
ed
ictio
n
s
s
in
ce
ea
ch
s
am
p
le
was e
v
alu
ated
b
y
a
m
o
d
el
th
at
h
ad
n
o
t seen
it d
u
r
in
g
tr
ain
i
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
506
-
5
1
4
510
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
A
to
tal
o
f
1
,
5
5
0
v
alid
in
s
tan
ce
s
wer
e
o
b
tain
e
d
b
ased
o
n
k
ey
p
o
i
n
t
ex
tr
ac
tio
n
s
co
r
es,
c
o
n
s
is
tin
g
o
f
8
7
3
e
r
g
o
n
o
m
ic
a
n
d
6
7
7
n
o
n
-
e
r
g
o
n
o
m
ic
s
am
p
les.
Fig
u
r
e
4
illu
s
tr
ates
th
e
k
ey
p
o
in
t
ex
t
r
ac
tio
n
p
r
o
ce
s
s
(
im
ag
e
n
o
t
to
s
ca
le)
.
Af
ter
n
o
r
m
aliza
t
io
n
an
d
ce
n
ter
in
g
,
th
e
k
ey
p
o
i
n
ts
wer
e
u
s
ed
to
c
r
ea
te
a
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
s
p
lit
f
o
r
tr
ain
in
g
an
d
test
in
g
.
T
h
r
ee
m
o
d
els
wer
e
tr
ain
ed
u
s
in
g
Ad
a
B
o
o
s
t,
XGBo
o
s
t
,
an
d
ML
P
clas
s
if
ier
s
,
an
d
th
eir
p
er
f
o
r
m
an
ce
was
ev
alu
ated
b
y
av
er
ag
in
g
th
e
ac
cu
r
a
cy
,
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
R
OC
-
AU
C
.
T
ab
le
1
an
d
Fig
u
r
e
5
s
u
m
m
ar
i
ze
th
e
r
esu
lts
.
Fig
u
r
e
5
p
r
o
v
id
es a
co
m
p
ar
ativ
e
b
ar
p
lo
t
(
y
-
a
x
is
s
tar
tin
g
at
0
.
7
5
)
.
Fig
u
r
e
4
.
T
h
e
p
r
o
ce
s
s
o
f
ex
tr
a
ctin
g
k
ey
p
o
in
ts
f
r
o
m
an
im
a
g
e
u
s
in
g
Mo
v
eNe
t
T
ab
le
1
.
C
r
o
s
s
-
v
alid
atio
n
p
er
f
o
r
m
an
ce
(
m
ea
n
±
SD)
C
l
a
s
si
f
i
e
r
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
R
O
C
-
AUC
A
d
a
B
o
o
st
0
.
8
9
4
±
0
.
0
2
1
0
.
9
3
6
±
0
.
0
3
1
0
.
8
4
7
±
0
.
3
1
3
0
.
8
8
9
±
0
.
0
2
2
0
.
9
5
0
±
0
.
0
1
6
M
LP
0
.
9
1
8
±
0
.
2
2
1
0
.
9
4
6
±
0
.
0
2
4
0
.
8
8
6
±
0
.
0
3
5
0
.
9
1
5
±
0
.
0
2
4
0
.
9
6
0
±
0
.
0
1
1
X
G
B
o
o
st
0
.
9
3
0
±
0
.
0
1
9
0
.
9
4
6
±
0
.
0
3
2
0
.
9
1
4
±
0
.
0
1
9
0
.
9
2
9
±
0
.
0
1
9
0
.
9
7
4
±
0
.
0
1
0
Fig
u
r
e
5
.
Mu
ltip
le
b
ar
p
l
o
t f
o
r
m
etr
ics v
is
u
aliza
tio
n
ac
r
o
s
s
class
if
ier
s
T
h
e
r
esu
lts
s
h
o
w
th
at
XGBo
o
s
t
ac
h
iev
es
th
e
b
est
o
v
er
all
p
er
f
o
r
m
an
ce
,
with
t
h
e
h
ig
h
e
s
t
av
er
ag
e
ac
cu
r
ac
y
(
9
3
.
0
%),
p
r
ec
is
io
n
(
9
4
.
6
%),
r
ec
all
(
9
1
.
4
%),
F1
-
s
co
r
e
(
9
2
.
9
%),
an
d
th
e
t
o
p
R
OC
–
AUC
v
alu
e
o
f
0
.
9
7
4
±
0
.
0
1
0
,
in
d
icatin
g
s
tab
le
class
s
ep
ar
atio
n
u
n
d
er
cr
o
s
s
-
v
alid
atio
n
.
ML
P
r
a
n
k
s
s
ec
o
n
d
,
p
er
f
o
r
m
in
g
co
m
p
etitiv
ely
(
ac
cu
r
ac
y
0
.
9
1
8
±
0
.
2
2
1
,
p
r
ec
is
io
n
0
.
9
4
6
±
0
.
0
2
4
,
r
ec
all
0
.
8
8
6
±
0
.
0
3
5
,
F1
-
s
co
r
e
0
.
9
1
5
±
0
.
0
2
4
,
an
d
R
OC
–
AU
C
0
.
9
6
0
±
0
.
0
1
1
)
,
th
o
u
g
h
its
lar
g
e
ac
cu
r
ac
y
v
a
r
i
an
ce
s
u
g
g
ests
f
o
ld
-
to
-
f
o
ld
in
s
tab
ilit
y
.
Ad
aBo
o
s
t
y
ield
s
th
e
wea
k
est
r
esu
lts
(
ac
cu
r
ac
y
0
.
8
9
4
±
0
.
0
2
1
,
p
r
ec
i
s
io
n
0
.
9
3
6
±
0
.
0
3
1
,
r
ec
all
0
.
8
4
7
±
0
.
3
1
3
,
F1
-
s
co
r
e
0
.
8
8
9
±
0
.
0
2
2
,
an
d
R
OC
–
AUC 0
.
9
5
0
±
0
.
0
1
6
)
,
with
n
o
ta
b
ly
u
n
s
tab
le
r
ec
all.
T
h
e
co
n
f
u
s
i
o
n
m
at
r
ic
es
s
h
o
w
n
in
Fi
g
u
r
e
6
ill
u
s
t
r
a
te
t
h
e
cl
ass
if
ica
ti
o
n
p
e
r
f
o
r
m
a
n
c
e
o
f
e
ac
h
m
o
d
el.
Fig
u
r
e
6
(
a
)
p
r
ese
n
ts
t
h
e
A
d
aBo
o
s
t
class
if
i
e
r
,
wh
ic
h
e
x
h
i
b
its
th
e
h
i
g
h
est
n
u
m
b
er
o
f
f
als
e
n
e
g
a
ti
v
es
f
o
r
er
g
o
n
o
m
ic
p
o
s
t
u
r
es
a
n
d
o
v
e
r
a
ll
wea
k
er
p
e
r
f
o
r
m
a
n
c
e.
Fi
g
u
r
e
6
(
b
)
s
h
o
ws
t
h
e
M
L
P
cl
ass
i
f
i
er
,
wh
ic
h
p
r
o
d
u
ce
s
th
e
h
i
g
h
est
n
u
m
b
e
r
o
f
tr
u
e
p
o
s
it
iv
es
f
o
r
e
r
g
o
n
o
m
ic
p
o
s
tu
r
es
a
n
d
p
er
f
o
r
m
s
b
ett
er
t
h
a
n
Ad
aB
o
o
s
t
.
Fi
n
all
y
,
Fig
u
r
e
6
(
c)
d
ep
icts
th
e
XGB
o
o
s
t
c
lass
i
f
i
er
,
w
h
i
ch
ac
h
i
ev
es
th
e
tr
u
est
n
e
g
at
iv
es
a
n
d
t
h
e
f
e
west
f
als
e
p
o
s
i
ti
v
es
f
o
r
n
o
n
-
er
g
o
n
o
m
i
c
p
o
s
t
u
r
es
,
i
n
d
ic
ati
n
g
th
e
b
es
t
o
v
e
r
all
p
er
f
o
r
m
a
n
c
e
am
o
n
g
t
h
e
th
r
ee
class
if
ie
r
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
erg
o
n
o
mic
s
itti
n
g
p
o
s
tu
r
es d
etec
tio
n
fo
r
o
ffice
w
o
r
ksta
tio
n
u
s
in
g
…
(
Th
eres
ia
A
melia
P
a
w
itr
a
)
511
C
o
r
r
es
p
o
n
d
in
g
l
y
,
t
h
e
R
OC
cu
r
v
es
i
n
Fi
g
u
r
e
7
s
h
o
w
t
h
at
X
GB
o
o
s
t
h
as
t
h
e
h
ig
h
es
t
A
UC
,
ML
P
is
s
ec
o
n
d
,
a
n
d
Ad
aB
o
o
s
t
is
l
o
w
est
.
A
ll
m
a
tr
i
ce
s
an
d
c
u
r
v
es
ar
e
d
e
r
i
v
e
d
f
r
o
m
c
o
m
b
i
n
e
d
o
u
t
-
of
-
f
o
l
d
p
r
e
d
i
cti
o
n
s
a
cr
o
s
s
1
0
-
f
o
l
d
cr
o
s
s
-
v
ali
d
a
ti
o
n
,
e
n
s
u
r
i
n
g
a
n
u
n
b
ias
ed
e
v
al
u
ati
o
n
.
(
a)
(
b
)
(
c)
Fig
u
r
e
6
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
(
a)
Ad
aBo
o
s
t,
(
b
)
ML
P,
an
d
(
c)
XGBo
o
s
t c
lass
if
ier
s
Fig
u
r
e
7
.
R
OC
cu
r
v
es f
o
r
h
e
p
r
o
p
o
s
ed
s
itti
n
g
p
o
s
tu
r
e
d
etec
ti
o
n
m
o
d
el
A
co
m
p
ar
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
with
o
th
e
r
s
tu
d
ies
is
p
r
esen
ted
in
T
a
b
le
2
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el,
h
ig
h
lig
h
te
d
in
b
o
ld
,
wh
ich
im
p
lem
e
n
ts
th
e
XG
B
o
o
s
t
class
if
ier
,
d
em
o
n
s
tr
ated
an
ac
c
u
r
ac
y
o
f
9
3
.
0
2
±
1
.
9
1
%
in
class
if
y
in
g
e
r
g
o
n
o
m
ic
p
o
s
tu
r
es.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
th
e
d
ee
p
r
ec
u
r
r
e
n
t
h
ier
ar
c
h
ical
n
etwo
r
k
[
1
9
]
,
wh
ich
ac
h
iev
e
d
a
n
ac
c
u
r
ac
y
o
f
9
1
.
4
7
%
in
s
p
in
e
p
o
s
tu
r
e
r
ec
o
g
n
itio
n
wh
ile
s
itti
n
g
.
Fu
r
th
e
r
m
o
r
e,
th
e
p
r
o
p
o
s
ed
m
o
d
el
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
co
m
p
ar
ed
to
th
e
Me
d
iaPip
e+
d
ec
is
io
n
tr
ee
m
o
d
el
[
2
0
]
,
wh
ich
ac
h
iev
ed
ac
cu
r
ac
y
o
f
9
1
.
5
an
d
9
7
.
0
5
%
in
r
ec
o
g
n
izin
g
p
r
o
p
er
s
itti
n
g
p
o
s
tu
r
es
f
r
o
m
th
e
lef
t
an
d
r
ig
h
t,
r
esp
ec
tiv
ely
.
Alth
o
u
g
h
th
e
im
p
r
o
v
em
en
t
o
v
er
p
r
ev
io
u
s
s
tu
d
ies
ar
e
m
o
d
est,
th
e
p
r
o
p
o
s
ed
m
o
d
el
b
en
ef
its
f
r
o
m
u
s
in
g
im
ag
es
ca
p
tu
r
ed
f
r
o
m
th
r
ee
an
g
les.
I
n
co
n
tr
ast,
th
e
d
ee
p
r
ec
u
r
r
en
t
h
ier
ar
ch
ical
n
etwo
r
k
an
d
Me
d
iaPip
e+
d
ec
is
io
n
tr
e
e
m
o
d
els
r
ely
o
n
a
s
in
g
le
v
iewp
o
in
t
(
lef
t,
r
i
g
h
t,
o
r
f
r
o
n
t)
.
Mo
r
eo
v
e
r
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
o
u
t
p
er
f
o
r
m
s
th
e
Op
en
Po
s
e+
r
an
d
o
m
f
o
r
est
ap
p
r
o
ac
h
[
2
1
]
,
wh
ich
r
ep
o
r
ted
an
ac
cu
r
ac
y
o
f
9
0
.
6
4
%
in
h
u
m
an
ac
tiv
ity
r
ec
o
g
n
itio
n
.
T
h
is
h
ig
h
lig
h
ts
th
e
m
o
d
el’
s
ef
f
ec
tiv
en
ess
in
class
if
y
in
g
er
g
o
n
o
m
ic
p
o
s
tu
r
es
an
d
its
p
o
ten
tial
f
o
r
in
teg
r
atio
n
in
to
s
y
s
tem
s
d
esig
n
ed
to
r
ed
u
ce
MSDs in
s
ed
en
tar
y
wo
r
k
p
lace
s
.
T
h
e
s
y
s
tem
in
teg
r
ates
with
s
m
ar
t
-
o
f
f
ice
p
latf
o
r
m
s
u
s
in
g
a
lig
h
tweig
h
t
clien
t
–
s
er
v
er
ar
c
h
itectu
r
e.
Po
s
tu
r
e
is
in
f
er
r
ed
o
n
-
d
ev
ice,
an
d
o
n
ly
an
o
n
y
m
ized
f
ea
tu
r
es
an
d
r
is
k
s
co
r
es
ar
e
tr
an
s
m
i
tted
f
o
r
ce
n
tr
alize
d
ag
g
r
eg
atio
n
,
in
d
e
x
co
m
p
u
tat
io
n
,
an
d
e
r
g
o
n
o
m
ic
aler
ts
.
User
f
ee
d
b
ac
k
is
d
eliv
er
e
d
th
r
o
u
g
h
d
esk
t
o
p
n
o
tific
atio
n
s
o
r
co
llab
o
r
atio
n
to
o
ls
,
an
d
th
e
m
o
d
u
lar
d
esig
n
s
u
p
p
o
r
ts
ea
s
y
d
ep
lo
y
m
e
n
t
with
in
ex
is
tin
g
welln
ess
s
y
s
tem
s
wh
ile
p
r
eser
v
in
g
p
r
iv
ac
y
th
r
o
u
g
h
m
i
n
im
al
d
ata
s
h
ar
in
g
.
L
o
n
g
-
ter
m
ex
p
o
s
u
r
e
m
etr
ics
(
e.
g
.
,
m
in
u
tes
p
er
h
o
u
r
s
p
e
n
t
in
m
o
d
e
r
ate
o
r
h
ig
h
-
r
is
k
p
o
s
tu
r
es)
en
ab
le
o
n
g
o
in
g
m
o
n
ito
r
in
g
o
f
m
u
s
c
u
lo
s
k
eleta
l
r
is
k
an
d
s
u
p
p
o
r
t
e
ar
ly
er
g
o
n
o
m
ic
i
n
ter
v
en
tio
n
.
R
ed
u
cin
g
h
ig
h
-
r
is
k
ex
p
o
s
u
r
e
m
a
y
h
elp
lo
wer
m
u
s
cu
lo
s
k
eleta
l
co
m
p
lain
ts
an
d
p
r
ev
en
t
p
r
o
d
u
ctiv
ity
lo
s
s
.
T
ea
m
d
ash
b
o
ar
d
s
ca
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
506
-
5
1
4
512
s
u
m
m
ar
ize
k
ey
p
er
f
o
r
m
an
ce
in
d
icato
r
(
KPI
)
s
u
c
h
as
ex
p
o
s
u
r
e
r
ate,
aler
t
-
r
eso
lu
tio
n
tim
e,
an
d
er
g
o
n
o
m
ic
-
co
m
p
lian
ce
lev
els,
lin
k
in
g
t
h
em
to
o
p
er
atio
n
al
o
u
tco
m
e
s
f
o
r
r
etu
r
n
o
n
in
v
estme
n
t
(
R
OI
)
ass
es
s
m
en
t.
Ho
wev
er
,
th
e
s
tu
d
y
is
lim
ited
b
y
its
s
m
all,
co
n
tr
o
lled
s
am
p
le
o
f
3
0
p
ar
ticip
an
ts
,
its
r
elia
n
ce
o
n
u
p
p
er
-
b
o
d
y
k
ey
p
o
i
n
ts
th
at
ar
e
s
en
s
itiv
e
to
v
iewp
o
in
t
c
h
an
g
es,
o
cc
l
u
s
io
n
,
lig
h
tin
g
,
a
n
d
p
o
s
e
-
est
im
atio
n
er
r
o
r
s
,
its
o
m
is
s
io
n
o
f
lo
wer
-
lim
b
cu
es,
an
d
its
r
estricte
d
an
d
im
b
alan
ce
d
p
o
s
tu
r
e
class
es.
T
h
e
wo
r
k
also
d
o
es
n
o
t
ev
alu
ate
r
eso
u
r
ce
d
em
an
d
s
o
n
em
b
ed
d
e
d
d
ev
ices o
r
ad
d
r
ess
p
r
iv
ac
y
c
o
n
s
id
er
atio
n
s
f
o
r
o
n
-
d
ev
ice
p
r
o
ce
s
s
in
g
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
with
o
th
e
r
s
tu
d
i
es
M
e
t
h
o
d
Ta
sk
A
c
c
u
r
a
c
y
(
%)
D
e
e
p
r
e
c
u
r
r
e
n
t
h
i
e
r
a
r
c
h
i
c
a
l
n
e
t
w
o
r
k
[
1
9
]
S
p
i
n
e
p
o
st
u
r
e
r
e
c
o
g
n
i
t
i
o
n
w
h
i
l
e
s
i
t
t
i
n
g
9
1
.
4
7
M
e
d
i
a
P
i
p
e
+
d
e
c
i
si
o
n
t
r
e
e
[
2
0
]
R
e
c
o
g
n
i
t
i
o
n
o
f
p
r
o
p
e
r
a
n
d
i
m
p
r
o
p
e
r
s
i
t
t
i
n
g
p
o
st
u
r
e
s
9
1
.
5
a
n
d
9
7
.
0
5
O
p
e
n
P
o
s
e
+
r
a
n
d
o
m
f
o
r
e
s
t
[
2
1
]
H
u
ma
n
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
9
0
.
6
4
M
o
v
e
N
e
t
+
X
G
B
o
o
s
t
(
t
h
i
s
w
o
r
k
)
Er
g
o
n
o
mi
c
s
i
t
t
i
n
g
p
o
s
t
u
r
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
9
3
.
0
2
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
s
u
cc
ess
f
u
lly
d
ev
el
o
p
ed
a
n
d
e
v
alu
ated
a
m
eth
o
d
f
o
r
d
etec
tin
g
an
d
class
if
y
in
g
er
g
o
n
o
m
ic
p
o
s
tu
r
es
u
s
in
g
c
o
m
p
u
ter
v
is
io
n
an
d
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
.
T
h
e
Mo
v
eNe
t
p
o
s
e
esti
m
atio
n
m
o
d
el
was
em
p
lo
y
ed
to
ex
tr
ac
t
k
ey
p
o
in
t
s
f
r
o
m
im
ag
es,
wh
ic
h
wer
e
th
en
p
r
o
ce
s
s
ed
f
o
r
class
if
icatio
n
u
s
in
g
Ad
aBo
o
s
t,
XGBo
o
s
t,
an
d
ML
P
cla
s
s
if
ie
r
s
.
Am
o
n
g
th
e
class
if
ier
s
te
s
ted
,
XGBo
o
s
t
e
s
tab
lis
h
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
F1
-
s
co
r
e,
a
n
d
R
OC
-
AUC,
m
ak
in
g
it
th
e
m
o
s
t
r
eliab
le
f
o
r
o
v
er
all
p
er
f
o
r
m
a
n
ce
.
ML
P
class
if
ier
f
o
llo
wed
b
y
Ad
aBo
o
s
t
u
n
d
er
p
er
f
o
r
m
e
d
ac
r
o
s
s
all
m
etr
ics.
T
h
e
r
esu
lts
in
d
icate
th
at
XGBo
o
s
t
is
ef
f
ec
tiv
e
f
o
r
p
o
s
tu
r
e
class
if
icatio
n
an
d
ca
n
s
u
p
p
o
r
t
h
ea
lth
an
d
s
af
ety
ef
f
o
r
ts
in
s
ed
en
tar
y
wo
r
k
p
lace
s
.
T
h
e
m
o
d
el
co
u
ld
b
e
in
teg
r
ated
i
n
to
s
m
ar
t
o
f
f
ice
s
y
s
tem
s
u
s
in
g
web
ca
m
s
o
r
s
m
all
ed
g
e
-
d
ev
ice
ca
m
er
as
to
d
eliv
er
er
g
o
n
o
m
ic
f
ee
d
b
ac
k
an
d
tr
ig
g
er
ale
r
ts
f
o
r
n
o
n
-
er
g
o
n
o
m
ic
p
o
s
tu
r
es.
Fu
tu
r
e
wo
r
k
m
a
y
r
ef
in
e
th
e
m
o
d
el
an
d
ex
p
an
d
its
ap
p
licatio
n
in
v
ar
io
u
s
wo
r
k
s
ettin
g
s
,
in
clu
d
in
g
c
o
n
tin
u
o
u
s
h
ea
lth
-
m
o
n
ito
r
in
g
s
y
s
tem
s
,
to
h
elp
r
e
d
u
ce
m
u
s
cu
lo
s
k
eleta
l r
is
k
s
an
d
im
p
r
o
v
e
p
r
o
d
u
ctiv
ity
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
e
x
p
r
ess
th
eir
s
in
ce
r
e
g
r
atitu
d
e
t
o
th
e
I
n
d
u
s
tr
ial
T
ec
h
n
o
lo
g
y
L
ab
o
r
ato
r
y
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
Un
iv
e
r
s
itas
Mu
lawa
r
m
an
f
o
r
p
r
o
v
id
i
n
g
th
e
f
ac
ilit
ies an
d
s
u
p
p
o
r
t
f
o
r
d
ata
co
llectio
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
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
T
h
e
r
e
s
i
a
A
m
e
l
ia
P
aw
i
t
r
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Far
id
a
Dju
m
iati Sitan
ia
✓
✓
✓
✓
✓
✓
An
in
d
ita
Sep
tiar
in
i
✓
✓
✓
✓
✓
✓
✓
Ham
d
an
i
Ham
d
an
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
aila
b
le
o
n
r
eq
u
est
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
,
[
T
AP]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
A
u
to
ma
ted
erg
o
n
o
mic
s
itti
n
g
p
o
s
tu
r
es d
etec
tio
n
fo
r
o
ffice
w
o
r
ksta
tio
n
u
s
in
g
…
(
Th
eres
ia
A
melia
P
a
w
itr
a
)
513
RE
F
E
R
E
NC
E
S
[
1
]
H
.
D
a
n
e
s
h
ma
n
d
i
,
A
.
C
h
o
o
b
i
n
e
h
,
H
.
G
h
a
e
m
,
a
n
d
M
.
K
a
r
i
m
i
,
“
A
d
v
e
r
se
e
f
f
e
c
t
s
o
f
p
r
o
l
o
n
g
e
d
si
t
t
i
n
g
b
e
h
a
v
i
o
r
o
n
t
h
e
g
e
n
e
r
a
l
h
e
a
l
t
h
o
f
o
f
f
i
c
e
w
o
r
k
e
r
s,
”
J
o
u
rn
a
l
o
f
L
i
f
e
st
y
l
e
M
e
d
i
c
i
n
e
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
6
9
–
7
5
,
2
0
1
7
,
d
o
i
:
1
0
.
1
5
2
8
0
/
j
l
m.
2
0
1
7
.
7
.
2
.
6
9
.
[
2
]
X
.
Zh
a
n
g
,
P
.
Z
h
e
n
g
,
T
.
P
e
n
g
,
Q
.
H
e
,
C
.
K
.
M
.
Le
e
,
a
n
d
R
.
T
a
n
g
,
“
P
r
o
mo
t
i
n
g
e
m
p
l
o
y
e
e
h
e
a
l
t
h
i
n
s
mart
o
f
f
i
c
e
:
a
s
u
r
v
e
y
,
”
Ad
v
a
n
c
e
d
En
g
i
n
e
e
r
i
n
g
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
5
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
i
.
2
0
2
1
.
1
0
1
5
1
8
.
[
3
]
F
.
F
e
r
a
d
o
v
,
V
.
M
a
r
k
o
v
a
,
a
n
d
T
.
G
a
n
c
h
e
v
,
“
A
u
t
o
ma
t
e
d
d
e
t
e
c
t
i
o
n
o
f
i
mp
r
o
p
e
r
si
t
t
i
n
g
p
o
st
u
r
e
s
i
n
c
o
mp
u
t
e
r
u
s
e
r
s
b
a
s
e
d
o
n
mo
t
i
o
n
c
a
p
t
u
r
e
s
e
n
s
o
r
s,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
1
1
,
n
o
.
7
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
e
r
s
1
1
0
7
0
1
1
6
.
[
4
]
C
.
S
o
a
r
e
s,
S
.
G
.
N
.
S
h
i
m
a
n
o
,
P
.
R
.
M
a
r
c
a
c
i
n
e
,
L.
F
.
R
.
M
.
F
e
r
n
a
n
d
e
s,
L.
L.
P
.
T.
d
e
C
a
s
t
r
o
,
a
n
d
I
.
A
.
P
.
d
e
W
a
l
s
h
,
“
Er
g
o
n
o
mi
c
i
n
t
e
r
v
e
n
t
i
o
n
s
f
o
r
w
o
r
k
i
n
a
si
t
t
i
n
g
p
o
si
t
i
o
n
:
a
n
i
n
t
e
g
r
a
t
i
v
e
r
e
v
i
e
w
,
”
Re
v
i
s
t
a
Br
a
si
l
e
i
ra
d
e
M
e
d
i
c
i
n
a
d
o
T
r
a
b
a
l
h
o
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
1
–
1
0
,
2
0
2
3
,
d
o
i
:
1
0
.
4
7
6
2
6
/
1
6
7
9
-
4
4
3
5
-
2
0
2
3
-
7
7
0
.
[
5
]
N
.
V
i
n
c
e
n
t
,
M
.
N
.
C
,
K
.
P
.
-
G
.
D
,
a
n
d
S
.
E.
O
,
“
P
r
o
l
o
n
g
s
i
t
t
i
n
g
:
a
m
e
t
a
b
o
l
i
c
h
e
a
l
t
h
r
i
s
k
a
m
o
n
g
w
h
i
t
e
-
c
o
l
l
a
r
w
o
r
k
e
r
s
:
a
r
e
v
i
e
w
a
r
t
i
c
l
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
f
o
r
R
e
s
e
a
r
c
h
i
n
Ap
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
1
,
n
o
.
7
,
p
p
.
1
9
3
2
–
1
9
3
8
,
2
0
2
3
,
d
o
i
:
1
0
.
2
2
2
1
4
/
i
j
r
a
s
e
t
.
2
0
2
3
.
5
5
0
0
5
.
[
6
]
Y
.
Zh
a
o
,
C
.
S
u
n
,
X
.
X
u
,
a
n
d
J.
C
h
e
n
,
“
R
I
C
-
N
e
t
:
a
p
l
a
n
t
d
i
se
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
m
o
d
e
l
b
a
s
e
d
o
n
t
h
e
f
u
s
i
o
n
o
f
I
n
c
e
p
t
i
o
n
a
n
d
r
e
s
i
d
u
a
l
st
r
u
c
t
u
r
e
a
n
d
e
m
b
e
d
d
e
d
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
s
m,”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ro
n
i
c
s
i
n
Ag
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
9
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
1
.
1
0
6
6
4
4
.
[
7
]
H
.
Ji
,
J.
X
i
e
,
a
n
d
P
.
S
u
n
,
“
A
l
i
g
h
t
w
e
i
g
h
t
I
o
T
d
e
v
i
c
e
-
f
r
i
e
n
d
l
y
a
n
o
ma
l
y
si
t
t
i
n
g
p
o
s
t
u
r
e
d
e
t
e
c
t
o
r
f
o
r
p
r
o
t
e
c
t
i
n
g
a
d
o
l
e
sce
n
t
b
o
n
e
d
e
v
e
l
o
p
me
n
t
,
”
i
n
2
0
2
3
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
s
o
n
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
(
i
T
h
i
n
g
s)
a
n
d
I
EE
E
G
re
e
n
C
o
m
p
u
t
i
n
g
&
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
G
r
e
e
n
C
o
m
)
a
n
d
I
E
EE
C
y
b
e
r,
P
h
y
s
i
c
a
l
& S
o
c
i
a
l
C
o
m
p
u
t
i
n
g
(
C
PS
C
o
m
)
a
n
d
I
EE
E
S
m
a
r
t
D
a
t
a
(
S
m
a
r
t
D
a
t
a
)
a
n
d
I
EEE
C
o
n
g
r
e
ss
o
n
C
y
b
e
rm
a
t
i
c
s
(
C
y
b
e
rm
a
t
i
c
s)
,
2
0
2
3
,
p
p
.
2
3
3
–
2
3
8
,
d
o
i
:
1
0
.
1
1
0
9
/
i
t
h
i
n
g
s
-
g
r
e
e
n
c
o
m
-
c
p
sco
m
-
sm
a
r
t
d
a
t
a
-
c
y
b
e
r
ma
t
i
c
s
6
0
7
2
4
.
2
0
2
3
.
0
0
0
5
9
.
[
8
]
H
.
Je
o
n
g
a
n
d
W
.
P
a
r
k
,
“
D
e
v
e
l
o
p
i
n
g
a
n
d
e
v
a
l
u
a
t
i
n
g
a
mi
x
e
d
se
n
so
r
s
mart
c
h
a
i
r
s
y
st
e
m
f
o
r
r
e
a
l
-
t
i
me
p
o
s
t
u
r
e
c
l
a
ssi
f
i
c
a
t
i
o
n
:
c
o
m
b
i
n
i
n
g
p
r
e
ss
u
r
e
a
n
d
d
i
s
t
a
n
c
e
se
n
so
r
s,”
I
EEE
J
o
u
r
n
a
l
o
f
Bi
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
5
,
n
o
.
5
,
p
p
.
1
8
0
5
–
1
8
1
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
j
b
h
i
.
2
0
2
0
.
3
0
3
0
0
9
6
.
[
9
]
F
.
L
.
-
P
e
r
e
j
ó
n
,
J
.
M
.
M
.
-
S
á
n
c
h
e
z
,
L.
D
.
-
Ló
p
e
z
,
A
.
V
.
-
B
a
e
z
a
,
I
.
B
.
-
B
o
h
ó
r
q
u
e
z
,
a
n
d
J.
L.
S
.
-
R
a
mo
s
,
“
I
o
T
d
e
v
i
c
e
f
o
r
si
t
t
i
n
g
p
o
st
u
r
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
El
e
c
t
ro
n
i
c
s
,
v
o
l
.
1
0
,
n
o
.
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
0
1
5
1
8
2
5
.
[
1
0
]
T.
A
.
G
e
l
a
w
a
n
d
M
.
T
.
H
a
g
o
s
,
“
P
o
st
u
r
e
p
r
e
d
i
c
t
i
o
n
f
o
r
h
e
a
l
t
h
y
s
i
t
t
i
n
g
u
s
i
n
g
a
smar
t
c
h
a
i
r
,
”
i
n
A
d
v
a
n
c
e
s o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
(
I
C
AS
T
2
0
2
1
)
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
2
2
,
p
p
.
4
0
1
–
4
1
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
9
3
7
0
9
-
6
_
2
6
.
[
1
1
]
S.
-
M
.
L
e
e
,
H
.
-
J.
K
i
m,
S
.
-
J.
H
a
m,
a
n
d
S
.
K
i
m,
“
A
ssi
s
t
i
v
e
d
e
v
i
c
e
s t
o
h
e
l
p
c
o
r
r
e
c
t
s
i
t
t
i
n
g
-
p
o
st
u
r
e
b
a
s
e
d
o
n
p
o
s
t
u
r
e
a
n
a
l
y
s
i
s
r
e
s
u
l
t
s,
”
J
O
I
V
:
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
I
n
f
o
r
m
a
t
i
c
s
Vi
s
u
a
l
i
z
a
t
i
o
n
,
v
o
l
.
5
,
n
o
.
3
,
p
p
.
3
4
0
–
3
4
6
,
2
0
2
1
,
d
o
i
:
1
0
.
3
0
6
3
0
/
j
o
i
v
.
5
.
3
.
6
7
3
.
[
1
2
]
L.
Zh
o
u
,
L.
Z
h
a
n
g
,
a
n
d
N
.
K
o
n
z
,
“
C
o
m
p
u
t
e
r
v
i
s
i
o
n
t
e
c
h
n
i
q
u
e
s
i
n
ma
n
u
f
a
c
t
u
r
i
n
g
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
S
y
st
e
m
s,
M
a
n
,
a
n
d
C
y
b
e
r
n
e
t
i
c
s:
S
y
st
e
m
s
,
v
o
l
.
5
3
,
n
o
.
1
,
p
p
.
1
0
5
–
1
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
t
smc
.
2
0
2
2
.
3
1
6
6
3
9
7
.
[
1
3
]
N
.
F
.
Z
u
l
k
u
r
n
a
i
n
,
Y
.
A
.
A
h
m
a
d
,
a
n
d
N
.
A
.
M
.
N
a
z
r
i
,
“
W
e
b
-
b
a
s
e
d
saf
e
t
y
e
y
e
w
e
a
r
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
i
n
w
o
r
k
p
l
a
c
e
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
2
0
2
3
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
En
g
i
n
e
e
ri
n
g
(
I
C
C
C
E)
,
2
0
2
3
,
p
p
.
2
8
9
–
293
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
c
c
e
5
8
8
5
4
.
2
0
2
3
.
1
0
2
4
6
0
8
7
.
[
1
4
]
B.
-
T.
N
g
u
y
e
n
-
Ta
t
,
M
.
-
Q
.
B
u
i
,
a
n
d
V
.
M
.
N
g
o
,
“
A
u
t
o
m
a
t
i
n
g
a
t
t
e
n
d
a
n
c
e
m
a
n
a
g
e
me
n
t
i
n
h
u
ma
n
r
e
s
o
u
r
c
e
s:
a
d
e
s
i
g
n
sc
i
e
n
c
e
a
p
p
r
o
a
c
h
u
si
n
g
c
o
m
p
u
t
e
r
v
i
s
i
o
n
a
n
d
f
a
c
i
a
l
r
e
c
o
g
n
i
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
I
n
f
o
rm
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
D
a
t
a
I
n
si
g
h
t
s
,
v
o
l
.
4
,
n
o
.
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
j
i
m
e
i
.
2
0
2
4
.
1
0
0
2
5
3
.
[
1
5
]
H
.
B
.
K
h
o
i
r
u
l
l
a
h
,
N
.
Y
u
d
i
s
t
i
r
a
,
a
n
d
F
.
A
.
B
a
c
h
t
i
a
r
,
“
F
a
c
i
a
l
e
x
p
r
e
s
s
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
a
t
t
e
n
t
i
o
n
m
o
d
u
l
e
,
”
J
O
I
V
:
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
I
n
f
o
r
m
a
t
i
c
s
V
i
s
u
a
l
i
z
a
t
i
o
n
,
v
o
l
.
6
,
n
o
.
4
,
p
p
.
8
9
7
–
9
0
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
0
6
3
0
/
j
o
i
v
.
6
.
4
.
9
6
3
.
[
1
6
]
C
.
H
.
B
o
e
,
K
.
-
W
.
N
g
,
S
.
-
C
.
H
a
w
,
P
.
N
a
v
e
e
n
,
a
n
d
E.
A
.
A
n
a
a
m,
“
A
n
a
u
t
o
m
a
t
e
d
f
a
c
e
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
f
o
r
c
l
a
s
s
a
t
t
e
n
d
a
n
c
e
,
”
J
O
I
V
:
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
I
n
f
o
r
m
a
t
i
c
s
V
i
s
u
a
l
i
z
a
t
i
o
n
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
1
1
4
6
–
1
1
5
3
,
2
0
2
4
,
d
o
i
:
1
0
.
6
2
5
2
7
/
j
o
i
v
.
8
.
3
.
2
9
6
7
.
[
1
7
]
J.
P
a
u
l
,
A
.
M
i
t
r
a
,
D
.
K
u
l
h
a
d
i
y
a
,
T.
P
a
w
a
r
,
A
.
R
o
y
,
a
n
d
J.
S
i
l
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
a
p
p
r
o
a
c
h
t
o
r
e
a
l
-
t
i
me
a
t
t
e
n
d
a
n
c
e
s
y
st
e
ms:
i
n
t
e
g
r
a
t
i
n
g
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
a
n
d
e
m
o
t
i
o
n
d
e
t
e
c
t
i
o
n
a
n
d
w
i
t
h
w
e
b
t
e
c
h
n
o
l
o
g
i
e
s
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
5
8
,
n
o
.
2
,
p
p
.
3
4
3
6
–
3
4
4
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
5
.
0
4
.
6
0
0
.
[
1
8
]
V
.
A
d
e
w
o
p
o
e
t
a
l
.
,
“
B
i
g
d
a
t
a
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
i
n
sm
a
r
t
c
i
t
i
e
s
:
a
c
o
m
p
r
e
h
e
n
si
v
e
d
a
t
a
s
e
t
f
o
r
A
I
-
d
r
i
v
e
n
t
r
a
f
f
i
c
a
c
c
i
d
e
n
t
d
e
t
e
c
t
i
o
n
a
n
d
c
o
m
p
u
t
e
r
v
i
si
o
n
sy
s
t
e
m
s,”
i
n
2
0
2
4
I
EE
E
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
i
n
g
a
n
d
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
(
I
C
MI)
,
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
m
i
6
0
7
9
0
.
2
0
2
4
.
1
0
5
8
6
0
7
3
.
[
1
9
]
A
.
K
u
l
i
k
a
j
e
v
a
s
,
R
.
M
a
sk
e
l
i
u
n
a
s,
a
n
d
R
.
D
a
m
a
še
v
i
č
i
u
s,
“
D
e
t
e
c
t
i
o
n
o
f
si
t
t
i
n
g
p
o
s
t
u
r
e
u
si
n
g
h
i
e
r
a
r
c
h
i
c
a
l
i
ma
g
e
c
o
m
p
o
si
t
i
o
n
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
P
e
e
r
J
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
2
0
2
1
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s.4
4
2
.
[
2
0
]
J.
E.
Es
t
r
a
d
a
,
L.
A
.
V
e
a
,
a
n
d
M
.
D
e
v
a
r
a
j
,
“
M
o
d
e
l
l
i
n
g
p
r
o
p
e
r
a
n
d
i
m
p
r
o
p
e
r
si
t
t
i
n
g
p
o
st
u
r
e
o
f
c
o
mp
u
t
e
r
u
sers u
si
n
g
ma
c
h
i
n
e
v
i
s
i
on
f
o
r
a
h
u
ma
n
–
c
o
mp
u
t
e
r
i
n
t
e
l
l
i
g
e
n
t
i
n
t
e
r
a
c
t
i
v
e
s
y
st
e
m
d
u
r
i
n
g
C
O
V
I
D
-
1
9
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
9
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
9
5
4
0
2
.
[
2
1
]
P.
-
C
.
L
i
n
,
Y
.
-
J
.
C
h
e
n
,
W
.
-
S
.
C
h
e
n
,
a
n
d
Y
.
-
J.
Le
e
,
“
A
u
t
o
m
a
t
i
c
r
e
a
l
-
t
i
m
e
o
c
c
u
p
a
t
i
o
n
a
l
p
o
st
u
r
e
e
v
a
l
u
a
t
i
o
n
a
n
d
se
l
e
c
t
c
o
r
r
e
s
p
o
n
d
i
n
g
e
r
g
o
n
o
mi
c
a
ssessm
e
n
t
s,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
2
-
0
5
8
1
2
-
9.
[
2
2
]
S
.
R
e
i
d
,
S
.
C
o
l
e
ma
n
,
D
.
K
e
r
r
,
P
.
V
a
n
c
e
,
a
n
d
S
.
O
’
N
e
i
l
l
,
“
K
e
y
p
o
i
n
t
c
h
a
n
g
e
s
f
o
r
f
a
s
t
h
u
m
a
n
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
,
”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
4
,
n
o
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
2
9
7
9
-
023
-
0
2
0
6
3
-
x.
[
2
3
]
I
.
A
k
h
t
e
r
,
A
.
Ja
l
a
l
,
a
n
d
K
.
K
i
m,
“
P
o
s
e
e
st
i
ma
t
i
o
n
a
n
d
d
e
t
e
c
t
i
o
n
f
o
r
e
v
e
n
t
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
s
e
n
se
-
a
w
a
r
e
f
e
a
t
u
r
e
s
a
n
d
A
d
a
B
o
o
st
c
l
a
ss
i
f
i
e
r
,
”
i
n
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
Bh
u
rb
a
n
C
o
n
f
e
r
e
n
c
e
o
n
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
a
n
d
T
e
c
h
n
o
l
o
g
i
e
s
(
I
B
C
AS
T
)
,
2
0
2
1
,
p
p
.
5
0
0
–
5
0
5
,
d
o
i
:
1
0
.
1
1
0
9
/
i
b
c
a
s
t
5
1
2
5
4
.
2
0
2
1
.
9
3
9
3
2
9
3
.
[
2
4
]
J.
G
a
o
,
C
.
M
a
,
D
.
W
u
,
X
.
X
u
,
S
.
W
a
n
g
,
a
n
d
J
.
Y
a
o
,
“
R
e
c
o
g
n
i
t
i
o
n
o
f
h
u
m
a
n
m
o
t
i
o
n
i
n
t
e
n
t
i
o
n
s
b
a
se
d
o
n
B
a
y
e
s
i
a
n
-
o
p
t
i
mi
z
e
d
X
G
B
o
o
st
a
l
g
o
r
i
t
h
m
,
”
J
o
u
r
n
a
l
o
f
S
e
n
s
o
rs
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
3
0
1
5
6
4
5
.
[
2
5
]
Y
.
F
a
n
g
,
S
.
S
h
i
,
J.
F
a
n
g
,
a
n
d
W
.
Y
i
n
,
“
S
P
R
N
e
t
:
si
t
t
i
n
g
p
o
st
u
r
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
i
m
p
r
o
v
e
d
v
i
s
i
o
n
t
r
a
n
sf
o
r
mer,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
N
e
u
ra
l
N
e
t
w
o
rks
(
I
J
C
N
N
)
,
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
j
c
n
n
5
5
0
6
4
.
2
0
2
2
.
9
8
9
2
0
2
1
.
[
2
6
]
S
.
H
a
n
c
h
i
n
a
m
a
n
i
,
P
.
Ti
g
a
d
i
,
P
.
P
u
t
t
a
n
a
v
v
a
r
,
D
.
P
a
t
i
l
k
u
l
k
a
r
n
i
,
a
n
d
P
.
P
a
t
i
l
,
“
I
n
t
e
g
r
a
t
i
n
g
k
e
y
f
r
a
me
e
x
t
r
a
c
t
i
o
n
a
n
d
M
o
v
e
N
e
t
t
h
u
n
d
e
r
f
o
r
r
o
b
u
st
v
i
d
e
o
p
o
se
e
s
t
i
m
a
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
2
0
2
4
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
f
o
r
Em
e
r
g
i
n
g
T
e
c
h
n
o
l
o
g
y
(
I
N
C
ET)
,
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
n
c
e
t
6
1
5
1
6
.
2
0
2
4
.
1
0
5
9
3
2
3
6
.
[
2
7
]
A
.
S
a
b
o
,
N
.
M
i
t
t
a
l
,
A
.
D
e
s
h
p
a
n
d
e
,
H
.
C
l
a
r
k
e
,
a
n
d
B
.
Ta
a
t
i
,
“
A
u
t
o
m
a
t
e
d
,
v
i
s
i
o
n
-
b
a
se
d
g
o
n
i
o
me
t
r
y
a
n
d
r
a
n
g
e
o
f
m
o
t
i
o
n
c
a
l
c
u
l
a
t
i
o
n
i
n
i
n
d
i
v
i
d
u
a
l
s
w
i
t
h
s
u
s
p
e
c
t
e
d
E
h
l
e
r
s
-
D
a
n
l
o
s
s
y
n
d
r
o
m
e
s/
g
e
n
e
r
a
l
i
z
e
d
h
y
p
e
r
mo
b
i
l
i
t
y
sp
e
c
t
r
u
m
d
i
so
r
d
e
r
s:
a
c
o
m
p
a
r
i
s
o
n
o
f
p
o
s
e
-
e
st
i
mat
i
o
n
l
i
b
r
a
r
i
e
s
t
o
g
o
n
i
o
me
t
r
i
c
m
e
a
s
u
r
e
me
n
t
s
,
”
I
EEE
J
o
u
rn
a
l
o
f
T
ra
n
s
l
a
t
i
o
n
a
l
E
n
g
i
n
e
e
ri
n
g
i
n
H
e
a
l
t
h
a
n
d
Me
d
i
c
i
n
e
,
v
o
l
.
1
2
,
p
p
.
1
4
0
–
1
5
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
j
t
e
h
m.2
0
2
3
.
3
3
2
7
6
9
1
.
[
2
8
]
B
.
J
o
a
n
d
S
.
K
i
m,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
O
p
e
n
P
o
s
e
,
P
o
seN
e
t
,
a
n
d
M
o
v
e
N
e
t
m
o
d
e
l
s
f
o
r
p
o
se
e
s
t
i
m
a
t
i
o
n
i
n
mo
b
i
l
e
d
e
v
i
c
e
s
,
”
T
ra
i
t
e
m
e
n
t
d
u
S
i
g
n
a
l
,
v
o
l
.
3
9
,
n
o
.
1
,
p
p
.
1
1
9
–
1
2
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
8
2
8
0
/
t
s.
3
9
0
1
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
506
-
5
1
4
514
[
2
9
]
X
.
Zh
a
n
g
,
J.
F
a
n
,
T.
P
e
n
g
,
P
.
Zh
e
n
g
,
X
.
Zh
a
n
g
,
a
n
d
R
.
T
a
n
g
,
“
M
u
l
t
i
m
o
d
a
l
d
a
t
a
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
si
t
t
i
n
g
p
o
s
t
u
r
e
r
e
c
o
g
n
i
t
i
o
n
t
o
w
a
r
d
o
f
f
i
c
e
w
o
r
k
e
r
s’
h
e
a
l
t
h
p
r
o
m
o
t
i
o
n
,
”
S
e
n
s
o
rs
a
n
d
A
c
t
u
a
t
o
rs
A:
Ph
y
si
c
a
l
,
v
o
l
.
3
5
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
n
a
.
2
0
2
2
.
1
1
4
1
5
0
.
[
3
0
]
M
.
R
.
C
a
r
d
o
s
o
,
A
.
K
.
C
a
r
d
e
n
a
s,
a
n
d
W
.
J
.
A
l
b
e
r
t
,
“
A
b
i
o
m
e
c
h
a
n
i
c
a
l
a
n
a
l
y
s
i
s
o
f
a
c
t
i
v
e
v
s
st
a
t
i
c
o
f
f
i
c
e
c
h
a
i
r
d
e
s
i
g
n
s,
”
A
p
p
l
i
e
d
Erg
o
n
o
m
i
c
s
,
v
o
l
.
9
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
e
r
g
o
.
2
0
2
1
.
1
0
3
4
8
1
.
[
3
1
]
E.
W
e
st
o
n
,
P
.
Le
,
a
n
d
W
.
S
.
M
a
r
r
a
s
,
“
A
b
i
o
me
c
h
a
n
i
c
a
l
a
n
d
p
h
y
s
i
o
l
o
g
i
c
a
l
st
u
d
y
o
f
o
f
f
i
c
e
s
e
a
t
a
n
d
t
a
b
l
e
t
d
e
v
i
c
e
i
n
t
e
r
a
c
t
i
o
n
,
”
Ap
p
l
i
e
d
Er
g
o
n
o
m
i
c
s
,
v
o
l
.
6
2
,
p
p
.
8
3
–
9
3
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
p
e
r
g
o
.
2
0
1
7
.
0
2
.
0
1
3
.
[
3
2
]
S
.
B
e
n
g
h
a
z
o
u
a
n
i
,
S
.
N
o
u
h
,
a
n
d
A
.
Za
k
r
a
n
i
,
“
E
n
h
a
n
c
i
n
g
b
r
e
a
s
t
c
a
n
c
e
r
d
i
a
g
n
o
si
s
:
a
c
o
m
p
a
r
a
t
i
v
e
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
t
e
c
h
n
i
q
u
e
s,
”
I
AES
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
4
3
1
2
–
4
3
2
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
4
.
p
p
4
3
1
2
-
4
3
2
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Th
e
r
e
sia
Am
e
li
a
P
a
witr
a
is
c
u
rre
n
tl
y
a
f
u
ll
-
t
ime
lec
tu
re
r
in
t
h
e
De
p
a
rtme
n
t
o
f
In
d
u
strial
En
g
in
e
e
rin
g
a
t
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
M
u
law
a
rm
a
n
Un
iv
e
rsit
y
in
S
a
m
a
rin
d
a
.
S
h
e
c
o
m
p
lete
d
h
e
r
u
n
d
e
rg
ra
d
u
a
te
stu
d
ies
a
t
t
h
e
U
n
iv
e
rsit
y
o
f
S
u
ra
b
a
y
a
a
n
d
p
u
rsu
e
d
h
e
r
m
a
ste
r’s
d
e
g
re
e
s
(M
a
ste
r
o
f
S
c
ien
c
e
a
n
d
M
a
ste
r
o
f
E
n
g
in
e
e
rin
g
)
a
t
Na
ti
o
n
a
l
Un
iv
e
rsit
y
o
f
S
in
g
a
p
o
re
i
n
th
e
De
p
a
rtme
n
t
o
f
I
n
d
u
strial
a
n
d
S
y
ste
m
s
En
g
i
n
e
e
rin
g
.
He
r
re
se
a
rc
h
in
tere
sts
a
re
in
e
rg
o
n
o
m
ics
,
se
rv
ice
m
a
n
a
g
e
m
e
n
t
,
a
n
d
o
c
c
u
p
a
ti
o
n
a
l
sa
fe
ty
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
tri
c
iap
a
witra@g
m
a
il
.
c
o
m
.
Fa
r
id
a
Dj
u
m
i
a
ti
S
it
a
n
i
a
is a l
e
c
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
In
d
u
strial
En
g
i
n
e
e
rin
g
a
t
M
u
law
a
rm
a
n
Un
iv
e
rsity
,
In
d
o
n
e
sia
.
S
h
e
o
b
tai
n
e
d
h
e
r
Ba
c
h
e
lo
r
o
f
En
g
i
n
e
e
rin
g
(S
.
T
.
)
d
e
g
re
e
in
2
0
2
3
fr
o
m
In
sti
tu
t
Tek
n
o
l
o
g
i
S
e
p
u
l
u
h
N
o
v
e
m
b
e
r,
S
u
ra
b
a
y
a
.
I
n
2
0
0
9
,
s
h
e
c
o
m
p
lete
d
h
e
r
m
a
ste
r’s
p
ro
g
ra
m
in
In
d
u
str
ial
En
g
i
n
e
e
rin
g
a
n
d
M
a
n
a
g
e
m
e
n
t
with
a
sp
e
c
ializa
ti
o
n
in
m
a
n
u
fa
c
tu
rin
g
e
n
g
i
n
e
e
rin
g
fr
o
m
In
stit
u
t
Te
k
n
o
lo
g
i
Ba
n
d
u
n
g
.
S
h
e
a
c
ti
v
e
ly
e
n
g
a
g
e
s
in
re
se
a
rc
h
a
n
d
tea
c
h
in
g
i
n
th
e
f
ield
s
o
f
p
r
o
d
u
c
ti
o
n
p
la
n
n
i
n
g
a
n
d
c
o
n
tr
o
l,
m
a
in
ten
a
n
c
e
m
a
n
a
g
e
m
e
n
t,
a
n
d
lea
n
m
a
n
u
fa
c
tu
rin
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
i
d
a
.
sitan
ia@
g
m
a
il
.
c
o
m
.
Ani
n
d
it
a
S
e
p
t
ia
r
in
i
is
a
p
r
o
fe
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
c
s
a
t
M
u
law
a
rm
a
n
Un
i
v
e
rsity
,
In
d
o
n
e
sia
.
S
h
e
h
o
ld
s
a
d
o
c
to
ra
l
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
G
a
d
jah
M
a
d
a
Un
iv
e
rsit
y
,
I
n
d
o
n
e
sia
,
sp
e
c
ializin
g
in
ima
g
e
a
n
a
ly
s
is.
S
h
e
is
a
lso
a
re
se
a
rc
h
e
r
a
n
d
g
o
t
a
g
ra
n
t
fr
o
m
th
e
M
in
i
stry
o
f
Ed
u
c
a
ti
o
n
,
C
u
lt
u
re
,
Re
s
e
a
rc
h
,
a
n
d
Tec
h
n
o
l
o
g
y
o
f
In
d
o
n
e
sia
fro
m
2
0
1
6
u
n
t
il
t
h
e
p
re
se
n
t.
He
r
re
se
a
rc
h
in
tere
sts
l
ie
in
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
e
sp
e
c
ially
p
a
tt
e
rn
re
c
o
g
n
i
ti
o
n
,
i
m
a
g
e
p
ro
c
e
ss
in
g
,
a
n
d
c
o
m
p
u
ter
v
isio
n
.
S
h
e
h
a
s
re
c
e
iv
e
d
n
a
ti
o
n
a
l
a
wa
rd
s
s
u
c
h
a
s
sc
ien
ti
fi
c
a
rti
c
le
in
c
e
n
t
iv
e
s
fr
o
m
t
h
e
M
in
istry
o
f
Ed
u
c
a
ti
o
n
,
C
u
lt
u
re
,
Re
se
a
rc
h
,
a
n
d
Tec
h
n
o
l
o
g
y
o
f
In
d
o
n
e
sia
i
n
2
0
1
7
a
n
d
2
0
1
9
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
in
d
it
a
@u
n
m
u
l.
a
c
.
id
.
H
a
m
d
a
n
i
H
a
m
d
a
n
i
is
a
p
ro
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
ti
c
s
a
t
M
u
law
a
rm
a
n
Un
iv
e
rsity
,
I
n
d
o
n
e
sia
.
He
is
a
le
c
tu
re
r
a
n
d
re
se
a
rc
h
e
r
sin
c
e
2
0
0
5
a
t
M
u
law
a
rm
a
n
Un
i
v
e
rsity
,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
li
e
in
th
e
field
o
f
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
e
sp
e
c
ially
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
d
e
c
isio
n
su
p
p
o
rt
sy
st
e
m
,
a
n
d
e
x
p
e
rt
sy
ste
m
.
He
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
in
2
0
0
2
fr
o
m
Un
iv
e
rsitas
Ah
m
a
d
Da
h
lan
,
In
d
o
n
e
sia
,
h
is
m
a
ste
r’s
d
e
g
re
e
in
2
0
0
9
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
a
n
d
h
e
r
d
o
c
to
ra
l
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
in
2
0
1
8
fro
m
Un
i
v
e
rsitas
G
a
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
m
d
a
n
i@u
n
m
u
l.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.